Re: [PATCH 3/5] vDPA: introduce vDPA bus

[Michael S. Tsirkin]

On Mon, Jan 20, 2020 at 05:49:39PM +0000, Jason Gunthorpe wrote:
> On Mon, Jan 20, 2020 at 04:43:53PM +0800, Jason Wang wrote:
> > This is similar to the design of platform IOMMU part of vhost-vdpa. We
> > decide to send diffs to platform IOMMU there. If it's ok to do that in
> > driver, we can replace set_map with incremental API like map()/unmap().
> > 
> > Then driver need to maintain rbtree itself.
> 
> I think we really need to see two modes, one where there is a fixed
> translation without dynamic vIOMMU driven changes and one that
> supports vIOMMU.
> 
> There are different optimization goals in the drivers for these two
> configurations.
> 
> > > If the first one, then I think memory hotplug is a heavy flow
> > > regardless. Do you think the extra cycles for the tree traverse
> > > will be visible in any way?
> > 
> > I think if the driver can pause the DMA during the time for setting up new
> > mapping, it should be fine.
> 
> This is very tricky for any driver if the mapping change hits the
> virtio rings. :(
> 
> Even a IOMMU using driver is going to have problems with that..
> 
> Jason

I think for starters we can assume this doesn't happen,
so any change doesn't affect any buffers in use.
Certainly true e.g. for memory hotplug.

-- 
MST