diff options
Diffstat (limited to 'arch/x86/kvm/mmu/mmu.c')
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 608 |
1 files changed, 257 insertions, 351 deletions
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index c478904af518..d75524bc8423 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -190,7 +190,7 @@ static void kvm_flush_remote_tlbs_with_range(struct kvm *kvm, int ret = -ENOTSUPP; if (range && kvm_x86_ops.tlb_remote_flush_with_range) - ret = kvm_x86_ops.tlb_remote_flush_with_range(kvm, range); + ret = static_call(kvm_x86_tlb_remote_flush_with_range)(kvm, range); if (ret) kvm_flush_remote_tlbs(kvm); @@ -844,17 +844,17 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte, int i, count = 0; if (!rmap_head->val) { - rmap_printk("pte_list_add: %p %llx 0->1\n", spte, *spte); + rmap_printk("%p %llx 0->1\n", spte, *spte); rmap_head->val = (unsigned long)spte; } else if (!(rmap_head->val & 1)) { - rmap_printk("pte_list_add: %p %llx 1->many\n", spte, *spte); + rmap_printk("%p %llx 1->many\n", spte, *spte); desc = mmu_alloc_pte_list_desc(vcpu); desc->sptes[0] = (u64 *)rmap_head->val; desc->sptes[1] = spte; rmap_head->val = (unsigned long)desc | 1; ++count; } else { - rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte); + rmap_printk("%p %llx many->many\n", spte, *spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); while (desc->sptes[PTE_LIST_EXT-1]) { count += PTE_LIST_EXT; @@ -906,14 +906,14 @@ static void __pte_list_remove(u64 *spte, struct kvm_rmap_head *rmap_head) pr_err("%s: %p 0->BUG\n", __func__, spte); BUG(); } else if (!(rmap_head->val & 1)) { - rmap_printk("%s: %p 1->0\n", __func__, spte); + rmap_printk("%p 1->0\n", spte); if ((u64 *)rmap_head->val != spte) { pr_err("%s: %p 1->BUG\n", __func__, spte); BUG(); } rmap_head->val = 0; } else { - rmap_printk("%s: %p many->many\n", __func__, spte); + rmap_printk("%p many->many\n", spte); desc = (struct pte_list_desc *)(rmap_head->val & ~1ul); prev_desc = NULL; while (desc) { @@ -1115,7 +1115,7 @@ static bool spte_write_protect(u64 *sptep, bool pt_protect) !(pt_protect && spte_can_locklessly_be_made_writable(spte))) return false; - rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); + rmap_printk("spte %p %llx\n", sptep, *sptep); if (pt_protect) spte &= ~SPTE_MMU_WRITEABLE; @@ -1142,7 +1142,7 @@ static bool spte_clear_dirty(u64 *sptep) { u64 spte = *sptep; - rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep); + rmap_printk("spte %p %llx\n", sptep, *sptep); MMU_WARN_ON(!spte_ad_enabled(spte)); spte &= ~shadow_dirty_mask; @@ -1165,7 +1165,8 @@ static bool spte_wrprot_for_clear_dirty(u64 *sptep) * - W bit on ad-disabled SPTEs. * Returns true iff any D or W bits were cleared. */ -static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) +static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -1180,35 +1181,6 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) return flush; } -static bool spte_set_dirty(u64 *sptep) -{ - u64 spte = *sptep; - - rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep); - - /* - * Similar to the !kvm_x86_ops.slot_disable_log_dirty case, - * do not bother adding back write access to pages marked - * SPTE_AD_WRPROT_ONLY_MASK. - */ - spte |= shadow_dirty_mask; - - return mmu_spte_update(sptep, spte); -} - -static bool __rmap_set_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head) -{ - u64 *sptep; - struct rmap_iterator iter; - bool flush = false; - - for_each_rmap_spte(rmap_head, &iter, sptep) - if (spte_ad_enabled(*sptep)) - flush |= spte_set_dirty(sptep); - - return flush; -} - /** * kvm_mmu_write_protect_pt_masked - write protect selected PT level pages * @kvm: kvm instance @@ -1225,7 +1197,7 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, { struct kvm_rmap_head *rmap_head; - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, true); while (mask) { @@ -1248,25 +1220,24 @@ static void kvm_mmu_write_protect_pt_masked(struct kvm *kvm, * * Used for PML to re-log the dirty GPAs after userspace querying dirty_bitmap. */ -void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, - struct kvm_memory_slot *slot, - gfn_t gfn_offset, unsigned long mask) +static void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm, + struct kvm_memory_slot *slot, + gfn_t gfn_offset, unsigned long mask) { struct kvm_rmap_head *rmap_head; - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_clear_dirty_pt_masked(kvm, slot, slot->base_gfn + gfn_offset, mask, false); while (mask) { rmap_head = __gfn_to_rmap(slot->base_gfn + gfn_offset + __ffs(mask), PG_LEVEL_4K, slot); - __rmap_clear_dirty(kvm, rmap_head); + __rmap_clear_dirty(kvm, rmap_head, slot); /* clear the first set bit */ mask &= mask - 1; } } -EXPORT_SYMBOL_GPL(kvm_mmu_clear_dirty_pt_masked); /** * kvm_arch_mmu_enable_log_dirty_pt_masked - enable dirty logging for selected @@ -1282,19 +1253,15 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn_offset, unsigned long mask) { - if (kvm_x86_ops.enable_log_dirty_pt_masked) - kvm_x86_ops.enable_log_dirty_pt_masked(kvm, slot, gfn_offset, - mask); + if (kvm_x86_ops.cpu_dirty_log_size) + kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask); else kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask); } int kvm_cpu_dirty_log_size(void) { - if (kvm_x86_ops.cpu_dirty_log_size) - return kvm_x86_ops.cpu_dirty_log_size(); - - return 0; + return kvm_x86_ops.cpu_dirty_log_size; } bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, @@ -1309,7 +1276,7 @@ bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm, write_protected |= __rmap_write_protect(kvm, rmap_head, true); } - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) write_protected |= kvm_tdp_mmu_write_protect_gfn(kvm, slot, gfn); @@ -1324,14 +1291,15 @@ static bool rmap_write_protect(struct kvm_vcpu *vcpu, u64 gfn) return kvm_mmu_slot_gfn_write_protect(vcpu->kvm, slot, gfn); } -static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head) +static bool kvm_zap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; bool flush = false; while ((sptep = rmap_get_first(rmap_head, &iter))) { - rmap_printk("%s: spte %p %llx.\n", __func__, sptep, *sptep); + rmap_printk("spte %p %llx.\n", sptep, *sptep); pte_list_remove(rmap_head, sptep); flush = true; @@ -1344,7 +1312,7 @@ static int kvm_unmap_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, struct kvm_memory_slot *slot, gfn_t gfn, int level, unsigned long data) { - return kvm_zap_rmapp(kvm, rmap_head); + return kvm_zap_rmapp(kvm, rmap_head, slot); } static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, @@ -1363,7 +1331,7 @@ static int kvm_set_pte_rmapp(struct kvm *kvm, struct kvm_rmap_head *rmap_head, restart: for_each_rmap_spte(rmap_head, &iter, sptep) { - rmap_printk("kvm_set_pte_rmapp: spte %p %llx gfn %llx (%d)\n", + rmap_printk("spte %p %llx gfn %llx (%d)\n", sptep, *sptep, gfn, level); need_flush = 1; @@ -1456,16 +1424,17 @@ static void slot_rmap_walk_next(struct slot_rmap_walk_iterator *iterator) slot_rmap_walk_okay(_iter_); \ slot_rmap_walk_next(_iter_)) -static int kvm_handle_hva_range(struct kvm *kvm, - unsigned long start, - unsigned long end, - unsigned long data, - int (*handler)(struct kvm *kvm, - struct kvm_rmap_head *rmap_head, - struct kvm_memory_slot *slot, - gfn_t gfn, - int level, - unsigned long data)) +static __always_inline int +kvm_handle_hva_range(struct kvm *kvm, + unsigned long start, + unsigned long end, + unsigned long data, + int (*handler)(struct kvm *kvm, + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot, + gfn_t gfn, + int level, + unsigned long data)) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; @@ -1521,7 +1490,7 @@ int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, r = kvm_handle_hva_range(kvm, start, end, 0, kvm_unmap_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) r |= kvm_tdp_mmu_zap_hva_range(kvm, start, end); return r; @@ -1533,7 +1502,7 @@ int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte) r = kvm_handle_hva(kvm, hva, (unsigned long)&pte, kvm_set_pte_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) r |= kvm_tdp_mmu_set_spte_hva(kvm, hva, &pte); return r; @@ -1588,7 +1557,7 @@ int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end) int young = false; young = kvm_handle_hva_range(kvm, start, end, 0, kvm_age_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_age_hva_range(kvm, start, end); return young; @@ -1599,7 +1568,7 @@ int kvm_test_age_hva(struct kvm *kvm, unsigned long hva) int young = false; young = kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) young |= kvm_tdp_mmu_test_age_hva(kvm, hva); return young; @@ -1723,13 +1692,6 @@ static int nonpaging_sync_page(struct kvm_vcpu *vcpu, return 0; } -static void nonpaging_update_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - const void *pte) -{ - WARN_ON(1); -} - #define KVM_PAGE_ARRAY_NR 16 struct kvm_mmu_pages { @@ -2016,9 +1978,9 @@ static void mmu_sync_children(struct kvm_vcpu *vcpu, flush |= kvm_sync_page(vcpu, sp, &invalid_list); mmu_pages_clear_parents(&parents); } - if (need_resched() || spin_needbreak(&vcpu->kvm->mmu_lock)) { + if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) { kvm_mmu_flush_or_zap(vcpu, &invalid_list, false, flush); - cond_resched_lock(&vcpu->kvm->mmu_lock); + cond_resched_rwlock_write(&vcpu->kvm->mmu_lock); flush = false; } } @@ -2417,7 +2379,7 @@ static unsigned long kvm_mmu_zap_oldest_mmu_pages(struct kvm *kvm, return 0; restart: - list_for_each_entry_safe(sp, tmp, &kvm->arch.active_mmu_pages, link) { + list_for_each_entry_safe_reverse(sp, tmp, &kvm->arch.active_mmu_pages, link) { /* * Don't zap active root pages, the page itself can't be freed * and zapping it will just force vCPUs to realloc and reload. @@ -2470,7 +2432,7 @@ static int make_mmu_pages_available(struct kvm_vcpu *vcpu) */ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) { - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); if (kvm->arch.n_used_mmu_pages > goal_nr_mmu_pages) { kvm_mmu_zap_oldest_mmu_pages(kvm, kvm->arch.n_used_mmu_pages - @@ -2481,7 +2443,7 @@ void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned long goal_nr_mmu_pages) kvm->arch.n_max_mmu_pages = goal_nr_mmu_pages; - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) @@ -2492,7 +2454,7 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) pgprintk("%s: looking for gfn %llx\n", __func__, gfn); r = 0; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); for_each_gfn_indirect_valid_sp(kvm, sp, gfn) { pgprintk("%s: gfn %llx role %x\n", __func__, gfn, sp->role.word); @@ -2500,11 +2462,25 @@ int kvm_mmu_unprotect_page(struct kvm *kvm, gfn_t gfn) kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); } kvm_mmu_commit_zap_page(kvm, &invalid_list); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); + + return r; +} + +static int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) +{ + gpa_t gpa; + int r; + + if (vcpu->arch.mmu->direct_map) + return 0; + + gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); + + r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); return r; } -EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page); static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -2758,11 +2734,18 @@ static void direct_pte_prefetch(struct kvm_vcpu *vcpu, u64 *sptep) if (sp->role.level > PG_LEVEL_4K) return; + /* + * If addresses are being invalidated, skip prefetching to avoid + * accidentally prefetching those addresses. + */ + if (unlikely(vcpu->kvm->mmu_notifier_count)) + return; + __direct_pte_prefetch(vcpu, sp, sptep); } -static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, - kvm_pfn_t pfn, struct kvm_memory_slot *slot) +static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, + struct kvm_memory_slot *slot) { unsigned long hva; pte_t *pte; @@ -2781,19 +2764,36 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn, */ hva = __gfn_to_hva_memslot(slot, gfn); - pte = lookup_address_in_mm(vcpu->kvm->mm, hva, &level); + pte = lookup_address_in_mm(kvm->mm, hva, &level); if (unlikely(!pte)) return PG_LEVEL_4K; return level; } +int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_memory_slot *slot, + gfn_t gfn, kvm_pfn_t pfn, int max_level) +{ + struct kvm_lpage_info *linfo; + + max_level = min(max_level, max_huge_page_level); + for ( ; max_level > PG_LEVEL_4K; max_level--) { + linfo = lpage_info_slot(gfn, slot, max_level); + if (!linfo->disallow_lpage) + break; + } + + if (max_level == PG_LEVEL_4K) + return PG_LEVEL_4K; + + return host_pfn_mapping_level(kvm, gfn, pfn, slot); +} + int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, int max_level, kvm_pfn_t *pfnp, bool huge_page_disallowed, int *req_level) { struct kvm_memory_slot *slot; - struct kvm_lpage_info *linfo; kvm_pfn_t pfn = *pfnp; kvm_pfn_t mask; int level; @@ -2810,17 +2810,7 @@ int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn, if (!slot) return PG_LEVEL_4K; - max_level = min(max_level, max_huge_page_level); - for ( ; max_level > PG_LEVEL_4K; max_level--) { - linfo = lpage_info_slot(gfn, slot, max_level); - if (!linfo->disallow_lpage) - break; - } - - if (max_level == PG_LEVEL_4K) - return PG_LEVEL_4K; - - level = host_pfn_mapping_level(vcpu, gfn, pfn, slot); + level = kvm_mmu_max_mapping_level(vcpu->kvm, slot, gfn, pfn, max_level); if (level == PG_LEVEL_4K) return level; @@ -3161,7 +3151,7 @@ static void mmu_free_root_page(struct kvm *kvm, hpa_t *root_hpa, sp = to_shadow_page(*root_hpa & PT64_BASE_ADDR_MASK); if (kvm_mmu_put_root(kvm, sp)) { - if (sp->tdp_mmu_page) + if (is_tdp_mmu_page(sp)) kvm_tdp_mmu_free_root(kvm, sp); else if (sp->role.invalid) kvm_mmu_prepare_zap_page(kvm, sp, invalid_list); @@ -3192,7 +3182,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, return; } - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) if (roots_to_free & KVM_MMU_ROOT_PREVIOUS(i)) @@ -3215,7 +3205,7 @@ void kvm_mmu_free_roots(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, } kvm_mmu_commit_zap_page(kvm, &invalid_list); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } EXPORT_SYMBOL_GPL(kvm_mmu_free_roots); @@ -3236,16 +3226,16 @@ static hpa_t mmu_alloc_root(struct kvm_vcpu *vcpu, gfn_t gfn, gva_t gva, { struct kvm_mmu_page *sp; - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); if (make_mmu_pages_available(vcpu)) { - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); return INVALID_PAGE; } sp = kvm_mmu_get_page(vcpu, gfn, gva, level, direct, ACC_ALL); ++sp->root_count; - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); return __pa(sp->spt); } @@ -3255,7 +3245,7 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) hpa_t root; unsigned i; - if (vcpu->kvm->arch.tdp_mmu_enabled) { + if (is_tdp_mmu_enabled(vcpu->kvm)) { root = kvm_tdp_mmu_get_vcpu_root_hpa(vcpu); if (!VALID_PAGE(root)) @@ -3416,17 +3406,17 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) !smp_load_acquire(&sp->unsync_children)) return; - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); mmu_sync_children(vcpu, sp); kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); return; } - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); kvm_mmu_audit(vcpu, AUDIT_PRE_SYNC); for (i = 0; i < 4; ++i) { @@ -3440,9 +3430,8 @@ void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu) } kvm_mmu_audit(vcpu, AUDIT_POST_SYNC); - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); } -EXPORT_SYMBOL_GPL(kvm_mmu_sync_roots); static gpa_t nonpaging_gva_to_gpa(struct kvm_vcpu *vcpu, gpa_t vaddr, u32 access, struct x86_exception *exception) @@ -3493,26 +3482,25 @@ static bool mmio_info_in_cache(struct kvm_vcpu *vcpu, u64 addr, bool direct) * Return the level of the lowest level SPTE added to sptes. * That SPTE may be non-present. */ -static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) +static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { struct kvm_shadow_walk_iterator iterator; - int leaf = vcpu->arch.mmu->root_level; + int leaf = -1; u64 spte; - walk_shadow_page_lockless_begin(vcpu); - for (shadow_walk_init(&iterator, vcpu, addr); + for (shadow_walk_init(&iterator, vcpu, addr), + *root_level = iterator.level; shadow_walk_okay(&iterator); __shadow_walk_next(&iterator, spte)) { leaf = iterator.level; spte = mmu_spte_get_lockless(iterator.sptep); - sptes[leaf - 1] = spte; + sptes[leaf] = spte; if (!is_shadow_present_pte(spte)) break; - } walk_shadow_page_lockless_end(vcpu); @@ -3520,14 +3508,12 @@ static int get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes) return leaf; } -/* return true if reserved bit is detected on spte. */ +/* return true if reserved bit(s) are detected on a valid, non-MMIO SPTE. */ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) { - u64 sptes[PT64_ROOT_MAX_LEVEL]; + u64 sptes[PT64_ROOT_MAX_LEVEL + 1]; struct rsvd_bits_validate *rsvd_check; - int root = vcpu->arch.mmu->shadow_root_level; - int leaf; - int level; + int root, leaf, level; bool reserved = false; if (!VALID_PAGE(vcpu->arch.mmu->root_hpa)) { @@ -3536,35 +3522,45 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep) } if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) - leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes); + leaf = kvm_tdp_mmu_get_walk(vcpu, addr, sptes, &root); else - leaf = get_walk(vcpu, addr, sptes); + leaf = get_walk(vcpu, addr, sptes, &root); + + if (unlikely(leaf < 0)) { + *sptep = 0ull; + return reserved; + } + + *sptep = sptes[leaf]; + + /* + * Skip reserved bits checks on the terminal leaf if it's not a valid + * SPTE. Note, this also (intentionally) skips MMIO SPTEs, which, by + * design, always have reserved bits set. The purpose of the checks is + * to detect reserved bits on non-MMIO SPTEs. i.e. buggy SPTEs. + */ + if (!is_shadow_present_pte(sptes[leaf])) + leaf++; rsvd_check = &vcpu->arch.mmu->shadow_zero_check; - for (level = root; level >= leaf; level--) { - if (!is_shadow_present_pte(sptes[level - 1])) - break; + for (level = root; level >= leaf; level--) /* * Use a bitwise-OR instead of a logical-OR to aggregate the * reserved bit and EPT's invalid memtype/XWR checks to avoid * adding a Jcc in the loop. */ - reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level - 1]) | - __is_rsvd_bits_set(rsvd_check, sptes[level - 1], - level); - } + reserved |= __is_bad_mt_xwr(rsvd_check, sptes[level]) | + __is_rsvd_bits_set(rsvd_check, sptes[level], level); if (reserved) { pr_err("%s: detect reserved bits on spte, addr 0x%llx, dump hierarchy:\n", __func__, addr); for (level = root; level >= leaf; level--) pr_err("------ spte 0x%llx level %d.\n", - sptes[level - 1], level); + sptes[level], level); } - *sptep = sptes[leaf - 1]; - return reserved; } @@ -3651,8 +3647,8 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, } static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, - gpa_t cr2_or_gpa, kvm_pfn_t *pfn, bool write, - bool *writable) + gpa_t cr2_or_gpa, kvm_pfn_t *pfn, hva_t *hva, + bool write, bool *writable) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); bool async; @@ -3665,7 +3661,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, } async = false; - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, &async, + write, writable, hva); if (!async) return false; /* *pfn has correct page already */ @@ -3679,7 +3676,8 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool prefault, gfn_t gfn, return true; } - *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, write, writable); + *pfn = __gfn_to_pfn_memslot(slot, gfn, false, NULL, + write, writable, hva); return false; } @@ -3692,6 +3690,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, gfn_t gfn = gpa >> PAGE_SHIFT; unsigned long mmu_seq; kvm_pfn_t pfn; + hva_t hva; int r; if (page_fault_handle_page_track(vcpu, error_code, gfn)) @@ -3710,15 +3709,21 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, mmu_seq = vcpu->kvm->mmu_notifier_seq; smp_rmb(); - if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, write, &map_writable)) + if (try_async_pf(vcpu, prefault, gfn, gpa, &pfn, &hva, + write, &map_writable)) return RET_PF_RETRY; if (handle_abnormal_pfn(vcpu, is_tdp ? 0 : gpa, gfn, pfn, ACC_ALL, &r)) return r; r = RET_PF_RETRY; - spin_lock(&vcpu->kvm->mmu_lock); - if (mmu_notifier_retry(vcpu->kvm, mmu_seq)) + + if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + read_lock(&vcpu->kvm->mmu_lock); + else + write_lock(&vcpu->kvm->mmu_lock); + + if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; r = make_mmu_pages_available(vcpu); if (r) @@ -3732,7 +3737,10 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code, prefault, is_tdp); out_unlock: - spin_unlock(&vcpu->kvm->mmu_lock); + if (is_tdp_mmu_root(vcpu->kvm, vcpu->arch.mmu->root_hpa)) + read_unlock(&vcpu->kvm->mmu_lock); + else + write_unlock(&vcpu->kvm->mmu_lock); kvm_release_pfn_clean(pfn); return r; } @@ -3806,7 +3814,6 @@ static void nonpaging_init_context(struct kvm_vcpu *vcpu, context->gva_to_gpa = nonpaging_gva_to_gpa; context->sync_page = nonpaging_sync_page; context->invlpg = NULL; - context->update_pte = nonpaging_update_pte; context->root_level = 0; context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = true; @@ -3977,20 +3984,27 @@ static inline bool is_last_gpte(struct kvm_mmu *mmu, static void __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct rsvd_bits_validate *rsvd_check, - int maxphyaddr, int level, bool nx, bool gbpages, + u64 pa_bits_rsvd, int level, bool nx, bool gbpages, bool pse, bool amd) { - u64 exb_bit_rsvd = 0; u64 gbpages_bit_rsvd = 0; u64 nonleaf_bit8_rsvd = 0; + u64 high_bits_rsvd; rsvd_check->bad_mt_xwr = 0; - if (!nx) - exb_bit_rsvd = rsvd_bits(63, 63); if (!gbpages) gbpages_bit_rsvd = rsvd_bits(7, 7); + if (level == PT32E_ROOT_LEVEL) + high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 62); + else + high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); + + /* Note, NX doesn't exist in PDPTEs, this is handled below. */ + if (!nx) + high_bits_rsvd |= rsvd_bits(63, 63); + /* * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for * leaf entries) on AMD CPUs only. @@ -4019,45 +4033,39 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, rsvd_check->rsvd_bits_mask[1][1] = rsvd_bits(13, 21); break; case PT32E_ROOT_LEVEL: - rsvd_check->rsvd_bits_mask[0][2] = - rsvd_bits(maxphyaddr, 63) | - rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ - rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 62); /* PDE */ - rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 62); /* PTE */ - rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 62) | - rsvd_bits(13, 20); /* large page */ + rsvd_check->rsvd_bits_mask[0][2] = rsvd_bits(63, 63) | + high_bits_rsvd | + rsvd_bits(5, 8) | + rsvd_bits(1, 2); /* PDPTE */ + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd; /* PDE */ + rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* PTE */ + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | + rsvd_bits(13, 20); /* large page */ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; break; case PT64_ROOT_5LEVEL: - rsvd_check->rsvd_bits_mask[0][4] = exb_bit_rsvd | - nonleaf_bit8_rsvd | rsvd_bits(7, 7) | - rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | + nonleaf_bit8_rsvd | + rsvd_bits(7, 7); rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; fallthrough; case PT64_ROOT_4LEVEL: - rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd | - nonleaf_bit8_rsvd | rsvd_bits(7, 7) | - rsvd_bits(maxphyaddr, 51); - rsvd_check->rsvd_bits_mask[0][2] = exb_bit_rsvd | - gbpages_bit_rsvd | - rsvd_bits(maxphyaddr, 51); - rsvd_check->rsvd_bits_mask[0][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51); - rsvd_check->rsvd_bits_mask[0][0] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | + nonleaf_bit8_rsvd | + rsvd_bits(7, 7); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | + gbpages_bit_rsvd; + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd; + rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = exb_bit_rsvd | - gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | - rsvd_bits(13, 29); - rsvd_check->rsvd_bits_mask[1][1] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | - rsvd_bits(13, 20); /* large page */ + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | + gbpages_bit_rsvd | + rsvd_bits(13, 29); + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | + rsvd_bits(13, 20); /* large page */ rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; break; @@ -4068,8 +4076,8 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) { __reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check, - cpuid_maxphyaddr(vcpu), context->root_level, - context->nx, + vcpu->arch.reserved_gpa_bits, + context->root_level, context->nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), guest_cpuid_is_amd_or_hygon(vcpu)); @@ -4077,27 +4085,22 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, - int maxphyaddr, bool execonly) + u64 pa_bits_rsvd, bool execonly) { + u64 high_bits_rsvd = pa_bits_rsvd & rsvd_bits(0, 51); u64 bad_mt_xwr; - rsvd_check->rsvd_bits_mask[0][4] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][3] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 7); - rsvd_check->rsvd_bits_mask[0][2] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][1] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(3, 6); - rsvd_check->rsvd_bits_mask[0][0] = rsvd_bits(maxphyaddr, 51); + rsvd_check->rsvd_bits_mask[0][4] = high_bits_rsvd | rsvd_bits(3, 7); + rsvd_check->rsvd_bits_mask[0][3] = high_bits_rsvd | rsvd_bits(3, 7); + rsvd_check->rsvd_bits_mask[0][2] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][1] = high_bits_rsvd | rsvd_bits(3, 6); + rsvd_check->rsvd_bits_mask[0][0] = high_bits_rsvd; /* large page */ rsvd_check->rsvd_bits_mask[1][4] = rsvd_check->rsvd_bits_mask[0][4]; rsvd_check->rsvd_bits_mask[1][3] = rsvd_check->rsvd_bits_mask[0][3]; - rsvd_check->rsvd_bits_mask[1][2] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 29); - rsvd_check->rsvd_bits_mask[1][1] = - rsvd_bits(maxphyaddr, 51) | rsvd_bits(12, 20); + rsvd_check->rsvd_bits_mask[1][2] = high_bits_rsvd | rsvd_bits(12, 29); + rsvd_check->rsvd_bits_mask[1][1] = high_bits_rsvd | rsvd_bits(12, 20); rsvd_check->rsvd_bits_mask[1][0] = rsvd_check->rsvd_bits_mask[0][0]; bad_mt_xwr = 0xFFull << (2 * 8); /* bits 3..5 must not be 2 */ @@ -4116,7 +4119,12 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->guest_rsvd_check, - cpuid_maxphyaddr(vcpu), execonly); + vcpu->arch.reserved_gpa_bits, execonly); +} + +static inline u64 reserved_hpa_bits(void) +{ + return rsvd_bits(shadow_phys_bits, 63); } /* @@ -4138,7 +4146,7 @@ reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context) */ shadow_zero_check = &context->shadow_zero_check; __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - shadow_phys_bits, + reserved_hpa_bits(), context->shadow_root_level, uses_nx, guest_cpuid_has(vcpu, X86_FEATURE_GBPAGES), is_pse(vcpu), true); @@ -4175,14 +4183,13 @@ reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, if (boot_cpu_is_amd()) __reset_rsvds_bits_mask(vcpu, shadow_zero_check, - shadow_phys_bits, + reserved_hpa_bits(), context->shadow_root_level, false, boot_cpu_has(X86_FEATURE_GBPAGES), true, true); else __reset_rsvds_bits_mask_ept(shadow_zero_check, - shadow_phys_bits, - false); + reserved_hpa_bits(), false); if (!shadow_me_mask) return; @@ -4202,7 +4209,7 @@ reset_ept_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context, bool execonly) { __reset_rsvds_bits_mask_ept(&context->shadow_zero_check, - shadow_phys_bits, execonly); + reserved_hpa_bits(), execonly); } #define BYTE_MASK(access) \ @@ -4388,7 +4395,6 @@ static void paging64_init_context_common(struct kvm_vcpu *vcpu, context->gva_to_gpa = paging64_gva_to_gpa; context->sync_page = paging64_sync_page; context->invlpg = paging64_invlpg; - context->update_pte = paging64_update_pte; context->shadow_root_level = level; context->direct_map = false; } @@ -4417,7 +4423,6 @@ static void paging32_init_context(struct kvm_vcpu *vcpu, context->gva_to_gpa = paging32_gva_to_gpa; context->sync_page = paging32_sync_page; context->invlpg = paging32_invlpg; - context->update_pte = paging32_update_pte; context->shadow_root_level = PT32E_ROOT_LEVEL; context->direct_map = false; } @@ -4499,7 +4504,6 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu) context->page_fault = kvm_tdp_page_fault; context->sync_page = nonpaging_sync_page; context->invlpg = NULL; - context->update_pte = nonpaging_update_pte; context->shadow_root_level = kvm_mmu_get_tdp_level(vcpu); context->direct_map = true; context->get_guest_pgd = get_cr3; @@ -4671,7 +4675,6 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly, context->gva_to_gpa = ept_gva_to_gpa; context->sync_page = ept_sync_page; context->invlpg = ept_invlpg; - context->update_pte = ept_update_pte; context->root_level = level; context->direct_map = false; context->mmu_role.as_u64 = new_role.as_u64; @@ -4804,7 +4807,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu) if (r) goto out; kvm_mmu_load_pgd(vcpu); - kvm_x86_ops.tlb_flush_current(vcpu); + static_call(kvm_x86_tlb_flush_current)(vcpu); out: return r; } @@ -4819,19 +4822,6 @@ void kvm_mmu_unload(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_mmu_unload); -static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp, u64 *spte, - const void *new) -{ - if (sp->role.level != PG_LEVEL_4K) { - ++vcpu->kvm->stat.mmu_pde_zapped; - return; - } - - ++vcpu->kvm->stat.mmu_pte_updated; - vcpu->arch.mmu->update_pte(vcpu, sp, spte, new); -} - static bool need_remote_flush(u64 old, u64 new) { if (!is_shadow_present_pte(old)) @@ -4947,22 +4937,6 @@ static u64 *get_written_sptes(struct kvm_mmu_page *sp, gpa_t gpa, int *nspte) return spte; } -/* - * Ignore various flags when determining if a SPTE can be immediately - * overwritten for the current MMU. - * - level: explicitly checked in mmu_pte_write_new_pte(), and will never - * match the current MMU role, as MMU's level tracks the root level. - * - access: updated based on the new guest PTE - * - quadrant: handled by get_written_sptes() - * - invalid: always false (loop only walks valid shadow pages) - */ -static const union kvm_mmu_page_role role_ign = { - .level = 0xf, - .access = 0x7, - .quadrant = 0x3, - .invalid = 0x1, -}; - static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, int bytes, struct kvm_page_track_notifier_node *node) @@ -4992,7 +4966,7 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, */ mmu_topup_memory_caches(vcpu, true); - spin_lock(&vcpu->kvm->mmu_lock); + write_lock(&vcpu->kvm->mmu_lock); gentry = mmu_pte_write_fetch_gpte(vcpu, &gpa, &bytes); @@ -5013,14 +4987,10 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, local_flush = true; while (npte--) { - u32 base_role = vcpu->arch.mmu->mmu_role.base.word; - entry = *spte; mmu_page_zap_pte(vcpu->kvm, sp, spte, NULL); - if (gentry && - !