KVM: MMU: reclaim the zapped-obsolete page first

As Marcelo pointed out that
| "(retention of large number of pages while zapping)
| can be fatal, it can lead to OOM and host crash"

We introduce a list, kvm->arch.zapped_obsolete_pages, to link all
the pages which are deleted from the mmu cache but not actually
freed. When page reclaiming is needed, we always zap this kind of
pages first.
Signed-off-by: NXiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Reviewed-by: NMarcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: NGleb Natapov <gleb@redhat.com>

arch/x86/include/asm/kvm_host.h

@@ -536,6 +536,8 @@ struct kvm_arch {
 	 * Hash table of struct kvm_mmu_page.
 	 */
 	struct list_head active_mmu_pages;
+	struct list_head zapped_obsolete_pages;
+
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
 	int iommu_flags;

arch/x86/kvm/mmu.c

@@ -4211,7 +4211,6 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot)
 static void kvm_zap_obsolete_pages(struct kvm *kvm)
 {
 	struct kvm_mmu_page *sp, *node;
-	LIST_HEAD(invalid_list);
 	int batch = 0;
 
 restart:
@@ -4244,7 +4243,8 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm)
 			goto restart;
 		}
 
-		ret = kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
+		ret = kvm_mmu_prepare_zap_page(kvm, sp,
+				&kvm->arch.zapped_obsolete_pages);
 		batch += ret;
 
 		if (ret)
@@ -4255,7 +4255,7 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm)
 	 * Should flush tlb before free page tables since lockless-walking
 	 * may use the pages.
 	 */
-	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages);
 }
 
 /*
@@ -4306,6 +4306,11 @@ void kvm_mmu_zap_mmio_sptes(struct kvm *kvm)
 	spin_unlock(&kvm->mmu_lock);
 }
 
+static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
+{
+	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
+}
+
 static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
 {
 	struct kvm *kvm;
@@ -4334,15 +4339,23 @@ static int mmu_shrink(struct shrinker *shrink, struct shrink_control *sc)
 		 * want to shrink a VM that only started to populate its MMU
 		 * anyway.
 		 */
-		if (!kvm->arch.n_used_mmu_pages)
+		if (!kvm->arch.n_used_mmu_pages &&
+		      !kvm_has_zapped_obsolete_pages(kvm))
 			continue;
 
 		idx = srcu_read_lock(&kvm->srcu);
 		spin_lock(&kvm->mmu_lock);
 
+		if (kvm_has_zapped_obsolete_pages(kvm)) {
+			kvm_mmu_commit_zap_page(kvm,
+			      &kvm->arch.zapped_obsolete_pages);
+			goto unlock;
+		}
+
 		prepare_zap_oldest_mmu_page(kvm, &invalid_list);
 		kvm_mmu_commit_zap_page(kvm, &invalid_list);
 
+unlock:
 		spin_unlock(&kvm->mmu_lock);
 		srcu_read_unlock(&kvm->srcu, idx);
 

arch/x86/kvm/x86.c

@@ -6832,6 +6832,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		return -EINVAL;
 
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 
 	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */