mm/memcg: cache vmstat data in percpu memcg_stock_pcp

Before the new slab memory controller with per object byte charging,
charging and vmstat data update happen only when new slab pages are
allocated or freed.  Now they are done with every kmem_cache_alloc() and
kmem_cache_free().  This causes additional overhead for workloads that
generate a lot of alloc and free calls.

The memcg_stock_pcp is used to cache byte charge for a specific obj_cgroup
to reduce that overhead.  To further reducing it, this patch makes the
vmstat data cached in the memcg_stock_pcp structure as well until it
accumulates a page size worth of update or when other cached data change.
Caching the vmstat data in the per-cpu stock eliminates two writes to
non-hot cachelines for memcg specific as well as memcg-lruvecs specific
vmstat data by a write to a hot local stock cacheline.

On a 2-socket Cascade Lake server with instrumentation enabled and this
patch applied, it was found that about 20% (634400 out of 3243830) of the
time when mod_objcg_state() is called leads to an actual call to
__mod_objcg_state() after initial boot.  When doing parallel kernel build,
the figure was about 17% (24329265 out of 142512465).  So caching the
vmstat data reduces the number of calls to __mod_objcg_state() by more
than 80%.

Link: https://lkml.kernel.org/r/20210506150007.16288-3-longman@redhat.com
Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Chris Down <chris@chrisdown.name>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Masayoshi Mizuma <msys.mizuma@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Cc: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/memcontrol.c

@@ -782,7 +782,8 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
 	rcu_read_unlock();
 }
 
-void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
+static inline void mod_objcg_mlstate(struct obj_cgroup *objcg,
+				     struct pglist_data *pgdat,
 				     enum node_stat_item idx, int nr)
 {
 	struct mem_cgroup *memcg;
@@ -791,7 +792,7 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 	rcu_read_lock();
 	memcg = obj_cgroup_memcg(objcg);
 	lruvec = mem_cgroup_lruvec(memcg, pgdat);
-	mod_memcg_lruvec_state(lruvec, idx, nr);
+	__mod_memcg_lruvec_state(lruvec, idx, nr);
 	rcu_read_unlock();
 }
 
@@ -2059,7 +2060,10 @@ struct memcg_stock_pcp {
 
 #ifdef CONFIG_MEMCG_KMEM
 	struct obj_cgroup *cached_objcg;
+	struct pglist_data *cached_pgdat;
 	unsigned int nr_bytes;
+	int nr_slab_reclaimable_b;
+	int nr_slab_unreclaimable_b;
 #endif
 
 	struct work_struct work;
@@ -3008,6 +3012,67 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
 	obj_cgroup_put(objcg);
 }
 
+void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
+		     enum node_stat_item idx, int nr)
+{
+	struct memcg_stock_pcp *stock;
+	unsigned long flags;
+	int *bytes;
+
+	local_irq_save(flags);
+	stock = this_cpu_ptr(&memcg_stock);
+
+	/*
+	 * Save vmstat data in stock and skip vmstat array update unless
+	 * accumulating over a page of vmstat data or when pgdat or idx
+	 * changes.
+	 */
+	if (stock->cached_objcg != objcg) {
+		drain_obj_stock(stock);
+		obj_cgroup_get(objcg);
+		stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes)
+				? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0;
+		stock->cached_objcg = objcg;
+		stock->cached_pgdat = pgdat;
+	} else if (stock->cached_pgdat != pgdat) {
+		/* Flush the existing cached vmstat data */
+		if (stock->nr_slab_reclaimable_b) {
+			mod_objcg_mlstate(objcg, pgdat, NR_SLAB_RECLAIMABLE_B,
+					  stock->nr_slab_reclaimable_b);
+			stock->nr_slab_reclaimable_b = 0;
+		}
+		if (stock->nr_slab_unreclaimable_b) {
+			mod_objcg_mlstate(objcg, pgdat, NR_SLAB_UNRECLAIMABLE_B,
+					  stock->nr_slab_unreclaimable_b);
+			stock->nr_slab_unreclaimable_b = 0;
+		}
+		stock->cached_pgdat = pgdat;
+	}
+
+	bytes = (idx == NR_SLAB_RECLAIMABLE_B) ? &stock->nr_slab_reclaimable_b
+					       : &stock->nr_slab_unreclaimable_b;
+	/*
+	 * Even for large object >= PAGE_SIZE, the vmstat data will still be
+	 * cached locally at least once before pushing it out.
+	 */
+	if (!*bytes) {
+		*bytes = nr;
+		nr = 0;
+	} else {
+		*bytes += nr;
+		if (abs(*bytes) > PAGE_SIZE) {
+			nr = *bytes;
+			*bytes = 0;
+		} else {
+			nr = 0;
+		}
+	}
+	if (nr)
+		mod_objcg_mlstate(objcg, pgdat, idx, nr);
+
+	local_irq_restore(flags);
+}
+
 static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
 {
 	struct memcg_stock_pcp *stock;
@@ -3055,6 +3120,25 @@ static void drain_obj_stock(struct memcg_stock_pcp *stock)
 		stock->nr_bytes = 0;
 	}
 
+	/*
+	 * Flush the vmstat data in current stock
+	 */
+	if (stock->nr_slab_reclaimable_b || stock->nr_slab_unreclaimable_b) {
+		if (stock->nr_slab_reclaimable_b) {
+			mod_objcg_mlstate(old, stock->cached_pgdat,
+					  NR_SLAB_RECLAIMABLE_B,
+					  stock->nr_slab_reclaimable_b);
+			stock->nr_slab_reclaimable_b = 0;
+		}
+		if (stock->nr_slab_unreclaimable_b) {
+			mod_objcg_mlstate(old, stock->cached_pgdat,
+					  NR_SLAB_UNRECLAIMABLE_B,
+					  stock->nr_slab_unreclaimable_b);
+			stock->nr_slab_unreclaimable_b = 0;
+		}
+		stock->cached_pgdat = NULL;
+	}
+
 	obj_cgroup_put(old);
 	stock->cached_objcg = NULL;
 }