Re: [PATCH v10 0/4] BPF controlled io_uring

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

On 3/9/26 15:02, Caleb Sander Mateos wrote:
> On Mon, Mar 9, 2026 at 6:24 AM Pavel Begunkov <asml.silence@gmail.com> wrote:
...
>>> - Smarter polling. Napi polling is performed only once per syscall
>>>     and then it switches to waiting. We can do smarter and intermix
>>>     polling with waiting using the hook.
>>
>> Any comments for the patch set?
> 
> I'm not opposed to this feature, but I agree with Ming that it seems
> largely orthogonal to his patchset allowing BPF programs to access
> io_uring registered buffers[1]. This patchset doesn't provide any

The idea of giving BPF access to registered buffers is largely
orthogonal to underlying ops implementation, I agree.

> kfuncs for interacting with registered buffers, so we would still need
> something like the kfuncs implemented by Ming's patchset to allow BPF
> programs to access registered buffers directly. Although either the

Surely

> ->loop_step() or ->prep()/->issue() interface could allow userspace to
> run a BPF program in the context of the io_uring, I wouldn't be keen
> on reimplementing the entire io_uring_enter() loop logic just to
> intercept a few requests to run BPF programs. 

I don't think some 50 or maybe fewer lines of generic code is that
much of a hassle, I'm thinking about adding it as a library code of
some sort. In either case, I'm not trying to convince you to do more
work.

-- 
Pavel Begunkov