Merge commit 'v2.6.28-rc2' into x86/pci-ioapic-boot-irq-quirks

1 files changed, 413 insertions, 359 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e46451e1d9b..866dcc7eeb0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -32,12 +32,13 @@
 #include <linux/fs.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
+#include <linux/page_cgroup.h>
 
 #include <asm/uaccess.h>
 
-struct cgroup_subsys mem_cgroup_subsys;
-static const int MEM_CGROUP_RECLAIM_RETRIES = 5;
-static struct kmem_cache *page_cgroup_cache;
+struct cgroup_subsys mem_cgroup_subsys __read_mostly;
+#define MEM_CGROUP_RECLAIM_RETRIES	5
 
 /*
  * Statistics for memory cgroup.
@@ -65,11 +66,10 @@ struct mem_cgroup_stat {
 /*
  * For accounting under irq disable, no need for increment preempt count.
  */
-static void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat *stat,
+static inline void __mem_cgroup_stat_add_safe(struct mem_cgroup_stat_cpu *stat,
 		enum mem_cgroup_stat_index idx, int val)
 {
-	int cpu = smp_processor_id();
-	stat->cpustat[cpu].count[idx] += val;
+	stat->count[idx] += val;
 }
 
 static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
@@ -85,22 +85,13 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
 /*
  * per-zone information in memory controller.
  */
-
-enum mem_cgroup_zstat_index {
-	MEM_CGROUP_ZSTAT_ACTIVE,
-	MEM_CGROUP_ZSTAT_INACTIVE,
-
-	NR_MEM_CGROUP_ZSTAT,
-};
-
 struct mem_cgroup_per_zone {
 	/*
 	 * spin_lock to protect the per cgroup LRU
 	 */
 	spinlock_t		lru_lock;
-	struct list_head	active_list;
-	struct list_head	inactive_list;
-	unsigned long count[NR_MEM_CGROUP_ZSTAT];
+	struct list_head	lists[NR_LRU_LISTS];
+	unsigned long		count[NR_LRU_LISTS];
 };
 /* Macro for accessing counter */
 #define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
@@ -144,69 +135,52 @@ struct mem_cgroup {
 };
 static struct mem_cgroup init_mem_cgroup;
 
-/*
- * We use the lower bit of the page->page_cgroup pointer as a bit spin
- * lock.  We need to ensure that page->page_cgroup is at least two
- * byte aligned (based on comments from Nick Piggin).  But since
- * bit_spin_lock doesn't actually set that lock bit in a non-debug
- * uniprocessor kernel, we should avoid setting it here too.
- */
-#define PAGE_CGROUP_LOCK_BIT 	0x0
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-#define PAGE_CGROUP_LOCK 	(1 << PAGE_CGROUP_LOCK_BIT)
-#else
-#define PAGE_CGROUP_LOCK	0x0
-#endif
-
-/*
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- */
-struct page_cgroup {
-	struct list_head lru;		/* per cgroup LRU list */
-	struct page *page;
-	struct mem_cgroup *mem_cgroup;
-	int ref_cnt;			/* cached, mapped, migrating */
-	int flags;
-};
-#define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */
-#define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */
-
-static int page_cgroup_nid(struct page_cgroup *pc)
-{
-	return page_to_nid(pc->page);
-}
-
-static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
-{
-	return page_zonenum(pc->page);
-}
-
 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 */
+	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 */
+	0, /* FORCE */
 };
 
 /*
  * Always modified under lru lock. Then, not necessary to preempt_disable()
  */
-static void mem_cgroup_charge_statistics(struct mem_cgroup *mem, int flags,
-					bool charge)
+static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
+					 struct page_cgroup *pc,
+					 bool charge)
 {
 	int val = (charge)? 1 : -1;
 	struct mem_cgroup_stat *stat = &mem->stat;
+	struct mem_cgroup_stat_cpu *cpustat;
 
 	VM_BUG_ON(!irqs_disabled());
-	if (flags & PAGE_CGROUP_FLAG_CACHE)
-		__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_CACHE, val);
+
+	cpustat = &stat->cpustat[smp_processor_id()];
+	if (PageCgroupCache(pc))
+		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val);
 	else
-		__mem_cgroup_stat_add_safe(stat, MEM_CGROUP_STAT_RSS, val);
+		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_RSS, val);
 
 	if (charge)
-		__mem_cgroup_stat_add_safe(stat,
+		__mem_cgroup_stat_add_safe(cpustat,
 				MEM_CGROUP_STAT_PGPGIN_COUNT, 1);
 	else
-		__mem_cgroup_stat_add_safe(stat,
+		__mem_cgroup_stat_add_safe(cpustat,
 				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
 }
 
@@ -227,7 +201,7 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
 }
 
 static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
-					enum mem_cgroup_zstat_index idx)
+					enum lru_list idx)
 {
 	int nid, zid;
 	struct mem_cgroup_per_zone *mz;
@@ -250,89 +224,89 @@ static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 {
+	/*
+	 * mm_update_next_owner() may clear mm->owner to NULL
+	 * if it races with swapoff, page migration, etc.
+	 * So this can be called with p == NULL.
+	 */
+	if (unlikely(!p))
+		return NULL;
+
 	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
 				struct mem_cgroup, css);
 }
 
-static inline int page_cgroup_locked(struct page *page)
-{
-	return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
-{
-	VM_BUG_ON(!page_cgroup_locked(page));
-	page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
-}
-
-struct page_cgroup *page_get_page_cgroup(struct page *page)
-{
-	return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
-}
-
-static void lock_page_cgroup(struct page *page)
-{
-	bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static int try_lock_page_cgroup(struct page *page)
-{
-	return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void unlock_page_cgroup(struct page *page)
-{
-	bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
 static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 			struct page_cgroup *pc)
 {
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int lru = LRU_BASE;
+
+	if (PageCgroupUnevictable(pc))
+		lru = LRU_UNEVICTABLE;
+	else {
+		if (PageCgroupActive(pc))
+			lru += LRU_ACTIVE;
+		if (PageCgroupFile(pc))
+			lru += LRU_FILE;
+	}
 
-	if (from)
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
-	else
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
-	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false);
-	list_del_init(&pc->lru);
+	mem_cgroup_charge_statistics(pc->mem_cgroup, pc, false);
+	list_del(&pc->lru);
 }
 
 static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 				struct page_cgroup *pc)
 {
-	int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-
-	if (!to) {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
-		list_add(&pc->lru, &mz->inactive_list);
-	} else {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
-		list_add(&pc->lru, &mz->active_list);
+	int lru = LRU_BASE;
+
+	if (PageCgroupUnevictable(pc))
+		lru = LRU_UNEVICTABLE;
+	else {
+		if (PageCgroupActive(pc))
+			lru += LRU_ACTIVE;
+		if (PageCgroupFile(pc))
+			lru += LRU_FILE;
 	}
-	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
+
+	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	list_add(&pc->lru, &mz->lists[lru]);
+
+	mem_cgroup_charge_statistics(pc->mem_cgroup, pc, true);
 }
 
-static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
+static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
 {
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
 	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);
 
-	if (from)
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
-	else
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+	if (lru == from)
+		return;
 
-	if (active) {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
-		pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
-		list_move(&pc->lru, &mz->active_list);
+	MEM_CGROUP_ZSTAT(mz, from) -= 1;
+	/*
+	 * 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.
+	 */
+	if (is_unevictable_lru(lru)) {
+		ClearPageCgroupActive(pc);
+		SetPageCgroupUnevictable(pc);
 	} else {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
-		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
-		list_move(&pc->lru, &mz->inactive_list);
+		if (is_active_lru(lru))
+			SetPageCgroupActive(pc);
+		else
+			ClearPageCgroupActive(pc);
+		ClearPageCgroupUnevictable(pc);
 	}
+
+	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	list_move(&pc->lru, &mz->lists[lru]);
 }
 
