drm/i915/execbuffer: Clear domains before beginning reloc processing

After reordering the sequence of relocating objects, commit 6fe4f1404,
we can no longer rely on seeing all reloc targets prior to performing
the relocation. As a result we were ignoring the need to flush objects
from the render cache and invalidate the sampler caches, resulting in
rendering glitches. So we need to clear the relocation domains earlier.

Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Tested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 6b34e98..8db88e3 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -464,8 +464,6 @@
 	int ret;
 
 	list_for_each_entry(obj, objects, exec_list) {
-		obj->base.pending_read_domains = 0;
-		obj->base.pending_write_domain = 0;
 		ret = i915_gem_execbuffer_relocate_object(obj, eb);
 		if (ret)
 			return ret;
@@ -505,6 +503,9 @@
 			list_move(&obj->exec_list, &ordered_objects);
 		else
 			list_move_tail(&obj->exec_list, &ordered_objects);
+
+		obj->base.pending_read_domains = 0;
+		obj->base.pending_write_domain = 0;
 	}
 	list_splice(&ordered_objects, objects);
 
@@ -712,8 +713,6 @@
 
 	list_for_each_entry(obj, objects, exec_list) {
 		int offset = obj->exec_entry - exec;
-		obj->base.pending_read_domains = 0;
-		obj->base.pending_write_domain = 0;
 		ret = i915_gem_execbuffer_relocate_object_slow(obj, eb,
 							       reloc + reloc_offset[offset]);
 		if (ret)