memcg: switch lruvec stats to rstat

The commit 2d146aa3aa84 ("mm: memcontrol: switch to rstat") switched memcg
stats to rstat infrastructure but skipped the conversion of the lruvec
stats as such stats are read in the performance critical code paths and
flushing stats may have impacted the performances of the applications.
This patch converts the lruvec stats to rstat and later patches add
mechanisms to keep the performance impact to minimum.

The rstat conversion comes with the price i.e.  memory cost.  Effectively
this patch reverts the savings done by the commit f3344adf38bd ("mm:
memcontrol: optimize per-lruvec stats counter memory usage").  However
this cost is justified due to negative impact of the inaccurate lruvec
stats on many heuristics.  One such case is reported in [1].

The memory reclaim code is filled with plethora of heuristics and many of
those heuristics reads the lruvec stats.  So, inaccurate stats can make
such heuristics ineffective.  [1] reports the impact of inaccurate lruvec
stats on the "cache trim mode" heuristic.  Inaccurate lruvec stats can
impact the deactivation and aging anon heuristics as well.

[1] https://lore.kernel.org/linux-mm/20210311004449.1170308-1-ying.huang@intel.com/

Link: https://lkml.kernel.org/r/20210716212137.1391164-1-shakeelb@google.com
Link: https://lkml.kernel.org/r/20210714013948.270662-1-shakeelb@google.com
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Hillf Danton <hdanton@sina.com>
Cc: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 20 insertions, 22 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a00bf337567b..47d35bef9f6e 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -105,14 +105,6 @@ struct mem_cgroup_reclaim_iter {
 	unsigned int generation;
 };
 
-struct lruvec_stat {
-	long count[NR_VM_NODE_STAT_ITEMS];
-};
-
-struct batched_lruvec_stat {
-	s32 count[NR_VM_NODE_STAT_ITEMS];
-};
-
 /*
  * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
  * shrinkers, which have elements charged to this memcg.
@@ -123,24 +115,30 @@ struct shrinker_info {
 	unsigned long *map;
 };
 
+struct lruvec_stats_percpu {
+	/* Local (CPU and cgroup) state */
+	long state[NR_VM_NODE_STAT_ITEMS];
+
+	/* Delta calculation for lockless upward propagation */
+	long state_prev[NR_VM_NODE_STAT_ITEMS];
+};
+
+struct lruvec_stats {
+	/* Aggregated (CPU and subtree) state */
+	long state[NR_VM_NODE_STAT_ITEMS];
+
+	/* Pending child counts during tree propagation */
+	long state_pending[NR_VM_NODE_STAT_ITEMS];
+};
+
 /*
  * per-node information in memory controller.
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 
-	/*
-	 * 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 batched_lruvec_stat __percpu *lruvec_stat_cpu;
-	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
+	struct lruvec_stats_percpu __percpu	*lruvec_stats_percpu;
+	struct lruvec_stats			lruvec_stats;
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
@@ -997,7 +995,7 @@ static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	x = atomic_long_read(&pn->lruvec_stat[idx]);
+	x = READ_ONCE(pn->lruvec_stats.state[idx]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -1017,7 +1015,7 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	for_each_possible_cpu(cpu)
-		x += per_cpu(pn->lruvec_stat_local->count[idx], cpu);
+		x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;