diff options
Diffstat (limited to 'arch/x86/kvm')
29 files changed, 1430 insertions, 1066 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 599aebec2d52..123bf8b97a4b 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -60,12 +60,6 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted) return ret; } -/* - * This one is tied to SSB in the user API, and not - * visible in /proc/cpuinfo. - */ -#define KVM_X86_FEATURE_AMD_PSFD (13*32+28) /* Predictive Store Forwarding Disable */ - #define F feature_bit /* Scattered Flag - For features that are scattered by cpufeatures.h. */ @@ -266,7 +260,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e /* Update OSXSAVE bit */ if (boot_cpu_has(X86_FEATURE_XSAVE)) cpuid_entry_change(best, X86_FEATURE_OSXSAVE, - kvm_read_cr4_bits(vcpu, X86_CR4_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); @@ -275,7 +269,7 @@ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_e 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_read_cr4_bits(vcpu, X86_CR4_PKE)); + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE)); best = cpuid_entry2_find(entries, nent, 0xD, 0); if (best) @@ -420,7 +414,7 @@ static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2, * KVM_SET_CPUID{,2} again. To support this legacy behavior, check * whether the supplied CPUID data is equal to what's already set. */ - if (vcpu->arch.last_vmentry_cpu != -1) { + if (kvm_vcpu_has_run(vcpu)) { r = kvm_cpuid_check_equal(vcpu, e2, nent); if (r) return r; @@ -653,7 +647,7 @@ void kvm_set_cpu_caps(void) 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(AMX_TILE) | F(AMX_INT8) | F(AMX_BF16) | F(FLUSH_L1D) ); /* TSC_ADJUST and ARCH_CAPABILITIES are emulated in software. */ @@ -715,7 +709,7 @@ void kvm_set_cpu_caps(void) 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) | - __feature_bit(KVM_X86_FEATURE_AMD_PSFD) + F(AMD_PSFD) ); /* @@ -1002,7 +996,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function) entry->eax = entry->ebx = entry->ecx = 0; break; case 0xd: { - u64 permitted_xcr0 = kvm_caps.supported_xcr0 & xstate_get_guest_group_perm(); + u64 permitted_xcr0 = kvm_get_filtered_xcr0(); u64 permitted_xss = kvm_caps.supported_xss; entry->eax &= permitted_xcr0; diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index a20bec931764..936a397a08cd 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -1640,6 +1640,14 @@ static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; break; case VCPU_SREG_CS: + /* + * KVM uses "none" when loading CS as part of emulating Real + * Mode exceptions and IRET (handled above). In all other + * cases, loading CS without a control transfer is a KVM bug. + */ + if (WARN_ON_ONCE(transfer == X86_TRANSFER_NONE)) + goto exception; + if (!(seg_desc.type & 8)) goto exception; diff --git a/arch/x86/kvm/kvm_cache_regs.h b/arch/x86/kvm/kvm_cache_regs.h index 4c91f626c058..75eae9c4998a 100644 --- a/arch/x86/kvm/kvm_cache_regs.h +++ b/arch/x86/kvm/kvm_cache_regs.h @@ -4,7 +4,7 @@ #include <linux/kvm_host.h> -#define KVM_POSSIBLE_CR0_GUEST_BITS X86_CR0_TS +#define KVM_POSSIBLE_CR0_GUEST_BITS (X86_CR0_TS | X86_CR0_WP) #define KVM_POSSIBLE_CR4_GUEST_BITS \ (X86_CR4_PVI | X86_CR4_DE | X86_CR4_PCE | X86_CR4_OSFXSR \ | X86_CR4_OSXMMEXCPT | X86_CR4_PGE | X86_CR4_TSD | X86_CR4_FSGSBASE) @@ -157,6 +157,14 @@ static inline ulong kvm_read_cr0_bits(struct kvm_vcpu *vcpu, ulong mask) return vcpu->arch.cr0 & mask; } +static __always_inline bool kvm_is_cr0_bit_set(struct kvm_vcpu *vcpu, + unsigned long cr0_bit) +{ + BUILD_BUG_ON(!is_power_of_2(cr0_bit)); + + return !!kvm_read_cr0_bits(vcpu, cr0_bit); +} + static inline ulong kvm_read_cr0(struct kvm_vcpu *vcpu) { return kvm_read_cr0_bits(vcpu, ~0UL); @@ -171,6 +179,14 @@ static inline ulong kvm_read_cr4_bits(struct kvm_vcpu *vcpu, ulong mask) return vcpu->arch.cr4 & mask; } +static __always_inline bool kvm_is_cr4_bit_set(struct kvm_vcpu *vcpu, + unsigned long cr4_bit) +{ + BUILD_BUG_ON(!is_power_of_2(cr4_bit)); + + return !!kvm_read_cr4_bits(vcpu, cr4_bit); +} + static inline ulong kvm_read_cr3(struct kvm_vcpu *vcpu) { if (!kvm_register_is_available(vcpu, VCPU_EXREG_CR3)) diff --git a/arch/x86/kvm/kvm_onhyperv.c b/arch/x86/kvm/kvm_onhyperv.c index 482d6639ef88..ded0bd688c65 100644 --- a/arch/x86/kvm/kvm_onhyperv.c +++ b/arch/x86/kvm/kvm_onhyperv.c @@ -10,17 +10,22 @@ #include "hyperv.h" #include "kvm_onhyperv.h" +struct kvm_hv_tlb_range { + u64 start_gfn; + u64 pages; +}; + static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush, void *data) { - struct kvm_tlb_range *range = data; + struct kvm_hv_tlb_range *range = data; return hyperv_fill_flush_guest_mapping_list(flush, range->start_gfn, range->pages); } static inline int hv_remote_flush_root_tdp(hpa_t root_tdp, - struct kvm_tlb_range *range) + struct kvm_hv_tlb_range *range) { if (range) return hyperv_flush_guest_mapping_range(root_tdp, @@ -29,8 +34,8 @@ static inline int hv_remote_flush_root_tdp(hpa_t root_tdp, return hyperv_flush_guest_mapping(root_tdp); } -int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) +static int __hv_flush_remote_tlbs_range(struct kvm *kvm, + struct kvm_hv_tlb_range *range) { struct kvm_arch *kvm_arch = &kvm->arch; struct kvm_vcpu *vcpu; @@ -86,19 +91,29 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm, spin_unlock(&kvm_arch->hv_root_tdp_lock); return ret; } -EXPORT_SYMBOL_GPL(hv_remote_flush_tlb_with_range); -int hv_remote_flush_tlb(struct kvm *kvm) +int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, gfn_t nr_pages) +{ + struct kvm_hv_tlb_range range = { + .start_gfn = start_gfn, + .pages = nr_pages, + }; + + return __hv_flush_remote_tlbs_range(kvm, &range); +} +EXPORT_SYMBOL_GPL(hv_flush_remote_tlbs_range); + +int hv_flush_remote_tlbs(struct kvm *kvm) { - return hv_remote_flush_tlb_with_range(kvm, NULL); + return __hv_flush_remote_tlbs_range(kvm, NULL); } -EXPORT_SYMBOL_GPL(hv_remote_flush_tlb); +EXPORT_SYMBOL_GPL(hv_flush_remote_tlbs); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp) { struct kvm_arch *kvm_arch = &vcpu->kvm->arch; - if (kvm_x86_ops.tlb_remote_flush == hv_remote_flush_tlb) { + if (kvm_x86_ops.flush_remote_tlbs == hv_flush_remote_tlbs) { spin_lock(&kvm_arch->hv_root_tdp_lock); vcpu->arch.hv_root_tdp = root_tdp; if (root_tdp != kvm_arch->hv_root_tdp) diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h index 6272dabec02d..f9ca3e7432b2 100644 --- a/arch/x86/kvm/kvm_onhyperv.h +++ b/arch/x86/kvm/kvm_onhyperv.h @@ -7,12 +7,11 @@ #define __ARCH_X86_KVM_KVM_ONHYPERV_H__ #if IS_ENABLED(CONFIG_HYPERV) -int hv_remote_flush_tlb_with_range(struct kvm *kvm, - struct kvm_tlb_range *range); -int hv_remote_flush_tlb(struct kvm *kvm); +int hv_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, gfn_t nr_pages); +int hv_flush_remote_tlbs(struct kvm *kvm); void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp); #else /* !CONFIG_HYPERV */ -static inline int hv_remote_flush_tlb(struct kvm *kvm) +static inline int hv_flush_remote_tlbs(struct kvm *kvm) { return -EOPNOTSUPP; } diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 168c46fd8dd1..92d5a1924fc1 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -113,6 +113,8 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu); int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, u64 fault_address, char *insn, int insn_len); +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu); int kvm_mmu_load(struct kvm_vcpu *vcpu); void kvm_mmu_unload(struct kvm_vcpu *vcpu); @@ -132,7 +134,7 @@ static inline unsigned long kvm_get_pcid(struct kvm_vcpu *vcpu, gpa_t cr3) { BUILD_BUG_ON((X86_CR3_PCID_MASK & PAGE_MASK) != 0); - return kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE) + return kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE) ? cr3 & X86_CR3_PCID_MASK : 0; } @@ -153,6 +155,24 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu) vcpu->arch.mmu->root_role.level); } +static inline void kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + /* + * When EPT is enabled, KVM may passthrough CR0.WP to the guest, i.e. + * @mmu's snapshot of CR0.WP and thus all related paging metadata may + * be stale. Refresh CR0.WP and the metadata on-demand when checking + * for permission faults. Exempt nested MMUs, i.e. MMUs for shadowing + * nEPT and nNPT, as CR0.WP is ignored in both cases. Note, KVM does + * need to refresh nested_mmu, a.k.a. the walker used to translate L2 + * GVAs to GPAs, as that "MMU" needs to honor L2's CR0.WP. + */ + if (!tdp_enabled || mmu == &vcpu->arch.guest_mmu) + return; + + __kvm_mmu_refresh_passthrough_bits(vcpu, mmu); +} + /* * Check if a given access (described through the I/D, W/R and U/S bits of a * page fault error code pfec) causes a permission fault with the given PTE @@ -184,8 +204,12 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 implicit_access = access & PFERR_IMPLICIT_ACCESS; bool not_smap = ((rflags & X86_EFLAGS_AC) | implicit_access) == X86_EFLAGS_AC; int index = (pfec + (not_smap << PFERR_RSVD_BIT)) >> 1; - bool fault = (mmu->permissions[index] >> pte_access) & 1; u32 errcode = PFERR_PRESENT_MASK; + bool fault; + + kvm_mmu_refresh_passthrough_bits(vcpu, mmu); + + fault = (mmu->permissions[index] >> pte_access) & 1; WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK)); if (unlikely(mmu->pkru_mask)) { diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c8ebe542c565..c8961f45e3b1 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -125,17 +125,31 @@ module_param(dbg, bool, 0644); #define PTE_LIST_EXT 14 /* - * Slight optimization of cacheline layout, by putting `more' and `spte_count' - * at the start; then accessing it will only use one single cacheline for - * either full (entries==PTE_LIST_EXT) case or entries<=6. + * struct pte_list_desc is the core data structure used to implement a custom + * list for tracking a set of related SPTEs, e.g. all the SPTEs that map a + * given GFN when used in the context of rmaps. Using a custom list allows KVM + * to optimize for the common case where many GFNs will have at most a handful + * of SPTEs pointing at them, i.e. allows packing multiple SPTEs into a small + * memory footprint, which in turn improves runtime performance by exploiting + * cache locality. + * + * A list is comprised of one or more pte_list_desc objects (descriptors). + * Each individual descriptor stores up to PTE_LIST_EXT SPTEs. If a descriptor + * is full and a new SPTEs needs to be added, a new descriptor is allocated and + * becomes the head of the list. This means that by definitions, all tail + * descriptors are full. + * + * Note, the meta data fields are deliberately placed at the start of the + * structure to optimize the cacheline layout; accessing the descriptor will + * touch only a single cacheline so long as @spte_count<=6 (or if only the + * descriptors metadata is accessed). */ struct pte_list_desc { struct pte_list_desc *more; - /* - * Stores number of entries stored in the pte_list_desc. No need to be - * u64 but just for easier alignment. When PTE_LIST_EXT, means full. - */ - u64 spte_count; + /* The number of PTEs stored in _this_ descriptor. */ + u32 spte_count; + /* The number of PTEs stored in all tails of this descriptor. */ + u32 tail_count; u64 *sptes[PTE_LIST_EXT]; }; @@ -242,32 +256,35 @@ static struct kvm_mmu_role_regs vcpu_to_role_regs(struct kvm_vcpu *vcpu) return regs; } -static inline bool kvm_available_flush_tlb_with_range(void) +static unsigned long get_guest_cr3(struct kvm_vcpu *vcpu) { - return kvm_x86_ops.tlb_remote_flush_with_range; + return kvm_read_cr3(vcpu); } -static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, - struct kvm_tlb_range *range) +static inline unsigned long kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) { - int ret = -ENOTSUPP; - - if (range && kvm_x86_ops.tlb_remote_flush_with_range) - ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, range); + if (IS_ENABLED(CONFIG_RETPOLINE) && mmu->get_guest_pgd == get_guest_cr3) + return kvm_read_cr3(vcpu); - if (ret) - kvm_flush_remote_tlbs(kvm); + return mmu->get_guest_pgd(vcpu); } -void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, - u64 start_gfn, u64 pages) +static inline bool kvm_available_flush_remote_tlbs_range(void) { - struct kvm_tlb_range range; + return kvm_x86_ops.flush_remote_tlbs_range; +} - range.start_gfn = start_gfn; - range.pages = pages; +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, + gfn_t nr_pages) +{ + int ret = -EOPNOTSUPP; - kvm_flush_remote_tlbs_with_range(kvm, &range); + if (kvm_x86_ops.flush_remote_tlbs_range) + ret = static_call(kvm_x86_flush_remote_tlbs_range)(kvm, start_gfn, + nr_pages); + if (ret) + kvm_flush_remote_tlbs(kvm); } static gfn_t kvm_mmu_page_get_gfn(struct kvm_mmu_page *sp, int index); @@ -888,9 +905,9 @@ static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) untrack_possible_nx_huge_page(kvm, sp); } -static struct kvm_memory_slot * -gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn, - bool no_dirty_log) +static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, + gfn_t gfn, + bool no_dirty_log) { struct kvm_memory_slot *slot; @@ -929,53 +946,69 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte, desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; desc->spte_count = 2; + desc->tail_count = 0; rmap_head->val = (unsigned long)desc | 1; ++count; } else { rmap_printk("%p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - while (desc->spte_count == PTE_LIST_EXT) { - count += PTE_LIST_EXT; - if (!desc->more) { - desc->more = kvm_mmu_memory_cache_alloc(cache); - desc = desc->more; - desc->spte_count = 0; - break; - } - desc = desc->more; + count = desc->tail_count + desc->spte_count; + + /* + * If the previous head is full, allocate a new head descriptor + * as tail descriptors are always kept full. + */ + if (desc->spte_count == PTE_LIST_EXT) { + desc = kvm_mmu_memory_cache_alloc(cache); + desc->more = (struct pte_list_desc *)(rmap_head->val & ~1ul); + desc->spte_count = 0; + desc->tail_count = count; + rmap_head->val = (unsigned long)desc | 1; } - count += desc->spte_count; desc->sptes[desc->spte_count++] = spte; } return count; } -static void -pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, - struct pte_list_desc *desc, int i, - struct pte_list_desc *prev_desc) +static void pte_list_desc_remove_entry(struct kvm_rmap_head *rmap_head, + struct pte_list_desc *desc, int i) { - int j = desc->spte_count - 1; + struct pte_list_desc *head_desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); + int j = head_desc->spte_count - 1; + + /* + * The head descriptor should never be empty. A new head is added only + * when adding an entry and the previous head is full, and heads are + * removed (this flow) when they become empty. + */ + BUG_ON(j < 0); - desc->sptes[i] = desc->sptes[j]; - desc->sptes[j] = NULL; - desc->spte_count--; - if (desc->spte_count) + /* + * Replace the to-be-freed SPTE with the last valid entry from the head + * descriptor to ensure that tail descriptors are full at all times. + * Note, this also means that tail_count is stable for each descriptor. + */ + desc->sptes[i] = head_desc->sptes[j]; + head_desc->sptes[j] = NULL; + head_desc->spte_count--; + if (head_desc->spte_count) return; - if (!prev_desc && !desc->more) + + /* + * The head descriptor is empty. If there are no tail descriptors, + * nullify the rmap head to mark the list as emtpy, else point the rmap + * head at the next descriptor, i.e. the new head. + */ + if (!head_desc->more) rmap_head->val = 0; else - if (prev_desc) - prev_desc->more = desc->more; - else - rmap_head->val = (unsigned long)desc->more | 1; - mmu_free_pte_list_desc(desc); + rmap_head->val = (unsigned long)head_desc->more | 1; + mmu_free_pte_list_desc(head_desc); } static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; - struct pte_list_desc *prev_desc; int i; if (!rmap_head->val) { @@ -991,16 +1024,13 @@ static void pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) } else { rmap_printk("%p many->many\n", spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - prev_desc = NULL; while (desc) { for (i = 0; i < desc->spte_count; ++i) { if (desc->sptes[i] == spte) { - pte_list_desc_remove_entry(rmap_head, - desc, i, prev_desc); + pte_list_desc_remove_entry(rmap_head, desc, i); return; } } - prev_desc = desc; desc = desc->more; } pr_err("%s: %p many->many\n", __func__, spte); @@ -1047,7 +1077,6 @@ out: unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) { struct pte_list_desc *desc; - unsigned int count = 0; if (!rmap_head->val) return 0; @@ -1055,13 +1084,7 @@ unsigned int pte_list_count(struct kvm_rmap_head *rmap_head) return 1; desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); - - while (desc) { - count += desc->spte_count; - desc = desc->more; - } - - return count; + return desc->tail_count + desc->spte_count; } static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level, @@ -1073,14 +1096,6 @@ static struct kvm_rmap_head *gfn_to_rmap(gfn_t gfn, int level, return &slot->arch.rmap[level - PG_LEVEL_4K][idx]; } -static bool rmap_can_add(struct kvm_vcpu *vcpu) -{ - struct kvm_mmu_memory_cache *mc; - - mc = &vcpu->arch.mmu_pte_list_desc_cache; - return kvm_mmu_memory_cache_nr_free_objects(mc); -} - static void rmap_remove(struct kvm *kvm, u64 *spte) { struct kvm_memslots *slots; @@ -1479,7 +1494,7 @@ restart: } } - if (need_flush && kvm_available_flush_tlb_with_range()) { + if (need_flush && kvm_available_flush_remote_tlbs_range()) { kvm_flush_remote_tlbs_gfn(kvm, gfn, level); return false; } @@ -1504,8 +1519,8 @@ struct slot_rmap_walk_iterator { struct kvm_rmap_head *end_rmap; }; -static void -rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) +static void rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, + int level) { iterator->level = level; iterator->gfn = iterator->start_gfn; @@ -1513,10 +1528,10 @@ rmap_walk_init_level(struct slot_rmap_walk_iterator *iterator, int level) iterator->end_rmap = gfn_to_rmap(iterator->end_gfn, level, iterator->slot); } -static void -slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, - const struct kvm_memory_slot *slot, int start_level, - int end_level, gfn_t start_gfn, gfn_t end_gfn) +static void slot_rmap_walk_init(struct slot_rmap_walk_iterator *iterator, + const struct kvm_memory_slot *slot, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn) { iterator->slot = slot; iterator->start_level = start_level; @@ -1789,12 +1804,6 @@ static void mark_unsync(u64 *spte) kvm_mmu_mark_parents_unsync(sp); } -static int nonpaging_sync_page(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp) -{ - return -1; -} - #define KVM_PAGE_ARRAY_NR 16 struct kvm_mmu_pages { @@ -1914,10 +1923,79 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp) &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \ if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else +static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +{ + union kvm_mmu_page_role root_role = vcpu->arch.mmu->root_role; + + /* + * Ignore various flags when verifying that it's safe to sync a shadow + * page using the current MMU context. + * + * - level: not part of the overall MMU role and will never match as the MMU's + * level tracks the root level + * - access: updated based on the new guest PTE + * - quadrant: not part of the overall MMU role (similar to level) + */ + const union kvm_mmu_page_role sync_role_ign = { + .level = 0xf, + .access = 0x7, + .quadrant = 0x3, + .passthrough = 0x1, + }; + + /* + * Direct pages can never be unsync, and KVM should never attempt to + * sync a shadow page for a different MMU context, e.g. if the role + * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the + * reserved bits checks will be wrong, etc... + */ + if (WARN_ON_ONCE(sp->role.direct || !vcpu->arch.mmu->sync_spte || + (sp->role.word ^ root_role.word) & ~sync_role_ign.word)) + return false; + + return true; +} + +static int kvm_sync_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) +{ + if (!sp->spt[i]) + return 0; + + return vcpu->arch.mmu->sync_spte(vcpu, sp, i); +} + +static int __kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +{ + int flush = 0; + int i; + + if (!kvm_sync_page_check(vcpu, sp)) + return -1; + + for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { + int ret = kvm_sync_spte(vcpu, sp, i); + + if (ret < -1) + return -1; + flush |= ret; + } + + /* + * Note, any flush is purely for KVM's correctness, e.g. when dropping + * an existing SPTE or clearing W/A/D bits to ensure an mmu_notifier + * unmap or dirty logging event doesn't fail to flush. The guest is + * responsible for flushing the TLB to ensure any changes in protection + * bits are recognized, i.e. until the guest flushes or page faults on + * a relevant address, KVM is architecturally allowed to let vCPUs use + * cached translations with the old protection bits. + */ + return flush; +} + static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, struct list_head *invalid_list) { - int ret = vcpu->arch.mmu->sync_page(vcpu, sp); + int ret = __kvm_sync_page(vcpu, sp); if (ret < 0) kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list); @@ -3304,9 +3382,9 @@ static bool page_fault_can_be_fast(struct kvm_page_fault *fault) * Returns true if the SPTE was fixed successfully. Otherwise, * someone else modified the SPTE from its original value. */ -static bool -fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, - u64 *sptep, u64 old_spte, u64 new_spte) +static bool fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault, + u64 *sptep, u64 old_spte, u64 new_spte) { /* * Theoretically we could also set dirty bit (and flush TLB) here in @@ -3513,6 +3591,8 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, LIST_HEAD(invalid_list); bool free_active_root; + WARN_ON_ONCE(roots_to_free & ~KVM_MMU_ROOTS_ALL); + BUILD_BUG_ON(KVM_MMU_NUM_PREV_ROOTS >= BITS_PER_LONG); /* Before acquiring the MMU lock, see if we need to do any real work. */ @@ -3731,7 +3811,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu) int quadrant, i, r; hpa_t root; - root_pgd = mmu->get_guest_pgd(vcpu); + root_pgd = kvm_mmu_get_guest_pgd(vcpu, mmu); root_gfn = root_pgd >> PAGE_SHIFT; if (mmu_check_root(vcpu, root_gfn)) @@ -4181,7 +4261,7 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, arch.token = alloc_apf_token(vcpu); arch.gfn = gfn; arch.direct_map = vcpu->arch.mmu->root_role.direct; - arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu); + arch.cr3 = kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu); return kvm_setup_async_pf(vcpu, cr2_or_gpa, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch); @@ -4200,10 +4280,10 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) return; if (!vcpu->arch.mmu->root_role.direct && - work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu)) + work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu)) return; - kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true); + kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true, NULL); } static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) @@ -4469,8 +4549,7 @@ static void nonpaging_init_context(struct kvm_mmu *context) { context->page_fault = nonpaging_page_fault; context->gva_to_gpa = nonpaging_gva_to_gpa; - context->sync_page = nonpaging_sync_page; - context->invlpg = NULL; + context->sync_spte = NULL; } static inline bool is_root_usable(struct kvm_mmu_root_info *root, gpa_t pgd, @@ -4604,11 +4683,6 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) } EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); -static unsigned long get_cr3(struct kvm_vcpu *vcpu) -{ - return kvm_read_cr3(vcpu); -} - static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) { @@ -4638,10 +4712,9 @@ static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, #include "paging_tmpl.h" #undef PTTYPE -static void -__reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, int level, bool nx, bool gbpages, - bool pse, bool amd) +static void __reset_rsvds_bits_mask(struct rsvd_bits_validate *rsvd_check, + u64 pa_bits_rsvd, int level, bool nx, + bool gbpages, bool pse, bool amd) { u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; @@ -4754,9 +4827,9 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, guest_cpuid_is_amd_or_hygon(vcpu)); } -static void -__reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - u64 pa_bits_rsvd, bool execonly, int huge_page_level) +static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, + u64 pa_bits_rsvd, bool execonly, + int huge_page_level) { u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); u64 large_1g_rsvd = 0, large_2m_rsvd = 0; @@ -4856,8 +4929,7 @@ static inline bool boot_cpu_is_amd(void) * the direct page table on host, use as much mmu features as * possible, however, kvm currently does not do execution-protection. */ -static void -reset_tdp_shadow_zero_bits_mask(struct kvm_mmu *context) +static void reset_tdp_shadow_zero_bits_mask(struct kvm_mmu *context) { struct rsvd_bits_validate *shadow_zero_check; int i; @@ -5060,20 +5132,18 @@ static void paging64_init_context(struct kvm_mmu *context) { context->page_fault = paging64_page_fault; context->gva_to_gpa = paging64_gva_to_gpa; - context->sync_page = paging64_sync_page; - context->invlpg = paging64_invlpg; + context->sync_spte = paging64_sync_spte; } static void paging32_init_context(struct kvm_mmu *context) { context->page_fault = paging32_page_fault; context->gva_to_gpa = paging32_gva_to_gpa; - context->sync_page = paging32_sync_page; - context->invlpg = paging32_invlpg; + context->sync_spte = paging32_sync_spte; } -static union kvm_cpu_role -kvm_calc_cpu_role(struct kvm_vcpu *vcpu, const struct kvm_mmu_role_regs *regs) +static union kvm_cpu_role kvm_calc_cpu_role(struct kvm_vcpu *vcpu, + const struct kvm_mmu_role_regs *regs) { union kvm_cpu_role role = {0}; @@ -5112,6 +5182,21 @@ kvm_calc_cpu_role(struct kvm_vcpu *vcpu, const struct kvm_mmu_role_regs *regs) return role; } +void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu, + struct kvm_mmu *mmu) +{ + const bool cr0_wp = kvm_is_cr0_bit_set(vcpu, X86_CR0_WP); + + BUILD_BUG_ON((KVM_MMU_CR0_ROLE_BITS & KVM_POSSIBLE_CR0_GUEST_BITS) != X86_CR0_WP); + BUILD_BUG_ON((KVM_MMU_CR4_ROLE_BITS & KVM_POSSIBLE_CR4_GUEST_BITS)); + + if (is_cr0_wp(mmu) == cr0_wp) + return; + + mmu->cpu_role.base.cr0_wp = cr0_wp; + reset_guest_paging_metadata(vcpu, mmu); +} + static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu) { /* tdp_root_level is architecture forced level, use it if nonzero */ @@ -5157,9 +5242,8 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu, context->cpu_role.as_u64 = cpu_role.as_u64; context->root_role.word = root_role.word; context->page_fault = kvm_tdp_page_fault; - context->sync_page = nonpaging_sync_page; - context->invlpg = NULL; - context->get_guest_pgd = get_cr3; + context->sync_spte = NULL; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; @@ -5289,8 +5373,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->page_fault = ept_page_fault; context->gva_to_gpa = ept_gva_to_gpa; - context->sync_page = ept_sync_page; - context->invlpg = ept_invlpg; + context->sync_spte = ept_sync_spte; update_permission_bitmask(context, true); context->pkru_mask = 0; @@ -5309,7 +5392,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu, kvm_init_shadow_mmu(vcpu, cpu_role); - context->get_guest_pgd = get_cr3; + context->get_guest_pgd = get_guest_cr3; context->get_pdptr = kvm_pdptr_read; context->inject_page_fault = kvm_inject_page_fault; } @@ -5323,7 +5406,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu, return; g_context->cpu_role.as_u64 = new_mode.as_u64; - g_context->get_guest_pgd = get_cr3; + g_context->get_guest_pgd = get_guest_cr3; g_context->get_pdptr = kvm_pdptr_read; g_context->inject_page_fault = kvm_inject_page_fault; @@ -5331,7 +5414,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu, * L2 page tables are never shadowed, so there is no need to sync * SPTEs. */ - g_context->invlpg = NULL; + g_context->sync_spte = NULL; /* * Note that arch.mmu->gva_to_gpa translates l2_gpa to l1_gpa using @@ -5393,7 +5476,7 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * Changing guest CPUID after KVM_RUN is forbidden, see the comment in * kvm_arch_vcpu_ioctl(). */ - KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm); + KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm); } void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) @@ -5664,7 +5747,8 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err if (r == RET_PF_INVALID) { r = kvm_mmu_do_page_fault(vcpu, cr2_or_gpa, - lower_32_bits(error_code), false); + lower_32_bits(error_code), false, + &emulation_type); if (KVM_BUG_ON(r == RET_PF_INVALID, vcpu->kvm)) return -EIO; } @@ -5706,48 +5790,77 @@ emulate: } EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); -void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, - gva_t gva, hpa_t root_hpa) +static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + u64 addr, hpa_t root_hpa) +{ + struct kvm_shadow_walk_iterator iterator; + + vcpu_clear_mmio_info(vcpu, addr); + + if (!VALID_PAGE(root_hpa)) + return; + + write_lock(&vcpu->kvm->mmu_lock); + for_each_shadow_entry_using_root(vcpu, root_hpa, addr, iterator) { + struct kvm_mmu_page *sp = sptep_to_sp(iterator.sptep); + + if (sp->unsync) { + int ret = kvm_sync_spte(vcpu, sp, iterator.index); + + if (ret < 0) + mmu_page_zap_pte(vcpu->kvm, sp, iterator.sptep, NULL); + if (ret) + kvm_flush_remote_tlbs_sptep(vcpu->kvm, iterator.sptep); + } + + if (!sp->unsync_children) + break; + } + write_unlock(&vcpu->kvm->mmu_lock); +} + +void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, + u64 addr, unsigned long roots) { int i; + WARN_ON_ONCE(roots & ~KVM_MMU_ROOTS_ALL); + /* It's actually a GPA for vcpu->arch.guest_mmu. */ if (mmu != &vcpu->arch.guest_mmu) { /* INVLPG on a non-canonical address is a NOP according to the SDM. */ - if (is_noncanonical_address(gva, vcpu)) + if (is_noncanonical_address(addr, vcpu)) return; - static_call(kvm_x86_flush_tlb_gva)(vcpu, gva); + static_call(kvm_x86_flush_tlb_gva)(vcpu, addr); } - if (!mmu->invlpg) + if (!mmu->sync_spte) return; - if (root_hpa == INVALID_PAGE) { - mmu->invlpg(vcpu, gva, mmu->root.hpa); + if (roots & KVM_MMU_ROOT_CURRENT) + __kvm_mmu_invalidate_addr(vcpu, mmu, addr, mmu->root.hpa); - /* - * INVLPG is required to invalidate any global mappings for the VA, - * irrespective of PCID. Since it would take us roughly similar amount - * of work to determine whether any of the prev_root mappings of the VA - * is marked global, or to just sync it blindly, so we might as well - * just always sync it. - * - * Mappings not reachable via the current cr3 or the prev_roots will be - * synced when switching to that cr3, so nothing needs to be done here - * for them. - */ - for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) - if (VALID_PAGE(mmu->prev_roots[i].hpa)) - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); - } else { - mmu->invlpg(vcpu, gva, root_hpa); + for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { + if (roots & KVM_MMU_ROOT_PREVIOUS(i)) + __kvm_mmu_invalidate_addr(vcpu, mmu, addr, mmu->prev_roots[i].hpa); } } +EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_addr); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { - kvm_mmu_invalidate_gva(vcpu, vcpu->arch.walk_mmu, gva, INVALID_PAGE); + /* + * INVLPG is required to invalidate any global mappings for the VA, + * irrespective of PCID. Blindly sync all roots as it would take + * roughly the same amount of work/time to determine whether any of the + * previous roots have a global mapping. + * + * Mappings not reachable via the current or previous cached roots will + * be synced when switching to that new cr3, so nothing needs to be + * done here for them. + */ + kvm_mmu_invalidate_addr(vcpu, vcpu->arch.walk_mmu, gva, KVM_MMU_ROOTS_ALL); ++vcpu->stat.invlpg; } EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); @@ -5756,27 +5869,20 @@ EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) { struct kvm_mmu *mmu = vcpu->arch.mmu; - bool tlb_flush = false; + unsigned long roots = 0; uint i; - if (pcid == kvm_get_active_pcid(vcpu)) { - if (mmu->invlpg) - mmu->invlpg(vcpu, gva, mmu->root.hpa); - tlb_flush = true; - } + if (pcid == kvm_get_active_pcid(vcpu)) + roots |= KVM_MMU_ROOT_CURRENT; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) { if (VALID_PAGE(mmu->prev_roots[i].hpa) && - pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) { - if (mmu->invlpg) - mmu->invlpg(vcpu, gva, mmu->prev_roots[i].hpa); - tlb_flush = true; - } + pcid == kvm_get_pcid(vcpu, mmu->prev_roots[i].pgd)) + roots |= KVM_MMU_ROOT_PREVIOUS(i); } - if (tlb_flush) - static_call(kvm_x86_flush_tlb_gva)(vcpu, gva); - + if (roots) + kvm_mmu_invalidate_addr(vcpu, mmu, gva, roots); ++vcpu->stat.invlpg; /* @@ -5813,29 +5919,30 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, EXPORT_SYMBOL_GPL(kvm_configure_mmu); /* The return value indicates if tlb flush on all vcpus is needed. */ -typedef bool (*slot_level_handler) (struct kvm *kvm, +typedef bool (*slot_rmaps_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head, const struct kvm_memory_slot *slot); -/* The caller should hold mmu-lock before calling this function. */ -static __always_inline bool -slot_handle_level_range(struct kvm *kvm, const struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - gfn_t start_gfn, gfn_t end_gfn, bool flush_on_yield, - bool flush) +static __always_inline bool __walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + gfn_t start_gfn, gfn_t end_gfn, + bool flush_on_yield, bool flush) { struct slot_rmap_walk_iterator iterator; - for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, + lockdep_assert_held_write(&kvm->mmu_lock); + + for_each_slot_rmap_range(slot, start_level, end_level, start_gfn, end_gfn, &iterator) { if (iterator.rmap) - flush |= fn(kvm, iterator.rmap, memslot); + flush |= fn(kvm, iterator.rmap, slot); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { if (flush && flush_on_yield) { - kvm_flush_remote_tlbs_with_address(kvm, - start_gfn, - iterator.gfn - start_gfn + 1); + kvm_flush_remote_tlbs_range(kvm, start_gfn, + iterator.gfn - start_gfn + 1); flush = false; } cond_resched_rwlock_write(&kvm->mmu_lock); @@ -5845,23 +5952,23 @@ slot_handle_level_range(struct kvm *kvm, const struct kvm_memory_slot *memslot, return flush; } -static __always_inline bool -slot_handle_level(struct kvm *kvm, const struct kvm_memory_slot *memslot, - slot_level_handler fn, int start_level, int end_level, - bool flush_on_yield) +static __always_inline bool walk_slot_rmaps(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + int start_level, int end_level, + bool flush_on_yield) { - return slot_handle_level_range(kvm, memslot, fn, start_level, - end_level, memslot->base_gfn, - memslot->base_gfn + memslot->npages - 1, - flush_on_yield, false); + return __walk_slot_rmaps(kvm, slot, fn, start_level, end_level, + slot->base_gfn, slot->base_gfn + slot->npages - 1, + flush_on_yield, false); } -static __always_inline bool -slot_handle_level_4k(struct kvm *kvm, const struct kvm_memory_slot *memslot, - slot_level_handler fn, bool flush_on_yield) +static __always_inline bool walk_slot_rmaps_4k(struct kvm *kvm, + const struct kvm_memory_slot *slot, + slot_rmaps_handler fn, + bool flush_on_yield) { - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, - PG_LEVEL_4K, flush_on_yield); + return walk_slot_rmaps(kvm, slot, fn, PG_LEVEL_4K, PG_LEVEL_4K, flush_on_yield); } static void free_mmu_pages(struct kvm_mmu *mmu) @@ -6156,9 +6263,9 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e if (WARN_ON_ONCE(start >= end)) continue; - flush = slot_handle_level_range(kvm, memslot, __kvm_zap_rmap, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, - start, end - 1, true, flush); + flush = __walk_slot_rmaps(kvm, memslot, __kvm_zap_rmap, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL, + start, end - 1, true, flush); } } @@ -6190,8 +6297,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) } if (flush) - kvm_flush_remote_tlbs_with_address(kvm, gfn_start, - gfn_end - gfn_start); + kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start); kvm_mmu_invalidate_end(kvm, 0, -1ul); @@ -6211,8 +6317,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, { if (kvm_memslots_have_rmaps(kvm)) { write_lock(&kvm->mmu_lock); - slot_handle_level(kvm, memslot, slot_rmap_write_protect, - start_level, KVM_MAX_HUGEPAGE_LEVEL, false); + walk_slot_rmaps(kvm, memslot, slot_rmap_write_protect, + start_level, KVM_MAX_HUGEPAGE_LEVEL, false); write_unlock(&kvm->mmu_lock); } @@ -6447,10 +6553,9 @@ static void kvm_shadow_mmu_try_split_huge_pages(struct kvm *kvm, * all the way to the target level. There's no need to split pages * already at the target level. */ - for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) { - slot_handle_level_range(kvm, slot, shadow_mmu_try_split_huge_pages, - level, level, start, end - 1, true, false); - } + for (level = KVM_MAX_HUGEPAGE_LEVEL; level > target_level; level--) + __walk_slot_rmaps(kvm, slot, shadow_mmu_try_split_huge_pages, + level, level, start, end - 1, true, false); } /* Must be called with the mmu_lock held in write-mode. */ @@ -6529,7 +6634,7 @@ restart: PG_LEVEL_NUM)) { kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); - if (kvm_available_flush_tlb_with_range()) + if (kvm_available_flush_remote_tlbs_range()) kvm_flush_remote_tlbs_sptep(kvm, sptep); else need_tlb_flush = 1; @@ -6548,8 +6653,8 @@ static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, * Note, use KVM_MAX_HUGEPAGE_LEVEL - 1 since there's no need to zap * pages that are already mapped at the maximum hugepage level. */ - if (slot_handle_level(kvm, slot, kvm_mmu_zap_collapsible_spte, - PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true)) + if (walk_slot_rmaps(kvm, slot, kvm_mmu_zap_collapsible_spte, + PG_LEVEL_4K, KVM_MAX_HUGEPAGE_LEVEL - 1, true)) kvm_arch_flush_remote_tlbs_memslot(kvm, slot); } @@ -6580,8 +6685,7 @@ void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, * is observed by any other operation on the same memslot. */ lockdep_assert_held(&kvm->slots_lock); - kvm_flush_remote_tlbs_with_address(kvm, memslot->base_gfn, - memslot->npages); + kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); } void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, @@ -6593,7 +6697,7 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, * Clear dirty bits only on 4k SPTEs since the legacy MMU only * support dirty logging at a 4k granularity. */ - slot_handle_level_4k(kvm, memslot, __rmap_clear_dirty, false); + walk_slot_rmaps_4k(kvm, memslot, __rmap_clear_dirty, false); write_unlock(&kvm->mmu_lock); } @@ -6663,8 +6767,8 @@ void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) } } -static unsigned long -mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long mmu_shrink_scan(struct shrinker *shrink, + struct shrink_control *sc) { struct kvm *kvm; int nr_to_scan = sc->nr_to_scan; @@ -6722,8 +6826,8 @@ unlock: return freed; } -static unsigned long -mmu_shrink_count(struct shrinker *shrink, struct shrink_control *sc) +static unsigned long mmu_shrink_count(struct shrinker *shrink, + struct shrink_control *sc) { return percpu_counter_read_positive(&kvm_total_used_mmu_pages); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index cc58631e2336..d39af5639ce9 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -170,14 +170,14 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, struct kvm_memory_slot *slot, u64 gfn, int min_level); -void kvm_flush_remote_tlbs_with_address(struct kvm *kvm, - u64 start_gfn, u64 pages); +void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t start_gfn, + gfn_t nr_pages); /* Flush the given page (huge or not) of guest memory. */ static inline void kvm_flush_remote_tlbs_gfn(struct kvm *kvm, gfn_t gfn, int level) { - kvm_flush_remote_tlbs_with_address(kvm, gfn_round_for_level(gfn, level), - KVM_PAGES_PER_HPAGE(level)); + kvm_flush_remote_tlbs_range(kvm, gfn_round_for_level(gfn, level), + KVM_PAGES_PER_HPAGE(level)); } unsigned int pte_list_count(struct kvm_rmap_head *rmap_head); @@ -240,6 +240,13 @@ struct kvm_page_fault { kvm_pfn_t pfn; hva_t hva; bool map_writable; + + /* + * Indicates the guest is trying to write a gfn that contains one or + * more of the PTEs used to translate the write itself, i.e. the access + * is changing its own translation in the guest page tables. + */ + bool write_fault_to_shadow_pgtable; }; int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); @@ -273,7 +280,7 @@ enum { }; static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - u32 err, bool prefetch) + u32 err, bool prefetch, int *emulation_type) { struct kvm_page_fault fault = { .addr = cr2_or_gpa, @@ -312,6 +319,9 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, else r = vcpu->arch.mmu->page_fault(vcpu, &fault); + if (fault.write_fault_to_shadow_pgtable && emulation_type) + *emulation_type |= EMULTYPE_WRITE_PF_TO_SP; + /* * Similar to above, prefetch faults aren't truly spurious, and the * async #PF path doesn't do emulation. Do count faults that are fixed diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h index 57f0b75c80f9..0662e0278e70 100644 --- a/arch/x86/kvm/mmu/paging_tmpl.h +++ b/arch/x86/kvm/mmu/paging_tmpl.h @@ -324,7 +324,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker, trace_kvm_mmu_pagetable_walk(addr, access); retry_walk: walker->level = mmu->cpu_role.base.level; - pte = mmu->get_guest_pgd(vcpu); + pte = kvm_mmu_get_guest_pgd(vcpu, mmu); have_ad = PT_HAVE_ACCESSED_DIRTY(mmu); #if PTTYPE == 64 @@ -519,7 +519,7 @@ static int FNAME(walk_addr)(struct guest_walker *walker, static bool FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, - u64 *spte, pt_element_t gpte, bool no_dirty_log) + u64 *spte, pt_element_t gpte) { struct kvm_memory_slot *slot; unsigned pte_access; @@ -535,8 +535,7 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, pte_access = sp->role.access & FNAME(gpte_access)(gpte); FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); - slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, - no_dirty_log && (pte_access & ACC_WRITE_MASK)); + slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, pte_access & ACC_WRITE_MASK); if (!slot) return false; @@ -605,7 +604,7 @@ static void FNAME(pte_prefetch)(struct kvm_vcpu *vcpu, struct guest_walker *gw, if (is_shadow_present_pte(*spte)) continue; - if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i], true)) + if (!FNAME(prefetch_gpte)(vcpu, sp, spte, gptep[i])) break; } } @@ -685,8 +684,17 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, if (sp != ERR_PTR(-EEXIST)) link_shadow_page(vcpu, it.sptep, sp); + + if (fault->write && table_gfn == fault->gfn) + fault->write_fault_to_shadow_pgtable = true; } + /* + * Adjust the hugepage size _after_ resolving indirect shadow pages. + * KVM doesn't support mapping hugepages into the guest for gfns that + * are being shadowed by KVM, i.e. allocating a new shadow page may + * affect the allowed hugepage size. + */ kvm_mmu_hugepage_adjust(vcpu, fault); trace_kvm_mmu_spte_requested(fault); @@ -731,46 +739,6 @@ out_gpte_changed: return RET_PF_RETRY; } - /* - * To see whether the mapped gfn can write its page table in the current - * mapping. - * - * It is the helper function of FNAME(page_fault). When guest uses large page - * size to map the writable gfn which is used as current page table, we should - * force kvm to use small page size to map it because new shadow page will be - * created when kvm establishes shadow page table that stop kvm using large - * page size. Do it early can avoid unnecessary #PF and emulation. - * - * @write_fault_to_shadow_pgtable will return true if the fault gfn is - * currently used as its page table. - * - * Note: the PDPT page table is not checked for PAE-32 bit guest. It is ok - * since the PDPT is always shadowed, that means, we can not use large page - * size to map the gfn which is used as PDPT. - */ -static bool -FNAME(is_self_change_mapping)(struct kvm_vcpu *vcpu, - struct guest_walker *walker, bool user_fault, - bool *write_fault_to_shadow_pgtable) -{ - int level; - gfn_t mask = ~(KVM_PAGES_PER_HPAGE(walker->level) - 1); - bool self_changed = false; - - if (!(walker->pte_access & ACC_WRITE_MASK || - (!is_cr0_wp(vcpu->arch.mmu) && !user_fault))) - return false; - - for (level = walker->level; level <= walker->max_level; level++) { - gfn_t gfn = walker->gfn ^ walker->table_gfn[level - 1]; - - self_changed |= !(gfn & mask); - *write_fault_to_shadow_pgtable |= !gfn; - } - - return self_changed; -} - /* * Page fault handler. There are several causes for a page fault: * - there is no shadow pte for the guest pte @@ -789,7 +757,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault { struct guest_walker walker; int r; - bool is_self_change_mapping; pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code); WARN_ON_ONCE(fault->is_tdp); @@ -814,6 +781,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault } fault->gfn = walker.gfn; + fault->max_level = walker.level; fault->slot = kvm_vcpu_gfn_to_memslot(vcpu, fault->gfn); if (page_fault_handle_page_track(vcpu, fault)) { @@ -825,16 +793,6 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault if (r) return r; - vcpu->arch.write_fault_to_shadow_pgtable = false; - - is_self_change_mapping = FNAME(is_self_change_mapping)(vcpu, - &walker, fault->user, &vcpu->arch.write_fault_to_shadow_pgtable); - - if (is_self_change_mapping) - fault->max_level = PG_LEVEL_4K; - else - fault->max_level = walker.level; - r = kvm_faultin_pfn(vcpu, fault, walker.pte_access); if (r != RET_PF_CONTINUE) return r; @@ -887,64 +845,6 @@ static gpa_t FNAME(get_level1_sp_gpa)(struct kvm_mmu_page *sp) return gfn_to_gpa(sp->gfn) + offset * sizeof(pt_element_t); } -static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva, hpa_t root_hpa) -{ - struct kvm_shadow_walk_iterator iterator; - struct kvm_mmu_page *sp; - u64 old_spte; - int level; - u64 *sptep; - - vcpu_clear_mmio_info(vcpu, gva); - - /* - * No need to check return value here, rmap_can_add() can - * help us to skip pte prefetch later. - */ - mmu_topup_memory_caches(vcpu, true); - - if (!VALID_PAGE(root_hpa)) { - WARN_ON(1); - return; - } - - write_lock(&vcpu->kvm->mmu_lock); - for_each_shadow_entry_using_root(vcpu, root_hpa, gva, iterator) { - level = iterator.level; - sptep = iterator.sptep; - - sp = sptep_to_sp(sptep); - old_spte = *sptep; - if (is_last_spte(old_spte, level)) { - pt_element_t gpte; - gpa_t pte_gpa; - - if (!sp->unsync) - break; - - pte_gpa = FNAME(get_level1_sp_gpa)(sp); - pte_gpa += spte_index(sptep) * sizeof(pt_element_t); - - mmu_page_zap_pte(vcpu->kvm, sp, sptep, NULL); - if (is_shadow_present_pte(old_spte)) - kvm_flush_remote_tlbs_sptep(vcpu->kvm, sptep); - - if (!rmap_can_add(vcpu)) - break; - - if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, - sizeof(pt_element_t))) - break; - - FNAME(prefetch_gpte)(vcpu, sp, sptep, gpte, false); - } - - if (!sp->unsync_children) - break; - } - write_unlock(&vcpu->kvm->mmu_lock); -} - /* Note, @addr is a GPA when gva_to_gpa() translates an L2 GPA to an L1 GPA. */ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, gpa_t addr, u64 access, @@ -977,114 +877,75 @@ static gpa_t FNAME(gva_to_gpa)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, * can't change unless all sptes pointing to it are nuked first. * * Returns - * < 0: the sp should be zapped - * 0: the sp is synced and no tlb flushing is required - * > 0: the sp is synced and tlb flushing is required + * < 0: failed to sync spte + * 0: the spte is synced and no tlb flushing is required + * > 0: the spte is synced and tlb flushing is required */ -static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +static int FNAME(sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i) { - union kvm_mmu_page_role root_role = vcpu->arch.mmu->root_role; - int i; bool host_writable; gpa_t first_pte_gpa; - bool flush = false; - - /* - * Ignore various flags when verifying that it's safe to sync a shadow - * page using the current MMU context. - * - * - level: not part of the overall MMU role and will never match as the MMU's - * level tracks the root level - * - access: updated based on the new guest PTE - * - quadrant: not part of the overall MMU role (similar to level) - */ - const union kvm_mmu_page_role sync_role_ign = { - .level = 0xf, - .access = 0x7, - .quadrant = 0x3, - .passthrough = 0x1, - }; + u64 *sptep, spte; + struct kvm_memory_slot *slot; + unsigned pte_access; + pt_element_t gpte; + gpa_t pte_gpa; + gfn_t gfn; - /* - * Direct pages can never be unsync, and KVM should never attempt to - * sync a shadow page for a different MMU context, e.g. if the role - * differs then the memslot lookup (SMM vs. non-SMM) will be bogus, the - * reserved bits checks will be wrong, etc... - */ - if (WARN_ON_ONCE(sp->role.direct || - (sp->role.word ^ root_role.word) & ~sync_role_ign.word)) - return -1; + if (WARN_ON_ONCE(!sp->spt[i])) + return 0; first_pte_gpa = FNAME(get_level1_sp_gpa)(sp); + pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); - for (i = 0; i < SPTE_ENT_PER_PAGE; i++) { - u64 *sptep, spte; - struct kvm_memory_slot *slot; - unsigned pte_access; - pt_element_t gpte; - gpa_t pte_gpa; - gfn_t gfn; - - if (!sp->spt[i]) - continue; - - pte_gpa = first_pte_gpa + i * sizeof(pt_element_t); - - if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, - sizeof(pt_element_t))) - return -1; - - if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - flush = true; - continue; - } - - gfn = gpte_to_gfn(gpte); - pte_access = sp->role.access; - pte_access &= FNAME(gpte_access)(gpte); - FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); - - if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access)) - continue; + if (kvm_vcpu_read_guest_atomic(vcpu, pte_gpa, &gpte, + sizeof(pt_element_t))) + return -1; - /* - * Drop the SPTE if the new protections would result in a RWX=0 - * SPTE or if the gfn is changing. The RWX=0 case only affects - * EPT with execute-only support, i.e. EPT without an effective - * "present" bit, as all other paging modes will create a - * read-only SPTE if pte_access is zero. - */ - if ((!pte_access && !shadow_present_mask) || - gfn != kvm_mmu_page_get_gfn(sp, i)) { - drop_spte(vcpu->kvm, &sp->spt[i]); - flush = true; - continue; - } + if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) + return 1; - /* Update the shadowed access bits in case they changed. */ - kvm_mmu_page_set_access(sp, i, pte_access); + gfn = gpte_to_gfn(gpte); + pte_access = sp->role.access; + pte_access &= FNAME(gpte_access)(gpte); + FNAME(protect_clean_gpte)(vcpu->arch.mmu, &pte_access, gpte); - sptep = &sp->spt[i]; - spte = *sptep; - host_writable = spte & shadow_host_writable_mask; - slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); - make_spte(vcpu, sp, slot, pte_access, gfn, - spte_to_pfn(spte), spte, true, false, - host_writable, &spte); + if (sync_mmio_spte(vcpu, &sp->spt[i], gfn, pte_access)) + return 0; - flush |= mmu_spte_update(sptep, spte); + /* + * Drop the SPTE if the new protections would result in a RWX=0 + * SPTE or if the gfn is changing. The RWX=0 case only affects + * EPT with execute-only support, i.e. EPT without an effective + * "present" bit, as all other paging modes will create a + * read-only SPTE if pte_access is zero. + */ + if ((!pte_access && !shadow_present_mask) || + gfn != kvm_mmu_page_get_gfn(sp, i)) { + drop_spte(vcpu->kvm, &sp->spt[i]); + return 1; } - /* - * Note, any flush is purely for KVM's correctness, e.g. when dropping - * an existing SPTE or clearing W/A/D bits to ensure an mmu_notifier - * unmap or dirty logging event doesn't fail to flush. The guest is - * responsible for flushing the TLB to ensure any changes in protection - * bits are recognized, i.e. until the guest flushes or page faults on - * a relevant address, KVM is architecturally allowed to let vCPUs use - * cached translations with the old protection bits. + * Do nothing if the permissions are unchanged. The existing SPTE is + * still, and prefetch_invalid_gpte() has verified that the A/D bits + * are set in the "new" gPTE, i.e. there is no danger of missing an A/D + * update due to A/D bits being set in the SPTE but not the gPTE. */ - return flush; + if (kvm_mmu_page_get_access(sp, i) == pte_access) + return 0; + + /* Update the shadowed access bits in case they changed. */ + kvm_mmu_page_set_access(sp, i, pte_access); + + sptep = &sp->spt[i]; + spte = *sptep; + host_writable = spte & shadow_host_writable_mask; + slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + make_spte(vcpu, sp, slot, pte_access, gfn, + spte_to_pfn(spte), spte, true, false, + host_writable, &spte); + + return mmu_spte_update(sptep, spte); } #undef pt_element_t diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index c15bfca3ed15..cf2c6426a6fc 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -164,7 +164,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, /* * For simplicity, enforce the NX huge page mitigation even if not * strictly necessary. KVM could ignore the mitigation if paging is - * disabled in the guest, as the guest doesn't have an page tables to + * disabled in the guest, as the guest doesn't have any page tables to * abuse. But to safely ignore the mitigation, KVM would have to * ensure a new MMU is loaded (or all shadow pages zapped) when CR0.PG * is toggled on, and that's a net negative for performance when TDP is diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index f0af385c56e0..fae559559a80 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -29,29 +29,49 @@ static inline void __kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 new_spte) WRITE_ONCE(*rcu_dereference(sptep), new_spte); } +/* + * SPTEs must be modified atomically if they are shadow-present, leaf + * SPTEs, and have volatile bits, i.e. has bits that can be set outside + * of mmu_lock. The Writable bit can be set by KVM's fast page fault + * handler, and Accessed and Dirty bits can be set by the CPU. + * + * Note, non-leaf SPTEs do have Accessed bits and those bits are + * technically volatile, but KVM doesn't consume the Accessed bit of + * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This + * logic needs to be reassessed if KVM were to use non-leaf Accessed + * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. + */ +static inline bool kvm_tdp_mmu_spte_need_atomic_write(u64 old_spte, int level) +{ + return is_shadow_present_pte(old_spte) && + is_last_spte(old_spte, level) && + spte_has_volatile_bits(old_spte); +} + static inline u64 kvm_tdp_mmu_write_spte(tdp_ptep_t sptep, u64 old_spte, u64 new_spte, int level) { - /* - * Atomically write the SPTE if it is a shadow-present, leaf SPTE with - * volatile bits, i.e. has bits that can be set outside of mmu_lock. - * The Writable bit can be set by KVM's fast page fault handler, and - * Accessed and Dirty bits can be set by the CPU. - * - * Note, non-leaf SPTEs do have Accessed bits and those bits are - * technically volatile, but KVM doesn't consume the Accessed bit of - * non-leaf SPTEs, i.e. KVM doesn't care if it clobbers the bit. This - * logic needs to be reassessed if KVM were