Merge branch 'master' into next

Conflicts:
	fs/namei.c

Manually merged per:

diff --cc fs/namei.c
index 734f2b5,bbc15c2..0000000
--- a/fs/namei.c
+++ b/fs/namei.c
@@@ -860,9 -848,8 +849,10 @@@ static int __link_path_walk(const char
  		nd->flags |= LOOKUP_CONTINUE;
  		err = exec_permission_lite(inode);
  		if (err == -EAGAIN)
- 			err = vfs_permission(nd, MAY_EXEC);
+ 			err = inode_permission(nd->path.dentry->d_inode,
+ 					       MAY_EXEC);
 +		if (!err)
 +			err = ima_path_check(&nd->path, MAY_EXEC);
   		if (err)
  			break;

@@@ -1525,14 -1506,9 +1509,14 @@@ int may_open(struct path *path, int acc
  		flag &= ~O_TRUNC;
  	}

- 	error = vfs_permission(nd, acc_mode);
+ 	error = inode_permission(inode, acc_mode);
  	if (error)
  		return error;
 +
- 	error = ima_path_check(&nd->path,
++	error = ima_path_check(path,
 +			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
 +	if (error)
 +		return error;
  	/*
  	 * An append-only file must be opened in append mode for writing.
  	 */

Signed-off-by: James Morris <jmorris@namei.org>

40 files changed, 4061 insertions, 1854 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 5b5790f8a816..a5b77811fdf2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -181,12 +181,6 @@ config MIGRATION
 	  example on NUMA systems to put pages nearer to the processors accessing
 	  the page.
 
-config RESOURCES_64BIT
-	bool "64 bit Memory and IO resources (EXPERIMENTAL)" if (!64BIT && EXPERIMENTAL)
-	default 64BIT
-	help
-	  This option allows memory and IO resources to be 64 bit.
-
 config PHYS_ADDR_T_64BIT
 	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
 
diff --git a/mm/Makefile b/mm/Makefile
index 51c27709cc7c..72255be57f89 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -9,7 +9,7 @@ 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 \
 			   maccess.o page_alloc.o page-writeback.o pdflush.o \
-			   readahead.o swap.o truncate.o vmscan.o \
+			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   page_isolation.o mm_init.o $(mmu-y)
 
@@ -21,9 +21,7 @@ obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
-obj-$(CONFIG_SHMEM) += shmem.o
 obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o
-obj-$(CONFIG_TINY_SHMEM) += tiny-shmem.o
 obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_SLAB) += slab.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 801c08b046e6..8e8587444132 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -24,9 +24,9 @@ static void bdi_debug_init(void)
 static int bdi_debug_stats_show(struct seq_file *m, void *v)
 {
 	struct backing_dev_info *bdi = m->private;
-	long background_thresh;
-	long dirty_thresh;
-	long bdi_thresh;
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
+	unsigned long bdi_thresh;
 
 	get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi);
 
@@ -223,7 +223,7 @@ int bdi_init(struct backing_dev_info *bdi)
 	bdi->max_prop_frac = PROP_FRAC_BASE;
 
 	for (i = 0; i < NR_BDI_STAT_ITEMS; i++) {
-		err = percpu_counter_init_irq(&bdi->bdi_stat[i], 0);
+		err = percpu_counter_init(&bdi->bdi_stat[i], 0);
 		if (err)
 			goto err;
 	}
diff --git a/mm/bootmem.c b/mm/bootmem.c
index ac5a891f142a..51a0ccf61e0e 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -435,6 +435,10 @@ static void * __init alloc_bootmem_core(struct bootmem_data *bdata,
 	unsigned long fallback = 0;
 	unsigned long min, max, start, sidx, midx, step;
 
+	bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n",
+		bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT,
+		align, goal, limit);
+
 	BUG_ON(!size);
 	BUG_ON(align & (align - 1));
 	BUG_ON(limit && goal + size > limit);
@@ -442,10 +446,6 @@ static void * __init alloc_bootmem_core(struct bootmem_data *bdata,
 	if (!bdata->node_bootmem_map)
 		return NULL;
 
-	bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n",
-		bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT,
-		align, goal, limit);
-
 	min = bdata->node_min_pfn;
 	max = bdata->node_low_pfn;
 
diff --git a/mm/fadvise.c b/mm/fadvise.c
index a1da969bd980..54a0f8040afa 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -24,7 +24,7 @@
  * POSIX_FADV_WILLNEED could set PG_Referenced, and POSIX_FADV_NOREUSE could
  * deactivate the pages and clear PG_Referenced.
  */
-asmlinkage long sys_fadvise64_64(int fd, loff_t offset, loff_t len, int advice)
+SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
 {
 	struct file *file = fget(fd);
 	struct address_space *mapping;
@@ -126,12 +126,26 @@ out:
 	fput(file);
 	return ret;
 }
+#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
+asmlinkage long SyS_fadvise64_64(long fd, loff_t offset, loff_t len, long advice)
+{
+	return SYSC_fadvise64_64((int) fd, offset, len, (int) advice);
+}
+SYSCALL_ALIAS(sys_fadvise64_64, SyS_fadvise64_64);
+#endif
 
 #ifdef __ARCH_WANT_SYS_FADVISE64
 
-asmlinkage long sys_fadvise64(int fd, loff_t offset, size_t len, int advice)
+SYSCALL_DEFINE(fadvise64)(int fd, loff_t offset, size_t len, int advice)
 {
 	return sys_fadvise64_64(fd, offset, len, advice);
 }
+#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
+asmlinkage long SyS_fadvise64(long fd, loff_t offset, long len, long advice)
+{
+	return SYSC_fadvise64((int) fd, offset, (size_t)len, (int)advice);
+}
+SYSCALL_ALIAS(sys_fadvise64, SyS_fadvise64);
+#endif
 
 #endif
diff --git a/mm/filemap.c b/mm/filemap.c
index f3e5f8944d17..23acefe51808 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -210,7 +210,7 @@ int __filemap_fdatawrite_range(struct address_space *mapping, loff_t start,
 	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = sync_mode,
-		.nr_to_write = mapping->nrpages * 2,
+		.nr_to_write = LONG_MAX,
 		.range_start = start,
 		.range_end = end,
 	};
@@ -460,7 +460,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 	VM_BUG_ON(!PageLocked(page));
 
 	error = mem_cgroup_cache_charge(page, current->mm,
-					gfp_mask & ~__GFP_HIGHMEM);
+					gfp_mask & GFP_RECLAIM_MASK);
 	if (error)
 		goto out;
 
@@ -741,7 +741,14 @@ repeat:
 		page = __page_cache_alloc(gfp_mask);
 		if (!page)
 			return NULL;
-		err = add_to_page_cache_lru(page, mapping, index, gfp_mask);
+		/*
+		 * We want a regular kernel memory (not highmem or DMA etc)
+		 * allocation for the radix tree nodes, but we need to honour
+		 * the context-specific requirements the caller has asked for.
+		 * GFP_RECLAIM_MASK collects those requirements.
+		 */
+		err = add_to_page_cache_lru(page, mapping, index,
+			(gfp_mask & GFP_RECLAIM_MASK));
 		if (unlikely(err)) {
 			page_cache_release(page);
 			page = NULL;
@@ -950,7 +957,7 @@ grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
 		return NULL;
 	}
 	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~__GFP_FS);
-	if (page && add_to_page_cache_lru(page, mapping, index, GFP_KERNEL)) {
+	if (page && add_to_page_cache_lru(page, mapping, index, GFP_NOFS)) {
 		page_cache_release(page);
 		page = NULL;
 	}
@@ -1317,7 +1324,8 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 			goto out; /* skip atime */
 		size = i_size_read(inode);
 		if (pos < size) {
-			retval = filemap_write_and_wait(mapping);
+			retval = filemap_write_and_wait_range(mapping, pos,
+					pos + iov_length(iov, nr_segs) - 1);
 			if (!retval) {
 				retval = mapping->a_ops->direct_IO(READ, iocb,
 							iov, pos, nr_segs);
@@ -1366,7 +1374,7 @@ do_readahead(struct address_space *mapping, struct file *filp,
 	return 0;
 }
 
-asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
+SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
 {
 	ssize_t ret;
 	struct file *file;
@@ -1385,6 +1393,13 @@ asmlinkage ssize_t sys_readahead(int fd, loff_t offset, size_t count)
 	}
 	return ret;
 }
+#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
+asmlinkage long SyS_readahead(long fd, loff_t offset, long count)
+{
+	return SYSC_readahead((int) fd, offset, (size_t) count);
+}
+SYSCALL_ALIAS(sys_readahead, SyS_readahead);
+#endif
 
 #ifdef CONFIG_MMU
 /**
@@ -1530,7 +1545,6 @@ retry_find:
 	/*
 	 * Found the page and have a reference on it.
 	 */
-	mark_page_accessed(page);
 	ra->prev_pos = (loff_t)page->index << PAGE_CACHE_SHIFT;
 	vmf->page = page;
 	return ret | VM_FAULT_LOCKED;
@@ -1766,7 +1780,7 @@ int should_remove_suid(struct dentry *dentry)
 	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
 		kill |= ATTR_KILL_SGID;
 
-	if (unlikely(kill && !capable(CAP_FSETID)))
+	if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode)))
 		return kill;
 
 	return 0;
@@ -2060,18 +2074,10 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	if (count != ocount)
 		*nr_segs = iov_shorten((struct iovec *)iov, *nr_segs, count);
 
-	/*
-	 * Unmap all mmappings of the file up-front.
-	 *
-	 * This will cause any pte dirty bits to be propagated into the
-	 * pageframes for the subsequent filemap_write_and_wait().
-	 */
 	write_len = iov_length(iov, *nr_segs);
 	end = (pos + write_len - 1) >> PAGE_CACHE_SHIFT;
-	if (mapping_mapped(mapping))
-		unmap_mapping_range(mapping, pos, write_len, 0);
 
-	written = filemap_write_and_wait(mapping);
+	written = filemap_write_and_wait_range(mapping, pos, pos + write_len - 1);
 	if (written)
 		goto out;
 
@@ -2140,19 +2146,24 @@ EXPORT_SYMBOL(generic_file_direct_write);
  * Find or create a page at the given pagecache position. Return the locked
  * page. This function is specifically for buffered writes.
  */
-struct page *__grab_cache_page(struct address_space *mapping, pgoff_t index)
+struct page *grab_cache_page_write_begin(struct address_space *mapping,
+					pgoff_t index, unsigned flags)
 {
 	int status;
 	struct page *page;
+	gfp_t gfp_notmask = 0;
+	if (flags & AOP_FLAG_NOFS)
+		gfp_notmask = __GFP_FS;
 repeat:
 	page = find_lock_page(mapping, index);
 	if (likely(page))
 		return page;
 
-	page = page_cache_alloc(mapping);
+	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
 	if (!page)
 		return NULL;
-	status = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+	status = add_to_page_cache_lru(page, mapping, index,
+						GFP_KERNEL & ~gfp_notmask);
 	if (unlikely(status)) {
 		page_cache_release(page);
 		if (status == -EEXIST)
@@ -2161,7 +2172,7 @@ repeat:
 	}
 	return page;
 }
-EXPORT_SYMBOL(__grab_cache_page);
+EXPORT_SYMBOL(grab_cache_page_write_begin);
 
 static ssize_t generic_perform_write(struct file *file,
 				struct iov_iter *i, loff_t pos)
@@ -2286,7 +2297,8 @@ generic_file_buffered_write(struct kiocb *iocb, const struct iovec *iov,
 	 * the file data here, to try to honour O_DIRECT expectations.
 	 */
 	if (unlikely(file->f_flags & O_DIRECT) && written)
-		status = filemap_write_and_wait(mapping);
+		status = filemap_write_and_wait_range(mapping,
+					pos, pos + written - 1);
 
 	return written ? written : status;
 }
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index b5167dfb2f2d..0c04615651b7 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -193,7 +193,7 @@ retry:
 			/* Nuke the page table entry. */
 			flush_cache_page(vma, address, pte_pfn(*pte));
 			pteval = ptep_clear_flush_notify(vma, address, pte);
-			page_remove_rmap(page, vma);
+			page_remove_rmap(page);
 			dec_mm_counter(mm, file_rss);
 			BUG_ON(pte_dirty(pteval));
 			pte_unmap_unlock(pte, ptl);
diff --git a/mm/fremap.c b/mm/fremap.c
index 7d12ca70ef7b..736ba7f3306a 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -37,7 +37,7 @@ static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (page) {
 			if (pte_dirty(pte))
 				set_page_dirty(page);
-			page_remove_rmap(page, vma);
+			page_remove_rmap(page);
 			page_cache_release(page);
 			update_hiwater_rss(mm);
 			dec_mm_counter(mm, file_rss);
@@ -120,8 +120,8 @@ static int populate_range(struct mm_struct *mm, struct vm_area_struct *vma,
  * and the vma's default protection is used. Arbitrary protections
  * might be implemented in the future.
  */
-asmlinkage long sys_remap_file_pages(unsigned long start, unsigned long size,
-	unsigned long prot, unsigned long pgoff, unsigned long flags)
+SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+		unsigned long, prot, unsigned long, pgoff, unsigned long, flags)
 {
 	struct mm_struct *mm = current->mm;
 	struct address_space *mapping;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 6058b53dcb89..618e98304080 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -220,6 +220,35 @@ static pgoff_t vma_hugecache_offset(struct hstate *h,
 }
 
 /*
+ * Return the size of the pages allocated when backing a VMA. In the majority
+ * cases this will be same size as used by the page table entries.
+ */
+unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
+{
+	struct hstate *hstate;
+
+	if (!is_vm_hugetlb_page(vma))
+		return PAGE_SIZE;
+
+	hstate = hstate_vma(vma);
+
+	return 1UL << (hstate->order + PAGE_SHIFT);
+}
+
+/*
+ * Return the page size being used by the MMU to back a VMA. In the majority
+ * of cases, the page size used by the kernel matches the MMU size. On
+ * architectures where it differs, an architecture-specific version of this
+ * function is required.
+ */
+#ifndef vma_mmu_pagesize
+unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
+{
+	return vma_kernel_pagesize(vma);
+}
+#endif
+
+/*
  * Flags for MAP_PRIVATE reservations.  These are stored in the bottom
  * bits of the reservation map pointer, which are always clear due to
  * alignment.
@@ -371,8 +400,10 @@ static void clear_huge_page(struct page *page,
 {
 	int i;
 
-	if (unlikely(sz > MAX_ORDER_NR_PAGES))
-		return clear_gigantic_page(page, addr, sz);
+	if (unlikely(sz > MAX_ORDER_NR_PAGES)) {
+		clear_gigantic_page(page, addr, sz);
+		return;
+	}
 
 	might_sleep();
 	for (i = 0; i < sz/PAGE_SIZE; i++) {
@@ -404,8 +435,10 @@ static void copy_huge_page(struct page *dst, struct page *src,
 	int i;
 	struct hstate *h = hstate_vma(vma);
 
-	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES))
-		return copy_gigantic_page(dst, src, addr, vma);
+	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
+		copy_gigantic_page(dst, src, addr, vma);
+		return;
+	}
 
 	might_sleep();
 	for (i = 0; i < pages_per_huge_page(h); i++) {
@@ -972,7 +1005,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	return page;
 }
 
-__attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h)
+int __weak alloc_bootmem_huge_page(struct hstate *h)
 {
 	struct huge_bootmem_page *m;
 	int nr_nodes = nodes_weight(node_online_map);
@@ -991,8 +1024,7 @@ __attribute__((weak)) int alloc_bootmem_huge_page(struct hstate *h)
 			 * puts them into the mem_map).
 			 */
 			m = addr;
-			if (m)
-				goto found;
+			goto found;
 		}
 		hstate_next_node(h);
 		nr_nodes--;
diff --git a/mm/internal.h b/mm/internal.h
index 13333bc2eb68..478223b73a2a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -49,6 +49,7 @@ extern void putback_lru_page(struct page *page);
 /*
  * in mm/page_alloc.c
  */
+extern unsigned long highest_memmap_pfn;
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
@@ -275,6 +276,7 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 #define GUP_FLAGS_WRITE                  0x1
 #define GUP_FLAGS_FORCE                  0x2
 #define GUP_FLAGS_IGNORE_VMA_PERMISSIONS 0x4
+#define GUP_FLAGS_IGNORE_SIGKILL         0x8
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long start, int len, int flags,
diff --git a/mm/madvise.c b/mm/madvise.c
index f9349c18a1b5..b9ce574827c8 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -281,7 +281,7 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
  *  -EBADF  - map exists, but area maps something that isn't a file.
  *  -EAGAIN - a kernel resource was temporarily unavailable.
  */
-asmlinkage long sys_madvise(unsigned long start, size_t len_in, int behavior)
+SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct * vma, *prev;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 866dcc7eeb0c..8e4be9cb2a6a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -21,11 +21,13 @@
 #include <linux/memcontrol.h>
 #include <linux/cgroup.h>
 #include <linux/mm.h>
+#include <linux/pagemap.h>
 #include <linux/smp.h>
 #include <linux/page-flags.h>
 #include <linux/backing-dev.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/spinlock.h>
@@ -34,12 +36,23 @@
 #include <linux/vmalloc.h>
 #include <linux/mm_inline.h>
 #include <linux/page_cgroup.h>
+#include "internal.h"
 
 #include <asm/uaccess.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+/* Turned on only when memory cgroup is enabled && really_do_swap_account = 0 */
+int do_swap_account __read_mostly;
+static int really_do_swap_account __initdata = 1; /* for remember boot option*/
+#else
+#define do_swap_account		(0)
+#endif
+
+static DEFINE_MUTEX(memcg_tasklist);	/* can be hold under cgroup_mutex */
+
 /*
  * Statistics for memory cgroup.
  */
@@ -60,7 +73,7 @@ struct mem_cgroup_stat_cpu {
 } ____cacheline_aligned_in_smp;
 
 struct mem_cgroup_stat {
-	struct mem_cgroup_stat_cpu cpustat[NR_CPUS];
+	struct mem_cgroup_stat_cpu cpustat[0];
 };
 
 /*
@@ -89,9 +102,10 @@ struct mem_cgroup_per_zone {
 	/*
 	 * spin_lock to protect the per cgroup LRU
 	 */
-	spinlock_t		lru_lock;
 	struct list_head	lists[NR_LRU_LISTS];
 	unsigned long		count[NR_LRU_LISTS];
+
+	struct zone_reclaim_stat reclaim_stat;
 };
 /* Macro for accessing counter */
 #define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
@@ -122,44 +136,74 @@ struct mem_cgroup {
 	 */
 	struct res_counter res;
 	/*
+	 * the counter to account for mem+swap usage.
+	 */
+	struct res_counter memsw;
+	/*
 	 * Per cgroup active and inactive list, similar to the
 	 * per zone LRU lists.
 	 */
 	struct mem_cgroup_lru_info info;
 
+	/*
+	  protect against reclaim related member.
+	*/
+	spinlock_t reclaim_param_lock;
+
 	int	prev_priority;	/* for recording reclaim priority */
+
+	/*
+	 * While reclaiming in a hiearchy, we cache the last child we
+	 * reclaimed from. Protected by hierarchy_mutex
+	 */
+	struct mem_cgroup *last_scanned_child;
 	/*
-	 * statistics.
+	 * Should the accounting and control be hierarchical, per subtree?
+	 */
+	bool use_hierarchy;
+	unsigned long	last_oom_jiffies;
+	atomic_t	refcnt;
+
+	unsigned int	swappiness;
+
+	/*
+	 * statistics. This must be placed at the end of memcg.
 	 */
 	struct mem_cgroup_stat stat;
 };
-static struct mem_cgroup init_mem_cgroup;
 
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
 	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
 	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
+	MEM_CGROUP_CHARGE_TYPE_SWAPOUT,	/* for accounting swapcache */
 	NR_CHARGE_TYPE,
 };
 
 /* only for here (for easy reading.) */
 #define PCGF_CACHE	(1UL << PCG_CACHE)
 #define PCGF_USED	(1UL << PCG_USED)
-#define PCGF_ACTIVE	(1UL << PCG_ACTIVE)
 #define PCGF_LOCK	(1UL << PCG_LOCK)
-#define PCGF_FILE	(1UL << PCG_FILE)
 static const unsigned long
 pcg_default_flags[NR_CHARGE_TYPE] = {
-	PCGF_CACHE | PCGF_FILE | PCGF_USED | PCGF_LOCK, /* File Cache */
-	PCGF_ACTIVE | PCGF_USED | PCGF_LOCK, /* Anon */
-	PCGF_ACTIVE | PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
+	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* File Cache */
+	PCGF_USED | PCGF_LOCK, /* Anon */
+	PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
 	0, /* FORCE */
 };
 
-/*
- * Always modified under lru lock. Then, not necessary to preempt_disable()
- */
+/* for encoding cft->private value on file */
+#define _MEM			(0)
+#define _MEMSWAP		(1)
+#define MEMFILE_PRIVATE(x, val)	(((x) << 16) | (val))
+#define MEMFILE_TYPE(val)	(((val) >> 16) & 0xffff)
+#define MEMFILE_ATTR(val)	((val) & 0xffff)
+
+static void mem_cgroup_get(struct mem_cgroup *mem);
+static void mem_cgroup_put(struct mem_cgroup *mem);
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem);
+
 static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 					 struct page_cgroup *pc,
 					 bool charge)
@@ -167,10 +211,9 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 	int val = (charge)? 1 : -1;
 	struct mem_cgroup_stat *stat = &mem->stat;
 	struct mem_cgroup_stat_cpu *cpustat;
+	int cpu = get_cpu();
 
-	VM_BUG_ON(!irqs_disabled());
-
-	cpustat = &stat->cpustat[smp_processor_id()];
+	cpustat = &stat->cpustat[cpu];
 	if (PageCgroupCache(pc))
 		__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_CACHE, val);
 	else
@@ -182,6 +225,7 @@ static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
 	else
 		__mem_cgroup_stat_add_safe(cpustat,
 				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
+	put_cpu();
 }
 
 static struct mem_cgroup_per_zone *
@@ -197,6 +241,9 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
 	int nid = page_cgroup_nid(pc);
 	int zid = page_cgroup_zid(pc);
 
+	if (!mem)
+		return NULL;
+
 	return mem_cgroup_zoneinfo(mem, nid, zid);
 }
 
@@ -236,118 +283,169 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 				struct mem_cgroup, css);
 }
 
-static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
-			struct page_cgroup *pc)
+static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
-	int lru = LRU_BASE;
-
-	if (PageCgroupUnevictable(pc))
-		lru = LRU_UNEVICTABLE;
-	else {
-		if (PageCgroupActive(pc))
-			lru += LRU_ACTIVE;
-		if (PageCgroupFile(pc))
-			lru += LRU_FILE;
-	}
-
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
-
-	mem_cgroup_charge_statistics(pc->mem_cgroup, pc, false);
-	list_del(&pc->lru);
+	struct mem_cgroup *mem = NULL;
+	/*
+	 * Because we have no locks, mm->owner's may be being moved to other
+	 * cgroup. We use css_tryget() here even if this looks
+	 * pessimistic (rather than adding locks here).
+	 */
+	rcu_read_lock();
+	do {
+		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+		if (unlikely(!mem))
+			break;
+	} while (!css_tryget(&mem->css));
+	rcu_read_unlock();
+	return mem;
 }
 
-static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
-				struct page_cgroup *pc)
+static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
 {
-	int lru = LRU_BASE;
+	if (!mem)
+		return true;
+	return css_is_removed(&mem->css);
+}
 
-	if (PageCgroupUnevictable(pc))
-		lru = LRU_UNEVICTABLE;
-	else {
-		if (PageCgroupActive(pc))
-			lru += LRU_ACTIVE;
-		if (PageCgroupFile(pc))
-			lru += LRU_FILE;
-	}
+/*
+ * Following LRU functions are allowed to be used without PCG_LOCK.
+ * Operations are called by routine of global LRU independently from memcg.
+ * What we have to take care of here is validness of pc->mem_cgroup.
+ *
+ * Changes to pc->mem_cgroup happens when
+ * 1. charge
+ * 2. moving account
+ * In typical case, "charge" is done before add-to-lru. Exception is SwapCache.
+ * It is added to LRU before charge.
+ * If PCG_USED bit is not set, page_cgroup is not added to this private LRU.
+ * When moving account, the page is not on LRU. It's isolated.
+ */
 
-	MEM_CGROUP_ZSTAT(mz, lru) += 1;
-	list_add(&pc->lru, &mz->lists[lru]);
+void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
+{
+	struct page_cgroup *pc;
+	struct mem_cgroup *mem;
+	struct mem_cgroup_per_zone *mz;
 
-	mem_cgroup_charge_statistics(pc->mem_cgroup, pc, true);
+	if (mem_cgroup_disabled())
+		return;
+	pc = lookup_page_cgroup(page);
+	/* can happen while we handle swapcache. */
+	if (list_empty(&pc->lru) || !pc->mem_cgroup)
+		return;
+	/*
+	 * We don't check PCG_USED bit. It's cleared when the "page" is finally
+	 * removed from global LRU.
+	 */
+	mz = page_cgroup_zoneinfo(pc);
+	mem = pc->mem_cgroup;
+	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	list_del_init(&pc->lru);
+	return;
 }
 
-static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
+void mem_cgroup_del_lru(struct page *page)
 {
-	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
-	int active    = PageCgroupActive(pc);
-	int file      = PageCgroupFile(pc);
-	int unevictable = PageCgroupUnevictable(pc);
-	enum lru_list from = unevictable ? LRU_UNEVICTABLE :
-				(LRU_FILE * !!file + !!active);
+	mem_cgroup_del_lru_list(page, page_lru(page));
+}
 
-	if (lru == from)
+void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
+{
+	struct mem_cgroup_per_zone *mz;
+	struct page_cgroup *pc;
+
+	if (mem_cgroup_disabled())
 		return;
 
-	MEM_CGROUP_ZSTAT(mz, from) -= 1;
+	pc = lookup_page_cgroup(page);
 	/*
-	 * However this is done under mz->lru_lock, another flags, which
-	 * are not related to LRU, will be modified from out-of-lock.
-	 * We have to use atomic set/clear flags.
+	 * Used bit is set without atomic ops but after smp_wmb().
+	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
 	 */
-	if (is_unevictable_lru(lru)) {
-		ClearPageCgroupActive(pc);
-		SetPageCgroupUnevictable(pc);
-	} else {
-		if (is_active_lru(lru))
-			SetPageCgroupActive(pc);
-		else
-			ClearPageCgroupActive(pc);
-		ClearPageCgroupUnevictable(pc);
-	}
-
-	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	smp_rmb();
+	/* unused page is not rotated. */
+	if (!PageCgroupUsed(pc))
+		return;
+	mz = page_cgroup_zoneinfo(pc);
 	list_move(&pc->lru, &mz->lists[lru]);
 }
 
-int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
+void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
 {
-	int ret;
+	struct page_cgroup *pc;
+	struct mem_cgroup_per_zone *mz;
 
-	task_lock(task);
-	ret = task->mm && mm_match_cgroup(task->mm, mem);
-	task_unlock(task);
-	return ret;
+	if (mem_cgroup_disabled())
+		return;
+	pc = lookup_page_cgroup(page);
+	/*
+	 * Used bit is set without atomic ops but after smp_wmb().
+	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
+	 */
+	smp_rmb();
+	if (!PageCgroupUsed(pc))
+		return;
+
+	mz = page_cgroup_zoneinfo(pc);
+	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	list_add(&pc->lru, &mz->lists[lru]);
 }
 
 /*
- * This routine assumes that the appropriate zone's lru lock is already held
+ * At handling SwapCache, pc->mem_cgroup may be changed while it's linked to
+ * lru because the page may.be reused after it's fully uncharged (because of
+ * SwapCache behavior).To handle that, unlink page_cgroup from LRU when charge
+ * it again. This function is only used to charge SwapCache. It's done under
+ * lock_page and expected that zone->lru_lock is never held.
  */
-void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
+static void mem_cgroup_lru_del_before_commit_swapcache(struct page *page)
 {
-	struct page_cgroup *pc;
-	struct mem_cgroup_per_zone *mz;
 	unsigned long flags;
+	struct zone *zone = page_zone(page);
+	struct page_cgroup *pc = lookup_page_cgroup(page);
 
-	if (mem_cgroup_subsys.disabled)
-		return;
-
+	spin_lock_irqsave(&zone->lru_lock, flags);
 	/*
-	 * We cannot lock_page_cgroup while holding zone's lru_lock,
-	 * because other holders of lock_page_cgroup can be interrupted
-	 * with an attempt to rotate_reclaimable_page.  But we cannot
-	 * safely get to page_cgroup without it, so just try_lock it:
-	 * mem_cgroup_isolate_pages allows for page left on wrong list.
+	 * Forget old LRU when this page_cgroup is *not* used. This Used bit
+	 * is guarded by lock_page() because the page is SwapCache.
 	 */
-	pc = lookup_page_cgroup(page);
-	if (!trylock_page_cgroup(pc))
+	if (!PageCgroupUsed(pc))
+		mem_cgroup_del_lru_list(page, page_lru(page));
+	spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
+
+static void mem_cgroup_lru_add_after_commit_swapcache(struct page *page)
+{
+	unsigned long flags;
+	struct zone *zone = page_zone(page);
+	struct page_cgroup *pc = lookup_page_cgroup(page);
+
+	spin_lock_irqsave(&zone->lru_lock, flags);
+	/* link when the page is linked to LRU but page_cgroup isn't */
+	if (PageLRU(page) && list_empty(&pc->lru))
+		mem_cgroup_add_lru_list(page, page_lru(page));
+	spin_unlock_irqrestore(&zone->lru_lock, flags);
+}
+
+
+void mem_cgroup_move_lists(struct page *page,
+			   enum lru_list from, enum lru_list to)
+{
+	if (mem_cgroup_disabled())
 		return;
-	if (pc && PageCgroupUsed(pc)) {
-		mz = page_cgroup_zoneinfo(pc);
-		spin_lock_irqsave(&mz->lru_lock, flags);
-		__mem_cgroup_move_lists(pc, lru);
-		spin_unlock_irqrestore(&mz->lru_lock, flags);
-	}
-	unlock_page_cgroup(pc);
+	mem_cgroup_del_lru_list(page, from);
+	mem_cgroup_add_lru_list(page, to);
+}
+
+int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
+{
+	int ret;
+
+	task_lock(task);
+	ret = task->mm && mm_match_cgroup(task->mm, mem);
+	task_unlock(task);
+	return ret;
 }
 
 /*
@@ -372,39 +470,116 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
  */
 int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
 {
-	return mem->prev_priority;
+	int prev_priority;
+
+	spin_lock(&mem->reclaim_param_lock);
+	prev_priority = mem->prev_priority;
+	spin_unlock(&mem->reclaim_param_lock);
+
+	return prev_priority;
 }
 
 void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem, int priority)
 {
+	spin_lock(&mem->reclaim_param_lock);
 	if (priority < mem->prev_priority)
 		mem->prev_priority = priority;
+	spin_unlock(&mem->reclaim_param_lock);
 }
 
 void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
 {
+	spin_lock(&mem->reclaim_param_lock);
 	mem->prev_priority = priority;
+	spin_unlock(&mem->reclaim_param_lock);
 }
 
-/*
- * Calculate # of pages to be scanned in this priority/zone.
- * See also vmscan.c
- *
- * priority starts from "DEF_PRIORITY" and decremented in each loop.
- * (see include/linux/mmzone.h)
- */
+static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_pages)
+{
+	unsigned long active;
+	unsigned long inactive;
+	unsigned long gb;
+	unsigned long inactive_ratio;
+
+	inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON);
+	active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON);
+
+	gb = (inactive + active) >> (30 - PAGE_SHIFT);
+	if (gb)
+		inactive_ratio = int_sqrt(10 * gb);
+	else
+		inactive_ratio = 1;
+
+	if (present_pages) {
+		present_pages[0] = inactive;
+		present_pages[1] = active;
+	}
+
+	return inactive_ratio;
+}
 
-long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
-					int priority, enum lru_list lru)
+int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg)
+{
+	unsigned long active;
+	unsigned long inactive;
+	unsigned long present_pages[2];
+	unsigned long inactive_ratio;
+
+	inactive_ratio = calc_inactive_ratio(memcg, present_pages);
+
+	inactive = present_pages[0];
+	active = present_pages[1];
+
+	if (inactive * inactive_ratio < active)
+		return 1;
+
+	return 0;
+}
+
+unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
+				       struct zone *zone,
+				       enum lru_list lru)
 {
-	long nr_pages;
 	int nid = zone->zone_pgdat->node_id;
 	int zid = zone_idx(zone);
-	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
+	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
 
-	nr_pages = MEM_CGROUP_ZSTAT(mz, lru);
+	return MEM_CGROUP_ZSTAT(mz, lru);
+}
+
+struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
+						      struct zone *zone)
+{
+	int nid = zone->zone_pgdat->node_id;
+	int zid = zone_idx(zone);
+	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(memcg, nid, zid);
 
-	return (nr_pages >> priority);
+	return &mz->reclaim_stat;
+}
+
+struct zone_reclaim_stat *
+mem_cgroup_get_reclaim_stat_from_page(struct page *page)
+{
+	struct page_cgroup *pc;
+	struct mem_cgroup_per_zone *mz;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	pc = lookup_page_cgroup(page);
+	/*
+	 * Used bit is set without atomic ops but after smp_wmb().
+	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
+	 */
+	smp_rmb();
+	if (!PageCgroupUsed(pc))
+		return NULL;
+
+	mz = page_cgroup_zoneinfo(pc);
+	if (!mz)
+		return NULL;
+
+	return &mz->reclaim_stat;
 }
 
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
@@ -429,94 +604,279 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
 	src = &mz->lists[lru];
 
-	spin_lock(&mz->lru_lock);
 	scan = 0;
 	list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
 		if (scan >= nr_to_scan)
 			break;
+
+		page = pc->page;
 		if (unlikely(!PageCgroupUsed(pc)))
 			continue;
-		page = pc->page;
-
 		if (unlikely(!PageLRU(page)))
 			continue;
 
-		/*
-		 * TODO: play better with lumpy reclaim, grabbing anything.
-		 */
-		if (PageUnevictable(page) ||
-		    (PageActive(page) && !active) ||
-		    (!PageActive(page) && active)) {
-			__mem_cgroup_move_lists(pc, page_lru(page));
-			continue;
-		}
-
 		scan++;
-		list_move(&pc->lru, &pc_list);
-
 		if (__isolate_lru_page(page, mode, file) == 0) {
 			list_move(&page->lru, dst);
 			nr_taken++;
 		}
 	}
 
-	list_splice(&pc_list, src);
-	spin_unlock(&mz->lru_lock);
-
 	*scanned = scan;
 	return nr_taken;
 }
 
+#define mem_cgroup_from_res_counter(counter, member)	\
+	container_of(counter, struct mem_cgroup, member)
+
 /*
- * Charge the memory controller for page usage.
- * Return
- * 0 if the charge was successful
- * < 0 if the cgroup is over its limit
+ * This routine finds the DFS walk successor. This routine should be
+ * called with hierarchy_mutex held
  */
-static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
-				gfp_t gfp_mask, enum charge_type ctype,
-				struct mem_cgroup *memcg)
+static struct mem_cgroup *
+__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
 {
+	struct cgroup *cgroup, *curr_cgroup, *root_cgroup;
+
+	curr_cgroup = curr->css.cgroup;
+	root_cgroup = root_mem->css.cgroup;
+
+	if (!list_empty(&curr_cgroup->children)) {
+		/*
+		 * Walk down to children
+		 */
+		cgroup = list_entry(curr_cgroup->children.next,
+						struct cgroup, sibling);
+		curr = mem_cgroup_from_cont(cgroup);
+		goto done;
+	}
+
+visit_parent:
+	if (curr_cgroup == root_cgroup) {
+		/* caller handles NULL case */
+		curr = NULL;
+		goto done;
+	}
+
+	/*
+	 * Goto next sibling
+	 */
+	if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) {
+		cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup,
+						sibling);
+		curr = mem_cgroup_from_cont(cgroup);
+		goto done;
+	}
+
+	/*
+	 * Go up to next parent and next parent's sibling if need be
+	 */
+	curr_cgroup = curr_cgroup->parent;
+	goto visit_parent;
+
+done:
+	return curr;
+}
+
+/*
+ * Visit the first child (need not be the first child as per the ordering
+ * of the cgroup list, since we track last_scanned_child) of @mem and use
+ * that to reclaim free pages from.
+ */
+static struct mem_cgroup *
+mem_cgroup_get_next_node(struct mem_cgroup *root_mem)
+{
+	struct cgroup *cgroup;
+	struct mem_cgroup *orig, *next;
+	bool obsolete;
+
+	/*
+	 * Scan all children under the mem_cgroup mem
+	 */
+	mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);
+
+	orig = root_mem->last_scanned_child;
+	obsolete = mem_cgroup_is_obsolete(orig);
+
+	if (list_empty(&root_mem->css.cgroup->children)) {
+		/*
+		 * root_mem might have children before and last_scanned_child
+		 * may point to one of them. We put it later.
+		 */
+		if (orig)
+			VM_BUG_ON(!obsolete);
+		next = NULL;
+		goto done;
+	}
+
+	if (!orig || obsolete) {
+		cgroup = list_first_entry(&root_mem->css.cgroup->children,
+				struct cgroup, sibling);
+		next = mem_cgroup_from_cont(cgroup);
+	} else
+		next = __mem_cgroup_get_next_node(orig, root_mem);
+
+done:
+	if (next)
+		mem_cgroup_get(next);
+	root_mem->last_scanned_child = next;
+	if (orig)
+		mem_cgroup_put(orig);
+	mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
+	return (next) ? next : root_mem;
+}
+
+static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
+{
+	if (do_swap_account) {
+		if (res_counter_check_under_limit(&mem->res) &&
+			res_counter_check_under_limit(&mem->memsw))
+			return true;
+	} else
+		if (res_counter_check_under_limit(&mem->res))
+			return true;
+	return false;
+}
+
+static unsigned int get_swappiness(struct mem_cgroup *memcg)
+{
+	struct cgroup *cgrp = memcg->css.cgroup;
+	unsigned int swappiness;
+
+	/* root ? */
+	if (cgrp->parent == NULL)
+		return vm_swappiness;
+
+	spin_lock(&memcg->reclaim_param_lock);
+	swappiness = memcg->swappiness;
+	spin_unlock(&memcg->reclaim_param_lock);
+
+	return swappiness;
+}
+
+/*
+ * Dance down the hierarchy if needed to reclaim memory. We remember the
+ * last child we reclaimed from, so that we don't end up penalizing
+ * one child extensively based on its position in the children list.
+ *
+ * root_mem is the original ancestor that we've been reclaim from.
+ */
+static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
+						gfp_t gfp_mask, bool noswap)
+{
+	struct mem_cgroup *next_mem;
+	int ret = 0;
+
+	/*
+	 * Reclaim unconditionally and don't check for return value.
+	 * We need to reclaim in the current group and down the tree.
+	 * One might think about checking for children before reclaiming,
+	 * but there might be left over accounting, even after children
+	 * have left.
+	 */
+	ret += try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap,
+					   get_swappiness(root_mem));
+	if (mem_cgroup_check_under_limit(root_mem))
+		return 1;	/* indicate reclaim has succeeded */
+	if (!root_mem->use_hierarchy)
+		return ret;
+
+	next_mem = mem_cgroup_get_next_node(root_mem);
+
+	while (next_mem != root_mem) {
+		if (mem_cgroup_is_obsolete(next_mem)) {
+			next_mem = mem_cgroup_get_next_node(root_mem);
+			continue;
+		}
+		ret += try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap,
+						   get_swappiness(next_mem));
+		if (mem_cgroup_check_under_limit(root_mem))
+			return 1;	/* indicate reclaim has succeeded */
+		next_mem = mem_cgroup_get_next_node(root_mem);
+	}
+	return ret;
+}
+
+bool mem_cgroup_oom_called(struct task_struct *task)
+{
+	bool ret = false;
 	struct mem_cgroup *mem;
-	struct page_cgroup *pc;
-	unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
-	struct mem_cgroup_per_zone *mz;
-	unsigned long flags;
+	struct mm_struct *mm;
 
-	pc = lookup_page_cgroup(page);
-	/* can happen at boot */
-	if (unlikely(!pc))
+	rcu_read_lock();
+	mm = task->mm;
+	if (!mm)
+		mm = &init_mm;
+	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (mem && time_before(jiffies, mem->last_oom_jiffies + HZ/10))
+		ret = true;
+	rcu_read_unlock();
+	return ret;
+}
+/*
+ * Unlike exported interface, "oom" parameter is added. if oom==true,
+ * oom-killer can be invoked.
+ */
+static int __mem_cgroup_try_charge(struct mm_struct *mm,
+			gfp_t gfp_mask, struct mem_cgroup **memcg,
+			bool oom)
+{
+	struct mem_cgroup *mem, *mem_over_limit;
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct res_counter *fail_res;
+
+	if (unlikely(test_thread_flag(TIF_MEMDIE))) {
+		/* Don't account this! */
+		*memcg = NULL;
 		return 0;
-	prefetchw(pc);
+	}
+
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
 	 * thread group leader migrates. It's possible that mm is not
 	 * set, if so charge the init_mm (happens for pagecache usage).
 	 */
-
-	if (likely(!memcg)) {
-		rcu_read_lock();
-		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
-		if (unlikely(!mem)) {
-			rcu_read_unlock();
-			return 0;
-		}
-		/*
-		 * For every charge from the cgroup, increment reference count
-		 */
-		css_get(&mem->css);
-		rcu_read_unlock();
+	mem = *memcg;
+	if (likely(!mem)) {
+		mem = try_get_mem_cgroup_from_mm(mm);
+		*memcg = mem;
 	} else {
-		mem = memcg;
-		css_get(&memcg->css);
+		css_get(&mem->css);
 	}
+	if (unlikely(!mem))
+		return 0;
+
+	VM_BUG_ON(mem_cgroup_is_obsolete(mem));
+
+	while (1) {
+		int ret;
+		bool noswap = false;
+
+		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
+		if (likely(!ret)) {
+			if (!do_swap_account)
+				break;
+			ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
+							&fail_res);
+			if (likely(!ret))
+				break;
+			/* mem+swap counter fails */
+			res_counter_uncharge(&mem->res, PAGE_SIZE);
+			noswap = true;
+			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
+									memsw);
+		} else
+			/* mem counter fails */
+			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
+									res);
 
-	while (unlikely(res_counter_charge(&mem->res, PAGE_SIZE))) {
 		if (!(gfp_mask & __GFP_WAIT))
-			goto out;
+			goto nomem;
 
-		if (try_to_free_mem_cgroup_pages(mem, gfp_mask))
+		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
+							noswap);
+		if (ret)
 			continue;
 
 		/*
@@ -525,49 +885,221 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		 * moved to swap cache or just unmapped from the cgroup.
 		 * Check the limit again to see if the reclaim reduced the
 		 * current usage of the cgroup before giving up
+		 *
 		 */
-		if (res_counter_check_under_limit(&mem->res))
+		if (mem_cgroup_check_under_limit(mem_over_limit))
 			continue;
 
 		if (!nr_retries--) {
-			mem_cgroup_out_of_memory(mem, gfp_mask);
-			goto out;
+			if (oom) {
+				mutex_lock(&memcg_tasklist);
+				mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
+				mutex_unlock(&memcg_tasklist);
+				mem_over_limit->last_oom_jiffies = jiffies;
+			}
+			goto nomem;
 		}
 	}
+	return 0;
+nomem:
+	css_put(&mem->css);
+	return -ENOMEM;
+}
+
+static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
+{
+	struct mem_cgroup *mem;
+	swp_entry_t ent;
+
+	if (!PageSwapCache(page))
+		return NULL;
 
+	ent.val = page_private(page);
+	mem = lookup_swap_cgroup(ent);
+	if (!mem)
+		return NULL;
+	if (!css_tryget(&mem->css))
+		return NULL;
+	return mem;
+}
+
+/*
+ * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be
+ * USED state. If already USED, uncharge and return.
+ */
+
+static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
+				     struct page_cgroup *pc,
+				     enum charge_type ctype)
+{
+	/* try_charge() can return NULL to *memcg, taking care of it. */
+	if (!mem)
+		return;
 
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
 		unlock_page_cgroup(pc);
 		res_counter_uncharge(&mem->res, PAGE_SIZE);
+		if (do_swap_account)
+			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
 		css_put(&mem->css);
-
-		goto done;
+		return;
 	}
 	pc->mem_cgroup = mem;
-	/*
-	 * If a page is accounted as a page cache, insert to inactive list.
-	 * If anon, insert to active list.
-	 */
+	smp_wmb();
 	pc->flags = pcg_default_flags[ctype];
 
-	mz = page_cgroup_zoneinfo(pc);
+	mem_cgroup_charge_statistics(mem, pc, true);
 
-	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_add_list(mz, pc);
-	spin_unlock_irqrestore(&mz->lru_lock, flags);
 	unlock_page_cgroup(pc);
+}
 
-done:
-	return 0;
+/**
+ * mem_cgroup_move_account - move account of the page
+ * @pc:	page_cgroup of the page.
+ * @from: mem_cgroup which the page is moved from.
+ * @to:	mem_cgroup which the page is moved to. @from != @to.
+ *
+ * The caller must confirm following.
+ * - page is not on LRU (isolate_page() is useful.)
+ *
+ * returns 0 at success,
+ * returns -EBUSY when lock is busy or "pc" is unstable.
+ *
+ * This function does "uncharge" from old cgroup but doesn't do "charge" to
+ * new cgroup. It should be done by a caller.
+ */
+
+static int mem_cgroup_move_account(struct page_cgroup *pc,
+	struct mem_cgroup *from, struct mem_cgroup *to)
+{
+	struct mem_cgroup_per_zone *from_mz, *to_mz;
+	int nid, zid;
+	int ret = -EBUSY;
+
+	VM_BUG_ON(from == to);
+	VM_BUG_ON(PageLRU(pc->page));
+
+	nid = page_cgroup_nid(pc);
+	zid = page_cgroup_zid(pc);
+	from_mz =  mem_cgroup_zoneinfo(from, nid, zid);
+	to_mz =  mem_cgroup_zoneinfo(to, nid, zid);
+
+	if (!trylock_page_cgroup(pc))
+		return ret;
+
+	if (!PageCgroupUsed(pc))
+		goto out;
+
+	if (pc->mem_cgroup != from)
+		goto out;
+
+	res_counter_uncharge(&from->res, PAGE_SIZE);
+	mem_cgroup_charge_statistics(from, pc, false);
+	if (do_swap_account)
+		res_counter_uncharge(&from->memsw, PAGE_SIZE);
+	css_put(&from->css);
+
+	css_get(&to->css);
+	pc->mem_cgroup = to;
+	mem_cgroup_charge_statistics(to, pc, true);
+	ret = 0;
 out:
-	css_put(&mem->css);
-	return -ENOMEM;
+	unlock_page_cgroup(pc);
+	return ret;
+}
+
+/*
+ * move charges to its parent.
+ */
+
+static int mem_cgroup_move_parent(struct page_cgroup *pc,
+				  struct mem_cgroup *child,
+				  gfp_t gfp_mask)
+{
+	struct page *page = pc->page;
+	struct cgroup *cg = child->css.cgroup;
+	struct cgroup *pcg = cg->parent;
+	struct mem_cgroup *parent;
+	int ret;
+
+	/* Is ROOT ? */
+	if (!pcg)
+		return -EINVAL;
+
+
+	parent = mem_cgroup_from_cont(pcg);
+
+
+	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
+	if (ret || !parent)
+		return ret;
+
+	if (!get_page_unless_zero(page)) {
+		ret = -EBUSY;
+		goto uncharge;
+	}
+
+	ret = isolate_lru_page(page);
+
+	if (ret)
+		goto cancel;
+
+	ret = mem_cgroup_move_account(pc, child, parent);
+
+	putback_lru_page(page);
+	if (!ret) {
+		put_page(page);
+		/* drop extra refcnt by try_charge() */
+		css_put(&parent->css);
+		return 0;
+	}
+
+cancel:
+	put_page(page);
+uncharge:
+	/* drop extra refcnt by try_charge() */
+	css_put(&parent->css);
+	/* uncharge if move fails */
+	res_counter_uncharge(&parent->res, PAGE_SIZE);
+	if (do_swap_account)
+		res_counter_uncharge(&parent->memsw, PAGE_SIZE);
+	return ret;
+}
+
+/*
+ * Charge the memory controller for page usage.
+ * Return
+ * 0 if the charge was successful
+ * < 0 if the cgroup is over its limit
+ */
+static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
+				gfp_t gfp_mask, enum charge_type ctype,
+				struct mem_cgroup *memcg)
+{
+	struct mem_cgroup *mem;
+	struct page_cgroup *pc;
+	int ret;
+
+	pc = lookup_page_cgroup(page);
+	/* can happen at boot */
+	if (unlikely(!pc))
+		return 0;
+	prefetchw(pc);
+
+	mem = memcg;
+	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
+	if (ret || !mem)
+		return ret;
+
+	__mem_cgroup_commit_charge(mem, pc, ctype);
+	return 0;
 }
 
-int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
+int mem_cgroup_newpage_charge(struct page *page,
+			      struct mm_struct *mm, gfp_t gfp_mask)
 {
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return 0;
 	if (PageCompound(page))
 		return 0;
@@ -589,7 +1121,10 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
-	if (mem_cgroup_subsys.disabled)
+	struct mem_cgroup *mem = NULL;
+	int ret;
+
+	if (mem_cgroup_disabled())
 		return 0;
 	if (PageCompound(page))
 		return 0;
@@ -601,6 +1136,8 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 	 * For GFP_NOWAIT case, the page may be pre-charged before calling
 	 * add_to_page_cache(). (See shmem.c) check it here and avoid to call
 	 * charge twice. (It works but has to pay a bit larger cost.)
+	 * And when the page is SwapCache, it should take swap information
+	 * into account. This is under lock_page() now.
 	 */
 	if (!(gfp_mask & __GFP_WAIT)) {
 		struct page_cgroup *pc;
@@ -617,58 +1154,198 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		unlock_page_cgroup(pc);
 	}
 
-	if (unlikely(!mm))
+	if (do_swap_account && PageSwapCache(page)) {
+		mem = try_get_mem_cgroup_from_swapcache(page);
+		if (mem)
+			mm = NULL;
+		  else
+			mem = NULL;
+		/* SwapCache may be still linked to LRU now. */
+		mem_cgroup_lru_del_before_commit_swapcache(page);
+	}
+
+	if (unlikely(!mm && !mem))
 		mm = &init_mm;
 
 	if (page_is_file_cache(page))
 		return mem_cgroup_charge_common(page, mm, gfp_mask,
 				MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
-	else
-		return mem_cgroup_charge_common(page, mm, gfp_mask,
-				MEM_CGROUP_CHARGE_TYPE_SHMEM, NULL);
+
+	ret = mem_cgroup_charge_common(page, mm, gfp_mask,
+				MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
+	if (mem)
+		css_put(&mem->css);
+	if (PageSwapCache(page))
+		mem_cgroup_lru_add_after_commit_swapcache(page);
+
+	if (do_swap_account && !ret && PageSwapCache(page)) {
+		swp_entry_t ent = {.val = page_private(page)};
+		/* avoid double counting */
+		mem = swap_cgroup_record(ent, NULL);
+		if (mem) {
+			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+			mem_cgroup_put(mem);
+		}
+	}
+	return ret;
+}
+
+/*
+ * While swap-in, try_charge -> commit or cancel, the page is locked.
+ * And when try_charge() successfully returns, one refcnt to memcg without
+ * struct page_cgroup is aquired. This refcnt will be cumsumed by
+ * "commit()" or removed by "cancel()"
+ */
+int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
+				 struct page *page,
+				 gfp_t mask, struct mem_cgroup **ptr)
+{
+	struct mem_cgroup *mem;
+	int ret;
+
+	if (mem_cgroup_disabled())
+		return 0;
+
+	if (!do_swap_account)
+		goto charge_cur_mm;
+	/*
+	 * A racing thread's fault, or swapoff, may have already updated
+	 * the pte, and even removed page from swap cache: return success
+	 * to go on to do_swap_page()'s pte_same() test, which should fail.
+	 */
+	if (!PageSwapCache(page))
+		return 0;
+	mem = try_get_mem_cgroup_from_swapcache(page);
+	if (!mem)
+		goto charge_cur_mm;
+	*ptr = mem;
+	ret = __mem_cgroup_try_charge(NULL, mask, ptr, true);
+	/* drop extra refcnt from tryget */
+	css_put(&mem->css);
+	return ret;
+charge_cur_mm:
+	if (unlikely(!mm))
+		mm = &init_mm;
+	return __mem_cgroup_try_charge(mm, mask, ptr, true);
+}
+
+void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+{
+	struct page_cgroup *pc;
+
+	if (mem_cgroup_disabled())
+		return;
+	if (!ptr)
+		return;
+	pc = lookup_page_cgroup(page);
+	mem_cgroup_lru_del_before_commit_swapcache(page);
+	__mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+	mem_cgroup_lru_add_after_commit_swapcache(page);
+	/*
+	 * Now swap is on-memory. This means this page may be
+	 * counted both as mem and swap....double count.
+	 * Fix it by uncharging from memsw. Basically, this SwapCache is stable
+	 * under lock_page(). But in do_swap_page()::memory.c, reuse_swap_page()
+	 * may call delete_from_swap_cache() before reach here.
+	 */
+	if (do_swap_account && PageSwapCache(page)) {
+		swp_entry_t ent = {.val = page_private(page)};
+		struct mem_cgroup *memcg;
+		memcg = swap_cgroup_record(ent, NULL);
+		if (memcg) {
+			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+			mem_cgroup_put(memcg);
+		}
+
+	}
+	/* add this page(page_cgroup) to the LRU we want. */
+
+}
+
+void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
+{
+	if (mem_cgroup_disabled())
+		return;
+	if (!mem)
+		return;
+	res_counter_uncharge(&mem->res, PAGE_SIZE);
+	if (do_swap_account)
+		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+	css_put(&mem->css);
 }
 
+
 /*
  * uncharge if !page_mapped(page)
  */
-static void
+static struct mem_cgroup *
 __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 {
 	struct page_cgroup *pc;
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem = NULL;
 	struct mem_cgroup_per_zone *mz;
-	unsigned long flags;
 
-	if (mem_cgroup_subsys.disabled)
-		return;
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	if (PageSwapCache(page))
+		return NULL;
 
 	/*
 	 * Check if our page_cgroup is valid
 	 */
 	pc = lookup_page_cgroup(page);
 	if (unlikely(!pc || !PageCgroupUsed(pc)))
-		return;
+		return NULL;
 
 	lock_page_cgroup(pc);
-	if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED && page_mapped(page))
-	     || !PageCgroupUsed(pc)) {
-		/* This happens at race in zap_pte_range() and do_swap_page()*/
-		unlock_page_cgroup(pc);
-		return;
+
+	mem = pc->mem_cgroup;
+
+	if (!PageCgroupUsed(pc))
+		goto unlock_out;
+
+	switch (ctype) {
+	case MEM_CGROUP_CHARGE_TYPE_MAPPED:
+		if (page_mapped(page))
+			goto unlock_out;
+		break;
+	case MEM_CGROUP_CHARGE_TYPE_SWAPOUT:
+		if (!PageAnon(page)) {	/* Shared memory */
+			if (page->mapping && !page_is_file_cache(page))
+				goto unlock_out;
+		} else if (page_mapped(page)) /* Anon */
+				goto unlock_out;
+		break;
+	default:
+		break;
 	}
+
+	res_counter_uncharge(&mem->res, PAGE_SIZE);
+	if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
+		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+
+	mem_cgroup_charge_statistics(mem, pc, false);
 	ClearPageCgroupUsed(pc);
-	mem = pc->mem_cgroup;
+	/*
+	 * pc->mem_cgroup is not cleared here. It will be accessed when it's
+	 * freed from LRU. This is safe because uncharged page is expected not
+	 * to be reused (freed soon). Exception is SwapCache, it's handled by
+	 * special functions.
+	 */
 
 	mz = page_cgroup_zoneinfo(pc);
-	spin_lock_irqsave(&mz->lru_lock, flags);
-	__mem_cgroup_remove_list(mz, pc);
-	spin_unlock_irqrestore(&mz->lru_lock, flags);
 	unlock_page_cgroup(pc);
 
-	res_counter_uncharge(&mem->res, PAGE_SIZE);
-	css_put(&mem->css);
+	/* at swapout, this memcg will be accessed to record to swap */
+	if (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT)
+		css_put(&mem->css);
 
-	return;
+	return mem;
+
+unlock_out:
+	unlock_page_cgroup(pc);
+	return NULL;
 }
 
 void mem_cgroup_uncharge_page(struct page *page)
@@ -689,16 +1366,55 @@ void mem_cgroup_uncharge_cache_page(struct page *page)
 }
 
 /*
- * Before starting migration, account against new page.
+ * called from __delete_from_swap_cache() and drop "page" account.
+ * memcg information is recorded to swap_cgroup of "ent"
  */
-int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
+void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
+{
+	struct mem_cgroup *memcg;
+
+	memcg = __mem_cgroup_uncharge_common(page,
+					MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
+	/* record memcg information */
+	if (do_swap_account && memcg) {
+		swap_cgroup_record(ent, memcg);
+		mem_cgroup_get(memcg);
+	}
+	if (memcg)
+		css_put(&memcg->css);
+}
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+/*
+ * called from swap_entry_free(). remove record in swap_cgroup and
+ * uncharge "memsw" account.
+ */
+void mem_cgroup_uncharge_swap(swp_entry_t ent)
+{
+	struct mem_cgroup *memcg;
+
+	if (!do_swap_account)
+		return;
+
+	memcg = swap_cgroup_record(ent, NULL);
+	if (memcg) {
+		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
+		mem_cgroup_put(memcg);
+	}
+}
+#endif
+
+/*
+ * Before starting migration, account PAGE_SIZE to mem_cgroup that the old
+ * page belongs to.
+ */
+int mem_cgroup_prepare_migration(struct page *page, struct mem_cgroup **ptr)
 {
 	struct page_cgroup *pc;
 	struct mem_cgroup *mem = NULL;
-	enum charge_type ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
 	int ret = 0;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return 0;
 
 	pc = lookup_page_cgroup(page);
@@ -706,41 +1422,67 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 	if (PageCgroupUsed(pc)) {
 		mem = pc->mem_cgroup;
 		css_get(&mem->css);
-		if (PageCgroupCache(pc)) {
-			if (page_is_file_cache(page))
-				ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
-			else
-				ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-		}
 	}
 	unlock_page_cgroup(pc);
+
 	if (mem) {
-		ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
-			ctype, mem);
+		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
 		css_put(&mem->css);
 	}
+	*ptr = mem;
 	return ret;
 }
 
 /* remove redundant charge if migration failed*/
-void mem_cgroup_end_migration(struct page *newpage)
+void mem_cgroup_end_migration(struct mem_cgroup *mem,
+		struct page *oldpage, struct page *newpage)
 {
+	struct page *target, *unused;
+	struct page_cgroup *pc;
+	enum charge_type ctype;
+
+	if (!mem)
+		return;
+
+	/* at migration success, oldpage->mapping is NULL. */
+	if (oldpage->mapping) {
+		target = oldpage;
+		unused = NULL;
+	} else {
+		target = newpage;
+		unused = oldpage;
+	}
+
+	if (PageAnon(target))
+		ctype = MEM_CGROUP_CHARGE_TYPE_MAPPED;
+	else if (page_is_file_cache(target))
+		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+	else
+		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+
+	/* unused page is not on radix-tree now. */
+	if (unused)
+		__mem_cgroup_uncharge_common(unused, ctype);
+
+	pc = lookup_page_cgroup(target);
 	/*
-	 * At success, page->mapping is not NULL.
-	 * special rollback care is necessary when
-	 * 1. at migration failure. (newpage->mapping is cleared in this case)
-	 * 2. the newpage was moved but not remapped again because the task
-	 *    exits and the newpage is obsolete. In this case, the new page
-	 *    may be a swapcache. So, we just call mem_cgroup_uncharge_page()
-	 *    always for avoiding mess. The  page_cgroup will be removed if
-	 *    unnecessary. File cache pages is still on radix-tree. Don't
-	 *    care it.
+	 * __mem_cgroup_commit_charge() check PCG_USED bit of page_cgroup.
+	 * So, double-counting is effectively avoided.
 	 */
-	if (!newpage->mapping)
-		__mem_cgroup_uncharge_common(newpage,
-				MEM_CGROUP_CHARGE_TYPE_FORCE);
-	else if (PageAnon(newpage))
-		mem_cgroup_uncharge_page(newpage);
+	__mem_cgroup_commit_charge(mem, pc, ctype);
+
+	/*
+	 * Both of oldpage and newpage are still under lock_page().
+	 * Then, we don't have to care about race in radix-tree.
+	 * But we have to be careful that this page is unmapped or not.
+	 *
+	 * There is a case for !page_mapped(). At the start of
+	 * migration, oldpage was mapped. But now, it's zapped.
+	 * But we know *target* page is not freed/reused under us.
+	 * mem_cgroup_uncharge_page() does all necessary checks.
+	 */
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
+		mem_cgroup_uncharge_page(target);
 }
 
 /*
@@ -748,29 +1490,26 @@ void mem_cgroup_end_migration(struct page *newpage)
  * This is typically used for page reclaiming for shmem for reducing side
  * effect of page allocation from shmem, which is used by some mem_cgroup.
  */
-int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
+int mem_cgroup_shrink_usage(struct page *page,
+			    struct mm_struct *mm,
+			    gfp_t gfp_mask)
 {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem = NULL;
 	int progress = 0;
 	int retry = MEM_CGROUP_RECLAIM_RETRIES;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return 0;
-	if (!mm)
+	if (page)
+		mem = try_get_mem_cgroup_from_swapcache(page);
+	if (!mem && mm)
+		mem = try_get_mem_cgroup_from_mm(mm);
+	if (unlikely(!mem))
 		return 0;
 
-	rcu_read_lock();
-	mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	if (unlikely(!mem)) {
-		rcu_read_unlock();
-		return 0;
-	}
-	css_get(&mem->css);
-	rcu_read_unlock();
-
 	do {
-		progress = try_to_free_mem_cgroup_pages(mem, gfp_mask);
-		progress += res_counter_check_under_limit(&mem->res);
+		progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
+		progress += mem_cgroup_check_under_limit(mem);
 	} while (!progress && --retry);
 
 	css_put(&mem->css);
@@ -779,116 +1518,295 @@ int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask)
 	return 0;
 }
 
-int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
+static DEFINE_MUTEX(set_limit_mutex);
+
+static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
+				unsigned long long val)
 {
 
 	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
 	int progress;
+	u64 memswlimit;
 	int ret = 0;
 
-	while (res_counter_set_limit(&memcg->res, val)) {
+	while (retry_count) {
 		if (signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
-		if (!retry_count) {
-			ret = -EBUSY;
+		/*
+		 * Rather than hide all in some function, I do this in
+		 * open coded manner. You see what this really does.
+		 * We have to guarantee mem->res.limit < mem->memsw.limit.
+		 */
+		mutex_lock(&set_limit_mutex);
+		memswlimit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+		if (memswlimit < val) {
+			ret = -EINVAL;
+			mutex_unlock(&set_limit_mutex);
 			break;
 		}
-		progress = try_to_free_mem_cgroup_pages(memcg, GFP_KERNEL);
-		if (!progress)
-			retry_count--;
+		ret = res_counter_set_limit(&memcg->res, val);
+		mutex_unlock(&set_limit_mutex);
+
+		if (!ret)
+			break;
+
+		progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
+							   false);
+  		if (!progress)			retry_count--;
 	}
+
 	return ret;
 }
 
+int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
+				unsigned long long val)
+{
+	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	u64 memlimit, oldusage, curusage;
+	int ret;
+
+	if (!do_swap_account)
+		return -EINVAL;
+
+	while (retry_count) {
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+		/*
+		 * Rather than hide all in some function, I do this in
+		 * open coded manner. You see what this really does.
+		 * We have to guarantee mem->res.limit < mem->memsw.limit.
+		 */
+		mutex_lock(&set_limit_mutex);
+		memlimit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+		if (memlimit > val) {
+			ret = -EINVAL;
+			mutex_unlock(&set_limit_mutex);
+			break;
+		}
+		ret = res_counter_set_limit(&memcg->memsw, val);
+		mutex_unlock(&set_limit_mutex);
+
+		if (!ret)
+			break;
+
+		oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true);
+		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		if (curusage >= oldusage)
+			retry_count--;
+	}
+	return ret;
+}
 
 /*
  * This routine traverse page_cgroup in given list and drop them all.
  * *And* this routine doesn't reclaim page itself, just removes page_cgroup.
  */
-#define FORCE_UNCHARGE_BATCH	(128)
-static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
-			    struct mem_cgroup_per_zone *mz,
-			    enum lru_list lru)
+static int mem_cgroup_force_empty_list(struct mem_cgroup *mem,
+				int node, int zid, enum lru_list lru)
 {
-	struct page_cgroup *pc;
-	struct page *page;
-	int count = FORCE_UNCHARGE_BATCH;
-	unsigned long flags;
+	struct zone *zone;
+	struct mem_cgroup_per_zone *mz;
+	struct page_cgroup *pc, *busy;
+	unsigned long flags, loop;
 	struct list_head *list;
+	int ret = 0;
 
+	zone = &NODE_DATA(node)->node_zones[zid];
+	mz = mem_cgroup_zoneinfo(mem, node, zid);
 	list = &mz->lists[lru];
 
-	spin_lock_irqsave(&mz->lru_lock, flags);
-	while (!list_empty(list)) {
-		pc = list_entry(list->prev, struct page_cgroup, lru);
-		page = pc->page;
-		if (!PageCgroupUsed(pc))
-			break;
-		get_page(page);
-		spin_unlock_irqrestore(&mz->lru_lock, flags);
-		/*
-		 * Check if this page is on LRU. !LRU page can be found
-		 * if it's under page migration.
-		 */
-		if (PageLRU(page)) {
-			__mem_cgroup_uncharge_common(page,
-					MEM_CGROUP_CHARGE_TYPE_FORCE);
-			put_page(page);
-			if (--count <= 0) {
-				count = FORCE_UNCHARGE_BATCH;
-				cond_resched();
-			}
-		} else {
-			spin_lock_irqsave(&mz->lru_lock, flags);
+	loop = MEM_CGROUP_ZSTAT(mz, lru);
+	/* give some margin against EBUSY etc...*/
+	loop += 256;
+	busy = NULL;
+	while (loop--) {
+		ret = 0;
+		spin_lock_irqsave(&zone->lru_lock, flags);
+		if (list_empty(list)) {
+			spin_unlock_irqrestore(&zone->lru_lock, flags);
 			break;
 		}
-		spin_lock_irqsave(&mz->lru_lock, flags);
+		pc = list_entry(list->prev, struct page_cgroup, lru);
+		if (busy == pc) {
+			list_move(&pc->lru, list);
+			busy = 0;
+			spin_unlock_irqrestore(&zone->lru_lock, flags);
+			continue;
+		}
+		spin_unlock_irqrestore(&zone->lru_lock, flags);
+
+		ret = mem_cgroup_move_parent(pc, mem, GFP_KERNEL);
+		if (ret == -ENOMEM)
+			break;
+
+		if (ret == -EBUSY || ret == -EINVAL) {
+			/* found lock contention or "pc" is obsolete. */
+			busy = pc;
+			cond_resched();
+		} else
+			busy = NULL;
 	}
-	spin_unlock_irqrestore(&mz->lru_lock, flags);
+
+	if (!ret && !list_empty(list))
+		return -EBUSY;
+	return ret;
 }
 
 /*
  * make mem_cgroup's charge to be 0 if there is no task.
  * This enables deleting this mem_cgroup.
  */
-static int mem_cgroup_force_empty(struct mem_cgroup *mem)
+static int mem_cgroup_force_empty(struct mem_cgroup *mem, bool free_all)
 {
-	int ret = -EBUSY;
-	int node, zid;
+	int ret;
+	int node, zid, shrink;
+	int nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
+	struct cgroup *cgrp = mem->css.cgroup;
 
 	css_get(&mem->css);
-	/*
-	 * page reclaim code (kswapd etc..) will move pages between
-	 * active_list <-> inactive_list while we don't take a lock.
-	 * So, we have to do loop here until all lists are empty.
-	 */
+
+	shrink = 0;
+	/* should free all ? */
+	if (free_all)
+		goto try_to_free;
+move_account:
 	while (mem->res.usage > 0) {
-		if (atomic_read(&mem->css.cgroup->count) > 0)
+		ret = -EBUSY;
+		if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children))
+			goto out;
+		ret = -EINTR;
+		if (signal_pending(current))
 			goto out;
 		/* This is for making all *used* pages to be on LRU. */
 		lru_add_drain_all();
-		for_each_node_state(node, N_POSSIBLE)
-			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
-				struct mem_cgroup_per_zone *mz;
+		ret = 0;
+		for_each_node_state(node, N_HIGH_MEMORY) {
+			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
 				enum lru_list l;
-				mz = mem_cgroup_zoneinfo(mem, node, zid);
-				for_each_lru(l)
-					mem_cgroup_force_empty_list(mem, mz, l);
+				for_each_lru(l) {
+					ret = mem_cgroup_force_empty_list(mem,
+							node, zid, l);
+					if (ret)
+						break;
+				}
 			}
+			if (ret)
+				break;
+		}
+		/* it seems parent cgroup doesn't have enough mem */
+		if (ret == -ENOMEM)
+			goto try_to_free;
 		cond_resched();
 	}
 	ret = 0;
 out:
 	css_put(&mem->css);
 	return ret;
+
+try_to_free:
+	/* returns EBUSY if there is a task or if we come here twice. */
+	if (cgroup_task_count(cgrp) || !list_empty(&cgrp->children) || shrink) {
+		ret = -EBUSY;
+		goto out;
+	}
+	/* we call try-to-free pages for make this cgroup empty */
+	lru_add_drain_all();
+	/* try to free all pages in this cgroup */
+	shrink = 1;
+	while (nr_retries && mem->res.usage > 0) {
+		int progress;
+
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			goto out;
+		}
+		progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
+						false, get_swappiness(mem));
+		if (!progress) {
+			nr_retries--;
+			/* maybe some writeback is necessary */
+			congestion_wait(WRITE, HZ/10);
+		}
+
+	}
+	lru_add_drain();
+	/* try move_account...there may be some *locked* pages. */
+	if (mem->res.usage)
+		goto move_account;
+	ret = 0;
+	goto out;
+}
+
+int mem_cgroup_force_empty_write(struct cgroup *cont, unsigned int event)
+{
+	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont), true);
+}
+
+
+static u64 mem_cgroup_hierarchy_read(struct cgroup *cont, struct cftype *cft)
+{
+	return mem_cgroup_from_cont(cont)->use_hierarchy;
+}
+
+static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
+					u64 val)
+{
+	int retval = 0;
+	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+	struct cgroup *parent = cont->parent;
+	struct mem_cgroup *parent_mem = NULL;
+
+	if (parent)
+		parent_mem = mem_cgroup_from_cont(parent);
+
+	cgroup_lock();
+	/*
+	 * If parent's use_hiearchy is set, we can't make any modifications
+	 * in the child subtrees. If it is unset, then the change can
+	 * occur, provided the current cgroup has no children.
+	 *
+	 * For the root cgroup, parent_mem is NULL, we allow value to be
+	 * set if there are no children.
+	 */
+	if ((!parent_mem || !parent_mem->use_hierarchy) &&
+				(val == 1 || val == 0)) {
+		if (list_empty(&cont->children))
+			mem->use_hierarchy = val;
+		else
+			retval = -EBUSY;
+	} else
+		retval = -EINVAL;
+	cgroup_unlock();
+
+	return retval;
 }
 
 static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
 {
-	return res_counter_read_u64(&mem_cgroup_from_cont(cont)->res,
-				    cft->private);
+	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+	u64 val = 0;
+	int type, name;
+
+	type = MEMFILE_TYPE(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+	switch (type) {
+	case _MEM:
+		val = res_counter_read_u64(&mem->res, name);
+		break;
+	case _MEMSWAP:
+		if (do_swap_account)
+			val = res_counter_read_u64(&mem->memsw, name);
+		break;
+	default:
+		BUG();
+		break;
+	}
+	return val;
 }
 /*
  * The user of this function is...
@@ -898,15 +1816,22 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 			    const char *buffer)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+	int type, name;
 	unsigned long long val;
 	int ret;
 
-	switch (cft->private) {
+	type = MEMFILE_TYPE(cft->private);
+	name = MEMFILE_ATTR(cft->private);
+	switch (name) {
 	case RES_LIMIT:
 		/* This function does all necessary parse...reuse it */
 		ret = res_counter_memparse_write_strategy(buffer, &val);
-		if (!ret)
+		if (ret)
+			break;
+		if (type == _MEM)
 			ret = mem_cgroup_resize_limit(memcg, val);
+		else
+			ret = mem_cgroup_resize_memsw_limit(memcg, val);
 		break;
 	default:
 		ret = -EINVAL; /* should be BUG() ? */
@@ -915,27 +1840,59 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
 	return ret;
 }
 
+static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg,
+		unsigned long long *mem_limit, unsigned long long *memsw_limit)
+{
+	struct cgroup *cgroup;
+	unsigned long long min_limit, min_memsw_limit, tmp;
+
+	min_limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+	min_memsw_limit = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+	cgroup = memcg->css.cgroup;
+	if (!memcg->use_hierarchy)
+		goto out;
+
+	while (cgroup->parent) {
+		cgroup = cgroup->parent;
+		memcg = mem_cgroup_from_cont(cgroup);
+		if (!memcg->use_hierarchy)
+			break;
+		tmp = res_counter_read_u64(&memcg->res, RES_LIMIT);
+		min_limit = min(min_limit, tmp);
+		tmp = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
+		min_memsw_limit = min(min_memsw_limit, tmp);
+	}
+out:
+	*mem_limit = min_limit;
+	*memsw_limit = min_memsw_limit;
+	return;
+}
+
 static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 {
 	struct mem_cgroup *mem;
+	int type, name;
 
 	mem = mem_cgroup_from_cont(cont);
-	switch (event) {
+	type = MEMFILE_TYPE(event);
+	name = MEMFILE_ATTR(event);
+	switch (name) {
 	case RES_MAX_USAGE:
-		res_counter_reset_max(&mem->res);
+		if (type == _MEM)
+			res_counter_reset_max(&mem->res);
+		else
+			res_counter_reset_max(&mem->memsw);
 		break;
 	case RES_FAILCNT:
-		res_counter_reset_failcnt(&mem->res);
+		if (type == _MEM)
+			res_counter_reset_failcnt(&mem->res);
+		else
+			res_counter_reset_failcnt(&mem->memsw);
 		break;
 	}
 	return 0;
 }
 
-static int mem_force_empty_write(struct cgroup *cont, unsigned int event)
-{
-	return mem_cgroup_force_empty(mem_cgroup_from_cont(cont));
-}
-
 static const struct mem_cgroup_stat_desc {
 	const char *msg;
 	u64 unit;
@@ -984,42 +1941,170 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 		cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);
 
