Re: [PATCH 4/4] [x86] perf: fix accidentally ack'ing a second eventon intel perf counter

[Stephane Eranian]

On Fri, Sep 3, 2010 at 4:03 PM, Don Zickus <dzickus@xxxxxxxxxx> wrote:
> On Fri, Sep 03, 2010 at 01:02:49PM +0200, Stephane Eranian wrote:
>> Here is an example of what I gathered on a Westmere:
>>
>> This is coming into the interrupt handler:
>> - status  = overflow status coming from GLOBAL_OVF_STATUS
>> - status2 = inspection of the counters
>> - act = cpuc->active_mask[0]
>>
>> In case both status don't match, I dump the state of the active events
>> incl. the counter values(val).
>>
>> [ Â822.813808] CPU2 irqin status=0x6 status2=0x4 act=0x7
>> [ Â822.813818] CPU2 cfg=0x13003c idx=0 sel=53003c val=ffffa833f298
>> [ Â822.813821] CPU2 cfg=0x12003c idx=1 sel=52003c val=fffffe130229
>> [ Â822.813823] CPU2 cfg=0x11003c idx=2 sel=51003c val=5e9
>>
>> Here only counter2 has overflowed, yet the handler will also process counter1
>> which is wrong.
>
> Hmm, the test case I used was 'perf top'. ÂThis was only using perf
> counter0. ÂSo I am not sure, at least in my case, it was a stale event.
> Though I don't think I remember checking the status immediately after
> acking it just to verify the ack worked.

I am not acking it right away, this is still without patch 4/4. I am trying to
understand how we can get to this situation.

>
> I'll poke some more on my machine today.
>
> Cheers,
> Don
>
--
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/