On Mon, Oct 19, 2026 at 03:14:38PM -0600, Logan Gunthorpe wrote: > > > On 2026-10-19 13:48, Popov, Pavel E wrote: > > Logan, Leon, > > > > I kept the hypervisor check to avoid changing what the host bridge > > whitelist refuses on bare metal. Looking at those cases again, on the > > listed Xeon CPUs this is a limitation of the whitelist itself, not a > > known hardware limit, and it is why Intel QAT/DSA/IAA had to be added > > by ID. So I'd drop the hypervisor check. > > > > Would a v3 that moves the Xeon list into cpu_supports_p2pdma(), the > > same way as the AMD check, be acceptable to you both? > > Yes, that's essentially what I was suggesting before. That would be > acceptable to me.
Right, I also wrote the same thing in my summary "We agreed ...". Thanks > > Thanks, > > Logan >
