linux-kernel - Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue

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]

Message-ID: <4E30327C.5020509@redhat.com>
Date:	Wed, 27 Jul 2011 18:45:00 +0300
From:	Avi Kivity <avi@...hat.com>
To:	Borislav Petkov <bp@...64.org>
CC:	Ingo Molnar <mingo@...e.hu>,
	"Przywara, Andre" <Andre.Przywara@....com>,
	"H. Peter Anvin" <hpa@...or.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	LKML <linux-kernel@...r.kernel.org>,
	"Pohlack, Martin" <Martin.Pohlack@....com>
Subject: Re: [PATCH] x86, AMD: Correct F15h IC aliasing issue

On 07/27/2011 06:37 PM, Borislav Petkov wrote:
> On Wed, Jul 27, 2011 at 05:30:56AM -0400, Avi Kivity wrote:
> >  On 07/27/2011 09:59 AM, Ingo Molnar wrote:
> >  >  >
> >  >  >   Yeah, actually the idea is to patch the kernel only this one time
> >  >  >   and never ever be needing to do this for future CPUs, for this
> >  >  >   matter.
> >  >
> >  >  But the check you have added turns this workaround on for all family
> >  >  0x15 CPUs. If a family 0x15 CPU is built with a larger or more
> >  >  associative cache, one that does not need the workaround, we would
> >  >  still turn on the workaround.
> >
> >  Similarly, if family 0x21 CPUs have a similar arrangement (with
> >  identical or different cache sizes and associativity) the hardcoded
> >  check will fail.
>
> So, in short, I$ design is the same for all F15h processors so a family
> 0x15 check suffices here.

What about F21h processors?  I see you're not checking them.

Is there any reason the check should not be made based on topology?

-- 
error compiling committee.c: too many arguments to function

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/