mm, oom: introduce memory.oom.group

For some workloads an intervention from the OOM killer can be painful.
Killing a random task can bring the workload into an inconsistent state.

Historically, there are two common solutions for this
problem:
1) enabling panic_on_oom,
2) using a userspace daemon to monitor OOMs and kill
   all outstanding processes.

Both approaches have their downsides: rebooting on each OOM is an obvious
waste of capacity, and handling all in userspace is tricky and requires a
userspace agent, which will monitor all cgroups for OOMs.

In most cases an in-kernel after-OOM cleaning-up mechanism can eliminate
the necessity of enabling panic_on_oom.  Also, it can simplify the cgroup
management for userspace applications.

This commit introduces a new knob for cgroup v2 memory controller:
memory.oom.group.  The knob determines whether the cgroup should be
treated as an indivisible workload by the OOM killer.  If set, all tasks
belonging to the cgroup or to its descendants (if the memory cgroup is not
a leaf cgroup) are killed together or not at all.

To determine which cgroup has to be killed, we do traverse the cgroup
hierarchy from the victim task's cgroup up to the OOMing cgroup (or root)
and looking for the highest-level cgroup with memory.oom.group set.

Tasks with the OOM protection (oom_score_adj set to -1000) are treated as
an exception and are never killed.

This patch doesn't change the OOM victim selection algorithm.

Link: http://lkml.kernel.org/r/20180802003201.817-4-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>
Cc: David Rientjes <rientjes@google.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 123 insertions, 0 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 59c14c988143..4ead5a4817de 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1777,6 +1777,62 @@ cleanup:
 }
 
 /**
+ * mem_cgroup_get_oom_group - get a memory cgroup to clean up after OOM
+ * @victim: task to be killed by the OOM killer
+ * @oom_domain: memcg in case of memcg OOM, NULL in case of system-wide OOM
+ *
+ * Returns a pointer to a memory cgroup, which has to be cleaned up
+ * by killing all belonging OOM-killable tasks.
+ *
+ * Caller has to call mem_cgroup_put() on the returned non-NULL memcg.
+ */
+struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
+					    struct mem_cgroup *oom_domain)
+{
+	struct mem_cgroup *oom_group = NULL;
+	struct mem_cgroup *memcg;
+
+	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
+		return NULL;
+
+	if (!oom_domain)
+		oom_domain = root_mem_cgroup;
+
+	rcu_read_lock();
+
+	memcg = mem_cgroup_from_task(victim);
+	if (memcg == root_mem_cgroup)
+		goto out;
+
+	/*
+	 * Traverse the memory cgroup hierarchy from the victim task's
+	 * cgroup up to the OOMing cgroup (or root) to find the
+	 * highest-level memory cgroup with oom.group set.
+	 */
+	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
+		if (memcg->oom_group)
+			oom_group = memcg;
+
+		if (memcg == oom_domain)
+			break;
+	}
+
+	if (oom_group)
+		css_get(&oom_group->css);
+out:
+	rcu_read_unlock();
+
+	return oom_group;
+}
+
+void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
+{
+	pr_info("Tasks in ");
+	pr_cont_cgroup_path(memcg->css.cgroup);
+	pr_cont(" are going to be killed due to memory.oom.group set\n");
+}
+
+/**
  * lock_page_memcg - lock a page->mem_cgroup binding
  * @page: the page
  *
@@ -5561,6 +5617,37 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	return 0;
 }
 
+static int memory_oom_group_show(struct seq_file *m, void *v)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
+
+	seq_printf(m, "%d\n", memcg->oom_group);
+
+	return 0;
+}
+
+static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+	int ret, oom_group;
+
+	buf = strstrip(buf);
+	if (!buf)
+		return -EINVAL;
+
+	ret = kstrtoint(buf, 0, &oom_group);
+	if (ret)
+		return ret;
+
+	if (oom_group != 0 && oom_group != 1)
+		return -EINVAL;
+
+	memcg->oom_group = oom_group;
+
+	return nbytes;
+}
+
 static struct cftype memory_files[] = {
 	{
 		.name = "current",
@@ -5602,6 +5689,12 @@ static struct cftype memory_files[] = {
 		.flags = CFTYPE_NOT_ON_ROOT,
 		.seq_show = memory_stat_show,
 	},
+	{
+		.name = "oom.group",
+		.flags = CFTYPE_NOT_ON_ROOT | CFTYPE_NS_DELEGATABLE,
+		.seq_show = memory_oom_group_show,
+		.write = memory_oom_group_write,
+	},
 	{ }	/* terminate */
 };
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 330416c67ce5..0e10b864e074 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -908,6 +908,19 @@ static void __oom_kill_process(struct task_struct *victim)
 }
 #undef K
 
+/*
+ * Kill provided task unless it's secured by setting
+ * oom_score_adj to OOM_SCORE_ADJ_MIN.
+ */
+static int oom_kill_memcg_member(struct task_struct *task, void *unused)
+{
+	if (task->signal->oom_score_adj != OOM_SCORE_ADJ_MIN) {
+		get_task_struct(task);
+		__oom_kill_process(task);
+	}
+	return 0;
+}
+
 static void oom_kill_process(struct oom_control *oc, const char *message)
 {
 	struct task_struct *p = oc->chosen;
@@ -915,6 +928,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	struct task_struct *victim = p;
 	struct task_struct *child;
 	struct task_struct *t;
+	struct mem_cgroup *oom_group;
 	unsigned int victim_points = 0;
 	static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL,
 					      DEFAULT_RATELIMIT_BURST);
@@ -968,7 +982,23 @@ static void oom_kill_process(struct oom_control *oc, const char *message)
 	}
 	read_unlock(&tasklist_lock);
 
+	/*
+	 * Do we need to kill the entire memory cgroup?
+	 * Or even one of the ancestor memory cgroups?
+	 * Check this out before killing the victim task.
+	 */
+	oom_group = mem_cgroup_get_oom_group(victim, oc->memcg);
+
 	__oom_kill_process(victim);
+
+	/*
+	 * If necessary, kill all tasks in the selected memory cgroup.
+	 */
+	if (oom_group) {
+		mem_cgroup_print_oom_group(oom_group);
+		mem_cgroup_scan_tasks(oom_group, oom_kill_memcg_member, NULL);
+		mem_cgroup_put(oom_group);
+	}
 }
 
 /*