Merge branch 'master'

29 files changed, 2603 insertions, 1587 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index a9cb80a..332f5c2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -137,5 +137,11 @@ config SPLIT_PTLOCK_CPUS
 # support for page migration
 #
 config MIGRATION
-	def_bool y if NUMA || SPARSEMEM || DISCONTIGMEM
-	depends on SWAP
+	bool "Page migration"
+	def_bool y if NUMA
+	depends on SWAP && NUMA
+	help
+	  Allows the migration of the physical location of pages of processes
+	  while the virtual addresses are not changed. This is useful for
+	  example on NUMA systems to put pages nearer to the processors accessing
+	  the page.
diff --git a/mm/Makefile b/mm/Makefile
index 9aa03fa..0b8f73f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -10,7 +10,7 @@ mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   page_alloc.o page-writeback.o pdflush.o \
 			   readahead.o swap.o truncate.o vmscan.o \
-			   prio_tree.o util.o $(mmu-y)
+			   prio_tree.o util.o mmzone.o $(mmu-y)
 
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
@@ -22,3 +22,5 @@ obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
+obj-$(CONFIG_MIGRATION) += migrate.o
+
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 35c3229..d3e3bd2 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -33,6 +33,7 @@ EXPORT_SYMBOL(max_pfn);		/* This is exported so
 				 * dma_get_required_mask(), which uses
 				 * it, can be an inline function */
 
+static LIST_HEAD(bdata_list);
 #ifdef CONFIG_CRASH_DUMP
 /*
  * If we have booted due to a crash, max_pfn will be a very low value. We need
@@ -52,6 +53,27 @@ unsigned long __init bootmem_bootmap_pages (unsigned long pages)
 
 	return mapsize;
 }
+/*
+ * link bdata in order
+ */
+static void link_bootmem(bootmem_data_t *bdata)
+{
+	bootmem_data_t *ent;
+	if (list_empty(&bdata_list)) {
+		list_add(&bdata->list, &bdata_list);
+		return;
+	}
+	/* insert in order */
+	list_for_each_entry(ent, &bdata_list, list) {
+		if (bdata->node_boot_start < ent->node_boot_start) {
+			list_add_tail(&bdata->list, &ent->list);
+			return;
+		}
+	}
+	list_add_tail(&bdata->list, &bdata_list);
+	return;
+}
+
 
 /*
  * Called once to set up the allocator itself.
@@ -62,13 +84,11 @@ static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
 	bootmem_data_t *bdata = pgdat->bdata;
 	unsigned long mapsize = ((end - start)+7)/8;
 
-	pgdat->pgdat_next = pgdat_list;
-	pgdat_list = pgdat;
-
 	mapsize = ALIGN(mapsize, sizeof(long));
 	bdata->node_bootmem_map = phys_to_virt(mapstart << PAGE_SHIFT);
 	bdata->node_boot_start = (start << PAGE_SHIFT);
 	bdata->node_low_pfn = end;
+	link_bootmem(bdata);
 
 	/*
 	 * Initially all pages are reserved - setup_arch() has to
@@ -152,7 +172,7 @@ static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr,
  *
  * NOTE:  This function is _not_ reentrant.
  */
-static void * __init
+void * __init
 __alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
 	      unsigned long align, unsigned long goal, unsigned long limit)
 {
@@ -383,12 +403,11 @@ unsigned long __init free_all_bootmem (void)
 
 void * __init __alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal)
 {
-	pg_data_t *pgdat = pgdat_list;
+	bootmem_data_t *bdata;
 	void *ptr;
 
-	for_each_pgdat(pgdat)
-		if ((ptr = __alloc_bootmem_core(pgdat->bdata, size,
-						 align, goal, 0)))
+	list_for_each_entry(bdata, &bdata_list, list)
+		if ((ptr = __alloc_bootmem_core(bdata, size, align, goal, 0)))
 			return(ptr);
 
 	/*
@@ -416,11 +435,11 @@ void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, unsigne
 
 void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal)
 {
-	pg_data_t *pgdat = pgdat_list;
+	bootmem_data_t *bdata;
 	void *ptr;
 
-	for_each_pgdat(pgdat)
-		if ((ptr = __alloc_bootmem_core(pgdat->bdata, size,
+	list_for_each_entry(bdata, &bdata_list, list)
+		if ((ptr = __alloc_bootmem_core(bdata, size,
 						 align, goal, LOW32LIMIT)))
 			return(ptr);
 
diff --git a/mm/fadvise.c b/mm/fadvise.c
index d257c89..907c392 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -15,6 +15,7 @@
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 #include <linux/fadvise.h>
+#include <linux/writeback.h>
 #include <linux/syscalls.h>
 
 #include <asm/unistd.h>
@@ -22,13 +23,36 @@
 /*
  * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
  * deactivate the pages and clear PG_Referenced.
+ *
+ * LINUX_FADV_ASYNC_WRITE: start async writeout of any dirty pages between file
+ * offsets `offset' and `offset+len' inclusive.  Any pages which are currently
+ * under writeout are skipped, whether or not they are dirty.
+ *
+ * LINUX_FADV_WRITE_WAIT: wait upon writeout of any dirty pages between file
+ * offsets `offset' and `offset+len'.
+ *
+ * By combining these two operations the application may do several things:
+ *
+ * LINUX_FADV_ASYNC_WRITE: push some or all of the dirty pages at the disk.
+ *
+ * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE: push all of the currently
+ * dirty pages at the disk.
+ *
+ * LINUX_FADV_WRITE_WAIT, LINUX_FADV_ASYNC_WRITE, LINUX_FADV_WRITE_WAIT: push
+ * all of the currently dirty pages at the disk, wait until they have been
+ * written.
+ *
+ * It should be noted that none of these operations write out the file's
+ * metadata.  So unless the application is strictly performing overwrites of
+ * already-instantiated disk blocks, there are no guarantees here that the data
+ * will be available after a crash.
  */
 asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 {
 	struct file *file = fget(fd);
 	struct address_space *mapping;
 	struct backing_dev_info *bdi;
-	loff_t endbyte;
+	loff_t endbyte;			/* inclusive */
 	pgoff_t start_index;
 	pgoff_t end_index;
 	unsigned long nrpages;
@@ -56,6 +80,8 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 	endbyte = offset + len;
 	if (!len || endbyte < len)
 		endbyte = -1;
+	else
+		endbyte--;		/* inclusive */
 
 	bdi = mapping->backing_dev_info;
 
@@ -78,7 +104,7 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 
 		/* First and last PARTIAL page! */
 		start_index = offset >> PAGE_CACHE_SHIFT;
-		end_index = (endbyte-1) >> PAGE_CACHE_SHIFT;
+		end_index = endbyte >> PAGE_CACHE_SHIFT;
 
 		/* Careful about overflow on the "+1" */
 		nrpages = end_index - start_index + 1;
@@ -96,11 +122,21 @@ asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
 			filemap_flush(mapping);
 
 		/* First and last FULL page! */
-		start_index = (offset + (PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
+		start_index = (offset+(PAGE_CACHE_SIZE-1)) >> PAGE_CACHE_SHIFT;
 		end_index = (endbyte >> PAGE_CACHE_SHIFT);
 
-		if (end_index > start_index)
-			invalidate_mapping_pages(mapping, start_index, end_index-1);
+		if (end_index >= start_index)
+			invalidate_mapping_pages(mapping, start_index,
+						end_index);
+		break;
+	case LINUX_FADV_ASYNC_WRITE:
+		ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
+						WB_SYNC_NONE);
+		break;
+	case LINUX_FADV_WRITE_WAIT:
+		ret = wait_on_page_writeback_range(mapping,
+					offset >> PAGE_CACHE_SHIFT,
+					endbyte >> PAGE_CACHE_SHIFT);
 		break;
 	default:
 		ret = -EINVAL;
diff --git a/mm/filemap.c b/mm/filemap.c
index 7624c26..1120338 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -29,7 +29,10 @@
 #include <linux/blkdev.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/cpuset.h>
 #include "filemap.h"
+#include "internal.h"
+
 /*
  * FIXME: remove all knowledge of the buffer layer from the core VM
  */
@@ -172,7 +175,7 @@ static int sync_page(void *word)
  * dirty pages that lie within the byte offsets <start, end>
  * @mapping:	address space structure to write
  * @start:	offset in bytes where the range starts
- * @end:	offset in bytes where the range ends
+ * @end:	offset in bytes where the range ends (inclusive)
  * @sync_mode:	enable synchronous operation
  *
  * If sync_mode is WB_SYNC_ALL then this is a "data integrity" operation, as
@@ -180,8 +183,8 @@ static int sync_page(void *word)
  * these two operations is that if a dirty page/buffer is encountered, it must
  * be waited upon, and not just skipped over.
  */
-static int __filemap_fdatawrite_range(struct address_space *mapping,
-	loff_t start, loff_t end, int sync_mode)
+int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+				loff_t end, int sync_mode)
 {
 	int ret;
 	struct writeback_control wbc = {
@@ -210,8 +213,8 @@ int filemap_fdatawrite(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_fdatawrite);
 
-static int filemap_fdatawrite_range(struct address_space *mapping,
-	loff_t start, loff_t end)
+static int filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
+				loff_t end)
 {
 	return __filemap_fdatawrite_range(mapping, start, end, WB_SYNC_ALL);
 }
@@ -230,7 +233,7 @@ EXPORT_SYMBOL(filemap_flush);
  * Wait for writeback to complete against pages indexed by start->end
  * inclusive
  */
-static int wait_on_page_writeback_range(struct address_space *mapping,
+int wait_on_page_writeback_range(struct address_space *mapping,
 				pgoff_t start, pgoff_t end)
 {
 	struct pagevec pvec;
@@ -365,6 +368,12 @@ int filemap_write_and_wait(struct address_space *mapping)
 }
 EXPORT_SYMBOL(filemap_write_and_wait);
 
+/*
+ * Write out and wait upon file offsets lstart->lend, inclusive.
+ *
+ * Note that `lend' is inclusive (describes the last byte to be written) so
+ * that this function can be used to write to the very end-of-file (end = -1).
+ */
 int filemap_write_and_wait_range(struct address_space *mapping,
 				 loff_t lstart, loff_t lend)
 {
@@ -425,6 +434,28 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	return ret;
 }
 
+#ifdef CONFIG_NUMA
+struct page *page_cache_alloc(struct address_space *x)
+{
+	if (cpuset_do_page_mem_spread()) {
+		int n = cpuset_mem_spread_node();
+		return alloc_pages_node(n, mapping_gfp_mask(x), 0);
+	}
+	return alloc_pages(mapping_gfp_mask(x), 0);
+}
+EXPORT_SYMBOL(page_cache_alloc);
+
+struct page *page_cache_alloc_cold(struct address_space *x)
+{
+	if (cpuset_do_page_mem_spread()) {
+		int n = cpuset_mem_spread_node();
+		return alloc_pages_node(n, mapping_gfp_mask(x)|__GFP_COLD, 0);
+	}
+	return alloc_pages(mapping_gfp_mask(x)|__GFP_COLD, 0);
+}
+EXPORT_SYMBOL(page_cache_alloc_cold);
+#endif
+
 /*
  * In order to wait for pages to become available there must be
  * waitqueues associated with pages. By using a hash table of
diff --git a/mm/highmem.c b/mm/highmem.c
index ce2e7e8..55885f6 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -26,18 +26,14 @@
 #include <linux/init.h>
 #include <linux/hash.h>
 #include <linux/highmem.h>
+#include <linux/blktrace_api.h>
 #include <asm/tlbflush.h>
 
 static mempool_t *page_pool, *isa_page_pool;
 
-static void *page_pool_alloc_isa(gfp_t gfp_mask, void *data)
+static void *mempool_alloc_pages_isa(gfp_t gfp_mask, void *data)
 {
-	return alloc_page(gfp_mask | GFP_DMA);
-}
-
-static void page_pool_free(void *page, void *data)
-{
-	__free_page(page);
+	return mempool_alloc_pages(gfp_mask | GFP_DMA, data);
 }
 
 /*
@@ -50,11 +46,6 @@ static void page_pool_free(void *page, void *data)
  */
 #ifdef CONFIG_HIGHMEM
 
-static void *page_pool_alloc(gfp_t gfp_mask, void *data)
-{
-	return alloc_page(gfp_mask);
-}
-
 static int pkmap_count[LAST_PKMAP];
 static unsigned int last_pkmap_nr;
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kmap_lock);
@@ -228,7 +219,7 @@ static __init int init_emergency_pool(void)
 	if (!i.totalhigh)
 		return 0;
 
-	page_pool = mempool_create(POOL_SIZE, page_pool_alloc, page_pool_free, NULL);
+	page_pool = mempool_create_page_pool(POOL_SIZE, 0);
 	if (!page_pool)
 		BUG();
 	printk("highmem bounce pool size: %d pages\n", POOL_SIZE);
@@ -271,7 +262,8 @@ int init_emergency_isa_pool(void)
 	if (isa_page_pool)
 		return 0;
 
-	isa_page_pool = mempool_create(ISA_POOL_SIZE, page_pool_alloc_isa, page_pool_free, NULL);
+	isa_page_pool = mempool_create(ISA_POOL_SIZE, mempool_alloc_pages_isa,
+				       mempool_free_pages, (void *) 0);
 	if (!isa_page_pool)
 		BUG();
 
@@ -336,7 +328,7 @@ static void bounce_end_io(struct bio *bio, mempool_t *pool, int err)
 	bio_put(bio);
 }
 
-static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done,int err)
+static int bounce_end_io_write(struct bio *bio, unsigned int bytes_done, int err)
 {
 	if (bio->bi_size)
 		return 1;
@@ -383,7 +375,7 @@ static int bounce_end_io_read_isa(struct bio *bio, unsigned int bytes_done, int
 }
 
 static void __blk_queue_bounce(request_queue_t *q, struct bio **bio_orig,
-			mempool_t *pool)
+			       mempool_t *pool)
 {
 	struct page *page;
 	struct bio *bio = NULL;
@@ -483,6 +475,8 @@ void blk_queue_bounce(request_queue_t *q, struct bio **bio_orig)
 		pool = isa_page_pool;
 	}
 
+	blk_add_trace_bio(q, *bio_orig, BLK_TA_BOUNCE);
+
 	/*
 	 * slow path
 	 */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5087077..ebad6bb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -13,24 +13,48 @@
 #include <linux/pagemap.h>
 #include <linux/mempolicy.h>
 #include <linux/cpuset.h>
+#include <linux/mutex.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
 #include <linux/hugetlb.h>
+#include "internal.h"
 
 const unsigned long hugetlb_zero = 0, hugetlb_infinity = ~0UL;
-static unsigned long nr_huge_pages, free_huge_pages;
+static unsigned long nr_huge_pages, free_huge_pages, reserved_huge_pages;
 unsigned long max_huge_pages;
 static struct list_head hugepage_freelists[MAX_NUMNODES];
 static unsigned int nr_huge_pages_node[MAX_NUMNODES];
 static unsigned int free_huge_pages_node[MAX_NUMNODES];
-
 /*
  * Protects updates to hugepage_freelists, nr_huge_pages, and free_huge_pages
  */
 static DEFINE_SPINLOCK(hugetlb_lock);
 
+static void clear_huge_page(struct page *page, unsigned long addr)
+{
+	int i;
+
+	might_sleep();
+	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); i++) {
+		cond_resched();
+		clear_user_highpage(page + i, addr);
+	}
+}
+
+static void copy_huge_page(struct page *dst, struct page *src,
+			   unsigned long addr)
+{
+	int i;
+
+	might_sleep();
+	for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++) {
+		cond_resched();
+		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE);
+	}
+}
+
 static void enqueue_huge_page(struct page *page)
 {
 	int nid = page_to_nid(page);
@@ -64,57 +88,176 @@ static struct page *dequeue_huge_page(struct vm_area_struct *vma,
 	return page;
 }
 
-static struct page *alloc_fresh_huge_page(void)
+static void free_huge_page(struct page *page)
+{
+	BUG_ON(page_count(page));
+
+	INIT_LIST_HEAD(&page->lru);
+
+	spin_lock(&hugetlb_lock);
+	enqueue_huge_page(page);
+	spin_unlock(&hugetlb_lock);
+}
+
+static int alloc_fresh_huge_page(void)
 {
 	static int nid = 0;
 	struct page *page;
 	page = alloc_pages_node(nid, GFP_HIGHUSER|__GFP_COMP|__GFP_NOWARN,
 					HUGETLB_PAGE_ORDER);
-	nid = (nid + 1) % num_online_nodes();
+	nid = next_node(nid, node_online_map);
+	if (nid == MAX_NUMNODES)
+		nid = first_node(node_online_map);
 	if (page) {
+		page[1].lru.next = (void *)free_huge_page;	/* dtor */
 		spin_lock(&hugetlb_lock);
 		nr_huge_pages++;
 		nr_huge_pages_node[page_to_nid(page)]++;
 		spin_unlock(&hugetlb_lock);
+		put_page(page); /* free it into the hugepage allocator */
+		return 1;
 	}
-	return page;
+	return 0;
 }
 
-void free_huge_page(struct page *page)
+static struct page *alloc_huge_page(struct vm_area_struct *vma,
+				    unsigned long addr)
 {
-	BUG_ON(page_count(page));
+	struct inode *inode = vma->vm_file->f_dentry->d_inode;
+	struct page *page;
+	int use_reserve = 0;
+	unsigned long idx;
 
-	INIT_LIST_HEAD(&page->lru);
-	page[1].lru.next = NULL;			/* reset dtor */
+	spin_lock(&hugetlb_lock);
+
+	if (vma->vm_flags & VM_MAYSHARE) {
+
+		/* idx = radix tree index, i.e. offset into file in
+		 * HPAGE_SIZE units */
+		idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
+			+ (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
+
+		/* The hugetlbfs specific inode info stores the number
+		 * of "guaranteed available" (huge) pages.  That is,
+		 * the first 'prereserved_hpages' pages of the inode
+		 * are either already instantiated, or have been
+		 * pre-reserved (by hugetlb_reserve_for_inode()). Here
+		 * we're in the process of instantiating the page, so
+		 * we use this to determine whether to draw from the
+		 * pre-reserved pool or the truly free pool. */
+		if (idx < HUGETLBFS_I(inode)->prereserved_hpages)
+			use_reserve = 1;
+	}
+
+	if (!use_reserve) {
+		if (free_huge_pages <= reserved_huge_pages)
+			goto fail;
+	} else {
+		BUG_ON(reserved_huge_pages == 0);
+		reserved_huge_pages--;
+	}
+
+	page = dequeue_huge_page(vma, addr);
+	if (!page)
+		goto fail;
+
+	spin_unlock(&hugetlb_lock);
+	set_page_refcounted(page);
+	return page;
+
+ fail:
+	WARN_ON(use_reserve); /* reserved allocations shouldn't fail */
+	spin_unlock(&hugetlb_lock);
+	return NULL;
+}
+
+/* hugetlb_extend_reservation()
+ *
+ * Ensure that at least 'atleast' hugepages are, and will remain,
+ * available to instantiate the first 'atleast' pages of the given
+ * inode.  If the inode doesn't already have this many pages reserved
+ * or instantiated, set aside some hugepages in the reserved pool to
+ * satisfy later faults (or fail now if there aren't enough, rather
+ * than getting the SIGBUS later).
+ */
+int hugetlb_extend_reservation(struct hugetlbfs_inode_info *info,
+			       unsigned long atleast)
+{
+	struct inode *inode = &info->vfs_inode;
+	unsigned long change_in_reserve = 0;
+	int ret = 0;
 
 	spin_lock(&hugetlb_lock);
-	enqueue_huge_page(page);
+	read_lock_irq(&inode->i_mapping->tree_lock);
+
+	if (info->prereserved_hpages >= atleast)
+		goto out;
+
+	/* Because we always call this on shared mappings, none of the
+	 * pages beyond info->prereserved_hpages can have been
+	 * instantiated, so we need to reserve all of them now. */
+	change_in_reserve = atleast - info->prereserved_hpages;
+
+	if ((reserved_huge_pages + change_in_reserve) > free_huge_pages) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	reserved_huge_pages += change_in_reserve;
+	info->prereserved_hpages = atleast;
+
+ out:
+	read_unlock_irq(&inode->i_mapping->tree_lock);
 	spin_unlock(&hugetlb_lock);
+
+	return ret;
 }
 
-struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr)
+/* hugetlb_truncate_reservation()
+ *
+ * This returns pages reserved for the given inode to the general free
+ * hugepage pool.  If the inode has any pages prereserved, but not
+ * instantiated, beyond offset (atmost << HPAGE_SIZE), then release
+ * them.
+ */
+void hugetlb_truncate_reservation(struct hugetlbfs_inode_info *info,
+				  unsigned long atmost)
 {
+	struct inode *inode = &info->vfs_inode;
+	struct address_space *mapping = inode->i_mapping;
+	unsigned long idx;
+	unsigned long change_in_reserve = 0;
 	struct page *page;
-	int i;
 
 	spin_lock(&hugetlb_lock);
-	page = dequeue_huge_page(vma, addr);
-	if (!page) {
-		spin_unlock(&hugetlb_lock);
-		return NULL;
+	read_lock_irq(&inode->i_mapping->tree_lock);
+
+	if (info->prereserved_hpages <= atmost)
+		goto out;
+
+	/* Count pages which were reserved, but not instantiated, and
+	 * which we can now release. */
+	for (idx = atmost; idx < info->prereserved_hpages; idx++) {
+		page = radix_tree_lookup(&mapping->page_tree, idx);
+		if (!page)
+			/* Pages which are already instantiated can't
+			 * be unreserved (and in fact have already
+			 * been removed from the reserved pool) */
+			change_in_reserve++;
 	}
+
+	BUG_ON(reserved_huge_pages < change_in_reserve);
+	reserved_huge_pages -= change_in_reserve;
+	info->prereserved_hpages = atmost;
+
+ out:
+	read_unlock_irq(&inode->i_mapping->tree_lock);
 	spin_unlock(&hugetlb_lock);
-	set_page_count(page, 1);
-	page[1].lru.next = (void *)free_huge_page;	/* set dtor */
-	for (i = 0; i < (HPAGE_SIZE/PAGE_SIZE); ++i)
-		clear_user_highpage(&page[i], addr);
-	return page;
 }
 
 static int __init hugetlb_init(void)
 {
 	unsigned long i;
-	struct page *page;
 
 	if (HPAGE_SHIFT == 0)
 		return 0;
@@ -123,12 +266,8 @@ static int __init hugetlb_init(void)
 		INIT_LIST_HEAD(&hugepage_freelists[i]);
 
 	for (i = 0; i < max_huge_pages; ++i) {
-		page = alloc_fresh_huge_page();
-		if (!page)
+		if (!alloc_fresh_huge_page())
 			break;
-		spin_lock(&hugetlb_lock);
-		enqueue_huge_page(page);
-		spin_unlock(&hugetlb_lock);
 	}
 	max_huge_pages = free_huge_pages = nr_huge_pages = i;
 	printk("Total HugeTLB memory allocated, %ld\n", free_huge_pages);
@@ -154,9 +293,9 @@ static void update_and_free_page(struct page *page)
 		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_page_count(&page[i], 0);
 	}
-	set_page_count(page, 1);
+	page[1].lru.next = NULL;
+	set_page_refcounted(page);
 	__free_pages(page, HUGETLB_PAGE_ORDER);
 }
 
@@ -188,12 +327,8 @@ static inline void try_to_free_low(unsigned long count)
 static unsigned long set_max_huge_pages(unsigned long count)
 {
 	while (count > nr_huge_pages) {
-		struct page *page = alloc_fresh_huge_page();
-		if (!page)
+		if (!alloc_fresh_huge_page())
 			return nr_huge_pages;
-		spin_lock(&hugetlb_lock);
-		enqueue_huge_page(page);
-		spin_unlock(&hugetlb_lock);
 	}
 	if (count >= nr_huge_pages)
 		return nr_huge_pages;
@@ -225,9 +360,11 @@ int hugetlb_report_meminfo(char *buf)
 	return sprintf(buf,
 			"HugePages_Total: %5lu\n"
 			"HugePages_Free:  %5lu\n"
+		        "HugePages_Rsvd:  %5lu\n"
 			"Hugepagesize:    %5lu kB\n",
 			nr_huge_pages,
 			free_huge_pages,
+		        reserved_huge_pages,
 			HPAGE_SIZE/1024);
 }
 
@@ -240,11 +377,6 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 		nid, free_huge_pages_node[nid]);
 }
 
-int is_hugepage_mem_enough(size_t size)
-{
-	return (size + ~HPAGE_MASK)/HPAGE_SIZE <= free_huge_pages;
-}
-
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
@@ -374,7 +506,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte)
 {
 	struct page *old_page, *new_page;
-	int i, avoidcopy;
+	int avoidcopy;
 
 	old_page = pte_page(pte);
 
@@ -395,9 +527,7 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	spin_unlock(&mm->page_table_lock);
-	for (i = 0; i < HPAGE_SIZE/PAGE_SIZE; i++)
-		copy_user_highpage(new_page + i, old_page + i,
-				   address + i*PAGE_SIZE);
+	copy_huge_page(new_page, old_page, address);
 	spin_lock(&mm->page_table_lock);
 
 	ptep = huge_pte_offset(mm, address & HPAGE_MASK);
@@ -442,6 +572,7 @@ retry:
 			ret = VM_FAULT_OOM;
 			goto out;
 		}
+		clear_huge_page(page, address);
 
 		if (vma->vm_flags & VM_SHARED) {
 			int err;
@@ -496,14 +627,24 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *ptep;
 	pte_t entry;
 	int ret;
+	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 
 	ptep = huge_pte_alloc(mm, address);
 	if (!ptep)
 		return VM_FAULT_OOM;
 
+	/*
+	 * Serialize hugepage allocation and instantiation, so that we don't
+	 * get spurious allocation failures if two CPUs race to instantiate
+	 * the same page in the page cache.
+	 */
+	mutex_lock(&hugetlb_instantiation_mutex);
 	entry = *ptep;
-	if (pte_none(entry))
-		return hugetlb_no_page(mm, vma, address, ptep, write_access);
+	if (pte_none(entry)) {
+		ret = hugetlb_no_page(mm, vma, address, ptep, write_access);
+		mutex_unlock(&hugetlb_instantiation_mutex);
+		return ret;
+	}
 
 	ret = VM_FAULT_MINOR;
 
@@ -513,6 +654,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (write_access && !pte_write(entry))
 			ret = hugetlb_cow(mm, vma, address, ptep, entry);
 	spin_unlock(&mm->page_table_lock);
+	mutex_unlock(&hugetlb_instantiation_mutex);
 
 	return ret;
 }
@@ -521,10 +663,10 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			struct page **pages, struct vm_area_struct **vmas,
 			unsigned long *position, int *length, int i)
 {
-	unsigned long vpfn, vaddr = *position;
+	unsigned long pfn_offset;
+	unsigned long vaddr = *position;
 	int remainder = *length;
 
-	vpfn = vaddr/PAGE_SIZE;
 	spin_lock(&mm->page_table_lock);
 	while (vaddr < vma->vm_end && remainder) {
 		pte_t *pte;
@@ -552,19 +694,28 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			break;
 		}
 
-		if (pages) {
-			page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
-			get_page(page);
-			pages[i] = page;
-		}
+		pfn_offset = (vaddr & ~HPAGE_MASK) >> PAGE_SHIFT;
+		page = pte_page(*pte);
+same_page:
+		get_page(page);
+		if (pages)
+			pages[i] = page + pfn_offset;
 
 		if (vmas)
 			vmas[i] = vma;
 
 		vaddr += PAGE_SIZE;
-		++vpfn;
+		++pfn_offset;
 		--remainder;
 		++i;
+		if (vaddr < vma->vm_end && remainder &&
+				pfn_offset < HPAGE_SIZE/PAGE_SIZE) {
+			/*
+			 * We use pfn_offset to avoid touching the pageframes
+			 * of this compound page.
+			 */
+			goto same_page;
+		}
 	}
 	spin_unlock(&mm->page_table_lock);
 	*length = remainder;
@@ -572,3 +723,32 @@ int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	return i;
 }
+
+void hugetlb_change_protection(struct vm_area_struct *vma,
+		unsigned long address, unsigned long end, pgprot_t newprot)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long start = address;
+	pte_t *ptep;
+	pte_t pte;
+
+	BUG_ON(address >= end);
+	flush_cache_range(vma, address, end);
+
+	spin_lock(&mm->page_table_lock);
+	for (; address < end; address += HPAGE_SIZE) {
+		ptep = huge_pte_offset(mm, address);
+		if (!ptep)
+			continue;
+		if (!pte_none(*ptep)) {
+			pte = huge_ptep_get_and_clear(mm, address, ptep);
+			pte = pte_mkhuge(pte_modify(pte, newprot));
+			set_huge_pte_at(mm, address, ptep, pte);
+			lazy_mmu_prot_update(pte);
+		}
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	flush_tlb_range(vma, start, end);
+}
+
diff --git a/mm/internal.h b/mm/internal.h
index 17256bb..d20e3cc 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -8,23 +8,33 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
+#ifndef __MM_INTERNAL_H
+#define __MM_INTERNAL_H
 
-static inline void set_page_refs(struct page *page, int order)
+#include <linux/mm.h>
+
+static inline void set_page_count(struct page *page, int v)
+{
+	atomic_set(&page->_count, v);
+}
+
+/*
+ * Turn a non-refcounted page (->_count == 0) into refcounted with
+ * a count of one.
+ */
+static inline void set_page_refcounted(struct page *page)
 {
-#ifdef CONFIG_MMU
+	BUG_ON(PageCompound(page) && page_private(page) != (unsigned long)page);
+	BUG_ON(atomic_read(&page->_count));
 	set_page_count(page, 1);
-#else
-	int i;
+}
 
-	/*
-	 * We need to reference all the pages for this order, otherwise if
-	 * anyone accesses one of the pages with (get/put) it will be freed.
-	 * - eg: access_process_vm()
-	 */
-	for (i = 0; i < (1 << order); i++)
-		set_page_count(page + i, 1);
-#endif /* CONFIG_MMU */
+static inline void __put_page(struct page *page)
+{
+	atomic_dec(&page->_count);
 }
 
 extern void fastcall __init __free_pages_bootmem(struct page *page,
 						unsigned int order);
+
+#endif
diff --git a/mm/memory.c b/mm/memory.c
index 85e80a5..8d8f525 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -277,7 +277,7 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
 		anon_vma_unlink(vma);
 		unlink_file_vma(vma);
 
-		if (is_hugepage_only_range(vma->vm_mm, addr, HPAGE_SIZE)) {
+		if (is_vm_hugetlb_page(vma)) {
 			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
 				floor, next? next->vm_start: ceiling);
 		} else {
@@ -285,8 +285,7 @@ void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
 			 * Optimization: gather nearby vmas into one call down
 			 */
 			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
-			  && !is_hugepage_only_range(vma->vm_mm, next->vm_start,
-							HPAGE_SIZE)) {
+			       && !is_vm_hugetlb_page(next)) {
 				vma = next;
 				next = vma->vm_next;
 				anon_vma_unlink(vma);
@@ -388,7 +387,7 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_
 {
 	unsigned long pfn = pte_pfn(pte);
 
-	if (vma->vm_flags & VM_PFNMAP) {
+	if (unlikely(vma->vm_flags & VM_PFNMAP)) {
 		unsigned long off = (addr - vma->vm_start) >> PAGE_SHIFT;
 		if (pfn == vma->vm_pgoff + off)
 			return NULL;
@@ -401,8 +400,6 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_
 	 * we should just do "return pfn_to_page(pfn)", but
 	 * in the meantime we check that we get a valid pfn,
 	 * and that the resulting page looks ok.
-	 *
-	 * Remove this test eventually!
 	 */
 	if (unlikely(!pfn_valid(pfn))) {
 		print_bad_pte(vma, pte, addr);
@@ -1074,6 +1071,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			}
 			if (pages) {
 				pages[i] = page;
+
+				flush_anon_page(page, start);
 				flush_dcache_page(page);
 			}
 			if (vmas)
@@ -1221,9 +1220,7 @@ out:
  * The page has to be a nice clean _individual_ kernel allocation.
  * If you allocate a compound page, you need to have marked it as
  * such (__GFP_COMP), or manually just split the page up yourself
- * (which is mainly an issue of doing "set_page_count(page, 1)" for
- * each sub-page, and then freeing them one by one when you free
- * them rather than freeing it as a compound page).
+ * (see split_page()).
  *
  * NOTE! Traditionally this was done with "remap_pfn_range()" which
  * took an arbitrary page protection parameter. This doesn't allow
@@ -2357,10 +2354,8 @@ int make_pages_present(unsigned long addr, unsigned long end)
 	if (!vma)
 		return -1;
 	write = (vma->vm_flags & VM_WRITE) != 0;
-	if (addr >= end)
-		BUG();
-	if (end > vma->vm_end)
-		BUG();
+	BUG_ON(addr >= end);
+	BUG_ON(end > vma->vm_end);
 	len = (end+PAGE_SIZE-1)/PAGE_SIZE-addr/PAGE_SIZE;
 	ret = get_user_pages(current, current->mm, addr,
 			len, write, 0, NULL, NULL);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b21869a..dec8249 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -86,6 +86,7 @@
 #include <linux/swap.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
+#include <linux/migrate.h>
 
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
@@ -95,11 +96,8 @@
 #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */
 #define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2)		/* Gather statistics */
 
-/* The number of pages to migrate per call to migrate_pages() */
-#define MIGRATE_CHUNK_SIZE 256
-
-static kmem_cache_t *policy_cache;
-static kmem_cache_t *sn_cache;
+static struct kmem_cache *policy_cache;
+static struct kmem_cache *sn_cache;
 
 #define PDprintk(fmt...)
 
