diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 5b7004b580353f23a2e064dc1975792961fc1d15..526ac57b370e9d4f0e5c28b8c69b8a0531e95518 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -160,7 +160,7 @@ static void cgroup_bpf_release_fn(struct percpu_ref *ref)
 	struct cgroup *cgrp = container_of(ref, struct cgroup, bpf.refcnt);
 
 	INIT_WORK(&cgrp->bpf.release_work, cgroup_bpf_release);
-	queue_work(system_wq, &cgrp->bpf.release_work);
+	queue_work(cgroup_destroy_wq, &cgrp->bpf.release_work);
 }
 
 /* Get underlying bpf_prog of bpf_prog_list entry, regardless if it's through
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h
index 470f196b7f7491eab6bbf778a9b114f05f5a7e5e..096cee0e111a4fd4f5aaf7ce544c76e0f3d7e324 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -14,6 +14,7 @@ extern spinlock_t trace_cgroup_path_lock;
 extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
 extern bool cgroup_debug;
 extern void __init enable_debug_cgroup(void);
+extern struct workqueue_struct *cgroup_destroy_wq;
 
 /*
  * cgroup_path() takes a spin lock. It is good practice not to take
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 21a46f616756b5fb5f5d6b2486e92d283736886f..69b6bbaf28a31d75ba3484ba2ca1b463b296bde1 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -123,7 +123,7 @@ DEFINE_PERCPU_RWSEM(cgroup_threadgroup_rwsem);
  * destruction work items don't end up filling up max_active of system_wq
  * which may lead to deadlock.
  */
-static struct workqueue_struct *cgroup_destroy_wq;
+struct workqueue_struct *cgroup_destroy_wq;
 
 /* generate an array of cgroup subsystem pointers */
 #define SUBSYS(_x) [_x ## _cgrp_id] = &_x ## _cgrp_subsys,