Merge branch 'net-sched-convert-cls-ndo_setup_tc-offload-calls-to-per-block-callbacks'

Jiri Pirko says:

====================
net: sched: convert cls ndo_setup_tc offload calls to per-block callbacks

This patchset is a bit bigger, but most of the patches are doing the
same changes in multiple classifiers and drivers. I could do some
squashes, but I think it is better split.

This is another dependency on the way to shared block implementation.
The goal is to remove use of tp->q in classifiers code.

Also, this provides drivers possibility to track binding of blocks to
qdiscs. Legacy drivers which do not support shared block offloading.
register one callback per binding. That maintains the current
functionality we have with ndo_setup_tc. Drivers which support block
sharing offload register one callback per block which safes overhead.

Patches 1-4 introduce the binding notifications and per-block callbacks
Patches 5-8 add block callbacks calls to classifiers
Patches 9-17 do convert from ndo_setup_tc calls to block callbacks for
             classifier offloads in drivers
Patches 18-20 do cleanup

v1->v2:
- patch1:
  - move new enum value to the end
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 346 insertions, 118 deletions

diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 6906de0f0050..d0ae7010ea45 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -777,17 +777,9 @@ static void dsa_slave_del_cls_matchall(struct net_device *dev,
 }
 
 static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev,
-					   struct tc_cls_matchall_offload *cls)
+					   struct tc_cls_matchall_offload *cls,
+					   bool ingress)
 {
-	bool ingress;
-
-	if (is_classid_clsact_ingress(cls->common.classid))
-		ingress = true;
-	else if (is_classid_clsact_egress(cls->common.classid))
-		ingress = false;
-	else
-		return -EOPNOTSUPP;
-
 	if (cls->common.chain_index)
 		return -EOPNOTSUPP;
 
@@ -802,12 +794,60 @@ static int dsa_slave_setup_tc_cls_matchall(struct net_device *dev,
 	}
 }
 
+static int dsa_slave_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				       void *cb_priv, bool ingress)
+{
+	struct net_device *dev = cb_priv;
+
+	switch (type) {
+	case TC_SETUP_CLSMATCHALL:
+		return dsa_slave_setup_tc_cls_matchall(dev, type_data, ingress);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int dsa_slave_setup_tc_block_cb_ig(enum tc_setup_type type,
+					  void *type_data, void *cb_priv)
+{
+	return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, true);
+}
+
+static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type,
+					  void *type_data, void *cb_priv)
+{
+	return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false);
+}
+
+static int dsa_slave_setup_tc_block(struct net_device *dev,
+				    struct tc_block_offload *f)
+{
+	tc_setup_cb_t *cb;
+
+	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		cb = dsa_slave_setup_tc_block_cb_ig;
+	else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+		cb = dsa_slave_setup_tc_block_cb_eg;
+	else
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block, cb, dev, dev);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, cb, dev);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int dsa_slave_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
 	switch (type) {
-	case TC_SETUP_CLSMATCHALL:
-		return dsa_slave_setup_tc_cls_matchall(dev, type_data);
+	case TC_SETUP_BLOCK:
+		return dsa_slave_setup_tc_block(dev, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2e8e87fd9d97..cdfdc24b89cf 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -240,8 +240,36 @@ tcf_chain_filter_chain_ptr_set(struct tcf_chain *chain,
 	chain->p_filter_chain = p_filter_chain;
 }
 
-int tcf_block_get(struct tcf_block **p_block,
-		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+static void tcf_block_offload_cmd(struct tcf_block *block, struct Qdisc *q,
+				  struct tcf_block_ext_info *ei,
+				  enum tc_block_command command)
+{
+	struct net_device *dev = q->dev_queue->dev;
+	struct tc_block_offload bo = {};
+
+	if (!tc_can_offload(dev))
+		return;
+	bo.command = command;
+	bo.binder_type = ei->binder_type;
+	bo.block = block;
+	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+}
+
+static void tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
+				   struct tcf_block_ext_info *ei)
+{
+	tcf_block_offload_cmd(block, q, ei, TC_BLOCK_BIND);
+}
+
+static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
+				     struct tcf_block_ext_info *ei)
+{
+	tcf_block_offload_cmd(block, q, ei, TC_BLOCK_UNBIND);
+}
+
+int tcf_block_get_ext(struct tcf_block **p_block,
+		      struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
+		      struct tcf_block_ext_info *ei)
 {
 	struct tcf_block *block = kzalloc(sizeof(*block), GFP_KERNEL);
 	struct tcf_chain *chain;
@@ -250,6 +278,8 @@ int tcf_block_get(struct tcf_block **p_block,
 	if (!block)
 		return -ENOMEM;
 	INIT_LIST_HEAD(&block->chain_list);
+	INIT_LIST_HEAD(&block->cb_list);
+
 	/* Create chain 0 by default, it has to be always present. */
 	chain = tcf_chain_create(block, 0);
 	if (!chain) {
@@ -259,6 +289,7 @@ int tcf_block_get(struct tcf_block **p_block,
 	tcf_chain_filter_chain_ptr_set(chain, p_filter_chain);
 	block->net = qdisc_net(q);
 	block->q = q;
+	tcf_block_offload_bind(block, q, ei);
 	*p_block = block;
 	return 0;
 
@@ -266,15 +297,28 @@ err_chain_create:
 	kfree(block);
 	return err;
 }
+EXPORT_SYMBOL(tcf_block_get_ext);
+
+int tcf_block_get(struct tcf_block **p_block,
+		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q)
+{
+	struct tcf_block_ext_info ei = {0, };
+
+	return tcf_block_get_ext(p_block, p_filter_chain, q, &ei);
+}
 EXPORT_SYMBOL(tcf_block_get);
 
-void tcf_block_put(struct tcf_block *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)
 {
 	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
@@ -302,8 +346,119 @@ void tcf_block_put(struct tcf_block *block)
 		tcf_chain_put(chain);
 	kfree(block);
 }
+EXPORT_SYMBOL(tcf_block_put_ext);
+
+void tcf_block_put(struct tcf_block *block)
+{
+	struct tcf_block_ext_info ei = {0, };
+
+	tcf_block_put_ext(block, NULL, block->q, &ei);
+}
 EXPORT_SYMBOL(tcf_block_put);
 
+struct tcf_block_cb {
+	struct list_head list;
+	tc_setup_cb_t *cb;
+	void *cb_ident;
+	void *cb_priv;
+	unsigned int refcnt;
+};
+
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
+{
+	return block_cb->cb_priv;
+}
+EXPORT_SYMBOL(tcf_block_cb_priv);
+
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+					 tc_setup_cb_t *cb, void *cb_ident)
+{	struct tcf_block_cb *block_cb;
+
+	list_for_each_entry(block_cb, &block->cb_list, list)
+		if (block_cb->cb == cb && block_cb->cb_ident == cb_ident)
+			return block_cb;
+	return NULL;
+}
+EXPORT_SYMBOL(tcf_block_cb_lookup);
+
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
+{
+	block_cb->refcnt++;
+}
+EXPORT_SYMBOL(tcf_block_cb_incref);
+
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
+{
+	return --block_cb->refcnt;
+}
+EXPORT_SYMBOL(tcf_block_cb_decref);
+
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+					     tc_setup_cb_t *cb, void *cb_ident,
+					     void *cb_priv)
+{
+	struct tcf_block_cb *block_cb;
+
+	block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
+	if (!block_cb)
+		return NULL;
+	block_cb->cb = cb;
+	block_cb->cb_ident = cb_ident;
+	block_cb->cb_priv = cb_priv;
+	list_add(&block_cb->list, &block->cb_list);
+	return block_cb;
+}
+EXPORT_SYMBOL(__tcf_block_cb_register);
+
+int tcf_block_cb_register(struct tcf_block *block,
+			  tc_setup_cb_t *cb, void *cb_ident,
+			  void *cb_priv)
+{
+	struct tcf_block_cb *block_cb;
+
+	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv);
+	return block_cb ? 0 : -ENOMEM;
+}
+EXPORT_SYMBOL(tcf_block_cb_register);
+
+void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+{
+	list_del(&block_cb->list);
+	kfree(block_cb);
+}
+EXPORT_SYMBOL(__tcf_block_cb_unregister);
+
+void tcf_block_cb_unregister(struct tcf_block *block,
+			     tc_setup_cb_t *cb, void *cb_ident)
+{
+	struct tcf_block_cb *block_cb;
+
+	block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
+	if (!block_cb)
+		return;
+	__tcf_block_cb_unregister(block_cb);
+}
+EXPORT_SYMBOL(tcf_block_cb_unregister);
+
+static int tcf_block_cb_call(struct tcf_block *block, enum tc_setup_type type,
+			     void *type_data, bool err_stop)
+{
+	struct tcf_block_cb *block_cb;
+	int ok_count = 0;
+	int err;
+
+	list_for_each_entry(block_cb, &block->cb_list, list) {
+		err = block_cb->cb(type, type_data, block_cb->cb_priv);
+		if (err) {
+			if (err_stop)
+				return err;
+		} else {
+			ok_count++;
+		}
+	}
+	return ok_count;
+}
+
 /* Main classifier routine: scans classifier chain attached
  * to this qdisc, (optionally) tests for protocol and asks
  * specific classifiers.
@@ -1051,10 +1206,25 @@ static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
 	return ok_count;
 }
 
