Just s/no mappable GGTT/not supported/ Quoting Janusz Krzysztofik (2019-11-26 12:31:03) > As we've agreed that using I915_GEM_PREAD/PWRITE IOCTLs on dma-buf > objects doesn't make much sense, we are not going to extend their > handlers in the i915 driver with new processing paths required for them > to work correctly with dma-buf objects on future hardware with no > mappable aperture. When running on that kind of hardware, just skip > subtests which use those IOCTLs. > > v2: Examine pread/pwrite ABI, not mmap ABI (Chris) > > Signed-off-by: Janusz Krzysztofik <janusz.krzysztofik@xxxxxxxxxxxxxxx> > Cc: Daniel Vetter <daniel@xxxxxxxx> > Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx> > Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> I like this. We are not here to prove gem_read/gem_write themselves work (if we haven't done that already, we've lost), but whether they work in conjunction with the dmabuf. Reviewed-by: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> I still have a bad feeling about any API change not accompanied by a separate parameter to indicate the change (just from the discoverability aspect of the API), but as proven, an introspection API is not required here. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
