14 files changed, 268 insertions, 56 deletions

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index ec986ae52808..a9f9a2ccc664 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -264,6 +264,7 @@ static int __init sample_init_module(void)
 
 static void __exit sample_cleanup_module(void)
 {
+	rcu_barrier();
 	tcf_unregister_action(&act_sample_ops, &sample_net_ops);
 }
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0e96cdae9995..d9d54b367d23 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -77,6 +77,8 @@ out:
 }
 EXPORT_SYMBOL(register_tcf_proto_ops);
 
+static struct workqueue_struct *tc_filter_wq;
+
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 {
 	struct tcf_proto_ops *t;
@@ -86,6 +88,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 	 * tcf_proto_ops's destroy() handler.
 	 */
 	rcu_barrier();
+	flush_workqueue(tc_filter_wq);
 
 	write_lock(&cls_mod_lock);
 	list_for_each_entry(t, &tcf_proto_base, head) {
@@ -100,6 +103,12 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 }
 EXPORT_SYMBOL(unregister_tcf_proto_ops);
 
+bool tcf_queue_work(struct work_struct *work)
+{
+	return queue_work(tc_filter_wq, work);
+}
+EXPORT_SYMBOL(tcf_queue_work);
+
 /* Select new prio value from the range, managed by kernel. */
 
 static inline u32 tcf_auto_prio(struct tcf_proto *tp)
@@ -308,27 +317,30 @@ int tcf_block_get(struct tcf_block **p_block,
 }
 EXPORT_SYMBOL(tcf_block_get);
 
-void tcf_block_put_ext(struct tcf_block *block,
-		       struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
-		       struct tcf_block_ext_info *ei)
+static void tcf_block_put_final(struct work_struct *work)
 {
+	struct tcf_block *block = container_of(work, struct tcf_block, work);
 	struct tcf_chain *chain, *tmp;
 
-	if (!block)
-		return;
-
-	tcf_block_offload_unbind(block, q, ei);
-
-	/* XXX: Standalone actions are not allowed to jump to any chain, and
-	 * bound actions should be all removed after flushing. However,
-	 * filters are destroyed in RCU callbacks, we have to hold the chains
-	 * first, otherwise we would always race with RCU callbacks on this list
-	 * without proper locking.
-	 */
+	/* At this point, all the chains should have refcnt == 1. */
+	rtnl_lock();
+	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+		tcf_chain_put(chain);
+	rtnl_unlock();
+	kfree(block);
+}
 
-	/* Wait for existing RCU callbacks to cool down. */
-	rcu_barrier();
+/* XXX: Standalone actions are not allowed to jump to any chain, and bound
+ * actions should be all removed after flushing. However, filters are destroyed
+ * in RCU callbacks, we have to hold the chains first, otherwise we would
+ * always race with RCU callbacks on this list without proper locking.
+ */
+static void tcf_block_put_deferred(struct work_struct *work)
+{
+	struct tcf_block *block = container_of(work, struct tcf_block, work);
+	struct tcf_chain *chain;
 
+	rtnl_lock();
 	/* Hold a refcnt for all chains, except 0, in case they are gone. */
 	list_for_each_entry(chain, &block->chain_list, list)
 		if (chain->index)
@@ -338,13 +350,31 @@ void tcf_block_put_ext(struct tcf_block *block,
 	list_for_each_entry(chain, &block->chain_list, list)
 		tcf_chain_flush(chain);
 
-	/* Wait for RCU callbacks to release the reference count. */
+	INIT_WORK(&block->work, tcf_block_put_final);
+	/* Wait for RCU callbacks to release the reference count and make
+	 * sure their works have been queued before this.
+	 */
 	rcu_barrier();
+	tcf_queue_work(&block->work);
+	rtnl_unlock();
+}
 
