diff options
Diffstat (limited to 'arch/x86')
206 files changed, 2452 insertions, 2117 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 3762f41bb092..53f2e7797b1d 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -88,6 +88,7 @@ config X86 select ARCH_HAS_PMEM_API if X86_64 select ARCH_HAS_PTE_DEVMAP if X86_64 select ARCH_HAS_PTE_SPECIAL + select ARCH_HAS_HW_PTE_YOUNG select ARCH_HAS_NONLEAF_PMD_YOUNG if PGTABLE_LEVELS > 2 select ARCH_HAS_UACCESS_FLUSHCACHE if X86_64 select ARCH_HAS_COPY_MC if X86_64 @@ -169,7 +170,7 @@ config X86 select HAS_IOPORT select HAVE_ACPI_APEI if ACPI select HAVE_ACPI_APEI_NMI if ACPI - select HAVE_ALIGNED_STRUCT_PAGE if SLUB + select HAVE_ALIGNED_STRUCT_PAGE select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_HUGE_VMAP if X86_64 || X86_PAE select HAVE_ARCH_HUGE_VMALLOC if X86_64 @@ -384,10 +385,6 @@ config HAVE_INTEL_TXT def_bool y depends on INTEL_IOMMU && ACPI -config X86_32_SMP - def_bool y - depends on X86_32 && SMP - config X86_64_SMP def_bool y depends on X86_64 && SMP @@ -1415,7 +1412,7 @@ config HIGHMEM4G config HIGHMEM64G bool "64GB" - depends on !M486SX && !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !MWINCHIP3D && !MK6 + depends on X86_HAVE_PAE select X86_PAE help Select this if you have a 32-bit processor and more than 4 @@ -1472,7 +1469,7 @@ config HIGHMEM config X86_PAE bool "PAE (Physical Address Extension) Support" - depends on X86_32 && !HIGHMEM4G + depends on X86_32 && X86_HAVE_PAE select PHYS_ADDR_T_64BIT select SWIOTLB help @@ -2072,7 +2069,7 @@ config ARCH_SUPPORTS_KEXEC def_bool y config ARCH_SUPPORTS_KEXEC_FILE - def_bool X86_64 && CRYPTO && CRYPTO_SHA256 + def_bool X86_64 config ARCH_SELECTS_KEXEC_FILE def_bool y @@ -2080,7 +2077,7 @@ config ARCH_SELECTS_KEXEC_FILE select HAVE_IMA_KEXEC if IMA config ARCH_SUPPORTS_KEXEC_PURGATORY - def_bool KEXEC_FILE + def_bool y config ARCH_SUPPORTS_KEXEC_SIG def_bool y diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 00468adf180f..b9224cf2ee4d 100644 --- a/arch/x86/Kconfig.cpu +++ b/arch/x86/Kconfig.cpu @@ -362,9 +362,13 @@ config X86_TSC def_bool y depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64 +config X86_HAVE_PAE + def_bool y + depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC7 || MCORE2 || MATOM || X86_64 + config X86_CMPXCHG64 def_bool y - depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 + depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7 # this should be set for all -march=.. options where the compiler # generates cmov. diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 71fc531b95b4..f19c038409aa 100644 --- a/arch/x86/boot/compressed/Makefile +++ b/arch/x86/boot/compressed/Makefile @@ -53,7 +53,7 @@ KBUILD_CFLAGS += -D__DISABLE_EXPORTS KBUILD_CFLAGS += $(call cc-option,-Wa$(comma)-mrelax-relocations=no) KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h -# sev.c indirectly inludes inat-table.h which is generated during +# sev.c indirectly includes inat-table.h which is generated during # compilation and stored in $(objtree). Add the directory to the includes so # that the compiler finds it even with out-of-tree builds (make O=/some/path). CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/ diff --git a/arch/x86/boot/compressed/acpi.c b/arch/x86/boot/compressed/acpi.c index 55c98fdd67d2..18d15d1ce87d 100644 --- a/arch/x86/boot/compressed/acpi.c +++ b/arch/x86/boot/compressed/acpi.c @@ -178,7 +178,7 @@ static unsigned long get_cmdline_acpi_rsdp(void) { unsigned long addr = 0; -#ifdef CONFIG_KEXEC +#ifdef CONFIG_KEXEC_CORE char val[MAX_ADDR_LEN] = { }; int ret; diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c index 473ba59b82a8..d040080d7edb 100644 --- a/arch/x86/boot/compressed/ident_map_64.c +++ b/arch/x86/boot/compressed/ident_map_64.c @@ -386,3 +386,8 @@ void do_boot_page_fault(struct pt_regs *regs, unsigned long error_code) */ kernel_add_identity_map(address, end); } + +void do_boot_nmi_trap(struct pt_regs *regs, unsigned long error_code) +{ + /* Empty handler to ignore NMI during early boot */ +} diff --git a/arch/x86/boot/compressed/idt_64.c b/arch/x86/boot/compressed/idt_64.c index 3cdf94b41456..d100284bbef4 100644 --- a/arch/x86/boot/compressed/idt_64.c +++ b/arch/x86/boot/compressed/idt_64.c @@ -61,6 +61,7 @@ void load_stage2_idt(void) boot_idt_desc.address = (unsigned long)boot_idt; set_idt_entry(X86_TRAP_PF, boot_page_fault); + set_idt_entry(X86_TRAP_NMI, boot_nmi_trap); #ifdef CONFIG_AMD_MEM_ENCRYPT /* diff --git a/arch/x86/boot/compressed/idt_handlers_64.S b/arch/x86/boot/compressed/idt_handlers_64.S index 22890e199f5b..4d03c8562f63 100644 --- a/arch/x86/boot/compressed/idt_handlers_64.S +++ b/arch/x86/boot/compressed/idt_handlers_64.S @@ -70,6 +70,7 @@ SYM_FUNC_END(\name) .code64 EXCEPTION_HANDLER boot_page_fault do_boot_page_fault error_code=1 +EXCEPTION_HANDLER boot_nmi_trap do_boot_nmi_trap error_code=0 #ifdef CONFIG_AMD_MEM_ENCRYPT EXCEPTION_HANDLER boot_stage1_vc do_vc_no_ghcb error_code=1 diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index b3c3a4be7471..dbba332e4a12 100644 --- a/arch/x86/boot/compressed/mem.c +++ b/arch/x86/boot/compressed/mem.c @@ -8,7 +8,7 @@ /* * accept_memory() and process_unaccepted_memory() called from EFI stub which - * runs before decompresser and its early_tdx_detect(). + * runs before decompressor and its early_tdx_detect(). * * Enumerate TDX directly from the early users. */ diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h index c0d502bd8716..bc2f0f17fb90 100644 --- a/arch/x86/boot/compressed/misc.h +++ b/arch/x86/boot/compressed/misc.h @@ -196,6 +196,7 @@ static inline void cleanup_exception_handling(void) { } /* IDT Entry Points */ void boot_page_fault(void); +void boot_nmi_trap(void); void boot_stage1_vc(void); void boot_stage2_vc(void); diff --git a/arch/x86/boot/pm.c b/arch/x86/boot/pm.c index 40031a614712..5941f930f6c5 100644 --- a/arch/x86/boot/pm.c +++ b/arch/x86/boot/pm.c @@ -11,6 +11,7 @@ */ #include "boot.h" +#include <asm/desc_defs.h> #include <asm/segment.h> /* @@ -67,13 +68,13 @@ static void setup_gdt(void) being 8-byte unaligned. Intel recommends 16 byte alignment. */ static const u64 boot_gdt[] __attribute__((aligned(16))) = { /* CS: code, read/execute, 4 GB, base 0 */ - [GDT_ENTRY_BOOT_CS] = GDT_ENTRY(0xc09b, 0, 0xfffff), + [GDT_ENTRY_BOOT_CS] = GDT_ENTRY(DESC_CODE32, 0, 0xfffff), /* DS: data, read/write, 4 GB, base 0 */ - [GDT_ENTRY_BOOT_DS] = GDT_ENTRY(0xc093, 0, 0xfffff), + [GDT_ENTRY_BOOT_DS] = GDT_ENTRY(DESC_DATA32, 0, 0xfffff), /* TSS: 32-bit tss, 104 bytes, base 4096 */ /* We only have a TSS here to keep Intel VT happy; we don't actually use it for anything. */ - [GDT_ENTRY_BOOT_TSS] = GDT_ENTRY(0x0089, 4096, 103), + [GDT_ENTRY_BOOT_TSS] = GDT_ENTRY(DESC_TSS32, 4096, 103), }; /* Xen HVM incorrectly stores a pointer to the gdt_ptr, instead of the gdt_ptr contents. Thus, make it static so it will diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 1c8541ae3b3a..c23f3b9c84fe 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -49,7 +49,7 @@ int strcmp(const char *str1, const char *str2) { const unsigned char *s1 = (const unsigned char *)str1; const unsigned char *s2 = (const unsigned char *)str2; - int delta = 0; + int delta; while (*s1 || *s2) { delta = *s1 - *s2; diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 1b5d17a9f70d..c1cb90369915 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -10,6 +10,7 @@ #include <asm/coco.h> #include <asm/tdx.h> #include <asm/vmx.h> +#include <asm/ia32.h> #include <asm/insn.h> #include <asm/insn-eval.h> #include <asm/pgtable.h> @@ -886,7 +887,7 @@ void __init tdx_early_init(void) * there. * * Intel-TDX has a secure RDMSR hypercall, but that needs to be - * implemented seperately in the low level startup ASM code. + * implemented separately in the low level startup ASM code. * Until that is in place, disable parallel bringup for TDX. */ x86_cpuinit.parallel_bringup = false; diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig index 9bbfd01cfa2f..c9e59589a1ce 100644 --- a/arch/x86/crypto/Kconfig +++ b/arch/x86/crypto/Kconfig @@ -189,7 +189,7 @@ config CRYPTO_SERPENT_AVX2_X86_64 Processes 16 blocks in parallel. config CRYPTO_SM4_AESNI_AVX_X86_64 - tristate "Ciphers: SM4 with modes: ECB, CBC, CFB, CTR (AES-NI/AVX)" + tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX)" depends on X86 && 64BIT select CRYPTO_SKCIPHER select CRYPTO_SIMD @@ -197,7 +197,7 @@ config CRYPTO_SM4_AESNI_AVX_X86_64 select CRYPTO_SM4 help Length-preserving ciphers: SM4 cipher algorithms - (OSCCA GB/T 32907-2016) with ECB, CBC, CFB, and CTR modes + (OSCCA GB/T 32907-2016) with ECB, CBC, and CTR modes Architecture: x86_64 using: - AES-NI (AES New Instructions) @@ -210,7 +210,7 @@ config CRYPTO_SM4_AESNI_AVX_X86_64 If unsure, say N. config CRYPTO_SM4_AESNI_AVX2_X86_64 - tristate "Ciphers: SM4 with modes: ECB, CBC, CFB, CTR (AES-NI/AVX2)" + tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX2)" depends on X86 && 64BIT select CRYPTO_SKCIPHER select CRYPTO_SIMD @@ -219,7 +219,7 @@ config CRYPTO_SM4_AESNI_AVX2_X86_64 select CRYPTO_SM4_AESNI_AVX_X86_64 help Length-preserving ciphers: SM4 cipher algorithms - (OSCCA GB/T 32907-2016) with ECB, CBC, CFB, and CTR modes + (OSCCA GB/T 32907-2016) with ECB, CBC, and CTR modes Architecture: x86_64 using: - AES-NI (AES New Instructions) diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 187f913cc239..411d8c83e88a 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -666,7 +666,7 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff .ifc \operation, dec movdqa %xmm1, %xmm3 - pxor %xmm1, %xmm9 # Cyphertext XOR E(K, Yn) + pxor %xmm1, %xmm9 # Ciphertext XOR E(K, Yn) mov \PLAIN_CYPH_LEN, %r10 add %r13, %r10 diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S index 74dd230973cf..8c9749ed0651 100644 --- a/arch/x86/crypto/aesni-intel_avx-x86_64.S +++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S @@ -747,7 +747,7 @@ VARIABLE_OFFSET = 16*8 .if \ENC_DEC == DEC vmovdqa %xmm1, %xmm3 - pxor %xmm1, %xmm9 # Cyphertext XOR E(K, Yn) + pxor %xmm1, %xmm9 # Ciphertext XOR E(K, Yn) mov \PLAIN_CYPH_LEN, %r10 add %r13, %r10 diff --git a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S index 81ce0f4db555..bbcff1fb78cb 100644 --- a/arch/x86/crypto/crc32c-pcl-intel-asm_64.S +++ b/arch/x86/crypto/crc32c-pcl-intel-asm_64.S @@ -184,7 +184,7 @@ SYM_FUNC_START(crc_pcl) xor crc1,crc1 xor crc2,crc2 - # Fall thruogh into top of crc array (crc_128) + # Fall through into top of crc array (crc_128) ################################################################ ## 3) CRC Array: diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 959afa705e95..ab8bc54f254d 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -2,8 +2,8 @@ /* * Cryptographic API. * - * Glue code for the SHA1 Secure Hash Algorithm assembler implementation using - * Supplemental SSE3 instructions. + * Glue code for the SHA1 Secure Hash Algorithm assembler implementations + * using SSSE3, AVX, AVX2, and SHA-NI instructions. * * This file is based on sha1_generic.c * @@ -28,6 +28,9 @@ #include <asm/simd.h> static const struct x86_cpu_id module_cpu_ids[] = { +#ifdef CONFIG_AS_SHA1_NI + X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL), +#endif X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index 4c0383a90e11..e04a43d9f7d5 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -1,8 +1,8 @@ /* * Cryptographic API. * - * Glue code for the SHA256 Secure Hash Algorithm assembler - * implementation using supplemental SSE3 / AVX / AVX2 instructions. + * Glue code for the SHA256 Secure Hash Algorithm assembler implementations + * using SSSE3, AVX, AVX2, and SHA-NI instructions. * * This file is based on sha256_generic.c * @@ -45,6 +45,9 @@ asmlinkage void sha256_transform_ssse3(struct sha256_state *state, const u8 *data, int blocks); static const struct x86_cpu_id module_cpu_ids[] = { +#ifdef CONFIG_AS_SHA256_NI + X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL), +#endif X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL), X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL), X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL), diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S index d902b8ea0721..5bfce4b045fd 100644 --- a/arch/x86/crypto/sha512-avx-asm.S +++ b/arch/x86/crypto/sha512-avx-asm.S @@ -84,7 +84,7 @@ frame_size = frame_WK + WK_SIZE # Useful QWORD "arrays" for simpler memory references # MSG, DIGEST, K_t, W_t are arrays -# WK_2(t) points to 1 of 2 qwords at frame.WK depdending on t being odd/even +# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even # Input message (arg1) #define MSG(i) 8*i(msg) diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S index 65be30156816..30a2c4777f9d 100644 --- a/arch/x86/crypto/sha512-ssse3-asm.S +++ b/arch/x86/crypto/sha512-ssse3-asm.S @@ -82,7 +82,7 @@ frame_size = frame_WK + WK_SIZE # Useful QWORD "arrays" for simpler memory references # MSG, DIGEST, K_t, W_t are arrays -# WK_2(t) points to 1 of 2 qwords at frame.WK depdending on t being odd/even +# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even # Input message (arg1) #define MSG(i) 8*i(msg) diff --git a/arch/x86/crypto/sm4-aesni-avx-asm_64.S b/arch/x86/crypto/sm4-aesni-avx-asm_64.S index e2668d2fe6ce..2bf611eaa191 100644 --- a/arch/x86/crypto/sm4-aesni-avx-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx-asm_64.S @@ -534,55 +534,3 @@ SYM_TYPED_FUNC_START(sm4_aesni_avx_cbc_dec_blk8) FRAME_END RET; SYM_FUNC_END(sm4_aesni_avx_cbc_dec_blk8) - -/* - * void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst, - * const u8 *src, u8 *iv) - */ -SYM_TYPED_FUNC_START(sm4_aesni_avx_cfb_dec_blk8) - /* input: - * %rdi: round key array, CTX - * %rsi: dst (8 blocks) - * %rdx: src (8 blocks) - * %rcx: iv - */ - FRAME_BEGIN - - /* Load input */ - vmovdqu (%rcx), RA0; - vmovdqu 0 * 16(%rdx), RA1; - vmovdqu 1 * 16(%rdx), RA2; - vmovdqu 2 * 16(%rdx), RA3; - vmovdqu 3 * 16(%rdx), RB0; - vmovdqu 4 * 16(%rdx), RB1; - vmovdqu 5 * 16(%rdx), RB2; - vmovdqu 6 * 16(%rdx), RB3; - - /* Update IV */ - vmovdqu 7 * 16(%rdx), RNOT; - vmovdqu RNOT, (%rcx); - - call __sm4_crypt_blk8; - - vpxor (0 * 16)(%rdx), RA0, RA0; - vpxor (1 * 16)(%rdx), RA1, RA1; - vpxor (2 * 16)(%rdx), RA2, RA2; - vpxor (3 * 16)(%rdx), RA3, RA3; - vpxor (4 * 16)(%rdx), RB0, RB0; - vpxor (5 * 16)(%rdx), RB1, RB1; - vpxor (6 * 16)(%rdx), RB2, RB2; - vpxor (7 * 16)(%rdx), RB3, RB3; - - vmovdqu RA0, (0 * 16)(%rsi); - vmovdqu RA1, (1 * 16)(%rsi); - vmovdqu RA2, (2 * 16)(%rsi); - vmovdqu RA3, (3 * 16)(%rsi); - vmovdqu RB0, (4 * 16)(%rsi); - vmovdqu RB1, (5 * 16)(%rsi); - vmovdqu RB2, (6 * 16)(%rsi); - vmovdqu RB3, (7 * 16)(%rsi); - - vzeroall; - FRAME_END - RET; -SYM_FUNC_END(sm4_aesni_avx_cfb_dec_blk8) diff --git a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S index 98ede9459287..9ff5ba075591 100644 --- a/arch/x86/crypto/sm4-aesni-avx2-asm_64.S +++ b/arch/x86/crypto/sm4-aesni-avx2-asm_64.S @@ -439,58 +439,3 @@ SYM_TYPED_FUNC_START(sm4_aesni_avx2_cbc_dec_blk16) FRAME_END RET; SYM_FUNC_END(sm4_aesni_avx2_cbc_dec_blk16) - -/* - * void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst, - * const u8 *src, u8 *iv) - */ -SYM_TYPED_FUNC_START(sm4_aesni_avx2_cfb_dec_blk16) - /* input: - * %rdi: round key array, CTX - * %rsi: dst (16 blocks) - * %rdx: src (16 blocks) - * %rcx: iv - */ - FRAME_BEGIN - - vzeroupper; - - /* Load input */ - vmovdqu (%rcx), RNOTx; - vinserti128 $1, (%rdx), RNOT, RA0; - vmovdqu (0 * 32 + 16)(%rdx), RA1; - vmovdqu (1 * 32 + 16)(%rdx), RA2; - vmovdqu (2 * 32 + 16)(%rdx), RA3; - vmovdqu (3 * 32 + 16)(%rdx), RB0; - vmovdqu (4 * 32 + 16)(%rdx), RB1; - vmovdqu (5 * 32 + 16)(%rdx), RB2; - vmovdqu (6 * 32 + 16)(%rdx), RB3; - - /* Update IV */ - vmovdqu (7 * 32 + 16)(%rdx), RNOTx; - vmovdqu RNOTx, (%rcx); - - call __sm4_crypt_blk16; - - vpxor (0 * 32)(%rdx), RA0, RA0; - vpxor (1 * 32)(%rdx), RA1, RA1; - vpxor (2 * 32)(%rdx), RA2, RA2; - vpxor (3 * 32)(%rdx), RA3, RA3; - vpxor (4 * 32)(%rdx), RB0, RB0; - vpxor (5 * 32)(%rdx), RB1, RB1; - vpxor (6 * 32)(%rdx), RB2, RB2; - vpxor (7 * 32)(%rdx), RB3, RB3; - - vmovdqu RA0, (0 * 32)(%rsi); - vmovdqu RA1, (1 * 32)(%rsi); - vmovdqu RA2, (2 * 32)(%rsi); - vmovdqu RA3, (3 * 32)(%rsi); - vmovdqu RB0, (4 * 32)(%rsi); - vmovdqu RB1, (5 * 32)(%rsi); - vmovdqu RB2, (6 * 32)(%rsi); - vmovdqu RB3, (7 * 32)(%rsi); - - vzeroall; - FRAME_END - RET; -SYM_FUNC_END(sm4_aesni_avx2_cfb_dec_blk16) diff --git a/arch/x86/crypto/sm4-avx.h b/arch/x86/crypto/sm4-avx.h index 1bceab7516aa..b5b5e67e40ed 100644 --- a/arch/x86/crypto/sm4-avx.h +++ b/arch/x86/crypto/sm4-avx.h @@ -14,10 +14,6 @@ int sm4_cbc_encrypt(struct skcipher_request *req); int sm4_avx_cbc_decrypt(struct skcipher_request *req, unsigned int bsize, sm4_crypt_func func); -int sm4_cfb_encrypt(struct skcipher_request *req); -int sm4_avx_cfb_decrypt(struct skcipher_request *req, - unsigned int bsize, sm4_crypt_func func); - int sm4_avx_ctr_crypt(struct skcipher_request *req, unsigned int bsize, sm4_crypt_func func); diff --git a/arch/x86/crypto/sm4_aesni_avx2_glue.c b/arch/x86/crypto/sm4_aesni_avx2_glue.c index 84bc718f49a3..1148fd4cd57f 100644 --- a/arch/x86/crypto/sm4_aesni_avx2_glue.c +++ b/arch/x86/crypto/sm4_aesni_avx2_glue.c @@ -23,8 +23,6 @@ asmlinkage void sm4_aesni_avx2_ctr_enc_blk16(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); asmlinkage void sm4_aesni_avx2_cbc_dec_blk16(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); -asmlinkage void sm4_aesni_avx2_cfb_dec_blk16(const u32 *rk, u8 *dst, - const u8 *src, u8 *iv); static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int key_len) @@ -41,12 +39,6 @@ static int cbc_decrypt(struct skcipher_request *req) } -static int cfb_decrypt(struct skcipher_request *req) -{ - return sm4_avx_cfb_decrypt(req, SM4_CRYPT16_BLOCK_SIZE, - sm4_aesni_avx2_cfb_dec_blk16); -} - static int ctr_crypt(struct skcipher_request *req) { return sm4_avx_ctr_crypt(req, SM4_CRYPT16_BLOCK_SIZE, @@ -89,24 +81,6 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = { .decrypt = cbc_decrypt, }, { .base = { - .cra_name = "__cfb(sm4)", - .cra_driver_name = "__cfb-sm4-aesni-avx2", - .cra_priority = 500, - .cra_flags = CRYPTO_ALG_INTERNAL, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct sm4_ctx), - .cra_module = THIS_MODULE, - }, - .min_keysize = SM4_KEY_SIZE, - .max_keysize = SM4_KEY_SIZE, - .ivsize = SM4_BLOCK_SIZE, - .chunksize = SM4_BLOCK_SIZE, - .walksize = 16 * SM4_BLOCK_SIZE, - .setkey = sm4_skcipher_setkey, - .encrypt = sm4_cfb_encrypt, - .decrypt = cfb_decrypt, - }, { - .base = { .cra_name = "__ctr(sm4)", .cra_driver_name = "__ctr-sm4-aesni-avx2", .cra_priority = 500, diff --git a/arch/x86/crypto/sm4_aesni_avx_glue.c b/arch/x86/crypto/sm4_aesni_avx_glue.c index 7800f77d68ad..85b4ca78b47b 100644 --- a/arch/x86/crypto/sm4_aesni_avx_glue.c +++ b/arch/x86/crypto/sm4_aesni_avx_glue.c @@ -27,8 +27,6 @@ asmlinkage void sm4_aesni_avx_ctr_enc_blk8(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); asmlinkage void sm4_aesni_avx_cbc_dec_blk8(const u32 *rk, u8 *dst, const u8 *src, u8 *iv); -asmlinkage void sm4_aesni_avx_cfb_dec_blk8(const u32 *rk, u8 *dst, - const u8 *src, u8 *iv); static int sm4_skcipher_setkey(struct crypto_skcipher *tfm, const u8 *key, unsigned int key_len) @@ -188,116 +186,6 @@ static int cbc_decrypt(struct skcipher_request *req) sm4_aesni_avx_cbc_dec_blk8); } -int sm4_cfb_encrypt(struct skcipher_request *req) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes) > 0) { - u8 keystream[SM4_BLOCK_SIZE]; - const u8 *iv = walk.iv; - const u8 *src = walk.src.virt.addr; - u8 *dst = walk.dst.virt.addr; - - while (nbytes >= SM4_BLOCK_SIZE) { - sm4_crypt_block(ctx->rkey_enc, keystream, iv); - crypto_xor_cpy(dst, src, keystream, SM4_BLOCK_SIZE); - iv = dst; - src += SM4_BLOCK_SIZE; - dst += SM4_BLOCK_SIZE; - nbytes -= SM4_BLOCK_SIZE; - } - if (iv != walk.iv) - memcpy(walk.iv, iv, SM4_BLOCK_SIZE); - - /* tail */ - if (walk.nbytes == walk.total && nbytes > 0) { - sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv); - crypto_xor_cpy(dst, src, keystream, nbytes); - nbytes = 0; - } - - err = skcipher_walk_done(&walk, nbytes); - } - - return err; -} -EXPORT_SYMBOL_GPL(sm4_cfb_encrypt); - -int sm4_avx_cfb_decrypt(struct skcipher_request *req, - unsigned int bsize, sm4_crypt_func func) -{ - struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct sm4_ctx *ctx = crypto_skcipher_ctx(tfm); - struct skcipher_walk walk; - unsigned int nbytes; - int err; - - err = skcipher_walk_virt(&walk, req, false); - - while ((nbytes = walk.nbytes) > 0) { - const u8 *src = walk.src.virt.addr; - u8 *dst = walk.dst.virt.addr; - - kernel_fpu_begin(); - - while (nbytes >= bsize) { - func(ctx->rkey_enc, dst, src, walk.iv); - dst += bsize; - src += bsize; - nbytes -= bsize; - } - - while (nbytes >= SM4_BLOCK_SIZE) { - u8 keystream[SM4_BLOCK_SIZE * 8]; - unsigned int nblocks = min(nbytes >> 4, 8u); - - memcpy(keystream, walk.iv, SM4_BLOCK_SIZE); - if (nblocks > 1) - memcpy(&keystream[SM4_BLOCK_SIZE], src, - (nblocks - 1) * SM4_BLOCK_SIZE); - memcpy(walk.iv, src + (nblocks - 1) * SM4_BLOCK_SIZE, - SM4_BLOCK_SIZE); - - sm4_aesni_avx_crypt8(ctx->rkey_enc, keystream, - keystream, nblocks); - - crypto_xor_cpy(dst, src, keystream, - nblocks * SM4_BLOCK_SIZE); - dst += nblocks * SM4_BLOCK_SIZE; - src += nblocks * SM4_BLOCK_SIZE; - nbytes -= nblocks * SM4_BLOCK_SIZE; - } - - kernel_fpu_end(); - - /* tail */ - if (walk.nbytes == walk.total && nbytes > 0) { - u8 keystream[SM4_BLOCK_SIZE]; - - sm4_crypt_block(ctx->rkey_enc, keystream, walk.iv); - crypto_xor_cpy(dst, src, keystream, nbytes); - nbytes = 0; - } - - err = skcipher_walk_done(&walk, nbytes); - } - - return err; -} -EXPORT_SYMBOL_GPL(sm4_avx_cfb_decrypt); - -static int cfb_decrypt(struct skcipher_request *req) -{ - return sm4_avx_cfb_decrypt(req, SM4_CRYPT8_BLOCK_SIZE, - sm4_aesni_avx_cfb_dec_blk8); -} - int sm4_avx_ctr_crypt(struct skcipher_request *req, unsigned int bsize, sm4_crypt_func func) { @@ -408,24 +296,6 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = { .decrypt = cbc_decrypt, }, { .base = { - .cra_name = "__cfb(sm4)", - .cra_driver_name = "__cfb-sm4-aesni-avx", - .cra_priority = 400, - .cra_flags = CRYPTO_ALG_INTERNAL, - .cra_blocksize = 1, - .cra_ctxsize = sizeof(struct sm4_ctx), - .cra_module = THIS_MODULE, - }, - .min_keysize = SM4_KEY_SIZE, - .max_keysize = SM4_KEY_SIZE, - .ivsize = SM4_BLOCK_SIZE, - .chunksize = SM4_BLOCK_SIZE, - .walksize = 8 * SM4_BLOCK_SIZE, - .setkey = sm4_skcipher_setkey, - .encrypt = sm4_cfb_encrypt, - .decrypt = cfb_decrypt, - }, { - .base = { .cra_name = "__ctr(sm4)", .cra_driver_name = "__ctr-sm4-aesni-avx", .cra_priority = 400, diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h index f6907627172b..9f1d94790a54 100644 --- a/arch/x86/entry/calling.h +++ b/arch/x86/entry/calling.h @@ -175,8 +175,7 @@ For 32-bit we have the following conventions - kernel is built with #define THIS_CPU_user_pcid_flush_mask \ PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask -.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req - ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI +.macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req mov %cr3, \scratch_reg ALTERNATIVE "jmp .Lwrcr3_\@", "", X86_FEATURE_PCID @@ -206,13 +205,20 @@ For 32-bit we have the following conventions - kernel is built with /* Flip the PGD to the user version */ orq $(PTI_USER_PGTABLE_MASK), \scratch_reg mov \scratch_reg, %cr3 +.endm + +.macro SWITCH_TO_USER_CR3_NOSTACK scratch_reg:req scratch_reg2:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI + SWITCH_TO_USER_CR3 \scratch_reg \scratch_reg2 .Lend_\@: .endm .macro SWITCH_TO_USER_CR3_STACK scratch_reg:req + ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI pushq %rax - SWITCH_TO_USER_CR3_NOSTACK scratch_reg=\scratch_reg scratch_reg2=%rax + SWITCH_TO_USER_CR3 scratch_reg=\scratch_reg scratch_reg2=%rax popq %rax +.Lend_\@: .endm .macro SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg:req save_reg:req diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index d813160b14d8..6356060caaf3 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -26,6 +26,7 @@ #include <xen/events.h> #endif +#include <asm/apic.h> #include <asm/desc.h> #include <asm/traps.h> #include <asm/vdso.h> @@ -167,7 +168,96 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) } } -/* Handles int $0x80 */ +#ifdef CONFIG_IA32_EMULATION +static __always_inline bool int80_is_external(void) +{ + const unsigned int offs = (0x80 / 32) * 0x10; + const u32 bit = BIT(0x80 % 32); + + /* The local APIC on XENPV guests is fake */ + if (cpu_feature_enabled(X86_FEATURE_XENPV)) + return false; + + /* + * If vector 0x80 is set in the APIC ISR then this is an external + * interrupt. Either from broken hardware or injected by a VMM. + * + * Note: In guest mode this is only valid for secure guests where + * the secure module fully controls the vAPIC exposed to the guest. + */ + return apic_read(APIC_ISR + offs) & bit; +} + +/** + * int80_emulation - 32-bit legacy syscall entry + * + * This entry point can be used by 32-bit and 64-bit programs to perform + * 32-bit system calls. Instances of INT $0x80 can be found inline in + * various programs and libraries. It is also used by the vDSO's + * __kernel_vsyscall fallback for hardware that doesn't support a faster + * entry method. Restarted 32-bit system calls also fall back to INT + * $0x80 regardless of what instruction was originally used to do the + * system call. + * + * This is considered a slow path. It is not used by most libc + * implementations on modern hardware except during process startup. + * + * The arguments for the INT $0x80 based syscall are on stack in the + * pt_regs structure: + * eax: system call number + * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 + */ +DEFINE_IDTENTRY_RAW(int80_emulation) +{ + int nr; + + /* Kernel does not use INT $0x80! */ + if (unlikely(!user_mode(regs))) { + irqentry_enter(regs); + instrumentation_begin(); + panic("Unexpected external interrupt 0x80\n"); + } + + /* + * Establish kernel context for instrumentation, including for + * int80_is_external() below which calls into the APIC driver. + * Identical for soft and external interrupts. + */ + enter_from_user_mode(regs); + + instrumentation_begin(); + add_random_kstack_offset(); + + /* Validate that this is a soft interrupt to the extent possible */ + if (unlikely(int80_is_external())) + panic("Unexpected external interrupt 0x80\n"); + + /* + * The low level idtentry code pushed -1 into regs::orig_ax + * and regs::ax contains the syscall number. + * + * User tracing code (ptrace or signal handlers) might assume + * that the regs::orig_ax contains a 32-bit number on invoking + * a 32-bit syscall. + * + * Establish the syscall convention by saving the 32bit truncated + * syscall number in regs::orig_ax and by invalidating regs::ax. + */ + regs->orig_ax = regs->ax & GENMASK(31, 0); + regs->ax = -ENOSYS; + + nr = syscall_32_enter(regs); + + local_irq_enable(); + nr = syscall_enter_from_user_mode_work(regs, nr); + do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); + syscall_exit_to_user_mode(regs); +} +#else /* CONFIG_IA32_EMULATION */ + +/* Handles int $0x80 on a 32bit kernel */ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) { int nr = syscall_32_enter(regs); @@ -186,6 +276,7 @@ __visible noinstr void do_int80_syscall_32(struct pt_regs *regs) instrumentation_end(); syscall_exit_to_user_mode(regs); } +#endif /* !CONFIG_IA32_EMULATION */ static noinstr bool __do_fast_syscall_32(struct pt_regs *regs) { diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index de6469dffe3a..c40f89ab1b4c 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -559,17 +559,27 @@ __irqentry_text_end: SYM_CODE_START_LOCAL(common_interrupt_return) SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) IBRS_EXIT -#ifdef CONFIG_DEBUG_ENTRY - /* Assert that pt_regs indicates user mode. */ - testb $3, CS(%rsp) - jnz 1f - ud2 -1: -#endif #ifdef CONFIG_XEN_PV ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV #endif +#ifdef CONFIG_PAGE_TABLE_ISOLATION + ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI +#endif + + STACKLEAK_ERASE + POP_REGS + add $8, %rsp /* orig_ax */ + UNWIND_HINT_IRET_REGS + +.Lswapgs_and_iret: + swapgs + /* Assert that the IRET frame indicates user mode. */ + testb $3, 8(%rsp) + jnz .Lnative_iret + ud2 +#ifdef CONFIG_PAGE_TABLE_ISOLATION +.Lpti_restore_regs_and_return_to_usermode: POP_REGS pop_rdi=0 /* @@ -596,13 +606,14 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL) */ STACKLEAK_ERASE_NOCLOBBER - SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi + push %rax + SWITCH_TO_USER_CR3 scratch_reg=%rdi scratch_reg2=%rax + pop %rax /* Restore RDI. */ popq %rdi - swapgs - jmp .Lnative_iret - + jmp .Lswapgs_and_iret +#endif SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL) #ifdef CONFIG_DEBUG_ENTRY diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index 27c05d08558a..de94e2e84ecc 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -275,80 +275,3 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR int3 SYM_CODE_END(entry_SYSCALL_compat) - -/* - * 32-bit legacy system call entry. - * - * 32-bit x86 Linux system calls traditionally used the INT $0x80 - * instruction. INT $0x80 lands here. - * - * This entry point can be used by 32-bit and 64-bit programs to perform - * 32-bit system calls. Instances of INT $0x80 can be found inline in - * various programs and libraries. It is also used by the vDSO's - * __kernel_vsyscall fallback for hardware that doesn't support a faster - * entry method. Restarted 32-bit system calls also fall back to INT - * $0x80 regardless of what instruction was originally used to do the - * system call. - * - * This is considered a slow path. It is not used by most libc - * implementations on modern hardware except during process startup. - * - * Arguments: - * eax system call number - * ebx arg1 - * ecx arg2 - * edx arg3 - * esi arg4 - * edi arg5 - * ebp arg6 - */ -SYM_CODE_START(entry_INT80_compat) - UNWIND_HINT_ENTRY - ENDBR - /* - * Interrupts are off on entry. - */ - ASM_CLAC /* Do this early to minimize exposure */ - ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV - - /* - * User tracing code (ptrace or signal handlers) might assume that - * the saved RAX contains a 32-bit number when we're invoking a 32-bit - * syscall. Just in case the high bits are nonzero, zero-extend - * the syscall number. (This could almost certainly be deleted - * with no ill effects.) - */ - movl %eax, %eax - - /* switch to thread stack expects orig_ax and rdi to be pushed */ - pushq %rax /* pt_regs->orig_ax */ - - /* Need to switch before accessing the thread stack. */ - SWITCH_TO_KERNEL_CR3 scratch_reg=%rax - - /* In the Xen PV case we already run on the thread stack. */ - ALTERNATIVE "", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV - - movq %rsp, %rax - movq PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp - - pushq 5*8(%rax) /* regs->ss */ - pushq 4*8(%rax) /* regs->rsp */ - pushq 3*8(%rax) /* regs->eflags */ - pushq 2*8(%rax) /* regs->cs */ - pushq 1*8(%rax) /* regs->ip */ - pushq 0*8(%rax) /* regs->orig_ax */ -.Lint80_keep_stack: - - PUSH_AND_CLEAR_REGS rax=$-ENOSYS - UNWIND_HINT_REGS - - cld - - IBRS_ENTER - UNTRAIN_RET - - movq %rsp, %rdi - call do_int80_syscall_32 - jmp swapgs_restore_regs_and_return_to_usermode -SYM_CODE_END(entry_INT80_compat) diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index c8fac5205803..5f8591ce7f25 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -461,3 +461,8 @@ 454 i386 futex_wake sys_futex_wake 455 i386 futex_wait sys_futex_wait 456 i386 futex_requeue sys_futex_requeue +457 i386 statmount sys_statmount +458 i386 listmount sys_listmount +459 i386 lsm_get_self_attr sys_lsm_get_self_attr +460 i386 lsm_set_self_attr sys_lsm_set_self_attr +461 i386 lsm_list_modules sys_lsm_list_modules diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 8cb8bf68721c..7e8d46f4147f 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -378,6 +378,11 @@ 454 common futex_wake sys_futex_wake 455 common futex_wait sys_futex_wait 456 common futex_requeue sys_futex_requeue +457 common statmount sys_statmount +458 common listmount sys_listmount +459 common lsm_get_self_attr sys_lsm_get_self_attr +460 common lsm_set_self_attr sys_lsm_set_self_attr +461 common lsm_list_modules sys_lsm_list_modules # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 7d70935b6758..0debc194bd78 100644 --- a/arch/x86/entry/vdso/vclock_gettime.c +++ b/arch/x86/entry/vdso/vclock_gettime.c @@ -11,12 +11,10 @@ #include <linux/time.h> #include <linux/kernel.h> #include <linux/types.h> +#include <vdso/gettime.h> #include "../../../../lib/vdso/gettimeofday.c" -extern int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz); -extern __kernel_old_time_t __vdso_time(__kernel_old_time_t *t); - int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz) { return __cvdso_gettimeofday(tv, tz); @@ -35,9 +33,6 @@ __kernel_old_time_t time(__kernel_old_time_t *t) __attribute__((weak, alias("__v #if defined(CONFIG_X86_64) && !defined(BUILD_VDSO32_64) /* both 64-bit and x32 use these */ -extern int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts); -extern int __vdso_clock_getres(clockid_t clock, struct __kernel_timespec *res); - int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts) { return __cvdso_clock_gettime(clock, ts); @@ -56,9 +51,6 @@ int clock_getres(clockid_t, struct __kernel_timespec *) #else /* i386 only */ -extern int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts); -extern int __vdso_clock_getres(clockid_t clock, struct old_timespec32 *res); - int __vdso_clock_gettime(clockid_t clock, struct old_timespec32 *ts) { return __cvdso_clock_gettime32(clock, ts); diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c index ed308719236c..780acd3dff22 100644 --- a/arch/x86/events/amd/brs.c +++ b/arch/x86/events/amd/brs.c @@ -125,7 +125,7 @@ int amd_brs_hw_config(struct perf_event *event) * Where X is the number of taken branches due to interrupt * skid. Skid is large. * - * Where Y is the occurences of the event while BRS is + * Where Y is the occurrences of the event while BRS is * capturing the lbr_nr entries. * * By using retired taken branches, we limit the impact on the diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c index e24976593a29..81f6d8275b6b 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -940,7 +940,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs) continue; if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); @@ -1184,7 +1184,7 @@ static void amd_put_event_constraints_f17h(struct cpu_hw_events *cpuc, * period of each one and given that the BRS saturates, it would not be possible * to guarantee correlated content for all events. Therefore, in situations * where multiple events want to use BRS, the kernel enforces mutual exclusion. - * Exclusion is enforced by chosing only one counter for events using BRS. + * Exclusion is enforced by choosing only one counter for events using BRS. * The event scheduling logic will then automatically multiplex the * events and ensure that at most one event is actively using BRS. * diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 6911c5399d02..e91970b01d62 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -287,6 +287,9 @@ static int perf_ibs_init(struct perf_event *event) if (config & ~perf_ibs->config_mask) return -EINVAL; + if (has_branch_stack(event)) + return -EOPNOTSUPP; + ret = validate_group(event); if (ret) return ret; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 40ad1425ffa2..09050641ce5d 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -601,7 +601,7 @@ int x86_pmu_hw_config(struct perf_event *event) } } - if (event->attr.branch_sample_type & PERF_SAMPLE_BRANCH_CALL_STACK) + if (branch_sample_call_stack(event)) event->attach_state |= PERF_ATTACH_TASK_DATA; /* @@ -1702,7 +1702,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs) perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index ce1c777227b4..3804f21ab049 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2527,9 +2527,14 @@ static void intel_pmu_assign_event(struct perf_event *event, int idx) perf_report_aux_output_id(event, idx); } +static __always_inline bool intel_pmu_needs_branch_stack(struct perf_event *event) +{ + return event->hw.flags & PERF_X86_EVENT_NEEDS_BRANCH_STACK; +} + static void intel_pmu_del_event(struct perf_event *event) { - if (needs_branch_stack(event)) + if (intel_pmu_needs_branch_stack(event)) intel_pmu_lbr_del(event); if (event->attr.precise_ip) intel_pmu_pebs_del(event); @@ -2787,6 +2792,7 @@ static void intel_pmu_enable_fixed(struct perf_event *event) static void intel_pmu_enable_event(struct perf_event *event) { + u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE; struct hw_perf_event *hwc = &event->hw; int idx = hwc->idx; @@ -2795,8 +2801,10 @@ static void intel_pmu_enable_event(struct perf_event *event) switch (idx) { case 0 ... INTEL_PMC_IDX_FIXED - 1: + if (branch_sample_counters(event)) + enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR; intel_set_masks(event, idx); - __x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE); + __x86_pmu_enable_event(hwc, enable_mask); break; case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1: case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END: @@ -2820,7 +2828,7 @@ static void intel_pmu_add_event(struct perf_event *event) { if (event->attr.precise_ip) intel_pmu_pebs_add(event); - if (needs_branch_stack(event)) + if (intel_pmu_needs_branch_stack(event)) intel_pmu_lbr_add(event); } @@ -3047,7 +3055,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status) perf_sample_data_init(&data, 0, event->hw.last_period); if (has_branch_stack(event)) - perf_sample_save_brstack(&data, event, &cpuc->lbr_stack); + intel_pmu_lbr_save_brstack(&data, cpuc, event); if (perf_event_overflow(event, &data, regs)) x86_pmu_stop(event, 0); @@ -3612,6 +3620,13 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx, if (cpuc->excl_cntrs) return intel_get_excl_constraints(cpuc, event, idx, c2); + /* Not all counters support the branch counter feature. */ + if (branch_sample_counters(event)) { + c2 = dyn_constraint(cpuc, c2, idx); + c2->idxmsk64 &= x86_pmu.lbr_counters; + c2->weight = hweight64(c2->idxmsk64); + } + return c2; } @@ -3897,7 +3912,62 @@ static int intel_pmu_hw_config(struct perf_event *event) x86_pmu.pebs_aliases(event); } - if (needs_branch_stack(event)) { + if (needs_branch_stack(event) && is_sampling_event(event)) + event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK; + + if (branch_sample_counters(event)) { + struct perf_event *leader, *sibling; + int num = 0; + + if (!(x86_pmu.flags & PMU_FL_BR_CNTR) || + (event->attr.config & ~INTEL_ARCH_EVENT_MASK)) + return -EINVAL; + + /* + * The branch counter logging is not supported in the call stack + * mode yet, since we cannot simply flush the LBR during e.g., + * multiplexing. Also, there is no obvious usage with the call + * stack mode. Simply forbids it for now. + * + * If any events in the group enable the branch counter logging + * feature, the group is treated as a branch counter logging + * group, which requires the extra space to store the counters. + */ + leader = event->group_leader; + if (branch_sample_call_stack(leader)) + return -EINVAL; + if (branch_sample_counters(leader)) + num++; + leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS; + + for_each_sibling_event(sibling, leader) { + if (branch_sample_call_stack(sibling)) + return -EINVAL; + if (branch_sample_counters(sibling)) + num++; + } + + if (num > fls(x86_pmu.lbr_counters)) + return -EINVAL; + /* + * Only applying the PERF_SAMPLE_BRANCH_COUNTERS doesn't + * require any branch stack setup. + * Clear the bit to avoid unnecessary branch stack setup. + */ + if (0 == (event->attr.branch_sample_type & + ~(PERF_SAMPLE_BRANCH_PLM_ALL | + PERF_SAMPLE_BRANCH_COUNTERS))) + event->hw.flags &= ~PERF_X86_EVENT_NEEDS_BRANCH_STACK; + + /* + * Force the leader to be a LBR event. So LBRs can be reset + * with the leader event. See intel_pmu_lbr_del() for details. + */ + if (!intel_pmu_needs_branch_stack(leader)) + return -EINVAL; + } + + if (intel_pmu_needs_branch_stack(event)) { ret = intel_pmu_setup_lbr_filter(event); if (ret) return ret; @@ -4027,7 +4097,7 @@ static int intel_pmu_hw_config(struct perf_event *event) /* * Currently, the only caller of this function is the atomic_switch_perf_msrs(). - * The host perf conext helps to prepare the values of the real hardware for + * The host perf context helps to prepare the values of the real hardware for * a set of msrs that need to be switched atomically in a vmx transaction. * * For example, the pseudocode needed to add a new msr should look like: @@ -4051,12 +4121,17 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data) u64 pebs_mask = cpuc->pebs_enabled & x86_pmu.pebs_capable; int global_ctrl, pebs_enable; + /* + * In addition to obeying exclude_guest/exclude_host, remove bits being + * used for PEBS when running a guest, because PEBS writes to virtual + * addresses (not physical addresses). + */ *nr = 0; global_ctrl = (*nr)++; arr[global_ctrl] = (struct perf_guest_switch_msr){ .msr = MSR_CORE_PERF_GLOBAL_CTRL, .host = intel_ctrl & ~cpuc->intel_ctrl_guest_mask, - .guest = intel_ctrl & (~cpuc->intel_ctrl_host_mask | ~pebs_mask), + .guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask, }; if (!x86_pmu.pebs) @@ -4375,8 +4450,13 @@ cmt_get_event_constraints(struct cpu_hw_events *cpuc, int idx, */ if (event->attr.precise_ip == 3) { /* Force instruction:ppp on PMC0, 1 and Fixed counter 0 */ - if (constraint_match(&fixed0_constraint, event->hw.config)) - return &fixed0_counter0_1_constraint; + if (constraint_match(&fixed0_constraint, event->hw.config)) { + /* The fixed counter 0 doesn't support LBR event logging. */ + if (branch_sample_counters(event)) + return &counter0_1_constraint; + else + return &fixed0_counter0_1_constraint; + } switch (c->idxmsk64 & 0x3ull) { case 0x1: @@ -4555,7 +4635,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu) goto err; } - if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA)) { + if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) { size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint); cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); @@ -5527,11 +5607,41 @@ static ssize_t branches_show(struct device *cdev, static DEVICE_ATTR_RO(branches); +static ssize_t branch_counter_nr_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", fls(x86_pmu.lbr_counters)); +} + +static DEVICE_ATTR_RO(branch_counter_nr); + +static ssize_t branch_counter_width_show(struct device *cdev, + struct device_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "%d\n", LBR_INFO_BR_CNTR_BITS); +} + +static DEVICE_ATTR_RO(branch_counter_width); + static struct attribute *lbr_attrs[] = { &dev_attr_branches.attr, + &dev_attr_branch_counter_nr.attr, + &dev_attr_branch_counter_width.attr, NULL }; +static umode_t +lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + /* branches */ + if (i == 0) + return x86_pmu.lbr_nr ? attr->mode : 0; + + return (x86_pmu.flags & PMU_FL_BR_CNTR) ? attr->mode : 0; +} + static char pmu_name_str[30]; static ssize_t pmu_name_show(struct device *cdev, @@ -5559,6 +5669,15 @@ static struct attribute *intel_pmu_attrs[] = { }; static umode_t +default_is_visible(struct kobject *kobj, struct attribute *attr, int i) +{ + if (attr == &dev_attr_allow_tsx_force_abort.attr) + return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0; + + return attr->mode; +} + +static umode_t tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i) { return boot_cpu_has(X86_FEATURE_RTM) ? attr->mode : 0; @@ -5580,26 +5699,11 @@ mem_is_visible(struct kobject *kobj, struct attribute *attr, int i) } static umode_t -lbr_is_visible(struct kobject *kobj, struct attribute *attr, int i) -{ - return x86_pmu.lbr_nr ? attr->mode : 0; -} - -static umode_t exra_is_visible(struct kobject *kobj, struct attribute *attr, int i) { return x86_pmu.version >= 2 ? attr->mode : 0; } -static umode_t -default_is_visible(struct kobject *kobj, struct attribute *attr, int i) -{ - if (attr == &dev_attr_allow_tsx_force_abort.attr) - return x86_pmu.flags & PMU_FL_TFA ? attr->mode : 0; - - return attr->mode; -} - static struct attribute_group group_events_td = { .name = "events", }; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index cbeb6d2bf5b4..4b50a3a9818a 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -41,7 +41,7 @@ * MSR_CORE_C1_RES: CORE C1 Residency Counter * perf code: 0x00 * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL - * MTL + * MTL,SRF,GRR * Scope: Core (each processor core has a MSR) * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter * perf code: 0x01 @@ -52,7 +52,8 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR,MTL + * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF, + * GRR * Scope: Core * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter * perf code: 0x03 @@ -75,7 +76,7 @@ * perf code: 0x02 * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW, * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX, - * TGL,TNT,RKL,ADL,RPL,SPR,MTL + * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF * Scope: Package (physical package) * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 @@ -97,6 +98,10 @@ * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL, * TNT,RKL,ADL,RPL,MTL * Scope: Package (physical package) + * MSR_MODULE_C6_RES_MS: Module C6 Residency Counter. + * perf code: 0x00 + * Available model: SRF,GRR + * Scope: A cluster of cores shared L2 cache * */ @@ -130,6 +135,7 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, struct cstate_model { unsigned long core_events; unsigned long pkg_events; + unsigned long module_events; unsigned long quirks; }; @@ -189,20 +195,20 @@ static struct attribute *attrs_empty[] = { * "events" group (with empty attrs) before updating * it with detected events. */ -static struct attribute_group core_events_attr_group = { +static struct attribute_group cstate_events_attr_group = { .name = "events", .attrs = attrs_empty, }; -DEFINE_CSTATE_FORMAT_ATTR(core_event, event, "config:0-63"); -static struct attribute *core_format_attrs[] = { - &format_attr_core_event.attr, +DEFINE_CSTATE_FORMAT_ATTR(cstate_event, event, "config:0-63"); +static struct attribute *cstate_format_attrs[] = { + &format_attr_cstate_event.attr, NULL, }; -static struct attribute_group core_format_attr_group = { +static struct attribute_group cstate_format_attr_group = { .name = "format", - .attrs = core_format_attrs, + .attrs = cstate_format_attrs, }; static cpumask_t cstate_core_cpu_mask; @@ -217,9 +223,9 @@ static struct attribute_group cpumask_attr_group = { .attrs = cstate_cpumask_attrs, }; -static const struct attribute_group *core_attr_groups[] = { - &core_events_attr_group, - &core_format_attr_group, +static const struct attribute_group *cstate_attr_groups[] = { + &cstate_events_attr_group, + &cstate_format_attr_group, &cpumask_attr_group, NULL, }; @@ -268,30 +274,30 @@ static struct perf_msr pkg_msr[] = { [PERF_CSTATE_PKG_C10_RES] = { MSR_PKG_C10_RESIDENCY, &group_cstate_pkg_c10, test_msr }, }; -static struct attribute_group pkg_events_attr_group = { - .name = "events", - .attrs = attrs_empty, -}; +static cpumask_t cstate_pkg_cpu_mask; -DEFINE_CSTATE_FORMAT_ATTR(pkg_event, event, "config:0-63"); -static struct attribute *pkg_format_attrs[] = { - &format_attr_pkg_event.attr, - NULL, -}; -static struct attribute_group pkg_format_attr_group = { - .name = "format", - .attrs = pkg_format_attrs, +/* cstate_module PMU */ +static struct pmu cstate_module_pmu; +static bool has_cstate_module; + +enum perf_cstate_module_events { + PERF_CSTATE_MODULE_C6_RES = 0, + + PERF_CSTATE_MODULE_EVENT_MAX, }; -static cpumask_t cstate_pkg_cpu_mask; +PMU_EVENT_ATTR_STRING(c6-residency, attr_cstate_module_c6, "event=0x00"); -static const struct attribute_group *pkg_attr_groups[] = { - &pkg_events_attr_group, - &pkg_format_attr_group, - &cpumask_attr_group, - NULL, +static unsigned long module_msr_mask; + +PMU_EVENT_GROUP(events, cstate_module_c6); + +static struct perf_msr module_msr[] = { + [PERF_CSTATE_MODULE_C6_RES] = { MSR_MODULE_C6_RES_MS, &group_cstate_module_c6, test_msr }, }; +static cpumask_t cstate_module_cpu_mask; + static ssize_t cstate_get_attr_cpumask(struct device *dev, struct device_attribute *attr, char *buf) @@ -302,6 +308,8 @@ static ssize_t cstate_get_attr_cpumask(struct device *dev, return cpumap_print_to_pagebuf(true, buf, &cstate_core_cpu_mask); else if (pmu == &cstate_pkg_pmu) return cpumap_print_to_pagebuf(true, buf, &cstate_pkg_cpu_mask); + else if (pmu == &cstate_module_pmu) + return cpumap_print_to_pagebuf(true, buf, &cstate_module_cpu_mask); else return 0; } @@ -342,6 +350,15 @@ static int cstate_pmu_event_init(struct perf_event *event) event->hw.event_base = pkg_msr[cfg].msr; cpu = cpumask_any_and(&cstate_pkg_cpu_mask, topology_die_cpumask(event->cpu)); + } else if (event->pmu == &cstate_module_pmu) { + if (cfg >= PERF_CSTATE_MODULE_EVENT_MAX) + return -EINVAL; + cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_MODULE_EVENT_MAX); + if (!(module_msr_mask & (1 << cfg))) + return -EINVAL; + event->hw.event_base = module_msr[cfg].msr; + cpu = cpumask_any_and(&cstate_module_cpu_mask, + topology_cluster_cpumask(event->cpu)); } else { return -ENOENT; } @@ -429,6 +446,17 @@ static int cstate_cpu_exit(unsigned int cpu) perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target); } } + + if (has_cstate_module && + cpumask_test_and_clear_cpu(cpu, &cstate_module_cpu_mask)) { + + target = cpumask_any_but(topology_cluster_cpumask(cpu), cpu); + /* Migrate events if there is a valid target */ + if (target < nr_cpu_ids) { + cpumask_set_cpu(target, &cstate_module_cpu_mask); + perf_pmu_migrate_context(&cstate_module_pmu, cpu, target); + } + } return 0; } @@ -455,6 +483,15 @@ static int cstate_cpu_init(unsigned int cpu) if (has_cstate_pkg && target >= nr_cpu_ids) cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask); + /* + * If this is the first online thread of that cluster, set it + * in the cluster cpu mask as the designated reader. + */ + target = cpumask_any_and(&cstate_module_cpu_mask, + topology_cluster_cpumask(cpu)); + if (has_cstate_module && target >= nr_cpu_ids) + cpumask_set_cpu(cpu, &cstate_module_cpu_mask); + return 0; } @@ -477,8 +514,13 @@ static const struct attribute_group *pkg_attr_update[] = { NULL, }; +static const struct attribute_group *module_attr_update[] = { + &group_cstate_module_c6, + NULL +}; + static struct pmu cstate_core_pmu = { - .attr_groups = core_attr_groups, + .attr_groups = cstate_attr_groups, .attr_update = core_attr_update, .name = "cstate_core", .task_ctx_nr = perf_invalid_context, @@ -493,7 +535,7 @@ static struct pmu cstate_core_pmu = { }; static struct pmu cstate_pkg_pmu = { - .attr_groups = pkg_attr_groups, + .attr_groups = cstate_attr_groups, .attr_update = pkg_attr_update, .name = "cstate_pkg", .task_ctx_nr = perf_invalid_context, @@ -507,6 +549,21 @@ static struct pmu cstate_pkg_pmu = { .module = THIS_MODULE, }; +static struct pmu cstate_module_pmu = { + .attr_groups = cstate_attr_groups, + .attr_update = module_attr_update, + .name = "cstate_module", + .task_ctx_nr = perf_invalid_context, + .event_init = cstate_pmu_event_init, + .add = cstate_pmu_event_add, + .del = cstate_pmu_event_del, + .start = cstate_pmu_event_start, + .stop = cstate_pmu_event_stop, + .read = cstate_pmu_event_update, + .capabilities = PERF_PMU_CAP_NO_INTERRUPT | PERF_PMU_CAP_NO_EXCLUDE, + .module = THIS_MODULE, +}; + static const struct cstate_model nhm_cstates __initconst = { .core_events = BIT(PERF_CSTATE_CORE_C3_RES) | BIT(PERF_CSTATE_CORE_C6_RES), @@ -621,6 +678,22 @@ static const struct cstate_model glm_cstates __initconst = { BIT(PERF_CSTATE_PKG_C10_RES), }; +static const struct cstate_model grr_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .module_events = BIT(PERF_CSTATE_MODULE_C6_RES), +}; + +static const struct cstate_model srf_cstates __initconst = { + .core_events = BIT(PERF_CSTATE_CORE_C1_RES) | + BIT(PERF_CSTATE_CORE_C6_RES), + + .pkg_events = BIT(PERF_CSTATE_PKG_C6_RES), + + .module_events = BIT(PERF_CSTATE_MODULE_C6_RES), +}; + static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(NEHALEM, &nhm_cstates), @@ -673,6 +746,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_L, &glm_cstates), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, &srf_cstates), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, &grr_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L, &icl_cstates), X86_MATCH_INTEL_FAM6_MODEL(ICELAKE, &icl_cstates), @@ -714,10 +789,14 @@ static int __init cstate_probe(const struct cstate_model *cm) pkg_msr_mask = perf_msr_probe(pkg_msr, PERF_CSTATE_PKG_EVENT_MAX, true, (void *) &cm->pkg_events); + module_msr_mask = perf_msr_probe(module_msr, PERF_CSTATE_MODULE_EVENT_MAX, + true, (void *) &cm->module_events); + has_cstate_core = !!core_msr_mask; has_cstate_pkg = !!pkg_msr_mask; + has_cstate_module = !!module_msr_mask; - return (has_cstate_core || has_cstate_pkg) ? 0 : -ENODEV; + return (has_cstate_core || has_cstate_pkg || has_cstate_module) ? 0 : -ENODEV; } static inline void cstate_cleanup(void) @@ -730,6 +809,9 @@ static inline void cstate_cleanup(void) if (has_cstate_pkg) perf_pmu_unregister(&cstate_pkg_pmu); + + if (has_cstate_module) + perf_pmu_unregister(&cstate_module_pmu); } static int __init cstate_init(void) @@ -766,6 +848,16 @@ static int __init cstate_init(void) return err; } } + + if (has_cstate_module) { + err = perf_pmu_register(&cstate_module_pmu, cstate_module_pmu.name, -1); + if (err) { + has_cstate_module = false; + pr_info("Failed to register cstate cluster pmu\n"); + cstate_cleanup(); + return err; + } + } return 0; } diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index bf97ab904d40..d49d661ec0a7 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1755,7 +1755,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, setup_pebs_time(event, data, pebs->tsc); if (has_branch_stack(event)) - perf_sample_save_brstack(data, event, &cpuc->lbr_stack); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1912,7 +1912,7 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, if (has_branch_stack(event)) { intel_pmu_store_pebs_lbrs(lbr); - perf_sample_save_brstack(data, event, &cpuc->lbr_stack); + intel_pmu_lbr_save_brstack(data, cpuc, event); } } diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index c3b0d15a9841..78cd5084104e 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -676,6 +676,25 @@ void intel_pmu_lbr_del(struct perf_event *event) WARN_ON_ONCE(cpuc->lbr_users < 0); WARN_ON_ONCE(cpuc->lbr_pebs_users < 0); perf_sched_cb_dec(event->pmu); + + /* + * The logged occurrences information is only valid for the + * current LBR group. If another LBR group is scheduled in + * later, the information from the stale LBRs will be wrongly + * interpreted. Reset the LBRs here. + * + * Only clear once for a branch counter group with the leader + * event. Because + * - Cannot simply reset the LBRs with the !cpuc->lbr_users. + * Because it's possible that the last LBR user is not in a + * branch counter group, e.g., a branch_counters group + + * several normal LBR events. + * - The LBR reset can be done with any one of the events in a + * branch counter group, since they are always scheduled together. + * It's easy to force the leader event an LBR event. + */ + if (is_branch_counters_group(event) && event == event->group_leader) + intel_pmu_lbr_reset(); } static inline bool vlbr_exclude_host(void) @@ -866,6 +885,8 @@ static __always_inline u16 get_lbr_cycles(u64 info) return cycles; } +static_assert((64 - PERF_BRANCH_ENTRY_INFO_BITS_MAX) > LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS); + static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, struct lbr_entry *entries) { @@ -898,11 +919,67 @@ static void intel_pmu_store_lbr(struct cpu_hw_events *cpuc, e->abort = !!(info & LBR_INFO_ABORT); e->cycles = get_lbr_cycles(info); e->type = get_lbr_br_type(info); + + /* + * Leverage the reserved field of cpuc->lbr_entries[i] to + * temporarily store the branch counters information. + * The later code will decide what content can be disclosed + * to the perf tool. Pleae see intel_pmu_lbr_counters_reorder(). + */ + e->reserved = (info >> LBR_INFO_BR_CNTR_OFFSET) & LBR_INFO_BR_CNTR_FULL_MASK; } cpuc->lbr_stack.nr = i; } +/* + * The enabled order may be different from the counter order. + * Update the lbr_counters with the enabled order. + */ +static void intel_pmu_lbr_counters_reorder(struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + int i, j, pos = 0, order[X86_PMC_IDX_MAX]; + struct perf_event *leader, *sibling; + u64 src, dst, cnt; + + leader = event->group_leader; + if (branch_sample_counters(leader)) + order[pos++] = leader->hw.idx; + + for_each_sibling_event(sibling, leader) { + if (!branch_sample_counters(sibling)) + continue; + order[pos++] = sibling->hw.idx; + } + + WARN_ON_ONCE(!pos); + + for (i = 0; i < cpuc->lbr_stack.nr; i++) { + src = cpuc->lbr_entries[i].reserved; + dst = 0; + for (j = 0; j < pos; j++) { + cnt = (src >> (order[j] * LBR_INFO_BR_CNTR_BITS)) & LBR_INFO_BR_CNTR_MASK; + dst |= cnt << j * LBR_INFO_BR_CNTR_BITS; + } + cpuc->lbr_counters[i] = dst; + cpuc->lbr_entries[i].reserved = 0; + } +} + +void intel_pmu_lbr_save_brstack(struct perf_sample_data *data, + struct cpu_hw_events *cpuc, + struct perf_event *event) +{ + if (is_branch_counters_group(event)) { + intel_pmu_lbr_counters_reorder(cpuc, event); + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, cpuc->lbr_counters); + return; + } + + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); +} + static void intel_pmu_arch_lbr_read(struct cpu_hw_events *cpuc) { intel_pmu_store_lbr(cpuc, NULL); @@ -1173,8 +1250,10 @@ intel_pmu_lbr_filter(struct cpu_hw_events *cpuc) for (i = 0; i < cpuc->lbr_stack.nr; ) { if (!cpuc->lbr_entries[i].from) { j = i; - while (++j < cpuc->lbr_stack.nr) + while (++j < cpuc->lbr_stack.nr) { cpuc->lbr_entries[j-1] = cpuc->lbr_entries[j]; + cpuc->lbr_counters[j-1] = cpuc->lbr_counters[j]; + } cpuc->lbr_stack.nr--; if (!cpuc->lbr_entries[i].from) continue; @@ -1525,8 +1604,12 @@ void __init intel_pmu_arch_lbr_init(void) x86_pmu.lbr_mispred = ecx.split.lbr_mispred; x86_pmu.lbr_timed_lbr = ecx.split.lbr_timed_lbr; x86_pmu.lbr_br_type = ecx.split.lbr_br_type; + x86_pmu.lbr_counters = ecx.split.lbr_counters; x86_pmu.lbr_nr = lbr_nr; + if (!!x86_pmu.lbr_counters) + x86_pmu.flags |= PMU_FL_BR_CNTR; + if (x86_pmu.lbr_mispred) static_branch_enable(&x86_lbr_mispred); if (x86_pmu.lbr_timed_lbr) diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c index 01023aa5125b..7927c0b832fa 100644 --- a/arch/x86/events/intel/uncore.c +++ b/arch/x86/events/intel/uncore.c @@ -1814,6 +1814,14 @@ static const struct intel_uncore_init_fun spr_uncore_init __initconst = { .uncore_units_ignore = spr_uncore_units_ignore, }; +static const struct intel_uncore_init_fun gnr_uncore_init __initconst = { + .cpu_init = gnr_uncore_cpu_init, + .pci_init = gnr_uncore_pci_init, + .mmio_init = gnr_uncore_mmio_init, + .use_discovery = true, + .uncore_units_ignore = gnr_uncore_units_ignore, +}; + static const struct intel_uncore_init_fun generic_uncore_init __initconst = { .cpu_init = intel_uncore_generic_uncore_cpu_init, .pci_init = intel_uncore_generic_uncore_pci_init, @@ -1865,8 +1873,12 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = { X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, &mtl_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, &spr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(EMERALDRAPIDS_X, &spr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_X, &gnr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(GRANITERAPIDS_D, &gnr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_TREMONT_D, &snr_uncore_init), X86_MATCH_INTEL_FAM6_MODEL(ATOM_GRACEMONT, &adl_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT_X, &gnr_uncore_init), + X86_MATCH_INTEL_FAM6_MODEL(ATOM_CRESTMONT, &gnr_uncore_init), {}, }; MODULE_DEVICE_TABLE(x86cpu, intel_uncore_match); diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h index c30fb5bb1222..4838502d89ae 100644 --- a/arch/x86/events/intel/uncore.h +++ b/arch/x86/events/intel/uncore.h @@ -72,9 +72,9 @@ struct intel_uncore_type { unsigned single_fixed:1; unsigned pair_ctr_ctl:1; union { - unsigned *msr_offsets; - unsigned *pci_offsets; - unsigned *mmio_offsets; + u64 *msr_offsets; + u64 *pci_offsets; + u64 *mmio_offsets; }; unsigned *box_ids; struct event_constraint unconstrainted; @@ -593,6 +593,7 @@ extern struct list_head pci2phy_map_head; extern struct pci_extra_dev *uncore_extra_pci_dev; extern struct event_constraint uncore_constraint_empty; extern int spr_uncore_units_ignore[]; +extern int gnr_uncore_units_ignore[]; /* uncore_snb.c */ int snb_uncore_pci_init(void); @@ -634,6 +635,9 @@ void icx_uncore_mmio_init(void); int spr_uncore_pci_init(void); void spr_uncore_cpu_init(void); void spr_uncore_mmio_init(void); +int gnr_uncore_pci_init(void); +void gnr_uncore_cpu_init(void); +void gnr_uncore_mmio_init(void); /* uncore_nhmex.c */ void nhmex_uncore_cpu_init(void); diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c index cb488e41807c..9a698a92962a 100644 --- a/arch/x86/events/intel/uncore_discovery.c +++ b/arch/x86/events/intel/uncore_discovery.c @@ -125,7 +125,8 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit, int die, bool parsed) { struct intel_uncore_discovery_type *type; - unsigned int *box_offset, *ids; + unsigned int *ids; + u64 *box_offset; int i; if (!unit->ctl || !unit->ctl_offset || !unit->ctr_offset) { @@ -153,7 +154,7 @@ uncore_insert_box_info(struct uncore_unit_discovery *unit, if (!type) return; - box_offset = kcalloc(type->num_boxes + 1, sizeof(unsigned int), GFP_KERNEL); + box_offset = kcalloc(type->num_boxes + 1, sizeof(u64), GFP_KERNEL); if (!box_offset) return; diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h index 6ee80ad3423e..22e769a81103 100644 --- a/arch/x86/events/intel/uncore_discovery.h +++ b/arch/x86/events/intel/uncore_discovery.h @@ -125,7 +125,7 @@ struct intel_uncore_discovery_type { u8 ctr_offset; /* Counter 0 offset */ u16 num_boxes; /* number of boxes for the uncore block */ unsigned int *ids; /* Box IDs */ - unsigned int *box_offset; /* Box offset */ + u64 *box_offset; /* Box offset */ }; bool intel_uncore_has_discovery_tables(int *ignore); diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c index 173e2674be6e..56eea2c66cfb 100644 --- a/arch/x86/events/intel/uncore_nhmex.c +++ b/arch/x86/events/intel/uncore_nhmex.c @@ -306,7 +306,7 @@ static const struct attribute_group nhmex_uncore_cbox_format_group = { }; /* msr offset for each instance of cbox */ -static unsigned nhmex_cbox_msr_offsets[] = { +static u64 nhmex_cbox_msr_offsets[] = { 0x0, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0, 0x240, 0x2c0, }; diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 8250f0f59c2b..a96496bef678 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -1396,6 +1396,29 @@ err: return ret; } +static int topology_gidnid_map(int nodeid, u32 gidnid) +{ + int i, die_id = -1; + + /* + * every three bits in the Node ID mapping register maps + * to a particular node. + */ + for (i = 0; i < 8; i++) { + if (nodeid == GIDNIDMAP(gidnid, i)) { + if (topology_max_die_per_package() > 1) + die_id = i; + else + die_id = topology_phys_to_logical_pkg(i); + if (die_id < 0) + die_id = -ENODEV; + break; + } + } + + return die_id; +} + /* * build pci bus to socket mapping */ @@ -1435,22 +1458,7 @@ static int snbep_pci2phy_map_init(int devid, int nodeid_loc, int idmap_loc, bool break; } - /* - * every three bits in the Node ID mapping register maps - * to a particular node. - */ - for (i = 0; i < 8; i++) { - if (nodeid == GIDNIDMAP(config, i)) { - if (topology_max_die_per_package() > 1) - die_id = i; - else - die_id = topology_phys_to_logical_pkg(i); - if (die_id < 0) - die_id = -ENODEV; - map->pbus_to_dieid[bus] = die_id; - break; - } - } + map->pbus_to_dieid[bus] = topology_gidnid_map(nodeid, config); raw_spin_unlock(&pci2phy_map_lock); } else { segment = pci_domain_nr(ubox_dev->bus); @@ -5278,7 +5286,7 @@ void snr_uncore_mmio_init(void) /* ICX uncore support */ -static unsigned icx_cha_msr_offsets[] = { +static u64 icx_cha_msr_offsets[] = { 0x2a0, 0x2ae, 0x2bc, 0x2ca, 0x2d8, 0x2e6, 0x2f4, 0x302, 0x310, 0x31e, 0x32c, 0x33a, 0x348, 0x356, 0x364, 0x372, 0x380, 0x38e, 0x3aa, 0x3b8, 0x3c6, 0x3d4, 0x3e2, 0x3f0, 0x3fe, 0x40c, 0x41a, @@ -5326,7 +5334,7 @@ static struct intel_uncore_type icx_uncore_chabox = { .format_group = &snr_uncore_chabox_format_group, }; -static unsigned icx_msr_offsets[] = { +static u64 icx_msr_offsets[] = { 0x0, 0x20, 0x40, 0x90, 0xb0, 0xd0, }; @@ -5596,7 +5604,7 @@ static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, i struct pci_dev *ubox = NULL; struct pci_dev *dev = NULL; u32 nid, gid; - int i, idx, ret = -EPERM; + int idx, lgc_pkg, ret = -EPERM; struct intel_uncore_topology *upi; unsigned int devfn; @@ -5611,20 +5619,21 @@ static int discover_upi_topology(struct intel_uncore_type *type, int ubox_did, i break; } - for (i = 0; i < 8; i++) { - if (nid != GIDNIDMAP(gid, i)) - continue; - for (idx = 0; idx < type->num_boxes; idx++) { - upi = &type->topology[nid][idx]; - devfn = PCI_DEVFN(dev_link0 + idx, ICX_UPI_REGS_ADDR_FUNCTION); - dev = pci_get_domain_bus_and_slot(pci_domain_nr(ubox->bus), - ubox->bus->number, - devfn); - if (dev) { - ret = upi_fill_topology(dev, upi, idx); - if (ret) - goto err; - } + lgc_pkg = topology_gidnid_map(nid, gid); + if (lgc_pkg < 0) { + ret = -EPERM; + goto err; + } + for (idx = 0; idx < type->num_boxes; idx++) { + upi = &type->topology[lgc_pkg][idx]; + devfn = PCI_DEVFN(dev_link0 + idx, ICX_UPI_REGS_ADDR_FUNCTION); + dev = pci_get_domain_bus_and_slot(pci_domain_nr(ubox->bus), + ubox->bus->number, + devfn); + if (dev) { + ret = upi_fill_topology(dev, upi, idx); + if (ret) + goto err; } } } @@ -6079,13 +6088,16 @@ static struct uncore_event_desc spr_uncore_imc_events[] = { { /* end: all zeroes */ }, }; +#define SPR_UNCORE_MMIO_COMMON_FORMAT() \ + SPR_UNCORE_COMMON_FORMAT(), \ + .ops = &spr_uncore_mmio_ops + static struct intel_uncore_type spr_uncore_imc = { - SPR_UNCORE_COMMON_FORMAT(), + SPR_UNCORE_MMIO_COMMON_FORMAT(), .name = "imc", .fixed_ctr_bits = 48, .fixed_ctr = SNR_IMC_MMIO_PMON_FIXED_CTR, .fixed_ctl = SNR_IMC_MMIO_PMON_FIXED_CTL, - .ops = &spr_uncore_mmio_ops, .event_descs = spr_uncore_imc_events, }; @@ -6181,7 +6193,7 @@ static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = { */ #define SPR_UNCORE_UPI_NUM_BOXES 4 -static unsigned int spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = { +static u64 spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = { 0, 0x8000, 0x10000, 0x18000 }; @@ -6412,7 +6424,8 @@ static void uncore_type_customized_copy(struct intel_uncore_type *to_type, static struct intel_uncore_type ** uncore_get_uncores(enum uncore_access_type type_id, int num_extra, - struct intel_uncore_type **extra) + struct intel_uncore_type **extra, int max_num_types, + struct intel_uncore_type **uncores) { struct intel_uncore_type **types, **start_types; int i; @@ -6421,9 +6434,9 @@ uncore_get_uncores(enum uncore_access_type type_id, int num_extra, /* Only copy the customized features */ for (; *types; types++) { - if ((*types)->type_id >= UNCORE_SPR_NUM_UNCORE_TYPES) + if ((*types)->type_id >= max_num_types) continue; - uncore_type_customized_copy(*types, spr_uncores[(*types)->type_id]); + uncore_type_customized_copy(*types, uncores[(*types)->type_id]); } for (i = 0; i < num_extra; i++, types++) @@ -6470,7 +6483,9 @@ void spr_uncore_cpu_init(void) uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR, UNCORE_SPR_MSR_EXTRA_UNCORES, - spr_msr_uncores); + spr_msr_uncores, + UNCORE_SPR_NUM_UNCORE_TYPES, + spr_uncores); type = uncore_find_type_by_id(uncore_msr_uncores, UNCORE_SPR_CHA); if (type) { @@ -6552,7 +6567,9 @@ int spr_uncore_pci_init(void) spr_update_device_location(UNCORE_SPR_M3UPI); uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI, UNCORE_SPR_PCI_EXTRA_UNCORES, - spr_pci_uncores); + spr_pci_uncores, + UNCORE_SPR_NUM_UNCORE_TYPES, + spr_uncores); return 0; } @@ -6560,15 +6577,116 @@ void spr_uncore_mmio_init(void) { int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true); - if (ret) - uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL); - else { + if (ret) { + uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL, + UNCORE_SPR_NUM_UNCORE_TYPES, + spr_uncores); + } else { uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, UNCORE_SPR_MMIO_EXTRA_UNCORES, - spr_mmio_uncores); + spr_mmio_uncores, + UNCORE_SPR_NUM_UNCORE_TYPES, + spr_uncores); spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2; } } /* end of SPR uncore support */ + +/* GNR uncore support */ + +#define UNCORE_GNR_NUM_UNCORE_TYPES 23 +#define UNCORE_GNR_TYPE_15 15 +#define UNCORE_GNR_B2UPI 18 +#define UNCORE_GNR_TYPE_21 21 +#define UNCORE_GNR_TYPE_22 22 + +int gnr_uncore_units_ignore[] = { + UNCORE_SPR_UPI, + UNCORE_GNR_TYPE_15, + UNCORE_GNR_B2UPI, + UNCORE_GNR_TYPE_21, + UNCORE_GNR_TYPE_22, + UNCORE_IGNORE_END +}; + +static struct intel_uncore_type gnr_uncore_ubox = { + .name = "ubox", + .attr_update = uncore_alias_groups, +}; + +static struct intel_uncore_type gnr_uncore_b2cmi = { + SPR_UNCORE_PCI_COMMON_FORMAT(), + .name = "b2cmi", +}; + +static struct intel_uncore_type gnr_uncore_b2cxl = { + SPR_UNCORE_MMIO_COMMON_FORMAT(), + .name = "b2cxl", +}; + +static struct intel_uncore_type gnr_uncore_mdf_sbo = { + .name = "mdf_sbo", + .attr_update = uncore_alias_groups, +}; + +static struct intel_uncore_type *gnr_uncores[UNCORE_GNR_NUM_UNCORE_TYPES] = { + &spr_uncore_chabox, + &spr_uncore_iio, + &spr_uncore_irp, + NULL, + &spr_uncore_pcu, + &gnr_uncore_ubox, + &spr_uncore_imc, + NULL, + NULL, + NULL, + NULL, + NULL, + NULL, + NULL, + NULL, + NULL, + &gnr_uncore_b2cmi, + &gnr_uncore_b2cxl, + NULL, + NULL, + &gnr_uncore_mdf_sbo, + NULL, + NULL, +}; + +static struct freerunning_counters gnr_iio_freerunning[] = { + [SPR_IIO_MSR_IOCLK] = { 0x290e, 0x01, 0x10, 1, 48 }, + [SPR_IIO_MSR_BW_IN] = { 0x360e, 0x10, 0x80, 8, 48 }, + [SPR_IIO_MSR_BW_OUT] = { 0x2e0e, 0x10, 0x80, 8, 48 }, +}; + +void gnr_uncore_cpu_init(void) +{ + uncore_msr_uncores = uncore_get_uncores(UNCORE_ACCESS_MSR, + UNCORE_SPR_MSR_EXTRA_UNCORES, + spr_msr_uncores, + UNCORE_GNR_NUM_UNCORE_TYPES, + gnr_uncores); + spr_uncore_iio_free_running.num_boxes = uncore_type_max_boxes(uncore_msr_uncores, UNCORE_SPR_IIO); + spr_uncore_iio_free_running.freerunning = gnr_iio_freerunning; +} + +int gnr_uncore_pci_init(void) +{ + uncore_pci_uncores = uncore_get_uncores(UNCORE_ACCESS_PCI, 0, NULL, + UNCORE_GNR_NUM_UNCORE_TYPES, + gnr_uncores); + return 0; +} + +void gnr_uncore_mmio_init(void) +{ + uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL, + UNCORE_GNR_NUM_UNCORE_TYPES, + gnr_uncores); +} + +/* end of GNR uncore support */ diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 53dd5d495ba6..fb56518356ec 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -110,6 +110,11 @@ static inline bool is_topdown_event(struct perf_event *event) return is_metric_event(event) || is_slots_event(event); } +static inline bool is_branch_counters_group(struct perf_event *event) +{ + return event->group_leader->hw.flags & PERF_X86_EVENT_BRANCH_COUNTERS; +} + struct amd_nb { int nb_id; /* NorthBridge id */ int refcnt; /* reference count */ @@ -283,6 +288,7 @@ struct cpu_hw_events { int lbr_pebs_users; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; + u64 lbr_counters[MAX_LBR_ENTRIES]; /* branch stack extra */ union { struct er_account *lbr_sel; struct er_account *lbr_ctl; @@ -888,6 +894,7 @@ struct x86_pmu { unsigned int lbr_mispred:1; unsigned int lbr_timed_lbr:1; unsigned int lbr_br_type:1; + unsigned int lbr_counters:4; void (*lbr_reset)(void); void (*lbr_read)(struct cpu_hw_events *cpuc); @@ -1012,6 +1019,7 @@ do { \ #define PMU_FL_INSTR_LATENCY 0x80 /* Support Instruction Latency in PEBS Memory Info Record */ #define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */ #define PMU_FL_RETIRE_LATENCY 0x200 /* Support Retire Latency in PEBS */ +#define PMU_FL_BR_CNTR 0x400 /* Support branch counter logging */ #define EVENT_VAR(_id) event_attr_##_id #define EVENT_PTR(_id) &event_attr_##_id.attr.attr @@ -1552,6 +1560,10 @@ void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr); void intel_ds_init(void); +void intel_pmu_lbr_save_brstack(struct perf_sample_data *data, + struct cpu_hw_events *cpuc, + struct perf_event *event); + void intel_pmu_lbr_swap_task_ctx(struct perf_event_pmu_context *prev_epc, struct perf_event_pmu_context *next_epc); diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h index 1dc19b9b4426..6c977c19f2cd 100644 --- a/arch/x86/events/perf_event_flags.h +++ b/arch/x86/events/perf_event_flags.h @@ -20,3 +20,5 @@ PERF_ARCH(TOPDOWN, 0x04000) /* Count Topdown slots/metrics events */ PERF_ARCH(PEBS_STLAT, 0x08000) /* st+stlat data address sampling */ PERF_ARCH(AMD_BRS, 0x10000) /* AMD Branch Sampling */ PERF_ARCH(PEBS_LAT_HYBRID, 0x20000) /* ld and st lat for hybrid */ +PERF_ARCH(NEEDS_BRANCH_STACK, 0x40000) /* require branch stack setup */ +PERF_ARCH(BRANCH_COUNTERS, 0x80000) /* logs the counters in the extra space of each branch */ diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 97bfe5f0531f..5fc45543e955 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -209,7 +209,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector, /* * This particular version of the IPI hypercall can - * only target upto 64 CPUs. + * only target up to 64 CPUs. */ if (vcpu >= 64) goto do_ex_hypercall; diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c index 42c70d28ef27..3215a4a07408 100644 --- a/arch/x86/hyperv/irqdomain.c +++ b/arch/x86/hyperv/irqdomain.c @@ -212,7 +212,7 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) * This interrupt is already mapped. Let's unmap first. * * We don't use retarget interrupt hypercalls here because - * Microsoft Hypervisor doens't allow root to change the vector + * Microsoft Hypervisor doesn't allow root to change the vector * or specify VPs outside of the set that is initially used * during mapping. */ diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c index 02e55237d919..7dcbf153ad72 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -144,7 +144,7 @@ void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason) /* Tell the hypervisor what went wrong. */ val |= GHCB_SEV_TERM_REASON(set, reason); - /* Request Guest Termination from Hypvervisor */ + /* Request Guest Termination from Hypervisor */ wr_ghcb_msr(val); VMGEXIT(); diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 65f79092c9d9..fcd20c6dc7f9 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -10,6 +10,9 @@ #define ALT_FLAG_NOT (1 << 0) #define ALT_NOT(feature) ((ALT_FLAG_NOT << ALT_FLAGS_SHIFT) | (feature)) +#define ALT_FLAG_DIRECT_CALL (1 << 1) +#define ALT_DIRECT_CALL(feature) ((ALT_FLAG_DIRECT_CALL << ALT_FLAGS_SHIFT) | (feature)) +#define ALT_CALL_ALWAYS ALT_DIRECT_CALL(X86_FEATURE_ALWAYS) #ifndef __ASSEMBLY__ @@ -86,6 +89,8 @@ struct alt_instr { u8 replacementlen; /* length of new instruction */ } __packed; +extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; + /* * Debug flag that can be tested to see whether alternative * instructions were patched in already: @@ -101,11 +106,10 @@ extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine, s32 *start_cfi, s32 *end_cfi); struct module; -struct paravirt_patch_site; struct callthunk_sites { s32 *call_start, *call_end; - struct paravirt_patch_site *pv_start, *pv_end; + struct alt_instr *alt_start, *alt_end; }; #ifdef CONFIG_CALL_THUNKS @@ -150,6 +154,8 @@ static inline int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ +#define ALT_CALL_INSTR "call BUG_func" + #define b_replacement(num) "664"#num #define e_replacement(num) "665"#num @@ -330,6 +336,22 @@ static inline int alternatives_text_reserved(void *start, void *end) */ #define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr +/* Macro for creating assembler functions avoiding any C magic. */ +#define DEFINE_ASM_FUNC(func, instr, sec) \ + asm (".pushsection " #sec ", \"ax\"\n" \ + ".global " #func "\n\t" \ + ".type " #func ", @function\n\t" \ + ASM_FUNC_ALIGN "\n" \ + #func ":\n\t" \ + ASM_ENDBR \ + instr "\n\t" \ + ASM_RET \ + ".size " #func ", . - " #func "\n\t" \ + ".popsection") + +void BUG_func(void); +void nop_func(void); + #else /* __ASSEMBLY__ */ #ifdef CONFIG_SMP @@ -370,6 +392,10 @@ static inline int alternatives_text_reserved(void *start, void *end) .byte \alt_len .endm +.macro ALT_CALL_INSTR + call BUG_func +.endm + /* * Define an alternative between two instructions. If @feature is * present, early code in apply_alternatives() replaces @oldinstr with diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index ed0eaf65c437..5c37944c8a5e 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -104,7 +104,7 @@ 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 */ + /* GART present only on Fam15h, up to model 0fh */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10)) return true; diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index d21f48f1c242..9d159b771dc8 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -272,8 +272,6 @@ struct apic { void (*send_IPI_all)(int vector); void (*send_IPI_self)(int vector); - enum apic_delivery_modes delivery_mode; - u32 disable_esr : 1, dest_mode_logical : 1, x2apic_set_max_apicid : 1, diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h index 4b125e5b3187..094106b6a538 100644 --- a/arch/x86/include/asm/apicdef.h +++ b/arch/x86/include/asm/apicdef.h @@ -20,6 +20,13 @@ */ #define IO_APIC_SLOT_SIZE 1024 +#define APIC_DELIVERY_MODE_FIXED 0 +#define APIC_DELIVERY_MODE_LOWESTPRIO 1 +#define APIC_DELIVERY_MODE_SMI 2 +#define APIC_DELIVERY_MODE_NMI 4 +#define APIC_DELIVERY_MODE_INIT 5 +#define APIC_DELIVERY_MODE_EXTINT 7 + #define APIC_ID 0x20 #define APIC_LVR 0x30 @@ -165,279 +172,10 @@ #define APIC_CPUID(apicid) ((apicid) & XAPIC_DEST_CPUS_MASK) #define NUM_APIC_CLUSTERS ((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT) -#ifndef __ASSEMBLY__ -/* - * the local APIC register structure, memory mapped. Not terribly well - * tested, but we might eventually use this one in the future - the - * problem why we cannot use it right now is the P5 APIC, it has an - * errata which cannot take 8-bit reads and writes, only 32-bit ones ... - */ -#define u32 unsigned int - -struct local_apic { - -/*000*/ struct { u32 __reserved[4]; } __reserved_01; - -/*010*/ struct { u32 __reserved[4]; } __reserved_02; - -/*020*/ struct { /* APIC ID Register */ - u32 __reserved_1 : 24, - phys_apic_id : 4, - __reserved_2 : 4; - u32 __reserved[3]; - } id; - -/*030*/ const - struct { /* APIC Version Register */ - u32 version : 8, - __reserved_1 : 8, - max_lvt : 8, - __reserved_2 : 8; - u32 __reserved[3]; - } version; - -/*040*/ struct { u32 __reserved[4]; } __reserved_03; - -/*050*/ struct { u32 __reserved[4]; } __reserved_04; - -/*060*/ struct { u32 __reserved[4]; } __reserved_05; - -/*070*/ struct { u32 __reserved[4]; } __reserved_06; - -/*080*/ struct { /* Task Priority Register */ - u32 priority : 8, - __reserved_1 : 24; - u32 __reserved_2[3]; - } tpr; - -/*090*/ const - struct { /* Arbitration Priority Register */ - u32 priority : 8, - __reserved_1 : 24; - u32 __reserved_2[3]; - } apr; - -/*0A0*/ const - struct { /* Processor Priority Register */ - u32 priority : 8, - __reserved_1 : 24; - u32 __reserved_2[3]; - } ppr; - -/*0B0*/ struct { /* End Of Interrupt Register */ - u32 eoi; - u32 __reserved[3]; - } eoi; - -/*0C0*/ struct { u32 __reserved[4]; } __reserved_07; - -/*0D0*/ struct { /* Logical Destination Register */ - u32 __reserved_1 : 24, - logical_dest : 8; - u32 __reserved_2[3]; - } ldr; - -/*0E0*/ struct { /* Destination Format Register */ - u32 __reserved_1 : 28, - model : 4; - u32 __reserved_2[3]; - } dfr; - -/*0F0*/ struct { /* Spurious Interrupt Vector Register */ - u32 spurious_vector : 8, - apic_enabled : 1, - focus_cpu : 1, - __reserved_2 : 22; - u32 __reserved_3[3]; - } svr; - -/*100*/ struct { /* In Service Register */ -/*170*/ u32 bitfield; - u32 __reserved[3]; - } isr [8]; - -/*180*/ struct { /* Trigger Mode Register */ -/*1F0*/ u32 bitfield; - u32 __reserved[3]; - } tmr [8]; - -/*200*/ struct { /* Interrupt Request Register */ -/*270*/ u32 bitfield; - u32 __reserved[3]; - } irr [8]; - -/*280*/ union { /* Error Status Register */ - struct { - u32 send_cs_error : 1, - receive_cs_error : 1, - send_accept_error : 1, - receive_accept_error : 1, - __reserved_1 : 1, - send_illegal_vector : 1, - receive_illegal_vector : 1, - illegal_register_address : 1, - __reserved_2 : 24; - u32 __reserved_3[3]; - } error_bits; - struct { - u32 errors; - u32 __reserved_3[3]; - } all_errors; - } esr; - -/*290*/ struct { u32 __reserved[4]; } __reserved_08; - -/*2A0*/ struct { u32 __reserved[4]; } __reserved_09; - -/*2B0*/ struct { u32 __reserved[4]; } __reserved_10; - -/*2C0*/ struct { u32 __reserved[4]; } __reserved_11; - -/*2D0*/ struct { u32 __reserved[4]; } __reserved_12; - -/*2E0*/ struct { u32 __reserved[4]; } __reserved_13; - -/*2F0*/ struct { u32 __reserved[4]; } __reserved_14; - -/*300*/ struct { /* Interrupt Command Register 1 */ - u32 vector : 8, - delivery_mode : 3, - destination_mode : 1, - delivery_status : 1, - __reserved_1 : 1, - level : 1, - trigger : 1, - __reserved_2 : 2, - shorthand : 2, - __reserved_3 : 12; - u32 __reserved_4[3]; - } icr1; - -/*310*/ struct { /* Interrupt Command Register 2 */ - union { - u32 __reserved_1 : 24, - phys_dest : 4, - __reserved_2 : 4; - u32 __reserved_3 : 24, - logical_dest : 8; - } dest; - u32 __reserved_4[3]; - } icr2; - -/*320*/ struct { /* LVT - Timer */ - u32 vector : 8, - __reserved_1 : 4, - delivery_status : 1, - __reserved_2 : 3, - mask : 1, - timer_mode : 1, - __reserved_3 : 14; - u32 __reserved_4[3]; - } lvt_timer; - -/*330*/ struct { /* LVT - Thermal Sensor */ - u32 vector : 8, - delivery_mode : 3, - __reserved_1 : 1, - delivery_status : 1, - __reserved_2 : 3, - mask : 1, - __reserved_3 : 15; - u32 __reserved_4[3]; - } lvt_thermal; - -/*340*/ struct { /* LVT - Performance Counter */ - u32 vector : 8, - delivery_mode : 3, - __reserved_1 : 1, - delivery_status : 1, - __reserved_2 : 3, - mask : 1, - __reserved_3 : 15; - u32 __reserved_4[3]; - } lvt_pc; - -/*350*/ struct { /* LVT - LINT0 */ - u32 vector : 8, - delivery_mode : 3, - __reserved_1 : 1, - delivery_status : 1, - polarity : 1, - remote_irr : 1, - trigger : 1, - mask : 1, - __reserved_2 : 15; - u32 __reserved_3[3]; - } lvt_lint0; - -/*360*/ struct { /* LVT - LINT1 */ - u32 vector : 8, - delivery_mode : 3, - __reserved_1 : 1, - delivery_status : 1, - polarity : 1, - remote_irr : 1, - trigger : 1, - mask : 1, - __reserved_2 : 15; - u32 __reserved_3[3]; - } lvt_lint1; - -/*370*/ struct { /* LVT - Error */ - u32 vector : 8, - __reserved_1 : 4, - delivery_status : 1, - __reserved_2 : 3, - mask : 1, - __reserved_3 : 15; - u32 __reserved_4[3]; - } lvt_error; - -/*380*/ struct { /* Timer Initial Count Register */ - u32 initial_count; - u32 __reserved_2[3]; - } timer_icr; - -/*390*/ const - struct { /* Timer Current Count Register */ - u32 curr_count; - u32 __reserved_2[3]; - } timer_ccr; - -/*3A0*/ struct { u32 __reserved[4]; } __reserved_16; - -/*3B0*/ struct { u32 __reserved[4]; } __reserved_17; - -/*3C0*/ struct { u32 __reserved[4]; } __reserved_18; - -/*3D0*/ struct { u32 __reserved[4]; } __reserved_19; - -/*3E0*/ struct { /* Timer Divide Configuration Register */ - u32 divisor : 4, - __reserved_1 : 28; - u32 __reserved_2[3]; - } timer_dcr; - -/*3F0*/ struct { u32 __reserved[4]; } __reserved_20; - -} __attribute__ ((packed)); - -#undef u32 - #ifdef CONFIG_X86_32 #define BAD_APICID 0xFFu #else #define BAD_APICID 0xFFFFu #endif -enum apic_delivery_modes { - APIC_DELIVERY_MODE_FIXED = 0, - APIC_DELIVERY_MODE_LOWESTPRIO = 1, - APIC_DELIVERY_MODE_SMI = 2, - APIC_DELIVERY_MODE_NMI = 4, - APIC_DELIVERY_MODE_INIT = 5, - APIC_DELIVERY_MODE_EXTINT = 7, -}; - -#endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_APICDEF_H */ diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 35389b2af88e..0216f63a366b 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -81,22 +81,4 @@ do { \ #include <asm-generic/barrier.h> -/* - * Make previous memory operations globally visible before - * a WRMSR. - * - * MFENCE makes writes visible, but only affects load/store - * instructions. WRMSR is unfortunately not a load/store - * instruction and is unaffected by MFENCE. The LFENCE ensures - * that the WRMSR is not reordered. - * - * Most WRMSRs are full serializing instructions themselves and - * do not require this barrier. This is only required for the - * IA32_TSC_DEADLINE and X2APIC MSRs. - */ -static inline void weak_wrmsr_fence(void) -{ - asm volatile("mfence; lfence" : : : "memory"); -} - #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h index 58dacd90daef..7cd752557905 100644 --- a/arch/x86/include/asm/cfi.h +++ b/arch/x86/include/asm/cfi.h @@ -7,16 +7,140 @@ * * Copyright (C) 2022 Google LLC */ +#include <linux/bug.h> +#include <asm/ibt.h> -#include <linux/cfi.h> +/* + * An overview of the various calling conventions... + * + * Traditional: + * + * foo: + * ... code here ... + * ret + * + * direct caller: + * call foo + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * call *%r11 + * + * + * IBT: + * + * foo: + * endbr64 + * ... code here ... + * ret + * + * direct caller: + * call foo / call foo+4 + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * call *%r11 + * + * + * kCFI: + * + * __cfi_foo: + * movl $0x12345678, %eax + * # 11 nops when CONFIG_CALL_PADDING + * foo: + * endbr64 # when IBT + * ... code here ... + * ret + * + * direct call: + * call foo # / call foo+4 when IBT + * + * indirect call: + * lea foo(%rip), %r11 + * ... + * movl $(-0x12345678), %r10d + * addl -4(%r11), %r10d # -15 when CONFIG_CALL_PADDING + * jz 1f + * ud2 + * 1:call *%r11 + * + * + * FineIBT (builds as kCFI + CALL_PADDING + IBT + RETPOLINE and runtime patches into): + * + * __cfi_foo: + * endbr64 + * subl 0x12345678, %r10d + * jz foo + * ud2 + * nop + * foo: + * osp nop3 # was endbr64 + * ... code here ... + * ret + * + * direct caller: + * call foo / call foo+4 + * + * indirect caller: + * lea foo(%rip), %r11 + * ... + * movl $0x12345678, %r10d + * subl $16, %r11 + * nop4 + * call *%r11 + * + */ +enum cfi_mode { + CFI_DEFAULT, /* FineIBT if hardware has IBT, otherwise kCFI */ + CFI_OFF, /* Taditional / IBT depending on .config */ + CFI_KCFI, /* Optionally CALL_PADDING, IBT, RETPOLINE */ + CFI_FINEIBT, /* see arch/x86/kernel/alternative.c */ +}; + +extern enum cfi_mode cfi_mode; + +struct pt_regs; #ifdef CONFIG_CFI_CLANG enum bug_trap_type handle_cfi_failure(struct pt_regs *regs); +#define __bpfcall +extern u32 cfi_bpf_hash; +extern u32 cfi_bpf_subprog_hash; + +static inline int cfi_get_offset(void) +{ + switch (cfi_mode) { + case CFI_FINEIBT: + return 16; + case CFI_KCFI: + if (IS_ENABLED(CONFIG_CALL_PADDING)) + return 16; + return 5; + default: + return 0; + } +} +#define cfi_get_offset cfi_get_offset + +extern u32 cfi_get_func_hash(void *func); + #else static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs) { return BUG_TRAP_TYPE_NONE; } +#define cfi_bpf_hash 0U +#define cfi_bpf_subprog_hash 0U +static inline u32 cfi_get_func_hash(void *func) +{ + return 0; +} #endif /* CONFIG_CFI_CLANG */ +#if HAS_KERNEL_IBT == 1 +#define CFI_NOSEAL(x) asm(IBT_NOSEAL(__stringify(x))) +#endif + #endif /* _ASM_X86_CFI_H */ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 4af140cf5719..632c26cdeeda 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -218,7 +218,7 @@ #define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ #define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ -#define X86_FEATURE_ZEN (7*32+28) /* "" CPU based on Zen microarchitecture */ +#define X86_FEATURE_ZEN ( 7*32+28) /* "" Generic flag for all Zen and newer */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ #define X86_FEATURE_IBRS_ENHANCED ( 7*32+30) /* Enhanced IBRS */ #define X86_FEATURE_MSR_IA32_FEAT_CTL ( 7*32+31) /* "" MSR IA32_FEAT_CTL configured */ @@ -308,10 +308,14 @@ #define X86_FEATURE_SMBA (11*32+21) /* "" Slow Memory Bandwidth Allocation */ #define X86_FEATURE_BMEC (11*32+22) /* "" Bandwidth Monitoring Event Configuration */ #define X86_FEATURE_USER_SHSTK (11*32+23) /* Shadow stack support for user mode applications */ - #define X86_FEATURE_SRSO (11*32+24) /* "" AMD BTB untrain RETs */ #define X86_FEATURE_SRSO_ALIAS (11*32+25) /* "" AMD BTB untrain RETs through aliasing */ #define X86_FEATURE_IBPB_ON_VMEXIT (11*32+26) /* "" Issue an IBPB only on VMEXIT */ +#define X86_FEATURE_APIC_MSRS_FENCE (11*32+27) /* "" IA32_TSC_DEADLINE and X2APIC MSRs need fencing */ +#define X86_FEATURE_ZEN2 (11*32+28) /* "" CPU based on Zen2 microarchitecture */ +#define X86_FEATURE_ZEN3 (11*32+29) /* "" CPU based on Zen3 microarchitecture */ +#define X86_FEATURE_ZEN4 (11*32+30) /* "" CPU based on Zen4 microarchitecture */ +#define X86_FEATURE_ZEN1 (11*32+31) /* "" CPU based on Zen1 microarchitecture */ /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index a1168e7b69e5..dd4b67101bb7 100644 --- a/arch/x86/include/asm/current.h +++ b/arch/x86/include/asm/current.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_CURRENT_H #define _ASM_X86_CURRENT_H +#include <linux/build_bug.h> #include <linux/compiler.h> #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h index 66eb5e1ac4fb..0cec92c430cc 100644 --- a/arch/x86/include/asm/debugreg.h +++ b/arch/x86/include/asm/debugreg.h @@ -5,6 +5,7 @@ #include <linux/bug.h> #include <linux/percpu.h> #include <uapi/asm/debugreg.h> +#include <asm/cpufeature.h> DECLARE_PER_CPU(unsigned long, cpu_dr7); diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h index f7e7099af595..d440a65af8f3 100644 --- a/arch/x86/include/asm/desc_defs.h +++ b/arch/x86/include/asm/desc_defs.h @@ -8,6 +8,56 @@ * archs. */ +/* + * Low-level interface mapping flags/field names to bits + */ + +/* Flags for _DESC_S (non-system) descriptors */ +#define _DESC_ACCESSED 0x0001 +#define _DESC_DATA_WRITABLE 0x0002 +#define _DESC_CODE_READABLE 0x0002 +#define _DESC_DATA_EXPAND_DOWN 0x0004 +#define _DESC_CODE_CONFORMING 0x0004 +#define _DESC_CODE_EXECUTABLE 0x0008 + +/* Common flags */ +#define _DESC_S 0x0010 +#define _DESC_DPL(dpl) ((dpl) << 5) +#define _DESC_PRESENT 0x0080 + +#define _DESC_LONG_CODE 0x2000 +#define _DESC_DB 0x4000 +#define _DESC_GRANULARITY_4K 0x8000 + +/* System descriptors have a numeric "type" field instead of flags */ +#define _DESC_SYSTEM(code) (code) + +/* + * High-level interface mapping intended usage to low-level combinations + * of flags + */ + +#define _DESC_DATA (_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \ + _DESC_DATA_WRITABLE) +#define _DESC_CODE (_DESC_S | _DESC_PRESENT | _DESC_ACCESSED | \ + _DESC_CODE_READABLE | _DESC_CODE_EXECUTABLE) + +#define DESC_DATA16 (_DESC_DATA) +#define DESC_CODE16 (_DESC_CODE) + +#define DESC_DATA32 (_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB) +#define DESC_DATA32_BIOS (_DESC_DATA | _DESC_DB) + +#define DESC_CODE32 (_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_DB) +#define DESC_CODE32_BIOS (_DESC_CODE | _DESC_DB) + +#define DESC_TSS32 (_DESC_SYSTEM(9) | _DESC_PRESENT) + +#define DESC_DATA64 (_DESC_DATA | _DESC_GRANULARITY_4K | _DESC_DB) +#define DESC_CODE64 (_DESC_CODE | _DESC_GRANULARITY_4K | _DESC_LONG_CODE) + +#define DESC_USER (_DESC_DPL(3)) + #ifndef __ASSEMBLY__ #include <linux/types.h> @@ -22,19 +72,19 @@ struct desc_struct { #define GDT_ENTRY_INIT(flags, base, limit) \ { \ - .limit0 = (u16) (limit), \ - .limit1 = ((limit) >> 16) & 0x0F, \ - .base0 = (u16) (base), \ - .base1 = ((base) >> 16) & 0xFF, \ - .base2 = ((base) >> 24) & 0xFF, \ - .type = (flags & 0x0f), \ - .s = (flags >> 4) & 0x01, \ - .dpl = (flags >> 5) & 0x03, \ - .p = (flags >> 7) & 0x01, \ - .avl = (flags >> 12) & 0x01, \ - .l = (flags >> 13) & 0x01, \ - .d = (flags >> 14) & 0x01, \ - .g = (flags >> 15) & 0x01, \ + .limit0 = ((limit) >> 0) & 0xFFFF, \ + .limit1 = ((limit) >> 16) & 0x000F, \ + .base0 = ((base) >> 0) & 0xFFFF, \ + .base1 = ((base) >> 16) & 0x00FF, \ + .base2 = ((base) >> 24) & 0x00FF, \ + .type = ((flags) >> 0) & 0x000F, \ + .s = ((flags) >> 4) & 0x0001, \ + .dpl = ((flags) >> 5) & 0x0003, \ + .p = ((flags) >> 7) & 0x0001, \ + .avl = ((flags) >> 12) & 0x0001, \ + .l = ((flags) >> 13) & 0x0001, \ + .d = ((flags) >> 14) & 0x0001, \ + .g = ((flags) >> 15) & 0x0001, \ } enum { @@ -94,6 +144,7 @@ struct gate_struct { typedef struct gate_struct gate_desc; +#ifndef _SETUP static inline unsigned long gate_offset(const gate_desc *g) { #ifdef CONFIG_X86_64 @@ -108,6 +159,7 @@ static inline unsigned long gate_segment(const gate_desc *g) { return g->segment; } +#endif struct desc_ptr { unsigned short size; diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index a0234dfd1031..1e16bd5ac781 100644 --- a/arch/x86/include/asm/elf.h +++ b/arch/x86/include/asm/elf.h @@ -150,7 +150,7 @@ do { \ ((x)->e_machine == EM_X86_64) #define compat_elf_check_arch(x) \ - ((elf_check_arch_ia32(x) && ia32_enabled()) || \ + ((elf_check_arch_ia32(x) && ia32_enabled_verbose()) || \ (IS_ENABLED(CONFIG_X86_X32_ABI) && (x)->e_machine == EM_X86_64)) static inline void elf_common_init(struct thread_struct *t, diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h index 991e31cfde94..fe6312045042 100644 --- a/arch/x86/include/asm/extable_fixup_types.h +++ b/arch/x86/include/asm/extable_fixup_types.h @@ -4,7 +4,7 @@ /* * Our IMM is signed, as such it must live at the top end of the word. Also, - * since C99 hex constants are of ambigious type, force cast the mask to 'int' + * since C99 hex constants are of ambiguous type, force cast the mask to 'int' * so that FIELD_GET() will DTRT and sign extend the value when it extracts it. */ #define EX_DATA_TYPE_MASK ((int)0x000000FF) diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index eb810074f1e7..ace9aa3b78a3 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -5,6 +5,8 @@ #ifndef _ASM_X86_FPU_H #define _ASM_X86_FPU_H +#include <asm/page_types.h> + /* * The legacy x87 FPU state format, as saved by FSAVE and * restored by the FRSTOR instructions: @@ -415,7 +417,7 @@ struct fpu_state_perm { * * This master permission field is only to be used when * task.fpu.fpstate based checks fail to validate whether the task - * is allowed to expand it's xfeatures set which requires to + * is allowed to expand its xfeatures set which requires to * allocate a larger sized fpstate buffer. * * Do not access this field directly. Use the provided helper diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h index 5a2ae24b1204..c7ef6ea2fa99 100644 --- a/arch/x86/include/asm/ia32.h +++ b/arch/x86/include/asm/ia32.h @@ -2,7 +2,6 @@ #ifndef _ASM_X86_IA32_H #define _ASM_X86_IA32_H - #ifdef CONFIG_IA32_EMULATION #include <linux/compat.h> @@ -75,6 +74,11 @@ static inline bool ia32_enabled(void) return __ia32_enabled; } +static inline void ia32_disable(void) +{ + __ia32_enabled = false; +} + #else /* !CONFIG_IA32_EMULATION */ static inline bool ia32_enabled(void) @@ -82,6 +86,18 @@ static inline bool ia32_enabled(void) return IS_ENABLED(CONFIG_X86_32); } +static inline void ia32_disable(void) {} + #endif +static inline bool ia32_enabled_verbose(void) +{ + bool enabled = ia32_enabled(); + + if (IS_ENABLED(CONFIG_IA32_EMULATION) && !enabled) + pr_notice_once("32-bit emulation disabled. You can reenable with ia32_emulation=on\n"); + + return enabled; +} + #endif /* _ASM_X86_IA32_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index 05fd175cec7d..13639e57e1f8 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -569,6 +569,10 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_UD, exc_invalid_op); DECLARE_IDTENTRY_RAW(X86_TRAP_BP, exc_int3); DECLARE_IDTENTRY_RAW_ERRORCODE(X86_TRAP_PF, exc_page_fault); +#if defined(CONFIG_IA32_EMULATION) +DECLARE_IDTENTRY_RAW(IA32_SYSCALL_VECTOR, int80_emulation); +#endif + #ifdef CONFIG_X86_MCE #ifdef CONFIG_X86_64 DECLARE_IDTENTRY_MCE(X86_TRAP_MC, exc_machine_check); diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 76238842406a..3814a9263d64 100644 --- a/arch/x86/include/asm/io.h +++ b/arch/x86/include/asm/io.h @@ -242,7 +242,7 @@ static inline void slow_down_io(void) #endif -#define BUILDIO(bwl, bw, type) \ +#define BUILDIO(bwl, type) \ static inline void out##bwl##_p(type value, u16 port) \ { \ out##bwl(value, port); \ @@ -288,9 +288,9 @@ static inline void ins##bwl(u16 port, void *addr, unsigned long count) \ } \ } -BUILDIO(b, b, u8) -BUILDIO(w, w, u16) -BUILDIO(l, , u32) +BUILDIO(b, u8) +BUILDIO(w, u16) +BUILDIO(l, u32) #undef BUILDIO #define inb_p inb_p diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index a1911fea8739..af7541c11821 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -111,7 +111,7 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); * 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 + * Note on these systems the i2c-bus driver will request a semaphore from the * P-Unit for exclusive access to the PMIC bus when i2c drivers are accessing * it, but this does not appear to be sufficient, we still need to avoid making * certain P-Unit requests during the access window to avoid problems. diff --git a/arch/x86/include/asm/irq_work.h b/arch/x86/include/asm/irq_work.h index 800ffce0db29..6b4d36c95165 100644 --- a/arch/x86/include/asm/irq_work.h +++ b/arch/x86/include/asm/irq_work.h @@ -9,7 +9,6 @@ static inline bool arch_irq_work_has_interrupt(void) { return boot_cpu_has(X86_FEATURE_APIC); } -extern void arch_irq_work_raise(void); #else static inline bool arch_irq_work_has_interrupt(void) { diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d7036982332e..6711da000bb7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1652,7 +1652,7 @@ struct kvm_x86_ops { /* Whether or not a virtual NMI is pending in hardware. */ bool (*is_vnmi_pending)(struct kvm_vcpu *vcpu); /* - * Attempt to pend a virtual NMI in harware. Returns %true on success + * Attempt to pend a virtual NMI in hardware. Returns %true on success * to allow using static_call_ret0 as the fallback. */ bool (*set_vnmi_pending)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6de6e1d95952..de3118305838 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -311,6 +311,7 @@ enum smca_bank_types { SMCA_PIE, /* Power, Interrupts, etc. */ SMCA_UMC, /* Unified Memory Controller */ SMCA_UMC_V2, + SMCA_MA_LLC, /* Memory Attached Last Level Cache */ SMCA_PB, /* Parameter Block */ SMCA_PSP, /* Platform Security Processor */ SMCA_PSP_V2, @@ -326,6 +327,8 @@ enum smca_bank_types { SMCA_SHUB, /* System HUB Unit */ SMCA_SATA, /* SATA Unit */ SMCA_USB, /* USB Unit */ + SMCA_USR_DP, /* Ultra Short Reach Data Plane Controller */ + SMCA_USR_CP, /* Ultra Short Reach Control Plane Controller */ SMCA_GMI_PCS, /* GMI PCS Unit */ SMCA_XGMI_PHY, /* xGMI PHY Unit */ SMCA_WAFL_PHY, /* WAFL PHY Unit */ @@ -333,7 +336,6 @@ enum smca_bank_types { N_SMCA_BANK_TYPES }; -extern const char *smca_get_long_name(enum smca_bank_types t); extern bool amd_mce_is_memory_error(struct mce *m); extern int mce_threshold_create_device(unsigned int cpu); diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 1d51e1850ed0..737a52b89e64 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -237,6 +237,11 @@ #define LBR_INFO_CYCLES 0xffff #define LBR_INFO_BR_TYPE_OFFSET 56 #define LBR_INFO_BR_TYPE (0xfull << LBR_INFO_BR_TYPE_OFFSET) +#define LBR_INFO_BR_CNTR_OFFSET 32 +#define LBR_INFO_BR_CNTR_NUM 4 +#define LBR_INFO_BR_CNTR_BITS 2 +#define LBR_INFO_BR_CNTR_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_BITS - 1, 0) +#define LBR_INFO_BR_CNTR_FULL_MASK GENMASK_ULL(LBR_INFO_BR_CNTR_NUM * LBR_INFO_BR_CNTR_BITS - 1, 0) #define MSR_ARCH_LBR_CTL 0x000014ce #define ARCH_LBR_CTL_LBREN BIT(0) diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index 778df05f8539..920426d691ce 100644 --- a/arch/x86/include/asm/mwait.h +++ b/arch/x86/include/asm/mwait.h @@ -87,6 +87,15 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx, :: "a" (eax), "b" (ebx), "c" (ecx)); } +/* + * Re-enable interrupts right upon calling mwait in such a way that + * no interrupt can fire _before_ the execution of mwait, ie: no + * instruction must be placed between "sti" and "mwait". + * + * This is necessary because if an interrupt queues a timer before + * executing mwait, it would otherwise go unnoticed and the next tick + * would not be reprogrammed accordingly before mwait ever wakes up. + */ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx) { mds_idle_clear_cpu_buffers(); @@ -115,8 +124,15 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo } __monitor((void *)¤t_thread_info()->flags, 0, 0); - if (!need_resched()) - __mwait(eax, ecx); + + if (!need_resched()) { + if (ecx & 1) { + __mwait(eax, ecx); + } else { + __sti_mwait(eax, ecx); + raw_local_irq_disable(); + } + } } current_clr_polling(); } diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f93e9b96927a..262e65539f83 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -49,7 +49,7 @@ * but there is still a cushion vs. the RSB depth. The algorithm does not * claim to be perfect and it can be speculated around by the CPU, but it * is considered that it obfuscates the problem enough to make exploitation - * extremly difficult. + * extremely difficult. */ #define RET_DEPTH_SHIFT 5 #define RSB_RET_STUFF_LOOPS 16 @@ -208,7 +208,7 @@ /* * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should - * eventually turn into it's own annotation. + * eventually turn into its own annotation. */ .macro VALIDATE_UNRET_END #if defined(CONFIG_NOINSTR_VALIDATION) && \ diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 6c8ff12140ae..d4eb9e1d61b8 100644 --- a/arch/x86/include/asm/paravirt.h +++ b/arch/x86/include/asm/paravirt.h @@ -6,6 +6,10 @@ #include <asm/paravirt_types.h> +#ifndef __ASSEMBLY__ +struct mm_struct; +#endif + #ifdef CONFIG_PARAVIRT #include <asm/pgtable_types.h> #include <asm/asm.h> @@ -142,8 +146,7 @@ static inline void write_cr0(unsigned long x) static __always_inline unsigned long read_cr2(void) { return PVOP_ALT_CALLEE0(unsigned long, mmu.read_cr2, - "mov %%cr2, %%rax;", - ALT_NOT(X86_FEATURE_XENPV)); + "mov %%cr2, %%rax;", ALT_NOT_XEN); } static __always_inline void write_cr2(unsigned long x) @@ -154,13 +157,12 @@ static __always_inline void write_cr2(unsigned long x) static inline unsigned long __read_cr3(void) { return PVOP_ALT_CALL0(unsigned long, mmu.read_cr3, - "mov %%cr3, %%rax;", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%cr3, %%rax;", ALT_NOT_XEN); } static inline void write_cr3(unsigned long x) { - PVOP_ALT_VCALL1(mmu.write_cr3, x, - "mov %%rdi, %%cr3", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALL1(mmu.write_cr3, x, "mov %%rdi, %%cr3", ALT_NOT_XEN); } static inline void __write_cr4(unsigned long x) @@ -182,7 +184,7 @@ extern noinstr void pv_native_wbinvd(void); static __always_inline void wbinvd(void) { - PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALL0(cpu.wbinvd, "wbinvd", ALT_NOT_XEN); } static inline u64 paravirt_read_msr(unsigned msr) @@ -390,27 +392,25 @@ static inline void paravirt_release_p4d(unsigned long pfn) static inline pte_t __pte(pteval_t val) { return (pte_t) { PVOP_ALT_CALLEE1(pteval_t, mmu.make_pte, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)) }; + "mov %%rdi, %%rax", ALT_NOT_XEN) }; } static inline pteval_t pte_val(pte_t pte) { return PVOP_ALT_CALLEE1(pteval_t, mmu.pte_val, pte.pte, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline pgd_t __pgd(pgdval_t val) { return (pgd_t) { PVOP_ALT_CALLEE1(pgdval_t, mmu.make_pgd, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)) }; + "mov %%rdi, %%rax", ALT_NOT_XEN) }; } static inline pgdval_t pgd_val(pgd_t pgd) { return PVOP_ALT_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION @@ -444,14 +444,13 @@ static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) static inline pmd_t __pmd(pmdval_t val) { return (pmd_t) { PVOP_ALT_CALLEE1(pmdval_t, mmu.make_pmd, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)) }; + "mov %%rdi, %%rax", ALT_NOT_XEN) }; } static inline pmdval_t pmd_val(pmd_t pmd) { return PVOP_ALT_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline void set_pud(pud_t *pudp, pud_t pud) @@ -464,7 +463,7 @@ static inline pud_t __pud(pudval_t val) pudval_t ret; ret = PVOP_ALT_CALLEE1(pudval_t, mmu.make_pud, val, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); return (pud_t) { ret }; } @@ -472,7 +471,7 @@ static inline pud_t __pud(pudval_t val) static inline pudval_t pud_val(pud_t pud) { return PVOP_ALT_CALLEE1(pudval_t, mmu.pud_val, pud.pud, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline void pud_clear(pud_t *pudp) @@ -492,8 +491,7 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) static inline p4d_t __p4d(p4dval_t val) { p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val, - "mov %%rdi, %%rax", - ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); return (p4d_t) { ret }; } @@ -501,7 +499,7 @@ static inline p4d_t __p4d(p4dval_t val) static inline p4dval_t p4d_val(p4d_t p4d) { return PVOP_ALT_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d, - "mov %%rdi, %%rax", ALT_NOT(X86_FEATURE_XENPV)); + "mov %%rdi, %%rax", ALT_NOT_XEN); } static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) @@ -687,17 +685,17 @@ bool __raw_callee_save___native_vcpu_is_preempted(long cpu); static __always_inline unsigned long arch_local_save_flags(void) { return PVOP_ALT_CALLEE0(unsigned long, irq.save_fl, "pushf; pop %%rax;", - ALT_NOT(X86_FEATURE_XENPV)); + ALT_NOT_XEN); } static __always_inline void arch_local_irq_disable(void) { - PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALLEE0(irq.irq_disable, "cli;", ALT_NOT_XEN); } static __always_inline void arch_local_irq_enable(void) { - PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT(X86_FEATURE_XENPV)); + PVOP_ALT_VCALLEE0(irq.irq_enable, "sti;", ALT_NOT_XEN); } static __always_inline unsigned long arch_local_irq_save(void) @@ -726,52 +724,25 @@ static __always_inline unsigned long arch_local_irq_save(void) #undef PVOP_VCALL4 #undef PVOP_CALL4 -#define DEFINE_PARAVIRT_ASM(func, instr, sec) \ - asm (".pushsection " #sec ", \"ax\"\n" \ - ".global " #func "\n\t" \ - ".type " #func ", @function\n\t" \ - ASM_FUNC_ALIGN "\n" \ - #func ":\n\t" \ - ASM_ENDBR \ - instr "\n\t" \ - ASM_RET \ - ".size " #func ", . - " #func "\n\t" \ - ".popsection") - extern void default_banner(void); void native_pv_lock_init(void) __init; #else /* __ASSEMBLY__ */ -#define _PVSITE(ptype, ops, word, algn) \ -771:; \ - ops; \ -772:; \ - .pushsection .parainstructions,"a"; \ - .align algn; \ - word 771b; \ - .byte ptype; \ - .byte 772b-771b; \ - _ASM_ALIGN; \ - .popsection - - #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT_XXL +#ifdef CONFIG_DEBUG_ENTRY -#define PARA_PATCH(off) ((off) / 8) -#define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) -#ifdef CONFIG_DEBUG_ENTRY .macro PARA_IRQ_save_fl - PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), - ANNOTATE_RETPOLINE_SAFE; - call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl);) + ANNOTATE_RETPOLINE_SAFE; + call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); .endm -#define SAVE_FLAGS ALTERNATIVE "PARA_IRQ_save_fl;", "pushf; pop %rax;", \ - ALT_NOT(X86_FEATURE_XENPV) +#define SAVE_FLAGS ALTERNATIVE_2 "PARA_IRQ_save_fl;", \ + "ALT_CALL_INSTR;", ALT_CALL_ALWAYS, \ + "pushf; pop %rax;", ALT_NOT_XEN #endif #endif /* CONFIG_PARAVIRT_XXL */ #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h index 772d03487520..8d4fbe1be489 100644 --- a/arch/x86/include/asm/paravirt_types.h +++ b/arch/x86/include/asm/paravirt_types.h @@ -2,18 +2,10 @@ #ifndef _ASM_X86_PARAVIRT_TYPES_H #define _ASM_X86_PARAVIRT_TYPES_H -#ifndef __ASSEMBLY__ -/* These all sit in the .parainstructions section to tell us what to patch. */ -struct paravirt_patch_site { - u8 *instr; /* original instructions */ - u8 type; /* type of this instruction */ - u8 len; /* length of original instruction */ -}; -#endif - #ifdef CONFIG_PARAVIRT #ifndef __ASSEMBLY__ +#include <linux/types.h> #include <asm/desc_defs.h> #include <asm/pgtable_types.h> @@ -250,43 +242,11 @@ struct paravirt_patch_template { extern struct pv_info pv_info; 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] "m" (pv_ops.op) -/* - * Generate some code, and mark it as patchable by the - * apply_paravirt() alternate instruction patcher. - */ -#define _paravirt_alt(insn_string, type) \ - "771:\n\t" insn_string "\n" "772:\n" \ - ".pushsection .parainstructions,\"a\"\n" \ - _ASM_ALIGN "\n" \ - _ASM_PTR " 771b\n" \ - " .byte " type "\n" \ - " .byte 772b-771b\n" \ - _ASM_ALIGN "\n" \ - ".popsection\n" - -/* Generate patchable code, with the default asm parameters. */ -#define paravirt_alt(insn_string) \ - _paravirt_alt(insn_string, "%c[paravirt_typenum]") - -/* Simple instruction patching code. */ -#define NATIVE_LABEL(a,x,b) "\n\t.globl " a #x "_" #b "\n" a #x "_" #b ":\n\t" - -unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, unsigned int len); +#define paravirt_ptr(op) [paravirt_opptr] "m" (pv_ops.op) int paravirt_disable_iospace(void); -/* - * This generates an indirect call based on the operation type number. - * The type number, computed in PARAVIRT_PATCH, is derived from the - * offset into the paravirt_patch_template structure, and can therefore be - * freely converted back into a structure offset. - */ +/* This generates an indirect call based on the operation type number. */ #define PARAVIRT_CALL \ ANNOTATE_RETPOLINE_SAFE \ "call *%[paravirt_opptr];" @@ -319,12 +279,6 @@ int paravirt_disable_iospace(void); * However, x86_64 also has to clobber all caller saved registers, which * unfortunately, are quite a bit (r8 - r11) * - * The call instruction itself is marked by placing its start address - * and size into the .parainstructions section, so that - * apply_paravirt() in arch/i386/kernel/alternative.c can do the - * appropriate patching under the control of the backend pv_init_ops - * implementation. - * * Unfortunately there's no way to get gcc to generate the args setup * for the call, and then allow the call itself to be generated by an * inline asm. Because of this, we must do the complete arg setup and @@ -423,14 +377,27 @@ int paravirt_disable_iospace(void); __mask & __eax; \ }) - +/* + * Use alternative patching for paravirt calls: + * - For replacing an indirect call with a direct one, use the "normal" + * ALTERNATIVE() macro with the indirect call as the initial code sequence, + * which will be replaced with the related direct call by using the + * ALT_FLAG_DIRECT_CALL special case and the "always on" feature. + * - In case the replacement is either a direct call or a short code sequence + * depending on a feature bit, the ALTERNATIVE_2() macro is being used. + * The indirect call is the initial code sequence again, while the special + * code sequence is selected with the specified feature bit. In case the + * feature is not active, the direct call is used as above via the + * ALT_FLAG_DIRECT_CALL special case and the "always on" feature. + */ #define ____PVOP_CALL(ret, op, call_clbr, extra_clbr, ...) \ ({ \ PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ - asm volatile(paravirt_alt(PARAVIRT_CALL) \ + asm volatile(ALTERNATIVE(PARAVIRT_CALL, ALT_CALL_INSTR, \ + ALT_CALL_ALWAYS) \ : call_clbr, ASM_CALL_CONSTRAINT \ - : paravirt_type(op), \ + : paravirt_ptr(op), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ ret; \ @@ -441,10 +408,11 @@ int paravirt_disable_iospace(void); ({ \ PVOP_CALL_ARGS; \ PVOP_TEST_NULL(op); \ - asm volatile(ALTERNATIVE(paravirt_alt(PARAVIRT_CALL), \ - alt, cond) \ + asm volatile(ALTERNATIVE_2(PARAVIRT_CALL, \ + ALT_CALL_INSTR, ALT_CALL_ALWAYS, \ + alt, cond) \ : call_clbr, ASM_CALL_CONSTRAINT \ - : paravirt_type(op), \ + : paravirt_ptr(op), \ ##__VA_ARGS__ \ : "memory", "cc" extra_clbr); \ ret; \ @@ -542,8 +510,6 @@ int paravirt_disable_iospace(void); __PVOP_VCALL(op, PVOP_CALL_ARG1(arg1), PVOP_CALL_ARG2(arg2), \ PVOP_CALL_ARG3(arg3), PVOP_CALL_ARG4(arg4)) -void _paravirt_nop(void); -void paravirt_BUG(void); unsigned long paravirt_ret0(void); #ifdef CONFIG_PARAVIRT_XXL u64 _paravirt_ident_64(u64); @@ -553,11 +519,11 @@ void pv_native_irq_enable(void); unsigned long pv_native_read_cr2(void); #endif -#define paravirt_nop ((void *)_paravirt_nop) - -extern struct paravirt_patch_site __parainstructions[], - __parainstructions_end[]; +#define paravirt_nop ((void *)nop_func) #endif /* __ASSEMBLY__ */ + +#define ALT_NOT_XEN ALT_NOT(X86_FEATURE_XENPV) + #endif /* CONFIG_PARAVIRT */ #endif /* _ASM_X86_PARAVIRT_TYPES_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 20624b80f890..5e01883eb51e 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -24,8 +24,8 @@ #else /* ...!ASSEMBLY */ -#include <linux/kernel.h> #include <linux/stringify.h> +#include <asm/asm.h> #ifdef CONFIG_SMP #define __percpu_prefix "%%"__stringify(__percpu_seg)":" diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 2618ec7c3d1d..3736b8a46c04 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -31,6 +31,7 @@ #define ARCH_PERFMON_EVENTSEL_ENABLE (1ULL << 22) #define ARCH_PERFMON_EVENTSEL_INV (1ULL << 23) #define ARCH_PERFMON_EVENTSEL_CMASK 0xFF000000ULL +#define ARCH_PERFMON_EVENTSEL_BR_CNTR (1ULL << 35) #define INTEL_FIXED_BITS_MASK 0xFULL #define INTEL_FIXED_BITS_STRIDE 4 @@ -223,6 +224,9 @@ union cpuid28_ecx { unsigned int lbr_timed_lbr:1; /* Branch Type Field Supported */ unsigned int lbr_br_type:1; + unsigned int reserved:13; + /* Branch counters (Event Logging) Supported */ + unsigned int lbr_counters:4; } split; unsigned int full; }; diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 57bab91bbf50..9d077bca6a10 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -141,6 +141,7 @@ static inline int pte_young(pte_t pte) return pte_flags(pte) & _PAGE_ACCESSED; } +#define pmd_dirty pmd_dirty static inline bool pmd_dirty(pmd_t pmd) { return pmd_flags(pmd) & _PAGE_DIRTY_BITS; @@ -1679,12 +1680,6 @@ static inline bool arch_has_pfn_modify_check(void) return boot_cpu_has_bug(X86_BUG_L1TF); } -#define arch_has_hw_pte_young arch_has_hw_pte_young -static inline bool arch_has_hw_pte_young(void) -{ - return true; -} - #define arch_check_zapped_pte arch_check_zapped_pte void arch_check_zapped_pte(struct vm_area_struct *vma, pte_t pte); diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index a629b1b9f65a..24af25b1551a 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -203,7 +203,7 @@ static inline void native_pgd_clear(pgd_t *pgd) * F (2) in swp entry is used to record when a pagetable is * writeprotected by userfaultfd WP support. * - * E (3) in swp entry is used to rememeber PG_anon_exclusive. + * E (3) in swp entry is used to remember PG_anon_exclusive. * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 4527e1430c6d..af77235fded6 100644 --- a/arch/x86/include/asm/preempt.h +++ b/arch/x86/include/asm/preempt.h @@ -6,7 +6,6 @@ #include <asm/percpu.h> #include <asm/current.h> -#include <linux/thread_info.h> #include <linux/static_call_types.h> /* We use the MSB mostly because its available */ diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index ae81a7191c1c..26620d7642a9 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -749,4 +749,22 @@ enum mds_mitigations { extern bool gds_ucode_mitigated(void); +/* + * Make previous memory operations globally visible before + * a WRMSR. + * + * MFENCE makes writes visible, but only affects load/store + * instructions. WRMSR is unfortunately not a load/store + * instruction and is unaffected by MFENCE. The LFENCE ensures + * that the WRMSR is not reordered. + * + * Most WRMSRs are full serializing instructions themselves and + * do not require this barrier. This is only required for the + * IA32_TSC_DEADLINE and X2APIC MSRs. + */ +static inline void weak_wrmsr_fence(void) +{ + alternative("mfence; lfence", "", ALT_NOT(X86_FEATURE_APIC_MSRS_FENCE)); +} + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h index 4d84122bd643..484f4f0131a5 100644 --- a/arch/x86/include/asm/proto.h +++ b/arch/x86/include/asm/proto.h @@ -32,10 +32,6 @@ void entry_SYSCALL_compat(void); void entry_SYSCALL_compat_safe_stack(void); void entry_SYSRETL_compat_unsafe_stack(void); void entry_SYSRETL_compat_end(void); -void entry_INT80_compat(void); -#ifdef CONFIG_XEN_PV -void xen_entry_INT80_compat(void); -#endif #else /* !CONFIG_IA32_EMULATION */ #define entry_SYSCALL_compat NULL #define entry_SYSENTER_compat NULL diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 85b6e3609cb9..ef9697f20129 100644 --- a/arch/x86/include/asm/qspinlock_paravirt.h +++ b/arch/x86/include/asm/qspinlock_paravirt.h @@ -56,8 +56,8 @@ __PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath, ".spinlock.text"); "pop %rdx\n\t" \ FRAME_END -DEFINE_PARAVIRT_ASM(__raw_callee_save___pv_queued_spin_unlock, - PV_UNLOCK_ASM, .spinlock.text); +DEFINE_ASM_FUNC(__raw_callee_save___pv_queued_spin_unlock, + PV_UNLOCK_ASM, .spinlock.text); #else /* CONFIG_64BIT */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index bf483fcb4e57..5c83729c8e71 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -31,8 +31,6 @@ #include <asm/bootparam.h> #include <asm/x86_init.h> -extern u64 relocated_ramdisk; - /* Interrupt control for vSMPowered x86_64 systems */ #ifdef CONFIG_X86_64 void vsmp_init(void); diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h index fd2669b1cb2d..21f9407be5d3 100644 --- a/arch/x86/include/asm/syscall_wrapper.h +++ b/arch/x86/include/asm/syscall_wrapper.h @@ -86,9 +86,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); return sys_ni_syscall(); \ } -#define __SYS_NI(abi, name) \ - SYSCALL_ALIAS(__##abi##_##name, sys_ni_posix_timers); - #ifdef CONFIG_X86_64 #define __X64_SYS_STUB0(name) \ __SYS_STUB0(x64, sys_##name) @@ -100,13 +97,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __X64_COND_SYSCALL(name) \ __COND_SYSCALL(x64, sys_##name) -#define __X64_SYS_NI(name) \ - __SYS_NI(x64, sys_##name) #else /* CONFIG_X86_64 */ #define __X64_SYS_STUB0(name) #define __X64_SYS_STUBx(x, name, ...) #define __X64_COND_SYSCALL(name) -#define __X64_SYS_NI(name) #endif /* CONFIG_X86_64 */ #if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) @@ -120,13 +114,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __IA32_COND_SYSCALL(name) \ __COND_SYSCALL(ia32, sys_##name) -#define __IA32_SYS_NI(name) \ - __SYS_NI(ia32, sys_##name) #else /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ #define __IA32_SYS_STUB0(name) #define __IA32_SYS_STUBx(x, name, ...) #define __IA32_COND_SYSCALL(name) -#define __IA32_SYS_NI(name) #endif /* CONFIG_X86_32 || CONFIG_IA32_EMULATION */ #ifdef CONFIG_IA32_EMULATION @@ -135,8 +126,7 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * additional wrappers (aptly named __ia32_sys_xyzzy) which decode the * ia32 regs in the proper order for shared or "common" syscalls. As some * syscalls may not be implemented, we need to expand COND_SYSCALL in - * kernel/sys_ni.c and SYS_NI in kernel/time/posix-stubs.c to cover this - * case as well. + * kernel/sys_ni.c to cover this case as well. */ #define __IA32_COMPAT_SYS_STUB0(name) \ __SYS_STUB0(ia32, compat_sys_##name) @@ -148,14 +138,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __IA32_COMPAT_COND_SYSCALL(name) \ __COND_SYSCALL(ia32, compat_sys_##name) -#define __IA32_COMPAT_SYS_NI(name) \ - __SYS_NI(ia32, compat_sys_##name) - #else /* CONFIG_IA32_EMULATION */ #define __IA32_COMPAT_SYS_STUB0(name) #define __IA32_COMPAT_SYS_STUBx(x, name, ...) #define __IA32_COMPAT_COND_SYSCALL(name) -#define __IA32_COMPAT_SYS_NI(name) #endif /* CONFIG_IA32_EMULATION */ @@ -175,13 +161,10 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); #define __X32_COMPAT_COND_SYSCALL(name) \ __COND_SYSCALL(x64, compat_sys_##name) -#define __X32_COMPAT_SYS_NI(name) \ - __SYS_NI(x64, compat_sys_##name) #else /* CONFIG_X86_X32_ABI */ #define __X32_COMPAT_SYS_STUB0(name) #define __X32_COMPAT_SYS_STUBx(x, name, ...) #define __X32_COMPAT_COND_SYSCALL(name) -#define __X32_COMPAT_SYS_NI(name) #endif /* CONFIG_X86_X32_ABI */ @@ -212,17 +195,12 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); /* * As some compat syscalls may not be implemented, we need to expand - * COND_SYSCALL_COMPAT in kernel/sys_ni.c and COMPAT_SYS_NI in - * kernel/time/posix-stubs.c to cover this case as well. + * COND_SYSCALL_COMPAT in kernel/sys_ni.c to cover this case as well. */ #define COND_SYSCALL_COMPAT(name) \ __IA32_COMPAT_COND_SYSCALL(name) \ __X32_COMPAT_COND_SYSCALL(name) -#define COMPAT_SYS_NI(name) \ - __IA32_COMPAT_SYS_NI(name) \ - __X32_COMPAT_SYS_NI(name) - #endif /* CONFIG_COMPAT */ #define __SYSCALL_DEFINEx(x, name, ...) \ @@ -243,8 +221,8 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); * As the generic SYSCALL_DEFINE0() macro does not decode any parameters for * obvious reasons, and passing struct pt_regs *regs to it in %rdi does not * hurt, we only need to re-define it here to keep the naming congruent to - * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() and SYS_NI() - * macros to work correctly. + * SYSCALL_DEFINEx() -- which is essential for the COND_SYSCALL() macro + * to work correctly. */ #define SYSCALL_DEFINE0(sname) \ SYSCALL_METADATA(_##sname, 0); \ @@ -257,10 +235,6 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs); __X64_COND_SYSCALL(name) \ __IA32_COND_SYSCALL(name) -#define SYS_NI(name) \ - __X64_SYS_NI(name) \ - __IA32_SYS_NI(name) - /* * For VSYSCALLS, we need to declare these three syscalls with the new diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 29832c338cdc..0b70653a98c1 100644 --- a/arch/x86/include/asm/text-patching.h +++ b/arch/x86/include/asm/text-patching.h @@ -6,18 +6,6 @@ #include <linux/stddef.h> #include <asm/ptrace.h> -struct paravirt_patch_site; -#ifdef CONFIG_PARAVIRT -void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end); -#else -static inline void apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{} -#define __parainstructions NULL -#define __parainstructions_end NULL -#endif - /* * Currently, the max observed size in the kernel code is * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5. diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index b1c9cea6ba88..1f1deaecd364 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -14,7 +14,6 @@ asmlinkage __visible notrace struct pt_regs *sync_regs(struct pt_regs *eregs); asmlinkage __visible notrace struct pt_regs *fixup_bad_iret(struct pt_regs *bad_regs); -void __init trap_init(void); asmlinkage __visible noinstr struct pt_regs *vc_switch_off_ist(struct pt_regs *eregs); #endif diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index 5fa76c2ced51..ea877fd83114 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -653,7 +653,7 @@ static inline int uv_blade_to_node(int blade) return uv_socket_to_node(blade); } -/* Blade number of current cpu. Numnbered 0 .. <#blades -1> */ +/* Blade number of current cpu. Numbered 0 .. <#blades -1> */ static inline int uv_numa_blade_id(void) { return uv_hub_info->numa_blade_id; diff --git a/arch/x86/include/asm/vdso/gettimeofday.h b/arch/x86/include/asm/vdso/gettimeofday.h index c81858d903dc..8e048ca980df 100644 --- a/arch/x86/include/asm/vdso/gettimeofday.h +++ b/arch/x86/include/asm/vdso/gettimeofday.h @@ -321,7 +321,7 @@ static __always_inline u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) { /* - * Due to the MSB/Sign-bit being used as invald marker (see + * Due to the MSB/Sign-bit being used as invalid marker (see * arch_vdso_cycles_valid() above), the effective mask is S64_MAX. */ u64 delta = (cycles - last) & S64_MAX; @@ -337,8 +337,6 @@ u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult) } #define vdso_calc_delta vdso_calc_delta -int __vdso_clock_gettime64(clockid_t clock, struct __kernel_timespec *ts); - #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h index c599ec269a25..c10f279aae93 100644 --- a/arch/x86/include/asm/xen/interface_64.h +++ b/arch/x86/include/asm/xen/interface_64.h @@ -61,7 +61,7 @@ * RING1 -> RING3 kernel mode. * RING2 -> RING3 kernel mode. * RING3 -> RING3 user mode. - * However RING0 indicates that the guest kernel should return to iteself + * However RING0 indicates that the guest kernel should return to itself * directly with * orb $3,1*8(%rsp) * iretq diff --git a/arch/x86/include/uapi/asm/amd_hsmp.h b/arch/x86/include/uapi/asm/amd_hsmp.h index fce22686c834..e5d182c7373c 100644 --- a/arch/x86/include/uapi/asm/amd_hsmp.h +++ b/arch/x86/include/uapi/asm/amd_hsmp.h @@ -238,7 +238,7 @@ static const struct hsmp_msg_desc hsmp_msg_desc_table[] = { /* * HSMP_GET_DIMM_THERMAL, num_args = 1, response_sz = 1 * input: args[0] = DIMM address[7:0] - * output: args[0] = temperature in degree celcius[31:21] + update rate in ms[16:8] + + * output: args[0] = temperature in degree celsius[31:21] + update rate in ms[16:8] + * DIMM address[7:0] */ {1, 1, HSMP_GET}, diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h index 777c3a0f4e23..f777346450ec 100644 --- a/arch/x86/include/uapi/asm/signal.h +++ b/arch/x86/include/uapi/asm/signal.h @@ -4,7 +4,6 @@ #ifndef __ASSEMBLY__ #include <linux/types.h> -#include <linux/time.h> #include <linux/compiler.h> /* Avoid too many header ordering problems. */ diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 1a0dd80d81ac..85a3ce2a3666 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -293,6 +293,7 @@ acpi_parse_lapic(union acpi_subtable_headers * header, const unsigned long end) processor->processor_id, /* ACPI ID */ processor->lapic_flags & ACPI_MADT_ENABLED); + has_lapic_cpus = true; return 0; } @@ -1134,7 +1135,6 @@ static int __init acpi_parse_madt_lapic_entries(void) if (!count) { count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_APIC, acpi_parse_lapic, MAX_LOCAL_APIC); - has_lapic_cpus = count > 0; x2count = acpi_table_parse_madt(ACPI_MADT_TYPE_LOCAL_X2APIC, acpi_parse_x2apic, MAX_LOCAL_APIC); } diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 73be3931e4f0..cc130b57542a 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -30,6 +30,7 @@ #include <asm/fixmap.h> #include <asm/paravirt.h> #include <asm/asm-prototypes.h> +#include <asm/cfi.h> int __read_mostly alternatives_patched; @@ -160,7 +161,6 @@ extern s32 __retpoline_sites[], __retpoline_sites_end[]; extern s32 __return_sites[], __return_sites_end[]; extern s32 __cfi_sites[], __cfi_sites_end[]; extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[]; -extern struct alt_instr __alt_instructions[], __alt_instructions_end[]; extern s32 __smp_locks[], __smp_locks_end[]; void text_poke_early(void *addr, const void *opcode, size_t len); @@ -255,6 +255,16 @@ static void __init_or_module noinline optimize_nops(u8 *instr, size_t len) } } +static void __init_or_module noinline optimize_nops_inplace(u8 *instr, size_t len) +{ + unsigned long flags; + + local_irq_save(flags); + optimize_nops(instr, len); + sync_core(); + local_irq_restore(flags); +} + /* * In this context, "source" is where the instructions are placed in the * section .altinstr_replacement, for example during kernel build by the @@ -385,6 +395,63 @@ apply_relocation(u8 *buf, size_t len, u8 *dest, u8 *src, size_t src_len) } } +/* Low-level backend functions usable from alternative code replacements. */ +DEFINE_ASM_FUNC(nop_func, "", .entry.text); +EXPORT_SYMBOL_GPL(nop_func); + +noinstr void BUG_func(void) +{ + BUG(); +} +EXPORT_SYMBOL_GPL(BUG_func); + +#define CALL_RIP_REL_OPCODE 0xff +#define CALL_RIP_REL_MODRM 0x15 + +/* + * Rewrite the "call BUG_func" replacement to point to the target of the + * indirect pv_ops call "call *disp(%ip)". + */ +static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a) +{ + void *target, *bug = &BUG_func; + s32 disp; + + if (a->replacementlen != 5 || insn_buff[0] != CALL_INSN_OPCODE) { + pr_err("ALT_FLAG_DIRECT_CALL set for a non-call replacement instruction\n"); + BUG(); + } + + if (a->instrlen != 6 || + instr[0] != CALL_RIP_REL_OPCODE || + instr[1] != CALL_RIP_REL_MODRM) { + pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n"); + BUG(); + } + + /* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */ + disp = *(s32 *)(instr + 2); +#ifdef CONFIG_X86_64 + /* ff 15 00 00 00 00 call *0x0(%rip) */ + /* target address is stored at "next instruction + disp". */ + target = *(void **)(instr + a->instrlen + disp); +#else + /* ff 15 00 00 00 00 call *0x0 */ + /* target address is stored at disp. */ + target = *(void **)disp; +#endif + if (!target) + target = bug; + + /* (BUG_func - .) + (target - BUG_func) := target - . */ + *(s32 *)(insn_buff + 1) += target - bug; + + if (target == &nop_func) + return 0; + + return 5; +} + /* * Replace instructions with better alternatives for this CPU type. This runs * before SMP is initialized to avoid SMP problems with self modifying code. @@ -438,20 +505,25 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, * patch if feature is *NOT* present. */ if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) { - optimize_nops(instr, a->instrlen); + optimize_nops_inplace(instr, a->instrlen); continue; } - DPRINTK(ALT, "feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d)", - (a->flags & ALT_FLAG_NOT) ? "!" : "", + DPRINTK(ALT, "feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d) flags: 0x%x", a->cpuid >> 5, a->cpuid & 0x1f, instr, instr, a->instrlen, - replacement, a->replacementlen); + replacement, a->replacementlen, a->flags); memcpy(insn_buff, replacement, a->replacementlen); insn_buff_sz = a->replacementlen; + if (a->flags & ALT_FLAG_DIRECT_CALL) { + insn_buff_sz = alt_replace_call(instr, insn_buff, a); + if (insn_buff_sz < 0) + continue; + } + for (; insn_buff_sz < a->instrlen; insn_buff_sz++) insn_buff[insn_buff_sz] = 0x90; @@ -832,15 +904,82 @@ void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { } #endif /* CONFIG_X86_KERNEL_IBT */ #ifdef CONFIG_FINEIBT +#define __CFI_DEFAULT CFI_DEFAULT +#elif defined(CONFIG_CFI_CLANG) +#define __CFI_DEFAULT CFI_KCFI +#else +#define __CFI_DEFAULT CFI_OFF +#endif -enum cfi_mode { - CFI_DEFAULT, - CFI_OFF, - CFI_KCFI, - CFI_FINEIBT, -}; +enum cfi_mode cfi_mode __ro_after_init = __CFI_DEFAULT; + +#ifdef CONFIG_CFI_CLANG +struct bpf_insn; + +/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */ +extern unsigned int __bpf_prog_runX(const void *ctx, + const struct bpf_insn *insn); + +/* + * Force a reference to the external symbol so the compiler generates + * __kcfi_typid. + */ +__ADDRESSABLE(__bpf_prog_runX); + +/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_hash,@object \n" +" .globl cfi_bpf_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_hash: \n" +" .long __kcfi_typeid___bpf_prog_runX \n" +" .size cfi_bpf_hash, 4 \n" +" .popsection \n" +); + +/* Must match bpf_callback_t */ +extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64); + +__ADDRESSABLE(__bpf_callback_fn); + +/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */ +asm ( +" .pushsection .data..ro_after_init,\"aw\",@progbits \n" +" .type cfi_bpf_subprog_hash,@object \n" +" .globl cfi_bpf_subprog_hash \n" +" .p2align 2, 0x0 \n" +"cfi_bpf_subprog_hash: \n" +" .long __kcfi_typeid___bpf_callback_fn \n" +" .size cfi_bpf_subprog_hash, 4 \n" +" .popsection \n" +); + +u32 cfi_get_func_hash(void *func) +{ + u32 hash; + + func -= cfi_get_offset(); + switch (cfi_mode) { + case CFI_FINEIBT: + func += 7; + break; + case CFI_KCFI: + func += 1; + break; + default: + return 0; + } + + if (get_kernel_nofault(hash, func)) + return 0; + + return hash; +} +#endif + +#ifdef CONFIG_FINEIBT -static enum cfi_mode cfi_mode __ro_after_init = CFI_DEFAULT; static bool cfi_rand __ro_after_init = true; static u32 cfi_seed __ro_after_init; @@ -1149,8 +1288,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, goto err; if (cfi_rand) { - if (builtin) + if (builtin) { cfi_seed = get_random_u32(); + cfi_bpf_hash = cfi_rehash(cfi_bpf_hash); + cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash); + } ret = cfi_rand_preamble(start_cfi, end_cfi); if (ret) @@ -1411,46 +1553,6 @@ int alternatives_text_reserved(void *start, void *end) } #endif /* CONFIG_SMP */ -#ifdef CONFIG_PARAVIRT - -/* Use this to add nops to a buffer, then text_poke the whole buffer. */ -static void __init_or_module add_nops(void *insns, unsigned int len) -{ - while (len > 0) { - unsigned int noplen = len; - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - memcpy(insns, x86_nops[noplen], noplen); - insns += noplen; - len -= noplen; - } -} - -void __init_or_module apply_paravirt(struct paravirt_patch_site *start, - struct paravirt_patch_site *end) -{ - struct paravirt_patch_site *p; - char insn_buff[MAX_PATCH_LEN]; - - for (p = start; p < end; p++) { - unsigned int used; - - BUG_ON(p->len > MAX_PATCH_LEN); - /* prep the buffer with the original instructions */ - memcpy(insn_buff, p->instr, p->len); - used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len); - - BUG_ON(used > p->len); - - /* Pad the rest with nops */ - add_nops(insn_buff + used, p->len - used); - text_poke_early(p->instr, insn_buff, p->len); - } -} -extern struct paravirt_patch_site __start_parainstructions[], - __stop_parainstructions[]; -#endif /* CONFIG_PARAVIRT */ - /* * Self-test for the INT3 based CALL emulation code. * @@ -1586,28 +1688,11 @@ void __init alternative_instructions(void) */ /* - * Paravirt patching and alternative patching can be combined to - * replace a function call with a short direct code sequence (e.g. - * by setting a constant return value instead of doing that in an - * external function). - * In order to make this work the following sequence is required: - * 1. set (artificial) features depending on used paravirt - * functions which can later influence alternative patching - * 2. apply paravirt patching (generally replacing an indirect - * function call with a direct one) - * 3. apply alternative patching (e.g. replacing a direct function - * call with a custom code sequence) - * Doing paravirt patching after alternative patching would clobber - * the optimization of the custom code with a function call again. + * Make sure to set (artificial) features depending on used paravirt + * functions which can later influence alternative patching. */ paravirt_set_cap(); - /* - * First patch paravirt functions, such that we overwrite the indirect - * call with the direct call. - */ - apply_paravirt(__parainstructions, __parainstructions_end); - __apply_fineibt(__retpoline_sites, __retpoline_sites_end, __cfi_sites, __cfi_sites_end, true); @@ -1618,10 +1703,6 @@ void __init alternative_instructions(void) apply_retpolines(__retpoline_sites, __retpoline_sites_end); apply_returns(__return_sites, __return_sites_end); - /* - * Then patch alternatives, such that those paravirt calls that are in - * alternatives can be overwritten by their immediate fragments. - */ apply_alternatives(__alt_instructions, __alt_instructions_end); /* @@ -1685,8 +1766,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode, } else { local_irq_save(flags); memcpy(addr, opcode, len); - local_irq_restore(flags); sync_core(); + local_irq_restore(flags); /* * Could also do a CLFLUSH here to speed up CPU recovery; but @@ -1896,7 +1977,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l * Note that the caller must ensure that if the modified code is part of a * module, the module would not be removed during poking. This can be achieved * by registering a module notifier, and ordering module removal and patching - * trough a mutex. + * through a mutex. */ void *text_poke(void *addr, const void *opcode, size_t len) { diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index 56a917df410d..2ae98f754e59 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -776,7 +776,7 @@ int __init gart_iommu_init(void) iommu_size >> PAGE_SHIFT); /* * Tricky. The GART table remaps the physical memory range, - * so the CPU wont notice potential aliases and if the memory + * so the CPU won't notice potential aliases and if the memory * is remapped to UC later on, we might surprise the PCI devices * with a stray writeout of a cacheline. So play it sure and * do an explicit, full-scale wbinvd() _after_ having marked all diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 2ee867d796d9..3bf0487cf3b7 100644 --- a/arch/x86/kernel/apic/Makefile +++ b/arch/x86/kernel/apic/Makefile @@ -4,7 +4,7 @@ # # Leads to non-deterministic coverage that is not a function of syscall inputs. -# In particualr, smp_apic_timer_interrupt() is called in random places. +# In particular, smp_apic_timer_interrupt() is called in random places. KCOV_INSTRUMENT := n obj-$(CONFIG_X86_LOCAL_APIC) += apic.o apic_common.o apic_noop.o ipi.o vector.o init.o diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index 41093cf20acd..4667bc4b00ab 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -782,7 +782,7 @@ bool __init apic_needs_pit(void) /* * If interrupt delivery mode is legacy PIC or virtual wire without - * configuration, the local APIC timer wont be set up. Make sure + * configuration, the local APIC timer won't be set up. Make sure * that the PIT is initialized. */ if (apic_intr_mode == APIC_PIC || diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 7139867d69cd..b295a056a4fc 100644 --- a/arch/x86/kernel/apic/apic_flat_64.c +++ b/arch/x86/kernel/apic/apic_flat_64.c @@ -82,7 +82,6 @@ static struct apic apic_flat __ro_after_init = { .acpi_madt_oem_check = flat_acpi_madt_oem_check, .apic_id_registered = default_apic_id_registered, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, @@ -154,7 +153,6 @@ static struct apic apic_physflat __ro_after_init = { .acpi_madt_oem_check = physflat_acpi_madt_oem_check, .apic_id_registered = default_apic_id_registered, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index b00d52ae84fa..9f1d553eb48f 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -47,7 +47,6 @@ static void noop_apic_write(u32 reg, u32 val) struct apic apic_noop __ro_after_init = { .name = "noop", - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c index 456a14c44f67..7d0c51b9d3bc 100644 --- a/arch/x86/kernel/apic/apic_numachip.c +++ b/arch/x86/kernel/apic/apic_numachip.c @@ -222,7 +222,6 @@ static const struct apic apic_numachip1 __refconst = { .probe = numachip1_probe, .acpi_madt_oem_check = numachip1_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, @@ -259,7 +258,6 @@ static const struct apic apic_numachip2 __refconst = { .probe = numachip2_probe, .acpi_madt_oem_check = numachip2_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 7ee3c486cb33..5a0d60b38e6b 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -80,7 +80,6 @@ static struct apic apic_bigsmp __ro_after_init = { .name = "bigsmp", .probe = probe_bigsmp, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 1, diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 00da6cf6b07d..40c7cf180c20 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -997,7 +997,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, /* * Legacy ISA IRQ has already been allocated, just add pin to * the pin list associated with this IRQ and program the IOAPIC - * entry. The IOAPIC entry + * entry. */ if (irq_data && irq_data->parent_data) { if (!mp_check_pin_attr(irq, info)) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index 5eb3fbe472da..c0f78059f06a 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -45,7 +45,6 @@ static struct apic apic_default __ro_after_init = { .probe = probe_default, .apic_id_registered = default_apic_id_registered, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c index 319448d87b99..185738c72766 100644 --- a/arch/x86/kernel/apic/vector.c +++ b/arch/x86/kernel/apic/vector.c @@ -738,8 +738,8 @@ int __init arch_probe_nr_irqs(void) void lapic_assign_legacy_vector(unsigned int irq, bool replace) { /* - * Use assign system here so it wont get accounted as allocated - * and moveable in the cpu hotplug check and it prevents managed + * Use assign system here so it won't get accounted as allocated + * and movable in the cpu hotplug check and it prevents managed * irq reservation from touching it. */ irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace); diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c index a8306089c91b..28a7d3f2312d 100644 --- a/arch/x86/kernel/apic/x2apic_cluster.c +++ b/arch/x86/kernel/apic/x2apic_cluster.c @@ -227,7 +227,6 @@ static struct apic apic_x2apic_cluster __ro_after_init = { .probe = x2apic_cluster_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = true, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c index 558a4a8824f4..409815a40668 100644 --- a/arch/x86/kernel/apic/x2apic_phys.c +++ b/arch/x86/kernel/apic/x2apic_phys.c @@ -145,7 +145,6 @@ static struct apic apic_x2apic_phys __ro_after_init = { .probe = x2apic_phys_probe, .acpi_madt_oem_check = x2apic_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 1b0d7336a28f..f1766b18dcd0 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -805,7 +805,6 @@ static struct apic apic_x2apic_uv_x __ro_after_init = { .probe = uv_probe, .acpi_madt_oem_check = uv_acpi_madt_oem_check, - .delivery_mode = APIC_DELIVERY_MODE_FIXED, .dest_mode_logical = false, .disable_esr = 0, diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 5934ee5bc087..76a5ced278c2 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -420,7 +420,7 @@ static DEFINE_MUTEX(apm_mutex); * This is for buggy BIOS's that refer to (real mode) segment 0x40 * even though they are called in protected mode. */ -static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(0x4092, +static struct desc_struct bad_bios_desc = GDT_ENTRY_INIT(DESC_DATA32_BIOS, (unsigned long)__va(0x400UL), PAGE_SIZE - 0x400 - 1); static const char driver_version[] = "1.16ac"; /* no spaces */ diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c index e9ad518a5003..64ad2ddea121 100644 --- a/arch/x86/kernel/callthunks.c +++ b/arch/x86/kernel/callthunks.c @@ -233,14 +233,13 @@ patch_call_sites(s32 *start, s32 *end, const struct core_text *ct) } static __init_or_module void -patch_paravirt_call_sites(struct paravirt_patch_site *start, - struct paravirt_patch_site *end, - const struct core_text *ct) +patch_alt_call_sites(struct alt_instr *start, struct alt_instr *end, + const struct core_text *ct) { - struct paravirt_patch_site *p; + struct alt_instr *a; - for (p = start; p < end; p++) - patch_call(p->instr, ct); + for (a = start; a < end; a++) + patch_call((void *)&a->instr_offset + a->instr_offset, ct); } static __init_or_module void @@ -248,7 +247,7 @@ callthunks_setup(struct callthunk_sites *cs, const struct core_text *ct) { prdbg("Patching call sites %s\n", ct->name); patch_call_sites(cs->call_start, cs->call_end, ct); - patch_paravirt_call_sites(cs->pv_start, cs->pv_end, ct); + patch_alt_call_sites(cs->alt_start, cs->alt_end, ct); prdbg("Patching call sites done%s\n", ct->name); } @@ -257,8 +256,8 @@ void __init callthunks_patch_builtin_calls(void) struct callthunk_sites cs = { .call_start = __call_sites, .call_end = __call_sites_end, - .pv_start = __parainstructions, - .pv_end = __parainstructions_end + .alt_start = __alt_instructions, + .alt_end = __alt_instructions_end }; if (!cpu_feature_enabled(X86_FEATURE_CALL_DEPTH)) diff --git a/arch/x86/kernel/cfi.c b/arch/x86/kernel/cfi.c index 8674a5c0c031..e6bf78fac146 100644 --- a/arch/x86/kernel/cfi.c +++ b/arch/x86/kernel/cfi.c @@ -4,10 +4,10 @@ * * Copyright (C) 2022 Google LLC */ -#include <asm/cfi.h> +#include <linux/string.h> +#include <linux/cfi.h> #include <asm/insn.h> #include <asm/insn-eval.h> -#include <linux/string.h> /* * Returns the target address and the expected type when regs->ip points diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index a7eab05e5f29..9f42d1c59e09 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -34,87 +34,6 @@ */ static u32 nodes_per_socket = 1; -/* - * AMD errata checking - * - * Errata are defined as arrays of ints using the AMD_LEGACY_ERRATUM() or - * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that - * have an OSVW id assigned, which it takes as first argument. Both take a - * variable number of family-specific model-stepping ranges created by - * AMD_MODEL_RANGE(). - * - * Example: - * - * const int amd_erratum_319[] = - * AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0x4, 0x2), - * AMD_MODEL_RANGE(0x10, 0x8, 0x0, 0x8, 0x0), - * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); - */ - -#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } -#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } -#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ - ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) -#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) -#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) -#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) - -static const int amd_erratum_400[] = - AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), - AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); - -static const int amd_erratum_383[] = - AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); - -/* #1054: Instructions Retired Performance Counter May Be Inaccurate */ -static const int amd_erratum_1054[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0, 0, 0x2f, 0xf)); - -static const int amd_zenbleed[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x30, 0x0, 0x4f, 0xf), - AMD_MODEL_RANGE(0x17, 0x60, 0x0, 0x7f, 0xf), - AMD_MODEL_RANGE(0x17, 0x90, 0x0, 0x91, 0xf), - AMD_MODEL_RANGE(0x17, 0xa0, 0x0, 0xaf, 0xf)); - -static const int amd_div0[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf), - AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf)); - -static const int amd_erratum_1485[] = - AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf), - AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf)); - -static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum) -{ - int osvw_id = *erratum++; - u32 range; - u32 ms; - - if (osvw_id >= 0 && osvw_id < 65536 && - cpu_has(cpu, X86_FEATURE_OSVW)) { - u64 osvw_len; - - rdmsrl(MSR_AMD64_OSVW_ID_LENGTH, osvw_len); - if (osvw_id < osvw_len) { - u64 osvw_bits; - - rdmsrl(MSR_AMD64_OSVW_STATUS + (osvw_id >> 6), - osvw_bits); - return osvw_bits & (1ULL << (osvw_id & 0x3f)); - } - } - - /* OSVW unavailable or ID unknown, match family-model-stepping range */ - ms = (cpu->x86_model << 4) | cpu->x86_stepping; - while ((range = *erratum++)) - if ((cpu->x86 == AMD_MODEL_RANGE_FAMILY(range)) && - (ms >= AMD_MODEL_RANGE_START(range)) && - (ms <= AMD_MODEL_RANGE_END(range))) - return true; - - return false; -} - static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { u32 gprs[8] = { 0 }; @@ -616,6 +535,49 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) } resctrl_cpu_detect(c); + + /* Figure out Zen generations: */ + switch (c->x86) { + case 0x17: { + switch (c->x86_model) { + case 0x00 ... 0x2f: + case 0x50 ... 0x5f: + setup_force_cpu_cap(X86_FEATURE_ZEN1); + break; + case 0x30 ... 0x4f: + case 0x60 ... 0x7f: + case 0x90 ... 0x91: + case 0xa0 ... 0xaf: + setup_force_cpu_cap(X86_FEATURE_ZEN2); + break; + default: + goto warn; + } + break; + } + case 0x19: { + switch (c->x86_model) { + case 0x00 ... 0x0f: + case 0x20 ... 0x5f: + setup_force_cpu_cap(X86_FEATURE_ZEN3); + break; + case 0x10 ... 0x1f: + case 0x60 ... 0xaf: + setup_force_cpu_cap(X86_FEATURE_ZEN4); + break; + default: + goto warn; + } + break; + } + default: + break; + } + + return; + +warn: + WARN_ONCE(1, "Family 0x%x, model: 0x%x??\n", c->x86, c->x86_model); } static void early_detect_mem_encrypt(struct cpuinfo_x86 *c) @@ -739,15 +701,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) if (c->x86 == 0x16 && c->x86_model <= 0xf) msr_set_bit(MSR_AMD64_LS_CFG, 15); - /* - * Check whether the machine is affected by erratum 400. This is - * used to select the proper idle routine and to enable the check - * whether the machine is affected in arch_post_acpi_init(), which - * sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check. - */ - if (cpu_has_amd_erratum(c, amd_erratum_400)) - set_cpu_bug(c, X86_BUG_AMD_E400); - early_detect_mem_encrypt(c); /* Re-enable TopologyExtensions if switched off by BIOS */ @@ -814,6 +767,16 @@ static void init_amd_k8(struct cpuinfo_x86 *c) msr_set_bit(MSR_K7_HWCR, 6); #endif set_cpu_bug(c, X86_BUG_SWAPGS_FENCE); + + /* + * Check models and steppings affected by erratum 400. This is + * used to select the proper idle routine and to enable the + * check whether the machine is affected in arch_post_acpi_subsys_init() + * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check. + */ + if (c->x86_model > 0x41 || + (c->x86_model == 0x41 && c->x86_stepping >= 0x2)) + setup_force_cpu_bug(X86_BUG_AMD_E400); } static void init_amd_gh(struct cpuinfo_x86 *c) @@ -847,8 +810,17 @@ static void init_amd_gh(struct cpuinfo_x86 *c) */ msr_clear_bit(MSR_AMD64_BU_CFG2, 24); - if (cpu_has_amd_erratum(c, amd_erratum_383)) - set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); + set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); + + /* + * Check models and steppings affected by erratum 400. This is + * used to select the proper idle routine and to enable the + * check whether the machine is affected in arch_post_acpi_subsys_init() + * which sets the X86_BUG_AMD_APIC_C1E bug depending on the MSR check. + */ + if (c->x86_model > 0x2 || + (c->x86_model == 0x2 && c->x86_stepping >= 0x1)) + setup_force_cpu_bug(X86_BUG_AMD_E400); } static void init_amd_ln(struct cpuinfo_x86 *c) @@ -941,6 +913,19 @@ static void init_amd_bd(struct cpuinfo_x86 *c) clear_rdrand_cpuid_bit(c); } +static void fix_erratum_1386(struct cpuinfo_x86 *c) +{ + /* + * Work around Erratum 1386. The XSAVES instruction malfunctions in + * certain circumstances on Zen1/2 uarch, and not all parts have had + * updated microcode at the time of writing (March 2023). + * + * Affected parts all have no supervisor XSAVE states, meaning that + * the XSAVEC instruction (which works fine) is equivalent. + */ + clear_cpu_cap(c, X86_FEATURE_XSAVES); +} + void init_spectral_chicken(struct cpuinfo_x86 *c) { #ifdef CONFIG_CPU_UNRET_ENTRY @@ -951,34 +936,28 @@ void init_spectral_chicken(struct cpuinfo_x86 *c) * * This suppresses speculation from the middle of a basic block, i.e. it * suppresses non-branch predictions. - * - * We use STIBP as a heuristic to filter out Zen2 from the rest of F17H */ - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_AMD_STIBP)) { + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) { value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT; wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value); } } #endif - /* - * Work around Erratum 1386. The XSAVES instruction malfunctions in - * certain circumstances on Zen1/2 uarch, and not all parts have had - * updated microcode at the time of writing (March 2023). - * - * Affected parts all have no supervisor XSAVE states, meaning that - * the XSAVEC instruction (which works fine) is equivalent. - */ - clear_cpu_cap(c, X86_FEATURE_XSAVES); } -static void init_amd_zn(struct cpuinfo_x86 *c) +static void init_amd_zen_common(void) { - set_cpu_cap(c, X86_FEATURE_ZEN); - + setup_force_cpu_cap(X86_FEATURE_ZEN); #ifdef CONFIG_NUMA node_reclaim_distance = 32; #endif +} + +static void init_amd_zen1(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + fix_erratum_1386(c); /* Fix up CPUID bits, but only if not virtualised. */ if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { @@ -986,15 +965,10 @@ static void init_amd_zn(struct cpuinfo_x86 *c) /* Erratum 1076: CPB feature bit not being set in CPUID. */ if (!cpu_has(c, X86_FEATURE_CPB)) set_cpu_cap(c, X86_FEATURE_CPB); - - /* - * Zen3 (Fam19 model < 0x10) parts are not susceptible to - * Branch Type Confusion, but predate the allocation of the - * BTC_NO bit. - */ - if (c->x86 == 0x19 && !cpu_has(c, X86_FEATURE_BTC_NO)) - set_cpu_cap(c, X86_FEATURE_BTC_NO); } + + pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); + setup_force_cpu_bug(X86_BUG_DIV0); } static bool cpu_has_zenbleed_microcode(void) @@ -1018,11 +992,8 @@ static bool cpu_has_zenbleed_microcode(void) return true; } -static void zenbleed_check(struct cpuinfo_x86 *c) +static void zen2_zenbleed_check(struct cpuinfo_x86 *c) { - if (!cpu_has_amd_erratum(c, amd_zenbleed)) - return; - if (cpu_has(c, X86_FEATURE_HYPERVISOR)) return; @@ -1037,6 +1008,37 @@ static void zenbleed_check(struct cpuinfo_x86 *c) } } +static void init_amd_zen2(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + init_spectral_chicken(c); + fix_erratum_1386(c); + zen2_zenbleed_check(c); +} + +static void init_amd_zen3(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) { + /* + * Zen3 (Fam19 model < 0x10) parts are not susceptible to + * Branch Type Confusion, but predate the allocation of the + * BTC_NO bit. + */ + if (!cpu_has(c, X86_FEATURE_BTC_NO)) + set_cpu_cap(c, X86_FEATURE_BTC_NO); + } +} + +static void init_amd_zen4(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); + + if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) + msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); +} + static void init_amd(struct cpuinfo_x86 *c) { u64 vm_cr; @@ -1072,11 +1074,17 @@ static void init_amd(struct cpuinfo_x86 *c) case 0x12: init_amd_ln(c); break; case 0x15: init_amd_bd(c); break; case 0x16: init_amd_jg(c); break; - case 0x17: init_spectral_chicken(c); - fallthrough; - case 0x19: init_amd_zn(c); break; } + if (boot_cpu_has(X86_FEATURE_ZEN1)) + init_amd_zen1(c); + else if (boot_cpu_has(X86_FEATURE_ZEN2)) + init_amd_zen2(c); + else if (boot_cpu_has(X86_FEATURE_ZEN3)) + init_amd_zen3(c); + else if (boot_cpu_has(X86_FEATURE_ZEN4)) + init_amd_zen4(c); + /* * Enable workaround for FXSAVE leak on CPUs * without a XSaveErPtr feature @@ -1136,7 +1144,7 @@ static void init_amd(struct cpuinfo_x86 *c) * Counter May Be Inaccurate". */ if (cpu_has(c, X86_FEATURE_IRPERF) && - !cpu_has_amd_erratum(c, amd_erratum_1054)) + (boot_cpu_has(X86_FEATURE_ZEN1) && c->x86_model > 0x2f)) msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_IRPERF_EN_BIT); check_null_seg_clears_base(c); @@ -1152,16 +1160,8 @@ static void init_amd(struct cpuinfo_x86 *c) cpu_has(c, X86_FEATURE_AUTOIBRS)) WARN_ON_ONCE(msr_set_bit(MSR_EFER, _EFER_AUTOIBRS)); - zenbleed_check(c); - - if (cpu_has_amd_erratum(c, amd_div0)) { - pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n"); - setup_force_cpu_bug(X86_BUG_DIV0); - } - - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && - cpu_has_amd_erratum(c, amd_erratum_1485)) - msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT); + /* AMD CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } #ifdef CONFIG_X86_32 @@ -1315,11 +1315,14 @@ static void zenbleed_check_cpu(void *unused) { struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); - zenbleed_check(c); + zen2_zenbleed_check(c); } void amd_check_microcode(void) { + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return; + on_each_cpu(zenbleed_check_cpu, NULL, 1); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index b14fc8c1c953..94bff381ef20 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -188,45 +188,37 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = { * TLS descriptors are currently at a different place compared to i386. * Hopefully nobody expects them at a fixed place (Wine?) */ - [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(0xc0fb, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f3, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xa0fb, 0, 0xfffff), + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER32_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA64 | DESC_USER, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE64 | DESC_USER, 0, 0xfffff), #else - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xc09a, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(0xc0fa, 0, 0xfffff), - [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(0xc0f2, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_CS] = GDT_ENTRY_INIT(DESC_CODE32 | DESC_USER, 0, 0xfffff), + [GDT_ENTRY_DEFAULT_USER_DS] = GDT_ENTRY_INIT(DESC_DATA32 | DESC_USER, 0, 0xfffff), /* * Segments used for calling PnP BIOS have byte granularity. * They code segments and data segments have fixed 64k limits, * the transfer segment sizes are set at run time. */ - /* 32-bit code */ - [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(0x409a, 0, 0xffff), - /* 16-bit code */ - [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(0x009a, 0, 0xffff), - /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(0x0092, 0, 0xffff), - /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(0x0092, 0, 0), - /* 16-bit data */ - [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(0x0092, 0, 0), + [GDT_ENTRY_PNPBIOS_CS32] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff), + [GDT_ENTRY_PNPBIOS_CS16] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff), + [GDT_ENTRY_PNPBIOS_DS] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0xffff), + [GDT_ENTRY_PNPBIOS_TS1] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0), + [GDT_ENTRY_PNPBIOS_TS2] = GDT_ENTRY_INIT(DESC_DATA16, 0, 0), /* * The APM segments have byte granularity and their bases * are set at run time. All have 64k limits. */ - /* 32-bit code */ - [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(0x409a, 0, 0xffff), - /* 16-bit code */ - [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(0x009a, 0, 0xffff), - /* data */ - [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(0x4092, 0, 0xffff), - - [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), - [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(0xc092, 0, 0xfffff), + [GDT_ENTRY_APMBIOS_BASE] = GDT_ENTRY_INIT(DESC_CODE32_BIOS, 0, 0xffff), + [GDT_ENTRY_APMBIOS_BASE+1] = GDT_ENTRY_INIT(DESC_CODE16, 0, 0xffff), + [GDT_ENTRY_APMBIOS_BASE+2] = GDT_ENTRY_INIT(DESC_DATA32_BIOS, 0, 0xffff), + + [GDT_ENTRY_ESPFIX_SS] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff), + [GDT_ENTRY_PERCPU] = GDT_ENTRY_INIT(DESC_DATA32, 0, 0xfffff), #endif } }; EXPORT_PER_CPU_SYMBOL_GPL(gdt_page); @@ -1856,6 +1848,13 @@ static void identify_cpu(struct cpuinfo_x86 *c) c->topo.apicid = apic->phys_pkg_id(c->topo.initial_apicid, 0); #endif + + /* + * Set default APIC and TSC_DEADLINE MSR fencing flag. AMD and + * Hygon will clear it in ->c_init() below. + */ + set_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); + /* * Vendor-specific initialization. In this section we * canonicalize the feature flags, meaning if there are diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c index 6f247d66758d..f0cd95502faa 100644 --- a/arch/x86/kernel/cpu/hygon.c +++ b/arch/x86/kernel/cpu/hygon.c @@ -354,6 +354,9 @@ static void init_hygon(struct cpuinfo_x86 *c) set_cpu_bug(c, X86_BUG_SYSRET_SS_ATTRS); check_null_seg_clears_base(c); + + /* Hygon CPUs don't need fencing after x2APIC/TSC_DEADLINE MSR writes. */ + clear_cpu_cap(c, X86_FEATURE_APIC_MSRS_FENCE); } static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c) diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c index e4c3ba91321c..f18d35fe27a9 100644 --- a/arch/x86/kernel/cpu/intel_epb.c +++ b/arch/x86/kernel/cpu/intel_epb.c @@ -237,4 +237,4 @@ err_out_online: cpuhp_remove_state(CPUHP_AP_X86_INTEL_EPB_ONLINE); return ret; } -subsys_initcall(intel_epb_init); +late_initcall(intel_epb_init); diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index f3517b8a8e91..2b46eb0fdf3a 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -87,42 +87,40 @@ struct smca_bank { static DEFINE_PER_CPU_READ_MOSTLY(struct smca_bank[MAX_NR_BANKS], smca_banks); static DEFINE_PER_CPU_READ_MOSTLY(u8[N_SMCA_BANK_TYPES], smca_bank_counts); -struct smca_bank_name { - const char *name; /* Short name for sysfs */ - const char *long_name; /* Long name for pretty-printing */ -}; - -static struct smca_bank_name smca_names[] = { - [SMCA_LS ... SMCA_LS_V2] = { "load_store", "Load Store Unit" }, - [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, - [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, - [SMCA_DE] = { "decode_unit", "Decode Unit" }, - [SMCA_RESERVED] = { "reserved", "Reserved" }, - [SMCA_EX] = { "execution_unit", "Execution Unit" }, - [SMCA_FP] = { "floating_point", "Floating Point Unit" }, - [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, - [SMCA_CS ... SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" }, - [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, +static const char * const smca_names[] = { + [SMCA_LS ... SMCA_LS_V2] = "load_store", + [SMCA_IF] = "insn_fetch", + [SMCA_L2_CACHE] = "l2_cache", + [SMCA_DE] = "decode_unit", + [SMCA_RESERVED] = "reserved", + [SMCA_EX] = "execution_unit", + [SMCA_FP] = "floating_point", + [SMCA_L3_CACHE] = "l3_cache", + [SMCA_CS ... SMCA_CS_V2] = "coherent_slave", + [SMCA_PIE] = "pie", /* UMC v2 is separate because both of them can exist in a single system. */ - [SMCA_UMC] = { "umc", "Unified Memory Controller" }, - [SMCA_UMC_V2] = { "umc_v2", "Unified Memory Controller v2" }, - [SMCA_PB] = { "param_block", "Parameter Block" }, - [SMCA_PSP ... SMCA_PSP_V2] = { "psp", "Platform Security Processor" }, - [SMCA_SMU ... SMCA_SMU_V2] = { "smu", "System Management Unit" }, - [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" }, - [SMCA_MPDMA] = { "mpdma", "MPDMA Unit" }, - [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" }, - [SMCA_PCIE ... SMCA_PCIE_V2] = { "pcie", "PCI Express Unit" }, - [SMCA_XGMI_PCS] = { "xgmi_pcs", "Ext Global Memory Interconnect PCS Unit" }, - [SMCA_NBIF] = { "nbif", "NBIF Unit" }, - [SMCA_SHUB] = { "shub", "System Hub Unit" }, - [SMCA_SATA] = { "sata", "SATA Unit" }, - [SMCA_USB] = { "usb", "USB Unit" }, - [SMCA_GMI_PCS] = { "gmi_pcs", "Global Memory Interconnect PCS Unit" }, - [SMCA_XGMI_PHY] = { "xgmi_phy", "Ext Global Memory Interconnect PHY Unit" }, - [SMCA_WAFL_PHY] = { "wafl_phy", "WAFL PHY Unit" }, - [SMCA_GMI_PHY] = { "gmi_phy", "Global Memory Interconnect PHY Unit" }, + [SMCA_UMC] = "umc", + [SMCA_UMC_V2] = "umc_v2", + [SMCA_MA_LLC] = "ma_llc", + [SMCA_PB] = "param_block", + [SMCA_PSP ... SMCA_PSP_V2] = "psp", + [SMCA_SMU ... SMCA_SMU_V2] = "smu", + [SMCA_MP5] = "mp5", + [SMCA_MPDMA] = "mpdma", + [SMCA_NBIO] = "nbio", + [SMCA_PCIE ... SMCA_PCIE_V2] = "pcie", + [SMCA_XGMI_PCS] = "xgmi_pcs", + [SMCA_NBIF] = "nbif", + [SMCA_SHUB] = "shub", + [SMCA_SATA] = "sata", + [SMCA_USB] = "usb", + [SMCA_USR_DP] = "usr_dp", + [SMCA_USR_CP] = "usr_cp", + [SMCA_GMI_PCS] = "gmi_pcs", + [SMCA_XGMI_PHY] = "xgmi_phy", + [SMCA_WAFL_PHY] = "wafl_phy", + [SMCA_GMI_PHY] = "gmi_phy", }; static const char *smca_get_name(enum smca_bank_types t) @@ -130,17 +128,8 @@ static const char *smca_get_name(enum smca_bank_types t) if (t >= N_SMCA_BANK_TYPES) return NULL; - return smca_names[t].name; -} - -const char *smca_get_long_name(enum smca_bank_types t) -{ - if (t >= N_SMCA_BANK_TYPES) - return NULL; - - return smca_names[t].long_name; + return smca_names[t]; } -EXPORT_SYMBOL_GPL(smca_get_long_name); enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank) { @@ -178,6 +167,7 @@ static const struct smca_hwid smca_hwid_mcatypes[] = { { SMCA_CS, HWID_MCATYPE(0x2E, 0x0) }, { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1) }, { SMCA_CS_V2, HWID_MCATYPE(0x2E, 0x2) }, + { SMCA_MA_LLC, HWID_MCATYPE(0x2E, 0x4) }, /* Unified Memory Controller MCA type */ { SMCA_UMC, HWID_MCATYPE(0x96, 0x0) }, @@ -212,6 +202,8 @@ static const struct smca_hwid smca_hwid_mcatypes[] = { { SMCA_SHUB, HWID_MCATYPE(0x80, 0x0) }, { SMCA_SATA, HWID_MCATYPE(0xA8, 0x0) }, { SMCA_USB, HWID_MCATYPE(0xAA, 0x0) }, + { SMCA_USR_DP, HWID_MCATYPE(0x170, 0x0) }, + { SMCA_USR_CP, HWID_MCATYPE(0x180, 0x0) }, { SMCA_GMI_PCS, HWID_MCATYPE(0x241, 0x0) }, { SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0) }, { SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0) }, diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 7b397370b4d6..fd5ce12c4f9a 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -44,6 +44,7 @@ #include <linux/sync_core.h> #include <linux/task_work.h> #include <linux/hardirq.h> +#include <linux/kexec.h> #include <asm/intel-family.h> #include <asm/processor.h> @@ -233,6 +234,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) struct llist_node *pending; struct mce_evt_llist *l; int apei_err = 0; + struct page *p; /* * Allow instrumentation around external facilities usage. Not that it @@ -286,6 +288,20 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; + + /* + * Kdump skips the poisoned page in order to avoid + * touching the error bits again. Poison the page even + * if the error is fatal and the machine is about to + * panic. + */ + if (kexec_crash_loaded()) { + if (final && (final->status & MCI_STATUS_ADDRV)) { + p = pfn_to_online_page(final->addr >> PAGE_SHIFT); + if (p) + SetPageHWPoison(p); + } + } panic(msg); } else pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); @@ -670,6 +686,16 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) barrier(); m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); + /* + * Update storm tracking here, before checking for the + * MCI_STATUS_VAL bit. Valid corrected errors count + * towards declaring, or maintaining, storm status. No + * error in a bank counts towards avoiding, or ending, + * storm status. + */ + if (!mca_cfg.cmci_disabled) + mce_track_storm(&m); + /* If this entry is not valid, ignore it */ if (!(m.status & MCI_STATUS_VAL)) continue; @@ -1601,13 +1627,6 @@ static unsigned long check_interval = INITIAL_CHECK_INTERVAL; static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ static DEFINE_PER_CPU(struct timer_list, mce_timer); -static unsigned long mce_adjust_timer_default(unsigned long interval) -{ - return interval; -} - -static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; - static void __start_timer(struct timer_list *t, unsigned long interval) { unsigned long when = jiffies + interval; @@ -1637,15 +1656,9 @@ static void mce_timer_fn(struct timer_list *t) iv = __this_cpu_read(mce_next_interval); - if (mce_available(this_cpu_ptr(&cpu_info))) { + if (mce_available(this_cpu_ptr(&cpu_info))) mc_poll_banks(); - if (mce_intel_cmci_poll()) { - iv = mce_adjust_timer(iv); - goto done; - } - } - /* * Alert userspace if needed. If we logged an MCE, reduce the polling * interval, otherwise increase the polling interval. @@ -1655,23 +1668,29 @@ static void mce_timer_fn(struct timer_list *t) else iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); -done: - __this_cpu_write(mce_next_interval, iv); - __start_timer(t, iv); + if (mce_get_storm_mode()) { + __start_timer(t, HZ); + } else { + __this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); + } } /* - * Ensure that the timer is firing in @interval from now. + * When a storm starts on any bank on this CPU, switch to polling + * once per second. When the storm ends, revert to the default + * polling interval. */ -void mce_timer_kick(unsigned long interval) +void mce_timer_kick(bool storm) { struct timer_list *t = this_cpu_ptr(&mce_timer); - unsigned long iv = __this_cpu_read(mce_next_interval); - __start_timer(t, interval); + mce_set_storm_mode(storm); - if (interval < iv) - __this_cpu_write(mce_next_interval, interval); + if (storm) + __start_timer(t, HZ); + else + __this_cpu_write(mce_next_interval, check_interval * HZ); } /* Must not be called in IRQ context where del_timer_sync() can deadlock */ @@ -1995,7 +2014,6 @@ static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) intel_init_cmci(); intel_init_lmce(); - mce_adjust_timer = cmci_intel_adjust_timer; } static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c) @@ -2008,7 +2026,6 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) switch (c->x86_vendor) { case X86_VENDOR_INTEL: mce_intel_feature_init(c); - mce_adjust_timer = cmci_intel_adjust_timer; break; case X86_VENDOR_AMD: { @@ -2568,9 +2585,6 @@ static int mce_device_create(unsigned int cpu) int err; int i, j; - if (!mce_available(&boot_cpu_data)) - return -EIO; - dev = per_cpu(mce_device, cpu); if (dev) return 0; @@ -2665,8 +2679,6 @@ static void mce_reenable_cpu(void) static int mce_cpu_dead(unsigned int cpu) { - mce_intel_hcpu_update(cpu); - /* intentionally ignoring frozen here */ if (!cpuhp_tasks_frozen) cmci_rediscover(); diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 4d8d4bcf915d..72f0695c3dc1 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -746,6 +746,7 @@ static void check_hw_inj_possible(void) wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status); rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status); + wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0); if (!status) { hw_injection_possible = false; diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 52bce533ddcc..399b62e223d2 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -42,15 +42,6 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); /* - * CMCI storm detection backoff counter - * - * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've - * encountered an error. If not, we decrement it by one. We signal the end of - * the CMCI storm when it reaches 0. - */ -static DEFINE_PER_CPU(int, cmci_backoff_cnt); - -/* * cmci_discover_lock protects against parallel discovery attempts * which could race against each other. */ @@ -63,22 +54,26 @@ static DEFINE_RAW_SPINLOCK(cmci_discover_lock); */ static DEFINE_SPINLOCK(cmci_poll_lock); +/* Linux non-storm CMCI threshold (may be overridden by BIOS) */ #define CMCI_THRESHOLD 1 -#define CMCI_POLL_INTERVAL (30 * HZ) -#define CMCI_STORM_INTERVAL (HZ) -#define CMCI_STORM_THRESHOLD 15 -static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); -static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt); -static DEFINE_PER_CPU(unsigned int, cmci_storm_state); - -enum { - CMCI_STORM_NONE, - CMCI_STORM_ACTIVE, - CMCI_STORM_SUBSIDED, -}; +/* + * MCi_CTL2 threshold for each bank when there is no storm. + * Default value for each bank may have been set by BIOS. + */ +static u16 cmci_threshold[MAX_NR_BANKS]; -static atomic_t cmci_storm_on_cpus; +/* + * High threshold to limit CMCI rate during storms. Max supported is + * 0x7FFF. Use this slightly smaller value so it has a distinctive + * signature when some asks "Why am I not seeing all corrected errors?" + * A high threshold is used instead of just disabling CMCI for a + * bank because both corrected and uncorrected errors may be logged + * in the same bank and signalled with CMCI. The threshold only applies + * to corrected errors, so keeping CMCI enabled means that uncorrected + * errors will still be processed in a timely fashion. + */ +#define CMCI_STORM_THRESHOLD 32749 static int cmci_supported(int *banks) { @@ -134,204 +129,166 @@ static bool lmce_supported(void) return tmp & FEAT_CTL_LMCE_ENABLED; } -bool mce_intel_cmci_poll(void) +/* + * Set a new CMCI threshold value. Preserve the state of the + * MCI_CTL2_CMCI_EN bit in case this happens during a + * cmci_rediscover() operation. + */ +static void cmci_set_threshold(int bank, int thresh) { - if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) - return false; - - /* - * Reset the counter if we've logged an error in the last poll - * during the storm. - */ - if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned))) - this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); - else - this_cpu_dec(cmci_backoff_cnt); + unsigned long flags; + u64 val; - return true; + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + wrmsrl(MSR_IA32_MCx_CTL2(bank), val | thresh); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } -void mce_intel_hcpu_update(unsigned long cpu) +void mce_intel_handle_storm(int bank, bool on) { - if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE) - atomic_dec(&cmci_storm_on_cpus); + if (on) + cmci_set_threshold(bank, CMCI_STORM_THRESHOLD); + else + cmci_set_threshold(bank, cmci_threshold[bank]); +} - per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; +/* + * The interrupt handler. This is called on every event. + * Just call the poller directly to log any events. + * This could in theory increase the threshold under high load, + * but doesn't for now. + */ +static void intel_threshold_interrupt(void) +{ + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); } -static void cmci_toggle_interrupt_mode(bool on) +/* + * Check all the reasons why current CPU cannot claim + * ownership of a bank. + * 1: CPU already owns this bank + * 2: BIOS owns this bank + * 3: Some other CPU owns this bank + */ +static bool cmci_skip_bank(int bank, u64 *val) { - unsigned long flags, *owned; - int bank; - u64 val; + unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned); - raw_spin_lock_irqsave(&cmci_discover_lock, flags); - owned = this_cpu_ptr(mce_banks_owned); - for_each_set_bit(bank, owned, MAX_NR_BANKS) { - rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + if (test_bit(bank, owned)) + return true; - if (on) - val |= MCI_CTL2_CMCI_EN; - else - val &= ~MCI_CTL2_CMCI_EN; + /* Skip banks in firmware first mode */ + if (test_bit(bank, mce_banks_ce_disabled)) + return true; - wrmsrl(MSR_IA32_MCx_CTL2(bank), val); - } - raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); -} + rdmsrl(MSR_IA32_MCx_CTL2(bank), *val); -unsigned long cmci_intel_adjust_timer(unsigned long interval) -{ - if ((this_cpu_read(cmci_backoff_cnt) > 0) && - (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) { - mce_notify_irq(); - return CMCI_STORM_INTERVAL; + /* Already owned by someone else? */ + if (*val & MCI_CTL2_CMCI_EN) { + clear_bit(bank, owned); + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + return true; } - switch (__this_cpu_read(cmci_storm_state)) { - case CMCI_STORM_ACTIVE: - - /* - * We switch back to interrupt mode once the poll timer has - * silenced itself. That means no events recorded and the timer - * interval is back to our poll interval. - */ - __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); - if (!atomic_sub_return(1, &cmci_storm_on_cpus)) - pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + return false; +} - fallthrough; +/* + * Decide which CMCI interrupt threshold to use: + * 1: If this bank is in storm mode from whichever CPU was + * the previous owner, stay in storm mode. + * 2: If ignoring any threshold set by BIOS, set Linux default + * 3: Try to honor BIOS threshold (unless buggy BIOS set it at zero). + */ +static u64 cmci_pick_threshold(u64 val, int *bios_zero_thresh) +{ + if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) + return val; - case CMCI_STORM_SUBSIDED: + if (!mca_cfg.bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { /* - * We wait for all CPUs to go back to SUBSIDED state. When that - * happens we switch back to interrupt mode. + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. */ - if (!atomic_read(&cmci_storm_on_cpus)) { - __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); - cmci_toggle_interrupt_mode(true); - cmci_recheck(); - } - return CMCI_POLL_INTERVAL; - default: - - /* We have shiny weather. Let the poll do whatever it thinks. */ - return interval; + *bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; } + + return val; } -static bool cmci_storm_detect(void) +/* + * Try to claim ownership of a bank. + */ +static void cmci_claim_bank(int bank, u64 val, int bios_zero_thresh, int *bios_wrong_thresh) { - unsigned int cnt = __this_cpu_read(cmci_storm_cnt); - unsigned long ts = __this_cpu_read(cmci_time_stamp); - unsigned long now = jiffies; - int r; + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); - if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE) - return true; + val |= MCI_CTL2_CMCI_EN; + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); - if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) { - cnt++; - } else { - cnt = 1; - __this_cpu_write(cmci_time_stamp, now); + /* If the enable bit did not stick, this bank should be polled. */ + if (!(val & MCI_CTL2_CMCI_EN)) { + WARN_ON(!test_bit(bank, this_cpu_ptr(mce_poll_banks))); + storm->banks[bank].poll_only = true; + return; } - __this_cpu_write(cmci_storm_cnt, cnt); - if (cnt <= CMCI_STORM_THRESHOLD) - return false; - - cmci_toggle_interrupt_mode(false); - __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); - r = atomic_add_return(1, &cmci_storm_on_cpus); - mce_timer_kick(CMCI_STORM_INTERVAL); - this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); + /* This CPU successfully set the enable bit. */ + set_bit(bank, (void *)this_cpu_ptr(&mce_banks_owned)); - if (r == 1) - pr_notice("CMCI storm detected: switching to poll mode\n"); - return true; -} + if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) { + pr_notice("CPU%d BANK%d CMCI inherited storm\n", smp_processor_id(), bank); + mce_inherit_storm(bank); + cmci_storm_begin(bank); + } else { + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + } -/* - * The interrupt handler. This is called on every event. - * Just call the poller directly to log any events. - * This could in theory increase the threshold under high load, - * but doesn't for now. - */ -static void intel_threshold_interrupt(void) -{ - if (cmci_storm_detect()) - return; + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + *bios_wrong_thresh = 1; - machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); + /* Save default threshold for each bank */ + if (cmci_threshold[bank] == 0) + cmci_threshold[bank] = val & MCI_CTL2_CMCI_THRESHOLD_MASK; } /* * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks * on this CPU. Use the algorithm recommended in the SDM to discover shared - * banks. + * banks. Called during initial bootstrap, and also for hotplug CPU operations + * to rediscover/reassign machine check banks. */ static void cmci_discover(int banks) { - unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned); + int bios_wrong_thresh = 0; unsigned long flags; int i; - int bios_wrong_thresh = 0; raw_spin_lock_irqsave(&cmci_discover_lock, flags); for (i = 0; i < banks; i++) { u64 val; int bios_zero_thresh = 0; - if (test_bit(i, owned)) + if (cmci_skip_bank(i, &val)) continue; - /* Skip banks in firmware first mode */ - if (test_bit(i, mce_banks_ce_disabled)) - continue; - - rdmsrl(MSR_IA32_MCx_CTL2(i), val); - - /* Already owned by someone else? */ - if (val & MCI_CTL2_CMCI_EN) { - clear_bit(i, owned); - __clear_bit(i, this_cpu_ptr(mce_poll_banks)); - continue; - } - - if (!mca_cfg.bios_cmci_threshold) { - val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; - val |= CMCI_THRESHOLD; - } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { - /* - * If bios_cmci_threshold boot option was specified - * but the threshold is zero, we'll try to initialize - * it to 1. - */ - bios_zero_thresh = 1; - val |= CMCI_THRESHOLD; - } - - val |= MCI_CTL2_CMCI_EN; - wrmsrl(MSR_IA32_MCx_CTL2(i), val); - rdmsrl(MSR_IA32_MCx_CTL2(i), val); - - /* Did the enable bit stick? -- the bank supports CMCI */ - if (val & MCI_CTL2_CMCI_EN) { - set_bit(i, owned); - __clear_bit(i, this_cpu_ptr(mce_poll_banks)); - /* - * We are able to set thresholds for some banks that - * had a threshold of 0. This means the BIOS has not - * set the thresholds properly or does not work with - * this boot option. Note down now and report later. - */ - if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && - (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) - bios_wrong_thresh = 1; - } else { - WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks))); - } + val = cmci_pick_threshold(val, &bios_zero_thresh); + cmci_claim_bank(i, val, bios_zero_thresh, &bios_wrong_thresh); } raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) { @@ -370,6 +327,9 @@ static void __cmci_disable_bank(int bank) val &= ~MCI_CTL2_CMCI_EN; wrmsrl(MSR_IA32_MCx_CTL2(bank), val); __clear_bit(bank, this_cpu_ptr(mce_banks_owned)); + + if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD) + cmci_storm_end(bank); } /* diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index e13a26c9c0ac..01f8f03969e6 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -41,9 +41,7 @@ struct dentry *mce_get_debugfs_dir(void); extern mce_banks_t mce_banks_ce_disabled; #ifdef CONFIG_X86_MCE_INTEL -unsigned long cmci_intel_adjust_timer(unsigned long interval); -bool mce_intel_cmci_poll(void); -void mce_intel_hcpu_update(unsigned long cpu); +void mce_intel_handle_storm(int bank, bool on); void cmci_disable_bank(int bank); void intel_init_cmci(void); void intel_init_lmce(void); @@ -51,9 +49,7 @@ void intel_clear_lmce(void); bool intel_filter_mce(struct mce *m); bool intel_mce_usable_address(struct mce *m); #else -# define cmci_intel_adjust_timer mce_adjust_timer_default -static inline bool mce_intel_cmci_poll(void) { return false; } -static inline void mce_intel_hcpu_update(unsigned long cpu) { } +static inline void mce_intel_handle_storm(int bank, bool on) { } static inline void cmci_disable_bank(int bank) { } static inline void intel_init_cmci(void) { } static inline void intel_init_lmce(void) { } @@ -62,7 +58,63 @@ static inline bool intel_filter_mce(struct mce *m) { return false; } static inline bool intel_mce_usable_address(struct mce *m) { return false; } #endif -void mce_timer_kick(unsigned long interval); +void mce_timer_kick(bool storm); + +#ifdef CONFIG_X86_MCE_THRESHOLD +void cmci_storm_begin(unsigned int bank); +void cmci_storm_end(unsigned int bank); +void mce_track_storm(struct mce *mce); +void mce_inherit_storm(unsigned int bank); +bool mce_get_storm_mode(void); +void mce_set_storm_mode(bool storm); +#else +static inline void cmci_storm_begin(unsigned int bank) {} +static inline void cmci_storm_end(unsigned int bank) {} +static inline void mce_track_storm(struct mce *mce) {} +static inline void mce_inherit_storm(unsigned int bank) {} +static inline bool mce_get_storm_mode(void) { return false; } +static inline void mce_set_storm_mode(bool storm) {} +#endif + +/* + * history: Bitmask tracking errors occurrence. Each set bit + * represents an error seen. + * + * timestamp: Last time (in jiffies) that the bank was polled. + * in_storm_mode: Is this bank in storm mode? + * poll_only: Bank does not support CMCI, skip storm tracking. + */ +struct storm_bank { + u64 history; + u64 timestamp; + bool in_storm_mode; + bool poll_only; +}; + +#define NUM_HISTORY_BITS (sizeof(u64) * BITS_PER_BYTE) + +/* How many errors within the history buffer mark the start of a storm. */ +#define STORM_BEGIN_THRESHOLD 5 + +/* + * How many polls of machine check bank without an error before declaring + * the storm is over. Since it is tracked by the bitmasks in the history + * field of struct storm_bank the mask is 30 bits [0 ... 29]. + */ +#define STORM_END_POLL_THRESHOLD 29 + +/* + * banks: per-cpu, per-bank details + * stormy_bank_count: count of MC banks in storm state + * poll_mode: CPU is in poll mode + */ +struct mca_storm_desc { + struct storm_bank banks[MAX_NR_BANKS]; + u8 stormy_bank_count; + bool poll_mode; +}; + +DECLARE_PER_CPU(struct mca_storm_desc, storm_desc); #ifdef CONFIG_ACPI_APEI int apei_write_mce(struct mce *m); diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c index ef4e7bb5fd88..89e31e1e5c9c 100644 --- a/arch/x86/kernel/cpu/mce/threshold.c +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -29,3 +29,118 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_threshold) trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); apic_eoi(); } + +DEFINE_PER_CPU(struct mca_storm_desc, storm_desc); + +void mce_inherit_storm(unsigned int bank) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + + /* + * Previous CPU owning this bank had put it into storm mode, + * but the precise history of that storm is unknown. Assume + * the worst (all recent polls of the bank found a valid error + * logged). This will avoid the new owner prematurely declaring + * the storm has ended. + */ + storm->banks[bank].history = ~0ull; + storm->banks[bank].timestamp = jiffies; +} + +bool mce_get_storm_mode(void) +{ + return __this_cpu_read(storm_desc.poll_mode); +} + +void mce_set_storm_mode(bool storm) +{ + __this_cpu_write(storm_desc.poll_mode, storm); +} + +static void mce_handle_storm(unsigned int bank, bool on) +{ + switch (boot_cpu_data.x86_vendor) { + case X86_VENDOR_INTEL: + mce_intel_handle_storm(bank, on); + break; + } +} + +void cmci_storm_begin(unsigned int bank) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + + __set_bit(bank, this_cpu_ptr(mce_poll_banks)); + storm->banks[bank].in_storm_mode = true; + + /* + * If this is the first bank on this CPU to enter storm mode + * start polling. + */ + if (++storm->stormy_bank_count == 1) + mce_timer_kick(true); +} + +void cmci_storm_end(unsigned int bank) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + storm->banks[bank].history = 0; + storm->banks[bank].in_storm_mode = false; + + /* If no banks left in storm mode, stop polling. */ + if (!this_cpu_dec_return(storm_desc.stormy_bank_count)) + mce_timer_kick(false); +} + +void mce_track_storm(struct mce *mce) +{ + struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc); + unsigned long now = jiffies, delta; + unsigned int shift = 1; + u64 history = 0; + + /* No tracking needed for banks that do not support CMCI */ + if (storm->banks[mce->bank].poll_only) + return; + + /* + * When a bank is in storm mode it is polled once per second and + * the history mask will record about the last minute of poll results. + * If it is not in storm mode, then the bank is only checked when + * there is a CMCI interrupt. Check how long it has been since + * this bank was last checked, and adjust the amount of "shift" + * to apply to history. + */ + if (!storm->banks[mce->bank].in_storm_mode) { + delta = now - storm->banks[mce->bank].timestamp; + shift = (delta + HZ) / HZ; + } + + /* If it has been a long time since the last poll, clear history. */ + if (shift < NUM_HISTORY_BITS) + history = storm->banks[mce->bank].history << shift; + + storm->banks[mce->bank].timestamp = now; + + /* History keeps track of corrected errors. VAL=1 && UC=0 */ + if ((mce->status & MCI_STATUS_VAL) && mce_is_correctable(mce)) + history |= 1; + + storm->banks[mce->bank].history = history; + + if (storm->banks[mce->bank].in_storm_mode) { + if (history & GENMASK_ULL(STORM_END_POLL_THRESHOLD, 0)) + return; + printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm subsided\n", smp_processor_id(), mce->bank); + mce_handle_storm(mce->bank, false); + cmci_storm_end(mce->bank); + } else { + if (hweight64(history) < STORM_BEGIN_THRESHOLD) + return; + printk_deferred(KERN_NOTICE "CPU%d BANK%d CMCI storm detected\n", smp_processor_id(), mce->bank); + mce_handle_storm(mce->bank, true); + cmci_storm_begin(mce->bank); + } +} diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c index 070426b9895f..857e608af641 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -370,14 +370,14 @@ static __init struct microcode_intel *get_microcode_blob(struct ucode_cpu_info * { struct cpio_data cp; + intel_collect_cpu_info(&uci->cpu_sig); + if (!load_builtin_intel_microcode(&cp)) cp = find_microcode_in_initrd(ucode_path); if (!(cp.data && cp.size)) return NULL; - intel_collect_cpu_info(&uci->cpu_sig); - return scan_microcode(cp.data, cp.size, uci, save); } @@ -410,13 +410,13 @@ void __init load_ucode_intel_bsp(struct early_load_data *ed) { struct ucode_cpu_info uci; - ed->old_rev = intel_get_microcode_revision(); - uci.mc = get_microcode_blob(&uci, false); - if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) - ucode_patch_va = UCODE_BSP_LOADED; + ed->old_rev = uci.cpu_sig.rev; - ed->new_rev = uci.cpu_sig.rev; + if (uci.mc && apply_microcode_early(&uci) == UCODE_UPDATED) { + ucode_patch_va = UCODE_BSP_LOADED; + ed->new_rev = uci.cpu_sig.rev; + } } void load_ucode_intel_ap(void) @@ -457,12 +457,6 @@ static enum ucode_state apply_microcode_late(int cpu) if (ret != UCODE_UPDATED && ret != UCODE_OK) return ret; - if (!cpu && uci->cpu_sig.rev != cur_rev) { - pr_info("Updated to revision 0x%x, date = %04x-%02x-%02x\n", - uci->cpu_sig.rev, mc->hdr.date & 0xffff, mc->hdr.date >> 24, - (mc->hdr.date >> 16) & 0xff); - } - cpu_data(cpu).microcode = uci->cpu_sig.rev; if (!cpu) boot_cpu_data.microcode = uci->cpu_sig.rev; diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c index 2d6aa5d2e3d7..d3524778a545 100644 --- a/arch/x86/kernel/cpu/mtrr/generic.c +++ b/arch/x86/kernel/cpu/mtrr/generic.c @@ -428,6 +428,10 @@ void __init mtrr_copy_map(void) * from the x86_init.hyper.init_platform() hook. It can be called only once. * The MTRR state can't be changed afterwards. To ensure that, X86_FEATURE_MTRR * is cleared. + * + * @var: MTRR variable range array to use + * @num_var: length of the @var array + * @def_type: default caching type */ void mtrr_overwrite_state(struct mtrr_var_range *var, unsigned int num_var, mtrr_type def_type) @@ -492,13 +496,15 @@ static u8 type_merge(u8 type, u8 new_type, u8 *uniform) /** * mtrr_type_lookup - look up memory type in MTRR * + * @start: Begin of the physical address range + * @end: End of the physical address range + * @uniform: output argument: + * - 1: the returned MTRR type is valid for the whole region + * - 0: otherwise + * * Return Values: * MTRR_TYPE_(type) - The effective MTRR type for the region * MTRR_TYPE_INVALID - MTRR is disabled - * - * Output Argument: - * uniform - Set to 1 when the returned MTRR type is valid for the whole - * region, set to 0 else. */ u8 mtrr_type_lookup(u64 start, u64 end, u8 *uniform) { diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 5d390df21440..b65ab214bdf5 100644 --- a/arch/x86/kernel/cpu/sgx/ioctl.c +++ b/arch/x86/kernel/cpu/sgx/ioctl.c @@ -581,7 +581,7 @@ err_out: * * Flush any outstanding enqueued EADD operations and perform EINIT. The * Launch Enclave Public Key Hash MSRs are rewritten as necessary to match - * the enclave's MRSIGNER, which is caculated from the provided sigstruct. + * the enclave's MRSIGNER, which is calculated from the provided sigstruct. * * Return: * - 0: Success. diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c index c92d88680dbf..b6b044356f1b 100644 --- a/arch/x86/kernel/crash.c +++ b/arch/x86/kernel/crash.c @@ -170,7 +170,7 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem) int ret = 0; /* Exclude the low 1M because it is always reserved */ - ret = crash_exclude_mem_range(cmem, 0, (1<<20)-1); + ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1); if (ret) return ret; @@ -198,8 +198,8 @@ static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg) } /* Prepare elf headers. Return addr and size */ -static int prepare_elf_headers(struct kimage *image, void **addr, - unsigned long *sz, unsigned long *nr_mem_ranges) +static int prepare_elf_headers(void **addr, unsigned long *sz, + unsigned long *nr_mem_ranges) { struct crash_mem *cmem; int ret; @@ -221,7 +221,7 @@ static int prepare_elf_headers(struct kimage *image, void **addr, *nr_mem_ranges = cmem->nr_ranges; /* By default prepare 64bit headers */ - ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); + ret = crash_prepare_elf64_headers(cmem, IS_ENABLED(CONFIG_X86_64), addr, sz); out: vfree(cmem); @@ -349,7 +349,7 @@ int crash_load_segments(struct kimage *image) .buf_max = ULONG_MAX, .top_down = false }; /* Prepare elf headers and add a segment */ - ret = prepare_elf_headers(image, &kbuf.buffer, &kbuf.bufsz, &pnum); + ret = prepare_elf_headers(&kbuf.buffer, &kbuf.bufsz, &pnum); if (ret) return ret; @@ -386,8 +386,8 @@ int crash_load_segments(struct kimage *image) if (ret) return ret; image->elf_load_addr = kbuf.mem; - pr_debug("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - image->elf_load_addr, kbuf.bufsz, kbuf.memsz); + kexec_dprintk("Loaded ELF headers at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->elf_load_addr, kbuf.bufsz, kbuf.memsz); return ret; } @@ -452,7 +452,7 @@ void arch_crash_handle_hotplug_event(struct kimage *image) * Create the new elfcorehdr reflecting the changes to CPU and/or * memory resources. */ - if (prepare_elf_headers(image, &elfbuf, &elfsz, &nr_mem_ranges)) { + if (prepare_elf_headers(&elfbuf, &elfsz, &nr_mem_ranges)) { pr_err("unable to create new elfcorehdr"); goto out; } diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index 794e70151203..a06b876bbf2d 100644 --- a/arch/x86/kernel/fpu/bugs.c +++ b/arch/x86/kernel/fpu/bugs.c @@ -2,6 +2,7 @@ /* * x86 FPU bug checks: */ +#include <asm/cpufeature.h> #include <asm/fpu/api.h> /* diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c index a21a4d0ecc34..520deb411a70 100644 --- a/arch/x86/kernel/fpu/core.c +++ b/arch/x86/kernel/fpu/core.c @@ -308,7 +308,7 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd); * Must be invoked from KVM after a VMEXIT before enabling interrupts when * XFD write emulation is disabled. This is required because the guest can * freely modify XFD and the state at VMEXIT is not guaranteed to be the - * same as the state on VMENTER. So software state has to be udpated before + * same as the state on VMENTER. So software state has to be updated before * any operation which depends on it can take place. * * Note: It can be invoked unconditionally even when write emulation is diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 05a110c97111..dc0956067944 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -71,9 +71,9 @@ EXPORT_SYMBOL(vmemmap_base); * GDT used on the boot CPU before switching to virtual addresses. */ static struct desc_struct startup_gdt[GDT_ENTRIES] __initdata = { - [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(0xc09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(0xa09b, 0, 0xfffff), - [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(0xc093, 0, 0xfffff), + [GDT_ENTRY_KERNEL32_CS] = GDT_ENTRY_INIT(DESC_CODE32, 0, 0xfffff), + [GDT_ENTRY_KERNEL_CS] = GDT_ENTRY_INIT(DESC_CODE64, 0, 0xfffff), + [GDT_ENTRY_KERNEL_DS] = GDT_ENTRY_INIT(DESC_DATA64, 0, 0xfffff), }; /* diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 086a2c3aaaa0..d4918d03efb4 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -114,6 +114,28 @@ SYM_CODE_START_NOALIGN(startup_64) /* Form the CR3 value being sure to include the CR3 modifier */ addq $(early_top_pgt - __START_KERNEL_map), %rax + +#ifdef CONFIG_AMD_MEM_ENCRYPT + mov %rax, %rdi + mov %rax, %r14 + + addq phys_base(%rip), %rdi + + /* + * For SEV guests: Verify that the C-bit is correct. A malicious + * hypervisor could lie about the C-bit position to perform a ROP + * attack on the guest by writing to the unencrypted stack and wait for + * the next RET instruction. + */ + call sev_verify_cbit + + /* + * Restore CR3 value without the phys_base which will be added + * below, before writing %cr3. + */ + mov %r14, %rax +#endif + jmp 1f SYM_CODE_END(startup_64) @@ -182,7 +204,7 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) /* Enable PAE mode, PSE, PGE and LA57 */ orl $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx #ifdef CONFIG_X86_5LEVEL - testl $1, __pgtable_l5_enabled(%rip) + testb $1, __pgtable_l5_enabled(%rip) jz 1f orl $X86_CR4_LA57, %ecx 1: @@ -193,21 +215,12 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) addq phys_base(%rip), %rax /* - * For SEV guests: Verify that the C-bit is correct. A malicious - * hypervisor could lie about the C-bit position to perform a ROP - * attack on the guest by writing to the unencrypted stack and wait for - * the next RET instruction. - */ - movq %rax, %rdi - call sev_verify_cbit - - /* * Switch to new page-table * * For the boot CPU this switches to early_top_pgt which still has the - * indentity mappings present. The secondary CPUs will switch to the + * identity mappings present. The secondary CPUs will switch to the * init_top_pgt here, away from the trampoline_pgd and unmap the - * indentity mapped ranges. + * identity mapped ranges. */ movq %rax, %cr3 @@ -255,6 +268,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL) testl $X2APIC_ENABLE, %eax jnz .Lread_apicid_msr +#ifdef CONFIG_X86_X2APIC + /* + * If system is in X2APIC mode then MMIO base might not be + * mapped causing the MMIO read below to fault. Faults can't + * be handled at that point. + */ + cmpl $0, x2apic_mode(%rip) + jz .Lread_apicid_mmio + + /* Force the AP into X2APIC mode. */ + orl $X2APIC_ENABLE, %eax + wrmsr + jmp .Lread_apicid_msr +#endif + +.Lread_apicid_mmio: /* Read the APIC ID from the fix-mapped MMIO space. */ movq apic_mmio_base(%rip), %rcx addq $APIC_ID, %rcx diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 41eecf180b7f..8ff2bf921519 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -707,7 +707,7 @@ static void __init hpet_select_clockevents(void) hpet_base.nr_clockevents = 0; - /* No point if MSI is disabled or CPU has an Always Runing APIC Timer */ + /* No point if MSI is disabled or CPU has an Always Running APIC Timer */ if (hpet_msi_disable || boot_cpu_has(X86_FEATURE_ARAT)) return; @@ -965,7 +965,7 @@ static bool __init mwait_pc10_supported(void) * and per CPU timer interrupts. * * The probability that this problem is going to be solved in the - * forseeable future is close to zero, so the kernel has to be cluttered + * foreseeable future is close to zero, so the kernel has to be cluttered * with heuristics to keep up with the ever growing amount of hardware and * firmware trainwrecks. Hopefully some day hardware people will understand * that the approach of "This can be fixed in software" is not sustainable. diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c index 8857abc706e4..660b601f1d6c 100644 --- a/arch/x86/kernel/idt.c +++ b/arch/x86/kernel/idt.c @@ -121,7 +121,7 @@ static const __initconst struct idt_data def_idts[] = { static const struct idt_data ia32_idt[] __initconst = { #if defined(CONFIG_IA32_EMULATION) - SYSG(IA32_SYSCALL_VECTOR, entry_INT80_compat), + SYSG(IA32_SYSCALL_VECTOR, asm_int80_emulation), #elif defined(CONFIG_X86_32) SYSG(IA32_SYSCALL_VECTOR, entry_INT80_32), #endif diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index a61c12c01270..2a422e00ed4b 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -82,7 +82,7 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params, cmdline_ptr[cmdline_len - 1] = '\0'; - pr_debug("Final command line is: %s\n", cmdline_ptr); + kexec_dprintk("Final command line is: %s\n", cmdline_ptr); cmdline_ptr_phys = bootparams_load_addr + cmdline_offset; cmdline_low_32 = cmdline_ptr_phys & 0xffffffffUL; cmdline_ext_32 = cmdline_ptr_phys >> 32; @@ -272,7 +272,12 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params, nr_e820_entries = params->e820_entries; + kexec_dprintk("E820 memmap:\n"); for (i = 0; i < nr_e820_entries; i++) { + kexec_dprintk("%016llx-%016llx (%d)\n", + params->e820_table[i].addr, + params->e820_table[i].addr + params->e820_table[i].size - 1, + params->e820_table[i].type); if (params->e820_table[i].type != E820_TYPE_RAM) continue; start = params->e820_table[i].addr; @@ -424,7 +429,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, * command line. Make sure it does not overflow */ if (cmdline_len + MAX_ELFCOREHDR_STR_LEN > header->cmdline_size) { - pr_debug("Appending elfcorehdr=<addr> to command line exceeds maximum allowed length\n"); + pr_err("Appending elfcorehdr=<addr> to command line exceeds maximum allowed length\n"); return ERR_PTR(-EINVAL); } @@ -445,7 +450,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel, return ERR_PTR(ret); } - pr_debug("Loaded purgatory at 0x%lx\n", pbuf.mem); + kexec_dprintk("Loaded purgatory at 0x%lx\n", pbuf.mem); /* @@ -490,8 +495,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, if (ret) goto out_free_params; bootparam_load_addr = kbuf.mem; - pr_debug("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - bootparam_load_addr, kbuf.bufsz, kbuf.bufsz); + kexec_dprintk("Loaded boot_param, command line and misc at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + bootparam_load_addr, kbuf.bufsz, kbuf.memsz); /* Load kernel */ kbuf.buffer = kernel + kern16_size; @@ -505,8 +510,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, goto out_free_params; kernel_load_addr = kbuf.mem; - pr_debug("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - kernel_load_addr, kbuf.bufsz, kbuf.memsz); + kexec_dprintk("Loaded 64bit kernel at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + kernel_load_addr, kbuf.bufsz, kbuf.memsz); /* Load initrd high */ if (initrd) { @@ -520,8 +525,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel, goto out_free_params; initrd_load_addr = kbuf.mem; - pr_debug("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", - initrd_load_addr, initrd_len, initrd_len); + kexec_dprintk("Loaded initrd at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + initrd_load_addr, initrd_len, initrd_len); setup_initrd(params, initrd_load_addr, initrd_len); } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index e8babebad7b8..a0ce46c0a2d8 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -576,7 +576,8 @@ static void kprobe_emulate_call_indirect(struct kprobe *p, struct pt_regs *regs) { unsigned long offs = addrmode_regoffs[p->ainsn.indirect.reg]; - int3_emulate_call(regs, regs_get_register(regs, offs)); + int3_emulate_push(regs, regs->ip - INT3_INSN_SIZE + p->ainsn.size); + int3_emulate_jmp(regs, regs_get_register(regs, offs)); } NOKPROBE_SYMBOL(kprobe_emulate_call_indirect); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 0ddb3bd0f1aa..dfe9945b9bec 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -803,8 +803,8 @@ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long); "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax)\n\t" \ "setne %al\n\t" -DEFINE_PARAVIRT_ASM(__raw_callee_save___kvm_vcpu_is_preempted, - PV_VCPU_PREEMPTED_ASM, .text); +DEFINE_ASM_FUNC(__raw_callee_save___kvm_vcpu_is_preempted, + PV_VCPU_PREEMPTED_ASM, .text); #endif static void __init kvm_guest_init(void) @@ -942,7 +942,7 @@ static void __init kvm_init_platform(void) * Reset the host's shared pages list related to kernel * specific page encryption status settings before we load a * new kernel by kexec. Reset the page encryption status - * during early boot intead of just before kexec to avoid SMP + * during early boot instead of just before kexec to avoid SMP * races during kvm_pv_guest_cpu_reboot(). * NOTE: We cannot reset the complete shared pages list * here as we need to retain the UEFI/OVMF firmware diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c index fb8f52149be9..a95d0900e8c6 100644 --- a/arch/x86/kernel/kvmclock.c +++ b/arch/x86/kernel/kvmclock.c @@ -42,7 +42,7 @@ static int __init parse_no_kvmclock_vsyscall(char *arg) } early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall); -/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */ +/* Aligned to page sizes to match what's mapped via vsyscalls to userspace */ #define HVC_BOOT_ARRAY_SIZE \ (PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info)) diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index adc67f98819a..7a814b41402d 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -7,7 +7,7 @@ * This handles calls from both 32bit and 64bit mode. * * Lock order: - * contex.ldt_usr_sem + * context.ldt_usr_sem * mmap_lock * context.lock */ @@ -49,7 +49,7 @@ void load_mm_ldt(struct mm_struct *mm) /* * Any change to mm->context.ldt is followed by an IPI to all * CPUs with the mm active. The LDT will not be freed until - * after the IPI is handled by all such CPUs. This means that, + * after the IPI is handled by all such CPUs. This means that * if the ldt_struct changes before we return, the values we see * will be safe, and the new values will be loaded before we run * any user code. @@ -685,7 +685,7 @@ SYSCALL_DEFINE3(modify_ldt, int , func , void __user * , ptr , } /* * The SYSCALL_DEFINE() macros give us an 'unsigned long' - * return type, but tht ABI for sys_modify_ldt() expects + * return type, but the ABI for sys_modify_ldt() expects * 'int'. This cast gives us an int-sized value in %rax * for the return code. The 'unsigned' is necessary so * the compiler does not try to sign-extend the negative diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 1a3e2c05a8a5..bc0a5348b4a6 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -42,12 +42,9 @@ struct init_pgtable_data { static int mem_region_callback(struct resource *res, void *arg) { struct init_pgtable_data *data = arg; - unsigned long mstart, mend; - - mstart = res->start; - mend = mstart + resource_size(res) - 1; - return kernel_ident_mapping_init(data->info, data->level4p, mstart, mend); + return kernel_ident_mapping_init(data->info, data->level4p, + res->start, res->end + 1); } static int diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 5f71a0cf4399..e18914c0e38a 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -276,7 +276,7 @@ int module_finalize(const Elf_Ehdr *hdr, struct module *me) { const Elf_Shdr *s, *alt = NULL, *locks = NULL, - *para = NULL, *orc = NULL, *orc_ip = NULL, + *orc = NULL, *orc_ip = NULL, *retpolines = NULL, *returns = NULL, *ibt_endbr = NULL, *calls = NULL, *cfi = NULL; char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; @@ -286,8 +286,6 @@ int module_finalize(const Elf_Ehdr *hdr, alt = s; if (!strcmp(".smp_locks", secstrings + s->sh_name)) locks = s; - if (!strcmp(".parainstructions", secstrings + s->sh_name)) - para = s; if (!strcmp(".orc_unwind", secstrings + s->sh_name)) orc = s; if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name)) @@ -304,14 +302,6 @@ int module_finalize(const Elf_Ehdr *hdr, ibt_endbr = s; } - /* - * See alternative_instructions() for the ordering rules between the - * various patching types. - */ - if (para) { - void *pseg = (void *)para->sh_addr; - apply_paravirt(pseg, pseg + para->sh_size); - } if (retpolines || cfi) { void *rseg = NULL, *cseg = NULL; unsigned int rsize = 0, csize = 0; @@ -341,7 +331,7 @@ int module_finalize(const Elf_Ehdr *hdr, void *aseg = (void *)alt->sh_addr; apply_alternatives(aseg, aseg + alt->sh_size); } - if (calls || para) { + if (calls || alt) { struct callthunk_sites cs = {}; if (calls) { @@ -349,9 +339,9 @@ int module_finalize(const Elf_Ehdr *hdr, cs.call_end = (void *)calls->sh_addr + calls->sh_size; } - if (para) { - cs.pv_start = (void *)para->sh_addr; - cs.pv_end = (void *)para->sh_addr + para->sh_size; + if (alt) { + cs.alt_start = (void *)alt->sh_addr; + cs.alt_end = (void *)alt->sh_addr + alt->sh_size; } callthunks_patch_module_calls(&cs, me); diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 97f1436c1a20..5358d43886ad 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -34,14 +34,8 @@ #include <asm/io_bitmap.h> #include <asm/gsseg.h> -/* - * nop stub, which must not clobber anything *including the stack* to - * avoid confusing the entry prologues. - */ -DEFINE_PARAVIRT_ASM(_paravirt_nop, "", .entry.text); - /* stub always returning 0. */ -DEFINE_PARAVIRT_ASM(paravirt_ret0, "xor %eax,%eax", .entry.text); +DEFINE_ASM_FUNC(paravirt_ret0, "xor %eax,%eax", .entry.text); void __init default_banner(void) { @@ -49,26 +43,12 @@ void __init default_banner(void) pv_info.name); } -/* Undefined instruction for dealing with missing ops pointers. */ -noinstr void paravirt_BUG(void) -{ - BUG(); -} - -static unsigned paravirt_patch_call(void *insn_buff, const void *target, - unsigned long addr, unsigned len) -{ - __text_gen_insn(insn_buff, CALL_INSN_OPCODE, - (void *)addr, target, CALL_INSN_SIZE); - return CALL_INSN_SIZE; -} - #ifdef CONFIG_PARAVIRT_XXL -DEFINE_PARAVIRT_ASM(_paravirt_ident_64, "mov %rdi, %rax", .text); -DEFINE_PARAVIRT_ASM(pv_native_save_fl, "pushf; pop %rax", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_irq_disable, "cli", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_irq_enable, "sti", .noinstr.text); -DEFINE_PARAVIRT_ASM(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); +DEFINE_ASM_FUNC(_paravirt_ident_64, "mov %rdi, %rax", .text); +DEFINE_ASM_FUNC(pv_native_save_fl, "pushf; pop %rax", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_irq_disable, "cli", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text); +DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text); #endif DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key); @@ -85,28 +65,6 @@ static void native_tlb_remove_table(struct mmu_gather *tlb, void *table) tlb_remove_page(tlb, table); } -unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr, - unsigned int len) -{ - /* - * Neat trick to map patch type back to the call within the - * corresponding structure. - */ - void *opfunc = *((void **)&pv_ops + type); - unsigned ret; - - if (opfunc == NULL) - /* If there's no function, patch it with paravirt_BUG() */ - ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len); - else if (opfunc == _paravirt_nop) - ret = 0; - else - /* Otherwise call the function. */ - ret = paravirt_patch_call(insn_buff, opfunc, addr, len); - - return ret; -} - struct static_key paravirt_steal_enabled; struct static_key paravirt_steal_rq_enabled; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index b6f4e8399fca..ab49ade31b0d 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -477,7 +477,7 @@ void native_tss_update_io_bitmap(void) /* * Make sure that the TSS limit is covering the IO bitmap. It might have * been cut down by a VMEXIT to 0x67 which would cause a subsequent I/O - * access from user space to trigger a #GP because tbe bitmap is outside + * access from user space to trigger a #GP because the bitmap is outside * the TSS limit. */ refresh_tss_limit(); diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 1526747bedf2..ec2c21a1844e 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -226,8 +226,6 @@ static void __init reserve_brk(void) _brk_start = 0; } -u64 relocated_ramdisk; - #ifdef CONFIG_BLK_DEV_INITRD static u64 __init get_ramdisk_image(void) @@ -261,7 +259,7 @@ static void __init relocate_initrd(void) u64 area_size = PAGE_ALIGN(ramdisk_size); /* We need to move the initrd down into directly mapped mem */ - relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0, + u64 relocated_ramdisk = memblock_phys_alloc_range(area_size, PAGE_SIZE, 0, PFN_PHYS(max_pfn_mapped)); if (!relocated_ramdisk) panic("Cannot find place for new RAMDISK of size %lld\n", diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 2c97bf7b56ae..b30d6e180df7 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -106,8 +106,8 @@ void __init pcpu_populate_pte(unsigned long addr) static inline void setup_percpu_segment(int cpu) { #ifdef CONFIG_X86_32 - struct desc_struct d = GDT_ENTRY_INIT(0x8092, per_cpu_offset(cpu), - 0xFFFFF); + struct desc_struct d = GDT_ENTRY_INIT(DESC_DATA32, + per_cpu_offset(cpu), 0xFFFFF); write_gdt_entry(get_cpu_gdt_rw(cpu), GDT_ENTRY_PERCPU, &d, DESCTYPE_S); #endif diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index ccb0915e84e1..1d24ec679915 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -96,7 +96,7 @@ static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) /* Tell the hypervisor what went wrong. */ val |= GHCB_SEV_TERM_REASON(set, reason); - /* Request Guest Termination from Hypvervisor */ + /* Request Guest Termination from Hypervisor */ sev_es_wr_ghcb_msr(val); VMGEXIT(); diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 70472eebe719..c67285824e82 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -1234,10 +1234,6 @@ void setup_ghcb(void) if (!cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT)) return; - /* First make sure the hypervisor talks a supported protocol. */ - if (!sev_es_negotiate_protocol()) - sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); - /* * Check whether the runtime #VC exception handler is active. It uses * the per-CPU GHCB page which is set up by sev_es_init_vc_handling(). @@ -1255,6 +1251,13 @@ void setup_ghcb(void) } /* + * Make sure the hypervisor talks a supported protocol. + * This gets called only in the BSP boot phase. + */ + if (!sev_es_negotiate_protocol()) + sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ); + + /* * Clear the boot_ghcb. The first exception comes in before the bss * section is cleared. */ diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 65fe2094da59..31b6f5dddfc2 100644 --- a/arch/x86/kernel/signal.c +++ b/arch/x86/kernel/signal.c @@ -27,6 +27,7 @@ #include <linux/context_tracking.h> #include <linux/entry-common.h> #include <linux/syscalls.h> +#include <linux/rseq.h> #include <asm/processor.h> #include <asm/ucontext.h> diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 2cc2aa120b4b..3f57ce68a3f1 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -757,6 +757,7 @@ const struct cpumask *cpu_clustergroup_mask(int cpu) { return cpu_l2c_shared_mask(cpu); } +EXPORT_SYMBOL_GPL(cpu_clustergroup_mask); static void impress_friends(void) { diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index c876f1d36a81..b0737a15c470 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -37,6 +37,7 @@ #include <linux/nmi.h> #include <linux/mm.h> #include <linux/smp.h> +#include <linux/cpu.h> #include <linux/io.h> #include <linux/hardirq.h> #include <linux/atomic.h> diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 54a5596adaa6..a349dbfc6d5a 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -267,19 +267,6 @@ SECTIONS } #endif - /* - * start address and size of operations which during runtime - * can be patched with virtualization friendly instructions or - * baremetal native ones. Think page table operations. - * Details in paravirt_types.h - */ - . = ALIGN(8); - .parainstructions : AT(ADDR(.parainstructions) - LOAD_OFFSET) { - __parainstructions = .; - *(.parainstructions) - __parainstructions_end = .; - } - #ifdef CONFIG_RETPOLINE /* * List of instructions that call/jmp/jcc to retpoline thunks diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index dda6fc4cfae8..42d3f47f4c07 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -105,7 +105,7 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( /* * If the index isn't significant, use the first entry with a - * matching function. It's userspace's responsibilty to not + * matching function. It's userspace's responsibility to not * provide "duplicate" entries in all cases. */ if (!(e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) || e->index == index) diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index ee8c4c3496ed..eea6ea7f14af 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -182,6 +182,7 @@ static int kvm_mmu_rmaps_stat_release(struct inode *inode, struct file *file) } static const struct file_operations mmu_rmaps_stat_fops = { + .owner = THIS_MODULE, .open = kvm_mmu_rmaps_stat_open, .read = seq_read, .llseek = seq_lseek, diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 238afd7335e4..4943f6b2bbee 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -2388,7 +2388,7 @@ static u16 kvm_hvcall_signal_event(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *h if (!eventfd) return HV_STATUS_INVALID_PORT_ID; - eventfd_signal(eventfd, 1); + eventfd_signal(eventfd); return HV_STATUS_SUCCESS; } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c57e181bba21..0b1f991b9a31 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -987,7 +987,7 @@ static void pte_list_desc_remove_entry(struct kvm *kvm, /* * The head descriptor is empty. If there are no tail descriptors, - * nullify the rmap head to mark the list as emtpy, else point the rmap + * nullify the rmap head to mark the list as empty, else point the rmap * head at the next descriptor, i.e. the new head. */ if (!head_desc->more) @@ -6544,7 +6544,7 @@ void kvm_mmu_try_split_huge_pages(struct kvm *kvm, kvm_tdp_mmu_try_split_huge_pages(kvm, memslot, start, end, target_level, false); /* - * A TLB flush is unnecessary at this point for the same resons as in + * A TLB flush is unnecessary at this point for the same reasons as in * kvm_mmu_slot_try_split_huge_pages(). */ } diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index bd30ebfb2f2c..04c247bfe318 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -146,7 +146,7 @@ static bool try_step_up(struct tdp_iter *iter) * Step to the next SPTE in a pre-order traversal of the paging structure. * To get to the next SPTE, the iterator either steps down towards the goal * GFN, if at a present, non-last-level SPTE, or over to a SPTE mapping a - * highter GFN. + * higher GFN. * * The basic algorithm is as follows: * 1. If the current SPTE is a non-last-level SPTE, step down into the page diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 4900c078045a..6ee925d66648 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2972,6 +2972,25 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); } + + /* + * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if + * the host/guest supports its use. + * + * guest_can_use() checks a number of requirements on the host/guest to + * ensure that MSR_IA32_XSS is available, but it might report true even + * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host + * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better + * to further check that the guest CPUID actually supports + * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved + * guests will still get intercepted and caught in the normal + * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths. + */ + if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); + else + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0); } void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm) diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 712146312358..7fb51424fc74 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -103,6 +103,7 @@ static const struct svm_direct_access_msrs { { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, { .index = MSR_IA32_LASTINTTOIP, .always = false }, + { .index = MSR_IA32_XSS, .always = false }, { .index = MSR_EFER, .always = false }, { .index = MSR_IA32_CR_PAT, .always = false }, { .index = MSR_AMD64_SEV_ES_GHCB, .always = true }, @@ -1855,15 +1856,17 @@ void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) bool old_paging = is_paging(vcpu); #ifdef CONFIG_X86_64 - if (vcpu->arch.efer & EFER_LME && !vcpu->arch.guest_state_protected) { + if (vcpu->arch.efer & EFER_LME) { if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) { vcpu->arch.efer |= EFER_LMA; - svm->vmcb->save.efer |= EFER_LMA | EFER_LME; + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer |= EFER_LMA | EFER_LME; } if (is_paging(vcpu) && !(cr0 & X86_CR0_PG)) { vcpu->arch.efer &= ~EFER_LMA; - svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); + if (!vcpu->arch.guest_state_protected) + svm->vmcb->save.efer &= ~(EFER_LMA | EFER_LME); } } #endif @@ -4741,7 +4744,7 @@ static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * Emulation is possible for SEV guests if and only if a prefilled * buffer containing the bytes of the intercepted instruction is * available. SEV guest memory is encrypted with a guest specific key - * and cannot be decrypted by KVM, i.e. KVM would read cyphertext and + * and cannot be decrypted by KVM, i.e. KVM would read ciphertext and * decode garbage. * * If KVM is NOT trying to simply skip an instruction, inject #UD if diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index be67ab7fdd10..c409f934c377 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -30,7 +30,7 @@ #define IOPM_SIZE PAGE_SIZE * 3 #define MSRPM_SIZE PAGE_SIZE * 2 -#define MAX_DIRECT_ACCESS_MSRS 46 +#define MAX_DIRECT_ACCESS_MSRS 47 #define MSRPM_OFFSETS 32 extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly; extern bool npt_enabled; diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index c5ec0ef51ff7..65826fe23f33 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -6561,7 +6561,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, * code was changed such that flag signals vmcs12 should * be copied into eVMCS in guest memory. * - * To preserve backwards compatability, allow user + * To preserve backwards compatibility, allow user * to set this flag even when there is no VMXON region. */ if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS) diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index be20a60047b1..e0f86f11c345 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1809,7 +1809,7 @@ static void vmx_inject_exception(struct kvm_vcpu *vcpu) * do generate error codes with bits 31:16 set, and so KVM's * ABI lets userspace shove in arbitrary 32-bit values. Drop * the upper bits to avoid VM-Fail, losing information that - * does't really exist is preferable to killing the VM. + * doesn't really exist is preferable to killing the VM. */ vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, (u16)ex->error_code); intr_info |= INTR_INFO_DELIVER_CODE_MASK; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2c924075f6f1..cec0fc2a4b1c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5518,8 +5518,8 @@ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu, static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu, struct kvm_xsave *guest_xsave) { - return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, - sizeof(guest_xsave->region)); + kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region, + sizeof(guest_xsave->region)); } static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu, @@ -10165,7 +10165,7 @@ static void kvm_inject_exception(struct kvm_vcpu *vcpu) * * But, if a VM-Exit occurs during instruction execution, and KVM does NOT skip * the instruction or inject an exception, then KVM can incorrecty inject a new - * asynchrounous event if the event became pending after the CPU fetched the + * asynchronous event if the event became pending after the CPU fetched the * instruction (in the guest). E.g. if a page fault (#PF, #NPF, EPT violation) * occurs and is resolved by KVM, a coincident NMI, SMI, IRQ, etc... can be * injected on the restarted instruction instead of being deferred until the @@ -10186,7 +10186,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, int r; /* - * Process nested events first, as nested VM-Exit supercedes event + * Process nested events first, as nested VM-Exit supersedes event * re-injection. If there's an event queued for re-injection, it will * be saved into the appropriate vmc{b,s}12 fields on nested VM-Exit. */ @@ -10884,7 +10884,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) /* * Assert that vCPU vs. VM APICv state is consistent. An APICv * update must kick and wait for all vCPUs before toggling the - * per-VM state, and responsing vCPUs must wait for the update + * per-VM state, and responding vCPUs must wait for the update * to complete before servicing KVM_REQ_APICV_UPDATE. */ WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) && @@ -13031,7 +13031,10 @@ bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return true; - return vcpu->arch.preempted_in_kernel; + if (vcpu != kvm_get_running_vcpu()) + return vcpu->arch.preempted_in_kernel; + + return static_call(kvm_x86_get_cpl)(vcpu) == 0; } unsigned long kvm_arch_vcpu_get_ip(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index e53fad915a62..523bb6df5ac9 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -2088,7 +2088,7 @@ static bool kvm_xen_hcall_evtchn_send(struct kvm_vcpu *vcpu, u64 param, u64 *r) if (ret < 0 && ret != -ENOTCONN) return false; } else { - eventfd_signal(evtchnfd->deliver.eventfd.ctx, 1); + eventfd_signal(evtchnfd->deliver.eventfd.ctx); } *r = 0; diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c index 7c48ff4ae8d1..7af743bd3b13 100644 --- a/arch/x86/lib/cache-smp.c +++ b/arch/x86/lib/cache-smp.c @@ -1,4 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 +#include <asm/paravirt.h> #include <linux/smp.h> #include <linux/export.h> diff --git a/arch/x86/lib/csum-partial_64.c b/arch/x86/lib/csum-partial_64.c index cea25ca8b8cf..c9dae65ac01b 100644 --- a/arch/x86/lib/csum-partial_64.c +++ b/arch/x86/lib/csum-partial_64.c @@ -11,26 +11,23 @@ #include <asm/checksum.h> #include <asm/word-at-a-time.h> -static inline unsigned short from32to16(unsigned a) +static inline __wsum csum_finalize_sum(u64 temp64) { - unsigned short b = a >> 16; - asm("addw %w2,%w0\n\t" - "adcw $0,%w0\n" - : "=r" (b) - : "0" (b), "r" (a)); - return b; + return (__force __wsum)((temp64 + ror64(temp64, 32)) >> 32); } -static inline __wsum csum_tail(u64 temp64, int odd) +static inline unsigned long update_csum_40b(unsigned long sum, const unsigned long m[5]) { - unsigned int result; - - result = add32_with_carry(temp64 >> 32, temp64 & 0xffffffff); - if (unlikely(odd)) { - result = from32to16(result); - result = ((result >> 8) & 0xff) | ((result & 0xff) << 8); - } - return (__force __wsum)result; + asm("addq %1,%0\n\t" + "adcq %2,%0\n\t" + "adcq %3,%0\n\t" + "adcq %4,%0\n\t" + "adcq %5,%0\n\t" + "adcq $0,%0" + :"+r" (sum) + :"m" (m[0]), "m" (m[1]), "m" (m[2]), + "m" (m[3]), "m" (m[4])); + return sum; } /* @@ -47,64 +44,32 @@ static inline __wsum csum_tail(u64 temp64, int odd) __wsum csum_partial(const void *buff, int len, __wsum sum) { u64 temp64 = (__force u64)sum; - unsigned odd; - odd = 1 & (unsigned long) buff; - if (unlikely(odd)) { - if (unlikely(len == 0)) - return sum; - temp64 = ror32((__force u32)sum, 8); - temp64 += (*(unsigned char *)buff << 8); - len--; - buff++; + /* Do two 40-byte chunks in parallel to get better ILP */ + if (likely(len >= 80)) { + u64 temp64_2 = 0; + do { + temp64 = update_csum_40b(temp64, buff); + temp64_2 = update_csum_40b(temp64_2, buff + 40); + buff += 80; + len -= 80; + } while (len >= 80); + + asm("addq %1,%0\n\t" + "adcq $0,%0" + :"+r" (temp64): "r" (temp64_2)); } /* - * len == 40 is the hot case due to IPv6 headers, but annotating it likely() - * has noticeable negative affect on codegen for all other cases with - * minimal performance benefit here. + * len == 40 is the hot case due to IPv6 headers, so return + * early for that exact case without checking the tail bytes. */ - if (len == 40) { - asm("addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcq 4*8(%[src]),%[res]\n\t" - "adcq $0,%[res]" - : [res] "+r"(temp64) - : [src] "r"(buff), "m"(*(const char(*)[40])buff)); - return csum_tail(temp64, odd); - } - if (unlikely(len >= 64)) { - /* - * Extra accumulators for better ILP in the loop. - */ - u64 tmp_accum, tmp_carries; - - asm("xorl %k[tmp_accum],%k[tmp_accum]\n\t" - "xorl %k[tmp_carries],%k[tmp_carries]\n\t" - "subl $64, %[len]\n\t" - "1:\n\t" - "addq 0*8(%[src]),%[res]\n\t" - "adcq 1*8(%[src]),%[res]\n\t" - "adcq 2*8(%[src]),%[res]\n\t" - "adcq 3*8(%[src]),%[res]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq 4*8(%[src]),%[tmp_accum]\n\t" - "adcq 5*8(%[src]),%[tmp_accum]\n\t" - "adcq 6*8(%[src]),%[tmp_accum]\n\t" - "adcq 7*8(%[src]),%[tmp_accum]\n\t" - "adcl $0,%k[tmp_carries]\n\t" - "addq $64, %[src]\n\t" - "subl $64, %[len]\n\t" - "jge 1b\n\t" - "addq %[tmp_accum],%[res]\n\t" - "adcq %[tmp_carries],%[res]\n\t" - "adcq $0,%[res]" - : [tmp_accum] "=&r"(tmp_accum), - [tmp_carries] "=&r"(tmp_carries), [res] "+r"(temp64), - [len] "+r"(len), [src] "+r"(buff) - : "m"(*(const char *)buff)); + if (len >= 40) { + temp64 = update_csum_40b(temp64, buff); + len -= 40; + if (!len) + return csum_finalize_sum(temp64); + buff += 40; } if (len & 32) { @@ -143,7 +108,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum) : [res] "+r"(temp64) : [trail] "r"(trail)); } - return csum_tail(temp64, odd); + return csum_finalize_sum(temp64); } EXPORT_SYMBOL(csum_partial); diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c index 0e65d00e2339..23f81ca3f06b 100644 --- a/arch/x86/lib/delay.c +++ b/arch/x86/lib/delay.c @@ -128,7 +128,7 @@ static void delay_halt_mwaitx(u64 unused, u64 cycles) delay = min_t(u64, MWAITX_MAX_WAIT_CYCLES, cycles); /* - * Use cpu_tss_rw as a cacheline-aligned, seldomly accessed per-cpu + * Use cpu_tss_rw as a cacheline-aligned, seldom accessed per-cpu * variable as the monitor target. */ __monitorx(raw_cpu_ptr(&cpu_tss_rw), 0, 0); diff --git a/arch/x86/lib/misc.c b/arch/x86/lib/misc.c index 92cd8ecc3a2c..40b81c338ae5 100644 --- a/arch/x86/lib/misc.c +++ b/arch/x86/lib/misc.c @@ -8,7 +8,7 @@ */ int num_digits(int val) { - int m = 10; + long long m = 10; int d = 1; if (val < 0) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index ab778eac1952..679b09cfe241 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1370,6 +1370,8 @@ void do_user_addr_fault(struct pt_regs *regs, goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); + if (fault & VM_FAULT_MAJOR) + flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a190aae8ceaf..a0dffaca6d2b 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1013,7 +1013,7 @@ static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd) return; } - /* free a pte talbe */ + /* free a pte table */ free_pagetable(pmd_page(*pmd), 0); spin_lock(&init_mm.page_table_lock); pmd_clear(pmd); @@ -1031,7 +1031,7 @@ static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud) return; } - /* free a pmd talbe */ + /* free a pmd table */ free_pagetable(pud_page(*pud), 0); spin_lock(&init_mm.page_table_lock); pud_clear(pud); @@ -1049,7 +1049,7 @@ static void __meminit free_pud_table(pud_t *pud_start, p4d_t *p4d) return; } - /* free a pud talbe */ + /* free a pud table */ free_pagetable(p4d_page(*p4d), 0); spin_lock(&init_mm.page_table_lock); p4d_clear(p4d); diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c index a68f2dda0948..70b91de2e053 100644 --- a/arch/x86/mm/mem_encrypt_amd.c +++ b/arch/x86/mm/mem_encrypt_amd.c @@ -32,6 +32,7 @@ #include <asm/msr.h> #include <asm/cmdline.h> #include <asm/sev.h> +#include <asm/ia32.h> #include "mm_internal.h" @@ -481,6 +482,16 @@ void __init sme_early_init(void) */ if (sev_status & MSR_AMD64_SEV_ES_ENABLED) x86_cpuinit.parallel_bringup = false; + + /* + * The VMM is capable of injecting interrupt 0x80 and triggering the + * compatibility syscall path. + * + * By default, the 32-bit emulation is disabled in order to ensure + * the safety of the VM. + */ + if (sev_status & MSR_AMD64_SEV_ENABLED) + ia32_disable(); } void __init mem_encrypt_free_decrypted_mem(void) diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index b29ceb19e46e..adc497b93f03 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -450,37 +450,6 @@ int __node_distance(int from, int to) EXPORT_SYMBOL(__node_distance); /* - * Sanity check to catch more bad NUMA configurations (they are amazingly - * common). Make sure the nodes cover all memory. - */ -static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) -{ - u64 numaram, e820ram; - int i; - - numaram = 0; - for (i = 0; i < mi->nr_blks; i++) { - u64 s = mi->blk[i].start >> PAGE_SHIFT; - u64 e = mi->blk[i].end >> PAGE_SHIFT; - numaram += e - s; - numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); - if ((s64)numaram < 0) - numaram = 0; - } - - e820ram = max_pfn - absent_pages_in_range(0, max_pfn); - - /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ - if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { - printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", - (numaram << PAGE_SHIFT) >> 20, - (e820ram << PAGE_SHIFT) >> 20); - return false; - } - return true; -} - -/* * Mark all currently memblock-reserved physical memory (which covers the * kernel's own memory ranges) as hot-unswappable. */ @@ -585,7 +554,8 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) return -EINVAL; } } - if (!numa_meminfo_cover_memory(mi)) + + if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; /* Finally register nodes. */ diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c index de10800cd4dd..0904d7e8e126 100644 --- a/arch/x86/mm/pat/memtype.c +++ b/arch/x86/mm/pat/memtype.c @@ -14,7 +14,7 @@ * memory ranges: uncached, write-combining, write-through, write-protected, * and the most commonly used and default attribute: write-back caching. * - * PAT support supercedes and augments MTRR support in a compatible fashion: MTRR is + * PAT support supersedes and augments MTRR support in a compatible fashion: MTRR is * a hardware interface to enumerate a limited number of physical memory ranges * and set their caching attributes explicitly, programmed into the CPU via MSRs. * Even modern CPUs have MTRRs enabled - but these are typically not touched diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index bda9f129835e..e9b448d1b1b7 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -1621,7 +1621,7 @@ repeat: /* * We need to keep the pfn from the existing PTE, - * after all we're only going to change it's attributes + * after all we're only going to change its attributes * not the memory it points to */ new_pte = pfn_pte(pfn, new_prot); @@ -2447,7 +2447,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address, /* * The typical sequence for unmapping is to find a pte through * lookup_address_in_pgd() (ideally, it should never return NULL because - * the address is already mapped) and change it's protections. As pfn is + * the address is already mapped) and change its protections. As pfn is * the *target* of a mapping, it's not useful while unmapping. */ struct cpa_data cpa = { diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 5dd733944629..669ba1c345b3 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -6,7 +6,7 @@ * * https://github.com/IAIK/KAISER * - * The original work was written by and and signed off by for the Linux + * The original work was written by and signed off by for the Linux * kernel by: * * Signed-off-by: Richard Fellner <richard.fellner@student.tugraz.at> diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 453ea95b667d..5768d386efab 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -355,7 +355,7 @@ static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm, /* * Validate that it is not running on an SMT sibling as this would - * make the excercise pointless because the siblings share L1D. If + * make the exercise pointless because the siblings share L1D. If * it runs on a SMT sibling, notify it with SIGBUS on return to * user/guest */ diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 8c10d9abc239..919f647c740f 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -17,6 +17,7 @@ #include <asm/nospec-branch.h> #include <asm/text-patching.h> #include <asm/unwind.h> +#include <asm/cfi.h> static bool all_callee_regs_used[4] = {true, true, true, true}; @@ -51,9 +52,11 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) #ifdef CONFIG_X86_KERNEL_IBT -#define EMIT_ENDBR() EMIT(gen_endbr(), 4) +#define EMIT_ENDBR() EMIT(gen_endbr(), 4) +#define EMIT_ENDBR_POISON() EMIT(gen_endbr_poison(), 4) #else #define EMIT_ENDBR() +#define EMIT_ENDBR_POISON() #endif static bool is_imm8(int value) @@ -304,6 +307,88 @@ static void pop_callee_regs(u8 **pprog, bool *callee_regs_used) *pprog = prog; } +static void emit_nops(u8 **pprog, int len) +{ + u8 *prog = *pprog; + int i, noplen; + + while (len > 0) { + noplen = len; + + if (noplen > ASM_NOP_MAX) + noplen = ASM_NOP_MAX; + + for (i = 0; i < noplen; i++) + EMIT1(x86_nops[noplen][i]); + len -= noplen; + } + + *pprog = prog; +} + +/* + * Emit the various CFI preambles, see asm/cfi.h and the comments about FineIBT + * in arch/x86/kernel/alternative.c + */ + +static void emit_fineibt(u8 **pprog, u32 hash) +{ + u8 *prog = *pprog; + + EMIT_ENDBR(); + EMIT3_off32(0x41, 0x81, 0xea, hash); /* subl $hash, %r10d */ + EMIT2(0x74, 0x07); /* jz.d8 +7 */ + EMIT2(0x0f, 0x0b); /* ud2 */ + EMIT1(0x90); /* nop */ + EMIT_ENDBR_POISON(); + + *pprog = prog; +} + +static void emit_kcfi(u8 **pprog, u32 hash) +{ + u8 *prog = *pprog; + + EMIT1_off32(0xb8, hash); /* movl $hash, %eax */ +#ifdef CONFIG_CALL_PADDING + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); + EMIT1(0x90); +#endif + EMIT_ENDBR(); + + *pprog = prog; +} + +static void emit_cfi(u8 **pprog, u32 hash) +{ + u8 *prog = *pprog; + + switch (cfi_mode) { + case CFI_FINEIBT: + emit_fineibt(&prog, hash); + break; + + case CFI_KCFI: + emit_kcfi(&prog, hash); + break; + + default: + EMIT_ENDBR(); + break; + } + + *pprog = prog; +} + /* * Emit x86-64 prologue code for BPF program. * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes @@ -315,12 +400,11 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf, { u8 *prog = *pprog; + emit_cfi(&prog, is_subprog ? cfi_bpf_subprog_hash : cfi_bpf_hash); /* BPF trampoline can be made to work without these nops, * but let's waste 5 bytes for now and optimize later */ - EMIT_ENDBR(); - memcpy(prog, x86_nops[5], X86_PATCH_SIZE); - prog += X86_PATCH_SIZE; + emit_nops(&prog, X86_PATCH_SIZE); if (!ebpf_from_cbpf) { if (tail_call_reachable && !is_subprog) /* When it's the entry of the whole tailcall context, @@ -626,8 +710,7 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog, if (stack_depth) EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8)); - memcpy(prog, x86_nops[5], X86_PATCH_SIZE); - prog += X86_PATCH_SIZE; + emit_nops(&prog, X86_PATCH_SIZE); /* out: */ ctx->tail_call_direct_label = prog - start; @@ -989,25 +1072,6 @@ static void detect_reg_usage(struct bpf_insn *insn, int insn_cnt, } } -static void emit_nops(u8 **pprog, int len) -{ - u8 *prog = *pprog; - int i, noplen; - - while (len > 0) { - noplen = len; - - if (noplen > ASM_NOP_MAX) - noplen = ASM_NOP_MAX; - - for (i = 0; i < noplen; i++) - EMIT1(x86_nops[noplen][i]); - len -= noplen; - } - - *pprog = prog; -} - /* emit the 3-byte VEX prefix * * r: same as rex.r, extra bit for ModRM reg field @@ -2143,7 +2207,7 @@ static void save_args(const struct btf_func_model *m, u8 **prog, } else { /* Only copy the arguments on-stack to current * 'stack_size' and ignore the regs, used to - * prepare the arguments on-stack for orign call. + * prepare the arguments on-stack for origin call. */ if (for_call_origin) { nr_regs += arg_regs; @@ -2198,7 +2262,8 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_link *l, int stack_size, - int run_ctx_off, bool save_ret) + int run_ctx_off, bool save_ret, + void *image, void *rw_image) { u8 *prog = *pprog; u8 *jmp_insn; @@ -2226,7 +2291,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, else EMIT4(0x48, 0x8D, 0x75, -run_ctx_off); - if (emit_rsb_call(&prog, bpf_trampoline_enter(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_enter(p), image + (prog - (u8 *)rw_image))) return -EINVAL; /* remember prog start time returned by __bpf_prog_enter */ emit_mov_reg(&prog, true, BPF_REG_6, BPF_REG_0); @@ -2250,7 +2315,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, (long) p->insnsi >> 32, (u32) (long) p->insnsi); /* call JITed bpf program or interpreter */ - if (emit_rsb_call(&prog, p->bpf_func, prog)) + if (emit_rsb_call(&prog, p->bpf_func, image + (prog - (u8 *)rw_image))) return -EINVAL; /* @@ -2277,7 +2342,7 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog, EMIT3_off32(0x48, 0x8D, 0x95, -run_ctx_off); else EMIT4(0x48, 0x8D, 0x55, -run_ctx_off); - if (emit_rsb_call(&prog, bpf_trampoline_exit(p), prog)) + if (emit_rsb_call(&prog, bpf_trampoline_exit(p), image + (prog - (u8 *)rw_image))) return -EINVAL; *pprog = prog; @@ -2312,14 +2377,15 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond) static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, - int run_ctx_off, bool save_ret) + int run_ctx_off, bool save_ret, + void *image, void *rw_image) { int i; u8 *prog = *pprog; for (i = 0; i < tl->nr_links; i++) { if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, - run_ctx_off, save_ret)) + run_ctx_off, save_ret, image, rw_image)) return -EINVAL; } *pprog = prog; @@ -2328,7 +2394,8 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog, static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, struct bpf_tramp_links *tl, int stack_size, - int run_ctx_off, u8 **branches) + int run_ctx_off, u8 **branches, + void *image, void *rw_image) { u8 *prog = *pprog; int i; @@ -2339,7 +2406,8 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, emit_mov_imm32(&prog, false, BPF_REG_0, 0); emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); for (i = 0; i < tl->nr_links; i++) { - if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true)) + if (invoke_bpf_prog(m, &prog, tl->links[i], stack_size, run_ctx_off, true, + image, rw_image)) return -EINVAL; /* mod_ret prog stored return value into [rbp - 8]. Emit: @@ -2422,10 +2490,11 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog, * add rsp, 8 // skip eth_type_trans's frame * ret // return to its caller */ -int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, - const struct btf_func_model *m, u32 flags, - struct bpf_tramp_links *tlinks, - void *func_addr) +static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_image, + void *rw_image_end, void *image, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, + void *func_addr) { int i, ret, nr_regs = m->nr_args, stack_size = 0; int regs_off, nregs_off, ip_off, run_ctx_off, arg_stack_off, rbx_off; @@ -2437,10 +2506,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i u8 *prog; bool save_ret; + /* + * F_INDIRECT is only compatible with F_RET_FENTRY_RET, it is + * explicitly incompatible with F_CALL_ORIG | F_SKIP_FRAME | F_IP_ARG + * because @func_addr. + */ + WARN_ON_ONCE((flags & BPF_TRAMP_F_INDIRECT) && + (flags & ~(BPF_TRAMP_F_INDIRECT | BPF_TRAMP_F_RET_FENTRY_RET))); + /* extra registers for struct arguments */ - for (i = 0; i < m->nr_args; i++) + for (i = 0; i < m->nr_args; i++) { if (m->arg_flags[i] & BTF_FMODEL_STRUCT_ARG) nr_regs += (m->arg_size[i] + 7) / 8 - 1; + } /* x86-64 supports up to MAX_BPF_FUNC_ARGS arguments. 