1 files changed, 561 insertions, 116 deletions

diff --git a/mm/truncate.c b/mm/truncate.c
index 29c18f68dc3..eda24730716 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -3,91 +3,227 @@
  *
  * Copyright (C) 2002, Linus Torvalds
  *
- * 10Sep2002	akpm@zip.com.au
+ * 10Sep2002	Andrew Morton
  *		Initial version.
  */
 
 #include <linux/kernel.h>
+#include <linux/backing-dev.h>
+#include <linux/gfp.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/export.h>
 #include <linux/pagemap.h>
+#include <linux/highmem.h>
 #include <linux/pagevec.h>
+#include <linux/task_io_accounting_ops.h>
 #include <linux/buffer_head.h>	/* grr. try_to_release_page,
 				   do_invalidatepage */
+#include <linux/cleancache.h>
+#include "internal.h"
 
+static void clear_exceptional_entry(struct address_space *mapping,
+				    pgoff_t index, void *entry)
+{
+	struct radix_tree_node *node;
+	void **slot;
+
+	/* Handled by shmem itself */
+	if (shmem_mapping(mapping))
+		return;
+
+	spin_lock_irq(&mapping->tree_lock);
+	/*
+	 * Regular page slots are stabilized by the page lock even
+	 * without the tree itself locked.  These unlocked entries
+	 * need verification under the tree lock.
+	 */
+	if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot))
+		goto unlock;
+	if (*slot != entry)
+		goto unlock;
+	radix_tree_replace_slot(slot, NULL);
+	mapping->nrshadows--;
+	if (!node)
+		goto unlock;
+	workingset_node_shadows_dec(node);
+	/*
+	 * Don't track node without shadow entries.
+	 *
+	 * Avoid acquiring the list_lru lock if already untracked.
+	 * The list_empty() test is safe as node->private_list is
+	 * protected by mapping->tree_lock.
+	 */
+	if (!workingset_node_shadows(node) &&
+	    !list_empty(&node->private_list))
+		list_lru_del(&workingset_shadow_nodes, &node->private_list);
+	__radix_tree_delete_node(&mapping->page_tree, node);
+unlock:
+	spin_unlock_irq(&mapping->tree_lock);
+}
 
-static inline void truncate_partial_page(struct page *page, unsigned partial)
+/**
+ * do_invalidatepage - invalidate part or all of a page
+ * @page: the page which is affected
+ * @offset: start of the range to invalidate
+ * @length: length of the range to invalidate
+ *
+ * do_invalidatepage() is called when all or part of the page has become
+ * invalidated by a truncate operation.
+ *
+ * do_invalidatepage() does not have to release all buffers, but it must
+ * ensure that no dirty buffer is left outside @offset and that no I/O
+ * is underway against any of the blocks which are outside the truncation
+ * point.  Because the caller is about to free (and possibly reuse) those
+ * blocks on-disk.
+ */
+void do_invalidatepage(struct page *page, unsigned int offset,
+		       unsigned int length)
 {
-	memclear_highpage_flush(page, partial, PAGE_CACHE_SIZE-partial);
-	if (PagePrivate(page))
-		do_invalidatepage(page, partial);
+	void (*invalidatepage)(struct page *, unsigned int, unsigned int);
+
+	invalidatepage = page->mapping->a_ops->invalidatepage;
+#ifdef CONFIG_BLOCK
+	if (!invalidatepage)
+		invalidatepage = block_invalidatepage;
+#endif
+	if (invalidatepage)
+		(*invalidatepage)(page, offset, length);
+}
+
+/*
+ * This cancels just the dirty bit on the kernel page itself, it
+ * does NOT actually remove dirty bits on any mmap's that may be
+ * around. It also leaves the page tagged dirty, so any sync
+ * activity will still find it on the dirty lists, and in particular,
+ * clear_page_dirty_for_io() will still look at the dirty bits in
+ * the VM.
+ *
+ * Doing this should *normally* only ever be done when a page
+ * is truncated, and is not actually mapped anywhere at all. However,
+ * fs/buffer.c does this when it notices that somebody has cleaned
+ * out all the buffers on a page without actually doing it through
+ * the VM. Can you say "ext3 is horribly ugly"? Tought you could.
+ */
+void cancel_dirty_page(struct page *page, unsigned int account_size)
+{
+	if (TestClearPageDirty(page)) {
+		struct address_space *mapping = page->mapping;
+		if (mapping && mapping_cap_account_dirty(mapping)) {
+			dec_zone_page_state(page, NR_FILE_DIRTY);
+			dec_bdi_stat(mapping->backing_dev_info,
+					BDI_RECLAIMABLE);
+			if (account_size)
+				task_io_account_cancelled_write(account_size);
+		}
+	}
 }
+EXPORT_SYMBOL(cancel_dirty_page);
 
 /*
  * If truncate cannot remove the fs-private metadata from the page, the page
- * becomes anonymous.  It will be left on the LRU and may even be mapped into
- * user pagetables if we're racing with filemap_nopage().
+ * becomes orphaned.  It will be left on the LRU and may even be mapped into
+ * user pagetables if we're racing with filemap_fault().
  *
  * We need to bale out if page->mapping is no longer equal to the original
  * mapping.  This happens a) when the VM reclaimed the page while we waited on
- * its lock, b) when a concurrent invalidate_inode_pages got there first and
+ * its lock, b) when a concurrent invalidate_mapping_pages got there first and
  * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space.
  */
-static void
+static int
 truncate_complete_page(struct address_space *mapping, struct page *page)
 {
 	if (page->mapping != mapping)
-		return;
+		return -EIO;
+
+	if (page_has_private(page))
+		do_invalidatepage(page, 0, PAGE_CACHE_SIZE);
 
-	if (PagePrivate(page))
-		do_invalidatepage(page, 0);
+	cancel_dirty_page(page, PAGE_CACHE_SIZE);
 
-	clear_page_dirty(page);
-	ClearPageUptodate(page);
 	ClearPageMappedToDisk(page);
-	remove_from_page_cache(page);
-	page_cache_release(page);	/* pagecache ref */
+	delete_from_page_cache(page);
+	return 0;
 }
 
 /*
- * This is for invalidate_inode_pages().  That function can be called at
+ * This is for invalidate_mapping_pages().  That function can be called at
  * any time, and is not supposed to throw away dirty pages.  But pages can
- * be marked dirty at any time too.  So we re-check the dirtiness inside
- * ->tree_lock.  That provides exclusion against the __set_page_dirty
- * functions.
+ * be marked dirty at any time too, so use remove_mapping which safely
+ * discards clean, unused pages.
  *
  * Returns non-zero if the page was successfully invalidated.
  */
 static int
 invalidate_complete_page(struct address_space *mapping, struct page *page)
 {
+	int ret;
+
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, 0))
+	if (page_has_private(page) && !try_to_release_page(page, 0))
 		return 0;
 
-	write_lock_irq(&mapping->tree_lock);
-	if (PageDirty(page)) {
-		write_unlock_irq(&mapping->tree_lock);
-		return 0;
+	ret = remove_mapping(mapping, page);
+
+	return ret;
+}
+
+int truncate_inode_page(struct address_space *mapping, struct page *page)
+{
+	if (page_mapped(page)) {
+		unmap_mapping_range(mapping,
+				   (loff_t)page->index << PAGE_CACHE_SHIFT,
+				   PAGE_CACHE_SIZE, 0);
 	}
+	return truncate_complete_page(mapping, page);
+}
 
-	BUG_ON(PagePrivate(page));
-	__remove_from_page_cache(page);
-	write_unlock_irq(&mapping->tree_lock);
-	ClearPageUptodate(page);
-	page_cache_release(page);	/* pagecache ref */
-	return 1;
+/*
+ * Used to get rid of pages on hardware memory corruption.
+ */
+int generic_error_remove_page(struct address_space *mapping, struct page *page)
+{
+	if (!mapping)
+		return -EINVAL;
+	/*
+	 * Only punch for normal data pages for now.
+	 * Handling other types like directories would need more auditing.
+	 */
+	if (!S_ISREG(mapping->host->i_mode))
+		return -EIO;
+	return truncate_inode_page(mapping, page);
+}
+EXPORT_SYMBOL(generic_error_remove_page);
+
+/*
+ * Safely invalidate one page from its pagecache mapping.
+ * It only drops clean, unused pages. The page must be locked.
+ *
+ * Returns 1 if the page is successfully invalidated, otherwise 0.
+ */
+int invalidate_inode_page(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	if (!mapping)
+		return 0;
+	if (PageDirty(page) || PageWriteback(page))
+		return 0;
+	if (page_mapped(page))
+		return 0;
+	return invalidate_complete_page(mapping, page);
 }
 