 	}
+	{
+		unsigned long long limit, memsw_limit;
+		memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
+		cb->fill(cb, "hierarchical_memory_limit", limit);
+		if (do_swap_account)
+			cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
+	}
+
+#ifdef CONFIG_DEBUG_VM
+	cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
+
+	{
+		int nid, zid;
+		struct mem_cgroup_per_zone *mz;
+		unsigned long recent_rotated[2] = {0, 0};
+		unsigned long recent_scanned[2] = {0, 0};
+
+		for_each_online_node(nid)
+			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
+				mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
+
+				recent_rotated[0] +=
+					mz->reclaim_stat.recent_rotated[0];
+				recent_rotated[1] +=
+					mz->reclaim_stat.recent_rotated[1];
+				recent_scanned[0] +=
+					mz->reclaim_stat.recent_scanned[0];
+				recent_scanned[1] +=
+					mz->reclaim_stat.recent_scanned[1];
+			}
+		cb->fill(cb, "recent_rotated_anon", recent_rotated[0]);
+		cb->fill(cb, "recent_rotated_file", recent_rotated[1]);
+		cb->fill(cb, "recent_scanned_anon", recent_scanned[0]);
+		cb->fill(cb, "recent_scanned_file", recent_scanned[1]);
+	}
+#endif
+
 	return 0;
 }
 
+static u64 mem_cgroup_swappiness_read(struct cgroup *cgrp, struct cftype *cft)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+
+	return get_swappiness(memcg);
+}
+
+static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
+				       u64 val)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+	struct mem_cgroup *parent;
+
+	if (val > 100)
+		return -EINVAL;
+
+	if (cgrp->parent == NULL)
+		return -EINVAL;
+
+	parent = mem_cgroup_from_cont(cgrp->parent);
+
+	cgroup_lock();
+
+	/* If under hierarchy, only empty-root can set this value */
+	if ((parent->use_hierarchy) ||
+	    (memcg->use_hierarchy && !list_empty(&cgrp->children))) {
+		cgroup_unlock();
+		return -EINVAL;
+	}
+
+	spin_lock(&memcg->reclaim_param_lock);
+	memcg->swappiness = val;
+	spin_unlock(&memcg->reclaim_param_lock);
+
+	cgroup_unlock();
+
+	return 0;
+}
+
+
 static struct cftype mem_cgroup_files[] = {
 	{
 		.name = "usage_in_bytes",
-		.private = RES_USAGE,
+		.private = MEMFILE_PRIVATE(_MEM, RES_USAGE),
 		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "max_usage_in_bytes",
-		.private = RES_MAX_USAGE,
+		.private = MEMFILE_PRIVATE(_MEM, RES_MAX_USAGE),
 		.trigger = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "limit_in_bytes",
-		.private = RES_LIMIT,
+		.private = MEMFILE_PRIVATE(_MEM, RES_LIMIT),
 		.write_string = mem_cgroup_write,
 		.read_u64 = mem_cgroup_read,
 	},
 	{
 		.name = "failcnt",
-		.private = RES_FAILCNT,
+		.private = MEMFILE_PRIVATE(_MEM, RES_FAILCNT),
 		.trigger = mem_cgroup_reset,
 		.read_u64 = mem_cgroup_read,
 	},
 	{
+		.name = "stat",
+		.read_map = mem_control_stat_show,
+	},
+	{
 		.name = "force_empty",
-		.trigger = mem_force_empty_write,
+		.trigger = mem_cgroup_force_empty_write,
 	},
 	{
-		.name = "stat",
-		.read_map = mem_control_stat_show,
+		.name = "use_hierarchy",
+		.write_u64 = mem_cgroup_hierarchy_write,
+		.read_u64 = mem_cgroup_hierarchy_read,
 	},
+	{
+		.name = "swappiness",
+		.read_u64 = mem_cgroup_swappiness_read,
+		.write_u64 = mem_cgroup_swappiness_write,
+	},
+};
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static struct cftype memsw_cgroup_files[] = {
+	{
+		.name = "memsw.usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE),
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.max_usage_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE),
+		.trigger = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.limit_in_bytes",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT),
+		.write_string = mem_cgroup_write,
+		.read_u64 = mem_cgroup_read,
+	},
+	{
+		.name = "memsw.failcnt",
+		.private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT),
+		.trigger = mem_cgroup_reset,
+		.read_u64 = mem_cgroup_read,
+	},
+};
+
+static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	if (!do_swap_account)
+		return 0;
+	return cgroup_add_files(cont, ss, memsw_cgroup_files,
+				ARRAY_SIZE(memsw_cgroup_files));
 };
+#else
+static int register_memsw_files(struct cgroup *cont, struct cgroup_subsys *ss)
+{
+	return 0;
+}
+#endif
 
 static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 {
@@ -1046,7 +2131,6 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
-		spin_lock_init(&mz->lru_lock);
 		for_each_lru(l)
 			INIT_LIST_HEAD(&mz->lists[l]);
 	}
@@ -1058,55 +2142,133 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 	kfree(mem->info.nodeinfo[node]);
 }
 
+static int mem_cgroup_size(void)
+{
+	int cpustat_size = nr_cpu_ids * sizeof(struct mem_cgroup_stat_cpu);
+	return sizeof(struct mem_cgroup) + cpustat_size;
+}
+
 static struct mem_cgroup *mem_cgroup_alloc(void)
 {
 	struct mem_cgroup *mem;
+	int size = mem_cgroup_size();
 
-	if (sizeof(*mem) < PAGE_SIZE)
-		mem = kmalloc(sizeof(*mem), GFP_KERNEL);
+	if (size < PAGE_SIZE)
+		mem = kmalloc(size, GFP_KERNEL);
 	else
-		mem = vmalloc(sizeof(*mem));
+		mem = vmalloc(size);
 
 	if (mem)
-		memset(mem, 0, sizeof(*mem));
+		memset(mem, 0, size);
 	return mem;
 }
 
-static void mem_cgroup_free(struct mem_cgroup *mem)
+/*
+ * At destroying mem_cgroup, references from swap_cgroup can remain.
+ * (scanning all at force_empty is too costly...)
+ *
+ * Instead of clearing all references at force_empty, we remember
+ * the number of reference from swap_cgroup and free mem_cgroup when
+ * it goes down to 0.
+ *
+ * Removal of cgroup itself succeeds regardless of refs from swap.
+ */
+
+static void __mem_cgroup_free(struct mem_cgroup *mem)
 {
-	if (sizeof(*mem) < PAGE_SIZE)
+	int node;
+
+	for_each_node_state(node, N_POSSIBLE)
+		free_mem_cgroup_per_zone_info(mem, node);
+
+	if (mem_cgroup_size() < PAGE_SIZE)
 		kfree(mem);
 	else
 		vfree(mem);
 }
 
+static void mem_cgroup_get(struct mem_cgroup *mem)
+{
+	atomic_inc(&mem->refcnt);
+}
 
-static struct cgroup_subsys_state *
+static void mem_cgroup_put(struct mem_cgroup *mem)
+{
+	if (atomic_dec_and_test(&mem->refcnt)) {
+		struct mem_cgroup *parent = parent_mem_cgroup(mem);
+		__mem_cgroup_free(mem);
+		if (parent)
+			mem_cgroup_put(parent);
+	}
+}
+
+/*
+ * Returns the parent mem_cgroup in memcgroup hierarchy with hierarchy enabled.
+ */
+static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem)
+{
+	if (!mem->res.parent)
+		return NULL;
+	return mem_cgroup_from_res_counter(mem->res.parent, res);
+}
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static void __init enable_swap_cgroup(void)
+{
+	if (!mem_cgroup_disabled() && really_do_swap_account)
+		do_swap_account = 1;
+}
+#else
+static void __init enable_swap_cgroup(void)
+{
+}
+#endif
+
+static struct cgroup_subsys_state * __ref
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
-	struct mem_cgroup *mem;
+	struct mem_cgroup *mem, *parent;
 	int node;
 
-	if (unlikely((cont->parent) == NULL)) {
-		mem = &init_mem_cgroup;
-	} else {
-		mem = mem_cgroup_alloc();
-		if (!mem)
-			return ERR_PTR(-ENOMEM);
-	}
-
-	res_counter_init(&mem->res);
+	mem = mem_cgroup_alloc();
+	if (!mem)
+		return ERR_PTR(-ENOMEM);
 
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
 			goto free_out;
+	/* root ? */
+	if (cont->parent == NULL) {
+		enable_swap_cgroup();
+		parent = NULL;
+	} else {
+		parent = mem_cgroup_from_cont(cont->parent);
+		mem->use_hierarchy = parent->use_hierarchy;
+	}
 
+	if (parent && parent->use_hierarchy) {
+		res_counter_init(&mem->res, &parent->res);
+		res_counter_init(&mem->memsw, &parent->memsw);
+		/*
+		 * We increment refcnt of the parent to ensure that we can
+		 * safely access it on res_counter_charge/uncharge.
+		 * This refcnt will be decremented when freeing this
+		 * mem_cgroup(see mem_cgroup_put).
+		 */
+		mem_cgroup_get(parent);
+	} else {
+		res_counter_init(&mem->res, NULL);
+		res_counter_init(&mem->memsw, NULL);
+	}
+	mem->last_scanned_child = NULL;
+	spin_lock_init(&mem->reclaim_param_lock);
+
+	if (parent)
+		mem->swappiness = get_swappiness(parent);
+	atomic_set(&mem->refcnt, 1);
 	return &mem->css;
 free_out:
-	for_each_node_state(node, N_POSSIBLE)
-		free_mem_cgroup_per_zone_info(mem, node);
-	if (cont->parent != NULL)
-		mem_cgroup_free(mem);
+	__mem_cgroup_free(mem);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -1114,26 +2276,33 @@ static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
 					struct cgroup *cont)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	mem_cgroup_force_empty(mem);
+	mem_cgroup_force_empty(mem, false);
 }
 
 static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
-	int node;
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
+	struct mem_cgroup *last_scanned_child = mem->last_scanned_child;
 
-	for_each_node_state(node, N_POSSIBLE)
-		free_mem_cgroup_per_zone_info(mem, node);
-
-	mem_cgroup_free(mem_cgroup_from_cont(cont));
+	if (last_scanned_child) {
+		VM_BUG_ON(!mem_cgroup_is_obsolete(last_scanned_child));
+		mem_cgroup_put(last_scanned_child);
+	}
+	mem_cgroup_put(mem);
 }
 
 static int mem_cgroup_populate(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
-	return cgroup_add_files(cont, ss, mem_cgroup_files,
-					ARRAY_SIZE(mem_cgroup_files));
+	int ret;
+
+	ret = cgroup_add_files(cont, ss, mem_cgroup_files,
+				ARRAY_SIZE(mem_cgroup_files));
+
+	if (!ret)
+		ret = register_memsw_files(cont, ss);
+	return ret;
 }
 
 static void mem_cgroup_move_task(struct cgroup_subsys *ss,
@@ -1141,25 +2310,12 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss,
 				struct cgroup *old_cont,
 				struct task_struct *p)
 {
-	struct mm_struct *mm;
-	struct mem_cgroup *mem, *old_mem;
-
-	mm = get_task_mm(p);
-	if (mm == NULL)
-		return;
-
-	mem = mem_cgroup_from_cont(cont);
-	old_mem = mem_cgroup_from_cont(old_cont);
-
+	mutex_lock(&memcg_tasklist);
 	/*
-	 * Only thread group leaders are allowed to migrate, the mm_struct is
-	 * in effect owned by the leader
+	 * FIXME: It's better to move charges of this process from old
+	 * memcg to new memcg. But it's just on TODO-List now.
 	 */
-	if (!thread_group_leader(p))
-		goto out;
-
-out:
-	mmput(mm);
+	mutex_unlock(&memcg_tasklist);
 }
 
 struct cgroup_subsys mem_cgroup_subsys = {
@@ -1172,3 +2328,13 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.attach = mem_cgroup_move_task,
 	.early_init = 0,
 };
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static int __init disable_swap_account(char *s)
+{
+	really_do_swap_account = 0;
+	return 1;
+}
+__setup("noswapaccount", disable_swap_account);
+#endif
diff --git a/mm/memory.c b/mm/memory.c
index 0a2010a9518c..baa999e87cd2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -52,6 +52,9 @@
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
+#include <linux/kallsyms.h>
+#include <linux/swapops.h>
+#include <linux/elf.h>
 
 #include <asm/pgalloc.h>
 #include <asm/uaccess.h>
@@ -59,9 +62,6 @@
 #include <asm/tlbflush.h>
 #include <asm/pgtable.h>
 
-#include <linux/swapops.h>
-#include <linux/elf.h>
-
 #include "internal.h"
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -375,15 +375,65 @@ static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss)
  *
  * The calling function must still handle the error.
  */
-static void print_bad_pte(struct vm_area_struct *vma, pte_t pte,
-			  unsigned long vaddr)
-{
-	printk(KERN_ERR "Bad pte = %08llx, process = %s, "
-			"vm_flags = %lx, vaddr = %lx\n",
-		(long long)pte_val(pte),
-		(vma->vm_mm == current->mm ? current->comm : "???"),
-		vma->vm_flags, vaddr);
+static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
+			  pte_t pte, struct page *page)
+{
+	pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
+	pud_t *pud = pud_offset(pgd, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
+	struct address_space *mapping;
+	pgoff_t index;
+	static unsigned long resume;
+	static unsigned long nr_shown;
+	static unsigned long nr_unshown;
+
+	/*
+	 * Allow a burst of 60 reports, then keep quiet for that minute;
+	 * or allow a steady drip of one report per second.
+	 */
+	if (nr_shown == 60) {
+		if (time_before(jiffies, resume)) {
+			nr_unshown++;
+			return;
+		}
+		if (nr_unshown) {
+			printk(KERN_ALERT
+				"BUG: Bad page map: %lu messages suppressed\n",
+				nr_unshown);
+			nr_unshown = 0;
+		}
+		nr_shown = 0;
+	}
+	if (nr_shown++ == 0)
+		resume = jiffies + 60 * HZ;
+
+	mapping = vma->vm_file ? vma->vm_file->f_mapping : NULL;
+	index = linear_page_index(vma, addr);
+
+	printk(KERN_ALERT
+		"BUG: Bad page map in process %s  pte:%08llx pmd:%08llx\n",
+		current->comm,
+		(long long)pte_val(pte), (long long)pmd_val(*pmd));
+	if (page) {
+		printk(KERN_ALERT
+		"page:%p flags:%p count:%d mapcount:%d mapping:%p index:%lx\n",
+		page, (void *)page->flags, page_count(page),
+		page_mapcount(page), page->mapping, page->index);
+	}
+	printk(KERN_ALERT
+		"addr:%p vm_flags:%08lx anon_vma:%p mapping:%p index:%lx\n",
+		(void *)addr, vma->vm_flags, vma->anon_vma, mapping, index);
+	/*
+	 * Choose text because data symbols depend on CONFIG_KALLSYMS_ALL=y
+	 */
+	if (vma->vm_ops)
+		print_symbol(KERN_ALERT "vma->vm_ops->fault: %s\n",
+				(unsigned long)vma->vm_ops->fault);
+	if (vma->vm_file && vma->vm_file->f_op)
+		print_symbol(KERN_ALERT "vma->vm_file->f_op->mmap: %s\n",
+				(unsigned long)vma->vm_file->f_op->mmap);
 	dump_stack();
+	add_taint(TAINT_BAD_PAGE);
 }
 
 static inline int is_cow_mapping(unsigned int flags)
@@ -441,21 +491,18 @@ static inline int is_cow_mapping(unsigned int flags)
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 				pte_t pte)
 {
-	unsigned long pfn;
+	unsigned long pfn = pte_pfn(pte);
 
 	if (HAVE_PTE_SPECIAL) {
-		if (likely(!pte_special(pte))) {
-			VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-			return pte_page(pte);
-		}
-		VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)));
+		if (likely(!pte_special(pte)))
+			goto check_pfn;
+		if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)))
+			print_bad_pte(vma, addr, pte, NULL);
 		return NULL;
 	}
 
 	/* !HAVE_PTE_SPECIAL case follows: */
 
-	pfn = pte_pfn(pte);
-
 	if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) {
 		if (vma->vm_flags & VM_MIXEDMAP) {
 			if (!pfn_valid(pfn))
@@ -471,11 +518,14 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		}
 	}
 
-	VM_BUG_ON(!pfn_valid(pfn));
+check_pfn:
+	if (unlikely(pfn > highest_memmap_pfn)) {
+		print_bad_pte(vma, addr, pte, NULL);
+		return NULL;
+	}
 
 	/*
 	 * NOTE! We still have PageReserved() pages in the page tables.
-	 *
 	 * eg. VDSO mappings can cause them to exist.
 	 */
 out:
@@ -767,11 +817,14 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 			else {
 				if (pte_dirty(ptent))
 					set_page_dirty(page);
-				if (pte_young(ptent))
-					SetPageReferenced(page);
+				if (pte_young(ptent) &&
+				    likely(!VM_SequentialReadHint(vma)))
+					mark_page_accessed(page);
 				file_rss--;
 			}
-			page_remove_rmap(page, vma);
+			page_remove_rmap(page);
+			if (unlikely(page_mapcount(page) < 0))
+				print_bad_pte(vma, addr, ptent, page);
 			tlb_remove_page(tlb, page);
 			continue;
 		}
@@ -781,8 +834,12 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb,
 		 */
 		if (unlikely(details))
 			continue;
-		if (!pte_file(ptent))
-			free_swap_and_cache(pte_to_swp_entry(ptent));
+		if (pte_file(ptent)) {
+			if (unlikely(!(vma->vm_flags & VM_NONLINEAR)))
+				print_bad_pte(vma, addr, ptent, NULL);
+		} else if
+		  (unlikely(!free_swap_and_cache(pte_to_swp_entry(ptent))))
+			print_bad_pte(vma, addr, ptent, NULL);
 		pte_clear_not_present_full(mm, addr, pte, tlb->fullmm);
 	} while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0));
 
@@ -1153,6 +1210,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	int write = !!(flags & GUP_FLAGS_WRITE);
 	int force = !!(flags & GUP_FLAGS_FORCE);
 	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
+	int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);
 
 	if (len <= 0)
 		return 0;
@@ -1231,12 +1289,15 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			struct page *page;
 
 			/*
-			 * If tsk is ooming, cut off its access to large memory
-			 * allocations. It has a pending SIGKILL, but it can't
-			 * be processed until returning to user space.
+			 * If we have a pending SIGKILL, don't keep faulting
+			 * pages and potentially allocating memory, unless
+			 * current is handling munlock--e.g., on exit. In
+			 * that case, we are not allocating memory.  Rather,
+			 * we're only unlocking already resident/mapped pages.
 			 */
-			if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE)))
-				return i ? i : -ENOMEM;
+			if (unlikely(!ignore_sigkill &&
+					fatal_signal_pending(current)))
+				return i ? i : -ERESTARTSYS;
 
 			if (write)
 				foll_flags |= FOLL_WRITE;
@@ -1263,9 +1324,15 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				 * do_wp_page has broken COW when necessary,
 				 * even if maybe_mkwrite decided not to set
 				 * pte_write. We can thus safely do subsequent
-				 * page lookups as if they were reads.
+				 * page lookups as if they were reads. But only
+				 * do so when looping for pte_write is futile:
+				 * in some cases userspace may also be wanting
+				 * to write to the gotten user page, which a
+				 * read fault here might prevent (a readonly
+				 * page might get reCOWed by userspace write).
 				 */
-				if (ret & VM_FAULT_WRITE)
+				if ((ret & VM_FAULT_WRITE) &&
+				    !(vma->vm_flags & VM_WRITE))
 					foll_flags &= ~FOLL_WRITE;
 
 				cond_resched();
@@ -1444,6 +1511,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn)
 {
 	int ret;
+	pgprot_t pgprot = vma->vm_page_prot;
 	/*
 	 * Technically, architectures with pte_special can avoid all these
 	 * restrictions (same for remap_pfn_range).  However we would like
@@ -1458,10 +1526,10 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
-	if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+	if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
 		return -EINVAL;
 
-	ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+	ret = insert_pfn(vma, addr, pfn, pgprot);
 
 	if (ret)
 		untrack_pfn_vma(vma, pfn, PAGE_SIZE);
@@ -1604,9 +1672,15 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 
 	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
-	err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
-	if (err)
+	err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size));
+	if (err) {
+		/*
+		 * To indicate that track_pfn related cleanup is not
+		 * needed from higher level routine calling unmap_vmas
+		 */
+		vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
 		return -EINVAL;
+	}
 
 	BUG_ON(addr >= end);
 	pfn -= addr >> PAGE_SHIFT;
@@ -1644,6 +1718,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 
 	BUG_ON(pmd_huge(*pmd));
 
+	arch_enter_lazy_mmu_mode();
+
 	token = pmd_pgtable(*pmd);
 
 	do {
@@ -1652,6 +1728,8 @@ static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd,
 			break;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
+	arch_leave_lazy_mmu_mode();
+
 	if (mm != &init_mm)
 		pte_unmap_unlock(pte-1, ptl);
 	return err;
@@ -1837,10 +1915,21 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * not dirty accountable.
 	 */
 	if (PageAnon(old_page)) {
-		if (trylock_page(old_page)) {
-			reuse = can_share_swap_page(old_page);
-			unlock_page(old_page);
+		if (!trylock_page(old_page)) {
+			page_cache_get(old_page);
+			pte_unmap_unlock(page_table, ptl);
+			lock_page(old_page);
+			page_table = pte_offset_map_lock(mm, pmd, address,
+							 &ptl);
+			if (!pte_same(*page_table, orig_pte)) {
+				unlock_page(old_page);
+				page_cache_release(old_page);
+				goto unlock;
+			}
+			page_cache_release(old_page);
 		}
+		reuse = reuse_swap_page(old_page);
+		unlock_page(old_page);
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
 		/*
@@ -1910,7 +1999,7 @@ gotten:
 	 * Don't let another task, with possibly unlocked vma,
 	 * keep the mlocked page.
 	 */
-	if (vma->vm_flags & VM_LOCKED) {
+	if ((vma->vm_flags & VM_LOCKED) && old_page) {
 		lock_page(old_page);	/* for LRU manipulation */
 		clear_page_mlock(old_page);
 		unlock_page(old_page);
@@ -1918,7 +2007,7 @@ gotten:
 	cow_user_page(new_page, old_page, address, vma);
 	__SetPageUptodate(new_page);
 
-	if (mem_cgroup_charge(new_page, mm, GFP_KERNEL))
+	if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
 		goto oom_free_new;
 
 	/*
@@ -1943,11 +2032,7 @@ gotten:
 		 * thread doing COW.
 		 */
 		ptep_clear_flush_notify(vma, address, page_table);
-		SetPageSwapBacked(new_page);
-		lru_cache_add_active_or_unevictable(new_page, vma);
 		page_add_new_anon_rmap(new_page, vma, address);
-
-//TODO:  is this safe?  do_anonymous_page() does it this way.
 		set_pte_at(mm, address, page_table, entry);
 		update_mmu_cache(vma, address, entry);
 		if (old_page) {
@@ -1973,7 +2058,7 @@ gotten:
 			 * mapcount is visible. So transitively, TLBs to
 			 * old page will be flushed before it can be reused.
 			 */
-			page_remove_rmap(old_page, vma);
+			page_remove_rmap(old_page);
 		}
 
 		/* Free the old page.. */
@@ -2266,7 +2351,7 @@ int vmtruncate(struct inode * inode, loff_t offset)
 		unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
 	}
 
-	if (inode->i_op && inode->i_op->truncate)
+	if (inode->i_op->truncate)
 		inode->i_op->truncate(inode);
 	return 0;
 
@@ -2286,7 +2371,7 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
 	 * a way to truncate a range of blocks (punch a hole) -
 	 * we should return failure right now.
 	 */
-	if (!inode->i_op || !inode->i_op->truncate_range)
+	if (!inode->i_op->truncate_range)
 		return -ENOSYS;
 
 	mutex_lock(&inode->i_mutex);
@@ -2314,6 +2399,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page;
 	swp_entry_t entry;
 	pte_t pte;
+	struct mem_cgroup *ptr = NULL;
 	int ret = 0;
 
 	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
@@ -2352,7 +2438,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	lock_page(page);
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 
-	if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
+	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
 		ret = VM_FAULT_OOM;
 		unlock_page(page);
 		goto out;
@@ -2370,22 +2456,35 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_nomap;
 	}
 
-	/* The page isn't present yet, go ahead with the fault. */
+	/*
+	 * The page isn't present yet, go ahead with the fault.
+	 *
+	 * Be careful about the sequence of operations here.
+	 * To get its accounting right, reuse_swap_page() must be called
+	 * while the page is counted on swap but not yet in mapcount i.e.
+	 * before page_add_anon_rmap() and swap_free(); try_to_free_swap()
+	 * must be called after the swap_free(), or it will never succeed.
+	 * Because delete_from_swap_page() may be called by reuse_swap_page(),
+	 * mem_cgroup_commit_charge_swapin() may not be able to find swp_entry
+	 * in page->private. In this case, a record in swap_cgroup  is silently
+	 * discarded at swap_free().
+	 */
 
 	inc_mm_counter(mm, anon_rss);
 	pte = mk_pte(page, vma->vm_page_prot);
-	if (write_access && can_share_swap_page(page)) {
+	if (write_access && reuse_swap_page(page)) {
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 		write_access = 0;
 	}
-
 	flush_icache_page(vma, page);
 	set_pte_at(mm, address, page_table, pte);
 	page_add_anon_rmap(page, vma, address);
+	/* It's better to call commit-charge after rmap is established */
+	mem_cgroup_commit_charge_swapin(page, ptr);
 
 	swap_free(entry);
 	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
-		remove_exclusive_swap_page(page);
+		try_to_free_swap(page);
 	unlock_page(page);
 
 	if (write_access) {
@@ -2402,7 +2501,7 @@ unlock:
 out:
 	return ret;
 out_nomap:
-	mem_cgroup_uncharge_page(page);
+	mem_cgroup_cancel_charge_swapin(ptr);
 	pte_unmap_unlock(page_table, ptl);
 	unlock_page(page);
 	page_cache_release(page);
@@ -2432,7 +2531,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto oom;
 	__SetPageUptodate(page);
 
-	if (mem_cgroup_charge(page, mm, GFP_KERNEL))
+	if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))
 		goto oom_free_page;
 
 	entry = mk_pte(page, vma->vm_page_prot);
@@ -2442,8 +2541,6 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pte_none(*page_table))
 		goto release;
 	inc_mm_counter(mm, anon_rss);
-	SetPageSwapBacked(page);
-	lru_cache_add_active_or_unevictable(page, vma);
 	page_add_new_anon_rmap(page, vma, address);
 	set_pte_at(mm, address, page_table, entry);
 
@@ -2525,7 +2622,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				ret = VM_FAULT_OOM;
 				goto out;
 			}
-			if (mem_cgroup_charge(page, mm, GFP_KERNEL)) {
+			if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
 				ret = VM_FAULT_OOM;
 				page_cache_release(page);
 				goto out;
@@ -2591,8 +2688,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		if (anon) {
 			inc_mm_counter(mm, anon_rss);
-			SetPageSwapBacked(page);
-			lru_cache_add_active_or_unevictable(page, vma);
 			page_add_new_anon_rmap(page, vma, address);
 		} else {
 			inc_mm_counter(mm, file_rss);
@@ -2602,7 +2697,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				get_page(dirty_page);
 			}
 		}
-//TODO:  is this safe?  do_anonymous_page() does it this way.
 		set_pte_at(mm, address, page_table, entry);
 
 		/* no need to invalidate: a not-present page won't be cached */
@@ -2666,12 +2760,11 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
 		return 0;
 
-	if (unlikely(!(vma->vm_flags & VM_NONLINEAR) ||
-			!(vma->vm_flags & VM_CAN_NONLINEAR))) {
+	if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
 		/*
 		 * Page table corrupted: show pte and kill process.
 		 */
-		print_bad_pte(vma, orig_pte, address);
+		print_bad_pte(vma, address, orig_pte, NULL);
 		return VM_FAULT_OOM;
 	}
 
@@ -2953,7 +3046,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 {
 	resource_size_t phys_addr;
 	unsigned long prot = 0;
-	void *maddr;
+	void __iomem *maddr;
 	int offset = addr & (PAGE_SIZE-1);
 
 	if (follow_phys(vma, addr, write, &prot, &phys_addr))
@@ -3079,6 +3172,15 @@ void print_vma_addr(char *prefix, unsigned long ip)
 #ifdef CONFIG_PROVE_LOCKING
 void might_fault(void)
 {
+	/*
+	 * Some code (nfs/sunrpc) uses socket ops on kernel memory while
+	 * holding the mmap_sem, this is safe because kernel memory doesn't
+	 * get paged out, therefore we'll never actually fault, and the
+	 * below annotations will generate false positives.
+	 */
+	if (segment_eq(get_fs(), KERNEL_DS))
+		return;
+
 	might_sleep();
 	/*
 	 * it would be nicer only to annotate paths which are not under
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b17371185468..c083cf5fd6df 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -216,7 +216,8 @@ static int __meminit __add_zone(struct zone *zone, unsigned long phys_start_pfn)
 	return 0;
 }
 
-static int __meminit __add_section(struct zone *zone, unsigned long phys_start_pfn)
+static int __meminit __add_section(int nid, struct zone *zone,
+					unsigned long phys_start_pfn)
 {
 	int nr_pages = PAGES_PER_SECTION;
 	int ret;
@@ -234,7 +235,7 @@ static int __meminit __add_section(struct zone *zone, unsigned long phys_start_p
 	if (ret < 0)
 		return ret;
 
-	return register_new_memory(__pfn_to_section(phys_start_pfn));
+	return register_new_memory(nid, __pfn_to_section(phys_start_pfn));
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
@@ -273,8 +274,8 @@ static int __remove_section(struct zone *zone, struct mem_section *ms)
  * call this function after deciding the zone to which to
  * add the new pages.
  */
-int __ref __add_pages(struct zone *zone, unsigned long phys_start_pfn,
-		 unsigned long nr_pages)
+int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn,
+			unsigned long nr_pages)
 {
 	unsigned long i;
 	int err = 0;
@@ -284,7 +285,7 @@ int __ref __add_pages(struct zone *zone, unsigned long phys_start_pfn,
 	end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1);
 
 	for (i = start_sec; i <= end_sec; i++) {
-		err = __add_section(zone, i << PFN_SECTION_SHIFT);
+		err = __add_section(nid, zone, i << PFN_SECTION_SHIFT);
 
 		/*
 		 * EEXIST is finally dealt with by ioresource collision
@@ -626,15 +627,12 @@ int scan_lru_pages(unsigned long start, unsigned long end)
 }
 
 static struct page *
-hotremove_migrate_alloc(struct page *page,
-			unsigned long private,
-			int **x)
+hotremove_migrate_alloc(struct page *page, unsigned long private, int **x)
 {
-	/* This should be improoooooved!! */
-	return alloc_page(GFP_HIGHUSER_PAGECACHE);
+	/* This should be improooooved!! */
+	return alloc_page(GFP_HIGHUSER_MOVABLE);
 }
 
-
 #define NR_OFFLINE_AT_ONCE_PAGES	(256)
 static int
 do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index e412ffa8e52e..3eb4a6fdc043 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1068,10 +1068,9 @@ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
 	return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
 }
 
-asmlinkage long sys_mbind(unsigned long start, unsigned long len,
-			unsigned long mode,
-			unsigned long __user *nmask, unsigned long maxnode,
-			unsigned flags)
+SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
+		unsigned long, mode, unsigned long __user *, nmask,
+		unsigned long, maxnode, unsigned, flags)
 {
 	nodemask_t nodes;
 	int err;
@@ -1091,8 +1090,8 @@ asmlinkage long sys_mbind(unsigned long start, unsigned long len,
 }
 
 /* Set the process memory policy */
-asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
-		unsigned long maxnode)
+SYSCALL_DEFINE3(set_mempolicy, int, mode, unsigned long __user *, nmask,
+		unsigned long, maxnode)
 {
 	int err;
 	nodemask_t nodes;
@@ -1110,9 +1109,9 @@ asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
 	return do_set_mempolicy(mode, flags, &nodes);
 }
 
-asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
-		const unsigned long __user *old_nodes,
-		const unsigned long __user *new_nodes)
+SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
+		const unsigned long __user *, old_nodes,
+		const unsigned long __user *, new_nodes)
 {
 	const struct cred *cred = current_cred(), *tcred;
 	struct mm_struct *mm;
@@ -1185,10 +1184,9 @@ out:
 
 
 /* Retrieve NUMA policy */
-asmlinkage long sys_get_mempolicy(int __user *policy,
-				unsigned long __user *nmask,
-				unsigned long maxnode,
-				unsigned long addr, unsigned long flags)
+SYSCALL_DEFINE5(get_mempolicy, int __user *, policy,
+		unsigned long __user *, nmask, unsigned long, maxnode,
+		unsigned long, addr, unsigned long, flags)
 {
 	int err;
 	int uninitialized_var(pval);
diff --git a/mm/migrate.c b/mm/migrate.c
index 21631ab8c08b..2bb4e1d63520 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -121,20 +121,6 @@ static void remove_migration_pte(struct vm_area_struct *vma,
 	if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
 		goto out;
 
-	/*
-	 * Yes, ignore the return value from a GFP_ATOMIC mem_cgroup_charge.
-	 * Failure is not an option here: we're now expected to remove every
-	 * migration pte, and will cause crashes otherwise.  Normally this
-	 * is not an issue: mem_cgroup_prepare_migration bumped up the old
-	 * page_cgroup count for safety, that's now attached to the new page,
-	 * so this charge should just be another incrementation of the count,
-	 * to keep in balance with rmap.c's mem_cgroup_uncharging.  But if
-	 * there's been a force_empty, those reference counts may no longer
-	 * be reliable, and this charge can actually fail: oh well, we don't
-	 * make the situation any worse by proceeding as if it had succeeded.
-	 */
-	mem_cgroup_charge(new, mm, GFP_ATOMIC);
-
 	get_page(new);
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (is_write_migration_entry(entry))
@@ -300,12 +286,10 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	 * Now we know that no one else is looking at the page.
 	 */
 	get_page(newpage);	/* add cache reference */
-#ifdef CONFIG_SWAP
 	if (PageSwapCache(page)) {
 		SetPageSwapCache(newpage);
 		set_page_private(newpage, page_private(page));
 	}
-#endif
 
 	radix_tree_replace_slot(pslot, newpage);
 
@@ -373,18 +357,13 @@ static void migrate_page_copy(struct page *newpage, struct page *page)
 
 	mlock_migrate_page(newpage, page);
 
-#ifdef CONFIG_SWAP
 	ClearPageSwapCache(page);
-#endif
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
 	/* page->mapping contains a flag for PageAnon() */
 	anon = PageAnon(page);
 	page->mapping = NULL;
 
-	if (!anon) /* This page was removed from radix-tree. */
-		mem_cgroup_uncharge_cache_page(page);
-
 	/*
 	 * If any waiters have accumulated on the new page then
 	 * wake them up.
@@ -618,6 +597,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	struct page *newpage = get_new_page(page, private, &result);
 	int rcu_locked = 0;
 	int charge = 0;
+	struct mem_cgroup *mem;
 
 	if (!newpage)
 		return -ENOMEM;
@@ -627,24 +607,26 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 		goto move_newpage;
 	}
 
-	charge = mem_cgroup_prepare_migration(page, newpage);
-	if (charge == -ENOMEM) {
-		rc = -ENOMEM;
-		goto move_newpage;
-	}
 	/* prepare cgroup just returns 0 or -ENOMEM */
-	BUG_ON(charge);
-
 	rc = -EAGAIN;
+
 	if (!trylock_page(page)) {
 		if (!force)
 			goto move_newpage;
 		lock_page(page);
 	}
 
+	/* charge against new page */
+	charge = mem_cgroup_prepare_migration(page, &mem);
+	if (charge == -ENOMEM) {
+		rc = -ENOMEM;
+		goto unlock;
+	}
+	BUG_ON(charge);
+
 	if (PageWriteback(page)) {
 		if (!force)
-			goto unlock;
+			goto uncharge;
 		wait_on_page_writeback(page);
 	}
 	/*
@@ -697,7 +679,9 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 rcu_unlock:
 	if (rcu_locked)
 		rcu_read_unlock();
-
+uncharge:
+	if (!charge)
+		mem_cgroup_end_migration(mem, page, newpage);
 unlock:
 	unlock_page(page);
 
@@ -713,8 +697,6 @@ unlock:
 	}
 
 move_newpage:
-	if (!charge)
-		mem_cgroup_end_migration(newpage);
 
 	/*
 	 * Move the new page to the LRU. If migration was not successful
@@ -848,12 +830,6 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 		struct vm_area_struct *vma;
 		struct page *page;
 
-		/*
-		 * A valid page pointer that will not match any of the
-		 * pages that will be moved.
-		 */
-		pp->page = ZERO_PAGE(0);
-
 		err = -EFAULT;
 		vma = find_vma(mm, pp->addr);
 		if (!vma || !vma_migratable(vma))
@@ -919,41 +895,43 @@ static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
 			 const int __user *nodes,
 			 int __user *status, int flags)
 {
-	struct page_to_node *pm = NULL;
+	struct page_to_node *pm;
 	nodemask_t task_nodes;
-	int err = 0;
-	int i;
+	unsigned long chunk_nr_pages;
+	unsigned long chunk_start;
+	int err;
 
 	task_nodes = cpuset_mems_allowed(task);
 
-	/* Limit nr_pages so that the multiplication may not overflow */
-	if (nr_pages >= ULONG_MAX / sizeof(struct page_to_node) - 1) {
-		err = -E2BIG;
-		goto out;
-	}
-
-	pm = vmalloc((nr_pages + 1) * sizeof(struct page_to_node));
-	if (!pm) {
-		err = -ENOMEM;
+	err = -ENOMEM;
+	pm = (struct page_to_node *)__get_free_page(GFP_KERNEL);
+	if (!pm)
 		goto out;
-	}
-
 	/*
-	 * Get parameters from user space and initialize the pm
-	 * array. Return various errors if the user did something wrong.
+	 * Store a chunk of page_to_node array in a page,
+	 * but keep the last one as a marker
 	 */
-	for (i = 0; i < nr_pages; i++) {
-		const void __user *p;
+	chunk_nr_pages = (PAGE_SIZE / sizeof(struct page_to_node)) - 1;
 
-		err = -EFAULT;
-		if (get_user(p, pages + i))
-			goto out_pm;
+	for (chunk_start = 0;
+	     chunk_start < nr_pages;
+	     chunk_start += chunk_nr_pages) {
+		int j;
+
+		if (chunk_start + chunk_nr_pages > nr_pages)
+			chunk_nr_pages = nr_pages - chunk_start;
 
-		pm[i].addr = (unsigned long)p;
-		if (nodes) {
+		/* fill the chunk pm with addrs and nodes from user-space */
+		for (j = 0; j < chunk_nr_pages; j++) {
+			const void __user *p;
 			int node;
 
-			if (get_user(node, nodes + i))
+			err = -EFAULT;
+			if (get_user(p, pages + j + chunk_start))
+				goto out_pm;
+			pm[j].addr = (unsigned long) p;
+
+			if (get_user(node, nodes + j + chunk_start))
 				goto out_pm;
 
 			err = -ENODEV;
@@ -964,22 +942,29 @@ static int do_pages_move(struct mm_struct *mm, struct task_struct *task,
 			if (!node_isset(node, task_nodes))
 				goto out_pm;
 
-			pm[i].node = node;
-		} else
-			pm[i].node = 0;	/* anything to not match MAX_NUMNODES */
-	}
-	/* End marker */
-	pm[nr_pages].node = MAX_NUMNODES;
+			pm[j].node = node;
+		}
+
+		/* End marker for this chunk */
+		pm[chunk_nr_pages].node = MAX_NUMNODES;
+
+		/* Migrate this chunk */
+		err = do_move_page_to_node_array(mm, pm,
+						 flags & MPOL_MF_MOVE_ALL);
+		if (err < 0)
+			goto out_pm;
 
-	err = do_move_page_to_node_array(mm, pm, flags & MPOL_MF_MOVE_ALL);
-	if (err >= 0)
 		/* Return status information */
-		for (i = 0; i < nr_pages; i++)
-			if (put_user(pm[i].status, status + i))
+		for (j = 0; j < chunk_nr_pages; j++)
+			if (put_user(pm[j].status, status + j + chunk_start)) {
 				err = -EFAULT;
+				goto out_pm;
+			}
+	}
+	err = 0;
 
 out_pm:
-	vfree(pm);
+	free_page((unsigned long)pm);
 out:
 	return err;
 }
@@ -1070,10 +1055,10 @@ out:
  * Move a list of pages in the address space of the currently executing
  * process.
  */
-asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages,
-			const void __user * __user *pages,
-			const int __user *nodes,
-			int __user *status, int flags)
+SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
+		const void __user * __user *, pages,
+		const int __user *, nodes,
+		int __user *, status, int, flags)
 {
 	const struct cred *cred = current_cred(), *tcred;
 	struct task_struct *task;
diff --git a/mm/mincore.c b/mm/mincore.c
index 5178800bc129..8cb508f84ea4 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -177,8 +177,8 @@ none_mapped:
  *		mapped
  *  -EAGAIN - A kernel resource was temporarily unavailable.
  */
-asmlinkage long sys_mincore(unsigned long start, size_t len,
-	unsigned char __user * vec)
+SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
+		unsigned char __user *, vec)
 {
 	long retval;
 	unsigned long pages;
diff --git a/mm/mlock.c b/mm/mlock.c
index 3035a56e7616..028ec482fdd4 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -173,12 +173,13 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 		  (atomic_read(&mm->mm_users) != 0));
 
 	/*
-	 * mlock:   don't page populate if page has PROT_NONE permission.
-	 * munlock: the pages always do munlock althrough
-	 *          its has PROT_NONE permission.
+	 * mlock:   don't page populate if vma has PROT_NONE permission.
+	 * munlock: always do munlock although the vma has PROT_NONE
+	 *          permission, or SIGKILL is pending.
 	 */
 	if (!mlock)
-		gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS;
+		gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS |
+			     GUP_FLAGS_IGNORE_SIGKILL;
 
 	if (vma->vm_flags & VM_WRITE)
 		gup_flags |= GUP_FLAGS_WRITE;
@@ -293,14 +294,10 @@ static inline int __mlock_posix_error_return(long retval)
  *
  * return number of pages [> 0] to be removed from locked_vm on success
  * of "special" vmas.
- *
- * return negative error if vma spanning @start-@range disappears while
- * mmap semaphore is dropped.  Unlikely?
  */
 long mlock_vma_pages_range(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
-	struct mm_struct *mm = vma->vm_mm;
 	int nr_pages = (end - start) / PAGE_SIZE;
 	BUG_ON(!(vma->vm_flags & VM_LOCKED));
 
@@ -313,20 +310,8 @@ long mlock_vma_pages_range(struct vm_area_struct *vma,
 	if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
 			is_vm_hugetlb_page(vma) ||
 			vma == get_gate_vma(current))) {
-		long error;
-		downgrade_write(&mm->mmap_sem);
-
-		error = __mlock_vma_pages_range(vma, start, end, 1);
 
-		up_read(&mm->mmap_sem);
-		/* vma can change or disappear */
-		down_write(&mm->mmap_sem);
-		vma = find_vma(mm, start);
-		/* non-NULL vma must contain @start, but need to check @end */
-		if (!vma ||  end > vma->vm_end)
-			return -ENOMEM;
-
-		return 0;	/* hide other errors from mmap(), et al */
+		return __mlock_vma_pages_range(vma, start, end, 1);
 	}
 
 	/*
@@ -437,41 +422,14 @@ success:
 	vma->vm_flags = newflags;
 
 	if (lock) {
-		/*
-		 * mmap_sem is currently held for write.  Downgrade the write
-		 * lock to a read lock so that other faults, mmap scans, ...
-		 * while we fault in all pages.
-		 */
-		downgrade_write(&mm->mmap_sem);
-
 		ret = __mlock_vma_pages_range(vma, start, end, 1);
 
-		/*
-		 * Need to reacquire mmap sem in write mode, as our callers
-		 * expect this.  We have no support for atomically upgrading
-		 * a sem to write, so we need to check for ranges while sem
-		 * is unlocked.
-		 */
-		up_read(&mm->mmap_sem);
-		/* vma can change or disappear */
-		down_write(&mm->mmap_sem);
-		*prev = find_vma(mm, start);
-		/* non-NULL *prev must contain @start, but need to check @end */
-		if (!(*prev) || end > (*prev)->vm_end)
-			ret = -ENOMEM;
-		else if (ret > 0) {
+		if (ret > 0) {
 			mm->locked_vm -= ret;
 			ret = 0;
 		} else
 			ret = __mlock_posix_error_return(ret); /* translate if needed */
 	} else {
-		/*
-		 * TODO:  for unlocking, pages will already be resident, so
-		 * we don't need to wait for allocations/reclaim/pagein, ...
-		 * However, unlocking a very large region can still take a
-		 * while.  Should we downgrade the semaphore for both lock
-		 * AND unlock ?
-		 */
 		__mlock_vma_pages_range(vma, start, end, 0);
 	}
 
@@ -529,7 +487,7 @@ static int do_mlock(unsigned long start, size_t len, int on)
 	return error;
 }
 
-asmlinkage long sys_mlock(unsigned long start, size_t len)
+SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 {
 	unsigned long locked;
 	unsigned long lock_limit;
@@ -557,7 +515,7 @@ asmlinkage long sys_mlock(unsigned long start, size_t len)
 	return error;
 }
 
-asmlinkage long sys_munlock(unsigned long start, size_t len)
+SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len)
 {
 	int ret;
 
@@ -594,7 +552,7 @@ out:
 	return 0;
 }
 
-asmlinkage long sys_mlockall(int flags)
+SYSCALL_DEFINE1(mlockall, int, flags)
 {
 	unsigned long lock_limit;
 	int ret = -EINVAL;
@@ -622,7 +580,7 @@ out:
 	return ret;
 }
 
-asmlinkage long sys_munlockall(void)
+SYSCALL_DEFINE0(munlockall)
 {
 	int ret;
 
diff --git a/mm/mmap.c b/mm/mmap.c
index c3647f3b0621..3b3ed0bb9fdb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3,7 +3,7 @@
  *
  * Written by obz.
  *
- * Address space accounting code	<alan@redhat.com>
+ * Address space accounting code	<alan@lxorguk.ukuu.org.uk>
  */
 
 #include <linux/slab.h>
@@ -246,7 +246,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
 	return next;
 }
 
-asmlinkage unsigned long sys_brk(unsigned long brk)
+SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	unsigned long rlim, retval;
 	unsigned long newbrk, oldbrk;
@@ -414,7 +414,7 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 
 static void __vma_link_file(struct vm_area_struct *vma)
 {
-	struct file * file;
+	struct file *file;
 
 	file = vma->vm_file;
 	if (file) {
@@ -475,11 +475,10 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
  * insert vm structure into list and rbtree and anon_vma,
  * but it has already been inserted into prio_tree earlier.
  */
-static void
-__insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
+static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct vm_area_struct * __vma, * prev;
-	struct rb_node ** rb_link, * rb_parent;
+	struct vm_area_struct *__vma, *prev;
+	struct rb_node **rb_link, *rb_parent;
 
 	__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent);
 	BUG_ON(__vma && __vma->vm_start < vma->vm_end);
@@ -660,6 +659,9 @@ again:			remove_next = 1 + (end > next->vm_end);
 	validate_mm(mm);
 }
 
+/* Flags that can be inherited from an existing mapping when merging */
+#define VM_MERGEABLE_FLAGS (VM_CAN_NONLINEAR)
+
 /*
  * 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.
@@ -667,7 +669,7 @@ again:			remove_next = 1 + (end > next->vm_end);
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags)
 {
-	if (vma->vm_flags != vm_flags)
+	if ((vma->vm_flags ^ vm_flags) & ~VM_MERGEABLE_FLAGS)
 		return 0;
 	if (vma->vm_file != file)
 		return 0;
@@ -909,7 +911,7 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags,
  * The caller must hold down_write(current->mm->mmap_sem).
  */
 
-unsigned long do_mmap_pgoff(struct file * file, unsigned long addr,
+unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 			unsigned long len, unsigned long prot,
 			unsigned long flags, unsigned long pgoff)
 {
@@ -1092,6 +1094,15 @@ int vma_wants_writenotify(struct vm_area_struct *vma)
 		mapping_cap_account_dirty(vma->vm_file->f_mapping);
 }
 
+/*
+ * We account for memory if it's a private writeable mapping,
+ * and VM_NORESERVE wasn't set.
+ */
+static inline int accountable_mapping(unsigned int vm_flags)
+{
+	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
+}
+
 unsigned long mmap_region(struct file *file, unsigned long addr,
 			  unsigned long len, unsigned long flags,
 			  unsigned int vm_flags, unsigned long pgoff,
@@ -1119,36 +1130,32 @@ munmap_back:
 	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
 		return -ENOMEM;
 
-	if (flags & MAP_NORESERVE)
+	/*
+	 * Set 'VM_NORESERVE' if we should not account for the
+	 * memory use of this mapping. We only honor MAP_NORESERVE
+	 * if we're allowed to overcommit memory.
+	 */
+	if ((flags & MAP_NORESERVE) && sysctl_overcommit_memory != OVERCOMMIT_NEVER)
+		vm_flags |= VM_NORESERVE;
+	if (!accountable)
 		vm_flags |= VM_NORESERVE;
 
-	if (accountable && (!(flags & MAP_NORESERVE) ||
-			    sysctl_overcommit_memory == OVERCOMMIT_NEVER)) {
-		if (vm_flags & VM_SHARED) {
-			/* Check memory availability in shmem_file_setup? */
-			vm_flags |= VM_ACCOUNT;
-		} else if (vm_flags & VM_WRITE) {
-			/*
-			 * Private writable mapping: check memory availability
-			 */
-			charged = len >> PAGE_SHIFT;
-			if (security_vm_enough_memory(charged))
-				return -ENOMEM;
-			vm_flags |= VM_ACCOUNT;
-		}
+	/*
+	 * Private writable mapping: check memory availability
+	 */
+	if (accountable_mapping(vm_flags)) {
+		charged = len >> PAGE_SHIFT;
+		if (security_vm_enough_memory(charged))
+			return -ENOMEM;
+		vm_flags |= VM_ACCOUNT;
 	}
 
 	/*
-	 * Can we just expand an old private anonymous mapping?
-	 * The VM_SHARED test is necessary because shmem_zero_setup
-	 * will create the file object for a shared anonymous map below.
+	 * Can we just expand an old mapping?
 	 */
-	if (!file && !(vm_flags & VM_SHARED)) {
-		vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
-					NULL, NULL, pgoff, NULL);
-		if (vma)
-			goto out;
-	}
+	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
+	if (vma)
+		goto out;
 
 	/*
 	 * Determine the object being mapped and call the appropriate
@@ -1191,14 +1198,6 @@ munmap_back:
 			goto free_vma;
 	}
 
-	/* We set VM_ACCOUNT in a shared mapping's vm_flags, to inform
-	 * shmem_zero_setup (perhaps called through /dev/zero's ->mmap)
-	 * that memory reservation must be checked; but that reservation
-	 * belongs to shared memory object, not to vma: so now clear it.
-	 */
-	if ((vm_flags & (VM_SHARED|VM_ACCOUNT)) == (VM_SHARED|VM_ACCOUNT))
-		vma->vm_flags &= ~VM_ACCOUNT;
-
 	/* Can addr have changed??
 	 *
 	 * Answer: Yes, several device drivers can do it in their
@@ -1211,17 +1210,8 @@ munmap_back:
 	if (vma_wants_writenotify(vma))
 		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
 
-	if (file && vma_merge(mm, prev, addr, vma->vm_end,
-			vma->vm_flags, NULL, file, pgoff, vma_policy(vma))) {
-		mpol_put(vma_policy(vma));
-		kmem_cache_free(vm_area_cachep, vma);
-		fput(file);
-		if (vm_flags & VM_EXECUTABLE)
-			removed_exe_file_vma(mm);
-	} else {
-		vma_link(mm, vma, prev, rb_link, rb_parent);
-		file = vma->vm_file;
-	}
+	vma_link(mm, vma, prev, rb_link, rb_parent);
+	file = vma->vm_file;
 
 	/* Once vma denies write, undo our temporary denial count */
 	if (correct_wcount)
@@ -1468,7 +1458,7 @@ get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 EXPORT_SYMBOL(get_unmapped_area);
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
-struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr)
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
 {
 	struct vm_area_struct *vma = NULL;
 
@@ -1511,7 +1501,7 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr,
 			struct vm_area_struct **pprev)
 {
 	struct vm_area_struct *vma = NULL, *prev = NULL;
-	struct rb_node * rb_node;
+	struct rb_node *rb_node;
 	if (!mm)
 		goto out;
 
@@ -1545,7 +1535,7 @@ out:
  * update accounting. This is shared with both the
  * grow-up and grow-down cases.
  */
-static int acct_stack_growth(struct vm_area_struct * vma, unsigned long size, unsigned long grow)
+static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct rlimit *rlim = current->signal->rlim;
@@ -1953,7 +1943,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 
 EXPORT_SYMBOL(do_munmap);
 
-asmlinkage long sys_munmap(unsigned long addr, size_t len)
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
 	int ret;
 	struct mm_struct *mm = current->mm;
@@ -2095,6 +2085,9 @@ void exit_mmap(struct mm_struct *mm)
 	arch_exit_mmap(mm);
 	mmu_notifier_release(mm);
 
+	if (!mm->mmap)	/* Can happen if dup_mmap() received an OOM */
+		return;
+
 	if (mm->locked_vm) {
 		vma = mm->mmap;
 		while (vma) {
@@ -2107,7 +2100,7 @@ void exit_mmap(struct mm_struct *mm)
 	lru_add_drain();
 	flush_cache_mm(mm);
 	tlb = tlb_gather_mmu(mm, 1);
-	/* Don't update_hiwater_rss(mm) here, do_exit already did */
+	/* update_hiwater_rss(mm) here? but nobody should be looking */
 	/* Use -1 here to ensure all VMAs in the mm are unmapped */
 	end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
 	vm_unacct_memory(nr_accounted);
@@ -2474,3 +2467,13 @@ void mm_drop_all_locks(struct mm_struct *mm)
 
 	mutex_unlock(&mm_all_locks_mutex);
 }
+
+/*
+ * initialise the VMA slab
+ */
+void __init mmap_init(void)
+{
+	vm_area_cachep = kmem_cache_create("vm_area_struct",
+			sizeof(struct vm_area_struct), 0,
+			SLAB_PANIC, NULL);
+}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index fded06f923f4..abe2694e13f4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -4,7 +4,7 @@
  *  (C) Copyright 1994 Linus Torvalds
  *  (C) Copyright 2002 Christoph Hellwig
  *
- *  Address space accounting code	<alan@redhat.com>
+ *  Address space accounting code	<alan@lxorguk.ukuu.org.uk>
  *  (C) Copyright 2002 Red Hat Inc, All Rights Reserved
  */
 
@@ -22,6 +22,7 @@
 #include <linux/swap.h>
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
+#include <linux/migrate.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
@@ -59,8 +60,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				ptent = pte_mkwrite(ptent);
 
 			ptep_modify_prot_commit(mm, addr, pte, ptent);
-#ifdef CONFIG_MIGRATION
-		} else if (!pte_file(oldpte)) {
+		} else if (PAGE_MIGRATION && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
 			if (is_write_migration_entry(entry)) {
@@ -72,9 +72,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 				set_pte_at(mm, addr, pte,
 					swp_entry_to_pte(entry));
 			}
-#endif
 		}
-
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
@@ -219,8 +217,8 @@ fail:
 	return error;
 }
 
-asmlinkage long
-sys_mprotect(unsigned long start, size_t len, unsigned long prot)
+SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
+		unsigned long, prot)
 {
 	unsigned long vm_flags, nstart, end, tmp, reqprot;
 	struct vm_area_struct *vma, *prev;
diff --git a/mm/mremap.c b/mm/mremap.c
index 58a2908f42f5..a39b7b91be46 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -3,7 +3,7 @@
  *
  *	(C) Copyright 1996 Linus Torvalds
  *
- *	Address space accounting code	<alan@redhat.com>
+ *	Address space accounting code	<alan@lxorguk.ukuu.org.uk>
  *	(C) Copyright 2002 Red Hat Inc, All Rights Reserved
  */
 
@@ -420,9 +420,9 @@ out_nc:
 	return ret;
 }
 
-asmlinkage unsigned long sys_mremap(unsigned long addr,
-	unsigned long old_len, unsigned long new_len,
-	unsigned long flags, unsigned long new_addr)
+SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
+		unsigned long, new_len, unsigned long, flags,
+		unsigned long, new_addr)
 {
 	unsigned long ret;
 
diff --git a/mm/msync.c b/mm/msync.c
index 144a7570535d..4083209b7f02 100644
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -28,7 +28,7 @@
  * So by _not_ starting I/O in MS_ASYNC we provide complete flexibility to
  * applications.
  */
-asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
+SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags)
 {
 	unsigned long end;
 	struct mm_struct *mm = current->mm;
@@ -82,7 +82,7 @@ asmlinkage long sys_msync(unsigned long start, size_t len, int flags)
 				(vma->vm_flags & VM_SHARED)) {
 			get_file(file);
 			up_read(&mm->mmap_sem);
-			error = do_fsync(file, 0);
+			error = vfs_fsync(file, file->f_path.dentry, 0);
 			fput(file);
 			if (error || start >= end)
 				goto out;
diff --git a/mm/nommu.c b/mm/nommu.c
index 7695dc850785..2fcf47d449b4 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -6,11 +6,11 @@
  *
  *  See Documentation/nommu-mmap.txt
  *
- *  Copyright (c) 2004-2005 David Howells <dhowells@redhat.com>
+ *  Copyright (c) 2004-2008 David Howells <dhowells@redhat.com>
  *  Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
  *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
  *  Copyright (c) 2002      Greg Ungerer <gerg@snapgear.com>
- *  Copyright (c) 2007      Paul Mundt <lethal@linux-sh.org>
+ *  Copyright (c) 2007-2009 Paul Mundt <lethal@linux-sh.org>
  */
 
 #include <linux/module.h>
@@ -33,6 +33,28 @@
 #include <asm/uaccess.h>
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
+#include "internal.h"
+
+static inline __attribute__((format(printf, 1, 2)))
+void no_printk(const char *fmt, ...)
+{
+}
+
+#if 0
+#define kenter(FMT, ...) \
+	printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__)
+#else
+#define kenter(FMT, ...) \
+	no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) \
+	no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) \
+	no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
+#endif
 
 #include "internal.h"
 
@@ -40,19 +62,22 @@ void *high_memory;
 struct page *mem_map;
 unsigned long max_mapnr;
 unsigned long num_physpages;
-unsigned long askedalloc, realalloc;
 atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50; /* default is 50% */
 int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
+int sysctl_nr_trim_pages = 1; /* page trimming behaviour */
 int heap_stack_gap = 0;
 
+atomic_t mmap_pages_allocated;
+
 EXPORT_SYMBOL(mem_map);
 EXPORT_SYMBOL(num_physpages);
 
-/* list of shareable VMAs */
-struct rb_root nommu_vma_tree = RB_ROOT;
-DECLARE_RWSEM(nommu_vma_sem);
+/* list of mapped, potentially shareable regions */
+static struct kmem_cache *vm_region_jar;
+struct rb_root nommu_region_tree = RB_ROOT;
+DECLARE_RWSEM(nommu_region_sem);
 
 struct vm_operations_struct generic_file_vm_ops = {
 };
@@ -86,7 +111,7 @@ do_expand:
 	i_size_write(inode, offset);
 
 out_truncate:
-	if (inode->i_op && inode->i_op->truncate)
+	if (inode->i_op->truncate)
 		inode->i_op->truncate(inode);
 	return 0;
 out_sig:
@@ -124,6 +149,20 @@ unsigned int kobjsize(const void *objp)
 		return ksize(objp);
 
 	/*
+	 * If it's not a compound page, see if we have a matching VMA
+	 * region. This test is intentionally done in reverse order,
+	 * so if there's no VMA, we still fall through and hand back
+	 * PAGE_SIZE for 0-order pages.
+	 */
+	if (!PageCompound(page)) {
+		struct vm_area_struct *vma;
+
+		vma = find_vma(current->mm, (unsigned long)objp);
+		if (vma)
+			return vma->vm_end - vma->vm_start;
+	}
+
+	/*
 	 * The ksize() function is only guaranteed to work for pointers
 	 * returned by kmalloc(). So handle arbitrary pointers here.
 	 */
@@ -355,6 +394,24 @@ void vunmap(const void *addr)
 }
 EXPORT_SYMBOL(vunmap);
 
+void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
+{
+	BUG();
+	return NULL;
+}
+EXPORT_SYMBOL(vm_map_ram);
+
+void vm_unmap_ram(const void *mem, unsigned int count)
+{
+	BUG();
+}
+EXPORT_SYMBOL(vm_unmap_ram);
+
+void vm_unmap_aliases(void)
+{
+}
+EXPORT_SYMBOL_GPL(vm_unmap_aliases);
+
 /*
  * Implement a stub for vmalloc_sync_all() if the architecture chose not to
  * have one.
@@ -377,7 +434,7 @@ EXPORT_SYMBOL(vm_insert_page);
  *  to a regular file.  in this case, the unmapping will need
  *  to invoke file system routines that need the global lock.
  */
-asmlinkage unsigned long sys_brk(unsigned long brk)
+SYSCALL_DEFINE1(brk, unsigned long, brk)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -401,129 +458,178 @@ asmlinkage unsigned long sys_brk(unsigned long brk)
 	return mm->brk = brk;
 }
 
-#ifdef DEBUG
-static void show_process_blocks(void)
+/*
+ * initialise the VMA and region record slabs
+ */
+void __init mmap_init(void)
 {
-	struct vm_list_struct *vml;
-
-	printk("Process blocks %d:", current->pid);
-
-	for (vml = &current->mm->context.vmlist; vml; vml = vml->next) {
-		printk(" %p: %p", vml, vml->vma);
-		if (vml->vma)
-			printk(" (%d @%lx #%d)",
-			       kobjsize((void *) vml->vma->vm_start),
-			       vml->vma->vm_start,
-			       atomic_read(&vml->vma->vm_usage));
-		printk(vml->next ? " ->" : ".\n");
-	}
+	vm_region_jar = kmem_cache_create("vm_region_jar",
+					  sizeof(struct vm_region), 0,
+					  SLAB_PANIC, NULL);
+	vm_area_cachep = kmem_cache_create("vm_area_struct",
+					   sizeof(struct vm_area_struct), 0,
+					   SLAB_PANIC, NULL);
 }
-#endif /* DEBUG */
 
 /*
- * add a VMA into a process's mm_struct in the appropriate place in the list
- * - should be called with mm->mmap_sem held writelocked
+ * validate the region tree
+ * - the caller must hold the region lock
  */
-static void add_vma_to_mm(struct mm_struct *mm, struct vm_list_struct *vml)
+#ifdef CONFIG_DEBUG_NOMMU_REGIONS
+static noinline void validate_nommu_regions(void)
 {
-	struct vm_list_struct **ppv;
-
-	for (ppv = &current->mm->context.vmlist; *ppv; ppv = &(*ppv)->next)
-		if ((*ppv)->vma->vm_start > vml->vma->vm_start)
-			break;
-
-	vml->next = *ppv;
-	*ppv = vml;
+	struct vm_region *region, *last;
+	struct rb_node *p, *lastp;
+
+	lastp = rb_first(&nommu_region_tree);
+	if (!lastp)
+		return;
+
+	last = rb_entry(lastp, struct vm_region, vm_rb);
+	if (unlikely(last->vm_end <= last->vm_start))
+		BUG();
+	if (unlikely(last->vm_top < last->vm_end))
+		BUG();
+
+	while ((p = rb_next(lastp))) {
+		region = rb_entry(p, struct vm_region, vm_rb);
+		last = rb_entry(lastp, struct vm_region, vm_rb);
+
+		if (unlikely(region->vm_end <= region->vm_start))
+			BUG();
+		if (unlikely(region->vm_top < region->vm_end))
+			BUG();
+		if (unlikely(region->vm_start < last->vm_top))
+			BUG();
+
+		lastp = p;
+	}
 }
+#else
+#define validate_nommu_regions() do {} while(0)
+#endif
 
 /*
- * look up the first VMA in which addr resides, NULL if none
- * - should be called with mm->mmap_sem at least held readlocked
+ * add a region into the global tree
  */
-struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+static void add_nommu_region(struct vm_region *region)
 {
-	struct vm_list_struct *loop, *vml;
+	struct vm_region *pregion;
+	struct rb_node **p, *parent;
 
-	/* search the vm_start ordered list */
-	vml = NULL;
-	for (loop = mm->context.vmlist; loop; loop = loop->next) {
-		if (loop->vma->vm_start > addr)
-			break;
-		vml = loop;
+	validate_nommu_regions();
+
+	BUG_ON(region->vm_start & ~PAGE_MASK);
+
+	parent = NULL;
+	p = &nommu_region_tree.rb_node;
+	while (*p) {
+		parent = *p;
+		pregion = rb_entry(parent, struct vm_region, vm_rb);
+		if (region->vm_start < pregion->vm_start)
+			p = &(*p)->rb_left;
+		else if (region->vm_start > pregion->vm_start)
+			p = &(*p)->rb_right;
+		else if (pregion == region)
+			return;
+		else
+			BUG();
 	}
 
-	if (vml && vml->vma->vm_end > addr)
-		return vml->vma;
+	rb_link_node(&region->vm_rb, parent, p);
+	rb_insert_color(&region->vm_rb, &nommu_region_tree);
 
-	return NULL;
+	validate_nommu_regions();
 }
-EXPORT_SYMBOL(find_vma);
 
 /*
- * find a VMA
- * - we don't extend stack VMAs under NOMMU conditions
+ * delete a region from the global tree
  */
-struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
+static void delete_nommu_region(struct vm_region *region)
 {
-	return find_vma(mm, addr);
-}
+	BUG_ON(!nommu_region_tree.rb_node);
 
-int expand_stack(struct vm_area_struct *vma, unsigned long address)
-{
-	return -ENOMEM;
+	validate_nommu_regions();
+	rb_erase(&region->vm_rb, &nommu_region_tree);
+	validate_nommu_regions();
 }
 
 /*
- * look up the first VMA exactly that exactly matches addr
- * - should be called with mm->mmap_sem at least held readlocked
+ * free a contiguous series of pages
  */
-static inline struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
-						    unsigned long addr)
+static void free_page_series(unsigned long from, unsigned long to)
 {
-	struct vm_list_struct *vml;
-
-	/* search the vm_start ordered list */
-	for (vml = mm->context.vmlist; vml; vml = vml->next) {
-		if (vml->vma->vm_start == addr)
-			return vml->vma;
-		if (vml->vma->vm_start > addr)
-			break;
+	for (; from < to; from += PAGE_SIZE) {
+		struct page *page = virt_to_page(from);
+
+		kdebug("- free %lx", from);
+		atomic_dec(&mmap_pages_allocated);
+		if (page_count(page) != 1)
+			kdebug("free page %p [%d]", page, page_count(page));
+		put_page(page);
 	}
-
-	return NULL;
 }
 
 /*
- * find a VMA in the global tree
+ * release a reference to a region
+ * - the caller must hold the region semaphore, which this releases
+ * - the region may not have been added to the tree yet, in which case vm_top
+ *   will equal vm_start
  */
-static inline struct vm_area_struct *find_nommu_vma(unsigned long start)
+static void __put_nommu_region(struct vm_region *region)
+	__releases(nommu_region_sem)
 {
-	struct vm_area_struct *vma;
-	struct rb_node *n = nommu_vma_tree.rb_node;
+	kenter("%p{%d}", region, atomic_read(&region->vm_usage));
 
-	while (n) {
-		vma = rb_entry(n, struct vm_area_struct, vm_rb);
+	BUG_ON(!nommu_region_tree.rb_node);
 
-		if (start < vma->vm_start)
-			n = n->rb_left;
-		else if (start > vma->vm_start)
-			n = n->rb_right;
-		else
-			return vma;
+	if (atomic_dec_and_test(&region->vm_usage)) {
+		if (region->vm_top > region->vm_start)
+			delete_nommu_region(region);
+		up_write(&nommu_region_sem);
+
+		if (region->vm_file)
+			fput(region->vm_file);
+
+		/* IO memory and memory shared directly out of the pagecache
+		 * from ramfs/tmpfs mustn't be released here */
+		if (region->vm_flags & VM_MAPPED_COPY) {
+			kdebug("free series");
+			free_page_series(region->vm_start, region->vm_top);
+		}
+		kmem_cache_free(vm_region_jar, region);
+	} else {
+		up_write(&nommu_region_sem);
 	}
+}
 
-	return NULL;
+/*
+ * release a reference to a region
+ */
+static void put_nommu_region(struct vm_region *region)
+{
+	down_write(&nommu_region_sem);
+	__put_nommu_region(region);
 }
 
 /*
- * add a VMA in the global tree
+ * add a VMA into a process's mm_struct in the appropriate place in the list
+ * and tree and add to the address space's page tree also if not an anonymous
+ * page
+ * - should be called with mm->mmap_sem held writelocked
  */
-static void add_nommu_vma(struct vm_area_struct *vma)
+static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
 {
-	struct vm_area_struct *pvma;
+	struct vm_area_struct *pvma, **pp;
 	struct address_space *mapping;
-	struct rb_node **p = &nommu_vma_tree.rb_node;
-	struct rb_node *parent = NULL;
+	struct rb_node **p, *parent;
+
+	kenter(",%p", vma);
+
+	BUG_ON(!vma->vm_region);
+
+	mm->map_count++;
+	vma->vm_mm = mm;
 
 	/* add the VMA to the mapping */
 	if (vma->vm_file) {
@@ -534,42 +640,62 @@ static void add_nommu_vma(struct vm_area_struct *vma)
 		flush_dcache_mmap_unlock(mapping);
 	}
 
-	/* add the VMA to the master list */
+	/* add the VMA to the tree */
+	parent = NULL;
+	p = &mm->mm_rb.rb_node;
 	while (*p) {
 		parent = *p;
 		pvma = rb_entry(parent, struct vm_area_struct, vm_rb);
 
-		if (vma->vm_start < pvma->vm_start) {
+		/* sort by: start addr, end addr, VMA struct addr in that order
+		 * (the latter is necessary as we may get identical VMAs) */
+		if (vma->vm_start < pvma->vm_start)
 			p = &(*p)->rb_left;
-		}
-		else if (vma->vm_start > pvma->vm_start) {
+		else if (vma->vm_start > pvma->vm_start)
 			p = &(*p)->rb_right;
-		}
-		else {
-			/* mappings are at the same address - this can only
-			 * happen for shared-mem chardevs and shared file
-			 * mappings backed by ramfs/tmpfs */
-			BUG_ON(!(pvma->vm_flags & VM_SHARED));
-
-			if (vma < pvma)
-				p = &(*p)->rb_left;
-			else if (vma > pvma)
-				p = &(*p)->rb_right;
-			else
-				BUG();
-		}
+		else if (vma->vm_end < pvma->vm_end)
+			p = &(*p)->rb_left;
+		else if (vma->vm_end > pvma->vm_end)
+			p = &(*p)->rb_right;
+		else if (vma < pvma)
+			p = &(*p)->rb_left;
+		else if (vma > pvma)
+			p = &(*p)->rb_right;
+		else
+			BUG();
 	}
 
 	rb_link_node(&vma->vm_rb, parent, p);
-	rb_insert_color(&vma->vm_rb, &nommu_vma_tree);
+	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
+
+	/* add VMA to the VMA list also */
+	for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) {
+		if (pvma->vm_start > vma->vm_start)
+			break;
+		if (pvma->vm_start < vma->vm_start)
+			continue;
+		if (pvma->vm_end < vma->vm_end)
+			break;
+	}
+
+	vma->vm_next = *pp;
+	*pp = vma;
 }
 
 /*
- * delete a VMA from the global list
+ * delete a VMA from its owning mm_struct and address space
  */
-static void delete_nommu_vma(struct vm_area_struct *vma)
+static void delete_vma_from_mm(struct vm_area_struct *vma)
 {
+	struct vm_area_struct **pp;
 	struct address_space *mapping;
+	struct mm_struct *mm = vma->vm_mm;
+
+	kenter("%p", vma);
+
+	mm->map_count--;
+	if (mm->mmap_cache == vma)
+		mm->mmap_cache = NULL;
 
 	/* remove the VMA from the mapping */
 	if (vma->vm_file) {
@@ -580,8 +706,115 @@ static void delete_nommu_vma(struct vm_area_struct *vma)
 		flush_dcache_mmap_unlock(mapping);
 	}
 
-	/* remove from the master list */
-	rb_erase(&vma->vm_rb, &nommu_vma_tree);
+	/* remove from the MM's tree and list */
+	rb_erase(&vma->vm_rb, &mm->mm_rb);
+	for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) {
+		if (*pp == vma) {
+			*pp = vma->vm_next;
+			break;
+		}
+	}
+
+	vma->vm_mm = NULL;
+}
+
+/*
+ * destroy a VMA record
+ */
+static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+	kenter("%p", vma);
+	if (vma->vm_ops && vma->vm_ops->close)
+		vma->vm_ops->close(vma);
+	if (vma->vm_file) {
+		fput(vma->vm_file);
+		if (vma->vm_flags & VM_EXECUTABLE)
+			removed_exe_file_vma(mm);
+	}
+	put_nommu_region(vma->vm_region);
+	kmem_cache_free(vm_area_cachep, vma);
+}
+
+/*
+ * look up the first VMA in which addr resides, NULL if none
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma;
+	struct rb_node *n = mm->mm_rb.rb_node;
+
+	/* check the cache first */
+	vma = mm->mmap_cache;
+	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
+		return vma;
+
+	/* trawl the tree (there may be multiple mappings in which addr
+	 * resides) */
+	for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
+		vma = rb_entry(n, struct vm_area_struct, vm_rb);
+		if (vma->vm_start > addr)
+			return NULL;
+		if (vma->vm_end > addr) {
+			mm->mmap_cache = vma;
+			return vma;
+		}
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(find_vma);
+
+/*
+ * find a VMA
+ * - we don't extend stack VMAs under NOMMU conditions
+ */
+struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
+{
+	return find_vma(mm, addr);
+}
+
+/*
+ * expand a stack to a given address
+ * - not supported under NOMMU conditions
+ */
+int expand_stack(struct vm_area_struct *vma, unsigned long address)
+{
+	return -ENOMEM;
+}
+
+/*
+ * look up the first VMA exactly that exactly matches addr
+ * - should be called with mm->mmap_sem at least held readlocked
+ */
+static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
+					     unsigned long addr,
+					     unsigned long len)
+{
+	struct vm_area_struct *vma;
+	struct rb_node *n = mm->mm_rb.rb_node;
+	unsigned long end = addr + len;
+
+	/* check the cache first */
+	vma = mm->mmap_cache;
+	if (vma && vma->vm_start == addr && vma->vm_end == end)
+		return vma;
+
+	/* trawl the tree (there may be multiple mappings in which addr
+	 * resides) */
+	for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
+		vma = rb_entry(n, struct vm_area_struct, vm_rb);
+		if (vma->vm_start < addr)
+			continue;
+		if (vma->vm_start > addr)
+			return NULL;
+		if (vma->vm_end == end) {
+			mm->mmap_cache = vma;
+			return vma;
+		}
+	}
+
+	return NULL;
 }
 
