[Devel,RHEL7,COMMIT] ms/mm: memcontrol: rewrite uncharge API

Submitted by Konstantin Khorenko on Jan. 16, 2017, 4:27 p.m.

Details

Message ID 201701161627.v0GGREq6028894@finist_cl7.x64_64.work.ct
State New
Series "Series without cover letter"
Headers show

Commit Message

Konstantin Khorenko Jan. 16, 2017, 4:27 p.m.
The commit is pushed to "branch-rh7-3.10.0-514.vz7.27.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-514.vz7.27.10
------>
commit 11b315d114183c9bb803b4f622c31b5072110b5e
Author: Johannes Weiner <hannes@cmpxchg.org>
Date:   Mon Jan 16 20:27:14 2017 +0400

    ms/mm: memcontrol: rewrite uncharge API
    
    The memcg uncharging code that is involved towards the end of a page's
    lifetime - truncation, reclaim, swapout, migration - is impressively
    complicated and fragile.
    
    Because anonymous and file pages were always charged before they had their
    page->mapping established, uncharges had to happen when the page type
    could still be known from the context; as in unmap for anonymous, page
    cache removal for file and shmem pages, and swap cache truncation for swap
    pages.  However, these operations happen well before the page is actually
    freed, and so a lot of synchronization is necessary:
    
    - Charging, uncharging, page migration, and charge migration all need
      to take a per-page bit spinlock as they could race with uncharging.
    
    - Swap cache truncation happens during both swap-in and swap-out, and
      possibly repeatedly before the page is actually freed.  This means
      that the memcg swapout code is called from many contexts that make
      no sense and it has to figure out the direction from page state to
      make sure memory and memory+swap are always correctly charged.
    
    - On page migration, the old page might be unmapped but then reused,
      so memcg code has to prevent untimely uncharging in that case.
      Because this code - which should be a simple charge transfer - is so
      special-cased, it is not reusable for replace_page_cache().
    
    But now that charged pages always have a page->mapping, introduce
    mem_cgroup_uncharge(), which is called after the final put_page(), when we
    know for sure that nobody is looking at the page anymore.
    
    For page migration, introduce mem_cgroup_migrate(), which is called after
    the migration is successful and the new page is fully rmapped.  Because
    the old page is no longer uncharged after migration, prevent double
    charges by decoupling the page's memcg association (PCG_USED and
    pc->mem_cgroup) from the page holding an actual charge.  The new bits
    PCG_MEM and PCG_MEMSW represent the respective charges and are transferred
    to the new page during migration.
    
    mem_cgroup_migrate() is suitable for replace_page_cache() as well,
    which gets rid of mem_cgroup_replace_page_cache().  However, care
    needs to be taken because both the source and the target page can
    already be charged and on the LRU when fuse is splicing: grab the page
    lock on the charge moving side to prevent changing pc->mem_cgroup of a
    page under migration.  Also, the lruvecs of both pages change as we
    uncharge the old and charge the new during migration, and putback may
    race with us, so grab the lru lock and isolate the pages iff on LRU to
    prevent races and ensure the pages are on the right lruvec afterward.
    
    Swap accounting is massively simplified: because the page is no longer
    uncharged as early as swap cache deletion, a new mem_cgroup_swapout() can
    transfer the page's memory+swap charge (PCG_MEMSW) to the swap entry
    before the final put_page() in page reclaim.
    
    Finally, page_cgroup changes are now protected by whatever protection the
    page itself offers: anonymous pages are charged under the page table lock,
    whereas page cache insertions, swapin, and migration hold the page lock.
    Uncharging happens under full exclusion with no outstanding references.
    Charging and uncharging also ensure that the page is off-LRU, which
    serializes against charge migration.  Remove the very costly page_cgroup
    lock and set pc->flags non-atomically.
    
    [mhocko@suse.cz: mem_cgroup_charge_statistics needs preempt_disable]
    [vdavydov@parallels.com: fix flags definition]
    Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
    Cc: Hugh Dickins <hughd@google.com>
    Cc: Tejun Heo <tj@kernel.org>
    Cc: Vladimir Davydov <vdavydov@parallels.com>
    Tested-by: Jet Chen <jet.chen@intel.com>
    Acked-by: Michal Hocko <mhocko@suse.cz>
    Tested-by: Felipe Balbi <balbi@ti.com>
    Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
    
    Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
    Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
    
    https://jira.sw.ru/browse/PSBM-51558
    (cherry picked from commit 0a31bc97c80c3fa87b32c091d9a930ac19cd0c40)
    Signed-off-by: Andrey Ryabinin <aryabinin@virtuozzo.com>
---
 Documentation/cgroups/memcg_test.txt | 128 +-----
 drivers/staging/zcache/zcache-main.c |   2 +-
 include/linux/memcontrol.h           |  49 +-
 include/linux/page_cgroup.h          |  43 +-
 include/linux/swap.h                 |  12 +-
 mm/filemap.c                         |   4 +-
 mm/hmm_migrate.c                     |  12 -
 mm/memcontrol.c                      | 850 ++++++++++++++---------------------
 mm/memory.c                          |   2 -
 mm/migrate.c                         |  39 +-
 mm/rmap.c                            |   1 -
 mm/shmem.c                           |   8 +-
 mm/swap.c                            |   5 +
 mm/swap_state.c                      |   8 +-
 mm/swapfile.c                        |   9 +-
 mm/truncate.c                        |   9 -
 mm/tswap.c                           |   2 +-
 mm/vmscan.c                          |  12 +-
 mm/zswap.c                           |   2 +-
 19 files changed, 396 insertions(+), 801 deletions(-)

Patch hide | download patch | download mbox

diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index bcf750d..8870b02 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -29,28 +29,13 @@  Please note that implementation details can be changed.
 2. Uncharge
   a page/swp_entry may be uncharged (usage -= PAGE_SIZE) by
 
-	mem_cgroup_uncharge_page()
-	  Called when an anonymous page is fully unmapped. I.e., mapcount goes
-	  to 0. If the page is SwapCache, uncharge is delayed until
-	  mem_cgroup_uncharge_swapcache().
-
-	mem_cgroup_uncharge_cache_page()
-	  Called when a page-cache is deleted from radix-tree. If the page is
-	  SwapCache, uncharge is delayed until mem_cgroup_uncharge_swapcache().
-
-	mem_cgroup_uncharge_swapcache()
-	  Called when SwapCache is removed from radix-tree. The charge itself
-	  is moved to swap_cgroup. (If mem+swap controller is disabled, no
-	  charge to swap occurs.)
+	mem_cgroup_uncharge()
+	  Called when a page's refcount goes down to 0.
 
 	mem_cgroup_uncharge_swap()
 	  Called when swp_entry's refcnt goes down to 0. A charge against swap
 	  disappears.
 
-	mem_cgroup_end_migration(old, new)
-	At success of migration old is uncharged (if necessary), a charge
-	to new page is committed. At failure, charge to old page is committed.
-
 3. charge-commit-cancel
 	Memcg pages are charged in two steps:
 		mem_cgroup_try_charge()
@@ -69,18 +54,6 @@  Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	Anonymous page is newly allocated at
 		  - page fault into MAP_ANONYMOUS mapping.
 		  - Copy-On-Write.
- 	It is charged right after it's allocated before doing any page table
-	related operations. Of course, it's uncharged when another page is used
-	for the fault address.
-
-	At freeing anonymous page (by exit() or munmap()), zap_pte() is called
-	and pages for ptes are freed one by one.(see mm/memory.c). Uncharges
-	are done at page_remove_rmap() when page_mapcount() goes down to 0.
-
-	Another page freeing is by page-reclaim (vmscan.c) and anonymous
-	pages are swapped out. In this case, the page is marked as
-	PageSwapCache(). uncharge() routine doesn't uncharge the page marked
-	as SwapCache(). It's delayed until __delete_from_swap_cache().
 
 	4.1 Swap-in.
 	At swap-in, the page is taken from swap-cache. There are 2 cases.
@@ -89,41 +62,6 @@  Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	(b) If the SwapCache has been mapped by processes, it has been
 	    charged already.
 
-	This swap-in is one of the most complicated work. In do_swap_page(),
-	following events occur when pte is unchanged.
-
-	(1) the page (SwapCache) is looked up.
-	(2) lock_page()
-	(3) try_charge_swapin()
-	(4) reuse_swap_page() (may call delete_swap_cache())
-	(5) commit_charge_swapin()
-	(6) swap_free().
-
-	Considering following situation for example.
-
-	(A) The page has not been charged before (2) and reuse_swap_page()
-	    doesn't call delete_from_swap_cache().
-	(B) The page has not been charged before (2) and reuse_swap_page()
-	    calls delete_from_swap_cache().
-	(C) The page has been charged before (2) and reuse_swap_page() doesn't
-	    call delete_from_swap_cache().
-	(D) The page has been charged before (2) and reuse_swap_page() calls
-	    delete_from_swap_cache().
-
-	    memory.usage/memsw.usage changes to this page/swp_entry will be
-	 Case          (A)      (B)       (C)     (D)
-         Event
-       Before (2)     0/ 1     0/ 1      1/ 1    1/ 1
-          ===========================================
-          (3)        +1/+1    +1/+1     +1/+1   +1/+1
-          (4)          -       0/ 0       -     -1/ 0
-          (5)         0/-1     0/ 0     -1/-1    0/ 0
-          (6)          -       0/-1       -      0/-1
-          ===========================================
-       Result         1/ 1     1/ 1      1/ 1    1/ 1
-
-       In any cases, charges to this page should be 1/ 1.
-
 	4.2 Swap-out.
 	At swap-out, typical state transition is below.
 
@@ -136,28 +74,20 @@  Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	    swp_entry's refcnt -= 1.
 
 
-	At (b), the page is marked as SwapCache and not uncharged.
-	At (d), the page is removed from SwapCache and a charge in page_cgroup
-	is moved to swap_cgroup.
-
 	Finally, at task exit,
 	(e) zap_pte() is called and swp_entry's refcnt -=1 -> 0.
-	Here, a charge in swap_cgroup disappears.
 
 5. Page Cache
    	Page Cache is charged at
 	- add_to_page_cache_locked().
 
-	uncharged at
-	- __remove_from_page_cache().
-
 	The logic is very clear. (About migration, see below)
 	Note: __remove_from_page_cache() is called by remove_from_page_cache()
 	and __remove_mapping().
 
 6. Shmem(tmpfs) Page Cache
-	Memcg's charge/uncharge have special handlers of shmem. The best way
-	to understand shmem's page state transition is to read mm/shmem.c.
+	The best way to understand shmem's page state transition is to read
+	mm/shmem.c.
 	But brief explanation of the behavior of memcg around shmem will be
 	helpful to understand the logic.
 
@@ -170,56 +100,10 @@  Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	It's charged when...
 	- A new page is added to shmem's radix-tree.
 	- A swp page is read. (move a charge from swap_cgroup to page_cgroup)
-	It's uncharged when
-	- A page is removed from radix-tree and not SwapCache.
-	- When SwapCache is removed, a charge is moved to swap_cgroup.
-	- When swp_entry's refcnt goes down to 0, a charge in swap_cgroup
-	  disappears.
 
 7. Page Migration
-   	One of the most complicated functions is page-migration-handler.
-	Memcg has 2 routines. Assume that we are migrating a page's contents
-	from OLDPAGE to NEWPAGE.
-
-	Usual migration logic is..
-	(a) remove the page from LRU.
-	(b) allocate NEWPAGE (migration target)
-	(c) lock by lock_page().
-	(d) unmap all mappings.
-	(e-1) If necessary, replace entry in radix-tree.
-	(e-2) move contents of a page.
-	(f) map all mappings again.
-	(g) pushback the page to LRU.
-	(-) OLDPAGE will be freed.
-
-	Before (g), memcg should complete all necessary charge/uncharge to
-	NEWPAGE/OLDPAGE.
-
-	The point is....
-	- If OLDPAGE is anonymous, all charges will be dropped at (d) because
-          try_to_unmap() drops all mapcount and the page will not be
-	  SwapCache.
-
-	- If OLDPAGE is SwapCache, charges will be kept at (g) because
-	  __delete_from_swap_cache() isn't called at (e-1)
-
-	- If OLDPAGE is page-cache, charges will be kept at (g) because
-	  remove_from_swap_cache() isn't called at (e-1)
-
-	memcg provides following hooks.
-
-	- mem_cgroup_prepare_migration(OLDPAGE)
-	  Called after (b) to account a charge (usage += PAGE_SIZE) against
-	  memcg which OLDPAGE belongs to.
-
-        - mem_cgroup_end_migration(OLDPAGE, NEWPAGE)
-	  Called after (f) before (g).
-	  If OLDPAGE is used, commit OLDPAGE again. If OLDPAGE is already
-	  charged, a charge by prepare_migration() is automatically canceled.
-	  If NEWPAGE is used, commit NEWPAGE and uncharge OLDPAGE.
-
-	  But zap_pte() (by exit or munmap) can be called while migration,
-	  we have to check if OLDPAGE/NEWPAGE is a valid page after commit().
+
+	mem_cgroup_migrate()
 
 8. LRU
         Each memcg has its own private LRU. Now, its handling is under global
diff --git a/drivers/staging/zcache/zcache-main.c b/drivers/staging/zcache/zcache-main.c
index 81972fa..3fe94dd 100644
--- a/drivers/staging/zcache/zcache-main.c
+++ b/drivers/staging/zcache/zcache-main.c
@@ -961,7 +961,7 @@  static int zcache_get_swap_cache_page(int type, pgoff_t offset,
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
 		 */
-		swapcache_free(entry, NULL);
+		swapcache_free(entry);
 		/* FIXME: is it possible to get here without err==-ENOMEM?
 		 * If not, we can dispense with the do loop, use goto retry */
 	} while (err != -ENOMEM);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 54d4aa0..ca343bf 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -52,15 +52,17 @@  void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 			      bool lrucare);
 void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg);
 
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
+void mem_cgroup_uncharge(struct page *page);
+
+/* Batched uncharging */
+void mem_cgroup_uncharge_start(void);
+void mem_cgroup_uncharge_end(void);
 
-/* For coalescing uncharge for reducing memcg' overhead*/
-extern void mem_cgroup_uncharge_start(void);
-extern void mem_cgroup_uncharge_end(void);
+void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
+			bool lrucare);
 
-extern void mem_cgroup_uncharge_page(struct page *page);
-extern void mem_cgroup_uncharge_cache_page(struct page *page);
+struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
+struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
 
 bool __mem_cgroup_same_or_subtree(const struct mem_cgroup *root_memcg,
 				  struct mem_cgroup *memcg);
@@ -90,12 +92,6 @@  extern struct cgroup_subsys_state *mem_cgroup_css(struct mem_cgroup *memcg);
 
 unsigned long page_cgroup_ino(struct page *page);
 
-extern void
-mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-			     struct mem_cgroup **memcgp);
-extern void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-	struct page *oldpage, struct page *newpage, bool migration_ok);
-
 struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,
 				   struct mem_cgroup_reclaim_cookie *);
@@ -117,8 +113,6 @@  extern void mem_cgroup_note_oom_kill(struct mem_cgroup *memcg,
 				     struct task_struct *task);
 extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
 					struct task_struct *p);
-extern void mem_cgroup_replace_page_cache(struct page *oldpage,
-					struct page *newpage);
 
 static inline void mem_cgroup_oom_enable(void)
 {
@@ -246,19 +240,21 @@  static inline void mem_cgroup_cancel_charge(struct page *page,
 {
 }
 
-static inline void mem_cgroup_uncharge_start(void)
+static inline void mem_cgroup_uncharge(struct page *page)
 {
 }
 
-static inline void mem_cgroup_uncharge_end(void)
+static inline void mem_cgroup_uncharge_start(void)
 {
 }
 
-static inline void mem_cgroup_uncharge_page(struct page *page)
+static inline void mem_cgroup_uncharge_end(void)
 {
 }
 
-static inline void mem_cgroup_uncharge_cache_page(struct page *page)
+static inline void mem_cgroup_migrate(struct page *oldpage,
+				      struct page *newpage,
+				      bool lrucare)
 {
 }
 
@@ -302,17 +298,6 @@  static inline struct cgroup_subsys_state
 	return NULL;
 }
 
-static inline void
-mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-			     struct mem_cgroup **memcgp)
-{
-}
-
-static inline void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-		struct page *oldpage, struct page *newpage, bool migration_ok)
-{
-}
-
 static inline struct mem_cgroup *
 mem_cgroup_iter(struct mem_cgroup *root,
 		struct mem_cgroup *prev,
@@ -448,10 +433,6 @@  static inline
 void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
-static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
-				struct page *newpage)
-{
-}
 #endif /* CONFIG_MEMCG */
 
 #if !defined(CONFIG_MEMCG) || !defined(CONFIG_DEBUG_VM)
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 777a524..9bfb8e6 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -3,9 +3,9 @@ 
 
 enum {
 	/* flags for mem_cgroup */
-	PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
-	PCG_USED, /* this object is in use. */
-	PCG_MIGRATION, /* under page migration */
+	PCG_USED = 0x01,	/* This page is charged to a memcg */
+	PCG_MEM = 0x02,		/* This page holds a memory charge */
+	PCG_MEMSW = 0x04,	/* This page holds a memory+swap charge */
 	__NR_PCG_FLAGS,
 };
 
@@ -44,42 +44,9 @@  static inline void __init page_cgroup_init(void)
 struct page_cgroup *lookup_page_cgroup(struct page *page);
 struct page *lookup_cgroup_page(struct page_cgroup *pc);
 
-#define TESTPCGFLAG(uname, lname)			\
-static inline int PageCgroup##uname(struct page_cgroup *pc)	\
-	{ return test_bit(PCG_##lname, &pc->flags); }
-
-#define SETPCGFLAG(uname, lname)			\
-static inline void SetPageCgroup##uname(struct page_cgroup *pc)\
-	{ set_bit(PCG_##lname, &pc->flags);  }
-
-#define CLEARPCGFLAG(uname, lname)			\
-static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
-	{ clear_bit(PCG_##lname, &pc->flags);  }
-
-#define TESTCLEARPCGFLAG(uname, lname)			\
-static inline int TestClearPageCgroup##uname(struct page_cgroup *pc)	\
-	{ return test_and_clear_bit(PCG_##lname, &pc->flags);  }
-
-TESTPCGFLAG(Used, USED)
-CLEARPCGFLAG(Used, USED)
-SETPCGFLAG(Used, USED)
-
-SETPCGFLAG(Migration, MIGRATION)
-CLEARPCGFLAG(Migration, MIGRATION)
-TESTPCGFLAG(Migration, MIGRATION)
-
-static inline void lock_page_cgroup(struct page_cgroup *pc)
-{
-	/*
-	 * Don't take this lock in IRQ context.
-	 * This lock is for pc->mem_cgroup, USED, MIGRATION
-	 */
-	bit_spin_lock(PCG_LOCK, &pc->flags);
-}
-
-static inline void unlock_page_cgroup(struct page_cgroup *pc)
+static inline int PageCgroupUsed(struct page_cgroup *pc)
 {
-	bit_spin_unlock(PCG_LOCK, &pc->flags);
+	return !!(pc->flags & PCG_USED);
 }
 
