Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

Conflicts:
	drivers/scsi/fcoe/fcoe.c

14 files changed, 249 insertions, 181 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index b53427ad30a..c2b57d81e15 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -213,6 +213,8 @@ config UNEVICTABLE_LRU
 	  will use one page flag and increase the code size a little,
 	  say Y unless you know what you are doing.
 
+	  See Documentation/vm/unevictable-lru.txt for more information.
+
 config HAVE_MLOCK
 	bool
 	default y if MMU=y
@@ -223,3 +225,31 @@ config HAVE_MLOCKED_PAGE_BIT
 
 config MMU_NOTIFIER
 	bool
+
+config NOMMU_INITIAL_TRIM_EXCESS
+	int "Turn on mmap() excess space trimming before booting"
+	depends on !MMU
+	default 1
+	help
+	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
+	  of memory on which to store mappings, but it can only ask the system
+	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
+	  more than it requires.  To deal with this, mmap() is able to trim off
+	  the excess and return it to the allocator.
+
+	  If trimming is enabled, the excess is trimmed off and returned to the
+	  system allocator, which can cause extra fragmentation, particularly
+	  if there are a lot of transient processes.
+
+	  If trimming is disabled, the excess is kept, but not used, which for
+	  long-term mappings means that the space is wasted.
+
+	  Trimming can be dynamically controlled through a sysctl option
+	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
+	  excess pages there must be before trimming should occur, or zero if
+	  no trimming is to occur.
+
+	  This option specifies the initial value of this option.  The default
+	  of 1 says that all excess pages should be trimmed.
+
+	  See Documentation/nommu-mmap.txt for more information.
diff --git a/mm/filemap.c b/mm/filemap.c
index 2e2d38ebda4..379ff0bcbf6 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -441,6 +441,7 @@ int filemap_write_and_wait_range(struct address_space *mapping,
 	}
 	return err;
 }
+EXPORT_SYMBOL(filemap_write_and_wait_range);
 
 /**
  * add_to_page_cache_locked - add a locked page to the pagecache
@@ -567,8 +568,8 @@ EXPORT_SYMBOL(wait_on_page_bit);
 
 /**
  * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
- * @page - Page defining the wait queue of interest
- * @waiter - Waiter to add to the queue
+ * @page: Page defining the wait queue of interest
+ * @waiter: Waiter to add to the queue
  *
  * Add an arbitrary @waiter to the wait queue for the nominated @page.
  */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 2fc6d6c4823..01c2d8f1468 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -932,7 +932,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 	if (unlikely(!mem))
 		return 0;
 
-	VM_BUG_ON(mem_cgroup_is_obsolete(mem));
+	VM_BUG_ON(!mem || mem_cgroup_is_obsolete(mem));
 
 	while (1) {
 		int ret;
@@ -1024,9 +1024,7 @@ static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 		return NULL;
 
 	pc = lookup_page_cgroup(page);
-	/*
-	 * Used bit of swapcache is solid under page lock.
-	 */
+	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc)) {
 		mem = pc->mem_cgroup;
 		if (mem && !css_tryget(&mem->css))
@@ -1040,6 +1038,7 @@ static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 			mem = NULL;
 		rcu_read_unlock();
 	}
+	unlock_page_cgroup(pc);
 	return mem;
 }
 
@@ -1618,37 +1617,28 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
 }
 
 /*
- * A call to try to shrink memory usage under specified resource controller.
- * This is typically used for page reclaiming for shmem for reducing side
- * effect of page allocation from shmem, which is used by some mem_cgroup.
+ * A call to try to shrink memory usage on charge failure at shmem's swapin.
+ * Calling hierarchical_reclaim is not enough because we should update
+ * last_oom_jiffies to prevent pagefault_out_of_memory from invoking global OOM.
+ * Moreover considering hierarchy, we should reclaim from the mem_over_limit,
+ * not from the memcg which this page would be charged to.
+ * try_charge_swapin does all of these works properly.
  */
-int mem_cgroup_shrink_usage(struct page *page,
+int mem_cgroup_shmem_charge_fallback(struct page *page,
 			    struct mm_struct *mm,
 			    gfp_t gfp_mask)
 {
 	struct mem_cgroup *mem = NULL;
-	int progress = 0;
-	int retry = MEM_CGROUP_RECLAIM_RETRIES;
+	int ret;
 
 	if (mem_cgroup_disabled())
 		return 0;
-	if (page)
-		mem = try_get_mem_cgroup_from_swapcache(page);
-	if (!mem && mm)
-		mem = try_get_mem_cgroup_from_mm(mm);
-	if (unlikely(!mem))
-		return 0;
 
