Re: [PATCH v3 04/12] x86,fs/resctrl: Program PLZA through kmode arch hooks

[Babu Moger]

Hi Peter,


On 6/11/26 06:44, Peter Newman wrote:
> Hi Babu,
>
> On Thu, May 21, 2026 at 1:09 AM Moger, Babu <bmoger@xxxxxxx> wrote:
> > Hi Tony,
> >
> > On 5/20/2026 5:16 PM, Luck, Tony wrote:
> > > On Wed, May 20, 2026 at 12:49:25PM -0500, Babu Moger wrote:
> > > > Hi Tony,
> > > >
> > > >
> > > > On 5/19/26 15:59, Luck, Tony wrote:
> > > > > On Thu, Apr 30, 2026 at 06:24:49PM -0500, Babu Moger wrote:
> > > > > > +void resctrl_arch_configure_kmode(cpumask_var_t cpu_mask, u32 closid, u32 rmid, bool enable)
> > > > > > +{
> > > > > > +  union msr_pqr_plza_assoc plza = { 0 };
> > > > > > +
> > > > > > +  plza.split.rmid = rmid;
> > > > > > +  plza.split.rmid_en = 1;
> > > > >
> > > > > Shouldn't there be a parameter for the value of rmid_en?
> > > >
> > > >
> > > > I realized that behavior is not required—it was actually due to a mistake in
> > > > my v2 series implementation.
>
> Really? This is in fact the only behavior we wanted:
>
> https://lore.kernel.org/lkml/CABPqkBSq=cgn-am4qorA_VN0vsbpbfDePSi7gubicpROB1=djw@xxxxxxxxxxxxxx/

I have responded to similar comment already.

https://lore.kernel.org/lkml/1d7c79bf-1e40-4db7-8f66-45f234b6d87e@xxxxxxx/

You are right—we should not set rmid_en = 1 in all cases.

For the "inherit_mon" mode, rmid_en will be 0, so the monitoring counts 
will remain unaffected. This represents the generic use case.

For the "assign_mon" mode, rmid_en will be 1. In this case, the kernel 
monitoring counts will be separate from the user’s.

So, we have both the options. I hope this addresses your concerns.

Thanks

Babu