 /**
- * truncate_inode_pages - truncate *all* the pages from an offset
+ * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets
  * @mapping: mapping to truncate
  * @lstart: offset from which to truncate
+ * @lend: offset to which to truncate (inclusive)
  *
- * Truncate the page cache at a set offset, removing the pages that are beyond
- * that offset (and zeroing out partial pages).
+ * Truncate the page cache, removing the pages that are between
+ * specified offsets (and zeroing out partial pages
+ * if lstart or lend + 1 is not page aligned).
  *
  * Truncate takes two passes - the first pass is nonblocking.  It will not
  * block on page locks and it will not block on writeback.  The second pass
@@ -95,86 +231,242 @@ invalidate_complete_page(struct address_space *mapping, 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.
  *
- * Called under (and serialised by) inode->i_sem.
+ * Note that since ->invalidatepage() accepts range to invalidate
+ * truncate_inode_pages_range is able to handle cases where lend + 1 is not
+ * page aligned properly.
  */
-void truncate_inode_pages(struct address_space *mapping, loff_t lstart)
+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;
-	const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
-	struct pagevec pvec;
-	pgoff_t next;
-	int i;
+	pgoff_t		start;		/* inclusive */
+	pgoff_t		end;		/* exclusive */
+	unsigned int	partial_start;	/* inclusive */
+	unsigned int	partial_end;	/* exclusive */
+	struct pagevec	pvec;
+	pgoff_t		indices[PAGEVEC_SIZE];
+	pgoff_t		index;
+	int		i;
 
-	if (mapping->nrpages == 0)
+	cleancache_invalidate_inode(mapping);
+	if (mapping->nrpages == 0 && mapping->nrshadows == 0)
 		return;
 
+	/* Offsets within partial pages */
+	partial_start = lstart & (PAGE_CACHE_SIZE - 1);
+	partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
+
+	/*
+	 * 'start' and 'end' always covers the range of pages to be fully
+	 * truncated. Partial pages are covered with 'partial_start' at the
+	 * start of the range and 'partial_end' at the end of the range.
+	 * Note that 'end' is exclusive while 'lend' is inclusive.
+	 */
+	start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	if (lend == -1)
+		/*
+		 * lend == -1 indicates end-of-file so we have to set 'end'
+		 * to the highest possible pgoff_t and since the type is
+		 * unsigned we're using -1.
+		 */
+		end = -1;
+	else
+		end = (lend + 1) >> PAGE_CACHE_SHIFT;
+
 	pagevec_init(&pvec, 0);
-	next = start;
-	while (pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+	index = start;
+	while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE),
+			indices)) {
+		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 > next)
-				next = page_index;
-			next++;
-			if (TestSetPageLocked(page))
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index >= end)
+				break;
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
+			if (!trylock_page(page))
 				continue;
+			WARN_ON(page->index != index);
 			if (PageWriteback(page)) {
 				unlock_page(page);
 				continue;
 			}
-			truncate_complete_page(mapping, page);
+			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
+		mem_cgroup_uncharge_end();
 		cond_resched();
+		index++;
 	}
 
-	if (partial) {
+	if (partial_start) {
 		struct page *page = find_lock_page(mapping, start - 1);
 		if (page) {
+			unsigned int top = PAGE_CACHE_SIZE;
+			if (start > end) {
+				/* Truncation within a single page */
+				top = partial_end;
+				partial_end = 0;
+			}
 			wait_on_page_writeback(page);
-			truncate_partial_page(page, partial);
+			zero_user_segment(page, partial_start, top);
+			cleancache_invalidate_page(mapping, page);
+			if (page_has_private(page))
+				do_invalidatepage(page, partial_start,
+						  top - partial_start);
 			unlock_page(page);
 			page_cache_release(page);
 		}
 	}
+	if (partial_end) {
+		struct page *page = find_lock_page(mapping, end);
+		if (page) {
+			wait_on_page_writeback(page);
+			zero_user_segment(page, 0, partial_end);
+			cleancache_invalidate_page(mapping, page);
+			if (page_has_private(page))
+				do_invalidatepage(page, 0,
+						  partial_end);
+			unlock_page(page);
+			page_cache_release(page);
+		}
+	}
+	/*
+	 * If the truncation happened within a single page no pages
+	 * will be released, just zeroed, so we can bail out now.
+	 */
+	if (start >= end)
+		return;
 