-	do {
-		progress = mem_cgroup_hierarchical_reclaim(mem,
-					gfp_mask, true, false);
-		progress += mem_cgroup_check_under_limit(mem);
-	} while (!progress && --retry);
+	ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
+	if (!ret)
+		mem_cgroup_cancel_charge_swapin(mem); /* it does !mem check */
 
-	css_put(&mem->css);
-	if (!retry)
-		return -ENOMEM;
-	return 0;
+	return ret;
 }
 
 static DEFINE_MUTEX(set_limit_mutex);
diff --git a/mm/memory.c b/mm/memory.c
index cf6873e91c6..4126dd16778 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1971,6 +1971,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				ret = tmp;
 				goto unwritable_page;
 			}
+			if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
+				lock_page(old_page);
+				if (!old_page->mapping) {
+					ret = 0; /* retry the fault */
+					unlock_page(old_page);
+					goto unwritable_page;
+				}
+			} else
+				VM_BUG_ON(!PageLocked(old_page));
 
 			/*
 			 * Since we dropped the lock we need to revalidate
@@ -1980,9 +1989,11 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 */
 			page_table = pte_offset_map_lock(mm, pmd, address,
 							 &ptl);
-			page_cache_release(old_page);
-			if (!pte_same(*page_table, orig_pte))
+			if (!pte_same(*page_table, orig_pte)) {
+				unlock_page(old_page);
+				page_cache_release(old_page);
 				goto unlock;
+			}
 
 			page_mkwrite = 1;
 		}
@@ -2094,9 +2105,6 @@ gotten:
 unlock:
 	pte_unmap_unlock(page_table, ptl);
 	if (dirty_page) {
-		if (vma->vm_file)
-			file_update_time(vma->vm_file);
-
 		/*
 		 * Yes, Virginia, this is actually required to prevent a race
 		 * with clear_page_dirty_for_io() from clearing the page dirty
@@ -2105,16 +2113,41 @@ unlock:
 		 *
 		 * do_no_page is protected similarly.
 		 */
-		wait_on_page_locked(dirty_page);
-		set_page_dirty_balance(dirty_page, page_mkwrite);
+		if (!page_mkwrite) {
+			wait_on_page_locked(dirty_page);
+			set_page_dirty_balance(dirty_page, page_mkwrite);
+		}
 		put_page(dirty_page);
+		if (page_mkwrite) {
+			struct address_space *mapping = dirty_page->mapping;
+
+			set_page_dirty(dirty_page);
+			unlock_page(dirty_page);
+			page_cache_release(dirty_page);
+			if (mapping)	{
+				/*
+				 * Some device drivers do not set page.mapping
+				 * but still dirty their pages
+				 */
+				balance_dirty_pages_ratelimited(mapping);
+			}
+		}
+
+		/* file_update_time outside page_lock */
+		if (vma->vm_file)
+			file_update_time(vma->vm_file);
 	}
 	return ret;
 oom_free_new:
 	page_cache_release(new_page);
 oom:
-	if (old_page)
+	if (old_page) {
+		if (page_mkwrite) {
+			unlock_page(old_page);
+			page_cache_release(old_page);
+		}
 		page_cache_release(old_page);
+	}
 	return VM_FAULT_OOM;
 
 unwritable_page:
@@ -2458,8 +2491,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (mem_cgroup_try_charge_swapin(mm, page, GFP_KERNEL, &ptr)) {
 		ret = VM_FAULT_OOM;
-		unlock_page(page);
-		goto out;
+		goto out_page;
 	}
 
