diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index 08f97cf97264..346e47f15572 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -81,6 +81,9 @@ bool kvm_gfn_to_pfn_cache_check(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 
+	if (!gpc->active)
+		return false;
+
 	if ((gpa & ~PAGE_MASK) + len > PAGE_SIZE)
 		return false;
 
@@ -240,10 +243,11 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	unsigned long page_offset = gpa & ~PAGE_MASK;
-	kvm_pfn_t old_pfn, new_pfn;
+	bool unmap_old = false;
 	unsigned long old_uhva;
+	kvm_pfn_t old_pfn;
 	void *old_khva;
-	int ret = 0;
+	int ret;
 
 	/*
 	 * If must fit within a single page. The 'len' argument is
@@ -261,6 +265,11 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 
 	write_lock_irq(&gpc->lock);
 
+	if (!gpc->active) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	old_pfn = gpc->pfn;
 	old_khva = gpc->khva - offset_in_page(gpc->khva);
 	old_uhva = gpc->uhva;
@@ -291,6 +300,7 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 		/* If the HVA→PFN mapping was already valid, don't unmap it. */
 		old_pfn = KVM_PFN_ERR_FAULT;
 		old_khva = NULL;
+		ret = 0;
 	}
 
  out:
@@ -305,14 +315,15 @@ int kvm_gfn_to_pfn_cache_refresh(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 		gpc->khva = NULL;
 	}
 
-	/* Snapshot the new pfn before dropping the lock! */
-	new_pfn = gpc->pfn;
+	/* Detect a pfn change before dropping the lock! */
+	unmap_old = (old_pfn != gpc->pfn);
 
+out_unlock:
 	write_unlock_irq(&gpc->lock);
 
 	mutex_unlock(&gpc->refresh_lock);
 
-	if (old_pfn != new_pfn)
+	if (unmap_old)
 		gpc_unmap_khva(kvm, old_pfn, old_khva);
 
 	return ret;
@@ -366,11 +377,19 @@ int kvm_gpc_activate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc,
 		gpc->vcpu = vcpu;
 		gpc->usage = usage;
 		gpc->valid = false;
-		gpc->active = true;
 
 		spin_lock(&kvm->gpc_lock);
 		list_add(&gpc->list, &kvm->gpc_list);
 		spin_unlock(&kvm->gpc_lock);
+
+		/*
+		 * Activate the cache after adding it to the list, a concurrent
+		 * refresh must not establish a mapping until the cache is
+		 * reachable by mmu_notifier events.
+		 */
+		write_lock_irq(&gpc->lock);
+		gpc->active = true;
+		write_unlock_irq(&gpc->lock);
 	}
 	return kvm_gfn_to_pfn_cache_refresh(kvm, gpc, gpa, len);
 }
@@ -379,12 +398,20 @@ EXPORT_SYMBOL_GPL(kvm_gpc_activate);
 void kvm_gpc_deactivate(struct kvm *kvm, struct gfn_to_pfn_cache *gpc)
 {
 	if (gpc->active) {
+		/*
+		 * Deactivate the cache before removing it from the list, KVM
+		 * must stall mmu_notifier events until all users go away, i.e.
+		 * until gpc->lock is dropped and refresh is guaranteed to fail.
+		 */
+		write_lock_irq(&gpc->lock);
+		gpc->active = false;
+		write_unlock_irq(&gpc->lock);
+
 		spin_lock(&kvm->gpc_lock);
 		list_del(&gpc->list);
 		spin_unlock(&kvm->gpc_lock);
 
 		kvm_gfn_to_pfn_cache_unmap(kvm, gpc);
-		gpc->active = false;
 	}
 }
 EXPORT_SYMBOL_GPL(kvm_gpc_deactivate);