Commit 1af8efe9 authored by Michal Hocko's avatar Michal Hocko Committed by Linus Torvalds
Browse files

memcg: change memcg_oom_mutex to spinlock 



memcg_oom_mutex is used to protect memcg OOM path and eventfd interface
for oom_control.  None of the critical sections which it protects sleep
(eventfd_signal works from atomic context and the rest are simple linked
list resp.  oom_lock atomic operations).

Mutex is also too heavyweight for those code paths because it triggers a
lot of scheduling.  It also makes makes convoying effects more visible
when we have a big number of oom killing because we take the lock
mutliple times during mem_cgroup_handle_oom so we have multiple places
where many processes can sleep.

Signed-off-by: default avatarMichal Hocko <mhocko@suse.cz>
Cc: Balbir Singh <bsingharora@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 79dfdacc

mm/memcontrol.c

+11 −11
Original line number Diff line number Diff line
@@ -1725,7 +1725,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, 
/*

 * Check OOM-Killer is already running under our hierarchy.

 * If someone is running, return false.

 * Has to be called with memcg_oom_mutex

 * Has to be called with memcg_oom_lock

 */

static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)

{
@@ -1770,7 +1770,7 @@ done: 
}



/*

 * Has to be called with memcg_oom_mutex

 * Has to be called with memcg_oom_lock

 */

static int mem_cgroup_oom_unlock(struct mem_cgroup *mem)

{
@@ -1802,7 +1802,7 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *mem) 
		atomic_add_unless(&iter->under_oom, -1, 0);

}



static DEFINE_MUTEX(memcg_oom_mutex);

static DEFINE_SPINLOCK(memcg_oom_lock);

static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);



struct oom_wait_info {
@@ -1864,7 +1864,7 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) 
	mem_cgroup_mark_under_oom(mem);



	/* At first, try to OOM lock hierarchy under mem.*/

	mutex_lock(&memcg_oom_mutex);

	spin_lock(&memcg_oom_lock);

	locked = mem_cgroup_oom_lock(mem);

	/*

	 * Even if signal_pending(), we can't quit charge() loop without
@@ -1876,7 +1876,7 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) 
		need_to_kill = false;

	if (locked)

		mem_cgroup_oom_notify(mem);

	mutex_unlock(&memcg_oom_mutex);

	spin_unlock(&memcg_oom_lock);



	if (need_to_kill) {

		finish_wait(&memcg_oom_waitq, &owait.wait);
@@ -1885,11 +1885,11 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask) 
		schedule();

		finish_wait(&memcg_oom_waitq, &owait.wait);

	}

	mutex_lock(&memcg_oom_mutex);

	spin_lock(&memcg_oom_lock);

	if (locked)

		mem_cgroup_oom_unlock(mem);

	memcg_wakeup_oom(mem);

	mutex_unlock(&memcg_oom_mutex);

	spin_unlock(&memcg_oom_lock);



	mem_cgroup_unmark_under_oom(mem);
@@ -4553,7 +4553,7 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp, 
	if (!event)

		return -ENOMEM;



	mutex_lock(&memcg_oom_mutex);

	spin_lock(&memcg_oom_lock);



	event->eventfd = eventfd;

	list_add(&event->list, &memcg->oom_notify);
@@ -4561,7 +4561,7 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp, 
	/* already in OOM ? */

	if (atomic_read(&memcg->under_oom))

		eventfd_signal(eventfd, 1);

	mutex_unlock(&memcg_oom_mutex);

	spin_unlock(&memcg_oom_lock);



	return 0;

}
@@ -4575,7 +4575,7 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, 


	BUG_ON(type != _OOM_TYPE);



	mutex_lock(&memcg_oom_mutex);

	spin_lock(&memcg_oom_lock);



	list_for_each_entry_safe(ev, tmp, &mem->oom_notify, list) {

		if (ev->eventfd == eventfd) {
@@ -4584,7 +4584,7 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp, 
		}

	}



	mutex_unlock(&memcg_oom_mutex);

	spin_unlock(&memcg_oom_lock);

}



static int mem_cgroup_oom_control_read(struct cgroup *cgrp,

CRA Git | Maintained and supported by SUSTech CRA and CCSE