-	/* At this point, all the chains should have refcnt == 1. */
-	list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
-		tcf_chain_put(chain);
-	kfree(block);
+void tcf_block_put_ext(struct tcf_block *block,
+		       struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		       struct tcf_block_ext_info *ei)
+{
+	if (!block)
+		return;
+
+	tcf_block_offload_unbind(block, q, ei);
+
+	INIT_WORK(&block->work, tcf_block_put_deferred);
+	/* Wait for existing RCU callbacks to cool down, make sure their works
+	 * have been queued before this. We can not flush pending works here
+	 * because we are holding the RTNL lock.
+	 */
+	rcu_barrier();
+	tcf_queue_work(&block->work);
 }
 EXPORT_SYMBOL(tcf_block_put_ext);
 
@@ -354,6 +384,7 @@ void tcf_block_put(struct tcf_block *block)
 
 	tcf_block_put_ext(block, NULL, block->q, &ei);
 }
+
 EXPORT_SYMBOL(tcf_block_put);
 
 struct tcf_block_cb {
@@ -1051,6 +1082,7 @@ void tcf_exts_destroy(struct tcf_exts *exts)
 #ifdef CONFIG_NET_CLS_ACT
 	LIST_HEAD(actions);
 
+	ASSERT_RTNL();
 	tcf_exts_to_list(exts, &actions);
 	tcf_action_destroy(&actions, TCA_ACT_UNBIND);
 	kfree(exts->actions);
@@ -1229,6 +1261,10 @@ EXPORT_SYMBOL(tc_setup_cb_call);
 
 static int __init tc_filter_init(void)
 {
+	tc_filter_wq = alloc_ordered_workqueue("tc_filter_workqueue", 0);
+	if (!tc_filter_wq)
+		return -ENOMEM;
+
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter,
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 700b345b07f9..871351358c10 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -35,7 +35,10 @@ struct basic_filter {
 	struct tcf_result	res;
 	struct tcf_proto	*tp;
 	struct list_head	link;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -84,15 +87,26 @@ static int basic_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static void basic_delete_filter(struct rcu_head *head)
+static void basic_delete_filter_work(struct work_struct *work)
 {
-	struct basic_filter *f = container_of(head, struct basic_filter, rcu);
+	struct basic_filter *f = container_of(work, struct basic_filter, work);
 
+	rtnl_lock();
 	tcf_exts_destroy(&f->exts);
 	tcf_em_tree_destroy(&f->ematches);
+	rtnl_unlock();
+
 	kfree(f);
 }
 
+static void basic_delete_filter(struct rcu_head *head)
+{
+	struct basic_filter *f = container_of(head, struct basic_filter, rcu);
+
+	INIT_WORK(&f->work, basic_delete_filter_work);
+	tcf_queue_work(&f->work);
+}
+
 static void basic_destroy(struct tcf_proto *tp)
 {
 	struct basic_head *head = rtnl_dereference(tp->root);
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 0f8b51061c39..5f701c8670a2 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -50,7 +50,10 @@ struct cls_bpf_prog {
 	struct sock_filter *bpf_ops;
 	const char *bpf_name;
 	struct tcf_proto *tp;
-	struct rcu_head rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 };
 
 static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
@@ -269,9 +272,21 @@ static void __cls_bpf_delete_prog(struct cls_bpf_prog *prog)
 	kfree(prog);
 }
 
+static void cls_bpf_delete_prog_work(struct work_struct *work)
+{
+	struct cls_bpf_prog *prog = container_of(work, struct cls_bpf_prog, work);
+
+	rtnl_lock();
+	__cls_bpf_delete_prog(prog);
+	rtnl_unlock();
+}
+
 static void cls_bpf_delete_prog_rcu(struct rcu_head *rcu)
 {
-	__cls_bpf_delete_prog(container_of(rcu, struct cls_bpf_prog, rcu));
+	struct cls_bpf_prog *prog = container_of(rcu, struct cls_bpf_prog, rcu);
+
+	INIT_WORK(&prog->work, cls_bpf_delete_prog_work);
+	tcf_queue_work(&prog->work);
 }
 
 static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog)
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index d48452f87975..a97e069bee89 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -23,7 +23,10 @@ struct cls_cgroup_head {
 	struct tcf_exts		exts;
 	struct tcf_ematch_tree	ematches;
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -57,15 +60,26 @@ static const struct nla_policy cgroup_policy[TCA_CGROUP_MAX + 1] = {
 	[TCA_CGROUP_EMATCHES]	= { .type = NLA_NESTED },
 };
 
+static void cls_cgroup_destroy_work(struct work_struct *work)
+{
+	struct cls_cgroup_head *head = container_of(work,
+						    struct cls_cgroup_head,
+						    work);
+	rtnl_lock();
+	tcf_exts_destroy(&head->exts);
+	tcf_em_tree_destroy(&head->ematches);
+	kfree(head);
+	rtnl_unlock();
+}
+
 static void cls_cgroup_destroy_rcu(struct rcu_head *root)
 {
 	struct cls_cgroup_head *head = container_of(root,
 						    struct cls_cgroup_head,
 						    rcu);
 
-	tcf_exts_destroy(&head->exts);
-	tcf_em_tree_destroy(&head->ematches);
-	kfree(head);
+	INIT_WORK(&head->work, cls_cgroup_destroy_work);
+	tcf_queue_work(&head->work);
 }
 
 static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 6b29cef90bec..9c08fcdaf41c 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -57,7 +57,10 @@ struct flow_filter {
 	u32			divisor;
 	u32			baseclass;
 	u32			hashrnd;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static inline u32 addr_fold(void *addr)
@@ -369,14 +372,24 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = {
 	[TCA_FLOW_PERTURB]	= { .type = NLA_U32 },
 };
 
-static void flow_destroy_filter(struct rcu_head *head)
+static void flow_destroy_filter_work(struct work_struct *work)
 {
-	struct flow_filter *f = container_of(head, struct flow_filter, rcu);
+	struct flow_filter *f = container_of(work, struct flow_filter, work);
 
+	rtnl_lock();
 	del_timer_sync(&f->perturb_timer);
 	tcf_exts_destroy(&f->exts);
 	tcf_em_tree_destroy(&f->ematches);
 	kfree(f);
+	rtnl_unlock();
+}
+
+static void flow_destroy_filter(struct rcu_head *head)
+{
+	struct flow_filter *f = container_of(head, struct flow_filter, rcu);
+
+	INIT_WORK(&f->work, flow_destroy_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static int flow_change(struct net *net, struct sk_buff *in_skb,
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 16f58abaa697..35cb6d684e44 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -87,7 +87,11 @@ struct cls_fl_filter {
 	struct list_head list;
 	u32 handle;
 	u32 flags;
-	struct rcu_head	rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head	rcu;
+	};
+	struct net_device *hw_dev;
 };
 
 static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
@@ -189,12 +193,22 @@ static int fl_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static void fl_destroy_filter(struct rcu_head *head)
+static void fl_destroy_filter_work(struct work_struct *work)
 {
-	struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu);
+	struct cls_fl_filter *f = container_of(work, struct cls_fl_filter, work);
 
+	rtnl_lock();
 	tcf_exts_destroy(&f->exts);
 	kfree(f);
+	rtnl_unlock();
+}
+
+static void fl_destroy_filter(struct rcu_head *head)
+{
+	struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu);
+
+	INIT_WORK(&f->work, fl_destroy_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index aa1e1f3bd20c..5908f56f76da 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -47,7 +47,10 @@ struct fw_filter {
 #endif /* CONFIG_NET_CLS_IND */
 	struct tcf_exts		exts;
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 static u32 fw_hash(u32 handle)
@@ -122,12 +125,22 @@ static int fw_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static void fw_delete_filter(struct rcu_head *head)
+static void fw_delete_filter_work(struct work_struct *work)
 {
-	struct fw_filter *f = container_of(head, struct fw_filter, rcu);
+	struct fw_filter *f = container_of(work, struct fw_filter, work);
 