 	/*
@@ -2521,6 +2553,7 @@ out:
 out_nomap:
 	mem_cgroup_cancel_charge_swapin(ptr);
 	pte_unmap_unlock(page_table, ptl);
+out_page:
 	unlock_page(page);
 	page_cache_release(page);
 	return ret;
@@ -2664,27 +2697,22 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				int tmp;
 
 				unlock_page(page);
-				vmf.flags |= FAULT_FLAG_MKWRITE;
+				vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
 				tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
 				if (unlikely(tmp &
 					  (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
 					ret = tmp;
-					anon = 1; /* no anon but release vmf.page */
-					goto out_unlocked;
-				}
-				lock_page(page);
-				/*
-				 * XXX: this is not quite right (racy vs
-				 * invalidate) to unlock and relock the page
-				 * like this, however a better fix requires
-				 * reworking page_mkwrite locking API, which
-				 * is better done later.
-				 */
-				if (!page->mapping) {
-					ret = 0;
-					anon = 1; /* no anon but release vmf.page */
-					goto out;
+					goto unwritable_page;
 				}
+				if (unlikely(!(tmp & VM_FAULT_LOCKED))) {
+					lock_page(page);
+					if (!page->mapping) {
+						ret = 0; /* retry the fault */
+						unlock_page(page);
+						goto unwritable_page;
+					}
+				} else
+					VM_BUG_ON(!PageLocked(page));
 				page_mkwrite = 1;
 			}
 		}
@@ -2736,19 +2764,35 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_unmap_unlock(page_table, ptl);
 
 out:
-	unlock_page(vmf.page);
-out_unlocked:
-	if (anon)
-		page_cache_release(vmf.page);
-	else if (dirty_page) {
-		if (vma->vm_file)
-			file_update_time(vma->vm_file);
+	if (dirty_page) {
+		struct address_space *mapping = page->mapping;
 
-		set_page_dirty_balance(dirty_page, page_mkwrite);
+		if (set_page_dirty(dirty_page))
+			page_mkwrite = 1;
+		unlock_page(dirty_page);
 		put_page(dirty_page);
+		if (page_mkwrite && mapping) {
+			/*
+			 * Some device drivers do not set page.mapping but still
+			 * dirty their pages
+			 */
+			balance_dirty_pages_ratelimited(mapping);
+		}
+
+		/* file_update_time outside page_lock */
+		if (vma->vm_file)
+			file_update_time(vma->vm_file);
+	} else {
+		unlock_page(vmf.page);
+		if (anon)
+			page_cache_release(vmf.page);
 	}
 
 	return ret;
+
+unwritable_page:
+	page_cache_release(page);
+	return ret;
 }
 
 static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
diff --git a/mm/mmap.c b/mm/mmap.c
index 4a3841186c1..6b7b1a95944 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -85,7 +85,7 @@ EXPORT_SYMBOL(vm_get_page_prot);
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS;  /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50;	/* default is 50% */
 int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
 
 /*
  * Check that a process has enough memory to allocate a new virtual
@@ -179,11 +179,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 	if (mm)
 		allowed -= mm->total_vm / 32;
 
-	/*
-	 * cast `allowed' as a signed long because vm_committed_space
-	 * sometimes has a negative value
-	 */
-	if (atomic_long_read(&vm_committed_space) < (long)allowed)
+	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
 		return 0;
 error:
 	vm_unacct_memory(pages);
@@ -1575,7 +1571,7 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 	 * Overcommit..  This must be the final test, as it will
 	 * update security statistics.
 	 */
-	if (security_vm_enough_memory(grow))
+	if (security_vm_enough_memory_mm(mm, grow))
 		return -ENOMEM;
 
