X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fmemcontrol.c;h=8e4be9cb2a6a7642601516e3587d151dcea586f4;hb=0a0dd05dd7e1a800241888cbf515bf8d3dc2e59c;hp=b8c1e5acc25a18ecec7f2676d85c383c370a0cc2;hpb=9439c1c95b5c25b8031b2a7eb7e1590eb84be7f5;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b8c1e5a..8e4be9c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -51,6 +51,7 @@ static int really_do_swap_account __initdata = 1; /* for remember boot option*/
 #define do_swap_account		(0)
 #endif
 
+static DEFINE_MUTEX(memcg_tasklist);	/* can be hold under cgroup_mutex */
 
 /*
  * Statistics for memory cgroup.
@@ -144,11 +145,16 @@ struct mem_cgroup {
 	 */
 	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 cgroup_lock()
+	 * reclaimed from. Protected by hierarchy_mutex
 	 */
 	struct mem_cgroup *last_scanned_child;
 	/*
@@ -156,10 +162,9 @@ struct mem_cgroup {
 	 */
 	bool use_hierarchy;
 	unsigned long	last_oom_jiffies;
-	int		obsolete;
 	atomic_t	refcnt;
 
-	unsigned int inactive_ratio;
+	unsigned int	swappiness;
 
 	/*
 	 * statistics. This must be placed at the end of memcg.
@@ -197,6 +202,7 @@ pcg_default_flags[NR_CHARGE_TYPE] = {
 
 static void mem_cgroup_get(struct mem_cgroup *mem);
 static void mem_cgroup_put(struct mem_cgroup *mem);
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 					 struct page_cgroup *pc,
@@ -277,6 +283,31 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 				struct mem_cgroup, css);
 }
 
+static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
+{
+	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;
+}
+
+static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
+{
+	if (!mem)
+		return true;
+	return css_is_removed(&mem->css);
+}
+
 /*
  * Following LRU functions are allowed to be used without PCG_LOCK.
  * Operations are called by routine of global LRU independently from memcg.
@@ -301,8 +332,12 @@ void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
 		return;
 	pc = lookup_page_cgroup(page);
 	/* can happen while we handle swapcache. */
-	if (list_empty(&pc->lru))
+	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;
@@ -324,6 +359,10 @@ void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
 		return;
 
 	pc = lookup_page_cgroup(page);
+	/*
+	 * Used bit is set without atomic ops but after smp_wmb().
+	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
+	 */
 	smp_rmb();
 	/* unused page is not rotated. */
 	if (!PageCgroupUsed(pc))
@@ -340,7 +379,10 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
 	if (mem_cgroup_disabled())
 		return;
 	pc = lookup_page_cgroup(page);
-	/* barrier to sync with "charge" */
+	/*
+	 * Used bit is set without atomic ops but after smp_wmb().
+	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
+	 */
 	smp_rmb();
 	if (!PageCgroupUsed(pc))
 		return;
@@ -349,16 +391,44 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_add(&pc->lru, &mz->lists[lru]);
 }
+
 /*
- * To add swapcache into LRU. Be careful to all this function.
- * zone->lru_lock shouldn't be held and irq must not be disabled.
+ * 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_fixup(struct page *page)
+static void mem_cgroup_lru_del_before_commit_swapcache(struct page *page)
 {
-	if (!isolate_lru_page(page))
-		putback_lru_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);
+	/*
+	 * Forget old LRU when this page_cgroup is *not* used. This Used bit
+	 * is guarded by lock_page() because the page is SwapCache.
+	 */
+	if (!PageCgroupUsed(pc))
+		mem_cgroup_del_lru_list(page, page_lru(page));
+	spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
+
+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)
 {
@@ -400,29 +470,67 @@ 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);
 }
 
-int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg, struct zone *zone)
+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);
 
-	if (inactive * memcg->inactive_ratio < active)
+	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;
+
+	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;
@@ -459,6 +567,14 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 		return NULL;
 
 	pc = lookup_page_cgroup(page);
+	/*
+	 * Used bit is set without atomic ops but after smp_wmb().
+	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
+	 */
+	smp_rmb();
+	if (!PageCgroupUsed(pc))
+		return NULL;
+
 	mz = page_cgroup_zoneinfo(pc);
 	if (!mz)
 		return NULL;
@@ -515,10 +631,10 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 
 /*
  * This routine finds the DFS walk successor. This routine should be
- * called with cgroup_mutex held
+ * called with hierarchy_mutex held
  */
 static struct mem_cgroup *
-mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
+__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
 {
 	struct cgroup *cgroup, *curr_cgroup, *root_cgroup;
 
@@ -529,19 +645,16 @@ mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
 		/*
 		 * 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);
+		/* caller handles NULL case */
+		curr = NULL;
 		goto done;
 	}
 
@@ -549,11 +662,9 @@ visit_parent:
 	 * 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;
 	}
 
@@ -564,7 +675,6 @@ visit_parent:
 	goto visit_parent;
 
 done:
-	root_mem->last_scanned_child = curr;
 	return curr;
 }
 
@@ -574,39 +684,46 @@ done:
  * that to reclaim free pages from.
  */
 static struct mem_cgroup *
-mem_cgroup_get_first_node(struct mem_cgroup *root_mem)
+mem_cgroup_get_next_node(struct mem_cgroup *root_mem)
 {
 	struct cgroup *cgroup;
-	struct mem_cgroup *ret;
-	bool obsolete = (root_mem->last_scanned_child &&
-				root_mem->last_scanned_child->obsolete);
+	struct mem_cgroup *orig, *next;
+	bool obsolete;
 
 	/*
 	 * Scan all children under the mem_cgroup mem
 	 */
-	cgroup_lock();
+	mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);
+
+	orig = root_mem->last_scanned_child;
+	obsolete = mem_cgroup_is_obsolete(orig);
+
 	if (list_empty(&root_mem->css.cgroup->children)) {
-		ret = root_mem;
+		/*
+		 * root_mem might have children before and last_scanned_child
+		 * may point to one of them. We put it later.
+		 */
+		if (orig)
+			VM_BUG_ON(!obsolete);
+		next = NULL;
 		goto done;
 	}
 
-	if (!root_mem->last_scanned_child || obsolete) {
-
-		if (obsolete)
-			mem_cgroup_put(root_mem->last_scanned_child);
-
+	if (!orig || obsolete) {
 		cgroup = list_first_entry(&root_mem->css.cgroup->children,
 				struct cgroup, sibling);
-		ret = mem_cgroup_from_cont(cgroup);
-		mem_cgroup_get(ret);
+		next = mem_cgroup_from_cont(cgroup);
 	} else
-		ret = mem_cgroup_get_next_node(root_mem->last_scanned_child,
-						root_mem);
+		next = __mem_cgroup_get_next_node(orig, root_mem);
 
 done:
-	root_mem->last_scanned_child = ret;
-	cgroup_unlock();
-	return ret;
+	if (next)
+		mem_cgroup_get(next);
+	root_mem->last_scanned_child = next;
+	if (orig)
+		mem_cgroup_put(orig);
+	mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
+	return (next) ? next : root_mem;
 }
 
 static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
@@ -621,6 +738,22 @@ static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
 	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
@@ -641,28 +774,25 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	 * but there might be left over accounting, even after children
 	 * have left.
 	 */
-	ret = try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap);
+	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;
+		return 1;	/* indicate reclaim has succeeded */
 	if (!root_mem->use_hierarchy)
 		return ret;
 
-	next_mem = mem_cgroup_get_first_node(root_mem);
+	next_mem = mem_cgroup_get_next_node(root_mem);
 
 	while (next_mem != root_mem) {
-		if (next_mem->obsolete) {
-			mem_cgroup_put(next_mem);
-			cgroup_lock();
-			next_mem = mem_cgroup_get_first_node(root_mem);
-			cgroup_unlock();
+		if (mem_cgroup_is_obsolete(next_mem)) {
+			next_mem = mem_cgroup_get_next_node(root_mem);
 			continue;
 		}
-		ret = try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap);
+		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;
-		cgroup_lock();
-		next_mem = mem_cgroup_get_next_node(next_mem, root_mem);
-		cgroup_unlock();
+			return 1;	/* indicate reclaim has succeeded */
+		next_mem = mem_cgroup_get_next_node(root_mem);
 	}
 	return ret;
 }
@@ -707,23 +837,17 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	 * 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);
+	mem = *memcg;
+	if (likely(!mem)) {
+		mem = try_get_mem_cgroup_from_mm(mm);
 		*memcg = mem;
-		rcu_read_unlock();
 	} else {
-		mem = *memcg;
 		css_get(&mem->css);
 	}
+	if (unlikely(!mem))
+		return 0;
+
+	VM_BUG_ON(mem_cgroup_is_obsolete(mem));
 
 	while (1) {
 		int ret;
@@ -752,6 +876,8 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 
 		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
 							noswap);
+		if (ret)
+			continue;
 
