mm, oom: refactor dump_tasks for memcg OOMs

dump_tasks() traverses all the existing processes even for the memcg OOM
context which is not only unnecessary but also wasteful.  This imposes a
long RCU critical section even from a contained context which can be quite
disruptive.

Change dump_tasks() to be aligned with select_bad_process and use
mem_cgroup_scan_tasks to selectively traverse only processes of the target
memcg hierarchy during memcg OOM.

Link: http://lkml.kernel.org/r/20190617231207.160865-1-shakeelb@google.comSigned-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/oom_kill.c

@@ -382,28 +382,13 @@ static void select_bad_process(struct oom_control *oc)
 	oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
 }
 
-/**
- * dump_tasks - dump current memory state of all system tasks
- * @memcg: current's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
- *
- * Dumps the current memory state of all eligible tasks.  Tasks not in the same
- * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
- * are not shown.
- * State information includes task's pid, uid, tgid, vm size, rss,
- * pgtables_bytes, swapents, oom_score_adj value, and name.
- */
-static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
+static int dump_task(struct task_struct *p, void *arg)
 {
-	struct task_struct *p;
+	struct oom_control *oc = arg;
 	struct task_struct *task;
 
-	pr_info("Tasks state (memory values in pages):\n");
-	pr_info("[  pid  ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name\n");
-	rcu_read_lock();
-	for_each_process(p) {
-		if (oom_unkillable_task(p, memcg, nodemask))
-			continue;
+	if (oom_unkillable_task(p, NULL, oc->nodemask))
+		return 0;
 
 	task = find_lock_task_mm(p);
 	if (!task) {
@@ -412,7 +397,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 		 * detached their mm's.  There's no need to report
 		 * them; they can't be oom killed anyway.
 		 */
-			continue;
+		return 0;
 	}
 
 	pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
@@ -422,8 +407,35 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask)
 		get_mm_counter(task->mm, MM_SWAPENTS),
 		task->signal->oom_score_adj, task->comm);
 	task_unlock(task);
-	}
+
+	return 0;
+}
+
+/**
+ * dump_tasks - dump current memory state of all system tasks
+ * @oc: pointer to struct oom_control
+ *
+ * Dumps the current memory state of all eligible tasks.  Tasks not in the same
+ * memcg, not in the same cpuset, or bound to a disjoint set of mempolicy nodes
+ * are not shown.
+ * State information includes task's pid, uid, tgid, vm size, rss,
+ * pgtables_bytes, swapents, oom_score_adj value, and name.
+ */
+static void dump_tasks(struct oom_control *oc)
+{
+	pr_info("Tasks state (memory values in pages):\n");
+	pr_info("[  pid  ]   uid  tgid total_vm      rss pgtables_bytes swapents oom_score_adj name\n");
+
+	if (is_memcg_oom(oc))
+		mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
+	else {
+		struct task_struct *p;
+
+		rcu_read_lock();
+		for_each_process(p)
+			dump_task(p, oc);
 		rcu_read_unlock();
+	}
 }
 
 static void dump_oom_summary(struct oom_control *oc, struct task_struct *victim)
@@ -455,7 +467,7 @@ static void dump_header(struct oom_control *oc, struct task_struct *p)
 			dump_unreclaimable_slab();
 	}
 	if (sysctl_oom_dump_tasks)
-		dump_tasks(oc->memcg, oc->nodemask);
+		dump_tasks(oc);
 	if (p)
 		dump_oom_summary(oc, p);
 }