[RFC PATCH v4 11/25] KVM: guest_memfd: Clear private device state on final close

["Aneesh Kumar K.V (Arm)" <aneesh.kumar@kernel.org>]

Add an optional backing release() callback after the generic
file-release path invalidates guest mappings. Device backing uses it to
clear has_private_ranges so device cleanup can proceed after the last
file user is gone.

Hold the provider lock across invalidation and the release callback so
device unlock cannot race with mapping removal and summary updates.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Cc: David Hildenbrand <david@kernel.org>
Cc: kvm@vger.kernel.org
Cc: patches@lists.linux.dev
Signed-off-by: Aneesh Kumar K.V (Arm) <aneesh.kumar@kernel.org>
---
 virt/kvm/guest_memfd.c | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c
index dd567979d938..d3de2e7bb9f5 100644
--- a/virt/kvm/guest_memfd.c
+++ b/virt/kvm/guest_memfd.c
@@ -65,6 +65,12 @@ struct kvm_gmem_backing_ops {
 			   kvm_pfn_t nr_pages, u64 attrs);
 	/* Called after the common code stores the new attributes. */
 	void (*update_attributes)(struct inode *inode);
+	/*
+	 * Finish file cleanup after invalidation. Caller holds kvm->slots_lock
+	 * and inode->i_mapping->invalidate_lock for write, between calls to
+	 * gmem_provider_lock() and gmem_provider_unlock().
+	 */
+	void (*release)(struct inode *inode);
 };
 
 struct gmem_inode {
@@ -104,6 +110,7 @@ static bool gmem_provider_is_device(struct gmem_inode *gi)
 static void kvm_gmem_device_update_attributes(struct inode *inode);
 static int kvm_gmem_device_convert_attributes(struct inode *inode, pgoff_t start,
 					      pgoff_t end, u64 attrs);
+static void kvm_gmem_device_release(struct inode *inode);
 
 static bool kvm_gmem_is_pfn_mode(struct gmem_inode *gi)
 {
@@ -751,9 +758,11 @@ static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset,
 static int kvm_gmem_release(struct inode *inode, struct file *file)
 {
 	struct gmem_file *f = file->private_data;
+	struct gmem_inode *gi = GMEM_I(inode);
 	struct kvm_memory_slot *slot;
 	struct kvm *kvm = f->kvm;
 	unsigned long index;
+	enum kvm_gfn_range_filter filter = kvm_gmem_get_all_gfns_filter(inode);
 
 	/*
 	 * Prevent concurrent attempts to *unbind* a memslot.  This is the last
@@ -766,6 +775,8 @@ static int kvm_gmem_release(struct inode *inode, struct file *file)
 
 	filemap_invalidate_lock(inode->i_mapping);
 
+	gmem_provider_lock(gi);
+
 	/*
 	 * Note!  synchronize_srcu() is _not_ needed after nullifying memslot
 	 * bindings as slot->gmem.file cannot be set back to a non-null value
@@ -815,13 +826,15 @@ static int kvm_gmem_release(struct inode *inode, struct file *file)
 		WRITE_ONCE(slot->gmem.file, NULL);
 
 	/*
-	 * All in-flight operations are gone and new bindings can be created.
+	 * All in-flight operations are gone and no new bindings can be created.
 	 * Zap all SPTEs pointed at by this file.  Do not free the backing
 	 * memory, as its lifetime is associated with the inode, not the file.
 	 */
-	__kvm_gmem_invalidate_start(f, 0, -1ul,
-				    kvm_gmem_get_all_gfns_filter(inode));
+	__kvm_gmem_invalidate_start(f, 0, -1ul, filter);
 	__kvm_gmem_invalidate_end(f, 0, -1ul);
+	if (gi->backing_ops && gi->backing_ops->release)
+		gi->backing_ops->release(inode);
+	gmem_provider_unlock(gi);
 
 	list_del(&f->entry);
 
@@ -1228,6 +1241,7 @@ static const struct kvm_gmem_backing_ops kvm_gmem_device_backing_ops = {
 	.prepare_attributes = kvm_gmem_pfn_prepare_attributes,
 	.convert_attributes = kvm_gmem_device_convert_attributes,
 	.update_attributes = kvm_gmem_device_update_attributes,
+	.release = kvm_gmem_device_release,
 };
 
 static const struct kvm_gmem_backing_ops *
@@ -1638,6 +1652,12 @@ static int kvm_gmem_device_convert_attributes(struct inode *inode, pgoff_t start
 	return 0;
 }
 
+/* No file users remain, so private attributes cannot create new mappings. */
+static void kvm_gmem_device_release(struct inode *inode)
+{
+	WRITE_ONCE(GMEM_I(inode)->device.has_private_ranges, false);
+}
+
 static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags, int resource_fd)
 {
 	static const char *name = "[kvm-gmem]";
-- 
2.43.0