i965 gen6: Implement pass-through GS for transform feedback.

In Gen6, transform feedback is accomplished by having the geometry
shader send vertex data to the data port using "Streamed Vertex Buffer
Write" messages, while simultaneously passing vertices through to the
rest of the graphics pipeline (if rendering is enabled).

This patch adds a geometry shader program that simply passes vertices
through to the rest of the graphics pipeline.  The rest of transform
feedback functionality will be added in future patches.

To make the new geometry shader easier to test, I've added an
environment variable "INTEL_FORCE_GS".  If this environment variable
is enabled, then the pass-through geometry shader will always be used,
regardless of whether transform feedback is in effect.

On my Sandy Bridge laptop, I'm able to enable INTEL_FORCE_GS with no
Piglit regressions.

Reviewed-by: Kenneth Graunke <[email protected]>
Acked-by: Eric Anholt <[email protected]>

1 files changed, 30 insertions, 16 deletions

diff --git a/src/mesa/drivers/dri/i965/gen6_gs_state.c b/src/mesa/drivers/dri/i965/gen6_gs_state.c
index d29f0290727..42962a64d36 100644
--- a/src/mesa/drivers/dri/i965/gen6_gs_state.c
+++ b/src/mesa/drivers/dri/i965/gen6_gs_state.c
@@ -44,22 +44,36 @@ upload_gs_state(struct brw_context *brw)
    OUT_BATCH(0);
    ADVANCE_BATCH();
 
-   // GS should never be used on Gen6.  Disable it.
-   assert(!brw->gs.prog_active);
-   BEGIN_BATCH(7);
-   OUT_BATCH(_3DSTATE_GS << 16 | (7 - 2));
-   OUT_BATCH(0); /* prog_bo */
-   OUT_BATCH((0 << GEN6_GS_SAMPLER_COUNT_SHIFT) |
-	     (0 << GEN6_GS_BINDING_TABLE_ENTRY_COUNT_SHIFT));
-   OUT_BATCH(0); /* scratch space base offset */
-   OUT_BATCH((1 << GEN6_GS_DISPATCH_START_GRF_SHIFT) |
-	     (0 << GEN6_GS_URB_READ_LENGTH_SHIFT) |
-	     (0 << GEN6_GS_URB_ENTRY_READ_OFFSET_SHIFT));
-   OUT_BATCH((0 << GEN6_GS_MAX_THREADS_SHIFT) |
-	     GEN6_GS_STATISTICS_ENABLE |
-	     GEN6_GS_RENDERING_ENABLE);
-   OUT_BATCH(0);
-   ADVANCE_BATCH();
+   if (brw->gs.prog_active) {
+      BEGIN_BATCH(7);
+      OUT_BATCH(_3DSTATE_GS << 16 | (7 - 2));
+      OUT_BATCH(brw->gs.prog_offset);
+      OUT_BATCH(GEN6_GS_SPF_MODE | GEN6_GS_VECTOR_MASK_ENABLE);
+      OUT_BATCH(0); /* no scratch space */
+      OUT_BATCH((1 << GEN6_GS_DISPATCH_START_GRF_SHIFT) |
+	        (brw->gs.prog_data->urb_read_length << GEN6_GS_URB_READ_LENGTH_SHIFT));
+      OUT_BATCH(((brw->max_gs_threads - 1) << GEN6_GS_MAX_THREADS_SHIFT) |
+	        GEN6_GS_STATISTICS_ENABLE |
+		GEN6_GS_SO_STATISTICS_ENABLE |
+		GEN6_GS_RENDERING_ENABLE);
+      OUT_BATCH(GEN6_GS_ENABLE);
+      ADVANCE_BATCH();
+   } else {
+      BEGIN_BATCH(7);
+      OUT_BATCH(_3DSTATE_GS << 16 | (7 - 2));
+      OUT_BATCH(0); /* prog_bo */
+      OUT_BATCH((0 << GEN6_GS_SAMPLER_COUNT_SHIFT) |
+		(0 << GEN6_GS_BINDING_TABLE_ENTRY_COUNT_SHIFT));
+      OUT_BATCH(0); /* scratch space base offset */
+      OUT_BATCH((1 << GEN6_GS_DISPATCH_START_GRF_SHIFT) |
+		(0 << GEN6_GS_URB_READ_LENGTH_SHIFT) |
+		(0 << GEN6_GS_URB_ENTRY_READ_OFFSET_SHIFT));
+      OUT_BATCH((0 << GEN6_GS_MAX_THREADS_SHIFT) |
+		GEN6_GS_STATISTICS_ENABLE |
+		GEN6_GS_RENDERING_ENABLE);
+      OUT_BATCH(0);
+      ADVANCE_BATCH();
+   }
 }
 
 const struct brw_tracked_state gen6_gs_state = {