tcg/tci: Implement mulu2, muls2

We already had mulu2_i32 for a 32-bit host; expand this to 64-bit
hosts as well.  The muls2_i32 and 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>

1 files changed, 29 insertions, 6 deletions

diff --git a/tcg/tci.c b/tcg/tci.c
index adfca71c0f..ebe2eafa62 100644
--- a/tcg/tci.c
+++ b/tcg/tci.c
@@ -41,7 +41,7 @@ __thread uintptr_t tci_tb_ptr;
 static void tci_write_reg64(tcg_target_ulong *regs, uint32_t high_index,
                             uint32_t low_index, uint64_t value)
 {
-    regs[low_index] = value;
+    regs[low_index] = (uint32_t)value;
     regs[high_index] = value >> 32;
 }
 
@@ -173,7 +173,6 @@ static void tci_args_rrrrr(uint32_t insn, TCGReg *r0, TCGReg *r1,
     *r4 = extract32(insn, 24, 4);
 }
 
-#if TCG_TARGET_REG_BITS == 32
 static void tci_args_rrrr(uint32_t insn,
                           TCGReg *r0, TCGReg *r1, TCGReg *r2, TCGReg *r3)
 {
@@ -182,7 +181,6 @@ static void tci_args_rrrr(uint32_t insn,
     *r2 = extract32(insn, 16, 4);
     *r3 = extract32(insn, 20, 4);
 }
-#endif
 
 static void tci_args_rrrrrc(uint32_t insn, TCGReg *r0, TCGReg *r1,
                             TCGReg *r2, TCGReg *r3, TCGReg *r4, TCGCond *c5)
@@ -671,11 +669,21 @@ uintptr_t QEMU_DISABLE_CFI tcg_qemu_tb_exec(CPUArchState *env,
             T2 = tci_uint64(regs[r5], regs[r4]);
             tci_write_reg64(regs, r1, r0, T1 - T2);
             break;
+#endif /* TCG_TARGET_REG_BITS == 32 */
+#if TCG_TARGET_HAS_mulu2_i32
         case INDEX_op_mulu2_i32:
             tci_args_rrrr(insn, &r0, &r1, &r2, &r3);
-            tci_write_reg64(regs, r1, r0, (uint64_t)regs[r2] * regs[r3]);
+            tmp64 = (uint64_t)(uint32_t)regs[r2] * (uint32_t)regs[r3];
+            tci_write_reg64(regs, r1, r0, tmp64);
             break;
-#endif /* TCG_TARGET_REG_BITS == 32 */
+#endif
+#if TCG_TARGET_HAS_muls2_i32
+        case INDEX_op_muls2_i32:
+            tci_args_rrrr(insn, &r0, &r1, &r2, &r3);
+            tmp64 = (int64_t)(int32_t)regs[r2] * (int32_t)regs[r3];
+            tci_write_reg64(regs, r1, r0, tmp64);
+            break;
+#endif
 #if TCG_TARGET_HAS_ext8s_i32 || TCG_TARGET_HAS_ext8s_i64
         CASE_32_64(ext8s)
             tci_args_rr(insn, &r0, &r1);
@@ -779,6 +787,18 @@ uintptr_t QEMU_DISABLE_CFI tcg_qemu_tb_exec(CPUArchState *env,
             regs[r0] = ctpop64(regs[r1]);
             break;
 #endif
+#if TCG_TARGET_HAS_mulu2_i64
+        case INDEX_op_mulu2_i64:
+            tci_args_rrrr(insn, &r0, &r1, &r2, &r3);
+            mulu64(&regs[r0], &regs[r1], regs[r2], regs[r3]);
+            break;
+#endif
+#if TCG_TARGET_HAS_muls2_i64
+        case INDEX_op_muls2_i64:
+            tci_args_rrrr(insn, &r0, &r1, &r2, &r3);
+            muls64(&regs[r0], &regs[r1], regs[r2], regs[r3]);
+            break;
+#endif
 
             /* Shift/rotate operations (64 bit). */
 
@@ -1286,14 +1306,17 @@ int print_insn_tci(bfd_vma addr, disassemble_info *info)
                            str_r(r3), str_r(r4), str_c(c));
         break;
 
-#if TCG_TARGET_REG_BITS == 32
     case INDEX_op_mulu2_i32:
+    case INDEX_op_mulu2_i64:
+    case INDEX_op_muls2_i32:
+    case INDEX_op_muls2_i64:
         tci_args_rrrr(insn, &r0, &r1, &r2, &r3);
         info->fprintf_func(info->stream, "%-12s  %s, %s, %s, %s",
                            op_name, str_r(r0), str_r(r1),
                            str_r(r2), str_r(r3));
         break;
 
+#if TCG_TARGET_REG_BITS == 32
     case INDEX_op_add2_i32:
     case INDEX_op_sub2_i32:
         tci_args_rrrrrr(insn, &r0, &r1, &r2, &r3, &r4, &r5);