diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index fab30af86f949c7c118257be7ad0139d20f62373..45ef41ebb20f934aa61b03ca18728007e8d1dddc 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -328,9 +328,6 @@ TranslationBlock *tb_htable_lookup(CPUState *cpu, target_ulong pc,
     struct tb_desc desc;
     uint32_t h;
 
-    cf_mask &= ~CF_CLUSTER_MASK;
-    cf_mask |= cpu->cluster_index << CF_CLUSTER_SHIFT;
-
     desc.env = (CPUArchState *)cpu->env_ptr;
     desc.cs_base = cs_base;
     desc.flags = flags;
diff --git a/include/exec/tb-lookup.h b/include/exec/tb-lookup.h
index 492cb682894b28a856ff7dd72f3a296e8cf00483..26921b6dafdaf6d44c3b0e5bb587cfd477bae5f5 100644
--- a/include/exec/tb-lookup.h
+++ b/include/exec/tb-lookup.h
@@ -28,6 +28,10 @@ tb_lookup__cpu_state(CPUState *cpu, target_ulong *pc, target_ulong *cs_base,
     cpu_get_tb_cpu_state(env, pc, cs_base, flags);
     hash = tb_jmp_cache_hash_func(*pc);
     tb = atomic_rcu_read(&cpu->tb_jmp_cache[hash]);
+
+    cf_mask &= ~CF_CLUSTER_MASK;
+    cf_mask |= cpu->cluster_index << CF_CLUSTER_SHIFT;
+
     if (likely(tb &&
                tb->pc == *pc &&
                tb->cs_base == *cs_base &&
diff --git a/include/qemu/atomic128.h b/include/qemu/atomic128.h
index a6af22ff1096c072fb64a49d39653b59317b10de..ddd0d55d31c8e3457f8585b26f930ea889862183 100644
--- a/include/qemu/atomic128.h
+++ b/include/qemu/atomic128.h
@@ -68,7 +68,7 @@ static inline Int128 atomic16_cmpxchg(Int128 *ptr, Int128 cmp, Int128 new)
         "cbnz %w[tmp], 0b\n"
         "1:"
         : [mem] "+m"(*ptr), [tmp] "=&r"(tmp),
-          [oldl] "=&r"(oldl), [oldh] "=r"(oldh)
+          [oldl] "=&r"(oldl), [oldh] "=&r"(oldh)
         : [cmpl] "r"(cmpl), [cmph] "r"(cmph),
           [newl] "r"(newl), [newh] "r"(newh)
         : "memory", "cc");