Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

14 files changed, 2645 insertions, 837 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 2f55a1e..ceba0bd 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -460,7 +460,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 	VM_BUG_ON(!PageLocked(page));
 
 	error = mem_cgroup_cache_charge(page, current->mm,
-					gfp_mask & ~__GFP_HIGHMEM);
+					gfp_mask & GFP_RECLAIM_MASK);
 	if (error)
 		goto out;
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 51ee965..e2996b8 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
diff --git a/mm/memory.c b/mm/memory.c
index 3f8fa06..22bfa7a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1511,6 +1511,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)
 {
 	int ret;
+	pgprot_t pgprot = vma->vm_page_prot;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1525,10 +1526,10 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
-	if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+	if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
 		return -EINVAL;
 
-	ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+	ret = insert_pfn(vma, addr, pfn, pgprot);
 
 	if (ret)
 		untrack_pfn_vma(vma, pfn, PAGE_SIZE);
@@ -1671,9 +1672,15 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 
 	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
-	err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
-	if (err)
+	err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size));
+	if (err) {
+		/*
+		 * To indicate that track_pfn related cleanup is not
+		 * needed from higher level routine calling unmap_vmas
+		 */
+		vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
 		return -EINVAL;
+	}
 
 	BUG_ON(addr >= end);
 	pfn -= addr >> PAGE_SHIFT;
@@ -2000,7 +2007,7 @@ gotten:
 	cow_user_page(new_page, old_page, address, vma);
 	__SetPageUptodate(new_page);
 
-	if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
+	if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
 		goto oom_free_new;
 
 	/*
@@ -2392,6 +2399,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	swp_entry_t entry;
 	pte_t pte;
+	struct mem_cgroup *ptr = NULL;
 	int ret = 0;
 
 	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
@@ -2430,7 +2438,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	lock_page(page);
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 
-	if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
+	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
 		ret = VM_FAULT_OOM;
 		unlock_page(page);
 		goto out;
@@ -2448,7 +2456,19 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_nomap;
 	}
 
-	/* The page isn't present yet, go ahead with the fault. */
+	/*
+	 * The page isn't present yet, go ahead with the fault.
+	 *
+	 * Be careful about the sequence of operations here.
+	 * To get its accounting right, reuse_swap_page() must be called
+	 * while the page is counted on swap but not yet in mapcount i.e.
+	 * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
+	 * must be called after the swap_free(), or it will never succeed.
+	 * Because delete_from_swap_page() may be called by reuse_swap_page(),
+	 * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
+	 * in page->private. In this case, a record in swap_cgroup  is silently
+	 * discarded at swap_free().
+	 */
 
 	inc_mm_counter(mm, anon_rss);
 	pte = mk_pte(page, vma->vm_page_prot);
@@ -2456,10 +2476,11 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 		write_access = 0;
 	}
-
 	flush_icache_page(vma, page);
 	set_pte_at(mm, address, page_table, pte);
 	page_add_anon_rmap(page, vma, address);
+	/* It's better to call commit-charge after rmap is established */
+	mem_cgroup_commit_charge_swapin(page, ptr);
 
 	swap_free(entry);
 	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
@@ -2480,7 +2501,7 @@ unlock:
 out:
 	return ret;
 out_nomap:
-	mem_cgroup_uncharge_page(page);
+	mem_cgroup_cancel_charge_swapin(ptr);
 	pte_unmap_unlock(page_table, ptl);
 	unlock_page(page);
 	page_cache_release(page);
@@ -2510,7 +2531,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto oom;
 	__SetPageUptodate(page);
 
-	if (mem_cgroup_charge(page, mm, GFP_KERNEL))
+	if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
 		goto oom_free_page;
 
 	entry = mk_pte(page, vma->vm_page_prot);
@@ -2601,7 +2622,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				ret = VM_FAULT_OOM;
 				goto out;
 			}
-			if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
+			if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
 				ret = VM_FAULT_OOM;
 				page_cache_release(page);
 				goto out;
@@ -3151,6 +3172,15 @@ void print_vma_addr(char *prefix, unsigned long ip)
 #ifdef CONFIG_PROVE_LOCKING
 void might_fault(void)
 {
+	/*
+	 * Some code (nfs/sunrpc) uses socket ops on kernel memory while
+	 * holding the mmap_sem, this is safe because kernel memory doesn't
+	 * get paged out, therefore we'll never actually fault, and the
+	 * below annotations will generate false positives.
+	 */
+	if (segment_eq(get_fs(), KERNEL_DS))
+		return;
+
 	might_sleep();
 	/*
 	 * it would be nicer only to annotate paths which are not under
diff --git a/mm/migrate.c b/mm/migrate.c
index 5537398..a30ea5f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -121,20 +121,6 @@ static void remove_migration_pte(struct vm_area_struct *vma,
 	if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
 		goto out;
 
-	/*
-	 * Yes, ignore the return value from a GFP_ATOMIC mem_cgroup_charge.
-	 * Failure is not an option here: we're now expected to remove every
-	 * migration pte, and will cause crashes otherwise.  Normally this
-	 * is not an issue: mem_cgroup_prepare_migration bumped up the old
-	 * page_cgroup count for safety, that's now attached to the new page,
-	 * so this charge should just be another incrementation of the count,
-	 * to keep in balance with rmap.c's mem_cgroup_uncharging.  But if
-	 * there's been a force_empty, those reference counts may no longer
-	 * be reliable, and this charge can actually fail: oh well, we don't
-	 * make the situation any worse by proceeding as if it had succeeded.
-	 */
-	mem_cgroup_charge(new, mm, GFP_ATOMIC);
-
 	get_page(new);
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (is_write_migration_entry(entry))
@@ -378,9 +364,6 @@ static void migrate_page_copy(struct page *newpage, struct page *page)
 	anon = PageAnon(page);
 	page->mapping = NULL;
 
-	if (!anon) /* This page was removed from radix-tree. */
-		mem_cgroup_uncharge_cache_page(page);
-
 	/*
 	 * If any waiters have accumulated on the new page then
 	 * wake them up.
@@ -614,6 +597,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	struct page *newpage = get_new_page(page, private, &result);
 	int rcu_locked = 0;
 	int charge = 0;
+	struct mem_cgroup *mem;
 
 	if (!newpage)
 		return -ENOMEM;
@@ -623,24 +607,26 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 		goto move_newpage;
 	}
 
-	charge = mem_cgroup_prepare_migration(page, newpage);
-	if (charge == -ENOMEM) {
-		rc = -ENOMEM;
-		goto move_newpage;
-	}
 	/* prepare cgroup just returns 0 or -ENOMEM */
-	BUG_ON(charge);
-
 	rc = -EAGAIN;
+
 	if (!trylock_page(page)) {
 		if (!force)
 			goto move_newpage;
 		lock_page(page);
 	}
 
+	/* charge against new page */
+	charge = mem_cgroup_prepare_migration(page, &mem);
+	if (charge == -ENOMEM) {
+		rc = -ENOMEM;
+		goto unlock;
+	}
+	BUG_ON(charge);
+
 	if (PageWriteback(page)) {
 		if (!force)
-			goto unlock;
+			goto uncharge;
 		wait_on_page_writeback(page);
 	}
 	/*
@@ -693,7 +679,9 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 rcu_unlock:
 	if (rcu_locked)
 		rcu_read_unlock();
-
+uncharge:
+	if (!charge)
+		mem_cgroup_end_migration(mem, page, newpage);
 unlock:
 	unlock_page(page);
 
@@ -709,8 +697,6 @@ unlock:
 	}
 
 move_newpage:
-	if (!charge)
-		mem_cgroup_end_migration(newpage);
 
 	/*
 	 * Move the new page to the LRU. If migration was not successful
diff --git a/mm/mmap.c b/mm/mmap.c
index a910c045..74962319 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2472,3 +2472,13 @@ void mm_drop_all_locks(struct mm_struct *mm)
 
 	mutex_unlock(&mm_all_locks_mutex);
 }
+
+/*
+ * initialise the VMA slab
+ */
+void __init mmap_init(void)
+{
+	vm_area_cachep = kmem_cache_create("vm_area_struct",
+			sizeof(struct vm_area_struct), 0,
+			SLAB_PANIC, NULL);
+}
diff --git a/mm/nommu.c b/mm/nommu.c
index 1c28ea3..60ed837 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -6,11 +6,11 @@
  *
  *  See Documentation/nommu-mmap.txt
  *
- *  Copyright (c) 2004-2005 David Howells <dhowells@redhat.com>
+ *  Copyright (c) 2004-2008 David Howells <dhowells@redhat.com>
  *  Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
  *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
  *  Copyright (c) 2002      Greg Ungerer <gerg@snapgear.com>
- *  Copyright (c) 2007      Paul Mundt <lethal@linux-sh.org>
+ *  Copyright (c) 2007-2008 Paul Mundt <lethal@linux-sh.org>
  */
 
 #include <linux/module.h>
@@ -33,6 +33,28 @@
 #include <asm/uaccess.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include "internal.h"
+
+static inline __attribute__((format(printf, 1, 2)))
+void no_printk(const char *fmt, ...)
+{
+}
+
+#if 0
+#define kenter(FMT, ...) \
+	printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__)
+#else
+#define kenter(FMT, ...) \
+	no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
+#endif
 
 #include "internal.h"
 
@@ -40,19 +62,22 @@ void *high_memory;
 struct page *mem_map;
 unsigned long max_mapnr;
 unsigned long num_physpages;
-unsigned long askedalloc, realalloc;
 atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50; /* default is 50% */
 int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
+int sysctl_nr_trim_pages = 1; /* page trimming behaviour */
 int heap_stack_gap = 0;
 
+atomic_t mmap_pages_allocated;
+
 EXPORT_SYMBOL(mem_map);
 EXPORT_SYMBOL(num_physpages);
 
-/* list of shareable VMAs */
-struct rb_root nommu_vma_tree = RB_ROOT;
-DECLARE_RWSEM(nommu_vma_sem);
+/* list of mapped, potentially shareable regions */
+static struct kmem_cache *vm_region_jar;
+struct rb_root nommu_region_tree = RB_ROOT;
+DECLARE_RWSEM(nommu_region_sem);
 
 struct vm_operations_struct generic_file_vm_ops = {
 };
@@ -124,6 +149,20 @@ unsigned int kobjsize(const void *objp)
 		return ksize(objp);
 
 	/*
+	 * If it's not a compound page, see if we have a matching VMA
+	 * region. This test is intentionally done in reverse order,
+	 * so if there's no VMA, we still fall through and hand back
+	 * PAGE_SIZE for 0-order pages.
+	 */
+	if (!PageCompound(page)) {
+		struct vm_area_struct *vma;
+
+		vma = find_vma(current->mm, (unsigned long)objp);
+		if (vma)
+			return vma->vm_end - vma->vm_start;
+	}
+
+	/*
 	 * The ksize() function is only guaranteed to work for pointers
 	 * returned by kmalloc(). So handle arbitrary pointers here.
 	 */
@@ -401,129 +440,178 @@ asmlinkage unsigned long sys_brk(unsigned long brk)
 	return mm->brk = brk;
 }
 
-#ifdef DEBUG
-static void show_process_blocks(void)
+/*
+ * initialise the VMA and region record slabs
+ */
+void __init mmap_init(void)
 {
-	struct vm_list_struct *vml;
-
-	printk("Process blocks %d:", current->pid);
-
-	for (vml = &current->mm->context.vmlist; vml; vml = vml->next) {
-		printk(" %p: %p", vml, vml->vma);
-		if (vml->vma)
-			printk(" (%d @%lx #%d)",
-			       kobjsize((void *) vml->vma->vm_start),
-			       vml->vma->vm_start,
-			       atomic_read(&vml->vma->vm_usage));
-		printk(vml->next ? " ->" : ".\n");
-	}
+	vm_region_jar = kmem_cache_create("vm_region_jar",
+					  sizeof(struct vm_region), 0,
+					  SLAB_PANIC, NULL);
+	vm_area_cachep = kmem_cache_create("vm_area_struct",
+					   sizeof(struct vm_area_struct), 0,
+					   SLAB_PANIC, NULL);
 }
-#endif /* DEBUG */
 
 /*
- * add a VMA into a process's mm_struct in the appropriate place in the list
- * - should be called with mm->mmap_sem held writelocked
+ * validate the region tree
+ * - the caller must hold the region lock
  */
-static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml)
+#ifdef CONFIG_DEBUG_NOMMU_REGIONS
+static noinline void validate_nommu_regions(void)
 {
-	struct vm_list_struct **ppv;
-
-	for (ppv = &current->mm->context.vmlist; *ppv; ppv = &(*ppv)->next)
-		if ((*ppv)->vma->vm_start > vml->vma->vm_start)
-			break;
-
-	vml->next = *ppv;
-	*ppv = vml;
+	struct vm_region *region, *last;
+	struct rb_node *p, *lastp;
+
+	lastp = rb_first(&nommu_region_tree);
+	if (!lastp)
+		return;
+
+	last = rb_entry(lastp, struct vm_region, vm_rb);
+	if (unlikely(last->vm_end <= last->vm_start))
+		BUG();
+	if (unlikely(last->vm_top < last->vm_end))
+		BUG();
+
+	while ((p = rb_next(lastp))) {
+		region = rb_entry(p, struct vm_region, vm_rb);
+		last = rb_entry(lastp, struct vm_region, vm_rb);
+
+		if (unlikely(region->vm_end <= region->vm_start))
+			BUG();
+		if (unlikely(region->vm_top < region->vm_end))
+			BUG();
+		if (unlikely(region->vm_start < last->vm_top))
+			BUG();
+
+		lastp = p;
+	}
 }
+#else
+#define validate_nommu_regions() do {} while(0)
+#endif
 
 /*
- * look up the first VMA in which addr resides, NULL if none
- * - should be called with mm->mmap_sem at least held readlocked
+ * add a region into the global tree
  */
-struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+static void add_nommu_region(struct vm_region *region)
 {
-	struct vm_list_struct *loop, *vml;
+	struct vm_region *pregion;
+	struct rb_node **p, *parent;
 
-	/* search the vm_start ordered list */
-	vml = NULL;
-	for (loop = mm->context.vmlist; loop; loop = loop->next) {
-		if (loop->vma->vm_start > addr)
-			break;
-		vml = loop;
+	validate_nommu_regions();
+
+	BUG_ON(region->vm_start & ~PAGE_MASK);
+
+	parent = NULL;
+	p = &nommu_region_tree.rb_node;
+	while (*p) {
+		parent = *p;
+		pregion = rb_entry(parent, struct vm_region, vm_rb);
+		if (region->vm_start < pregion->vm_start)
+			p = &(*p)->rb_left;
+		else if (region->vm_start > pregion->vm_start)
+			p = &(*p)->rb_right;
+		else if (pregion == region)
+			return;
+		else
+			BUG();
 	}
 
-	if (vml && vml->vma->vm_end > addr)
-		return vml->vma;
+	rb_link_node(&region->vm_rb, parent, p);
+	rb_insert_color(&region->vm_rb, &nommu_region_tree);
 
-	return NULL;
+	validate_nommu_regions();
 }
-EXPORT_SYMBOL(find_vma);
 
 /*
- * find a VMA
- * - we don't extend stack VMAs under NOMMU conditions
+ * delete a region from the global tree
  */
-struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
+static void delete_nommu_region(struct vm_region *region)
 {
-	return find_vma(mm, addr);
-}
+	BUG_ON(!nommu_region_tree.rb_node);
 
-int expand_stack(struct vm_area_struct *vma, unsigned long address)
-{
-	return -ENOMEM;
+	validate_nommu_regions();
+	rb_erase(&region->vm_rb, &nommu_region_tree);
+	validate_nommu_regions();
 }
 
 /*
- * look up the first VMA exactly that exactly matches addr
- * - should be called with mm->mmap_sem at least held readlocked
+ * free a contiguous series of pages
  */
-static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
-						    unsigned long addr)
+static void free_page_series(unsigned long from, unsigned long to)
 {
-	struct vm_list_struct *vml;
-
-	/* search the vm_start ordered list */
-	for (vml = mm->context.vmlist; vml; vml = vml->next) {
-		if (vml->vma->vm_start == addr)
-			return vml->vma;
-		if (vml->vma->vm_start > addr)
-			break;
+	for (; from < to; from += PAGE_SIZE) {
+		struct page *page = virt_to_page(from);
+
+		kdebug("- free %lx", from);
+		atomic_dec(&mmap_pages_allocated);
+		if (page_count(page) != 1)
+			kdebug("free page %p [%d]", page, page_count(page));
+		put_page(page);
 	}
-
-	return NULL;
 }
 
 /*
- * find a VMA in the global tree
+ * release a reference to a region
+ * - the caller must hold the region semaphore, which this releases
+ * - the region may not have been added to the tree yet, in which case vm_top
+ *   will equal vm_start
  */
-static inline struct vm_area_struct *find_nommu_vma(unsigned long start)
+static void __put_nommu_region(struct vm_region *region)
+	__releases(nommu_region_sem)
 {
-	struct vm_area_struct *vma;
-	struct rb_node *n = nommu_vma_tree.rb_node;
+	kenter("%p{%d}", region, atomic_read(&region->vm_usage));
 
-	while (n) {
-		vma = rb_entry(n, struct vm_area_struct, vm_rb);
+	BUG_ON(!nommu_region_tree.rb_node);
 
-		if (start < vma->vm_start)
-			n = n->rb_left;
-		else if (start > vma->vm_start)
-			n = n->rb_right;
-		else
-			return vma;
+	if (atomic_dec_and_test(&region->vm_usage)) {
+		if (region->vm_top > region->vm_start)
+			delete_nommu_region(region);
+		up_write(&nommu_region_sem);
+
+		if (region->vm_file)
+			fput(region->vm_file);
+
+		/* IO memory and memory shared directly out of the pagecache
+		 * from ramfs/tmpfs mustn't be released here */
+		if (region->vm_flags & VM_MAPPED_COPY) {
+			kdebug("free series");
+			free_page_series(region->vm_start, region->vm_top);
+		}
+		kmem_cache_free(vm_region_jar, region);
+	} else {
+		up_write(&nommu_region_sem);
 	}
+}
 
-	return NULL;
+/*
+ * release a reference to a region
+ */
+static void put_nommu_region(struct vm_region *region)
+{
+	down_write(&nommu_region_sem);
+	__put_nommu_region(region);
 }
 
 /*
- * add a VMA in the global tree
+ * add a VMA into a process's mm_struct in the appropriate place in the list
+ * and tree and add to the address space's page tree also if not an anonymous
+ * page
+ * - should be called with mm->mmap_sem held writelocked
  */
-static void add_nommu_vma(struct vm_area_struct *vma)
+static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct vm_area_struct *pvma;
+	struct vm_area_struct *pvma, **pp;
 	struct address_space *mapping;
-	struct rb_node **p = &nommu_vma_tree.rb_node;
-	struct rb_node *parent = NULL;
+	struct rb_node **p, *parent;
+
+	kenter(",%p", vma);
+
+	BUG_ON(!vma->vm_region);
+
+	mm->map_count++;
+	vma->vm_mm = mm;
 
 	/* add the VMA to the mapping */
 	if (vma->vm_file) {
@@ -534,42 +622,62 @@ static void add_nommu_vma(struct vm_area_struct *vma)
 		flush_dcache_mmap_unlock(mapping);
 	}
 
-	/* add the VMA to the master list */
+	/* add the VMA to the tree */
+	parent = NULL;
+	p = &mm->mm_rb.rb_node;
 	while (*p) {
 		parent = *p;
 		pvma = rb_entry(parent, struct vm_area_struct, vm_rb);
 
-		if (vma->vm_start < pvma->vm_start) {
+		/* sort by: start addr, end addr, VMA struct addr in that order
+		 * (the latter is necessary as we may get identical VMAs) */
+		if (vma->vm_start < pvma->vm_start)
 			p = &(*p)->rb_left;
-		}
-		else if (vma->vm_start > pvma->vm_start) {
+		else if (vma->vm_start > pvma->vm_start)
 			p = &(*p)->rb_right;
-		}
-		else {
-			/* mappings are at the same address - this can only
-			 * happen for shared-mem chardevs and shared file
-			 * mappings backed by ramfs/tmpfs */
-			BUG_ON(!(pvma->vm_flags & VM_SHARED));
-
-			if (vma < pvma)
-				p = &(*p)->rb_left;
-			else if (vma > pvma)
-				p = &(*p)->rb_right;
-			else
-				BUG();
-		}
+		else if (vma->vm_end < pvma->vm_end)
+			p = &(*p)->rb_left;
+		else if (vma->vm_end > pvma->vm_end)
+			p = &(*p)->rb_right;
+		else if (vma < pvma)
+			p = &(*p)->rb_left;
+		else if (vma > pvma)
+			p = &(*p)->rb_right;
+		else
+			BUG();
 	}
 
 	rb_link_node(&vma->vm_rb, parent, p);
-	rb_insert_color(&vma->vm_rb, &nommu_vma_tree);
+	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
+
+	/* add VMA to the VMA list also */
+	for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) {
+		if (pvma->vm_start > vma->vm_start)
+			break;
+		if (pvma->vm_start < vma->vm_start)
+			continue;
+		if (pvma->vm_end < vma->vm_end)
+			break;
+	}
+
+	vma->vm_next = *pp;
+	*pp = vma;
 }
 
 /*
- * delete a VMA from the global list
+ * delete a VMA from its owning mm_struct and address space
  */
-static void delete_nommu_vma(struct vm_area_struct *vma)
+static void delete_vma_from_mm(struct vm_area_struct *vma)
 {
+	struct vm_area_struct **pp;
 	struct address_space *mapping;
+	struct mm_struct *mm = vma->vm_mm;
+
+	kenter("%p", vma);
+
+	mm->map_count--;
+	if (mm->mmap_cache == vma)
+		mm->mmap_cache = NULL;
 
 	/* remove the VMA from the mapping */
 	if (vma->vm_file) {
@@ -580,8 +688,115 @@ static void delete_nommu_vma(struct vm_area_struct *vma)
 		flush_dcache_mmap_unlock(mapping);
 	}
 
-	/* remove from the master list */
-	rb_erase(&vma->vm_rb, &nommu_vma_tree);
+	/* remove from the MM's tree and list */
+	rb_erase(&vma->vm_rb, &mm->mm_rb);
+	for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) {
+		if (*pp == vma) {
+			*pp = vma->vm_next;
+			break;
+		}
+	}
+
+	vma->vm_mm = NULL;
+}
+
+/*
+ * destroy a VMA record
+ */
+static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+	kenter("%p", vma);
+	if (vma->vm_ops && vma->vm_ops->close)
+		vma->vm_ops->close(vma);
+	if (vma->vm_file) {
+		fput(vma->vm_file);
+		if (vma->vm_flags & VM_EXECUTABLE)
+			removed_exe_file_vma(mm);
+	}
+	put_nommu_region(vma->vm_region);
+	kmem_cache_free(vm_area_cachep, vma);
+}
+
+/*
+ * look up the first VMA in which addr resides, NULL if none
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma;
+	struct rb_node *n = mm->mm_rb.rb_node;
+
+	/* check the cache first */
+	vma = mm->mmap_cache;
+	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+		return vma;
+
+	/* trawl the tree (there may be multiple mappings in which addr
+	 * resides) */
+	for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
+		vma = rb_entry(n, struct vm_area_struct, vm_rb);
+		if (vma->vm_start > addr)
+			return NULL;
+		if (vma->vm_end > addr) {
+			mm->mmap_cache = vma;
+			return vma;
+		}
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(find_vma);
+
+/*
+ * find a VMA
+ * - we don't extend stack VMAs under NOMMU conditions
+ */
+struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
+{
+	return find_vma(mm, addr);
+}
+
+/*
+ * expand a stack to a given address
+ * - not supported under NOMMU conditions
+ */
+int expand_stack(struct vm_area_struct *vma, unsigned long address)
+{
+	return -ENOMEM;
+}
+
+/*
+ * look up the first VMA exactly that exactly matches addr
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
+					     unsigned long addr,
+					     unsigned long len)
+{
+	struct vm_area_struct *vma;
+	struct rb_node *n = mm->mm_rb.rb_node;
+	unsigned long end = addr + len;
+
+	/* check the cache first */
+	vma = mm->mmap_cache;
+	if (vma && vma->vm_start == addr && vma->vm_end == end)
+		return vma;
+
+	/* trawl the tree (there may be multiple mappings in which addr
+	 * resides) */
+	for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
+		vma = rb_entry(n, struct vm_area_struct, vm_rb);
+		if (vma->vm_start < addr)
+			continue;
+		if (vma->vm_start > addr)
+			return NULL;
+		if (vma->vm_end == end) {
+			mm->mmap_cache = vma;
+			return vma;
+		}
+	}
+
+	return NULL;
 }
 
 /*
@@ -596,7 +811,7 @@ static int validate_mmap_request(struct file *file,
 				 unsigned long pgoff,
 				 unsigned long *_capabilities)
 {
-	unsigned long capabilities;
+	unsigned long capabilities, rlen;
 	unsigned long reqprot = prot;
 	int ret;
 
@@ -616,12 +831,12 @@ static int validate_mmap_request(struct file *file,
 		return -EINVAL;
 
 	/* Careful about overflows.. */
-	len = PAGE_ALIGN(len);
-	if (!len || len > TASK_SIZE)
+	rlen = PAGE_ALIGN(len);
+	if (!rlen || rlen > TASK_SIZE)
 		return -ENOMEM;
 
 	/* offset overflow? */
-	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
+	if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff)
 		return -EOVERFLOW;
 
 	if (file) {
@@ -795,13 +1010,18 @@ static unsigned long determine_vm_flags(struct file *file,
 }
 
 /*
- * set up a shared mapping on a file
+ * set up a shared mapping on a file (the driver or filesystem provides and
+ * pins the storage)
  */
-static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len)
+static int do_mmap_shared_file(struct vm_area_struct *vma)
 {
 	int ret;
 
 	ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
+	if (ret == 0) {
+		vma->vm_region->vm_top = vma->vm_region->vm_end;
+		return ret;
+	}
 	if (ret != -ENOSYS)
 		return ret;
 
@@ -815,10 +1035,14 @@ static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len)
 /*
  * set up a private mapping or an anonymous shared mapping
  */
-static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
+static int do_mmap_private(struct vm_area_struct *vma,
+			   struct vm_region *region,
+			   unsigned long len)
 {
+	struct page *pages;
+	unsigned long total, point, n, rlen;
 	void *base;
-	int ret;
+	int ret, order;
 
 	/* invoke the file's mapping function so that it can keep track of
 	 * shared mappings on devices or memory
@@ -826,34 +1050,63 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
 	 */
 	if (vma->vm_file) {
 		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
-		if (ret != -ENOSYS) {
+		if (ret == 0) {
 			/* shouldn't return success if we're not sharing */
-			BUG_ON(ret == 0 && !(vma->vm_flags & VM_MAYSHARE));
-			return ret; /* success or a real error */
+			BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
+			vma->vm_region->vm_top = vma->vm_region->vm_end;
+			return ret;
 		}
+		if (ret != -ENOSYS)
+			return ret;
 
 		/* getting an ENOSYS error indicates that direct mmap isn't
 		 * possible (as opposed to tried but failed) so we'll try to
 		 * make a private copy of the data and map that instead */
 	}
 
+	rlen = PAGE_ALIGN(len);
+
 	/* allocate some memory to hold the mapping
 	 * - note that this may not return a page-aligned address if the object
 	 *   we're allocating is smaller than a page
 	 */
-	base = kmalloc(len, GFP_KERNEL|__GFP_COMP);
-	if (!base)
+	order = get_order(rlen);
+	kdebug("alloc order %d for %lx", order, len);
+
+	pages = alloc_pages(GFP_KERNEL, order);
+	if (!pages)
 		goto enomem;
 
-	vma->vm_start = (unsigned long) base;
-	vma->vm_end = vma->vm_start + len;
-	vma->vm_flags |= VM_MAPPED_COPY;
+	total = 1 << order;
+	atomic_add(total, &mmap_pages_allocated);
+
+	point = rlen >> PAGE_SHIFT;
+
+	/* we allocated a power-of-2 sized page set, so we may want to trim off
+	 * the excess */
+	if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) {
+		while (total > point) {
+			order = ilog2(total - point);
+			n = 1 << order;
+			kdebug("shave %lu/%lu @%lu", n, total - point, total);
+			atomic_sub(n, &mmap_pages_allocated);
+			total -= n;
+			set_page_refcounted(pages + total);
+			__free_pages(pages + total, order);
+		}
+	}
+
+	for (point = 1; point < total; point++)
+		set_page_refcounted(&pages[point]);
 
-#ifdef WARN_ON_SLACK
-	if (len + WARN_ON_SLACK <= kobjsize(result))
-		printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n",
-		       len, current->pid, kobjsize(result) - len);
-#endif
+	base = page_address(pages);
+	region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY;
+	region->vm_start = (unsigned long) base;
+	region->vm_end   = region->vm_start + rlen;
+	region->vm_top   = region->vm_start + (total << PAGE_SHIFT);
+
+	vma->vm_start = region->vm_start;
+	vma->vm_end   = region->vm_start + len;
 
 	if (vma->vm_file) {
 		/* read the contents of a file into the copy */
@@ -865,26 +1118,28 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
 
 		old_fs = get_fs();
 		set_fs(KERNEL_DS);
-		ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos);
+		ret = vma->vm_file->f_op->read(vma->vm_file, base, rlen, &fpos);
 		set_fs(old_fs);
 
 		if (ret < 0)
 			goto error_free;
 
 		/* clear the last little bit */
-		if (ret < len)
-			memset(base + ret, 0, len - ret);
+		if (ret < rlen)
+			memset(base + ret, 0, rlen - ret);
 
 	} else {
 		/* if it's an anonymous mapping, then just clear it */
-		memset(base, 0, len);
+		memset(base, 0, rlen);
 	}
 
 	return 0;
 
 error_free:
-	kfree(base);
-	vma->vm_start = 0;
+	free_page_series(region->vm_start, region->vm_end);
+	region->vm_start = vma->vm_start = 0;
+	region->vm_end   = vma->vm_end = 0;
+	region->vm_top   = 0;
 	return ret;
 
 enomem:
@@ -904,13 +1159,14 @@ unsigned long do_mmap_pgoff(struct file *file,
 			    unsigned long flags,
 			    unsigned long pgoff)
 {
-	struct vm_list_struct *vml = NULL;
-	struct vm_area_struct *vma = NULL;
+	struct vm_area_struct *vma;
+	struct vm_region *region;
 	struct rb_node *rb;
-	unsigned long capabilities, vm_flags;
-	void *result;
+	unsigned long capabilities, vm_flags, result;
 	int ret;
 
+	kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
+
 	if (!(flags & MAP_FIXED))
 		addr = round_hint_to_min(addr);
 
@@ -918,73 +1174,120 @@ unsigned long do_mmap_pgoff(struct file *file,
 	 * mapping */
 	ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
 				    &capabilities);
-	if (ret < 0)
+	if (ret < 0) {
+		kleave(" = %d [val]", ret);
 		return ret;
+	}
 
 	/* we've determined that we can make the mapping, now translate what we
 	 * now know into VMA flags */
 	vm_flags = determine_vm_flags(file, prot, flags, capabilities);
 
-	/* we're going to need to record the mapping if it works */
-	vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL);
-	if (!vml)
-		goto error_getting_vml;
+	/* we're going to need to record the mapping */
+	region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL);
+	if (!region)
+		goto error_getting_region;
+
+	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	if (!vma)
+		goto error_getting_vma;
+
+	atomic_set(&region->vm_usage, 1);
+	region->vm_flags = vm_flags;
+	region->vm_pgoff = pgoff;
+
+	INIT_LIST_HEAD(&vma->anon_vma_node);
+	vma->vm_flags = vm_flags;
+	vma->vm_pgoff = pgoff;
 
-	down_write(&nommu_vma_sem);
+	if (file) {
+		region->vm_file = file;
+		get_file(file);
+		vma->vm_file = file;
+		get_file(file);
+		if (vm_flags & VM_EXECUTABLE) {
+			added_exe_file_vma(current->mm);
+			vma->vm_mm = current->mm;
+		}
+	}
 
-	/* if we want to share, we need to check for VMAs created by other
+	down_write(&nommu_region_sem);
+
+	/* if we want to share, we need to check for regions created by other
 	 * mmap() calls that overlap with our proposed mapping
-	 * - we can only share with an exact match on most regular files
+	 * - we can only share with a superset match on most regular files
 	 * - shared mappings on character devices and memory backed files are
 	 *   permitted to overlap inexactly as far as we are concerned for in
 	 *   these cases, sharing is handled in the driver or filesystem rather
 	 *   than here
 	 */
 	if (vm_flags & VM_MAYSHARE) {
-		unsigned long pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		unsigned long vmpglen;
+		struct vm_region *pregion;
+		unsigned long pglen, rpglen, pgend, rpgend, start;
 
-		/* suppress VMA sharing for shared regions */
-		if (vm_flags & VM_SHARED &&
-		    capabilities & BDI_CAP_MAP_DIRECT)
-			goto dont_share_VMAs;
+		pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		pgend = pgoff + pglen;
 
-		for (rb = rb_first(&nommu_vma_tree); rb; rb = rb_next(rb)) {
-			vma = rb_entry(rb, struct vm_area_struct, vm_rb);
+		for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) {
+			pregion = rb_entry(rb, struct vm_region, vm_rb);
 
-			if (!(vma->vm_flags & VM_MAYSHARE))
+			if (!(pregion->vm_flags & VM_MAYSHARE))
 				continue;
 
 			/* search for overlapping mappings on the same file */
-			if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode)
+			if (pregion->vm_file->f_path.dentry->d_inode !=
+			    file->f_path.dentry->d_inode)
 				continue;
 
-			if (vma->vm_pgoff >= pgoff + pglen)
+			if (pregion->vm_pgoff >= pgend)
 				continue;
 
-			vmpglen = vma->vm_end - vma->vm_start + PAGE_SIZE - 1;
-			vmpglen >>= PAGE_SHIFT;
-			if (pgoff >= vma->vm_pgoff + vmpglen)
+			rpglen = pregion->vm_end - pregion->vm_start;
+			rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+			rpgend = pregion->vm_pgoff + rpglen;
+			if (pgoff >= rpgend)
 				continue;
 
-			/* handle inexactly overlapping matches between mappings */
-			if (vma->vm_pgoff != pgoff || vmpglen != pglen) {
+			/* handle inexactly overlapping matches between
+			 * mappings */
+			if ((pregion->vm_pgoff != pgoff || rpglen != pglen) &&
+			    !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) {
+				/* new mapping is not a subset of the region */
 				if (!(capabilities & BDI_CAP_MAP_DIRECT))
 					goto sharing_violation;
 				continue;
 			}
 
-			/* we've found a VMA we can share */
-			atomic_inc(&vma->vm_usage);
-
-			vml->vma = vma;
-			result = (void *) vma->vm_start;
-			goto shared;
+			/* we've found a region we can share */
+			atomic_inc(&pregion->vm_usage);
+			vma->vm_region = pregion;
+			start = pregion->vm_start;
+			start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT;
+			vma->vm_start = start;
+			vma->vm_end = start + len;
+
+			if (pregion->vm_flags & VM_MAPPED_COPY) {
+				kdebug("share copy");
+				vma->vm_flags |= VM_MAPPED_COPY;
+			} else {
+				kdebug("share mmap");
+				ret = do_mmap_shared_file(vma);
+				if (ret < 0) {
+					vma->vm_region = NULL;
+					vma->vm_start = 0;
+					vma->vm_end = 0;
+					atomic_dec(&pregion->vm_usage);
+					pregion = NULL;
+					goto error_just_free;
+				}
+			}
+			fput(region->vm_file);
+			kmem_cache_free(vm_region_jar, region);
+			region = pregion;
+			result = start;
+			goto share;
 		}
 
-	dont_share_VMAs:
-		vma = NULL;
-
 		/* obtain the address at which to make a shared mapping
 		 * - this is the hook for quasi-memory character devices to
 		 *   tell us the location of a shared mapping
@@ -995,113 +1298,93 @@ unsigned long do_mmap_pgoff(struct file *file,
 			if (IS_ERR((void *) addr)) {
 				ret = addr;
 				if (ret != (unsigned long) -ENOSYS)
-					goto error;
+					goto error_just_free;
 
 				/* the driver refused to tell us where to site
 				 * the mapping so we'll have to attempt to copy
 				 * it */
 				ret = (unsigned long) -ENODEV;
 				if (!(capabilities & BDI_CAP_MAP_COPY))
-					goto error;
+					goto error_just_free;
 
 				capabilities &= ~BDI_CAP_MAP_DIRECT;
+			} else {
+				vma->vm_start = region->vm_start = addr;
+				vma->vm_end = region->vm_end = addr + len;
 			}
 		}
 	}
 
-	/* we're going to need a VMA struct as well */
-	vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL);
-	if (!vma)
-		goto error_getting_vma;
-
-	INIT_LIST_HEAD(&vma->anon_vma_node);
-	atomic_set(&vma->vm_usage, 1);
-	if (file) {
-		get_file(file);
-		if (vm_flags & VM_EXECUTABLE) {
-			added_exe_file_vma(current->mm);
-			vma->vm_mm = current->mm;
-		}
-	}
-	vma->vm_file	= file;
-	vma->vm_flags	= vm_flags;
-	vma->vm_start	= addr;
-	vma->vm_end	= addr + len;
-	vma->vm_pgoff	= pgoff;
-
-	vml->vma = vma;
+	vma->vm_region = region;
 
 	/* set up the mapping */
 	if (file && vma->vm_flags & VM_SHARED)
-		ret = do_mmap_shared_file(vma, len);
+		ret = do_mmap_shared_file(vma);
 	else
-		ret = do_mmap_private(vma, len);
+		ret = do_mmap_private(vma, region, len);
 	if (ret < 0)
-		goto error;
-
-	/* okay... we have a mapping; now we have to register it */
-	result = (void *) vma->vm_start;
+		goto error_put_region;
 
-	if (vma->vm_flags & VM_MAPPED_COPY) {
-		realalloc += kobjsize(result);
-		askedalloc += len;
-	}
+	add_nommu_region(region);
 
-	realalloc += kobjsize(vma);
-	askedalloc += sizeof(*vma);
+	/* okay... we have a mapping; now we have to register it */
+	result = vma->vm_start;
 
 	current->mm->total_vm += len >> PAGE_SHIFT;
 
-	add_nommu_vma(vma);
-
- shared:
-	realalloc += kobjsize(vml);
-	askedalloc += sizeof(*vml);
-
-	add_vma_to_mm(current->mm, vml);
+share:
+	add_vma_to_mm(current->mm, vma);
 
-	up_write(&nommu_vma_sem);
+	up_write(&nommu_region_sem);
 
 	if (prot & PROT_EXEC)
-		flush_icache_range((unsigned long) result,
-				   (unsigned long) result + len);
+		flush_icache_range(result, result + len);
 
-#ifdef DEBUG
-	printk("do_mmap:\n");
-	show_process_blocks();
-#endif
-
-	return (unsigned long) result;
+	kleave(" = %lx", result);
+	return result;
 
- error:
-	up_write(&nommu_vma_sem);
-	kfree(vml);
+error_put_region:
+	__put_nommu_region(region);
 	if (vma) {
 		if (vma->vm_file) {
 			fput(vma->vm_file);
 			if (vma->vm_flags & VM_EXECUTABLE)
 				removed_exe_file_vma(vma->vm_mm);
 		}
-		kfree(vma);
+		kmem_cache_free(vm_area_cachep, vma);
 	}
+	kleave(" = %d [pr]", ret);
 	return ret;
 
- sharing_violation:
-	up_write(&nommu_vma_sem);
-	printk("Attempt to share mismatched mappings\n");
-	kfree(vml);
-	return -EINVAL;
+error_just_free:
+	up_write(&nommu_region_sem);
+error:
+	fput(region->vm_file);
+	kmem_cache_free(vm_region_jar, region);
+	fput(vma->vm_file);
+	if (vma->vm_flags & VM_EXECUTABLE)
+		removed_exe_file_vma(vma->vm_mm);
+	kmem_cache_free(vm_area_cachep, vma);
+	kleave(" = %d", ret);
+	return ret;
 
- error_getting_vma:
-	up_write(&nommu_vma_sem);
-	kfree(vml);
-	printk("Allocation of vma for %lu byte allocation from process %d failed\n",
+sharing_violation:
+	up_write(&nommu_region_sem);
+	printk(KERN_WARNING "Attempt to share mismatched mappings\n");
+	ret = -EINVAL;
+	goto error;
+
+error_getting_vma:
+	kmem_cache_free(vm_region_jar, region);
+	printk(KERN_WARNING "Allocation of vma for %lu byte allocation"
+	       " from process %d failed\n",
 	       len, current->pid);
 	show_free_areas();
 	return -ENOMEM;
 
- error_getting_vml:
-	printk("Allocation of vml for %lu byte allocation from process %d failed\n",
+error_getting_region:
+	printk(KERN_WARNING "Allocation of vm region for %lu byte allocation"
+	       " from process %d failed\n",
 	       len, current->pid);
 	show_free_areas();
 	return -ENOMEM;
@@ -1109,85 +1392,183 @@ unsigned long do_mmap_pgoff(struct file *file,
 EXPORT_SYMBOL(do_mmap_pgoff);
 
 /*
- * handle mapping disposal for uClinux
+ * split a vma into two pieces at address 'addr', a new vma is allocated either
+ * for the first part or the tail.
  */
-static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+	      unsigned long addr, int new_below)
 {
-	if (vma) {
-		down_write(&nommu_vma_sem);
+	struct vm_area_struct *new;
+	struct vm_region *region;
+	unsigned long npages;
 
-		if (atomic_dec_and_test(&vma->vm_usage)) {
-			delete_nommu_vma(vma);
+	kenter("");
 
-			if (vma->vm_ops && vma->vm_ops->close)
-				vma->vm_ops->close(vma);
+	/* we're only permitted to split anonymous regions that have a single
+	 * owner */
+	if (vma->vm_file ||
+	    atomic_read(&vma->vm_region->vm_usage) != 1)
+		return -ENOMEM;
 
-			/* IO memory and memory shared directly out of the pagecache from
-			 * ramfs/tmpfs mustn't be released here */
-			if (vma->vm_flags & VM_MAPPED_COPY) {
-				realalloc -= kobjsize((void *) vma->vm_start);
-				askedalloc -= vma->vm_end - vma->vm_start;
-				kfree((void *) vma->vm_start);
-			}
+	if (mm->map_count >= sysctl_max_map_count)
+		return -ENOMEM;
 
-			realalloc -= kobjsize(vma);
-			askedalloc -= sizeof(*vma);
+	region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL);
+	if (!region)
+		return -ENOMEM;
 
-			if (vma->vm_file) {
-				fput(vma->vm_file);
-				if (vma->vm_flags & VM_EXECUTABLE)
-					removed_exe_file_vma(mm);
-			}
-			kfree(vma);
-		}
+	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	if (!new) {
+		kmem_cache_free(vm_region_jar, region);
+		return -ENOMEM;
+	}
+
+	/* most fields are the same, copy all, and then fixup */
+	*new = *vma;
+	*region = *vma->vm_region;
+	new->vm_region = region;
+
+	npages = (addr - vma->vm_start) >> PAGE_SHIFT;
 
-		up_write(&nommu_vma_sem);
+	if (new_below) {
+		region->vm_top = region->vm_end = new->vm_end = addr;
+	} else {
+		region->vm_start = new->vm_start = addr;
+		region->vm_pgoff = new->vm_pgoff += npages;
+	}
+
+	if (new->vm_ops && new->vm_ops->open)
+		new->vm_ops->open(new);
+
+	delete_vma_from_mm(vma);
+	down_write(&nommu_region_sem);
+	delete_nommu_region(vma->vm_region);
+	if (new_below) {
+		vma->vm_region->vm_start = vma->vm_start = addr;
+		vma->vm_region->vm_pgoff = vma->vm_pgoff += npages;
+	} else {
+		vma->vm_region->vm_end = vma->vm_end = addr;
+		vma->vm_region->vm_top = addr;
 	}
+	add_nommu_region(vma->vm_region);
+	add_nommu_region(new->vm_region);
+	up_write(&nommu_region_sem);
+	add_vma_to_mm(mm, vma);
+	add_vma_to_mm(mm, new);
+	return 0;
 }
 
 /*
- * release a mapping
- * - under NOMMU conditions the parameters must match exactly to the mapping to
- *   be removed
+ * shrink a VMA by removing the specified chunk from either the beginning or
+ * the end
  */
-int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
+static int shrink_vma(struct mm_struct *mm,
+		      struct vm_area_struct *vma,
+		      unsigned long from, unsigned long to)
 {
-	struct vm_list_struct *vml, **parent;
-	unsigned long end = addr + len;
+	struct vm_region *region;
 
-#ifdef DEBUG
-	printk("do_munmap:\n");
-#endif
+	kenter("");
 
-	for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) {
-		if ((*parent)->vma->vm_start > addr)
-			break;
-		if ((*parent)->vma->vm_start == addr &&
-		    ((len == 0) || ((*parent)->vma->vm_end == end)))
-			goto found;
+	/* adjust the VMA's pointers, which may reposition it in the MM's tree
+	 * and list */
+	delete_vma_from_mm(vma);
+	if (from > vma->vm_start)
+		vma->vm_end = from;
+	else
+		vma->vm_start = to;
+	add_vma_to_mm(mm, vma);
+
+	/* cut the backing region down to size */
+	region = vma->vm_region;
+	BUG_ON(atomic_read(&region->vm_usage) != 1);
+
+	down_write(&nommu_region_sem);
+	delete_nommu_region(region);
+	if (from > region->vm_start) {
+		to = region->vm_top;
+		region->vm_top = region->vm_end = from;
+	} else {
+		region->vm_start = to;
 	}
+	add_nommu_region(region);
+	up_write(&nommu_region_sem);
 
-	printk("munmap of non-mmaped memory by process %d (%s): %p\n",
-	       current->pid, current->comm, (void *) addr);
-	return -EINVAL;
+	free_page_series(from, to);
+	return 0;
+}
 
- found:
-	vml = *parent;
+/*
+ * release a mapping
+ * - under NOMMU conditions the chunk to be unmapped must be backed by a single
+ *   VMA, though it need not cover the whole VMA
+ */
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+{
+	struct vm_area_struct *vma;
+	struct rb_node *rb;
+	unsigned long end = start + len;
+	int ret;
 
-	put_vma(mm, vml->vma);
+	kenter(",%lx,%zx", start, len);
 
-	*parent = vml->next;
-	realalloc -= kobjsize(vml);
-	askedalloc -= sizeof(*vml);
-	kfree(vml);
+	if (len == 0)
+		return -EINVAL;
 
-	update_hiwater_vm(mm);
-	mm->total_vm -= len >> PAGE_SHIFT;
+	/* find the first potentially overlapping VMA */
+	vma = find_vma(mm, start);
+	if (!vma) {
+		printk(KERN_WARNING
+		       "munmap of memory not mmapped by process %d (%s):"
+		       " 0x%lx-0x%lx\n",
+		       current->pid, current->comm, start, start + len - 1);
+		return -EINVAL;
+	}
 
-#ifdef DEBUG
-	show_process_blocks();
-#endif
+	/* we're allowed to split an anonymous VMA but not a file-backed one */
+	if (vma->vm_file) {
+		do {
+			if (start > vma->vm_start) {
+				kleave(" = -EINVAL [miss]");
+				return -EINVAL;
+			}
+			if (end == vma->vm_end)
+				goto erase_whole_vma;
+			rb = rb_next(&vma->vm_rb);
+			vma = rb_entry(rb, struct vm_area_struct, vm_rb);
+		} while (rb);
+		kleave(" = -EINVAL [split file]");
+		return -EINVAL;
+	} else {
+		/* the chunk must be a subset of the VMA found */
+		if (start == vma->vm_start && end == vma->vm_end)
+			goto erase_whole_vma;
+		if (start < vma->vm_start || end > vma->vm_end) {
+			kleave(" = -EINVAL [superset]");
+			return -EINVAL;
+		}
+		if (start & ~PAGE_MASK) {
+			kleave(" = -EINVAL [unaligned start]");
+			return -EINVAL;
+		}
+		if (end != vma->vm_end && end & ~PAGE_MASK) {
+			kleave(" = -EINVAL [unaligned split]");
+			return -EINVAL;
+		}
+		if (start != vma->vm_start && end != vma->vm_end) {
+			ret = split_vma(mm, vma, start, 1);
+			if (ret < 0) {
+				kleave(" = %d [split]", ret);
+				return ret;
+			}
+		}
+		return shrink_vma(mm, vma, start, end);
+	}
 
+erase_whole_vma:
+	delete_vma_from_mm(vma);
+	delete_vma(mm, vma);
+	kleave(" = 0");
 	return 0;
 }
 EXPORT_SYMBOL(do_munmap);
@@ -1204,32 +1585,26 @@ asmlinkage long sys_munmap(unsigned long addr, size_t len)
 }
 
 /*
- * Release all mappings
+ * release all the mappings made in a process's VM space
  */
-void exit_mmap(struct mm_struct * mm)
+void exit_mmap(struct mm_struct *mm)
 {
-	struct vm_list_struct *tmp;
-
-	if (mm) {
-#ifdef DEBUG
-		printk("Exit_mmap:\n");
-#endif
+	struct vm_area_struct *vma;
 
-		mm->total_vm = 0;
+	if (!mm)
+		return;
 
-		while ((tmp = mm->context.vmlist)) {
-			mm->context.vmlist = tmp->next;
-			put_vma(mm, tmp->vma);
+	kenter("");
 
-			realalloc -= kobjsize(tmp);
-			askedalloc -= sizeof(*tmp);
-			kfree(tmp);
-		}
+	mm->total_vm = 0;
 
-#ifdef DEBUG
-		show_process_blocks();
-#endif
+	while ((vma = mm->mmap)) {
+		mm->mmap = vma->vm_next;
+		delete_vma_from_mm(vma);
+		delete_vma(mm, vma);
 	}
+
+	kleave("");
 }
 
 unsigned long do_brk(unsigned long addr, unsigned long len)
@@ -1242,8 +1617,8 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
  * time (controlled by the MREMAP_MAYMOVE flag and available VM space)
  *
  * under NOMMU conditions, we only permit changing a mapping's size, and only
- * as long as it stays within the hole allocated by the kmalloc() call in
- * do_mmap_pgoff() and the block is not shareable
+ * as long as it stays within the region allocated by do_mmap_private() and the
+ * block is not shareable
  *
  * MREMAP_FIXED is not supported under NOMMU conditions
  */
@@ -1254,13 +1629,16 @@ unsigned long do_mremap(unsigned long addr,
 	struct vm_area_struct *vma;
 
 	/* insanity checks first */
-	if (new_len == 0)
+	if (old_len == 0 || new_len == 0)
 		return (unsigned long) -EINVAL;
 
+	if (addr & ~PAGE_MASK)
+		return -EINVAL;
+
 	if (flags & MREMAP_FIXED && new_addr != addr)
 		return (unsigned long) -EINVAL;
 
-	vma = find_vma_exact(current->mm, addr);
+	vma = find_vma_exact(current->mm, addr, old_len);
 	if (!vma)
 		return (unsigned long) -EINVAL;
 
@@ -1270,22 +1648,19 @@ unsigned long do_mremap(unsigned long addr,
 	if (vma->vm_flags & VM_MAYSHARE)
 		return (unsigned long) -EPERM;
 
-	if (new_len > kobjsize((void *) addr))
+	if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start)
 		return (unsigned long) -ENOMEM;
 
 	/* all checks complete - do it */
 	vma->vm_end = vma->vm_start + new_len;
-
-	askedalloc -= old_len;
-	askedalloc += new_len;
-
 	return vma->vm_start;
 }
 EXPORT_SYMBOL(do_mremap);
 
-asmlinkage unsigned long sys_mremap(unsigned long addr,
-	unsigned long old_len, unsigned long new_len,
-	unsigned long flags, unsigned long new_addr)
+asmlinkage
+unsigned long sys_mremap(unsigned long addr,
+			 unsigned long old_len, unsigned long new_len,
+			 unsigned long flags, unsigned long new_addr)
 {
 	unsigned long ret;
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 6b9e758..40ba050 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -429,7 +429,6 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
 	unsigned long points = 0;
 	struct task_struct *p;
 
-	cgroup_lock();
 	read_lock(&tasklist_lock);
 retry:
 	p = select_bad_process(&points, mem);
@@ -444,7 +443,6 @@ retry:
 		goto retry;
 out:
 	read_unlock(&tasklist_lock);
-	cgroup_unlock();
 }
 #endif
 
@@ -560,6 +558,13 @@ void pagefault_out_of_memory(void)
 		/* Got some memory back in the last second. */
 		return;
 
+	/*
+	 * If this is from memcg, oom-killer is already invoked.
+	 * and not worth to go system-wide-oom.
+	 */
+	if (mem_cgroup_oom_called(current))
+		goto rest_and_return;
+
 	if (sysctl_panic_on_oom)
 		panic("out of memory from page fault. panic_on_oom is selected.\n");
 
@@ -571,6 +576,7 @@ void pagefault_out_of_memory(void)
 	 * Give "p" a good chance of killing itself before we
 	 * retry to allocate memory.
 	 */
+rest_and_return:
 	if (!test_thread_flag(TIF_MEMDIE))
 		schedule_timeout_uninterruptible(1);
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7bf22e0..5675b30 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3523,10 +3523,10 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			INIT_LIST_HEAD(&zone->lru[l].list);
 			zone->lru[l].nr_scan = 0;
 		}
-		zone->recent_rotated[0] = 0;
-		zone->recent_rotated[1] = 0;
-		zone->recent_scanned[0] = 0;
-		zone->recent_scanned[1] = 0;
+		zone->reclaim_stat.recent_rotated[0] = 0;
+		zone->reclaim_stat.recent_rotated[1] = 0;
+		zone->reclaim_stat.recent_scanned[0] = 0;
+		zone->reclaim_stat.recent_scanned[1] = 0;
 		zap_zone_vm_stats(zone);
 		zone->flags = 0;
 		if (!size)
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index d6507a6..7006a11 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -8,6 +8,7 @@
 #include <linux/memory.h>
 #include <linux/vmalloc.h>
 #include <linux/cgroup.h>
+#include <linux/swapops.h>
 
 static void __meminit
 __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
@@ -15,6 +16,7 @@ __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
 	pc->flags = 0;
 	pc->mem_cgroup = NULL;
 	pc->page = pfn_to_page(pfn);
+	INIT_LIST_HEAD(&pc->lru);
 }
 static unsigned long total_usage;
 
@@ -72,7 +74,7 @@ void __init page_cgroup_init(void)
 
 	int nid, fail;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return;
 
 	for_each_online_node(nid)  {
@@ -103,13 +105,11 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
 /* __alloc_bootmem...() is protected by !slab_available() */
 static int __init_refok init_section_page_cgroup(unsigned long pfn)
 {
-	struct mem_section *section;
+	struct mem_section *section = __pfn_to_section(pfn);
 	struct page_cgroup *base, *pc;
 	unsigned long table_size;
 	int nid, index;
 
-	section = __pfn_to_section(pfn);
-
 	if (!section->page_cgroup) {
 		nid = page_to_nid(pfn_to_page(pfn));
 		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
@@ -145,7 +145,6 @@ static int __init_refok init_section_page_cgroup(unsigned long pfn)
 		__init_page_cgroup(pc, pfn + index);
 	}
 
-	section = __pfn_to_section(pfn);
 	section->page_cgroup = base - pfn;
 	total_usage += table_size;
 	return 0;
@@ -248,7 +247,7 @@ void __init page_cgroup_init(void)
 	unsigned long pfn;
 	int fail = 0;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return;
 
 	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
@@ -273,3 +272,199 @@ void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
 }
 
 #endif
+
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static DEFINE_MUTEX(swap_cgroup_mutex);
+struct swap_cgroup_ctrl {
+	struct page **map;
+	unsigned long length;
+};
+
+struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+
+/*
+ * This 8bytes seems big..maybe we can reduce this when we can use "id" for
+ * cgroup rather than pointer.
+ */
+struct swap_cgroup {
+	struct mem_cgroup	*val;
+};
+#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
+#define SC_POS_MASK	(SC_PER_PAGE - 1)
+
+/*
+ * SwapCgroup implements "lookup" and "exchange" operations.
+ * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
+ * against SwapCache. At swap_free(), this is accessed directly from swap.
+ *
+ * This means,
+ *  - we have no race in "exchange" when we're accessed via SwapCache because
+ *    SwapCache(and its swp_entry) is under lock.
+ *  - When called via swap_free(), there is no user of this entry and no race.
+ * Then, we don't need lock around "exchange".
+ *
+ * TODO: we can push these buffers out to HIGHMEM.
+ */
+
+/*
+ * allocate buffer for swap_cgroup.
+ */
+static int swap_cgroup_prepare(int type)
+{
+	struct page *page;
+	struct swap_cgroup_ctrl *ctrl;
+	unsigned long idx, max;
+
+	if (!do_swap_account)
+		return 0;
+	ctrl = &swap_cgroup_ctrl[type];
+
+	for (idx = 0; idx < ctrl->length; idx++) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			goto not_enough_page;
+		ctrl->map[idx] = page;
+	}
+	return 0;
+not_enough_page:
+	max = idx;
+	for (idx = 0; idx < max; idx++)
+		__free_page(ctrl->map[idx]);
+
+	return -ENOMEM;
+}
+
+/**
+ * swap_cgroup_record - record mem_cgroup for this swp_entry.
+ * @ent: swap entry to be recorded into
+ * @mem: mem_cgroup to be recorded
+ *
+ * Returns old value at success, NULL at failure.
+ * (Of course, old value can be NULL.)
+ */
+struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+{
+	int type = swp_type(ent);
+	unsigned long offset = swp_offset(ent);
+	unsigned long idx = offset / SC_PER_PAGE;
+	unsigned long pos = offset & SC_POS_MASK;
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+	struct mem_cgroup *old;
+
+	if (!do_swap_account)
+		return NULL;
+
+	ctrl = &swap_cgroup_ctrl[type];
+
+	mappage = ctrl->map[idx];
+	sc = page_address(mappage);
+	sc += pos;
+	old = sc->val;
+	sc->val = mem;
+
+	return old;
+}
+
+/**
+ * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
+ * @ent: swap entry to be looked up.
+ *
+ * Returns pointer to mem_cgroup at success. NULL at failure.
+ */
+struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+{
+	int type = swp_type(ent);
+	unsigned long offset = swp_offset(ent);
+	unsigned long idx = offset / SC_PER_PAGE;
+	unsigned long pos = offset & SC_POS_MASK;
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+	struct mem_cgroup *ret;
+
+	if (!do_swap_account)
+		return NULL;
+
+	ctrl = &swap_cgroup_ctrl[type];
+	mappage = ctrl->map[idx];
+	sc = page_address(mappage);
+	sc += pos;
+	ret = sc->val;
+	return ret;
+}
+
+int swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	void *array;
+	unsigned long array_size;
+	unsigned long length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return 0;
+
+	length = ((max_pages/SC_PER_PAGE) + 1);
+	array_size = length * sizeof(void *);
+
+	array = vmalloc(array_size);
+	if (!array)
+		goto nomem;
+
+	memset(array, 0, array_size);
+	ctrl = &swap_cgroup_ctrl[type];
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl->length = length;
+	ctrl->map = array;
+	if (swap_cgroup_prepare(type)) {
+		/* memory shortage */
+		ctrl->map = NULL;
+		ctrl->length = 0;
+		vfree(array);
+		mutex_unlock(&swap_cgroup_mutex);
+		goto nomem;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+
+	printk(KERN_INFO
+		"swap_cgroup: uses %ld bytes of vmalloc for pointer array space"
+		" and %ld bytes to hold mem_cgroup pointers on swap\n",
+		array_size, length * PAGE_SIZE);
+	printk(KERN_INFO
+	"swap_cgroup can be disabled by noswapaccount boot option.\n");
+
+	return 0;
+nomem:
+	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
+	printk(KERN_INFO
+		"swap_cgroup can be disabled by noswapaccount boot option\n");
+	return -ENOMEM;
+}
+
+void swap_cgroup_swapoff(int type)
+{
+	int i;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return;
+
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl = &swap_cgroup_ctrl[type];
+	if (ctrl->map) {
+		for (i = 0; i < ctrl->length; i++) {
+			struct page *page = ctrl->map[i];
+			if (page)
+				__free_page(page);
+		}
+		vfree(ctrl->map);
+		ctrl->map = NULL;
+		ctrl->length = 0;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+}
+
+#endif
diff --git a/mm/shmem.c b/mm/shmem.c
index 5941f98..5d0de96 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -928,7 +928,11 @@ found:
 	error = 1;
 	if (!inode)
 		goto out;
-	/* Precharge page using GFP_KERNEL while we can wait */
+	/*
+	 * Charge page using GFP_KERNEL while we can wait.
+	 * Charged back to the user(not to caller) when swap account is used.
+	 * add_to_page_cache() will be called with GFP_NOWAIT.
+	 */
 	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
 	if (error)
 		goto out;
@@ -1320,15 +1324,19 @@ repeat:
 		} else {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
-			unlock_page(swappage);
-			page_cache_release(swappage);
 			if (error == -ENOMEM) {
 				/* allow reclaim from this memory cgroup */
-				error = mem_cgroup_shrink_usage(current->mm,
+				error = mem_cgroup_shrink_usage(swappage,
+								current->mm,
 								gfp);
-				if (error)
+				if (error) {
+					unlock_page(swappage);
+					page_cache_release(swappage);
 					goto failed;
+				}
 			}
+			unlock_page(swappage);
+			page_cache_release(swappage);
 			goto repeat;
 		}
 	} else if (sgp == SGP_READ && !filepage) {
@@ -1379,7 +1387,7 @@ repeat:
 
