diff options
Diffstat (limited to 'arch/x86/kvm')
37 files changed, 1714 insertions, 921 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index ae0b438a2c99..8eb3a88707f2 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -82,15 +82,6 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } -#define F feature_bit - -/* Scattered Flag - For features that are scattered by cpufeatures.h. */ -#define SF(name) \ -({ \ - BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ - (boot_cpu_has(X86_FEATURE_##name) ? F(name) : 0); \ -}) - /* * Magic value used by KVM when querying userspace-provided CPUID entries and * doesn't care about the CPIUD index because the index of the function in @@ -100,8 +91,8 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) */ #define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull -static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( - struct kvm_cpuid_entry2 *entries, int nent, u32 function, u64 index) +static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu, + u32 function, u64 index) { struct kvm_cpuid_entry2 *e; int i; @@ -118,8 +109,8 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( */ lockdep_assert_irqs_enabled(); - for (i = 0; i < nent; i++) { - e = &entries[i]; + for (i = 0; i < vcpu->arch.cpuid_nent; i++) { + e = &vcpu->arch.cpuid_entries[i]; if (e->function != function) continue; @@ -151,9 +142,27 @@ static inline struct kvm_cpuid_entry2 *cpuid_entry2_find( return NULL; } -static int kvm_check_cpuid(struct kvm_vcpu *vcpu, - struct kvm_cpuid_entry2 *entries, - int nent) +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, + u32 function, u32 index) +{ + return cpuid_entry2_find(vcpu, function, index); +} +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index); + +struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, + u32 function) +{ + return cpuid_entry2_find(vcpu, function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); +} +EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); + +/* + * cpuid_entry2_find() and KVM_CPUID_INDEX_NOT_SIGNIFICANT should never be used + * directly outside of kvm_find_cpuid_entry() and kvm_find_cpuid_entry_index(). + */ +#undef KVM_CPUID_INDEX_NOT_SIGNIFICANT + +static int kvm_check_cpuid(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; u64 xfeatures; @@ -162,8 +171,7 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu, * The existing code assumes virtual address is 48-bit or 57-bit in the * canonical address checks; exit if it is ever changed. */ - best = cpuid_entry2_find(entries, nent, 0x80000008, - KVM_CPUID_INDEX_NOT_SIGNIFICANT); + best = kvm_find_cpuid_entry(vcpu, 0x80000008); if (best) { int vaddr_bits = (best->eax & 0xff00) >> 8; @@ -175,7 +183,7 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu, * Exposing dynamic xfeatures to the guest requires additional * enabling in the FPU, e.g. to expand the guest XSAVE state size. */ - best = cpuid_entry2_find(entries, nent, 0xd, 0); + best = kvm_find_cpuid_entry_index(vcpu, 0xd, 0); if (!best) return 0; @@ -187,6 +195,8 @@ static int kvm_check_cpuid(struct kvm_vcpu *vcpu, return fpu_enable_guest_xfd_features(&vcpu->arch.guest_fpu, xfeatures); } +static u32 kvm_apply_cpuid_pv_features_quirk(struct kvm_vcpu *vcpu); + /* Check whether the supplied CPUID data is equal to what is already set for the vCPU. */ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) @@ -194,6 +204,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 struct kvm_cpuid_entry2 *orig; int i; + /* + * Apply runtime CPUID updates to the incoming CPUID entries to avoid + * false positives due mismatches on KVM-owned feature flags. + * + * Note! @e2 and @nent track the _old_ CPUID entries! + */ + kvm_update_cpuid_runtime(vcpu); + kvm_apply_cpuid_pv_features_quirk(vcpu); + if (nent != vcpu->arch.cpuid_nent) return -EINVAL; @@ -210,15 +229,15 @@ static int kvm_cpuid_check_equal(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 return 0; } -static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_entry2 *entries, - int nent, const char *sig) +static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, + const char *sig) { struct kvm_hypervisor_cpuid cpuid = {}; struct kvm_cpuid_entry2 *entry; u32 base; for_each_possible_hypervisor_cpuid_base(base) { - entry = cpuid_entry2_find(entries, nent, base, KVM_CPUID_INDEX_NOT_SIGNIFICANT); + entry = kvm_find_cpuid_entry(vcpu, base); if (entry) { u32 signature[3]; @@ -238,118 +257,90 @@ static struct kvm_hypervisor_cpuid __kvm_get_hypervisor_cpuid(struct kvm_cpuid_e return cpuid; } -static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcpu, - const char *sig) +static u32 kvm_apply_cpuid_pv_features_quirk(struct kvm_vcpu *vcpu) { - return __kvm_get_hypervisor_cpuid(vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent, sig); -} - -static struct kvm_cpuid_entry2 *__kvm_find_kvm_cpuid_features(struct kvm_cpuid_entry2 *entries, - int nent, u32 kvm_cpuid_base) -{ - return cpuid_entry2_find(entries, nent, kvm_cpuid_base | KVM_CPUID_FEATURES, - KVM_CPUID_INDEX_NOT_SIGNIFICANT); -} - -static struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu) -{ - u32 base = vcpu->arch.kvm_cpuid.base; + struct kvm_hypervisor_cpuid kvm_cpuid; + struct kvm_cpuid_entry2 *best; - if (!base) - return NULL; + kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); + if (!kvm_cpuid.base) + return 0; - return __kvm_find_kvm_cpuid_features(vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent, base); -} + best = kvm_find_cpuid_entry(vcpu, kvm_cpuid.base | KVM_CPUID_FEATURES); + if (!best) + return 0; -void kvm_update_pv_runtime(struct kvm_vcpu *vcpu) -{ - struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu); + if (kvm_hlt_in_guest(vcpu->kvm)) + best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - /* - * save the feature bitmap to avoid cpuid lookup for every PV - * operation - */ - if (best) - vcpu->arch.pv_cpuid.features = best->eax; + return best->eax; } /* * Calculate guest's supported XCR0 taking into account guest CPUID data and * KVM's supported XCR0 (comprised of host's XCR0 and KVM_SUPPORTED_XCR0). */ -static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent) +static u64 cpuid_get_supported_xcr0(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - best = cpuid_entry2_find(entries, nent, 0xd, 0); + best = kvm_find_cpuid_entry_index(vcpu, 0xd, 0); if (!best) return 0; return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0; } -static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries, - int nent) +static __always_inline void kvm_update_feature_runtime(struct kvm_vcpu *vcpu, + struct kvm_cpuid_entry2 *entry, + unsigned int x86_feature, + bool has_feature) +{ + cpuid_entry_change(entry, x86_feature, has_feature); + guest_cpu_cap_change(vcpu, x86_feature, has_feature); +} + +void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; - struct kvm_hypervisor_cpuid kvm_cpuid; - best = cpuid_entry2_find(entries, nent, 1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); + best = kvm_find_cpuid_entry(vcpu, 1); if (best) { - /* Update OSXSAVE bit */ - if (boot_cpu_has(X86_FEATURE_XSAVE)) - cpuid_entry_change(best, X86_FEATURE_OSXSAVE, + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_OSXSAVE, kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)); - cpuid_entry_change(best, X86_FEATURE_APIC, - vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_APIC, + vcpu->arch.apic_base & MSR_IA32_APICBASE_ENABLE); + + if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_MWAIT, + vcpu->arch.ia32_misc_enable_msr & + MSR_IA32_MISC_ENABLE_MWAIT); } - best = cpuid_entry2_find(entries, nent, 7, 0); - if (best && boot_cpu_has(X86_FEATURE_PKU) && best->function == 0x7) - cpuid_entry_change(best, X86_FEATURE_OSPKE, - kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); + best = kvm_find_cpuid_entry_index(vcpu, 7, 0); + if (best) + kvm_update_feature_runtime(vcpu, best, X86_FEATURE_OSPKE, + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); + - best = cpuid_entry2_find(entries, nent, 0xD, 0); + best = kvm_find_cpuid_entry_index(vcpu, 0xD, 0); if (best) best->ebx = xstate_required_size(vcpu->arch.xcr0, false); - best = cpuid_entry2_find(entries, nent, 0xD, 1); + best = kvm_find_cpuid_entry_index(vcpu, 0xD, 1); if (best && (cpuid_entry_has(best, X86_FEATURE_XSAVES) || cpuid_entry_has(best, X86_FEATURE_XSAVEC))) best->ebx = xstate_required_size(vcpu->arch.xcr0, true); - - kvm_cpuid = __kvm_get_hypervisor_cpuid(entries, nent, KVM_SIGNATURE); - if (kvm_cpuid.base) { - best = __kvm_find_kvm_cpuid_features(entries, nent, kvm_cpuid.base); - if (kvm_hlt_in_guest(vcpu->kvm) && best) - best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT); - } - - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) { - best = cpuid_entry2_find(entries, nent, 0x1, KVM_CPUID_INDEX_NOT_SIGNIFICANT); - if (best) - cpuid_entry_change(best, X86_FEATURE_MWAIT, - vcpu->arch.ia32_misc_enable_msr & - MSR_IA32_MISC_ENABLE_MWAIT); - } -} - -void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu) -{ - __kvm_update_cpuid_runtime(vcpu, vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); } EXPORT_SYMBOL_GPL(kvm_update_cpuid_runtime); -static bool kvm_cpuid_has_hyperv(struct kvm_cpuid_entry2 *entries, int nent) +static bool kvm_cpuid_has_hyperv(struct kvm_vcpu *vcpu) { #ifdef CONFIG_KVM_HYPERV struct kvm_cpuid_entry2 *entry; - entry = cpuid_entry2_find(entries, nent, HYPERV_CPUID_INTERFACE, - KVM_CPUID_INDEX_NOT_SIGNIFICANT); + entry = kvm_find_cpuid_entry(vcpu, HYPERV_CPUID_INTERFACE); return entry && entry->eax == HYPERV_CPUID_SIGNATURE_EAX; #else return false; @@ -368,15 +359,71 @@ static bool guest_cpuid_is_amd_or_hygon(struct kvm_vcpu *vcpu) is_guest_vendor_hygon(entry->ebx, entry->ecx, entry->edx); } -static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) +/* + * This isn't truly "unsafe", but except for the cpu_caps initialization code, + * all register lookups should use __cpuid_entry_get_reg(), which provides + * compile-time validation of the input. + */ +static u32 cpuid_get_reg_unsafe(struct kvm_cpuid_entry2 *entry, u32 reg) +{ + switch (reg) { + case CPUID_EAX: + return entry->eax; + case CPUID_EBX: + return entry->ebx; + case CPUID_ECX: + return entry->ecx; + case CPUID_EDX: + return entry->edx; + default: + WARN_ON_ONCE(1); + return 0; + } +} + +static int cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, u32 func, + bool include_partially_emulated); + +void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) { struct kvm_lapic *apic = vcpu->arch.apic; struct kvm_cpuid_entry2 *best; + struct kvm_cpuid_entry2 *entry; bool allow_gbpages; + int i; + + memset(vcpu->arch.cpu_caps, 0, sizeof(vcpu->arch.cpu_caps)); + BUILD_BUG_ON(ARRAY_SIZE(reverse_cpuid) != NR_KVM_CPU_CAPS); - BUILD_BUG_ON(KVM_NR_GOVERNED_FEATURES > KVM_MAX_NR_GOVERNED_FEATURES); - bitmap_zero(vcpu->arch.governed_features.enabled, - KVM_MAX_NR_GOVERNED_FEATURES); + /* + * Reset guest capabilities to userspace's guest CPUID definition, i.e. + * honor userspace's definition for features that don't require KVM or + * hardware management/support (or that KVM simply doesn't care about). + */ + for (i = 0; i < NR_KVM_CPU_CAPS; i++) { + const struct cpuid_reg cpuid = reverse_cpuid[i]; + struct kvm_cpuid_entry2 emulated; + + if (!cpuid.function) + continue; + + entry = kvm_find_cpuid_entry_index(vcpu, cpuid.function, cpuid.index); + if (!entry) + continue; + + cpuid_func_emulated(&emulated, cpuid.function, true); + + /* + * A vCPU has a feature if it's supported by KVM and is enabled + * in guest CPUID. Note, this includes features that are + * supported by KVM but aren't advertised to userspace! + */ + vcpu->arch.cpu_caps[i] = kvm_cpu_caps[i] | + cpuid_get_reg_unsafe(&emulated, cpuid.reg); + vcpu->arch.cpu_caps[i] &= cpuid_get_reg_unsafe(entry, cpuid.reg); + } + + kvm_update_cpuid_runtime(vcpu); /* * If TDP is enabled, let the guest use GBPAGES if they're supported in @@ -390,9 +437,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * and can install smaller shadow pages if the host lacks 1GiB support. */ allow_gbpages = tdp_enabled ? boot_cpu_has(X86_FEATURE_GBPAGES) : - guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES); - if (allow_gbpages) - kvm_governed_feature_set(vcpu, X86_FEATURE_GBPAGES); + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES); + guest_cpu_cap_change(vcpu, X86_FEATURE_GBPAGES, allow_gbpages); best = kvm_find_cpuid_entry(vcpu, 1); if (best && apic) { @@ -404,21 +450,22 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_apic_set_version(vcpu); } - vcpu->arch.guest_supported_xcr0 = - cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent); + vcpu->arch.guest_supported_xcr0 = cpuid_get_supported_xcr0(vcpu); - kvm_update_pv_runtime(vcpu); + vcpu->arch.pv_cpuid.features = kvm_apply_cpuid_pv_features_quirk(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); kvm_pmu_refresh(vcpu); - vcpu->arch.cr4_guest_rsvd_bits = - __cr4_reserved_bits(guest_cpuid_has, vcpu); - kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu->arch.cpuid_entries, - vcpu->arch.cpuid_nent)); +#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) + vcpu->arch.cr4_guest_rsvd_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_) | + __cr4_reserved_bits(guest_cpu_cap_has, vcpu); +#undef __kvm_cpu_cap_has + + kvm_hv_set_cpuid(vcpu, kvm_cpuid_has_hyperv(vcpu)); /* Invoke the vendor callback only after the above state is updated. */ kvm_x86_call(vcpu_after_set_cpuid)(vcpu); @@ -457,9 +504,25 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu) static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, int nent) { + u32 vcpu_caps[NR_KVM_CPU_CAPS]; int r; - __kvm_update_cpuid_runtime(vcpu, e2, nent); + /* + * Swap the existing (old) entries with the incoming (new) entries in + * order to massage the new entries, e.g. to account for dynamic bits + * that KVM controls, without clobbering the current guest CPUID, which + * KVM needs to preserve in order to unwind on failure. + * + * Similarly, save the vCPU's current cpu_caps so that the capabilities + * can be updated alongside the CPUID entries when performing runtime + * updates. Full initialization is done if and only if the vCPU hasn't + * run, i.e. only if userspace is potentially changing CPUID features. + */ + swap(vcpu->arch.cpuid_entries, e2); + swap(vcpu->arch.cpuid_nent, nent); + + memcpy(vcpu_caps, vcpu->arch.cpu_caps, sizeof(vcpu_caps)); + BUILD_BUG_ON(sizeof(vcpu_caps) != sizeof(vcpu->arch.cpu_caps)); /* * KVM does not correctly handle changing guest CPUID after KVM_RUN, as @@ -475,35 +538,36 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, if (kvm_vcpu_has_run(vcpu)) { r = kvm_cpuid_check_equal(vcpu, e2, nent); if (r) - return r; - - kvfree(e2); - return 0; + goto err; + goto success; } #ifdef CONFIG_KVM_HYPERV - if (kvm_cpuid_has_hyperv(e2, nent)) { + if (kvm_cpuid_has_hyperv(vcpu)) { r = kvm_hv_vcpu_init(vcpu); if (r) - return r; + goto err; } #endif - r = kvm_check_cpuid(vcpu, e2, nent); + r = kvm_check_cpuid(vcpu); if (r) - return r; - - kvfree(vcpu->arch.cpuid_entries); - vcpu->arch.cpuid_entries = e2; - vcpu->arch.cpuid_nent = nent; + goto err; - vcpu->arch.kvm_cpuid = kvm_get_hypervisor_cpuid(vcpu, KVM_SIGNATURE); #ifdef CONFIG_KVM_XEN vcpu->arch.xen.cpuid = kvm_get_hypervisor_cpuid(vcpu, XEN_SIGNATURE); #endif kvm_vcpu_after_set_cpuid(vcpu); +success: + kvfree(e2); return 0; + +err: + memcpy(vcpu->arch.cpu_caps, vcpu_caps, sizeof(vcpu_caps)); + swap(vcpu->arch.cpuid_entries, e2); + swap(vcpu->arch.cpuid_nent, nent); + return r; } /* when an old userspace process fills a new kernel module */ @@ -590,107 +654,294 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu, return 0; } -/* Mask kvm_cpu_caps for @leaf with the raw CPUID capabilities of this CPU. */ -static __always_inline void __kvm_cpu_cap_mask(unsigned int leaf) +static __always_inline u32 raw_cpuid_get(struct cpuid_reg cpuid) { - const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); struct kvm_cpuid_entry2 entry; + u32 base; - reverse_cpuid_check(leaf); + /* + * KVM only supports features defined by Intel (0x0), AMD (0x80000000), + * and Centaur (0xc0000000). WARN if a feature for new vendor base is + * defined, as this and other code would need to be updated. + */ + base = cpuid.function & 0xffff0000; + if (WARN_ON_ONCE(base && base != 0x80000000 && base != 0xc0000000)) + return 0; + + if (cpuid_eax(base) < cpuid.function) + return 0; cpuid_count(cpuid.function, cpuid.index, &entry.eax, &entry.ebx, &entry.ecx, &entry.edx); - kvm_cpu_caps[leaf] &= *__cpuid_entry_get_reg(&entry, cpuid.reg); + return *__cpuid_entry_get_reg(&entry, cpuid.reg); } -static __always_inline -void kvm_cpu_cap_init_kvm_defined(enum kvm_only_cpuid_leafs leaf, u32 mask) -{ - /* Use kvm_cpu_cap_mask for leafs that aren't KVM-only. */ - BUILD_BUG_ON(leaf < NCAPINTS); +/* + * For kernel-defined leafs, mask KVM's supported feature set with the kernel's + * capabilities as well as raw CPUID. For KVM-defined leafs, consult only raw + * CPUID, as KVM is the one and only authority (in the kernel). + */ +#define kvm_cpu_cap_init(leaf, feature_initializers...) \ +do { \ + const struct cpuid_reg cpuid = x86_feature_cpuid(leaf * 32); \ + const u32 __maybe_unused kvm_cpu_cap_init_in_progress = leaf; \ + const u32 *kernel_cpu_caps = boot_cpu_data.x86_capability; \ + u32 kvm_cpu_cap_passthrough = 0; \ + u32 kvm_cpu_cap_synthesized = 0; \ + u32 kvm_cpu_cap_emulated = 0; \ + u32 kvm_cpu_cap_features = 0; \ + \ + feature_initializers \ + \ + kvm_cpu_caps[leaf] = kvm_cpu_cap_features; \ + \ + if (leaf < NCAPINTS) \ + kvm_cpu_caps[leaf] &= kernel_cpu_caps[leaf]; \ + \ + kvm_cpu_caps[leaf] |= kvm_cpu_cap_passthrough; \ + kvm_cpu_caps[leaf] &= (raw_cpuid_get(cpuid) | \ + kvm_cpu_cap_synthesized); \ + kvm_cpu_caps[leaf] |= kvm_cpu_cap_emulated; \ +} while (0) - kvm_cpu_caps[leaf] = mask; +/* + * Assert that the feature bit being declared, e.g. via F(), is in the CPUID + * word that's being initialized. Exempt 0x8000_0001.EDX usage of 0x1.EDX + * features, as AMD duplicated many 0x1.EDX features into 0x8000_0001.EDX. + */ +#define KVM_VALIDATE_CPU_CAP_USAGE(name) \ +do { \ + u32 __leaf = __feature_leaf(X86_FEATURE_##name); \ + \ + BUILD_BUG_ON(__leaf != kvm_cpu_cap_init_in_progress); \ +} while (0) + +#define F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ + kvm_cpu_cap_features |= feature_bit(name); \ +}) - __kvm_cpu_cap_mask(leaf); -} +/* Scattered Flag - For features that are scattered by cpufeatures.h. */ +#define SCATTERED_F(name) \ +({ \ + BUILD_BUG_ON(X86_FEATURE_##name >= MAX_CPU_FEATURES); \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ + if (boot_cpu_has(X86_FEATURE_##name)) \ + F(name); \ +}) -static __always_inline void kvm_cpu_cap_mask(enum cpuid_leafs leaf, u32 mask) -{ - /* Use kvm_cpu_cap_init_kvm_defined for KVM-only leafs. */ - BUILD_BUG_ON(leaf >= NCAPINTS); +/* Features that KVM supports only on 64-bit kernels. */ +#define X86_64_F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ + if (IS_ENABLED(CONFIG_X86_64)) \ + F(name); \ +}) - kvm_cpu_caps[leaf] &= mask; +/* + * Emulated Feature - For features that KVM emulates in software irrespective + * of host CPU/kernel support. + */ +#define EMULATED_F(name) \ +({ \ + kvm_cpu_cap_emulated |= feature_bit(name); \ + F(name); \ +}) - __kvm_cpu_cap_mask(leaf); -} +/* + * Synthesized Feature - For features that are synthesized into boot_cpu_data, + * i.e. may not be present in the raw CPUID, but can still be advertised to + * userspace. Primarily used for mitigation related feature flags. + */ +#define SYNTHESIZED_F(name) \ +({ \ + kvm_cpu_cap_synthesized |= feature_bit(name); \ + F(name); \ +}) + +/* + * Passthrough Feature - For features that KVM supports based purely on raw + * hardware CPUID, i.e. that KVM virtualizes even if the host kernel doesn't + * use the feature. Simply force set the feature in KVM's capabilities, raw + * CPUID support will be factored in by kvm_cpu_cap_mask(). + */ +#define PASSTHROUGH_F(name) \ +({ \ + kvm_cpu_cap_passthrough |= feature_bit(name); \ + F(name); \ +}) + +/* + * Aliased Features - For features in 0x8000_0001.EDX that are duplicates of + * identical 0x1.EDX features, and thus are aliased from 0x1 to 0x8000_0001. + */ +#define ALIASED_1_EDX_F(name) \ +({ \ + BUILD_BUG_ON(__feature_leaf(X86_FEATURE_##name) != CPUID_1_EDX); \ + BUILD_BUG_ON(kvm_cpu_cap_init_in_progress != CPUID_8000_0001_EDX); \ + kvm_cpu_cap_features |= feature_bit(name); \ +}) + +/* + * Vendor Features - For features that KVM supports, but are added in later + * because they require additional vendor enabling. + */ +#define VENDOR_F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ +}) + +/* + * Runtime Features - For features that KVM dynamically sets/clears at runtime, + * e.g. when CR4 changes, but which are never advertised to userspace. + */ +#define RUNTIME_F(name) \ +({ \ + KVM_VALIDATE_CPU_CAP_USAGE(name); \ +}) + +/* + * Undefine the MSR bit macro to avoid token concatenation issues when + * processing X86_FEATURE_SPEC_CTRL_SSBD. + */ +#undef SPEC_CTRL_SSBD + +/* DS is defined by ptrace-abi.h on 32-bit builds. */ +#undef DS void kvm_set_cpu_caps(void) { -#ifdef CONFIG_X86_64 - unsigned int f_gbpages = F(GBPAGES); - unsigned int f_lm = F(LM); - unsigned int f_xfd = F(XFD); -#else - unsigned int f_gbpages = 0; - unsigned int f_lm = 0; - unsigned int f_xfd = 0; -#endif memset(kvm_cpu_caps, 0, sizeof(kvm_cpu_caps)); BUILD_BUG_ON(sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps)) > sizeof(boot_cpu_data.x86_capability)); - memcpy(&kvm_cpu_caps, &boot_cpu_data.x86_capability, - sizeof(kvm_cpu_caps) - (NKVMCAPINTS * sizeof(*kvm_cpu_caps))); - - kvm_cpu_cap_mask(CPUID_1_ECX, + kvm_cpu_cap_init(CPUID_1_ECX, + F(XMM3), + F(PCLMULQDQ), + VENDOR_F(DTES64), /* * NOTE: MONITOR (and MWAIT) are emulated as NOP, but *not* - * advertised to guests via CPUID! + * advertised to guests via CPUID! MWAIT is also technically a + * runtime flag thanks to IA32_MISC_ENABLES; mark it as such so + * that KVM is aware that it's a known, unadvertised flag. */ - F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | - 0 /* DS-CPL, VMX, SMX, EST */ | - 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | - F(FMA) | F(CX16) | 0 /* xTPR Update */ | F(PDCM) | - F(PCID) | 0 /* Reserved, DCA */ | F(XMM4_1) | - F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) | - 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) | - F(F16C) | F(RDRAND) + RUNTIME_F(MWAIT), + /* DS-CPL */ + VENDOR_F(VMX), + /* SMX, EST */ + /* TM2 */ + F(SSSE3), + /* CNXT-ID */ + /* Reserved */ + F(FMA), + F(CX16), + /* xTPR Update */ + F(PDCM), + F(PCID), + /* Reserved, DCA */ + F(XMM4_1), + F(XMM4_2), + EMULATED_F(X2APIC), + F(MOVBE), + F(POPCNT), + EMULATED_F(TSC_DEADLINE_TIMER), + F(AES), + F(XSAVE), + RUNTIME_F(OSXSAVE), + F(AVX), + F(F16C), + F(RDRAND), + EMULATED_F(HYPERVISOR), ); - /* KVM emulates x2apic in software irrespective of host support. */ - kvm_cpu_cap_set(X86_FEATURE_X2APIC); - - kvm_cpu_cap_mask(CPUID_1_EDX, - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) | - 0 /* Reserved, DS, ACPI */ | F(MMX) | - F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) | - 0 /* HTT, TM, Reserved, PBE */ + + kvm_cpu_cap_init(CPUID_1_EDX, + F(FPU), + F(VME), + F(DE), + F(PSE), + F(TSC), + F(MSR), + F(PAE), + F(MCE), + F(CX8), + F(APIC), + /* Reserved */ + F(SEP), + F(MTRR), + F(PGE), + F(MCA), + F(CMOV), + F(PAT), + F(PSE36), + /* PSN */ + F(CLFLUSH), + /* Reserved */ + VENDOR_F(DS), + /* ACPI */ + F(MMX), + F(FXSR), + F(XMM), + F(XMM2), + F(SELFSNOOP), + /* HTT, TM, Reserved, PBE */ ); - kvm_cpu_cap_mask(CPUID_7_0_EBX, - F(FSGSBASE) | F(SGX) | F(BMI1) | F(HLE) | F(AVX2) | - F(FDP_EXCPTN_ONLY) | F(SMEP) | F(BMI2) | F(ERMS) | F(INVPCID) | - F(RTM) | F(ZERO_FCS_FDS) | 0 /*MPX*/ | F(AVX512F) | - F(AVX512DQ) | F(RDSEED) | F(ADX) | F(SMAP) | F(AVX512IFMA) | - F(CLFLUSHOPT) | F(CLWB) | 0 /*INTEL_PT*/ | F(AVX512PF) | - F(AVX512ER) | F(AVX512CD) | F(SHA_NI) | F(AVX512BW) | - F(AVX512VL)); - - kvm_cpu_cap_mask(CPUID_7_ECX, - F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) | - F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) | - F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) | - F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/ | - F(SGX_LC) | F(BUS_LOCK_DETECT) + kvm_cpu_cap_init(CPUID_7_0_EBX, + F(FSGSBASE), + EMULATED_F(TSC_ADJUST), + F(SGX), + F(BMI1), + F(HLE), + F(AVX2), + F(FDP_EXCPTN_ONLY), + F(SMEP), + F(BMI2), + F(ERMS), + F(INVPCID), + F(RTM), + F(ZERO_FCS_FDS), + VENDOR_F(MPX), + F(AVX512F), + F(AVX512DQ), + F(RDSEED), + F(ADX), + F(SMAP), + F(AVX512IFMA), + F(CLFLUSHOPT), + F(CLWB), + VENDOR_F(INTEL_PT), + F(AVX512PF), + F(AVX512ER), + F(AVX512CD), + F(SHA_NI), + F(AVX512BW), + F(AVX512VL), + ); + + kvm_cpu_cap_init(CPUID_7_ECX, + F(AVX512VBMI), + PASSTHROUGH_F(LA57), + F(PKU), + RUNTIME_F(OSPKE), + F(RDPID), + F(AVX512_VPOPCNTDQ), + F(UMIP), + F(AVX512_VBMI2), + F(GFNI), + F(VAES), + F(VPCLMULQDQ), + F(AVX512_VNNI), + F(AVX512_BITALG), + F(CLDEMOTE), + F(MOVDIRI), + F(MOVDIR64B), + VENDOR_F(WAITPKG), + F(SGX_LC), + F(BUS_LOCK_DETECT), ); - /* Set LA57 based on hardware capability. */ - if (cpuid_ecx(7) & F(LA57)) - kvm_cpu_cap_set(X86_FEATURE_LA57); /* * PKU not yet implemented for shadow paging and requires OSPKE @@ -699,18 +950,25 @@ void kvm_set_cpu_caps(void) if (!tdp_enabled || !boot_cpu_has(X86_FEATURE_OSPKE)) kvm_cpu_cap_clear(X86_FEATURE_PKU); - kvm_cpu_cap_mask(CPUID_7_EDX, - F(AVX512_4VNNIW) | F(AVX512_4FMAPS) | F(SPEC_CTRL) | - F(SPEC_CTRL_SSBD) | F(ARCH_CAPABILITIES) | F(INTEL_STIBP) | - F(MD_CLEAR) | F(AVX512_VP2INTERSECT) | F(FSRM) | - F(SERIALIZE) | F(TSXLDTRK) | F(AVX512_FP16) | - F(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) | F(FLUSH_L1D) + kvm_cpu_cap_init(CPUID_7_EDX, + F(AVX512_4VNNIW), + F(AVX512_4FMAPS), + F(SPEC_CTRL), + F(SPEC_CTRL_SSBD), + EMULATED_F(ARCH_CAPABILITIES), + F(INTEL_STIBP), + F(MD_CLEAR), + F(AVX512_VP2INTERSECT), + F(FSRM), + F(SERIALIZE), + F(TSXLDTRK), + F(AVX512_FP16), + F(AMX_TILE), + F(AMX_INT8), + F(AMX_BF16), + F(FLUSH_L1D), ); - /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ - kvm_cpu_cap_set(X86_FEATURE_TSC_ADJUST); - kvm_cpu_cap_set(X86_FEATURE_ARCH_CAPABILITIES); - if (boot_cpu_has(X86_FEATURE_AMD_IBPB_RET) && boot_cpu_has(X86_FEATURE_AMD_IBPB) && boot_cpu_has(X86_FEATURE_AMD_IBRS)) @@ -720,65 +978,133 @@ void kvm_set_cpu_caps(void) if (boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); - kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(SHA512) | F(SM3) | F(SM4) | F(AVX_VNNI) | F(AVX512_BF16) | - F(CMPCCXADD) | F(FZRM) | F(FSRS) | F(FSRC) | F(AMX_FP16) | - F(AVX_IFMA) | F(LAM) + kvm_cpu_cap_init(CPUID_7_1_EAX, + F(SHA512), + F(SM3), + F(SM4), + F(AVX_VNNI), + F(AVX512_BF16), + F(CMPCCXADD), + F(FZRM), + F(FSRS), + F(FSRC), + F(AMX_FP16), + F(AVX_IFMA), + F(LAM), ); - kvm_cpu_cap_init_kvm_defined(CPUID_7_1_EDX, - F(AVX_VNNI_INT8) | F(AVX_NE_CONVERT) | F(AMX_COMPLEX) | - F(AVX_VNNI_INT16) | F(PREFETCHITI) | F(AVX10) + kvm_cpu_cap_init(CPUID_7_1_EDX, + F(AVX_VNNI_INT8), + F(AVX_NE_CONVERT), + F(AMX_COMPLEX), + F(AVX_VNNI_INT16), + F(PREFETCHITI), + F(AVX10), ); - kvm_cpu_cap_init_kvm_defined(CPUID_7_2_EDX, - F(INTEL_PSFD) | F(IPRED_CTRL) | F(RRSBA_CTRL) | F(DDPD_U) | - F(BHI_CTRL) | F(MCDT_NO) + kvm_cpu_cap_init(CPUID_7_2_EDX, + F(INTEL_PSFD), + F(IPRED_CTRL), + F(RRSBA_CTRL), + F(DDPD_U), + F(BHI_CTRL), + F(MCDT_NO), ); - kvm_cpu_cap_mask(CPUID_D_1_EAX, - F(XSAVEOPT) | F(XSAVEC) | F(XGETBV1) | F(XSAVES) | f_xfd + kvm_cpu_cap_init(CPUID_D_1_EAX, + F(XSAVEOPT), + F(XSAVEC), + F(XGETBV1), + F(XSAVES), + X86_64_F(XFD), ); - kvm_cpu_cap_init_kvm_defined(CPUID_12_EAX, - SF(SGX1) | SF(SGX2) | SF(SGX_EDECCSSA) + kvm_cpu_cap_init(CPUID_12_EAX, + SCATTERED_F(SGX1), + SCATTERED_F(SGX2), + SCATTERED_F(SGX_EDECCSSA), ); - kvm_cpu_cap_init_kvm_defined(CPUID_24_0_EBX, - F(AVX10_128) | F(AVX10_256) | F(AVX10_512) + kvm_cpu_cap_init(CPUID_24_0_EBX, + F(AVX10_128), + F(AVX10_256), + F(AVX10_512), ); - kvm_cpu_cap_mask(CPUID_8000_0001_ECX, - F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ | - F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) | - F(3DNOWPREFETCH) | F(OSVW) | 0 /* IBS */ | F(XOP) | - 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM) | - F(TOPOEXT) | 0 /* PERFCTR_CORE */ + kvm_cpu_cap_init(CPUID_8000_0001_ECX, + F(LAHF_LM), + F(CMP_LEGACY), + VENDOR_F(SVM), + /* ExtApicSpace */ + F(CR8_LEGACY), + F(ABM), + F(SSE4A), + F(MISALIGNSSE), + F(3DNOWPREFETCH), + F(OSVW), + /* IBS */ + F(XOP), + /* SKINIT, WDT, LWP */ + F(FMA4), + F(TBM), + F(TOPOEXT), + VENDOR_F(PERFCTR_CORE), ); - kvm_cpu_cap_mask(CPUID_8000_0001_EDX, - F(FPU) | F(VME) | F(DE) | F(PSE) | - F(TSC) | F(MSR) | F(PAE) | F(MCE) | - F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) | - F(MTRR) | F(PGE) | F(MCA) | F(CMOV) | - F(PAT) | F(PSE36) | 0 /* Reserved */ | - F(NX) | 0 /* Reserved */ | F(MMXEXT) | F(MMX) | - F(FXSR) | F(FXSR_OPT) | f_gbpages | F(RDTSCP) | - 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW) + kvm_cpu_cap_init(CPUID_8000_0001_EDX, + ALIASED_1_EDX_F(FPU), + ALIASED_1_EDX_F(VME), + ALIASED_1_EDX_F(DE), + ALIASED_1_EDX_F(PSE), + ALIASED_1_EDX_F(TSC), + ALIASED_1_EDX_F(MSR), + ALIASED_1_EDX_F(PAE), + ALIASED_1_EDX_F(MCE), + ALIASED_1_EDX_F(CX8), + ALIASED_1_EDX_F(APIC), + /* Reserved */ + F(SYSCALL), + ALIASED_1_EDX_F(MTRR), + ALIASED_1_EDX_F(PGE), + ALIASED_1_EDX_F(MCA), + ALIASED_1_EDX_F(CMOV), + ALIASED_1_EDX_F(PAT), + ALIASED_1_EDX_F(PSE36), + /* Reserved */ + F(NX), + /* Reserved */ + F(MMXEXT), + ALIASED_1_EDX_F(MMX), + ALIASED_1_EDX_F(FXSR), + F(FXSR_OPT), + X86_64_F(GBPAGES), + F(RDTSCP), + /* Reserved */ + X86_64_F(LM), + F(3DNOWEXT), + F(3DNOW), ); if (!tdp_enabled && IS_ENABLED(CONFIG_X86_64)) kvm_cpu_cap_set(X86_FEATURE_GBPAGES); - kvm_cpu_cap_init_kvm_defined(CPUID_8000_0007_EDX, - SF(CONSTANT_TSC) + kvm_cpu_cap_init(CPUID_8000_0007_EDX, + SCATTERED_F(CONSTANT_TSC), ); - kvm_cpu_cap_mask(CPUID_8000_0008_EBX, - F(CLZERO) | F(XSAVEERPTR) | - F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) | - F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON) | - F(AMD_PSFD) | F(AMD_IBPB_RET) + kvm_cpu_cap_init(CPUID_8000_0008_EBX, + F(CLZERO), + F(XSAVEERPTR), + F(WBNOINVD), + F(AMD_IBPB), + F(AMD_IBRS), + F(AMD_SSBD), + F(VIRT_SSBD), + F(AMD_SSB_NO), + F(AMD_STIBP), + F(AMD_STIBP_ALWAYS_ON), + F(AMD_PSFD), + F(AMD_IBPB_RET), ); /* @@ -808,50 +1134,73 @@ void kvm_set_cpu_caps(void) !boot_cpu_has(X86_FEATURE_AMD_SSBD)) kvm_cpu_cap_set(X86_FEATURE_VIRT_SSBD); - /* - * Hide all SVM features by default, SVM will set the cap bits for - * features it emulates and/or exposes for L1. - */ - kvm_cpu_cap_mask(CPUID_8000_000A_EDX, 0); - - kvm_cpu_cap_mask(CPUID_8000_001F_EAX, - 0 /* SME */ | 0 /* SEV */ | 0 /* VM_PAGE_FLUSH */ | 0 /* SEV_ES */ | - F(SME_COHERENT)); + /* All SVM features required additional vendor module enabling. */ + kvm_cpu_cap_init(CPUID_8000_000A_EDX, + VENDOR_F(NPT), + VENDOR_F(VMCBCLEAN), + VENDOR_F(FLUSHBYASID), + VENDOR_F(NRIPS), + VENDOR_F(TSCRATEMSR), + VENDOR_F(V_VMSAVE_VMLOAD), + VENDOR_F(LBRV), + VENDOR_F(PAUSEFILTER), + VENDOR_F(PFTHRESHOLD), + VENDOR_F(VGIF), + VENDOR_F(VNMI), + VENDOR_F(SVME_ADDR_CHK), + ); - kvm_cpu_cap_mask(CPUID_8000_0021_EAX, - F(NO_NESTED_DATA_BP) | F(LFENCE_RDTSC) | 0 /* SmmPgCfgLock */ | - F(NULL_SEL_CLR_BASE) | F(AUTOIBRS) | 0 /* PrefetchCtlMsr */ | - F(WRMSR_XX_BASE_NS) + kvm_cpu_cap_init(CPUID_8000_001F_EAX, + VENDOR_F(SME), + VENDOR_F(SEV), + /* VM_PAGE_FLUSH */ + VENDOR_F(SEV_ES), + F(SME_COHERENT), ); - kvm_cpu_cap_check_and_set(X86_FEATURE_SBPB); - kvm_cpu_cap_check_and_set(X86_FEATURE_IBPB_BRTYPE); - kvm_cpu_cap_check_and_set(X86_FEATURE_SRSO_NO); + kvm_cpu_cap_init(CPUID_8000_0021_EAX, + F(NO_NESTED_DATA_BP), + /* + * Synthesize "LFENCE is serializing" into the AMD-defined entry + * in KVM's supported CPUID, i.e. if the feature is reported as + * supported by the kernel. LFENCE_RDTSC was a Linux-defined + * synthetic feature long before AMD joined the bandwagon, e.g. + * LFENCE is serializing on most CPUs that support SSE2. On + * CPUs that don't support AMD's leaf, ANDing with the raw host + * CPUID will drop the flags, and reporting support in AMD's + * leaf can make it easier for userspace to detect the feature. + */ + SYNTHESIZED_F(LFENCE_RDTSC), + /* SmmPgCfgLock */ + F(NULL_SEL_CLR_BASE), + F(AUTOIBRS), + EMULATED_F(NO_SMM_CTL_MSR), + /* PrefetchCtlMsr */ + F(WRMSR_XX_BASE_NS), + SYNTHESIZED_F(SBPB), + SYNTHESIZED_F(IBPB_BRTYPE), + SYNTHESIZED_F(SRSO_NO), + F(SRSO_USER_KERNEL_NO), + ); - kvm_cpu_cap_init_kvm_defined(CPUID_8000_0022_EAX, - F(PERFMON_V2) + kvm_cpu_cap_init(CPUID_8000_0022_EAX, + F(PERFMON_V2), ); - /* - * Synthesize "LFENCE is serializing" into the AMD-defined entry in - * KVM's supported CPUID if the feature is reported as supported by the - * kernel. LFENCE_RDTSC was a Linux-defined synthetic feature long - * before AMD joined the bandwagon, e.g. LFENCE is serializing on most - * CPUs that support SSE2. On CPUs that don't support AMD's leaf, - * kvm_cpu_cap_mask() will unfortunately drop the flag due to ANDing - * the mask with the raw host CPUID, and reporting support in AMD's - * leaf can make it easier for userspace to detect the feature. - */ - if (cpu_feature_enabled(X86_FEATURE_LFENCE_RDTSC)) - kvm_cpu_cap_set(X86_FEATURE_LFENCE_RDTSC); if (!static_cpu_has_bug(X86_BUG_NULL_SEG)) kvm_cpu_cap_set(X86_FEATURE_NULL_SEL_CLR_BASE); - kvm_cpu_cap_set(X86_FEATURE_NO_SMM_CTL_MSR); - kvm_cpu_cap_mask(CPUID_C000_0001_EDX, - F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) | - F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) | - F(PMM) | F(PMM_EN) + kvm_cpu_cap_init(CPUID_C000_0001_EDX, + F(XSTORE), + F(XSTORE_EN), + F(XCRYPT), + F(XCRYPT_EN), + F(ACE2), + F(ACE2_EN), + F(PHE), + F(PHE_EN), + F(PMM), + F(PMM_EN), ); /* @@ -871,6 +1220,16 @@ void kvm_set_cpu_caps(void) } EXPORT_SYMBOL_GPL(kvm_set_cpu_caps); +#undef F +#undef SCATTERED_F +#undef X86_64_F +#undef EMULATED_F +#undef SYNTHESIZED_F +#undef PASSTHROUGH_F +#undef ALIASED_1_EDX_F +#undef VENDOR_F +#undef RUNTIME_F + struct kvm_cpuid_array { struct kvm_cpuid_entry2 *entries; int maxnent; @@ -928,14 +1287,11 @@ static struct kvm_cpuid_entry2 *do_host_cpuid(struct kvm_cpuid_array *array, return entry; } -static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) +static int cpuid_func_emulated(struct kvm_cpuid_entry2 *entry, u32 func, + bool include_partially_emulated) { - struct kvm_cpuid_entry2 *entry; - - if (array->nent >= array->maxnent) - return -E2BIG; + memset(entry, 0, sizeof(*entry)); - entry = &array->entries[array->nent]; entry->function = func; entry->index = 0; entry->flags = 0; @@ -943,23 +1299,37 @@ static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) switch (func) { case 0: entry->eax = 7; - ++array->nent; - break; + return 1; case 1: - entry->ecx = F(MOVBE); - ++array->nent; - break; + entry->ecx = feature_bit(MOVBE); + /* + * KVM allows userspace to enumerate MONITOR+MWAIT support to + * the guest, but the MWAIT feature flag is never advertised + * to userspace because MONITOR+MWAIT aren't virtualized by + * hardware, can't be faithfully emulated in software (KVM + * emulates them as NOPs), and allowing the guest to execute + * them natively requires enabling a per-VM capability. + */ + if (include_partially_emulated) + entry->ecx |= feature_bit(MWAIT); + return 1; case 7: entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX; entry->eax = 0; if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) - entry->ecx = F(RDPID); - ++array->nent; - break; + entry->ecx = feature_bit(RDPID); + return 1; default: - break; + return 0; } +} + +static int __do_cpuid_func_emulated(struct kvm_cpuid_array *array, u32 func) +{ + if (array->nent >= array->maxnent) + return -E2BIG; + array->nent += cpuid_func_emulated(&array->entries[array->nent], func, false); return 0; } @@ -1103,7 +1473,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) goto out; cpuid_entry_override(entry, CPUID_D_1_EAX); - if (entry->eax & (F(XSAVES)|F(XSAVEC))) + if (entry->eax & (feature_bit(XSAVES) | feature_bit(XSAVEC))) entry->ebx = xstate_required_size(permitted_xcr0 | permitted_xss, true); else { @@ -1540,22 +1910,6 @@ out_free: return r; } -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, - u32 function, u32 index) -{ - return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, - function, index); -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index); - -struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, - u32 function) -{ - return cpuid_entry2_find(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent, - function, KVM_CPUID_INDEX_NOT_SIGNIFICANT); -} -EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry); - /* * Intel CPUID semantics treats any query for an out-of-range leaf as if the * highest basic leaf (i.e. CPUID.0H:EAX) were requested. AMD CPUID semantics @@ -1648,10 +2002,10 @@ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx, u64 data; if (!__kvm_get_msr(vcpu, MSR_IA32_TSX_CTRL, &data, true) && (data & TSX_CTRL_CPUID_CLEAR)) - *ebx &= ~(F(RTM) | F(HLE)); + *ebx &= ~(feature_bit(RTM) | feature_bit(HLE)); } else if (function == 0x80000007) { if (kvm_hv_invtsc_suppressed(vcpu)) - *edx &= ~SF(CONSTANT_TSC); + *edx &= ~feature_bit(CONSTANT_TSC); } } else { *eax = *ebx = *ecx = *edx = 0; diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index f16a7b2c2adc..67d80aa72d50 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -10,8 +10,8 @@ extern u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly; void kvm_set_cpu_caps(void); +void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu); void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu); -void kvm_update_pv_runtime(struct kvm_vcpu *vcpu); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu, u32 function, u32 index); struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu, @@ -67,41 +67,40 @@ static __always_inline void cpuid_entry_override(struct kvm_cpuid_entry2 *entry, *reg = kvm_cpu_caps[leaf]; } -static __always_inline u32 *guest_cpuid_get_register(struct kvm_vcpu *vcpu, - unsigned int x86_feature) +static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { const struct cpuid_reg cpuid = x86_feature_cpuid(x86_feature); struct kvm_cpuid_entry2 *entry; + u32 *reg; + + /* + * XSAVES is a special snowflake. Due to lack of a dedicated intercept + * on SVM, KVM must assume that XSAVES (and thus XRSTORS) is usable by + * the guest if the host supports XSAVES and *XSAVE* is exposed to the + * guest. Because the guest can execute XSAVES and XRSTORS, i.e. can + * indirectly consume XSS, KVM must ensure XSS is zeroed when running + * the guest, i.e. must set XSAVES in vCPU capabilities. But to reject + * direct XSS reads and writes (to minimize the virtualization hole and + * honor userspace's CPUID), KVM needs to check the raw guest CPUID, + * not KVM's view of guest capabilities. + * + * For all other features, guest capabilities are accurate. Expand + * this allowlist with extreme vigilance. + */ + BUILD_BUG_ON(x86_feature != X86_FEATURE_XSAVES); entry = kvm_find_cpuid_entry_index(vcpu, cpuid.function, cpuid.index); if (!entry) return NULL; - return __cpuid_entry_get_reg(entry, cpuid.reg); -} - -static __always_inline bool guest_cpuid_has(struct kvm_vcpu *vcpu, - unsigned int x86_feature) -{ - u32 *reg; - - reg = guest_cpuid_get_register(vcpu, x86_feature); + reg = __cpuid_entry_get_reg(entry, cpuid.reg); if (!reg) return false; return *reg & __feature_bit(x86_feature); } -static __always_inline void guest_cpuid_clear(struct kvm_vcpu *vcpu, - unsigned int x86_feature) -{ - u32 *reg; - - reg = guest_cpuid_get_register(vcpu, x86_feature); - if (reg) - *reg &= ~__feature_bit(x86_feature); -} - static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) { return vcpu->arch.is_amd_compatible; @@ -150,21 +149,6 @@ static inline int guest_cpuid_stepping(struct kvm_vcpu *vcpu) return x86_stepping(best->eax); } -static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) -{ - return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_STIBP) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBRS) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_SSBD)); -} - -static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) -{ - return (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) || - guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB) || - guest_cpuid_has(vcpu, X86_FEATURE_SBPB)); -} - static inline bool supports_cpuid_fault(struct kvm_vcpu *vcpu) { return vcpu->arch.msr_platform_info & MSR_PLATFORM_INFO_CPUID_FAULT; @@ -180,7 +164,6 @@ static __always_inline void kvm_cpu_cap_clear(unsigned int x86_feature) { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); kvm_cpu_caps[x86_leaf] &= ~__feature_bit(x86_feature); } @@ -188,7 +171,6 @@ static __always_inline void kvm_cpu_cap_set(unsigned int x86_feature) { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); kvm_cpu_caps[x86_leaf] |= __feature_bit(x86_feature); } @@ -196,7 +178,6 @@ static __always_inline u32 kvm_cpu_cap_get(unsigned int x86_feature) { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); return kvm_cpu_caps[x86_leaf] & __feature_bit(x86_feature); } @@ -220,58 +201,61 @@ static __always_inline bool guest_pv_has(struct kvm_vcpu *vcpu, return vcpu->arch.pv_cpuid.features & (1u << kvm_feature); } -enum kvm_governed_features { -#define KVM_GOVERNED_FEATURE(x) KVM_GOVERNED_##x, -#include "governed_features.h" - KVM_NR_GOVERNED_FEATURES -}; - -static __always_inline int kvm_governed_feature_index(unsigned int x86_feature) +static __always_inline void guest_cpu_cap_set(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - switch (x86_feature) { -#define KVM_GOVERNED_FEATURE(x) case x: return KVM_GOVERNED_##x; -#include "governed_features.h" - default: - return -1; - } -} + unsigned int x86_leaf = __feature_leaf(x86_feature); -static __always_inline bool kvm_is_governed_feature(unsigned int x86_feature) -{ - return kvm_governed_feature_index(x86_feature) >= 0; + vcpu->arch.cpu_caps[x86_leaf] |= __feature_bit(x86_feature); } -static __always_inline void kvm_governed_feature_set(struct kvm_vcpu *vcpu, - unsigned int x86_feature) +static __always_inline void guest_cpu_cap_clear(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature)); + unsigned int x86_leaf = __feature_leaf(x86_feature); - __set_bit(kvm_governed_feature_index(x86_feature), - vcpu->arch.governed_features.enabled); + vcpu->arch.cpu_caps[x86_leaf] &= ~__feature_bit(x86_feature); } -static __always_inline void kvm_governed_feature_check_and_set(struct kvm_vcpu *vcpu, - unsigned int x86_feature) +static __always_inline void guest_cpu_cap_change(struct kvm_vcpu *vcpu, + unsigned int x86_feature, + bool guest_has_cap) { - if (kvm_cpu_cap_has(x86_feature) && guest_cpuid_has(vcpu, x86_feature)) - kvm_governed_feature_set(vcpu, x86_feature); + if (guest_has_cap) + guest_cpu_cap_set(vcpu, x86_feature); + else + guest_cpu_cap_clear(vcpu, x86_feature); } -static __always_inline bool guest_can_use(struct kvm_vcpu *vcpu, - unsigned int x86_feature) +static __always_inline bool guest_cpu_cap_has(struct kvm_vcpu *vcpu, + unsigned int x86_feature) { - BUILD_BUG_ON(!kvm_is_governed_feature(x86_feature)); + unsigned int x86_leaf = __feature_leaf(x86_feature); - return test_bit(kvm_governed_feature_index(x86_feature), - vcpu->arch.governed_features.enabled); + return vcpu->arch.cpu_caps[x86_leaf] & __feature_bit(x86_feature); } static inline bool kvm_vcpu_is_legal_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) { - if (guest_can_use(vcpu, X86_FEATURE_LAM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LAM)) cr3 &= ~(X86_CR3_LAM_U48 | X86_CR3_LAM_U57); return kvm_vcpu_is_legal_gpa(vcpu, cr3); } +static inline bool guest_has_spec_ctrl_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_STIBP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBRS) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_SSBD)); +} + +static inline bool guest_has_pred_cmd_msr(struct kvm_vcpu *vcpu) +{ + return (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) || + guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBPB) || + guest_cpu_cap_has(vcpu, X86_FEATURE_SBPB)); +} + #endif diff --git a/arch/x86/kvm/governed_features.h b/arch/x86/kvm/governed_features.h deleted file mode 100644 index ad463b1ed4e4..000000000000 --- a/arch/x86/kvm/governed_features.h +++ /dev/null @@ -1,22 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#if !defined(KVM_GOVERNED_FEATURE) || defined(KVM_GOVERNED_X86_FEATURE) -BUILD_BUG() -#endif - -#define KVM_GOVERNED_X86_FEATURE(x) KVM_GOVERNED_FEATURE(X86_FEATURE_##x) - -KVM_GOVERNED_X86_FEATURE(GBPAGES) -KVM_GOVERNED_X86_FEATURE(XSAVES) -KVM_GOVERNED_X86_FEATURE(VMX) -KVM_GOVERNED_X86_FEATURE(NRIPS) -KVM_GOVERNED_X86_FEATURE(TSCRATEMSR) -KVM_GOVERNED_X86_FEATURE(V_VMSAVE_VMLOAD) -KVM_GOVERNED_X86_FEATURE(LBRV) -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 4f0a94346d00..6a6dd5a84f22 100644 --- a/arch/x86/kvm/hyperv.c +++ b/arch/x86/kvm/hyperv.c @@ -1352,7 +1352,7 @@ static void __kvm_hv_xsaves_xsavec_maybe_warn(struct kvm_vcpu *vcpu) return; if (guest_cpuid_has(vcpu, X86_FEATURE_XSAVES) || - !guest_cpuid_has(vcpu, X86_FEATURE_XSAVEC)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVEC)) return; pr_notice_ratelimited("Booting SMP Windows KVM VM with !XSAVES && XSAVEC. " diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index cd57a517d04a..d7ab8780ab9e 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -681,7 +681,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags) pid_nr = pid_vnr(pid); put_pid(pid); - pit->worker = kthread_create_worker(0, "kvm-pit/%d", pid_nr); + pit->worker = kthread_run_worker(0, "kvm-pit/%d", pid_nr); if (IS_ERR(pit->worker)) goto fail_kthread; diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h index 10495fffb890..73072585e164 100644 --- a/arch/x86/kvm/kvm_emulate.h +++ b/arch/x86/kvm/kvm_emulate.h @@ -88,6 +88,8 @@ struct x86_instruction_info { #define X86EMUL_CMPXCHG_FAILED 4 /* cmpxchg did not see expected value */ #define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ #define X86EMUL_INTERCEPTED 6 /* Intercepted by nested VMCB/VMCS */ +/* Emulation during event vectoring is unhandleable. */ +#define X86EMUL_UNHANDLEABLE_VECTORING 7 /* x86-specific emulation flags */ #define X86EMUL_F_WRITE BIT(0) diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 3c83951c619e..a009c94c26c2 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -598,7 +598,7 @@ void kvm_apic_set_version(struct kvm_vcpu *vcpu) * version first and level-triggered interrupts never get EOIed in * IOAPIC. */ - if (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) && !ioapic_in_kernel(vcpu->kvm)) v |= APIC_LVR_DIRECTED_EOI; kvm_lapic_set_reg(apic, APIC_LVR, v); @@ -734,10 +734,7 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic) static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) { if (unlikely(apic->apicv_active)) { - /* need to update RVI */ kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); - kvm_x86_call(hwapic_irr_update)(apic->vcpu, - apic_find_highest_irr(apic)); } else { apic->irr_pending = false; kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR); @@ -763,7 +760,7 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) * just set SVI. */ if (unlikely(apic->apicv_active)) - kvm_x86_call(hwapic_isr_update)(vec); + kvm_x86_call(hwapic_isr_update)(apic->vcpu, vec); else { ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -808,7 +805,7 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) * and must be left alone. */ if (unlikely(apic->apicv_active)) - kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic)); + kvm_x86_call(hwapic_isr_update)(apic->vcpu, apic_find_highest_isr(apic)); else { --apic->isr_count; BUG_ON(apic->isr_count < 0); @@ -816,6 +813,17 @@ static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) } } +void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu) +{ + struct kvm_lapic *apic = vcpu->arch.apic; + + if (WARN_ON_ONCE(!lapic_in_kernel(vcpu)) || !apic->apicv_active) + return; + + kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic)); +} +EXPORT_SYMBOL_GPL(kvm_apic_update_hwapic_isr); + int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) { /* This may race with setting of irr in __apic_accept_irq() and @@ -2357,7 +2365,7 @@ static int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val) case APIC_LVTT: if (!kvm_apic_sw_enabled(apic)) val |= APIC_LVT_MASKED; - val &= (apic_lvt_mask[0] | apic->lapic_timer.timer_mode_mask); + val &= (apic_lvt_mask[LVT_TIMER] | apic->lapic_timer.timer_mode_mask); kvm_lapic_set_reg(apic, APIC_LVTT, val); apic_update_lvtt(apic); break; @@ -2634,7 +2642,7 @@ int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated) return 0; u64 reserved_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu) | 0x2ff | - (guest_cpuid_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); + (guest_cpu_cap_has(vcpu, X86_FEATURE_X2APIC) ? 0 : X2APIC_ENABLE); if ((value & reserved_bits) != 0 || new_mode == LAPIC_MODE_INVALID) return 1; @@ -2805,8 +2813,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu, bool init_event) apic_update_ppr(apic); if (apic->apicv_active) { kvm_x86_call(apicv_post_state_restore)(vcpu); - kvm_x86_call(hwapic_irr_update)(vcpu, -1); - kvm_x86_call(hwapic_isr_update)(-1); + kvm_x86_call(hwapic_isr_update)(vcpu, -1); } vcpu->arch.apic_arb_prio = 0; @@ -3121,9 +3128,7 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s) kvm_apic_update_apicv(vcpu); if (apic->apicv_active) { kvm_x86_call(apicv_post_state_restore)(vcpu); - kvm_x86_call(hwapic_irr_update)(vcpu, - apic_find_highest_irr(apic)); - kvm_x86_call(hwapic_isr_update)(apic_find_highest_isr(apic)); + kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic)); } kvm_make_request(KVM_REQ_EVENT, vcpu); if (ioapic_in_kernel(vcpu->kvm)) diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h index 24add38beaf0..1a8553ebdb42 100644 --- a/arch/x86/kvm/lapic.h +++ b/arch/x86/kvm/lapic.h @@ -118,6 +118,7 @@ void kvm_apic_send_ipi(struct kvm_lapic *apic, u32 icr_low, u32 icr_high); int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated); int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s); +void kvm_apic_update_hwapic_isr(struct kvm_vcpu *vcpu); int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu); u64 kvm_get_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e9322358678b..050a0e229a4d 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { + /* + * Checking root.hpa is sufficient even when KVM has mirror root. + * We can have either: + * (1) mirror_root_hpa = INVALID_PAGE, root.hpa = INVALID_PAGE + * (2) mirror_root_hpa = root, root.hpa = INVALID_PAGE + * (3) mirror_root_hpa = root1, root.hpa = root2 + * We don't ever have: + * mirror_root_hpa = INVALID_PAGE, root.hpa = root + */ if (likely(vcpu->arch.mmu->root.hpa != INVALID_PAGE)) return 0; @@ -126,7 +135,7 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu) static inline unsigned long kvm_get_active_cr3_lam_bits(struct kvm_vcpu *vcpu) { - if (!guest_can_use(vcpu, X86_FEATURE_LAM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LAM)) return 0; return kvm_read_cr3(vcpu) & (X86_CR3_LAM_U48 | X86_CR3_LAM_U57); @@ -287,4 +296,26 @@ static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, return gpa; return translate_nested_gpa(vcpu, gpa, access, exception); } + +static inline bool kvm_has_mirrored_tdp(const struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_TDX_VM; +} + +static inline gfn_t kvm_gfn_direct_bits(const struct kvm *kvm) +{ + return kvm->arch.gfn_direct_bits; +} + +static inline bool kvm_is_addr_direct(struct kvm *kvm, gpa_t gpa) +{ + gpa_t gpa_direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(kvm)); + + return !gpa_direct_bits || (gpa & gpa_direct_bits); +} + +static inline bool kvm_is_gfn_alias(struct kvm *kvm, gfn_t gfn) +{ + return gfn & kvm_gfn_direct_bits(kvm); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2401606db260..74c20dbb92da 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -599,6 +599,12 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect) 1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM); if (r) return r; + if (kvm_has_mirrored_tdp(vcpu->kvm)) { + r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_external_spt_cache, + PT64_ROOT_MAX_LEVEL); + if (r) + return r; + } r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache, PT64_ROOT_MAX_LEVEL); if (r) @@ -618,6 +624,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache); + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_external_spt_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); } @@ -3656,8 +3663,13 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) unsigned i; int r; - if (tdp_mmu_enabled) - return kvm_tdp_mmu_alloc_root(vcpu); + if (tdp_mmu_enabled) { + if (kvm_has_mirrored_tdp(vcpu->kvm) && + !VALID_PAGE(mmu->mirror_root_hpa)) + kvm_tdp_mmu_alloc_root(vcpu, true); + kvm_tdp_mmu_alloc_root(vcpu, false); + return 0; + } write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); @@ -4379,8 +4391,12 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, unsigned int access) { struct kvm_memory_slot *slot = fault->slot; + struct kvm *kvm = vcpu->kvm; int ret; + if (KVM_BUG_ON(kvm_is_gfn_alias(kvm, fault->gfn), kvm)) + return -EFAULT; + /* * Note that the mmu_invalidate_seq also serves to detect a concurrent * change in attributes. is_page_fault_stale() will detect an @@ -4394,7 +4410,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * Now that we have a snapshot of mmu_invalidate_seq we can check for a * private vs. shared mismatch. */ - if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + if (fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return -EFAULT; } @@ -4456,7 +4472,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * *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 (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) return RET_PF_RETRY; ret = __kvm_mmu_faultin_pfn(vcpu, fault); @@ -4476,7 +4492,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * 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)) { + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) { kvm_mmu_finish_page_fault(vcpu, fault, RET_PF_RETRY); return RET_PF_RETRY; } @@ -5022,7 +5038,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(&context->guest_rsvd_check, vcpu->arch.reserved_gpa_bits, context->cpu_role.base.level, is_efer_nx(context), - guest_can_use(vcpu, X86_FEATURE_GBPAGES), + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), guest_cpuid_is_amd_compatible(vcpu)); } @@ -5099,7 +5115,7 @@ static void reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, __reset_rsvds_bits_mask(shadow_zero_check, reserved_hpa_bits(), context->root_role.level, context->root_role.efer_nx, - guest_can_use(vcpu, X86_FEATURE_GBPAGES), + guest_cpu_cap_has(vcpu, X86_FEATURE_GBPAGES), is_pse, is_amd); if (!shadow_me_mask) @@ -6095,8 +6111,16 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err else if (r == RET_PF_SPURIOUS) vcpu->stat.pf_spurious++; + /* + * None of handle_mmio_page_fault(), kvm_mmu_do_page_fault(), or + * kvm_mmu_write_protect_fault() return RET_PF_CONTINUE. + * kvm_mmu_do_page_fault() only uses RET_PF_CONTINUE internally to + * indicate continuing the page fault handling until to the final + * page table mapping phase. + */ + WARN_ON_ONCE(r == RET_PF_CONTINUE); if (r != RET_PF_EMULATE) - return 1; + return r; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, @@ -6272,6 +6296,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root.hpa = INVALID_PAGE; mmu->root.pgd = 0; + mmu->mirror_root_hpa = INVALID_PAGE; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; @@ -6441,8 +6466,13 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ - if (tdp_mmu_enabled) - kvm_tdp_mmu_invalidate_all_roots(kvm); + if (tdp_mmu_enabled) { + /* + * External page tables don't support fast zapping, therefore + * their mirrors must be invalidated separately by the caller. + */ + kvm_tdp_mmu_invalidate_roots(kvm, KVM_DIRECT_ROOTS); + } /* * Notify all vcpus to reload its shadow page table and flush TLB. @@ -6467,7 +6497,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * lead to use-after-free. */ if (tdp_mmu_enabled) - kvm_tdp_mmu_zap_invalidated_roots(kvm); + kvm_tdp_mmu_zap_invalidated_roots(kvm, true); } void kvm_mmu_init_vm(struct kvm *kvm) @@ -7090,6 +7120,19 @@ static void mmu_destroy_caches(void) kmem_cache_destroy(mmu_page_header_cache); } +static void kvm_wake_nx_recovery_thread(struct kvm *kvm) +{ + /* + * The NX recovery thread is spawned on-demand at the first KVM_RUN and + * may not be valid even though the VM is globally visible. Do nothing, + * as such a VM can't have any possible NX huge pages. + */ + struct vhost_task *nx_thread = READ_ONCE(kvm->arch.nx_huge_page_recovery_thread); + + if (nx_thread) + vhost_task_wake(nx_thread); +} + static int get_nx_huge_pages(char *buffer, const struct kernel_param *kp) { if (nx_hugepage_mitigation_hard_disabled) @@ -7150,7 +7193,7 @@ static int set_nx_huge_pages(const char *val, const struct kernel_param *kp) kvm_mmu_zap_all_fast(kvm); mutex_unlock(&kvm->slots_lock); - vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); } mutex_unlock(&kvm_lock); } @@ -7220,6 +7263,12 @@ out: void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); + if (tdp_mmu_enabled) { + read_lock(&vcpu->kvm->mmu_lock); + mmu_free_root_page(vcpu->kvm, &vcpu->arch.mmu->mirror_root_hpa, + NULL); + read_unlock(&vcpu->kvm->mmu_lock); + } free_mmu_pages(&vcpu->arch.root_mmu); free_mmu_pages(&vcpu->arch.guest_mmu); mmu_free_memory_caches(vcpu); @@ -7279,7 +7328,7 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) - vhost_task_wake(kvm->arch.nx_huge_page_recovery_thread); + kvm_wake_nx_recovery_thread(kvm); mutex_unlock(&kvm_lock); } @@ -7411,20 +7460,34 @@ static bool kvm_nx_huge_page_recovery_worker(void *data) return true; } +static void kvm_mmu_start_lpage_recovery(struct once *once) +{ + struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once); + struct kvm *kvm = container_of(ka, struct kvm, arch); + struct vhost_task *nx_thread; + + kvm->arch.nx_huge_page_last = get_jiffies_64(); + nx_thread = vhost_task_create(kvm_nx_huge_page_recovery_worker, + kvm_nx_huge_page_recovery_worker_kill, + kvm, "kvm-nx-lpage-recovery"); + + if (!nx_thread) + return; + + vhost_task_start(nx_thread); + + /* Make the task visible only once it is fully started. */ + WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread); +} + int kvm_mmu_post_init_vm(struct kvm *kvm) { if (nx_hugepage_mitigation_hard_disabled) return 0; - kvm->arch.nx_huge_page_last = get_jiffies_64(); - kvm->arch.nx_huge_page_recovery_thread = vhost_task_create( - kvm_nx_huge_page_recovery_worker, kvm_nx_huge_page_recovery_worker_kill, - kvm, "kvm-nx-lpage-recovery"); - + call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery); if (!kvm->arch.nx_huge_page_recovery_thread) return -ENOMEM; - - vhost_task_start(kvm->arch.nx_huge_page_recovery_thread); return 0; } @@ -7452,6 +7515,12 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; + /* Unmap the old attribute page. */ + if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) + range->attr_filter = KVM_FILTER_SHARED; + else + range->attr_filter = KVM_FILTER_PRIVATE; + return kvm_unmap_gfn_range(kvm, range); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index b00abbe3f6cf..75f00598289d 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -6,6 +6,8 @@ #include <linux/kvm_host.h> #include <asm/kvm_host.h> +#include "mmu.h" + #ifdef CONFIG_KVM_PROVE_MMU #define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x) #else @@ -101,7 +103,22 @@ struct kvm_mmu_page { int root_count; refcount_t tdp_mmu_root_count; }; - unsigned int unsync_children; + union { + /* These two members aren't used for TDP MMU */ + struct { + unsigned int unsync_children; + /* + * Number of writes since the last time traversal + * visited this page. + */ + atomic_t write_flooding_count; + }; + /* + * Page table page of external PT. + * Passed to TDX module, not accessed by KVM. + */ + void *external_spt; + }; union { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; @@ -124,9 +141,6 @@ struct kvm_mmu_page { int clear_spte_count; #endif - /* Number of writes since the last time traversal visited this page. */ - atomic_t write_flooding_count; - #ifdef CONFIG_X86_64 /* Used for freeing the page asynchronously if it is a TDP MMU page. */ struct rcu_head rcu_head; @@ -145,6 +159,34 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } +static inline bool is_mirror_sp(const struct kvm_mmu_page *sp) +{ + return sp->role.is_mirror; +} + +static inline void kvm_mmu_alloc_external_spt(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +{ + /* + * external_spt is allocated for TDX module to hold private EPT mappings, + * TDX module will initialize the page by itself. + * Therefore, KVM does not need to initialize or access external_spt. + * KVM only interacts with sp->spt for private EPT operations. + */ + sp->external_spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_external_spt_cache); +} + +static inline gfn_t kvm_gfn_root_bits(const struct kvm *kvm, const struct kvm_mmu_page *root) +{ + /* + * Since mirror SPs are used only for TDX, which maps private memory + * at its "natural" GFN, no mask needs to be applied to them - and, dually, + * we expect that the bits is only used for the shared PT. + */ + if (is_mirror_sp(root)) + return 0; + return kvm_gfn_direct_bits(kvm); +} + static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* @@ -229,7 +271,12 @@ struct kvm_page_fault { */ u8 goal_level; - /* Shifted addr, or result of guest page table walk if addr is a gva. */ + /* + * Shifted addr, or result of guest page table walk if addr is a gva. In + * the case of VM where memslot's can be mapped at multiple GPA aliases + * (i.e. TDX), the gfn field does not contain the bit that selects between + * the aliases (i.e. the shared bit for TDX). + */ gfn_t gfn; /* The memslot containing gfn. May be NULL. */ @@ -268,9 +315,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); * tracepoints via TRACE_DEFINE_ENUM() in mmutrace.h * * Note, all values must be greater than or equal to zero so as not to encroach - * on -errno return values. Somewhat arbitrarily use '0' for CONTINUE, which - * will allow for efficient machine code when checking for CONTINUE, e.g. - * "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero. + * on -errno return values. */ enum { RET_PF_CONTINUE = 0, @@ -282,6 +327,14 @@ enum { RET_PF_SPURIOUS, }; +/* + * Define RET_PF_CONTINUE as 0 to allow for + * - efficient machine code when checking for CONTINUE, e.g. + * "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero, + * - kvm_mmu_do_page_fault() to return other RET_PF_* as a positive value. + */ +static_assert(RET_PF_CONTINUE == 0); + static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { @@ -317,10 +370,19 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int r; if (vcpu->arch.mmu->root_role.direct) { - fault.gfn = fault.addr >> PAGE_SHIFT; + /* + * Things like memslots don't understand the concept of a shared + * bit. Strip it so that the GFN can be used like normal, and the + * fault.addr can be used when the shared bit is needed. + */ + fault.gfn = gpa_to_gfn(fault.addr) & ~kvm_gfn_direct_bits(vcpu->kvm); fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn); } + /* + * With retpoline being active an indirect call is rather expensive, + * so do a direct call in the most common case. + */ if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && fault.is_tdp) r = kvm_tdp_page_fault(vcpu, &fault); else diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index af10bc0380a3..59746854c0af 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -276,6 +276,11 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root) return spte_to_child_sp(root); } +static inline bool is_mirror_sptep(tdp_ptep_t sptep) +{ + return is_mirror_sp(sptep_to_sp(rcu_dereference(sptep))); +} + static inline bool is_mmio_spte(struct kvm *kvm, u64 spte) { return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value && diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 04c247bfe318..9e17bfa80901 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -12,7 +12,7 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) { iter->sptep = iter->pt_path[iter->level - 1] + - SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level); + SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level); iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); } @@ -37,15 +37,17 @@ void tdp_iter_restart(struct tdp_iter *iter) * rooted at root_pt, starting with the walk to translate next_last_level_gfn. */ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, - int min_level, gfn_t next_last_level_gfn) + int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits) { if (WARN_ON_ONCE(!root || (root->role.level < 1) || - (root->role.level > PT64_ROOT_MAX_LEVEL))) { + (root->role.level > PT64_ROOT_MAX_LEVEL) || + (gfn_bits && next_last_level_gfn >= gfn_bits))) { iter->valid = false; return; } iter->next_last_level_gfn = next_last_level_gfn; + iter->gfn_bits = gfn_bits; iter->root_level = root->role.level; iter->min_level = min_level; iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt; @@ -113,7 +115,7 @@ static bool try_step_side(struct tdp_iter *iter) * Check if the iterator is already at the end of the current page * table. */ - if (SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level) == + if (SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level) == (SPTE_ENT_PER_PAGE - 1)) return false; diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index 2880fd392e0c..047b78333653 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -93,8 +93,10 @@ struct tdp_iter { tdp_ptep_t pt_path[PT64_ROOT_MAX_LEVEL]; /* A pointer to the current SPTE */ tdp_ptep_t sptep; - /* The lowest GFN mapped by the current SPTE */ + /* The lowest GFN (mask bits excluded) mapped by the current SPTE */ gfn_t gfn; + /* Mask applied to convert the GFN to the mapping GPA */ + gfn_t gfn_bits; /* The level of the root page given to the iterator */ int root_level; /* The lowest level the iterator should traverse to */ @@ -122,18 +124,23 @@ struct tdp_iter { * Iterates over every SPTE mapping the GFN range [start, end) in a * preorder traversal. */ -#define for_each_tdp_pte_min_level(iter, root, min_level, start, end) \ - for (tdp_iter_start(&iter, root, min_level, start); \ - iter.valid && iter.gfn < end; \ +#define for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) \ + for (tdp_iter_start(&iter, root, min_level, start, kvm_gfn_root_bits(kvm, root)); \ + iter.valid && iter.gfn < end; \ tdp_iter_next(&iter)) -#define for_each_tdp_pte(iter, root, start, end) \ - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) +#define for_each_tdp_pte_min_level_all(iter, root, min_level) \ + for (tdp_iter_start(&iter, root, min_level, 0, 0); \ + iter.valid && iter.gfn < tdp_mmu_max_gfn_exclusive(); \ + tdp_iter_next(&iter)) + +#define for_each_tdp_pte(iter, kvm, root, start, end) \ + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) tdp_ptep_t spte_to_child_pt(u64 pte, int level); void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, - int min_level, gfn_t next_last_level_gfn); + int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits); void tdp_iter_next(struct tdp_iter *iter); void tdp_iter_restart(struct tdp_iter *iter); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 2f15e0e33903..046b6ba31197 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -37,8 +37,8 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * for zapping and thus puts the TDP MMU's reference to each root, i.e. * ultimately frees all roots. */ - kvm_tdp_mmu_invalidate_all_roots(kvm); - kvm_tdp_mmu_zap_invalidated_roots(kvm); + kvm_tdp_mmu_invalidate_roots(kvm, KVM_VALID_ROOTS); + kvm_tdp_mmu_zap_invalidated_roots(kvm, false); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); @@ -53,6 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) static void tdp_mmu_free_sp(struct kvm_mmu_page *sp) { + free_page((unsigned long)sp->external_spt); free_page((unsigned long)sp->spt); kmem_cache_free(mmu_page_header_cache, sp); } @@ -91,19 +92,33 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } +static bool tdp_mmu_root_match(struct kvm_mmu_page *root, + enum kvm_tdp_mmu_root_types types) +{ + if (WARN_ON_ONCE(!(types & KVM_VALID_ROOTS))) + return false; + + if (root->role.invalid && !(types & KVM_INVALID_ROOTS)) + return false; + + if (likely(!is_mirror_sp(root))) + return types & KVM_DIRECT_ROOTS; + return types & KVM_MIRROR_ROOTS; +} + /* * Returns the next root after @prev_root (or the first root if @prev_root is - * NULL). A reference to the returned root is acquired, and the reference to - * @prev_root is released (the caller obviously must hold a reference to - * @prev_root if it's non-NULL). + * NULL) that matches with @types. A reference to the returned root is + * acquired, and the reference to @prev_root is released (the caller obviously + * must hold a reference to @prev_root if it's non-NULL). * - * If @only_valid is true, invalid roots are skipped. + * Roots that doesn't match with @types are skipped. * * Returns NULL if the end of tdp_mmu_roots was reached. */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool only_valid) + enum kvm_tdp_mmu_root_types types) { struct kvm_mmu_page *next_root; @@ -124,7 +139,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, typeof(*next_root), link); while (next_root) { - if ((!only_valid || !next_root->role.invalid) && + if (tdp_mmu_root_match(next_root, types) && kvm_tdp_mmu_get_root(next_root)) break; @@ -149,20 +164,20 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * If shared is set, this function is operating under the MMU lock in read * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _types) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _types); \ ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + _root = tdp_mmu_next_root(_kvm, _root, _types)) \ if (_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) { \ } else #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) + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, KVM_VALID_ROOTS) #define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + for (_root = tdp_mmu_next_root(_kvm, NULL, KVM_ALL_ROOTS); \ ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, false)) + _root = tdp_mmu_next_root(_kvm, _root, KVM_ALL_ROOTS)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -171,18 +186,15 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * Holding mmu_lock for write obviates the need for RCU protection as the list * is guaranteed to be stable. */ -#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _only_valid) \ +#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _types) \ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \ - ((_only_valid) && (_root)->role.invalid))) { \ + !tdp_mmu_root_match((_root), (_types)))) { \ } else -#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root(_kvm, _root, _as_id, false) - #define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root(_kvm, _root, _as_id, true) + __for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_VALID_ROOTS) static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) { @@ -223,7 +235,7 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp, tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role); } -int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool mirror) { struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role role = mmu->root_role; @@ -231,6 +243,9 @@ int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_mmu_page *root; + if (mirror) + role.is_mirror = true; + /* * Check for an existing root before acquiring the pages lock to avoid * unnecessary serialization if multiple vCPUs are loading a new root. @@ -282,9 +297,12 @@ out_read_unlock: * and actually consuming the root if it's invalidated after dropping * mmu_lock, and the root can't be freed as this vCPU holds a reference. */ - mmu->root.hpa = __pa(root->spt); - mmu->root.pgd = 0; - return 0; + if (mirror) { + mmu->mirror_root_hpa = __pa(root->spt); + } else { + mmu->root.hpa = __pa(root->spt); + mmu->root.pgd = 0; + } } static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, @@ -322,6 +340,29 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } +static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte, + int level) +{ + kvm_pfn_t old_pfn = spte_to_pfn(old_spte); + int ret; + + /* + * External (TDX) SPTEs are limited to PG_LEVEL_4K, and external + * PTs are removed in a special order, involving free_external_spt(). + * But remove_external_spte() will be called on non-leaf PTEs via + * __tdp_mmu_zap_root(), so avoid the error the former would return + * in this case. + */ + if (!is_last_spte(old_spte, level)) + return; + + /* Zapping leaf spte is allowed only when write lock is held. */ + lockdep_assert_held_write(&kvm->mmu_lock); + /* Because write lock is held, operation should success. */ + ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn); + KVM_BUG_ON(ret, kvm); +} + /** * handle_removed_pt() - handle a page table removed from the TDP structure * @@ -417,11 +458,81 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, old_spte, FROZEN_SPTE, level, shared); + + if (is_mirror_sp(sp)) { + KVM_BUG_ON(shared, kvm); + remove_external_spte(kvm, gfn, old_spte, level); + } + } + + if (is_mirror_sp(sp) && + WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level, + sp->external_spt))) { + /* + * Failed to free page table page in mirror page table and + * there is nothing to do further. + * Intentionally leak the page to prevent the kernel from + * accessing the encrypted page. + */ + sp->external_spt = NULL; } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); } +static void *get_external_spt(gfn_t gfn, u64 new_spte, int level) +{ + if (is_shadow_present_pte(new_spte) && !is_last_spte(new_spte, level)) { + struct kvm_mmu_page *sp = spte_to_child_sp(new_spte); + + WARN_ON_ONCE(sp->role.level + 1 != level); + WARN_ON_ONCE(sp->gfn != gfn); + return sp->external_spt; + } + + return NULL; +} + +static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sptep, + gfn_t gfn, u64 old_spte, + u64 new_spte, int level) +{ + bool was_present = is_shadow_present_pte(old_spte); + bool is_present = is_shadow_present_pte(new_spte); + bool is_leaf = is_present && is_last_spte(new_spte, level); + kvm_pfn_t new_pfn = spte_to_pfn(new_spte); + int ret = 0; + + KVM_BUG_ON(was_present, kvm); + + lockdep_assert_held(&kvm->mmu_lock); + /* + * We need to lock out other updates to the SPTE until the external + * page table has been modified. Use FROZEN_SPTE similar to + * the zapping case. + */ + if (!try_cmpxchg64(rcu_dereference(sptep), &old_spte, FROZEN_SPTE)) + return -EBUSY; + + /* + * Use different call to either set up middle level + * external page table, or leaf. + */ + if (is_leaf) { + ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn); + } else { + void *external_spt = get_external_spt(gfn, new_spte, level); + + KVM_BUG_ON(!external_spt, kvm); + ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt); + } + if (ret) + __kvm_tdp_mmu_write_spte(sptep, old_spte); + else + __kvm_tdp_mmu_write_spte(sptep, new_spte); + return ret; +} + /** * handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance @@ -522,11 +633,10 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, handle_removed_pt(kvm, spte_to_child_pt(old_spte, level), shared); } -static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, +static inline int __must_check __tdp_mmu_set_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter, u64 new_spte) { - u64 *sptep = rcu_dereference(iter->sptep); - /* * The caller is responsible for ensuring the old SPTE is not a FROZEN * SPTE. KVM should never attempt to zap or manipulate a FROZEN SPTE, @@ -535,15 +645,34 @@ static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, */ WARN_ON_ONCE(iter->yielded || is_frozen_spte(iter->old_spte)); - /* - * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. On failure, i.e. if a different logical - * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with - * the current value, so the caller operates on fresh data, e.g. if it - * retries tdp_mmu_set_spte_atomic() - */ - if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) - return -EBUSY; + if (is_mirror_sptep(iter->sptep) && !is_frozen_spte(new_spte)) { + int ret; + + /* + * Users of atomic zapping don't operate on mirror roots, + * so don't handle it and bug the VM if it's seen. + */ + if (KVM_BUG_ON(!is_shadow_present_pte(new_spte), kvm)) + return -EBUSY; + + ret = set_external_spte_present(kvm, iter->sptep, iter->gfn, + iter->old_spte, new_spte, iter->level); + if (ret) + return ret; + } else { + u64 *sptep = rcu_dereference(iter->sptep); + + /* + * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs + * and does not hold the mmu_lock. On failure, i.e. if a + * different logical CPU modified the SPTE, try_cmpxchg64() + * updates iter->old_spte with the current value, so the caller + * operates on fresh data, e.g. if it retries + * tdp_mmu_set_spte_atomic() + */ + if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) + return -EBUSY; + } return 0; } @@ -573,7 +702,7 @@ static inline int __must_check tdp_mmu_set_spte_atomic(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - ret = __tdp_mmu_set_spte_atomic(iter, new_spte); + ret = __tdp_mmu_set_spte_atomic(kvm, iter, new_spte); if (ret) return ret; @@ -613,6 +742,16 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); + + /* + * Users that do non-atomic setting of PTEs don't operate on mirror + * roots, so don't handle it and bug the VM if it's seen. + */ + if (is_mirror_sptep(sptep)) { + KVM_BUG_ON(is_shadow_present_pte(new_spte), kvm); + remove_external_spte(kvm, gfn, old_spte, level); + } + return old_spte; } @@ -625,18 +764,18 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, iter->gfn, iter->level); } -#define tdp_root_for_each_pte(_iter, _root, _start, _end) \ - for_each_tdp_pte(_iter, _root, _start, _end) +#define tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end) \ + for_each_tdp_pte(_iter, _kvm, _root, _start, _end) -#define tdp_root_for_each_leaf_pte(_iter, _root, _start, _end) \ - tdp_root_for_each_pte(_iter, _root, _start, _end) \ +#define tdp_root_for_each_leaf_pte(_iter, _kvm, _root, _start, _end) \ + tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end) \ if (!is_shadow_present_pte(_iter.old_spte) || \ !is_last_spte(_iter.old_spte, _iter.level)) \ continue; \ else -#define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end) \ - for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end) +#define tdp_mmu_for_each_pte(_iter, _kvm, _root, _start, _end) \ + for_each_tdp_pte(_iter, _kvm, _root, _start, _end) static inline bool __must_check tdp_mmu_iter_need_resched(struct kvm *kvm, struct tdp_iter *iter) @@ -705,10 +844,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_exclusive(); - gfn_t start = 0; - - for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { + for_each_tdp_pte_min_level_all(iter, root, zap_level) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared)) continue; @@ -812,7 +948,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) { if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) { flush = false; @@ -863,19 +999,21 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) struct kvm_mmu_page *root; /* - * Zap all roots, including invalid roots, as all SPTEs must be dropped - * before returning to the caller. Zap directly even if the root is - * also being zapped by a worker. Walking zapped top-level SPTEs isn't - * all that expensive and mmu_lock is already held, which means the - * worker has yielded, i.e. flushing the work instead of zapping here - * isn't guaranteed to be any faster. + * Zap all direct roots, including invalid direct roots, as all direct + * SPTEs must be dropped before returning to the caller. For TDX, mirror + * roots don't need handling in response to the mmu notifier (the caller). + * + * Zap directly even if the root is also being zapped by a concurrent + * "fast zap". Walking zapped top-level SPTEs isn't all that expensive + * and mmu_lock is already held, which means the other thread has yielded. * * A TLB flush is unnecessary, KVM zaps everything if and only the VM * 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. */ lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root) + __for_each_tdp_mmu_root_yield_safe(kvm, root, -1, + KVM_DIRECT_ROOTS | KVM_INVALID_ROOTS) tdp_mmu_zap_root(kvm, root, false); } @@ -883,11 +1021,14 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * Zap all invalidated roots to ensure all SPTEs are dropped before the "fast * zap" completes. */ -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared) { struct kvm_mmu_page *root; - read_lock(&kvm->mmu_lock); + if (shared) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); for_each_tdp_mmu_root_yield_safe(kvm, root) { if (!root->tdp_mmu_scheduled_root_to_zap) @@ -905,7 +1046,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * that may be zapped, as such entries are associated with the * ASID on both VMX and SVM. */ - tdp_mmu_zap_root(kvm, root, true); + tdp_mmu_zap_root(kvm, root, shared); /* * The referenced needs to be put *after* zapping the root, as @@ -915,7 +1056,10 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) kvm_tdp_mmu_put_root(kvm, root); } - read_unlock(&kvm->mmu_lock); + if (shared) + read_unlock(&kvm->mmu_lock); + else + write_unlock(&kvm->mmu_lock); } /* @@ -928,11 +1072,19 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_alloc_root(). */ -void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) +void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm, + enum kvm_tdp_mmu_root_types root_types) { struct kvm_mmu_page *root; /* + * Invalidating invalid roots doesn't make sense, prevent developers from + * having to think about it. + */ + if (WARN_ON_ONCE(root_types & KVM_INVALID_ROOTS)) + root_types &= ~KVM_INVALID_ROOTS; + + /* * mmu_lock must be held for write to ensure that a root doesn't become * invalid while there are active readers (invalidating a root while * there are active readers may or may not be problematic in practice, @@ -953,6 +1105,9 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) * or get/put references to roots. */ list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + if (!tdp_mmu_root_match(root, root_types)) + continue; + /* * Note, invalid roots can outlive a memslot update! Invalid * roots must be *zapped* before the memslot update completes, @@ -1068,7 +1223,7 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, */ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_mmu *mmu = vcpu->arch.mmu; + struct kvm_mmu_page *root = tdp_mmu_get_root_for_fault(vcpu, fault); struct kvm *kvm = vcpu->kvm; struct tdp_iter iter; struct kvm_mmu_page *sp; @@ -1080,7 +1235,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) rcu_read_lock(); - tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) { + tdp_mmu_for_each_pte(iter, kvm, root, fault->gfn, fault->gfn + 1) { int r; if (fault->nx_huge_page_workaround_enabled) @@ -1107,13 +1262,18 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) */ sp = tdp_mmu_alloc_sp(vcpu); tdp_mmu_init_child_sp(sp, &iter); + if (is_mirror_sp(sp)) + kvm_mmu_alloc_external_spt(vcpu, sp); sp->nx_huge_page_disallowed = fault->huge_page_disallowed; - if (is_shadow_present_pte(iter.old_spte)) + if (is_shadow_present_pte(iter.old_spte)) { + /* Don't support large page for mirrored roots (TDX) */ + KVM_BUG_ON(is_mirror_sptep(iter.sptep), vcpu->kvm); r = tdp_mmu_split_huge_page(kvm, &iter, sp, true); - else + } else { r = tdp_mmu_link_sp(kvm, &iter, sp, true); + } /* * Force the guest to retry if installing an upper level SPTE @@ -1148,12 +1308,16 @@ retry: return ret; } +/* Used by mmu notifier via kvm_unmap_gfn_range() */ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { + enum kvm_tdp_mmu_root_types types; struct kvm_mmu_page *root; - __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter) | KVM_INVALID_ROOTS; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, types) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); @@ -1193,20 +1357,24 @@ static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool test_only) { + enum kvm_tdp_mmu_root_types types; struct kvm_mmu_page *root; struct tdp_iter iter; bool ret = false; + types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter); + /* * Don't support rescheduling, none of the MMU notifiers that funnel * into this helper allow blocking; it'd be dead, wasteful code. Note, * this helper must NOT be used to unmap GFNs, as it processes only * valid roots! */ - for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) { + WARN_ON(types & ~KVM_VALID_ROOTS); + __for_each_tdp_mmu_root(kvm, root, range->slot->as_id, types) { guard(rcu)(); - tdp_root_for_each_leaf_pte(iter, root, range->start, range->end) { + tdp_root_for_each_leaf_pte(iter, kvm, root, range->start, range->end) { if (!is_accessed_spte(iter.old_spte)) continue; @@ -1247,7 +1415,7 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); - for_each_tdp_pte_min_level(iter, root, min_level, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; @@ -1366,7 +1534,7 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm, * level above the target level (e.g. splitting a 1GB to 512 2MB pages, * and then splitting each of those to 512 4KB pages). */ - for_each_tdp_pte_min_level(iter, root, target_level + 1, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, target_level + 1, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared)) continue; @@ -1464,7 +1632,7 @@ static void clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_pte(iter, root, start, end) { + tdp_root_for_each_pte(iter, kvm, root, start, end) { retry: if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) @@ -1512,7 +1680,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask), + tdp_root_for_each_leaf_pte(iter, kvm, root, gfn + __ffs(mask), gfn + BITS_PER_LONG) { if (!mask) break; @@ -1566,7 +1734,7 @@ static int tdp_mmu_make_huge_spte(struct kvm *kvm, gfn_t end = start + KVM_PAGES_PER_HPAGE(parent->level); struct tdp_iter iter; - tdp_root_for_each_leaf_pte(iter, root, start, end) { + tdp_root_for_each_leaf_pte(iter, kvm, root, start, end) { /* * Use the parent iterator when checking for forward progress so * that KVM doesn't get stuck continuously trying to yield (i.e. @@ -1600,7 +1768,7 @@ static void recover_huge_pages_range(struct kvm *kvm, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_2M, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_2M, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) { flush = false; @@ -1681,7 +1849,7 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, min_level, gfn, gfn + 1) { + for_each_tdp_pte_min_level(iter, kvm, root, min_level, gfn, gfn + 1) { if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) continue; @@ -1729,14 +1897,14 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); struct tdp_iter iter; - struct kvm_mmu *mmu = vcpu->arch.mmu; gfn_t gfn = addr >> PAGE_SHIFT; int leaf = -1; *root_level = vcpu->arch.mmu->root_role.level; - tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { leaf = iter.level; sptes[leaf] = iter.old_spte; } @@ -1758,11 +1926,12 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *spte) { + /* Fast pf is not supported for mirrored roots */ + struct kvm_mmu_page *root = tdp_mmu_get_root(vcpu, KVM_DIRECT_ROOTS); struct tdp_iter iter; - struct kvm_mmu *mmu = vcpu->arch.mmu; tdp_ptep_t sptep = NULL; - tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { *spte = iter.old_spte; sptep = iter.sptep; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index f03ca0dd13d9..52acf99d40a0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,7 +10,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu); +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool private); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) { @@ -19,11 +19,56 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); +enum kvm_tdp_mmu_root_types { + KVM_INVALID_ROOTS = BIT(0), + KVM_DIRECT_ROOTS = BIT(1), + KVM_MIRROR_ROOTS = BIT(2), + KVM_VALID_ROOTS = KVM_DIRECT_ROOTS | KVM_MIRROR_ROOTS, + KVM_ALL_ROOTS = KVM_VALID_ROOTS | KVM_INVALID_ROOTS, +}; + +static inline enum kvm_tdp_mmu_root_types kvm_gfn_range_filter_to_root_types(struct kvm *kvm, + enum kvm_gfn_range_filter process) +{ + enum kvm_tdp_mmu_root_types ret = 0; + + if (!kvm_has_mirrored_tdp(kvm)) + return KVM_DIRECT_ROOTS; + + if (process & KVM_FILTER_PRIVATE) + ret |= KVM_MIRROR_ROOTS; + if (process & KVM_FILTER_SHARED) + ret |= KVM_DIRECT_ROOTS; + + WARN_ON_ONCE(!ret); + + return ret; +} + +static inline struct kvm_mmu_page *tdp_mmu_get_root_for_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + if (unlikely(!kvm_is_addr_direct(vcpu->kvm, fault->addr))) + return root_to_sp(vcpu->arch.mmu->mirror_root_hpa); + + return root_to_sp(vcpu->arch.mmu->root.hpa); +} + +static inline struct kvm_mmu_page *tdp_mmu_get_root(struct kvm_vcpu *vcpu, + enum kvm_tdp_mmu_root_types type) +{ + if (unlikely(type == KVM_MIRROR_ROOTS)) + return root_to_sp(vcpu->arch.mmu->mirror_root_hpa); + + return root_to_sp(vcpu->arch.mmu->root.hpa); +} + 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); void kvm_tdp_mmu_zap_all(struct kvm *kvm); -void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm); +void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm, + enum kvm_tdp_mmu_root_types root_types); +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 47a46283c866..75e9cfc689f8 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -797,7 +797,6 @@ void kvm_pmu_init(struct kvm_vcpu *vcpu) memset(pmu, 0, sizeof(*pmu)); kvm_pmu_call(init)(vcpu); - kvm_pmu_refresh(vcpu); } /* Release perf_events for vPMCs that have been unused for a full time slice. */ diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index e46220ece83c..fde0ae986003 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -7,23 +7,6 @@ #include <asm/cpufeatures.h> /* - * Hardware-defined CPUID leafs that are either scattered by the kernel or are - * unknown to the kernel, but need to be directly used by KVM. Note, these - * word values conflict with the kernel's "bug" caps, but KVM doesn't use those. - */ -enum kvm_only_cpuid_leafs { - CPUID_12_EAX = NCAPINTS, - CPUID_7_1_EDX, - CPUID_8000_0007_EDX, - CPUID_8000_0022_EAX, - CPUID_7_2_EDX, - CPUID_24_0_EBX, - NR_KVM_CPU_CAPS, - - NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS, -}; - -/* * Define a KVM-only feature flag. * * For features that are scattered by cpufeatures.h, __feature_translate() also @@ -145,7 +128,10 @@ static __always_inline u32 __feature_translate(int x86_feature) static __always_inline u32 __feature_leaf(int x86_feature) { - return __feature_translate(x86_feature) / 32; + u32 x86_leaf = __feature_translate(x86_feature) / 32; + + reverse_cpuid_check(x86_leaf); + return x86_leaf; } /* @@ -168,7 +154,6 @@ static __always_inline struct cpuid_reg x86_feature_cpuid(unsigned int x86_featu { unsigned int x86_leaf = __feature_leaf(x86_feature); - reverse_cpuid_check(x86_leaf); return reverse_cpuid[x86_leaf]; } diff --git a/arch/x86/kvm/smm.c b/arch/x86/kvm/smm.c index 85241c0c7f56..e0ab7df27b66 100644 --- a/arch/x86/kvm/smm.c +++ b/arch/x86/kvm/smm.c @@ -283,7 +283,7 @@ void enter_smm(struct kvm_vcpu *vcpu) memset(smram.bytes, 0, sizeof(smram.bytes)); #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) enter_smm_save_state_64(vcpu, &smram.smram64); else #endif @@ -353,7 +353,7 @@ void enter_smm(struct kvm_vcpu *vcpu) kvm_set_segment(vcpu, &ds, VCPU_SREG_SS); #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) if (kvm_x86_call(set_efer)(vcpu, 0)) goto error; #endif @@ -586,7 +586,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) * supports long mode. */ #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) { struct kvm_segment cs_desc; unsigned long cr4; @@ -609,7 +609,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) kvm_set_cr0(vcpu, cr0 & ~(X86_CR0_PG | X86_CR0_PE)); #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) { unsigned long cr4, efer; /* Clear CR4.PAE before clearing EFER.LME. */ @@ -634,7 +634,7 @@ int emulator_leave_smm(struct x86_emulate_ctxt *ctxt) return X86EMUL_UNHANDLEABLE; #ifdef CONFIG_X86_64 - if (guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) ret = rsm_load_state_64(ctxt, &smram.smram64); else #endif diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index b708bdf7eaff..d77b094d9a4d 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -111,7 +111,7 @@ static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu) static bool nested_vmcb_needs_vls_intercept(struct vcpu_svm *svm) { - if (!guest_can_use(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) + if (!guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_V_VMSAVE_VMLOAD)) return true; if (!nested_npt_enabled(svm)) @@ -594,7 +594,7 @@ static void nested_vmcb02_prepare_save(struct vcpu_svm *svm, struct vmcb *vmcb12 vmcb_mark_dirty(vmcb02, VMCB_DR); } - if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { /* * Reserved bits of DEBUGCTL are ignored. Be consistent with @@ -651,7 +651,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * exit_int_info, exit_int_info_err, next_rip, insn_len, insn_bytes. */ - if (guest_can_use(vcpu, X86_FEATURE_VGIF) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VGIF) && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK)) int_ctl_vmcb12_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); else @@ -689,7 +689,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.tsc_offset = vcpu->arch.tsc_offset; - if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR) && svm->tsc_ratio_msr != kvm_caps.default_tsc_scaling_ratio) nested_svm_update_tsc_ratio_msr(vcpu); @@ -710,7 +710,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, * what a nrips=0 CPU would do (L1 is responsible for advancing RIP * prior to injecting the event). */ - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) vmcb02->control.next_rip = svm->nested.ctl.next_rip; else if (boot_cpu_has(X86_FEATURE_NRIPS)) vmcb02->control.next_rip = vmcb12_rip; @@ -720,7 +720,7 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, svm->soft_int_injected = true; svm->soft_int_csbase = vmcb12_csbase; svm->soft_int_old_rip = vmcb12_rip; - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) svm->soft_int_next_rip = svm->nested.ctl.next_rip; else svm->soft_int_next_rip = vmcb12_rip; @@ -728,18 +728,18 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, vmcb02->control.virt_ext = vmcb01->control.virt_ext & LBR_CTL_ENABLE_MASK; - if (guest_can_use(vcpu, X86_FEATURE_LBRV)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV)) vmcb02->control.virt_ext |= (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK); if (!nested_vmcb_needs_vls_intercept(svm)) vmcb02->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK; - if (guest_can_use(vcpu, X86_FEATURE_PAUSEFILTER)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PAUSEFILTER)) pause_count12 = svm->nested.ctl.pause_filter_count; else pause_count12 = 0; - if (guest_can_use(vcpu, X86_FEATURE_PFTHRESHOLD)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PFTHRESHOLD)) pause_thresh12 = svm->nested.ctl.pause_filter_thresh; else pause_thresh12 = 0; @@ -1026,7 +1026,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (vmcb12->control.exit_code != SVM_EXIT_ERR) nested_save_pending_event_to_vmcb12(svm, vmcb12); - if (guest_can_use(vcpu, X86_FEATURE_NRIPS)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_NRIPS)) vmcb12->control.next_rip = vmcb02->control.next_rip; vmcb12->control.int_ctl = svm->nested.ctl.int_ctl; @@ -1065,7 +1065,7 @@ int nested_svm_vmexit(struct vcpu_svm *svm) if (!nested_exit_on_intr(svm)) kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); - if (unlikely(guest_can_use(vcpu, X86_FEATURE_LBRV) && + if (unlikely(guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { svm_copy_lbrs(vmcb12, vmcb02); svm_update_lbrv(vcpu); diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index 22d5a65b410c..288f7f2a46f2 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -46,7 +46,7 @@ static inline struct kvm_pmc *get_gp_pmc_amd(struct kvm_pmu *pmu, u32 msr, switch (msr) { case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: - if (!guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE)) return NULL; /* * Each PMU counter has a pair of CTL and CTR MSRs. CTLn @@ -109,7 +109,7 @@ static bool amd_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) case MSR_K7_EVNTSEL0 ... MSR_K7_PERFCTR3: return pmu->version > 0; case MSR_F15H_PERF_CTL0 ... MSR_F15H_PERF_CTR5: - return guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE); + return guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE); case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS: case MSR_AMD64_PERF_CNTR_GLOBAL_CTL: case MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR: @@ -179,7 +179,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) union cpuid_0x80000022_ebx ebx; pmu->version = 1; - if (guest_cpuid_has(vcpu, X86_FEATURE_PERFMON_V2)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFMON_V2)) { pmu->version = 2; /* * Note, PERFMON_V2 is also in 0x80000022.0x0, i.e. the guest @@ -189,7 +189,7 @@ static void amd_pmu_refresh(struct kvm_vcpu *vcpu) x86_feature_cpuid(X86_FEATURE_PERFMON_V2).index); ebx.full = kvm_find_cpuid_entry_index(vcpu, 0x80000022, 0)->ebx; pmu->nr_arch_gp_counters = ebx.split.num_core_pmc; - } else if (guest_cpuid_has(vcpu, X86_FEATURE_PERFCTR_CORE)) { + } else if (guest_cpu_cap_has(vcpu, X86_FEATURE_PERFCTR_CORE)) { pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS_CORE; } else { pmu->nr_arch_gp_counters = AMD64_NUM_COUNTERS; diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 943bd074a5d3..a2a794c32050 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -3051,11 +3051,11 @@ out: min_sev_asid, max_sev_asid); if (boot_cpu_has(X86_FEATURE_SEV_ES)) pr_info("SEV-ES %s (ASIDs %u - %u)\n", - sev_es_supported ? "enabled" : "disabled", + str_enabled_disabled(sev_es_supported), min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); if (boot_cpu_has(X86_FEATURE_SEV_SNP)) pr_info("SEV-SNP %s (ASIDs %u - %u)\n", - sev_snp_supported ? "enabled" : "disabled", + str_enabled_disabled(sev_snp_supported), min_sev_asid > 1 ? 1 : 0, min_sev_asid - 1); sev_enabled = sev_supported; @@ -3627,13 +3627,20 @@ static int snp_begin_psc_msr(struct vcpu_svm *svm, u64 ghcb_msr) return 1; /* resume guest */ } - if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) { + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) { set_ghcb_msr(svm, GHCB_MSR_PSC_RESP_ERROR); return 1; /* resume guest */ } vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = 1; vcpu->run->hypercall.args[2] = (op == SNP_PAGE_STATE_PRIVATE) @@ -3710,7 +3717,7 @@ static int snp_begin_psc(struct vcpu_svm *svm, struct psc_buffer *psc) bool huge; u64 gfn; - if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) { + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) { snp_complete_psc(svm, VMGEXIT_PSC_ERROR_GENERIC); return 1; } @@ -3797,6 +3804,13 @@ next_range: case VMGEXIT_PSC_OP_SHARED: vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gfn_to_gpa(gfn); vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = entry_start.operation == VMGEXIT_PSC_OP_PRIVATE @@ -3820,7 +3834,7 @@ next_range: goto next_range; } - unreachable(); + BUG(); } static int __sev_snp_update_protected_guest_state(struct kvm_vcpu *vcpu) @@ -4435,8 +4449,8 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) struct kvm_vcpu *vcpu = &svm->vcpu; if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) { - bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + bool v_tsc_aux = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux); } @@ -4445,16 +4459,15 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm) * For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if * the host/guest supports its use. * - * guest_can_use() checks a number of requirements on the host/guest to - * ensure that MSR_IA32_XSS is available, but it might report true even - * if X86_FEATURE_XSAVES isn't configured in the guest to ensure host - * MSR_IA32_XSS is always properly restored. For SEV-ES, it is better - * to further check that the guest CPUID actually supports - * X86_FEATURE_XSAVES so that accesses to MSR_IA32_XSS by misbehaved - * guests will still get intercepted and caught in the normal - * kvm_emulate_rdmsr()/kvm_emulated_wrmsr() paths. + * KVM treats the guest as being capable of using XSAVES even if XSAVES + * isn't enabled in guest CPUID as there is no intercept for XSAVES, + * i.e. the guest can use XSAVES/XRSTOR to read/write XSS if XSAVE is + * exposed to the guest and XSAVES is supported in hardware. Condition + * full XSS passthrough on the guest being able to use XSAVES *and* + * XSAVES being exposed to the guest so that KVM can at least honor + * guest CPUID for RDMSR and WRMSR. */ - if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && guest_cpuid_has(vcpu, X86_FEATURE_XSAVES)) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1); else diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 21dacd312779..7640a84e554a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -28,6 +28,7 @@ #include <linux/rwsem.h> #include <linux/cc_platform.h> #include <linux/smp.h> +#include <linux/string_choices.h> #include <asm/apic.h> #include <asm/perf_event.h> @@ -284,8 +285,6 @@ u32 svm_msrpm_offset(u32 msr) return MSR_INVALID; } -static void svm_flush_tlb_current(struct kvm_vcpu *vcpu); - static int get_npt_level(void) { #ifdef CONFIG_X86_64 @@ -1049,7 +1048,7 @@ void svm_update_lbrv(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); bool current_enable_lbrv = svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK; bool enable_lbrv = (svm_get_lbr_vmcb(svm)->save.dbgctl & DEBUGCTLMSR_LBR) || - (is_guest_mode(vcpu) && guest_can_use(vcpu, X86_FEATURE_LBRV) && + (is_guest_mode(vcpu) && guest_cpu_cap_has(vcpu, X86_FEATURE_LBRV) && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK)); if (enable_lbrv == current_enable_lbrv) @@ -1187,14 +1186,14 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu, */ if (kvm_cpu_cap_has(X86_FEATURE_INVPCID)) { if (!npt_enabled || - !guest_cpuid_has(&svm->vcpu, X86_FEATURE_INVPCID)) + !guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_INVPCID)) svm_set_intercept(svm, INTERCEPT_INVPCID); else svm_clr_intercept(svm, INTERCEPT_INVPCID); } if (kvm_cpu_cap_has(X86_FEATURE_RDTSCP)) { - if (guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP)) svm_clr_intercept(svm, INTERCEPT_RDTSCP); else svm_set_intercept(svm, INTERCEPT_RDTSCP); @@ -1921,9 +1920,6 @@ void svm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) unsigned long host_cr4_mce = cr4_read_shadow() & X86_CR4_MCE; unsigned long old_cr4 = vcpu->arch.cr4; - if (npt_enabled && ((old_cr4 ^ cr4) & X86_CR4_PGE)) - svm_flush_tlb_current(vcpu); - vcpu->arch.cr4 = cr4; if (!npt_enabled) { cr4 |= X86_CR4_PAE; @@ -2864,7 +2860,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr_info->index) { case MSR_AMD64_TSC_RATIO: if (!msr_info->host_initiated && - !guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR)) return 1; msr_info->data = svm->tsc_ratio_msr; break; @@ -2940,7 +2936,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD)) return 1; msr_info->data = svm->virt_spec_ctrl; @@ -3024,7 +3020,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) switch (ecx) { case MSR_AMD64_TSC_RATIO: - if (!guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR)) { if (!msr->host_initiated) return 1; @@ -3046,7 +3042,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) svm->tsc_ratio_msr = data; - if (guest_can_use(vcpu, X86_FEATURE_TSCRATEMSR) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSCRATEMSR) && is_guest_mode(vcpu)) nested_svm_update_tsc_ratio_msr(vcpu); @@ -3091,7 +3087,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_VIRT_SSBD)) return 1; if (data & ~SPEC_CTRL_SSBD) @@ -3263,7 +3259,7 @@ static int invpcid_interception(struct kvm_vcpu *vcpu) unsigned long type; gva_t gva; - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -3533,6 +3529,21 @@ static void svm_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, *error_code = 0; } +static void svm_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, + u32 *error_code) +{ + struct vmcb_control_area *control = &to_svm(vcpu)->vmcb->control; + + *intr_info = control->event_inj; + + if ((*intr_info & SVM_EXITINTINFO_VALID) && + (*intr_info & SVM_EXITINTINFO_VALID_ERR)) + *error_code = control->event_inj_err; + else + *error_code = 0; + +} + static int svm_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) { struct vcpu_svm *svm = to_svm(vcpu); @@ -4392,27 +4403,17 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * XSS on VM-Enter/VM-Exit. Failure to do so would effectively give * the guest read/write access to the host's XSS. */ - if (boot_cpu_has(X86_FEATURE_XSAVE) && - boot_cpu_has(X86_FEATURE_XSAVES) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) - kvm_governed_feature_set(vcpu, X86_FEATURE_XSAVES); - - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_NRIPS); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_TSCRATEMSR); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_LBRV); + guest_cpu_cap_change(vcpu, X86_FEATURE_XSAVES, + boot_cpu_has(X86_FEATURE_XSAVES) && + guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)); /* * Intercept VMLOAD if the vCPU model is Intel in order to emulate that * VMLOAD drops bits 63:32 of SYSENTER (ignoring the fact that exposing * SVM on Intel is bonkers and extremely unlikely to work). */ - if (!guest_cpuid_is_intel_compatible(vcpu)) - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); - - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PAUSEFILTER); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_PFTHRESHOLD); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VGIF); - kvm_governed_feature_check_and_set(vcpu, X86_FEATURE_VNMI); + if (guest_cpuid_is_intel_compatible(vcpu)) + guest_cpu_cap_clear(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD); svm_recalc_instruction_intercepts(vcpu, svm); @@ -4422,7 +4423,7 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0, - !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + !!guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); if (sev_guest(vcpu->kvm)) sev_vcpu_after_set_cpuid(svm); @@ -4673,7 +4674,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram) * responsible for ensuring nested SVM and SMIs are mutually exclusive. */ - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return 1; smram->smram64.svm_guest_flag = 1; @@ -4720,14 +4721,14 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram) const struct kvm_smram_state_64 *smram64 = &smram->smram64; - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return 0; /* Non-zero if SMI arrived while vCPU was in guest mode. */ if (!smram64->svm_guest_flag) return 0; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SVM)) return 1; if (!(smram64->efer & EFER_SVME)) @@ -4790,9 +4791,15 @@ static void svm_enable_smi_window(struct kvm_vcpu *vcpu) static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { + struct vcpu_svm *svm = to_svm(vcpu); bool smep, smap, is_user; u64 error_code; + /* Check that emulation is possible during event vectoring */ + if ((svm->vmcb->control.exit_int_info & SVM_EXITINTINFO_TYPE_MASK) && + !kvm_can_emulate_event_vectoring(emul_type)) + return X86EMUL_UNHANDLEABLE_VECTORING; + /* Emulation is always possible when KVM has access to all guest state. */ if (!sev_guest(vcpu->kvm)) return X86EMUL_CONTINUE; @@ -4889,7 +4896,7 @@ static int svm_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, * In addition, don't apply the erratum workaround if the #NPF occurred * while translating guest page tables (see below). */ - error_code = to_svm(vcpu)->vmcb->control.exit_info_1; + error_code = svm->vmcb->control.exit_info_1; if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) goto resume_guest; @@ -5077,6 +5084,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .required_apicv_inhibits = AVIC_REQUIRED_APICV_INHIBITS, .get_exit_info = svm_get_exit_info, + .get_entry_info = svm_get_entry_info, .vcpu_after_set_cpuid = svm_vcpu_after_set_cpuid, @@ -5328,7 +5336,7 @@ static __init int svm_hardware_setup(void) /* Force VM NPT level equal to the host's paging level */ kvm_configure_mmu(npt_enabled, get_npt_level(), get_npt_level(), PG_LEVEL_1G); - pr_info("Nested Paging %sabled\n", npt_enabled ? "en" : "dis"); + pr_info("Nested Paging %s\n", str_enabled_disabled(npt_enabled)); /* Setup shadow_me_value and shadow_me_mask */ kvm_mmu_set_me_spte_mask(sme_me_mask, sme_me_mask); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 43fa6a16eb19..9d7cdb8fbf87 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -358,39 +358,32 @@ static __always_inline struct kvm_sev_info *to_kvm_sev_info(struct kvm *kvm) return &to_kvm_svm(kvm)->sev_info; } +#ifdef CONFIG_KVM_AMD_SEV static __always_inline bool sev_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->active; -#else - return false; -#endif } - static __always_inline bool sev_es_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return sev->es_active && !WARN_ON_ONCE(!sev->active); -#else - return false; -#endif } static __always_inline bool sev_snp_guest(struct kvm *kvm) { -#ifdef CONFIG_KVM_AMD_SEV struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; return (sev->vmsa_features & SVM_SEV_FEAT_SNP_ACTIVE) && !WARN_ON_ONCE(!sev_es_guest(kvm)); +} #else - return false; +#define sev_guest(kvm) false +#define sev_es_guest(kvm) false +#define sev_snp_guest(kvm) false #endif -} static inline bool ghcb_gpa_is_registered(struct vcpu_svm *svm, u64 val) { @@ -502,7 +495,7 @@ static inline bool svm_is_intercept(struct vcpu_svm *svm, int bit) static inline bool nested_vgif_enabled(struct vcpu_svm *svm) { - return guest_can_use(&svm->vcpu, X86_FEATURE_VGIF) && + return guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_VGIF) && (svm->nested.ctl.int_ctl & V_GIF_ENABLE_MASK); } @@ -554,7 +547,7 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) static inline bool nested_vnmi_enabled(struct vcpu_svm *svm) { - return guest_can_use(&svm->vcpu, X86_FEATURE_VNMI) && + return guest_cpu_cap_has(&svm->vcpu, X86_FEATURE_VNMI) && (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK); } diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index d3aeffd6ae75..0b844cb97978 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -22,15 +22,22 @@ TRACE_EVENT(kvm_entry, __field( unsigned int, vcpu_id ) __field( unsigned long, rip ) __field( bool, immediate_exit ) + __field( u32, intr_info ) + __field( u32, error_code ) ), TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; __entry->rip = kvm_rip_read(vcpu); __entry->immediate_exit = force_immediate_exit; + + kvm_x86_call(get_entry_info)(vcpu, &__entry->intr_info, + &__entry->error_code); ), - TP_printk("vcpu %u, rip 0x%lx%s", __entry->vcpu_id, __entry->rip, + TP_printk("vcpu %u, rip 0x%lx intr_info 0x%08x error_code 0x%08x%s", + __entry->vcpu_id, __entry->rip, + __entry->intr_info, __entry->error_code, __entry->immediate_exit ? "[immediate exit]" : "") ); @@ -308,12 +315,14 @@ TRACE_EVENT(name, \ __field( u32, intr_info ) \ __field( u32, error_code ) \ __field( unsigned int, vcpu_id ) \ + __field( u64, requests ) \ ), \ \ TP_fast_assign( \ __entry->guest_rip = kvm_rip_read(vcpu); \ __entry->isa = isa; \ __entry->vcpu_id = vcpu->vcpu_id; \ + __entry->requests = READ_ONCE(vcpu->requests); \ kvm_x86_call(get_exit_info)(vcpu, \ &__entry->exit_reason, \ &__entry->info1, \ @@ -323,11 +332,13 @@ TRACE_EVENT(name, \ ), \ \ TP_printk("vcpu %u reason %s%s%s rip 0x%lx info1 0x%016llx " \ - "info2 0x%016llx intr_info 0x%08x error_code 0x%08x", \ + "info2 0x%016llx intr_info 0x%08x error_code 0x%08x " \ + "requests 0x%016llx", \ __entry->vcpu_id, \ kvm_print_exit_reason(__entry->exit_reason, __entry->isa), \ __entry->guest_rip, __entry->info1, __entry->info2, \ - __entry->intr_info, __entry->error_code) \ + __entry->intr_info, __entry->error_code, \ + __entry->requests) \ ) /* diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index a87407412615..11a339009781 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -42,7 +42,7 @@ static inline struct hv_enlightened_vmcs *nested_vmx_evmcs(struct vcpu_vmx *vmx) return vmx->nested.hv_evmcs; } -static inline bool guest_cpuid_has_evmcs(struct kvm_vcpu *vcpu) +static inline bool guest_cpu_cap_has_evmcs(struct kvm_vcpu *vcpu) { /* * eVMCS is exposed to the guest if Hyper-V is enabled in CPUID and diff --git a/arch/x86/kvm/vmx/hyperv_evmcs.h b/arch/x86/kvm/vmx/hyperv_evmcs.h index a543fccfc574..6536290f4274 100644 --- a/arch/x86/kvm/vmx/hyperv_evmcs.h +++ b/arch/x86/kvm/vmx/hyperv_evmcs.h @@ -6,7 +6,7 @@ #ifndef __KVM_X86_VMX_HYPERV_EVMCS_H #define __KVM_X86_VMX_HYPERV_EVMCS_H -#include <asm/hyperv-tlfs.h> +#include <hyperv/hvhdk.h> #include "capabilities.h" #include "vmcs12.h" diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c index 92d35cc6cd15..2427f918e763 100644 --- a/arch/x86/kvm/vmx/main.c +++ b/arch/x86/kvm/vmx/main.c @@ -100,7 +100,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .load_eoi_exitmap = vmx_load_eoi_exitmap, .apicv_pre_state_restore = vmx_apicv_pre_state_restore, .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS, - .hwapic_irr_update = vmx_hwapic_irr_update, .hwapic_isr_update = vmx_hwapic_isr_update, .sync_pir_to_irr = vmx_sync_pir_to_irr, .deliver_interrupt = vmx_deliver_interrupt, @@ -111,6 +110,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .get_mt_mask = vmx_get_mt_mask, .get_exit_info = vmx_get_exit_info, + .get_entry_info = vmx_get_entry_info, .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid, @@ -126,7 +126,7 @@ struct kvm_x86_ops vt_x86_ops __initdata = { .check_intercept = vmx_check_intercept, .handle_exit_irqoff = vmx_handle_exit_irqoff, - .cpu_dirty_log_size = PML_ENTITY_NUM, + .cpu_dirty_log_size = PML_LOG_NR_ENTRIES, .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging, .nested_ops = &vmx_nested_ops, diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index aa78b6f38dfe..8a7af02d466e 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -257,7 +257,7 @@ static bool nested_evmcs_handle_vmclear(struct kvm_vcpu *vcpu, gpa_t vmptr) * 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) || + if (!guest_cpu_cap_has_evmcs(vcpu) || !evmptr_is_valid(nested_get_evmptr(vcpu))) return false; @@ -2089,7 +2089,7 @@ static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld( bool evmcs_gpa_changed = false; u64 evmcs_gpa; - if (likely(!guest_cpuid_has_evmcs(vcpu))) + if (likely(!guest_cpu_cap_has_evmcs(vcpu))) return EVMPTRLD_DISABLED; evmcs_gpa = nested_get_evmptr(vcpu); @@ -2992,7 +2992,7 @@ static int nested_vmx_check_controls(struct kvm_vcpu *vcpu, return -EINVAL; #ifdef CONFIG_KVM_HYPERV - if (guest_cpuid_has_evmcs(vcpu)) + if (guest_cpu_cap_has_evmcs(vcpu)) return nested_evmcs_check_controls(vmcs12); #endif @@ -3287,7 +3287,7 @@ static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu) * L2 was running), map it here to make sure vmcs12 changes are * properly reflected. */ - if (guest_cpuid_has_evmcs(vcpu) && + if (guest_cpu_cap_has_evmcs(vcpu) && vmx->nested.hv_evmcs_vmptr == EVMPTR_MAP_PENDING) { enum nested_evmptrld_status evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, false); @@ -3442,7 +3442,7 @@ static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa) if (!nested_cpu_has_pml(vmcs12)) return 0; - if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) { + if (vmcs12->guest_pml_index >= PML_LOG_NR_ENTRIES) { vmx->nested.pml_full = true; return 1; } @@ -3481,14 +3481,6 @@ static int nested_vmx_check_permission(struct kvm_vcpu *vcpu) return 1; } -static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu) -{ - u8 rvi = vmx_get_rvi(); - u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI); - - return ((rvi & 0xf0) > (vppr & 0xf0)); -} - static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12); @@ -3508,7 +3500,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx = to_vmx(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu); enum vm_entry_failure_code entry_failure_code; - bool evaluate_pending_interrupts; union vmx_exit_reason exit_reason = { .basic = EXIT_REASON_INVALID_STATE, .failed_vmentry = 1, @@ -3527,13 +3518,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, kvm_service_local_tlb_flush_requests(vcpu); - evaluate_pending_interrupts = exec_controls_get(vmx) & - (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING); - if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu)) - evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu); - if (!evaluate_pending_interrupts) - evaluate_pending_interrupts |= kvm_apic_has_pending_init_or_sipi(vcpu); - if (!vmx->nested.nested_run_pending || !(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL); @@ -3616,9 +3600,13 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, * Re-evaluate pending events if L1 had a pending IRQ/NMI/INIT/SIPI * when it executed VMLAUNCH/VMRESUME, as entering non-root mode can * effectively unblock various events, e.g. INIT/SIPI cause VM-Exit - * unconditionally. + * unconditionally. Take care to pull data from vmcs01 as appropriate, + * e.g. when checking for interrupt windows, as vmcs02 is now loaded. */ - if (unlikely(evaluate_pending_interrupts)) + if ((__exec_controls_get(&vmx->vmcs01) & (CPU_BASED_INTR_WINDOW_EXITING | + CPU_BASED_NMI_WINDOW_EXITING)) || + kvm_apic_has_pending_init_or_sipi(vcpu) || + kvm_apic_has_interrupt(vcpu)) kvm_make_request(KVM_REQ_EVENT, vcpu); /* @@ -3751,14 +3739,6 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch) if (unlikely(status != NVMX_VMENTRY_SUCCESS)) goto vmentry_failed; - /* Emulate processing of posted interrupts on VM-Enter. */ - if (nested_cpu_has_posted_intr(vmcs12) && - kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) { - vmx->nested.pi_pending = true; - kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv); - } - /* Hide L1D cache contents from the nested guest. */ vmx->vcpu.arch.l1tf_flush_l1d = true; @@ -4220,13 +4200,25 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) */ bool block_nested_exceptions = vmx->nested.nested_run_pending; /* - * New events (not exceptions) are only recognized at instruction + * Events that don't require injection, i.e. that are virtualized by + * hardware, aren't blocked by a pending VM-Enter as KVM doesn't need + * to regain control in order to deliver the event, and hardware will + * handle event ordering, e.g. with respect to injected exceptions. + * + * But, new events (not exceptions) are only recognized at instruction * boundaries. If an event needs reinjection, then KVM is handling a - * VM-Exit that occurred _during_ instruction execution; new events are - * blocked until the instruction completes. + * VM-Exit that occurred _during_ instruction execution; new events, + * irrespective of whether or not they're injected, are blocked until + * the instruction completes. + */ + bool block_non_injected_events = kvm_event_needs_reinjection(vcpu); + /* + * Inject events are blocked by nested VM-Enter, as KVM is responsible + * for managing priority between concurrent events, i.e. KVM needs to + * wait until after VM-Enter completes to deliver injected events. */ bool block_nested_events = block_nested_exceptions || - kvm_event_needs_reinjection(vcpu); + block_non_injected_events; if (lapic_in_kernel(vcpu) && test_bit(KVM_APIC_INIT, &apic->pending_events)) { @@ -4338,18 +4330,26 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) { int irq; - if (block_nested_events) - return -EBUSY; - if (!nested_exit_on_intr(vcpu)) + if (!nested_exit_on_intr(vcpu)) { + if (block_nested_events) + return -EBUSY; + goto no_vmexit; + } if (!nested_exit_intr_ack_set(vcpu)) { + if (block_nested_events) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0); return 0; } irq = kvm_cpu_get_extint(vcpu); if (irq != -1) { + if (block_nested_events) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); return 0; @@ -4368,11 +4368,22 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu) * and enabling posted interrupts requires ACK-on-exit. */ if (irq == vmx->nested.posted_intr_nv) { + /* + * Nested posted interrupts are delivered via RVI, i.e. + * aren't injected by KVM, and so can be queued even if + * manual event injection is disallowed. + */ + if (block_non_injected_events) + return -EBUSY; + vmx->nested.pi_pending = true; kvm_apic_clear_irr(vcpu, irq); goto no_vmexit; } + if (block_nested_events) + return -EBUSY; + nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR | irq, 0); @@ -5015,7 +5026,7 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, * doesn't isolate different VMCSs, i.e. in this case, doesn't provide * separate modes for L2 vs L1. */ - if (guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL)) indirect_branch_prediction_barrier(); /* Update any VMCS fields that might have changed while L2 ran */ @@ -5050,6 +5061,11 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason, kvm_make_request(KVM_REQ_APICV_UPDATE, vcpu); } + if (vmx->nested.update_vmcs01_hwapic_isr) { + vmx->nested.update_vmcs01_hwapic_isr = false; + kvm_apic_update_hwapic_isr(vcpu); + } + if ((vm_exit_reason != -1) && (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))) vmx->nested.need_vmcs12_to_shadow_sync = true; @@ -6279,7 +6295,7 @@ static bool nested_vmx_exit_handled_encls(struct kvm_vcpu *vcpu, { u32 encls_leaf; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SGX) || + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || !nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENCLS_EXITING)) return false; @@ -6617,7 +6633,7 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu, vmx = to_vmx(vcpu); vmcs12 = get_vmcs12(vcpu); - if (guest_can_use(vcpu, X86_FEATURE_VMX) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) && (vmx->nested.vmxon || vmx->nested.smm.vmxon)) { kvm_state.hdr.vmx.vmxon_pa = vmx->nested.vmxon_ptr; kvm_state.hdr.vmx.vmcs12_pa = vmx->nested.current_vmptr; @@ -6758,7 +6774,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, if (kvm_state->flags & ~KVM_STATE_NESTED_EVMCS) return -EINVAL; } else { - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return -EINVAL; if (!page_address_valid(vcpu, kvm_state->hdr.vmx.vmxon_pa)) @@ -6792,7 +6808,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu, return -EINVAL; if ((kvm_state->flags & KVM_STATE_NESTED_EVMCS) && - (!guest_can_use(vcpu, X86_FEATURE_VMX) || + (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX) || !vmx->nested.enlightened_vmcs_enabled)) return -EINVAL; diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 9c9d4a336166..77012b2eca0e 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -110,7 +110,7 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu, static inline u64 vcpu_get_perf_capabilities(struct kvm_vcpu *vcpu) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return 0; return vcpu->arch.perf_capabilities; @@ -160,7 +160,7 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr) ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT; break; case MSR_IA32_DS_AREA: - ret = guest_cpuid_has(vcpu, X86_FEATURE_DS); + ret = guest_cpu_cap_has(vcpu, X86_FEATURE_DS); break; case MSR_PEBS_DATA_CFG: perf_capabilities = vcpu_get_perf_capabilities(vcpu); diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index b352a3ba7354..9961e07cf071 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -122,7 +122,7 @@ static int sgx_inject_fault(struct kvm_vcpu *vcpu, gva_t gva, int trapnr) * likely than a bad userspace address. */ if ((trapnr == PF_VECTOR || !boot_cpu_has(X86_FEATURE_SGX2)) && - guest_cpuid_has(vcpu, X86_FEATURE_SGX2)) { + guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2)) { memset(&ex, 0, sizeof(ex)); ex.vector = PF_VECTOR; ex.error_code = PFERR_PRESENT_MASK | PFERR_WRITE_MASK | @@ -365,7 +365,7 @@ static inline bool encls_leaf_enabled_in_guest(struct kvm_vcpu *vcpu, u32 leaf) return true; if (leaf >= EAUG && leaf <= EMODT) - return guest_cpuid_has(vcpu, X86_FEATURE_SGX2); + return guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2); return false; } @@ -381,8 +381,8 @@ int handle_encls(struct kvm_vcpu *vcpu) { u32 leaf = (u32)kvm_rax_read(vcpu); - if (!enable_sgx || !guest_cpuid_has(vcpu, X86_FEATURE_SGX) || - !guest_cpuid_has(vcpu, X86_FEATURE_SGX1)) { + if (!enable_sgx || !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) || + !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX1)) { kvm_queue_exception(vcpu, UD_VECTOR); } else if (!encls_leaf_enabled_in_guest(vcpu, leaf) || !sgx_enabled_in_guest_bios(vcpu) || !is_paging(vcpu)) { @@ -479,15 +479,15 @@ void vmx_write_encls_bitmap(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (!cpu_has_vmx_encls_vmexit()) return; - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX) && sgx_enabled_in_guest_bios(vcpu)) { - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX1)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX1)) { bitmap &= ~GENMASK_ULL(ETRACK, ECREATE); if (sgx_intercept_encls_ecreate(vcpu)) bitmap |= (1 << ECREATE); } - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX2)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX2)) bitmap &= ~GENMASK_ULL(EMODT, EAUG); /* diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 893366e53732..f72835e85b6d 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -1636,7 +1636,8 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data) * result in a #GP unless the same write also clears TraceEn. */ if ((vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) && - ((vmx->pt_desc.guest.ctl ^ data) & ~RTIT_CTL_TRACEEN)) + (data & RTIT_CTL_TRACEEN) && + data != vmx->pt_desc.guest.ctl) return 1; /* @@ -1705,6 +1706,12 @@ int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, kvm_queue_exception(vcpu, UD_VECTOR); return X86EMUL_PROPAGATE_FAULT; } + + /* Check that emulation is possible during event vectoring */ + if ((to_vmx(vcpu)->idt_vectoring_info & VECTORING_INFO_VALID_MASK) && + !kvm_can_emulate_event_vectoring(emul_type)) + return X86EMUL_UNHANDLEABLE_VECTORING; + return X86EMUL_CONTINUE; } @@ -1908,8 +1915,8 @@ static void vmx_setup_uret_msrs(struct vcpu_vmx *vmx) vmx_setup_uret_msr(vmx, MSR_EFER, update_transition_efer(vmx)); vmx_setup_uret_msr(vmx, MSR_TSC_AUX, - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(&vmx->vcpu, X86_FEATURE_RDPID)); + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(&vmx->vcpu, X86_FEATURE_RDPID)); /* * hle=0, rtm=0, tsx_ctrl=1 can be found with some combinations of new @@ -2062,7 +2069,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; msr_info->data = vmcs_read64(GUEST_BNDCFGS); break; @@ -2078,13 +2085,13 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_SGXLEPUBKEYHASH0 ... MSR_IA32_SGXLEPUBKEYHASH3: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) return 1; msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, &msr_info->data)) @@ -2097,7 +2104,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * sanity checking and refuse to boot. Filter all unsupported * features out. */ - if (!msr_info->host_initiated && guest_cpuid_has_evmcs(vcpu)) + if (!msr_info->host_initiated && guest_cpu_cap_has_evmcs(vcpu)) nested_evmcs_filter_control_msr(vcpu, msr_info->index, &msr_info->data); #endif @@ -2167,7 +2174,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu, u64 data) { #ifdef CONFIG_X86_64 - if (!guest_cpuid_has(vcpu, X86_FEATURE_LM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return (u32)data; #endif return (unsigned long)data; @@ -2178,7 +2185,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated u64 debugctl = 0; if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) && - (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) + (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))) debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT; if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) && @@ -2282,7 +2289,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_IA32_BNDCFGS: if (!kvm_mpx_supported() || (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_MPX))) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MPX))) return 1; if (is_noncanonical_msr_address(data & PAGE_MASK, vcpu) || (data & MSR_IA32_BNDCFGS_RSVD)) @@ -2384,7 +2391,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) * behavior, but it's close enough. */ if (!msr_info->host_initiated && - (!guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC) || + (!guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC) || ((vmx->msr_ia32_feature_control & FEAT_CTL_LOCKED) && !(vmx->msr_ia32_feature_control & FEAT_CTL_SGX_LC_ENABLED)))) return 1; @@ -2394,7 +2401,7 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ - if (!guest_can_use(vcpu, X86_FEATURE_VMX)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) return 1; return vmx_set_vmx_msr(vcpu, msr_index, data); case MSR_IA32_RTIT_CTL: @@ -2468,9 +2475,9 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((data & PERF_CAP_PEBS_MASK) != (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK)) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_DS)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DS)) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_DTES64)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_DTES64)) return 1; if (!cpuid_model_is_consistent(vcpu)) return 1; @@ -4590,10 +4597,7 @@ vmx_adjust_secondary_exec_control(struct vcpu_vmx *vmx, u32 *exec_control, bool __enabled; \ \ if (cpu_has_vmx_##name()) { \ - if (kvm_is_governed_feature(X86_FEATURE_##feat_name)) \ - __enabled = guest_can_use(__vcpu, X86_FEATURE_##feat_name); \ - else \ - __enabled = guest_cpuid_has(__vcpu, X86_FEATURE_##feat_name); \ + __enabled = guest_cpu_cap_has(__vcpu, X86_FEATURE_##feat_name); \ vmx_adjust_secondary_exec_control(vmx, exec_control, SECONDARY_EXEC_##ctrl_name,\ __enabled, exiting); \ } \ @@ -4669,8 +4673,8 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx) */ if (cpu_has_vmx_rdtscp()) { bool rdpid_or_rdtscp_enabled = - guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) || - guest_cpuid_has(vcpu, X86_FEATURE_RDPID); + guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) || + guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID); vmx_adjust_secondary_exec_control(vmx, &exec_control, SECONDARY_EXEC_ENABLE_RDTSCP, @@ -4820,7 +4824,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) if (enable_pml) { vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg)); - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } vmx_write_encls_bitmap(&vmx->vcpu, NULL); @@ -5959,7 +5963,7 @@ static int handle_invpcid(struct kvm_vcpu *vcpu) } operand; int gpr_index; - if (!guest_cpuid_has(vcpu, X86_FEATURE_INVPCID)) { + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_INVPCID)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -6049,7 +6053,7 @@ static int handle_preemption_timer(struct kvm_vcpu *vcpu) /* * When nested=0, all VMX instruction VM Exits filter here. The handlers - * are overwritten by nested_vmx_setup() when nested=1. + * are overwritten by nested_vmx_hardware_setup() when nested=1. */ static int handle_vmx_instruction(struct kvm_vcpu *vcpu) { @@ -6191,6 +6195,15 @@ void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, } } +void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code) +{ + *intr_info = vmcs_read32(VM_ENTRY_INTR_INFO_FIELD); + if (is_exception_with_error_code(*intr_info)) + *error_code = vmcs_read32(VM_ENTRY_EXCEPTION_ERROR_CODE); + else + *error_code = 0; +} + static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) { if (vmx->pml_pg) { @@ -6202,32 +6215,40 @@ static void vmx_destroy_pml_buffer(struct vcpu_vmx *vmx) static void vmx_flush_pml_buffer(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); + u16 pml_idx, pml_tail_index; u64 *pml_buf; - u16 pml_idx; + int i; pml_idx = vmcs_read16(GUEST_PML_INDEX); /* Do nothing if PML buffer is empty */ - if (pml_idx == (PML_ENTITY_NUM - 1)) + if (pml_idx == PML_HEAD_INDEX) return; + /* + * PML index always points to the next available PML buffer entity + * unless PML log has just overflowed. + */ + pml_tail_index = (pml_idx >= PML_LOG_NR_ENTRIES) ? 0 : pml_idx + 1; - /* PML index always points to next available PML buffer entity */ - if (pml_idx >= PML_ENTITY_NUM) - pml_idx = 0; - else - pml_idx++; - + /* + * PML log is written backwards: the CPU first writes the entry 511 + * then the entry 510, and so on. + * + * Read the entries in the same order they were written, to ensure that + * the dirty ring is filled in the same order the CPU wrote them. + */ pml_buf = page_address(vmx->pml_pg); - for (; pml_idx < PML_ENTITY_NUM; pml_idx++) { + + for (i = PML_HEAD_INDEX; i >= pml_tail_index; i--) { u64 gpa; - gpa = pml_buf[pml_idx]; + gpa = pml_buf[i]; WARN_ON(gpa & (PAGE_SIZE - 1)); kvm_vcpu_mark_page_dirty(vcpu, gpa >> PAGE_SHIFT); } /* reset PML index */ - vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1); + vmcs_write16(GUEST_PML_INDEX, PML_HEAD_INDEX); } static void vmx_dump_sel(char *name, uint32_t sel) @@ -6543,33 +6564,15 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath) return 0; } - /* - * Note: - * Do not try to fix EXIT_REASON_EPT_MISCONFIG if it caused by - * delivery event since it indicates guest is accessing MMIO. - * The vm-exit can be triggered again after return to guest that - * will cause infinite loop. - */ if ((vectoring_info & VECTORING_INFO_VALID_MASK) && (exit_reason.basic != EXIT_REASON_EXCEPTION_NMI && exit_reason.basic != EXIT_REASON_EPT_VIOLATION && exit_reason.basic != EXIT_REASON_PML_FULL && exit_reason.basic != EXIT_REASON_APIC_ACCESS && exit_reason.basic != EXIT_REASON_TASK_SWITCH && - exit_reason.basic != EXIT_REASON_NOTIFY)) { - int ndata = 3; - - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; - vcpu->run->internal.data[0] = vectoring_info; - vcpu->run->internal.data[1] = exit_reason.full; - vcpu->run->internal.data[2] = vmx_get_exit_qual(vcpu); - if (exit_reason.basic == EXIT_REASON_EPT_MISCONFIG) { - vcpu->run->internal.data[ndata++] = - vmcs_read64(GUEST_PHYSICAL_ADDRESS); - } - vcpu->run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; - vcpu->run->internal.ndata = ndata; + exit_reason.basic != EXIT_REASON_NOTIFY && + exit_reason.basic != EXIT_REASON_EPT_MISCONFIG)) { + kvm_prepare_event_vectoring_exit(vcpu, INVALID_GPA); return 0; } @@ -6862,11 +6865,32 @@ void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu) read_unlock(&vcpu->kvm->mmu_lock); } -void vmx_hwapic_isr_update(int max_isr) +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr) { u16 status; u8 old; + /* + * If L2 is active, defer the SVI update until vmcs01 is loaded, as SVI + * is only relevant for if and only if Virtual Interrupt Delivery is + * enabled in vmcs12, and if VID is enabled then L2 EOIs affect L2's + * vAPIC, not L1's vAPIC. KVM must update vmcs01 on the next nested + * VM-Exit, otherwise L1 with run with a stale SVI. + */ + if (is_guest_mode(vcpu)) { + /* + * KVM is supposed to forward intercepted L2 EOIs to L1 if VID + * is enabled in vmcs12; as above, the EOIs affect L2's vAPIC. + * Note, userspace can stuff state while L2 is active; assert + * that VID is disabled if and only if the vCPU is in KVM_RUN + * to avoid false positives if userspace is setting APIC state. + */ + WARN_ON_ONCE(vcpu->wants_to_run && + nested_cpu_has_vid(get_vmcs12(vcpu))); + to_vmx(vcpu)->nested.update_vmcs01_hwapic_isr = true; + return; + } + if (max_isr == -1) max_isr = 0; @@ -6896,20 +6920,6 @@ static void vmx_set_rvi(int vector) } } -void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr) -{ - /* - * When running L2, updating RVI is only relevant when - * vmcs12 virtual-interrupt-delivery enabled. - * However, it can be enabled only when L1 also - * intercepts external-interrupts and in that case - * we should not update vmcs02 RVI but instead intercept - * interrupt. Therefore, do nothing when running L2. - */ - if (!is_guest_mode(vcpu)) - vmx_set_rvi(max_irr); -} - int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); @@ -7828,12 +7838,8 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) * to the guest. XSAVES depends on CR4.OSXSAVE, and CR4.OSXSAVE can be * set if and only if XSAVE is supported. */ - if (boot_cpu_has(X86_FEATURE_XSAVE) && - guest_cpuid_has(vcpu, X86_FEATURE_XSAVE)) - 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); + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVE)) + guest_cpu_cap_clear(vcpu, X86_FEATURE_XSAVES); vmx_setup_uret_msrs(vmx); @@ -7841,7 +7847,7 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmcs_set_secondary_exec_control(vmx, vmx_secondary_exec_control(vmx)); - if (guest_can_use(vcpu, X86_FEATURE_VMX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; @@ -7850,25 +7856,25 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) ~(FEAT_CTL_VMX_ENABLED_INSIDE_SMX | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX); - if (guest_can_use(vcpu, X86_FEATURE_VMX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_VMX)) nested_vmx_cr_fixed1_bits_update(vcpu); if (boot_cpu_has(X86_FEATURE_INTEL_PT) && - guest_cpuid_has(vcpu, X86_FEATURE_INTEL_PT)) + guest_cpu_cap_has(vcpu, X86_FEATURE_INTEL_PT)) update_intel_pt_cfg(vcpu); if (boot_cpu_has(X86_FEATURE_RTM)) { struct vmx_uret_msr *msr; msr = vmx_find_uret_msr(vmx, MSR_IA32_TSX_CTRL); if (msr) { - bool enabled = guest_cpuid_has(vcpu, X86_FEATURE_RTM); + bool enabled = guest_cpu_cap_has(vcpu, X86_FEATURE_RTM); vmx_set_guest_uret_msr(vmx, msr, enabled ? 0 : TSX_CTRL_RTM_DISABLE); } } if (kvm_cpu_cap_has(X86_FEATURE_XFD)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)); + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)); if (boot_cpu_has(X86_FEATURE_IBPB)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W, @@ -7876,17 +7882,17 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) if (boot_cpu_has(X86_FEATURE_FLUSH_L1D)) vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W, - !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)); + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)); set_cr4_guest_host_mask(vmx); vmx_write_encls_bitmap(vcpu, NULL); - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_ENABLED; else vmx->msr_ia32_feature_control_valid_bits &= ~FEAT_CTL_SGX_ENABLED; - if (guest_cpuid_has(vcpu, X86_FEATURE_SGX_LC)) + if (guest_cpu_cap_has(vcpu, X86_FEATURE_SGX_LC)) vmx->msr_ia32_feature_control_valid_bits |= FEAT_CTL_SGX_LC_ENABLED; else @@ -8597,7 +8603,7 @@ static void __vmx_exit(void) vmx_cleanup_l1d_flush(); } -static void vmx_exit(void) +static void __exit vmx_exit(void) { kvm_exit(); __vmx_exit(); diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 43f573f6ca46..8b111ce1087c 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -176,6 +176,7 @@ struct nested_vmx { bool reload_vmcs01_apic_access_page; bool update_vmcs01_cpu_dirty_logging; bool update_vmcs01_apicv_status; + bool update_vmcs01_hwapic_isr; /* * Enlightened VMCS has been enabled. It does not mean that L1 has to @@ -330,7 +331,10 @@ struct vcpu_vmx { bool ple_window_dirty; /* Support for PML */ -#define PML_ENTITY_NUM 512 +#define PML_LOG_NR_ENTRIES 512 + /* PML is written backwards: this is the first entry written by the CPU */ +#define PML_HEAD_INDEX (PML_LOG_NR_ENTRIES-1) + struct page *pml_pg; /* apic deadline value in host tsc */ diff --git a/arch/x86/kvm/vmx/vmx_onhyperv.h b/arch/x86/kvm/vmx/vmx_onhyperv.h index bba24ed99ee6..cdf8cbb69209 100644 --- a/arch/x86/kvm/vmx/vmx_onhyperv.h +++ b/arch/x86/kvm/vmx/vmx_onhyperv.h @@ -3,7 +3,7 @@ #ifndef __ARCH_X86_KVM_VMX_ONHYPERV_H__ #define __ARCH_X86_KVM_VMX_ONHYPERV_H__ -#include <asm/hyperv-tlfs.h> +#include <hyperv/hvhdk.h> #include <asm/mshyperv.h> #include <linux/jump_label.h> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h index a55981c5216e..ce3295a67c04 100644 --- a/arch/x86/kvm/vmx/x86_ops.h +++ b/arch/x86/kvm/vmx/x86_ops.h @@ -47,8 +47,7 @@ bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu); void vmx_migrate_timers(struct kvm_vcpu *vcpu); void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu); void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu); -void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr); -void vmx_hwapic_isr_update(int max_isr); +void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr); int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu); void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode, int trig_mode, int vector); @@ -104,8 +103,11 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap); int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr); int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr); u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio); + void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason, u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code); +void vmx_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code); + u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu); u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu); void vmx_write_tsc_offset(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index c79a8cc57ba4..8e77e61d4fbd 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -119,8 +119,6 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA)); static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE); #endif -static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS; - #define KVM_EXIT_HYPERCALL_VALID_MASK (1 << KVM_HC_MAP_GPA_RANGE) #define KVM_CAP_PMU_VALID_MASK KVM_PMU_CAP_DISABLE @@ -1179,7 +1177,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.xcr0 != kvm_host.xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); - if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != kvm_host.xss) wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss); } @@ -1188,7 +1186,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) - write_pkru(vcpu->arch.pkru); + wrpkru(vcpu->arch.pkru); } EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state); @@ -1202,7 +1200,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) { vcpu->arch.pkru = rdpkru(); if (vcpu->arch.pkru != vcpu->arch.host_pkru) - write_pkru(vcpu->arch.host_pkru); + wrpkru(vcpu->arch.host_pkru); } if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { @@ -1210,7 +1208,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.xcr0 != kvm_host.xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, kvm_host.xcr0); - if (guest_can_use(vcpu, X86_FEATURE_XSAVES) && + if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) && vcpu->arch.ia32_xss != kvm_host.xss) wrmsrl(MSR_IA32_XSS, kvm_host.xss); } @@ -1283,18 +1281,6 @@ int kvm_emulate_xsetbv(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_emulate_xsetbv); -bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) -{ - if (cr4 & cr4_reserved_bits) - return false; - - if (cr4 & vcpu->arch.cr4_guest_rsvd_bits) - return false; - - return true; -} -EXPORT_SYMBOL_GPL(__kvm_is_valid_cr4); - static bool kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) { return __kvm_is_valid_cr4(vcpu, cr4) && @@ -1516,10 +1502,10 @@ static u64 kvm_dr6_fixed(struct kvm_vcpu *vcpu) { u64 fixed = DR6_FIXED_1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_RTM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_RTM)) fixed |= DR6_RTM; - if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)) fixed |= DR6_BUS_LOCK; return fixed; } @@ -1695,20 +1681,20 @@ static int do_get_feature_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer) { - if (efer & EFER_AUTOIBRS && !guest_cpuid_has(vcpu, X86_FEATURE_AUTOIBRS)) + if (efer & EFER_AUTOIBRS && !guest_cpu_cap_has(vcpu, X86_FEATURE_AUTOIBRS)) return false; - if (efer & EFER_FFXSR && !guest_cpuid_has(vcpu, X86_FEATURE_FXSR_OPT)) + if (efer & EFER_FFXSR && !guest_cpu_cap_has(vcpu, X86_FEATURE_FXSR_OPT)) return false; - if (efer & EFER_SVME && !guest_cpuid_has(vcpu, X86_FEATURE_SVM)) + if (efer & EFER_SVME && !guest_cpu_cap_has(vcpu, X86_FEATURE_SVM)) return false; if (efer & (EFER_LME | EFER_LMA) && - !guest_cpuid_has(vcpu, X86_FEATURE_LM)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_LM)) return false; - if (efer & EFER_NX && !guest_cpuid_has(vcpu, X86_FEATURE_NX)) + if (efer & EFER_NX && !guest_cpu_cap_has(vcpu, X86_FEATURE_NX)) return false; return true; @@ -1850,8 +1836,8 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data, return 1; if (!host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; /* @@ -1908,8 +1894,8 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data, return 1; if (!host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) && - !guest_cpuid_has(vcpu, X86_FEATURE_RDPID)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID)) return 1; break; } @@ -2095,7 +2081,7 @@ EXPORT_SYMBOL_GPL(kvm_handle_invalid_op); static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn) { if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS) && - !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_MWAIT)) return kvm_handle_invalid_op(vcpu); pr_warn_once("%s instruction emulated as NOP!\n", insn); @@ -3767,13 +3753,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_ARCH_CAPABILITIES: if (!msr_info->host_initiated || - !guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) return KVM_MSR_RET_UNSUPPORTED; vcpu->arch.arch_capabilities = data; break; case MSR_IA32_PERF_CAPABILITIES: if (!msr_info->host_initiated || - !guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return KVM_MSR_RET_UNSUPPORTED; if (data & ~kvm_caps.supported_perf_cap) @@ -3797,11 +3783,11 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((!guest_has_pred_cmd_msr(vcpu))) return 1; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SPEC_CTRL) && - !guest_cpuid_has(vcpu, X86_FEATURE_AMD_IBPB)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) && + !guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBPB)) reserved_bits |= PRED_CMD_IBPB; - if (!guest_cpuid_has(vcpu, X86_FEATURE_SBPB)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_SBPB)) reserved_bits |= PRED_CMD_SBPB; } @@ -3822,7 +3808,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) } case MSR_IA32_FLUSH_CMD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D)) return 1; if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) @@ -3873,7 +3859,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_set_lapic_tscdeadline_msr(vcpu, data); break; case MSR_IA32_TSC_ADJUST: - if (guest_cpuid_has(vcpu, X86_FEATURE_TSC_ADJUST)) { + if (guest_cpu_cap_has(vcpu, X86_FEATURE_TSC_ADJUST)) { if (!msr_info->host_initiated) { s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr; adjust_tsc_offset_guest(vcpu, adj); @@ -3900,7 +3886,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT) && ((old_val ^ data) & MSR_IA32_MISC_ENABLE_MWAIT)) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_XMM3)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_XMM3)) return 1; vcpu->arch.ia32_misc_enable_msr = data; kvm_update_cpuid_runtime(vcpu); @@ -4077,12 +4063,12 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) kvm_pr_unimpl_wrmsr(vcpu, msr, data); break; case MSR_AMD64_OSVW_ID_LENGTH: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.length = data; break; case MSR_AMD64_OSVW_STATUS: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; vcpu->arch.osvw.status = data; break; @@ -4101,7 +4087,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) @@ -4111,7 +4097,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; if (data & ~kvm_guest_supported_xfd(vcpu)) @@ -4226,12 +4212,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = vcpu->arch.microcode_version; break; case MSR_IA32_ARCH_CAPABILITIES: - if (!guest_cpuid_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_ARCH_CAPABILITIES)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.arch_capabilities; break; case MSR_IA32_PERF_CAPABILITIES: - if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_PDCM)) return KVM_MSR_RET_UNSUPPORTED; msr_info->data = vcpu->arch.perf_capabilities; break; @@ -4432,12 +4418,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = 0xbe702111; break; case MSR_AMD64_OSVW_ID_LENGTH: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.length; break; case MSR_AMD64_OSVW_STATUS: - if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW)) + if (!guest_cpu_cap_has(vcpu, X86_FEATURE_OSVW)) return 1; msr_info->data = vcpu->arch.osvw.status; break; @@ -4456,14 +4442,14 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) #ifdef CONFIG_X86_64 case MSR_IA32_XFD: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.fpstate->xfd; break; case MSR_IA32_XFD_ERR: if (!msr_info->host_initiated && - !guest_cpuid_has(vcpu, X86_FEATURE_XFD)) + !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD)) return 1; msr_info->data = vcpu->arch.guest_fpu.xfd_err; @@ -4545,6 +4531,20 @@ static inline bool kvm_can_mwait_in_guest(void) boot_cpu_has(X86_FEATURE_ARAT); } +static u64 kvm_get_allowed_disable_exits(void) +{ + u64 r = KVM_X86_DISABLE_EXITS_PAUSE; + + if (!mitigate_smt_rsb) { + r |= KVM_X86_DISABLE_EXITS_HLT | + KVM_X86_DISABLE_EXITS_CSTATE; + + if (kvm_can_mwait_in_guest()) + r |= KVM_X86_DISABLE_EXITS_MWAIT; + } + return r; +} + #ifdef CONFIG_KVM_HYPERV static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 __user *cpuid_arg) @@ -4687,15 +4687,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: - r = KVM_X86_DISABLE_EXITS_PAUSE; - - if (!mitigate_smt_rsb) { - r |= KVM_X86_DISABLE_EXITS_HLT | - KVM_X86_DISABLE_EXITS_CSTATE; - - if (kvm_can_mwait_in_guest()) - r |= KVM_X86_DISABLE_EXITS_MWAIT; - } + r = kvm_get_allowed_disable_exits(); break; case KVM_CAP_X86_SMM: if (!IS_ENABLED(CONFIG_KVM_SMM)) @@ -5822,9 +5814,6 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, case KVM_CAP_ENFORCE_PV_FEATURE_CPUID: vcpu->arch.pv_cpuid.enforce = cap->args[0]; - if (vcpu->arch.pv_cpuid.enforce) - kvm_update_pv_runtime(vcpu); - return 0; default: return -EINVAL; @@ -6542,30 +6531,32 @@ split_irqchip_unlock: break; case KVM_CAP_X86_DISABLE_EXITS: r = -EINVAL; - if (cap->args[0] & ~KVM_X86_DISABLE_VALID_EXITS) + if (cap->args[0] & ~kvm_get_allowed_disable_exits()) break; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) - kvm->arch.pause_in_guest = true; + mutex_lock(&kvm->lock); + if (kvm->created_vcpus) + goto disable_exits_unlock; #define SMT_RSB_MSG "This processor is affected by the Cross-Thread Return Predictions vulnerability. " \ "KVM_CAP_X86_DISABLE_EXITS should only be used with SMT disabled or trusted guests." - if (!mitigate_smt_rsb) { - if (boot_cpu_has_bug(X86_BUG_SMT_RSB) && cpu_smt_possible() && - (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) - pr_warn_once(SMT_RSB_MSG); - - if ((cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) && - kvm_can_mwait_in_guest()) - kvm->arch.mwait_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) - kvm->arch.hlt_in_guest = true; - if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) - kvm->arch.cstate_in_guest = true; - } + if (!mitigate_smt_rsb && boot_cpu_has_bug(X86_BUG_SMT_RSB) && + cpu_smt_possible() && + (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE)) + pr_warn_once(SMT_RSB_MSG); + if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE) + kvm->arch.pause_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT) + kvm->arch.mwait_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT) + kvm->arch.hlt_in_guest = true; + if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE) + kvm->arch.cstate_in_guest = true; r = 0; +disable_exits_unlock: + mutex_unlock(&kvm->lock); break; case KVM_CAP_MSR_PLATFORM_INFO: kvm->arch.guest_can_read_msr_platform_info = cap->args[0]; @@ -8511,17 +8502,17 @@ static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt, static bool emulator_guest_has_movbe(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_MOVBE); } static bool emulator_guest_has_fxsr(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_FXSR); } static bool emulator_guest_has_rdpid(struct x86_emulate_ctxt *ctxt) { - return guest_cpuid_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); + return guest_cpu_cap_has(emul_to_vcpu(ctxt), X86_FEATURE_RDPID); } static bool emulator_guest_cpuid_is_intel_compatible(struct x86_emulate_ctxt *ctxt) @@ -8813,6 +8804,28 @@ void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit); +void kvm_prepare_event_vectoring_exit(struct kvm_vcpu *vcpu, gpa_t gpa) +{ + u32 reason, intr_info, error_code; + struct kvm_run *run = vcpu->run; + u64 info1, info2; + int ndata = 0; + + kvm_x86_call(get_exit_info)(vcpu, &reason, &info1, &info2, + &intr_info, &error_code); + + run->internal.data[ndata++] = info2; + run->internal.data[ndata++] = reason; + run->internal.data[ndata++] = info1; + run->internal.data[ndata++] = gpa; + run->internal.data[ndata++] = vcpu->arch.last_vmentry_cpu; + + run->exit_reason = KVM_EXIT_INTERNAL_ERROR; + run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV; + run->internal.ndata = ndata; +} +EXPORT_SYMBOL_GPL(kvm_prepare_event_vectoring_exit); + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; @@ -9085,6 +9098,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, if (r == X86EMUL_RETRY_INSTR || r == X86EMUL_PROPAGATE_FAULT) return 1; + if (kvm_unprotect_and_retry_on_failure(vcpu, cr2_or_gpa, + emulation_type)) + return 1; + + if (r == X86EMUL_UNHANDLEABLE_VECTORING) { + kvm_prepare_event_vectoring_exit(vcpu, cr2_or_gpa); + return 0; + } + WARN_ON_ONCE(r != X86EMUL_UNHANDLEABLE); return handle_emulation_failure(vcpu, emulation_type); } @@ -9773,10 +9795,6 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES)) kvm_caps.supported_xss = 0; -#define __kvm_cpu_cap_has(UNUSED_, f) kvm_cpu_cap_has(f) - cr4_reserved_bits = __cr4_reserved_bits(__kvm_cpu_cap_has, UNUSED_); -#undef __kvm_cpu_cap_has - if (kvm_caps.has_tsc_control) { /* * Make sure the user can only configure tsc_khz values that @@ -9979,17 +9997,19 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu) if (!is_64_bit_hypercall(vcpu)) ret = (u32)ret; kvm_rax_write(vcpu, ret); - ++vcpu->stat.hypercalls; return kvm_skip_emulated_instruction(vcpu); } -unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, - unsigned long a0, unsigned long a1, - unsigned long a2, unsigned long a3, - int op_64_bit, int cpl) +int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl, + int (*complete_hypercall)(struct kvm_vcpu *)) { unsigned long ret; + ++vcpu->stat.hypercalls; + trace_kvm_hypercall(nr, a0, a1, a2, a3); if (!op_64_bit) { @@ -10041,7 +10061,7 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, u64 gpa = a0, npages = a1, attrs = a2; ret = -KVM_ENOSYS; - if (!(vcpu->kvm->arch.hypercall_exit_enabled & (1 << KVM_HC_MAP_GPA_RANGE))) + if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) break; if (!PAGE_ALIGNED(gpa) || !npages || @@ -10052,6 +10072,13 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, vcpu->run->exit_reason = KVM_EXIT_HYPERCALL; vcpu->run->hypercall.nr = KVM_HC_MAP_GPA_RANGE; + /* + * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2) + * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that + * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting + * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU. + */ + vcpu->run->hypercall.ret = 0; vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; @@ -10060,8 +10087,7 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, vcpu->run->hypercall.flags |= KVM_EXIT_HYPERCALL_LONG_MODE; WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ); - vcpu->arch.complete_userspace_io = complete_hypercall_exit; - /* stat is incremented on completion. */ + vcpu->arch.complete_userspace_io = complete_hypercall; return 0; } default: @@ -10070,41 +10096,23 @@ unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, } out: - ++vcpu->stat.hypercalls; - return ret; + vcpu->run->hypercall.ret = ret; + return 1; } -EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall); +EXPORT_SYMBOL_GPL(____kvm_emulate_hypercall); int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) { - unsigned long nr, a0, a1, a2, a3, ret; - int op_64_bit; - int cpl; - if (kvm_xen_hypercall_enabled(vcpu->kvm)) return kvm_xen_hypercall(vcpu); if (kvm_hv_hypercall_enabled(vcpu)) return kvm_hv_hypercall(vcpu); - nr = kvm_rax_read(vcpu); - a0 = kvm_rbx_read(vcpu); - a1 = kvm_rcx_read(vcpu); - a2 = kvm_rdx_read(vcpu); - a3 = kvm_rsi_read(vcpu); - op_64_bit = is_64_bit_hypercall(vcpu); - cpl = kvm_x86_call(get_cpl)(vcpu); - - ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl); - if (nr == KVM_HC_MAP_GPA_RANGE && !ret) - /* MAP_GPA tosses the request to the user space. */ - return 0; - - if (!op_64_bit) - ret = (u32)ret; - kvm_rax_write(vcpu, ret); - - return kvm_skip_emulated_instruction(vcpu); + return __kvm_emulate_hypercall(vcpu, rax, rbx, rcx, rdx, rsi, + is_64_bit_hypercall(vcpu), + kvm_x86_call(get_cpl)(vcpu), + complete_hypercall_exit); } EXPORT_SYMBOL_GPL(kvm_emulate_hypercall); @@ -11463,6 +11471,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) struct kvm_run *kvm_run = vcpu->run; int r; + r = kvm_mmu_post_init_vm(vcpu->kvm); + if (r) + return r; + vcpu_load(vcpu); kvm_sigset_activate(vcpu); kvm_run->flags = 0; @@ -12276,9 +12288,6 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) goto free_emulate_ctxt; } - vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); - vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); - kvm_async_pf_hash_reset(vcpu); if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS)) { @@ -12301,6 +12310,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu) kvm_xen_init_vcpu(vcpu); vcpu_load(vcpu); + kvm_vcpu_after_set_cpuid(vcpu); kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz); kvm_vcpu_reset(vcpu, false); kvm_init_mmu(vcpu); @@ -12731,6 +12741,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) "does not run without ignore_msrs=1, please report it to kvm@vger.kernel.org.\n"); } + once_init(&kvm->arch.nx_once); return 0; out_uninit_mmu: @@ -12740,11 +12751,6 @@ out: return ret; } -int kvm_arch_post_init_vm(struct kvm *kvm) -{ - return kvm_mmu_post_init_vm(kvm); -} - static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu) { vcpu_load(vcpu); @@ -12800,7 +12806,8 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *slot; - /* Called with kvm->slots_lock held. */ + lockdep_assert_held(&kvm->slots_lock); + if (WARN_ON(id >= KVM_MEM_SLOTS_NUM)) return ERR_PTR_USR(-EINVAL); @@ -12833,7 +12840,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, m.guest_phys_addr = gpa; m.userspace_addr = hva; m.memory_size = size; - r = __kvm_set_memory_region(kvm, &m); + r = kvm_set_internal_memslot(kvm, &m); if (r < 0) return ERR_PTR_USR(r); } @@ -12934,7 +12941,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, /* * Clear out the previous array pointers for the KVM_MR_MOVE case. The - * old arrays will be freed by __kvm_set_memory_region() if installing + * old arrays will be freed by kvm_set_memory_region() if installing * the new memslot is successful. */ memset(&slot->arch, 0, sizeof(slot->arch)); @@ -13027,6 +13034,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) return -EINVAL; + if (kvm_is_gfn_alias(kvm, new->base_gfn + new->npages - 1)) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); } diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index ec623d23d13d..91e50a513100 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -550,7 +550,6 @@ static inline void kvm_machine_check(void) void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu); void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu); int kvm_spec_ctrl_test_value(u64 value); -bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, struct x86_exception *e); int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva); @@ -577,6 +576,11 @@ enum kvm_msr_access { #define KVM_MSR_RET_UNSUPPORTED 2 #define KVM_MSR_RET_FILTERED 3 +static inline bool __kvm_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) +{ + return !(cr4 & vcpu->arch.cr4_guest_rsvd_bits); +} + #define __cr4_reserved_bits(__cpu_has, __c) \ ({ \ u64 __reserved_bits = CR4_RESERVED_BITS; \ @@ -612,4 +616,32 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size, unsigned int port, void *data, unsigned int count, int in); +static inline bool user_exit_on_hypercall(struct kvm *kvm, unsigned long hc_nr) +{ + return kvm->arch.hypercall_exit_enabled & BIT(hc_nr); +} + +int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr, + unsigned long a0, unsigned long a1, + unsigned long a2, unsigned long a3, + int op_64_bit, int cpl, + int (*complete_hypercall)(struct kvm_vcpu *)); + +#define __kvm_emulate_hypercall(_vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl, complete_hypercall) \ +({ \ + int __ret; \ + \ + __ret = ____kvm_emulate_hypercall(_vcpu, \ + kvm_##nr##_read(_vcpu), kvm_##a0##_read(_vcpu), \ + kvm_##a1##_read(_vcpu), kvm_##a2##_read(_vcpu), \ + kvm_##a3##_read(_vcpu), op_64_bit, cpl, \ + complete_hypercall); \ + \ + if (__ret > 0) \ + __ret = complete_hypercall(_vcpu); \ + __ret; \ +}) + +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu); + #endif |