Merge 'akpm' patch series

* Merge akpm patch series: (122 commits)
  drivers/connector/cn_proc.c: remove unused local
  Documentation/SubmitChecklist: add RCU debug config options
  reiserfs: use hweight_long()
  reiserfs: use proper little-endian bitops
  pnpacpi: register disabled resources
  drivers/rtc/rtc-tegra.c: properly initialize spinlock
  drivers/rtc/rtc-twl.c: check return value of twl_rtc_write_u8() in twl_rtc_set_time()
  drivers/rtc: add support for Qualcomm PMIC8xxx RTC
  drivers/rtc/rtc-s3c.c: support clock gating
  drivers/rtc/rtc-mpc5121.c: add support for RTC on MPC5200
  init: skip calibration delay if previously done
  misc/eeprom: add eeprom access driver for digsy_mtc board
  misc/eeprom: add driver for microwire 93xx46 EEPROMs
  checkpatch.pl: update $logFunctions
  checkpatch: make utf-8 test --strict
  checkpatch.pl: add ability to ignore various messages
  checkpatch: add a "prefer __aligned" check
  checkpatch: validate signature styles and To: and Cc: lines
  checkpatch: add __rcu as a sparse modifier
  checkpatch: suggest using min_t or max_t
  ...

Did this as a merge because of (trivial) conflicts in
 - Documentation/feature-removal-schedule.txt
 - arch/xtensa/include/asm/uaccess.h
that were just easier to fix up in the merge than in the patch series.

19 files changed, 695 insertions, 482 deletions

diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 2ef0dc9e7f3..8290b1e8825 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -606,6 +606,7 @@ static void bdi_prune_sb(struct backing_dev_info *bdi)
 void bdi_unregister(struct backing_dev_info *bdi)
 {
 	if (bdi->dev) {
+		bdi_set_min_ratio(bdi, 0);
 		trace_writeback_bdi_unregister(bdi);
 		bdi_prune_sb(bdi);
 		del_timer_sync(&bdi->wb.wakeup_timer);
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 03bf3bb4519..fbb58e34688 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -500,7 +500,7 @@ void dmam_pool_destroy(struct dma_pool *pool)
 {
 	struct device *dev = pool->dev;
 
-	dma_pool_destroy(pool);
 	WARN_ON(devres_destroy(dev, dmam_pool_release, dmam_pool_match, pool));
+	dma_pool_destroy(pool);
 }
 EXPORT_SYMBOL(dmam_pool_destroy);
diff --git a/mm/filemap.c b/mm/filemap.c
index f820e600f1a..10a17111327 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -128,6 +128,7 @@ void __delete_from_page_cache(struct page *page)
 
 	radix_tree_delete(&mapping->page_tree, page->index);
 	page->mapping = NULL;
+	/* Leave page->index set: truncation lookup relies upon it */
 	mapping->nrpages--;
 	__dec_zone_page_state(page, NR_FILE_PAGES);
 	if (PageSwapBacked(page))
@@ -483,6 +484,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 			spin_unlock_irq(&mapping->tree_lock);
 		} else {
 			page->mapping = NULL;
+			/* Leave page->index set: truncation relies upon it */
 			spin_unlock_irq(&mapping->tree_lock);
 			mem_cgroup_uncharge_cache_page(page);
 			page_cache_release(page);
@@ -1792,7 +1794,7 @@ EXPORT_SYMBOL(generic_file_readonly_mmap);
 
 static struct page *__read_cache_page(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data,
 				gfp_t gfp)
 {
@@ -1823,7 +1825,7 @@ repeat:
 
 static struct page *do_read_cache_page(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data,
 				gfp_t gfp)
 
@@ -1863,7 +1865,7 @@ out:
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
- * @data:	destination for read data
+ * @data:	first arg to filler(data, page) function, often left as NULL
  *
  * Same as read_cache_page, but don't wait for page to become unlocked
  * after submitting it to the filler.
@@ -1875,7 +1877,7 @@ out:
  */
 struct page *read_cache_page_async(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return do_read_cache_page(mapping, index, filler, data, mapping_gfp_mask(mapping));
@@ -1923,7 +1925,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
  * @mapping:	the page's address_space
  * @index:	the page index
  * @filler:	function to perform the read
- * @data:	destination for read data
+ * @data:	first arg to filler(data, page) function, often left as NULL
  *
  * Read into the page cache. If a page already exists, and PageUptodate() is
  * not set, try to fill the page then wait for it to become unlocked.
@@ -1932,7 +1934,7 @@ EXPORT_SYMBOL(read_cache_page_gfp);
  */
 struct page *read_cache_page(struct address_space *mapping,
 				pgoff_t index,
-				int (*filler)(void *,struct page*),
+				int (*filler)(void *, struct page *),
 				void *data)
 {
 	return wait_on_page_read(read_cache_page_async(mapping, index, filler, data));
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 81532f297fd..e2d1587be26 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1596,14 +1596,13 @@ void __khugepaged_exit(struct mm_struct *mm)
 		list_del(&mm_slot->mm_node);
 		free = 1;
 	}
+	spin_unlock(&khugepaged_mm_lock);
 
 	if (free) {
-		spin_unlock(&khugepaged_mm_lock);
 		clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
 		free_mm_slot(mm_slot);
 		mmdrop(mm);
 	} else if (mm_slot) {
-		spin_unlock(&khugepaged_mm_lock);
 		/*
 		 * This is required to serialize against
 		 * khugepaged_test_exit() (which is guaranteed to run
@@ -1614,8 +1613,7 @@ void __khugepaged_exit(struct mm_struct *mm)
 		 */
 		down_write(&mm->mmap_sem);
 		up_write(&mm->mmap_sem);
-	} else
-		spin_unlock(&khugepaged_mm_lock);
+	}
 }
 
 static void release_pte_page(struct page *page)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index bfcf153bc82..dae27ba3be2 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -24,7 +24,7 @@
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
-#include <asm/io.h>
+#include <linux/io.h>
 
 #include <linux/hugetlb.h>
 #include <linux/node.h>
@@ -62,10 +62,10 @@ static DEFINE_SPINLOCK(hugetlb_lock);
  * must either hold the mmap_sem for write, or the mmap_sem for read and
  * the hugetlb_instantiation mutex:
  *
- * 	down_write(&mm->mmap_sem);
+ *	down_write(&mm->mmap_sem);
  * or
- * 	down_read(&mm->mmap_sem);
- * 	mutex_lock(&hugetlb_instantiation_mutex);
+ *	down_read(&mm->mmap_sem);
+ *	mutex_lock(&hugetlb_instantiation_mutex);
  */
 struct file_region {
 	struct list_head link;
@@ -503,9 +503,10 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
 	for (i = 0; i < pages_per_huge_page(h); i++) {
-		page[i].flags &= ~(1 << PG_locked | 1 << PG_error | 1 << PG_referenced |
-				1 << PG_dirty | 1 << PG_active | 1 << PG_reserved |
-				1 << PG_private | 1<< PG_writeback);
+		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
+				1 << PG_referenced | 1 << PG_dirty |
+				1 << PG_active | 1 << PG_reserved |
+				1 << PG_private | 1 << PG_writeback);
 	}
 	set_compound_page_dtor(page, NULL);
 	set_page_refcounted(page);
@@ -591,7 +592,6 @@ int PageHuge(struct page *page)
 
 	return dtor == free_huge_page;
 }
-
 EXPORT_SYMBOL_GPL(PageHuge);
 
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
@@ -1105,8 +1105,16 @@ static void __init gather_bootmem_prealloc(void)
 	struct huge_bootmem_page *m;
 
 	list_for_each_entry(m, &huge_boot_pages, list) {
-		struct page *page = virt_to_page(m);
 		struct hstate *h = m->hstate;
+		struct page *page;
+
+#ifdef CONFIG_HIGHMEM
+		page = pfn_to_page(m->phys >> PAGE_SHIFT);
+		free_bootmem_late((unsigned long)m,
+				  sizeof(struct huge_bootmem_page));
+#else
+		page = virt_to_page(m);
+#endif
 		__ClearPageReserved(page);
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
@@ -2124,9 +2132,8 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma,
 	pte_t entry;
 
 	entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep)));
-	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) {
+	if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1))
 		update_mmu_cache(vma, address, ptep);
-	}
 }
 
 
@@ -2181,9 +2188,9 @@ static int is_hugetlb_entry_migration(pte_t pte)
 	if (huge_pte_none(pte) || pte_present(pte))
 		return 0;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_migration_entry(swp)) {
+	if (non_swap_entry(swp) && is_migration_entry(swp))
 		return 1;
-	} else
+	else
 		return 0;
 }
 
@@ -2194,9 +2201,9 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 	if (huge_pte_none(pte) || pte_present(pte))
 		return 0;
 	swp = pte_to_swp_entry(pte);
-	if (non_swap_entry(swp) && is_hwpoison_entry(swp)) {
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp))
 		return 1;
-	} else
+	else
 		return 0;
 }
 
