Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Add Maglev hashing scheduler to IPVS, from Inju Song.

 2) Lots of new TC subsystem tests from Roman Mashak.

 3) Add TCP zero copy receive and fix delayed acks and autotuning with
    SO_RCVLOWAT, from Eric Dumazet.

 4) Add XDP_REDIRECT support to mlx5 driver, from Jesper Dangaard
    Brouer.

 5) Add ttl inherit support to vxlan, from Hangbin Liu.

 6) Properly separate ipv6 routes into their logically independant
    components. fib6_info for the routing table, and fib6_nh for sets of
    nexthops, which thus can be shared. From David Ahern.

 7) Add bpf_xdp_adjust_tail helper, which can be used to generate ICMP
    messages from XDP programs. From Nikita V. Shirokov.

 8) Lots of long overdue cleanups to the r8169 driver, from Heiner
    Kallweit.

 9) Add BTF ("BPF Type Format"), from Martin KaFai Lau.

10) Add traffic condition monitoring to iwlwifi, from Luca Coelho.

11) Plumb extack down into fib_rules, from Roopa Prabhu.

12) Add Flower classifier offload support to igb, from Vinicius Costa
    Gomes.

13) Add UDP GSO support, from Willem de Bruijn.

14) Add documentation for eBPF helpers, from Quentin Monnet.

15) Add TLS tx offload to mlx5, from Ilya Lesokhin.

16) Allow applications to be given the number of bytes available to read
    on a socket via a control message returned from recvmsg(), from
    Soheil Hassas Yeganeh.

17) Add x86_32 eBPF JIT compiler, from Wang YanQing.

18) Add AF_XDP sockets, with zerocopy support infrastructure as well.
    From Björn Töpel.

19) Remove indirect load support from all of the BPF JITs and handle
    these operations in the verifier by translating them into native BPF
    instead. From Daniel Borkmann.

20) Add GRO support to ipv6 gre tunnels, from Eran Ben Elisha.

21) Allow XDP programs to do lookups in the main kernel routing tables
    for forwarding. From David Ahern.

22) Allow drivers to store hardware state into an ELF section of kernel
    dump vmcore files, and use it in cxgb4. From Rahul Lakkireddy.

23) Various RACK and loss detection improvements in TCP, from Yuchung
    Cheng.

24) Add TCP SACK compression, from Eric Dumazet.

25) Add User Mode Helper support and basic bpfilter infrastructure, from
    Alexei Starovoitov.

26) Support ports and protocol values in RTM_GETROUTE, from Roopa
    Prabhu.

27) Support bulking in ->ndo_xdp_xmit() API, from Jesper Dangaard
    Brouer.

28) Add lots of forwarding selftests, from Petr Machata.

29) Add generic network device failover driver, from Sridhar Samudrala.

* ra.kernel.org:/pub/scm/linux/kernel/git/davem/net-next: (1959 commits)
  strparser: Add __strp_unpause and use it in ktls.
  rxrpc: Fix terminal retransmission connection ID to include the channel
  net: hns3: Optimize PF CMDQ interrupt switching process
  net: hns3: Fix for VF mailbox receiving unknown message
  net: hns3: Fix for VF mailbox cannot receiving PF response
  bnx2x: use the right constant
  Revert "net: sched: cls: Fix offloading when ingress dev is vxlan"
  net: dsa: b53: Fix for brcm tag issue in Cygnus SoC
  enic: fix UDP rss bits
  netdev-FAQ: clarify DaveM's position for stable backports
  rtnetlink: validate attributes in do_setlink()
  mlxsw: Add extack messages for port_{un, }split failures
  netdevsim: Add extack error message for devlink reload
  devlink: Add extack to reload and port_{un, }split operations
  net: metrics: add proper netlink validation
  ipmr: fix error path when ipmr_new_table fails
  ip6mr: only set ip6mr_table from setsockopt when ip6mr_new_table succeeds
  net: hns3: remove unused hclgevf_cfg_func_mta_filter
  netfilter: provide udp*_lib_lookup for nf_tproxy
  qed*: Utilize FW 8.37.2.0
  ...

16 files changed, 628 insertions, 503 deletions

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 72251241665a..3f4cf930f809 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -77,9 +77,9 @@ static void free_tcf(struct tc_action *p)
 
 static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p)
 {
-	spin_lock_bh(&idrinfo->lock);
+	spin_lock(&idrinfo->lock);
 	idr_remove(&idrinfo->action_idr, p->tcfa_index);
-	spin_unlock_bh(&idrinfo->lock);
+	spin_unlock(&idrinfo->lock);
 	gen_kill_estimator(&p->tcfa_rate_est);
 	free_tcf(p);
 }
@@ -156,7 +156,7 @@ static int tcf_dump_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb,
 	struct tc_action *p;
 	unsigned long id = 1;
 
-	spin_lock_bh(&idrinfo->lock);
+	spin_lock(&idrinfo->lock);
 
 	s_i = cb->args[0];
 
@@ -191,7 +191,7 @@ done:
 	if (index >= 0)
 		cb->args[0] = index + 1;
 
-	spin_unlock_bh(&idrinfo->lock);
+	spin_unlock(&idrinfo->lock);
 	if (n_i) {
 		if (act_flags & TCA_FLAG_LARGE_DUMP_ON)
 			cb->args[1] = n_i;
@@ -261,9 +261,9 @@ static struct tc_action *tcf_idr_lookup(u32 index, struct tcf_idrinfo *idrinfo)
 {
 	struct tc_action *p = NULL;
 
-	spin_lock_bh(&idrinfo->lock);
+	spin_lock(&idrinfo->lock);
 	p = idr_find(&idrinfo->action_idr, index);
-	spin_unlock_bh(&idrinfo->lock);
+	spin_unlock(&idrinfo->lock);
 
 	return p;
 }
@@ -323,7 +323,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 	}
 	spin_lock_init(&p->tcfa_lock);
 	idr_preload(GFP_KERNEL);
-	spin_lock_bh(&idrinfo->lock);
+	spin_lock(&idrinfo->lock);
 	/* user doesn't specify an index */
 	if (!index) {
 		index = 1;
@@ -331,7 +331,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 	} else {
 		err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC);
 	}
-	spin_unlock_bh(&idrinfo->lock);
+	spin_unlock(&idrinfo->lock);
 	idr_preload_end();
 	if (err)
 		goto err3;
@@ -369,9 +369,9 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
 {
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
 
-	spin_lock_bh(&idrinfo->lock);
+	spin_lock(&idrinfo->lock);
 	idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
-	spin_unlock_bh(&idrinfo->lock);
+	spin_unlock(&idrinfo->lock);
 }
 EXPORT_SYMBOL(tcf_idr_insert);
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 7e28b2ce1437..526a8e491626 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -648,6 +648,11 @@ static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static size_t tcf_csum_get_fill_size(const struct tc_action *act)
+{
+	return nla_total_size(sizeof(struct tc_csum));
+}
+
 static struct tc_action_ops act_csum_ops = {
 	.kind		= "csum",
 	.type		= TCA_ACT_CSUM,
@@ -658,6 +663,7 @@ static struct tc_action_ops act_csum_ops = {
 	.cleanup	= tcf_csum_cleanup,
 	.walk		= tcf_csum_walker,
 	.lookup		= tcf_csum_search,
+	.get_fill_size  = tcf_csum_get_fill_size,
 	.size		= sizeof(struct tcf_csum),
 };
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a57e112d9b3e..cdc3c87c53e6 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -103,9 +103,10 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops)
 }
 EXPORT_SYMBOL(unregister_tcf_proto_ops);
 
-bool tcf_queue_work(struct work_struct *work)
+bool tcf_queue_work(struct rcu_work *rwork, work_func_t func)
 {
-	return queue_work(tc_filter_wq, work);
+	INIT_RCU_WORK(rwork, func);
+	return queue_rcu_work(tc_filter_wq, rwork);
 }
 EXPORT_SYMBOL(tcf_queue_work);
 
@@ -436,6 +437,78 @@ static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
 	return idr_find(&tn->idr, block_index);
 }
 
+/* Find tcf block.
+ * Set q, parent, cl when appropriate.
+ */
+
+static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
+					u32 *parent, unsigned long *cl,
+					int ifindex, u32 block_index,
+					struct netlink_ext_ack *extack)
+{
+	struct tcf_block *block;
+
+	if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
+		block = tcf_block_lookup(net, block_index);
+		if (!block) {
+			NL_SET_ERR_MSG(extack, "Block of given index was not found");
+			return ERR_PTR(-EINVAL);
+		}
+	} else {
+		const struct Qdisc_class_ops *cops;
+		struct net_device *dev;
+
+		/* Find link */
+		dev = __dev_get_by_index(net, ifindex);
+		if (!dev)
+			return ERR_PTR(-ENODEV);
+
+		/* Find qdisc */
+		if (!*parent) {
+			*q = dev->qdisc;
+			*parent = (*q)->handle;
+		} else {
+			*q = qdisc_lookup(dev, TC_H_MAJ(*parent));
+			if (!*q) {
+				NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
+				return ERR_PTR(-EINVAL);
+			}
+		}
+
+		/* Is it classful? */
+		cops = (*q)->ops->cl_ops;
+		if (!cops) {
+			NL_SET_ERR_MSG(extack, "Qdisc not classful");
+			return ERR_PTR(-EINVAL);
+		}
+
+		if (!cops->tcf_block) {
+			NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+
+		/* Do we search for filter, attached to class? */
+		if (TC_H_MIN(*parent)) {
+			*cl = cops->find(*q, *parent);
+			if (*cl == 0) {
+				NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
+				return ERR_PTR(-ENOENT);
+			}
+		}
+
+		/* And the last stroke */
+		block = cops->tcf_block(*q, *cl, extack);
+		if (!block)
+			return ERR_PTR(-EINVAL);
+		if (tcf_block_shared(block)) {
+			NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
+			return ERR_PTR(-EOPNOTSUPP);
+		}
+	}
+
+	return block;
+}
+
 static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block)
 {
 	return list_first_entry(&block->chain_list, struct tcf_chain, list);
@@ -983,9 +1056,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb,
 			       q, parent, 0, event, false);
 }
 
-/* Add/change/delete/get a filter node */
-
-static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
+static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
@@ -1006,8 +1077,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	int err;
 	int tp_created;
 
-	if ((n->nlmsg_type != RTM_GETTFILTER) &&
-	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
 replay:
@@ -1025,24 +1095,13 @@ replay:
 	cl = 0;
 
 	if (prio == 0) {
-		switch (n->nlmsg_type) {
-		case RTM_DELTFILTER:
-			if (protocol || t->tcm_handle || tca[TCA_KIND]) {
-				NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set");
-				return -ENOENT;
-			}
-			break;
-		case RTM_NEWTFILTER:
-			/* If no priority is provided by the user,
-			 * we allocate one.
-			 */
-			if (n->nlmsg_flags & NLM_F_CREATE) {
-				prio = TC_H_MAKE(0x80000000U, 0U);
-				prio_allocate = true;
-				break;
-			}
-			/* fall-through */
-		default:
+		/* If no priority is provided by the user,
+		 * we allocate one.
+		 */
+		if (n->nlmsg_flags & NLM_F_CREATE) {
+			prio = TC_H_MAKE(0x80000000U, 0U);
+			prio_allocate = true;
+		} else {
 			NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
 			return -ENOENT;
 		}
@@ -1050,66 +1109,11 @@ replay:
 
 	/* Find head of filter chain. */
 
-	if (t->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
-		block = tcf_block_lookup(net, t->tcm_block_index);
-		if (!block) {
-			NL_SET_ERR_MSG(extack, "Block of given index was not found");
-			err = -EINVAL;
-			goto errout;
-		}
-	} else {
-		const struct Qdisc_class_ops *cops;
-		struct net_device *dev;
-
-		/* Find link */
-		dev = __dev_get_by_index(net, t->tcm_ifindex);
-		if (!dev)
-			return -ENODEV;
-
-		/* Find qdisc */
-		if (!parent) {
-			q = dev->qdisc;
-			parent = q->handle;
-		} else {
-			q = qdisc_lookup(dev, TC_H_MAJ(t->tcm_parent));
-			if (!q) {
-				NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
-				return -EINVAL;
-			}
-		}
-
-		/* Is it classful? */
-		cops = q->ops->cl_ops;
-		if (!cops) {
-			NL_SET_ERR_MSG(extack, "Qdisc not classful");
-			return -EINVAL;
-		}
-
-		if (!cops->tcf_block) {
-			NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
-			return -EOPNOTSUPP;
-		}
-
-		/* Do we search for filter, attached to class? */
-		if (TC_H_MIN(parent)) {
-			cl = cops->find(q, parent);
-			if (cl == 0) {
-				NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
-				return -ENOENT;
-			}
-		}
-
-		/* And the last stroke */
-		block = cops->tcf_block(q, cl, extack);
-		if (!block) {
-			err = -EINVAL;
-			goto errout;
-		}
-		if (tcf_block_shared(block)) {
-			NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
-			err = -EOPNOTSUPP;
-			goto errout;
-		}
+	block = tcf_block_find(net, &q, &parent, &cl,
+			       t->tcm_ifindex, t->tcm_block_index, extack);
+	if (IS_ERR(block)) {
+		err = PTR_ERR(block);
+		goto errout;
 	}
 
 	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
@@ -1118,19 +1122,10 @@ replay:
 		err = -EINVAL;
 		goto errout;
 	}
-	chain = tcf_chain_get(block, chain_index,
-			      n->nlmsg_type == RTM_NEWTFILTER);
+	chain = tcf_chain_get(block, chain_index, true);
 	if (!chain) {
 		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
-		err = n->nlmsg_type == RTM_NEWTFILTER ? -ENOMEM : -EINVAL;
-		goto errout;
-	}
-
-	if (n->nlmsg_type == RTM_DELTFILTER && prio == 0) {
-		tfilter_notify_chain(net, skb, block, q, parent, n,
-				     chain, RTM_DELTFILTER);
-		tcf_chain_flush(chain);
-		err = 0;
+		err = -ENOMEM;
 		goto errout;
 	}
 
@@ -1151,8 +1146,7 @@ replay:
 			goto errout;
 		}
 
-		if (n->nlmsg_type != RTM_NEWTFILTER ||
-		    !(n->nlmsg_flags & NLM_F_CREATE)) {
+		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
 			NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
 			err = -ENOENT;
 			goto errout;
@@ -1177,56 +1171,15 @@ replay:
 	fh = tp->ops->get(tp, t->tcm_handle);
 
 	if (!fh) {
-		if (n->nlmsg_type == RTM_DELTFILTER && t->tcm_handle == 0) {
-			tcf_chain_tp_remove(chain, &chain_info, tp);
-			tfilter_notify(net, skb, n, tp, block, q, parent, fh,
-				       RTM_DELTFILTER, false);
-			tcf_proto_destroy(tp, extack);
-			err = 0;
-			goto errout;
-		}
-
-		if (n->nlmsg_type != RTM_NEWTFILTER ||
-		    !(n->nlmsg_flags & NLM_F_CREATE)) {
+		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
 			NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter");
 			err = -ENOENT;
 			goto errout;
 		}
-	} else {
-		bool last;
-
-		switch (n->nlmsg_type) {
-		case RTM_NEWTFILTER:
-			if (n->nlmsg_flags & NLM_F_EXCL) {
-				if (tp_created)
-					tcf_proto_destroy(tp, NULL);
-				NL_SET_ERR_MSG(extack, "Filter already exists");
-				err = -EEXIST;
-				goto errout;
-			}
-			break;
-		case RTM_DELTFILTER:
-			err = tfilter_del_notify(net, skb, n, tp, block,
-						 q, parent, fh, false, &last,
-						 extack);
-			if (err)
-				goto errout;
-			if (last) {
-				tcf_chain_tp_remove(chain, &chain_info, tp);
-				tcf_proto_destroy(tp, extack);
-			}
-			goto errout;
-		case RTM_GETTFILTER:
-			err = tfilter_notify(net, skb, n, tp, block, q, parent,
-					     fh, RTM_NEWTFILTER, true);
-			if (err < 0)
-				NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
-			goto errout;
-		default:
-			NL_SET_ERR_MSG(extack, "Invalid netlink message type");
-			err = -EINVAL;
-			goto errout;
-		}
+	} else if (n->nlmsg_flags & NLM_F_EXCL) {
+		NL_SET_ERR_MSG(extack, "Filter already exists");
+		err = -EEXIST;
+		goto errout;
 	}
 
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
@@ -1251,6 +1204,202 @@ errout:
 	return err;
 }
 
