Re: [PATCH 3/3] io_uring: add IORING_CQE_F_POLLED flag

[Pavel Begunkov <asml.silence@gmail.com>]

On 7/12/25 12:34, Pavel Begunkov wrote:
> On 7/12/25 00:59, Jens Axboe wrote:
> ...>       /*
>>        * If multishot has already posted deferred completions, ensure that
>>        * those are flushed first before posting this one. If not, CQEs
>> diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
>> index dc17162e7af1..d837e02d26b2 100644
>> --- a/io_uring/io_uring.h
>> +++ b/io_uring/io_uring.h
>> @@ -235,6 +235,8 @@ static inline void req_set_fail(struct io_kiocb *req)
>>   static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
>>   {
>> +    if (req->flags & REQ_F_POLL_WAKE)
>> +        cflags |= IORING_CQE_F_POLLED;
> 
> Can you avoid introducing this new uapi (and overhead) for requests that
> don't care about it please? It's useless for multishots, and the only
> real potential use case is send requests.

Another thought, I think the userspace can already easily infer
information similar to what this flag gives. E.g. peek at CQEs
right after submission and mark the inverse of the flag. The
actual impl can be made nicer than that.

-- 
Pavel Begunkov