-	next = start;
+	index = start;
 	for ( ; ; ) {
 		cond_resched();
-		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
-			if (next == start)
+		if (!pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) {
+			/* If all gone from start onwards, we're done */
+			if (index == start)
 				break;
-			next = start;
+			/* Otherwise restart to make sure all gone */
+			index = start;
 			continue;
 		}
+		if (index == start && indices[0] >= end) {
+			/* All gone out of hole to be punched, we're done */
+			pagevec_remove_exceptionals(&pvec);
+			pagevec_release(&pvec);
+			break;
+		}
+		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index >= end) {
+				/* Restart punch to make sure all gone */
+				index = start - 1;
+				break;
+			}
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
+
 			lock_page(page);
+			WARN_ON(page->index != index);
 			wait_on_page_writeback(page);
-			if (page->index > next)
-				next = page->index;
-			next++;
-			truncate_complete_page(mapping, page);
+			truncate_inode_page(mapping, page);
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
+		mem_cgroup_uncharge_end();
+		index++;
 	}
+	cleancache_invalidate_inode(mapping);
 }
+EXPORT_SYMBOL(truncate_inode_pages_range);
 
+/**
+ * truncate_inode_pages - truncate *all* the pages from an offset
+ * @mapping: mapping to truncate
+ * @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)
+{
+	truncate_inode_pages_range(mapping, lstart, (loff_t)-1);
+}
 EXPORT_SYMBOL(truncate_inode_pages);
 
 /**
+ * truncate_inode_pages_final - truncate *all* pages before inode dies
+ * @mapping: mapping to truncate
+ *
+ * Called under (and serialized by) inode->i_mutex.
+ *
+ * Filesystems have to use this in the .evict_inode path to inform the
+ * VM that this is the final truncate and the inode is going away.
+ */
+void truncate_inode_pages_final(struct address_space *mapping)
+{
+	unsigned long nrshadows;
+	unsigned long nrpages;
+
+	/*
+	 * Page reclaim can not participate in regular inode lifetime
+	 * management (can't call iput()) and thus can race with the
+	 * inode teardown.  Tell it when the address space is exiting,
+	 * so that it does not install eviction information after the
+	 * final truncate has begun.
+	 */
+	mapping_set_exiting(mapping);
+
+	/*
+	 * When reclaim installs eviction entries, it increases
+	 * nrshadows first, then decreases nrpages.  Make sure we see
+	 * this in the right order or we might miss an entry.
+	 */
+	nrpages = mapping->nrpages;
+	smp_rmb();
+	nrshadows = mapping->nrshadows;
+
+	if (nrpages || nrshadows) {
+		/*
+		 * As truncation uses a lockless tree lookup, cycle
+		 * the tree lock to make sure any ongoing tree
+		 * modification that does not see AS_EXITING is
+		 * completed before starting the final truncate.
+		 */
+		spin_lock_irq(&mapping->tree_lock);
+		spin_unlock_irq(&mapping->tree_lock);
+
+		truncate_inode_pages(mapping, 0);
+	}
+}
+EXPORT_SYMBOL(truncate_inode_pages_final);
+
+/**
  * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode
  * @mapping: the address_space which holds the pages to invalidate
  * @start: the offset 'from' which to invalidate
@@ -188,48 +480,99 @@ EXPORT_SYMBOL(truncate_inode_pages);
  * pagetables.
  */
 unsigned long invalidate_mapping_pages(struct address_space *mapping,
-				pgoff_t start, pgoff_t end)
+		pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	struct pagevec pvec;
-	pgoff_t next = start;
-	unsigned long ret = 0;
+	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_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
+		mem_cgroup_uncharge_start();
 		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
 
