[Mesa-dev] [PATCH v3] i965: Implement GL_PRIMITIVES_GENERATED with non-zero streams.

[Iago Toral Quiroga]

So far we have been using CL_INVOCATION_COUNT to resolve this query but this
is no good with streams, as only stream 0 reaches the clipping stage. Instead
we will use SO_PRIM_STORAGE_NEEDED which can keep track of the primitives sent
to each individual stream.

Since SO_PRIM_STORAGE_NEEDED is related to the SOL stage and according to
ARB_transform_feedback3 we need to be able to query primitives generated in
each stream whether transform feedback is active or not what we do is to
enable the SOL unit even if transform feedback is not active but disable all
output buffers in that case. This effectively disables transform feedback
but permits activation of statistics enabling SO_PRIM_STORAGE_NEEDED even
when transform feedback is not active.
---
 src/mesa/drivers/dri/i965/gen6_queryobj.c  | 13 +++++++++----
 src/mesa/drivers/dri/i965/gen7_sol_state.c | 20 +++++++++++++++++---
 2 files changed, 26 insertions(+), 7 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/gen6_queryobj.c b/src/mesa/drivers/dri/i965/gen6_queryobj.c
index 0cb64ca..b4b1509 100644
--- a/src/mesa/drivers/dri/i965/gen6_queryobj.c
+++ b/src/mesa/drivers/dri/i965/gen6_queryobj.c
@@ -84,11 +84,16 @@ brw_store_register_mem64(struct brw_context *brw,
 
 static void
 write_primitives_generated(struct brw_context *brw,
-                           drm_intel_bo *query_bo, int idx)
+                           drm_intel_bo *query_bo, int stream, int idx)
 {
    intel_batchbuffer_emit_mi_flush(brw);
 
-   brw_store_register_mem64(brw, query_bo, CL_INVOCATION_COUNT, idx);
+   if (brw->gen >= 7) {
+      brw_store_register_mem64(brw, query_bo,
+                               GEN7_SO_PRIM_STORAGE_NEEDED(stream), idx);
+   } else {
+      brw_store_register_mem64(brw, query_bo, CL_INVOCATION_COUNT, idx);
+   }
 }
 
 static void
@@ -240,7 +245,7 @@ gen6_begin_query(struct gl_context *ctx, struct gl_query_object *q)
       break;
 
    case GL_PRIMITIVES_GENERATED:
-      write_primitives_generated(brw, query->bo, 0);
+      write_primitives_generated(brw, query->bo, query->Base.Stream, 0);
       break;
 
    case GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN:
@@ -279,7 +284,7 @@ gen6_end_query(struct gl_context *ctx, struct gl_query_object *q)
       break;
 
    case GL_PRIMITIVES_GENERATED:
-      write_primitives_generated(brw, query->bo, 1);
+      write_primitives_generated(brw, query->bo, query->Base.Stream, 1);
       break;
 
    case GL_TRANSFORM_FEEDBACK_PRIMITIVES_WRITTEN:
diff --git a/src/mesa/drivers/dri/i965/gen7_sol_state.c b/src/mesa/drivers/dri/i965/gen7_sol_state.c
index 11b2e2e..d2c3ae3 100644
--- a/src/mesa/drivers/dri/i965/gen7_sol_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_sol_state.c
@@ -223,14 +223,28 @@ upload_3dstate_streamout(struct brw_context *brw, bool active,
    uint32_t dw1 = 0, dw2 = 0;
    int i;
 
+   /*
+    * From ARB_transform_feedback3:
+    *
+    *   "When a generated primitive query for a vertex stream is active, the
+    *   primitives-generated count is incremented every time a primitive
+    *   emitted to that stream reaches the Discarding Rasterization stage
+    *   (see Section 3.x) right before rasterization. This counter is
+    *   incremented whether or not transform feedback is active."
+    *
+    * Since we can only keep track of generated primitives for each stream
+    * in the SOL stage we need to make sure it is always active even if
+    * transform beedback is not. This way we can track primitives generated
+    * in each stream via SO_PRIMITIVE_STORAGE_NEEDED.
+    */
+   dw1 |= SO_FUNCTION_ENABLE;
+   dw1 |= SO_STATISTICS_ENABLE;
+
    if (active) {
       int urb_entry_read_offset = 0;
       int urb_entry_read_length = (vue_map->num_slots + 1) / 2 -
 	 urb_entry_read_offset;
 
-      dw1 |= SO_FUNCTION_ENABLE;
-      dw1 |= SO_STATISTICS_ENABLE;
-
       /* _NEW_LIGHT */
       if (ctx->Light.ProvokingVertex != GL_FIRST_VERTEX_CONVENTION)
 	 dw1 |= SO_REORDER_TRAILING;
-- 
1.9.1