i965/gs: Fix EndPrimitive on Broadwell.

My earlier patch (i965: Reserve space for "Vertex Count" in GS outputs.)
incremented Global Offset for most URB writes to make room for the new
"Vertex Count" field, but failed to shift the URB writes used for
writing control bits.

Confusingly, Global Offset must be incremented by 2 here, rather than 1.
The URB writes we use for actual data are HWord writes, which treat
Global Offset as a 256-bit offset.  These are OWord writes, so it's
treated as a 128-bit offset instead.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>

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

@@ -409,6 +409,13 @@ vec4_gs_visitor::emit_control_data_bits()
       inst->force_writemask_all = true;
       inst = emit(GS_OPCODE_URB_WRITE);
       inst->urb_write_flags = urb_write_flags;
+      /* We need to increment Global Offset by 256-bits to make room for
+       * Broadwell's extra "Vertex Count" payload at the beginning of the
+       * URB entry.  Since this is an OWord message, Global Offset is counted
+       * in 128-bit units, so we must set it to 2.
+       */
+      if (brw->gen >= 8)
+         inst->offset = 2;
       inst->base_mrf = base_mrf;
       inst->mlen = 2;
    }