@@ -2559,7 +2566,7 @@ retry:
 		 * So we need to block hugepage fault by PG_hwpoison bit check.
 		 */
 		if (unlikely(PageHWPoison(page))) {
-			ret = VM_FAULT_HWPOISON | 
+			ret = VM_FAULT_HWPOISON |
 			      VM_FAULT_SET_HINDEX(h - hstates);
 			goto backout_unlocked;
 		}
@@ -2627,7 +2634,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 			migration_entry_wait(mm, (pmd_t *)ptep, address);
 			return 0;
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
-			return VM_FAULT_HWPOISON_LARGE | 
+			return VM_FAULT_HWPOISON_LARGE |
 			       VM_FAULT_SET_HINDEX(h - hstates);
 	}
 
diff --git a/mm/memblock.c b/mm/memblock.c
index a0562d1a6ad..ccbf9733959 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -758,9 +758,9 @@ void __init memblock_analyze(void)
 
 	/* Check marker in the unused last array entry */
 	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
-		!= (phys_addr_t)RED_INACTIVE);
+		!= MEMBLOCK_INACTIVE);
 	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
-		!= (phys_addr_t)RED_INACTIVE);
+		!= MEMBLOCK_INACTIVE);
 
 	memblock.memory_size = 0;
 
@@ -786,8 +786,8 @@ void __init memblock_init(void)
 	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
 
 	/* Write a marker in the unused last array entry */
-	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
-	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = MEMBLOCK_INACTIVE;
 
 	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
 	 * This simplifies the memblock_add() code below...
diff --git a/mm/memory.c b/mm/memory.c
index 9b8a01d941c..a56e3ba816b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1290,13 +1290,6 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
 	return addr;
 }
 
-#ifdef CONFIG_PREEMPT
-# define ZAP_BLOCK_SIZE	(8 * PAGE_SIZE)
-#else
-/* No preempt: go for improved straight-line efficiency */
-# define ZAP_BLOCK_SIZE	(1024 * PAGE_SIZE)
-#endif
-
 /**
  * unmap_vmas - unmap a range of memory covered by a list of vma's
  * @tlb: address of the caller's struct mmu_gather
@@ -1310,10 +1303,6 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb,
  *
  * Unmap all pages in the vma list.
  *
- * We aim to not hold locks for too long (for scheduling latency reasons).
- * So zap pages in ZAP_BLOCK_SIZE bytecounts.  This means we need to
- * return the ending mmu_gather to the caller.
- *
  * Only addresses between `start' and `end' will be unmapped.
  *
  * The VMA list must be sorted in ascending virtual address order.
@@ -1816,7 +1805,63 @@ next_page:
 }
 EXPORT_SYMBOL(__get_user_pages);
 
-/**
+/*
+ * fixup_user_fault() - manually resolve a user page fault
+ * @tsk:	the task_struct to use for page fault accounting, or
+ *		NULL if faults are not to be recorded.
+ * @mm:		mm_struct of target mm
+ * @address:	user address
+ * @fault_flags:flags to pass down to handle_mm_fault()
+ *
+ * This is meant to be called in the specific scenario where for locking reasons
+ * we try to access user memory in atomic context (within a pagefault_disable()
+ * section), this returns -EFAULT, and we want to resolve the user fault before
+ * trying again.
+ *
+ * Typically this is meant to be used by the futex code.
+ *
+ * The main difference with get_user_pages() is that this function will
+ * unconditionally call handle_mm_fault() which will in turn perform all the
+ * necessary SW fixup of the dirty and young bits in the PTE, while
+ * handle_mm_fault() only guarantees to update these in the struct page.
+ *
+ * This is important for some architectures where those bits also gate the
+ * access permission to the page because they are maintained in software.  On
+ * such architectures, gup() will not be enough to make a subsequent access
+ * succeed.
+ *
+ * This should be called with the mm_sem held for read.
+ */
+int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long address, unsigned int fault_flags)
+{
+	struct vm_area_struct *vma;
+	int ret;
+
+	vma = find_extend_vma(mm, address);
+	if (!vma || address < vma->vm_start)
+		return -EFAULT;
+
+	ret = handle_mm_fault(mm, vma, address, fault_flags);
+	if (ret & VM_FAULT_ERROR) {
+		if (ret & VM_FAULT_OOM)
+			return -ENOMEM;
+		if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE))
+			return -EHWPOISON;
+		if (ret & VM_FAULT_SIGBUS)
+			return -EFAULT;
+		BUG();
+	}
+	if (tsk) {
+		if (ret & VM_FAULT_MAJOR)
+			tsk->maj_flt++;
+		else
+			tsk->min_flt++;
+	}
+	return 0;
+}
+
+/*
  * get_user_pages() - pin user pages in memory
  * @tsk:	the task_struct to use for page fault accounting, or
  *		NULL if faults are not to be recorded.
@@ -3104,14 +3149,34 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *page_table;
 	spinlock_t *ptl;
 	struct page *page;
+	struct page *cow_page;
 	pte_t entry;
 	int anon = 0;
-	int charged = 0;
 	struct page *dirty_page = NULL;
 	struct vm_fault vmf;
 	int ret;
 	int page_mkwrite = 0;
 
+	/*
+	 * If we do COW later, allocate page befor taking lock_page()
+	 * on the file cache page. This will reduce lock holding time.
+	 */
+	if ((flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) {
+
+		if (unlikely(anon_vma_prepare(vma)))
+			return VM_FAULT_OOM;
+
+		cow_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+		if (!cow_page)
+			return VM_FAULT_OOM;
+
+		if (mem_cgroup_newpage_charge(cow_page, mm, GFP_KERNEL)) {
+			page_cache_release(cow_page);
+			return VM_FAULT_OOM;
+		}
+	} else
+		cow_page = NULL;
+
 	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
@@ -3120,12 +3185,13 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	ret = vma->vm_ops->fault(vma, &vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
 			    VM_FAULT_RETRY)))
-		return ret;
+		goto uncharge_out;
 
 	if (unlikely(PageHWPoison(vmf.page))) {
 		if (ret & VM_FAULT_LOCKED)
 			unlock_page(vmf.page);
-		return VM_FAULT_HWPOISON;
+		ret = VM_FAULT_HWPOISON;
+		goto uncharge_out;
 	}
 
 	/*
@@ -3143,23 +3209,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	page = vmf.page;
 	if (flags & FAULT_FLAG_WRITE) {
 		if (!(vma->vm_flags & VM_SHARED)) {
+			page = cow_page;
 			anon = 1;
-			if (unlikely(anon_vma_prepare(vma))) {
-				ret = VM_FAULT_OOM;
-				goto out;
-			}
-			page = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
-						vma, address);
-			if (!page) {
-				ret = VM_FAULT_OOM;
-				goto out;
-			}
-			if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) {
-				ret = VM_FAULT_OOM;
-				page_cache_release(page);
-				goto out;
-			}
-			charged = 1;
 			copy_user_highpage(page, vmf.page, address, vma);
 			__SetPageUptodate(page);
 		} else {
@@ -3228,8 +3279,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* no need to invalidate: a not-present page won't be cached */
 		update_mmu_cache(vma, address, page_table);
 	} else {
-		if (charged)
-			mem_cgroup_uncharge_page(page);
+		if (cow_page)
+			mem_cgroup_uncharge_page(cow_page);
 		if (anon)
 			page_cache_release(page);
 		else
@@ -3238,7 +3289,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 
 	pte_unmap_unlock(page_table, ptl);
 
-out:
 	if (dirty_page) {
 		struct address_space *mapping = page->mapping;
 
@@ -3268,6 +3318,13 @@ out:
 unwritable_page:
 	page_cache_release(page);
 	return ret;
+uncharge_out:
+	/* fs's fault handler get error */
+	if (cow_page) {
+		mem_cgroup_uncharge_page(cow_page);
+		page_cache_release(cow_page);
+	}
+	return ret;
 }
 
 static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c46887b5a11..6e7d8b21dbf 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -34,6 +34,17 @@
 
 #include "internal.h"
 
+/*
+ * online_page_callback contains pointer to current page onlining function.
+ * Initially it is generic_online_page(). If it is required it could be
+ * changed by calling set_online_page_callback() for callback registration
+ * and restore_online_page_callback() for generic callback restore.
+ */
+
+static void generic_online_page(struct page *page);
+
+static online_page_callback_t online_page_callback = generic_online_page;
+
 DEFINE_MUTEX(mem_hotplug_mutex);
 
 void lock_memory_hotplug(void)
@@ -361,23 +372,74 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn,
 }
 EXPORT_SYMBOL_GPL(__remove_pages);
 
-void online_page(struct page *page)
+int set_online_page_callback(online_page_callback_t callback)
+{
+	int rc = -EINVAL;
+
+	lock_memory_hotplug();
+
+	if (online_page_callback == generic_online_page) {
+		online_page_callback = callback;
+		rc = 0;
+	}
+
+	unlock_memory_hotplug();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(set_online_page_callback);
+
+int restore_online_page_callback(online_page_callback_t callback)
+{
+	int rc = -EINVAL;
+
+	lock_memory_hotplug();
+
+	if (online_page_callback == callback) {
+		online_page_callback = generic_online_page;
+		rc = 0;
+	}
+
+	unlock_memory_hotplug();
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(restore_online_page_callback);
+
+void __online_page_set_limits(struct page *page)
 {
 	unsigned long pfn = page_to_pfn(page);
 
-	totalram_pages++;
 	if (pfn >= num_physpages)
 		num_physpages = pfn + 1;
+}
+EXPORT_SYMBOL_GPL(__online_page_set_limits);
+
+void __online_page_increment_counters(struct page *page)
+{
+	totalram_pages++;
 
 #ifdef CONFIG_HIGHMEM
 	if (PageHighMem(page))
 		totalhigh_pages++;
 #endif
+}
+EXPORT_SYMBOL_GPL(__online_page_increment_counters);
 
+void __online_page_free(struct page *page)
+{
 	ClearPageReserved(page);
 	init_page_count(page);
 	__free_page(page);
 }
+EXPORT_SYMBOL_GPL(__online_page_free);
+
+static void generic_online_page(struct page *page)
+{
+	__online_page_set_limits(page);
+	__online_page_increment_counters(page);
+	__online_page_free(page);
+}
 
 static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 			void *arg)
@@ -388,7 +450,7 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 	if (PageReserved(pfn_to_page(start_pfn)))
 		for (i = 0; i < nr_pages; i++) {
 			page = pfn_to_page(start_pfn + i);
-			online_page(page);
+			(*online_page_callback)(page);
 			onlined_pages++;
 		}
 	*(unsigned long *)arg = onlined_pages;
diff --git a/mm/mmap.c b/mm/mmap.c
index d49736ff8a8..a65efd4db3e 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -122,9 +122,17 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		return 0;
 
 	if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
-		unsigned long n;
+		free = global_page_state(NR_FREE_PAGES);
+		free += global_page_state(NR_FILE_PAGES);
+
+		/*
+		 * shmem pages shouldn't be counted as free in this
+		 * case, they can't be purged, only swapped out, and
+		 * that won't affect the overall amount of available
+		 * memory in the system.
+		 */
+		free -= global_page_state(NR_SHMEM);
 
-		free = global_page_state(NR_FILE_PAGES);
 		free += nr_swap_pages;
 
 		/*
@@ -136,34 +144,18 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		free += global_page_state(NR_SLAB_RECLAIMABLE);
 
 		/*
-		 * Leave the last 3% for root
-		 */
-		if (!cap_sys_admin)
-			free -= free / 32;
-
-		if (free > pages)
-			return 0;
-
-		/*
-		 * nr_free_pages() is very expensive on large systems,
-		 * only call if we're about to fail.
-		 */
-		n = nr_free_pages();
-
-		/*
 		 * Leave reserved pages. The pages are not for anonymous pages.
 		 */
-		if (n <= totalreserve_pages)
+		if (free <= totalreserve_pages)
 			goto error;
 		else
-			n -= totalreserve_pages;
+			free -= totalreserve_pages;
 
 		/*
 		 * Leave the last 3% for root
 		 */
 		if (!cap_sys_admin)
-			n -= n / 32;
-		free += n;
+			free -= free / 32;
 
 		if (free > pages)
 			return 0;
diff --git a/mm/nommu.c b/mm/nommu.c
index 5c5c2d4b180..4358032566e 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1884,9 +1884,17 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		return 0;
 
 	if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
-		unsigned long n;
+		free = global_page_state(NR_FREE_PAGES);
+		free += global_page_state(NR_FILE_PAGES);
+
+		/*
+		 * shmem pages shouldn't be counted as free in this
+		 * case, they can't be purged, only swapped out, and
+		 * that won't affect the overall amount of available
+		 * memory in the system.
+		 */
+		free -= global_page_state(NR_SHMEM);
 
-		free = global_page_state(NR_FILE_PAGES);
 		free += nr_swap_pages;
 
 		/*
@@ -1898,34 +1906,18 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
 		free += global_page_state(NR_SLAB_RECLAIMABLE);
 
 		/*
-		 * Leave the last 3% for root
-		 */
-		if (!cap_sys_admin)
-			free -= free / 32;
-
-		if (free > pages)
-			return 0;
-
-		/*
-		 * nr_free_pages() is very expensive on large systems,
-		 * only call if we're about to fail.
-		 */
-		n = nr_free_pages();
-
-		/*
 		 * Leave reserved pages. The pages are not for anonymous pages.
 		 */
-		if (n <= totalreserve_pages)
+		if (free <= totalreserve_pages)
 			goto error;
 		else
-			n -= totalreserve_pages;
+			free -= totalreserve_pages;
 
 		/*
 		 * Leave the last 3% for root
 		 */
 		if (!cap_sys_admin)
-			n -= n / 32;
-		free += n;
+			free -= free / 32;
 
 		if (free > pages)
 			return 0;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index b0be989d436..eafff89b3dd 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -487,7 +487,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 
 	/*
 	 * If any of p's children has a different mm and is eligible for kill,
-	 * the one with the highest badness() score is sacrificed for its
+	 * the one with the highest oom_badness() score is sacrificed for its
 	 * parent.  This attempts to lose the minimal amount of work done while
 	 * still freeing memory.
 	 */
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 31f69886242..d8767b381b9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1141,7 +1141,6 @@ EXPORT_SYMBOL(account_page_dirtied);
 void account_page_writeback(struct page *page)
 {
 	inc_zone_page_state(page, NR_WRITEBACK);
-	inc_zone_page_state(page, NR_WRITTEN);
 }
 EXPORT_SYMBOL(account_page_writeback);
 
@@ -1358,8 +1357,10 @@ int test_clear_page_writeback(struct page *page)
 	} else {
 		ret = TestClearPageWriteback(page);
 	}
-	if (ret)
+	if (ret) {
 		dec_zone_page_state(page, NR_WRITEBACK);
+		inc_zone_page_state(page, NR_WRITTEN);
+	}
 	return ret;
 }
 
@@ -1405,10 +1406,6 @@ EXPORT_SYMBOL(test_set_page_writeback);
  */
 int mapping_tagged(struct address_space *mapping, int tag)
 {
-	int ret;
-	rcu_read_lock();
-	ret = radix_tree_tagged(&mapping->page_tree, tag);
-	rcu_read_unlock();
-	return ret;
+	return radix_tree_tagged(&mapping->page_tree, tag);
 }
 EXPORT_SYMBOL(mapping_tagged);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9119faae6e6..094472377d8 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1616,6 +1616,21 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
 	set_bit(i, zlc->fullzones);
 }
 
+/*
+ * clear all zones full, called after direct reclaim makes progress so that
+ * a zone that was recently full is not skipped over for up to a second
+ */
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+	struct zonelist_cache *zlc;	/* cached zonelist speedup info */
+
+	zlc = zonelist->zlcache_ptr;
+	if (!zlc)
+		return;
+
+	bitmap_zero(zlc->fullzones, MAX_ZONES_PER_ZONELIST);
+}
+
 #else	/* CONFIG_NUMA */
 
 static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
@@ -1632,6 +1647,10 @@ static int zlc_zone_worth_trying(struct zonelist *zonelist, struct zoneref *z,
 static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z)
 {
 }
+
+static void zlc_clear_zones_full(struct zonelist *zonelist)
+{
+}
 #endif	/* CONFIG_NUMA */
 
 /*
@@ -1664,7 +1683,7 @@ zonelist_scan:
 				continue;
 		if ((alloc_flags & ALLOC_CPUSET) &&
 			!cpuset_zone_allowed_softwall(zone, gfp_mask))
-				goto try_next_zone;
+				continue;
 
 		BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
 		if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
@@ -1676,17 +1695,36 @@ zonelist_scan:
 				    classzone_idx, alloc_flags))
 				goto try_this_zone;
 
+			if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+				/*
+				 * we do zlc_setup if there are multiple nodes
+				 * and before considering the first zone allowed
+				 * by the cpuset.
+				 */
+				allowednodes = zlc_setup(zonelist, alloc_flags);
+				zlc_active = 1;
+				did_zlc_setup = 1;
+			}
+
 			if (zone_reclaim_mode == 0)
 				goto this_zone_full;
 
+			/*
+			 * As we may have just activated ZLC, check if the first
+			 * eligible zone has failed zone_reclaim recently.
+			 */
+			if (NUMA_BUILD && zlc_active &&
+				!zlc_zone_worth_trying(zonelist, z, allowednodes))
+				continue;
+
 			ret = zone_reclaim(zone, gfp_mask, order);
 			switch (ret) {
 			case ZONE_RECLAIM_NOSCAN:
 				/* did not scan */
-				goto try_next_zone;
+				continue;
 			case ZONE_RECLAIM_FULL:
 				/* scanned but unreclaimable */
-				goto this_zone_full;
+				continue;
 			default:
 				/* did we reclaim enough */
 				if (!zone_watermark_ok(zone, order, mark,
@@ -1703,16 +1741,6 @@ try_this_zone:
 this_zone_full:
 		if (NUMA_BUILD)
 			zlc_mark_zone_full(zonelist, z);
-try_next_zone:
-		if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
-			/*
-			 * we do zlc_setup after the first zone is tried but only
-			 * if there are multiple nodes make it worthwhile
-			 */
-			allowednodes = zlc_setup(zonelist, alloc_flags);
-			zlc_active = 1;
-			did_zlc_setup = 1;
-		}
 	}
 
 	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
@@ -1954,6 +1982,10 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!(*did_some_progress)))
 		return NULL;
 
+	/* After successful reclaim, reconsider all zones for allocation */
+	if (NUMA_BUILD)
+		zlc_clear_zones_full(zonelist);
+
 retry:
 	page = get_page_from_freelist(gfp_mask, nodemask, order,
 					zonelist, high_zoneidx,
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 53bffc6c293..39d216d535e 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -225,8 +225,8 @@ int __meminit online_page_cgroup(unsigned long start_pfn,
 	unsigned long start, end, pfn;
 	int fail = 0;
 
-	start = start_pfn & ~(PAGES_PER_SECTION - 1);
-	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+	start = SECTION_ALIGN_DOWN(start_pfn);
+	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
 
 	if (nid == -1) {
 		/*
@@ -258,8 +258,8 @@ int __meminit offline_page_cgroup(unsigned long start_pfn,
 {
 	unsigned long start, end, pfn;
 
-	start = start_pfn & ~(PAGES_PER_SECTION - 1);
-	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+	start = SECTION_ALIGN_DOWN(start_pfn);
+	end = SECTION_ALIGN_UP(start_pfn + nr_pages);
 
 	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
 		__free_page_cgroup(pfn);
@@ -537,7 +537,7 @@ int swap_cgroup_swapon(int type, unsigned long max_pages)
 nomem:
 	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
 	printk(KERN_INFO
-		"swap_cgroup can be disabled by noswapaccount boot option\n");
+		"swap_cgroup can be disabled by swapaccount=0 boot option\n");
 	return -ENOMEM;
 }
 
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index c3450d53361..2f5cf10ff66 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -126,7 +126,39 @@ static int walk_hugetlb_range(struct vm_area_struct *vma,
 
 	return 0;
 }
-#endif
+
+static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk)
+{
+	struct vm_area_struct *vma;
+
+	/* We don't need vma lookup at all. */
+	if (!walk->hugetlb_entry)
+		return NULL;
+
+	VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
+	vma = find_vma(walk->mm, addr);
+	if (vma && vma->vm_start <= addr && is_vm_hugetlb_page(vma))
+		return vma;
+
+	return NULL;
+}
+
+#else /* CONFIG_HUGETLB_PAGE */
+static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk)
+{
+	return NULL;
+}
+
+static int walk_hugetlb_range(struct vm_area_struct *vma,
+			      unsigned long addr, unsigned long end,
+			      struct mm_walk *walk)
+{
+	return 0;
+}
+
+#endif /* CONFIG_HUGETLB_PAGE */
+
+
 
 /**
  * walk_page_range - walk a memory map's page tables with a callback
@@ -144,11 +176,15 @@ static int walk_hugetlb_range(struct vm_area_struct *vma,
  * associated range, and a copy of the original mm_walk for access to
  * the ->private or ->mm fields.
  *
- * No locks are taken, but the bottom level iterator will map PTE
+ * Usually no locks are taken, but splitting transparent huge page may
+ * take page table lock. And the bottom level iterator will map PTE
  * directories from highmem if necessary.
  *
  * If any callback returns a non-zero value, the walk is aborted and
  * the return value is propagated back to the caller. Otherwise 0 is returned.
+ *
+ * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry
+ * is !NULL.
  */
 int walk_page_range(unsigned long addr, unsigned long end,
 		    struct mm_walk *walk)
@@ -165,18 +201,17 @@ int walk_page_range(unsigned long addr, unsigned long end,
 
 	pgd = pgd_offset(walk->mm, addr);
 	do {
-		struct vm_area_struct *uninitialized_var(vma);
+		struct vm_area_struct *vma;
 
 		next = pgd_addr_end(addr, end);
 
-#ifdef CONFIG_HUGETLB_PAGE
 		/*
 		 * handle hugetlb vma individually because pagetable walk for
 		 * the hugetlb page is dependent on the architecture and
 		 * we can't handled it in the same manner as non-huge pages.
 		 */
-		vma = find_vma(walk->mm, addr);
-		if (vma && is_vm_hugetlb_page(vma)) {
+		vma = hugetlb_vma(addr, walk);
+		if (vma) {
 			if (vma->vm_end < next)
 				next = vma->vm_end;
 			/*
@@ -189,7 +224,7 @@ int walk_page_range(unsigned long addr, unsigned long end,
 			pgd = pgd_offset(walk->mm, next);
 			continue;
 		}
-#endif
+
 		if (pgd_none_or_clear_bad(pgd)) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);
diff --git a/mm/shmem.c b/mm/shmem.c
index 3e519798b52..5cc21f8b4cd 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -51,6 +51,7 @@ static struct vfsmount *shm_mnt;
 #include <linux/shmem_fs.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
+#include <linux/splice.h>
 #include <linux/security.h>
 #include <linux/swapops.h>
 #include <linux/mempolicy.h>
@@ -126,8 +127,15 @@ static unsigned long shmem_default_max_inodes(void)
 }
 #endif
 
-static int shmem_getpage(struct inode *inode, unsigned long idx,
-			 struct page **pagep, enum sgp_type sgp, int *type);
+static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
+	struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type);
+
+static inline int shmem_getpage(struct inode *inode, pgoff_t index,
+	struct page **pagep, enum sgp_type sgp, int *fault_type)
+{
+	return shmem_getpage_gfp(inode, index, pagep, sgp,
+			mapping_gfp_mask(inode->i_mapping), fault_type);
+}
 
 static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
 {
@@ -241,9 +249,7 @@ static void shmem_free_blocks(struct inode *inode, long pages)
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
 	if (sbinfo->max_blocks) {
 		percpu_counter_add(&sbinfo->used_blocks, -pages);
-		spin_lock(&inode->i_lock);
 		inode->i_blocks -= pages*BLOCKS_PER_PAGE;
-		spin_unlock(&inode->i_lock);
 	}
 }
 
@@ -405,10 +411,12 @@ static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, uns
  * @info:	info structure for the inode
  * @index:	index of the page to find
  * @sgp:	check and recheck i_size? skip allocation?
+ * @gfp:	gfp mask to use for any page allocation
  *
  * If the entry does not exist, allocate it.
  */
-static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp)
+static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info,
+			unsigned long index, enum sgp_type sgp, gfp_t gfp)
 {
 	struct inode *inode = &info->vfs_inode;
 	struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
@@ -432,13 +440,11 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long
 						sbinfo->max_blocks - 1) >= 0)
 				return ERR_PTR(-ENOSPC);
 			percpu_counter_inc(&sbinfo->used_blocks);
-			spin_lock(&inode->i_lock);
 			inode->i_blocks += BLOCKS_PER_PAGE;
-			spin_unlock(&inode->i_lock);
 		}
 
 		spin_unlock(&info->lock);
-		page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
+		page = shmem_dir_alloc(gfp);
 		spin_lock(&info->lock);
 
 		if (!page) {
@@ -966,20 +972,7 @@ found:
 	error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT);
 	/* which does mem_cgroup_uncharge_cache_page on error */
 
-	if (error == -EEXIST) {
-		struct page *filepage = find_get_page(mapping, idx);
-		error = 1;
-		if (filepage) {
-			/*
-			 * There might be a more uptodate page coming down
-			 * from a stacked writepage: forget our swappage if so.
-			 */
-			if (PageUptodate(filepage))
-				error = 0;
-			page_cache_release(filepage);
-		}
-	}
-	if (!error) {
+	if (error != -ENOMEM) {
 		delete_from_swap_cache(page);
 		set_page_dirty(page);
 		info->flags |= SHMEM_PAGEIN;
@@ -1066,16 +1059,17 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	/*
 	 * shmem_backing_dev_info's capabilities prevent regular writeback or
 	 * sync from ever calling shmem_writepage; but a stacking filesystem
-	 * may use the ->writepage of its underlying filesystem, in which case
+	 * might use ->writepage of its underlying filesystem, in which case
 	 * tmpfs should write out to swap only in response to memory pressure,
-	 * and not for the writeback threads or sync.  However, in those cases,
-	 * we do still want to check if there's a redundant swappage to be
-	 * discarded.
+	 * and not for the writeback threads or sync.
 	 */
-	if (wbc->for_reclaim)
-		swap = get_swap_page();
-	else
-		swap.val = 0;
+	if (!wbc->for_reclaim) {
+		WARN_ON_ONCE(1);	/* Still happens? Tell us about it! */
+		goto redirty;
+	}
+	swap = get_swap_page();
+	if (!swap.val)
+		goto redirty;
 
