On 01/08/16 00:54, Jan Beulich wrote: > >>> On 08.01.16 at 02:15, <haozhong.zh...@intel.com> wrote: > > On 01/07/16 06:53, Jan Beulich wrote: > >> >>> On 30.12.15 at 12:48, <haozhong.zh...@intel.com> wrote: > >> > --- a/xen/arch/x86/hvm/hvm.c > >> > +++ b/xen/arch/x86/hvm/hvm.c > >> > @@ -4605,6 +4605,9 @@ void hvm_cpuid(unsigned int input, unsigned int > >> > *eax, > > unsigned int *ebx, > >> > > >> > if ( !cpu_has_clwb ) > >> > *ebx &= ~cpufeat_mask(X86_FEATURE_CLWB); > >> > + > >> > + if ( !cpu_has_pcommit ) > >> > + *ebx &= ~cpufeat_mask(X86_FEATURE_PCOMMIT); > >> > >> Other than for patch 1, this not only need to stay, but needs to be > >> extended along the lines of X86_FEATURE_MPX handling. > >> > > > > In section "PCOMMIT - Virtualization Support" of Intel Architecture > > Instruction Set Extensions Programming Reference, it says > > > > IA32_VMX_PROCBASED_CTLS2[53] (which enumerates support for the > > 1-setting of “PCOMMIT exiting”) is always the same as > > CPUID.07H:EBX.PCOMMIT[bit 22]. > > > > so checking cpu_has_pcommit is enough here. > > Even if the documentation says so, I think it is appropriate (as > indicated at the very least to match with MPX handling) to add > the check (here or elsewhere), just to make obvious that both > are a prereq. > > Jan
OK, I'll modify in the next version. Haozhong _______________________________________________ Xen-devel mailing list Xen-devel@lists.xen.org http://lists.xen.org/xen-devel
