memcg: fix oom killing a child process in an other cgroup

Presently the oom-killer is memcg aware and it finds the worst process
from processes under memcg(s) in oom.  Then, it kills victim's child
first.

It may kill a child in another cgroup and may not be any help for
recovery.  And it will break the assumption users have.

This patch fixes it.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Balbir Singh <balbir@linux.vnet.ibm.com>
Reviewed-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: David Rientjes <rientjes@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/oom_kill.c

@@ -459,6 +459,8 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	list_for_each_entry(c, &p->children, sibling) {
 		if (c->mm == p->mm)
 			continue;
+		if (mem && !task_in_mem_cgroup(c, mem))
+			continue;
 		if (!oom_kill_task(c))
 			return 0;
 	}