Merge remote-tracking branch 'kernelorg/linux-3.0.y' into 3_0_64

Conflicts:
	arch/arm/Kconfig
	arch/arm/include/asm/hwcap.h
	arch/arm/kernel/smp.c
	arch/arm/plat-samsung/adc.c
	drivers/gpu/drm/i915/i915_reg.h
	drivers/gpu/drm/i915/intel_drv.h
	drivers/mmc/core/sd.c
	drivers/net/tun.c
	drivers/net/usb/usbnet.c
	drivers/regulator/max8997.c
	drivers/usb/core/hub.c
	drivers/usb/host/xhci.h
	drivers/usb/serial/qcserial.c
	fs/jbd2/transaction.c
	include/linux/migrate.h
	kernel/sys.c
	kernel/time/timekeeping.c
	lib/genalloc.c
	mm/memory-failure.c
	mm/memory_hotplug.c
	mm/mempolicy.c
	mm/page_alloc.c
	mm/vmalloc.c
	mm/vmscan.c
	mm/vmstat.c
	scripts/Kbuild.include

Change-Id: I91e2d85c07320c7ccfc04cf98a448e89bed6ade6

24 files changed, 868 insertions, 446 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 051a04e..f550ecf 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -35,10 +35,6 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	bool sync;			/* Synchronous migration */
 
-	/* Account for isolated anon and file pages */
-	unsigned long nr_anon;
-	unsigned long nr_file;
-
 	unsigned int order;		/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
@@ -223,17 +219,13 @@ static void isolate_freepages(struct zone *zone,
 static void acct_isolated(struct zone *zone, struct compact_control *cc)
 {
 	struct page *page;
-	unsigned int count[NR_LRU_LISTS] = { 0, };
+	unsigned int count[2] = { 0, };
 
-	list_for_each_entry(page, &cc->migratepages, lru) {
-		int lru = page_lru_base_type(page);
-		count[lru]++;
-	}
+	list_for_each_entry(page, &cc->migratepages, lru)
+		count[!!page_is_file_cache(page)]++;
 
-	cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
-	cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file);
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -269,6 +261,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
+	isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;
 
 	/* Do not scan outside zone boundaries */
 	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
@@ -378,8 +371,11 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			continue;
 		}
 
+		if (!cc->sync)
+			mode |= ISOLATE_ASYNC_MIGRATE;
+
 		/* Try isolate the page */
-		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
+		if (__isolate_lru_page(page, mode, 0) != 0)
 			continue;
 
 		VM_BUG_ON(PageTransCompound(page));
@@ -581,7 +577,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				(unsigned long)cc, false,
-				cc->sync);
+				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 
@@ -596,8 +592,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		if (err) {
 			putback_lru_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
+			if (err == -ENOMEM) {
+				ret = COMPACT_PARTIAL;
+				goto out;
+			}
 		}
-
 	}
 
 out:
@@ -719,14 +718,12 @@ static int compact_node(int nid)
 }
 
 /* Compact all nodes in the system */
-static int compact_nodes(void)
+static void compact_nodes(void)
 {
 	int nid;
 
 	for_each_online_node(nid)
 		compact_node(nid);
-
-	return COMPACT_COMPLETE;
 }
 
 /* The written value is actually unused, all memory is compacted */
@@ -737,7 +734,7 @@ int sysctl_compaction_handler(struct ctl_table *table, int write,
 			void __user *buffer, size_t *length, loff_t *ppos)
 {
 	if (write)
-		return compact_nodes();
+		compact_nodes();
 
 	return 0;
 }
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 03bf3bb..f8e675e 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -49,7 +49,6 @@ struct dma_pool {		/* the pool */
 	size_t allocation;
 	size_t boundary;
 	char name[32];
-	wait_queue_head_t waitq;
 	struct list_head pools;
 };
 
@@ -61,8 +60,6 @@ struct dma_page {		/* cacheable header for 'allocation' bytes */
 	unsigned int offset;
 };
 
-#define	POOL_TIMEOUT_JIFFIES	((100 /* msec */ * HZ) / 1000)
-
 static DEFINE_MUTEX(pools_lock);
 
 static ssize_t
@@ -171,7 +168,6 @@ struct dma_pool *dma_pool_create(const char *name, struct device *dev,
 	retval->size = size;
 	retval->boundary = boundary;
 	retval->allocation = allocation;
-	init_waitqueue_head(&retval->waitq);
 
 	if (dev) {
 		int ret;
@@ -226,7 +222,6 @@ static struct dma_page *pool_alloc_page(struct dma_pool *pool, gfp_t mem_flags)
 		memset(page->vaddr, POOL_POISON_FREED, pool->allocation);
 #endif
 		pool_initialise_page(pool, page);
-		list_add(&page->page_list, &pool->page_list);
 		page->in_use = 0;
 		page->offset = 0;
 	} else {
@@ -314,30 +309,21 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 	might_sleep_if(mem_flags & __GFP_WAIT);
 
 	spin_lock_irqsave(&pool->lock, flags);
- restart:
 	list_for_each_entry(page, &pool->page_list, page_list) {
 		if (page->offset < pool->allocation)
 			goto ready;
 	}
-	page = pool_alloc_page(pool, GFP_ATOMIC);
-	if (!page) {
-		if (mem_flags & __GFP_WAIT) {
-			DECLARE_WAITQUEUE(wait, current);
 
-			__set_current_state(TASK_UNINTERRUPTIBLE);
-			__add_wait_queue(&pool->waitq, &wait);
-			spin_unlock_irqrestore(&pool->lock, flags);
+	/* pool_alloc_page() might sleep, so temporarily drop &pool->lock */
+	spin_unlock_irqrestore(&pool->lock, flags);
 
-			schedule_timeout(POOL_TIMEOUT_JIFFIES);
+	page = pool_alloc_page(pool, mem_flags);
+	if (!page)
+		return NULL;
 
-			spin_lock_irqsave(&pool->lock, flags);
-			__remove_wait_queue(&pool->waitq, &wait);
-			goto restart;
-		}
-		retval = NULL;
-		goto done;
-	}
+	spin_lock_irqsave(&pool->lock, flags);
 
+	list_add(&page->page_list, &pool->page_list);
  ready:
 	page->in_use++;
 	offset = page->offset;
@@ -347,7 +333,6 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 #ifdef	DMAPOOL_DEBUG
 	memset(retval, POOL_POISON_ALLOCATED, pool->size);
 #endif
- done:
 	spin_unlock_irqrestore(&pool->lock, flags);
 	return retval;
 }
@@ -434,8 +419,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
 	page->in_use--;
 	*(int *)vaddr = page->offset;
 	page->offset = offset;
-	if (waitqueue_active(&pool->waitq))
-		wake_up_locked(&pool->waitq);
 	/*
 	 * Resist a temptation to do
 	 *    if (!is_page_busy(page)) pool_free_page(pool, page);
diff --git a/mm/filemap.c b/mm/filemap.c
index b7d8603..10481eb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -516,10 +516,13 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	struct page *page;
 
 	if (cpuset_do_page_mem_spread()) {
-		get_mems_allowed();
-		n = cpuset_mem_spread_node();
-		page = alloc_pages_exact_node(n, gfp, 0);
-		put_mems_allowed();
+		unsigned int cpuset_mems_cookie;
+		do {
+			cpuset_mems_cookie = get_mems_allowed();
+			n = cpuset_mem_spread_node();
+			page = alloc_pages_exact_node(n, gfp, 0);
+		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+
 		return page;
 	}
 	return alloc_pages(gfp, 0);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 8cc11dd..a9ab45e 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -920,6 +920,8 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		count_vm_event(THP_FAULT_FALLBACK);
 		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 						   pmd, orig_pmd, page, haddr);
+		if (ret & VM_FAULT_OOM)
+			split_huge_page(page);
 		put_page(page);
 		goto out;
 	}
@@ -927,6 +929,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
 		put_page(new_page);
+		split_huge_page(page);
 		put_page(page);
 		ret |= VM_FAULT_OOM;
 		goto out;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f7001ac..037f077 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -460,8 +460,10 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	struct zonelist *zonelist;
 	struct zone *zone;
 	struct zoneref *z;
+	unsigned int cpuset_mems_cookie;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask, &mpol, &nodemask);
 	/*
@@ -488,10 +490,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 			}
 		}
 	}
-err:
+
 	mpol_cond_put(mpol);
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
+
+err:
+	mpol_cond_put(mpol);
+	return NULL;
 }
 
 static void update_and_free_page(struct hstate *h, struct page *page)
@@ -2060,6 +2067,15 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 		kref_get(&reservations->refs);
 }
 
+static void resv_map_put(struct vm_area_struct *vma)
+{
+	struct resv_map *reservations = vma_resv_map(vma);
+
+	if (!reservations)
+		return;
+	kref_put(&reservations->refs, resv_map_release);
+}
+
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
@@ -2075,7 +2091,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 		reserve = (end - start) -
 			region_count(&reservations->regions, start, end);
 
