1 files changed, 28 insertions, 10 deletions

diff --git a/fs/btrfs/direct-io.c b/fs/btrfs/direct-io.c
index f9fb2db6a1e4..67adbe9d294a 100644
--- a/fs/btrfs/direct-io.c
+++ b/fs/btrfs/direct-io.c
@@ -856,21 +856,37 @@ relock:
 	 * So here we disable page faults in the iov_iter and then retry if we
 	 * got -EFAULT, faulting in the pages before the retry.
 	 */
+again:
 	from->nofault = true;
 	dio = btrfs_dio_write(iocb, from, written);
 	from->nofault = false;
 
-	/*
-	 * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync
-	 * iocb, and that needs to lock the inode. So unlock it before calling
-	 * iomap_dio_complete() to avoid a deadlock.
-	 */
-	btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
-
-	if (IS_ERR_OR_NULL(dio))
+	if (IS_ERR_OR_NULL(dio)) {
 		ret = PTR_ERR_OR_ZERO(dio);
-	else
+	} else {
+		struct btrfs_file_private stack_private = { 0 };
+		struct btrfs_file_private *private;
+		const bool have_private = (file->private_data != NULL);
+
+		if (!have_private)
+			file->private_data = &stack_private;
+
+		/*
+		 * If we have a synchronous write, we must make sure the fsync
+		 * triggered by the iomap_dio_complete() call below doesn't
+		 * deadlock on the inode lock - we are already holding it and we
+		 * can't call it after unlocking because we may need to complete
+		 * partial writes due to the input buffer (or parts of it) not
+		 * being already faulted in.
+		 */
+		private = file->private_data;
+		private->fsync_skip_inode_lock = true;
 		ret = iomap_dio_complete(dio);
+		private->fsync_skip_inode_lock = false;
+
+		if (!have_private)
+			file->private_data = NULL;
+	}
 
 	/* No increment (+=) because iomap returns a cumulative value. */
 	if (ret > 0)
@@ -897,10 +913,12 @@ relock:
 		} else {
 			fault_in_iov_iter_readable(from, left);
 			prev_left = left;
-			goto relock;
+			goto again;
 		}
 	}
 
+	btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
+
 	/*
 	 * If 'ret' is -ENOTBLK or we have not written all data, then it means
 	 * we must fallback to buffered IO.