On Tue, Sep 1, 2020 at 11:14 PM Peter Xu <pet...@redhat.com> wrote: > > On Tue, Sep 01, 2020 at 04:26:03PM +0200, Eugenio Pérez wrote: > > I am able to hit this assertion when a Red Hat 7 guest virtio_net device > > raises an "Invalidation" of all the TLB entries. This happens in the > > guest's startup if 'intel_iommu=on' argument is passed to the guest > > kernel and right IOMMU/ATS devices are declared in qemu's command line. > > Thanks for working on this, Eugenio! Sorry to let the original one-liner > patch > grow into a patchset... :) >
On the contrary, I knew it was not going to be so easy and it's been a pleasure to learn the DEVIOTLB intrinsics with it :). > I think it at least looks very good to me in general, besides another trivial > comment on patch 4. > Will address it and send PATCH then. Thanks! > -- > Peter Xu >