Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

* 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (43 commits)
  ext4: fix a BUG in mb_mark_used during trim.
  ext4: unused variables cleanup in fs/ext4/extents.c
  ext4: remove redundant set_buffer_mapped() in ext4_da_get_block_prep()
  ext4: add more tracepoints and use dev_t in the trace buffer
  ext4: don't kfree uninitialized s_group_info members
  ext4: add missing space in printk's in __ext4_grp_locked_error()
  ext4: add FITRIM to compat_ioctl.
  ext4: handle errors in ext4_clear_blocks()
  ext4: unify the ext4_handle_release_buffer() api
  ext4: handle errors in ext4_rename
  jbd2: add COW fields to struct jbd2_journal_handle
  jbd2: add the b_cow_tid field to journal_head struct
  ext4: Initialize fsync transaction ids in ext4_new_inode()
  ext4: Use single thread to perform DIO unwritten convertion
  ext4: optimize ext4_bio_write_page() when no extent conversion is needed
  ext4: skip orphan cleanup if fs has unknown ROCOMPAT features
  ext4: use the nblocks arg to ext4_truncate_restart_trans()
  ext4: fix missing iput of root inode for some mount error paths
  ext4: make FIEMAP and delayed allocation play well together
  ext4: suppress verbose debugging information if malloc-debug is off
  ...

Fi up conflicts in fs/ext4/super.c due to workqueue changes

15 files changed, 450 insertions, 348 deletions

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index adf96b82278..97b970e7dd1 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -21,6 +21,8 @@
 #include "ext4_jbd2.h"
 #include "mballoc.h"
 
+#include <trace/events/ext4.h>
+
 /*
  * balloc.c contains the blocks allocation and deallocation routines
  */
@@ -342,6 +344,7 @@ ext4_read_block_bitmap(struct super_block *sb, ext4_group_t block_group)
 	 * We do it here so the bitmap uptodate bit
 	 * get set with buffer lock held.
 	 */
+	trace_ext4_read_block_bitmap_load(sb, block_group);
 	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index d8b992e658c..e25e99bf7ee 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -202,13 +202,6 @@ static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
 	return 1;
 }
 
-static inline void ext4_journal_release_buffer(handle_t *handle,
-						struct buffer_head *bh)
-{
-	if (ext4_handle_valid(handle))
-		jbd2_journal_release_buffer(handle, bh);
-}
-
 static inline handle_t *ext4_journal_start(struct inode *inode, int nblocks)
 {
 	return ext4_journal_start_sb(inode->i_sb, nblocks);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 7516fb9c0bd..dd2cb5076ff 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -44,6 +44,8 @@
 #include "ext4_jbd2.h"
 #include "ext4_extents.h"
 
+#include <trace/events/ext4.h>
+
 static int ext4_ext_truncate_extend_restart(handle_t *handle,
 					    struct inode *inode,
 					    int needed)
@@ -664,6 +666,8 @@ ext4_ext_find_extent(struct inode *inode, ext4_lblk_t block,
 		if (unlikely(!bh))
 			goto err;
 		if (!bh_uptodate_or_lock(bh)) {
+			trace_ext4_ext_load_extent(inode, block,
+						path[ppos].p_block);
 			if (bh_submit_read(bh) < 0) {
 				put_bh(bh);
 				goto err;
@@ -1034,7 +1038,7 @@ cleanup:
 		for (i = 0; i < depth; i++) {
 			if (!ablocks[i])
 				continue;
-			ext4_free_blocks(handle, inode, 0, ablocks[i], 1,
+			ext4_free_blocks(handle, inode, NULL, ablocks[i], 1,
 					 EXT4_FREE_BLOCKS_METADATA);
 		}
 	}
@@ -2059,7 +2063,7 @@ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode,
 	if (err)
 		return err;
 	ext_debug("index is empty, remove it, free block %llu\n", leaf);
-	ext4_free_blocks(handle, inode, 0, leaf, 1,
+	ext4_free_blocks(handle, inode, NULL, leaf, 1,
 			 EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET);
 	return err;
 }
@@ -2156,7 +2160,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 		num = le32_to_cpu(ex->ee_block) + ee_len - from;
 		start = ext4_ext_pblock(ex) + ee_len - num;
 		ext_debug("free last %u blocks starting %llu\n", num, start);
-		ext4_free_blocks(handle, inode, 0, start, num, flags);
+		ext4_free_blocks(handle, inode, NULL, start, num, flags);
 	} else if (from == le32_to_cpu(ex->ee_block)
 		   && to <= le32_to_cpu(ex->ee_block) + ee_len - 1) {
 		printk(KERN_INFO "strange request: removal %u-%u from %u:%u\n",
@@ -3108,14 +3112,13 @@ static int check_eofblocks_fl(handle_t *handle, struct inode *inode,
 {
 	int i, depth;
 	struct ext4_extent_header *eh;
-	struct ext4_extent *ex, *last_ex;
+	struct ext4_extent *last_ex;
 
 	if (!ext4_test_inode_flag(inode, EXT4_INODE_EOFBLOCKS))
 		return 0;
 
 	depth = ext_depth(inode);
 	eh = path[depth].p_hdr;
-	ex = path[depth].p_ext;
 
 	if (unlikely(!eh->eh_entries)) {
 		EXT4_ERROR_INODE(inode, "eh->eh_entries == 0 and "
@@ -3295,9 +3298,8 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 			struct ext4_map_blocks *map, int flags)
 {
 	struct ext4_ext_path *path = NULL;
-	struct ext4_extent_header *eh;
 	struct ext4_extent newex, *ex;
-	ext4_fsblk_t newblock;
+	ext4_fsblk_t newblock = 0;
 	int err = 0, depth, ret;
 	unsigned int allocated = 0;
 	struct ext4_allocation_request ar;
@@ -3305,6 +3307,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 
 	ext_debug("blocks %u/%u requested for inode %lu\n",
 		  map->m_lblk, map->m_len, inode->i_ino);
+	trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
 
 	/* check in cache */
 	if (ext4_ext_in_cache(inode, map->m_lblk, &newex)) {
@@ -3352,7 +3355,6 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		err = -EIO;
 		goto out2;
 	}
-	eh = path[depth].p_hdr;
 
 	ex = path[depth].p_ext;
 	if (ex) {
@@ -3485,7 +3487,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode,
 		/* not a good idea to call discard here directly,
 		 * but otherwise we'd need to call it every free() */
 		ext4_discard_preallocations(inode);
-		ext4_free_blocks(handle, inode, 0, ext4_ext_pblock(&newex),
+		ext4_free_blocks(handle, inode, NULL, ext4_ext_pblock(&newex),
 				 ext4_ext_get_actual_len(&newex), 0);
 		goto out2;
 	}
@@ -3525,6 +3527,8 @@ out2:
 		ext4_ext_drop_refs(path);
 		kfree(path);
 	}
+	trace_ext4_ext_map_blocks_exit(inode, map->m_lblk,
+		newblock, map->m_len, err ? err : allocated);
 	return err ? err : allocated;
 }
 
@@ -3658,6 +3662,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
 		return -EOPNOTSUPP;
 
+	trace_ext4_fallocate_enter(inode, offset, len, mode);
 	map.m_lblk = offset >> blkbits;
 	/*
 	 * We can't just convert len to max_blocks because
@@ -3673,6 +3678,7 @@ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	ret = inode_newsize_ok(inode, (len + offset));
 	if (ret) {
 		mutex_unlock(&inode->i_mutex);
+		trace_ext4_fallocate_exit(inode, offset, max_blocks, ret);
 		return ret;
 	}
 retry:
@@ -3717,6 +3723,8 @@ retry:
 		goto retry;
 	}
 	mutex_unlock(&inode->i_mutex);
+	trace_ext4_fallocate_exit(inode, offset, max_blocks,
+				ret > 0 ? ret2 : ret);
 	return ret > 0 ? ret2 : ret;
 }
 
@@ -3775,6 +3783,7 @@ int ext4_convert_unwritten_extents(struct inode *inode, loff_t offset,
 	}
 	return ret > 0 ? ret2 : ret;
 }
+
 /*
  * Callback function called for each extent to gather FIEMAP information.
  */
@@ -3782,38 +3791,162 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 		       struct ext4_ext_cache *newex, struct ext4_extent *ex,
 		       void *data)
 {
-	struct fiemap_extent_info *fieinfo = data;
-	unsigned char blksize_bits = inode->i_sb->s_blocksize_bits;
 	__u64	logical;
 	__u64	physical;
 	__u64	length;
+	loff_t	size;
 	__u32	flags = 0;
-	int	error;
+	int		ret = 0;
+	struct fiemap_extent_info *fieinfo = data;
+	unsigned char blksize_bits;
 
-	logical =  (__u64)newex->ec_block << blksize_bits;
+	blksize_bits = inode->i_sb->s_blocksize_bits;
+	logical = (__u64)newex->ec_block << blksize_bits;
 
 	if (newex->ec_start == 0) {
-		pgoff_t offset;
-		struct page *page;
+		/*
+		 * No extent in extent-tree contains block @newex->ec_start,
+		 * then the block may stay in 1)a hole or 2)delayed-extent.
+		 *
+		 * Holes or delayed-extents are processed as follows.
+		 * 1. lookup dirty pages with specified range in pagecache.
+		 *    If no page is got, then there is no delayed-extent and
+		 *    return with EXT_CONTINUE.
+		 * 2. find the 1st mapped buffer,
+		 * 3. check if the mapped buffer is both in the request range
+		 *    and a delayed buffer. If not, there is no delayed-extent,
+		 *    then return.
+		 * 4. a delayed-extent is found, the extent will be collected.
+		 */
+		ext4_lblk_t	end = 0;
+		pgoff_t		last_offset;
+		pgoff_t		offset;
+		pgoff_t		index;
+		struct page	**pages = NULL;
 		struct buffer_head *bh = NULL;
+		struct buffer_head *head = NULL;
+		unsigned int nr_pages = PAGE_SIZE / sizeof(struct page *);
+
+		pages = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		if (pages == NULL)
+			return -ENOMEM;
 
 		offset = logical >> PAGE_SHIFT;
-		page = find_get_page(inode->i_mapping, offset);
-		if (!page || !page_has_buffers(page))
-			return EXT_CONTINUE;
+repeat:
+		last_offset = offset;
+		head = NULL;
+		ret = find_get_pages_tag(inode->i_mapping, &offset,
+					PAGECACHE_TAG_DIRTY, nr_pages, pages);
+
+		if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
+			/* First time, try to find a mapped buffer. */
+			if (ret == 0) {
+out:
+				for (index = 0; index < ret; index++)
+					page_cache_release(pages[index]);
+				/* just a hole. */
+				kfree(pages);
+				return EXT_CONTINUE;
+			}
 
-		bh = page_buffers(page);
+			/* Try to find the 1st mapped buffer. */
+			end = ((__u64)pages[0]->index << PAGE_SHIFT) >>
+				  blksize_bits;
+			if (!page_has_buffers(pages[0]))
+				goto out;
+			head = page_buffers(pages[0]);
+			if (!head)
+				goto out;
 
-		if (!bh)
-			return EXT_CONTINUE;
+			bh = head;
+			do {
+				if (buffer_mapped(bh)) {
+					/* get the 1st mapped buffer. */
+					if (end > newex->ec_block +
+						newex->ec_len)
+						/* The buffer is out of
+						 * the request range.
+						 */
+						goto out;
+					goto found_mapped_buffer;
+				}
+				bh = bh->b_this_page;
+				end++;
+			} while (bh != head);
 
-		if (buffer_delay(bh)) {
-			flags |= FIEMAP_EXTENT_DELALLOC;
-			page_cache_release(page);
+			/* No mapped buffer found. */
+			goto out;
 		} else {
-			page_cache_release(page);
-			return EXT_CONTINUE;
+			/*Find contiguous delayed buffers. */
+			if (ret > 0 && pages[0]->index == last_offset)
+				head = page_buffers(pages[0]);
+			bh = head;
 		}
+
+found_mapped_buffer:
+		if (bh != NULL && buffer_delay(bh)) {
+			/* 1st or contiguous delayed buffer found. */
+			if (!(flags & FIEMAP_EXTENT_DELALLOC)) {
+				/*
+				 * 1st delayed buffer found, record
+				 * the start of extent.
+				 */
+				flags |= FIEMAP_EXTENT_DELALLOC;
+				newex->ec_block = end;
+				logical = (__u64)end << blksize_bits;
+			}
+			/* Find contiguous delayed buffers. */
+			do {
+				if (!buffer_delay(bh))
+					goto found_delayed_extent;
+				bh = bh->b_this_page;
+				end++;
+			} while (bh != head);
+
+			for (index = 1; index < ret; index++) {
+				if (!page_has_buffers(pages[index])) {
+					bh = NULL;
+					break;
+				}
+				head = page_buffers(pages[index]);
+				if (!head) {
+					bh = NULL;
+					break;
+				}
+				if (pages[index]->index !=
+					pages[0]->index + index) {
+					/* Blocks are not contiguous. */
+					bh = NULL;
+					break;
+				}
+				bh = head;
+				do {
+					if (!buffer_delay(bh))
+						/* Delayed-extent ends. */
+						goto found_delayed_extent;
+					bh = bh->b_this_page;
+					end++;
+				} while (bh != head);
+			}
+		} else if (!(flags & FIEMAP_EXTENT_DELALLOC))
+			/* a hole found. */
+			goto out;
+
+found_delayed_extent:
+		newex->ec_len = min(end - newex->ec_block,
+						(ext4_lblk_t)EXT_INIT_MAX_LEN);
+		if (ret == nr_pages && bh != NULL &&
+			newex->ec_len < EXT_INIT_MAX_LEN &&
+			buffer_delay(bh)) {
+			/* Have not collected an extent and continue. */
+			for (index = 0; index < ret; index++)
+				page_cache_release(pages[index]);
+			goto repeat;
+		}
+
+		for (index = 0; index < ret; index++)
+			page_cache_release(pages[index]);
+		kfree(pages);
 	}
 
