nvme-tcp will opportunistically try a network send directly from
.queue_rq(), but always with MSG_DONTWAIT, so that is not a problem.
nbd though can block in .queue_rq() with blocking network sends, however
afaict nbd allocates a tagset per nbd_device, and also a request_queue
per device, so its effectively the same if the srcu is in the tagset or
in the request_queue.
Yes, the only multiple request_queue per tag_set cases right now
are nvme-tcp and mmc. There have been patches from iSCSI, but they
seem to be stuck.
iscsi defers network sends to a workqueue anyways, and no scsi lld sets
BLK_MQ_F_BLOCKING.
