diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 0bbf78cc5f75e..4fd242acec3cc 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -9809,10 +9809,6 @@ static int start_delalloc_inodes(struct btrfs_root *root,
 					 &work->work);
 		} else {
 			ret = sync_inode(inode, wbc);
-			if (!ret &&
-			    test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
-				     &BTRFS_I(inode)->runtime_flags))
-				ret = sync_inode(inode, wbc);
 			btrfs_add_delayed_iput(inode);
 			if (ret || wbc->nr_to_write <= 0)
 				goto out;
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 87f258600acc9..facd1c6876f03 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -532,9 +532,49 @@ static void shrink_delalloc(struct btrfs_fs_info *fs_info,
 	while ((delalloc_bytes || ordered_bytes) && loops < 3) {
 		u64 temp = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
 		long nr_pages = min_t(u64, temp, LONG_MAX);
+		int async_pages;
 
 		btrfs_start_delalloc_roots(fs_info, nr_pages, true);
 
+		/*
+		 * We need to make sure any outstanding async pages are now
+		 * processed before we continue.  This is because things like
+		 * sync_inode() try to be smart and skip writing if the inode is
+		 * marked clean.  We don't use filemap_fwrite for flushing
+		 * because we want to control how many pages we write out at a
+		 * time, thus this is the only safe way to make sure we've
+		 * waited for outstanding compressed workers to have started
+		 * their jobs and thus have ordered extents set up properly.
+		 *
+		 * This exists because we do not want to wait for each
+		 * individual inode to finish its async work, we simply want to
+		 * start the IO on everybody, and then come back here and wait
+		 * for all of the async work to catch up.  Once we're done with
+		 * that we know we'll have ordered extents for everything and we
+		 * can decide if we wait for that or not.
+		 *
+		 * If we choose to replace this in the future, make absolutely
+		 * sure that the proper waiting is being done in the async case,
+		 * as there have been bugs in that area before.
+		 */
+		async_pages = atomic_read(&fs_info->async_delalloc_pages);
+		if (!async_pages)
+			goto skip_async;
+
+		/*
+		 * We don't want to wait forever, if we wrote less pages in this
+		 * loop than we have outstanding, only wait for that number of
+		 * pages, otherwise we can wait for all async pages to finish
+		 * before continuing.
+		 */
+		if (async_pages > nr_pages)
+			async_pages -= nr_pages;
+		else
+			async_pages = 0;
+		wait_event(fs_info->async_submit_wait,
+			   atomic_read(&fs_info->async_delalloc_pages) <=
+			   async_pages);
+skip_async:
 		loops++;
 		if (wait_ordered && !trans) {
 			btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);