From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Thu, 12 Sep 2019 19:46:10 -0700
Subject: KVM: x86/mmu: Revert "KVM: x86/mmu: Remove is_obsolete() call"
Git-commit: 10605204e91f46bdec98bef81923263d245515a0
Patch-mainline: v5.4-rc1
References: bsc#1164357

Now that the fast invalidate mechanism has been reintroduced, restore
the performance tweaks for fast invalidation that existed prior to its
removal.

Paraphrasing the original changelog (commit 5ff0568374ed2 was itself a
partial revert):

  Don't force reloading the remote mmu when zapping an obsolete page, as
  a MMU_RELOAD request has already been issued by kvm_mmu_zap_all_fast()
  immediately after incrementing mmu_valid_gen, i.e. after marking pages
  obsolete.

This reverts commit 5ff0568374ed2e585376a3832857ade5daccd381.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Joerg Roedel <jroedel@suse.de>
---
 arch/x86/kvm/mmu.c | 29 +++++++++++++++++++++++------
 arch/x86/kvm/x86.c |  1 +
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 652f2ce14583..e552fd5cd33d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2752,7 +2752,12 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 	} else {
 		list_move(&sp->link, &kvm->arch.active_mmu_pages);
 
-		if (!sp->role.invalid)
+		/*
+		 * Obsolete pages cannot be used on any vCPUs, see the comment
+		 * in kvm_mmu_zap_all_fast().  Note, is_obsolete_sp() also
+		 * treats invalid shadow pages as being obsolete.
+		 */
+		if (!is_obsolete_sp(kvm, sp))
 			kvm_reload_remote_mmus(kvm);
 	}
 
@@ -5675,7 +5680,6 @@ int kvm_mmu_create(struct kvm_vcpu *vcpu)
 static void kvm_zap_obsolete_pages(struct kvm *kvm)
 {
 	struct kvm_mmu_page *sp, *node;
-	LIST_HEAD(invalid_list);
 	int nr_zapped, batch = 0;
 
 restart:
@@ -5708,8 +5712,8 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm)
 			goto restart;
 		}
 
-		if (__kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list,
-					       &nr_zapped)) {
+		if (__kvm_mmu_prepare_zap_page(kvm, sp,
+				&kvm->arch.zapped_obsolete_pages, &nr_zapped)) {
 			batch += nr_zapped;
 			goto restart;
 		}
@@ -5720,7 +5724,7 @@ static void kvm_zap_obsolete_pages(struct kvm *kvm)
 	 * KVM is not in the middle of a lockless shadow page table walk, which
 	 * may reference the pages.
 	 */
-	kvm_mmu_commit_zap_page(kvm, &invalid_list);
+	kvm_mmu_commit_zap_page(kvm, &kvm->arch.zapped_obsolete_pages);
 }
 
 /*
@@ -5752,6 +5756,11 @@ static void kvm_mmu_zap_all_fast(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 void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
 			struct kvm_memory_slot *slot,
 			struct kvm_page_track_notifier_node *node)
@@ -6022,16 +6031,24 @@ mmu_shrink_scan(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;
+		}
+
 		if (prepare_zap_oldest_mmu_page(kvm, &invalid_list))
 			freed++;
 		kvm_mmu_commit_zap_page(kvm, &invalid_list);
 
+unlock:
 		spin_unlock(&kvm->mmu_lock);
 		srcu_read_unlock(&kvm->srcu, idx);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 977b36348bed..c9a3d8efe1c2 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9425,6 +9425,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
+	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);