Merge branch 'next' into for-linus

Prepare first set of updates for 3.10 merge window.

1 files changed, 1550 insertions, 323 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 7acf43bf04a2..2b552224f5cf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -10,6 +10,10 @@
  * Copyright (C) 2009 Nokia Corporation
  * Author: Kirill A. Shutemov
  *
+ * Kernel Memory Controller
+ * Copyright (C) 2012 Parallels Inc. and Google Inc.
+ * Authors: Glauber Costa and Suleiman Souhlal
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -59,6 +63,8 @@
 #include <trace/events/vmscan.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
+EXPORT_SYMBOL(mem_cgroup_subsys);
+
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 static struct mem_cgroup *root_mem_cgroup __read_mostly;
 
@@ -114,6 +120,14 @@ static const char * const mem_cgroup_events_names[] = {
 	"pgmajfault",
 };
 
+static const char * const mem_cgroup_lru_names[] = {
+	"inactive_anon",
+	"active_anon",
+	"inactive_file",
+	"active_file",
+	"unevictable",
+};
+
 /*
  * Per memcg event counter is incremented at every pagein/pageout. With THP,
  * it will be incremated by the number of pages. This counter is used for
@@ -166,7 +180,7 @@ struct mem_cgroup_per_node {
 };
 
 struct mem_cgroup_lru_info {
-	struct mem_cgroup_per_node *nodeinfo[MAX_NUMNODES];
+	struct mem_cgroup_per_node *nodeinfo[0];
 };
 
 /*
@@ -266,20 +280,14 @@ struct mem_cgroup {
 	};
 
 	/*
-	 * Per cgroup active and inactive list, similar to the
-	 * per zone LRU lists.
+	 * the counter to account for kernel memory usage.
 	 */
-	struct mem_cgroup_lru_info info;
-	int last_scanned_node;
-#if MAX_NUMNODES > 1
-	nodemask_t	scan_nodes;
-	atomic_t	numainfo_events;
-	atomic_t	numainfo_updating;
-#endif
+	struct res_counter kmem;
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
+	unsigned long kmem_account_flags; /* See KMEM_ACCOUNTED_*, below */
 
 	bool		oom_lock;
 	atomic_t	under_oom;
@@ -330,12 +338,86 @@ struct mem_cgroup {
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
 	struct tcp_memcontrol tcp_mem;
 #endif
+#if defined(CONFIG_MEMCG_KMEM)
+	/* analogous to slab_common's slab_caches list. per-memcg */
+	struct list_head memcg_slab_caches;
+	/* Not a spinlock, we can take a lot of time walking the list */
+	struct mutex slab_caches_mutex;
+        /* Index in the kmem_cache->memcg_params->memcg_caches array */
+	int kmemcg_id;
+#endif
+
+	int last_scanned_node;
+#if MAX_NUMNODES > 1
+	nodemask_t	scan_nodes;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
+#endif
+	/*
+	 * Per cgroup active and inactive list, similar to the
+	 * per zone LRU lists.
+	 *
+	 * WARNING: This has to be the last element of the struct. Don't
+	 * add new fields after this point.
+	 */
+	struct mem_cgroup_lru_info info;
+};
+
+static size_t memcg_size(void)
+{
+	return sizeof(struct mem_cgroup) +
+		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+}
+
+/* internal only representation about the status of kmem accounting. */
+enum {
+	KMEM_ACCOUNTED_ACTIVE = 0, /* accounted by this cgroup itself */
+	KMEM_ACCOUNTED_ACTIVATED, /* static key enabled. */
+	KMEM_ACCOUNTED_DEAD, /* dead memcg with pending kmem charges */
 };
 
+/* We account when limit is on, but only after call sites are patched */
+#define KMEM_ACCOUNTED_MASK \
+		((1 << KMEM_ACCOUNTED_ACTIVE) | (1 << KMEM_ACCOUNTED_ACTIVATED))
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline void memcg_kmem_set_active(struct mem_cgroup *memcg)
+{
+	set_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
+}
+
+static bool memcg_kmem_is_active(struct mem_cgroup *memcg)
+{
+	return test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_set_activated(struct mem_cgroup *memcg)
+{
+	set_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_clear_activated(struct mem_cgroup *memcg)
+{
+	clear_bit(KMEM_ACCOUNTED_ACTIVATED, &memcg->kmem_account_flags);
+}
+
+static void memcg_kmem_mark_dead(struct mem_cgroup *memcg)
+{
+	if (test_bit(KMEM_ACCOUNTED_ACTIVE, &memcg->kmem_account_flags))
+		set_bit(KMEM_ACCOUNTED_DEAD, &memcg->kmem_account_flags);
+}
+
+static bool memcg_kmem_test_and_clear_dead(struct mem_cgroup *memcg)
+{
+	return test_and_clear_bit(KMEM_ACCOUNTED_DEAD,
+				  &memcg->kmem_account_flags);
+}
+#endif
+
 /* Stuffs for move charges at task migration. */
 /*
- * Types of charges to be moved. "move_charge_at_immitgrate" is treated as a
- * left-shifted bitmap of these types.
+ * Types of charges to be moved. "move_charge_at_immitgrate" and
+ * "immigrate_flags" are treated as a left-shifted bitmap of these types.
  */
 enum move_type {
 	MOVE_CHARGE_TYPE_ANON,	/* private anonymous page and swap of it */
@@ -348,6 +430,7 @@ static struct move_charge_struct {
 	spinlock_t	  lock; /* for from, to */
 	struct mem_cgroup *from;
 	struct mem_cgroup *to;
+	unsigned long immigrate_flags;
 	unsigned long precharge;
 	unsigned long moved_charge;
 	unsigned long moved_swap;
@@ -360,14 +443,12 @@ static struct move_charge_struct {
 
 static bool move_anon(void)
 {
-	return test_bit(MOVE_CHARGE_TYPE_ANON,
-					&mc.to->move_charge_at_immigrate);
+	return test_bit(MOVE_CHARGE_TYPE_ANON, &mc.immigrate_flags);
 }
 
 static bool move_file(void)
 {
-	return test_bit(MOVE_CHARGE_TYPE_FILE,
-					&mc.to->move_charge_at_immigrate);
+	return test_bit(MOVE_CHARGE_TYPE_FILE, &mc.immigrate_flags);
 }
 
 /*
@@ -386,9 +467,13 @@ enum charge_type {
 };
 
 /* for encoding cft->private value on file */
-#define _MEM			(0)
-#define _MEMSWAP		(1)
-#define _OOM_TYPE		(2)
+enum res_type {
+	_MEM,
+	_MEMSWAP,
+	_OOM_TYPE,
+	_KMEM,
+};
+
 #define MEMFILE_PRIVATE(x, val)	((x) << 16 | (val))
 #define MEMFILE_TYPE(val)	((val) >> 16 & 0xffff)
 #define MEMFILE_ATTR(val)	((val) & 0xffff)
@@ -403,6 +488,13 @@ enum charge_type {
 #define MEM_CGROUP_RECLAIM_SHRINK_BIT	0x1
 #define MEM_CGROUP_RECLAIM_SHRINK	(1 << MEM_CGROUP_RECLAIM_SHRINK_BIT)
 
+/*
+ * The memcg_create_mutex will be held whenever a new cgroup is created.
+ * As a consequence, any change that needs to protect against new child cgroups
+ * appearing has to hold it as well.
+ */
+static DEFINE_MUTEX(memcg_create_mutex);
+
 static void mem_cgroup_get(struct mem_cgroup *memcg);
 static void mem_cgroup_put(struct mem_cgroup *memcg);
 
@@ -485,11 +577,81 @@ static void disarm_sock_keys(struct mem_cgroup *memcg)
 }
 #endif
 
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * This will be the memcg's index in each cache's ->memcg_params->memcg_caches.
+ * There are two main reasons for not using the css_id for this:
+ *  1) this works better in sparse environments, where we have a lot of memcgs,
+ *     but only a few kmem-limited. Or also, if we have, for instance, 200
+ *     memcgs, and none but the 200th is kmem-limited, we'd have to have a
+ *     200 entry array for that.
+ *
+ *  2) In order not to violate the cgroup API, we would like to do all memory
+ *     allocation in ->create(). At that point, we haven't yet allocated the
+ *     css_id. Having a separate index prevents us from messing with the cgroup
+ *     core for this
+ *
+ * The current size of the caches array is stored in
+ * memcg_limited_groups_array_size.  It will double each time we have to
+ * increase it.
+ */
+static DEFINE_IDA(kmem_limited_groups);
+int memcg_limited_groups_array_size;
+
+/*
+ * MIN_SIZE is different than 1, because we would like to avoid going through
+ * the alloc/free process all the time. In a small machine, 4 kmem-limited
+ * cgroups is a reasonable guess. In the future, it could be a parameter or
+ * tunable, but that is strictly not necessary.
+ *
+ * MAX_SIZE should be as large as the number of css_ids. Ideally, we could get
+ * this constant directly from cgroup, but it is understandable that this is
+ * better kept as an internal representation in cgroup.c. In any case, the
+ * css_id space is not getting any smaller, and we don't have to necessarily
+ * increase ours as well if it increases.
+ */
+#define MEMCG_CACHES_MIN_SIZE 4
+#define MEMCG_CACHES_MAX_SIZE 65535
+
+/*
+ * A lot of the calls to the cache allocation functions are expected to be
+ * inlined by the compiler. Since the calls to memcg_kmem_get_cache are
+ * conditional to this static branch, we'll have to allow modules that does
+ * kmem_cache_alloc and the such to see this symbol as well
+ */
+struct static_key memcg_kmem_enabled_key;
+EXPORT_SYMBOL(memcg_kmem_enabled_key);
+
+static void disarm_kmem_keys(struct mem_cgroup *memcg)
+{
+	if (memcg_kmem_is_active(memcg)) {
+		static_key_slow_dec(&memcg_kmem_enabled_key);
+		ida_simple_remove(&kmem_limited_groups, memcg->kmemcg_id);
+	}
+	/*
+	 * This check can't live in kmem destruction function,
+	 * since the charges will outlive the cgroup
+	 */
+	WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0);
+}
+#else
+static void disarm_kmem_keys(struct mem_cgroup *memcg)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+static void disarm_static_keys(struct mem_cgroup *memcg)
+{
+	disarm_sock_keys(memcg);
+	disarm_kmem_keys(memcg);
+}
+
 static void drain_all_stock_async(struct mem_cgroup *memcg);
 
 static struct mem_cgroup_per_zone *
 mem_cgroup_zoneinfo(struct mem_cgroup *memcg, int nid, int zid)
 {
+	VM_BUG_ON((unsigned)nid >= nr_node_ids);
 	return &memcg->info.nodeinfo[nid]->zoneinfo[zid];
 }
 
@@ -800,7 +962,7 @@ static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg,
 	int nid;
 	u64 total = 0;
 
-	for_each_node_state(nid, N_HIGH_MEMORY)
+	for_each_node_state(nid, N_MEMORY)
 		total += mem_cgroup_node_nr_lru_pages(memcg, nid, lru_mask);
 	return total;
 }
@@ -1015,13 +1177,10 @@ void mem_cgroup_iter_break(struct mem_cgroup *root,
 	     iter != NULL;				\
 	     iter = mem_cgroup_iter(NULL, iter, NULL))
 
-void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
+void __mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 {
 	struct mem_cgroup *memcg;
 
-	if (!mm)
-		return;
-
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	if (unlikely(!memcg))
@@ -1040,7 +1199,7 @@ void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 out:
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(mem_cgroup_count_vm_event);
+EXPORT_SYMBOL(__mem_cgroup_count_vm_event);
 
 /**
  * mem_cgroup_zone_lruvec - get the lru list vector for a zone and memcg
@@ -1055,12 +1214,24 @@ 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())
-		return &zone->lruvec;
+	if (mem_cgroup_disabled()) {
+		lruvec = &zone->lruvec;
+		goto out;
+	}
 
 	mz = mem_cgroup_zoneinfo(memcg, zone_to_nid(zone), zone_idx(zone));
-	return &mz->lruvec;
+	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;
 }
 
 /*
@@ -1087,9 +1258,12 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 	struct mem_cgroup_per_zone *mz;
 	struct mem_cgroup *memcg;
 	struct page_cgroup *pc;
+	struct lruvec *lruvec;
 
-	if (mem_cgroup_disabled())
-		return &zone->lruvec;
+	if (mem_cgroup_disabled()) {
+		lruvec = &zone->lruvec;
+		goto out;
+	}
 
 	pc = lookup_page_cgroup(page);
 	memcg = pc->mem_cgroup;
@@ -1107,7 +1281,16 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct zone *zone)
 		pc->mem_cgroup = memcg = root_mem_cgroup;
 
 	mz = page_cgroup_zoneinfo(memcg, page);
-	return &mz->lruvec;
+	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;
 }
 
 /**
@@ -1213,17 +1396,6 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec)
 	return inactive * inactive_ratio < active;
 }
 
-int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec)
-{
-	unsigned long active;
-	unsigned long inactive;
-
-	inactive = mem_cgroup_get_lru_size(lruvec, LRU_INACTIVE_FILE);
-	active = mem_cgroup_get_lru_size(lruvec, LRU_ACTIVE_FILE);
-
-	return (active > inactive);
-}
-
 #define mem_cgroup_from_res_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
@@ -1366,8 +1538,9 @@ static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
 	spin_unlock_irqrestore(&memcg->move_lock, *flags);
 }
 
+#define K(x) ((x) << (PAGE_SHIFT-10))
 /**
- * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode.
+ * mem_cgroup_print_oom_info: Print OOM information relevant to memory controller.
  * @memcg: The memory cgroup that went over limit
  * @p: Task that is going to be killed
  *
@@ -1385,8 +1558,10 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	 */
 	static char memcg_name[PATH_MAX];
 	int ret;
+	struct mem_cgroup *iter;
+	unsigned int i;
 
-	if (!memcg || !p)
+	if (!p)
 		return;
 
 	rcu_read_lock();
@@ -1405,7 +1580,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	}
 	rcu_read_unlock();
 
-	printk(KERN_INFO "Task in %s killed", memcg_name);
+	pr_info("Task in %s killed", memcg_name);
 
 	rcu_read_lock();
 	ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
@@ -1418,18 +1593,45 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	/*
 	 * Continues from above, so we don't need an KERN_ level
 	 */
-	printk(KERN_CONT " as a result of limit of %s\n", memcg_name);
+	pr_cont(" as a result of limit of %s\n", memcg_name);
 done:
 
-	printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n",
+	pr_info("memory: usage %llukB, limit %llukB, failcnt %llu\n",
 		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
 		res_counter_read_u64(&memcg->res, RES_FAILCNT));
-	printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, "
-		"failcnt %llu\n",
+	pr_info("memory+swap: usage %llukB, limit %llukB, failcnt %llu\n",
 		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
 		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
 		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
+	pr_info("kmem: usage %llukB, limit %llukB, failcnt %llu\n",
+		res_counter_read_u64(&memcg->kmem, RES_USAGE) >> 10,
+		res_counter_read_u64(&memcg->kmem, RES_LIMIT) >> 10,
+		res_counter_read_u64(&memcg->kmem, RES_FAILCNT));
+
+	for_each_mem_cgroup_tree(iter, memcg) {
+		pr_info("Memory cgroup stats");
+
+		rcu_read_lock();
+		ret = cgroup_path(iter->css.cgroup, memcg_name, PATH_MAX);
+		if (!ret)
+			pr_cont(" for %s", memcg_name);
+		rcu_read_unlock();
+		pr_cont(":");
+
+		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
+			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
+				continue;
+			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+				K(mem_cgroup_read_stat(iter, i)));
+		}
+
+		for (i = 0; i < NR_LRU_LISTS; i++)
+			pr_cont(" %s:%luKB", mem_cgroup_lru_names[i],
+				K(mem_cgroup_nr_lru_pages(iter, BIT(i))));
+
+		pr_cont("\n");
+	}
 }
 
 /*
@@ -1452,21 +1654,30 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
 	u64 limit;
-	u64 memsw;
 
 	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
-	limit += total_swap_pages << PAGE_SHIFT;
 
-	memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
 	/*
-	 * If memsw is finite and limits the amount of swap space available
-	 * to this memcg, return that limit.
+	 * Do not consider swap space if we cannot swap due to swappiness
 	 */
-	return min(limit, memsw);
+	if (mem_cgroup_swappiness(memcg)) {
+		u64 memsw;
+
+		limit += total_swap_pages << PAGE_SHIFT;
+		memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+
+		/*
+		 * If memsw is finite and limits the amount of swap space
+		 * available to this memcg, return that limit.
+		 */
+		limit = min(limit, memsw);
+	}
+
+	return limit;
 }
 
-void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-			      int order)
+static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order)
 {
 	struct mem_cgroup *iter;
 	unsigned long chosen_points = 0;
@@ -1611,9 +1822,9 @@ static void mem_cgroup_may_update_nodemask(struct mem_cgroup *memcg)
 		return;
 
 	/* make a nodemask where this memcg uses memory from */
-	memcg->scan_nodes = node_states[N_HIGH_MEMORY];
+	memcg->scan_nodes = node_states[N_MEMORY];
 
-	for_each_node_mask(nid, node_states[N_HIGH_MEMORY]) {
+	for_each_node_mask(nid, node_states[N_MEMORY]) {
 
 		if (!test_mem_cgroup_node_reclaimable(memcg, nid, false))
 			node_clear(nid, memcg->scan_nodes);
@@ -1684,7 +1895,7 @@ static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap)
 	/*
 	 * Check rest of nodes.
 	 */
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		if (node_isset(nid, memcg->scan_nodes))
 			continue;
 		if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap))
@@ -2028,20 +2239,28 @@ struct memcg_stock_pcp {
 static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
 static DEFINE_MUTEX(percpu_charge_mutex);
 
-/*
- * Try to consume stocked charge on this cpu. If success, one page is consumed
- * from local stock and true is returned. If the stock is 0 or charges from a
- * cgroup which is not current target, returns false. This stock will be
- * refilled.
+/**
+ * consume_stock: Try to consume stocked charge on this cpu.
+ * @memcg: memcg to consume from.
+ * @nr_pages: how many pages to charge.
+ *
+ * The charges will only happen if @memcg matches the current cpu's memcg
+ * stock, and at least @nr_pages are available in that stock.  Failure to
+ * service an allocation will refill the stock.
+ *
+ * returns true if successful, false otherwise.
  */
-static bool consume_stock(struct mem_cgroup *memcg)
+static bool consume_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
 	struct memcg_stock_pcp *stock;
 	bool ret = true;
 
+	if (nr_pages > CHARGE_BATCH)
+		return false;
+
 	stock = &get_cpu_var(memcg_stock);
-	if (memcg == stock->cached && stock->nr_pages)
-		stock->nr_pages--;
+	if (memcg == stock->cached && stock->nr_pages >= nr_pages)
+		stock->nr_pages -= nr_pages;
 	else /* need to call res_counter_charge */
 		ret = false;
 	put_cpu_var(memcg_stock);
@@ -2077,6 +2296,17 @@ static void drain_local_stock(struct work_struct *dummy)
 	clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
 }
 
+static void __init memcg_stock_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct memcg_stock_pcp *stock =
+					&per_cpu(memcg_stock, cpu);
+		INIT_WORK(&stock->work, drain_local_stock);
+	}
+}
+
 /*
  * Cache charges(val) which is from res_counter, to local per_cpu area.
  * This will be consumed by consume_stock() function, later.
@@ -2218,7 +2448,8 @@ enum {
 };
 
 static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
-				unsigned int nr_pages, bool oom_check)
+				unsigned int nr_pages, unsigned int min_pages,
+				bool oom_check)
 {
 	unsigned long csize = nr_pages * PAGE_SIZE;
 	struct mem_cgroup *mem_over_limit;
@@ -2241,18 +2472,18 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	} else
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
 	/*
-	 * nr_pages can be either a huge page (HPAGE_PMD_NR), a batch
-	 * of regular pages (CHARGE_BATCH), or a single regular page (1).
-	 *
 	 * Never reclaim on behalf of optional batching, retry with a
 	 * single page instead.
 	 */
-	if (nr_pages == CHARGE_BATCH)
+	if (nr_pages > min_pages)
 		return CHARGE_RETRY;
 
 	if (!(gfp_mask & __GFP_WAIT))
 		return CHARGE_WOULDBLOCK;
 
+	if (gfp_mask & __GFP_NORETRY)
+		return CHARGE_NOMEM;
+
 	ret = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
 		return CHARGE_RETRY;
@@ -2265,7 +2496,7 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * unlikely to succeed so close to the limit, and we fall back
 	 * to regular pages anyway in case of failure.
 	 */
-	if (nr_pages == 1 && ret)
+	if (nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER) && ret)
 		return CHARGE_RETRY;
 
 	/*
@@ -2337,10 +2568,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 again:
 	if (*ptr) { /* css should be a valid one */
 		memcg = *ptr;
-		VM_BUG_ON(css_is_removed(&memcg->css));
 		if (mem_cgroup_is_root(memcg))
 			goto done;
-		if (nr_pages == 1 && consume_stock(memcg))
+		if (consume_stock(memcg, nr_pages))
 			goto done;
 		css_get(&memcg->css);
 	} else {
@@ -2365,7 +2595,7 @@ again:
 			rcu_read_unlock();
 			goto done;
 		}
-		if (nr_pages == 1 && consume_stock(memcg)) {
+		if (consume_stock(memcg, nr_pages)) {
 			/*
 			 * It seems dagerous to access memcg without css_get().
 			 * But considering how consume_stok works, it's not
@@ -2400,7 +2630,8 @@ again:
 			nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
 		}
 
