1 files changed, 98 insertions, 72 deletions

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 015910079e73..56032c518b26 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -368,6 +368,7 @@ struct async_chunk {
 	u64 end;
 	unsigned int write_flags;
 	struct list_head extents;
+	struct cgroup_subsys_state *blkcg_css;
 	struct btrfs_work work;
 	atomic_t *pending;
 };
@@ -712,10 +713,12 @@ cleanup_and_bail_uncompressed:
 	 * to our extent and set things up for the async work queue to run
 	 * cow_file_range to do the normal delalloc dance.
 	 */
-	if (page_offset(async_chunk->locked_page) >= start &&
-	    page_offset(async_chunk->locked_page) <= end)
+	if (async_chunk->locked_page &&
+	    (page_offset(async_chunk->locked_page) >= start &&
+	     page_offset(async_chunk->locked_page)) <= end) {
 		__set_page_dirty_nobuffers(async_chunk->locked_page);
 		/* unlocked later on in the async handlers */
+	}
 
 	if (redirty)
 		extent_range_redirty_for_io(inode, start, end);
@@ -795,7 +798,7 @@ retry:
 						  async_extent->start +
 						  async_extent->ram_size - 1,
 						  WB_SYNC_ALL);
-			else if (ret)
+			else if (ret && async_chunk->locked_page)
 				unlock_page(async_chunk->locked_page);
 			kfree(async_extent);
 			cond_resched();
@@ -878,7 +881,8 @@ retry:
 				    ins.objectid,
 				    ins.offset, async_extent->pages,
 				    async_extent->nr_pages,
-				    async_chunk->write_flags)) {
+				    async_chunk->write_flags,
+				    async_chunk->blkcg_css)) {
 			struct page *p = async_extent->pages[0];
 			const u64 start = async_extent->start;
 			const u64 end = start + async_extent->ram_size - 1;
@@ -1196,6 +1200,8 @@ static noinline void async_cow_free(struct btrfs_work *work)
 	async_chunk = container_of(work, struct async_chunk, work);
 	if (async_chunk->inode)
 		btrfs_add_delayed_iput(async_chunk->inode);
+	if (async_chunk->blkcg_css)
+		css_put(async_chunk->blkcg_css);
 	/*
 	 * Since the pointer to 'pending' is at the beginning of the array of
 	 * async_chunk's, freeing it ensures the whole array has been freed.
@@ -1204,12 +1210,14 @@ static noinline void async_cow_free(struct btrfs_work *work)
 		kvfree(async_chunk->pending);
 }
 
-static int cow_file_range_async(struct inode *inode, struct page *locked_page,
+static int cow_file_range_async(struct inode *inode,
+				struct writeback_control *wbc,
+				struct page *locked_page,
 				u64 start, u64 end, int *page_started,
-				unsigned long *nr_written,
-				unsigned int write_flags)
+				unsigned long *nr_written)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc);
 	struct async_cow *ctx;
 	struct async_chunk *async_chunk;
 	unsigned long nr_pages;
@@ -1218,6 +1226,7 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 	int i;
 	bool should_compress;
 	unsigned nofs_flag;
+	const unsigned int write_flags = wbc_to_write_flags(wbc);
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 
@@ -1264,14 +1273,45 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 		async_chunk[i].inode = inode;
 		async_chunk[i].start = start;
 		async_chunk[i].end = cur_end;
-		async_chunk[i].locked_page = locked_page;
 		async_chunk[i].write_flags = write_flags;
 		INIT_LIST_HEAD(&async_chunk[i].extents);
 
-		btrfs_init_work(&async_chunk[i].work,
-				btrfs_delalloc_helper,
-				async_cow_start, async_cow_submit,
-				async_cow_free);
+		/*
+		 * The locked_page comes all the way from writepage and its
+		 * the original page we were actually given.  As we spread
+		 * this large delalloc region across multiple async_chunk
+		 * structs, only the first struct needs a pointer to locked_page
+		 *
+		 * This way we don't need racey decisions about who is supposed
+		 * to unlock it.
+		 */
+		if (locked_page) {
+			/*
+			 * Depending on the compressibility, the pages might or
+			 * might not go through async.  We want all of them to
+			 * be accounted against wbc once.  Let's do it here
+			 * before the paths diverge.  wbc accounting is used
+			 * only for foreign writeback detection and doesn't
+			 * need full accuracy.  Just account the whole thing
+			 * against the first page.
+			 */
+			wbc_account_cgroup_owner(wbc, locked_page,
+						 cur_end - start);
+			async_chunk[i].locked_page = locked_page;
+			locked_page = NULL;
+		} else {
+			async_chunk[i].locked_page = NULL;
+		}
+
+		if (blkcg_css != blkcg_root_css) {
+			css_get(blkcg_css);
+			async_chunk[i].blkcg_css = blkcg_css;
+		} else {
+			async_chunk[i].blkcg_css = NULL;
+		}
+
+		btrfs_init_work(&async_chunk[i].work, async_cow_start,
+				async_cow_submit, async_cow_free);
 