-		kref_put(&reservations->refs, resv_map_release);
+		resv_map_put(vma);
 
 		if (reserve) {
 			hugetlb_acct_memory(h, -reserve);
@@ -2285,6 +2301,22 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 {
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
 	__unmap_hugepage_range(vma, start, end, ref_page);
+	/*
+	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
+	 * test will fail on a vma being torn down, and not grab a page table
+	 * on its way out.  We're lucky that the flag has such an appropriate
+	 * name, and can in fact be safely cleared here. We could clear it
+	 * before the __unmap_hugepage_range above, but all that's necessary
+	 * is to clear it before releasing the i_mmap_mutex below.
+	 *
+	 * This works because in the contexts this is called, the VMA is
+	 * going to be destroyed. It is not vunerable to madvise(DONTNEED)
+	 * because madvise is not supported on hugetlbfs. The same applies
+	 * for direct IO. unmap_hugepage_range() is only being called just
+	 * before free_pgtables() so clearing VM_MAYSHARE will not cause
+	 * surprises later.
+	 */
+	vma->vm_flags &= ~VM_MAYSHARE;
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
@@ -2398,7 +2430,6 @@ retry_avoidcopy:
 		if (outside_reserve) {
 			BUG_ON(huge_pte_none(pte));
 			if (unmap_ref_private(mm, vma, old_page, address)) {
-				BUG_ON(page_count(old_page) != 1);
 				BUG_ON(huge_pte_none(pte));
 				spin_lock(&mm->page_table_lock);
 				goto retry_avoidcopy;
@@ -2838,9 +2869,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
-
+	/*
+	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
+	 * may have cleared our pud entry and done put_page on the page table:
+	 * once we release i_mmap_mutex, another task can do the final put_page
+	 * and that page table be reused and filled with junk.
+	 */
 	flush_tlb_range(vma, start, end);
+	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
 int hugetlb_reserve_pages(struct inode *inode,
@@ -2878,12 +2914,16 @@ int hugetlb_reserve_pages(struct inode *inode,
 		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
 	}
 
-	if (chg < 0)
-		return chg;
+	if (chg < 0) {
+		ret = chg;
+		goto out_err;
+	}
 
 	/* There must be enough filesystem quota for the mapping */
-	if (hugetlb_get_quota(inode->i_mapping, chg))
-		return -ENOSPC;
+	if (hugetlb_get_quota(inode->i_mapping, chg)) {
+		ret = -ENOSPC;
+		goto out_err;
+	}
 
 	/*
 	 * Check enough hugepages are available for the reservation.
@@ -2892,7 +2932,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugetlb_put_quota(inode->i_mapping, chg);
-		return ret;
+		goto out_err;
 	}
 
 	/*
@@ -2909,6 +2949,10 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
+out_err:
+	if (vma)
+		resv_map_put(vma);
+	return ret;
 }
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
diff --git a/mm/madvise.c b/mm/madvise.c
index 2221491..deabe5f6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>
 #include <linux/sched.h>
 #include <linux/ksm.h>
+#include <linux/file.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -197,14 +198,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 	struct address_space *mapping;
 	loff_t offset, endoff;
 	int error;
+	struct file *f;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
 	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
 		return -EINVAL;
 
-	if (!vma->vm_file || !vma->vm_file->f_mapping
-		|| !vma->vm_file->f_mapping->host) {
+	f = vma->vm_file;
+
+	if (!f || !f->f_mapping || !f->f_mapping->host) {
 			return -EINVAL;
 	}
 
@@ -218,9 +221,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 	endoff = (loff_t)(end - vma->vm_start - 1)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* vmtruncate_range needs to take i_mutex and i_alloc_sem */
+	/*
+	 * vmtruncate_range may need to take i_mutex and i_alloc_sem.
+	 * We need to explicitly grab a reference because the vma (and
+	 * hence the vma's reference to the file) can go away as soon as
+	 * we drop mmap_sem.
+	 */
+	get_file(f);
 	up_read(&current->mm->mmap_sem);
 	error = vmtruncate_range(mapping->host, offset, endoff);
+	fput(f);
 	down_read(&current->mm->mmap_sem);
 	return error;
 }
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 283068f..57cdf5a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1251,7 +1251,8 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
-					int mode, struct zone *z,
+					isolate_mode_t mode,
+					struct zone *z,
 					struct mem_cgroup *mem_cont,
 					int active, int file)
 {
@@ -4605,6 +4606,12 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp,
 swap_buffers:
 	/* Swap primary and spare array */
 	thresholds->spare = thresholds->primary;
+	/* If all events are unregistered, free the spare array */
+	if (!new) {
+		kfree(thresholds->spare);
+		thresholds->spare = NULL;
+	}
+
 	rcu_assign_pointer(thresholds->primary, new);
 
 	/* To be sure that nobody uses thresholds */
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b4d627d..809823d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1338,8 +1338,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	/* Keep page count to indicate a given hugepage is isolated. */
 
 	list_add(&hpage->lru, &pagelist);
-	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0,
-				true);
+	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false,
+				MIGRATE_SYNC);
 	if (ret) {
 		struct page *page1, *page2;
 		list_for_each_entry_safe(page1, page2, &pagelist, lru)
@@ -1386,9 +1386,17 @@ int soft_offline_page(struct page *page, int flags)
 {
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
+	struct page *hpage = compound_trans_head(page);
 
 	if (PageHuge(page))
 		return soft_offline_huge_page(page, flags);
+	if (PageTransHuge(hpage)) {
+		if (PageAnon(hpage) && unlikely(split_huge_page(hpage))) {
+			pr_info("soft offline: %#lx: failed to split THP\n",
+				pfn);
+			return -EBUSY;
+		}
+	}
 
 	ret = get_any_page(page, pfn, flags);
 	if (ret < 0)
@@ -1469,10 +1477,10 @@ int soft_offline_page(struct page *page, int flags)
 		list_add(&page->lru, &pagelist);
 #ifndef CONFIG_DMA_CMA
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-								0, true);
+								false, MIGRATE_SYNC);
 #else
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-								0, true, 0);
+								false, MIGRATE_SYNC, 0);
 #endif
 		if (ret) {
 			putback_lru_pages(&pagelist);
diff --git a/mm/memory.c b/mm/memory.c
index 159985d..6204ce2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -208,10 +208,14 @@ static int tlb_next_batch(struct mmu_gather *tlb)
 		return 1;
 	}
 
+	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
+		return 0;
+
 	batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
 	if (!batch)
 		return 0;
 
+	tlb->batch_count++;
 	batch->next = NULL;
 	batch->nr   = 0;
 	batch->max  = MAX_GATHER_BATCH;
@@ -238,6 +242,7 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm)
 	tlb->local.nr   = 0;
 	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
 	tlb->active     = &tlb->local;
+	tlb->batch_count = 0;
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 	tlb->batch = NULL;
@@ -3568,6 +3573,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(is_vm_hugetlb_page(vma)))
 		return hugetlb_fault(mm, vma, address, flags);
 
+retry:
 	pgd = pgd_offset(mm, address);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
@@ -3581,13 +3587,24 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 							  pmd, flags);
 	} else {
 		pmd_t orig_pmd = *pmd;
+		int ret;
+
 		barrier();
 		if (pmd_trans_huge(orig_pmd)) {
 			if (flags & FAULT_FLAG_WRITE &&
 			    !pmd_write(orig_pmd) &&
-			    !pmd_trans_splitting(orig_pmd))
-				return do_huge_pmd_wp_page(mm, vma, address,
-							   pmd, orig_pmd);
+			    !pmd_trans_splitting(orig_pmd)) {
+				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
+							  orig_pmd);
+				/*
+				 * If COW results in an oom, the huge pmd will
+				 * have been split, so retry the fault on the
+				 * pte for a smaller charge.
+				 */
+				if (unlikely(ret & VM_FAULT_OOM))
+					goto retry;
+				return ret;
+			}
 			return 0;
 		}
 	}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 348d7bf..9fcd1b9 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -116,9 +116,6 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
 	struct mem_section *ms;
 	struct page *page, *memmap;
 
-	if (!pfn_valid(start_pfn))
-		return;
-
 	section_nr = pfn_to_section_nr(start_pfn);
 	ms = __nr_to_section(section_nr);
 
@@ -177,9 +174,16 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
 	end_pfn = pfn + pgdat->node_spanned_pages;
 
 	/* register_section info */
-	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
-		register_page_bootmem_info_section(pfn);
-
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		/*
+		 * Some platforms can assign the same pfn to multiple nodes - on
+		 * node0 as well as nodeN.  To avoid registering a pfn against
+		 * multiple nodes we check that this pfn does not already
+		 * reside in some other node.
+		 */
+		if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
+			register_page_bootmem_info_section(pfn);
+	}
 }
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP */
 
@@ -748,10 +752,10 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		/* this function returns # of failed pages */
 #ifndef CONFIG_DMA_CMA
 		ret = migrate_pages(&source, hotremove_migrate_alloc, 0,
-								true, true);
+								true, MIGRATE_SYNC);
 #else
 		ret = migrate_pages(&source, hotremove_migrate_alloc, 0,
-								true, true, 0);
+								true, MIGRATE_SYNC, 0);
 #endif
 		if (ret)
 			putback_lru_pages(&source);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 703b42a..7065fb3 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -606,24 +606,39 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	return first;
 }
 
-/* Apply policy to a single VMA */
-static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
+/*
+ * Apply policy to a single VMA
+ * This must be called with the mmap_sem held for writing.
+ */
+static int vma_replace_policy(struct vm_area_struct *vma,
+						struct mempolicy *pol)
 {
-	int err = 0;
-	struct mempolicy *old = vma->vm_policy;
+	int err;
+	struct mempolicy *old;
+	struct mempolicy *new;
 
 	pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
 		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
 		 vma->vm_ops, vma->vm_file,
 		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);
 
-	if (vma->vm_ops && vma->vm_ops->set_policy)
+	new = mpol_dup(pol);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+
+	if (vma->vm_ops && vma->vm_ops->set_policy) {
 		err = vma->vm_ops->set_policy(vma, new);
-	if (!err) {
-		mpol_get(new);
-		vma->vm_policy = new;
-		mpol_put(old);
+		if (err)
+			goto err_out;
 	}
+
+	old = vma->vm_policy;
+	vma->vm_policy = new; /* protected by mmap_sem */
+	mpol_put(old);
+
+	return 0;
+ err_out:
+	mpol_put(new);
 	return err;
 }
 
