Re: [PATCH] perf/x86: enable Intel Cedarview Atom suppport

[Stephane Eranian]

On Mon, Aug 20, 2012 at 11:41 AM, Andi Kleen <andi@xxxxxxxxxxxxxx> wrote:
>> diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
>> index 7f2739e..0d3d63a 100644
>> --- a/arch/x86/kernel/cpu/perf_event_intel.c
>> +++ b/arch/x86/kernel/cpu/perf_event_intel.c
>> @@ -2008,6 +2008,7 @@ __init int intel_pmu_init(void)
>>               break;
>>
>>       case 28: /* Atom */
>> +     case 54: /* Cedariew */
>
> Ack. We currently miss some more 32nm Atoms too, will send patches soon.
>
>>               memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
>>                      sizeof(hw_cache_event_ids));
>>
>> diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
>> index 520b426..da02e9c 100644
>> --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
>> +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
>> @@ -686,7 +686,8 @@ void intel_pmu_lbr_init_atom(void)
>>        * to have an operational LBR which can freeze
>>        * on PMU interrupt
>>        */
>> -     if (boot_cpu_data.x86_mask < 10) {
>> +     if (boot_cpu_data.x86_model == 28
>> +         && boot_cpu_data.x86_mask < 10) {
>
> Is that correct?
>
Yes, had to do that to re-enable LBR on Cedarview.
The < 10 is a trick to disable LBR on very old Atom (prior to N4xx generation).
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/