Re: [RFC] virtio: Use DMA MAP API for devices without an IOMMU

[Benjamin Herrenschmidt <benh@kernel.crashing.org>]

On Thu, 2018-04-05 at 17:54 +0300, Michael S. Tsirkin wrote:
> On Thu, Apr 05, 2018 at 08:09:30PM +0530, Anshuman Khandual wrote:
> > On 04/05/2018 04:26 PM, Anshuman Khandual wrote:
> > > There are certian platforms which would like to use SWIOTLB based DMA API
> > > for bouncing purpose without actually requiring an IOMMU back end. But the
> > > virtio core does not allow such mechanism. Right now DMA MAP API is only
> > > selected for devices which have an IOMMU and then the QEMU/host back end
> > > will process all incoming SG buffer addresses as IOVA instead of simple
> > > GPA which is the case for simple bounce buffers after being processed with
> > > SWIOTLB API. To enable this usage, it introduces an architecture specific
> > > function which will just make virtio core front end select DMA operations
> > > structure.
> > > 
> > > Signed-off-by: Anshuman Khandual <khandual@linux.vnet.ibm.com>
> > 
> > + "Michael S. Tsirkin" <mst@redhat.com>
> 
> I'm confused by this.
> 
> static bool vring_use_dma_api(struct virtio_device *vdev)
> {
>         if (!virtio_has_iommu_quirk(vdev))
>                 return true;
> 
> 
> Why doesn't setting VIRTIO_F_IOMMU_PLATFORM on the
> hypervisor side sufficient?

In this specific case, because that would make qemu expect an iommu,
and there isn't one.

Anshuman, you need to provide more background here. I don't have time
right now it's late, but explain about the fact that this is for a
specific type of secure VM which has only a limited pool of (insecure)
memory that can be shared with qemu, so all IOs need to bounce via that
pool, which can be achieved by using swiotlb.

Note: this isn't urgent, we can discuss alternative approaches, this is
just to start the conversation.

Cheers,
Ben.