[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZfmMah58YSyYGywo@gmail.com>
Date: Tue, 19 Mar 2024 14:00:26 +0100
From: Ingo Molnar <mingo@...nel.org>
To: Sandipan Das <sandipan.das@....com>
Cc: linux-perf-users@...r.kernel.org, linux-kernel@...r.kernel.org,
x86@...nel.org, peterz@...radead.org, acme@...nel.org,
namhyung@...nel.org, mark.rutland@....com,
alexander.shishkin@...ux.intel.com, jolsa@...nel.org,
adrian.hunter@...el.com, tglx@...utronix.de, bp@...en8.de,
seanjc@...gle.com, pbonzini@...hat.com, eranian@...gle.com,
irogers@...gle.com, ravi.bangoria@....com, ananth.narayan@....com
Subject: Re: [PATCH v4 1/2] x86/cpufeatures: Add dedicated feature word for
CPUID leaf 0x80000022[EAX]
* Ingo Molnar <mingo@...nel.org> wrote:
> > +/* AMD-defined performance monitoring features, CPUID level 0x80000022 (EAX), word 21 */
> > +#define X86_FEATURE_PERFMON_V2 (21*32+ 0) /* AMD Performance Monitoring Version 2 */
> > +#define X86_FEATURE_AMD_LBR_V2 (21*32+ 1) /* AMD Last Branch Record Extension Version 2 */
>
> Thank you! I presume you tested both patches on the relevant system
> with the X86_FEATURE_AMD_LBR_PMC_FREEZE bug?
Also, Boris reminds me that we really want to do what I suggested
originally and use a new synthethic word here, not a new vendor word, to
keep all the bits better compressed in cpuinfo.x86_capability[] - so one
more iteration will be needed.
Thanks,
Ingo
Powered by blists - more mailing lists