xfs: fix locking for inode cache radix tree tag updates

The radix-tree code requires it's users to serialize tag updates
against other updates to the tree.  While XFS protects tag updates
against each other it does not serialize them against updates of the
tree contents, which can lead to tag corruption.  Fix the inode
cache to always take pag_ici_lock in exclusive mode when updating
radix tree tags.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Patrick Schreurs <patrick@news-service.com>
Tested-by: Patrick Schreurs <patrick@news-service.com>
Signed-off-by: Alex Elder <aelder@sgi.com>

2 files changed, 15 insertions, 8 deletions

diff --git a/fs/xfs/linux-2.6/xfs_sync.c b/fs/xfs/linux-2.6/xfs_sync.c
index a9f6d20aff41..f9fc154d9f72 100644
--- a/fs/xfs/linux-2.6/xfs_sync.c
+++ b/fs/xfs/linux-2.6/xfs_sync.c
@@ -688,12 +688,12 @@ xfs_inode_set_reclaim_tag(
         struct xfs_perag *pag;
 
         pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
-        read_lock(&pag->pag_ici_lock);
+        write_lock(&pag->pag_ici_lock);
         spin_lock(&ip->i_flags_lock);
         __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);
+        write_unlock(&pag->pag_ici_lock);
         xfs_perag_put(pag);
 }
 
diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index e281eb4a1c49..6845db90818f 100644
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -190,13 +190,12 @@ xfs_iget_cache_hit(
                 trace_xfs_iget_reclaim(ip);
 
                 /*
-                 * We need to set XFS_INEW atomically with clearing the
-                 * reclaimable tag so that we do have an indicator of the
-                 * inode still being initialized.
+                 * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
+                 * from stomping over us while we recycle the inode.  We can't
+                 * clear the radix tree reclaimable tag yet as it requires
+                 * pag_ici_lock to be held exclusive.
                  */
-                ip->i_flags |= XFS_INEW;
-                ip->i_flags &= ~XFS_IRECLAIMABLE;
-                __xfs_inode_clear_reclaim_tag(mp, pag, ip);
+                ip->i_flags |= XFS_IRECLAIM;
 
                 spin_unlock(&ip->i_flags_lock);
                 read_unlock(&pag->pag_ici_lock);
@@ -216,7 +215,15 @@ xfs_iget_cache_hit(
                         trace_xfs_iget_reclaim(ip);
                         goto out_error;
                 }
+
+                write_lock(&pag->pag_ici_lock);
+                spin_lock(&ip->i_flags_lock);
+                ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM);
+                ip->i_flags |= XFS_INEW;
+                __xfs_inode_clear_reclaim_tag(mp, pag, ip);
                 inode->i_state = I_NEW;
+                spin_unlock(&ip->i_flags_lock);
+                write_unlock(&pag->pag_ici_lock);
         } else {
                 /* If the VFS inode is being torn down, pause and try again. */
                 if (!igrab(inode)) {