+static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
+			  struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tca[TCA_MAX + 1];
+	struct tcmsg *t;
+	u32 protocol;
+	u32 prio;
+	u32 parent;
+	u32 chain_index;
+	struct Qdisc *q = NULL;
+	struct tcf_chain_info chain_info;
+	struct tcf_chain *chain = NULL;
+	struct tcf_block *block;
+	struct tcf_proto *tp = NULL;
+	unsigned long cl = 0;
+	void *fh = NULL;
+	int err;
+
+	if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+	if (err < 0)
+		return err;
+
+	t = nlmsg_data(n);
+	protocol = TC_H_MIN(t->tcm_info);
+	prio = TC_H_MAJ(t->tcm_info);
+	parent = t->tcm_parent;
+
+	if (prio == 0 && (protocol || t->tcm_handle || tca[TCA_KIND])) {
+		NL_SET_ERR_MSG(extack, "Cannot flush filters with protocol, handle or kind set");
+		return -ENOENT;
+	}
+
+	/* Find head of filter chain. */
+
+	block = tcf_block_find(net, &q, &parent, &cl,
+			       t->tcm_ifindex, t->tcm_block_index, extack);
+	if (IS_ERR(block)) {
+		err = PTR_ERR(block);
+		goto errout;
+	}
+
+	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+	if (chain_index > TC_ACT_EXT_VAL_MASK) {
+		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
+		err = -EINVAL;
+		goto errout;
+	}
+	chain = tcf_chain_get(block, chain_index, false);
+	if (!chain) {
+		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
+		err = -EINVAL;
+		goto errout;
+	}
+
+	if (prio == 0) {
+		tfilter_notify_chain(net, skb, block, q, parent, n,
+				     chain, RTM_DELTFILTER);
+		tcf_chain_flush(chain);
+		err = 0;
+		goto errout;
+	}
+
+	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
+			       prio, false);
+	if (!tp || IS_ERR(tp)) {
+		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
+		err = tp ? PTR_ERR(tp) : -ENOENT;
+		goto errout;
+	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
+		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
+		err = -EINVAL;
+		goto errout;
+	}
+
+	fh = tp->ops->get(tp, t->tcm_handle);
+
+	if (!fh) {
+		if (t->tcm_handle == 0) {
+			tcf_chain_tp_remove(chain, &chain_info, tp);
+			tfilter_notify(net, skb, n, tp, block, q, parent, fh,
+				       RTM_DELTFILTER, false);
+			tcf_proto_destroy(tp, extack);
+			err = 0;
+		} else {
+			NL_SET_ERR_MSG(extack, "Specified filter handle not found");
+			err = -ENOENT;
+		}
+	} else {
+		bool last;
+
+		err = tfilter_del_notify(net, skb, n, tp, block,
+					 q, parent, fh, false, &last,
+					 extack);
+		if (err)
+			goto errout;
+		if (last) {
+			tcf_chain_tp_remove(chain, &chain_info, tp);
+			tcf_proto_destroy(tp, extack);
+		}
+	}
+
+errout:
+	if (chain)
+		tcf_chain_put(chain);
+	return err;
+}
+
+static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
+			  struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tca[TCA_MAX + 1];
+	struct tcmsg *t;
+	u32 protocol;
+	u32 prio;
+	u32 parent;
+	u32 chain_index;
+	struct Qdisc *q = NULL;
+	struct tcf_chain_info chain_info;
+	struct tcf_chain *chain = NULL;
+	struct tcf_block *block;
+	struct tcf_proto *tp = NULL;
+	unsigned long cl = 0;
+	void *fh = NULL;
+	int err;
+
+	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+	if (err < 0)
+		return err;
+
+	t = nlmsg_data(n);
+	protocol = TC_H_MIN(t->tcm_info);
+	prio = TC_H_MAJ(t->tcm_info);
+	parent = t->tcm_parent;
+
+	if (prio == 0) {
+		NL_SET_ERR_MSG(extack, "Invalid filter command with priority of zero");
+		return -ENOENT;
+	}
+
+	/* Find head of filter chain. */
+
+	block = tcf_block_find(net, &q, &parent, &cl,
+			       t->tcm_ifindex, t->tcm_block_index, extack);
+	if (IS_ERR(block)) {
+		err = PTR_ERR(block);
+		goto errout;
+	}
+
+	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+	if (chain_index > TC_ACT_EXT_VAL_MASK) {
+		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
+		err = -EINVAL;
+		goto errout;
+	}
+	chain = tcf_chain_get(block, chain_index, false);
+	if (!chain) {
+		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
+		err = -EINVAL;
+		goto errout;
+	}
+
+	tp = tcf_chain_tp_find(chain, &chain_info, protocol,
+			       prio, false);
+	if (!tp || IS_ERR(tp)) {
+		NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found");
+		err = tp ? PTR_ERR(tp) : -ENOENT;
+		goto errout;
+	} else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) {
+		NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one");
+		err = -EINVAL;
+		goto errout;
+	}
+
+	fh = tp->ops->get(tp, t->tcm_handle);
+
+	if (!fh) {
+		NL_SET_ERR_MSG(extack, "Specified filter handle not found");
+		err = -ENOENT;
+	} else {
+		err = tfilter_notify(net, skb, n, tp, block, q, parent,
+				     fh, RTM_NEWTFILTER, true);
+		if (err < 0)
+			NL_SET_ERR_MSG(extack, "Failed to send filter notify message");
+	}
+
+errout:
+	if (chain)
+		tcf_chain_put(chain);
+	return err;
+}
+
 struct tcf_dump_args {
 	struct tcf_walker w;
 	struct sk_buff *skb;
@@ -1633,9 +1782,9 @@ static int __init tc_filter_init(void)
 	if (err)
 		goto err_register_pernet_subsys;
 
-	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,
+	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0);
+	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
+	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
 		      tc_dump_tfilter, 0);
 
 	return 0;
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 6b7ab3512f5b..95367f37098d 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -35,10 +35,7 @@ struct basic_filter {
 	struct tcf_result	res;
 	struct tcf_proto	*tp;
 	struct list_head	link;
-	union {
-		struct work_struct	work;
-		struct rcu_head		rcu;
-	};
+	struct rcu_work		rwork;
 };
 
 static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -97,21 +94,14 @@ static void __basic_delete_filter(struct basic_filter *f)
 
 static void basic_delete_filter_work(struct work_struct *work)
 {
-	struct basic_filter *f = container_of(work, struct basic_filter, work);
-
+	struct basic_filter *f = container_of(to_rcu_work(work),
+					      struct basic_filter,
+					      rwork);
 	rtnl_lock();
 	__basic_delete_filter(f);
 	rtnl_unlock();
 }
 
-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 netlink_ext_ack *extack)
 {
 	struct basic_head *head = rtnl_dereference(tp->root);
@@ -122,7 +112,7 @@ static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 		tcf_unbind_filter(tp, &f->res);
 		idr_remove(&head->handle_idr, f->handle);
 		if (tcf_exts_get_net(&f->exts))
-			call_rcu(&f->rcu, basic_delete_filter);
+			tcf_queue_work(&f->rwork, basic_delete_filter_work);
 		else
 			__basic_delete_filter(f);
 	}
@@ -140,7 +130,7 @@ static int basic_delete(struct tcf_proto *tp, void *arg, bool *last,
 	tcf_unbind_filter(tp, &f->res);
 	idr_remove(&head->handle_idr, f->handle);
 	tcf_exts_get_net(&f->exts);
-	call_rcu(&f->rcu, basic_delete_filter);
+	tcf_queue_work(&f->rwork, basic_delete_filter_work);
 	*last = list_empty(&head->flist);
 	return 0;
 }
@@ -234,7 +224,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 		list_replace_rcu(&fold->link, &fnew->link);
 		tcf_unbind_filter(tp, &fold->res);
 		tcf_exts_get_net(&fold->exts);
-		call_rcu(&fold->rcu, basic_delete_filter);
+		tcf_queue_work(&fold->rwork, basic_delete_filter_work);
 	} else {
 		list_add_rcu(&fnew->link, &head->flist);
 	}
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index b07c1fa8bc0d..1aa7f6511065 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -49,10 +49,7 @@ struct cls_bpf_prog {
 	struct sock_filter *bpf_ops;
 	const char *bpf_name;
 	struct tcf_proto *tp;
-	union {
-		struct work_struct work;
-		struct rcu_head rcu;
-	};
+	struct rcu_work rwork;
 };
 
 static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = {
@@ -275,21 +272,14 @@ static void __cls_bpf_delete_prog(struct cls_bpf_prog *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);
-
+	struct cls_bpf_prog *prog = container_of(to_rcu_work(work),
+						 struct cls_bpf_prog,
+						 rwork);
 	rtnl_lock();
 	__cls_bpf_delete_prog(prog);
 	rtnl_unlock();
 }
 
-static void cls_bpf_delete_prog_rcu(struct rcu_head *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,
 			     struct netlink_ext_ack *extack)
 {
@@ -300,7 +290,7 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	list_del_rcu(&prog->link);
 	tcf_unbind_filter(tp, &prog->res);
 	if (tcf_exts_get_net(&prog->exts))
-		call_rcu(&prog->rcu, cls_bpf_delete_prog_rcu);
+		tcf_queue_work(&prog->rwork, cls_bpf_delete_prog_work);
 	else
 		__cls_bpf_delete_prog(prog);
 }
@@ -526,7 +516,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 		list_replace_rcu(&oldprog->link, &prog->link);
 		tcf_unbind_filter(tp, &oldprog->res);
 		tcf_exts_get_net(&oldprog->exts);
-		call_rcu(&oldprog->rcu, cls_bpf_delete_prog_rcu);
+		tcf_queue_work(&oldprog->rwork, cls_bpf_delete_prog_work);
 	} else {
 		list_add_rcu(&prog->link, &head->plist);
 	}
diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c
index 762da5c0cf5e..3bc01bdde165 100644
--- a/net/sched/cls_cgroup.c
+++ b/net/sched/cls_cgroup.c
@@ -23,10 +23,7 @@ struct cls_cgroup_head {
 	struct tcf_exts		exts;
 	struct tcf_ematch_tree	ematches;
 	struct tcf_proto	*tp;
-	union {
-		struct work_struct	work;
-		struct rcu_head		rcu;
-	};
+	struct rcu_work		rwork;
 };
 
 static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -70,24 +67,14 @@ static void __cls_cgroup_destroy(struct cls_cgroup_head *head)
 
 static void cls_cgroup_destroy_work(struct work_struct *work)
 {
-	struct cls_cgroup_head *head = container_of(work,
+	struct cls_cgroup_head *head = container_of(to_rcu_work(work),
 						    struct cls_cgroup_head,
-						    work);
+						    rwork);
 	rtnl_lock();
 	__cls_cgroup_destroy(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);
-
-	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,
 			     struct tcf_proto *tp, unsigned long base,
 			     u32 handle, struct nlattr **tca,
@@ -134,7 +121,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 	rcu_assign_pointer(tp->root, new);
 	if (head) {
 		tcf_exts_get_net(&head->exts);
-		call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
+		tcf_queue_work(&head->rwork, cls_cgroup_destroy_work);
 	}
 	return 0;
 errout:
@@ -151,7 +138,7 @@ static void cls_cgroup_destroy(struct tcf_proto *tp,
 	/* Head can still be NULL due to cls_cgroup_init(). */
 	if (head) {
 		if (tcf_exts_get_net(&head->exts))
-			call_rcu(&head->rcu, cls_cgroup_destroy_rcu);
+			tcf_queue_work(&head->rwork, cls_cgroup_destroy_work);
 		else
 			__cls_cgroup_destroy(head);
 	}
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index cd5fe383afdd..2bb043cd436b 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -57,10 +57,7 @@ struct flow_filter {
 	u32			divisor;
 	u32			baseclass;
 	u32			hashrnd;
-	union {
-		struct work_struct	work;
-		struct rcu_head		rcu;
-	};
+	struct rcu_work		rwork;
 };
 
 static inline u32 addr_fold(void *addr)
@@ -383,21 +380,14 @@ static void __flow_destroy_filter(struct flow_filter *f)
 
 static void flow_destroy_filter_work(struct work_struct *work)
 {
-	struct flow_filter *f = container_of(work, struct flow_filter, work);
-
+	struct flow_filter *f = container_of(to_rcu_work(work),
+					     struct flow_filter,
+					     rwork);
 	rtnl_lock();
 	__flow_destroy_filter(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,
 		       struct tcf_proto *tp, unsigned long base,
 		       u32 handle, struct nlattr **tca,
@@ -563,7 +553,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 
 	if (fold) {
 		tcf_exts_get_net(&fold->exts);
-		call_rcu(&fold->rcu, flow_destroy_filter);
+		tcf_queue_work(&fold->rwork, flow_destroy_filter_work);
 	}
 	return 0;
 
@@ -583,7 +573,7 @@ static int flow_delete(struct tcf_proto *tp, void *arg, bool *last,
 
 	list_del_rcu(&f->list);
 	tcf_exts_get_net(&f->exts);
-	call_rcu(&f->rcu, flow_destroy_filter);
+	tcf_queue_work(&f->rwork, flow_destroy_filter_work);
 	*last = list_empty(&head->filters);
 	return 0;
 }
@@ -608,7 +598,7 @@ static void flow_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 	list_for_each_entry_safe(f, next, &head->filters, list) {
 		list_del_rcu(&f->list);
 		if (tcf_exts_get_net(&f->exts))
-			call_rcu(&f->rcu, flow_destroy_filter);
+			tcf_queue_work(&f->rwork, flow_destroy_filter_work);
 		else
 			__flow_destroy_filter(f);
 	}
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index c79f6e71512e..2b5be42a9f1c 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -61,24 +61,24 @@ struct fl_flow_mask_range {
 struct fl_flow_mask {
 	struct fl_flow_key key;
 	struct fl_flow_mask_range range;
-	struct rcu_head	rcu;
+	struct rhash_head ht_node;
+	struct rhashtable ht;
+	struct rhashtable_params filter_ht_params;
+	struct flow_dissector dissector;
+	struct list_head filters;
+	struct rcu_head rcu;
+	struct list_head list;
 };
 
 struct cls_fl_head {
 	struct rhashtable ht;
-	struct fl_flow_mask mask;
-	struct flow_dissector dissector;
-	bool mask_assigned;
-	struct list_head filters;
-	struct rhashtable_params ht_params;
-	union {
-		struct work_struct work;
-		struct rcu_head	rcu;
-	};
+	struct list_head masks;
+	struct rcu_work rwork;
 	struct idr handle_idr;
 };
 
 struct cls_fl_filter {
+	struct fl_flow_mask *mask;
 	struct rhash_head ht_node;
 	struct fl_flow_key mkey;
 	struct tcf_exts exts;
@@ -87,13 +87,17 @@ struct cls_fl_filter {
 	struct list_head list;
 	u32 handle;
 	u32 flags;
-	union {
-		struct work_struct work;
-		struct rcu_head	rcu;
-	};
+	struct rcu_work rwork;
 	struct net_device *hw_dev;
 };
 
+static const struct rhashtable_params mask_ht_params = {
+	.key_offset = offsetof(struct fl_flow_mask, key),
+	.key_len = sizeof(struct fl_flow_key),
+	.head_offset = offsetof(struct fl_flow_mask, ht_node),
+	.automatic_shrinking = true,
+};
+
 static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
 {
 	return mask->range.end - mask->range.start;
@@ -103,13 +107,19 @@ static void fl_mask_update_range(struct fl_flow_mask *mask)
 {
 	const u8 *bytes = (const u8 *) &mask->key;
 	size_t size = sizeof(mask->key);
-	size_t i, first = 0, last = size - 1;
+	size_t i, first = 0, last;
 
-	for (i = 0; i < sizeof(mask->key); i++) {
+	for (i = 0; i < size; i++) {
+		if (bytes[i]) {
+			first = i;
+			break;
+		}
+	}
+	last = first;
+	for (i = size - 1; i != first; i--) {
 		if (bytes[i]) {
-			if (!first && i)
-				first = i;
 			last = i;
+			break;
 		}
 	}
 	mask->range.start = rounddown(first, sizeof(long));
@@ -140,12 +150,11 @@ static void fl_clear_masked_range(struct fl_flow_key *key,
 	memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
 }
 
-static struct cls_fl_filter *fl_lookup(struct cls_fl_head *head,
+static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask,
 				       struct fl_flow_key *mkey)
 {
-	return rhashtable_lookup_fast(&head->ht,
-				      fl_key_get_start(mkey, &head->mask),
-				      head->ht_params);
+	return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask),
+				      mask->filter_ht_params);
 }
 
 static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -153,28 +162,28 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 {
 	struct cls_fl_head *head = rcu_dereference_bh(tp->root);
 	struct cls_fl_filter *f;
+	struct fl_flow_mask *mask;
 	struct fl_flow_key skb_key;
 	struct fl_flow_key skb_mkey;
 
-	if (!atomic_read(&head->ht.nelems))
-		return -1;
-
-	fl_clear_masked_range(&skb_key, &head->mask);
+	list_for_each_entry_rcu(mask, &head->masks, list) {
+		fl_clear_masked_range(&skb_key, mask);
 