@@ -331,17 +329,10 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	struct vm_area_struct *first, *vma, *prev;
 
 	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
-		/* Must have swap device for migration */
-		if (nr_swap_pages <= 0)
-			return ERR_PTR(-ENODEV);
 
-		/*
-		 * Clear the LRU lists so pages can be isolated.
-		 * Note that pages may be moved off the LRU after we have
-		 * drained them. Those pages will fail to migrate like other
-		 * pages that may be busy.
-		 */
-		lru_add_drain_all();
+		err = migrate_prep();
+		if (err)
+			return ERR_PTR(err);
 	}
 
 	first = find_vma(mm, start);
@@ -431,6 +422,37 @@ static int contextualize_policy(int mode, nodemask_t *nodes)
 	return mpol_check_policy(mode, nodes);
 }
 
+
+/*
+ * Update task->flags PF_MEMPOLICY bit: set iff non-default
+ * mempolicy.  Allows more rapid checking of this (combined perhaps
+ * with other PF_* flag bits) on memory allocation hot code paths.
+ *
+ * If called from outside this file, the task 'p' should -only- be
+ * a newly forked child not yet visible on the task list, because
+ * manipulating the task flags of a visible task is not safe.
+ *
+ * The above limitation is why this routine has the funny name
+ * mpol_fix_fork_child_flag().
+ *
+ * It is also safe to call this with a task pointer of current,
+ * which the static wrapper mpol_set_task_struct_flag() does,
+ * for use within this file.
+ */
+
+void mpol_fix_fork_child_flag(struct task_struct *p)
+{
+	if (p->mempolicy)
+		p->flags |= PF_MEMPOLICY;
+	else
+		p->flags &= ~PF_MEMPOLICY;
+}
+
+static void mpol_set_task_struct_flag(void)
+{
+	mpol_fix_fork_child_flag(current);
+}
+
 /* Set the process memory policy */
 long do_set_mempolicy(int mode, nodemask_t *nodes)
 {
@@ -443,6 +465,7 @@ long do_set_mempolicy(int mode, nodemask_t *nodes)
 		return PTR_ERR(new);
 	mpol_free(current->mempolicy);
 	current->mempolicy = new;
+	mpol_set_task_struct_flag();
 	if (new && new->policy == MPOL_INTERLEAVE)
 		current->il_next = first_node(new->v.nodes);
 	return 0;
@@ -550,92 +573,18 @@ long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	return err;
 }
 
+#ifdef CONFIG_MIGRATION
 /*
  * page migration
  */
-
 static void migrate_page_add(struct page *page, struct list_head *pagelist,
 				unsigned long flags)
 {
 	/*
 	 * Avoid migrating a page that is shared with others.
 	 */
-	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
-		if (isolate_lru_page(page))
-			list_add_tail(&page->lru, pagelist);
-	}
-}
-
-/*
- * Migrate the list 'pagelist' of pages to a certain destination.
- *
- * Specify destination with either non-NULL vma or dest_node >= 0
- * Return the number of pages not migrated or error code
- */
-static int migrate_pages_to(struct list_head *pagelist,
-			struct vm_area_struct *vma, int dest)
-{
-	LIST_HEAD(newlist);
-	LIST_HEAD(moved);
-	LIST_HEAD(failed);
-	int err = 0;
-	unsigned long offset = 0;
-	int nr_pages;
-	struct page *page;
-	struct list_head *p;
-
-redo:
-	nr_pages = 0;
-	list_for_each(p, pagelist) {
-		if (vma) {
-			/*
-			 * The address passed to alloc_page_vma is used to
-			 * generate the proper interleave behavior. We fake
-			 * the address here by an increasing offset in order
-			 * to get the proper distribution of pages.
-			 *
-			 * No decision has been made as to which page
-			 * a certain old page is moved to so we cannot
-			 * specify the correct address.
-			 */
-			page = alloc_page_vma(GFP_HIGHUSER, vma,
-					offset + vma->vm_start);
-			offset += PAGE_SIZE;
-		}
-		else
-			page = alloc_pages_node(dest, GFP_HIGHUSER, 0);
-
-		if (!page) {
-			err = -ENOMEM;
-			goto out;
-		}
-		list_add_tail(&page->lru, &newlist);
-		nr_pages++;
-		if (nr_pages > MIGRATE_CHUNK_SIZE)
-			break;
-	}
-	err = migrate_pages(pagelist, &newlist, &moved, &failed);
-
-	putback_lru_pages(&moved);	/* Call release pages instead ?? */
-
-	if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist))
-		goto redo;
-out:
-	/* Return leftover allocated pages */
-	while (!list_empty(&newlist)) {
-		page = list_entry(newlist.next, struct page, lru);
-		list_del(&page->lru);
-		__free_page(page);
-	}
-	list_splice(&failed, pagelist);
-	if (err < 0)
-		return err;
-
-	/* Calculate number of leftover pages */
-	nr_pages = 0;
-	list_for_each(p, pagelist)
-		nr_pages++;
-	return nr_pages;
+	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1)
+		isolate_lru_page(page, pagelist);
 }
 
 /*
@@ -742,8 +691,23 @@ int do_migrate_pages(struct mm_struct *mm,
 	if (err < 0)
 		return err;
 	return busy;
+
 }
 
+#else
+
+static void migrate_page_add(struct page *page, struct list_head *pagelist,
+				unsigned long flags)
+{
+}
+
+int do_migrate_pages(struct mm_struct *mm,
+	const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+{
+	return -ENOSYS;
+}
+#endif
+
 long do_mbind(unsigned long start, unsigned long len,
 		unsigned long mode, nodemask_t *nmask, unsigned long flags)
 {
@@ -808,6 +772,7 @@ long do_mbind(unsigned long start, unsigned long len,
 		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	}
+
 	if (!list_empty(&pagelist))
 		putback_lru_pages(&pagelist);
 
@@ -947,7 +912,7 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
 	/*
 	 * Check if this process has the right to modify the specified
 	 * process. The right exists if the process has administrative
-	 * capabilities, superuser priviledges or the same
+	 * capabilities, superuser privileges or the same
 	 * userid as the target process.
 	 */
 	if ((current->euid != task->suid) && (current->euid != task->uid) &&
diff --git a/mm/mempool.c b/mm/mempool.c
index 1a99b80..fe6e052 100644
--- a/mm/mempool.c
+++ b/mm/mempool.c
@@ -183,8 +183,8 @@ EXPORT_SYMBOL(mempool_resize);
  */
 void mempool_destroy(mempool_t *pool)
 {
-	if (pool->curr_nr != pool->min_nr)
-		BUG();		/* There were outstanding elements */
+	/* Check for outstanding elements */
+	BUG_ON(pool->curr_nr != pool->min_nr);
 	free_pool(pool);
 }
 EXPORT_SYMBOL(mempool_destroy);
@@ -278,14 +278,56 @@ EXPORT_SYMBOL(mempool_free);
  */
 void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data)
 {
-	kmem_cache_t *mem = (kmem_cache_t *) pool_data;
+	struct kmem_cache *mem = pool_data;
 	return kmem_cache_alloc(mem, gfp_mask);
 }
 EXPORT_SYMBOL(mempool_alloc_slab);
 
 void mempool_free_slab(void *element, void *pool_data)
 {
-	kmem_cache_t *mem = (kmem_cache_t *) pool_data;
+	struct kmem_cache *mem = pool_data;
 	kmem_cache_free(mem, element);
 }
 EXPORT_SYMBOL(mempool_free_slab);
+
+/*
+ * A commonly used alloc and free fn that kmalloc/kfrees the amount of memory
+ * specfied by pool_data
+ */
+void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data)
+{
+	size_t size = (size_t)(long)pool_data;
+	return kmalloc(size, gfp_mask);
+}
+EXPORT_SYMBOL(mempool_kmalloc);
+
+void *mempool_kzalloc(gfp_t gfp_mask, void *pool_data)
+{
+	size_t size = (size_t) pool_data;
+	return kzalloc(size, gfp_mask);
+}
+EXPORT_SYMBOL(mempool_kzalloc);
+
+void mempool_kfree(void *element, void *pool_data)
+{
+	kfree(element);
+}
+EXPORT_SYMBOL(mempool_kfree);
+
+/*
+ * A simple mempool-backed page allocator that allocates pages
+ * of the order specified by pool_data.
+ */
+void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data)
+{
+	int order = (int)(long)pool_data;
+	return alloc_pages(gfp_mask, order);
+}
+EXPORT_SYMBOL(mempool_alloc_pages);
+
+void mempool_free_pages(void *element, void *pool_data)
+{
+	int order = (int)(long)pool_data;
+	__free_pages(element, order);
+}
+EXPORT_SYMBOL(mempool_free_pages);
diff --git a/mm/migrate.c b/mm/migrate.c
new file mode 100644
index 0000000..09f6e4a
--- /dev/null
+++ b/mm/migrate.c
@@ -0,0 +1,655 @@
+/*
+ * Memory Migration functionality - linux/mm/migration.c
+ *
+ * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
+ *
+ * Page migration was first developed in the context of the memory hotplug
+ * project. The main authors of the migration code are:
+ *
+ * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
+ * Hirokazu Takahashi <taka@valinux.co.jp>
+ * Dave Hansen <haveblue@us.ibm.com>
+ * Christoph Lameter <clameter@sgi.com>
+ */
+
+#include <linux/migrate.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/buffer_head.h>	/* for try_to_release_page(),
+					buffer_heads_over_limit */
+#include <linux/mm_inline.h>
+#include <linux/pagevec.h>
+#include <linux/rmap.h>
+#include <linux/topology.h>
+#include <linux/cpu.h>
+#include <linux/cpuset.h>
+#include <linux/swapops.h>
+
+#include "internal.h"
+
+#include "internal.h"
+
+/* The maximum number of pages to take off the LRU for migration */
+#define MIGRATE_CHUNK_SIZE 256
+
+#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
+
+/*
+ * Isolate one page from the LRU lists. If successful put it onto
+ * the indicated list with elevated page count.
+ *
+ * Result:
+ *  -EBUSY: page not on LRU list
+ *  0: page removed from LRU list and added to the specified list.
+ */
+int isolate_lru_page(struct page *page, struct list_head *pagelist)
+{
+	int ret = -EBUSY;
+
+	if (PageLRU(page)) {
+		struct zone *zone = page_zone(page);
+
+		spin_lock_irq(&zone->lru_lock);
+		if (PageLRU(page)) {
+			ret = 0;
+			get_page(page);
+			ClearPageLRU(page);
+			if (PageActive(page))
+				del_page_from_active_list(zone, page);
+			else
+				del_page_from_inactive_list(zone, page);
+			list_add_tail(&page->lru, pagelist);
+		}
+		spin_unlock_irq(&zone->lru_lock);
+	}
+	return ret;
+}
+
+/*
+ * migrate_prep() needs to be called after we have compiled the list of pages
+ * to be migrated using isolate_lru_page() but before we begin a series of calls
+ * to migrate_pages().
+ */
+int migrate_prep(void)
+{
+	/* Must have swap device for migration */
+	if (nr_swap_pages <= 0)
+		return -ENODEV;
+
+	/*
+	 * Clear the LRU lists so pages can be isolated.
+	 * Note that pages may be moved off the LRU after we have
+	 * drained them. Those pages will fail to migrate like other
+	 * pages that may be busy.
+	 */
+	lru_add_drain_all();
+
+	return 0;
+}
+
+static inline void move_to_lru(struct page *page)
+{
+	list_del(&page->lru);
+	if (PageActive(page)) {
+		/*
+		 * lru_cache_add_active checks that
+		 * the PG_active bit is off.
+		 */
+		ClearPageActive(page);
+		lru_cache_add_active(page);
+	} else {
+		lru_cache_add(page);
+	}
+	put_page(page);
+}
+
+/*
+ * Add isolated pages on the list back to the LRU.
+ *
+ * returns the number of pages put back.
+ */
+int putback_lru_pages(struct list_head *l)
+{
+	struct page *page;
+	struct page *page2;
+	int count = 0;
+
+	list_for_each_entry_safe(page, page2, l, lru) {
+		move_to_lru(page);
+		count++;
+	}
+	return count;
+}
+
+/*
+ * Non migratable page
+ */
+int fail_migrate_page(struct page *newpage, struct page *page)
+{
+	return -EIO;
+}
+EXPORT_SYMBOL(fail_migrate_page);
+
+/*
+ * swapout a single page
+ * page is locked upon entry, unlocked on exit
+ */
+static int swap_page(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+
+	if (page_mapped(page) && mapping)
+		if (try_to_unmap(page, 1) != SWAP_SUCCESS)
+			goto unlock_retry;
+
+	if (PageDirty(page)) {
+		/* Page is dirty, try to write it out here */
+		switch(pageout(page, mapping)) {
+		case PAGE_KEEP:
+		case PAGE_ACTIVATE:
+			goto unlock_retry;
+
+		case PAGE_SUCCESS:
+			goto retry;
+
+		case PAGE_CLEAN:
+			; /* try to free the page below */
+		}
+	}
+
+	if (PagePrivate(page)) {
+		if (!try_to_release_page(page, GFP_KERNEL) ||
+		    (!mapping && page_count(page) == 1))
+			goto unlock_retry;
+	}
+
+	if (remove_mapping(mapping, page)) {
+		/* Success */
+		unlock_page(page);
+		return 0;
+	}
+
+unlock_retry:
+	unlock_page(page);
+
+retry:
+	return -EAGAIN;
+}
+EXPORT_SYMBOL(swap_page);
+
+/*
+ * Remove references for a page and establish the new page with the correct
+ * basic settings to be able to stop accesses to the page.
+ */
+int migrate_page_remove_references(struct page *newpage,
+				struct page *page, int nr_refs)
+{
+	struct address_space *mapping = page_mapping(page);
+	struct page **radix_pointer;
+
+	/*
+	 * Avoid doing any of the following work if the page count
+	 * indicates that the page is in use or truncate has removed
+	 * the page.
+	 */
+	if (!mapping || page_mapcount(page) + nr_refs != page_count(page))
+		return -EAGAIN;
+
+	/*
+	 * Establish swap ptes for anonymous pages or destroy pte
+	 * maps for files.
+	 *
+	 * In order to reestablish file backed mappings the fault handlers
+	 * will take the radix tree_lock which may then be used to stop
+  	 * processses from accessing this page until the new page is ready.
+	 *
+	 * A process accessing via a swap pte (an anonymous page) will take a
+	 * page_lock on the old page which will block the process until the
+	 * migration attempt is complete. At that time the PageSwapCache bit
+	 * will be examined. If the page was migrated then the PageSwapCache
+	 * bit will be clear and the operation to retrieve the page will be
+	 * retried which will find the new page in the radix tree. Then a new
+	 * direct mapping may be generated based on the radix tree contents.
+	 *
+	 * If the page was not migrated then the PageSwapCache bit
+	 * is still set and the operation may continue.
+	 */
+	if (try_to_unmap(page, 1) == SWAP_FAIL)
+		/* A vma has VM_LOCKED set -> permanent failure */
+		return -EPERM;
+
+	/*
+	 * Give up if we were unable to remove all mappings.
+	 */
+	if (page_mapcount(page))
+		return -EAGAIN;
+
+	write_lock_irq(&mapping->tree_lock);
+
+	radix_pointer = (struct page **)radix_tree_lookup_slot(
+						&mapping->page_tree,
+						page_index(page));
+
+	if (!page_mapping(page) || page_count(page) != nr_refs ||
+			*radix_pointer != page) {
+		write_unlock_irq(&mapping->tree_lock);
+		return 1;
+	}
+
+	/*
+	 * Now we know that no one else is looking at the page.
+	 *
+	 * Certain minimal information about a page must be available
+	 * in order for other subsystems to properly handle the page if they
+	 * find it through the radix tree update before we are finished
+	 * copying the page.
+	 */
+	get_page(newpage);
+	newpage->index = page->index;
+	newpage->mapping = page->mapping;
+	if (PageSwapCache(page)) {
+		SetPageSwapCache(newpage);
+		set_page_private(newpage, page_private(page));
+	}
+
+	*radix_pointer = newpage;
+	__put_page(page);
+	write_unlock_irq(&mapping->tree_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(migrate_page_remove_references);
+
+/*
+ * Copy the page to its new location
+ */
+void migrate_page_copy(struct page *newpage, struct page *page)
+{
+	copy_highpage(newpage, page);
+
+	if (PageError(page))
+		SetPageError(newpage);
+	if (PageReferenced(page))
+		SetPageReferenced(newpage);
+	if (PageUptodate(page))
+		SetPageUptodate(newpage);
+	if (PageActive(page))
+		SetPageActive(newpage);
+	if (PageChecked(page))
+		SetPageChecked(newpage);
+	if (PageMappedToDisk(page))
+		SetPageMappedToDisk(newpage);
+
+	if (PageDirty(page)) {
+		clear_page_dirty_for_io(page);
+		set_page_dirty(newpage);
+ 	}
+
+	ClearPageSwapCache(page);
+	ClearPageActive(page);
+	ClearPagePrivate(page);
+	set_page_private(page, 0);
+	page->mapping = NULL;
+
+	/*
+	 * If any waiters have accumulated on the new page then
+	 * wake them up.
+	 */
+	if (PageWriteback(newpage))
+		end_page_writeback(newpage);
+}
+EXPORT_SYMBOL(migrate_page_copy);
+
+/*
+ * Common logic to directly migrate a single page suitable for
+ * pages that do not use PagePrivate.
+ *
+ * Pages are locked upon entry and exit.
+ */
+int migrate_page(struct page *newpage, struct page *page)
+{
+	int rc;
+
+	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
+
+	rc = migrate_page_remove_references(newpage, page, 2);
+
+	if (rc)
+		return rc;
+
+	migrate_page_copy(newpage, page);
+
+	/*
+	 * Remove auxiliary swap entries and replace
+	 * them with real ptes.
+	 *
+	 * Note that a real pte entry will allow processes that are not
+	 * waiting on the page lock to use the new page via the page tables
+	 * before the new page is unlocked.
+	 */
+	remove_from_swap(newpage);
+	return 0;
+}
+EXPORT_SYMBOL(migrate_page);
+
+/*
+ * migrate_pages
+ *
+ * Two lists are passed to this function. The first list
+ * contains the pages isolated from the LRU to be migrated.
+ * The second list contains new pages that the pages isolated
+ * can be moved to. If the second list is NULL then all
+ * pages are swapped out.
+ *
+ * The function returns after 10 attempts or if no pages
+ * are movable anymore because to has become empty
+ * or no retryable pages exist anymore.
+ *
+ * Return: Number of pages not migrated when "to" ran empty.
+ */
+int migrate_pages(struct list_head *from, struct list_head *to,
+		  struct list_head *moved, struct list_head *failed)
+{
+	int retry;
+	int nr_failed = 0;
+	int pass = 0;
+	struct page *page;
+	struct page *page2;
+	int swapwrite = current->flags & PF_SWAPWRITE;
+	int rc;
+
+	if (!swapwrite)
+		current->flags |= PF_SWAPWRITE;
+
+redo:
+	retry = 0;
+
+	list_for_each_entry_safe(page, page2, from, lru) {
+		struct page *newpage = NULL;
+		struct address_space *mapping;
+
+		cond_resched();
+
+		rc = 0;
+		if (page_count(page) == 1)
+			/* page was freed from under us. So we are done. */
+			goto next;
+
+		if (to && list_empty(to))
+			break;
+
+		/*
+		 * Skip locked pages during the first two passes to give the
+		 * functions holding the lock time to release the page. Later we
+		 * use lock_page() to have a higher chance of acquiring the
+		 * lock.
+		 */
+		rc = -EAGAIN;
+		if (pass > 2)
+			lock_page(page);
+		else
+			if (TestSetPageLocked(page))
+				goto next;
+
+		/*
+		 * Only wait on writeback if we have already done a pass where
+		 * we we may have triggered writeouts for lots of pages.
+		 */
+		if (pass > 0) {
+			wait_on_page_writeback(page);
+		} else {
+			if (PageWriteback(page))
+				goto unlock_page;
+		}
+
+		/*
+		 * Anonymous pages must have swap cache references otherwise
+		 * the information contained in the page maps cannot be
+		 * preserved.
+		 */
+		if (PageAnon(page) && !PageSwapCache(page)) {
+			if (!add_to_swap(page, GFP_KERNEL)) {
+				rc = -ENOMEM;
+				goto unlock_page;
+			}
+		}
+
+		if (!to) {
+			rc = swap_page(page);
+			goto next;
+		}
+
+		newpage = lru_to_page(to);
+		lock_page(newpage);
+
+		/*
+		 * Pages are properly locked and writeback is complete.
+		 * Try to migrate the page.
+		 */
+		mapping = page_mapping(page);
+		if (!mapping)
+			goto unlock_both;
+
+		if (mapping->a_ops->migratepage) {
+			/*
+			 * Most pages have a mapping and most filesystems
+			 * should provide a migration function. Anonymous
+			 * pages are part of swap space which also has its
+			 * own migration function. This is the most common
+			 * path for page migration.
+			 */
+			rc = mapping->a_ops->migratepage(newpage, page);
+			goto unlock_both;
+                }
+
+		/*
+		 * Default handling if a filesystem does not provide
+		 * a migration function. We can only migrate clean
+		 * pages so try to write out any dirty pages first.
+		 */
+		if (PageDirty(page)) {
+			switch (pageout(page, mapping)) {
+			case PAGE_KEEP:
+			case PAGE_ACTIVATE:
+				goto unlock_both;
+
+			case PAGE_SUCCESS:
+				unlock_page(newpage);
+				goto next;
+
+			case PAGE_CLEAN:
+				; /* try to migrate the page below */
+			}
+                }
+
+		/*
+		 * Buffers are managed in a filesystem specific way.
+		 * We must have no buffers or drop them.
+		 */
+		if (!page_has_buffers(page) ||
+		    try_to_release_page(page, GFP_KERNEL)) {
+			rc = migrate_page(newpage, page);
+			goto unlock_both;
+		}
+
+		/*
+		 * On early passes with mapped pages simply
+		 * retry. There may be a lock held for some
+		 * buffers that may go away. Later
+		 * swap them out.
+		 */
+		if (pass > 4) {
+			/*
+			 * Persistently unable to drop buffers..... As a
+			 * measure of last resort we fall back to
+			 * swap_page().
+			 */
+			unlock_page(newpage);
+			newpage = NULL;
+			rc = swap_page(page);
+			goto next;
+		}
+
+unlock_both:
+		unlock_page(newpage);
+
+unlock_page:
+		unlock_page(page);
+
+next:
+		if (rc == -EAGAIN) {
+			retry++;
+		} else if (rc) {
+			/* Permanent failure */
+			list_move(&page->lru, failed);
+			nr_failed++;
+		} else {
+			if (newpage) {
+				/* Successful migration. Return page to LRU */
+				move_to_lru(newpage);
+			}
+			list_move(&page->lru, moved);
+		}
+	}
+	if (retry && pass++ < 10)
+		goto redo;
+
+	if (!swapwrite)
+		current->flags &= ~PF_SWAPWRITE;
+
+	return nr_failed + retry;
+}
+
+/*
+ * Migration function for pages with buffers. This function can only be used
+ * if the underlying filesystem guarantees that no other references to "page"
+ * exist.
+ */
+int buffer_migrate_page(struct page *newpage, struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct buffer_head *bh, *head;
+	int rc;
+
+	if (!mapping)
+		return -EAGAIN;
+
+	if (!page_has_buffers(page))
+		return migrate_page(newpage, page);
+
+	head = page_buffers(page);
+
+	rc = migrate_page_remove_references(newpage, page, 3);
+
+	if (rc)
+		return rc;
+
+	bh = head;
+	do {
+		get_bh(bh);
+		lock_buffer(bh);
+		bh = bh->b_this_page;
+
+	} while (bh != head);
+
+	ClearPagePrivate(page);
+	set_page_private(newpage, page_private(page));
+	set_page_private(page, 0);
+	put_page(page);
+	get_page(newpage);
+
+	bh = head;
+	do {
+		set_bh_page(bh, newpage, bh_offset(bh));
+		bh = bh->b_this_page;
+
+	} while (bh != head);
+
+	SetPagePrivate(newpage);
+
+	migrate_page_copy(newpage, page);
+
+	bh = head;
+	do {
+		unlock_buffer(bh);
+ 		put_bh(bh);
+		bh = bh->b_this_page;
+
+	} while (bh != head);
+
+	return 0;
+}
+EXPORT_SYMBOL(buffer_migrate_page);
+
+/*
+ * Migrate the list 'pagelist' of pages to a certain destination.
+ *
+ * Specify destination with either non-NULL vma or dest_node >= 0
+ * Return the number of pages not migrated or error code
+ */
+int migrate_pages_to(struct list_head *pagelist,
+			struct vm_area_struct *vma, int dest)
+{
+	LIST_HEAD(newlist);
+	LIST_HEAD(moved);
+	LIST_HEAD(failed);
+	int err = 0;
+	unsigned long offset = 0;
+	int nr_pages;
+	struct page *page;
+	struct list_head *p;
+
+redo:
+	nr_pages = 0;
+	list_for_each(p, pagelist) {
+		if (vma) {
+			/*
+			 * The address passed to alloc_page_vma is used to
+			 * generate the proper interleave behavior. We fake
+			 * the address here by an increasing offset in order
+			 * to get the proper distribution of pages.
+			 *
+			 * No decision has been made as to which page
+			 * a certain old page is moved to so we cannot
+			 * specify the correct address.
+			 */
+			page = alloc_page_vma(GFP_HIGHUSER, vma,
+					offset + vma->vm_start);
+			offset += PAGE_SIZE;
+		}
+		else
+			page = alloc_pages_node(dest, GFP_HIGHUSER, 0);
+
+		if (!page) {
+			err = -ENOMEM;
+			goto out;
+		}
+		list_add_tail(&page->lru, &newlist);
+		nr_pages++;
+		if (nr_pages > MIGRATE_CHUNK_SIZE)
+			break;
+	}
+	err = migrate_pages(pagelist, &newlist, &moved, &failed);
+
+	putback_lru_pages(&moved);	/* Call release pages instead ?? */
+
+	if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist))
+		goto redo;
+out:
+	/* Return leftover allocated pages */
+	while (!list_empty(&newlist)) {
+		page = list_entry(newlist.next, struct page, lru);
+		list_del(&page->lru);
+		__free_page(page);
+	}
+	list_splice(&failed, pagelist);
+	if (err < 0)
+		return err;
+
+	/* Calculate number of leftover pages */
+	nr_pages = 0;
+	list_for_each(p, pagelist)
+		nr_pages++;
+	return nr_pages;
+}
diff --git a/mm/mmap.c b/mm/mmap.c
index 47556d2..4f5b570 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -612,7 +612,7 @@ again:			remove_next = 1 + (end > next->vm_end);
  * If the vma has a ->close operation then the driver probably needs to release
  * per-vma resources, so we don't attempt to merge those.
  */
-#define VM_SPECIAL (VM_IO | VM_DONTCOPY | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
 
