i965: Only flush the batchbuffer if we need to zero the SO offsets

If we don't have pipelined register access (e.g. Haswell before kernel
v4.2), then we can only implement EXT_transform_feedback by reseting the
SO offsets *between* batches. However, if we do have pipelined access to
the SO registers on gen7, we can simply emit an inline reset of the SO
registers without a full batch flush.

v2 [by Ken]: Simplify after recent kernel feature detection changes.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/gen7_sol_state.c b/src/mesa/drivers/dri/i965/gen7_sol_state.c
index d3dcf49a36d213aced96f0d402768fc62dbfe687..a4f46ea486c0816371152285f48a7b67e002f56b 100644 (file)
--- a/src/mesa/drivers/dri/i965/gen7_sol_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sol_state.c
@@ -352,10 +352,6 @@ gen7_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
 
    assert(brw->gen == 7);
 
-   /* Reset the SO buffer offsets to 0. */
-   intel_batchbuffer_flush(brw);
-   brw->batch.needs_sol_reset = true;
-
    /* We're about to lose the information needed to compute the number of
     * vertices written during the last Begin/EndTransformFeedback section,
     * so we can't delay it any further.
@@ -370,6 +366,20 @@ gen7_begin_transform_feedback(struct gl_context *ctx, GLenum mode,
    /* Store the starting value of the SO_NUM_PRIMS_WRITTEN counters. */
    brw_save_primitives_written_counters(brw, brw_obj);
 
+   /* Reset the SO buffer offsets to 0. */
+   if (!can_do_pipelined_register_writes(brw->screen)) {
+      intel_batchbuffer_flush(brw);
+      brw->batch.needs_sol_reset = true;
+   } else {
+      for (int i = 0; i < 4; i++) {
+         BEGIN_BATCH(3);
+         OUT_BATCH(MI_LOAD_REGISTER_IMM | (3 - 2));
+         OUT_BATCH(GEN7_SO_WRITE_OFFSET(i));
+         OUT_BATCH(0);
+         ADVANCE_BATCH();
+      }
+   }
+
    brw_obj->primitive_mode = mode;
 }