diff options
Diffstat (limited to 'arch/x86/kvm/mmu')
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 339 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/mmu_internal.h | 8 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/mmutrace.h | 3 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/spte.c | 10 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 53 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.h | 3 |
6 files changed, 259 insertions, 157 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 6e838cb6c9e1..667d66cf76d5 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -110,7 +110,7 @@ static bool __ro_after_init tdp_mmu_allowed; #ifdef CONFIG_X86_64 bool __read_mostly tdp_mmu_enabled = true; module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444); -EXPORT_SYMBOL_GPL(tdp_mmu_enabled); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(tdp_mmu_enabled); #endif static int max_huge_page_level __read_mostly; @@ -776,7 +776,8 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_flush_remote_tlbs_gfn(kvm, gfn, PG_LEVEL_4K); } -void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, + enum kvm_mmu_type mmu_type) { /* * If it's possible to replace the shadow page with an NX huge page, @@ -790,8 +791,9 @@ void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) return; ++kvm->stat.nx_lpage_splits; + ++kvm->arch.possible_nx_huge_pages[mmu_type].nr_pages; list_add_tail(&sp->possible_nx_huge_page_link, - &kvm->arch.possible_nx_huge_pages); + &kvm->arch.possible_nx_huge_pages[mmu_type].pages); } static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, @@ -800,7 +802,7 @@ static void account_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, sp->nx_huge_page_disallowed = true; if (nx_huge_page_possible) - track_possible_nx_huge_page(kvm, sp); + track_possible_nx_huge_page(kvm, sp, KVM_SHADOW_MMU); } static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) @@ -819,12 +821,14 @@ static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp) kvm_mmu_gfn_allow_lpage(slot, gfn); } -void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, + enum kvm_mmu_type mmu_type) { if (list_empty(&sp->possible_nx_huge_page_link)) return; --kvm->stat.nx_lpage_splits; + --kvm->arch.possible_nx_huge_pages[mmu_type].nr_pages; list_del_init(&sp->possible_nx_huge_page_link); } @@ -832,7 +836,7 @@ static void unaccount_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp) { sp->nx_huge_page_disallowed = false; - untrack_possible_nx_huge_page(kvm, sp); + untrack_possible_nx_huge_page(kvm, sp, KVM_SHADOW_MMU); } static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, @@ -3285,12 +3289,72 @@ out: return level; } -static int __kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, - gfn_t gfn, int max_level, bool is_private) +static u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) + return PG_LEVEL_1G; + + if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) + return PG_LEVEL_2M; + + return PG_LEVEL_4K; +} + +static u8 kvm_gmem_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, + const struct kvm_memory_slot *slot, gfn_t gfn, + bool is_private) +{ + u8 max_level, coco_level; + kvm_pfn_t pfn; + + /* For faults, use the gmem information that was resolved earlier. */ + if (fault) { + pfn = fault->pfn; + max_level = fault->max_level; + } else { + /* TODO: Call into guest_memfd once hugepages are supported. */ + WARN_ONCE(1, "Get pfn+order from guest_memfd"); + pfn = KVM_PFN_ERR_FAULT; + max_level = PG_LEVEL_4K; + } + + if (max_level == PG_LEVEL_4K) + return max_level; + + /* + * CoCo may influence the max mapping level, e.g. due to RMP or S-EPT + * restrictions. A return of '0' means "no additional restrictions", to + * allow for using an optional "ret0" static call. + */ + coco_level = kvm_x86_call(gmem_max_mapping_level)(kvm, pfn, is_private); + if (coco_level) + max_level = min(max_level, coco_level); + + return max_level; +} + +int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, + const struct kvm_memory_slot *slot, gfn_t gfn) { struct kvm_lpage_info *linfo; - int host_level; + int host_level, max_level; + bool is_private; + + lockdep_assert_held(&kvm->mmu_lock); + + if (fault) { + max_level = fault->max_level; + is_private = fault->is_private; + } else { + max_level = PG_LEVEL_NUM; + is_private = kvm_mem_is_private(kvm, gfn); + } max_level = min(max_level, max_huge_page_level); for ( ; max_level > PG_LEVEL_4K; max_level--) { @@ -3299,25 +3363,17 @@ static int __kvm_mmu_max_mapping_level(struct kvm *kvm, break; } - if (is_private) - return max_level; - if (max_level == PG_LEVEL_4K) return PG_LEVEL_4K; - host_level = host_pfn_mapping_level(kvm, gfn, slot); + if (is_private || kvm_memslot_is_gmem_only(slot)) + host_level = kvm_gmem_max_mapping_level(kvm, fault, slot, gfn, + is_private); + else + host_level = host_pfn_mapping_level(kvm, gfn, slot); return min(host_level, max_level); } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn) -{ - bool is_private = kvm_slot_can_be_private(slot) && - kvm_mem_is_private(kvm, gfn); - - return __kvm_mmu_max_mapping_level(kvm, slot, gfn, PG_LEVEL_NUM, is_private); -} - void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3338,9 +3394,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * level, which will be used to do precise, accurate accounting. */ - fault->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, - fault->gfn, fault->max_level, - fault->is_private); + fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, fault, + fault->slot, fault->gfn); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -3810,7 +3865,7 @@ void kvm_mmu_free_roots(struct kvm *kvm, struct kvm_mmu *mmu, write_unlock(&kvm->mmu_lock); } } -EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_free_roots); void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) { @@ -3837,7 +3892,7 @@ void kvm_mmu_free_guest_mode_roots(struct kvm *kvm, struct kvm_mmu *mmu) kvm_mmu_free_roots(kvm, mmu, roots_to_free); } -EXPORT_SYMBOL_GPL(kvm_mmu_free_guest_mode_roots); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_free_guest_mode_roots); static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, int quadrant, u8 level) @@ -4503,42 +4558,6 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work) vcpu->stat.pf_fixed++; } -static inline u8 kvm_max_level_for_order(int order) -{ - BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); - - KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && - order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && - order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); - - if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G)) - return PG_LEVEL_1G; - - if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M)) - return PG_LEVEL_2M; - - return PG_LEVEL_4K; -} - -static u8 kvm_max_private_mapping_level(struct kvm *kvm, kvm_pfn_t pfn, - u8 max_level, int gmem_order) -{ - u8 req_max_level; - - if (max_level == PG_LEVEL_4K) - return PG_LEVEL_4K; - - max_level = min(kvm_max_level_for_order(gmem_order), max_level); - if (max_level == PG_LEVEL_4K) - return PG_LEVEL_4K; - - req_max_level = kvm_x86_call(private_max_mapping_level)(kvm, pfn); - if (req_max_level) - max_level = min(max_level, req_max_level); - - return max_level; -} - static void kvm_mmu_finish_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, int r) { @@ -4546,12 +4565,12 @@ static void kvm_mmu_finish_page_fault(struct kvm_vcpu *vcpu, r == RET_PF_RETRY, fault->map_writable); } -static int kvm_mmu_faultin_pfn_private(struct kvm_vcpu *vcpu, - struct kvm_page_fault *fault) +static int kvm_mmu_faultin_pfn_gmem(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) { int max_order, r; - if (!kvm_slot_can_be_private(fault->slot)) { + if (!kvm_slot_has_gmem(fault->slot)) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return -EFAULT; } @@ -4564,8 +4583,7 @@ static int kvm_mmu_faultin_pfn_private(struct kvm_vcpu *vcpu, } fault->map_writable = !(fault->slot->flags & KVM_MEM_READONLY); - fault->max_level = kvm_max_private_mapping_level(vcpu->kvm, fault->pfn, - fault->max_level, max_order); + fault->max_level = kvm_max_level_for_order(max_order); return RET_PF_CONTINUE; } @@ -4575,8 +4593,8 @@ static int __kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, { unsigned int foll = fault->write ? FOLL_WRITE : 0; - if (fault->is_private) - return kvm_mmu_faultin_pfn_private(vcpu, fault); + if (fault->is_private || kvm_memslot_is_gmem_only(fault->slot)) + return kvm_mmu_faultin_pfn_gmem(vcpu, fault); foll |= FOLL_NOWAIT; fault->pfn = __kvm_faultin_pfn(fault->slot, fault->gfn, foll, @@ -4649,10 +4667,16 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, /* * Retry the page fault if the gfn hit a memslot that is being deleted * or moved. This ensures any existing SPTEs for the old memslot will - * be zapped before KVM inserts a new MMIO SPTE for the gfn. + * be zapped before KVM inserts a new MMIO SPTE for the gfn. Punt the + * error to userspace if this is a prefault, as KVM's prefaulting ABI + * doesn't provide the same forward progress guarantees as KVM_RUN. */ - if (slot->flags & KVM_MEMSLOT_INVALID) + if (slot->flags & KVM_MEMSLOT_INVALID) { + if (fault->prefetch) + return -EAGAIN; + return RET_PF_RETRY; + } if (slot->id == APIC_ACCESS_PAGE_PRIVATE_MEMSLOT) { /* @@ -4852,7 +4876,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code, return r; } -EXPORT_SYMBOL_GPL(kvm_handle_page_fault); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_handle_page_fault); #ifdef CONFIG_X86_64 static int kvm_tdp_mmu_page_fault(struct kvm_vcpu *vcpu, @@ -4942,7 +4966,7 @@ int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level return -EIO; } } -EXPORT_SYMBOL_GPL(kvm_tdp_map_page); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_tdp_map_page); long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range) @@ -5138,7 +5162,7 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd) __clear_sp_write_flooding_count(sp); } } -EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_new_pgd); static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn, unsigned int access) @@ -5784,7 +5808,7 @@ void kvm_init_shadow_npt_mmu(struct kvm_vcpu *vcpu, unsigned long cr0, shadow_mmu_init_context(vcpu, context, cpu_role, root_role); kvm_mmu_new_pgd(vcpu, nested_cr3); } -EXPORT_SYMBOL_GPL(kvm_init_shadow_npt_mmu); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_init_shadow_npt_mmu); static union kvm_cpu_role kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty, @@ -5838,7 +5862,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, kvm_mmu_new_pgd(vcpu, new_eptp); } -EXPORT_SYMBOL_GPL(kvm_init_shadow_ept_mmu); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_init_shadow_ept_mmu); static void init_kvm_softmmu(struct kvm_vcpu *vcpu, union kvm_cpu_role cpu_role) @@ -5903,7 +5927,7 @@ void kvm_init_mmu(struct kvm_vcpu *vcpu) else init_kvm_softmmu(vcpu, cpu_role); } -EXPORT_SYMBOL_GPL(kvm_init_mmu); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_init_mmu); void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) { @@ -5939,7 +5963,7 @@ void kvm_mmu_reset_context(struct kvm_vcpu *vcpu) kvm_mmu_unload(vcpu); kvm_init_mmu(vcpu); } -EXPORT_SYMBOL_GPL(kvm_mmu_reset_context); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_reset_context); int kvm_mmu_load(struct kvm_vcpu *vcpu) { @@ -5973,7 +5997,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) out: return r; } -EXPORT_SYMBOL_GPL(kvm_mmu_load); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_load); void kvm_mmu_unload(struct kvm_vcpu *vcpu) { @@ -6035,7 +6059,7 @@ void kvm_mmu_free_obsolete_roots(struct kvm_vcpu *vcpu) __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.root_mmu); __kvm_mmu_free_obsolete_roots(vcpu->kvm, &vcpu->arch.guest_mmu); } -EXPORT_SYMBOL_GPL(kvm_mmu_free_obsolete_roots); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_free_obsolete_roots); static u64 mmu_pte_write_fetch_gpte(struct kvm_vcpu *vcpu, gpa_t *gpa, int *bytes) @@ -6361,7 +6385,7 @@ emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, insn_len); } -EXPORT_SYMBOL_GPL(kvm_mmu_page_fault); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_page_fault); void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg) { @@ -6377,7 +6401,7 @@ void kvm_mmu_print_sptes(struct kvm_vcpu *vcpu, gpa_t gpa, const char *msg) pr_cont(", spte[%d] = 0x%llx", level, sptes[level]); pr_cont("\n"); } -EXPORT_SYMBOL_GPL(kvm_mmu_print_sptes); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_print_sptes); static void __kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, u64 addr, hpa_t root_hpa) @@ -6443,7 +6467,7 @@ void kvm_mmu_invalidate_addr(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, __kvm_mmu_invalidate_addr(vcpu, mmu, addr, mmu->prev_roots[i].hpa); } } -EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_addr); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_invalidate_addr); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { @@ -6460,7 +6484,7 @@ void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) kvm_mmu_invalidate_addr(vcpu, vcpu->arch.walk_mmu, gva, KVM_MMU_ROOTS_ALL); ++vcpu->stat.invlpg; } -EXPORT_SYMBOL_GPL(kvm_mmu_invlpg); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_invlpg); void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) @@ -6513,7 +6537,7 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, else max_huge_page_level = PG_LEVEL_2M; } -EXPORT_SYMBOL_GPL(kvm_configure_mmu); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_configure_mmu); static void free_mmu_pages(struct kvm_mmu *mmu) { @@ -6737,11 +6761,12 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) int kvm_mmu_init_vm(struct kvm *kvm) { - int r; + int r, i; kvm->arch.shadow_mmio_value = shadow_mmio_value; INIT_LIST_HEAD(&kvm->arch.active_mmu_pages); - INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages); + for (i = 0; i < KVM_NR_MMU_TYPES; ++i) + INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages[i].pages); spin_lock_init(&kvm->arch.mmu_unsync_pages_lock); if (tdp_mmu_enabled) { @@ -7165,7 +7190,7 @@ restart: * mapping if the indirect sp has level = 1. */ if (sp->role.direct && - sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn)) { + sp->role.level < kvm_mmu_max_mapping_level(kvm, NULL, slot, sp->gfn)) { kvm_zap_one_rmap_spte(kvm, rmap_head, sptep); if (kvm_available_flush_remote_tlbs_range()) @@ -7179,7 +7204,7 @@ restart: return need_tlb_flush; } -EXPORT_SYMBOL_GPL(kvm_zap_gfn_range); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_zap_gfn_range); static void kvm_rmap_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -7582,19 +7607,64 @@ static int set_nx_huge_pages_recovery_param(const char *val, const struct kernel return err; } -static void kvm_recover_nx_huge_pages(struct kvm *kvm) +static unsigned long nx_huge_pages_to_zap(struct kvm *kvm, + enum kvm_mmu_type mmu_type) +{ + unsigned long pages = READ_ONCE(kvm->arch.possible_nx_huge_pages[mmu_type].nr_pages); + unsigned int ratio = READ_ONCE(nx_huge_pages_recovery_ratio); + + return ratio ? DIV_ROUND_UP(pages, ratio) : 0; +} + +static bool kvm_mmu_sp_dirty_logging_enabled(struct kvm *kvm, + struct kvm_mmu_page *sp) { - unsigned long nx_lpage_splits = kvm->stat.nx_lpage_splits; struct kvm_memory_slot *slot; - int rcu_idx; + + /* + * Skip the memslot lookup if dirty tracking can't possibly be enabled, + * as memslot lookups are relatively expensive. + * + * If a memslot update is in progress, reading an incorrect value of + * kvm->nr_memslots_dirty_logging is not a problem: if it is becoming + * zero, KVM will do an unnecessary memslot lookup; if it is becoming + * nonzero, the page will be zapped unnecessarily. Either way, this + * only affects efficiency in racy situations, and not correctness. + */ + if (!atomic_read(&kvm->nr_memslots_dirty_logging)) + return false; + + slot = __gfn_to_memslot(kvm_memslots_for_spte_role(kvm, sp->role), sp->gfn); + if (WARN_ON_ONCE(!slot)) + return false; + + return