> From: Jason Gunthorpe <j...@nvidia.com>
> Sent: Friday, June 10, 2022 7:53 AM
> On Thu, Jun 09, 2022 at 05:25:42PM +0000, Raj, Ashok wrote:
> >
> > On Tue, Jun 07, 2022 at 09:49:32AM +0800, Lu Baolu wrote:
> > > Use this field to keep the number of supported PASIDs that an IOMMU
> > > hardware is able to support. This is a generic attribute of an IOMMU
> > > and lifting it into the per-IOMMU device structure makes it possible
> >
> > There is also a per-device attribute that tells what width is supported on
> > each device. When a device enables SVM, for simplicity we were proposing
> to
> > disable SVM on devices that don't support the full width, since it adds
> > additional complexity on the allocation interface. Is that factored into
> > this?
> I would like to see the concept of a 'global PASID' and this is the
> only place we'd union all the per-device limits together. SVM can
> optionally use a global PASID and ENQCMD requires it, but I don't want
> to see the core code assuming everything is ENQCMD.

Agree. and I think this is what this v8 is leaning toward. The core
code simply populates the pasid entry of the target device w/o
assuming the pasid is 'local' or 'global'. Then sva helpers actually
decides how the pasid is allocated.

Currently only global pasids are supported which is how sva works
before. We don't plan to change it in this series.

In parallel Jacob is working on per-device local pasids which will
then be used by his DMA API pasid work and also iommufd.

iommu mailing list

Reply via email to