On Fri, Jun 28, 2024 at 6:35 PM Tejun Heo <tj@xxxxxxxxxx> wrote: > > Hello, Andrii. > > On Fri, Jun 28, 2024 at 04:56:55PM -0700, Andrii Nakryiko wrote: > > > Just a bit of addition and a question. scx_bpf_consume_task() is maybe named > > > too generically and I have a hard time imagining it being useful outside > > > iteration loop. So, it does work out kinda neatly if we can tie the whole > > > thing (DSQ lookup, barrier seq) to the iterator. > > > > > > The reason why this becomes nasty is because I can't pass the pointer to the > > > iterator to a kfunc, so maybe allowing that can be a solution here too? > > > > Sure, if that's the best way to go about this. > > If we decide to go this way, how difficult would it be to change the > verifier to allow this? Shouldn't be too difficult, but we'll know for sure when we start implementing this, of course. > > BTW, as none of the practical schedulers use consume_task() yet, I can skip > this for now. I'll post an updated patches for the iterator itself. We can > decide what to do with consume_task() later. > Sounds good. > Thanks. > > -- > tejun
