btrfs: unlock locked extent area if we have contention

In production we hit the following deadlock

task 1			task 2			task 3
------			------			------
fiemap(file)		falloc(file)		fsync(file)
						  write(0, 1MiB)
						  btrfs_commit_transaction()
						    wait_on(!pending_ordered)
			  lock(512MiB, 1GiB)
			  start_transaction
			    wait_on_transaction

  lock(0, 1GiB)
    wait_extent_bit(512MiB)

task 4
------
finish_ordered_extent(0, 1MiB)
  lock(0, 1MiB)
  **DEADLOCK**

This occurs because when task 1 does it's lock, it locks everything from
0-512MiB, and then waits for the 512MiB chunk to unlock.  task 2 will
never unlock because it's waiting on the transaction commit to happen,
the transaction commit is waiting for the outstanding ordered extents,
and then the ordered extent thread is blocked waiting on the 0-1MiB
range to unlock.

To fix this we have to clear anything we've locked so far, wait for the
extent_state that we contended on, and then try to re-lock the entire
range again.

CC: stable@vger.kernel.org # 5.15+
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/extent-io-tree.c b/fs/btrfs/extent-io-tree.c
index 618275af19c49da1a75f8b7ca3e08405ec19fe23..83cb0378096f209ae6b0c05896359575103eb4b3 100644 (file)
--- a/fs/btrfs/extent-io-tree.c
+++ b/fs/btrfs/extent-io-tree.c
@@ -1641,16 +1641,17 @@ int lock_extent(struct extent_io_tree *tree, u64 start, u64 end,
        int err;
        u64 failed_start;
 
-       while (1) {
+       err = __set_extent_bit(tree, start, end, EXTENT_LOCKED, &failed_start,
+                              cached_state, NULL, GFP_NOFS);
+       while (err == -EEXIST) {
+               if (failed_start != start)
+                       clear_extent_bit(tree, start, failed_start - 1,
+                                        EXTENT_LOCKED, cached_state);
+
+               wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED);
                err = __set_extent_bit(tree, start, end, EXTENT_LOCKED,
                                       &failed_start, cached_state, NULL,
                                       GFP_NOFS);
-               if (err == -EEXIST) {
-                       wait_extent_bit(tree, failed_start, end, EXTENT_LOCKED);
-                       start = failed_start;
-               } else
-                       break;
-               WARN_ON(start > end);
        }
        return err;
 }