Merge branch 'xfs-misc-fixes-3.17-2' into for-next

1 files changed, 48 insertions, 52 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d32889af1777..2f1e30d39a35 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -809,7 +809,7 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 	 * have speculative prealloc/delalloc blocks to remove.
 	 */
 	if (VFS_I(ip)->i_size == 0 &&
-	    VN_CACHED(VFS_I(ip)) == 0 &&
+	    VFS_I(ip)->i_mapping->nrpages == 0 &&
 	    ip->i_delayed_blks == 0)
 		return false;
 
@@ -1619,6 +1619,30 @@ xfs_swap_extents_check_format(
 }
 
 int
+xfs_swap_extent_flush(
+	struct xfs_inode	*ip)
+{
+	int	error;
+
+	error = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+	if (error)
+		return error;
+	truncate_pagecache_range(VFS_I(ip), 0, -1);
+
+	/* Verify O_DIRECT for ftmp */
+	if (VFS_I(ip)->i_mapping->nrpages)
+		return -EINVAL;
+
+	/*
+	 * Don't try to swap extents on mmap()d files because we can't lock
+	 * out races against page faults safely.
+	 */
+	if (mapping_mapped(VFS_I(ip)->i_mapping))
+		return -EBUSY;
+	return 0;
+}
+
+int
 xfs_swap_extents(
 	xfs_inode_t	*ip,	/* target inode */
 	xfs_inode_t	*tip,	/* tmp inode */
@@ -1633,6 +1657,7 @@ xfs_swap_extents(
 	int		aforkblks = 0;
 	int		taforkblks = 0;
 	__uint64_t	tmp;
+	int		lock_flags;
 
 	tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
 	if (!tempifp) {
@@ -1641,13 +1666,13 @@ xfs_swap_extents(
 	}
 
 	/*
-	 * we have to do two separate lock calls here to keep lockdep
-	 * happy. If we try to get all the locks in one call, lock will
-	 * report false positives when we drop the ILOCK and regain them
-	 * below.
+	 * Lock up the inodes against other IO and truncate to begin with.
+	 * Then we can ensure the inodes are flushed and have no page cache
+	 * safely. Once we have done this we can take the ilocks and do the rest
+	 * of the checks.
 	 */
+	lock_flags = XFS_IOLOCK_EXCL;
 	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
-	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
 
 	/* Verify that both files have the same format */
 	if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
@@ -1661,23 +1686,28 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
-	error = filemap_write_and_wait(VFS_I(tip)->i_mapping);
+	error = xfs_swap_extent_flush(ip);
+	if (error)
+		goto out_unlock;
+	error = xfs_swap_extent_flush(tip);
 	if (error)
 		goto out_unlock;
-	truncate_pagecache_range(VFS_I(tip), 0, -1);
 
-	/* Verify O_DIRECT for ftmp */
-	if (VN_CACHED(VFS_I(tip)) != 0) {
-		error = -EINVAL;
+	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
+	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
 		goto out_unlock;
 	}
+	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
+	lock_flags |= XFS_ILOCK_EXCL;
 
 	/* Verify all data are being swapped */
 	if (sxp->sx_offset != 0 ||
 	    sxp->sx_length != ip->i_d.di_size ||
 	    sxp->sx_length != tip->i_d.di_size) {
 		error = -EFAULT;
-		goto out_unlock;
+		goto out_trans_cancel;
 	}
 
 	trace_xfs_swap_extent_before(ip, 0);
@@ -1689,7 +1719,7 @@ xfs_swap_extents(
 		xfs_notice(mp,
 		    "%s: inode 0x%llx format is incompatible for exchanging.",
 				__func__, ip->i_ino);
-		goto out_unlock;
+		goto out_trans_cancel;
 	}
 
 	/*
@@ -1704,42 +1734,8 @@ xfs_swap_extents(
 	    (sbp->bs_mtime.tv_sec != VFS_I(ip)->i_mtime.tv_sec) ||
 	    (sbp->bs_mtime.tv_nsec != VFS_I(ip)->i_mtime.tv_nsec)) {
 		error = -EBUSY;
-		goto out_unlock;
-	}
-
-	/* We need to fail if the file is memory mapped.  Once we have tossed
-	 * all existing pages, the page fault will have no option
-	 * but to go to the filesystem for pages. By making the page fault call
-	 * vop_read (or write in the case of autogrow) they block on the iolock
-	 * until we have switched the extents.
-	 */
-	if (VN_MAPPED(VFS_I(ip))) {
-		error = -EBUSY;
-		goto out_unlock;
-	}
-
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	xfs_iunlock(tip, XFS_ILOCK_EXCL);
-
-	/*
-	 * There is a race condition here since we gave up the
-	 * ilock.  However, the data fork will not change since
-	 * we have the iolock (locked for truncation too) so we
-	 * are safe.  We don't really care if non-io related
-	 * fields change.
-	 */
-	truncate_pagecache_range(VFS_I(ip), 0, -1);
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
-	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
-	if (error) {
-		xfs_iunlock(ip,  XFS_IOLOCK_EXCL);
-		xfs_iunlock(tip, XFS_IOLOCK_EXCL);
-		xfs_trans_cancel(tp, 0);
-		goto out;
+		goto out_trans_cancel;
 	}
-	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
-
 	/*
 	 * Count the number of extended attribute blocks
 	 */
@@ -1757,8 +1753,8 @@ xfs_swap_extents(
 			goto out_trans_cancel;
 	}
 
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-	xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, lock_flags);
+	xfs_trans_ijoin(tp, tip, lock_flags);
 
 	/*
 	 * Before we've swapped the forks, lets set the owners of the forks
@@ -1887,8 +1883,8 @@ out:
 	return error;
 
 out_unlock:
-	xfs_iunlock(ip,  XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
-	xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	xfs_iunlock(ip, lock_flags);
+	xfs_iunlock(tip, lock_flags);
 	goto out;
 
 out_trans_cancel: