diff options
Diffstat (limited to 'arch/x86')
279 files changed, 6752 insertions, 3405 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 9241274858..6f49999a6b 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -59,8 +59,10 @@ config X86 # select ACPI_LEGACY_TABLES_LOOKUP if ACPI select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI + select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT + select ARCH_CONFIGURES_CPU_MITIGATIONS select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 @@ -71,6 +73,7 @@ config X86 select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION select ARCH_HAS_CPU_FINALIZE_INIT + select ARCH_HAS_CPU_PASID if IOMMU_SVA select ARCH_HAS_CURRENT_STACK_POINTER select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE @@ -88,6 +91,7 @@ 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 @@ -147,6 +151,7 @@ config X86 select GENERIC_CLOCKEVENTS_MIN_ADJUST select GENERIC_CMOS_UPDATE select GENERIC_CPU_AUTOPROBE + select GENERIC_CPU_DEVICES select GENERIC_CPU_VULNERABILITIES select GENERIC_EARLY_IOREMAP select GENERIC_ENTRY @@ -169,7 +174,7 @@ 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 +389,6 @@ 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 +1416,7 @@ 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 +1473,7 @@ 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 @@ -1957,6 +1958,11 @@ config INTEL_TDX_HOST depends on CPU_SUP_INTEL depends on X86_64 depends on KVM_INTEL + depends on X86_X2APIC + select ARCH_KEEP_MEMBLOCK + depends on CONTIG_ALLOC + depends on !KEXEC_CORE + depends on X86_MCE help Intel Trust Domain Extensions (TDX) protects guest VMs from malicious host and certain physical attacks. This option enables necessary TDX @@ -2462,17 +2468,17 @@ config PREFIX_SYMBOLS def_bool y depends on CALL_PADDING && !CFI_CLANG -menuconfig SPECULATION_MITIGATIONS - bool "Mitigations for speculative execution vulnerabilities" +menuconfig CPU_MITIGATIONS + bool "Mitigations for CPU vulnerabilities" default y help - Say Y here to enable options which enable mitigations for - speculative execution hardware vulnerabilities. + Say Y here to enable options which enable mitigations for hardware + vulnerabilities (usually related to speculative execution). If you say N, all mitigations will be disabled. You really should know what you are doing to say so. -if SPECULATION_MITIGATIONS +if CPU_MITIGATIONS config PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" @@ -2607,6 +2613,16 @@ config MITIGATION_RFDS stored in floating point, vector and integer registers. See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> +config MITIGATION_SPECTRE_BHI + bool "Mitigate Spectre-BHB (Branch History Injection)" + depends on CPU_SUP_INTEL + default y + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See <file:Documentation/admin-guide/hw-vuln/spectre.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu index 87396575cf..2a7279d804 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/Makefile b/arch/x86/Makefile index 1a068de12a..da8f3caf27 100644 --- a/arch/x86/Makefile +++ b/arch/x86/Makefile @@ -112,13 +112,13 @@ ifeq ($(CONFIG_X86_32),y) # temporary until string.h is fixed KBUILD_CFLAGS += -ffreestanding - ifeq ($(CONFIG_STACKPROTECTOR),y) - ifeq ($(CONFIG_SMP),y) + ifeq ($(CONFIG_STACKPROTECTOR),y) + ifeq ($(CONFIG_SMP),y) KBUILD_CFLAGS += -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - else + else KBUILD_CFLAGS += -mstack-protector-guard=global - endif - endif + endif + endif else BITS := 64 UTS_MACHINE := x86_64 diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile index 71fc531b95..e9522c6893 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/ @@ -84,7 +84,7 @@ LDFLAGS_vmlinux += -T hostprogs := mkpiggy HOST_EXTRACFLAGS += -I$(srctree)/tools/include -sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' +sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p' quiet_cmd_voffset = VOFFSET $@ cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@ diff --git a/arch/x86/boot/compressed/mem.c b/arch/x86/boot/compressed/mem.c index b3c3a4be74..dbba332e4a 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.c b/arch/x86/boot/compressed/misc.c index b99e08e681..ee0fac468e 100644 --- a/arch/x86/boot/compressed/misc.c +++ b/arch/x86/boot/compressed/misc.c @@ -330,6 +330,7 @@ static size_t parse_elf(void *output) return ehdr.e_entry - LOAD_PHYSICAL_ADDR; } +const unsigned long kernel_text_size = VO___start_rodata - VO__text; const unsigned long kernel_total_size = VO__end - VO__text; static u8 boot_heap[BOOT_HEAP_SIZE] __aligned(4); @@ -358,6 +359,19 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, } /* + * Set the memory encryption xloadflag based on the mem_encrypt= command line + * parameter, if provided. + */ +static void parse_mem_encrypt(struct setup_header *hdr) +{ + int on = cmdline_find_option_bool("mem_encrypt=on"); + int off = cmdline_find_option_bool("mem_encrypt=off"); + + if (on > off) + hdr->xloadflags |= XLF_MEM_ENCRYPTION; +} + +/* * The compressed kernel image (ZO), has been moved so that its position * is against the end of the buffer used to hold the uncompressed kernel * image (VO) and the execution environment (.bss, .brk), which makes sure @@ -387,6 +401,8 @@ asmlinkage __visible void *extract_kernel(void *rmode, unsigned char *output) /* Clear flags intended for solely in-kernel use. */ boot_params_ptr->hdr.loadflags &= ~KASLR_FLAG; + parse_mem_encrypt(&boot_params_ptr->hdr); + sanitize_boot_params(boot_params_ptr); if (boot_params_ptr->screen_info.orig_video_mode == 7) { diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c index 454acd7a2d..4c9b752814 100644 --- a/arch/x86/boot/compressed/sev.c +++ b/arch/x86/boot/compressed/sev.c @@ -116,6 +116,9 @@ static bool fault_in_kernel_space(unsigned long address) #undef __init #define __init +#undef __head +#define __head + #define __BOOT_COMPRESSED /* Basic instruction decoding support needed */ diff --git a/arch/x86/boot/pm.c b/arch/x86/boot/pm.c index 40031a6147..5941f930f6 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 1c8541ae3b..c23f3b9c84 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/core.c b/arch/x86/coco/core.c index d07be9d05c..ddd4efdc79 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -3,13 +3,17 @@ * Confidential Computing Platform Capability checks * * Copyright (C) 2021 Advanced Micro Devices, Inc. + * Copyright (C) 2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. * * Author: Tom Lendacky <thomas.lendacky@amd.com> */ #include <linux/export.h> #include <linux/cc_platform.h> +#include <linux/string.h> +#include <linux/random.h> +#include <asm/archrandom.h> #include <asm/coco.h> #include <asm/processor.h> @@ -148,3 +152,40 @@ u64 cc_mkdec(u64 val) } } EXPORT_SYMBOL_GPL(cc_mkdec); + +__init void cc_random_init(void) +{ + /* + * The seed is 32 bytes (in units of longs), which is 256 bits, which + * is the security level that the RNG is targeting. + */ + unsigned long rng_seed[32 / sizeof(long)]; + size_t i, longs; + + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + return; + + /* + * Since the CoCo threat model includes the host, the only reliable + * source of entropy that can be neither observed nor manipulated is + * RDRAND. Usually, RDRAND failure is considered tolerable, but since + * CoCo guests have no other unobservable source of entropy, it's + * important to at least ensure the RNG gets some initial random seeds. + */ + for (i = 0; i < ARRAY_SIZE(rng_seed); i += longs) { + longs = arch_get_random_longs(&rng_seed[i], ARRAY_SIZE(rng_seed) - i); + + /* + * A zero return value means that the guest doesn't have RDRAND + * or the CPU is physically broken, and in both cases that + * means most crypto inside of the CoCo instance will be + * broken, defeating the purpose of CoCo in the first place. So + * just panic here because it's absolutely unsafe to continue + * executing. + */ + if (longs == 0) + panic("RDRAND is defective."); + } + add_device_randomness(rng_seed, sizeof(rng_seed)); + memzero_explicit(rng_seed, sizeof(rng_seed)); +} diff --git a/arch/x86/coco/tdx/tdx-shared.c b/arch/x86/coco/tdx/tdx-shared.c index 78e4132697..1655aa56a0 100644 --- a/arch/x86/coco/tdx/tdx-shared.c +++ b/arch/x86/coco/tdx/tdx-shared.c @@ -22,13 +22,13 @@ static unsigned long try_accept_one(phys_addr_t start, unsigned long len, */ switch (pg_level) { case PG_LEVEL_4K: - page_size = 0; + page_size = TDX_PS_4K; break; case PG_LEVEL_2M: - page_size = 1; + page_size = TDX_PS_2M; break; case PG_LEVEL_1G: - page_size = 2; + page_size = TDX_PS_1G; break; default: return 0; diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index cf1f13c821..c1cb903699 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -887,7 +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 9bbfd01cfa..c9e59589a1 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 187f913cc2..411d8c83e8 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 74dd230973..8c9749ed06 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 81ce0f4db5..bbcff1fb78 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 959afa705e..ab8bc54f25 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 4c0383a90e..e04a43d9f7 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 d902b8ea07..5bfce4b045 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 65be301568..30a2c4777f 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 e2668d2fe6..2bf611eaa1 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 98ede94592..9ff5ba0755 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 1bceab7516..b5b5e67e40 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 84bc718f49..1148fd4cd5 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 7800f77d68..85b4ca78b4 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 f690762717..9f1d94790a 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 6356060caa..6de50b8070 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } @@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void) } /** - * int80_emulation - 32-bit legacy syscall entry + * do_int80_emulation - 32-bit legacy syscall C entry from asm * * 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 @@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void) * eax: system call number * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 */ -DEFINE_IDTENTRY_RAW(int80_emulation) +__visible noinstr void do_int80_emulation(struct pt_regs *regs) { int nr; diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index bdb17fad5d..e986331b14 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -560,17 +561,28 @@ __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 + CLEAR_CPU_BUFFERS + /* 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 /* @@ -597,14 +609,14 @@ 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 - CLEAR_CPU_BUFFERS - jmp .Lnative_iret - + jmp .Lswapgs_and_iret +#endif SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL) #ifdef CONFIG_DEBUG_ENTRY @@ -1483,3 +1495,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index eabf48c4d4..c779046cc3 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY /* * SYSENTER doesn't filter flags, so we need to clear NT and AC @@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR int3 SYM_CODE_END(entry_SYSCALL_compat) + +/* + * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries + * point to C routines, however since this is a system call interface the branch + * history needs to be scrubbed to protect against BHI attacks, and that + * scrubbing needs to take place in assembly code prior to entering any C + * routines. + */ +SYM_CODE_START(int80_emulation) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + CLEAR_BRANCH_HISTORY + jmp do_int80_emulation +SYM_CODE_END(int80_emulation) diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e..c2235bae17 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include <asm/syscalls_32.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_32.h> + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1f..33b3f09e6f 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include <asm/syscalls_64.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_64.h> + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a12..03de4a9321 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include <asm/syscalls_x32.h> #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include <asm/syscalls_x32.h> +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_x32.h> + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index c8fac52058..5f8591ce7f 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 8cb8bf6872..7e8d46f414 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/Makefile b/arch/x86/entry/vdso/Makefile index b1b8dd1608..73ac5adb0b 100644 --- a/arch/x86/entry/vdso/Makefile +++ b/arch/x86/entry/vdso/Makefile @@ -34,8 +34,13 @@ obj-y += vma.o extable.o KASAN_SANITIZE_vma.o := y UBSAN_SANITIZE_vma.o := y KCSAN_SANITIZE_vma.o := y -OBJECT_FILES_NON_STANDARD_vma.o := n -OBJECT_FILES_NON_STANDARD_extable.o := n + +OBJECT_FILES_NON_STANDARD_extable.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-x32.o := n +OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n +OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n +OBJECT_FILES_NON_STANDARD_vma.o := n # vDSO images to build vdso_img-$(VDSO64-y) += 64 @@ -43,7 +48,6 @@ vdso_img-$(VDSOX32-y) += x32 vdso_img-$(VDSO32-y) += 32 obj-$(VDSO32-y) += vdso32-setup.o -OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n vobjs := $(foreach F,$(vobjs-y),$(obj)/$F) vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F) diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c index 7d70935b67..0debc194bd 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 ed30871923..780acd3dff 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 5365d6acbf..eb5c8539d6 100644 --- a/arch/x86/events/amd/core.c +++ b/arch/x86/events/amd/core.c @@ -250,7 +250,7 @@ static const u64 amd_perfmon_event_map[PERF_COUNT_HW_MAX] = /* * AMD Performance Monitor Family 17h and later: */ -static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = +static const u64 amd_zen1_perfmon_event_map[PERF_COUNT_HW_MAX] = { [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, @@ -262,10 +262,24 @@ static const u64 amd_f17h_perfmon_event_map[PERF_COUNT_HW_MAX] = [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = 0x0187, }; +static const u64 amd_zen2_perfmon_event_map[PERF_COUNT_HW_MAX] = +{ + [PERF_COUNT_HW_CPU_CYCLES] = 0x0076, + [PERF_COUNT_HW_INSTRUCTIONS] = 0x00c0, + [PERF_COUNT_HW_CACHE_REFERENCES] = 0xff60, + [PERF_COUNT_HW_CACHE_MISSES] = 0x0964, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x00c2, + [PERF_COUNT_HW_BRANCH_MISSES] = 0x00c3, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = 0x00a9, +}; + static u64 amd_pmu_event_map(int hw_event) { - if (boot_cpu_data.x86 >= 0x17) - return amd_f17h_perfmon_event_map[hw_event]; + if (cpu_feature_enabled(X86_FEATURE_ZEN2) || boot_cpu_data.x86 >= 0x19) + return amd_zen2_perfmon_event_map[hw_event]; + + if (cpu_feature_enabled(X86_FEATURE_ZEN1)) + return amd_zen1_perfmon_event_map[hw_event]; return amd_perfmon_event_map[hw_event]; } @@ -939,7 +953,7 @@ 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); @@ -1183,7 +1197,7 @@ 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 6911c5399d..e91970b01d 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/amd/lbr.c b/arch/x86/events/amd/lbr.c index eb31f85084..4a1e600314 100644 --- a/arch/x86/events/amd/lbr.c +++ b/arch/x86/events/amd/lbr.c @@ -173,9 +173,11 @@ void amd_pmu_lbr_read(void) /* * Check if a branch has been logged; if valid = 0, spec = 0 - * then no branch was recorded + * then no branch was recorded; if reserved = 1 then an + * erroneous branch was recorded (see Erratum 1452) */ - if (!entry.to.split.valid && !entry.to.split.spec) + if ((!entry.to.split.valid && !entry.to.split.spec) || + entry.to.split.reserved) continue; perf_clear_branch_entry_bitfields(br + out); diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 40ad1425ff..5b0dd07b1e 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; /* @@ -1644,6 +1644,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; @@ -1702,7 +1703,7 @@ 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 0f2786d4e4..3804f21ab0 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: @@ -4380,8 +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: @@ -4560,7 +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)); @@ -5532,11 +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, @@ -5564,6 +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; @@ -5585,26 +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 cbeb6d2bf5..4b50a3a981 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 bf97ab904d..807de7b596 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -1236,11 +1236,11 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu = event->pmu; /* - * Make sure we get updated with the first PEBS - * event. It will trigger also during removal, but - * that does not hurt: + * Make sure we get updated with the first PEBS event. + * During removal, ->pebs_data_cfg is still valid for + * the last PEBS event. Don't clear it. */ - if (cpuc->n_pebs == 1) + if ((cpuc->n_pebs == 1) && add) cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { @@ -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 c3b0d15a98..78cd508410 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 01023aa512..7927c0b832 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 c30fb5bb12..4838502d89 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 cb488e4180..9a698a9296 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 6ee80ad342..22e769a811 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 173e2674be..56eea2c66c 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 49bc27ab26..a96496bef6 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, lgc_pkg, ret = -EPERM; + int idx, lgc_pkg, ret = -EPERM; struct intel_uncore_topology *upi; unsigned int devfn; @@ -5611,27 +5619,22 @@ 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; - lgc_pkg = topology_phys_to_logical_pkg(i); - 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; - } + 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; } - break; } } err: @@ -6085,13 +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, }; @@ -6187,7 +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 }; @@ -6418,7 +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; @@ -6427,9 +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++) @@ -6476,7 +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) { @@ -6558,7 +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; } @@ -6566,15 +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 53dd5d495b..fb56518356 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 1dc19b9b44..6c977c19f2 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 97bfe5f053..5fc45543e9 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 42c70d28ef..3215a4a074 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 02e55237d9..768d73de0d 100644 --- a/arch/x86/hyperv/ivm.c +++ b/arch/x86/hyperv/ivm.c @@ -15,6 +15,7 @@ #include <asm/io.h> #include <asm/coco.h> #include <asm/mem_encrypt.h> +#include <asm/set_memory.h> #include <asm/mshyperv.h> #include <asm/hypervisor.h> #include <asm/mtrr.h> @@ -144,7 +145,7 @@ 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(); @@ -503,6 +504,31 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[], } /* + * When transitioning memory between encrypted and decrypted, the caller + * of set_memory_encrypted() or set_memory_decrypted() is responsible for + * ensuring that the memory isn't in use and isn't referenced while the + * transition is in progress. The transition has multiple steps, and the + * memory is in an inconsistent state until all steps are complete. A + * reference while the state is inconsistent could result in an exception + * that can't be cleanly fixed up. + * + * But the Linux kernel load_unaligned_zeropad() mechanism could cause a + * stray reference that can't be prevented by the caller, so Linux has + * specific code to handle this case. But when the #VC and #VE exceptions + * routed to a paravisor, the specific code doesn't work. To avoid this + * problem, mark the pages as "not present" while the transition is in + * progress. If load_unaligned_zeropad() causes a stray reference, a normal + * page fault is generated instead of #VC or #VE, and the page-fault-based + * handlers for load_unaligned_zeropad() resolve the reference. When the + * transition is complete, hv_vtom_set_host_visibility() marks the pages + * as "present" again. + */ +static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc) +{ + return !set_memory_np(kbuffer, pagecount); +} + +/* * hv_vtom_set_host_visibility - Set specified memory visible to host. * * In Isolation VM, all guest memory is encrypted from host and guest @@ -515,16 +541,28 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo enum hv_mem_host_visibility visibility = enc ? VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE; u64 *pfn_array; + phys_addr_t paddr; + void *vaddr; int ret = 0; bool result = true; int i, pfn; pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); - if (!pfn_array) - return false; + if (!pfn_array) { + result = false; + goto err_set_memory_p; + } for (i = 0, pfn = 0; i < pagecount; i++) { - pfn_array[pfn] = virt_to_hvpfn((void *)kbuffer + i * HV_HYP_PAGE_SIZE); + /* + * Use slow_virt_to_phys() because the PRESENT bit has been + * temporarily cleared in the PTEs. slow_virt_to_phys() works + * without the PRESENT bit while virt_to_hvpfn() or similar + * does not. + */ + vaddr = (void *)kbuffer + (i * HV_HYP_PAGE_SIZE); + paddr = slow_virt_to_phys(vaddr); + pfn_array[pfn] = paddr >> HV_HYP_PAGE_SHIFT; pfn++; if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) { @@ -538,14 +576,30 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo } } - err_free_pfn_array: +err_free_pfn_array: kfree(pfn_array); + +err_set_memory_p: + /* + * Set the PTE PRESENT bits again to revert what hv_vtom_clear_present() + * did. Do this even if there is an error earlier in this function in + * order to avoid leaving the memory range in a "broken" state. Setting + * the PRESENT bits shouldn't fail, but return an error if it does. + */ + if (set_memory_p(kbuffer, pagecount)) + result = false; + return result; } static bool hv_vtom_tlb_flush_required(bool private) { - return true; + /* + * Since hv_vtom_clear_present() marks the PTEs as "not present" + * and flushes the TLB, they can't be in the TLB. That makes the + * flush controlled by this function redundant, so return "false". + */ + return false; } static bool hv_vtom_cache_flush_required(void) @@ -608,6 +662,7 @@ void __init hv_vtom_init(void) x86_platform.hyper.is_private_mmio = hv_is_private_mmio; x86_platform.guest.enc_cache_flush_required = hv_vtom_cache_flush_required; x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required; + x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present; x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility; /* Set WB as the default cache mode. */ diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 65f79092c9..fcd20c6dc7 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 ed0eaf65c4..5c37944c8a 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 d21f48f1c2..dddd3fc195 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -13,6 +13,7 @@ #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/hardirq.h> +#include <asm/io.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -96,7 +97,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) static inline u32 native_apic_mem_read(u32 reg) { - return *((volatile u32 *)(APIC_BASE + reg)); + return readl((void __iomem *)(APIC_BASE + reg)); } static inline void native_apic_mem_eoi(void) @@ -272,8 +273,6 @@ 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 4b125e5b31..094106b6a5 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 0216f63a36..d0795b5fab 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -79,6 +79,9 @@ do { \ #define __smp_mb__before_atomic() do { } while (0) #define __smp_mb__after_atomic() do { } while (0) +/* Writing to CR3 provides a full memory barrier in switch_mm(). */ +#define smp_mb__after_switch_mm() do { } while (0) + #include <asm-generic/barrier.h> #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h index a38cc0afc9..a3e0be0470 100644 --- a/arch/x86/include/asm/boot.h +++ b/arch/x86/include/asm/boot.h @@ -81,6 +81,7 @@ #ifndef __ASSEMBLY__ extern unsigned int output_len; +extern const unsigned long kernel_text_size; extern const unsigned long kernel_total_size; unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr, diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h index 58dacd90da..7cd7525579 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/coco.h b/arch/x86/include/asm/coco.h index 21940ef8d2..a368afce37 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -11,10 +11,9 @@ enum cc_vendor { CC_VENDOR_INTEL, }; +#ifdef CONFIG_ARCH_HAS_CC_PLATFORM extern enum cc_vendor cc_vendor; extern u64 cc_mask; - -#ifdef CONFIG_ARCH_HAS_CC_PLATFORM static inline void cc_set_mask(u64 mask) { RIP_REL_REF(cc_mask) = mask; @@ -22,7 +21,11 @@ static inline void cc_set_mask(u64 mask) u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); +void cc_random_init(void); #else +#define cc_vendor (CC_VENDOR_NONE) +static const u64 cc_mask = 0; + static inline u64 cc_mkenc(u64 val) { return val; @@ -32,6 +35,7 @@ static inline u64 cc_mkdec(u64 val) { return val; } +static inline void cc_random_init(void) { } #endif #endif /* _ASM_X86_COCO_H */ diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h index fecc4fe1d6..f8f9a9b793 100644 --- a/arch/x86/include/asm/cpu.h +++ b/arch/x86/include/asm/cpu.h @@ -23,10 +23,6 @@ static inline void prefill_possible_map(void) {} #endif /* CONFIG_SMP */ -struct x86_cpu { - struct cpu cpu; -}; - #ifdef CONFIG_HOTPLUG_CPU extern void soft_restart_cpu(void); #endif diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index a1273698fc..686e92d266 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -33,6 +33,8 @@ enum cpuid_leafs CPUID_7_EDX, CPUID_8000_001F_EAX, CPUID_8000_0021_EAX, + CPUID_LNX_5, + NR_CPUID_WORDS, }; #define X86_CAP_FMT_NUM "%d:%d" @@ -91,8 +93,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) || \ REQUIRED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define DISABLED_MASK_BIT_SET(feature_bit) \ ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 0, feature_bit) || \ @@ -116,8 +119,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32]; CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) || \ CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) || \ + CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) || \ DISABLED_MASK_CHECK || \ - BUILD_BUG_ON_ZERO(NCAPINTS != 21)) + BUILD_BUG_ON_ZERO(NCAPINTS != 22)) #define cpu_has(c, bit) \ (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 0e4f2da9f6..76b3b00ff1 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -13,7 +13,7 @@ /* * Defines x86 CPU feature bits */ -#define NCAPINTS 21 /* N 32-bit words worth of info */ +#define NCAPINTS 22 /* N 32-bit words worth of info */ #define NBUGINTS 2 /* N 32-bit bug flags */ /* @@ -81,10 +81,8 @@ #define X86_FEATURE_K6_MTRR ( 3*32+ 1) /* AMD K6 nonstandard MTRRs */ #define X86_FEATURE_CYRIX_ARR ( 3*32+ 2) /* Cyrix ARRs (= MTRRs) */ #define X86_FEATURE_CENTAUR_MCR ( 3*32+ 3) /* Centaur MCRs (= MTRRs) */ - -/* CPU types for specific tunings: */ #define X86_FEATURE_K8 ( 3*32+ 4) /* "" Opteron, Athlon64 */ -/* FREE, was #define X86_FEATURE_K7 ( 3*32+ 5) "" Athlon */ +#define X86_FEATURE_ZEN5 ( 3*32+ 5) /* "" CPU based on Zen5 microarchitecture */ #define X86_FEATURE_P3 ( 3*32+ 6) /* "" P3 */ #define X86_FEATURE_P4 ( 3*32+ 7) /* "" P4 */ #define X86_FEATURE_CONSTANT_TSC ( 3*32+ 8) /* TSC ticks at a constant rate */ @@ -198,6 +196,7 @@ #define X86_FEATURE_CAT_L3 ( 7*32+ 4) /* Cache Allocation Technology L3 */ #define X86_FEATURE_CAT_L2 ( 7*32+ 5) /* Cache Allocation Technology L2 */ #define X86_FEATURE_CDP_L3 ( 7*32+ 6) /* Code and Data Prioritization L3 */ +#define X86_FEATURE_TDX_HOST_PLATFORM ( 7*32+ 7) /* Platform supports being a TDX host */ #define X86_FEATURE_HW_PSTATE ( 7*32+ 8) /* AMD HW-PState */ #define X86_FEATURE_PROC_FEEDBACK ( 7*32+ 9) /* AMD ProcFeedbackInterface */ #define X86_FEATURE_XCOMPACTED ( 7*32+10) /* "" Use compacted XSTATE (XSAVES or XSAVEC) */ @@ -218,7 +217,7 @@ #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 */ @@ -312,6 +311,10 @@ #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 */ @@ -454,6 +457,17 @@ #define X86_FEATURE_SRSO_NO (20*32+29) /* "" CPU is not affected by SRSO */ /* + * Extended auxiliary flags: Linux defined - for features scattered in various + * CPUID levels like 0x80000022, etc and Linux defined features. + * + * Reuse free bits when adding new feature flags! + */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ + +/* * BUG word(s) */ #define X86_BUG(x) (NCAPINTS*32 + (x)) @@ -495,9 +509,11 @@ #define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* EIBRS is vulnerable to Post Barrier RSB Predictions */ #define X86_BUG_SMT_RSB X86_BUG(29) /* CPU is vulnerable to Cross-Thread Return Address Predictions */ #define X86_BUG_GDS X86_BUG(30) /* CPU is affected by Gather Data Sampling */ +#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* CPU may incur #MC if non-TD software does partial write to TDX private memory */ /* BUG word 2 */ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h index a1168e7b69..dd4b67101b 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 66eb5e1ac4..0cec92c430 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 f7e7099af5..d440a65af8 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/disabled-features.h b/arch/x86/include/asm/disabled-features.h index 702d93fdd1..88fcf08458 100644 --- a/arch/x86/include/asm/disabled-features.h +++ b/arch/x86/include/asm/disabled-features.h @@ -143,6 +143,7 @@ #define DISABLED_MASK18 (DISABLE_IBT) #define DISABLED_MASK19 0 #define DISABLED_MASK20 0 -#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define DISABLED_MASK21 0 +#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_DISABLED_FEATURES_H */ diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h index a0234dfd10..1e16bd5ac7 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 991e31cfde..fe63120450 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 eb810074f1..ace9aa3b78 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 9805629479..c7ef6ea2fa 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> @@ -91,4 +90,14 @@ 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/intel-family.h b/arch/x86/include/asm/intel-family.h index 197316121f..b65e9c46b9 100644 --- a/arch/x86/include/asm/intel-family.h +++ b/arch/x86/include/asm/intel-family.h @@ -162,6 +162,8 @@ #define INTEL_FAM6_ATOM_CRESTMONT_X 0xAF /* Sierra Forest */ #define INTEL_FAM6_ATOM_CRESTMONT 0xB6 /* Grand Ridge */ +#define INTEL_FAM6_ATOM_DARKMONT_X 0xDD /* Clearwater Forest */ + /* Xeon Phi */ #define INTEL_FAM6_XEON_PHI_KNL 0x57 /* Knights Landing */ diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h index 7623884240..294cd2a408 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 @@ -379,7 +379,7 @@ static inline void iosubmit_cmds512(void __iomem *dst, const void *src, const u8 *end = from + count * 64; while (from < end) { - movdir64b(dst, from); + movdir64b_io(dst, from); from += 64; } } diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index a1911fea87..af7541c118 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/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 26b628d845..378ed944b8 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -55,8 +55,10 @@ KVM_X86_OP(set_rflags) KVM_X86_OP(get_if_flag) KVM_X86_OP(flush_tlb_all) KVM_X86_OP(flush_tlb_current) +#if IS_ENABLED(CONFIG_HYPERV) KVM_X86_OP_OPTIONAL(flush_remote_tlbs) KVM_X86_OP_OPTIONAL(flush_remote_tlbs_range) +#endif KVM_X86_OP(flush_tlb_gva) KVM_X86_OP(flush_tlb_guest) KVM_X86_OP(vcpu_pre_run) @@ -135,6 +137,7 @@ KVM_X86_OP(msr_filter_changed) KVM_X86_OP(complete_emulated_msr) KVM_X86_OP(vcpu_deliver_sipi_vector) KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons); +KVM_X86_OP_OPTIONAL(get_untagged_addr) #undef KVM_X86_OP #undef KVM_X86_OP_OPTIONAL diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index d703698233..b7a539ea29 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -133,7 +133,8 @@ | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \ | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \ | X86_CR4_OSXMMEXCPT | X86_CR4_LA57 | X86_CR4_VMXE \ - | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP)) + | X86_CR4_SMAP | X86_CR4_PKE | X86_CR4_UMIP \ + | X86_CR4_LAM_SUP)) #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR) @@ -500,8 +501,23 @@ struct kvm_pmc { u8 idx; bool is_paused; bool intr; + /* + * Base value of the PMC counter, relative to the *consumed* count in + * the associated perf_event. This value includes counter updates from + * the perf_event and emulated_count since the last time the counter + * was reprogrammed, but it is *not* the current value as seen by the + * guest or userspace. + * + * The count is relative to the associated perf_event so that KVM + * doesn't need to reprogram the perf_event every time the guest writes + * to the counter. + */ u64 counter; - u64 prev_counter; + /* + * PMC events triggered by KVM emulation that haven't been fully + * processed, i.e. haven't undergone overflow detection. + */ + u64 emulated_counter; u64 eventsel; struct perf_event *perf_event; struct kvm_vcpu *vcpu; @@ -838,6 +854,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; struct kvm_hypervisor_cpuid kvm_cpuid; + bool is_amd_compatible; /* * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly @@ -937,8 +954,10 @@ struct kvm_vcpu_arch { /* used for guest single stepping over the given code position */ unsigned long singlestep_rip; +#ifdef CONFIG_KVM_HYPERV bool hyperv_enabled; struct kvm_vcpu_hv *hyperv; +#endif #ifdef CONFIG_KVM_XEN struct kvm_vcpu_xen xen; #endif @@ -1095,6 +1114,7 @@ enum hv_tsc_page_status { HV_TSC_PAGE_BROKEN, }; +#ifdef CONFIG_KVM_HYPERV /* Hyper-V emulation context */ struct kvm_hv { struct mutex hv_lock; @@ -1125,9 +1145,11 @@ struct kvm_hv { */ unsigned int synic_auto_eoi_used; - struct hv_partition_assist_pg *hv_pa_pg; struct kvm_hv_syndbg hv_syndbg; + + bool xsaves_xsavec_checked; }; +#endif struct msr_bitmap_range { u32 flags; @@ -1136,6 +1158,7 @@ struct msr_bitmap_range { unsigned long *bitmap; }; +#ifdef CONFIG_KVM_XEN /* Xen emulation context */ struct kvm_xen { struct mutex xen_lock; @@ -1147,6 +1170,7 @@ struct kvm_xen { struct idr evtchn_ports; unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)]; }; +#endif enum kvm_irqchip_mode { KVM_IRQCHIP_NONE, @@ -1255,6 +1279,7 @@ enum kvm_apicv_inhibit { }; struct kvm_arch { + unsigned long vm_type; unsigned long n_used_mmu_pages; unsigned long n_requested_mmu_pages; unsigned long n_max_mmu_pages; @@ -1347,8 +1372,13 @@ struct kvm_arch { /* reads protected by irq_srcu, writes by irq_lock */ struct hlist_head mask_notifier_list; +#ifdef CONFIG_KVM_HYPERV struct kvm_hv hyperv; +#endif + +#ifdef CONFIG_KVM_XEN struct kvm_xen xen; +#endif bool backwards_tsc_observed; bool boot_vcpu_runs_old_kvmclock; @@ -1406,9 +1436,8 @@ struct kvm_arch { * the MMU lock in read mode + RCU or * the MMU lock in write mode * - * For writes, this list is protected by: - * the MMU lock in read mode + the tdp_mmu_pages_lock or - * the MMU lock in write mode + * For writes, this list is protected by tdp_mmu_pages_lock; see + * below for the details. * * Roots will remain in the list until their tdp_mmu_root_count * drops to zero, at which point the thread that decremented the @@ -1425,8 +1454,10 @@ struct kvm_arch { * - possible_nx_huge_pages; * - the possible_nx_huge_page_link field of kvm_mmu_page structs used * by the TDP MMU - * It is acceptable, but not necessary, to acquire this lock when - * the thread holds the MMU lock in write mode. + * Because the lock is only taken within the MMU lock, strictly + * speaking it is redundant to acquire this lock when the thread + * holds the MMU lock in write mode. However it often simplifies + * the code to do so. */ spinlock_t tdp_mmu_pages_lock; #endif /* CONFIG_X86_64 */ @@ -1441,6 +1472,7 @@ struct kvm_arch { #if IS_ENABLED(CONFIG_HYPERV) hpa_t hv_root_tdp; spinlock_t hv_root_tdp_lock; + struct hv_partition_assist_pg *hv_pa_pg; #endif /* * VM-scope maximum vCPU ID. Used to determine the size of structures @@ -1613,9 +1645,11 @@ struct kvm_x86_ops { void (*flush_tlb_all)(struct kvm_vcpu *vcpu); void (*flush_tlb_current)(struct kvm_vcpu *vcpu); +#if IS_ENABLED(CONFIG_HYPERV) int (*flush_remote_tlbs)(struct kvm *kvm); int (*flush_remote_tlbs_range)(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); +#endif /* * Flush any TLB entries associated with the given GVA. @@ -1652,7 +1686,7 @@ 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); @@ -1761,6 +1795,8 @@ struct kvm_x86_ops { * Returns vCPU specific APICv inhibit reasons */ unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu); + + gva_t (*get_untagged_addr)(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); }; struct kvm_x86_nested_ops { @@ -1824,6 +1860,7 @@ static inline struct kvm *kvm_arch_alloc_vm(void) #define __KVM_HAVE_ARCH_VM_FREE void kvm_arch_free_vm(struct kvm *kvm); +#if IS_ENABLED(CONFIG_HYPERV) #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) { @@ -1835,6 +1872,15 @@ static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm) } #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE +static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, + u64 nr_pages) +{ + if (!kvm_x86_ops.flush_remote_tlbs_range) + return -EOPNOTSUPP; + + return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages); +} +#endif /* CONFIG_HYPERV */ #define kvm_arch_pmi_in_guest(vcpu) \ ((vcpu) && (vcpu)->arch.handling_intr_from_guest) @@ -1848,6 +1894,9 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu); void kvm_mmu_init_vm(struct kvm *kvm); void kvm_mmu_uninit_vm(struct kvm *kvm); +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot); + void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_mmu_reset_context(struct kvm_vcpu *vcpu); void kvm_mmu_slot_remove_write_access(struct kvm *kvm, @@ -2086,6 +2135,12 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd); void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); +#ifdef CONFIG_KVM_PRIVATE_MEM +#define kvm_arch_has_private_mem(kvm) ((kvm)->arch.vm_type != KVM_X86_DEFAULT_VM) +#else +#define kvm_arch_has_private_mem(kvm) false +#endif + static inline u16 kvm_read_ldt(void) { u16 ldt; @@ -2133,16 +2188,15 @@ enum { #define HF_SMM_MASK (1 << 1) #define HF_SMM_INSIDE_NMI_MASK (1 << 2) -# define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE -# define KVM_ADDRESS_SPACE_NUM 2 +# define KVM_MAX_NR_ADDRESS_SPACES 2 +/* SMM is currently unsupported for guests with private memory. */ +# define kvm_arch_nr_memslot_as_ids(kvm) (kvm_arch_has_private_mem(kvm) ? 1 : 2) # define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0) # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm) #else # define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, 0) #endif -#define KVM_ARCH_WANT_MMU_NOTIFIER - int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v); int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu); int kvm_cpu_has_extint(struct kvm_vcpu *v); diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6de6e1d959..de31183058 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/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index b31eb9fd59..f922b682b9 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -47,8 +47,8 @@ void __init sme_unmap_bootdata(char *real_mode_data); void __init sme_early_init(void); -void __init sme_encrypt_kernel(struct boot_params *bp); -void __init sme_enable(struct boot_params *bp); +void sme_encrypt_kernel(struct boot_params *bp); +void sme_enable(struct boot_params *bp); int __init early_set_memory_decrypted(unsigned long vaddr, unsigned long size); int __init early_set_memory_encrypted(unsigned long vaddr, unsigned long size); @@ -81,8 +81,8 @@ static inline void __init sme_unmap_bootdata(char *real_mode_data) { } static inline void __init sme_early_init(void) { } -static inline void __init sme_encrypt_kernel(struct boot_params *bp) { } -static inline void __init sme_enable(struct boot_params *bp) { } +static inline void sme_encrypt_kernel(struct boot_params *bp) { } +static inline void sme_enable(struct boot_params *bp) { } static inline void sev_es_init_vc_handling(void) { } diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 857839df66..d65f8ce6b7 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -50,10 +50,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -152,6 +155,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. @@ -245,6 +252,11 @@ #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) @@ -544,6 +556,9 @@ #define MSR_RELOAD_PMC0 0x000014c1 #define MSR_RELOAD_FIXED_CTR0 0x00001309 +/* KeyID partitioning between MKTME and TDX */ +#define MSR_IA32_MKTME_KEYID_PARTITIONING 0x00000087 + /* * AMD64 MSRs. Not complete. See the architecture manual for a more * complete list. diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h index bae8381050..920426d691 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(); diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 4e33cc834b..3ff081a74a 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) && \ @@ -335,6 +335,19 @@ ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF .endm +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -377,6 +390,10 @@ extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + extern void (*x86_return_thunk)(void); #ifdef CONFIG_CALL_DEPTH_TRACKING diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h index 6c8ff12140..d4eb9e1d61 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 772d034875..8d4fbe1be4 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 20624b80f8..5e01883eb5 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 2618ec7c3d..3736b8a46c 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 57bab91bbf..9d077bca6a 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 a629b1b9f6..24af25b155 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/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0b748ee16b..9abb8cc4cd 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -148,7 +148,7 @@ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | \ _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ - _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP) + _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -173,6 +173,7 @@ enum page_cache_mode { }; #endif +#define _PAGE_CC (_AT(pteval_t, cc_mask)) #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h index 4527e1430c..af77235fde 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/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h index 85b6e3609c..ef9697f201 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/required-features.h b/arch/x86/include/asm/required-features.h index 7ba1726b71..e9187ddd3d 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -99,6 +99,7 @@ #define REQUIRED_MASK18 0 #define REQUIRED_MASK19 0 #define REQUIRED_MASK20 0 -#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21) +#define REQUIRED_MASK21 0 +#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22) #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h index a5e89641bd..9aee31862b 100644 --- a/arch/x86/include/asm/set_memory.h +++ b/arch/x86/include/asm/set_memory.h @@ -47,6 +47,7 @@ int set_memory_uc(unsigned long addr, int numpages); int set_memory_wc(unsigned long addr, int numpages); int set_memory_wb(unsigned long addr, int numpages); int set_memory_np(unsigned long addr, int numpages); +int set_memory_p(unsigned long addr, int numpages); int set_memory_4k(unsigned long addr, int numpages); int set_memory_encrypted(unsigned long addr, int numpages); int set_memory_decrypted(unsigned long addr, int numpages); diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index bf483fcb4e..5c83729c8e 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/sev.h b/arch/x86/include/asm/sev.h index 36f9057970..75a5388d40 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -199,15 +199,15 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) struct snp_guest_request_ioctl; void setup_ghcb(void); -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, - unsigned long npages); -void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, - unsigned long npages); +void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, + unsigned long npages); +void early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr, + unsigned long npages); void snp_set_memory_shared(unsigned long vaddr, unsigned long npages); void snp_set_memory_private(unsigned long vaddr, unsigned long npages); void snp_set_wakeup_secondary_cpu(void); bool snp_init(struct boot_params *bp); -void __init __noreturn snp_abort(void); +void __noreturn snp_abort(void); void snp_dmi_setup(void); int snp_issue_guest_request(u64 exit_code, struct snp_req_data *input, struct snp_guest_request_ioctl *rio); void snp_accept_memory(phys_addr_t start, phys_addr_t end); diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h index ccce7ebd86..fdfd41511b 100644 --- a/arch/x86/include/asm/shared/tdx.h +++ b/arch/x86/include/asm/shared/tdx.h @@ -55,6 +55,12 @@ (TDX_RDX | TDX_RBX | TDX_RSI | TDX_RDI | TDX_R8 | TDX_R9 | \ TDX_R10 | TDX_R11 | TDX_R12 | TDX_R13 | TDX_R14 | TDX_R15) +/* TDX supported page sizes from the TDX module ABI. */ +#define TDX_PS_4K 0 +#define TDX_PS_2M 1 +#define TDX_PS_1G 2 +#define TDX_PS_NR (TDX_PS_1G + 1) + #ifndef __ASSEMBLY__ #include <linux/compiler_attributes.h> diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h index 48f8dd47cf..09a5461d72 100644 --- a/arch/x86/include/asm/special_insns.h +++ b/arch/x86/include/asm/special_insns.h @@ -224,10 +224,10 @@ static inline void serialize(void) } /* The dst parameter must be 64-bytes aligned */ -static inline void movdir64b(void __iomem *dst, const void *src) +static inline void movdir64b(void *dst, const void *src) { const struct { char _[64]; } *__src = src; - struct { char _[64]; } __iomem *__dst = dst; + struct { char _[64]; } *__dst = dst; /* * MOVDIR64B %(rdx), rax. @@ -245,6 +245,11 @@ static inline void movdir64b(void __iomem *dst, const void *src) : "m" (*__src), "a" (__dst), "d" (__src)); } +static inline void movdir64b_io(void __iomem *dst, const void *src) +{ + movdir64b((void __force *)dst, src); +} + /** * enqcmds - Enqueue a command in supervisor (CPL0) mode * @dst: destination, in MMIO space (must be 512-bit aligned) diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f44e2f9ab6..2fc7bc3863 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. @@ -127,6 +125,7 @@ static inline int syscall_get_arch(struct task_struct *task) } bool do_syscall_64(struct pt_regs *regs, int nr); +void do_int80_emulation(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h index f3d5305a60..eba178996d 100644 --- a/arch/x86/include/asm/tdx.h +++ b/arch/x86/include/asm/tdx.h @@ -24,8 +24,16 @@ #define TDX_SEAMCALL_GP (TDX_SW_ERROR | X86_TRAP_GP) #define TDX_SEAMCALL_UD (TDX_SW_ERROR | X86_TRAP_UD) +/* + * TDX module SEAMCALL leaf function error codes + */ +#define TDX_SUCCESS 0ULL +#define TDX_RND_NO_ENTROPY 0x8000020300000000ULL + #ifndef __ASSEMBLY__ +#include <uapi/asm/mce.h> + /* * Used by the #VE exception handler to gather the #VE exception * info from the TDX module. This is a software only structure @@ -83,6 +91,36 @@ static inline long tdx_kvm_hypercall(unsigned int nr, unsigned long p1, u64 __seamcall(u64 fn, struct tdx_module_args *args); u64 __seamcall_ret(u64 fn, struct tdx_module_args *args); u64 __seamcall_saved_ret(u64 fn, struct tdx_module_args *args); +void tdx_init(void); + +#include <asm/archrandom.h> + +typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args); + +static inline u64 sc_retry(sc_func_t func, u64 fn, + struct tdx_module_args *args) +{ + int retry = RDRAND_RETRY_LOOPS; + u64 ret; + + do { + ret = func(fn, args); + } while (ret == TDX_RND_NO_ENTROPY && --retry); + + return ret; +} + +#define seamcall(_fn, _args) sc_retry(__seamcall, (_fn), (_args)) +#define seamcall_ret(_fn, _args) sc_retry(__seamcall_ret, (_fn), (_args)) +#define seamcall_saved_ret(_fn, _args) sc_retry(__seamcall_saved_ret, (_fn), (_args)) +int tdx_cpu_enable(void); +int tdx_enable(void); +const char *tdx_dump_mce_info(struct mce *m); +#else +static inline void tdx_init(void) { } +static inline int tdx_cpu_enable(void) { return -ENODEV; } +static inline int tdx_enable(void) { return -ENODEV; } +static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; } #endif /* CONFIG_INTEL_TDX_HOST */ #endif /* !__ASSEMBLY__ */ diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h index 29832c338c..0b70653a98 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 b1c9cea6ba..1f1deaecd3 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 5fa76c2ced..ea877fd831 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 c81858d903..8e048ca980 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/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h index a908825077..64fbd2dbc5 100644 --- a/arch/x86/include/asm/xen/hypervisor.h +++ b/arch/x86/include/asm/xen/hypervisor.h @@ -62,6 +62,11 @@ void xen_arch_unregister_cpu(int num); #ifdef CONFIG_PVH void __init xen_pvh_init(struct boot_params *boot_params); void __init mem_map_via_hcall(struct boot_params *boot_params_p); +#ifdef CONFIG_XEN_PVH +void __init xen_reserve_extra_memory(struct boot_params *bootp); +#else +static inline void xen_reserve_extra_memory(struct boot_params *bootp) { } +#endif #endif /* Lazy mode for batching updates / context switch */ diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h index c599ec269a..c10f279aae 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 fce22686c8..e5d182c737 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/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h index 01d19fc223..eeea058cf6 100644 --- a/arch/x86/include/uapi/asm/bootparam.h +++ b/arch/x86/include/uapi/asm/bootparam.h @@ -38,6 +38,7 @@ #define XLF_EFI_KEXEC (1<<4) #define XLF_5LEVEL (1<<5) #define XLF_5LEVEL_ENABLED (1<<6) +#define XLF_MEM_ENCRYPTION (1<<7) #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 1a6a1f9879..a448d0964f 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -562,4 +562,7 @@ struct kvm_pmu_event_filter { /* x86-specific KVM_EXIT_HYPERCALL flags. */ #define KVM_EXIT_HYPERCALL_LONG_MODE BIT(0) +#define KVM_X86_DEFAULT_VM 0 +#define KVM_X86_SW_PROTECTED_VM 1 + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/uapi/asm/signal.h b/arch/x86/include/uapi/asm/signal.h index 777c3a0f4e..f777346450 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/alternative.c b/arch/x86/kernel/alternative.c index aae7456ece..1d85cb7071 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); @@ -395,6 +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(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. @@ -452,16 +509,21 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start, 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; @@ -842,15 +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; @@ -1159,8 +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) @@ -1421,46 +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. * @@ -1596,28 +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); @@ -1628,10 +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); /* @@ -1906,7 +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 56a917df41..2ae98f754e 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/aperture_64.c b/arch/x86/kernel/aperture_64.c index 4feaa670d5..89c0c8a3fc 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -259,10 +259,9 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) order); } - /* No multi-function device? */ type = read_pci_config_byte(bus, slot, func, PCI_HEADER_TYPE); - if (!(type & 0x80)) + if (!(type & PCI_HEADER_TYPE_MFD)) break; } } diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile index 2ee867d796..3bf0487cf3 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 41093cf20a..75bd5ac7ac 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 || @@ -1724,11 +1724,11 @@ static int x2apic_state; static bool x2apic_hw_locked(void) { - u64 ia32_cap; + u64 x86_arch_cap_msr; u64 msr; - ia32_cap = x86_read_arch_cap_msr(); - if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + x86_arch_cap_msr = x86_read_arch_cap_msr(); + if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) { rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); return (msr & LEGACY_XAPIC_DISABLED); } diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c index 7139867d69..b295a056a4 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 b00d52ae84..9f1d553eb4 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 456a14c44f..7d0c51b9d3 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 7ee3c486cb..5a0d60b38e 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 00da6cf6b0..40c7cf180c 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 5eb3fbe472..c0f78059f0 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 319448d87b..185738c727 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 a8306089c9..28a7d3f231 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 558a4a8824..409815a406 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 1b0d7336a2..f1766b18dc 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 5934ee5bc0..76a5ced278 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 e9ad518a50..64ad2ddea1 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 8674a5c0c0..e6bf78fac1 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 77a1ceb717..0838ea579e 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 +535,61 @@ 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; + + case 0x1a: + switch (c->x86_model) { + case 0x00 ... 0x2f: + case 0x40 ... 0x4f: + case 0x70 ... 0x7f: + setup_force_cpu_cap(X86_FEATURE_ZEN5); + 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 +713,6 @@ 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 +779,16 @@ 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 +822,17 @@ 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 +925,19 @@ 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 +948,28 @@ 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 +977,10 @@ 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 +1004,8 @@ 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 +1020,42 @@ 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_zen5(struct cpuinfo_x86 *c) +{ + init_amd_zen_common(); +} + static void init_amd(struct cpuinfo_x86 *c) { u64 vm_cr; @@ -1072,11 +1091,19 @@ 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); + else if (boot_cpu_has(X86_FEATURE_ZEN5)) + init_amd_zen5(c); + /* * Enable workaround for FXSAVE leak on CPUs * without a XSaveErPtr feature @@ -1136,7 +1163,7 @@ 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); @@ -1152,17 +1179,6 @@ 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); } @@ -1318,7 +1334,7 @@ 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) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 01ac18f561..e7ceee008b 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -61,6 +61,8 @@ EXPORT_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); +static u64 __ro_after_init x86_arch_cap_msr; + static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; @@ -144,6 +146,8 @@ void __init cpu_select_mitigations(void) x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; } + x86_arch_cap_msr = x86_read_arch_cap_msr(); + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -301,8 +305,6 @@ static const char * const taa_strings[] = { static void __init taa_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_OFF; return; @@ -341,9 +343,8 @@ static void __init taa_select_mitigation(void) * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode * update is required. */ - ia32_cap = x86_read_arch_cap_msr(); - if ( (ia32_cap & ARCH_CAP_MDS_NO) && - !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) && + !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)) taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* @@ -401,8 +402,6 @@ static const char * const mmio_strings[] = { static void __init mmio_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || cpu_mitigations_off()) { @@ -413,8 +412,6 @@ static void __init mmio_select_mitigation(void) if (mmio_mitigation == MMIO_MITIGATION_OFF) return; - ia32_cap = x86_read_arch_cap_msr(); - /* * Enable CPU buffer clear mitigation for host and VMM, if also affected * by MDS or TAA. Otherwise, enable mitigation for VMM only. @@ -437,7 +434,7 @@ static void __init mmio_select_mitigation(void) * be propagated to uncore buffers, clearing the Fill buffers on idle * is required irrespective of SMT state. */ - if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) static_branch_enable(&mds_idle_clear); /* @@ -447,10 +444,10 @@ static void __init mmio_select_mitigation(void) * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS * affected systems. */ - if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) || (boot_cpu_has(X86_FEATURE_MD_CLEAR) && boot_cpu_has(X86_FEATURE_FLUSH_L1D) && - !(ia32_cap & ARCH_CAP_MDS_NO))) + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))) mmio_mitigation = MMIO_MITIGATION_VERW; else mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; @@ -508,7 +505,7 @@ static void __init rfds_select_mitigation(void) if (rfds_mitigation == RFDS_MITIGATION_OFF) return; - if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; @@ -659,8 +656,6 @@ void update_srbds_msr(void) static void __init srbds_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; @@ -669,8 +664,7 @@ static void __init srbds_select_mitigation(void) * are only exposed to SRBDS when TSX is enabled or when CPU is affected * by Processor MMIO Stale Data vulnerability. */ - ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) @@ -813,7 +807,7 @@ static void __init gds_select_mitigation(void) /* Will verify below that mitigation _can_ be disabled */ /* No microcode */ - if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) { if (gds_mitigation == GDS_MITIGATION_FORCE) { /* * This only needs to be done on the boot CPU so do it @@ -1543,20 +1537,25 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +static bool __ro_after_init rrsba_disabled; + /* Disable in-kernel use of non-RSB RET predictors */ static void __init spec_ctrl_disable_kernel_rrsba(void) { - u64 ia32_cap; + if (rrsba_disabled) + return; - if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) { + rrsba_disabled = true; return; + } - ia32_cap = x86_read_arch_cap_msr(); + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; - if (ia32_cap & ARCH_CAP_RRSBA) { - x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - update_spec_ctrl(x86_spec_ctrl_base); - } + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + rrsba_disabled = true; } static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) @@ -1606,6 +1605,74 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + spec_ctrl_disable_kernel_rrsba(); + if (rrsba_disabled) + return; + } + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1717,6 +1784,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1831,8 +1901,6 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { - u64 ia32_cap = x86_read_arch_cap_msr(); - /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1847,7 +1915,7 @@ static void update_mds_branch_idle(void) if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || - (ia32_cap & ARCH_CAP_FBSDP_NO)) { + (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); } } @@ -2694,15 +2762,15 @@ static char *stibp_state(void) switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2711,10 +2779,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2724,14 +2792,32 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char *spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && + rrsba_disabled) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Vulnerable, KVM: SW loop"; + + return "; BHI: Vulnerable"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) @@ -2744,13 +2830,15 @@ static ssize_t spectre_v2_show_state(char *buf) spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sysfs_emit(buf, "%s%s%s%s%s%s%s\n", + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ spectre_v2_module_string()); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 97ea52a4e8..46603c6e40 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -66,6 +66,7 @@ #include <asm/set_memory.h> #include <asm/traps.h> #include <asm/sev.h> +#include <asm/tdx.h> #include "cpu.h" @@ -188,45 +189,37 @@ 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); @@ -1170,6 +1163,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1232,18 +1226,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1333,25 +1327,25 @@ static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long whi u64 x86_read_arch_cap_msr(void) { - u64 ia32_cap = 0; + u64 x86_arch_cap_msr = 0; if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr); - return ia32_cap; + return x86_arch_cap_msr; } -static bool arch_cap_mmio_immune(u64 ia32_cap) +static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr) { - return (ia32_cap & ARCH_CAP_FBSDP_NO && - ia32_cap & ARCH_CAP_PSDP_NO && - ia32_cap & ARCH_CAP_SBDR_SSDP_NO); + return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO && + x86_arch_cap_msr & ARCH_CAP_PSDP_NO && + x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO); } -static bool __init vulnerable_to_rfds(u64 ia32_cap) +static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) { /* The "immunity" bit trumps everything else: */ - if (ia32_cap & ARCH_CAP_RFDS_NO) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO) return false; /* @@ -1359,7 +1353,7 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap) * indicate that mitigation is needed because guest is running on a * vulnerable hardware or may migrate to such hardware: */ - if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) return true; /* Only consult the blacklist when there is no enumeration: */ @@ -1368,11 +1362,11 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap) static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { - u64 ia32_cap = x86_read_arch_cap_msr(); + u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && - !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) @@ -1384,7 +1378,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1392,15 +1386,15 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * AMD's AutoIBRS is equivalent to Intel's eIBRS - use the Intel feature * flag and protect from vendor-specific bugs via the whitelist. */ - if ((ia32_cap & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || cpu_has(c, X86_FEATURE_AUTOIBRS)) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && - !(ia32_cap & ARCH_CAP_MDS_NO)) { + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); @@ -1419,9 +1413,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * TSX_CTRL check alone is not sufficient for cases when the microcode * update is not present or running as guest that don't get TSX_CTRL. */ - if (!(ia32_cap & ARCH_CAP_TAA_NO) && + if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) && (cpu_has(c, X86_FEATURE_RTM) || - (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); /* @@ -1447,7 +1441,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (!arch_cap_mmio_immune(ia32_cap)) { + if (!arch_cap_mmio_immune(x86_arch_cap_msr)) { if (cpu_matches(cpu_vuln_blacklist, MMIO)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) @@ -1455,7 +1449,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { - if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA)) setup_force_cpu_bug(X86_BUG_RETBLEED); } @@ -1473,18 +1467,25 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * disabling AVX2. The only way to do this in HW is to clear XCR0[2], * which means that AVX will be disabled. */ - if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) && boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); - if (vulnerable_to_rfds(ia32_cap)) + if (vulnerable_to_rfds(x86_arch_cap_msr)) setup_force_cpu_bug(X86_BUG_RFDS); + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ - if (ia32_cap & ARCH_CAP_RDCL_NO) + if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); @@ -2026,6 +2027,7 @@ static __init void identify_boot_cpu(void) setup_cr_pinning(); tsx_init(); + tdx_init(); lkgs_init(); } diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index e462c1d380..6fb6d8a57c 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c index e4c3ba9132..f18d35fe27 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 f3517b8a8e..2b46eb0fdf 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 df8d25e744..c17f9403cf 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -53,6 +53,7 @@ #include <asm/mce.h> #include <asm/msr.h> #include <asm/reboot.h> +#include <asm/tdx.h> #include "internal.h" @@ -229,12 +230,20 @@ static void wait_for_panic(void) panic("Panicing machine check CPU died"); } +static const char *mce_dump_aux_info(struct mce *m) +{ + if (boot_cpu_has_bug(X86_BUG_TDX_PW_MCE)) + return tdx_dump_mce_info(m); + + return NULL; +} + 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; + const char *memmsg; /* * Allow instrumentation around external facilities usage. Not that it @@ -285,6 +294,11 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) } if (exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); + + memmsg = mce_dump_aux_info(final); + if (memmsg) + pr_emerg(HW_ERR "Machine check: %s\n", memmsg); + if (!fake_panic) { if (panic_timeout == 0) panic_timeout = mca_cfg.panic_timeout; @@ -297,6 +311,7 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) */ if (kexec_crash_loaded()) { if (final && (final->status & MCI_STATUS_ADDRV)) { + struct page *p; p = pfn_to_online_page(final->addr >> PAGE_SHIFT); if (p) SetPageHWPoison(p); @@ -686,6 +701,16 @@ 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; @@ -1617,13 +1642,6 @@ 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; @@ -1653,15 +1671,9 @@ 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. @@ -1671,23 +1683,29 @@ 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 */ @@ -2011,7 +2029,6 @@ 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) @@ -2024,7 +2041,6 @@ 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: { @@ -2458,12 +2474,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } @@ -2584,9 +2602,6 @@ 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; @@ -2681,8 +2696,6 @@ 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/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 52bce533dd..399b62e223 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 e13a26c9c0..01f8f03969 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 ef4e7bb5fd..89e31e1e5c 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 334972c097..857e608af6 100644 --- a/arch/x86/kernel/cpu/microcode/intel.c +++ b/arch/x86/kernel/cpu/microcode/intel.c @@ -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 2d6aa5d2e3..d3524778a5 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/scattered.c b/arch/x86/kernel/cpu/scattered.c index 0dad49a09b..0ebca40dfd 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c index 5d390df214..b65ab214bd 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 c92d88680d..b6b044356f 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/early-quirks.c b/arch/x86/kernel/early-quirks.c index a6c1867fc7..59f4aefc6b 100644 --- a/arch/x86/kernel/early-quirks.c +++ b/arch/x86/kernel/early-quirks.c @@ -779,13 +779,13 @@ static int __init check_dev_quirk(int num, int slot, int func) type = read_pci_config_byte(num, slot, func, PCI_HEADER_TYPE); - if ((type & 0x7f) == PCI_HEADER_TYPE_BRIDGE) { + if ((type & PCI_HEADER_TYPE_MASK) == PCI_HEADER_TYPE_BRIDGE) { sec = read_pci_config_byte(num, slot, func, PCI_SECONDARY_BUS); if (sec > num) early_pci_scan_bus(sec); } - if (!(type & 0x80)) + if (!(type & PCI_HEADER_TYPE_MFD)) return -1; return 0; diff --git a/arch/x86/kernel/fpu/bugs.c b/arch/x86/kernel/fpu/bugs.c index 794e701512..a06b876bbf 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 a21a4d0ecc..520deb411a 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 05a110c971..dc09560679 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 0f8103240f..d4918d03ef 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 diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 17adad4cbe..a38d0c93a6 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/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index a61c12c012..2a422e00ed 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/kvm.c b/arch/x86/kernel/kvm.c index 0ddb3bd0f1..428ee74002 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -434,7 +434,8 @@ static void __init sev_map_percpu_data(void) { int cpu; - if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) + if (cc_vendor != CC_VENDOR_AMD || + !cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; for_each_possible_cpu(cpu) { @@ -803,8 +804,8 @@ 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 +943,7 @@ 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 f2fff62557..5bb395551c 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 adc67f9881..7a814b4140 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 1a3e2c05a8..bc0a5348b4 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 5f71a0cf43..e18914c0e3 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/mpparse.c b/arch/x86/kernel/mpparse.c index 15c700d358..b223922248 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -196,12 +196,12 @@ static int __init smp_read_mpc(struct mpc_table *mpc, unsigned early) if (!smp_check_mpc(mpc, oem, str)) return 0; - if (early) { - /* Initialize the lapic mapping */ - if (!acpi_lapic) - register_lapic_address(mpc->lapic); + /* Initialize the lapic mapping */ + if (!acpi_lapic) + register_lapic_address(mpc->lapic); + + if (early) return 1; - } /* Now process the configuration blocks. */ while (count < mpc->length) { diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 97f1436c1a..5358d43886 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 b6f4e8399f..ab49ade31b 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/process_64.c b/arch/x86/kernel/process_64.c index 33b268747b..4989095ab7 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -138,7 +138,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, log_lvl, d3, d6, d7); } - if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + if (cr4 & X86_CR4_PKE) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index b002ebf024..3998109195 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -35,6 +35,7 @@ #include <asm/bios_ebda.h> #include <asm/bugs.h> #include <asm/cacheinfo.h> +#include <asm/coco.h> #include <asm/cpu.h> #include <asm/efi.h> #include <asm/gart.h> @@ -225,8 +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) @@ -260,7 +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", @@ -995,6 +994,7 @@ void __init setup_arch(char **cmdline_p) * memory size. */ mem_encrypt_setup_arch(); + cc_random_init(); efi_fake_memmap(); efi_find_mirror(); @@ -1032,6 +1032,8 @@ void __init setup_arch(char **cmdline_p) * * Moreover, on machines with SandyBridge graphics or in setups that use * crashkernel the entire 1M is reserved anyway. + * + * Note the host kernel TDX also requires the first 1MB being reserved. */ x86_platform.realmode_reserve(); diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 2c97bf7b56..b30d6e180d 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 466fe09898..be2fa2fc02 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -89,14 +89,15 @@ static bool __init sev_es_check_cpu_features(void) return true; } -static void __noreturn sev_es_terminate(unsigned int set, unsigned int reason) +static void __head __noreturn +sev_es_terminate(unsigned int set, unsigned int reason) { u64 val = GHCB_MSR_TERM_REQ; /* 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(); @@ -326,13 +327,7 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid */ static const struct snp_cpuid_table *snp_cpuid_get_table(void) { - void *ptr; - - asm ("lea cpuid_table_copy(%%rip), %0" - : "=r" (ptr) - : "p" (&cpuid_table_copy)); - - return ptr; + return &RIP_REL_REF(cpuid_table_copy); } /* @@ -391,7 +386,7 @@ static u32 snp_cpuid_calc_xsave_size(u64 xfeatures_en, bool compacted) return xsave_size; } -static bool +static bool __head snp_cpuid_get_validated_func(struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -528,7 +523,8 @@ static int snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt, * Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value * should be treated as fatal by caller. */ -static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) +static int __head +snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf) { const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table(); @@ -570,7 +566,7 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le * page yet, so it only supports the MSR based communication with the * hypervisor and only the CPUID exit-code. */ -void __init do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) +void __head do_vc_no_ghcb(struct pt_regs *regs, unsigned long exit_code) { unsigned int subfn = lower_bits(regs->cx, 32); unsigned int fn = lower_bits(regs->ax, 32); @@ -1016,7 +1012,8 @@ struct cc_setup_data { * Search for a Confidential Computing blob passed in as a setup_data entry * via the Linux Boot Protocol. */ -static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) +static __head +struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) { struct cc_setup_data *sd = NULL; struct setup_data *hdr; @@ -1043,7 +1040,7 @@ static struct cc_blob_sev_info *find_cc_blob_setup_data(struct boot_params *bp) * mapping needs to be updated in sync with all the changes to virtual memory * layout and related mapping facilities throughout the boot process. */ -static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) +static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info) { const struct snp_cpuid_table *cpuid_table_fw, *cpuid_table; int i; diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 0f58242b54..eb2873b5eb 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -26,6 +26,7 @@ #include <linux/dmi.h> #include <uapi/linux/sev-guest.h> +#include <asm/init.h> #include <asm/cpu_entry_area.h> #include <asm/stacktrace.h> #include <asm/sev.h> @@ -683,8 +684,9 @@ static u64 __init get_jump_table_addr(void) return ret; } -static void early_set_pages_state(unsigned long vaddr, unsigned long paddr, - unsigned long npages, enum psc_op op) +static void __head +early_set_pages_state(unsigned long vaddr, unsigned long paddr, + unsigned long npages, enum psc_op op) { unsigned long paddr_end; u64 val; @@ -740,7 +742,7 @@ e_term: sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC); } -void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, +void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr, unsigned long npages) { /* @@ -2045,7 +2047,7 @@ fail: * * Scan for the blob in that order. */ -static __init struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) +static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2071,7 +2073,7 @@ found_cc_info: return cc_info; } -bool __init snp_init(struct boot_params *bp) +bool __head snp_init(struct boot_params *bp) { struct cc_blob_sev_info *cc_info; @@ -2093,7 +2095,7 @@ bool __init snp_init(struct boot_params *bp) return true; } -void __init __noreturn snp_abort(void) +void __head __noreturn snp_abort(void) { sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED); } diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c index 65fe2094da..31b6f5dddf 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 2cc2aa120b..3f57ce68a3 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/topology.c b/arch/x86/kernel/topology.c index 0bab031300..d42c28b8bf 100644 --- a/arch/x86/kernel/topology.c +++ b/arch/x86/kernel/topology.c @@ -35,38 +35,9 @@ #include <asm/io_apic.h> #include <asm/cpu.h> -static DEFINE_PER_CPU(struct x86_cpu, cpu_devices); - #ifdef CONFIG_HOTPLUG_CPU -int arch_register_cpu(int cpu) +bool arch_cpu_is_hotpluggable(int cpu) { - struct x86_cpu *xc = per_cpu_ptr(&cpu_devices, cpu); - - xc->cpu.hotpluggable = cpu > 0; - return register_cpu(&xc->cpu, cpu); -} -EXPORT_SYMBOL(arch_register_cpu); - -void arch_unregister_cpu(int num) -{ - unregister_cpu(&per_cpu(cpu_devices, num).cpu); -} -EXPORT_SYMBOL(arch_unregister_cpu); -#else /* CONFIG_HOTPLUG_CPU */ - -int __init arch_register_cpu(int num) -{ - return register_cpu(&per_cpu(cpu_devices, num).cpu, num); + return cpu > 0; } #endif /* CONFIG_HOTPLUG_CPU */ - -static int __init topology_init(void) -{ - int i; - - for_each_present_cpu(i) - arch_register_cpu(i); - - return 0; -} -subsys_initcall(topology_init); diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 832f4413d9..c3b2f863ac 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> @@ -565,7 +566,7 @@ static bool fixup_iopl_exception(struct pt_regs *regs) */ static bool try_fixup_enqcmd_gp(void) { -#ifdef CONFIG_IOMMU_SVA +#ifdef CONFIG_ARCH_HAS_CPU_PASID u32 pasid; /* diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 54a5596ada..a349dbfc6d 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/Kconfig b/arch/x86/kvm/Kconfig index 950c12868d..65ed14b654 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -23,17 +23,15 @@ config KVM depends on HAVE_KVM depends on HIGH_RES_TIMERS depends on X86_LOCAL_APIC - select PREEMPT_NOTIFIERS - select MMU_NOTIFIER + select KVM_COMMON + select KVM_GENERIC_MMU_NOTIFIER select HAVE_KVM_IRQCHIP select HAVE_KVM_PFNCACHE - select HAVE_KVM_IRQFD select HAVE_KVM_DIRTY_RING_TSO select HAVE_KVM_DIRTY_RING_ACQ_REL select IRQ_BYPASS_MANAGER select HAVE_KVM_IRQ_BYPASS select HAVE_KVM_IRQ_ROUTING - select HAVE_KVM_EVENTFD select KVM_ASYNC_PF select USER_RETURN_NOTIFIER select KVM_MMIO @@ -46,7 +44,6 @@ config KVM select KVM_XFER_TO_GUEST_WORK select KVM_GENERIC_DIRTYLOG_READ_PROTECT select KVM_VFIO - select INTERVAL_TREE select HAVE_KVM_PM_NOTIFIER if PM select KVM_GENERIC_HARDWARE_ENABLING help @@ -65,18 +62,31 @@ config KVM config KVM_WERROR bool "Compile KVM with -Werror" - # KASAN may cause the build to fail due to larger frames - default y if X86_64 && !KASAN - # We use the dependency on !COMPILE_TEST to not be enabled - # blindly in allmodconfig or allyesconfig configurations - depends on KVM - depends on (X86_64 && !KASAN) || !COMPILE_TEST - depends on EXPERT + # Disallow KVM's -Werror if KASAN is enabled, e.g. to guard against + # randomized configs from selecting KVM_WERROR=y, which doesn't play + # nice with KASAN. KASAN builds generates warnings for the default + # FRAME_WARN, i.e. KVM_WERROR=y with KASAN=y requires special tuning. + # Building KVM with -Werror and KASAN is still doable via enabling + # the kernel-wide WERROR=y. + depends on KVM && EXPERT && !KASAN help Add -Werror to the build flags for KVM. If in doubt, say "N". +config KVM_SW_PROTECTED_VM + bool "Enable support for KVM software-protected VMs" + depends on EXPERT + depends on KVM && X86_64 + select KVM_GENERIC_PRIVATE_MEM + help + Enable support for KVM software-protected VMs. Currently, software- + protected VMs are purely a development and testing vehicle for + KVM_CREATE_GUEST_MEMFD. Attempting to run a "real" VM workload as a + software-protected VM will fail miserably. + + If unsure, say "N". + config KVM_INTEL tristate "KVM for Intel (and compatible) processors support" depends on KVM && IA32_FEAT_CTL @@ -129,6 +139,20 @@ config KVM_SMM If unsure, say Y. +config KVM_HYPERV + bool "Support for Microsoft Hyper-V emulation" + depends on KVM + default y + help + Provides KVM support for emulating Microsoft Hyper-V. This allows KVM + to expose a subset of the paravirtualized interfaces defined in the + Hyper-V Hypervisor Top-Level Functional Specification (TLFS): + https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs + These interfaces are required for the correct and performant functioning + of Windows and Hyper-V guests on KVM. + + If unsure, say "Y". + config KVM_XEN bool "Support for Xen hypercall interface" depends on KVM diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 80e3fe184d..475b5fa917 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -11,25 +11,27 @@ include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \ - hyperv.o debugfs.o mmu/mmu.o mmu/page_track.o \ + debugfs.o mmu/mmu.o mmu/page_track.o \ mmu/spte.o -ifdef CONFIG_HYPERV -kvm-y += kvm_onhyperv.o -endif - kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o +kvm-$(CONFIG_KVM_HYPERV) += hyperv.o kvm-$(CONFIG_KVM_XEN) += xen.o kvm-$(CONFIG_KVM_SMM) += smm.o kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \ - vmx/hyperv.o vmx/nested.o vmx/posted_intr.o + vmx/nested.o vmx/posted_intr.o + kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o +kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o \ - svm/sev.o svm/hyperv.o + svm/sev.o +kvm-amd-$(CONFIG_KVM_HYPERV) += svm/hyperv.o ifdef CONFIG_HYPERV +kvm-y += kvm_onhyperv.o +kvm-intel-y += vmx/vmx_onhyperv.o vmx/hyperv_evmcs.o kvm-amd-y += svm/svm_onhyperv.o endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 1811a9ddfe..3a02276899 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) @@ -314,11 +314,15 @@ EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) { +#ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, KVM_CPUID_INDEX_NOT_SIGNIFICANT); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; +#else + return false; +#endif } static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) @@ -362,6 +366,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); + vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); @@ -433,11 +438,13 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, return 0; } +#ifdef CONFIG_KVM_HYPERV if (kvm_cpuid_has_hyperv(e2, nent)) { r = kvm_hv_vcpu_init(vcpu); if (r) return r; } +#endif r = kvm_check_cpuid(vcpu, e2, nent); if (r) @@ -469,7 +476,7 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu, return -E2BIG; if (cpuid->nent) { - e = vmemdup_user(entries, array_size(sizeof(*e), cpuid->nent)); + e = vmemdup_array_user(entries, cpuid->nent, sizeof(*e)); if (IS_ERR(e)) return PTR_ERR(e); @@ -513,7 +520,7 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu, return -E2BIG; if (cpuid->nent) { - e2 = vmemdup_user(entries, array_size(sizeof(*e2), cpuid->nent)); + e2 = vmemdup_array_user(entries, cpuid->nent, sizeof(*e2)); if (IS_ERR(e2)) return PTR_ERR(e2); } @@ -671,7 +678,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_mask(CPUID_7_1_EAX, F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(FZRM) | F(FSRS) | F(FSRC) | - F(AMX_FP16) | F(AVX_IFMA) + F(AMX_FP16) | F(AVX_IFMA) | F(LAM) ); kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 0b90532b6e..23dbb9eb27 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -47,11 +47,6 @@ static inline bool kvm_vcpu_is_legal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) return !(gpa & vcpu->arch.reserved_gpa_bits); } -static inline bool kvm_vcpu_is_illegal_gpa(struct kvm_vcpu *vcpu, gpa_t gpa) -{ - return !kvm_vcpu_is_legal_gpa(vcpu, gpa); -} - static inline bool kvm_vcpu_is_legal_aligned_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, gpa_t alignment) { @@ -125,6 +120,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } +static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.is_amd_compatible; +} + +static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu) +{ + return !guest_cpuid_is_amd_compatible(vcpu); +} + static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; @@ -279,4 +284,12 @@ static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu, vcpu->arch.governed_features.enabled); } +static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) +{ + if (guest_can_use(vcpu, X86_FEATURE_LAM)) + cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57); + + return kvm_vcpu_is_legal_gpa(vcpu, cr3); +} + #endif diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c index eea6ea7f14..95ea1a1f74 100644 --- a/arch/x86/kvm/debugfs.c +++ b/arch/x86/kvm/debugfs.c @@ -111,7 +111,7 @@ static int kvm_mmu_rmaps_stat_show(struct seq_file *m, void *v) mutex_lock(&kvm->slots_lock); write_lock(&kvm->mmu_lock); - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { int bkt; slots = __kvm_memslots(kvm, i); diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 2673cd5c46..e223043ef5 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -687,8 +687,8 @@ static unsigned insn_alignment(struct x86_emulate_ctxt *ctxt, unsigned size) static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, struct segmented_address addr, unsigned *max_size, unsigned size, - bool write, bool fetch, - enum x86emul_mode mode, ulong *linear) + enum x86emul_mode mode, ulong *linear, + unsigned int flags) { struct desc_struct desc; bool usable; @@ -701,7 +701,7 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, *max_size = 0; switch (mode) { case X86EMUL_MODE_PROT64: - *linear = la; + *linear = la = ctxt->ops->get_untagged_addr(ctxt, la, flags); va_bits = ctxt_virt_addr_bits(ctxt); if (!__is_canonical_address(la, va_bits)) goto bad; @@ -717,11 +717,11 @@ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt, if (!usable) goto bad; /* code segment in protected mode or read-only data segment */ - if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) - || !(desc.type & 2)) && write) + if ((((ctxt->mode != X86EMUL_MODE_REAL) && (desc.type & 8)) || !(desc.type & 2)) && + (flags & X86EMUL_F_WRITE)) goto bad; /* unreadable code segment */ - if (!fetch && (desc.type & 8) && !(desc.type & 2)) + if (!(flags & X86EMUL_F_FETCH) && (desc.type & 8) && !(desc.type & 2)) goto bad; lim = desc_limit_scaled(&desc); if (!(desc.type & 8) && (desc.type & 4)) { @@ -757,8 +757,8 @@ static int linearize(struct x86_emulate_ctxt *ctxt, ulong *linear) { unsigned max_size; - return __linearize(ctxt, addr, &max_size, size, write, false, - ctxt->mode, linear); + return __linearize(ctxt, addr, &max_size, size, ctxt->mode, linear, + write ? X86EMUL_F_WRITE : 0); } static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) @@ -771,7 +771,8 @@ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst) if (ctxt->op_bytes != sizeof(unsigned long)) addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1); - rc = __linearize(ctxt, addr, &max_size, 1, false, true, ctxt->mode, &linear); + rc = __linearize(ctxt, addr, &max_size, 1, ctxt->mode, &linear, + X86EMUL_F_FETCH); if (rc == X86EMUL_CONTINUE) ctxt->_eip = addr.ea; return rc; @@ -907,8 +908,8 @@ static int __do_insn_fetch_bytes(struct x86_emulate_ctxt *ctxt, int op_size) * boundary check itself. Instead, we use max_size to check * against op_size. */ - rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode, - &linear); + rc = __linearize(ctxt, addr, &max_size, 0, ctxt->mode, &linear, + X86EMUL_F_FETCH); if (unlikely(rc != X86EMUL_CONTINUE)) return rc; @@ -3439,8 +3440,10 @@ static int em_invlpg(struct x86_emulate_ctxt *ctxt) { int rc; ulong linear; + unsigned int max_size; - rc = linearize(ctxt, ctxt->src.addr.mem, 1, false, &linear); + rc = __linearize(ctxt, ctxt->src.addr.mem, &max_size, 1, ctxt->mode, + &linear, X86EMUL_F_INVLPG); if (rc == X86EMUL_CONTINUE) ctxt->ops->invlpg(ctxt, linear); /* Disable writeback. */ diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h index 423a73395c..ad463b1ed4 100644 --- a/arch/x86/kvm/governed_features.h +++ b/arch/x86/kvm/governed_features.h @@ -16,6 +16,7 @@ KVM_GOVERNED_X86_FEATURE(PAUSEFILTER) KVM_GOVERNED_X86_FEATURE(PFTHRESHOLD) KVM_GOVERNED_X86_FEATURE(VGIF) KVM_GOVERNED_X86_FEATURE(VNMI) +KVM_GOVERNED_X86_FEATURE(LAM) #undef KVM_GOVERNED_X86_FEATURE #undef KVM_GOVERNED_FEATURE diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c index 4943f6b2bb..8a47f8541e 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1322,6 +1322,56 @@ static bool hv_check_msr_access(struct kvm_vcpu_hv *hv_vcpu, u32 msr) return false; } +#define KVM_HV_WIN2016_GUEST_ID 0x1040a00003839 +#define KVM_HV_WIN2016_GUEST_ID_MASK (~GENMASK_ULL(23, 16)) /* mask out the service version */ + +/* + * Hyper-V enabled Windows Server 2016 SMP VMs fail to boot in !XSAVES && XSAVEC + * configuration. + * Such configuration can result from, for example, AMD Erratum 1386 workaround. + * + * Print a notice so users aren't left wondering what's suddenly gone wrong. + */ +static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) +{ + struct kvm *kvm = vcpu->kvm; + struct kvm_hv *hv = to_kvm_hv(kvm); + + /* Check again under the hv_lock. */ + if (hv->xsaves_xsavec_checked) + return; + + if ((hv->hv_guest_os_id & KVM_HV_WIN2016_GUEST_ID_MASK) != + KVM_HV_WIN2016_GUEST_ID) + return; + + hv->xsaves_xsavec_checked = true; + + /* UP configurations aren't affected */ + if (atomic_read(&kvm->online_vcpus) < 2) + return; + + if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) || + !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC)) + return; + + pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. " + "If it fails to boot try disabling XSAVEC in the VM config.\n"); +} + +void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) +{ + struct kvm_hv *hv = to_kvm_hv(vcpu->kvm); + + if (!vcpu->arch.hyperv_enabled || + hv->xsaves_xsavec_checked) + return; + + mutex_lock(&hv->hv_lock); + __kvm_hv_xsaves_xsavec_maybe_warn(vcpu); + mutex_unlock(&hv->hv_lock); +} + static int kvm_hv_set_msr_pw(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host) { diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h index f83b8db72b..923e64903d 100644 --- a/arch/x86/kvm/hyperv.h +++ b/arch/x86/kvm/hyperv.h @@ -24,6 +24,8 @@ #include <linux/kvm_host.h> #include "x86.h" +#ifdef CONFIG_KVM_HYPERV + /* "Hv#1" signature */ #define HYPERV_CPUID_SIGNATURE_EAX 0x31237648 @@ -105,6 +107,17 @@ int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint); void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector); int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages); +static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) +{ + return to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->vec_bitmap); +} + +static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector) +{ + return to_hv_vcpu(vcpu) && + test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap); +} + void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu); bool kvm_hv_assist_page_enabled(struct kvm_vcpu *vcpu); @@ -169,6 +182,8 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm, struct pvclock_vcpu_time_info *hv_clock); void kvm_hv_request_tsc_page_update(struct kvm *kvm); +void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu); + void kvm_hv_init_vm(struct kvm *kvm); void kvm_hv_destroy_vm(struct kvm *kvm); int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu); @@ -236,6 +251,77 @@ static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) return kvm_hv_get_assist_page(vcpu); } +static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, + bool tdp_enabled) +{ + /* + * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or + * L2's VP_ID upon request from the guest. Make sure we check for + * pending entries in the right FIFO upon L1/L2 transition as these + * requests are put by other vCPUs asynchronously. + */ + if (to_hv_vcpu(vcpu) && tdp_enabled) + kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); +} + int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void kvm_hv_setup_tsc_page(struct kvm *kvm, + struct pvclock_vcpu_time_info *hv_clock) {} +static inline void kvm_hv_request_tsc_page_update(struct kvm *kvm) {} +static inline void kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) {} +static inline void kvm_hv_init_vm(struct kvm *kvm) {} +static inline void kvm_hv_destroy_vm(struct kvm *kvm) {} +static inline int kvm_hv_vcpu_init(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline void kvm_hv_vcpu_uninit(struct kvm_vcpu *vcpu) {} +static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_hypercall(struct kvm_vcpu *vcpu) +{ + return HV_STATUS_ACCESS_DENIED; +} +static inline void kvm_hv_vcpu_purge_flush_tlb(struct kvm_vcpu *vcpu) {} +static inline void kvm_hv_free_pa_page(struct kvm *kvm) {} +static inline bool kvm_hv_synic_has_vector(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline bool kvm_hv_synic_auto_eoi_set(struct kvm_vcpu *vcpu, int vector) +{ + return false; +} +static inline void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector) {} +static inline bool kvm_hv_invtsc_suppressed(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void kvm_hv_set_cpuid(struct kvm_vcpu *vcpu, bool hyperv_enabled) {} +static inline bool kvm_hv_has_stimer_pending(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool kvm_hv_is_tlb_flush_hcall(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline bool guest_hv_cpuid_has_l2_tlb_flush(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline int kvm_hv_verify_vp_assist(struct kvm_vcpu *vcpu) +{ + return 0; +} +static inline u32 kvm_hv_get_vpindex(struct kvm_vcpu *vcpu) +{ + return vcpu->vcpu_idx; +} +static inline void kvm_hv_nested_transtion_tlb_flush(struct kvm_vcpu *vcpu, bool tdp_enabled) {} +#endif /* CONFIG_KVM_HYPERV */ -#endif +#endif /* __ARCH_X86_KVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index b2c397dd2b..ad9ca8a601 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -118,8 +118,10 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v) if (!lapic_in_kernel(v)) return v->arch.interrupt.nr; +#ifdef CONFIG_KVM_XEN if (kvm_xen_has_interrupt(v)) return v->kvm->arch.xen.upcall_vector; +#endif if (irqchip_split(v->kvm)) { int vector = v->arch.pending_external_vector; diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 16d076a1b9..68f3f6c260 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -144,7 +144,7 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL); } - +#ifdef CONFIG_KVM_HYPERV static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, bool line_status) @@ -154,6 +154,7 @@ static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e, return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint); } +#endif int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm, int irq_source_id, int level, @@ -163,9 +164,11 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e, int r; switch (e->type) { +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: return kvm_hv_set_sint(e, kvm, irq_source_id, level, line_status); +#endif case KVM_IRQ_ROUTING_MSI: if (kvm_msi_route_invalid(kvm, e)) @@ -314,11 +317,13 @@ int kvm_set_routing_entry(struct kvm *kvm, if (kvm_msi_route_invalid(kvm, e)) return -EINVAL; break; +#ifdef CONFIG_KVM_HYPERV case KVM_IRQ_ROUTING_HV_SINT: e->set = kvm_hv_set_sint; e->hv_sint.vcpu = ue->u.hv_sint.vcpu; e->hv_sint.sint = ue->u.hv_sint.sint; break; +#endif #ifdef CONFIG_KVM_XEN case KVM_IRQ_ROUTING_XEN_EVTCHN: return kvm_xen_setup_evtchn(kvm, e, ue); @@ -438,5 +443,7 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu, void kvm_arch_irq_routing_update(struct kvm *kvm) { +#ifdef CONFIG_KVM_HYPERV kvm_hv_irq_routing_update(kvm); +#endif } diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index be7aeb9b8e..e6d1498251 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -88,6 +88,12 @@ struct x86_instruction_info { #define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ #define X86EMUL_INTERCEPTED 6 /* Intercepted by nested VMCB/VMCS */ +/* x86-specific emulation flags */ +#define X86EMUL_F_WRITE BIT(0) +#define X86EMUL_F_FETCH BIT(1) +#define X86EMUL_F_IMPLICIT BIT(2) +#define X86EMUL_F_INVLPG BIT(3) + struct x86_emulate_ops { void (*vm_bugged)(struct x86_emulate_ctxt *ctxt); /* @@ -224,6 +230,9 @@ struct x86_emulate_ops { int (*leave_smm)(struct x86_emulate_ctxt *ctxt); void (*triple_fault)(struct x86_emulate_ctxt *ctxt); int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr); + + gva_t (*get_untagged_addr)(struct x86_emulate_ctxt *ctxt, gva_t addr, + unsigned int flags); }; /* Type, address-of, and value of an instruction's operand. */ diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h index f9ca3e7432..eefab3dc84 100644 --- a/arch/x86/kvm/kvm_onhyperv.h +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -10,6 +10,26 @@ int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); int hv_flush_remote_tlbs(struct kvm *kvm); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp); +static inline hpa_t hv_get_partition_assist_page(struct kvm_vcpu *vcpu) +{ + /* + * Partition assist page is something which Hyper-V running in L0 + * requires from KVM running in L1 before direct TLB flush for L2 + * guests can be enabled. KVM doesn't currently use the page but to + * comply with TLFS it still needs to be allocated. For now, this + * is a single page shared among all vCPUs. + */ + struct hv_partition_assist_pg **p_hv_pa_pg = + &vcpu->kvm->arch.hv_pa_pg; + + if (!*p_hv_pa_pg) + *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); + + if (!*p_hv_pa_pg) + return INVALID_PAGE; + + return __pa(*p_hv_pa_pg); +} #else /* !CONFIG_HYPERV */ static inline int hv_flush_remote_tlbs(struct kvm *kvm) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 23fab75993..76fcee92b0 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1478,8 +1478,7 @@ static int apic_set_eoi(struct kvm_lapic *apic) apic_clear_isr(vector, apic); apic_update_ppr(apic); - if (to_hv_vcpu(apic->vcpu) && - test_bit(vector, to_hv_synic(apic->vcpu)->vec_bitmap)) + if (kvm_hv_synic_has_vector(apic->vcpu, vector)) kvm_hv_synic_send_eoi(apic->vcpu, vector); kvm_ioapic_send_eoi(apic, vector); @@ -2772,7 +2771,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); - if (r && lvt_type == APIC_LVTPC) + if (r && lvt_type == APIC_LVTPC && + guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } @@ -2908,7 +2908,7 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) */ apic_clear_irr(vector, apic); - if (to_hv_vcpu(vcpu) && test_bit(vector, to_hv_synic(vcpu)->auto_eoi_bitmap)) { + if (kvm_hv_synic_auto_eoi_set(vcpu, vector)) { /* * For auto-EOI interrupts, there might be another pending * interrupt above PPR, so check whether to raise another diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index bb8c86eefa..60f21bb4c2 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -146,6 +146,14 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) return kvm_get_pcid(vcpu, kvm_read_cr3(vcpu)); } +static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu) +{ + if (!guest_can_use(vcpu, X86_FEATURE_LAM)) + return 0; + + return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57); +} + static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) { u64 root_hpa = vcpu->arch.mmu->root.hpa; diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c57e181bba..982cf41e14 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -271,15 +271,11 @@ static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, static inline bool kvm_available_flush_remote_tlbs_range(void) { +#if IS_ENABLED(CONFIG_HYPERV) return kvm_x86_ops.flush_remote_tlbs_range; -} - -int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) -{ - if (!kvm_x86_ops.flush_remote_tlbs_range) - return -EOPNOTSUPP; - - return static_call(kvm_x86_flush_remote_tlbs_range)(kvm, gfn, nr_pages); +#else + return false; +#endif } static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); @@ -795,16 +791,26 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn, return &slot->arch.lpage_info[level - 2][idx]; } +/* + * The most significant bit in disallow_lpage tracks whether or not memory + * attributes are mixed, i.e. not identical for all gfns at the current level. + * The lower order bits are used to refcount other cases where a hugepage is + * disallowed, e.g. if KVM has shadow a page table at the gfn. + */ +#define KVM_LPAGE_MIXED_FLAG BIT(31) + static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot, gfn_t gfn, int count) { struct kvm_lpage_info *linfo; - int i; + int old, i; for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) { linfo = lpage_info_slot(gfn, slot, i); + + old = linfo->disallow_lpage; linfo->disallow_lpage += count; - WARN_ON_ONCE(linfo->disallow_lpage < 0); + WARN_ON_ONCE((old ^ linfo->disallow_lpage) & KVM_LPAGE_MIXED_FLAG); } } @@ -987,7 +993,7 @@ 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) @@ -1382,7 +1388,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, gfn_t end = slot->base_gfn + gfn_offset + __fls(mask); if (READ_ONCE(eager_page_split)) - kvm_mmu_try_split_huge_pages(kvm, slot, start, end, PG_LEVEL_4K); + kvm_mmu_try_split_huge_pages(kvm, slot, start, end + 1, PG_LEVEL_4K); kvm_mmu_slot_gfn_write_protect(kvm, slot, start, PG_LEVEL_2M); @@ -2840,9 +2846,9 @@ int mmu_try_to_unsync_pages(struct kvm *kvm, const struct kvm_memory_slot *slot, /* * Recheck after taking the spinlock, a different vCPU * may have since marked the page unsync. A false - * positive on the unprotected check above is not + * negative on the unprotected check above is not * possible as clearing sp->unsync _must_ hold mmu_lock - * for write, i.e. unsync cannot transition from 0->1 + * for write, i.e. unsync cannot transition from 1->0 * while this CPU holds mmu_lock for read (or write). */ if (READ_ONCE(sp->unsync)) @@ -3056,7 +3062,7 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) * * There are several ways to safely use this helper: * - * - Check mmu_invalidate_retry_hva() after grabbing the mapping level, before + * - Check mmu_invalidate_retry_gfn() after grabbing the mapping level, before * consuming it. In this case, mmu_lock doesn't need to be held during the * lookup, but it does need to be held while checking the MMU notifier. * @@ -3120,7 +3126,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, if (pud_none(pud) || !pud_present(pud)) goto out; - if (pud_large(pud)) { + if (pud_leaf(pud)) { level = PG_LEVEL_1G; goto out; } @@ -3137,9 +3143,9 @@ out: return level; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) +static int __kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, int max_level, bool is_private) { struct kvm_lpage_info *linfo; int host_level; @@ -3151,6 +3157,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, break; } + if (is_private) + return max_level; + if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; @@ -3158,6 +3167,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } +int kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn, + int max_level) +{ + bool is_private = kvm_slot_can_be_private(slot) && + kvm_mem_is_private(kvm, gfn); + + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private); +} + void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3178,8 +3197,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, - fault->gfn, fault->max_level); + fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->max_level, + fault->is_private); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -3556,7 +3576,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, return; if (is_tdp_mmu_page(sp)) - kvm_tdp_mmu_put_root(kvm, sp, false); + kvm_tdp_mmu_put_root(kvm, sp); else if (!--sp->root_count && sp->role.invalid) kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); @@ -3739,7 +3759,7 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm) kvm_page_track_write_tracking_enabled(kvm)) goto out_success; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(slot, bkt, slots) { /* @@ -3782,7 +3802,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) hpa_t root; root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); - root_gfn = root_pgd >> PAGE_SHIFT; + root_gfn = (root_pgd & __PT_BASE_ADDR_MASK) >> PAGE_SHIFT; if (!kvm_vcpu_is_visible_gfn(vcpu, root_gfn)) { mmu->root.hpa = kvm_mmu_get_dummy_root(); @@ -4259,6 +4279,55 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); } +static inline u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) + return PG_LEVEL_1G; + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int max_order, r; + + if (!kvm_slot_can_be_private(fault->slot)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, + &max_order); + if (r) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return r; + } + + fault->max_level = min(kvm_max_level_for_order(max_order), + fault->max_level); + fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); + + return RET_PF_CONTINUE; +} + static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -4291,6 +4360,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_EMULATE; } + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (fault->is_private) + return kvm_faultin_pfn_private(vcpu, fault); + async = false; fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, @@ -4328,6 +4405,31 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, fault->mmu_seq = vcpu->kvm->mmu_invalidate_seq; smp_rmb(); + /* + * Check for a relevant mmu_notifier invalidation event before getting + * the pfn from the primary MMU, and before acquiring mmu_lock. + * + * For mmu_lock, if there is an in-progress invalidation and the kernel + * allows preemption, the invalidation task may drop mmu_lock and yield + * in response to mmu_lock being contended, which is *very* counter- + * productive as this vCPU can't actually make forward progress until + * the invalidation completes. + * + * Retrying now can also avoid unnessary lock contention in the primary + * MMU, as the primary MMU doesn't necessarily hold a single lock for + * the duration of the invalidation, i.e. faulting in a conflicting pfn + * can cause the invalidation to take longer by holding locks that are + * needed to complete the invalidation. + * + * Do the pre-check even for non-preemtible kernels, i.e. even if KVM + * will never yield mmu_lock in response to contention, as this vCPU is + * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held + * to detect retry guarantees the worst case latency for the vCPU. + */ + if (fault->slot && + mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + return RET_PF_RETRY; + ret = __kvm_faultin_pfn(vcpu, fault); if (ret != RET_PF_CONTINUE) return ret; @@ -4338,6 +4440,18 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (unlikely(!fault->slot)) return kvm_handle_noslot_fault(vcpu, fault, access); + /* + * Check again for a relevant mmu_notifier invalidation event purely to + * avoid contending mmu_lock. Most invalidations will be detected by + * the previous check, but checking is extremely cheap relative to the + * overall cost of failing to detect the invalidation until after + * mmu_lock is acquired. + */ + if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) { + kvm_release_pfn_clean(fault->pfn); + return RET_PF_RETRY; + } + return RET_PF_CONTINUE; } @@ -4365,8 +4479,13 @@ static bool is_page_fault_stale(struct kvm_vcpu *vcpu, if (!sp && kvm_test_request(KVM_REQ_MMU_FREE_OBSOLETE_ROOTS, vcpu)) return true; + /* + * Check for a relevant mmu_notifier invalidation event one last time + * now that mmu_lock is held, as the "unsafe" checks performed without + * holding mmu_lock can get false negatives. + */ return fault->slot && - mmu_invalidate_retry_hva(vcpu->kvm, fault->mmu_seq, fault->hva); + mmu_invalidate_retry_gfn(vcpu->kvm, fault->mmu_seq, fault->gfn); } static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -4803,7 +4922,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, context->cpu_role.base.level, is_efer_nx(context), guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), - guest_cpuid_is_amd_or_hygon(vcpu)); + guest_cpuid_is_amd_compatible(vcpu)); } static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, @@ -6228,7 +6347,7 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (!kvm_memslots_have_rmaps(kvm)) return flush; - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, gfn_start, gfn_end) { @@ -6260,7 +6379,9 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) write_lock(&kvm->mmu_lock); - kvm_mmu_invalidate_begin(kvm, 0, -1ul); + kvm_mmu_invalidate_begin(kvm); + + kvm_mmu_invalidate_range_add(kvm, gfn_start, gfn_end); flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end); @@ -6270,7 +6391,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) if (flush) kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); - kvm_mmu_invalidate_end(kvm, 0, -1ul); + kvm_mmu_invalidate_end(kvm); write_unlock(&kvm->mmu_lock); } @@ -6544,7 +6665,7 @@ 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(). */ } @@ -6723,7 +6844,7 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) * modifier prior to checking for a wrap of the MMIO generation so * that a wrap in any address space is detected. */ - gen &= ~((u64)KVM_ADDRESS_SPACE_NUM - 1); + gen &= ~((u64)kvm_arch_nr_memslot_as_ids(kvm) - 1); /* * The very rare case: if the MMIO generation number has wrapped, @@ -7176,3 +7297,164 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) if (kvm->arch.nx_huge_page_recovery_thread) kthread_stop(kvm->arch.nx_huge_page_recovery_thread); } + +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * Zap SPTEs even if the slot can't be mapped PRIVATE. KVM x86 only + * supports KVM_MEMORY_ATTRIBUTE_PRIVATE, and so it *seems* like KVM + * can simply ignore such slots. But if userspace is making memory + * PRIVATE, then KVM must prevent the guest from accessing the memory + * as shared. And if userspace is making memory SHARED and this point + * is reached, then at least one page within the range was previously + * PRIVATE, i.e. the slot's possible hugepage ranges are changing. + * Zapping SPTEs in this case ensures KVM will reassess whether or not + * a hugepage can be used for affected ranges. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + return kvm_unmap_gfn_range(kvm, range); +} + +static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + return lpage_info_slot(gfn, slot, level)->disallow_lpage & KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_clear_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage &= ~KVM_LPAGE_MIXED_FLAG; +} + +static void hugepage_set_mixed(struct kvm_memory_slot *slot, gfn_t gfn, + int level) +{ + lpage_info_slot(gfn, slot, level)->disallow_lpage |= KVM_LPAGE_MIXED_FLAG; +} + +static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, int level, unsigned long attrs) +{ + const unsigned long start = gfn; + const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); + + if (level == PG_LEVEL_2M) + return kvm_range_has_memory_attributes(kvm, start, end, attrs); + + for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { + if (hugepage_test_mixed(slot, gfn, level - 1) || + attrs != kvm_get_memory_attributes(kvm, gfn)) + return false; + } + return true; +} + +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + unsigned long attrs = range->arg.attributes; + struct kvm_memory_slot *slot = range->slot; + int level; + + lockdep_assert_held_write(&kvm->mmu_lock); + lockdep_assert_held(&kvm->slots_lock); + + /* + * Calculate which ranges can be mapped with hugepages even if the slot + * can't map memory PRIVATE. KVM mustn't create a SHARED hugepage over + * a range that has PRIVATE GFNs, and conversely converting a range to + * SHARED may now allow hugepages. + */ + if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) + return false; + + /* + * The sequence matters here: upper levels consume the result of lower + * level's scanning. + */ + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn = gfn_round_for_level(range->start, level); + + /* Process the head page if it straddles the range. */ + if (gfn != range->start || gfn + nr_pages > range->end) { + /* + * Skip mixed tracking if the aligned gfn isn't covered + * by the memslot, KVM can't use a hugepage due to the + * misaligned address regardless of memory attributes. + */ + if (gfn >= slot->base_gfn && + gfn + nr_pages <= slot->base_gfn + slot->npages) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + gfn += nr_pages; + } + + /* + * Pages entirely covered by the range are guaranteed to have + * only the attributes which were just set. + */ + for ( ; gfn + nr_pages <= range->end; gfn += nr_pages) + hugepage_clear_mixed(slot, gfn, level); + + /* + * Process the last tail page if it straddles the range and is + * contained by the memslot. Like the head page, KVM can't + * create a hugepage if the slot size is misaligned. + */ + if (gfn < range->end && + (gfn + nr_pages) <= (slot->base_gfn + slot->npages)) { + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } + return false; +} + +void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm, + struct kvm_memory_slot *slot) +{ + int level; + + if (!kvm_arch_has_private_mem(kvm)) + return; + + for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) { + /* + * Don't bother tracking mixed attributes for pages that can't + * be huge due to alignment, i.e. process only pages that are + * entirely contained by the memslot. + */ + gfn_t end = gfn_round_for_level(slot->base_gfn + slot->npages, level); + gfn_t start = gfn_round_for_level(slot->base_gfn, level); + gfn_t nr_pages = KVM_PAGES_PER_HPAGE(level); + gfn_t gfn; + + if (start < slot->base_gfn) + start += nr_pages; + + /* + * Unlike setting attributes, every potential hugepage needs to + * be manually checked as the attributes may already be mixed. + */ + for (gfn = start; gfn < end; gfn += nr_pages) { + unsigned long attrs = kvm_get_memory_attributes(kvm, gfn); + + if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) + hugepage_clear_mixed(slot, gfn, level); + else + hugepage_set_mixed(slot, gfn, level); + } + } +} +#endif diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index decc1f1536..0669a8a668 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -13,6 +13,7 @@ #endif /* Page table builder macros common to shadow (host) PTEs and guest PTEs. */ +#define __PT_BASE_ADDR_MASK GENMASK_ULL(51, 12) #define __PT_LEVEL_SHIFT(level, bits_per_level) \ (PAGE_SHIFT + ((level) - 1) * (bits_per_level)) #define __PT_INDEX(address, level, bits_per_level) \ @@ -201,6 +202,7 @@ struct kvm_page_fault { /* Derived from mmu and global state. */ const bool is_tdp; + const bool is_private; const bool nx_huge_page_workaround_enabled; /* @@ -296,6 +298,7 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, .max_level = KVM_MAX_HUGEPAGE_LEVEL, .req_level = PG_LEVEL_4K, .goal_level = PG_LEVEL_4K, + .is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT), }; int r; diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index c85255073f..4d4e98fe4f 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -62,7 +62,7 @@ #endif /* Common logic, but per-type values. These also need to be undefined. */ -#define PT_BASE_ADDR_MASK ((pt_element_t)(((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))) +#define PT_BASE_ADDR_MASK ((pt_element_t)__PT_BASE_ADDR_MASK) #define PT_LVL_ADDR_MASK(lvl) __PT_LVL_ADDR_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_LVL_OFFSET_MASK(lvl) __PT_LVL_OFFSET_MASK(PT_BASE_ADDR_MASK, lvl, PT_LEVEL_BITS) #define PT_INDEX(addr, lvl) __PT_INDEX(addr, lvl, PT_LEVEL_BITS) diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index bd30ebfb2f..04c247bfe3 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/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 6cd4dd631a..953082bf96 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -73,11 +73,8 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head) tdp_mmu_free_sp(sp); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared) +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) { - kvm_lockdep_assert_mmu_lock_held(kvm, shared); - if (!refcount_dec_and_test(&root->tdp_mmu_root_count)) return; @@ -106,10 +103,16 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool shared, bool only_valid) + bool only_valid) { struct kvm_mmu_page *next_root; + /* + * While the roots themselves are RCU-protected, fields such as + * role.invalid are protected by mmu_lock. + */ + lockdep_assert_held(&kvm->mmu_lock); + rcu_read_lock(); if (prev_root) @@ -132,7 +135,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, rcu_read_unlock(); if (prev_root) - kvm_tdp_mmu_put_root(kvm, prev_root, shared); + kvm_tdp_mmu_put_root(kvm, prev_root); return next_root; } @@ -144,26 +147,22 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * recent root. (Unless keeping a live reference is desirable.) * * If shared is set, this function is operating under the MMU lock in read - * mode. In the unlikely event that this thread must free a root, the lock - * will be temporarily dropped and reacquired in write mode. + * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, _only_valid)\ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, _only_valid); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, _only_valid)) \ - if (kvm_lockdep_assert_mmu_lock_held(_kvm, _shared) && \ - kvm_mmu_page_as_id(_root) != _as_id) { \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid)\ + for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + if (kvm_mmu_page_as_id(_root) != _as_id) { \ } else -#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true) +#define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true) -#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false); \ - _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _shared, false)) \ - if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) { \ - } else +#define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ + _root = tdp_mmu_next_root(_kvm, _root, false)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -276,28 +275,18 @@ static void tdp_unaccount_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) * * @kvm: kvm instance * @sp: the page to be removed - * @shared: This operation may not be running under the exclusive use of - * the MMU lock and the operation must synchronize with other - * threads that might be adding or removing pages. */ -static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp, - bool shared) +static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) { tdp_unaccount_mmu_page(kvm, sp); if (!sp->nx_huge_page_disallowed) return; - if (shared) - spin_lock(&kvm->arch.tdp_mmu_pages_lock); - else - lockdep_assert_held_write(&kvm->mmu_lock); - + spin_lock(&kvm->arch.tdp_mmu_pages_lock); sp->nx_huge_page_disallowed = false; untrack_possible_nx_huge_page(kvm, sp); - - if (shared) - spin_unlock(&kvm->arch.tdp_mmu_pages_lock); + spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } /** @@ -326,7 +315,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) trace_kvm_mmu_prepare_zap_page(sp); - tdp_mmu_unlink_sp(kvm, sp, shared); + tdp_mmu_unlink_sp(kvm, sp); for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { tdp_ptep_t sptep = pt + i; @@ -832,7 +821,8 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush) { struct kvm_mmu_page *root; - for_each_tdp_mmu_root_yield_safe(kvm, root, false) + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush); return flush; @@ -854,7 +844,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ - for_each_tdp_mmu_root_yield_safe(kvm, root, false) + lockdep_assert_held_write(&kvm->mmu_lock); + for_each_tdp_mmu_root_yield_safe(kvm, root) tdp_mmu_zap_root(kvm, root, false); } @@ -868,7 +859,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) read_lock(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root, true) { + for_each_tdp_mmu_root_yield_safe(kvm, root) { if (!root->tdp_mmu_scheduled_root_to_zap) continue; @@ -891,7 +882,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * the root must be reachable by mmu_notifiers while it's being * zapped */ - kvm_tdp_mmu_put_root(kvm, root, true); + kvm_tdp_mmu_put_root(kvm, root); } read_unlock(&kvm->mmu_lock); @@ -1125,7 +1116,7 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false) + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); @@ -1314,7 +1305,7 @@ bool kvm_tdp_mmu_wrprot_slot(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= wrprot_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages, min_level); @@ -1346,6 +1337,8 @@ static struct kvm_mmu_page *tdp_mmu_alloc_sp_for_split(struct kvm *kvm, { struct kvm_mmu_page *sp; + kvm_lockdep_assert_mmu_lock_held(kvm, shared); + /* * Since we are allocating while under the MMU lock we have to be * careful about GFP flags. Use GFP_NOWAIT to avoid blocking on direct @@ -1496,16 +1489,25 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, int r = 0; kvm_lockdep_assert_mmu_lock_held(kvm, shared); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, shared) { + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) { r = tdp_mmu_split_huge_pages_root(kvm, root, start, end, target_level, shared); if (r) { - kvm_tdp_mmu_put_root(kvm, root, shared); + kvm_tdp_mmu_put_root(kvm, root); break; } } } +static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) +{ + /* + * All TDP MMU shadow pages share the same role as their root, aside + * from level, so it is valid to key off any shadow page to determine if + * write protection is needed for an entire tree. + */ + return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); +} + /* * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. @@ -1516,21 +1518,23 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { - u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; + const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; bool spte_set = false; rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, start, end) { + tdp_root_for_each_pte(iter, root, start, end) { retry: - if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) + if (!is_shadow_present_pte(iter.old_spte) || + !is_last_spte(iter.old_spte, iter.level)) continue; - if (!is_shadow_present_pte(iter.old_spte)) + if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) @@ -1560,8 +1564,7 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, bool spte_set = false; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) spte_set |= clear_dirty_gfn_range(kvm, root, slot->base_gfn, slot->base_gfn + slot->npages); @@ -1578,8 +1581,8 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { - u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : - shadow_dirty_mask; + const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; lockdep_assert_held_write(&kvm->mmu_lock); @@ -1591,7 +1594,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || @@ -1695,8 +1698,7 @@ void kvm_tdp_mmu_zap_collapsible_sptes(struct kvm *kvm, struct kvm_mmu_page *root; lockdep_assert_held_read(&kvm->mmu_lock); - - for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id, true) + for_each_valid_tdp_mmu_root_yield_safe(kvm, root, slot->as_id) zap_collapsible_spte_range(kvm, root, slot); } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 733a3aef3a..20d97aa46c 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -17,8 +17,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) return refcount_inc_not_zero(&root->tdp_mmu_root_count); } -void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root, - bool shared); +void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index dc8e8e907c..2ab2d5213f 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -127,9 +127,9 @@ static void kvm_perf_overflow(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; /* - * Ignore overflow events for counters that are scheduled to be - * reprogrammed, e.g. if a PMI for the previous event races with KVM's - * handling of a related guest WRMSR. + * Ignore asynchronous overflow events for counters that are scheduled + * to be reprogrammed, e.g. if a PMI for the previous event races with + * KVM's handling of a related guest WRMSR. */ if (test_and_set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi)) return; @@ -161,6 +161,15 @@ static u64 pmc_get_pebs_precise_level(struct kvm_pmc *pmc) return 1; } +static u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) +{ + u64 sample_period = (-counter_value) & pmc_bitmask(pmc); + + if (!sample_period) + sample_period = pmc_bitmask(pmc) + 1; + return sample_period; +} + static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, bool exclude_user, bool exclude_kernel, bool intr) @@ -215,17 +224,30 @@ static int pmc_reprogram_counter(struct kvm_pmc *pmc, u32 type, u64 config, return 0; } -static void pmc_pause_counter(struct kvm_pmc *pmc) +static bool pmc_pause_counter(struct kvm_pmc *pmc) { u64 counter = pmc->counter; - - if (!pmc->perf_event || pmc->is_paused) - return; + u64 prev_counter; /* update counter, reset event value to avoid redundant accumulation */ - counter += perf_event_pause(pmc->perf_event, true); + if (pmc->perf_event && !pmc->is_paused) + counter += perf_event_pause(pmc->perf_event, true); + + /* + * Snapshot the previous counter *after* accumulating state from perf. + * If overflow already happened, hardware (via perf) is responsible for + * generating a PMI. KVM just needs to detect overflow on emulated + * counter events that haven't yet been processed. + */ + prev_counter = counter & pmc_bitmask(pmc); + + counter += pmc->emulated_counter; pmc->counter = counter & pmc_bitmask(pmc); + + pmc->emulated_counter = 0; pmc->is_paused = true; + + return pmc->counter < prev_counter; } static bool pmc_resume_counter(struct kvm_pmc *pmc) @@ -268,6 +290,33 @@ static void pmc_stop_counter(struct kvm_pmc *pmc) } } +static void pmc_update_sample_period(struct kvm_pmc *pmc) +{ + if (!pmc->perf_event || pmc->is_paused || + !is_sampling_event(pmc->perf_event)) + return; + + perf_event_period(pmc->perf_event, + get_sample_period(pmc, pmc->counter)); +} + +void pmc_write_counter(struct kvm_pmc *pmc, u64 val) +{ + /* + * Drop any unconsumed accumulated counts, the WRMSR is a write, not a + * read-modify-write. Adjust the counter value so that its value is + * relative to the current count, as reading the current count from + * perf is faster than pausing and repgrogramming the event in order to + * reset it to '0'. Note, this very sneakily offsets the accumulated + * emulated count too, by using pmc_read_counter()! + */ + pmc->emulated_counter = 0; + pmc->counter += val - pmc_read_counter(pmc); + pmc->counter &= pmc_bitmask(pmc); + pmc_update_sample_period(pmc); +} +EXPORT_SYMBOL_GPL(pmc_write_counter); + static int filter_cmp(const void *pa, const void *pb, u64 mask) { u64 a = *(u64 *)pa & mask; @@ -401,14 +450,15 @@ static void reprogram_counter(struct kvm_pmc *pmc) struct kvm_pmu *pmu = pmc_to_pmu(pmc); u64 eventsel = pmc->eventsel; u64 new_config = eventsel; + bool emulate_overflow; u8 fixed_ctr_ctrl; - pmc_pause_counter(pmc); + emulate_overflow = pmc_pause_counter(pmc); if (!pmc_event_is_allowed(pmc)) goto reprogram_complete; - if (pmc->counter < pmc->prev_counter) + if (emulate_overflow) __kvm_perf_overflow(pmc, false); if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL) @@ -448,7 +498,6 @@ static void reprogram_counter(struct kvm_pmc *pmc) reprogram_complete: clear_bit(pmc->idx, (unsigned long *)&pmc_to_pmu(pmc)->reprogram_pmi); - pmc->prev_counter = 0; } void kvm_pmu_handle_event(struct kvm_vcpu *vcpu) @@ -657,7 +706,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 0; } -void kvm_pmu_reset(struct kvm_vcpu *vcpu) +static void kvm_pmu_reset(struct kvm_vcpu *vcpu) { struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); struct kvm_pmc *pmc; @@ -674,6 +723,7 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) pmc_stop_counter(pmc); pmc->counter = 0; + pmc->emulated_counter = 0; if (pmc_is_gp(pmc)) pmc->eventsel = 0; @@ -691,6 +741,8 @@ void kvm_pmu_reset(struct kvm_vcpu *vcpu) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { + struct kvm_pmu *pmu = vcpu_to_pmu(vcpu); + if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm)) return; @@ -700,8 +752,34 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) */ kvm_pmu_reset(vcpu); - bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); + pmu->version = 0; + pmu->nr_arch_gp_counters = 0; + pmu->nr_arch_fixed_counters = 0; + pmu->counter_bitmask[KVM_PMC_GP] = 0; + pmu->counter_bitmask[KVM_PMC_FIXED] = 0; + pmu->reserved_bits = 0xffffffff00200000ull; + pmu->raw_event_mask = X86_RAW_EVENT_MASK; + pmu->global_ctrl_mask = ~0ull; + pmu->global_status_mask = ~0ull; + pmu->fixed_ctr_ctrl_mask = ~0ull; + pmu->pebs_enable_mask = ~0ull; + pmu->pebs_data_cfg_mask = ~0ull; + bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); + + if (!vcpu->kvm->arch.enable_pmu) + return; + static_call(kvm_x86_pmu_refresh)(vcpu); + + /* + * At RESET, both Intel and AMD CPUs set all enable bits for general + * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that + * was written for v1 PMUs don't unknowingly leave GP counters disabled + * in the global controls). Emulate that behavior when refreshing the + * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL. + */ + if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters) + pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0); } void kvm_pmu_init(struct kvm_vcpu *vcpu) @@ -710,8 +788,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); static_call(kvm_x86_pmu_init)(vcpu); - pmu->event_count = 0; - pmu->need_cleanup = false; kvm_pmu_refresh(vcpu); } @@ -747,8 +823,7 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu) static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) { - pmc->prev_counter = pmc->counter; - pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); + pmc->emulated_counter++; kvm_pmu_request_counter_reprogram(pmc); } diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index a46aa9b251..7caeb3d8d4 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -66,7 +66,8 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) { u64 counter, enabled, running; - counter = pmc->counter; + counter = pmc->counter + pmc->emulated_counter; + if (pmc->perf_event && !pmc->is_paused) counter += perf_event_read_value(pmc->perf_event, &enabled, &running); @@ -74,11 +75,7 @@ static inline u64 pmc_read_counter(struct kvm_pmc *pmc) return counter & pmc_bitmask(pmc); } -static inline void pmc_write_counter(struct kvm_pmc *pmc, u64 val) -{ - pmc->counter += val - pmc_read_counter(pmc); - pmc->counter &= pmc_bitmask(pmc); -} +void pmc_write_counter(struct kvm_pmc *pmc, u64 val); static inline bool pmc_is_gp(struct kvm_pmc *pmc) { @@ -128,25 +125,6 @@ static inline struct kvm_pmc *get_fixed_pmc(struct kvm_pmu *pmu, u32 msr) return NULL; } -static inline u64 get_sample_period(struct kvm_pmc *pmc, u64 counter_value) -{ - u64 sample_period = (-counter_value) & pmc_bitmask(pmc); - - if (!sample_period) - sample_period = pmc_bitmask(pmc) + 1; - return sample_period; -} - -static inline void pmc_update_sample_period(struct kvm_pmc *pmc) -{ - if (!pmc->perf_event || pmc->is_paused || - !is_sampling_event(pmc->perf_event)) - return; - - perf_event_period(pmc->perf_event, - get_sample_period(pmc, pmc->counter)); -} - static inline bool pmc_speculative_in_use(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -243,7 +221,6 @@ bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr); int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info); void kvm_pmu_refresh(struct kvm_vcpu *vcpu); -void kvm_pmu_reset(struct kvm_vcpu *vcpu); void kvm_pmu_init(struct kvm_vcpu *vcpu); void kvm_pmu_cleanup(struct kvm_vcpu *vcpu); void kvm_pmu_destroy(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index aadefcaa95..2f4e155080 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -52,7 +52,7 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) #define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) #define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) -#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) #define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) /* CPUID level 0x80000007 (EDX). */ @@ -102,10 +102,12 @@ static const struct cpuid_reg reverse_cpuid[] = { */ static __always_inline void reverse_cpuid_check(unsigned int x86_leaf) { + BUILD_BUG_ON(NR_CPUID_WORDS != NCAPINTS); BUILD_BUG_ON(x86_leaf == CPUID_LNX_1); BUILD_BUG_ON(x86_leaf == CPUID_LNX_2); BUILD_BUG_ON(x86_leaf == CPUID_LNX_3); BUILD_BUG_ON(x86_leaf == CPUID_LNX_4); + BUILD_BUG_ON(x86_leaf == CPUID_LNX_5); BUILD_BUG_ON(x86_leaf >= ARRAY_SIZE(reverse_cpuid)); BUILD_BUG_ON(reverse_cpuid[x86_leaf].function == 0); } @@ -126,6 +128,7 @@ static __always_inline u32 __feature_translate(int x86_feature) KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); default: return x86_feature; } diff --git a/arch/x86/kvm/svm/hyperv.h b/arch/x86/kvm/svm/hyperv.h index 02f4784b5d..d3f8bfc058 100644 --- a/arch/x86/kvm/svm/hyperv.h +++ b/arch/x86/kvm/svm/hyperv.h @@ -11,6 +11,7 @@ #include "../hyperv.h" #include "svm.h" +#ifdef CONFIG_KVM_HYPERV static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -41,5 +42,13 @@ static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) } void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else /* CONFIG_KVM_HYPERV */ +static inline void nested_svm_hv_update_vm_vp_ids(struct kvm_vcpu *vcpu) {} +static inline bool nested_svm_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu) +{ + return false; +} +static inline void svm_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu) {} +#endif /* CONFIG_KVM_HYPERV */ #endif /* __ARCH_X86_KVM_SVM_HYPERV_H__ */ diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 60891b9ce2..dee62362a3 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -187,7 +187,6 @@ void recalc_intercepts(struct vcpu_svm *svm) */ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) { - struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; int i; /* @@ -198,11 +197,16 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) * - Nested hypervisor (L1) is using Hyper-V emulation interface and * tells KVM (L0) there were no changes in MSR bitmap for L2. */ - if (!svm->nested.force_msr_bitmap_recalc && - kvm_hv_hypercall_enabled(&svm->vcpu) && - hve->hv_enlightenments_control.msr_bitmap && - (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) - goto set_msrpm_base_pa; +#ifdef CONFIG_KVM_HYPERV + if (!svm->nested.force_msr_bitmap_recalc) { + struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments; + + if (kvm_hv_hypercall_enabled(&svm->vcpu) && + hve->hv_enlightenments_control.msr_bitmap && + (svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS))) + goto set_msrpm_base_pa; + } +#endif if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))) return true; @@ -230,7 +234,9 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm) svm->nested.force_msr_bitmap_recalc = false; +#ifdef CONFIG_KVM_HYPERV set_msrpm_base_pa: +#endif svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm)); return true; @@ -296,7 +302,7 @@ static bool __nested_vmcb_check_save(struct kvm_vcpu *vcpu, if ((save->efer & EFER_LME) && (save->cr0 & X86_CR0_PG)) { if (CC(!(save->cr4 & X86_CR4_PAE)) || CC(!(save->cr0 & X86_CR0_PE)) || - CC(kvm_vcpu_is_illegal_gpa(vcpu, save->cr3))) + CC(!kvm_vcpu_is_legal_cr3(vcpu, save->cr3))) return false; } @@ -363,12 +369,14 @@ void __nested_copy_vmcb_control_to_cache(struct kvm_vcpu *vcpu, to->msrpm_base_pa &= ~0x0fffULL; to->iopm_base_pa &= ~0x0fffULL; +#ifdef CONFIG_KVM_HYPERV /* Hyper-V extensions (Enlightened VMCB) */ if (kvm_hv_hypercall_enabled(vcpu)) { to->clean = from->clean; memcpy(&to->hv_enlightenments, &from->hv_enlightenments, sizeof(to->hv_enlightenments)); } +#endif } void nested_copy_vmcb_control_to_cache(struct vcpu_svm *svm, @@ -472,14 +480,8 @@ static void nested_save_pending_event_to_vmcb12(struct vcpu_svm *svm, static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) { - /* - * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or - * L2's VP_ID upon request from the guest. Make sure we check for - * pending entries in the right FIFO upon L1/L2 transition as these - * requests are put by other vCPUs asynchronously. - */ - if (to_hv_vcpu(vcpu) && npt_enabled) - kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + /* Handle pending Hyper-V TLB flush requests */ + kvm_hv_nested_transtion_tlb_flush(vcpu, npt_enabled); /* * TODO: optimize unconditional TLB flush/MMU sync. A partial list of @@ -505,7 +507,7 @@ static void nested_svm_transition_tlb_flush(struct kvm_vcpu *vcpu) static int nested_svm_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_npt, bool reload_pdptrs) { - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) + if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) return -EINVAL; if (reload_pdptrs && !nested_npt && is_pae_paging(vcpu) && diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 3fd47de14b..b6a7ad4d69 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -161,7 +161,6 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) pmc = get_gp_pmc_amd(pmu, msr, PMU_TYPE_COUNTER); if (pmc) { pmc_write_counter(pmc, data); - pmc_update_sample_period(pmc); return 0; } /* MSR_EVNTSELn */ diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 1226bb2151..86088d1250 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -84,9 +84,10 @@ struct enc_region { }; /* Called with the sev_bitmap_lock held, or on shutdown */ -static int sev_flush_asids(int min_asid, int max_asid) +static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid) { - int ret, asid, error = 0; + int ret, error = 0; + unsigned int asid; /* Check if there are any ASIDs to reclaim before performing a flush */ asid = find_next_bit(sev_reclaim_asid_bitmap, nr_asids, min_asid); @@ -116,7 +117,7 @@ static inline bool is_mirroring_enc_context(struct kvm *kvm) } /* Must be called with the sev_bitmap_lock held */ -static bool __sev_recycle_asids(int min_asid, int max_asid) +static bool __sev_recycle_asids(unsigned int min_asid, unsigned int max_asid) { if (sev_flush_asids(min_asid, max_asid)) return false; @@ -143,8 +144,20 @@ static void sev_misc_cg_uncharge(struct kvm_sev_info *sev) static int sev_asid_new(struct kvm_sev_info *sev) { - int asid, min_asid, max_asid, ret; + /* + * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. + * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. + * Note: min ASID can end up larger than the max if basic SEV support is + * effectively disabled by disallowing use of ASIDs for SEV guests. + */ + unsigned int min_asid = sev->es_active ? 1 : min_sev_asid; + unsigned int max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; + unsigned int asid; bool retry = true; + int ret; + + if (min_asid > max_asid) + return -ENOTTY; WARN_ON(sev->misc_cg); sev->misc_cg = get_current_misc_cg(); @@ -157,12 +170,6 @@ static int sev_asid_new(struct kvm_sev_info *sev) mutex_lock(&sev_bitmap_lock); - /* - * SEV-enabled guests must use asid from min_sev_asid to max_sev_asid. - * SEV-ES-enabled guest can use from 1 to min_sev_asid - 1. - */ - min_asid = sev->es_active ? 1 : min_sev_asid; - max_asid = sev->es_active ? min_sev_asid - 1 : max_sev_asid; again: asid = find_next_zero_bit(sev_asid_bitmap, max_asid + 1, min_asid); if (asid > max_asid) { @@ -187,7 +194,7 @@ e_uncharge: return ret; } -static int sev_get_asid(struct kvm *kvm) +static unsigned int sev_get_asid(struct kvm *kvm) { struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; @@ -284,8 +291,8 @@ e_no_asid: static int sev_bind_asid(struct kvm *kvm, unsigned int handle, int *error) { + unsigned int asid = sev_get_asid(kvm); struct sev_data_activate activate; - int asid = sev_get_asid(kvm); int ret; /* activate ASID on the given handle */ @@ -2196,10 +2203,13 @@ void __init sev_hardware_setup(void) /* * SEV must obviously be supported in hardware. Sanity check that the * CPU supports decode assists, which is mandatory for SEV guests to - * support instruction emulation. + * support instruction emulation. Ditto for flushing by ASID, as SEV + * guests are bound to a single ASID, i.e. KVM can't rotate to a new + * ASID to effect a TLB flush. */ if (!boot_cpu_has(X86_FEATURE_SEV) || - WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS))) + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_DECODEASSISTS)) || + WARN_ON_ONCE(!boot_cpu_has(X86_FEATURE_FLUSHBYASID))) goto out; /* Retrieve SEV CPUID information */ @@ -2234,8 +2244,10 @@ void __init sev_hardware_setup(void) goto out; } - sev_asid_count = max_sev_asid - min_sev_asid + 1; - WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + if (min_sev_asid <= max_sev_asid) { + sev_asid_count = max_sev_asid - min_sev_asid + 1; + WARN_ON_ONCE(misc_cg_set_capacity(MISC_CG_RES_SEV, sev_asid_count)); + } sev_supported = true; /* SEV-ES support requested? */ @@ -2266,7 +2278,9 @@ void __init sev_hardware_setup(void) out: if (boot_cpu_has(X86_FEATURE_SEV)) pr_info("SEV %s (ASIDs %u - %u)\n", - sev_supported ? "enabled" : "disabled", + sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" : + "unusable" : + "disabled", min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", @@ -2314,7 +2328,7 @@ int sev_cpu_init(struct svm_cpu_data *sd) */ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va) { - int asid = to_kvm_svm(vcpu->kvm)->sev_info.asid; + unsigned int asid = sev_get_asid(vcpu->kvm); /* * Note! The address must be a kernel address, as regular page walk @@ -2632,7 +2646,7 @@ void sev_es_unmap_ghcb(struct vcpu_svm *svm) void pre_sev_run(struct vcpu_svm *svm, int cpu) { struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu); - int asid = sev_get_asid(svm->vcpu.kvm); + unsigned int asid = sev_get_asid(svm->vcpu.kvm); /* Assign the asid allocated with this SEV guest */ svm->asid = asid; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index a8bd4e909a..e90b429c84 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -3563,8 +3563,15 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) if (svm->nmi_l1_to_l2) return; - svm->nmi_masked = true; - svm_set_iret_intercept(svm); + /* + * No need to manually track NMI masking when vNMI is enabled, hardware + * automatically sets V_NMI_BLOCKING_MASK as appropriate, including the + * case where software directly injects an NMI. + */ + if (!is_vnmi_enabled(svm)) { + svm->nmi_masked = true; + svm_set_iret_intercept(svm); + } ++vcpu->stat.nmi_injections; } @@ -4744,7 +4751,7 @@ 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 @@ -5079,6 +5086,13 @@ static __init void svm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SVM); kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN); + /* + * KVM currently flushes TLBs on *every* nested SVM transition, + * and so for all intents and purposes KVM supports flushing by + * ASID, i.e. KVM is guaranteed to honor every L1 ASID flush. + */ + kvm_cpu_cap_set(X86_FEATURE_FLUSHBYASID); + if (nrips) kvm_cpu_cap_set(X86_FEATURE_NRIPS); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index c409f934c3..8ef95139cd 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -148,7 +148,9 @@ struct vmcb_ctrl_area_cached { u64 virt_ext; u32 clean; union { +#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV) struct hv_vmcb_enlightenments hv_enlightenments; +#endif u8 reserved_sw[32]; }; }; diff --git a/arch/x86/kvm/svm/svm_onhyperv.c b/arch/x86/kvm/svm/svm_onhyperv.c index 7af8422d33..3971b3ea5d 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.c +++ b/arch/x86/kvm/svm/svm_onhyperv.c @@ -18,18 +18,14 @@ int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_vmcb_enlightenments *hve; - struct hv_partition_assist_pg **p_hv_pa_pg = - &to_kvm_hv(vcpu->kvm)->hv_pa_pg; + hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL); - - if (!*p_hv_pa_pg) + if (partition_assist_page == INVALID_PAGE) return -ENOMEM; hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments; - hve->partition_assist_page = __pa(*p_hv_pa_pg); + hve->partition_assist_page = partition_assist_page; hve->hv_vm_id = (unsigned long)vcpu->kvm; if (!hve->hv_enlightenments_control.nested_flush_hypercall) { hve->hv_enlightenments_control.nested_flush_hypercall = 1; diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index ef2ebabb05..9499f9c6b0 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -270,16 +270,16 @@ SYM_FUNC_START(__svm_vcpu_run) RESTORE_GUEST_SPEC_CTRL_BODY RESTORE_HOST_SPEC_CTRL_BODY -10: cmpb $0, kvm_rebooting +10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b ud2 -30: cmpb $0, kvm_rebooting +30: cmpb $0, _ASM_RIP(kvm_rebooting) jne 4b ud2 -50: cmpb $0, kvm_rebooting +50: cmpb $0, _ASM_RIP(kvm_rebooting) jne 6b ud2 -70: cmpb $0, kvm_rebooting +70: cmpb $0, _ASM_RIP(kvm_rebooting) jne 8b ud2 @@ -381,7 +381,7 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) RESTORE_GUEST_SPEC_CTRL_BODY RESTORE_HOST_SPEC_CTRL_BODY -3: cmpb $0, kvm_rebooting +3: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b ud2 diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 8384337981..b82e6ed4f0 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -732,13 +732,13 @@ TRACE_EVENT(kvm_nested_intr_vmexit, * Tracepoint for nested #vmexit because of interrupt pending */ TRACE_EVENT(kvm_invlpga, - TP_PROTO(__u64 rip, int asid, u64 address), + TP_PROTO(__u64 rip, unsigned int asid, u64 address), TP_ARGS(rip, asid, address), TP_STRUCT__entry( - __field( __u64, rip ) - __field( int, asid ) - __field( __u64, address ) + __field( __u64, rip ) + __field( unsigned int, asid ) + __field( __u64, address ) ), TP_fast_assign( @@ -747,7 +747,7 @@ TRACE_EVENT(kvm_invlpga, __entry->address = address; ), - TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx", + TP_printk("rip: 0x%016llx asid: %u address: 0x%016llx", __entry->rip, __entry->asid, __entry->address) ); diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 313b8bb5b8..fab6a1ad98 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,419 +13,6 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_ENABLE_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - -#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) -#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ - {EVMCS1_OFFSET(name), clean_field} - -const struct evmcs_field vmcs_field_to_evmcs_1[] = { - /* 64 bit rw */ - EVMCS1_FIELD(GUEST_RIP, guest_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_RSP, guest_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR0, host_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR3, host_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CR4, host_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_RIP, host_rip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), - EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), - EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(TSC_OFFSET, tsc_offset, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR0, guest_cr0, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR3, guest_cr3, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_CR4, guest_cr4, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(GUEST_DR7, guest_dr7, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), - EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(HOST_RSP, host_rsp, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), - EVMCS1_FIELD(EPT_POINTER, ept_pointer, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), - EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), - /* - * Not used by KVM: - * - * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x0000682A, guest_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1A, host_ssp, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - */ - - /* 64 bit read only */ - EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - /* - * Not defined in KVM: - * - * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, - * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); - */ - EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* - * No mask defined in the spec as Hyper-V doesn't currently support - * these. Future proof by resetting the whole clean field mask on - * access. - */ - EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 32 bit rw */ - EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), - EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), - EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), - EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), - EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, - vm_entry_exception_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), - EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), - EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), - - /* 32 bit read only */ - EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), - - /* No mask defined in the spec (not used) */ - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), - - /* 16 bit rw */ - EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), - EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), - EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, - HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), -}; -const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); - u64 nested_get_evmptr(struct kvm_vcpu *vcpu) { struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); @@ -608,40 +195,6 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) return 0; } -#if IS_ENABLED(CONFIG_HYPERV) -DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -/* - * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption - * is: in case a feature has corresponding fields in eVMCS described and it was - * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a - * feature which has no corresponding eVMCS field, this likely means that KVM - * needs to be updated. - */ -#define evmcs_check_vmcs_conf(field, ctrl) \ - do { \ - typeof(vmcs_conf->field) unsupported; \ - \ - unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ - if (unsupported) { \ - pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ - (u64)unsupported); \ - vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ - } \ - } \ - while (0) - -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) -{ - evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); - evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); - evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); - evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); - evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); - evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); -} -#endif - int nested_enable_evmcs(struct kvm_vcpu *vcpu, uint16_t *vmcs_version) { diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 9623fe1651..a874074126 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -2,199 +2,89 @@ #ifndef __KVM_X86_VMX_HYPERV_H #define __KVM_X86_VMX_HYPERV_H -#include <linux/jump_label.h> - -#include <asm/hyperv-tlfs.h> -#include <asm/mshyperv.h> -#include <asm/vmx.h> - -#include "../hyperv.h" - -#include "capabilities.h" -#include "vmcs.h" +#include <linux/kvm_host.h> #include "vmcs12.h" +#include "vmx.h" -struct vmcs_config; - -#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) - -#define KVM_EVMCS_VERSION 1 +#define EVMPTR_INVALID (-1ULL) +#define EVMPTR_MAP_PENDING (-2ULL) -struct evmcs_field { - u16 offset; - u16 clean_field; +enum nested_evmptrld_status { + EVMPTRLD_DISABLED, + EVMPTRLD_SUCCEEDED, + EVMPTRLD_VMFAIL, + EVMPTRLD_ERROR, }; -extern const struct evmcs_field vmcs_field_to_evmcs_1[]; -extern const unsigned int nr_evmcs_1_fields; - -static __always_inline int evmcs_field_offset(unsigned long field, - u16 *clean_field) -{ - unsigned int index = ROL16(field, 6); - const struct evmcs_field *evmcs_field; - - if (unlikely(index >= nr_evmcs_1_fields)) - return -ENOENT; - - evmcs_field = &vmcs_field_to_evmcs_1[index]; - - /* - * Use offset=0 to detect holes in eVMCS. This offset belongs to - * 'revision_id' but this field has no encoding and is supposed to - * be accessed directly. - */ - if (unlikely(!evmcs_field->offset)) - return -ENOENT; - - if (clean_field) - *clean_field = evmcs_field->clean_field; - - return evmcs_field->offset; -} - -static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, - unsigned long field, u16 offset) +#ifdef CONFIG_KVM_HYPERV +static inline bool evmptr_is_valid(u64 evmptr) { - /* - * vmcs12_read_any() doesn't care whether the supplied structure - * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes - * the exact offset of the required field, use it for convenience - * here. - */ - return vmcs12_read_any((void *)evmcs, field, offset); + return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; } -#if IS_ENABLED(CONFIG_HYPERV) - -DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); - -static __always_inline bool kvm_is_using_evmcs(void) +static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { - return static_branch_unlikely(&__kvm_is_using_evmcs); + return evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); } -static __always_inline int get_evmcs_offset(unsigned long field, - u16 *clean_field) +static inline bool evmptr_is_set(u64 evmptr) { - int offset = evmcs_field_offset(field, clean_field); - - WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); - return offset; + return evmptr != EVMPTR_INVALID; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) +static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u64 *)((char *)current_evmcs + offset) = value; - - current_evmcs->hv_clean_fields &= ~clean_field; + return evmptr_is_set(vmx->nested.hv_evmcs_vmptr); } -static __always_inline void evmcs_write32(unsigned long field, u32 value) +static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u32 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; + return vmx->nested.hv_evmcs; } -static __always_inline void evmcs_write16(unsigned long field, u16 value) +static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) { - u16 clean_field; - int offset = get_evmcs_offset(field, &clean_field); - - if (offset < 0) - return; - - *(u16 *)((char *)current_evmcs + offset) = value; - current_evmcs->hv_clean_fields &= ~clean_field; + /* + * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and + * eVMCS has been explicitly enabled by userspace. + */ + return vcpu->arch.hyperv_enabled && + to_vmx(vcpu)->nested.enlightened_vmcs_enabled; } -static __always_inline u64 evmcs_read64(unsigned long field) +u64 nested_get_evmptr(struct kvm_vcpu *vcpu); +uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); +int nested_enable_evmcs(struct kvm_vcpu *vcpu, + uint16_t *vmcs_version); +void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); +int nested_evmcs_check_controls(struct vmcs12 *vmcs12); +bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); +void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#else +static inline bool evmptr_is_valid(u64 evmptr) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u64 *)((char *)current_evmcs + offset); + return false; } -static __always_inline u32 evmcs_read32(unsigned long field) +static inline bool nested_vmx_is_evmptr12_valid(struct vcpu_vmx *vmx) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u32 *)((char *)current_evmcs + offset); + return false; } -static __always_inline u16 evmcs_read16(unsigned long field) +static inline bool evmptr_is_set(u64 evmptr) { - int offset = get_evmcs_offset(field, NULL); - - if (offset < 0) - return 0; - - return *(u16 *)((char *)current_evmcs + offset); + return false; } -static inline void evmcs_load(u64 phys_addr) +static inline bool nested_vmx_is_evmptr12_set(struct vcpu_vmx *vmx) { - struct hv_vp_assist_page *vp_ap = - hv_get_vp_assist_page(smp_processor_id()); - - if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) - vp_ap->nested_control.features.directhypercall = 1; - vp_ap->current_nested_vmcs = phys_addr; - vp_ap->enlighten_vmentry = 1; + return false; } -void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); -#else /* !IS_ENABLED(CONFIG_HYPERV) */ -static __always_inline bool kvm_is_using_evmcs(void) { return false; } -static __always_inline void evmcs_write64(unsigned long field, u64 value) {} -static __always_inline void evmcs_write32(unsigned long field, u32 value) {} -static __always_inline void evmcs_write16(unsigned long field, u16 value) {} -static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } -static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } -static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } -static inline void evmcs_load(u64 phys_addr) {} -#endif /* IS_ENABLED(CONFIG_HYPERV) */ - -#define EVMPTR_INVALID (-1ULL) -#define EVMPTR_MAP_PENDING (-2ULL) - -static inline bool evmptr_is_valid(u64 evmptr) +static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) { - return evmptr != EVMPTR_INVALID && evmptr != EVMPTR_MAP_PENDING; + return NULL; } - -enum nested_evmptrld_status { - EVMPTRLD_DISABLED, - EVMPTRLD_SUCCEEDED, - EVMPTRLD_VMFAIL, - EVMPTRLD_ERROR, -}; - -u64 nested_get_evmptr(struct kvm_vcpu *vcpu); -uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu); -int nested_enable_evmcs(struct kvm_vcpu *vcpu, - uint16_t *vmcs_version); -void nested_evmcs_filter_control_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); -int nested_evmcs_check_controls(struct vmcs12 *vmcs12); -bool nested_evmcs_l2_tlb_flush_enabled(struct kvm_vcpu *vcpu); -void vmx_hv_inject_synthetic_vmexit_post_tlb_flush(struct kvm_vcpu *vcpu); +#endif #endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.c b/arch/x86/kvm/vmx/hyperv_evmcs.c new file mode 100644 index 0000000000..904bfcd151 --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.c @@ -0,0 +1,315 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This file contains common code for working with Enlightened VMCS which is + * used both by Hyper-V on KVM and KVM on Hyper-V. + */ + +#include "hyperv_evmcs.h" + +#define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) +#define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ + {EVMCS1_OFFSET(name), clean_field} + +const struct evmcs_field vmcs_field_to_evmcs_1[] = { + /* 64 bit rw */ + EVMCS1_FIELD(GUEST_RIP, guest_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_RSP, guest_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(GUEST_RFLAGS, guest_rflags, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(HOST_IA32_PAT, host_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_EFER, host_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_PERF_GLOBAL_CTRL, host_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR0, host_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR3, host_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CR4, host_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_ESP, host_ia32_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_IA32_SYSENTER_EIP, host_ia32_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_RIP, host_rip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(IO_BITMAP_A, io_bitmap_a, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(IO_BITMAP_B, io_bitmap_b, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_IO_BITMAP), + EVMCS1_FIELD(MSR_BITMAP, msr_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP), + EVMCS1_FIELD(GUEST_ES_BASE, guest_es_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_BASE, guest_cs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_BASE, guest_ss_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_BASE, guest_ds_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_BASE, guest_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_BASE, guest_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_BASE, guest_ldtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_BASE, guest_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_BASE, guest_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_BASE, guest_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(TSC_OFFSET, tsc_offset, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VIRTUAL_APIC_PAGE_ADDR, virtual_apic_page_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(VMCS_LINK_POINTER, vmcs_link_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_DEBUGCTL, guest_ia32_debugctl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PAT, guest_ia32_pat, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_EFER, guest_ia32_efer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_IA32_PERF_GLOBAL_CTRL, guest_ia32_perf_global_ctrl, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR0, guest_pdptr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR1, guest_pdptr1, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR2, guest_pdptr2, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PDPTR3, guest_pdptr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_PENDING_DBG_EXCEPTIONS, guest_pending_dbg_exceptions, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_ESP, guest_sysenter_esp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_EIP, guest_sysenter_eip, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(CR0_GUEST_HOST_MASK, cr0_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_GUEST_HOST_MASK, cr4_guest_host_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR0_READ_SHADOW, cr0_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(CR4_READ_SHADOW, cr4_read_shadow, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR0, guest_cr0, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR3, guest_cr3, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_CR4, guest_cr4, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(GUEST_DR7, guest_dr7, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CRDR), + EVMCS1_FIELD(HOST_FS_BASE, host_fs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GS_BASE, host_gs_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_TR_BASE, host_tr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_GDTR_BASE, host_gdtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_IDTR_BASE, host_idtr_base, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(HOST_RSP, host_rsp, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_POINTER), + EVMCS1_FIELD(EPT_POINTER, ept_pointer, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), + EVMCS1_FIELD(GUEST_BNDCFGS, guest_bndcfgs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(XSS_EXIT_BITMAP, xss_exit_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(ENCLS_EXITING_BITMAP, encls_exiting_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + EVMCS1_FIELD(TSC_MULTIPLIER, tsc_multiplier, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP2), + /* + * Not used by KVM: + * + * EVMCS1_FIELD(0x00006828, guest_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x0000682A, guest_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + * EVMCS1_FIELD(0x0000682C, guest_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00002816, guest_ia32_lbr_ctl, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + * EVMCS1_FIELD(0x00006C18, host_ia32_s_cet, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1A, host_ssp, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + * EVMCS1_FIELD(0x00006C1C, host_ia32_int_ssp_table_addr, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + */ + + /* 64 bit read only */ + EVMCS1_FIELD(GUEST_PHYSICAL_ADDRESS, guest_physical_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(EXIT_QUALIFICATION, exit_qualification, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + /* + * Not defined in KVM: + * + * EVMCS1_FIELD(0x00006402, exit_io_instruction_ecx, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006404, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006406, exit_io_instruction_esi, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + * EVMCS1_FIELD(0x00006408, exit_io_instruction_eip, + * HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE); + */ + EVMCS1_FIELD(GUEST_LINEAR_ADDRESS, guest_linear_address, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* + * No mask defined in the spec as Hyper-V doesn't currently support + * these. Future proof by resetting the whole clean field mask on + * access. + */ + EVMCS1_FIELD(VM_EXIT_MSR_STORE_ADDR, vm_exit_msr_store_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_ADDR, vm_exit_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_ADDR, vm_entry_msr_load_addr, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 32 bit rw */ + EVMCS1_FIELD(TPR_THRESHOLD, tpr_threshold, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(GUEST_INTERRUPTIBILITY_INFO, guest_interruptibility_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_BASIC), + EVMCS1_FIELD(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_PROC), + EVMCS1_FIELD(EXCEPTION_BITMAP, exception_bitmap, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EXCPN), + EVMCS1_FIELD(VM_ENTRY_CONTROLS, vm_entry_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_ENTRY), + EVMCS1_FIELD(VM_ENTRY_INTR_INFO_FIELD, vm_entry_intr_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_EXCEPTION_ERROR_CODE, + vm_entry_exception_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(VM_ENTRY_INSTRUCTION_LEN, vm_entry_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_EVENT), + EVMCS1_FIELD(HOST_IA32_SYSENTER_CS, host_ia32_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(PIN_BASED_VM_EXEC_CONTROL, pin_based_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(VM_EXIT_CONTROLS, vm_exit_controls, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(SECONDARY_VM_EXEC_CONTROL, secondary_vm_exec_control, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_GRP1), + EVMCS1_FIELD(GUEST_ES_LIMIT, guest_es_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_LIMIT, guest_cs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_LIMIT, guest_ss_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_LIMIT, guest_ds_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_LIMIT, guest_fs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_LIMIT, guest_gs_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_LIMIT, guest_ldtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_LIMIT, guest_tr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GDTR_LIMIT, guest_gdtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_IDTR_LIMIT, guest_idtr_limit, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ES_AR_BYTES, guest_es_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_AR_BYTES, guest_cs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_AR_BYTES, guest_ss_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_AR_BYTES, guest_ds_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_AR_BYTES, guest_fs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_AR_BYTES, guest_gs_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_AR_BYTES, guest_ldtr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_AR_BYTES, guest_tr_ar_bytes, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_ACTIVITY_STATE, guest_activity_state, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + EVMCS1_FIELD(GUEST_SYSENTER_CS, guest_sysenter_cs, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1), + + /* 32 bit read only */ + EVMCS1_FIELD(VM_INSTRUCTION_ERROR, vm_instruction_error, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_REASON, vm_exit_reason, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_INFO, vm_exit_intr_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INTR_ERROR_CODE, vm_exit_intr_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_INFO_FIELD, idt_vectoring_info_field, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(IDT_VECTORING_ERROR_CODE, idt_vectoring_error_code, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VM_EXIT_INSTRUCTION_LEN, vm_exit_instruction_len, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + EVMCS1_FIELD(VMX_INSTRUCTION_INFO, vmx_instruction_info, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE), + + /* No mask defined in the spec (not used) */ + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MASK, page_fault_error_code_mask, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(CR3_TARGET_COUNT, cr3_target_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + EVMCS1_FIELD(VM_ENTRY_MSR_LOAD_COUNT, vm_entry_msr_load_count, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL), + + /* 16 bit rw */ + EVMCS1_FIELD(HOST_ES_SELECTOR, host_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_CS_SELECTOR, host_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_SS_SELECTOR, host_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_DS_SELECTOR, host_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_FS_SELECTOR, host_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_GS_SELECTOR, host_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(HOST_TR_SELECTOR, host_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_HOST_GRP1), + EVMCS1_FIELD(GUEST_ES_SELECTOR, guest_es_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_CS_SELECTOR, guest_cs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_SS_SELECTOR, guest_ss_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_DS_SELECTOR, guest_ds_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_FS_SELECTOR, guest_fs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_GS_SELECTOR, guest_gs_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_LDTR_SELECTOR, guest_ldtr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(GUEST_TR_SELECTOR, guest_tr_selector, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2), + EVMCS1_FIELD(VIRTUAL_PROCESSOR_ID, virtual_processor_id, + HV_VMX_ENLIGHTENED_CLEAN_FIELD_CONTROL_XLAT), +}; +const unsigned int nr_evmcs_1_fields = ARRAY_SIZE(vmcs_field_to_evmcs_1); diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h new file mode 100644 index 0000000000..a543fccfc5 --- /dev/null +++ b/arch/x86/kvm/vmx/hyperv_evmcs.h @@ -0,0 +1,166 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * This file contains common definitions for working with Enlightened VMCS which + * are used both by Hyper-V on KVM and KVM on Hyper-V. + */ +#ifndef __KVM_X86_VMX_HYPERV_EVMCS_H +#define __KVM_X86_VMX_HYPERV_EVMCS_H + +#include <asm/hyperv-tlfs.h> + +#include "capabilities.h" +#include "vmcs12.h" + +#define KVM_EVMCS_VERSION 1 + +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_ENABLE_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) + +struct evmcs_field { + u16 offset; + u16 clean_field; +}; + +extern const struct evmcs_field vmcs_field_to_evmcs_1[]; +extern const unsigned int nr_evmcs_1_fields; + +static __always_inline int evmcs_field_offset(unsigned long field, + u16 *clean_field) +{ + const struct evmcs_field *evmcs_field; + unsigned int index = ROL16(field, 6); + + if (unlikely(index >= nr_evmcs_1_fields)) + return -ENOENT; + + evmcs_field = &vmcs_field_to_evmcs_1[index]; + + /* + * Use offset=0 to detect holes in eVMCS. This offset belongs to + * 'revision_id' but this field has no encoding and is supposed to + * be accessed directly. + */ + if (unlikely(!evmcs_field->offset)) + return -ENOENT; + + if (clean_field) + *clean_field = evmcs_field->clean_field; + + return evmcs_field->offset; +} + +static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, + unsigned long field, u16 offset) +{ + /* + * vmcs12_read_any() doesn't care whether the supplied structure + * is 'struct vmcs12' or 'struct hv_enlightened_vmcs' as it takes + * the exact offset of the required field, use it for convenience + * here. + */ + return vmcs12_read_any((void *)evmcs, field, offset); +} + +#endif /* __KVM_X86_VMX_HYPERV_H */ diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index c5ec0ef51f..6329a30685 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -179,7 +179,7 @@ static int nested_vmx_failValid(struct kvm_vcpu *vcpu, * VM_INSTRUCTION_ERROR is not shadowed. Enlightened VMCS 'shadows' all * fields and thus must be synced. */ - if (to_vmx(vcpu)->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(to_vmx(vcpu))) to_vmx(vcpu)->nested.need_vmcs12_to_shadow_sync = true; return kvm_skip_emulated_instruction(vcpu); @@ -194,7 +194,7 @@ static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error) * can't be done if there isn't a current VMCS. */ if (vmx->nested.current_vmptr == INVALID_GPA && - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + !nested_vmx_is_evmptr12_valid(vmx)) return nested_vmx_failInvalid(vcpu); return nested_vmx_failValid(vcpu, vm_instruction_error); @@ -226,10 +226,11 @@ static void vmx_disable_shadow_vmcs(struct vcpu_vmx *vmx) static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (nested_vmx_is_evmptr12_valid(vmx)) { kvm_vcpu_unmap(vcpu, &vmx->nested.hv_evmcs_map, true); vmx->nested.hv_evmcs = NULL; } @@ -241,6 +242,34 @@ static inline void nested_release_evmcs(struct kvm_vcpu *vcpu) hv_vcpu->nested.vm_id = 0; hv_vcpu->nested.vp_id = 0; } +#endif +} + +static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) +{ +#ifdef CONFIG_KVM_HYPERV + struct vcpu_vmx *vmx = to_vmx(vcpu); + /* + * When Enlightened VMEntry is enabled on the calling CPU we treat + * memory area pointer by vmptr as Enlightened VMCS (as there's no good + * way to distinguish it from VMCS12) and we must not corrupt it by + * writing to the non-existent 'launch_state' field. The area doesn't + * have to be the currently active EVMCS on the calling CPU and there's + * nothing KVM has to do to transition it from 'active' to 'non-active' + * state. It is possible that the area will stay mapped as + * vmx->nested.hv_evmcs but this shouldn't be a problem. + */ + if (!guest_cpuid_has_evmcs(vcpu) || + !evmptr_is_valid(nested_get_evmptr(vcpu))) + return false; + + if (nested_vmx_evmcs(vmx) && vmptr == vmx->nested.hv_evmcs_vmptr) + nested_release_evmcs(vcpu); + + return true; +#else + return false; +#endif } static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx, @@ -572,7 +601,6 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, int msr; unsigned long *msr_bitmap_l1; unsigned long *msr_bitmap_l0 = vmx->nested.vmcs02.msr_bitmap; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; struct kvm_host_map *map = &vmx->nested.msr_bitmap_map; /* Nothing to do if the MSR bitmap is not in use. */ @@ -588,10 +616,13 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, * - Nested hypervisor (L1) has enabled 'Enlightened MSR Bitmap' feature * and tells KVM (L0) there were no changes in MSR bitmap for L2. */ - if (!vmx->nested.force_msr_bitmap_recalc && evmcs && - evmcs->hv_enlightenments_control.msr_bitmap && - evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) - return true; + if (!vmx->nested.force_msr_bitmap_recalc) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + if (evmcs && evmcs->hv_enlightenments_control.msr_bitmap && + evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_MSR_BITMAP) + return true; + } if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcs12->msr_bitmap), map)) return false; @@ -1085,7 +1116,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, bool reload_pdptrs, enum vm_entry_failure_code *entry_failure_code) { - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) { + if (CC(!kvm_vcpu_is_legal_cr3(vcpu, cr3))) { *entry_failure_code = ENTRY_FAIL_DEFAULT; return -EINVAL; } @@ -1139,14 +1170,8 @@ static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu, { struct vcpu_vmx *vmx = to_vmx(vcpu); - /* - * KVM_REQ_HV_TLB_FLUSH flushes entries from either L1's VP_ID or - * L2's VP_ID upon request from the guest. Make sure we check for - * pending entries in the right FIFO upon L1/L2 transition as these - * requests are put by other vCPUs asynchronously. - */ - if (to_hv_vcpu(vcpu) && enable_ept) - kvm_make_request(KVM_REQ_HV_TLB_FLUSH, vcpu); + /* Handle pending Hyper-V TLB flush requests */ + kvm_hv_nested_transtion_tlb_flush(vcpu, enable_ept); /* * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings @@ -1578,8 +1603,9 @@ static void copy_vmcs12_to_shadow(struct vcpu_vmx *vmx) static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(&vmx->vcpu); /* HV_VMX_ENLIGHTENED_CLEAN_FIELD_NONE */ @@ -1818,12 +1844,16 @@ static void copy_enlightened_to_vmcs12(struct vcpu_vmx *vmx, u32 hv_clean_fields */ return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) { +#ifdef CONFIG_KVM_HYPERV struct vmcs12 *vmcs12 = vmx->nested.cached_vmcs12; - struct hv_enlightened_vmcs *evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); /* * Should not be changed by KVM: @@ -1992,6 +2022,9 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) evmcs->guest_bndcfgs = vmcs12->guest_bndcfgs; return; +#else /* CONFIG_KVM_HYPERV */ + KVM_BUG_ON(1, vmx->vcpu.kvm); +#endif /* CONFIG_KVM_HYPERV */ } /* @@ -2001,6 +2034,7 @@ static void copy_vmcs12_to_enlightened(struct vcpu_vmx *vmx) static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( struct kvm_vcpu *vcpu, bool from_launch) { +#ifdef CONFIG_KVM_HYPERV struct vcpu_vmx *vmx = to_vmx(vcpu); bool evmcs_gpa_changed = false; u64 evmcs_gpa; @@ -2082,13 +2116,16 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( } return EVMPTRLD_SUCCEEDED; +#else + return EVMPTRLD_DISABLED; +#endif } void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) copy_vmcs12_to_enlightened(vmx); else copy_vmcs12_to_shadow(vmx); @@ -2242,7 +2279,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 u32 exec_control; u64 guest_efer = nested_vmx_calc_efer(vmx, vmcs12); - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) prepare_vmcs02_early_rare(vmx, vmcs12); /* @@ -2403,7 +2440,7 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0 static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12) { - struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; + struct hv_enlightened_vmcs *hv_evmcs = nested_vmx_evmcs(vmx); if (!hv_evmcs || !(hv_evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP2)) { @@ -2535,15 +2572,15 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, enum vm_entry_failure_code *entry_failure_code) { struct vcpu_vmx *vmx = to_vmx(vcpu); + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); bool load_guest_pdptrs_vmcs12 = false; - if (vmx->nested.dirty_vmcs12 || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (vmx->nested.dirty_vmcs12 || nested_vmx_is_evmptr12_valid(vmx)) { prepare_vmcs02_rare(vmx, vmcs12); vmx->nested.dirty_vmcs12 = false; - load_guest_pdptrs_vmcs12 = !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) || - !(vmx->nested.hv_evmcs->hv_clean_fields & - HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); + load_guest_pdptrs_vmcs12 = !nested_vmx_is_evmptr12_valid(vmx) || + !(evmcs->hv_clean_fields & HV_VMX_ENLIGHTENED_CLEAN_FIELD_GUEST_GRP1); } if (vmx->nested.nested_run_pending && @@ -2664,9 +2701,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, * bits when it changes a field in eVMCS. Mark all fields as clean * here. */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) - vmx->nested.hv_evmcs->hv_clean_fields |= - HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; + if (nested_vmx_is_evmptr12_valid(vmx)) + evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; return 0; } @@ -2717,7 +2753,7 @@ static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp) } /* Reserved bits should not be set */ - if (CC(kvm_vcpu_is_illegal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) + if (CC(!kvm_vcpu_is_legal_gpa(vcpu, new_eptp) || ((new_eptp >> 7) & 0x1f))) return false; /* AD, if set, should be supported */ @@ -2888,8 +2924,10 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, nested_check_vm_entry_controls(vcpu, vmcs12)) return -EINVAL; +#ifdef CONFIG_KVM_HYPERV if (guest_cpuid_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); +#endif return 0; } @@ -2912,7 +2950,7 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu, if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) || CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) || - CC(kvm_vcpu_is_illegal_gpa(vcpu, vmcs12->host_cr3))) + CC(!kvm_vcpu_is_legal_cr3(vcpu, vmcs12->host_cr3))) return -EINVAL; if (CC(is_noncanonical_address(vmcs12->host_ia32_sysenter_esp, vcpu)) || @@ -3161,6 +3199,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu) return 0; } +#ifdef CONFIG_KVM_HYPERV static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -3188,6 +3227,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) return true; } +#endif static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) { @@ -3279,6 +3319,7 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu) static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) { +#ifdef CONFIG_KVM_HYPERV /* * Note: nested_get_evmcs_page() also updates 'vp_assist_page' copy * in 'struct kvm_vcpu_hv' in case eVMCS is in use, this is mandatory @@ -3295,6 +3336,7 @@ static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu) return false; } +#endif if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu)) return false; @@ -3538,7 +3580,7 @@ vmentry_fail_vmexit: load_vmcs12_host_state(vcpu, vmcs12); vmcs12->vm_exit_reason = exit_reason.full; - if (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx)) vmx->nested.need_vmcs12_to_shadow_sync = true; return NVMX_VMENTRY_VMEXIT; } @@ -3569,7 +3611,7 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) return nested_vmx_failInvalid(vcpu); - if (CC(!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr) && + if (CC(!nested_vmx_is_evmptr12_valid(vmx) && vmx->nested.current_vmptr == INVALID_GPA)) return nested_vmx_failInvalid(vcpu); @@ -3584,8 +3626,10 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (CC(vmcs12->hdr.shadow_vmcs)) return nested_vmx_failInvalid(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { - copy_enlightened_to_vmcs12(vmx, vmx->nested.hv_evmcs->hv_clean_fields); + if (nested_vmx_is_evmptr12_valid(vmx)) { + struct hv_enlightened_vmcs *evmcs = nested_vmx_evmcs(vmx); + + copy_enlightened_to_vmcs12(vmx, evmcs->hv_clean_fields); /* Enlightened VMCS doesn't have launch state */ vmcs12->launch_state = !launch; } else if (enable_shadow_vmcs) { @@ -4329,11 +4373,11 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12); vmx->nested.need_sync_vmcs02_to_vmcs12_rare = - !evmptr_is_valid(vmx->nested.hv_evmcs_vmptr); + !nested_vmx_is_evmptr12_valid(vmx); vmcs12->guest_cr0 = vmcs12_guest_cr0(vcpu, vmcs12); vmcs12->guest_cr4 = vmcs12_guest_cr4(vcpu, vmcs12); @@ -4732,6 +4776,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, /* trying to cancel vmlaunch/vmresume is a bug */ WARN_ON_ONCE(vmx->nested.nested_run_pending); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) { /* * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map @@ -4741,6 +4786,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, */ (void)nested_get_evmcs_page(vcpu); } +#endif /* Service pending TLB flush requests for L2 before switching to L1. */ kvm_service_local_tlb_flush_requests(vcpu); @@ -4854,7 +4900,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, } if ((vm_exit_reason != -1) && - (enable_shadow_vmcs || evmptr_is_valid(vmx->nested.hv_evmcs_vmptr))) + (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; /* in case we halted in L2 */ @@ -4980,6 +5026,7 @@ int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification, else *ret = off; + *ret = vmx_get_untagged_addr(vcpu, *ret, 0); /* Long mode: #GP(0)/#SS(0) if the memory address is in a * non-canonical form. This is the only check on the memory * destination for long mode! @@ -5292,18 +5339,7 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) if (vmptr == vmx->nested.vmxon_ptr) return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER); - /* - * When Enlightened VMEntry is enabled on the calling CPU we treat - * memory area pointer by vmptr as Enlightened VMCS (as there's no good - * way to distinguish it from VMCS12) and we must not corrupt it by - * writing to the non-existent 'launch_state' field. The area doesn't - * have to be the currently active EVMCS on the calling CPU and there's - * nothing KVM has to do to transition it from 'active' to 'non-active' - * state. It is possible that the area will stay mapped as - * vmx->nested.hv_evmcs but this shouldn't be a problem. - */ - if (likely(!guest_cpuid_has_evmcs(vcpu) || - !evmptr_is_valid(nested_get_evmptr(vcpu)))) { + if (likely(!nested_evmcs_handle_vmclear(vcpu, vmptr))) { if (vmptr == vmx->nested.current_vmptr) nested_release_vmcs12(vcpu); @@ -5320,8 +5356,6 @@ static int handle_vmclear(struct kvm_vcpu *vcpu) vmptr + offsetof(struct vmcs12, launch_state), &zero, sizeof(zero)); - } else if (vmx->nested.hv_evmcs && vmptr == vmx->nested.hv_evmcs_vmptr) { - nested_release_evmcs(vcpu); } return nested_vmx_succeed(vcpu); @@ -5360,7 +5394,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) /* Decode instruction info and find the field to read */ field = kvm_register_read(vcpu, (((instr_info) >> 28) & 0xf)); - if (!evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) { + if (!nested_vmx_is_evmptr12_valid(vmx)) { /* * In VMX non-root operation, when the VMCS-link pointer is INVALID_GPA, * any VMREAD sets the ALU flags for VMfailInvalid. @@ -5398,7 +5432,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT); /* Read the field, zero-extended to a u64 value */ - value = evmcs_read_any(vmx->nested.hv_evmcs, field, offset); + value = evmcs_read_any(nested_vmx_evmcs(vmx), field, offset); } /* @@ -5586,7 +5620,7 @@ static int handle_vmptrld(struct kvm_vcpu *vcpu) return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER); /* Forbid normal VMPTRLD if Enlightened version was used */ - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) return 1; if (vmx->nested.current_vmptr != vmptr) { @@ -5649,7 +5683,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu) if (!nested_vmx_check_permission(vcpu)) return 1; - if (unlikely(evmptr_is_valid(to_vmx(vcpu)->nested.hv_evmcs_vmptr))) + if (unlikely(nested_vmx_is_evmptr12_valid(to_vmx(vcpu)))) return 1; if (get_vmx_mem_address(vcpu, exit_qual, instr_info, @@ -5797,6 +5831,10 @@ static int handle_invvpid(struct kvm_vcpu *vcpu) vpid02 = nested_get_vpid02(vcpu); switch (type) { case VMX_VPID_EXTENT_INDIVIDUAL_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if (!operand.vpid || is_noncanonical_address(operand.gla, vcpu)) return nested_vmx_fail(vcpu, @@ -6208,11 +6246,13 @@ static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu, * Handle L2's bus locks in L0 directly. */ return true; +#ifdef CONFIG_KVM_HYPERV case EXIT_REASON_VMCALL: /* Hyper-V L2 TLB flush hypercall is handled by L0 */ return guest_hv_cpuid_has_l2_tlb_flush(vcpu) && nested_evmcs_l2_tlb_flush_enabled(vcpu) && kvm_hv_is_tlb_flush_hcall(vcpu); +#endif default: break; } @@ -6435,7 +6475,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, kvm_state.size += sizeof(user_vmx_nested_state->vmcs12); /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ - if (vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID) + if (nested_vmx_is_evmptr12_set(vmx)) kvm_state.flags |= KVM_STATE_NESTED_EVMCS; if (is_guest_mode(vcpu) && @@ -6491,7 +6531,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, } else { copy_vmcs02_to_vmcs12_rare(vcpu, get_vmcs12(vcpu)); if (!vmx->nested.need_vmcs12_to_shadow_sync) { - if (evmptr_is_valid(vmx->nested.hv_evmcs_vmptr)) + if (nested_vmx_is_evmptr12_valid(vmx)) /* * L1 hypervisor is not obliged to keep eVMCS * clean fields data always up-to-date while @@ -6561,7 +6601,7 @@ 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) @@ -6632,6 +6672,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa); +#ifdef CONFIG_KVM_HYPERV } else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) { /* * nested_vmx_handle_enlightened_vmptrld() cannot be called @@ -6641,6 +6682,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, */ vmx->nested.hv_evmcs_vmptr = EVMPTR_MAP_PENDING; kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu); +#endif } else { return -EINVAL; } @@ -7096,7 +7138,9 @@ struct kvm_x86_nested_ops vmx_nested_ops = { .set_state = vmx_set_nested_state, .get_nested_state_pages = vmx_get_nested_state_pages, .write_log_dirty = nested_vmx_write_pml_buffer, +#ifdef CONFIG_KVM_HYPERV .enable_evmcs = nested_enable_evmcs, .get_evmcs_version = nested_get_evmcs_version, .hv_inject_synthetic_vmexit_post_tlb_flush = vmx_hv_inject_synthetic_vmexit_post_tlb_flush, +#endif }; diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h index b4b9d51438..cce4e2aa30 100644 --- a/arch/x86/kvm/vmx/nested.h +++ b/arch/x86/kvm/vmx/nested.h @@ -3,6 +3,7 @@ #define __KVM_X86_VMX_NESTED_H #include "kvm_cache_regs.h" +#include "hyperv.h" #include "vmcs12.h" #include "vmx.h" @@ -57,7 +58,7 @@ static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu) /* 'hv_evmcs_vmptr' can also be EVMPTR_MAP_PENDING here */ return vmx->nested.current_vmptr != -1ull || - vmx->nested.hv_evmcs_vmptr != EVMPTR_INVALID; + nested_vmx_is_evmptr12_set(vmx); } static inline u16 nested_get_vpid02(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 1549461fa4..600a021ae9 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -437,11 +437,9 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc_write_counter(pmc, data); - pmc_update_sample_period(pmc); break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc_write_counter(pmc, data); - pmc_update_sample_period(pmc); break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { reserved_bits = pmu->reserved_bits; @@ -493,19 +491,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) u64 counter_mask; int i; - pmu->nr_arch_gp_counters = 0; - pmu->nr_arch_fixed_counters = 0; - pmu->counter_bitmask[KVM_PMC_GP] = 0; - pmu->counter_bitmask[KVM_PMC_FIXED] = 0; - pmu->version = 0; - pmu->reserved_bits = 0xffffffff00200000ull; - pmu->raw_event_mask = X86_RAW_EVENT_MASK; - pmu->global_ctrl_mask = ~0ull; - pmu->global_status_mask = ~0ull; - pmu->fixed_ctr_ctrl_mask = ~0ull; - pmu->pebs_enable_mask = ~0ull; - pmu->pebs_data_cfg_mask = ~0ull; - memset(&lbr_desc->records, 0, sizeof(lbr_desc->records)); /* @@ -517,8 +502,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) return; entry = kvm_find_cpuid_entry(vcpu, 0xa); - if (!entry || !vcpu->kvm->arch.enable_pmu) + if (!entry) return; + eax.full = entry->eax; edx.full = entry->edx; diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index 3e822e5824..6fef01e053 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -37,6 +37,7 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, if (!IS_ALIGNED(*gva, alignment)) { fault = true; } else if (likely(is_64_bit_mode(vcpu))) { + *gva = vmx_get_untagged_addr(vcpu, *gva, 0); fault = is_noncanonical_address(*gva, vcpu); } else { *gva &= 0xffffffff; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 139960deb7..f6986dee6f 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -275,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX @@ -292,7 +294,7 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) RET .Lfixup: - cmpb $0, kvm_rebooting + cmpb $0, _ASM_RIP(kvm_rebooting) jne .Lvmfail ud2 .Lvmfail: diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 856eef56b3..784f2ecca5 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -66,6 +66,7 @@ #include "vmx.h" #include "x86.h" #include "smm.h" +#include "vmx_onhyperv.h" MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); @@ -532,22 +533,14 @@ module_param(enlightened_vmcs, bool, 0444); static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu) { struct hv_enlightened_vmcs *evmcs; - struct hv_partition_assist_pg **p_hv_pa_pg = - &to_kvm_hv(vcpu->kvm)->hv_pa_pg; - /* - * Synthetic VM-Exit is not enabled in current code and so All - * evmcs in singe VM shares same assist page. - */ - if (!*p_hv_pa_pg) - *p_hv_pa_pg = kzalloc(PAGE_SIZE, GFP_KERNEL_ACCOUNT); + hpa_t partition_assist_page = hv_get_partition_assist_page(vcpu); - if (!*p_hv_pa_pg) + if (partition_assist_page == INVALID_PAGE) return -ENOMEM; evmcs = (struct hv_enlightened_vmcs *)to_vmx(vcpu)->loaded_vmcs->vmcs; - evmcs->partition_assist_page = - __pa(*p_hv_pa_pg); + evmcs->partition_assist_page = partition_assist_page; evmcs->hv_vm_id = (unsigned long)vcpu->kvm; evmcs->hv_enlightenments_control.nested_flush_hypercall = 1; @@ -1818,7 +1811,7 @@ 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; @@ -2064,6 +2057,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) return 1; +#ifdef CONFIG_KVM_HYPERV /* * Enlightened VMCS v1 doesn't have certain VMCS fields but * instead of just ignoring the features, different Hyper-V @@ -2074,6 +2068,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); +#endif break; case MSR_IA32_RTIT_CTL: if (!vmx_pt_mode_is_host_guest()) @@ -3409,7 +3404,8 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, update_guest_cr3 = false; vmx_ept_load_pdptrs(vcpu); } else { - guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu); + guest_cr3 = root_hpa | kvm_get_active_pcid(vcpu) | + kvm_get_active_cr3_lam_bits(vcpu); } if (update_guest_cr3) @@ -4842,7 +4838,10 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu) vmx->nested.posted_intr_nv = -1; vmx->nested.vmxon_ptr = INVALID_GPA; vmx->nested.current_vmptr = INVALID_GPA; + +#ifdef CONFIG_KVM_HYPERV vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID; +#endif vcpu->arch.microcode_version = 0x100000000ULL; vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED; @@ -5791,7 +5790,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu) * would also use advanced VM-exit information for EPT violations to * reconstruct the page fault error code. */ - if (unlikely(allow_smaller_maxphyaddr && kvm_vcpu_is_illegal_gpa(vcpu, gpa))) + if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa))) return kvm_emulate_instruction(vcpu, 0); return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0); @@ -6766,10 +6765,10 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; /* - * Grab the memslot so that the hva lookup for the mmu_notifier retry - * is guaranteed to use the same memslot as the pfn lookup, i.e. rely - * on the pfn lookup's validation of the memslot to ensure a valid hva - * is used for the retry check. + * Explicitly grab the memslot using KVM's internal slot ID to ensure + * KVM doesn't unintentionally grab a userspace memslot. It _should_ + * be impossible for userspace to create a memslot for the APIC when + * APICv is enabled, but paranoia won't hurt in this case. */ slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) @@ -6794,8 +6793,7 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) return; read_lock(&vcpu->kvm->mmu_lock); - if (mmu_invalidate_retry_hva(kvm, mmu_seq, - gfn_to_hva_memslot(slot, gfn))) { + if (mmu_invalidate_retry_gfn(kvm, mmu_seq, gfn)) { kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu); read_unlock(&vcpu->kvm->mmu_lock); goto out; @@ -7686,6 +7684,9 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu) cr4_fixed1_update(X86_CR4_UMIP, ecx, feature_bit(UMIP)); cr4_fixed1_update(X86_CR4_LA57, ecx, feature_bit(LA57)); + entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1); + cr4_fixed1_update(X86_CR4_LAM_SUP, eax, feature_bit(LAM)); + #undef cr4_fixed1_update } @@ -7772,6 +7773,7 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_XSAVES); kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VMX); + kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LAM); vmx_setup_uret_msrs(vmx); @@ -7855,8 +7857,28 @@ static u64 vmx_get_perf_capabilities(void) if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; @@ -8218,6 +8240,50 @@ static void vmx_vm_destroy(struct kvm *kvm) free_pages((unsigned long)kvm_vmx->pid_table, vmx_get_pid_table_order(kvm)); } +/* + * Note, the SDM states that the linear address is masked *after* the modified + * canonicality check, whereas KVM masks (untags) the address and then performs + * a "normal" canonicality check. Functionally, the two methods are identical, + * and when the masking occurs relative to the canonicality check isn't visible + * to software, i.e. KVM's behavior doesn't violate the SDM. + */ +gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags) +{ + int lam_bit; + unsigned long cr3_bits; + + if (flags & (X86EMUL_F_FETCH | X86EMUL_F_IMPLICIT | X86EMUL_F_INVLPG)) + return gva; + + if (!is_64_bit_mode(vcpu)) + return gva; + + /* + * Bit 63 determines if the address should be treated as user address + * or a supervisor address. + */ + if (!