memcg: remove PCG_MOVE_LOCK flag from page_cgroup
PCG_MOVE_LOCK is used for bit spinlock to avoid race between overwriting
pc->mem_cgroup and page statistics accounting per memcg. This lock helps
to avoid the race but the race is very rare because moving tasks between
cgroup is not a usual job. So, it seems using 1bit per page is too
costly.
This patch changes this lock as per-memcg spinlock and removes
PCG_MOVE_LOCK.
If smaller lock is required, we'll be able to add some hashes but I'd like
to start from this.
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Greg Thelen <gthelen@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index cfd2db0..8afed28 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -300,6 +300,8 @@
* set > 0 if pages under this cgroup are moving to other cgroup.
*/
atomic_t moving_account;
+ /* taken only while moving_account > 0 */
+ spinlock_t move_lock;
/*
* percpu counter.
*/
@@ -1376,6 +1378,24 @@
return false;
}
+/*
+ * Take this lock when
+ * - a code tries to modify page's memcg while it's USED.
+ * - a code tries to modify page state accounting in a memcg.
+ * see mem_cgroup_stealed(), too.
+ */
+static void move_lock_mem_cgroup(struct mem_cgroup *memcg,
+ unsigned long *flags)
+{
+ spin_lock_irqsave(&memcg->move_lock, *flags);
+}
+
+static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
+ unsigned long *flags)
+{
+ spin_unlock_irqrestore(&memcg->move_lock, *flags);
+}
+
/**
* mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode.
* @memcg: The memory cgroup that went over limit
@@ -1900,7 +1920,7 @@
if (mem_cgroup_disabled())
return;
-
+again:
rcu_read_lock();
memcg = pc->mem_cgroup;
if (unlikely(!memcg || !PageCgroupUsed(pc)))
@@ -1908,11 +1928,13 @@
/* pc->mem_cgroup is unstable ? */
if (unlikely(mem_cgroup_stealed(memcg))) {
/* take a lock against to access pc->mem_cgroup */
- move_lock_page_cgroup(pc, &flags);
+ move_lock_mem_cgroup(memcg, &flags);
+ if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) {
+ move_unlock_mem_cgroup(memcg, &flags);
+ rcu_read_unlock();
+ goto again;
+ }
need_unlock = true;
- memcg = pc->mem_cgroup;
- if (!memcg || !PageCgroupUsed(pc))
- goto out;
}
switch (idx) {
@@ -1931,7 +1953,7 @@
out:
if (unlikely(need_unlock))
- move_unlock_page_cgroup(pc, &flags);
+ move_unlock_mem_cgroup(memcg, &flags);
rcu_read_unlock();
}
@@ -2500,8 +2522,7 @@
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\
- (1 << PCG_MIGRATION))
+#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MIGRATION))
/*
* Because tail pages are not marked as "used", set it. We're under
* zone->lru_lock, 'splitting on pmd' and compound_lock.
@@ -2572,7 +2593,7 @@
if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
goto unlock;
- move_lock_page_cgroup(pc, &flags);
+ move_lock_mem_cgroup(from, &flags);
if (PageCgroupFileMapped(pc)) {
/* Update mapped_file data for mem_cgroup */
@@ -2596,7 +2617,7 @@
* guaranteed that "to" is never removed. So, we don't check rmdir
* status here.
*/
- move_unlock_page_cgroup(pc, &flags);
+ move_unlock_mem_cgroup(from, &flags);
ret = 0;
unlock:
unlock_page_cgroup(pc);
@@ -4971,6 +4992,7 @@
atomic_set(&memcg->refcnt, 1);
memcg->move_charge_at_immigrate = 0;
mutex_init(&memcg->thresholds_lock);
+ spin_lock_init(&memcg->move_lock);
return &memcg->css;
free_out:
__mem_cgroup_free(memcg);