Commit be23e837 authored by Zhiqiang Liu's avatar Zhiqiang Liu Committed by Jens Axboe

bcache: fix potential deadlock problem in btree_gc_coalesce

coccicheck reports:
  drivers/md//bcache/btree.c:1538:1-7: preceding lock on line 1417

In btree_gc_coalesce func, if the coalescing process fails, we will goto
to out_nocoalesce tag directly without releasing new_nodes[i]->write_lock.
Then, it will cause a deadlock when trying to acquire new_nodes[i]->
write_lock for freeing new_nodes[i] before return.

btree_gc_coalesce func details as follows:
	if alloc new_nodes[i] fails:
		goto out_nocoalesce;
	// obtain new_nodes[i]->write_lock
	mutex_lock(&new_nodes[i]->write_lock)
	// main coalescing process
	for (i = nodes - 1; i > 0; --i)
		[snipped]
		if coalescing process fails:
			// Here, directly goto out_nocoalesce
			 // tag will cause a deadlock
			goto out_nocoalesce;
		[snipped]
	// release new_nodes[i]->write_lock
	mutex_unlock(&new_nodes[i]->write_lock)
	// coalesing succ, return
	return;
out_nocoalesce:
	btree_node_free(new_nodes[i])	// free new_nodes[i]
	// obtain new_nodes[i]->write_lock
	mutex_lock(&new_nodes[i]->write_lock);
	// set flag for reuse
	clear_bit(BTREE_NODE_dirty, &ew_nodes[i]->flags);
	// release new_nodes[i]->write_lock
	mutex_unlock(&new_nodes[i]->write_lock);

To fix the problem, we add a new tag 'out_unlock_nocoalesce' for
releasing new_nodes[i]->write_lock before out_nocoalesce tag. If
coalescing process fails, we will go to out_unlock_nocoalesce tag
for releasing new_nodes[i]->write_lock before free new_nodes[i] in
out_nocoalesce tag.

(Coly Li helps to clean up commit log format.)

Fixes: 2a285686 ("bcache: btree locking rework")
Signed-off-by: default avatarZhiqiang Liu <liuzhiqiang26@huawei.com>
Signed-off-by: default avatarColy Li <colyli@suse.de>
Signed-off-by: default avatarJens Axboe <axboe@kernel.dk>
parent b3a9e3b9
...@@ -1389,7 +1389,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, ...@@ -1389,7 +1389,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
if (__set_blocks(n1, n1->keys + n2->keys, if (__set_blocks(n1, n1->keys + n2->keys,
block_bytes(b->c)) > block_bytes(b->c)) >
btree_blocks(new_nodes[i])) btree_blocks(new_nodes[i]))
goto out_nocoalesce; goto out_unlock_nocoalesce;
keys = n2->keys; keys = n2->keys;
/* Take the key of the node we're getting rid of */ /* Take the key of the node we're getting rid of */
...@@ -1418,7 +1418,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, ...@@ -1418,7 +1418,7 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
if (__bch_keylist_realloc(&keylist, if (__bch_keylist_realloc(&keylist,
bkey_u64s(&new_nodes[i]->key))) bkey_u64s(&new_nodes[i]->key)))
goto out_nocoalesce; goto out_unlock_nocoalesce;
bch_btree_node_write(new_nodes[i], &cl); bch_btree_node_write(new_nodes[i], &cl);
bch_keylist_add(&keylist, &new_nodes[i]->key); bch_keylist_add(&keylist, &new_nodes[i]->key);
...@@ -1464,6 +1464,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op, ...@@ -1464,6 +1464,10 @@ static int btree_gc_coalesce(struct btree *b, struct btree_op *op,
/* Invalidated our iterator */ /* Invalidated our iterator */
return -EINTR; return -EINTR;
out_unlock_nocoalesce:
for (i = 0; i < nodes; i++)
mutex_unlock(&new_nodes[i]->write_lock);
out_nocoalesce: out_nocoalesce:
closure_sync(&cl); closure_sync(&cl);
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment