Re: [PATCH 3/4] perf, x86: check ucode before disabling PEBS onSandyBridge v3

[Peter Zijlstra]

On Wed, 2012-06-13 at 14:34 -0700, Andi Kleen wrote:
> > Stephane actually wrote:
> > 
> > "Ok, so to close on this, I tried the 6/6/2012 ucode update on a few
> > SNB-EP systems.
> > 
> > I got two answers depending on the stepping:
> > C1 (stepping 6) -> 0x618
> > C2 (stepping 7) -> 0x70c
> > 
> > So we need to check x86_mask for stepping and adjust the value of
> > snb_ucode_rev accordingly for model 45."
> 
> not sure i understood your point? 
> What do you want me to change?
> 
> I check different numbers on the different models.
> 
> FWIW it works on a Sandy Bridge E and I believe I didn't change
> the logic for non E, which Stephane tested.

Is there a ucode revision for C2 higher than 0x618 but lower than
0x70c ? If so, your code is wrong for it would enable PEBS on that chip.
--
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/