Merge tag 'v3.6-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux

Having missed the merge window, update to 3.6-rc2 to avoid conflicts with
new patches.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>

1 files changed, 232 insertions, 164 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ac35bccadb7b..795e525afaba 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -61,12 +61,12 @@ struct cgroup_subsys mem_cgroup_subsys __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 static struct mem_cgroup *root_mem_cgroup __read_mostly;
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
 int do_swap_account __read_mostly;
 
 /* for remember boot option*/
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+#ifdef CONFIG_MEMCG_SWAP_ENABLED
 static int really_do_swap_account __initdata = 1;
 #else
 static int really_do_swap_account __initdata = 0;
@@ -87,7 +87,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_CACHE, 	   /* # of pages charged as cache */
 	MEM_CGROUP_STAT_RSS,	   /* # of pages charged as anon rss */
 	MEM_CGROUP_STAT_FILE_MAPPED,  /* # of pages charged as file rss */
-	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
+	MEM_CGROUP_STAT_SWAP, /* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 };
 
@@ -378,9 +378,7 @@ static bool move_file(void)
 
 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_ANON,
 	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
 	MEM_CGROUP_CHARGE_TYPE_DROP,	/* a page was unused swap cache */
 	NR_CHARGE_TYPE,
@@ -407,8 +405,14 @@ enum charge_type {
 static void mem_cgroup_get(struct mem_cgroup *memcg);
 static void mem_cgroup_put(struct mem_cgroup *memcg);
 
+static inline
+struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s)
+{
+	return container_of(s, struct mem_cgroup, css);
+}
+
 /* Writing them here to avoid exposing memcg's inner layout */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 #include <net/sock.h>
 #include <net/ip.h>
 
@@ -467,9 +471,9 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(tcp_proto_cgroup);
 #endif /* CONFIG_INET */
-#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
+#endif /* CONFIG_MEMCG_KMEM */
 
-#if defined(CONFIG_INET) && defined(CONFIG_CGROUP_MEM_RES_CTLR_KMEM)
+#if defined(CONFIG_INET) && defined(CONFIG_MEMCG_KMEM)
 static void disarm_sock_keys(struct mem_cgroup *memcg)
 {
 	if (!memcg_proto_activated(&memcg->tcp_mem.cg_proto))
@@ -703,7 +707,7 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
 					 bool charge)
 {
 	int val = (charge) ? 1 : -1;
-	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAPOUT], val);
+	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val);
 }
 
 static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
@@ -864,9 +868,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 
 struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
 {
-	return container_of(cgroup_subsys_state(cont,
-				mem_cgroup_subsys_id), struct mem_cgroup,
-				css);
+	return mem_cgroup_from_css(
+		cgroup_subsys_state(cont, mem_cgroup_subsys_id));
 }
 
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
@@ -879,8 +882,7 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 	if (unlikely(!p))
 		return NULL;
 
-	return container_of(task_subsys_state(p, mem_cgroup_subsys_id),
-				struct mem_cgroup, css);
+	return mem_cgroup_from_css(task_subsys_state(p, mem_cgroup_subsys_id));
 }
 
 struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
@@ -966,8 +968,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
 		css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id);
 		if (css) {
 			if (css == &root->css || css_tryget(css))
-				memcg = container_of(css,
-						     struct mem_cgroup, css);
+				memcg = mem_cgroup_from_css(css);
 		} else
 			id = 0;
 		rcu_read_unlock();
@@ -1148,7 +1149,7 @@ bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 {
 	if (root_memcg == memcg)
 		return true;
-	if (!root_memcg->use_hierarchy)
+	if (!root_memcg->use_hierarchy || !memcg)
 		return false;
 	return css_is_ancestor(&memcg->css, &root_memcg->css);
 }
@@ -1234,7 +1235,7 @@ int mem_cgroup_inactive_file_is_low(struct lruvec *lruvec)
 
 /**
  * mem_cgroup_margin - calculate chargeable space of a memory cgroup
- * @mem: the memory cgroup
+ * @memcg: the memory cgroup
  *
  * Returns the maximum amount of memory @mem can be charged with, in
  * pages.
@@ -1454,7 +1455,7 @@ static int mem_cgroup_count_children(struct mem_cgroup *memcg)
 /*
  * Return the memory (and swap, if configured) limit for a memcg.
  */
-u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
+static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 {
 	u64 limit;
 	u64 memsw;
@@ -1470,6 +1471,73 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 	return min(limit, memsw);
 }
 
+void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+			      int order)
+{
+	struct mem_cgroup *iter;
+	unsigned long chosen_points = 0;
+	unsigned long totalpages;
+	unsigned int points = 0;
+	struct task_struct *chosen = NULL;
+
+	/*
+	 * If current has a pending SIGKILL, then automatically select it.  The
+	 * goal is to allow it to allocate so that it may quickly exit and free
+	 * its memory.
+	 */
+	if (fatal_signal_pending(current)) {
+		set_thread_flag(TIF_MEMDIE);
+		return;
+	}
+
+	check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL);
+	totalpages = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT ? : 1;
+	for_each_mem_cgroup_tree(iter, memcg) {
+		struct cgroup *cgroup = iter->css.cgroup;
+		struct cgroup_iter it;
+		struct task_struct *task;
+
+		cgroup_iter_start(cgroup, &it);
+		while ((task = cgroup_iter_next(cgroup, &it))) {
+			switch (oom_scan_process_thread(task, totalpages, NULL,
+							false)) {
+			case OOM_SCAN_SELECT:
+				if (chosen)
+					put_task_struct(chosen);
+				chosen = task;
+				chosen_points = ULONG_MAX;
+				get_task_struct(chosen);
+				/* fall through */
+			case OOM_SCAN_CONTINUE:
+				continue;
+			case OOM_SCAN_ABORT:
+				cgroup_iter_end(cgroup, &it);
+				mem_cgroup_iter_break(memcg, iter);
+				if (chosen)
+					put_task_struct(chosen);
+				return;
+			case OOM_SCAN_OK:
+				break;
+			};
+			points = oom_badness(task, memcg, NULL, totalpages);
+			if (points > chosen_points) {
+				if (chosen)
+					put_task_struct(chosen);
+				chosen = task;
+				chosen_points = points;
+				get_task_struct(chosen);
+			}
+		}
+		cgroup_iter_end(cgroup, &it);
+	}
+
+	if (!chosen)
+		return;
+	points = chosen_points * 1000 / totalpages;
+	oom_kill_process(chosen, gfp_mask, order, points, totalpages, memcg,
+			 NULL, "Memory cgroup out of memory");
+}
+
 static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
 					gfp_t gfp_mask,
 					unsigned long flags)
@@ -1508,7 +1576,7 @@ static unsigned long mem_cgroup_reclaim(struct mem_cgroup *memcg,
 
 /**
  * test_mem_cgroup_node_reclaimable
- * @mem: the target memcg
+ * @memcg: the target memcg
  * @nid: the node ID to be checked.
  * @noswap : specify true here if the user wants flle only information.
  *
@@ -1899,7 +1967,7 @@ again:
 		return;
 	/*
 	 * If this memory cgroup is not under account moving, we don't
-	 * need to take move_lock_page_cgroup(). Because we already hold
+	 * need to take move_lock_mem_cgroup(). Because we already hold
 	 * rcu_read_lock(), any calls to move_account will be delayed until
 	 * rcu_read_unlock() if mem_cgroup_stolen() == true.
 	 */
@@ -1921,7 +1989,7 @@ void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags)
 	/*
 	 * It's guaranteed that pc->mem_cgroup never changes while
 	 * lock is held because a routine modifies pc->mem_cgroup
-	 * should take move_lock_page_cgroup().
+	 * should take move_lock_mem_cgroup().
 	 */
 	move_unlock_mem_cgroup(pc->mem_cgroup, flags);
 }
@@ -2268,7 +2336,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	 * 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).
+	 * set, if so charge the root memcg (happens for pagecache usage).
 	 */
 	if (!*ptr && !mm)
 		*ptr = root_mem_cgroup;
@@ -2429,7 +2497,7 @@ static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 	css = css_lookup(&mem_cgroup_subsys, id);
 	if (!css)
 		return NULL;
-	return container_of(css, struct mem_cgroup, css);
+	return mem_cgroup_from_css(css);
 }
 
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
@@ -2473,11 +2541,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	bool anon;
 
 	lock_page_cgroup(pc);
-	if (unlikely(PageCgroupUsed(pc))) {
-		unlock_page_cgroup(pc);
-		__mem_cgroup_cancel_charge(memcg, nr_pages);
-		return;
-	}
+	VM_BUG_ON(PageCgroupUsed(pc));
 	/*
 	 * we don't need page_cgroup_lock about tail pages, becase they are not
 	 * accessed by any other context at this point.
@@ -2519,7 +2583,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON)
 		anon = true;
 	else
 		anon = false;
@@ -2644,8 +2708,7 @@ out:
 
 static int mem_cgroup_move_parent(struct page *page,
 				  struct page_cgroup *pc,
-				  struct mem_cgroup *child,
-				  gfp_t gfp_mask)
+				  struct mem_cgroup *child)
 {
 	struct mem_cgroup *parent;
 	unsigned int nr_pages;
@@ -2728,38 +2791,7 @@ int mem_cgroup_newpage_charge(struct page *page,
 	VM_BUG_ON(page->mapping && !PageAnon(page));
 	VM_BUG_ON(!mm);
 	return mem_cgroup_charge_common(page, mm, gfp_mask,
-					MEM_CGROUP_CHARGE_TYPE_MAPPED);
-}
-
-static void
-__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
-					enum charge_type ctype);
-
-int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask)
-{
-	struct mem_cgroup *memcg = NULL;
-	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
-	int ret;
-
-	if (mem_cgroup_disabled())
-		return 0;
-	if (PageCompound(page))
-		return 0;
-
-	if (unlikely(!mm))
-		mm = &init_mm;
-	if (!page_is_file_cache(page))
-		type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-
-	if (!PageSwapCache(page))
-		ret = mem_cgroup_charge_common(page, mm, gfp_mask, type);
-	else { /* page is swapcache/shmem */
-		ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &memcg);
-		if (!ret)
-			__mem_cgroup_commit_charge_swapin(page, memcg, type);
-	}
-	return ret;
+					MEM_CGROUP_CHARGE_TYPE_ANON);
 }
 
 /*
@@ -2768,27 +2800,26 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
  * struct page_cgroup is acquired. This refcnt will be consumed 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 **memcgp)
+static int __mem_cgroup_try_charge_swapin(struct mm_struct *mm,
+					  struct page *page,
+					  gfp_t mask,
+					  struct mem_cgroup **memcgp)
 {
 	struct mem_cgroup *memcg;
+	struct page_cgroup *pc;
 	int ret;
 
-	*memcgp = NULL;
-
-	if (mem_cgroup_disabled())
-		return 0;
-
-	if (!do_swap_account)
-		goto charge_cur_mm;
+	pc = lookup_page_cgroup(page);
 	/*
-	 * A racing thread's fault, or swapoff, may have already updated
-	 * the pte, and even removed page from swap cache: in those cases
-	 * do_swap_page()'s pte_same() test will fail; but there's also a
-	 * KSM case which does need to charge the page.
+	 * Every swap fault against a single page tries to charge the
+	 * page, bail as early as possible.  shmem_unuse() encounters
+	 * already charged pages, too.  The USED bit is protected by
+	 * the page lock, which serializes swap cache removal, which
+	 * in turn serializes uncharging.
 	 */
-	if (!PageSwapCache(page))
+	if (PageCgroupUsed(pc))
+		return 0;
+	if (!do_swap_account)
 		goto charge_cur_mm;
 	memcg = try_get_mem_cgroup_from_page(page);
 	if (!memcg)
@@ -2800,14 +2831,44 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 		ret = 0;
 	return ret;
 charge_cur_mm:
-	if (unlikely(!mm))
-		mm = &init_mm;
 	ret = __mem_cgroup_try_charge(mm, mask, 1, memcgp, true);
 	if (ret == -EINTR)
 		ret = 0;
 	return ret;
 }
 
+int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page,
+				 gfp_t gfp_mask, struct mem_cgroup **memcgp)
+{
+	*memcgp = NULL;
+	if (mem_cgroup_disabled())
+		return 0;
+	/*
+	 * A racing thread's fault, or swapoff, may have already
+	 * updated the pte, and even removed page from swap cache: in
+	 * those cases unuse_pte()'s pte_same() test will fail; but
+	 * there's also a KSM case which does need to charge the page.
+	 */
+	if (!PageSwapCache(page)) {
+		int ret;
+
+		ret = __mem_cgroup_try_charge(mm, gfp_mask, 1, memcgp, true);
+		if (ret == -EINTR)
+			ret = 0;
+		return ret;
+	}
+	return __mem_cgroup_try_charge_swapin(mm, page, gfp_mask, memcgp);
+}
+
+void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
+{
+	if (mem_cgroup_disabled())
+		return;
+	if (!memcg)
+		return;
+	__mem_cgroup_cancel_charge(memcg, 1);
+}
+
 static void
 __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg,
 					enum charge_type ctype)
@@ -2842,16 +2903,30 @@ void mem_cgroup_commit_charge_swapin(struct page *page,
 				     struct mem_cgroup *memcg)
 {
 	__mem_cgroup_commit_charge_swapin(page, memcg,
-					  MEM_CGROUP_CHARGE_TYPE_MAPPED);
+					  MEM_CGROUP_CHARGE_TYPE_ANON);
 }
 
-void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *memcg)
+int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
+				gfp_t gfp_mask)
 {
+	struct mem_cgroup *memcg = NULL;
+	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	int ret;
+
 	if (mem_cgroup_disabled())
-		return;
-	if (!memcg)
-		return;
-	__mem_cgroup_cancel_charge(memcg, 1);
+		return 0;
+	if (PageCompound(page))
+		return 0;
+
+	if (!PageSwapCache(page))
+		ret = mem_cgroup_charge_common(page, mm, gfp_mask, type);
+	else { /* page is swapcache/shmem */
+		ret = __mem_cgroup_try_charge_swapin(mm, page,
+						     gfp_mask, &memcg);
+		if (!ret)
+			__mem_cgroup_commit_charge_swapin(page, memcg, type);
+	}
+	return ret;
 }
 
 static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg,
@@ -2911,7 +2986,8 @@ direct_uncharge:
  * uncharge if !page_mapped(page)
  */
 static struct mem_cgroup *
-__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
+__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype,
+			     bool end_migration)
 {
 	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
@@ -2921,8 +2997,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	if (mem_cgroup_disabled())
 		return NULL;
 
-	if (PageSwapCache(page))
-		return NULL;
+	VM_BUG_ON(PageSwapCache(page));
 
 	if (PageTransHuge(page)) {
 		nr_pages <<= compound_order(page);
@@ -2945,7 +3020,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	anon = PageAnon(page);
 
 	switch (ctype) {
-	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+	case MEM_CGROUP_CHARGE_TYPE_ANON:
 		/*
 		 * Generally PageAnon tells if it's the anon statistics to be
 		 * updated; but sometimes e.g. mem_cgroup_uncharge_page() is
@@ -2955,7 +3030,16 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		/* fallthrough */
 	case MEM_CGROUP_CHARGE_TYPE_DROP:
 		/* See mem_cgroup_prepare_migration() */
-		if (page_mapped(page) || PageCgroupMigration(pc))
+		if (page_mapped(page))
+			goto unlock_out;
+		/*
+		 * Pages under migration may not be uncharged.  But
+		 * end_migration() /must/ be the one uncharging the
+		 * unused post-migration page and so it has to call
+		 * here with the migration bit still set.  See the
+		 * res_counter handling below.
+		 */
+		if (!end_migration && PageCgroupMigration(pc))
 			goto unlock_out;
 		break;
 	case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
@@ -2989,7 +3073,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		mem_cgroup_swap_statistics(memcg, true);
 		mem_cgroup_get(memcg);
 	}
-	if (!mem_cgroup_is_root(memcg))
+	/*
+	 * Migration does not charge the res_counter for the
+	 * replacement page, so leave it alone when phasing out the
+	 * page that is unused after the migration.
+	 */
+	if (!end_migration && !mem_cgroup_is_root(memcg))
 		mem_cgroup_do_uncharge(memcg, nr_pages, ctype);
 
 	return memcg;
@@ -3005,14 +3094,16 @@ void mem_cgroup_uncharge_page(struct page *page)
 	if (page_mapped(page))
 		return;
 	VM_BUG_ON(page->mapping && !PageAnon(page));
-	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+	if (PageSwapCache(page))
+		return;
+	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false);
 }
 
 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);
+	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false);
 }
 
 /*
@@ -3076,7 +3167,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 	if (!swapout) /* this was a swap cache but the swap is unused ! */
 		ctype = MEM_CGROUP_CHARGE_TYPE_DROP;
 
-	memcg = __mem_cgroup_uncharge_common(page, ctype);
+	memcg = __mem_cgroup_uncharge_common(page, ctype, false);
 
 	/*
 	 * record memcg information,  if swapout && memcg != NULL,
@@ -3087,7 +3178,7 @@ mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
 }
 #endif
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 /*
  * called from swap_entry_free(). remove record in swap_cgroup and
  * uncharge "memsw" account.
@@ -3166,19 +3257,18 @@ static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
  * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
  * page belongs to.
  */
-int mem_cgroup_prepare_migration(struct page *page,
-	struct page *newpage, struct mem_cgroup **memcgp, gfp_t gfp_mask)
+void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
+				  struct mem_cgroup **memcgp)
 {
 	struct mem_cgroup *memcg = NULL;
 	struct page_cgroup *pc;
 	enum charge_type ctype;
-	int ret = 0;
 
 	*memcgp = NULL;
 
 	VM_BUG_ON(PageTransHuge(page));
 	if (mem_cgroup_disabled())
-		return 0;
+		return;
 
 	pc = lookup_page_cgroup(page);
 	lock_page_cgroup(pc);
@@ -3223,24 +3313,9 @@ int mem_cgroup_prepare_migration(struct page *page,
 	 * we return here.
 	 */
 	if (!memcg)
-		return 0;
+		return;
 
 	*memcgp = memcg;
-	ret = __mem_cgroup_try_charge(NULL, gfp_mask, 1, memcgp, false);
-	css_put(&memcg->css);/* drop extra refcnt */
-	if (ret) {
-		if (PageAnon(page)) {
-			lock_page_cgroup(pc);
-			ClearPageCgroupMigration(pc);
-			unlock_page_cgroup(pc);
-			/*
-			 * The old page may be fully unmapped while we kept it.
-			 */
-			mem_cgroup_uncharge_page(page);
-		}
-		/* we'll need to revisit this error code (we have -EINTR) */
-		return -ENOMEM;
-	}
 	/*
 	 * We charge new page before it's used/mapped. So, even if unlock_page()
 	 * is called before end_migration, we can catch all events on this new
@@ -3248,13 +3323,15 @@ int mem_cgroup_prepare_migration(struct page *page,
 	 * mapcount will be finally 0 and we call uncharge in end_migration().
 	 */
 	if (PageAnon(page))
-		ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
-	else if (page_is_file_cache(page))
-		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+		ctype = MEM_CGROUP_CHARGE_TYPE_ANON;
 	else
-		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	/*
+	 * The page is committed to the memcg, but it's not actually
+	 * charged to the res_counter since we plan on replacing the
+	 * old one and only one page is going to be left afterwards.
+	 */
 	__mem_cgroup_commit_charge(memcg, newpage, 1, ctype, false);
-	return ret;
 }
 
 /* remove redundant charge if migration failed*/
@@ -3276,6 +3353,12 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 		used = newpage;
 		unused = oldpage;
 	}
+	anon = PageAnon(used);
+	__mem_cgroup_uncharge_common(unused,
+				     anon ? MEM_CGROUP_CHARGE_TYPE_ANON
+				     : MEM_CGROUP_CHARGE_TYPE_CACHE,
+				     true);
+	css_put(&memcg->css);
 	/*
 	 * We disallowed uncharge of pages under migration because mapcount
 	 * of the page goes down to zero, temporarly.
@@ -3285,10 +3368,6 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg,
 	lock_page_cgroup(pc);
 	ClearPageCgroupMigration(pc);
 	unlock_page_cgroup(pc);
-	anon = PageAnon(used);
-	__mem_cgroup_uncharge_common(unused,
-		anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED
-		     : MEM_CGROUP_CHARGE_TYPE_CACHE);
 
 	/*
 	 * If a page is a file cache, radix-tree replacement is very atomic
@@ -3340,10 +3419,6 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	 */
 	if (!memcg)
 		return;
-
-	if (PageSwapBacked(oldpage))
-		type = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-
 	/*
 	 * Even if newpage->mapping was NULL before starting replacement,
 	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
@@ -3418,7 +3493,7 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 		/*
 		 * Rather than hide all in some function, I do this in
 		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit < memcg->memsw.limit.
+		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
 		 */
 		mutex_lock(&set_limit_mutex);
 		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
@@ -3479,7 +3554,7 @@ static int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 		/*
 		 * Rather than hide all in some function, I do this in
 		 * open coded manner. You see what this really does.
-		 * We have to guarantee memcg->res.limit < memcg->memsw.limit.
+		 * We have to guarantee memcg->res.limit <= memcg->memsw.limit.
 		 */
 		mutex_lock(&set_limit_mutex);
 		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
@@ -3611,10 +3686,12 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 }
 
 /*
- * This routine traverse page_cgroup in given list and drop them all.
- * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
+ * Traverse a specified page_cgroup list and try to drop them all.  This doesn't
+ * reclaim the pages page themselves - it just removes the page_cgroups.
+ * Returns true if some page_cgroups were not freed, indicating that the caller
+ * must retry this operation.
  */
-static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
+static bool mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 				int node, int zid, enum lru_list lru)
 {
 	struct mem_cgroup_per_zone *mz;
@@ -3622,7 +3699,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 	struct list_head *list;
 	struct page *busy;
 	struct zone *zone;
-	int ret = 0;
 
 	zone = &NODE_DATA(node)->node_zones[zid];
 	mz = mem_cgroup_zoneinfo(memcg, node, zid);
@@ -3636,7 +3712,6 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 		struct page_cgroup *pc;
 		struct page *page;
 
-		ret = 0;
 		spin_lock_irqsave(&zone->lru_lock, flags);
 		if (list_empty(list)) {
 			spin_unlock_irqrestore(&zone->lru_lock, flags);
@@ -3653,21 +3728,14 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg,
 
 		pc = lookup_page_cgroup(page);
 
-		ret = mem_cgroup_move_parent(page, pc, memcg, GFP_KERNEL);
-		if (ret == -ENOMEM || ret == -EINTR)
-			break;
-
-		if (ret == -EBUSY || ret == -EINVAL) {
+		if (mem_cgroup_move_parent(page, pc, memcg)) {
 			/* found lock contention or "pc" is obsolete. */
 			busy = page;
 			cond_resched();
 		} else
 			busy = NULL;
 	}
-
-	if (!ret && !list_empty(list))
-		return -EBUSY;
-	return ret;
+	return !list_empty(list);
 }
 
 /*
@@ -3692,9 +3760,6 @@ move_account:
 		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();
 		drain_all_stock_sync(memcg);
@@ -3715,9 +3780,6 @@ move_account:
 		}
 		mem_cgroup_end_move(memcg);
 		memcg_oom_recover(memcg);
-		/* it seems parent cgroup doesn't have enough mem */
-		if (ret == -ENOMEM)
-			goto try_to_free;
 		cond_resched();
 	/* "ret" should also be checked to ensure all lists are empty. */
 	} while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0 || ret);
@@ -3779,6 +3841,10 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 		parent_memcg = mem_cgroup_from_cont(parent);
 
 	cgroup_lock();
+
+	if (memcg->use_hierarchy == val)
+		goto out;
+
 	/*
 	 * If parent's use_hierarchy is set, we can't make any modifications
 	 * in the child subtrees. If it is unset, then the change can
@@ -3795,6 +3861,8 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 			retval = -EBUSY;
 	} else
 		retval = -EINVAL;
+
+out:
 	cgroup_unlock();
 
 	return retval;
@@ -3831,7 +3899,7 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
 
 	if (swap)
-		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAPOUT);
+		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
 
 	return val << PAGE_SHIFT;
 }
@@ -4015,7 +4083,7 @@ static int mem_cgroup_move_charge_write(struct cgroup *cgrp,
 #endif
 
 #ifdef CONFIG_NUMA
-static int mem_control_numa_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_numa_stat_show(struct cgroup *cont, struct cftype *cft,
 				      struct seq_file *m)
 {
 	int nid;
@@ -4074,7 +4142,7 @@ static inline void mem_cgroup_lru_names_not_uptodate(void)
 	BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS);
 }
 
-static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
+static int memcg_stat_show(struct cgroup *cont, struct cftype *cft,
 				 struct seq_file *m)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
@@ -4082,7 +4150,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	unsigned int i;
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
-		if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
+		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
 			   mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
@@ -4109,7 +4177,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		long long val = 0;
 
-		if (i == MEM_CGROUP_STAT_SWAPOUT && !do_swap_account)
+		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		for_each_mem_cgroup_tree(mi, memcg)
 			val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
@@ -4533,7 +4601,7 @@ static int mem_cgroup_oom_control_write(struct cgroup *cgrp,
 	return 0;
 }
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
+#ifdef CONFIG_MEMCG_KMEM
 static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss)
 {
 	return mem_cgroup_sockets_init(memcg, ss);
@@ -4588,7 +4656,7 @@ static struct cftype mem_cgroup_files[] = {
 	},
 	{
 		.name = "stat",
-		.read_seq_string = mem_control_stat_show,
+		.read_seq_string = memcg_stat_show,
 	},
 	{
 		.name = "force_empty",
@@ -4620,10 +4688,10 @@ static struct cftype mem_cgroup_files[] = {
 #ifdef CONFIG_NUMA
 	{
 		.name = "numa_stat",
-		.read_seq_string = mem_control_numa_stat_show,
+		.read_seq_string = memcg_numa_stat_show,
 	},
 #endif
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 	{
 		.name = "memsw.usage_in_bytes",
 		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
@@ -4810,7 +4878,7 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 }
 EXPORT_SYMBOL(parent_mem_cgroup);
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 static void __init enable_swap_cgroup(void)
 {
 	if (!mem_cgroup_disabled() && really_do_swap_account)
@@ -5541,7 +5609,7 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.__DEPRECATED_clear_css_refs = true,
 };
 
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+#ifdef CONFIG_MEMCG_SWAP
 static int __init enable_swap_account(char *s)
 {
 	/* consider enabled if no parameter or 1 is given */