diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4bed78e47347..9b08d792fa95 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -275,7 +275,11 @@ struct bpf_map {
 	 */
 	atomic64_t refcnt ____cacheline_aligned;
 	atomic64_t usercnt;
-	struct work_struct work;
+	/* rcu is used before freeing and work is only used during freeing */
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 	struct mutex freeze_mutex;
 	atomic64_t writecnt;
 	/* 'Ownership' of program-containing map is claimed by the first program
@@ -291,6 +295,7 @@ struct bpf_map {
 	} owner;
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
+	bool free_after_mult_rcu_gp;
 	s64 __percpu *elem_count;
 };
 
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 2dfeb5835e16..3248ff5d8161 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -129,10 +129,15 @@ void *bpf_map_fd_get_ptr(struct bpf_map *map,
 
 void bpf_map_fd_put_ptr(struct bpf_map *map, void *ptr, bool need_defer)
 {
-	/* ptr->ops->map_free() has to go through one
-	 * rcu grace period by itself.
+	struct bpf_map *inner_map = ptr;
+
+	/* The inner map may still be used by both non-sleepable and sleepable
+	 * bpf program, so free it after one RCU grace period and one tasks
+	 * trace RCU grace period.
 	 */
-	bpf_map_put(ptr);
+	if (need_defer)
+		WRITE_ONCE(inner_map->free_after_mult_rcu_gp, true);
+	bpf_map_put(inner_map);
 }
 
 u32 bpf_map_fd_sys_lookup_elem(void *ptr)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index d77b2f8b9364..1625b9d5202c 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -717,6 +717,28 @@ static void bpf_map_put_uref(struct bpf_map *map)
 	}
 }
 
+static void bpf_map_free_in_work(struct bpf_map *map)
+{
+	INIT_WORK(&map->work, bpf_map_free_deferred);
+	/* Avoid spawning kworkers, since they all might contend
+	 * for the same mutex like slab_mutex.
+	 */
+	queue_work(system_unbound_wq, &map->work);
+}
+
+static void bpf_map_free_rcu_gp(struct rcu_head *rcu)
+{
+	bpf_map_free_in_work(container_of(rcu, struct bpf_map, rcu));
+}
+
+static void bpf_map_free_mult_rcu_gp(struct rcu_head *rcu)
+{
+	if (rcu_trace_implies_rcu_gp())
+		bpf_map_free_rcu_gp(rcu);
+	else
+		call_rcu(rcu, bpf_map_free_rcu_gp);
+}
+
 /* decrement map refcnt and schedule it for freeing via workqueue
  * (underlying map implementation ops->map_free() might sleep)
  */
@@ -726,11 +748,11 @@ void bpf_map_put(struct bpf_map *map)
 		/* bpf_map_free_id() must be called first */
 		bpf_map_free_id(map);
 		btf_put(map->btf);
-		INIT_WORK(&map->work, bpf_map_free_deferred);
-		/* Avoid spawning kworkers, since they all might contend
-		 * for the same mutex like slab_mutex.
-		 */
-		queue_work(system_unbound_wq, &map->work);
+
+		if (READ_ONCE(map->free_after_mult_rcu_gp))
+			call_rcu_tasks_trace(&map->rcu, bpf_map_free_mult_rcu_gp);
+		else
+			bpf_map_free_in_work(map);
 	}
 }
 EXPORT_SYMBOL_GPL(bpf_map_put);