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
@@ -348,12 +322,15 @@ 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, bool active)
+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
@@ -361,17 +338,16 @@ void mem_cgroup_move_lists(struct page *page, bool active)
 	 * safely get to page_cgroup without it, so just try_lock it:
 	 * mem_cgroup_isolate_pages allows for page left on wrong list.
 	 */
-	if (!try_lock_page_cgroup(page))
+	pc = lookup_page_cgroup(page);
+	if (!trylock_page_cgroup(pc))
 		return;
-
-	pc = page_get_page_cgroup(page);
-	if (pc) {
+	if (pc && PageCgroupUsed(pc)) {
 		mz = page_cgroup_zoneinfo(pc);
 		spin_lock_irqsave(&mz->lru_lock, flags);
-		__mem_cgroup_move_lists(pc, active);
+		__mem_cgroup_move_lists(pc, lru);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 	}
-	unlock_page_cgroup(page);
+	unlock_page_cgroup(pc);
 }
 
 /*
@@ -392,21 +368,6 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
 }
 
 /*
- * This function is called from vmscan.c. In page reclaiming loop. balance
- * between active and inactive list is calculated. For memory controller
- * page reclaiming, we should use using mem_cgroup's imbalance rather than
- * zone's global lru imbalance.
- */
-long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
-{
-	unsigned long active, inactive;
-	/* active and inactive are the number of pages. 'long' is ok.*/
-	active = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_ACTIVE);
-	inactive = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_INACTIVE);
-	return (long) (active / (inactive + 1));
-}
-
-/*
  * prev_priority control...this will be used in memory reclaim path.
  */
 int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
@@ -433,28 +394,17 @@ void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
  * (see include/linux/mmzone.h)
  */
 
-long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
-				   struct zone *zone, int priority)
+long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
+					int priority, enum lru_list lru)
 {
-	long nr_active;
+	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);
 
-	nr_active = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE);
-	return (nr_active >> priority);
-}
+	nr_pages = MEM_CGROUP_ZSTAT(mz, lru);
 
-long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
-					struct zone *zone, int priority)
-{
-	long nr_inactive;
-	int nid = zone->zone_pgdat->node_id;
-	int zid = zone_idx(zone);
-	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
-
-	nr_inactive = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE);
-	return (nr_inactive >> priority);
+	return (nr_pages >> priority);
 }
 
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
@@ -462,7 +412,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					unsigned long *scanned, int order,
 					int mode, struct zone *z,
 					struct mem_cgroup *mem_cont,
-					int active)
+					int active, int file)
 {
 	unsigned long nr_taken = 0;
 	struct page *page;
@@ -473,38 +423,38 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	int nid = z->zone_pgdat->node_id;
 	int zid = zone_idx(z);
 	struct mem_cgroup_per_zone *mz;
+	int lru = LRU_FILE * !!file + !!active;
 
 	BUG_ON(!mem_cont);
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
-	if (active)
-		src = &mz->active_list;
-	else
-		src = &mz->inactive_list;
-
+	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;
+		if (unlikely(!PageCgroupUsed(pc)))
+			continue;
 		page = pc->page;
 
 		if (unlikely(!PageLRU(page)))
 			continue;
 
-		if (PageActive(page) && !active) {
-			__mem_cgroup_move_lists(pc, true);
-			continue;
-		}
-		if (!PageActive(page) && active) {
-			__mem_cgroup_move_lists(pc, false);
+		/*
+		 * 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) == 0) {
+		if (__isolate_lru_page(page, mode, file) == 0) {
 			list_move(&page->lru, dst);
 			nr_taken++;
 		}
@@ -524,63 +474,45 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
  * < 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)
+				gfp_t gfp_mask, enum charge_type ctype,
+				struct mem_cgroup *memcg)
 {
 	struct mem_cgroup *mem;
 	struct page_cgroup *pc;
-	unsigned long flags;
 	unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup_per_zone *mz;
+	unsigned long flags;
 
-	if (mem_cgroup_subsys.disabled)
+	pc = lookup_page_cgroup(page);
+	/* can happen at boot */
+	if (unlikely(!pc))
 		return 0;
-
-	/*
-	 * Should page_cgroup's go to their own slab?
-	 * One could optimize the performance of the charging routine
-	 * by saving a bit in the page_flags and using it as a lock
-	 * to see if the cgroup page already has a page_cgroup associated
-	 * with it
-	 */
-retry:
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	/*
-	 * The page_cgroup exists and
-	 * the page has already been accounted.
-	 */
-	if (pc) {
-		VM_BUG_ON(pc->page != page);
-		VM_BUG_ON(pc->ref_cnt <= 0);
-
-		pc->ref_cnt++;
-		unlock_page_cgroup(page);
-		goto done;
-	}
-	unlock_page_cgroup(page);
-
-	pc = kmem_cache_zalloc(page_cgroup_cache, gfp_mask);
-	if (pc == NULL)
-		goto err;
-
+	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 (!mm)
-		mm = &init_mm;
 
-	rcu_read_lock();
-	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	/*
-	 * For every charge from the cgroup, increment reference count
-	 */
-	css_get(&mem->css);
-	rcu_read_unlock();
+	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();
+	} else {
+		mem = memcg;
+		css_get(&memcg->css);
+	}
 
-	while (res_counter_charge(&mem->res, PAGE_SIZE)) {
+	while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE))) {
 		if (!(gfp_mask & __GFP_WAIT))
 			goto out;
 
@@ -603,63 +535,104 @@ retry:
 		}
 	}
 
-	pc->ref_cnt = 1;
-	pc->mem_cgroup = mem;
-	pc->page = page;
-	pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
-	if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
-		pc->flags = PAGE_CGROUP_FLAG_CACHE;
-
-	lock_page_cgroup(page);
-	if (page_get_page_cgroup(page)) {
-		unlock_page_cgroup(page);
-		/*
-		 * Another charge has been added to this page already.
-		 * We take lock_page_cgroup(page) again and read
-		 * page->cgroup, increment refcnt.... just retry is OK.
-		 */
+
+	lock_page_cgroup(pc);
+	if (unlikely(PageCgroupUsed(pc))) {
+		unlock_page_cgroup(pc);
 		res_counter_uncharge(&mem->res, PAGE_SIZE);
 		css_put(&mem->css);
-		kmem_cache_free(page_cgroup_cache, pc);
-		goto retry;
+
+		goto done;
 	}
-	page_assign_page_cgroup(page, pc);
+	pc->mem_cgroup = mem;
+	/*
+	 * If a page is accounted as a page cache, insert to inactive list.
+	 * If anon, insert to active list.
+	 */
+	pc->flags = pcg_default_flags[ctype];
 
 	mz = page_cgroup_zoneinfo(pc);
+
 	spin_lock_irqsave(&mz->lru_lock, flags);
 	__mem_cgroup_add_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
+	unlock_page_cgroup(pc);
 
-	unlock_page_cgroup(page);
 done:
 	return 0;
 out:
 	css_put(&mem->css);
-	kmem_cache_free(page_cgroup_cache, pc);
-err:
 	return -ENOMEM;
 }
 
 int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 {
+	if (mem_cgroup_subsys.disabled)
+		return 0;
+	if (PageCompound(page))
+		return 0;
+	/*
+	 * If already mapped, we don't have to account.
+	 * If page cache, page->mapping has address_space.
+	 * But page->mapping may have out-of-use anon_vma pointer,
+	 * detecit it by PageAnon() check. newly-mapped-anon's page->mapping
+	 * is NULL.
+  	 */
+	if (page_mapped(page) || (page->mapping && !PageAnon(page)))
+		return 0;
+	if (unlikely(!mm))
+		mm = &init_mm;
 	return mem_cgroup_charge_common(page, mm, gfp_mask,
-				MEM_CGROUP_CHARGE_TYPE_MAPPED);
+				MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
 }
 
