diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 8ecac2e77a43..6675e916ebcd 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -538,6 +538,13 @@ struct btrfs_fs_info {
 	struct list_head dead_roots;
 	atomic_t nr_async_submits;
 
+	/*
+	 * this is used by the balancing code to wait for all the pending
+	 * ordered extents
+	 */
+	spinlock_t ordered_extent_lock;
+	struct list_head ordered_extents;
+
 	/*
 	 * there is a pool of worker threads for checksumming during writes
 	 * and a pool for checksumming after reads.  This is because readers
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 7ce3f83c5dd6..ec01062eb41d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1252,6 +1252,9 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->btree_inode->i_nlink = 1;
 	fs_info->thread_pool_size = min(num_online_cpus() + 2, 8);
 
+	INIT_LIST_HEAD(&fs_info->ordered_extents);
+	spin_lock_init(&fs_info->ordered_extent_lock);
+
 	sb->s_blocksize = 4096;
 	sb->s_blocksize_bits = blksize_bits(4096);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index febc6295c7a9..f92b297e7da5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2640,6 +2640,7 @@ static int noinline relocate_inode_pages(struct inode *inode, u64 start,
 	struct file_ra_state *ra;
 	unsigned long total_read = 0;
 	unsigned long ra_pages;
+	struct btrfs_ordered_extent *ordered;
 	struct btrfs_trans_handle *trans;
 
 	ra = kzalloc(sizeof(*ra), GFP_NOFS);
@@ -2658,9 +2659,9 @@ static int noinline relocate_inode_pages(struct inode *inode, u64 start,
 				       calc_ra(i, last_index, ra_pages));
 		}
 		total_read++;
-		if (((u64)i << PAGE_CACHE_SHIFT) > inode->i_size)
+again:
+		if (((u64)i << PAGE_CACHE_SHIFT) > i_size_read(inode))
 			goto truncate_racing;
-
 		page = grab_cache_page(inode->i_mapping, i);
 		if (!page) {
 			goto out_unlock;
@@ -2674,18 +2675,24 @@ static int noinline relocate_inode_pages(struct inode *inode, u64 start,
 				goto out_unlock;
 			}
 		}
-#if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,18)
-		ClearPageDirty(page);
-#else
-		cancel_dirty_page(page, PAGE_CACHE_SIZE);
-#endif
 		wait_on_page_writeback(page);
-		set_page_extent_mapped(page);
+
 		page_start = (u64)page->index << PAGE_CACHE_SHIFT;
 		page_end = page_start + PAGE_CACHE_SIZE - 1;
-
 		lock_extent(io_tree, page_start, page_end, GFP_NOFS);
 
+		ordered = btrfs_lookup_ordered_extent(inode, page_start);
+		if (ordered) {
+			unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
+			unlock_page(page);
+			page_cache_release(page);
+			btrfs_start_ordered_extent(inode, ordered, 1);
+			btrfs_put_ordered_extent(ordered);
+			goto again;
+		}
+		set_page_extent_mapped(page);
+
+
 		set_extent_delalloc(io_tree, page_start,
 				    page_end, GFP_NOFS);
 		set_page_dirty(page);
@@ -2694,10 +2701,18 @@ static int noinline relocate_inode_pages(struct inode *inode, u64 start,
 		unlock_page(page);
 		page_cache_release(page);
 	}
-	balance_dirty_pages_ratelimited_nr(inode->i_mapping,
-					   total_read);
 
 out_unlock:
+	/* we have to start the IO in order to get the ordered extents
+	 * instantiated.  This allows the relocation to code to wait
+	 * for all the ordered extents to hit the disk.
+	 *
+	 * Otherwise, it would constantly loop over the same extents
+	 * because the old ones don't get deleted  until the IO is
+	 * started
+	 */
+	btrfs_fdatawrite_range(inode->i_mapping, start, start + len - 1,
+			       WB_SYNC_NONE);
 	kfree(ra);
 	trans = btrfs_start_transaction(BTRFS_I(inode)->root, 1);
 	if (trans) {
@@ -3238,6 +3253,8 @@ next:
 
 		btrfs_clean_old_snapshots(tree_root);
 
+		btrfs_wait_ordered_extents(tree_root);
+
 		trans = btrfs_start_transaction(tree_root, 1);
 		btrfs_commit_transaction(trans, tree_root);
 		mutex_lock(&root->fs_info->alloc_mutex);
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 83f17a5cbd6a..a61f2e7e2db5 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -213,6 +213,7 @@ int btrfs_defrag_file(struct file *file)
 	struct inode *inode = fdentry(file)->d_inode;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	struct btrfs_ordered_extent *ordered;
 	struct page *page;
 	unsigned long last_index;
 	unsigned long ra_pages = root->fs_info->bdi.ra_pages;
@@ -234,6 +235,7 @@ int btrfs_defrag_file(struct file *file)
 				       min(last_index, i + ra_pages - 1));
 		}
 		total_read++;
+again:
 		page = grab_cache_page(inode->i_mapping, i);
 		if (!page)
 			goto out_unlock;
@@ -247,18 +249,23 @@ int btrfs_defrag_file(struct file *file)
 			}
 		}
 