+	rtnl_lock();
 	tcf_exts_destroy(&f->exts);
 	kfree(f);
+	rtnl_unlock();
+}
+
+static void fw_delete_filter(struct rcu_head *head)
+{
+	struct fw_filter *f = container_of(head, struct fw_filter, rcu);
+
+	INIT_WORK(&f->work, fw_delete_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void fw_destroy(struct tcf_proto *tp)
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 70e78d74f6d3..95dc997873e8 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -21,7 +21,10 @@ struct cls_mall_head {
 	struct tcf_result res;
 	u32 handle;
 	u32 flags;
-	struct rcu_head	rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head	rcu;
+	};
 };
 
 static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -41,13 +44,23 @@ static int mall_init(struct tcf_proto *tp)
 	return 0;
 }
 
+static void mall_destroy_work(struct work_struct *work)
+{
+	struct cls_mall_head *head = container_of(work, struct cls_mall_head,
+						  work);
+	rtnl_lock();
+	tcf_exts_destroy(&head->exts);
+	kfree(head);
+	rtnl_unlock();
+}
+
 static void mall_destroy_rcu(struct rcu_head *rcu)
 {
 	struct cls_mall_head *head = container_of(rcu, struct cls_mall_head,
 						  rcu);
 
-	tcf_exts_destroy(&head->exts);
-	kfree(head);
+	INIT_WORK(&head->work, mall_destroy_work);
+	tcf_queue_work(&head->work);
 }
 
 static void mall_destroy_hw_filter(struct tcf_proto *tp,
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 9ddde65915d2..4b14ccd8b8f2 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -57,7 +57,10 @@ struct route4_filter {
 	u32			handle;
 	struct route4_bucket	*bkt;
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 #define ROUTE4_FAILURE ((struct route4_filter *)(-1L))
@@ -254,12 +257,22 @@ static int route4_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static void route4_delete_filter(struct rcu_head *head)
+static void route4_delete_filter_work(struct work_struct *work)
 {
-	struct route4_filter *f = container_of(head, struct route4_filter, rcu);
+	struct route4_filter *f = container_of(work, struct route4_filter, work);
 
+	rtnl_lock();
 	tcf_exts_destroy(&f->exts);
 	kfree(f);
+	rtnl_unlock();
+}
+
+static void route4_delete_filter(struct rcu_head *head)
+{
+	struct route4_filter *f = container_of(head, struct route4_filter, rcu);
+
+	INIT_WORK(&f->work, route4_delete_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void route4_destroy(struct tcf_proto *tp)
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index b1f6ed48bc72..bdbc541787f8 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -97,7 +97,10 @@ struct rsvp_filter {
 
 	u32				handle;
 	struct rsvp_session		*sess;
-	struct rcu_head			rcu;
+	union {
+		struct work_struct		work;
+		struct rcu_head			rcu;
+	};
 };
 
 static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid)
@@ -282,12 +285,22 @@ static int rsvp_init(struct tcf_proto *tp)
 	return -ENOBUFS;
 }
 
-static void rsvp_delete_filter_rcu(struct rcu_head *head)
+static void rsvp_delete_filter_work(struct work_struct *work)
 {
-	struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu);
+	struct rsvp_filter *f = container_of(work, struct rsvp_filter, work);
 
+	rtnl_lock();
 	tcf_exts_destroy(&f->exts);
 	kfree(f);
+	rtnl_unlock();
+}
+
+static void rsvp_delete_filter_rcu(struct rcu_head *head)
+{
+	struct rsvp_filter *f = container_of(head, struct rsvp_filter, rcu);
+
+	INIT_WORK(&f->work, rsvp_delete_filter_work);
+	tcf_queue_work(&f->work);
 }
 
 static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index d732b5474a4d..d6abfa6757f2 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -28,14 +28,20 @@
 struct tcindex_filter_result {
 	struct tcf_exts		exts;
 	struct tcf_result	res;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 };
 
 struct tcindex_filter {
 	u16 key;
 	struct tcindex_filter_result result;
 	struct tcindex_filter __rcu *next;
-	struct rcu_head rcu;
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 };
 
 
@@ -136,12 +142,34 @@ static int tcindex_init(struct tcf_proto *tp)
 	return 0;
 }
 
+static void tcindex_destroy_rexts_work(struct work_struct *work)
+{
+	struct tcindex_filter_result *r;
+
+	r = container_of(work, struct tcindex_filter_result, work);
+	rtnl_lock();
+	tcf_exts_destroy(&r->exts);
+	rtnl_unlock();
+}
+
 static void tcindex_destroy_rexts(struct rcu_head *head)
 {
 	struct tcindex_filter_result *r;
 
 	r = container_of(head, struct tcindex_filter_result, rcu);
-	tcf_exts_destroy(&r->exts);
+	INIT_WORK(&r->work, tcindex_destroy_rexts_work);
+	tcf_queue_work(&r->work);
+}
+
+static void tcindex_destroy_fexts_work(struct work_struct *work)
+{
+	struct tcindex_filter *f = container_of(work, struct tcindex_filter,
+						work);
+
+	rtnl_lock();
+	tcf_exts_destroy(&f->result.exts);
+	kfree(f);
+	rtnl_unlock();
 }
 
 static void tcindex_destroy_fexts(struct rcu_head *head)
@@ -149,8 +177,8 @@ static void tcindex_destroy_fexts(struct rcu_head *head)
 	struct tcindex_filter *f = container_of(head, struct tcindex_filter,
 						rcu);
 
-	tcf_exts_destroy(&f->result.exts);
-	kfree(f);
+	INIT_WORK(&f->work, tcindex_destroy_fexts_work);
+	tcf_queue_work(&f->work);
 }
 
 static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last)
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 9ff17159fb61..86145867b424 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -69,7 +69,10 @@ struct tc_u_knode {
 	u32 __percpu		*pcpu_success;
 #endif
 	struct tcf_proto	*tp;
-	struct rcu_head		rcu;
+	union {
+		struct work_struct	work;
+		struct rcu_head		rcu;
+	};
 	/* The 'sel' field MUST be the last field in structure to allow for
 	 * tc_u32_keys allocated at end of structure.
 	 */
@@ -418,11 +421,21 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
  * this the u32_delete_key_rcu variant does not free the percpu
  * statistics.
  */
+static void u32_delete_key_work(struct work_struct *work)
+{
+	struct tc_u_knode *key = container_of(work, struct tc_u_knode, work);
+
+	rtnl_lock();
+	u32_destroy_key(key->tp, key, false);
+	rtnl_unlock();
+}
+
 static void u32_delete_key_rcu(struct rcu_head *rcu)
 {
 	struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu);
 
-	u32_destroy_key(key->tp, key, false);
+	INIT_WORK(&key->work, u32_delete_key_work);
+	tcf_queue_work(&key->work);
 }
 
 /* u32_delete_key_freepf_rcu is the rcu callback variant
@@ -432,11 +445,21 @@ static void u32_delete_key_rcu(struct rcu_head *rcu)
  * for the variant that should be used with keys return from
  * u32_init_knode()
  */
+static void u32_delete_key_freepf_work(struct work_struct *work)
+{
+	struct tc_u_knode *key = container_of(work, struct tc_u_knode, work);
+
+	rtnl_lock();
+	u32_destroy_key(key->tp, key, true);
+	rtnl_unlock();
+}
+
 static void u32_delete_key_freepf_rcu(struct rcu_head *rcu)
 {
 	struct tc_u_knode *key = container_of(rcu, struct tc_u_knode, rcu);
 
-	u32_destroy_key(key->tp, key, true);
+	INIT_WORK(&key->work, u32_delete_key_freepf_work);
+	tcf_queue_work(&key->work);
 }
 
 static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index a9ac912f1d67..b6c4f536876b 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -301,6 +301,8 @@ struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle)
 {
 	struct Qdisc *q;
 
+	if (!handle)
+		return NULL;
 	q = qdisc_match_from_root(dev->qdisc, handle);
 	if (q)
 		goto out;