drm/i915: Use the reloc.handle as an index into the execbuffer array

Using copywinwin10 as an example that is dependent upon emitting a lot
of relocations (2 per operation), we see improvements of:

c2d/gm45: 618000.0/sec to 623000.0/sec.
i3-330m: 748000.0/sec to 789000.0/sec.

(measured relative to a baseline with neither optimisations applied).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 7 insertions, 1 deletions

diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 2430b6ad6a85..07d59419fe6b 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -309,6 +309,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_HAS_SECURE_BATCHES    23
 #define I915_PARAM_HAS_PINNED_BATCHES    24
 #define I915_PARAM_HAS_EXEC_NO_RELOC     25
+#define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
 
 typedef struct drm_i915_getparam {
         int param;
@@ -699,7 +700,12 @@ struct drm_i915_gem_execbuffer2 {
  */
 #define I915_EXEC_NO_RELOC              (1<<11)
 
-#define __I915_EXEC_UNKNOWN_FLAGS -(I915_EXEC_NO_RELOC<<1)
+/** Use the reloc.handle as an index into the exec object array rather
+ * than as the per-file handle.
+ */
+#define I915_EXEC_HANDLE_LUT            (1<<12)
+
+#define __I915_EXEC_UNKNOWN_FLAGS -(I915_EXEC_HANDLE_LUT<<1)
 
 #define I915_EXEC_CONTEXT_ID_MASK       (0xffffffff)
 #define i915_execbuffer2_set_context_id(eb2, context) \