 	/* Ok, everything looks good - let it rip */
@@ -2481,4 +2477,8 @@ void mm_drop_all_locks(struct mm_struct *mm)
  */
 void __init mmap_init(void)
 {
+	int ret;
+
+	ret = percpu_counter_init(&vm_committed_as, 0);
+	VM_BUG_ON(ret);
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index 72eda4aee2c..b571ef70742 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -62,11 +62,11 @@ void *high_memory;
 struct page *mem_map;
 unsigned long max_mapnr;
 unsigned long num_physpages;
-atomic_long_t vm_committed_space = ATOMIC_LONG_INIT(0);
+struct percpu_counter vm_committed_as;
 int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
 int sysctl_overcommit_ratio = 50; /* default is 50% */
 int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
-int sysctl_nr_trim_pages = 1; /* page trimming behaviour */
+int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
 int heap_stack_gap = 0;
 
 atomic_long_t mmap_pages_allocated;
@@ -463,6 +463,10 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
  */
 void __init mmap_init(void)
 {
+	int ret;
+
+	ret = percpu_counter_init(&vm_committed_as, 0);
+	VM_BUG_ON(ret);
 	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
 }
 
@@ -511,8 +515,6 @@ static void add_nommu_region(struct vm_region *region)
 
 	validate_nommu_regions();
 
-	BUG_ON(region->vm_start & ~PAGE_MASK);
-
 	parent = NULL;
 	p = &nommu_region_tree.rb_node;
 	while (*p) {
@@ -1847,12 +1849,9 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 	if (mm)
 		allowed -= mm->total_vm / 32;
 
-	/*
-	 * cast `allowed' as a signed long because vm_committed_space
-	 * sometimes has a negative value
-	 */
-	if (atomic_long_read(&vm_committed_space) < (long)allowed)
+	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
 		return 0;
+
 error:
 	vm_unacct_memory(pages);
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 2f3166e308d..92bcf1db16b 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -514,34 +514,32 @@ void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_mask)
  */
 static void __out_of_memory(gfp_t gfp_mask, int order)
 {
-	if (sysctl_oom_kill_allocating_task) {
-		oom_kill_process(current, gfp_mask, order, 0, NULL,
-				"Out of memory (oom_kill_allocating_task)");
-
-	} else {
-		unsigned long points;
-		struct task_struct *p;
-
-retry:
-		/*
-		 * Rambo mode: Shoot down a process and hope it solves whatever
-		 * issues we may have.
-		 */
-		p = select_bad_process(&points, NULL);
+	struct task_struct *p;
+	unsigned long points;
 
-		if (PTR_ERR(p) == -1UL)
+	if (sysctl_oom_kill_allocating_task)
+		if (!oom_kill_process(current, gfp_mask, order, 0, NULL,
+				"Out of memory (oom_kill_allocating_task)"))
 			return;
+retry:
+	/*
+	 * Rambo mode: Shoot down a process and hope it solves whatever
+	 * issues we may have.
+	 */
+	p = select_bad_process(&points, NULL);
 
-		/* Found nothing?!?! Either we hang forever, or we panic. */
-		if (!p) {
-			read_unlock(&tasklist_lock);
-			panic("Out of memory and no killable processes...\n");
-		}
+	if (PTR_ERR(p) == -1UL)
+		return;
 
-		if (oom_kill_process(p, gfp_mask, order, points, NULL,
-				     "Out of memory"))
-			goto retry;
+	/* Found nothing?!?! Either we hang forever, or we panic. */
+	if (!p) {
+		read_unlock(&tasklist_lock);
+		panic("Out of memory and no killable processes...\n");
 	}
+
+	if (oom_kill_process(p, gfp_mask, order, points, NULL,
+			     "Out of memory"))
+		goto retry;
 }
 
 /*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e2f26991fff..fe753ecf2aa 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2681,6 +2681,7 @@ static void __meminit zone_init_free_lists(struct zone *zone)
 
 static int zone_batchsize(struct zone *zone)
 {
+#ifdef CONFIG_MMU
 	int batch;
 
