Re: [Xen-devel] [PATCH 13/13] Nested Virtualization: hap-on-hap

[Tim Deegan <Tim.Deegan@xxxxxxxxxx>]

At 16:27 +0000 on 20 Dec (1292862443), Christoph Egger wrote:
> > > An other vcpu is in VMRUN emulation after a nestedp2m is assigned.
> > >    It will VMEXIT with a nested page fault.
> >
> > Why?
> 
> Because the p2m is empty. The MMU can not do a page table walk.
> 
> > > An other vcpu already running l2 guest.
> > >    It will VMEXIT with a nested page fault immediately.
> >
> > Hmm.  It will exit for the TLB shootdown IPI, but I think you need to
> > clear vcpu_nestedhvm(v).nh_p2m on the other vcpu to make sure it doesn't
> > re-enter with the p2m you've just recycled.
> 
> The p2m is empty so I don't see a problem when it gets recycled.

It's only empty very briefly.  You've assigned it to a vcpu which is
about to take a nested fault and fill it with entries, right?

What happens if the other vcpu is handling an SMI or executing a tight
loop of register arithmetic for a few thousand cycles?  What stops it
seeing the new contents of the p2m?

Tim.

-- 
Tim Deegan <Tim.Deegan@xxxxxxxxxx>
Principal Software Engineer, Xen Platform Team
Citrix Systems UK Ltd.  (Company #02937203, SL9 0BG)

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