-		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, oom_check);
+		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch, nr_pages,
+		    oom_check);
 		switch (ret) {
 		case CHARGE_OK:
 			break;
@@ -2477,9 +2708,9 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 
 /*
  * A helper function to get mem_cgroup from ID. must be called under
- * rcu_read_lock(). The caller must check css_is_removed() or some if
- * it's concern. (dropping refcnt from swap can be called against removed
- * memcg.)
+ * rcu_read_lock().  The caller is responsible for calling css_tryget if
+ * the mem_cgroup is used for charging. (dropping refcnt from swap can be
+ * called against removed memcg.)
  */
 static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 {
@@ -2593,6 +2824,772 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	memcg_check_events(memcg, page);
 }
 
+static DEFINE_MUTEX(set_limit_mutex);
+
+#ifdef CONFIG_MEMCG_KMEM
+static inline bool memcg_can_account_kmem(struct mem_cgroup *memcg)
+{
+	return !mem_cgroup_disabled() && !mem_cgroup_is_root(memcg) &&
+		(memcg->kmem_account_flags & KMEM_ACCOUNTED_MASK);
+}
+
+/*
+ * This is a bit cumbersome, but it is rarely used and avoids a backpointer
+ * in the memcg_cache_params struct.
+ */
+static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p)
+{
+	struct kmem_cache *cachep;
+
+	VM_BUG_ON(p->is_root_cache);
+	cachep = p->root_cache;
+	return cachep->memcg_params->memcg_caches[memcg_cache_id(p->memcg)];
+}
+
+#ifdef CONFIG_SLABINFO
+static int mem_cgroup_slabinfo_read(struct cgroup *cont, struct cftype *cft,
+					struct seq_file *m)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	struct memcg_cache_params *params;
+
+	if (!memcg_can_account_kmem(memcg))
+		return -EIO;
+
+	print_slabinfo_header(m);
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_for_each_entry(params, &memcg->memcg_slab_caches, list)
+		cache_show(memcg_params_to_cache(params), m);
+	mutex_unlock(&memcg->slab_caches_mutex);
+
+	return 0;
+}
+#endif
+
+static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
+{
+	struct res_counter *fail_res;
+	struct mem_cgroup *_memcg;
+	int ret = 0;
+	bool may_oom;
+
+	ret = res_counter_charge(&memcg->kmem, size, &fail_res);
+	if (ret)
+		return ret;
+
+	/*
+	 * Conditions under which we can wait for the oom_killer. Those are
+	 * the same conditions tested by the core page allocator
+	 */
+	may_oom = (gfp & __GFP_FS) && !(gfp & __GFP_NORETRY);
+
+	_memcg = memcg;
+	ret = __mem_cgroup_try_charge(NULL, gfp, size >> PAGE_SHIFT,
+				      &_memcg, may_oom);
+
+	if (ret == -EINTR)  {
+		/*
+		 * __mem_cgroup_try_charge() chosed to bypass to root due to
+		 * OOM kill or fatal signal.  Since our only options are to
+		 * either fail the allocation or charge it to this cgroup, do
+		 * it as a temporary condition. But we can't fail. From a
+		 * kmem/slab perspective, the cache has already been selected,
+		 * by mem_cgroup_kmem_get_cache(), so it is too late to change
+		 * our minds.
+		 *
+		 * This condition will only trigger if the task entered
+		 * memcg_charge_kmem in a sane state, but was OOM-killed during
+		 * __mem_cgroup_try_charge() above. Tasks that were already
+		 * dying when the allocation triggers should have been already
+		 * directed to the root cgroup in memcontrol.h
+		 */
+		res_counter_charge_nofail(&memcg->res, size, &fail_res);
+		if (do_swap_account)
+			res_counter_charge_nofail(&memcg->memsw, size,
+						  &fail_res);
+		ret = 0;
+	} else if (ret)
+		res_counter_uncharge(&memcg->kmem, size);
+
+	return ret;
+}
+
+static void memcg_uncharge_kmem(struct mem_cgroup *memcg, u64 size)
+{
+	res_counter_uncharge(&memcg->res, size);
+	if (do_swap_account)
+		res_counter_uncharge(&memcg->memsw, size);
+
+	/* Not down to 0 */
+	if (res_counter_uncharge(&memcg->kmem, size))
+		return;
+
+	if (memcg_kmem_test_and_clear_dead(memcg))
+		mem_cgroup_put(memcg);
+}
+
+void memcg_cache_list_add(struct mem_cgroup *memcg, struct kmem_cache *cachep)
+{
+	if (!memcg)
+		return;
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches);
+	mutex_unlock(&memcg->slab_caches_mutex);
+}
+
+/*
+ * helper for acessing a memcg's index. It will be used as an index in the
+ * child cache array in kmem_cache, and also to derive its name. This function
+ * will return -1 when this is not a kmem-limited memcg.
+ */
+int memcg_cache_id(struct mem_cgroup *memcg)
+{
+	return memcg ? memcg->kmemcg_id : -1;
+}
+
+/*
+ * This ends up being protected by the set_limit mutex, during normal
+ * operation, because that is its main call site.
+ *
+ * But when we create a new cache, we can call this as well if its parent
+ * is kmem-limited. That will have to hold set_limit_mutex as well.
+ */
+int memcg_update_cache_sizes(struct mem_cgroup *memcg)
+{
+	int num, ret;
+
+	num = ida_simple_get(&kmem_limited_groups,
+				0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL);
+	if (num < 0)
+		return num;
+	/*
+	 * After this point, kmem_accounted (that we test atomically in
+	 * the beginning of this conditional), is no longer 0. This
+	 * guarantees only one process will set the following boolean
+	 * to true. We don't need test_and_set because we're protected
+	 * by the set_limit_mutex anyway.
+	 */
+	memcg_kmem_set_activated(memcg);
+
+	ret = memcg_update_all_caches(num+1);
+	if (ret) {
+		ida_simple_remove(&kmem_limited_groups, num);
+		memcg_kmem_clear_activated(memcg);
+		return ret;
+	}
+
+	memcg->kmemcg_id = num;
+	INIT_LIST_HEAD(&memcg->memcg_slab_caches);
+	mutex_init(&memcg->slab_caches_mutex);
+	return 0;
+}
+
+static size_t memcg_caches_array_size(int num_groups)
+{
+	ssize_t size;
+	if (num_groups <= 0)
+		return 0;
+
+	size = 2 * num_groups;
+	if (size < MEMCG_CACHES_MIN_SIZE)
+		size = MEMCG_CACHES_MIN_SIZE;
+	else if (size > MEMCG_CACHES_MAX_SIZE)
+		size = MEMCG_CACHES_MAX_SIZE;
+
+	return size;
+}
+
+/*
+ * We should update the current array size iff all caches updates succeed. This
+ * can only be done from the slab side. The slab mutex needs to be held when
+ * calling this.
+ */
+void memcg_update_array_size(int num)
+{
+	if (num > memcg_limited_groups_array_size)
+		memcg_limited_groups_array_size = memcg_caches_array_size(num);
+}
+
+static void kmem_cache_destroy_work_func(struct work_struct *w);
+
+int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
+{
+	struct memcg_cache_params *cur_params = s->memcg_params;
+
+	VM_BUG_ON(s->memcg_params && !s->memcg_params->is_root_cache);
+
+	if (num_groups > memcg_limited_groups_array_size) {
+		int i;
+		ssize_t size = memcg_caches_array_size(num_groups);
+
+		size *= sizeof(void *);
+		size += sizeof(struct memcg_cache_params);
+
+		s->memcg_params = kzalloc(size, GFP_KERNEL);
+		if (!s->memcg_params) {
+			s->memcg_params = cur_params;
+			return -ENOMEM;
+		}
+
+		INIT_WORK(&s->memcg_params->destroy,
+				kmem_cache_destroy_work_func);
+		s->memcg_params->is_root_cache = true;
+
+		/*
+		 * There is the chance it will be bigger than
+		 * memcg_limited_groups_array_size, if we failed an allocation
+		 * in a cache, in which case all caches updated before it, will
+		 * have a bigger array.
+		 *
+		 * But if that is the case, the data after
+		 * memcg_limited_groups_array_size is certainly unused
+		 */
+		for (i = 0; i < memcg_limited_groups_array_size; i++) {
+			if (!cur_params->memcg_caches[i])
+				continue;
+			s->memcg_params->memcg_caches[i] =
+						cur_params->memcg_caches[i];
+		}
+
+		/*
+		 * Ideally, we would wait until all caches succeed, and only
+		 * then free the old one. But this is not worth the extra
+		 * pointer per-cache we'd have to have for this.
+		 *
+		 * It is not a big deal if some caches are left with a size
+		 * bigger than the others. And all updates will reset this
+		 * anyway.
+		 */
+		kfree(cur_params);
+	}
+	return 0;
+}
+
+int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
+			 struct kmem_cache *root_cache)
+{
+	size_t size = sizeof(struct memcg_cache_params);
+
+	if (!memcg_kmem_enabled())
+		return 0;
+
+	if (!memcg)
+		size += memcg_limited_groups_array_size * sizeof(void *);
+
+	s->memcg_params = kzalloc(size, GFP_KERNEL);
+	if (!s->memcg_params)
+		return -ENOMEM;
+
+	INIT_WORK(&s->memcg_params->destroy,
+			kmem_cache_destroy_work_func);
+	if (memcg) {
+		s->memcg_params->memcg = memcg;
+		s->memcg_params->root_cache = root_cache;
+	} else
+		s->memcg_params->is_root_cache = true;
+
+	return 0;
+}
+
+void memcg_release_cache(struct kmem_cache *s)
+{
+	struct kmem_cache *root;
+	struct mem_cgroup *memcg;
+	int id;
+
+	/*
+	 * This happens, for instance, when a root cache goes away before we
+	 * add any memcg.
+	 */
+	if (!s->memcg_params)
+		return;
+
+	if (s->memcg_params->is_root_cache)
+		goto out;
+
+	memcg = s->memcg_params->memcg;
+	id  = memcg_cache_id(memcg);
+
+	root = s->memcg_params->root_cache;
+	root->memcg_params->memcg_caches[id] = NULL;
+	mem_cgroup_put(memcg);
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_del(&s->memcg_params->list);
+	mutex_unlock(&memcg->slab_caches_mutex);
+
+out:
+	kfree(s->memcg_params);
+}
+
+/*
+ * During the creation a new cache, we need to disable our accounting mechanism
+ * altogether. This is true even if we are not creating, but rather just
+ * enqueing new caches to be created.
+ *
+ * This is because that process will trigger allocations; some visible, like
+ * explicit kmallocs to auxiliary data structures, name strings and internal
+ * cache structures; some well concealed, like INIT_WORK() that can allocate
+ * objects during debug.
+ *
+ * If any allocation happens during memcg_kmem_get_cache, we will recurse back
+ * to it. This may not be a bounded recursion: since the first cache creation
+ * failed to complete (waiting on the allocation), we'll just try to create the
+ * cache again, failing at the same point.
+ *
+ * memcg_kmem_get_cache is prepared to abort after seeing a positive count of
+ * memcg_kmem_skip_account. So we enclose anything that might allocate memory
+ * inside the following two functions.
+ */
+static inline void memcg_stop_kmem_account(void)
+{
+	VM_BUG_ON(!current->mm);
+	current->memcg_kmem_skip_account++;
+}
+
+static inline void memcg_resume_kmem_account(void)
+{
+	VM_BUG_ON(!current->mm);
+	current->memcg_kmem_skip_account--;
+}
+
+static void kmem_cache_destroy_work_func(struct work_struct *w)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *p;
+
+	p = container_of(w, struct memcg_cache_params, destroy);
+
+	cachep = memcg_params_to_cache(p);
+
+	/*
+	 * If we get down to 0 after shrink, we could delete right away.
+	 * However, memcg_release_pages() already puts us back in the workqueue
+	 * in that case. If we proceed deleting, we'll get a dangling
+	 * reference, and removing the object from the workqueue in that case
+	 * is unnecessary complication. We are not a fast path.
+	 *
+	 * Note that this case is fundamentally different from racing with
+	 * shrink_slab(): if memcg_cgroup_destroy_cache() is called in
+	 * kmem_cache_shrink, not only we would be reinserting a dead cache
+	 * into the queue, but doing so from inside the worker racing to
+	 * destroy it.
+	 *
+	 * So if we aren't down to zero, we'll just schedule a worker and try
+	 * again
+	 */
+	if (atomic_read(&cachep->memcg_params->nr_pages) != 0) {
+		kmem_cache_shrink(cachep);
+		if (atomic_read(&cachep->memcg_params->nr_pages) == 0)
+			return;
+	} else
+		kmem_cache_destroy(cachep);
+}
+
+void mem_cgroup_destroy_cache(struct kmem_cache *cachep)
+{
+	if (!cachep->memcg_params->dead)
+		return;
+
+	/*
+	 * There are many ways in which we can get here.
+	 *
+	 * We can get to a memory-pressure situation while the delayed work is
+	 * still pending to run. The vmscan shrinkers can then release all
+	 * cache memory and get us to destruction. If this is the case, we'll
+	 * be executed twice, which is a bug (the second time will execute over
+	 * bogus data). In this case, cancelling the work should be fine.
+	 *
+	 * But we can also get here from the worker itself, if
+	 * kmem_cache_shrink is enough to shake all the remaining objects and
+	 * get the page count to 0. In this case, we'll deadlock if we try to
+	 * cancel the work (the worker runs with an internal lock held, which
+	 * is the same lock we would hold for cancel_work_sync().)
+	 *
+	 * Since we can't possibly know who got us here, just refrain from
+	 * running if there is already work pending
+	 */
+	if (work_pending(&cachep->memcg_params->destroy))
+		return;
+	/*
+	 * We have to defer the actual destroying to a workqueue, because
+	 * we might currently be in a context that cannot sleep.
+	 */
+	schedule_work(&cachep->memcg_params->destroy);
+}
+
+static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s)
+{
+	char *name;
+	struct dentry *dentry;
+
+	rcu_read_lock();
+	dentry = rcu_dereference(memcg->css.cgroup->dentry);
+	rcu_read_unlock();
+
+	BUG_ON(dentry == NULL);
+
+	name = kasprintf(GFP_KERNEL, "%s(%d:%s)", s->name,
+			 memcg_cache_id(memcg), dentry->d_name.name);
+
+	return name;
+}
+
+static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg,
+					 struct kmem_cache *s)
+{
+	char *name;
+	struct kmem_cache *new;
+
+	name = memcg_cache_name(memcg, s);
+	if (!name)
+		return NULL;
+
+	new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align,
+				      (s->flags & ~SLAB_PANIC), s->ctor, s);
+
+	if (new)
+		new->allocflags |= __GFP_KMEMCG;
+
+	kfree(name);
+	return new;
+}
+
+/*
+ * This lock protects updaters, not readers. We want readers to be as fast as
+ * they can, and they will either see NULL or a valid cache value. Our model
+ * allow them to see NULL, in which case the root memcg will be selected.
+ *
+ * We need this lock because multiple allocations to the same cache from a non
+ * will span more than one worker. Only one of them can create the cache.
+ */
+static DEFINE_MUTEX(memcg_cache_mutex);
+static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
+						  struct kmem_cache *cachep)
+{
+	struct kmem_cache *new_cachep;
+	int idx;
+
+	BUG_ON(!memcg_can_account_kmem(memcg));
+
+	idx = memcg_cache_id(memcg);
+
+	mutex_lock(&memcg_cache_mutex);
+	new_cachep = cachep->memcg_params->memcg_caches[idx];
+	if (new_cachep)
+		goto out;
+
+	new_cachep = kmem_cache_dup(memcg, cachep);
+	if (new_cachep == NULL) {
+		new_cachep = cachep;
+		goto out;
+	}
+
+	mem_cgroup_get(memcg);
+	atomic_set(&new_cachep->memcg_params->nr_pages , 0);
+
+	cachep->memcg_params->memcg_caches[idx] = new_cachep;
+	/*
+	 * the readers won't lock, make sure everybody sees the updated value,
+	 * so they won't put stuff in the queue again for no reason
+	 */
+	wmb();
+out:
+	mutex_unlock(&memcg_cache_mutex);
+	return new_cachep;
+}
+
+void kmem_cache_destroy_memcg_children(struct kmem_cache *s)
+{
+	struct kmem_cache *c;
+	int i;
+
+	if (!s->memcg_params)
+		return;
+	if (!s->memcg_params->is_root_cache)
+		return;
+
+	/*
+	 * If the cache is being destroyed, we trust that there is no one else
+	 * requesting objects from it. Even if there are, the sanity checks in
+	 * kmem_cache_destroy should caught this ill-case.
+	 *
+	 * Still, we don't want anyone else freeing memcg_caches under our
+	 * noses, which can happen if a new memcg comes to life. As usual,
+	 * we'll take the set_limit_mutex to protect ourselves against this.
+	 */
+	mutex_lock(&set_limit_mutex);
+	for (i = 0; i < memcg_limited_groups_array_size; i++) {
+		c = s->memcg_params->memcg_caches[i];
+		if (!c)
+			continue;
+
+		/*
+		 * We will now manually delete the caches, so to avoid races
+		 * we need to cancel all pending destruction workers and
+		 * proceed with destruction ourselves.
+		 *
+		 * kmem_cache_destroy() will call kmem_cache_shrink internally,
+		 * and that could spawn the workers again: it is likely that
+		 * the cache still have active pages until this very moment.
+		 * This would lead us back to mem_cgroup_destroy_cache.
+		 *
+		 * But that will not execute at all if the "dead" flag is not
+		 * set, so flip it down to guarantee we are in control.
+		 */
+		c->memcg_params->dead = false;
+		cancel_work_sync(&c->memcg_params->destroy);
+		kmem_cache_destroy(c);
+	}
+	mutex_unlock(&set_limit_mutex);
+}
+
+struct create_work {
+	struct mem_cgroup *memcg;
+	struct kmem_cache *cachep;
+	struct work_struct work;
+};
+
+static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+	struct kmem_cache *cachep;
+	struct memcg_cache_params *params;
+
+	if (!memcg_kmem_is_active(memcg))
+		return;
+
+	mutex_lock(&memcg->slab_caches_mutex);
+	list_for_each_entry(params, &memcg->memcg_slab_caches, list) {
+		cachep = memcg_params_to_cache(params);
+		cachep->memcg_params->dead = true;
+		schedule_work(&cachep->memcg_params->destroy);
+	}
+	mutex_unlock(&memcg->slab_caches_mutex);
+}
+
+static void memcg_create_cache_work_func(struct work_struct *w)
+{
+	struct create_work *cw;
+
+	cw = container_of(w, struct create_work, work);
+	memcg_create_kmem_cache(cw->memcg, cw->cachep);
+	/* Drop the reference gotten when we enqueued. */
+	css_put(&cw->memcg->css);
+	kfree(cw);
+}
+
+/*
+ * Enqueue the creation of a per-memcg kmem_cache.
+ * Called with rcu_read_lock.
+ */
+static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg,
+					 struct kmem_cache *cachep)
+{
+	struct create_work *cw;
+
+	cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT);
+	if (cw == NULL)
+		return;
+
+	/* The corresponding put will be done in the workqueue. */
+	if (!css_tryget(&memcg->css)) {
+		kfree(cw);
+		return;
+	}
+
+	cw->memcg = memcg;
+	cw->cachep = cachep;
+
+	INIT_WORK(&cw->work, memcg_create_cache_work_func);
+	schedule_work(&cw->work);
+}
+
+static void memcg_create_cache_enqueue(struct mem_cgroup *memcg,
+				       struct kmem_cache *cachep)
+{
+	/*
+	 * We need to stop accounting when we kmalloc, because if the
+	 * corresponding kmalloc cache is not yet created, the first allocation
+	 * in __memcg_create_cache_enqueue will recurse.
+	 *
+	 * However, it is better to enclose the whole function. Depending on
+	 * the debugging options enabled, INIT_WORK(), for instance, can
+	 * trigger an allocation. This too, will make us recurse. Because at
+	 * this point we can't allow ourselves back into memcg_kmem_get_cache,
+	 * the safest choice is to do it like this, wrapping the whole function.
+	 */
+	memcg_stop_kmem_account();
+	__memcg_create_cache_enqueue(memcg, cachep);
+	memcg_resume_kmem_account();
+}
+/*
+ * 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.
+ *
+ * Can't be called in interrupt context or from kernel threads.
+ * This function needs to be called with rcu_read_lock() held.
+ */
+struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep,
+					  gfp_t gfp)
+{
+	struct mem_cgroup *memcg;
+	int idx;
+
+	VM_BUG_ON(!cachep->memcg_params);
+	VM_BUG_ON(!cachep->memcg_params->is_root_cache);
+
+	if (!current->mm || current->memcg_kmem_skip_account)
+		return cachep;
+
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner));
+	rcu_read_unlock();
+
+	if (!memcg_can_account_kmem(memcg))
+		return cachep;
+
+	idx = memcg_cache_id(memcg);
+
+	/*
+	 * barrier to mare sure we're always seeing the up to date value.  The
+	 * code updating memcg_caches will issue a write barrier to match this.
+	 */
+	read_barrier_depends();
+	if (unlikely(cachep->memcg_params->memcg_caches[idx] == NULL)) {
+		/*
+		 * If we are in a safe context (can wait, and not in interrupt
+		 * context), we could be be predictable and return right away.
+		 * This would guarantee that the allocation being performed
+		 * already belongs in the new cache.
+		 *
+		 * However, there are some clashes that can arrive from locking.
+		 * For instance, because we acquire the slab_mutex while doing
+		 * kmem_cache_dup, this means no further allocation could happen
+		 * with the slab_mutex held.
+		 *
+		 * Also, because cache creation issue get_online_cpus(), this
+		 * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex,
+		 * that ends up reversed during cpu hotplug. (cpuset allocates
+		 * a bunch of GFP_KERNEL memory during cpuup). Due to all that,
+		 * better to defer everything.
+		 */
+		memcg_create_cache_enqueue(memcg, cachep);
+		return cachep;
+	}
+
+	return cachep->memcg_params->memcg_caches[idx];
+}
+EXPORT_SYMBOL(__memcg_kmem_get_cache);
+
+/*
+ * We need to verify if the allocation against current->mm->owner's memcg is
+ * possible for the given order. But the page is not allocated yet, so we'll
+ * need a further commit step to do the final arrangements.
+ *
+ * It is possible for the task to switch cgroups in this mean time, so at
+ * commit time, we can't rely on task conversion any longer.  We'll then use
+ * the handle argument to return to the caller which cgroup we should commit
+ * against. We could also return the memcg directly and avoid the pointer
+ * passing, but a boolean return value gives better semantics considering
+ * the compiled-out case as well.
+ *
+ * Returning true means the allocation is possible.
+ */
+bool
+__memcg_kmem_newpage_charge(gfp_t gfp, struct mem_cgroup **_memcg, int order)
+{
+	struct mem_cgroup *memcg;
+	int ret;
+
+	*_memcg = NULL;
+	memcg = try_get_mem_cgroup_from_mm(current->mm);
+
+	/*
+	 * very rare case described in mem_cgroup_from_task. Unfortunately there
+	 * isn't much we can do without complicating this too much, and it would
+	 * be gfp-dependent anyway. Just let it go
+	 */
+	if (unlikely(!memcg))
+		return true;
+
+	if (!memcg_can_account_kmem(memcg)) {
+		css_put(&memcg->css);
+		return true;
+	}
+
+	ret = memcg_charge_kmem(memcg, gfp, PAGE_SIZE << order);
+	if (!ret)
+		*_memcg = memcg;
+
+	css_put(&memcg->css);
+	return (ret == 0);
+}
+
+void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
+			      int order)
+{
+	struct page_cgroup *pc;
+
+	VM_BUG_ON(mem_cgroup_is_root(memcg));
+
+	/* The page allocation failed. Revert */
+	if (!page) {
+		memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+		return;
+	}
+
+	pc = lookup_page_cgroup(page);
+	lock_page_cgroup(pc);
+	pc->mem_cgroup = memcg;
+	SetPageCgroupUsed(pc);
+	unlock_page_cgroup(pc);
+}
+
+void __memcg_kmem_uncharge_pages(struct page *page, int order)
+{
+	struct mem_cgroup *memcg = NULL;
+	struct page_cgroup *pc;
+
+
+	pc = lookup_page_cgroup(page);
+	/*
+	 * Fast unlocked return. Theoretically might have changed, have to
+	 * check again after locking.
+	 */
+	if (!PageCgroupUsed(pc))
+		return;
+
+	lock_page_cgroup(pc);
+	if (PageCgroupUsed(pc)) {
+		memcg = pc->mem_cgroup;
+		ClearPageCgroupUsed(pc);
+	}
+	unlock_page_cgroup(pc);
+
+	/*
+	 * We trust that only if there is a memcg associated with the page, it
+	 * is a valid allocation
+	 */
+	if (!memcg)
+		return;
+
+	VM_BUG_ON(mem_cgroup_is_root(memcg));
+	memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
+}
+#else
+static inline void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 #define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION)
@@ -2676,13 +3673,6 @@ static int mem_cgroup_move_account(struct page *page,
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
 	mem_cgroup_charge_statistics(to, anon, nr_pages);
-	/*
-	 * We charges against "to" which may not have any tasks. Then, "to"
-	 * can be under rmdir(). But in current implementation, caller of
-	 * this function is just force_empty() and move charge, so it's
-	 * guaranteed that "to" is never removed. So, we don't check rmdir
-	 * status here.
-	 */
 	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
 unlock:
@@ -2696,10 +3686,27 @@ out:
 	return ret;
 }
 
-/*
- * move charges to its parent.
+/**
+ * mem_cgroup_move_parent - moves page to the parent group
+ * @page: the page to move
+ * @pc: page_cgroup of the page
+ * @child: page's cgroup
+ *
+ * move charges to its parent or the root cgroup if the group has no
+ * parent (aka use_hierarchy==0).
+ * Although this might fail (get_page_unless_zero, isolate_lru_page or
+ * mem_cgroup_move_account fails) the failure is always temporary and
+ * it signals a race with a page removal/uncharge or migration. In the
+ * first case the page is on the way out and it will vanish from the LRU
+ * on the next attempt and the call should be retried later.
+ * Isolation from the LRU fails only if page has been isolated from
+ * the LRU since we looked at it and that usually means either global
+ * reclaim or migration going on. The page will either get back to the
+ * LRU or vanish.
+ * Finaly mem_cgroup_move_account fails only if the page got uncharged
+ * (!PageCgroupUsed) or moved to a different group. The page will
+ * disappear in the next attempt.
  */
-
 static int mem_cgroup_move_parent(struct page *page,
 				  struct page_cgroup *pc,
 				  struct mem_cgroup *child)
@@ -2709,9 +3716,7 @@ static int mem_cgroup_move_parent(struct page *page,
 	unsigned long uninitialized_var(flags);
 	int ret;
 
-	/* Is ROOT ? */
-	if (mem_cgroup_is_root(child))
-		return -EINVAL;
+	VM_BUG_ON(mem_cgroup_is_root(child));
 
 	ret = -EBUSY;
 	if (!get_page_unless_zero(page))
@@ -2728,8 +3733,10 @@ static int mem_cgroup_move_parent(struct page *page,
 	if (!parent)
 		parent = root_mem_cgroup;
 
-	if (nr_pages > 1)
+	if (nr_pages > 1) {
+		VM_BUG_ON(!PageTransHuge(page));
 		flags = compound_lock_irqsave(page);
+	}
 
 	ret = mem_cgroup_move_account(page, nr_pages,
 				pc, child, parent);
@@ -2871,7 +3878,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		return;
 	if (!memcg)
 		return;
-	cgroup_exclude_rmdir(&memcg->css);
 
 	__mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
 	/*
@@ -2885,12 +3891,6 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 		swp_entry_t ent = {.val = page_private(page)};
 		mem_cgroup_uncharge_swap(ent);
 	}
-	/*
-	 * At swapin, we may charge account against cgroup which has no tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 void mem_cgroup_commit_charge_swapin(struct page *page,
@@ -3255,15 +4255,18 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 				  struct mem_cgroup **memcgp)
 {
 	struct mem_cgroup *memcg = NULL;
+	unsigned int nr_pages = 1;
 	struct page_cgroup *pc;
 	enum charge_type ctype;
 
 	*memcgp = NULL;
 
-	VM_BUG_ON(PageTransHuge(page));
 	if (mem_cgroup_disabled())
 		return;
 
+	if (PageTransHuge(page))
+		nr_pages <<= compound_order(page);
+
 	pc = lookup_page_cgroup(page);
 	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
@@ -3325,7 +4328,7 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 	 * charged to the res_counter since we plan on replacing the
 	 * old one and only one page is going to be left afterwards.
 	 */
-	__mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false);
+	__mem_cgroup_commit_charge(memcg, newpage, nr_pages, ctype, false);
 }
 
 /* remove redundant charge if migration failed*/
@@ -3338,8 +4341,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 
 	if (!memcg)
 		return;
-	/* blocks rmdir() */
-	cgroup_exclude_rmdir(&memcg->css);
+
 	if (!migration_ok) {
 		used = oldpage;
 		unused = newpage;
@@ -3373,13 +4375,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	 */
 	if (anon)
 		mem_cgroup_uncharge_page(used);
-	/*
-	 * At migration, we may charge account against cgroup which has no
-	 * tasks.
-	 * So, rmdir()->pre_destroy() can be called while we do this charge.
-	 * In that case, we need to call pre_destroy() again. check it here.
-	 */
-	cgroup_release_and_wakeup_rmdir(&memcg->css);
 }
 
 /*
@@ -3451,14 +4446,12 @@ void mem_cgroup_print_bad_page(struct page *page)
 
 	pc = lookup_page_cgroup_used(page);
 	if (pc) {
-		printk(KERN_ALERT "pc:%p pc->flags:%lx pc->mem_cgroup:%p\n",
-		       pc, pc->flags, pc->mem_cgroup);
+		pr_alert("pc:%p pc->flags:%lx pc->mem_cgroup:%p\n",
+			 pc, pc->flags, pc->mem_cgroup);
 	}
 }
 #endif
 
-static DEFINE_MUTEX(set_limit_mutex);
-
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
@@ -3679,30 +4672,32 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 	return nr_reclaimed;
 }
 
-/*
+/**
+ * mem_cgroup_force_empty_list - clears LRU of a group
+ * @memcg: group to clear
+ * @node: NUMA node
+ * @zid: zone id
+ * @lru: lru to to clear
+ *
  * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
- * reclaim the pages page themselves - it just removes the page_cgroups.
- * Returns true if some page_cgroups were not freed, indicating that the caller
- * must retry this operation.
+ * reclaim the pages page themselves - pages are moved to the parent (or root)
+ * group.
  */
-static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
+static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 				int node, int zid, enum lru_list lru)
 {
-	struct mem_cgroup_per_zone *mz;
-	unsigned long flags, loop;
+	struct lruvec *lruvec;
+	unsigned long flags;
 	struct list_head *list;
 	struct page *busy;
 	struct zone *zone;
 
 	zone = &NODE_DATA(node)->node_zones[zid];
-	mz = mem_cgroup_zoneinfo(memcg, node, zid);
-	list = &mz->lruvec.lists[lru];
+	lruvec = mem_cgroup_zone_lruvec(zone, memcg);
+	list = &lruvec->lists[lru];
 
-	loop = mz->lru_size[lru];
-	/* give some margin against EBUSY etc...*/
-	loop += 256;
 	busy = NULL;
-	while (loop--) {
+	do {
 		struct page_cgroup *pc;
 		struct page *page;
 
@@ -3728,76 +4723,107 @@ static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 			cond_resched();
 		} else
 			busy = NULL;
-	}
-	return !list_empty(list);
+	} while (!list_empty(list));
 }
 
 /*
- * make mem_cgroup's charge to be 0 if there is no task.
+ * make mem_cgroup's charge to be 0 if there is no task by moving
+ * all the charges and pages to the parent.
  * This enables deleting this mem_cgroup.
+ *
+ * Caller is responsible for holding css reference on the memcg.
  */
-static int mem_cgroup_force_empty(struct mem_cgroup *memcg, bool free_all)
+static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg)
 {
-	int ret;
-	int node, zid, shrink;
-	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct cgroup *cgrp = memcg->css.cgroup;
-
-	css_get(&memcg->css);
+	int node, zid;
+	u64 usage;
 
-	shrink = 0;
-	/* should free all ? */
-	if (free_all)
-		goto try_to_free;
-move_account:
 	do {
-		ret = -EBUSY;
-		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
-			goto out;
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
 		drain_all_stock_sync(memcg);
-		ret = 0;
 		mem_cgroup_start_move(memcg);
-		for_each_node_state(node, N_HIGH_MEMORY) {
-			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
+		for_each_node_state(node, N_MEMORY) {
+			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				enum lru_list lru;
 				for_each_lru(lru) {
-					ret = mem_cgroup_force_empty_list(memcg,
+					mem_cgroup_force_empty_list(memcg,
 							node, zid, lru);
-					if (ret)
-						break;
 				}
 			}
-			if (ret)
-				break;
 		}
 		mem_cgroup_end_move(memcg);
 		memcg_oom_recover(memcg);
 		cond_resched();
-	/* "ret" should also be checked to ensure all lists are empty. */
-	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
-out:
-	css_put(&memcg->css);
-	return ret;
 
-try_to_free:
+		/*
+		 * Kernel memory may not necessarily be trackable to a specific
+		 * process. So they are not migrated, and therefore we can't
+		 * expect their value to drop to 0 here.
+		 * Having res filled up with kmem only is enough.
+		 *
+		 * This is a safety check because mem_cgroup_force_empty_list
+		 * could have raced with mem_cgroup_replace_page_cache callers
+		 * so the lru seemed empty but the page could have been added
+		 * right after the check. RES_USAGE should be safe as we always
+		 * charge before adding to the LRU.
+		 */
+		usage = res_counter_read_u64(&memcg->res, RES_USAGE) -
+			res_counter_read_u64(&memcg->kmem, RES_USAGE);
+	} while (usage > 0);
+}
+
+/*
+ * This mainly exists for tests during the setting of set of use_hierarchy.
+ * Since this is the very setting we are changing, the current hierarchy value
+ * is meaningless
+ */
+static inline bool __memcg_has_children(struct mem_cgroup *memcg)
+{
+	struct cgroup *pos;
+
+	/* bounce at first found */
+	cgroup_for_each_child(pos, memcg->css.cgroup)
+		return true;
+	return false;
+}
+
+/*
+ * Must be called with memcg_create_mutex held, unless the cgroup is guaranteed
+ * to be already dead (as in mem_cgroup_force_empty, for instance).  This is
+ * from mem_cgroup_count_children(), in the sense that we don't really care how
+ * many children we have; we only need to know if we have any.  It also counts
+ * any memcg without hierarchy as infertile.
+ */
+static inline bool memcg_has_children(struct mem_cgroup *memcg)
+{
+	return memcg->use_hierarchy && __memcg_has_children(memcg);
+}
+
+/*
+ * Reclaims as many pages from the given memcg as possible and moves
+ * the rest to the parent.
+ *
+ * Caller is responsible for holding css reference for memcg.
+ */
+static int mem_cgroup_force_empty(struct mem_cgroup *memcg)
+{
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct cgroup *cgrp = memcg->css.cgroup;
+
 	/* returns EBUSY if there is a task or if we come here twice. */
-	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+		return -EBUSY;
+
 	/* we call try-to-free pages for make this cgroup empty */
 	lru_add_drain_all();
 	/* try to free all pages in this cgroup */
-	shrink = 1;
 	while (nr_retries && res_counter_read_u64(&memcg->res, RES_USAGE) > 0) {
 		int progress;
 
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			goto out;
-		}
+		if (signal_pending(current))
+			return -EINTR;
+
 		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL,
 						false);
 		if (!progress) {
@@ -3808,13 +4834,23 @@ try_to_free:
 
 	}
 	lru_add_drain();
-	/* try move_account...there may be some *locked* pages. */
-	goto move_account;
+	mem_cgroup_reparent_charges(memcg);
+
+	return 0;
 }
 
 static int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
 {
-	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	int ret;
+
+	if (mem_cgroup_is_root(memcg))
+		return -EINVAL;
+	css_get(&memcg->css);
+	ret = mem_cgroup_force_empty(memcg);
+	css_put(&memcg->css);
+
+	return ret;
 }
 
 
@@ -3834,7 +4870,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 	if (parent)
 		parent_memcg = mem_cgroup_from_cont(parent);
 
-	cgroup_lock();
+	mutex_lock(&memcg_create_mutex);
 
 	if (memcg->use_hierarchy == val)
 		goto out;
@@ -3849,7 +4885,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 	 */
 	if ((!parent_memcg || !parent_memcg->use_hierarchy) &&
 				(val == 1 || val == 0)) {
-		if (list_empty(&cont->children))
+		if (!__memcg_has_children(memcg))
 			memcg->use_hierarchy = val;
 		else
 			retval = -EBUSY;
@@ -3857,7 +4893,7 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 		retval = -EINVAL;
 
 out:
-	cgroup_unlock();
+	mutex_unlock(&memcg_create_mutex);
 
 	return retval;
 }
@@ -3905,7 +4941,8 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	char str[64];
 	u64 val;
-	int type, name, len;
+	int name, len;
+	enum res_type type;
 
 	type = MEMFILE_TYPE(cft->private);
 	name = MEMFILE_ATTR(cft->private);
@@ -3926,6 +4963,9 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
 		else
 			val = res_counter_read_u64(&memcg->memsw, name);
 		break;
+	case _KMEM:
+		val = res_counter_read_u64(&memcg->kmem, name);
+		break;
 	default:
 		BUG();
 	}
@@ -3933,6 +4973,101 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft,
 	len = scnprintf(str, sizeof(str), "%llu\n", (unsigned long long)val);
 	return simple_read_from_buffer(buf, nbytes, ppos, str, len);
 }
+
+static int memcg_update_kmem_limit(struct cgroup *cont, u64 val)
+{
+	int ret = -EINVAL;
+#ifdef CONFIG_MEMCG_KMEM
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	/*
+	 * For simplicity, we won't allow this to be disabled.  It also can't
+	 * be changed if the cgroup has children already, or if tasks had
+	 * already joined.
+	 *
+	 * If tasks join before we set the limit, a person looking at
+	 * kmem.usage_in_bytes will have no way to determine when it took
+	 * place, which makes the value quite meaningless.
+	 *
+	 * After it first became limited, changes in the value of the limit are
+	 * of course permitted.
+	 */
+	mutex_lock(&memcg_create_mutex);
+	mutex_lock(&set_limit_mutex);
+	if (!memcg->kmem_account_flags && val != RESOURCE_MAX) {
+		if (cgroup_task_count(cont) || memcg_has_children(memcg)) {
+			ret = -EBUSY;
+			goto out;
+		}
+		ret = res_counter_set_limit(&memcg->kmem, val);
+		VM_BUG_ON(ret);
+
+		ret = memcg_update_cache_sizes(memcg);
+		if (ret) {
+			res_counter_set_limit(&memcg->kmem, RESOURCE_MAX);
+			goto out;
+		}
+		static_key_slow_inc(&memcg_kmem_enabled_key);
+		/*
+		 * setting the active bit after the inc will guarantee no one
+		 * starts accounting before all call sites are patched
+		 */
+		memcg_kmem_set_active(memcg);
+
+		/*
+		 * kmem charges can outlive the cgroup. In the case of slab
+		 * pages, for instance, a page contain objects from various
+		 * processes, so it is unfeasible to migrate them away. We
+		 * need to reference count the memcg because of that.
+		 */
+		mem_cgroup_get(memcg);
+	} else
+		ret = res_counter_set_limit(&memcg->kmem, val);
+out:
+	mutex_unlock(&set_limit_mutex);
+	mutex_unlock(&memcg_create_mutex);
+#endif
+	return ret;
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+static int memcg_propagate_kmem(struct mem_cgroup *memcg)
+{
+	int ret = 0;
+	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
+	if (!parent)
+		goto out;
+
+	memcg->kmem_account_flags = parent->kmem_account_flags;
+	/*
+	 * When that happen, we need to disable the static branch only on those
+	 * memcgs that enabled it. To achieve this, we would be forced to
+	 * complicate the code by keeping track of which memcgs were the ones
+	 * that actually enabled limits, and which ones got it from its
+	 * parents.
+	 *
+	 * It is a lot simpler just to do static_key_slow_inc() on every child
+	 * that is accounted.
+	 */
+	if (!memcg_kmem_is_active(memcg))
+		goto out;
+
+	/*
+	 * destroy(), called if we fail, will issue static_key_slow_inc() and
+	 * mem_cgroup_put() if kmem is enabled. We have to either call them
+	 * unconditionally, or clear the KMEM_ACTIVE flag. I personally find
+	 * this more consistent, since it always leads to the same destroy path
+	 */
+	mem_cgroup_get(memcg);
+	static_key_slow_inc(&memcg_kmem_enabled_key);
+
+	mutex_lock(&set_limit_mutex);
+	ret = memcg_update_cache_sizes(memcg);
+	mutex_unlock(&set_limit_mutex);
+out:
+	return ret;
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 /*
  * The user of this function is...
  * RES_LIMIT.
@@ -3941,7 +5076,8 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 			    const char *buffer)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
-	int type, name;
+	enum res_type type;
+	int name;
 	unsigned long long val;
 	int ret;
 
@@ -3963,8 +5099,12 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 			break;
 		if (type == _MEM)
 			ret = mem_cgroup_resize_limit(memcg, val);
-		else
+		else if (type == _MEMSWAP)
 			ret = mem_cgroup_resize_memsw_limit(memcg, val);
+		else if (type == _KMEM)
+			ret = memcg_update_kmem_limit(cont, val);
+		else
+			return -EINVAL;
 		break;
 	case RES_SOFT_LIMIT:
 		ret = res_counter_memparse_write_strategy(buffer, &val);
@@ -4017,7 +5157,8 @@ out:
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
-	int type, name;
+	int name;
+	enum res_type type;
 
 	type = MEMFILE_TYPE(event);
 	name = MEMFILE_ATTR(event);
@@ -4029,14 +5170,22 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 	case RES_MAX_USAGE:
 		if (type == _MEM)
 			res_counter_reset_max(&memcg->res);
-		else
+		else if (type == _MEMSWAP)
 			res_counter_reset_max(&memcg->memsw);
+		else if (type == _KMEM)
+			res_counter_reset_max(&memcg->kmem);
+		else
+			return -EINVAL;
 		break;
 	case RES_FAILCNT:
 		if (type == _MEM)
 			res_counter_reset_failcnt(&memcg->res);
-		else
+		else if (type == _MEMSWAP)
 			res_counter_reset_failcnt(&memcg->memsw);
+		else if (type == _KMEM)
+			res_counter_reset_failcnt(&memcg->kmem);
+		else
+			return -EINVAL;
 		break;
 	}
 
@@ -4057,15 +5206,14 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
 
 	if (val >= (1 << NR_MOVE_TYPE))
 		return -EINVAL;
+
 	/*
-	 * We check this value several times in both in can_attach() and
-	 * attach(), so we need cgroup lock to prevent this value from being
-	 * inconsistent.
+	 * No kind of locking is needed in here, because ->can_attach() will
+	 * check this value once in the beginning of the process, and then carry
+	 * on with stale data. This means that changes to this value will only
+	 * affect task migrations starting after the change.
 	 */
-	cgroup_lock();
 	memcg->move_charge_at_immigrate = val;
-	cgroup_unlock();
-
 	return 0;
 }
 #else
@@ -4087,7 +5235,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL);
 	seq_printf(m, "total=%lu", total_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
@@ -4095,7 +5243,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE);
 	seq_printf(m, "file=%lu", file_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_FILE);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
@@ -4104,7 +5252,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON);
 	seq_printf(m, "anon=%lu", anon_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_ANON);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
@@ -4113,7 +5261,7 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 
 	unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE));
 	seq_printf(m, "unevictable=%lu", unevictable_nr);
-	for_each_node_state(nid, N_HIGH_MEMORY) {
+	for_each_node_state(nid, N_MEMORY) {
 		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				BIT(LRU_UNEVICTABLE));
 		seq_printf(m, " N%d=%lu", nid, node_nr);
@@ -4123,14 +5271,6 @@ static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 }
 #endif /* CONFIG_NUMA */
 
-static const char * const mem_cgroup_lru_names[] = {
-	"inactive_anon",
-	"active_anon",
-	"inactive_file",
-	"active_file",
-	"unevictable",
-};
-
 static inline void mem_cgroup_lru_names_not_uptodate(void)
 {
 	BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
@@ -4244,18 +5384,17 @@ static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
 
 	parent = mem_cgroup_from_cont(cgrp->parent);
 
-	cgroup_lock();
+	mutex_lock(&memcg_create_mutex);
 
 	/* If under hierarchy, only empty-root can set this value */
-	if ((parent->use_hierarchy) ||
-	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
-		cgroup_unlock();
+	if ((parent->use_hierarchy) || memcg_has_children(memcg)) {
+		mutex_unlock(&memcg_create_mutex);
 		return -EINVAL;
 	}
 
 	memcg->swappiness = val;
 
-	cgroup_unlock();
+	mutex_unlock(&memcg_create_mutex);
 
 	return 0;
 }
@@ -4353,7 +5492,7 @@ static int mem_cgroup_usage_register_event(struct cgroup *cgrp,
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 	u64 threshold, usage;
 	int i, size, ret;
 
@@ -4436,7 +5575,7 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_thresholds *thresholds;
 	struct mem_cgroup_threshold_ary *new;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 	u64 usage;
 	int i, j, size;
 
@@ -4514,7 +5653,7 @@ static int mem_cgroup_oom_register_event(struct cgroup *cgrp,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_eventfd_list *event;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 
 	BUG_ON(type != _OOM_TYPE);
 	event = kmalloc(sizeof(*event),	GFP_KERNEL);
@@ -4539,7 +5678,7 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
 	struct mem_cgroup_eventfd_list *ev, *tmp;
-	int type = MEMFILE_TYPE(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
 
 	BUG_ON(type != _OOM_TYPE);
 
@@ -4581,29 +5720,49 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 
 	parent = mem_cgroup_from_cont(cgrp->parent);
 
-	cgroup_lock();
+	mutex_lock(&memcg_create_mutex);
 	/* oom-kill-disable is a flag for subhierarchy. */
-	if ((parent->use_hierarchy) ||
-	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
-		cgroup_unlock();
+	if ((parent->use_hierarchy) || memcg_has_children(memcg)) {
+		mutex_unlock(&memcg_create_mutex);
 		return -EINVAL;
 	}
 	memcg->oom_kill_disable = val;
 	if (!val)
 		memcg_oom_recover(memcg);
-	cgroup_unlock();
+	mutex_unlock(&memcg_create_mutex);
 	return 0;
 }
 
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
+	int ret;
+
+	memcg->kmemcg_id = -1;
+	ret = memcg_propagate_kmem(memcg);
+	if (ret)
+		return ret;
+
 	return mem_cgroup_sockets_init(memcg, ss);
 };
 
 static void kmem_cgroup_destroy(struct mem_cgroup *memcg)
 {
 	mem_cgroup_sockets_destroy(memcg);
+
+	memcg_kmem_mark_dead(memcg);
+
+	if (res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0)
+		return;
+
+	/*
+	 * Charges already down to 0, undo mem_cgroup_get() done in the charge
+	 * path here, being careful not to race with memcg_uncharge_kmem: it is
+	 * possible that the charges went down to 0 between mark_dead and the
+	 * res_counter read, so in that case, we don't need the put
+	 */
+	if (memcg_kmem_test_and_clear_dead(memcg))
+		mem_cgroup_put(memcg);
 }
 #else
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
@@ -4685,7 +5844,42 @@ static struct cftype mem_cgroup_files[] = {
 		.read_seq_string = memcg_numa_stat_show,
 	},
 #endif
+#ifdef CONFIG_MEMCG_KMEM
+	{
+		.name = "kmem.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
+		.write_string = mem_cgroup_write,
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "kmem.usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "kmem.failcnt",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_FAILCNT),
+		.trigger = mem_cgroup_reset,
+		.read = mem_cgroup_read,
+	},
+	{
+		.name = "kmem.max_usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_KMEM, RES_MAX_USAGE),
+		.trigger = mem_cgroup_reset,
+		.read = mem_cgroup_read,
+	},
+#ifdef CONFIG_SLABINFO
+	{
+		.name = "kmem.slabinfo",
+		.read_seq_string = mem_cgroup_slabinfo_read,
+	},
+#endif
+#endif
+	{ },	/* terminate */
+};
+
 #ifdef CONFIG_MEMCG_SWAP
+static struct cftype memsw_cgroup_files[] = {
 	{
 		.name = "memsw.usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
@@ -4711,10 +5905,9 @@ static struct cftype mem_cgroup_files[] = {
 		.trigger = mem_cgroup_reset,
 		.read = mem_cgroup_read,
 	},
-#endif
 	{ },	/* terminate */
 };
-
+#endif
 static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
@@ -4736,7 +5929,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
-		lruvec_init(&mz->lruvec, &NODE_DATA(node)->node_zones[zone]);
+		lruvec_init(&mz->lruvec);
 		mz->usage_in_excess = 0;
 		mz->on_tree = false;
 		mz->memcg = memcg;
@@ -4753,9 +5946,9 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *memcg;
-	int size = sizeof(struct mem_cgroup);
+	size_t size = memcg_size();
 
-	/* Can be very big if MAX_NUMNODES is very big */
+	/* Can be very big if nr_node_ids is very big */
 	if (size < PAGE_SIZE)
 		memcg = kzalloc(size, GFP_KERNEL);
 	else
@@ -4779,16 +5972,29 @@ out_free:
 }
 
 /*
- * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU,
- * but in process context.  The work_freeing structure is overlaid
- * on the rcu_freeing structure, which itself is overlaid on memsw.
+ * At destroying mem_cgroup, references from swap_cgroup can remain.
+ * (scanning all at force_empty is too costly...)
+ *
+ * Instead of clearing all references at force_empty, we remember
+ * the number of reference from swap_cgroup and free mem_cgroup when
+ * it goes down to 0.
+ *
+ * Removal of cgroup itself succeeds regardless of refs from swap.
  */
-static void free_work(struct work_struct *work)
+
+static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg;
-	int size = sizeof(struct mem_cgroup);
+	int node;
+	size_t size = memcg_size();
+
+	mem_cgroup_remove_from_trees(memcg);
+	free_css_id(&mem_cgroup_subsys, &memcg->css);
+
+	for_each_node(node)
+		free_mem_cgroup_per_zone_info(memcg, node);
+
+	free_percpu(memcg->stat);
 
-	memcg = container_of(work, struct mem_cgroup, work_freeing);
 	/*
 	 * We need to make sure that (at least for now), the jump label
 	 * destruction code runs outside of the cgroup lock. This is because
@@ -4800,45 +6006,34 @@ static void free_work(struct work_struct *work)
 	 * to move this code around, and make sure it is outside
 	 * the cgroup_lock.
 	 */
-	disarm_sock_keys(memcg);
+	disarm_static_keys(memcg);
 	if (size < PAGE_SIZE)
 		kfree(memcg);
 	else
 		vfree(memcg);
 }
 
-static void free_rcu(struct rcu_head *rcu_head)
-{
-	struct mem_cgroup *memcg;
-
-	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
-	INIT_WORK(&memcg->work_freeing, free_work);
-	schedule_work(&memcg->work_freeing);
-}
 
 /*
- * At destroying mem_cgroup, references from swap_cgroup can remain.
- * (scanning all at force_empty is too costly...)
- *
- * Instead of clearing all references at force_empty, we remember
- * the number of reference from swap_cgroup and free mem_cgroup when
- * it goes down to 0.
- *
- * Removal of cgroup itself succeeds regardless of refs from swap.
+ * Helpers for freeing a kmalloc()ed/vzalloc()ed mem_cgroup by RCU,
+ * but in process context.  The work_freeing structure is overlaid
+ * on the rcu_freeing structure, which itself is overlaid on memsw.
  */
-
-static void __mem_cgroup_free(struct mem_cgroup *memcg)
+static void free_work(struct work_struct *work)
 {
-	int node;
+	struct mem_cgroup *memcg;
 
-	mem_cgroup_remove_from_trees(memcg);
-	free_css_id(&mem_cgroup_subsys, &memcg->css);
+	memcg = container_of(work, struct mem_cgroup, work_freeing);
+	__mem_cgroup_free(memcg);
+}
 
-	for_each_node(node)
-		free_mem_cgroup_per_zone_info(memcg, node);
+static void free_rcu(struct rcu_head *rcu_head)
+{
+	struct mem_cgroup *memcg;
 
-	free_percpu(memcg->stat);
-	call_rcu(&memcg->rcu_freeing, free_rcu);
+	memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing);
+	INIT_WORK(&memcg->work_freeing, free_work);
+	schedule_work(&memcg->work_freeing);
 }
 
 static void mem_cgroup_get(struct mem_cgroup *memcg)
@@ -4850,7 +6045,7 @@ static void __mem_cgroup_put(struct mem_cgroup *memcg, int count)
 {
 	if (atomic_sub_and_test(count, &memcg->refcnt)) {
 		struct mem_cgroup *parent = parent_mem_cgroup(memcg);
-		__mem_cgroup_free(memcg);
+		call_rcu(&memcg->rcu_freeing, free_rcu);
 		if (parent)
 			mem_cgroup_put(parent);
 	}
@@ -4872,19 +6067,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
-#ifdef CONFIG_MEMCG_SWAP
-static void __init enable_swap_cgroup(void)
-{
-	if (!mem_cgroup_disabled() && really_do_swap_account)
-		do_swap_account = 1;
-}
-#else
-static void __init enable_swap_cgroup(void)
-{
-}
-#endif
-
-static int mem_cgroup_soft_limit_tree_init(void)
+static void __init mem_cgroup_soft_limit_tree_init(void)
 {
 	struct mem_cgroup_tree_per_node *rtpn;
 	struct mem_cgroup_tree_per_zone *rtpz;
@@ -4895,8 +6078,7 @@ static int mem_cgroup_soft_limit_tree_init(void)
 		if (!node_state(node, N_NORMAL_MEMORY))
 			tmp = -1;
 		rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp);
-		if (!rtpn)
-			goto err_cleanup;
+		BUG_ON(!rtpn);
 
 		soft_limit_tree.rb_tree_per_node[node] = rtpn;
 
@@ -4906,23 +6088,12 @@ static int mem_cgroup_soft_limit_tree_init(void)
 			spin_lock_init(&rtpz->lock);
 		}
 	}
-	return 0;
-
-err_cleanup:
-	for_each_node(node) {
-		if (!soft_limit_tree.rb_tree_per_node[node])
-			break;
-		kfree(soft_limit_tree.rb_tree_per_node[node]);
-		soft_limit_tree.rb_tree_per_node[node] = NULL;
-	}
-	return 1;
-
 }
 
 static struct cgroup_subsys_state * __ref
-mem_cgroup_create(struct cgroup *cont)
+mem_cgroup_css_alloc(struct cgroup *cont)
 {
-	struct mem_cgroup *memcg, *parent;
+	struct mem_cgroup *memcg;
 	long error = -ENOMEM;
 	int node;
 
@@ -4936,27 +6107,48 @@ mem_cgroup_create(struct cgroup *cont)
 
 	/* root ? */
 	if (cont->parent == NULL) {
-		int cpu;
-		enable_swap_cgroup();
-		parent = NULL;
-		if (mem_cgroup_soft_limit_tree_init())
-			goto free_out;
 		root_mem_cgroup = memcg;
-		for_each_possible_cpu(cpu) {
-			struct memcg_stock_pcp *stock =
-						&per_cpu(memcg_stock, cpu);
-			INIT_WORK(&stock->work, drain_local_stock);
-		}
-		hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
-	} else {
-		parent = mem_cgroup_from_cont(cont->parent);
-		memcg->use_hierarchy = parent->use_hierarchy;
-		memcg->oom_kill_disable = parent->oom_kill_disable;
+		res_counter_init(&memcg->res, NULL);
+		res_counter_init(&memcg->memsw, NULL);
+		res_counter_init(&memcg->kmem, NULL);
 	}
 
-	if (parent && parent->use_hierarchy) {
+	memcg->last_scanned_node = MAX_NUMNODES;
+	INIT_LIST_HEAD(&memcg->oom_notify);
+	atomic_set(&memcg->refcnt, 1);
+	memcg->move_charge_at_immigrate = 0;
+	mutex_init(&memcg->thresholds_lock);
+	spin_lock_init(&memcg->move_lock);
+
+	return &memcg->css;
+
+free_out:
+	__mem_cgroup_free(memcg);
+	return ERR_PTR(error);
+}
+
+static int
+mem_cgroup_css_online(struct cgroup *cont)
+{
+	struct mem_cgroup *memcg, *parent;
+	int error = 0;
+
+	if (!cont->parent)
+		return 0;
+
+	mutex_lock(&memcg_create_mutex);
+	memcg = mem_cgroup_from_cont(cont);
+	parent = mem_cgroup_from_cont(cont->parent);
+
+	memcg->use_hierarchy = parent->use_hierarchy;
+	memcg->oom_kill_disable = parent->oom_kill_disable;
+	memcg->swappiness = mem_cgroup_swappiness(parent);
+
+	if (parent->use_hierarchy) {
 		res_counter_init(&memcg->res, &parent->res);
 		res_counter_init(&memcg->memsw, &parent->memsw);
+		res_counter_init(&memcg->kmem, &parent->kmem);
+
 		/*
 		 * We increment refcnt of the parent to ensure that we can
 		 * safely access it on res_counter_charge/uncharge.
@@ -4967,25 +6159,18 @@ mem_cgroup_create(struct cgroup *cont)
 	} else {
 		res_counter_init(&memcg->res, NULL);
 		res_counter_init(&memcg->memsw, NULL);
+		res_counter_init(&memcg->kmem, NULL);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
 		 * unfortunate state in our controller.
 		 */
-		if (parent && parent != root_mem_cgroup)
+		if (parent != root_mem_cgroup)
 			mem_cgroup_subsys.broken_hierarchy = true;
 	}
-	memcg->last_scanned_node = MAX_NUMNODES;
-	INIT_LIST_HEAD(&memcg->oom_notify);
-
-	if (parent)
-		memcg->swappiness = mem_cgroup_swappiness(parent);
-	atomic_set(&memcg->refcnt, 1);
-	memcg->move_charge_at_immigrate = 0;
-	mutex_init(&memcg->thresholds_lock);
-	spin_lock_init(&memcg->move_lock);
 
 	error = memcg_init_kmem(memcg, &mem_cgroup_subsys);
+	mutex_unlock(&memcg_create_mutex);
 	if (error) {
 		/*
 		 * We call put now because our (and parent's) refcnts
@@ -4993,22 +6178,21 @@ mem_cgroup_create(struct cgroup *cont)
 		 * call __mem_cgroup_free, so return directly
 		 */
 		mem_cgroup_put(memcg);
-		return ERR_PTR(error);
+		if (parent->use_hierarchy)
+			mem_cgroup_put(parent);
 	}
-	return &memcg->css;
-free_out:
-	__mem_cgroup_free(memcg);
-	return ERR_PTR(error);
+	return error;
 }
 
-static int mem_cgroup_pre_destroy(struct cgroup *cont)
+static void mem_cgroup_css_offline(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-	return mem_cgroup_force_empty(memcg, false);
+	mem_cgroup_reparent_charges(memcg);
+	mem_cgroup_destroy_all_caches(memcg);
 }
 
-static void mem_cgroup_destroy(struct cgroup *cont)
+static void mem_cgroup_css_free(struct cgroup *cont)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
@@ -5133,7 +6317,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 	 * Because lookup_swap_cache() updates some statistics counter,
 	 * we call find_get_page() with swapper_space directly.
 	 */
-	page = find_get_page(&swapper_space, ent.val);
+	page = find_get_page(swap_address_space(ent), ent.val);
 	if (do_swap_account)
 		entry->val = ent.val;
 
@@ -5174,7 +6358,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 		swp_entry_t swap = radix_to_swp_entry(page);
 		if (do_swap_account)
 			*entry = swap;
-		page = find_get_page(&swapper_space, swap.val);
+		page = find_get_page(swap_address_space(swap), swap.val);
 	}
 #endif
 	return page;
@@ -5384,8 +6568,15 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup,
 	struct task_struct *p = cgroup_taskset_first(tset);
 	int ret = 0;
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgroup);
+	unsigned long move_charge_at_immigrate;
 
-	if (memcg->move_charge_at_immigrate) {
+	/*
+	 * We are now commited to this value whatever it is. Changes in this
+	 * tunable will only affect upcoming migrations, not the current one.
+	 * So we need to save it, and keep it going.
+	 */
+	move_charge_at_immigrate  = memcg->move_charge_at_immigrate;
+	if (move_charge_at_immigrate) {
 		struct mm_struct *mm;
 		struct mem_cgroup *from = mem_cgroup_from_task(p);
 
@@ -5405,6 +6596,7 @@ static int mem_cgroup_can_attach(struct cgroup *cgroup,
 			spin_lock(&mc.lock);
 			mc.from = from;
 			mc.to = memcg;
+			mc.immigrate_flags = move_charge_at_immigrate;
 			spin_unlock(&mc.lock);
 			/* We set mc.moving_task later */
 
@@ -5598,16 +6790,16 @@ static void mem_cgroup_move_task(struct cgroup *cont,
 struct cgroup_subsys mem_cgroup_subsys = {
 	.name = "memory",
 	.subsys_id = mem_cgroup_subsys_id,
-	.create = mem_cgroup_create,
-	.pre_destroy = mem_cgroup_pre_destroy,
-	.destroy = mem_cgroup_destroy,
+	.css_alloc = mem_cgroup_css_alloc,
+	.css_online = mem_cgroup_css_online,
+	.css_offline = mem_cgroup_css_offline,
+	.css_free = mem_cgroup_css_free,
 	.can_attach = mem_cgroup_can_attach,
 	.cancel_attach = mem_cgroup_cancel_attach,
 	.attach = mem_cgroup_move_task,
 	.base_cftypes = mem_cgroup_files,
 	.early_init = 0,
 	.use_id = 1,
-	.__DEPRECATED_clear_css_refs = true,
 };
 
 #ifdef CONFIG_MEMCG_SWAP
@@ -5622,4 +6814,39 @@ static int __init enable_swap_account(char *s)
 }
 __setup("swapaccount=", enable_swap_account);
 
+static void __init memsw_file_init(void)
+{
+	WARN_ON(cgroup_add_cftypes(&mem_cgroup_subsys, memsw_cgroup_files));
+}
+
+static void __init enable_swap_cgroup(void)
+{
+	if (!mem_cgroup_disabled() && really_do_swap_account) {
+		do_swap_account = 1;
+		memsw_file_init();
+	}
+}
+
+#else
+static void __init enable_swap_cgroup(void)
+{
+}
 #endif
+
+/*
+ * subsys_initcall() for memory controller.
+ *
+ * Some parts like hotcpu_notifier() have to be initialized from this context
+ * because of lock dependencies (cgroup_lock -> cpu hotplug) but basically
+ * everything that doesn't depend on a specific mem_cgroup structure should
+ * be initialized from here.
+ */
+static int __init mem_cgroup_init(void)
+{
+	hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
+	enable_swap_cgroup();
+	mem_cgroup_soft_limit_tree_init();
+	memcg_stock_init();
+	return 0;
+}
+subsys_initcall(mem_cgroup_init);