 	/*
@@ -2706,9 +2707,26 @@ static int zone_batchsize(struct zone *zone)
 	 * of pages of one half of the possible page colors
 	 * and the other with pages of the other colors.
 	 */
-	batch = (1 << (fls(batch + batch/2)-1)) - 1;
+	batch = rounddown_pow_of_two(batch + batch/2) - 1;
 
 	return batch;
+
+#else
+	/* The deferral and batching of frees should be suppressed under NOMMU
+	 * conditions.
+	 *
+	 * The problem is that NOMMU needs to be able to allocate large chunks
+	 * of contiguous memory as there's no hardware page translation to
+	 * assemble apparent contiguous memory from discontiguous pages.
+	 *
+	 * Queueing large contiguous runs of pages for batching, however,
+	 * causes the pages to actually be freed in smaller chunks.  As there
+	 * can be a significant delay between the individual batches being
+	 * recycled, this leads to the once large chunks of space being
+	 * fragmented and becoming unavailable for high-order allocations.
+	 */
+	return 0;
+#endif
 }
 
 static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
diff --git a/mm/pdflush.c b/mm/pdflush.c
index f2caf96993f..235ac440c44 100644
--- a/mm/pdflush.c
+++ b/mm/pdflush.c
@@ -58,14 +58,6 @@ static DEFINE_SPINLOCK(pdflush_lock);
 int nr_pdflush_threads = 0;
 
 /*
- * The max/min number of pdflush threads. R/W by sysctl at
- * /proc/sys/vm/nr_pdflush_threads_max/min
- */
-int nr_pdflush_threads_max __read_mostly = MAX_PDFLUSH_THREADS;
-int nr_pdflush_threads_min __read_mostly = MIN_PDFLUSH_THREADS;
-
-
-/*
  * The time at which the pdflush thread pool last went empty
  */
 static unsigned long last_empty_jifs;
@@ -76,7 +68,7 @@ static unsigned long last_empty_jifs;
  * Thread pool management algorithm:
  * 
  * - The minimum and maximum number of pdflush instances are bound
- *   by nr_pdflush_threads_min and nr_pdflush_threads_max.
+ *   by MIN_PDFLUSH_THREADS and MAX_PDFLUSH_THREADS.
  * 
  * - If there have been no idle pdflush instances for 1 second, create
  *   a new one.
@@ -142,13 +134,14 @@ static int __pdflush(struct pdflush_work *my_work)
 		 * To throttle creation, we reset last_empty_jifs.
 		 */
 		if (time_after(jiffies, last_empty_jifs + 1 * HZ)) {
-			if (list_empty(&pdflush_list) &&
-			    nr_pdflush_threads < nr_pdflush_threads_max) {
-				last_empty_jifs = jiffies;
-				nr_pdflush_threads++;
-				spin_unlock_irq(&pdflush_lock);
-				start_one_pdflush_thread();
-				spin_lock_irq(&pdflush_lock);
+			if (list_empty(&pdflush_list)) {
+				if (nr_pdflush_threads < MAX_PDFLUSH_THREADS) {
+					last_empty_jifs = jiffies;
+					nr_pdflush_threads++;
+					spin_unlock_irq(&pdflush_lock);
+					start_one_pdflush_thread();
+					spin_lock_irq(&pdflush_lock);
+				}
 			}
 		}
 
@@ -160,7 +153,7 @@ static int __pdflush(struct pdflush_work *my_work)
 		 */
 		if (list_empty(&pdflush_list))
 			continue;
-		if (nr_pdflush_threads <= nr_pdflush_threads_min)
+		if (nr_pdflush_threads <= MIN_PDFLUSH_THREADS)
 			continue;
 		pdf = list_entry(pdflush_list.prev, struct pdflush_work, list);
 		if (time_after(jiffies, pdf->when_i_went_to_sleep + 1 * HZ)) {
@@ -266,9 +259,9 @@ static int __init pdflush_init(void)
 	 * Pre-set nr_pdflush_threads...  If we fail to create,
 	 * the count will be decremented.
 	 */
-	nr_pdflush_threads = nr_pdflush_threads_min;
+	nr_pdflush_threads = MIN_PDFLUSH_THREADS;
 
