[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <f519dabb-2cce-711f-3fea-ccb756a0b73c@linux.intel.com>
Date: Wed, 22 Jun 2022 15:32:42 -0400
From: "Liang, Kan" <kan.liang@...ux.intel.com>
To: Dave Hansen <dave.hansen@...el.com>,
Maxim Levitsky <mlevitsk@...hat.com>,
linux-kernel@...r.kernel.org
Cc: "Chang S. Bae" <chang.seok.bae@...el.com>,
Jiri Olsa <jolsa@...nel.org>, linux-perf-users@...r.kernel.org,
Peter Zijlstra <peterz@...radead.org>,
"H. Peter Anvin" <hpa@...or.com>,
"David S. Miller" <davem@...emloft.net>,
Borislav Petkov <bp@...en8.de>,
Kees Cook <keescook@...omium.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Namhyung Kim <namhyung@...nel.org>,
Tim Chen <tim.c.chen@...ux.intel.com>,
Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>,
Herbert Xu <herbert@...dor.apana.org.au>,
Dave Hansen <dave.hansen@...ux.intel.com>,
"maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)" <x86@...nel.org>,
Jane Malalane <jane.malalane@...rix.com>,
Tony Luck <tony.luck@...el.com>,
Ingo Molnar <mingo@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
"open list:CRYPTO API" <linux-crypto@...r.kernel.org>,
Paolo Bonzini <pbonzini@...hat.com>
Subject: Re: [PATCH 1/4] perf/x86/intel/lbr: use setup_clear_cpu_cap instead
of clear_cpu_cap
On 6/22/2022 2:57 PM, Liang, Kan wrote:
>
>
> On 6/22/2022 10:58 AM, Dave Hansen wrote:
>> On 6/22/22 07:48, Maxim Levitsky wrote:
>>> clear_cpu_cap(&boot_cpu_data) is very similar to setup_clear_cpu_cap
>>> except that the latter also sets a bit in 'cpu_caps_cleared' which
>>> later clears the same cap in secondary cpus, which is likely
>>> what is meant here.
>>>
>>> Signed-off-by: Maxim Levitsky <mlevitsk@...hat.com>
>>
>> Seems like a:
>>
>> Fixes: 47125db27e47 ("perf/x86/intel/lbr: Support Architectural LBR")
>>
>> would be in order.
>>
>> Kan, does this change look right to you?
>
> For the current implementation, the Arch LBR feature should be either
> supported by all the CPUs or disabled on all the CPUs. It cannot be only
> enabled for partial CPUs, even in a hybrid platform.
> So the current code only check the boot CPU via static_cpu_has().
>
> Ideally, Yes, I think it may be better to clear the bit for all CPUs,
> which makes the capability consistent among CPUs.
>
Reviewed-by: Kan Liang <kan.liang@...ux.intel.com>
Thanks,
Kan
> Thanks,
> Kan
>>
>>> arch/x86/events/intel/lbr.c | 2 +-
>>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>>
>>> diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
>>> index 13179f31fe10fa..b08715172309a7 100644
>>> --- a/arch/x86/events/intel/lbr.c
>>> +++ b/arch/x86/events/intel/lbr.c
>>> @@ -1860,7 +1860,7 @@ void __init intel_pmu_arch_lbr_init(void)
>>> return;
>>> clear_arch_lbr:
>>> - clear_cpu_cap(&boot_cpu_data, X86_FEATURE_ARCH_LBR);
>>> + setup_clear_cpu_cap(X86_FEATURE_ARCH_LBR);
>>> }
>>> /**
>>
Powered by blists - more mailing lists