Re: [Qemu-devel] [PATCH 3/7] AMD IOMMU emulation

[Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>]

On Mon, Aug 30, 2010 at 12:07:30PM +0900, Isaku Yamahata wrote:
> On Sat, Aug 28, 2010 at 05:54:54PM +0300, Eduard - Gabriel Munteanu wrote:
> > diff --git a/hw/pc.c b/hw/pc.c
> > index a96187f..e2456b0 100644
> > --- a/hw/pc.c
> > +++ b/hw/pc.c
> > @@ -1068,6 +1068,8 @@ void pc_pci_device_init(PCIBus *pci_bus)
> >      int max_bus;
> >      int bus;
> >  
> > +    pci_create_simple(pci_bus, -1, "amd-iommu");
> > +
> >      max_bus = drive_get_max_bus(IF_SCSI);
> >      for (bus = 0; bus <= max_bus; bus++) {
> >          pci_create_simple(pci_bus, -1, "lsi53c895a");
> 
> This always instantiate iommu.
> How to coexist with other iommu(Intel VT-d) emulation?
> -- 
> yamahata

I suppose it could be turned into a compile-time/runtime configurable
option when VT-d emulation arrives. Unless you mean having both IOMMUs
run at the same time, which is impossible unless some meaningful
topology is specified (presumably hardcoded as well).

Considering this is only a machine model I'm modifying, it's just like
other emulated pieces of PC hardware that are (at the moment) hardcoded.


	Eduard