-int tc_setup_cb_call(struct tcf_exts *exts, enum tc_setup_type type,
-		     void *type_data, bool err_stop)
+int tc_setup_cb_call(struct tcf_block *block, struct tcf_exts *exts,
+		     enum tc_setup_type type, void *type_data, bool err_stop)
 {
-	return tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
+	int ok_count;
+	int ret;
+
+	ret = tcf_block_cb_call(block, type, type_data, err_stop);
+	if (ret < 0)
+		return ret;
+	ok_count = ret;
+
+	if (!exts)
+		return ok_count;
+	ret = tc_exts_setup_cb_egdev_call(exts, type, type_data, err_stop);
+	if (ret < 0)
+		return ret;
+	ok_count += ret;
+
+	return ok_count;
 }
 EXPORT_SYMBOL(tc_setup_cb_call);
 
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 6c6b21f6ba62..0f8b51061c39 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -147,7 +147,9 @@ static bool cls_bpf_is_ebpf(const struct cls_bpf_prog *prog)
 static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			       enum tc_clsbpf_command cmd)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	bool addorrep = cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE;
+	struct tcf_block *block = tp->chain->block;
+	bool skip_sw = tc_skip_sw(prog->gen_flags);
 	struct tc_cls_bpf_offload cls_bpf = {};
 	int err;
 
@@ -159,17 +161,25 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 	cls_bpf.exts_integrated = prog->exts_integrated;
 	cls_bpf.gen_flags = prog->gen_flags;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSBPF, &cls_bpf);
-	if (!err && (cmd == TC_CLSBPF_ADD || cmd == TC_CLSBPF_REPLACE))
-		prog->gen_flags |= TCA_CLS_FLAGS_IN_HW;
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSBPF, &cls_bpf, skip_sw);
+	if (addorrep) {
+		if (err < 0) {
+			cls_bpf_offload_cmd(tp, prog, TC_CLSBPF_DESTROY);
+			return err;
+		} else if (err > 0) {
+			prog->gen_flags |= TCA_CLS_FLAGS_IN_HW;
+		}
+	}
+
+	if (addorrep && skip_sw && !(prog->gen_flags && TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
 
