RE: [RFC PATCH v5 0/5] vfio-pci: Add support for mmapping MSI-X table

From: David Laight
Date: Tue Aug 15 2017 - 10:49:12 EST


From: Benjamin Herrenschmidt
> Sent: 15 August 2017 02:34
> On Tue, 2017-08-15 at 09:16 +0800, Jike Song wrote:
> > > Taking a step back, though, why does vfio-pci perform this check in the
> > > first place? If a malicious guest already has control of a device, any
> > > kind of interrupt spoofing it could do by fiddling with the MSI-X
> > > message address/data it could simply do with a DMA write anyway, so the
> > > security argument doesn't stand up in general (sure, not all PCIe
> > > devices may be capable of arbitrary DMA, but that seems like more of a
> > > tenuous security-by-obscurity angle to me).
>
> I tried to make that point for years, thanks for re-iterating it :-)

Indeed, we have an FPGA based PCIe card where the MSI-X table is just a
piece of PCIe accessible memory.
The device driver has to read the MSI-X table and write the address+data
values to other registers which are then used to raise the interrupt.
(Ok, I've written a better interrupt generator so we don't do that
any more.)

David