X-Git-Url: http://git.cascardo.info/?a=blobdiff_plain;f=mm%2Fmemcontrol.c;h=1cbe1e54ff5f5fbee575c68f28f89088ad72ea5a;hb=00501b531c472;hp=f009a14918d29c8c9b7c09db6c60428a0042f644;hpb=79eb238c76782a59d51adf8a3dd7f6444245b475;p=cascardo%2Flinux.git

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f009a14918d2..1cbe1e54ff5f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2551,55 +2551,63 @@ static int memcg_cpu_hotplug_callback(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-
-/* See mem_cgroup_try_charge() for details */
-enum {
-	CHARGE_OK,		/* success */
-	CHARGE_RETRY,		/* need to retry but retry is not bad */
-	CHARGE_NOMEM,		/* we can't do more. return -ENOMEM */
-	CHARGE_WOULDBLOCK,	/* GFP_WAIT wasn't set and no enough res. */
-};
-
-static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
-				unsigned int nr_pages, unsigned int min_pages,
-				bool invoke_oom)
+static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
+		      unsigned int nr_pages)
 {
-	unsigned long csize = nr_pages * PAGE_SIZE;
+	unsigned int batch = max(CHARGE_BATCH, nr_pages);
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup *mem_over_limit;
 	struct res_counter *fail_res;
+	unsigned long nr_reclaimed;
 	unsigned long flags = 0;
-	int ret;
+	unsigned long long size;
+	int ret = 0;
 
-	ret = res_counter_charge(&memcg->res, csize, &fail_res);
+retry:
+	if (consume_stock(memcg, nr_pages))
+		goto done;
 
-	if (likely(!ret)) {
+	size = batch * PAGE_SIZE;
+	if (!res_counter_charge(&memcg->res, size, &fail_res)) {
 		if (!do_swap_account)
-			return CHARGE_OK;
-		ret = res_counter_charge(&memcg->memsw, csize, &fail_res);
-		if (likely(!ret))
-			return CHARGE_OK;
-
-		res_counter_uncharge(&memcg->res, csize);
+			goto done_restock;
+		if (!res_counter_charge(&memcg->memsw, size, &fail_res))
+			goto done_restock;
+		res_counter_uncharge(&memcg->res, size);
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
 		flags |= MEM_CGROUP_RECLAIM_NOSWAP;
 	} else
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
+
+	if (batch > nr_pages) {
+		batch = nr_pages;
+		goto retry;
+	}
+
 	/*
-	 * Never reclaim on behalf of optional batching, retry with a
-	 * single page instead.
+	 * Unlike in global OOM situations, memcg is not in a physical
+	 * memory shortage.  Allow dying and OOM-killed tasks to
+	 * bypass the last charges so that they can exit quickly and
+	 * free their memory.
 	 */
-	if (nr_pages > min_pages)
-		return CHARGE_RETRY;
+	if (unlikely(test_thread_flag(TIF_MEMDIE) ||
+		     fatal_signal_pending(current) ||
+		     current->flags & PF_EXITING))
+		goto bypass;
+
+	if (unlikely(task_in_memcg_oom(current)))
+		goto nomem;
 
 	if (!(gfp_mask & __GFP_WAIT))
-		return CHARGE_WOULDBLOCK;
+		goto nomem;
 
-	if (gfp_mask & __GFP_NORETRY)
-		return CHARGE_NOMEM;
+	nr_reclaimed = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
 
-	ret = mem_cgroup_reclaim(mem_over_limit, gfp_mask, flags);
 	if (mem_cgroup_margin(mem_over_limit) >= nr_pages)
-		return CHARGE_RETRY;
+		goto retry;
+
+	if (gfp_mask & __GFP_NORETRY)
+		goto nomem;
 	/*
 	 * Even though the limit is exceeded at this point, reclaim
 	 * may have been able to free some pages.  Retry the charge
@@ -2609,142 +2617,47 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	 * unlikely to succeed so close to the limit, and we fall back
 	 * to regular pages anyway in case of failure.
 	 */
-	if (nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER) && ret)
-		return CHARGE_RETRY;
-
+	if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER))
+		goto retry;
 	/*
 	 * At task move, charge accounts can be doubly counted. So, it's
 	 * better to wait until the end of task_move if something is going on.
 	 */
 	if (mem_cgroup_wait_acct_move(mem_over_limit))
-		return CHARGE_RETRY;
-
-	if (invoke_oom)
-		mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(csize));
-
-	return CHARGE_NOMEM;
-}
-
-/**
- * mem_cgroup_try_charge - try charging a memcg
- * @memcg: memcg to charge
- * @nr_pages: number of pages to charge
- * @oom: trigger OOM if reclaim fails
- *
- * Returns 0 if @memcg was charged successfully, -EINTR if the charge
- * was bypassed to root_mem_cgroup, and -ENOMEM if the charge failed.
- */
-static int mem_cgroup_try_charge(struct mem_cgroup *memcg,
-				 gfp_t gfp_mask,
-				 unsigned int nr_pages,
-				 bool oom)
-{
-	unsigned int batch = max(CHARGE_BATCH, nr_pages);
-	int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	int ret;
-
-	if (mem_cgroup_is_root(memcg))
-		goto done;
-	/*
-	 * Unlike in global OOM situations, memcg is not in a physical
-	 * memory shortage.  Allow dying and OOM-killed tasks to
-	 * bypass the last charges so that they can exit quickly and
-	 * free their memory.
-	 */
-	if (unlikely(test_thread_flag(TIF_MEMDIE) ||
-		     fatal_signal_pending(current) ||
-		     current->flags & PF_EXITING))
-		goto bypass;
+		goto retry;
 
-	if (unlikely(task_in_memcg_oom(current)))
-		goto nomem;
+	if (nr_retries--)
+		goto retry;
 
 	if (gfp_mask & __GFP_NOFAIL)
-		oom = false;
-again:
-	if (consume_stock(memcg, nr_pages))
-		goto done;
-
-	do {
-		bool invoke_oom = oom && !nr_oom_retries;
-
-		/* If killed, bypass charge */
-		if (fatal_signal_pending(current))
-			goto bypass;
+		goto bypass;
 
-		ret = mem_cgroup_do_charge(memcg, gfp_mask, batch,
-					   nr_pages, invoke_oom);
-		switch (ret) {
-		case CHARGE_OK:
-			break;
-		case CHARGE_RETRY: /* not in OOM situation but retry */
-			batch = nr_pages;
-			goto again;
-		case CHARGE_WOULDBLOCK: /* !__GFP_WAIT */
-			goto nomem;
-		case CHARGE_NOMEM: /* OOM routine works */
-			if (!oom || invoke_oom)
-				goto nomem;
-			nr_oom_retries--;
-			break;
-		}
-	} while (ret != CHARGE_OK);
+	if (fatal_signal_pending(current))
+		goto bypass;
 
-	if (batch > nr_pages)
-		refill_stock(memcg, batch - nr_pages);
-done:
-	return 0;
+	mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages));
 nomem:
 	if (!(gfp_mask & __GFP_NOFAIL))
 		return -ENOMEM;
 bypass:
-	return -EINTR;
-}
-
-/**
- * mem_cgroup_try_charge_mm - try charging a mm
- * @mm: mm_struct to charge
- * @nr_pages: number of pages to charge
- * @oom: trigger OOM if reclaim fails
- *
- * Returns the charged mem_cgroup associated with the given mm_struct or
- * NULL the charge failed.
- */
-static struct mem_cgroup *mem_cgroup_try_charge_mm(struct mm_struct *mm,
-				 gfp_t gfp_mask,
-				 unsigned int nr_pages,
-				 bool oom)
+	memcg = root_mem_cgroup;
+	ret = -EINTR;
+	goto retry;
 
-{
-	struct mem_cgroup *memcg;
-	int ret;
-
-	memcg = get_mem_cgroup_from_mm(mm);
-	ret = mem_cgroup_try_charge(memcg, gfp_mask, nr_pages, oom);
-	css_put(&memcg->css);
-	if (ret == -EINTR)
-		memcg = root_mem_cgroup;
-	else if (ret)
-		memcg = NULL;
-
-	return memcg;
+done_restock:
+	if (batch > nr_pages)
+		refill_stock(memcg, batch - nr_pages);
+done:
+	return ret;
 }
 
-/*
- * Somemtimes we have to undo a charge we got by try_charge().
- * This function is for that and do uncharge, put css's refcnt.
- * gotten by try_charge().
- */
-static void __mem_cgroup_cancel_charge(struct mem_cgroup *memcg,
-				       unsigned int nr_pages)
+static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	if (!mem_cgroup_is_root(memcg)) {
-		unsigned long bytes = nr_pages * PAGE_SIZE;
+	unsigned long bytes = nr_pages * PAGE_SIZE;
 
-		res_counter_uncharge(&memcg->res, bytes);
-		if (do_swap_account)
-			res_counter_uncharge(&memcg->memsw, bytes);
-	}
+	res_counter_uncharge(&memcg->res, bytes);
+	if (do_swap_account)
+		res_counter_uncharge(&memcg->memsw, bytes);
 }
 
 /*
@@ -2756,9 +2669,6 @@ static void __mem_cgroup_cancel_local_charge(struct mem_cgroup *memcg,
 {
 	unsigned long bytes = nr_pages * PAGE_SIZE;
 
-	if (mem_cgroup_is_root(memcg))
-		return;
-
 	res_counter_uncharge_until(&memcg->res, memcg->res.parent, bytes);
 	if (do_swap_account)
 		res_counter_uncharge_until(&memcg->memsw,
@@ -2807,17 +2717,13 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	return memcg;
 }
 
-static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
-				       struct page *page,
-				       unsigned int nr_pages,
-				       enum charge_type ctype,
-				       bool lrucare)
+static void commit_charge(struct page *page, struct mem_cgroup *memcg,
+			  unsigned int nr_pages, bool anon, bool lrucare)
 {
 	struct page_cgroup *pc = lookup_page_cgroup(page);
 	struct zone *uninitialized_var(zone);
 	struct lruvec *lruvec;
 	bool was_on_lru = false;
-	bool anon;
 
 	lock_page_cgroup(pc);
 	VM_BUG_ON_PAGE(PageCgroupUsed(pc), page);
@@ -2842,14 +2748,6 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 	}
 
 	pc->mem_cgroup = memcg;
-	/*
-	 * We access a page_cgroup asynchronously without lock_page_cgroup().
-	 * Especially when a page_cgroup is taken from a page, pc->mem_cgroup
-	 * is accessed after testing USED bit. To make pc->mem_cgroup visible
-	 * before USED bit, we need memory barrier here.
-	 * See mem_cgroup_add_lru_list(), etc.
-	 */
-	smp_wmb();
 	SetPageCgroupUsed(pc);
 
 	if (lrucare) {
@@ -2862,11 +2760,6 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg,
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	if (ctype == MEM_CGROUP_CHARGE_TYPE_ANON)
-		anon = true;
-	else
-		anon = false;
-
 	mem_cgroup_charge_statistics(memcg, page, anon, nr_pages);
 	unlock_page_cgroup(pc);
 
@@ -2937,22 +2830,21 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, u64 size)
 	if (ret)
 		return ret;
 
-	ret = mem_cgroup_try_charge(memcg, gfp, size >> PAGE_SHIFT,
-				    oom_gfp_allowed(gfp));
+	ret = try_charge(memcg, gfp, size >> PAGE_SHIFT);
 	if (ret == -EINTR)  {
 		/*
-		 * mem_cgroup_try_charge() chosed to bypass to root due to
-		 * OOM kill or fatal signal.  Since our only options are to
-		 * either fail the allocation or charge it to this cgroup, do
-		 * it as a temporary condition. But we can't fail. From a
-		 * kmem/slab perspective, the cache has already been selected,
-		 * by mem_cgroup_kmem_get_cache(), so it is too late to change
+		 * try_charge() chose to bypass to root due to OOM kill or
+		 * fatal signal.  Since our only options are to either fail
+		 * the allocation or charge it to this cgroup, do it as a
+		 * temporary condition. But we can't fail. From a kmem/slab
+		 * perspective, the cache has already been selected, by
+		 * mem_cgroup_kmem_get_cache(), so it is too late to change
 		 * our minds.
 		 *
 		 * This condition will only trigger if the task entered
-		 * memcg_charge_kmem in a sane state, but was OOM-killed during
-		 * mem_cgroup_try_charge() above. Tasks that were already
-		 * dying when the allocation triggers should have been already
+		 * memcg_charge_kmem in a sane state, but was OOM-killed
+		 * during try_charge() above. Tasks that were already dying
+		 * when the allocation triggers should have been already
 		 * directed to the root cgroup in memcontrol.h
 		 */
 		res_counter_charge_nofail(&memcg->res, size, &fail_res);
@@ -3463,12 +3355,13 @@ void __memcg_kmem_commit_charge(struct page *page, struct mem_cgroup *memcg,
 		memcg_uncharge_kmem(memcg, PAGE_SIZE << order);
 		return;
 	}
-
+	/*
+	 * The page is freshly allocated and not visible to any
+	 * outside callers yet.  Set up pc non-atomically.
+	 */
 	pc = lookup_page_cgroup(page);
-	lock_page_cgroup(pc);
 	pc->mem_cgroup = memcg;
-	SetPageCgroupUsed(pc);
-	unlock_page_cgroup(pc);
+	pc->flags = PCG_USED;
 }
 
 void __memcg_kmem_uncharge_pages(struct page *page, int order)
@@ -3478,19 +3371,11 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order)
 
 
 	pc = lookup_page_cgroup(page);
-	/*
-	 * Fast unlocked return. Theoretically might have changed, have to
-	 * check again after locking.
-	 */
 	if (!PageCgroupUsed(pc))
 		return;
 
-	lock_page_cgroup(pc);
-	if (PageCgroupUsed(pc)) {
-		memcg = pc->mem_cgroup;
-		ClearPageCgroupUsed(pc);
-	}
-	unlock_page_cgroup(pc);
+	memcg = pc->mem_cgroup;
+	pc->flags = 0;
 
 	/*
 	 * We trust that only if there is a memcg associated with the page, it
@@ -3531,7 +3416,6 @@ void mem_cgroup_split_huge_fixup(struct page *head)
 	for (i = 1; i < HPAGE_PMD_NR; i++) {
 		pc = head_pc + i;
 		pc->mem_cgroup = memcg;
-		smp_wmb();/* see __commit_charge() */
 		pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
 	}
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
@@ -3682,170 +3566,6 @@ out:
 	return ret;
 }
 
-int mem_cgroup_charge_anon(struct page *page,
-			      struct mm_struct *mm, gfp_t gfp_mask)
-{
-	unsigned int nr_pages = 1;
-	struct mem_cgroup *memcg;
-	bool oom = true;
-
-	if (mem_cgroup_disabled())
-		return 0;
-
-	VM_BUG_ON_PAGE(page_mapped(page), page);
-	VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page);
-	VM_BUG_ON(!mm);
-
-	if (PageTransHuge(page)) {
-		nr_pages <<= compound_order(page);
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-		/*
-		 * Never OOM-kill a process for a huge page.  The
-		 * fault handler will fall back to regular pages.
-		 */
-		oom = false;
-	}
-
-	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, nr_pages, oom);
-	if (!memcg)
-		return -ENOMEM;
-	__mem_cgroup_commit_charge(memcg, page, nr_pages,
-				   MEM_CGROUP_CHARGE_TYPE_ANON, false);
-	return 0;
-}
-
-/*
- * 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 acquired. This refcnt will be consumed by
- * "commit()" or removed by "cancel()"
- */
-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 = NULL;
-	struct page_cgroup *pc;
-	int ret;
-
-	pc = lookup_page_cgroup(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 (PageCgroupUsed(pc))
-		goto out;
-	if (do_swap_account)
-		memcg = try_get_mem_cgroup_from_page(page);
-	if (!memcg)
-		memcg = get_mem_cgroup_from_mm(mm);
-	ret = mem_cgroup_try_charge(memcg, mask, 1, true);
-	css_put(&memcg->css);
-	if (ret == -EINTR)
-		memcg = root_mem_cgroup;
-	else if (ret)
-		return ret;
-out:
-	*memcgp = memcg;
-	return 0;
-}
-
-int mem_cgroup_try_charge_swapin(struct mm_struct *mm, struct page *page,
-				 gfp_t gfp_mask, struct mem_cgroup **memcgp)
-{
-	if (mem_cgroup_disabled()) {
-		*memcgp = NULL;
-		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)) {
-		struct mem_cgroup *memcg;
-
-		memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
-		if (!memcg)
-			return -ENOMEM;
-		*memcgp = memcg;
-		return 0;
-	}
-	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)
-{
-	if (mem_cgroup_disabled())
-		return;
-	if (!memcg)
-		return;
-
-	__mem_cgroup_commit_charge(memcg, page, 1, ctype, true);
-	/*
-	 * Now swap is on-memory. This means this page may be
-	 * counted both as mem and swap....double count.
-	 * Fix it by uncharging from memsw. Basically, this SwapCache is stable
-	 * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page()
-	 * may call delete_from_swap_cache() before reach here.
-	 */
-	if (do_swap_account && PageSwapCache(page)) {
-		swp_entry_t ent = {.val = page_private(page)};
-		mem_cgroup_uncharge_swap(ent);
-	}
-}
-
-void mem_cgroup_commit_charge_swapin(struct page *page,
-				     struct mem_cgroup *memcg)
-{
-	__mem_cgroup_commit_charge_swapin(page, memcg,
-					  MEM_CGROUP_CHARGE_TYPE_ANON);
-}
-
-int mem_cgroup_charge_file(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask)
-{
-	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
-	struct mem_cgroup *memcg;
-	int ret;
-
-	if (mem_cgroup_disabled())
-		return 0;
-	if (PageCompound(page))
-		return 0;
-
-	if (PageSwapCache(page)) { /* shmem */
-		ret = __mem_cgroup_try_charge_swapin(mm, page,
-						     gfp_mask, &memcg);
-		if (ret)
-			return ret;
-		__mem_cgroup_commit_charge_swapin(page, memcg, type);
-		return 0;
-	}
-
-	memcg = mem_cgroup_try_charge_mm(mm, gfp_mask, 1, true);
-	if (!memcg)
-		return -ENOMEM;
-	__mem_cgroup_commit_charge(memcg, page, 1, type, false);
-	return 0;
-}
-
 static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg,
 				   unsigned int nr_pages,
 				   const enum charge_type ctype)
@@ -3993,7 +3713,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype,
 	 * 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))
+	if (!end_migration)
 		mem_cgroup_do_uncharge(memcg, nr_pages, ctype);
 
 	return memcg;
@@ -4126,8 +3846,7 @@ void mem_cgroup_uncharge_swap(swp_entry_t ent)
 		 * We uncharge this because swap is freed.  This memcg can
 		 * be obsolete one. We avoid calling css_tryget_online().
 		 */
-		if (!mem_cgroup_is_root(memcg))
-			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 		mem_cgroup_swap_statistics(memcg, false);
 		css_put(&memcg->css);
 	}
@@ -4193,7 +3912,6 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 	struct mem_cgroup *memcg = NULL;
 	unsigned int nr_pages = 1;
 	struct page_cgroup *pc;
-	enum charge_type ctype;
 
 	*memcgp = NULL;
 
@@ -4255,16 +3973,12 @@ void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 	 * page. In the case new page is migrated but not remapped, new page's
 	 * mapcount will be finally 0 and we call uncharge in end_migration().
 	 */
-	if (PageAnon(page))
-		ctype = MEM_CGROUP_CHARGE_TYPE_ANON;
-	else
-		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, nr_pages, ctype, false);
+	commit_charge(newpage, memcg, nr_pages, PageAnon(page), false);
 }
 
 /* remove redundant charge if migration failed*/
@@ -4323,7 +4037,6 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 {
 	struct mem_cgroup *memcg = NULL;
 	struct page_cgroup *pc;
-	enum charge_type type = MEM_CGROUP_CHARGE_TYPE_CACHE;
 
 	if (mem_cgroup_disabled())
 		return;
@@ -4349,7 +4062,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage,
 	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
 	 * LRU while we overwrite pc->mem_cgroup.
 	 */
-	__mem_cgroup_commit_charge(memcg, newpage, 1, type, true);
+	commit_charge(newpage, memcg, 1, false, true);
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -4817,78 +4530,24 @@ out:
 	return retval;
 }
 
-
-static unsigned long mem_cgroup_recursive_stat(struct mem_cgroup *memcg,
-					       enum mem_cgroup_stat_index idx)
-{
-	struct mem_cgroup *iter;
-	long val = 0;
-
-	/* Per-cpu values can be negative, use a signed accumulator */
-	for_each_mem_cgroup_tree(iter, memcg)
-		val += mem_cgroup_read_stat(iter, idx);
-
-	if (val < 0) /* race ? */
-		val = 0;
-	return val;
-}
-
-static inline u64 mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
-{
-	u64 val;
-
-	if (!mem_cgroup_is_root(memcg)) {
-		if (!swap)
-			return res_counter_read_u64(&memcg->res, RES_USAGE);
-		else
-			return res_counter_read_u64(&memcg->memsw, RES_USAGE);
-	}
-
-	/*
-	 * Transparent hugepages are still accounted for in MEM_CGROUP_STAT_RSS
-	 * as well as in MEM_CGROUP_STAT_RSS_HUGE.
-	 */
-	val = mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_CACHE);
-	val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_RSS);
-
-	if (swap)
-		val += mem_cgroup_recursive_stat(memcg, MEM_CGROUP_STAT_SWAP);
-
-	return val << PAGE_SHIFT;
-}
-
 static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css,
-				   struct cftype *cft)
+			       struct cftype *cft)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
-	u64 val;
-	int name;
-	enum res_type type;
-
-	type = MEMFILE_TYPE(cft->private);
-	name = MEMFILE_ATTR(cft->private);
+	enum res_type type = MEMFILE_TYPE(cft->private);
+	int name = MEMFILE_ATTR(cft->private);
 
 	switch (type) {
 	case _MEM:
-		if (name == RES_USAGE)
-			val = mem_cgroup_usage(memcg, false);
-		else
-			val = res_counter_read_u64(&memcg->res, name);
-		break;
+		return res_counter_read_u64(&memcg->res, name);
 	case _MEMSWAP:
-		if (name == RES_USAGE)
-			val = mem_cgroup_usage(memcg, true);
-		else
-			val = res_counter_read_u64(&memcg->memsw, name);
-		break;
+		return res_counter_read_u64(&memcg->memsw, name);
 	case _KMEM:
-		val = res_counter_read_u64(&memcg->kmem, name);
+		return res_counter_read_u64(&memcg->kmem, name);
 		break;
 	default:
 		BUG();
 	}
-
-	return val;
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -5350,7 +5009,10 @@ static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
 	if (!t)
 		goto unlock;
 
-	usage = mem_cgroup_usage(memcg, swap);
+	if (!swap)
+		usage = res_counter_read_u64(&memcg->res, RES_USAGE);
+	else
+		usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 
 	/*
 	 * current_threshold points to threshold just below or equal to usage.
@@ -5446,15 +5108,15 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg,
 
 	mutex_lock(&memcg->thresholds_lock);
 
-	if (type == _MEM)
+	if (type == _MEM) {
 		thresholds = &memcg->thresholds;
-	else if (type == _MEMSWAP)
+		usage = res_counter_read_u64(&memcg->res, RES_USAGE);
+	} else if (type == _MEMSWAP) {
 		thresholds = &memcg->memsw_thresholds;
-	else
+		usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+	} else
 		BUG();
 
-	usage = mem_cgroup_usage(memcg, type == _MEMSWAP);
-
 	/* Check if a threshold crossed before adding a new one */
 	if (thresholds->primary)
 		__mem_cgroup_threshold(memcg, type == _MEMSWAP);
@@ -5534,18 +5196,19 @@ static void __mem_cgroup_usage_unregister_event(struct mem_cgroup *memcg,
 	int i, j, size;
 
 	mutex_lock(&memcg->thresholds_lock);
-	if (type == _MEM)
+
+	if (type == _MEM) {
 		thresholds = &memcg->thresholds;
-	else if (type == _MEMSWAP)
+		usage = res_counter_read_u64(&memcg->res, RES_USAGE);
+	} else if (type == _MEMSWAP) {
 		thresholds = &memcg->memsw_thresholds;
-	else
+		usage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+	} else
 		BUG();
 
 	if (!thresholds->primary)
 		goto unlock;
 
-	usage = mem_cgroup_usage(memcg, type == _MEMSWAP);
-
 	/* Check if a threshold crossed before removing */
 	__mem_cgroup_threshold(memcg, type == _MEMSWAP);
 
@@ -6299,9 +5962,9 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css)
 		 * core guarantees its existence.
 		 */
 	} else {
-		res_counter_init(&memcg->res, NULL);
-		res_counter_init(&memcg->memsw, NULL);
-		res_counter_init(&memcg->kmem, NULL);
+		res_counter_init(&memcg->res, &root_mem_cgroup->res);
+		res_counter_init(&memcg->memsw, &root_mem_cgroup->memsw);
+		res_counter_init(&memcg->kmem, &root_mem_cgroup->kmem);
 		/*
 		 * Deeper hierachy with use_hierarchy == false doesn't make
 		 * much sense so let cgroup subsystem know about this
@@ -6435,55 +6098,38 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css)
 
 #ifdef CONFIG_MMU
 /* Handlers for move charge at task migration. */
-#define PRECHARGE_COUNT_AT_ONCE	256
 static int mem_cgroup_do_precharge(unsigned long count)
 {
-	int ret = 0;
-	int batch_count = PRECHARGE_COUNT_AT_ONCE;
-	struct mem_cgroup *memcg = mc.to;
+	int ret;
 
-	if (mem_cgroup_is_root(memcg)) {
+	/* Try a single bulk charge without reclaim first */
+	ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_WAIT, count);
+	if (!ret) {
 		mc.precharge += count;
-		/* we don't need css_get for root */
 		return ret;
 	}
-	/* try to charge at once */
-	if (count > 1) {
-		struct res_counter *dummy;
-		/*
-		 * "memcg" cannot be under rmdir() because we've already checked
-		 * by cgroup_lock_live_cgroup() that it is not removed and we
-		 * are still under the same cgroup_mutex. So we can postpone
-		 * css_get().
-		 */
-		if (res_counter_charge(&memcg->res, PAGE_SIZE * count, &dummy))
-			goto one_by_one;
-		if (do_swap_account && res_counter_charge(&memcg->memsw,
-						PAGE_SIZE * count, &dummy)) {
-			res_counter_uncharge(&memcg->res, PAGE_SIZE * count);
-			goto one_by_one;
-		}
-		mc.precharge += count;
+	if (ret == -EINTR) {
+		cancel_charge(root_mem_cgroup, count);
 		return ret;
 	}
-one_by_one:
-	/* fall back to one by one charge */
+
+	/* Try charges one by one with reclaim */
 	while (count--) {
-		if (signal_pending(current)) {
-			ret = -EINTR;
-			break;
-		}
-		if (!batch_count--) {
-			batch_count = PRECHARGE_COUNT_AT_ONCE;
-			cond_resched();
-		}
-		ret = mem_cgroup_try_charge(memcg, GFP_KERNEL, 1, false);
+		ret = try_charge(mc.to, GFP_KERNEL & ~__GFP_NORETRY, 1);
+		/*
+		 * In case of failure, any residual charges against
+		 * mc.to will be dropped by mem_cgroup_clear_mc()
+		 * later on.  However, cancel any charges that are
+		 * bypassed to root right away or they'll be lost.
+		 */
+		if (ret == -EINTR)
+			cancel_charge(root_mem_cgroup, 1);
 		if (ret)
-			/* mem_cgroup_clear_mc() will do uncharge later */
 			return ret;
 		mc.precharge++;
+		cond_resched();
 	}
-	return ret;
+	return 0;
 }
 
 /**
@@ -6746,7 +6392,7 @@ static void __mem_cgroup_clear_mc(void)
 
 	/* we must uncharge all the leftover precharges from mc.to */
 	if (mc.precharge) {
-		__mem_cgroup_cancel_charge(mc.to, mc.precharge);
+		cancel_charge(mc.to, mc.precharge);
 		mc.precharge = 0;
 	}
 	/*
@@ -6754,27 +6400,24 @@ static void __mem_cgroup_clear_mc(void)
 	 * we must uncharge here.
 	 */
 	if (mc.moved_charge) {
-		__mem_cgroup_cancel_charge(mc.from, mc.moved_charge);
+		cancel_charge(mc.from, mc.moved_charge);
 		mc.moved_charge = 0;
 	}
 	/* we must fixup refcnts and charges */
 	if (mc.moved_swap) {
 		/* uncharge swap account from the old cgroup */
-		if (!mem_cgroup_is_root(mc.from))
-			res_counter_uncharge(&mc.from->memsw,
-						PAGE_SIZE * mc.moved_swap);
+		res_counter_uncharge(&mc.from->memsw,
+				     PAGE_SIZE * mc.moved_swap);
 
 		for (i = 0; i < mc.moved_swap; i++)
 			css_put(&mc.from->css);
 
-		if (!mem_cgroup_is_root(mc.to)) {
-			/*
-			 * we charged both to->res and to->memsw, so we should
-			 * uncharge to->res.
-			 */
-			res_counter_uncharge(&mc.to->res,
-						PAGE_SIZE * mc.moved_swap);
-		}
+		/*
+		 * we charged both to->res and to->memsw, so we should
+		 * uncharge to->res.
+		 */
+		res_counter_uncharge(&mc.to->res,
+				     PAGE_SIZE * mc.moved_swap);
 		/* we've already done css_get(mc.to) */
 		mc.moved_swap = 0;
 	}
@@ -7086,6 +6729,150 @@ static void __init enable_swap_cgroup(void)
 }
 #endif
 
