tcg/tci: Implement add2, sub2

We already had the 32-bit versions for a 32-bit host; expand this
to 64-bit hosts as well.  The 64-bit opcodes are new.

Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
diff --git a/tcg/tci.c b/tcg/tci.c
index ebe2eaf..7103005 100644
--- a/tcg/tci.c
+++ b/tcg/tci.c
@@ -193,7 +193,6 @@
     *c5 = extract32(insn, 28, 4);
 }
 
-#if TCG_TARGET_REG_BITS == 32
 static void tci_args_rrrrrr(uint32_t insn, TCGReg *r0, TCGReg *r1,
                             TCGReg *r2, TCGReg *r3, TCGReg *r4, TCGReg *r5)
 {
@@ -204,7 +203,6 @@
     *r4 = extract32(insn, 24, 4);
     *r5 = extract32(insn, 28, 4);
 }
-#endif
 
 static bool tci_compare32(uint32_t u0, uint32_t u1, TCGCond condition)
 {
@@ -355,17 +353,14 @@
     for (;;) {
         uint32_t insn;
         TCGOpcode opc;
-        TCGReg r0, r1, r2, r3, r4;
+        TCGReg r0, r1, r2, r3, r4, r5;
         tcg_target_ulong t1;
         TCGCond condition;
         target_ulong taddr;
         uint8_t pos, len;
         uint32_t tmp32;
         uint64_t tmp64;
-#if TCG_TARGET_REG_BITS == 32
-        TCGReg r5;
         uint64_t T1, T2;
-#endif
         TCGMemOpIdx oi;
         int32_t ofs;
         void *ptr;
@@ -656,20 +651,22 @@
                 tb_ptr = ptr;
             }
             break;
-#if TCG_TARGET_REG_BITS == 32
+#if TCG_TARGET_REG_BITS == 32 || TCG_TARGET_HAS_add2_i32
         case INDEX_op_add2_i32:
             tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
             T1 = tci_uint64(regs[r3], regs[r2]);
             T2 = tci_uint64(regs[r5], regs[r4]);
             tci_write_reg64(regs, r1, r0, T1 + T2);
             break;
+#endif
+#if TCG_TARGET_REG_BITS == 32 || TCG_TARGET_HAS_sub2_i32
         case INDEX_op_sub2_i32:
             tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
             T1 = tci_uint64(regs[r3], regs[r2]);
             T2 = tci_uint64(regs[r5], regs[r4]);
             tci_write_reg64(regs, r1, r0, T1 - T2);
             break;
-#endif /* TCG_TARGET_REG_BITS == 32 */
+#endif
 #if TCG_TARGET_HAS_mulu2_i32
         case INDEX_op_mulu2_i32:
             tci_args_rrrr(insn, &r0, &r1, &r2, &r3);
@@ -799,6 +796,24 @@
             muls64(&regs[r0], &regs[r1], regs[r2], regs[r3]);
             break;
 #endif
+#if TCG_TARGET_HAS_add2_i64
+        case INDEX_op_add2_i64:
+            tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
+            T1 = regs[r2] + regs[r4];
+            T2 = regs[r3] + regs[r5] + (T1 < regs[r2]);
+            regs[r0] = T1;
+            regs[r1] = T2;
+            break;
+#endif
+#if TCG_TARGET_HAS_add2_i64
+        case INDEX_op_sub2_i64:
+            tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
+            T1 = regs[r2] - regs[r4];
+            T2 = regs[r3] - regs[r5] - (regs[r2] < regs[r4]);
+            regs[r0] = T1;
+            regs[r1] = T2;
+            break;
+#endif
 
             /* Shift/rotate operations (64 bit). */
 
@@ -1115,10 +1130,7 @@
     const char *op_name;
     uint32_t insn;
     TCGOpcode op;
-    TCGReg r0, r1, r2, r3, r4;
-#if TCG_TARGET_REG_BITS == 32
-    TCGReg r5;
-#endif
+    TCGReg r0, r1, r2, r3, r4, r5;
     tcg_target_ulong i1;
     int32_t s2;
     TCGCond c;
@@ -1316,15 +1328,15 @@
                            str_r(r2), str_r(r3));
         break;
 
-#if TCG_TARGET_REG_BITS == 32
     case INDEX_op_add2_i32:
+    case INDEX_op_add2_i64:
     case INDEX_op_sub2_i32:
+    case INDEX_op_sub2_i64:
         tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);
         info->fprintf_func(info->stream, "%-12s  %s, %s, %s, %s, %s, %s",
                            op_name, str_r(r0), str_r(r1), str_r(r2),
                            str_r(r3), str_r(r4), str_r(r5));
         break;
-#endif
 
     case INDEX_op_qemu_ld_i64:
     case INDEX_op_qemu_st_i64: