Re: [RFC][PATCH 1/4] sched: Force the address order of each sched class descriptor

[Rasmus Villemoes]

On 20/12/2019 11.00, Peter Zijlstra wrote:
> On Fri, Dec 20, 2019 at 09:52:37AM +0100, Rasmus Villemoes wrote:
>> On 19/12/2019 22.44, Steven Rostedt wrote:
>>> From: "Steven Rostedt (VMware)" <rostedt@xxxxxxxxxxx>
>>>
>>> In order to make a micro optimization in pick_next_task(), the order of the
>>> sched class descriptor address must be in the same order as their priority
>>> to each other. That is:
>>>
>>>  &idle_sched_class < &fair_sched_class < &rt_sched_class <
>>>  &dl_sched_class < &stop_sched_class
>>>
>>> In order to guarantee this order of the sched class descriptors, add each
>>> one into their own data section and force the order in the linker script.
>>
>> I think it would make the code simpler if one reverses these, see other
>> reply.
> 
> I started out agreeing, because of that mess around STOP_SCHED_CLASS and
> that horrid BEFORE_CRUD thing.
> 
> Then, when I fixed it all up, I saw what it did to Kyrill's patch (#4)
> and that ends up looking like:
> 
> -       if (likely((prev->sched_class == &idle_sched_class ||
> -                   prev->sched_class == &fair_sched_class) &&
> +       if (likely(prev->sched_class >= &fair_sched_class &&
> 
> And that's just weird.

I kind of agree, but if one can come up with good enough macro names, I
think all that comparison logic should be in helpers either way the
array is laid out. Something like

#define sched_class_lower_eq [something] /* perhaps comment on the array
order */
sched_class_lower_eq(prev->sched_class, &fair_sched_class)

> Then I had a better look and now...
> 
>>> +/*
>>> + * The order of the sched class addresses are important, as they are
>>> + * used to determine the order of the priority of each sched class in
>>> + * relation to each other.
>>> + */
>>> +#define SCHED_DATA				\
>>> +	*(__idle_sched_class)			\
>>> +	*(__fair_sched_class)			\
>>> +	*(__rt_sched_class)			\
>>> +	*(__dl_sched_class)			\
>>> +	STOP_SCHED_CLASS
> 
> I'm confused, why does that STOP_SCHED_CLASS need magic here at all?
> Doesn't the linker deal with empty sections already by making them 0
> sized?

Yes, but dropping the STOP_SCHED_CLASS define doesn't prevent one from
needing some ifdeffery to define highest_sched_class if they are laid
out in (higher sched class <-> higher address) order.

Rasmus