Merge branch 'akpm' (patches from Andrew)

Merge misc mm fixes from Andrew Morton:
 "7 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: memcontrol: fix percpu vmstats and vmevents flush
  mm, memcg: do not set reclaim_state on soft limit reclaim
  mailmap: add aliases for Dmitry Safonov
  mm/z3fold.c: fix lock/unlock imbalance in z3fold_page_isolate
  mm, memcg: partially revert "mm/memcontrol.c: keep local VM counters in sync with the hierarchical ones"
  mm/zsmalloc.c: fix build when CONFIG_COMPACTION=n
  mm: memcontrol: flush percpu slab vmstats on kmem offlining

6 files changed, 47 insertions, 22 deletions

diff --git a/.mailmap b/.mailmap
index ebdca3fba91fd6..afaad605284a8b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -64,6 +64,9 @@ Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@imgtec.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dczhu@mips.com>
 Dengcheng Zhu <dzhu@wavecomp.com> <dengcheng.zhu@gmail.com>
 Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <dsafonov@virtuozzo.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <d.safonov@partner.samsung.com>
+Dmitry Safonov <0x7f454c46@gmail.com> <dima@arista.com>
 Domen Puncer <domen@coderock.org>
 Douglas Gilbert <dougg@torque.net>
 Ed L. Cashin <ecashin@coraid.com>
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d77d717c620cbe..3f38c30d2f13d1 100644
--- a/include/linux/mmzone.h
+++ b/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,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 26e2999af608d3..9ec5e12486a780 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -752,15 +752,13 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	/* Update memcg */
 	__mod_memcg_state(memcg, idx, val);
 
+	/* Update lruvec */
+	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup_per_node *pi;
 
-		/*
-		 * Batch local counters to keep them in sync with
-		 * the hierarchical ones.
-		 */
-		__this_cpu_add(pn->lruvec_stat_local->count[idx], x);
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
 			atomic_long_add(x, &pi->lruvec_stat[idx]);
 		x = 0;
@@ -3260,37 +3258,49 @@ 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++)
-			stat[i] += raw_cpu_read(memcg->vmstats_percpu->stat[i]);
+		for (i = min_idx; i < max_idx; i++)
+			stat[i] += per_cpu(memcg->vmstats_percpu->stat[i], cpu);
 
 	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++)
-				stat[i] += raw_cpu_read(
-					pn->lruvec_stat_cpu->count[i]);
+			for (i = min_idx; i < max_idx; i++)
+				stat[i] += per_cpu(
+					pn->lruvec_stat_cpu->count[i], cpu);
 
 		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]);
 	}
 }
@@ -3306,8 +3316,8 @@ static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
 
 	for_each_online_cpu(cpu)
 		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
-			events[i] += raw_cpu_read(
-				memcg->vmstats_percpu->events[i]);
+			events[i] += per_cpu(memcg->vmstats_percpu->events[i],
+					     cpu);
 
 	for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
@@ -3363,7 +3373,14 @@ 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 +4757,7 @@ 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);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c77d1e3761a7f1..a6c5d0b28321c3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3220,6 +3220,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 
 #ifdef CONFIG_MEMCG
 
+/* Only used by soft limit reclaim. Do not reuse for anything else. */
 unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 						gfp_t gfp_mask, bool noswap,
 						pg_data_t *pgdat,
@@ -3235,7 +3236,8 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 	};
 	unsigned long lru_pages;
 
-	set_task_reclaim_state(current, &sc.reclaim_state);
+	WARN_ON_ONCE(!current->reclaim_state);
+
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 
@@ -3253,7 +3255,6 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
 
-	set_task_reclaim_state(current, NULL);
 	*nr_scanned = sc.nr_scanned;
 
 	return sc.nr_reclaimed;
diff --git a/mm/z3fold.c b/mm/z3fold.c
index e31cd9bd4ed561..75b7962439ff8b 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -1406,6 +1406,7 @@ static bool z3fold_page_isolate(struct page *page, isolate_mode_t mode)
 				 * should freak out.
 				 */
 				WARN(1, "Z3fold is experiencing kref problems\n");
+				z3fold_page_unlock(zhdr);
 				return false;
 			}
 			z3fold_page_unlock(zhdr);
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 08def3a0d2007c..e98bb6ab4f7e76 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -2412,7 +2412,9 @@ struct zs_pool *zs_create_pool(const char *name)
 	if (!pool->name)
 		goto err;
 
+#ifdef CONFIG_COMPACTION
 	init_waitqueue_head(&pool->migration_wait);
+#endif
 
 	if (create_cache(pool))
 		goto err;