mm: memcontrol: optimize per-lruvec stats counter memory usage

The vmstat threshold is 32 (MEMCG_CHARGE_BATCH), Actually the threshold
can be as big as MEMCG_CHARGE_BATCH * PAGE_SIZE.  It still fits into s32.
So introduce struct batched_lruvec_stat to optimize memory usage.

The size of struct lruvec_stat is 304 bytes on 64 bit systems.  As it is a
per-cpu structure.  So with this patch, we can save 304 / 2 * ncpu bytes
per-memcg per-node where ncpu is the number of the possible CPU.  If there
are c memory cgroup (include dying cgroup) and n NUMA node in the system.
Finally, we can save (152 * ncpu * c * n) bytes.

[akpm@linux-foundation.org: fix typo in comment]

Link: https://lkml.kernel.org/r/20201210042121.39665-1-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Chris Down <chris@chrisdown.name>
Cc: Yafang Shao <laoar.shao@gmail.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

Author: Muchun Song

include/linux/memcontrol.h

@@ -92,6 +92,10 @@ struct lruvec_stat {
 	long count[NR_VM_NODE_STAT_ITEMS];
 };
 
+struct batched_lruvec_stat {
+	s32 count[NR_VM_NODE_STAT_ITEMS];
+};
+
 /*
  * Bitmap of shrinker::id corresponding to memcg-aware shrinkers,
  * which have elements charged to this memcg.
@@ -107,11 +111,17 @@ struct memcg_shrinker_map {
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 
-	/* Legacy local VM stats */
+	/*
+	 * Legacy local VM stats. This should be struct lruvec_stat and
+	 * cannot be optimized to struct batched_lruvec_stat. Because
+	 * the threshold of the lruvec_stat_cpu can be as big as
+	 * MEMCG_CHARGE_BATCH * PAGE_SIZE. It can fit into s32. But this
+	 * filed has no upper limit.
+	 */
 	struct lruvec_stat __percpu *lruvec_stat_local;
 
 	/* Subtree VM stats (batched updates) */
-	struct lruvec_stat __percpu *lruvec_stat_cpu;
+	struct batched_lruvec_stat __percpu *lruvec_stat_cpu;
 	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];

mm/memcontrol.c

@@ -5208,7 +5208,7 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 		return 1;
 	}
 
-	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct lruvec_stat,
+	pn->lruvec_stat_cpu = alloc_percpu_gfp(struct batched_lruvec_stat,
 					       GFP_KERNEL_ACCOUNT);
 	if (!pn->lruvec_stat_cpu) {
 		free_percpu(pn->lruvec_stat_local);
@@ -7093,6 +7093,14 @@ static int __init mem_cgroup_init(void)
 {
 	int cpu, node;
 
+	/*
+	 * Currently s32 type (can refer to struct batched_lruvec_stat) is
+	 * used for per-memcg-per-cpu caching of per-node statistics. In order
+	 * to work fine, we should make sure that the overfill threshold can't
+	 * exceed S32_MAX / PAGE_SIZE.
+	 */
+	BUILD_BUG_ON(MEMCG_CHARGE_BATCH > S32_MAX / PAGE_SIZE);
+
 	cpuhp_setup_state_nocalls(CPUHP_MM_MEMCQ_DEAD, "mm/memctrl:dead", NULL,
 				  memcg_hotplug_cpu_dead);