linux-kernel - Re: [PATCH] x86/cpuid: expose AVX512_4VNNIW and AVX512

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: <425702906.9319122.1477743677017.JavaMail.zimbra@redhat.com>
Date:   Sat, 29 Oct 2016 08:21:17 -0400 (EDT)
From:   Paolo Bonzini <pbonzini@...hat.com>
To:     Borislav Petkov <bp@...en8.de>
Cc:     Piotr Luc <Piotr.Luc@...el.com>, kvm@...r.kernel.org,
        he chen <he.chen@...ux.intel.com>,
        linux-kernel@...r.kernel.org, tglx@...utronix.de, x86@...nel.org,
        hpa@...or.com, mingo@...hat.com, Luwei Kang <luwei.kang@...el.com>,
        rkrcmar@...hat.com
Subject: Re: [PATCH] x86/cpuid: expose AVX512_4VNNIW and AVX512_4FMAPS
 features to kvm guest



----- Original Message -----
> From: "Borislav Petkov" <bp@...en8.de>
> To: "Paolo Bonzini" <pbonzini@...hat.com>
> Cc: "Piotr Luc" <Piotr.Luc@...el.com>, kvm@...r.kernel.org, "he chen" <he.chen@...ux.intel.com>,
> linux-kernel@...r.kernel.org, tglx@...utronix.de, x86@...nel.org, hpa@...or.com, mingo@...hat.com, "Luwei Kang"
> <luwei.kang@...el.com>, rkrcmar@...hat.com
> Sent: Friday, October 28, 2016 2:21:23 PM
> Subject: Re: [PATCH] x86/cpuid: expose AVX512_4VNNIW and AVX512_4FMAPS features to kvm guest
> 
> On Fri, Oct 28, 2016 at 02:07:21PM +0200, Paolo Bonzini wrote:
> > cpuid_count_edx would be just
> > 
> > static inline unsigned int cpuid_count_edx(unsigned op, unsigned count)
> > {
> >         unsigned int eax, ebx, ecx, edx;
> > 
> >         cpuid_count(op, count, &eax, &ebx, &ecx, &edx);
> > 
> >         return edx;
> > }
> 
> Even better.
> 
> But shouldn't this be hiding unimplemented CPUID bits from the guest?

Currently none of the bits in CPUID[7,0].edx is ever masked by the host, so
this would be enough.  If we ever need to do some masking, I guess I'll
practice my puss-in-boots look and submit a patch to add CPUID[7,0] back
as a separate cpufeature entr.

Paolo