memcg: fix percpu cached charge draining frequency

For performance, memory cgroup caches some "charge" from res_counter into
per cpu cache.  This works well but because it's cache, it needs to be
flushed in some cases.  Typical cases are

   1. when someone hit limit.

   2. when rmdir() is called and need to charges to be 0.

But "1" has problem.

Recently, with large SMP machines, we see many kworker runs because of
flushing memcg's cache.  Bad things in implementation are that even if a
cpu contains a cache for memcg not related to a memcg which hits limit,
drain code is called.

This patch does
        A) check percpu cache contains a useful data or not.
        B) check other asynchronous percpu draining doesn't run.
        C) don't call local cpu callback.

(*)This patch avoid changing the calling condition with hard-limit.

When I run "cat 1Gfile > /dev/null" under 300M limit memcg,

[Before]
13767 kamezawa  20   0 98.6m  424  416 D 10.0  0.0   0:00.61 cat
   58 root      20   0     0    0    0 S  0.6  0.0   0:00.09 kworker/2:1
   60 root      20   0     0    0    0 S  0.6  0.0   0:00.08 kworker/4:1
    4 root      20   0     0    0    0 S  0.3  0.0   0:00.02 kworker/0:0
   57 root      20   0     0    0    0 S  0.3  0.0   0:00.05 kworker/1:1
   61 root      20   0     0    0    0 S  0.3  0.0   0:00.05 kworker/5:1
   62 root      20   0     0    0    0 S  0.3  0.0   0:00.05 kworker/6:1
   63 root      20   0     0    0    0 S  0.3  0.0   0:00.05 kworker/7:1

[After]
 2676 root      20   0 98.6m  416  416 D  9.3  0.0   0:00.87 cat
 2626 kamezawa  20   0 15192 1312  920 R  0.3  0.0   0:00.28 top
    1 root      20   0 19384 1496 1204 S  0.0  0.0   0:00.66 init
    2 root      20   0     0    0    0 S  0.0  0.0   0:00.00 kthreadd
    3 root      20   0     0    0    0 S  0.0  0.0   0:00.00 ksoftirqd/0
    4 root      20   0     0    0    0 S  0.0  0.0   0:00.00 kworker/0:0

[akpm@linux-foundation.org: make percpu_charge_mutex static, tweak comments]
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Acked-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Tested-by: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/memcontrol.c

@@ -359,7 +359,7 @@ enum charge_type {
 static void mem_cgroup_get(struct mem_cgroup *mem);
 static void mem_cgroup_put(struct mem_cgroup *mem);
 static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
-static void drain_all_stock_async(void);
+static void drain_all_stock_async(struct mem_cgroup *mem);
 
 static struct mem_cgroup_per_zone *
 mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid)
@@ -1671,7 +1671,7 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 		if (victim == root_mem) {
 			loop++;
 			if (loop >= 1)
-				drain_all_stock_async();
+				drain_all_stock_async(root_mem);
 			if (loop >= 2) {
 				/*
 				 * If we have not been able to reclaim
@@ -1934,9 +1934,11 @@ struct memcg_stock_pcp {
 	struct mem_cgroup *cached; /* this never be root cgroup */
 	unsigned int nr_pages;
 	struct work_struct work;
+	unsigned long flags;
+#define FLUSHING_CACHED_CHARGE	(0)
 };
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
-static atomic_t memcg_drain_count;
+static DEFINE_MUTEX(percpu_charge_mutex);
 
 /*
  * Try to consume stocked charge on this cpu. If success, one page is consumed
@@ -1984,6 +1986,7 @@ static void drain_local_stock(struct work_struct *dummy)
 {
 	struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock);
 	drain_stock(stock);
+	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 }
 
 /*
@@ -2008,26 +2011,45 @@ static void refill_stock(struct mem_cgroup *mem, unsigned int nr_pages)
  * expects some charges will be back to res_counter later but cannot wait for
  * it.
  */
-static void drain_all_stock_async(void)
+static void drain_all_stock_async(struct mem_cgroup *root_mem)
 {
-	int cpu;
-	/* This function is for scheduling "drain" in asynchronous way.
-	 * The result of "drain" is not directly handled by callers. Then,
-	 * if someone is calling drain, we don't have to call drain more.
-	 * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if
-	 * there is a race. We just do loose check here.
+	int cpu, curcpu;
+	/*
+	 * If someone calls draining, avoid adding more kworker runs.
 	 */
-	if (atomic_read(&memcg_drain_count))
+	if (!mutex_trylock(&percpu_charge_mutex))
 		return;
 	/* Notify other cpus that system-wide "drain" is running */
-	atomic_inc(&memcg_drain_count);
 	get_online_cpus();
+	/*
+	 * Get a hint for avoiding draining charges on the current cpu,
+	 * which must be exhausted by our charging.  It is not required that
+	 * this be a precise check, so we use raw_smp_processor_id() instead of
+	 * getcpu()/putcpu().
+	 */
+	curcpu = raw_smp_processor_id();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
-		schedule_work_on(cpu, &stock->work);
+		struct mem_cgroup *mem;
+
+		if (cpu == curcpu)
+			continue;
+
+		mem = stock->cached;
+		if (!mem)
+			continue;
+		if (mem != root_mem) {
+			if (!root_mem->use_hierarchy)
+				continue;
+			/* check whether "mem" is under tree of "root_mem" */
+			if (!css_is_ancestor(&mem->css, &root_mem->css))
+				continue;
+		}
+		if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags))
+			schedule_work_on(cpu, &stock->work);
 	}
  	put_online_cpus();
-	atomic_dec(&memcg_drain_count);
+	mutex_unlock(&percpu_charge_mutex);
 	/* We don't wait for flush_work */
 }
 
@@ -2035,9 +2057,9 @@ static void drain_all_stock_async(void)
 static void drain_all_stock_sync(void)
 {
 	/* called when force_empty is called */
-	atomic_inc(&memcg_drain_count);
+	mutex_lock(&percpu_charge_mutex);
 	schedule_on_each_cpu(drain_local_stock);
-	atomic_dec(&memcg_drain_count);
+	mutex_unlock(&percpu_charge_mutex);
 }
 
 /*