(gva & BIT_ULL(63))) { + cr3_bits = kvm_get_active_cr3_lam_bits(vcpu); + if (!(cr3_bits & (X86_CR3_LAM_U57 | X86_CR3_LAM_U48))) + return gva; + + /* LAM_U48 is ignored if LAM_U57 is set. */ + lam_bit = cr3_bits & X86_CR3_LAM_U57 ? 56 : 47; + } else { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_LAM_SUP)) + return gva; + + lam_bit = kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 56 : 47; + } + + /* + * Untag the address by sign-extending the lam_bit, but NOT to bit 63. + * Bit 63 is retained from the raw virtual address so that untagging + * doesn't change a user access to a supervisor access, and vice versa. + */ + return (sign_extend64(gva, lam_bit) & ~BIT_ULL(63)) | (gva & BIT_ULL(63)); +} + static struct kvm_x86_ops vmx_x86_ops __initdata = { .name = KBUILD_MODNAME, @@ -8358,6 +8424,8 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = { .complete_emulated_msr = kvm_complete_insn_gp, .vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector, + + .get_untagged_addr = vmx_get_untagged_addr, }; static unsigned int vmx_handle_intel_pt_intr(void) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index c2130d2c8e..e3b0985bb7 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -241,9 +241,11 @@ struct nested_vmx { bool guest_mode; } smm; +#ifdef CONFIG_KVM_HYPERV gpa_t hv_evmcs_vmptr; struct kvm_host_map hv_evmcs_map; struct hv_enlightened_vmcs *hv_evmcs; +#endif }; struct vcpu_vmx { @@ -420,6 +422,8 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type); u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); +gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags); + static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool value) { @@ -745,14 +749,4 @@ static inline bool vmx_can_use_ipiv(struct kvm_vcpu *vcpu) return lapic_in_kernel(vcpu) && enable_ipiv; } -static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) -{ - /* - * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and - * eVMCS has been explicitly enabled by userspace. - */ - return vcpu->arch.hyperv_enabled && - to_vmx(vcpu)->nested.enlightened_vmcs_enabled; -} - #endif /* __KVM_X86_VMX_H */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.c b/arch/x86/kvm/vmx/vmx_onhyperv.c new file mode 100644 index 0000000000..b9a8b91166 --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "capabilities.h" +#include "vmx_onhyperv.h" + +DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +/* + * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption + * is: in case a feature has corresponding fields in eVMCS described and it was + * exposed in VMX feature MSRs, KVM is free to use it. Warn if KVM meets a + * feature which has no corresponding eVMCS field, this likely means that KVM + * needs to be updated. + */ +#define evmcs_check_vmcs_conf(field, ctrl) \ + do { \ + typeof(vmcs_conf->field) unsupported; \ + \ + unsupported = vmcs_conf->field & ~EVMCS1_SUPPORTED_ ## ctrl; \ + if (unsupported) { \ + pr_warn_once(#field " unsupported with eVMCS: 0x%llx\n",\ + (u64)unsupported); \ + vmcs_conf->field &= EVMCS1_SUPPORTED_ ## ctrl; \ + } \ + } \ + while (0) + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf) +{ + evmcs_check_vmcs_conf(cpu_based_exec_ctrl, EXEC_CTRL); + evmcs_check_vmcs_conf(pin_based_exec_ctrl, PINCTRL); + evmcs_check_vmcs_conf(cpu_based_2nd_exec_ctrl, 2NDEXEC); + evmcs_check_vmcs_conf(cpu_based_3rd_exec_ctrl, 3RDEXEC); + evmcs_check_vmcs_conf(vmentry_ctrl, VMENTRY_CTRL); + evmcs_check_vmcs_conf(vmexit_ctrl, VMEXIT_CTRL); +} diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h new file mode 100644 index 0000000000..eb48153bfd --- /dev/null +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -0,0 +1,125 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ +#define __ARCH_X86_KVM_VMX_ONHYPERV_H__ + +#include <asm/hyperv-tlfs.h> +#include <asm/mshyperv.h> + +#include <linux/jump_label.h> + +#include "capabilities.h" +#include "hyperv_evmcs.h" +#include "vmcs12.h" + +#define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) + +#if IS_ENABLED(CONFIG_HYPERV) + +DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +static __always_inline bool kvm_is_using_evmcs(void) +{ + return static_branch_unlikely(&__kvm_is_using_evmcs); +} + +static __always_inline int get_evmcs_offset(unsigned long field, + u16 *clean_field) +{ + int offset = evmcs_field_offset(field, clean_field); + + WARN_ONCE(offset < 0, "accessing unsupported EVMCS field %lx\n", field); + return offset; +} + +static __always_inline void evmcs_write64(unsigned long field, u64 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u64 *)((char *)current_evmcs + offset) = value; + + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write32(unsigned long field, u32 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u32 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline void evmcs_write16(unsigned long field, u16 value) +{ + u16 clean_field; + int offset = get_evmcs_offset(field, &clean_field); + + if (offset < 0) + return; + + *(u16 *)((char *)current_evmcs + offset) = value; + current_evmcs->hv_clean_fields &= ~clean_field; +} + +static __always_inline u64 evmcs_read64(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u64 *)((char *)current_evmcs + offset); +} + +static __always_inline u32 evmcs_read32(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u32 *)((char *)current_evmcs + offset); +} + +static __always_inline u16 evmcs_read16(unsigned long field) +{ + int offset = get_evmcs_offset(field, NULL); + + if (offset < 0) + return 0; + + return *(u16 *)((char *)current_evmcs + offset); +} + +static inline void evmcs_load(u64 phys_addr) +{ + struct hv_vp_assist_page *vp_ap = + hv_get_vp_assist_page(smp_processor_id()); + + if (current_evmcs->hv_enlightenments_control.nested_flush_hypercall) + vp_ap->nested_control.features.directhypercall = 1; + vp_ap->current_nested_vmcs = phys_addr; + vp_ap->enlighten_vmentry = 1; +} + +void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); +#else /* !IS_ENABLED(CONFIG_HYPERV) */ +static __always_inline bool kvm_is_using_evmcs(void) { return false; } +static __always_inline void evmcs_write64(unsigned long field, u64 value) {} +static __always_inline void evmcs_write32(unsigned long field, u32 value) {} +static __always_inline void evmcs_write16(unsigned long field, u16 value) {} +static __always_inline u64 evmcs_read64(unsigned long field) { return 0; } +static __always_inline u32 evmcs_read32(unsigned long field) { return 0; } +static __always_inline u16 evmcs_read16(unsigned long field) { return 0; } +static inline void evmcs_load(u64 phys_addr) {} +#endif /* IS_ENABLED(CONFIG_HYPERV) */ + +#endif /* __ARCH_X86_KVM_VMX_ONHYPERV_H__ */ diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index 6a0c6e81f7..8060e5fc6d 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -6,7 +6,7 @@ #include <asm/vmx.h> -#include "hyperv.h" +#include "vmx_onhyperv.h" #include "vmcs.h" #include "../x86.h" diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 365caf7328..c84927216f 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1284,7 +1284,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) * stuff CR3, e.g. for RSM emulation, and there is no guarantee that * the current vCPU mode is accurate. */ - if (kvm_vcpu_is_illegal_gpa(vcpu, cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, cr3)) return 1; if (is_pae_paging(vcpu) && !load_pdptrs(vcpu, cr3)) @@ -1504,6 +1504,8 @@ static unsigned num_msrs_to_save; static const u32 emulated_msrs_all[] = { MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK, MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW, + +#ifdef CONFIG_KVM_HYPERV HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL, HV_X64_MSR_TIME_REF_COUNT, HV_X64_MSR_REFERENCE_TSC, HV_X64_MSR_TSC_FREQUENCY, HV_X64_MSR_APIC_FREQUENCY, @@ -1521,6 +1523,7 @@ static const u32 emulated_msrs_all[] = { HV_X64_MSR_SYNDBG_CONTROL, HV_X64_MSR_SYNDBG_STATUS, HV_X64_MSR_SYNDBG_SEND_BUFFER, HV_X64_MSR_SYNDBG_RECV_BUFFER, HV_X64_MSR_SYNDBG_PENDING_BUFFER, +#endif MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME, MSR_KVM_PV_EOI_EN, MSR_KVM_ASYNC_PF_INT, MSR_KVM_ASYNC_PF_ACK, @@ -1621,7 +1624,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ - ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR) + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -1704,22 +1707,17 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data) struct kvm_msr_entry msr; int r; + /* Unconditionally clear the output for simplicity */ + msr.data = 0; msr.index = index; r = kvm_get_msr_feature(&msr); - if (r == KVM_MSR_RET_INVALID) { - /* Unconditionally clear the output for simplicity */ - *data = 0; - if (kvm_msr_ignored_check(index, 0, false)) - r = 0; - } - - if (r) - return r; + if (r == KVM_MSR_RET_INVALID && kvm_msr_ignored_check(index, 0, false)) + r = 0; *data = msr.data; - return 0; + return r; } static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) @@ -1782,6 +1780,10 @@ static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((efer ^ old_efer) & KVM_MMU_EFER_ROLE_BITS) kvm_mmu_reset_context(vcpu); + if (!static_cpu_has(X86_FEATURE_XSAVES) && + (efer & EFER_SVME)) + kvm_hv_xsaves_xsavec_maybe_warn(vcpu); + return 0; } @@ -2507,32 +2509,35 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns) } #ifdef CONFIG_X86_64 -static inline int gtod_is_based_on_tsc(int mode) +static inline bool gtod_is_based_on_tsc(int mode) { return mode == VDSO_CLOCKMODE_TSC || mode == VDSO_CLOCKMODE_HVCLOCK; } #endif -static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu) +static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu, bool new_generation) { #ifdef CONFIG_X86_64 - bool vcpus_matched; struct kvm_arch *ka = &vcpu->kvm->arch; struct pvclock_gtod_data *gtod = &pvclock_gtod_data; - vcpus_matched = (ka->nr_vcpus_matched_tsc + 1 == - atomic_read(&vcpu->kvm->online_vcpus)); + /* + * To use the masterclock, the host clocksource must be based on TSC + * and all vCPUs must have matching TSCs. Note, the count for matching + * vCPUs doesn't include the reference vCPU, hence "+1". + */ + bool use_master_clock = (ka->nr_vcpus_matched_tsc + 1 == + atomic_read(&vcpu->kvm->online_vcpus)) && + gtod_is_based_on_tsc(gtod->clock.vclock_mode); /* - * Once the masterclock is enabled, always perform request in - * order to update it. - * - * In order to enable masterclock, the host clocksource must be TSC - * and the vcpus need to have matched TSCs. When that happens, - * perform request to enable masterclock. + * Request a masterclock update if the masterclock needs to be toggled + * on/off, or when starting a new generation and the masterclock is + * enabled (compute_guest_tsc() requires the masterclock snapshot to be + * taken _after_ the new generation is created). */ - if (ka->use_master_clock || - (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched)) + if ((ka->use_master_clock && new_generation) || + (ka->use_master_clock != use_master_clock)) kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu); trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc, @@ -2709,7 +2714,7 @@ static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc, vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec; vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write; - kvm_track_tsc_matching(vcpu); + kvm_track_tsc_matching(vcpu, !matched); } static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 *user_value) @@ -3107,7 +3112,8 @@ u64 get_kvmclock_ns(struct kvm *kvm) static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, struct gfn_to_pfn_cache *gpc, - unsigned int offset) + unsigned int offset, + bool force_tsc_unstable) { struct kvm_vcpu_arch *vcpu = &v->arch; struct pvclock_vcpu_time_info *guest_hv_clock; @@ -3144,6 +3150,10 @@ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v, } memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock)); + + if (force_tsc_unstable) + guest_hv_clock->flags &= ~PVCLOCK_TSC_STABLE_BIT; + smp_wmb(); guest_hv_clock->version = ++vcpu->hv_clock.version; @@ -3164,6 +3174,16 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) u64 tsc_timestamp, host_tsc; u8 pvclock_flags; bool use_master_clock; +#ifdef CONFIG_KVM_XEN + /* + * For Xen guests we may need to override PVCLOCK_TSC_STABLE_BIT as unless + * explicitly told to use TSC as its clocksource Xen will not set this bit. + * This default behaviour led to bugs in some guest kernels which cause + * problems if they observe PVCLOCK_TSC_STABLE_BIT in the pvclock flags. + */ + bool xen_pvclock_tsc_unstable = + ka->xen_hvm_config.flags & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; +#endif kernel_ns = 0; host_tsc = 0; @@ -3242,13 +3262,15 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->hv_clock.flags = pvclock_flags; if (vcpu->pv_time.active) - kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0); + kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0, false); #ifdef CONFIG_KVM_XEN if (vcpu->xen.vcpu_info_cache.active) kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache, - offsetof(struct compat_vcpu_info, time)); + offsetof(struct compat_vcpu_info, time), + xen_pvclock_tsc_unstable); if (vcpu->xen.vcpu_time_info_cache.active) - kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0); + kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0, + xen_pvclock_tsc_unstable); #endif kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock); return 0; @@ -3400,7 +3422,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; @@ -4023,6 +4045,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * the need to ignore the workaround. */ break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4035,6 +4058,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case HV_X64_MSR_TSC_INVARIANT_CONTROL: return kvm_hv_set_msr_common(vcpu, msr, data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* Drop writes to this legacy MSR -- see rdmsr * counterpart for further detail. @@ -4380,6 +4404,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ msr_info->data = 0x20000000; break; +#ifdef CONFIG_KVM_HYPERV case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15: case HV_X64_MSR_SYNDBG_CONTROL ... HV_X64_MSR_SYNDBG_PENDING_BUFFER: case HV_X64_MSR_SYNDBG_OPTIONS: @@ -4393,6 +4418,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return kvm_hv_get_msr_common(vcpu, msr_info->index, &msr_info->data, msr_info->host_initiated); +#endif case MSR_IA32_BBL_CR_CTL3: /* This legacy MSR exists but isn't fully documented in current * silicon. It is however accessed by winxp in very narrow @@ -4530,6 +4556,7 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +#ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) { @@ -4550,6 +4577,14 @@ static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, return 0; } +#endif + +static bool kvm_is_vm_type_supported(unsigned long type) +{ + return type == KVM_X86_DEFAULT_VM || + (type == KVM_X86_SW_PROTECTED_VM && + IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled); +} int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) { @@ -4576,9 +4611,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: case KVM_CAP_VCPU_EVENTS: +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV: case KVM_CAP_HYPERV_VAPIC: case KVM_CAP_HYPERV_SPIN: + case KVM_CAP_HYPERV_TIME: case KVM_CAP_HYPERV_SYNIC: case KVM_CAP_HYPERV_SYNIC2: case KVM_CAP_HYPERV_VP_INDEX: @@ -4588,6 +4625,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_HYPERV_CPUID: case KVM_CAP_HYPERV_ENFORCE_CPUID: case KVM_CAP_SYS_HYPERV_CPUID: +#endif case KVM_CAP_PCI_SEGMENT: case KVM_CAP_DEBUGREGS: case KVM_CAP_X86_ROBUST_SINGLESTEP: @@ -4597,7 +4635,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_GET_TSC_KHZ: case KVM_CAP_KVMCLOCK_CTRL: case KVM_CAP_READONLY_MEM: - case KVM_CAP_HYPERV_TIME: case KVM_CAP_IOAPIC_POLARITY_IGNORED: case KVM_CAP_TSC_DEADLINE_TIMER: case KVM_CAP_DISABLE_QUIRKS: @@ -4628,6 +4665,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP: case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES: case KVM_CAP_IRQFD_RESAMPLE: + case KVM_CAP_MEMORY_FAULT_INFO: r = 1; break; case KVM_CAP_EXIT_HYPERCALL: @@ -4641,7 +4679,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | KVM_XEN_HVM_CONFIG_SHARED_INFO | KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; if (sched_info_on()) r |= KVM_XEN_HVM_CONFIG_RUNSTATE | KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; @@ -4707,12 +4746,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = kvm_x86_ops.nested_ops->get_state ? kvm_x86_ops.nested_ops->get_state(NULL, NULL, 0) : 0; break; +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: r = kvm_x86_ops.enable_l2_tlb_flush != NULL; break; case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: r = kvm_x86_ops.nested_ops->enable_evmcs != NULL; break; +#endif case KVM_CAP_SMALLER_MAXPHYADDR: r = (int) allow_smaller_maxphyaddr; break; @@ -4741,6 +4782,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_X86_NOTIFY_VMEXIT: r = kvm_caps.has_notify_vmexit; break; + case KVM_CAP_VM_TYPES: + r = BIT(KVM_X86_DEFAULT_VM); + if (kvm_is_vm_type_supported(KVM_X86_SW_PROTECTED_VM)) + r |= BIT(KVM_X86_SW_PROTECTED_VM); + break; default: break; } @@ -4874,9 +4920,11 @@ long kvm_arch_dev_ioctl(struct file *filp, case KVM_GET_MSRS: r = msr_io(NULL, argp, do_get_msr_feature, 1); break; +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp); break; +#endif case KVM_GET_DEVICE_ATTR: { struct kvm_device_attr attr; r = -EFAULT; @@ -5703,14 +5751,11 @@ static int kvm_vcpu_ioctl_device_attr(struct kvm_vcpu *vcpu, static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, struct kvm_enable_cap *cap) { - int r; - uint16_t vmcs_version; - void __user *user_ptr; - if (cap->flags) return -EINVAL; switch (cap->cap) { +#ifdef CONFIG_KVM_HYPERV case KVM_CAP_HYPERV_SYNIC2: if (cap->args[0]) return -EINVAL; @@ -5722,16 +5767,22 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, return kvm_hv_activate_synic(vcpu, cap->cap == KVM_CAP_HYPERV_SYNIC2); case KVM_CAP_HYPERV_ENLIGHTENED_VMCS: - if (!kvm_x86_ops.nested_ops->enable_evmcs) - return -ENOTTY; - r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); - if (!r) { - user_ptr = (void __user *)(uintptr_t)cap->args[0]; - if (copy_to_user(user_ptr, &vmcs_version, - sizeof(vmcs_version))) - r = -EFAULT; + { + int r; + uint16_t vmcs_version; + void __user *user_ptr; + + if (!kvm_x86_ops.nested_ops->enable_evmcs) + return -ENOTTY; + r = kvm_x86_ops.nested_ops->enable_evmcs(vcpu, &vmcs_version); + if (!r) { + user_ptr = (void __user *)(uintptr_t)cap->args[0]; + if (copy_to_user(user_ptr, &vmcs_version, + sizeof(vmcs_version))) + r = -EFAULT; + } + return r; } - return r; case KVM_CAP_HYPERV_DIRECT_TLBFLUSH: if (!kvm_x86_ops.enable_l2_tlb_flush) return -ENOTTY; @@ -5740,6 +5791,7 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_HYPERV_ENFORCE_CPUID: return kvm_hv_set_enforce_cpuid(vcpu, cap->args[0]); +#endif case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; @@ -6132,9 +6184,11 @@ long kvm_arch_vcpu_ioctl(struct file *filp, srcu_read_unlock(&vcpu->kvm->srcu, idx); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_GET_SUPPORTED_HV_CPUID: r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp); break; +#endif #ifdef CONFIG_KVM_XEN case KVM_XEN_VCPU_GET_ATTR: { struct kvm_xen_vcpu_attr xva; @@ -6965,6 +7019,9 @@ set_identity_unlock: r = -EEXIST; if (kvm->arch.vpit) goto create_pit_unlock; + r = -ENOENT; + if (!pic_in_kernel(kvm)) + goto create_pit_unlock; r = -ENOMEM; kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags); if (kvm->arch.vpit) @@ -7192,6 +7249,7 @@ set_pit2_out: r = static_call(kvm_x86_mem_enc_unregister_region)(kvm, ®ion); break; } +#ifdef CONFIG_KVM_HYPERV case KVM_HYPERV_EVENTFD: { struct kvm_hyperv_eventfd hvevfd; @@ -7201,6 +7259,7 @@ set_pit2_out: r = kvm_vm_ioctl_hv_eventfd(kvm, &hvevfd); break; } +#endif case KVM_SET_PMU_EVENT_FILTER: r = kvm_vm_ioctl_set_pmu_event_filter(kvm, argp); break; @@ -8446,6 +8505,15 @@ static void emulator_vm_bugged(struct x86_emulate_ctxt *ctxt) kvm_vm_bugged(kvm); } +static gva_t emulator_get_untagged_addr(struct x86_emulate_ctxt *ctxt, + gva_t addr, unsigned int flags) +{ + if (!kvm_x86_ops.get_untagged_addr) + return addr; + + return static_call(kvm_x86_get_untagged_addr)(emul_to_vcpu(ctxt), addr, flags); +} + static const struct x86_emulate_ops emulate_ops = { .vm_bugged = emulator_vm_bugged, .read_gpr = emulator_read_gpr, @@ -8490,6 +8558,7 @@ static const struct x86_emulate_ops emulate_ops = { .leave_smm = emulator_leave_smm, .triple_fault = emulator_triple_fault, .set_xcr = emulator_set_xcr, + .get_untagged_addr = emulator_get_untagged_addr, }; static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask) @@ -10179,7 +10248,7 @@ 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 @@ -10200,7 +10269,7 @@ 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. */ @@ -10589,19 +10658,20 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu) static void vcpu_load_eoi_exitmap(struct kvm_vcpu *vcpu) { - u64 eoi_exit_bitmap[4]; - if (!kvm_apic_hw_enabled(vcpu->arch.apic)) return; +#ifdef CONFIG_KVM_HYPERV if (to_hv_vcpu(vcpu)) { + u64 eoi_exit_bitmap[4]; + bitmap_or((ulong *)eoi_exit_bitmap, vcpu->arch.ioapic_handled_vectors, to_hv_synic(vcpu)->vec_bitmap, 256); static_call_cond(kvm_x86_load_eoi_exitmap)(vcpu, eoi_exit_bitmap); return; } - +#endif static_call_cond(kvm_x86_load_eoi_exitmap)( vcpu, (u64 *)vcpu->arch.ioapic_handled_vectors); } @@ -10692,9 +10762,11 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) * the flushes are considered "remote" and not "local" because * the requests can be initiated from other vCPUs. */ +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu) && kvm_hv_vcpu_flush_tlb(vcpu)) kvm_vcpu_flush_tlb_guest(vcpu); +#endif if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS; @@ -10747,6 +10819,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu_load_eoi_exitmap(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) kvm_vcpu_reload_apic_access_page(vcpu); +#ifdef CONFIG_KVM_HYPERV if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) { vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT; vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH; @@ -10777,6 +10850,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) */ if (kvm_check_request(KVM_REQ_HV_STIMER, vcpu)) kvm_hv_process_stimers(vcpu); +#endif if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu)) kvm_vcpu_update_apicv(vcpu); if (kvm_check_request(KVM_REQ_APF_READY, vcpu)) @@ -10898,7 +10972,7 @@ 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)) && @@ -11095,6 +11169,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu) { int r; + vcpu->run->exit_reason = KVM_EXIT_UNKNOWN; vcpu->arch.l1tf_flush_l1d = true; for (;;) { @@ -11612,7 +11687,7 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs) */ if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA)) return false; - if (kvm_vcpu_is_illegal_gpa(vcpu, sregs->cr3)) + if (!kvm_vcpu_is_legal_cr3(vcpu, sregs->cr3)) return false; } else { /* @@ -12221,7 +12296,6 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event) } if (!init_event) { - kvm_pmu_reset(vcpu); vcpu->arch.smbase = 0x30000; vcpu->arch.msr_misc_features_enables = 0; @@ -12438,7 +12512,9 @@ void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) void kvm_arch_free_vm(struct kvm *kvm) { - kfree(to_kvm_hv(kvm)->hv_pa_pg); +#if IS_ENABLED(CONFIG_HYPERV) + kfree(kvm->arch.hv_pa_pg); +#endif __kvm_arch_free_vm(kvm); } @@ -12448,9 +12524,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) int ret; unsigned long flags; - if (type) + if (!kvm_is_vm_type_supported(type)) return -EINVAL; + kvm->arch.vm_type = type; + ret = kvm_page_track_init(kvm); if (ret) goto out; @@ -12589,8 +12667,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, hva = slot->userspace_addr; } - for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { - struct kvm_userspace_memory_region m; + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { + struct kvm_userspace_memory_region2 m; m.slot = id | (i << 16); m.flags = 0; @@ -12740,6 +12818,10 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, } } +#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES + kvm_mmu_init_memslot_memory_attributes(kvm, slot); +#endif + if (kvm_page_track_create_memslot(kvm, slot, npages)) goto out_free; @@ -13550,6 +13632,10 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) switch (type) { case INVPCID_TYPE_INDIV_ADDR: + /* + * LAM doesn't apply to addresses that are inputs to TLB + * invalidation. + */ if ((!pcid_enabled && (operand.pcid != 0)) || is_noncanonical_address(operand.gla, vcpu)) { kvm_inject_gp(vcpu, 0); diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index 5184fde1dc..2f7e191666 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -530,6 +530,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type); __reserved_bits |= X86_CR4_VMXE; \ if (!__cpu_has(__c, X86_FEATURE_PCID)) \ __reserved_bits |= X86_CR4_PCIDE; \ + if (!__cpu_has(__c, X86_FEATURE_LAM)) \ + __reserved_bits |= X86_CR4_LAM_SUP; \ __reserved_bits; \ }) diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index c069521f24..b0212ba2d8 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -1162,7 +1162,9 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) { /* Only some feature flags need to be *enabled* by userspace */ u32 permitted_flags = KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL | - KVM_XEN_HVM_CONFIG_EVTCHN_SEND; + KVM_XEN_HVM_CONFIG_EVTCHN_SEND | + KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE; + u32 old_flags; if (xhc->flags & ~permitted_flags) return -EINVAL; @@ -1183,9 +1185,14 @@ int kvm_xen_hvm_config(struct kvm *kvm, struct kvm_xen_hvm_config *xhc) else if (!xhc->msr && kvm->arch.xen_hvm_config.msr) static_branch_slow_dec_deferred(&kvm_xen_enabled); + old_flags = kvm->arch.xen_hvm_config.flags; memcpy(&kvm->arch.xen_hvm_config, xhc, sizeof(*xhc)); mutex_unlock(&kvm->arch.xen.xen_lock); + + if ((old_flags ^ xhc->flags) & KVM_XEN_HVM_CONFIG_PVCLOCK_TSC_UNSTABLE) + kvm_make_all_cpus_request(kvm, KVM_REQ_CLOCK_UPDATE); + return 0; } diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index ea3a28e7b6..f0dae4fb6d 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -14,19 +14,6 @@ ifdef CONFIG_KCSAN CFLAGS_REMOVE_delay.o = $(CC_FLAGS_FTRACE) endif -# Early boot use of cmdline; don't instrument it -ifdef CONFIG_AMD_MEM_ENCRYPT -KCOV_INSTRUMENT_cmdline.o := n -KASAN_SANITIZE_cmdline.o := n -KCSAN_SANITIZE_cmdline.o := n - -ifdef CONFIG_FUNCTION_TRACER -CFLAGS_REMOVE_cmdline.o = -pg -endif - -CFLAGS_cmdline.o := -fno-stack-protector -fno-jump-tables -endif - inat_tables_script = $(srctree)/arch/x86/tools/gen-insn-attr-x86.awk inat_tables_maps = $(srctree)/arch/x86/lib/x86-opcode-map.txt quiet_cmd_inat_tables = GEN $@ diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c index 7c48ff4ae8..7af743bd3b 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/delay.c b/arch/x86/lib/delay.c index 0e65d00e23..23f81ca3f0 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/retpoline.S b/arch/x86/lib/retpoline.S index 1e59367b46..5b26a952e2 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -229,8 +229,12 @@ SYM_CODE_END(srso_return_thunk) #define JMP_SRSO_UNTRAIN_RET "ud2" /* Dummy for the alternative in CALL_UNTRAIN_RET. */ SYM_CODE_START(srso_alias_untrain_ret) - RET + ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR + ret + int3 SYM_FUNC_END(srso_alias_untrain_ret) +__EXPORT_THUNK(srso_alias_untrain_ret) #endif /* CONFIG_CPU_SRSO */ #ifdef CONFIG_CPU_UNRET_ENTRY diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index d6375b3c63..b01df023de 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -376,7 +376,7 @@ static void dump_pagetable(unsigned long address) goto bad; pr_cont("PUD %lx ", pud_val(*pud)); - if (!pud_present(*pud) || pud_large(*pud)) + if (!pud_present(*pud) || pud_leaf(*pud)) goto out; pmd = pmd_offset(pud, address); @@ -1037,7 +1037,7 @@ spurious_kernel_fault(unsigned long error_code, unsigned long address) if (!pud_present(*pud)) return 0; - if (pud_large(*pud)) + if (pud_leaf(*pud)) return spurious_kernel_fault_check(error_code, (pte_t *) pud); pmd = pmd_offset(pud, address); diff --git a/arch/x86/mm/ident_map.c b/arch/x86/mm/ident_map.c index f50cc210a9..968d7005f4 100644 --- a/arch/x86/mm/ident_map.c +++ b/arch/x86/mm/ident_map.c @@ -26,31 +26,18 @@ static int ident_pud_init(struct x86_mapping_info *info, pud_t *pud_page, for (; addr < end; addr = next) { pud_t *pud = pud_page + pud_index(addr); pmd_t *pmd; - bool use_gbpage; next = (addr & PUD_MASK) + PUD_SIZE; if (next > end) next = end; - /* if this is already a gbpage, this portion is already mapped */ - if (pud_large(*pud)) - continue; - - /* Is using a gbpage allowed? */ - use_gbpage = info->direct_gbpages; - - /* Don't use gbpage if it maps more than the requested region. */ - /* at the begining: */ - use_gbpage &= ((addr & ~PUD_MASK) == 0); - /* ... or at the end: */ - use_gbpage &= ((next & ~PUD_MASK) == 0); - - /* Never overwrite existing mappings */ - use_gbpage &= !pud_present(*pud); - - if (use_gbpage) { + if (info->direct_gbpages) { pud_t pudval; + if (pud_present(*pud)) + continue; + + addr &= PUD_MASK; pudval = __pud((addr - info->offset) | info->page_flag); set_pud(pud, pudval); continue; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index a190aae8ce..534436c9d3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -617,7 +617,7 @@ phys_pud_init(pud_t *pud_page, unsigned long paddr, unsigned long paddr_end, } if (!pud_none(*pud)) { - if (!pud_large(*pud)) { + if (!pud_leaf(*pud)) { pmd = pmd_offset(pud, 0); paddr_last = phys_pmd_init(pmd, paddr, paddr_end, @@ -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); @@ -1163,7 +1163,7 @@ remove_pud_table(pud_t *pud_start, unsigned long addr, unsigned long end, if (!pud_present(*pud)) continue; - if (pud_large(*pud) && + if (pud_leaf(*pud) && IS_ALIGNED(addr, PUD_SIZE) && IS_ALIGNED(next, PUD_SIZE)) { spin_lock(&init_mm.page_table_lock); diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 0302491d79..fcf508c52b 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -115,7 +115,7 @@ static void __init kasan_populate_p4d(p4d_t *p4d, unsigned long addr, pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); - if (!pud_large(*pud)) + if (!pud_leaf(*pud)) kasan_populate_pud(pud, addr, next, nid); } while (pud++, addr = next, addr != end); } diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index 0166ab1780..cc47a818a6 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -41,9 +41,9 @@ #include <linux/mem_encrypt.h> #include <linux/cc_platform.h> +#include <asm/init.h> #include <asm/setup.h> #include <asm/sections.h> -#include <asm/cmdline.h> #include <asm/coco.h> #include <asm/sev.h> @@ -95,10 +95,7 @@ struct sme_populate_pgd_data { */ static char sme_workarea[2 * PMD_SIZE] __section(".init.scratch"); -static char sme_cmdline_arg[] __initdata = "mem_encrypt"; -static char sme_cmdline_on[] __initdata = "on"; - -static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_clear_pgd(struct sme_populate_pgd_data *ppd) { unsigned long pgd_start, pgd_end, pgd_size; pgd_t *pgd_p; @@ -113,7 +110,7 @@ static void __init sme_clear_pgd(struct sme_populate_pgd_data *ppd) memset(pgd_p, 0, pgd_size); } -static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) +static pud_t __head *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) { pgd_t *pgd; p4d_t *p4d; @@ -144,13 +141,13 @@ static pud_t __init *sme_prepare_pgd(struct sme_populate_pgd_data *ppd) set_pud(pud, __pud(PUD_FLAGS | __pa(pmd))); } - if (pud_large(*pud)) + if (pud_leaf(*pud)) return NULL; return pud; } -static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -166,7 +163,7 @@ static void __init sme_populate_pgd_large(struct sme_populate_pgd_data *ppd) set_pmd(pmd, __pmd(ppd->paddr | ppd->pmd_flags)); } -static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) +static void __head sme_populate_pgd(struct sme_populate_pgd_data *ppd) { pud_t *pud; pmd_t *pmd; @@ -192,7 +189,7 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd) set_pte(pte, __pte(ppd->paddr | ppd->pte_flags)); } -static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd_large(ppd); @@ -202,7 +199,7 @@ static void __init __sme_map_range_pmd(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) +static void __head __sme_map_range_pte(struct sme_populate_pgd_data *ppd) { while (ppd->vaddr < ppd->vaddr_end) { sme_populate_pgd(ppd); @@ -212,7 +209,7 @@ static void __init __sme_map_range_pte(struct sme_populate_pgd_data *ppd) } } -static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, +static void __head __sme_map_range(struct sme_populate_pgd_data *ppd, pmdval_t pmd_flags, pteval_t pte_flags) { unsigned long vaddr_end; @@ -236,22 +233,22 @@ static void __init __sme_map_range(struct sme_populate_pgd_data *ppd, __sme_map_range_pte(ppd); } -static void __init sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_encrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_ENC, PTE_FLAGS_ENC); } -static void __init sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC, PTE_FLAGS_DEC); } -static void __init sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) +static void __head sme_map_range_decrypted_wp(struct sme_populate_pgd_data *ppd) { __sme_map_range(ppd, PMD_FLAGS_DEC_WP, PTE_FLAGS_DEC_WP); } -static unsigned long __init sme_pgtable_calc(unsigned long len) +static unsigned long __head sme_pgtable_calc(unsigned long len) { unsigned long entries = 0, tables = 0; @@ -288,7 +285,7 @@ static unsigned long __init sme_pgtable_calc(unsigned long len) return entries + tables; } -void __init sme_encrypt_kernel(struct boot_params *bp) +void __head sme_encrypt_kernel(struct boot_params *bp) { unsigned long workarea_start, workarea_end, workarea_len; unsigned long execute_start, execute_end, execute_len; @@ -323,9 +320,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * memory from being cached. */ - /* Physical addresses gives us the identity mapped virtual addresses */ - kernel_start = __pa_symbol(_text); - kernel_end = ALIGN(__pa_symbol(_end), PMD_SIZE); + kernel_start = (unsigned long)RIP_REL_REF(_text); + kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE); kernel_len = kernel_end - kernel_start; initrd_start = 0; @@ -343,14 +339,6 @@ void __init sme_encrypt_kernel(struct boot_params *bp) #endif /* - * We're running identity mapped, so we must obtain the address to the - * SME encryption workarea using rip-relative addressing. - */ - asm ("lea sme_workarea(%%rip), %0" - : "=r" (workarea_start) - : "p" (sme_workarea)); - - /* * Calculate required number of workarea bytes needed: * executable encryption area size: * stack page (PAGE_SIZE) @@ -359,7 +347,7 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * pagetable structures for the encryption of the kernel * pagetable structures for workarea (in case not currently mapped) */ - execute_start = workarea_start; + execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea); execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE; execute_len = execute_end - execute_start; @@ -502,13 +490,11 @@ void __init sme_encrypt_kernel(struct boot_params *bp) native_write_cr3(__native_read_cr3()); } -void __init sme_enable(struct boot_params *bp) +void __head sme_enable(struct boot_params *bp) { - const char *cmdline_ptr, *cmdline_arg, *cmdline_on; unsigned int eax, ebx, ecx, edx; unsigned long feature_mask; unsigned long me_mask; - char buffer[16]; bool snp; u64 msr; @@ -551,6 +537,9 @@ void __init sme_enable(struct boot_params *bp) /* Check if memory encryption is enabled */ if (feature_mask == AMD_SME_BIT) { + if (!(bp->hdr.xloadflags & XLF_MEM_ENCRYPTION)) + return; + /* * No SME if Hypervisor bit is set. This check is here to * prevent a guest from trying to enable SME. For running as a @@ -570,31 +559,8 @@ void __init sme_enable(struct boot_params *bp) msr = __rdmsr(MSR_AMD64_SYSCFG); if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT)) return; - } else { - /* SEV state cannot be controlled by a command line option */ - goto out; } - /* - * Fixups have not been applied to phys_base yet and we're running - * identity mapped, so we must obtain the address to the SME command - * line argument data using rip-relative addressing. - */ - asm ("lea sme_cmdline_arg(%%rip), %0" - : "=r" (cmdline_arg) - : "p" (sme_cmdline_arg)); - asm ("lea sme_cmdline_on(%%rip), %0" - : "=r" (cmdline_on) - : "p" (sme_cmdline_on)); - - cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | - ((u64)bp->ext_cmd_line_ptr << 32)); - - if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0 || - strncmp(buffer, cmdline_on, sizeof(buffer))) - return; - -out: RIP_REL_REF(sme_me_mask) = me_mask; physical_mask &= ~me_mask; cc_vendor = CC_VENDOR_AMD; diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 9d63cfff1f..65e9a6e391 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 de10800cd4..37d51cfd77 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 @@ -950,6 +950,38 @@ static void free_pfn_range(u64 paddr, unsigned long size) memtype_free(paddr, paddr + size); } +static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr, + pgprot_t *pgprot) +{ + unsigned long prot; + + VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT)); + + /* + * We need the starting PFN and cachemode used for track_pfn_remap() + * that covered the whole VMA. For most mappings, we can obtain that + * information from the page tables. For COW mappings, we might now + * suddenly have anon folios mapped and follow_phys() will fail. + * + * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to + * detect the PFN. If we need the cachemode as well, we're out of luck + * for now and have to fail fork(). + */ + if (!follow_phys(vma, vma->vm_start, 0, &prot, paddr)) { + if (pgprot) + *pgprot = __pgprot(prot); + return 0; + } + if (is_cow_mapping(vma->vm_flags)) { + if (pgprot) + return -EINVAL; + *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT; + return 0; + } + WARN_ON_ONCE(1); + return -EINVAL; +} + /* * track_pfn_copy is called when vma that is covering the pfnmap gets * copied through copy_page_range(). @@ -960,20 +992,13 @@ static void free_pfn_range(u64 paddr, unsigned long size) int track_pfn_copy(struct vm_area_struct *vma) { resource_size_t paddr; - unsigned long prot; unsigned long vma_size = vma->vm_end - vma->vm_start; pgprot_t pgprot; if (vma->vm_flags & VM_PAT) { - /* - * reserve the whole chunk covered by vma. We need the - * starting address and protection from pte. - */ - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, &pgprot)) return -EINVAL; - } - pgprot = __pgprot(prot); + /* reserve the whole chunk covered by vma. */ return reserve_pfn_range(paddr, vma_size, &pgprot, 1); } @@ -1048,7 +1073,6 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, unsigned long size, bool mm_wr_locked) { resource_size_t paddr; - unsigned long prot; if (vma && !(vma->vm_flags & VM_PAT)) return; @@ -1056,11 +1080,8 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, /* free the chunk starting from pfn or the whole chunk */ paddr = (resource_size_t)pfn << PAGE_SHIFT; if (!paddr && !size) { - if (follow_phys(vma, vma->vm_start, 0, &prot, &paddr)) { - WARN_ON_ONCE(1); + if (get_pat_info(vma, &paddr, NULL)) return; - } - size = vma->vm_end - vma->vm_start; } free_pfn_range(paddr, size); diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c index bda9f12983..135bb594df 100644 --- a/arch/x86/mm/pat/set_memory.c +++ b/arch/x86/mm/pat/set_memory.c @@ -684,7 +684,7 @@ pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, return NULL; *level = PG_LEVEL_1G; - if (pud_large(*pud) || !pud_present(*pud)) + if (pud_leaf(*pud) || !pud_present(*pud)) return (pte_t *)pud; pmd = pmd_offset(pud, address); @@ -743,7 +743,7 @@ pmd_t *lookup_pmd_address(unsigned long address) return NULL; pud = pud_offset(p4d, address); - if (pud_none(*pud) || pud_large(*pud) || !pud_present(*pud)) + if (pud_none(*pud) || pud_leaf(*pud) || !pud_present(*pud)) return NULL; return pmd_offset(pud, address); @@ -755,10 +755,14 @@ pmd_t *lookup_pmd_address(unsigned long address) * areas on 32-bit NUMA systems. The percpu areas can * end up in this kind of memory, for instance. * - * This could be optimized, but it is only intended to be - * used at initialization time, and keeping it - * unoptimized should increase the testing coverage for - * the more obscure platforms. + * Note that as long as the PTEs are well-formed with correct PFNs, this + * works without checking the PRESENT bit in the leaf PTE. This is unlike + * the similar vmalloc_to_page() and derivatives. Callers may depend on + * this behavior. + * + * This could be optimized, but it is only used in paths that are not perf + * sensitive, and keeping it unoptimized should increase the testing coverage + * for the more obscure platforms. */ phys_addr_t slow_virt_to_phys(void *__virt_addr) { @@ -1274,7 +1278,7 @@ static void unmap_pud_range(p4d_t *p4d, unsigned long start, unsigned long end) */ while (end - start >= PUD_SIZE) { - if (pud_large(*pud)) + if (pud_leaf(*pud)) pud_clear(pud); else unmap_pmd_range(pud, start, start + PUD_SIZE); @@ -1621,7 +1625,7 @@ 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); @@ -2041,17 +2045,12 @@ int set_mce_nospec(unsigned long pfn) return rc; } -static int set_memory_p(unsigned long *addr, int numpages) -{ - return change_page_attr_set(addr, numpages, __pgprot(_PAGE_PRESENT), 0); -} - /* Restore full speculative operation to the pfn. */ int clear_mce_nospec(unsigned long pfn) { unsigned long addr = (unsigned long) pfn_to_kaddr(pfn); - return set_memory_p(&addr, 1); + return set_memory_p(addr, 1); } EXPORT_SYMBOL_GPL(clear_mce_nospec); #endif /* CONFIG_X86_64 */ @@ -2104,6 +2103,11 @@ int set_memory_np_noalias(unsigned long addr, int numpages) CPA_NO_CHECK_ALIAS, NULL); } +int set_memory_p(unsigned long addr, int numpages) +{ + return change_page_attr_set(&addr, numpages, __pgprot(_PAGE_PRESENT), 0); +} + int set_memory_4k(unsigned long addr, int numpages) { return change_page_attr_set_clr(&addr, numpages, __pgprot(0), @@ -2447,7 +2451,7 @@ 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/pgtable.c b/arch/x86/mm/pgtable.c index 0cbc1b8e8e..a67bb8f982 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -777,7 +777,7 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot) */ int pud_clear_huge(pud_t *pud) { - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { pud_clear(pud); return 1; } diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 5dd7339446..912b1da7ed 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> @@ -217,7 +217,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) pud = pud_offset(p4d, address); /* The user page tables do not use large mappings: */ - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { WARN_ON(1); return NULL; } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index 453ea95b66..5768d386ef 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 e89e415aa7..df484885cc 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, @@ -382,7 +466,7 @@ static int emit_call(u8 **pprog, void *func, void *ip) static int emit_rsb_call(u8 **pprog, void *func, void *ip) { OPTIMIZER_HIDE_VAR(func); - x86_call_depth_emit_accounting(pprog, func); + ip += x86_call_depth_emit_accounting(pprog, func); return emit_patch(pprog, func, ip, 0xE8); } @@ -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)); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c index 429a89c546..b18ce19981 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/acpi.c b/arch/x86/pci/acpi.c index ea2eb2ec90..55c4b07ec1 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -283,6 +283,9 @@ static int setup_mcfg_map(struct acpi_pci_root_info *ci) info->mcfg_added = false; seg = info->sd.domain; + dev_dbg(dev, "%s(%04x %pR ECAM %pa)\n", __func__, seg, + &root->secondary, &root->mcfg_addr); + /* return success if MMCFG is not in use */ if (raw_pci_ext_ops && raw_pci_ext_ops != &pci_mmcfg) return 0; diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index f347c20247..b33afb2406 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -907,6 +907,54 @@ static void chromeos_fixup_apl_pci_l1ss_capability(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_save_apl_pci_l1ss_capability); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_INTEL, 0x5ad6, chromeos_fixup_apl_pci_l1ss_capability); +/* + * Disable D3cold on Asus B1400 PCI-NVMe bridge + * + * On this platform with VMD off, the NVMe device cannot successfully power + * back on from D3cold. This appears to be an untested transition by the + * vendor: Windows leaves the NVMe and parent bridge in D0 during suspend. + * + * We disable D3cold on the parent bridge for simplicity, and the fact that + * both parent bridge and NVMe device share the same power resource. + * + * This is only needed on BIOS versions before 308; the newer versions flip + * StorageD3Enable from 1 to 0. + */ +static const struct dmi_system_id asus_nvme_broken_d3cold_table[] = { + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.304"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.305"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.306"), + }, + }, + { + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BIOS_VERSION, "B1400CEAE.307"), + }, + }, + {} +}; + +static void asus_disable_nvme_d3cold(struct pci_dev *pdev) +{ + if (dmi_check_system(asus_nvme_broken_d3cold_table) > 0) + pci_d3cold_disable(pdev); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x9a09, asus_disable_nvme_d3cold); + #ifdef CONFIG_SUSPEND /* * Root Ports on some AMD SoCs advertise PME_Support for D3hot and D3cold, but diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c index e9497ee0f8..0cc9520666 100644 --- a/arch/x86/pci/mmconfig-shared.c +++ b/arch/x86/pci/mmconfig-shared.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* - * mmconfig-shared.c - Low-level direct PCI config space access via - * MMCONFIG - common code between i386 and x86-64. + * Low-level direct PCI config space access via ECAM - common code between + * i386 and x86-64. * * This code does: * - known chipset handling @@ -11,6 +11,8 @@ * themselves. */ +#define pr_fmt(fmt) "PCI: " fmt + #include <linux/acpi.h> #include <linux/efi.h> #include <linux/pci.h> @@ -24,9 +26,7 @@ #include <asm/pci_x86.h> #include <asm/acpi.h> -#define PREFIX "PCI: " - -/* Indicate if the mmcfg resources have been placed into the resource table. */ +/* Indicate if the ECAM resources have been placed into the resource table */ static bool pci_mmcfg_running_state; static bool pci_mmcfg_arch_init_failed; static DEFINE_MUTEX(pci_mmcfg_lock); @@ -90,7 +90,7 @@ static struct pci_mmcfg_region *pci_mmconfig_alloc(int segment, int start, res->end = addr + PCI_MMCFG_BUS_OFFSET(end + 1) - 1; res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; snprintf(new->name, PCI_MMCFG_RESOURCE_NAME_LEN, - "PCI MMCONFIG %04x [bus %02x-%02x]", segment, start, end); + "PCI ECAM %04x [bus %02x-%02x]", segment, start, end); res->name = new->name; return new; @@ -102,16 +102,15 @@ struct pci_mmcfg_region *__init pci_mmconfig_add(int segment, int start, struct pci_mmcfg_region *new; new = pci_mmconfig_alloc(segment, start, end, addr); - if (new) { - mutex_lock(&pci_mmcfg_lock); - list_add_sorted(new); - mutex_unlock(&pci_mmcfg_lock); + if (!new) + return NULL; - pr_info(PREFIX - "MMCONFIG for domain %04x [bus %02x-%02x] at %pR " - "(base %#lx)\n", - segment, start, end, &new->res, (unsigned long)addr); - } + mutex_lock(&pci_mmcfg_lock); + list_add_sorted(new); + mutex_unlock(&pci_mmcfg_lock); + + pr_info("ECAM %pR (base %#lx) for domain %04x [bus %02x-%02x]\n", + &new->res, (unsigned long)addr, segment, start, end); return new; } @@ -205,7 +204,7 @@ static const char *__init pci_mmcfg_amd_fam10h(void) msr <<= 32; msr |= low; - /* mmconfig is not enable */ + /* ECAM is not enabled */ if (!(msr & FAM10H_MMIO_CONF_ENABLE)) return NULL; @@ -367,7 +366,7 @@ static int __init pci_mmcfg_check_hostbridge(void) name = pci_mmcfg_probes[i].probe(); if (name) - pr_info(PREFIX "%s with MMCONFIG support\n", name); + pr_info("%s with ECAM support\n", name); } /* some end_bus_number is crazy, fix it */ @@ -443,9 +442,11 @@ static bool is_acpi_reserved(u64 start, u64 end, enum e820_type not_used) return mcfg_res.flags; } -static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) +static bool is_efi_mmio(struct resource *res) { #ifdef CONFIG_EFI + u64 start = res->start; + u64 end = res->start + resource_size(res); efi_memory_desc_t *md; u64 size, mmio_start, mmio_end; @@ -455,11 +456,6 @@ static bool is_efi_mmio(u64 start, u64 end, enum e820_type not_used) mmio_start = md->phys_addr; mmio_end = mmio_start + size; - /* - * N.B. Caller supplies (start, start + size), - * so to match, mmio_end is the first address - * *past* the EFI_MEMORY_MAPPED_IO area. - */ if (mmio_start <= start && end <= mmio_end) return true; } @@ -490,11 +486,10 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, return false; if (dev) - dev_info(dev, "MMCONFIG at %pR reserved as %s\n", + dev_info(dev, "ECAM %pR reserved as %s\n", &cfg->res, method); else - pr_info(PREFIX "MMCONFIG at %pR reserved as %s\n", - &cfg->res, method); + pr_info("ECAM %pR reserved as %s\n", &cfg->res, method); if (old_size != size) { /* update end_bus */ @@ -503,27 +498,23 @@ static bool __ref is_mmconf_reserved(check_reserved_t is_reserved, cfg->res.end = cfg->res.start + PCI_MMCFG_BUS_OFFSET(num_buses) - 1; snprintf(cfg->name, PCI_MMCFG_RESOURCE_NAME_LEN, - "PCI MMCONFIG %04x [bus %02x-%02x]", + "PCI ECAM %04x [bus %02x-%02x]", cfg->segment, cfg->start_bus, cfg->end_bus); if (dev) - dev_info(dev, - "MMCONFIG " - "at %pR (base %#lx) (size reduced!)\n", - &cfg->res, (unsigned long) cfg->address); + dev_info(dev, "ECAM %pR (base %#lx) (size reduced!)\n", + &cfg->res, (unsigned long) cfg->address); else - pr_info(PREFIX - "MMCONFIG for %04x [bus%02x-%02x] " - "at %pR (base %#lx) (size reduced!)\n", - cfg->segment, cfg->start_bus, cfg->end_bus, - &cfg->res, (unsigned long) cfg->address); + pr_info("ECAM %pR (base %#lx) for %04x [bus%02x-%02x] (size reduced!)\n", + &cfg->res, (unsigned long) cfg->address, + cfg->segment, cfg->start_bus, cfg->end_bus); } return true; } -static bool __ref -pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int early) +static bool __ref pci_mmcfg_reserved(struct device *dev, + struct pci_mmcfg_region *cfg, int early) { struct resource *conflict; @@ -533,25 +524,22 @@ pci_mmcfg_check_reserved(struct device *dev, struct pci_mmcfg_region *cfg, int e return true; if (dev) - dev_info(dev, FW_INFO - "MMCONFIG at %pR not reserved in " - "ACPI motherboard resources\n", + dev_info(dev, FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n", &cfg->res); else - pr_info(FW_INFO PREFIX - "MMCONFIG at %pR not reserved in " - "ACPI motherboard resources\n", - &cfg->res); + pr_info(FW_INFO "ECAM %pR not reserved in ACPI motherboard resources\n", + &cfg->res); - if (is_mmconf_reserved(is_efi_mmio, cfg, dev, - "EfiMemoryMappedIO")) { + if (is_efi_mmio(&cfg->res)) { + pr_info("ECAM %pR is EfiMemoryMappedIO; assuming valid\n", + &cfg->res); conflict = insert_resource_conflict(&iomem_resource, &cfg->res); if (conflict) - pr_warn("MMCONFIG %pR conflicts with %s %pR\n", + pr_warn("ECAM %pR conflicts with %s %pR\n", &cfg->res, conflict->name, conflict); else - pr_info("MMCONFIG %pR reserved to work around lack of ACPI motherboard _CRS\n", + pr_info("ECAM %pR reserved to work around lack of ACPI motherboard _CRS\n", &cfg->res); return true; } @@ -580,30 +568,31 @@ static void __init pci_mmcfg_reject_broken(int early) struct pci_mmcfg_region *cfg; list_for_each_entry(cfg, &pci_mmcfg_list, list) { - if (pci_mmcfg_check_reserved(NULL, cfg, early) == 0) { - pr_info(PREFIX "not using MMCONFIG\n"); + if (!pci_mmcfg_reserved(NULL, cfg, early)) { + pr_info("not using ECAM (%pR not reserved)\n", + &cfg->res); free_all_mmcfg(); return; } } } -static int __init acpi_mcfg_check_entry(struct acpi_table_mcfg *mcfg, - struct acpi_mcfg_allocation *cfg) +static bool __init acpi_mcfg_valid_entry(struct acpi_table_mcfg *mcfg, + struct acpi_mcfg_allocation *cfg) { if (cfg->address < 0xFFFFFFFF) - return 0; + return true; if (!strncmp(mcfg->header.oem_id, "SGI", 3)) - return 0; + return true; if ((mcfg->header.revision >= 1) && (dmi_get_bios_year() >= 2010)) - return 0; + return true; - pr_err(PREFIX "MCFG region for %04x [bus %02x-%02x] at %#llx " - "is above 4GB, ignored\n", cfg->pci_segment, - cfg->start_bus_number, cfg->end_bus_number, cfg->address); - return -EINVAL; + pr_err("ECAM at %#llx for %04x [bus %02x-%02x] is above 4GB, ignored\n", + cfg->address, cfg->pci_segment, cfg->start_bus_number, + cfg->end_bus_number); + return false; } static int __init pci_parse_mcfg(struct acpi_table_header *header) @@ -627,21 +616,21 @@ static int __init pci_parse_mcfg(struct acpi_table_header *header) i -= sizeof(struct acpi_mcfg_allocation); } if (entries == 0) { - pr_err(PREFIX "MMCONFIG has no entries\n"); + pr_err("MCFG has no entries\n"); return -ENODEV; } cfg_table = (struct acpi_mcfg_allocation *) &mcfg[1]; for (i = 0; i < entries; i++) { cfg = &cfg_table[i]; - if (acpi_mcfg_check_entry(mcfg, cfg)) { + if (!acpi_mcfg_valid_entry(mcfg, cfg)) { free_all_mmcfg(); return -ENODEV; } if (pci_mmconfig_add(cfg->pci_segment, cfg->start_bus_number, cfg->end_bus_number, cfg->address) == NULL) { - pr_warn(PREFIX "no memory for MCFG entries\n"); + pr_warn("no memory for MCFG entries\n"); free_all_mmcfg(); return -ENOMEM; } @@ -678,6 +667,8 @@ static int pci_mmcfg_for_each_region(int (*func)(__u64 start, __u64 size, static void __init __pci_mmcfg_init(int early) { + pr_debug("%s(%s)\n", __func__, early ? "early" : "late"); + pci_mmcfg_reject_broken(early); if (list_empty(&pci_mmcfg_list)) return; @@ -704,6 +695,8 @@ static int __initdata known_bridge; void __init pci_mmcfg_early_init(void) { + pr_debug("%s() pci_probe %#x\n", __func__, pci_probe); + if (pci_probe & PCI_PROBE_MMCONF) { if (pci_mmcfg_check_hostbridge()) known_bridge = 1; @@ -717,14 +710,16 @@ void __init pci_mmcfg_early_init(void) void __init pci_mmcfg_late_init(void) { - /* MMCONFIG disabled */ + pr_debug("%s() pci_probe %#x\n", __func__, pci_probe); + + /* ECAM disabled */ if ((pci_probe & PCI_PROBE_MMCONF) == 0) return; if (known_bridge) return; - /* MMCONFIG hasn't been enabled yet, try again */ + /* ECAM hasn't been enabled yet, try again */ if (pci_probe & PCI_PROBE_MASK & ~PCI_PROBE_MMCONF) { acpi_table_parse(ACPI_SIG_MCFG, pci_parse_mcfg); __pci_mmcfg_init(0); @@ -737,7 +732,9 @@ static int __init pci_mmcfg_late_insert_resources(void) pci_mmcfg_running_state = true; - /* If we are not using MMCONFIG, don't insert the resources. */ + pr_debug("%s() pci_probe %#x\n", __func__, pci_probe); + + /* If we are not using ECAM, don't insert the resources. */ if ((pci_probe & PCI_PROBE_MMCONF) == 0) return 1; @@ -746,21 +743,24 @@ static int __init pci_mmcfg_late_insert_resources(void) * marked so it won't cause request errors when __request_region is * called. */ - list_for_each_entry(cfg, &pci_mmcfg_list, list) - if (!cfg->res.parent) + list_for_each_entry(cfg, &pci_mmcfg_list, list) { + if (!cfg->res.parent) { + pr_debug("%s() insert %pR\n", __func__, &cfg->res); insert_resource(&iomem_resource, &cfg->res); + } + } return 0; } /* - * Perform MMCONFIG resource insertion after PCI initialization to allow for + * Perform ECAM resource insertion after PCI initialization to allow for * misprogrammed MCFG tables that state larger sizes but actually conflict * with other system resources. */ late_initcall(pci_mmcfg_late_insert_resources); -/* Add MMCFG information for host bridges */ +/* Add ECAM information for host bridges */ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, phys_addr_t addr) { @@ -768,6 +768,8 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, struct resource *tmp = NULL; struct pci_mmcfg_region *cfg; + dev_dbg(dev, "%s(%04x [bus %02x-%02x])\n", __func__, seg, start, end); + if (!(pci_probe & PCI_PROBE_MMCONF) || pci_mmcfg_arch_init_failed) return -ENODEV; @@ -778,15 +780,17 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, cfg = pci_mmconfig_lookup(seg, start); if (cfg) { if (cfg->end_bus < end) - dev_info(dev, FW_INFO - "MMCONFIG for " - "domain %04x [bus %02x-%02x] " - "only partially covers this bridge\n", - cfg->segment, cfg->start_bus, cfg->end_bus); + dev_info(dev, FW_INFO "ECAM %pR for domain %04x [bus %02x-%02x] only partially covers this bridge\n", + &cfg->res, cfg->segment, cfg->start_bus, + cfg->end_bus); mutex_unlock(&pci_mmcfg_lock); return -EEXIST; } + /* + * Don't move earlier; we must return -EEXIST, not -EINVAL, if + * pci_mmconfig_lookup() finds something + */ if (!addr) { mutex_unlock(&pci_mmcfg_lock); return -EINVAL; @@ -795,10 +799,10 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, rc = -EBUSY; cfg = pci_mmconfig_alloc(seg, start, end, addr); if (cfg == NULL) { - dev_warn(dev, "fail to add MMCONFIG (out of memory)\n"); + dev_warn(dev, "fail to add ECAM (out of memory)\n"); rc = -ENOMEM; - } else if (!pci_mmcfg_check_reserved(dev, cfg, 0)) { - dev_warn(dev, FW_BUG "MMCONFIG %pR isn't reserved\n", + } else if (!pci_mmcfg_reserved(dev, cfg, 0)) { + dev_warn(dev, FW_BUG "ECAM %pR isn't reserved\n", &cfg->res); } else { /* Insert resource if it's not in boot stage */ @@ -807,16 +811,13 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, &cfg->res); if (tmp) { - dev_warn(dev, - "MMCONFIG %pR conflicts with " - "%s %pR\n", + dev_warn(dev, "ECAM %pR conflicts with %s %pR\n", &cfg->res, tmp->name, tmp); } else if (pci_mmcfg_arch_map(cfg)) { - dev_warn(dev, "fail to map MMCONFIG %pR.\n", - &cfg->res); + dev_warn(dev, "fail to map ECAM %pR\n", &cfg->res); } else { list_add_sorted(cfg); - dev_info(dev, "MMCONFIG at %pR (base %#lx)\n", + dev_info(dev, "ECAM %pR (base %#lx)\n", &cfg->res, (unsigned long)addr); cfg = NULL; rc = 0; @@ -834,7 +835,7 @@ int pci_mmconfig_insert(struct device *dev, u16 seg, u8 start, u8 end, return rc; } -/* Delete MMCFG information for host bridges */ +/* Delete ECAM information for host bridges */ int pci_mmconfig_delete(u16 seg, u8 start, u8 end) { struct pci_mmcfg_region *cfg; diff --git a/arch/x86/pci/mmconfig_32.c b/arch/x86/pci/mmconfig_32.c index bfa7898753..f9ef97c593 100644 --- a/arch/x86/pci/mmconfig_32.c +++ b/arch/x86/pci/mmconfig_32.c @@ -131,7 +131,7 @@ const struct pci_raw_ops pci_mmcfg = { int __init pci_mmcfg_arch_init(void) { - printk(KERN_INFO "PCI: Using MMCONFIG for extended config space\n"); + printk(KERN_INFO "PCI: Using ECAM for extended config space\n"); raw_pci_ext_ops = &pci_mmcfg; return 1; } diff --git a/arch/x86/pci/mmconfig_64.c b/arch/x86/pci/mmconfig_64.c index 0c7b6e66c6..cb5aa79a75 100644 --- a/arch/x86/pci/mmconfig_64.c +++ b/arch/x86/pci/mmconfig_64.c @@ -6,6 +6,8 @@ * space mapped. This allows lockless config space operation. */ +#define pr_fmt(fmt) "PCI: " fmt + #include <linux/pci.h> #include <linux/init.h> #include <linux/acpi.h> @@ -14,8 +16,6 @@ #include <asm/e820/api.h> #include <asm/pci_x86.h> -#define PREFIX "PCI: " - static char __iomem *pci_dev_base(unsigned int seg, unsigned int bus, unsigned int devfn) { struct pci_mmcfg_region *cfg = pci_mmconfig_lookup(seg, bus); @@ -111,6 +111,25 @@ static void __iomem *mcfg_ioremap(struct pci_mmcfg_region *cfg) return addr; } +int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) +{ + cfg->virt = mcfg_ioremap(cfg); + if (!cfg->virt) { + pr_err("can't map ECAM at %pR\n", &cfg->res); + return -ENOMEM; + } + + return 0; +} + +void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg) +{ + if (cfg && cfg->virt) { + iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus)); + cfg->virt = NULL; + } +} + int __init pci_mmcfg_arch_init(void) { struct pci_mmcfg_region *cfg; @@ -133,22 +152,3 @@ void __init pci_mmcfg_arch_free(void) list_for_each_entry(cfg, &pci_mmcfg_list, list) pci_mmcfg_arch_unmap(cfg); } - -int pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg) -{ - cfg->virt = mcfg_ioremap(cfg); - if (!cfg->virt) { - pr_err(PREFIX "can't map MMCONFIG at %pR\n", &cfg->res); - return -ENOMEM; - } - - return 0; -} - -void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg) -{ - if (cfg && cfg->virt) { - iounmap(cfg->virt + PCI_MMCFG_BUS_OFFSET(cfg->start_bus)); - cfg->virt = NULL; - } -} diff --git a/arch/x86/pci/pcbios.c b/arch/x86/pci/pcbios.c index 4f15280732..244c643bb0 100644 --- a/arch/x86/pci/pcbios.c +++ b/arch/x86/pci/pcbios.c @@ -3,6 +3,8 @@ * BIOS32 and PCI BIOS handling. */ +#include <linux/bits.h> +#include <linux/bitfield.h> #include <linux/pci.h> #include <linux/init.h> #include <linux/slab.h> @@ -29,8 +31,19 @@ #define PCIBIOS_HW_TYPE1_SPEC 0x10 #define PCIBIOS_HW_TYPE2_SPEC 0x20 +/* + * Returned in EAX: + * - AH: return code + */ +#define PCIBIOS_RETURN_CODE GENMASK(15, 8) + int pcibios_enabled; +static u8 pcibios_get_return_code(u32 eax) +{ + return FIELD_GET(PCIBIOS_RETURN_CODE, eax); +} + /* According to the BIOS specification at: * http://members.datafast.net.au/dft0802/specs/bios21.pdf, we could * restrict the x zone to some pages and make it ro. But this may be @@ -154,7 +167,7 @@ static int __init check_pcibios(void) : "memory"); local_irq_restore(flags); - status = (eax >> 8) & 0xff; + status = pcibios_get_return_code(eax); hw_mech = eax & 0xff; major_ver = (ebx >> 8) & 0xff; minor_ver = ebx & 0xff; @@ -227,7 +240,7 @@ static int pci_bios_read(unsigned int seg, unsigned int bus, raw_spin_unlock_irqrestore(&pci_config_lock, flags); - return (int)((result & 0xff00) >> 8); + return pcibios_get_return_code(result); } static int pci_bios_write(unsigned int seg, unsigned int bus, @@ -269,7 +282,7 @@ static int pci_bios_write(unsigned int seg, unsigned int bus, raw_spin_unlock_irqrestore(&pci_config_lock, flags); - return (int)((result & 0xff00) >> 8); + return pcibios_get_return_code(result); } @@ -385,9 +398,10 @@ struct irq_routing_table * pcibios_get_irq_routing_table(void) "m" (opt) : "memory"); DBG("OK ret=%d, size=%d, map=%x\n", ret, opt.size, map); - if (ret & 0xff00) - printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", (ret >> 8) & 0xff); - else if (opt.size) { + ret = pcibios_get_return_code(ret); + if (ret) { + printk(KERN_ERR "PCI: Error %02x when fetching IRQ routing table.\n", ret); + } else if (opt.size) { rt = kmalloc(sizeof(struct irq_routing_table) + opt.size, GFP_KERNEL); if (rt) { memset(rt, 0, sizeof(struct irq_routing_table)); @@ -415,7 +429,7 @@ int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq) "b" ((dev->bus->number << 8) | dev->devfn), "c" ((irq << 8) | (pin + 10)), "S" (&pci_indirect)); - return !(ret & 0xff00); + return pcibios_get_return_code(ret) == PCIBIOS_SUCCESSFUL; } EXPORT_SYMBOL(pcibios_set_irq_routing); diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 7368afc039..8c8ddc4dcc 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 761f3689f6..84ba715f44 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/enlighten.c b/arch/x86/platform/pvh/enlighten.c index 00a92cb2c8..a12117f3d4 100644 --- a/arch/x86/platform/pvh/enlighten.c +++ b/arch/x86/platform/pvh/enlighten.c @@ -74,6 +74,9 @@ static void __init init_pvh_bootparams(bool xen_guest) } else xen_raw_printk("Warning: Can fit ISA range into e820\n"); + if (xen_guest) + xen_reserve_extra_memory(&pvh_bootparams); + pvh_bootparams.hdr.cmd_line_ptr = pvh_start_info.cmdline_paddr; diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S index c4365a05ab..f7235ef87b 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 4221259a58..a379501b7a 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 e03207de28..5c50e550ab 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 ff5afc8a5a..3712afc353 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/power/hibernate.c b/arch/x86/power/hibernate.c index 6f955eb1e1..d8af46e677 100644 --- a/arch/x86/power/hibernate.c +++ b/arch/x86/power/hibernate.c @@ -170,7 +170,7 @@ int relocate_restore_code(void) goto out; } pud = pud_offset(p4d, relocated_restore_code); - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX)); goto out; } diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c index 788e555954..f9bc444a30 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 f10515b10e..e714b4624e 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 90e820ac97..7278e2545c 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 a4cf678cf5..0000000000 --- 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 = $(i); - break; - } - if (verstr == "") { - printf("Warning: Failed to find objdump version number.\n"); - exit 0; - } - split(verstr, ver, "."); - if (ver[1] > od_ver || - (ver[1] == od_ver && ver[2] >= od_sver)) { - exit 1; - } else { - printf("Warning: objdump version %s is older than %d.%d\n", - verstr, od_ver, od_sver); - print("Warning: Skipping posttest."); - # Logic is inverted, because we just skip test without error. - exit 0; - } -} diff --git a/arch/x86/tools/objdump_reformat.awk b/arch/x86/tools/objdump_reformat.awk index f418c91b71..20b08a6c4d 100644 --- a/arch/x86/tools/objdump_reformat.awk +++ b/arch/x86/tools/objdump_reformat.awk @@ -11,8 +11,8 @@ BEGIN { prev_addr = "" prev_hex = "" prev_mnemonic = "" - bad_expr = "(\\(bad\\)|^rex|^.byte|^rep(z|nz)$|^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 e701328364..b029fb81eb 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 6523eb7c3b..6052200fe9 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 1ef9c21877..f901595089 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 ae169125d0..5249bbc30d 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 8431e87ac3..0000000000 --- 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 0bc4b73a9c..7f1abde2c8 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 289d0159b0..aa68d83d3f 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 db8478a83a..0c4989842f 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 44782bbad4..1d1a824fa6 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 38fa894b65..ea8b5a2d67 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 2de1c8f881..b24168ef0a 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 27b29ae6c4..6a00a28c9c 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 ef1eb4f4f6..0bf6de40ab 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 ebd3855d9b..c51a613f6f 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/virt/vmx/tdx/Makefile b/arch/x86/virt/vmx/tdx/Makefile index 46ef8f73ae..90da47eb85 100644 --- a/arch/x86/virt/vmx/tdx/Makefile +++ b/arch/x86/virt/vmx/tdx/Makefile @@ -1,2 +1,2 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-y += seamcall.o +obj-y += seamcall.o tdx.o diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c new file mode 100644 index 0000000000..4d6826a76f --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx.c @@ -0,0 +1,1492 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright(c) 2023 Intel Corporation. + * + * Intel Trusted Domain Extensions (TDX) support + */ + +#define pr_fmt(fmt) "virt/tdx: " fmt + +#include <linux/types.h> +#include <linux/cache.h> +#include <linux/init.h> +#include <linux/errno.h> +#include <linux/printk.h> +#include <linux/cpu.h> +#include <linux/spinlock.h> +#include <linux/percpu-defs.h> +#include <linux/mutex.h> +#include <linux/list.h> +#include <linux/memblock.h> +#include <linux/memory.h> +#include <linux/minmax.h> +#include <linux/sizes.h> +#include <linux/pfn.h> +#include <linux/align.h> +#include <linux/sort.h> +#include <linux/log2.h> +#include <linux/acpi.h> +#include <linux/suspend.h> +#include <linux/acpi.h> +#include <asm/page.h> +#include <asm/special_insns.h> +#include <asm/msr-index.h> +#include <asm/msr.h> +#include <asm/cpufeature.h> +#include <asm/tdx.h> +#include <asm/intel-family.h> +#include <asm/processor.h> +#include <asm/mce.h> +#include "tdx.h" + +static u32 tdx_global_keyid __ro_after_init; +static u32 tdx_guest_keyid_start __ro_after_init; +static u32 tdx_nr_guest_keyids __ro_after_init; + +static DEFINE_PER_CPU(bool, tdx_lp_initialized); + +static struct tdmr_info_list tdx_tdmr_list; + +static enum tdx_module_status_t tdx_module_status; +static DEFINE_MUTEX(tdx_module_lock); + +/* All TDX-usable memory regions. Protected by mem_hotplug_lock. */ +static LIST_HEAD(tdx_memlist); + +typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args); + +static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args) +{ + pr_err("SEAMCALL (0x%016llx) failed: 0x%016llx\n", fn, err); +} + +static inline void seamcall_err_ret(u64 fn, u64 err, + struct tdx_module_args *args) +{ + seamcall_err(fn, err, args); + pr_err("RCX 0x%016llx RDX 0x%016llx R08 0x%016llx\n", + args->rcx, args->rdx, args->r8); + pr_err("R09 0x%016llx R10 0x%016llx R11 0x%016llx\n", + args->r9, args->r10, args->r11); +} + +static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func, + u64 fn, struct tdx_module_args *args) +{ + u64 sret = sc_retry(func, fn, args); + + if (sret == TDX_SUCCESS) + return 0; + + if (sret == TDX_SEAMCALL_VMFAILINVALID) + return -ENODEV; + + if (sret == TDX_SEAMCALL_GP) + return -EOPNOTSUPP; + + if (sret == TDX_SEAMCALL_UD) + return -EACCES; + + err_func(fn, sret, args); + return -EIO; +} + +#define seamcall_prerr(__fn, __args) \ + sc_retry_prerr(__seamcall, seamcall_err, (__fn), (__args)) + +#define seamcall_prerr_ret(__fn, __args) \ + sc_retry_prerr(__seamcall_ret, seamcall_err_ret, (__fn), (__args)) + +/* + * Do the module global initialization once and return its result. + * It can be done on any cpu. It's always called with interrupts + * disabled. + */ +static int try_init_module_global(void) +{ + struct tdx_module_args args = {}; + static DEFINE_RAW_SPINLOCK(sysinit_lock); + static bool sysinit_done; + static int sysinit_ret; + + lockdep_assert_irqs_disabled(); + + raw_spin_lock(&sysinit_lock); + + if (sysinit_done) + goto out; + + /* RCX is module attributes and all bits are reserved */ + args.rcx = 0; + sysinit_ret = seamcall_prerr(TDH_SYS_INIT, &args); + + /* + * The first SEAMCALL also detects the TDX module, thus + * it can fail due to the TDX module is not loaded. + * Dump message to let the user know. + */ + if (sysinit_ret == -ENODEV) + pr_err("module not loaded\n"); + + sysinit_done = true; +out: + raw_spin_unlock(&sysinit_lock); + return sysinit_ret; +} + +/** + * tdx_cpu_enable - Enable TDX on local cpu + * + * Do one-time TDX module per-cpu initialization SEAMCALL (and TDX module + * global initialization SEAMCALL if not done) on local cpu to make this + * cpu be ready to run any other SEAMCALLs. + * + * Always call this function via IPI function calls. + * + * Return 0 on success, otherwise errors. + */ +int tdx_cpu_enable(void) +{ + struct tdx_module_args args = {}; + int ret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return -ENODEV; + + lockdep_assert_irqs_disabled(); + + if (__this_cpu_read(tdx_lp_initialized)) + return 0; + + /* + * The TDX module global initialization is the very first step + * to enable TDX. Need to do it first (if hasn't been done) + * before the per-cpu initialization. + */ + ret = try_init_module_global(); + if (ret) + return ret; + + ret = seamcall_prerr(TDH_SYS_LP_INIT, &args); + if (ret) + return ret; + + __this_cpu_write(tdx_lp_initialized, true); + + return 0; +} +EXPORT_SYMBOL_GPL(tdx_cpu_enable); + +/* + * Add a memory region as a TDX memory block. The caller must make sure + * all memory regions are added in address ascending order and don't + * overlap. + */ +static int add_tdx_memblock(struct list_head *tmb_list, unsigned long start_pfn, + unsigned long end_pfn, int nid) +{ + struct tdx_memblock *tmb; + + tmb = kmalloc(sizeof(*tmb), GFP_KERNEL); + if (!tmb) + return -ENOMEM; + + INIT_LIST_HEAD(&tmb->list); + tmb->start_pfn = start_pfn; + tmb->end_pfn = end_pfn; + tmb->nid = nid; + + /* @tmb_list is protected by mem_hotplug_lock */ + list_add_tail(&tmb->list, tmb_list); + return 0; +} + +static void free_tdx_memlist(struct list_head *tmb_list) +{ + /* @tmb_list is protected by mem_hotplug_lock */ + while (!list_empty(tmb_list)) { + struct tdx_memblock *tmb = list_first_entry(tmb_list, + struct tdx_memblock, list); + + list_del(&tmb->list); + kfree(tmb); + } +} + +/* + * Ensure that all memblock memory regions are convertible to TDX + * memory. Once this has been established, stash the memblock + * ranges off in a secondary structure because memblock is modified + * in memory hotplug while TDX memory regions are fixed. + */ +static int build_tdx_memlist(struct list_head *tmb_list) +{ + unsigned long start_pfn, end_pfn; + int i, nid, ret; + + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + /* + * The first 1MB is not reported as TDX convertible memory. + * Although the first 1MB is always reserved and won't end up + * to the page allocator, it is still in memblock's memory + * regions. Skip them manually to exclude them as TDX memory. + */ + start_pfn = max(start_pfn, PHYS_PFN(SZ_1M)); + if (start_pfn >= end_pfn) + continue; + + /* + * Add the memory regions as TDX memory. The regions in + * memblock has already guaranteed they are in address + * ascending order and don't overlap. + */ + ret = add_tdx_memblock(tmb_list, start_pfn, end_pfn, nid); + if (ret) + goto err; + } + + return 0; +err: + free_tdx_memlist(tmb_list); + return ret; +} + +static int read_sys_metadata_field(u64 field_id, u64 *data) +{ + struct tdx_module_args args = {}; + int ret; + + /* + * TDH.SYS.RD -- reads one global metadata field + * - RDX (in): the field to read + * - R8 (out): the field data + */ + args.rdx = field_id; + ret = seamcall_prerr_ret(TDH_SYS_RD, &args); + if (ret) + return ret; + + *data = args.r8; + + return 0; +} + +static int read_sys_metadata_field16(u64 field_id, + int offset, + struct tdx_tdmr_sysinfo *ts) +{ + u16 *ts_member = ((void *)ts) + offset; + u64 tmp; + int ret; + + if (WARN_ON_ONCE(MD_FIELD_ID_ELE_SIZE_CODE(field_id) != + MD_FIELD_ID_ELE_SIZE_16BIT)) + return -EINVAL; + + ret = read_sys_metadata_field(field_id, &tmp); + if (ret) + return ret; + + *ts_member = tmp; + + return 0; +} + +struct field_mapping { + u64 field_id; + int offset; +}; + +#define TD_SYSINFO_MAP(_field_id, _offset) \ + { .field_id = MD_FIELD_ID_##_field_id, \ + .offset = offsetof(struct tdx_tdmr_sysinfo, _offset) } + +/* Map TD_SYSINFO fields into 'struct tdx_tdmr_sysinfo': */ +static const struct field_mapping fields[] = { + TD_SYSINFO_MAP(MAX_TDMRS, max_tdmrs), + TD_SYSINFO_MAP(MAX_RESERVED_PER_TDMR, max_reserved_per_tdmr), + TD_SYSINFO_MAP(PAMT_4K_ENTRY_SIZE, pamt_entry_size[TDX_PS_4K]), + TD_SYSINFO_MAP(PAMT_2M_ENTRY_SIZE, pamt_entry_size[TDX_PS_2M]), + TD_SYSINFO_MAP(PAMT_1G_ENTRY_SIZE, pamt_entry_size[TDX_PS_1G]), +}; + +static int get_tdx_tdmr_sysinfo(struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + int ret; + int i; + + /* Populate 'tdmr_sysinfo' fields using the mapping structure above: */ + for (i = 0; i < ARRAY_SIZE(fields); i++) { + ret = read_sys_metadata_field16(fields[i].field_id, + fields[i].offset, + tdmr_sysinfo); + if (ret) + return ret; + } + + return 0; +} + +/* Calculate the actual TDMR size */ +static int tdmr_size_single(u16 max_reserved_per_tdmr) +{ + int tdmr_sz; + + /* + * The actual size of TDMR depends on the maximum + * number of reserved areas. + */ + tdmr_sz = sizeof(struct tdmr_info); + tdmr_sz += sizeof(struct tdmr_reserved_area) * max_reserved_per_tdmr; + + return ALIGN(tdmr_sz, TDMR_INFO_ALIGNMENT); +} + +static int alloc_tdmr_list(struct tdmr_info_list *tdmr_list, + struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + size_t tdmr_sz, tdmr_array_sz; + void *tdmr_array; + + tdmr_sz = tdmr_size_single(tdmr_sysinfo->max_reserved_per_tdmr); + tdmr_array_sz = tdmr_sz * tdmr_sysinfo->max_tdmrs; + + /* + * To keep things simple, allocate all TDMRs together. + * The buffer needs to be physically contiguous to make + * sure each TDMR is physically contiguous. + */ + tdmr_array = alloc_pages_exact(tdmr_array_sz, + GFP_KERNEL | __GFP_ZERO); + if (!tdmr_array) + return -ENOMEM; + + tdmr_list->tdmrs = tdmr_array; + + /* + * Keep the size of TDMR to find the target TDMR + * at a given index in the TDMR list. + */ + tdmr_list->tdmr_sz = tdmr_sz; + tdmr_list->max_tdmrs = tdmr_sysinfo->max_tdmrs; + tdmr_list->nr_consumed_tdmrs = 0; + + return 0; +} + +static void free_tdmr_list(struct tdmr_info_list *tdmr_list) +{ + free_pages_exact(tdmr_list->tdmrs, + tdmr_list->max_tdmrs * tdmr_list->tdmr_sz); +} + +/* Get the TDMR from the list at the given index. */ +static struct tdmr_info *tdmr_entry(struct tdmr_info_list *tdmr_list, + int idx) +{ + int tdmr_info_offset = tdmr_list->tdmr_sz * idx; + + return (void *)tdmr_list->tdmrs + tdmr_info_offset; +} + +#define TDMR_ALIGNMENT SZ_1G +#define TDMR_ALIGN_DOWN(_addr) ALIGN_DOWN((_addr), TDMR_ALIGNMENT) +#define TDMR_ALIGN_UP(_addr) ALIGN((_addr), TDMR_ALIGNMENT) + +static inline u64 tdmr_end(struct tdmr_info *tdmr) +{ + return tdmr->base + tdmr->size; +} + +/* + * Take the memory referenced in @tmb_list and populate the + * preallocated @tdmr_list, following all the special alignment + * and size rules for TDMR. + */ +static int fill_out_tdmrs(struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list) +{ + struct tdx_memblock *tmb; + int tdmr_idx = 0; + + /* + * Loop over TDX memory regions and fill out TDMRs to cover them. + * To keep it simple, always try to use one TDMR to cover one + * memory region. + * + * In practice TDX supports at least 64 TDMRs. A 2-socket system + * typically only consumes less than 10 of those. This code is + * dumb and simple and may use more TMDRs than is strictly + * required. + */ + list_for_each_entry(tmb, tmb_list, list) { + struct tdmr_info *tdmr = tdmr_entry(tdmr_list, tdmr_idx); + u64 start, end; + + start = TDMR_ALIGN_DOWN(PFN_PHYS(tmb->start_pfn)); + end = TDMR_ALIGN_UP(PFN_PHYS(tmb->end_pfn)); + + /* + * A valid size indicates the current TDMR has already + * been filled out to cover the previous memory region(s). + */ + if (tdmr->size) { + /* + * Loop to the next if the current memory region + * has already been fully covered. + */ + if (end <= tdmr_end(tdmr)) + continue; + + /* Otherwise, skip the already covered part. */ + if (start < tdmr_end(tdmr)) + start = tdmr_end(tdmr); + + /* + * Create a new TDMR to cover the current memory + * region, or the remaining part of it. + */ + tdmr_idx++; + if (tdmr_idx >= tdmr_list->max_tdmrs) { + pr_warn("initialization failed: TDMRs exhausted.