 		/*
 		 * try_to_free_mem_cgroup_pages() might not give us a full
@@ -766,7 +892,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 
 		if (!nr_retries--) {
 			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;
@@ -778,27 +906,25 @@ nomem:
 	return -ENOMEM;
 }
 
-/**
- * mem_cgroup_try_charge - get charge of PAGE_SIZE.
- * @mm: an mm_struct which is charged against. (when *memcg is NULL)
- * @gfp_mask: gfp_mask for reclaim.
- * @memcg: a pointer to memory cgroup which is charged against.
- *
- * charge against memory cgroup pointed by *memcg. if *memcg == NULL, estimated
- * memory cgroup from @mm is got and stored in *memcg.
- *
- * Returns 0 if success. -ENOMEM at failure.
- * This call can invoke OOM-Killer.
- */
-
-int mem_cgroup_try_charge(struct mm_struct *mm,
-			  gfp_t mask, struct mem_cgroup **memcg)
+static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 {
-	return __mem_cgroup_try_charge(mm, mask, memcg, true);
+	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
+ * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be
  * USED state. If already USED, uncharge and return.
  */
 
@@ -868,14 +994,15 @@ static int mem_cgroup_move_account(struct page_cgroup *pc,
 	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);
+	css_put(&from->css);
+
+	css_get(&to->css);
 	pc->mem_cgroup = to;
 	mem_cgroup_charge_statistics(to, pc, true);
-	css_get(&to->css);
 	ret = 0;
 out:
 	unlock_page_cgroup(pc);
@@ -908,8 +1035,10 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
 	if (ret || !parent)
 		return ret;
 
-	if (!get_page_unless_zero(page))
-		return -EBUSY;
+	if (!get_page_unless_zero(page)) {
+		ret = -EBUSY;
+		goto uncharge;
+	}
 
 	ret = isolate_lru_page(page);
 
@@ -918,19 +1047,23 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
 
 	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);
+		/* drop extra refcnt by try_charge() */
+		css_put(&parent->css);
 		return 0;
 	}
-	/* uncharge if move fails */
+
 cancel:
+	put_page(page);
+uncharge:
+	/* drop extra refcnt by try_charge() */
+	css_put(&parent->css);
+	/* uncharge if move fails */
 	res_counter_uncharge(&parent->res, PAGE_SIZE);
 	if (do_swap_account)
 		res_counter_uncharge(&parent->memsw, PAGE_SIZE);
-	put_page(page);
 	return ret;
 }
 
@@ -988,6 +1121,9 @@ int mem_cgroup_newpage_charge(struct page *page,
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
+	struct mem_cgroup *mem = NULL;
+	int ret;
+
 	if (mem_cgroup_disabled())
 		return 0;
 	if (PageCompound(page))
@@ -1000,6 +1136,8 @@ 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;
@@ -1016,30 +1154,60 @@ 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;
-	swp_entry_t     ent;
+	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
@@ -1047,70 +1215,20 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 	 */
 	if (!PageSwapCache(page))
 		return 0;
-
-	ent.val = page_private(page);
-
-	mem = lookup_swap_cgroup(ent);
-	if (!mem || mem->obsolete)
+	mem = try_get_mem_cgroup_from_swapcache(page);
+	if (!mem)
 		goto charge_cur_mm;
 	*ptr = mem;
-	return __mem_cgroup_try_charge(NULL, mask, ptr, true);
+	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);
 }
 
-#ifdef CONFIG_SWAP
-
-int mem_cgroup_cache_charge_swapin(struct page *page,
-			struct mm_struct *mm, gfp_t mask, bool locked)
-{
-	int ret = 0;
-
-	if (mem_cgroup_disabled())
-		return 0;
-	if (unlikely(!mm))
-		mm = &init_mm;
-	if (!locked)
-		lock_page(page);
-	/*
-	 * If not locked, the page can be dropped from SwapCache until
-	 * we reach here.
-	 */
-	if (PageSwapCache(page)) {
-		struct mem_cgroup *mem = NULL;
-		swp_entry_t ent;
-
-		ent.val = page_private(page);
-		if (do_swap_account) {
-			mem = lookup_swap_cgroup(ent);
-			if (mem && mem->obsolete)
-				mem = NULL;
-			if (mem)
-				mm = NULL;
-		}
-		ret = mem_cgroup_charge_common(page, mm, mask,
-				MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
-
-		if (!ret && do_swap_account) {
-			/* avoid double counting */
-			mem = swap_cgroup_record(ent, NULL);
-			if (mem) {
-				res_counter_uncharge(&mem->memsw, PAGE_SIZE);
-				mem_cgroup_put(mem);
-			}
-		}
-	}
-	if (!locked)
-		unlock_page(page);
-	/* add this page(page_cgroup) to the LRU we want. */
-	mem_cgroup_lru_fixup(page);
-
-	return ret;
-}
-#endif
-
 void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
 {
 	struct page_cgroup *pc;
@@ -1120,26 +1238,28 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
 	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. This SwapCache is stable
-	 * because we're still under lock_page().
+	 * 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) {
+	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) {
-			/* If memcg is obsolete, memcg can be != ptr */
 			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 			mem_cgroup_put(memcg);
 		}
 
 	}
 	/* add this page(page_cgroup) to the LRU we want. */
-	mem_cgroup_lru_fixup(page);
+
 }
 
 void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
@@ -1207,6 +1327,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 
 	mem_cgroup_charge_statistics(mem, pc, false);
 	ClearPageCgroupUsed(pc);
+	/*
+	 * 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);
 	unlock_page_cgroup(pc);
@@ -1300,7 +1426,7 @@ int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
 	unlock_page_cgroup(pc);
 
 	if (mem) {
-		ret = mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem);
+		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
 		css_put(&mem->css);
 	}
 	*ptr = mem;
@@ -1364,28 +1490,25 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
  * 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_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();
+	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;
-	}
-	css_get(&mem->css);
-	rcu_read_unlock();
 
 	do {
-		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask, true);
+		progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
 		progress += mem_cgroup_check_under_limit(mem);
 	} while (!progress && --retry);
 
@@ -1395,29 +1518,6 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 	return 0;
 }
 
-/*
- * The inactive anon list should be small enough that the VM never has to
- * do too much work, but large enough that each inactive page has a chance
- * to be referenced again before it is swapped out.
- *
- * this calculation is straightforward porting from
- * page_alloc.c::setup_per_zone_inactive_ratio().
- * it describe more detail.
- */
-static void mem_cgroup_set_inactive_ratio(struct mem_cgroup *memcg)
-{
-	unsigned int gb, ratio;
-
-	gb = res_counter_read_u64(&memcg->res, RES_LIMIT) >> 30;
-	if (gb)
-		ratio = int_sqrt(10 * gb);
-	else
-		ratio = 1;
-
-	memcg->inactive_ratio = ratio;
-
-}
-
 static DEFINE_MUTEX(set_limit_mutex);
 
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
@@ -1452,14 +1552,11 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		progress = try_to_free_mem_cgroup_pages(memcg,
-				GFP_KERNEL, false);
+		progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
+							   false);
   		if (!progress)			retry_count--;
 	}
 
-	if (!ret)
-		mem_cgroup_set_inactive_ratio(memcg);
-
 	return ret;
 }
 
@@ -1497,7 +1594,7 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 			break;
 
 		oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
-		try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL, true);
+		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true);
 		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 		if (curusage >= oldusage)
 			retry_count--;
@@ -1588,7 +1685,7 @@ move_account:
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
 		ret = 0;
-		for_each_node_state(node, N_POSSIBLE) {
+		for_each_node_state(node, N_HIGH_MEMORY) {
 			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
 				enum lru_list l;
 				for_each_lru(l) {
@@ -1628,8 +1725,8 @@ try_to_free:
 			ret = -EINTR;
 			goto out;
 		}
-		progress = try_to_free_mem_cgroup_pages(mem,
-						  GFP_KERNEL, false);
+		progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
+						false, get_swappiness(mem));
 		if (!progress) {
 			nr_retries--;
 			/* maybe some writeback is necessary */
@@ -1743,6 +1840,34 @@ 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;
@@ -1816,6 +1941,82 @@ 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);
+
+	cgroup_lock();
+
+	/* If under hierarchy, only empty-root can set this value */
+	if ((parent->use_hierarchy) ||
+	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
+		cgroup_unlock();
+		return -EINVAL;
+	}
+
+	spin_lock(&memcg->reclaim_param_lock);
+	memcg->swappiness = val;
+	spin_unlock(&memcg->reclaim_param_lock);
+
+	cgroup_unlock();
+
 	return 0;
 }
 
@@ -1857,6 +2058,11 @@ static struct cftype mem_cgroup_files[] = {
 		.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
@@ -1965,20 +2171,13 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
  * the number of reference from swap_cgroup and free mem_cgroup when
  * it goes down to 0.
  *
- * When mem_cgroup is destroyed, mem->obsolete will be set to 0 and
- * entry which points to this memcg will be ignore at swapin.
- *
  * Removal of cgroup itself succeeds regardless of refs from swap.
  */
 
-static void mem_cgroup_free(struct mem_cgroup *mem)
+static void __mem_cgroup_free(struct mem_cgroup *mem)
 {
 	int node;
 
-	if (atomic_read(&mem->refcnt) > 0)
-		return;
-
-
 	for_each_node_state(node, N_POSSIBLE)
 		free_mem_cgroup_per_zone_info(mem, node);
 
@@ -1996,12 +2195,22 @@ static void mem_cgroup_get(struct mem_cgroup *mem)
 static void mem_cgroup_put(struct mem_cgroup *mem)
 {
 	if (atomic_dec_and_test(&mem->refcnt)) {
-		if (!mem->obsolete)
-			return;
-		mem_cgroup_free(mem);
+		struct mem_cgroup *parent = parent_mem_cgroup(mem);
+		__mem_cgroup_free(mem);
+		if (parent)
+			mem_cgroup_put(parent);
 	}
 }
 
+/*
+ * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
+ */
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem)
+{
+	if (!mem->res.parent)
+		return NULL;
+	return mem_cgroup_from_res_counter(mem->res.parent, res);
+}
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 static void __init enable_swap_cgroup(void)
@@ -2015,7 +2224,7 @@ static void __init enable_swap_cgroup(void)
 }
 #endif
 
-static struct cgroup_subsys_state *
+static struct cgroup_subsys_state * __ref
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	struct mem_cgroup *mem, *parent;
@@ -2040,18 +2249,26 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	if (parent && parent->use_hierarchy) {
 		res_counter_init(&mem->res, &parent->res);
 		res_counter_init(&mem->memsw, &parent->memsw);
+		/*
+		 * We increment refcnt of the parent to ensure that we can
+		 * safely access it on res_counter_charge/uncharge.
+		 * This refcnt will be decremented when freeing this
+		 * mem_cgroup(see mem_cgroup_put).
+		 */
+		mem_cgroup_get(parent);
 	} else {
 		res_counter_init(&mem->res, NULL);
 		res_counter_init(&mem->memsw, NULL);
 	}
-	mem_cgroup_set_inactive_ratio(mem);
 	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);
-	mem_cgroup_free(mem);
+	__mem_cgroup_free(mem);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -2059,14 +2276,20 @@ static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
 					struct cgroup *cont)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	mem->obsolete = 1;
 	mem_cgroup_force_empty(mem, false);
 }
 
 static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
-	mem_cgroup_free(mem_cgroup_from_cont(cont));
+	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+	struct mem_cgroup *last_scanned_child = mem->last_scanned_child;
+
+	if (last_scanned_child) {
+		VM_BUG_ON(!mem_cgroup_is_obsolete(last_scanned_child));
+		mem_cgroup_put(last_scanned_child);
+	}
+	mem_cgroup_put(mem);
 }
 
 static int mem_cgroup_populate(struct cgroup_subsys *ss,
@@ -2087,10 +2310,12 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 				struct cgroup *old_cont,
 				struct task_struct *p)
 {
+	mutex_lock(&memcg_tasklist);
 	/*
 	 * FIXME: It's better to move charges of this process from old
 	 * memcg to new memcg. But it's just on TODO-List now.
 	 */
+	mutex_unlock(&memcg_tasklist);
 }
 
 struct cgroup_subsys mem_cgroup_subsys = {