diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c
index 870027d435..6c4a33262f 100644
--- a/accel/tcg/cpu-exec.c
+++ b/accel/tcg/cpu-exec.c
@@ -325,6 +325,9 @@ 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/accel/tcg/translate-all.c b/accel/tcg/translate-all.c
index 8cb8c8870e..7364e8a071 100644
--- a/accel/tcg/translate-all.c
+++ b/accel/tcg/translate-all.c
@@ -1688,6 +1688,9 @@ TranslationBlock *tb_gen_code(CPUState *cpu,
         cflags |= CF_NOCACHE | 1;
     }
 
+    cflags &= ~CF_CLUSTER_MASK;
+    cflags |= cpu->cluster_index << CF_CLUSTER_SHIFT;
+
  buffer_overflow:
     tb = tb_alloc(pc);
     if (unlikely(!tb)) {
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 815e5b1e83..aa7b81aaf0 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -351,9 +351,11 @@ struct TranslationBlock {
 #define CF_USE_ICOUNT  0x00020000
 #define CF_INVALID     0x00040000 /* TB is stale. Set with @jmp_lock held */
 #define CF_PARALLEL    0x00080000 /* Generate code for a parallel context */
+#define CF_CLUSTER_MASK 0xff000000 /* Top 8 bits are cluster ID */
+#define CF_CLUSTER_SHIFT 24
 /* cflags' mask for hashing/comparison */
 #define CF_HASH_MASK   \
-    (CF_COUNT_MASK | CF_LAST_IO | CF_USE_ICOUNT | CF_PARALLEL)
+    (CF_COUNT_MASK | CF_LAST_IO | CF_USE_ICOUNT | CF_PARALLEL | CF_CLUSTER_MASK)
 
     /* Per-vCPU dynamic tracing state used to generate this TB */
     uint32_t trace_vcpu_dstate;