Re: [PATCH rc v2] iommu/arm-smmu-v3: Fix inconsistent ATS state tracking

[Pranjal Shrivastava <praan@google.com>]

On Mon, May 11, 2026 at 09:30:49AM -0700, David Matlack wrote:
> On Mon, May 11, 2026 at 9:07 AM Pranjal Shrivastava <praan@google.com> wrote:
> >
> > On Mon, May 11, 2026 at 11:16:07AM -0300, Jason Gunthorpe wrote:
> > > On Mon, May 11, 2026 at 12:07:04PM +0000, Pranjal Shrivastava wrote:
> > > >
> > > > > Thus the quirk should cover the VFs too and also disable ATS there.
> > > >
> > > > I observe the quirk does apply VFs but after the VF's iommu attach
> > > > because of how the pci_iov_add_virtfn() is written:
> > >
> > > Ah, that seems to be the issue then :\
> >
> > Yea :/ we need something to ensure that quirk orders don't impact sanity
> 
> I haven't read through this whole thread, but I think this patch is
> related to the issue you are discussing:
> 
>   https://lore.kernel.org/linux-pci/20260403222750.1215002-1-dmatlack@google.com/

Yup, This should be the proper fix to the quirk issue. It moves the ats
quirk from final -> header and makes ats_init quirk-aware. I'll test out
this patch. Thanks for sharing it!

That said, I think even if we solve the quirk timing, pci_enable_ats() &
pci_prepare_ats can still fail for runtime reasons & the arm-smmu-v3
driver should check their return values for correctly tracking ATS state

Thanks,
Praan