 		nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE);
 		atomic_add(nr_pages, &fs_info->async_delalloc_pages);
@@ -1697,7 +1737,6 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
 {
 	int ret;
 	int force_cow = need_force_cow(inode, start, end);
-	unsigned int write_flags = wbc_to_write_flags(wbc);
 
 	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
 		ret = run_delalloc_nocow(inode, locked_page, start, end,
@@ -1712,9 +1751,8 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
 	} else {
 		set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
 			&BTRFS_I(inode)->runtime_flags);
-		ret = cow_file_range_async(inode, locked_page, start, end,
-					   page_started, nr_written,
-					   write_flags);
+		ret = cow_file_range_async(inode, wbc, locked_page, start, end,
+					   page_started, nr_written);
 	}
 	if (ret)
 		btrfs_cleanup_ordered_extents(inode, locked_page, start,
@@ -2110,7 +2148,7 @@ static blk_status_t btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 	}
 
 mapit:
-	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, bio, mirror_num);
 
 out:
 	if (ret) {
@@ -2214,12 +2252,16 @@ again:
 		mapping_set_error(page->mapping, ret);
 		end_extent_writepage(page, ret, page_start, page_end);
 		ClearPageChecked(page);
-		goto out;
+		goto out_reserved;
 	}
 
 	ClearPageChecked(page);
 	set_page_dirty(page);
+out_reserved:
 	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
+	if (ret)
+		btrfs_delalloc_release_space(inode, data_reserved, page_start,
+					     PAGE_SIZE, true);
 out:
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start, page_end,
 			     &cached_state);
@@ -2260,8 +2302,7 @@ int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end)
 
 	SetPageChecked(page);
 	get_page(page);
-	btrfs_init_work(&fixup->work, btrfs_fixup_helper,
-			btrfs_writepage_fixup_worker, NULL, NULL);
+	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL, NULL);
 	fixup->page = page;
 	btrfs_queue_work(fs_info->fixup_workers, &fixup->work);
 	return -EBUSY;
@@ -2675,7 +2716,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 
-	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
+	inode = btrfs_iget(fs_info->sb, &key, root);
 	if (IS_ERR(inode)) {
 		srcu_read_unlock(&fs_info->subvol_srcu, index);
 		return 0;
@@ -2999,7 +3040,7 @@ out_kfree:
 static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info,
 					 u64 start, u64 len)
 {
-	struct btrfs_block_group_cache *cache;
+	struct btrfs_block_group *cache;
 
 	cache = btrfs_lookup_block_group(fs_info, start);
 	ASSERT(cache);
@@ -3027,7 +3068,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	int compress_type = 0;
 	int ret = 0;
 	u64 logical_len = ordered_extent->len;
-	bool nolock;
+	bool freespace_inode;
 	bool truncated = false;
 	bool range_locked = false;
 	bool clear_new_delalloc_bytes = false;
@@ -3038,7 +3079,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
 		clear_new_delalloc_bytes = true;
 
-	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
+	freespace_inode = btrfs_is_free_space_inode(BTRFS_I(inode));
 
 	if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
 		ret = -EIO;
@@ -3069,8 +3110,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
 				       ordered_extent->len);
 		btrfs_ordered_update_i_size(inode, 0, ordered_extent);
-		if (nolock)
-			trans = btrfs_join_transaction_nolock(root);
+		if (freespace_inode)
+			trans = btrfs_join_transaction_spacecache(root);
 		else
 			trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans)) {
@@ -3104,8 +3145,8 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 			EXTENT_DEFRAG, 0, 0, &cached_state);
 	}
 
-	if (nolock)
-		trans = btrfs_join_transaction_nolock(root);
+	if (freespace_inode)
+		trans = btrfs_join_transaction_spacecache(root);
 	else
 		trans = btrfs_join_transaction(root);
 	if (IS_ERR(trans)) {
@@ -3254,7 +3295,6 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered_extent = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 
 	trace_btrfs_writepage_end_io_hook(page, start, end, uptodate);
 
@@ -3263,16 +3303,12 @@ void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
 					    end - start + 1, uptodate))
 		return;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
-	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
-			NULL);
+	btrfs_init_work(&ordered_extent->work, finish_ordered_fn, NULL, NULL);
 	btrfs_queue_work(wq, &ordered_extent->work);
 }
 
@@ -3531,7 +3567,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 		found_key.objectid = found_key.offset;
 		found_key.type = BTRFS_INODE_ITEM_KEY;
 		found_key.offset = 0;
-		inode = btrfs_iget(fs_info->sb, &found_key, root, NULL);
+		inode = btrfs_iget(fs_info->sb, &found_key, root);
 		ret = PTR_ERR_OR_ZERO(inode);
 		if (ret && ret != -ENOENT)
 			goto out;
@@ -5153,7 +5189,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 			hole_em->block_len = 0;
 			hole_em->orig_block_len = 0;
 			hole_em->ram_bytes = hole_size;
-			hole_em->bdev = fs_info->fs_devices->latest_bdev;
 			hole_em->compress_type = BTRFS_COMPRESS_NONE;
 			hole_em->generation = fs_info->generation;
 
@@ -5750,12 +5785,14 @@ static struct inode *btrfs_iget_locked(struct super_block *s,
 	return inode;
 }
 
-/* Get an inode object given its location and corresponding root.
- * Returns in *is_new if the inode was read from disk
+/*
+ * Get an inode object given its location and corresponding root.
+ * Path can be preallocated to prevent recursing back to iget through
+ * allocator. NULL is also valid but may require an additional allocation
+ * later.
  */
 struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
-			      struct btrfs_root *root, int *new,
-			      struct btrfs_path *path)
+			      struct btrfs_root *root, struct btrfs_path *path)
 {
 	struct inode *inode;
 
@@ -5770,8 +5807,6 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
 		if (!ret) {
 			inode_tree_add(inode);
 			unlock_new_inode(inode);
-			if (new)
-				*new = 1;
 		} else {
 			iget_failed(inode);
 			/*
@@ -5789,9 +5824,9 @@ struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
 }
 
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
-			 struct btrfs_root *root, int *new)
+			 struct btrfs_root *root)
 {
-	return btrfs_iget_path(s, location, root, new, NULL);
+	return btrfs_iget_path(s, location, root, NULL);
 }
 
 static struct inode *new_simple_dir(struct super_block *s,
@@ -5857,7 +5892,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		return ERR_PTR(ret);
 
 	if (location.type == BTRFS_INODE_ITEM_KEY) {
-		inode = btrfs_iget(dir->i_sb, &location, root, NULL);
+		inode = btrfs_iget(dir->i_sb, &location, root);
 		if (IS_ERR(inode))
 			return inode;
 
@@ -5882,7 +5917,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
 		else
 			inode = new_simple_dir(dir->i_sb, &location, sub_root);
 	} else {
-		inode = btrfs_iget(dir->i_sb, &location, sub_root, NULL);
+		inode = btrfs_iget(dir->i_sb, &location, sub_root);
 	}
 	srcu_read_unlock(&fs_info->subvol_srcu, index);
 
@@ -6931,8 +6966,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 
 	read_lock(&em_tree->lock);
 	em = lookup_extent_mapping(em_tree, start, len);
-	if (em)
-		em->bdev = fs_info->fs_devices->latest_bdev;
 	read_unlock(&em_tree->lock);
 
 	if (em) {
@@ -6948,7 +6981,6 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 		err = -ENOMEM;
 		goto out;
 	}
-	em->bdev = fs_info->fs_devices->latest_bdev;
 	em->start = EXTENT_MAP_HOLE;
 	em->orig_start = EXTENT_MAP_HOLE;
 	em->len = (u64)-1;
@@ -7207,7 +7239,6 @@ struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
 			err = -ENOMEM;
 			goto out;
 		}
-		em->bdev = NULL;
 
 		ASSERT(hole_em);
 		/*
@@ -7567,7 +7598,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 {
 	struct extent_map_tree *em_tree;
 	struct extent_map *em;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
 	ASSERT(type == BTRFS_ORDERED_PREALLOC ||
@@ -7585,7 +7615,6 @@ static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
 	em->len = len;
 	em->block_len = block_len;
 	em->block_start = block_start;
-	em->bdev = root->fs_info->fs_devices->latest_bdev;
 	em->orig_block_len = orig_block_len;
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
@@ -7624,6 +7653,8 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
 					struct inode *inode,
 					u64 start, u64 len)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+
 	if (em->block_start == EXTENT_MAP_HOLE ||
 			test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 		return -ENOENT;
@@ -7633,7 +7664,7 @@ static int btrfs_get_blocks_direct_read(struct extent_map *em,
 	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
 		inode->i_blkbits;
 	bh_result->b_size = len;
-	bh_result->b_bdev = em->bdev;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
 	set_buffer_mapped(bh_result);
 
 	return 0;
@@ -7716,7 +7747,7 @@ skip_cow:
 	bh_result->b_blocknr = (em->block_start + (start - em->start)) >>
 		inode->i_blkbits;
 	bh_result->b_size = len;
-	bh_result->b_bdev = em->bdev;
+	bh_result->b_bdev = fs_info->fs_devices->latest_bdev;
 	set_buffer_mapped(bh_result);
 
 	if (!test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
@@ -7858,7 +7889,7 @@ static inline blk_status_t submit_dio_repair_bio(struct inode *inode,
 	if (ret)
 		return ret;
 
-	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
+	ret = btrfs_map_bio(fs_info, bio, mirror_num);
 
 	return ret;
 }
@@ -8211,18 +8242,14 @@ static void __endio_write_update_ordered(struct inode *inode,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered = NULL;
 	struct btrfs_workqueue *wq;
-	btrfs_work_func_t func;
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
 	u64 last_offset;
 
-	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		wq = fs_info->endio_freespace_worker;
-		func = btrfs_freespace_write_helper;
-	} else {
+	else
 		wq = fs_info->endio_write_workers;
-		func = btrfs_endio_write_helper;
-	}
 
 	while (ordered_offset < offset + bytes) {
 		last_offset = ordered_offset;
@@ -8230,9 +8257,8 @@ static void __endio_write_update_ordered(struct inode *inode,
 							   &ordered_offset,
 							   ordered_bytes,
 							   uptodate)) {
-			btrfs_init_work(&ordered->work, func,
-					finish_ordered_fn,
-					NULL, NULL);
+			btrfs_init_work(&ordered->work, finish_ordered_fn, NULL,
+					NULL);
 			btrfs_queue_work(wq, &ordered->work);
 		}
 		/*
@@ -8389,7 +8415,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 			goto err;
 	}
 map:
-	ret = btrfs_map_bio(fs_info, bio, 0, 0);
+	ret = btrfs_map_bio(fs_info, bio, 0);
 err:
 	return ret;
 }
@@ -9321,7 +9347,6 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->io_failure_tree.track_uptodate = true;
 	atomic_set(&ei->sync_writers, 0);
 	mutex_init(&ei->log_mutex);
-	mutex_init(&ei->delalloc_mutex);
 	btrfs_ordered_inode_tree_init(&ei->ordered_tree);
 	INIT_LIST_HEAD(&ei->delalloc_inodes);
 	INIT_LIST_HEAD(&ei->delayed_iput);
@@ -9550,6 +9575,9 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		goto out_notrans;
 	}
 
+	if (dest != root)
+		btrfs_record_root_in_trans(trans, dest);
+
 	/*
 	 * We need to find a free sequence number both in the source and
 	 * in the destination directory for the exchange.
@@ -10116,8 +10144,7 @@ static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode
 	init_completion(&work->completion);
 	INIT_LIST_HEAD(&work->list);
 	work->inode = inode;
-	btrfs_init_work(&work->work, btrfs_flush_delalloc_helper,
-			btrfs_run_delalloc_work, NULL, NULL);
+	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL, NULL);
 
 	return work;
 }
@@ -10450,7 +10477,6 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 		em->block_len = ins.offset;
 		em->orig_block_len = ins.offset;
 		em->ram_bytes = ins.offset;
-		em->bdev = fs_info->fs_devices->latest_bdev;
 		set_bit(EXTENT_FLAG_PREALLOC, &em->flags);
 		em->generation = trans->transid;
 
@@ -10806,7 +10832,7 @@ static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
 	start = 0;
 	while (start < isize) {
 		u64 logical_block_start, physical_block_start;
-		struct btrfs_block_group_cache *bg;
+		struct btrfs_block_group *bg;
 		u64 len = isize - start;
 
 		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);