xfs: don't start out with the exclusive ilock for direct I/O

Christoph Hellwig · djwong · commit af5b5afe9ac6 · 2018-03-01T14:12:12.000-08:00
There is no reason to take the ilock exclusively at the start of
xfs_file_iomap_begin for direct I/O, given that it will be demoted
just before calling xfs_iomap_write_direct anyway.

Signed-off-by: Christoph Hellwig &lt;hch@lst.de&gt;
Reviewed-by: Dave Chinner &lt;dchinner@redhat.com&gt;
Reviewed-by: Darrick J. Wong &lt;darrick.wong@oracle.com&gt;
Signed-off-by: Darrick J. Wong &lt;darrick.wong@oracle.com&gt;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
@@ -965,13 +965,11 @@ static inline bool needs_cow_for_zeroing(struct xfs_bmbt_irec *imap, int nimaps)
 static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
 {
 	/*
-	 * COW writes will allocate delalloc space, so we need to make sure
-	 * to take the lock exclusively here.
+	 * COW writes may allocate delalloc space or convert unwritten COW
+	 * extents, so we need to make sure to take the lock exclusively here.
 	 */
 	if (xfs_is_reflink_inode(ip) && (flags & (IOMAP_WRITE | IOMAP_ZERO)))
 		return true;
-	if ((flags & IOMAP_DIRECT) && (flags & IOMAP_WRITE))
-		return true;
 	return false;
 }
 
