xfs: fix locking in xfs_iget_cache_hit

The locking in xfs_iget_cache_hit currently has numerous problems:

 - we clear the reclaim tag without i_flags_lock which protects
   modifications to it
 - we call inode_init_always which can sleep with pag_ici_lock
   held (this is oss.sgi.com BZ #819)
 - we acquire and drop i_flags_lock a lot and thus provide no
   consistency between the various flags we set/clear under it

This patch fixes all that with a major revamp of the locking in
the function.  The new version acquires i_flags_lock early and
only drops it once we need to call into inode_init_always or before
calling xfs_ilock.

This patch fixes a bug seen in the wild where we race modifying the
reclaim tag.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Felix Blyakher <felixb@sgi.com>
Reviewed-by: Eric Sandeen <sandeen@sandeen.net>
Signed-off-by: Felix Blyakher <felixb@sgi.com>

2 files changed, 12 insertions, 2 deletions

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index b619d6b8ca43..98ef624d9baf 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -708,6 +708,16 @@ xfs_reclaim_inode(
         return 0;
 }
 
+void
+__xfs_inode_set_reclaim_tag(
+        struct xfs_perag        *pag,
+        struct xfs_inode        *ip)
+{
+        radix_tree_tag_set(&pag->pag_ici_root,
+                           XFS_INO_TO_AGINO(ip->i_mount, ip->i_ino),
+                           XFS_ICI_RECLAIM_TAG);
+}
+
 /*
  * We set the inode flag atomically with the radix tree tag.
  * Once we get tag lookups on the radix tree, this inode flag
@@ -722,8 +732,7 @@ xfs_inode_set_reclaim_tag(
 
         read_lock(&pag->pag_ici_lock);
         spin_lock(&ip->i_flags_lock);
-        radix_tree_tag_set(&pag->pag_ici_root,
-                        XFS_INO_TO_AGINO(mp, ip->i_ino), XFS_ICI_RECLAIM_TAG);
+        __xfs_inode_set_reclaim_tag(pag, ip);
         __xfs_iflags_set(ip, XFS_IRECLAIMABLE);
         spin_unlock(&ip->i_flags_lock);
         read_unlock(&pag->pag_ici_lock);
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 2a10301c99c7..59120602588a 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -48,6 +48,7 @@ int xfs_reclaim_inode(struct xfs_inode *ip, int locked, int sync_mode);
 int xfs_reclaim_inodes(struct xfs_mount *mp, int mode);
 
 void xfs_inode_set_reclaim_tag(struct xfs_inode *ip);
+void __xfs_inode_set_reclaim_tag(struct xfs_perag *pag, struct xfs_inode *ip);
 void xfs_inode_clear_reclaim_tag(struct xfs_inode *ip);
 void __xfs_inode_clear_reclaim_tag(struct xfs_mount *mp, struct xfs_perag *pag,
                                 struct xfs_inode *ip);