RE: [Xen-ia64-devel] Time for hybrid virtualization?

["Dong, Eddie" <eddie.dong@xxxxxxxxx>]

tgingold@xxxxxxx wrote:
> Quoting "Dong, Eddie" <eddie.dong@xxxxxxxxx>:
> 
>> tgingold@xxxxxxx wrote:
>>> Quoting "Dong, Eddie" <eddie.dong@xxxxxxxxx>:
>>>> Not sure if anybody ever tried to run Xen/IA64 VMM in Xen/IA64 HVM
>>>> guest? It may not be already there, but looks like not that far.
>>> 
>>> I tried in the past, but it doesn't work out of the box.  You of
>>> course can't run bare Xen within VTi, but a modified version can
>>> run. 
>> 
>> Why?  The goal of hardware virtualization is to provide architecture
>> equavalent virtualization. We may see the gap.
> 
> Xen requires 61 bits of VA, while Vti only provides 60.  That's the

Yes, we met this too yesterday, current Xen/IA64 doesn't check supported
VA address bits # in architecture safe way, it just assume it is 61
bits. 

> main issue my patch addresses.  The other issue is VHPT long format. 

Can u repost it? We need to make Xen/IA64 following SDM.
Yes, LVHPT is another major gap, good catch indeed! 
This is worth to solving, and it should not be a very big effort if we
don't work guest page table. Luckily, today's Xen/IA64 is implementing
 virtual TLB rather than shadow page table which makes it simple, right?

If we really push paravirt_ops or hybrid forward to maintain
backward compatability, this is probably the way we can go.


> Currently Xen/VTi allows it but doesn't use it.  

BTW, in Xen/X86 side, running Xen in X86 HVM is fine. So eventually we
should be able to do that too.

Thx, eddie

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel