35 files changed, 1181 insertions, 532 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index a5b77811fdf..b53427ad30a 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 +213,13 @@ config UNEVICTABLE_LRU
 	  will use one page flag and increase the code size a little,
 	  say Y unless you know what you are doing.
 
+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
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
new file mode 100644
index 00000000000..bb01e298f26
--- /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 818569b68f4..ec73c68b601 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 1882923bc70..dfdee6a4735 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 be68c956a66..493b468a503 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 00000000000..a1e3324de2b
--- /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 7c6ea6493f8..9339de5f0a9 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 126d3973b3d..2e2d38ebda4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -513,6 +513,7 @@ 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 +566,24 @@ 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 +646,7 @@ 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 +2483,9 @@ 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 0c04615651b..427dfe3ce78 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 910198037bf..68eb1d9b63f 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 107da3d809a..28c655ba935 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 478223b73a2..987bb03fbdd 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/memcontrol.c b/mm/memcontrol.c
index 8e4be9cb2a6..2fc6d6c4823 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;
 
-	orig = root_mem->last_scanned_child;
-	obsolete = mem_cgroup_is_obsolete(orig);
 
-	if (list_empty(&root_mem->css.cgroup->children)) {
+	rcu_read_lock();
+
+	mem_cgrp = memcg->css.cgroup;
+	task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
+
+	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;
 }