 #else /* CONFIG_MEMCG */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 9a61e51..bd162f9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -365,9 +365,13 @@  static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 #ifdef CONFIG_MEMCG_SWAP
-extern void mem_cgroup_uncharge_swap(swp_entry_t ent);
+extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
+extern void mem_cgroup_uncharge_swap(swp_entry_t entry);
 #else
-static inline void mem_cgroup_uncharge_swap(swp_entry_t ent)
+static inline void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
+{
+}
+static inline void mem_cgroup_uncharge_swap(swp_entry_t entry)
 {
 }
 #endif
@@ -427,7 +431,7 @@  extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);
 extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
-extern void swapcache_free(swp_entry_t, struct page *page);
+extern void swapcache_free(swp_entry_t);
 extern int free_swap_and_cache(swp_entry_t);
 extern int swap_type_of(dev_t, sector_t, struct block_device **);
 extern unsigned int count_swap_pages(int, int);
@@ -490,7 +494,7 @@  static inline void swap_free(swp_entry_t swp)
 {
 }
 
-static inline void swapcache_free(swp_entry_t swp, struct page *page)
+static inline void swapcache_free(swp_entry_t swp)
 {
 }
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 26f6fd6..16517c6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -248,7 +248,6 @@  void delete_from_page_cache(struct page *page)
 	spin_lock_irq(&mapping->tree_lock);
 	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
-	mem_cgroup_uncharge_cache_page(page);
 
 	if (freepage)
 		freepage(page);
@@ -504,8 +503,7 @@  int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
 		if (PageSwapBacked(new))
 			__inc_zone_page_state(new, NR_SHMEM);
 		spin_unlock_irq(&mapping->tree_lock);
-		/* mem_cgroup codes must not be called under tree_lock */
-		mem_cgroup_replace_page_cache(old, new);
+		mem_cgroup_migrate(old, new, true);
 		radix_tree_preload_end();
 		if (freepage)
 			freepage(old);
diff --git a/mm/hmm_migrate.c b/mm/hmm_migrate.c
index f08d1fe..b614d34 100644
--- a/mm/hmm_migrate.c
+++ b/mm/hmm_migrate.c
@@ -347,7 +347,6 @@  static int hmm_migrate_check(struct vm_area_struct *vma,
 
 	do {
 		struct page *spage, *dpage;
-		struct mem_cgroup *memcg;
 		pte_t pte = *ptep;
 		swp_entry_t swap;
 
@@ -403,8 +402,6 @@  static int hmm_migrate_check(struct vm_area_struct *vma,
 		if (PageSwapBacked(spage))
 			SetPageSwapBacked(dpage);
 
-		mem_cgroup_prepare_migration(spage, dpage, &memcg);
-		dpage->mapping = (void *)memcg;
 		*gtep = hmm_entry_set_memcg(*gtep);
 	} while (ptep++, gtep++, addr += PAGE_SIZE, addr != end);
 
@@ -530,15 +527,6 @@  static int hmm_migrate_cleanup(struct vm_area_struct *vma,
 		VM_BUG_ON(!spage);
 
 		dpage = hmm_entry_to_page(*gtep);
-		if (hmm_entry_is_memcg(*gtep)) {
-			struct mem_cgroup *memcg;
-
-			memcg = (struct mem_cgroup *)dpage->mapping;
-			dpage->mapping = NULL;
-			mem_cgroup_end_migration(memcg, spage, dpage,
-					         hmm_entry_is_migrate(*gtep));
-		}
-
 		if (hmm_entry_is_migrate(*gtep)) {
 			VM_BUG_ON(!spage);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 50f440c..1eb0e85 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -731,10 +731,8 @@  ino_t page_cgroup_ino(struct page *page)
 	pc = lookup_page_cgroup(page);
 	if (!PageCgroupUsed(pc))
 		return 0;
-	lock_page_cgroup(pc);
 	if (likely(PageCgroupUsed(pc)))
 		ino = pc->mem_cgroup->css.cgroup->dentry->d_inode->i_ino;
-	unlock_page_cgroup(pc);
 	return ino;
 }
 
@@ -812,9 +810,11 @@  mem_cgroup_remove_exceeded(struct mem_cgroup *memcg,
 				struct mem_cgroup_per_zone *mz,
 				struct mem_cgroup_tree_per_zone *mctz)
 {
-	spin_lock(&mctz->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&mctz->lock, flags);
 	__mem_cgroup_remove_exceeded(memcg, mz, mctz);
-	spin_unlock(&mctz->lock);
+	spin_unlock_irqrestore(&mctz->lock, flags);
 }
 
 static unsigned long soft_limit_excess(struct mem_cgroup *memcg)
@@ -850,7 +850,9 @@  static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 		 * mem is over its softlimit.
 		 */
 		if (excess || mz->on_tree) {
-			spin_lock(&mctz->lock);
+			unsigned long flags;
+
+			spin_lock_irqsave(&mctz->lock, flags);
 			/* if on-tree, remove it */
 			if (mz->on_tree)
 				__mem_cgroup_remove_exceeded(memcg, mz, mctz);
@@ -859,7 +861,7 @@  static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page)
 			 * If excess is 0, no tree ops.
 			 */
 			__mem_cgroup_insert_exceeded(memcg, mz, mctz, excess);
-			spin_unlock(&mctz->lock);
+			spin_unlock_irqrestore(&mctz->lock, flags);
 		}
 	}
 }
@@ -910,9 +912,9 @@  mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
 {
 	struct mem_cgroup_per_zone *mz;
 
-	spin_lock(&mctz->lock);
+	spin_lock_irq(&mctz->lock);
 	mz = __mem_cgroup_largest_soft_limit_node(mctz);
-	spin_unlock(&mctz->lock);
+	spin_unlock_irq(&mctz->lock);
 	return mz;
 }
 
@@ -946,13 +948,6 @@  static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
 	return val;
 }
 
-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_SWAP], val);
-}
-
 static void mem_cgroup_update_swap_max(struct mem_cgroup *memcg)
 {
 	long long swap;
@@ -964,11 +959,11 @@  static void mem_cgroup_update_swap_max(struct mem_cgroup *memcg)
 		/* This is racy, but we don't have to be absolutely precise */
 		if (swap > (long long)memcg->swap_max)
 			memcg->swap_max = swap;
-	}
+       }
 }
 
 static void mem_cgroup_inc_failcnt(struct mem_cgroup *memcg,
-				   gfp_t gfp_mask, unsigned int nr_pages)
+                                  gfp_t gfp_mask, unsigned int nr_pages)
 {
 	unsigned long margin = 0;
 	unsigned long count;
@@ -1000,7 +995,7 @@  static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg,
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 					 struct page *page,
-					 bool anon, int nr_pages)
+					 int nr_pages)
 {
 	preempt_disable();
 
@@ -1008,7 +1003,7 @@  static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
 	 * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is
 	 * counted as CACHE even if it's on ANON LRU.
 	 */
-	if (anon)
+	if (PageAnon(page))
 		__this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS],
 				nr_pages);
 	else {
@@ -1121,7 +1116,6 @@  static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
  */
 static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 {
-	preempt_disable();
 	/* threshold event is triggered in finer grain than soft limit */
 	if (unlikely(mem_cgroup_event_ratelimit(memcg,
 						MEM_CGROUP_TARGET_THRESH))) {
@@ -1134,8 +1128,6 @@  static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 		do_numainfo = mem_cgroup_event_ratelimit(memcg,
 						MEM_CGROUP_TARGET_NUMAINFO);
 #endif
-		preempt_enable();
-
 		mem_cgroup_threshold(memcg);
 		if (unlikely(do_softlimit))
 			mem_cgroup_update_tree(memcg, page);
@@ -1143,8 +1135,7 @@  static void memcg_check_events(struct mem_cgroup *memcg, struct page *page)
 		if (unlikely(do_numainfo))
 			atomic_inc(&memcg->numainfo_events);
 #endif
-	} else
-		preempt_enable();
+	}
 }
 
 struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
@@ -1439,20 +1430,6 @@  out:
 	return lruvec;
 }
 
-/*
- * Following LRU functions are allowed to be used without PCG_LOCK.
- * Operations are called by routine of global LRU independently from memcg.
- * What we have to take care of here is validness of pc->mem_cgroup.
- *
- * Changes to pc->mem_cgroup happens when
- * 1. charge
- * 2. moving account
- * In typical case, "charge" is done before add-to-lru. Exception is SwapCache.
- * It is added to LRU before charge.
- * If PCG_USED bit is not set, page_cgroup is not added to this private LRU.
- * When moving account, the page is not on LRU. It's isolated.
- */
-
 /**
  * mem_cgroup_page_lruvec - return lruvec for adding an lru page
  * @page: the page
@@ -1681,10 +1658,8 @@  bool mem_cgroup_cleancache_disabled(struct page *page)
 	if (!PageCgroupUsed(pc))
 		return false;
 
-	lock_page_cgroup(pc);
 	if (likely(PageCgroupUsed(pc)))
 		ret = pc->mem_cgroup->cleancache_disabled;
-	unlock_page_cgroup(pc);
 	return ret;
 }
 #endif
@@ -2479,22 +2454,14 @@  cleanup:
  *
  * Notes: Race condition
  *
- * We usually use page_cgroup_lock() for accessing page_cgroup member but
- * it tends to be costly. But considering some conditions, we doesn't need
- * to do so _always_.
+ * Charging occurs during page instantiation, while the page is
+ * unmapped and locked in page migration, or while the page table is
+ * locked in THP migration.  No race is possible.
  *
- * Considering "charge", lock_page_cgroup() is not required because all
- * file-stat operations happen after a page is attached to radix-tree. There
- * are no race with "charge".
+ * Uncharge happens to pages with zero references, no race possible.
  *
- * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup
- * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even
- * if there are race with "uncharge". Statistics itself is properly handled
- * by flags.
- *
- * Considering "move", this is an only case we see a race. To make the race
- * small, we check mm->moving_account and detect there are possibility of race
- * If there is, we take a lock.
+ * Charge moving between groups is protected by checking mm->moving
+ * account and taking the move_lock in the slowpath.
  */
 
 void __mem_cgroup_begin_update_page_stat(struct page *page,
@@ -2881,6 +2848,16 @@  static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
 	return mem_cgroup_from_css(css);
 }
 
+/*
+ * try_get_mem_cgroup_from_page - look up page's memcg association
+ * @page: the page
+ *
+ * Look up, get a css reference, and return the memcg that owns @page.
+ *
+ * The page must be locked to prevent racing with swap-in and page
+ * cache charges.  If coming from an unlocked page table, the caller
+ * must ensure the page is on the LRU or this can race with charging.
+ */
 struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 {
 	struct mem_cgroup *memcg = NULL;
@@ -2891,7 +2868,6 @@  struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 
 	pc = lookup_page_cgroup(page);
-	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
 		memcg = pc->mem_cgroup;
 		if (memcg && !css_tryget(&memcg->css))
@@ -2905,19 +2881,46 @@  struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 			memcg = NULL;
 		rcu_read_unlock();
 	}
-	unlock_page_cgroup(pc);
 	return memcg;
 }
 
+static void lock_page_lru(struct page *page, int *isolated)
+{
+	struct zone *zone = page_zone(page);
+
+	spin_lock_irq(&zone->lru_lock);
+	if (PageLRU(page)) {
+		struct lruvec *lruvec;
+
+		lruvec = mem_cgroup_page_lruvec(page, zone);
+		ClearPageLRU(page);
+		del_page_from_lru_list(page, lruvec, page_lru(page));
+		*isolated = 1;
+	} else
+		*isolated = 0;
+}
+
+static void unlock_page_lru(struct page *page, int isolated)
+{
+	struct zone *zone = page_zone(page);
+
+	if (isolated) {
+		struct lruvec *lruvec;
+
+		lruvec = mem_cgroup_page_lruvec(page, zone);
+		VM_BUG_ON_PAGE(PageLRU(page), page);
+		SetPageLRU(page);
+		add_page_to_lru_list(page, lruvec, page_lru(page));
+	}
+	spin_unlock_irq(&zone->lru_lock);
+}
+
 static void commit_charge(struct page *page, struct mem_cgroup *memcg,
-			  unsigned int nr_pages, bool anon, bool lrucare)
+			  unsigned int nr_pages, bool lrucare)
 {
 	struct page_cgroup *pc = lookup_page_cgroup(page);
-	struct zone *uninitialized_var(zone);
-	struct lruvec *lruvec;
-	bool was_on_lru = false;
+	int isolated;
 
-	lock_page_cgroup(pc);
 	VM_BUG_ON_PAGE(PageCgroupUsed(pc), page);
 	/*
 	 * we don't need page_cgroup_lock about tail pages, becase they are not
@@ -2928,39 +2931,38 @@  static void commit_charge(struct page *page, struct mem_cgroup *memcg,
 	 * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page
 	 * may already be on some other mem_cgroup's LRU.  Take care of it.
 	 */
-	if (lrucare) {
-		zone = page_zone(page);
-		spin_lock_irq(&zone->lru_lock);
-		if (PageLRU(page)) {
-			lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
-			ClearPageLRU(page);
-			del_page_from_lru_list(page, lruvec, page_lru(page));
-			was_on_lru = true;
-		}
-	}
+	if (lrucare)
+		lock_page_lru(page, &isolated);
 
+	/*
+	 * Nobody should be changing or seriously looking at
+	 * pc->mem_cgroup and pc->flags at this point:
+	 *
+	 * - the page is uncharged
+	 *
+	 * - the page is off-LRU
+	 *
+	 * - an anonymous fault has exclusive page access, except for
+	 *   a locked page table
+	 *
+	 * - a page cache insertion, a swapin fault, or a migration
+	 *   have the page locked
+	 */
 	pc->mem_cgroup = memcg;
-	SetPageCgroupUsed(pc);
-
-	if (lrucare) {
-		if (was_on_lru) {
-			lruvec = mem_cgroup_zone_lruvec(zone, pc->mem_cgroup);
-			VM_BUG_ON_PAGE(PageLRU(page), page);
-			SetPageLRU(page);
-			add_page_to_lru_list(page, lruvec, page_lru(page));
-		}
-		spin_unlock_irq(&zone->lru_lock);
-	}
+	pc->flags = PCG_USED | PCG_MEM | (do_swap_account ? PCG_MEMSW : 0);
 
-	mem_cgroup_charge_statistics(memcg, page, anon, nr_pages);
-	unlock_page_cgroup(pc);
+	if (lrucare)
+		unlock_page_lru(page, isolated);
 
+	local_irq_disable();
+	mem_cgroup_charge_statistics(memcg, page, nr_pages);
 	/*
 	 * "charge_statistics" updated event counter. Then, check it.
 	 * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree.
 	 * if they exceeds softlimit.
 	 */
 	memcg_check_events(memcg, page);
+	local_irq_enable();
 }
 
 #ifdef CONFIG_MEMCG_KMEM
@@ -3381,10 +3383,8 @@  __memcg_kmem_newpage_charge(struct page *page, gfp_t gfp, int order)
 		return false;
 
 	pc = lookup_page_cgroup(page);
-	lock_page_cgroup(pc);
 	pc->mem_cgroup = memcg;
-	SetPageCgroupUsed(pc);
-	unlock_page_cgroup(pc);
+        pc->flags = PCG_USED;
 
 	__SetPageKmemcg(page);
 
@@ -3405,12 +3405,10 @@  void __memcg_kmem_uncharge_pages(struct page *page, int order)
 	if (!PageCgroupUsed(pc))
 		return;
 
-	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
 		memcg = pc->mem_cgroup;
-		ClearPageCgroupUsed(pc);
+		pc->flags = 0;
 	}
-	unlock_page_cgroup(pc);
 
 	/*
 	 * We trust that only if there is a memcg associated with the page, it
@@ -3449,7 +3447,6 @@  struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr)
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
-#define PCGF_NOCOPY_AT_SPLIT (1 << PCG_LOCK | 1 << PCG_MIGRATION)
 /*
  * Because tail pages are not marked as "used", set it. We're under
  * zone->lru_lock, 'splitting on pmd' and compound_lock.
@@ -3470,7 +3467,7 @@  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;
-		pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
+		pc->flags = head_pc->flags;
 	}
 	__this_cpu_sub(memcg->stat->count[MEM_CGROUP_STAT_RSS_HUGE],
 		       HPAGE_PMD_NR);
@@ -3500,7 +3497,6 @@  static int mem_cgroup_move_account(struct page *page,
 {
 	unsigned long flags;
 	int ret;
-	bool anon = PageAnon(page);
 
 	VM_BUG_ON(from == to);
 	VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -3514,35 +3510,47 @@  static int mem_cgroup_move_account(struct page *page,
 	if (nr_pages > 1 && !PageTransHuge(page))
 		goto out;
 
-	lock_page_cgroup(pc);
+	/*
+	 * Prevent mem_cgroup_migrate() from looking at pc->mem_cgroup
+	 * of its source page while we change it: page migration takes
+	 * both pages off the LRU, but page cache replacement doesn't.
+	 */
+	if (!trylock_page(page))
+		goto out;
 
 	ret = -EINVAL;
 	if (!PageCgroupUsed(pc) || pc->mem_cgroup != from)
-		goto unlock;
+		goto out_unlock;
 
 	move_lock_mem_cgroup(from, &flags);
 
-	if (!anon && page_mapped(page)) {
+	if (!PageAnon(page) && page_mapped(page)) {
 		/* Update mapped_file data for mem_cgroup */
 		preempt_disable();
 		__this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		preempt_enable();
 	}
-	mem_cgroup_charge_statistics(from, page, anon, -nr_pages);
+
+	/*
+	 * It is safe to change pc->mem_cgroup here because the page
+	 * is referenced, charged, and isolated - we can't race with
+	 * uncharging, charging, migration, or LRU putback.
+	 */
 
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, page, anon, nr_pages);
 	move_unlock_mem_cgroup(from, &flags);
 	ret = 0;
-unlock:
-	unlock_page_cgroup(pc);
-	/*
-	 * check events
-	 */
+
+	local_irq_disable();
+	mem_cgroup_charge_statistics(to, page, nr_pages);
 	memcg_check_events(to, page);
+	mem_cgroup_charge_statistics(from, page, -nr_pages);
 	memcg_check_events(from, page);
+	local_irq_enable();
+out_unlock:
+	unlock_page(page);
 out:
 	return ret;
 }
@@ -3617,194 +3625,6 @@  out:
 	return ret;
 }
 
-static void mem_cgroup_do_uncharge(struct mem_cgroup *memcg,
-				   unsigned int nr_pages,
-				   const enum charge_type ctype)
-{
-	struct memcg_batch_info *batch = NULL;
-	bool uncharge_memsw = true;
-
-	/* If swapout, usage of swap doesn't decrease */
-	if (!do_swap_account || ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
-		uncharge_memsw = false;
-
-	batch = &current->memcg_batch;
-	/*
-	 * In usual, we do css_get() when we remember memcg pointer.
-	 * But in this case, we keep res->usage until end of a series of
-	 * uncharges. Then, it's ok to ignore memcg's refcnt.
-	 */
-	if (!batch->memcg)
-		batch->memcg = memcg;
-	/*
-	 * do_batch > 0 when unmapping pages or inode invalidate/truncate.
-	 * In those cases, all pages freed continuously can be expected to be in
-	 * the same cgroup and we have chance to coalesce uncharges.
-	 * But we do uncharge one by one if this is killed by OOM(TIF_MEMDIE)
-	 * because we want to do uncharge as soon as possible.
-	 */
-
-	if (!batch->do_batch || test_thread_flag(TIF_MEMDIE))
-		goto direct_uncharge;
-
-	if (nr_pages > 1)
-		goto direct_uncharge;
-
-	/*
-	 * In typical case, batch->memcg == mem. This means we can
-	 * merge a series of uncharges to an uncharge of page_counter.
-	 * If not, we uncharge page_counter ony by one.
-	 */
-	if (batch->memcg != memcg)
-		goto direct_uncharge;
-	/* remember freed charge and uncharge it later */
-	batch->nr_pages++;
-	if (uncharge_memsw)
-		batch->memsw_nr_pages++;
-	return;
-direct_uncharge:
-	page_counter_uncharge(&memcg->memory, nr_pages);
-	if (uncharge_memsw)
-		page_counter_uncharge(&memcg->memsw, nr_pages);
-	if (unlikely(batch->memcg != memcg))
-		memcg_oom_recover(memcg);
-}
-
-/*
- * uncharge if !page_mapped(page)
- */
-static struct mem_cgroup *
-__mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype,
-			     bool end_migration)
-{
-	struct mem_cgroup *memcg = NULL;
-	unsigned int nr_pages = 1;
-	struct page_cgroup *pc;
-	bool anon;
-
-	if (mem_cgroup_disabled())
-		return NULL;
-
-	if (PageTransHuge(page)) {
-		nr_pages <<= compound_order(page);
-		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
-	}
-	/*
-	 * Check if our page_cgroup is valid
-	 */
-	pc = lookup_page_cgroup(page);
-	if (unlikely(!PageCgroupUsed(pc)))
-		return NULL;
-
-	lock_page_cgroup(pc);
-
-	memcg = pc->mem_cgroup;
-
-	if (!PageCgroupUsed(pc))
-		goto unlock_out;
-
-	anon = PageAnon(page);
-
-	switch (ctype) {
-	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
-		 * used before page reached the stage of being marked PageAnon.
-		 */
-		anon = true;
-		/* fallthrough */
-	case MEM_CGROUP_CHARGE_TYPE_DROP:
-		/* See mem_cgroup_prepare_migration() */
-		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
-		 * page_counter handling below.
-		 */
-		if (!end_migration && PageCgroupMigration(pc))
-			goto unlock_out;
-		break;
-	case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
-		if (!PageAnon(page)) {	/* Shared memory */
-			if (page->mapping && !page_is_file_cache(page))
-				goto unlock_out;
-		} else if (page_mapped(page)) /* Anon */
-				goto unlock_out;
-		break;
-	default:
-		break;
-	}
-
-	mem_cgroup_charge_statistics(memcg, page, anon, -nr_pages);
-
-	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.
-	 */
-
-	unlock_page_cgroup(pc);
-	/*
-	 * even after unlock, we have memcg->memory.usage here and this memcg
-	 * will never be freed, so it's safe to call css_get().
-	 */
-	memcg_check_events(memcg, page);
-	if (do_swap_account && ctype == MEM_CGROUP_CHARGE_TYPE_SWAPOUT) {
-		mem_cgroup_swap_statistics(memcg, true);
-		mem_cgroup_update_swap_max(memcg);
-		css_get(&memcg->css);
-	}
-	/*
-	 * Migration does not charge the page_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;
-
-unlock_out:
-	unlock_page_cgroup(pc);
-	return NULL;
-}
-
-void mem_cgroup_uncharge_page(struct page *page)
-{
-	/* early check. */
-	if (page_mapped(page))
-		return;
-	VM_BUG_ON_PAGE(page->mapping && !PageAnon(page), page);
-	/*
-	 * If the page is in swap cache, uncharge should be deferred
-	 * to the swap path, which also properly accounts swap usage
-	 * and handles memcg lifetime.
-	 *
-	 * Note that this check is not stable and reclaim may add the
-	 * page to swap cache at any time after this.  However, if the
-	 * page is not in swap cache by the time page->mapcount hits
-	 * 0, there won't be any page table references to the swap
-	 * slot, and reclaim will free it and not actually write the
-	 * page to disk.
-	 */
-	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(page_mapped(page), page);
-	VM_BUG_ON_PAGE(page->mapping, page);
-	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_CACHE, false);
-}
-
 /*
  * Batch_start/batch_end is called in unmap_page_range/invlidate/trucate.
  * In that cases, pages are freed continuously and we can expect pages
@@ -3815,6 +3635,9 @@  void mem_cgroup_uncharge_cache_page(struct page *page)
 
 void mem_cgroup_uncharge_start(void)
 {
+	unsigned long flags;
+
+	local_irq_save(flags);
 	current->memcg_batch.do_batch++;
 	/* We can do nest. */
 	if (current->memcg_batch.do_batch == 1) {
@@ -3822,21 +3645,18 @@  void mem_cgroup_uncharge_start(void)
 		current->memcg_batch.nr_pages = 0;
 		current->memcg_batch.memsw_nr_pages = 0;
 	}
+	local_irq_restore(flags);
 }
 
 void mem_cgroup_uncharge_end(void)
 {
 	struct memcg_batch_info *batch = &current->memcg_batch;
+	unsigned long flags;
 
-	if (!batch->do_batch)
-		return;
-
-	batch->do_batch--;
-	if (batch->do_batch) /* If stacked, do nothing. */
-		return;
-
-	if (!batch->memcg)
-		return;
+	local_irq_save(flags);
+	VM_BUG_ON(!batch->do_batch);
+	if (--batch->do_batch) /* If stacked, do nothing */
+		goto out;
 	/*
 	 * This "batch->memcg" is valid without any css_get/put etc...
 	 * bacause we hide charges behind us.
@@ -3846,65 +3666,16 @@  void mem_cgroup_uncharge_end(void)
 	if (batch->memsw_nr_pages)
 		page_counter_uncharge(&batch->memcg->memsw, batch->memsw_nr_pages);
 	memcg_oom_recover(batch->memcg);
-	/* forget this pointer (for sanity check) */
-	batch->memcg = NULL;
-}
-
-#ifdef CONFIG_SWAP
-/*
- * called after __delete_from_swap_cache() and drop "page" account.
- * memcg information is recorded to swap_cgroup of "ent"
- */
-void
-mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent, bool swapout)
-{
-	struct mem_cgroup *memcg;
-	int ctype = MEM_CGROUP_CHARGE_TYPE_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, false);
-
-	/*
-	 * record memcg information,  if swapout && memcg != NULL,
-	 * css_get() was called in uncharge().
-	 */
-	if (do_swap_account && swapout && memcg)
-		swap_cgroup_record(ent, css_id(&memcg->css));
-
-	if (swapout && memcg)
-		this_cpu_inc(memcg->stat->events[MEM_CGROUP_EVENTS_PSWPOUT]);
+out:
+	local_irq_restore(flags);
 }
-#endif
 
 #ifdef CONFIG_MEMCG_SWAP
-/*
- * called from swap_entry_free(). remove record in swap_cgroup and
- * uncharge "memsw" account.
- */
-void mem_cgroup_uncharge_swap(swp_entry_t ent)
+static void mem_cgroup_swap_statistics(struct mem_cgroup *memcg,
+					 bool charge)
 {
-	struct mem_cgroup *memcg;
-	unsigned short id;
-
-	if (!do_swap_account)
-		return;
-
-	id = swap_cgroup_record(ent, 0);
-	rcu_read_lock();
-	memcg = mem_cgroup_lookup(id);
-	if (memcg) {
-		/*
-		 * We uncharge this because swap is freed.
-		 * This memcg can be obsolete one. We avoid calling css_tryget
-		 */
-		if (!mem_cgroup_is_root(memcg))
-			page_counter_uncharge(&memcg->memsw, 1);
-		mem_cgroup_swap_statistics(memcg, false);
-		css_put(&memcg->css);
-	}
-	rcu_read_unlock();
+	int val = (charge) ? 1 : -1;
+	this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_SWAP], val);
 }
 
 /**
@@ -3956,169 +3727,6 @@  static inline int mem_cgroup_move_swap_account(swp_entry_t entry,
 }
 #endif
 
-/*
- * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
- * page belongs to.
- */
-void mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
-				  struct mem_cgroup **memcgp)
-{
-	struct mem_cgroup *memcg = NULL;
-	unsigned int nr_pages = 1;
-	struct page_cgroup *pc;
-
-	*memcgp = NULL;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	if (PageTransHuge(page))
-		nr_pages <<= compound_order(page);
-
-	pc = lookup_page_cgroup(page);
-	lock_page_cgroup(pc);
-	if (PageCgroupUsed(pc)) {
-		memcg = pc->mem_cgroup;
-		css_get(&memcg->css);
-		/*
-		 * At migrating an anonymous page, its mapcount goes down
-		 * to 0 and uncharge() will be called. But, even if it's fully
-		 * unmapped, migration may fail and this page has to be
-		 * charged again. We set MIGRATION flag here and delay uncharge
-		 * until end_migration() is called
-		 *
-		 * Corner Case Thinking
-		 * A)
-		 * When the old page was mapped as Anon and it's unmap-and-freed
-		 * while migration was ongoing.
-		 * If unmap finds the old page, uncharge() of it will be delayed
-		 * until end_migration(). If unmap finds a new page, it's
-		 * uncharged when it make mapcount to be 1->0. If unmap code
-		 * finds swap_migration_entry, the new page will not be mapped
-		 * and end_migration() will find it(mapcount==0).
-		 *
-		 * B)
-		 * When the old page was mapped but migraion fails, the kernel
-		 * remaps it. A charge for it is kept by MIGRATION flag even
-		 * if mapcount goes down to 0. We can do remap successfully
-		 * without charging it again.
-		 *
-		 * C)
-		 * The "old" page is under lock_page() until the end of
-		 * migration, so, the old page itself will not be swapped-out.
-		 * If the new page is swapped out before end_migraton, our
-		 * hook to usual swap-out path will catch the event.
-		 */
-		if (PageAnon(page))
-			SetPageCgroupMigration(pc);
-	}
-	unlock_page_cgroup(pc);
-	/*
-	 * If the page is not charged at this point,
-	 * we return here.
-	 */
-	if (!memcg)
-		return;
-
-	*memcgp = memcg;
-	/*
-	 * 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
-	 * 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().
-	 */
-	/*
-	 * The page is committed to the memcg, but it's not actually
-	 * charged to the page_counter since we plan on replacing the
-	 * old one and only one page is going to be left afterwards.
-	 */
-	commit_charge(newpage, memcg, nr_pages, PageAnon(page), false);
-}
-
-/* remove redundant charge if migration failed*/
-void mem_cgroup_end_migration(struct mem_cgroup *memcg,
-	struct page *oldpage, struct page *newpage, bool migration_ok)
-{
-	struct page *used, *unused;
-	struct page_cgroup *pc;
-	bool anon;
-
-	if (!memcg)
-		return;
-
-	if (!migration_ok) {
-		used = oldpage;
-		unused = newpage;
-	} else {
-		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.
-	 * Clear the flag and check the page should be charged.
-	 */
-	pc = lookup_page_cgroup(oldpage);
-	lock_page_cgroup(pc);
-	ClearPageCgroupMigration(pc);
-	unlock_page_cgroup(pc);
-
-	/*
-	 * If a page is a file cache, radix-tree replacement is very atomic
-	 * and we can skip this check. When it was an Anon page, its mapcount
-	 * goes down to 0. But because we added MIGRATION flage, it's not
-	 * uncharged yet. There are several case but page->mapcount check
-	 * and USED bit check in mem_cgroup_uncharge_page() will do enough
-	 * check. (see prepare_charge() also)
-	 */
-	if (anon)
-		mem_cgroup_uncharge_page(used);
-}
-
-/*
- * At replace page cache, newpage is not under any memcg but it's on
- * LRU. So, this function doesn't touch page_counter but handles LRU
- * in correct way. Both pages are locked so we cannot race with uncharge.
- */
-void mem_cgroup_replace_page_cache(struct page *oldpage,
-				  struct page *newpage)
-{
-	struct mem_cgroup *memcg = NULL;
-	struct page_cgroup *pc;
-
-	if (mem_cgroup_disabled())
-		return;
-
-	pc = lookup_page_cgroup(oldpage);
-	/* fix accounting on old pages */
-	lock_page_cgroup(pc);
-	if (PageCgroupUsed(pc)) {
-		memcg = pc->mem_cgroup;
-		mem_cgroup_charge_statistics(memcg, oldpage, false, -1);
-		ClearPageCgroupUsed(pc);
-	}
-	unlock_page_cgroup(pc);
-
-	/*
-	 * When called from shmem_replace_page(), in some cases the
-	 * oldpage has already been charged, and in some cases not.
-	 */
-	if (!memcg)
-		return;
-	/*
-	 * Even if newpage->mapping was NULL before starting replacement,
-	 * the newpage may be on LRU(or pagevec for LRU) already. We lock
-	 * LRU while we overwrite pc->mem_cgroup.
-	 */
-	commit_charge(newpage, memcg, 1, false, true);
-}
-
 #ifdef CONFIG_DEBUG_VM
 static struct page_cgroup *lookup_page_cgroup_used(struct page *page)
 {
@@ -4312,7 +3920,7 @@  unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						    gfp_mask, &nr_scanned);
 		nr_reclaimed += reclaimed;
 		*total_scanned += nr_scanned;
-		spin_lock(&mctz->lock);
+		spin_lock_irq(&mctz->lock);
 
 		/*
 		 * If we failed to reclaim anything from this memory cgroup
@@ -4352,7 +3960,7 @@  unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 		 */
 		/* If excess == 0, no tree ops */
 		__mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess);
-		spin_unlock(&mctz->lock);
+		spin_unlock_irq(&mctz->lock);
 		css_put(&mz->memcg->css);
 		loop++;
 		/*
@@ -6674,9 +6282,9 @@  static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma,
 	if (page) {
 		pc = lookup_page_cgroup(page);
 		/*
-		 * Do only loose check w/o page_cgroup lock.
-		 * mem_cgroup_move_account() checks the pc is valid or not under
-		 * the lock.
+		 * Do only loose check w/o serialization.
+		 * mem_cgroup_move_account() checks the pc is valid or
+		 * not under LRU exclusion.
 		 */
 		if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) {
 			ret = MC_TARGET_PAGE;
@@ -7144,6 +6752,67 @@  static void __init enable_swap_cgroup(void)
 }
 #endif
 
+#ifdef CONFIG_MEMCG_SWAP
+/**
+ * mem_cgroup_swapout - transfer a memsw charge to swap
+ * @page: page whose memsw charge to transfer
+ * @entry: swap entry to move the charge to
+ *
+ * Transfer the memsw charge of @page to @entry.
+ */
+void mem_cgroup_swapout(struct page *page, swp_entry_t entry)
+{
+	struct page_cgroup *pc;
+	unsigned short oldid;
+
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_PAGE(page_count(page), page);
+
+	if (!do_swap_account)
+		return;
+
+	pc = lookup_page_cgroup(page);
+
+	/* Readahead page, never charged */
+	if (!PageCgroupUsed(pc))
+		return;
+
+	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEMSW), page);
+
+	oldid = swap_cgroup_record(entry, css_id(&pc->mem_cgroup->css));
+	VM_BUG_ON_PAGE(oldid, page);
+
+	pc->flags &= ~PCG_MEMSW;
+	css_get(&pc->mem_cgroup->css);
+	mem_cgroup_swap_statistics(pc->mem_cgroup, true);
+}
+
+/**
+ * mem_cgroup_uncharge_swap - uncharge a swap entry
+ * @entry: swap entry to uncharge
+ *
+ * Drop the memsw charge associated with @entry.
+ */
+void mem_cgroup_uncharge_swap(swp_entry_t entry)
+{
+	struct mem_cgroup *memcg;
+	unsigned short id;
+
+	if (!do_swap_account)
+		return;
+
+	id = swap_cgroup_record(entry, 0);
+	rcu_read_lock();
+	memcg = mem_cgroup_lookup(id);
+	if (memcg) {
+		page_counter_uncharge(&memcg->memsw, 1);
+		mem_cgroup_swap_statistics(memcg, false);
+		css_put(&memcg->css);
+	}
+	rcu_read_unlock();
+}
+#endif
+
 /**
  * mem_cgroup_try_charge - try charging a page
  * @page: page to charge
@@ -7246,7 +6915,7 @@  void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 	}
 
-	commit_charge(page, memcg, nr_pages, PageAnon(page), lrucare);
+	commit_charge(page, memcg, nr_pages, lrucare);
 
 	if (do_swap_account && PageSwapCache(page)) {
 		swp_entry_t entry = { .val = page_private(page) };
@@ -7288,6 +6957,139 @@  void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg)
 	cancel_charge(memcg, nr_pages);
 }
 
+/**
+ * mem_cgroup_uncharge - uncharge a page
+ * @page: page to uncharge
+ *
+ * Uncharge a page previously charged with mem_cgroup_try_charge() and
+ * mem_cgroup_commit_charge().
+ */
+void mem_cgroup_uncharge(struct page *page)
+{
+	struct memcg_batch_info *batch;
+	unsigned int nr_pages = 1;
+	struct mem_cgroup *memcg;
+	struct page_cgroup *pc;
+	unsigned long pc_flags;
+	unsigned long flags;
+
+	VM_BUG_ON_PAGE(PageLRU(page), page);
+	VM_BUG_ON_PAGE(page_count(page), page);
+
+	if (mem_cgroup_disabled())
+		return;
+
+	pc = lookup_page_cgroup(page);
+
+	/* Every final put_page() ends up here */
+	if (!PageCgroupUsed(pc))
+		return;
+
+	if (PageTransHuge(page)) {
+		nr_pages <<= compound_order(page);
+		VM_BUG_ON_PAGE(!PageTransHuge(page), page);
+	}
+	/*
+	 * Nobody should be changing or seriously looking at
+	 * pc->mem_cgroup and pc->flags at this point, we have fully
+	 * exclusive access to the page.
+	 */
+	memcg = pc->mem_cgroup;
+	pc_flags = pc->flags;
+	pc->flags = 0;
+
+	local_irq_save(flags);
+
+	if (nr_pages > 1)
+		goto direct;
+	if (unlikely(test_thread_flag(TIF_MEMDIE)))
+		goto direct;
+	batch = &current->memcg_batch;
+	if (!batch->do_batch)
+		goto direct;
+	if (batch->memcg && batch->memcg != memcg)
+		goto direct;
+	if (!batch->memcg)
+		batch->memcg = memcg;
+	if (pc_flags & PCG_MEM)
+		batch->nr_pages++;
+	if (pc_flags & PCG_MEMSW)
+		batch->memsw_nr_pages++;
+	goto out;
+direct:
+	if (pc_flags & PCG_MEM)
+		page_counter_uncharge(&memcg->memory, nr_pages);
+	if (pc_flags & PCG_MEMSW)
+		page_counter_uncharge(&memcg->memsw, nr_pages);
+	memcg_oom_recover(memcg);
+out:
+	mem_cgroup_charge_statistics(memcg, page, -nr_pages);
+	memcg_check_events(memcg, page);
+
+	local_irq_restore(flags);
+}
+
+/**
+ * mem_cgroup_migrate - migrate a charge to another page
+ * @oldpage: currently charged page
+ * @newpage: page to transfer the charge to
+ * @lrucare: both pages might be on the LRU already
+ *
+ * Migrate the charge from @oldpage to @newpage.
+ *
+ * Both pages must be locked, @newpage->mapping must be set up.
+ */
+void mem_cgroup_migrate(struct page *oldpage, struct page *newpage,
+			bool lrucare)
+{
+	unsigned int nr_pages = 1;
+	struct page_cgroup *pc;
+	int isolated;
+
+	VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage);
+	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
+	VM_BUG_ON_PAGE(!lrucare && PageLRU(oldpage), oldpage);
+	VM_BUG_ON_PAGE(!lrucare && PageLRU(newpage), newpage);
+	VM_BUG_ON_PAGE(PageAnon(oldpage) != PageAnon(newpage), newpage);
+
+	if (mem_cgroup_disabled())
+		return;
+
+	/* Page cache replacement: new page already charged? */
+	pc = lookup_page_cgroup(newpage);
+	if (PageCgroupUsed(pc))
+		return;
+
+	/* Re-entrant migration: old page already uncharged? */
+	pc = lookup_page_cgroup(oldpage);
+	if (!PageCgroupUsed(pc))
+		return;
+
+	VM_BUG_ON_PAGE(!(pc->flags & PCG_MEM), oldpage);
+	VM_BUG_ON_PAGE(do_swap_account && !(pc->flags & PCG_MEMSW), oldpage);
+
+	if (PageTransHuge(oldpage)) {
+		nr_pages <<= compound_order(oldpage);
+		VM_BUG_ON_PAGE(!PageTransHuge(oldpage), oldpage);
+		VM_BUG_ON_PAGE(!PageTransHuge(newpage), newpage);
+	}
+
+	if (lrucare)
+		lock_page_lru(oldpage, &isolated);
+
+	pc->flags = 0;
+
+	if (lrucare)
+		unlock_page_lru(oldpage, isolated);
+
+	local_irq_disable();
+	mem_cgroup_charge_statistics(pc->mem_cgroup, oldpage, -nr_pages);
+	memcg_check_events(pc->mem_cgroup, oldpage);
+	local_irq_enable();
+
+	commit_charge(newpage, pc->mem_cgroup, nr_pages, lrucare);
+}
+
 /*
  * subsys_initcall() for memory controller.
  *
diff --git a/mm/memory.c b/mm/memory.c
index 80cc801..b408ff27 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1287,7 +1287,6 @@  static void unmap_page_range(struct mmu_gather *tlb,
 		details = NULL;
 
 	BUG_ON(addr >= end);
-	mem_cgroup_uncharge_start();
 	tlb_start_vma(tlb, vma);
 	pgd = pgd_offset(vma->vm_mm, addr);
 	do {
@@ -1297,7 +1296,6 @@  static void unmap_page_range(struct mmu_gather *tlb,
 		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
-	mem_cgroup_uncharge_end();
 }
 
 
diff --git a/mm/migrate.c b/mm/migrate.c
index f268953..ef1eef8 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -778,6 +778,7 @@  static int move_to_new_page(struct page *newpage, struct page *page,
 	if (rc != MIGRATEPAGE_SUCCESS) {
 		newpage->mapping = NULL;
 	} else {
+		mem_cgroup_migrate(page, newpage, false);
 		if (page_was_mapped)
 			remove_migration_ptes(page, newpage);
 		page->mapping = NULL;
@@ -793,7 +794,6 @@  static int __unmap_and_move(struct page *page, struct page *newpage,
 {
 	int rc = -EAGAIN;
 	int page_was_mapped = 0;
-	struct mem_cgroup *mem;
 	struct anon_vma *anon_vma = NULL;
 
 	if (!trylock_page(page)) {
@@ -819,9 +819,6 @@  static int __unmap_and_move(struct page *page, struct page *newpage,
 		lock_page(page);
 	}
 
-	/* charge against new page */
-	mem_cgroup_prepare_migration(page, newpage, &mem);
-
 	if (PageWriteback(page)) {
 		/*
 		 * Only in the case of a full synchronous migration is it
@@ -831,10 +828,10 @@  static int __unmap_and_move(struct page *page, struct page *newpage,
 		 */
 		if (mode != MIGRATE_SYNC) {
 			rc = -EBUSY;
-			goto uncharge;
+			goto out_unlock;
 		}
 		if (!force)
-			goto uncharge;
+			goto out_unlock;
 		wait_on_page_writeback(page);
 	}
 	/*
@@ -869,7 +866,7 @@  static int __unmap_and_move(struct page *page, struct page *newpage,
 			 * completes
 			 */
 		} else {
-			goto uncharge;
+			goto out_unlock;
 		}
 	}
 
@@ -882,7 +879,7 @@  static int __unmap_and_move(struct page *page, struct page *newpage,
 		 * the page migration right away (proteced by page lock).
 		 */
 		rc = balloon_page_migrate(newpage, page, mode);
-		goto uncharge;
+		goto out_unlock;
 	}
 
 	/*
@@ -901,7 +898,7 @@  static int __unmap_and_move(struct page *page, struct page *newpage,
 		VM_BUG_ON_PAGE(PageAnon(page), page);
 		if (page_has_private(page)) {
 			try_to_free_buffers(page);
-			goto uncharge;
+			goto out_unlock;
 		}
 		goto skip_unmap;
 	}
@@ -924,9 +921,7 @@  skip_unmap:
 	if (anon_vma)
 		put_anon_vma(anon_vma);
 
-uncharge:
-	mem_cgroup_end_migration(mem, page, newpage,
-				 rc == MIGRATEPAGE_SUCCESS);
+out_unlock:
 	unlock_page(page);
 out:
 	return rc;
@@ -1751,7 +1746,6 @@  int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated = 0;
 	struct page *new_page = NULL;
-	struct mem_cgroup *memcg = NULL;
 	int page_lru = page_is_file_cache(page);
 	unsigned long mmun_start = address & HPAGE_PMD_MASK;
 	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
@@ -1817,17 +1811,6 @@  fail_putback:
 		goto out_unlock;
 	}
 
-	/*
-	 * Traditional migration needs to prepare the memcg charge
-	 * transaction early to prevent the old page from being
-	 * uncharged when installing migration entries.  Here we can
-	 * save the potential rollback and start the charge transfer
-	 * only when migration is already known to end successfully.
-	 */
-	mem_cgroup_prepare_migration(page, new_page, &memcg);
-
-	init_trans_huge_mmu_gather_count(new_page);
-
 	orig_entry = *pmd;
 	entry = mk_pmd(new_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
@@ -1856,14 +1839,10 @@  fail_putback:
 		goto fail_putback;
 	}
 
+	mem_cgroup_migrate(page, new_page, false);
+
 	page_remove_rmap(page);
 
-	/*
-	 * Finish the charge transaction under the page table lock to
-	 * prevent split_huge_page() from dividing up the charge
-	 * before it's fully transferred to the new page.
-	 */
-	mem_cgroup_end_migration(memcg, page, new_page, true);
 	spin_unlock(ptl);
 	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index 60897ca..4668df5 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1333,7 +1333,6 @@  void page_remove_rmap(struct page *page)
 	if (unlikely(PageHuge(page)))
 		goto out;
 	if (anon) {
-		mem_cgroup_uncharge_page(page);
 		if (!PageTransHuge(page))
 			__dec_zone_page_state(page, NR_ANON_PAGES);
 		else
diff --git a/mm/shmem.c b/mm/shmem.c
index 14cc977..d2bda92 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -556,7 +556,6 @@  static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			pvec.pages, indices);
 		if (!pvec.nr)
 			break;
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -584,7 +583,6 @@  static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
@@ -632,7 +630,6 @@  static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 			index = start;
 			continue;
 		}
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -668,7 +665,6 @@  static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		index++;
 	}
 
@@ -976,7 +972,7 @@  static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 
 	mutex_unlock(&shmem_swaplist_mutex);
-	swapcache_free(swap, NULL);
+	swapcache_free(swap);
 redirty:
 	set_page_dirty(page);
 	if (wbc->for_reclaim)
@@ -1149,7 +1145,7 @@  static int shmem_replace_page(struct page **pagep, gfp_t gfp,
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_replace_page_cache(oldpage, newpage);
+		mem_cgroup_migrate(oldpage, newpage, false);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
diff --git a/mm/swap.c b/mm/swap.c
index 842832a..865375c 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -64,6 +64,7 @@  static void __page_cache_release(struct page *page)
 		del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 	}
+	mem_cgroup_uncharge(page);
 }
 
 static void __put_single_page(struct page *page)
@@ -927,6 +928,8 @@  void release_pages(struct page **pages, int nr, bool cold)
 	unsigned long uninitialized_var(flags);
 	unsigned int uninitialized_var(lock_batch);
 
+	mem_cgroup_uncharge_start();
+
 	for (i = 0; i < nr; i++) {
 		struct page *page = pages[i];
 		const bool was_thp = is_trans_huge_page_release(page);
@@ -1022,6 +1025,7 @@  void release_pages(struct page **pages, int nr, bool cold)
 			__ClearPageLRU(page);
 			del_page_from_lru_list(page, lruvec, page_off_lru(page));
 		}
+		mem_cgroup_uncharge(page);
 
 		if (!was_thp) {
 			/*
@@ -1037,6 +1041,7 @@  void release_pages(struct page **pages, int nr, bool cold)
 	if (zone)
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 
+	mem_cgroup_uncharge_end();
 	if (!list_empty(&pages_to_free))
 		free_hot_cold_page_list(&pages_to_free, cold);
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 95c7855..bd37db2 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -176,7 +176,7 @@  int add_to_swap(struct page *page, struct list_head *list)
 
 	if (unlikely(PageTransHuge(page)))
 		if (unlikely(split_huge_page_to_list(page, list))) {
-			swapcache_free(entry, NULL);
+			swapcache_free(entry);
 			return 0;
 		}
 
@@ -202,7 +202,7 @@  int add_to_swap(struct page *page, struct list_head *list)
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
 		 */
-		swapcache_free(entry, NULL);
+		swapcache_free(entry);
 		return 0;
 	}
 }
@@ -225,7 +225,7 @@  void delete_from_swap_cache(struct page *page)
 	__delete_from_swap_cache(page);
 	spin_unlock_irq(&address_space->tree_lock);
 
-	swapcache_free(entry, page);
+	swapcache_free(entry);
 	page_cache_release(page);
 }
 
@@ -395,7 +395,7 @@  struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
 		 */
-		swapcache_free(entry, NULL);
+		swapcache_free(entry);
 	} while (err != -ENOMEM);
 
 	if (new_page)
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 3a87c51..86ffe4c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -641,16 +641,13 @@  void swap_free(swp_entry_t entry)
 /*
  * Called after dropping swapcache to decrease refcnt to swap entries.
  */
-void swapcache_free(swp_entry_t entry, struct page *page)
+void swapcache_free(swp_entry_t entry)
 {
 	struct swap_info_struct *p;
-	unsigned char count;
 
 	p = swap_info_get(entry);
 	if (p) {
-		count = swap_entry_free(p, entry, SWAP_HAS_CACHE);
-		if (page)
-			mem_cgroup_uncharge_swapcache(page, entry, count != 0);
+		swap_entry_free(p, entry, SWAP_HAS_CACHE);
 		spin_unlock(&p->lock);
 	}
 }
@@ -703,7 +700,7 @@  int reuse_swap_page(struct page *page)
 			spin_unlock_irq(&address_space->tree_lock);
 
 			/* the page is still in use, do not uncharge */
-			swapcache_free(entry, NULL);
+			swapcache_free(entry);
 			page_cache_release(page);
 
 			SetPageDirty(page);
diff --git a/mm/truncate.c b/mm/truncate.c
index 15ba201..f460e67 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -317,7 +317,6 @@  void truncate_inode_pages_range(struct address_space *mapping,
 	while (index < end && __pagevec_lookup(&pvec, mapping, index,
 			min(end - index, (pgoff_t)PAGEVEC_SIZE),
 			indices)) {
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -343,7 +342,6 @@  void truncate_inode_pages_range(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
@@ -410,7 +408,6 @@  void truncate_inode_pages_range(struct address_space *mapping,
 			pagevec_release(&pvec);
 			break;
 		}
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -432,7 +429,6 @@  void truncate_inode_pages_range(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		index++;
 	}
 	cleancache_invalidate_inode(mapping);
@@ -531,7 +527,6 @@  unsigned long invalidate_mapping_pages(struct address_space *mapping,
 	while (index <= end && __pagevec_lookup(&pvec, mapping, index,
 			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
 			indices)) {
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -560,7 +555,6 @@  unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
@@ -591,7 +585,6 @@  invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	BUG_ON(page_has_private(page));
 	__delete_from_page_cache(page, NULL);
 	spin_unlock_irq(&mapping->tree_lock);
-	mem_cgroup_uncharge_cache_page(page);
 
 	if (mapping->a_ops->freepage)
 		mapping->a_ops->freepage(page);
@@ -640,7 +633,6 @@  int invalidate_inode_pages2_range(struct address_space *mapping,
 	while (index <= end && __pagevec_lookup(&pvec, mapping, index,
 			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
 			indices)) {
-		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
@@ -693,7 +685,6 @@  int invalidate_inode_pages2_range(struct address_space *mapping,
 		}
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
-		mem_cgroup_uncharge_end();
 		cond_resched();
 		index++;
 	}
diff --git a/mm/tswap.c b/mm/tswap.c
index d3b878e..4c6c5bc 100644
--- a/mm/tswap.c
+++ b/mm/tswap.c
@@ -216,7 +216,7 @@  retry:
 	return 0;
 
 out_free_swapcache:
-	swapcache_free(entry, NULL);
+	swapcache_free(entry);
 out:
 	return err;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b29668f..6987a4b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -600,9 +600,10 @@  static int __remove_mapping(struct address_space *mapping, struct page *page,
 
 	if (PageSwapCache(page)) {
 		swp_entry_t swap = { .val = page_private(page) };
+		mem_cgroup_swapout(page, swap);
 		__delete_from_swap_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
-		swapcache_free(swap, page);
+		swapcache_free(swap);
 	} else {
 		void (*freepage)(struct page *);
 		void *shadow = NULL;
@@ -629,7 +630,6 @@  static int __remove_mapping(struct address_space *mapping, struct page *page,
 			shadow = workingset_eviction(mapping, page);
 		__delete_from_page_cache(page, shadow);
 		spin_unlock_irq(&mapping->tree_lock);
-		mem_cgroup_uncharge_cache_page(page);
 
 		if (freepage != NULL)
 			freepage(page);
@@ -1135,6 +1135,7 @@  static unsigned long shrink_page_list(struct list_head *page_list,
 		 */
 		__clear_page_locked(page);
 free_it:
+		mem_cgroup_uncharge(page);
 		nr_reclaimed++;
 
 		/*
@@ -1164,13 +1165,14 @@  keep:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON_PAGE(PageLRU(page) || PageUnevictable(page), page);
 	}
+	mem_cgroup_uncharge_end();
 
 	try_to_unmap_flush();
 	free_hot_cold_page_list(&free_pages, true);
 
 	list_splice(&ret_pages, page_list);
 	count_vm_events(PGACTIVATE, pgactivate);
-	mem_cgroup_uncharge_end();
+
 	*ret_nr_dirty += nr_dirty;
 	*ret_nr_congested += nr_congested;
 	*ret_nr_unqueued_dirty += nr_unqueued_dirty;
@@ -1486,6 +1488,8 @@  putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 			__ClearPageActive(page);
 			del_page_from_lru_list(page, lruvec, lru);
 
+			mem_cgroup_uncharge(page);
+
 			if (unlikely(PageCompound(page))) {
 				spin_unlock_irq(&zone->lru_lock);
 				(*get_compound_page_dtor(page))(page);
@@ -1693,6 +1697,8 @@  static void move_active_pages_to_lru(struct lruvec *lruvec,
 			__ClearPageActive(page);
 			del_page_from_lru_list(page, lruvec, lru);
 
+			mem_cgroup_uncharge(page);
+
 			if (unlikely(PageCompound(page))) {
 				spin_unlock_irq(&zone->lru_lock);
 				(*get_compound_page_dtor(page))(page);
diff --git a/mm/zswap.c b/mm/zswap.c
index 4eb661c..e2f8c7e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -507,7 +507,7 @@  static int zswap_get_swap_cache_page(swp_entry_t entry,
 		 * add_to_swap_cache() doesn't return -EEXIST, so we can safely
 		 * clear SWAP_HAS_CACHE flag.
 		 */
-		swapcache_free(entry, NULL);
+		swapcache_free(entry);
 	} while (err != -ENOMEM);
 
 	if (new_page)