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags)
@@ -845,14 +845,6 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags,
 	const unsigned long stack_flags
 		= VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN);
 
-#ifdef CONFIG_HUGETLB
-	if (flags & VM_HUGETLB) {
-		if (!(flags & VM_DONTCOPY))
-			mm->shared_vm += pages;
-		return;
-	}
-#endif /* CONFIG_HUGETLB */
-
 	if (file) {
 		mm->shared_vm += pages;
 		if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC)
@@ -1048,12 +1040,11 @@ munmap_back:
 	 * specific mapper. the address has already been validated, but
 	 * not unmapped, but the maps are removed from the list.
 	 */
-	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
 	if (!vma) {
 		error = -ENOMEM;
 		goto unacct_error;
 	}
-	memset(vma, 0, sizeof(*vma));
 
 	vma->vm_mm = mm;
 	vma->vm_start = addr;
@@ -1904,12 +1895,11 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
 	/*
 	 * create a vma struct for an anonymous mapping
 	 */
-	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
+	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
 	if (!vma) {
 		vm_unacct_memory(len >> PAGE_SHIFT);
 		return -ENOMEM;
 	}
-	memset(vma, 0, sizeof(*vma));
 
 	vma->vm_mm = mm;
 	vma->vm_start = addr;
diff --git a/mm/mmzone.c b/mm/mmzone.c
new file mode 100644
index 0000000..b022370
--- /dev/null
+++ b/mm/mmzone.c
@@ -0,0 +1,50 @@
+/*
+ * linux/mm/mmzone.c
+ *
+ * management codes for pgdats and zones.
+ */
+
+
+#include <linux/config.h>
+#include <linux/stddef.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+
+struct pglist_data *first_online_pgdat(void)
+{
+	return NODE_DATA(first_online_node);
+}
+
+EXPORT_SYMBOL(first_online_pgdat);
+
+struct pglist_data *next_online_pgdat(struct pglist_data *pgdat)
+{
+	int nid = next_online_node(pgdat->node_id);
+
+	if (nid == MAX_NUMNODES)
+		return NULL;
+	return NODE_DATA(nid);
+}
+EXPORT_SYMBOL(next_online_pgdat);
+
+
+/*
+ * next_zone - helper magic for for_each_zone()
+ */
+struct zone *next_zone(struct zone *zone)
+{
+	pg_data_t *pgdat = zone->zone_pgdat;
+
+	if (zone < pgdat->node_zones + MAX_NR_ZONES - 1)
+		zone++;
+	else {
+		pgdat = next_online_pgdat(pgdat);
+		if (pgdat)
+			zone = pgdat->node_zones;
+		else
+			zone = NULL;
+	}
+	return zone;
+}
+EXPORT_SYMBOL(next_zone);
+
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 653b857..4c14d42 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -124,7 +124,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	 * a MAP_NORESERVE private mapping to writable will now reserve.
 	 */
 	if (newflags & VM_WRITE) {
-		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED|VM_HUGETLB))) {
+		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_SHARED))) {
 			charged = nrpages;
 			if (security_vm_enough_memory(charged))
 				return -ENOMEM;
@@ -166,7 +166,10 @@ success:
 	 */
 	vma->vm_flags = newflags;
 	vma->vm_page_prot = newprot;
-	change_protection(vma, start, end, newprot);
+	if (is_vm_hugetlb_page(vma))
+		hugetlb_change_protection(vma, start, end, newprot);
+	else
+		change_protection(vma, start, end, newprot);
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
 	return 0;
@@ -240,11 +243,6 @@ sys_mprotect(unsigned long start, size_t len, unsigned long prot)
 
 		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */
 
-		if (is_vm_hugetlb_page(vma)) {
-			error = -EACCES;
-			goto out;
-		}
-
 		newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));
 
 		/* newflags >> 4 shift VM_MAY% in place of VM_% */
diff --git a/mm/msync.c b/mm/msync.c
index 3563a56..bc6c953 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -9,20 +9,24 @@
  */
 #include <linux/slab.h>
 #include <linux/pagemap.h>
+#include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/hugetlb.h>
+#include <linux/writeback.h>
+#include <linux/file.h>
 #include <linux/syscalls.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
-static void msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+static unsigned long msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				unsigned long addr, unsigned long end)
 {
 	pte_t *pte;
 	spinlock_t *ptl;
 	int progress = 0;
+	unsigned long ret = 0;
 
 again:
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
@@ -43,58 +47,64 @@ again:
 		if (!page)
 			continue;
 		if (ptep_clear_flush_dirty(vma, addr, pte) ||
-		    page_test_and_clear_dirty(page))
-			set_page_dirty(page);
+				page_test_and_clear_dirty(page))
+			ret += set_page_dirty(page);
 		progress += 3;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
 	if (addr != end)
 		goto again;
+	return ret;
 }
 
-static inline void msync_pmd_range(struct vm_area_struct *vma, pud_t *pud,
-				unsigned long addr, unsigned long end)
+static inline unsigned long msync_pmd_range(struct vm_area_struct *vma,
+			pud_t *pud, unsigned long addr, unsigned long end)
 {
 	pmd_t *pmd;
 	unsigned long next;
+	unsigned long ret = 0;
 
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		msync_pte_range(vma, pmd, addr, next);
+		ret += msync_pte_range(vma, pmd, addr, next);
 	} while (pmd++, addr = next, addr != end);
+	return ret;
 }
 
-static inline void msync_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
-				unsigned long addr, unsigned long end)
+static inline unsigned long msync_pud_range(struct vm_area_struct *vma,
+			pgd_t *pgd, unsigned long addr, unsigned long end)
 {
 	pud_t *pud;
 	unsigned long next;
+	unsigned long ret = 0;
 
 	pud = pud_offset(pgd, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		msync_pmd_range(vma, pud, addr, next);
+		ret += msync_pmd_range(vma, pud, addr, next);
 	} while (pud++, addr = next, addr != end);
+	return ret;
 }
 
-static void msync_page_range(struct vm_area_struct *vma,
+static unsigned long msync_page_range(struct vm_area_struct *vma,
 				unsigned long addr, unsigned long end)
 {
 	pgd_t *pgd;
 	unsigned long next;
+	unsigned long ret = 0;
 
 	/* For hugepages we can't go walking the page table normally,
 	 * but that's ok, hugetlbfs is memory based, so we don't need
 	 * to do anything more on an msync().
 	 */
 	if (vma->vm_flags & VM_HUGETLB)
-		return;
+		return 0;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(vma->vm_mm, addr);
@@ -103,8 +113,9 @@ static void msync_page_range(struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		msync_pud_range(vma, pgd, addr, next);
+		ret += msync_pud_range(vma, pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
+	return ret;
 }
 
 /*
@@ -115,53 +126,31 @@ static void msync_page_range(struct vm_area_struct *vma,
  * write out the dirty pages and wait on the writeout and check the result.
  * Or the application may run fadvise(FADV_DONTNEED) against the fd to start
  * async writeout immediately.
- * So my _not_ starting I/O in MS_ASYNC we provide complete flexibility to
+ * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
  * applications.
  */
-static int msync_interval(struct vm_area_struct *vma,
-			unsigned long addr, unsigned long end, int flags)
+static int msync_interval(struct vm_area_struct *vma, unsigned long addr,
+			unsigned long end, int flags,
+			unsigned long *nr_pages_dirtied)
 {
-	int ret = 0;
 	struct file *file = vma->vm_file;
 
 	if ((flags & MS_INVALIDATE) && (vma->vm_flags & VM_LOCKED))
 		return -EBUSY;
 
-	if (file && (vma->vm_flags & VM_SHARED)) {
-		msync_page_range(vma, addr, end);
-
-		if (flags & MS_SYNC) {
-			struct address_space *mapping = file->f_mapping;
-			int err;
-
-			ret = filemap_fdatawrite(mapping);
-			if (file->f_op && file->f_op->fsync) {
-				/*
-				 * We don't take i_mutex here because mmap_sem
-				 * is already held.
-				 */
-				err = file->f_op->fsync(file,file->f_dentry,1);
-				if (err && !ret)
-					ret = err;
-			}
-			err = filemap_fdatawait(mapping);
-			if (!ret)
-				ret = err;
-		}
-	}
-	return ret;
+	if (file && (vma->vm_flags & VM_SHARED))
+		*nr_pages_dirtied = msync_page_range(vma, addr, end);
+	return 0;
 }
 
 asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
 {
 	unsigned long end;
 	struct vm_area_struct *vma;
-	int unmapped_error, error = -EINVAL;
-
-	if (flags & MS_SYNC)
-		current->flags |= PF_SYNCWRITE;
+	int unmapped_error = 0;
+	int error = -EINVAL;
+	int done = 0;
 
-	down_read(&current->mm->mmap_sem);
 	if (flags & ~(MS_ASYNC | MS_INVALIDATE | MS_SYNC))
 		goto out;
 	if (start & ~PAGE_MASK)
@@ -180,13 +169,18 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
 	 * If the interval [start,end) covers some unmapped address ranges,
 	 * just ignore them, but return -ENOMEM at the end.
 	 */
+	down_read(&current->mm->mmap_sem);
+	if (flags & MS_SYNC)
+		current->flags |= PF_SYNCWRITE;
 	vma = find_vma(current->mm, start);
-	unmapped_error = 0;
-	for (;;) {
-		/* Still start < end. */
+	if (!vma) {
 		error = -ENOMEM;
-		if (!vma)
-			goto out;
+		goto out_unlock;
+	}
+	do {
+		unsigned long nr_pages_dirtied = 0;
+		struct file *file;
+
 		/* Here start < vma->vm_end. */
 		if (start < vma->vm_start) {
 			unmapped_error = -ENOMEM;
@@ -195,22 +189,47 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
 		/* Here vma->vm_start <= start < vma->vm_end. */
 		if (end <= vma->vm_end) {
 			if (start < end) {
-				error = msync_interval(vma, start, end, flags);
+				error = msync_interval(vma, start, end, flags,
+							&nr_pages_dirtied);
 				if (error)
-					goto out;
+					goto out_unlock;
 			}
 			error = unmapped_error;
-			goto out;
+			done = 1;
+		} else {
+			/* Here vma->vm_start <= start < vma->vm_end < end. */
+			error = msync_interval(vma, start, vma->vm_end, flags,
+						&nr_pages_dirtied);
+			if (error)
+				goto out_unlock;
 		}
-		/* Here vma->vm_start <= start < vma->vm_end < end. */
-		error = msync_interval(vma, start, vma->vm_end, flags);
-		if (error)
-			goto out;
+		file = vma->vm_file;
 		start = vma->vm_end;
-		vma = vma->vm_next;
-	}
-out:
-	up_read(&current->mm->mmap_sem);
+		if ((flags & MS_ASYNC) && file && nr_pages_dirtied) {
+			get_file(file);
+			up_read(&current->mm->mmap_sem);
+			balance_dirty_pages_ratelimited_nr(file->f_mapping,
+							nr_pages_dirtied);
+			fput(file);
+			down_read(&current->mm->mmap_sem);
+			vma = find_vma(current->mm, start);
+		} else if ((flags & MS_SYNC) && file &&
+				(vma->vm_flags & VM_SHARED)) {
+			get_file(file);
+			up_read(&current->mm->mmap_sem);
+			error = do_fsync(file, 0);
+			fput(file);
+			down_read(&current->mm->mmap_sem);
+			if (error)
+				goto out_unlock;
+			vma = find_vma(current->mm, start);
+		} else {
+			vma = vma->vm_next;
+		}
+	} while (vma && !done);
+out_unlock:
 	current->flags &= ~PF_SYNCWRITE;
+	up_read(&current->mm->mmap_sem);
+out:
 	return error;
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index 4951f47..db45efa 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -159,7 +159,7 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 	/*
 	 * kmalloc doesn't like __GFP_HIGHMEM for some reason
 	 */
-	return kmalloc(size, gfp_mask & ~__GFP_HIGHMEM);
+	return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM);
 }
 
 struct page * vmalloc_to_page(void *addr)
@@ -623,7 +623,7 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
 	 * - note that this may not return a page-aligned address if the object
 	 *   we're allocating is smaller than a page
 	 */
-	base = kmalloc(len, GFP_KERNEL);
+	base = kmalloc(len, GFP_KERNEL|__GFP_COMP);
 	if (!base)
 		goto enomem;
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 945559f..893d767 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -75,12 +75,12 @@ int vm_dirty_ratio = 40;
  * The interval between `kupdate'-style writebacks, in centiseconds
  * (hundredths of a second)
  */
-int dirty_writeback_centisecs = 5 * 100;
+int dirty_writeback_interval = 5 * HZ;
 
 /*
  * The longest number of centiseconds for which data is allowed to remain dirty
  */
-int dirty_expire_centisecs = 30 * 100;
+int dirty_expire_interval = 30 * HZ;
 
 /*
  * Flag that makes the machine dump writes/reads and block dirtyings.
@@ -88,7 +88,8 @@ int dirty_expire_centisecs = 30 * 100;
 int block_dump;
 
 /*
- * Flag that puts the machine in "laptop mode".
+ * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies:
+ * a full sync is triggered after this time elapses without any disk activity.
  */
 int laptop_mode;
 
@@ -255,8 +256,9 @@ static void balance_dirty_pages(struct address_space *mapping)
 }
 
 /**
- * balance_dirty_pages_ratelimited - balance dirty memory state
+ * balance_dirty_pages_ratelimited_nr - balance dirty memory state
  * @mapping: address_space which was dirtied
+ * @nr_pages: number of pages which the caller has just dirtied
  *
  * Processes which are dirtying memory should call in here once for each page
  * which was newly dirtied.  The function will periodically check the system's
@@ -267,10 +269,12 @@ static void balance_dirty_pages(struct address_space *mapping)
  * limit we decrease the ratelimiting by a lot, to prevent individual processes
  * from overshooting the limit by (ratelimit_pages) each.
  */
-void balance_dirty_pages_ratelimited(struct address_space *mapping)
+void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
+					unsigned long nr_pages_dirtied)
 {
-	static DEFINE_PER_CPU(int, ratelimits) = 0;
-	long ratelimit;
+	static DEFINE_PER_CPU(unsigned long, ratelimits) = 0;
+	unsigned long ratelimit;
+	unsigned long *p;
 
 	ratelimit = ratelimit_pages;
 	if (dirty_exceeded)
@@ -280,15 +284,18 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping)
 	 * Check the rate limiting. Also, we do not want to throttle real-time
 	 * tasks in balance_dirty_pages(). Period.
 	 */
-	if (get_cpu_var(ratelimits)++ >= ratelimit) {
-		__get_cpu_var(ratelimits) = 0;
-		put_cpu_var(ratelimits);
+	preempt_disable();
+	p =  &__get_cpu_var(ratelimits);
+	*p += nr_pages_dirtied;
+	if (unlikely(*p >= ratelimit)) {
+		*p = 0;
+		preempt_enable();
 		balance_dirty_pages(mapping);
 		return;
 	}
-	put_cpu_var(ratelimits);
+	preempt_enable();
 }
-EXPORT_SYMBOL(balance_dirty_pages_ratelimited);
+EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
 void throttle_vm_writeout(void)
 {
@@ -380,8 +387,8 @@ static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0);
  * just walks the superblock inode list, writing back any inodes which are
  * older than a specific point in time.
  *
- * Try to run once per dirty_writeback_centisecs.  But if a writeback event
- * takes longer than a dirty_writeback_centisecs interval, then leave a
+ * Try to run once per dirty_writeback_interval.  But if a writeback event
+ * takes longer than a dirty_writeback_interval interval, then leave a
  * one-second gap.
  *
  * older_than_this takes precedence over nr_to_write.  So we'll only write back
@@ -406,9 +413,9 @@ static void wb_kupdate(unsigned long arg)
 	sync_supers();
 
 	get_writeback_state(&wbs);
-	oldest_jif = jiffies - (dirty_expire_centisecs * HZ) / 100;
+	oldest_jif = jiffies - dirty_expire_interval;
 	start_jif = jiffies;
-	next_jif = start_jif + (dirty_writeback_centisecs * HZ) / 100;
+	next_jif = start_jif + dirty_writeback_interval;
 	nr_to_write = wbs.nr_dirty + wbs.nr_unstable +
 			(inodes_stat.nr_inodes - inodes_stat.nr_unused);
 	while (nr_to_write > 0) {
@@ -425,7 +432,7 @@ static void wb_kupdate(unsigned long arg)
 	}
 	if (time_before(next_jif, jiffies + HZ))
 		next_jif = jiffies + HZ;
-	if (dirty_writeback_centisecs)
+	if (dirty_writeback_interval)
 		mod_timer(&wb_timer, next_jif);
 }
 
@@ -435,11 +442,11 @@ 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(table, write, file, buffer, length, ppos);
-	if (dirty_writeback_centisecs) {
+	proc_dointvec_userhz_jiffies(table, write, file, buffer, length, ppos);
+	if (dirty_writeback_interval) {
 		mod_timer(&wb_timer,
-			jiffies + (dirty_writeback_centisecs * HZ) / 100);
-	} else {
+			jiffies + dirty_writeback_interval);
+		} else {
 		del_timer(&wb_timer);
 	}
 	return 0;
@@ -468,7 +475,7 @@ static void laptop_timer_fn(unsigned long unused)
  */
 void laptop_io_completion(void)
 {
-	mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode * HZ);
+	mod_timer(&laptop_mode_wb_timer, jiffies + laptop_mode);
 }
 
 /*
@@ -544,7 +551,7 @@ void __init page_writeback_init(void)
 		if (vm_dirty_ratio <= 0)
 			vm_dirty_ratio = 1;
 	}
-	mod_timer(&wb_timer, jiffies + (dirty_writeback_centisecs * HZ) / 100);
+	mod_timer(&wb_timer, jiffies + dirty_writeback_interval);
 	set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
 }
@@ -621,8 +628,6 @@ EXPORT_SYMBOL(write_one_page);
  */
 int __set_page_dirty_nobuffers(struct page *page)
 {
-	int ret = 0;
-
 	if (!TestSetPageDirty(page)) {
 		struct address_space *mapping = page_mapping(page);
 		struct address_space *mapping2;
@@ -644,8 +649,9 @@ int __set_page_dirty_nobuffers(struct page *page)
 							I_DIRTY_PAGES);
 			}
 		}
+		return 1;
 	}
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(__set_page_dirty_nobuffers);
 
@@ -675,8 +681,10 @@ int fastcall set_page_dirty(struct page *page)
 			return (*spd)(page);
 		return __set_page_dirty_buffers(page);
 	}
-	if (!PageDirty(page))
-		SetPageDirty(page);
+	if (!PageDirty(page)) {
+		if (!TestSetPageDirty(page))
+			return 1;
+	}
 	return 0;
 }
 EXPORT_SYMBOL(set_page_dirty);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 234bd48..dc523a1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -49,13 +49,11 @@ nodemask_t node_online_map __read_mostly = { { [0] = 1UL } };
 EXPORT_SYMBOL(node_online_map);
 nodemask_t node_possible_map __read_mostly = NODE_MASK_ALL;
 EXPORT_SYMBOL(node_possible_map);
-struct pglist_data *pgdat_list __read_mostly;
 unsigned long totalram_pages __read_mostly;
 unsigned long totalhigh_pages __read_mostly;
 long nr_swap_pages;
 int percpu_pagelist_fraction;
 
-static void fastcall free_hot_cold_page(struct page *page, int cold);
 static void __free_pages_ok(struct page *page, unsigned int order);
 
 /*
@@ -190,7 +188,7 @@ static void prep_compound_page(struct page *page, unsigned long order)
 	for (i = 0; i < nr_pages; i++) {
 		struct page *p = page + i;
 
-		SetPageCompound(p);
+		__SetPageCompound(p);
 		set_page_private(p, (unsigned long)page);
 	}
 }
@@ -209,10 +207,24 @@ static void destroy_compound_page(struct page *page, unsigned long order)
 		if (unlikely(!PageCompound(p) |
 				(page_private(p) != (unsigned long)page)))
 			bad_page(page);
-		ClearPageCompound(p);
+		__ClearPageCompound(p);
 	}
 }
 
+static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
+{
+	int i;
+
+	BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
+	/*
+	 * clear_highpage() will use KM_USER0, so it's a bug to use __GFP_ZERO
+	 * and __GFP_HIGHMEM from hard or soft interrupt context.
+	 */
+	BUG_ON((gfp_flags & __GFP_HIGHMEM) && in_interrupt());
+	for (i = 0; i < (1 << order); i++)
+		clear_highpage(page + i);
+}
+
 /*
  * function for dealing with page's order in buddy system.
  * zone->lock is already acquired when we use these.
@@ -423,11 +435,6 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 		mutex_debug_check_no_locks_freed(page_address(page),
 						 PAGE_SIZE<<order);
 
-#ifndef CONFIG_MMU
-	for (i = 1 ; i < (1 << order) ; ++i)
-		__put_page(page + i);
-#endif
-
 	for (i = 0 ; i < (1 << order) ; ++i)
 		reserved += free_pages_check(page + i);
 	if (reserved)
@@ -448,28 +455,23 @@ void fastcall __init __free_pages_bootmem(struct page *page, unsigned int order)
 	if (order == 0) {
 		__ClearPageReserved(page);
 		set_page_count(page, 0);
-
-		free_hot_cold_page(page, 0);
+		set_page_refcounted(page);
+		__free_page(page);
 	} else {
-		LIST_HEAD(list);
 		int loop;
 
+		prefetchw(page);
 		for (loop = 0; loop < BITS_PER_LONG; loop++) {
 			struct page *p = &page[loop];
 
-			if (loop + 16 < BITS_PER_LONG)
-				prefetchw(p + 16);
+			if (loop + 1 < BITS_PER_LONG)
+				prefetchw(p + 1);
 			__ClearPageReserved(p);
 			set_page_count(p, 0);
 		}
 
-		arch_free_page(page, order);
-
-		mod_page_state(pgfree, 1 << order);
-
-		list_add(&page->lru, &list);
-		kernel_map_pages(page, 1 << order, 0);
-		free_pages_bulk(page_zone(page), 1, &list, order);
+		set_page_refcounted(page);
+		__free_pages(page, order);
 	}
 }
 
@@ -507,7 +509,7 @@ static inline void expand(struct zone *zone, struct page *page,
 /*
  * This page is about to be returned from the page allocator
  */
-static int prep_new_page(struct page *page, int order)
+static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 {
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
@@ -536,8 +538,15 @@ static int prep_new_page(struct page *page, int order)
 			1 << PG_referenced | 1 << PG_arch_1 |
 			1 << PG_checked | 1 << PG_mappedtodisk);
 	set_page_private(page, 0);
-	set_page_refs(page, order);
+	set_page_refcounted(page);
 	kernel_map_pages(page, 1 << order, 1);
+
+	if (gfp_flags & __GFP_ZERO)
+		prep_zero_page(page, order, gfp_flags);
+
+	if (order && (gfp_flags & __GFP_COMP))
+		prep_compound_page(page, order);
+
 	return 0;
 }
 
@@ -593,13 +602,14 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
 /*
  * Called from the slab reaper to drain pagesets on a particular node that
  * belong to the currently executing processor.
+ * Note that this function must be called with the thread pinned to
+ * a single processor.
  */
 void drain_node_pages(int nodeid)
 {
 	int i, z;
 	unsigned long flags;
 
-	local_irq_save(flags);
 	for (z = 0; z < MAX_NR_ZONES; z++) {
 		struct zone *zone = NODE_DATA(nodeid)->node_zones + z;
 		struct per_cpu_pageset *pset;
@@ -609,11 +619,14 @@ void drain_node_pages(int nodeid)
 			struct per_cpu_pages *pcp;
 
 			pcp = &pset->pcp[i];
-			free_pages_bulk(zone, pcp->count, &pcp->list, 0);
-			pcp->count = 0;
+			if (pcp->count) {
+				local_irq_save(flags);
+				free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+				pcp->count = 0;
+				local_irq_restore(flags);
+			}
 		}
 	}
-	local_irq_restore(flags);
 }
 #endif
 
@@ -743,13 +756,22 @@ void fastcall free_cold_page(struct page *page)
 	free_hot_cold_page(page, 1);
 }
 
-static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
+/*
+ * split_page takes a non-compound higher-order page, and splits it into
+ * n (1<<order) sub-pages: page[0..n]
+ * Each sub-page must be freed individually.
+ *
+ * Note: this is probably too low level an operation for use in drivers.
+ * Please consult with lkml before using this in your driver.
+ */
+void split_page(struct page *page, unsigned int order)
 {
 	int i;
 
-	BUG_ON((gfp_flags & (__GFP_WAIT | __GFP_HIGHMEM)) == __GFP_HIGHMEM);
-	for(i = 0; i < (1 << order); i++)
-		clear_highpage(page + i);
+	BUG_ON(PageCompound(page));
+	BUG_ON(!page_count(page));
+	for (i = 1; i < (1 << order); i++)
+		set_page_refcounted(page + i);
 }
 
 /*
@@ -795,14 +817,8 @@ again:
 	put_cpu();
 
 	BUG_ON(bad_range(zone, page));
-	if (prep_new_page(page, order))
+	if (prep_new_page(page, order, gfp_flags))
 		goto again;
-
-	if (gfp_flags & __GFP_ZERO)
-		prep_zero_page(page, order, gfp_flags);
-
-	if (order && (gfp_flags & __GFP_COMP))
-		prep_compound_page(page, order);
 	return page;
 
 failed:
@@ -926,7 +942,8 @@ restart:
 		goto got_pg;
 
 	do {
-		wakeup_kswapd(*z, order);
+		if (cpuset_zone_allowed(*z, gfp_mask))
+			wakeup_kswapd(*z, order);
 	} while (*(++z));
 
 	/*
@@ -1183,7 +1200,7 @@ unsigned int nr_free_highpages (void)
 	pg_data_t *pgdat;
 	unsigned int pages = 0;
 
-	for_each_pgdat(pgdat)
+	for_each_online_pgdat(pgdat)
 		pages += pgdat->node_zones[ZONE_HIGHMEM].free_pages;
 
 	return pages;
@@ -1214,24 +1231,22 @@ DEFINE_PER_CPU(long, nr_pagecache_local) = 0;
 
 static void __get_page_state(struct page_state *ret, int nr, cpumask_t *cpumask)
 {
-	int cpu = 0;
+	unsigned cpu;
 
 	memset(ret, 0, nr * sizeof(unsigned long));
 	cpus_and(*cpumask, *cpumask, cpu_online_map);
 
-	cpu = first_cpu(*cpumask);
-	while (cpu < NR_CPUS) {
-		unsigned long *in, *out, off;
-
-		if (!cpu_isset(cpu, *cpumask))
-			continue;
+	for_each_cpu_mask(cpu, *cpumask) {
+		unsigned long *in;
+		unsigned long *out;
+		unsigned off;
+		unsigned next_cpu;
 
 		in = (unsigned long *)&per_cpu(page_states, cpu);
 