+/**
+ * mem_cgroup_try_charge - try charging a page
+ * @page: page to charge
+ * @mm: mm context of the victim
+ * @gfp_mask: reclaim mode
+ * @memcgp: charged memcg return
+ *
+ * Try to charge @page to the memcg that @mm belongs to, reclaiming
+ * pages according to @gfp_mask if necessary.
+ *
+ * Returns 0 on success, with *@memcgp pointing to the charged memcg.
+ * Otherwise, an error code is returned.
+ *
+ * After page->mapping has been set up, the caller must finalize the
+ * charge with mem_cgroup_commit_charge().  Or abort the transaction
+ * with mem_cgroup_cancel_charge() in case page instantiation fails.
+ */
+int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp)
+{
+	struct mem_cgroup *memcg = NULL;
+	unsigned int nr_pages = 1;
+	int ret = 0;
+
+	if (mem_cgroup_disabled())
+		goto out;
+
+	if (PageSwapCache(page)) {
+		struct page_cgroup *pc = lookup_page_cgroup(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 (PageCgroupUsed(pc))
+			goto out;
+	}
+
+	if (PageTransHuge(page)) {
+		nr_pages <<= compound_order(page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+	}
+
+	if (do_swap_account && PageSwapCache(page))
+		memcg = try_get_mem_cgroup_from_page(page);
+	if (!memcg)
+		memcg = get_mem_cgroup_from_mm(mm);
+
+	ret = try_charge(memcg, gfp_mask, nr_pages);
+
+	css_put(&memcg->css);
+
+	if (ret == -EINTR) {
+		memcg = root_mem_cgroup;
+		ret = 0;
+	}
+out:
+	*memcgp = memcg;
+	return ret;
+}
+
+/**
+ * mem_cgroup_commit_charge - commit a page charge
+ * @page: page to charge
+ * @memcg: memcg to charge the page to
+ * @lrucare: page might be on LRU already
+ *
+ * Finalize a charge transaction started by mem_cgroup_try_charge(),
+ * after page->mapping has been set up.  This must happen atomically
+ * as part of the page instantiation, i.e. under the page table lock
+ * for anonymous pages, under the page lock for page and swap cache.
+ *
+ * In addition, the page must not be on the LRU during the commit, to
+ * prevent racing with task migration.  If it might be, use @lrucare.
+ *
+ * Use mem_cgroup_cancel_charge() to cancel the transaction instead.
+ */
+void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
+			      bool lrucare)
+{
+	unsigned int nr_pages = 1;
+
+	VM_BUG_ON_PAGE(!page->mapping, page);
+	VM_BUG_ON_PAGE(PageLRU(page) && !lrucare, page);
+
+	if (mem_cgroup_disabled())
+		return;
+	/*
+	 * Swap faults will attempt to charge the same page multiple
+	 * times.  But reuse_swap_page() might have removed the page
+	 * from swapcache already, so we can't check PageSwapCache().
+	 */
+	if (!memcg)
+		return;
+
+	if (PageTransHuge(page)) {
+		nr_pages <<= compound_order(page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+	}
+
+	commit_charge(page, memcg, nr_pages, PageAnon(page), lrucare);
+
+	if (do_swap_account && PageSwapCache(page)) {
+		swp_entry_t entry = { .val = page_private(page) };
+		/*
+		 * The swap entry might not get freed for a long time,
+		 * let's not wait for it.  The page already received a
+		 * memory+swap charge, drop the swap entry duplicate.
+		 */
+		mem_cgroup_uncharge_swap(entry);
+	}
+}
+
+/**
+ * mem_cgroup_cancel_charge - cancel a page charge
+ * @page: page to charge
+ * @memcg: memcg to charge the page to
+ *
+ * Cancel a charge transaction started by mem_cgroup_try_charge().
+ */
+void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
+{
+	unsigned int nr_pages = 1;
+
+	if (mem_cgroup_disabled())
+		return;
+	/*
+	 * Swap faults will attempt to charge the same page multiple
+	 * times.  But reuse_swap_page() might have removed the page
+	 * from swapcache already, so we can't check PageSwapCache().
+	 */
+	if (!memcg)
+		return;
+
+	if (PageTransHuge(page)) {
+		nr_pages <<= compound_order(page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+	}
+
+	cancel_charge(memcg, nr_pages);
+}
+
 /*
  * subsys_initcall() for memory controller.
  *