Re: [RFC PATCH v4 13/16] io_uring: add io_recvzc request

[Jens Axboe <axboe@kernel.dk>]

(Apparently this went out without my comments attached, only one thing
worth noting so repeating that)

>>> @@ -695,7 +701,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
>>>       unsigned int cflags;
>>>         cflags = io_put_kbuf(req, issue_flags);
>>> -    if (msg->msg_inq && msg->msg_inq != -1)
>>> +    if (msg && msg->msg_inq && msg->msg_inq != -1)
>>>           cflags |= IORING_CQE_F_SOCK_NONEMPTY;
>>>         if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
>>> @@ -723,7 +729,7 @@ static inline bool io_recv_finish(struct io_kiocb *req, int *ret,
>>>               goto enobufs;
>>>             /* Known not-empty or unknown state, retry */
>>> -        if (cflags & IORING_CQE_F_SOCK_NONEMPTY || msg->msg_inq == -1) {
>>> +        if (cflags & IORING_CQE_F_SOCK_NONEMPTY || (msg && msg->msg_inq == -1)) {
>>>               if (sr->nr_multishot_loops++ < MULTISHOT_MAX_RETRY)
>>>                   return false;
>>>               /* mshot retries exceeded, force a requeue */
>>
>> Maybe refactor this a bit so that you don't need to add these NULL
>> checks? That seems pretty fragile, hard to read, and should be doable
>> without extra checks.
> 
> That chunk can be completely thrown away, we're not using
> io_recv_finish() here anymore

OK good!

>>> @@ -1053,6 +1058,85 @@ struct io_zc_rx_ifq *io_zc_verify_sock(struct io_kiocb *req,
>>>       return ifq;
>>>   }
>>>   +int io_recvzc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
>>> +{
>>> +    struct io_recvzc *zc = io_kiocb_to_cmd(req, struct io_recvzc);
>>> +
>>> +    /* non-iopoll defer_taskrun only */
>>> +    if (!req->ctx->task_complete)
>>> +        return -EINVAL;
>>
>> What's the reasoning behind this?
> 
> CQ locking, see the comment a couple lines below

My question here was more towards "is this something we want to do".
Maybe this is just a temporary work-around and it's nothing to discuss,
but I'm not sure we want to have opcodes only work on certain ring
setups.


-- 
Jens Axboe