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

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>

2 files changed, 15 insertions, 8 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6273984f2e3..a294b757607 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -760,7 +760,13 @@ 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);
@@ -1009,7 +1015,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	static char memcg_name[PATH_MAX];
 	int ret;
 
-	if (!memcg)
+	if (!memcg || !p)
 		return;
 
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 25c679e0288..f52481b1c1e 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -356,7 +356,8 @@ static void dump_tasks(const struct mem_cgroup *mem)
 	} while_each_thread(g, p);
 }
 
-static void dump_header(gfp_t gfp_mask, int order, struct mem_cgroup *mem)
+static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
+							struct mem_cgroup *mem)
 {
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
 		"oom_adj=%d\n",
@@ -365,7 +366,7 @@ static void dump_header(gfp_t gfp_mask, int order, struct mem_cgroup *mem)
 	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);
@@ -440,7 +441,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 	struct task_struct *c;
 
 	if (printk_ratelimit())
-		dump_header(gfp_mask, order, mem);
+		dump_header(p, gfp_mask, order, mem);
 
 	/*
 	 * If the task is already exiting, don't alarm the sysadmin or kill
@@ -576,7 +577,7 @@ retry:
 	/* Found nothing?!?! Either we hang forever, or we panic. */
 	if (!p) {
 		read_unlock(&tasklist_lock);
-		dump_header(gfp_mask, order, NULL);
+		dump_header(NULL, gfp_mask, order, NULL);
 		panic("Out of memory and no killable processes...\n");
 	}
 
@@ -644,7 +645,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		return;
 
 	if (sysctl_panic_on_oom == 2) {
-		dump_header(gfp_mask, order, NULL);
+		dump_header(NULL, gfp_mask, order, NULL);
 		panic("out of memory. Compulsory panic_on_oom is selected.\n");
 	}
 
@@ -663,7 +664,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 
 	case CONSTRAINT_NONE:
 		if (sysctl_panic_on_oom) {
-			dump_header(gfp_mask, order, NULL);
+			dump_header(NULL, gfp_mask, order, NULL);
 			panic("out of memory. panic_on_oom is selected\n");
 		}
 		/* Fall-through */