On Thu, May 24, 2007 at 11:38:19AM +0200, Jes Sorensen wrote:
> Isaku Yamahata wrote:
> > On Thu, May 24, 2007 at 10:34:22AM +0200, Jes Sorensen wrote:
> >> dom0 needs the metaphysical addresses or nothing can work as we use the
> >> node info for talking to the PCI controllers, memory controllers (IPIs
> >> and TLB flushes) etc.
> >
> > I don't understand why 'must match' here.
> > dom0 can convert psudo(meta) phsyical address into
> > machine physical address, then it can get node id.
>
> It can, but if I take that approach, I am going to have to rewrite a
> significant part of dom0, it's not realistic to do so. It would affect
> memory management, PCI & IO code etc etc.
P=M will break the current grant table api. It means all of virtual
io device (balloon, vbd, vnif, ...) will be broken.
What do you think about it?
In fact, Virtual Physical address model was introduced to
resolve the grant table issue. And the ia64 default dma api and
hp zx1 iommu are already paravirtulized.
> In addition we want this
> feature when we want to support multiple dom0's in the future.
Do you mean driver domain by "multiple dom0"?
I.e. domain which can serves as backend.
If so, it is already supported by pci backend/frontend driver.
--
yamahata
_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel
|