to use non-leaf Accessed - * bits, e.g. to skip stepping down into child SPTEs when aging SPTEs. - */ - if (is_shadow_present_pte(old_spte) && is_last_spte(old_spte, level) && - spte_has_volatile_bits(old_spte)) + if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level)) return kvm_tdp_mmu_write_spte_atomic(sptep, new_spte); __kvm_tdp_mmu_write_spte(sptep, new_spte); return old_spte; } +static inline u64 tdp_mmu_clear_spte_bits(tdp_ptep_t sptep, u64 old_spte, + u64 mask, int level) +{ + atomic64_t *sptep_atomic; + + if (kvm_tdp_mmu_spte_need_atomic_write(old_spte, level)) { + sptep_atomic = (atomic64_t *)rcu_dereference(sptep); + return (u64)atomic64_fetch_and(~mask, sptep_atomic); + } + + __kvm_tdp_mmu_write_spte(sptep, old_spte & ~mask); + return old_spte; +} + /* * A TDP iterator performs a pre-order walk over a TDP paging structure. */ diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7c25dbf32ecc..b2fca11b91ff 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -334,35 +334,6 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, u64 old_spte, u64 new_spte, int level, bool shared); -static void handle_changed_spte_acc_track(u64 old_spte, u64 new_spte, int level) -{ - if (!is_shadow_present_pte(old_spte) || !is_last_spte(old_spte, level)) - return; - - if (is_accessed_spte(old_spte) && - (!is_shadow_present_pte(new_spte) || !is_accessed_spte(new_spte) || - spte_to_pfn(old_spte) != spte_to_pfn(new_spte))) - kvm_set_pfn_accessed(spte_to_pfn(old_spte)); -} - -static void handle_changed_spte_dirty_log(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level) -{ - bool pfn_changed; - struct kvm_memory_slot *slot; - - if (level > PG_LEVEL_4K) - return; - - pfn_changed = spte_to_pfn(old_spte) != spte_to_pfn(new_spte); - - if ((!is_writable_pte(old_spte) || pfn_changed) && - is_writable_pte(new_spte)) { - slot = __gfn_to_memslot(__kvm_memslots(kvm, as_id), gfn); - mark_page_dirty_in_slot(kvm, slot, gfn); - } -} - static void tdp_account_mmu_page(struct kvm *kvm, struct kvm_mmu_page *sp) { kvm_account_pgtable_pages((void *)sp->spt, +1); @@ -505,7 +476,7 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) } /** - * __handle_changed_spte - handle bookkeeping associated with an SPTE change + * handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance * @as_id: the address space of the paging structure the SPTE was a part of * @gfn: the base GFN that was mapped by the SPTE @@ -516,12 +487,13 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) * the MMU lock and the operation must synchronize with other * threads that might be modifying SPTEs. * - * Handle bookkeeping that might result from the modification of a SPTE. - * This function must be called for all TDP SPTE modifications. + * Handle bookkeeping that might result from the modification of a SPTE. Note, + * dirty logging updates are handled in common code, not here (see make_spte() + * and fast_pf_fix_direct_spte()). */ -static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level, - bool shared) +static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, + u64 old_spte, u64 new_spte, int level, + bool shared) { bool was_present = is_shadow_present_pte(old_spte); bool is_present = is_shadow_present_pte(new_spte); @@ -605,17 +577,10 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, if (was_present && !was_leaf && (is_leaf || !is_present || WARN_ON_ONCE(pfn_changed))) handle_removed_pt(kvm, spte_to_child_pt(old_spte, level), shared); -} -static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, - u64 old_spte, u64 new_spte, int level, - bool shared) -{ - __handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, - shared); - handle_changed_spte_acc_track(old_spte, new_spte, level); - handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, - new_spte, level); + if (was_leaf && is_accessed_spte(old_spte) && + (!is_present || !is_accessed_spte(new_spte) || pfn_changed)) + kvm_set_pfn_accessed(spte_to_pfn(old_spte)); } /* @@ -658,9 +623,8 @@ static inline int tdp_mmu_set_spte_atomic(struct kvm *kvm, if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) return -EBUSY; - __handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, - new_spte, iter->level, true); - handle_changed_spte_acc_track(iter->old_spte, new_spte, iter->level); + handle_changed_spte(kvm, iter->as_id, iter->gfn, iter->old_spte, + new_spte, iter->level, true); return 0; } @@ -696,7 +660,7 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, /* - * __tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping + * tdp_mmu_set_spte - Set a TDP MMU SPTE and handle the associated bookkeeping * @kvm: KVM instance * @as_id: Address space ID, i.e. regular vs. SMM * @sptep: Pointer to the SPTE @@ -704,23 +668,12 @@ static inline int tdp_mmu_zap_spte_atomic(struct kvm *kvm, * @new_spte: The new value that will be set for the SPTE * @gfn: The base GFN that was (or will be) mapped by the SPTE * @level: The level _containing_ the SPTE (its parent PT's level) - * @record_acc_track: Notify the MM subsystem of changes to the accessed state - * of the page. Should be set unless handling an MMU - * notifier for access tracking. Leaving record_acc_track - * unset in that case prevents page accesses from being - * double counted. - * @record_dirty_log: Record the page as dirty in the dirty bitmap if - * appropriate for the change being made. Should be set - * unless performing certain dirty logging operations. - * Leaving record_dirty_log unset in that case prevents page - * writes from being double counted. * * Returns the old SPTE value, which _may_ be different than @old_spte if the * SPTE had voldatile bits. */ -static u64 __tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, - u64 old_spte, u64 new_spte, gfn_t gfn, int level, - bool record_acc_track, bool record_dirty_log) +static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, + u64 old_spte, u64 new_spte, gfn_t gfn, int level) { lockdep_assert_held_write(&kvm->mmu_lock); @@ -735,46 +688,17 @@ 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); - - if (record_acc_track) - handle_changed_spte_acc_track(old_spte, new_spte, level); - if (record_dirty_log) - handle_changed_spte_dirty_log(kvm, as_id, gfn, old_spte, - new_spte, level); + handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); return old_spte; } -static inline void _tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, - u64 new_spte, bool record_acc_track, - bool record_dirty_log) +static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, + u64 new_spte) { WARN_ON_ONCE(iter->yielded); - - iter->old_spte = __tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, - iter->old_spte, new_spte, - iter->gfn, iter->level, - record_acc_track, record_dirty_log); -} - -static inline void tdp_mmu_set_spte(struct kvm *kvm, struct tdp_iter *iter, - u64 new_spte) -{ - _tdp_mmu_set_spte(kvm, iter, new_spte, true, true); -} - -static inline void tdp_mmu_set_spte_no_acc_track(struct kvm *kvm, - struct tdp_iter *iter, - u64 new_spte) -{ - _tdp_mmu_set_spte(kvm, iter, new_spte, false, true); -} - -static inline void tdp_mmu_set_spte_no_dirty_log(struct kvm *kvm, - struct tdp_iter *iter, - u64 new_spte) -{ - _tdp_mmu_set_spte(kvm, iter, new_spte, true, false); + iter->old_spte = tdp_mmu_set_spte(kvm, iter->as_id, iter->sptep, + iter->old_spte, new_spte, + iter->gfn, iter->level); } #define tdp_root_for_each_pte(_iter, _root, _start, _end) \ @@ -866,7 +790,7 @@ retry: continue; if (!shared) - tdp_mmu_set_spte(kvm, &iter, 0); + tdp_mmu_iter_set_spte(kvm, &iter, 0); else if (tdp_mmu_set_spte_atomic(kvm, &iter, 0)) goto retry; } @@ -923,8 +847,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte))) return false; - __tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0, - sp->gfn, sp->role.level + 1, true, true); + tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, 0, + sp->gfn, sp->role.level + 1); return true; } @@ -958,7 +882,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, !is_last_spte(iter.old_spte, iter.level)) continue; - tdp_mmu_set_spte(kvm, &iter, 0); + tdp_mmu_iter_set_spte(kvm, &iter, 0); flush = true; } @@ -1128,7 +1052,7 @@ static int tdp_mmu_link_sp(struct kvm *kvm, struct tdp_iter *iter, if (ret) return ret; } else { - tdp_mmu_set_spte(kvm, iter, spte); + tdp_mmu_iter_set_spte(kvm, iter, spte); } tdp_account_mmu_page(kvm, sp); @@ -1262,33 +1186,42 @@ static __always_inline bool kvm_tdp_mmu_handle_gfn(struct kvm *kvm, /* * Mark the SPTEs range of GFNs [start, end) unaccessed and return non-zero * if any of the GFNs in the range have been accessed. + * + * No need to mark the corresponding PFN as accessed as this call is coming + * from the clear_young() or clear_flush_young() notifier, which uses the + * return value to determine if the page has been accessed. */ static bool age_gfn_range(struct kvm *kvm, struct tdp_iter *iter, struct kvm_gfn_range *range) { - u64 new_spte = 0; + u64 new_spte; /* If we have a non-accessed entry we don't need to change the pte. */ if (!is_accessed_spte(iter->old_spte)) return false; - new_spte = iter->old_spte; - - if (spte_ad_enabled(new_spte)) { - new_spte &= ~shadow_accessed_mask; + if (spte_ad_enabled(iter->old_spte)) { + iter->old_spte = tdp_mmu_clear_spte_bits(iter->sptep, + iter->old_spte, + shadow_accessed_mask, + iter->level); + new_spte = iter->old_spte & ~shadow_accessed_mask; } else { /* * Capture the dirty status of the page, so that it doesn't get * lost when the SPTE is marked for access tracking. */ - if (is_writable_pte(new_spte)) - kvm_set_pfn_dirty(spte_to_pfn(new_spte)); + if (is_writable_pte(iter->old_spte)) + kvm_set_pfn_dirty(spte_to_pfn(iter->old_spte)); - new_spte = mark_spte_for_access_track(new_spte); + new_spte = mark_spte_for_access_track(iter->old_spte); + iter->old_spte = kvm_tdp_mmu_write_spte(iter->sptep, + iter->old_spte, new_spte, + iter->level); } - tdp_mmu_set_spte_no_acc_track(kvm, iter, new_spte); - + trace_kvm_tdp_mmu_spte_changed(iter->as_id, iter->gfn, iter->level, + iter->old_spte, new_spte); return true; } @@ -1324,15 +1257,15 @@ static bool set_spte_gfn(struct kvm *kvm, struct tdp_iter *iter, * Note, when changing a read-only SPTE, it's not strictly necessary to * zero the SPTE before setting the new PFN, but doing so preserves the * invariant that the PFN of a present * leaf SPTE can never change. - * See __handle_changed_spte(). + * See handle_changed_spte(). */ - tdp_mmu_set_spte(kvm, iter, 0); + tdp_mmu_iter_set_spte(kvm, iter, 0); if (!pte_write(range->pte)) { new_spte = kvm_mmu_changed_pte_notifier_make_spte(iter->old_spte, pte_pfn(range->pte)); - tdp_mmu_set_spte(kvm, iter, new_spte); + tdp_mmu_iter_set_spte(kvm, iter, new_spte); } return true; @@ -1349,7 +1282,7 @@ bool kvm_tdp_mmu_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) /* * No need to handle the remote TLB flush under RCU protection, the * target SPTE _must_ be a leaf SPTE, i.e. cannot result in freeing a - * shadow page. See the WARN on pfn_changed in __handle_changed_spte(). + * shadow page. See the WARN on pfn_changed in handle_changed_spte(). */ return kvm_tdp_mmu_handle_gfn(kvm, range, set_spte_gfn); } @@ -1607,8 +1540,8 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { + u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; struct tdp_iter iter; - u64 new_spte; bool spte_set = false; rcu_read_lock(); @@ -1621,19 +1554,13 @@ retry: if (!is_shadow_present_pte(iter.old_spte)) continue; - if (spte_ad_need_write_protect(iter.old_spte)) { - if (is_writable_pte(iter.old_spte)) - new_spte = iter.old_spte & ~PT_WRITABLE_MASK; - else - continue; - } else { - if (iter.old_spte & shadow_dirty_mask) - new_spte = iter.old_spte & ~shadow_dirty_mask; - else - continue; - } + MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); - if (tdp_mmu_set_spte_atomic(kvm, &iter, new_spte)) + if (!(iter.old_spte & dbit)) + continue; + + if (tdp_mmu_set_spte_atomic(kvm, &iter, iter.old_spte & ~dbit)) goto retry; spte_set = true; @@ -1675,8 +1602,9 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { + u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; - u64 new_spte; rcu_read_lock(); @@ -1685,25 +1613,26 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; + MMU_WARN_ON(kvm_ad_enabled() && + spte_ad_need_write_protect(iter.old_spte)); + if (iter.level > PG_LEVEL_4K || !(mask & (1UL << (iter.gfn - gfn)))) continue; mask &= ~(1UL << (iter.gfn - gfn)); - if (wrprot || spte_ad_need_write_protect(iter.old_spte)) { - if (is_writable_pte(iter.old_spte)) - new_spte = iter.old_spte & ~PT_WRITABLE_MASK; - else - continue; - } else { - if (iter.old_spte & shadow_dirty_mask) - new_spte = iter.old_spte & ~shadow_dirty_mask; - else - continue; - } + if (!(iter.old_spte & dbit)) + continue; + + iter.old_spte = tdp_mmu_clear_spte_bits(iter.sptep, + iter.old_spte, dbit, + iter.level); - tdp_mmu_set_spte_no_dirty_log(kvm, &iter, new_spte); + trace_kvm_tdp_mmu_spte_changed(iter.as_id, iter.gfn, iter.level, + iter.old_spte, + iter.old_spte & ~dbit); + kvm_set_pfn_dirty(spte_to_pfn(iter.old_spte)); } rcu_read_unlock(); @@ -1821,7 +1750,7 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, if (new_spte == iter.old_spte) break; - tdp_mmu_set_spte(kvm, &iter, new_spte); + tdp_mmu_iter_set_spte(kvm, &iter, new_spte); spte_set = true; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 612e6c70ce2e..1690d41c1830 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -93,7 +93,7 @@ void kvm_pmu_ops_update(const struct kvm_pmu_ops *pmu_ops) #undef __KVM_X86_PMU_OP } -static inline bool pmc_is_enabled(struct kvm_pmc *pmc) +static inline bool pmc_is_globally_enabled(struct kvm_pmc *pmc) { return static_call(kvm_x86_pmu_pmc_is_enabled)(pmc); } @@ -400,6 +400,12 @@ static bool check_pmu_event_filter(struct kvm_pmc *pmc) return is_fixed_event_allowed(filter, pmc->idx); } +static bool pmc_event_is_allowed(struct kvm_pmc *pmc) +{ + return pmc_is_globally_enabled(pmc) && pmc_speculative_in_use(pmc) && + check_pmu_event_filter(pmc); +} + static void reprogram_counter(struct kvm_pmc *pmc) { struct kvm_pmu *pmu = pmc_to_pmu(pmc); @@ -409,10 +415,7 @@ static void reprogram_counter(struct kvm_pmc *pmc) pmc_pause_counter(pmc); - if (!pmc_speculative_in_use(pmc) || !pmc_is_enabled(pmc)) - goto reprogram_complete; - - if (!check_pmu_event_filter(pmc)) + if (!pmc_event_is_allowed(pmc)) goto reprogram_complete; if (pmc->counter < pmc->prev_counter) @@ -540,9 +543,9 @@ int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned idx, u64 *data) if (!pmc) return 1; - if (!(kvm_read_cr4(vcpu) & X86_CR4_PCE) && + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCE) && (static_call(kvm_x86_get_cpl)(vcpu) != 0) && - (kvm_read_cr0(vcpu) & X86_CR0_PE)) + kvm_is_cr0_bit_set(vcpu, X86_CR0_PE)) return 1; *data = pmc_read_counter(pmc) & mask; @@ -589,6 +592,10 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) */ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) { + if (KVM_BUG_ON(kvm_vcpu_has_run(vcpu), vcpu->kvm)) + return; + + bitmap_zero(vcpu_to_pmu(vcpu)->all_valid_pmc_idx, X86_PMC_IDX_MAX); static_call(kvm_x86_pmu_refresh)(vcpu); } @@ -646,7 +653,7 @@ static void kvm_pmu_incr_counter(struct kvm_pmc *pmc) { pmc->prev_counter = pmc->counter; pmc->counter = (pmc->counter + 1) & pmc_bitmask(pmc); - kvm_pmu_request_counter_reprogam(pmc); + kvm_pmu_request_counter_reprogram(pmc); } static inline bool eventsel_match_perf_hw_id(struct kvm_pmc *pmc, @@ -684,7 +691,7 @@ void kvm_pmu_trigger_event(struct kvm_vcpu *vcpu, u64 perf_hw_id) for_each_set_bit(i, pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX) { pmc = static_call(kvm_x86_pmu_pmc_idx_to_pmc)(pmu, i); - if (!pmc || !pmc_is_enabled(pmc) || !pmc_speculative_in_use(pmc)) + if (!pmc || !pmc_event_is_allowed(pmc)) continue; /* Ignore checks for edge detect, pin control, invert and CMASK bits */ diff --git a/arch/x86/kvm/pmu.h b/arch/x86/kvm/pmu.h index be62c16f2265..5c7bbf03b599 100644 --- a/arch/x86/kvm/pmu.h +++ b/arch/x86/kvm/pmu.h @@ -195,7 +195,7 @@ static inline void kvm_init_pmu_capability(const struct kvm_pmu_ops *pmu_ops) KVM_PMC_MAX_FIXED); } -static inline void kvm_pmu_request_counter_reprogam(struct kvm_pmc *pmc) +static inline void kvm_pmu_request_counter_reprogram(struct kvm_pmc *pmc) { set_bit(pmc->idx, pmc_to_pmu(pmc)->reprogram_pmi); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 05d38944a6c0..96936ddf1b3c 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -139,13 +139,18 @@ void recalc_intercepts(struct vcpu_svm *svm) if (g->int_ctl & V_INTR_MASKING_MASK) { /* - * Once running L2 with HF_VINTR_MASK, EFLAGS.IF and CR8 - * does not affect any interrupt we may want to inject; - * therefore, writes to CR8 are irrelevant to L0, as are - * interrupt window vmexits. + * If L2 is active and V_INTR_MASKING is enabled in vmcb12, + * disable intercept of CR8 writes as L2's CR8 does not affect + * any interrupt KVM may want to inject. + * + * Similarly, disable intercept of virtual interrupts (used to + * detect interrupt windows) if the saved RFLAGS.IF is '0', as + * the effective RFLAGS.IF for L1 interrupts will never be set + * while L2 is running (L2's RFLAGS.IF doesn't affect L1 IRQs). */ vmcb_clr_intercept(c, INTERCEPT_CR8_WRITE); - vmcb_clr_intercept(c, INTERCEPT_VINTR); + if (!(svm->vmcb01.ptr->save.rflags & X86_EFLAGS_IF)) + vmcb_clr_intercept(c, INTERCEPT_VINTR); } /* @@ -276,6 +281,11 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu, if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl))) return false; + if (CC((control->int_ctl & V_NMI_ENABLE_MASK) && + !vmcb12_is_intercept(control, INTERCEPT_NMI))) { + return false; + } + return true; } @@ -416,22 +426,24 @@ void nested_sync_control_from_vmcb02(struct vcpu_svm *svm) /* Only a few fields of int_ctl are written by the processor. */ mask = V_IRQ_MASK | V_TPR_MASK; - if (!(svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK) && - svm_is_intercept(svm, INTERCEPT_VINTR)) { - /* - * In order to request an interrupt window, L0 is usurping - * svm->vmcb->control.int_ctl and possibly setting V_IRQ - * even if it was clear in L1's VMCB. Restoring it would be - * wrong. However, in this case V_IRQ will remain true until - * interrupt_window_interception calls svm_clear_vintr and - * restores int_ctl. We can just leave it aside. - */ + /* + * Don't sync vmcb02 V_IRQ back to vmcb12 if KVM (L0) is intercepting + * virtual interrupts in order to request an interrupt window, as KVM + * has usurped vmcb02's int_ctl. If an interrupt window opens before + * the next VM-Exit, svm_clear_vintr() will restore vmcb12's int_ctl. + * If no window opens, V_IRQ will be correctly preserved in vmcb12's + * int_ctl (because it was never recognized while L2 was running). + */ + if (svm_is_intercept(svm, INTERCEPT_VINTR) && + !test_bit(INTERCEPT_VINTR, (unsigned long *)svm->nested.ctl.intercepts)) mask &= ~V_IRQ_MASK; - } if (nested_vgif_enabled(svm)) mask |= V_GIF_MASK; + if (nested_vnmi_enabled(svm)) + mask |= V_NMI_BLOCKING_MASK | V_NMI_PENDING_MASK; + svm->nested.ctl.int_ctl &= ~mask; svm->nested.ctl.int_ctl |= svm->vmcb->control.int_ctl & mask; } @@ -651,6 +663,17 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm, else int_ctl_vmcb01_bits |= (V_GIF_MASK | V_GIF_ENABLE_MASK); + if (vnmi) { + if (vmcb01->control.int_ctl & V_NMI_PENDING_MASK) { + svm->vcpu.arch.nmi_pending++; + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + } + if (nested_vnmi_enabled(svm)) + int_ctl_vmcb12_bits |= (V_NMI_PENDING_MASK | + V_NMI_ENABLE_MASK | + V_NMI_BLOCKING_MASK); + } + /* Copied from vmcb01. msrpm_base can be overwritten later. */ vmcb02->control.nested_ctl = vmcb01->control.nested_ctl; vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa; @@ -1021,6 +1044,28 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm_switch_vmcb(svm, &svm->vmcb01); + /* + * Rules for synchronizing int_ctl bits from vmcb02 to vmcb01: + * + * V_IRQ, V_IRQ_VECTOR, V_INTR_PRIO_MASK, V_IGN_TPR: If L1 doesn't + * intercept interrupts, then KVM will use vmcb02's V_IRQ (and related + * flags) to detect interrupt windows for L1 IRQs (even if L1 uses + * virtual interrupt masking). Raise KVM_REQ_EVENT to ensure that + * KVM re-requests an interrupt window if necessary, which implicitly + * copies this bits from vmcb02 to vmcb01. + * + * V_TPR: If L1 doesn't use virtual interrupt masking, then L1's vTPR + * is stored in vmcb02, but its value doesn't need to be copied from/to + * vmcb01 because it is copied from/to the virtual APIC's TPR register + * on each VM entry/exit. + * + * V_GIF: If nested vGIF is not used, KVM uses vmcb02's V_GIF for L1's + * V_GIF. However, GIF is architecturally clear on each VM exit, thus + * there is no need to copy V_GIF from vmcb02 to vmcb01. + */ + if (!nested_exit_on_intr(svm)) + kvm_make_request(KVM_REQ_EVENT, &svm->vcpu); + if (unlikely(svm->lbrv_enabled && (svm->nested.ctl.virt_ext & LBR_CTL_ENABLE_MASK))) { svm_copy_lbrs(vmcb12, vmcb02); svm_update_lbrv(vcpu); @@ -1029,6 +1074,20 @@ int nested_svm_vmexit(struct vcpu_svm *svm) svm_update_lbrv(vcpu); } + if (vnmi) { + if (vmcb02->control.int_ctl & V_NMI_BLOCKING_MASK) + vmcb01->control.int_ctl |= V_NMI_BLOCKING_MASK; + else + vmcb01->control.int_ctl &= ~V_NMI_BLOCKING_MASK; + + if (vcpu->arch.nmi_pending) { + vcpu->arch.nmi_pending--; + vmcb01->control.int_ctl |= V_NMI_PENDING_MASK; + } else { + vmcb01->control.int_ctl &= ~V_NMI_PENDING_MASK; + } + } + /* * On vmexit the GIF is set to false and * no event can be injected in L1. diff --git a/arch/x86/kvm/svm/pmu.c b/arch/x86/kvm/svm/pmu.c index cc77a0681800..5fa939e411d8 100644 --- a/arch/x86/kvm/svm/pmu.c +++ b/arch/x86/kvm/svm/pmu.c @@ -161,7 +161,7 @@ static int amd_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) data &= ~pmu->reserved_bits; if (data != pmc->eventsel) { pmc->eventsel = data; - kvm_pmu_request_counter_reprogam(pmc); + kvm_pmu_request_counter_reprogram(pmc); } return 0; } diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index a1b08359769b..ca32389f3c36 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -99,6 +99,7 @@ static const struct svm_direct_access_msrs { #endif { .index = MSR_IA32_SPEC_CTRL, .always = false }, { .index = MSR_IA32_PRED_CMD, .always = false }, + { .index = MSR_IA32_FLUSH_CMD, .always = false }, { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false }, { .index = MSR_IA32_LASTBRANCHTOIP, .always = false }, { .index = MSR_IA32_LASTINTFROMIP, .always = false }, @@ -234,6 +235,8 @@ module_param(dump_invalid_vmcb, bool, 0644); bool intercept_smi = true; module_param(intercept_smi, bool, 0444); +bool vnmi = true; +module_param(vnmi, bool, 0444); static bool svm_gp_erratum_intercept = true; @@ -1315,6 +1318,9 @@ static void init_vmcb(struct kvm_vcpu *vcpu) if (kvm_vcpu_apicv_active(vcpu)) avic_init_vmcb(svm, vmcb); + if (vnmi) + svm->vmcb->control.int_ctl |= V_NMI_ENABLE_MASK; + if (vgif) { svm_clr_intercept(svm, INTERCEPT_STGI); svm_clr_intercept(svm, INTERCEPT_CLGI); @@ -1588,6 +1594,16 @@ static void svm_set_vintr(struct vcpu_svm *svm) svm_set_intercept(svm, INTERCEPT_VINTR); /* + * Recalculating intercepts may have cleared the VINTR intercept. If + * V_INTR_MASKING is enabled in vmcb12, then the effective RFLAGS.IF + * for L1 physical interrupts is L1's RFLAGS.IF at the time of VMRUN. + * Requesting an interrupt window if save.RFLAGS.IF=0 is pointless as + * interrupts will never be unblocked while L2 is running. + */ + if (!svm_is_intercept(svm, INTERCEPT_VINTR)) + return; + + /* * This is just a dummy VINTR to actually cause a vmexit to happen. * Actual injection of virtual interrupts happens through EVENTINJ. */ @@ -2484,16 +2500,29 @@ static int task_switch_interception(struct kvm_vcpu *vcpu) has_error_code, error_code); } +static void svm_clr_iret_intercept(struct vcpu_svm *svm) +{ + if (!sev_es_guest(svm->vcpu.kvm)) + svm_clr_intercept(svm, INTERCEPT_IRET); +} + +static void svm_set_iret_intercept(struct vcpu_svm *svm) +{ + if (!sev_es_guest(svm->vcpu.kvm)) + svm_set_intercept(svm, INTERCEPT_IRET); +} + static int iret_interception(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); ++vcpu->stat.nmi_window_exits; svm->awaiting_iret_completion = true; - if (!sev_es_guest(vcpu->kvm)) { - svm_clr_intercept(svm, INTERCEPT_IRET); + + svm_clr_iret_intercept(svm); + if (!sev_es_guest(vcpu->kvm)) svm->nmi_iret_rip = kvm_rip_read(vcpu); - } + kvm_make_request(KVM_REQ_EVENT, vcpu); return 1; } @@ -2876,7 +2905,7 @@ static int svm_set_vm_cr(struct kvm_vcpu *vcpu, u64 data) static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) { struct vcpu_svm *svm = to_svm(vcpu); - int r; + int ret = 0; u32 ecx = msr->index; u64 data = msr->data; @@ -2946,21 +2975,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) */ set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1); break; - case MSR_IA32_PRED_CMD: - if (!msr->host_initiated && - !guest_has_pred_cmd_msr(vcpu)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - if (!boot_cpu_has(X86_FEATURE_IBPB)) - return 1; - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1); - break; case MSR_AMD64_VIRT_SPEC_CTRL: if (!msr->host_initiated && !guest_cpuid_has(vcpu, X86_FEATURE_VIRT_SSBD)) @@ -3013,10 +3027,10 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) * guest via direct_access_msrs, and switch it via user return. */ preempt_disable(); - r = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); + ret = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull); preempt_enable(); - if (r) - return 1; + if (ret) + break; svm->tsc_aux = data; break; @@ -3074,7 +3088,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) default: return kvm_set_msr_common(vcpu, msr); } - return 0; + return ret; } static int msr_interception(struct kvm_vcpu *vcpu) @@ -3485,11 +3499,43 @@ static void svm_inject_nmi(struct kvm_vcpu *vcpu) return; svm->nmi_masked = true; - if (!sev_es_guest(vcpu->kvm)) - svm_set_intercept(svm, INTERCEPT_IRET); + svm_set_iret_intercept(svm); ++vcpu->stat.nmi_injections; } +static bool svm_is_vnmi_pending(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!is_vnmi_enabled(svm)) + return false; + + return !!(svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK); +} + +static bool svm_set_vnmi_pending(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (!is_vnmi_enabled(svm)) + return false; + + if (svm->vmcb->control.int_ctl & V_NMI_PENDING_MASK) + return false; + + svm->vmcb->control.int_ctl |= V_NMI_PENDING_MASK; + vmcb_mark_dirty(svm->vmcb, VMCB_INTR); + + /* + * Because the pending NMI is serviced by hardware, KVM can't know when + * the NMI is "injected", but for all intents and purposes, passing the + * NMI off to hardware counts as injection. + */ + ++vcpu->stat.nmi_injections; + + return true; +} + static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3585,6 +3631,35 @@ static void svm_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr) svm_set_intercept(svm, INTERCEPT_CR8_WRITE); } +static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_vnmi_enabled(svm)) + return svm->vmcb->control.int_ctl & V_NMI_BLOCKING_MASK; + else + return svm->nmi_masked; +} + +static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) +{ + struct vcpu_svm *svm = to_svm(vcpu); + + if (is_vnmi_enabled(svm)) { + if (masked) + svm->vmcb->control.int_ctl |= V_NMI_BLOCKING_MASK; + else + svm->vmcb->control.int_ctl &= ~V_NMI_BLOCKING_MASK; + + } else { + svm->nmi_masked = masked; + if (masked) + svm_set_iret_intercept(svm); + else + svm_clr_iret_intercept(svm); + } +} + bool svm_nmi_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3596,8 +3671,10 @@ bool svm_nmi_blocked(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && nested_exit_on_nmi(svm)) return false; - return (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) || - svm->nmi_masked; + if (svm_get_nmi_mask(vcpu)) + return true; + + return vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK; } static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) @@ -3615,26 +3692,6 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return 1; } -static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu) -{ - return to_svm(vcpu)->nmi_masked; -} - -static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked) -{ - struct vcpu_svm *svm = to_svm(vcpu); - - if (masked) { - svm->nmi_masked = true; - if (!sev_es_guest(vcpu->kvm)) - svm_set_intercept(svm, INTERCEPT_IRET); - } else { - svm->nmi_masked = false; - if (!sev_es_guest(vcpu->kvm)) - svm_clr_intercept(svm, INTERCEPT_IRET); - } -} - bool svm_interrupt_blocked(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -3715,7 +3772,16 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); - if (svm->nmi_masked && !svm->awaiting_iret_completion) + /* + * KVM should never request an NMI window when vNMI is enabled, as KVM + * allows at most one to-be-injected NMI and one pending NMI, i.e. if + * two NMIs arrive simultaneously, KVM will inject one and set + * V_NMI_PENDING for the other. WARN, but continue with the standard + * single-step approach to try and salvage the pending NMI. + */ + WARN_ON_ONCE(is_vnmi_enabled(svm)); + + if (svm_get_nmi_mask(vcpu) && !svm->awaiting_iret_completion) return; /* IRET will cause a vm exit */ if (!gif_set(svm)) { @@ -3777,13 +3843,13 @@ static void svm_flush_tlb_all(struct kvm_vcpu *vcpu) { /* * When running on Hyper-V with EnlightenedNptTlb enabled, remote TLB - * flushes should be routed to hv_remote_flush_tlb() without requesting + * flushes should be routed to hv_flush_remote_tlbs() without requesting * a "regular" remote flush. Reaching this point means either there's - * a KVM bug or a prior hv_remote_flush_tlb() call failed, both of + * a KVM bug or a prior hv_flush_remote_tlbs() call failed, both of * which might be fatal to the guest. Yell, but try to recover. */ if (WARN_ON_ONCE(svm_hv_is_enlightened_tlb_enabled(vcpu))) - hv_remote_flush_tlb(vcpu->kvm); + hv_flush_remote_tlbs(vcpu->kvm); svm_flush_tlb_asid(vcpu); } @@ -4142,7 +4208,7 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index) { switch (index) { case MSR_IA32_MCG_EXT_CTL: - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: return false; case MSR_IA32_SMBASE: if (!IS_ENABLED(CONFIG_KVM_SMM)) @@ -4184,8 +4250,18 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) svm->vgif_enabled = vgif && guest_cpuid_has(vcpu, X86_FEATURE_VGIF); + svm->vnmi_enabled = vnmi && guest_cpuid_has(vcpu, X86_FEATURE_VNMI); + svm_recalc_instruction_intercepts(vcpu, svm); + if (boot_cpu_has(X86_FEATURE_IBPB)) + set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, + !!guest_has_pred_cmd_msr(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)); + /* For sev guests, the memory encryption bit is not reserved in CR3. */ if (sev_guest(vcpu->kvm)) { best = kvm_find_cpuid_entry(vcpu, 0x8000001F); @@ -4563,7 +4639,6 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, void *insn, int insn_len) { bool smep, smap, is_user; - unsigned long cr4; u64 error_code; /* Emulation is always possible when KVM has access to all guest state. */ @@ -4655,9 +4730,8 @@ static bool svm_can_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type, if (error_code & (PFERR_GUEST_PAGE_MASK | PFERR_FETCH_MASK)) goto resume_guest; - cr4 = kvm_read_cr4(vcpu); - smep = cr4 & X86_CR4_SMEP; - smap = cr4 & X86_CR4_SMAP; + smep = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMEP); + smap = kvm_is_cr4_bit_set(vcpu, X86_CR4_SMAP); is_user = svm_get_cpl(vcpu) == 3; if (smap && (!smep || is_user)) { pr_err_ratelimited("SEV Guest triggered AMD Erratum 1096\n"); @@ -4795,6 +4869,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .patch_hypercall = svm_patch_hypercall, .inject_irq = svm_inject_irq, .inject_nmi = svm_inject_nmi, + .is_vnmi_pending = svm_is_vnmi_pending, + .set_vnmi_pending = svm_set_vnmi_pending, .inject_exception = svm_inject_exception, .cancel_injection = svm_cancel_injection, .interrupt_allowed = svm_interrupt_allowed, @@ -4937,6 +5013,9 @@ static __init void svm_set_cpu_caps(void) if (vgif) kvm_cpu_cap_set(X86_FEATURE_VGIF); + if (vnmi) + kvm_cpu_cap_set(X86_FEATURE_VNMI); + /* Nested VM can receive #VMEXIT instead of triggering #GP */ kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK); } @@ -5088,6 +5167,16 @@ static __init int svm_hardware_setup(void) pr_info("Virtual GIF supported\n"); } + vnmi = vgif && vnmi && boot_cpu_has(X86_FEATURE_VNMI); + if (vnmi) + pr_info("Virtual NMI enabled\n"); + + if (!vnmi) { + svm_x86_ops.is_vnmi_pending = NULL; + svm_x86_ops.set_vnmi_pending = NULL; + } + + if (lbrv) { if (!boot_cpu_has(X86_FEATURE_LBRV)) lbrv = false; diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 839809972da1..f44751dd8d5d 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -36,6 +36,7 @@ extern bool npt_enabled; extern int vgif; extern bool intercept_smi; extern bool x2avic_enabled; +extern bool vnmi; /* * Clean bits in VMCB. @@ -265,6 +266,7 @@ struct vcpu_svm { bool pause_filter_enabled : 1; bool pause_threshold_enabled : 1; bool vgif_enabled : 1; + bool vnmi_enabled : 1; u32 ldr_reg; u32 dfr_reg; @@ -539,6 +541,12 @@ static inline bool nested_npt_enabled(struct vcpu_svm *svm) return svm->nested.ctl.nested_ctl & SVM_NESTED_CTL_NP_ENABLE; } +static inline bool nested_vnmi_enabled(struct vcpu_svm *svm) +{ + return svm->vnmi_enabled && + (svm->nested.ctl.int_ctl & V_NMI_ENABLE_MASK); +} + static inline bool is_x2apic_msrpm_offset(u32 offset) { /* 4 msrs per u8, and 4 u8 in u32 */ @@ -548,6 +556,27 @@ static inline bool is_x2apic_msrpm_offset(u32 offset) (msr < (APIC_BASE_MSR + 0x100)); } +static inline struct vmcb *get_vnmi_vmcb_l1(struct vcpu_svm *svm) +{ + if (!vnmi) + return NULL; + + if (is_guest_mode(&svm->vcpu)) + return NULL; + else + return svm->vmcb01.ptr; +} + +static inline bool is_vnmi_enabled(struct vcpu_svm *svm) +{ + struct vmcb *vmcb = get_vnmi_vmcb_l1(svm); + + if (vmcb) + return !!(vmcb->control.int_ctl & V_NMI_ENABLE_MASK); + else + return false; +} + /* svm.c */ #define MSR_INVALID 0xffffffffU diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h index 786d46d73a8e..f85bc617ffe4 100644 --- a/arch/x86/kvm/svm/svm_onhyperv.h +++ b/arch/x86/kvm/svm/svm_onhyperv.h @@ -45,9 +45,8 @@ static inline __init void svm_hv_hardware_setup(void) if (npt_enabled && ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB) { pr_info(KBUILD_MODNAME ": Hyper-V enlightened NPT TLB flush enabled\n"); - svm_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; - svm_x86_ops.tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; + svm_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + svm_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) { diff --git a/arch/x86/kvm/vmx/hyperv.c b/arch/x86/kvm/vmx/hyperv.c index 22daca752797..79450e1ed7cf 100644 --- a/arch/x86/kvm/vmx/hyperv.c +++ b/arch/x86/kvm/vmx/hyperv.c @@ -13,7 +13,110 @@ #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK -DEFINE_STATIC_KEY_FALSE(enable_evmcs); +/* + * Enlightened VMCSv1 doesn't support these: + * + * POSTED_INTR_NV = 0x00000002, + * GUEST_INTR_STATUS = 0x00000810, + * APIC_ACCESS_ADDR = 0x00002014, + * POSTED_INTR_DESC_ADDR = 0x00002016, + * EOI_EXIT_BITMAP0 = 0x0000201c, + * EOI_EXIT_BITMAP1 = 0x0000201e, + * EOI_EXIT_BITMAP2 = 0x00002020, + * EOI_EXIT_BITMAP3 = 0x00002022, + * GUEST_PML_INDEX = 0x00000812, + * PML_ADDRESS = 0x0000200e, + * VM_FUNCTION_CONTROL = 0x00002018, + * EPTP_LIST_ADDRESS = 0x00002024, + * VMREAD_BITMAP = 0x00002026, + * VMWRITE_BITMAP = 0x00002028, + * + * TSC_MULTIPLIER = 0x00002032, + * PLE_GAP = 0x00004020, + * PLE_WINDOW = 0x00004022, + * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, + * + * Currently unsupported in KVM: + * GUEST_IA32_RTIT_CTL = 0x00002814, + */ +#define EVMCS1_SUPPORTED_PINCTRL \ + (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + PIN_BASED_EXT_INTR_MASK | \ + PIN_BASED_NMI_EXITING | \ + PIN_BASED_VIRTUAL_NMIS) + +#define EVMCS1_SUPPORTED_EXEC_CTRL \ + (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ + CPU_BASED_HLT_EXITING | \ + CPU_BASED_CR3_LOAD_EXITING | \ + CPU_BASED_CR3_STORE_EXITING | \ + CPU_BASED_UNCOND_IO_EXITING | \ + CPU_BASED_MOV_DR_EXITING | \ + CPU_BASED_USE_TSC_OFFSETTING | \ + CPU_BASED_MWAIT_EXITING | \ + CPU_BASED_MONITOR_EXITING | \ + CPU_BASED_INVLPG_EXITING | \ + CPU_BASED_RDPMC_EXITING | \ + CPU_BASED_INTR_WINDOW_EXITING | \ + CPU_BASED_CR8_LOAD_EXITING | \ + CPU_BASED_CR8_STORE_EXITING | \ + CPU_BASED_RDTSC_EXITING | \ + CPU_BASED_TPR_SHADOW | \ + CPU_BASED_USE_IO_BITMAPS | \ + CPU_BASED_MONITOR_TRAP_FLAG | \ + CPU_BASED_USE_MSR_BITMAPS | \ + CPU_BASED_NMI_WINDOW_EXITING | \ + CPU_BASED_PAUSE_EXITING | \ + CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) + +#define EVMCS1_SUPPORTED_2NDEXEC \ + (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ + SECONDARY_EXEC_WBINVD_EXITING | \ + SECONDARY_EXEC_ENABLE_VPID | \ + SECONDARY_EXEC_ENABLE_EPT | \ + SECONDARY_EXEC_UNRESTRICTED_GUEST | \ + SECONDARY_EXEC_DESC | \ + SECONDARY_EXEC_ENABLE_RDTSCP | \ + SECONDARY_EXEC_ENABLE_INVPCID | \ + SECONDARY_EXEC_XSAVES | \ + SECONDARY_EXEC_RDSEED_EXITING | \ + SECONDARY_EXEC_RDRAND_EXITING | \ + SECONDARY_EXEC_TSC_SCALING | \ + SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ + SECONDARY_EXEC_PT_USE_GPA | \ + SECONDARY_EXEC_PT_CONCEAL_VMX | \ + SECONDARY_EXEC_BUS_LOCK_DETECTION | \ + SECONDARY_EXEC_NOTIFY_VM_EXITING | \ + SECONDARY_EXEC_ENCLS_EXITING) + +#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) + +#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ + (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_EXIT_SAVE_DEBUG_CONTROLS | \ + VM_EXIT_ACK_INTR_ON_EXIT | \ + VM_EXIT_HOST_ADDR_SPACE_SIZE | \ + VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_EXIT_SAVE_IA32_PAT | \ + VM_EXIT_LOAD_IA32_PAT | \ + VM_EXIT_SAVE_IA32_EFER | \ + VM_EXIT_LOAD_IA32_EFER | \ + VM_EXIT_CLEAR_BNDCFGS | \ + VM_EXIT_PT_CONCEAL_PIP | \ + VM_EXIT_CLEAR_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ + (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ + VM_ENTRY_LOAD_DEBUG_CONTROLS | \ + VM_ENTRY_IA32E_MODE | \ + VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ + VM_ENTRY_LOAD_IA32_PAT | \ + VM_ENTRY_LOAD_IA32_EFER | \ + VM_ENTRY_LOAD_BNDCFGS | \ + VM_ENTRY_PT_CONCEAL_PIP | \ + VM_ENTRY_LOAD_IA32_RTIT_CTL) + +#define EVMCS1_SUPPORTED_VMFUNC (0) #define EVMCS1_OFFSET(x) offsetof(struct hv_enlightened_vmcs, x) #define EVMCS1_FIELD(number, name, clean_field)[ROL16(number, 6)] = \ @@ -506,6 +609,8 @@ int nested_evmcs_check_controls(struct vmcs12 *vmcs12) } #if IS_ENABLED(CONFIG_HYPERV) +DEFINE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + /* * KVM on Hyper-V always uses the latest known eVMCSv1 revision, the assumption * is: in case a feature has corresponding fields in eVMCS described and it was diff --git a/arch/x86/kvm/vmx/hyperv.h b/arch/x86/kvm/vmx/hyperv.h index 78d17667e7ec..9623fe1651c4 100644 --- a/arch/x86/kvm/vmx/hyperv.h +++ b/arch/x86/kvm/vmx/hyperv.h @@ -16,117 +16,10 @@ struct vmcs_config; -DECLARE_STATIC_KEY_FALSE(enable_evmcs); - #define current_evmcs ((struct hv_enlightened_vmcs *)this_cpu_read(current_vmcs)) #define KVM_EVMCS_VERSION 1 -/* - * Enlightened VMCSv1 doesn't support these: - * - * POSTED_INTR_NV = 0x00000002, - * GUEST_INTR_STATUS = 0x00000810, - * APIC_ACCESS_ADDR = 0x00002014, - * POSTED_INTR_DESC_ADDR = 0x00002016, - * EOI_EXIT_BITMAP0 = 0x0000201c, - * EOI_EXIT_BITMAP1 = 0x0000201e, - * EOI_EXIT_BITMAP2 = 0x00002020, - * EOI_EXIT_BITMAP3 = 0x00002022, - * GUEST_PML_INDEX = 0x00000812, - * PML_ADDRESS = 0x0000200e, - * VM_FUNCTION_CONTROL = 0x00002018, - * EPTP_LIST_ADDRESS = 0x00002024, - * VMREAD_BITMAP = 0x00002026, - * VMWRITE_BITMAP = 0x00002028, - * - * TSC_MULTIPLIER = 0x00002032, - * PLE_GAP = 0x00004020, - * PLE_WINDOW = 0x00004022, - * VMX_PREEMPTION_TIMER_VALUE = 0x0000482E, - * - * Currently unsupported in KVM: - * GUEST_IA32_RTIT_CTL = 0x00002814, - */ -#define EVMCS1_SUPPORTED_PINCTRL \ - (PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - PIN_BASED_EXT_INTR_MASK | \ - PIN_BASED_NMI_EXITING | \ - PIN_BASED_VIRTUAL_NMIS) - -#define EVMCS1_SUPPORTED_EXEC_CTRL \ - (CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR | \ - CPU_BASED_HLT_EXITING | \ - CPU_BASED_CR3_LOAD_EXITING | \ - CPU_BASED_CR3_STORE_EXITING | \ - CPU_BASED_UNCOND_IO_EXITING | \ - CPU_BASED_MOV_DR_EXITING | \ - CPU_BASED_USE_TSC_OFFSETTING | \ - CPU_BASED_MWAIT_EXITING | \ - CPU_BASED_MONITOR_EXITING | \ - CPU_BASED_INVLPG_EXITING | \ - CPU_BASED_RDPMC_EXITING | \ - CPU_BASED_INTR_WINDOW_EXITING | \ - CPU_BASED_CR8_LOAD_EXITING | \ - CPU_BASED_CR8_STORE_EXITING | \ - CPU_BASED_RDTSC_EXITING | \ - CPU_BASED_TPR_SHADOW | \ - CPU_BASED_USE_IO_BITMAPS | \ - CPU_BASED_MONITOR_TRAP_FLAG | \ - CPU_BASED_USE_MSR_BITMAPS | \ - CPU_BASED_NMI_WINDOW_EXITING | \ - CPU_BASED_PAUSE_EXITING | \ - CPU_BASED_ACTIVATE_SECONDARY_CONTROLS) - -#define EVMCS1_SUPPORTED_2NDEXEC \ - (SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE | \ - SECONDARY_EXEC_WBINVD_EXITING | \ - SECONDARY_EXEC_ENABLE_VPID | \ - SECONDARY_EXEC_ENABLE_EPT | \ - SECONDARY_EXEC_UNRESTRICTED_GUEST | \ - SECONDARY_EXEC_DESC | \ - SECONDARY_EXEC_ENABLE_RDTSCP | \ - SECONDARY_EXEC_ENABLE_INVPCID | \ - SECONDARY_EXEC_XSAVES | \ - SECONDARY_EXEC_RDSEED_EXITING | \ - SECONDARY_EXEC_RDRAND_EXITING | \ - SECONDARY_EXEC_TSC_SCALING | \ - SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE | \ - SECONDARY_EXEC_PT_USE_GPA | \ - SECONDARY_EXEC_PT_CONCEAL_VMX | \ - SECONDARY_EXEC_BUS_LOCK_DETECTION | \ - SECONDARY_EXEC_NOTIFY_VM_EXITING | \ - SECONDARY_EXEC_ENCLS_EXITING) - -#define EVMCS1_SUPPORTED_3RDEXEC (0ULL) - -#define EVMCS1_SUPPORTED_VMEXIT_CTRL \ - (VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_EXIT_SAVE_DEBUG_CONTROLS | \ - VM_EXIT_ACK_INTR_ON_EXIT | \ - VM_EXIT_HOST_ADDR_SPACE_SIZE | \ - VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_EXIT_SAVE_IA32_PAT | \ - VM_EXIT_LOAD_IA32_PAT | \ - VM_EXIT_SAVE_IA32_EFER | \ - VM_EXIT_LOAD_IA32_EFER | \ - VM_EXIT_CLEAR_BNDCFGS | \ - VM_EXIT_PT_CONCEAL_PIP | \ - VM_EXIT_CLEAR_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMENTRY_CTRL \ - (VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | \ - VM_ENTRY_LOAD_DEBUG_CONTROLS | \ - VM_ENTRY_IA32E_MODE | \ - VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL | \ - VM_ENTRY_LOAD_IA32_PAT | \ - VM_ENTRY_LOAD_IA32_EFER | \ - VM_ENTRY_LOAD_BNDCFGS | \ - VM_ENTRY_PT_CONCEAL_PIP | \ - VM_ENTRY_LOAD_IA32_RTIT_CTL) - -#define EVMCS1_SUPPORTED_VMFUNC (0) - struct evmcs_field { u16 offset; u16 clean_field; @@ -174,6 +67,13 @@ static inline u64 evmcs_read_any(struct hv_enlightened_vmcs *evmcs, #if IS_ENABLED(CONFIG_HYPERV) +DECLARE_STATIC_KEY_FALSE(__kvm_is_using_evmcs); + +static __always_inline bool kvm_is_using_evmcs(void) +{ + return static_branch_unlikely(&__kvm_is_using_evmcs); +} + static __always_inline int get_evmcs_offset(unsigned long field, u16 *clean_field) { @@ -263,6 +163,7 @@ static inline void evmcs_load(u64 phys_addr) void evmcs_sanitize_exec_ctrls(struct vmcs_config *vmcs_conf); #else /* !IS_ENABLED(CONFIG_HYPERV) */ +static __always_inline bool kvm_is_using_evmcs(void) { return false; } static __always_inline void evmcs_write64(unsigned long field, u64 value) {} static __always_inline void evmcs_write32(unsigned long field, u32 value) {} static __always_inline void evmcs_write16(unsigned long field, u16 value) {} diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 768487611db7..e35cf0bd0df9 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -358,6 +358,7 @@ static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp) static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, gpa_t addr) { + unsigned long roots = 0; uint i; struct kvm_mmu_root_info *cached_root; @@ -368,8 +369,10 @@ static void nested_ept_invalidate_addr(struct kvm_vcpu *vcpu, gpa_t eptp, if (nested_ept_root_matches(cached_root->hpa, cached_root->pgd, eptp)) - vcpu->arch.mmu->invlpg(vcpu, addr, cached_root->hpa); + roots |= KVM_MMU_ROOT_PREVIOUS(i); } + if (roots) + kvm_mmu_invalidate_addr(vcpu, vcpu->arch.mmu, addr, roots); } static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu, @@ -654,6 +657,9 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu, nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, MSR_IA32_PRED_CMD, MSR_TYPE_W); + nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0, + MSR_IA32_FLUSH_CMD, MSR_TYPE_W); + kvm_vcpu_unmap(vcpu, &vmx->nested.msr_bitmap_map, false); vmx->nested.force_msr_bitmap_recalc = false; @@ -4483,7 +4489,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, * CR0_GUEST_HOST_MASK is already set in the original vmcs01 * (KVM doesn't change it); */ - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs12->host_cr0); /* Same as above - no reason to call set_cr4_guest_host_mask(). */ @@ -4634,7 +4640,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu) */ vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx)); - vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW)); vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK); @@ -5156,7 +5162,7 @@ static int handle_vmxon(struct kvm_vcpu *vcpu) * does force CR0.PE=1, but only to also force VM86 in order to emulate * Real Mode, and so there's no need to check CR0.PE manually. */ - if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) { + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } @@ -6755,36 +6761,9 @@ static u64 nested_vmx_calc_vmcs_enum_msr(void) return (u64)max_idx << VMCS_FIELD_INDEX_SHIFT; } -/* - * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be - * returned for the various VMX controls MSRs when nested VMX is enabled. - * The same values should also be used to verify that vmcs12 control fields are - * valid during nested entry from L1 to L2. - * Each of these control msrs has a low and high 32-bit half: A low bit is on - * if the corresponding bit in the (32-bit) control field *must* be on, and a - * bit in the high half is on if the corresponding bit in the control field - * may be on. See also vmx_control_verify(). - */ -void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) +static void nested_vmx_setup_pinbased_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) { - struct nested_vmx_msrs *msrs = &vmcs_conf->nested; - - /* - * Note that as a general rule, the high half of the MSRs (bits in - * the control fields which may be 1) should be initialized by the - * intersection of the underlying hardware's MSR (i.e., features which - * can be supported) and the list of features we want to expose - - * because they are known to be properly supported in our code. - * Also, usually, the low half of the MSRs (bits which must be 1) can - * be set to 0, meaning that L1 may turn off any of these bits. The - * reason is that if one of these bits is necessary, it will appear - * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control - * fields of vmcs01 and vmcs02, will turn these bits off - and - * nested_vmx_l1_wants_exit() will not pass related exits to L1. - * These rules have exceptions below. - */ - - /* pin-based controls */ msrs->pinbased_ctls_low = PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6797,8 +6776,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) msrs->pinbased_ctls_high |= PIN_BASED_ALWAYSON_WITHOUT_TRUE_MSR | PIN_BASED_VMX_PREEMPTION_TIMER; +} - /* exit controls */ +static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6817,8 +6799,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) /* We support free control of debug control saving. */ msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS; +} - /* entry controls */ +static void nested_vmx_setup_entry_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->entry_ctls_low = VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6834,8 +6819,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) /* We support free control of debug control loading. */ msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS; +} - /* cpu-based controls */ +static void nested_vmx_setup_cpubased_ctls(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->procbased_ctls_low = CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR; @@ -6867,12 +6855,12 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) /* We support free control of CR3 access interception. */ msrs->procbased_ctls_low &= ~(CPU_BASED_CR3_LOAD_EXITING | CPU_BASED_CR3_STORE_EXITING); +} - /* - * secondary cpu-based controls. Do not include those that - * depend on CPUID bits, they are added later by - * vmx_vcpu_after_set_cpuid. - */ +static void nested_vmx_setup_secondary_ctls(u32 ept_caps, + struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->secondary_ctls_low = 0; msrs->secondary_ctls_high = vmcs_conf->cpu_based_2nd_exec_ctrl; @@ -6950,8 +6938,11 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) if (enable_sgx) msrs->secondary_ctls_high |= SECONDARY_EXEC_ENCLS_EXITING; +} - /* miscellaneous data */ +static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf, + struct nested_vmx_msrs *msrs) +{ msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA; msrs->misc_low |= MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | @@ -6959,7 +6950,10 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) VMX_MISC_ACTIVITY_HLT | VMX_MISC_ACTIVITY_WAIT_SIPI; msrs->misc_high = 0; +} +static void nested_vmx_setup_basic(struct nested_vmx_msrs *msrs) +{ /* * This MSR reports some information about VMX support. We * should return information about the VMX we emulate for the @@ -6974,7 +6968,10 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) if (cpu_has_vmx_basic_inout()) msrs->basic |= VMX_BASIC_INOUT; +} +static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs) +{ /* * These MSRs specify bits which the guest must keep fixed on * while L1 is in VMXON mode (in L1's root mode, or running an L2). @@ -6991,6 +6988,51 @@ void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) if (vmx_umip_emulated()) msrs->cr4_fixed1 |= X86_CR4_UMIP; +} + +/* + * nested_vmx_setup_ctls_msrs() sets up variables containing the values to be + * returned for the various VMX controls MSRs when nested VMX is enabled. + * The same values should also be used to verify that vmcs12 control fields are + * valid during nested entry from L1 to L2. + * Each of these control msrs has a low and high 32-bit half: A low bit is on + * if the corresponding bit in the (32-bit) control field *must* be on, and a + * bit in the high half is on if the corresponding bit in the control field + * may be on. See also vmx_control_verify(). + */ +void nested_vmx_setup_ctls_msrs(struct vmcs_config *vmcs_conf, u32 ept_caps) +{ + struct nested_vmx_msrs *msrs = &vmcs_conf->nested; + + /* + * Note that as a general rule, the high half of the MSRs (bits in + * the control fields which may be 1) should be initialized by the + * intersection of the underlying hardware's MSR (i.e., features which + * can be supported) and the list of features we want to expose - + * because they are known to be properly supported in our code. + * Also, usually, the low half of the MSRs (bits which must be 1) can + * be set to 0, meaning that L1 may turn off any of these bits. The + * reason is that if one of these bits is necessary, it will appear + * in vmcs01 and prepare_vmcs02, when it bitwise-or's the control + * fields of vmcs01 and vmcs02, will turn these bits off - and + * nested_vmx_l1_wants_exit() will not pass related exits to L1. + * These rules have exceptions below. + */ + nested_vmx_setup_pinbased_ctls(vmcs_conf, msrs); + + nested_vmx_setup_exit_ctls(vmcs_conf, msrs); + + nested_vmx_setup_entry_ctls(vmcs_conf, msrs); + + nested_vmx_setup_cpubased_ctls(vmcs_conf, msrs); + + nested_vmx_setup_secondary_ctls(ept_caps, vmcs_conf, msrs); + + nested_vmx_setup_misc_data(vmcs_conf, msrs); + + nested_vmx_setup_basic(msrs); + + nested_vmx_setup_cr_fixed(msrs); msrs->vmcs_enum = nested_vmx_calc_vmcs_enum_msr(); } diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index e8a3be0b9df9..741efe2c497b 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -57,7 +57,7 @@ static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data) pmc = get_fixed_pmc(pmu, MSR_CORE_PERF_FIXED_CTR0 + i); __set_bit(INTEL_PMC_IDX_FIXED + i, pmu->pmc_in_use); - kvm_pmu_request_counter_reprogam(pmc); + kvm_pmu_request_counter_reprogram(pmc); } } @@ -76,13 +76,13 @@ static struct kvm_pmc *intel_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx) static void reprogram_counters(struct kvm_pmu *pmu, u64 diff) { int bit; - struct kvm_pmc *pmc; - for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) { - pmc = intel_pmc_idx_to_pmc(pmu, bit); - if (pmc) - kvm_pmu_request_counter_reprogam(pmc); - } + if (!diff) + return; + + for_each_set_bit(bit, (unsigned long *)&diff, X86_PMC_IDX_MAX) + set_bit(bit, pmu->reprogram_pmi); + kvm_make_request(KVM_REQ_PMU, pmu_to_vcpu(pmu)); } static bool intel_hw_event_available(struct kvm_pmc *pmc) @@ -351,45 +351,47 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: msr_info->data = pmu->fixed_ctr_ctrl; - return 0; + break; case MSR_CORE_PERF_GLOBAL_STATUS: msr_info->data = pmu->global_status; - return 0; + break; case MSR_CORE_PERF_GLOBAL_CTRL: msr_info->data = pmu->global_ctrl; - return 0; + break; case MSR_CORE_PERF_GLOBAL_OVF_CTRL: msr_info->data = 0; - return 0; + break; case MSR_IA32_PEBS_ENABLE: msr_info->data = pmu->pebs_enable; - return 0; + break; case MSR_IA32_DS_AREA: msr_info->data = pmu->ds_area; - return 0; + break; case MSR_PEBS_DATA_CFG: msr_info->data = pmu->pebs_data_cfg; - return 0; + break; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || (pmc = get_gp_pmc(pmu, msr, MSR_IA32_PMC0))) { u64 val = pmc_read_counter(pmc); msr_info->data = val & pmu->counter_bitmask[KVM_PMC_GP]; - return 0; + break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { u64 val = pmc_read_counter(pmc); msr_info->data = val & pmu->counter_bitmask[KVM_PMC_FIXED]; - return 0; + break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { msr_info->data = pmc->eventsel; - return 0; - } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, true)) - return 0; + break; + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, true)) { + break; + } + return 1; } - return 1; + return 0; } static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) @@ -402,44 +404,43 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) switch (msr) { case MSR_CORE_PERF_FIXED_CTR_CTRL: - if (pmu->fixed_ctr_ctrl == data) - return 0; - if (!(data & pmu->fixed_ctr_ctrl_mask)) { + if (data & pmu->fixed_ctr_ctrl_mask) + return 1; + + if (pmu->fixed_ctr_ctrl != data) reprogram_fixed_counters(pmu, data); - return 0; - } break; case MSR_CORE_PERF_GLOBAL_STATUS: - if (msr_info->host_initiated) { - pmu->global_status = data; - return 0; - } - break; /* RO MSR */ + if (!msr_info->host_initiated) + return 1; /* RO MSR */ + + pmu->global_status = data; + break; case MSR_CORE_PERF_GLOBAL_CTRL: - if (pmu->global_ctrl == data) - return 0; - if (kvm_valid_perf_global_ctrl(pmu, data)) { + if (!kvm_valid_perf_global_ctrl(pmu, data)) + return 1; + + if (pmu->global_ctrl != data) { diff = pmu->global_ctrl ^ data; pmu->global_ctrl = data; reprogram_counters(pmu, diff); - return 0; } break; case MSR_CORE_PERF_GLOBAL_OVF_CTRL: - if (!