33 files changed, 1842 insertions, 984 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 8ca47a5ee9c..f2f1ca19ed5 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -356,7 +356,7 @@ config CLEANCACHE
 	  for clean pages that the kernel's pageframe replacement algorithm
 	  (PFRA) would like to keep around, but can't since there isn't enough
 	  memory.  So when the PFRA "evicts" a page, it first attempts to use
-	  cleancacne code to put the data contained in that page into
+	  cleancache code to put the data contained in that page into
 	  "transcendent memory", memory that is not directly accessible or
 	  addressable by the kernel and is of unknown and possibly
 	  time-varying size.  And when a cleancache-enabled
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index f032e6e1e09..d6edf8d14f9 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -45,6 +45,17 @@ static struct timer_list sync_supers_timer;
 static int bdi_sync_supers(void *);
 static void sync_supers_timer_fn(unsigned long);
 
+void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2)
+{
+	if (wb1 < wb2) {
+		spin_lock(&wb1->list_lock);
+		spin_lock_nested(&wb2->list_lock, 1);
+	} else {
+		spin_lock(&wb2->list_lock);
+		spin_lock_nested(&wb1->list_lock, 1);
+	}
+}
+
 #ifdef CONFIG_DEBUG_FS
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
@@ -67,34 +78,42 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 	struct inode *inode;
 
 	nr_dirty = nr_io = nr_more_io = 0;
-	spin_lock(&inode_wb_list_lock);
+	spin_lock(&wb->list_lock);
 	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
 	list_for_each_entry(inode, &wb->b_io, i_wb_list)
 		nr_io++;
 	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
-	spin_unlock(&inode_wb_list_lock);
+	spin_unlock(&wb->list_lock);
 
 	global_dirty_limits(&background_thresh, &dirty_thresh);
 	bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);
 
 #define K(x) ((x) << (PAGE_SHIFT - 10))
 	seq_printf(m,
-		   "BdiWriteback:     %8lu kB\n"
-		   "BdiReclaimable:   %8lu kB\n"
-		   "BdiDirtyThresh:   %8lu kB\n"
-		   "DirtyThresh:      %8lu kB\n"
-		   "BackgroundThresh: %8lu kB\n"
-		   "b_dirty:          %8lu\n"
-		   "b_io:             %8lu\n"
-		   "b_more_io:        %8lu\n"
-		   "bdi_list:         %8u\n"
-		   "state:            %8lx\n",
+		   "BdiWriteback:       %10lu kB\n"
+		   "BdiReclaimable:     %10lu kB\n"
+		   "BdiDirtyThresh:     %10lu kB\n"
+		   "DirtyThresh:        %10lu kB\n"
+		   "BackgroundThresh:   %10lu kB\n"
+		   "BdiWritten:         %10lu kB\n"
+		   "BdiWriteBandwidth:  %10lu kBps\n"
+		   "b_dirty:            %10lu\n"
+		   "b_io:               %10lu\n"
+		   "b_more_io:          %10lu\n"
+		   "bdi_list:           %10u\n"
+		   "state:              %10lx\n",
 		   (unsigned long) K(bdi_stat(bdi, BDI_WRITEBACK)),
 		   (unsigned long) K(bdi_stat(bdi, BDI_RECLAIMABLE)),
-		   K(bdi_thresh), K(dirty_thresh),
-		   K(background_thresh), nr_dirty, nr_io, nr_more_io,
+		   K(bdi_thresh),
+		   K(dirty_thresh),
+		   K(background_thresh),
+		   (unsigned long) K(bdi_stat(bdi, BDI_WRITTEN)),
+		   (unsigned long) K(bdi->write_bandwidth),
+		   nr_dirty,
+		   nr_io,
+		   nr_more_io,
 		   !list_empty(&bdi->bdi_list), bdi->state);
 #undef K
 
@@ -249,18 +268,6 @@ int bdi_has_dirty_io(struct backing_dev_info *bdi)
 	return wb_has_dirty_io(&bdi->wb);
 }
 