-	for (i = 0; i < nr_pdflush_threads_min; i++)
+	for (i = 0; i < MIN_PDFLUSH_THREADS; i++)
 		start_one_pdflush_thread();
 	return 0;
 }
diff --git a/mm/shmem.c b/mm/shmem.c
index d94d2e9146b..b25f95ce3db 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -24,6 +24,7 @@
 #include <linux/init.h>
 #include <linux/vfs.h>
 #include <linux/mount.h>
+#include <linux/pagemap.h>
 #include <linux/file.h>
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -43,7 +44,6 @@ static struct vfsmount *shm_mnt;
 #include <linux/exportfs.h>
 #include <linux/generic_acl.h>
 #include <linux/mman.h>
-#include <linux/pagemap.h>
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/backing-dev.h>
@@ -65,13 +65,28 @@ static struct vfsmount *shm_mnt;
 #include <asm/div64.h>
 #include <asm/pgtable.h>
 
+/*
+ * The maximum size of a shmem/tmpfs file is limited by the maximum size of
+ * its triple-indirect swap vector - see illustration at shmem_swp_entry().
+ *
+ * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel,
+ * but one eighth of that on a 64-bit kernel.  With 8kB page size, maximum
+ * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel,
+ * MAX_LFS_FILESIZE being then more restrictive than swap vector layout.
+ *
+ * We use / and * instead of shifts in the definitions below, so that the swap
+ * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE.
+ */
 #define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
-#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
-#define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)
+#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
 
-#define SHMEM_MAX_INDEX  (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
-#define SHMEM_MAX_BYTES  ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)
+#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
+#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT)
 
+#define SHMEM_MAX_BYTES  min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE)
+#define SHMEM_MAX_INDEX  ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT))
+
+#define BLOCKS_PER_PAGE  (PAGE_CACHE_SIZE/512)
 #define VM_ACCT(size)    (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)
 
 /* info->flags needs VM_flags to handle pagein/truncate races efficiently */
@@ -1325,8 +1340,12 @@ repeat:
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
 			if (error == -ENOMEM) {
-				/* allow reclaim from this memory cgroup */
-				error = mem_cgroup_shrink_usage(swappage,
+				/*
+				 * reclaim from proper memory cgroup and
+				 * call memcg's OOM if needed.
+				 */
+				error = mem_cgroup_shmem_charge_fallback(
+								swappage,
 								current->mm,
 								gfp);
 				if (error) {
@@ -2581,7 +2600,7 @@ int shmem_unuse(swp_entry_t entry, struct page *page)
 #define shmem_get_inode(sb, mode, dev, flags)	ramfs_get_inode(sb, mode, dev)
 #define shmem_acct_size(flags, size)		0
 #define shmem_unacct_size(flags, size)		do {} while (0)
-#define SHMEM_MAX_BYTES				LLONG_MAX
+#define SHMEM_MAX_BYTES				MAX_LFS_FILESIZE
 
 #endif /* CONFIG_SHMEM */
 
diff --git a/mm/swap.c b/mm/swap.c
index bede23ce64e..cb29ae5d33a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -491,49 +491,6 @@ unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
 
 EXPORT_SYMBOL(pagevec_lookup_tag);
 
-#ifdef CONFIG_SMP
-/*
- * We tolerate a little inaccuracy to avoid ping-ponging the counter between
- * CPUs
- */
-#define ACCT_THRESHOLD	max(16, NR_CPUS * 2)
-
-static DEFINE_PER_CPU(long, committed_space);
-
-void vm_acct_memory(long pages)
-{
-	long *local;
-
-	preempt_disable();
-	local = &__get_cpu_var(committed_space);
-	*local += pages;
-	if (*local > ACCT_THRESHOLD || *local < -ACCT_THRESHOLD) {
-		atomic_long_add(*local, &vm_committed_space);
-		*local = 0;
-	}
-	preempt_enable();
-}
-
-#ifdef CONFIG_HOTPLUG_CPU
-
-/* Drop the CPU's cached committed space back into the central pool. */
-static int cpu_swap_callback(struct notifier_block *nfb,
-			     unsigned long action,
-			     void *hcpu)
-{
-	long *committed;
-
-	committed = &per_cpu(committed_space, (long)hcpu);
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		atomic_long_add(*committed, &vm_committed_space);
-		*committed = 0;
-		drain_cpu_pagevecs((long)hcpu);
-	}
-	return NOTIFY_OK;
-}
-#endif /* CONFIG_HOTPLUG_CPU */
-#endif /* CONFIG_SMP */
-
 /*
  * Perform any setup for the swap system
  */
@@ -554,7 +511,4 @@ void __init swap_setup(void)
 	 * Right now other parts of the system means that we
 	 * _really_ don't want to cluster much more
 	 */
-#ifdef CONFIG_HOTPLUG_CPU
-	hotcpu_notifier(cpu_swap_callback, 0);
-#endif
 }
diff --git a/mm/util.c b/mm/util.c
index 2599e83eea1..55bef160b9f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -223,6 +223,22 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 }
 #endif
 
