Re: [PATCH 2/3] drm/msm: add DRM_MSM_GEM_SYNC_CACHE for non-coherent cache maintenance

[Jonathan Marek]

On 10/2/20 3:53 AM, Christoph Hellwig wrote:
> > @@ -8,6 +8,7 @@
> >   #include <linux/shmem_fs.h>
> >   #include <linux/dma-buf.h>
> >   #include <linux/pfn_t.h>
> > +#include <linux/dma-noncoherent.h>
>
> NAK, dma-noncoherent.h is not for driver use.  And will in fact go
> away in 5.10.

Not actually used, so can be removed.

> >   
> >   #include <drm/drm_prime.h>
> >   
> > @@ -808,6 +809,20 @@ int msm_gem_cpu_fini(struct drm_gem_object *obj)
> >   	return 0;
> >   }
> >   
> > +void msm_gem_sync_cache(struct drm_gem_object *obj, uint32_t flags,
> > +		size_t range_start, size_t range_end)
> > +{
> > +	struct msm_gem_object *msm_obj = to_msm_bo(obj);
> > +
> > +	/* TODO: sync only the required range, and don't invalidate on clean */
> > +
> > +	if (flags & MSM_GEM_SYNC_CACHE_CLEAN)
> > +		sync_for_device(msm_obj);
> > +
> > +	if (flags & MSM_GEM_SYNC_CACHE_INVALIDATE)
> > +		sync_for_cpu(msm_obj);
>
> And make to these ones as well.  They are complete abuses of the DMA
> API, and while we had to live with that for now to not cause regressions
> they absoutely must not be exposed in a userspace ABI like this.

How do you propose that cached non-coherent memory be implemented? It is 
a useful feature for userspace.