1-6 * are passed through regs, the remains are through stack. @@ -2521,22 +2599,29 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i orig_call += X86_PATCH_SIZE; } - prog = image; + prog = rw_image; - EMIT_ENDBR(); - /* - * This is the direct-call trampoline, as such it needs accounting - * for the __fentry__ call. - */ - x86_call_depth_emit_accounting(&prog, NULL); + if (flags & BPF_TRAMP_F_INDIRECT) { + /* + * Indirect call for bpf_struct_ops + */ + emit_cfi(&prog, cfi_get_func_hash(func_addr)); + } else { + /* + * Direct-call fentry stub, as such it needs accounting for the + * __fentry__ call. + */ + x86_call_depth_emit_accounting(&prog, NULL); + } EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */ - if (!is_imm8(stack_size)) + if (!is_imm8(stack_size)) { /* sub rsp, stack_size */ EMIT3_off32(0x48, 0x81, 0xEC, stack_size); - else + } else { /* sub rsp, stack_size */ EMIT4(0x48, 0x83, 0xEC, stack_size); + } if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) EMIT1(0x50); /* push rax */ /* mov QWORD PTR [rbp - rbx_off], rbx */ @@ -2563,16 +2648,18 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i if (flags & BPF_TRAMP_F_CALL_ORIG) { /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_rsb_call(&prog, __bpf_tramp_enter, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_enter, + image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } - if (fentry->nr_links) + if (fentry->nr_links) { if (invoke_bpf(m, &prog, fentry, regs_off, run_ctx_off, - flags & BPF_TRAMP_F_RET_FENTRY_RET)) + flags & BPF_TRAMP_F_RET_FENTRY_RET, image, rw_image)) return -EINVAL; + } if (fmod_ret->nr_links) { branches = kcalloc(fmod_ret->nr_links, sizeof(u8 *), @@ -2581,7 +2668,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i return -ENOMEM; if (invoke_bpf_mod_ret(m, &prog, fmod_ret, regs_off, - run_ctx_off, branches)) { + run_ctx_off, branches, image, rw_image)) { ret = -EINVAL; goto cleanup; } @@ -2591,27 +2678,27 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i restore_regs(m, &prog, regs_off); save_args(m, &prog, arg_stack_off, true); - if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { /* Before calling the original function, restore the * tail_call_cnt from stack to rax. */ RESTORE_TAIL_CALL_CNT(stack_size); + } if (flags & BPF_TRAMP_F_ORIG_STACK) { emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, 8); EMIT2(0xff, 0xd3); /* call *rbx */ } else { /* call original function */ - if (emit_rsb_call(&prog, orig_call, prog)) { + if (emit_rsb_call(&prog, orig_call, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } } /* remember return value in a stack for bpf prog to access */ emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8); - im->ip_after_call = prog; - memcpy(prog, x86_nops[5], X86_PATCH_SIZE); - prog += X86_PATCH_SIZE; + im->ip_after_call = image + (prog - (u8 *)rw_image); + emit_nops(&prog, X86_PATCH_SIZE); } if (fmod_ret->nr_links) { @@ -2624,16 +2711,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i /* Update the branches saved in invoke_bpf_mod_ret with the * aligned address of do_fexit. */ - for (i = 0; i < fmod_ret->nr_links; i++) - emit_cond_near_jump(&branches[i], prog, branches[i], - X86_JNE); + for (i = 0; i < fmod_ret->nr_links; i++) { + emit_cond_near_jump(&branches[i], image + (prog - (u8 *)rw_image), + image + (branches[i] - (u8 *)rw_image), X86_JNE); + } } - if (fexit->nr_links) - if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, false)) { + if (fexit->nr_links) { + if (invoke_bpf(m, &prog, fexit, regs_off, run_ctx_off, + false, image, rw_image)) { ret = -EINVAL; goto cleanup; } + } if (flags & BPF_TRAMP_F_RESTORE_REGS) restore_regs(m, &prog, regs_off); @@ -2643,18 +2733,19 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i * restored to R0. */ if (flags & BPF_TRAMP_F_CALL_ORIG) { - im->ip_epilogue = prog; + im->ip_epilogue = image + (prog - (u8 *)rw_image); /* arg1: mov rdi, im */ emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im); - if (emit_rsb_call(&prog, __bpf_tramp_exit, prog)) { + if (emit_rsb_call(&prog, __bpf_tramp_exit, image + (prog - (u8 *)rw_image))) { ret = -EINVAL; goto cleanup; } - } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) + } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) { /* Before running the original function, restore the * tail_call_cnt from stack to rax. */ RESTORE_TAIL_CALL_CNT(stack_size); + } /* restore return value of orig_call or fentry prog back into RAX */ if (save_ret) @@ -2662,22 +2753,94 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i emit_ldx(&prog, BPF_DW, BPF_REG_6, BPF_REG_FP, -rbx_off); EMIT1(0xC9); /* leave */ - if (flags & BPF_TRAMP_F_SKIP_FRAME) + if (flags & BPF_TRAMP_F_SKIP_FRAME) { /* skip our return address and return to parent */ EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */ - emit_return(&prog, prog); + } + emit_return(&prog, image + (prog - (u8 *)rw_image)); /* Make sure the trampoline generation logic doesn't overflow */ - if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) { + if (WARN_ON_ONCE(prog > (u8 *)rw_image_end - BPF_INSN_SAFETY)) { ret = -EFAULT; goto cleanup; } - ret = prog - (u8 *)image; + ret = prog - (u8 *)rw_image + BPF_INSN_SAFETY; cleanup: kfree(branches); return ret; } +void *arch_alloc_bpf_trampoline(unsigned int size) +{ + return bpf_prog_pack_alloc(size, jit_fill_hole); +} + +void arch_free_bpf_trampoline(void *image, unsigned int size) +{ + bpf_prog_pack_free(image, size); +} + +void arch_protect_bpf_trampoline(void *image, unsigned int size) +{ +} + +void arch_unprotect_bpf_trampoline(void *image, unsigned int size) +{ +} + +int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end, + const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, + void *func_addr) +{ + void *rw_image, *tmp; + int ret; + u32 size = image_end - image; + + /* rw_image doesn't need to be in module memory range, so we can + * use kvmalloc. + */ + rw_image = kvmalloc(size, GFP_KERNEL); + if (!rw_image) + return -ENOMEM; + + ret = __arch_prepare_bpf_trampoline(im, rw_image, rw_image + size, image, m, + flags, tlinks, func_addr); + if (ret < 0) + goto out; + + tmp = bpf_arch_text_copy(image, rw_image, size); + if (IS_ERR(tmp)) + ret = PTR_ERR(tmp); +out: + kvfree(rw_image); + return ret; +} + +int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags, + struct bpf_tramp_links *tlinks, void *func_addr) +{ + struct bpf_tramp_image im; + void *image; + int ret; + + /* Allocate a temporary buffer for __arch_prepare_bpf_trampoline(). + * This will NOT cause fragmentation in direct map, as we do not + * call set_memory_*() on this buffer. + * + * We cannot use kvmalloc here, because we need image to be in + * module memory range. + */ + image = bpf_jit_alloc_exec(PAGE_SIZE); + if (!image) + return -ENOMEM; + + ret = __arch_prepare_bpf_trampoline(&im, image, image + PAGE_SIZE, image, + m, flags, tlinks, func_addr); + bpf_jit_free_exec(image); + return ret; +} + static int emit_bpf_dispatcher(u8 **pprog, int a, int b, s64 *progs, u8 *image, u8 *buf) { u8 *jg_reloc, *prog = *pprog; @@ -2935,9 +3098,16 @@ out_image: jit_data->header = header; jit_data->rw_header = rw_header; } - prog->bpf_func = (void *)image; + /* + * ctx.prog_offset is used when CFI preambles put code *before* + * the function. See emit_cfi(). For FineIBT specifically this code + * can also be executed and bpf_prog_kallsyms_add() will + * generate an additional symbol to cover this, hence also + * decrement proglen. + */ + prog->bpf_func = (void *)image + cfi_get_offset(); prog->jited = 1; - prog->jited_len = proglen; + prog->jited_len = proglen - cfi_get_offset(); } else { prog = orig_prog; } @@ -2992,6 +3162,7 @@ void bpf_jit_free(struct bpf_prog *prog) kvfree(jit_data->addrs); kfree(jit_data); } + prog->bpf_func = (void *)prog->bpf_func - cfi_get_offset(); hdr = bpf_jit_binary_pack_hdr(prog); bpf_jit_binary_pack_free(hdr, NULL); WARN_ON_ONCE(!bpf_prog_kallsyms_verify_off(prog)); @@ -3025,3 +3196,49 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp #endif WARN(1, "verification of programs using bpf_throw should have failed\n"); } + +void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke, + struct bpf_prog *new, struct bpf_prog *old) +{ + u8 *old_addr, *new_addr, *old_bypass_addr; + int ret; + + old_bypass_addr = old ? NULL : poke->bypass_addr; + old_addr = old ? (u8 *)old->bpf_func + poke->adj_off : NULL; + new_addr = new ? (u8 *)new->bpf_func + poke->adj_off : NULL; + + /* + * On program loading or teardown, the program's kallsym entry + * might not be in place, so we use __bpf_arch_text_poke to skip + * the kallsyms check. + */ + if (new) { + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, new_addr); + BUG_ON(ret < 0); + if (!old) { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + poke->bypass_addr, + NULL); + BUG_ON(ret < 0); + } + } else { + ret = __bpf_arch_text_poke(poke->tailcall_bypass, + BPF_MOD_JUMP, + old_bypass_addr, + poke->bypass_addr); + BUG_ON(ret < 0); + /* let other CPUs finish the execution of program + * so that it will not possible to expose them + * to invalid nop, stack unwind, nop state + */ + if (!ret) + synchronize_rcu(); + ret = __bpf_arch_text_poke(poke->tailcall_target, + BPF_MOD_JUMP, + old_addr, NULL); + BUG_ON(ret < 0); + } +} diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 429a89c5468b..b18ce19981ec 100644 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@ -1194,7 +1194,7 @@ struct jit_context { #define PROLOGUE_SIZE 35 /* - * Emit prologue code for BPF program and check it's size. + * Emit prologue code for BPF program and check its size. * bpf_tail_call helper will skip it while jumping into another program. */ static void emit_prologue(u8 **pprog, u32 stack_depth) diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 7368afc03998..8c8ddc4dcc08 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -14,6 +14,7 @@ #include <linux/dma-map-ops.h> #include <linux/swiotlb.h> #include <asm/iommu.h> +#include <asm/sta2x11.h> #define STA2X11_SWIOTLB_SIZE (4*1024*1024) diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c index 761f3689f60a..84ba715f44d1 100644 --- a/arch/x86/platform/intel-quark/imr_selftest.c +++ b/arch/x86/platform/intel-quark/imr_selftest.c @@ -6,7 +6,7 @@ * Copyright(c) 2015 Bryan O'Donoghue <pure.logic@nexus-software.ie> * * IMR self test. The purpose of this module is to run a set of tests on the - * IMR API to validate it's sanity. We check for overlapping, reserved + * IMR API to validate its sanity. We check for overlapping, reserved * addresses and setup/teardown sanity. * */ diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index c4365a05ab83..f7235ef87bc3 100644 --- a/arch/x86/platform/pvh/head.S +++ b/arch/x86/platform/pvh/head.S @@ -11,6 +11,7 @@ #include <linux/elfnote.h> #include <linux/init.h> #include <linux/linkage.h> +#include <asm/desc_defs.h> #include <asm/segment.h> #include <asm/asm.h> #include <asm/boot.h> @@ -41,7 +42,7 @@ * Bit 8 (TF) must be cleared. Other bits are all unspecified. * * All other processor registers and flag bits are unspecified. The OS is in - * charge of setting up it's own stack, GDT and IDT. + * charge of setting up its own stack, GDT and IDT. */ #define PVH_GDT_ENTRY_CS 1 @@ -148,11 +149,11 @@ SYM_DATA_END(gdt) SYM_DATA_START_LOCAL(gdt_start) .quad 0x0000000000000000 /* NULL descriptor */ #ifdef CONFIG_X86_64 - .quad GDT_ENTRY(0xa09a, 0, 0xfffff) /* PVH_CS_SEL */ + .quad GDT_ENTRY(DESC_CODE64, 0, 0xfffff) /* PVH_CS_SEL */ #else - .quad GDT_ENTRY(0xc09a, 0, 0xfffff) /* PVH_CS_SEL */ + .quad GDT_ENTRY(DESC_CODE32, 0, 0xfffff) /* PVH_CS_SEL */ #endif - .quad GDT_ENTRY(0xc092, 0, 0xfffff) /* PVH_DS_SEL */ + .quad GDT_ENTRY(DESC_DATA32, 0, 0xfffff) /* PVH_DS_SEL */ SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end) .balign 16 diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index 4221259a5870..a379501b7a69 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -35,7 +35,7 @@ static void uv_program_mmr(struct irq_cfg *cfg, struct uv_irq_2_mmr_pnode *info) mmr_value = 0; entry = (struct uv_IO_APIC_route_entry *)&mmr_value; entry->vector = cfg->vector; - entry->delivery_mode = apic->delivery_mode; + entry->delivery_mode = APIC_DELIVERY_MODE_FIXED; entry->dest_mode = apic->dest_mode_logical; entry->polarity = 0; entry->trigger = 0; diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index e03207de2880..5c50e550ab63 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -741,7 +741,7 @@ static void uv_nmi_dump_state_cpu(int cpu, struct pt_regs *regs) this_cpu_write(uv_cpu_nmi.state, UV_NMI_STATE_DUMP_DONE); } -/* Trigger a slave CPU to dump it's state */ +/* Trigger a slave CPU to dump its state */ static void uv_nmi_trigger_dump(int cpu) { int retry = uv_nmi_trigger_delay; diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c index ff5afc8a5a41..3712afc3534d 100644 --- a/arch/x86/platform/uv/uv_time.c +++ b/arch/x86/platform/uv/uv_time.c @@ -270,7 +270,7 @@ static int uv_rtc_unset_timer(int cpu, int force) * Read the RTC. * * Starting with HUB rev 2.0, the UV RTC register is replicated across all - * cachelines of it's own page. This allows faster simultaneous reads + * cachelines of its own page. This allows faster simultaneous reads * from a given socket. */ static u64 uv_read_rtc(struct clocksource *cs) diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 788e5559549f..f9bc444a3064 100644 --- a/arch/x86/realmode/init.c +++ b/arch/x86/realmode/init.c @@ -61,7 +61,7 @@ void __init reserve_real_mode(void) set_real_mode_mem(mem); /* - * Unconditionally reserve the entire fisrt 1M, see comment in + * Unconditionally reserve the entire first 1M, see comment in * setup_arch(). */ memblock_reserve(0, SZ_1M); diff --git a/arch/x86/realmode/rm/reboot.S b/arch/x86/realmode/rm/reboot.S index f10515b10e0a..e714b4624e36 100644 --- a/arch/x86/realmode/rm/reboot.S +++ b/arch/x86/realmode/rm/reboot.S @@ -1,5 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/linkage.h> +#include <asm/desc_defs.h> #include <asm/segment.h> #include <asm/page_types.h> #include <asm/processor-flags.h> @@ -153,5 +154,5 @@ SYM_DATA_START(machine_real_restart_gdt) * base value 0x100; since this is consistent with real mode * semantics we don't have to reload the segments once CR0.PE = 0. */ - .quad GDT_ENTRY(0x0093, 0x100, 0xffff) + .quad GDT_ENTRY(DESC_DATA16, 0x100, 0xffff) SYM_DATA_END(machine_real_restart_gdt) diff --git a/arch/x86/tools/Makefile b/arch/x86/tools/Makefile index 90e820ac9771..7278e2545c35 100644 --- a/arch/x86/tools/Makefile +++ b/arch/x86/tools/Makefile @@ -17,7 +17,7 @@ reformatter = $(srctree)/arch/x86/tools/objdump_reformat.awk chkobjdump = $(srctree)/arch/x86/tools/chkobjdump.awk quiet_cmd_posttest = TEST $@ - cmd_posttest = ($(OBJDUMP) -v | $(AWK) -f $(chkobjdump)) || $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose) + cmd_posttest = $(OBJDUMP) -d -j .text $(objtree)/vmlinux | $(AWK) -f $(reformatter) | $(obj)/insn_decoder_test $(posttest_64bit) $(posttest_verbose) quiet_cmd_sanitytest = TEST $@ cmd_sanitytest = $(obj)/insn_sanity $(posttest_64bit) -m 1000000 diff --git a/arch/x86/tools/chkobjdump.awk b/arch/x86/tools/chkobjdump.awk deleted file mode 100644 index a4cf678cf5c8..000000000000 --- a/arch/x86/tools/chkobjdump.awk +++ /dev/null @@ -1,34 +0,0 @@ -# GNU objdump version checker -# -# Usage: -# objdump -v | awk -f chkobjdump.awk -BEGIN { - # objdump version 2.19 or later is OK for the test. - od_ver = 2; - od_sver = 19; -} - -/^GNU objdump/ { - verstr = "" - gsub(/\(.*\)/, ""); - for (i = 3; i <= NF; i++) - if (match($(i), "^[0-9]")) { - verstr = $(i); - break; - } - if (verstr == "") { - printf("Warning: Failed to find objdump version number.\n"); - exit 0; - } - split(verstr, ver, "."); - if (ver[1] > od_ver || - (ver[1] == od_ver && ver[2] >= od_sver)) { - exit 1; - } else { - printf("Warning: objdump version %s is older than %d.%d\n", - verstr, od_ver, od_sver); - print("Warning: Skipping posttest."); - # Logic is inverted, because we just skip test without error. - exit 0; - } -} diff --git a/arch/x86/tools/objdump_reformat.awk b/arch/x86/tools/objdump_reformat.awk index f418c91b71f0..20b08a6c4d33 100644 --- a/arch/x86/tools/objdump_reformat.awk +++ b/arch/x86/tools/objdump_reformat.awk @@ -11,8 +11,8 @@ BEGIN { prev_addr = "" prev_hex = "" prev_mnemonic = "" - bad_expr = "(\\(bad\\)|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))" - fwait_expr = "^9b " + bad_expr = "(\\(bad\\)|<unknown>|^rex|^.byte|^rep(z|nz)$|^lock$|^es$|^cs$|^ss$|^ds$|^fs$|^gs$|^data(16|32)$|^addr(16|32|64))" + fwait_expr = "^9b[ \t]*fwait" fwait_str="9b\tfwait" } @@ -22,7 +22,7 @@ BEGIN { } /^ *[0-9a-f]+:/ { - if (split($0, field, "\t") < 3) { + if (split($0, field, /: |\t/) < 3) { # This is a continuation of the same insn. prev_hex = prev_hex field[2] } else { diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c index d30949e25ebd..a3bae2b24626 100644 --- a/arch/x86/tools/relocs.c +++ b/arch/x86/tools/relocs.c @@ -66,7 +66,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = { [S_REL] = "^(__init_(begin|end)|" "__x86_cpu_dev_(start|end)|" - "(__parainstructions|__alt_instructions)(_end)?|" + "__alt_instructions(_end)?|" "(__iommu_table|__apicdrivers|__smp_locks)(_end)?|" "__(start|end)_pci_.*|" #if CONFIG_FW_LOADER diff --git a/arch/x86/um/asm/elf.h b/arch/x86/um/asm/elf.h index 6523eb7c3bd1..6052200fe925 100644 --- a/arch/x86/um/asm/elf.h +++ b/arch/x86/um/asm/elf.h @@ -168,8 +168,8 @@ do { \ (pr_reg)[18] = (_regs)->regs.gp[18]; \ (pr_reg)[19] = (_regs)->regs.gp[19]; \ (pr_reg)[20] = (_regs)->regs.gp[20]; \ - (pr_reg)[21] = current->thread.arch.fs; \ - (pr_reg)[22] = 0; \ + (pr_reg)[21] = (_regs)->regs.gp[21]; \ + (pr_reg)[22] = (_regs)->regs.gp[22]; \ (pr_reg)[23] = 0; \ (pr_reg)[24] = 0; \ (pr_reg)[25] = 0; \ diff --git a/arch/x86/um/asm/processor_64.h b/arch/x86/um/asm/processor_64.h index 1ef9c21877bc..f90159508936 100644 --- a/arch/x86/um/asm/processor_64.h +++ b/arch/x86/um/asm/processor_64.h @@ -10,13 +10,11 @@ struct arch_thread { unsigned long debugregs[8]; int debugregs_seq; - unsigned long fs; struct faultinfo faultinfo; }; #define INIT_ARCH_THREAD { .debugregs = { [ 0 ... 7 ] = 0 }, \ .debugregs_seq = 0, \ - .fs = 0, \ .faultinfo = { 0, 0, 0 } } #define STACKSLOTS_PER_LINE 4 @@ -28,7 +26,6 @@ static inline void arch_flush_thread(struct arch_thread *thread) static inline void arch_copy_thread(struct arch_thread *from, struct arch_thread *to) { - to->fs = from->fs; } #define current_sp() ({ void *sp; __asm__("movq %%rsp, %0" : "=r" (sp) : ); sp; }) diff --git a/arch/x86/um/os-Linux/Makefile b/arch/x86/um/os-Linux/Makefile index ae169125d03f..5249bbc30dcd 100644 --- a/arch/x86/um/os-Linux/Makefile +++ b/arch/x86/um/os-Linux/Makefile @@ -6,7 +6,6 @@ obj-y = registers.o task_size.o mcontext.o obj-$(CONFIG_X86_32) += tls.o -obj-$(CONFIG_64BIT) += prctl.o USER_OBJS := $(obj-y) diff --git a/arch/x86/um/os-Linux/prctl.c b/arch/x86/um/os-Linux/prctl.c deleted file mode 100644 index 8431e87ac333..000000000000 --- a/arch/x86/um/os-Linux/prctl.c +++ /dev/null @@ -1,12 +0,0 @@ -/* - * Copyright (C) 2007 Jeff Dike (jdike@{addtoit.com,linux.intel.com}) - * Licensed under the GPL - */ - -#include <sys/ptrace.h> -#include <asm/ptrace.h> - -int os_arch_prctl(int pid, int option, unsigned long *arg2) -{ - return ptrace(PTRACE_ARCH_PRCTL, pid, (unsigned long) arg2, option); -} diff --git a/arch/x86/um/ptrace_32.c b/arch/x86/um/ptrace_32.c index 0bc4b73a9cde..7f1abde2c84b 100644 --- a/arch/x86/um/ptrace_32.c +++ b/arch/x86/um/ptrace_32.c @@ -25,30 +25,6 @@ void arch_switch_to(struct task_struct *to) printk(KERN_WARNING "arch_switch_tls failed, errno = EINVAL\n"); } -int is_syscall(unsigned long addr) -{ - unsigned short instr; - int n; - - n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); - if (n) { - /* access_process_vm() grants access to vsyscall and stub, - * while copy_from_user doesn't. Maybe access_process_vm is - * slow, but that doesn't matter, since it will be called only - * in case of singlestepping, if copy_from_user failed. - */ - n = access_process_vm(current, addr, &instr, sizeof(instr), - FOLL_FORCE); - if (n != sizeof(instr)) { - printk(KERN_ERR "is_syscall : failed to read " - "instruction from 0x%lx\n", addr); - return 1; - } - } - /* int 0x80 or sysenter */ - return (instr == 0x80cd) || (instr == 0x340f); -} - /* determines which flags the user has access to. */ /* 1 = access 0 = no access */ #define FLAG_MASK 0x00044dd5 diff --git a/arch/x86/um/ptrace_64.c b/arch/x86/um/ptrace_64.c index 289d0159b041..aa68d83d3f44 100644 --- a/arch/x86/um/ptrace_64.c +++ b/arch/x86/um/ptrace_64.c @@ -188,32 +188,6 @@ int peek_user(struct task_struct *child, long addr, long data) return put_user(tmp, (unsigned long *) data); } -/* XXX Mostly copied from sys-i386 */ -int is_syscall(unsigned long addr) -{ - unsigned short instr; - int n; - - n = copy_from_user(&instr, (void __user *) addr, sizeof(instr)); - if (n) { - /* - * access_process_vm() grants access to vsyscall and stub, - * while copy_from_user doesn't. Maybe access_process_vm is - * slow, but that doesn't matter, since it will be called only - * in case of singlestepping, if copy_from_user failed. - */ - n = access_process_vm(current, addr, &instr, sizeof(instr), - FOLL_FORCE); - if (n != sizeof(instr)) { - printk("is_syscall : failed to read instruction from " - "0x%lx\n", addr); - return 1; - } - } - /* sysenter */ - return instr == 0x050f; -} - static int get_fpregs(struct user_i387_struct __user *buf, struct task_struct *child) { int err, n, cpu = ((struct thread_info *) child->stack)->cpu; diff --git a/arch/x86/um/shared/sysdep/ptrace_32.h b/arch/x86/um/shared/sysdep/ptrace_32.h index db8478a83a09..0c4989842fbe 100644 --- a/arch/x86/um/shared/sysdep/ptrace_32.h +++ b/arch/x86/um/shared/sysdep/ptrace_32.h @@ -8,10 +8,6 @@ #define MAX_FP_NR HOST_FPX_SIZE -void set_using_sysemu(int value); -int get_using_sysemu(void); -extern int sysemu_supported; - #define UPT_SYSCALL_ARG1(r) UPT_BX(r) #define UPT_SYSCALL_ARG2(r) UPT_CX(r) #define UPT_SYSCALL_ARG3(r) UPT_DX(r) diff --git a/arch/x86/um/shared/sysdep/ptrace_user.h b/arch/x86/um/shared/sysdep/ptrace_user.h index 44782bbad41e..1d1a824fa652 100644 --- a/arch/x86/um/shared/sysdep/ptrace_user.h +++ b/arch/x86/um/shared/sysdep/ptrace_user.h @@ -15,14 +15,12 @@ #define FP_SIZE ((HOST_FPX_SIZE > HOST_FP_SIZE) ? HOST_FPX_SIZE : HOST_FP_SIZE) #else #define FP_SIZE HOST_FP_SIZE +#endif /* - * x86_64 FC3 doesn't define this in /usr/include/linux/ptrace.h even though - * it's defined in the kernel's include/linux/ptrace.h. Additionally, use the - * 2.4 name and value for 2.4 host compatibility. + * glibc before 2.27 does not include PTRACE_SYSEMU_SINGLESTEP in its enum, + * ensure we have a definition by (re-)defining it here. */ -#ifndef PTRACE_OLDSETOPTIONS -#define PTRACE_OLDSETOPTIONS 21 -#endif - +#ifndef PTRACE_SYSEMU_SINGLESTEP +#define PTRACE_SYSEMU_SINGLESTEP 32 #endif diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h index 38fa894b65d0..ea8b5a2d67af 100644 --- a/arch/x86/um/shared/sysdep/stub_32.h +++ b/arch/x86/um/shared/sysdep/stub_32.h @@ -12,72 +12,79 @@ #define STUB_MMAP_NR __NR_mmap2 #define MMAP_OFFSET(o) ((o) >> UM_KERN_PAGE_SHIFT) -static inline long stub_syscall0(long syscall) +static __always_inline long stub_syscall0(long syscall) { long ret; - __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall)); + __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall) + : "memory"); return ret; } -static inline long stub_syscall1(long syscall, long arg1) +static __always_inline long stub_syscall1(long syscall, long arg1) { long ret; - __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1)); + __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1) + : "memory"); return ret; } -static inline long stub_syscall2(long syscall, long arg1, long arg2) +static __always_inline long stub_syscall2(long syscall, long arg1, long arg2) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2)); + "c" (arg2) + : "memory"); return ret; } -static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3) +static __always_inline long stub_syscall3(long syscall, long arg1, long arg2, + long arg3) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2), "d" (arg3)); + "c" (arg2), "d" (arg3) + : "memory"); return ret; } -static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, - long arg4) +static __always_inline long stub_syscall4(long syscall, long arg1, long arg2, + long arg3, long arg4) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2), "d" (arg3), "S" (arg4)); + "c" (arg2), "d" (arg3), "S" (arg4) + : "memory"); return ret; } -static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3, - long arg4, long arg5) +static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5) { long ret; __asm__ volatile ("int $0x80" : "=a" (ret) : "0" (syscall), "b" (arg1), - "c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5)); + "c" (arg2), "d" (arg3), "S" (arg4), "D" (arg5) + : "memory"); return ret; } -static inline void trap_myself(void) +static __always_inline void trap_myself(void) { __asm("int3"); } -static inline void remap_stack_and_trap(void) +static __always_inline void remap_stack_and_trap(void) { __asm__ volatile ( "movl %%esp,%%ebx ;" diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h index 2de1c8f88173..b24168ef0ac4 100644 --- a/arch/x86/um/shared/sysdep/stub_64.h +++ b/arch/x86/um/shared/sysdep/stub_64.h @@ -16,7 +16,7 @@ #define __syscall_clobber "r11","rcx","memory" #define __syscall "syscall" -static inline long stub_syscall0(long syscall) +static __always_inline long stub_syscall0(long syscall) { long ret; @@ -27,7 +27,7 @@ static inline long stub_syscall0(long syscall) return ret; } -static inline long stub_syscall2(long syscall, long arg1, long arg2) +static __always_inline long stub_syscall2(long syscall, long arg1, long arg2) { long ret; @@ -38,7 +38,8 @@ static inline long stub_syscall2(long syscall, long arg1, long arg2) return ret; } -static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3) +static __always_inline long stub_syscall3(long syscall, long arg1, long arg2, + long arg3) { long ret; @@ -50,7 +51,7 @@ static inline long stub_syscall3(long syscall, long arg1, long arg2, long arg3) return ret; } -static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, +static __always_inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, long arg4) { long ret; @@ -64,8 +65,8 @@ static inline long stub_syscall4(long syscall, long arg1, long arg2, long arg3, return ret; } -static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3, - long arg4, long arg5) +static __always_inline long stub_syscall5(long syscall, long arg1, long arg2, + long arg3, long arg4, long arg5) { long ret; @@ -78,12 +79,12 @@ static inline long stub_syscall5(long syscall, long arg1, long arg2, long arg3, return ret; } -static inline void trap_myself(void) +static __always_inline void trap_myself(void) { __asm("int3"); } -static inline void remap_stack_and_trap(void) +static __always_inline void remap_stack_and_trap(void) { __asm__ volatile ( "movq %0,%%rax ;" diff --git a/arch/x86/um/syscalls_64.c b/arch/x86/um/syscalls_64.c index 27b29ae6c471..6a00a28c9cca 100644 --- a/arch/x86/um/syscalls_64.c +++ b/arch/x86/um/syscalls_64.c @@ -16,60 +16,24 @@ long arch_prctl(struct task_struct *task, int option, unsigned long __user *arg2) { - unsigned long *ptr = arg2, tmp; - long ret; - int pid = task->mm->context.id.u.pid; - - /* - * With ARCH_SET_FS (and ARCH_SET_GS is treated similarly to - * be safe), we need to call arch_prctl on the host because - * setting %fs may result in something else happening (like a - * GDT or thread.fs being set instead). So, we let the host - * fiddle the registers and thread struct and restore the - * registers afterwards. - * - * So, the saved registers are stored to the process (this - * needed because a stub may have been the last thing to run), - * arch_prctl is run on the host, then the registers are read - * back. - */ - switch (option) { - case ARCH_SET_FS: - case ARCH_SET_GS: - ret = restore_pid_registers(pid, ¤t->thread.regs.regs); - if (ret) - return ret; - break; - case ARCH_GET_FS: - case ARCH_GET_GS: - /* - * With these two, we read to a local pointer and - * put_user it to the userspace pointer that we were - * given. If addr isn't valid (because it hasn't been - * faulted in or is just bogus), we want put_user to - * fault it in (or return -EFAULT) instead of having - * the host return -EFAULT. - */ - ptr = &tmp; - } - - ret = os_arch_prctl(pid, option, ptr); - if (ret) - return ret; + long ret = -EINVAL; switch (option) { case ARCH_SET_FS: - current->thread.arch.fs = (unsigned long) ptr; - ret = save_registers(pid, ¤t->thread.regs.regs); + current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] = + (unsigned long) arg2; + ret = 0; break; case ARCH_SET_GS: - ret = save_registers(pid, ¤t->thread.regs.regs); + current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)] = + (unsigned long) arg2; + ret = 0; break; case ARCH_GET_FS: - ret = put_user(tmp, arg2); + ret = put_user(current->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)], arg2); break; case ARCH_GET_GS: - ret = put_user(tmp, arg2); + ret = put_user(current->thread.regs.regs.gp[GS_BASE / sizeof(unsigned long)], arg2); break; } @@ -83,10 +47,10 @@ SYSCALL_DEFINE2(arch_prctl, int, option, unsigned long, arg2) void arch_switch_to(struct task_struct *to) { - if ((to->thread.arch.fs == 0) || (to->mm == NULL)) - return; - - arch_prctl(to, ARCH_SET_FS, (void __user *) to->thread.arch.fs); + /* + * Nothing needs to be done on x86_64. + * The FS_BASE/GS_BASE registers are saved in the ptrace register set. + */ } SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, diff --git a/arch/x86/um/sysrq_64.c b/arch/x86/um/sysrq_64.c index ef1eb4f4f612..0bf6de40abff 100644 --- a/arch/x86/um/sysrq_64.c +++ b/arch/x86/um/sysrq_64.c @@ -6,6 +6,7 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/pid.h> #include <linux/sched.h> #include <linux/sched/debug.h> #include <linux/utsname.h> diff --git a/arch/x86/um/tls_64.c b/arch/x86/um/tls_64.c index ebd3855d9b13..c51a613f6f5c 100644 --- a/arch/x86/um/tls_64.c +++ b/arch/x86/um/tls_64.c @@ -12,7 +12,7 @@ int arch_set_tls(struct task_struct *t, unsigned long tls) * If CLONE_SETTLS is set, we need to save the thread id * so it can be set during context switches. */ - t->thread.arch.fs = tls; + t->thread.regs.regs.gp[FS_BASE / sizeof(unsigned long)] = tls; return 0; } diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig index 9b1ec5d8c99c..a65fc2ae15b4 100644 --- a/arch/x86/xen/Kconfig +++ b/arch/x86/xen/Kconfig @@ -9,6 +9,7 @@ config XEN select PARAVIRT_CLOCK select X86_HV_CALLBACK_VECTOR depends on X86_64 || (X86_32 && X86_PAE) + depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8) depends on X86_LOCAL_APIC && X86_TSC help This is the Linux Xen port. Enabling this will allow the diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 0337392a3121..3c61bb98c10e 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -33,9 +33,12 @@ EXPORT_SYMBOL_GPL(hypercall_page); * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info * but during boot it is switched to point to xen_vcpu_info. * The pointer is used in xen_evtchn_do_upcall to acknowledge pending events. + * Make sure that xen_vcpu_info doesn't cross a page boundary by making it + * cache-line aligned (the struct is guaranteed to have a size of 64 bytes, + * which matches the cache line size of 64-bit x86 processors). */ DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu); -DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info); +DEFINE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info); /* Linux <-> Xen vCPU id mapping */ DEFINE_PER_CPU(uint32_t, xen_vcpu_id); @@ -160,6 +163,7 @@ void xen_vcpu_setup(int cpu) int err; struct vcpu_info *vcpup; + BUILD_BUG_ON(sizeof(*vcpup) > SMP_CACHE_BYTES); BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info); /* diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index bbbfdd495ebd..aeb33e0a3f76 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -704,7 +704,7 @@ static struct trap_array_entry trap_array[] = { TRAP_ENTRY(exc_int3, false ), TRAP_ENTRY(exc_overflow, false ), #ifdef CONFIG_IA32_EMULATION - { entry_INT80_compat, xen_entry_INT80_compat, false }, + TRAP_ENTRY(int80_emulation, false ), #endif TRAP_ENTRY(exc_page_fault, false ), TRAP_ENTRY(exc_divide_error, false ), diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 6092fea7d651..39982f955cfe 100644 --- a/arch/x86/xen/irq.c +++ b/arch/x86/xen/irq.c @@ -45,7 +45,7 @@ static const typeof(pv_ops) xen_irq_ops __initconst = { /* Initial interrupt flag handling only called while interrupts off. */ .save_fl = __PV_IS_CALLEE_SAVE(paravirt_ret0), .irq_disable = __PV_IS_CALLEE_SAVE(paravirt_nop), - .irq_enable = __PV_IS_CALLEE_SAVE(paravirt_BUG), + .irq_enable = __PV_IS_CALLEE_SAVE(BUG_func), .safe_halt = xen_safe_halt, .halt = xen_halt, diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index b6830554ff69..72af496a160c 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -34,7 +34,7 @@ * would need to validate the whole pagetable before going on. * Naturally, this is quite slow. The solution is to "pin" a * pagetable, which enforces all the constraints on the pagetable even - * when it is not actively in use. This menas that Xen can be assured + * when it is not actively in use. This means that Xen can be assured * that it is still valid when you do load it into %cr3, and doesn't * need to revalidate it. * diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S index 9e5e68008785..1a9cd18dfbd3 100644 --- a/arch/x86/xen/xen-asm.S +++ b/arch/x86/xen/xen-asm.S @@ -156,7 +156,7 @@ xen_pv_trap asm_xenpv_exc_machine_check #endif /* CONFIG_X86_MCE */ xen_pv_trap asm_exc_simd_coprocessor_error #ifdef CONFIG_IA32_EMULATION -xen_pv_trap entry_INT80_compat +xen_pv_trap asm_int80_emulation #endif xen_pv_trap asm_exc_xen_unknown_trap xen_pv_trap asm_exc_xen_hypervisor_callback diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 408a2aa66c69..a87ab36889e7 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -21,7 +21,7 @@ extern void *xen_initial_gdt; struct trap_info; void xen_copy_trap_info(struct trap_info *traps); -DECLARE_PER_CPU(struct vcpu_info, xen_vcpu_info); +DECLARE_PER_CPU_ALIGNED(struct vcpu_info, xen_vcpu_info); DECLARE_PER_CPU(unsigned long, xen_cr3); DECLARE_PER_CPU(unsigned long, xen_current_cr3); |