-		cpu = next_cpu(cpu, *cpumask);
-
-		if (likely(cpu < NR_CPUS))
-			prefetch(&per_cpu(page_states, cpu));
+		next_cpu = next_cpu(cpu, *cpumask);
+		if (likely(next_cpu < NR_CPUS))
+			prefetch(&per_cpu(page_states, next_cpu));
 
 		out = (unsigned long *)ret;
 		for (off = 0; off < nr; off++)
@@ -1327,7 +1342,7 @@ void get_zone_counts(unsigned long *active,
 	*active = 0;
 	*inactive = 0;
 	*free = 0;
-	for_each_pgdat(pgdat) {
+	for_each_online_pgdat(pgdat) {
 		unsigned long l, m, n;
 		__get_zone_counts(&l, &m, &n, pgdat);
 		*active += l;
@@ -1764,7 +1779,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 			continue;
 		page = pfn_to_page(pfn);
 		set_page_links(page, zone, nid, pfn);
-		set_page_count(page, 1);
+		init_page_count(page);
 		reset_page_mapcount(page);
 		SetPageReserved(page);
 		INIT_LIST_HEAD(&page->lru);
@@ -2013,8 +2028,9 @@ static __meminit void zone_pcp_init(struct zone *zone)
 		setup_pageset(zone_pcp(zone,cpu), batch);
 #endif
 	}
-	printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%lu\n",
-		zone->name, zone->present_pages, batch);
+	if (zone->present_pages)
+		printk(KERN_DEBUG "  %s zone: %lu pages, LIFO batch:%lu\n",
+			zone->name, zone->present_pages, batch);
 }
 
 static __meminit void init_currently_empty_zone(struct zone *zone,
@@ -2025,7 +2041,6 @@ static __meminit void init_currently_empty_zone(struct zone *zone,
 	zone_wait_table_init(zone, size);
 	pgdat->nr_zones = zone_idx(zone) + 1;
 
-	zone->zone_mem_map = pfn_to_page(zone_start_pfn);
 	zone->zone_start_pfn = zone_start_pfn;
 
 	memmap_init(size, pgdat->node_id, zone_idx(zone), zone_start_pfn);
@@ -2153,8 +2168,9 @@ static void *frag_start(struct seq_file *m, loff_t *pos)
 {
 	pg_data_t *pgdat;
 	loff_t node = *pos;
-
-	for (pgdat = pgdat_list; pgdat && node; pgdat = pgdat->pgdat_next)
+	for (pgdat = first_online_pgdat();
+	     pgdat && node;
+	     pgdat = next_online_pgdat(pgdat))
 		--node;
 
 	return pgdat;
@@ -2165,7 +2181,7 @@ static void *frag_next(struct seq_file *m, void *arg, loff_t *pos)
 	pg_data_t *pgdat = (pg_data_t *)arg;
 
 	(*pos)++;
-	return pgdat->pgdat_next;
+	return next_online_pgdat(pgdat);
 }
 
 static void frag_stop(struct seq_file *m, void *arg)
@@ -2466,7 +2482,7 @@ static void setup_per_zone_lowmem_reserve(void)
 	struct pglist_data *pgdat;
 	int j, idx;
 
-	for_each_pgdat(pgdat) {
+	for_each_online_pgdat(pgdat) {
 		for (j = 0; j < MAX_NR_ZONES; j++) {
 			struct zone *zone = pgdat->node_zones + j;
 			unsigned long present_pages = zone->present_pages;
@@ -2685,8 +2701,7 @@ void *__init alloc_large_system_hash(const char *tablename,
 		else
 			numentries <<= (PAGE_SHIFT - scale);
 	}
-	/* rounded up to nearest power of 2 in size */
-	numentries = 1UL << (long_log2(numentries) + 1);
+	numentries = roundup_pow_of_two(numentries);
 
 	/* limit allocation size to 1/16 total memory by default */
 	if (max == 0) {
@@ -2729,3 +2744,44 @@ void *__init alloc_large_system_hash(const char *tablename,
 
 	return table;
 }
+
+#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE
+/*
+ * pfn <-> page translation. out-of-line version.
+ * (see asm-generic/memory_model.h)
+ */
+#if defined(CONFIG_FLATMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+	return mem_map + (pfn - ARCH_PFN_OFFSET);
+}
+unsigned long page_to_pfn(struct page *page)
+{
+	return (page - mem_map) + ARCH_PFN_OFFSET;
+}
+#elif defined(CONFIG_DISCONTIGMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+	int nid = arch_pfn_to_nid(pfn);
+	return NODE_DATA(nid)->node_mem_map + arch_local_page_offset(pfn,nid);
+}
+unsigned long page_to_pfn(struct page *page)
+{
+	struct pglist_data *pgdat = NODE_DATA(page_to_nid(page));
+	return (page - pgdat->node_mem_map) + pgdat->node_start_pfn;
+}
+#elif defined(CONFIG_SPARSEMEM)
+struct page *pfn_to_page(unsigned long pfn)
+{
+	return __section_mem_map_addr(__pfn_to_section(pfn)) + pfn;
+}
+
+unsigned long page_to_pfn(struct page *page)
+{
+	long section_id = page_to_section(page);
+	return page - __section_mem_map_addr(__nr_to_section(section_id));
+}
+#endif /* CONFIG_FLATMEM/DISCONTIGMME/SPARSEMEM */
+EXPORT_SYMBOL(pfn_to_page);
+EXPORT_SYMBOL(page_to_pfn);
+#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */
diff --git a/mm/readahead.c b/mm/readahead.c
index 9f0b982..ba7db81 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -53,13 +53,24 @@ static inline unsigned long get_min_readahead(struct file_ra_state *ra)
 	return (VM_MIN_READAHEAD * 1024) / PAGE_CACHE_SIZE;
 }
 
+static inline void reset_ahead_window(struct file_ra_state *ra)
+{
+	/*
+	 * ... but preserve ahead_start + ahead_size value,
+	 * see 'recheck:' label in page_cache_readahead().
+	 * Note: We never use ->ahead_size as rvalue without
+	 * checking ->ahead_start != 0 first.
+	 */
+	ra->ahead_size += ra->ahead_start;
+	ra->ahead_start = 0;
+}
+
 static inline void ra_off(struct file_ra_state *ra)
 {
 	ra->start = 0;
 	ra->flags = 0;
 	ra->size = 0;
-	ra->ahead_start = 0;
-	ra->ahead_size = 0;
+	reset_ahead_window(ra);
 	return;
 }
 
@@ -73,10 +84,10 @@ static unsigned long get_init_ra_size(unsigned long size, unsigned long max)
 {
 	unsigned long newsize = roundup_pow_of_two(size);
 
-	if (newsize <= max / 64)
-		newsize = newsize * newsize;
+	if (newsize <= max / 32)
+		newsize = newsize * 4;
 	else if (newsize <= max / 4)
-		newsize = max / 4;
+		newsize = newsize * 2;
 	else
 		newsize = max;
 	return newsize;
@@ -427,8 +438,7 @@ static int make_ahead_window(struct address_space *mapping, struct file *filp,
 		 * congestion.  The ahead window will any way be closed
 		 * in case we failed due to excessive page cache hits.
 		 */
-		ra->ahead_start = 0;
-		ra->ahead_size = 0;
+		reset_ahead_window(ra);
 	}
 
 	return ret;
@@ -521,11 +531,11 @@ page_cache_readahead(struct address_space *mapping, struct file_ra_state *ra,
 	 * If we get here we are doing sequential IO and this was not the first
 	 * occurence (ie we have an existing window)
 	 */
-
 	if (ra->ahead_start == 0) {	 /* no ahead window yet */
 		if (!make_ahead_window(mapping, filp, ra, 0))
-			goto out;
+			goto recheck;
 	}
+
 	/*
 	 * Already have an ahead window, check if we crossed into it.
 	 * If so, shift windows and issue a new ahead window.
@@ -537,11 +547,16 @@ page_cache_readahead(struct address_space *mapping, struct file_ra_state *ra,
 		ra->start = ra->ahead_start;
 		ra->size = ra->ahead_size;
 		make_ahead_window(mapping, filp, ra, 0);
+recheck:
+		/* prev_page shouldn't overrun the ahead window */
+		ra->prev_page = min(ra->prev_page,
+			ra->ahead_start + ra->ahead_size - 1);
 	}
 
 out:
 	return ra->prev_page + 1;
 }
+EXPORT_SYMBOL_GPL(page_cache_readahead);
 
 /*
  * handle_ra_miss() is called when it is known that a page which should have
diff --git a/mm/rmap.c b/mm/rmap.c
index 67f0e20..1963e26 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -56,13 +56,11 @@
 
 #include <asm/tlbflush.h>
 
-//#define RMAP_DEBUG /* can be enabled only for debugging */
-
-kmem_cache_t *anon_vma_cachep;
+struct kmem_cache *anon_vma_cachep;
 
 static inline void validate_anon_vma(struct vm_area_struct *find_vma)
 {
-#ifdef RMAP_DEBUG
+#ifdef CONFIG_DEBUG_VM
 	struct anon_vma *anon_vma = find_vma->anon_vma;
 	struct vm_area_struct *vma;
 	unsigned int mapcount = 0;
@@ -166,7 +164,8 @@ void anon_vma_unlink(struct vm_area_struct *vma)
 		anon_vma_free(anon_vma);
 }
 
-static void anon_vma_ctor(void *data, kmem_cache_t *cachep, unsigned long flags)
+static void anon_vma_ctor(void *data, struct kmem_cache *cachep,
+			  unsigned long flags)
 {
 	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
 						SLAB_CTOR_CONSTRUCTOR) {
@@ -550,13 +549,14 @@ void page_add_file_rmap(struct page *page)
 void page_remove_rmap(struct page *page)
 {
 	if (atomic_add_negative(-1, &page->_mapcount)) {
-		if (page_mapcount(page) < 0) {
+#ifdef CONFIG_DEBUG_VM
+		if (unlikely(page_mapcount(page) < 0)) {
 			printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page));
 			printk (KERN_EMERG "  page->flags = %lx\n", page->flags);
 			printk (KERN_EMERG "  page->count = %x\n", page_count(page));
 			printk (KERN_EMERG "  page->mapping = %p\n", page->mapping);
 		}
-
+#endif
 		BUG_ON(page_mapcount(page) < 0);
 		/*
 		 * It would be tidy to reset the PageAnon mapping here,
diff --git a/mm/shmem.c b/mm/shmem.c
index 7c455fb..37eaf42e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -875,7 +875,7 @@ redirty:
 }
 
 #ifdef CONFIG_NUMA
-static int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
+static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
 {
 	char *nodelist = strchr(value, ':');
 	int err = 1;
@@ -2119,7 +2119,7 @@ failed:
 	return err;
 }
 
-static kmem_cache_t *shmem_inode_cachep;
+static struct kmem_cache *shmem_inode_cachep;
 
 static struct inode *shmem_alloc_inode(struct super_block *sb)
 {
@@ -2139,7 +2139,8 @@ static void shmem_destroy_inode(struct inode *inode)
 	kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
 }
 
-static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags)
+static void init_once(void *foo, struct kmem_cache *cachep,
+		      unsigned long flags)
 {
 	struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
 
diff --git a/mm/slab.c b/mm/slab.c
index d0bd7f0..4cbf8bb 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -50,7 +50,7 @@
  * The head array is strictly LIFO and should improve the cache hit rates.
  * On SMP, it additionally reduces the spinlock operations.
  *
- * The c_cpuarray may not be read with enabled local interrupts - 
+ * The c_cpuarray may not be read with enabled local interrupts -
  * it's changed with a smp_call_function().
  *
  * SMP synchronization:
@@ -94,6 +94,7 @@
 #include	<linux/interrupt.h>
 #include	<linux/init.h>
 #include	<linux/compiler.h>
+#include	<linux/cpuset.h>
 #include	<linux/seq_file.h>
 #include	<linux/notifier.h>
 #include	<linux/kallsyms.h>
@@ -170,15 +171,15 @@
 #if DEBUG
 # define CREATE_MASK	(SLAB_DEBUG_INITIAL | SLAB_RED_ZONE | \
 			 SLAB_POISON | SLAB_HWCACHE_ALIGN | \
-			 SLAB_NO_REAP | SLAB_CACHE_DMA | \
+			 SLAB_CACHE_DMA | \
 			 SLAB_MUST_HWCACHE_ALIGN | SLAB_STORE_USER | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
-			 SLAB_DESTROY_BY_RCU)
+			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
 #else
-# define CREATE_MASK	(SLAB_HWCACHE_ALIGN | SLAB_NO_REAP | \
+# define CREATE_MASK	(SLAB_HWCACHE_ALIGN | \
 			 SLAB_CACHE_DMA | SLAB_MUST_HWCACHE_ALIGN | \
 			 SLAB_RECLAIM_ACCOUNT | SLAB_PANIC | \
-			 SLAB_DESTROY_BY_RCU)
+			 SLAB_DESTROY_BY_RCU | SLAB_MEM_SPREAD)
 #endif
 
 /*
@@ -203,7 +204,8 @@
 typedef unsigned int kmem_bufctl_t;
 #define BUFCTL_END	(((kmem_bufctl_t)(~0U))-0)
 #define BUFCTL_FREE	(((kmem_bufctl_t)(~0U))-1)
-#define	SLAB_LIMIT	(((kmem_bufctl_t)(~0U))-2)
+#define	BUFCTL_ACTIVE	(((kmem_bufctl_t)(~0U))-2)
+#define	SLAB_LIMIT	(((kmem_bufctl_t)(~0U))-3)
 
 /* Max number of objs-per-slab for caches which use off-slab slabs.
  * Needed to avoid a possible looping condition in cache_grow().
@@ -266,16 +268,17 @@ struct array_cache {
 	unsigned int batchcount;
 	unsigned int touched;
 	spinlock_t lock;
-	void *entry[0];		/*
-				 * Must have this definition in here for the proper
-				 * alignment of array_cache. Also simplifies accessing
-				 * the entries.
-				 * [0] is for gcc 2.95. It should really be [].
-				 */
+	void *entry[0];	/*
+			 * Must have this definition in here for the proper
+			 * alignment of array_cache. Also simplifies accessing
+			 * the entries.
+			 * [0] is for gcc 2.95. It should really be [].
+			 */
 };
 
-/* bootstrap: The caches do not work without cpuarrays anymore,
- * but the cpuarrays are allocated from the generic caches...
+/*
+ * bootstrap: The caches do not work without cpuarrays anymore, but the
+ * cpuarrays are allocated from the generic caches...
  */
 #define BOOT_CPUCACHE_ENTRIES	1
 struct arraycache_init {
@@ -291,13 +294,13 @@ struct kmem_list3 {
 	struct list_head slabs_full;
 	struct list_head slabs_free;
 	unsigned long free_objects;
-	unsigned long next_reap;
-	int free_touched;
 	unsigned int free_limit;
 	unsigned int colour_next;	/* Per-node cache coloring */
 	spinlock_t list_lock;
 	struct array_cache *shared;	/* shared per node */
 	struct array_cache **alien;	/* on other nodes */
+	unsigned long next_reap;	/* updated without locking */
+	int free_touched;		/* updated without locking */
 };
 
 /*
@@ -310,10 +313,8 @@ struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
 #define	SIZE_L3 (1 + MAX_NUMNODES)
 
 /*
- * This function must be completely optimized away if
- * a constant is passed to it. Mostly the same as
- * what is in linux/slab.h except it returns an
- * index.
+ * This function must be completely optimized away if a constant is passed to
+ * it.  Mostly the same as what is in linux/slab.h except it returns an index.
  */
 static __always_inline int index_of(const size_t size)
 {
@@ -351,14 +352,14 @@ static void kmem_list3_init(struct kmem_list3 *parent)
 	parent->free_touched = 0;
 }
 
-#define MAKE_LIST(cachep, listp, slab, nodeid)	\
-	do {	\
-		INIT_LIST_HEAD(listp);		\
-		list_splice(&(cachep->nodelists[nodeid]->slab), listp); \
+#define MAKE_LIST(cachep, listp, slab, nodeid)				\
+	do {								\
+		INIT_LIST_HEAD(listp);					\
+		list_splice(&(cachep->nodelists[nodeid]->slab), listp);	\
 	} while (0)
 
-#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)			\
-	do {					\
+#define	MAKE_ALL_LISTS(cachep, ptr, nodeid)				\
+	do {								\
 	MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid);	\
 	MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
 	MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid);	\
@@ -373,28 +374,30 @@ static void kmem_list3_init(struct kmem_list3 *parent)
 struct kmem_cache {
 /* 1) per-cpu data, touched during every alloc/free */
 	struct array_cache *array[NR_CPUS];
+/* 2) Cache tunables. Protected by cache_chain_mutex */
 	unsigned int batchcount;
 	unsigned int limit;
 	unsigned int shared;
+
 	unsigned int buffer_size;
-/* 2) touched by every alloc & free from the backend */
+/* 3) touched by every alloc & free from the backend */
 	struct kmem_list3 *nodelists[MAX_NUMNODES];
-	unsigned int flags;	/* constant flags */
-	unsigned int num;	/* # of objs per slab */
-	spinlock_t spinlock;
 
-/* 3) cache_grow/shrink */
+	unsigned int flags;		/* constant flags */
+	unsigned int num;		/* # of objs per slab */
+
+/* 4) cache_grow/shrink */
 	/* order of pgs per slab (2^n) */
 	unsigned int gfporder;
 
 	/* force GFP flags, e.g. GFP_DMA */
 	gfp_t gfpflags;
 
-	size_t colour;		/* cache colouring range */
+	size_t colour;			/* cache colouring range */
 	unsigned int colour_off;	/* colour offset */
 	struct kmem_cache *slabp_cache;
 	unsigned int slab_size;
-	unsigned int dflags;	/* dynamic flags */
+	unsigned int dflags;		/* dynamic flags */
 
 	/* constructor func */
 	void (*ctor) (void *, struct kmem_cache *, unsigned long);
@@ -402,11 +405,11 @@ struct kmem_cache {
 	/* de-constructor func */
 	void (*dtor) (void *, struct kmem_cache *, unsigned long);
 
-/* 4) cache creation/removal */
+/* 5) cache creation/removal */
 	const char *name;
 	struct list_head next;
 
-/* 5) statistics */
+/* 6) statistics */
 #if STATS
 	unsigned long num_active;
 	unsigned long num_allocations;
@@ -438,8 +441,9 @@ struct kmem_cache {
 #define	OFF_SLAB(x)	((x)->flags & CFLGS_OFF_SLAB)
 
 #define BATCHREFILL_LIMIT	16
-/* Optimization question: fewer reaps means less 
- * probability for unnessary cpucache drain/refill cycles.
+/*
+ * Optimization question: fewer reaps means less probability for unnessary
+ * cpucache drain/refill cycles.
  *
  * OTOH the cpuarrays can contain lots of objects,
  * which could lock up otherwise freeable slabs.
@@ -453,17 +457,19 @@ struct kmem_cache {
 #define	STATS_INC_ALLOCED(x)	((x)->num_allocations++)
 #define	STATS_INC_GROWN(x)	((x)->grown++)
 #define	STATS_INC_REAPED(x)	((x)->reaped++)
-#define	STATS_SET_HIGH(x)	do { if ((x)->num_active > (x)->high_mark) \
-					(x)->high_mark = (x)->num_active; \
-				} while (0)
+#define	STATS_SET_HIGH(x)						\
+	do {								\
+		if ((x)->num_active > (x)->high_mark)			\
+			(x)->high_mark = (x)->num_active;		\
+	} while (0)
 #define	STATS_INC_ERR(x)	((x)->errors++)
 #define	STATS_INC_NODEALLOCS(x)	((x)->node_allocs++)
 #define	STATS_INC_NODEFREES(x)	((x)->node_frees++)
-#define	STATS_SET_FREEABLE(x, i) \
-				do { if ((x)->max_freeable < i) \
-					(x)->max_freeable = i; \
-				} while (0)
-
+#define	STATS_SET_FREEABLE(x, i)					\
+	do {								\
+		if ((x)->max_freeable < i)				\
+			(x)->max_freeable = i;				\
+	} while (0)
 #define STATS_INC_ALLOCHIT(x)	atomic_inc(&(x)->allochit)
 #define STATS_INC_ALLOCMISS(x)	atomic_inc(&(x)->allocmiss)
 #define STATS_INC_FREEHIT(x)	atomic_inc(&(x)->freehit)
@@ -478,9 +484,7 @@ struct kmem_cache {
 #define	STATS_INC_ERR(x)	do { } while (0)
 #define	STATS_INC_NODEALLOCS(x)	do { } while (0)
 #define	STATS_INC_NODEFREES(x)	do { } while (0)
-#define	STATS_SET_FREEABLE(x, i) \
-				do { } while (0)
-
+#define	STATS_SET_FREEABLE(x, i) do { } while (0)
 #define STATS_INC_ALLOCHIT(x)	do { } while (0)
 #define STATS_INC_ALLOCMISS(x)	do { } while (0)
 #define STATS_INC_FREEHIT(x)	do { } while (0)
@@ -488,7 +492,8 @@ struct kmem_cache {
 #endif
 
 #if DEBUG
-/* Magic nums for obj red zoning.
+/*
+ * Magic nums for obj red zoning.
  * Placed in the first word before and the first word after an obj.
  */
 #define	RED_INACTIVE	0x5A2CF071UL	/* when obj is inactive */
@@ -499,7 +504,8 @@ struct kmem_cache {
 #define POISON_FREE	0x6b	/* for use-after-free poisoning */
 #define	POISON_END	0xa5	/* end-byte of poisoning */
 
-/* memory layout of objects:
+/*
+ * memory layout of objects:
  * 0		: objp
  * 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that
  * 		the end of an object is aligned with the end of the real
@@ -508,7 +514,8 @@ struct kmem_cache {
  * 		redzone word.
  * cachep->obj_offset: The real object.
  * cachep->buffer_size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
- * cachep->buffer_size - 1* BYTES_PER_WORD: last caller address [BYTES_PER_WORD long]
+ * cachep->buffer_size - 1* BYTES_PER_WORD: last caller address
+ *					[BYTES_PER_WORD long]
  */
 static int obj_offset(struct kmem_cache *cachep)
 {
@@ -552,8 +559,8 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 #endif
 
 /*
- * Maximum size of an obj (in 2^order pages)
- * and absolute limit for the gfp order.
+ * Maximum size of an obj (in 2^order pages) and absolute limit for the gfp
+ * order.
  */
 #if defined(CONFIG_LARGE_ALLOCS)
 #define	MAX_OBJ_ORDER	13	/* up to 32Mb */
@@ -573,9 +580,10 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
 #define	BREAK_GFP_ORDER_LO	0
 static int slab_break_gfp_order = BREAK_GFP_ORDER_LO;
 
-/* Functions for storing/retrieving the cachep and or slab from the
- * global 'mem_map'. These are used to find the slab an obj belongs to.
- * With kfree(), these are used to find the cache which an obj belongs to.
+/*
+ * Functions for storing/retrieving the cachep and or slab from the page
+ * allocator.  These are used to find the slab an obj belongs to.  With kfree(),
+ * these are used to find the cache which an obj belongs to.
  */
 static inline void page_set_cache(struct page *page, struct kmem_cache *cache)
 {
@@ -584,6 +592,8 @@ static inline void page_set_cache(struct page *page, struct kmem_cache *cache)
 
 static inline struct kmem_cache *page_get_cache(struct page *page)
 {
+	if (unlikely(PageCompound(page)))
+		page = (struct page *)page_private(page);
 	return (struct kmem_cache *)page->lru.next;
 }
 
@@ -594,6 +604,8 @@ static inline void page_set_slab(struct page *page, struct slab *slab)
 
 static inline struct slab *page_get_slab(struct page *page)
 {
+	if (unlikely(PageCompound(page)))
+		page = (struct page *)page_private(page);
 	return (struct slab *)page->lru.prev;
 }
 
@@ -609,7 +621,21 @@ static inline struct slab *virt_to_slab(const void *obj)
 	return page_get_slab(page);
 }
 
-/* These are the default caches for kmalloc. Custom caches can have other sizes. */
+static inline void *index_to_obj(struct kmem_cache *cache, struct slab *slab,
+				 unsigned int idx)
+{
+	return slab->s_mem + cache->buffer_size * idx;
+}
+
+static inline unsigned int obj_to_index(struct kmem_cache *cache,
+					struct slab *slab, void *obj)
+{
+	return (unsigned)(obj - slab->s_mem) / cache->buffer_size;
+}
+
+/*
+ * These are the default caches for kmalloc. Custom caches can have other sizes.
+ */
 struct cache_sizes malloc_sizes[] = {
 #define CACHE(x) { .cs_size = (x) },
 #include <linux/kmalloc_sizes.h>
@@ -642,8 +668,6 @@ static struct kmem_cache cache_cache = {
 	.limit = BOOT_CPUCACHE_ENTRIES,
 	.shared = 1,
 	.buffer_size = sizeof(struct kmem_cache),
-	.flags = SLAB_NO_REAP,
-	.spinlock = SPIN_LOCK_UNLOCKED,
 	.name = "kmem_cache",
 #if DEBUG
 	.obj_size = sizeof(struct kmem_cache),
@@ -655,8 +679,8 @@ static DEFINE_MUTEX(cache_chain_mutex);
 static struct list_head cache_chain;
 
 /*
- * vm_enough_memory() looks at this to determine how many
- * slab-allocated pages are possibly freeable under pressure
+ * vm_enough_memory() looks at this to determine how many slab-allocated pages
+ * are possibly freeable under pressure
  *
  * SLAB_RECLAIM_ACCOUNT turns this on per-slab
  */
@@ -675,7 +699,8 @@ static enum {
 
 static DEFINE_PER_CPU(struct work_struct, reap_work);
 
-static void free_block(struct kmem_cache *cachep, void **objpp, int len, int node);
+static void free_block(struct kmem_cache *cachep, void **objpp, int len,
+			int node);
 static void enable_cpucache(struct kmem_cache *cachep);
 static void cache_reap(void *unused);
 static int __node_shrink(struct kmem_cache *cachep, int node);
@@ -685,7 +710,8 @@ static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 	return cachep->array[smp_processor_id()];
 }
 
-static inline struct kmem_cache *__find_general_cachep(size_t size, gfp_t gfpflags)
+static inline struct kmem_cache *__find_general_cachep(size_t size,
+							gfp_t gfpflags)
 {
 	struct cache_sizes *csizep = malloc_sizes;
 
@@ -720,8 +746,9 @@ static size_t slab_mgmt_size(size_t nr_objs, size_t align)
 	return ALIGN(sizeof(struct slab)+nr_objs*sizeof(kmem_bufctl_t), align);
 }
 
-/* Calculate the number of objects and left-over bytes for a given
-   buffer size. */
+/*
+ * Calculate the number of objects and left-over bytes for a given buffer size.
+ */
 static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 			   size_t align, int flags, size_t *left_over,
 			   unsigned int *num)
@@ -782,7 +809,8 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
 
 #define slab_error(cachep, msg) __slab_error(__FUNCTION__, cachep, msg)
 
-static void __slab_error(const char *function, struct kmem_cache *cachep, char *msg)
+static void __slab_error(const char *function, struct kmem_cache *cachep,
+			char *msg)
 {
 	printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
 	       function, cachep->name, msg);
@@ -804,7 +832,7 @@ static void init_reap_node(int cpu)
 
 	node = next_node(cpu_to_node(cpu), node_online_map);
 	if (node == MAX_NUMNODES)
-		node = 0;
+		node = first_node(node_online_map);
 
 	__get_cpu_var(reap_node) = node;
 }
@@ -870,8 +898,33 @@ static struct array_cache *alloc_arraycache(int node, int entries,
 	return nc;
 }
 
+/*
+ * Transfer objects in one arraycache to another.
+ * Locking must be handled by the caller.
+ *
+ * Return the number of entries transferred.
+ */
+static int transfer_objects(struct array_cache *to,
+		struct array_cache *from, unsigned int max)
+{
+	/* Figure out how many entries to transfer */
+	int nr = min(min(from->avail, max), to->limit - to->avail);
+
+	if (!nr)
+		return 0;
+
+	memcpy(to->entry + to->avail, from->entry + from->avail -nr,
+			sizeof(void *) *nr);
+
+	from->avail -= nr;
+	to->avail += nr;
+	to->touched = 1;
+	return nr;
+}
+
 #ifdef CONFIG_NUMA
 static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
+static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
 
 static struct array_cache **alloc_alien_cache(int node, int limit)
 {
@@ -906,10 +959,8 @@ static void free_alien_cache(struct array_cache **ac_ptr)
 
 	if (!ac_ptr)
 		return;
-
 	for_each_node(i)
 	    kfree(ac_ptr[i]);
-
 	kfree(ac_ptr);
 }
 
@@ -920,6 +971,13 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
 
 	if (ac->avail) {
 		spin_lock(&rl3->list_lock);
+		/*
+		 * Stuff objects into the remote nodes shared array first.
+		 * That way we could avoid the overhead of putting the objects
+		 * into the free lists and getting them back later.
+		 */
+		transfer_objects(rl3->shared, ac, ac->limit);
+
 		free_block(cachep, ac->entry, ac->avail, node);
 		ac->avail = 0;
 		spin_unlock(&rl3->list_lock);
@@ -935,15 +993,16 @@ static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
 
 	if (l3->alien) {
 		struct array_cache *ac = l3->alien[node];
-		if (ac && ac->avail) {
-			spin_lock_irq(&ac->lock);
+
+		if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
 			__drain_alien_cache(cachep, ac, node);
 			spin_unlock_irq(&ac->lock);
 		}
 	}
 }
 
-static void drain_alien_cache(struct kmem_cache *cachep, struct array_cache **alien)
+static void drain_alien_cache(struct kmem_cache *cachep,
+				struct array_cache **alien)
 {
 	int i = 0;
 	struct array_cache *ac;
@@ -986,20 +1045,22 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_UP_PREPARE:
 		mutex_lock(&cache_chain_mutex);
-		/* we need to do this right in the beginning since
+		/*
+		 * We need to do this right in the beginning since
 		 * alloc_arraycache's are going to use this list.
 		 * kmalloc_node allows us to add the slab to the right
 		 * kmem_list3 and not this cpu's kmem_list3
 		 */
 
 		list_for_each_entry(cachep, &cache_chain, next) {
-			/* setup the size64 kmemlist for cpu before we can
+			/*
+			 * Set up the size64 kmemlist for cpu before we can
 			 * begin anything. Make sure some other cpu on this
 			 * node has not already allocated this
 			 */
 			if (!cachep->nodelists[node]) {
-				if (!(l3 = kmalloc_node(memsize,
-							GFP_KERNEL, node)))
+				l3 = kmalloc_node(memsize, GFP_KERNEL, node);
+				if (!l3)
 					goto bad;
 				kmem_list3_init(l3);
 				l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
@@ -1015,13 +1076,15 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 
 			spin_lock_irq(&cachep->nodelists[node]->list_lock);
 			cachep->nodelists[node]->free_limit =
-			    (1 + nr_cpus_node(node)) *
-			    cachep->batchcount + cachep->num;
+				(1 + nr_cpus_node(node)) *
+				cachep->batchcount + cachep->num;
 			spin_unlock_irq(&cachep->nodelists[node]->list_lock);
 		}
 
-		/* Now we can go ahead with allocating the shared array's
-		   & array cache's */
+		/*
+		 * Now we can go ahead with allocating the shared arrays and
+		 * array caches
+		 */
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
 			struct array_cache *shared;
@@ -1041,7 +1104,6 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 			if (!alien)
 				goto bad;
 			cachep->array[cpu] = nc;
-
 			l3 = cachep->nodelists[node];
 			BUG_ON(!l3);
 
@@ -1061,7 +1123,6 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 			}
 #endif
 			spin_unlock_irq(&l3->list_lock);
-
 			kfree(shared);
 			free_alien_cache(alien);
 		}
@@ -1083,7 +1144,6 @@ static int __devinit cpuup_callback(struct notifier_block *nfb,
 		/* fall thru */
 	case CPU_UP_CANCELED:
 		mutex_lock(&cache_chain_mutex);
-
 		list_for_each_entry(cachep, &cache_chain, next) {
 			struct array_cache *nc;
 			struct array_cache *shared;
@@ -1150,7 +1210,7 @@ free_array_cache:
 #endif
 	}
 	return NOTIFY_OK;
-      bad:
+bad:
 	mutex_unlock(&cache_chain_mutex);
 	return NOTIFY_BAD;
 }
@@ -1160,7 +1220,8 @@ static struct notifier_block cpucache_notifier = { &cpuup_callback, NULL, 0 };
 /*
  * swap the static kmem_list3 with kmalloced memory
  */
-static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list, int nodeid)
+static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
+			int nodeid)
 {
 	struct kmem_list3 *ptr;
 
@@ -1175,8 +1236,9 @@ static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list, int no
 	local_irq_enable();
 }
 
-/* Initialisation.
- * Called after the gfp() functions have been enabled, and before smp_init().
+/*
+ * Initialisation.  Called after the page allocator have been initialised and
+ * before smp_init().
  */
 void __init kmem_cache_init(void)
 {
@@ -1201,9 +1263,9 @@ void __init kmem_cache_init(void)
 
 	/* Bootstrap is tricky, because several objects are allocated
 	 * from caches that do not exist yet:
-	 * 1) initialize the cache_cache cache: it contains the struct kmem_cache
-	 *    structures of all caches, except cache_cache itself: cache_cache
-	 *    is statically allocated.
+	 * 1) initialize the cache_cache cache: it contains the struct
+	 *    kmem_cache structures of all caches, except cache_cache itself:
+	 *    cache_cache is statically allocated.
 	 *    Initially an __init data area is used for the head array and the
 	 *    kmem_list3 structures, it's replaced with a kmalloc allocated
 	 *    array at the end of the bootstrap.
@@ -1226,7 +1288,8 @@ void __init kmem_cache_init(void)
 	cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
 	cache_cache.nodelists[numa_node_id()] = &initkmem_list3[CACHE_CACHE];
 
-	cache_cache.buffer_size = ALIGN(cache_cache.buffer_size, cache_line_size());
+	cache_cache.buffer_size = ALIGN(cache_cache.buffer_size,
+					cache_line_size());
 
 	for (order = 0; order < MAX_ORDER; order++) {
 		cache_estimate(order, cache_cache.buffer_size,
@@ -1245,24 +1308,26 @@ void __init kmem_cache_init(void)
 	sizes = malloc_sizes;
 	names = cache_names;
 
-	/* Initialize the caches that provide memory for the array cache
-	 * and the kmem_list3 structures first.
-	 * Without this, further allocations will bug
+	/*
+	 * Initialize the caches that provide memory for the array cache and the
+	 * kmem_list3 structures first.  Without this, further allocations will
+	 * bug.
 	 */
 
 	sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name,
-						      sizes[INDEX_AC].cs_size,
-						      ARCH_KMALLOC_MINALIGN,
-						      (ARCH_KMALLOC_FLAGS |
-						       SLAB_PANIC), NULL, NULL);
+					sizes[INDEX_AC].cs_size,
+					ARCH_KMALLOC_MINALIGN,
+					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
+					NULL, NULL);
 
-	if (INDEX_AC != INDEX_L3)
+	if (INDEX_AC != INDEX_L3) {
 		sizes[INDEX_L3].cs_cachep =
-		    kmem_cache_create(names[INDEX_L3].name,
-				      sizes[INDEX_L3].cs_size,
-				      ARCH_KMALLOC_MINALIGN,
-				      (ARCH_KMALLOC_FLAGS | SLAB_PANIC), NULL,
-				      NULL);
+			kmem_cache_create(names[INDEX_L3].name,
+				sizes[INDEX_L3].cs_size,
+				ARCH_KMALLOC_MINALIGN,
+				ARCH_KMALLOC_FLAGS|SLAB_PANIC,
+				NULL, NULL);
+	}
 
 	while (sizes->cs_size != ULONG_MAX) {
 		/*
@@ -1272,13 +1337,13 @@ void __init kmem_cache_init(void)
 		 * Note for systems short on memory removing the alignment will
 		 * allow tighter packing of the smaller caches.
 		 */
-		if (!sizes->cs_cachep)
+		if (!sizes->cs_cachep) {
 			sizes->cs_cachep = kmem_cache_create(names->name,
-							     sizes->cs_size,
-							     ARCH_KMALLOC_MINALIGN,
-							     (ARCH_KMALLOC_FLAGS
-							      | SLAB_PANIC),
-							     NULL, NULL);
+					sizes->cs_size,
+					ARCH_KMALLOC_MINALIGN,
+					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
+					NULL, NULL);
+		}
 
 		/* Inc off-slab bufctl limit until the ceiling is hit. */
 		if (!(OFF_SLAB(sizes->cs_cachep))) {
@@ -1287,13 +1352,11 @@ void __init kmem_cache_init(void)
 		}
 
 		sizes->cs_dmacachep = kmem_cache_create(names->name_dma,
-							sizes->cs_size,
-							ARCH_KMALLOC_MINALIGN,
-							(ARCH_KMALLOC_FLAGS |
-							 SLAB_CACHE_DMA |
-							 SLAB_PANIC), NULL,
-							NULL);
-
+					sizes->cs_size,
+					ARCH_KMALLOC_MINALIGN,
+					ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA|
+						SLAB_PANIC,
+					NULL, NULL);
 		sizes++;
 		names++;
 	}
@@ -1345,20 +1408,22 @@ void __init kmem_cache_init(void)
 		struct kmem_cache *cachep;
 		mutex_lock(&cache_chain_mutex);
 		list_for_each_entry(cachep, &cache_chain, next)
-		    enable_cpucache(cachep);
+			enable_cpucache(cachep);
 		mutex_unlock(&cache_chain_mutex);
 	}
 
 	/* Done! */
 	g_cpucache_up = FULL;
 
-	/* Register a cpu startup notifier callback
-	 * that initializes cpu_cache_get for all new cpus
+	/*
+	 * Register a cpu startup notifier callback that initializes
+	 * cpu_cache_get for all new cpus
 	 */
 	register_cpu_notifier(&cpucache_notifier);
 
-	/* The reap timers are started later, with a module init call:
-	 * That part of the kernel is not yet operational.
+	/*
+	 * The reap timers are started later, with a module init call: That part
+	 * of the kernel is not yet operational.
 	 */
 }
 
@@ -1366,16 +1431,13 @@ static int __init cpucache_init(void)
 {
 	int cpu;
 
-	/* 
-	 * Register the timers that return unneeded
-	 * pages to gfp.
+	/*
+	 * Register the timers that return unneeded pages to the page allocator
 	 */
 	for_each_online_cpu(cpu)
-	    start_cpu_timer(cpu);
-
+		start_cpu_timer(cpu);
 	return 0;
 }
-
 __initcall(cpucache_init);
 
 /*
@@ -1402,7 +1464,7 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 		atomic_add(i, &slab_reclaim_pages);
 	add_page_state(nr_slab, i);
 	while (i--) {
-		SetPageSlab(page);
+		__SetPageSlab(page);
 		page++;
 	}
 	return addr;
@@ -1418,8 +1480,8 @@ static void kmem_freepages(struct kmem_cache *cachep, void *addr)
 	const unsigned long nr_freed = i;
 
 	while (i--) {
-		if (!TestClearPageSlab(page))
-			BUG();
+		BUG_ON(!PageSlab(page));
+		__ClearPageSlab(page);
 		page++;
 	}
 	sub_page_state(nr_slab, nr_freed);
@@ -1489,9 +1551,8 @@ static void dump_line(char *data, int offset, int limit)
 {
 	int i;
 	printk(KERN_ERR "%03x:", offset);
-	for (i = 0; i < limit; i++) {
+	for (i = 0; i < limit; i++)
 		printk(" %02x", (unsigned char)data[offset + i]);
-	}
 	printk("\n");
 }
 #endif
@@ -1505,15 +1566,15 @@ static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
 
 	if (cachep->flags & SLAB_RED_ZONE) {
 		printk(KERN_ERR "Redzone: 0x%lx/0x%lx.\n",
-		       *dbg_redzone1(cachep, objp),
-		       *dbg_redzone2(cachep, objp));
+			*dbg_redzone1(cachep, objp),
+			*dbg_redzone2(cachep, objp));
 	}
 
 	if (cachep->flags & SLAB_STORE_USER) {
 		printk(KERN_ERR "Last user: [<%p>]",
-		       *dbg_userword(cachep, objp));
+			*dbg_userword(cachep, objp));
 		print_symbol("(%s)",
-			     (unsigned long)*dbg_userword(cachep, objp));
+				(unsigned long)*dbg_userword(cachep, objp));
 		printk("\n");
 	}
 	realobj = (char *)objp + obj_offset(cachep);
@@ -1546,8 +1607,8 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 			/* Print header */
 			if (lines == 0) {
 				printk(KERN_ERR
-				       "Slab corruption: start=%p, len=%d\n",
-				       realobj, size);
+					"Slab corruption: start=%p, len=%d\n",
+					realobj, size);
 				print_objinfo(cachep, objp, 0);
 			}
 			/* Hexdump the affected line */
@@ -1568,18 +1629,18 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 		 * exist:
 		 */
 		struct slab *slabp = virt_to_slab(objp);
-		int objnr;
+		unsigned int objnr;
 
-		objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
+		objnr = obj_to_index(cachep, slabp, objp);
 		if (objnr) {
-			objp = slabp->s_mem + (objnr - 1) * cachep->buffer_size;
+			objp = index_to_obj(cachep, slabp, objnr - 1);
 			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
 			       realobj, size);
 			print_objinfo(cachep, objp, 2);
 		}
 		if (objnr + 1 < cachep->num) {
-			objp = slabp->s_mem + (objnr + 1) * cachep->buffer_size;
+			objp = index_to_obj(cachep, slabp, objnr + 1);
 			realobj = (char *)objp + obj_offset(cachep);
 			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
 			       realobj, size);
@@ -1591,22 +1652,25 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 
 #if DEBUG
 /**
- * slab_destroy_objs - call the registered destructor for each object in
- *      a slab that is to be destroyed.
+ * slab_destroy_objs - destroy a slab and its objects
+ * @cachep: cache pointer being destroyed
+ * @slabp: slab pointer being destroyed
+ *
+ * Call the registered destructor for each object in a slab that is being
+ * destroyed.
  */
 static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
 {
 	int i;
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = slabp->s_mem + cachep->buffer_size * i;
+		void *objp = index_to_obj(cachep, slabp, i);
 
 		if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
-			if ((cachep->buffer_size % PAGE_SIZE) == 0
-			    && OFF_SLAB(cachep))
+			if (cachep->buffer_size % PAGE_SIZE == 0 &&
+					OFF_SLAB(cachep))
 				kernel_map_pages(virt_to_page(objp),
-						 cachep->buffer_size / PAGE_SIZE,
-						 1);
+					cachep->buffer_size / PAGE_SIZE, 1);
 			else
 				check_poison_obj(cachep, objp);
 #else
@@ -1631,7 +1695,7 @@ static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
 	if (cachep->dtor) {
 		int i;
 		for (i = 0; i < cachep->num; i++) {
-			void *objp = slabp->s_mem + cachep->buffer_size * i;
+			void *objp = index_to_obj(cachep, slabp, i);
 			(cachep->dtor) (objp, cachep, 0);
 		}
 	}
@@ -1639,9 +1703,13 @@ static void slab_destroy_objs(struct kmem_cache *cachep, struct slab *slabp)
 #endif
 
 /**
+ * slab_destroy - destroy and release all objects in a slab
+ * @cachep: cache pointer being destroyed
+ * @slabp: slab pointer being destroyed
+ *
  * Destroy all the objs in a slab, and release the mem back to the system.
- * Before calling the slab must have been unlinked from the cache.
- * The cache-lock is not held/needed.
+ * Before calling the slab must have been unlinked from the cache.  The
+ * cache-lock is not held/needed.
  */
 static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
 {
@@ -1662,8 +1730,10 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
 	}
 }
 
-/* For setting up all the kmem_list3s for cache whose buffer_size is same
-   as size of kmem_list3. */
+/*
+ * For setting up all the kmem_list3s for cache whose buffer_size is same as
+ * size of kmem_list3.
+ */
 static void set_up_list3s(struct kmem_cache *cachep, int index)
 {
 	int node;
@@ -1689,13 +1759,13 @@ static void set_up_list3s(struct kmem_cache *cachep, int index)
  * high order pages for slabs.  When the gfp() functions are more friendly
  * towards high-order requests, this should be changed.
  */
-static inline size_t calculate_slab_order(struct kmem_cache *cachep,
+static size_t calculate_slab_order(struct kmem_cache *cachep,
 			size_t size, size_t align, unsigned long flags)
 {
 	size_t left_over = 0;
 	int gfporder;
 
-	for (gfporder = 0 ; gfporder <= MAX_GFP_ORDER; gfporder++) {
+	for (gfporder = 0; gfporder <= MAX_GFP_ORDER; gfporder++) {
 		unsigned int num;
 		size_t remainder;
 
@@ -1730,12 +1800,66 @@ static inline size_t calculate_slab_order(struct kmem_cache *cachep,
 		/*
 		 * Acceptable internal fragmentation?
 		 */
-		if ((left_over * 8) <= (PAGE_SIZE << gfporder))
+		if (left_over * 8 <= (PAGE_SIZE << gfporder))
 			break;
 	}
 	return left_over;
 }
 
+static void setup_cpu_cache(struct kmem_cache *cachep)
+{
+	if (g_cpucache_up == FULL) {
+		enable_cpucache(cachep);
+		return;
+	}
+	if (g_cpucache_up == NONE) {
+		/*
+		 * Note: the first kmem_cache_create must create the cache
+		 * that's used by kmalloc(24), otherwise the creation of
+		 * further caches will BUG().
+		 */
+		cachep->array[smp_processor_id()] = &initarray_generic.cache;
+
+		/*
+		 * If the cache that's used by kmalloc(sizeof(kmem_list3)) is
+		 * the first cache, then we need to set up all its list3s,
+		 * otherwise the creation of further caches will BUG().
+		 */
+		set_up_list3s(cachep, SIZE_AC);
+		if (INDEX_AC == INDEX_L3)
+			g_cpucache_up = PARTIAL_L3;
+		else
+			g_cpucache_up = PARTIAL_AC;
+	} else {
+		cachep->array[smp_processor_id()] =
+			kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
+
+		if (g_cpucache_up == PARTIAL_AC) {
+			set_up_list3s(cachep, SIZE_L3);
+			g_cpucache_up = PARTIAL_L3;
+		} else {
+			int node;
+			for_each_online_node(node) {
+				cachep->nodelists[node] =
+				    kmalloc_node(sizeof(struct kmem_list3),
+						GFP_KERNEL, node);
+				BUG_ON(!cachep->nodelists[node]);
+				kmem_list3_init(cachep->nodelists[node]);
+			}
+		}
+	}
+	cachep->nodelists[numa_node_id()]->next_reap =
+			jiffies + REAPTIMEOUT_LIST3 +
+			((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+
+	cpu_cache_get(cachep)->avail = 0;
+	cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
+	cpu_cache_get(cachep)->batchcount = 1;
+	cpu_cache_get(cachep)->touched = 0;
+	cachep->batchcount = 1;
+	cachep->limit = BOOT_CPUCACHE_ENTRIES;
+}
+
 /**
  * kmem_cache_create - Create a cache.
  * @name: A string which is used in /proc/slabinfo to identify this cache.
@@ -1751,9 +1875,8 @@ static inline size_t calculate_slab_order(struct kmem_cache *cachep,
  * and the @dtor is run before the pages are handed back.
  *
  * @name must be valid until the cache is destroyed. This implies that
- * the module calling this has to destroy the cache before getting 
- * unloaded.
- * 
+ * the module calling this has to destroy the cache before getting unloaded.
+ *
  * The flags are
  *
  * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
@@ -1762,16 +1885,14 @@ static inline size_t calculate_slab_order(struct kmem_cache *cachep,
  * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
  * for buffer overruns.
  *
- * %SLAB_NO_REAP - Don't automatically reap this cache when we're under
- * memory pressure.
- *
  * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
  * cacheline.  This can be beneficial if you're counting cycles as closely
  * as davem.
  */
 struct kmem_cache *
 kmem_cache_create (const char *name, size_t size, size_t align,
-	unsigned long flags, void (*ctor)(void*, struct kmem_cache *, unsigned long),
+	unsigned long flags,
+	void (*ctor)(void*, struct kmem_cache *, unsigned long),
 	void (*dtor)(void*, struct kmem_cache *, unsigned long))
 {
 	size_t left_over, slab_size, ralign;
@@ -1781,12 +1902,10 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	/*
 	 * Sanity checks... these are all serious usage bugs.
 	 */
-	if ((!name) ||
-	    in_interrupt() ||
-	    (size < BYTES_PER_WORD) ||
+	if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
 	    (size > (1 << MAX_OBJ_ORDER) * PAGE_SIZE) || (dtor && !ctor)) {
-		printk(KERN_ERR "%s: Early error in slab %s\n",
-		       __FUNCTION__, name);
+		printk(KERN_ERR "%s: Early error in slab %s\n", __FUNCTION__,
+				name);
 		BUG();
 	}
 
@@ -1840,8 +1959,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	 * above the next power of two: caches with object sizes just above a
 	 * power of two have a significant amount of internal fragmentation.
 	 */
-	if ((size < 4096
-	     || fls(size - 1) == fls(size - 1 + 3 * BYTES_PER_WORD)))
+	if (size < 4096 || fls(size - 1) == fls(size-1 + 3 * BYTES_PER_WORD))
 		flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
 	if (!(flags & SLAB_DESTROY_BY_RCU))
 		flags |= SLAB_POISON;
@@ -1853,13 +1971,14 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		BUG_ON(dtor);
 
 	/*
-	 * Always checks flags, a caller might be expecting debug
-	 * support which isn't available.
+	 * Always checks flags, a caller might be expecting debug support which
+	 * isn't available.
 	 */
 	if (flags & ~CREATE_MASK)
 		BUG();
 
-	/* Check that size is in terms of words.  This is needed to avoid
+	/*
+	 * Check that size is in terms of words.  This is needed to avoid
 	 * unaligned accesses for some archs when redzoning is used, and makes
 	 * sure any on-slab bufctl's are also correctly aligned.
 	 */
@@ -1868,12 +1987,14 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		size &= ~(BYTES_PER_WORD - 1);
 	}
 
-	/* calculate out the final buffer alignment: */
+	/* calculate the final buffer alignment: */
+
 	/* 1) arch recommendation: can be overridden for debug */
 	if (flags & SLAB_HWCACHE_ALIGN) {
-		/* Default alignment: as specified by the arch code.
-		 * Except if an object is really small, then squeeze multiple
-		 * objects into one cacheline.
+		/*
+		 * Default alignment: as specified by the arch code.  Except if
+		 * an object is really small, then squeeze multiple objects into
+		 * one cacheline.
 		 */
 		ralign = cache_line_size();
 		while (size <= ralign / 2)
@@ -1893,16 +2014,16 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 		if (ralign > BYTES_PER_WORD)
 			flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
 	}
-	/* 4) Store it. Note that the debug code below can reduce
+	/*
+	 * 4) Store it. Note that the debug code below can reduce
 	 *    the alignment to BYTES_PER_WORD.
 	 */
 	align = ralign;
 
 	/* Get cache's description obj. */
-	cachep = kmem_cache_alloc(&cache_cache, SLAB_KERNEL);
+	cachep = kmem_cache_zalloc(&cache_cache, SLAB_KERNEL);
 	if (!cachep)
 		goto oops;
-	memset(cachep, 0, sizeof(struct kmem_cache));
 
 #if DEBUG
 	cachep->obj_size = size;
@@ -1978,7 +2099,6 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	cachep->gfpflags = 0;
 	if (flags & SLAB_CACHE_DMA)
 		cachep->gfpflags |= GFP_DMA;
-	spin_lock_init(&cachep->spinlock);
 	cachep->buffer_size = size;
 
 	if (flags & CFLGS_OFF_SLAB)
@@ -1988,64 +2108,11 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 	cachep->name = name;
 
 
-	if (g_cpucache_up == FULL) {
-		enable_cpucache(cachep);
-	} else {
-		if (g_cpucache_up == NONE) {
-			/* Note: the first kmem_cache_create must create
-			 * the cache that's used by kmalloc(24), otherwise
-			 * the creation of further caches will BUG().
-			 */
-			cachep->array[smp_processor_id()] =
-			    &initarray_generic.cache;
-
-			/* If the cache that's used by
-			 * kmalloc(sizeof(kmem_list3)) is the first cache,
-			 * then we need to set up all its list3s, otherwise
-			 * the creation of further caches will BUG().
-			 */
-			set_up_list3s(cachep, SIZE_AC);
-			if (INDEX_AC == INDEX_L3)
-				g_cpucache_up = PARTIAL_L3;
-			else
-				g_cpucache_up = PARTIAL_AC;
-		} else {
-			cachep->array[smp_processor_id()] =
-			    kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);
-
-			if (g_cpucache_up == PARTIAL_AC) {
-				set_up_list3s(cachep, SIZE_L3);
-				g_cpucache_up = PARTIAL_L3;
-			} else {
-				int node;
-				for_each_online_node(node) {
-
-					cachep->nodelists[node] =
-					    kmalloc_node(sizeof
-							 (struct kmem_list3),
-							 GFP_KERNEL, node);
-					BUG_ON(!cachep->nodelists[node]);
-					kmem_list3_init(cachep->
-							nodelists[node]);
-				}
-			}
-		}
-		cachep->nodelists[numa_node_id()]->next_reap =
-		    jiffies + REAPTIMEOUT_LIST3 +
-		    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
-
-		BUG_ON(!cpu_cache_get(cachep));
-		cpu_cache_get(cachep)->avail = 0;
-		cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
-		cpu_cache_get(cachep)->batchcount = 1;
-		cpu_cache_get(cachep)->touched = 0;
-		cachep->batchcount = 1;
-		cachep->limit = BOOT_CPUCACHE_ENTRIES;
-	}
+	setup_cpu_cache(cachep);
 
 	/* cache setup completed, link it into the list */
 	list_add(&cachep->next, &cache_chain);
-      oops:
+oops:
 	if (!cachep && (flags & SLAB_PANIC))
 		panic("kmem_cache_create(): failed to create slab `%s'\n",
 		      name);
@@ -2089,30 +2156,13 @@ static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
 #define check_spinlock_acquired_node(x, y) do { } while(0)
 #endif
 
-/*
- * Waits for all CPUs to execute func().
- */
-static void smp_call_function_all_cpus(void (*func)(void *arg), void *arg)
-{
-	check_irq_on();
-	preempt_disable();
-
-	local_irq_disable();
-	func(arg);
-	local_irq_enable();
-
-	if (smp_call_function(func, arg, 1, 1))
-		BUG();
-
-	preempt_enable();
-}
-
-static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac,
-				int force, int node);
+static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
+			struct array_cache *ac,
+			int force, int node);
 
 static void do_drain(void *arg)
 {
-	struct kmem_cache *cachep = (struct kmem_cache *) arg;
+	struct kmem_cache *cachep = arg;
 	struct array_cache *ac;
 	int node = numa_node_id();
 
@@ -2129,14 +2179,12 @@ static void drain_cpu_caches(struct kmem_cache *cachep)
 	struct kmem_list3 *l3;
 	int node;
 
-	smp_call_function_all_cpus(do_drain, cachep);
+	on_each_cpu(do_drain, cachep, 1, 1);
 	check_irq_on();
 	for_each_online_node(node) {
 		l3 = cachep->nodelists[node];
 		if (l3) {
-			spin_lock_irq(&l3->list_lock);
-			drain_array_locked(cachep, l3->shared, 1, node);
-			spin_unlock_irq(&l3->list_lock);
+			drain_array(cachep, l3, l3->shared, 1, node);
 			if (l3->alien)
 				drain_alien_cache(cachep, l3->alien);
 		}
@@ -2260,16 +2308,15 @@ int kmem_cache_destroy(struct kmem_cache *cachep)
 
 	/* NUMA: free the list3 structures */
 	for_each_online_node(i) {
-		if ((l3 = cachep->nodelists[i])) {
+		l3 = cachep->nodelists[i];
+		if (l3) {
 			kfree(l3->shared);
 			free_alien_cache(l3->alien);
 			kfree(l3);
 		}
 	}
 	kmem_cache_free(&cache_cache, cachep);
-
 	unlock_cpu_hotplug();
-
 	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
@@ -2292,7 +2339,6 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
 	slabp->inuse = 0;
 	slabp->colouroff = colour_off;
 	slabp->s_mem = objp + colour_off;
-
 	return slabp;
 }
 
@@ -2307,7 +2353,7 @@ static void cache_init_objs(struct kmem_cache *cachep,
 	int i;
 
 	for (i = 0; i < cachep->num; i++) {
-		void *objp = slabp->s_mem + cachep->buffer_size * i;
+		void *objp = index_to_obj(cachep, slabp, i);
 #if DEBUG
 		/* need to poison the objs? */
 		if (cachep->flags & SLAB_POISON)
@@ -2320,9 +2366,9 @@ static void cache_init_objs(struct kmem_cache *cachep,
 			*dbg_redzone2(cachep, objp) = RED_INACTIVE;
 		}
 		/*
-		 * Constructors are not allowed to allocate memory from
-		 * the same cache which they are a constructor for.
-		 * Otherwise, deadlock. They must also be threaded.
+		 * Constructors are not allowed to allocate memory from the same
+		 * cache which they are a constructor for.  Otherwise, deadlock.
+		 * They must also be threaded.
 		 */
 		if (cachep->ctor && !(cachep->flags & SLAB_POISON))
 			cachep->ctor(objp + obj_offset(cachep), cachep,
@@ -2336,8 +2382,8 @@ static void cache_init_objs(struct kmem_cache *cachep,
 				slab_error(cachep, "constructor overwrote the"
 					   " start of an object");
 		}
-		if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)
-		    && cachep->flags & SLAB_POISON)
+		if ((cachep->buffer_size % PAGE_SIZE) == 0 &&
+			    OFF_SLAB(cachep) && cachep->flags & SLAB_POISON)
 			kernel_map_pages(virt_to_page(objp),
 					 cachep->buffer_size / PAGE_SIZE, 0);
 #else
@@ -2352,18 +2398,16 @@ static void cache_init_objs(struct kmem_cache *cachep,
 
 static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
 {
-	if (flags & SLAB_DMA) {
-		if (!(cachep->gfpflags & GFP_DMA))
-			BUG();
-	} else {
-		if (cachep->gfpflags & GFP_DMA)
-			BUG();
-	}
+	if (flags & SLAB_DMA)
+		BUG_ON(!(cachep->gfpflags & GFP_DMA));
+	else
+		BUG_ON(cachep->gfpflags & GFP_DMA);
 }
 
-static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp, int nodeid)
+static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp,
+				int nodeid)
 {
-	void *objp = slabp->s_mem + (slabp->free * cachep->buffer_size);
+	void *objp = index_to_obj(cachep, slabp, slabp->free);
 	kmem_bufctl_t next;
 
 	slabp->inuse++;
@@ -2377,18 +2421,18 @@ static void *slab_get_obj(struct kmem_cache *cachep, struct slab *slabp, int nod
 	return objp;
 }
 
-static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, void *objp,
-			  int nodeid)
+static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
+				void *objp, int nodeid)
 {
-	unsigned int objnr = (unsigned)(objp-slabp->s_mem) / cachep->buffer_size;
+	unsigned int objnr = obj_to_index(cachep, slabp, objp);
 
 #if DEBUG
 	/* Verify that the slab belongs to the intended node */
 	WARN_ON(slabp->nodeid != nodeid);
 
-	if (slab_bufctl(slabp)[objnr] != BUFCTL_FREE) {
+	if (slab_bufctl(slabp)[objnr] + 1 <= SLAB_LIMIT + 1) {
 		printk(KERN_ERR "slab: double free detected in cache "
-		       "'%s', objp %p\n", cachep->name, objp);
+				"'%s', objp %p\n", cachep->name, objp);
 		BUG();
 	}
 #endif
@@ -2397,14 +2441,18 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp, void *ob
 	slabp->inuse--;
 }
 
-static void set_slab_attr(struct kmem_cache *cachep, struct slab *slabp, void *objp)
+static void set_slab_attr(struct kmem_cache *cachep, struct slab *slabp,
+			void *objp)
 {
 	int i;
 	struct page *page;
 
 	/* Nasty!!!!!! I hope this is OK. */
-	i = 1 << cachep->gfporder;
 	page = virt_to_page(objp);
+
+	i = 1;
+	if (likely(!PageCompound(page)))
+		i <<= cachep->gfporder;
 	do {
 		page_set_cache(page, cachep);
 		page_set_slab(page, slabp);
@@ -2425,8 +2473,9 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	unsigned long ctor_flags;
 	struct kmem_list3 *l3;
 
-	/* Be lazy and only check for valid flags here,
-	 * keeping it out of the critical path in kmem_cache_alloc().
+	/*
+	 * Be lazy and only check for valid flags here,  keeping it out of the
+	 * critical path in kmem_cache_alloc().
 	 */
 	if (flags & ~(SLAB_DMA | SLAB_LEVEL_MASK | SLAB_NO_GROW))
 		BUG();
@@ -2467,14 +2516,17 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	 */
 	kmem_flagcheck(cachep, flags);
 
-	/* Get mem for the objs.
-	 * Attempt to allocate a physical page from 'nodeid',
+	/*
+	 * Get mem for the objs.  Attempt to allocate a physical page from
+	 * 'nodeid'.
 	 */
-	if (!(objp = kmem_getpages(cachep, flags, nodeid)))
+	objp = kmem_getpages(cachep, flags, nodeid);
+	if (!objp)
 		goto failed;
 
 	/* Get slab management. */
-	if (!(slabp = alloc_slabmgmt(cachep, objp, offset, local_flags)))
+	slabp = alloc_slabmgmt(cachep, objp, offset, local_flags);
+	if (!slabp)
 		goto opps1;
 
 	slabp->nodeid = nodeid;
@@ -2493,9 +2545,9 @@ static int cache_grow(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	l3->free_objects += cachep->num;
 	spin_unlock(&l3->list_lock);
 	return 1;
-      opps1:
+opps1:
 	kmem_freepages(cachep, objp);
-      failed:
+failed:
 	if (local_flags & __GFP_WAIT)
 		local_irq_disable();
 	return 0;
@@ -2538,8 +2590,8 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	page = virt_to_page(objp);
 
 	if (page_get_cache(page) != cachep) {
-		printk(KERN_ERR
-		       "mismatch in kmem_cache_free: expected cache %p, got %p\n",
+		printk(KERN_ERR "mismatch in kmem_cache_free: expected "
+				"cache %p, got %p\n",
 		       page_get_cache(page), cachep);
 		printk(KERN_ERR "%p is %s.\n", cachep, cachep->name);
 		printk(KERN_ERR "%p is %s.\n", page_get_cache(page),
@@ -2549,13 +2601,12 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	slabp = page_get_slab(page);
 
 	if (cachep->flags & SLAB_RED_ZONE) {
-		if (*dbg_redzone1(cachep, objp) != RED_ACTIVE
-		    || *dbg_redzone2(cachep, objp) != RED_ACTIVE) {
-			slab_error(cachep,
-				   "double free, or memory outside"
-				   " object was overwritten");
-			printk(KERN_ERR
-			       "%p: redzone 1: 0x%lx, redzone 2: 0x%lx.\n",
+		if (*dbg_redzone1(cachep, objp) != RED_ACTIVE ||
+				*dbg_redzone2(cachep, objp) != RED_ACTIVE) {
+			slab_error(cachep, "double free, or memory outside"
+						" object was overwritten");
+			printk(KERN_ERR "%p: redzone 1:0x%lx, "
+					"redzone 2:0x%lx.\n",
 			       objp, *dbg_redzone1(cachep, objp),
 			       *dbg_redzone2(cachep, objp));
 		}
@@ -2565,15 +2616,16 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 	if (cachep->flags & SLAB_STORE_USER)
 		*dbg_userword(cachep, objp) = caller;
 
-	objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
+	objnr = obj_to_index(cachep, slabp, objp);
 
 	BUG_ON(objnr >= cachep->num);
-	BUG_ON(objp != slabp->s_mem + objnr * cachep->buffer_size);
+	BUG_ON(objp != index_to_obj(cachep, slabp, objnr));
 
 	if (cachep->flags & SLAB_DEBUG_INITIAL) {
-		/* Need to call the slab's constructor so the
-		 * caller can perform a verify of its state (debugging).
-		 * Called without the cache-lock held.
+		/*
+		 * Need to call the slab's constructor so the caller can
+		 * perform a verify of its state (debugging).  Called without
+		 * the cache-lock held.
 		 */
 		cachep->ctor(objp + obj_offset(cachep),
 			     cachep, SLAB_CTOR_CONSTRUCTOR | SLAB_CTOR_VERIFY);
@@ -2584,9 +2636,12 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
 		 */
 		cachep->dtor(objp + obj_offset(cachep), cachep, 0);
 	}
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+	slab_bufctl(slabp)[objnr] = BUFCTL_FREE;
+#endif
 	if (cachep->flags & SLAB_POISON) {
 #ifdef CONFIG_DEBUG_PAGEALLOC
-		if ((cachep->buffer_size % PAGE_SIZE) == 0 && OFF_SLAB(cachep)) {
+		if ((cachep->buffer_size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
 			store_stackinfo(cachep, objp, (unsigned long)caller);
 			kernel_map_pages(virt_to_page(objp),
 					 cachep->buffer_size / PAGE_SIZE, 0);
@@ -2612,14 +2667,14 @@ static void check_slabp(struct kmem_cache *cachep, struct slab *slabp)
 			goto bad;
 	}
 	if (entries != cachep->num - slabp->inuse) {
-	      bad:
-		printk(KERN_ERR
-		       "slab: Internal list corruption detected in cache '%s'(%d), slabp %p(%d). Hexdump:\n",
-		       cachep->name, cachep->num, slabp, slabp->inuse);
+bad:
+		printk(KERN_ERR "slab: Internal list corruption detected in "
+				"cache '%s'(%d), slabp %p(%d). Hexdump:\n",
+			cachep->name, cachep->num, slabp, slabp->inuse);
 		for (i = 0;
 		     i < sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t);
 		     i++) {
-			if ((i % 16) == 0)
+			if (i % 16 == 0)
 				printk("\n%03x:", i);
 			printk(" %02x", ((unsigned char *)slabp)[i]);
 		}
@@ -2641,12 +2696,13 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
 
 	check_irq_off();
 	ac = cpu_cache_get(cachep);
-      retry:
+retry:
 	batchcount = ac->batchcount;
 	if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
-		/* if there was little recent activity on this
-		 * cache, then perform only a partial refill.
-		 * Otherwise we could generate refill bouncing.
+		/*
+		 * If there was little recent activity on this cache, then
+		 * perform only a partial refill.  Otherwise we could generate
+		 * refill bouncing.
 		 */
 		batchcount = BATCHREFILL_LIMIT;
 	}
@@ -2655,20 +2711,10 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
 	BUG_ON(ac->avail > 0 || !l3);
 	spin_lock(&l3->list_lock);
 
-	if (l3->shared) {
-		struct array_cache *shared_array = l3->shared;
-		if (shared_array->avail) {
-			if (batchcount > shared_array->avail)
-				batchcount = shared_array->avail;
-			shared_array->avail -= batchcount;
-			ac->avail = batchcount;
-			memcpy(ac->entry,
-			       &(shared_array->entry[shared_array->avail]),
-			       sizeof(void *) * batchcount);
-			shared_array->touched = 1;
-			goto alloc_done;
-		}
-	}
+	/* See if we can refill from the shared array */
+	if (l3->shared && transfer_objects(ac, l3->shared, batchcount))
+		goto alloc_done;
+
 	while (batchcount > 0) {
 		struct list_head *entry;
 		struct slab *slabp;
@@ -2702,29 +2748,29 @@ static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
 			list_add(&slabp->list, &l3->slabs_partial);
 	}
 
-      must_grow:
+must_grow:
 	l3->free_objects -= ac->avail;
-      alloc_done:
+alloc_done:
 	spin_unlock(&l3->list_lock);
 
 	if (unlikely(!ac->avail)) {
 		int x;
 		x = cache_grow(cachep, flags, numa_node_id());
 
-		// cache_grow can reenable interrupts, then ac could change.
+		/* cache_grow can reenable interrupts, then ac could change. */
 		ac = cpu_cache_get(cachep);
-		if (!x && ac->avail == 0)	// no objects in sight? abort
+		if (!x && ac->avail == 0)	/* no objects in sight? abort */
 			return NULL;
 
-		if (!ac->avail)	// objects refilled by interrupt?
+		if (!ac->avail)		/* objects refilled by interrupt? */
 			goto retry;
 	}
 	ac->touched = 1;
 	return ac->entry[--ac->avail];
 }
 
-static inline void
-cache_alloc_debugcheck_before(struct kmem_cache *cachep, gfp_t flags)
+static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
+						gfp_t flags)
 {
 	might_sleep_if(flags & __GFP_WAIT);
 #if DEBUG
@@ -2733,8 +2779,8 @@ cache_alloc_debugcheck_before(struct kmem_cache *cachep, gfp_t flags)
 }
 
 #if DEBUG
-static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags,
-					void *objp, void *caller)
+static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
+				gfp_t flags, void *objp, void *caller)
 {
 	if (!objp)
 		return objp;
@@ -2754,19 +2800,28 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep, gfp_t flags
 		*dbg_userword(cachep, objp) = caller;
 
 	if (cachep->flags & SLAB_RED_ZONE) {
-		if (*dbg_redzone1(cachep, objp) != RED_INACTIVE
-		    || *dbg_redzone2(cachep, objp) != RED_INACTIVE) {
-			slab_error(cachep,
-				   "double free, or memory outside"
-				   " object was overwritten");
+		if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
+				*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
+			slab_error(cachep, "double free, or memory outside"
+						" object was overwritten");
 			printk(KERN_ERR
-			       "%p: redzone 1: 0x%lx, redzone 2: 0x%lx.\n",
-			       objp, *dbg_redzone1(cachep, objp),
-			       *dbg_redzone2(cachep, objp));
+				"%p: redzone 1:0x%lx, redzone 2:0x%lx\n",
+				objp, *dbg_redzone1(cachep, objp),
+				*dbg_redzone2(cachep, objp));
 		}
 		*dbg_redzone1(cachep, objp) = RED_ACTIVE;
 		*dbg_redzone2(cachep, objp) = RED_ACTIVE;
 	}
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+	{
+		struct slab *slabp;
+		unsigned objnr;
+
+		slabp = page_get_slab(virt_to_page(objp));
+		objnr = (unsigned)(objp - slabp->s_mem) / cachep->buffer_size;
+		slab_bufctl(slabp)[objnr] = BUFCTL_ACTIVE;
+	}
+#endif
 	objp += obj_offset(cachep);
 	if (cachep->ctor && cachep->flags & SLAB_POISON) {
 		unsigned long ctor_flags = SLAB_CTOR_CONSTRUCTOR;
@@ -2788,11 +2843,10 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 	struct array_cache *ac;
 
 #ifdef CONFIG_NUMA
-	if (unlikely(current->mempolicy && !in_interrupt())) {
-		int nid = slab_node(current->mempolicy);
-
-		if (nid != numa_node_id())
-			return __cache_alloc_node(cachep, flags, nid);
+	if (unlikely(current->flags & (PF_SPREAD_SLAB | PF_MEMPOLICY))) {
+		objp = alternate_node_alloc(cachep, flags);
+		if (objp != NULL)
+			return objp;
 	}
 #endif
 
@@ -2809,8 +2863,8 @@ static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 	return objp;
 }
 
-static __always_inline void *
-__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
+static __always_inline void *__cache_alloc(struct kmem_cache *cachep,
+						gfp_t flags, void *caller)
 {
 	unsigned long save_flags;
 	void *objp;
@@ -2828,9 +2882,32 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 
 #ifdef CONFIG_NUMA
 /*
+ * Try allocating on another node if PF_SPREAD_SLAB|PF_MEMPOLICY.
+ *
+ * If we are in_interrupt, then process context, including cpusets and
+ * mempolicy, may not apply and should not be used for allocation policy.
+ */
+static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
+{
+	int nid_alloc, nid_here;
+
+	if (in_interrupt())
+		return NULL;
+	nid_alloc = nid_here = numa_node_id();
+	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
+		nid_alloc = cpuset_mem_spread_node();
+	else if (current->mempolicy)
+		nid_alloc = slab_node(current->mempolicy);
+	if (nid_alloc != nid_here)
+		return __cache_alloc_node(cachep, flags, nid_alloc);
+	return NULL;
+}
+
+/*
  * A interface to enable slab creation on nodeid
  */
-static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
+static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
+				int nodeid)
 {
 	struct list_head *entry;
 	struct slab *slabp;
@@ -2841,7 +2918,7 @@ static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int node
 	l3 = cachep->nodelists[nodeid];
 	BUG_ON(!l3);
 
-      retry:
+retry:
 	check_irq_off();
 	spin_lock(&l3->list_lock);
 	entry = l3->slabs_partial.next;
@@ -2868,16 +2945,15 @@ static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int node
 	/* move slabp to correct slabp list: */
 	list_del(&slabp->list);
 
-	if (slabp->free == BUFCTL_END) {
+	if (slabp->free == BUFCTL_END)
 		list_add(&slabp->list, &l3->slabs_full);
-	} else {
+	else
 		list_add(&slabp->list, &l3->slabs_partial);
-	}
 
 	spin_unlock(&l3->list_lock);
 	goto done;
 
-      must_grow:
+must_grow:
 	spin_unlock(&l3->list_lock);
 	x = cache_grow(cachep, flags, nodeid);
 
@@ -2885,7 +2961,7 @@ static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int node
 		return NULL;
 
 	goto retry;
-      done:
+done:
 	return obj;
 }
 #endif
@@ -2958,7 +3034,7 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
 	}
 
 	free_block(cachep, ac->entry, batchcount, node);
-      free_done:
+free_done:
 #if STATS
 	{
 		int i = 0;
@@ -2979,16 +3055,12 @@ static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
 #endif
 	spin_unlock(&l3->list_lock);
 	ac->avail -= batchcount;
-	memmove(ac->entry, &(ac->entry[batchcount]),
-		sizeof(void *) * ac->avail);
+	memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
 }
 
 /*
- * __cache_free
- * Release an obj back to its cache. If the obj has a constructed
- * state, it must be in this state _before_ it is released.
- *
- * Called with disabled ints.
+ * Release an obj back to its cache. If the obj has a constructed state, it must
+ * be in this state _before_ it is released.  Called with disabled ints.
  */
 static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 {
@@ -3007,9 +3079,9 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp)
 		if (unlikely(slabp->nodeid != numa_node_id())) {
 			struct array_cache *alien = NULL;
 			int nodeid = slabp->nodeid;
-			struct kmem_list3 *l3 =
-			    cachep->nodelists[numa_node_id()];
+			struct kmem_list3 *l3;
 
+			l3 = cachep->nodelists[numa_node_id()];
 			STATS_INC_NODEFREES(cachep);
 			if (l3->alien && l3->alien[nodeid]) {
 				alien = l3->alien[nodeid];
@@ -3056,6 +3128,23 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 EXPORT_SYMBOL(kmem_cache_alloc);
 
 /**
+ * kmem_cache_alloc - Allocate an object. The memory is set to zero.
+ * @cache: The cache to allocate from.
+ * @flags: See kmalloc().
+ *
+ * Allocate an object from this cache and set the allocated memory to zero.
+ * The flags are only relevant if the cache has no available objects.
+ */
+void *kmem_cache_zalloc(struct kmem_cache *cache, gfp_t flags)
+{
+	void *ret = __cache_alloc(cache, flags, __builtin_return_address(0));
+	if (ret)
+		memset(ret, 0, obj_size(cache));
+	return ret;
+}
+EXPORT_SYMBOL(kmem_cache_zalloc);
+
+/**
  * kmem_ptr_validate - check if an untrusted pointer might
  *	be a slab entry.
  * @cachep: the cache we're checking against
@@ -3093,7 +3182,7 @@ int fastcall kmem_ptr_validate(struct kmem_cache *cachep, void *ptr)
 	if (unlikely(page_get_cache(page) != cachep))
 		goto out;
 	return 1;
-      out:
+out:
 	return 0;
 }
 
@@ -3119,7 +3208,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 	local_irq_save(save_flags);
 
 	if (nodeid == -1 || nodeid == numa_node_id() ||
-	    !cachep->nodelists[nodeid])
+			!cachep->nodelists[nodeid])
 		ptr = ____cache_alloc(cachep, flags);
 	else
 		ptr = __cache_alloc_node(cachep, flags, nodeid);
@@ -3148,6 +3237,7 @@ EXPORT_SYMBOL(kmalloc_node);
  * kmalloc - allocate memory
  * @size: how many bytes of memory are required.
  * @flags: the type of memory to allocate.
+ * @caller: function caller for debug tracking of the caller
  *
  * kmalloc is the normal method of allocating memory
  * in the kernel.
@@ -3181,22 +3271,23 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	return __cache_alloc(cachep, flags, caller);
 }
 
-#ifndef CONFIG_DEBUG_SLAB
 
 void *__kmalloc(size_t size, gfp_t flags)
 {
+#ifndef CONFIG_DEBUG_SLAB
 	return __do_kmalloc(size, flags, NULL);
+#else
+	return __do_kmalloc(size, flags, __builtin_return_address(0));
+#endif
 }
 EXPORT_SYMBOL(__kmalloc);
 
-#else
-
+#ifdef CONFIG_DEBUG_SLAB
 void *__kmalloc_track_caller(size_t size, gfp_t flags, void *caller)
 {
 	return __do_kmalloc(size, flags, caller);
 }
 EXPORT_SYMBOL(__kmalloc_track_caller);
-
 #endif
 
 #ifdef CONFIG_SMP
@@ -3220,7 +3311,7 @@ void *__alloc_percpu(size_t size)
 	 * and we have no way of figuring out how to fix the array
 	 * that we have allocated then....
 	 */
-	for_each_cpu(i) {
+	for_each_possible_cpu(i) {
 		int node = cpu_to_node(i);
 
 		if (node_online(node))
@@ -3236,7 +3327,7 @@ void *__alloc_percpu(size_t size)
 	/* Catch derefs w/o wrappers */
 	return (void *)(~(unsigned long)pdata);
 
-      unwind_oom:
+unwind_oom:
 	while (--i >= 0) {
 		if (!cpu_possible(i))
 			continue;
@@ -3307,7 +3398,7 @@ void free_percpu(const void *objp)
 	/*
 	 * We allocate for all cpus so we cannot use for online cpu here.
 	 */
-	for_each_cpu(i)
+	for_each_possible_cpu(i)
 	    kfree(p->ptrs[i]);
 	kfree(p);
 }
@@ -3327,61 +3418,86 @@ const char *kmem_cache_name(struct kmem_cache *cachep)
 EXPORT_SYMBOL_GPL(kmem_cache_name);
 
 /*
- * This initializes kmem_list3 for all nodes.
+ * This initializes kmem_list3 or resizes varioius caches for all nodes.
  */
 static int alloc_kmemlist(struct kmem_cache *cachep)
 {
 	int node;
 	struct kmem_list3 *l3;
-	int err = 0;
+	struct array_cache *new_shared;
+	struct array_cache **new_alien;
 
 	for_each_online_node(node) {
-		struct array_cache *nc = NULL, *new;
-		struct array_cache **new_alien = NULL;
-#ifdef CONFIG_NUMA
-		if (!(new_alien = alloc_alien_cache(node, cachep->limit)))
+
+		new_alien = alloc_alien_cache(node, cachep->limit);
+		if (!new_alien)
 			goto fail;
-#endif
-		if (!(new = alloc_arraycache(node, (cachep->shared *
-						    cachep->batchcount),
-					     0xbaadf00d)))
+
+		new_shared = alloc_arraycache(node,
+				cachep->shared*cachep->batchcount,
+					0xbaadf00d);
+		if (!new_shared) {
+			free_alien_cache(new_alien);
 			goto fail;
-		if ((l3 = cachep->nodelists[node])) {
+		}
+
+		l3 = cachep->nodelists[node];
+		if (l3) {
+			struct array_cache *shared = l3->shared;
 
 			spin_lock_irq(&l3->list_lock);
 
-			if ((nc = cachep->nodelists[node]->shared))
-				free_block(cachep, nc->entry, nc->avail, node);
+			if (shared)
+				free_block(cachep, shared->entry,
+						shared->avail, node);
 
-			l3->shared = new;
-			if (!cachep->nodelists[node]->alien) {
+			l3->shared = new_shared;
+			if (!l3->alien) {
 				l3->alien = new_alien;
 				new_alien = NULL;
 			}
 			l3->free_limit = (1 + nr_cpus_node(node)) *
-			    cachep->batchcount + cachep->num;
+					cachep->batchcount + cachep->num;
 			spin_unlock_irq(&l3->list_lock);
-			kfree(nc);
+			kfree(shared);
 			free_alien_cache(new_alien);
 			continue;
 		}
-		if (!(l3 = kmalloc_node(sizeof(struct kmem_list3),
-					GFP_KERNEL, node)))
+		l3 = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, node);
+		if (!l3) {
+			free_alien_cache(new_alien);
+			kfree(new_shared);
 			goto fail;
+		}
 
 		kmem_list3_init(l3);
 		l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
-		    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
-		l3->shared = new;
+				((unsigned long)cachep) % REAPTIMEOUT_LIST3;
+		l3->shared = new_shared;
 		l3->alien = new_alien;
 		l3->free_limit = (1 + nr_cpus_node(node)) *
-		    cachep->batchcount + cachep->num;
+					cachep->batchcount + cachep->num;
 		cachep->nodelists[node] = l3;
 	}
-	return err;
-      fail:
-	err = -ENOMEM;
-	return err;
+	return 0;
+
+fail:
+	if (!cachep->next.next) {
+		/* Cache is not active yet. Roll back what we did */
+		node--;
+		while (node >= 0) {
+			if (cachep->nodelists[node]) {
+				l3 = cachep->nodelists[node];
+
+				kfree(l3->shared);
+				free_alien_cache(l3->alien);
+				kfree(l3);
+				cachep->nodelists[node] = NULL;
+			}
+			node--;
+		}
+	}
+	return -ENOMEM;
 }
 
 struct ccupdate_struct {
@@ -3391,7 +3507,7 @@ struct ccupdate_struct {
 
 static void do_ccupdate_local(void *info)
 {
-	struct ccupdate_struct *new = (struct ccupdate_struct *)info;
+	struct ccupdate_struct *new = info;
 	struct array_cache *old;
 
 	check_irq_off();
@@ -3401,16 +3517,17 @@ static void do_ccupdate_local(void *info)
 	new->new[smp_processor_id()] = old;
 }
 
-static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount,
-			    int shared)
+/* Always called with the cache_chain_mutex held */
+static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
+				int batchcount, int shared)
 {
 	struct ccupdate_struct new;
 	int i, err;
 
 	memset(&new.new, 0, sizeof(new.new));
 	for_each_online_cpu(i) {
-		new.new[i] =
-		    alloc_arraycache(cpu_to_node(i), limit, batchcount);
+		new.new[i] = alloc_arraycache(cpu_to_node(i), limit,
+						batchcount);
 		if (!new.new[i]) {
 			for (i--; i >= 0; i--)
 				kfree(new.new[i]);
@@ -3419,14 +3536,12 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount
 	}
 	new.cachep = cachep;
 
-	smp_call_function_all_cpus(do_ccupdate_local, (void *)&new);
+	on_each_cpu(do_ccupdate_local, (void *)&new, 1, 1);
 
 	check_irq_on();
-	spin_lock(&cachep->spinlock);
 	cachep->batchcount = batchcount;
 	cachep->limit = limit;
 	cachep->shared = shared;
-	spin_unlock(&cachep->spinlock);
 
 	for_each_online_cpu(i) {
 		struct array_cache *ccold = new.new[i];
@@ -3447,15 +3562,17 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount
 	return 0;
 }
 
+/* Called with cache_chain_mutex held always */
 static void enable_cpucache(struct kmem_cache *cachep)
 {
 	int err;
 	int limit, shared;
 
-	/* The head array serves three purposes:
+	/*
+	 * The head array serves three purposes:
 	 * - create a LIFO ordering, i.e. return objects that are cache-warm
 	 * - reduce the number of spinlock operations.
-	 * - reduce the number of linked list operations on the slab and 
+	 * - reduce the number of linked list operations on the slab and
 	 *   bufctl chains: array operations are cheaper.
 	 * The numbers are guessed, we should auto-tune as described by
 	 * Bonwick.
@@ -3471,7 +3588,8 @@ static void enable_cpucache(struct kmem_cache *cachep)
 	else
 		limit = 120;
 
-	/* Cpu bound tasks (e.g. network routing) can exhibit cpu bound
+	/*
+	 * CPU bound tasks (e.g. network routing) can exhibit cpu bound
 	 * allocation behaviour: Most allocs on one cpu, most free operations
 	 * on another cpu. For these cases, an efficient object passing between
 	 * cpus is necessary. This is provided by a shared array. The array
@@ -3486,9 +3604,9 @@ static void enable_cpucache(struct kmem_cache *cachep)
 #endif
 
 #if DEBUG
-	/* With debugging enabled, large batchcount lead to excessively
-	 * long periods with disabled local interrupts. Limit the 
-	 * batchcount
+	/*
+	 * With debugging enabled, large batchcount lead to excessively long
+	 * periods with disabled local interrupts. Limit the batchcount
 	 */
 	if (limit > 32)
 		limit = 32;
@@ -3499,23 +3617,32 @@ static void enable_cpucache(struct kmem_cache *cachep)
 		       cachep->name, -err);
 }
 
-static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac,
-				int force, int node)
+/*
+ * Drain an array if it contains any elements taking the l3 lock only if
+ * necessary. Note that the l3 listlock also protects the array_cache
+ * if drain_array() is used on the shared array.
+ */
+void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
+			 struct array_cache *ac, int force, int node)
 {
 	int tofree;
 
-	check_spinlock_acquired_node(cachep, node);
+	if (!ac || !ac->avail)
+		return;
 	if (ac->touched && !force) {
 		ac->touched = 0;
-	} else if (ac->avail) {
-		tofree = force ? ac->avail : (ac->limit + 4) / 5;
-		if (tofree > ac->avail) {
-			tofree = (ac->avail + 1) / 2;
+	} else {
+		spin_lock_irq(&l3->list_lock);
+		if (ac->avail) {
+			tofree = force ? ac->avail : (ac->limit + 4) / 5;
+			if (tofree > ac->avail)
+				tofree = (ac->avail + 1) / 2;
+			free_block(cachep, ac->entry, tofree, node);
+			ac->avail -= tofree;
+			memmove(ac->entry, &(ac->entry[tofree]),
+				sizeof(void *) * ac->avail);
 		}
-		free_block(cachep, ac->entry, tofree, node);
-		ac->avail -= tofree;
-		memmove(ac->entry, &(ac->entry[tofree]),
-			sizeof(void *) * ac->avail);
+		spin_unlock_irq(&l3->list_lock);
 	}
 }
 
@@ -3528,13 +3655,14 @@ static void drain_array_locked(struct kmem_cache *cachep, struct array_cache *ac
  * - clear the per-cpu caches for this CPU.
  * - return freeable pages to the main free memory pool.
  *
- * If we cannot acquire the cache chain mutex then just give up - we'll
- * try again on the next iteration.
+ * If we cannot acquire the cache chain mutex then just give up - we'll try
+ * again on the next iteration.
  */
 static void cache_reap(void *unused)
 {
 	struct list_head *walk;
 	struct kmem_list3 *l3;
+	int node = numa_node_id();
 
 	if (!mutex_trylock(&cache_chain_mutex)) {
 		/* Give up. Setup the next iteration. */
@@ -3550,65 +3678,72 @@ static void cache_reap(void *unused)
 		struct slab *slabp;
 
 		searchp = list_entry(walk, struct kmem_cache, next);
-
-		if (searchp->flags & SLAB_NO_REAP)
-			goto next;
-
 		check_irq_on();
 
-		l3 = searchp->nodelists[numa_node_id()];
+		/*
+		 * We only take the l3 lock if absolutely necessary and we
+		 * have established with reasonable certainty that
+		 * we can do some work if the lock was obtained.
+		 */
+		l3 = searchp->nodelists[node];
+
 		reap_alien(searchp, l3);
-		spin_lock_irq(&l3->list_lock);
 
-		drain_array_locked(searchp, cpu_cache_get(searchp), 0,
-				   numa_node_id());
+		drain_array(searchp, l3, cpu_cache_get(searchp), 0, node);
 
+		/*
+		 * These are racy checks but it does not matter
+		 * if we skip one check or scan twice.
+		 */
 		if (time_after(l3->next_reap, jiffies))
-			goto next_unlock;
+			goto next;
 
 		l3->next_reap = jiffies + REAPTIMEOUT_LIST3;
 
-		if (l3->shared)
-			drain_array_locked(searchp, l3->shared, 0,
-					   numa_node_id());
+		drain_array(searchp, l3, l3->shared, 0, node);
 
 		if (l3->free_touched) {
 			l3->free_touched = 0;
-			goto next_unlock;
+			goto next;
 		}
 
-		tofree =
-		    (l3->free_limit + 5 * searchp->num -
-		     1) / (5 * searchp->num);
+		tofree = (l3->free_limit + 5 * searchp->num - 1) /
+				(5 * searchp->num);
 		do {
+			/*
+			 * Do not lock if there are no free blocks.
+			 */
+			if (list_empty(&l3->slabs_free))
+				break;
+
+			spin_lock_irq(&l3->list_lock);
 			p = l3->slabs_free.next;
-			if (p == &(l3->slabs_free))
+			if (p == &(l3->slabs_free)) {
+				spin_unlock_irq(&l3->list_lock);
 				break;
+			}
 
 			slabp = list_entry(p, struct slab, list);
 			BUG_ON(slabp->inuse);
 			list_del(&slabp->list);
 			STATS_INC_REAPED(searchp);
 
-			/* Safe to drop the lock. The slab is no longer
-			 * linked to the cache.
-			 * searchp cannot disappear, we hold
+			/*
+			 * Safe to drop the lock. The slab is no longer linked
+			 * to the cache. searchp cannot disappear, we hold
 			 * cache_chain_lock
 			 */
 			l3->free_objects -= searchp->num;
 			spin_unlock_irq(&l3->list_lock);
 			slab_destroy(searchp, slabp);
-			spin_lock_irq(&l3->list_lock);
 		} while (--tofree > 0);
-	      next_unlock:
-		spin_unlock_irq(&l3->list_lock);
-	      next:
+next:
 		cond_resched();
 	}
 	check_irq_on();
 	mutex_unlock(&cache_chain_mutex);
 	next_reap_node();
-	/* Setup the next iteration */
+	/* Set up the next iteration */
 	schedule_delayed_work(&__get_cpu_var(reap_work), REAPTIMEOUT_CPUC);
 }
 
@@ -3658,8 +3793,8 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct kmem_cache *cachep = p;
 	++*pos;
-	return cachep->next.next == &cache_chain ? NULL
-	    : list_entry(cachep->next.next, struct kmem_cache, next);
+	return cachep->next.next == &cache_chain ?
+		NULL : list_entry(cachep->next.next, struct kmem_cache, next);
 }
 
 static void s_stop(struct seq_file *m, void *p)
@@ -3681,7 +3816,6 @@ static int s_show(struct seq_file *m, void *p)
 	int node;
 	struct kmem_list3 *l3;
 
-	spin_lock(&cachep->spinlock);
 	active_objs = 0;
 	num_slabs = 0;
 	for_each_online_node(node) {
@@ -3748,7 +3882,9 @@ static int s_show(struct seq_file *m, void *p)
 		unsigned long node_frees = cachep->node_frees;
 
 		seq_printf(m, " : globalstat %7lu %6lu %5lu %4lu \
-				%4lu %4lu %4lu %4lu", allocs, high, grown, reaped, errors, max_freeable, node_allocs, node_frees);
+				%4lu %4lu %4lu %4lu", allocs, high, grown,
+				reaped, errors, max_freeable, node_allocs,
+				node_frees);
 	}
 	/* cpu stats */
 	{
@@ -3762,7 +3898,6 @@ static int s_show(struct seq_file *m, void *p)
 	}
 #endif
 	seq_putc(m, '\n');
-	spin_unlock(&cachep->spinlock);
 	return 0;
 }
 
@@ -3820,13 +3955,12 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 	mutex_lock(&cache_chain_mutex);
 	res = -EINVAL;
 	list_for_each(p, &cache_chain) {
-		struct kmem_cache *cachep = list_entry(p, struct kmem_cache,
-						       next);
+		struct kmem_cache *cachep;
 
+		cachep = list_entry(p, struct kmem_cache, next);
 		if (!strcmp(cachep->name, kbuf)) {
-			if (limit < 1 ||
-			    batchcount < 1 ||
-			    batchcount > limit || shared < 0) {
+			if (limit < 1 || batchcount < 1 ||
+					batchcount > limit || shared < 0) {
 				res = 0;
 			} else {
 				res = do_tune_cpucache(cachep, limit,
@@ -3840,6 +3974,159 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 		res = count;
 	return res;
 }
+
+#ifdef CONFIG_DEBUG_SLAB_LEAK
+
+static void *leaks_start(struct seq_file *m, loff_t *pos)
+{
+	loff_t n = *pos;
+	struct list_head *p;
+
+	mutex_lock(&cache_chain_mutex);
+	p = cache_chain.next;
+	while (n--) {
+		p = p->next;
+		if (p == &cache_chain)
+			return NULL;
+	}
+	return list_entry(p, struct kmem_cache, next);
+}
+
+static inline int add_caller(unsigned long *n, unsigned long v)
+{
+	unsigned long *p;
+	int l;
+	if (!v)
+		return 1;
+	l = n[1];
+	p = n + 2;
+	while (l) {
+		int i = l/2;
+		unsigned long *q = p + 2 * i;
+		if (*q == v) {
+			q[1]++;
+			return 1;
+		}
+		if (*q > v) {
+			l = i;
+		} else {
+			p = q + 2;
+			l -= i + 1;
+		}
+	}
+	if (++n[1] == n[0])
+		return 0;
+	memmove(p + 2, p, n[1] * 2 * sizeof(unsigned long) - ((void *)p - (void *)n));
+	p[0] = v;
+	p[1] = 1;
+	return 1;
+}
+
+static void handle_slab(unsigned long *n, struct kmem_cache *c, struct slab *s)
+{
+	void *p;
+	int i;
+	if (n[0] == n[1])
+		return;
+	for (i = 0, p = s->s_mem; i < c->num; i++, p += c->buffer_size) {
+		if (slab_bufctl(s)[i] != BUFCTL_ACTIVE)
+			continue;
+		if (!add_caller(n, (unsigned long)*dbg_userword(c, p)))
+			return;
+	}
+}
+
+static void show_symbol(struct seq_file *m, unsigned long address)
+{
+#ifdef CONFIG_KALLSYMS
+	char *modname;
+	const char *name;
+	unsigned long offset, size;
+	char namebuf[KSYM_NAME_LEN+1];
+
+	name = kallsyms_lookup(address, &size, &offset, &modname, namebuf);
+
+	if (name) {
+		seq_printf(m, "%s+%#lx/%#lx", name, offset, size);
+		if (modname)
+			seq_printf(m, " [%s]", modname);
+		return;
+	}
+#endif
+	seq_printf(m, "%p", (void *)address);
+}
+
+static int leaks_show(struct seq_file *m, void *p)
+{
+	struct kmem_cache *cachep = p;
+	struct list_head *q;
+	struct slab *slabp;
+	struct kmem_list3 *l3;
+	const char *name;
+	unsigned long *n = m->private;
+	int node;
+	int i;
+
+	if (!(cachep->flags & SLAB_STORE_USER))
+		return 0;
+	if (!(cachep->flags & SLAB_RED_ZONE))
+		return 0;
+
+	/* OK, we can do it */
+
+	n[1] = 0;
+
+	for_each_online_node(node) {
+		l3 = cachep->nodelists[node];
+		if (!l3)
+			continue;
+
+		check_irq_on();
+		spin_lock_irq(&l3->list_lock);
+
+		list_for_each(q, &l3->slabs_full) {
+			slabp = list_entry(q, struct slab, list);
+			handle_slab(n, cachep, slabp);
+		}
+		list_for_each(q, &l3->slabs_partial) {
+			slabp = list_entry(q, struct slab, list);
+			handle_slab(n, cachep, slabp);
+		}
+		spin_unlock_irq(&l3->list_lock);
+	}
+	name = cachep->name;
+	if (n[0] == n[1]) {
+		/* Increase the buffer size */
+		mutex_unlock(&cache_chain_mutex);
+		m->private = kzalloc(n[0] * 4 * sizeof(unsigned long), GFP_KERNEL);
+		if (!m->private) {
+			/* Too bad, we are really out */
+			m->private = n;
+			mutex_lock(&cache_chain_mutex);
+			return -ENOMEM;
+		}
+		*(unsigned long *)m->private = n[0] * 2;
+		kfree(n);
+		mutex_lock(&cache_chain_mutex);
+		/* Now make sure this entry will be retried */
+		m->count = m->size;
+		return 0;
+	}
+	for (i = 0; i < n[1]; i++) {
+		seq_printf(m, "%s: %lu ", name, n[2*i+3]);
+		show_symbol(m, n[2*i+2]);
+		seq_putc(m, '\n');
+	}
+	return 0;
+}
+
+struct seq_operations slabstats_op = {
+	.start = leaks_start,
+	.next = s_next,
+	.stop = s_stop,
+	.show = leaks_show,
+};
+#endif
 #endif
 
 /**
diff --git a/mm/slob.c b/mm/slob.c
index a1f42bd..9bcc7e2 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -294,6 +294,16 @@ void *kmem_cache_alloc(struct kmem_cache *c, gfp_t flags)
 }
 EXPORT_SYMBOL(kmem_cache_alloc);
 
+void *kmem_cache_zalloc(struct kmem_cache *c, gfp_t flags)
+{
+	void *ret = kmem_cache_alloc(c, flags);
+	if (ret)
+		memset(ret, 0, c->size);
+
+	return ret;
+}
+EXPORT_SYMBOL(kmem_cache_zalloc);
+
 void kmem_cache_free(struct kmem_cache *c, void *b)
 {
 	if (c->dtor)
diff --git a/mm/swap.c b/mm/swap.c
index b524ea9..88895c2 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -209,19 +209,18 @@ int lru_add_drain_all(void)
  */
 void fastcall __page_cache_release(struct page *page)
 {
-	unsigned long flags;
-	struct zone *zone = page_zone(page);
+	if (PageLRU(page)) {
+		unsigned long flags;
+		struct zone *zone = page_zone(page);
 
-	spin_lock_irqsave(&zone->lru_lock, flags);
-	if (TestClearPageLRU(page))
+		spin_lock_irqsave(&zone->lru_lock, flags);
+		BUG_ON(!PageLRU(page));
+		__ClearPageLRU(page);
 		del_page_from_lru(zone, page);
-	if (page_count(page) != 0)
-		page = NULL;
-	spin_unlock_irqrestore(&zone->lru_lock, flags);
-	if (page)
-		free_hot_page(page);
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
+	}
+	free_hot_page(page);
 }
-
 EXPORT_SYMBOL(__page_cache_release);
 
 /*
@@ -245,7 +244,6 @@ void release_pages(struct page **pages, int nr, int cold)
 	pagevec_init(&pages_to_free, cold);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pages[i];
-		struct zone *pagezone;
 
 		if (unlikely(PageCompound(page))) {
 			if (zone) {
@@ -259,23 +257,27 @@ void release_pages(struct page **pages, int nr, int cold)
 		if (!put_page_testzero(page))
 			continue;
 
-		pagezone = page_zone(page);
-		if (pagezone != zone) {
-			if (zone)
-				spin_unlock_irq(&zone->lru_lock);
-			zone = pagezone;
-			spin_lock_irq(&zone->lru_lock);
-		}
-		if (TestClearPageLRU(page))
+		if (PageLRU(page)) {
+			struct zone *pagezone = page_zone(page);
+			if (pagezone != zone) {
+				if (zone)
+					spin_unlock_irq(&zone->lru_lock);
+				zone = pagezone;
+				spin_lock_irq(&zone->lru_lock);
+			}
+			BUG_ON(!PageLRU(page));
+			__ClearPageLRU(page);
 			del_page_from_lru(zone, page);
-		if (page_count(page) == 0) {
-			if (!pagevec_add(&pages_to_free, page)) {
+		}
+
+		if (!pagevec_add(&pages_to_free, page)) {
+			if (zone) {
 				spin_unlock_irq(&zone->lru_lock);
-				__pagevec_free(&pages_to_free);
-				pagevec_reinit(&pages_to_free);
-				zone = NULL;	/* No lock is held */
+				zone = NULL;
 			}
-		}
+			__pagevec_free(&pages_to_free);
+			pagevec_reinit(&pages_to_free);
+  		}
 	}
 	if (zone)
 		spin_unlock_irq(&zone->lru_lock);
@@ -343,8 +345,8 @@ void __pagevec_lru_add(struct pagevec *pvec)
 			zone = pagezone;
 			spin_lock_irq(&zone->lru_lock);
 		}
-		if (TestSetPageLRU(page))
-			BUG();
+		BUG_ON(PageLRU(page));
+		SetPageLRU(page);
 		add_page_to_inactive_list(zone, page);
 	}
 	if (zone)
@@ -370,10 +372,10 @@ void __pagevec_lru_add_active(struct pagevec *pvec)
 			zone = pagezone;
 			spin_lock_irq(&zone->lru_lock);
 		}
-		if (TestSetPageLRU(page))
-			BUG();
-		if (TestSetPageActive(page))
-			BUG();
+		BUG_ON(PageLRU(page));
+		SetPageLRU(page);
+		BUG_ON(PageActive(page));
+		SetPageActive(page);
 		add_page_to_active_list(zone, page);
 	}
 	if (zone)
@@ -510,7 +512,7 @@ long percpu_counter_sum(struct percpu_counter *fbc)
 
 	spin_lock(&fbc->lock);
 	ret = fbc->count;
-	for_each_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		long *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
 	}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index db8a3d3..d7af296 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -15,6 +15,7 @@
 #include <linux/buffer_head.h>
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
+#include <linux/migrate.h>
 
 #include <asm/pgtable.h>
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1f9cf0d..39aa9d1 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -45,7 +45,7 @@ static const char Unused_offset[] = "Unused swap offset entry ";
 
 struct swap_list_t swap_list = {-1, -1};
 
-struct swap_info_struct swap_info[MAX_SWAPFILES];
+static struct swap_info_struct swap_info[MAX_SWAPFILES];
 
 static DEFINE_MUTEX(swapon_mutex);
 
@@ -116,7 +116,7 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si)
 				last_in_cluster = offset + SWAPFILE_CLUSTER;
 			else if (offset == last_in_cluster) {
 				spin_lock(&swap_lock);
-				si->cluster_next = offset-SWAPFILE_CLUSTER-1;
+				si->cluster_next = offset-SWAPFILE_CLUSTER+1;
 				goto cluster;
 			}
 			if (unlikely(--latency_ration < 0)) {
@@ -417,6 +417,61 @@ void free_swap_and_cache(swp_entry_t entry)
 	}
 }
 
+#ifdef CONFIG_SOFTWARE_SUSPEND
+/*
+ * Find the swap type that corresponds to given device (if any)
+ *
+ * This is needed for software suspend and is done in such a way that inode
+ * aliasing is allowed.
+ */
+int swap_type_of(dev_t device)
+{
+	int i;
+
+	spin_lock(&swap_lock);
+	for (i = 0; i < nr_swapfiles; i++) {
+		struct inode *inode;
+
+		if (!(swap_info[i].flags & SWP_WRITEOK))
+			continue;
+		if (!device) {
+			spin_unlock(&swap_lock);
+			return i;
+		}
+		inode = swap_info->swap_file->f_dentry->d_inode;
+		if (S_ISBLK(inode->i_mode) &&
+		    device == MKDEV(imajor(inode), iminor(inode))) {
+			spin_unlock(&swap_lock);
+			return i;
+		}
+	}
+	spin_unlock(&swap_lock);
+	return -ENODEV;
+}
+
+/*
+ * Return either the total number of swap pages of given type, or the number
+ * of free pages of that type (depending on @free)
+ *
+ * This is needed for software suspend
+ */
+unsigned int count_swap_pages(int type, int free)
+{
+	unsigned int n = 0;
+
+	if (type < nr_swapfiles) {
+		spin_lock(&swap_lock);
+		if (swap_info[type].flags & SWP_WRITEOK) {
+			n = swap_info[type].pages;
+			if (free)
+				n -= swap_info[type].inuse_pages;
+		}
+		spin_unlock(&swap_lock);
+	}
+	return n;
+}
+#endif
+
 /*
  * No need to decide whether this PTE shares the swap entry with others,
  * just let do_wp_page work it out if a write is requested later - to
diff --git a/mm/util.c b/mm/util.c
index 5f4bb59..73684792 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -1,20 +1,22 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/module.h>
+#include <linux/err.h>
+#include <asm/uaccess.h>
 
 /**
- * kzalloc - allocate memory. The memory is set to zero.
+ * __kzalloc - allocate memory. The memory is set to zero.
  * @size: how many bytes of memory are required.
  * @flags: the type of memory to allocate.
  */
-void *kzalloc(size_t size, gfp_t flags)
+void *__kzalloc(size_t size, gfp_t flags)
 {
-	void *ret = kmalloc(size, flags);
+	void *ret = ____kmalloc(size, flags);
 	if (ret)
 		memset(ret, 0, size);
 	return ret;
 }
-EXPORT_SYMBOL(kzalloc);
+EXPORT_SYMBOL(__kzalloc);
 
 /*
  * kstrdup - allocate space for and copy an existing string
@@ -31,9 +33,44 @@ char *kstrdup(const char *s, gfp_t gfp)
 		return NULL;
 
 	len = strlen(s) + 1;
-	buf = kmalloc(len, gfp);
+	buf = ____kmalloc(len, gfp);
 	if (buf)
 		memcpy(buf, s, len);
 	return buf;
 }
 EXPORT_SYMBOL(kstrdup);
+
+/*
+ * strndup_user - duplicate an existing string from user space
+ *
+ * @s: The string to duplicate
+ * @n: Maximum number of bytes to copy, including the trailing NUL.
+ */
+char *strndup_user(const char __user *s, long n)
+{
+	char *p;
+	long length;
+
+	length = strnlen_user(s, n);
+
+	if (!length)
+		return ERR_PTR(-EFAULT);
+
+	if (length > n)
+		return ERR_PTR(-EINVAL);
+
+	p = kmalloc(length, GFP_KERNEL);
+
+	if (!p)
+		return ERR_PTR(-ENOMEM);
+
+	if (copy_from_user(p, s, length)) {
+		kfree(p);
+		return ERR_PTR(-EFAULT);
+	}
+
+	p[length - 1] = '\0';
+
+	return p;
+}
+EXPORT_SYMBOL(strndup_user);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4fe7e3a..acdf001 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -33,39 +33,21 @@
 #include <linux/cpuset.h>
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
+#include <linux/delay.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
 
 #include <linux/swapops.h>
 
-/* possible outcome of pageout() */
-typedef enum {
-	/* failed to write page out, page is locked */
-	PAGE_KEEP,
-	/* move page to the active list, page is locked */
-	PAGE_ACTIVATE,
-	/* page has been sent to the disk successfully, page is unlocked */
-	PAGE_SUCCESS,
-	/* page is clean and locked */
-	PAGE_CLEAN,
-} pageout_t;
+#include "internal.h"
 
 struct scan_control {
-	/* Ask refill_inactive_zone, or shrink_cache to scan this many pages */
-	unsigned long nr_to_scan;
-
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
 
-	/* Incremented by the number of pages reclaimed */
-	unsigned long nr_reclaimed;
-
 	unsigned long nr_mapped;	/* From page_state */
 
-	/* Ask shrink_caches, or shrink_zone to scan at this priority */
-	unsigned int priority;
-
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -183,10 +165,11 @@ EXPORT_SYMBOL(remove_shrinker);
  *
  * Returns the number of slab objects which we shrunk.
  */
-int shrink_slab(unsigned long scanned, gfp_t gfp_mask, unsigned long lru_pages)
+unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
+			unsigned long lru_pages)
 {
 	struct shrinker *shrinker;
-	int ret = 0;
+	unsigned long ret = 0;
 
 	if (scanned == 0)
 		scanned = SWAP_CLUSTER_MAX;
@@ -306,9 +289,10 @@ static void handle_write_error(struct address_space *mapping,
 }
 
 /*
- * pageout is called by shrink_list() for each dirty page. Calls ->writepage().
+ * pageout is called by shrink_page_list() for each dirty page.
+ * Calls ->writepage().
  */
-static pageout_t pageout(struct page *page, struct address_space *mapping)
+pageout_t pageout(struct page *page, struct address_space *mapping)
 {
 	/*
 	 * If the page is dirty, only perform writeback if that write
@@ -376,7 +360,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 	return PAGE_CLEAN;
 }
 
-static int remove_mapping(struct address_space *mapping, struct page *page)
+int remove_mapping(struct address_space *mapping, struct page *page)
 {
 	if (!mapping)
 		return 0;		/* truncate got there first */
@@ -414,14 +398,15 @@ cannot_free:
 }
 
 /*
- * shrink_list adds the number of reclaimed pages to sc->nr_reclaimed
+ * shrink_page_list() returns the number of reclaimed pages
  */
-static int shrink_list(struct list_head *page_list, struct scan_control *sc)
+static unsigned long shrink_page_list(struct list_head *page_list,
+					struct scan_control *sc)
 {
 	LIST_HEAD(ret_pages);
 	struct pagevec freed_pvec;
 	int pgactivate = 0;
-	int reclaimed = 0;
+	unsigned long nr_reclaimed = 0;
 
 	cond_resched();
 
@@ -464,12 +449,9 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 */
-		if (PageAnon(page) && !PageSwapCache(page)) {
-			if (!sc->may_swap)
-				goto keep_locked;
+		if (PageAnon(page) && !PageSwapCache(page))
 			if (!add_to_swap(page, GFP_ATOMIC))
 				goto activate_locked;
-		}
 #endif /* CONFIG_SWAP */
 
 		mapping = page_mapping(page);
@@ -481,12 +463,6 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 		 * processes. Try to unmap it here.
 		 */
 		if (page_mapped(page) && mapping) {
-			/*
-			 * No unmapping if we do not swap
-			 */
-			if (!sc->may_swap)
-				goto keep_locked;
-
 			switch (try_to_unmap(page, 0)) {
 			case SWAP_FAIL:
 				goto activate_locked;
@@ -561,7 +537,7 @@ static int shrink_list(struct list_head *page_list, struct scan_control *sc)
 
 free_it:
 		unlock_page(page);
-		reclaimed++;
+		nr_reclaimed++;
 		if (!pagevec_add(&freed_pvec, page))
 			__pagevec_release_nonlru(&freed_pvec);
 		continue;
@@ -579,483 +555,8 @@ keep:
 	if (pagevec_count(&freed_pvec))
 		__pagevec_release_nonlru(&freed_pvec);
 	mod_page_state(pgactivate, pgactivate);
-	sc->nr_reclaimed += reclaimed;
-	return reclaimed;
-}
-
-#ifdef CONFIG_MIGRATION
-static inline void move_to_lru(struct page *page)
-{
-	list_del(&page->lru);
-	if (PageActive(page)) {
-		/*
-		 * lru_cache_add_active checks that
-		 * the PG_active bit is off.
-		 */
-		ClearPageActive(page);
-		lru_cache_add_active(page);
-	} else {
-		lru_cache_add(page);
-	}
-	put_page(page);
-}
-
-/*
- * Add isolated pages on the list back to the LRU.
- *
- * returns the number of pages put back.
- */
-int putback_lru_pages(struct list_head *l)
-{
-	struct page *page;
-	struct page *page2;
-	int count = 0;
-
-	list_for_each_entry_safe(page, page2, l, lru) {
-		move_to_lru(page);
-		count++;
-	}
-	return count;
-}
-
-/*
- * Non migratable page
- */
-int fail_migrate_page(struct page *newpage, struct page *page)
-{
-	return -EIO;
-}
-EXPORT_SYMBOL(fail_migrate_page);
-
-/*
- * swapout a single page
- * page is locked upon entry, unlocked on exit
- */
-static int swap_page(struct page *page)
-{
-	struct address_space *mapping = page_mapping(page);
-
-	if (page_mapped(page) && mapping)
-		if (try_to_unmap(page, 1) != SWAP_SUCCESS)
-			goto unlock_retry;
-
-	if (PageDirty(page)) {
-		/* Page is dirty, try to write it out here */
-		switch(pageout(page, mapping)) {
-		case PAGE_KEEP:
-		case PAGE_ACTIVATE:
-			goto unlock_retry;
-
-		case PAGE_SUCCESS:
-			goto retry;
-
-		case PAGE_CLEAN:
-			; /* try to free the page below */
-		}
-	}
-
-	if (PagePrivate(page)) {
-		if (!try_to_release_page(page, GFP_KERNEL) ||
-		    (!mapping && page_count(page) == 1))
-			goto unlock_retry;
-	}
-
-	if (remove_mapping(mapping, page)) {
-		/* Success */
-		unlock_page(page);
-		return 0;
-	}
-
-unlock_retry:
-	unlock_page(page);
-
-retry:
-	return -EAGAIN;
+	return nr_reclaimed;
 }
-EXPORT_SYMBOL(swap_page);
-
-/*
- * Page migration was first developed in the context of the memory hotplug
- * project. The main authors of the migration code are:
- *
- * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
- * Hirokazu Takahashi <taka@valinux.co.jp>
- * Dave Hansen <haveblue@us.ibm.com>
- * Christoph Lameter <clameter@sgi.com>
- */
-
-/*
- * Remove references for a page and establish the new page with the correct
- * basic settings to be able to stop accesses to the page.
- */
-int migrate_page_remove_references(struct page *newpage,
-				struct page *page, int nr_refs)
-{
-	struct address_space *mapping = page_mapping(page);
-	struct page **radix_pointer;
-
-	/*
-	 * Avoid doing any of the following work if the page count
-	 * indicates that the page is in use or truncate has removed
-	 * the page.
-	 */
-	if (!mapping || page_mapcount(page) + nr_refs != page_count(page))
-		return -EAGAIN;
-
-	/*
-	 * Establish swap ptes for anonymous pages or destroy pte
-	 * maps for files.
-	 *
-	 * In order to reestablish file backed mappings the fault handlers
-	 * will take the radix tree_lock which may then be used to stop
-  	 * processses from accessing this page until the new page is ready.
-	 *
-	 * A process accessing via a swap pte (an anonymous page) will take a
-	 * page_lock on the old page which will block the process until the
-	 * migration attempt is complete. At that time the PageSwapCache bit
-	 * will be examined. If the page was migrated then the PageSwapCache
-	 * bit will be clear and the operation to retrieve the page will be
-	 * retried which will find the new page in the radix tree. Then a new
-	 * direct mapping may be generated based on the radix tree contents.
-	 *
-	 * If the page was not migrated then the PageSwapCache bit
-	 * is still set and the operation may continue.
-	 */
-	if (try_to_unmap(page, 1) == SWAP_FAIL)
-		/* A vma has VM_LOCKED set -> Permanent failure */
-		return -EPERM;
-
-	/*
-	 * Give up if we were unable to remove all mappings.
-	 */
-	if (page_mapcount(page))
-		return -EAGAIN;
-
-	write_lock_irq(&mapping->tree_lock);
-
-	radix_pointer = (struct page **)radix_tree_lookup_slot(
-						&mapping->page_tree,
-						page_index(page));
-
-	if (!page_mapping(page) || page_count(page) != nr_refs ||
-			*radix_pointer != page) {
-		write_unlock_irq(&mapping->tree_lock);
-		return -EAGAIN;
-	}
-
-	/*
-	 * Now we know that no one else is looking at the page.
-	 *
-	 * Certain minimal information about a page must be available
-	 * in order for other subsystems to properly handle the page if they
-	 * find it through the radix tree update before we are finished
-	 * copying the page.
-	 */
-	get_page(newpage);
-	newpage->index = page->index;
-	newpage->mapping = page->mapping;
-	if (PageSwapCache(page)) {
-		SetPageSwapCache(newpage);
-		set_page_private(newpage, page_private(page));
-	}
-
-	*radix_pointer = newpage;
-	__put_page(page);
-	write_unlock_irq(&mapping->tree_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(migrate_page_remove_references);
-
-/*
- * Copy the page to its new location
- */
-void migrate_page_copy(struct page *newpage, struct page *page)
-{
-	copy_highpage(newpage, page);
-
-	if (PageError(page))
-		SetPageError(newpage);
-	if (PageReferenced(page))
-		SetPageReferenced(newpage);
-	if (PageUptodate(page))
-		SetPageUptodate(newpage);
-	if (PageActive(page))
-		SetPageActive(newpage);
-	if (PageChecked(page))
-		SetPageChecked(newpage);
-	if (PageMappedToDisk(page))
-		SetPageMappedToDisk(newpage);
-
-	if (PageDirty(page)) {
-		clear_page_dirty_for_io(page);
-		set_page_dirty(newpage);
- 	}
-
-	ClearPageSwapCache(page);
-	ClearPageActive(page);
-	ClearPagePrivate(page);
-	set_page_private(page, 0);
-	page->mapping = NULL;
-
-	/*
-	 * If any waiters have accumulated on the new page then
-	 * wake them up.
-	 */
-	if (PageWriteback(newpage))
-		end_page_writeback(newpage);
-}
-EXPORT_SYMBOL(migrate_page_copy);
-
-/*
- * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
- *
- * Pages are locked upon entry and exit.
- */
-int migrate_page(struct page *newpage, struct page *page)
-{
-	int rc;
-
-	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
-
-	rc = migrate_page_remove_references(newpage, page, 2);
-
-	if (rc)
-		return rc;
-
-	migrate_page_copy(newpage, page);
-
-	/*
-	 * Remove auxiliary swap entries and replace
-	 * them with real ptes.
-	 *
-	 * Note that a real pte entry will allow processes that are not
-	 * waiting on the page lock to use the new page via the page tables
-	 * before the new page is unlocked.
-	 */
-	remove_from_swap(newpage);
-	return 0;
-}
-EXPORT_SYMBOL(migrate_page);
-
-/*
- * migrate_pages
- *
- * Two lists are passed to this function. The first list
- * contains the pages isolated from the LRU to be migrated.
- * The second list contains new pages that the pages isolated
- * can be moved to. If the second list is NULL then all
- * pages are swapped out.
- *
- * The function returns after 10 attempts or if no pages
- * are movable anymore because to has become empty
- * or no retryable pages exist anymore.
- *
- * Return: Number of pages not migrated when "to" ran empty.
- */
-int migrate_pages(struct list_head *from, struct list_head *to,
-		  struct list_head *moved, struct list_head *failed)
-{
-	int retry;
-	int nr_failed = 0;
-	int pass = 0;
-	struct page *page;
-	struct page *page2;
-	int swapwrite = current->flags & PF_SWAPWRITE;
-	int rc;
-
-	if (!swapwrite)
-		current->flags |= PF_SWAPWRITE;
-
-redo:
-	retry = 0;
-
-	list_for_each_entry_safe(page, page2, from, lru) {
-		struct page *newpage = NULL;
-		struct address_space *mapping;
-
-		cond_resched();
-
-		rc = 0;
-		if (page_count(page) == 1)
-			/* page was freed from under us. So we are done. */
-			goto next;
-
-		if (to && list_empty(to))
-			break;
-
-		/*
-		 * Skip locked pages during the first two passes to give the
-		 * functions holding the lock time to release the page. Later we
-		 * use lock_page() to have a higher chance of acquiring the
-		 * lock.
-		 */
-		rc = -EAGAIN;
-		if (pass > 2)
-			lock_page(page);
-		else
-			if (TestSetPageLocked(page))
-				goto next;
-
-		/*
-		 * Only wait on writeback if we have already done a pass where
-		 * we we may have triggered writeouts for lots of pages.
-		 */
-		if (pass > 0) {
-			wait_on_page_writeback(page);
-		} else {
-			if (PageWriteback(page))
-				goto unlock_page;
-		}
-
-		/*
-		 * Anonymous pages must have swap cache references otherwise
-		 * the information contained in the page maps cannot be
-		 * preserved.
-		 */
-		if (PageAnon(page) && !PageSwapCache(page)) {
-			if (!add_to_swap(page, GFP_KERNEL)) {
-				rc = -ENOMEM;
-				goto unlock_page;
-			}
-		}
-
-		if (!to) {
-			rc = swap_page(page);
-			goto next;
-		}
-
-		newpage = lru_to_page(to);
-		lock_page(newpage);
-
-		/*
-		 * Pages are properly locked and writeback is complete.
-		 * Try to migrate the page.
-		 */
-		mapping = page_mapping(page);
-		if (!mapping)
-			goto unlock_both;
-
-		if (mapping->a_ops->migratepage) {
-			/*
-			 * Most pages have a mapping and most filesystems
-			 * should provide a migration function. Anonymous
-			 * pages are part of swap space which also has its
-			 * own migration function. This is the most common
-			 * path for page migration.
-			 */
-			rc = mapping->a_ops->migratepage(newpage, page);
-			goto unlock_both;
-                }
-
-		/*
-		 * Default handling if a filesystem does not provide
-		 * a migration function. We can only migrate clean
-		 * pages so try to write out any dirty pages first.
-		 */
-		if (PageDirty(page)) {
-			switch (pageout(page, mapping)) {
-			case PAGE_KEEP:
-			case PAGE_ACTIVATE:
-				goto unlock_both;
-
-			case PAGE_SUCCESS:
-				unlock_page(newpage);
-				goto next;
-
-			case PAGE_CLEAN:
-				; /* try to migrate the page below */
-			}
-                }
-
-		/*
-		 * Buffers are managed in a filesystem specific way.
-		 * We must have no buffers or drop them.
-		 */
-		if (!page_has_buffers(page) ||
-		    try_to_release_page(page, GFP_KERNEL)) {
-			rc = migrate_page(newpage, page);
-			goto unlock_both;
-		}
-
-		/*
-		 * On early passes with mapped pages simply
-		 * retry. There may be a lock held for some
-		 * buffers that may go away. Later
-		 * swap them out.
-		 */
-		if (pass > 4) {
-			/*
-			 * Persistently unable to drop buffers..... As a
-			 * measure of last resort we fall back to
-			 * swap_page().
-			 */
-			unlock_page(newpage);
-			newpage = NULL;
-			rc = swap_page(page);
-			goto next;
-		}
-
-unlock_both:
-		unlock_page(newpage);
-
-unlock_page:
-		unlock_page(page);
-
-next:
-		if (rc == -EAGAIN) {
-			retry++;
-		} else if (rc) {
-			/* Permanent failure */
-			list_move(&page->lru, failed);
-			nr_failed++;
-		} else {
-			if (newpage) {
-				/* Successful migration. Return page to LRU */
-				move_to_lru(newpage);
-			}
-			list_move(&page->lru, moved);
-		}
-	}
-	if (retry && pass++ < 10)
-		goto redo;
-
-	if (!swapwrite)
-		current->flags &= ~PF_SWAPWRITE;
-
-	return nr_failed + retry;
-}
-
-/*
- * Isolate one page from the LRU lists and put it on the
- * indicated list with elevated refcount.
- *
- * Result:
- *  0 = page not on LRU list
- *  1 = page removed from LRU list and added to the specified list.
- */
-int isolate_lru_page(struct page *page)
-{
-	int ret = 0;
-
-	if (PageLRU(page)) {
-		struct zone *zone = page_zone(page);
-		spin_lock_irq(&zone->lru_lock);
-		if (TestClearPageLRU(page)) {
-			ret = 1;
-			get_page(page);
-			if (PageActive(page))
-				del_page_from_active_list(zone, page);
-			else
-				del_page_from_inactive_list(zone, page);
-		}
-		spin_unlock_irq(&zone->lru_lock);
-	}
-
-	return ret;
-}
-#endif
 
