On 2/11/20 2:13 PM, Keith Busch wrote: > I must be missing something: md's make_request_fn always returns > BLK_QC_T_NONE for the cookie, and that couldn't get past blk_poll's > blk_qc_t_valid(cookie) check. How does the initial blk_poll() caller get > a valid cookie for an md backing device's request_queue? And how is the > same cookie valid for more than one request_queue? That's true md_make_request() always returns BLK_QC_T_NONE. md_make_request() recursively calls generic_make_request() for the underlying device (e.g. nvme). That block io request directed to member disk is added into bio_list and is processed later by top level generic_make_request(). generic_make_request() returns cookie that is returned by blk_mq_make_request(). That cookie is later used to poll for completion.