 	physical = (__u64)newex->ec_start << blksize_bits;
@@ -3822,32 +3955,16 @@ static int ext4_ext_fiemap_cb(struct inode *inode, struct ext4_ext_path *path,
 	if (ex && ext4_ext_is_uninitialized(ex))
 		flags |= FIEMAP_EXTENT_UNWRITTEN;
 
-	/*
-	 * If this extent reaches EXT_MAX_BLOCK, it must be last.
-	 *
-	 * Or if ext4_ext_next_allocated_block is EXT_MAX_BLOCK,
-	 * this also indicates no more allocated blocks.
-	 *
-	 * XXX this might miss a single-block extent at EXT_MAX_BLOCK
-	 */
-	if (ext4_ext_next_allocated_block(path) == EXT_MAX_BLOCK ||
-	    newex->ec_block + newex->ec_len - 1 == EXT_MAX_BLOCK) {
-		loff_t size = i_size_read(inode);
-		loff_t bs = EXT4_BLOCK_SIZE(inode->i_sb);
-
+	size = i_size_read(inode);
+	if (logical + length >= size)
 		flags |= FIEMAP_EXTENT_LAST;
-		if ((flags & FIEMAP_EXTENT_DELALLOC) &&
-		    logical+length > size)
-			length = (size - logical + bs - 1) & ~(bs-1);
-	}
 
-	error = fiemap_fill_next_extent(fieinfo, logical, physical,
+	ret = fiemap_fill_next_extent(fieinfo, logical, physical,
 					length, flags);
-	if (error < 0)
-		return error;
-	if (error == 1)
+	if (ret < 0)
+		return ret;
+	if (ret == 1)
 		return EXT_BREAK;
-
 	return EXT_CONTINUE;
 }
 
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 7829b287822..7f74019d6d7 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -164,20 +164,20 @@ int ext4_sync_file(struct file *file, int datasync)
 
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
-	trace_ext4_sync_file(file, datasync);
+	trace_ext4_sync_file_enter(file, datasync);
 
 	if (inode->i_sb->s_flags & MS_RDONLY)
 		return 0;
 
 	ret = ext4_flush_completed_IO(inode);
 	if (ret < 0)
-		return ret;
+		goto out;
 
 	if (!journal) {
 		ret = generic_file_fsync(file, datasync);
 		if (!ret && !list_empty(&inode->i_dentry))
 			ext4_sync_parent(inode);
-		return ret;
+		goto out;
 	}
 
 	/*
@@ -194,8 +194,10 @@ int ext4_sync_file(struct file *file, int datasync)
 	 *  (they were dirtied by commit).  But that's OK - the blocks are
 	 *  safe in-journal, which is all fsync() needs to ensure.
 	 */
-	if (ext4_should_journal_data(inode))
-		return ext4_force_commit(inode->i_sb);
+	if (ext4_should_journal_data(inode)) {
+		ret = ext4_force_commit(inode->i_sb);
+		goto out;
+	}
 
 	commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
 	if (jbd2_log_start_commit(journal, commit_tid)) {
@@ -215,5 +217,7 @@ int ext4_sync_file(struct file *file, int datasync)
 		ret = jbd2_log_wait_commit(journal, commit_tid);
 	} else if (journal->j_flags & JBD2_BARRIER)
 		blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
+ out:
+	trace_ext4_sync_file_exit(inode, ret);
 	return ret;
 }
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 78b79e1bd7e..21bb2f61e50 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -152,6 +152,7 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	 * We do it here so the bitmap uptodate bit
 	 * get set with buffer lock held.
 	 */
+	trace_ext4_load_inode_bitmap(sb, block_group);
 	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
@@ -649,7 +650,7 @@ static int find_group_other(struct super_block *sb, struct inode *parent,
 		*group = parent_group + flex_size;
 		if (*group > ngroups)
 			*group = 0;
-		return find_group_orlov(sb, parent, group, mode, 0);
+		return find_group_orlov(sb, parent, group, mode, NULL);
 	}
 
 	/*
@@ -1054,6 +1055,11 @@ got:
 		}
 	}
 
+	if (ext4_handle_valid(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
+
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {
 		ext4_std_error(sb, err);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 9297ad46c46..1a86282b902 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -173,7 +173,7 @@ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
 	BUG_ON(EXT4_JOURNAL(inode) == NULL);
 	jbd_debug(2, "restarting handle %p\n", handle);
 	up_write(&EXT4_I(inode)->i_data_sem);
-	ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
+	ret = ext4_journal_restart(handle, nblocks);
 	down_write(&EXT4_I(inode)->i_data_sem);
 	ext4_discard_preallocations(inode);
 
@@ -720,7 +720,7 @@ allocated:
 	return ret;
 failed_out:
 	for (i = 0; i < index; i++)
-		ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
+		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
 	return ret;
 }
 
@@ -823,20 +823,20 @@ static int ext4_alloc_branch(handle_t *handle, struct inode *inode,
 	return err;
 failed:
 	/* Allocation failed, free what we already allocated */
-	ext4_free_blocks(handle, inode, 0, new_blocks[0], 1, 0);
+	ext4_free_blocks(handle, inode, NULL, new_blocks[0], 1, 0);
 	for (i = 1; i <= n ; i++) {
 		/*
 		 * branch[i].bh is newly allocated, so there is no
 		 * need to revoke the block, which is why we don't
 		 * need to set EXT4_FREE_BLOCKS_METADATA.
 		 */
-		ext4_free_blocks(handle, inode, 0, new_blocks[i], 1,
+		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1,
 				 EXT4_FREE_BLOCKS_FORGET);
 	}
 	for (i = n+1; i < indirect_blks; i++)
-		ext4_free_blocks(handle, inode, 0, new_blocks[i], 1, 0);
+		ext4_free_blocks(handle, inode, NULL, new_blocks[i], 1, 0);
 
-	ext4_free_blocks(handle, inode, 0, new_blocks[i], num, 0);
+	ext4_free_blocks(handle, inode, NULL, new_blocks[i], num, 0);
 
 	return err;
 }
@@ -924,7 +924,7 @@ err_out:
 		ext4_free_blocks(handle, inode, where[i].bh, 0, 1,
 				 EXT4_FREE_BLOCKS_FORGET);
 	}
-	ext4_free_blocks(handle, inode, 0, le32_to_cpu(where[num].key),
+	ext4_free_blocks(handle, inode, NULL, le32_to_cpu(where[num].key),
 			 blks, 0);
 
 	return err;
@@ -973,6 +973,7 @@ static int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
 	int count = 0;
 	ext4_fsblk_t first_block = 0;
 
+	trace_ext4_ind_map_blocks_enter(inode, map->m_lblk, map->m_len, flags);
 	J_ASSERT(!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)));
 	J_ASSERT(handle != NULL || (flags & EXT4_GET_BLOCKS_CREATE) == 0);
 	depth = ext4_block_to_path(inode, map->m_lblk, offsets,
@@ -1058,6 +1059,8 @@ cleanup:
 		partial--;
 	}
 out:
+	trace_ext4_ind_map_blocks_exit(inode, map->m_lblk,
+				map->m_pblk, map->m_len, err);
 	return err;
 }
 
@@ -2060,7 +2063,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 		if (nr_pages == 0)
 			break;
 		for (i = 0; i < nr_pages; i++) {
-			int commit_write = 0, redirty_page = 0;
+			int commit_write = 0, skip_page = 0;
 			struct page *page = pvec.pages[i];
 
 			index = page->index;
@@ -2086,14 +2089,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 			 * If the page does not have buffers (for
 			 * whatever reason), try to create them using
 			 * __block_write_begin.  If this fails,
-			 * redirty the page and move on.
+			 * skip the page and move on.
 			 */
 			if (!page_has_buffers(page)) {
 				if (__block_write_begin(page, 0, len,
 						noalloc_get_block_write)) {
-				redirty_page:
-					redirty_page_for_writepage(mpd->wbc,
-								   page);
+				skip_page:
 					unlock_page(page);
 					continue;
 				}
@@ -2104,7 +2105,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 			block_start = 0;
 			do {
 				if (!bh)
-					goto redirty_page;
+					goto skip_page;
 				if (map && (cur_logical >= map->m_lblk) &&
 				    (cur_logical <= (map->m_lblk +
 						     (map->m_len - 1)))) {
@@ -2120,22 +2121,23 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 					clear_buffer_unwritten(bh);
 				}
 
-				/* redirty page if block allocation undone */
+				/* skip page if block allocation undone */
 				if (buffer_delay(bh) || buffer_unwritten(bh))
-					redirty_page = 1;
+					skip_page = 1;
 				bh = bh->b_this_page;
 				block_start += bh->b_size;
 				cur_logical++;
 				pblock++;
 			} while (bh != page_bufs);
 
-			if (redirty_page)
-				goto redirty_page;
+			if (skip_page)
+				goto skip_page;
 
 			if (commit_write)
 				/* mark the buffer_heads as dirty & uptodate */
 				block_commit_write(page, 0, len);
 
+			clear_page_dirty_for_io(page);
 			/*
 			 * Delalloc doesn't support data journalling,
 			 * but eventually maybe we'll lift this
@@ -2165,8 +2167,7 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
 	return ret;
 }
 
-static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
-					sector_t logical, long blk_cnt)
+static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd)
 {
 	int nr_pages, i;
 	pgoff_t index, end;
@@ -2174,9 +2175,8 @@ static void ext4_da_block_invalidatepages(struct mpage_da_data *mpd,
 	struct inode *inode = mpd->inode;
 	struct address_space *mapping = inode->i_mapping;
 
-	index = logical >> (PAGE_CACHE_SHIFT - inode->i_blkbits);
-	end   = (logical + blk_cnt - 1) >>
-				(PAGE_CACHE_SHIFT - inode->i_blkbits);
+	index = mpd->first_page;
+	end   = mpd->next_page - 1;
 	while (index <= end) {
 		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
 		if (nr_pages == 0)
@@ -2279,9 +2279,8 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
 		err = blks;
 		/*
 		 * If get block returns EAGAIN or ENOSPC and there
-		 * appears to be free blocks we will call
-		 * ext4_writepage() for all of the pages which will
-		 * just redirty the pages.
+		 * appears to be free blocks we will just let
+		 * mpage_da_submit_io() unlock all of the pages.
 		 */
 		if (err == -EAGAIN)
 			goto submit_io;
@@ -2312,8 +2311,10 @@ static void mpage_da_map_and_submit(struct mpage_da_data *mpd)
 				ext4_print_free_blocks(mpd->inode);
 		}
 		/* invalidate all the pages */
-		ext4_da_block_invalidatepages(mpd, next,
-				mpd->b_size >> mpd->inode->i_blkbits);
+		ext4_da_block_invalidatepages(mpd);
+
+		/* Mark this page range as having been completed */
+		mpd->io_done = 1;
 		return;
 	}
 	BUG_ON(blks == 0);
@@ -2438,102 +2439,6 @@ static int ext4_bh_delay_or_unwritten(handle_t *handle, struct buffer_head *bh)
 }
 
