On Tue, Apr 05, 2022, Michael Roth wrote:

On Thu, Mar 10, 2022 at 10:09:09PM +0800, Chao Peng wrote:

quoted

 static inline bool kvm_slot_is_private(const struct kvm_memory_slot *slot)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 67349421eae3..52319f49d58a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c

@@ -841,8 +841,43 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
 #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
 
 #ifdef CONFIG_MEMFILE_NOTIFIER
+static void kvm_memfile_notifier_handler(struct memfile_notifier *notifier,
+					 pgoff_t start, pgoff_t end)
+{
+	int idx;
+	struct kvm_memory_slot *slot = container_of(notifier,
+						    struct kvm_memory_slot,
+						    notifier);
+	struct kvm_gfn_range gfn_range = {
+		.slot		= slot,
+		.start		= start - (slot->private_offset >> PAGE_SHIFT),
+		.end		= end - (slot->private_offset >> PAGE_SHIFT),
+		.may_block 	= true,
+	};
+	struct kvm *kvm = slot->kvm;
+
+	gfn_range.start = max(gfn_range.start, slot->base_gfn);
+	gfn_range.end = min(gfn_range.end, slot->base_gfn + slot->npages);
+
+	if (gfn_range.start >= gfn_range.end)
+		return;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	KVM_MMU_LOCK(kvm);
+	kvm_unmap_gfn_range(kvm, &gfn_range);
+	kvm_flush_remote_tlbs(kvm);
+	KVM_MMU_UNLOCK(kvm);
+	srcu_read_unlock(&kvm->srcu, idx);

Should this also invalidate gfn_to_pfn_cache mappings? Otherwise it seems
possible the kernel might end up inadvertantly writing to now-private guest
memory via a now-stale gfn_to_pfn_cache entry.

Yes.  Ideally we'd get these flows to share common code and avoid these goofs.
I tried very briefly but they're just different enough to make it ugly.