kvm_slot_dirty_track_enabled(slot); +} + +static void kvm_recover_nx_huge_pages(struct kvm *kvm, + const enum kvm_mmu_type mmu_type) +{ +#ifdef CONFIG_X86_64 + const bool is_tdp_mmu = mmu_type == KVM_TDP_MMU; + spinlock_t *tdp_mmu_pages_lock = &kvm->arch.tdp_mmu_pages_lock; +#else + const bool is_tdp_mmu = false; + spinlock_t *tdp_mmu_pages_lock = NULL; +#endif + unsigned long to_zap = nx_huge_pages_to_zap(kvm, mmu_type); + struct list_head *nx_huge_pages; struct kvm_mmu_page *sp; - unsigned int ratio; LIST_HEAD(invalid_list); bool flush = false; - ulong to_zap; + int rcu_idx; + + nx_huge_pages = &kvm->arch.possible_nx_huge_pages[mmu_type].pages; rcu_idx = srcu_read_lock(&kvm->srcu); - write_lock(&kvm->mmu_lock); + if (is_tdp_mmu) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); /* * Zapping TDP MMU shadow pages, including the remote TLB flush, must @@ -7603,11 +7673,15 @@ static void kvm_recover_nx_huge_pages(struct kvm *kvm) */ rcu_read_lock(); - ratio = READ_ONCE(nx_huge_pages_recovery_ratio); - to_zap = ratio ? DIV_ROUND_UP(nx_lpage_splits, ratio) : 0; for ( ; to_zap; --to_zap) { - if (list_empty(&kvm->arch.possible_nx_huge_pages)) + if (is_tdp_mmu) + spin_lock(tdp_mmu_pages_lock); + + if (list_empty(nx_huge_pages)) { + if (is_tdp_mmu) + spin_unlock(tdp_mmu_pages_lock); break; + } /* * We use a separate list instead of just using active_mmu_pages @@ -7616,56 +7690,44 @@ static void kvm_recover_nx_huge_pages(struct kvm *kvm) * the total number of shadow pages. And because the TDP MMU * doesn't use active_mmu_pages. */ - sp = list_first_entry(&kvm->arch.possible_nx_huge_pages, + sp = list_first_entry(nx_huge_pages, struct kvm_mmu_page, possible_nx_huge_page_link); WARN_ON_ONCE(!sp->nx_huge_page_disallowed); WARN_ON_ONCE(!sp->role.direct); + unaccount_nx_huge_page(kvm, sp); + + if (is_tdp_mmu) + spin_unlock(tdp_mmu_pages_lock); + /* - * Unaccount and do not attempt to recover any NX Huge Pages - * that are being dirty tracked, as they would just be faulted - * back in as 4KiB pages. The NX Huge Pages in this slot will be - * recovered, along with all the other huge pages in the slot, - * when dirty logging is disabled. - * - * Since gfn_to_memslot() is relatively expensive, it helps to - * skip it if it the test cannot possibly return true. On the - * other hand, if any memslot has logging enabled, chances are - * good that all of them do, in which case unaccount_nx_huge_page() - * is much cheaper than zapping the page. - * - * If a memslot update is in progress, reading an incorrect value - * of kvm->nr_memslots_dirty_logging is not a problem: if it is - * becoming zero, gfn_to_memslot() will be done unnecessarily; if - * it is becoming nonzero, the page will be zapped unnecessarily. - * Either way, this only affects efficiency in racy situations, - * and not correctness. + * Do not attempt to recover any NX Huge Pages that are being + * dirty tracked, as they would just be faulted back in as 4KiB + * pages. The NX Huge Pages in this slot will be recovered, + * along with all the other huge pages in the slot, when dirty + * logging is disabled. */ - slot = NULL; - if (atomic_read(&kvm->nr_memslots_dirty_logging)) { - struct kvm_memslots *slots; + if (!kvm_mmu_sp_dirty_logging_enabled(kvm, sp)) { + if (is_tdp_mmu) + flush |= kvm_tdp_mmu_zap_possible_nx_huge_page(kvm, sp); + else + kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); - slots = kvm_memslots_for_spte_role(kvm, sp->role); - slot = __gfn_to_memslot(slots, sp->gfn); - WARN_ON_ONCE(!slot); } - if (slot && kvm_slot_dirty_track_enabled(slot)) - unaccount_nx_huge_page(kvm, sp); - else if (is_tdp_mmu_page(sp)) - flush |= kvm_tdp_mmu_zap_sp(kvm, sp); - else - kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->nx_huge_page_disallowed); if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush); rcu_read_unlock(); - cond_resched_rwlock_write(&kvm->mmu_lock); - flush = false; + if (is_tdp_mmu) + cond_resched_rwlock_read(&kvm->mmu_lock); + else + cond_resched_rwlock_write(&kvm->mmu_lock); + flush = false; rcu_read_lock(); } } @@ -7673,7 +7735,10 @@ static void kvm_recover_nx_huge_pages(struct kvm *kvm) rcu_read_unlock(); - write_unlock(&kvm->mmu_lock); + if (is_tdp_mmu) + read_unlock(&kvm->mmu_lock); + else + write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); } @@ -7684,9 +7749,10 @@ static void kvm_nx_huge_page_recovery_worker_kill(void *data) static bool kvm_nx_huge_page_recovery_worker(void *data) { struct kvm *kvm = data; + long remaining_time; bool enabled; uint period; - long remaining_time; + int i; enabled = calc_nx_huge_pages_recovery_period(&period); if (!enabled) @@ -7701,7 +7767,8 @@ static bool kvm_nx_huge_page_recovery_worker(void *data) } __set_current_state(TASK_RUNNING); - kvm_recover_nx_huge_pages(kvm); + for (i = 0; i < KVM_NR_MMU_TYPES; ++i) + kvm_recover_nx_huge_pages(kvm, i); kvm->arch.nx_huge_page_last = get_jiffies_64(); return true; } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 65f3c89d7c5d..ed5c01df21ba 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -411,12 +411,14 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, return r; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, +int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, const struct kvm_memory_slot *slot, gfn_t gfn); void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); void disallowed_hugepage_adjust(struct kvm_page_fault *fault, u64 spte, int cur_level); -void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); -void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp); +void track_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, + enum kvm_mmu_type mmu_type); +void untrack_possible_nx_huge_page(struct kvm *kvm, struct kvm_mmu_page *sp, + enum kvm_mmu_type mmu_type); #endif /* __KVM_X86_MMU_INTERNAL_H */ diff --git a/arch/x86/kvm/mmu/mmutrace.h b/arch/x86/kvm/mmu/mmutrace.h index f35a830ce469..764e3015d021 100644 --- a/arch/x86/kvm/mmu/mmutrace.h +++ b/arch/x86/kvm/mmu/mmutrace.h @@ -51,6 +51,9 @@ { PFERR_PRESENT_MASK, "P" }, \ { PFERR_WRITE_MASK, "W" }, \ { PFERR_USER_MASK, "U" }, \ + { PFERR_PK_MASK, "PK" }, \ + { PFERR_SS_MASK, "SS" }, \ + { PFERR_SGX_MASK, "SGX" }, \ { PFERR_RSVD_MASK, "RSVD" }, \ { PFERR_FETCH_MASK, "F" } diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c index df31039b5d63..37647afde7d3 100644 --- a/arch/x86/kvm/mmu/spte.c +++ b/arch/x86/kvm/mmu/spte.c @@ -22,7 +22,7 @@ bool __read_mostly enable_mmio_caching = true; static bool __ro_after_init allow_mmio_caching; module_param_named(mmio_caching, enable_mmio_caching, bool, 0444); -EXPORT_SYMBOL_GPL(enable_mmio_caching); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(enable_mmio_caching); bool __read_mostly kvm_ad_enabled; @@ -470,13 +470,13 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask) shadow_mmio_mask = mmio_mask; shadow_mmio_access_mask = access_mask; } -EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_mmio_spte_mask); void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value) { kvm->arch.shadow_mmio_value = mmio_value; } -EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_value); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_mmio_spte_value); void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask) { @@ -487,7 +487,7 @@ void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask) shadow_me_value = me_value; shadow_me_mask = me_mask; } -EXPORT_SYMBOL_GPL(kvm_mmu_set_me_spte_mask); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_me_spte_mask); void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only) { @@ -513,7 +513,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only) kvm_mmu_set_mmio_spte_mask(VMX_EPT_MISCONFIG_WX_VALUE, VMX_EPT_RWX_MASK | VMX_EPT_SUPPRESS_VE_BIT, 0); } -EXPORT_SYMBOL_GPL(kvm_mmu_set_ept_masks); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_mmu_set_ept_masks); void kvm_mmu_reset_all_pte_masks(void) { diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7f3d7229b2c1..c5734ca5c17d 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -355,7 +355,7 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) spin_lock(&kvm->arch.tdp_mmu_pages_lock); sp->nx_huge_page_disallowed = false; - untrack_possible_nx_huge_page(kvm, sp); + untrack_possible_nx_huge_page(kvm, sp, KVM_TDP_MMU); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } @@ -925,23 +925,52 @@ static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_unlock(); } -bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp) +bool kvm_tdp_mmu_zap_possible_nx_huge_page(struct kvm *kvm, + struct kvm_mmu_page *sp) { - u64 old_spte; + struct tdp_iter iter = { + .old_spte = sp->ptep ? kvm_tdp_mmu_read_spte(sp->ptep) : 0, + .sptep = sp->ptep, + .level = sp->role.level + 1, + .gfn = sp->gfn, + .as_id = kvm_mmu_page_as_id(sp), + }; + + lockdep_assert_held_read(&kvm->mmu_lock); + + if (WARN_ON_ONCE(!is_tdp_mmu_page(sp))) + return false; /* - * This helper intentionally doesn't allow zapping a root shadow page, - * which doesn't have a parent page table and thus no associated entry. + * Root shadow pages don't have a parent page table and thus no + * associated entry, but they can never be possible NX huge pages. */ if (WARN_ON_ONCE(!sp->ptep)) return false; - old_spte = kvm_tdp_mmu_read_spte(sp->ptep); - if (WARN_ON_ONCE(!is_shadow_present_pte(old_spte))) + /* + * Since mmu_lock is held in read mode, it's possible another task has + * already modified the SPTE. Zap the SPTE if and only if the SPTE + * points at the SP's page table, as checking shadow-present isn't + * sufficient, e.g. the SPTE could be replaced by a leaf SPTE, or even + * another SP. Note, spte_to_child_pt() also checks that the SPTE is + * shadow-present, i.e. guards against zapping a frozen SPTE. + */ + if ((tdp_ptep_t)sp->spt != spte_to_child_pt(iter.old_spte, iter.level)) return false; - tdp_mmu_set_spte(kvm, kvm_mmu_page_as_id(sp), sp->ptep, old_spte, - SHADOW_NONPRESENT_VALUE, sp->gfn, sp->role.level + 1); + /* + * If a different task modified the SPTE, then it should be impossible + * for the SPTE to still be used for the to-be-zapped SP. Non-leaf + * SPTEs don't have Dirty bits, KVM always sets the Accessed bit when + * creating non-leaf SPTEs, and all other bits are immutable for non- + * leaf SPTEs, i.e. the only legal operations for non-leaf SPTEs are + * zapping and replacement. + */ + if (tdp_mmu_set_spte_atomic(kvm, &iter, SHADOW_NONPRESENT_VALUE)) { + WARN_ON_ONCE((tdp_ptep_t)sp->spt == spte_to_child_pt(iter.old_spte, iter.level)); + return false; + } return true; } @@ -1303,7 +1332,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) fault->req_level >= iter.level) { spin_lock(&kvm->arch.tdp_mmu_pages_lock); if (sp->nx_huge_page_disallowed) - track_possible_nx_huge_page(kvm, sp); + track_possible_nx_huge_page(kvm, sp, KVM_TDP_MMU); spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } } @@ -1813,7 +1842,7 @@ retry: if (iter.gfn < start || iter.gfn >= end) continue; - max_mapping_level = kvm_mmu_max_mapping_level(kvm, slot, iter.gfn); + max_mapping_level = kvm_mmu_max_mapping_level(kvm, NULL, slot, iter.gfn); if (max_mapping_level < iter.level) continue; @@ -1953,7 +1982,7 @@ bool kvm_tdp_mmu_gpa_is_mapped(struct kvm_vcpu *vcpu, u64 gpa) spte = sptes[leaf]; return is_shadow_present_pte(spte) && is_last_spte(spte, leaf); } -EXPORT_SYMBOL_GPL(kvm_tdp_mmu_gpa_is_mapped); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_tdp_mmu_gpa_is_mapped); /* * Returns the last level spte pointer of the shadow page walk for the given diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 52acf99d40a0..bd62977c9199 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -64,7 +64,8 @@ static inline struct kvm_mmu_page *tdp_mmu_get_root(struct kvm_vcpu *vcpu, } bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); -bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); +bool kvm_tdp_mmu_zap_possible_nx_huge_page(struct kvm *kvm, + struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm, enum kvm_tdp_mmu_root_types root_types); |