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
-	if (!mm)
+	if (mem_cgroup_subsys.disabled)
+		return 0;
+	if (PageCompound(page))
+		return 0;
+	/*
+	 * Corner case handling. This is called from add_to_page_cache()
+	 * in usual. But some FS (shmem) precharges this page before calling it
+	 * and call add_to_page_cache() with GFP_NOWAIT.
+	 *
+	 * 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.)
+	 */
+	if (!(gfp_mask & __GFP_WAIT)) {
+		struct page_cgroup *pc;
+
+
+		pc = lookup_page_cgroup(page);
+		if (!pc)
+			return 0;
+		lock_page_cgroup(pc);
+		if (PageCgroupUsed(pc)) {
+			unlock_page_cgroup(pc);
+			return 0;
+		}
+		unlock_page_cgroup(pc);
+	}
+
+	if (unlikely(!mm))
 		mm = &init_mm;
-	return mem_cgroup_charge_common(page, mm, gfp_mask,
-				MEM_CGROUP_CHARGE_TYPE_CACHE);
+
+	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);
 }
 
 /*
- * Uncharging is always a welcome operation, we never complain, simply
- * uncharge.
+ * uncharge if !page_mapped(page)
  */
-void mem_cgroup_uncharge_page(struct page *page)
+static void
+__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 {
 	struct page_cgroup *pc;
 	struct mem_cgroup *mem;
@@ -672,106 +645,172 @@ void mem_cgroup_uncharge_page(struct page *page)
 	/*
 	 * Check if our page_cgroup is valid
 	 */
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	if (!pc)
-		goto unlock;
+	pc = lookup_page_cgroup(page);
+	if (unlikely(!pc || !PageCgroupUsed(pc)))
+		return;
 
-	VM_BUG_ON(pc->page != page);
-	VM_BUG_ON(pc->ref_cnt <= 0);
+	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;
+	}
+	ClearPageCgroupUsed(pc);
+	mem = pc->mem_cgroup;
 
-	if (--(pc->ref_cnt) == 0) {
-		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);
+	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);
 
-		page_assign_page_cgroup(page, NULL);
-		unlock_page_cgroup(page);
+	res_counter_uncharge(&mem->res, PAGE_SIZE);
+	css_put(&mem->css);
 
-		mem = pc->mem_cgroup;
-		res_counter_uncharge(&mem->res, PAGE_SIZE);
-		css_put(&mem->css);
+	return;
+}
 
-		kmem_cache_free(page_cgroup_cache, pc);
+void mem_cgroup_uncharge_page(struct page *page)
+{
+	/* early check. */
+	if (page_mapped(page))
 		return;
-	}
+	if (page->mapping && !PageAnon(page))
+		return;
+	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
 
-unlock:
-	unlock_page_cgroup(page);
+void mem_cgroup_uncharge_cache_page(struct page *page)
+{
+	VM_BUG_ON(page_mapped(page));
+	VM_BUG_ON(page->mapping);
+	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE);
 }
 
 /*
- * Returns non-zero if a page (under migration) has valid page_cgroup member.
- * Refcnt of page_cgroup is incremented.
+ * Before starting migration, account against new page.
  */
-int mem_cgroup_prepare_migration(struct page *page)
+int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 {
 	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)
 		return 0;
 
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	if (pc)
-		pc->ref_cnt++;
-	unlock_page_cgroup(page);
-	return pc != NULL;
+	pc = lookup_page_cgroup(page);
+	lock_page_cgroup(pc);
+	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);
+		css_put(&mem->css);
+	}
+	return ret;
 }
 
-void mem_cgroup_end_migration(struct page *page)
+/* remove redundant charge if migration failed*/
+void mem_cgroup_end_migration(struct page *newpage)
 {
-	mem_cgroup_uncharge_page(page);
+	/*
+	 * 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.
+	 */
+	if (!newpage->mapping)
+		__mem_cgroup_uncharge_common(newpage,
+				MEM_CGROUP_CHARGE_TYPE_FORCE);
+	else if (PageAnon(newpage))
+		mem_cgroup_uncharge_page(newpage);
 }
 
 /*
- * We know both *page* and *newpage* are now not-on-LRU and PG_locked.
- * And no race with uncharge() routines because page_cgroup for *page*
- * has extra one reference by mem_cgroup_prepare_migration.
+ * A call to try to shrink memory usage under specified resource controller.
+ * 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.
  */
-void mem_cgroup_page_migration(struct page *page, struct page *newpage)
+int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 {
-	struct page_cgroup *pc;
-	struct mem_cgroup_per_zone *mz;
-	unsigned long flags;
+	struct mem_cgroup *mem;
+	int progress = 0;
+	int retry = MEM_CGROUP_RECLAIM_RETRIES;
 
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	if (!pc) {
-		unlock_page_cgroup(page);
-		return;
+	if (mem_cgroup_subsys.disabled)
+		return 0;
+	if (!mm)
+		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();
 
-	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);
+	do {
+		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
+		progress += res_counter_check_under_limit(&mem->res);
+	} while (!progress && --retry);
 
-	page_assign_page_cgroup(page, NULL);
-	unlock_page_cgroup(page);
+	css_put(&mem->css);
+	if (!retry)
+		return -ENOMEM;
+	return 0;
+}
 
-	pc->page = newpage;
-	lock_page_cgroup(newpage);
-	page_assign_page_cgroup(newpage, pc);
+int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
+{
 
-	mz = page_cgroup_zoneinfo(pc);
-	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_add_list(mz, pc);
-	spin_unlock_irqrestore(&mz->lru_lock, flags);
+	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	int progress;
+	int ret = 0;
 
-	unlock_page_cgroup(newpage);
+	while (res_counter_set_limit(&memcg->res, val)) {
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+		if (!retry_count) {
+			ret = -EBUSY;
+			break;
+		}
+		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
+		if (!progress)
+			retry_count--;
+	}
+	return ret;
 }
 
+
 /*
  * This routine traverse page_cgroup in given list and drop them all.
- * This routine ignores page_cgroup->ref_cnt.
  * *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,
-			    int active)
+			    enum lru_list lru)
 {
 	struct page_cgroup *pc;
 	struct page *page;
@@ -779,22 +818,31 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
 	unsigned long flags;
 	struct list_head *list;
 
-	if (active)
-		list = &mz->active_list;
-	else
-		list = &mz->inactive_list;
+	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);
-		mem_cgroup_uncharge_page(page);
-		put_page(page);
-		if (--count <= 0) {
-			count = FORCE_UNCHARGE_BATCH;
-			cond_resched();
+		/*
+		 * 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);
+			break;
 		}
 		spin_lock_irqsave(&mz->lru_lock, flags);
 	}
@@ -810,9 +858,6 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem)
 	int ret = -EBUSY;
 	int node, zid;
 
-	if (mem_cgroup_subsys.disabled)
-		return 0;
-
 	css_get(&mem->css);
 	/*
 	 * page reclaim code (kswapd etc..) will move pages between
@@ -822,15 +867,17 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem)
 	while (mem->res.usage > 0) {
 		if (atomic_read(&mem->css.cgroup->count) > 0)
 			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;
+				enum lru_list l;
 				mz = mem_cgroup_zoneinfo(mem, node, zid);
-				/* drop all page_cgroup in active_list */
-				mem_cgroup_force_empty_list(mem, mz, 1);
-				/* drop all page_cgroup in inactive_list */
-				mem_cgroup_force_empty_list(mem, mz, 0);
+				for_each_lru(l)
+					mem_cgroup_force_empty_list(mem, mz, l);
 			}
+		cond_resched();
 	}
 	ret = 0;
 out:
@@ -838,32 +885,34 @@ out:
 	return ret;
 }
 
