xfs: allow linkat() on O_TMPFILE files

The VFS allows an anonymous temporary file to be named at a later
time via a linkat() syscall. The inodes for O_TMPFILE files are
are marked with a special flag I_LINKABLE and have a zero link count.

To support this in XFS, xfs_link() detects if this flag I_LINKABLE
is set and behaves appropriately when detected. So in this case,
its transaciton reservation takes into account the additional
overhead of removing the inode from the unlinked list. Then the
inode is removed from the unlinked list and the directory entry
is added. Finally its link count is bumped accordingly.

Signed-off-by: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de> 
Signed-off-by: Ben Myers <bpm@sgi.com>

2 files changed, 26 insertions, 3 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ac133ea91c4b..b08b5a84cf0a 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -61,6 +61,8 @@ kmem_zone_t *xfs_inode_zone;
 
 STATIC int xfs_iflush_int(xfs_inode_t *, xfs_buf_t *);
 
+STATIC int xfs_iunlink_remove(xfs_trans_t *, xfs_inode_t *);
+
 /*
  * helper function to extract extent size hint from inode
  */
@@ -1118,7 +1120,7 @@ xfs_bumplink(
 {
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	ASSERT(ip->i_d.di_nlink > 0);
+	ASSERT(ip->i_d.di_nlink > 0 || (VFS_I(ip)->i_state & I_LINKABLE));
 	ip->i_d.di_nlink++;
 	inc_nlink(VFS_I(ip));
 	if ((ip->i_d.di_version == 1) &&
@@ -1504,6 +1506,12 @@ xfs_link(
 
 	xfs_bmap_init(&free_list, &first_block);
 
+	if (sip->i_d.di_nlink == 0) {
+		error = xfs_iunlink_remove(tp, sip);
+		if (error)
+			goto abort_return;
+	}
+
 	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
 					&first_block, &free_list, resblks);
 	if (error)
diff --git a/fs/xfs/xfs_trans_resv.c b/fs/xfs/xfs_trans_resv.c
index bd3b4b7831b7..76f9a02bc36b 100644
--- a/fs/xfs/xfs_trans_resv.c
+++ b/fs/xfs/xfs_trans_resv.c
@@ -204,6 +204,20 @@ xfs_calc_rename_reservation(
 }
 
 /*
+ * For removing an inode from unlinked list at first, we can modify:
+ *    the agi hash list and counters: sector size
+ *    the on disk inode before ours in the agi hash list: inode cluster size
+ */
+STATIC uint
+xfs_calc_iunlink_remove_reservation(
+	struct xfs_mount        *mp)
+{
+	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+		MAX((__uint16_t)XFS_FSB_TO_B(mp, 1),
+			(__uint16_t)XFS_INODE_CLUSTER_SIZE(mp));
+}
+
+/*
  * For creating a link to an inode:
  *    the parent directory inode: inode size
  *    the linked inode: inode size
@@ -220,6 +234,7 @@ xfs_calc_link_reservation(
 	struct xfs_mount	*mp)
 {
 	return XFS_DQUOT_LOGRES(mp) +
+		xfs_calc_iunlink_remove_reservation(mp) +
 		MAX((xfs_calc_inode_res(mp, 2) +
 		     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
 				      XFS_FSB_TO_B(mp, 1))),
@@ -410,9 +425,9 @@ xfs_calc_ifree_reservation(
 {
 	return XFS_DQUOT_LOGRES(mp) +
 		xfs_calc_inode_res(mp, 1) +
-		xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
 		xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
-		max_t(uint, XFS_FSB_TO_B(mp, 1), XFS_INODE_CLUSTER_SIZE(mp)) +
+		xfs_calc_iunlink_remove_reservation(mp) +
 		xfs_calc_buf_res(1, 0) +
 		xfs_calc_buf_res(2 + XFS_IALLOC_BLOCKS(mp) +
 				 mp->m_in_maxlevels, 0) +