[Intel-gfx] [i-g-t PATCH v1 07/14] lib: Map dumb buffers

Daniel Stone daniels at collabora.com
Wed Mar 2 14:22:58 UTC 2016


On Wed, 2016-03-02 at 14:21 +0000, Chris Wilson wrote:
> On Wed, Mar 02, 2016 at 03:00:14PM +0100, Tomeu Vizoso wrote:
> > @@ -1006,8 +1019,9 @@ static cairo_surface_t *get_cairo_surface(int
> > fd, struct igt_fb *fb)
> >  			create_cairo_surface__gtt(fd, fb);
> >  	}
> >  
> > -	gem_set_domain(fd, fb->gem_handle,
> > -		       I915_GEM_DOMAIN_CPU, I915_GEM_DOMAIN_CPU);
> > +	if (!fb->is_dumb)
> > +		gem_set_domain(fd, fb->gem_handle,
> > I915_GEM_DOMAIN_CPU,
> > +			       I915_GEM_DOMAIN_CPU);
> At the risk of opening a can-of-worms, what is the synchronisation
> protocol for dumb buffers? Even CPU access to a dumb needs set-domain 
> on
> Intel.

Then Intel is broken, because the literal entire point of dumb buffers
is that you do not require driver-specific calls to operate them.

Map, populate, unmap, display.

Cheers,
Daniel


More information about the Intel-gfx mailing list