intel/ir: Use brw::performance object instead of CFG cycle counts for codegen stats.

These should be more accurate than the current cycle counts, since
among other things they consider the effect of post-scheduling passes
like the software scoreboard on TGL.  In addition it will enable us to
clean up some of the now redundant cycle-count estimation
functionality in the instruction scheduler.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

src/intel/compiler/brw_fs.h

@@ -477,6 +477,7 @@ public:
    void enable_debug(const char *shader_name);
    int generate_code(const cfg_t *cfg, int dispatch_width,
                      struct shader_stats shader_stats,
+                     const brw::performance &perf,
                      struct brw_compile_stats *stats);
    const unsigned *get_assembly();