-	skb_key.indev_ifindex = skb->skb_iif;
-	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
-	 * so do it rather here.
-	 */
-	skb_key.basic.n_proto = skb->protocol;
-	skb_flow_dissect_tunnel_info(skb, &head->dissector, &skb_key);
-	skb_flow_dissect(skb, &head->dissector, &skb_key, 0);
+		skb_key.indev_ifindex = skb->skb_iif;
+		/* skb_flow_dissect() does not set n_proto in case an unknown
+		 * protocol, so do it rather here.
+		 */
+		skb_key.basic.n_proto = skb->protocol;
+		skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key);
+		skb_flow_dissect(skb, &mask->dissector, &skb_key, 0);
 
-	fl_set_masked_key(&skb_mkey, &skb_key, &head->mask);
+		fl_set_masked_key(&skb_mkey, &skb_key, mask);
 
-	f = fl_lookup(head, &skb_mkey);
-	if (f && !tc_skip_sw(f->flags)) {
-		*res = f->res;
-		return tcf_exts_exec(skb, &f->exts, res);
+		f = fl_lookup(mask, &skb_mkey);
+		if (f && !tc_skip_sw(f->flags)) {
+			*res = f->res;
+			return tcf_exts_exec(skb, &f->exts, res);
+		}
 	}
 	return -1;
 }
@@ -187,11 +196,28 @@ static int fl_init(struct tcf_proto *tp)
 	if (!head)
 		return -ENOBUFS;
 
-	INIT_LIST_HEAD_RCU(&head->filters);
+	INIT_LIST_HEAD_RCU(&head->masks);
 	rcu_assign_pointer(tp->root, head);
 	idr_init(&head->handle_idr);
 
-	return 0;
+	return rhashtable_init(&head->ht, &mask_ht_params);
+}
+
+static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask,
+			bool async)
+{
+	if (!list_empty(&mask->filters))
+		return false;
+
+	rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params);
+	rhashtable_destroy(&mask->ht);
+	list_del_rcu(&mask->list);
+	if (async)
+		kfree_rcu(mask, rcu);
+	else
+		kfree(mask);
+
+	return true;
 }
 
 static void __fl_destroy_filter(struct cls_fl_filter *f)
@@ -203,21 +229,14 @@ static void __fl_destroy_filter(struct cls_fl_filter *f)
 
 static void fl_destroy_filter_work(struct work_struct *work)
 {
-	struct cls_fl_filter *f = container_of(work, struct cls_fl_filter, work);
+	struct cls_fl_filter *f = container_of(to_rcu_work(work),
+					struct cls_fl_filter, rwork);
 
 	rtnl_lock();
 	__fl_destroy_filter(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,
 				 struct netlink_ext_ack *extack)
 {
@@ -234,8 +253,6 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f,
 }
 
 static int fl_hw_replace_filter(struct tcf_proto *tp,
-				struct flow_dissector *dissector,
-				struct fl_flow_key *mask,
 				struct cls_fl_filter *f,
 				struct netlink_ext_ack *extack)
 {
@@ -247,8 +264,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
 	cls_flower.command = TC_CLSFLOWER_REPLACE;
 	cls_flower.cookie = (unsigned long) f;
-	cls_flower.dissector = dissector;
-	cls_flower.mask = mask;
+	cls_flower.dissector = &f->mask->dissector;
+	cls_flower.mask = &f->mask->key;
 	cls_flower.key = &f->mkey;
 	cls_flower.exts = &f->exts;
 	cls_flower.classid = f->res.classid;
@@ -283,51 +300,54 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 			 &cls_flower, false);
 }
 
-static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
+static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f,
 			struct netlink_ext_ack *extack)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
+	bool async = tcf_exts_get_net(&f->exts);
+	bool last;
 
 	idr_remove(&head->handle_idr, f->handle);
 	list_del_rcu(&f->list);
+	last = fl_mask_put(head, f->mask, async);
 	if (!tc_skip_hw(f->flags))
 		fl_hw_destroy_filter(tp, f, extack);
 	tcf_unbind_filter(tp, &f->res);
-	if (tcf_exts_get_net(&f->exts))
-		call_rcu(&f->rcu, fl_destroy_filter);
+	if (async)
+		tcf_queue_work(&f->rwork, fl_destroy_filter_work);
 	else
 		__fl_destroy_filter(f);
+
+	return last;
 }
 
 static void fl_destroy_sleepable(struct work_struct *work)
 {
-	struct cls_fl_head *head = container_of(work, struct cls_fl_head,
-						work);
-	if (head->mask_assigned)
-		rhashtable_destroy(&head->ht);
+	struct cls_fl_head *head = container_of(to_rcu_work(work),
+						struct cls_fl_head,
+						rwork);
+
+	rhashtable_destroy(&head->ht);
 	kfree(head);
 	module_put(THIS_MODULE);
 }
 
-static void fl_destroy_rcu(struct rcu_head *rcu)
-{
-	struct cls_fl_head *head = container_of(rcu, struct cls_fl_head, rcu);
-
-	INIT_WORK(&head->work, fl_destroy_sleepable);
-	schedule_work(&head->work);
-}
-
 static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
+	struct fl_flow_mask *mask, *next_mask;
 	struct cls_fl_filter *f, *next;
 
-	list_for_each_entry_safe(f, next, &head->filters, list)
-		__fl_delete(tp, f, extack);
+	list_for_each_entry_safe(mask, next_mask, &head->masks, list) {
+		list_for_each_entry_safe(f, next, &mask->filters, list) {
+			if (__fl_delete(tp, f, extack))
+				break;
+		}
+	}
 	idr_destroy(&head->handle_idr);
 
 	__module_get(THIS_MODULE);
-	call_rcu(&head->rcu, fl_destroy_rcu);
+	tcf_queue_work(&head->rwork, fl_destroy_sleepable);
 }
 
 static void *fl_get(struct tcf_proto *tp, u32 handle)
@@ -715,14 +735,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 	return ret;
 }
 
-static bool fl_mask_eq(struct fl_flow_mask *mask1,
-		       struct fl_flow_mask *mask2)
+static void fl_mask_copy(struct fl_flow_mask *dst,
+			 struct fl_flow_mask *src)
 {
-	const long *lmask1 = fl_key_get_start(&mask1->key, mask1);
-	const long *lmask2 = fl_key_get_start(&mask2->key, mask2);
+	const void *psrc = fl_key_get_start(&src->key, src);
+	void *pdst = fl_key_get_start(&dst->key, src);
 
-	return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) &&
-	       !memcmp(lmask1, lmask2, fl_mask_range(mask1));
+	memcpy(pdst, psrc, fl_mask_range(src));
+	dst->range = src->range;
 }
 
 static const struct rhashtable_params fl_ht_params = {
@@ -731,14 +751,13 @@ static const struct rhashtable_params fl_ht_params = {
 	.automatic_shrinking = true,
 };
 
-static int fl_init_hashtable(struct cls_fl_head *head,
-			     struct fl_flow_mask *mask)
+static int fl_init_mask_hashtable(struct fl_flow_mask *mask)
 {
-	head->ht_params = fl_ht_params;
-	head->ht_params.key_len = fl_mask_range(mask);
-	head->ht_params.key_offset += mask->range.start;
+	mask->filter_ht_params = fl_ht_params;
+	mask->filter_ht_params.key_len = fl_mask_range(mask);
+	mask->filter_ht_params.key_offset += mask->range.start;
 
-	return rhashtable_init(&head->ht, &head->ht_params);
+	return rhashtable_init(&mask->ht, &mask->filter_ht_params);
 }
 
 #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member)
@@ -761,8 +780,7 @@ static int fl_init_hashtable(struct cls_fl_head *head,
 			FL_KEY_SET(keys, cnt, id, member);			\
 	} while(0);
 
-static void fl_init_dissector(struct cls_fl_head *head,
-			      struct fl_flow_mask *mask)
+static void fl_init_dissector(struct fl_flow_mask *mask)
 {
 	struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
 	size_t cnt = 0;
@@ -802,31 +820,66 @@ static void fl_init_dissector(struct cls_fl_head *head,
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
 
-	skb_flow_dissector_init(&head->dissector, keys, cnt);
+	skb_flow_dissector_init(&mask->dissector, keys, cnt);
+}
+
+static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
+					       struct fl_flow_mask *mask)
+{
+	struct fl_flow_mask *newmask;
+	int err;
+
+	newmask = kzalloc(sizeof(*newmask), GFP_KERNEL);
+	if (!newmask)
+		return ERR_PTR(-ENOMEM);
+
+	fl_mask_copy(newmask, mask);
+
+	err = fl_init_mask_hashtable(newmask);
+	if (err)
+		goto errout_free;
+
+	fl_init_dissector(newmask);
+
+	INIT_LIST_HEAD_RCU(&newmask->filters);
+
+	err = rhashtable_insert_fast(&head->ht, &newmask->ht_node,
+				     mask_ht_params);
+	if (err)
+		goto errout_destroy;
+
+	list_add_tail_rcu(&newmask->list, &head->masks);
+
+	return newmask;
+
+errout_destroy:
+	rhashtable_destroy(&newmask->ht);
+errout_free:
+	kfree(newmask);
+
+	return ERR_PTR(err);
 }
 
 static int fl_check_assign_mask(struct cls_fl_head *head,
+				struct cls_fl_filter *fnew,
+				struct cls_fl_filter *fold,
 				struct fl_flow_mask *mask)
 {
-	int err;
+	struct fl_flow_mask *newmask;
 
-	if (head->mask_assigned) {
-		if (!fl_mask_eq(&head->mask, mask))
+	fnew->mask = rhashtable_lookup_fast(&head->ht, mask, mask_ht_params);
+	if (!fnew->mask) {
+		if (fold)
 			return -EINVAL;
-		else
-			return 0;
-	}
 
-	/* Mask is not assigned yet. So assign it and init hashtable
-	 * according to that.
-	 */
-	err = fl_init_hashtable(head, mask);
-	if (err)
-		return err;
-	memcpy(&head->mask, mask, sizeof(head->mask));
-	head->mask_assigned = true;
+		newmask = fl_create_new_mask(head, mask);
+		if (IS_ERR(newmask))
+			return PTR_ERR(newmask);
 
-	fl_init_dissector(head, mask);
+		fnew->mask = newmask;
+	} else if (fold && fold->mask != fnew->mask) {
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -924,30 +977,26 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (err)
 		goto errout_idr;
 
-	err = fl_check_assign_mask(head, &mask);
+	err = fl_check_assign_mask(head, fnew, fold, &mask);
 	if (err)
 		goto errout_idr;
 
 	if (!tc_skip_sw(fnew->flags)) {
-		if (!fold && fl_lookup(head, &fnew->mkey)) {
+		if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
 			err = -EEXIST;
-			goto errout_idr;
+			goto errout_mask;
 		}
 
-		err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
-					     head->ht_params);
+		err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
+					     fnew->mask->filter_ht_params);
 		if (err)
-			goto errout_idr;
+			goto errout_mask;
 	}
 
 	if (!tc_skip_hw(fnew->flags)) {
-		err = fl_hw_replace_filter(tp,
-					   &head->dissector,
-					   &mask.key,
-					   fnew,
-					   extack);
+		err = fl_hw_replace_filter(tp, fnew, extack);
 		if (err)
-			goto errout_idr;
+			goto errout_mask;
 	}
 
 	if (!tc_in_hw(fnew->flags))
@@ -955,8 +1004,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 
 	if (fold) {
 		if (!tc_skip_sw(fold->flags))
-			rhashtable_remove_fast(&head->ht, &fold->ht_node,
-					       head->ht_params);
+			rhashtable_remove_fast(&fold->mask->ht,
+					       &fold->ht_node,
+					       fold->mask->filter_ht_params);
 		if (!tc_skip_hw(fold->flags))
 			fl_hw_destroy_filter(tp, fold, NULL);
 	}
@@ -968,14 +1018,17 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 		list_replace_rcu(&fold->list, &fnew->list);
 		tcf_unbind_filter(tp, &fold->res);
 		tcf_exts_get_net(&fold->exts);
-		call_rcu(&fold->rcu, fl_destroy_filter);
+		tcf_queue_work(&fold->rwork, fl_destroy_filter_work);
 	} else {
-		list_add_tail_rcu(&fnew->list, &head->filters);
+		list_add_tail_rcu(&fnew->list, &fnew->mask->filters);
 	}
 
 	kfree(tb);
 	return 0;
 
+errout_mask:
+	fl_mask_put(head, fnew->mask, false);
+
 errout_idr:
 	if (!fold)
 		idr_remove(&head->handle_idr, fnew->handle);
@@ -994,10 +1047,10 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last,
 	struct cls_fl_filter *f = arg;
 
 	if (!tc_skip_sw(f->flags))
-		rhashtable_remove_fast(&head->ht, &f->ht_node,
-				       head->ht_params);
+		rhashtable_remove_fast(&f->mask->ht, &f->ht_node,
+				       f->mask->filter_ht_params);
 	__fl_delete(tp, f, extack);
-	*last = list_empty(&head->filters);
+	*last = list_empty(&head->masks);
 	return 0;
 }
 
@@ -1005,16 +1058,19 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *f;
-
-	list_for_each_entry_rcu(f, &head->filters, list) {
-		if (arg->count < arg->skip)
-			goto skip;
-		if (arg->fn(tp, f, arg) < 0) {
-			arg->stop = 1;
-			break;
-		}
+	struct fl_flow_mask *mask;
+
+	list_for_each_entry_rcu(mask, &head->masks, list) {
+		list_for_each_entry_rcu(f, &mask->filters, list) {
+			if (arg->count < arg->skip)
+				goto skip;
+			if (arg->fn(tp, f, arg) < 0) {
+				arg->stop = 1;
+				break;
+			}
 skip:
-		arg->count++;
+			arg->count++;
+		}
 	}
 }
 
@@ -1150,7 +1206,6 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
 static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 		   struct sk_buff *skb, struct tcmsg *t)
 {
-	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *f = fh;
 	struct nlattr *nest;
 	struct fl_flow_key *key, *mask;
@@ -1169,7 +1224,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 		goto nla_put_failure;
 
 	key = &f->key;
-	mask = &head->mask.key;
+	mask = &f->mask->key;
 
 	if (mask->indev_ifindex) {
 		struct net_device *dev;
diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c
index 8b207723fbc2..29eeeaf3ea44 100644
--- a/net/sched/cls_fw.c
+++ b/net/sched/cls_fw.c
@@ -47,10 +47,7 @@ struct fw_filter {
 #endif /* CONFIG_NET_CLS_IND */
 	struct tcf_exts		exts;
 	struct tcf_proto	*tp;
-	union {
-		struct work_struct	work;
-		struct rcu_head		rcu;
-	};
+	struct rcu_work		rwork;
 };
 
 static u32 fw_hash(u32 handle)
@@ -134,21 +131,14 @@ static void __fw_delete_filter(struct fw_filter *f)
 
 static void fw_delete_filter_work(struct work_struct *work)
 {
-	struct fw_filter *f = container_of(work, struct fw_filter, work);
-
+	struct fw_filter *f = container_of(to_rcu_work(work),
+					   struct fw_filter,
+					   rwork);
 	rtnl_lock();
 	__fw_delete_filter(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, struct netlink_ext_ack *extack)
 {
 	struct fw_head *head = rtnl_dereference(tp->root);
@@ -164,7 +154,7 @@ static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 					 rtnl_dereference(f->next));
 			tcf_unbind_filter(tp, &f->res);
 			if (tcf_exts_get_net(&f->exts))
-				call_rcu(&f->rcu, fw_delete_filter);
+				tcf_queue_work(&f->rwork, fw_delete_filter_work);
 			else
 				__fw_delete_filter(f);
 		}
@@ -193,7 +183,7 @@ static int fw_delete(struct tcf_proto *tp, void *arg, bool *last,
 			RCU_INIT_POINTER(*fp, rtnl_dereference(f->next));
 			tcf_unbind_filter(tp, &f->res);
 			tcf_exts_get_net(&f->exts);
-			call_rcu(&f->rcu, fw_delete_filter);
+			tcf_queue_work(&f->rwork, fw_delete_filter_work);
 			ret = 0;
 			break;
 		}
@@ -316,7 +306,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 		rcu_assign_pointer(*fp, fnew);
 		tcf_unbind_filter(tp, &f->res);
 		tcf_exts_get_net(&f->exts);
-		call_rcu(&f->rcu, fw_delete_filter);
+		tcf_queue_work(&f->rwork, fw_delete_filter_work);
 
