On Tue, Aug 19, 2025 at 8:40 PM Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>
> On Tue, Aug 19, 2025 at 09:58:31AM +0800, Menglong Dong wrote:
>
> > The "struct rq" is not available in include/linux/sched.h, so we can't
> > access the "runqueues" with this_cpu_ptr(), as the compilation will fail
> > in this_cpu_ptr() -> raw_cpu_ptr() -> __verify_pcpu_ptr():
> > typeof((ptr) + 0)
> >
> > So we introduce the this_rq_raw() and access the runqueues with
> > arch_raw_cpu_ptr() directly.
>
> ^ That, wants to be a comment near here:
>
> > @@ -2312,4 +2315,78 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo
> > #define alloc_tag_restore(_tag, _old) do {} while (0)
> > #endif
> >
> > +#ifndef COMPILE_OFFSETS
> > +
> > +extern void __migrate_enable(void);
> > +
> > +struct rq;
> > +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
> > +
> > +#ifdef CONFIG_SMP
> > +#define this_rq_raw() arch_raw_cpu_ptr(&runqueues)
> > +#else
> > +#define this_rq_raw() PERCPU_PTR(&runqueues)
> > +#endif
>
> Because that arch_ thing really is weird.
OK! I'll comment on this part.
>
> > + (*(unsigned int *)((void *)this_rq_raw() + RQ_nr_pinned))--;
> > + (*(unsigned int *)((void *)this_rq_raw() + RQ_nr_pinned))++;
>
> And since you did a macro anyway, why not fold that magic in there,
> instead of duplicating it?
>
> #define __this_rq_raw() ((void *)arch_raw_cpu_ptr(&runqueues))
> #define this_rq_pinned() (*(unsigned int *)(__this_rq_raw() + RQ_nr_pinned))
>
> this_rq_pinned()--;
> this_rq_pinned()++;
>
> is nicer, no?
Yeah, much better!
