Our test robot reported a warning for refcount_dec trying to decrease
value '0'. The reason is that blk_mq_dispatch_rq_list() try to complete
the failed request from nbd driver, while the request have finished in
nbd timeout handle function. The race as following:
CPU1 CPU2
//req->ref = 1
blk_mq_dispatch_rq_list
nbd_queue_rq
nbd_handle_cmd
blk_mq_start_request
blk_mq_check_expired
//req->ref = 2
blk_mq_rq_timed_out
nbd_xmit_timeout
blk_mq_complete_request
//req->ref = 1
refcount_dec_and_test(&req->ref)
refcount_dec_and_test(&req->ref)
//req->ref = 0
__blk_mq_free_request(req)
ret = BLK_STS_IOERR
blk_mq_end_request
// req->ref = 0, req have been free
refcount_dec_and_test(&rq->ref)
In fact, the bug also have been reported by syzbot:
https://lkml.org/lkml/2018/12/5/1308
Since the request have been freed by timeout handle, it can be reused
by others. Then, blk_mq_end_request() may get the re-initialized request
and free it, which is unexpected.
To fix the problem, we move blk_mq_start_request() down until the driver
will handle the request actully. If .queue_rq return something error in
preparation phase, timeout handle may don't need. Thus, moving start
request down may be more reasonable. Then, nbd_queue_rq() will not return
BLK_STS_IOERR after starting request.
Reported-by: Hulk Robot <hulkci@huawei.com>
Signed-off-by: Yufen Yu <yuyufen@huawei.com>
---
drivers/block/nbd.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 78181908f0df..5256e9d02a03 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -541,6 +541,8 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index)
return -EIO;
}
+ blk_mq_start_request(req);
+
if (req->cmd_flags & REQ_FUA)
nbd_cmd_flags |= NBD_CMD_FLAG_FUA;
@@ -879,7 +881,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
if (!refcount_inc_not_zero(&nbd->config_refs)) {
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Socks array is empty\n");
- blk_mq_start_request(req);
return -EINVAL;
}
config = nbd->config;
@@ -888,7 +889,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
dev_err_ratelimited(disk_to_dev(nbd->disk),
"Attempted send on invalid socket\n");
nbd_config_put(nbd);
- blk_mq_start_request(req);
return -EINVAL;
}
cmd->status = BLK_STS_OK;
@@ -912,7 +912,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
*/
sock_shutdown(nbd);
nbd_config_put(nbd);
- blk_mq_start_request(req);
return -EIO;
}
goto again;
@@ -923,7 +922,6 @@ static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)
* here so that it gets put _after_ the request that is already on the
* dispatch list.
*/
- blk_mq_start_request(req);
if (unlikely(nsock->pending && nsock->pending != req)) {
nbd_requeue_cmd(cmd);
ret = 0;