\n"); + return -ENOSPC; + } + + tdmr = tdmr_entry(tdmr_list, tdmr_idx); + } + + tdmr->base = start; + tdmr->size = end - start; + } + + /* @tdmr_idx is always the index of the last valid TDMR. */ + tdmr_list->nr_consumed_tdmrs = tdmr_idx + 1; + + /* + * Warn early that kernel is about to run out of TDMRs. + * + * This is an indication that TDMR allocation has to be + * reworked to be smarter to not run into an issue. + */ + if (tdmr_list->max_tdmrs - tdmr_list->nr_consumed_tdmrs < TDMR_NR_WARN) + pr_warn("consumed TDMRs reaching limit: %d used out of %d\n", + tdmr_list->nr_consumed_tdmrs, + tdmr_list->max_tdmrs); + + return 0; +} + +/* + * Calculate PAMT size given a TDMR and a page size. The returned + * PAMT size is always aligned up to 4K page boundary. + */ +static unsigned long tdmr_get_pamt_sz(struct tdmr_info *tdmr, int pgsz, + u16 pamt_entry_size) +{ + unsigned long pamt_sz, nr_pamt_entries; + + switch (pgsz) { + case TDX_PS_4K: + nr_pamt_entries = tdmr->size >> PAGE_SHIFT; + break; + case TDX_PS_2M: + nr_pamt_entries = tdmr->size >> PMD_SHIFT; + break; + case TDX_PS_1G: + nr_pamt_entries = tdmr->size >> PUD_SHIFT; + break; + default: + WARN_ON_ONCE(1); + return 0; + } + + pamt_sz = nr_pamt_entries * pamt_entry_size; + /* TDX requires PAMT size must be 4K aligned */ + pamt_sz = ALIGN(pamt_sz, PAGE_SIZE); + + return pamt_sz; +} + +/* + * Locate a NUMA node which should hold the allocation of the @tdmr + * PAMT. This node will have some memory covered by the TDMR. The + * relative amount of memory covered is not considered. + */ +static int tdmr_get_nid(struct tdmr_info *tdmr, struct list_head *tmb_list) +{ + struct tdx_memblock *tmb; + + /* + * A TDMR must cover at least part of one TMB. That TMB will end + * after the TDMR begins. But, that TMB may have started before + * the TDMR. Find the next 'tmb' that _ends_ after this TDMR + * begins. Ignore 'tmb' start addresses. They are irrelevant. + */ + list_for_each_entry(tmb, tmb_list, list) { + if (tmb->end_pfn > PHYS_PFN(tdmr->base)) + return tmb->nid; + } + + /* + * Fall back to allocating the TDMR's metadata from node 0 when + * no TDX memory block can be found. This should never happen + * since TDMRs originate from TDX memory blocks. + */ + pr_warn("TDMR [0x%llx, 0x%llx): unable to find local NUMA node for PAMT allocation, fallback to use node 0.\n", + tdmr->base, tdmr_end(tdmr)); + return 0; +} + +/* + * Allocate PAMTs from the local NUMA node of some memory in @tmb_list + * within @tdmr, and set up PAMTs for @tdmr. + */ +static int tdmr_set_up_pamt(struct tdmr_info *tdmr, + struct list_head *tmb_list, + u16 pamt_entry_size[]) +{ + unsigned long pamt_base[TDX_PS_NR]; + unsigned long pamt_size[TDX_PS_NR]; + unsigned long tdmr_pamt_base; + unsigned long tdmr_pamt_size; + struct page *pamt; + int pgsz, nid; + + nid = tdmr_get_nid(tdmr, tmb_list); + + /* + * Calculate the PAMT size for each TDX supported page size + * and the total PAMT size. + */ + tdmr_pamt_size = 0; + for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) { + pamt_size[pgsz] = tdmr_get_pamt_sz(tdmr, pgsz, + pamt_entry_size[pgsz]); + tdmr_pamt_size += pamt_size[pgsz]; + } + + /* + * Allocate one chunk of physically contiguous memory for all + * PAMTs. This helps minimize the PAMT's use of reserved areas + * in overlapped TDMRs. + */ + pamt = alloc_contig_pages(tdmr_pamt_size >> PAGE_SHIFT, GFP_KERNEL, + nid, &node_online_map); + if (!pamt) + return -ENOMEM; + + /* + * Break the contiguous allocation back up into the + * individual PAMTs for each page size. + */ + tdmr_pamt_base = page_to_pfn(pamt) << PAGE_SHIFT; + for (pgsz = TDX_PS_4K; pgsz < TDX_PS_NR; pgsz++) { + pamt_base[pgsz] = tdmr_pamt_base; + tdmr_pamt_base += pamt_size[pgsz]; + } + + tdmr->pamt_4k_base = pamt_base[TDX_PS_4K]; + tdmr->pamt_4k_size = pamt_size[TDX_PS_4K]; + tdmr->pamt_2m_base = pamt_base[TDX_PS_2M]; + tdmr->pamt_2m_size = pamt_size[TDX_PS_2M]; + tdmr->pamt_1g_base = pamt_base[TDX_PS_1G]; + tdmr->pamt_1g_size = pamt_size[TDX_PS_1G]; + + return 0; +} + +static void tdmr_get_pamt(struct tdmr_info *tdmr, unsigned long *pamt_base, + unsigned long *pamt_size) +{ + unsigned long pamt_bs, pamt_sz; + + /* + * The PAMT was allocated in one contiguous unit. The 4K PAMT + * should always point to the beginning of that allocation. + */ + pamt_bs = tdmr->pamt_4k_base; + pamt_sz = tdmr->pamt_4k_size + tdmr->pamt_2m_size + tdmr->pamt_1g_size; + + WARN_ON_ONCE((pamt_bs & ~PAGE_MASK) || (pamt_sz & ~PAGE_MASK)); + + *pamt_base = pamt_bs; + *pamt_size = pamt_sz; +} + +static void tdmr_do_pamt_func(struct tdmr_info *tdmr, + void (*pamt_func)(unsigned long base, unsigned long size)) +{ + unsigned long pamt_base, pamt_size; + + tdmr_get_pamt(tdmr, &pamt_base, &pamt_size); + + /* Do nothing if PAMT hasn't been allocated for this TDMR */ + if (!pamt_size) + return; + + if (WARN_ON_ONCE(!pamt_base)) + return; + + pamt_func(pamt_base, pamt_size); +} + +static void free_pamt(unsigned long pamt_base, unsigned long pamt_size) +{ + free_contig_range(pamt_base >> PAGE_SHIFT, pamt_size >> PAGE_SHIFT); +} + +static void tdmr_free_pamt(struct tdmr_info *tdmr) +{ + tdmr_do_pamt_func(tdmr, free_pamt); +} + +static void tdmrs_free_pamt_all(struct tdmr_info_list *tdmr_list) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_free_pamt(tdmr_entry(tdmr_list, i)); +} + +/* Allocate and set up PAMTs for all TDMRs */ +static int tdmrs_set_up_pamt_all(struct tdmr_info_list *tdmr_list, + struct list_head *tmb_list, + u16 pamt_entry_size[]) +{ + int i, ret = 0; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + ret = tdmr_set_up_pamt(tdmr_entry(tdmr_list, i), tmb_list, + pamt_entry_size); + if (ret) + goto err; + } + + return 0; +err: + tdmrs_free_pamt_all(tdmr_list); + return ret; +} + +/* + * Convert TDX private pages back to normal by using MOVDIR64B to + * clear these pages. Note this function doesn't flush cache of + * these TDX private pages. The caller should make sure of that. + */ +static void reset_tdx_pages(unsigned long base, unsigned long size) +{ + const void *zero_page = (const void *)page_address(ZERO_PAGE(0)); + unsigned long phys, end; + + end = base + size; + for (phys = base; phys < end; phys += 64) + movdir64b(__va(phys), zero_page); + + /* + * MOVDIR64B uses WC protocol. Use memory barrier to + * make sure any later user of these pages sees the + * updated data. + */ + mb(); +} + +static void tdmr_reset_pamt(struct tdmr_info *tdmr) +{ + tdmr_do_pamt_func(tdmr, reset_tdx_pages); +} + +static void tdmrs_reset_pamt_all(struct tdmr_info_list *tdmr_list) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_reset_pamt(tdmr_entry(tdmr_list, i)); +} + +static unsigned long tdmrs_count_pamt_kb(struct tdmr_info_list *tdmr_list) +{ + unsigned long pamt_size = 0; + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + unsigned long base, size; + + tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size); + pamt_size += size; + } + + return pamt_size / 1024; +} + +static int tdmr_add_rsvd_area(struct tdmr_info *tdmr, int *p_idx, u64 addr, + u64 size, u16 max_reserved_per_tdmr) +{ + struct tdmr_reserved_area *rsvd_areas = tdmr->reserved_areas; + int idx = *p_idx; + + /* Reserved area must be 4K aligned in offset and size */ + if (WARN_ON(addr & ~PAGE_MASK || size & ~PAGE_MASK)) + return -EINVAL; + + if (idx >= max_reserved_per_tdmr) { + pr_warn("initialization failed: TDMR [0x%llx, 0x%llx): reserved areas exhausted.\n", + tdmr->base, tdmr_end(tdmr)); + return -ENOSPC; + } + + /* + * Consume one reserved area per call. Make no effort to + * optimize or reduce the number of reserved areas which are + * consumed by contiguous reserved areas, for instance. + */ + rsvd_areas[idx].offset = addr - tdmr->base; + rsvd_areas[idx].size = size; + + *p_idx = idx + 1; + + return 0; +} + +/* + * Go through @tmb_list to find holes between memory areas. If any of + * those holes fall within @tdmr, set up a TDMR reserved area to cover + * the hole. + */ +static int tdmr_populate_rsvd_holes(struct list_head *tmb_list, + struct tdmr_info *tdmr, + int *rsvd_idx, + u16 max_reserved_per_tdmr) +{ + struct tdx_memblock *tmb; + u64 prev_end; + int ret; + + /* + * Start looking for reserved blocks at the + * beginning of the TDMR. + */ + prev_end = tdmr->base; + list_for_each_entry(tmb, tmb_list, list) { + u64 start, end; + + start = PFN_PHYS(tmb->start_pfn); + end = PFN_PHYS(tmb->end_pfn); + + /* Break if this region is after the TDMR */ + if (start >= tdmr_end(tdmr)) + break; + + /* Exclude regions before this TDMR */ + if (end < tdmr->base) + continue; + + /* + * Skip over memory areas that + * have already been dealt with. + */ + if (start <= prev_end) { + prev_end = end; + continue; + } + + /* Add the hole before this region */ + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end, + start - prev_end, + max_reserved_per_tdmr); + if (ret) + return ret; + + prev_end = end; + } + + /* Add the hole after the last region if it exists. */ + if (prev_end < tdmr_end(tdmr)) { + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, prev_end, + tdmr_end(tdmr) - prev_end, + max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* + * Go through @tdmr_list to find all PAMTs. If any of those PAMTs + * overlaps with @tdmr, set up a TDMR reserved area to cover the + * overlapping part. + */ +static int tdmr_populate_rsvd_pamts(struct tdmr_info_list *tdmr_list, + struct tdmr_info *tdmr, + int *rsvd_idx, + u16 max_reserved_per_tdmr) +{ + int i, ret; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + struct tdmr_info *tmp = tdmr_entry(tdmr_list, i); + unsigned long pamt_base, pamt_size, pamt_end; + + tdmr_get_pamt(tmp, &pamt_base, &pamt_size); + /* Each TDMR must already have PAMT allocated */ + WARN_ON_ONCE(!pamt_size || !pamt_base); + + pamt_end = pamt_base + pamt_size; + /* Skip PAMTs outside of the given TDMR */ + if ((pamt_end <= tdmr->base) || + (pamt_base >= tdmr_end(tdmr))) + continue; + + /* Only mark the part within the TDMR as reserved */ + if (pamt_base < tdmr->base) + pamt_base = tdmr->base; + if (pamt_end > tdmr_end(tdmr)) + pamt_end = tdmr_end(tdmr); + + ret = tdmr_add_rsvd_area(tdmr, rsvd_idx, pamt_base, + pamt_end - pamt_base, + max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* Compare function called by sort() for TDMR reserved areas */ +static int rsvd_area_cmp_func(const void *a, const void *b) +{ + struct tdmr_reserved_area *r1 = (struct tdmr_reserved_area *)a; + struct tdmr_reserved_area *r2 = (struct tdmr_reserved_area *)b; + + if (r1->offset + r1->size <= r2->offset) + return -1; + if (r1->offset >= r2->offset + r2->size) + return 1; + + /* Reserved areas cannot overlap. The caller must guarantee. */ + WARN_ON_ONCE(1); + return -1; +} + +/* + * Populate reserved areas for the given @tdmr, including memory holes + * (via @tmb_list) and PAMTs (via @tdmr_list). + */ +static int tdmr_populate_rsvd_areas(struct tdmr_info *tdmr, + struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list, + u16 max_reserved_per_tdmr) +{ + int ret, rsvd_idx = 0; + + ret = tdmr_populate_rsvd_holes(tmb_list, tdmr, &rsvd_idx, + max_reserved_per_tdmr); + if (ret) + return ret; + + ret = tdmr_populate_rsvd_pamts(tdmr_list, tdmr, &rsvd_idx, + max_reserved_per_tdmr); + if (ret) + return ret; + + /* TDX requires reserved areas listed in address ascending order */ + sort(tdmr->reserved_areas, rsvd_idx, sizeof(struct tdmr_reserved_area), + rsvd_area_cmp_func, NULL); + + return 0; +} + +/* + * Populate reserved areas for all TDMRs in @tdmr_list, including memory + * holes (via @tmb_list) and PAMTs. + */ +static int tdmrs_populate_rsvd_areas_all(struct tdmr_info_list *tdmr_list, + struct list_head *tmb_list, + u16 max_reserved_per_tdmr) +{ + int i; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + int ret; + + ret = tdmr_populate_rsvd_areas(tdmr_entry(tdmr_list, i), + tmb_list, tdmr_list, max_reserved_per_tdmr); + if (ret) + return ret; + } + + return 0; +} + +/* + * Construct a list of TDMRs on the preallocated space in @tdmr_list + * to cover all TDX memory regions in @tmb_list based on the TDX module + * TDMR global information in @tdmr_sysinfo. + */ +static int construct_tdmrs(struct list_head *tmb_list, + struct tdmr_info_list *tdmr_list, + struct tdx_tdmr_sysinfo *tdmr_sysinfo) +{ + int ret; + + ret = fill_out_tdmrs(tmb_list, tdmr_list); + if (ret) + return ret; + + ret = tdmrs_set_up_pamt_all(tdmr_list, tmb_list, + tdmr_sysinfo->pamt_entry_size); + if (ret) + return ret; + + ret = tdmrs_populate_rsvd_areas_all(tdmr_list, tmb_list, + tdmr_sysinfo->max_reserved_per_tdmr); + if (ret) + tdmrs_free_pamt_all(tdmr_list); + + /* + * The tdmr_info_list is read-only from here on out. + * Ensure that these writes are seen by other CPUs. + * Pairs with a smp_rmb() in is_pamt_page(). + */ + smp_wmb(); + + return ret; +} + +static int config_tdx_module(struct tdmr_info_list *tdmr_list, u64 global_keyid) +{ + struct tdx_module_args args = {}; + u64 *tdmr_pa_array; + size_t array_sz; + int i, ret; + + /* + * TDMRs are passed to the TDX module via an array of physical + * addresses of each TDMR. The array itself also has certain + * alignment requirement. + */ + array_sz = tdmr_list->nr_consumed_tdmrs * sizeof(u64); + array_sz = roundup_pow_of_two(array_sz); + if (array_sz < TDMR_INFO_PA_ARRAY_ALIGNMENT) + array_sz = TDMR_INFO_PA_ARRAY_ALIGNMENT; + + tdmr_pa_array = kzalloc(array_sz, GFP_KERNEL); + if (!tdmr_pa_array) + return -ENOMEM; + + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) + tdmr_pa_array[i] = __pa(tdmr_entry(tdmr_list, i)); + + args.rcx = __pa(tdmr_pa_array); + args.rdx = tdmr_list->nr_consumed_tdmrs; + args.r8 = global_keyid; + ret = seamcall_prerr(TDH_SYS_CONFIG, &args); + + /* Free the array as it is not required anymore. */ + kfree(tdmr_pa_array); + + return ret; +} + +static int do_global_key_config(void *unused) +{ + struct tdx_module_args args = {}; + + return seamcall_prerr(TDH_SYS_KEY_CONFIG, &args); +} + +/* + * Attempt to configure the global KeyID on all physical packages. + * + * This requires running code on at least one CPU in each package. + * TDMR initialization) will fail will fail if any package in the + * system has no online CPUs. + * + * This code takes no affirmative steps to online CPUs. Callers (aka. + * KVM) can ensure success by ensuring sufficient CPUs are online and + * can run SEAMCALLs. + */ +static int config_global_keyid(void) +{ + cpumask_var_t packages; + int cpu, ret = -EINVAL; + + if (!zalloc_cpumask_var(&packages, GFP_KERNEL)) + return -ENOMEM; + + /* + * Hardware doesn't guarantee cache coherency across different + * KeyIDs. The kernel needs to flush PAMT's dirty cachelines + * (associated with KeyID 0) before the TDX module can use the + * global KeyID to access the PAMT. Given PAMTs are potentially + * large (~1/256th of system RAM), just use WBINVD. + */ + wbinvd_on_all_cpus(); + + for_each_online_cpu(cpu) { + /* + * The key configuration only needs to be done once per + * package and will return an error if configured more + * than once. Avoid doing it multiple times per package. + */ + if (cpumask_test_and_set_cpu(topology_physical_package_id(cpu), + packages)) + continue; + + /* + * TDH.SYS.KEY.CONFIG cannot run concurrently on + * different cpus. Do it one by one. + */ + ret = smp_call_on_cpu(cpu, do_global_key_config, NULL, true); + if (ret) + break; + } + + free_cpumask_var(packages); + return ret; +} + +static int init_tdmr(struct tdmr_info *tdmr) +{ + u64 next; + + /* + * Initializing a TDMR can be time consuming. To avoid long + * SEAMCALLs, the TDX module may only initialize a part of the + * TDMR in each call. + */ + do { + struct tdx_module_args args = { + .rcx = tdmr->base, + }; + int ret; + + ret = seamcall_prerr_ret(TDH_SYS_TDMR_INIT, &args); + if (ret) + return ret; + /* + * RDX contains 'next-to-initialize' address if + * TDH.SYS.TDMR.INIT did not fully complete and + * should be retried. + */ + next = args.rdx; + cond_resched(); + /* Keep making SEAMCALLs until the TDMR is done */ + } while (next < tdmr->base + tdmr->size); + + return 0; +} + +static int init_tdmrs(struct tdmr_info_list *tdmr_list) +{ + int i; + + /* + * This operation is costly. It can be parallelized, + * but keep it simple for now. + */ + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + int ret; + + ret = init_tdmr(tdmr_entry(tdmr_list, i)); + if (ret) + return ret; + } + + return 0; +} + +static int init_tdx_module(void) +{ + struct tdx_tdmr_sysinfo tdmr_sysinfo; + int ret; + + /* + * To keep things simple, assume that all TDX-protected memory + * will come from the page allocator. Make sure all pages in the + * page allocator are TDX-usable memory. + * + * Build the list of "TDX-usable" memory regions which cover all + * pages in the page allocator to guarantee that. Do it while + * holding mem_hotplug_lock read-lock as the memory hotplug code + * path reads the @tdx_memlist to reject any new memory. + */ + get_online_mems(); + + ret = build_tdx_memlist(&tdx_memlist); + if (ret) + goto out_put_tdxmem; + + ret = get_tdx_tdmr_sysinfo(&tdmr_sysinfo); + if (ret) + goto err_free_tdxmem; + + /* Allocate enough space for constructing TDMRs */ + ret = alloc_tdmr_list(&tdx_tdmr_list, &tdmr_sysinfo); + if (ret) + goto err_free_tdxmem; + + /* Cover all TDX-usable memory regions in TDMRs */ + ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &tdmr_sysinfo); + if (ret) + goto err_free_tdmrs; + + /* Pass the TDMRs and the global KeyID to the TDX module */ + ret = config_tdx_module(&tdx_tdmr_list, tdx_global_keyid); + if (ret) + goto err_free_pamts; + + /* Config the key of global KeyID on all packages */ + ret = config_global_keyid(); + if (ret) + goto err_reset_pamts; + + /* Initialize TDMRs to complete the TDX module initialization */ + ret = init_tdmrs(&tdx_tdmr_list); + if (ret) + goto err_reset_pamts; + + pr_info("%lu KB allocated for PAMT\n", tdmrs_count_pamt_kb(&tdx_tdmr_list)); + +out_put_tdxmem: + /* + * @tdx_memlist is written here and read at memory hotplug time. + * Lock out memory hotplug code while building it. + */ + put_online_mems(); + return ret; + +err_reset_pamts: + /* + * Part of PAMTs may already have been initialized by the + * TDX module. Flush cache before returning PAMTs back + * to the kernel. + */ + wbinvd_on_all_cpus(); + /* + * According to the TDX hardware spec, if the platform + * doesn't have the "partial write machine check" + * erratum, any kernel read/write will never cause #MC + * in kernel space, thus it's OK to not convert PAMTs + * back to normal. But do the conversion anyway here + * as suggested by the TDX spec. + */ + tdmrs_reset_pamt_all(&tdx_tdmr_list); +err_free_pamts: + tdmrs_free_pamt_all(&tdx_tdmr_list); +err_free_tdmrs: + free_tdmr_list(&tdx_tdmr_list); +err_free_tdxmem: + free_tdx_memlist(&tdx_memlist); + goto out_put_tdxmem; +} + +static int __tdx_enable(void) +{ + int ret; + + ret = init_tdx_module(); + if (ret) { + pr_err("module initialization failed (%d)\n", ret); + tdx_module_status = TDX_MODULE_ERROR; + return ret; + } + + pr_info("module initialized\n"); + tdx_module_status = TDX_MODULE_INITIALIZED; + + return 0; +} + +/** + * tdx_enable - Enable TDX module to make it ready to run TDX guests + * + * This function assumes the caller has: 1) held read lock of CPU hotplug + * lock to prevent any new cpu from becoming online; 2) done both VMXON + * and tdx_cpu_enable() on all online cpus. + * + * This function requires there's at least one online cpu for each CPU + * package to succeed. + * + * This function can be called in parallel by multiple callers. + * + * Return 0 if TDX is enabled successfully, otherwise error. + */ +int tdx_enable(void) +{ + int ret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return -ENODEV; + + lockdep_assert_cpus_held(); + + mutex_lock(&tdx_module_lock); + + switch (tdx_module_status) { + case TDX_MODULE_UNINITIALIZED: + ret = __tdx_enable(); + break; + case TDX_MODULE_INITIALIZED: + /* Already initialized, great, tell the caller. */ + ret = 0; + break; + default: + /* Failed to initialize in the previous attempts */ + ret = -EINVAL; + break; + } + + mutex_unlock(&tdx_module_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(tdx_enable); + +static bool is_pamt_page(unsigned long phys) +{ + struct tdmr_info_list *tdmr_list = &tdx_tdmr_list; + int i; + + /* Ensure that all remote 'tdmr_list' writes are visible: */ + smp_rmb(); + + /* + * The TDX module is no longer returning TDX_SYS_NOT_READY and + * is initialized. The 'tdmr_list' was initialized long ago + * and is now read-only. + */ + for (i = 0; i < tdmr_list->nr_consumed_tdmrs; i++) { + unsigned long base, size; + + tdmr_get_pamt(tdmr_entry(tdmr_list, i), &base, &size); + + if (phys >= base && phys < (base + size)) + return true; + } + + return false; +} + +/* + * Return whether the memory page at the given physical address is TDX + * private memory or not. + * + * This can be imprecise for two known reasons: + * 1. PAMTs are private memory and exist before the TDX module is + * ready and TDH_PHYMEM_PAGE_RDMD works. This is a relatively + * short window that occurs once per boot. + * 2. TDH_PHYMEM_PAGE_RDMD reflects the TDX module's knowledge of the + * page. However, the page can still cause #MC until it has been + * fully converted to shared using 64-byte writes like MOVDIR64B. + * Buggy hosts might still leave #MC-causing memory in place which + * this function can not detect. + */ +static bool paddr_is_tdx_private(unsigned long phys) +{ + struct tdx_module_args args = { + .rcx = phys & PAGE_MASK, + }; + u64 sret; + + if (!boot_cpu_has(X86_FEATURE_TDX_HOST_PLATFORM)) + return false; + + /* Get page type from the TDX module */ + sret = __seamcall_ret(TDH_PHYMEM_PAGE_RDMD, &args); + + /* + * The SEAMCALL will not return success unless there is a + * working, "ready" TDX module. Assume an absence of TDX + * private pages until SEAMCALL is working. + */ + if (sret) + return false; + + /* + * SEAMCALL was successful -- read page type (via RCX): + * + * - PT_NDA: Page is not used by the TDX module + * - PT_RSVD: Reserved for Non-TDX use + * - Others: Page is used by the TDX module + * + * Note PAMT pages are marked as PT_RSVD but they are also TDX + * private memory. + */ + switch (args.rcx) { + case PT_NDA: + return false; + case PT_RSVD: + return is_pamt_page(phys); + default: + return true; + } +} + +/* + * Some TDX-capable CPUs have an erratum. A write to TDX private + * memory poisons that memory, and a subsequent read of that memory + * triggers #MC. + * + * Help distinguish erratum-triggered #MCs from a normal hardware one. + * Just print additional message to show such #MC may be result of the + * erratum. + */ +const char *tdx_dump_mce_info(struct mce *m) +{ + if (!m || !mce_is_memory_error(m) || !mce_usable_address(m)) + return NULL; + + if (!paddr_is_tdx_private(m->addr)) + return NULL; + + return "TDX private memory error. Possible kernel bug."; +} + +static __init int record_keyid_partitioning(u32 *tdx_keyid_start, + u32 *nr_tdx_keyids) +{ + u32 _nr_mktme_keyids, _tdx_keyid_start, _nr_tdx_keyids; + int ret; + + /* + * IA32_MKTME_KEYID_PARTIONING: + * Bit [31:0]: Number of MKTME KeyIDs. + * Bit [63:32]: Number of TDX private KeyIDs. + */ + ret = rdmsr_safe(MSR_IA32_MKTME_KEYID_PARTITIONING, &_nr_mktme_keyids, + &_nr_tdx_keyids); + if (ret || !_nr_tdx_keyids) + return -EINVAL; + + /* TDX KeyIDs start after the last MKTME KeyID. */ + _tdx_keyid_start = _nr_mktme_keyids + 1; + + *tdx_keyid_start = _tdx_keyid_start; + *nr_tdx_keyids = _nr_tdx_keyids; + + return 0; +} + +static bool is_tdx_memory(unsigned long start_pfn, unsigned long end_pfn) +{ + struct tdx_memblock *tmb; + + /* + * This check assumes that the start_pfn<->end_pfn range does not + * cross multiple @tdx_memlist entries. A single memory online + * event across multiple memblocks (from which @tdx_memlist + * entries are derived at the time of module initialization) is + * not possible. This is because memory offline/online is done + * on granularity of 'struct memory_block', and the hotpluggable + * memory region (one memblock) must be multiple of memory_block. + */ + list_for_each_entry(tmb, &tdx_memlist, list) { + if (start_pfn >= tmb->start_pfn && end_pfn <= tmb->end_pfn) + return true; + } + return false; +} + +static int tdx_memory_notifier(struct notifier_block *nb, unsigned long action, + void *v) +{ + struct memory_notify *mn = v; + + if (action != MEM_GOING_ONLINE) + return NOTIFY_OK; + + /* + * Empty list means TDX isn't enabled. Allow any memory + * to go online. + */ + if (list_empty(&tdx_memlist)) + return NOTIFY_OK; + + /* + * The TDX memory configuration is static and can not be + * changed. Reject onlining any memory which is outside of + * the static configuration whether it supports TDX or not. + */ + if (is_tdx_memory(mn->start_pfn, mn->start_pfn + mn->nr_pages)) + return NOTIFY_OK; + + return NOTIFY_BAD; +} + +static struct notifier_block tdx_memory_nb = { + .notifier_call = tdx_memory_notifier, +}; + +static void __init check_tdx_erratum(void) +{ + /* + * These CPUs have an erratum. A partial write from non-TD + * software (e.g. via MOVNTI variants or UC/WC mapping) to TDX + * private memory poisons that memory, and a subsequent read of + * that memory triggers #MC. + */ + switch (boot_cpu_data.x86_model) { + case INTEL_FAM6_SAPPHIRERAPIDS_X: + case INTEL_FAM6_EMERALDRAPIDS_X: + setup_force_cpu_bug(X86_BUG_TDX_PW_MCE); + } +} + +void __init tdx_init(void) +{ + u32 tdx_keyid_start, nr_tdx_keyids; + int err; + + err = record_keyid_partitioning(&tdx_keyid_start, &nr_tdx_keyids); + if (err) + return; + + pr_info("BIOS enabled: private KeyID range [%u, %u)\n", + tdx_keyid_start, tdx_keyid_start + nr_tdx_keyids); + + /* + * The TDX module itself requires one 'global KeyID' to protect + * its metadata. If there's only one TDX KeyID, there won't be + * any left for TDX guests thus there's no point to enable TDX + * at all. + */ + if (nr_tdx_keyids < 2) { + pr_err("initialization failed: too few private KeyIDs available.\n"); + return; + } + + /* + * At this point, hibernation_available() indicates whether or + * not hibernation support has been permanently disabled. + */ + if (hibernation_available()) { + pr_err("initialization failed: Hibernation support is enabled\n"); + return; + } + + err = register_memory_notifier(&tdx_memory_nb); + if (err) { + pr_err("initialization failed: register_memory_notifier() failed (%d)\n", + err); + return; + } + +#if defined(CONFIG_ACPI) && defined(CONFIG_SUSPEND) + pr_info("Disable ACPI S3. Turn off TDX in the BIOS to use ACPI S3.\n"); + acpi_suspend_lowlevel = NULL; +#endif + + /* + * Just use the first TDX KeyID as the 'global KeyID' and + * leave the rest for TDX guests. + */ + tdx_global_keyid = tdx_keyid_start; + tdx_guest_keyid_start = tdx_keyid_start + 1; + tdx_nr_guest_keyids = nr_tdx_keyids - 1; + + setup_force_cpu_cap(X86_FEATURE_TDX_HOST_PLATFORM); + + check_tdx_erratum(); +} diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h new file mode 100644 index 0000000000..b701f69485 --- /dev/null +++ b/arch/x86/virt/vmx/tdx/tdx.h @@ -0,0 +1,121 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _X86_VIRT_TDX_H +#define _X86_VIRT_TDX_H + +#include <linux/bits.h> + +/* + * This file contains both macros and data structures defined by the TDX + * architecture and Linux defined software data structures and functions. + * The two should not be mixed together for better readability. The + * architectural definitions come first. + */ + +/* + * TDX module SEAMCALL leaf functions + */ +#define TDH_PHYMEM_PAGE_RDMD 24 +#define TDH_SYS_KEY_CONFIG 31 +#define TDH_SYS_INIT 33 +#define TDH_SYS_RD 34 +#define TDH_SYS_LP_INIT 35 +#define TDH_SYS_TDMR_INIT 36 +#define TDH_SYS_CONFIG 45 + +/* TDX page types */ +#define PT_NDA 0x0 +#define PT_RSVD 0x1 + +/* + * Global scope metadata field ID. + * + * See Table "Global Scope Metadata", TDX module 1.5 ABI spec. + */ +#define MD_FIELD_ID_MAX_TDMRS 0x9100000100000008ULL +#define MD_FIELD_ID_MAX_RESERVED_PER_TDMR 0x9100000100000009ULL +#define MD_FIELD_ID_PAMT_4K_ENTRY_SIZE 0x9100000100000010ULL +#define MD_FIELD_ID_PAMT_2M_ENTRY_SIZE 0x9100000100000011ULL +#define MD_FIELD_ID_PAMT_1G_ENTRY_SIZE 0x9100000100000012ULL + +/* + * Sub-field definition of metadata field ID. + * + * See Table "MD_FIELD_ID (Metadata Field Identifier / Sequence Header) + * Definition", TDX module 1.5 ABI spec. + * + * - Bit 33:32: ELEMENT_SIZE_CODE -- size of a single element of metadata + * + * 0: 8 bits + * 1: 16 bits + * 2: 32 bits + * 3: 64 bits + */ +#define MD_FIELD_ID_ELE_SIZE_CODE(_field_id) \ + (((_field_id) & GENMASK_ULL(33, 32)) >> 32) + +#define MD_FIELD_ID_ELE_SIZE_16BIT 1 + +struct tdmr_reserved_area { + u64 offset; + u64 size; +} __packed; + +#define TDMR_INFO_ALIGNMENT 512 +#define TDMR_INFO_PA_ARRAY_ALIGNMENT 512 + +struct tdmr_info { + u64 base; + u64 size; + u64 pamt_1g_base; + u64 pamt_1g_size; + u64 pamt_2m_base; + u64 pamt_2m_size; + u64 pamt_4k_base; + u64 pamt_4k_size; + /* + * The actual number of reserved areas depends on the value of + * field MD_FIELD_ID_MAX_RESERVED_PER_TDMR in the TDX module + * global metadata. + */ + DECLARE_FLEX_ARRAY(struct tdmr_reserved_area, reserved_areas); +} __packed __aligned(TDMR_INFO_ALIGNMENT); + +/* + * Do not put any hardware-defined TDX structure representations below + * this comment! + */ + +/* Kernel defined TDX module status during module initialization. */ +enum tdx_module_status_t { + TDX_MODULE_UNINITIALIZED, + TDX_MODULE_INITIALIZED, + TDX_MODULE_ERROR +}; + +struct tdx_memblock { + struct list_head list; + unsigned long start_pfn; + unsigned long end_pfn; + int nid; +}; + +/* "TDMR info" part of "Global Scope Metadata" for constructing TDMRs */ +struct tdx_tdmr_sysinfo { + u16 max_tdmrs; + u16 max_reserved_per_tdmr; + u16 pamt_entry_size[TDX_PS_NR]; +}; + +/* Warn if kernel has less than TDMR_NR_WARN TDMRs after allocation */ +#define TDMR_NR_WARN 4 + +struct tdmr_info_list { + void *tdmrs; /* Flexible array to hold 'tdmr_info's */ + int nr_consumed_tdmrs; /* How many 'tdmr_info's are in use */ + + /* Metadata for finding target 'tdmr_info' and freeing @tdmrs */ + int tdmr_sz; /* Size of one 'tdmr_info' */ + int max_tdmrs; /* How many 'tdmr_info's are allocated */ +}; + +#endif diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 3c61bb98c1..a01ca255b0 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -6,6 +6,7 @@ #include <linux/console.h> #include <linux/cpu.h> #include <linux/kexec.h> +#include <linux/memblock.h> #include <linux/slab.h> #include <linux/panic_notifier.h> @@ -350,3 +351,34 @@ void xen_arch_unregister_cpu(int num) } EXPORT_SYMBOL(xen_arch_unregister_cpu); #endif + +/* Amount of extra memory space we add to the e820 ranges */ +struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; + +void __init xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns) +{ + unsigned int i; + + /* + * No need to check for zero size, should happen rarely and will only + * write a new entry regarded to be unused due to zero size. + */ + for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { + /* Add new region. */ + if (xen_extra_mem[i].n_pfns == 0) { + xen_extra_mem[i].start_pfn = start_pfn; + xen_extra_mem[i].n_pfns = n_pfns; + break; + } + /* Append to existing region. */ + if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == + start_pfn) { + xen_extra_mem[i].n_pfns += n_pfns; + break; + } + } + if (i == XEN_EXTRA_MEM_MAX_REGIONS) + printk(KERN_WARNING "Warning: not enough extra memory regions\n"); + + memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); +} diff --git a/arch/x86/xen/enlighten_pvh.c b/arch/x86/xen/enlighten_pvh.c index ada3868c02..c28f073c1d 100644 --- a/arch/x86/xen/enlighten_pvh.c +++ b/arch/x86/xen/enlighten_pvh.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <linux/acpi.h> #include <linux/export.h> +#include <linux/mm.h> #include <xen/hvc-console.h> @@ -72,3 +73,70 @@ void __init mem_map_via_hcall(struct boot_params *boot_params_p) } boot_params_p->e820_entries = memmap.nr_entries; } + +/* + * Reserve e820 UNUSABLE regions to inflate the memory balloon. + * + * On PVH dom0 the host memory map is used, RAM regions available to dom0 are + * located as the same place as in the native memory map, but since dom0 gets + * less memory than the total amount of host RAM the ranges that can't be + * populated are converted from RAM -> UNUSABLE. Use such regions (up to the + * ratio signaled in EXTRA_MEM_RATIO) in order to inflate the balloon driver at + * boot. Doing so prevents the guest (even if just temporary) from using holes + * in the memory map in order to map grants or foreign addresses, and + * hopefully limits the risk of a clash with a device MMIO region. Ideally the + * hypervisor should notify us which memory ranges are suitable for creating + * foreign mappings, but that's not yet implemented. + */ +void __init xen_reserve_extra_memory(struct boot_params *bootp) +{ + unsigned int i, ram_pages = 0, extra_pages; + + for (i = 0; i < bootp->e820_entries; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + + if (e->type != E820_TYPE_RAM) + continue; + ram_pages += PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr); + } + + /* Max amount of extra memory. */ + extra_pages = EXTRA_MEM_RATIO * ram_pages; + + /* + * Convert UNUSABLE ranges to RAM and reserve them for foreign mapping + * purposes. + */ + for (i = 0; i < bootp->e820_entries && extra_pages; i++) { + struct boot_e820_entry *e = &bootp->e820_table[i]; + unsigned long pages; + + if (e->type != E820_TYPE_UNUSABLE) + continue; + + pages = min(extra_pages, + PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr)); + + if (pages != (PFN_DOWN(e->addr + e->size) - PFN_UP(e->addr))) { + struct boot_e820_entry *next; + + if (bootp->e820_entries == + ARRAY_SIZE(bootp->e820_table)) + /* No space left to split - skip region. */ + continue; + + /* Split entry. */ + next = e + 1; + memmove(next, e, + (bootp->e820_entries - i) * sizeof(*e)); + bootp->e820_entries++; + next->addr = PAGE_ALIGN(e->addr) + PFN_PHYS(pages); + e->size = next->addr - e->addr; + next->size -= e->size; + } + e->type = E820_TYPE_RAM; + extra_pages -= pages; + + xen_add_extra_mem(PFN_UP(e->addr), pages); + } +} diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c index 6092fea7d6..39982f955c 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 b6830554ff..994aef4473 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. * @@ -1082,7 +1082,7 @@ static void __init xen_cleanmfnmap_pud(pud_t *pud, bool unpin) pmd_t *pmd_tbl; int i; - if (pud_large(*pud)) { + if (pud_leaf(*pud)) { pa = pud_val(*pud) & PHYSICAL_PAGE_MASK; xen_free_ro_pages(pa, PUD_SIZE); return; @@ -1863,7 +1863,7 @@ static phys_addr_t __init xen_early_virt_to_phys(unsigned long vaddr) if (!pud_present(pud)) return 0; pa = pud_val(pud) & PTE_PFN_MASK; - if (pud_large(pud)) + if (pud_leaf(pud)) return pa + (vaddr & ~PUD_MASK); pmd = native_make_pmd(xen_read_phys_ulong(pa + pmd_index(vaddr) * diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index b3e3796106..380591028c 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -38,9 +38,6 @@ #define GB(x) ((uint64_t)(x) * 1024 * 1024 * 1024) -/* Amount of extra memory space we add to the e820 ranges */ -struct xen_memory_region xen_extra_mem[XEN_EXTRA_MEM_MAX_REGIONS] __initdata; - /* Number of pages released from the initial allocation. */ unsigned long xen_released_pages; @@ -64,18 +61,6 @@ static struct { } xen_remap_buf __initdata __aligned(PAGE_SIZE); static unsigned long xen_remap_mfn __initdata = INVALID_P2M_ENTRY; -/* - * The maximum amount of extra memory compared to the base size. The - * main scaling factor is the size of struct page. At extreme ratios - * of base:extra, all the base memory can be filled with page - * structures for the extra memory, leaving no space for anything - * else. - * - * 10x seems like a reasonable balance between scaling flexibility and - * leaving a practically usable system. - */ -#define EXTRA_MEM_RATIO (10) - static bool xen_512gb_limit __initdata = IS_ENABLED(CONFIG_XEN_512GB); static void __init xen_parse_512gb(void) @@ -96,35 +81,6 @@ static void __init xen_parse_512gb(void) xen_512gb_limit = val; } -static void __init xen_add_extra_mem(unsigned long start_pfn, - unsigned long n_pfns) -{ - int i; - - /* - * No need to check for zero size, should happen rarely and will only - * write a new entry regarded to be unused due to zero size. - */ - for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) { - /* Add new region. */ - if (xen_extra_mem[i].n_pfns == 0) { - xen_extra_mem[i].start_pfn = start_pfn; - xen_extra_mem[i].n_pfns = n_pfns; - break; - } - /* Append to existing region. */ - if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns == - start_pfn) { - xen_extra_mem[i].n_pfns += n_pfns; - break; - } - } - if (i == XEN_EXTRA_MEM_MAX_REGIONS) - printk(KERN_WARNING "Warning: not enough extra memory regions\n"); - - memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns)); -} - static void __init xen_del_extra_mem(unsigned long start_pfn, unsigned long n_pfns) { diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index a87ab36889..79cf93f2c9 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -163,4 +163,18 @@ void xen_hvm_post_suspend(int suspend_cancelled); static inline void xen_hvm_post_suspend(int suspend_cancelled) {} #endif +/* + * The maximum amount of extra memory compared to the base size. The + * main scaling factor is the size of struct page. At extreme ratios + * of base:extra, all the base memory can be filled with page + * structures for the extra memory, leaving no space for anything + * else. + * + * 10x seems like a reasonable balance between scaling flexibility and + * leaving a practically usable system. + */ +#define EXTRA_MEM_RATIO (10) + +void xen_add_extra_mem(unsigned long start_pfn, unsigned long n_pfns); + #endif /* XEN_OPS_H */ |