 	/*
 	 * Add inode to shmem_unuse()'s list of swapped-out inodes,
@@ -1086,15 +1080,12 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	 * we've taken the spinlock, because shmem_unuse_inode() will
 	 * prune a !swapped inode from the swaplist under both locks.
 	 */
-	if (swap.val) {
-		mutex_lock(&shmem_swaplist_mutex);
-		if (list_empty(&info->swaplist))
-			list_add_tail(&info->swaplist, &shmem_swaplist);
-	}
+	mutex_lock(&shmem_swaplist_mutex);
+	if (list_empty(&info->swaplist))
+		list_add_tail(&info->swaplist, &shmem_swaplist);
 
 	spin_lock(&info->lock);
-	if (swap.val)
-		mutex_unlock(&shmem_swaplist_mutex);
+	mutex_unlock(&shmem_swaplist_mutex);
 
 	if (index >= info->next_index) {
 		BUG_ON(!(info->flags & SHMEM_TRUNCATE));
@@ -1102,16 +1093,13 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	}
 	entry = shmem_swp_entry(info, index, NULL);
 	if (entry->val) {
-		/*
-		 * The more uptodate page coming down from a stacked
-		 * writepage should replace our old swappage.
-		 */
+		WARN_ON_ONCE(1);	/* Still happens? Tell us about it! */
 		free_swap_and_cache(*entry);
 		shmem_swp_set(info, entry, 0);
 	}
 	shmem_recalc_inode(inode);
 
-	if (swap.val && add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
+	if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
 		delete_from_page_cache(page);
 		shmem_swp_set(info, entry, swap.val);
 		shmem_swp_unmap(entry);
@@ -1228,92 +1216,83 @@ static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
 #endif
 
 /*
- * shmem_getpage - either get the page from swap or allocate a new one
+ * shmem_getpage_gfp - find page in cache, or get from swap, or allocate
  *
  * If we allocate a new one we do not mark it dirty. That's up to the
  * vm. If we swap it in we mark it dirty since we also free the swap
  * entry since a page cannot live in both the swap and page cache
  */
-static int shmem_getpage(struct inode *inode, unsigned long idx,
-			struct page **pagep, enum sgp_type sgp, int *type)
+static int shmem_getpage_gfp(struct inode *inode, pgoff_t idx,
+	struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type)
 {
 	struct address_space *mapping = inode->i_mapping;
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	struct shmem_sb_info *sbinfo;
-	struct page *filepage = *pagep;
-	struct page *swappage;
+	struct page *page;
 	struct page *prealloc_page = NULL;
 	swp_entry_t *entry;
 	swp_entry_t swap;
-	gfp_t gfp;
 	int error;
+	int ret;
 
 	if (idx >= SHMEM_MAX_INDEX)
 		return -EFBIG;
-
-	if (type)
-		*type = 0;
-
-	/*
-	 * Normally, filepage is NULL on entry, and either found
-	 * uptodate immediately, or allocated and zeroed, or read
-	 * in under swappage, which is then assigned to filepage.
-	 * But shmem_readpage (required for splice) passes in a locked
-	 * filepage, which may be found not uptodate by other callers
-	 * too, and may need to be copied from the swappage read in.
-	 */
 repeat:
-	if (!filepage)
-		filepage = find_lock_page(mapping, idx);
-	if (filepage && PageUptodate(filepage))
-		goto done;
-	gfp = mapping_gfp_mask(mapping);
-	if (!filepage) {
+	page = find_lock_page(mapping, idx);
+	if (page) {
 		/*
-		 * Try to preload while we can wait, to not make a habit of
-		 * draining atomic reserves; but don't latch on to this cpu.
+		 * Once we can get the page lock, it must be uptodate:
+		 * if there were an error in reading back from swap,
+		 * the page would not be inserted into the filecache.
 		 */
-		error = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
-		if (error)
-			goto failed;
-		radix_tree_preload_end();
-		if (sgp != SGP_READ && !prealloc_page) {
-			/* We don't care if this fails */
-			prealloc_page = shmem_alloc_page(gfp, info, idx);
-			if (prealloc_page) {
-				if (mem_cgroup_cache_charge(prealloc_page,
-						current->mm, GFP_KERNEL)) {
-					page_cache_release(prealloc_page);
-					prealloc_page = NULL;
-				}
+		BUG_ON(!PageUptodate(page));
+		goto done;
+	}
+
+	/*
+	 * Try to preload while we can wait, to not make a habit of
+	 * draining atomic reserves; but don't latch on to this cpu.
+	 */
+	error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+	if (error)
+		goto out;
+	radix_tree_preload_end();
+
+	if (sgp != SGP_READ && !prealloc_page) {
+		prealloc_page = shmem_alloc_page(gfp, info, idx);
+		if (prealloc_page) {
+			SetPageSwapBacked(prealloc_page);
+			if (mem_cgroup_cache_charge(prealloc_page,
+					current->mm, GFP_KERNEL)) {
+				page_cache_release(prealloc_page);
+				prealloc_page = NULL;
 			}
 		}
 	}
-	error = 0;
 
 	spin_lock(&info->lock);
 	shmem_recalc_inode(inode);
-	entry = shmem_swp_alloc(info, idx, sgp);
+	entry = shmem_swp_alloc(info, idx, sgp, gfp);
 	if (IS_ERR(entry)) {
 		spin_unlock(&info->lock);
 		error = PTR_ERR(entry);
-		goto failed;
+		goto out;
 	}
 	swap = *entry;
 
 	if (swap.val) {
 		/* Look it up and read it in.. */
-		swappage = lookup_swap_cache(swap);
-		if (!swappage) {
+		page = lookup_swap_cache(swap);
+		if (!page) {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
 			/* here we actually do the io */
-			if (type)
-				*type |= VM_FAULT_MAJOR;
-			swappage = shmem_swapin(swap, gfp, info, idx);
-			if (!swappage) {
+			if (fault_type)
+				*fault_type |= VM_FAULT_MAJOR;
+			page = shmem_swapin(swap, gfp, info, idx);
+			if (!page) {
 				spin_lock(&info->lock);
-				entry = shmem_swp_alloc(info, idx, sgp);
+				entry = shmem_swp_alloc(info, idx, sgp, gfp);
 				if (IS_ERR(entry))
 					error = PTR_ERR(entry);
 				else {
@@ -1323,62 +1302,42 @@ repeat:
 				}
 				spin_unlock(&info->lock);
 				if (error)
-					goto failed;
+					goto out;
 				goto repeat;
 			}
-			wait_on_page_locked(swappage);
-			page_cache_release(swappage);
+			wait_on_page_locked(page);
+			page_cache_release(page);
 			goto repeat;
 		}
 
 		/* We have to do this with page locked to prevent races */
-		if (!trylock_page(swappage)) {
+		if (!trylock_page(page)) {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
-			wait_on_page_locked(swappage);
-			page_cache_release(swappage);
+			wait_on_page_locked(page);
+			page_cache_release(page);
 			goto repeat;
 		}
-		if (PageWriteback(swappage)) {
+		if (PageWriteback(page)) {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
-			wait_on_page_writeback(swappage);
-			unlock_page(swappage);
-			page_cache_release(swappage);
+			wait_on_page_writeback(page);
+			unlock_page(page);
+			page_cache_release(page);
 			goto repeat;
 		}
-		if (!PageUptodate(swappage)) {
+		if (!PageUptodate(page)) {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
-			unlock_page(swappage);
-			page_cache_release(swappage);
+			unlock_page(page);
+			page_cache_release(page);
 			error = -EIO;
-			goto failed;
+			goto out;
 		}
 
