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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Wed, 11 Jun 2014 13:54:13 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	HATAYAMA Daisuke <d.hatayama@...fujitsu.com>
Cc:	acme@...nel.org, mingo@...hat.com, paulus@...ba.org, hpa@...or.com,
	tglx@...utronix.de, x86@...nel.org, linux-kernel@...r.kernel.org,
	matt@...sole-pimps.org
Subject: Re: [PATCH] perf/x86/intel: ignore CondChgd bit to avoid false NMI
 handling

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 ‘sticky bit’ 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.


Content of type "application/pgp-signature" skipped