Hi Eric,

> -----Original Message-----
> From: Eric Auger <[email protected]>
> Sent: 04 March 2026 07:47
> To: Shameer Kolothum Thodi <[email protected]>; Jason Gunthorpe
> <[email protected]>; Pavel Hrdina <[email protected]>
> Cc: [email protected]; [email protected];
> [email protected]; Nicolin Chen <[email protected]>;
> [email protected]; [email protected]; [email protected];
> [email protected]; Nathan Chen <[email protected]>; Matt Ochs
> <[email protected]>; [email protected]; [email protected];
> [email protected]; [email protected];
> [email protected]; [email protected]; [email protected];
> Krishnakant Jaju <[email protected]>
> Subject: Re: [PATCH v9 31/37] hw/arm/smmuv3-accel: Add property to specify
> OAS bits
> 
[...]
> >
> > This is how the usage would look with an added "ats" property on the
> > vfio-pci device:
> >
> > -device vfio-pci,...,ats=on
> >     if ATS_NOT_SUPPORTED then reject
> > -device vfio-pci,...,ats=off
> >     keep ATS off
> > -device vfio-pci,...,ats=auto (default)
> >    if ATS_NOT_SUPPORTED, disable ATS
> >     otherwise, enable ATS if the PCIe ATS capability is present
> >     (this also covers behaviour on older kernels)
> >
> > Does the above make sense?
> Do you have plans wrt the migration to auto properties for the various
> vSMMU properties (RIL, ssidsize, OAS, ATS)? I just would like to make
> sure libvirt integrators take this new design into account.
> Please let me know if some help is needed for the conversion of some of
> the properties?

Yes, Nathan is working on a QEMU series to convert those to auto
properties. I have also sent out a kernel series to report the effective
ATS status for the device. Sorry, I missed CCing you on that thread.
Please find it here [0]. The QEMU series needs to make use of this
as well.

Hopefully, Nathan will be able to send out the QEMU series soon after
internal review and testing.

Thanks,
Shameer
[0] 
https://lore.kernel.org/linux-iommu/[email protected]/



Reply via email to