@@ -666,7 +681,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 			if (err)
 				goto out;
 		}
-		err = policy_vma(vma, new_pol);
+		err = vma_replace_policy(vma, new_pol);
 		if (err)
 			goto out;
 	}
@@ -934,10 +949,10 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 	if (!list_empty(&pagelist)) {
 #ifndef CONFIG_DMA_CMA
 		err = migrate_pages(&pagelist, new_node_page, dest,
-								false, true);
+								false, MIGRATE_SYNC);
 #else
 		err = migrate_pages(&pagelist, new_node_page, dest,
-								false, true, 0);
+								false, MIGRATE_SYNC, 0);
 #endif
 		if (err)
 			putback_lru_pages(&pagelist);
@@ -1507,8 +1522,18 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 									addr);
 			if (vpol)
 				pol = vpol;
-		} else if (vma->vm_policy)
+		} else if (vma->vm_policy) {
 			pol = vma->vm_policy;
+
+			/*
+			 * shmem_alloc_page() passes MPOL_F_SHARED policy with
+			 * a pseudo vma whose vma->vm_ops=NULL. Take a reference
+			 * count on these policies which will be dropped by
+			 * mpol_cond_put() later
+			 */
+			if (mpol_needs_cond_ref(pol))
+				mpol_get(pol);
+		}
 	}
 	if (!pol)
 		pol = &default_policy;
@@ -1828,18 +1853,24 @@ struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, int node)
 {
-	struct mempolicy *pol = get_vma_policy(current, vma, addr);
+	struct mempolicy *pol;
 	struct zonelist *zl;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
+
+retry_cpuset:
+	pol = get_vma_policy(current, vma, addr);
+	cpuset_mems_cookie = get_mems_allowed();
 
-	get_mems_allowed();
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
+
 		return page;
 	}
 	zl = policy_zonelist(gfp, pol, node);
@@ -1850,7 +1881,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		struct page *page =  __alloc_pages_nodemask(gfp, order,
 						zl, policy_nodemask(gfp, pol));
 		__mpol_put(pol);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
 		return page;
 	}
 	/*
@@ -1858,7 +1890,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	 */
 	page = __alloc_pages_nodemask(gfp, order, zl,
 				      policy_nodemask(gfp, pol));
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
 }
 
@@ -1885,11 +1918,14 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = current->mempolicy;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
 
 	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/*
 	 * No reference counting needed for current->mempolicy
 	 * nor system default_policy
@@ -1900,7 +1936,10 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		page = __alloc_pages_nodemask(gfp, order,
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(alloc_pages_current);
@@ -1945,28 +1984,6 @@ struct mempolicy *__mpol_dup(struct mempolicy *old)
 	return new;
 }
 
-/*
- * If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
- * eliminate the * MPOL_F_* flags that require conditional ref and
- * [NOTE!!!] drop the extra ref.  Not safe to reference *frompol directly
- * after return.  Use the returned value.
- *
- * Allows use of a mempolicy for, e.g., multiple allocations with a single
- * policy lookup, even if the policy needs/has extra ref on lookup.
- * shmem_readahead needs this.
- */
-struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
-						struct mempolicy *frompol)
-{
-	if (!mpol_needs_cond_ref(frompol))
-		return frompol;
-
-	*tompol = *frompol;
-	tompol->flags &= ~MPOL_F_SHARED;	/* copy doesn't need unref */
-	__mpol_put(frompol);
-	return tompol;
-}
-
 /* Slow path of a mempolicy comparison */
 int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
@@ -2003,7 +2020,7 @@ int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
  */
 
 /* lookup first element intersecting start-end */
-/* Caller holds sp->lock */
+/* Caller holds sp->mutex */
 static struct sp_node *
 sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 {
@@ -2067,36 +2084,50 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
 
 	if (!sp->root.rb_node)
 		return NULL;
-	spin_lock(&sp->lock);
+	mutex_lock(&sp->mutex);
 	sn = sp_lookup(sp, idx, idx+1);
 	if (sn) {
 		mpol_get(sn->policy);
 		pol = sn->policy;
 	}
-	spin_unlock(&sp->lock);
+	mutex_unlock(&sp->mutex);
 	return pol;
 }
 
+static void sp_free(struct sp_node *n)
+{
+	mpol_put(n->policy);
+	kmem_cache_free(sn_cache, n);
+}
+
 static void sp_delete(struct shared_policy *sp, struct sp_node *n)
 {
 	pr_debug("deleting %lx-l%lx\n", n->start, n->end);
 	rb_erase(&n->nd, &sp->root);
-	mpol_put(n->policy);
-	kmem_cache_free(sn_cache, n);
+	sp_free(n);
 }
 
 static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 				struct mempolicy *pol)
 {
-	struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
+	struct sp_node *n;
+	struct mempolicy *newpol;
 
+	n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
 	if (!n)
 		return NULL;
+
+	newpol = mpol_dup(pol);
+	if (IS_ERR(newpol)) {
+		kmem_cache_free(sn_cache, n);
+		return NULL;
+	}
+	newpol->flags |= MPOL_F_SHARED;
+
 	n->start = start;
 	n->end = end;
-	mpol_get(pol);
-	pol->flags |= MPOL_F_SHARED;	/* for unref */
-	n->policy = pol;
+	n->policy = newpol;
+
 	return n;
 }
 
@@ -2104,10 +2135,10 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
 static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
 				 unsigned long end, struct sp_node *new)
 {
-	struct sp_node *n, *new2 = NULL;
+	struct sp_node *n;
+	int ret = 0;
 
-restart:
-	spin_lock(&sp->lock);
+	mutex_lock(&sp->mutex);
 	n = sp_lookup(sp, start, end);
 	/* Take care of old policies in the same range. */
 	while (n && n->start < end) {
@@ -2120,16 +2151,14 @@ restart:
 		} else {
 			/* Old policy spanning whole new range. */
 			if (n->end > end) {
+				struct sp_node *new2;
+				new2 = sp_alloc(end, n->end, n->policy);
 				if (!new2) {
-					spin_unlock(&sp->lock);
-					new2 = sp_alloc(end, n->end, n->policy);
-					if (!new2)
-						return -ENOMEM;
-					goto restart;
+					ret = -ENOMEM;
+					goto out;
 				}
 				n->end = start;
 				sp_insert(sp, new2);
-				new2 = NULL;
 				break;
 			} else
 				n->end = start;
@@ -2140,12 +2169,9 @@ restart:
 	}
 	if (new)
 		sp_insert(sp, new);
-	spin_unlock(&sp->lock);
-	if (new2) {
-		mpol_put(new2->policy);
-		kmem_cache_free(sn_cache, new2);
-	}
-	return 0;
+out:
+	mutex_unlock(&sp->mutex);
+	return ret;
 }
 
 /**
@@ -2163,7 +2189,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
 	int ret;
 
 	sp->root = RB_ROOT;		/* empty tree == default mempolicy */
-	spin_lock_init(&sp->lock);
+	mutex_init(&sp->mutex);
 
 	if (mpol) {
 		struct vm_area_struct pvma;
@@ -2217,7 +2243,7 @@ int mpol_set_shared_policy(struct shared_policy *info,
 	}
 	err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
 	if (err && new)
-		kmem_cache_free(sn_cache, new);
+		sp_free(new);
 	return err;
 }
 
@@ -2229,16 +2255,14 @@ void mpol_free_shared_policy(struct shared_policy *p)
 
 	if (!p->root.rb_node)
 		return;
-	spin_lock(&p->lock);
+	mutex_lock(&p->mutex);
 	next = rb_first(&p->root);
 	while (next) {
 		n = rb_entry(next, struct sp_node, nd);
 		next = rb_next(&n->nd);
-		rb_erase(&n->nd, &p->root);
-		mpol_put(n->policy);
-		kmem_cache_free(sn_cache, n);
+		sp_delete(p, n);
 	}
-	spin_unlock(&p->lock);
+	mutex_unlock(&p->mutex);
 }
 
 /* assumes fs == KERNEL_DS */
@@ -2295,8 +2319,7 @@ void numa_default_policy(void)
  */
 
 /*
- * "local" is pseudo-policy:  MPOL_PREFERRED with MPOL_F_LOCAL flag
- * Used only for mpol_parse_str() and mpol_to_str()
+ * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
  */
 #define MPOL_LOCAL MPOL_MAX
 static const char * const policy_modes[] =
@@ -2311,28 +2334,21 @@ static const char * const policy_modes[] =
 
 #ifdef CONFIG_TMPFS
 /**
- * mpol_parse_str - parse string to mempolicy
+ * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
  * @str:  string containing mempolicy to parse
  * @mpol:  pointer to struct mempolicy pointer, returned on success.
- * @no_context:  flag whether to "contextualize" the mempolicy
+ * @unused:  redundant argument, to be removed later.
  *
  * Format of input:
  *	<mode>[=<flags>][:<nodelist>]
  *
- * if @no_context is true, save the input nodemask in w.user_nodemask in
- * the returned mempolicy.  This will be used to "clone" the mempolicy in
- * a specific context [cpuset] at a later time.  Used to parse tmpfs mpol
- * mount option.  Note that if 'static' or 'relative' mode flags were
- * specified, the input nodemask will already have been saved.  Saving
- * it again is redundant, but safe.
- *
  * On success, returns 0, else 1
  */
-int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
+int mpol_parse_str(char *str, struct mempolicy **mpol, int unused)
 {
 	struct mempolicy *new = NULL;
 	unsigned short mode;
-	unsigned short uninitialized_var(mode_flags);
+	unsigned short mode_flags;
 	nodemask_t nodes;
 	char *nodelist = strchr(str, ':');
 	char *flags = strchr(str, '=');
@@ -2420,24 +2436,23 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
 	if (IS_ERR(new))
 		goto out;
 
