diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 2211803..78ef2c5 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -16,14 +16,11 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <linux/cgroup.h>
+#include <linux/rcupdate.h>
 #include <net/rtnetlink.h>
 #include <net/pkt_cls.h>
-
-struct cgroup_cls_state
-{
-	struct cgroup_subsys_state css;
-	u32 classid;
-};
+#include <net/sock.h>
+#include <net/cls_cgroup.h>
 
 static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss,
 					       struct cgroup *cgrp);
@@ -112,6 +109,10 @@
 	struct cls_cgroup_head *head = tp->root;
 	u32 classid;
 
+	rcu_read_lock();
+	classid = task_cls_state(current)->classid;
+	rcu_read_unlock();
+
 	/*
 	 * Due to the nature of the classifier it is required to ignore all
 	 * packets originating from softirq context as accessing `current'
@@ -122,12 +123,12 @@
 	 * calls by looking at the number of nested bh disable calls because
 	 * softirqs always disables bh.
 	 */
-	if (softirq_count() != SOFTIRQ_OFFSET)
-		return -1;
-
-	rcu_read_lock();
-	classid = task_cls_state(current)->classid;
-	rcu_read_unlock();
+	if (softirq_count() != SOFTIRQ_OFFSET) {
+		/* If there is an sk_classid we'll use that. */
+		if (!skb->sk)
+			return -1;
+		classid = skb->sk->sk_classid;
+	}
 
 	if (!classid)
 		return -1;
@@ -289,18 +290,35 @@
 
 static int __init init_cgroup_cls(void)
 {
-	int ret = register_tcf_proto_ops(&cls_cgroup_ops);
-	if (ret)
-		return ret;
+	int ret;
+
 	ret = cgroup_load_subsys(&net_cls_subsys);
 	if (ret)
-		unregister_tcf_proto_ops(&cls_cgroup_ops);
+		goto out;
+
+#ifndef CONFIG_NET_CLS_CGROUP
+	/* We can't use rcu_assign_pointer because this is an int. */
+	smp_wmb();
+	net_cls_subsys_id = net_cls_subsys.subsys_id;
+#endif
+
+	ret = register_tcf_proto_ops(&cls_cgroup_ops);
+	if (ret)
+		cgroup_unload_subsys(&net_cls_subsys);
+
+out:
 	return ret;
 }
 
 static void __exit exit_cgroup_cls(void)
 {
 	unregister_tcf_proto_ops(&cls_cgroup_ops);
+
+#ifndef CONFIG_NET_CLS_CGROUP
+	net_cls_subsys_id = -1;
+	synchronize_rcu();
+#endif
+
 	cgroup_unload_subsys(&net_cls_subsys);
 }