-#if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,18)
-		ClearPageDirty(page);
-#else
-		cancel_dirty_page(page, PAGE_CACHE_SIZE);
-#endif
 		wait_on_page_writeback(page);
-		set_page_extent_mapped(page);
 
 		page_start = (u64)page->index << PAGE_CACHE_SHIFT;
 		page_end = page_start + PAGE_CACHE_SIZE - 1;
-
 		lock_extent(io_tree, page_start, page_end, GFP_NOFS);
+
+		ordered = btrfs_lookup_ordered_extent(inode, page_start);
+		if (ordered) {
+			unlock_extent(io_tree, page_start, page_end, GFP_NOFS);
+			unlock_page(page);
+			page_cache_release(page);
+			btrfs_start_ordered_extent(inode, ordered, 1);
+			btrfs_put_ordered_extent(ordered);
+			goto again;
+		}
+		set_page_extent_mapped(page);
+
 		set_extent_delalloc(io_tree, page_start,
 				    page_end, GFP_NOFS);
 
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index e42fd233e04c..676e4bd65c52 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -167,20 +167,28 @@ int btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 	entry->file_offset = file_offset;
 	entry->start = start;
 	entry->len = len;
+	entry->inode = inode;
+
 	/* one ref for the tree */
 	atomic_set(&entry->refs, 1);
 	init_waitqueue_head(&entry->wait);
 	INIT_LIST_HEAD(&entry->list);
+	INIT_LIST_HEAD(&entry->root_extent_list);
 
 	node = tree_insert(&tree->tree, file_offset,
 			   &entry->rb_node);
 	if (node) {
-		entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
-		atomic_inc(&entry->refs);
+		printk("warning dup entry from add_ordered_extent\n");
+		BUG();
 	}
 	set_extent_ordered(&BTRFS_I(inode)->io_tree, file_offset,
 			   entry_end(entry) - 1, GFP_NOFS);
 
+	spin_lock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
+	list_add_tail(&entry->root_extent_list,
+		      &BTRFS_I(inode)->root->fs_info->ordered_extents);
+	spin_unlock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
+
 	mutex_unlock(&tree->mutex);
 	BUG_ON(node);
 	return 0;
@@ -285,11 +293,55 @@ int btrfs_remove_ordered_extent(struct inode *inode,
 	rb_erase(node, &tree->tree);
 	tree->last = NULL;
 	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
+
+	spin_lock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
+	list_del_init(&entry->root_extent_list);
+	spin_unlock(&BTRFS_I(inode)->root->fs_info->ordered_extent_lock);
+
 	mutex_unlock(&tree->mutex);
 	wake_up(&entry->wait);
 	return 0;
 }
 
+int btrfs_wait_ordered_extents(struct btrfs_root *root)
+{
+	struct list_head splice;
+	struct list_head *cur;
+	struct btrfs_ordered_extent *ordered;
+	struct inode *inode;
+
+	INIT_LIST_HEAD(&splice);
+
+	spin_lock(&root->fs_info->ordered_extent_lock);
+	list_splice_init(&root->fs_info->ordered_extents, &splice);
+	while(!list_empty(&splice)) {
+		cur = splice.next;
+		ordered = list_entry(cur, struct btrfs_ordered_extent,
+				     root_extent_list);
+		list_del_init(&ordered->root_extent_list);
+		atomic_inc(&ordered->refs);
+		inode = ordered->inode;
+
+		/*
+		 * the inode can't go away until all the pages are gone
+		 * and the pages won't go away while there is still
+		 * an ordered extent and the ordered extent won't go
+		 * away until it is off this list.  So, we can safely
+		 * increment i_count here and call iput later
+		 */
+		atomic_inc(&inode->i_count);
+		spin_unlock(&root->fs_info->ordered_extent_lock);
+
+		btrfs_start_ordered_extent(inode, ordered, 1);
+		btrfs_put_ordered_extent(ordered);
+		iput(inode);
+
+		spin_lock(&root->fs_info->ordered_extent_lock);
+	}
+	spin_unlock(&root->fs_info->ordered_extent_lock);
+	return 0;
+}
+
 /*
  * Used to start IO or wait for a given ordered extent to finish.
  *
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 199cb0b4f1d9..5efe6b63c74c 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -80,6 +80,9 @@ struct btrfs_ordered_extent {
 	/* reference count */
 	atomic_t refs;
 
+	/* the inode we belong to */
+	struct inode *inode;
+
 	/* list of checksums for insertion when the extent io is done */
 	struct list_head list;
 
@@ -88,6 +91,9 @@ struct btrfs_ordered_extent {
 
 	/* our friendly rbtree entry */
 	struct rb_node rb_node;
+
+	/* a per root list of all the pending ordered extents */
+	struct list_head root_extent_list;
 };
 
 
@@ -137,4 +143,5 @@ int btrfs_wait_on_page_writeback_range(struct address_space *mapping,
 				       pgoff_t start, pgoff_t end);
 int btrfs_fdatawrite_range(struct address_space *mapping, loff_t start,
 			   loff_t end, int sync_mode);
+int btrfs_wait_ordered_extents(struct btrfs_root *root);
 #endif