Re: [PATCH] perf/x86/intel: ignore CondChgd bit to avoid false NMI handling

From: Peter Zijlstra
Date: Wed Jun 11 2014 - 07:54:25 EST


On Wed, Jun 11, 2014 at 10:54:48AM +0200, Peter Zijlstra wrote:
> > I'm not sure about exact behavior of CondChgd bit, in particular when
> > this bit is set. Although I read Intel System Programmer's Manual to
> > figure out but I have yet completed that. At least, I think ignoring
> > CondChgd bit should be enough for NMI watchdog perspective.
>
> So yes, the SDM lists the bit as existing but never once mentions it
> outside of that, and its been doing that at least back to 2008.
>
> Ooh, I found it:
>
> "The IA32_PERF_GLOBAL_STATUS MSR also provides a âsticky bitâ to
> indicate changes to the state of performance monitoring hardware (see
> Figure 18-29)."
>
> Which is of course completely useless, not to mention inconsistent with
> the later CondChgd name.
>
> HPA, can you explain wtf that bit does and why hatayama-san's ivb feels
> like having that set on boot?

Matt found in the MSR listing for GLOBAL_STATUS:

63 CondChg: status bits of this register has changed. If CPUID.0AH: EAX[7:0] > 0

Which brings us to a grand total of 3 different names for this bit.

If it indeed does what it says on the tin, set every time the status
changes its like the most useless bit ever and I wonder why people
bothered to spend silicon on it.

In any case, the proposed patch seems fine, just needs a better
changelog.

Attachment: pgpOqPm5m4cYz.pgp
Description: PGP signature