+/**
+ * get_user_pages_fast() - pin user pages in memory
+ * @start:	starting user address
+ * @nr_pages:	number of pages from start to pin
+ * @write:	whether pages will be written to
+ * @pages:	array that receives pointers to the pages pinned.
+ *		Should be at least nr_pages long.
+ *
+ * Attempt to pin user pages in memory without taking mm->mmap_sem.
+ * If not successful, it will fall back to taking the lock and
+ * calling get_user_pages().
+ *
+ * Returns number of pages pinned. This may be fewer than the number
+ * requested. If nr_pages is 0 or negative, returns 0. If no pages
+ * were pinned, returns -errno.
+ */
 int __attribute__((weak)) get_user_pages_fast(unsigned long start,
 				int nr_pages, int write, struct page **pages)
 {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index fab19876b4d..083716ea38c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -402,6 +402,7 @@ overflow:
 			printk(KERN_WARNING
 				"vmap allocation for size %lu failed: "
 				"use vmalloc=<size> to increase size.\n", size);
+		kfree(va);
 		return ERR_PTR(-EBUSY);
 	}
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 39fdfb14eea..5fa3eda1f03 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -63,6 +63,9 @@ struct scan_control {
 	/* Can mapped pages be reclaimed? */
 	int may_unmap;
 
+	/* Can pages be swapped as part of reclaim? */
+	int may_swap;
+
 	/* This context's SWAP_CLUSTER_MAX. If freeing memory for
 	 * suspend, we effectively ignore SWAP_CLUSTER_MAX.
 	 * In this context, it doesn't matter that we scan the
@@ -1380,7 +1383,7 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	/* If we have no swap space, do not bother scanning anon pages. */
-	if (nr_swap_pages <= 0) {
+	if (!sc->may_swap || (nr_swap_pages <= 0)) {
 		percent[0] = 0;
 		percent[1] = 100;
 		return;
@@ -1468,7 +1471,7 @@ static void shrink_zone(int priority, struct zone *zone,
 
 	for_each_evictable_lru(l) {
 		int file = is_file_lru(l);
-		int scan;
+		unsigned long scan;
 
 		scan = zone_nr_pages(zone, sc, l);
 		if (priority) {
@@ -1697,6 +1700,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.may_unmap = 1,
+		.may_swap = 1,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
@@ -1717,6 +1721,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
+		.may_swap = !noswap,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = swappiness,
 		.order = 0,
@@ -1726,9 +1731,6 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 	};
 	struct zonelist *zonelist;
 
-	if (noswap)
-		sc.may_unmap = 0;
-
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
@@ -1767,6 +1769,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.may_unmap = 1,
+		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = vm_swappiness,
 		.order = order,
@@ -2088,13 +2091,13 @@ static void shrink_all_zones(unsigned long nr_pages, int prio,
 				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
 								sc, prio);
 				if (nr_reclaimed >= nr_pages) {
-					sc->nr_reclaimed = nr_reclaimed;
+					sc->nr_reclaimed += nr_reclaimed;
 					return;
 				}
 			}
 		}
 	}
-	sc->nr_reclaimed = nr_reclaimed;
+	sc->nr_reclaimed += nr_reclaimed;
 }
 
 /*
@@ -2115,6 +2118,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 		.may_unmap = 0,
 		.may_writepage = 1,
 		.isolate_pages = isolate_pages_global,
+		.nr_reclaimed = 0,
 	};
 
 	current->reclaim_state = &reclaim_state;
@@ -2297,6 +2301,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	struct scan_control sc = {
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
 		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.may_swap = 1,
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
 					SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,