Re: [regression 2.6.39-rc2][bisected] "perf, x86: P4 PMU - Read properMSR register to catch" and NMIs

From: Cyrill Gorcunov
Date: Wed Apr 13 2011 - 17:25:58 EST

On 04/14/2011 01:22 AM, Don Zickus wrote:
> On Thu, Apr 14, 2011 at 12:43:47AM +0400, Cyrill Gorcunov wrote:
>> On 04/14/2011 12:35 AM, Shaun Ruffell wrote:
>> ...
>>> I had the first version of the patch running the test builds all night without
>>> any NMIs. I installed this one and ran it through the case where I would
>>> reliably get early NMIs and it still no NMIs.
>>> So for v2:
>>> Tested-by: Shaun Ruffell <sruffell@xxxxxxxxxx>
>>> Thanks!
>> Thanks a huge Shaun. The thing is (if only I don't miss something) at moment there is
>> no much difference in which patch to pick up. But as only kgdb dives in or any other
>> subsystem (which say would use same manner of nmi delivery) we might be unmasking
>> lvt entry even if nothing were handled at all, so I bias to a second version.
> I agree with the second version. Initially I wanted to enable it in the
> case of the !handled path. But your reasoning makes sense to me, don't
> enable it in the !handled case because you might accidentally do something
> bad.
> Cheers,
> Don

OK, thanks for review! Shaun please continue testing it, if all will be fine until tomorrow
we will ask Ingo to pick it up then. Sounds OK for everyone?

(CC'ed a couple of people which were involved into this code snippet)
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at