drm/i915: execbuffer pins objects, no need to ensure they're still in the GTT

Before we had the notion of pinning objects, we had a kludge around to make
sure all of the objects were still resident in the GTT before we committed
to executing a batch buffer. We don't need this any longer, and it sticks an
error return in the middle of object domain computations that must be
associated with a subsequent flush/invalidate emmission into the ring.

Signed-off-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>

authored by Keith Packard and committed by Dave Airlie 6133047a 05eff845

-11
-11
drivers/gpu/drm/i915/i915_gem.c
··· 1866 1867 for (i = 0; i < args->buffer_count; i++) { 1868 struct drm_gem_object *obj = object_list[i]; 1869 - struct drm_i915_gem_object *obj_priv = obj->driver_private; 1870 - 1871 - if (obj_priv->gtt_space == NULL) { 1872 - /* We evicted the buffer in the process of validating 1873 - * our set of buffers in. We could try to recover by 1874 - * kicking them everything out and trying again from 1875 - * the start. 1876 - */ 1877 - ret = -ENOMEM; 1878 - goto err; 1879 - } 1880 1881 /* make sure all previous memory operations have passed */ 1882 ret = i915_gem_object_set_domain(obj,
··· 1866 1867 for (i = 0; i < args->buffer_count; i++) { 1868 struct drm_gem_object *obj = object_list[i]; 1869 1870 /* make sure all previous memory operations have passed */ 1871 ret = i915_gem_object_set_domain(obj,