drm/i915: Mark untiled BLT commands as fenced on gen2/3

The BLT commands on gen2/3 utilize the fence registers and so we cannot
modify any fences for the object whilst those commands are in flight.
Currently we marked tiled commands as occupying a fence, but forgot to
restrict the untiled commands from preventing a fence being assigned
before they were completed.

One side-effect is that we ten have to double check that a fence was
allocated for a fenced buffer during move-to-active.
Reported-by: Jiri Slaby <jirislaby@gmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=43427
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=47990Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Testcase: i-g-t/tests/gem_tiled_after_untiled_blt
Tested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: stable@kernel.org
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/i915_gem.c

@@ -1472,16 +1472,19 @@ i915_gem_object_move_to_active(struct drm_i915_gem_object *obj,
 	list_move_tail(&obj->ring_list, &ring->active_list);
 
 	obj->last_rendering_seqno = seqno;
-	if (obj->fenced_gpu_access) {
-		struct drm_i915_fence_reg *reg;
-
-		BUG_ON(obj->fence_reg == I915_FENCE_REG_NONE);
 
+	if (obj->fenced_gpu_access) {
 		obj->last_fenced_seqno = seqno;
 		obj->last_fenced_ring = ring;
 
-		reg = &dev_priv->fence_regs[obj->fence_reg];
-		list_move_tail(&reg->lru_list, &dev_priv->mm.fence_list);
+		/* Bump MRU to take account of the delayed flush */
+		if (obj->fence_reg != I915_FENCE_REG_NONE) {
+			struct drm_i915_fence_reg *reg;
+
+			reg = &dev_priv->fence_regs[obj->fence_reg];
+			list_move_tail(&reg->lru_list,
+				       &dev_priv->mm.fence_list);
+		}
 	}
 }
 

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -498,8 +498,8 @@ pin_and_fence_object(struct drm_i915_gem_object *obj,
 				if (ret)
 					goto err_unpin;
 			}
+			obj->pending_fenced_gpu_access = true;
 		}
-		obj->pending_fenced_gpu_access = need_fence;
 	}
 
 	entry->offset = obj->gtt_offset;