diff --git a/tcg/optimize.c b/tcg/optimize.c
index e84d10be53..e2ecad2884 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -1412,19 +1412,44 @@ static bool fold_mul_highpart(OptContext *ctx, TCGOp *op)
     return false;
 }
 
-static bool fold_mulu2_i32(OptContext *ctx, TCGOp *op)
+static bool fold_multiply2(OptContext *ctx, TCGOp *op)
 {
     if (arg_is_const(op->args[2]) && arg_is_const(op->args[3])) {
-        uint32_t a = arg_info(op->args[2])->val;
-        uint32_t b = arg_info(op->args[3])->val;
-        uint64_t r = (uint64_t)a * b;
+        uint64_t a = arg_info(op->args[2])->val;
+        uint64_t b = arg_info(op->args[3])->val;
+        uint64_t h, l;
         TCGArg rl, rh;
-        TCGOp *op2 = tcg_op_insert_before(ctx->tcg, op, INDEX_op_mov_i32);
+        TCGOp *op2;
+
+        switch (op->opc) {
+        case INDEX_op_mulu2_i32:
+            l = (uint64_t)(uint32_t)a * (uint32_t)b;
+            h = (int32_t)(l >> 32);
+            l = (int32_t)l;
+            break;
+        case INDEX_op_muls2_i32:
+            l = (int64_t)(int32_t)a * (int32_t)b;
+            h = l >> 32;
+            l = (int32_t)l;
+            break;
+        case INDEX_op_mulu2_i64:
+            mulu64(&l, &h, a, b);
+            break;
+        case INDEX_op_muls2_i64:
+            muls64(&l, &h, a, b);
+            break;
+        default:
+            g_assert_not_reached();
+        }
 
         rl = op->args[0];
         rh = op->args[1];
-        tcg_opt_gen_movi(ctx, op, rl, (int32_t)r);
-        tcg_opt_gen_movi(ctx, op2, rh, (int32_t)(r >> 32));
+
+        /* The proper opcode is supplied by tcg_opt_gen_mov. */
+        op2 = tcg_op_insert_before(ctx->tcg, op, 0);
+
+        tcg_opt_gen_movi(ctx, op, rl, l);
+        tcg_opt_gen_movi(ctx, op2, rh, h);
         return true;
     }
     return false;
@@ -1932,8 +1957,9 @@ void tcg_optimize(TCGContext *s)
         CASE_OP_32_64(muluh):
             done = fold_mul_highpart(&ctx, op);
             break;
-        case INDEX_op_mulu2_i32:
-            done = fold_mulu2_i32(&ctx, op);
+        CASE_OP_32_64(muls2):
+        CASE_OP_32_64(mulu2):
+            done = fold_multiply2(&ctx, op);
             break;
         CASE_OP_32_64(nand):
             done = fold_nand(&ctx, op);