diff --git a/target/i386/cpu.c b/target/i386/cpu.c index efe8bf0948100cd1c320668f610ba57d00a84c32..fd6ff026a60113d15a8acbb36f8f1b094d71882a 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -48,6 +48,9 @@ #include "cpu-internal.h" static void x86_cpu_realizefn(DeviceState *dev, Error **errp); +static void x86_cpu_get_supported_cpuid(uint32_t func, uint32_t index, + uint32_t *eax, uint32_t *ebx, + uint32_t *ecx, uint32_t *edx); /* Helpers for building CPUID[2] descriptors: */ @@ -751,6 +754,7 @@ void x86_cpu_vendor_words2str(char *dst, uint32_t vendor1, #define TCG_SGX_12_0_EAX_FEATURES 0 #define TCG_SGX_12_0_EBX_FEATURES 0 #define TCG_SGX_12_1_EAX_FEATURES 0 +#define TCG_24_0_EBX_FEATURES 0 #if defined CONFIG_USER_ONLY #define CPUID_8000_0008_EBX_KERNEL_FEATURES (CPUID_8000_0008_EBX_IBPB | \ @@ -985,7 +989,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { "avx-vnni-int8", "avx-ne-convert", NULL, NULL, "amx-complex", NULL, NULL, NULL, NULL, NULL, "prefetchiti", NULL, - NULL, NULL, NULL, NULL, + NULL, NULL, NULL, "avx10", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, @@ -1016,6 +1020,20 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { }, .tcg_features = TCG_7_2_EDX_FEATURES, }, + [FEAT_24_0_EBX] = { + .type = CPUID_FEATURE_WORD, + .feat_names = { + [16] = "avx10-128", + [17] = "avx10-256", + [18] = "avx10-512", + }, + .cpuid = { + .eax = 0x24, + .needs_ecx = true, .ecx = 0, + .reg = R_EBX, + }, + .tcg_features = TCG_24_0_EBX_FEATURES, + }, [FEAT_8000_0007_EDX] = { .type = CPUID_FEATURE_WORD, .feat_names = { @@ -1133,7 +1151,9 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .needs_ecx = true, .ecx = 0, .reg = R_EAX, }, - .tcg_features = ~0U, + .tcg_features = XSTATE_FP_MASK | XSTATE_SSE_MASK | + XSTATE_YMM_MASK | XSTATE_BNDREGS_MASK | XSTATE_BNDCSR_MASK | + XSTATE_PKRU_MASK, .migratable_flags = XSTATE_FP_MASK | XSTATE_SSE_MASK | XSTATE_YMM_MASK | XSTATE_BNDREGS_MASK | XSTATE_BNDCSR_MASK | XSTATE_OPMASK_MASK | XSTATE_ZMM_Hi256_MASK | XSTATE_Hi16_ZMM_MASK | @@ -1146,7 +1166,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .needs_ecx = true, .ecx = 0, .reg = R_EDX, }, - .tcg_features = ~0U, + .tcg_features = 0U, }, /*Below are MSR exposed features*/ [FEAT_ARCH_CAPABILITIES] = { @@ -1566,6 +1586,22 @@ static FeatureDep feature_dependencies[] = { .from = { FEAT_7_1_EAX, CPUID_7_1_EAX_WRMSRNS }, .to = { FEAT_7_1_EAX, CPUID_7_1_EAX_FRED }, }, + { + .from = { FEAT_24_0_EBX, CPUID_24_0_EBX_AVX10_128 }, + .to = { FEAT_24_0_EBX, CPUID_24_0_EBX_AVX10_256 }, + }, + { + .from = { FEAT_24_0_EBX, CPUID_24_0_EBX_AVX10_256 }, + .to = { FEAT_24_0_EBX, CPUID_24_0_EBX_AVX10_512 }, + }, + { + .from = { FEAT_24_0_EBX, CPUID_24_0_EBX_AVX10_VL_MASK }, + .to = { FEAT_7_1_EDX, CPUID_7_1_EDX_AVX10 }, + }, + { + .from = { FEAT_7_1_EDX, CPUID_7_1_EDX_AVX10 }, + .to = { FEAT_24_0_EBX, ~0ull }, + }, }; typedef struct X86RegisterInfo32 { @@ -1787,6 +1823,7 @@ typedef struct X86CPUDefinition { int family; int model; int stepping; + uint8_t avx10_version; FeatureWordArray features; const char *model_id; const CPUCaches *const cache_info; @@ -4189,6 +4226,23 @@ static const X86CPUDefinition builtin_x86_defs[] = { .model_id = "Intel Xeon Processor (GraniteRapids)", .versions = (X86CPUVersionDefinition[]) { { .version = 1 }, + { + .version = 2, + .props = (PropValue[]) { + { "ss", "on" }, + { "tsc-adjust", "on" }, + { "cldemote", "on" }, + { "movdiri", "on" }, + { "movdir64b", "on" }, + { "avx10", "on" }, + { "avx10-128", "on" }, + { "avx10-256", "on" }, + { "avx10-512", "on" }, + { "avx10-version", "1" }, + { "stepping", "1" }, + { /* end of list */ } + } + }, { /* end of list */ }, }, }, @@ -5942,7 +5996,7 @@ static void x86_cpu_parse_featurestr(const char *typename, char *features, } } -static void x86_cpu_filter_features(X86CPU *cpu, bool verbose); +static bool x86_cpu_filter_features(X86CPU *cpu, bool verbose); /* Build a list with the name of all features on a feature word array */ static void x86_cpu_list_feature_names(FeatureWordArray features, @@ -6403,6 +6457,9 @@ static void x86_cpu_load_model(X86CPU *cpu, X86CPUModel *model) */ object_property_set_str(OBJECT(cpu), "vendor", def->vendor, &error_abort); + object_property_set_uint(OBJECT(cpu), "avx10-version", def->avx10_version, + &error_abort); + x86_cpu_apply_version_props(cpu, model); /* @@ -6957,6 +7014,16 @@ void cpu_x86_cpuid(CPUX86State *env, uint32_t index, uint32_t count, } break; } + case 0x24: { + *eax = 0; + *ebx = 0; + *ecx = 0; + *edx = 0; + if ((env->features[FEAT_7_1_EDX] & CPUID_7_1_EDX_AVX10) && count == 0) { + *ebx = env->features[FEAT_24_0_EBX] | env->avx10_version; + } + break; + } case 0x40000000: /* * CPUID code in kvm_arch_init_vcpu() ignores stuff @@ -7186,6 +7253,23 @@ static void x86_cpu_set_sgxlepubkeyhash(CPUX86State *env) #endif } +static bool cpuid_has_xsave_feature(CPUX86State *env, const ExtSaveArea *esa) +{ + if (!esa->size) { + return false; + } + + if (env->features[esa->feature] & esa->bits) { + return true; + } + if (esa->feature == FEAT_7_0_EBX && esa->bits == CPUID_7_0_EBX_AVX512F + && (env->features[FEAT_7_1_EDX] & CPUID_7_1_EDX_AVX10)) { + return true; + } + + return false; +} + static void x86_cpu_reset_hold(Object *obj) { CPUState *s = CPU(obj); @@ -7294,7 +7378,7 @@ static void x86_cpu_reset_hold(Object *obj) if (!((1 << i) & CPUID_XSTATE_XCR0_MASK)) { continue; } - if (env->features[esa->feature] & esa->bits) { + if (cpuid_has_xsave_feature(env, esa)) { xcr0 |= 1ull << i; } } @@ -7432,7 +7516,7 @@ static void x86_cpu_enable_xsave_components(X86CPU *cpu) mask = 0; for (i = 0; i < ARRAY_SIZE(x86_ext_save_areas); i++) { const ExtSaveArea *esa = &x86_ext_save_areas[i]; - if (env->features[esa->feature] & esa->bits) { + if (cpuid_has_xsave_feature(env, esa)) { mask |= (1ULL << i); } } @@ -7525,6 +7609,12 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) ~env->user_features[w] & ~feature_word_info[w].no_autoenable_flags; } + + if ((env->features[FEAT_7_1_EDX] & CPUID_7_1_EDX_AVX10) && !env->avx10_version) { + uint32_t eax, ebx, ecx, edx; + x86_cpu_get_supported_cpuid(0x24, 0, &eax, &ebx, &ecx, &edx); + env->avx10_version = ebx & 0xff; + } } for (i = 0; i < ARRAY_SIZE(feature_dependencies); i++) { @@ -7588,6 +7678,11 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) x86_cpu_adjust_level(cpu, &env->cpuid_min_level, 0x1F); } + /* Advanced Vector Extensions 10 (AVX10) requires CPUID[0x24] */ + if (env->features[FEAT_7_1_EDX] & CPUID_7_1_EDX_AVX10) { + x86_cpu_adjust_level(cpu, &env->cpuid_min_level, 0x24); + } + /* SVM requires CPUID[0x8000000A] */ if (env->features[FEAT_8000_0001_ECX] & CPUID_EXT3_SVM) { x86_cpu_adjust_level(cpu, &env->cpuid_min_xlevel, 0x8000000A); @@ -7631,13 +7726,17 @@ void x86_cpu_expand_features(X86CPU *cpu, Error **errp) * Finishes initialization of CPUID data, filters CPU feature * words based on host availability of each feature. * - * Returns: 0 if all flags are supported by the host, non-zero otherwise. + * Returns: true if any flag is not supported by the host, false otherwise. */ -static void x86_cpu_filter_features(X86CPU *cpu, bool verbose) +static bool x86_cpu_filter_features(X86CPU *cpu, bool verbose) { CPUX86State *env = &cpu->env; FeatureWord w; const char *prefix = NULL; + bool have_filtered_features; + + uint32_t eax_0, ebx_0, ecx_0, edx_0; + uint32_t eax_1, ebx_1, ecx_1, edx_1; if (verbose) { prefix = accel_uses_host_cpuid() @@ -7654,13 +7753,10 @@ static void x86_cpu_filter_features(X86CPU *cpu, bool verbose) } if (env->features[FEAT_7_0_EBX] & CPUID_7_0_EBX_INTEL_PT) { - uint32_t eax_0, ebx_0, ecx_0, edx_0_unused; - uint32_t eax_1, ebx_1, ecx_1_unused, edx_1_unused; - x86_cpu_get_supported_cpuid(0x14, 0, - &eax_0, &ebx_0, &ecx_0, &edx_0_unused); + &eax_0, &ebx_0, &ecx_0, &edx_0); x86_cpu_get_supported_cpuid(0x14, 1, - &eax_1, &ebx_1, &ecx_1_unused, &edx_1_unused); + &eax_1, &ebx_1, &ecx_1, &edx_1); if (!eax_0 || ((ebx_0 & INTEL_PT_MINIMAL_EBX) != INTEL_PT_MINIMAL_EBX) || @@ -7680,6 +7776,28 @@ static void x86_cpu_filter_features(X86CPU *cpu, bool verbose) mark_unavailable_features(cpu, FEAT_7_0_EBX, CPUID_7_0_EBX_INTEL_PT, prefix); } } + + have_filtered_features = x86_cpu_have_filtered_features(cpu); + + if (env->features[FEAT_7_1_EDX] & CPUID_7_1_EDX_AVX10) { + x86_cpu_get_supported_cpuid(0x24, 0, + &eax_0, &ebx_0, &ecx_0, &edx_0); + uint8_t version = ebx_0 & 0xff; + + if (version < env->avx10_version) { + if (prefix) { + warn_report("%s: avx10.%d. Adjust to avx10.%d", + prefix, env->avx10_version, version); + } + env->avx10_version = version; + have_filtered_features = true; + } + } else if (env->avx10_version && prefix) { + warn_report("%s: avx10.%d.", prefix, env->avx10_version); + have_filtered_features = true; + } + + return have_filtered_features; } static void x86_cpu_hyperv_realize(X86CPU *cpu) @@ -7778,14 +7896,14 @@ static void x86_cpu_realizefn(DeviceState *dev, Error **errp) } } - x86_cpu_filter_features(cpu, cpu->check_cpuid || cpu->enforce_cpuid); - - if (cpu->enforce_cpuid && x86_cpu_have_filtered_features(cpu)) { - error_setg(&local_err, - accel_uses_host_cpuid() ? + if (x86_cpu_filter_features(cpu, cpu->check_cpuid || cpu->enforce_cpuid)) { + if (cpu->enforce_cpuid) { + error_setg(&local_err, + accel_uses_host_cpuid() ? "Host doesn't support requested features" : "TCG doesn't support requested features"); - goto out; + goto out; + } } /* On AMD CPUs, some CPUID[8000_0001].EDX bits must match the bits on @@ -8101,6 +8219,26 @@ static void x86_cpu_register_feature_bit_props(X86CPUClass *xcc, static void x86_cpu_post_initfn(Object *obj) { + static bool first = true; + uint64_t supported_xcr0; + int i; + + if (first) { + first = false; + + supported_xcr0 = + ((uint64_t) x86_cpu_get_supported_feature_word(NULL, FEAT_XSAVE_XCR0_HI) << 32) | + x86_cpu_get_supported_feature_word(NULL, FEAT_XSAVE_XCR0_LO); + + for (i = XSTATE_SSE_BIT + 1; i < XSAVE_STATE_AREA_COUNT; i++) { + ExtSaveArea *esa = &x86_ext_save_areas[i]; + + if (!(supported_xcr0 & (1 << i))) { + esa->size = 0; + } + } + } + accel_cpu_instance_init(CPU(obj)); } @@ -8395,6 +8533,7 @@ static Property x86_cpu_properties[] = { DEFINE_PROP_UINT32("min-level", X86CPU, env.cpuid_min_level, 0), DEFINE_PROP_UINT32("min-xlevel", X86CPU, env.cpuid_min_xlevel, 0), DEFINE_PROP_UINT32("min-xlevel2", X86CPU, env.cpuid_min_xlevel2, 0), + DEFINE_PROP_UINT8("avx10-version", X86CPU, env.avx10_version, 0), DEFINE_PROP_UINT64("ucode-rev", X86CPU, ucode_rev, 0), DEFINE_PROP_BOOL("full-cpuid-auto-level", X86CPU, full_cpuid_auto_level, true), DEFINE_PROP_STRING("hv-vendor-id", X86CPU, hyperv_vendor), diff --git a/target/i386/cpu.h b/target/i386/cpu.h index 9b37b6a8c40eb431ef26468bf5b153bbf0e3febc..e4e0e1abd9b7aeab511c3adc6a4bc155a65492a5 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -650,6 +650,7 @@ typedef enum FeatureWord { FEAT_XSAVE_XSS_HI, /* CPUID[EAX=0xd,ECX=1].EDX */ FEAT_7_1_EDX, /* CPUID[EAX=7,ECX=1].EDX */ FEAT_7_2_EDX, /* CPUID[EAX=7,ECX=2].EDX */ + FEAT_24_0_EBX, /* CPUID[EAX=0x24,ECX=0].EBX */ FEATURE_WORDS, } FeatureWord; @@ -976,6 +977,8 @@ uint64_t x86_cpu_get_supported_feature_word(X86CPU *cpu, FeatureWord w); #define CPUID_7_1_EDX_AVX_VNNI_INT16 (1U << 10) /* PREFETCHIT0/1 Instructions */ #define CPUID_7_1_EDX_PREFETCHITI (1U << 14) +/* Support for Advanced Vector Extensions 10 */ +#define CPUID_7_1_EDX_AVX10 (1U << 19) /* Indicate bit 7 of the IA32_SPEC_CTRL MSR is supported */ #define CPUID_7_2_EDX_PSFD (1U << 0) @@ -996,6 +999,17 @@ uint64_t x86_cpu_get_supported_feature_word(X86CPU *cpu, FeatureWord w); /* Packets which contain IP payload have LIP values */ #define CPUID_14_0_ECX_LIP (1U << 31) +/* AVX10 128-bit vector support is present */ +#define CPUID_24_0_EBX_AVX10_128 (1U << 16) +/* AVX10 256-bit vector support is present */ +#define CPUID_24_0_EBX_AVX10_256 (1U << 17) +/* AVX10 512-bit vector support is present */ +#define CPUID_24_0_EBX_AVX10_512 (1U << 18) +/* AVX10 vector length support mask */ +#define CPUID_24_0_EBX_AVX10_VL_MASK (CPUID_24_0_EBX_AVX10_128 | \ + CPUID_24_0_EBX_AVX10_256 | \ + CPUID_24_0_EBX_AVX10_512) + /* CLZERO instruction */ #define CPUID_8000_0008_EBX_CLZERO (1U << 0) /* Always save/restore FP error pointers */ @@ -1876,6 +1890,8 @@ typedef struct CPUArchState { uint32_t cpuid_vendor3; uint32_t cpuid_version; FeatureWordArray features; + /* AVX10 version */ + uint8_t avx10_version; /* Features that were explicitly enabled/disabled */ FeatureWordArray user_features; uint32_t cpuid_model[12]; diff --git a/target/i386/kvm/kvm-cpu.c b/target/i386/kvm/kvm-cpu.c index a3bc8d8f832c1358270846b473769d872a14463b..5df8a013135de1c238889f441d29e5e689ffef6e 100644 --- a/target/i386/kvm/kvm-cpu.c +++ b/target/i386/kvm/kvm-cpu.c @@ -137,10 +137,6 @@ static void kvm_cpu_xsave_init(void) if (!esa->size) { continue; } - if ((x86_cpu_get_supported_feature_word(NULL, esa->feature) & esa->bits) - != esa->bits) { - continue; - } host_cpuid(0xd, i, &eax, &ebx, &ecx, &edx); if (eax != 0) { assert(esa->size == eax); diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c index 59b004142795843d9150b3bf090f68af027583a9..3e2d4aaa26b8690a161037bc5385d2513a1297ca 100644 --- a/target/i386/kvm/kvm.c +++ b/target/i386/kvm/kvm.c @@ -1796,7 +1796,8 @@ static uint32_t kvm_x86_build_cpuid(CPUX86State *env, case 0x7: case 0x14: case 0x1d: - case 0x1e: { + case 0x1e: + case 0x24: { uint32_t times; c->function = i;