-	return err;
+	return 0;
 }
 
 static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			   struct cls_bpf_prog *oldprog)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct cls_bpf_prog *obj = prog;
 	enum tc_clsbpf_command cmd;
 	bool skip_sw;
@@ -179,7 +189,7 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 		(oldprog && tc_skip_sw(oldprog->gen_flags));
 
 	if (oldprog && oldprog->offloaded) {
-		if (tc_should_offload(dev, prog->gen_flags)) {
+		if (!tc_skip_hw(prog->gen_flags)) {
 			cmd = TC_CLSBPF_REPLACE;
 		} else if (!tc_skip_sw(prog->gen_flags)) {
 			obj = oldprog;
@@ -188,14 +198,14 @@ static int cls_bpf_offload(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			return -EINVAL;
 		}
 	} else {
-		if (!tc_should_offload(dev, prog->gen_flags))
+		if (tc_skip_hw(prog->gen_flags))
 			return skip_sw ? -EINVAL : 0;
 		cmd = TC_CLSBPF_ADD;
 	}
 
 	ret = cls_bpf_offload_cmd(tp, obj, cmd);
 	if (ret)
-		return skip_sw ? ret : 0;
+		return ret;
 
 	obj->offloaded = true;
 	if (oldprog)
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 5b7bb968d1d4..16f58abaa697 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -200,16 +200,13 @@ static void fl_destroy_filter(struct rcu_head *head)
 static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
 {
 	struct tc_cls_flower_offload cls_flower = {};
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 
 	tc_cls_common_offload_init(&cls_flower.common, tp);
 	cls_flower.command = TC_CLSFLOWER_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
 
-	if (tc_can_offload(dev))
-		dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER,
-					      &cls_flower);
-	tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER,
+	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
 			 &cls_flower, false);
 }
 
@@ -218,8 +215,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 				struct fl_flow_key *mask,
 				struct cls_fl_filter *f)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_flower_offload cls_flower = {};
+	struct tcf_block *block = tp->chain->block;
 	bool skip_sw = tc_skip_sw(f->flags);
 	int err;
 
@@ -231,18 +228,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 	cls_flower.key = &f->mkey;
 	cls_flower.exts = &f->exts;
 
-	if (tc_can_offload(dev)) {
-		err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER,
-						    &cls_flower);
-		if (err) {
-			if (skip_sw)
-				return err;
-		} else {
-			f->flags |= TCA_CLS_FLAGS_IN_HW;
-		}
-	}
-
-	err = tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER,
+	err = tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
 			       &cls_flower, skip_sw);
 	if (err < 0) {
 		fl_hw_destroy_filter(tp, f);
@@ -260,17 +246,14 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 {
 	struct tc_cls_flower_offload cls_flower = {};
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 
 	tc_cls_common_offload_init(&cls_flower.common, tp);
 	cls_flower.command = TC_CLSFLOWER_STATS;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.exts = &f->exts;
 
-	if (tc_can_offload(dev))
-		dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSFLOWER,
-					      &cls_flower);
-	tc_setup_cb_call(&f->exts, TC_SETUP_CLSFLOWER,
+	tc_setup_cb_call(block, &f->exts, TC_SETUP_CLSFLOWER,
 			 &cls_flower, false);
 }
 
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index eeac606c95ab..70e78d74f6d3 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -50,12 +50,27 @@ static void mall_destroy_rcu(struct rcu_head *rcu)
 	kfree(head);
 }
 
+static void mall_destroy_hw_filter(struct tcf_proto *tp,
+				   struct cls_mall_head *head,
+				   unsigned long cookie)
+{
+	struct tc_cls_matchall_offload cls_mall = {};
+	struct tcf_block *block = tp->chain->block;
+
+	tc_cls_common_offload_init(&cls_mall.common, tp);
+	cls_mall.command = TC_CLSMATCHALL_DESTROY;
+	cls_mall.cookie = cookie;
+
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL, &cls_mall, false);
+}
+
 static int mall_replace_hw_filter(struct tcf_proto *tp,
 				  struct cls_mall_head *head,
 				  unsigned long cookie)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_matchall_offload cls_mall = {};
+	struct tcf_block *block = tp->chain->block;
+	bool skip_sw = tc_skip_sw(head->flags);
 	int err;
 
 	tc_cls_common_offload_init(&cls_mall.common, tp);
@@ -63,37 +78,29 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 	cls_mall.exts = &head->exts;
 	cls_mall.cookie = cookie;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL,
-					    &cls_mall);
-	if (!err)
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSMATCHALL,
+			       &cls_mall, skip_sw);
+	if (err < 0) {
+		mall_destroy_hw_filter(tp, head, cookie);
+		return err;
+	} else if (err > 0) {
 		head->flags |= TCA_CLS_FLAGS_IN_HW;
+	}
 
-	return err;
-}
-
-static void mall_destroy_hw_filter(struct tcf_proto *tp,
-				   struct cls_mall_head *head,
-				   unsigned long cookie)
-{
-	struct net_device *dev = tp->q->dev_queue->dev;
-	struct tc_cls_matchall_offload cls_mall = {};
-
-	tc_cls_common_offload_init(&cls_mall.common, tp);
-	cls_mall.command = TC_CLSMATCHALL_DESTROY;
-	cls_mall.cookie = cookie;
+	if (skip_sw && !(head->flags & TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSMATCHALL, &cls_mall);
+	return 0;
 }
 
 static void mall_destroy(struct tcf_proto *tp)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct net_device *dev = tp->q->dev_queue->dev;
 
 	if (!head)
 		return;
 
-	if (tc_should_offload(dev, head->flags))
+	if (!tc_skip_hw(head->flags))
 		mall_destroy_hw_filter(tp, head, (unsigned long) head);
 
 	call_rcu(&head->rcu, mall_destroy_rcu);
@@ -133,7 +140,6 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 		       void **arg, bool ovr)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct nlattr *tb[TCA_MATCHALL_MAX + 1];
 	struct cls_mall_head *new;
 	u32 flags = 0;
@@ -173,14 +179,10 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 	if (err)
 		goto err_set_parms;
 
-	if (tc_should_offload(dev, flags)) {
+	if (!tc_skip_hw(new->flags)) {
 		err = mall_replace_hw_filter(tp, new, (unsigned long) new);
-		if (err) {
-			if (tc_skip_sw(flags))
-				goto err_replace_hw_filter;
-			else
-				err = 0;
-		}
+		if (err)
+			goto err_replace_hw_filter;
 	}
 
 	if (!tc_in_hw(new->flags))
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 49d96b45a8ce..9ff17159fb61 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -462,71 +462,69 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 	return 0;
 }
 
-static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
+static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	if (!tc_should_offload(dev, 0))
-		return;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
-	cls_u32.command = TC_CLSU32_DELETE_KNODE;
-	cls_u32.knode.handle = handle;
+	cls_u32.command = TC_CLSU32_DELETE_HNODE;
+	cls_u32.hnode.divisor = h->divisor;
+	cls_u32.hnode.handle = h->handle;
+	cls_u32.hnode.prio = h->prio;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false);
 }
 
 static int u32_replace_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h,
 				u32 flags)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
+	bool skip_sw = tc_skip_sw(flags);
+	bool offloaded = false;
 	int err;
 
-	if (!tc_should_offload(dev, flags))
-		return tc_skip_sw(flags) ? -EINVAL : 0;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
 	cls_u32.command = TC_CLSU32_NEW_HNODE;
 	cls_u32.hnode.divisor = h->divisor;
 	cls_u32.hnode.handle = h->handle;
 	cls_u32.hnode.prio = h->prio;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
-	if (tc_skip_sw(flags))
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw);
+	if (err < 0) {
+		u32_clear_hw_hnode(tp, h);
 		return err;
+	} else if (err > 0) {
+		offloaded = true;
+	}
+
+	if (skip_sw && !offloaded)
+		return -EINVAL;
 
 	return 0;
 }
 
-static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
+static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
 
-	if (!tc_should_offload(dev, 0))
-		return;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
-	cls_u32.command = TC_CLSU32_DELETE_HNODE;
-	cls_u32.hnode.divisor = h->divisor;
-	cls_u32.hnode.handle = h->handle;
-	cls_u32.hnode.prio = h->prio;
+	cls_u32.command = TC_CLSU32_DELETE_KNODE;
+	cls_u32.knode.handle = handle;
 
-	dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, false);
 }
 
 static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 				u32 flags)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
+	struct tcf_block *block = tp->chain->block;
 	struct tc_cls_u32_offload cls_u32 = {};
+	bool skip_sw = tc_skip_sw(flags);
 	int err;
 
-	if (!tc_should_offload(dev, flags))
-		return tc_skip_sw(flags) ? -EINVAL : 0;
-
 	tc_cls_common_offload_init(&cls_u32.common, tp);
 	cls_u32.command = TC_CLSU32_REPLACE_KNODE;
 	cls_u32.knode.handle = n->handle;
@@ -543,13 +541,16 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	if (n->ht_down)
 		cls_u32.knode.link_handle = n->ht_down->handle;
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_CLSU32, &cls_u32);
-
-	if (!err)
+	err = tc_setup_cb_call(block, NULL, TC_SETUP_CLSU32, &cls_u32, skip_sw);
+	if (err < 0) {
+		u32_remove_hw_knode(tp, n->handle);
+		return err;
+	} else if (err > 0) {
 		n->flags |= TCA_CLS_FLAGS_IN_HW;
+	}
 
-	if (tc_skip_sw(flags))
-		return err;
+	if (skip_sw && !(n->flags && TCA_CLS_FLAGS_IN_HW))
+		return -EINVAL;
 
 	return 0;
 }
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 9ccc1b89b0d9..b599db26d34b 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -20,6 +20,7 @@
 
 struct ingress_sched_data {
 	struct tcf_block *block;
+	struct tcf_block_ext_info block_info;
 };
 
 static struct Qdisc *ingress_leaf(struct Qdisc *sch, unsigned long arg)
@@ -59,7 +60,10 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
-	err = tcf_block_get(&q->block, &dev->ingress_cl_list, sch);
+	q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+
+	err = tcf_block_get_ext(&q->block, &dev->ingress_cl_list,
+				sch, &q->block_info);
 	if (err)
 		return err;
 
@@ -72,8 +76,10 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt)
 static void ingress_destroy(struct Qdisc *sch)
 {
 	struct ingress_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
 
-	tcf_block_put(q->block);
+	tcf_block_put_ext(q->block, &dev->ingress_cl_list,
+			  sch, &q->block_info);
 	net_dec_ingress_queue();
 }
 
@@ -114,6 +120,8 @@ static struct Qdisc_ops ingress_qdisc_ops __read_mostly = {
 struct clsact_sched_data {
 	struct tcf_block *ingress_block;
 	struct tcf_block *egress_block;
+	struct tcf_block_ext_info ingress_block_info;
+	struct tcf_block_ext_info egress_block_info;
 };
 
 static unsigned long clsact_find(struct Qdisc *sch, u32 classid)
@@ -153,13 +161,19 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 	struct net_device *dev = qdisc_dev(sch);
 	int err;
 
-	err = tcf_block_get(&q->ingress_block, &dev->ingress_cl_list, sch);
+	q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+
+	err = tcf_block_get_ext(&q->ingress_block, &dev->ingress_cl_list,
+				sch, &q->ingress_block_info);
 	if (err)
 		return err;
 
-	err = tcf_block_get(&q->egress_block, &dev->egress_cl_list, sch);
+	q->egress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
+
+	err = tcf_block_get_ext(&q->egress_block, &dev->egress_cl_list,
+				sch, &q->egress_block_info);
 	if (err)
-		return err;
+		goto err_egress_block_get;
 
 	net_inc_ingress_queue();
 	net_inc_egress_queue();
@@ -167,14 +181,22 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt)
 	sch->flags |= TCQ_F_CPUSTATS;
 
 	return 0;
+
+err_egress_block_get:
+	tcf_block_put_ext(q->ingress_block, &dev->ingress_cl_list,
+			  sch, &q->ingress_block_info);
+	return err;
 }
 
 static void clsact_destroy(struct Qdisc *sch)
 {
 	struct clsact_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
 
-	tcf_block_put(q->egress_block);
-	tcf_block_put(q->ingress_block);
+	tcf_block_put_ext(q->egress_block, &dev->egress_cl_list,
+			  sch, &q->egress_block_info);
+	tcf_block_put_ext(q->ingress_block, &dev->ingress_cl_list,
+			  sch, &q->ingress_block_info);
 
 	net_dec_ingress_queue();
 	net_dec_egress_queue();