On Tuesday 03 February 2015 12:35:34 Rob Clark wrote:
>
> I can't think of cases outside of GPU's.. if it were more common I'd
> be in favor of teaching dma api about multiple contexts, but right now
> I think that would just amount to forcing a lot of churn on everyone
> else for the benefit of GPU's.
We have a couple of users of the iommu API at the moment outside of
GPUs:
* drivers/media/platform/omap3isp/isp.c
* drivers/remoteproc/remoteproc_core.c
* drivers/infiniband/hw/usnic/usnic_uiom.c
* drivers/vfio/
I assume we will see a few more over time. The vfio case is the most
important one here, since that is what the iommu API was designed for.
Arnd