((sp->role.word ^ base_role) & ~role_ign.word) && - rmap_can_add(vcpu)) - mmu_pte_write_new_pte(vcpu, sp, spte, &gentry); + if (gentry && sp->role.level != PG_LEVEL_4K) + ++vcpu->kvm->stat.mmu_pde_zapped; if (need_remote_flush(entry, *spte)) remote_flush = true; ++spte; @@ -5028,25 +4998,9 @@ static void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, } kvm_mmu_flush_or_zap(vcpu, &invalid_list, remote_flush, local_flush); kvm_mmu_audit(vcpu, AUDIT_POST_PTE_WRITE); - spin_unlock(&vcpu->kvm->mmu_lock); + write_unlock(&vcpu->kvm->mmu_lock); } -int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva) -{ - gpa_t gpa; - int r; - - if (vcpu->arch.mmu->direct_map) - return 0; - - gpa = kvm_mmu_gva_to_gpa_read(vcpu, gva, NULL); - - r = kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT); - - return r; -} -EXPORT_SYMBOL_GPL(kvm_mmu_unprotect_page_virt); - int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code, void *insn, int insn_len) { @@ -5118,7 +5072,7 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, if (is_noncanonical_address(gva, vcpu)) return; - kvm_x86_ops.tlb_flush_gva(vcpu, gva); + static_call(kvm_x86_tlb_flush_gva)(vcpu, gva); } if (!mmu->invlpg) @@ -5145,7 +5099,6 @@ void kvm_mmu_invalidate_gva(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, mmu->invlpg(vcpu, gva, root_hpa); } } -EXPORT_SYMBOL_GPL(kvm_mmu_invalidate_gva); void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva) { @@ -5175,7 +5128,7 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) } if (tlb_flush) - kvm_x86_ops.tlb_flush_gva(vcpu, gva); + static_call(kvm_x86_tlb_flush_gva)(vcpu, gva); ++vcpu->stat.invlpg; @@ -5185,7 +5138,6 @@ void kvm_mmu_invpcid_gva(struct kvm_vcpu *vcpu, gva_t gva, unsigned long pcid) * for them. */ } -EXPORT_SYMBOL_GPL(kvm_mmu_invpcid_gva); void kvm_configure_mmu(bool enable_tdp, int tdp_max_root_level, int tdp_huge_page_level) @@ -5210,7 +5162,8 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_max_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, struct kvm_rmap_head *rmap_head); +typedef bool (*slot_level_handler) (struct kvm *kvm, struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot); /* The caller should hold mmu-lock before calling this function. */ static __always_inline bool @@ -5224,16 +5177,16 @@ slot_handle_level_range(struct kvm *kvm, struct kvm_memory_slot *memslot, for_each_slot_rmap_range(memslot, start_level, end_level, start_gfn, end_gfn, &iterator) { if (iterator.rmap) - flush |= fn(kvm, iterator.rmap); + flush |= fn(kvm, iterator.rmap, memslot); - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { if (flush && lock_flush_tlb) { kvm_flush_remote_tlbs_with_address(kvm, start_gfn, iterator.gfn - start_gfn + 1); flush = false; } - cond_resched_lock(&kvm->mmu_lock); + cond_resched_rwlock_write(&kvm->mmu_lock); } } @@ -5258,22 +5211,6 @@ slot_handle_level(struct kvm *kvm, struct kvm_memory_slot *memslot, } static __always_inline bool -slot_handle_all_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K, - KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} - -static __always_inline bool -slot_handle_large_level(struct kvm *kvm, struct kvm_memory_slot *memslot, - slot_level_handler fn, bool lock_flush_tlb) -{ - return slot_handle_level(kvm, memslot, fn, PG_LEVEL_4K + 1, - KVM_MAX_HUGEPAGE_LEVEL, lock_flush_tlb); -} - -static __always_inline bool slot_handle_leaf(struct kvm *kvm, struct kvm_memory_slot *memslot, slot_level_handler fn, bool lock_flush_tlb) { @@ -5383,7 +5320,7 @@ restart: * be in active use by the guest. */ if (batch >= BATCH_ZAP_PAGES && - cond_resched_lock(&kvm->mmu_lock)) { + cond_resched_rwlock_write(&kvm->mmu_lock)) { batch = 0; goto restart; } @@ -5416,7 +5353,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) { lockdep_assert_held(&kvm->slots_lock); - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); trace_kvm_mmu_zap_all_fast(kvm); /* @@ -5440,10 +5377,10 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) kvm_zap_obsolete_pages(kvm); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_zap_all(kvm); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm) @@ -5485,7 +5422,7 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) int i; bool flush; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot(memslot, slots) { @@ -5503,17 +5440,18 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end) } } - if (kvm->arch.tdp_mmu_enabled) { + if (is_tdp_mmu_enabled(kvm)) { flush = kvm_tdp_mmu_zap_gfn_range(kvm, gfn_start, gfn_end); if (flush) kvm_flush_remote_tlbs(kvm); } - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } static bool slot_rmap_write_protect(struct kvm *kvm, - struct kvm_rmap_head *rmap_head) + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { return __rmap_write_protect(kvm, rmap_head, false); } @@ -5524,12 +5462,12 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, { bool flush; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); flush = slot_handle_level(kvm, memslot, slot_rmap_write_protect, start_level, KVM_MAX_HUGEPAGE_LEVEL, false); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_4K); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); /* * We can flush all the TLBs out of the mmu lock without TLB @@ -5547,7 +5485,8 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, } static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, - struct kvm_rmap_head *rmap_head) + struct kvm_rmap_head *rmap_head, + struct kvm_memory_slot *slot) { u64 *sptep; struct rmap_iterator iter; @@ -5568,8 +5507,8 @@ restart: * mapping if the indirect sp has level = 1. */ if (sp->role.direct && !kvm_is_reserved_pfn(pfn) && - (kvm_is_zone_device_pfn(pfn) || - PageCompound(pfn_to_page(pfn)))) { + sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn, + pfn, PG_LEVEL_NUM)) { pte_list_remove(rmap_head, sptep); if (kvm_available_flush_tlb_with_range()) @@ -5589,13 +5528,14 @@ void kvm_mmu_zap_collapsible_sptes(struct kvm *kvm, const struct kvm_memory_slot *memslot) { /* FIXME: const-ify all uses of struct kvm_memory_slot. */ - spin_lock(&kvm->mmu_lock); - slot_handle_leaf(kvm, (struct kvm_memory_slot *)memslot, - kvm_mmu_zap_collapsible_spte, true); + struct kvm_memory_slot *slot = (struct kvm_memory_slot *)memslot; - if (kvm->arch.tdp_mmu_enabled) - kvm_tdp_mmu_zap_collapsible_sptes(kvm, memslot); - spin_unlock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); + slot_handle_leaf(kvm, slot, kvm_mmu_zap_collapsible_spte, true); + + if (is_tdp_mmu_enabled(kvm)) + kvm_tdp_mmu_zap_collapsible_sptes(kvm, slot); + write_unlock(&kvm->mmu_lock); } void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, @@ -5618,11 +5558,11 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, { bool flush; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); flush = slot_handle_leaf(kvm, memslot, __rmap_clear_dirty, false); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) flush |= kvm_tdp_mmu_clear_dirty_slot(kvm, memslot); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); /* * It's also safe to flush TLBs out of mmu lock here as currently this @@ -5633,40 +5573,6 @@ void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm, if (flush) kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); } -EXPORT_SYMBOL_GPL(kvm_mmu_slot_leaf_clear_dirty); - -void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm, - struct kvm_memory_slot *memslot) -{ - bool flush; - - spin_lock(&kvm->mmu_lock); - flush = slot_handle_large_level(kvm, memslot, slot_rmap_write_protect, - false); - if (kvm->arch.tdp_mmu_enabled) - flush |= kvm_tdp_mmu_wrprot_slot(kvm, memslot, PG_LEVEL_2M); - spin_unlock(&kvm->mmu_lock); - - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); -} -EXPORT_SYMBOL_GPL(kvm_mmu_slot_largepage_remove_write_access); - -void kvm_mmu_slot_set_dirty(struct kvm *kvm, - struct kvm_memory_slot *memslot) -{ - bool flush; - - spin_lock(&kvm->mmu_lock); - flush = slot_handle_all_level(kvm, memslot, __rmap_set_dirty, false); - if (kvm->arch.tdp_mmu_enabled) - flush |= kvm_tdp_mmu_slot_set_dirty(kvm, memslot); - spin_unlock(&kvm->mmu_lock); - - if (flush) - kvm_arch_flush_remote_tlbs_memslot(kvm, memslot); -} -EXPORT_SYMBOL_GPL(kvm_mmu_slot_set_dirty); void kvm_mmu_zap_all(struct kvm *kvm) { @@ -5674,23 +5580,23 @@ void kvm_mmu_zap_all(struct kvm *kvm) LIST_HEAD(invalid_list); int ign; - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); restart: list_for_each_entry_safe(sp, node, &kvm->arch.active_mmu_pages, link) { if (WARN_ON(sp->role.invalid)) continue; if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list, &ign)) goto restart; - if (cond_resched_lock(&kvm->mmu_lock)) + if (cond_resched_rwlock_write(&kvm->mmu_lock)) goto restart; } kvm_mmu_commit_zap_page(kvm, &invalid_list); - if (kvm->arch.tdp_mmu_enabled) + if (is_tdp_mmu_enabled(kvm)) kvm_tdp_mmu_zap_all(kvm); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); } void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm, u64 gen) @@ -5750,7 +5656,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) continue; idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); if (kvm_has_zapped_obsolete_pages(kvm)) { kvm_mmu_commit_zap_page(kvm, @@ -5761,7 +5667,7 @@ mmu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) freed = kvm_mmu_zap_oldest_mmu_pages(kvm, sc->nr_to_scan); unlock: - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); /* @@ -5981,7 +5887,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) ulong to_zap; rcu_idx = srcu_read_lock(&kvm->srcu); - spin_lock(&kvm->mmu_lock); + write_lock(&kvm->mmu_lock); ratio = READ_ONCE(nx_huge_pages_recovery_ratio); to_zap = ratio ? DIV_ROUND_UP(kvm->stat.nx_lpage_splits, ratio) : 0; @@ -5998,22 +5904,22 @@ static void kvm_recover_nx_lpages(struct kvm *kvm) struct kvm_mmu_page, lpage_disallowed_link); WARN_ON_ONCE(!sp->lpage_disallowed); - if (sp->tdp_mmu_page) + if (is_tdp_mmu_page(sp)) { kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level)); - else { + } else { kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list); WARN_ON_ONCE(sp->lpage_disallowed); } - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { + if (need_resched() || rwlock_needbreak(&kvm->mmu_lock)) { kvm_mmu_commit_zap_page(kvm, &invalid_list); - cond_resched_lock(&kvm->mmu_lock); + cond_resched_rwlock_write(&kvm->mmu_lock); } } kvm_mmu_commit_zap_page(kvm, &invalid_list); - spin_unlock(&kvm->mmu_lock); + write_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, rcu_idx); } |