1 files changed, 1477 insertions, 369 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 51ee96545579..e2996b80601f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -21,11 +21,13 @@
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/mm.h>
+#include <linux/pagemap.h>
 #include <linux/smp.h>
 #include <linux/page-flags.h>
 #include <linux/backing-dev.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/spinlock.h>
@@ -34,12 +36,23 @@
 #include <linux/vmalloc.h>
 #include <linux/mm_inline.h>
 #include <linux/page_cgroup.h>
+#include "internal.h"
 
 #include <asm/uaccess.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
+int do_swap_account __read_mostly;
+static int really_do_swap_account __initdata = 1; /* for remember boot option*/
+#else
+#define do_swap_account		(0)
+#endif
+
+static DEFINE_MUTEX(memcg_tasklist);	/* can be hold under cgroup_mutex */
+
 /*
  * Statistics for memory cgroup.
  */
@@ -60,7 +73,7 @@ struct mem_cgroup_stat_cpu {
 } ____cacheline_aligned_in_smp;
 
 struct mem_cgroup_stat {
-	struct mem_cgroup_stat_cpu cpustat[NR_CPUS];
+	struct mem_cgroup_stat_cpu cpustat[0];
 };
 
 /*
@@ -89,9 +102,10 @@ struct mem_cgroup_per_zone {
 	/*
 	 * spin_lock to protect the per cgroup LRU
 	 */
-	spinlock_t		lru_lock;
 	struct list_head	lists[NR_LRU_LISTS];
 	unsigned long		count[NR_LRU_LISTS];
+
+	struct zone_reclaim_stat reclaim_stat;
 };
 /* Macro for accessing counter */
 #define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
@@ -122,44 +136,73 @@ struct mem_cgroup {
 	 */
 	struct res_counter res;
 	/*
+	 * the counter to account for mem+swap usage.
+	 */
+	struct res_counter memsw;
+	/*
 	 * Per cgroup active and inactive list, similar to the
 	 * per zone LRU lists.
 	 */
 	struct mem_cgroup_lru_info info;
 
+	/*
+	  protect against reclaim related member.
+	*/
+	spinlock_t reclaim_param_lock;
+
 	int	prev_priority;	/* for recording reclaim priority */
+
+	/*
+	 * While reclaiming in a hiearchy, we cache the last child we
+	 * reclaimed from. Protected by hierarchy_mutex
+	 */
+	struct mem_cgroup *last_scanned_child;
 	/*
-	 * statistics.
+	 * Should the accounting and control be hierarchical, per subtree?
+	 */
+	bool use_hierarchy;
+	unsigned long	last_oom_jiffies;
+	atomic_t	refcnt;
+
+	unsigned int	swappiness;
+
+	/*
+	 * statistics. This must be placed at the end of memcg.
 	 */
 	struct mem_cgroup_stat stat;
 };
-static struct mem_cgroup init_mem_cgroup;
 
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
 	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
 	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
+	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
 	NR_CHARGE_TYPE,
 };
 
 /* only for here (for easy reading.) */
 #define PCGF_CACHE	(1UL << PCG_CACHE)
 #define PCGF_USED	(1UL << PCG_USED)
-#define PCGF_ACTIVE	(1UL << PCG_ACTIVE)
 #define PCGF_LOCK	(1UL << PCG_LOCK)
-#define PCGF_FILE	(1UL << PCG_FILE)
 static const unsigned long
 pcg_default_flags[NR_CHARGE_TYPE] = {
-	PCGF_CACHE | PCGF_FILE | PCGF_USED | PCGF_LOCK, /* File Cache */
-	PCGF_ACTIVE | PCGF_USED | PCGF_LOCK, /* Anon */
-	PCGF_ACTIVE | PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
+	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* File Cache */
+	PCGF_USED | PCGF_LOCK, /* Anon */
+	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
 	0, /* FORCE */
 };
 
-/*
- * Always modified under lru lock. Then, not necessary to preempt_disable()
- */
+/* for encoding cft->private value on file */
+#define _MEM			(0)
+#define _MEMSWAP		(1)
+#define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
+#define MEMFILE_TYPE(val)	(((val) >> 16) & 0xffff)
+#define MEMFILE_ATTR(val)	((val) & 0xffff)
+
+static void mem_cgroup_get(struct mem_cgroup *mem);
+static void mem_cgroup_put(struct mem_cgroup *mem);
+
 static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 					 struct page_cgroup *pc,
 					 bool charge)
@@ -167,10 +210,9 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 	int val = (charge)? 1 : -1;
 	struct mem_cgroup_stat *stat = &mem->stat;
 	struct mem_cgroup_stat_cpu *cpustat;
+	int cpu = get_cpu();
 
-	VM_BUG_ON(!irqs_disabled());
-
-	cpustat = &stat->cpustat[smp_processor_id()];
+	cpustat = &stat->cpustat[cpu];
 	if (PageCgroupCache(pc))
 		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val);
 	else
@@ -182,6 +224,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 	else
 		__mem_cgroup_stat_add_safe(cpustat,
 				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
+	put_cpu();
 }
 
 static struct mem_cgroup_per_zone *
@@ -197,6 +240,9 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
 	int nid = page_cgroup_nid(pc);
 	int zid = page_cgroup_zid(pc);
 
+	if (!mem)
+		return NULL;
+
 	return mem_cgroup_zoneinfo(mem, nid, zid);
 }
 
@@ -236,77 +282,152 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 				struct mem_cgroup, css);
 }
 
-static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
-			struct page_cgroup *pc)
+static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
-	int lru = LRU_BASE;
+	struct mem_cgroup *mem = NULL;
+	/*
+	 * Because we have no locks, mm->owner's may be being moved to other
+	 * cgroup. We use css_tryget() here even if this looks
+	 * pessimistic (rather than adding locks here).
+	 */
+	rcu_read_lock();
+	do {
+		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+		if (unlikely(!mem))
+			break;
+	} while (!css_tryget(&mem->css));
+	rcu_read_unlock();
+	return mem;
+}
 
-	if (PageCgroupUnevictable(pc))
-		lru = LRU_UNEVICTABLE;
-	else {
-		if (PageCgroupActive(pc))
-			lru += LRU_ACTIVE;
-		if (PageCgroupFile(pc))
-			lru += LRU_FILE;
-	}
+static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
+{
+	if (!mem)
+		return true;
+	return css_is_removed(&mem->css);
+}
 
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+/*
+ * Following LRU functions are allowed to be used without PCG_LOCK.
+ * Operations are called by routine of global LRU independently from memcg.
+ * What we have to take care of here is validness of pc->mem_cgroup.
+ *
+ * Changes to pc->mem_cgroup happens when
+ * 1. charge
+ * 2. moving account
+ * In typical case, "charge" is done before add-to-lru. Exception is SwapCache.
+ * It is added to LRU before charge.
+ * If PCG_USED bit is not set, page_cgroup is not added to this private LRU.
+ * When moving account, the page is not on LRU. It's isolated.
+ */
 
-	mem_cgroup_charge_statistics(pc->mem_cgroup, pc, false);
-	list_del(&pc->lru);
+void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
+{
+	struct page_cgroup *pc;
+	struct mem_cgroup *mem;
+	struct mem_cgroup_per_zone *mz;
+
+	if (mem_cgroup_disabled())
+		return;
+	pc = lookup_page_cgroup(page);
+	/* can happen while we handle swapcache. */
+	if (list_empty(&pc->lru) || !pc->mem_cgroup)
+		return;
+	/*
+	 * We don't check PCG_USED bit. It's cleared when the "page" is finally
+	 * removed from global LRU.
+	 */
+	mz = page_cgroup_zoneinfo(pc);
+	mem = pc->mem_cgroup;
+	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	list_del_init(&pc->lru);
+	return;
 }
 
-static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
-				struct page_cgroup *pc)
+void mem_cgroup_del_lru(struct page *page)
 {
-	int lru = LRU_BASE;
+	mem_cgroup_del_lru_list(page, page_lru(page));
+}
 
-	if (PageCgroupUnevictable(pc))
-		lru = LRU_UNEVICTABLE;
-	else {
-		if (PageCgroupActive(pc))
-			lru += LRU_ACTIVE;
-		if (PageCgroupFile(pc))
-			lru += LRU_FILE;
-	}
+void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
+{
+	struct mem_cgroup_per_zone *mz;
+	struct page_cgroup *pc;
 
-	MEM_CGROUP_ZSTAT(mz, lru) += 1;
-	list_add(&pc->lru, &mz->lists[lru]);
+	if (mem_cgroup_disabled())
+		return;
 
-	mem_cgroup_charge_statistics(pc->mem_cgroup, pc, true);
+	pc = lookup_page_cgroup(page);
+	smp_rmb();
+	/* unused page is not rotated. */
+	if (!PageCgroupUsed(pc))
+		return;
+	mz = page_cgroup_zoneinfo(pc);
+	list_move(&pc->lru, &mz->lists[lru]);
 }
 
-static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
+void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
 {
-	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
-	int active    = PageCgroupActive(pc);
-	int file      = PageCgroupFile(pc);
-	int unevictable = PageCgroupUnevictable(pc);
-	enum lru_list from = unevictable ? LRU_UNEVICTABLE :
-				(LRU_FILE * !!file + !!active);
+	struct page_cgroup *pc;
+	struct mem_cgroup_per_zone *mz;
 
-	if (lru == from)
+	if (mem_cgroup_disabled())
+		return;
+	pc = lookup_page_cgroup(page);
+	/* barrier to sync with "charge" */
+	smp_rmb();
+	if (!PageCgroupUsed(pc))
 		return;
 
-	MEM_CGROUP_ZSTAT(mz, from) -= 1;
+	mz = page_cgroup_zoneinfo(pc);
+	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	list_add(&pc->lru, &mz->lists[lru]);
+}
+
+/*
+ * At handling SwapCache, pc->mem_cgroup may be changed while it's linked to
+ * lru because the page may.be reused after it's fully uncharged (because of
+ * SwapCache behavior).To handle that, unlink page_cgroup from LRU when charge
+ * it again. This function is only used to charge SwapCache. It's done under
+ * lock_page and expected that zone->lru_lock is never held.
+ */
+static void mem_cgroup_lru_del_before_commit_swapcache(struct page *page)
+{
+	unsigned long flags;
+	struct zone *zone = page_zone(page);
+	struct page_cgroup *pc = lookup_page_cgroup(page);
+
+	spin_lock_irqsave(&zone->lru_lock, flags);
 	/*
-	 * However this is done under mz->lru_lock, another flags, which
-	 * are not related to LRU, will be modified from out-of-lock.
-	 * We have to use atomic set/clear flags.
+	 * Forget old LRU when this page_cgroup is *not* used. This Used bit
+	 * is guarded by lock_page() because the page is SwapCache.
 	 */
-	if (is_unevictable_lru(lru)) {
-		ClearPageCgroupActive(pc);
-		SetPageCgroupUnevictable(pc);
-	} else {
-		if (is_active_lru(lru))
-			SetPageCgroupActive(pc);
-		else
-			ClearPageCgroupActive(pc);
-		ClearPageCgroupUnevictable(pc);
-	}
+	if (!PageCgroupUsed(pc))
+		mem_cgroup_del_lru_list(page, page_lru(page));
+	spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
 
-	MEM_CGROUP_ZSTAT(mz, lru) += 1;
-	list_move(&pc->lru, &mz->lists[lru]);
+static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page)
+{
+	unsigned long flags;
+	struct zone *zone = page_zone(page);
+	struct page_cgroup *pc = lookup_page_cgroup(page);
+
+	spin_lock_irqsave(&zone->lru_lock, flags);
+	/* link when the page is linked to LRU but page_cgroup isn't */
+	if (PageLRU(page) && list_empty(&pc->lru))
+		mem_cgroup_add_lru_list(page, page_lru(page));
+	spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
+
+
+void mem_cgroup_move_lists(struct page *page,
+			   enum lru_list from, enum lru_list to)
+{
+	if (mem_cgroup_disabled())
+		return;
+	mem_cgroup_del_lru_list(page, from);
+	mem_cgroup_add_lru_list(page, to);
 }
 
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
@@ -320,37 +441,6 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 }
 
 /*
- * This routine assumes that the appropriate zone's lru lock is already held
- */
-void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
-{
-	struct page_cgroup *pc;
-	struct mem_cgroup_per_zone *mz;
-	unsigned long flags;
-
-	if (mem_cgroup_subsys.disabled)
-		return;
-
-	/*
-	 * We cannot lock_page_cgroup while holding zone's lru_lock,
-	 * because other holders of lock_page_cgroup can be interrupted
-	 * with an attempt to rotate_reclaimable_page.  But we cannot
-	 * safely get to page_cgroup without it, so just try_lock it:
-	 * mem_cgroup_isolate_pages allows for page left on wrong list.
-	 */
-	pc = lookup_page_cgroup(page);
-	if (!trylock_page_cgroup(pc))
-		return;
-	if (pc && PageCgroupUsed(pc)) {
-		mz = page_cgroup_zoneinfo(pc);
-		spin_lock_irqsave(&mz->lru_lock, flags);
-		__mem_cgroup_move_lists(pc, lru);
-		spin_unlock_irqrestore(&mz->lru_lock, flags);
-	}
-	unlock_page_cgroup(pc);
-}
-
-/*
  * Calculate mapped_ratio under memory controller. This will be used in
  * vmscan.c for deteremining we have to reclaim mapped pages.
  */
@@ -372,39 +462,108 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
  */
 int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
 {
-	return mem->prev_priority;
+	int prev_priority;
+
+	spin_lock(&mem->reclaim_param_lock);
+	prev_priority = mem->prev_priority;
+	spin_unlock(&mem->reclaim_param_lock);
+
+	return prev_priority;
 }
 
 void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority)
 {
+	spin_lock(&mem->reclaim_param_lock);
 	if (priority < mem->prev_priority)
 		mem->prev_priority = priority;
+	spin_unlock(&mem->reclaim_param_lock);
 }
 
 void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
 {
+	spin_lock(&mem->reclaim_param_lock);
 	mem->prev_priority = priority;
+	spin_unlock(&mem->reclaim_param_lock);
 }
 
-/*
- * Calculate # of pages to be scanned in this priority/zone.
- * See also vmscan.c
- *
- * priority starts from "DEF_PRIORITY" and decremented in each loop.
- * (see include/linux/mmzone.h)
- */
+static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
+{
+	unsigned long active;
+	unsigned long inactive;
+	unsigned long gb;
+	unsigned long inactive_ratio;
+
+	inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON);
+	active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON);
+
+	gb = (inactive + active) >> (30 - PAGE_SHIFT);
+	if (gb)
+		inactive_ratio = int_sqrt(10 * gb);
+	else
+		inactive_ratio = 1;
+
+	if (present_pages) {
+		present_pages[0] = inactive;
+		present_pages[1] = active;
+	}
+
+	return inactive_ratio;
+}
+
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
+{
+	unsigned long active;
+	unsigned long inactive;
+	unsigned long present_pages[2];
+	unsigned long inactive_ratio;
 
-long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
-					int priority, enum lru_list lru)
+	inactive_ratio = calc_inactive_ratio(memcg, present_pages);
+
+	inactive = present_pages[0];
+	active = present_pages[1];
+
+	if (inactive * inactive_ratio < active)
+		return 1;
+
+	return 0;
+}
+
+unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
+				       struct zone *zone,
+				       enum lru_list lru)
 {
-	long nr_pages;
 	int nid = zone->zone_pgdat->node_id;
 	int zid = zone_idx(zone);
-	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
+	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
 
-	nr_pages = MEM_CGROUP_ZSTAT(mz, lru);
+	return MEM_CGROUP_ZSTAT(mz, lru);
+}
 
-	return (nr_pages >> priority);
+struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
+						      struct zone *zone)
+{
+	int nid = zone->zone_pgdat->node_id;
+	int zid = zone_idx(zone);
+	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
+
+	return &mz->reclaim_stat;
+}
+
+struct zone_reclaim_stat *
+mem_cgroup_get_reclaim_stat_from_page(struct page *page)
+{
+	struct page_cgroup *pc;
+	struct mem_cgroup_per_zone *mz;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	pc = lookup_page_cgroup(page);
+	mz = page_cgroup_zoneinfo(pc);
+	if (!mz)
+		return NULL;
+
+	return &mz->reclaim_stat;
 }
 
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
@@ -429,95 +588,281 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
 	src = &mz->lists[lru];
 
-	spin_lock(&mz->lru_lock);
 	scan = 0;
 	list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
 		if (scan >= nr_to_scan)
 			break;
+
+		page = pc->page;
 		if (unlikely(!PageCgroupUsed(pc)))
 			continue;
-		page = pc->page;
-
 		if (unlikely(!PageLRU(page)))
 			continue;
 
-		/*
-		 * TODO: play better with lumpy reclaim, grabbing anything.
-		 */
-		if (PageUnevictable(page) ||
-		    (PageActive(page) && !active) ||
-		    (!PageActive(page) && active)) {
-			__mem_cgroup_move_lists(pc, page_lru(page));
-			continue;
-		}
-
 		scan++;
-		list_move(&pc->lru, &pc_list);
-
 		if (__isolate_lru_page(page, mode, file) == 0) {
 			list_move(&page->lru, dst);
 			nr_taken++;
 		}
 	}
 
-	list_splice(&pc_list, src);
-	spin_unlock(&mz->lru_lock);
-
 	*scanned = scan;
 	return nr_taken;
 }
 
+#define mem_cgroup_from_res_counter(counter, member)	\
+	container_of(counter, struct mem_cgroup, member)
+
 /*
- * Charge the memory controller for page usage.
- * Return
- * 0 if the charge was successful
- * < 0 if the cgroup is over its limit
+ * This routine finds the DFS walk successor. This routine should be
+ * called with hierarchy_mutex held
  */
-static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask, enum charge_type ctype,
-				struct mem_cgroup *memcg)
+static struct mem_cgroup *
+mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
 {
+	struct cgroup *cgroup, *curr_cgroup, *root_cgroup;
+
+	curr_cgroup = curr->css.cgroup;
+	root_cgroup = root_mem->css.cgroup;
+
+	if (!list_empty(&curr_cgroup->children)) {
+		/*
+		 * Walk down to children
+		 */
+		mem_cgroup_put(curr);
+		cgroup = list_entry(curr_cgroup->children.next,
+						struct cgroup, sibling);
+		curr = mem_cgroup_from_cont(cgroup);
+		mem_cgroup_get(curr);
+		goto done;
+	}
+
+visit_parent:
+	if (curr_cgroup == root_cgroup) {
+		mem_cgroup_put(curr);
+		curr = root_mem;
+		mem_cgroup_get(curr);
+		goto done;
+	}
+
+	/*
+	 * Goto next sibling
+	 */
+	if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) {
+		mem_cgroup_put(curr);
+		cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup,
+						sibling);
+		curr = mem_cgroup_from_cont(cgroup);
+		mem_cgroup_get(curr);
+		goto done;
+	}
+
+	/*
+	 * Go up to next parent and next parent's sibling if need be
+	 */
+	curr_cgroup = curr_cgroup->parent;
+	goto visit_parent;
+
+done:
+	root_mem->last_scanned_child = curr;
+	return curr;
+}
+
+/*
+ * Visit the first child (need not be the first child as per the ordering
+ * of the cgroup list, since we track last_scanned_child) of @mem and use
+ * that to reclaim free pages from.
+ */
+static struct mem_cgroup *
+mem_cgroup_get_first_node(struct mem_cgroup *root_mem)
+{
+	struct cgroup *cgroup;
+	struct mem_cgroup *ret;
+	bool obsolete;
+
+	obsolete = mem_cgroup_is_obsolete(root_mem->last_scanned_child);
+
+	/*
+	 * Scan all children under the mem_cgroup mem
+	 */
+	mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);
+	if (list_empty(&root_mem->css.cgroup->children)) {
+		ret = root_mem;
+		goto done;
+	}
+
+	if (!root_mem->last_scanned_child || obsolete) {
+
+		if (obsolete && root_mem->last_scanned_child)
+			mem_cgroup_put(root_mem->last_scanned_child);
+
+		cgroup = list_first_entry(&root_mem->css.cgroup->children,
+				struct cgroup, sibling);
+		ret = mem_cgroup_from_cont(cgroup);
+		mem_cgroup_get(ret);
+	} else
+		ret = mem_cgroup_get_next_node(root_mem->last_scanned_child,
+						root_mem);
+
+done:
+	root_mem->last_scanned_child = ret;
+	mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
+	return ret;
+}
+
+static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
+{
+	if (do_swap_account) {
+		if (res_counter_check_under_limit(&mem->res) &&
+			res_counter_check_under_limit(&mem->memsw))
+			return true;
+	} else
+		if (res_counter_check_under_limit(&mem->res))
+			return true;
+	return false;
+}
+
+static unsigned int get_swappiness(struct mem_cgroup *memcg)
+{
+	struct cgroup *cgrp = memcg->css.cgroup;
+	unsigned int swappiness;
+
+	/* root ? */
+	if (cgrp->parent == NULL)
+		return vm_swappiness;
+
+	spin_lock(&memcg->reclaim_param_lock);
+	swappiness = memcg->swappiness;
+	spin_unlock(&memcg->reclaim_param_lock);
+
+	return swappiness;
+}
+
+/*
+ * Dance down the hierarchy if needed to reclaim memory. We remember the
+ * last child we reclaimed from, so that we don't end up penalizing
+ * one child extensively based on its position in the children list.
+ *
+ * root_mem is the original ancestor that we've been reclaim from.
+ */
+static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
+						gfp_t gfp_mask, bool noswap)
+{
+	struct mem_cgroup *next_mem;
+	int ret = 0;
+
+	/*
+	 * Reclaim unconditionally and don't check for return value.
+	 * We need to reclaim in the current group and down the tree.
+	 * One might think about checking for children before reclaiming,
+	 * but there might be left over accounting, even after children
+	 * have left.
+	 */
+	ret = try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap,
+					   get_swappiness(root_mem));
+	if (mem_cgroup_check_under_limit(root_mem))
+		return 0;
+	if (!root_mem->use_hierarchy)
+		return ret;
+
+	next_mem = mem_cgroup_get_first_node(root_mem);
+
+	while (next_mem != root_mem) {
+		if (mem_cgroup_is_obsolete(next_mem)) {
+			mem_cgroup_put(next_mem);
+			next_mem = mem_cgroup_get_first_node(root_mem);
+			continue;
+		}
+		ret = try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap,
+						   get_swappiness(next_mem));
+		if (mem_cgroup_check_under_limit(root_mem))
+			return 0;
+		mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);
+		next_mem = mem_cgroup_get_next_node(next_mem, root_mem);
+		mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
+	}
+	return ret;
+}
+
+bool mem_cgroup_oom_called(struct task_struct *task)
+{
+	bool ret = false;
 	struct mem_cgroup *mem;
-	struct page_cgroup *pc;
-	unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct mem_cgroup_per_zone *mz;
-	unsigned long flags;
+	struct mm_struct *mm;
 
-	pc = lookup_page_cgroup(page);
-	/* can happen at boot */
-	if (unlikely(!pc))
+	rcu_read_lock();
+	mm = task->mm;
+	if (!mm)
+		mm = &init_mm;
+	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (mem && time_before(jiffies, mem->last_oom_jiffies + HZ/10))
+		ret = true;
+	rcu_read_unlock();
+	return ret;
+}
+/*
+ * Unlike exported interface, "oom" parameter is added. if oom==true,
+ * oom-killer can be invoked.
+ */
+static int __mem_cgroup_try_charge(struct mm_struct *mm,
+			gfp_t gfp_mask, struct mem_cgroup **memcg,
+			bool oom)
+{
+	struct mem_cgroup *mem, *mem_over_limit;
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct res_counter *fail_res;
+
+	if (unlikely(test_thread_flag(TIF_MEMDIE))) {
+		/* Don't account this! */
+		*memcg = NULL;
 		return 0;
-	prefetchw(pc);
+	}
+
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
 	 * thread group leader migrates. It's possible that mm is not
 	 * set, if so charge the init_mm (happens for pagecache usage).
 	 */
-
-	if (likely(!memcg)) {
-		rcu_read_lock();
-		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
-		if (unlikely(!mem)) {
-			rcu_read_unlock();
-			return 0;
-		}
-		/*
-		 * For every charge from the cgroup, increment reference count
-		 */
-		css_get(&mem->css);
-		rcu_read_unlock();
+	mem = *memcg;
+	if (likely(!mem)) {
+		mem = try_get_mem_cgroup_from_mm(mm);
+		*memcg = mem;
 	} else {
-		mem = memcg;
-		css_get(&memcg->css);
+		css_get(&mem->css);
 	}
+	if (unlikely(!mem))
+		return 0;
+
+	VM_BUG_ON(mem_cgroup_is_obsolete(mem));
+
+	while (1) {
+		int ret;
+		bool noswap = false;
+
+		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
+		if (likely(!ret)) {
+			if (!do_swap_account)
+				break;
+			ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
+							&fail_res);
+			if (likely(!ret))
+				break;
+			/* mem+swap counter fails */
+			res_counter_uncharge(&mem->res, PAGE_SIZE);
+			noswap = true;
+			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
+									memsw);
+		} else
+			/* mem counter fails */
+			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
+									res);
 
-	while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE))) {
 		if (!(gfp_mask & __GFP_WAIT))
-			goto out;
+			goto nomem;
 
-		if (try_to_free_mem_cgroup_pages(mem, gfp_mask))
-			continue;
+		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
+							noswap);
 
 		/*
 		 * try_to_free_mem_cgroup_pages() might not give us a full
@@ -525,49 +870,214 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		 * moved to swap cache or just unmapped from the cgroup.
 		 * Check the limit again to see if the reclaim reduced the
 		 * current usage of the cgroup before giving up
+		 *
 		 */
-		if (res_counter_check_under_limit(&mem->res))
+		if (mem_cgroup_check_under_limit(mem_over_limit))
 			continue;
 
 		if (!nr_retries--) {
-			mem_cgroup_out_of_memory(mem, gfp_mask);
-			goto out;
+			if (oom) {
+				mutex_lock(&memcg_tasklist);
+				mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
+				mutex_unlock(&memcg_tasklist);
+				mem_over_limit->last_oom_jiffies = jiffies;
+			}
+			goto nomem;
 		}
 	}
+	return 0;
+nomem:
+	css_put(&mem->css);
+	return -ENOMEM;
+}
 
+static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
+{
+	struct mem_cgroup *mem;
+	swp_entry_t ent;
+
+	if (!PageSwapCache(page))
+		return NULL;
+
+	ent.val = page_private(page);
+	mem = lookup_swap_cgroup(ent);
+	if (!mem)
+		return NULL;
+	if (!css_tryget(&mem->css))
+		return NULL;
+	return mem;
+}
+
+/*
+ * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be
+ * USED state. If already USED, uncharge and return.
+ */
+
+static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
+				     struct page_cgroup *pc,
+				     enum charge_type ctype)
+{
+	/* try_charge() can return NULL to *memcg, taking care of it. */
+	if (!mem)
+		return;
 
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
 		unlock_page_cgroup(pc);
 		res_counter_uncharge(&mem->res, PAGE_SIZE);
+		if (do_swap_account)
+			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
 		css_put(&mem->css);
-
-		goto done;
+		return;
 	}
 	pc->mem_cgroup = mem;
-	/*
-	 * If a page is accounted as a page cache, insert to inactive list.
-	 * If anon, insert to active list.
-	 */
+	smp_wmb();
 	pc->flags = pcg_default_flags[ctype];
 
-	mz = page_cgroup_zoneinfo(pc);
+	mem_cgroup_charge_statistics(mem, pc, true);
 
-	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_add_list(mz, pc);
-	spin_unlock_irqrestore(&mz->lru_lock, flags);
 	unlock_page_cgroup(pc);
+}
 
-done:
-	return 0;
+/**
+ * mem_cgroup_move_account - move account of the page
+ * @pc:	page_cgroup of the page.
+ * @from: mem_cgroup which the page is moved from.
+ * @to:	mem_cgroup which the page is moved to. @from != @to.
+ *
+ * The caller must confirm following.
+ * - page is not on LRU (isolate_page() is useful.)
+ *
+ * returns 0 at success,
+ * returns -EBUSY when lock is busy or "pc" is unstable.
+ *
+ * This function does "uncharge" from old cgroup but doesn't do "charge" to
+ * new cgroup. It should be done by a caller.
+ */
+
+static int mem_cgroup_move_account(struct page_cgroup *pc,
+	struct mem_cgroup *from, struct mem_cgroup *to)
+{
+	struct mem_cgroup_per_zone *from_mz, *to_mz;
+	int nid, zid;
+	int ret = -EBUSY;
+
+	VM_BUG_ON(from == to);
+	VM_BUG_ON(PageLRU(pc->page));
+
+	nid = page_cgroup_nid(pc);
+	zid = page_cgroup_zid(pc);
+	from_mz =  mem_cgroup_zoneinfo(from, nid, zid);
+	to_mz =  mem_cgroup_zoneinfo(to, nid, zid);
+
+	if (!trylock_page_cgroup(pc))
+		return ret;
+
+	if (!PageCgroupUsed(pc))
+		goto out;
+
+	if (pc->mem_cgroup != from)
+		goto out;
+
+	css_put(&from->css);
+	res_counter_uncharge(&from->res, PAGE_SIZE);
+	mem_cgroup_charge_statistics(from, pc, false);
+	if (do_swap_account)
+		res_counter_uncharge(&from->memsw, PAGE_SIZE);
+	pc->mem_cgroup = to;
+	mem_cgroup_charge_statistics(to, pc, true);
+	css_get(&to->css);
+	ret = 0;
 out:
-	css_put(&mem->css);
-	return -ENOMEM;
+	unlock_page_cgroup(pc);
+	return ret;
+}
+
+/*
+ * move charges to its parent.
+ */
+
+static int mem_cgroup_move_parent(struct page_cgroup *pc,
+				  struct mem_cgroup *child,
+				  gfp_t gfp_mask)
+{
+	struct page *page = pc->page;
+	struct cgroup *cg = child->css.cgroup;
+	struct cgroup *pcg = cg->parent;
+	struct mem_cgroup *parent;
+	int ret;
+
+	/* Is ROOT ? */
+	if (!pcg)
+		return -EINVAL;
+
+
+	parent = mem_cgroup_from_cont(pcg);
+
+
+	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
+	if (ret || !parent)
+		return ret;
+
+	if (!get_page_unless_zero(page))
+		return -EBUSY;
+
+	ret = isolate_lru_page(page);
+
+	if (ret)
+		goto cancel;
+
+	ret = mem_cgroup_move_account(pc, child, parent);
+
+	/* drop extra refcnt by try_charge() (move_account increment one) */
+	css_put(&parent->css);
+	putback_lru_page(page);
+	if (!ret) {
+		put_page(page);
+		return 0;
+	}
+	/* uncharge if move fails */
+cancel:
+	res_counter_uncharge(&parent->res, PAGE_SIZE);
+	if (do_swap_account)
+		res_counter_uncharge(&parent->memsw, PAGE_SIZE);
+	put_page(page);
+	return ret;
+}
+
+/*
+ * Charge the memory controller for page usage.
+ * Return
+ * 0 if the charge was successful
+ * < 0 if the cgroup is over its limit
+ */
+static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
+				gfp_t gfp_mask, enum charge_type ctype,
+				struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *mem;
+	struct page_cgroup *pc;
+	int ret;
+
+	pc = lookup_page_cgroup(page);
+	/* can happen at boot */
+	if (unlikely(!pc))
+		return 0;
+	prefetchw(pc);
+
+	mem = memcg;
+	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
+	if (ret || !mem)
+		return ret;
+
+	__mem_cgroup_commit_charge(mem, pc, ctype);
+	return 0;
 }
 
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
+int mem_cgroup_newpage_charge(struct page *page,
+			      struct mm_struct *mm, gfp_t gfp_mask)
 {
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return 0;
 	if (PageCompound(page))
 		return 0;
@@ -589,7 +1099,10 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
-	if (mem_cgroup_subsys.disabled)
+	struct mem_cgroup *mem = NULL;
+	int ret;
+
+	if (mem_cgroup_disabled())
 		return 0;
 	if (PageCompound(page))
 		return 0;
@@ -601,6 +1114,8 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 	 * For GFP_NOWAIT case, the page may be pre-charged before calling
 	 * add_to_page_cache(). (See shmem.c) check it here and avoid to call
 	 * charge twice. (It works but has to pay a bit larger cost.)
+	 * And when the page is SwapCache, it should take swap information
+	 * into account. This is under lock_page() now.
 	 */
 	if (!(gfp_mask & __GFP_WAIT)) {
 		struct page_cgroup *pc;
@@ -617,58 +1132,198 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		unlock_page_cgroup(pc);
 	}
 
-	if (unlikely(!mm))
+	if (do_swap_account && PageSwapCache(page)) {
+		mem = try_get_mem_cgroup_from_swapcache(page);
+		if (mem)
+			mm = NULL;
+		  else
+			mem = NULL;
+		/* SwapCache may be still linked to LRU now. */
+		mem_cgroup_lru_del_before_commit_swapcache(page);
+	}
+
+	if (unlikely(!mm && !mem))
 		mm = &init_mm;
 
 	if (page_is_file_cache(page))
 		return mem_cgroup_charge_common(page, mm, gfp_mask,
 				MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
-	else
-		return mem_cgroup_charge_common(page, mm, gfp_mask,
-				MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL);
+
+	ret = mem_cgroup_charge_common(page, mm, gfp_mask,
+				MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
+	if (mem)
+		css_put(&mem->css);
+	if (PageSwapCache(page))
+		mem_cgroup_lru_add_after_commit_swapcache(page);
+
+	if (do_swap_account && !ret && PageSwapCache(page)) {
+		swp_entry_t ent = {.val = page_private(page)};
+		/* avoid double counting */
+		mem = swap_cgroup_record(ent, NULL);
+		if (mem) {
+			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+			mem_cgroup_put(mem);
+		}
+	}
+	return ret;
+}
+
+/*
+ * While swap-in, try_charge -> commit or cancel, the page is locked.
+ * And when try_charge() successfully returns, one refcnt to memcg without
+ * struct page_cgroup is aquired. This refcnt will be cumsumed by
+ * "commit()" or removed by "cancel()"
+ */
+int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
+				 struct page *page,
+				 gfp_t mask, struct mem_cgroup **ptr)
+{
+	struct mem_cgroup *mem;
+	int ret;
+
+	if (mem_cgroup_disabled())
+		return 0;
+
+	if (!do_swap_account)
+		goto charge_cur_mm;
+	/*
+	 * A racing thread's fault, or swapoff, may have already updated
+	 * the pte, and even removed page from swap cache: return success
+	 * to go on to do_swap_page()'s pte_same() test, which should fail.
+	 */
+	if (!PageSwapCache(page))
+		return 0;
+	mem = try_get_mem_cgroup_from_swapcache(page);
+	if (!mem)
+		goto charge_cur_mm;
+	*ptr = mem;
+	ret = __mem_cgroup_try_charge(NULL, mask, ptr, true);
+	/* drop extra refcnt from tryget */
+	css_put(&mem->css);
+	return ret;
+charge_cur_mm:
+	if (unlikely(!mm))
+		mm = &init_mm;
+	return __mem_cgroup_try_charge(mm, mask, ptr, true);
+}
+
+void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+{
+	struct page_cgroup *pc;
+
+	if (mem_cgroup_disabled())
+		return;
+	if (!ptr)
+		return;
+	pc = lookup_page_cgroup(page);
+	mem_cgroup_lru_del_before_commit_swapcache(page);
+	__mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+	mem_cgroup_lru_add_after_commit_swapcache(page);
+	/*
+	 * Now swap is on-memory. This means this page may be
+	 * counted both as mem and swap....double count.
+	 * Fix it by uncharging from memsw. Basically, this SwapCache is stable
+	 * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page()
+	 * may call delete_from_swap_cache() before reach here.
+	 */
+	if (do_swap_account && PageSwapCache(page)) {
+		swp_entry_t ent = {.val = page_private(page)};
+		struct mem_cgroup *memcg;
+		memcg = swap_cgroup_record(ent, NULL);
+		if (memcg) {
+			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+			mem_cgroup_put(memcg);
+		}
+
+	}
+	/* add this page(page_cgroup) to the LRU we want. */
+
 }
 
+void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
+{
+	if (mem_cgroup_disabled())
+		return;
+	if (!mem)
+		return;
+	res_counter_uncharge(&mem->res, PAGE_SIZE);
+	if (do_swap_account)
+		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+	css_put(&mem->css);
+}
+
+
 /*
  * uncharge if !page_mapped(page)
  */
-static void
+static struct mem_cgroup *
 __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 {
 	struct page_cgroup *pc;
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem = NULL;
 	struct mem_cgroup_per_zone *mz;
-	unsigned long flags;
 
-	if (mem_cgroup_subsys.disabled)
-		return;
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	if (PageSwapCache(page))
+		return NULL;
 
 	/*
 	 * Check if our page_cgroup is valid
 	 */
 	pc = lookup_page_cgroup(page);
 	if (unlikely(!pc || !PageCgroupUsed(pc)))
-		return;
+		return NULL;
 
 	lock_page_cgroup(pc);
-	if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED && page_mapped(page))
-	     || !PageCgroupUsed(pc)) {
-		/* This happens at race in zap_pte_range() and do_swap_page()*/
-		unlock_page_cgroup(pc);
-		return;
+
+	mem = pc->mem_cgroup;
+
+	if (!PageCgroupUsed(pc))
+		goto unlock_out;
+
+	switch (ctype) {
+	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+		if (page_mapped(page))
+			goto unlock_out;
+		break;
+	case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
+		if (!PageAnon(page)) {	/* Shared memory */
+			if (page->mapping && !page_is_file_cache(page))
+				goto unlock_out;
+		} else if (page_mapped(page)) /* Anon */
+				goto unlock_out;
+		break;
+	default:
+		break;
 	}
+
+	res_counter_uncharge(&mem->res, PAGE_SIZE);
+	if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
+		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+
+	mem_cgroup_charge_statistics(mem, pc, false);
 	ClearPageCgroupUsed(pc);
-	mem = pc->mem_cgroup;
+	/*
+	 * pc->mem_cgroup is not cleared here. It will be accessed when it's
+	 * freed from LRU. This is safe because uncharged page is expected not
+	 * to be reused (freed soon). Exception is SwapCache, it's handled by
+	 * special functions.
+	 */
 
 	mz = page_cgroup_zoneinfo(pc);
-	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_remove_list(mz, pc);
-	spin_unlock_irqrestore(&mz->lru_lock, flags);
 	unlock_page_cgroup(pc);
 
-	res_counter_uncharge(&mem->res, PAGE_SIZE);
-	css_put(&mem->css);
+	/* at swapout, this memcg will be accessed to record to swap */
+	if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
+		css_put(&mem->css);
 
-	return;
+	return mem;
+
+unlock_out:
+	unlock_page_cgroup(pc);
+	return NULL;
 }
 
 void mem_cgroup_uncharge_page(struct page *page)
@@ -689,16 +1344,55 @@ void mem_cgroup_uncharge_cache_page(struct page *page)
 }
 
 /*
- * Before starting migration, account against new page.
+ * called from __delete_from_swap_cache() and drop "page" account.
+ * memcg information is recorded to swap_cgroup of "ent"
+ */
+void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = __mem_cgroup_uncharge_common(page,
+					MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
+	/* record memcg information */
+	if (do_swap_account && memcg) {
+		swap_cgroup_record(ent, memcg);
+		mem_cgroup_get(memcg);
+	}
+	if (memcg)
+		css_put(&memcg->css);
+}
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+/*
+ * called from swap_entry_free(). remove record in swap_cgroup and
+ * uncharge "memsw" account.
  */
-int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
+void mem_cgroup_uncharge_swap(swp_entry_t ent)
+{
+	struct mem_cgroup *memcg;
+
+	if (!do_swap_account)
+		return;
+
+	memcg = swap_cgroup_record(ent, NULL);
+	if (memcg) {
+		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+		mem_cgroup_put(memcg);
+	}
+}
+#endif
+
+/*
+ * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
+ * page belongs to.
+ */
+int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
 {
 	struct page_cgroup *pc;
 	struct mem_cgroup *mem = NULL;
-	enum charge_type ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
 	int ret = 0;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return 0;
 
 	pc = lookup_page_cgroup(page);
@@ -706,41 +1400,67 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 	if (PageCgroupUsed(pc)) {
 		mem = pc->mem_cgroup;
 		css_get(&mem->css);
-		if (PageCgroupCache(pc)) {
-			if (page_is_file_cache(page))
-				ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
-			else
-				ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-		}
 	}
 	unlock_page_cgroup(pc);
+
 	if (mem) {
-		ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
-			ctype, mem);
+		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
 		css_put(&mem->css);
 	}
+	*ptr = mem;
 	return ret;
 }
 
 /* remove redundant charge if migration failed*/
-void mem_cgroup_end_migration(struct page *newpage)
+void mem_cgroup_end_migration(struct mem_cgroup *mem,
+		struct page *oldpage, struct page *newpage)
 {
+	struct page *target, *unused;
+	struct page_cgroup *pc;
+	enum charge_type ctype;
+
+	if (!mem)
+		return;
+
+	/* at migration success, oldpage->mapping is NULL. */
+	if (oldpage->mapping) {
+		target = oldpage;
+		unused = NULL;
+	} else {
+		target = newpage;
+		unused = oldpage;
+	}
+
+	if (PageAnon(target))
+		ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
+	else if (page_is_file_cache(target))
+		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	else
+		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+
+	/* unused page is not on radix-tree now. */
+	if (unused)
+		__mem_cgroup_uncharge_common(unused, ctype);
+
+	pc = lookup_page_cgroup(target);
 	/*
-	 * At success, page->mapping is not NULL.
-	 * special rollback care is necessary when
-	 * 1. at migration failure. (newpage->mapping is cleared in this case)
-	 * 2. the newpage was moved but not remapped again because the task
-	 *    exits and the newpage is obsolete. In this case, the new page
-	 *    may be a swapcache. So, we just call mem_cgroup_uncharge_page()
-	 *    always for avoiding mess. The  page_cgroup will be removed if
-	 *    unnecessary. File cache pages is still on radix-tree. Don't
-	 *    care it.
+	 * __mem_cgroup_commit_charge() check PCG_USED bit of page_cgroup.
+	 * So, double-counting is effectively avoided.
 	 */
-	if (!newpage->mapping)
-		__mem_cgroup_uncharge_common(newpage,
-				MEM_CGROUP_CHARGE_TYPE_FORCE);
-	else if (PageAnon(newpage))
-		mem_cgroup_uncharge_page(newpage);
+	__mem_cgroup_commit_charge(mem, pc, ctype);
+
+	/*
+	 * Both of oldpage and newpage are still under lock_page().
+	 * Then, we don't have to care about race in radix-tree.
+	 * But we have to be careful that this page is unmapped or not.
+	 *
+	 * There is a case for !page_mapped(). At the start of
+	 * migration, oldpage was mapped. But now, it's zapped.
+	 * But we know *target* page is not freed/reused under us.
+	 * mem_cgroup_uncharge_page() does all necessary checks.
+	 */
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+		mem_cgroup_uncharge_page(target);
 }
 
 /*
@@ -748,29 +1468,26 @@ void mem_cgroup_end_migration(struct page *newpage)
  * This is typically used for page reclaiming for shmem for reducing side
  * effect of page allocation from shmem, which is used by some mem_cgroup.
  */
-int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
+int mem_cgroup_shrink_usage(struct page *page,
+			    struct mm_struct *mm,
+			    gfp_t gfp_mask)
 {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem = NULL;
 	int progress = 0;
 	int retry = MEM_CGROUP_RECLAIM_RETRIES;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return 0;
-	if (!mm)
+	if (page)
+		mem = try_get_mem_cgroup_from_swapcache(page);
+	if (!mem && mm)
+		mem = try_get_mem_cgroup_from_mm(mm);
+	if (unlikely(!mem))
 		return 0;
 
-	rcu_read_lock();
-	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	if (unlikely(!mem)) {
-		rcu_read_unlock();
-		return 0;
-	}
-	css_get(&mem->css);
-	rcu_read_unlock();
-
 	do {
-		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
-		progress += res_counter_check_under_limit(&mem->res);
+		progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
+		progress += mem_cgroup_check_under_limit(mem);
 	} while (!progress && --retry);
 
 	css_put(&mem->css);
@@ -779,117 +1496,295 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 	return 0;
 }
 
+static DEFINE_MUTEX(set_limit_mutex);
+
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
-				   unsigned long long val)
+				unsigned long long val)
 {
 
 	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
 	int progress;
+	u64 memswlimit;
 	int ret = 0;
 
-	while (res_counter_set_limit(&memcg->res, val)) {
+	while (retry_count) {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		if (!retry_count) {
-			ret = -EBUSY;
+		/*
+		 * Rather than hide all in some function, I do this in
+		 * open coded manner. You see what this really does.
+		 * We have to guarantee mem->res.limit < mem->memsw.limit.
+		 */
+		mutex_lock(&set_limit_mutex);
+		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+		if (memswlimit < val) {
+			ret = -EINVAL;
+			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
-		if (!progress)
-			retry_count--;
+		ret = res_counter_set_limit(&memcg->res, val);
+		mutex_unlock(&set_limit_mutex);
+
+		if (!ret)
+			break;
+
+		progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
+							   false);
+  		if (!progress)			retry_count--;
 	}
+
 	return ret;
 }
 
+int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
+				unsigned long long val)
+{
+	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	u64 memlimit, oldusage, curusage;
+	int ret;
+
+	if (!do_swap_account)
+		return -EINVAL;
+
+	while (retry_count) {
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+		/*
+		 * Rather than hide all in some function, I do this in
+		 * open coded manner. You see what this really does.
+		 * We have to guarantee mem->res.limit < mem->memsw.limit.
+		 */
+		mutex_lock(&set_limit_mutex);
+		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+		if (memlimit > val) {
+			ret = -EINVAL;
+			mutex_unlock(&set_limit_mutex);
+			break;
+		}
+		ret = res_counter_set_limit(&memcg->memsw, val);
+		mutex_unlock(&set_limit_mutex);
+
+		if (!ret)
+			break;
+
+		oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true);
+		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		if (curusage >= oldusage)
+			retry_count--;
+	}
+	return ret;
+}
 
 /*
  * This routine traverse page_cgroup in given list and drop them all.
  * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
  */
-#define FORCE_UNCHARGE_BATCH	(128)
-static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
-			    struct mem_cgroup_per_zone *mz,
-			    enum lru_list lru)
+static int mem_cgroup_force_empty_list(struct mem_cgroup *mem,
+				int node, int zid, enum lru_list lru)
 {
-	struct page_cgroup *pc;
-	struct page *page;
-	int count = FORCE_UNCHARGE_BATCH;
-	unsigned long flags;
+	struct zone *zone;
+	struct mem_cgroup_per_zone *mz;
+	struct page_cgroup *pc, *busy;
+	unsigned long flags, loop;
 	struct list_head *list;
+	int ret = 0;
 
+	zone = &NODE_DATA(node)->node_zones[zid];
+	mz = mem_cgroup_zoneinfo(mem, node, zid);
 	list = &mz->lists[lru];
 
-	spin_lock_irqsave(&mz->lru_lock, flags);
-	while (!list_empty(list)) {
-		pc = list_entry(list->prev, struct page_cgroup, lru);
-		page = pc->page;
-		if (!PageCgroupUsed(pc))
-			break;
-		get_page(page);
-		spin_unlock_irqrestore(&mz->lru_lock, flags);
-		/*
-		 * Check if this page is on LRU. !LRU page can be found
-		 * if it's under page migration.
-		 */
-		if (PageLRU(page)) {
-			__mem_cgroup_uncharge_common(page,
-					MEM_CGROUP_CHARGE_TYPE_FORCE);
-			put_page(page);
-			if (--count <= 0) {
-				count = FORCE_UNCHARGE_BATCH;
-				cond_resched();
-			}
-		} else {
-			spin_lock_irqsave(&mz->lru_lock, flags);
+	loop = MEM_CGROUP_ZSTAT(mz, lru);
+	/* give some margin against EBUSY etc...*/
+	loop += 256;
+	busy = NULL;
+	while (loop--) {
+		ret = 0;
+		spin_lock_irqsave(&zone->lru_lock, flags);
+		if (list_empty(list)) {
+			spin_unlock_irqrestore(&zone->lru_lock, flags);
 			break;
 		}
-		spin_lock_irqsave(&mz->lru_lock, flags);
+		pc = list_entry(list->prev, struct page_cgroup, lru);
+		if (busy == pc) {
+			list_move(&pc->lru, list);
+			busy = 0;
+			spin_unlock_irqrestore(&zone->lru_lock, flags);
+			continue;
+		}
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
+
+		ret = mem_cgroup_move_parent(pc, mem, GFP_KERNEL);
+		if (ret == -ENOMEM)
+			break;
+
+		if (ret == -EBUSY || ret == -EINVAL) {
+			/* found lock contention or "pc" is obsolete. */
+			busy = pc;
+			cond_resched();
+		} else
+			busy = NULL;
 	}
-	spin_unlock_irqrestore(&mz->lru_lock, flags);
+
+	if (!ret && !list_empty(list))
+		return -EBUSY;
+	return ret;
 }
 
 /*
  * make mem_cgroup's charge to be 0 if there is no task.
  * This enables deleting this mem_cgroup.
  */
-static int mem_cgroup_force_empty(struct mem_cgroup *mem)
+static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all)
 {
-	int ret = -EBUSY;
-	int node, zid;
+	int ret;
+	int node, zid, shrink;
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct cgroup *cgrp = mem->css.cgroup;
 
 	css_get(&mem->css);
-	/*
-	 * page reclaim code (kswapd etc..) will move pages between
-	 * active_list <-> inactive_list while we don't take a lock.
-	 * So, we have to do loop here until all lists are empty.
-	 */
+
+	shrink = 0;
+	/* should free all ? */
+	if (free_all)
+		goto try_to_free;
+move_account:
 	while (mem->res.usage > 0) {
-		if (atomic_read(&mem->css.cgroup->count) > 0)
+		ret = -EBUSY;
+		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+			goto out;
+		ret = -EINTR;
+		if (signal_pending(current))
 			goto out;
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
-		for_each_node_state(node, N_POSSIBLE)
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				struct mem_cgroup_per_zone *mz;
+		ret = 0;
+		for_each_node_state(node, N_POSSIBLE) {
+			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
 				enum lru_list l;
-				mz = mem_cgroup_zoneinfo(mem, node, zid);
-				for_each_lru(l)
-					mem_cgroup_force_empty_list(mem, mz, l);
+				for_each_lru(l) {
+					ret = mem_cgroup_force_empty_list(mem,
+							node, zid, l);
+					if (ret)
+						break;
+				}
 			}
+			if (ret)
+				break;
+		}
+		/* it seems parent cgroup doesn't have enough mem */
+		if (ret == -ENOMEM)
+			goto try_to_free;
 		cond_resched();
 	}
 	ret = 0;
 out:
 	css_put(&mem->css);
 	return ret;
+
+try_to_free:
+	/* 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;
+	}
+	/* 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 && mem->res.usage > 0) {
+		int progress;
+
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			goto out;
+		}
+		progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
+						false, get_swappiness(mem));
+		if (!progress) {
+			nr_retries--;
+			/* maybe some writeback is necessary */
+			congestion_wait(WRITE, HZ/10);
+		}
+
+	}
+	lru_add_drain();
+	/* try move_account...there may be some *locked* pages. */
+	if (mem->res.usage)
+		goto move_account;
+	ret = 0;
+	goto out;
+}
+
+int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
+{
+	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
+}
+
+
+static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft)
+{
+	return mem_cgroup_from_cont(cont)->use_hierarchy;
+}
+
+static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
+					u64 val)
+{
+	int retval = 0;
+	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+	struct cgroup *parent = cont->parent;
+	struct mem_cgroup *parent_mem = NULL;
+
+	if (parent)
+		parent_mem = mem_cgroup_from_cont(parent);
+
+	cgroup_lock();
+	/*
+	 * If parent's use_hiearchy is set, we can't make any modifications
+	 * in the child subtrees. If it is unset, then the change can
+	 * occur, provided the current cgroup has no children.
+	 *
+	 * For the root cgroup, parent_mem is NULL, we allow value to be
+	 * set if there are no children.
+	 */
+	if ((!parent_mem || !parent_mem->use_hierarchy) &&
+				(val == 1 || val == 0)) {
+		if (list_empty(&cont->children))
+			mem->use_hierarchy = val;
+		else
+			retval = -EBUSY;
+	} else
+		retval = -EINVAL;
+	cgroup_unlock();
+
+	return retval;
 }
 
 static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 {
-	return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
-				    cft->private);
+	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+	u64 val = 0;
+	int type, name;
+
+	type = MEMFILE_TYPE(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+	switch (type) {
+	case _MEM:
+		val = res_counter_read_u64(&mem->res, name);
+		break;
+	case _MEMSWAP:
+		if (do_swap_account)
+			val = res_counter_read_u64(&mem->memsw, name);
+		break;
+	default:
+		BUG();
+		break;
+	}
+	return val;
 }
 /*
  * The user of this function is...
@@ -899,15 +1794,22 @@ 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;
 	unsigned long long val;
 	int ret;
 
-	switch (cft->private) {
+	type = MEMFILE_TYPE(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+	switch (name) {
 	case RES_LIMIT:
 		/* This function does all necessary parse...reuse it */
 		ret = res_counter_memparse_write_strategy(buffer, &val);
-		if (!ret)
+		if (ret)
+			break;
+		if (type == _MEM)
 			ret = mem_cgroup_resize_limit(memcg, val);
+		else
+			ret = mem_cgroup_resize_memsw_limit(memcg, val);
 		break;
 	default:
 		ret = -EINVAL; /* should be BUG() ? */
@@ -916,27 +1818,59 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 	return ret;
 }
 
+static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
+		unsigned long long *mem_limit, unsigned long long *memsw_limit)
+{
+	struct cgroup *cgroup;
+	unsigned long long min_limit, min_memsw_limit, tmp;
+
+	min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+	min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+	cgroup = memcg->css.cgroup;
+	if (!memcg->use_hierarchy)
+		goto out;
+
+	while (cgroup->parent) {
+		cgroup = cgroup->parent;
+		memcg = mem_cgroup_from_cont(cgroup);
+		if (!memcg->use_hierarchy)
+			break;
+		tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
+		min_limit = min(min_limit, tmp);
+		tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+		min_memsw_limit = min(min_memsw_limit, tmp);
+	}
+out:
+	*mem_limit = min_limit;
+	*memsw_limit = min_memsw_limit;
+	return;
+}
+
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 {
 	struct mem_cgroup *mem;
+	int type, name;
 
 	mem = mem_cgroup_from_cont(cont);
-	switch (event) {
+	type = MEMFILE_TYPE(event);
+	name = MEMFILE_ATTR(event);
+	switch (name) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&mem->res);
+		if (type == _MEM)
+			res_counter_reset_max(&mem->res);
+		else
+			res_counter_reset_max(&mem->memsw);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&mem->res);
+		if (type == _MEM)
+			res_counter_reset_failcnt(&mem->res);
+		else
+			res_counter_reset_failcnt(&mem->memsw);
 		break;
 	}
 	return 0;
 }
 
-static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
-{
-	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
-}
-
 static const struct mem_cgroup_stat_desc {
 	const char *msg;
 	u64 unit;
@@ -985,43 +1919,163 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 		cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);
 
 	}
+	{
+		unsigned long long limit, memsw_limit;
+		memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
+		cb->fill(cb, "hierarchical_memory_limit", limit);
+		if (do_swap_account)
+			cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
+	}
+
+#ifdef CONFIG_DEBUG_VM
+	cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
+
+	{
+		int nid, zid;
+		struct mem_cgroup_per_zone *mz;
+		unsigned long recent_rotated[2] = {0, 0};
+		unsigned long recent_scanned[2] = {0, 0};
+
+		for_each_online_node(nid)
+			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+				mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
+
+				recent_rotated[0] +=
+					mz->reclaim_stat.recent_rotated[0];
+				recent_rotated[1] +=
+					mz->reclaim_stat.recent_rotated[1];
+				recent_scanned[0] +=
+					mz->reclaim_stat.recent_scanned[0];
+				recent_scanned[1] +=
+					mz->reclaim_stat.recent_scanned[1];
+			}
+		cb->fill(cb, "recent_rotated_anon", recent_rotated[0]);
+		cb->fill(cb, "recent_rotated_file", recent_rotated[1]);
+		cb->fill(cb, "recent_scanned_anon", recent_scanned[0]);
+		cb->fill(cb, "recent_scanned_file", recent_scanned[1]);
+	}
+#endif
+
+	return 0;
+}
+
+static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+
+	return get_swappiness(memcg);
+}
+
+static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
+				       u64 val)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+	struct mem_cgroup *parent;
+	if (val > 100)
+		return -EINVAL;
+
+	if (cgrp->parent == NULL)
+		return -EINVAL;
+
+	parent = mem_cgroup_from_cont(cgrp->parent);
+	/* If under hierarchy, only empty-root can set this value */
+	if ((parent->use_hierarchy) ||
+	    (memcg->use_hierarchy && !list_empty(&cgrp->children)))
+		return -EINVAL;
+
+	spin_lock(&memcg->reclaim_param_lock);
+	memcg->swappiness = val;
+	spin_unlock(&memcg->reclaim_param_lock);
+
 	return 0;
 }
 
+
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
-		.private = RES_USAGE,
+		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
 		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "max_usage_in_bytes",
-		.private = RES_MAX_USAGE,
+		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
 		.trigger = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "limit_in_bytes",
-		.private = RES_LIMIT,
+		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
 		.write_string = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "failcnt",
-		.private = RES_FAILCNT,
+		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
 		.trigger = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read,
 	},
 	{
+		.name = "stat",
+		.read_map = mem_control_stat_show,
+	},
+	{
 		.name = "force_empty",
-		.trigger = mem_force_empty_write,
+		.trigger = mem_cgroup_force_empty_write,
 	},
 	{
-		.name = "stat",
-		.read_map = mem_control_stat_show,
+		.name = "use_hierarchy",
+		.write_u64 = mem_cgroup_hierarchy_write,
+		.read_u64 = mem_cgroup_hierarchy_read,
+	},
+	{
+		.name = "swappiness",
+		.read_u64 = mem_cgroup_swappiness_read,
+		.write_u64 = mem_cgroup_swappiness_write,
 	},
 };
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static struct cftype memsw_cgroup_files[] = {
+	{
+		.name = "memsw.usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.max_usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
+		.trigger = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
+		.write_string = mem_cgroup_write,
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.failcnt",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
+		.trigger = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read,
+	},
+};
+
+static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	if (!do_swap_account)
+		return 0;
+	return cgroup_add_files(cont, ss, memsw_cgroup_files,
+				ARRAY_SIZE(memsw_cgroup_files));
+};
+#else
+static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	return 0;
+}
+#endif
+
 static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 {
 	struct mem_cgroup_per_node *pn;
@@ -1047,7 +2101,6 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
-		spin_lock_init(&mz->lru_lock);
 		for_each_lru(l)
 			INIT_LIST_HEAD(&mz->lists[l]);
 	}
@@ -1059,55 +2112,113 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 	kfree(mem->info.nodeinfo[node]);
 }
 
+static int mem_cgroup_size(void)
+{
+	int cpustat_size = nr_cpu_ids * sizeof(struct mem_cgroup_stat_cpu);
+	return sizeof(struct mem_cgroup) + cpustat_size;
+}
+
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *mem;
+	int size = mem_cgroup_size();
 
-	if (sizeof(*mem) < PAGE_SIZE)
-		mem = kmalloc(sizeof(*mem), GFP_KERNEL);
+	if (size < PAGE_SIZE)
+		mem = kmalloc(size, GFP_KERNEL);
 	else
-		mem = vmalloc(sizeof(*mem));
+		mem = vmalloc(size);
 
 	if (mem)
-		memset(mem, 0, sizeof(*mem));
+		memset(mem, 0, size);
 	return mem;
 }
 
-static void mem_cgroup_free(struct mem_cgroup *mem)
+/*
+ * 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 __mem_cgroup_free(struct mem_cgroup *mem)
 {
-	if (sizeof(*mem) < PAGE_SIZE)
+	int node;
+
+	for_each_node_state(node, N_POSSIBLE)
+		free_mem_cgroup_per_zone_info(mem, node);
+
+	if (mem_cgroup_size() < PAGE_SIZE)
 		kfree(mem);
 	else
 		vfree(mem);
 }
 
+static void mem_cgroup_get(struct mem_cgroup *mem)
+{
+	atomic_inc(&mem->refcnt);
+}
+
+static void mem_cgroup_put(struct mem_cgroup *mem)
+{
+	if (atomic_dec_and_test(&mem->refcnt))
+		__mem_cgroup_free(mem);
+}
+
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_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 struct cgroup_subsys_state *
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem, *parent;
 	int node;
 
-	if (unlikely((cont->parent) == NULL)) {
-		mem = &init_mem_cgroup;
-	} else {
-		mem = mem_cgroup_alloc();
-		if (!mem)
-			return ERR_PTR(-ENOMEM);
-	}
-
-	res_counter_init(&mem->res);
+	mem = mem_cgroup_alloc();
+	if (!mem)
+		return ERR_PTR(-ENOMEM);
 
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
 			goto free_out;
+	/* root ? */
+	if (cont->parent == NULL) {
+		enable_swap_cgroup();
+		parent = NULL;
+	} else {
+		parent = mem_cgroup_from_cont(cont->parent);
+		mem->use_hierarchy = parent->use_hierarchy;
+	}
 
+	if (parent && parent->use_hierarchy) {
+		res_counter_init(&mem->res, &parent->res);
+		res_counter_init(&mem->memsw, &parent->memsw);
+	} else {
+		res_counter_init(&mem->res, NULL);
+		res_counter_init(&mem->memsw, NULL);
+	}
+	mem->last_scanned_child = NULL;
+	spin_lock_init(&mem->reclaim_param_lock);
+
+	if (parent)
+		mem->swappiness = get_swappiness(parent);
+	atomic_set(&mem->refcnt, 1);
 	return &mem->css;
 free_out:
-	for_each_node_state(node, N_POSSIBLE)
-		free_mem_cgroup_per_zone_info(mem, node);
-	if (cont->parent != NULL)
-		mem_cgroup_free(mem);
+	__mem_cgroup_free(mem);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -1115,26 +2226,26 @@ static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
 					struct cgroup *cont)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	mem_cgroup_force_empty(mem);
+	mem_cgroup_force_empty(mem, false);
 }
 
 static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
-	int node;
-	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-
-	for_each_node_state(node, N_POSSIBLE)
-		free_mem_cgroup_per_zone_info(mem, node);
-
-	mem_cgroup_free(mem_cgroup_from_cont(cont));
+	mem_cgroup_put(mem_cgroup_from_cont(cont));
 }
 
 static int mem_cgroup_populate(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
-	return cgroup_add_files(cont, ss, mem_cgroup_files,
-					ARRAY_SIZE(mem_cgroup_files));
+	int ret;
+
+	ret = cgroup_add_files(cont, ss, mem_cgroup_files,
+				ARRAY_SIZE(mem_cgroup_files));
+
+	if (!ret)
+		ret = register_memsw_files(cont, ss);
+	return ret;
 }
 
 static void mem_cgroup_move_task(struct cgroup_subsys *ss,
@@ -1142,25 +2253,12 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 				struct cgroup *old_cont,
 				struct task_struct *p)
 {
-	struct mm_struct *mm;
-	struct mem_cgroup *mem, *old_mem;
-
-	mm = get_task_mm(p);
-	if (mm == NULL)
-		return;
-
-	mem = mem_cgroup_from_cont(cont);
-	old_mem = mem_cgroup_from_cont(old_cont);
-
+	mutex_lock(&memcg_tasklist);
 	/*
-	 * Only thread group leaders are allowed to migrate, the mm_struct is
-	 * in effect owned by the leader
+	 * FIXME: It's better to move charges of this process from old
+	 * memcg to new memcg. But it's just on TODO-List now.
 	 */
-	if (!thread_group_leader(p))
-		goto out;
-
-out:
-	mmput(mm);
+	mutex_unlock(&memcg_tasklist);
 }
 
 struct cgroup_subsys mem_cgroup_subsys = {
@@ -1173,3 +2271,13 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.attach = mem_cgroup_move_task,
 	.early_init = 0,
 };
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static int __init disable_swap_account(char *s)
+{
+	really_do_swap_account = 0;
+	return 1;
+}
+__setup("noswapaccount", disable_swap_account);
+#endif