1 files changed, 265 insertions, 220 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 58c69c94402a..c265212bec8c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -132,15 +132,11 @@ static const char * const mem_cgroup_lru_names[] = {
  * their hierarchy representation
  */
 
-struct mem_cgroup_tree_per_zone {
+struct mem_cgroup_tree_per_node {
 	struct rb_root rb_root;
 	spinlock_t lock;
 };
 
-struct mem_cgroup_tree_per_node {
-	struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES];
-};
-
 struct mem_cgroup_tree {
 	struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES];
 };
@@ -323,15 +319,6 @@ EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
 #endif /* !CONFIG_SLOB */
 
-static struct mem_cgroup_per_zone *
-mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone)
-{
-	int nid = zone_to_nid(zone);
-	int zid = zone_idx(zone);
-
-	return &memcg->nodeinfo[nid]->zoneinfo[zid];
-}
-
 /**
  * mem_cgroup_css_from_page - css of the memcg associated with a page
  * @page: page of interest
@@ -383,37 +370,35 @@ ino_t page_cgroup_ino(struct page *page)
 	return ino;
 }
 
-static struct mem_cgroup_per_zone *
-mem_cgroup_page_zoneinfo(struct mem_cgroup *memcg, struct page *page)
+static struct mem_cgroup_per_node *
+mem_cgroup_page_nodeinfo(struct mem_cgroup *memcg, struct page *page)
 {
 	int nid = page_to_nid(page);
-	int zid = page_zonenum(page);
 
-	return &memcg->nodeinfo[nid]->zoneinfo[zid];
+	return memcg->nodeinfo[nid];
 }
 
-static struct mem_cgroup_tree_per_zone *
-soft_limit_tree_node_zone(int nid, int zid)
+static struct mem_cgroup_tree_per_node *
+soft_limit_tree_node(int nid)
 {
-	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+	return soft_limit_tree.rb_tree_per_node[nid];
 }
 
-static struct mem_cgroup_tree_per_zone *
+static struct mem_cgroup_tree_per_node *
 soft_limit_tree_from_page(struct page *page)
 {
 	int nid = page_to_nid(page);
-	int zid = page_zonenum(page);
 
-	return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid];
+	return soft_limit_tree.rb_tree_per_node[nid];
 }
 
-static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
-					 struct mem_cgroup_tree_per_zone *mctz,
+static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz,
 					 unsigned long new_usage_in_excess)
 {
 	struct rb_node **p = &mctz->rb_root.rb_node;
 	struct rb_node *parent = NULL;
-	struct mem_cgroup_per_zone *mz_node;
+	struct mem_cgroup_per_node *mz_node;
 
 	if (mz->on_tree)
 		return;
@@ -423,7 +408,7 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
 		return;
 	while (*p) {
 		parent = *p;
-		mz_node = rb_entry(parent, struct mem_cgroup_per_zone,
+		mz_node = rb_entry(parent, struct mem_cgroup_per_node,
 					tree_node);
 		if (mz->usage_in_excess < mz_node->usage_in_excess)
 			p = &(*p)->rb_left;
@@ -439,8 +424,8 @@ static void __mem_cgroup_insert_exceeded(struct mem_cgroup_per_zone *mz,
 	mz->on_tree = true;
 }
 
-static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
-					 struct mem_cgroup_tree_per_zone *mctz)
+static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+					 struct mem_cgroup_tree_per_node *mctz)
 {
 	if (!mz->on_tree)
 		return;
@@ -448,8 +433,8 @@ static void __mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
 	mz->on_tree = false;
 }
 
-static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_zone *mz,
-				       struct mem_cgroup_tree_per_zone *mctz)
+static void mem_cgroup_remove_exceeded(struct mem_cgroup_per_node *mz,
+				       struct mem_cgroup_tree_per_node *mctz)
 {
 	unsigned long flags;
 
@@ -473,8 +458,8 @@ static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
 static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 {
 	unsigned long excess;
-	struct mem_cgroup_per_zone *mz;
-	struct mem_cgroup_tree_per_zone *mctz;
+	struct mem_cgroup_per_node *mz;
+	struct mem_cgroup_tree_per_node *mctz;
 
 	mctz = soft_limit_tree_from_page(page);
 	/*
@@ -482,7 +467,7 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 	 * because their event counter is not touched.
 	 */
 	for (; memcg; memcg = parent_mem_cgroup(memcg)) {
-		mz = mem_cgroup_page_zoneinfo(memcg, page);
+		mz = mem_cgroup_page_nodeinfo(memcg, page);
 		excess = soft_limit_excess(memcg);
 		/*
 		 * We have to update the tree if mz is on RB-tree or
@@ -507,24 +492,22 @@ static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 
 static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup_tree_per_zone *mctz;
-	struct mem_cgroup_per_zone *mz;
-	int nid, zid;
+	struct mem_cgroup_tree_per_node *mctz;
+	struct mem_cgroup_per_node *mz;
+	int nid;
 
 	for_each_node(nid) {
-		for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-			mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-			mctz = soft_limit_tree_node_zone(nid, zid);
-			mem_cgroup_remove_exceeded(mz, mctz);
-		}
+		mz = mem_cgroup_nodeinfo(memcg, nid);
+		mctz = soft_limit_tree_node(nid);
+		mem_cgroup_remove_exceeded(mz, mctz);
 	}
 }
 
-static struct mem_cgroup_per_zone *
-__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+static struct mem_cgroup_per_node *
+__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
 {
 	struct rb_node *rightmost = NULL;
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 
 retry:
 	mz = NULL;
@@ -532,7 +515,7 @@ retry:
 	if (!rightmost)
 		goto done;		/* Nothing to reclaim from */
 
-	mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node);
+	mz = rb_entry(rightmost, struct mem_cgroup_per_node, tree_node);
 	/*
 	 * Remove the node now but someone else can add it back,
 	 * we will to add it back at the end of reclaim to its correct
@@ -546,10 +529,10 @@ done:
 	return mz;
 }
 
-static struct mem_cgroup_per_zone *
-mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
+static struct mem_cgroup_per_node *
+mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 
 	spin_lock_irq(&mctz->lock);
 	mz = __mem_cgroup_largest_soft_limit_node(mctz);
@@ -643,20 +626,16 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 					   int nid, unsigned int lru_mask)
 {
 	unsigned long nr = 0;
-	int zid;
+	struct mem_cgroup_per_node *mz;
+	enum lru_list lru;
 
 	VM_BUG_ON((unsigned)nid >= nr_node_ids);
 
-	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-		struct mem_cgroup_per_zone *mz;
-		enum lru_list lru;
-
-		for_each_lru(lru) {
-			if (!(BIT(lru) & lru_mask))
-				continue;
-			mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-			nr += mz->lru_size[lru];
-		}
+	for_each_lru(lru) {
+		if (!(BIT(lru) & lru_mask))
+			continue;
+		mz = mem_cgroup_nodeinfo(memcg, nid);
+		nr += mz->lru_size[lru];
 	}
 	return nr;
 }
@@ -809,9 +788,9 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 	rcu_read_lock();
 
 	if (reclaim) {
-		struct mem_cgroup_per_zone *mz;
+		struct mem_cgroup_per_node *mz;
 
-		mz = mem_cgroup_zone_zoneinfo(root, reclaim->zone);
+		mz = mem_cgroup_nodeinfo(root, reclaim->pgdat->node_id);
 		iter = &mz->iter[reclaim->priority];
 
 		if (prev && reclaim->generation != iter->generation)
@@ -910,19 +889,17 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 {
 	struct mem_cgroup *memcg = dead_memcg;
 	struct mem_cgroup_reclaim_iter *iter;
-	struct mem_cgroup_per_zone *mz;
-	int nid, zid;
+	struct mem_cgroup_per_node *mz;
+	int nid;
 	int i;
 
 	while ((memcg = parent_mem_cgroup(memcg))) {
 		for_each_node(nid) {
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-				for (i = 0; i <= DEF_PRIORITY; i++) {
-					iter = &mz->iter[i];
-					cmpxchg(&iter->position,
-						dead_memcg, NULL);
-				}
+			mz = mem_cgroup_nodeinfo(memcg, nid);
+			for (i = 0; i <= DEF_PRIORITY; i++) {
+				iter = &mz->iter[i];
+				cmpxchg(&iter->position,
+					dead_memcg, NULL);
 			}
 		}
 	}
@@ -944,39 +921,6 @@ static void invalidate_reclaim_iterators(struct mem_cgroup *dead_memcg)
 	     iter = mem_cgroup_iter(NULL, iter, NULL))
 
 /**
- * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
- * @zone: zone of the wanted lruvec
- * @memcg: memcg of the wanted lruvec
- *
- * Returns the lru list vector holding pages for the given @zone and
- * @mem.  This can be the global zone lruvec, if the memory controller
- * is disabled.
- */
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
-				      struct mem_cgroup *memcg)
-{
-	struct mem_cgroup_per_zone *mz;
-	struct lruvec *lruvec;
-
-	if (mem_cgroup_disabled()) {
-		lruvec = &zone->lruvec;
-		goto out;
-	}
-
-	mz = mem_cgroup_zone_zoneinfo(memcg, zone);
-	lruvec = &mz->lruvec;
-out:
-	/*
-	 * Since a node can be onlined after the mem_cgroup was created,
-	 * we have to be prepared to initialize lruvec->zone here;
-	 * and if offlined then reonlined, we need to reinitialize it.
-	 */
-	if (unlikely(lruvec->zone != zone))
-		lruvec->zone = zone;
-	return lruvec;
-}
-
-/**
  * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
  * @page: the page
  * @zone: zone of the page
@@ -985,14 +929,14 @@ out:
  * and putback protocol: the LRU lock must be held, and the page must
  * either be PageLRU() or the caller must have isolated/allocated it.
  */
-struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
+struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 	struct mem_cgroup *memcg;
 	struct lruvec *lruvec;
 
 	if (mem_cgroup_disabled()) {
-		lruvec = &zone->lruvec;
+		lruvec = &pgdat->lruvec;
 		goto out;
 	}
 
@@ -1004,7 +948,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 	if (!memcg)
 		memcg = root_mem_cgroup;
 
-	mz = mem_cgroup_page_zoneinfo(memcg, page);
+	mz = mem_cgroup_page_nodeinfo(memcg, page);
 	lruvec = &mz->lruvec;
 out:
 	/*
@@ -1012,8 +956,8 @@ out:
 	 * we have to be prepared to initialize lruvec->zone here;
 	 * and if offlined then reonlined, we need to reinitialize it.
 	 */
-	if (unlikely(lruvec->zone != zone))
-		lruvec->zone = zone;
+	if (unlikely(lruvec->pgdat != pgdat))
+		lruvec->pgdat = pgdat;
 	return lruvec;
 }
 
@@ -1030,17 +974,15 @@ out:
 void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru,
 				int nr_pages)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 	unsigned long *lru_size;
 	long size;
 	bool empty;
 
-	__update_lru_size(lruvec, lru, nr_pages);
-
 	if (mem_cgroup_disabled())
 		return;
 
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	lru_size = mz->lru_size + lru;
 	empty = list_empty(lruvec->lists + lru);
 
@@ -1259,6 +1201,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	struct oom_control oc = {
 		.zonelist = NULL,
 		.nodemask = NULL,
+		.memcg = memcg,
 		.gfp_mask = gfp_mask,
 		.order = order,
 	};
@@ -1275,13 +1218,13 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * select it.  The goal is to allow it to allocate so that it may
 	 * quickly exit and free its memory.
 	 */
-	if (fatal_signal_pending(current) || task_will_free_mem(current)) {
+	if (task_will_free_mem(current)) {
 		mark_oom_victim(current);
-		try_oom_reaper(current);
+		wake_oom_reaper(current);
 		goto unlock;
 	}
 
-	check_panic_on_oom(&oc, CONSTRAINT_MEMCG, memcg);
+	check_panic_on_oom(&oc, CONSTRAINT_MEMCG);
 	totalpages = mem_cgroup_get_limit(memcg) ? : 1;
 	for_each_mem_cgroup_tree(iter, memcg) {
 		struct css_task_iter it;
@@ -1289,7 +1232,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 		css_task_iter_start(&iter->css, &it);
 		while ((task = css_task_iter_next(&it))) {
-			switch (oom_scan_process_thread(&oc, task, totalpages)) {
+			switch (oom_scan_process_thread(&oc, task)) {
 			case OOM_SCAN_SELECT:
 				if (chosen)
 					put_task_struct(chosen);
@@ -1329,7 +1272,7 @@ static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
 
 	if (chosen) {
 		points = chosen_points * 1000 / totalpages;
-		oom_kill_process(&oc, chosen, points, totalpages, memcg,
+		oom_kill_process(&oc, chosen, points, totalpages,
 				 "Memory cgroup out of memory");
 	}
 unlock:
@@ -1432,7 +1375,7 @@ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg)
 #endif
 
 static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
-				   struct zone *zone,
+				   pg_data_t *pgdat,
 				   gfp_t gfp_mask,
 				   unsigned long *total_scanned)
 {
@@ -1442,7 +1385,7 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 	unsigned long excess;
 	unsigned long nr_scanned;
 	struct mem_cgroup_reclaim_cookie reclaim = {
-		.zone = zone,
+		.pgdat = pgdat,
 		.priority = 0,
 	};
 
@@ -1472,8 +1415,8 @@ static int mem_cgroup_soft_reclaim(struct mem_cgroup *root_memcg,
 			}
 			continue;
 		}
-		total += mem_cgroup_shrink_node_zone(victim, gfp_mask, false,
-						     zone, &nr_scanned);
+		total += mem_cgroup_shrink_node(victim, gfp_mask, false,
+					pgdat, &nr_scanned);
 		*total_scanned += nr_scanned;
 		if (!soft_limit_excess(root_memcg))
 			break;
@@ -1608,7 +1551,7 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 
 static void mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
-	if (!current->memcg_may_oom || current->memcg_in_oom)
+	if (!current->memcg_may_oom)
 		return;
 	/*
 	 * We are in the middle of the charge context here, so we
@@ -2106,11 +2049,11 @@ static void lock_page_lru(struct page *page, int *isolated)
 {
 	struct zone *zone = page_zone(page);
 
-	spin_lock_irq(&zone->lru_lock);
+	spin_lock_irq(zone_lru_lock(zone));
 	if (PageLRU(page)) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
 		ClearPageLRU(page);
 		del_page_from_lru_list(page, lruvec, page_lru(page));
 		*isolated = 1;
@@ -2125,12 +2068,12 @@ static void unlock_page_lru(struct page *page, int isolated)
 	if (isolated) {
 		struct lruvec *lruvec;
 
-		lruvec = mem_cgroup_page_lruvec(page, zone);
+		lruvec = mem_cgroup_page_lruvec(page, zone->zone_pgdat);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
 		SetPageLRU(page);
 		add_page_to_lru_list(page, lruvec, page_lru(page));
 	}
-	spin_unlock_irq(&zone->lru_lock);
+	spin_unlock_irq(zone_lru_lock(zone));
 }
 
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
@@ -2272,20 +2215,30 @@ static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg,
 	current->memcg_kmem_skip_account = 0;
 }
 
-/*
+static inline bool memcg_kmem_bypass(void)
+{
+	if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD))
+		return true;
+	return false;
+}
+
+/**
+ * memcg_kmem_get_cache: select the correct per-memcg cache for allocation
+ * @cachep: the original global kmem cache
+ *
  * Return the kmem_cache we're supposed to use for a slab allocation.
  * We try to use the current memcg's version of the cache.
  *
- * If the cache does not exist yet, if we are the first user of it,
- * we either create it immediately, if possible, or create it asynchronously
- * in a workqueue.
- * In the latter case, we will let the current allocation go through with
- * the original cache.
+ * If the cache does not exist yet, if we are the first user of it, we
+ * create it asynchronously in a workqueue and let the current allocation
+ * go through with the original cache.
  *
- * Can't be called in interrupt context or from kernel threads.
- * This function needs to be called with rcu_read_lock() held.
+ * This function takes a reference to the cache it returns to assure it
+ * won't get destroyed while we are working with it. Once the caller is
+ * done with it, memcg_kmem_put_cache() must be called to release the
+ * reference.
  */
-struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
+struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep)
 {
 	struct mem_cgroup *memcg;
 	struct kmem_cache *memcg_cachep;
@@ -2293,10 +2246,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, gfp_t gfp)
 
 	VM_BUG_ON(!is_root_cache(cachep));
 
-	if (cachep->flags & SLAB_ACCOUNT)
-		gfp |= __GFP_ACCOUNT;
-
-	if (!(gfp & __GFP_ACCOUNT))
+	if (memcg_kmem_bypass())
 		return cachep;
 
 	if (current->memcg_kmem_skip_account)
@@ -2329,14 +2279,27 @@ out:
 	return cachep;
 }
 
-void __memcg_kmem_put_cache(struct kmem_cache *cachep)
+/**
+ * memcg_kmem_put_cache: drop reference taken by memcg_kmem_get_cache
+ * @cachep: the cache returned by memcg_kmem_get_cache
+ */
+void memcg_kmem_put_cache(struct kmem_cache *cachep)
 {
 	if (!is_root_cache(cachep))
 		css_put(&cachep->memcg_params.memcg->css);
 }
 
-int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
-			      struct mem_cgroup *memcg)
+/**
+ * memcg_kmem_charge: charge a kmem page
+ * @page: page to charge
+ * @gfp: reclaim mode
+ * @order: allocation order
+ * @memcg: memory cgroup to charge
+ *
+ * Returns 0 on success, an error code on failure.
+ */
+int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
+			    struct mem_cgroup *memcg)
 {
 	unsigned int nr_pages = 1 << order;
 	struct page_counter *counter;
@@ -2357,19 +2320,34 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 	return 0;
 }
 
-int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+/**
+ * memcg_kmem_charge: charge a kmem page to the current memory cgroup
+ * @page: page to charge
+ * @gfp: reclaim mode
+ * @order: allocation order
+ *
+ * Returns 0 on success, an error code on failure.
+ */
+int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
 {
 	struct mem_cgroup *memcg;
 	int ret = 0;
 
+	if (memcg_kmem_bypass())
+		return 0;
+
 	memcg = get_mem_cgroup_from_mm(current->mm);
 	if (!mem_cgroup_is_root(memcg))
-		ret = __memcg_kmem_charge_memcg(page, gfp, order, memcg);
+		ret = memcg_kmem_charge_memcg(page, gfp, order, memcg);
 	css_put(&memcg->css);
 	return ret;
 }
-
-void __memcg_kmem_uncharge(struct page *page, int order)
+/**
+ * memcg_kmem_uncharge: uncharge a kmem page
+ * @page: page to uncharge
+ * @order: allocation order
+ */
+void memcg_kmem_uncharge(struct page *page, int order)
 {
 	struct mem_cgroup *memcg = page->mem_cgroup;
 	unsigned int nr_pages = 1 << order;
@@ -2395,7 +2373,7 @@ void __memcg_kmem_uncharge(struct page *page, int order)
 
 /*
  * Because tail pages are not marked as "used", set it. We're under
- * zone->lru_lock and migration entries setup in all page mappings.
+ * zone_lru_lock and migration entries setup in all page mappings.
  */
 void mem_cgroup_split_huge_fixup(struct page *head)
 {
@@ -2565,22 +2543,22 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 	return ret;
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 					    gfp_t gfp_mask,
 					    unsigned long *total_scanned)
 {
 	unsigned long nr_reclaimed = 0;
-	struct mem_cgroup_per_zone *mz, *next_mz = NULL;
+	struct mem_cgroup_per_node *mz, *next_mz = NULL;
 	unsigned long reclaimed;
 	int loop = 0;
-	struct mem_cgroup_tree_per_zone *mctz;
+	struct mem_cgroup_tree_per_node *mctz;
 	unsigned long excess;
 	unsigned long nr_scanned;
 
 	if (order > 0)
 		return 0;
 
-	mctz = soft_limit_tree_node_zone(zone_to_nid(zone), zone_idx(zone));
+	mctz = soft_limit_tree_node(pgdat->node_id);
 	/*
 	 * This loop can run a while, specially if mem_cgroup's continuously
 	 * keep exceeding their soft limit and putting the system under
@@ -2595,7 +2573,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			break;
 
 		nr_scanned = 0;
-		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, pgdat,
 						    gfp_mask, &nr_scanned);
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
@@ -3216,22 +3194,21 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 
 #ifdef CONFIG_DEBUG_VM
 	{
-		int nid, zid;
-		struct mem_cgroup_per_zone *mz;
+		pg_data_t *pgdat;
+		struct mem_cgroup_per_node *mz;
 		struct zone_reclaim_stat *rstat;
 		unsigned long recent_rotated[2] = {0, 0};
 		unsigned long recent_scanned[2] = {0, 0};
 
-		for_each_online_node(nid)
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				mz = &memcg->nodeinfo[nid]->zoneinfo[zid];
-				rstat = &mz->lruvec.reclaim_stat;
+		for_each_online_pgdat(pgdat) {
+			mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+			rstat = &mz->lruvec.reclaim_stat;
 
-				recent_rotated[0] += rstat->recent_rotated[0];
-				recent_rotated[1] += rstat->recent_rotated[1];
-				recent_scanned[0] += rstat->recent_scanned[0];
-				recent_scanned[1] += rstat->recent_scanned[1];
-			}
+			recent_rotated[0] += rstat->recent_rotated[0];
+			recent_rotated[1] += rstat->recent_rotated[1];
+			recent_scanned[0] += rstat->recent_scanned[0];
+			recent_scanned[1] += rstat->recent_scanned[1];
+		}
 		seq_printf(m, "recent_rotated_anon %lu\n", recent_rotated[0]);
 		seq_printf(m, "recent_rotated_file %lu\n", recent_rotated[1]);
 		seq_printf(m, "recent_scanned_anon %lu\n", recent_scanned[0]);
@@ -4057,11 +4034,64 @@ static struct cftype mem_cgroup_legacy_files[] = {
 	{ },	/* terminate */
 };
 
-static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
+/*
+ * Private memory cgroup IDR
+ *
+ * Swap-out records and page cache shadow entries need to store memcg
+ * references in constrained space, so we maintain an ID space that is
+ * limited to 16 bit (MEM_CGROUP_ID_MAX), limiting the total number of
+ * memory-controlled cgroups to 64k.
+ *
+ * However, there usually are many references to the oflline CSS after
+ * the cgroup has been destroyed, such as page cache or reclaimable
+ * slab objects, that don't need to hang on to the ID. We want to keep
+ * those dead CSS from occupying IDs, or we might quickly exhaust the
+ * relatively small ID space and prevent the creation of new cgroups
+ * even when there are much fewer than 64k cgroups - possibly none.
+ *
+ * Maintain a private 16-bit ID space for memcg, and allow the ID to
+ * be freed and recycled when it's no longer needed, which is usually
+ * when the CSS is offlined.
+ *
+ * The only exception to that are records of swapped out tmpfs/shmem
+ * pages that need to be attributed to live ancestors on swapin. But
+ * those references are manageable from userspace.
+ */
+
+static DEFINE_IDR(mem_cgroup_idr);
+
+static void mem_cgroup_id_get(struct mem_cgroup *memcg)
+{
+	atomic_inc(&memcg->id.ref);
+}
+
+static void mem_cgroup_id_put(struct mem_cgroup *memcg)
+{
+	if (atomic_dec_and_test(&memcg->id.ref)) {
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
+		memcg->id.id = 0;
+
+		/* Memcg ID pins CSS */
+		css_put(&memcg->css);
+	}
+}
+
+/**
+ * mem_cgroup_from_id - look up a memcg from a memcg id
+ * @id: the memcg id to look up
+ *
+ * Caller must hold rcu_read_lock().
+ */
+struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return idr_find(&mem_cgroup_idr, id);
+}
+
+static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
-	struct mem_cgroup_per_zone *mz;
-	int zone, tmp = node;
+	int tmp = node;
 	/*
 	 * This routine is called against possible nodes.
 	 * But it's BUG to call kmalloc() against offline node.
@@ -4076,18 +4106,16 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 	if (!pn)
 		return 1;
 
-	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-		mz = &pn->zoneinfo[zone];
-		lruvec_init(&mz->lruvec);
-		mz->usage_in_excess = 0;
-		mz->on_tree = false;
-		mz->memcg = memcg;
-	}
+	lruvec_init(&pn->lruvec);
+	pn->usage_in_excess = 0;
+	pn->on_tree = false;
+	pn->memcg = memcg;
+
 	memcg->nodeinfo[node] = pn;
 	return 0;
 }
 
-static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
+static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node)
 {
 	kfree(memcg->nodeinfo[node]);
 }
@@ -4098,7 +4126,7 @@ static void mem_cgroup_free(struct mem_cgroup *memcg)
 
 	memcg_wb_domain_exit(memcg);
 	for_each_node(node)
-		free_mem_cgroup_per_zone_info(memcg, node);
+		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->stat);
 	kfree(memcg);
 }
@@ -4116,12 +4144,18 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (!memcg)
 		return NULL;
 
+	memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
+				 1, MEM_CGROUP_ID_MAX,
+				 GFP_KERNEL);
+	if (memcg->id.id < 0)
+		goto fail;
+
 	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
 	if (!memcg->stat)
 		goto fail;
 
 	for_each_node(node)
-		if (alloc_mem_cgroup_per_zone_info(memcg, node))
+		if (alloc_mem_cgroup_per_node_info(memcg, node))
 			goto fail;
 
 	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
@@ -4142,8 +4176,11 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&memcg->cgwb_list);
 #endif
+	idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
 	return memcg;
 fail:
+	if (memcg->id.id > 0)
+		idr_remove(&mem_cgroup_idr, memcg->id.id);
 	mem_cgroup_free(memcg);
 	return NULL;
 }
@@ -4203,15 +4240,14 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
 	return &memcg->css;
 fail:
 	mem_cgroup_free(memcg);
-	return NULL;
+	return ERR_PTR(-ENOMEM);
 }
 
-static int
-mem_cgroup_css_online(struct cgroup_subsys_state *css)
+static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 {
-	if (css->id > MEM_CGROUP_ID_MAX)
-		return -ENOSPC;
-
+	/* Online state pins memcg ID, memcg ID pins CSS */
+	mem_cgroup_id_get(mem_cgroup_from_css(css));
+	css_get(css);
 	return 0;
 }
 
@@ -4234,6 +4270,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 
 	memcg_offline_kmem(memcg);
 	wb_memcg_offline(memcg);
+
+	mem_cgroup_id_put(memcg);
 }
 
 static void mem_cgroup_css_released(struct cgroup_subsys_state *css)
@@ -4345,7 +4383,7 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma,
 
 #ifdef CONFIG_SWAP
 static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
-			unsigned long addr, pte_t ptent, swp_entry_t *entry)
+			pte_t ptent, swp_entry_t *entry)
 {
 	struct page *page = NULL;
 	swp_entry_t ent = pte_to_swp_entry(ptent);
@@ -4364,7 +4402,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 }
 #else
 static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
-			unsigned long addr, pte_t ptent, swp_entry_t *entry)
+			pte_t ptent, swp_entry_t *entry)
 {
 	return NULL;
 }
@@ -4407,7 +4445,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 /**
  * mem_cgroup_move_account - move account of the page
  * @page: the page
- * @nr_pages: number of regular pages (>1 for huge pages)
+ * @compound: charge the page as compound or small page
  * @from: mem_cgroup which the page is moved from.
  * @to:	mem_cgroup which the page is moved to. @from != @to.
  *
@@ -4529,7 +4567,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 	if (pte_present(ptent))
 		page = mc_handle_present_pte(vma, addr, ptent);
 	else if (is_swap_pte(ptent))
-		page = mc_handle_swap_pte(vma, addr, ptent, &ent);
+		page = mc_handle_swap_pte(vma, ptent, &ent);
 	else if (pte_none(ptent))
 		page = mc_handle_file_pte(vma, addr, ptent, &ent);
 
@@ -5133,7 +5171,7 @@ static int memory_stat_show(struct seq_file *m, void *v)
 	seq_printf(m, "file %llu\n",
 		   (u64)stat[MEM_CGROUP_STAT_CACHE] * PAGE_SIZE);
 	seq_printf(m, "kernel_stack %llu\n",
-		   (u64)stat[MEMCG_KERNEL_STACK] * PAGE_SIZE);
+		   (u64)stat[MEMCG_KERNEL_STACK_KB] * 1024);
 	seq_printf(m, "slab %llu\n",
 		   (u64)(stat[MEMCG_SLAB_RECLAIMABLE] +
 			 stat[MEMCG_SLAB_UNRECLAIMABLE]) * PAGE_SIZE);
@@ -5269,6 +5307,7 @@ bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg)
  * @mm: mm context of the victim
  * @gfp_mask: reclaim mode
  * @memcgp: charged memcg return
+ * @compound: charge the page as compound or small page
  *
  * Try to charge @page to the memcg that @mm belongs to, reclaiming
  * pages according to @gfp_mask if necessary.
@@ -5331,6 +5370,7 @@ out:
  * @page: page to charge
  * @memcg: memcg to charge the page to
  * @lrucare: page might be on LRU already
+ * @compound: charge the page as compound or small page
  *
  * Finalize a charge transaction started by mem_cgroup_try_charge(),
  * after page->mapping has been set up.  This must happen atomically
@@ -5382,6 +5422,7 @@ void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
  * mem_cgroup_cancel_charge - cancel a page charge
  * @page: page to charge
  * @memcg: memcg to charge the page to
+ * @compound: charge the page as compound or small page
  *
  * Cancel a charge transaction started by mem_cgroup_try_charge().
  */
@@ -5405,15 +5446,18 @@ void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
 
 static void uncharge_batch(struct mem_cgroup *memcg, unsigned long pgpgout,
 			   unsigned long nr_anon, unsigned long nr_file,
-			   unsigned long nr_huge, struct page *dummy_page)
+			   unsigned long nr_huge, unsigned long nr_kmem,
+			   struct page *dummy_page)
 {
-	unsigned long nr_pages = nr_anon + nr_file;
+	unsigned long nr_pages = nr_anon + nr_file + nr_kmem;
 	unsigned long flags;
 
 	if (!mem_cgroup_is_root(memcg)) {
 		page_counter_uncharge(&memcg->memory, nr_pages);
 		if (do_memsw_account())
 			page_counter_uncharge(&memcg->memsw, nr_pages);
+		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && nr_kmem)
+			page_counter_uncharge(&memcg->kmem, nr_kmem);
 		memcg_oom_recover(memcg);
 	}
 
@@ -5436,6 +5480,7 @@ static void uncharge_list(struct list_head *page_list)
 	unsigned long nr_anon = 0;
 	unsigned long nr_file = 0;
 	unsigned long nr_huge = 0;
+	unsigned long nr_kmem = 0;
 	unsigned long pgpgout = 0;
 	struct list_head *next;
 	struct page *page;
@@ -5446,8 +5491,6 @@ static void uncharge_list(struct list_head *page_list)
 	 */
 	next = page_list->next;
 	do {
-		unsigned int nr_pages = 1;
-
 		page = list_entry(next, struct page, lru);
 		next = page->lru.next;
 
@@ -5466,31 +5509,34 @@ static void uncharge_list(struct list_head *page_list)
 		if (memcg != page->mem_cgroup) {
 			if (memcg) {
 				uncharge_batch(memcg, pgpgout, nr_anon, nr_file,
-					       nr_huge, page);
-				pgpgout = nr_anon = nr_file = nr_huge = 0;
+					       nr_huge, nr_kmem, page);
+				pgpgout = nr_anon = nr_file =
+					nr_huge = nr_kmem = 0;
 			}
 			memcg = page->mem_cgroup;
 		}
 
-		if (PageTransHuge(page)) {
-			nr_pages <<= compound_order(page);
-			VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-			nr_huge += nr_pages;
-		}
+		if (!PageKmemcg(page)) {
+			unsigned int nr_pages = 1;
 
-		if (PageAnon(page))
-			nr_anon += nr_pages;
-		else
-			nr_file += nr_pages;
+			if (PageTransHuge(page)) {
+				nr_pages <<= compound_order(page);
+				nr_huge += nr_pages;
+			}
+			if (PageAnon(page))
+				nr_anon += nr_pages;
+			else
+				nr_file += nr_pages;
+			pgpgout++;
+		} else
+			nr_kmem += 1 << compound_order(page);
 
 		page->mem_cgroup = NULL;
-
-		pgpgout++;
 	} while (next != page_list);
 
 	if (memcg)
 		uncharge_batch(memcg, pgpgout, nr_anon, nr_file,
-			       nr_huge, page);
+			       nr_huge, nr_kmem, page);
 }
 
 /**
@@ -5544,6 +5590,7 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 	struct mem_cgroup *memcg;
 	unsigned int nr_pages;
 	bool compound;
+	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
 	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
@@ -5574,10 +5621,10 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage)
 
 	commit_charge(newpage, memcg, false);
 
-	local_irq_disable();
+	local_irq_save(flags);
 	mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages);
 	memcg_check_events(memcg, newpage);
-	local_irq_enable();
+	local_irq_restore(flags);
 }
 
 DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key);
@@ -5711,18 +5758,12 @@ static int __init mem_cgroup_init(void)
 
 	for_each_node(node) {
 		struct mem_cgroup_tree_per_node *rtpn;
-		int zone;
 
 		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL,
 				    node_online(node) ? node : NUMA_NO_NODE);
 
-		for (zone = 0; zone < MAX_NR_ZONES; zone++) {
-			struct mem_cgroup_tree_per_zone *rtpz;
-
-			rtpz = &rtpn->rb_tree_per_zone[zone];
-			rtpz->rb_root = RB_ROOT;
-			spin_lock_init(&rtpz->lock);
-		}
+		rtpn->rb_root = RB_ROOT;
+		spin_lock_init(&rtpn->lock);
 		soft_limit_tree.rb_tree_per_node[node] = rtpn;
 	}
 
@@ -5755,6 +5796,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	if (!memcg)
 		return;
 
+	mem_cgroup_id_get(memcg);
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
 	VM_BUG_ON_PAGE(oldid, page);
 	mem_cgroup_swap_statistics(memcg, true);
@@ -5773,6 +5815,9 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
 	VM_BUG_ON(!irqs_disabled());
 	mem_cgroup_charge_statistics(memcg, page, false, -1);
 	memcg_check_events(memcg, page);
+
+	if (!mem_cgroup_is_root(memcg))
+		css_put(&memcg->css);
 }
 
 /*
@@ -5803,11 +5848,11 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry)
 	    !page_counter_try_charge(&memcg->swap, 1, &counter))
 		return -ENOMEM;
 
+	mem_cgroup_id_get(memcg);
 	oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg));
 	VM_BUG_ON_PAGE(oldid, page);
 	mem_cgroup_swap_statistics(memcg, true);
 
-	css_get(&memcg->css);
 	return 0;
 }
 
@@ -5836,7 +5881,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t entry)
 				page_counter_uncharge(&memcg->memsw, 1);
 		}
 		mem_cgroup_swap_statistics(memcg, false);
-		css_put(&memcg->css);
+		mem_cgroup_id_put(memcg);
 	}
 	rcu_read_unlock();
 }