-static int mem_cgroup_write_strategy(char *buf, unsigned long long *tmp)
-{
-	*tmp = memparse(buf, &buf);
-	if (*buf != '\0')
-		return -EINVAL;
-
-	/*
-	 * Round up the value to the closest page size
-	 */
-	*tmp = ((*tmp + PAGE_SIZE - 1) >> PAGE_SHIFT) << PAGE_SHIFT;
-	return 0;
-}
-
 static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 {
 	return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
 				    cft->private);
 }
-
-static ssize_t mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
-				struct file *file, const char __user *userbuf,
-				size_t nbytes, loff_t *ppos)
+/*
+ * The user of this function is...
+ * RES_LIMIT.
+ */
+static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
+			    const char *buffer)
 {
-	return res_counter_write(&mem_cgroup_from_cont(cont)->res,
-				cft->private, userbuf, nbytes, ppos,
-				mem_cgroup_write_strategy);
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	unsigned long long val;
+	int ret;
+
+	switch (cft->private) {
+	case RES_LIMIT:
+		/* This function does all necessary parse...reuse it */
+		ret = res_counter_memparse_write_strategy(buffer, &val);
+		if (!ret)
+			ret = mem_cgroup_resize_limit(memcg, val);
+		break;
+	default:
+		ret = -EINVAL; /* should be BUG() ? */
+		break;
+	}
+	return ret;
 }
 
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
@@ -913,14 +962,27 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	}
 	/* showing # of active pages */
 	{
-		unsigned long active, inactive;
-
-		inactive = mem_cgroup_get_all_zonestat(mem_cont,
-						MEM_CGROUP_ZSTAT_INACTIVE);
-		active = mem_cgroup_get_all_zonestat(mem_cont,
-						MEM_CGROUP_ZSTAT_ACTIVE);
-		cb->fill(cb, "active", (active) * PAGE_SIZE);
-		cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
+		unsigned long active_anon, inactive_anon;
+		unsigned long active_file, inactive_file;
+		unsigned long unevictable;
+
+		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_INACTIVE_ANON);
+		active_anon = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_ACTIVE_ANON);
+		inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_INACTIVE_FILE);
+		active_file = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_ACTIVE_FILE);
+		unevictable = mem_cgroup_get_all_zonestat(mem_cont,
+							LRU_UNEVICTABLE);
+
+		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
+		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
+		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
+		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
+		cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);
+
 	}
 	return 0;
 }
@@ -940,7 +1002,7 @@ static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "limit_in_bytes",
 		.private = RES_LIMIT,
-		.write = mem_cgroup_write,
+		.write_string = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read,
 	},
 	{
@@ -963,6 +1025,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup_per_zone *mz;
+	enum lru_list l;
 	int zone, tmp = node;
 	/*
 	 * This routine is called against possible nodes.
@@ -983,9 +1046,9 @@ 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];
-		INIT_LIST_HEAD(&mz->active_list);
-		INIT_LIST_HEAD(&mz->inactive_list);
 		spin_lock_init(&mz->lru_lock);
+		for_each_lru(l)
+			INIT_LIST_HEAD(&mz->lists[l]);
 	}
 	return 0;
 }
@@ -1026,7 +1089,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 
 	if (unlikely((cont->parent) == NULL)) {
 		mem = &init_mem_cgroup;
-		page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
 	} else {
 		mem = mem_cgroup_alloc();
 		if (!mem)
@@ -1070,8 +1132,6 @@ static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 static int mem_cgroup_populate(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
-	if (mem_cgroup_subsys.disabled)
-		return 0;
 	return cgroup_add_files(cont, ss, mem_cgroup_files,
 					ARRAY_SIZE(mem_cgroup_files));
 }
@@ -1084,9 +1144,6 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 	struct mm_struct *mm;
 	struct mem_cgroup *mem, *old_mem;
 
-	if (mem_cgroup_subsys.disabled)
-		return;
-
 	mm = get_task_mm(p);
 	if (mm == NULL)
 		return;
@@ -1094,9 +1151,6 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 	mem = mem_cgroup_from_cont(cont);
 	old_mem = mem_cgroup_from_cont(old_cont);
 
-	if (mem == old_mem)
-		goto out;
-
 	/*
 	 * Only thread group leaders are allowed to migrate, the mm_struct is
 	 * in effect owned by the leader