Re: [PATCH 1/1] io_uring/poll: fix POLLERR handling

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

On 7/15/25 20:12, Jens Axboe wrote:
...>>> How is it related to POLLIN?
>>
>> Gah POLLOUT of course.
>>
>>>> should let it go through. And there should not be a need to call
>>>> vfs_poll() unless ->in_progress is already set. Something ala:
>>>
>>> In any case, v1 doesn't seem to work, so needs to be done differently.
>>
>> RIght, that's what I aluded to in the "improved/fixed" further. FWIW, I
>> did dig out the old test case I wrote for this and added it to liburing
>> as well. So should have somewhat better coverage now.
> 
> How about:
> 
> if (connect->in_progress) {
> 	struct poll_table_struct pt = { ._key = EPOLLERR };
> 
> 	if (vfs_poll(req->file, &pt) & EPOLLERR)
> 		goto get_sock_err;
> }
>   
> with get_sock_err being where we do sock_error()?

Seems to work. sock_error() can also race, but I don't want to
waste any more time on it.

-- 
Pavel Begunkov