[PATCH 3.5 68/78] devpts: plug the memory leak in kill_sb

[Luis Henriques]

3.5.7.26 -stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ilija Hadzic <ihadzic at research.bell-labs.com>

commit 66da0e1f9034140ae2f571ef96e254a25083906c upstream.

When devpts is unmounted, there may be a no-longer-used IDR tree hanging
off the superblock we are about to kill.  This needs to be cleaned up
before destroying the SB.

The leak is usually not a big deal because unmounting devpts is typically
done when shutting down the whole machine.  However, shutting down an LXC
container instead of a physical machine exposes the problem (the garbage
is detectable with kmemleak).

Signed-off-by: Ilija Hadzic <ihadzic at research.bell-labs.com>
Cc: Sukadev Bhattiprolu <sukadev at linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
Signed-off-by: Luis Henriques <luis.henriques at canonical.com>
---
 fs/devpts/inode.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 979c1e3..1ed9d5e 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -483,6 +483,7 @@ static void devpts_kill_sb(struct super_block *sb)
 {
 	struct pts_fs_info *fsi = DEVPTS_SB(sb);
 
+	ida_destroy(&fsi->allocated_ptys);
 	kfree(fsi);
 	kill_litter_super(sb);
 }
-- 
1.8.3.2