1 files changed, 290 insertions, 183 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 26c6f4ec20f..b2ee6df0e9b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -89,7 +89,6 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
 	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
 	MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
-	MEM_CGROUP_ON_MOVE,	/* someone is moving account between groups */
 	MEM_CGROUP_STAT_NSTATS,
 };
 
@@ -135,7 +134,7 @@ struct mem_cgroup_reclaim_iter {
  */
 struct mem_cgroup_per_zone {
 	struct lruvec		lruvec;
-	unsigned long		count[NR_LRU_LISTS];
+	unsigned long		lru_size[NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1];
 
@@ -144,11 +143,9 @@ struct mem_cgroup_per_zone {
 	unsigned long long	usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
-	struct mem_cgroup	*mem;		/* Back pointer, we cannot */
+	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
 						/* use container_of	   */
 };
-/* Macro for accessing counter */
-#define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
 
 struct mem_cgroup_per_node {
 	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
@@ -300,6 +297,12 @@ struct mem_cgroup {
 	 */
 	unsigned long 	move_charge_at_immigrate;
 	/*
+	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 */
+	atomic_t	moving_account;
+	/* taken only while moving_account > 0 */
+	spinlock_t	move_lock;
+	/*
 	 * percpu counter.
 	 */
 	struct mem_cgroup_stat_cpu *stat;
@@ -612,9 +615,9 @@ retry:
 	 * we will to add it back at the end of reclaim to its correct
 	 * position in the tree.
 	 */
-	__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
-	if (!res_counter_soft_limit_excess(&mz->mem->res) ||
-		!css_tryget(&mz->mem->css))
+	__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
+	if (!res_counter_soft_limit_excess(&mz->memcg->res) ||
+		!css_tryget(&mz->memcg->css))
 		goto retry;
 done:
 	return mz;
@@ -692,15 +695,19 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
-					 bool file, int nr_pages)
+					 bool anon, int nr_pages)
 {
 	preempt_disable();
 
-	if (file)
-		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
+	/*
+	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
+	 * counted as CACHE even if it's on ANON LRU.
+	 */
+	if (anon)
+		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
 				nr_pages);
 	else
-		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
+		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE],
 				nr_pages);
 
 	/* pagein of a big page is an event. So, ignore page size */
@@ -721,14 +728,14 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid,
 			unsigned int lru_mask)
 {
 	struct mem_cgroup_per_zone *mz;
-	enum lru_list l;
+	enum lru_list lru;
 	unsigned long ret = 0;
 
 	mz = mem_cgroup_zoneinfo(memcg, nid, zid);
 
-	for_each_lru(l) {
-		if (BIT(l) & lru_mask)
-			ret += MEM_CGROUP_ZSTAT(mz, l);
+	for_each_lru(lru) {
+		if (BIT(lru) & lru_mask)
+			ret += mz->lru_size[lru];
 	}
 	return ret;
 }
@@ -1077,7 +1084,7 @@ struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page,
 
 	mz = page_cgroup_zoneinfo(memcg, page);
 	/* compound_order() is stabilized through lru_lock */
-	MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
+	mz->lru_size[lru] += 1 << compound_order(page);
 	return &mz->lruvec;
 }
 
@@ -1105,8 +1112,8 @@ void mem_cgroup_lru_del_list(struct page *page, enum lru_list lru)
 	VM_BUG_ON(!memcg);
 	mz = page_cgroup_zoneinfo(memcg, page);
 	/* huge page split is done under lru_lock. so, we have no races. */
-	VM_BUG_ON(MEM_CGROUP_ZSTAT(mz, lru) < (1 << compound_order(page)));
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1 << compound_order(page);
+	VM_BUG_ON(mz->lru_size[lru] < (1 << compound_order(page)));
+	mz->lru_size[lru] -= 1 << compound_order(page);
 }
 
 void mem_cgroup_lru_del(struct page *page)
@@ -1285,40 +1292,48 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 	return memcg->swappiness;
 }
 
-static void mem_cgroup_start_move(struct mem_cgroup *memcg)
-{
-	int cpu;
+/*
+ * memcg->moving_account is used for checking possibility that some thread is
+ * calling move_account(). When a thread on CPU-A starts moving pages under
+ * a memcg, other threads should check memcg->moving_account under
+ * rcu_read_lock(), like this:
+ *
+ *         CPU-A                                    CPU-B
+ *                                              rcu_read_lock()
+ *         memcg->moving_account+1              if (memcg->mocing_account)
+ *                                                   take heavy locks.
+ *         synchronize_rcu()                    update something.
+ *                                              rcu_read_unlock()
+ *         start move here.
+ */
 
-	get_online_cpus();
-	spin_lock(&memcg->pcp_counter_lock);
-	for_each_online_cpu(cpu)
-		per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
-	memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
-	spin_unlock(&memcg->pcp_counter_lock);
-	put_online_cpus();
+/* for quick checking without looking up memcg */
+atomic_t memcg_moving __read_mostly;
 
+static void mem_cgroup_start_move(struct mem_cgroup *memcg)
+{
+	atomic_inc(&memcg_moving);
+	atomic_inc(&memcg->moving_account);
 	synchronize_rcu();
 }
 
 static void mem_cgroup_end_move(struct mem_cgroup *memcg)
 {
-	int cpu;
-
-	if (!memcg)
-		return;
-	get_online_cpus();
-	spin_lock(&memcg->pcp_counter_lock);
-	for_each_online_cpu(cpu)
-		per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
-	memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
-	spin_unlock(&memcg->pcp_counter_lock);
-	put_online_cpus();
+	/*
+	 * Now, mem_cgroup_clear_mc() may call this function with NULL.
+	 * We check NULL in callee rather than caller.
+	 */
+	if (memcg) {
+		atomic_dec(&memcg_moving);
+		atomic_dec(&memcg->moving_account);
+	}
 }
+
 /*
  * 2 routines for checking "mem" is under move_account() or not.
  *
- * mem_cgroup_stealed() - checking a cgroup is mc.from or not. This is used
- *			  for avoiding race in accounting. If true,
+ * mem_cgroup_stolen() -  checking whether a cgroup is mc.from or not. This
+ *			  is used for avoiding races in accounting.  If true,
  *			  pc->mem_cgroup may be overwritten.
  *
  * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or
@@ -1326,10 +1341,10 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg)
  *			  waiting at hith-memory prressure caused by "move".
  */
 
-static bool mem_cgroup_stealed(struct mem_cgroup *memcg)
+static bool mem_cgroup_stolen(struct mem_cgroup *memcg)
 {
 	VM_BUG_ON(!rcu_read_lock_held());
-	return this_cpu_read(memcg->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+	return atomic_read(&memcg->moving_account) > 0;
 }
 
 static bool mem_cgroup_under_move(struct mem_cgroup *memcg)
@@ -1370,6 +1385,24 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg)
 	return false;
 }
 
+/*
+ * Take this lock when
+ * - a code tries to modify page's memcg while it's USED.
+ * - a code tries to modify page state accounting in a memcg.
+ * see mem_cgroup_stolen(), too.
+ */
+static void move_lock_mem_cgroup(struct mem_cgroup *memcg,
+				  unsigned long *flags)
+{
+	spin_lock_irqsave(&memcg->move_lock, *flags);
+}
+
+static void move_unlock_mem_cgroup(struct mem_cgroup *memcg,
+				unsigned long *flags)
+{
+	spin_unlock_irqrestore(&memcg->move_lock, *flags);
+}
+
 /**
  * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode.
  * @memcg: The memory cgroup that went over limit
@@ -1393,7 +1426,6 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 	if (!memcg || !p)
 		return;
 
-
 	rcu_read_lock();
 
 	mem_cgrp = memcg->css.cgroup;
@@ -1772,22 +1804,22 @@ static DEFINE_SPINLOCK(memcg_oom_lock);
 static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
 
 struct oom_wait_info {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *memcg;
 	wait_queue_t	wait;
 };
 
 static int memcg_oom_wake_function(wait_queue_t *wait,
 	unsigned mode, int sync, void *arg)
 {
-	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg,
-			  *oom_wait_memcg;
+	struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg;
+	struct mem_cgroup *oom_wait_memcg;
 	struct oom_wait_info *oom_wait_info;
 
 	oom_wait_info = container_of(wait, struct oom_wait_info, wait);
-	oom_wait_memcg = oom_wait_info->mem;
+	oom_wait_memcg = oom_wait_info->memcg;
 
 	/*
-	 * Both of oom_wait_info->mem and wake_mem are stable under us.
+	 * Both of oom_wait_info->memcg and wake_memcg are stable under us.
 	 * Then we can use css_is_ancestor without taking care of RCU.
 	 */
 	if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg)
@@ -1811,12 +1843,12 @@ static void memcg_oom_recover(struct mem_cgroup *memcg)
 /*
  * try to call OOM killer. returns false if we should exit memory-reclaim loop.
  */
-bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
+bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask, int order)
 {
 	struct oom_wait_info owait;
 	bool locked, need_to_kill;
 
-	owait.mem = memcg;
+	owait.memcg = memcg;
 	owait.wait.flags = 0;
 	owait.wait.func = memcg_oom_wake_function;
 	owait.wait.private = current;
@@ -1841,7 +1873,7 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
 
 	if (need_to_kill) {
 		finish_wait(&memcg_oom_waitq, &owait.wait);
-		mem_cgroup_out_of_memory(memcg, mask);
+		mem_cgroup_out_of_memory(memcg, mask, order);
 	} else {
 		schedule();
 		finish_wait(&memcg_oom_waitq, &owait.wait);
@@ -1881,41 +1913,66 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask)
  * by flags.
  *
  * Considering "move", this is an only case we see a race. To make the race
- * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are
- * possibility of race condition. If there is, we take a lock.
+ * small, we check mm->moving_account and detect there are possibility of race
+ * If there is, we take a lock.
  */
 
+void __mem_cgroup_begin_update_page_stat(struct page *page,
+				bool *locked, unsigned long *flags)
+{
+	struct mem_cgroup *memcg;
+	struct page_cgroup *pc;
+
+	pc = lookup_page_cgroup(page);
+again:
+	memcg = pc->mem_cgroup;
+	if (unlikely(!memcg || !PageCgroupUsed(pc)))
+		return;
+	/*
+	 * If this memory cgroup is not under account moving, we don't
+	 * need to take move_lock_page_cgroup(). Because we already hold
+	 * rcu_read_lock(), any calls to move_account will be delayed until
+	 * rcu_read_unlock() if mem_cgroup_stolen() == true.
+	 */
+	if (!mem_cgroup_stolen(memcg))
+		return;
+
+	move_lock_mem_cgroup(memcg, flags);
+	if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) {
+		move_unlock_mem_cgroup(memcg, flags);
+		goto again;
+	}
+	*locked = true;
+}
+
+void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags)
+{
+	struct page_cgroup *pc = lookup_page_cgroup(page);
+
+	/*
+	 * It's guaranteed that pc->mem_cgroup never changes while
+	 * lock is held because a routine modifies pc->mem_cgroup
+	 * should take move_lock_page_cgroup().
+	 */
+	move_unlock_mem_cgroup(pc->mem_cgroup, flags);
+}
+
 void mem_cgroup_update_page_stat(struct page *page,
 				 enum mem_cgroup_page_stat_item idx, int val)
 {
 	struct mem_cgroup *memcg;
 	struct page_cgroup *pc = lookup_page_cgroup(page);
-	bool need_unlock = false;
 	unsigned long uninitialized_var(flags);
 
 	if (mem_cgroup_disabled())
 		return;
 
-	rcu_read_lock();
 	memcg = pc->mem_cgroup;
 	if (unlikely(!memcg || !PageCgroupUsed(pc)))
-		goto out;
-	/* pc->mem_cgroup is unstable ? */
-	if (unlikely(mem_cgroup_stealed(memcg)) || PageTransHuge(page)) {
-		/* take a lock against to access pc->mem_cgroup */
-		move_lock_page_cgroup(pc, &flags);
-		need_unlock = true;
-		memcg = pc->mem_cgroup;
-		if (!memcg || !PageCgroupUsed(pc))
-			goto out;
-	}
+		return;
 
 	switch (idx) {
 	case MEMCG_NR_FILE_MAPPED:
-		if (val > 0)
-			SetPageCgroupFileMapped(pc);
-		else if (!page_mapped(page))
-			ClearPageCgroupFileMapped(pc);
 		idx = MEM_CGROUP_STAT_FILE_MAPPED;
 		break;
 	default:
@@ -1923,14 +1980,7 @@ void mem_cgroup_update_page_stat(struct page *page,
 	}
 
 	this_cpu_add(memcg->stat->count[idx], val);
-
-out:
-	if (unlikely(need_unlock))
-		move_unlock_page_cgroup(pc, &flags);
-	rcu_read_unlock();
-	return;
 }
-EXPORT_SYMBOL(mem_cgroup_update_page_stat);
 
 /*
  * size of first charge trial. "32" comes from vmscan.c's magic value.
@@ -2101,17 +2151,6 @@ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu)
 		per_cpu(memcg->stat->events[i], cpu) = 0;
 		memcg->nocpu_base.events[i] += x;
 	}
-	/* need to clear ON_MOVE value, works as a kind of lock. */
-	per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
-	spin_unlock(&memcg->pcp_counter_lock);
-}
-
-static void synchronize_mem_cgroup_on_move(struct mem_cgroup *memcg, int cpu)
-{
-	int idx = MEM_CGROUP_ON_MOVE;
-
-	spin_lock(&memcg->pcp_counter_lock);
-	per_cpu(memcg->stat->count[idx], cpu) = memcg->nocpu_base.count[idx];
 	spin_unlock(&memcg->pcp_counter_lock);
 }
 
@@ -2123,11 +2162,8 @@ static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	struct memcg_stock_pcp *stock;
 	struct mem_cgroup *iter;
 
-	if ((action == CPU_ONLINE)) {
-		for_each_mem_cgroup(iter)
-			synchronize_mem_cgroup_on_move(iter, cpu);
+	if (action == CPU_ONLINE)
 		return NOTIFY_OK;
-	}
 
 	if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
 		return NOTIFY_OK;
@@ -2212,7 +2248,7 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	if (!oom_check)
 		return CHARGE_NOMEM;
 	/* check OOM */
-	if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask))
+	if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize)))
 		return CHARGE_OOM_DIE;
 
 	return CHARGE_RETRY;
@@ -2446,6 +2482,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 {
 	struct zone *uninitialized_var(zone);
 	bool was_on_lru = false;
+	bool anon;
 
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
@@ -2481,19 +2518,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	 * See mem_cgroup_add_lru_list(), etc.
  	 */
 	smp_wmb();
-	switch (ctype) {
-	case MEM_CGROUP_CHARGE_TYPE_CACHE:
-	case MEM_CGROUP_CHARGE_TYPE_SHMEM:
-		SetPageCgroupCache(pc);
-		SetPageCgroupUsed(pc);
-		break;
-	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
-		ClearPageCgroupCache(pc);
-		SetPageCgroupUsed(pc);
-		break;
-	default:
-		break;
-	}
+	SetPageCgroupUsed(pc);
 
 	if (lrucare) {
 		if (was_on_lru) {
@@ -2504,7 +2529,12 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages);
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+		anon = true;
+	else
+		anon = false;
+
+	mem_cgroup_charge_statistics(memcg, anon, nr_pages);
 	unlock_page_cgroup(pc);
 
 	/*
@@ -2517,8 +2547,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
-#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\
-			(1 << PCG_MIGRATION))
+#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MIGRATION))
 /*
  * Because tail pages are not marked as "used", set it. We're under
  * zone->lru_lock, 'splitting on pmd' and compound_lock.
@@ -2569,6 +2598,7 @@ static int mem_cgroup_move_account(struct page *page,
 {
 	unsigned long flags;
 	int ret;
+	bool anon = PageAnon(page);
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON(PageLRU(page));
@@ -2588,23 +2618,23 @@ static int mem_cgroup_move_account(struct page *page,
 	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
 		goto unlock;
 
-	move_lock_page_cgroup(pc, &flags);
+	move_lock_mem_cgroup(from, &flags);
 
-	if (PageCgroupFileMapped(pc)) {
+	if (!anon && page_mapped(page)) {
 		/* Update mapped_file data for mem_cgroup */
 		preempt_disable();
 		__this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		preempt_enable();
 	}
-	mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages);
+	mem_cgroup_charge_statistics(from, anon, -nr_pages);
 	if (uncharge)
 		/* This is not "cancel", but cancel_charge does all we need. */
 		__mem_cgroup_cancel_charge(from, nr_pages);
 
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, PageCgroupCache(pc), nr_pages);
+	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
@@ -2612,7 +2642,7 @@ static int mem_cgroup_move_account(struct page *page,
 	 * guaranteed that "to" is never removed. So, we don't check rmdir
 	 * status here.
 	 */
-	move_unlock_page_cgroup(pc, &flags);
+	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
 unlock:
 	unlock_page_cgroup(pc);
@@ -2914,7 +2944,6 @@ direct_uncharge:
 		res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE);
 	if (unlikely(batch->memcg != memcg))
 		memcg_oom_recover(memcg);
-	return;
 }
 
 /*
@@ -2926,6 +2955,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
 	struct page_cgroup *pc;
+	bool anon;
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -2951,8 +2981,17 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	if (!PageCgroupUsed(pc))
 		goto unlock_out;
 
+	anon = PageAnon(page);
+
 	switch (ctype) {
 	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+		/*
+		 * Generally PageAnon tells if it's the anon statistics to be
+		 * updated; but sometimes e.g. mem_cgroup_uncharge_page() is
+		 * used before page reached the stage of being marked PageAnon.
+		 */
+		anon = true;
+		/* fallthrough */
 	case MEM_CGROUP_CHARGE_TYPE_DROP:
 		/* See mem_cgroup_prepare_migration() */
 		if (page_mapped(page) || PageCgroupMigration(pc))
@@ -2969,7 +3008,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		break;
 	}
 
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages);
+	mem_cgroup_charge_statistics(memcg, anon, -nr_pages);
 
 	ClearPageCgroupUsed(pc);
 	/*
@@ -3276,6 +3315,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 {
 	struct page *used, *unused;
 	struct page_cgroup *pc;
+	bool anon;
 
 	if (!memcg)
 		return;
@@ -3297,8 +3337,10 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	lock_page_cgroup(pc);
 	ClearPageCgroupMigration(pc);
 	unlock_page_cgroup(pc);
-
-	__mem_cgroup_uncharge_common(unused, MEM_CGROUP_CHARGE_TYPE_FORCE);
+	anon = PageAnon(used);
+	__mem_cgroup_uncharge_common(unused,
+		anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED
+		     : MEM_CGROUP_CHARGE_TYPE_CACHE);
 
 	/*
 	 * If a page is a file cache, radix-tree replacement is very atomic
@@ -3308,7 +3350,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	 * and USED bit check in mem_cgroup_uncharge_page() will do enough
 	 * check. (see prepare_charge() also)
 	 */
-	if (PageAnon(used))
+	if (anon)
 		mem_cgroup_uncharge_page(used);
 	/*
 	 * At migration, we may charge account against cgroup which has no
@@ -3338,7 +3380,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	/* fix accounting on old pages */
 	lock_page_cgroup(pc);
 	memcg = pc->mem_cgroup;
-	mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -1);
+	mem_cgroup_charge_statistics(memcg, false, -1);
 	ClearPageCgroupUsed(pc);
 	unlock_page_cgroup(pc);
 
@@ -3549,7 +3591,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			break;
 
 		nr_scanned = 0;
-		reclaimed = mem_cgroup_soft_reclaim(mz->mem, zone,
+		reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone,
 						    gfp_mask, &nr_scanned);
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
@@ -3576,13 +3618,13 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 				next_mz =
 				__mem_cgroup_largest_soft_limit_node(mctz);
 				if (next_mz == mz)
-					css_put(&next_mz->mem->css);
+					css_put(&next_mz->memcg->css);
 				else /* next_mz == NULL or other memcg */
 					break;
 			} while (1);
 		}
-		__mem_cgroup_remove_exceeded(mz->mem, mz, mctz);
-		excess = res_counter_soft_limit_excess(&mz->mem->res);
+		__mem_cgroup_remove_exceeded(mz->memcg, mz, mctz);
+		excess = res_counter_soft_limit_excess(&mz->memcg->res);
 		/*
 		 * One school of thought says that we should not add
 		 * back the node to the tree if reclaim returns 0.
@@ -3592,9 +3634,9 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 		 * term TODO.
 		 */
 		/* If excess == 0, no tree ops */
-		__mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess);
+		__mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
 		spin_unlock(&mctz->lock);
-		css_put(&mz->mem->css);
+		css_put(&mz->memcg->css);
 		loop++;
 		/*
 		 * Could not reclaim anything and there are no more
@@ -3607,7 +3649,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 			break;
 	} while (!nr_reclaimed);
 	if (next_mz)
-		css_put(&next_mz->mem->css);
+		css_put(&next_mz->memcg->css);
 	return nr_reclaimed;
 }
 
@@ -3629,7 +3671,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 	mz = mem_cgroup_zoneinfo(memcg, node, zid);
 	list = &mz->lruvec.lists[lru];
 
-	loop = MEM_CGROUP_ZSTAT(mz, lru);
+	loop = mz->lru_size[lru];
 	/* give some margin against EBUSY etc...*/
 	loop += 256;
 	busy = NULL;
@@ -3703,10 +3745,10 @@ move_account:
 		mem_cgroup_start_move(memcg);
 		for_each_node_state(node, N_HIGH_MEMORY) {
 			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
-				enum lru_list l;
-				for_each_lru(l) {
+				enum lru_list lru;
+				for_each_lru(lru) {
 					ret = mem_cgroup_force_empty_list(memcg,
-							node, zid, l);
+							node, zid, lru);
 					if (ret)
 						break;
 				}
@@ -3860,7 +3902,6 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 		break;
 	default:
 		BUG();
-		break;
 	}
 	return val;
 }
@@ -3939,7 +3980,6 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
 out:
 	*mem_limit = min_limit;
 	*memsw_limit = min_memsw_limit;
-	return;
 }
 
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
@@ -4098,38 +4138,38 @@ static int mem_control_numa_stat_show(struct seq_file *m, void *arg)
 	unsigned long total_nr, file_nr, anon_nr, unevictable_nr;
 	unsigned long node_nr;
 	struct cgroup *cont = m->private;
-	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 
-	total_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL);
+	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) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, LRU_ALL);
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
 	seq_putc(m, '\n');
 
-	file_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_FILE);
+	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) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid,
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_FILE);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
 	seq_putc(m, '\n');
 
-	anon_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_ANON);
+	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) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid,
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				LRU_ALL_ANON);
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
 	seq_putc(m, '\n');
 
-	unevictable_nr = mem_cgroup_nr_lru_pages(mem_cont, BIT(LRU_UNEVICTABLE));
+	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) {
-		node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid,
+		node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid,
 				BIT(LRU_UNEVICTABLE));
 		seq_printf(m, " N%d=%lu", nid, node_nr);
 	}
@@ -4141,12 +4181,12 @@ static int mem_control_numa_stat_show(struct seq_file *m, void *arg)
 static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 				 struct cgroup_map_cb *cb)
 {
-	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
 	struct mcs_total_stat mystat;
 	int i;
 
 	memset(&mystat, 0, sizeof(mystat));
-	mem_cgroup_get_local_stat(mem_cont, &mystat);
+	mem_cgroup_get_local_stat(memcg, &mystat);
 
 
 	for (i = 0; i < NR_MCS_STAT; i++) {
@@ -4158,14 +4198,14 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	/* Hierarchical information */
 	{
 		unsigned long long limit, memsw_limit;
-		memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
+		memcg_get_hierarchical_limit(memcg, &limit, &memsw_limit);
 		cb->fill(cb, "hierarchical_memory_limit", limit);
 		if (do_swap_account)
 			cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
 	}
 
 	memset(&mystat, 0, sizeof(mystat));
-	mem_cgroup_get_total_stat(mem_cont, &mystat);
+	mem_cgroup_get_total_stat(memcg, &mystat);
 	for (i = 0; i < NR_MCS_STAT; i++) {
 		if (i == MCS_SWAP && !do_swap_account)
 			continue;
@@ -4181,7 +4221,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 
 		for_each_online_node(nid)
 			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
+				mz = mem_cgroup_zoneinfo(memcg, nid, zid);
 
 				recent_rotated[0] +=
 					mz->reclaim_stat.recent_rotated[0];
@@ -4426,12 +4466,6 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 	else
 		BUG();
 
-	/*
-	 * Something went wrong if we trying to unregister a threshold
-	 * if we don't have thresholds
-	 */
-	BUG_ON(!thresholds);
-
 	if (!thresholds->primary)
 		goto unlock;
 
@@ -4736,7 +4770,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node)
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup_per_zone *mz;
-	enum lru_list l;
+	enum lru_list lru;
 	int zone, tmp = node;
 	/*
 	 * This routine is called against possible nodes.
@@ -4754,11 +4788,11 @@ 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];
-		for_each_lru(l)
-			INIT_LIST_HEAD(&mz->lruvec.lists[l]);
+		for_each_lru(lru)
+			INIT_LIST_HEAD(&mz->lruvec.lists[lru]);
 		mz->usage_in_excess = 0;
 		mz->on_tree = false;
-		mz->mem = memcg;
+		mz->memcg = memcg;
 	}
 	memcg->info.nodeinfo[node] = pn;
 	return 0;
@@ -4771,29 +4805,29 @@ 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 *mem;
+	struct mem_cgroup *memcg;
 	int size = sizeof(struct mem_cgroup);
 
 	/* Can be very big if MAX_NUMNODES is very big */
 	if (size < PAGE_SIZE)
-		mem = kzalloc(size, GFP_KERNEL);
+		memcg = kzalloc(size, GFP_KERNEL);
 	else
-		mem = vzalloc(size);
+		memcg = vzalloc(size);
 
-	if (!mem)
+	if (!memcg)
 		return NULL;
 
-	mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
-	if (!mem->stat)
+	memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
+	if (!memcg->stat)
 		goto out_free;
-	spin_lock_init(&mem->pcp_counter_lock);
-	return mem;
+	spin_lock_init(&memcg->pcp_counter_lock);
+	return memcg;
 
 out_free:
 	if (size < PAGE_SIZE)
-		kfree(mem);
+		kfree(memcg);
 	else
-		vfree(mem);
+		vfree(memcg);
 	return NULL;
 }
 
@@ -4981,6 +5015,7 @@ mem_cgroup_create(struct cgroup *cont)
 	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);
@@ -5075,7 +5110,7 @@ one_by_one:
 }
 
 /**
- * is_target_pte_for_mc - check a pte whether it is valid for move charge
+ * get_mctgt_type - get target type of moving charge
  * @vma: the vma the pte to be checked belongs
  * @addr: the address corresponding to the pte to be checked
  * @ptent: the pte to be checked
@@ -5098,7 +5133,7 @@ union mc_target {
 };
 
 enum mc_target_type {
-	MC_TARGET_NONE,	/* not used */
+	MC_TARGET_NONE = 0,
 	MC_TARGET_PAGE,
 	MC_TARGET_SWAP,
 };
@@ -5179,12 +5214,12 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma,
 	return page;
 }
 
-static int is_target_pte_for_mc(struct vm_area_struct *vma,
+static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 		unsigned long addr, pte_t ptent, union mc_target *target)
 {
 	struct page *page = NULL;
 	struct page_cgroup *pc;
-	int ret = 0;
+	enum mc_target_type ret = MC_TARGET_NONE;
 	swp_entry_t ent = { .val = 0 };
 
 	if (pte_present(ptent))
@@ -5195,7 +5230,7 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma,
 		page = mc_handle_file_pte(vma, addr, ptent, &ent);
 
 	if (!page && !ent.val)
-		return 0;
+		return ret;
 	if (page) {
 		pc = lookup_page_cgroup(page);
 		/*
@@ -5221,6 +5256,41 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma,
 	return ret;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * We don't consider swapping or file mapped pages because THP does not
+ * support them for now.
+ * Caller should make sure that pmd_trans_huge(pmd) is true.
+ */
+static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t pmd, union mc_target *target)
+{
+	struct page *page = NULL;
+	struct page_cgroup *pc;
+	enum mc_target_type ret = MC_TARGET_NONE;
+
+	page = pmd_page(pmd);
+	VM_BUG_ON(!page || !PageHead(page));
+	if (!move_anon())
+		return ret;
+	pc = lookup_page_cgroup(page);
+	if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
+		ret = MC_TARGET_PAGE;
+		if (target) {
+			get_page(page);
+			target->page = page;
+		}
+	}
+	return ret;
+}
+#else
+static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma,
+		unsigned long addr, pmd_t pmd, union mc_target *target)
+{
+	return MC_TARGET_NONE;
+}
+#endif
+
 static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 					unsigned long addr, unsigned long end,
 					struct mm_walk *walk)
@@ -5229,11 +5299,16 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
-	split_huge_page_pmd(walk->mm, pmd);
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE)
+			mc.precharge += HPAGE_PMD_NR;
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		return 0;
+	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
-		if (is_target_pte_for_mc(vma, addr, *pte, NULL))
+		if (get_mctgt_type(vma, addr, *pte, NULL))
 			mc.precharge++;	/* increment precharge temporarily */
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
@@ -5388,23 +5463,55 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	struct vm_area_struct *vma = walk->private;
 	pte_t *pte;
 	spinlock_t *ptl;
+	enum mc_target_type target_type;
+	union mc_target target;
+	struct page *page;
+	struct page_cgroup *pc;
+
+	/*
+	 * We don't take compound_lock() here but no race with splitting thp
+	 * happens because:
+	 *  - if pmd_trans_huge_lock() returns 1, the relevant thp is not
+	 *    under splitting, which means there's no concurrent thp split,
+	 *  - if another thread runs into split_huge_page() just after we
+	 *    entered this if-block, the thread must wait for page table lock
+	 *    to be unlocked in __split_huge_page_splitting(), where the main
+	 *    part of thp split is not executed yet.
+	 */
+	if (pmd_trans_huge_lock(pmd, vma) == 1) {
+		if (!mc.precharge) {
+			spin_unlock(&vma->vm_mm->page_table_lock);
+			return 0;
+		}
+		target_type = get_mctgt_type_thp(vma, addr, *pmd, &target);
+		if (target_type == MC_TARGET_PAGE) {
+			page = target.page;
+			if (!isolate_lru_page(page)) {
+				pc = lookup_page_cgroup(page);
+				if (!mem_cgroup_move_account(page, HPAGE_PMD_NR,
+							     pc, mc.from, mc.to,
+							     false)) {
+					mc.precharge -= HPAGE_PMD_NR;
+					mc.moved_charge += HPAGE_PMD_NR;
+				}
+				putback_lru_page(page);
+			}
+			put_page(page);
+		}
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		return 0;
+	}
 
-	split_huge_page_pmd(walk->mm, pmd);
 retry:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
 		pte_t ptent = *(pte++);
-		union mc_target target;
-		int type;
-		struct page *page;
-		struct page_cgroup *pc;
 		swp_entry_t ent;
 
 		if (!mc.precharge)
 			break;
 
-		type = is_target_pte_for_mc(vma, addr, ptent, &target);
-		switch (type) {
+		switch (get_mctgt_type(vma, addr, ptent, &target)) {
 		case MC_TARGET_PAGE:
 			page = target.page;
 			if (isolate_lru_page(page))
@@ -5417,7 +5524,7 @@ retry:
 				mc.moved_charge++;
 			}
 			putback_lru_page(page);
-put:			/* is_target_pte_for_mc() gets the page */
+put:			/* get_mctgt_type() gets the page */
 			put_page(page);
 			break;
 		case MC_TARGET_SWAP: