tcg/sparc: Introduce tcg_out_mov_delay

This version of tcg_out_mov is emits a nop to fill the
delay slot if the move is not required.

The only current use, for INDEX_op_goto_ptr, will always
require the move but properly documents the delay slot.

Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

tcg/sparc/tcg-target.c.inc

@@ -362,6 +362,11 @@ static bool tcg_target_const_match(int64_t val, TCGType type, int ct)
     }
 }
 
+static void tcg_out_nop(TCGContext *s)
+{
+    tcg_out32(s, NOP);
+}
+
 static void tcg_out_arith(TCGContext *s, TCGReg rd, TCGReg rs1,
                           TCGReg rs2, int op)
 {
@@ -389,6 +394,15 @@ static bool tcg_out_mov(TCGContext *s, TCGType type, TCGReg ret, TCGReg arg)
     return true;
 }
 
+static void tcg_out_mov_delay(TCGContext *s, TCGReg ret, TCGReg arg)
+{
+    if (ret != arg) {
+        tcg_out_arith(s, ret, arg, TCG_REG_G0, ARITH_OR);
+    } else {
+        tcg_out_nop(s);
+    }
+}
+
 static void tcg_out_sethi(TCGContext *s, TCGReg ret, uint32_t arg)
 {
     tcg_out32(s, SETHI | INSN_RD(ret) | ((arg & 0xfffffc00) >> 10));
@@ -551,11 +565,6 @@ static void tcg_out_div32(TCGContext *s, TCGReg rd, TCGReg rs1,
                    uns ? ARITH_UDIV : ARITH_SDIV);
 }
 
-static void tcg_out_nop(TCGContext *s)
-{
-    tcg_out32(s, NOP);
-}
-
 static const uint8_t tcg_cond_to_bcond[] = {
     [TCG_COND_EQ] = COND_E,
     [TCG_COND_NE] = COND_NE,
@@ -1349,7 +1358,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_goto_ptr:
         tcg_out_arithi(s, TCG_REG_G0, a0, 0, JMPL);
         if (USE_REG_TB) {
-            tcg_out_arith(s, TCG_REG_TB, a0, TCG_REG_G0, ARITH_OR);
+            tcg_out_mov_delay(s, TCG_REG_TB, a0);
         } else {
             tcg_out_nop(s);
         }