-static void bdi_flush_io(struct backing_dev_info *bdi)
-{
-	struct writeback_control wbc = {
-		.sync_mode		= WB_SYNC_NONE,
-		.older_than_this	= NULL,
-		.range_cyclic		= 1,
-		.nr_to_write		= 1024,
-	};
-
-	writeback_inodes_wb(&bdi->wb, &wbc);
-}
-
 /*
  * kupdated() used to do this. We cannot do it from the bdi_forker_thread()
  * or we risk deadlocking on ->s_umount. The longer term solution would be
@@ -446,9 +453,10 @@ static int bdi_forker_thread(void *ptr)
 			if (IS_ERR(task)) {
 				/*
 				 * If thread creation fails, force writeout of
-				 * the bdi from the thread.
+				 * the bdi from the thread. Hopefully 1024 is
+				 * large enough for efficient IO.
 				 */
-				bdi_flush_io(bdi);
+				writeback_inodes_wb(&bdi->wb, 1024);
 			} else {
 				/*
 				 * The spinlock makes sure we do not lose
@@ -505,7 +513,7 @@ static void bdi_remove_from_list(struct backing_dev_info *bdi)
 	list_del_rcu(&bdi->bdi_list);
 	spin_unlock_bh(&bdi_lock);
 
-	synchronize_rcu();
+	synchronize_rcu_expedited();
 }
 
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
@@ -606,6 +614,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 		del_timer_sync(&bdi->wb.wakeup_timer);
@@ -628,9 +637,15 @@ static void bdi_wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi)
 	INIT_LIST_HEAD(&wb->b_dirty);
 	INIT_LIST_HEAD(&wb->b_io);
 	INIT_LIST_HEAD(&wb->b_more_io);
+	spin_lock_init(&wb->list_lock);
 	setup_timer(&wb->wakeup_timer, wakeup_timer_fn, (unsigned long)bdi);
 }
 
+/*
+ * Initial write bandwidth: 100 MB/s
+ */
+#define INIT_BW		(100 << (20 - PAGE_SHIFT))
+
 int bdi_init(struct backing_dev_info *bdi)
 {
 	int i, err;
@@ -653,6 +668,13 @@ int bdi_init(struct backing_dev_info *bdi)
 	}
 
 	bdi->dirty_exceeded = 0;
+
+	bdi->bw_time_stamp = jiffies;
+	bdi->written_stamp = 0;
+
+	bdi->write_bandwidth = INIT_BW;
+	bdi->avg_write_bandwidth = INIT_BW;
+
 	err = prop_local_init_percpu(&bdi->completions);
 
 	if (err) {
@@ -676,11 +698,12 @@ void bdi_destroy(struct backing_dev_info *bdi)
 	if (bdi_has_dirty_io(bdi)) {
 		struct bdi_writeback *dst = &default_backing_dev_info.wb;
 
-		spin_lock(&inode_wb_list_lock);
+		bdi_lock_two(&bdi->wb, dst);
 		list_splice(&bdi->wb.b_dirty, &dst->b_dirty);
 		list_splice(&bdi->wb.b_io, &dst->b_io);
 		list_splice(&bdi->wb.b_more_io, &dst->b_more_io);
-		spin_unlock(&inode_wb_list_lock);
+		spin_unlock(&bdi->wb.list_lock);
+		spin_unlock(&dst->list_lock);
 	}
 
 	bdi_unregister(bdi);
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 03bf3bb4519..fbb58e34688 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -500,7 +500,7 @@ void dmam_pool_destroy(struct dma_pool *pool)
 {
 	struct device *dev = pool->dev;
 
-	dma_pool_destroy(pool);
 	WARN_ON(devres_destroy(dev, dmam_pool_release, dmam_pool_match, pool));
+	dma_pool_destroy(pool);
 }
 EXPORT_SYMBOL(dmam_pool_destroy);
diff --git a/mm/failslab.c b/mm/failslab.c
index c5f88f240dd..1ce58c201dc 100644
--- a/mm/failslab.c
+++ b/mm/failslab.c
@@ -5,10 +5,6 @@ static struct {
 	struct fault_attr attr;
 	u32 ignore_gfp_wait;
 	int cache_filter;
-#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-	struct dentry *ignore_gfp_wait_file;
-	struct dentry *cache_filter_file;
-#endif
 } failslab = {
 	.attr = FAULT_ATTR_INITIALIZER,
 	.ignore_gfp_wait = 1,
@@ -39,31 +35,24 @@ __setup("failslab=", setup_failslab);
 static int __init failslab_debugfs_init(void)
 {
 	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
-	struct dentry *dir;
 	int err;
 
 	err = init_fault_attr_dentries(&failslab.attr, "failslab");
 	if (err)
 		return err;
-	dir = failslab.attr.dentries.dir;
-
-	failslab.ignore_gfp_wait_file =
-		debugfs_create_bool("ignore-gfp-wait", mode, dir,
-				      &failslab.ignore_gfp_wait);
 
-	failslab.cache_filter_file =
-		debugfs_create_bool("cache-filter", mode, dir,
-				      &failslab.cache_filter);
+	if (!debugfs_create_bool("ignore-gfp-wait", mode, failslab.attr.dir,
+				&failslab.ignore_gfp_wait))
+		goto fail;
+	if (!debugfs_create_bool("cache-filter", mode, failslab.attr.dir,
+				&failslab.cache_filter))
+		goto fail;
 
-	if (!failslab.ignore_gfp_wait_file ||
-	    !failslab.cache_filter_file) {
-		err = -ENOMEM;
-		debugfs_remove(failslab.cache_filter_file);
-		debugfs_remove(failslab.ignore_gfp_wait_file);
-		cleanup_fault_attr_dentries(&failslab.attr);
-	}
+	return 0;
+fail:
+	cleanup_fault_attr_dentries(&failslab.attr);
 
-	return err;
+	return -ENOMEM;
 }
 
 late_initcall(failslab_debugfs_init);
diff --git a/mm/filemap.c b/mm/filemap.c
index a8251a8d345..867d40222ec 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -78,10 +78,7 @@
  *  ->i_mutex			(generic_file_buffered_write)
  *    ->mmap_sem		(fault_in_pages_readable->do_page_fault)
  *
- *  ->i_mutex
- *    ->i_alloc_sem             (various)
- *
- *  inode_wb_list_lock
+ *  bdi->wb.list_lock
  *    sb_lock			(fs/fs-writeback.c)
  *    ->mapping->tree_lock	(__sync_single_inode)
  *
@@ -99,9 +96,9 @@
  *    ->zone.lru_lock		(check_pte_range->isolate_lru_page)
  *    ->private_lock		(page_remove_rmap->set_page_dirty)
  *    ->tree_lock		(page_remove_rmap->set_page_dirty)
- *    inode_wb_list_lock	(page_remove_rmap->set_page_dirty)
+ *    bdi.wb->list_lock		(page_remove_rmap->set_page_dirty)
  *    ->inode->i_lock		(page_remove_rmap->set_page_dirty)
- *    inode_wb_list_lock	(zap_pte_range->set_page_dirty)
+ *    bdi.wb->list_lock		(zap_pte_range->set_page_dirty)
  *    ->inode->i_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
@@ -131,6 +128,7 @@ void __delete_from_page_cache(struct page *page)
 
 	radix_tree_delete(&mapping->page_tree, page->index);
 	page->mapping = NULL;
+	/* Leave page->index set: truncation lookup relies upon it */
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
@@ -486,6 +484,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 			spin_unlock_irq(&mapping->tree_lock);
 		} else {
 			page->mapping = NULL;
+			/* Leave page->index set: truncation relies upon it */
 			spin_unlock_irq(&mapping->tree_lock);
 			mem_cgroup_uncharge_cache_page(page);
 			page_cache_release(page);
@@ -1795,7 +1794,7 @@ EXPORT_SYMBOL(generic_file_readonly_mmap);
 
 static struct page *__read_cache_page(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data,
 				gfp_t gfp)
 {
@@ -1826,7 +1825,7 @@ repeat:
 
 static struct page *do_read_cache_page(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data,
 				gfp_t gfp)
 
@@ -1866,7 +1865,7 @@ out:
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
- * @data:	destination for read data
+ * @data:	first arg to filler(data, page) function, often left as NULL
  *
  * Same as read_cache_page, but don't wait for page to become unlocked
  * after submitting it to the filler.
@@ -1878,7 +1877,7 @@ out:
  */
 struct page *read_cache_page_async(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
@@ -1926,7 +1925,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
- * @data:	destination for read data
+ * @data:	first arg to filler(data, page) function, often left as NULL
  *
  * Read into the page cache. If a page already exists, and PageUptodate() is
  * not set, try to fill the page then wait for it to become unlocked.
@@ -1935,7 +1934,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
  */
 struct page *read_cache_page(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 81532f297fd..e2d1587be26 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1596,14 +1596,13 @@ void __khugepaged_exit(struct mm_struct *mm)
 		list_del(&mm_slot->mm_node);
 		free = 1;
 	}
+	spin_unlock(&khugepaged_mm_lock);
 
 	if (free) {
-		spin_unlock(&khugepaged_mm_lock);
 		clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
 		free_mm_slot(mm_slot);
 		mmdrop(mm);
 	} else if (mm_slot) {
-		spin_unlock(&khugepaged_mm_lock);
 		/*
 		 * This is required to serialize against
 		 * khugepaged_test_exit() (which is guaranteed to run
@@ -1614,8 +1613,7 @@ void __khugepaged_exit(struct mm_struct *mm)
 		 */
 		down_write(&mm->mmap_sem);
 		up_write(&mm->mmap_sem);
-	} else
-		spin_unlock(&khugepaged_mm_lock);
+	}
 }
 
 static void release_pte_page(struct page *page)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bfcf153bc82..dae27ba3be2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -24,7 +24,7 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/hugetlb.h>
 #include <linux/node.h>
@@ -62,10 +62,10 @@ static DEFINE_SPINLOCK(hugetlb_lock);
  * must either hold the mmap_sem for write, or the mmap_sem for read and
  * the hugetlb_instantiation mutex:
  *
- * 	down_write(&mm->mmap_sem);
+ *	down_write(&mm->mmap_sem);
  * or
- * 	down_read(&mm->mmap_sem);
- * 	mutex_lock(&hugetlb_instantiation_mutex);
+ *	down_read(&mm->mmap_sem);
+ *	mutex_lock(&hugetlb_instantiation_mutex);
  */
 struct file_region {
 	struct list_head link;
@@ -503,9 +503,10 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
 	for (i = 0; i < pages_per_huge_page(h); i++) {
-		page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
-				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
-				1 << PG_private | 1<< PG_writeback);
+		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+				1 << PG_referenced | 1 << PG_dirty |
+				1 << PG_active | 1 << PG_reserved |
+				1 << PG_private | 1 << PG_writeback);
 	}
 	set_compound_page_dtor(page, NULL);
 	set_page_refcounted(page);
@@ -591,7 +592,6 @@ int PageHuge(struct page *page)
 
 	return dtor == free_huge_page;
 }
-
 EXPORT_SYMBOL_GPL(PageHuge);
 
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
@@ -1105,8 +1105,16 @@ static void __init gather_bootmem_prealloc(void)
 	struct huge_bootmem_page *m;
 
 	list_for_each_entry(m, &huge_boot_pages, list) {
-		struct page *page = virt_to_page(m);
 		struct hstate *h = m->hstate;
+		struct page *page;
+
+#ifdef CONFIG_HIGHMEM
+		page = pfn_to_page(m->phys >> PAGE_SHIFT);
+		free_bootmem_late((unsigned long)m,
+				  sizeof(struct huge_bootmem_page));
+#else
+		page = virt_to_page(m);
+#endif
 		__ClearPageReserved(page);
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
@@ -2124,9 +2132,8 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 	pte_t entry;
 
 	entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
-	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1))
 		update_mmu_cache(vma, address, ptep);
-	}
 }
 
 
@@ -2181,9 +2188,9 @@ static int is_hugetlb_entry_migration(pte_t pte)
 	if (huge_pte_none(pte) || pte_present(pte))
 		return 0;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp)) {
+	if (non_swap_entry(swp) && is_migration_entry(swp))
 		return 1;
-	} else
+	else
 		return 0;
 }
 
@@ -2194,9 +2201,9 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 	if (huge_pte_none(pte) || pte_present(pte))
 		return 0;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp)) {
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
 		return 1;
-	} else
+	else
 		return 0;
 }
 
@@ -2559,7 +2566,7 @@ retry:
 		 * So we need to block hugepage fault by PG_hwpoison bit check.
 		 */
 		if (unlikely(PageHWPoison(page))) {
-			ret = VM_FAULT_HWPOISON | 
+			ret = VM_FAULT_HWPOISON |
 			      VM_FAULT_SET_HINDEX(h - hstates);
 			goto backout_unlocked;
 		}
@@ -2627,7 +2634,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			migration_entry_wait(mm, (pmd_t *)ptep, address);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
-			return VM_FAULT_HWPOISON_LARGE | 
+			return VM_FAULT_HWPOISON_LARGE |
 			       VM_FAULT_SET_HINDEX(h - hstates);
 	}
 
diff --git a/mm/init-mm.c b/mm/init-mm.c
index 4019979b263..a56a851908d 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -5,7 +5,7 @@
 #include <linux/list.h>
 #include <linux/cpumask.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index aacee45616f..d6880f542f9 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -96,7 +96,7 @@
 
 #include <asm/sections.h>
 #include <asm/processor.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #include <linux/kmemcheck.h>
 #include <linux/kmemleak.h>
diff --git a/mm/madvise.c b/mm/madvise.c
index 2221491ed50..74bf193eff0 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -218,7 +218,7 @@ static long madvise_remove(struct vm_area_struct *vma,
 	endoff = (loff_t)(end - vma->vm_start - 1)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* vmtruncate_range needs to take i_mutex and i_alloc_sem */
+	/* vmtruncate_range needs to take i_mutex */
 	up_read(&current->mm->mmap_sem);
 	error = vmtruncate_range(mapping->host, offset, endoff);
 	down_read(&current->mm->mmap_sem);
diff --git a/mm/memblock.c b/mm/memblock.c
index a0562d1a6ad..ccbf9733959 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -758,9 +758,9 @@ void __init memblock_analyze(void)
 
 	/* Check marker in the unused last array entry */
 	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
-		!= (phys_addr_t)RED_INACTIVE);
+		!= MEMBLOCK_INACTIVE);
 	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
-		!= (phys_addr_t)RED_INACTIVE);
+		!= MEMBLOCK_INACTIVE);
 
 	memblock.memory_size = 0;
 
@@ -786,8 +786,8 @@ void __init memblock_init(void)
 	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
 
 	/* Write a marker in the unused last array entry */
-	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
-	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE;
 
 	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
 	 * This simplifies the memblock_add() code below...
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ddffc74cdeb..5f84d2351dd 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -108,10 +108,12 @@ enum mem_cgroup_events_index {
 enum mem_cgroup_events_target {
 	MEM_CGROUP_TARGET_THRESH,
 	MEM_CGROUP_TARGET_SOFTLIMIT,
+	MEM_CGROUP_TARGET_NUMAINFO,
 	MEM_CGROUP_NTARGETS,
 };
 #define THRESHOLDS_EVENTS_TARGET (128)
 #define SOFTLIMIT_EVENTS_TARGET (1024)
+#define NUMAINFO_EVENTS_TARGET	(1024)
 
 struct mem_cgroup_stat_cpu {
 	long count[MEM_CGROUP_STAT_NSTATS];
@@ -203,6 +205,50 @@ struct mem_cgroup_eventfd_list {
 static void mem_cgroup_threshold(struct mem_cgroup *mem);
 static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
 
+enum {
+	SCAN_BY_LIMIT,
+	SCAN_BY_SYSTEM,
+	NR_SCAN_CONTEXT,
+	SCAN_BY_SHRINK,	/* not recorded now */
+};
+
+enum {
+	SCAN,
+	SCAN_ANON,
+	SCAN_FILE,
+	ROTATE,
+	ROTATE_ANON,
+	ROTATE_FILE,
+	FREED,
+	FREED_ANON,
+	FREED_FILE,
+	ELAPSED,
+	NR_SCANSTATS,
+};
+
+struct scanstat {
+	spinlock_t	lock;
+	unsigned long	stats[NR_SCAN_CONTEXT][NR_SCANSTATS];
+	unsigned long	rootstats[NR_SCAN_CONTEXT][NR_SCANSTATS];
+};
+
+const char *scanstat_string[NR_SCANSTATS] = {
+	"scanned_pages",
+	"scanned_anon_pages",
+	"scanned_file_pages",
+	"rotated_pages",
+	"rotated_anon_pages",
+	"rotated_file_pages",
+	"freed_pages",
+	"freed_anon_pages",
+	"freed_file_pages",
+	"elapsed_ns",
+};
+#define SCANSTAT_WORD_LIMIT	"_by_limit"
+#define SCANSTAT_WORD_SYSTEM	"_by_system"
+#define SCANSTAT_WORD_HIERARCHY	"_under_hierarchy"
+
+
 /*
  * The memory controller data structure. The memory controller controls both
  * page cache and RSS per cgroup. We would eventually like to provide
@@ -237,16 +283,20 @@ struct mem_cgroup {
 	int last_scanned_node;
 #if MAX_NUMNODES > 1
 	nodemask_t	scan_nodes;
-	unsigned long   next_scan_node_update;
+	atomic_t	numainfo_events;
+	atomic_t	numainfo_updating;
 #endif
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
 	bool use_hierarchy;
-	atomic_t	oom_lock;
+
+	bool		oom_lock;
+	atomic_t	under_oom;
+
 	atomic_t	refcnt;
 
-	unsigned int	swappiness;
+	int	swappiness;
 	/* OOM-Killer disable */
 	int		oom_kill_disable;
 
@@ -264,7 +314,8 @@ struct mem_cgroup {
 
 	/* For oom notifier event fd */
 	struct list_head oom_notify;
-
+	/* For recording LRU-scan statistics */
+	struct scanstat scanstat;
 	/*
 	 * Should we move charges of a task when a task is moved into this
 	 * mem_cgroup ? And what type of charges should we move ?
@@ -577,15 +628,6 @@ static long mem_cgroup_read_stat(struct mem_cgroup *mem,
 	return val;
 }
 
-static long mem_cgroup_local_usage(struct mem_cgroup *mem)
-{
-	long ret;
-
-	ret = mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_RSS);
-	ret += mem_cgroup_read_stat(mem, MEM_CGROUP_STAT_CACHE);
-	return ret;
-}
-
 static void mem_cgroup_swap_statistics(struct mem_cgroup *mem,
 					 bool charge)
 {
@@ -642,27 +684,44 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 	preempt_enable();
 }
 
-static unsigned long
-mem_cgroup_get_zonestat_node(struct mem_cgroup *mem, int nid, enum lru_list idx)
+unsigned long
+mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *mem, int nid, int zid,
+			unsigned int lru_mask)
 {
 	struct mem_cgroup_per_zone *mz;
+	enum lru_list l;
+	unsigned long ret = 0;
+
+	mz = mem_cgroup_zoneinfo(mem, nid, zid);
+
+	for_each_lru(l) {
+		if (BIT(l) & lru_mask)
+			ret += MEM_CGROUP_ZSTAT(mz, l);
+	}
+	return ret;
+}
+
+static unsigned long
+mem_cgroup_node_nr_lru_pages(struct mem_cgroup *mem,
+			int nid, unsigned int lru_mask)
+{
 	u64 total = 0;
 	int zid;
 
