diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 8a33e8747a0e2c2841fa792de1edd05651e04345..6ae02be7a48e3165d860f29765b0f9f7e9443069 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -122,22 +122,6 @@ 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 void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 {
 	/* The tear-down procedure should have made sure that queue is
@@ -165,6 +149,30 @@ 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 void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
 				     struct list_head *listp,
 				     struct xdp_cpumap_stats *stats)