-		if (filepage) {
-			shmem_swp_set(info, entry, 0);
-			shmem_swp_unmap(entry);
-			delete_from_swap_cache(swappage);
-			spin_unlock(&info->lock);
-			copy_highpage(filepage, swappage);
-			unlock_page(swappage);
-			page_cache_release(swappage);
-			flush_dcache_page(filepage);
-			SetPageUptodate(filepage);
-			set_page_dirty(filepage);
-			swap_free(swap);
-		} else if (!(error = add_to_page_cache_locked(swappage, mapping,
-					idx, GFP_NOWAIT))) {
-			info->flags |= SHMEM_PAGEIN;
-			shmem_swp_set(info, entry, 0);
-			shmem_swp_unmap(entry);
-			delete_from_swap_cache(swappage);
-			spin_unlock(&info->lock);
-			filepage = swappage;
-			set_page_dirty(filepage);
-			swap_free(swap);
-		} else {
+		error = add_to_page_cache_locked(page, mapping,
+						 idx, GFP_NOWAIT);
+		if (error) {
 			shmem_swp_unmap(entry);
 			spin_unlock(&info->lock);
 			if (error == -ENOMEM) {
@@ -1387,32 +1346,38 @@ repeat:
 				 * call memcg's OOM if needed.
 				 */
 				error = mem_cgroup_shmem_charge_fallback(
-								swappage,
-								current->mm,
-								gfp);
+						page, current->mm, gfp);
 				if (error) {
-					unlock_page(swappage);
-					page_cache_release(swappage);
-					goto failed;
+					unlock_page(page);
+					page_cache_release(page);
+					goto out;
 				}
 			}
-			unlock_page(swappage);
-			page_cache_release(swappage);
+			unlock_page(page);
+			page_cache_release(page);
 			goto repeat;
 		}
-	} else if (sgp == SGP_READ && !filepage) {
+
+		info->flags |= SHMEM_PAGEIN;
+		shmem_swp_set(info, entry, 0);
 		shmem_swp_unmap(entry);
-		filepage = find_get_page(mapping, idx);
-		if (filepage &&
-		    (!PageUptodate(filepage) || !trylock_page(filepage))) {
+		delete_from_swap_cache(page);
+		spin_unlock(&info->lock);
+		set_page_dirty(page);
+		swap_free(swap);
+
+	} else if (sgp == SGP_READ) {
+		shmem_swp_unmap(entry);
+		page = find_get_page(mapping, idx);
+		if (page && !trylock_page(page)) {
 			spin_unlock(&info->lock);
-			wait_on_page_locked(filepage);
-			page_cache_release(filepage);
-			filepage = NULL;
+			wait_on_page_locked(page);
+			page_cache_release(page);
 			goto repeat;
 		}
 		spin_unlock(&info->lock);
-	} else {
+
+	} else if (prealloc_page) {
 		shmem_swp_unmap(entry);
 		sbinfo = SHMEM_SB(inode->i_sb);
 		if (sbinfo->max_blocks) {
@@ -1421,126 +1386,86 @@ repeat:
 			    shmem_acct_block(info->flags))
 				goto nospace;
 			percpu_counter_inc(&sbinfo->used_blocks);
-			spin_lock(&inode->i_lock);
 			inode->i_blocks += BLOCKS_PER_PAGE;
-			spin_unlock(&inode->i_lock);
 		} else if (shmem_acct_block(info->flags))
 			goto nospace;
 
-		if (!filepage) {
-			int ret;
-
-			if (!prealloc_page) {
-				spin_unlock(&info->lock);
-				filepage = shmem_alloc_page(gfp, info, idx);
-				if (!filepage) {
-					shmem_unacct_blocks(info->flags, 1);
-					shmem_free_blocks(inode, 1);
-					error = -ENOMEM;
-					goto failed;
-				}
-				SetPageSwapBacked(filepage);
+		page = prealloc_page;
+		prealloc_page = NULL;
 
-				/*
-				 * Precharge page while we can wait, compensate
-				 * after
-				 */
-				error = mem_cgroup_cache_charge(filepage,
-					current->mm, GFP_KERNEL);
-				if (error) {
-					page_cache_release(filepage);
-					shmem_unacct_blocks(info->flags, 1);
-					shmem_free_blocks(inode, 1);
-					filepage = NULL;
-					goto failed;
-				}
-
-				spin_lock(&info->lock);
-			} else {
-				filepage = prealloc_page;
-				prealloc_page = NULL;
-				SetPageSwapBacked(filepage);
-			}
-
-			entry = shmem_swp_alloc(info, idx, sgp);
-			if (IS_ERR(entry))
-				error = PTR_ERR(entry);
-			else {
-				swap = *entry;
-				shmem_swp_unmap(entry);
-			}
-			ret = error || swap.val;
-			if (ret)
-				mem_cgroup_uncharge_cache_page(filepage);
-			else
-				ret = add_to_page_cache_lru(filepage, mapping,
+		entry = shmem_swp_alloc(info, idx, sgp, gfp);
+		if (IS_ERR(entry))
+			error = PTR_ERR(entry);
+		else {
+			swap = *entry;
+			shmem_swp_unmap(entry);
+		}
+		ret = error || swap.val;
+		if (ret)
+			mem_cgroup_uncharge_cache_page(page);
+		else
+			ret = add_to_page_cache_lru(page, mapping,
 						idx, GFP_NOWAIT);
-			/*
-			 * At add_to_page_cache_lru() failure, uncharge will
-			 * be done automatically.
-			 */
-			if (ret) {
-				spin_unlock(&info->lock);
-				page_cache_release(filepage);
-				shmem_unacct_blocks(info->flags, 1);
-				shmem_free_blocks(inode, 1);
-				filepage = NULL;
-				if (error)
-					goto failed;
-				goto repeat;
-			}
-			info->flags |= SHMEM_PAGEIN;
+		/*
+		 * At add_to_page_cache_lru() failure,
+		 * uncharge will be done automatically.
+		 */
+		if (ret) {
+			shmem_unacct_blocks(info->flags, 1);
+			shmem_free_blocks(inode, 1);
+			spin_unlock(&info->lock);
+			page_cache_release(page);
+			if (error)
+				goto out;
+			goto repeat;
 		}
 
+		info->flags |= SHMEM_PAGEIN;
 		info->alloced++;
 		spin_unlock(&info->lock);
-		clear_highpage(filepage);
-		flush_dcache_page(filepage);
-		SetPageUptodate(filepage);
+		clear_highpage(page);
+		flush_dcache_page(page);
+		SetPageUptodate(page);
 		if (sgp == SGP_DIRTY)
-			set_page_dirty(filepage);
+			set_page_dirty(page);
+
+	} else {
+		spin_unlock(&info->lock);
+		error = -ENOMEM;
+		goto out;
 	}
 done:
-	*pagep = filepage;
+	*pagep = page;
 	error = 0;
-	goto out;
+out:
+	if (prealloc_page) {
+		mem_cgroup_uncharge_cache_page(prealloc_page);
+		page_cache_release(prealloc_page);
+	}
+	return error;
 
 nospace:
 	/*
 	 * Perhaps the page was brought in from swap between find_lock_page
 	 * and taking info->lock?  We allow for that at add_to_page_cache_lru,
 	 * but must also avoid reporting a spurious ENOSPC while working on a
-	 * full tmpfs.  (When filepage has been passed in to shmem_getpage, it
-	 * is already in page cache, which prevents this race from occurring.)
+	 * full tmpfs.
 	 */
-	if (!filepage) {
-		struct page *page = find_get_page(mapping, idx);
-		if (page) {
-			spin_unlock(&info->lock);
-			page_cache_release(page);
-			goto repeat;
-		}
-	}
+	page = find_get_page(mapping, idx);
 	spin_unlock(&info->lock);
-	error = -ENOSPC;
-failed:
-	if (*pagep != filepage) {
-		unlock_page(filepage);
-		page_cache_release(filepage);
-	}
-out:
-	if (prealloc_page) {
-		mem_cgroup_uncharge_cache_page(prealloc_page);
-		page_cache_release(prealloc_page);
+	if (page) {
+		page_cache_release(page);
+		goto repeat;
 	}
-	return error;
+	error = -ENOSPC;
+	goto out;
 }
 
 static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
 	int error;
-	int ret;
+	int ret = VM_FAULT_LOCKED;
 
 	if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode))
 		return VM_FAULT_SIGBUS;
@@ -1548,11 +1473,12 @@ static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
 	if (error)
 		return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
+
 	if (ret & VM_FAULT_MAJOR) {
 		count_vm_event(PGMAJFAULT);
 		mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
 	}
-	return ret | VM_FAULT_LOCKED;
+	return ret;
 }
 
 #ifdef CONFIG_NUMA
@@ -1669,19 +1595,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_symlink_inline_operations;
 
-/*
- * Normally tmpfs avoids the use of shmem_readpage and shmem_write_begin;
- * but providing them allows a tmpfs file to be used for splice, sendfile, and
- * below the loop driver, in the generic fashion that many filesystems support.
- */
-static int shmem_readpage(struct file *file, struct page *page)
-{
-	struct inode *inode = page->mapping->host;
-	int error = shmem_getpage(inode, page->index, &page, SGP_CACHE, NULL);
-	unlock_page(page);
-	return error;
-}
-
 static int
 shmem_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
@@ -1689,7 +1602,6 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 {
 	struct inode *inode = mapping->host;
 	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
-	*pagep = NULL;
 	return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
 }
 
@@ -1846,6 +1758,119 @@ static ssize_t shmem_file_aio_read(struct kiocb *iocb,
 	return retval;
 }
 
+static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
+				struct pipe_inode_info *pipe, size_t len,
+				unsigned int flags)
+{
+	struct address_space *mapping = in->f_mapping;
+	struct inode *inode = mapping->host;
+	unsigned int loff, nr_pages, req_pages;
+	struct page *pages[PIPE_DEF_BUFFERS];
+	struct partial_page partial[PIPE_DEF_BUFFERS];
+	struct page *page;
+	pgoff_t index, end_index;
+	loff_t isize, left;
+	int error, page_nr;
+	struct splice_pipe_desc spd = {
+		.pages = pages,
+		.partial = partial,
+		.flags = flags,
+		.ops = &page_cache_pipe_buf_ops,
+		.spd_release = spd_release_page,
+	};
+
+	isize = i_size_read(inode);
+	if (unlikely(*ppos >= isize))
+		return 0;
+
+	left = isize - *ppos;
+	if (unlikely(left < len))
+		len = left;
+
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
+
+	index = *ppos >> PAGE_CACHE_SHIFT;
+	loff = *ppos & ~PAGE_CACHE_MASK;
+	req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	nr_pages = min(req_pages, pipe->buffers);
+
+	spd.nr_pages = find_get_pages_contig(mapping, index,
+						nr_pages, spd.pages);
+	index += spd.nr_pages;
+	error = 0;
+
+	while (spd.nr_pages < nr_pages) {
+		error = shmem_getpage(inode, index, &page, SGP_CACHE, NULL);
+		if (error)
+			break;
+		unlock_page(page);
+		spd.pages[spd.nr_pages++] = page;
+		index++;
+	}
+
+	index = *ppos >> PAGE_CACHE_SHIFT;
+	nr_pages = spd.nr_pages;
+	spd.nr_pages = 0;
+
+	for (page_nr = 0; page_nr < nr_pages; page_nr++) {
+		unsigned int this_len;
+
+		if (!len)
+			break;
+
+		this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
+		page = spd.pages[page_nr];
+
+		if (!PageUptodate(page) || page->mapping != mapping) {
+			error = shmem_getpage(inode, index, &page,
+							SGP_CACHE, NULL);
+			if (error)
+				break;
+			unlock_page(page);
+			page_cache_release(spd.pages[page_nr]);
+			spd.pages[page_nr] = page;
+		}
+
+		isize = i_size_read(inode);
+		end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
+		if (unlikely(!isize || index > end_index))
+			break;
+
+		if (end_index == index) {
+			unsigned int plen;
+
+			plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
+			if (plen <= loff)
+				break;
+
+			this_len = min(this_len, plen - loff);
+			len = this_len;
+		}
+
+		spd.partial[page_nr].offset = loff;
+		spd.partial[page_nr].len = this_len;
+		len -= this_len;
+		loff = 0;
+		spd.nr_pages++;
+		index++;
+	}
+
+	while (page_nr < nr_pages)
+		page_cache_release(spd.pages[page_nr++]);
+
+	if (spd.nr_pages)
+		error = splice_to_pipe(pipe, &spd);
+
+	splice_shrink_spd(pipe, &spd);
+
+	if (error > 0) {
+		*ppos += error;
+		file_accessed(in);
+	}
+	return error;
+}
+
 static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb);
@@ -2006,7 +2031,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s
 	int error;
 	int len;
 	struct inode *inode;
-	struct page *page = NULL;
+	struct page *page;
 	char *kaddr;
 	struct shmem_inode_info *info;
 
@@ -2684,7 +2709,6 @@ static const struct address_space_operations shmem_aops = {
 	.writepage	= shmem_writepage,
 	.set_page_dirty	= __set_page_dirty_no_writeback,
 #ifdef CONFIG_TMPFS
-	.readpage	= shmem_readpage,
 	.write_begin	= shmem_write_begin,
 	.write_end	= shmem_write_end,
 #endif
@@ -2701,7 +2725,7 @@ static const struct file_operations shmem_file_operations = {
 	.aio_read	= shmem_file_aio_read,
 	.aio_write	= generic_file_aio_write,
 	.fsync		= noop_fsync,
-	.splice_read	= generic_file_splice_read,
+	.splice_read	= shmem_file_splice_read,
 	.splice_write	= generic_file_splice_write,
 #endif
 };
@@ -3042,13 +3066,29 @@ int shmem_zero_setup(struct vm_area_struct *vma)
  * suit tmpfs, since it may have pages in swapcache, and needs to find those
  * for itself; although drivers/gpu/drm i915 and ttm rely upon this support.
  *
- * Provide a stub for those callers to start using now, then later
- * flesh it out to call shmem_getpage() with additional gfp mask, when
- * shmem_file_splice_read() is added and shmem_readpage() is removed.
+ * i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in
+ * with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily.
  */
 struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					 pgoff_t index, gfp_t gfp)
 {
+#ifdef CONFIG_SHMEM
+	struct inode *inode = mapping->host;
+	struct page *page;
+	int error;
+
+	BUG_ON(mapping->a_ops != &shmem_aops);
+	error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL);
+	if (error)
+		page = ERR_PTR(error);
+	else
+		unlock_page(page);
+	return page;
+#else
+	/*
+	 * The tiny !SHMEM case uses ramfs without swap
+	 */
 	return read_cache_page_gfp(mapping, index, gfp);
+#endif
 }
 EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp);
diff --git a/mm/sparse.c b/mm/sparse.c
index aa64b12831a..858e1dff9b2 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -40,7 +40,7 @@ static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
 static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
 #endif
 
-int page_to_nid(struct page *page)
+int page_to_nid(const struct page *page)
 {
 	return section_to_node_table[page_to_section(page)];
 }
diff --git a/mm/thrash.c b/mm/thrash.c
index fabf2d0f516..e53f7d02c17 100644
--- a/mm/thrash.c
+++ b/mm/thrash.c
@@ -6,7 +6,7 @@
  * Released under the GPL, see the file COPYING for details.
  *
  * Simple token based thrashing protection, using the algorithm
- * described in:  http://www.cs.wm.edu/~sjiang/token.pdf
+ * described in: http://www.cse.ohio-state.edu/hpcs/WWW/HTML/publications/abs05-1.html
  *
  * Sep 2006, Ashwin Chaugule <ashwin.chaugule@celunite.com>
  * Improved algorithm to pass token:
@@ -30,8 +30,6 @@
 static DEFINE_SPINLOCK(swap_token_lock);
 struct mm_struct *swap_token_mm;
 struct mem_cgroup *swap_token_memcg;
-static unsigned int global_faults;
-static unsigned int last_aging;
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 static struct mem_cgroup *swap_token_memcg_from_mm(struct mm_struct *mm)
@@ -55,6 +53,8 @@ void grab_swap_token(struct mm_struct *mm)
 {
 	int current_interval;
 	unsigned int old_prio = mm->token_priority;
+	static unsigned int global_faults;
+	static unsigned int last_aging;
 
 	global_faults++;
 
@@ -67,6 +67,17 @@ void grab_swap_token(struct mm_struct *mm)
 	if (!swap_token_mm)
 		goto replace_token;
 
+	/*
+	 * Usually, we don't need priority aging because long interval faults
+	 * makes priority decrease quickly. But there is one exception. If the
+	 * token owner task is sleeping, it never make long interval faults.
+	 * Thus, we need a priority aging mechanism instead. The requirements
+	 * of priority aging are
+	 *  1) An aging interval is reasonable enough long. Too short aging
+	 *     interval makes quick swap token lost and decrease performance.
+	 *  2) The swap token owner task have to get priority aging even if
+	 *     it's under sleep.
+	 */
 	if ((global_faults - last_aging) > TOKEN_AGING_INTERVAL) {
 		swap_token_mm->token_priority /= 2;
 		last_aging = global_faults;
diff --git a/mm/truncate.c b/mm/truncate.c
index 003c6c685fc..232eb2736a7 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -199,9 +199,6 @@ int invalidate_inode_page(struct page *page)
  * The first pass will remove most pages, so the search cost of the second pass
  * is low.
  *
- * When looking at page->index outside the page lock we need to be careful to
- * copy it into a local to avoid races (it could change at any time).
- *
  * We pass down the cache-hot hint to the page freeing code.  Even if the
  * mapping is large, it is probably the case that the final pages are the most
  * recently touched, and freeing happens in ascending file offset order.
@@ -210,10 +207,10 @@ void truncate_inode_pages_range(struct address_space *mapping,
 				loff_t lstart, loff_t lend)
 {
 	const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT;
-	pgoff_t end;
 	const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
 	struct pagevec pvec;
-	pgoff_t next;
+	pgoff_t index;
+	pgoff_t end;
 	int i;
 
 	cleancache_flush_inode(mapping);
@@ -224,24 +221,21 @@ void truncate_inode_pages_range(struct address_space *mapping,
 	end = (lend >> PAGE_CACHE_SHIFT);
 
 	pagevec_init(&pvec, 0);
-	next = start;
-	while (next <= end &&
-	       pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+	index = start;
+	while (index <= end && pagevec_lookup(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
-			pgoff_t page_index = page->index;
 
-			if (page_index > end) {
-				next = page_index;
+			/* We rely upon deletion not changing page->index */
+			index = page->index;
+			if (index > end)
 				break;
-			}
 
-			if (page_index > next)
-				next = page_index;
-			next++;
 			if (!trylock_page(page))
 				continue;
+			WARN_ON(page->index != index);
 			if (PageWriteback(page)) {
 				unlock_page(page);
 				continue;
@@ -252,6 +246,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
+		index++;
 	}
 
 	if (partial) {
@@ -264,16 +259,17 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		}
 	}
 
-	next = start;
+	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
-			if (next == start)
+		if (!pagevec_lookup(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+			if (index == start)
 				break;
-			next = start;
+			index = start;
 			continue;
 		}
-		if (pvec.pages[0]->index > end) {
+		if (index == start && pvec.pages[0]->index > end) {
 			pagevec_release(&pvec);
 			break;
 		}
@@ -281,18 +277,20 @@ void truncate_inode_pages_range(struct address_space *mapping,
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
-			if (page->index > end)
+			/* We rely upon deletion not changing page->index */
+			index = page->index;
+			if (index > end)
 				break;
+
 			lock_page(page);
+			WARN_ON(page->index != index);
 			wait_on_page_writeback(page);
 			truncate_inode_page(mapping, page);
-			if (page->index > next)
-				next = page->index;
-			next++;
 			unlock_page(page);
 		}
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
+		index++;
 	}
 	cleancache_flush_inode(mapping);
 }
@@ -333,35 +331,26 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t end)
 {
 	struct pagevec pvec;
-	pgoff_t next = start;
+	pgoff_t index = start;
 	unsigned long ret;
 	unsigned long count = 0;
 	int i;
 
 	pagevec_init(&pvec, 0);
-	while (next <= end &&
-			pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+	while (index <= end && pagevec_lookup(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
-			pgoff_t index;
-			int lock_failed;
-
-			lock_failed = !trylock_page(page);
 
-			/*
-			 * We really shouldn't be looking at the ->index of an
-			 * unlocked page.  But we're not allowed to lock these
-			 * pages.  So we rely upon nobody altering the ->index
-			 * of this (pinned-by-us) page.
-			 */
+			/* We rely upon deletion not changing page->index */
 			index = page->index;
-			if (index > next)
-				next = index;
-			next++;
-			if (lock_failed)
-				continue;
+			if (index > end)
+				break;
 
+			if (!trylock_page(page))
+				continue;
+			WARN_ON(page->index != index);
 			ret = invalidate_inode_page(page);
 			unlock_page(page);
 			/*
@@ -371,12 +360,11 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			if (!ret)
 				deactivate_page(page);
 			count += ret;
-			if (next > end)
-				break;
 		}
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
+		index++;
 	}
 	return count;
 }
@@ -442,37 +430,32 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 				  pgoff_t start, pgoff_t end)
 {
 	struct pagevec pvec;
-	pgoff_t next;
+	pgoff_t index;
 	int i;
 	int ret = 0;
 	int ret2 = 0;
 	int did_range_unmap = 0;
-	int wrapped = 0;
 
 	cleancache_flush_inode(mapping);
 	pagevec_init(&pvec, 0);
-	next = start;
-	while (next <= end && !wrapped &&
-		pagevec_lookup(&pvec, mapping, next,
-			min(end - next, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
+	index = start;
+	while (index <= end && pagevec_lookup(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
 		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
-			pgoff_t page_index;
+
+			/* We rely upon deletion not changing page->index */
+			index = page->index;
+			if (index > end)
+				break;
 
 			lock_page(page);
+			WARN_ON(page->index != index);
 			if (page->mapping != mapping) {
 				unlock_page(page);
 				continue;
 			}
-			page_index = page->index;
-			next = page_index + 1;
-			if (next == 0)
-				wrapped = 1;
-			if (page_index > end) {
-				unlock_page(page);
-				break;
-			}
 			wait_on_page_writeback(page);
 			if (page_mapped(page)) {
 				if (!did_range_unmap) {
@@ -480,9 +463,9 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 					 * Zap the rest of the file in one hit.
 					 */
 					unmap_mapping_range(mapping,
-					   (loff_t)page_index<<PAGE_CACHE_SHIFT,
-					   (loff_t)(end - page_index + 1)
-							<< PAGE_CACHE_SHIFT,
+					   (loff_t)index << PAGE_CACHE_SHIFT,
+					   (loff_t)(1 + end - index)
+							 << PAGE_CACHE_SHIFT,
 					    0);
 					did_range_unmap = 1;
 				} else {
@@ -490,8 +473,8 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 					 * Just zap this page
 					 */
 					unmap_mapping_range(mapping,
-					  (loff_t)page_index<<PAGE_CACHE_SHIFT,
-					  PAGE_CACHE_SIZE, 0);
+					   (loff_t)index << PAGE_CACHE_SHIFT,
+					   PAGE_CACHE_SIZE, 0);
 				}
 			}
 			BUG_ON(page_mapped(page));
@@ -507,6 +490,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 		pagevec_release(&pvec);
 		mem_cgroup_uncharge_end();
 		cond_resched();
+		index++;
 	}
 	cleancache_flush_inode(mapping);
 	return ret;
@@ -531,8 +515,8 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
 /**
  * truncate_pagecache - unmap and remove pagecache that has been truncated
  * @inode: inode
- * @old: old file offset
- * @new: new file offset
+ * @oldsize: old file size
+ * @newsize: new file size
  *
  * inode's new i_size must already be written before truncate_pagecache
  * is called.
@@ -544,9 +528,10 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
  * situations such as writepage being called for a page that has already
  * had its underlying blocks deallocated.
  */
-void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
+void truncate_pagecache(struct inode *inode, loff_t oldsize, loff_t newsize)
 {
 	struct address_space *mapping = inode->i_mapping;
+	loff_t holebegin = round_up(newsize, PAGE_SIZE);
 
 	/*
 	 * unmap_mapping_range is called twice, first simply for
@@ -557,9 +542,9 @@ void truncate_pagecache(struct inode *inode, loff_t old, loff_t new)
 	 * truncate_inode_pages finishes, hence the second
 	 * unmap_mapping_range call must be made for correctness.
 	 */
-	unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
-	truncate_inode_pages(mapping, new);
-	unmap_mapping_range(mapping, new + PAGE_SIZE - 1, 0, 1);
+	unmap_mapping_range(mapping, holebegin, 0, 1);
+	truncate_inode_pages(mapping, newsize);
+	unmap_mapping_range(mapping, holebegin, 0, 1);
 }
 EXPORT_SYMBOL(truncate_pagecache);
 
@@ -589,29 +574,31 @@ EXPORT_SYMBOL(truncate_setsize);
 /**
  * vmtruncate - unmap mappings "freed" by truncate() syscall
  * @inode: inode of the file used
- * @offset: file offset to start truncating
+ * @newsize: file offset to start truncating
  *
  * This function is deprecated and truncate_setsize or truncate_pagecache
  * should be used instead, together with filesystem specific block truncation.
  */
-int vmtruncate(struct inode *inode, loff_t offset)
+int vmtruncate(struct inode *inode, loff_t newsize)
 {
 	int error;
 
-	error = inode_newsize_ok(inode, offset);
+	error = inode_newsize_ok(inode, newsize);
 	if (error)
 		return error;
 
-	truncate_setsize(inode, offset);
+	truncate_setsize(inode, newsize);
 	if (inode->i_op->truncate)
 		inode->i_op->truncate(inode);
 	return 0;
 }
 EXPORT_SYMBOL(vmtruncate);
 
-int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
+int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend)
 {
 	struct address_space *mapping = inode->i_mapping;
+	loff_t holebegin = round_up(lstart, PAGE_SIZE);
+	loff_t holelen = 1 + lend - holebegin;
 
 	/*
 	 * If the underlying filesystem is not going to provide
@@ -623,10 +610,10 @@ int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
 
 	mutex_lock(&inode->i_mutex);
 	inode_dio_wait(inode);
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	inode->i_op->truncate_range(inode, offset, end);
+	unmap_mapping_range(mapping, holebegin, holelen, 1);
+	inode->i_op->truncate_range(inode, lstart, lend);
 	/* unmap again to remove racily COWed private pages */
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
+	unmap_mapping_range(mapping, holebegin, holelen, 1);
 	mutex_unlock(&inode->i_mutex);
 
 	return 0;