-	for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-		mz = mem_cgroup_zoneinfo(mem, nid, zid);
-		total += MEM_CGROUP_ZSTAT(mz, idx);
-	}
+	for (zid = 0; zid < MAX_NR_ZONES; zid++)
+		total += mem_cgroup_zone_nr_lru_pages(mem, nid, zid, lru_mask);
+
 	return total;
 }
-static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem,
-					enum lru_list idx)
+
+static unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *mem,
+			unsigned int lru_mask)
 {
 	int nid;
 	u64 total = 0;
 
-	for_each_online_node(nid)
-		total += mem_cgroup_get_zonestat_node(mem, nid, idx);
+	for_each_node_state(nid, N_HIGH_MEMORY)
+		total += mem_cgroup_node_nr_lru_pages(mem, nid, lru_mask);
 	return total;
 }
 
@@ -689,6 +748,9 @@ static void __mem_cgroup_target_update(struct mem_cgroup *mem, int target)
 	case MEM_CGROUP_TARGET_SOFTLIMIT:
 		next = val + SOFTLIMIT_EVENTS_TARGET;
 		break;
+	case MEM_CGROUP_TARGET_NUMAINFO:
+		next = val + NUMAINFO_EVENTS_TARGET;
+		break;
 	default:
 		return;
 	}
@@ -707,11 +769,19 @@ static void memcg_check_events(struct mem_cgroup *mem, struct page *page)
 		mem_cgroup_threshold(mem);
 		__mem_cgroup_target_update(mem, MEM_CGROUP_TARGET_THRESH);
 		if (unlikely(__memcg_event_check(mem,
-			MEM_CGROUP_TARGET_SOFTLIMIT))){
+			     MEM_CGROUP_TARGET_SOFTLIMIT))) {
 			mem_cgroup_update_tree(mem, page);
 			__mem_cgroup_target_update(mem,
-				MEM_CGROUP_TARGET_SOFTLIMIT);
+						   MEM_CGROUP_TARGET_SOFTLIMIT);
+		}
+#if MAX_NUMNODES > 1
+		if (unlikely(__memcg_event_check(mem,
+			MEM_CGROUP_TARGET_NUMAINFO))) {
+			atomic_inc(&mem->numainfo_events);
+			__mem_cgroup_target_update(mem,
+				MEM_CGROUP_TARGET_NUMAINFO);
 		}
+#endif
 	}
 }
 
@@ -1038,6 +1108,21 @@ void mem_cgroup_move_lists(struct page *page,
 	mem_cgroup_add_lru_list(page, to);
 }
 
+/*
+ * Checks whether given mem is same or in the root_mem's
+ * hierarchy subtree
+ */
+static bool mem_cgroup_same_or_subtree(const struct mem_cgroup *root_mem,
+		struct mem_cgroup *mem)
+{
+	if (root_mem != mem) {
+		return (root_mem->use_hierarchy &&
+			css_is_ancestor(&mem->css, &root_mem->css));
+	}
+
+	return true;
+}
+
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 {
 	int ret;
@@ -1057,10 +1142,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 	 * enabled in "curr" and "curr" is a child of "mem" in *cgroup*
 	 * hierarchy(even if use_hierarchy is disabled in "mem").
 	 */
-	if (mem->use_hierarchy)
-		ret = css_is_ancestor(&curr->css, &mem->css);
-	else
-		ret = (curr == mem);
+	ret = mem_cgroup_same_or_subtree(mem, curr);
 	css_put(&curr->css);
 	return ret;
 }
@@ -1072,8 +1154,8 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_
 	unsigned long gb;
 	unsigned long inactive_ratio;
 
-	inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON);
-	active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON);
+	inactive = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_INACTIVE_ANON));
+	active = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_ACTIVE_ANON));
 
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
 	if (gb)
@@ -111