i965/gs: Fix up gl_PointSize input swizzling for DUAL_INSTANCED gs.

Geometry shaders that run in "DUAL_INSTANCED" mode store their inputs
in vec4's.  This means that when compiling gl_PointSize input
swizzling (a MOV instruction which uses a geometry shader input as
both source and destination), we need to do two things:

- Set force_writemask_all to ensure that the MOV happens regardless of
  which channels are enabled.

- Set the source register region to <4;4,1> (instead of <0;4,1> to
  satisfy register region restrictions.

v2: move the source register region fixup to the top of
vec4_generator::generate_vec4_instruction(), so that it applies to all
instructions rather than just MOV.

Reviewed-by: Eric Anholt <eric@anholt.net>

src/mesa/drivers/dri/i965/brw_vec4_generator.cpp

@@ -856,6 +856,31 @@ vec4_generator::generate_vec4_instruction(vec4_instruction *instruction,
 {
    vec4_instruction *inst = (vec4_instruction *) instruction;
 
+   if (dst.width == BRW_WIDTH_4) {
+      /* This happens in attribute fixups for "dual instanced" geometry
+       * shaders, since they use attributes that are vec4's.  Since the exec
+       * width is only 4, it's essential that the caller set
+       * force_writemask_all in order to make sure the instruction is executed
+       * regardless of which channels are enabled.
+       */
+      assert(inst->force_writemask_all);
+
+      /* Fix up any <8;8,1> or <0;4,1> source registers to <4;4,1> to satisfy
+       * the following register region restrictions (from Graphics BSpec:
+       * 3D-Media-GPGPU Engine > EU Overview > Registers and Register Regions
+       * > Register Region Restrictions)
+       *
+       *     1. ExecSize must be greater than or equal to Width.
+       *
+       *     2. If ExecSize = Width and HorzStride != 0, VertStride must be set
+       *        to Width * HorzStride."
+       */
+      for (int i = 0; i < 3; i++) {
+         if (src[i].file == BRW_GENERAL_REGISTER_FILE)
+            src[i] = stride(src[i], 4, 4, 1);
+      }
+   }
+
    switch (inst->opcode) {
    case BRW_OPCODE_MOV:
       brw_MOV(p, dst, src[0]);

src/mesa/drivers/dri/i965/brw_vec4_gs_visitor.cpp

@@ -181,7 +181,13 @@ vec4_gs_visitor::emit_prolog()
          src_reg src(dst);
          dst.writemask = WRITEMASK_X;
          src.swizzle = BRW_SWIZZLE_WWWW;
-         emit(MOV(dst, src));
+         inst = emit(MOV(dst, src));
+
+         /* In dual instanced dispatch mode, dst has a width of 4, so we need
+          * to make sure the MOV happens regardless of which channels are
+          * enabled.
+          */
+         inst->force_writemask_all = true;
       }
    }