memcg: avoid oom-killing innocent task in case of use_hierarchy

commit d31f56dbf8bafaacb0c617f9a6f137498d5c7aed upstream.

task_in_mem_cgroup(), which is called by select_bad_process() to check
whether a task can be a candidate for being oom-killed from memcg's limit,
checks "curr->use_hierarchy"("curr" is the mem_cgroup the task belongs
to).

But this check return true(it's false positive) when:

	<some path>/aa		use_hierarchy == 0	<- hitting limit
	  <some path>/aa/00	use_hierarchy == 1	<- the task belongs to

This leads to killing an innocent task in aa/00.  This patch is a fix for
this bug.  And this patch also fixes the arg for
mem_cgroup_print_oom_info().  We should print information of mem_cgroup
which the task being killed, not current, belongs to.

Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 63140151b61861104c0cf9a40c3e085b22b08195..5dc10374d7692ec2a2c409639ff107c8c0c59ded 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -758,7 +758,13 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
        task_unlock(task);
        if (!curr)
                return 0;
-       if (curr->use_hierarchy)
+       /*
+        * We should check use_hierarchy of "mem" not "curr". Because checking
+        * use_hierarchy of "curr" here make this function true if hierarchy is
+        * enabled in "curr" and "curr" is a child of "mem" in *cgroup*
+        * hierarchy(even if use_hierarchy is disabled in "mem").
+        */
+       if (mem->use_hierarchy)
                ret = css_is_ancestor(&curr->css, &mem->css);
        else
                ret = (curr == mem);

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index ea2147dabba60febfb381b8fb788c9a0cbf9ed30..9092b43f07fa01cda075b005fb66cd482eb90ecf 100644 (file)
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -404,7 +404,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
                cpuset_print_task_mems_allowed(current);
                task_unlock(current);
                dump_stack();
-               mem_cgroup_print_oom_info(mem, current);
+               mem_cgroup_print_oom_info(mem, p);
                show_mem();
                if (sysctl_oom_dump_tasks)
                        dump_tasks(mem);