-	if (no_context) {
-		/* save for contextualization */
-		new->w.user_nodemask = nodes;
-	} else {
-		int ret;
-		NODEMASK_SCRATCH(scratch);
-		if (scratch) {
-			task_lock(current);
-			ret = mpol_set_nodemask(new, &nodes, scratch);
-			task_unlock(current);
-		} else
-			ret = -ENOMEM;
-		NODEMASK_SCRATCH_FREE(scratch);
-		if (ret) {
-			mpol_put(new);
-			goto out;
-		}
-	}
+	/*
+	 * Save nodes for mpol_to_str() to show the tmpfs mount options
+	 * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo.
+	 */
+	if (mode != MPOL_PREFERRED)
+		new->v.nodes = nodes;
+	else if (nodelist)
+		new->v.preferred_node = first_node(nodes);
+	else
+		new->flags |= MPOL_F_LOCAL;
+
+	/*
+	 * Save nodes for contextualization: this will be used to "clone"
+	 * the mempolicy in a specific context [cpuset] at a later time.
+	 */
+	new->w.user_nodemask = nodes;
+
 	err = 0;
 
 out:
@@ -2457,13 +2472,13 @@ out:
  * @buffer:  to contain formatted mempolicy string
  * @maxlen:  length of @buffer
  * @pol:  pointer to mempolicy to be formatted
- * @no_context:  "context free" mempolicy - use nodemask in w.user_nodemask
+ * @unused:  redundant argument, to be removed later.
  *
  * Convert a mempolicy into a string.
  * Returns the number of characters in buffer (if positive)
  * or an error (negative)
  */
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int unused)
 {
 	char *p = buffer;
 	int l;
@@ -2489,7 +2504,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
 	case MPOL_PREFERRED:
 		nodes_clear(nodes);
 		if (flags & MPOL_F_LOCAL)
-			mode = MPOL_LOCAL;	/* pseudo-policy */
+			mode = MPOL_LOCAL;
 		else
 			node_set(pol->v.preferred_node, nodes);
 		break;
@@ -2497,14 +2512,11 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
 	case MPOL_BIND:
 		/* Fall through */
 	case MPOL_INTERLEAVE:
-		if (no_context)
-			nodes = pol->w.user_nodemask;
-		else
-			nodes = pol->v.nodes;
+		nodes = pol->v.nodes;
 		break;
 
 	default:
-		BUG();
+		return -EINVAL;
 	}
 
 	l = strlen(policy_modes[mode]);
diff --git a/mm/migrate.c b/mm/migrate.c
index 14d0a6a..480714b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -220,6 +220,56 @@ out:
 	pte_unmap_unlock(ptep, ptl);
 }
 
+#ifdef CONFIG_BLOCK
+/* Returns true if all buffers are successfully locked */
+static bool buffer_migrate_lock_buffers(struct buffer_head *head,
+							enum migrate_mode mode)
+{
+	struct buffer_head *bh = head;
+
+	/* Simple case, sync compaction */
+	if (mode != MIGRATE_ASYNC) {
+		do {
+			get_bh(bh);
+			lock_buffer(bh);
+			bh = bh->b_this_page;
+
+		} while (bh != head);
+
+		return true;
+	}
+
+	/* async case, we cannot block on lock_buffer so use trylock_buffer */
+	do {
+		get_bh(bh);
+		if (!trylock_buffer(bh)) {
+			/*
+			 * We failed to lock the buffer and cannot stall in
+			 * async migration. Release the taken locks
+			 */
+			struct buffer_head *failed_bh = bh;
+			put_bh(failed_bh);
+			bh = head;
+			while (bh != failed_bh) {
+				unlock_buffer(bh);
+				put_bh(bh);
+				bh = bh->b_this_page;
+			}
+			return false;
+		}
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+	return true;
+}
+#else
+static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
+							enum migrate_mode mode)
+{
+	return true;
+}
+#endif /* CONFIG_BLOCK */
+
 /*
  * Replace the page in the mapping.
  *
@@ -229,7 +279,8 @@ out:
  * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
 static int migrate_page_move_mapping(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page,
+		struct buffer_head *head, enum migrate_mode mode)
 {
 	int expected_count;
 	void **pslot;
@@ -259,6 +310,20 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	}
 
 	/*
+	 * In the async migration case of moving a page with buffers, lock the
+	 * buffers using trylock before the mapping is moved. If the mapping
+	 * was moved, we later failed to lock the buffers and could not move
+	 * the mapping back due to an elevated page count, we would have to
+	 * block waiting on other references to be dropped.
+	 */
+	if (mode == MIGRATE_ASYNC && head &&
+			!buffer_migrate_lock_buffers(head, mode)) {
+		page_unfreeze_refs(page, expected_count);
+		spin_unlock_irq(&mapping->tree_lock);
+		return -EAGAIN;
+	}
+
+	/*
 	 * Now we know that no one else is looking at the page.
 	 */
 	get_page(newpage);	/* add cache reference */
@@ -415,13 +480,14 @@ EXPORT_SYMBOL(fail_migrate_page);
  * Pages are locked upon entry and exit.
  */
 int migrate_page(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page,
+		enum migrate_mode mode)
 {
 	int rc;
 
 	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
 
-	rc = migrate_page_move_mapping(mapping, newpage, page);
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
 
 	if (rc)
 		return rc;
@@ -438,28 +504,28 @@ EXPORT_SYMBOL(migrate_page);
  * exist.
  */
 int buffer_migrate_page(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page, enum migrate_mode mode)
 {
 	struct buffer_head *bh, *head;
 	int rc;
 
 	if (!page_has_buffers(page))
-		return migrate_page(mapping, newpage, page);
+		return migrate_page(mapping, newpage, page, mode);
 
 	head = page_buffers(page);
 
-	rc = migrate_page_move_mapping(mapping, newpage, page);
+	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
 
 	if (rc)
 		return rc;
 
-	bh = head;
-	do {
-		get_bh(bh);
-		lock_buffer(bh);
-		bh = bh->b_this_page;
-
-	} while (bh != head);
+	/*
+	 * In the async case, migrate_page_move_mapping locked the buffers
+	 * with an IRQ-safe spinlock held. In the sync case, the buffers
+	 * need to be locked now
+	 */
+	if (mode != MIGRATE_ASYNC)
+		BUG_ON(!buffer_migrate_lock_buffers(head, mode));
 
 	ClearPagePrivate(page);
 	set_page_private(newpage, page_private(page));
@@ -536,10 +602,14 @@ static int writeout(struct address_space *mapping, struct page *page)
  * Default handling if a filesystem does not provide a migration function.
  */
 static int fallback_migrate_page(struct address_space *mapping,
-	struct page *newpage, struct page *page)
+	struct page *newpage, struct page *page, enum migrate_mode mode)
 {
-	if (PageDirty(page))
+	if (PageDirty(page)) {
+		/* Only writeback pages in full synchronous migration */
+		if (mode != MIGRATE_SYNC)
+			return -EBUSY;
 		return writeout(mapping, page);
+	}
 
 	/*
 	 * Buffers may be managed in a filesystem specific way.
@@ -549,7 +619,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, mode);
 }
 
 /*
@@ -564,7 +634,7 @@ static int fallback_migrate_page(struct address_space *mapping,
  *  == 0 - success
  */
 static int move_to_new_page(struct page *newpage, struct page *page,
-					int remap_swapcache, bool sync)
+				int remap_swapcache, enum migrate_mode mode)
 {
 	struct address_space *mapping;
 	int rc;
@@ -585,29 +655,18 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 
 	mapping = page_mapping(page);
 	if (!mapping)
-		rc = migrate_page(mapping, newpage, page);
-	else {
+		rc = migrate_page(mapping, newpage, page, mode);
+	else if (mapping->a_ops->migratepage)
 		/*
-		 * Do not writeback pages if !sync and migratepage is
-		 * not pointing to migrate_page() which is nonblocking
-		 * (swapcache/tmpfs uses migratepage = migrate_page).
+		 * Most pages have a mapping and most filesystems provide a
+		 * migratepage callback. Anonymous pages are part of swap
+		 * space which also has its own migratepage callback. This
+		 * is the most common path for page migration.
 		 */
-		if (PageDirty(page) && !sync &&
-		    mapping->a_ops->migratepage != migrate_page)
-			rc = -EBUSY;
-		else if (mapping->a_ops->migratepage)
-			/*
-			 * Most pages have a mapping and most filesystems
-			 * should provide a migration function. Anonymous
-			 * pages are part of swap space which also has its
-			 * own migration function. This is the most common
-			 * path for page migration.
-			 */
-			rc = mapping->a_ops->migratepage(mapping,
-							newpage, page);
-		else
-			rc = fallback_migrate_page(mapping, newpage, page);
-	}
+		rc = mapping->a_ops->migratepage(mapping,
+						newpage, page, mode);
+	else
+		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
 	if (rc) {
 		newpage->mapping = NULL;
@@ -621,38 +680,18 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	return rc;
 }
 
-/*
- * Obtain the lock on page, remove all ptes and migrate the page
- * to the newly allocated page in newpage.
- */
-static int unmap_and_move(new_page_t get_new_page, unsigned long private,
-			struct page *page, int force, bool offlining, bool sync)
+static int __unmap_and_move(struct page *page, struct page *newpage,
+			int force, bool offlining, enum migrate_mode mode)
 {
-	int rc = 0;
-	int *result = NULL;
-	struct page *newpage = get_new_page(page, private, &result);
+	int rc = -EAGAIN;
 	int remap_swapcache = 1;
 	int charge = 0;
 	struct mem_cgroup *mem;
 	struct anon_vma *anon_vma = NULL;
 
-	if (!newpage)
-		return -ENOMEM;
-
-	if (page_count(page) == 1) {
-		/* page was freed from under us. So we are done. */
-		goto move_newpage;
-	}
-	if (unlikely(PageTransHuge(page)))
-		if (unlikely(split_huge_page(page)))
-			goto move_newpage;
-
-	/* prepare cgroup just returns 0 or -ENOMEM */
-	rc = -EAGAIN;
-
 	if (!trylock_page(page)) {
-		if (!force || !sync)
-			goto move_newpage;
+		if (!force || mode == MIGRATE_ASYNC)
+			goto out;
 
 		/*
 		 * It's not safe for direct compaction to call lock_page.
@@ -668,7 +707,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 		 * altogether.
 		 */
 		if (current->flags & PF_MEMALLOC)
-			goto move_newpage;
+			goto out;
 
 		lock_page(page);
 	}
@@ -697,10 +736,12 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 
 	if (PageWriteback(page)) {
 		/*
-		 * For !sync, there is no point retrying as the retry loop
-		 * is expected to be too short for PageWriteback to be cleared
+		 * Only in the case of a full syncronous migration is it
+		 * necessary to wait for PageWriteback. In the async case,
+		 * the retry loop is too short and in the sync-light case,
+		 * the overhead of stalling is too much
 		 */
-		if (!sync) {
+		if (mode != MIGRATE_SYNC) {
 			rc = -EBUSY;
 			goto uncharge;
 		}
@@ -771,7 +812,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 
 skip_unmap:
 	if (!page_mapped(page))
-		rc = move_to_new_page(newpage, page, remap_swapcache, sync);
+		rc = move_to_new_page(newpage, page, remap_swapcache, mode);
 
 	if (rc && remap_swapcache)
 		remove_migration_ptes(page, page);
@@ -785,27 +826,53 @@ uncharge:
 		mem_cgroup_end_migration(mem, page, newpage, rc == 0);
 unlock:
 	unlock_page(page);
+out:
+	return rc;
+}
 
-move_newpage:
+/*
+ * Obtain the lock on page, remove all ptes and migrate the page
+ * to the newly allocated page in newpage.
+ */
+static int unmap_and_move(new_page_t get_new_page, unsigned long private,
+			struct page *page, int force, bool offlining,
+			enum migrate_mode mode)
+{
+	int rc = 0;
+	int *result = NULL;
+	struct page *newpage = get_new_page(page, private, &result);
+
+	if (!newpage)
+		return -ENOMEM;
+
+	if (page_count(page) == 1) {
+		/* page was freed from under us. So we are done. */
+		goto out;
+	}
+
+	if (unlikely(PageTransHuge(page)))
+		if (unlikely(split_huge_page(page)))
+			goto out;
+
+	rc = __unmap_and_move(page, newpage, force, offlining, mode);
+out:
 	if (rc != -EAGAIN) {
- 		/*
- 		 * A page that has been migrated has all references
- 		 * removed and will be freed. A page that has not been
- 		 * migrated will have kepts its references and be
- 		 * restored.
- 		 */
- 		list_del(&page->lru);
+		/*
+		 * A page that has been migrated has all references
+		 * removed and will be freed. A page that has not been
+		 * migrated will have kepts its references and be
+		 * restored.
+		 */
+		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 		putback_lru_page(page);
 	}
-
 	/*
 	 * Move the new page to the LRU. If migration was not successful
 	 * then this will free the page.
 	 */
 	putback_lru_page(newpage);
-
 	if (result) {
 		if (rc)
 			*result = rc;
@@ -835,7 +902,8 @@ move_newpage:
  */
 static int unmap_and_move_huge_page(new_page_t get_new_page,
 				unsigned long private, struct page *hpage,
-				int force, bool offlining, bool sync)
+				int force, bool offlining,
+				enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -848,7 +916,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	rc = -EAGAIN;
 
 	if (!trylock_page(hpage)) {
-		if (!force || !sync)
+		if (!force || mode != MIGRATE_SYNC)
 			goto out;
 		lock_page(hpage);
 	}
@@ -859,7 +927,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
 
 	if (!page_mapped(hpage))
-		rc = move_to_new_page(new_hpage, hpage, 1, sync);
+		rc = move_to_new_page(new_hpage, hpage, 1, mode);
 
 	if (rc)
 		remove_migration_ptes(hpage, hpage);
@@ -902,7 +970,7 @@ out:
  */
 int migrate_pages(struct list_head *from,
 		new_page_t get_new_page, unsigned long private, bool offlining,
-		bool sync)
+		enum migrate_mode mode)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -923,7 +991,7 @@ int migrate_pages(struct list_head *from,
 
 			rc = unmap_and_move(get_new_page, private,
 						page, pass > 2, offlining,
-						sync);
+						mode);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -953,7 +1021,7 @@ out:
 
 int migrate_huge_pages(struct list_head *from,
 		new_page_t get_new_page, unsigned long private, bool offlining,
-		bool sync)
+		enum migrate_mode mode)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -970,7 +1038,7 @@ int migrate_huge_pages(struct list_head *from,
 
 			rc = unmap_and_move_huge_page(get_new_page,
 					private, page, pass > 2, offlining,
-					sync);
+					mode);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -1099,7 +1167,7 @@ set_status:
 	err = 0;
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_page_node,
-				(unsigned long)pm, 0, true);
+				(unsigned long)pm, 0, MIGRATE_SYNC);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 8d032de..71c7811 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -33,6 +33,24 @@
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	/*
+	 * RCU here will block mmu_notifier_unregister until
+	 * ->release returns.
+	 */
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist)
+		/*
+		 * if ->release runs before mmu_notifier_unregister it
+		 * must be handled as it's the only way for the driver
+		 * to flush all existing sptes and stop the driver
+		 * from establishing any more sptes before all the
+		 * pages in the mm are freed.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+	rcu_read_unlock();
 
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
@@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm)
 		 * mmu_notifier_unregister to return.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
-		/*
-		 * RCU here will block mmu_notifier_unregister until
-		 * ->release returns.
-		 */
-		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
-		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
-		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
-		rcu_read_unlock();
-		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
@@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		hlist_del_rcu(&mn->hlist);
-
 		/*
 		 * RCU here will force exit_mmap to wait ->release to finish
 		 * before freeing the pages.
 		 */
 		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+
 		/*
 		 * exit_mmap will block in mmu_notifier_release to
 		 * guarantee ->release is called before freeing the
@@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
 		rcu_read_unlock();
-	} else
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
+		hlist_del_rcu(&mn->hlist);
 		spin_unlock(&mm->mmu_notifier_mm->lock);
+	}
 
 	/*
 	 * Wait any running method to finish, of course including
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 6e93dc7..e39e3ef 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -83,8 +83,7 @@ void __init free_bootmem_late(unsigned long addr, unsigned long size)
 
 static void __init __free_pages_memory(unsigned long start, unsigned long end)
 {
-	int i;
-	unsigned long start_aligned, end_aligned;
+	unsigned long i, start_aligned, end_aligned;
 	int order = ilog2(BITS_PER_LONG);
 
 	start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 54a4782..d1a7b6d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -565,7 +565,7 @@ static inline void __free_one_page(struct page *page,
 		combined_idx = buddy_idx & page_idx;
 		higher_page = page + (combined_idx - page_idx);
 		buddy_idx = __find_buddy_index(combined_idx, order + 1);
-		higher_buddy = page + (buddy_idx - combined_idx);
+		higher_buddy = higher_page + (buddy_idx - combined_idx);
 		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
 			list_add_tail(&page->lru,
 				&zone->free_area[order].free_list[migratetype]);
@@ -1952,14 +1952,20 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	if (!order || compaction_deferred(preferred_zone))
+	if (!order)
 		return NULL;
 
+	if (compaction_deferred(preferred_zone)) {
+		*deferred_compaction = true;
+		return NULL;
+	}
+
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, sync_migration);
@@ -1987,7 +1993,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * but not enough to satisfy watermarks.
 		 */
 		count_vm_event(COMPACTFAIL);
-		defer_compaction(preferred_zone);
+
+		/*
+		 * As async compaction considers a subset of pageblocks, only
+		 * defer if the failure was a sync compaction failure.
+		 */
+		if (sync_migration)
+			defer_compaction(preferred_zone);
 
 		cond_resched();
 	}
@@ -1999,8 +2011,9 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	return NULL;
 }
@@ -2153,6 +2166,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 #ifdef CONFIG_ANDROID_WIP
 	unsigned long start_tick = jiffies;
 #endif
+	bool deferred_compaction = false;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2236,12 +2250,22 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 	if (page)
 		goto got_pg;
 	sync_migration = true;
 
+	/*
+	 * If compaction is deferred for high-order allocations, it is because
+	 * sync compaction recently failed. In this is the case and the caller
+	 * has requested the system not be heavily disrupted, fail the
+	 * allocation now instead of entering direct reclaim
+	 */
+	if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+		goto nopage;
+
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
 					zonelist, high_zoneidx,
@@ -2323,8 +2347,9 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 		if (page)
 			goto got_pg;
 	}
@@ -2352,8 +2377,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zone *preferred_zone;
-	struct page *page;
+	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
+	unsigned int cpuset_mems_cookie;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2372,15 +2398,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
 				nodemask ? : &cpuset_current_mems_allowed,
 				&preferred_zone);
-	if (!preferred_zone) {
-		put_mems_allowed();
-		return NULL;
-	}
+	if (!preferred_zone)
+		goto out;
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
@@ -2390,9 +2416,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-	put_mems_allowed();
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+	/*
+	 * When updating a task's mems_allowed, it is possible to race with
+	 * parallel threads in such a way that an allocation can fail while
+	 * the mask is being updated. If a page allocation is about to fail,
+	 * check if the cpuset changed during allocation and if so, retry.
+	 */
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2616,13 +2652,15 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 bool skip_free_areas_node(unsigned int flags, int nid)
 {
 	bool ret = false;
+	unsigned int cpuset_mems_cookie;
 
 	if (!(flags & SHOW_MEM_FILTER_NODES))
 		goto out;
 
-	get_mems_allowed();
-	ret = !node_isset(nid, cpuset_current_mems_allowed);
-	put_mems_allowed();
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		ret = !node_isset(nid, cpuset_current_mems_allowed);
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 out:
 	return ret;
 }
@@ -3533,25 +3571,33 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 		if (page_to_nid(page) != zone_to_nid(zone))
 			continue;
 
-		/* Blocks with reserved pages will never free, skip them. */
-		block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
-		if (pageblock_is_reserved(pfn, block_end_pfn))
-			continue;
-
 		block_migratetype = get_pageblock_migratetype(page);
 
-		/* If this block is reserved, account for it */
-		if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
-			reserve--;
-			continue;
-		}
+		/* Only test what is necessary when the reserves are not met */
+		if (reserve > 0) {
+			/*
+			 * Blocks with reserved pages will never free, skip
+			 * them.
+			 */
+			block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+			if (pageblock_is_reserved(pfn, block_end_pfn))
+				continue;
 
-		/* Suitable for reserving if this block is movable */
-		if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
-			set_pageblock_migratetype(page, MIGRATE_RESERVE);
-			move_freepages_block(zone, page, MIGRATE_RESERVE);
-			reserve--;
-			continue;
+			/* If this block is reserved, account for it */
+			if (block_migratetype == MIGRATE_RESERVE) {
+				reserve--;
+				continue;
+			}
+
+			/* Suitable for reserving if this block is movable */
+			if (block_migratetype == MIGRATE_MOVABLE) {
+				set_pageblock_migratetype(page,
+							MIGRATE_RESERVE);
+				move_freepages_block(zone, page,
+							MIGRATE_RESERVE);
+				reserve--;
+				continue;
+			}
 		}
 
 		/*
@@ -5562,7 +5608,7 @@ static inline int pfn_to_bitidx(struct zone *zone, unsigned long pfn)
 	pfn &= (PAGES_PER_SECTION-1);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #else
-	pfn = pfn - zone->zone_start_pfn;
+	pfn = pfn - round_down(zone->zone_start_pfn, pageblock_nr_pages);
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 #endif /* CONFIG_SPARSEMEM */
 }
diff --git a/mm/percpu.c b/mm/percpu.c
index 0ae7a09..af0cc7a 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1630,6 +1630,16 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
 		areas[group] = ptr;
 
 		base = min(ptr, base);
+	}
+
+	/*
+	 * Copy data and free unused parts.  This should happen after all
+	 * allocations are complete; otherwise, we may end up with
+	 * overlapping groups.
+	 */
+	for (group = 0; group < ai->nr_groups; group++) {
+		struct pcpu_group_info *gi = &ai->groups[group];
+		void *ptr = areas[group];
 
 		for (i = 0; i < gi->nr_units; i++, ptr += ai->unit_size) {
 			if (gi->cpu_map[i] == NR_CPUS) {
diff --git a/mm/rmap.c b/mm/rmap.c
index 23295f6..30e44cb 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -57,6 +57,7 @@
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
 #include <linux/hugetlb.h>
+#include <linux/backing-dev.h>
 
 #include <asm/tlbflush.h>
 
@@ -936,11 +937,8 @@ int page_mkclean(struct page *page)
 
 	if (page_mapped(page)) {
 		struct address_space *mapping = page_mapping(page);
-		if (mapping) {
+		if (mapping)
 			ret = page_mkclean_file(mapping, page);
-			if (page_test_and_clear_dirty(page_to_pfn(page), 1))
-				ret = 1;
-		}
 	}
 
 	return ret;
@@ -1121,6 +1119,8 @@ void page_add_file_rmap(struct page *page)
  */
 void page_remove_rmap(struct page *page)
 {
+	struct address_space *mapping = page_mapping(page);
+
 	/* page still mapped by someone else? */
 	if (!atomic_add_negative(-1, &page->_mapcount))
 		return;
@@ -1131,8 +1131,19 @@ void page_remove_rmap(struct page *page)
 	 * this if the page is anon, so about to be freed; but perhaps
 	 * not if it's in swapcache - there might be another pte slot
 	 * containing the swap entry, but page not yet written to swap.
+	 *
+	 * And we can skip it on file pages, so long as the filesystem
+	 * participates in dirty tracking; but need to catch shm and tmpfs
+	 * and ramfs pages which have been modified since creation by read
+	 * fault.
+	 *
+	 * Note that mapping must be decided above, before decrementing
+	 * mapcount (which luckily provides a barrier): once page is unmapped,
+	 * it could be truncated and page->mapping reset to NULL at any moment.
+	 * Note also that we are relying on page_mapping(page) to set mapping
+	 * to &swapper_space when PageSwapCache(page).
 	 */
-	if ((!PageAnon(page) || PageSwapCache(page)) &&
+	if (mapping && !mapping_cap_account_dirty(mapping) &&
 	    page_test_and_clear_dirty(page_to_pfn(page), 1))
 		set_page_dirty(page);
 	/*
diff --git a/mm/shmem.c b/mm/shmem.c
index e76f74e..818947b 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1177,19 +1177,20 @@ static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
 static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp,
 			struct shmem_inode_info *info, unsigned long idx)
 {
-	struct mempolicy mpol, *spol;
 	struct vm_area_struct pvma;
 	struct page *page;
 
-	spol = mpol_cond_copy(&mpol,
-				mpol_shared_policy_lookup(&info->policy, idx));
-
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
 	pvma.vm_pgoff = idx;
 	pvma.vm_ops = NULL;
-	pvma.vm_policy = spol;
+	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
+
 	page = swapin_readahead(entry, gfp, &pvma, 0);
+
+	/* Drop reference taken by mpol_shared_policy_lookup() */
+	mpol_cond_put(pvma.vm_policy);
+
 	return page;
 }
 
@@ -1197,6 +1198,7 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 			struct shmem_inode_info *info, unsigned long idx)
 {
 	struct vm_area_struct pvma;
+	struct page *page;
 
 	/* Create a pseudo vma that just contains the policy */
 	pvma.vm_start = 0;
@@ -1204,10 +1206,12 @@ static struct page *shmem_alloc_page(gfp_t gfp,
 	pvma.vm_ops = NULL;
 	pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
 
-	/*
-	 * alloc_page_vma() will drop the shared policy reference
-	 */
-	return alloc_page_vma(gfp, &pvma, 0);
+	page = alloc_page_vma(gfp, &pvma, 0);
+
+	/* Drop reference taken by mpol_shared_policy_lookup() */
+	mpol_cond_put(pvma.vm_policy);
+
+	return page;
 }
 #else /* !CONFIG_NUMA */
 #ifdef CONFIG_TMPFS
@@ -2357,12 +2361,14 @@ static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
 {
 	struct inode *inode;
 	struct dentry *dentry = NULL;
-	u64 inum = fid->raw[2];
-	inum = (inum << 32) | fid->raw[1];
+	u64 inum;
 
 	if (fh_len < 3)
 		return NULL;
 
+	inum = fid->raw[2];
+	inum = (inum << 32) | fid->raw[1];
+
 	inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
 			shmem_match, fid->raw);
 	if (inode) {
diff --git a/mm/slab.c b/mm/slab.c
index d96e223..a67f812 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3218,12 +3218,10 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	if (in_interrupt() || (flags & __GFP_THISNODE))
 		return NULL;
 	nid_alloc = nid_here = numa_mem_id();
-	get_mems_allowed();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
 		nid_alloc = slab_node(current->mempolicy);
-	put_mems_allowed();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;
@@ -3246,14 +3244,17 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	void *obj = NULL;
 	int nid;
+	unsigned int cpuset_mems_cookie;
 
 	if (flags & __GFP_THISNODE)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+
 retry:
 	/*
 	 * Look through allowed nodes for objects available
@@ -3306,7 +3307,9 @@ retry:
 			}
 		}
 	}
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+		goto retry_cpuset;
 	return obj;
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index fa7c546..6b13a9c 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1467,6 +1467,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * The defrag ratio allows a configuration of the tradeoffs between
@@ -1490,23 +1491,32 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		struct kmem_cache_node *n;
-
-		n = get_node(s, zone_to_nid(zone));
-
-		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
-				n->nr_partial > s->min_partial) {
-			page = get_partial_node(n);
-			if (page) {
-				put_mems_allowed();
-				return page;
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+			struct kmem_cache_node *n;
+
+			n = get_node(s, zone_to_nid(zone));
+
+			if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+					n->nr_partial > s->min_partial) {
+				page = get_partial_node(n);
+				if (page) {
+					/*
+					 * Return the object even if
+					 * put_mems_allowed indicated that
+					 * the cpuset mems_allowed was
+					 * updated in parallel. It's a
+					 * harmless race between the alloc
+					 * and the cpuset update.
+					 */
+					put_mems_allowed(cpuset_mems_cookie);
+					return page;
+				}
 			}
 		}
-	}
-	put_mems_allowed();
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 #endif
 	return NULL;
 }
diff --git a/mm/sparse.c b/mm/sparse.c
index 4cd05e5..9054f83 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -619,7 +619,7 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 {
 	return; /* XXX: Not implemented yet */
 }
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 {
 }
 #else
@@ -660,10 +660,11 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 			   get_order(sizeof(struct page) * nr_pages));
 }
 
-static void free_map_bootmem(struct page *page, unsigned long nr_pages)
+static void free_map_bootmem(struct page *memmap, unsigned long nr_pages)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
 	unsigned long magic;
+	struct page *page = virt_to_page(memmap);
 
 	for (i = 0; i < nr_pages; i++, page++) {
 		magic = (unsigned long) page->lru.next;
@@ -712,13 +713,10 @@ static void free_section_usemap(struct page *memmap, unsigned long *usemap)
 	 */
 
 	if (memmap) {
-		struct page *memmap_page;
-		memmap_page = virt_to_page(memmap);
-
 		nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page))
 			>> PAGE_SHIFT;
 
-		free_map_bootmem(memmap_page, nr_pages);
+		free_map_bootmem(memmap, nr_pages);
 	}
 }
 
diff --git a/mm/truncate.c b/mm/truncate.c
index ca54477..6a11acb 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -404,11 +404,12 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
+	clear_page_mlock(page);
+
 	spin_lock_irq(&mapping->tree_lock);
 	if (PageDirty(page))
 		goto failed;
 
-	clear_page_mlock(page);
 	BUG_ON(page_has_private(page));
 	__delete_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d213fa1..a819c35 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -256,7 +256,7 @@ struct vmap_area {
 	struct rb_node rb_node;		/* address sorted rbtree */
 	struct list_head list;		/* address sorted list */
 	struct list_head purge_list;	/* "lazy purge" list */
-	void *private;
+	struct vm_struct *vm;
 	struct rcu_head rcu_head;
 };
 
@@ -1174,9 +1174,10 @@ void __init vmalloc_init(void)
 	/* Import existing vmlist entries. */
 	for (tmp = vmlist; tmp; tmp = tmp->next) {
 		va = kzalloc(sizeof(struct vmap_area), GFP_NOWAIT);
-		va->flags = tmp->flags | VM_VM_AREA;
+		va->flags = VM_VM_AREA;
 		va->va_start = (unsigned long)tmp->addr;
 		va->va_end = va->va_start + tmp->size;
+		va->vm = tmp;
 		__insert_vmap_area(va);
 	}
 
@@ -1279,6 +1280,7 @@ static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va,
 	vm->task_name = current->comm;
 #endif
 	va->private = vm;
+	va->vm = vm;
 	va->flags |= VM_VM_AREA;
 }
 
@@ -1401,7 +1403,7 @@ static struct vm_struct *find_vm_area(const void *addr)
 
 	va = find_vmap_area((unsigned long)addr);
 	if (va && va->flags & VM_VM_AREA)
-		return va->private;
+		return va->vm;
 
 	return NULL;
 }
@@ -1420,7 +1422,7 @@ struct vm_struct *remove_vm_area(const void *addr)
 
 	va = find_vmap_area((unsigned long)addr);
 	if (va && va->flags & VM_VM_AREA) {
-		struct vm_struct *vm = va->private;
+		struct vm_struct *vm = va->vm;
 
 		if (!(vm->flags & VM_UNLIST)) {
 			struct vm_struct *tmp, **p;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f6979dc..99082fa 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -248,35 +248,66 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
 		unsigned long long delta;
-		unsigned long total_scan;
-		unsigned long max_pass;
+		long total_scan;
+		long max_pass;
+		int shrink_ret = 0;
+		long nr;
+		long new_nr;
 
 		max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+		if (max_pass <= 0)
+			continue;
+
+		/*
+		 * copy the current shrinker scan count into a local variable
+		 * and zero it so that other concurrent shrinker invocations
+		 * don't also do this scanning work.
+		 */
+		do {
+			nr = shrinker->nr;
+		} while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+
+		total_scan = nr;
 		delta = (4 * nr_pages_scanned) / shrinker->seeks;
 		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
-		shrinker->nr += delta;
-		if (shrinker->nr < 0) {
+		total_scan += delta;
+		if (total_scan < 0) {
 			printk(KERN_ERR "shrink_slab: %pF negative objects to "
 			       "delete nr=%ld\n",
-			       shrinker->shrink, shrinker->nr);
-			shrinker->nr = max_pass;
+			       shrinker->shrink, total_scan);
+			total_scan = max_pass;
 		}
 
 		/*
+		 * We need to avoid excessive windup on filesystem shrinkers
+		 * due to large numbers of GFP_NOFS allocations causing the
+		 * shrinkers to return -1 all the time. This results in a large
+		 * nr being built up so when a shrink that can do some work
+		 * comes along it empties the entire cache due to nr >>>
+		 * max_pass.  This is bad for sustaining a working set in
+		 * memory.
+		 *
+		 * Hence only allow the shrinker to scan the entire cache when
+		 * a large delta change is calculated directly.
+		 */
+		if (delta < max_pass / 4)
+			total_scan = min(total_scan, max_pass / 2);
+
+		/*
 		 * Avoid risking looping forever due to too large nr value:
 		 * never try to free more than twice the estimate number of
 		 * freeable entries.
 		 */
-		if (shrinker->nr > max_pass * 2)
-			shrinker->nr = max_pass * 2;
+		if (total_scan > max_pass * 2)
+			total_scan = max_pass * 2;
 
-		total_scan = shrinker->nr;
-		shrinker->nr = 0;
+		trace_mm_shrink_slab_start(shrinker, shrink, nr,
+					nr_pages_scanned, lru_pages,
+					max_pass, delta, total_scan);
 
 		while (total_scan >= SHRINK_BATCH) {
 			long this_scan = SHRINK_BATCH;
-			int shrink_ret;
 			int nr_before;
 
 			nr_before = do_shrinker_shrink(shrinker, shrink, 0);
@@ -292,7 +323,19 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 			cond_resched();
 		}
 
-		shrinker->nr += total_scan;
+		/*
+		 * move the unused scan count back into the shrinker in a
+		 * manner that handles concurrent updates. If we exhausted the
+		 * scan, there is no need to do an update.
+		 */
+		do {
+			nr = shrinker->nr;
+			new_nr = total_scan + nr;
+			if (total_scan <= 0)
+				break;
+		} while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+
+		trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
 	}
 	up_read(&shrinker_rwsem);
 out:
@@ -665,7 +708,7 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_RECLAIM;
 
 	if (referenced_ptes) {
-		if (PageAnon(page))
+		if (PageSwapBacked(page))
 			return PAGEREF_ACTIVATE;
 		/*
 		 * All mapped pages start out with page table
@@ -985,23 +1028,27 @@ keep_lumpy:
  *
  * returns 0 on success, -ve errno on failure.
  */
-int __isolate_lru_page(struct page *page, int mode, int file)
+int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
 {
+	bool all_lru_mode;
 	int ret = -EINVAL;
 
 	/* Only take pages on the LRU. */
 	if (!PageLRU(page))
 		return ret;
 
+	all_lru_mode = (mode & (ISOLATE_ACTIVE|ISOLATE_INACTIVE)) ==
+		(ISOLATE_ACTIVE|ISOLATE_INACTIVE);
+
 	/*
 	 * When checking the active state, we need to be sure we are
 	 * dealing with comparible boolean values.  Take the logical not
 	 * of each.
 	 */
-	if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
+	if (!all_lru_mode && !PageActive(page) != !(mode & ISOLATE_ACTIVE))
 		return ret;
 
-	if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file)
+	if (!all_lru_mode && !!page_is_file_cache(page) != file)
 		return ret;
 
 	/*
@@ -1018,6 +1065,43 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 #endif
 	ret = -EBUSY;
 
+	/*
+	 * To minimise LRU disruption, the caller can indicate that it only
+	 * wants to isolate pages it will be able to operate on without
+	 * blocking - clean pages for the most part.
+	 *
+	 * ISOLATE_CLEAN means that only clean pages should be isolated. This
+	 * is used by reclaim when it is cannot write to backing storage
+	 *
+	 * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
+	 * that it is possible to migrate without blocking
+	 */
+	if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
+		/* All the caller can do on PageWriteback is block */
+		if (PageWriteback(page))
+			return ret;
+
+		if (PageDirty(page)) {
+			struct address_space *mapping;
+
+			/* ISOLATE_CLEAN means only clean pages */
+			if (mode & ISOLATE_CLEAN)
+				return ret;
+
+			/*
+			 * Only pages without mappings or that have a
+			 * ->migratepage callback are possible to migrate
+			 * without blocking
+			 */
+			mapping = page_mapping(page);
+			if (mapping && !mapping->a_ops->migratepage)
+				return ret;
+		}
+	}
+
+	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
+		return ret;
+
 	if (likely(get_page_unless_zero(page))) {
 		/*
 		 * Be careful not to clear PageLRU until after we're
@@ -1053,7 +1137,8 @@ int __isolate_lru_page(struct page *page, int mode, int file)
  */
 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct list_head *src, struct list_head *dst,
-		unsigned long *scanned, int order, int mode, int file)
+		unsigned long *scanned, int order, isolate_mode_t mode,
+		int file)
 {
 	unsigned long nr_taken = 0;
 	unsigned long nr_lumpy_taken = 0;
@@ -1128,7 +1213,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			 * anon page which don't already have a swap slot is
 			 * pointless.
 			 */
-			if (nr_swap_pages <= 0 && PageAnon(cursor_page) &&
+			if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) &&
 			    !PageSwapCache(cursor_page))
 				break;
 
@@ -1178,8 +1263,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 static unsigned long isolate_pages_global(unsigned long nr,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
-					int mode, struct zone *z,
-					int active, int file)
+					isolate_mode_t mode,
+					struct zone *z,	int active, int file)
 {
 	int lru = LRU_BASE;
 	if (active)
@@ -1462,6 +1547,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	unsigned long nr_taken;
 	unsigned long nr_anon;
 	unsigned long nr_file;
+	isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
 
 	while (unlikely(too_many_isolated(zone, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -1472,15 +1558,21 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	}
 
 	set_reclaim_mode(priority, sc, false);
+	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
+		reclaim_mode |= ISOLATE_ACTIVE;
+
 	lru_add_drain();
+
+	if (!sc->may_unmap)
+		reclaim_mode |= ISOLATE_UNMAPPED;
+	if (!sc->may_writepage)
+		reclaim_mode |= ISOLATE_CLEAN;
+
 	spin_lock_irq(&zone->lru_lock);
 
 	if (scanning_global_lru(sc)) {
-		nr_taken = isolate_pages_global(nr_to_scan,
-			&page_list, &nr_scanned, sc->order,
-			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
-					ISOLATE_BOTH : ISOLATE_INACTIVE,
-			zone, 0, file);
+		nr_taken = isolate_pages_global(nr_to_scan, &page_list,
+			&nr_scanned, sc->order, reclaim_mode, zone, 0, file);
 		zone->pages_scanned += nr_scanned;
 		if (current_is_kswapd())
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone,
@@ -1489,12 +1581,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 			__count_zone_vm_events(PGSCAN_DIRECT, zone,
 					       nr_scanned);
 	} else {
-		nr_taken = mem_cgroup_isolate_pages(nr_to_scan,
-			&page_list, &nr_scanned, sc->order,
-			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
-					ISOLATE_BOTH : ISOLATE_INACTIVE,
-			zone, sc->mem_cgroup,
-			0, file);
+		nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list,
+			&nr_scanned, sc->order, reclaim_mode, zone,
+			sc->mem_cgroup, 0, file);
 		/*
 		 * mem_cgroup_isolate_pages() keeps track of
 		 * scanned pages on its own.
@@ -1634,19 +1723,26 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	unsigned long nr_rotated = 0;
+	isolate_mode_t reclaim_mode = ISOLATE_ACTIVE;
 
 	lru_add_drain();
+
+	if (!sc->may_unmap)
+		reclaim_mode |= ISOLATE_UNMAPPED;
+	if (!sc->may_writepage)
+		reclaim_mode |= ISOLATE_CLEAN;
+
 	spin_lock_irq(&zone->lru_lock);
 	if (scanning_global_lru(sc)) {
 		nr_taken = isolate_pages_global(nr_pages, &l_hold,
 						&pgscanned, sc->order,
-						ISOLATE_ACTIVE, zone,
+						reclaim_mode, zone,
 						1, file);
 		zone->pages_scanned += pgscanned;
 	} else {
 		nr_taken = mem_cgroup_isolate_pages(nr_pages, &l_hold,
 						&pgscanned, sc->order,
-						ISOLATE_ACTIVE, zone,
+						reclaim_mode, zone,
 						sc->mem_cgroup, 1, file);
 		/*
 		 * mem_cgroup_isolate_pages() keeps track of
@@ -1839,23 +1935,16 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	u64 fraction[2], denominator;
 	enum lru_list l;
 	int noswap = 0;
-	int force_scan = 0;
+	bool force_scan = false;
 	unsigned long nr_force_scan[2];
 
-
-	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
-	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
-
-	if (((anon + file) >> priority) < SWAP_CLUSTER_MAX) {
-		/* kswapd does zone balancing and need to scan this zone */
-		if (scanning_global_lru(sc) && current_is_kswapd())
-			force_scan = 1;
-		/* memcg may have small limit and need to avoid priority drop */
-		if (!scanning_global_lru(sc))
-			force_scan = 1;
-	}
+	/* kswapd does zone balancing and needs to scan this zone */
+	if (scanning_global_lru(sc) && current_is_kswapd() &&
+	    zone->all_unreclaimable)
+		force_scan = true;
+	/* memcg may have small limit and need to avoid priority drop */
+	if (!scanning_global_lru(sc))
+		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (!sc->may_swap || (nr_swap_pages <= 0)) {
@@ -1868,6 +1957,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 		goto out;
 	}
 
+	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_lru_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,
@@ -2004,8 +2098,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	 * inactive lists are large enough, continue reclaiming
 	 */
 	pages_for_compaction = (2UL << sc->order);
-	inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON) +
-				zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+	inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+	if (nr_swap_pages > 0)
+		inactive_lru_pages += zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
 	if (sc->nr_reclaimed < pages_for_compaction &&
 			inactive_lru_pages > pages_for_compaction)
 		return true;
@@ -2080,6 +2175,42 @@ restart:
 	throttle_vm_writeout(sc->gfp_mask);
 }
 
+/* Returns true if compaction should go ahead for a high-order request */
+static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
+{
+	unsigned long balance_gap, watermark;
+	bool watermark_ok;
+
+	/* Do not consider compaction for orders reclaim is meant to satisfy */
+	if (sc->order <= PAGE_ALLOC_COSTLY_ORDER)
+		return false;
+
+	/*
+	 * Compaction takes time to run and there are potentially other
+	 * callers using the pages just freed. Continue reclaiming until
+	 * there is a buffer of free pages available to give compaction
+	 * a reasonable chance of completing and allocating the page
+	 */
+	balance_gap = min(low_wmark_pages(zone),
+		(zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
+			KSWAPD_ZONE_BALANCE_GAP_RATIO);
+	watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
+	watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
+
+	/*
+	 * If compaction is deferred, reclaim up to a point where
+	 * compaction will have a chance of success when re-enabled
+	 */
+	if (compaction_deferred(zone))
+		return watermark_ok;
+
+	/* If compaction is not ready to start, keep reclaiming */
+	if (!compaction_suitable(zone, sc->order))
+		return false;
+
+	return watermark_ok;
+}
+
 /*
  * This is the direct reclaim path, for page-allocating processes.  We only
  * try to reclaim pages from zones which will satisfy the caller's allocation
@@ -2095,14 +2226,20 @@ restart:
  *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
+ *
+ * This function returns true if a zone is being reclaimed for a costly
+ * high-order allocation and compaction is ready to begin. This indicates to
+ * the caller that it should consider retrying the allocation instead of
+ * further reclaim.
  */
-static void shrink_zones(int priority, struct zonelist *zonelist,
+static bool shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
+	bool aborted_reclaim = false;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2117,6 +2254,21 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
+			if (COMPACTION_BUILD) {
+				/*
+				 * If we already have plenty of memory free for
+				 * compaction in this zone, don't free any more.
+				 * Even though compaction is invoked for any
+				 * non-zero order, only frequent costly order
+				 * reclamation is disruptive enough to become a
+				 * noticable problem, like transparent huge page
+				 * allocations.
+				 */
+				if (compaction_ready(zone, sc)) {
+					aborted_reclaim = true;
+					continue;
+				}
+			}
 			/*
 			 * This steals pages from memory cgroups over softlimit
 			 * and returns the number of reclaimed pages and
@@ -2134,6 +2286,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 
 		shrink_zone(priority, zone, sc);
 	}
+
+	return aborted_reclaim;
 }
 
 static bool zone_reclaimable(struct zone *zone)
@@ -2187,8 +2341,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long writeback_threshold;
+	bool aborted_reclaim;
 
-	get_mems_allowed();
 	delayacct_freepages_start();
 
 	if (scanning_global_lru(sc))
@@ -2198,7 +2352,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token(sc->mem_cgroup);
-		shrink_zones(priority, zonelist, sc);
+		aborted_reclaim = shrink_zones(priority, zonelist, sc);
+
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -2250,7 +2405,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 out:
 	delayacct_freepages_end();
-	put_mems_allowed();
 
 	if (sc->nr_reclaimed)
 		return sc->nr_reclaimed;
@@ -2263,6 +2417,10 @@ out:
 	if (oom_killer_disabled)
 		return 0;
 
+	/* Aborted reclaim to try compaction? don't OOM, then */
+	if (aborted_reclaim)
+		return 1;
+
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
 		return 1;
@@ -2554,6 +2712,9 @@ loop_again:
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
+			} else {
+				/* If balanced, clear the congested flag */
+				zone_clear_flag(zone, ZONE_CONGESTED);
 			}
 		}
 		if (i < 0)
@@ -2790,7 +2951,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 		 * them before going back to sleep.
 		 */
 		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
-		schedule();
+
+		if (!kthread_should_stop())
+			schedule();
+
 		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
 	} else {
 		if (remaining)
@@ -2817,7 +2981,9 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 static int kswapd(void *p)
 {
 	unsigned long order, new_order;
+	unsigned balanced_order;
 	int classzone_idx, new_classzone_idx;
+	int balanced_classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -2848,7 +3014,9 @@ static int kswapd(void *p)
 	set_freezable();
 
 	order = new_order = 0;
+	balanced_order = 0;
 	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
+	balanced_classzone_idx = classzone_idx;
 	for ( ; ; ) {
 		int ret;
 
@@ -2857,7 +3025,8 @@ static int kswapd(void *p)
 		 * new request of a similar or harder type will succeed soon
 		 * so consider going to sleep on the basis we reclaimed at
 		 */
-		if (classzone_idx >= new_classzone_idx && order == new_order) {
+		if (balanced_classzone_idx >= new_classzone_idx &&
+					balanced_order == new_order) {
 			new_order = pgdat->kswapd_max_order;
 			new_classzone_idx = pgdat->classzone_idx;
 			pgdat->kswapd_max_order =  0;
@@ -2872,9 +3041,12 @@ static int kswapd(void *p)
 			order = new_order;
 			classzone_idx = new_classzone_idx;
 		} else {
-			kswapd_try_to_sleep(pgdat, order, classzone_idx);
+			kswapd_try_to_sleep(pgdat, balanced_order,
+						balanced_classzone_idx);
 			order = pgdat->kswapd_max_order;
 			classzone_idx = pgdat->classzone_idx;
+			new_order = order;
+			new_classzone_idx = classzone_idx;
 			pgdat->kswapd_max_order = 0;
 			pgdat->classzone_idx = pgdat->nr_zones - 1;
 		}
@@ -2889,9 +3061,13 @@ static int kswapd(void *p)
 		 */
 		if (!ret) {
 			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			order = balance_pgdat(pgdat, order, &classzone_idx);
+			balanced_classzone_idx = classzone_idx;
+			balanced_order = balance_pgdat(pgdat, order,
+						&balanced_classzone_idx);
 		}
 	}
+
+	current->reclaim_state = NULL;
 	return 0;
 }
 
@@ -3051,14 +3227,17 @@ int kswapd_run(int nid)
 }
 
 /*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined.  Caller must
+ * hold lock_memory_hotplug().
  */
 void kswapd_stop(int nid)
 {
 	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
 
-	if (kswapd)
+	if (kswapd) {
 		kthread_stop(kswapd);
+		NODE_DATA(nid)->kswapd = NULL;
+	}
 }
 
 static int __init kswapd_init(void)