xfs: fix inode lookup race

[firefly-linux-kernel-4.4.55.git] / fs / xfs / xfs_iget.c

diff --git a/fs/xfs/xfs_iget.c b/fs/xfs/xfs_iget.c
index cb9b6d1469f7579256061f6de61755c0d6b63df6..ca752f05c31c498b8ef6b1fc29c6e4ebe2ea6a33 100644 (file)
--- a/fs/xfs/xfs_iget.c
+++ b/fs/xfs/xfs_iget.c
@@ -253,16 +253,21 @@ xfs_iget_cache_hit(
                        rcu_read_lock();
                        spin_lock(&ip->i_flags_lock);
 
-                       ip->i_flags &= ~XFS_INEW;
-                       ip->i_flags |= XFS_IRECLAIMABLE;
-                       __xfs_inode_set_reclaim_tag(pag, ip);
+                       ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+                       ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
                        trace_xfs_iget_reclaim_fail(ip);
                        goto out_error;
                }
 
                spin_lock(&pag->pag_ici_lock);
                spin_lock(&ip->i_flags_lock);
-               ip->i_flags &= ~(XFS_IRECLAIMABLE | XFS_IRECLAIM);
+
+               /*
+                * Clear the per-lifetime state in the inode as we are now
+                * effectively a new inode and need to return to the initial
+                * state before reuse occurs.
+                */
+               ip->i_flags &= ~XFS_IRECLAIM_RESET_FLAGS;
                ip->i_flags |= XFS_INEW;
                __xfs_inode_clear_reclaim_tag(mp, pag, ip);
                inode->i_state = I_NEW;
@@ -351,9 +356,20 @@ xfs_iget_cache_miss(
                        BUG();
        }
 
-       spin_lock(&pag->pag_ici_lock);
+       /*
+        * These values must be set before inserting the inode into the radix
+        * tree as the moment it is inserted a concurrent lookup (allowed by the
+        * RCU locking mechanism) can find it and that lookup must see that this
+        * is an inode currently under construction (i.e. that XFS_INEW is set).
+        * The ip->i_flags_lock that protects the XFS_INEW flag forms the
+        * memory barrier that ensures this detection works correctly at lookup
+        * time.
+        */
+       ip->i_udquot = ip->i_gdquot = NULL;
+       xfs_iflags_set(ip, XFS_INEW);
 
        /* insert the new inode */
+       spin_lock(&pag->pag_ici_lock);
        error = radix_tree_insert(&pag->pag_ici_root, agino, ip);
        if (unlikely(error)) {
                WARN_ON(error != -EEXIST);
@@ -361,11 +377,6 @@ xfs_iget_cache_miss(
                error = EAGAIN;
                goto out_preload_end;
        }
-
-       /* These values _must_ be set before releasing the radix tree lock! */
-       ip->i_udquot = ip->i_gdquot = NULL;
-       xfs_iflags_set(ip, XFS_INEW);
-
        spin_unlock(&pag->pag_ici_lock);
        radix_tree_preload_end();