Merge branch 'master' into next

36 files changed, 1411 insertions, 679 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index a5b77811fdf2..c2b57d81e153 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -206,7 +206,6 @@ config VIRT_TO_BUS
 config UNEVICTABLE_LRU
 	bool "Add LRU list to track non-evictable pages"
 	default y
-	depends on MMU
 	help
 	  Keeps unevictable pages off of the active and inactive pageout
 	  lists, so kswapd will not waste CPU time or have its balancing
@@ -214,5 +213,43 @@ config UNEVICTABLE_LRU
 	  will use one page flag and increase the code size a little,
 	  say Y unless you know what you are doing.
 
+	  See Documentation/vm/unevictable-lru.txt for more information.
+
+config HAVE_MLOCK
+	bool
+	default y if MMU=y
+
+config HAVE_MLOCKED_PAGE_BIT
+	bool
+	default y if HAVE_MLOCK=y && UNEVICTABLE_LRU=y
+
 config MMU_NOTIFIER
 	bool
+
+config NOMMU_INITIAL_TRIM_EXCESS
+	int "Turn on mmap() excess space trimming before booting"
+	depends on !MMU
+	default 1
+	help
+	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
+	  of memory on which to store mappings, but it can only ask the system
+	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
+	  more than it requires.  To deal with this, mmap() is able to trim off
+	  the excess and return it to the allocator.
+
+	  If trimming is enabled, the excess is trimmed off and returned to the
+	  system allocator, which can cause extra fragmentation, particularly
+	  if there are a lot of transient processes.
+
+	  If trimming is disabled, the excess is kept, but not used, which for
+	  long-term mappings means that the space is wasted.
+
+	  Trimming can be dynamically controlled through a sysctl option
+	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
+	  excess pages there must be before trimming should occur, or zero if
+	  no trimming is to occur.
+
+	  This option specifies the initial value of this option.  The default
+	  of 1 says that all excess pages should be trimmed.
+
+	  See Documentation/nommu-mmap.txt for more information.
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
new file mode 100644
index 000000000000..bb01e298f260
--- /dev/null
+++ b/mm/Kconfig.debug
@@ -0,0 +1,26 @@
+config DEBUG_PAGEALLOC
+	bool "Debug page memory allocations"
+	depends on DEBUG_KERNEL && ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	depends on !HIBERNATION || !PPC && !SPARC
+	---help---
+	  Unmap pages from the kernel linear mapping after free_pages().
+	  This results in a large slowdown, but helps to find certain types
+	  of memory corruptions.
+
+config WANT_PAGE_DEBUG_FLAGS
+	bool
+
+config PAGE_POISONING
+	bool "Debug page memory allocations"
+	depends on DEBUG_KERNEL && !ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	depends on !HIBERNATION
+	select DEBUG_PAGEALLOC
+	select WANT_PAGE_DEBUG_FLAGS
+	help
+	   Fill the pages with poison patterns after free_pages() and verify
+	   the patterns before alloc_pages(). This results in a large slowdown,
+	   but helps to find certain types of memory corruptions.
+
+	   This option cannot enalbe with hibernation. Otherwise, it will get
+	   wrong messages for memory corruption because the free pages are not
+	   saved to the suspend image.
diff --git a/mm/Makefile b/mm/Makefile
index 818569b68f46..ec73c68b6015 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
 obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o
 obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
+obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_FAILSLAB) += failslab.o
diff --git a/mm/allocpercpu.c b/mm/allocpercpu.c
index 1882923bc706..dfdee6a47359 100644
--- a/mm/allocpercpu.c
+++ b/mm/allocpercpu.c
@@ -31,7 +31,7 @@ static void percpu_depopulate(void *__pdata, int cpu)
  * @__pdata: per-cpu data to depopulate
  * @mask: depopulate per-cpu data for cpu's selected through mask bits
  */
-static void __percpu_depopulate_mask(void *__pdata, cpumask_t *mask)
+static void __percpu_depopulate_mask(void *__pdata, const cpumask_t *mask)
 {
 	int cpu;
 	for_each_cpu_mask_nr(cpu, *mask)
@@ -143,7 +143,7 @@ void free_percpu(void *__pdata)
 {
 	if (unlikely(!__pdata))
 		return;
-	__percpu_depopulate_mask(__pdata, &cpu_possible_map);
+	__percpu_depopulate_mask(__pdata, cpu_possible_mask);
 	kfree(__percpu_disguise(__pdata));
 }
 EXPORT_SYMBOL_GPL(free_percpu);
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index be68c956a660..493b468a5035 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -284,12 +284,12 @@ static wait_queue_head_t congestion_wqh[2] = {
 	};
 
 
-void clear_bdi_congested(struct backing_dev_info *bdi, int rw)
+void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	enum bdi_state bit;
-	wait_queue_head_t *wqh = &congestion_wqh[rw];
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
-	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+	bit = sync ? BDI_sync_congested : BDI_async_congested;
 	clear_bit(bit, &bdi->state);
 	smp_mb__after_clear_bit();
 	if (waitqueue_active(wqh))
@@ -297,11 +297,11 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int rw)
 }
 EXPORT_SYMBOL(clear_bdi_congested);
 
-void set_bdi_congested(struct backing_dev_info *bdi, int rw)
+void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
 	enum bdi_state bit;
 
-	bit = (rw == WRITE) ? BDI_write_congested : BDI_read_congested;
+	bit = sync ? BDI_sync_congested : BDI_async_congested;
 	set_bit(bit, &bdi->state);
 }
 EXPORT_SYMBOL(set_bdi_congested);
diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c
new file mode 100644
index 000000000000..a1e3324de2b5
--- /dev/null
+++ b/mm/debug-pagealloc.c
@@ -0,0 +1,129 @@
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/page-debug-flags.h>
+#include <linux/poison.h>
+
+static inline void set_page_poison(struct page *page)
+{
+	__set_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+}
+
+static inline void clear_page_poison(struct page *page)
+{
+	__clear_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+}
+
+static inline bool page_poison(struct page *page)
+{
+	return test_bit(PAGE_DEBUG_FLAG_POISON, &page->debug_flags);
+}
+
+static void poison_highpage(struct page *page)
+{
+	/*
+	 * Page poisoning for highmem pages is not implemented.
+	 *
+	 * This can be called from interrupt contexts.
+	 * So we need to create a new kmap_atomic slot for this
+	 * application and it will need interrupt protection.
+	 */
+}
+
+static void poison_page(struct page *page)
+{
+	void *addr;
+
+	if (PageHighMem(page)) {
+		poison_highpage(page);
+		return;
+	}
+	set_page_poison(page);
+	addr = page_address(page);
+	memset(addr, PAGE_POISON, PAGE_SIZE);
+}
+
+static void poison_pages(struct page *page, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		poison_page(page + i);
+}
+
+static bool single_bit_flip(unsigned char a, unsigned char b)
+{
+	unsigned char error = a ^ b;
+
+	return error && !(error & (error - 1));
+}
+
+static void check_poison_mem(unsigned char *mem, size_t bytes)
+{
+	unsigned char *start;
+	unsigned char *end;
+
+	for (start = mem; start < mem + bytes; start++) {
+		if (*start != PAGE_POISON)
+			break;
+	}
+	if (start == mem + bytes)
+		return;
+
+	for (end = mem + bytes - 1; end > start; end--) {
+		if (*end != PAGE_POISON)
+			break;
+	}
+
+	if (!printk_ratelimit())
+		return;
+	else if (start == end && single_bit_flip(*start, PAGE_POISON))
+		printk(KERN_ERR "pagealloc: single bit error\n");
+	else
+		printk(KERN_ERR "pagealloc: memory corruption\n");
+
+	print_hex_dump(KERN_ERR, "", DUMP_PREFIX_ADDRESS, 16, 1, start,
+			end - start + 1, 1);
+	dump_stack();
+}
+
+static void unpoison_highpage(struct page *page)
+{
+	/*
+	 * See comment in poison_highpage().
+	 * Highmem pages should not be poisoned for now
+	 */
+	BUG_ON(page_poison(page));
+}
+
+static void unpoison_page(struct page *page)
+{
+	if (PageHighMem(page)) {
+		unpoison_highpage(page);
+		return;
+	}
+	if (page_poison(page)) {
+		void *addr = page_address(page);
+
+		check_poison_mem(addr, PAGE_SIZE);
+		clear_page_poison(page);
+	}
+}
+
+static void unpoison_pages(struct page *page, int n)
+{
+	int i;
+
+	for (i = 0; i < n; i++)
+		unpoison_page(page + i);
+}
+
+void kernel_map_pages(struct page *page, int numpages, int enable)
+{
+	if (!debug_pagealloc_enabled)
+		return;
+
+	if (enable)
+		unpoison_pages(page, numpages);
+	else
+		poison_pages(page, numpages);
+}
diff --git a/mm/failslab.c b/mm/failslab.c
index 7c6ea6493f80..9339de5f0a91 100644
--- a/mm/failslab.c
+++ b/mm/failslab.c
@@ -1,4 +1,5 @@
 #include <linux/fault-inject.h>
+#include <linux/gfp.h>
 
 static struct {
 	struct fault_attr attr;
diff --git a/mm/filemap.c b/mm/filemap.c
index 126d3973b3d1..379ff0bcbf6e 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -441,6 +441,7 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 	}
 	return err;
 }
+EXPORT_SYMBOL(filemap_write_and_wait_range);
 
 /**
  * add_to_page_cache_locked - add a locked page to the pagecache
@@ -513,6 +514,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
 
 #ifdef CONFIG_NUMA
 struct page *__page_cache_alloc(gfp_t gfp)
@@ -565,6 +567,24 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 EXPORT_SYMBOL(wait_on_page_bit);
 
 /**
+ * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
+ * @page: Page defining the wait queue of interest
+ * @waiter: Waiter to add to the queue
+ *
+ * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ */
+void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, waiter);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_page_wait_queue);
+
+/**
  * unlock_page - unlock a locked page
  * @page: the page
  *
@@ -627,6 +647,7 @@ int __lock_page_killable(struct page *page)
 	return __wait_on_bit_lock(page_waitqueue(page), &wait,
 					sync_page_killable, TASK_KILLABLE);
 }
+EXPORT_SYMBOL_GPL(__lock_page_killable);
 
 /**
  * __lock_page_nosync - get a lock on the page, without calling sync_page()
@@ -2463,6 +2484,9 @@ EXPORT_SYMBOL(generic_file_aio_write);
  * (presumably at page->private).  If the release was successful, return `1'.
  * Otherwise return zero.
  *
+ * This may also be called if PG_fscache is set on a page, indicating that the
+ * page is known to the local caching routines.
+ *
  * The @gfp_mask argument specifies whether I/O may be performed to release
  * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS).
  *
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 0c04615651b7..427dfe3ce78c 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -89,8 +89,8 @@ do_xip_mapping_read(struct address_space *mapping,
 			}
 		}
 		nr = nr - offset;
-		if (nr > len)
-			nr = len;
+		if (nr > len - copied)
+			nr = len - copied;
 
 		error = mapping->a_ops->get_xip_mem(mapping, index, 0,
 							&xip_mem, &xip_pfn);
diff --git a/mm/highmem.c b/mm/highmem.c
index 910198037bf5..68eb1d9b63fa 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -422,3 +422,48 @@ void __init page_address_init(void)
 }
 
 #endif	/* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */
+
+#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
+
+void debug_kmap_atomic(enum km_type type)
+{
+	static unsigned warn_count = 10;
+
+	if (unlikely(warn_count == 0))
+		return;
+
+	if (unlikely(in_interrupt())) {
+		if (in_irq()) {
+			if (type != KM_IRQ0 && type != KM_IRQ1 &&
+			    type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ &&
+			    type != KM_BOUNCE_READ) {
+				WARN_ON(1);
+				warn_count--;
+			}
+		} else if (!irqs_disabled()) {	/* softirq */
+			if (type != KM_IRQ0 && type != KM_IRQ1 &&
+			    type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 &&
+			    type != KM_SKB_SUNRPC_DATA &&
+			    type != KM_SKB_DATA_SOFTIRQ &&
+			    type != KM_BOUNCE_READ) {
+				WARN_ON(1);
+				warn_count--;
+			}
+		}
+	}
+
+	if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ ||
+			type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ) {
+		if (!irqs_disabled()) {
+			WARN_ON(1);
+			warn_count--;
+		}
+	} else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) {
+		if (irq_count() == 0 && !irqs_disabled()) {
+			WARN_ON(1);
+			warn_count--;
+		}
+	}
+}
+
+#endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 107da3d809a8..28c655ba9353 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -918,7 +918,7 @@ static void return_unused_surplus_pages(struct hstate *h,
  * an instantiated the change should be committed via vma_commit_reservation.
  * No action is required on failure.
  */
-static int vma_needs_reservation(struct hstate *h,
+static long vma_needs_reservation(struct hstate *h,
 			struct vm_area_struct *vma, unsigned long addr)
 {
 	struct address_space *mapping = vma->vm_file->f_mapping;
@@ -933,7 +933,7 @@ static int vma_needs_reservation(struct hstate *h,
 		return 1;
 
 	} else  {
-		int err;
+		long err;
 		pgoff_t idx = vma_hugecache_offset(h, vma, addr);
 		struct resv_map *reservations = vma_resv_map(vma);
 
@@ -969,7 +969,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	struct page *page;
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	struct inode *inode = mapping->host;
-	unsigned int chg;
+	long chg;
 
 	/*
 	 * Processes that did not create the mapping will have no reserves and
diff --git a/mm/internal.h b/mm/internal.h
index 478223b73a2a..987bb03fbdd8 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -63,6 +63,7 @@ static inline unsigned long page_order(struct page *page)
 	return page_private(page);
 }
 
+#ifdef CONFIG_HAVE_MLOCK
 extern long mlock_vma_pages_range(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
 extern void munlock_vma_pages_range(struct vm_area_struct *vma,
@@ -71,6 +72,7 @@ static inline void munlock_vma_pages_all(struct vm_area_struct *vma)
 {
 	munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
 }
+#endif
 
 #ifdef CONFIG_UNEVICTABLE_LRU
 /*
@@ -90,7 +92,7 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old)
 }
 #endif
 
-#ifdef CONFIG_UNEVICTABLE_LRU
+#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
 /*
  * Called only in fault path via page_evictable() for a new page
  * to determine if it's being mapped into a LOCKED vma.
@@ -165,7 +167,7 @@ static inline void free_page_mlock(struct page *page)
 	}
 }
 
-#else /* CONFIG_UNEVICTABLE_LRU */
+#else /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
 static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
 {
 	return 0;
@@ -175,7 +177,7 @@ static inline void mlock_vma_page(struct page *page) { }
 static inline void mlock_migrate_page(struct page *new, struct page *old) { }
 static inline void free_page_mlock(struct page *page) { }
 
-#endif /* CONFIG_UNEVICTABLE_LRU */
+#endif /* CONFIG_HAVE_MLOCKED_PAGE_BIT */
 
 /*
  * Return the mem_map entry representing the 'offset' subpage within
diff --git a/mm/madvise.c b/mm/madvise.c
index b9ce574827c8..36d6ea2b6340 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -112,6 +112,14 @@ static long madvise_willneed(struct vm_area_struct * vma,
 	if (!file)
 		return -EBADF;
 
+	/*
+	 * Page cache readahead assumes page cache pages are order-0 which
+	 * is not the case for hugetlbfs. Do not give a bad return value
+	 * but ignore the advice.
+	 */
+	if (vma->vm_flags & VM_HUGETLB)
+		return 0;
+
 	if (file->f_mapping->a_ops->get_xip_mem) {
 		/* no bad return value, but ignore advice */
 		return 0;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8e4be9cb2a6a..01c2d8f14685 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -27,6 +27,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -95,6 +96,15 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
 	return ret;
 }
 
+static s64 mem_cgroup_local_usage(struct mem_cgroup_stat *stat)
+{
+	s64 ret;
+
+	ret = mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_CACHE);
+	ret += mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_RSS);
+	return ret;
+}
+
 /*
  * per-zone information in memory controller.
  */
@@ -154,9 +164,9 @@ struct mem_cgroup {
 
 	/*
 	 * While reclaiming in a hiearchy, we cache the last child we
-	 * reclaimed from. Protected by hierarchy_mutex
+	 * reclaimed from.
 	 */
-	struct mem_cgroup *last_scanned_child;
+	int last_scanned_child;
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
@@ -247,7 +257,7 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
 	return mem_cgroup_zoneinfo(mem, nid, zid);
 }
 
-static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
+static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem,
 					enum lru_list idx)
 {
 	int nid, zid;
@@ -286,6 +296,9 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	struct mem_cgroup *mem = NULL;
+
+	if (!mm)
+		return NULL;
 	/*
 	 * Because we have no locks, mm->owner's may be being moved to other
 	 * cgroup. We use css_tryget() here even if this looks
@@ -308,6 +321,42 @@ static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
 	return css_is_removed(&mem->css);
 }
 
+
+/*
+ * Call callback function against all cgroup under hierarchy tree.
+ */
+static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data,
+			  int (*func)(struct mem_cgroup *, void *))
+{
+	int found, ret, nextid;
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *mem;
+
+	if (!root->use_hierarchy)
+		return (*func)(root, data);
+
+	nextid = 1;
+	do {
+		ret = 0;
+		mem = NULL;
+
+		rcu_read_lock();
+		css = css_get_next(&mem_cgroup_subsys, nextid, &root->css,
+				   &found);
+		if (css && css_tryget(css))
+			mem = container_of(css, struct mem_cgroup, css);
+		rcu_read_unlock();
+
+		if (mem) {
+			ret = (*func)(mem, data);
+			css_put(&mem->css);
+		}
+		nextid = found + 1;
+	} while (!ret && css);
+
+	return ret;
+}
+
 /*
  * Following LRU functions are allowed to be used without PCG_LOCK.
  * Operations are called by routine of global LRU independently from memcg.
@@ -441,31 +490,24 @@ void mem_cgroup_move_lists(struct page *page,
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 {
 	int ret;
+	struct mem_cgroup *curr = NULL;
 
 	task_lock(task);
-	ret = task->mm && mm_match_cgroup(task->mm, mem);
+	rcu_read_lock();
+	curr = try_get_mem_cgroup_from_mm(task->mm);
+	rcu_read_unlock();
 	task_unlock(task);
+	if (!curr)
+		return 0;
+	if (curr->use_hierarchy)
+		ret = css_is_ancestor(&curr->css, &mem->css);
+	else
+		ret = (curr == mem);
+	css_put(&curr->css);
 	return ret;
 }
 
 /*
- * Calculate mapped_ratio under memory controller. This will be used in
- * vmscan.c for deteremining we have to reclaim mapped pages.
- */
-int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
-{
-	long total, rss;
-
-	/*
-	 * usage is recorded in bytes. But, here, we assume the number of
-	 * physical pages can be represented by "long" on any arch.
-	 */
-	total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;
-	rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
-	return (int)((rss * 100L) / total);
-}
-
-/*
  * prev_priority control...this will be used in memory reclaim path.
  */
 int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
@@ -501,8 +543,8 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_
 	unsigned long gb;
 	unsigned long inactive_ratio;
 
-	inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON);
-	active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON);
+	inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON);
+	active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON);
 
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
 	if (gb)
@@ -629,172 +671,202 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 #define mem_cgroup_from_res_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
-/*
- * This routine finds the DFS walk successor. This routine should be
- * called with hierarchy_mutex held
- */
-static struct mem_cgroup *
-__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
+static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
 {
-	struct cgroup *cgroup, *curr_cgroup, *root_cgroup;
-
-	curr_cgroup = curr->css.cgroup;
-	root_cgroup = root_mem->css.cgroup;
+	if (do_swap_account) {
+		if (res_counter_check_under_limit(&mem->res) &&
+			res_counter_check_under_limit(&mem->memsw))
+			return true;
+	} else
+		if (res_counter_check_under_limit(&mem->res))
+			return true;
+	return false;
+}
 
-	if (!list_empty(&curr_cgroup->children)) {
-		/*
-		 * Walk down to children
-		 */
-		cgroup = list_entry(curr_cgroup->children.next,
-						struct cgroup, sibling);
-		curr = mem_cgroup_from_cont(cgroup);
-		goto done;
-	}
+static unsigned int get_swappiness(struct mem_cgroup *memcg)
+{
+	struct cgroup *cgrp = memcg->css.cgroup;
+	unsigned int swappiness;
 
-visit_parent:
-	if (curr_cgroup == root_cgroup) {
-		/* caller handles NULL case */
-		curr = NULL;
-		goto done;
-	}
+	/* root ? */
+	if (cgrp->parent == NULL)
+		return vm_swappiness;
 
-	/*
-	 * Goto next sibling
-	 */
-	if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) {
-		cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup,
-						sibling);
-		curr = mem_cgroup_from_cont(cgroup);
-		goto done;
-	}
+	spin_lock(&memcg->reclaim_param_lock);
+	swappiness = memcg->swappiness;
+	spin_unlock(&memcg->reclaim_param_lock);
 
-	/*
-	 * Go up to next parent and next parent's sibling if need be
-	 */
-	curr_cgroup = curr_cgroup->parent;
-	goto visit_parent;
+	return swappiness;
+}
 
-done:
-	return curr;
+static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
+{
+	int *val = data;
+	(*val)++;
+	return 0;
 }
 
-/*
- * Visit the first child (need not be the first child as per the ordering
- * of the cgroup list, since we track last_scanned_child) of @mem and use
- * that to reclaim free pages from.
+/**
+ * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode.
+ * @memcg: The memory cgroup that went over limit
+ * @p: Task that is going to be killed
+ *
+ * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
+ * enabled
  */
-static struct mem_cgroup *
-mem_cgroup_get_next_node(struct mem_cgroup *root_mem)
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
-	struct cgroup *cgroup;
-	struct mem_cgroup *orig, *next;
-	bool obsolete;
-
+	struct cgroup *task_cgrp;
+	struct cgroup *mem_cgrp;
 	/*
-	 * Scan all children under the mem_cgroup mem
+	 * Need a buffer in BSS, can't rely on allocations. The code relies
+	 * on the assumption that OOM is serialized for memory controller.
+	 * If this assumption is broken, revisit this code.
 	 */
-	mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);
+	static char memcg_name[PATH_MAX];
+	int ret;
+
+	if (!memcg)
+		return;
+
+
+	rcu_read_lock();
 
-	orig = root_mem->last_scanned_child;
-	obsolete = mem_cgroup_is_obsolete(orig);
+	mem_cgrp = memcg->css.cgroup;
+	task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
 
-	if (list_empty(&root_mem->css.cgroup->children)) {
+	ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
+	if (ret < 0) {
 		/*
-		 * root_mem might have children before and last_scanned_child
-		 * may point to one of them. We put it later.
+		 * Unfortunately, we are unable to convert to a useful name
+		 * But we'll still print out the usage information
 		 */
-		if (orig)
-			VM_BUG_ON(!obsolete);
-		next = NULL;
+		rcu_read_unlock();
 		goto done;
 	}
+	rcu_read_unlock();
 
-	if (!orig || obsolete) {
-		cgroup = list_first_entry(&root_mem->css.cgroup->children,
-				struct cgroup, sibling);
-		next = mem_cgroup_from_cont(cgroup);
-	} else
-		next = __mem_cgroup_get_next_node(orig, root_mem);
+	printk(KERN_INFO "Task in %s killed", memcg_name);
+
+	rcu_read_lock();
+	ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
+	if (ret < 0) {
+		rcu_read_unlock();
+		goto done;
+	}
+	rcu_read_unlock();
 
+	/*
+	 * Continues from above, so we don't need an KERN_ level
+	 */
+	printk(KERN_CONT " as a result of limit of %s\n", memcg_name);
 done:
-	if (next)
-		mem_cgroup_get(next);
-	root_mem->last_scanned_child = next;
-	if (orig)
-		mem_cgroup_put(orig);
-	mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
-	return (next) ? next : root_mem;
+
+	printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n",
+		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
+		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
+		res_counter_read_u64(&memcg->res, RES_FAILCNT));
+	printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, "
+		"failcnt %llu\n",
+		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
+		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
+		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
 }
 
-static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
+/*
+ * This function returns the number of memcg under hierarchy tree. Returns
+ * 1(self count) if no children.
+ */
+static int mem_cgroup_count_children(struct mem_cgroup *mem)
 {
-	if (do_swap_account) {
-		if (res_counter_check_under_limit(&mem->res) &&
-			res_counter_check_under_limit(&mem->memsw))
-			return true;
-	} else
-		if (res_counter_check_under_limit(&mem->res))
-			return true;
-	return false;
+	int num = 0;
+ 	mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb);
+	return num;
 }
 
-static unsigned int get_swappiness(struct mem_cgroup *memcg)
+/*
+ * Visit the first child (need not be the first child as per the ordering
+ * of the cgroup list, since we track last_scanned_child) of @mem and use
+ * that to reclaim free pages from.
+ */
+static struct mem_cgroup *
+mem_cgroup_select_victim(struct mem_cgroup *root_mem)
 {
-	struct cgroup *cgrp = memcg->css.cgroup;
-	unsigned int swappiness;
+	struct mem_cgroup *ret = NULL;
+	struct cgroup_subsys_state *css;
+	int nextid, found;
 
-	/* root ? */
-	if (cgrp->parent == NULL)
-		return vm_swappiness;
+	if (!root_mem->use_hierarchy) {
+		css_get(&root_mem->css);
+		ret = root_mem;
+	}
 
-	spin_lock(&memcg->reclaim_param_lock);
-	swappiness = memcg->swappiness;
-	spin_unlock(&memcg->reclaim_param_lock);
+	while (!ret) {
+		rcu_read_lock();
+		nextid = root_mem->last_scanned_child + 1;
+		css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css,
+				   &found);
+		if (css && css_tryget(css))
+			ret = container_of(css, struct mem_cgroup, css);
+
+		rcu_read_unlock();
+		/* Updates scanning parameter */
+		spin_lock(&root_mem->reclaim_param_lock);
+		if (!css) {
+			/* this means start scan from ID:1 */
+			root_mem->last_scanned_child = 0;
+		} else
+			root_mem->last_scanned_child = found;
+		spin_unlock(&root_mem->reclaim_param_lock);
+	}
 
-	return swappiness;
+	return ret;
 }
 
 /*
- * Dance down the hierarchy if needed to reclaim memory. We remember the
- * last child we reclaimed from, so that we don't end up penalizing
- * one child extensively based on its position in the children list.
+ * Scan the hierarchy if needed to reclaim memory. We remember the last child
+ * we reclaimed from, so that we don't end up penalizing one child extensively
+ * based on its position in the children list.
  *
  * root_mem is the original ancestor that we've been reclaim from.
+ *
+ * We give up and return to the caller when we visit root_mem twice.
+ * (other groups can be removed while we're walking....)
+ *
+ * If shrink==true, for avoiding to free too much, this returns immedieately.
  */
 static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
-						gfp_t gfp_mask, bool noswap)
-{
-	struct mem_cgroup *next_mem;
-	int ret = 0;
-
-	/*
-	 * Reclaim unconditionally and don't check for return value.
-	 * We need to reclaim in the current group and down the tree.
-	 * One might think about checking for children before reclaiming,
-	 * but there might be left over accounting, even after children
-	 * have left.
-	 */
-	ret += try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap,
-					   get_swappiness(root_mem));
-	if (mem_cgroup_check_under_limit(root_mem))
-		return 1;	/* indicate reclaim has succeeded */
-	if (!root_mem->use_hierarchy)
-		return ret;
-
-	next_mem = mem_cgroup_get_next_node(root_mem);
-
-	while (next_mem != root_mem) {
-		if (mem_cgroup_is_obsolete(next_mem)) {
-			next_mem = mem_cgroup_get_next_node(root_mem);
+				   gfp_t gfp_mask, bool noswap, bool shrink)
+{
+	struct mem_cgroup *victim;
+	int ret, total = 0;
+	int loop = 0;
+
+	while (loop < 2) {
+		victim = mem_cgroup_select_victim(root_mem);
+		if (victim == root_mem)
+			loop++;
+		if (!mem_cgroup_local_usage(&victim->stat)) {
+			/* this cgroup's local usage == 0 */
+			css_put(&victim->css);
 			continue;
 		}
-		ret += try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap,
-						   get_swappiness(next_mem));
+		/* we use swappiness of local cgroup */
+		ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap,
+						   get_swappiness(victim));
+		css_put(&victim->css);
+		/*
+		 * At shrinking usage, we can't check we should stop here or
+		 * reclaim more. It's depends on callers. last_scanned_child
+		 * will work enough for keeping fairness under tree.
+		 */
+		if (shrink)
+			return ret;
+		total += ret;
 		if (mem_cgroup_check_under_limit(root_mem))
-			return 1;	/* indicate reclaim has succeeded */
-		next_mem = mem_cgroup_get_next_node(root_mem);
+			return 1 + total;
 	}
-	return ret;
+	return total;
 }
 
 bool mem_cgroup_oom_called(struct task_struct *task)
@@ -813,6 +885,19 @@ bool mem_cgroup_oom_called(struct task_struct *task)
 	rcu_read_unlock();
 	return ret;
 }
+
+static int record_last_oom_cb(struct mem_cgroup *mem, void *data)
+{
+	mem->last_oom_jiffies = jiffies;
+	return 0;
+}
+
+static void record_last_oom(struct mem_cgroup *mem)
+{
+	mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
+}
+
+
 /*
  * Unlike exported interface, "oom" parameter is added. if oom==true,
  * oom-killer can be invoked.
@@ -847,7 +932,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	if (unlikely(!mem))
 		return 0;
 
-	VM_BUG_ON(mem_cgroup_is_obsolete(mem));
+	VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem));
 
 	while (1) {
 		int ret;
@@ -875,7 +960,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 			goto nomem;
 
 		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
-							noswap);
+							noswap, false);
 		if (ret)
 			continue;
 
@@ -895,7 +980,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 				mutex_lock(&memcg_tasklist);
 				mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
 				mutex_unlock(&memcg_tasklist);
-				mem_over_limit->last_oom_jiffies = jiffies;
+				record_last_oom(mem_over_limit);
 			}
 			goto nomem;
 		}
@@ -906,20 +991,54 @@ nomem:
 	return -ENOMEM;
 }
 
+
+/*
+ * A helper function to get mem_cgroup from ID. must be called under
+ * rcu_read_lock(). The caller must check css_is_removed() or some if
+ * it's concern. (dropping refcnt from swap can be called against removed
+ * memcg.)
+ */
+static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
+{
+	struct cgroup_subsys_state *css;
+
+	/* ID 0 is unused ID */
+	if (!id)
+		return NULL;
+	css = css_lookup(&mem_cgroup_subsys, id);
+	if (!css)
+		return NULL;
+	return container_of(css, struct mem_cgroup, css);
+}
+
 static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 {
 	struct mem_cgroup *mem;
+	struct page_cgroup *pc;
+	unsigned short id;
 	swp_entry_t ent;
 
+	VM_BUG_ON(!PageLocked(page));
+
 	if (!PageSwapCache(page))
 		return NULL;
 
-	ent.val = page_private(page);
-	mem = lookup_swap_cgroup(ent);
-	if (!mem)
-		return NULL;
-	if (!css_tryget(&mem->css))
-		return NULL;
+	pc = lookup_page_cgroup(page);
+	lock_page_cgroup(pc);
+	if (PageCgroupUsed(pc)) {
+		mem = pc->mem_cgroup;
+		if (mem && !css_tryget(&mem->css))
+			mem = NULL;
+	} else {
+		ent.val = page_private(page);
+		id = lookup_swap_cgroup(ent);
+		rcu_read_lock();
+		mem = mem_cgroup_lookup(id);
+		if (mem && !css_tryget(&mem->css))
+			mem = NULL;
+		rcu_read_unlock();
+	}
+	unlock_page_cgroup(pc);
 	return mem;
 }
 
@@ -1118,6 +1237,10 @@ int mem_cgroup_newpage_charge(struct page *page,
 				MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
 }
 
+static void
+__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
+					enum charge_type ctype);
+
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
@@ -1154,16 +1277,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		unlock_page_cgroup(pc);
 	}
 
-	if (do_swap_account && PageSwapCache(page)) {
-		mem = try_get_mem_cgroup_from_swapcache(page);
-		if (mem)
-			mm = NULL;
-		  else
-			mem = NULL;
-		/* SwapCache may be still linked to LRU now. */
-		mem_cgroup_lru_del_before_commit_swapcache(page);
-	}
-
 	if (unlikely(!mm && !mem))
 		mm = &init_mm;
 
@@ -1171,22 +1284,16 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		return mem_cgroup_charge_common(page, mm, gfp_mask,
 				MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
 
-	ret = mem_cgroup_charge_common(page, mm, gfp_mask,
-				MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
-	if (mem)
-		css_put(&mem->css);
-	if (PageSwapCache(page))
-		mem_cgroup_lru_add_after_commit_swapcache(page);
+	/* shmem */
+	if (PageSwapCache(page)) {
+		ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
+		if (!ret)
+			__mem_cgroup_commit_charge_swapin(page, mem,
+					MEM_CGROUP_CHARGE_TYPE_SHMEM);
+	} else
+		ret = mem_cgroup_charge_common(page, mm, gfp_mask,
+					MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
 
-	if (do_swap_account && !ret && PageSwapCache(page)) {
-		swp_entry_t ent = {.val = page_private(page)};
-		/* avoid double counting */
-		mem = swap_cgroup_record(ent, NULL);
-		if (mem) {
-			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
-			mem_cgroup_put(mem);
-		}
-	}
 	return ret;
 }
 
@@ -1229,7 +1336,9 @@ charge_cur_mm:
 	return __mem_cgroup_try_charge(mm, mask, ptr, true);
 }
 
-void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+static void
+__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
+					enum charge_type ctype)
 {
 	struct page_cgroup *pc;
 
@@ -1239,7 +1348,7 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
 		return;
 	pc = lookup_page_cgroup(page);
 	mem_cgroup_lru_del_before_commit_swapcache(page);
-	__mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+	__mem_cgroup_commit_charge(ptr, pc, ctype);
 	mem_cgroup_lru_add_after_commit_swapcache(page);
 	/*
 	 * Now swap is on-memory. This means this page may be
@@ -1250,18 +1359,32 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
 	 */
 	if (do_swap_account && PageSwapCache(page)) {
 		swp_entry_t ent = {.val = page_private(page)};
+		unsigned short id;
 		struct mem_cgroup *memcg;
-		memcg = swap_cgroup_record(ent, NULL);
+
+		id = swap_cgroup_record(ent, 0);
+		rcu_read_lock();
+		memcg = mem_cgroup_lookup(id);
 		if (memcg) {
+			/*
+			 * This recorded memcg can be obsolete one. So, avoid
+			 * calling css_tryget
+			 */
 			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 			mem_cgroup_put(memcg);
 		}
-
+		rcu_read_unlock();
 	}
 	/* add this page(page_cgroup) to the LRU we want. */
 
 }
 
+void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+{
+	__mem_cgroup_commit_charge_swapin(page, ptr,
+					MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
+
 void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
 {
 	if (mem_cgroup_disabled())
@@ -1324,8 +1447,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	res_counter_uncharge(&mem->res, PAGE_SIZE);
 	if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
 		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
-
 	mem_cgroup_charge_statistics(mem, pc, false);
+
 	ClearPageCgroupUsed(pc);
 	/*
 	 * pc->mem_cgroup is not cleared here. It will be accessed when it's
@@ -1377,7 +1500,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 					MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
 	/* record memcg information */
 	if (do_swap_account && memcg) {
-		swap_cgroup_record(ent, memcg);
+		swap_cgroup_record(ent, css_id(&memcg->css));
 		mem_cgroup_get(memcg);
 	}
 	if (memcg)
@@ -1392,15 +1515,23 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 void mem_cgroup_uncharge_swap(swp_entry_t ent)
 {
 	struct mem_cgroup *memcg;
+	unsigned short id;
 
 	if (!do_swap_account)
 		return;
 
-	memcg = swap_cgroup_record(ent, NULL);
+	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
+		 */
 		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 		mem_cgroup_put(memcg);
 	}
+	rcu_read_unlock();
 }
 #endif
 
@@ -1486,36 +1617,28 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
 }
 
 /*
- * A call to try to shrink memory usage under specified resource controller.
- * This is typically used for page reclaiming for shmem for reducing side
- * effect of page allocation from shmem, which is used by some mem_cgroup.
+ * A call to try to shrink memory usage on charge failure at shmem's swapin.
+ * Calling hierarchical_reclaim is not enough because we should update
+ * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM.
+ * Moreover considering hierarchy, we should reclaim from the mem_over_limit,
+ * not from the memcg which this page would be charged to.
+ * try_charge_swapin does all of these works properly.
  */
-int mem_cgroup_shrink_usage(struct page *page,
+int mem_cgroup_shmem_charge_fallback(struct page *page,
 			    struct mm_struct *mm,
 			    gfp_t gfp_mask)
 {
 	struct mem_cgroup *mem = NULL;
-	int progress = 0;
-	int retry = MEM_CGROUP_RECLAIM_RETRIES;
+	int ret;
 
 	if (mem_cgroup_disabled())
 		return 0;
-	if (page)
-		mem = try_get_mem_cgroup_from_swapcache(page);
-	if (!mem && mm)
-		mem = try_get_mem_cgroup_from_mm(mm);
-	if (unlikely(!mem))
-		return 0;
 
-	do {
-		progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
-		progress += mem_cgroup_check_under_limit(mem);
-	} while (!progress && --retry);
+	ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
+	if (!ret)
+		mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */
 
-	css_put(&mem->css);
-	if (!retry)
-		return -ENOMEM;
-	return 0;
+	return ret;
 }
 
 static DEFINE_MUTEX(set_limit_mutex);
@@ -1523,11 +1646,21 @@ static DEFINE_MUTEX(set_limit_mutex);
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
-
-	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	int retry_count;
 	int progress;
 	u64 memswlimit;
 	int ret = 0;
+	int children = mem_cgroup_count_children(memcg);
+	u64 curusage, oldusage;
+
+	/*
+	 * For keeping hierarchical_reclaim simple, how long we should retry
+	 * is depends on callers. We set our retry-count to be function
+	 * of # of children which we should visit in this loop.
+	 */
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;
+
+	oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 
 	while (retry_count) {
 		if (signal_pending(current)) {
@@ -1553,8 +1686,13 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 			break;
 
 		progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
-							   false);
-  		if (!progress)			retry_count--;
+						   false, true);
+		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+		/* Usage is reduced ? */
+  		if (curusage >= oldusage)
+			retry_count--;
+		else
+			oldusage = curusage;
 	}
 
 	return ret;
@@ -1563,13 +1701,16 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
-	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	int retry_count;
 	u64 memlimit, oldusage, curusage;
-	int ret;
+	int children = mem_cgroup_count_children(memcg);
+	int ret = -EBUSY;
 
 	if (!do_swap_account)
 		return -EINVAL;
-
+	/* see mem_cgroup_resize_res_limit */
+ 	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
+	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 	while (retry_count) {
 		if (signal_pending(current)) {
 			ret = -EINTR;
@@ -1593,11 +1734,13 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
-		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true);
+		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true, true);
 		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
+		else
+			oldusage = curusage;
 	}
 	return ret;
 }
@@ -1893,54 +2036,90 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 	return 0;
 }
 
-static const struct mem_cgroup_stat_desc {
-	const char *msg;
-	u64 unit;
-} mem_cgroup_stat_desc[] = {
-	[MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
-	[MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
-	[MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
-	[MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
+
+/* For read statistics */
+enum {
+	MCS_CACHE,
+	MCS_RSS,
+	MCS_PGPGIN,
+	MCS_PGPGOUT,
+	MCS_INACTIVE_ANON,
+	MCS_ACTIVE_ANON,
+	MCS_INACTIVE_FILE,
+	MCS_ACTIVE_FILE,
+	MCS_UNEVICTABLE,
+	NR_MCS_STAT,
+};
+
+struct mcs_total_stat {
+	s64 stat[NR_MCS_STAT];
+};
+
+struct {
+	char *local_name;
+	char *total_name;
+} memcg_stat_strings[NR_MCS_STAT] = {
+	{"cache", "total_cache"},
+	{"rss", "total_rss"},
+	{"pgpgin", "total_pgpgin"},
+	{"pgpgout", "total_pgpgout"},
+	{"inactive_anon", "total_inactive_anon"},
+	{"active_anon", "total_active_anon"},
+	{"inactive_file", "total_inactive_file"},
+	{"active_file", "total_active_file"},
+	{"unevictable", "total_unevictable"}
 };
 
+
+static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
+{
+	struct mcs_total_stat *s = data;
+	s64 val;
+
+	/* per cpu stat */
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_CACHE);
+	s->stat[MCS_CACHE] += val * PAGE_SIZE;
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
+	s->stat[MCS_RSS] += val * PAGE_SIZE;
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT);
+	s->stat[MCS_PGPGIN] += val;
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
+	s->stat[MCS_PGPGOUT] += val;
+
+	/* per zone stat */
+	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON);
+	s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON);
+	s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE);
+	s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE);
+	s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE);
+	s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE;
+	return 0;
+}
+
+static void
+mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
+{
+	mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat);
+}
+
 static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 				 struct cgroup_map_cb *cb)
 {
 	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
-	struct mem_cgroup_stat *stat = &mem_cont->stat;
+	struct mcs_total_stat mystat;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) {
-		s64 val;
+	memset(&mystat, 0, sizeof(mystat));
+	mem_cgroup_get_local_stat(mem_cont, &mystat);
 
-		val = mem_cgroup_read_stat(stat, i);
-		val *= mem_cgroup_stat_desc[i].unit;
-		cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
-	}
-	/* showing # of active pages */
-	{
-		unsigned long active_anon, inactive_anon;
-		unsigned long active_file, inactive_file;
-		unsigned long unevictable;
-
-		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_INACTIVE_ANON);
-		active_anon = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_ACTIVE_ANON);
-		inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_INACTIVE_FILE);
-		active_file = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_ACTIVE_FILE);
-		unevictable = mem_cgroup_get_all_zonestat(mem_cont,
-							LRU_UNEVICTABLE);
-
-		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
-		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
-		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
-		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
-		cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);
+	for (i = 0; i < NR_MCS_STAT; i++)
+		cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]);
 
-	}
+	/* Hierarchical information */
 	{
 		unsigned long long limit, memsw_limit;
 		memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
@@ -1949,6 +2128,12 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 			cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
 	}
 
+	memset(&mystat, 0, sizeof(mystat));
+	mem_cgroup_get_total_stat(mem_cont, &mystat);
+	for (i = 0; i < NR_MCS_STAT; i++)
+		cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]);
+
+
 #ifdef CONFIG_DEBUG_VM
 	cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
 
@@ -2178,6 +2363,8 @@ static void __mem_cgroup_free(struct mem_cgroup *mem)
 {
 	int node;
 
+	free_css_id(&mem_cgroup_subsys, &mem->css);
+
 	for_each_node_state(node, N_POSSIBLE)
 		free_mem_cgroup_per_zone_info(mem, node);
 
@@ -2228,11 +2415,12 @@ static struct cgroup_subsys_state * __ref
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	struct mem_cgroup *mem, *parent;
+	long error = -ENOMEM;
 	int node;
 
 	mem = mem_cgroup_alloc();
 	if (!mem)
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(error);
 
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
@@ -2260,7 +2448,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 		res_counter_init(&mem->res, NULL);
 		res_counter_init(&mem->memsw, NULL);
 	}
-	mem->last_scanned_child = NULL;
+	mem->last_scanned_child = 0;
 	spin_lock_init(&mem->reclaim_param_lock);
 
 	if (parent)
@@ -2269,26 +2457,22 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	return &mem->css;
 free_out:
 	__mem_cgroup_free(mem);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(error);
 }
 
-static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
+static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
 					struct cgroup *cont)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	mem_cgroup_force_empty(mem, false);
+
+	return mem_cgroup_force_empty(mem, false);
 }
 
 static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	struct mem_cgroup *last_scanned_child = mem->last_scanned_child;
 
-	if (last_scanned_child) {
-		VM_BUG_ON(!mem_cgroup_is_obsolete(last_scanned_child));
-		mem_cgroup_put(last_scanned_child);
-	}
 	mem_cgroup_put(mem);
 }
 
@@ -2327,6 +2511,7 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.populate = mem_cgroup_populate,
 	.attach = mem_cgroup_move_task,
 	.early_init = 0,
+	.use_id = 1,
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
diff --git a/mm/memory.c b/mm/memory.c
index baa999e87cd2..4126dd16778c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1151,6 +1151,11 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		if ((flags & FOLL_WRITE) &&
 		    !pte_dirty(pte) && !PageDirty(page))
 			set_page_dirty(page);
+		/*
+		 * pte_mkyoung() would be more correct here, but atomic care
+		 * is needed to avoid losing the dirty bit: it is easier to use
+		 * mark_page_accessed().
+		 */
 		mark_page_accessed(page);
 	}
 unlock:
@@ -1665,9 +1670,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	 * behaviour that some programs depend on. We mark the "original"
 	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
 	 */
-	if (addr == vma->vm_start && end == vma->vm_end)
+	if (addr == vma->vm_start && end == vma->vm_end) {
 		vma->vm_pgoff = pfn;
-	else if (is_cow_mapping(vma->vm_flags))
+		vma->vm_flags |= VM_PFN_AT_MMAP;
+	} else if (is_cow_mapping(vma->vm_flags))
 		return -EINVAL;
 
 	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
@@ -1679,6 +1685,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		 * needed from higher level routine calling unmap_vmas
 		 */
 		vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
+		vma->vm_flags &= ~VM_PFN_AT_MMAP;
 		return -EINVAL;
 	}
 
@@ -1938,6 +1945,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * get_user_pages(.write=1, .force=1).
 		 */
 		if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
+			struct vm_fault vmf;
+			int tmp;
+
+			vmf.virtual_address = (void __user *)(address &
+								PAGE_MASK);
+			vmf.pgoff = old_page->index;
+			vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+			vmf.page = old_page;
+
 			/*
 			 * Notify the address space that the page is about to
 			 * become writable so that it can prohibit this or wait
@@ -1949,8 +1965,21 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			page_cache_get(old_page);
 			pte_unmap_unlock(page_table, ptl);
 
-			if (vma->vm_ops->page_mkwrite(vma, old_page) < 0)
+			tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
+			if (unlikely(tmp &
+					(VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
+				ret = tmp;
 				goto unwritable_page;
+			}
+			if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
+				lock_page(old_page);
+				if (!old_page->mapping) {
+					ret = 0; /* retry the fault */
+					unlock_page(old_page);
+					goto unwritable_page;
+				}
+			} else
+				VM_BUG_ON(!PageLocked(old_page));
 
 			/*
 			 * Since we dropped the lock we need to revalidate
@@ -1960,9 +1989,11 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 */
 			page_table = pte_offset_map_lock(mm, pmd, address,
 							 &ptl);
-			page_cache_release(old_page);
-			if (!pte_same(*page_table, orig_pte))
+			if (!pte_same(*page_table, orig_pte)) {
+				unlock_page(old_page);
+				page_cache_release(old_page);
 				goto unlock;
+			}
 
 			page_mkwrite = 1;
 		}
@@ -2074,9 +2105,6 @@ gotten:
 unlock:
 	pte_unmap_unlock(page_table, ptl);
 	if (dirty_page) {
-		if (vma->vm_file)
-			file_update_time(vma->vm_file);
-
 		/*
 		 * Yes, Virginia, this is actually required to prevent a race
 		 * with clear_page_dirty_for_io() from clearing the page dirty
@@ -2085,21 +2113,46 @@ unlock:
 		 *
 		 * do_no_page is protected similarly.
 		 */
-		wait_on_page_locked(dirty_page);
-		set_page_dirty_balance(dirty_page, page_mkwrite);
+		if (!page_mkwrite) {
+			wait_on_page_locked(dirty_page);
+			set_page_dirty_balance(dirty_page, page_mkwrite);
+		}
 		put_page(dirty_page);
+		if (page_mkwrite) {
+			struct address_space *mapping = dirty_page->mapping;
+
+			set_page_dirty(dirty_page);
+			unlock_page(dirty_page);
+			page_cache_release(dirty_page);
+			if (mapping)	{
+				/*
+				 * Some device drivers do not set page.mapping
+				 * but still dirty their pages
+				 */
+				balance_dirty_pages_ratelimited(mapping);
+			}
+		}
+
+		/* file_update_time outside page_lock */
+		if (vma->vm_file)
+			file_update_time(vma->vm_file);
 	}
 	return ret;
 oom_free_new:
 	page_cache_release(new_page);
 oom:
-	if (old_page)
+	if (old_page) {
+		if (page_mkwrite) {
+			unlock_page(old_page);
+			page_cache_release(old_page);
+		}
 		page_cache_release(old_page);
+	}
 	return VM_FAULT_OOM;
 
 unwritable_page:
 	page_cache_release(old_page);
-	return VM_FAULT_SIGBUS;
+	return ret;
 }
 
 /*
@@ -2433,15 +2486,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(PGMAJFAULT);
 	}
 
-	mark_page_accessed(page);
-
 	lock_page(page);
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 
 	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
 		ret = VM_FAULT_OOM;
-		unlock_page(page);
-		goto out;
+		goto out_page;
 	}
 
 	/*
@@ -2503,6 +2553,7 @@ out:
 out_nomap:
 	mem_cgroup_cancel_charge_swapin(ptr);
 	pte_unmap_unlock(page_table, ptl);
+out_page:
 	unlock_page(page);
 	page_cache_release(page);
 	return ret;
@@ -2643,25 +2694,25 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			 * to become writable
 			 */
 			if (vma->vm_ops->page_mkwrite) {
+				int tmp;
+
 				unlock_page(page);
-				if (vma->vm_ops->page_mkwrite(vma, page) < 0) {
-					ret = VM_FAULT_SIGBUS;
-					anon = 1; /* no anon but release vmf.page */
-					goto out_unlocked;
-				}
-				lock_page(page);
-				/*
-				 * XXX: this is not quite right (racy vs
-				 * invalidate) to unlock and relock the page
-				 * like this, however a better fix requires
-				 * reworking page_mkwrite locking API, which
-				 * is better done later.
-				 */
-				if (!page->mapping) {
-					ret = 0;
-					anon = 1; /* no anon but release vmf.page */
-					goto out;
+				vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+				tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
+				if (unlikely(tmp &
+					  (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
+					ret = tmp;
+					goto unwritable_page;
 				}
+				if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
+					lock_page(page);
+					if (!page->mapping) {
+						ret = 0; /* retry the fault */
+						unlock_page(page);
+						goto unwritable_page;
+					}
+				} else
+					VM_BUG_ON(!PageLocked(page));
 				page_mkwrite = 1;
 			}
 		}
@@ -2713,19 +2764,35 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_unmap_unlock(page_table, ptl);
 
 out:
-	unlock_page(vmf.page);
-out_unlocked:
-	if (anon)
-		page_cache_release(vmf.page);
-	else if (dirty_page) {
-		if (vma->vm_file)
-			file_update_time(vma->vm_file);
+	if (dirty_page) {
+		struct address_space *mapping = page->mapping;
 
-		set_page_dirty_balance(dirty_page, page_mkwrite);
+		if (set_page_dirty(dirty_page))
+			page_mkwrite = 1;
+		unlock_page(dirty_page);
 		put_page(dirty_page);
+		if (page_mkwrite && mapping) {
+			/*
+			 * Some device drivers do not set page.mapping but still
+			 * dirty their pages
+			 */
+			balance_dirty_pages_ratelimited(mapping);
+		}
+
+		/* file_update_time outside page_lock */
+		if (vma->vm_file)
+			file_update_time(vma->vm_file);
+	} else {
+		unlock_page(vmf.page);
+		if (anon)
+			page_cache_release(vmf.page);
 	}
 
 	return ret;
+
+unwritable_page:
+	page_cache_release(page);
+	return ret;
 }
 
 static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
diff --git a/mm/migrate.c b/mm/migrate.c
index a9eff3f092f6..068655d8f883 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -250,7 +250,7 @@ out:
  * The number of remaining references must be:
  * 1 for anonymous pages without a mapping
  * 2 for pages with a mapping
- * 3 for pages with a mapping and PagePrivate set.
+ * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
 static int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page)
@@ -270,7 +270,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	pslot = radix_tree_lookup_slot(&mapping->page_tree,
  					page_index(page));
 
-	expected_count = 2 + !!PagePrivate(page);
+	expected_count = 2 + !!page_has_private(page);
 	if (page_count(page) != expected_count ||
 			(struct page *)radix_tree_deref_slot(pslot) != page) {
 		spin_unlock_irq(&mapping->tree_lock);
@@ -386,7 +386,7 @@ EXPORT_SYMBOL(fail_migrate_page);
 
 /*
  * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
+ * pages that do not use PagePrivate/PagePrivate2.
  *
  * Pages are locked upon entry and exit.
  */
@@ -522,7 +522,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	 * Buffers may be managed in a filesystem specific way.
 	 * We must have no buffers or drop them.
 	 */
-	if (PagePrivate(page) &&
+	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
@@ -655,7 +655,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	 * free the metadata, so the page can be freed.
 	 */
 	if (!page->mapping) {
-		if (!PageAnon(page) && PagePrivate(page)) {
+		if (!PageAnon(page) && page_has_private(page)) {
 			/*
 			 * Go direct to try_to_free_buffers() here because
 			 * a) that's what try_to_release_page() would do anyway
diff --git a/mm/mmap.c b/mm/mmap.c
index 1abb9185a686..6b7b1a95944b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL(vm_get_page_prot);
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50;	/* default is 50% */
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
 
 /*
  * Check that a process has enough memory to allocate a new virtual
@@ -179,11 +179,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 	if (mm)
 		allowed -= mm->total_vm / 32;
 
-	/*
-	 * cast `allowed' as a signed long because vm_committed_space
-	 * sometimes has a negative value
-	 */
-	if (atomic_long_read(&vm_committed_space) < (long)allowed)
+	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
 		return 0;
 error:
 	vm_unacct_memory(pages);
@@ -1575,7 +1571,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 	 * Overcommit..  This must be the final test, as it will
 	 * update security statistics.
 	 */
-	if (security_vm_enough_memory(grow))
+	if (security_vm_enough_memory_mm(mm, grow))
 		return -ENOMEM;
 
 	/* Ok, everything looks good - let it rip */
@@ -2481,7 +2477,8 @@ void mm_drop_all_locks(struct mm_struct *mm)
  */
 void __init mmap_init(void)
 {
-	vm_area_cachep = kmem_cache_create("vm_area_struct",
-			sizeof(struct vm_area_struct), 0,
-			SLAB_PANIC, NULL);
+	int ret;
+
+	ret = percpu_counter_init(&vm_committed_as, 0);
+	VM_BUG_ON(ret);
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index 2fcf47d449b4..b571ef707428 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -62,14 +62,14 @@ void *high_memory;
 struct page *mem_map;
 unsigned long max_mapnr;
 unsigned long num_physpages;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50; /* default is 50% */
 int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
-int sysctl_nr_trim_pages = 1; /* page trimming behaviour */
+int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 int heap_stack_gap = 0;
 
-atomic_t mmap_pages_allocated;
+atomic_long_t mmap_pages_allocated;
 
 EXPORT_SYMBOL(mem_map);
 EXPORT_SYMBOL(num_physpages);
@@ -463,12 +463,11 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
  */
 void __init mmap_init(void)
 {
-	vm_region_jar = kmem_cache_create("vm_region_jar",
-					  sizeof(struct vm_region), 0,
-					  SLAB_PANIC, NULL);
-	vm_area_cachep = kmem_cache_create("vm_area_struct",
-					   sizeof(struct vm_area_struct), 0,
-					   SLAB_PANIC, NULL);
+	int ret;
+
+	ret = percpu_counter_init(&vm_committed_as, 0);
+	VM_BUG_ON(ret);
+	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
 }
 
 /*
@@ -486,27 +485,24 @@ static noinline void validate_nommu_regions(void)
 		return;
 
 	last = rb_entry(lastp, struct vm_region, vm_rb);
-	if (unlikely(last->vm_end <= last->vm_start))
-		BUG();
-	if (unlikely(last->vm_top < last->vm_end))
-		BUG();
+	BUG_ON(unlikely(last->vm_end <= last->vm_start));
+	BUG_ON(unlikely(last->vm_top < last->vm_end));
 
 	while ((p = rb_next(lastp))) {
 		region = rb_entry(p, struct vm_region, vm_rb);
 		last = rb_entry(lastp, struct vm_region, vm_rb);
 
-		if (unlikely(region->vm_end <= region->vm_start))
-			BUG();
-		if (unlikely(region->vm_top < region->vm_end))
-			BUG();
-		if (unlikely(region->vm_start < last->vm_top))
-			BUG();
+		BUG_ON(unlikely(region->vm_end <= region->vm_start));
+		BUG_ON(unlikely(region->vm_top < region->vm_end));
+		BUG_ON(unlikely(region->vm_start < last->vm_top));
 
 		lastp = p;
 	}
 }
 #else
-#define validate_nommu_regions() do {} while(0)
+static void validate_nommu_regions(void)
+{
+}
 #endif
 
 /*
@@ -519,8 +515,6 @@ static void add_nommu_region(struct vm_region *region)
 
 	validate_nommu_regions();
 
-	BUG_ON(region->vm_start & ~PAGE_MASK);
-
 	parent = NULL;
 	p = &nommu_region_tree.rb_node;
 	while (*p) {
@@ -563,16 +557,17 @@ static void free_page_series(unsigned long from, unsigned long to)
 		struct page *page = virt_to_page(from);
 
 		kdebug("- free %lx", from);
-		atomic_dec(&mmap_pages_allocated);
+		atomic_long_dec(&mmap_pages_allocated);
 		if (page_count(page) != 1)
-			kdebug("free page %p [%d]", page, page_count(page));
+			kdebug("free page %p: refcount not one: %d",
+			       page, page_count(page));
 		put_page(page);
 	}
 }
 
 /*
  * release a reference to a region
- * - the caller must hold the region semaphore, which this releases
+ * - the caller must hold the region semaphore for writing, which this releases
  * - the region may not have been added to the tree yet, in which case vm_top
  *   will equal vm_start
  */
@@ -1096,7 +1091,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 		goto enomem;
 
 	total = 1 << order;
-	atomic_add(total, &mmap_pages_allocated);
+	atomic_long_add(total, &mmap_pages_allocated);
 
 	point = rlen >> PAGE_SHIFT;
 
@@ -1107,7 +1102,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 			order = ilog2(total - point);
 			n = 1 << order;
 			kdebug("shave %lu/%lu @%lu", n, total - point, total);
-			atomic_sub(n, &mmap_pages_allocated);
+			atomic_long_sub(n, &mmap_pages_allocated);
 			total -= n;
 			set_page_refcounted(pages + total);
 			__free_pages(pages + total, order);
@@ -1536,10 +1531,15 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	/* find the first potentially overlapping VMA */
 	vma = find_vma(mm, start);
 	if (!vma) {
-		printk(KERN_WARNING
-		       "munmap of memory not mmapped by process %d (%s):"
-		       " 0x%lx-0x%lx\n",
-		       current->pid, current->comm, start, start + len - 1);
+		static int limit = 0;
+		if (limit < 5) {
+			printk(KERN_WARNING
+			       "munmap of memory not mmapped by process %d"
+			       " (%s): 0x%lx-0x%lx\n",
+			       current->pid, current->comm,
+			       start, start + len - 1);
+			limit++;
+		}
 		return -EINVAL;
 	}
 
@@ -1849,12 +1849,9 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 	if (mm)
 		allowed -= mm->total_vm / 32;
 
-	/*
-	 * cast `allowed' as a signed long because vm_committed_space
-	 * sometimes has a negative value
-	 */
-	if (atomic_long_read(&vm_committed_space) < (long)allowed)
+	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
 		return 0;
+
 error:
 	vm_unacct_memory(pages);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 40ba05061a4f..92bcf1db16b2 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -55,7 +55,7 @@ static DEFINE_SPINLOCK(zone_scan_lock);
 
 unsigned long badness(struct task_struct *p, unsigned long uptime)
 {
-	unsigned long points, cpu_time, run_time, s;
+	unsigned long points, cpu_time, run_time;
 	struct mm_struct *mm;
 	struct task_struct *child;
 
@@ -110,12 +110,10 @@ unsigned long badness(struct task_struct *p, unsigned long uptime)
 	else
 		run_time = 0;
 
-	s = int_sqrt(cpu_time);
-	if (s)
-		points /= s;
-	s = int_sqrt(int_sqrt(run_time));
-	if (s)
-		points /= s;
+	if (cpu_time)
+		points /= int_sqrt(cpu_time);
+	if (run_time)
+		points /= int_sqrt(int_sqrt(run_time));
 
 	/*
 	 * Niced processes are most likely less important, so double
@@ -396,6 +394,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 		cpuset_print_task_mems_allowed(current);
 		task_unlock(current);
 		dump_stack();
+		mem_cgroup_print_oom_info(mem, current);
 		show_mem();
 		if (sysctl_oom_dump_tasks)
 			dump_tasks(mem);
@@ -515,34 +514,32 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
  */
 static void __out_of_memory(gfp_t gfp_mask, int order)
 {
-	if (sysctl_oom_kill_allocating_task) {
-		oom_kill_process(current, gfp_mask, order, 0, NULL,
-				"Out of memory (oom_kill_allocating_task)");
-
-	} else {
-		unsigned long points;
-		struct task_struct *p;
-
-retry:
-		/*
-		 * Rambo mode: Shoot down a process and hope it solves whatever
-		 * issues we may have.
-		 */
-		p = select_bad_process(&points, NULL);
+	struct task_struct *p;
+	unsigned long points;
 
-		if (PTR_ERR(p) == -1UL)
+	if (sysctl_oom_kill_allocating_task)
+		if (!oom_kill_process(current, gfp_mask, order, 0, NULL,
+				"Out of memory (oom_kill_allocating_task)"))
 			return;
+retry:
+	/*
+	 * Rambo mode: Shoot down a process and hope it solves whatever
+	 * issues we may have.
+	 */
+	p = select_bad_process(&points, NULL);
 
-		/* Found nothing?!?! Either we hang forever, or we panic. */
-		if (!p) {
-			read_unlock(&tasklist_lock);
-			panic("Out of memory and no killable processes...\n");
-		}
+	if (PTR_ERR(p) == -1UL)
+		return;
 
-		if (oom_kill_process(p, gfp_mask, order, points, NULL,
-				     "Out of memory"))
-			goto retry;
+	/* Found nothing?!?! Either we hang forever, or we panic. */
+	if (!p) {
+		read_unlock(&tasklist_lock);
+		panic("Out of memory and no killable processes...\n");
 	}
+
+	if (oom_kill_process(p, gfp_mask, order, points, NULL,
+			     "Out of memory"))
+		goto retry;
 }
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 40ca7cdb653e..30351f0063ac 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -92,14 +92,14 @@ int vm_dirty_ratio = 20;
 unsigned long vm_dirty_bytes;
 
 /*
- * The interval between `kupdate'-style writebacks, in jiffies
+ * The interval between `kupdate'-style writebacks
  */
-int dirty_writeback_interval = 5 * HZ;
+unsigned int dirty_writeback_interval = 5 * 100; /* sentiseconds */
 
 /*
- * The longest number of jiffies for which data is allowed to remain dirty
+ * The longest time for which data is allowed to remain dirty
  */
-int dirty_expire_interval = 30 * HZ;
+unsigned int dirty_expire_interval = 30 * 100; /* sentiseconds */
 
 /*
  * Flag that makes the machine dump writes/reads and block dirtyings.
@@ -770,9 +770,9 @@ static void wb_kupdate(unsigned long arg)
 
 	sync_supers();
 
-	oldest_jif = jiffies - dirty_expire_interval;
+	oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval);
 	start_jif = jiffies;
-	next_jif = start_jif + dirty_writeback_interval;
+	next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10);
 	nr_to_write = global_page_state(NR_FILE_DIRTY) +
 			global_page_state(NR_UNSTABLE_NFS) +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
@@ -801,9 +801,10 @@ static void wb_kupdate(unsigned long arg)
 int dirty_writeback_centisecs_handler(ctl_table *table, int write,
 	struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
 {
-	proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
+	proc_dointvec(table, write, file, buffer, length, ppos);
 	if (dirty_writeback_interval)
-		mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
+		mod_timer(&wb_timer, jiffies +
+			msecs_to_jiffies(dirty_writeback_interval * 10));
 	else
 		del_timer(&wb_timer);
 	return 0;
@@ -905,7 +906,8 @@ void __init page_writeback_init(void)
 {
 	int shift;
 
-	mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
+	mod_timer(&wb_timer,
+		  jiffies + msecs_to_jiffies(dirty_writeback_interval * 10));
 	writeback_set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
 
@@ -1198,6 +1200,20 @@ int __set_page_dirty_no_writeback(struct page *page)
 }
 
 /*
+ * Helper function for set_page_dirty family.
+ * NOTE: This relies on being atomic wrt interrupts.
+ */
+void account_page_dirtied(struct page *page, struct address_space *mapping)
+{
+	if (mapping_cap_account_dirty(mapping)) {
+		__inc_zone_page_state(page, NR_FILE_DIRTY);
+		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
+		task_dirty_inc(current);
+		task_io_account_write(PAGE_CACHE_SIZE);
+	}
+}
+
+/*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in
  * its radix tree.
  *
@@ -1226,13 +1242,7 @@ int __set_page_dirty_nobuffers(struct page *page)
 		if (mapping2) { /* Race with truncate? */
 			BUG_ON(mapping2 != mapping);
 			WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page));
-			if (mapping_cap_account_dirty(mapping)) {
-				__inc_zone_page_state(page, NR_FILE_DIRTY);
-				__inc_bdi_stat(mapping->backing_dev_info,
-						BDI_RECLAIMABLE);
-				task_dirty_inc(current);
-				task_io_account_write(PAGE_CACHE_SIZE);
-			}
+			account_page_dirtied(page, mapping);
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5c44ed49ca93..fe753ecf2aa5 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -331,7 +331,7 @@ static int destroy_compound_page(struct page *page, unsigned long order)
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 
-		if (unlikely(!PageTail(p) | (p->first_page != page))) {
+		if (unlikely(!PageTail(p) || (p->first_page != page))) {
 			bad_page(page);
 			bad++;
 		}
@@ -922,13 +922,10 @@ static void drain_pages(unsigned int cpu)
 	unsigned long flags;
 	struct zone *zone;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		struct per_cpu_pageset *pset;
 		struct per_cpu_pages *pcp;
 
-		if (!populated_zone(zone))
-			continue;
-
 		pset = zone_pcp(zone, cpu);
 
 		pcp = &pset->pcp;
@@ -1479,6 +1476,8 @@ __alloc_pages_internal(gfp_t gfp_mask, unsigned int order,
 	unsigned long did_some_progress;
 	unsigned long pages_reclaimed = 0;
 
+	lockdep_trace_alloc(gfp_mask);
+
 	might_sleep_if(wait);
 
 	if (should_fail_alloc_page(gfp_mask, order))
@@ -1578,12 +1577,16 @@ nofail_alloc:
 	 */
 	cpuset_update_task_memory_state();
 	p->flags |= PF_MEMALLOC;
+
+	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	did_some_progress = try_to_free_pages(zonelist, order, gfp_mask);
+	did_some_progress = try_to_free_pages(zonelist, order,
+						gfp_mask, nodemask);
 
 	p->reclaim_state = NULL;
+	lockdep_clear_current_reclaim_state();
 	p->flags &= ~PF_MEMALLOC;
 
 	cond_resched();
@@ -1874,10 +1877,7 @@ void show_free_areas(void)
 	int cpu;
 	struct zone *zone;
 
-	for_each_zone(zone) {
-		if (!populated_zone(zone))
-			continue;
-
+	for_each_populated_zone(zone) {
 		show_node(zone);
 		printk("%s per-cpu:\n", zone->name);
 
@@ -1917,12 +1917,9 @@ void show_free_areas(void)
 		global_page_state(NR_PAGETABLE),
 		global_page_state(NR_BOUNCE));
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		int i;
 
-		if (!populated_zone(zone))
-			continue;
-
 		show_node(zone);
 		printk("%s"
 			" free:%lukB"
@@ -1962,12 +1959,9 @@ void show_free_areas(void)
 		printk("\n");
 	}
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
  		unsigned long nr[MAX_ORDER], flags, order, total = 0;
 
-		if (!populated_zone(zone))
-			continue;
-
 		show_node(zone);
 		printk("%s: ", zone->name);
 
@@ -2134,7 +2128,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 	int n, val;
 	int min_val = INT_MAX;
 	int best_node = -1;
-	node_to_cpumask_ptr(tmp, 0);
+	const struct cpumask *tmp = cpumask_of_node(0);
 
 	/* Use the local node if we haven't already */
 	if (!node_isset(node, *used_node_mask)) {
@@ -2155,8 +2149,8 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 		val += (n < node);
 
 		/* Give preference to headless and unused nodes */
-		node_to_cpumask_ptr_next(tmp, n);
-		if (!cpus_empty(*tmp))
+		tmp = cpumask_of_node(n);
+		if (!cpumask_empty(tmp))
 			val += PENALTY_FOR_NODE_WITH_CPUS;
 
 		/* Slight preference for less loaded node */
@@ -2687,6 +2681,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 
 static int zone_batchsize(struct zone *zone)
 {
+#ifdef CONFIG_MMU
 	int batch;
 
 	/*
@@ -2712,9 +2707,26 @@ static int zone_batchsize(struct zone *zone)
 	 * of pages of one half of the possible page colors
 	 * and the other with pages of the other colors.
 	 */
-	batch = (1 << (fls(batch + batch/2)-1)) - 1;
+	batch = rounddown_pow_of_two(batch + batch/2) - 1;
 
 	return batch;
+
+#else
+	/* The deferral and batching of frees should be suppressed under NOMMU
+	 * conditions.
+	 *
+	 * The problem is that NOMMU needs to be able to allocate large chunks
+	 * of contiguous memory as there's no hardware page translation to
+	 * assemble apparent contiguous memory from discontiguous pages.
+	 *
+	 * Queueing large contiguous runs of pages for batching, however,
+	 * causes the pages to actually be freed in smaller chunks.  As there
+	 * can be a significant delay between the individual batches being
+	 * recycled, this leads to the once large chunks of space being
+	 * fragmented and becoming unavailable for high-order allocations.
+	 */
+	return 0;
+#endif
 }
 
 static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
@@ -2779,11 +2791,7 @@ static int __cpuinit process_zones(int cpu)
 
 	node_set_state(node, N_CPU);	/* this node has a cpu */
 
-	for_each_zone(zone) {
-
-		if (!populated_zone(zone))
-			continue;
-
+	for_each_populated_zone(zone) {
 		zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
 					 GFP_KERNEL, node);
 		if (!zone_pcp(zone, cpu))
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index ceecfbb143fa..791905c991df 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -285,12 +285,8 @@ struct swap_cgroup_ctrl {
 
 struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
 
-/*
- * This 8bytes seems big..maybe we can reduce this when we can use "id" for
- * cgroup rather than pointer.
- */
 struct swap_cgroup {
-	struct mem_cgroup	*val;
+	unsigned short		id;
 };
 #define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
 #define SC_POS_MASK	(SC_PER_PAGE - 1)
@@ -342,10 +338,10 @@ not_enough_page:
  * @ent: swap entry to be recorded into
  * @mem: mem_cgroup to be recorded
  *
- * Returns old value at success, NULL at failure.
- * (Of course, old value can be NULL.)
+ * Returns old value at success, 0 at failure.
+ * (Of course, old value can be 0.)
  */
-struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 {
 	int type = swp_type(ent);
 	unsigned long offset = swp_offset(ent);
@@ -354,18 +350,18 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
 	struct swap_cgroup_ctrl *ctrl;
 	struct page *mappage;
 	struct swap_cgroup *sc;
-	struct mem_cgroup *old;
+	unsigned short old;
 
 	if (!do_swap_account)
-		return NULL;
+		return 0;
 
 	ctrl = &swap_cgroup_ctrl[type];
 
 	mappage = ctrl->map[idx];
 	sc = page_address(mappage);
 	sc += pos;
-	old = sc->val;
-	sc->val = mem;
+	old = sc->id;
+	sc->id = id;
 
 	return old;
 }
@@ -374,9 +370,9 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
  * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
  * @ent: swap entry to be looked up.
  *
- * Returns pointer to mem_cgroup at success. NULL at failure.
+ * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
  */
-struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+unsigned short lookup_swap_cgroup(swp_entry_t ent)
 {
 	int type = swp_type(ent);
 	unsigned long offset = swp_offset(ent);
@@ -385,16 +381,16 @@ struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
 	struct swap_cgroup_ctrl *ctrl;
 	struct page *mappage;
 	struct swap_cgroup *sc;
-	struct mem_cgroup *ret;
+	unsigned short ret;
 
 	if (!do_swap_account)
-		return NULL;
+		return 0;
 
 	ctrl = &swap_cgroup_ctrl[type];
 	mappage = ctrl->map[idx];
 	sc = page_address(mappage);
 	sc += pos;
-	ret = sc->val;
+	ret = sc->id;
 	return ret;
 }
 
@@ -430,13 +426,6 @@ int swap_cgroup_swapon(int type, unsigned long max_pages)
 	}
 	mutex_unlock(&swap_cgroup_mutex);
 
-	printk(KERN_INFO
-		"swap_cgroup: uses %ld bytes of vmalloc for pointer array space"
-		" and %ld bytes to hold mem_cgroup pointers on swap\n",
-		array_size, length * PAGE_SIZE);
-	printk(KERN_INFO
-	"swap_cgroup can be disabled by noswapaccount boot option.\n");
-
 	return 0;
 nomem:
 	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
diff --git a/mm/pdflush.c b/mm/pdflush.c
index 15de509b68fd..f2caf96993f8 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -58,6 +58,14 @@ static DEFINE_SPINLOCK(pdflush_lock);
 int nr_pdflush_threads = 0;
 
 /*
+ * The max/min number of pdflush threads. R/W by sysctl at
+ * /proc/sys/vm/nr_pdflush_threads_max/min
+ */
+int nr_pdflush_threads_max __read_mostly = MAX_PDFLUSH_THREADS;
+int nr_pdflush_threads_min __read_mostly = MIN_PDFLUSH_THREADS;
+
+
+/*
  * The time at which the pdflush thread pool last went empty
  */
 static unsigned long last_empty_jifs;
@@ -68,7 +76,7 @@ static unsigned long last_empty_jifs;
  * Thread pool management algorithm:
  * 
  * - The minimum and maximum number of pdflush instances are bound
- *   by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
+ *   by nr_pdflush_threads_min and nr_pdflush_threads_max.
  * 
  * - If there have been no idle pdflush instances for 1 second, create
  *   a new one.
@@ -98,7 +106,6 @@ static int __pdflush(struct pdflush_work *my_work)
 	INIT_LIST_HEAD(&my_work->list);
 
 	spin_lock_irq(&pdflush_lock);
-	nr_pdflush_threads++;
 	for ( ; ; ) {
 		struct pdflush_work *pdf;
 
@@ -126,20 +133,25 @@ static int __pdflush(struct pdflush_work *my_work)
 
 		(*my_work->fn)(my_work->arg0);
 
+		spin_lock_irq(&pdflush_lock);
+
 		/*
 		 * Thread creation: For how long have there been zero
 		 * available threads?
+		 *
+		 * To throttle creation, we reset last_empty_jifs.
 		 */
 		if (time_after(jiffies, last_empty_jifs + 1 * HZ)) {
-			/* unlocked list_empty() test is OK here */
-			if (list_empty(&pdflush_list)) {
-				/* unlocked test is OK here */
-				if (nr_pdflush_threads < MAX_PDFLUSH_THREADS)
-					start_one_pdflush_thread();
+			if (list_empty(&pdflush_list) &&
+			    nr_pdflush_threads < nr_pdflush_threads_max) {
+				last_empty_jifs = jiffies;
+				nr_pdflush_threads++;
+				spin_unlock_irq(&pdflush_lock);
+				start_one_pdflush_thread();
+				spin_lock_irq(&pdflush_lock);
 			}
 		}
 
-		spin_lock_irq(&pdflush_lock);
 		my_work->fn = NULL;
 
 		/*
@@ -148,7 +160,7 @@ static int __pdflush(struct pdflush_work *my_work)
 		 */
 		if (list_empty(&pdflush_list))
 			continue;
-		if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
+		if (nr_pdflush_threads <= nr_pdflush_threads_min)
 			continue;
 		pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
 		if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) {
@@ -191,7 +203,7 @@ static int pdflush(void *dummy)
 
 	/*
 	 * Some configs put our parent kthread in a limited cpuset,
-	 * which kthread() overrides, forcing cpus_allowed == CPU_MASK_ALL.
+	 * which kthread() overrides, forcing cpus_allowed == cpu_all_mask.
 	 * Our needs are more modest - cut back to our cpusets cpus_allowed.
 	 * This is needed as pdflush's are dynamically created and destroyed.
 	 * The boottime pdflush's are easily placed w/o these 2 lines.
@@ -236,14 +248,27 @@ int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
 
 static void start_one_pdflush_thread(void)
 {
-	kthread_run(pdflush, NULL, "pdflush");
+	struct task_struct *k;
+
+	k = kthread_run(pdflush, NULL, "pdflush");
+	if (unlikely(IS_ERR(k))) {
+		spin_lock_irq(&pdflush_lock);
+		nr_pdflush_threads--;
+		spin_unlock_irq(&pdflush_lock);
+	}
 }
 
 static int __init pdflush_init(void)
 {
 	int i;
 
-	for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
+	/*
+	 * Pre-set nr_pdflush_threads...  If we fail to create,
+	 * the count will be decremented.
+	 */
+	nr_pdflush_threads = nr_pdflush_threads_min;
+
+	for (i = 0; i < nr_pdflush_threads_min; i++)
 		start_one_pdflush_thread();
 	return 0;
 }
diff --git a/mm/quicklist.c b/mm/quicklist.c
index 8dbb6805ef35..e66d07d1b4ff 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -29,7 +29,7 @@ static unsigned long max_pages(unsigned long min_pages)
 	int node = numa_node_id();
 	struct zone *zones = NODE_DATA(node)->node_zones;
 	int num_cpus_on_node;
-	node_to_cpumask_ptr(cpumask_on_node, node);
+	const struct cpumask *cpumask_on_node = cpumask_of_node(node);
 
 	node_free_pages =
 #ifdef CONFIG_ZONE_DMA
diff --git a/mm/readahead.c b/mm/readahead.c
index 9ce303d4b810..133b6d525513 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -31,6 +31,42 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
 
 #define list_to_page(head) (list_entry((head)->prev, struct page, lru))
 
+/*
+ * see if a page needs releasing upon read_cache_pages() failure
+ * - the caller of read_cache_pages() may have set PG_private or PG_fscache
+ *   before calling, such as the NFS fs marking pages that are cached locally
+ *   on disk, thus we need to give the fs a chance to clean up in the event of
+ *   an error
+ */
+static void read_cache_pages_invalidate_page(struct address_space *mapping,
+					     struct page *page)
+{
+	if (page_has_private(page)) {
+		if (!trylock_page(page))
+			BUG();
+		page->mapping = mapping;
+		do_invalidatepage(page, 0);
+		page->mapping = NULL;
+		unlock_page(page);
+	}
+	page_cache_release(page);
+}
+
+/*
+ * release a list of pages, invalidating them first if need be
+ */
+static void read_cache_pages_invalidate_pages(struct address_space *mapping,
+					      struct list_head *pages)
+{
+	struct page *victim;
+
+	while (!list_empty(pages)) {
+		victim = list_to_page(pages);
+		list_del(&victim->lru);
+		read_cache_pages_invalidate_page(mapping, victim);
+	}
+}
+
 /**
  * read_cache_pages - populate an address space with some pages & start reads against them
  * @mapping: the address_space
@@ -52,14 +88,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
-			page_cache_release(page);
+			read_cache_pages_invalidate_page(mapping, page);
 			continue;
 		}
 		page_cache_release(page);
 
 		ret = filler(data, page);
 		if (unlikely(ret)) {
-			put_pages_list(pages);
+			read_cache_pages_invalidate_pages(mapping, pages);
 			break;
 		}
 		task_io_account_read(PAGE_CACHE_SIZE);
diff --git a/mm/shmem.c b/mm/shmem.c
index 7ec78e24a30d..b25f95ce3db7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/vfs.h>
 #include <linux/mount.h>
+#include <linux/pagemap.h>
 #include <linux/file.h>
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -43,7 +44,6 @@ static struct vfsmount *shm_mnt;
 #include <linux/exportfs.h>
 #include <linux/generic_acl.h>
 #include <linux/mman.h>
-#include <linux/pagemap.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
@@ -65,13 +65,28 @@ static struct vfsmount *shm_mnt;
 #include <asm/div64.h>
 #include <asm/pgtable.h>
 
+/*
+ * The maximum size of a shmem/tmpfs file is limited by the maximum size of
+ * its triple-indirect swap vector - see illustration at shmem_swp_entry().
+ *
+ * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel,
+ * but one eighth of that on a 64-bit kernel.  With 8kB page size, maximum
+ * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel,
+ * MAX_LFS_FILESIZE being then more restrictive than swap vector layout.
+ *
+ * We use / and * instead of shifts in the definitions below, so that the swap
+ * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE.
+ */
 #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
-#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
-#define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)
+#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
+
+#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
+#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT)
 
-#define SHMEM_MAX_INDEX  (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
-#define SHMEM_MAX_BYTES  ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)
+#define SHMEM_MAX_BYTES  min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE)
+#define SHMEM_MAX_INDEX  ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT))
 
+#define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)
 #define VM_ACCT(size)    (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)
 
 /* info->flags needs VM_flags to handle pagein/truncate races efficiently */
@@ -1068,8 +1083,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		swap_duplicate(swap);
 		BUG_ON(page_mapped(page));
 		page_cache_release(page);	/* pagecache ref */
-		set_page_dirty(page);
-		unlock_page(page);
+		swap_writepage(page, wbc);
 		if (inode) {
 			mutex_lock(&shmem_swaplist_mutex);
 			/* move instead of add in case we're racing */
@@ -1326,8 +1340,12 @@ repeat:
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
 			if (error == -ENOMEM) {
-				/* allow reclaim from this memory cgroup */
-				error = mem_cgroup_shrink_usage(swappage,
+				/*
+				 * reclaim from proper memory cgroup and
+				 * call memcg's OOM if needed.
+				 */
+				error = mem_cgroup_shmem_charge_fallback(
+								swappage,
 								current->mm,
 								gfp);
 				if (error) {
@@ -2582,7 +2600,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
 #define shmem_get_inode(sb, mode, dev, flags)	ramfs_get_inode(sb, mode, dev)
 #define shmem_acct_size(flags, size)		0
 #define shmem_unacct_size(flags, size)		do {} while (0)
-#define SHMEM_MAX_BYTES				LLONG_MAX
+#define SHMEM_MAX_BYTES				MAX_LFS_FILESIZE
 
 #endif /* CONFIG_SHMEM */
 
diff --git a/mm/slab.c b/mm/slab.c
index 4d00855629c4..9a90b00d2f91 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -102,6 +102,7 @@
 #include	<linux/cpu.h>
 #include	<linux/sysctl.h>
 #include	<linux/module.h>
+#include	<trace/kmemtrace.h>
 #include	<linux/rcupdate.h>
 #include	<linux/string.h>
 #include	<linux/uaccess.h>
@@ -568,6 +569,14 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 
 #endif
 
+#ifdef CONFIG_KMEMTRACE
+size_t slab_buffer_size(struct kmem_cache *cachep)
+{
+	return cachep->buffer_size;
+}
+EXPORT_SYMBOL(slab_buffer_size);
+#endif
+
 /*
  * Do not go above this order unless 0 objects fit into the slab.
  */
@@ -1160,7 +1169,7 @@ static void __cpuinit cpuup_canceled(long cpu)
 	struct kmem_cache *cachep;
 	struct kmem_list3 *l3 = NULL;
 	int node = cpu_to_node(cpu);
-	node_to_cpumask_ptr(mask, node);
+	const struct cpumask *mask = cpumask_of_node(node);
 
 	list_for_each_entry(cachep, &cache_chain, next) {
 		struct array_cache *nc;
@@ -3318,6 +3327,8 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	unsigned long save_flags;
 	void *ptr;
 
+	lockdep_trace_alloc(flags);
+
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
@@ -3394,6 +3405,8 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	unsigned long save_flags;
 	void *objp;
 
+	lockdep_trace_alloc(flags);
+
 	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
@@ -3550,10 +3563,23 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
  */
 void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
-	return __cache_alloc(cachep, flags, __builtin_return_address(0));
+	void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0));
+
+	trace_kmem_cache_alloc(_RET_IP_, ret,
+			       obj_size(cachep), cachep->buffer_size, flags);
+
+	return ret;
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
+#ifdef CONFIG_KMEMTRACE
+void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags)
+{
+	return __cache_alloc(cachep, flags, __builtin_return_address(0));
+}
+EXPORT_SYMBOL(kmem_cache_alloc_notrace);
+#endif
+
 /**
  * kmem_ptr_validate - check if an untrusted pointer might be a slab entry.
  * @cachep: the cache we're checking against
@@ -3598,23 +3624,46 @@ out:
 #ifdef CONFIG_NUMA
 void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
-	return __cache_alloc_node(cachep, flags, nodeid,
-			__builtin_return_address(0));
+	void *ret = __cache_alloc_node(cachep, flags, nodeid,
+				       __builtin_return_address(0));
+
+	trace_kmem_cache_alloc_node(_RET_IP_, ret,
+				    obj_size(cachep), cachep->buffer_size,
+				    flags, nodeid);
+
+	return ret;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 
+#ifdef CONFIG_KMEMTRACE
+void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep,
+				    gfp_t flags,
+				    int nodeid)
+{
+	return __cache_alloc_node(cachep, flags, nodeid,
+				  __builtin_return_address(0));
+}
+EXPORT_SYMBOL(kmem_cache_alloc_node_notrace);
+#endif
+
 static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
 {
 	struct kmem_cache *cachep;
+	void *ret;
 
 	cachep = kmem_find_general_cachep(size, flags);
 	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
 		return cachep;
-	return kmem_cache_alloc_node(cachep, flags, node);
+	ret = kmem_cache_alloc_node_notrace(cachep, flags, node);
+
+	trace_kmalloc_node((unsigned long) caller, ret,
+			   size, cachep->buffer_size, flags, node);
+
+	return ret;
 }
 
-#ifdef CONFIG_DEBUG_SLAB
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE)
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	return __do_kmalloc_node(size, flags, node,
@@ -3647,6 +3696,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 					  void *caller)
 {
 	struct kmem_cache *cachep;
+	void *ret;
 
 	/* If you want to save a few bytes .text space: replace
 	 * __ with kmem_.
@@ -3656,11 +3706,16 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	cachep = __find_general_cachep(size, flags);
 	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
 		return cachep;
-	return __cache_alloc(cachep, flags, caller);
+	ret = __cache_alloc(cachep, flags, caller);
+
+	trace_kmalloc((unsigned long) caller, ret,
+		      size, cachep->buffer_size, flags);
+
+	return ret;
 }
 
 
-#ifdef CONFIG_DEBUG_SLAB
+#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_KMEMTRACE)
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	return __do_kmalloc(size, flags, __builtin_return_address(0));
@@ -3699,6 +3754,8 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 		debug_check_no_obj_freed(objp, obj_size(cachep));
 	__cache_free(cachep, objp);
 	local_irq_restore(flags);
+
+	trace_kmem_cache_free(_RET_IP_, objp);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
@@ -3716,6 +3773,8 @@ void kfree(const void *objp)
 	struct kmem_cache *c;
 	unsigned long flags;
 
+	trace_kfree(_RET_IP_, objp);
+
 	if (unlikely(ZERO_OR_NULL_PTR(objp)))
 		return;
 	local_irq_save(flags);
@@ -3988,8 +4047,7 @@ static void cache_reap(struct work_struct *w)
 	struct kmem_cache *searchp;
 	struct kmem_list3 *l3;
 	int node = numa_node_id();
-	struct delayed_work *work =
-		container_of(w, struct delayed_work, work);
+	struct delayed_work *work = to_delayed_work(w);
 
 	if (!mutex_trylock(&cache_chain_mutex))
 		/* Give up. Setup the next iteration. */
diff --git a/mm/slob.c b/mm/slob.c
index 0bfa680a8981..a2d4ab32198d 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -65,6 +65,7 @@
 #include <linux/module.h>
 #include <linux/rcupdate.h>
 #include <linux/list.h>
+#include <trace/kmemtrace.h>
 #include <asm/atomic.h>
 
 /*
@@ -474,18 +475,25 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 {
 	unsigned int *m;
 	int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	void *ret;
+
+	lockdep_trace_alloc(gfp);
 
 	if (size < PAGE_SIZE - align) {
 		if (!size)
 			return ZERO_SIZE_PTR;
 
 		m = slob_alloc(size + align, gfp, align, node);
+
 		if (!m)
 			return NULL;
 		*m = size;
-		return (void *)m + align;
+		ret = (void *)m + align;
+
+		trace_kmalloc_node(_RET_IP_, ret,
+				   size, size + align, gfp, node);
 	} else {
-		void *ret;
+		unsigned int order = get_order(size);
 
 		ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node);
 		if (ret) {
@@ -493,8 +501,12 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 			page = virt_to_page(ret);
 			page->private = size;
 		}
-		return ret;
+
+		trace_kmalloc_node(_RET_IP_, ret,
+				   size, PAGE_SIZE << order, gfp, node);
 	}
+
+	return ret;
 }
 EXPORT_SYMBOL(__kmalloc_node);
 
@@ -502,6 +514,8 @@ void kfree(const void *block)
 {
 	struct slob_page *sp;
 
+	trace_kfree(_RET_IP_, block);
+
 	if (unlikely(ZERO_OR_NULL_PTR(block)))
 		return;
 
@@ -581,10 +595,17 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 {
 	void *b;
 
-	if (c->size < PAGE_SIZE)
+	if (c->size < PAGE_SIZE) {
 		b = slob_alloc(c->size, flags, c->align, node);
-	else
+		trace_kmem_cache_alloc_node(_RET_IP_, b, c->size,
+					    SLOB_UNITS(c->size) * SLOB_UNIT,
+					    flags, node);
+	} else {
 		b = slob_new_pages(flags, get_order(c->size), node);
+		trace_kmem_cache_alloc_node(_RET_IP_, b, c->size,
+					    PAGE_SIZE << get_order(c->size),
+					    flags, node);
+	}
 
 	if (c->ctor)
 		c->ctor(b);
@@ -620,6 +641,8 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 	} else {
 		__kmem_cache_free(b, c->size);
 	}
+
+	trace_kmem_cache_free(_RET_IP_, b);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
diff --git a/mm/slub.c b/mm/slub.c
index c65a4edafc33..7ab54ecbd3f3 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
+#include <trace/kmemtrace.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
 #include <linux/mempolicy.h>
@@ -1590,6 +1591,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	unsigned long flags;
 	unsigned int objsize;
 
+	lockdep_trace_alloc(gfpflags);
 	might_sleep_if(gfpflags & __GFP_WAIT);
 
 	if (should_failslab(s->objsize, gfpflags))
@@ -1617,18 +1619,45 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 {
-	return slab_alloc(s, gfpflags, -1, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, -1, _RET_IP_);
+
+	trace_kmem_cache_alloc(_RET_IP_, ret, s->objsize, s->size, gfpflags);
+
+	return ret;
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
+#ifdef CONFIG_KMEMTRACE
+void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+{
+	return slab_alloc(s, gfpflags, -1, _RET_IP_);
+}
+EXPORT_SYMBOL(kmem_cache_alloc_notrace);
+#endif
+
 #ifdef CONFIG_NUMA
 void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
-	return slab_alloc(s, gfpflags, node, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+
+	trace_kmem_cache_alloc_node(_RET_IP_, ret,
+				    s->objsize, s->size, gfpflags, node);
+
+	return ret;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 #endif
 
+#ifdef CONFIG_KMEMTRACE
+void *kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+				    gfp_t gfpflags,
+				    int node)
+{
+	return slab_alloc(s, gfpflags, node, _RET_IP_);
+}
+EXPORT_SYMBOL(kmem_cache_alloc_node_notrace);
+#endif
+
 /*
  * Slow patch handling. This may still be called frequently since objects
  * have a longer lifetime than the cpu slabs in most processing loads.
@@ -1736,6 +1765,8 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 	page = virt_to_head_page(x);
 
 	slab_free(s, page, x, _RET_IP_);
+
+	trace_kmem_cache_free(_RET_IP_, x);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
@@ -2658,6 +2689,7 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags)
 void *__kmalloc(size_t size, gfp_t flags)
 {
 	struct kmem_cache *s;
+	void *ret;
 
 	if (unlikely(size > SLUB_MAX_SIZE))
 		return kmalloc_large(size, flags);
@@ -2667,7 +2699,11 @@ void *__kmalloc(size_t size, gfp_t flags)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	return slab_alloc(s, flags, -1, _RET_IP_);
+	ret = slab_alloc(s, flags, -1, _RET_IP_);
+
+	trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
+
+	return ret;
 }
 EXPORT_SYMBOL(__kmalloc);
 
@@ -2686,16 +2722,28 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	struct kmem_cache *s;
+	void *ret;
 
-	if (unlikely(size > SLUB_MAX_SIZE))
-		return kmalloc_large_node(size, flags, node);
+	if (unlikely(size > SLUB_MAX_SIZE)) {
+		ret = kmalloc_large_node(size, flags, node);
+
+		trace_kmalloc_node(_RET_IP_, ret,
+				   size, PAGE_SIZE << get_order(size),
+				   flags, node);
+
+		return ret;
+	}
 
 	s = get_slab(size, flags);
 
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	return slab_alloc(s, flags, node, _RET_IP_);
+	ret = slab_alloc(s, flags, node, _RET_IP_);
+
+	trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
+
+	return ret;
 }
 EXPORT_SYMBOL(__kmalloc_node);
 #endif
@@ -2744,6 +2792,8 @@ void kfree(const void *x)
 	struct page *page;
 	void *object = (void *)x;
 
+	trace_kfree(_RET_IP_, x);
+
 	if (unlikely(ZERO_OR_NULL_PTR(x)))
 		return;
 
@@ -3223,6 +3273,7 @@ static struct notifier_block __cpuinitdata slab_notifier = {
 void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 {
 	struct kmem_cache *s;
+	void *ret;
 
 	if (unlikely(size > SLUB_MAX_SIZE))
 		return kmalloc_large(size, gfpflags);
@@ -3232,13 +3283,19 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	return slab_alloc(s, gfpflags, -1, caller);
+	ret = slab_alloc(s, gfpflags, -1, caller);
+
+	/* Honor the call site pointer we recieved. */
+	trace_kmalloc(caller, ret, size, s->size, gfpflags);
+
+	return ret;
 }
 
 void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 					int node, unsigned long caller)
 {
 	struct kmem_cache *s;
+	void *ret;
 
 	if (unlikely(size > SLUB_MAX_SIZE))
 		return kmalloc_large_node(size, gfpflags, node);
@@ -3248,7 +3305,12 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	if (unlikely(ZERO_OR_NULL_PTR(s)))
 		return s;
 
-	return slab_alloc(s, gfpflags, node, caller);
+	ret = slab_alloc(s, gfpflags, node, caller);
+
+	/* Honor the call site pointer we recieved. */
+	trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node);
+
+	return ret;
 }
 
 #ifdef CONFIG_SLUB_DEBUG
diff --git a/mm/sparse.c b/mm/sparse.c
index 083f5b63e7a8..da432d9f0ae8 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -164,9 +164,7 @@ void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
 		WARN_ON_ONCE(1);
 		*start_pfn = max_sparsemem_pfn;
 		*end_pfn = max_sparsemem_pfn;
-	}
-
-	if (*end_pfn > max_sparsemem_pfn) {
+	} else if (*end_pfn > max_sparsemem_pfn) {
 		mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
 			"End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
 			*start_pfn, *end_pfn, max_sparsemem_pfn);
diff --git a/mm/swap.c b/mm/swap.c
index 8adb9feb61e1..cb29ae5d33ab 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -448,8 +448,8 @@ void pagevec_strip(struct pagevec *pvec)
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
 
-		if (PagePrivate(page) && trylock_page(page)) {
-			if (PagePrivate(page))
+		if (page_has_private(page) && trylock_page(page)) {
+			if (page_has_private(page))
 				try_to_release_page(page, 0);
 			unlock_page(page);
 		}
@@ -457,29 +457,6 @@ void pagevec_strip(struct pagevec *pvec)
 }
 
 /**
- * pagevec_swap_free - try to free swap space from the pages in a pagevec
- * @pvec: pagevec with swapcache pages to free the swap space of
- *
- * The caller needs to hold an extra reference to each page and
- * not hold the page lock on the pages.  This function uses a
- * trylock on the page lock so it may not always free the swap
- * space associated with a page.
- */
-void pagevec_swap_free(struct pagevec *pvec)
-{
-	int i;
-
-	for (i = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-
-		if (PageSwapCache(page) && trylock_page(page)) {
-			try_to_free_swap(page);
-			unlock_page(page);
-		}
-	}
-}
-
-/**
  * pagevec_lookup - gang pagecache lookup
  * @pvec:	Where the resulting pages are placed
  * @mapping:	The address_space to search
@@ -514,49 +491,6 @@ unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
 
 EXPORT_SYMBOL(pagevec_lookup_tag);
 
-#ifdef CONFIG_SMP
-/*
- * We tolerate a little inaccuracy to avoid ping-ponging the counter between
- * CPUs
- */
-#define ACCT_THRESHOLD	max(16, NR_CPUS * 2)
-
-static DEFINE_PER_CPU(long, committed_space);
-
-void vm_acct_memory(long pages)
-{
-	long *local;
-
-	preempt_disable();
-	local = &__get_cpu_var(committed_space);
-	*local += pages;
-	if (*local > ACCT_THRESHOLD || *local < -ACCT_THRESHOLD) {
-		atomic_long_add(*local, &vm_committed_space);
-		*local = 0;
-	}
-	preempt_enable();
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/* Drop the CPU's cached committed space back into the central pool. */
-static int cpu_swap_callback(struct notifier_block *nfb,
-			     unsigned long action,
-			     void *hcpu)
-{
-	long *committed;
-
-	committed = &per_cpu(committed_space, (long)hcpu);
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		atomic_long_add(*committed, &vm_committed_space);
-		*committed = 0;
-		drain_cpu_pagevecs((long)hcpu);
-	}
-	return NOTIFY_OK;
-}
-#endif /* CONFIG_HOTPLUG_CPU */
-#endif /* CONFIG_SMP */
-
 /*
  * Perform any setup for the swap system
  */
@@ -577,7 +511,4 @@ void __init swap_setup(void)
 	 * Right now other parts of the system means that we
 	 * _really_ don't want to cluster much more
 	 */
-#ifdef CONFIG_HOTPLUG_CPU
-	hotcpu_notifier(cpu_swap_callback, 0);
-#endif
 }
diff --git a/mm/truncate.c b/mm/truncate.c
index 1229211104f8..55206fab7b99 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -50,7 +50,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
 	zero_user_segment(page, partial, PAGE_CACHE_SIZE);
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, partial);
 }
 
@@ -99,7 +99,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return;
 
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, 0);
 
 	cancel_dirty_page(page, PAGE_CACHE_SIZE);
@@ -126,7 +126,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, 0))
+	if (page_has_private(page) && !try_to_release_page(page, 0))
 		return 0;
 
 	clear_page_mlock(page);
@@ -348,7 +348,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
 	spin_lock_irq(&mapping->tree_lock);
@@ -356,7 +356,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 		goto failed;
 
 	clear_page_mlock(page);
-	BUG_ON(PagePrivate(page));
+	BUG_ON(page_has_private(page));
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
 	page_cache_release(page);	/* pagecache ref */
diff --git a/mm/util.c b/mm/util.c
index 37eaccdf3054..55bef160b9f1 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -4,6 +4,7 @@
 #include <linux/module.h>
 #include <linux/err.h>
 #include <linux/sched.h>
+#include <linux/tracepoint.h>
 #include <asm/uaccess.h>
 
 /**
@@ -70,6 +71,36 @@ void *kmemdup(const void *src, size_t len, gfp_t gfp)
 EXPORT_SYMBOL(kmemdup);
 
 /**
+ * memdup_user - duplicate memory region from user space
+ *
+ * @src: source address in user space
+ * @len: number of bytes to copy
+ *
+ * Returns an ERR_PTR() on failure.
+ */
+void *memdup_user(const void __user *src, size_t len)
+{
+	void *p;
+
+	/*
+	 * Always use GFP_KERNEL, since copy_from_user() can sleep and
+	 * cause pagefault, which makes it pointless to use GFP_NOFS
+	 * or GFP_ATOMIC.
+	 */
+	p = kmalloc_track_caller(len, GFP_KERNEL);
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(p, src, len)) {
+		kfree(p);
+		return ERR_PTR(-EFAULT);
+	}
+
+	return p;
+}
+EXPORT_SYMBOL(memdup_user);
+
+/**
  * __krealloc - like krealloc() but don't free @p.
  * @p: object to reallocate memory for.
  * @new_size: how many bytes of memory are required.
@@ -192,6 +223,22 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 }
 #endif
 
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @write:	whether pages will be written to
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ */
 int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 				int nr_pages, int write, struct page **pages)
 {
@@ -206,3 +253,18 @@ int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(get_user_pages_fast);
+
+/* Tracepoints definitions. */
+DEFINE_TRACE(kmalloc);
+DEFINE_TRACE(kmem_cache_alloc);
+DEFINE_TRACE(kmalloc_node);
+DEFINE_TRACE(kmem_cache_alloc_node);
+DEFINE_TRACE(kfree);
+DEFINE_TRACE(kmem_cache_free);
+
+EXPORT_TRACEPOINT_SYMBOL(kmalloc);
+EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
+EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
+EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
+EXPORT_TRACEPOINT_SYMBOL(kfree);
+EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index af58324c361a..083716ea38c9 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -402,6 +402,7 @@ overflow:
 			printk(KERN_WARNING
 				"vmap allocation for size %lu failed: "
 				"use vmalloc=<size> to increase size.\n", size);
+		kfree(va);
 		return ERR_PTR(-EBUSY);
 	}
 
@@ -671,10 +672,7 @@ struct vmap_block {
 	DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS);
 	DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS);
 	union {
-		struct {
-			struct list_head free_list;
-			struct list_head dirty_list;
-		};
+		struct list_head free_list;
 		struct rcu_head rcu_head;
 	};
 };
@@ -741,7 +739,6 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
 	bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS);
 	bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS);
 	INIT_LIST_HEAD(&vb->free_list);
-	INIT_LIST_HEAD(&vb->dirty_list);
 
 	vb_idx = addr_to_vb_idx(va->va_start);
 	spin_lock(&vmap_block_tree_lock);
@@ -772,12 +769,7 @@ static void free_vmap_block(struct vmap_block *vb)
 	struct vmap_block *tmp;
 	unsigned long vb_idx;
 
-	spin_lock(&vb->vbq->lock);
-	if (!list_empty(&vb->free_list))
-		list_del(&vb->free_list);
-	if (!list_empty(&vb->dirty_list))
-		list_del(&vb->dirty_list);
-	spin_unlock(&vb->vbq->lock);
+	BUG_ON(!list_empty(&vb->free_list));
 
 	vb_idx = addr_to_vb_idx(vb->va->va_start);
 	spin_lock(&vmap_block_tree_lock);
@@ -862,11 +854,7 @@ static void vb_free(const void *addr, unsigned long size)
 
 	spin_lock(&vb->lock);
 	bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order);
-	if (!vb->dirty) {
-		spin_lock(&vb->vbq->lock);
-		list_add(&vb->dirty_list, &vb->vbq->dirty);
-		spin_unlock(&vb->vbq->lock);
-	}
+
 	vb->dirty += 1UL << order;
 	if (vb->dirty == VMAP_BBMAP_BITS) {
 		BUG_ON(vb->free || !list_empty(&vb->free_list));
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 56ddf41149eb..5fa3eda1f03f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -60,6 +60,9 @@ struct scan_control {
 
 	int may_writepage;
 
+	/* Can mapped pages be reclaimed? */
+	int may_unmap;
+
 	/* Can pages be swapped as part of reclaim? */
 	int may_swap;
 
@@ -78,6 +81,12 @@ struct scan_control {
 	/* Which cgroup do we reclaim from */
 	struct mem_cgroup *mem_cgroup;
 
+	/*
+	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
+	 * are scanned.
+	 */
+	nodemask_t	*nodemask;
+
 	/* Pluggable isolate pages callback */
 	unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
 			unsigned long *scanned, int order, int mode,
@@ -214,8 +223,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 		do_div(delta, lru_pages + 1);
 		shrinker->nr += delta;
 		if (shrinker->nr < 0) {
-			printk(KERN_ERR "%s: nr=%ld\n",
-					__func__, shrinker->nr);
+			printk(KERN_ERR "shrink_slab: %pF negative objects to "
+			       "delete nr=%ld\n",
+			       shrinker->shrink, shrinker->nr);
 			shrinker->nr = max_pass;
 		}
 
@@ -276,7 +286,7 @@ static inline int page_mapping_inuse(struct page *page)
 
 static inline int is_page_cache_freeable(struct page *page)
 {
-	return page_count(page) - !!PagePrivate(page) == 2;
+	return page_count(page) - !!page_has_private(page) == 2;
 }
 
 static int may_write_to_queue(struct backing_dev_info *bdi)
@@ -360,7 +370,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 		 * Some data journaling orphaned pages can have
 		 * page->mapping == NULL while being dirty with clean buffers.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (try_to_free_buffers(page)) {
 				ClearPageDirty(page);
 				printk("%s: orphaned page\n", __func__);
@@ -606,7 +616,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (unlikely(!page_evictable(page, NULL)))
 			goto cull_mlocked;
 
-		if (!sc->may_swap && page_mapped(page))
+		if (!sc->may_unmap && page_mapped(page))
 			goto keep_locked;
 
 		/* Double the slab pressure for mapped and swapcache pages */
@@ -720,7 +730,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * process address space (page_count == 1) it can be freed.
 		 * Otherwise, leave the page on the LRU so it is swappable.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (!try_to_release_page(page, sc->gfp_mask))
 				goto activate_locked;
 			if (!mapping && page_count(page) == 1) {
@@ -1298,17 +1308,11 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	}
 	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
 	pgdeactivate += pgmoved;
-	if (buffer_heads_over_limit) {
-		spin_unlock_irq(&zone->lru_lock);
-		pagevec_strip(&pvec);
-		spin_lock_irq(&zone->lru_lock);
-	}
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	__count_vm_events(PGDEACTIVATE, pgdeactivate);
 	spin_unlock_irq(&zone->lru_lock);
-	if (vm_swap_full())
-		pagevec_swap_free(&pvec);
-
+	if (buffer_heads_over_limit)
+		pagevec_strip(&pvec);
 	pagevec_release(&pvec);
 }
 
@@ -1379,7 +1383,7 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (nr_swap_pages <= 0) {
+	if (!sc->may_swap || (nr_swap_pages <= 0)) {
 		percent[0] = 0;
 		percent[1] = 100;
 		return;
@@ -1467,7 +1471,7 @@ static void shrink_zone(int priority, struct zone *zone,
 
 	for_each_evictable_lru(l) {
 		int file = is_file_lru(l);
-		int scan;
+		unsigned long scan;
 
 		scan = zone_nr_pages(zone, sc, l);
 		if (priority) {
@@ -1543,7 +1547,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 	struct zone *zone;
 
 	sc->all_unreclaimable = 1;
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
+					sc->nodemask) {
 		if (!populated_zone(zone))
 			continue;
 		/*
@@ -1688,17 +1693,19 @@ out:
 }
 
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
-								gfp_t gfp_mask)
+				gfp_t gfp_mask, nodemask_t *nodemask)
 {
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.may_unmap = 1,
 		.may_swap = 1,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
 		.isolate_pages = isolate_pages_global,
+		.nodemask = nodemask,
 	};
 
 	return do_try_to_free_pages(zonelist, &sc);
@@ -1713,18 +1720,17 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 {
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
-		.may_swap = 1,
+		.may_unmap = 1,
+		.may_swap = !noswap,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
 		.isolate_pages = mem_cgroup_isolate_pages,
+		.nodemask = NULL, /* we don't care the placement */
 	};
 	struct zonelist *zonelist;
 
-	if (noswap)
-		sc.may_swap = 0;
-
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
@@ -1762,6 +1768,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
+		.may_unmap = 1,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = vm_swappiness,
@@ -1963,7 +1970,9 @@ static int kswapd(void *p)
 	struct reclaim_state reclaim_state = {
 		.reclaimed_slab = 0,
 	};
-	node_to_cpumask_ptr(cpumask, pgdat->node_id);
+	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+
+	lockdep_set_current_reclaim_state(GFP_KERNEL);
 
 	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
@@ -2048,22 +2057,19 @@ unsigned long global_lru_pages(void)
 #ifdef CONFIG_PM
 /*
  * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
- * from LRU lists system-wide, for given pass and priority, and returns the
- * number of reclaimed pages
+ * from LRU lists system-wide, for given pass and priority.
  *
  * For pass > 3 we also try to shrink the LRU lists that contain a few pages
  */
-static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
+static void shrink_all_zones(unsigned long nr_pages, int prio,
 				      int pass, struct scan_control *sc)
 {
 	struct zone *zone;
-	unsigned long ret = 0;
+	unsigned long nr_reclaimed = 0;
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		enum lru_list l;
 
-		if (!populated_zone(zone))
-			continue;
 		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
 			continue;
 
@@ -2082,14 +2088,16 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 
 				zone->lru[l].nr_scan = 0;
 				nr_to_scan = min(nr_pages, lru_pages);
-				ret += shrink_list(l, nr_to_scan, zone,
+				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
 								sc, prio);
-				if (ret >= nr_pages)
-					return ret;
+				if (nr_reclaimed >= nr_pages) {
+					sc->nr_reclaimed += nr_reclaimed;
+					return;
+				}
 			}
 		}
 	}
-	return ret;
+	sc->nr_reclaimed += nr_reclaimed;
 }
 
 /*
@@ -2103,15 +2111,14 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 unsigned long shrink_all_memory(unsigned long nr_pages)
 {
 	unsigned long lru_pages, nr_slab;
-	unsigned long ret = 0;
 	int pass;
 	struct reclaim_state reclaim_state;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
-		.may_swap = 0,
-		.swap_cluster_max = nr_pages,
+		.may_unmap = 0,
 		.may_writepage = 1,
 		.isolate_pages = isolate_pages_global,
+		.nr_reclaimed = 0,
 	};
 
 	current->reclaim_state = &reclaim_state;
@@ -2125,8 +2132,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 		if (!reclaim_state.reclaimed_slab)
 			break;
 
-		ret += reclaim_state.reclaimed_slab;
-		if (ret >= nr_pages)
+		sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+		if (sc.nr_reclaimed >= nr_pages)
 			goto out;
 
 		nr_slab -= reclaim_state.reclaimed_slab;
@@ -2145,21 +2152,22 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 
 		/* Force reclaiming mapped pages in the passes #3 and #4 */
 		if (pass > 2)
-			sc.may_swap = 1;
+			sc.may_unmap = 1;
 
 		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
-			unsigned long nr_to_scan = nr_pages - ret;
+			unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
 
 			sc.nr_scanned = 0;
-			ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
-			if (ret >= nr_pages)
+			sc.swap_cluster_max = nr_to_scan;
+			shrink_all_zones(nr_to_scan, prio, pass, &sc);
+			if (sc.nr_reclaimed >= nr_pages)
 				goto out;
 
 			reclaim_state.reclaimed_slab = 0;
 			shrink_slab(sc.nr_scanned, sc.gfp_mask,
 					global_lru_pages());
-			ret += reclaim_state.reclaimed_slab;
-			if (ret >= nr_pages)
+			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+			if (sc.nr_reclaimed >= nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
@@ -2168,21 +2176,23 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 	}
 
 	/*
-	 * If ret = 0, we could not shrink LRUs, but there may be something
-	 * in slab caches
+	 * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
+	 * something in slab caches
 	 */
-	if (!ret) {
+	if (!sc.nr_reclaimed) {
 		do {
 			reclaim_state.reclaimed_slab = 0;
 			shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
-			ret += reclaim_state.reclaimed_slab;
-		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+		} while (sc.nr_reclaimed < nr_pages &&
+				reclaim_state.reclaimed_slab > 0);
 	}
 
+
 out:
 	current->reclaim_state = NULL;
 
-	return ret;
+	return sc.nr_reclaimed;
 }
 #endif
 
@@ -2198,7 +2208,9 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
 		for_each_node_state(nid, N_HIGH_MEMORY) {
 			pg_data_t *pgdat = NODE_DATA(nid);
-			node_to_cpumask_ptr(mask, pgdat->node_id);
+			const struct cpumask *mask;
+
+			mask = cpumask_of_node(pgdat->node_id);
 
 			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
 				/* One of our CPUs online: restore mask */
@@ -2288,11 +2300,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	int priority;
 	struct scan_control sc = {
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
-		.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.may_swap = 1,
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
 					SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
 		.swappiness = vm_swappiness,
+		.order = order,
 		.isolate_pages = isolate_pages_global,
 	};
 	unsigned long slab_reclaimable;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 91149746bb8d..66f6130976cb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -27,7 +27,7 @@ static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask)
 
 	memset(ret, 0, NR_VM_EVENT_ITEMS * sizeof(unsigned long));
 
-	for_each_cpu_mask_nr(cpu, *cpumask) {
+	for_each_cpu(cpu, cpumask) {
 		struct vm_event_state *this = &per_cpu(vm_event_states, cpu);
 
 		for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
@@ -135,11 +135,7 @@ static void refresh_zone_stat_thresholds(void)
 	int cpu;
 	int threshold;
 
-	for_each_zone(zone) {
-
-		if (!zone->present_pages)
-			continue;
-
+	for_each_populated_zone(zone) {
 		threshold = calculate_threshold(zone);
 
 		for_each_online_cpu(cpu)
@@ -301,12 +297,9 @@ void refresh_cpu_vm_stats(int cpu)
 	int i;
 	int global_diff[NR_VM_ZONE_STAT_ITEMS] = { 0, };
 
-	for_each_zone(zone) {
+	for_each_populated_zone(zone) {
 		struct per_cpu_pageset *p;
 
-		if (!populated_zone(zone))
-			continue;
-
 		p = zone_pcp(zone, cpu);
 
 		for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
@@ -898,7 +891,7 @@ static void vmstat_update(struct work_struct *w)
 {
 	refresh_cpu_vm_stats(smp_processor_id());
 	schedule_delayed_work(&__get_cpu_var(vmstat_work),
-		sysctl_stat_interval);
+		round_jiffies_relative(sysctl_stat_interval));
 }
 
 static void __cpuinit start_cpu_timer(int cpu)
@@ -906,7 +899,8 @@ static void __cpuinit start_cpu_timer(int cpu)
 	struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
 
 	INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
-	schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu);
+	schedule_delayed_work_on(cpu, vmstat_work,
+				 __round_jiffies_relative(HZ, cpu));
 }
 
 /*