-			if (TestSetPageLocked(page)) {
-				next++;
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index > end)
+				break;
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
 				continue;
 			}
-			if (page->index > next)
-				next = page->index;
-			next++;
-			if (PageDirty(page) || PageWriteback(page))
-				goto unlock;
-			if (page_mapped(page))
-				goto unlock;
-			ret += invalidate_complete_page(mapping, page);
-unlock:
+
+			if (!trylock_page(page))
+				continue;
+			WARN_ON(page->index != index);
+			ret = invalidate_inode_page(page);
 			unlock_page(page);
-			if (next > end)
-				break;
+			/*
+			 * Invalidation is a hint that the page is no longer
+			 * of interest and try to speed up its reclaim.
+			 */
+			if (!ret)
+				deactivate_page(page);
+			count += ret;
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
+		mem_cgroup_uncharge_end();
 		cond_resched();
+		index++;
 	}
-	return ret;
+	return count;
 }
+EXPORT_SYMBOL(invalidate_mapping_pages);
 
-unsigned long invalidate_inode_pages(struct address_space *mapping)
+/*
+ * This is like invalidate_complete_page(), except it ignores the page's
+ * refcount.  We do this because invalidate_inode_pages2() needs stronger
+ * invalidation guarantees, and cannot afford to leave pages behind because
+ * shrink_page_list() has a temp ref on them, or because they're transiently
+ * sitting in the lru_cache_add() pagevecs.
+ */
+static int
+invalidate_complete_page2(struct address_space *mapping, struct page *page)
 {
-	return invalidate_mapping_pages(mapping, 0, ~0UL);
+	if (page->mapping != mapping)
+		return 0;
+
+	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
+		return 0;
+
+	spin_lock_irq(&mapping->tree_lock);
+	if (PageDirty(page))
+		goto failed;
+
+	BUG_ON(page_has_private(page));
+	__delete_from_page_cache(page, NULL);
+	spin_unlock_irq(&mapping->tree_lock);
+	mem_cgroup_uncharge_cache_page(page);
+
+	if (mapping->a_ops->freepage)
+		mapping->a_ops->freepage(page);
+
+	page_cache_release(page);	/* pagecache ref */
+	return 1;
+failed:
+	spin_unlock_irq(&mapping->tree_lock);
+	return 0;
 }
 
-EXPORT_SYMBOL(invalidate_inode_pages);
+static int do_launder_page(struct address_space *mapping, struct page *page)
+{
+	if (!PageDirty(page))
+		return 0;
+	if (page->mapping != mapping || mapping->a_ops->launder_page == NULL)
+		return 0;
+	return mapping->a_ops->launder_page(page);
+}
 
 /**
  * invalidate_inode_pages2_range - remove range of pages from an address_space
@@ -240,51 +583,55 @@ EXPORT_SYMBOL(invalidate_inode_pages);
  * Any pages which are found to be mapped into pagetables are unmapped prior to
  * invalidation.
  *
- * Returns -EIO if any pages could not be invalidated.
+ * Returns -EBUSY if any pages could not be invalidated.
  */
 int invalidate_inode_pages2_range(struct address_space *mapping,
 				  pgoff_t start, pgoff_t end)
 {
+	pgoff_t indices[PAGEVEC_SIZE];
 	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_invalidate_inode(mapping);
 	pagevec_init(&pvec, 0);
-	next = start;
-	while (next <= end && !ret && !wrapped &&
-		pagevec_lookup(&pvec, mapping, next,
-			min(end - next, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) {
-		for (i = 0; !ret && i < pagevec_count(&pvec); i++) {
+	index = start;
+	while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
+			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+			indices)) {
+		mem_cgroup_uncharge_start();
+		for (i = 0; i < pagevec_count(&pvec); i++) {
 			struct page *page = pvec.pages[i];
-			pgoff_t page_index;
-			int was_dirty;
+
+			/* We rely upon deletion not changing page->index */
+			index = indices[i];
+			if (index > end)
+				break;
+
+			if (radix_tree_exceptional_entry(page)) {
+				clear_exceptional_entry(mapping, index, page);
+				continue;
+			}
 
 			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);
-			while (page_mapped(page)) {
+			if (page_mapped(page)) {
 				if (!did_range_unmap) {
 					/*
 					 * Zap the rest of the file in one hit.
 					 */
 					unmap_mapping_range(mapping,
-					    page_index << PAGE_CACHE_SHIFT,
-					    (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 {
@@ -292,21 +639,27 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 					 * Just zap this page
 					 */
 					unmap_mapping_range(mapping,
-					  page_index << PAGE_CACHE_SHIFT,
-					  PAGE_CACHE_SIZE, 0);
+					   (loff_t)index << PAGE_CACHE_SHIFT,
+					   PAGE_CACHE_SIZE, 0);
 				}
 			}
-			was_dirty = test_clear_page_dirty(page);
-			if (!invalidate_complete_page(mapping, page)) {
-				if (was_dirty)
-					set_page_dirty(page);
-				ret = -EIO;
+			BUG_ON(page_mapped(page));
+			ret2 = do_launder_page(mapping, page);
+			if (ret2 == 0) {
+				if (!invalidate_complete_page2(mapping, page))
+					ret2 = -EBUSY;
 			}
+			if (ret2 < 0)
+				ret = ret2;
 			unlock_page(page);
 		}
+		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
+		mem_cgroup_uncharge_end();
 		cond_resched();
+		index++;
 	}
+	cleancache_invalidate_inode(mapping);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
@@ -318,10 +671,102 @@ EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range);
  * Any pages which are found to be mapped into pagetables are unmapped prior to
  * invalidation.
  *
- * Returns -EIO if any pages could not be invalidated.
+ * Returns -EBUSY if any pages could not be invalidated.
  */
 int invalidate_inode_pages2(struct address_space *mapping)
 {
 	return invalidate_inode_pages2_range(mapping, 0, -1);
 }
 EXPORT_SYMBOL_GPL(invalidate_inode_pages2);
+
+/**
+ * truncate_pagecache - unmap and remove pagecache that has been truncated
+ * @inode: inode
+ * @newsize: new file size
+ *
+ * inode's new i_size must already be written before truncate_pagecache
+ * is called.
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * 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 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
+	 * efficiency so that truncate_inode_pages does fewer
+	 * single-page unmaps.  However after this first call, and
+	 * before truncate_inode_pages finishes, it is possible for
+	 * private pages to be COWed, which remain after
+	 * truncate_inode_pages finishes, hence the second
+	 * unmap_mapping_range call must be made for correctness.
+	 */
+	unmap_mapping_range(mapping, holebegin, 0, 1);
+	truncate_inode_pages(mapping, newsize);
+	unmap_mapping_range(mapping, holebegin, 0, 1);
+}
+EXPORT_SYMBOL(truncate_pagecache);
+
+/**
+ * truncate_setsize - update inode and pagecache for a new file size
+ * @inode: inode
+ * @newsize: new file size
+ *
+ * truncate_setsize updates i_size and performs pagecache truncation (if
+ * necessary) to @newsize. It will be typically be called from the filesystem's
+ * setattr function when ATTR_SIZE is passed in.
+ *
+ * Must be called with inode_mutex held and before all filesystem specific
+ * block truncation has been performed.
+ */
+void truncate_setsize(struct inode *inode, loff_t newsize)
+{
+	i_size_write(inode, newsize);
+	truncate_pagecache(inode, newsize);
+}
+EXPORT_SYMBOL(truncate_setsize);
+
+/**
+ * truncate_pagecache_range - unmap and remove pagecache that is hole-punched
+ * @inode: inode
+ * @lstart: offset of beginning of hole
+ * @lend: offset of last byte of hole
+ *
+ * This function should typically be called before the filesystem
+ * releases resources associated with the freed range (eg. deallocates
+ * blocks). This way, pagecache will always stay logically coherent
+ * with on-disk format, and the filesystem would not have to deal with
+ * situations such as writepage being called for a page that has already
+ * had its underlying blocks deallocated.
+ */
+void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+	struct address_space *mapping = inode->i_mapping;
+	loff_t unmap_start = round_up(lstart, PAGE_SIZE);
+	loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
+	/*
+	 * This rounding is currently just for example: unmap_mapping_range
+	 * expands its hole outwards, whereas we want it to contract the hole
+	 * inwards.  However, existing callers of truncate_pagecache_range are
+	 * doing their own page rounding first.  Note that unmap_mapping_range
+	 * allows holelen 0 for all, and we allow lend -1 for end of file.
+	 */
+
+	/*
+	 * Unlike in truncate_pagecache, unmap_mapping_range is called only
+	 * once (before truncating pagecache), and without "even_cows" flag:
+	 * hole-punching should not remove private COWed pages from the hole.
+	 */
+	if ((u64)unmap_end > (u64)unmap_start)
+		unmap_mapping_range(mapping, unmap_start,
+				    1 + unmap_end - unmap_start, 0);
+	truncate_inode_pages_range(mapping, lstart, lend);
+}
+EXPORT_SYMBOL(truncate_pagecache_range);