2 files changed, 91 insertions, 0 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f8ca2f351395..d71bf8fcccf8 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -1511,6 +1511,12 @@ static struct kvm_mmu_page *kvm_mmu_alloc_page(struct kvm_vcpu *vcpu,
         if (!direct)
                 sp->gfns = mmu_memory_cache_alloc(&vcpu->arch.mmu_page_cache);
         set_page_private(virt_to_page(sp->spt), (unsigned long)sp);
+
+        /*
+         * The active_mmu_pages list is the FIFO list, do not move the
+         * page until it is zapped. kvm_zap_obsolete_pages depends on
+         * this feature. See the comments in kvm_zap_obsolete_pages().
+         */
         list_add(&sp->link, &vcpu->kvm->arch.active_mmu_pages);
         sp->parent_ptes = 0;
         mmu_page_add_parent_pte(vcpu, sp, parent_pte);
@@ -1838,6 +1844,11 @@ static void clear_sp_write_flooding_count(u64 *spte)
         __clear_sp_write_flooding_count(sp);
 }
 
+static bool is_obsolete_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+        return unlikely(sp->mmu_valid_gen != kvm->arch.mmu_valid_gen);
+}
+
 static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
                                              gfn_t gfn,
                                              gva_t gaddr,
@@ -1900,6 +1911,7 @@ static struct kvm_mmu_page *kvm_mmu_get_page(struct kvm_vcpu *vcpu,
 
                 account_shadowed(vcpu->kvm, gfn);
         }
+        sp->mmu_valid_gen = vcpu->kvm->arch.mmu_valid_gen;
         init_shadow_page_table(sp);
         trace_kvm_mmu_get_page(sp, true);
         return sp;
@@ -2070,8 +2082,10 @@ static int kvm_mmu_prepare_zap_page(struct kvm *kvm, struct kvm_mmu_page *sp,
         ret = mmu_zap_unsync_children(kvm, sp, invalid_list);
         kvm_mmu_page_unlink_children(kvm, sp);
         kvm_mmu_unlink_parents(kvm, sp);
+
         if (!sp->role.invalid && !sp->role.direct)
                 unaccount_shadowed(kvm, sp->gfn);
+
         if (sp->unsync)
                 kvm_unlink_unsync_page(kvm, sp);
         if (!sp->root_count) {
@@ -4195,6 +4209,82 @@ restart:
         spin_unlock(&kvm->mmu_lock);
 }
 
+static void kvm_zap_obsolete_pages(struct kvm *kvm)
+{
+        struct kvm_mmu_page *sp, *node;
+        LIST_HEAD(invalid_list);
+
+restart:
+        list_for_each_entry_safe_reverse(sp, node,
+              &kvm->arch.active_mmu_pages, link) {
+                /*
+                 * No obsolete page exists before new created page since
+                 * active_mmu_pages is the FIFO list.
+                 */
+                if (!is_obsolete_sp(kvm, sp))
+                        break;
+
+                /*
+                 * Do not repeatedly zap a root page to avoid unnecessary
+                 * KVM_REQ_MMU_RELOAD, otherwise we may not be able to
+                 * progress:
+                 *    vcpu 0                        vcpu 1
+                 *                         call vcpu_enter_guest():
+                 *                            1): handle KVM_REQ_MMU_RELOAD
+                 *                                and require mmu-lock to
+                 *                                load mmu
+                 * repeat:
+                 *    1): zap root page and
+                 *        send KVM_REQ_MMU_RELOAD
+                 *
+                 *    2): if (cond_resched_lock(mmu-lock))
+                 *
+                 *                            2): hold mmu-lock and load mmu
+                 *
+                 *                            3): see KVM_REQ_MMU_RELOAD bit
+                 *                                on vcpu->requests is set
+                 *                                then return 1 to call
+                 *                                vcpu_enter_guest() again.
+                 *            goto repeat;
+                 *
+                 * Since we are reversely walking the list and the invalid
+                 * list will be moved to the head, skip the invalid page
+                 * can help us to avoid the infinity list walking.
+                 */
+                if (sp->role.invalid)
+                        continue;
+
+                if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
+                        kvm_mmu_commit_zap_page(kvm, &invalid_list);
+                        cond_resched_lock(&kvm->mmu_lock);
+                        goto restart;
+                }
+
+                if (kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list))
+                        goto restart;
+        }
+
+        kvm_mmu_commit_zap_page(kvm, &invalid_list);
+}
+
+/*
+ * Fast invalidate all shadow pages and use lock-break technique
+ * to zap obsolete pages.
+ *
+ * It's required when memslot is being deleted or VM is being
+ * destroyed, in these cases, we should ensure that KVM MMU does
+ * not use any resource of the being-deleted slot or all slots
+ * after calling the function.
+ */
+void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm)
+{
+        spin_lock(&kvm->mmu_lock);
+        kvm->arch.mmu_valid_gen++;
+
+        kvm_zap_obsolete_pages(kvm);
+        spin_unlock(&kvm->mmu_lock);
+}
+
 void kvm_mmu_zap_mmio_sptes(struct kvm *kvm)
 {
         struct kvm_mmu_page *sp, *node;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 2adcbc2cac6d..922bfae77c58 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -97,4 +97,5 @@ static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
         return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
 }
 
+void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
 #endif