Re: tip: demise of tsk_cpus_allowed() and tsk_nr_cpus_allowed()

[Peter Zijlstra <peterz@infradead.org>]

On Thu, Feb 09, 2017 at 07:57:27AM +0100, Ingo Molnar wrote:
> And -rt would do something like this in migration_disable()/enable():
>  
> 	t->cpus_ptr = &cpumask_of(task_cpu(p));
> 	t->nr_cpus = 1;
> 
> 	...
> 
> 	t->cpus_ptr = &t->cpus_mask;
> 	t->nr_cpus = cpumask_weight(t->cpus_mask);
> 
> In addition to that we could cache the weight of the cpumask as an additional 
> optimization:
> 
> 	t->cpus_ptr = &t->cpus_mask;
> 	t->nr_cpus = t->cpus_mask_weight;
> 
> It all looks like a pretty natural construct to me. The migration_disabled() flag 
> spreads almost a hundred branches all across the scheduler.

Could work I suppose. But please then implement this instead of ripping
out the current thing, because taking out the accessors leaves RT in a
bind without recourse.