diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ac37bd53aee031340c601ed4a79ac635824a2a7c..a511fdc623d2c82f42beed7cd8614ad28a4d9595 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -334,7 +334,7 @@ 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 96a9bd2c26f0a6570d9e03c35a311472549aec3a..f0450eec25907fc2f24e2a6fd4a98a9a257eb888 100644
--- a/kernel/cgroup/cgroup-internal.h
+++ b/kernel/cgroup/cgroup-internal.h
@@ -13,6 +13,7 @@
 extern spinlock_t trace_cgroup_path_lock;
 extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN];
 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 dd8eed3c6e3151b8d1444bea2a328ea65a3d7a63..ef9da2e19aad66b0453d4ef83ca7d58f7c56feec 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -126,7 +126,7 @@ 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,