diff --git a/qemu/target/m68k/helper.h b/qemu/target/m68k/helper.h
index a0c06d28..b864fa0f 100644
--- a/qemu/target/m68k/helper.h
+++ b/qemu/target/m68k/helper.h
@@ -15,6 +15,7 @@ DEF_HELPER_3(m68k_movec_to, void, env, i32, i32)
 DEF_HELPER_2(m68k_movec_from, i32, env, i32)
 DEF_HELPER_4(cas2w, void, env, i32, i32, i32)
 DEF_HELPER_4(cas2l, void, env, i32, i32, i32)
+DEF_HELPER_4(cas2l_parallel, void, env, i32, i32, i32)
 
 #define dh_alias_fp ptr
 #define dh_ctype_fp FPReg *
diff --git a/qemu/target/m68k/op_helper.c b/qemu/target/m68k/op_helper.c
index a38659d4..c3bedeb1 100644
--- a/qemu/target/m68k/op_helper.c
+++ b/qemu/target/m68k/op_helper.c
@@ -723,6 +723,7 @@ void HELPER(divsll)(CPUM68KState *env, int numr, int regr, int32_t den)
     env->dregs[numr] = quot;
 }
 
+/* We're executing in a serial context -- no need to be atomic.  */
 void HELPER(cas2w)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
 {
     uint32_t Dc1 = extract32(regs, 9, 3);
@@ -736,17 +737,11 @@ void HELPER(cas2w)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
     int16_t l1, l2;
     uintptr_t ra = GETPC();
 
-    if (env->uc->parallel_cpus) {
-        /* Tell the main loop we need to serialize this insn.  */
-        cpu_loop_exit_atomic(ENV_GET_CPU(env), ra);
-    } else {
-        /* We're executing in a serial context -- no need to be atomic.  */
-        l1 = cpu_lduw_data_ra(env, a1, ra);
-        l2 = cpu_lduw_data_ra(env, a2, ra);
-        if (l1 == c1 && l2 == c2) {
-            cpu_stw_data_ra(env, a1, u1, ra);
-            cpu_stw_data_ra(env, a2, u2, ra);
-        }
+    l1 = cpu_lduw_data_ra(env, a1, ra);
+    l2 = cpu_lduw_data_ra(env, a2, ra);
+    if (l1 == c1 && l2 == c2) {
+        cpu_stw_data_ra(env, a1, u1, ra);
+        cpu_stw_data_ra(env, a2, u2, ra);
     }
 
     if (c1 != l1) {
@@ -761,7 +756,8 @@ void HELPER(cas2w)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
     env->dregs[Dc2] = deposit32(env->dregs[Dc2], 0, 16, l2);
 }
 
-void HELPER(cas2l)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
+static void do_cas2l(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2,
+                     bool parallel)
 {
     uint32_t Dc1 = extract32(regs, 9, 3);
     uint32_t Dc2 = extract32(regs, 6, 3);
@@ -778,7 +774,7 @@ void HELPER(cas2l)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
     TCGMemOpIdx oi;
 #endif
 
-    if (env->uc->parallel_cpus) {
+    if (parallel) {
         /* We're executing in a parallel context -- must be atomic.  */
 #ifdef CONFIG_ATOMIC64
         uint64_t c, u, l;
@@ -832,6 +828,17 @@ void HELPER(cas2l)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
     env->dregs[Dc2] = l2;
 }
 
+void HELPER(cas2l)(CPUM68KState *env, uint32_t regs, uint32_t a1, uint32_t a2)
+{
+    do_cas2l(env, regs, a1, a2, false);
+}
+
+void HELPER(cas2l_parallel)(CPUM68KState *env, uint32_t regs, uint32_t a1,
+                            uint32_t a2)
+{
+    do_cas2l(env, regs, a1, a2, true);
+}
+
 struct bf_data {
     uint32_t addr;
     uint32_t bofs;
diff --git a/qemu/target/m68k/translate.c b/qemu/target/m68k/translate.c
index 3f8af3cb..4d5943b9 100644
--- a/qemu/target/m68k/translate.c
+++ b/qemu/target/m68k/translate.c
@@ -2527,7 +2527,11 @@ DISAS_INSN(cas2w)
                          (REG(ext1, 6) << 3) |
                          (REG(ext2, 0) << 6) |
                          (REG(ext1, 0) << 9));
-    gen_helper_cas2w(tcg_ctx, tcg_ctx->cpu_env, regs, addr1, addr2);
+    if (tb_cflags(s->tb) & CF_PARALLEL) {
+        gen_helper_exit_atomic(tcg_ctx, tcg_ctx->cpu_env);
+    } else {
+        gen_helper_cas2w(tcg_ctx, tcg_ctx->cpu_env, regs, addr1, addr2);
+    }
     tcg_temp_free(tcg_ctx, regs);
 
     /* Note that cas2w also assigned to env->cc_op.  */
@@ -2574,7 +2578,11 @@ DISAS_INSN(cas2l)
                          (REG(ext1, 6) << 3) |
                          (REG(ext2, 0) << 6) |
                          (REG(ext1, 0) << 9));
-    gen_helper_cas2l(tcg_ctx, tcg_ctx->cpu_env, regs, addr1, addr2);
+    if (tb_cflags(s->tb) & CF_PARALLEL) {
+        gen_helper_cas2l_parallel(tcg_ctx, tcg_ctx->cpu_env, regs, addr1, addr2);
+    } else {
+        gen_helper_cas2l(tcg_ctx, tcg_ctx->cpu_env, regs, addr1, addr2);
+    }
     tcg_temp_free(tcg_ctx, regs);
 
     /* Note that cas2l also assigned to env->cc_op.  */