Merge remote-tracking branch 'fixes/fixes'

9 files changed, 167 insertions, 153 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index a8251a8d3457..cfac89d95ec1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -131,6 +131,7 @@ 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))
@@ -486,6 +487,7 @@ 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);
@@ -1795,7 +1797,7 @@ 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)
 {
@@ -1826,7 +1828,7 @@ 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)
 
@@ -1866,7 +1868,7 @@ 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.
@@ -1878,7 +1880,7 @@ 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));
@@ -1926,7 +1928,7 @@ 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.
@@ -1935,7 +1937,7 @@ 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/memcontrol.c b/mm/memcontrol.c
index cf7d027a8844..ddffc74cdebe 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -35,6 +35,7 @@
 #include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
+#include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index eac0ba561491..740c4f52059c 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -391,10 +391,11 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 	struct task_struct *tsk;
 	struct anon_vma *av;
 
-	read_lock(&tasklist_lock);
 	av = page_lock_anon_vma(page);
 	if (av == NULL)	/* Not actually mapped anymore */
-		goto out;
+		return;
+
+	read_lock(&tasklist_lock);
 	for_each_process (tsk) {
 		struct anon_vma_chain *vmac;
 
@@ -408,9 +409,8 @@ static void collect_procs_anon(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	page_unlock_anon_vma(av);
-out:
 	read_unlock(&tasklist_lock);
+	page_unlock_anon_vma(av);
 }
 
 /*
@@ -424,17 +424,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 	struct prio_tree_iter iter;
 	struct address_space *mapping = page->mapping;
 
-	/*
-	 * A note on the locking order between the two locks.
-	 * We don't rely on this particular order.
-	 * If you have some other code that needs a different order
-	 * feel free to switch them around. Or add a reverse link
-	 * from mm_struct to task_struct, then this could be all
-	 * done without taking tasklist_lock and looping over all tasks.
-	 */
-
-	read_lock(&tasklist_lock);
 	mutex_lock(&mapping->i_mmap_mutex);
+	read_lock(&tasklist_lock);
 	for_each_process(tsk) {
 		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 
@@ -454,8 +445,8 @@ static void collect_procs_file(struct page *page, struct list_head *to_kill,
 				add_to_kill(tsk, page, vma, to_kill, tkc);
 		}
 	}
-	mutex_unlock(&mapping->i_mmap_mutex);
 	read_unlock(&tasklist_lock);
+	mutex_unlock(&mapping->i_mmap_mutex);
 }
 
 /*
diff --git a/mm/memory.c b/mm/memory.c
index 87d935333f0d..40b7531ee8ba 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2798,30 +2798,6 @@ void unmap_mapping_range(struct address_space *mapping,
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
-int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end)
-{
-	struct address_space *mapping = inode->i_mapping;
-
-	/*
-	 * If the underlying filesystem is not going to provide
-	 * a way to truncate a range of blocks (punch a hole) -
-	 * we should return failure right now.
-	 */
-	if (!inode->i_op->truncate_range)
-		return -ENOSYS;
-
-	mutex_lock(&inode->i_mutex);
-	down_write(&inode->i_alloc_sem);
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	truncate_inode_pages_range(mapping, offset, end);
-	unmap_mapping_range(mapping, offset, (end - offset), 1);
-	inode->i_op->truncate_range(inode, offset, end);
-	up_write(&inode->i_alloc_sem);
-	mutex_unlock(&inode->i_mutex);
-
-	return 0;
-}
-
 /*
  * We enter with non-exclusive mmap_sem (to exclude vma changes,
  * but allow concurrent faults), and pte mapped but not yet locked.
diff --git a/mm/nommu.c b/mm/nommu.c
index 1fd0c51b10a6..829848aba51c 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1817,6 +1817,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long from,
 		unsigned long to, unsigned long size, pgprot_t prot)
 {
 	vma->vm_start = vma->vm_pgoff << PAGE_SHIFT;
+	vma->vm_end = vma->vm_start + size;
 	return 0;
 }
 EXPORT_SYMBOL(remap_pfn_range);
diff --git a/mm/rmap.c b/mm/rmap.c
index 27dfd3b82b0f..23295f65ae43 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -38,9 +38,8 @@
  *                           in arch-dependent flush_dcache_mmap_lock,
  *                           within inode_wb_list_lock in __sync_single_inode)
  *
- * (code doesn't rely on that order so it could be switched around)
- * ->tasklist_lock
- *   anon_vma->mutex      (memory_failure, collect_procs_anon)
+ * anon_vma->mutex,mapping->i_mutex      (memory_failure, collect_procs_anon)
+ *   ->tasklist_lock
  *     pte map lock
  */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index d221a1cfd7b1..c1db11cf220d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -241,9 +241,7 @@ 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);
 	}
 }
 
@@ -432,9 +430,7 @@ 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);
@@ -539,7 +535,7 @@ static void shmem_free_pages(struct list_head *next)
 	} while (next);
 }
 
-static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 {
 	struct shmem_inode_info *info = SHMEM_I(inode);
 	unsigned long idx;
@@ -562,6 +558,8 @@ static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
 	spinlock_t *punch_lock;
 	unsigned long upper_limit;
 
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+
 	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
 	idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	if (idx >= info->next_index)
@@ -738,16 +736,8 @@ done2:
 		 * lowered next_index.  Also, though shmem_getpage checks
 		 * i_size before adding to cache, no recheck after: so fix the
 		 * narrow window there too.
-		 *
-		 * Recalling truncate_inode_pages_range and unmap_mapping_range
-		 * every time for punch_hole (which never got a chance to clear
-		 * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive,
-		 * yet hardly ever necessary: try to optimize them out later.
 		 */
 		truncate_inode_pages_range(inode->i_mapping, start, end);
-		if (punch_hole)
-			unmap_mapping_range(inode->i_mapping, start,
-							end - start, 1);
 	}
 
 	spin_lock(&info->lock);
@@ -766,22 +756,23 @@ done2:
 		shmem_free_pages(pages_to_free.next);
 	}
 }
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
-static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
+static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = dentry->d_inode;
-	loff_t newsize = attr->ia_size;
 	int error;
 
 	error = inode_change_ok(inode, attr);
 	if (error)
 		return error;
 
-	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)
-					&& newsize != inode->i_size) {
+	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
+		loff_t oldsize = inode->i_size;
+		loff_t newsize = attr->ia_size;
 		struct page *page = NULL;
 
-		if (newsize < inode->i_size) {
+		if (newsize < oldsize) {
 			/*
 			 * If truncating down to a partial page, then
 			 * if that page is already allocated, hold it
@@ -810,12 +801,19 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
 				spin_unlock(&info->lock);
 			}
 		}
-
-		/* XXX(truncate): truncate_setsize should be called last */
-		truncate_setsize(inode, newsize);
+		if (newsize != oldsize) {
+			i_size_write(inode, newsize);
+			inode->i_ctime = inode->i_mtime = CURRENT_TIME;
+		}
+		if (newsize < oldsize) {
+			loff_t holebegin = round_up(newsize, PAGE_SIZE);
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+			shmem_truncate_range(inode, newsize, (loff_t)-1);
+			/* unmap again to remove racily COWed private pages */
+			unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
+		}
 		if (page)
 			page_cache_release(page);
-		shmem_truncate_range(inode, newsize, (loff_t)-1);
 	}
 
 	setattr_copy(inode, attr);
@@ -832,7 +830,6 @@ static void shmem_evict_inode(struct inode *inode)
 	struct shmem_xattr *xattr, *nxattr;
 
 	if (inode->i_mapping->a_ops == &shmem_aops) {
-		truncate_inode_pages(inode->i_mapping, 0);
 		shmem_unacct_size(info->flags, inode->i_size);
 		inode->i_size = 0;
 		shmem_truncate_range(inode, 0, (loff_t)-1);
@@ -1420,9 +1417,7 @@ 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;
 
@@ -1433,8 +1428,10 @@ repeat:
 				spin_unlock(&info->lock);
 				filepage = shmem_alloc_page(gfp, info, idx);
 				if (!filepage) {
+					spin_lock(&info->lock);
 					shmem_unacct_blocks(info->flags, 1);
 					shmem_free_blocks(inode, 1);
+					spin_unlock(&info->lock);
 					error = -ENOMEM;
 					goto failed;
 				}
@@ -1448,8 +1445,10 @@ repeat:
 					current->mm, GFP_KERNEL);
 				if (error) {
 					page_cache_release(filepage);
+					spin_lock(&info->lock);
 					shmem_unacct_blocks(info->flags, 1);
 					shmem_free_blocks(inode, 1);
+					spin_unlock(&info->lock);
 					filepage = NULL;
 					goto failed;
 				}
@@ -1479,10 +1478,10 @@ repeat:
 			 * be done automatically.
 			 */
 			if (ret) {
-				spin_unlock(&info->lock);
-				page_cache_release(filepage);
 				shmem_unacct_blocks(info->flags, 1);
 				shmem_free_blocks(inode, 1);
+				spin_unlock(&info->lock);
+				page_cache_release(filepage);
 				filepage = NULL;
 				if (error)
 					goto failed;
@@ -2706,7 +2705,7 @@ static const struct file_operations shmem_file_operations = {
 };
 
 static const struct inode_operations shmem_inode_operations = {
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.truncate_range	= shmem_truncate_range,
 #ifdef CONFIG_TMPFS_XATTR
 	.setxattr	= shmem_setxattr,
@@ -2739,7 +2738,7 @@ static const struct inode_operations shmem_dir_inode_operations = {
 	.removexattr	= shmem_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
@@ -2752,7 +2751,7 @@ static const struct inode_operations shmem_special_inode_operations = {
 	.removexattr	= shmem_removexattr,
 #endif
 #ifdef CONFIG_TMPFS_POSIX_ACL
-	.setattr	= shmem_notify_change,
+	.setattr	= shmem_setattr,
 	.check_acl	= generic_check_acl,
 #endif
 };
@@ -2908,6 +2907,12 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 	return 0;
 }
 
+void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+{
+	truncate_inode_pages_range(inode->i_mapping, start, end);
+}
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
+
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 /**
  * mem_cgroup_get_shmem_target - find a page or entry assigned to the shmem file
@@ -3028,3 +3033,26 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	vma->vm_flags |= VM_CAN_NONLINEAR;
 	return 0;
 }
+
+/**
+ * shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags.
+ * @mapping:	the page's address_space
+ * @index:	the page index
+ * @gfp:	the page allocator flags to use if allocating
+ *
+ * This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)",
+ * with any new page allocations done using the specified allocation flags.
+ * But read_cache_page_gfp() uses the ->readpage() method: which does not
+ * 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.
+ */
+struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
+					 pgoff_t index, gfp_t gfp)
+{
+	return read_cache_page_gfp(mapping, index, gfp);
+}
+EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index d537d29e9b7b..ff8dc1a18cb4 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -14,7 +14,7 @@
 #include <linux/vmalloc.h>
 #include <linux/pagemap.h>
 #include <linux/namei.h>
-#include <linux/shm.h>
+#include <linux/shmem_fs.h>
 #include <linux/blkdev.h>
 #include <linux/random.h>
 #include <linux/writeback.h>
diff --git a/mm/truncate.c b/mm/truncate.c
index 3a29a6180212..0f78f8461773 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);
 }
@@ -304,6 +302,11 @@ EXPORT_SYMBOL(truncate_inode_pages_range);
  * @lstart: offset from which to truncate
  *
  * Called under (and serialised by) inode->i_mutex.
+ *
+ * Note: When this function returns, there can be a page in the process of
+ * deletion (inside __delete_from_page_cache()) in the specified range.  Thus
+ * mapping->nrpages can be non-zero when this function returns even after
+ * truncation of the whole mapping.
  */
 void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
 {
@@ -328,35 +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);
 			/*
@@ -366,12 +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;
 }
@@ -437,37 +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) {
@@ -475,9 +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 {
@@ -485,8 +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));
@@ -502,6 +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;
@@ -526,8 +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.
@@ -539,9 +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
@@ -552,9 +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);
 
@@ -584,22 +574,48 @@ 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 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
+	 * a way to truncate a range of blocks (punch a hole) -
+	 * we should return failure right now.
+	 */
+	if (!inode->i_op->truncate_range)
+		return -ENOSYS;
+
+	mutex_lock(&inode->i_mutex);
+	down_write(&inode->i_alloc_sem);
+	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, holebegin, holelen, 1);
+	up_write(&inode->i_alloc_sem);
+	mutex_unlock(&inode->i_mutex);
+
+	return 0;
+}