(data & pmu->global_ovf_ctrl_mask)) { - if (!msr_info->host_initiated) - pmu->global_status &= ~data; - return 0; - } + if (data & pmu->global_ovf_ctrl_mask) + return 1; + + if (!msr_info->host_initiated) + pmu->global_status &= ~data; break; case MSR_IA32_PEBS_ENABLE: - if (pmu->pebs_enable == data) - return 0; - if (!(data & pmu->pebs_enable_mask)) { + if (data & pmu->pebs_enable_mask) + return 1; + + if (pmu->pebs_enable != data) { diff = pmu->pebs_enable ^ data; pmu->pebs_enable = data; reprogram_counters(pmu, diff); - return 0; } break; case MSR_IA32_DS_AREA: @@ -447,15 +448,14 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) return 1; if (is_noncanonical_address(data, vcpu)) return 1; + pmu->ds_area = data; - return 0; + break; case MSR_PEBS_DATA_CFG: - if (pmu->pebs_data_cfg == data) - return 0; - if (!(data & pmu->pebs_data_cfg_mask)) { - pmu->pebs_data_cfg = data; - return 0; - } + if (data & pmu->pebs_data_cfg_mask) + return 1; + + pmu->pebs_data_cfg = data; break; default: if ((pmc = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0)) || @@ -463,33 +463,38 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if ((msr & MSR_PMC_FULL_WIDTH_BIT) && (data & ~pmu->counter_bitmask[KVM_PMC_GP])) return 1; + if (!msr_info->host_initiated && !(msr & MSR_PMC_FULL_WIDTH_BIT)) data = (s64)(s32)data; pmc->counter += data - pmc_read_counter(pmc); pmc_update_sample_period(pmc); - return 0; + break; } else if ((pmc = get_fixed_pmc(pmu, msr))) { pmc->counter += data - pmc_read_counter(pmc); pmc_update_sample_period(pmc); - return 0; + break; } else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) { - if (data == pmc->eventsel) - return 0; reserved_bits = pmu->reserved_bits; if ((pmc->idx == 2) && (pmu->raw_event_mask & HSW_IN_TX_CHECKPOINTED)) reserved_bits ^= HSW_IN_TX_CHECKPOINTED; - if (!(data & reserved_bits)) { + if (data & reserved_bits) + return 1; + + if (data != pmc->eventsel) { pmc->eventsel = data; - kvm_pmu_request_counter_reprogam(pmc); - return 0; + kvm_pmu_request_counter_reprogram(pmc); } - } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) - return 0; + break; + } else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false)) { + break; + } + /* Not a known PMU MSR. */ + return 1; } - return 1; + return 0; } static void setup_fixed_pmc_eventsel(struct kvm_pmu *pmu) @@ -531,6 +536,16 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) pmu->pebs_enable_mask = ~0ull; pmu->pebs_data_cfg_mask = ~0ull; + memset(&lbr_desc->records, 0, sizeof(lbr_desc->records)); + + /* + * Setting passthrough of LBR MSRs is done only in the VM-Entry loop, + * and PMU refresh is disallowed after the vCPU has run, i.e. this code + * should never be reached while KVM is passing through MSRs. + */ + if (KVM_BUG_ON(lbr_desc->msr_passthrough, vcpu->kvm)) + return; + entry = kvm_find_cpuid_entry(vcpu, 0xa); if (!entry || !vcpu->kvm->arch.enable_pmu) return; diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c index aa53c98034bf..0574030b071f 100644 --- a/arch/x86/kvm/vmx/sgx.c +++ b/arch/x86/kvm/vmx/sgx.c @@ -29,14 +29,14 @@ static int sgx_get_encls_gva(struct kvm_vcpu *vcpu, unsigned long offset, /* Skip vmcs.GUEST_DS retrieval for 64-bit mode to avoid VMREADs. */ *gva = offset; - if (!is_long_mode(vcpu)) { + if (!is_64_bit_mode(vcpu)) { vmx_get_segment(vcpu, &s, VCPU_SREG_DS); *gva += s.base; } if (!IS_ALIGNED(*gva, alignment)) { fault = true; - } else if (likely(is_long_mode(vcpu))) { + } else if (likely(is_64_bit_mode(vcpu))) { fault = is_noncanonical_address(*gva, vcpu); } else { *gva &= 0xffffffff; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index d2d6e1b6c788..44fb619803b8 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -164,6 +164,7 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO); static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = { MSR_IA32_SPEC_CTRL, MSR_IA32_PRED_CMD, + MSR_IA32_FLUSH_CMD, MSR_IA32_TSC, #ifdef CONFIG_X86_64 MSR_FS_BASE, @@ -579,7 +580,7 @@ static __init void hv_init_evmcs(void) if (enlightened_vmcs) { pr_info("Using Hyper-V Enlightened VMCS\n"); - static_branch_enable(&enable_evmcs); + static_branch_enable(&__kvm_is_using_evmcs); } if (ms_hyperv.nested_features & HV_X64_NESTED_DIRECT_FLUSH) @@ -595,7 +596,7 @@ static void hv_reset_evmcs(void) { struct hv_vp_assist_page *vp_ap; - if (!static_branch_unlikely(&enable_evmcs)) + if (!kvm_is_using_evmcs()) return; /* @@ -1945,7 +1946,7 @@ static inline bool is_vmx_feature_control_msr_valid(struct vcpu_vmx *vmx, static int vmx_get_msr_feature(struct kvm_msr_entry *msr) { switch (msr->index) { - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested) return 1; return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data); @@ -2030,7 +2031,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) msr_info->data = to_vmx(vcpu)->msr_ia32_sgxlepubkeyhash [msr_info->index - MSR_IA32_SGXLEPUBKEYHASH0]; break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!nested_vmx_allowed(vcpu)) return 1; if (vmx_get_vmx_msr(&vmx->nested.msrs, msr_info->index, @@ -2285,33 +2286,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~(TSX_CTRL_RTM_DISABLE | TSX_CTRL_CPUID_CLEAR)) return 1; goto find_uret_msr; - case MSR_IA32_PRED_CMD: - if (!msr_info->host_initiated && - !guest_has_pred_cmd_msr(vcpu)) - return 1; - - if (data & ~PRED_CMD_IBPB) - return 1; - if (!boot_cpu_has(X86_FEATURE_IBPB)) - return 1; - if (!data) - break; - - wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); - - /* - * For non-nested: - * When it's written (to non-zero) for the first time, pass - * it through. - * - * For nested: - * The handling of the MSR bitmap for L2 guests is done in - * nested_vmx_prepare_msr_bitmap. We should not touch the - * vmcs02.msr_bitmap here since it gets completely overwritten - * in the merging. - */ - vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W); - break; case MSR_IA32_CR_PAT: if (!kvm_pat_valid(data)) return 1; @@ -2366,7 +2340,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) vmx->msr_ia32_sgxlepubkeyhash [msr_index - MSR_IA32_SGXLEPUBKEYHASH0] = data; break; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: if (!msr_info->host_initiated) return 1; /* they are read-only */ if (!nested_vmx_allowed(vcpu)) @@ -2816,8 +2790,7 @@ static int vmx_hardware_enable(void) * This can happen if we hot-added a CPU but failed to allocate * VP assist page for it. */ - if (static_branch_unlikely(&enable_evmcs) && - !hv_get_vp_assist_page(cpu)) + if (kvm_is_using_evmcs() && !hv_get_vp_assist_page(cpu)) return -EFAULT; intel_pt_handle_vmx(1); @@ -2869,7 +2842,7 @@ struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags) memset(vmcs, 0, vmcs_config.size); /* KVM supports Enlightened VMCS v1 only */ - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = KVM_EVMCS_VERSION; else vmcs->hdr.revision_id = vmcs_config.revision_id; @@ -2964,7 +2937,7 @@ static __init int alloc_kvm_area(void) * still be marked with revision_id reported by * physical CPU. */ - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) vmcs->hdr.revision_id = vmcs_config.revision_id; per_cpu(vmxarea, cpu) = vmcs; @@ -3931,7 +3904,7 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx) * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR * bitmap has changed. */ - if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs)) { + if (kvm_is_using_evmcs()) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; if (evmcs->hv_enlightenments_control.msr_bitmap) @@ -4773,7 +4746,7 @@ static void init_vmcs(struct vcpu_vmx *vmx) /* 22.2.1, 20.8.1 */ vm_entry_controls_set(vmx, vmx_vmentry_ctrl()); - vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS; + vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits(); vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits); set_cr4_guest_host_mask(vmx); @@ -5163,7 +5136,7 @@ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu) if (!boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT)) return true; - return vmx_get_cpl(vcpu) == 3 && kvm_read_cr0_bits(vcpu, X86_CR0_AM) && + return vmx_get_cpl(vcpu) == 3 && kvm_is_cr0_bit_set(vcpu, X86_CR0_AM) && (kvm_get_rflags(vcpu) & X86_EFLAGS_AC); } @@ -5500,7 +5473,7 @@ static int handle_cr(struct kvm_vcpu *vcpu) break; case 3: /* lmsw */ val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f; - trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val); + trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val)); kvm_lmsw(vcpu, val); return kvm_skip_emulated_instruction(vcpu); @@ -6957,7 +6930,7 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index) * real mode. */ return enable_unrestricted_guest || emulate_invalid_guest_state; - case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC: + case KVM_FIRST_EMULATED_VMX_MSR ... KVM_LAST_EMULATED_VMX_MSR: return nested; case MSR_AMD64_VIRT_SPEC_CTRL: case MSR_AMD64_TSC_RATIO: @@ -7310,7 +7283,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu) vmx_vcpu_enter_exit(vcpu, __vmx_vcpu_run_flags(vmx)); /* All fields are clean at this point */ - if (static_branch_unlikely(&enable_evmcs)) { + if (kvm_is_using_evmcs()) { current_evmcs->hv_clean_fields |= HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL; @@ -7440,7 +7413,7 @@ static int vmx_vcpu_create(struct kvm_vcpu *vcpu) * feature only for vmcs01, KVM currently isn't equipped to realize any * performance benefits from enabling it for vmcs02. */ - if (IS_ENABLED(CONFIG_HYPERV) && static_branch_unlikely(&enable_evmcs) && + if (kvm_is_using_evmcs() && (ms_hyperv.nested_features & HV_X64_NESTED_MSR_BITMAP)) { struct hv_enlightened_vmcs *evmcs = (void *)vmx->vmcs01.vmcs; @@ -7558,7 +7531,7 @@ static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT; - if (kvm_read_cr0(vcpu) & X86_CR0_CD) { + if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) { if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) cache = MTRR_TYPE_WRBACK; else @@ -7744,6 +7717,13 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R, !guest_cpuid_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, + !guest_has_pred_cmd_msr(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)); set_cr4_guest_host_mask(vmx); @@ -7776,9 +7756,11 @@ static u64 vmx_get_perf_capabilities(void) if (boot_cpu_has(X86_FEATURE_PDCM)) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); - x86_perf_get_lbr(&lbr); - if (lbr.nr) - perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { + x86_perf_get_lbr(&lbr); + if (lbr.nr) + perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; + } if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; @@ -7918,6 +7900,21 @@ static int vmx_check_intercept(struct kvm_vcpu *vcpu, /* FIXME: produce nested vmexit and return X86EMUL_INTERCEPTED. */ break; + case x86_intercept_pause: + /* + * PAUSE is a single-byte NOP with a REPE prefix, i.e. collides + * with vanilla NOPs in the emulator. Apply the interception + * check only to actual PAUSE instructions. Don't check + * PAUSE-loop-exiting, software can't expect a given PAUSE to + * exit, i.e. KVM is within its rights to allow L2 to execute + * the PAUSE. + */ + if ((info->rep_prefix != REPE_PREFIX) || + !nested_cpu_has2(vmcs12, CPU_BASED_PAUSE_EXITING)) + return X86EMUL_CONTINUE; + + break; + /* TODO: check more intercepts... */ default: break; @@ -8415,9 +8412,8 @@ static __init int hardware_setup(void) #if IS_ENABLED(CONFIG_HYPERV) if (ms_hyperv.nested_features & HV_X64_NESTED_GUEST_MAPPING_FLUSH && enable_ept) { - vmx_x86_ops.tlb_remote_flush = hv_remote_flush_tlb; - vmx_x86_ops.tlb_remote_flush_with_range = - hv_remote_flush_tlb_with_range; + vmx_x86_ops.flush_remote_tlbs = hv_flush_remote_tlbs; + vmx_x86_ops.flush_remote_tlbs_range = hv_flush_remote_tlbs_range; } #endif diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 2acdc54bc34b..9e66531861cf 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -369,7 +369,7 @@ struct vcpu_vmx { struct lbr_desc lbr_desc; /* Save desired MSR intercept (read: pass-through) state */ -#define MAX_POSSIBLE_PASSTHROUGH_MSRS 15 +#define MAX_POSSIBLE_PASSTHROUGH_MSRS 16 struct { DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS); DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS); @@ -640,6 +640,24 @@ BUILD_CONTROLS_SHADOW(tertiary_exec, TERTIARY_VM_EXEC_CONTROL, 64) (1 << VCPU_EXREG_EXIT_INFO_1) | \ (1 << VCPU_EXREG_EXIT_INFO_2)) +static inline unsigned long vmx_l1_guest_owned_cr0_bits(void) +{ + unsigned long bits = KVM_POSSIBLE_CR0_GUEST_BITS; + + /* + * CR0.WP needs to be intercepted when KVM is shadowing legacy paging + * in order to construct shadow PTEs with the correct protections. + * Note! CR0.WP technically can be passed through to the guest if + * paging is disabled, but checking CR0.PG would generate a cyclical + * dependency of sorts due to forcing the caller to ensure CR0 holds + * the correct value prior to determining which CR0 bits can be owned + * by L1. Keep it simple and limit the optimization to EPT. + */ + if (!enable_ept) + bits &= ~X86_CR0_WP; + return bits; +} + static __always_inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm) { return container_of(kvm, struct kvm_vmx, kvm); diff --git a/arch/x86/kvm/vmx/vmx_ops.h b/arch/x86/kvm/vmx/vmx_ops.h index db95bde52998..ce47dc265f89 100644 --- a/arch/x86/kvm/vmx/vmx_ops.h +++ b/arch/x86/kvm/vmx/vmx_ops.h @@ -147,7 +147,7 @@ do_exception: static __always_inline u16 vmcs_read16(unsigned long field) { vmcs_check16(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read16(field); return __vmcs_readl(field); } @@ -155,7 +155,7 @@ static __always_inline u16 vmcs_read16(unsigned long field) static __always_inline u32 vmcs_read32(unsigned long field) { vmcs_check32(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read32(field); return __vmcs_readl(field); } @@ -163,7 +163,7 @@ static __always_inline u32 vmcs_read32(unsigned long field) static __always_inline u64 vmcs_read64(unsigned long field) { vmcs_check64(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read64(field); #ifdef CONFIG_X86_64 return __vmcs_readl(field); @@ -175,7 +175,7 @@ static __always_inline u64 vmcs_read64(unsigned long field) static __always_inline unsigned long vmcs_readl(unsigned long field) { vmcs_checkl(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_read64(field); return __vmcs_readl(field); } @@ -222,7 +222,7 @@ static __always_inline void __vmcs_writel(unsigned long field, unsigned long val static __always_inline void vmcs_write16(unsigned long field, u16 value) { vmcs_check16(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write16(field, value); __vmcs_writel(field, value); @@ -231,7 +231,7 @@ static __always_inline void vmcs_write16(unsigned long field, u16 value) static __always_inline void vmcs_write32(unsigned long field, u32 value) { vmcs_check32(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write32(field, value); __vmcs_writel(field, value); @@ -240,7 +240,7 @@ static __always_inline void vmcs_write32(unsigned long field, u32 value) static __always_inline void vmcs_write64(unsigned long field, u64 value) { vmcs_check64(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write64(field, value); __vmcs_writel(field, value); @@ -252,7 +252,7 @@ static __always_inline void vmcs_write64(unsigned long field, u64 value) static __always_inline void vmcs_writel(unsigned long field, unsigned long value) { vmcs_checkl(field); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write64(field, value); __vmcs_writel(field, value); @@ -262,7 +262,7 @@ static __always_inline void vmcs_clear_bits(unsigned long field, u32 mask) { BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, "vmcs_clear_bits does not support 64-bit fields"); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write32(field, evmcs_read32(field) & ~mask); __vmcs_writel(field, __vmcs_readl(field) & ~mask); @@ -272,7 +272,7 @@ static __always_inline void vmcs_set_bits(unsigned long field, u32 mask) { BUILD_BUG_ON_MSG(__builtin_constant_p(field) && ((field) & 0x6000) == 0x2000, "vmcs_set_bits does not support 64-bit fields"); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_write32(field, evmcs_read32(field) | mask); __vmcs_writel(field, __vmcs_readl(field) | mask); @@ -289,7 +289,7 @@ static inline void vmcs_load(struct vmcs *vmcs) { u64 phys_addr = __pa(vmcs); - if (static_branch_unlikely(&enable_evmcs)) + if (kvm_is_using_evmcs()) return evmcs_load(phys_addr); vmx_asm1(vmptrld, "m"(phys_addr), vmcs, phys_addr); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2b1d82647195..ceb7c5e9cf9e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -196,7 +196,7 @@ bool __read_mostly eager_page_split = true; module_param(eager_page_split, bool, 0644); /* Enable/disable SMT_RSB bug mitigation */ -bool __read_mostly mitigate_smt_rsb; +static bool __read_mostly mitigate_smt_rsb; module_param(mitigate_smt_rsb, bool, 0444); /* @@ -804,8 +804,8 @@ void kvm_inject_emulated_page_fault(struct kvm_vcpu *vcpu, */ if ((fault->error_code & PFERR_PRESENT_MASK) && !(fault->error_code & PFERR_RSVD_MASK)) - kvm_mmu_invalidate_gva(vcpu, fault_mmu, fault->address, - fault_mmu->root.hpa); + kvm_mmu_invalidate_addr(vcpu, fault_mmu, fault->address, + KVM_MMU_ROOT_CURRENT); fault_mmu->inject_page_fault(vcpu, fault); } @@ -843,7 +843,7 @@ bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl) bool kvm_require_dr(struct kvm_vcpu *vcpu, int dr) { - if ((dr != 4 && dr != 5) || !kvm_read_cr4_bits(vcpu, X86_CR4_DE)) + if ((dr != 4 && dr != 5) || !kvm_is_cr4_bit_set(vcpu, X86_CR4_DE)) return true; kvm_queue_exception(vcpu, UD_VECTOR); @@ -908,6 +908,24 @@ EXPORT_SYMBOL_GPL(load_pdptrs); void kvm_post_set_cr0(struct kvm_vcpu *vcpu, unsigned long old_cr0, unsigned long cr0) { + /* + * CR0.WP is incorporated into the MMU role, but only for non-nested, + * indirect shadow MMUs. If paging is disabled, no updates are needed + * as there are no permission bits to emulate. If TDP is enabled, the + * MMU's metadata needs to be updated, e.g. so that emulating guest + * translations does the right thing, but there's no need to unload the + * root as CR0.WP doesn't affect SPTEs. + */ + if ((cr0 ^ old_cr0) == X86_CR0_WP) { + if (!(cr0 & X86_CR0_PG)) + return; + + if (tdp_enabled) { + kvm_init_mmu(vcpu); + return; + } + } + if ((cr0 ^ old_cr0) & X86_CR0_PG) { kvm_clear_async_pf_completion_queue(vcpu); kvm_async_pf_hash_reset(vcpu); @@ -967,7 +985,7 @@ int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) return 1; if (!(cr0 & X86_CR0_PG) && - (is_64_bit_mode(vcpu) || kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE))) + (is_64_bit_mode(vcpu) || kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE))) return 1; static_call(kvm_x86_set_cr0)(vcpu, cr0); @@ -989,7 +1007,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) if (vcpu->arch.guest_state_protected) return; - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0); @@ -1003,7 +1021,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu) if (static_cpu_has(X86_FEATURE_PKU) && vcpu->arch.pkru != vcpu->arch.host_pkru && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || - kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) + kvm_is_cr4_bit_set(vcpu, X86_CR4_PKE))) write_pkru(vcpu->arch.pkru); #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ } @@ -1017,14 +1035,14 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu) #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS if (static_cpu_has(X86_FEATURE_PKU) && ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) || - kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) { + 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); } #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */ - if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) { + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_OSXSAVE)) { if (vcpu->arch.xcr0 != host_xcr0) xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0); @@ -1180,9 +1198,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4) return 1; if ((cr4 & X86_CR4_PCIDE) && !(old_cr4 & X86_CR4_PCIDE)) { - if (!guest_cpuid_has(vcpu, X86_FEATURE_PCID)) - return 1; - /* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */ if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu)) return 1; @@ -1229,7 +1244,7 @@ static void kvm_invalidate_pcid(struct kvm_vcpu *vcpu, unsigned long pcid) * PCIDs for them are also 0, because MOV to CR3 always flushes the TLB * with PCIDE=0. */ - if (!kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) + if (!kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) return; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) @@ -1244,9 +1259,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) bool skip_tlb_flush = false; unsigned long pcid = 0; #ifdef CONFIG_X86_64 - bool pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); - - if (pcid_enabled) { + if (kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE)) { skip_tlb_flush = cr3 & X86_CR3_PCID_NOFLUSH; cr3 &= ~X86_CR3_PCID_NOFLUSH; pcid = cr3 & X86_CR3_PCID_MASK; @@ -1545,39 +1558,41 @@ static u32 emulated_msrs[ARRAY_SIZE(emulated_msrs_all)]; static unsigned num_emulated_msrs; /* - * List of msr numbers which are used to expose MSR-based features that - * can be used by a hypervisor to validate requested CPU features. + * List of MSRs that control the existence of MSR-based features, i.e. MSRs + * that are effectively CPUID leafs. VMX MSRs are also included in the set of + * feature MSRs, but are handled separately to allow expedited lookups. */ -static const u32 msr_based_features_all[] = { - MSR_IA32_VMX_BASIC, - MSR_IA32_VMX_TRUE_PINBASED_CTLS, - MSR_IA32_VMX_PINBASED_CTLS, - MSR_IA32_VMX_TRUE_PROCBASED_CTLS, - MSR_IA32_VMX_PROCBASED_CTLS, - MSR_IA32_VMX_TRUE_EXIT_CTLS, - MSR_IA32_VMX_EXIT_CTLS, - MSR_IA32_VMX_TRUE_ENTRY_CTLS, - MSR_IA32_VMX_ENTRY_CTLS, - MSR_IA32_VMX_MISC, - MSR_IA32_VMX_CR0_FIXED0, - MSR_IA32_VMX_CR0_FIXED1, - MSR_IA32_VMX_CR4_FIXED0, - MSR_IA32_VMX_CR4_FIXED1, - MSR_IA32_VMX_VMCS_ENUM, - MSR_IA32_VMX_PROCBASED_CTLS2, - MSR_IA32_VMX_EPT_VPID_CAP, - MSR_IA32_VMX_VMFUNC, - +static const u32 msr_based_features_all_except_vmx[] = { MSR_AMD64_DE_CFG, MSR_IA32_UCODE_REV, MSR_IA32_ARCH_CAPABILITIES, MSR_IA32_PERF_CAPABILITIES, }; -static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all)]; +static u32 msr_based_features[ARRAY_SIZE(msr_based_features_all_except_vmx) + + (KVM_LAST_EMULATED_VMX_MSR - KVM_FIRST_EMULATED_VMX_MSR + 1)]; static unsigned int num_msr_based_features; /* + * All feature MSRs except uCode revID, which tracks the currently loaded uCode + * patch, are immutable once the vCPU model is defined. + */ +static bool kvm_is_immutable_feature_msr(u32 msr) +{ + int i; + + if (msr >= KVM_FIRST_EMULATED_VMX_MSR && msr <= KVM_LAST_EMULATED_VMX_MSR) + return true; + + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) { + if (msr == msr_based_features_all_except_vmx[i]) + return msr != MSR_IA32_UCODE_REV; + } + + return false; +} + +/* * Some IA32_ARCH_CAPABILITIES bits have dependencies on MSRs that KVM * does not yet virtualize. These include: * 10 - MISC_PACKAGE_CTRLS @@ -2194,6 +2209,22 @@ static int do_get_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data) { + u64 val; + + /* + * Disallow writes to immutable feature MSRs after KVM_RUN. KVM does + * not support modifying the guest vCPU model on the fly, e.g. changing + * the nVMX capabilities while L2 is running is nonsensical. Ignore + * writes of the same value, e.g. to allow userspace to blindly stuff + * all MSRs when emulating RESET. + */ + if (kvm_vcpu_has_run(vcpu) && kvm_is_immutable_feature_msr(index)) { + if (do_get_msr(vcpu, index, &val) || *data != val) + return -EINVAL; + + return 0; + } + return kvm_set_msr_ignored_check(vcpu, index, *data, true); } @@ -3616,9 +3647,40 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) if (data & ~kvm_caps.supported_perf_cap) return 1; + /* + * Note, this is not just a performance optimization! KVM + * disallows changing feature MSRs after the vCPU has run; PMU + * refresh will bug the VM if called after the vCPU has run. + */ + if (vcpu->arch.perf_capabilities == data) + break; + vcpu->arch.perf_capabilities = data; kvm_pmu_refresh(vcpu); - return 0; + break; + case MSR_IA32_PRED_CMD: + if (!msr_info->host_initiated && !guest_has_pred_cmd_msr(vcpu)) + return 1; + + if (!boot_cpu_has(X86_FEATURE_IBPB) || (data & ~PRED_CMD_IBPB)) + return 1; + if (!data) + break; + + wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB); + break; + case MSR_IA32_FLUSH_CMD: + if (!msr_info->host_initiated && + !guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D)) + return 1; + + if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D) || (data & ~L1D_FLUSH)) + return 1; + if (!data) + break; + + wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH); + break; case MSR_EFER: return set_efer(vcpu, msr_info); case MSR_K7_HWCR: @@ -4534,9 +4596,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = 0; break; case KVM_CAP_XSAVE2: { - u64 guest_perm = xstate_get_guest_group_perm(); - - r = xstate_required_size(kvm_caps.supported_xcr0 & guest_perm, false); + r = xstate_required_size(kvm_get_filtered_xcr0(), false); if (r < sizeof(struct kvm_xsave)) r = sizeof(struct kvm_xsave); break; @@ -5036,7 +5096,7 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu, return 0; if (mce->status & MCI_STATUS_UC) { if ((vcpu->arch.mcg_status & MCG_STATUS_MCIP) || - !kvm_read_cr4_bits(vcpu, X86_CR4_MCE)) { + !kvm_is_cr4_bit_set(vcpu, X86_CR4_MCE)) { kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu); return 0; } @@ -5128,7 +5188,7 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu); events->nmi.injected = vcpu->arch.nmi_injected; - events->nmi.pending = vcpu->arch.nmi_pending != 0; + events->nmi.pending = kvm_get_nr_pending_nmis(vcpu); events->nmi.masked = static_call(kvm_x86_get_nmi_mask)(vcpu); /* events->sipi_vector is never valid when reporting to user space */ @@ -5215,8 +5275,11 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu, events->interrupt.shadow); vcpu->arch.nmi_injected = events->nmi.injected; - if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) - vcpu->arch.nmi_pending = events->nmi.pending; + if (events->flags & KVM_VCPUEVENT_VALID_NMI_PENDING) { + vcpu->arch.nmi_pending = 0; + atomic_set(&vcpu->arch.nmi_queued, events->nmi.pending); + kvm_make_request(KVM_REQ_NMI, vcpu); + } static_call(kvm_x86_set_nmi_mask)(vcpu, events->nmi.masked); if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR && @@ -6024,11 +6087,6 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm, return 0; } -static unsigned long kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm) -{ - return kvm->arch.n_max_mmu_pages; -} - static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip) { struct kvm_pic *pic = kvm->arch.vpic; @@ -6675,8 +6733,7 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) return 0; } -long kvm_arch_vm_ioctl(struct file *filp, - unsigned int ioctl, unsigned long arg) +int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; @@ -6714,9 +6771,6 @@ set_identity_unlock: case KVM_SET_NR_MMU_PAGES: r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg); break; - case KVM_GET_NR_MMU_PAGES: - r = kvm_vm_ioctl_get_nr_mmu_pages(kvm); - break; case KVM_CREATE_IRQCHIP: { mutex_lock(&kvm->lock); @@ -7021,6 +7075,18 @@ out: return r; } +static void kvm_probe_feature_msr(u32 msr_index) +{ + struct kvm_msr_entry msr = { + .index = msr_index, + }; + + if (kvm_get_msr_feature(&msr)) + return; + + msr_based_features[num_msr_based_features++] = msr_index; +} + static void kvm_probe_msr_to_save(u32 msr_index) { u32 dummy[2]; @@ -7096,7 +7162,7 @@ static void kvm_probe_msr_to_save(u32 msr_index) msrs_to_save[num_msrs_to_save++] = msr_index; } -static void kvm_init_msr_list(void) +static void kvm_init_msr_lists(void) { unsigned i; @@ -7122,15 +7188,11 @@ static void kvm_init_msr_list(void) emulated_msrs[num_emulated_msrs++] = emulated_msrs_all[i]; } - for (i = 0; i < ARRAY_SIZE(msr_based_features_all); i++) { - struct kvm_msr_entry msr; + for (i = KVM_FIRST_EMULATED_VMX_MSR; i <= KVM_LAST_EMULATED_VMX_MSR; i++) + kvm_probe_feature_msr(i); - msr.index = msr_based_features_all[i]; - if (kvm_get_msr_feature(&msr)) - continue; - - msr_based_features[num_msr_based_features++] = msr_based_features_all[i]; - } + for (i = 0; i < ARRAY_SIZE(msr_based_features_all_except_vmx); i++) + kvm_probe_feature_msr(msr_based_features_all_except_vmx[i]); } static int vcpu_mmio_write(struct kvm_vcpu *vcpu, gpa_t addr, int len, @@ -8466,7 +8528,6 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) } static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, - bool write_fault_to_shadow_pgtable, int emulation_type) { gpa_t gpa = cr2_or_gpa; @@ -8537,7 +8598,7 @@ static bool reexecute_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, * be fixed by unprotecting shadow page and it should * be reported to userspace. */ - return !write_fault_to_shadow_pgtable; + return !(emulation_type & EMULTYPE_WRITE_PF_TO_SP); } static bool retry_instruction(struct x86_emulate_ctxt *ctxt, @@ -8785,20 +8846,12 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int r; struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; bool writeback = true; - bool write_fault_to_spt; if (unlikely(!kvm_can_emulate_insn(vcpu, emulation_type, insn, insn_len))) return 1; vcpu->arch.l1tf_flush_l1d = true; - /* - * Clear write_fault_to_shadow_pgtable here to ensure it is - * never reused. - */ - write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable; - vcpu->arch.write_fault_to_shadow_pgtable = false; - if (!(emulation_type & EMULTYPE_NO_DECODE)) { kvm_clear_exception_queue(vcpu); @@ -8819,7 +8872,6 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return 1; } if (reexecute_instruction(vcpu, cr2_or_gpa, - write_fault_to_spt, emulation_type)) return 1; @@ -8898,8 +8950,7 @@ restart: return 1; if (r == EMULATION_FAILED) { - if (reexecute_instruction(vcpu, cr2_or_gpa, write_fault_to_spt, - emulation_type)) + if (reexecute_instruction(vcpu, cr2_or_gpa, emulation_type)) return 1; return handle_emulation_failure(vcpu, emulation_type); @@ -9477,7 +9528,7 @@ static int __kvm_x86_vendor_init(struct kvm_x86_init_ops *ops) kvm_caps.max_guest_tsc_khz = max; } kvm_caps.default_tsc_scaling_ratio = 1ULL << kvm_caps.tsc_scaling_ratio_frac_bits; - kvm_init_msr_list(); + kvm_init_msr_lists(); return 0; out_unwind_ops: @@ -9808,7 +9859,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu) vcpu->run->hypercall.args[0] = gpa; vcpu->run->hypercall.args[1] = npages; vcpu->run->hypercall.args[2] = attrs; - vcpu->run->hypercall.longmode = op_64_bit; + vcpu->run->hypercall.flags = 0; + if (op_64_bit) + 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; return 0; } @@ -10170,19 +10225,46 @@ out: static void process_nmi(struct kvm_vcpu *vcpu) { - unsigned limit = 2; + unsigned int limit; /* - * x86 is limited to one NMI running, and one NMI pending after it. - * If an NMI is already in progress, limit further NMIs to just one. - * Otherwise, allow two (and we'll inject the first one immediately). + * x86 is limited to one NMI pending, but because KVM can't react to + * incoming NMIs as quickly as bare metal, e.g. if the vCPU is + * scheduled out, KVM needs to play nice with two queued NMIs showing + * up at the same time. To handle this scenario, allow two NMIs to be + * (temporarily) pending so long as NMIs are not blocked and KVM is not + * waiting for a previous NMI injection to complete (which effectively + * blocks NMIs). KVM will immediately inject one of the two NMIs, and + * will request an NMI window to handle the second NMI. */ if (static_call(kvm_x86_get_nmi_mask)(vcpu) || vcpu->arch.nmi_injected) limit = 1; + else + limit = 2; + + /* + * Adjust the limit to account for pending virtual NMIs, which aren't + * tracked in vcpu->arch.nmi_pending. + */ + if (static_call(kvm_x86_is_vnmi_pending)(vcpu)) + limit--; vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0); vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit); - kvm_make_request(KVM_REQ_EVENT, vcpu); + + if (vcpu->arch.nmi_pending && + (static_call(kvm_x86_set_vnmi_pending)(vcpu))) + vcpu->arch.nmi_pending--; + + if (vcpu->arch.nmi_pending) + kvm_make_request(KVM_REQ_EVENT, vcpu); +} + +/* Return total number of NMIs pending injection to the VM */ +int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.nmi_pending + + static_call(kvm_x86_is_vnmi_pending)(vcpu); } void kvm_make_scan_ioapic_request_mask(struct kvm *kvm, @@ -13268,7 +13350,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) return 1; } - pcid_enabled = kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE); + pcid_enabled = kvm_is_cr4_bit_set(vcpu, X86_CR4_PCIDE); switch (type) { case INVPCID_TYPE_INDIV_ADDR: diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h index a8167b47b8c8..c544602d07a3 100644 --- a/arch/x86/kvm/x86.h +++ b/arch/x86/kvm/x86.h @@ -3,6 +3,7 @@ #define ARCH_X86_KVM_X86_H #include <linux/kvm_host.h> +#include <asm/fpu/xstate.h> #include <asm/mce.h> #include <asm/pvclock.h> #include "kvm_cache_regs.h" @@ -40,6 +41,14 @@ void kvm_spurious_fault(void); failed; \ }) +/* + * The first...last VMX feature MSRs that are emulated by KVM. This may or may + * not cover all known VMX MSRs, as KVM doesn't emulate an MSR until there's an + * associated feature that KVM supports for nested virtualization. + */ +#define KVM_FIRST_EMULATED_VMX_MSR MSR_IA32_VMX_BASIC +#define KVM_LAST_EMULATED_VMX_MSR MSR_IA32_VMX_VMFUNC + #define KVM_DEFAULT_PLE_GAP 128 #define KVM_VMX_DEFAULT_PLE_WINDOW 4096 #define KVM_DEFAULT_PLE_WINDOW_GROW 2 @@ -83,6 +92,11 @@ static inline unsigned int __shrink_ple_window(unsigned int val, void kvm_service_local_tlb_flush_requests(struct kvm_vcpu *vcpu); int kvm_check_nested_events(struct kvm_vcpu *vcpu); +static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.last_vmentry_cpu != -1; +} + static inline bool kvm_is_exception_pending(struct kvm_vcpu *vcpu) { return vcpu->arch.exception.pending || @@ -123,15 +137,15 @@ static inline bool kvm_exception_is_soft(unsigned int nr) static inline bool is_protmode(struct kvm_vcpu *vcpu) { - return kvm_read_cr0_bits(vcpu, X86_CR0_PE); + return kvm_is_cr0_bit_set(vcpu, X86_CR0_PE); } -static inline int is_long_mode(struct kvm_vcpu *vcpu) +static inline bool is_long_mode(struct kvm_vcpu *vcpu) { #ifdef CONFIG_X86_64 - return vcpu->arch.efer & EFER_LMA; + return !!(vcpu->arch.efer & EFER_LMA); #else - return 0; + return false; #endif } @@ -171,19 +185,19 @@ static inline bool mmu_is_nested(struct kvm_vcpu *vcpu) return vcpu->arch.walk_mmu == &vcpu->arch.nested_mmu; } -static inline int is_pae(struct kvm_vcpu *vcpu) +static inline bool is_pae(struct kvm_vcpu *vcpu) { - return kvm_read_cr4_bits(vcpu, X86_CR4_PAE); + return kvm_is_cr4_bit_set(vcpu, X86_CR4_PAE); } -static inline int is_pse(struct kvm_vcpu *vcpu) +static inline bool is_pse(struct kvm_vcpu *vcpu) { - return kvm_read_cr4_bits(vcpu, X86_CR4_PSE); + return kvm_is_cr4_bit_set(vcpu, X86_CR4_PSE); } -static inline int is_paging(struct kvm_vcpu *vcpu) +static inline bool is_paging(struct kvm_vcpu *vcpu) { - return likely(kvm_read_cr0_bits(vcpu, X86_CR0_PG)); + return likely(kvm_is_cr0_bit_set(vcpu, X86_CR0_PG)); } static inline bool is_pae_paging(struct kvm_vcpu *vcpu) @@ -193,7 +207,7 @@ static inline bool is_pae_paging(struct kvm_vcpu *vcpu) static inline u8 vcpu_virt_addr_bits(struct kvm_vcpu *vcpu) { - return kvm_read_cr4_bits(vcpu, X86_CR4_LA57) ? 57 : 48; + return kvm_is_cr4_bit_set(vcpu, X86_CR4_LA57) ? 57 : 48; } static inline bool is_noncanonical_address(u64 la, struct kvm_vcpu *vcpu) @@ -315,6 +329,34 @@ extern struct kvm_caps kvm_caps; extern bool enable_pmu; +/* + * Get a filtered version of KVM's supported XCR0 that strips out dynamic + * features for which the current process doesn't (yet) have permission to use. + * This is intended to be used only when enumerating support to userspace, + * e.g. in KVM_GET_SUPPORTED_CPUID and KVM_CAP_XSAVE2, it does NOT need to be + * used to check/restrict guest behavior as KVM rejects KVM_SET_CPUID{2} if + * userspace attempts to enable unpermitted features. + */ +static inline u64 kvm_get_filtered_xcr0(void) +{ + u64 permitted_xcr0 = kvm_caps.supported_xcr0; + + BUILD_BUG_ON(XFEATURE_MASK_USER_DYNAMIC != XFEATURE_MASK_XTILE_DATA); + + if (permitted_xcr0 & XFEATURE_MASK_USER_DYNAMIC) { + permitted_xcr0 &= xstate_get_guest_group_perm(); + + /* + * Treat XTILE_CFG as unsupported if the current process isn't + * allowed to use XTILE_DATA, as attempting to set XTILE_CFG in + * XCR0 without setting XTILE_DATA is architecturally illegal. + */ + if (!(permitted_xcr0 & XFEATURE_MASK_XTILE_DATA)) + permitted_xcr0 &= ~XFEATURE_MASK_XTILE_CFG; + } + return permitted_xcr0; +} + static inline bool kvm_mpx_supported(void) { return (kvm_caps.supported_xcr0 & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) |