On Mon, Jun 24, 2013 at 07:36:25AM +1000, Benjamin Herrenschmidt wrote: > On Sun, 2013-06-23 at 17:07 +0300, Michael S. Tsirkin wrote: > > Yes I think that's fine really. > > > > Basically devices all speak MSIMessage as they should - > > this is what the PCI spec says. > > On all normal systems guests also speak MSIMessage so > > the API which uses these makes sense for kvm. > > Except, ppc architecture in its wisdom decided to hide this > > in firmware. QEMU does not have firmware so the translation > > has to be maintained in QEMU powerpc code. > > It is still not enough. There is nothing that says that an MSI > address/message is unique. On pseries (among others I'm sure), this is a > per-host-bridge concept since the MSIs are decoded by the PHB and turned > into standard fabric interrupts there. > > So at least the bus needs to be passed as well. > > Cheers, > Ben.
If passing bus (or dma context, etc) turns out to actually be helpful, why not. -- MST