Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Roman Gushchin <guro@fb.com>
To:     <linux-mm@kvack.org>
CC:     Michal Hocko <mhocko@suse.com>,
        Johannes Weiner <hannes@cmpxchg.org>,
        David Rientjes <rientjes@google.com>,
        Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>,
        Tejun Heo <tj@kernel.org>, <kernel-team@fb.com>,
        <linux-kernel@vger.kernel.org>, Roman Gushchin <guro@fb.com>,
        Vladimir Davydov <vdavydov.dev@gmail.com>,
        Michal Hocko <mhocko@kernel.org>,
        Andrew Morton <akpm@linux-foundation.org>
Subject: [PATCH 2/3] mm, oom: refactor oom_kill_process()
Date:   Mon, 30 Jul 2018 11:00:59 -0700
Message-ID: <20180730180100.25079-3-guro@fb.com>
In-Reply-To: <20180730180100.25079-1-guro@fb.com>
References: <20180730180100.25079-1-guro@fb.com>
MIME-Version: 1.0
Content-Type: text/plain
Received-SPF: None (protection.outlook.com: fb.com does not designate
 permitted sender hosts)
SpamDiagnosticOutput: 1:99
SpamDiagnosticMetadata: NSPM
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 30 Jul 2018 18:01:27.9244 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 3a521c10-fc15-4dc1-9807-08d5f64679de
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 8ae927fe-1255-47a7-a2af-5f3a069daaa2
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SN1PR15MB0175
X-OriginatorOrg: fb.com
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:,, definitions=2018-07-30_08:,,
 signatures=0
X-Proofpoint-Spam-Reason: safe
X-FB-Internal: Safe
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

oom_kill_process() consists of two logical parts: the first one is
responsible for considering task's children as a potential victim and
printing the debug information.  The second half is responsible for
sending SIGKILL to all tasks sharing the mm struct with the given victim.

This commit splits oom_kill_process() with an intention to re-use the the
second half: __oom_kill_process().

The cgroup-aware OOM killer will kill multiple tasks belonging to the
victim cgroup.  We don't need to print the debug information for the each
task, as well as play with task selection (considering task's children),
so we can't use the existing oom_kill_process().

Link: http://lkml.kernel.org/r/20171130152824.1591-2-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David Rientjes <rientjes@google.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: David Rientjes <rientjes@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/oom_kill.c | 123 +++++++++++++++++++++++++++++++---------------------------
 1 file changed, 65 insertions(+), 58 deletions(-)

diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 84081e77bc51..8bded6b3205b 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -835,68 +835,12 @@ static bool task_will_free_mem(struct task_struct *task)
 	return ret;
 }
 
-static void oom_kill_process(struct oom_control *oc, const char *message)
+static void __oom_kill_process(struct task_struct *victim)
 {
-	struct task_struct *p = oc->chosen;
-	unsigned int points = oc->chosen_points;
-	struct task_struct *victim = p;
-	struct task_struct *child;
-	struct task_struct *t;
+	struct task_struct *p;
 	struct mm_struct *mm;
-	unsigned int victim_points = 0;
-	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
-					      DEFAULT_RATELIMIT_BURST);
 	bool can_oom_reap = true;
 
-	/*
-	 * If the task is already exiting, don't alarm the sysadmin or kill
-	 * its children or threads, just give it access to memory reserves
-	 * so it can die quickly
-	 */
-	task_lock(p);
-	if (task_will_free_mem(p)) {
-		mark_oom_victim(p);
-		wake_oom_reaper(p);
-		task_unlock(p);
-		put_task_struct(p);
-		return;
-	}
-	task_unlock(p);
-
-	if (__ratelimit(&oom_rs))
-		dump_header(oc, p);
-
-	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
-		message, task_pid_nr(p), p->comm, points);
-
-	/*
-	 * If any of p's children has a different mm and is eligible for kill,
-	 * the one with the highest oom_badness() score is sacrificed for its
-	 * parent.  This attempts to lose the minimal amount of work done while
-	 * still freeing memory.
-	 */
-	read_lock(&tasklist_lock);
-	for_each_thread(p, t) {
-		list_for_each_entry(child, &t->children, sibling) {
-			unsigned int child_points;
-
-			if (process_shares_mm(child, p->mm))
-				continue;
-			/*
-			 * oom_badness() returns 0 if the thread is unkillable
-			 */
-			child_points = oom_badness(child,
-				oc->memcg, oc->nodemask, oc->totalpages);
-			if (child_points > victim_points) {
-				put_task_struct(victim);
-				victim = child;
-				victim_points = child_points;
-				get_task_struct(victim);
-			}
-		}
-	}
-	read_unlock(&tasklist_lock);
-
 	p = find_lock_task_mm(victim);
 	if (!p) {
 		put_task_struct(victim);
@@ -970,6 +914,69 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 }
 #undef K
 
+static void oom_kill_process(struct oom_control *oc, const char *message)
+{
+	struct task_struct *p = oc->chosen;
+	unsigned int points = oc->chosen_points;
+	struct task_struct *victim = p;
+	struct task_struct *child;
+	struct task_struct *t;
+	unsigned int victim_points = 0;
+	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
+					      DEFAULT_RATELIMIT_BURST);
+
+	/*
+	 * If the task is already exiting, don't alarm the sysadmin or kill
+	 * its children or threads, just give it access to memory reserves
+	 * so it can die quickly
+	 */
+	task_lock(p);
+	if (task_will_free_mem(p)) {
+		mark_oom_victim(p);
+		wake_oom_reaper(p);
+		task_unlock(p);
+		put_task_struct(p);
+		return;
+	}
+	task_unlock(p);
+
+	if (__ratelimit(&oom_rs))
+		dump_header(oc, p);
+
+	pr_err("%s: Kill process %d (%s) score %u or sacrifice child\n",
+		message, task_pid_nr(p), p->comm, points);
+
+	/*
+	 * If any of p's children has a different mm and is eligible for kill,
+	 * the one with the highest oom_badness() score is sacrificed for its
+	 * parent.  This attempts to lose the minimal amount of work done while
+	 * still freeing memory.
+	 */
+	read_lock(&tasklist_lock);
+	for_each_thread(p, t) {
+		list_for_each_entry(child, &t->children, sibling) {
+			unsigned int child_points;
+
+			if (process_shares_mm(child, p->mm))
+				continue;
+			/*
+			 * oom_badness() returns 0 if the thread is unkillable
+			 */
+			child_points = oom_badness(child,
+				oc->memcg, oc->nodemask, oc->totalpages);
+			if (child_points > victim_points) {
+				put_task_struct(victim);
+				victim = child;
+				victim_points = child_points;
+				get_task_struct(victim);
+			}
+		}
+	}
+	read_unlock(&tasklist_lock);
+
+	__oom_kill_process(victim);
+}
+
 /*
  * Determines whether the kernel must panic because of the panic_on_oom sysctl.
  */
-- 
2.14.4