btrfs: detect nocow for swap after snapshot delete

commit a84d5d429f9eb56f81b388609841ed993f0ddfca upstream.

can_nocow_extent and btrfs_cross_ref_exist both rely on a heuristic for
detecting a must cow condition which is not exactly accurate, but saves
unnecessary tree traversal. The incorrect assumption is that if the
extent was created in a generation smaller than the last snapshot
generation, it must be referenced by that snapshot. That is true, except
the snapshot could have since been deleted, without affecting the last
snapshot generation.

The original patch claimed a performance win from this check, but it
also leads to a bug where you are unable to use a swapfile if you ever
snapshotted the subvolume it's in. Make the check slower and more strict
for the swapon case, without modifying the general cow checks as a
compromise. Turning swap on does not seem to be a particularly
performance sensitive operation, so incurring a possibly unnecessary
btrfs_search_slot seems worthwhile for the added usability.

Note: Until the snapshot is competely cleaned after deletion,
check_committed_refs will still cause the logic to think that cow is
necessary, so the user must until 'btrfs subvolu sync' finished before
activating the swapfile swapon.

CC: stable@vger.kernel.org # 5.4+
Suggested-by: Omar Sandoval <osandov@osandov.com>
Signed-off-by: Boris Burkov <boris@bur.io>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 9 insertions, 7 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 411ec3e3a7dc..9ac40991a640 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1578,7 +1578,7 @@ next_slot:
 				goto out_check;
 			ret = btrfs_cross_ref_exist(root, ino,
 						    found_key.offset -
-						    extent_offset, disk_bytenr);
+						    extent_offset, disk_bytenr, false);
 			if (ret) {
 				/*
 				 * ret could be -EIO if the above fails to read
@@ -7529,7 +7529,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
  */
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
-			      u64 *ram_bytes)
+			      u64 *ram_bytes, bool strict)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_path *path;
@@ -7607,8 +7607,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	 * Do the same check as in btrfs_cross_ref_exist but without the
 	 * unnecessary search.
 	 */
-	if (btrfs_file_extent_generation(leaf, fi) <=
-	    btrfs_root_last_snapshot(&root->root_item))
+	if (!strict &&
+	    (btrfs_file_extent_generation(leaf, fi) <=
+	     btrfs_root_last_snapshot(&root->root_item)))
 		goto out;
 
 	backref_offset = btrfs_file_extent_offset(leaf, fi);
@@ -7644,7 +7645,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	 */
 
 	ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)),
-				    key.offset - backref_offset, disk_bytenr);
+				    key.offset - backref_offset, disk_bytenr,
+				    strict);
 	if (ret) {
 		ret = 0;
 		goto out;
@@ -7865,7 +7867,7 @@ static int btrfs_get_blocks_direct_write(struct extent_map **map,
 		block_start = em->block_start + (start - em->start);
 
 		if (can_nocow_extent(inode, start, &len, &orig_start,
-				     &orig_block_len, &ram_bytes) == 1 &&
+				     &orig_block_len, &ram_bytes, false) == 1 &&
 		    btrfs_inc_nocow_writers(fs_info, block_start)) {
 			struct extent_map *em2;
 
@@ -11030,7 +11032,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 		free_extent_map(em);
 		em = NULL;
 
-		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL);
+		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, true);
 		if (ret < 0) {
 			goto out;
 		} else if (ret) {