 			/* Precharge page while we can wait, compensate after */
 			error = mem_cgroup_cache_charge(filepage, current->mm,
-							gfp & ~__GFP_HIGHMEM);
+					GFP_KERNEL);
 			if (error) {
 				page_cache_release(filepage);
 				shmem_unacct_blocks(info->flags, 1);
diff --git a/mm/swap.c b/mm/swap.c
index ba2c0e8..8adb9fe 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -151,6 +151,26 @@ void  rotate_reclaimable_page(struct page *page)
 	}
 }
 
+static void update_page_reclaim_stat(struct zone *zone, struct page *page,
+				     int file, int rotated)
+{
+	struct zone_reclaim_stat *reclaim_stat = &zone->reclaim_stat;
+	struct zone_reclaim_stat *memcg_reclaim_stat;
+
+	memcg_reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page);
+
+	reclaim_stat->recent_scanned[file]++;
+	if (rotated)
+		reclaim_stat->recent_rotated[file]++;
+
+	if (!memcg_reclaim_stat)
+		return;
+
+	memcg_reclaim_stat->recent_scanned[file]++;
+	if (rotated)
+		memcg_reclaim_stat->recent_rotated[file]++;
+}
+
 /*
  * FIXME: speed this up?
  */
@@ -168,10 +188,8 @@ void activate_page(struct page *page)
 		lru += LRU_ACTIVE;
 		add_page_to_lru_list(zone, page, lru);
 		__count_vm_event(PGACTIVATE);
-		mem_cgroup_move_lists(page, lru);
 
-		zone->recent_rotated[!!file]++;
-		zone->recent_scanned[!!file]++;
+		update_page_reclaim_stat(zone, page, !!file, 1);
 	}
 	spin_unlock_irq(&zone->lru_lock);
 }
@@ -386,12 +404,14 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 {
 	int i;
 	struct zone *zone = NULL;
+
 	VM_BUG_ON(is_unevictable_lru(lru));
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
 		struct zone *pagezone = page_zone(page);
 		int file;
+		int active;
 
 		if (pagezone != zone) {
 			if (zone)
@@ -403,12 +423,11 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 		VM_BUG_ON(PageUnevictable(page));
 		VM_BUG_ON(PageLRU(page));
 		SetPageLRU(page);
+		active = is_active_lru(lru);
 		file = is_file_lru(lru);
-		zone->recent_scanned[file]++;
-		if (is_active_lru(lru)) {
+		if (active)
 			SetPageActive(page);
-			zone->recent_rotated[file]++;
-		}
+		update_page_reclaim_stat(zone, page, file, active);
 		add_page_to_lru_list(zone, page, lru);
 	}
 	if (zone)
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 81c825f..3ecea98 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -17,6 +17,7 @@
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
+#include <linux/page_cgroup.h>
 
 #include <asm/pgtable.h>
 
@@ -108,6 +109,8 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
  */
 void __delete_from_swap_cache(struct page *page)
 {
+	swp_entry_t ent = {.val = page_private(page)};
+
 	VM_BUG_ON(!PageLocked(page));
 	VM_BUG_ON(!PageSwapCache(page));
 	VM_BUG_ON(PageWriteback(page));
@@ -118,6 +121,7 @@ void __delete_from_swap_cache(struct page *page)
 	total_swapcache_pages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	INC_CACHE_INFO(del_total);
+	mem_cgroup_uncharge_swapcache(page, ent);
 }
 
 /**
diff --git a/mm/swapfile.c b/mm/swapfile.c
index eec5ca7..da422c4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -33,6 +33,7 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
+#include <linux/page_cgroup.h>
 
 static DEFINE_SPINLOCK(swap_lock);
 static unsigned int nr_swapfiles;
@@ -470,8 +471,9 @@ out:
 	return NULL;
 }
 
-static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
+static int swap_entry_free(struct swap_info_struct *p, swp_entry_t ent)
 {
+	unsigned long offset = swp_offset(ent);
 	int count = p->swap_map[offset];
 
 	if (count < SWAP_MAP_MAX) {
@@ -486,6 +488,7 @@ static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
 				swap_list.next = p - swap_info;
 			nr_swap_pages++;
 			p->inuse_pages--;
+			mem_cgroup_uncharge_swap(ent);
 		}
 	}
 	return count;
@@ -501,7 +504,7 @@ void swap_free(swp_entry_t entry)
 
 	p = swap_info_get(entry);
 	if (p) {
-		swap_entry_free(p, swp_offset(entry));
+		swap_entry_free(p, entry);
 		spin_unlock(&swap_lock);
 	}
 }
@@ -581,7 +584,7 @@ int free_swap_and_cache(swp_entry_t entry)
 
 	p = swap_info_get(entry);
 	if (p) {
-		if (swap_entry_free(p, swp_offset(entry)) == 1) {
+		if (swap_entry_free(p, entry) == 1) {
 			page = find_get_page(&swapper_space, entry.val);
 			if (page && !trylock_page(page)) {
 				page_cache_release(page);
@@ -690,17 +693,18 @@ unsigned int count_swap_pages(int type, int free)
 static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, swp_entry_t entry, struct page *page)
 {
+	struct mem_cgroup *ptr = NULL;
 	spinlock_t *ptl;
 	pte_t *pte;
 	int ret = 1;
 
-	if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
+	if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr))
 		ret = -ENOMEM;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
 		if (ret > 0)
-			mem_cgroup_uncharge_page(page);
+			mem_cgroup_cancel_charge_swapin(ptr);
 		ret = 0;
 		goto out;
 	}
@@ -710,6 +714,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	set_pte_at(vma->vm_mm, addr, pte,
 		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	page_add_anon_rmap(page, vma, addr);
+	mem_cgroup_commit_charge_swapin(page, ptr);
 	swap_free(entry);
 	/*
 	 * Move the page to the active list so it is not
@@ -1492,6 +1497,9 @@ asmlinkage long sys_swapoff(const char __user * specialfile)
 	spin_unlock(&swap_lock);
 	mutex_unlock(&swapon_mutex);
 	vfree(swap_map);
+	/* Destroy swap account informatin */
+	swap_cgroup_swapoff(type);
+
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		struct block_device *bdev = I_BDEV(inode);
@@ -1809,6 +1817,11 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 		}
 		swap_map[page_nr] = SWAP_MAP_BAD;
 	}
+
+	error = swap_cgroup_swapon(type, maxpages);
+	if (error)
+		goto bad_swap;
+
 	nr_good_pages = swap_header->info.last_page -
 			swap_header->info.nr_badpages -
 			1 /* header page */;
@@ -1880,6 +1893,7 @@ bad_swap:
 		bd_release(bdev);
 	}
 	destroy_swap_extents(p);
+	swap_cgroup_swapoff(type);
 bad_swap_2:
 	spin_lock(&swap_lock);
 	p->swap_file = NULL;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b07c48b..9a27c44 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -125,11 +125,30 @@ static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
-#define scan_global_lru(sc)	(!(sc)->mem_cgroup)
+#define scanning_global_lru(sc)	(!(sc)->mem_cgroup)
 #else
-#define scan_global_lru(sc)	(1)
+#define scanning_global_lru(sc)	(1)
 #endif
 
+static struct zone_reclaim_stat *get_reclaim_stat(struct zone *zone,
+						  struct scan_control *sc)
+{
+	if (!scanning_global_lru(sc))
+		return mem_cgroup_get_reclaim_stat(sc->mem_cgroup, zone);
+
+	return &zone->reclaim_stat;
+}
+
+static unsigned long zone_nr_pages(struct zone *zone, struct scan_control *sc,
+				   enum lru_list lru)
+{
+	if (!scanning_global_lru(sc))
+		return mem_cgroup_zone_nr_pages(sc->mem_cgroup, zone, lru);
+
+	return zone_page_state(zone, NR_LRU_BASE + lru);
+}
+
+
 /*
  * Add a shrinker callback to be called from the vm
  */
@@ -512,7 +531,6 @@ redo:
 		lru = LRU_UNEVICTABLE;
 		add_page_to_unevictable_list(page);
 	}
-	mem_cgroup_move_lists(page, lru);
 
 	/*
 	 * page's status can change while we move it among lru. If an evictable
@@ -547,7 +565,6 @@ void putback_lru_page(struct page *page)
 
 	lru = !!TestClearPageActive(page) + page_is_file_cache(page);
 	lru_cache_add_lru(page, lru);
-	mem_cgroup_move_lists(page, lru);
 	put_page(page);
 }
 #endif /* CONFIG_UNEVICTABLE_LRU */
@@ -813,6 +830,7 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 		return ret;
 
 	ret = -EBUSY;
+
 	if (likely(get_page_unless_zero(page))) {
 		/*
 		 * Be careful not to clear PageLRU until after we're
@@ -821,6 +839,7 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 		 */
 		ClearPageLRU(page);
 		ret = 0;
+		mem_cgroup_del_lru(page);
 	}
 
 	return ret;
@@ -1029,6 +1048,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 	struct pagevec pvec;
 	unsigned long nr_scanned = 0;
 	unsigned long nr_reclaimed = 0;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	pagevec_init(&pvec, 1);
 
@@ -1070,13 +1090,14 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		__mod_zone_page_state(zone, NR_INACTIVE_ANON,
 						-count[LRU_INACTIVE_ANON]);
 
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc))
 			zone->pages_scanned += nr_scan;
-			zone->recent_scanned[0] += count[LRU_INACTIVE_ANON];
-			zone->recent_scanned[0] += count[LRU_ACTIVE_ANON];
-			zone->recent_scanned[1] += count[LRU_INACTIVE_FILE];
-			zone->recent_scanned[1] += count[LRU_ACTIVE_FILE];
-		}
+
+		reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
+		reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
+		reclaim_stat->recent_scanned[1] += count[LRU_INACTIVE_FILE];
+		reclaim_stat->recent_scanned[1] += count[LRU_ACTIVE_FILE];
+
 		spin_unlock_irq(&zone->lru_lock);
 
 		nr_scanned += nr_scan;
@@ -1108,7 +1129,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		if (current_is_kswapd()) {
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
 			__count_vm_events(KSWAPD_STEAL, nr_freed);
-		} else if (scan_global_lru(sc))
+		} else if (scanning_global_lru(sc))
 			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
 
 		__count_zone_vm_events(PGSTEAL, zone, nr_freed);
@@ -1134,10 +1155,9 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			SetPageLRU(page);
 			lru = page_lru(page);
 			add_page_to_lru_list(zone, page, lru);
-			mem_cgroup_move_lists(page, lru);
-			if (PageActive(page) && scan_global_lru(sc)) {
+			if (PageActive(page)) {
 				int file = !!page_is_file_cache(page);
-				zone->recent_rotated[file]++;
+				reclaim_stat->recent_rotated[file]++;
 			}
 			if (!pagevec_add(&pvec, page)) {
 				spin_unlock_irq(&zone->lru_lock);
@@ -1197,6 +1217,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	struct page *page;
 	struct pagevec pvec;
 	enum lru_list lru;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
@@ -1207,10 +1228,10 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * zone->pages_scanned is used for detect zone's oom
 	 * mem_cgroup remembers nr_scan by itself.
 	 */
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		zone->pages_scanned += pgscanned;
-		zone->recent_scanned[!!file] += pgmoved;
 	}
+	reclaim_stat->recent_scanned[!!file] += pgmoved;
 
 	if (file)
 		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
@@ -1251,8 +1272,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * This helps balance scan pressure between file and anonymous
 	 * pages in get_scan_ratio.
 	 */
-	if (scan_global_lru(sc))
-		zone->recent_rotated[!!file] += pgmoved;
+	reclaim_stat->recent_rotated[!!file] += pgmoved;
 
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
@@ -1263,7 +1283,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		ClearPageActive(page);
 
 		list_move(&page->lru, &zone->lru[lru].list);
-		mem_cgroup_move_lists(page, lru);
+		mem_cgroup_add_lru_list(page, lru);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
 			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
@@ -1292,6 +1312,38 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	pagevec_release(&pvec);
 }
 
+static int inactive_anon_is_low_global(struct zone *zone)
+{
+	unsigned long active, inactive;
+
+	active = zone_page_state(zone, NR_ACTIVE_ANON);
+	inactive = zone_page_state(zone, NR_INACTIVE_ANON);
+
+	if (inactive * zone->inactive_ratio < active)
+		return 1;
+
+	return 0;
+}
+
+/**
+ * inactive_anon_is_low - check if anonymous pages need to be deactivated
+ * @zone: zone to check
+ * @sc:   scan control of this context
+ *
+ * Returns true if the zone does not have enough inactive anon pages,
+ * meaning some active anon pages need to be deactivated.
+ */
+static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
+{
+	int low;
+
+	if (scanning_global_lru(sc))
+		low = inactive_anon_is_low_global(zone);
+	else
+		low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
+	return low;
+}
+
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 	struct zone *zone, struct scan_control *sc, int priority)
 {
@@ -1302,8 +1354,7 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 		return 0;
 	}
 
-	if (lru == LRU_ACTIVE_ANON &&
-	    (!scan_global_lru(sc) || inactive_anon_is_low(zone))) {
+	if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) {
 		shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
@@ -1325,6 +1376,7 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	unsigned long anon, file, free;
 	unsigned long anon_prio, file_prio;
 	unsigned long ap, fp;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (nr_swap_pages <= 0) {
@@ -1333,17 +1385,20 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 		return;
 	}
 
-	anon  = zone_page_state(zone, NR_ACTIVE_ANON) +
-		zone_page_state(zone, NR_INACTIVE_ANON);
-	file  = zone_page_state(zone, NR_ACTIVE_FILE) +
-		zone_page_state(zone, NR_INACTIVE_FILE);
-	free  = zone_page_state(zone, NR_FREE_PAGES);
-
-	/* If we have very few page cache pages, force-scan anon pages. */
-	if (unlikely(file + free <= zone->pages_high)) {
-		percent[0] = 100;
-		percent[1] = 0;
-		return;
+	anon  = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_pages(zone, sc, LRU_INACTIVE_FILE);
+
+	if (scanning_global_lru(sc)) {
+		free  = zone_page_state(zone, NR_FREE_PAGES);
+		/* If we have very few page cache pages,
+		   force-scan anon pages. */
+		if (unlikely(file + free <= zone->pages_high)) {
+			percent[0] = 100;
+			percent[1] = 0;
+			return;
+		}
 	}
 
 	/*
@@ -1357,17 +1412,17 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	 *
 	 * anon in [0], file in [1]
 	 */
-	if (unlikely(zone->recent_scanned[0] > anon / 4)) {
+	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
 		spin_lock_irq(&zone->lru_lock);
-		zone->recent_scanned[0] /= 2;
-		zone->recent_rotated[0] /= 2;
+		reclaim_stat->recent_scanned[0] /= 2;
+		reclaim_stat->recent_rotated[0] /= 2;
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	if (unlikely(zone->recent_scanned[1] > file / 4)) {
+	if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
 		spin_lock_irq(&zone->lru_lock);
-		zone->recent_scanned[1] /= 2;
-		zone->recent_rotated[1] /= 2;
+		reclaim_stat->recent_scanned[1] /= 2;
+		reclaim_stat->recent_rotated[1] /= 2;
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
@@ -1383,11 +1438,11 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	 * proportional to the fraction of recently scanned pages on
 	 * each list that were recently referenced and in active use.
 	 */
-	ap = (anon_prio + 1) * (zone->recent_scanned[0] + 1);
-	ap /= zone->recent_rotated[0] + 1;
+	ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
+	ap /= reclaim_stat->recent_rotated[0] + 1;
 
-	fp = (file_prio + 1) * (zone->recent_scanned[1] + 1);
-	fp /= zone->recent_rotated[1] + 1;
+	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
+	fp /= reclaim_stat->recent_rotated[1] + 1;
 
 	/* Normalize to percentages */
 	percent[0] = 100 * ap / (ap + fp + 1);
@@ -1411,30 +1466,23 @@ static void shrink_zone(int priority, struct zone *zone,
 	get_scan_ratio(zone, sc, percent);
 
 	for_each_evictable_lru(l) {
-		if (scan_global_lru(sc)) {
-			int file = is_file_lru(l);
-			int scan;
-
-			scan = zone_page_state(zone, NR_LRU_BASE + l);
-			if (priority) {
-				scan >>= priority;
-				scan = (scan * percent[file]) / 100;
-			}
+		int file = is_file_lru(l);
+		int scan;
+
+		scan = zone_page_state(zone, NR_LRU_BASE + l);
+		if (priority) {
+			scan >>= priority;
+			scan = (scan * percent[file]) / 100;
+		}
+		if (scanning_global_lru(sc)) {
 			zone->lru[l].nr_scan += scan;
 			nr[l] = zone->lru[l].nr_scan;
 			if (nr[l] >= swap_cluster_max)
 				zone->lru[l].nr_scan = 0;
 			else
 				nr[l] = 0;
-		} else {
-			/*
-			 * This reclaim occurs not because zone memory shortage
-			 * but because memory controller hits its limit.
-			 * Don't modify zone reclaim related data.
-			 */
-			nr[l] = mem_cgroup_calc_reclaim(sc->mem_cgroup, zone,
-								priority, l);
-		}
+		} else
+			nr[l] = scan;
 	}
 
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
@@ -1467,9 +1515,7 @@ static void shrink_zone(int priority, struct zone *zone,
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (!scan_global_lru(sc) || inactive_anon_is_low(zone))
-		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
-	else if (!scan_global_lru(sc))
+	if (inactive_anon_is_low(zone, sc))
 		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
 
 	throttle_vm_writeout(sc->gfp_mask);
@@ -1504,7 +1550,7 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 		 * Take care memory controller reclaiming has small influence
 		 * to global LRU.
 		 */
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc)) {
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
 			note_zone_scanning_priority(zone, priority);
@@ -1557,12 +1603,12 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 	delayacct_freepages_start();
 
-	if (scan_global_lru(sc))
+	if (scanning_global_lru(sc))
 		count_vm_event(ALLOCSTALL);
 	/*
 	 * mem_cgroup will not do shrink_slab.
 	 */
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
@@ -1581,7 +1627,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
 		 */
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc)) {
 			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
 			if (reclaim_state) {
 				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
@@ -1612,7 +1658,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			congestion_wait(WRITE, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (!sc->all_unreclaimable && scan_global_lru(sc))
+	if (!sc->all_unreclaimable && scanning_global_lru(sc))
 		ret = sc->nr_reclaimed;
 out:
 	/*
@@ -1625,7 +1671,7 @@ out:
 	if (priority < 0)
 		priority = 0;
 
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
@@ -1661,19 +1707,24 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
-						gfp_t gfp_mask)
+					   gfp_t gfp_mask,
+					   bool noswap,
+					   unsigned int swappiness)
 {
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
-		.swappiness = vm_swappiness,
+		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
 		.isolate_pages = mem_cgroup_isolate_pages,
 	};
 	struct zonelist *zonelist;
 
+	if (noswap)
+		sc.may_swap = 0;
+
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
@@ -1761,7 +1812,7 @@ loop_again:
 			 * Do some background aging of the anon list, to give
 			 * pages a chance to be referenced before reclaiming.
 			 */
-			if (inactive_anon_is_low(zone))
+			if (inactive_anon_is_low(zone, &sc))
 				shrink_active_list(SWAP_CLUSTER_MAX, zone,
 							&sc, priority, 0);
 
@@ -2404,6 +2455,7 @@ retry:
 
 		__dec_zone_state(zone, NR_UNEVICTABLE);
 		list_move(&page->lru, &zone->lru[l].list);
+		mem_cgroup_move_lists(page, LRU_UNEVICTABLE, l);
 		__inc_zone_state(zone, NR_INACTIVE_ANON + l);
 		__count_vm_event(UNEVICTABLE_PGRESCUED);
 	} else {
@@ -2412,6 +2464,7 @@ retry:
 		 */
 		SetPageUnevictable(page);
 		list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
+		mem_cgroup_rotate_lru_list(page, LRU_UNEVICTABLE);
 		if (page_evictable(page, NULL))
 			goto retry;
 	}