From: Shakeel Butt <shakeelb@google.com>
Date: Fri, 12 Jul 2019 04:00:23 +0000 (-0700)
Subject: mm, oom: refactor dump_tasks for memcg OOMs
X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=5eee7e1cdb97123bb55ac14ccd3af8b6edc31537;p=openwrt%2Fstaging%2Fblogic.git

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.com
Signed-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>
---

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 606e5e4c6a3e..59326614508a 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -382,10 +382,38 @@ static void select_bad_process(struct oom_control *oc)
 	oc->chosen_points = oc->chosen_points * 1000 / oc->totalpages;
 }
 
+static int dump_task(struct task_struct *p, void *arg)
+{
+	struct oom_control *oc = arg;
+	struct task_struct *task;
+
+	if (oom_unkillable_task(p, NULL, oc->nodemask))
+		return 0;
+
+	task = find_lock_task_mm(p);
+	if (!task) {
+		/*
+		 * This is a kthread or all of p's threads have already
+		 * detached their mm's.  There's no need to report
+		 * them; they can't be oom killed anyway.
+		 */
+		return 0;
+	}
+
+	pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
+		task->pid, from_kuid(&init_user_ns, task_uid(task)),
+		task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
+		mm_pgtables_bytes(task->mm),
+		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
- * @memcg: current's memory controller, if constrained
- * @nodemask: nodemask passed to page allocator for mempolicy ooms
+ * @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
@@ -393,37 +421,21 @@ static void select_bad_process(struct oom_control *oc)
  * 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 void dump_tasks(struct oom_control *oc)
 {
-	struct task_struct *p;
-	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;
 
-		task = find_lock_task_mm(p);
-		if (!task) {
-			/*
-			 * This is a kthread or all of p's threads have already
-			 * detached their mm's.  There's no need to report
-			 * them; they can't be oom killed anyway.
-			 */
-			continue;
-		}
+	if (is_memcg_oom(oc))
+		mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
+	else {
+		struct task_struct *p;
 
-		pr_info("[%7d] %5d %5d %8lu %8lu %8ld %8lu         %5hd %s\n",
-			task->pid, from_kuid(&init_user_ns, task_uid(task)),
-			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
-			mm_pgtables_bytes(task->mm),
-			get_mm_counter(task->mm, MM_SWAPENTS),
-			task->signal->oom_score_adj, task->comm);
-		task_unlock(task);
+		rcu_read_lock();
+		for_each_process(p)
+			dump_task(p, oc);
+		rcu_read_unlock();
 	}
-	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);
 }