pica/primitive_assembly: Handle winding for GS primitive

hwtest shows that, although GS always emit a group of three vertices as one primitive, it still respects to the topology type, as if the three vertices are input into the primitive assembler independently and sequentially. It is also shown that the winding flag in SETEMIT only takes effect for Shader topology type, which is believed to be the actual difference between List and Shader (hence removed the TODO). However, only Shader topology type is observed in official games when GS is in use, so the other mode seems to be just unintended usage.

1 files changed, 12 insertions, 3 deletions

diff --git a/src/video_core/primitive_assembly.cpp b/src/video_core/primitive_assembly.cpp
index acd2ac5e2..9c3dd4cab 100644
--- a/src/video_core/primitive_assembly.cpp
+++ b/src/video_core/primitive_assembly.cpp
@@ -17,15 +17,18 @@ template <typename VertexType>
 void PrimitiveAssembler<VertexType>::SubmitVertex(const VertexType& vtx,
                                                   TriangleHandler triangle_handler) {
     switch (topology) {
-    // TODO: Figure out what's different with TriangleTopology::Shader.
     case PipelineRegs::TriangleTopology::List:
     case PipelineRegs::TriangleTopology::Shader:
         if (buffer_index < 2) {
             buffer[buffer_index++] = vtx;
         } else {
             buffer_index = 0;
-
-            triangle_handler(buffer[0], buffer[1], vtx);
+            if (topology == PipelineRegs::TriangleTopology::Shader && winding) {
+                triangle_handler(buffer[1], buffer[0], vtx);
+                winding = false;
+            } else {
+                triangle_handler(buffer[0], buffer[1], vtx);
+            }
         }
         break;
 
@@ -51,9 +54,15 @@ void PrimitiveAssembler<VertexType>::SubmitVertex(const VertexType& vtx,
 }
 
 template <typename VertexType>
+void PrimitiveAssembler<VertexType>::SetWinding() {
+    winding = true;
+}
+
+template <typename VertexType>
 void PrimitiveAssembler<VertexType>::Reset() {
     buffer_index = 0;
     strip_ready = false;
+    winding = false;
 }
 
 template <typename VertexType>