 /*
  * zone->lru_lock is heavily contended.  Some of the functions that
@@ -1074,32 +575,35 @@ int isolate_lru_page(struct page *page)
  *
  * returns how many pages were moved onto *@dst.
  */
-static int isolate_lru_pages(int nr_to_scan, struct list_head *src,
-			     struct list_head *dst, int *scanned)
+static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
+		struct list_head *src, struct list_head *dst,
+		unsigned long *scanned)
 {
-	int nr_taken = 0;
+	unsigned long nr_taken = 0;
 	struct page *page;
-	int scan = 0;
+	unsigned long scan;
 
-	while (scan++ < nr_to_scan && !list_empty(src)) {
+	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+		struct list_head *target;
 		page = lru_to_page(src);
 		prefetchw_prev_lru_page(page, src, flags);
 
-		if (!TestClearPageLRU(page))
-			BUG();
+		BUG_ON(!PageLRU(page));
+
 		list_del(&page->lru);
-		if (get_page_testone(page)) {
+		target = src;
+		if (likely(get_page_unless_zero(page))) {
 			/*
-			 * It is being freed elsewhere
+			 * Be careful not to clear PageLRU until after we're
+			 * sure the page is not being freed elsewhere -- the
+			 * page release code relies on it.
 			 */
-			__put_page(page);
-			SetPageLRU(page);
-			list_add(&page->lru, src);
-			continue;
-		} else {
-			list_add(&page->lru, dst);
+			ClearPageLRU(page);
+			target = dst;
 			nr_taken++;
-		}
+		} /* else it is being freed elsewhere */
+
+		list_add(&page->lru, target);
 	}
 
 	*scanned = scan;
@@ -1107,23 +611,26 @@ static int isolate_lru_pages(int nr_to_scan, struct list_head *src,
 }
 
 /*
- * shrink_cache() adds the number of pages reclaimed to sc->nr_reclaimed
+ * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
+ * of reclaimed pages
  */
-static void shrink_cache(struct zone *zone, struct scan_control *sc)
+static unsigned long shrink_inactive_list(unsigned long max_scan,
+				struct zone *zone, struct scan_control *sc)
 {
 	LIST_HEAD(page_list);
 	struct pagevec pvec;
-	int max_scan = sc->nr_to_scan;
+	unsigned long nr_scanned = 0;
+	unsigned long nr_reclaimed = 0;
 
 	pagevec_init(&pvec, 1);
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
-	while (max_scan > 0) {
+	do {
 		struct page *page;
-		int nr_taken;
-		int nr_scan;
-		int nr_freed;
+		unsigned long nr_taken;
+		unsigned long nr_scan;
+		unsigned long nr_freed;
 
 		nr_taken = isolate_lru_pages(sc->swap_cluster_max,
 					     &zone->inactive_list,
@@ -1132,12 +639,9 @@ static void shrink_cache(struct zone *zone, struct scan_control *sc)
 		zone->pages_scanned += nr_scan;
 		spin_unlock_irq(&zone->lru_lock);
 
-		if (nr_taken == 0)
-			goto done;
-
-		max_scan -= nr_scan;
-		nr_freed = shrink_list(&page_list, sc);
-
+		nr_scanned += nr_scan;
+		nr_freed = shrink_page_list(&page_list, sc);
+		nr_reclaimed += nr_freed;
 		local_irq_disable();
 		if (current_is_kswapd()) {
 			__mod_page_state_zone(zone, pgscan_kswapd, nr_scan);
@@ -1146,14 +650,17 @@ static void shrink_cache(struct zone *zone, struct scan_control *sc)
 			__mod_page_state_zone(zone, pgscan_direct, nr_scan);
 		__mod_page_state_zone(zone, pgsteal, nr_freed);
 
+		if (nr_taken == 0)
+			goto done;
+
 		spin_lock(&zone->lru_lock);
 		/*
 		 * Put back any unfreeable pages.
 		 */
 		while (!list_empty(&page_list)) {
 			page = lru_to_page(&page_list);
-			if (TestSetPageLRU(page))
-				BUG();
+			BUG_ON(PageLRU(page));
+			SetPageLRU(page);
 			list_del(&page->lru);
 			if (PageActive(page))
 				add_page_to_active_list(zone, page);
@@ -1165,10 +672,12 @@ static void shrink_cache(struct zone *zone, struct scan_control *sc)
 				spin_lock_irq(&zone->lru_lock);
 			}
 		}
-  	}
-	spin_unlock_irq(&zone->lru_lock);
+  	} while (nr_scanned < max_scan);
+	spin_unlock(&zone->lru_lock);
 done:
+	local_irq_enable();
 	pagevec_release(&pvec);
+	return nr_reclaimed;
 }
 
 /*
@@ -1188,13 +697,12 @@ done:
  * The downside is that we have to touch page->_count against each page.
  * But we had to alter page->flags anyway.
  */
-static void
-refill_inactive_zone(struct zone *zone, struct scan_control *sc)
+static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
+				struct scan_control *sc)
 {
-	int pgmoved;
+	unsigned long pgmoved;
 	int pgdeactivate = 0;
-	int pgscanned;
-	int nr_pages = sc->nr_to_scan;
+	unsigned long pgscanned;
 	LIST_HEAD(l_hold);	/* The pages which were snipped off */
 	LIST_HEAD(l_inactive);	/* Pages to go onto the inactive_list */
 	LIST_HEAD(l_active);	/* Pages to go onto the active_list */
@@ -1202,7 +710,7 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 	struct pagevec pvec;
 	int reclaim_mapped = 0;
 
-	if (unlikely(sc->may_swap)) {
+	if (sc->may_swap) {
 		long mapped_ratio;
 		long distress;
 		long swap_tendency;
@@ -1272,10 +780,11 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
 		prefetchw_prev_lru_page(page, &l_inactive, flags);
-		if (TestSetPageLRU(page))
-			BUG();
-		if (!TestClearPageActive(page))
-			BUG();
+		BUG_ON(PageLRU(page));
+		SetPageLRU(page);
+		BUG_ON(!PageActive(page));
+		ClearPageActive(page);
+
 		list_move(&page->lru, &zone->inactive_list);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
@@ -1301,8 +810,8 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 	while (!list_empty(&l_active)) {
 		page = lru_to_page(&l_active);
 		prefetchw_prev_lru_page(page, &l_active, flags);
-		if (TestSetPageLRU(page))
-			BUG();
+		BUG_ON(PageLRU(page));
+		SetPageLRU(page);
 		BUG_ON(!PageActive(page));
 		list_move(&page->lru, &zone->active_list);
 		pgmoved++;
@@ -1327,11 +836,13 @@ refill_inactive_zone(struct zone *zone, struct scan_control *sc)
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
-static void
-shrink_zone(struct zone *zone, struct scan_control *sc)
+static unsigned long shrink_zone(int priority, struct zone *zone,
+				struct scan_control *sc)
 {
 	unsigned long nr_active;
 	unsigned long nr_inactive;
+	unsigned long nr_to_scan;
+	unsigned long nr_reclaimed = 0;
 
 	atomic_inc(&zone->reclaim_in_progress);
 
@@ -1339,14 +850,14 @@ shrink_zone(struct zone *zone, struct scan_control *sc)
 	 * Add one to `nr_to_scan' just to make sure that the kernel will
 	 * slowly sift through the active list.
 	 */
-	zone->nr_scan_active += (zone->nr_active >> sc->priority) + 1;
+	zone->nr_scan_active += (zone->nr_active >> priority) + 1;
 	nr_active = zone->nr_scan_active;
 	if (nr_active >= sc->swap_cluster_max)
 		zone->nr_scan_active = 0;
 	else
 		nr_active = 0;
 
-	zone->nr_scan_inactive += (zone->nr_inactive >> sc->priority) + 1;
+	zone->nr_scan_inactive += (zone->nr_inactive >> priority) + 1;
 	nr_inactive = zone->nr_scan_inactive;
 	if (nr_inactive >= sc->swap_cluster_max)
 		zone->nr_scan_inactive = 0;
@@ -1355,23 +866,25 @@ shrink_zone(struct zone *zone, struct scan_control *sc)
 
 	while (nr_active || nr_inactive) {
 		if (nr_active) {
-			sc->nr_to_scan = min(nr_active,
+			nr_to_scan = min(nr_active,
 					(unsigned long)sc->swap_cluster_max);
-			nr_active -= sc->nr_to_scan;
-			refill_inactive_zone(zone, sc);
+			nr_active -= nr_to_scan;
+			shrink_active_list(nr_to_scan, zone, sc);
 		}
 
 		if (nr_inactive) {
-			sc->nr_to_scan = min(nr_inactive,
+			nr_to_scan = min(nr_inactive,
 					(unsigned long)sc->swap_cluster_max);
-			nr_inactive -= sc->nr_to_scan;
-			shrink_cache(zone, sc);
+			nr_inactive -= nr_to_scan;
+			nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
+								sc);
 		}
 	}
 
 	throttle_vm_writeout();
 
 	atomic_dec(&zone->reclaim_in_progress);
+	return nr_reclaimed;
 }
 
 /*
@@ -1390,9 +903,10 @@ shrink_zone(struct zone *zone, struct scan_control *sc)
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static void
-shrink_caches(struct zone **zones, struct scan_control *sc)
+static unsigned long shrink_zones(int priority, struct zone **zones,
+					struct scan_control *sc)
 {
+	unsigned long nr_reclaimed = 0;
 	int i;
 
 	for (i = 0; zones[i] != NULL; i++) {
@@ -1404,15 +918,16 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->temp_priority = sc->priority;
-		if (zone->prev_priority > sc->priority)
-			zone->prev_priority = sc->priority;
+		zone->temp_priority = priority;
+		if (zone->prev_priority > priority)
+			zone->prev_priority = priority;
 
-		if (zone->all_unreclaimable && sc->priority != DEF_PRIORITY)
+		if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 			continue;	/* Let kswapd poll it */
 
-		shrink_zone(zone, sc);
+		nr_reclaimed += shrink_zone(priority, zone, sc);
 	}
+	return nr_reclaimed;
 }
  
 /*
@@ -1428,19 +943,21 @@ shrink_caches(struct zone **zones, struct scan_control *sc)
  * holds filesystem locks which prevent writeout this might not work, and the
  * allocation attempt will fail.
  */
-int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
+unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 {
 	int priority;
 	int ret = 0;
-	int total_scanned = 0, total_reclaimed = 0;
+	unsigned long total_scanned = 0;
+	unsigned long nr_reclaimed = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct scan_control sc;
 	unsigned long lru_pages = 0;
 	int i;
-
-	sc.gfp_mask = gfp_mask;
-	sc.may_writepage = !laptop_mode;
-	sc.may_swap = 1;
+	struct scan_control sc = {
+		.gfp_mask = gfp_mask,
+		.may_writepage = !laptop_mode,
+		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.may_swap = 1,
+	};
 
 	inc_page_state(allocstall);
 
@@ -1457,20 +974,16 @@ int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		sc.nr_mapped = read_page_state(nr_mapped);
 		sc.nr_scanned = 0;
-		sc.nr_reclaimed = 0;
-		sc.priority = priority;
-		sc.swap_cluster_max = SWAP_CLUSTER_MAX;
 		if (!priority)
 			disable_swap_token();
-		shrink_caches(zones, &sc);
+		nr_reclaimed += shrink_zones(priority, zones, &sc);
 		shrink_slab(sc.nr_scanned, gfp_mask, lru_pages);
 		if (reclaim_state) {
-			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
+			nr_reclaimed += reclaim_state->reclaimed_slab;
 			reclaim_state->reclaimed_slab = 0;
 		}
 		total_scanned += sc.nr_scanned;
-		total_reclaimed += sc.nr_reclaimed;
-		if (total_reclaimed >= sc.swap_cluster_max) {
+		if (nr_reclaimed >= sc.swap_cluster_max) {
 			ret = 1;
 			goto out;
 		}
@@ -1482,7 +995,8 @@ int try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 		 * that's undesirable in laptop mode, where we *want* lumpy
 		 * writeout.  So in laptop mode, write out the whole world.
 		 */
-		if (total_scanned > sc.swap_cluster_max + sc.swap_cluster_max/2) {
+		if (total_scanned > sc.swap_cluster_max +
+					sc.swap_cluster_max / 2) {
 			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
 			sc.may_writepage = 1;
 		}
@@ -1528,22 +1042,26 @@ out:
  * the page allocator fallback scheme to ensure that aging of pages is balanced
  * across the zones.
  */
-static int balance_pgdat(pg_data_t *pgdat, int nr_pages, int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages,
+				int order)
 {
-	int to_free = nr_pages;
+	unsigned long to_free = nr_pages;
 	int all_zones_ok;
 	int priority;
 	int i;
-	int total_scanned, total_reclaimed;
+	unsigned long total_scanned;
+	unsigned long nr_reclaimed;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
-	struct scan_control sc;
+	struct scan_control sc = {
+		.gfp_mask = GFP_KERNEL,
+		.may_swap = 1,
+		.swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX,
+	};
 
 loop_again:
 	total_scanned = 0;
-	total_reclaimed = 0;
-	sc.gfp_mask = GFP_KERNEL;
-	sc.may_writepage = !laptop_mode;
-	sc.may_swap = 1;
+	nr_reclaimed = 0;
+	sc.may_writepage = !laptop_mode,
 	sc.nr_mapped = read_page_state(nr_mapped);
 
 	inc_page_state(pageoutrun);
@@ -1624,15 +1142,11 @@ scan:
 			if (zone->prev_priority > priority)
 				zone->prev_priority = priority;
 			sc.nr_scanned = 0;
-			sc.nr_reclaimed = 0;
-			sc.priority = priority;
-			sc.swap_cluster_max = nr_pages? nr_pages : SWAP_CLUSTER_MAX;
-			shrink_zone(zone, &sc);
+			nr_reclaimed += shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
 						lru_pages);
-			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
-			total_reclaimed += sc.nr_reclaimed;
+			nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 			if (zone->all_unreclaimable)
 				continue;
@@ -1645,10 +1159,10 @@ scan:
 			 * even in laptop mode
 			 */
 			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
-			    total_scanned > total_reclaimed+total_reclaimed/2)
+			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
 				sc.may_writepage = 1;
 		}
-		if (nr_pages && to_free > total_reclaimed)
+		if (nr_pages && to_free > nr_reclaimed)
 			continue;	/* swsusp: need to do more work */
 		if (all_zones_ok)
 			break;		/* kswapd: all done */
@@ -1665,7 +1179,7 @@ scan:
 		 * matches the direct reclaim path behaviour in terms of impact
 		 * on zone->*_priority.
 		 */
-		if ((total_reclaimed >= SWAP_CLUSTER_MAX) && (!nr_pages))
+		if ((nr_reclaimed >= SWAP_CLUSTER_MAX) && !nr_pages)
 			break;
 	}
 out:
@@ -1679,7 +1193,7 @@ out:
 		goto loop_again;
 	}
 
-	return total_reclaimed;
+	return nr_reclaimed;
 }
 
 /*
@@ -1779,24 +1293,31 @@ void wakeup_kswapd(struct zone *zone, int order)
  * Try to free `nr_pages' of memory, system-wide.  Returns the number of freed
  * pages.
  */
-int shrink_all_memory(int nr_pages)
+unsigned long shrink_all_memory(unsigned long nr_pages)
 {
 	pg_data_t *pgdat;
-	int nr_to_free = nr_pages;
-	int ret = 0;
+	unsigned long nr_to_free = nr_pages;
+	unsigned long ret = 0;
+	unsigned retry = 2;
 	struct reclaim_state reclaim_state = {
 		.reclaimed_slab = 0,
 	};
 
 	current->reclaim_state = &reclaim_state;
-	for_each_pgdat(pgdat) {
-		int freed;
+repeat:
+	for_each_online_pgdat(pgdat) {
+		unsigned long freed;
+
 		freed = balance_pgdat(pgdat, nr_to_free, 0);
 		ret += freed;
 		nr_to_free -= freed;
-		if (nr_to_free <= 0)
+		if ((long)nr_to_free <= 0)
 			break;
 	}
+	if (retry-- && ret < nr_pages) {
+		blk_congestion_wait(WRITE, HZ/5);
+		goto repeat;
+	}
 	current->reclaim_state = NULL;
 	return ret;
 }
@@ -1808,14 +1329,13 @@ int shrink_all_memory(int nr_pages)
    away, we get changed to run anywhere: as the first one comes back,
    restore their cpu bindings. */
 static int __devinit cpu_callback(struct notifier_block *nfb,
-				  unsigned long action,
-				  void *hcpu)
+				  unsigned long action, void *hcpu)
 {
 	pg_data_t *pgdat;
 	cpumask_t mask;
 
 	if (action == CPU_ONLINE) {
-		for_each_pgdat(pgdat) {
+		for_each_online_pgdat(pgdat) {
 			mask = node_to_cpumask(pgdat->node_id);
 			if (any_online_cpu(mask) != NR_CPUS)
 				/* One of our CPUs online: restore mask */
@@ -1829,10 +1349,17 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 static int __init kswapd_init(void)
 {
 	pg_data_t *pgdat;
+
 	swap_setup();
-	for_each_pgdat(pgdat)
-		pgdat->kswapd
-		= find_task_by_pid(kernel_thread(kswapd, pgdat, CLONE_KERNEL));
+	for_each_online_pgdat(pgdat) {
+		pid_t pid;
+
+		pid = kernel_thread(kswapd, pgdat, CLONE_KERNEL);
+		BUG_ON(pid < 0);
+		read_lock(&tasklist_lock);
+		pgdat->kswapd = find_task_by_pid(pid);
+		read_unlock(&tasklist_lock);
+	}
 	total_memory = nr_free_pagecache_pages();
 	hotcpu_notifier(cpu_callback, 0);
 	return 0;
@@ -1874,46 +1401,24 @@ int zone_reclaim_interval __read_mostly = 30*HZ;
 /*
  * Try to free up some pages from this zone through reclaim.
  */
-int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 {
-	int nr_pages;
+	/* Minimum pages needed in order to stay on node */
+	const unsigned long nr_pages = 1 << order;
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
-	struct scan_control sc;
-	cpumask_t mask;
-	int node_id;
-
-	if (time_before(jiffies,
-		zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
-			return 0;
-
-	if (!(gfp_mask & __GFP_WAIT) ||
-		zone->all_unreclaimable ||
-		atomic_read(&zone->reclaim_in_progress) > 0 ||
-		(p->flags & PF_MEMALLOC))
-			return 0;
-
-	node_id = zone->zone_pgdat->node_id;
-	mask = node_to_cpumask(node_id);
-	if (!cpus_empty(mask) && node_id != numa_node_id())
-		return 0;
-
-	sc.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE);
-	sc.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP);
-	sc.nr_scanned = 0;
-	sc.nr_reclaimed = 0;
-	sc.priority = ZONE_RECLAIM_PRIORITY + 1;
-	sc.nr_mapped = read_page_state(nr_mapped);
-	sc.gfp_mask = gfp_mask;
+	int priority;
+	unsigned long nr_reclaimed = 0;
+	struct scan_control sc = {
+		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
+		.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.nr_mapped = read_page_state(nr_mapped),
+		.swap_cluster_max = max_t(unsigned long, nr_pages,
+					SWAP_CLUSTER_MAX),
+		.gfp_mask = gfp_mask,
+	};
 
 	disable_swap_token();
-
-	nr_pages = 1 << order;
-	if (nr_pages > SWAP_CLUSTER_MAX)
-		sc.swap_cluster_max = nr_pages;
-	else
-		sc.swap_cluster_max = SWAP_CLUSTER_MAX;
-
 	cond_resched();
 	/*
 	 * We need to be able to allocate from the reserves for RECLAIM_SWAP
@@ -1928,17 +1433,20 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 * Free memory by calling shrink zone with increasing priorities
 	 * until we have enough memory freed.
 	 */
+	priority = ZONE_RECLAIM_PRIORITY;
 	do {
-		sc.priority--;
-		shrink_zone(zone, &sc);
+		nr_reclaimed += shrink_zone(priority, zone, &sc);
+		priority--;
+	} while (priority >= 0 && nr_reclaimed < nr_pages);
 
-	} while (sc.nr_reclaimed < nr_pages && sc.priority > 0);
-
-	if (sc.nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
+	if (nr_reclaimed < nr_pages && (zone_reclaim_mode & RECLAIM_SLAB)) {
 		/*
-		 * shrink_slab does not currently allow us to determine
-		 * how many pages were freed in the zone. So we just
-		 * shake the slab and then go offnode for a single allocation.
+		 * shrink_slab() does not currently allow us to determine how
+		 * many pages were freed in this zone. So we just shake the slab
+		 * a bit and then go off node for this particular allocation
+		 * despite possibly having freed enough memory to allocate in
+		 * this zone.  If we freed local memory then the next
+		 * allocations will be local again.
 		 *
 		 * shrink_slab will free memory on all zones and may take
 		 * a long time.
@@ -1949,10 +1457,54 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
 
-	if (sc.nr_reclaimed == 0)
+	if (nr_reclaimed == 0) {
+		/*
+		 * We were unable to reclaim enough pages to stay on node.  We
+		 * now allow off node accesses for a certain time period before
+		 * trying again to reclaim pages from the local zone.
+		 */
 		zone->last_unsuccessful_zone_reclaim = jiffies;
+	}
 
-	return sc.nr_reclaimed >= nr_pages;
+	return nr_reclaimed >= nr_pages;
 }
-#endif
 
+int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
+{
+	cpumask_t mask;
+	int node_id;
+
+	/*
+	 * Do not reclaim if there was a recent unsuccessful attempt at zone
+	 * reclaim.  In that case we let allocations go off node for the
+	 * zone_reclaim_interval.  Otherwise we would scan for each off-node
+	 * page allocation.
+	 */
+	if (time_before(jiffies,
+		zone->last_unsuccessful_zone_reclaim + zone_reclaim_interval))
+			return 0;
+
+	/*
+	 * Avoid concurrent zone reclaims, do not reclaim in a zone that does
+	 * not have reclaimable pages and if we should not delay the allocation
+	 * then do not scan.
+	 */
+	if (!(gfp_mask & __GFP_WAIT) ||
+		zone->all_unreclaimable ||
+		atomic_read(&zone->reclaim_in_progress) > 0 ||
+		(current->flags & PF_MEMALLOC))
+			return 0;
+
+	/*
+	 * Only run zone reclaim on the local zone or on zones that do not
+	 * have associated processors. This will favor the local processor
+	 * over remote processors and spread off node memory allocations
+	 * as wide as possible.
+	 */
+	node_id = zone->zone_pgdat->node_id;
+	mask = node_to_cpumask(node_id);
+	if (!cpus_empty(mask) && node_id != numa_node_id())
+		return 0;
+	return __zone_reclaim(zone, gfp_mask, order);
+}
+#endif