diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index 2206c463f5..5bb099174f 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -330,8 +330,7 @@ void cpu_exec_step_atomic(CPUState *cpu)
     CPUArchState *env = (CPUArchState *)cpu->env_ptr;
     TranslationBlock *tb;
     target_ulong cs_base, pc;
-    uint32_t flags;
-    uint32_t cflags = (curr_cflags(cpu) & ~CF_PARALLEL) | 1;
+    uint32_t flags, cflags;
     int tb_exit;
 
     if (sigsetjmp(cpu->jmp_env, 0) == 0) {
@@ -341,8 +340,14 @@ void cpu_exec_step_atomic(CPUState *cpu)
         cpu->running = true;
 
         cpu_get_tb_cpu_state(env, &pc, &cs_base, &flags);
-        tb = tb_lookup(cpu, pc, cs_base, flags, cflags);
 
+        cflags = curr_cflags(cpu);
+        /* Execute in a serial context. */
+        cflags &= ~CF_PARALLEL;
+        /* After 1 insn, return and release the exclusive lock. */
+        cflags |= CF_NO_GOTO_TB | CF_NO_GOTO_PTR | 1;
+
+        tb = tb_lookup(cpu, pc, cs_base, flags, cflags);
         if (tb == NULL) {
             mmap_lock();
             tb = tb_gen_code(cpu, pc, cs_base, flags, cflags);