[RFC PATCH v1] mm: oom: introduce cpuset oom

[Gang Li]

cpuset confine processes to processor and memory node subsets.
When a process in cpuset triggers oom, it may kill a completely
irrelevant process on another numa node, which will not release any
memory for this cpuset.

It seems that `CONSTRAINT_CPUSET` is not really doing much these
days. Using CONSTRAINT_CPUSET, we can easily achieve node aware oom
killing by selecting victim from the cpuset which triggers oom.

Suggested-by: Michal Hocko <mhocko@xxxxxxxx>
Signed-off-by: Gang Li <ligang.bdlg@xxxxxxxxxxxxx>
---
This idea comes from a previous patch:
mm, oom: Introduce per numa node oom for CONSTRAINT_MEMORY_POLICY
https://lore.kernel.org/all/YoJ%2FioXwGTdCywUE@xxxxxxxxxxxxxx/

Any comments are welcome.
---
 include/linux/cpuset.h |  6 ++++++
 kernel/cgroup/cpuset.c | 17 +++++++++++++++++
 mm/oom_kill.c          |  4 ++++
 3 files changed, 27 insertions(+)

diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index d58e0476ee8e..7475f613ab90 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -178,6 +178,8 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
+int cpuset_cgroup_scan_tasks(int (*fn)(struct task_struct *, void *), void *arg);
+
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -299,6 +301,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
+static inline int cpuset_cgroup_scan_tasks(int (*fn)(struct task_struct *, void *), void *arg)
+{
+	return 0;
+}
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index b474289c15b8..1f1238b4276d 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -3943,6 +3943,23 @@ void cpuset_print_current_mems_allowed(void)
 	rcu_read_unlock();
 }
 
+int cpuset_cgroup_scan_tasks(int (*fn)(struct task_struct *, void *), void *arg)
+{
+	int ret = 0;
+	struct cgroup *cgrp;
+	struct css_task_iter it;
+	struct task_struct *task;
+
+	rcu_read_lock();
+	css_task_iter_start(&(task_cs(current)->css), CSS_TASK_ITER_PROCS, &it);
+	while (!ret && (task = css_task_iter_next(&it)))
+		ret = fn(task, arg);
+	css_task_iter_end(&it);
+	rcu_read_unlock();
+
+	return ret;
+}
+
 /*
  * Collection of memory_pressure is suppressed unless
  * this flag is enabled by writing "1" to the special
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 46e7e073f137..8cea787b359c 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -367,6 +367,8 @@ static void select_bad_process(struct oom_control *oc)
 
 	if (is_memcg_oom(oc))
 		mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc);
+	else if (oc->constraint == CONSTRAINT_CPUSET)
+		cpuset_cgroup_scan_tasks(oom_evaluate_task, oc);
 	else {
 		struct task_struct *p;
 
@@ -427,6 +429,8 @@ static void dump_tasks(struct oom_control *oc)
 
 	if (is_memcg_oom(oc))
 		mem_cgroup_scan_tasks(oc->memcg, dump_task, oc);
+	else if (oc->constraint == CONSTRAINT_CPUSET)
+		cpuset_cgroup_scan_tasks(dump_task, oc);
 	else {
 		struct task_struct *p;
 
-- 
2.20.1