diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index c61a23b564aa5b5e04b3a822abaa8992ec3d3d0f..2097ed9bd583710a3df69503091c432073ed4bca 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -139,22 +139,6 @@ static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	atomic_inc(&rcpu->refcnt);
 }
 
-/* called from workqueue, to workaround syscall using preempt_disable */
-static void cpu_map_kthread_stop(struct work_struct *work)
-{
-	struct bpf_cpu_map_entry *rcpu;
-
-	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
-
-	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
-	 * as it waits until all in-flight call_rcu() callbacks complete.
-	 */
-	rcu_barrier();
-
-	/* kthread_stop will wake_up_process and wait for it to complete */
-	kthread_stop(rcpu->kthread);
-}
-
 static struct sk_buff *cpu_map_build_skb(struct xdp_frame *xdpf,
 					 struct sk_buff *skb)
 {
@@ -225,6 +209,30 @@ static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu)
 	}
 }
 
+/* called from workqueue, to workaround syscall using preempt_disable */
+static void cpu_map_kthread_stop(struct work_struct *work)
+{
+	struct bpf_cpu_map_entry *rcpu;
+	int err;
+
+	rcpu = container_of(work, struct bpf_cpu_map_entry, kthread_stop_wq);
+
+	/* Wait for flush in __cpu_map_entry_free(), via full RCU barrier,
+	 * as it waits until all in-flight call_rcu() callbacks complete.
+	 */
+	rcu_barrier();
+
+	/* kthread_stop will wake_up_process and wait for it to complete */
+	err = kthread_stop(rcpu->kthread);
+	if (err) {
+		/* kthread_stop may be called before cpu_map_kthread_run
+		 * is executed, so we need to release the memory related
+		 * to rcpu.
+		 */
+		put_cpu_map_entry(rcpu);
+	}
+}
+
 static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 				    void **frames, int n,
 				    struct xdp_cpumap_stats *stats)