Re: [PATCH V2 01/11] iommufd: Support a HWPT without an iommu driver for noiommu

[Samiullah Khawaja <skhawaja@google.com>]

On Mon, Mar 23, 2026 at 10:17:14AM -0300, Jason Gunthorpe wrote:
>On Wed, Mar 18, 2026 at 06:38:14PM +0000, Samiullah Khawaja wrote:
>
>> > +static const struct iommu_domain_ops noiommu_amdv1_ops = {
>> > +	IOMMU_PT_DOMAIN_OPS(amdv1),
>>
>> I understand that this fits in really well into the iommufd/hwpt
>> construction, but do we need page tables for this as all the
>> iova-to-phys information should be available in the IOPT in IOAS?
>
>Yes we do! That is the whole point.
>
>In iommufd once you pin the memory the phys is stored in only two
>possible ways:
>
>1) Inside an xarray if an access is used
>2) Inside at least one iommu_domain
>
>That's it. So to fit noiommu into this scheme, and have it rely on the
>existing pinning, we either have to make it use an access or make it
>use an iommu_domain -> a real one that can store phys.

Thanks for the explanation.

I missed the part where once pinning is done, the pfns are only
available in those two places.
>
>Maybe a comment is helpful, but using the domain like this to store
>the pinned phys has been the vfio design from day 1..
>
>> get_pa() function introduced in the later patch is only used for noiommu
>> use-cases, it can use the IOPT to get the physical addresses?
>
>No.
>
>Jason