 		*arg = fnew;
 		return err;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 2ba721a590a7..47b207ef7762 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -21,10 +21,7 @@ struct cls_mall_head {
 	struct tcf_result res;
 	u32 handle;
 	u32 flags;
-	union {
-		struct work_struct work;
-		struct rcu_head	rcu;
-	};
+	struct rcu_work rwork;
 };
 
 static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
@@ -53,22 +50,14 @@ static void __mall_destroy(struct cls_mall_head *head)
 
 static void mall_destroy_work(struct work_struct *work)
 {
-	struct cls_mall_head *head = container_of(work, struct cls_mall_head,
-						  work);
+	struct cls_mall_head *head = container_of(to_rcu_work(work),
+						  struct cls_mall_head,
+						  rwork);
 	rtnl_lock();
 	__mall_destroy(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);
-
-	INIT_WORK(&head->work, mall_destroy_work);
-	tcf_queue_work(&head->work);
-}
-
 static void mall_destroy_hw_filter(struct tcf_proto *tp,
 				   struct cls_mall_head *head,
 				   unsigned long cookie,
@@ -126,7 +115,7 @@ static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 		mall_destroy_hw_filter(tp, head, (unsigned long) head, extack);
 
 	if (tcf_exts_get_net(&head->exts))
-		call_rcu(&head->rcu, mall_destroy_rcu);
+		tcf_queue_work(&head->rwork, mall_destroy_work);
 	else
 		__mall_destroy(head);
 }
diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c
index 21a03a8ee029..0404aa5fa7cb 100644
--- a/net/sched/cls_route.c
+++ b/net/sched/cls_route.c
@@ -57,10 +57,7 @@ struct route4_filter {
 	u32			handle;
 	struct route4_bucket	*bkt;
 	struct tcf_proto	*tp;
-	union {
-		struct work_struct	work;
-		struct rcu_head		rcu;
-	};
+	struct rcu_work		rwork;
 };
 
 #define ROUTE4_FAILURE ((struct route4_filter *)(-1L))
@@ -266,19 +263,17 @@ static void __route4_delete_filter(struct route4_filter *f)
 
 static void route4_delete_filter_work(struct work_struct *work)
 {
-	struct route4_filter *f = container_of(work, struct route4_filter, work);
-
+	struct route4_filter *f = container_of(to_rcu_work(work),
+					       struct route4_filter,
+					       rwork);
 	rtnl_lock();
 	__route4_delete_filter(f);
 	rtnl_unlock();
 }
 
-static void route4_delete_filter(struct rcu_head *head)
+static void route4_queue_work(struct route4_filter *f)
 {
-	struct route4_filter *f = container_of(head, struct route4_filter, rcu);
-
-	INIT_WORK(&f->work, route4_delete_filter_work);
-	tcf_queue_work(&f->work);
+	tcf_queue_work(&f->rwork, route4_delete_filter_work);
 }
 
 static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
@@ -304,7 +299,7 @@ static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 					RCU_INIT_POINTER(b->ht[h2], next);
 					tcf_unbind_filter(tp, &f->res);
 					if (tcf_exts_get_net(&f->exts))
-						call_rcu(&f->rcu, route4_delete_filter);
+						route4_queue_work(f);
 					else
 						__route4_delete_filter(f);
 				}
@@ -349,7 +344,7 @@ static int route4_delete(struct tcf_proto *tp, void *arg, bool *last,
 			/* Delete it */
 			tcf_unbind_filter(tp, &f->res);
 			tcf_exts_get_net(&f->exts);
-			call_rcu(&f->rcu, route4_delete_filter);
+			tcf_queue_work(&f->rwork, route4_delete_filter_work);
 
 			/* Strip RTNL protected tree */
 			for (i = 0; i <= 32; i++) {
@@ -554,7 +549,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 	if (fold) {
 		tcf_unbind_filter(tp, &fold->res);
 		tcf_exts_get_net(&fold->exts);
-		call_rcu(&fold->rcu, route4_delete_filter);
+		tcf_queue_work(&fold->rwork, route4_delete_filter_work);
 	}
 	return 0;
 
diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h
index 4f1297657c27..e9ccf7daea7d 100644
--- a/net/sched/cls_rsvp.h
+++ b/net/sched/cls_rsvp.h
@@ -97,10 +97,7 @@ struct rsvp_filter {
 
 	u32				handle;
 	struct rsvp_session		*sess;
-	union {
-		struct work_struct		work;
-		struct rcu_head			rcu;
-	};
+	struct rcu_work			rwork;
 };
 
 static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid)
@@ -294,21 +291,14 @@ static void __rsvp_delete_filter(struct rsvp_filter *f)
 
 static void rsvp_delete_filter_work(struct work_struct *work)
 {
-	struct rsvp_filter *f = container_of(work, struct rsvp_filter, work);
-
+	struct rsvp_filter *f = container_of(to_rcu_work(work),
+					     struct rsvp_filter,
+					     rwork);
 	rtnl_lock();
 	__rsvp_delete_filter(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)
 {
 	tcf_unbind_filter(tp, &f->res);
@@ -317,7 +307,7 @@ static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f)
 	 * in cleanup() callback
 	 */
 	if (tcf_exts_get_net(&f->exts))
-		call_rcu(&f->rcu, rsvp_delete_filter_rcu);
+		tcf_queue_work(&f->rwork, rsvp_delete_filter_work);
 	else
 		__rsvp_delete_filter(f);
 }
diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index b49cc990a000..32f4bbd82f35 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -28,20 +28,14 @@
 struct tcindex_filter_result {
 	struct tcf_exts		exts;
 	struct tcf_result	res;
-	union {
-		struct work_struct	work;
-		struct rcu_head		rcu;
-	};
+	struct rcu_work		rwork;
 };
 
 struct tcindex_filter {
 	u16 key;
 	struct tcindex_filter_result result;
 	struct tcindex_filter __rcu *next;
-	union {
-		struct work_struct work;
-		struct rcu_head rcu;
-	};
+	struct rcu_work rwork;
 };
 
 
@@ -152,21 +146,14 @@ static void tcindex_destroy_rexts_work(struct work_struct *work)
 {
 	struct tcindex_filter_result *r;
 
-	r = container_of(work, struct tcindex_filter_result, work);
+	r = container_of(to_rcu_work(work),
+			 struct tcindex_filter_result,
+			 rwork);
 	rtnl_lock();
 	__tcindex_destroy_rexts(r);
 	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);
-	INIT_WORK(&r->work, tcindex_destroy_rexts_work);
-	tcf_queue_work(&r->work);
-}
-
 static void __tcindex_destroy_fexts(struct tcindex_filter *f)
 {
 	tcf_exts_destroy(&f->result.exts);
@@ -176,23 +163,15 @@ static void __tcindex_destroy_fexts(struct tcindex_filter *f)
 
 static void tcindex_destroy_fexts_work(struct work_struct *work)
 {
-	struct tcindex_filter *f = container_of(work, struct tcindex_filter,
-						work);
+	struct tcindex_filter *f = container_of(to_rcu_work(work),
+						struct tcindex_filter,
+						rwork);
 
 	rtnl_lock();
 	__tcindex_destroy_fexts(f);
 	rtnl_unlock();
 }
 
-static void tcindex_destroy_fexts(struct rcu_head *head)
-{
-	struct tcindex_filter *f = container_of(head, struct tcindex_filter,
-						rcu);
-
-	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,
 			  struct netlink_ext_ack *extack)
 {
@@ -228,12 +207,12 @@ found:
 	 */
 	if (f) {
 		if (tcf_exts_get_net(&f->result.exts))
-			call_rcu(&f->rcu, tcindex_destroy_fexts);
+			tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work);
 		else
 			__tcindex_destroy_fexts(f);
 	} else {
 		if (tcf_exts_get_net(&r->exts))
-			call_rcu(&r->rcu, tcindex_destroy_rexts);
+			tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work);
 		else
 			__tcindex_destroy_rexts(r);
 	}
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index bac47b5d18fd..fb861f90fde6 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -68,10 +68,7 @@ struct tc_u_knode {
 	u32 __percpu		*pcpu_success;
 #endif
 	struct tcf_proto	*tp;
-	union {
-		struct work_struct	work;
-		struct rcu_head		rcu;
-	};
+	struct rcu_work		rwork;
 	/* The 'sel' field MUST be the last field in structure to allow for
 	 * tc_u32_keys allocated at end of structure.
 	 */
@@ -436,21 +433,14 @@ static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
  */
 static void u32_delete_key_work(struct work_struct *work)
 {
-	struct tc_u_knode *key = container_of(work, struct tc_u_knode, work);
-
+	struct tc_u_knode *key = container_of(to_rcu_work(work),
+					      struct tc_u_knode,
+					      rwork);
 	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);
-
-	INIT_WORK(&key->work, u32_delete_key_work);
-	tcf_queue_work(&key->work);
-}
-
 /* u32_delete_key_freepf_rcu is the rcu callback variant
  * that free's the entire structure including the statistics
  * percpu variables. Only use this if the key is not a copy
@@ -460,21 +450,14 @@ static void u32_delete_key_rcu(struct rcu_head *rcu)
  */
 static void u32_delete_key_freepf_work(struct work_struct *work)
 {
-	struct tc_u_knode *key = container_of(work, struct tc_u_knode, work);
-
+	struct tc_u_knode *key = container_of(to_rcu_work(work),
+					      struct tc_u_knode,
+					      rwork);
 	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);
-
-	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)
 {
 	struct tc_u_knode __rcu **kp;
@@ -491,7 +474,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 				tcf_unbind_filter(tp, &key->res);
 				idr_remove(&ht->handle_idr, key->handle);
 				tcf_exts_get_net(&key->exts);
-				call_rcu(&key->rcu, u32_delete_key_freepf_rcu);
+				tcf_queue_work(&key->rwork, u32_delete_key_freepf_work);
 				return 0;
 			}
 		}
@@ -611,7 +594,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 			u32_remove_hw_knode(tp, n, extack);
 			idr_remove(&ht->handle_idr, n->handle);
 			if (tcf_exts_get_net(&n->exts))
-				call_rcu(&n->rcu, u32_delete_key_freepf_rcu);
+				tcf_queue_work(&n->rwork, u32_delete_key_freepf_work);
 			else
 				u32_destroy_key(n->tp, n, true);
 		}
@@ -995,7 +978,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		u32_replace_knode(tp, tp_c, new);
 		tcf_unbind_filter(tp, &n->res);
 		tcf_exts_get_net(&n->exts);
-		call_rcu(&n->rcu, u32_delete_key_rcu);
+		tcf_queue_work(&n->rwork, u32_delete_key_work);
 		return 0;
 	}
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 39c144b6ff98..69078c82963e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -346,9 +346,6 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
 		return false;
 	}
 
-	if (ret && netif_xmit_frozen_or_stopped(txq))
-		return false;
-
 	return true;
 }
 
@@ -373,33 +370,24 @@ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q,
  */
 static inline bool qdisc_restart(struct Qdisc *q, int *packets)
 {
-	bool more, validate, nolock = q->flags & TCQ_F_NOLOCK;
 	spinlock_t *root_lock = NULL;
 	struct netdev_queue *txq;
 	struct net_device *dev;
 	struct sk_buff *skb;
+	bool validate;
 
 	/* Dequeue packet */
-	if (nolock && test_and_set_bit(__QDISC_STATE_RUNNING, &q->state))
-		return false;
-
 	skb = dequeue_skb(q, &validate, packets);
-	if (unlikely(!skb)) {
-		if (nolock)
-			clear_bit(__QDISC_STATE_RUNNING, &q->state);
+	if (unlikely(!skb))
 		return false;
-	}
 
-	if (!nolock)
+	if (!(q->flags & TCQ_F_NOLOCK))
 		root_lock = qdisc_lock(q);
 
 	dev = qdisc_dev(q);
 	txq = skb_get_tx_queue(dev, skb);
 
-	more = sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
-	if (nolock)
-		clear_bit(__QDISC_STATE_RUNNING, &q->state);
-	return more;
+	return sch_direct_xmit(skb, q, dev, txq, root_lock, validate);
 }
 
 void __qdisc_run(struct Qdisc *q)
@@ -665,7 +653,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc)
 		if (__skb_array_empty(q))
 			continue;
 
-		skb = skb_array_consume_bh(q);
+		skb = __skb_array_consume(q);
 	}
 	if (likely(skb)) {
 		qdisc_qstats_cpu_backlog_dec(qdisc, skb);
@@ -706,7 +694,7 @@ static void pfifo_fast_reset(struct Qdisc *qdisc)
 		if (!q->ring.queue)
 			continue;
 
-		while ((skb = skb_array_consume_bh(q)) != NULL)
+		while ((skb = __skb_array_consume(q)) != NULL)
 			kfree_skb(skb);
 	}
 
@@ -867,6 +855,11 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
 	lockdep_set_class(&sch->busylock,
 			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
 
+	/* seqlock has the same scope of busylock, for NOLOCK qdisc */
+	spin_lock_init(&sch->seqlock);
+	lockdep_set_class(&sch->busylock,
+			  dev->qdisc_tx_busylock ?: &qdisc_tx_busylock);
+
 	seqcount_init(&sch->running);
 	lockdep_set_class(&sch->running,
 			  dev->qdisc_running_key ?: &qdisc_running_key);
@@ -1106,6 +1099,10 @@ static void dev_deactivate_queue(struct net_device *dev,
 
 	qdisc = rtnl_dereference(dev_queue->qdisc);
 	if (qdisc) {
+		bool nolock = qdisc->flags & TCQ_F_NOLOCK;
+
+		if (nolock)
+			spin_lock_bh(&qdisc->seqlock);
 		spin_lock_bh(qdisc_lock(qdisc));
 
 		if (!(qdisc->flags & TCQ_F_BUILTIN))
@@ -1115,6 +1112,8 @@ static void dev_deactivate_queue(struct net_device *dev,
 		qdisc_reset(qdisc);
 
 		spin_unlock_bh(qdisc_lock(qdisc));
+		if (nolock)
+			spin_unlock_bh(&qdisc->seqlock);
 	}
 }
 
@@ -1131,17 +1130,13 @@ static bool some_qdisc_is_busy(struct net_device *dev)
 		dev_queue = netdev_get_tx_queue(dev, i);
 		q = dev_queue->qdisc_sleeping;
 
-		if (q->flags & TCQ_F_NOLOCK) {
-			val = test_bit(__QDISC_STATE_SCHED, &q->state);
-		} else {
-			root_lock = qdisc_lock(q);
-			spin_lock_bh(root_lock);
+		root_lock = qdisc_lock(q);
+		spin_lock_bh(root_lock);
 
-			val = (qdisc_is_running(q) ||
-			       test_bit(__QDISC_STATE_SCHED, &q->state));
+		val = (qdisc_is_running(q) ||
+		       test_bit(__QDISC_STATE_SCHED, &q->state));
 
-			spin_unlock_bh(root_lock);
-		}
+		spin_unlock_bh(root_lock);
 
 		if (val)
 			return true;
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f062a18e9162..d6b8ae4ed7a3 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -16,6 +16,7 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <net/netlink.h>
+#include <net/pkt_cls.h>
 #include <net/pkt_sched.h>
 #include <net/sch_generic.h>
 
@@ -23,12 +24,44 @@ struct mq_sched {
 	struct Qdisc		**qdiscs;
 };
 
+static int mq_offload(struct Qdisc *sch, enum tc_mq_command cmd)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_mq_qopt_offload opt = {
+		.command = cmd,
+		.handle = sch->handle,
+	};
+
+	if (!tc_can_offload(dev) || !dev->netdev_ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt);
+}
+
+static void mq_offload_stats(struct Qdisc *sch)
+{
+	struct net_device *dev = qdisc_dev(sch);
+	struct tc_mq_qopt_offload opt = {
+		.command = TC_MQ_STATS,
+		.handle = sch->handle,
+		.stats = {
+			.bstats = &sch->bstats,
+			.qstats = &sch->qstats,
+		},
+	};
+
+	if (tc_can_offload(dev) && dev->netdev_ops->ndo_setup_tc)
+		dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQ, &opt);
+}
+
 static void mq_destroy(struct Qdisc *sch)
 {
 	struct net_device *dev = qdisc_dev(sch);
 	struct mq_sched *priv = qdisc_priv(sch);
 	unsigned int ntx;
 
+	mq_offload(sch, TC_MQ_DESTROY);
+
 	if (!priv->qdiscs)
 		return;
 	for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++)
@@ -70,6 +103,8 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	sch->flags |= TCQ_F_MQROOT;
+
+	mq_offload(sch, TC_MQ_CREATE);
 	return 0;
 }
 
@@ -127,6 +162,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 			sch->q.qlen		+= qdisc->q.qlen;
 			sch->bstats.bytes	+= qdisc->bstats.bytes;
 			sch->bstats.packets	+= qdisc->bstats.packets;
+			sch->qstats.qlen	+= qdisc->qstats.qlen;
 			sch->qstats.backlog	+= qdisc->qstats.backlog;
 			sch->qstats.drops	+= qdisc->qstats.drops;
 			sch->qstats.requeues	+= qdisc->qstats.requeues;
@@ -135,6 +171,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 		spin_unlock_bh(qdisc_lock(qdisc));
 	}
+	mq_offload_stats(sch);
 
 	return 0;
 }