Messages in this thread |  | | Date | Sat, 29 Oct 2016 08:21:17 -0400 (EDT) | From | Paolo Bonzini <> | Subject | Re: [PATCH] x86/cpuid: expose AVX512_4VNNIW and AVX512_4FMAPS features to kvm guest |
| |
----- Original Message ----- > From: "Borislav Petkov" <bp@alien8.de> > To: "Paolo Bonzini" <pbonzini@redhat.com> > Cc: "Piotr Luc" <Piotr.Luc@intel.com>, kvm@vger.kernel.org, "he chen" <he.chen@linux.intel.com>, > linux-kernel@vger.kernel.org, tglx@linutronix.de, x86@kernel.org, hpa@zytor.com, mingo@redhat.com, "Luwei Kang" > <luwei.kang@intel.com>, rkrcmar@redhat.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
|  |