xfs: take the ILOCK when readdir inspects directory mapping data

I was poking around in the directory code while diagnosing online fsck
bugs, and noticed that xfs_readdir doesn't actually take the directory
ILOCK when it calls xfs_dir2_isblock.  xfs_dir_open most probably loaded
the data fork mappings and the VFS took i_rwsem (aka IOLOCK_SHARED) so
we're protected against writer threads, but we really need to follow the
locking model like we do in other places.

To avoid unnecessarily cycling the ILOCK for fairly small directories,
change the block/leaf _getdents functions to consume the ILOCK hold that
the parent readdir function took to decide on a _getdents implementation.

It is ok to cycle the ILOCK in readdir because the VFS takes the IOLOCK
in the appropriate mode during lookups and writes, and we don't want to
be holding the ILOCK when we copy directory entries to userspace in case
there's a page fault.  We really only need it to protect against data
fork lookups, like we do for other files.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>

Author: Darrick J. Wong

fs/xfs/xfs_dir2_readdir.c

@@ -138,15 +138,15 @@ xfs_dir2_sf_getdents(
 STATIC int
 xfs_dir2_block_getdents(
 	struct xfs_da_args	*args,
-	struct dir_context	*ctx)
+	struct dir_context	*ctx,
+	unsigned int		*lock_mode)
 {
 	struct xfs_inode	*dp = args->dp;	/* incore directory inode */
 	struct xfs_buf		*bp;		/* buffer for block */
 	int			error;		/* error return value */
 	int			wantoff;	/* starting block offset */
 	xfs_off_t		cook;
 	struct xfs_da_geometry	*geo = args->geo;
-	int			lock_mode;
 	unsigned int		offset, next_offset;
 	unsigned int		end;
 
@@ -156,12 +156,13 @@ xfs_dir2_block_getdents(
 	if (xfs_dir2_dataptr_to_db(geo, ctx->pos) > geo->datablk)
 		return 0;
 
-	lock_mode = xfs_ilock_data_map_shared(dp);
 	error = xfs_dir3_block_read(args->trans, dp, &bp);
-	xfs_iunlock(dp, lock_mode);
 	if (error)
 		return error;
 
+	xfs_iunlock(dp, *lock_mode);
+	*lock_mode = 0;
+
 	/*
 	 * Extract the byte offset we start at from the seek pointer.
 	 * We'll skip entries before this.
@@ -344,7 +345,8 @@ STATIC int
 xfs_dir2_leaf_getdents(
 	struct xfs_da_args	*args,
 	struct dir_context	*ctx,
-	size_t			bufsize)
+	size_t			bufsize,
+	unsigned int		*lock_mode)
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_mount	*mp = dp->i_mount;
@@ -356,7 +358,6 @@ xfs_dir2_leaf_getdents(
 	xfs_dir2_off_t		curoff;		/* current overall offset */
 	int			length;		/* temporary length value */
 	int			byteoff;	/* offset in current block */
-	int			lock_mode;
 	unsigned int		offset = 0;
 	int			error = 0;	/* error return value */
 
@@ -390,13 +391,16 @@ xfs_dir2_leaf_getdents(
 				bp = NULL;
 			}
 
-			lock_mode = xfs_ilock_data_map_shared(dp);
+			if (*lock_mode == 0)
+				*lock_mode = xfs_ilock_data_map_shared(dp);
 			error = xfs_dir2_leaf_readbuf(args, bufsize, &curoff,
 					&rablk, &bp);
-			xfs_iunlock(dp, lock_mode);
 			if (error || !bp)
 				break;
 
+			xfs_iunlock(dp, *lock_mode);
+			*lock_mode = 0;
+
 			xfs_dir3_data_check(dp, bp);
 			/*
 			 * Find our position in the block.
@@ -496,7 +500,7 @@ xfs_dir2_leaf_getdents(
  *
  * If supplied, the transaction collects locked dir buffers to avoid
  * nested buffer deadlocks.  This function does not dirty the
- * transaction.  The caller should ensure that the inode is locked
+ * transaction.  The caller must hold the IOLOCK (shared or exclusive)
  * before calling this function.
  */
 int
@@ -507,29 +511,40 @@ xfs_readdir(
 	size_t			bufsize)
 {
 	struct xfs_da_args	args = { NULL };
-	int			rval;
-	int			v;
+	unsigned int		lock_mode;
+	int			isblock;
+	int			error;
 
 	trace_xfs_readdir(dp);
 
 	if (xfs_is_shutdown(dp->i_mount))
 		return -EIO;
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	ASSERT(xfs_isilocked(dp, XFS_IOLOCK_SHARED | XFS_IOLOCK_EXCL));
 	XFS_STATS_INC(dp->i_mount, xs_dir_getdents);
 
 	args.dp = dp;
 	args.geo = dp->i_mount->m_dir_geo;
 	args.trans = tp;
 
 	if (dp->i_df.if_format == XFS_DINODE_FMT_LOCAL)
-		rval = xfs_dir2_sf_getdents(&args, ctx);
-	else if ((rval = xfs_dir2_isblock(&args, &v)))
-		;
-	else if (v)
-		rval = xfs_dir2_block_getdents(&args, ctx);
-	else
-		rval = xfs_dir2_leaf_getdents(&args, ctx, bufsize);
+		return xfs_dir2_sf_getdents(&args, ctx);
 
-	return rval;
+	lock_mode = xfs_ilock_data_map_shared(dp);
+	error = xfs_dir2_isblock(&args, &isblock);
+	if (error)
+		goto out_unlock;
+
+	if (isblock) {
+		error = xfs_dir2_block_getdents(&args, ctx, &lock_mode);
+		goto out_unlock;
+	}
+
+	error = xfs_dir2_leaf_getdents(&args, ctx, bufsize, &lock_mode);
+
+out_unlock:
+	if (lock_mode)
+		xfs_iunlock(dp, lock_mode);
+	return error;
 }