Merge branch 'for-linus-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs

Pull btrfs fixes from Chris Mason:
 "A few more btrfs fixes.

  These range from corners Filipe found in the new free space cache
  writeback to a grab bag of fixes from the list"

* 'for-linus-4.1' of git://git.kernel.org/pub/scm/linux/kernel/git/mason/linux-btrfs:
  Btrfs: btrfs_release_extent_buffer_page didn't free pages of dummy extent
  Btrfs: fill ->last_trans for delayed inode in btrfs_fill_inode.
  btrfs: unlock i_mutex after attempting to delete subvolume during send
  btrfs: check io_ctl_prepare_pages return in __btrfs_write_out_cache
  btrfs: fix race on ENOMEM in alloc_extent_buffer
  btrfs: handle ENOMEM in btrfs_alloc_tree_block
  Btrfs: fix find_free_dev_extent() malfunction in case device tree has hole
  Btrfs: don't check for delalloc_bytes in cache_save_setup
  Btrfs: fix deadlock when starting writeback of bg caches
  Btrfs: fix race between start dirty bg cache writeout and bg deletion

fs/btrfs/delayed-inode.c

@@ -1802,6 +1802,8 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 	set_nlink(inode, btrfs_stack_inode_nlink(inode_item));
 	inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));
 	BTRFS_I(inode)->generation = btrfs_stack_inode_generation(inode_item);
+        BTRFS_I(inode)->last_trans = btrfs_stack_inode_transid(inode_item);
+
 	inode->i_version = btrfs_stack_inode_sequence(inode_item);
 	inode->i_rdev = 0;
 	*rdev = btrfs_stack_inode_rdev(inode_item);

fs/btrfs/extent-tree.c

@@ -3178,8 +3178,8 @@ static int write_one_cache_group(struct btrfs_trans_handle *trans,
 	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
 	write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
 	btrfs_mark_buffer_dirty(leaf);
-	btrfs_release_path(path);
 fail:
+	btrfs_release_path(path);
 	if (ret)
 		btrfs_abort_transaction(trans, root, ret);
 	return ret;
@@ -3305,8 +3305,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 
 	spin_lock(&block_group->lock);
 	if (block_group->cached != BTRFS_CACHE_FINISHED ||
-	    !btrfs_test_opt(root, SPACE_CACHE) ||
-	    block_group->delalloc_bytes) {
+	    !btrfs_test_opt(root, SPACE_CACHE)) {
 		/*
 		 * don't bother trying to write stuff out _if_
 		 * a) we're not cached,
@@ -3408,17 +3407,14 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
 	int loops = 0;
 
 	spin_lock(&cur_trans->dirty_bgs_lock);
-	if (!list_empty(&cur_trans->dirty_bgs)) {
-		list_splice_init(&cur_trans->dirty_bgs, &dirty);
+	if (list_empty(&cur_trans->dirty_bgs)) {
+		spin_unlock(&cur_trans->dirty_bgs_lock);
+		return 0;
 	}
+	list_splice_init(&cur_trans->dirty_bgs, &dirty);
 	spin_unlock(&cur_trans->dirty_bgs_lock);
 
 again:
-	if (list_empty(&dirty)) {
-		btrfs_free_path(path);
-		return 0;
-	}
-
 	/*
 	 * make sure all the block groups on our dirty list actually
 	 * exist
@@ -3431,18 +3427,16 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
 			return -ENOMEM;
 	}
 
+	/*
+	 * cache_write_mutex is here only to save us from balance or automatic
+	 * removal of empty block groups deleting this block group while we are
+	 * writing out the cache
+	 */
+	mutex_lock(&trans->transaction->cache_write_mutex);
 	while (!list_empty(&dirty)) {
 		cache = list_first_entry(&dirty,
 					 struct btrfs_block_group_cache,
 					 dirty_list);
-
-		/*
-		 * cache_write_mutex is here only to save us from balance
-		 * deleting this block group while we are writing out the
-		 * cache
-		 */
-		mutex_lock(&trans->transaction->cache_write_mutex);
-
 		/*
 		 * this can happen if something re-dirties a block
 		 * group that is already under IO.  Just wait for it to
@@ -3495,7 +3489,6 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
 		}
 		if (!ret)
 			ret = write_one_cache_group(trans, root, path, cache);
-		mutex_unlock(&trans->transaction->cache_write_mutex);
 
 		/* if its not on the io list, we need to put the block group */
 		if (should_put)
@@ -3503,7 +3496,16 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
 
 		if (ret)
 			break;
+
+		/*
+		 * Avoid blocking other tasks for too long. It might even save
+		 * us from writing caches for block groups that are going to be
+		 * removed.
+		 */
+		mutex_unlock(&trans->transaction->cache_write_mutex);
+		mutex_lock(&trans->transaction->cache_write_mutex);
 	}
+	mutex_unlock(&trans->transaction->cache_write_mutex);
 
 	/*
 	 * go through delayed refs for all the stuff we've just kicked off
@@ -3514,8 +3516,15 @@ int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans,
 		loops++;
 		spin_lock(&cur_trans->dirty_bgs_lock);
 		list_splice_init(&cur_trans->dirty_bgs, &dirty);
+		/*
+		 * dirty_bgs_lock protects us from concurrent block group
+		 * deletes too (not just cache_write_mutex).
+		 */
+		if (!list_empty(&dirty)) {
+			spin_unlock(&cur_trans->dirty_bgs_lock);
+			goto again;
+		}
 		spin_unlock(&cur_trans->dirty_bgs_lock);
-		goto again;
 	}
 
 	btrfs_free_path(path);
@@ -7537,7 +7546,7 @@ static void unuse_block_rsv(struct btrfs_fs_info *fs_info,
  * returns the key for the extent through ins, and a tree buffer for
  * the first block of the extent through buf.
  *
- * returns the tree buffer or NULL.
+ * returns the tree buffer or an ERR_PTR on error.
  */
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 					struct btrfs_root *root,
@@ -7548,6 +7557,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 	struct btrfs_key ins;
 	struct btrfs_block_rsv *block_rsv;
 	struct extent_buffer *buf;
+	struct btrfs_delayed_extent_op *extent_op;
 	u64 flags = 0;
 	int ret;
 	u32 blocksize = root->nodesize;
@@ -7568,13 +7578,14 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_reserve_extent(root, blocksize, blocksize,
 				   empty_size, hint, &ins, 0, 0);
-	if (ret) {
-		unuse_block_rsv(root->fs_info, block_rsv, blocksize);
-		return ERR_PTR(ret);
-	}
+	if (ret)
+		goto out_unuse;
 
 	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level);
-	BUG_ON(IS_ERR(buf)); /* -ENOMEM */
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		goto out_free_reserved;
+	}
 
 	if (root_objectid == BTRFS_TREE_RELOC_OBJECTID) {
 		if (parent == 0)
@@ -7584,9 +7595,11 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		BUG_ON(parent > 0);
 
 	if (root_objectid != BTRFS_TREE_LOG_OBJECTID) {
-		struct btrfs_delayed_extent_op *extent_op;
 		extent_op = btrfs_alloc_delayed_extent_op();
-		BUG_ON(!extent_op); /* -ENOMEM */
+		if (!extent_op) {
+			ret = -ENOMEM;
+			goto out_free_buf;
+		}
 		if (key)
 			memcpy(&extent_op->key, key, sizeof(extent_op->key));
 		else
@@ -7601,13 +7614,24 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		extent_op->level = level;
 
 		ret = btrfs_add_delayed_tree_ref(root->fs_info, trans,
-					ins.objectid,
-					ins.offset, parent, root_objectid,
-					level, BTRFS_ADD_DELAYED_EXTENT,
-					extent_op, 0);
-		BUG_ON(ret); /* -ENOMEM */
+						 ins.objectid, ins.offset,
+						 parent, root_objectid, level,
+						 BTRFS_ADD_DELAYED_EXTENT,
+						 extent_op, 0);
+		if (ret)
+			goto out_free_delayed;
 	}
 	return buf;
+
+out_free_delayed:
+	btrfs_free_delayed_extent_op(extent_op);
+out_free_buf:
+	free_extent_buffer(buf);
+out_free_reserved:
+	btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 0);
+out_unuse:
+	unuse_block_rsv(root->fs_info, block_rsv, blocksize);
+	return ERR_PTR(ret);
 }
 
 struct walk_control {

fs/btrfs/extent_io.c

@@ -4560,36 +4560,37 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 	do {
 		index--;
 		page = eb->pages[index];
-		if (page && mapped) {
+		if (!page)
+			continue;
+		if (mapped)
 			spin_lock(&page->mapping->private_lock);
+		/*
+		 * We do this since we'll remove the pages after we've
+		 * removed the eb from the radix tree, so we could race
+		 * and have this page now attached to the new eb.  So
+		 * only clear page_private if it's still connected to
+		 * this eb.
+		 */
+		if (PagePrivate(page) &&
+		    page->private == (unsigned long)eb) {
+			BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
+			BUG_ON(PageDirty(page));
+			BUG_ON(PageWriteback(page));
 			/*
-			 * We do this since we'll remove the pages after we've
-			 * removed the eb from the radix tree, so we could race
-			 * and have this page now attached to the new eb.  So
-			 * only clear page_private if it's still connected to
-			 * this eb.
+			 * We need to make sure we haven't be attached
+			 * to a new eb.
 			 */
-			if (PagePrivate(page) &&
-			    page->private == (unsigned long)eb) {
-				BUG_ON(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
-				BUG_ON(PageDirty(page));
-				BUG_ON(PageWriteback(page));
-				/*
-				 * We need to make sure we haven't be attached
-				 * to a new eb.
-				 */
-				ClearPagePrivate(page);
-				set_page_private(page, 0);
-				/* One for the page private */
-				page_cache_release(page);
-			}
-			spin_unlock(&page->mapping->private_lock);
-
-		}
-		if (page) {
-			/* One for when we alloced the page */
+			ClearPagePrivate(page);
+			set_page_private(page, 0);
+			/* One for the page private */
 			page_cache_release(page);
 		}
+
+		if (mapped)
+			spin_unlock(&page->mapping->private_lock);
+
+		/* One for when we alloced the page */
+		page_cache_release(page);
 	} while (index != 0);
 }
 
@@ -4870,6 +4871,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 				mark_extent_buffer_accessed(exists, p);
 				goto free_eb;
 			}
+			exists = NULL;
 
 			/*
 			 * Do this so attach doesn't complain and we need to
@@ -4933,12 +4935,12 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	return eb;
 
 free_eb:
+	WARN_ON(!atomic_dec_and_test(&eb->refs));
 	for (i = 0; i < num_pages; i++) {
 		if (eb->pages[i])
 			unlock_page(eb->pages[i]);
 	}
 
-	WARN_ON(!atomic_dec_and_test(&eb->refs));
 	btrfs_release_extent_buffer(eb);
 	return exists;
 }

fs/btrfs/free-space-cache.c

@@ -1218,7 +1218,7 @@ int btrfs_wait_cache_io(struct btrfs_root *root,
  *
  * This function writes out a free space cache struct to disk for quick recovery
  * on mount.  This will return 0 if it was successfull in writing the cache out,
- * and -1 if it was not.
+ * or an errno if it was not.
  */
 static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 				   struct btrfs_free_space_ctl *ctl,
@@ -1235,12 +1235,12 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	int must_iput = 0;
 
 	if (!i_size_read(inode))
-		return -1;
+		return -EIO;
 
 	WARN_ON(io_ctl->pages);
 	ret = io_ctl_init(io_ctl, inode, root, 1);
 	if (ret)
-		return -1;
+		return ret;
 
 	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA)) {
 		down_write(&block_group->data_rwsem);
@@ -1258,7 +1258,9 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 	}
 
 	/* Lock all pages first so we can lock the extent safely. */
-	io_ctl_prepare_pages(io_ctl, inode, 0);
+	ret = io_ctl_prepare_pages(io_ctl, inode, 0);
+	if (ret)
+		goto out;
 
 	lock_extent_bits(&BTRFS_I(inode)->io_tree, 0, i_size_read(inode) - 1,
 			 0, &cached_state);

fs/btrfs/inode.c

@@ -3632,25 +3632,28 @@ static void btrfs_read_locked_inode(struct inode *inode)
 	BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
 	BTRFS_I(inode)->last_trans = btrfs_inode_transid(leaf, inode_item);
 
+	inode->i_version = btrfs_inode_sequence(leaf, inode_item);
+	inode->i_generation = BTRFS_I(inode)->generation;
+	inode->i_rdev = 0;
+	rdev = btrfs_inode_rdev(leaf, inode_item);
+
+	BTRFS_I(inode)->index_cnt = (u64)-1;
+	BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
+
+cache_index:
 	/*
 	 * If we were modified in the current generation and evicted from memory
 	 * and then re-read we need to do a full sync since we don't have any
 	 * idea about which extents were modified before we were evicted from
 	 * cache.
+	 *
+	 * This is required for both inode re-read from disk and delayed inode
+	 * in delayed_nodes_tree.
 	 */
 	if (BTRFS_I(inode)->last_trans == root->fs_info->generation)
 		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			&BTRFS_I(inode)->runtime_flags);
 
-	inode->i_version = btrfs_inode_sequence(leaf, inode_item);
-	inode->i_generation = BTRFS_I(inode)->generation;
-	inode->i_rdev = 0;
-	rdev = btrfs_inode_rdev(leaf, inode_item);
-
-	BTRFS_I(inode)->index_cnt = (u64)-1;
-	BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
-
-cache_index:
 	path->slots[0]++;
 	if (inode->i_nlink != 1 ||
 	    path->slots[0] >= btrfs_header_nritems(leaf))

fs/btrfs/ioctl.c

@@ -2410,7 +2410,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 			"Attempt to delete subvolume %llu during send",
 			dest->root_key.objectid);
 		err = -EPERM;
-		goto out_dput;
+		goto out_unlock_inode;
 	}
 
 	d_invalidate(dentry);
@@ -2505,6 +2505,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
 		spin_unlock(&dest->root_item_lock);
 	}
+out_unlock_inode:
 	mutex_unlock(&inode->i_mutex);
 	if (!err) {
 		shrink_dcache_sb(root->fs_info->sb);

fs/btrfs/volumes.c

@@ -1058,6 +1058,7 @@ static int contains_pending_extent(struct btrfs_trans_handle *trans,
 	struct extent_map *em;
 	struct list_head *search_list = &trans->transaction->pending_chunks;
 	int ret = 0;
+	u64 physical_start = *start;
 
 again:
 	list_for_each_entry(em, search_list, list) {
@@ -1068,9 +1069,9 @@ static int contains_pending_extent(struct btrfs_trans_handle *trans,
 		for (i = 0; i < map->num_stripes; i++) {
 			if (map->stripes[i].dev != device)
 				continue;
-			if (map->stripes[i].physical >= *start + len ||
+			if (map->stripes[i].physical >= physical_start + len ||
 			    map->stripes[i].physical + em->orig_block_len <=
-			    *start)
+			    physical_start)
 				continue;
 			*start = map->stripes[i].physical +
 				em->orig_block_len;
@@ -1193,8 +1194,14 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans,
 			 */
 			if (contains_pending_extent(trans, device,
 						    &search_start,
-						    hole_size))
-				hole_size = 0;
+						    hole_size)) {
+				if (key.offset >= search_start) {
+					hole_size = key.offset - search_start;
+				} else {
+					WARN_ON_ONCE(1);
+					hole_size = 0;
+				}
+			}
 
 			if (hole_size > max_hole_size) {
 				max_hole_start = search_start;