x86_64: During VM oom condition, kill all threads in process group
authorWill Schmidt <will_schmidt@vnet.ibm.com>
Sat, 21 Jul 2007 15:11:17 +0000 (17:11 +0200)
committerLinus Torvalds <torvalds@woody.linux-foundation.org>
Sun, 22 Jul 2007 01:37:12 +0000 (18:37 -0700)
commit021daae2c265a844fd27bb6cc49c2bd114571069
treeaa97071978b3660b47792073d4342648021cf115
parent99253b8e734a7a773c0e4bedd7d8d1847c98c538
x86_64: During VM oom condition, kill all threads in process group

During a VM oom condition, kill all threads in the process group.

We have had complaints where a threaded application is left in a bad state
after one of it's threads is killed when we hit a VM: out_of_memory condition.

Killing just one of the process threads can leave the application in a bad
state, whereas killing the entire process group would allow for the
application to restart, or otherwise handled, and makes it very obvious that
something has gone wrong.

This change allows the entire process group to be taken down, rather than just
the one thread.

Signed-off-by: Will <will_schmidt@vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
arch/x86_64/mm/fault.c