Searched hist:"66 da0e1f" (Results 1 – 1 of 1) sorted by relevance
/openbmc/linux/fs/devpts/ |
H A D | inode.c | 66da0e1f Tue Nov 12 17:11:45 CST 2013 Ilija Hadzic <ihadzic@research.bell-labs.com> devpts: plug the memory leak in kill_sb
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@research.bell-labs.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> 66da0e1f Tue Nov 12 17:11:45 CST 2013 Ilija Hadzic <ihadzic@research.bell-labs.com> devpts: plug the memory leak in kill_sb 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@research.bell-labs.com> Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
|