TCG: fix copy propagation

Copy propagation introduced in 22613af4
considered only global registers. However, register temps and stack
allocated locals must be handled differently because register temps
don't survive across brcond.

Fix by propagating only within same class of temps.
Tested-by: NStefan Weil <weil@mail.berlios.de>
Signed-off-by: NBlue Swirl <blauwirbel@gmail.com>

tcg/optimize.c

@@ -185,12 +185,15 @@ static int op_to_movi(int op)
     }
 }
 
-static void tcg_opt_gen_mov(TCGArg *gen_args, TCGArg dst, TCGArg src,
-                            int nb_temps, int nb_globals)
+static void tcg_opt_gen_mov(TCGContext *s, TCGArg *gen_args, TCGArg dst,
+                            TCGArg src, int nb_temps, int nb_globals)
 {
         reset_temp(dst, nb_temps, nb_globals);
         assert(temps[src].state != TCG_TEMP_COPY);
-        if (src >= nb_globals) {
+        /* Don't try to copy if one of temps is a global or either one
+           is local and another is register */
+        if (src >= nb_globals && dst >= nb_globals &&
+            tcg_arg_is_local(s, src) == tcg_arg_is_local(s, dst)) {
             assert(temps[src].state != TCG_TEMP_CONST);
             if (temps[src].state != TCG_TEMP_HAS_COPY) {
                 temps[src].state = TCG_TEMP_HAS_COPY;
@@ -474,7 +477,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
                     gen_opc_buf[op_index] = INDEX_op_nop;
                 } else {
                     gen_opc_buf[op_index] = op_to_mov(op);
-                    tcg_opt_gen_mov(gen_args, args[0], args[1],
+                    tcg_opt_gen_mov(s, gen_args, args[0], args[1],
                                     nb_temps, nb_globals);
                     gen_args += 2;
                     args += 3;
@@ -500,7 +503,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
                     gen_opc_buf[op_index] = INDEX_op_nop;
                 } else {
                     gen_opc_buf[op_index] = op_to_mov(op);
-                    tcg_opt_gen_mov(gen_args, args[0], args[1], nb_temps,
+                    tcg_opt_gen_mov(s, gen_args, args[0], args[1], nb_temps,
                                     nb_globals);
                     gen_args += 2;
                     args += 3;
@@ -523,7 +526,7 @@ static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
                 break;
             }
             if (temps[args[1]].state != TCG_TEMP_CONST) {
-                tcg_opt_gen_mov(gen_args, args[0], args[1],
+                tcg_opt_gen_mov(s, gen_args, args[0], args[1],
                                 nb_temps, nb_globals);
                 gen_args += 2;
                 args += 2;

tcg/tcg.h

@@ -410,6 +410,11 @@ static inline TCGv_i64 tcg_temp_local_new_i64(void)
 void tcg_temp_free_i64(TCGv_i64 arg);
 char *tcg_get_arg_str_i64(TCGContext *s, char *buf, int buf_size, TCGv_i64 arg);
 
+static inline bool tcg_arg_is_local(TCGContext *s, TCGArg arg)
+{
+    return s->temps[arg].temp_local;
+}
+
 #if defined(CONFIG_DEBUG_TCG)
 /* If you call tcg_clear_temp_count() at the start of a section of
  * code which is not supposed to leak any TCG temporaries, then