Re: [PATCH 0/8] KVM updates for 2.6.20-rc2

[Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>]

Ingo Molnar wrote:
> * Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org> wrote:
>
>   
>>> hm. Could you try to just do a vmresume nevertheless - maybe it works 
>>> but is undocumented?
>>>       
>> I'd hate to do that.  There are at least three implementations of VT 
>> (PD, Core, Core2) and maybe more when steppings and microcode updates 
>> are considered.  Not to mention having kvm fail when a new cpu is 
>> introduced is not a pleasant scenario.
>>     
>
> lets check whether it's even possible ... Then we could ask Intel to 
> clarify their position on this. I can see no real reason why a vmclear 
> should really make it impossible to re-use the already loaded context 
> data /on the same CPU/. And that is the important case. When we migrate 
> to another CPU we have to do a VMLAUNCH anyway, upon the first execution 
> of that context.
>
>   

There's a documented error number, 5, for "VMRESUME with non-launched vmcs".

Furthermore, I checked, and it indeed doesn't work.


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


-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV