Re: [PATCH 4/4] perf, x86: Add PERF_COUNT_HW_NMI_WATCHDOG event

[Cyrill Gorcunov]

On 04/25/2011 05:41 PM, Don Zickus wrote:
> On Fri, Apr 22, 2011 at 07:15:12PM +0400, Cyrill Gorcunov wrote:
>> On 04/22/2011 01:45 PM, Peter Zijlstra wrote:
>> ...
>>>
>>> Right, so the idea is that one event (concept) has two (or more)
>>> representations in the config space. And when scheduling the events we
>>> find we have a conflict, we simply try the alternative encoding(s).
>>>
>> ...
>>
>>   Yeah, Peter, I think it's quite possible to use alternative encoding for p4 as well,
>> not sure tho if some "generalized" approach for all perf would be applied to p4 but
>> we can make event "aliases" being per-pmu eventually.
>>
>>   So Ingo, drop this patch then ;)
> 
> Eek, when can you have an alternate patch for this Cyril?  I just want to
> make sure this can still eventually find its way into 2.6.40.
> 
> Cheers,
> Don

  I need kinda aliases for events (or alternative scheme as PeterZ mentions),
Don I'll try to make something tomorrow, ok? With aliases we would not need
to even modify sources outside of p4 pmu which is good i think. I've some spare
bits in low hw:config bits so this aliases could go there as a start.

-- 
    Cyrill
--
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/