 /*
@@ -596,7 +829,7 @@ static int validate_mmap_request(struct file *file,
 				 unsigned long pgoff,
 				 unsigned long *_capabilities)
 {
-	unsigned long capabilities;
+	unsigned long capabilities, rlen;
 	unsigned long reqprot = prot;
 	int ret;
 
@@ -616,12 +849,12 @@ static int validate_mmap_request(struct file *file,
 		return -EINVAL;
 
 	/* Careful about overflows.. */
-	len = PAGE_ALIGN(len);
-	if (!len || len > TASK_SIZE)
+	rlen = PAGE_ALIGN(len);
+	if (!rlen || rlen > TASK_SIZE)
 		return -ENOMEM;
 
 	/* offset overflow? */
-	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
+	if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff)
 		return -EOVERFLOW;
 
 	if (file) {
@@ -795,13 +1028,18 @@ static unsigned long determine_vm_flags(struct file *file,
 }
 
 /*
- * set up a shared mapping on a file
+ * set up a shared mapping on a file (the driver or filesystem provides and
+ * pins the storage)
  */
-static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len)
+static int do_mmap_shared_file(struct vm_area_struct *vma)
 {
 	int ret;
 
 	ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
+	if (ret == 0) {
+		vma->vm_region->vm_top = vma->vm_region->vm_end;
+		return ret;
+	}
 	if (ret != -ENOSYS)
 		return ret;
 
@@ -815,10 +1053,14 @@ static int do_mmap_shared_file(struct vm_area_struct *vma, unsigned long len)
 /*
  * set up a private mapping or an anonymous shared mapping
  */
-static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
+static int do_mmap_private(struct vm_area_struct *vma,
+			   struct vm_region *region,
+			   unsigned long len)
 {
+	struct page *pages;
+	unsigned long total, point, n, rlen;
 	void *base;
-	int ret;
+	int ret, order;
 
 	/* invoke the file's mapping function so that it can keep track of
 	 * shared mappings on devices or memory
@@ -826,34 +1068,63 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
 	 */
 	if (vma->vm_file) {
 		ret = vma->vm_file->f_op->mmap(vma->vm_file, vma);
-		if (ret != -ENOSYS) {
+		if (ret == 0) {
 			/* shouldn't return success if we're not sharing */
-			BUG_ON(ret == 0 && !(vma->vm_flags & VM_MAYSHARE));
-			return ret; /* success or a real error */
+			BUG_ON(!(vma->vm_flags & VM_MAYSHARE));
+			vma->vm_region->vm_top = vma->vm_region->vm_end;
+			return ret;
 		}
+		if (ret != -ENOSYS)
+			return ret;
 
 		/* getting an ENOSYS error indicates that direct mmap isn't
 		 * possible (as opposed to tried but failed) so we'll try to
 		 * make a private copy of the data and map that instead */
 	}
 
+	rlen = PAGE_ALIGN(len);
+
 	/* allocate some memory to hold the mapping
 	 * - 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|__GFP_COMP);
-	if (!base)
+	order = get_order(rlen);
+	kdebug("alloc order %d for %lx", order, len);
+
+	pages = alloc_pages(GFP_KERNEL, order);
+	if (!pages)
 		goto enomem;
 
-	vma->vm_start = (unsigned long) base;
-	vma->vm_end = vma->vm_start + len;
-	vma->vm_flags |= VM_MAPPED_COPY;
+	total = 1 << order;
+	atomic_add(total, &mmap_pages_allocated);
+
+	point = rlen >> PAGE_SHIFT;
+
+	/* we allocated a power-of-2 sized page set, so we may want to trim off
+	 * the excess */
+	if (sysctl_nr_trim_pages && total - point >= sysctl_nr_trim_pages) {
+		while (total > point) {
+			order = ilog2(total - point);
+			n = 1 << order;
+			kdebug("shave %lu/%lu @%lu", n, total - point, total);
+			atomic_sub(n, &mmap_pages_allocated);
+			total -= n;
+			set_page_refcounted(pages + total);
+			__free_pages(pages + total, order);
+		}
+	}
 
-#ifdef WARN_ON_SLACK
-	if (len + WARN_ON_SLACK <= kobjsize(result))
-		printk("Allocation of %lu bytes from process %d has %lu bytes of slack\n",
-		       len, current->pid, kobjsize(result) - len);
-#endif
+	for (point = 1; point < total; point++)
+		set_page_refcounted(&pages[point]);
+
+	base = page_address(pages);
+	region->vm_flags = vma->vm_flags |= VM_MAPPED_COPY;
+	region->vm_start = (unsigned long) base;
+	region->vm_end   = region->vm_start + rlen;
+	region->vm_top   = region->vm_start + (total << PAGE_SHIFT);
+
+	vma->vm_start = region->vm_start;
+	vma->vm_end   = region->vm_start + len;
 
 	if (vma->vm_file) {
 		/* read the contents of a file into the copy */
@@ -865,31 +1136,33 @@ static int do_mmap_private(struct vm_area_struct *vma, unsigned long len)
 
 		old_fs = get_fs();
 		set_fs(KERNEL_DS);
-		ret = vma->vm_file->f_op->read(vma->vm_file, base, len, &fpos);
+		ret = vma->vm_file->f_op->read(vma->vm_file, base, rlen, &fpos);
 		set_fs(old_fs);
 
 		if (ret < 0)
 			goto error_free;
 
 		/* clear the last little bit */
-		if (ret < len)
-			memset(base + ret, 0, len - ret);
+		if (ret < rlen)
+			memset(base + ret, 0, rlen - ret);
 
 	} else {
 		/* if it's an anonymous mapping, then just clear it */
-		memset(base, 0, len);
+		memset(base, 0, rlen);
 	}
 
 	return 0;
 
 error_free:
-	kfree(base);
-	vma->vm_start = 0;
+	free_page_series(region->vm_start, region->vm_end);
+	region->vm_start = vma->vm_start = 0;
+	region->vm_end   = vma->vm_end = 0;
+	region->vm_top   = 0;
 	return ret;
 
 enomem:
-	printk("Allocation of length %lu from process %d failed\n",
-	       len, current->pid);
+	printk("Allocation of length %lu from process %d (%s) failed\n",
+	       len, current->pid, current->comm);
 	show_free_areas();
 	return -ENOMEM;
 }
@@ -904,13 +1177,14 @@ unsigned long do_mmap_pgoff(struct file *file,
 			    unsigned long flags,
 			    unsigned long pgoff)
 {
-	struct vm_list_struct *vml = NULL;
-	struct vm_area_struct *vma = NULL;
+	struct vm_area_struct *vma;
+	struct vm_region *region;
 	struct rb_node *rb;
-	unsigned long capabilities, vm_flags;
-	void *result;
+	unsigned long capabilities, vm_flags, result;
 	int ret;
 
+	kenter(",%lx,%lx,%lx,%lx,%lx", addr, len, prot, flags, pgoff);
+
 	if (!(flags & MAP_FIXED))
 		addr = round_hint_to_min(addr);
 
@@ -918,73 +1192,120 @@ unsigned long do_mmap_pgoff(struct file *file,
 	 * mapping */
 	ret = validate_mmap_request(file, addr, len, prot, flags, pgoff,
 				    &capabilities);
-	if (ret < 0)
+	if (ret < 0) {
+		kleave(" = %d [val]", ret);
 		return ret;
+	}
 
 	/* we've determined that we can make the mapping, now translate what we
 	 * now know into VMA flags */
 	vm_flags = determine_vm_flags(file, prot, flags, capabilities);
 
-	/* we're going to need to record the mapping if it works */
-	vml = kzalloc(sizeof(struct vm_list_struct), GFP_KERNEL);
-	if (!vml)
-		goto error_getting_vml;
+	/* we're going to need to record the mapping */
+	region = kmem_cache_zalloc(vm_region_jar, GFP_KERNEL);
+	if (!region)
+		goto error_getting_region;
+
+	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+	if (!vma)
+		goto error_getting_vma;
+
+	atomic_set(&region->vm_usage, 1);
+	region->vm_flags = vm_flags;
+	region->vm_pgoff = pgoff;
+
+	INIT_LIST_HEAD(&vma->anon_vma_node);
+	vma->vm_flags = vm_flags;
+	vma->vm_pgoff = pgoff;
+
+	if (file) {
+		region->vm_file = file;
+		get_file(file);
+		vma->vm_file = file;
+		get_file(file);
+		if (vm_flags & VM_EXECUTABLE) {
+			added_exe_file_vma(current->mm);
+			vma->vm_mm = current->mm;
+		}
+	}
 
-	down_write(&nommu_vma_sem);
+	down_write(&nommu_region_sem);
 
-	/* if we want to share, we need to check for VMAs created by other
+	/* if we want to share, we need to check for regions created by other
 	 * mmap() calls that overlap with our proposed mapping
-	 * - we can only share with an exact match on most regular files
+	 * - we can only share with a superset match on most regular files
 	 * - shared mappings on character devices and memory backed files are
 	 *   permitted to overlap inexactly as far as we are concerned for in
 	 *   these cases, sharing is handled in the driver or filesystem rather
 	 *   than here
 	 */
 	if (vm_flags & VM_MAYSHARE) {
-		unsigned long pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
-		unsigned long vmpglen;
+		struct vm_region *pregion;
+		unsigned long pglen, rpglen, pgend, rpgend, start;
 
-		/* suppress VMA sharing for shared regions */
-		if (vm_flags & VM_SHARED &&
-		    capabilities & BDI_CAP_MAP_DIRECT)
-			goto dont_share_VMAs;
+		pglen = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
+		pgend = pgoff + pglen;
 
-		for (rb = rb_first(&nommu_vma_tree); rb; rb = rb_next(rb)) {
-			vma = rb_entry(rb, struct vm_area_struct, vm_rb);
+		for (rb = rb_first(&nommu_region_tree); rb; rb = rb_next(rb)) {
+			pregion = rb_entry(rb, struct vm_region, vm_rb);
 
-			if (!(vma->vm_flags & VM_MAYSHARE))
+			if (!(pregion->vm_flags & VM_MAYSHARE))
 				continue;
 
 			/* search for overlapping mappings on the same file */
-			if (vma->vm_file->f_path.dentry->d_inode != file->f_path.dentry->d_inode)
+			if (pregion->vm_file->f_path.dentry->d_inode !=
+			    file->f_path.dentry->d_inode)
 				continue;
 
-			if (vma->vm_pgoff >= pgoff + pglen)
+			if (pregion->vm_pgoff >= pgend)
 				continue;
 
-			vmpglen = vma->vm_end - vma->vm_start + PAGE_SIZE - 1;
-			vmpglen >>= PAGE_SHIFT;
-			if (pgoff >= vma->vm_pgoff + vmpglen)
+			rpglen = pregion->vm_end - pregion->vm_start;
+			rpglen = (rpglen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+			rpgend = pregion->vm_pgoff + rpglen;
+			if (pgoff >= rpgend)
 				continue;
 
-			/* handle inexactly overlapping matches between mappings */
-			if (vma->vm_pgoff != pgoff || vmpglen != pglen) {
+			/* handle inexactly overlapping matches between
+			 * mappings */
+			if ((pregion->vm_pgoff != pgoff || rpglen != pglen) &&
+			    !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) {
+				/* new mapping is not a subset of the region */
 				if (!(capabilities & BDI_CAP_MAP_DIRECT))
 					goto sharing_violation;
 				continue;
 			}
 
-			/* we've found a VMA we can share */
-			atomic_inc(&vma->vm_usage);
-
-			vml->vma = vma;
-			result = (void *) vma->vm_start;
-			goto shared;
+			/* we've found a region we can share */
+			atomic_inc(&pregion->vm_usage);
+			vma->vm_region = pregion;
+			start = pregion->vm_start;
+			start += (pgoff - pregion->vm_pgoff) << PAGE_SHIFT;
+			vma->vm_start = start;
+			vma->vm_end = start + len;
+
+			if (pregion->vm_flags & VM_MAPPED_COPY) {
+				kdebug("share copy");
+				vma->vm_flags |= VM_MAPPED_COPY;
+			} else {
+				kdebug("share mmap");
+				ret = do_mmap_shared_file(vma);
+				if (ret < 0) {
+					vma->vm_region = NULL;
+					vma->vm_start = 0;
+					vma->vm_end = 0;
+					atomic_dec(&pregion->vm_usage);
+					pregion = NULL;
+					goto error_just_free;
+				}
+			}
+			fput(region->vm_file);
+			kmem_cache_free(vm_region_jar, region);
+			region = pregion;
+			result = start;
+			goto share;
 		}
 
-	dont_share_VMAs:
-		vma = NULL;
-
 		/* obtain the address at which to make a shared mapping
 		 * - this is the hook for quasi-memory character devices to
 		 *   tell us the location of a shared mapping
@@ -995,113 +1316,93 @@ unsigned long do_mmap_pgoff(struct file *file,
 			if (IS_ERR((void *) addr)) {
 				ret = addr;
 				if (ret != (unsigned long) -ENOSYS)
-					goto error;
+					goto error_just_free;
 
 				/* the driver refused to tell us where to site
 				 * the mapping so we'll have to attempt to copy
 				 * it */
 				ret = (unsigned long) -ENODEV;
 				if (!(capabilities & BDI_CAP_MAP_COPY))
-					goto error;
+					goto error_just_free;
 
 				capabilities &= ~BDI_CAP_MAP_DIRECT;
+			} else {
+				vma->vm_start = region->vm_start = addr;
+				vma->vm_end = region->vm_end = addr + len;
 			}
 		}
 	}
 
-	/* we're going to need a VMA struct as well */
-	vma = kzalloc(sizeof(struct vm_area_struct), GFP_KERNEL);
-	if (!vma)
-		goto error_getting_vma;
-
-	INIT_LIST_HEAD(&vma->anon_vma_node);
-	atomic_set(&vma->vm_usage, 1);
-	if (file) {
-		get_file(file);
-		if (vm_flags & VM_EXECUTABLE) {
-			added_exe_file_vma(current->mm);
-			vma->vm_mm = current->mm;
-		}
-	}
-	vma->vm_file	= file;
-	vma->vm_flags	= vm_flags;
-	vma->vm_start	= addr;
-	vma->vm_end	= addr + len;
-	vma->vm_pgoff	= pgoff;
-
-	vml->vma = vma;
+	vma->vm_region = region;
 
 	/* set up the mapping */
 	if (file && vma->vm_flags & VM_SHARED)
-		ret = do_mmap_shared_file(vma, len);
+		ret = do_mmap_shared_file(vma);
 	else
-		ret = do_mmap_private(vma, len);
+		ret = do_mmap_private(vma, region, len);
 	if (ret < 0)
-		goto error;
-
-	/* okay... we have a mapping; now we have to register it */
-	result = (void *) vma->vm_start;
+		goto error_put_region;
 
-	if (vma->vm_flags & VM_MAPPED_COPY) {
-		realalloc += kobjsize(result);
-		askedalloc += len;
-	}
+	add_nommu_region(region);
 
-	realalloc += kobjsize(vma);
-	askedalloc += sizeof(*vma);
+	/* okay... we have a mapping; now we have to register it */
+	result = vma->vm_start;
 
 	current->mm->total_vm += len >> PAGE_SHIFT;
 
-	add_nommu_vma(vma);
-
- shared:
-	realalloc += kobjsize(vml);
-	askedalloc += sizeof(*vml);
+share:
+	add_vma_to_mm(current->mm, vma);
 
-	add_vma_to_mm(current->mm, vml);
-
-	up_write(&nommu_vma_sem);
+	up_write(&nommu_region_sem);
 
 	if (prot & PROT_EXEC)
-		flush_icache_range((unsigned long) result,
-				   (unsigned long) result + len);
+		flush_icache_range(result, result + len);
 
-#ifdef DEBUG
-	printk("do_mmap:\n");
-	show_process_blocks();
-#endif
+	kleave(" = %lx", result);
+	return result;
 
-	return (unsigned long) result;
-
- error:
-	up_write(&nommu_vma_sem);
-	kfree(vml);
+error_put_region:
+	__put_nommu_region(region);
 	if (vma) {
 		if (vma->vm_file) {
 			fput(vma->vm_file);
 			if (vma->vm_flags & VM_EXECUTABLE)
 				removed_exe_file_vma(vma->vm_mm);
 		}
-		kfree(vma);
+		kmem_cache_free(vm_area_cachep, vma);
 	}
+	kleave(" = %d [pr]", ret);
 	return ret;
 
- sharing_violation:
-	up_write(&nommu_vma_sem);
-	printk("Attempt to share mismatched mappings\n");
-	kfree(vml);
-	return -EINVAL;
+error_just_free:
+	up_write(&nommu_region_sem);
+error:
+	fput(region->vm_file);
+	kmem_cache_free(vm_region_jar, region);
+	fput(vma->vm_file);
+	if (vma->vm_flags & VM_EXECUTABLE)
+		removed_exe_file_vma(vma->vm_mm);
+	kmem_cache_free(vm_area_cachep, vma);
+	kleave(" = %d", ret);
+	return ret;
 
- error_getting_vma:
-	up_write(&nommu_vma_sem);
-	kfree(vml);
-	printk("Allocation of vma for %lu byte allocation from process %d failed\n",
+sharing_violation:
+	up_write(&nommu_region_sem);
+	printk(KERN_WARNING "Attempt to share mismatched mappings\n");
+	ret = -EINVAL;
+	goto error;
+
+error_getting_vma:
+	kmem_cache_free(vm_region_jar, region);
+	printk(KERN_WARNING "Allocation of vma for %lu byte allocation"
+	       " from process %d failed\n",
 	       len, current->pid);
 	show_free_areas();
 	return -ENOMEM;
 
- error_getting_vml:
-	printk("Allocation of vml for %lu byte allocation from process %d failed\n",
+error_getting_region:
+	printk(KERN_WARNING "Allocation of vm region for %lu byte allocation"
+	       " from process %d failed\n",
 	       len, current->pid);
 	show_free_areas();
 	return -ENOMEM;
@@ -1109,90 +1410,188 @@ unsigned long do_mmap_pgoff(struct file *file,
 EXPORT_SYMBOL(do_mmap_pgoff);
 
 /*
- * handle mapping disposal for uClinux
+ * split a vma into two pieces at address 'addr', a new vma is allocated either
+ * for the first part or the tail.
  */
-static void put_vma(struct mm_struct *mm, struct vm_area_struct *vma)
+int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
+	      unsigned long addr, int new_below)
 {
-	if (vma) {
-		down_write(&nommu_vma_sem);
+	struct vm_area_struct *new;
+	struct vm_region *region;
+	unsigned long npages;
 
-		if (atomic_dec_and_test(&vma->vm_usage)) {
-			delete_nommu_vma(vma);
+	kenter("");
 
-			if (vma->vm_ops && vma->vm_ops->close)
-				vma->vm_ops->close(vma);
+	/* we're only permitted to split anonymous regions that have a single
+	 * owner */
+	if (vma->vm_file ||
+	    atomic_read(&vma->vm_region->vm_usage) != 1)
+		return -ENOMEM;
 
-			/* IO memory and memory shared directly out of the pagecache from
-			 * ramfs/tmpfs mustn't be released here */
-			if (vma->vm_flags & VM_MAPPED_COPY) {
-				realalloc -= kobjsize((void *) vma->vm_start);
-				askedalloc -= vma->vm_end - vma->vm_start;
-				kfree((void *) vma->vm_start);
-			}
+	if (mm->map_count >= sysctl_max_map_count)
+		return -ENOMEM;
 
-			realalloc -= kobjsize(vma);
-			askedalloc -= sizeof(*vma);
+	region = kmem_cache_alloc(vm_region_jar, GFP_KERNEL);
+	if (!region)
+		return -ENOMEM;
 
-			if (vma->vm_file) {
-				fput(vma->vm_file);
-				if (vma->vm_flags & VM_EXECUTABLE)
-					removed_exe_file_vma(mm);
-			}
-			kfree(vma);
-		}
+	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+	if (!new) {
+		kmem_cache_free(vm_region_jar, region);
+		return -ENOMEM;
+	}
+
+	/* most fields are the same, copy all, and then fixup */
+	*new = *vma;
+	*region = *vma->vm_region;
+	new->vm_region = region;
+
+	npages = (addr - vma->vm_start) >> PAGE_SHIFT;
 
-		up_write(&nommu_vma_sem);
+	if (new_below) {
+		region->vm_top = region->vm_end = new->vm_end = addr;
+	} else {
+		region->vm_start = new->vm_start = addr;
+		region->vm_pgoff = new->vm_pgoff += npages;
 	}
+
+	if (new->vm_ops && new->vm_ops->open)
+		new->vm_ops->open(new);
+
+	delete_vma_from_mm(vma);
+	down_write(&nommu_region_sem);
+	delete_nommu_region(vma->vm_region);
+	if (new_below) {
+		vma->vm_region->vm_start = vma->vm_start = addr;
+		vma->vm_region->vm_pgoff = vma->vm_pgoff += npages;
+	} else {
+		vma->vm_region->vm_end = vma->vm_end = addr;
+		vma->vm_region->vm_top = addr;
+	}
+	add_nommu_region(vma->vm_region);
+	add_nommu_region(new->vm_region);
+	up_write(&nommu_region_sem);
+	add_vma_to_mm(mm, vma);
+	add_vma_to_mm(mm, new);
+	return 0;
 }
 
 /*
- * release a mapping
- * - under NOMMU conditions the parameters must match exactly to the mapping to
- *   be removed
+ * shrink a VMA by removing the specified chunk from either the beginning or
+ * the end
  */
-int do_munmap(struct mm_struct *mm, unsigned long addr, size_t len)
+static int shrink_vma(struct mm_struct *mm,
+		      struct vm_area_struct *vma,
+		      unsigned long from, unsigned long to)
 {
-	struct vm_list_struct *vml, **parent;
-	unsigned long end = addr + len;
+	struct vm_region *region;
 
-#ifdef DEBUG
-	printk("do_munmap:\n");
-#endif
+	kenter("");
 
-	for (parent = &mm->context.vmlist; *parent; parent = &(*parent)->next) {
-		if ((*parent)->vma->vm_start > addr)
-			break;
-		if ((*parent)->vma->vm_start == addr &&
-		    ((len == 0) || ((*parent)->vma->vm_end == end)))
-			goto found;
+	/* adjust the VMA's pointers, which may reposition it in the MM's tree
+	 * and list */
+	delete_vma_from_mm(vma);
+	if (from > vma->vm_start)
+		vma->vm_end = from;
+	else
+		vma->vm_start = to;
+	add_vma_to_mm(mm, vma);
+
+	/* cut the backing region down to size */
+	region = vma->vm_region;
+	BUG_ON(atomic_read(&region->vm_usage) != 1);
+
+	down_write(&nommu_region_sem);
+	delete_nommu_region(region);
+	if (from > region->vm_start) {
+		to = region->vm_top;
+		region->vm_top = region->vm_end = from;
+	} else {
+		region->vm_start = to;
 	}
+	add_nommu_region(region);
+	up_write(&nommu_region_sem);
 
-	printk("munmap of non-mmaped memory by process %d (%s): %p\n",
-	       current->pid, current->comm, (void *) addr);
-	return -EINVAL;
+	free_page_series(from, to);
+	return 0;
+}
 
- found:
-	vml = *parent;
+/*
+ * release a mapping
+ * - under NOMMU conditions the chunk to be unmapped must be backed by a single
+ *   VMA, though it need not cover the whole VMA
+ */
+int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
+{
+	struct vm_area_struct *vma;
+	struct rb_node *rb;
+	unsigned long end = start + len;
+	int ret;
 
-	put_vma(mm, vml->vma);
+	kenter(",%lx,%zx", start, len);
 
-	*parent = vml->next;
-	realalloc -= kobjsize(vml);
-	askedalloc -= sizeof(*vml);
-	kfree(vml);
+	if (len == 0)
+		return -EINVAL;
 
-	update_hiwater_vm(mm);
-	mm->total_vm -= len >> PAGE_SHIFT;
+	/* find the first potentially overlapping VMA */
+	vma = find_vma(mm, start);
+	if (!vma) {
+		printk(KERN_WARNING
+		       "munmap of memory not mmapped by process %d (%s):"
+		       " 0x%lx-0x%lx\n",
+		       current->pid, current->comm, start, start + len - 1);
+		return -EINVAL;
+	}
 
-#ifdef DEBUG
-	show_process_blocks();
-#endif
+	/* we're allowed to split an anonymous VMA but not a file-backed one */
+	if (vma->vm_file) {
+		do {
+			if (start > vma->vm_start) {
+				kleave(" = -EINVAL [miss]");
+				return -EINVAL;
+			}
+			if (end == vma->vm_end)
+				goto erase_whole_vma;
+			rb = rb_next(&vma->vm_rb);
+			vma = rb_entry(rb, struct vm_area_struct, vm_rb);
+		} while (rb);
+		kleave(" = -EINVAL [split file]");
+		return -EINVAL;
+	} else {
+		/* the chunk must be a subset of the VMA found */
+		if (start == vma->vm_start && end == vma->vm_end)
+			goto erase_whole_vma;
+		if (start < vma->vm_start || end > vma->vm_end) {
+			kleave(" = -EINVAL [superset]");
+			return -EINVAL;
+		}
+		if (start & ~PAGE_MASK) {
+			kleave(" = -EINVAL [unaligned start]");
+			return -EINVAL;
+		}
+		if (end != vma->vm_end && end & ~PAGE_MASK) {
+			kleave(" = -EINVAL [unaligned split]");
+			return -EINVAL;
+		}
+		if (start != vma->vm_start && end != vma->vm_end) {
+			ret = split_vma(mm, vma, start, 1);
+			if (ret < 0) {
+				kleave(" = %d [split]", ret);
+				return ret;
+			}
+		}
+		return shrink_vma(mm, vma, start, end);
+	}
 
+erase_whole_vma:
+	delete_vma_from_mm(vma);
+	delete_vma(mm, vma);
+	kleave(" = 0");
 	return 0;
 }
 EXPORT_SYMBOL(do_munmap);
 
-asmlinkage long sys_munmap(unsigned long addr, size_t len)
+SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
 {
 	int ret;
 	struct mm_struct *mm = current->mm;
@@ -1204,32 +1603,26 @@ asmlinkage long sys_munmap(unsigned long addr, size_t len)
 }
 
 /*
- * Release all mappings
+ * release all the mappings made in a process's VM space
  */
-void exit_mmap(struct mm_struct * mm)
+void exit_mmap(struct mm_struct *mm)
 {
-	struct vm_list_struct *tmp;
-
-	if (mm) {
-#ifdef DEBUG
-		printk("Exit_mmap:\n");
-#endif
+	struct vm_area_struct *vma;
 
-		mm->total_vm = 0;
+	if (!mm)
+		return;
 
-		while ((tmp = mm->context.vmlist)) {
-			mm->context.vmlist = tmp->next;
-			put_vma(mm, tmp->vma);
+	kenter("");
 
-			realalloc -= kobjsize(tmp);
-			askedalloc -= sizeof(*tmp);
-			kfree(tmp);
-		}
+	mm->total_vm = 0;
 
-#ifdef DEBUG
-		show_process_blocks();
-#endif
+	while ((vma = mm->mmap)) {
+		mm->mmap = vma->vm_next;
+		delete_vma_from_mm(vma);
+		delete_vma(mm, vma);
 	}
+
+	kleave("");
 }
 
 unsigned long do_brk(unsigned long addr, unsigned long len)
@@ -1242,8 +1635,8 @@ unsigned long do_brk(unsigned long addr, unsigned long len)
  * time (controlled by the MREMAP_MAYMOVE flag and available VM space)
  *
  * under NOMMU conditions, we only permit changing a mapping's size, and only
- * as long as it stays within the hole allocated by the kmalloc() call in
- * do_mmap_pgoff() and the block is not shareable
+ * as long as it stays within the region allocated by do_mmap_private() and the
+ * block is not shareable
  *
  * MREMAP_FIXED is not supported under NOMMU conditions
  */
@@ -1254,13 +1647,16 @@ unsigned long do_mremap(unsigned long addr,
 	struct vm_area_struct *vma;
 
 	/* insanity checks first */
-	if (new_len == 0)
+	if (old_len == 0 || new_len == 0)
 		return (unsigned long) -EINVAL;
 
+	if (addr & ~PAGE_MASK)
+		return -EINVAL;
+
 	if (flags & MREMAP_FIXED && new_addr != addr)
 		return (unsigned long) -EINVAL;
 
-	vma = find_vma_exact(current->mm, addr);
+	vma = find_vma_exact(current->mm, addr, old_len);
 	if (!vma)
 		return (unsigned long) -EINVAL;
 
@@ -1270,22 +1666,18 @@ unsigned long do_mremap(unsigned long addr,
 	if (vma->vm_flags & VM_MAYSHARE)
 		return (unsigned long) -EPERM;
 
-	if (new_len > kobjsize((void *) addr))
+	if (new_len > vma->vm_region->vm_end - vma->vm_region->vm_start)
 		return (unsigned long) -ENOMEM;
 
 	/* all checks complete - do it */
 	vma->vm_end = vma->vm_start + new_len;
-
-	askedalloc -= old_len;
-	askedalloc += new_len;
-
 	return vma->vm_start;
 }
 EXPORT_SYMBOL(do_mremap);
 
-asmlinkage unsigned long sys_mremap(unsigned long addr,
-	unsigned long old_len, unsigned long new_len,
-	unsigned long flags, unsigned long new_addr)
+SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
+		unsigned long, new_len, unsigned long, flags,
+		unsigned long, new_addr)
 {
 	unsigned long ret;
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 558f9afe6e4e..40ba05061a4f 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -31,7 +31,7 @@
 int sysctl_panic_on_oom;
 int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks;
-static DEFINE_SPINLOCK(zone_scan_mutex);
+static DEFINE_SPINLOCK(zone_scan_lock);
 /* #define DEBUG */
 
 /**
@@ -392,6 +392,9 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 		printk(KERN_WARNING "%s invoked oom-killer: "
 			"gfp_mask=0x%x, order=%d, oomkilladj=%d\n",
 			current->comm, gfp_mask, order, current->oomkilladj);
+		task_lock(current);
+		cpuset_print_task_mems_allowed(current);
+		task_unlock(current);
 		dump_stack();
 		show_mem();
 		if (sysctl_oom_dump_tasks)
@@ -426,7 +429,6 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask)
 	unsigned long points = 0;
 	struct task_struct *p;
 
-	cgroup_lock();
 	read_lock(&tasklist_lock);
 retry:
 	p = select_bad_process(&points, mem);
@@ -441,7 +443,6 @@ retry:
 		goto retry;
 out:
 	read_unlock(&tasklist_lock);
-	cgroup_unlock();
 }
 #endif
 
@@ -470,7 +471,7 @@ int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 	struct zone *zone;
 	int ret = 1;
 
-	spin_lock(&zone_scan_mutex);
+	spin_lock(&zone_scan_lock);
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
 		if (zone_is_oom_locked(zone)) {
 			ret = 0;
@@ -480,7 +481,7 @@ int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
 		/*
-		 * Lock each zone in the zonelist under zone_scan_mutex so a
+		 * Lock each zone in the zonelist under zone_scan_lock so a
 		 * parallel invocation of try_set_zone_oom() doesn't succeed
 		 * when it shouldn't.
 		 */
@@ -488,7 +489,7 @@ int try_set_zone_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 	}
 
 out:
-	spin_unlock(&zone_scan_mutex);
+	spin_unlock(&zone_scan_lock);
 	return ret;
 }
 
@@ -502,11 +503,82 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
 	struct zoneref *z;
 	struct zone *zone;
 
-	spin_lock(&zone_scan_mutex);
+	spin_lock(&zone_scan_lock);
 	for_each_zone_zonelist(zone, z, zonelist, gfp_zone(gfp_mask)) {
 		zone_clear_flag(zone, ZONE_OOM_LOCKED);
 	}
-	spin_unlock(&zone_scan_mutex);
+	spin_unlock(&zone_scan_lock);
+}
+
+/*
+ * Must be called with tasklist_lock held for read.
+ */
+static void __out_of_memory(gfp_t gfp_mask, int order)
+{
+	if (sysctl_oom_kill_allocating_task) {
+		oom_kill_process(current, gfp_mask, order, 0, NULL,
+				"Out of memory (oom_kill_allocating_task)");
+
+	} else {
+		unsigned long points;
+		struct task_struct *p;
+
+retry:
+		/*
+		 * Rambo mode: Shoot down a process and hope it solves whatever
+		 * issues we may have.
+		 */
+		p = select_bad_process(&points, NULL);
+
+		if (PTR_ERR(p) == -1UL)
+			return;
+
+		/* Found nothing?!?! Either we hang forever, or we panic. */
+		if (!p) {
+			read_unlock(&tasklist_lock);
+			panic("Out of memory and no killable processes...\n");
+		}
+
+		if (oom_kill_process(p, gfp_mask, order, points, NULL,
+				     "Out of memory"))
+			goto retry;
+	}
+}
+
+/*
+ * pagefault handler calls into here because it is out of memory but
+ * doesn't know exactly how or why.
+ */
+void pagefault_out_of_memory(void)
+{
+	unsigned long freed = 0;
+
+	blocking_notifier_call_chain(&oom_notify_list, 0, &freed);
+	if (freed > 0)
+		/* Got some memory back in the last second. */
+		return;
+
+	/*
+	 * If this is from memcg, oom-killer is already invoked.
+	 * and not worth to go system-wide-oom.
+	 */
+	if (mem_cgroup_oom_called(current))
+		goto rest_and_return;
+
+	if (sysctl_panic_on_oom)
+		panic("out of memory from page fault. panic_on_oom is selected.\n");
+
+	read_lock(&tasklist_lock);
+	__out_of_memory(0, 0); /* unknown gfp_mask and order */
+	read_unlock(&tasklist_lock);
+
+	/*
+	 * Give "p" a good chance of killing itself before we
+	 * retry to allocate memory.
+	 */
+rest_and_return:
+	if (!test_thread_flag(TIF_MEMDIE))
+		schedule_timeout_uninterruptible(1);
 }
 
 /**
@@ -522,8 +594,6 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
  */
 void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 {
-	struct task_struct *p;
-	unsigned long points = 0;
 	unsigned long freed = 0;
 	enum oom_constraint constraint;
 
@@ -544,7 +614,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 
 	switch (constraint) {
 	case CONSTRAINT_MEMORY_POLICY:
-		oom_kill_process(current, gfp_mask, order, points, NULL,
+		oom_kill_process(current, gfp_mask, order, 0, NULL,
 				"No available memory (MPOL_BIND)");
 		break;
 
@@ -553,35 +623,10 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order)
 			panic("out of memory. panic_on_oom is selected\n");
 		/* Fall-through */
 	case CONSTRAINT_CPUSET:
-		if (sysctl_oom_kill_allocating_task) {
-			oom_kill_process(current, gfp_mask, order, points, NULL,
-					"Out of memory (oom_kill_allocating_task)");
-			break;
-		}
-retry:
-		/*
-		 * Rambo mode: Shoot down a process and hope it solves whatever
-		 * issues we may have.
-		 */
-		p = select_bad_process(&points, NULL);
-
-		if (PTR_ERR(p) == -1UL)
-			goto out;
-
-		/* Found nothing?!?! Either we hang forever, or we panic. */
-		if (!p) {
-			read_unlock(&tasklist_lock);
-			panic("Out of memory and no killable processes...\n");
-		}
-
-		if (oom_kill_process(p, gfp_mask, order, points, NULL,
-				     "Out of memory"))
-			goto retry;
-
+		__out_of_memory(gfp_mask, order);
 		break;
 	}
 
-out:
 	read_unlock(&tasklist_lock);
 
 	/*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 2970e35fd03f..dc32dae01e5f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -69,6 +69,12 @@ static inline long sync_writeback_pages(void)
 int dirty_background_ratio = 5;
 
 /*
+ * dirty_background_bytes starts at 0 (disabled) so that it is a function of
+ * dirty_background_ratio * the amount of dirtyable memory
+ */
+unsigned long dirty_background_bytes;
+
+/*
  * free highmem will not be subtracted from the total free memory
  * for calculating free ratios if vm_highmem_is_dirtyable is true
  */
@@ -80,6 +86,12 @@ int vm_highmem_is_dirtyable;
 int vm_dirty_ratio = 10;
 
 /*
+ * vm_dirty_bytes starts at 0 (disabled) so that it is a function of
+ * vm_dirty_ratio * the amount of dirtyable memory
+ */
+unsigned long vm_dirty_bytes;
+
+/*
  * The interval between `kupdate'-style writebacks, in jiffies
  */
 int dirty_writeback_interval = 5 * HZ;
@@ -135,23 +147,75 @@ static int calc_period_shift(void)
 {
 	unsigned long dirty_total;
 
-	dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) / 100;
+	if (vm_dirty_bytes)
+		dirty_total = vm_dirty_bytes / PAGE_SIZE;
+	else
+		dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
+				100;
 	return 2 + ilog2(dirty_total - 1);
 }
 
 /*
- * update the period when the dirty ratio changes.
+ * update the period when the dirty threshold changes.
  */
+static void update_completion_period(void)
+{
+	int shift = calc_period_shift();
+	prop_change_shift(&vm_completions, shift);
+	prop_change_shift(&vm_dirties, shift);
+}
+
+int dirty_background_ratio_handler(struct ctl_table *table, int write,
+		struct file *filp, void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		dirty_background_bytes = 0;
+	return ret;
+}
+
+int dirty_background_bytes_handler(struct ctl_table *table, int write,
+		struct file *filp, void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+	if (ret == 0 && write)
+		dirty_background_ratio = 0;
+	return ret;
+}
+
 int dirty_ratio_handler(struct ctl_table *table, int write,
 		struct file *filp, void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int old_ratio = vm_dirty_ratio;
-	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
 	if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
-		int shift = calc_period_shift();
-		prop_change_shift(&vm_completions, shift);
-		prop_change_shift(&vm_dirties, shift);
+		update_completion_period();
+		vm_dirty_bytes = 0;
+	}
+	return ret;
+}
+
+
+int dirty_bytes_handler(struct ctl_table *table, int write,
+		struct file *filp, void __user *buffer, size_t *lenp,
+		loff_t *ppos)
+{
+	int old_bytes = vm_dirty_bytes;
+	int ret;
+
+	ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+	if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
+		update_completion_period();
+		vm_dirty_ratio = 0;
 	}
 	return ret;
 }
@@ -362,26 +426,32 @@ unsigned long determine_dirtyable_memory(void)
 }
 
 void
-get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
-		 struct backing_dev_info *bdi)
+get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
+		 unsigned long *pbdi_dirty, struct backing_dev_info *bdi)
 {
-	int background_ratio;		/* Percentages */
-	int dirty_ratio;
-	long background;
-	long dirty;
+	unsigned long background;
+	unsigned long dirty;
 	unsigned long available_memory = determine_dirtyable_memory();
 	struct task_struct *tsk;
 
-	dirty_ratio = vm_dirty_ratio;
-	if (dirty_ratio < 5)
-		dirty_ratio = 5;
+	if (vm_dirty_bytes)
+		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
+	else {
+		int dirty_ratio;
+
+		dirty_ratio = vm_dirty_ratio;
+		if (dirty_ratio < 5)
+			dirty_ratio = 5;
+		dirty = (dirty_ratio * available_memory) / 100;
+	}
 
-	background_ratio = dirty_background_ratio;
-	if (background_ratio >= dirty_ratio)
-		background_ratio = dirty_ratio / 2;
+	if (dirty_background_bytes)
+		background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
+	else
+		background = (dirty_background_ratio * available_memory) / 100;
 
-	background = (background_ratio * available_memory) / 100;
-	dirty = (dirty_ratio * available_memory) / 100;
+	if (background >= dirty)
+		background = dirty / 2;
 	tsk = current;
 	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
 		background += background / 4;
@@ -423,9 +493,9 @@ static void balance_dirty_pages(struct address_space *mapping)
 {
 	long nr_reclaimable, bdi_nr_reclaimable;
 	long nr_writeback, bdi_nr_writeback;
-	long background_thresh;
-	long dirty_thresh;
-	long bdi_thresh;
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
+	unsigned long bdi_thresh;
 	unsigned long pages_written = 0;
 	unsigned long write_chunk = sync_writeback_pages();
 
@@ -580,8 +650,8 @@ EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
 void throttle_vm_writeout(gfp_t gfp_mask)
 {
-	long background_thresh;
-	long dirty_thresh;
+	unsigned long background_thresh;
+	unsigned long dirty_thresh;
 
         for ( ; ; ) {
 		get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
@@ -624,8 +694,8 @@ static void background_writeout(unsigned long _min_pages)
 	};
 
 	for ( ; ; ) {
-		long background_thresh;
-		long dirty_thresh;
+		unsigned long background_thresh;
+		unsigned long dirty_thresh;
 
 		get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL);
 		if (global_page_state(NR_FILE_DIRTY) +
@@ -868,9 +938,11 @@ int write_cache_pages(struct address_space *mapping,
 	int done = 0;
 	struct pagevec pvec;
 	int nr_pages;
+	pgoff_t uninitialized_var(writeback_index);
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
-	int scanned = 0;
+	pgoff_t done_index;
+	int cycled;
 	int range_whole = 0;
 	long nr_to_write = wbc->nr_to_write;
 
@@ -881,83 +953,143 @@ int write_cache_pages(struct address_space *mapping,
 
 	pagevec_init(&pvec, 0);
 	if (wbc->range_cyclic) {
-		index = mapping->writeback_index; /* Start from prev offset */
+		writeback_index = mapping->writeback_index; /* prev offset */
+		index = writeback_index;
+		if (index == 0)
+			cycled = 1;
+		else
+			cycled = 0;
 		end = -1;
 	} else {
 		index = wbc->range_start >> PAGE_CACHE_SHIFT;
 		end = wbc->range_end >> PAGE_CACHE_SHIFT;
 		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
 			range_whole = 1;
-		scanned = 1;
+		cycled = 1; /* ignore range_cyclic tests */
 	}
 retry:
-	while (!done && (index <= end) &&
-	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
-					      PAGECACHE_TAG_DIRTY,
-					      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1))) {
-		unsigned i;
+	done_index = index;
+	while (!done && (index <= end)) {
+		int i;
+
+		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
+			      PAGECACHE_TAG_DIRTY,
+			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
+		if (nr_pages == 0)
+			break;
 
-		scanned = 1;
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 
 			/*
-			 * At this point we hold neither mapping->tree_lock nor
-			 * lock on the page itself: the page may be truncated or
-			 * invalidated (changing page->mapping to NULL), or even
-			 * swizzled back from swapper_space to tmpfs file
-			 * mapping
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping. However, page->index will not change
+			 * because we have a reference on the page.
 			 */
+			if (page->index > end) {
+				/*
+				 * can't be range_cyclic (1st pass) because
+				 * end == -1 in that case.
+				 */
+				done = 1;
+				break;
+			}
+
+			done_index = page->index + 1;
+
 			lock_page(page);
 
+			/*
+			 * Page truncated or invalidated. We can freely skip it
+			 * then, even for data integrity operations: the page
+			 * has disappeared concurrently, so there could be no
+			 * real expectation of this data interity operation
+			 * even if there is now a new, dirty page at the same
+			 * pagecache address.
+			 */
 			if (unlikely(page->mapping != mapping)) {
+continue_unlock:
 				unlock_page(page);
 				continue;
 			}
 
-			if (!wbc->range_cyclic && page->index > end) {
-				done = 1;
-				unlock_page(page);
-				continue;
+			if (!PageDirty(page)) {
+				/* someone wrote it for us */
+				goto continue_unlock;
 			}
 
-			if (wbc->sync_mode != WB_SYNC_NONE)
-				wait_on_page_writeback(page);
-
-			if (PageWriteback(page) ||
-			    !clear_page_dirty_for_io(page)) {
-				unlock_page(page);
-				continue;
+			if (PageWriteback(page)) {
+				if (wbc->sync_mode != WB_SYNC_NONE)
+					wait_on_page_writeback(page);
+				else
+					goto continue_unlock;
 			}
 
-			ret = (*writepage)(page, wbc, data);
+			BUG_ON(PageWriteback(page));
+			if (!clear_page_dirty_for_io(page))
+				goto continue_unlock;
 
-			if (unlikely(ret == AOP_WRITEPAGE_ACTIVATE)) {
-				unlock_page(page);
-				ret = 0;
-			}
-			if (ret || (--nr_to_write <= 0))
+			ret = (*writepage)(page, wbc, data);
+			if (unlikely(ret)) {
+				if (ret == AOP_WRITEPAGE_ACTIVATE) {
+					unlock_page(page);
+					ret = 0;
+				} else {
+					/*
+					 * done_index is set past this page,
+					 * so media errors will not choke
+					 * background writeout for the entire
+					 * file. This has consequences for
+					 * range_cyclic semantics (ie. it may
+					 * not be suitable for data integrity
+					 * writeout).
+					 */
+					done = 1;
+					break;
+				}
+ 			}
+
+			if (nr_to_write > 0)
+				nr_to_write--;
+			else if (wbc->sync_mode == WB_SYNC_NONE) {
+				/*
+				 * We stop writing back only if we are not
+				 * doing integrity sync. In case of integrity
+				 * sync we have to keep going because someone
+				 * may be concurrently dirtying pages, and we
+				 * might have synced a lot of newly appeared
+				 * dirty pages, but have not synced all of the
+				 * old dirty pages.
+				 */
 				done = 1;
+				break;
+			}
+
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
 				done = 1;
+				break;
 			}
 		}
 		pagevec_release(&pvec);
 		cond_resched();
 	}
-	if (!scanned && !done) {
+	if (!cycled) {
 		/*
+		 * range_cyclic:
 		 * We hit the last page and there is more work to be done: wrap
 		 * back to the start of the file
 		 */
-		scanned = 1;
+		cycled = 1;
 		index = 0;
+		end = writeback_index - 1;
 		goto retry;
 	}
 	if (!wbc->no_nrwrite_index_update) {
 		if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
-			mapping->writeback_index = index;
+			mapping->writeback_index = done_index;
 		wbc->nr_to_write = nr_to_write;
 	}
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index d8ac01474563..5675b3073854 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -69,7 +69,7 @@ EXPORT_SYMBOL(node_states);
 
 unsigned long totalram_pages __read_mostly;
 unsigned long totalreserve_pages __read_mostly;
-long nr_swap_pages;
+unsigned long highest_memmap_pfn __read_mostly;
 int percpu_pagelist_fraction;
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -223,19 +223,41 @@ static inline int bad_range(struct zone *zone, struct page *page)
 
 static void bad_page(struct page *page)
 {
-	printk(KERN_EMERG "Bad page state in process '%s'\n" KERN_EMERG
-		"page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
-		current->comm, page, (int)(2*sizeof(unsigned long)),
-		(unsigned long)page->flags, page->mapping,
-		page_mapcount(page), page_count(page));
+	static unsigned long resume;
+	static unsigned long nr_shown;
+	static unsigned long nr_unshown;
+
+	/*
+	 * Allow a burst of 60 reports, then keep quiet for that minute;
+	 * or allow a steady drip of one report per second.
+	 */
+	if (nr_shown == 60) {
+		if (time_before(jiffies, resume)) {
+			nr_unshown++;
+			goto out;
+		}
+		if (nr_unshown) {
+			printk(KERN_ALERT
+			      "BUG: Bad page state: %lu messages suppressed\n",
+				nr_unshown);
+			nr_unshown = 0;
+		}
+		nr_shown = 0;
+	}
+	if (nr_shown++ == 0)
+		resume = jiffies + 60 * HZ;
+
+	printk(KERN_ALERT "BUG: Bad page state in process %s  pfn:%05lx\n",
+		current->comm, page_to_pfn(page));
+	printk(KERN_ALERT
+		"page:%p flags:%p count:%d mapcount:%d mapping:%p index:%lx\n",
+		page, (void *)page->flags, page_count(page),
+		page_mapcount(page), page->mapping, page->index);
 
-	printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
-		KERN_EMERG "Backtrace:\n");
 	dump_stack();
-	page->flags &= ~PAGE_FLAGS_CLEAR_WHEN_BAD;
-	set_page_count(page, 0);
-	reset_page_mapcount(page);
-	page->mapping = NULL;
+out:
+	/* Leave bad fields for debug, except PageBuddy could make trouble */
+	__ClearPageBuddy(page);
 	add_taint(TAINT_BAD_PAGE);
 }
 
@@ -292,25 +314,31 @@ void prep_compound_gigantic_page(struct page *page, unsigned long order)
 }
 #endif
 
-static void destroy_compound_page(struct page *page, unsigned long order)
+static int destroy_compound_page(struct page *page, unsigned long order)
 {
 	int i;
 	int nr_pages = 1 << order;
+	int bad = 0;
 
-	if (unlikely(compound_order(page) != order))
+	if (unlikely(compound_order(page) != order) ||
+	    unlikely(!PageHead(page))) {
 		bad_page(page);
+		bad++;
+	}
 
-	if (unlikely(!PageHead(page)))
-			bad_page(page);
 	__ClearPageHead(page);
+
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 
-		if (unlikely(!PageTail(p) |
-				(p->first_page != page)))
+		if (unlikely(!PageTail(p) | (p->first_page != page))) {
 			bad_page(page);
+			bad++;
+		}
 		__ClearPageTail(p);
 	}
+
+	return bad;
 }
 
 static inline void prep_zero_page(struct page *page, int order, gfp_t gfp_flags)
@@ -430,7 +458,8 @@ static inline void __free_one_page(struct page *page,
 	int migratetype = get_pageblock_migratetype(page);
 
 	if (unlikely(PageCompound(page)))
-		destroy_compound_page(page, order);
+		if (unlikely(destroy_compound_page(page, order)))
+			return;
 
 	page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1);
 
@@ -467,18 +496,13 @@ static inline int free_pages_check(struct page *page)
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
 		(page_count(page) != 0)  |
-		(page->flags & PAGE_FLAGS_CHECK_AT_FREE)))
+		(page->flags & PAGE_FLAGS_CHECK_AT_FREE))) {
 		bad_page(page);
-	if (PageDirty(page))
-		__ClearPageDirty(page);
-	if (PageSwapBacked(page))
-		__ClearPageSwapBacked(page);
-	/*
-	 * For now, we report if PG_reserved was found set, but do not
-	 * clear it, and do not free the page.  But we shall soon need
-	 * to do more, for when the ZERO_PAGE count wraps negative.
-	 */
-	return PageReserved(page);
+		return 1;
+	}
+	if (page->flags & PAGE_FLAGS_CHECK_AT_PREP)
+		page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
+	return 0;
 }
 
 /*
@@ -523,11 +547,11 @@ static void __free_pages_ok(struct page *page, unsigned int order)
 {
 	unsigned long flags;
 	int i;
-	int reserved = 0;
+	int bad = 0;
 
 	for (i = 0 ; i < (1 << order) ; ++i)
-		reserved += free_pages_check(page + i);
-	if (reserved)
+		bad += free_pages_check(page + i);
+	if (bad)
 		return;
 
 	if (!PageHighMem(page)) {
@@ -612,23 +636,11 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
 		(page_count(page) != 0)  |
-		(page->flags & PAGE_FLAGS_CHECK_AT_PREP)))
+		(page->flags & PAGE_FLAGS_CHECK_AT_PREP))) {
 		bad_page(page);
-
-	/*
-	 * For now, we report if PG_reserved was found set, but do not
-	 * clear it, and do not allocate the page: as a safety net.
-	 */
-	if (PageReserved(page))
 		return 1;
+	}
 
-	page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_reclaim |
-			1 << PG_referenced | 1 << PG_arch_1 |
-			1 << PG_owner_priv_1 | 1 << PG_mappedtodisk
-#ifdef CONFIG_UNEVICTABLE_LRU
-			| 1 << PG_mlocked
-#endif
-			);
 	set_page_private(page, 0);
 	set_page_refcounted(page);
 
@@ -2609,6 +2621,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 	unsigned long pfn;
 	struct zone *z;
 
+	if (highest_memmap_pfn < end_pfn - 1)
+		highest_memmap_pfn = end_pfn - 1;
+
 	z = &NODE_DATA(nid)->node_zones[zone];
 	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
 		/*
@@ -3381,10 +3396,8 @@ static void __init setup_usemap(struct pglist_data *pgdat,
 {
 	unsigned long usemapsize = usemap_size(zonesize);
 	zone->pageblock_flags = NULL;
-	if (usemapsize) {
+	if (usemapsize)
 		zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
-		memset(zone->pageblock_flags, 0, usemapsize);
-	}
 }
 #else
 static void inline setup_usemap(struct pglist_data *pgdat,
@@ -3469,9 +3482,10 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			PAGE_ALIGN(size * sizeof(struct page)) >> PAGE_SHIFT;
 		if (realsize >= memmap_pages) {
 			realsize -= memmap_pages;
-			printk(KERN_DEBUG
-				"  %s zone: %lu pages used for memmap\n",
-				zone_names[j], memmap_pages);
+			if (memmap_pages)
+				printk(KERN_DEBUG
+				       "  %s zone: %lu pages used for memmap\n",
+				       zone_names[j], memmap_pages);
 		} else
 			printk(KERN_WARNING
 				"  %s zone: %lu pages exceeds realsize %lu\n",
@@ -3509,10 +3523,10 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			INIT_LIST_HEAD(&zone->lru[l].list);
 			zone->lru[l].nr_scan = 0;
 		}
-		zone->recent_rotated[0] = 0;
-		zone->recent_rotated[1] = 0;
-		zone->recent_scanned[0] = 0;
-		zone->recent_scanned[1] = 0;
+		zone->reclaim_stat.recent_rotated[0] = 0;
+		zone->reclaim_stat.recent_rotated[1] = 0;
+		zone->reclaim_stat.recent_scanned[0] = 0;
+		zone->reclaim_stat.recent_scanned[1] = 0;
 		zap_zone_vm_stats(zone);
 		zone->flags = 0;
 		if (!size)
@@ -4316,7 +4330,7 @@ void setup_per_zone_pages_min(void)
  *    1TB     101        10GB
  *   10TB     320        32GB
  */
-void setup_per_zone_inactive_ratio(void)
+static void setup_per_zone_inactive_ratio(void)
 {
 	struct zone *zone;
 
@@ -4573,19 +4587,6 @@ void *__init alloc_large_system_hash(const char *tablename,
 	return table;
 }
 
-#ifdef CONFIG_OUT_OF_LINE_PFN_TO_PAGE
-struct page *pfn_to_page(unsigned long pfn)
-{
-	return __pfn_to_page(pfn);
-}
-unsigned long page_to_pfn(struct page *page)
-{
-	return __page_to_pfn(page);
-}
-EXPORT_SYMBOL(pfn_to_page);
-EXPORT_SYMBOL(page_to_pfn);
-#endif /* CONFIG_OUT_OF_LINE_PFN_TO_PAGE */
-
 /* Return a pointer to the bitmap storing bits affecting a block of pages */
 static inline unsigned long *get_pageblock_bitmap(struct zone *zone,
 							unsigned long pfn)
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index ab27ff750519..7006a11350c8 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -8,6 +8,7 @@
 #include <linux/memory.h>
 #include <linux/vmalloc.h>
 #include <linux/cgroup.h>
+#include <linux/swapops.h>
 
 static void __meminit
 __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
@@ -15,6 +16,7 @@ __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
 	pc->flags = 0;
 	pc->mem_cgroup = NULL;
 	pc->page = pfn_to_page(pfn);
+	INIT_LIST_HEAD(&pc->lru);
 }
 static unsigned long total_usage;
 
@@ -72,7 +74,7 @@ void __init page_cgroup_init(void)
 
 	int nid, fail;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return;
 
 	for_each_online_node(nid)  {
@@ -101,15 +103,13 @@ struct page_cgroup *lookup_page_cgroup(struct page *page)
 }
 
 /* __alloc_bootmem...() is protected by !slab_available() */
-int __init_refok init_section_page_cgroup(unsigned long pfn)
+static int __init_refok init_section_page_cgroup(unsigned long pfn)
 {
-	struct mem_section *section;
+	struct mem_section *section = __pfn_to_section(pfn);
 	struct page_cgroup *base, *pc;
 	unsigned long table_size;
 	int nid, index;
 
-	section = __pfn_to_section(pfn);
-
 	if (!section->page_cgroup) {
 		nid = page_to_nid(pfn_to_page(pfn));
 		table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
@@ -145,7 +145,6 @@ int __init_refok init_section_page_cgroup(unsigned long pfn)
 		__init_page_cgroup(pc, pfn + index);
 	}
 
-	section = __pfn_to_section(pfn);
 	section->page_cgroup = base - pfn;
 	total_usage += table_size;
 	return 0;
@@ -248,7 +247,7 @@ void __init page_cgroup_init(void)
 	unsigned long pfn;
 	int fail = 0;
 
-	if (mem_cgroup_subsys.disabled)
+	if (mem_cgroup_disabled())
 		return;
 
 	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
@@ -273,3 +272,199 @@ void __meminit pgdat_page_cgroup_init(struct pglist_data *pgdat)
 }
 
 #endif
+
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+
+static DEFINE_MUTEX(swap_cgroup_mutex);
+struct swap_cgroup_ctrl {
+	struct page **map;
+	unsigned long length;
+};
+
+struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
+
+/*
+ * This 8bytes seems big..maybe we can reduce this when we can use "id" for
+ * cgroup rather than pointer.
+ */
+struct swap_cgroup {
+	struct mem_cgroup	*val;
+};
+#define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
+#define SC_POS_MASK	(SC_PER_PAGE - 1)
+
+/*
+ * SwapCgroup implements "lookup" and "exchange" operations.
+ * In typical usage, this swap_cgroup is accessed via memcg's charge/uncharge
+ * against SwapCache. At swap_free(), this is accessed directly from swap.
+ *
+ * This means,
+ *  - we have no race in "exchange" when we're accessed via SwapCache because
+ *    SwapCache(and its swp_entry) is under lock.
+ *  - When called via swap_free(), there is no user of this entry and no race.
+ * Then, we don't need lock around "exchange".
+ *
+ * TODO: we can push these buffers out to HIGHMEM.
+ */
+
+/*
+ * allocate buffer for swap_cgroup.
+ */
+static int swap_cgroup_prepare(int type)
+{
+	struct page *page;
+	struct swap_cgroup_ctrl *ctrl;
+	unsigned long idx, max;
+
+	if (!do_swap_account)
+		return 0;
+	ctrl = &swap_cgroup_ctrl[type];
+
+	for (idx = 0; idx < ctrl->length; idx++) {
+		page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+		if (!page)
+			goto not_enough_page;
+		ctrl->map[idx] = page;
+	}
+	return 0;
+not_enough_page:
+	max = idx;
+	for (idx = 0; idx < max; idx++)
+		__free_page(ctrl->map[idx]);
+
+	return -ENOMEM;
+}
+
+/**
+ * swap_cgroup_record - record mem_cgroup for this swp_entry.
+ * @ent: swap entry to be recorded into
+ * @mem: mem_cgroup to be recorded
+ *
+ * Returns old value at success, NULL at failure.
+ * (Of course, old value can be NULL.)
+ */
+struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+{
+	int type = swp_type(ent);
+	unsigned long offset = swp_offset(ent);
+	unsigned long idx = offset / SC_PER_PAGE;
+	unsigned long pos = offset & SC_POS_MASK;
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+	struct mem_cgroup *old;
+
+	if (!do_swap_account)
+		return NULL;
+
+	ctrl = &swap_cgroup_ctrl[type];
+
+	mappage = ctrl->map[idx];
+	sc = page_address(mappage);
+	sc += pos;
+	old = sc->val;
+	sc->val = mem;
+
+	return old;
+}
+
+/**
+ * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
+ * @ent: swap entry to be looked up.
+ *
+ * Returns pointer to mem_cgroup at success. NULL at failure.
+ */
+struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+{
+	int type = swp_type(ent);
+	unsigned long offset = swp_offset(ent);
+	unsigned long idx = offset / SC_PER_PAGE;
+	unsigned long pos = offset & SC_POS_MASK;
+	struct swap_cgroup_ctrl *ctrl;
+	struct page *mappage;
+	struct swap_cgroup *sc;
+	struct mem_cgroup *ret;
+
+	if (!do_swap_account)
+		return NULL;
+
+	ctrl = &swap_cgroup_ctrl[type];
+	mappage = ctrl->map[idx];
+	sc = page_address(mappage);
+	sc += pos;
+	ret = sc->val;
+	return ret;
+}
+
+int swap_cgroup_swapon(int type, unsigned long max_pages)
+{
+	void *array;
+	unsigned long array_size;
+	unsigned long length;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return 0;
+
+	length = ((max_pages/SC_PER_PAGE) + 1);
+	array_size = length * sizeof(void *);
+
+	array = vmalloc(array_size);
+	if (!array)
+		goto nomem;
+
+	memset(array, 0, array_size);
+	ctrl = &swap_cgroup_ctrl[type];
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl->length = length;
+	ctrl->map = array;
+	if (swap_cgroup_prepare(type)) {
+		/* memory shortage */
+		ctrl->map = NULL;
+		ctrl->length = 0;
+		vfree(array);
+		mutex_unlock(&swap_cgroup_mutex);
+		goto nomem;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+
+	printk(KERN_INFO
+		"swap_cgroup: uses %ld bytes of vmalloc for pointer array space"
+		" and %ld bytes to hold mem_cgroup pointers on swap\n",
+		array_size, length * PAGE_SIZE);
+	printk(KERN_INFO
+	"swap_cgroup can be disabled by noswapaccount boot option.\n");
+
+	return 0;
+nomem:
+	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
+	printk(KERN_INFO
+		"swap_cgroup can be disabled by noswapaccount boot option\n");
+	return -ENOMEM;
+}
+
+void swap_cgroup_swapoff(int type)
+{
+	int i;
+	struct swap_cgroup_ctrl *ctrl;
+
+	if (!do_swap_account)
+		return;
+
+	mutex_lock(&swap_cgroup_mutex);
+	ctrl = &swap_cgroup_ctrl[type];
+	if (ctrl->map) {
+		for (i = 0; i < ctrl->length; i++) {
+			struct page *page = ctrl->map[i];
+			if (page)
+				__free_page(page);
+		}
+		vfree(ctrl->map);
+		ctrl->map = NULL;
+		ctrl->length = 0;
+	}
+	mutex_unlock(&swap_cgroup_mutex);
+}
+
+#endif
diff --git a/mm/page_io.c b/mm/page_io.c
index 065c4480eaf0..dc6ce0afbded 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -98,7 +98,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 	struct bio *bio;
 	int ret = 0, rw = WRITE;
 
-	if (remove_exclusive_swap_page(page)) {
+	if (try_to_free_swap(page)) {
 		unlock_page(page);
 		goto out;
 	}
@@ -125,8 +125,8 @@ int swap_readpage(struct file *file, struct page *page)
 	struct bio *bio;
 	int ret = 0;
 
-	BUG_ON(!PageLocked(page));
-	BUG_ON(PageUptodate(page));
+	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON(PageUptodate(page));
 	bio = get_swap_bio(GFP_KERNEL, page_private(page), page,
 				end_swap_bio_read);
 	if (bio == NULL) {
diff --git a/mm/pdflush.c b/mm/pdflush.c
index a0a14c4d5072..15de509b68fd 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -172,7 +172,16 @@ static int __pdflush(struct pdflush_work *my_work)
 static int pdflush(void *dummy)
 {
 	struct pdflush_work my_work;
-	cpumask_t cpus_allowed;
+	cpumask_var_t cpus_allowed;
+
+	/*
+	 * Since the caller doesn't even check kthread_run() worked, let's not
+	 * freak out too much if this fails.
+	 */
+	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
+		printk(KERN_WARNING "pdflush failed to allocate cpumask\n");
+		return 0;
+	}
 
 	/*
 	 * pdflush can spend a lot of time doing encryption via dm-crypt.  We
@@ -187,8 +196,9 @@ static int pdflush(void *dummy)
 	 * This is needed as pdflush's are dynamically created and destroyed.
 	 * The boottime pdflush's are easily placed w/o these 2 lines.
 	 */
-	cpuset_cpus_allowed(current, &cpus_allowed);
-	set_cpus_allowed_ptr(current, &cpus_allowed);
+	cpuset_cpus_allowed(current, cpus_allowed);
+	set_cpus_allowed_ptr(current, cpus_allowed);
+	free_cpumask_var(cpus_allowed);
 
 	return __pdflush(&my_work);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 10993942d6c9..ac4af8cffbf9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -47,9 +47,9 @@
 #include <linux/rmap.h>
 #include <linux/rcupdate.h>
 #include <linux/module.h>
-#include <linux/kallsyms.h>
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
+#include <linux/migrate.h>
 
 #include <asm/tlbflush.h>
 
@@ -191,7 +191,7 @@ void __init anon_vma_init(void)
  * Getting a lock on a stable anon_vma from a page off the LRU is
  * tricky: page_lock_anon_vma rely on RCU to guard against the races.
  */
-struct anon_vma *page_lock_anon_vma(struct page *page)
+static struct anon_vma *page_lock_anon_vma(struct page *page)
 {
 	struct anon_vma *anon_vma;
 	unsigned long anon_mapping;
@@ -211,7 +211,7 @@ out:
 	return NULL;
 }
 
-void page_unlock_anon_vma(struct anon_vma *anon_vma)
+static void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
 	spin_unlock(&anon_vma->lock);
 	rcu_read_unlock();
@@ -359,8 +359,17 @@ static int page_referenced_one(struct page *page,
 		goto out_unmap;
 	}
 
-	if (ptep_clear_flush_young_notify(vma, address, pte))
-		referenced++;
+	if (ptep_clear_flush_young_notify(vma, address, pte)) {
+		/*
+		 * Don't treat a reference through a sequentially read
+		 * mapping as such.  If the page has been used in
+		 * another mapping, we will catch it; if this other
+		 * mapping is already gone, the unmap path will have
+		 * set PG_referenced or activated the page.
+		 */
+		if (likely(!VM_SequentialReadHint(vma)))
+			referenced++;
+	}
 
 	/* Pretend the page is referenced if the task has the
 	   swap token and is in the middle of a page fault. */
@@ -661,9 +670,14 @@ void page_add_anon_rmap(struct page *page,
 void page_add_new_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address)
 {
-	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
-	atomic_set(&page->_mapcount, 0); /* elevate count by 1 (starts at -1) */
+	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	SetPageSwapBacked(page);
+	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
 	__page_set_anon_rmap(page, vma, address);
+	if (page_evictable(page, vma))
+		lru_cache_add_lru(page, LRU_ACTIVE_ANON);
+	else
+		add_page_to_unevictable_list(page);
 }
 
 /**
@@ -693,7 +707,6 @@ void page_add_file_rmap(struct page *page)
  */
 void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
 {
-	BUG_ON(page_mapcount(page) == 0);
 	if (PageAnon(page))
 		__page_check_anon_rmap(page, vma, address);
 	atomic_inc(&page->_mapcount);
@@ -703,28 +716,12 @@ void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long
 /**
  * page_remove_rmap - take down pte mapping from a page
  * @page: page to remove mapping from
- * @vma: the vm area in which the mapping is removed
  *
  * The caller needs to hold the pte lock.
  */
-void page_remove_rmap(struct page *page, struct vm_area_struct *vma)
+void page_remove_rmap(struct page *page)
 {
 	if (atomic_add_negative(-1, &page->_mapcount)) {
-		if (unlikely(page_mapcount(page) < 0)) {
-			printk (KERN_EMERG "Eeek! page_mapcount(page) went negative! (%d)\n", page_mapcount(page));
-			printk (KERN_EMERG "  page pfn = %lx\n", page_to_pfn(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);
-			print_symbol (KERN_EMERG "  vma->vm_ops = %s\n", (unsigned long)vma->vm_ops);
-			if (vma->vm_ops) {
-				print_symbol (KERN_EMERG "  vma->vm_ops->fault = %s\n", (unsigned long)vma->vm_ops->fault);
-			}
-			if (vma->vm_file && vma->vm_file->f_op)
-				print_symbol (KERN_EMERG "  vma->vm_file->f_op->mmap = %s\n", (unsigned long)vma->vm_file->f_op->mmap);
-			BUG();
-		}
-
 		/*
 		 * Now that the last pte has gone, s390 must transfer dirty
 		 * flag from storage key to struct page.  We can usually skip
@@ -818,8 +815,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 				spin_unlock(&mmlist_lock);
 			}
 			dec_mm_counter(mm, anon_rss);
-#ifdef CONFIG_MIGRATION
-		} else {
+		} else if (PAGE_MIGRATION) {
 			/*
 			 * Store the pfn of the page in a special migration
 			 * pte. do_swap_page() will wait until the migration
@@ -827,23 +823,19 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 			 */
 			BUG_ON(!migration);
 			entry = make_migration_entry(page, pte_write(pteval));
-#endif
 		}
 		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
 		BUG_ON(pte_file(*pte));
-	} else
-#ifdef CONFIG_MIGRATION
-	if (migration) {
+	} else if (PAGE_MIGRATION && migration) {
 		/* Establish migration entry for a file page */
 		swp_entry_t entry;
 		entry = make_migration_entry(page, pte_write(pteval));
 		set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
 	} else
-#endif
 		dec_mm_counter(mm, file_rss);
 
 
-	page_remove_rmap(page, vma);
+	page_remove_rmap(page);
 	page_cache_release(page);
 
 out_unmap:
@@ -958,7 +950,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		if (pte_dirty(pteval))
 			set_page_dirty(page);
 
-		page_remove_rmap(page, vma);
+		page_remove_rmap(page);
 		page_cache_release(page);
 		dec_mm_counter(mm, file_rss);
 		(*mapcount)--;
diff --git a/mm/shmem.c b/mm/shmem.c
index dd5588f5d939..75199888a6bd 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -14,31 +14,39 @@
  * Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
  * Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
  *
+ * tiny-shmem:
+ * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com>
+ *
  * This file is released under the GPL.
  */
 
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/vfs.h>
+#include <linux/mount.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+
+static struct vfsmount *shm_mnt;
+
+#ifdef CONFIG_SHMEM
 /*
  * This virtual memory filesystem is heavily based on the ramfs. It
  * extends ramfs by the ability to use swap and honor resource limits
  * which makes it a completely usable filesystem.
  */
 
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/fs.h>
 #include <linux/xattr.h>
 #include <linux/exportfs.h>
 #include <linux/generic_acl.h>
-#include <linux/mm.h>
 #include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
 #include <linux/shmem_fs.h>
-#include <linux/mount.h>
 #include <linux/writeback.h>
 #include <linux/vfs.h>
 #include <linux/blkdev.h>
@@ -921,7 +929,11 @@ found:
 	error = 1;
 	if (!inode)
 		goto out;
-	/* Precharge page using GFP_KERNEL while we can wait */
+	/*
+	 * Charge page using GFP_KERNEL while we can wait.
+	 * Charged back to the user(not to caller) when swap account is used.
+	 * add_to_page_cache() will be called with GFP_NOWAIT.
+	 */
 	error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
 	if (error)
 		goto out;
@@ -1313,15 +1325,19 @@ repeat:
 		} else {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
-			unlock_page(swappage);
-			page_cache_release(swappage);
 			if (error == -ENOMEM) {
 				/* allow reclaim from this memory cgroup */
-				error = mem_cgroup_shrink_usage(current->mm,
+				error = mem_cgroup_shrink_usage(swappage,
+								current->mm,
 								gfp);
-				if (error)
+				if (error) {
+					unlock_page(swappage);
+					page_cache_release(swappage);
 					goto failed;
+				}
 			}
+			unlock_page(swappage);
+			page_cache_release(swappage);
 			goto repeat;
 		}
 	} else if (sgp == SGP_READ && !filepage) {
@@ -1372,7 +1388,7 @@ repeat:
 
 			/* Precharge page while we can wait, compensate after */
 			error = mem_cgroup_cache_charge(filepage, current->mm,
-							gfp & ~__GFP_HIGHMEM);
+					GFP_KERNEL);
 			if (error) {
 				page_cache_release(filepage);
 				shmem_unacct_blocks(info->flags, 1);
@@ -1445,7 +1461,6 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
 
-	mark_page_accessed(vmf->page);
 	return ret | VM_FAULT_LOCKED;
 }
 
@@ -2487,7 +2502,6 @@ static struct file_system_type tmpfs_fs_type = {
 	.get_sb		= shmem_get_sb,
 	.kill_sb	= kill_litter_super,
 };
-static struct vfsmount *shm_mnt;
 
 static int __init init_tmpfs(void)
 {
@@ -2526,7 +2540,51 @@ out4:
 	shm_mnt = ERR_PTR(error);
 	return error;
 }
-module_init(init_tmpfs)
+
+#else /* !CONFIG_SHMEM */
+
+/*
+ * tiny-shmem: simple shmemfs and tmpfs using ramfs code
+ *
+ * This is intended for small system where the benefits of the full
+ * shmem code (swap-backed and resource-limited) are outweighed by
+ * their complexity. On systems without swap this code should be
+ * effectively equivalent, but much lighter weight.
+ */
+
+#include <linux/ramfs.h>
+
+static struct file_system_type tmpfs_fs_type = {
+	.name		= "tmpfs",
+	.get_sb		= ramfs_get_sb,
+	.kill_sb	= kill_litter_super,
+};
+
+static int __init init_tmpfs(void)
+{
+	BUG_ON(register_filesystem(&tmpfs_fs_type) != 0);
+
+	shm_mnt = kern_mount(&tmpfs_fs_type);
+	BUG_ON(IS_ERR(shm_mnt));
+
+	return 0;
+}
+
+int shmem_unuse(swp_entry_t entry, struct page *page)
+{
+	return 0;
+}
+
+#define shmem_file_operations ramfs_file_operations
+#define shmem_vm_ops generic_file_vm_ops
+#define shmem_get_inode ramfs_get_inode
+#define shmem_acct_size(a, b) 0
+#define shmem_unacct_size(a, b) do {} while (0)
+#define SHMEM_MAX_BYTES LLONG_MAX
+
+#endif /* CONFIG_SHMEM */
+
+/* common code */
 
 /**
  * shmem_file_setup - get an unlinked file living in tmpfs
@@ -2570,12 +2628,20 @@ struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
 	if (!inode)
 		goto close_file;
 
-	SHMEM_I(inode)->flags = flags & VM_ACCOUNT;
+#ifdef CONFIG_SHMEM
+	SHMEM_I(inode)->flags = (flags & VM_NORESERVE) ? 0 : VM_ACCOUNT;
+#endif
 	d_instantiate(dentry, inode);
 	inode->i_size = size;
 	inode->i_nlink = 0;	/* It is unlinked */
 	init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
-			&shmem_file_operations);
+		  &shmem_file_operations);
+
+#ifndef CONFIG_MMU
+	error = ramfs_nommu_expand_for_mapping(inode, size);
+	if (error)
+		goto close_file;
+#endif
 	return file;
 
 close_file:
@@ -2608,3 +2674,5 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	vma->vm_ops = &shmem_vm_ops;
 	return 0;
 }
+
+module_init(init_tmpfs)
diff --git a/mm/slab.c b/mm/slab.c
index f97e564bdf11..ddc41f337d58 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2157,7 +2157,7 @@ kmem_cache_create (const char *name, size_t size, size_t align,
 
 	/*
 	 * We use cache_chain_mutex to ensure a consistent view of
-	 * cpu_online_map as well.  Please see cpuup_callback
+	 * cpu_online_mask as well.  Please see cpuup_callback
 	 */
 	get_online_cpus();
 	mutex_lock(&cache_chain_mutex);
diff --git a/mm/slub.c b/mm/slub.c
index 6cb7ad107852..bdc9abb08a23 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1970,7 +1970,7 @@ static DEFINE_PER_CPU(struct kmem_cache_cpu,
 				kmem_cache_cpu)[NR_KMEM_CACHE_CPU];
 
 static DEFINE_PER_CPU(struct kmem_cache_cpu *, kmem_cache_cpu_free);
-static cpumask_t kmem_cach_cpu_free_init_once = CPU_MASK_NONE;
+static DECLARE_BITMAP(kmem_cach_cpu_free_init_once, CONFIG_NR_CPUS);
 
 static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,
 							int cpu, gfp_t flags)
@@ -1996,7 +1996,7 @@ static struct kmem_cache_cpu *alloc_kmem_cache_cpu(struct kmem_cache *s,
 static void free_kmem_cache_cpu(struct kmem_cache_cpu *c, int cpu)
 {
 	if (c < per_cpu(kmem_cache_cpu, cpu) ||
-			c > per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
+			c >= per_cpu(kmem_cache_cpu, cpu) + NR_KMEM_CACHE_CPU) {
 		kfree(c);
 		return;
 	}
@@ -2045,13 +2045,13 @@ static void init_alloc_cpu_cpu(int cpu)
 {
 	int i;
 
-	if (cpu_isset(cpu, kmem_cach_cpu_free_init_once))
+	if (cpumask_test_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once)))
 		return;
 
 	for (i = NR_KMEM_CACHE_CPU - 1; i >= 0; i--)
 		free_kmem_cache_cpu(&per_cpu(kmem_cache_cpu, cpu)[i], cpu);
 
-	cpu_set(cpu, kmem_cach_cpu_free_init_once);
+	cpumask_set_cpu(cpu, to_cpumask(kmem_cach_cpu_free_init_once));
 }
 
 static void __init init_alloc_cpu(void)
@@ -2254,7 +2254,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 		 * Add some empty padding so that we can catch
 		 * overwrites from earlier objects rather than let
 		 * tracking information or the free pointer be
-		 * corrupted if an user writes before the start
+		 * corrupted if a user writes before the start
 		 * of the object.
 		 */
 		size += sizeof(void *);
@@ -3451,7 +3451,7 @@ struct location {
 	long max_time;
 	long min_pid;
 	long max_pid;
-	cpumask_t cpus;
+	DECLARE_BITMAP(cpus, NR_CPUS);
 	nodemask_t nodes;
 };
 
@@ -3526,7 +3526,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 				if (track->pid > l->max_pid)
 					l->max_pid = track->pid;
 
-				cpu_set(track->cpu, l->cpus);
+				cpumask_set_cpu(track->cpu,
+						to_cpumask(l->cpus));
 			}
 			node_set(page_to_nid(virt_to_page(track)), l->nodes);
 			return 1;
@@ -3556,8 +3557,8 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 	l->max_time = age;
 	l->min_pid = track->pid;
 	l->max_pid = track->pid;
-	cpus_clear(l->cpus);
-	cpu_set(track->cpu, l->cpus);
+	cpumask_clear(to_cpumask(l->cpus));
+	cpumask_set_cpu(track->cpu, to_cpumask(l->cpus));
 	nodes_clear(l->nodes);
 	node_set(page_to_nid(virt_to_page(track)), l->nodes);
 	return 1;
@@ -3638,11 +3639,12 @@ static int list_locations(struct kmem_cache *s, char *buf,
 			len += sprintf(buf + len, " pid=%ld",
 				l->min_pid);
 
-		if (num_online_cpus() > 1 && !cpus_empty(l->cpus) &&
+		if (num_online_cpus() > 1 &&
+				!cpumask_empty(to_cpumask(l->cpus)) &&
 				len < PAGE_SIZE - 60) {
 			len += sprintf(buf + len, " cpus=");
 			len += cpulist_scnprintf(buf + len, PAGE_SIZE - len - 50,
-					l->cpus);
+						 to_cpumask(l->cpus));
 		}
 
 		if (num_online_nodes() > 1 && !nodes_empty(l->nodes) &&
diff --git a/mm/swap.c b/mm/swap.c
index b135ec90cdeb..8adb9feb61e1 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -151,6 +151,26 @@ void  rotate_reclaimable_page(struct page *page)
 	}
 }
 
+static void update_page_reclaim_stat(struct zone *zone, struct page *page,
+				     int file, int rotated)
+{
+	struct zone_reclaim_stat *reclaim_stat = &zone->reclaim_stat;
+	struct zone_reclaim_stat *memcg_reclaim_stat;
+
+	memcg_reclaim_stat = mem_cgroup_get_reclaim_stat_from_page(page);
+
+	reclaim_stat->recent_scanned[file]++;
+	if (rotated)
+		reclaim_stat->recent_rotated[file]++;
+
+	if (!memcg_reclaim_stat)
+		return;
+
+	memcg_reclaim_stat->recent_scanned[file]++;
+	if (rotated)
+		memcg_reclaim_stat->recent_rotated[file]++;
+}
+
 /*
  * FIXME: speed this up?
  */
@@ -168,10 +188,8 @@ void activate_page(struct page *page)
 		lru += LRU_ACTIVE;
 		add_page_to_lru_list(zone, page, lru);
 		__count_vm_event(PGACTIVATE);
-		mem_cgroup_move_lists(page, lru);
 
-		zone->recent_rotated[!!file]++;
-		zone->recent_scanned[!!file]++;
+		update_page_reclaim_stat(zone, page, !!file, 1);
 	}
 	spin_unlock_irq(&zone->lru_lock);
 }
@@ -246,25 +264,6 @@ void add_page_to_unevictable_list(struct page *page)
 	spin_unlock_irq(&zone->lru_lock);
 }
 
-/**
- * lru_cache_add_active_or_unevictable
- * @page:  the page to be added to LRU
- * @vma:   vma in which page is mapped for determining reclaimability
- *
- * place @page on active or unevictable LRU list, depending on
- * page_evictable().  Note that if the page is not evictable,
- * it goes directly back onto it's zone's unevictable list.  It does
- * NOT use a per cpu pagevec.
- */
-void lru_cache_add_active_or_unevictable(struct page *page,
-					struct vm_area_struct *vma)
-{
-	if (page_evictable(page, vma))
-		lru_cache_add_lru(page, LRU_ACTIVE + page_is_file_cache(page));
-	else
-		add_page_to_unevictable_list(page);
-}
-
 /*
  * Drain pages out of the cpu's pagevecs.
  * Either "cpu" is the current CPU, and preemption has already been
@@ -398,28 +397,6 @@ void __pagevec_release(struct pagevec *pvec)
 EXPORT_SYMBOL(__pagevec_release);
 
 /*
- * pagevec_release() for pages which are known to not be on the LRU
- *
- * This function reinitialises the caller's pagevec.
- */
-void __pagevec_release_nonlru(struct pagevec *pvec)
-{
-	int i;
-	struct pagevec pages_to_free;
-
-	pagevec_init(&pages_to_free, pvec->cold);
-	for (i = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-
-		VM_BUG_ON(PageLRU(page));
-		if (put_page_testzero(page))
-			pagevec_add(&pages_to_free, page);
-	}
-	pagevec_free(&pages_to_free);
-	pagevec_reinit(pvec);
-}
-
-/*
  * Add the passed pages to the LRU, then drop the caller's refcount
  * on them.  Reinitialises the caller's pagevec.
  */
@@ -427,12 +404,14 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 {
 	int i;
 	struct zone *zone = NULL;
+
 	VM_BUG_ON(is_unevictable_lru(lru));
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
 		struct zone *pagezone = page_zone(page);
 		int file;
+		int active;
 
 		if (pagezone != zone) {
 			if (zone)
@@ -444,12 +423,11 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 		VM_BUG_ON(PageUnevictable(page));
 		VM_BUG_ON(PageLRU(page));
 		SetPageLRU(page);
+		active = is_active_lru(lru);
 		file = is_file_lru(lru);
-		zone->recent_scanned[file]++;
-		if (is_active_lru(lru)) {
+		if (active)
 			SetPageActive(page);
-			zone->recent_rotated[file]++;
-		}
+		update_page_reclaim_stat(zone, page, file, active);
 		add_page_to_lru_list(zone, page, lru);
 	}
 	if (zone)
@@ -495,8 +473,7 @@ void pagevec_swap_free(struct pagevec *pvec)
 		struct page *page = pvec->pages[i];
 
 		if (PageSwapCache(page) && trylock_page(page)) {
-			if (PageSwapCache(page))
-				remove_exclusive_swap_page_ref(page);
+			try_to_free_swap(page);
 			unlock_page(page);
 		}
 	}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 3353c9029cef..3ecea98ecb45 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -17,6 +17,7 @@
 #include <linux/backing-dev.h>
 #include <linux/pagevec.h>
 #include <linux/migrate.h>
+#include <linux/page_cgroup.h>
 
 #include <asm/pgtable.h>
 
@@ -72,10 +73,10 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
 {
 	int error;
 
-	BUG_ON(!PageLocked(page));
-	BUG_ON(PageSwapCache(page));
-	BUG_ON(PagePrivate(page));
-	BUG_ON(!PageSwapBacked(page));
+	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON(PageSwapCache(page));
+	VM_BUG_ON(!PageSwapBacked(page));
+
 	error = radix_tree_preload(gfp_mask);
 	if (!error) {
 		page_cache_get(page);
@@ -108,10 +109,11 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
  */
 void __delete_from_swap_cache(struct page *page)
 {
-	BUG_ON(!PageLocked(page));
-	BUG_ON(!PageSwapCache(page));
-	BUG_ON(PageWriteback(page));
-	BUG_ON(PagePrivate(page));
+	swp_entry_t ent = {.val = page_private(page)};
+
+	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON(!PageSwapCache(page));
+	VM_BUG_ON(PageWriteback(page));
 
 	radix_tree_delete(&swapper_space.page_tree, page_private(page));
 	set_page_private(page, 0);
@@ -119,6 +121,7 @@ void __delete_from_swap_cache(struct page *page)
 	total_swapcache_pages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	INC_CACHE_INFO(del_total);
+	mem_cgroup_uncharge_swapcache(page, ent);
 }
 
 /**
@@ -129,13 +132,13 @@ void __delete_from_swap_cache(struct page *page)
  * Allocate swap space for the page and add the page to the
  * swap cache.  Caller needs to hold the page lock. 
  */
-int add_to_swap(struct page * page, gfp_t gfp_mask)
+int add_to_swap(struct page *page)
 {
 	swp_entry_t entry;
 	int err;
 
-	BUG_ON(!PageLocked(page));
-	BUG_ON(!PageUptodate(page));
+	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON(!PageUptodate(page));
 
 	for (;;) {
 		entry = get_swap_page();
@@ -154,7 +157,7 @@ int add_to_swap(struct page * page, gfp_t gfp_mask)
 		 * Add it to the swap cache and mark it dirty
 		 */
 		err = add_to_swap_cache(page, entry,
-				gfp_mask|__GFP_NOMEMALLOC|__GFP_NOWARN);
+				__GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN);
 
 		switch (err) {
 		case 0:				/* Success */
@@ -196,14 +199,14 @@ void delete_from_swap_cache(struct page *page)
  * If we are the only user, then try to free up the swap cache. 
  * 
  * Its ok to check for PageSwapCache without the page lock
- * here because we are going to recheck again inside 
- * exclusive_swap_page() _with_ the lock. 
+ * here because we are going to recheck again inside
+ * try_to_free_swap() _with_ the lock.
  * 					- Marcelo
  */
 static inline void free_swap_cache(struct page *page)
 {
-	if (PageSwapCache(page) && trylock_page(page)) {
-		remove_exclusive_swap_page(page);
+	if (PageSwapCache(page) && !page_mapped(page) && trylock_page(page)) {
+		try_to_free_swap(page);
 		unlock_page(page);
 	}
 }
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 54a9f87e5162..7e6304dfafab 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -16,6 +16,7 @@
 #include <linux/namei.h>
 #include <linux/shm.h>
 #include <linux/blkdev.h>
+#include <linux/random.h>
 #include <linux/writeback.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
@@ -32,9 +33,11 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 #include <linux/swapops.h>
+#include <linux/page_cgroup.h>
 
 static DEFINE_SPINLOCK(swap_lock);
 static unsigned int nr_swapfiles;
+long nr_swap_pages;
 long total_swap_pages;
 static int swap_overflow;
 static int least_priority;
@@ -83,15 +86,96 @@ void swap_unplug_io_fn(struct backing_dev_info *unused_bdi, struct page *page)
 	up_read(&swap_unplug_sem);
 }
 
+/*
+ * swapon tell device that all the old swap contents can be discarded,
+ * to allow the swap device to optimize its wear-levelling.
+ */
+static int discard_swap(struct swap_info_struct *si)
+{
+	struct swap_extent *se;
+	int err = 0;
+
+	list_for_each_entry(se, &si->extent_list, list) {
+		sector_t start_block = se->start_block << (PAGE_SHIFT - 9);
+		sector_t nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
+
+		if (se->start_page == 0) {
+			/* Do not discard the swap header page! */
+			start_block += 1 << (PAGE_SHIFT - 9);
+			nr_blocks -= 1 << (PAGE_SHIFT - 9);
+			if (!nr_blocks)
+				continue;
+		}
+
+		err = blkdev_issue_discard(si->bdev, start_block,
+						nr_blocks, GFP_KERNEL);
+		if (err)
+			break;
+
+		cond_resched();
+	}
+	return err;		/* That will often be -EOPNOTSUPP */
+}
+
+/*
+ * swap allocation tell device that a cluster of swap can now be discarded,
+ * to allow the swap device to optimize its wear-levelling.
+ */
+static void discard_swap_cluster(struct swap_info_struct *si,
+				 pgoff_t start_page, pgoff_t nr_pages)
+{
+	struct swap_extent *se = si->curr_swap_extent;
+	int found_extent = 0;
+
+	while (nr_pages) {
+		struct list_head *lh;
+
+		if (se->start_page <= start_page &&
+		    start_page < se->start_page + se->nr_pages) {
+			pgoff_t offset = start_page - se->start_page;
+			sector_t start_block = se->start_block + offset;
+			sector_t nr_blocks = se->nr_pages - offset;
+
+			if (nr_blocks > nr_pages)
+				nr_blocks = nr_pages;
+			start_page += nr_blocks;
+			nr_pages -= nr_blocks;
+
+			if (!found_extent++)
+				si->curr_swap_extent = se;
+
+			start_block <<= PAGE_SHIFT - 9;
+			nr_blocks <<= PAGE_SHIFT - 9;
+			if (blkdev_issue_discard(si->bdev, start_block,
+							nr_blocks, GFP_NOIO))
+				break;
+		}
+
+		lh = se->list.next;
+		if (lh == &si->extent_list)
+			lh = lh->next;
+		se = list_entry(lh, struct swap_extent, list);
+	}
+}
+
+static int wait_for_discard(void *word)
+{
+	schedule();
+	return 0;
+}
+
 #define SWAPFILE_CLUSTER	256
 #define LATENCY_LIMIT		256
 
 static inline unsigned long scan_swap_map(struct swap_info_struct *si)
 {
-	unsigned long offset, last_in_cluster;
+	unsigned long offset;
+	unsigned long scan_base;
+	unsigned long last_in_cluster = 0;
 	int latency_ration = LATENCY_LIMIT;
+	int found_free_cluster = 0;
 
-	/* 
+	/*
 	 * We try to cluster swap pages by allocating them sequentially
 	 * in swap.  Once we've allocated SWAPFILE_CLUSTER pages this
 	 * way, however, we resort to first-free allocation, starting
@@ -99,16 +183,42 @@ static inline unsigned long scan_swap_map(struct swap_info_struct *si)
 	 * all over the entire swap partition, so that we reduce
 	 * overall disk seek times between swap pages.  -- sct
 	 * But we do now try to find an empty cluster.  -Andrea
+	 * And we let swap pages go all over an SSD partition.  Hugh
 	 */
 
 	si->flags += SWP_SCANNING;
-	if (unlikely(!si->cluster_nr)) {
-		si->cluster_nr = SWAPFILE_CLUSTER - 1;
-		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER)
-			goto lowest;
+	scan_base = offset = si->cluster_next;
+
+	if (unlikely(!si->cluster_nr--)) {
+		if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) {
+			si->cluster_nr = SWAPFILE_CLUSTER - 1;
+			goto checks;
+		}
+		if (si->flags & SWP_DISCARDABLE) {
+			/*
+			 * Start range check on racing allocations, in case
+			 * they overlap the cluster we eventually decide on
+			 * (we scan without swap_lock to allow preemption).
+			 * It's hardly conceivable that cluster_nr could be
+			 * wrapped during our scan, but don't depend on it.
+			 */
+			if (si->lowest_alloc)
+				goto checks;
+			si->lowest_alloc = si->max;
+			si->highest_alloc = 0;
+		}
 		spin_unlock(&swap_lock);
 
-		offset = si->lowest_bit;
+		/*
+		 * If seek is expensive, start searching for new cluster from
+		 * start of partition, to minimize the span of allocated swap.
+		 * But if seek is cheap, search from our current position, so
+		 * that swap is allocated from all over the partition: if the
+		 * Flash Translation Layer only remaps within limited zones,
+		 * we don't want to wear out the first zone too quickly.
+		 */
+		if (!(si->flags & SWP_SOLIDSTATE))
+			scan_base = offset = si->lowest_bit;
 		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
 
 		/* Locate the first empty (unaligned) cluster */
@@ -117,43 +227,124 @@ 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;
-				goto cluster;
+				offset -= SWAPFILE_CLUSTER - 1;
+				si->cluster_next = offset;
+				si->cluster_nr = SWAPFILE_CLUSTER - 1;
+				found_free_cluster = 1;
+				goto checks;
 			}
 			if (unlikely(--latency_ration < 0)) {
 				cond_resched();
 				latency_ration = LATENCY_LIMIT;
 			}
 		}
+
+		offset = si->lowest_bit;
+		last_in_cluster = offset + SWAPFILE_CLUSTER - 1;
+
+		/* Locate the first empty (unaligned) cluster */
+		for (; last_in_cluster < scan_base; offset++) {
+			if (si->swap_map[offset])
+				last_in_cluster = offset + SWAPFILE_CLUSTER;
+			else if (offset == last_in_cluster) {
+				spin_lock(&swap_lock);
+				offset -= SWAPFILE_CLUSTER - 1;
+				si->cluster_next = offset;
+				si->cluster_nr = SWAPFILE_CLUSTER - 1;
+				found_free_cluster = 1;
+				goto checks;
+			}
+			if (unlikely(--latency_ration < 0)) {
+				cond_resched();
+				latency_ration = LATENCY_LIMIT;
+			}
+		}
+
+		offset = scan_base;
 		spin_lock(&swap_lock);
-		goto lowest;
+		si->cluster_nr = SWAPFILE_CLUSTER - 1;
+		si->lowest_alloc = 0;
 	}
 
-	si->cluster_nr--;
-cluster:
-	offset = si->cluster_next;
-	if (offset > si->highest_bit)
-lowest:		offset = si->lowest_bit;
-checks:	if (!(si->flags & SWP_WRITEOK))
+checks:
+	if (!(si->flags & SWP_WRITEOK))
 		goto no_page;
 	if (!si->highest_bit)
 		goto no_page;
-	if (!si->swap_map[offset]) {
-		if (offset == si->lowest_bit)
-			si->lowest_bit++;
-		if (offset == si->highest_bit)
-			si->highest_bit--;
-		si->inuse_pages++;
-		if (si->inuse_pages == si->pages) {
-			si->lowest_bit = si->max;
-			si->highest_bit = 0;
+	if (offset > si->highest_bit)
+		scan_base = offset = si->lowest_bit;
+	if (si->swap_map[offset])
+		goto scan;
+
+	if (offset == si->lowest_bit)
+		si->lowest_bit++;
+	if (offset == si->highest_bit)
+		si->highest_bit--;
+	si->inuse_pages++;
+	if (si->inuse_pages == si->pages) {
+		si->lowest_bit = si->max;
+		si->highest_bit = 0;
+	}
+	si->swap_map[offset] = 1;
+	si->cluster_next = offset + 1;
+	si->flags -= SWP_SCANNING;
+
+	if (si->lowest_alloc) {
+		/*
+		 * Only set when SWP_DISCARDABLE, and there's a scan
+		 * for a free cluster in progress or just completed.
+		 */
+		if (found_free_cluster) {
+			/*
+			 * To optimize wear-levelling, discard the
+			 * old data of the cluster, taking care not to
+			 * discard any of its pages that have already
+			 * been allocated by racing tasks (offset has
+			 * already stepped over any at the beginning).
+			 */
+			if (offset < si->highest_alloc &&
+			    si->lowest_alloc <= last_in_cluster)
+				last_in_cluster = si->lowest_alloc - 1;
+			si->flags |= SWP_DISCARDING;
+			spin_unlock(&swap_lock);
+
+			if (offset < last_in_cluster)
+				discard_swap_cluster(si, offset,
+					last_in_cluster - offset + 1);
+
+			spin_lock(&swap_lock);
+			si->lowest_alloc = 0;
+			si->flags &= ~SWP_DISCARDING;
+
+			smp_mb();	/* wake_up_bit advises this */
+			wake_up_bit(&si->flags, ilog2(SWP_DISCARDING));
+
+		} else if (si->flags & SWP_DISCARDING) {
+			/*
+			 * Delay using pages allocated by racing tasks
+			 * until the whole discard has been issued. We
+			 * could defer that delay until swap_writepage,
+			 * but it's easier to keep this self-contained.
+			 */
+			spin_unlock(&swap_lock);
+			wait_on_bit(&si->flags, ilog2(SWP_DISCARDING),
+				wait_for_discard, TASK_UNINTERRUPTIBLE);
+			spin_lock(&swap_lock);
+		} else {
+			/*
+			 * Note pages allocated by racing tasks while
+			 * scan for a free cluster is in progress, so
+			 * that its final discard can exclude them.
+			 */
+			if (offset < si->lowest_alloc)
+				si->lowest_alloc = offset;
+			if (offset > si->highest_alloc)
+				si->highest_alloc = offset;
 		}
-		si->swap_map[offset] = 1;
-		si->cluster_next = offset + 1;
-		si->flags -= SWP_SCANNING;
-		return offset;
 	}
+	return offset;
 
+scan:
 	spin_unlock(&swap_lock);
 	while (++offset <= si->highest_bit) {
 		if (!si->swap_map[offset]) {
@@ -165,8 +356,18 @@ checks:	if (!(si->flags & SWP_WRITEOK))
 			latency_ration = LATENCY_LIMIT;
 		}
 	}
+	offset = si->lowest_bit;
+	while (++offset < scan_base) {
+		if (!si->swap_map[offset]) {
+			spin_lock(&swap_lock);
+			goto checks;
+		}
+		if (unlikely(--latency_ration < 0)) {
+			cond_resched();
+			latency_ration = LATENCY_LIMIT;
+		}
+	}
 	spin_lock(&swap_lock);
-	goto lowest;
 
 no_page:
 	si->flags -= SWP_SCANNING;
@@ -268,10 +469,11 @@ bad_nofile:
 	printk(KERN_ERR "swap_free: %s%08lx\n", Bad_file, entry.val);
 out:
 	return NULL;
-}	
+}
 
-static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
+static int swap_entry_free(struct swap_info_struct *p, swp_entry_t ent)
 {
+	unsigned long offset = swp_offset(ent);
 	int count = p->swap_map[offset];
 
 	if (count < SWAP_MAP_MAX) {
@@ -286,6 +488,7 @@ static int swap_entry_free(struct swap_info_struct *p, unsigned long offset)
 				swap_list.next = p - swap_info;
 			nr_swap_pages++;
 			p->inuse_pages--;
+			mem_cgroup_uncharge_swap(ent);
 		}
 	}
 	return count;
@@ -301,7 +504,7 @@ void swap_free(swp_entry_t entry)
 
 	p = swap_info_get(entry);
 	if (p) {
-		swap_entry_free(p, swp_offset(entry));
+		swap_entry_free(p, entry);
 		spin_unlock(&swap_lock);
 	}
 }
@@ -326,101 +529,62 @@ static inline int page_swapcount(struct page *page)
 }
 
 /*
- * We can use this swap cache entry directly
- * if there are no other references to it.
+ * We can write to an anon page without COW if there are no other references
+ * to it.  And as a side-effect, free up its swap: because the old content
+ * on disk will never be read, and seeking back there to write new content
+ * later would only waste time away from clustering.
  */
-int can_share_swap_page(struct page *page)
+int reuse_swap_page(struct page *page)
 {
 	int count;
 
-	BUG_ON(!PageLocked(page));
+	VM_BUG_ON(!PageLocked(page));
 	count = page_mapcount(page);
-	if (count <= 1 && PageSwapCache(page))
+	if (count <= 1 && PageSwapCache(page)) {
 		count += page_swapcount(page);
+		if (count == 1 && !PageWriteback(page)) {
+			delete_from_swap_cache(page);
+			SetPageDirty(page);
+		}
+	}
 	return count == 1;
 }
 
 /*
- * Work out if there are any other processes sharing this
- * swap cache page. Free it if you can. Return success.
+ * If swap is getting full, or if there are no more mappings of this page,
+ * then try_to_free_swap is called to free its swap space.
  */
-static int remove_exclusive_swap_page_count(struct page *page, int count)
+int try_to_free_swap(struct page *page)
 {
-	int retval;
-	struct swap_info_struct * p;
-	swp_entry_t entry;
-
-	BUG_ON(PagePrivate(page));
-	BUG_ON(!PageLocked(page));
+	VM_BUG_ON(!PageLocked(page));
 
 	if (!PageSwapCache(page))
 		return 0;
 	if (PageWriteback(page))
 		return 0;
-	if (page_count(page) != count) /* us + cache + ptes */
+	if (page_swapcount(page))
 		return 0;
 
-	entry.val = page_private(page);
-	p = swap_info_get(entry);
-	if (!p)
-		return 0;
-
-	/* Is the only swap cache user the cache itself? */
-	retval = 0;
-	if (p->swap_map[swp_offset(entry)] == 1) {
-		/* Recheck the page count with the swapcache lock held.. */
-		spin_lock_irq(&swapper_space.tree_lock);
-		if ((page_count(page) == count) && !PageWriteback(page)) {
-			__delete_from_swap_cache(page);
-			SetPageDirty(page);
-			retval = 1;
-		}
-		spin_unlock_irq(&swapper_space.tree_lock);
-	}
-	spin_unlock(&swap_lock);
-
-	if (retval) {
-		swap_free(entry);
-		page_cache_release(page);
-	}
-
-	return retval;
-}
-
-/*
- * Most of the time the page should have two references: one for the
- * process and one for the swap cache.
- */
-int remove_exclusive_swap_page(struct page *page)
-{
-	return remove_exclusive_swap_page_count(page, 2);
-}
-
-/*
- * The pageout code holds an extra reference to the page.  That raises
- * the reference count to test for to 2 for a page that is only in the
- * swap cache plus 1 for each process that maps the page.
- */
-int remove_exclusive_swap_page_ref(struct page *page)
-{
-	return remove_exclusive_swap_page_count(page, 2 + page_mapcount(page));
+	delete_from_swap_cache(page);
+	SetPageDirty(page);
+	return 1;
 }
 
 /*
  * Free the swap entry like above, but also try to
  * free the page cache entry if it is the last user.
  */
-void free_swap_and_cache(swp_entry_t entry)
+int free_swap_and_cache(swp_entry_t entry)
 {
-	struct swap_info_struct * p;
+	struct swap_info_struct *p;
 	struct page *page = NULL;
 
 	if (is_migration_entry(entry))
-		return;
+		return 1;
 
 	p = swap_info_get(entry);
 	if (p) {
-		if (swap_entry_free(p, swp_offset(entry)) == 1) {
+		if (swap_entry_free(p, entry) == 1) {
 			page = find_get_page(&swapper_space, entry.val);
 			if (page && !trylock_page(page)) {
 				page_cache_release(page);
@@ -430,20 +594,19 @@ void free_swap_and_cache(swp_entry_t entry)
 		spin_unlock(&swap_lock);
 	}
 	if (page) {
-		int one_user;
-
-		BUG_ON(PagePrivate(page));
-		one_user = (page_count(page) == 2);
-		/* Only cache user (+us), or swap space full? Free it! */
-		/* Also recheck PageSwapCache after page is locked (above) */
+		/*
+		 * Not mapped elsewhere, or swap space full? Free it!
+		 * Also recheck PageSwapCache now page is locked (above).
+		 */
 		if (PageSwapCache(page) && !PageWriteback(page) &&
-					(one_user || vm_swap_full())) {
+				(!page_mapped(page) || vm_swap_full())) {
 			delete_from_swap_cache(page);
 			SetPageDirty(page);
 		}
 		unlock_page(page);
 		page_cache_release(page);
 	}
+	return p != NULL;
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -530,17 +693,20 @@ unsigned int count_swap_pages(int type, int free)
 static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 		unsigned long addr, swp_entry_t entry, struct page *page)
 {
+	struct mem_cgroup *ptr = NULL;
 	spinlock_t *ptl;
 	pte_t *pte;
 	int ret = 1;
 
-	if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
+	if (mem_cgroup_try_charge_swapin(vma->vm_mm, page, GFP_KERNEL, &ptr)) {
 		ret = -ENOMEM;
+		goto out_nolock;
+	}
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (unlikely(!pte_same(*pte, swp_entry_to_pte(entry)))) {
 		if (ret > 0)
-			mem_cgroup_uncharge_page(page);
+			mem_cgroup_cancel_charge_swapin(ptr);
 		ret = 0;
 		goto out;
 	}
@@ -550,6 +716,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	set_pte_at(vma->vm_mm, addr, pte,
 		   pte_mkold(mk_pte(page, vma->vm_page_prot)));
 	page_add_anon_rmap(page, vma, addr);
+	mem_cgroup_commit_charge_swapin(page, ptr);
 	swap_free(entry);
 	/*
 	 * Move the page to the active list so it is not
@@ -558,6 +725,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
 	activate_page(page);
 out:
 	pte_unmap_unlock(pte, ptl);
+out_nolock:
 	return ret;
 }
 
@@ -776,10 +944,10 @@ static int try_to_unuse(unsigned int type)
 			break;
 		}
 
-		/* 
+		/*
 		 * Get a page for the entry, using the existing swap
 		 * cache page if there is one.  Otherwise, get a clean
-		 * page and read the swap into it. 
+		 * page and read the swap into it.
 		 */
 		swap_map = &si->swap_map[i];
 		entry = swp_entry(type, i);
@@ -930,7 +1098,16 @@ static int try_to_unuse(unsigned int type)
 			lock_page(page);
 			wait_on_page_writeback(page);
 		}
-		if (PageSwapCache(page))
+
+		/*
+		 * It is conceivable that a racing task removed this page from
+		 * swap cache just before we acquired the page lock at the top,
+		 * or while we dropped it in unuse_mm().  The page might even
+		 * be back in swap cache on another swap area: that we must not
+		 * delete, since it may not have been written out to swap yet.
+		 */
+		if (PageSwapCache(page) &&
+		    likely(page_private(page) == entry.val))
 			delete_from_swap_cache(page);
 
 		/*
@@ -1203,27 +1380,7 @@ out:
 	return ret;
 }
 
-#if 0	/* We don't need this yet */
-#include <linux/backing-dev.h>
-int page_queue_congested(struct page *page)
-{
-	struct backing_dev_info *bdi;
-
-	BUG_ON(!PageLocked(page));	/* It pins the swap_info_struct */
-
-	if (PageSwapCache(page)) {
-		swp_entry_t entry = { .val = page_private(page) };
-		struct swap_info_struct *sis;
-
-		sis = get_swap_info_struct(swp_type(entry));
-		bdi = sis->bdev->bd_inode->i_mapping->backing_dev_info;
-	} else
-		bdi = page->mapping->backing_dev_info;
-	return bdi_write_congested(bdi);
-}
-#endif
-
-asmlinkage long sys_swapoff(const char __user * specialfile)
+SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 {
 	struct swap_info_struct * p = NULL;
 	unsigned short *swap_map;
@@ -1233,7 +1390,7 @@ asmlinkage long sys_swapoff(const char __user * specialfile)
 	char * pathname;
 	int i, type, prev;
 	int err;
-	
+
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
@@ -1253,7 +1410,7 @@ asmlinkage long sys_swapoff(const char __user * specialfile)
 	spin_lock(&swap_lock);
 	for (type = swap_list.head; type >= 0; type = swap_info[type].next) {
 		p = swap_info + type;
-		if ((p->flags & SWP_ACTIVE) == SWP_ACTIVE) {
+		if (p->flags & SWP_WRITEOK) {
 			if (p->swap_file->f_mapping == mapping)
 				break;
 		}
@@ -1343,6 +1500,9 @@ asmlinkage long sys_swapoff(const char __user * specialfile)
 	spin_unlock(&swap_lock);
 	mutex_unlock(&swapon_mutex);
 	vfree(swap_map);
+	/* Destroy swap account informatin */
+	swap_cgroup_swapoff(type);
+
 	inode = mapping->host;
 	if (S_ISBLK(inode->i_mode)) {
 		struct block_device *bdev = I_BDEV(inode);
@@ -1426,12 +1586,12 @@ static int swap_show(struct seq_file *swap, void *v)
 	file = ptr->swap_file;
 	len = seq_path(swap, &file->f_path, " \t\n\\");
 	seq_printf(swap, "%*s%s\t%u\t%u\t%d\n",
-		       len < 40 ? 40 - len : 1, " ",
-		       S_ISBLK(file->f_path.dentry->d_inode->i_mode) ?
+			len < 40 ? 40 - len : 1, " ",
+			S_ISBLK(file->f_path.dentry->d_inode->i_mode) ?
 				"partition" : "file\t",
-		       ptr->pages << (PAGE_SHIFT - 10),
-		       ptr->inuse_pages << (PAGE_SHIFT - 10),
-		       ptr->prio);
+			ptr->pages << (PAGE_SHIFT - 10),
+			ptr->inuse_pages << (PAGE_SHIFT - 10),
+			ptr->prio);
 	return 0;
 }
 
@@ -1476,7 +1636,7 @@ late_initcall(max_swapfiles_check);
  *
  * The swapon system call
  */
-asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
+SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 {
 	struct swap_info_struct * p;
 	char *name = NULL;
@@ -1487,12 +1647,11 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 	int i, prev;
 	int error;
 	union swap_header *swap_header = NULL;
-	int swap_header_version;
 	unsigned int nr_good_pages = 0;
 	int nr_extents = 0;
 	sector_t span;
 	unsigned long maxpages = 1;
-	int swapfilesize;
+	unsigned long swapfilepages;
 	unsigned short *swap_map = NULL;
 	struct page *page = NULL;
 	struct inode *inode = NULL;
@@ -1570,7 +1729,7 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 		goto bad_swap;
 	}
 
-	swapfilesize = i_size_read(inode) >> PAGE_SHIFT;
+	swapfilepages = i_size_read(inode) >> PAGE_SHIFT;
 
 	/*
 	 * Read the swap header.
@@ -1584,102 +1743,92 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 		error = PTR_ERR(page);
 		goto bad_swap;
 	}
-	kmap(page);
-	swap_header = page_address(page);
+	swap_header = kmap(page);
 
-	if (!memcmp("SWAP-SPACE",swap_header->magic.magic,10))
-		swap_header_version = 1;
-	else if (!memcmp("SWAPSPACE2",swap_header->magic.magic,10))
-		swap_header_version = 2;
-	else {
+	if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) {
 		printk(KERN_ERR "Unable to find swap-space signature\n");
 		error = -EINVAL;
 		goto bad_swap;
 	}
-	
-	switch (swap_header_version) {
-	case 1:
-		printk(KERN_ERR "version 0 swap is no longer supported. "
-			"Use mkswap -v1 %s\n", name);
+
+	/* swap partition endianess hack... */
+	if (swab32(swap_header->info.version) == 1) {
+		swab32s(&swap_header->info.version);
+		swab32s(&swap_header->info.last_page);
+		swab32s(&swap_header->info.nr_badpages);
+		for (i = 0; i < swap_header->info.nr_badpages; i++)
+			swab32s(&swap_header->info.badpages[i]);
+	}
+	/* Check the swap header's sub-version */
+	if (swap_header->info.version != 1) {
+		printk(KERN_WARNING
+		       "Unable to handle swap header version %d\n",
+		       swap_header->info.version);
 		error = -EINVAL;
 		goto bad_swap;
-	case 2:
-		/* swap partition endianess hack... */
-		if (swab32(swap_header->info.version) == 1) {
-			swab32s(&swap_header->info.version);
-			swab32s(&swap_header->info.last_page);
-			swab32s(&swap_header->info.nr_badpages);
-			for (i = 0; i < swap_header->info.nr_badpages; i++)
-				swab32s(&swap_header->info.badpages[i]);
-		}
-		/* Check the swap header's sub-version and the size of
-                   the swap file and bad block lists */
-		if (swap_header->info.version != 1) {
-			printk(KERN_WARNING
-			       "Unable to handle swap header version %d\n",
-			       swap_header->info.version);
-			error = -EINVAL;
-			goto bad_swap;
-		}
+	}
 
-		p->lowest_bit  = 1;
-		p->cluster_next = 1;
+	p->lowest_bit  = 1;
+	p->cluster_next = 1;
 
-		/*
-		 * Find out how many pages are allowed for a single swap
-		 * device. There are two limiting factors: 1) the number of
-		 * bits for the swap offset in the swp_entry_t type and
-		 * 2) the number of bits in the a swap pte as defined by
-		 * the different architectures. In order to find the
-		 * largest possible bit mask a swap entry with swap type 0
-		 * and swap offset ~0UL is created, encoded to a swap pte,
-		 * decoded to a swp_entry_t again and finally the swap
-		 * offset is extracted. This will mask all the bits from
-		 * the initial ~0UL mask that can't be encoded in either
-		 * the swp_entry_t or the architecture definition of a
-		 * swap pte.
-		 */
-		maxpages = swp_offset(pte_to_swp_entry(swp_entry_to_pte(swp_entry(0,~0UL)))) - 1;
-		if (maxpages > swap_header->info.last_page)
-			maxpages = swap_header->info.last_page;
-		p->highest_bit = maxpages - 1;
+	/*
+	 * Find out how many pages are allowed for a single swap
+	 * device. There are two limiting factors: 1) the number of
+	 * bits for the swap offset in the swp_entry_t type and
+	 * 2) the number of bits in the a swap pte as defined by
+	 * the different architectures. In order to find the
+	 * largest possible bit mask a swap entry with swap type 0
+	 * and swap offset ~0UL is created, encoded to a swap pte,
+	 * decoded to a swp_entry_t again and finally the swap
+	 * offset is extracted. This will mask all the bits from
+	 * the initial ~0UL mask that can't be encoded in either
+	 * the swp_entry_t or the architecture definition of a
+	 * swap pte.
+	 */
+	maxpages = swp_offset(pte_to_swp_entry(
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) - 1;
+	if (maxpages > swap_header->info.last_page)
+		maxpages = swap_header->info.last_page;
+	p->highest_bit = maxpages - 1;
 
-		error = -EINVAL;
-		if (!maxpages)
-			goto bad_swap;
-		if (swapfilesize && maxpages > swapfilesize) {
-			printk(KERN_WARNING
-			       "Swap area shorter than signature indicates\n");
-			goto bad_swap;
-		}
-		if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
-			goto bad_swap;
-		if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
-			goto bad_swap;
+	error = -EINVAL;
+	if (!maxpages)
+		goto bad_swap;
+	if (swapfilepages && maxpages > swapfilepages) {
+		printk(KERN_WARNING
+		       "Swap area shorter than signature indicates\n");
+		goto bad_swap;
+	}
+	if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode))
+		goto bad_swap;
+	if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES)
+		goto bad_swap;
 
-		/* OK, set up the swap map and apply the bad block list */
-		swap_map = vmalloc(maxpages * sizeof(short));
-		if (!swap_map) {
-			error = -ENOMEM;
-			goto bad_swap;
-		}
+	/* OK, set up the swap map and apply the bad block list */
+	swap_map = vmalloc(maxpages * sizeof(short));
+	if (!swap_map) {
+		error = -ENOMEM;
+		goto bad_swap;
+	}
 
-		error = 0;
-		memset(swap_map, 0, maxpages * sizeof(short));
-		for (i = 0; i < swap_header->info.nr_badpages; i++) {
-			int page_nr = swap_header->info.badpages[i];
-			if (page_nr <= 0 || page_nr >= swap_header->info.last_page)
-				error = -EINVAL;
-			else
-				swap_map[page_nr] = SWAP_MAP_BAD;
-		}
-		nr_good_pages = swap_header->info.last_page -
-				swap_header->info.nr_badpages -
-				1 /* header page */;
-		if (error)
+	memset(swap_map, 0, maxpages * sizeof(short));
+	for (i = 0; i < swap_header->info.nr_badpages; i++) {
+		int page_nr = swap_header->info.badpages[i];
+		if (page_nr <= 0 || page_nr >= swap_header->info.last_page) {
+			error = -EINVAL;
 			goto bad_swap;
+		}
+		swap_map[page_nr] = SWAP_MAP_BAD;
 	}
 
+	error = swap_cgroup_swapon(type, maxpages);
+	if (error)
+		goto bad_swap;
+
+	nr_good_pages = swap_header->info.last_page -
+			swap_header->info.nr_badpages -
+			1 /* header page */;
+
 	if (nr_good_pages) {
 		swap_map[0] = SWAP_MAP_BAD;
 		p->max = maxpages;
@@ -1697,6 +1846,13 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 		goto bad_swap;
 	}
 
+	if (blk_queue_nonrot(bdev_get_queue(p->bdev))) {
+		p->flags |= SWP_SOLIDSTATE;
+		p->cluster_next = 1 + (random32() % p->highest_bit);
+	}
+	if (discard_swap(p) == 0)
+		p->flags |= SWP_DISCARDABLE;
+
 	mutex_lock(&swapon_mutex);
 	spin_lock(&swap_lock);
 	if (swap_flags & SWAP_FLAG_PREFER)
@@ -1705,14 +1861,16 @@ asmlinkage long sys_swapon(const char __user * specialfile, int swap_flags)
 	else
 		p->prio = --least_priority;
 	p->swap_map = swap_map;
-	p->flags = SWP_ACTIVE;
+	p->flags |= SWP_WRITEOK;
 	nr_swap_pages += nr_good_pages;
 	total_swap_pages += nr_good_pages;
 
 	printk(KERN_INFO "Adding %uk swap on %s.  "
-			"Priority:%d extents:%d across:%lluk\n",
+			"Priority:%d extents:%d across:%lluk %s%s\n",
 		nr_good_pages<<(PAGE_SHIFT-10), name, p->prio,
-		nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10));
+		nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
+		(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
+		(p->flags & SWP_DISCARDABLE) ? "D" : "");
 
 	/* insert swap space into swap_list: */
 	prev = -1;
@@ -1738,6 +1896,7 @@ bad_swap:
 		bd_release(bdev);
 	}
 	destroy_swap_extents(p);
+	swap_cgroup_swapoff(type);
 bad_swap_2:
 	spin_lock(&swap_lock);
 	p->swap_file = NULL;
diff --git a/mm/tiny-shmem.c b/mm/tiny-shmem.c
deleted file mode 100644
index 3e67d575ee6e..000000000000
--- a/mm/tiny-shmem.c
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- * tiny-shmem.c: simple shmemfs and tmpfs using ramfs code
- *
- * Matt Mackall <mpm@selenic.com> January, 2004
- * derived from mm/shmem.c and fs/ramfs/inode.c
- *
- * This is intended for small system where the benefits of the full
- * shmem code (swap-backed and resource-limited) are outweighed by
- * their complexity. On systems without swap this code should be
- * effectively equivalent, but much lighter weight.
- */
-
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/vfs.h>
-#include <linux/mount.h>
-#include <linux/file.h>
-#include <linux/mm.h>
-#include <linux/module.h>
-#include <linux/swap.h>
-#include <linux/ramfs.h>
-
-static struct file_system_type tmpfs_fs_type = {
-	.name		= "tmpfs",
-	.get_sb		= ramfs_get_sb,
-	.kill_sb	= kill_litter_super,
-};
-
-static struct vfsmount *shm_mnt;
-
-static int __init init_tmpfs(void)
-{
-	BUG_ON(register_filesystem(&tmpfs_fs_type) != 0);
-
-	shm_mnt = kern_mount(&tmpfs_fs_type);
-	BUG_ON(IS_ERR(shm_mnt));
-
-	return 0;
-}
-module_init(init_tmpfs)
-
-/**
- * shmem_file_setup - get an unlinked file living in tmpfs
- * @name: name for dentry (to be seen in /proc/<pid>/maps
- * @size: size to be set for the file
- * @flags: vm_flags
- */
-struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
-{
-	int error;
-	struct file *file;
-	struct inode *inode;
-	struct dentry *dentry, *root;
-	struct qstr this;
-
-	if (IS_ERR(shm_mnt))
-		return (void *)shm_mnt;
-
-	error = -ENOMEM;
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0; /* will go */
-	root = shm_mnt->mnt_root;
-	dentry = d_alloc(root, &this);
-	if (!dentry)
-		goto put_memory;
-
-	error = -ENFILE;
-	file = get_empty_filp();
-	if (!file)
-		goto put_dentry;
-
-	error = -ENOSPC;
-	inode = ramfs_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
-	if (!inode)
-		goto close_file;
-
-	d_instantiate(dentry, inode);
-	inode->i_size = size;
-	inode->i_nlink = 0;	/* It is unlinked */
-	init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
-			&ramfs_file_operations);
-
-#ifndef CONFIG_MMU
-	error = ramfs_nommu_expand_for_mapping(inode, size);
-	if (error)
-		goto close_file;
-#endif
-	return file;
-
-close_file:
-	put_filp(file);
-put_dentry:
-	dput(dentry);
-put_memory:
-	return ERR_PTR(error);
-}
-EXPORT_SYMBOL_GPL(shmem_file_setup);
-
-/**
- * shmem_zero_setup - setup a shared anonymous mapping
- * @vma: the vma to be mmapped is prepared by do_mmap_pgoff
- */
-int shmem_zero_setup(struct vm_area_struct *vma)
-{
-	struct file *file;
-	loff_t size = vma->vm_end - vma->vm_start;
-
-	file = shmem_file_setup("dev/zero", size, vma->vm_flags);
-	if (IS_ERR(file))
-		return PTR_ERR(file);
-
-	if (vma->vm_file)
-		fput(vma->vm_file);
-	vma->vm_file = file;
-	vma->vm_ops = &generic_file_vm_ops;
-	return 0;
-}
-
-int shmem_unuse(swp_entry_t entry, struct page *page)
-{
-	return 0;
-}
-
-#ifndef CONFIG_MMU
-unsigned long shmem_get_unmapped_area(struct file *file,
-				      unsigned long addr,
-				      unsigned long len,
-				      unsigned long pgoff,
-				      unsigned long flags)
-{
-	return ramfs_nommu_get_unmapped_area(file, addr, len, pgoff, flags);
-}
-#endif
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 1ddb77ba3995..75f49d312e8c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -23,6 +23,7 @@
 #include <linux/rbtree.h>
 #include <linux/radix-tree.h>
 #include <linux/rcupdate.h>
+#include <linux/bootmem.h>
 
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
@@ -151,11 +152,12 @@ static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
  *
  * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
  */
-static int vmap_page_range(unsigned long addr, unsigned long end,
+static int vmap_page_range(unsigned long start, unsigned long end,
 				pgprot_t prot, struct page **pages)
 {
 	pgd_t *pgd;
 	unsigned long next;
+	unsigned long addr = start;
 	int err = 0;
 	int nr = 0;
 
@@ -167,7 +169,7 @@ static int vmap_page_range(unsigned long addr, unsigned long end,
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
-	flush_cache_vmap(addr, end);
+	flush_cache_vmap(start, end);
 
 	if (unlikely(err))
 		return err;
@@ -380,8 +382,9 @@ found:
 			goto retry;
 		}
 		if (printk_ratelimit())
-			printk(KERN_WARNING "vmap allocation failed: "
-				 "use vmalloc=<size> to increase size.\n");
+			printk(KERN_WARNING
+				"vmap allocation for size %lu failed: "
+				"use vmalloc=<size> to increase size.\n", size);
 		return ERR_PTR(-EBUSY);
 	}
 
@@ -431,6 +434,27 @@ static void unmap_vmap_area(struct vmap_area *va)
 	vunmap_page_range(va->va_start, va->va_end);
 }
 
+static void vmap_debug_free_range(unsigned long start, unsigned long end)
+{
+	/*
+	 * Unmap page tables and force a TLB flush immediately if
+	 * CONFIG_DEBUG_PAGEALLOC is set. This catches use after free
+	 * bugs similarly to those in linear kernel virtual address
+	 * space after a page has been freed.
+	 *
+	 * All the lazy freeing logic is still retained, in order to
+	 * minimise intrusiveness of this debugging feature.
+	 *
+	 * This is going to be *slow* (linear kernel virtual address
+	 * debugging doesn't do a broadcast TLB flush so it is a lot
+	 * faster).
+	 */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	vunmap_page_range(start, end);
+	flush_tlb_kernel_range(start, end);
+#endif
+}
+
 /*
  * lazy_max_pages is the maximum amount of virtual address space we gather up
  * before attempting to purge with a TLB flush.
@@ -911,6 +935,7 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 	BUG_ON(addr & (PAGE_SIZE-1));
 
 	debug_check_no_locks_freed(mem, size);
+	vmap_debug_free_range(addr, addr+size);
 
 	if (likely(count <= VMAP_MAX_ALLOC))
 		vb_free(mem, size);
@@ -959,6 +984,8 @@ EXPORT_SYMBOL(vm_map_ram);
 
 void __init vmalloc_init(void)
 {
+	struct vmap_area *va;
+	struct vm_struct *tmp;
 	int i;
 
 	for_each_possible_cpu(i) {
@@ -971,6 +998,14 @@ void __init vmalloc_init(void)
 		vbq->nr_dirty = 0;
 	}
 
+	/* Import existing vmlist entries. */
+	for (tmp = vmlist; tmp; tmp = tmp->next) {
+		va = alloc_bootmem(sizeof(struct vmap_area));
+		va->flags = tmp->flags | VM_VM_AREA;
+		va->va_start = (unsigned long)tmp->addr;
+		va->va_end = va->va_start + tmp->size;
+		__insert_vmap_area(va);
+	}
 	vmap_initialized = true;
 }
 
@@ -1127,6 +1162,8 @@ struct vm_struct *remove_vm_area(const void *addr)
 	if (va && va->flags & VM_VM_AREA) {
 		struct vm_struct *vm = va->private;
 		struct vm_struct *tmp, **p;
+
+		vmap_debug_free_range(va->va_start, va->va_end);
 		free_unmap_vmap_area(va);
 		vm->size -= PAGE_SIZE;
 
@@ -1374,7 +1411,8 @@ void *vmalloc_user(unsigned long size)
 	struct vm_struct *area;
 	void *ret;
 
-	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
+	ret = __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+			     PAGE_KERNEL, -1, __builtin_return_address(0));
 	if (ret) {
 		area = find_vm_area(ret);
 		area->flags |= VM_USERMAP;
@@ -1419,7 +1457,8 @@ EXPORT_SYMBOL(vmalloc_node);
 
 void *vmalloc_exec(unsigned long size)
 {
-	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
+	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
+			      -1, __builtin_return_address(0));
 }
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_ZONE_DMA32)
@@ -1439,7 +1478,8 @@ void *vmalloc_exec(unsigned long size)
  */
 void *vmalloc_32(unsigned long size)
 {
-	return __vmalloc(size, GFP_VMALLOC32, PAGE_KERNEL);
+	return __vmalloc_node(size, GFP_VMALLOC32, PAGE_KERNEL,
+			      -1, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc_32);
 
@@ -1455,7 +1495,8 @@ void *vmalloc_32_user(unsigned long size)
 	struct vm_struct *area;
 	void *ret;
 
-	ret = __vmalloc(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL);
+	ret = __vmalloc_node(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
+			     -1, __builtin_return_address(0));
 	if (ret) {
 		area = find_vm_area(ret);
 		area->flags |= VM_USERMAP;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 62e7f62fb559..9a27c44aa327 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -52,6 +52,9 @@ struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
 
+	/* Number of pages freed so far during a call to shrink_zones() */
+	unsigned long nr_reclaimed;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
@@ -122,11 +125,30 @@ static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
-#define scan_global_lru(sc)	(!(sc)->mem_cgroup)
+#define scanning_global_lru(sc)	(!(sc)->mem_cgroup)
 #else
-#define scan_global_lru(sc)	(1)
+#define scanning_global_lru(sc)	(1)
 #endif
 
+static struct zone_reclaim_stat *get_reclaim_stat(struct zone *zone,
+						  struct scan_control *sc)
+{
+	if (!scanning_global_lru(sc))
+		return mem_cgroup_get_reclaim_stat(sc->mem_cgroup, zone);
+
+	return &zone->reclaim_stat;
+}
+
+static unsigned long zone_nr_pages(struct zone *zone, struct scan_control *sc,
+				   enum lru_list lru)
+{
+	if (!scanning_global_lru(sc))
+		return mem_cgroup_zone_nr_pages(sc->mem_cgroup, zone, lru);
+
+	return zone_page_state(zone, NR_LRU_BASE + lru);
+}
+
+
 /*
  * Add a shrinker callback to be called from the vm
  */
@@ -509,7 +531,6 @@ redo:
 		lru = LRU_UNEVICTABLE;
 		add_page_to_unevictable_list(page);
 	}
-	mem_cgroup_move_lists(page, lru);
 
 	/*
 	 * page's status can change while we move it among lru. If an evictable
@@ -544,7 +565,6 @@ void putback_lru_page(struct page *page)
 
 	lru = !!TestClearPageActive(page) + page_is_file_cache(page);
 	lru_cache_add_lru(page, lru);
-	mem_cgroup_move_lists(page, lru);
 	put_page(page);
 }
 #endif /* CONFIG_UNEVICTABLE_LRU */
@@ -617,7 +637,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 					referenced && page_mapping_inuse(page))
 			goto activate_locked;
 
-#ifdef CONFIG_SWAP
 		/*
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
@@ -625,20 +644,10 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (PageAnon(page) && !PageSwapCache(page)) {
 			if (!(sc->gfp_mask & __GFP_IO))
 				goto keep_locked;
-			switch (try_to_munlock(page)) {
-			case SWAP_FAIL:		/* shouldn't happen */
-			case SWAP_AGAIN:
-				goto keep_locked;
-			case SWAP_MLOCK:
-				goto cull_mlocked;
-			case SWAP_SUCCESS:
-				; /* fall thru'; add to swap cache */
-			}
-			if (!add_to_swap(page, GFP_ATOMIC))
+			if (!add_to_swap(page))
 				goto activate_locked;
 			may_enter_fs = 1;
 		}
-#endif /* CONFIG_SWAP */
 
 		mapping = page_mapping(page);
 
@@ -752,6 +761,8 @@ free_it:
 		continue;
 
 cull_mlocked:
+		if (PageSwapCache(page))
+			try_to_free_swap(page);
 		unlock_page(page);
 		putback_lru_page(page);
 		continue;
@@ -759,7 +770,7 @@ cull_mlocked:
 activate_locked:
 		/* Not a candidate for swapping, so reclaim swap space. */
 		if (PageSwapCache(page) && vm_swap_full())
-			remove_exclusive_swap_page_ref(page);
+			try_to_free_swap(page);
 		VM_BUG_ON(PageActive(page));
 		SetPageActive(page);
 		pgactivate++;
@@ -819,6 +830,7 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 		return ret;
 
 	ret = -EBUSY;
+
 	if (likely(get_page_unless_zero(page))) {
 		/*
 		 * Be careful not to clear PageLRU until after we're
@@ -827,6 +839,7 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 		 */
 		ClearPageLRU(page);
 		ret = 0;
+		mem_cgroup_del_lru(page);
 	}
 
 	return ret;
@@ -1035,6 +1048,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 	struct pagevec pvec;
 	unsigned long nr_scanned = 0;
 	unsigned long nr_reclaimed = 0;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	pagevec_init(&pvec, 1);
 
@@ -1076,13 +1090,14 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		__mod_zone_page_state(zone, NR_INACTIVE_ANON,
 						-count[LRU_INACTIVE_ANON]);
 
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc))
 			zone->pages_scanned += nr_scan;
-			zone->recent_scanned[0] += count[LRU_INACTIVE_ANON];
-			zone->recent_scanned[0] += count[LRU_ACTIVE_ANON];
-			zone->recent_scanned[1] += count[LRU_INACTIVE_FILE];
-			zone->recent_scanned[1] += count[LRU_ACTIVE_FILE];
-		}
+
+		reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
+		reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
+		reclaim_stat->recent_scanned[1] += count[LRU_INACTIVE_FILE];
+		reclaim_stat->recent_scanned[1] += count[LRU_ACTIVE_FILE];
+
 		spin_unlock_irq(&zone->lru_lock);
 
 		nr_scanned += nr_scan;
@@ -1114,7 +1129,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		if (current_is_kswapd()) {
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
 			__count_vm_events(KSWAPD_STEAL, nr_freed);
-		} else if (scan_global_lru(sc))
+		} else if (scanning_global_lru(sc))
 			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
 
 		__count_zone_vm_events(PGSTEAL, zone, nr_freed);
@@ -1140,10 +1155,9 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			SetPageLRU(page);
 			lru = page_lru(page);
 			add_page_to_lru_list(zone, page, lru);
-			mem_cgroup_move_lists(page, lru);
-			if (PageActive(page) && scan_global_lru(sc)) {
+			if (PageActive(page)) {
 				int file = !!page_is_file_cache(page);
-				zone->recent_rotated[file]++;
+				reclaim_stat->recent_rotated[file]++;
 			}
 			if (!pagevec_add(&pvec, page)) {
 				spin_unlock_irq(&zone->lru_lock);
@@ -1173,11 +1187,6 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority)
 		zone->prev_priority = priority;
 }
 
-static inline int zone_is_near_oom(struct zone *zone)
-{
-	return zone->pages_scanned >= (zone_lru_pages(zone) * 3);
-}
-
 /*
  * This moves pages from the active list to the inactive list.
  *
@@ -1208,6 +1217,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	struct page *page;
 	struct pagevec pvec;
 	enum lru_list lru;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
@@ -1218,10 +1228,10 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * zone->pages_scanned is used for detect zone's oom
 	 * mem_cgroup remembers nr_scan by itself.
 	 */
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		zone->pages_scanned += pgscanned;
-		zone->recent_scanned[!!file] += pgmoved;
 	}
+	reclaim_stat->recent_scanned[!!file] += pgmoved;
 
 	if (file)
 		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
@@ -1248,6 +1258,13 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		list_add(&page->lru, &l_inactive);
 	}
 
+	/*
+	 * Move the pages to the [file or anon] inactive list.
+	 */
+	pagevec_init(&pvec, 1);
+	pgmoved = 0;
+	lru = LRU_BASE + file * LRU_FILE;
+
 	spin_lock_irq(&zone->lru_lock);
 	/*
 	 * Count referenced pages from currently used mappings as
@@ -1255,15 +1272,8 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * This helps balance scan pressure between file and anonymous
 	 * pages in get_scan_ratio.
 	 */
-	zone->recent_rotated[!!file] += pgmoved;
+	reclaim_stat->recent_rotated[!!file] += pgmoved;
 
-	/*
-	 * Move the pages to the [file or anon] inactive list.
-	 */
-	pagevec_init(&pvec, 1);
-
-	pgmoved = 0;
-	lru = LRU_BASE + file * LRU_FILE;
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
 		prefetchw_prev_lru_page(page, &l_inactive, flags);
@@ -1273,7 +1283,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		ClearPageActive(page);
 
 		list_move(&page->lru, &zone->lru[lru].list);
-		mem_cgroup_move_lists(page, lru);
+		mem_cgroup_add_lru_list(page, lru);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
 			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
@@ -1302,6 +1312,38 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	pagevec_release(&pvec);
 }
 
+static int inactive_anon_is_low_global(struct zone *zone)
+{
+	unsigned long active, inactive;
+
+	active = zone_page_state(zone, NR_ACTIVE_ANON);
+	inactive = zone_page_state(zone, NR_INACTIVE_ANON);
+
+	if (inactive * zone->inactive_ratio < active)
+		return 1;
+
+	return 0;
+}
+
+/**
+ * inactive_anon_is_low - check if anonymous pages need to be deactivated
+ * @zone: zone to check
+ * @sc:   scan control of this context
+ *
+ * Returns true if the zone does not have enough inactive anon pages,
+ * meaning some active anon pages need to be deactivated.
+ */
+static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
+{
+	int low;
+
+	if (scanning_global_lru(sc))
+		low = inactive_anon_is_low_global(zone);
+	else
+		low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
+	return low;
+}
+
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 	struct zone *zone, struct scan_control *sc, int priority)
 {
@@ -1312,8 +1354,7 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 		return 0;
 	}
 
-	if (lru == LRU_ACTIVE_ANON &&
-	    (!scan_global_lru(sc) || inactive_anon_is_low(zone))) {
+	if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) {
 		shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
@@ -1335,12 +1376,7 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	unsigned long anon, file, free;
 	unsigned long anon_prio, file_prio;
 	unsigned long ap, fp;
-
-	anon  = zone_page_state(zone, NR_ACTIVE_ANON) +
-		zone_page_state(zone, NR_INACTIVE_ANON);
-	file  = zone_page_state(zone, NR_ACTIVE_FILE) +
-		zone_page_state(zone, NR_INACTIVE_FILE);
-	free  = zone_page_state(zone, NR_FREE_PAGES);
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (nr_swap_pages <= 0) {
@@ -1349,11 +1385,20 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 		return;
 	}
 
-	/* If we have very few page cache pages, force-scan anon pages. */
-	if (unlikely(file + free <= zone->pages_high)) {
-		percent[0] = 100;
-		percent[1] = 0;
-		return;
+	anon  = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_pages(zone, sc, LRU_INACTIVE_FILE);
+
+	if (scanning_global_lru(sc)) {
+		free  = zone_page_state(zone, NR_FREE_PAGES);
+		/* If we have very few page cache pages,
+		   force-scan anon pages. */
+		if (unlikely(file + free <= zone->pages_high)) {
+			percent[0] = 100;
+			percent[1] = 0;
+			return;
+		}
 	}
 
 	/*
@@ -1367,17 +1412,17 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	 *
 	 * anon in [0], file in [1]
 	 */
-	if (unlikely(zone->recent_scanned[0] > anon / 4)) {
+	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
 		spin_lock_irq(&zone->lru_lock);
-		zone->recent_scanned[0] /= 2;
-		zone->recent_rotated[0] /= 2;
+		reclaim_stat->recent_scanned[0] /= 2;
+		reclaim_stat->recent_rotated[0] /= 2;
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	if (unlikely(zone->recent_scanned[1] > file / 4)) {
+	if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
 		spin_lock_irq(&zone->lru_lock);
-		zone->recent_scanned[1] /= 2;
-		zone->recent_rotated[1] /= 2;
+		reclaim_stat->recent_scanned[1] /= 2;
+		reclaim_stat->recent_rotated[1] /= 2;
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
@@ -1393,11 +1438,11 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	 * proportional to the fraction of recently scanned pages on
 	 * each list that were recently referenced and in active use.
 	 */
-	ap = (anon_prio + 1) * (zone->recent_scanned[0] + 1);
-	ap /= zone->recent_rotated[0] + 1;
+	ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
+	ap /= reclaim_stat->recent_rotated[0] + 1;
 
-	fp = (file_prio + 1) * (zone->recent_scanned[1] + 1);
-	fp /= zone->recent_rotated[1] + 1;
+	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
+	fp /= reclaim_stat->recent_rotated[1] + 1;
 
 	/* Normalize to percentages */
 	percent[0] = 100 * ap / (ap + fp + 1);
@@ -1408,69 +1453,72 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
-static unsigned long shrink_zone(int priority, struct zone *zone,
+static void shrink_zone(int priority, struct zone *zone,
 				struct scan_control *sc)
 {
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
-	unsigned long nr_reclaimed = 0;
 	unsigned long percent[2];	/* anon @ 0; file @ 1 */
 	enum lru_list l;
+	unsigned long nr_reclaimed = sc->nr_reclaimed;
+	unsigned long swap_cluster_max = sc->swap_cluster_max;
 
 	get_scan_ratio(zone, sc, percent);
 
 	for_each_evictable_lru(l) {
-		if (scan_global_lru(sc)) {
-			int file = is_file_lru(l);
-			int scan;
-
-			scan = zone_page_state(zone, NR_LRU_BASE + l);
-			if (priority) {
-				scan >>= priority;
-				scan = (scan * percent[file]) / 100;
-			}
+		int file = is_file_lru(l);
+		int scan;
+
+		scan = zone_page_state(zone, NR_LRU_BASE + l);
+		if (priority) {
+			scan >>= priority;
+			scan = (scan * percent[file]) / 100;
+		}
+		if (scanning_global_lru(sc)) {
 			zone->lru[l].nr_scan += scan;
 			nr[l] = zone->lru[l].nr_scan;
-			if (nr[l] >= sc->swap_cluster_max)
+			if (nr[l] >= swap_cluster_max)
 				zone->lru[l].nr_scan = 0;
 			else
 				nr[l] = 0;
-		} else {
-			/*
-			 * This reclaim occurs not because zone memory shortage
-			 * but because memory controller hits its limit.
-			 * Don't modify zone reclaim related data.
-			 */
-			nr[l] = mem_cgroup_calc_reclaim(sc->mem_cgroup, zone,
-								priority, l);
-		}
+		} else
+			nr[l] = scan;
 	}
 
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {
 			if (nr[l]) {
-				nr_to_scan = min(nr[l],
-					(unsigned long)sc->swap_cluster_max);
+				nr_to_scan = min(nr[l], swap_cluster_max);
 				nr[l] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(l, nr_to_scan,
-							zone, sc, priority);
+							    zone, sc, priority);
 			}
 		}
+		/*
+		 * On large memory systems, scan >> priority can become
+		 * really large. This is fine for the starting priority;
+		 * we want to put equal scanning pressure on each zone.
+		 * However, if the VM has a harder time of freeing pages,
+		 * with multiple processes reclaiming pages, the total
+		 * freeing target can get unreasonably large.
+		 */
+		if (nr_reclaimed > swap_cluster_max &&
+			priority < DEF_PRIORITY && !current_is_kswapd())
+			break;
 	}
 
+	sc->nr_reclaimed = nr_reclaimed;
+
 	/*
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (!scan_global_lru(sc) || inactive_anon_is_low(zone))
-		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
-	else if (!scan_global_lru(sc))
+	if (inactive_anon_is_low(zone, sc))
 		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
 
 	throttle_vm_writeout(sc->gfp_mask);
-	return nr_reclaimed;
 }
 
 /*
@@ -1484,16 +1532,13 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
  * b) The zones may be over pages_high but they must go *over* pages_high to
  *    satisfy the `incremental min' zone defense algorithm.
  *
- * Returns the number of reclaimed pages.
- *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
-	unsigned long nr_reclaimed = 0;
 	struct zoneref *z;
 	struct zone *zone;
 
@@ -1505,7 +1550,7 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 		 * Take care memory controller reclaiming has small influence
 		 * to global LRU.
 		 */
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc)) {
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
 			note_zone_scanning_priority(zone, priority);
@@ -1524,10 +1569,8 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 							priority);
 		}
 
-		nr_reclaimed += shrink_zone(priority, zone, sc);
+		shrink_zone(priority, zone, sc);
 	}
-
-	return nr_reclaimed;
 }
 
 /*
@@ -1552,7 +1595,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	int priority;
 	unsigned long ret = 0;
 	unsigned long total_scanned = 0;
-	unsigned long nr_reclaimed = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long lru_pages = 0;
 	struct zoneref *z;
@@ -1561,12 +1603,12 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 	delayacct_freepages_start();
 
-	if (scan_global_lru(sc))
+	if (scanning_global_lru(sc))
 		count_vm_event(ALLOCSTALL);
 	/*
 	 * mem_cgroup will not do shrink_slab.
 	 */
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
@@ -1580,21 +1622,21 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		nr_reclaimed += shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
 		 */
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc)) {
 			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
 			if (reclaim_state) {
-				nr_reclaimed += reclaim_state->reclaimed_slab;
+				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
 				reclaim_state->reclaimed_slab = 0;
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (nr_reclaimed >= sc->swap_cluster_max) {
-			ret = nr_reclaimed;
+		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+			ret = sc->nr_reclaimed;
 			goto out;
 		}
 
@@ -1616,8 +1658,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			congestion_wait(WRITE, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (!sc->all_unreclaimable && scan_global_lru(sc))
-		ret = nr_reclaimed;
+	if (!sc->all_unreclaimable && scanning_global_lru(sc))
+		ret = sc->nr_reclaimed;
 out:
 	/*
 	 * Now that we've scanned all the zones at this priority level, note
@@ -1629,7 +1671,7 @@ out:
 	if (priority < 0)
 		priority = 0;
 
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
@@ -1665,19 +1707,24 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
-						gfp_t gfp_mask)
+					   gfp_t gfp_mask,
+					   bool noswap,
+					   unsigned int swappiness)
 {
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
-		.swappiness = vm_swappiness,
+		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
 		.isolate_pages = mem_cgroup_isolate_pages,
 	};
 	struct zonelist *zonelist;
 
+	if (noswap)
+		sc.may_swap = 0;
+
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
@@ -1712,7 +1759,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	int priority;
 	int i;
 	unsigned long total_scanned;
-	unsigned long nr_reclaimed;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
@@ -1731,7 +1777,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 
 loop_again:
 	total_scanned = 0;
-	nr_reclaimed = 0;
+	sc.nr_reclaimed = 0;
 	sc.may_writepage = !laptop_mode;
 	count_vm_event(PAGEOUTRUN);
 
@@ -1766,7 +1812,7 @@ loop_again:
 			 * Do some background aging of the anon list, to give
 			 * pages a chance to be referenced before reclaiming.
 			 */
-			if (inactive_anon_is_low(zone))
+			if (inactive_anon_is_low(zone, &sc))
 				shrink_active_list(SWAP_CLUSTER_MAX, zone,
 							&sc, priority, 0);
 
@@ -1817,11 +1863,11 @@ loop_again:
 			 */
 			if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
 						end_zone, 0))
-				nr_reclaimed += shrink_zone(priority, zone, &sc);
+				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
 						lru_pages);
-			nr_reclaimed += reclaim_state->reclaimed_slab;
+			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 			if (zone_is_all_unreclaimable(zone))
 				continue;
@@ -1835,7 +1881,7 @@ loop_again:
 			 * even in laptop mode
 			 */
 			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
-			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
+			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 		}
 		if (all_zones_ok)
@@ -1853,7 +1899,7 @@ loop_again:
 		 * matches the direct reclaim path behaviour in terms of impact
 		 * on zone->*_priority.
 		 */
-		if (nr_reclaimed >= SWAP_CLUSTER_MAX)
+		if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
 			break;
 	}
 out:
@@ -1872,10 +1918,27 @@ out:
 
 		try_to_freeze();
 
+		/*
+		 * Fragmentation may mean that the system cannot be
+		 * rebalanced for high-order allocations in all zones.
+		 * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
+		 * it means the zones have been fully scanned and are still
+		 * not balanced. For high-order allocations, there is
+		 * little point trying all over again as kswapd may
+		 * infinite loop.
+		 *
+		 * Instead, recheck all watermarks at order-0 as they
+		 * are the most important. If watermarks are ok, kswapd will go
+		 * back to sleep. High-order users can still perform direct
+		 * reclaim if they wish.
+		 */
+		if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
+			order = sc.order = 0;
+
 		goto loop_again;
 	}
 
-	return nr_reclaimed;
+	return sc.nr_reclaimed;
 }
 
 /*
@@ -1902,7 +1965,7 @@ static int kswapd(void *p)
 	};
 	node_to_cpumask_ptr(cpumask, pgdat->node_id);
 
-	if (!cpus_empty(*cpumask))
+	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
 	current->reclaim_state = &reclaim_state;
 
@@ -2141,7 +2204,7 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 			pg_data_t *pgdat = NODE_DATA(nid);
 			node_to_cpumask_ptr(mask, pgdat->node_id);
 
-			if (any_online_cpu(*mask) < nr_cpu_ids)
+			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
 				/* One of our CPUs online: restore mask */
 				set_cpus_allowed_ptr(pgdat->kswapd, mask);
 		}
@@ -2227,7 +2290,6 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
 	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),
@@ -2260,9 +2322,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		priority = ZONE_RECLAIM_PRIORITY;
 		do {
 			note_zone_scanning_priority(zone, priority);
-			nr_reclaimed += shrink_zone(priority, zone, &sc);
+			shrink_zone(priority, zone, &sc);
 			priority--;
-		} while (priority >= 0 && nr_reclaimed < nr_pages);
+		} while (priority >= 0 && sc.nr_reclaimed < nr_pages);
 	}
 
 	slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
@@ -2286,13 +2348,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * Update nr_reclaimed by the number of slab pages we
 		 * reclaimed from this zone.
 		 */
-		nr_reclaimed += slab_reclaimable -
+		sc.nr_reclaimed += slab_reclaimable -
 			zone_page_state(zone, NR_SLAB_RECLAIMABLE);
 	}
 
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
-	return nr_reclaimed >= nr_pages;
+	return sc.nr_reclaimed >= nr_pages;
 }
 
 int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
@@ -2393,6 +2455,7 @@ retry:
 
 		__dec_zone_state(zone, NR_UNEVICTABLE);
 		list_move(&page->lru, &zone->lru[l].list);
+		mem_cgroup_move_lists(page, LRU_UNEVICTABLE, l);
 		__inc_zone_state(zone, NR_INACTIVE_ANON + l);
 		__count_vm_event(UNEVICTABLE_PGRESCUED);
 	} else {
@@ -2401,6 +2464,7 @@ retry:
 		 */
 		SetPageUnevictable(page);
 		list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
+		mem_cgroup_rotate_lru_list(page, LRU_UNEVICTABLE);
 		if (page_evictable(page, NULL))
 			goto retry;
 	}
@@ -2472,7 +2536,7 @@ void scan_mapping_unevictable_pages(struct address_space *mapping)
  * back onto @zone's unevictable list.
  */
 #define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
-void scan_zone_unevictable_pages(struct zone *zone)
+static void scan_zone_unevictable_pages(struct zone *zone)
 {
 	struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
 	unsigned long scan;
@@ -2514,7 +2578,7 @@ void scan_zone_unevictable_pages(struct zone *zone)
  * that has possibly/probably made some previously unevictable pages
  * evictable.
  */
-void scan_all_zones_unevictable_pages(void)
+static void scan_all_zones_unevictable_pages(void)
 {
 	struct zone *zone;
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c3ccfda23adc..91149746bb8d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -20,7 +20,7 @@
 DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
 EXPORT_PER_CPU_SYMBOL(vm_event_states);
 
-static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask)
+static void sum_vm_events(unsigned long *ret, const struct cpumask *cpumask)
 {
 	int cpu;
 	int i;
@@ -43,7 +43,7 @@ static void sum_vm_events(unsigned long *ret, cpumask_t *cpumask)
 void all_vm_events(unsigned long *ret)
 {
 	get_online_cpus();
-	sum_vm_events(ret, &cpu_online_map);
+	sum_vm_events(ret, cpu_online_mask);
 	put_online_cpus();
 }
 EXPORT_SYMBOL_GPL(all_vm_events);