mm: memcontrol: flush percpu slab vmstats on kmem offlining

I've noticed that the "slab" value in memory.stat is sometimes 0, even
if some children memory cgroups have a non-zero "slab" value.  The
following investigation showed that this is the result of the kmem_cache
reparenting in combination with the per-cpu batching of slab vmstats.

At the offlining some vmstat value may leave in the percpu cache, not
being propagated upwards by the cgroup hierarchy.  It means that stats
on ancestor levels are lower than actual.  Later when slab pages are
released, the precise number of pages is substracted on the parent
level, making the value negative.  We don't show negative values, 0 is
printed instead.

To fix this issue, let's flush percpu slab memcg and lruvec stats on
memcg offlining.  This guarantees that numbers on all ancestor levels
are accurate and match the actual number of outstanding slab pages.

Link: http://lkml.kernel.org/r/20190819202338.363363-3-guro@fb.com
Fixes: fb2f2b0a ("mm: memcg/slab: reparent memcg kmem_caches on cgroup removal")
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/mmzone.h

@@ -215,8 +215,9 @@ enum node_stat_item {
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
-	NR_SLAB_RECLAIMABLE,
-	NR_SLAB_UNRECLAIMABLE,
+	NR_SLAB_RECLAIMABLE,	/* Please do not reorder this item */
+	NR_SLAB_UNRECLAIMABLE,	/* and this one without looking at
+				 * memcg_flush_percpu_vmstats() first. */
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_NODES,

mm/memcontrol.c

@@ -3260,37 +3260,49 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
 	}
 }
 
-static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg)
+static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg, bool slab_only)
 {
 	unsigned long stat[MEMCG_NR_STAT];
 	struct mem_cgroup *mi;
 	int node, cpu, i;
+	int min_idx, max_idx;
 
-	for (i = 0; i < MEMCG_NR_STAT; i++)
+	if (slab_only) {
+		min_idx = NR_SLAB_RECLAIMABLE;
+		max_idx = NR_SLAB_UNRECLAIMABLE;
+	} else {
+		min_idx = 0;
+		max_idx = MEMCG_NR_STAT;
+	}
+
+	for (i = min_idx; i < max_idx; i++)
 		stat[i] = 0;
 
 	for_each_online_cpu(cpu)
-		for (i = 0; i < MEMCG_NR_STAT; i++)
+		for (i = min_idx; i < max_idx; i++)
 			stat[i] += raw_cpu_read(memcg->vmstats_percpu->stat[i]);
 
 	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
-		for (i = 0; i < MEMCG_NR_STAT; i++)
+		for (i = min_idx; i < max_idx; i++)
 			atomic_long_add(stat[i], &mi->vmstats[i]);
 
+	if (!slab_only)
+		max_idx = NR_VM_NODE_STAT_ITEMS;
+
 	for_each_node(node) {
 		struct mem_cgroup_per_node *pn = memcg->nodeinfo[node];
 		struct mem_cgroup_per_node *pi;
 
-		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+		for (i = min_idx; i < max_idx; i++)
 			stat[i] = 0;
 
 		for_each_online_cpu(cpu)
-			for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+			for (i = min_idx; i < max_idx; i++)
 				stat[i] += raw_cpu_read(
 					pn->lruvec_stat_cpu->count[i]);
 
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, node))
-			for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
+			for (i = min_idx; i < max_idx; i++)
 				atomic_long_add(stat[i], &pi->lruvec_stat[i]);
 	}
 }
@@ -3363,7 +3375,14 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
 	if (!parent)
 		parent = root_mem_cgroup;
 
+	/*
+	 * Deactivate and reparent kmem_caches. Then flush percpu
+	 * slab statistics to have precise values at the parent and
+	 * all ancestor levels. It's required to keep slab stats
+	 * accurate after the reparenting of kmem_caches.
+	 */
 	memcg_deactivate_kmem_caches(memcg, parent);
+	memcg_flush_percpu_vmstats(memcg, true);
 
 	kmemcg_id = memcg->kmemcg_id;
 	BUG_ON(kmemcg_id < 0);
@@ -4740,7 +4759,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 	 * Flush percpu vmstats and vmevents to guarantee the value correctness
 	 * on parent's and all ancestor levels.
 	 */
-	memcg_flush_percpu_vmstats(memcg);
+	memcg_flush_percpu_vmstats(memcg, false);
 	memcg_flush_percpu_vmevents(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);