Re: [Xen-devel] [Patch 2/4] Refining Xsave/Xrestore support

["Jan Beulich" <JBeulich@xxxxxxxxxx>]

>>> On 28.10.10 at 04:57, Haitao Shan <maillists.shan@xxxxxxxxx> wrote:
> My approach is based an old PV-OPS kernel source. Kernel tries to set
> CR4.OSXSAVE and read it back to determine whether Xsave is actually
> available.

Hmm, in our kernels we check the OSXSAVE feature bit instead,
expecting (just like for FXSAVE) the hypervisor to enable the bit
in CR4 when it supports the feature.

I think a mechanism needs to be found in the hypervisor that
accommodates both current pv-ops and current forward port
kernels' behaviors.

Jan

> 2010/10/28 Jeremy Fitzhardinge <jeremy@xxxxxxxx>:
>>  On 10/27/2010 12:04 AM, Haitao Shan wrote:
>>> Hi, Keir,
>>>
>>> This is patch #2, which adds PV guest Xsave support.
>>
>> How does a PV guest know whether Xsave support is available?  Previous
>> versions of Xen left the xsave cpu feature flag set even though xsave
>> wasn't usable by the domain, so I had to forceably mask it from the
>> cpuid features within the domain.  Given that a PV domain can't rely on
>> X86_FEATURE_XSAVE, how can it tell that the feature is actually usable?
>>
>> Thanks,
>>    J
>>
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@xxxxxxxxxxxxxxxxxxx 
> http://lists.xensource.com/xen-devel 




_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel