Re: [PATCH v2 01/15] perf/x86/lbr: Simplify the exposure check for the LBR_INFO registers

[Like Xu]

On 23/12/2022 1:41 am, Sean Christopherson wrote:
> On Thu, Dec 22, 2022, Like Xu wrote:
> > Hi Peter, would you help apply this one in your tip/perf tree,
> > as it doesn't seem to be closely tied to the KVM changes. Thanks.
> >
> > On 25/11/2022 12:05 pm, Yang Weijiang wrote:
> > > From: Like Xu <like.xu@xxxxxxxxxxxxxxx>
> > >
> > > The x86_pmu.lbr_info is 0 unless explicitly initialized, so there's
> > > no point checking x86_pmu.intel_cap.lbr_format.
> > >
> > > Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> > > Reviewed-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
> > > Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
> > > Signed-off-by: Like Xu <like.xu@xxxxxxxxxxxxxxx>
> > > Signed-off-by: Yang Weijiang <weijiang.yang@xxxxxxxxx>
> > > ---
> > >    arch/x86/events/intel/lbr.c | 4 +---
> > >    1 file changed, 1 insertion(+), 3 deletions(-)
> > >
> > > diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
> > > index 4dbde69c423b..e7caabfa1377 100644
> > > --- a/arch/x86/events/intel/lbr.c
> > > +++ b/arch/x86/events/intel/lbr.c
> > > @@ -1606,12 +1606,10 @@ void __init intel_pmu_arch_lbr_init(void)
> > >     */
> > >    void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
> > >    {
> > > -	int lbr_fmt = x86_pmu.intel_cap.lbr_format;
> > > -
> > >    	lbr->nr = x86_pmu.lbr_nr;
> > >    	lbr->from = x86_pmu.lbr_from;
> > >    	lbr->to = x86_pmu.lbr_to;
> > > -	lbr->info = (lbr_fmt == LBR_FORMAT_INFO) ? x86_pmu.lbr_info : 0;
> > > +	lbr->info = x86_pmu.lbr_info;
>
> This stable-worthy a bug fix, no?  E.g. won't the existing code misreport lbr->info
> if the format is LBR_FORMAT_INFO2?

Sure, we need "Cc: stable@xxxxxxxxxxxxxxx" in order not to lose misprediction 
and cycles
information on the LBR_FORMAT_INFO2 platforms like Goldmont plus.

> > >    }
> > >    EXPORT_SYMBOL_GPL(x86_perf_get_lbr);