On Fri, Apr 11, 2025 at 12:51:10PM -0700, Caleb Sander Mateos wrote: > On Fri, Apr 11, 2025 at 12:56 AM Ming Lei <ming.lei@xxxxxxxxxx> wrote: > > > > On Tue, Apr 08, 2025 at 08:49:54PM -0600, Caleb Sander Mateos wrote: > > > The ublk driver calls blk_mq_tag_to_rq() in several places. > > > blk_mq_tag_to_rq() tolerates an invalid tag for the tagset, checking it > > > against the number of tags and returning NULL if it is out of bounds. > > > But all the calls from the ublk driver have already verified the tag > > > against the ublk queue's queue depth. In ublk_commit_completion(), > > > ublk_handle_need_get_data(), and case UBLK_IO_COMMIT_AND_FETCH_REQ, the > > > tag has already been checked in __ublk_ch_uring_cmd(). In > > > ublk_abort_queue(), the loop bounds the tag by the queue depth. In > > > __ublk_check_and_get_req(), the tag has already been checked in > > > __ublk_ch_uring_cmd(), in the case of ublk_register_io_buf(), or in > > > ublk_check_and_get_req(). > > > > > > So just index the tagset's rqs array directly in the ublk driver. > > > Convert the tags to unsigned, as blk_mq_tag_to_rq() does. > > > > If blk_mq_tag_to_rq() turns out to be not efficient enough, we can kill it > > in fast path by storing it in ublk_io and sharing space with 'struct io_uring_cmd *', > > since the two's lifetime isn't overlapped basically. > > I agree it would be nice to just store a pointer from in struct > ublk_io to its current struct request. I guess we would set it in > ubq_complete_io_cmd() and clear it in ublk_commit_completion() > (matching when UBLK_IO_FLAG_OWNED_BY_SRV is set), as well as in > ublk_timeout() for UBLK_F_UNPRIVILEGED_DEV? > > I'm not sure it is possible to overlap the fields, though. When using > UBLK_U_IO_NEED_GET_DATA, the cmd field is overwritten with the a > pointer to the UBLK_U_IO_NEED_GET_DATA command, but the req would need Both UBLK_U_IO_NEED_GET_DATA & UBLK_IO_COMMIT_AND_FETCH_REQ share same usage on uring_cmd/request actually. Especially for UBLK_U_IO_NEED_GET_DATA, the uring cmd pointer needn't to be stored in ublk_io. Or just keep to use blk_mq_tag_to_rq() simply for it only. > to be recorded earlier upon completion of the > UBLK_U_IO_(COMMIT_AND_)FETCH_REQ command. Each one can be moved in local variable first, then store it. If we do this way, helper can be added for set/get cmd/req from ublk_io, then the implementation can be reliable & readable. > Would you be okay with 2 separate fields? Yeah, I think it is fine to do it first. Thanks, Ming