 /*
- * __mpage_da_writepage - finds extent of pages and blocks
- *
- * @page: page to consider
- * @wbc: not used, we just follow rules
- * @data: context
- *
- * The function finds extents of pages and scan them for all blocks.
- */
-static int __mpage_da_writepage(struct page *page,
-				struct writeback_control *wbc,
-				struct mpage_da_data *mpd)
-{
-	struct inode *inode = mpd->inode;
-	struct buffer_head *bh, *head;
-	sector_t logical;
-
-	/*
-	 * Can we merge this page to current extent?
-	 */
-	if (mpd->next_page != page->index) {
-		/*
-		 * Nope, we can't. So, we map non-allocated blocks
-		 * and start IO on them
-		 */
-		if (mpd->next_page != mpd->first_page) {
-			mpage_da_map_and_submit(mpd);
-			/*
-			 * skip rest of the page in the page_vec
-			 */
-			redirty_page_for_writepage(wbc, page);
-			unlock_page(page);
-			return MPAGE_DA_EXTENT_TAIL;
-		}
-
-		/*
-		 * Start next extent of pages ...
-		 */
-		mpd->first_page = page->index;
-
-		/*
-		 * ... and blocks
-		 */
-		mpd->b_size = 0;
-		mpd->b_state = 0;
-		mpd->b_blocknr = 0;
-	}
-
-	mpd->next_page = page->index + 1;
-	logical = (sector_t) page->index <<
-		  (PAGE_CACHE_SHIFT - inode->i_blkbits);
-
-	if (!page_has_buffers(page)) {
-		mpage_add_bh_to_extent(mpd, logical, PAGE_CACHE_SIZE,
-				       (1 << BH_Dirty) | (1 << BH_Uptodate));
-		if (mpd->io_done)
-			return MPAGE_DA_EXTENT_TAIL;
-	} else {
-		/*
-		 * Page with regular buffer heads, just add all dirty ones
-		 */
-		head = page_buffers(page);
-		bh = head;
-		do {
-			BUG_ON(buffer_locked(bh));
-			/*
-			 * We need to try to allocate
-			 * unmapped blocks in the same page.
-			 * Otherwise we won't make progress
-			 * with the page in ext4_writepage
-			 */
-			if (ext4_bh_delay_or_unwritten(NULL, bh)) {
-				mpage_add_bh_to_extent(mpd, logical,
-						       bh->b_size,
-						       bh->b_state);
-				if (mpd->io_done)
-					return MPAGE_DA_EXTENT_TAIL;
-			} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
-				/*
-				 * mapped dirty buffer. We need to update
-				 * the b_state because we look at
-				 * b_state in mpage_da_map_blocks. We don't
-				 * update b_size because if we find an
-				 * unmapped buffer_head later we need to
-				 * use the b_state flag of that buffer_head.
-				 */
-				if (mpd->b_size == 0)
-					mpd->b_state = bh->b_state & BH_FLAGS;
-			}
-			logical++;
-		} while ((bh = bh->b_this_page) != head);
-	}
-
-	return 0;
-}
-
-/*
  * This is a special get_blocks_t callback which is used by
  * ext4_da_write_begin().  It will either return mapped block or
  * reserve space for a single block.
@@ -2597,7 +2502,6 @@ static int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 		 * for partial write.
 		 */
 		set_buffer_new(bh);
-		set_buffer_mapped(bh);
 	}
 	return 0;
 }
@@ -2811,27 +2715,27 @@ static int ext4_da_writepages_trans_blocks(struct inode *inode)
 
 /*
  * write_cache_pages_da - walk the list of dirty pages of the given
- * address space and call the callback function (which usually writes
- * the pages).
- *
- * This is a forked version of write_cache_pages().  Differences:
- *	Range cyclic is ignored.
- *	no_nrwrite_index_update is always presumed true
+ * address space and accumulate pages that need writing, and call
+ * mpage_da_map_and_submit to map a single contiguous memory region
+ * and then write them.
  */
 static int write_cache_pages_da(struct address_space *mapping,
 				struct writeback_control *wbc,
 				struct mpage_da_data *mpd,
 				pgoff_t *done_index)
 {
-	int ret = 0;
-	int done = 0;
-	struct pagevec pvec;
-	unsigned nr_pages;
-	pgoff_t index;
-	pgoff_t end;		/* Inclusive */
-	long nr_to_write = wbc->nr_to_write;
-	int tag;
-
+	struct buffer_head	*bh, *head;
+	struct inode		*inode = mapping->host;
+	struct pagevec		pvec;
+	unsigned int		nr_pages;
+	sector_t		logical;
+	pgoff_t			index, end;
+	long			nr_to_write = wbc->nr_to_write;
+	int			i, tag, ret = 0;
+
+	memset(mpd, 0, sizeof(struct mpage_da_data));
+	mpd->wbc = wbc;
+	mpd->inode = inode;
 	pagevec_init(&pvec, 0);
 	index = wbc->range_start >> PAGE_CACHE_SHIFT;
 	end = wbc->range_end >> PAGE_CACHE_SHIFT;
@@ -2842,13 +2746,11 @@ static int write_cache_pages_da(struct address_space *mapping,
 		tag = PAGECACHE_TAG_DIRTY;
 
 	*done_index = index;
-	while (!done && (index <= end)) {
-		int i;
-
+	while (index <= end) {
 		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index, tag,
 			      min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
 		if (nr_pages == 0)
-			break;
+			return 0;
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
@@ -2860,60 +2762,100 @@ static int write_cache_pages_da(struct address_space *mapping,
 			 * mapping. However, page->index will not change
 			 * because we have a reference on the page.
 			 */
-			if (page->index > end) {
-				done = 1;
-				break;
-			}
+			if (page->index > end)
+				goto out;
 
 			*done_index = page->index + 1;
 
+			/*
+			 * If we can't merge this page, and we have
+			 * accumulated an contiguous region, write it
+			 */
+			if ((mpd->next_page != page->index) &&
+			    (mpd->next_page != mpd->first_page)) {
+				mpage_da_map_and_submit(mpd);
+				goto ret_extent_tail;
+			}
+
 			lock_page(page);
 
 			/*
-			 * Page truncated or invalidated. We can freely skip it
-			 * then, even for data integrity operations: the page
-			 * has disappeared concurrently, so there could be no
-			 * real expectation of this data interity operation
-			 * even if there is now a new, dirty page at the same
-			 * pagecache address.
+			 * If the page is no longer dirty, or its
+			 * mapping no longer corresponds to inode we
+			 * are writing (which means it has been
+			 * truncated or invalidated), or the page is
+			 * already under writeback and we are not
+			 * doing a data integrity writeback, skip the page
 			 */
-			if (unlikely(page->mapping != mapping)) {
-continue_unlock:
+			if (!PageDirty(page) ||
+			    (PageWriteback(page) &&
+			     (wbc->sync_mode == WB_SYNC_NONE)) ||
+			    unlikely(page->mapping != mapping)) {
 				unlock_page(page);
 				continue;
 			}
 
-			if (!PageDirty(page)) {
-				/* someone wrote it for us */
-				goto continue_unlock;
-			}
-
-			if (PageWriteback(page)) {
-				if (wbc->sync_mode != WB_SYNC_NONE)
-					wait_on_page_writeback(page);
-				else
-					goto continue_unlock;
-			}
+			if (PageWriteback(page))
+				wait_on_page_writeback(page);
 
 			BUG_ON(PageWriteback(page));
-			if (!clear_page_dirty_for_io(page))
-				goto continue_unlock;
 
-			ret = __mpage_da_writepage(page, wbc, mpd);
-			if (unlikely(ret)) {
-				if (ret == AOP_WRITEPAGE_ACTIVATE) {
-					unlock_page(page);
-					ret = 0;
-				} else {
-					done = 1;
-					break;
-				}
+			if (mpd->next_page != page->index)
+				mpd->first_page = page->index;
+			mpd->next_page = page->index + 1;
+			logical = (sector_t) page->index <<
+				(PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+			if (!page_has_buffers(page)) {
+				mpage_add_bh_to_extent(mpd, logical,
+						       PAGE_CACHE_SIZE,
+						       (1 << BH_Dirty) | (1 << BH_Uptodate));
+				if (mpd->io_done)
+					goto ret_extent_tail;
+			} else {
+				/*
+				 * Page with regular buffer heads,
+				 * just add all dirty ones
+				 */
+				head = page_buffers(page);
+				bh = head;
+				do {
+					BUG_ON(buffer_locked(bh));
+					/*
+					 * We need to try to allocate
+					 * unmapped blocks in the same page.
+					 * Otherwise we won't make progress
+					 * with the page in ext4_writepage
+					 */
+					if (ext4_bh_delay_or_unwritten(NULL, bh)) {
+						mpage_add_bh_to_extent(mpd, logical,
+								       bh->b_size,
+								       bh->b_state);
+						if (mpd->io_done)
+							goto ret_extent_tail;
+					} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
+						/*
+						 * mapped dirty buffer. We need
+						 * to update the b_state
+						 * because we look at b_state
+						 * in mpage_da_map_blocks.  We
+						 * don't update b_size because
+						 * if we find an unmapped
+						 * buffer_head later we need to
+						 * use the b_state flag of that
+						 * buffer_head.
+