[PATCH] fix for prune_icache()/forced final iput() races

Based on analysis and a patch from Russ Weight <rweight@us.ibm.com>

There is a race condition that can occur if an inode is allocated and then
released (using iput) during the ->fill_super functions.  The race
condition is between kswapd and mount.

For most filesystems this can only happen in an error path when kswapd is
running concurrently.  For isofs, however, the error can occur in a more
common code path (which is how the bug was found).

The logic here is "we want final iput() to free inode *now* instead of
letting it sit in cache if fs is going down or had not quite come up".  The
problem is with kswapd seeing such inodes in the middle of being killed and
happily taking over.

The clean solution would be to tell kswapd to leave those inodes alone and
let our final iput deal with them.  I.e.  add a new flag
(I_FORCED_FREEING), set it before write_inode_now() there and make
prune_icache() leave those alone.

Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 11 insertions, 6 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 801fe7f36280..1f9a3a2b89bc 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -500,7 +500,7 @@ repeat:
                         continue;
                 if (!test(inode, data))
                         continue;
-                if (inode->i_state & (I_FREEING|I_CLEAR)) {
+                if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
                         __wait_on_freeing_inode(inode);
                         goto repeat;
                 }
@@ -525,7 +525,7 @@ repeat:
                         continue;
                 if (inode->i_sb != sb)
                         continue;
-                if (inode->i_state & (I_FREEING|I_CLEAR)) {
+                if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
                         __wait_on_freeing_inode(inode);
                         goto repeat;
                 }
@@ -727,7 +727,7 @@ EXPORT_SYMBOL(iunique);
 struct inode *igrab(struct inode *inode)
 {
         spin_lock(&inode_lock);
-        if (!(inode->i_state & I_FREEING))
+        if (!(inode->i_state & (I_FREEING|I_WILL_FREE)))
                 __iget(inode);
         else
                 /*
@@ -1024,17 +1024,21 @@ static void generic_forget_inode(struct inode *inode)
                 if (!(inode->i_state & (I_DIRTY|I_LOCK)))
                         list_move(&inode->i_list, &inode_unused);
                 inodes_stat.nr_unused++;
-                spin_unlock(&inode_lock);
-                if (!sb || (sb->s_flags & MS_ACTIVE))
+                if (!sb || (sb->s_flags & MS_ACTIVE)) {
+                        spin_unlock(&inode_lock);
                         return;
+                }
+                inode->i_state |= I_WILL_FREE;
+                spin_unlock(&inode_lock);
                 write_inode_now(inode, 1);
                 spin_lock(&inode_lock);
+                inode->i_state &= ~I_WILL_FREE;
                 inodes_stat.nr_unused--;
                 hlist_del_init(&inode->i_hash);
         }
         list_del_init(&inode->i_list);
         list_del_init(&inode->i_sb_list);
-        inode->i_state|=I_FREEING;
+        inode->i_state |= I_FREEING;
         inodes_stat.nr_inodes--;
         spin_unlock(&inode_lock);
         if (inode->i_data.nrpages)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e5a8db00df29..3622e952e98c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1025,6 +1025,7 @@ struct super_operations {
 #define I_FREEING               16
 #define I_CLEAR                 32
 #define I_NEW                   64
+#define I_WILL_FREE             128
 
 #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES)