[PATCH net-next v2 0/3] flow_offload: add indr-block in nf_table_offload

[PATCH net-next v2 0/3] flow_offload: add indr-block in nf_table_offload

[wenxu]

From: wenxu <wenxu@ucloud.cn>

This series patch make nftables offload support the vlan and
tunnel device offload through indr-block architecture.

The first patch mv tc indr block to flow offload and rename
to flow-indr-block.
Because the new flow-indr-block can't get the tcf_block
directly. The second patch provide a callback to get tcf_block
immediately when the device register and contain a ingress block.
The third patch make nf_tables_offload support flow-indr-block.
 
wenxu (3):
  flow_offload: move tc indirect block to flow offload
  flow_offload: Support get tcf block immediately
  netfilter: nf_tables_offload: support indr block call

 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  10 +-
 .../net/ethernet/netronome/nfp/flower/offload.c    |  10 +-
 include/net/flow_offload.h                         |  45 ++++
 include/net/pkt_cls.h                              |  35 ---
 include/net/sch_generic.h                          |   3 -
 net/core/flow_offload.c                            | 202 +++++++++++++++++
 net/netfilter/nf_tables_api.c                      |   6 +
 net/netfilter/nf_tables_offload.c                  | 128 +++++++++--
 net/sched/cls_api.c                                | 243 ++++-----------------
 9 files changed, 410 insertions(+), 272 deletions(-)

-- 
1.8.3.1

[PATCH net-next v2 1/3] flow_offload: move tc indirect block to flow offload

[wenxu]

From: wenxu <wenxu@ucloud.cn>

move tc indirect block to flow_offload and rename
it to flow indirect block.The nf_tables can use the 
indr block architecture.

Signed-off-by: wenxu <wenxu@ucloud.cn>
---
v2: make use of flow_block from Pablo
    flow_indr_rhashtable_init advice by jakub.kicinski

 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  10 +-
 .../net/ethernet/netronome/nfp/flower/offload.c    |  10 +-
 include/net/flow_offload.h                         |  41 ++++
 include/net/pkt_cls.h                              |  35 ----
 include/net/sch_generic.h                          |   3 -
 net/core/flow_offload.c                            | 190 +++++++++++++++++
 net/sched/cls_api.c                                | 231 ++-------------------
 7 files changed, 261 insertions(+), 259 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 7f747cb..074573b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -785,9 +785,9 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv,
 {
 	int err;
 
-	err = __tc_indr_block_cb_register(netdev, rpriv,
-					  mlx5e_rep_indr_setup_tc_cb,
-					  rpriv);
+	err = __flow_indr_block_cb_register(netdev, rpriv,
+					    mlx5e_rep_indr_setup_tc_cb,
+					    rpriv);
 	if (err) {
 		struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
 
@@ -800,8 +800,8 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv,
 static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv,
 					    struct net_device *netdev)
 {
-	__tc_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb,
-				      rpriv);
+	__flow_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb,
+					rpriv);
 }
 
 static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index e209f15..6a0f034 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1479,16 +1479,16 @@ int nfp_flower_reg_indir_block_handler(struct nfp_app *app,
 		return NOTIFY_OK;
 
 	if (event == NETDEV_REGISTER) {
-		err = __tc_indr_block_cb_register(netdev, app,
-						  nfp_flower_indr_setup_tc_cb,
-						  app);
+		err = __flow_indr_block_cb_register(netdev, app,
+						    nfp_flower_indr_setup_tc_cb,
+						    app);
 		if (err)
 			nfp_flower_cmsg_warn(app,
 					     "Indirect block reg failed - %s\n",
 					     netdev->name);
 	} else if (event == NETDEV_UNREGISTER) {
-		__tc_indr_block_cb_unregister(netdev,
-					      nfp_flower_indr_setup_tc_cb, app);
+		__flow_indr_block_cb_unregister(netdev,
+						nfp_flower_indr_setup_tc_cb, app);
 	}
 
 	return NOTIFY_OK;
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index 00b9aab..b5ef5be 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -4,6 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <net/flow_dissector.h>
+#include <linux/rhashtable.h>
 
 struct flow_match {
 	struct flow_dissector	*dissector;
@@ -366,4 +367,44 @@ static inline void flow_block_init(struct flow_block *flow_block)
 	INIT_LIST_HEAD(&flow_block->cb_list);
 }
 
+typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
+				      enum tc_setup_type type, void *type_data);
+
+struct flow_indr_block_cb {
+	struct list_head list;
+	void *cb_priv;
+	flow_indr_block_bind_cb_t *cb;
+	void *cb_ident;
+};
+
+typedef void flow_indr_block_ing_cmd_t(struct net_device *dev,
+				       struct flow_block *flow_block,
+				       struct flow_indr_block_cb *indr_block_cb,
+				       enum flow_block_command command);
+
+struct flow_indr_block_dev {
+	struct rhash_head ht_node;
+	struct net_device *dev;
+	unsigned int refcnt;
+	struct list_head cb_list;
+	flow_indr_block_ing_cmd_t *ing_cmd_cb;
+	struct flow_block *flow_block;
+};
+
+struct flow_indr_block_dev *flow_indr_block_dev_lookup(struct net_device *dev);
+
+int flow_indr_rhashtable_init(void);
+
+int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+				  flow_indr_block_bind_cb_t *cb, void *cb_ident);
+
+void __flow_indr_block_cb_unregister(struct net_device *dev,
+				     flow_indr_block_bind_cb_t *cb, void *cb_ident);
+
+int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+				flow_indr_block_bind_cb_t *cb, void *cb_ident);
+
+void flow_indr_block_cb_unregister(struct net_device *dev,
+				   flow_indr_block_bind_cb_t *cb, void *cb_ident);
+
 #endif /* _NET_FLOW_OFFLOAD_H */
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e429809..0790a4e 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -70,15 +70,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 	return block->q;
 }
 
-int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
-				tc_indr_block_bind_cb_t *cb, void *cb_ident);
-int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
-			      tc_indr_block_bind_cb_t *cb, void *cb_ident);
-void __tc_indr_block_cb_unregister(struct net_device *dev,
-				   tc_indr_block_bind_cb_t *cb, void *cb_ident);
-void tc_indr_block_cb_unregister(struct net_device *dev,
-				 tc_indr_block_bind_cb_t *cb, void *cb_ident);
-
 int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 		 struct tcf_result *res, bool compat_mode);
 
@@ -137,32 +128,6 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb,
 {
 }
 
-static inline
-int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
-				tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	return 0;
-}
-
-static inline
-int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
-			      tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	return 0;
-}
-
-static inline
-void __tc_indr_block_cb_unregister(struct net_device *dev,
-				   tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-}
-
-static inline
-void tc_indr_block_cb_unregister(struct net_device *dev,
-				 tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-}
-
 static inline int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
 			       struct tcf_result *res, bool compat_mode)
 {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 6b6b012..d9f359a 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -23,9 +23,6 @@
 struct module;
 struct bpf_flow_keys;
 
-typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
-				    enum tc_setup_type type, void *type_data);
-
 struct qdisc_rate_table {
 	struct tc_ratespec rate;
 	u32		data[256];
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index d63b970..a6785df 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -2,6 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <net/flow_offload.h>
+#include <linux/rtnetlink.h>
 
 struct flow_rule *flow_rule_alloc(unsigned int num_actions)
 {
@@ -280,3 +281,192 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 	}
 }
 EXPORT_SYMBOL(flow_block_cb_setup_simple);
+
+static struct rhashtable indr_setup_block_ht;
+
+static const struct rhashtable_params flow_indr_setup_block_ht_params = {
+	.key_offset	= offsetof(struct flow_indr_block_dev, dev),
+	.head_offset	= offsetof(struct flow_indr_block_dev, ht_node),
+	.key_len	= sizeof(struct net_device *),
+};
+
+struct flow_indr_block_dev *
+flow_indr_block_dev_lookup(struct net_device *dev)
+{
+	return rhashtable_lookup_fast(&indr_setup_block_ht, &dev,
+				      flow_indr_setup_block_ht_params);
+}
+EXPORT_SYMBOL(flow_indr_block_dev_lookup);
+
+static struct flow_indr_block_dev *flow_indr_block_dev_get(struct net_device *dev)
+{
+	struct flow_indr_block_dev *indr_dev;
+
+	indr_dev = flow_indr_block_dev_lookup(dev);
+	if (indr_dev)
+		goto inc_ref;
+
+	indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL);
+	if (!indr_dev)
+		return NULL;
+
+	INIT_LIST_HEAD(&indr_dev->cb_list);
+	indr_dev->dev = dev;
+	if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node,
+				   flow_indr_setup_block_ht_params)) {
+		kfree(indr_dev);
+		return NULL;
+	}
+
+inc_ref:
+	indr_dev->refcnt++;
+	return indr_dev;
+}
+
+static void flow_indr_block_dev_put(struct flow_indr_block_dev *indr_dev)
+{
+	if (--indr_dev->refcnt)
+		return;
+
+	rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node,
+			       flow_indr_setup_block_ht_params);
+	kfree(indr_dev);
+}
+
+static struct flow_indr_block_cb *
+flow_indr_block_cb_lookup(struct flow_indr_block_dev *indr_dev,
+			  flow_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	struct flow_indr_block_cb *indr_block_cb;
+
+	list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
+		if (indr_block_cb->cb == cb &&
+		    indr_block_cb->cb_ident == cb_ident)
+			return indr_block_cb;
+	return NULL;
+}
+
+static struct flow_indr_block_cb *
+flow_indr_block_cb_add(struct flow_indr_block_dev *indr_dev, void *cb_priv,
+		       flow_indr_block_bind_cb_t *cb, void *cb_ident)
+{
+	struct flow_indr_block_cb *indr_block_cb;
+
+	indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident);
+	if (indr_block_cb)
+		return ERR_PTR(-EEXIST);
+
+	indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL);
+	if (!indr_block_cb)
+		return ERR_PTR(-ENOMEM);
+
+	indr_block_cb->cb_priv = cb_priv;
+	indr_block_cb->cb = cb;
+	indr_block_cb->cb_ident = cb_ident;
+	list_add(&indr_block_cb->list, &indr_dev->cb_list);
+
+	return indr_block_cb;
+}
+
+static void flow_indr_block_cb_del(struct flow_indr_block_cb *indr_block_cb)
+{
+	list_del(&indr_block_cb->list);
+	kfree(indr_block_cb);
+}
+
+int __flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+				  flow_indr_block_bind_cb_t *cb,
+				  void *cb_ident)
+{
+	struct flow_indr_block_cb *indr_block_cb;
+	struct flow_indr_block_dev *indr_dev;
+	int err;
+
+	indr_dev = flow_indr_block_dev_get(dev);
+	if (!indr_dev)
+		return -ENOMEM;
+
+	indr_block_cb = flow_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident);
+	err = PTR_ERR_OR_ZERO(indr_block_cb);
+	if (err)
+		goto err_dev_put;
+
+	if (indr_dev->ing_cmd_cb)
+		indr_dev->ing_cmd_cb(indr_dev->dev, indr_dev->flow_block, indr_block_cb,
+				     FLOW_BLOCK_BIND);
+
+	return 0;
+
+err_dev_put:
+	flow_indr_block_dev_put(indr_dev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(__flow_indr_block_cb_register);
+
+int flow_indr_block_cb_register(struct net_device *dev, void *cb_priv,
+				flow_indr_block_bind_cb_t *cb,
+				void *cb_ident)
+{
+	int err;
+
+	rtnl_lock();
+	err = __flow_indr_block_cb_register(dev, cb_priv, cb, cb_ident);
+	rtnl_unlock();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(flow_indr_block_cb_register);
+
+void __flow_indr_block_cb_unregister(struct net_device *dev,
+				     flow_indr_block_bind_cb_t *cb,
+				     void *cb_ident)
+{
+	struct flow_indr_block_cb *indr_block_cb;
+	struct flow_indr_block_dev *indr_dev;
+
+	indr_dev = flow_indr_block_dev_lookup(dev);
+	if (!indr_dev)
+		return;
+
+	indr_block_cb = flow_indr_block_cb_lookup(indr_dev, cb, cb_ident);
+	if (!indr_block_cb)
+		return;
+
+	/* Send unbind message if required to free any block cbs. */
+	if (indr_dev->ing_cmd_cb)
+		indr_dev->ing_cmd_cb(indr_dev->dev, indr_dev->flow_block,
+				     indr_block_cb,
+				     FLOW_BLOCK_UNBIND);
+
+	flow_indr_block_cb_del(indr_block_cb);
+	flow_indr_block_dev_put(indr_dev);
+}
+EXPORT_SYMBOL_GPL(__flow_indr_block_cb_unregister);
+
+void flow_indr_block_cb_unregister(struct net_device *dev,
+				   flow_indr_block_bind_cb_t *cb,
+				   void *cb_ident)
+{
+	rtnl_lock();
+	__flow_indr_block_cb_unregister(dev, cb, cb_ident);
+	rtnl_unlock();
+}
+EXPORT_SYMBOL_GPL(flow_indr_block_cb_unregister);
+
+int flow_indr_rhashtable_init(void)
+{
+	static bool rhash_table_init;
+	int err = 0;
+
+	if (rhash_table_init)
+		return 0;
+
+	err = rhashtable_init(&indr_setup_block_ht,
+			      &flow_indr_setup_block_ht_params);
+	if (err)
+		return err;
+
+	rhash_table_init = true;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(flow_indr_rhashtable_init);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3565d9a..d370c52 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -37,6 +37,7 @@
 #include <net/tc_act/tc_skbedit.h>
 #include <net/tc_act/tc_ct.h>
 #include <net/tc_act/tc_mpls.h>
+#include <net/flow_offload.h>
 
 extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1];
 
@@ -545,235 +546,43 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held)
 	}
 }
 
-static struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
-{
-	const struct Qdisc_class_ops *cops;
-	struct Qdisc *qdisc;
-
-	if (!dev_ingress_queue(dev))
-		return NULL;
-
-	qdisc = dev_ingress_queue(dev)->qdisc_sleeping;
-	if (!qdisc)
-		return NULL;
-
-	cops = qdisc->ops->cl_ops;
-	if (!cops)
-		return NULL;
-
-	if (!cops->tcf_block)
-		return NULL;
-
-	return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
-}
-
-static struct rhashtable indr_setup_block_ht;
-
-struct tc_indr_block_dev {
-	struct rhash_head ht_node;
-	struct net_device *dev;
-	unsigned int refcnt;
-	struct list_head cb_list;
-	struct tcf_block *block;
-};
-
-struct tc_indr_block_cb {
-	struct list_head list;
-	void *cb_priv;
-	tc_indr_block_bind_cb_t *cb;
-	void *cb_ident;
-};
-
-static const struct rhashtable_params tc_indr_setup_block_ht_params = {
-	.key_offset	= offsetof(struct tc_indr_block_dev, dev),
-	.head_offset	= offsetof(struct tc_indr_block_dev, ht_node),
-	.key_len	= sizeof(struct net_device *),
-};
-
-static struct tc_indr_block_dev *
-tc_indr_block_dev_lookup(struct net_device *dev)
-{
-	return rhashtable_lookup_fast(&indr_setup_block_ht, &dev,
-				      tc_indr_setup_block_ht_params);
-}
-
-static struct tc_indr_block_dev *tc_indr_block_dev_get(struct net_device *dev)
-{
-	struct tc_indr_block_dev *indr_dev;
-
-	indr_dev = tc_indr_block_dev_lookup(dev);
-	if (indr_dev)
-		goto inc_ref;
-
-	indr_dev = kzalloc(sizeof(*indr_dev), GFP_KERNEL);
-	if (!indr_dev)
-		return NULL;
-
-	INIT_LIST_HEAD(&indr_dev->cb_list);
-	indr_dev->dev = dev;
-	indr_dev->block = tc_dev_ingress_block(dev);
-	if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node,
-				   tc_indr_setup_block_ht_params)) {
-		kfree(indr_dev);
-		return NULL;
-	}
-
-inc_ref:
-	indr_dev->refcnt++;
-	return indr_dev;
-}
-
-static void tc_indr_block_dev_put(struct tc_indr_block_dev *indr_dev)
-{
-	if (--indr_dev->refcnt)
-		return;
-
-	rhashtable_remove_fast(&indr_setup_block_ht, &indr_dev->ht_node,
-			       tc_indr_setup_block_ht_params);
-	kfree(indr_dev);
-}
-
-static struct tc_indr_block_cb *
-tc_indr_block_cb_lookup(struct tc_indr_block_dev *indr_dev,
-			tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	struct tc_indr_block_cb *indr_block_cb;
-
-	list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
-		if (indr_block_cb->cb == cb &&
-		    indr_block_cb->cb_ident == cb_ident)
-			return indr_block_cb;
-	return NULL;
-}
-
-static struct tc_indr_block_cb *
-tc_indr_block_cb_add(struct tc_indr_block_dev *indr_dev, void *cb_priv,
-		     tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	struct tc_indr_block_cb *indr_block_cb;
-
-	indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
-	if (indr_block_cb)
-		return ERR_PTR(-EEXIST);
-
-	indr_block_cb = kzalloc(sizeof(*indr_block_cb), GFP_KERNEL);
-	if (!indr_block_cb)
-		return ERR_PTR(-ENOMEM);
-
-	indr_block_cb->cb_priv = cb_priv;
-	indr_block_cb->cb = cb;
-	indr_block_cb->cb_ident = cb_ident;
-	list_add(&indr_block_cb->list, &indr_dev->cb_list);
-
-	return indr_block_cb;
-}
-
-static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb)
-{
-	list_del(&indr_block_cb->list);
-	kfree(indr_block_cb);
-}
-
 static int tcf_block_setup(struct tcf_block *block,
 			   struct flow_block_offload *bo);
 
-static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
-				  struct tc_indr_block_cb *indr_block_cb,
+static void tc_indr_block_ing_cmd(struct net_device *dev,
+				  struct flow_block *flow_block,
+				  struct flow_indr_block_cb *indr_block_cb,
 				  enum flow_block_command command)
 {
+	struct tcf_block *block = flow_block ?
+				  container_of(flow_block,
+					       struct tcf_block,
+					       flow_block) : NULL;
 	struct flow_block_offload bo = {
 		.command	= command,
 		.binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
-		.net		= dev_net(indr_dev->dev),
-		.block_shared	= tcf_block_non_null_shared(indr_dev->block),
+		.net		= dev_net(dev),
+		.block_shared	= tcf_block_non_null_shared(block),
 	};
 	INIT_LIST_HEAD(&bo.cb_list);
 
-	if (!indr_dev->block)
-		return;
-
-	bo.block = &indr_dev->block->flow_block;
-
-	indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
-			  &bo);
-	tcf_block_setup(indr_dev->block, &bo);
-}
-
-int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
-				tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	struct tc_indr_block_cb *indr_block_cb;
-	struct tc_indr_block_dev *indr_dev;
-	int err;
-
-	indr_dev = tc_indr_block_dev_get(dev);
-	if (!indr_dev)
-		return -ENOMEM;
-
-	indr_block_cb = tc_indr_block_cb_add(indr_dev, cb_priv, cb, cb_ident);
-	err = PTR_ERR_OR_ZERO(indr_block_cb);
-	if (err)
-		goto err_dev_put;
-
-	tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_BIND);
-	return 0;
-
-err_dev_put:
-	tc_indr_block_dev_put(indr_dev);
-	return err;
-}
-EXPORT_SYMBOL_GPL(__tc_indr_block_cb_register);
-
-int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
-			      tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	int err;
-
-	rtnl_lock();
-	err = __tc_indr_block_cb_register(dev, cb_priv, cb, cb_ident);
-	rtnl_unlock();
-
-	return err;
-}
-EXPORT_SYMBOL_GPL(tc_indr_block_cb_register);
-
-void __tc_indr_block_cb_unregister(struct net_device *dev,
-				   tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	struct tc_indr_block_cb *indr_block_cb;
-	struct tc_indr_block_dev *indr_dev;
-
-	indr_dev = tc_indr_block_dev_lookup(dev);
-	if (!indr_dev)
+	if (!block)
 		return;
 
-	indr_block_cb = tc_indr_block_cb_lookup(indr_dev, cb, cb_ident);
-	if (!indr_block_cb)
-		return;
+	bo.block = flow_block;
 
-	/* Send unbind message if required to free any block cbs. */
-	tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_UNBIND);
-	tc_indr_block_cb_del(indr_block_cb);
-	tc_indr_block_dev_put(indr_dev);
-}
-EXPORT_SYMBOL_GPL(__tc_indr_block_cb_unregister);
+	indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, &bo);
 
-void tc_indr_block_cb_unregister(struct net_device *dev,
-				 tc_indr_block_bind_cb_t *cb, void *cb_ident)
-{
-	rtnl_lock();
-	__tc_indr_block_cb_unregister(dev, cb, cb_ident);
-	rtnl_unlock();
+	tcf_block_setup(block, &bo);
 }
-EXPORT_SYMBOL_GPL(tc_indr_block_cb_unregister);
 
 static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
 			       struct tcf_block_ext_info *ei,
 			       enum flow_block_command command,
 			       struct netlink_ext_ack *extack)
 {
-	struct tc_indr_block_cb *indr_block_cb;
-	struct tc_indr_block_dev *indr_dev;
+	struct flow_indr_block_cb *indr_block_cb;
+	struct flow_indr_block_dev *indr_dev;
 	struct flow_block_offload bo = {
 		.command	= command,
 		.binder_type	= ei->binder_type,
@@ -784,11 +593,12 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
 	};
 	INIT_LIST_HEAD(&bo.cb_list);
 
-	indr_dev = tc_indr_block_dev_lookup(dev);
+	indr_dev = flow_indr_block_dev_lookup(dev);
 	if (!indr_dev)
 		return;
 
-	indr_dev->block = command == FLOW_BLOCK_BIND ? block : NULL;
+	indr_dev->flow_block = command == FLOW_BLOCK_BIND ? &block->flow_block : NULL;
+	indr_dev->ing_cmd_cb = command == FLOW_BLOCK_BIND ? tc_indr_block_ing_cmd : NULL;
 
 	list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
 		indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
@@ -3358,8 +3168,7 @@ static int __init tc_filter_init(void)
 	if (err)
 		goto err_register_pernet_subsys;
 
-	err = rhashtable_init(&indr_setup_block_ht,
-			      &tc_indr_setup_block_ht_params);
+	err = flow_indr_rhashtable_init();
 	if (err)
 		goto err_rhash_setup_block_ht;
 
-- 
1.8.3.1

[PATCH net-next v2 2/3] flow_offload: Support get tcf block immediately

[wenxu]

From: wenxu <wenxu@ucloud.cn>

Because the new flow-indr-block can't get the tcf_block
directly.
It provide a callback to find the tcf block immediately
when the device register and contain a ingress block.

Signed-off-by: wenxu <wenxu@ucloud.cn>
---
v2: make use of flow_block

 include/net/flow_offload.h |  4 ++++
 net/core/flow_offload.c    | 12 ++++++++++++
 net/sched/cls_api.c        | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+)

diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index b5ef5be..bfe3a34 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -391,6 +391,10 @@ struct flow_indr_block_dev {
 	struct flow_block *flow_block;
 };
 
+typedef void flow_indr_get_default_block_t(struct flow_indr_block_dev *indr_dev);
+
+void flow_indr_set_default_block_cb(flow_indr_get_default_block_t *cb);
+
 struct flow_indr_block_dev *flow_indr_block_dev_lookup(struct net_device *dev);
 
 int flow_indr_rhashtable_init(void);
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index a6785df..eeff99f 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -298,6 +298,14 @@ struct flow_indr_block_dev *
 }
 EXPORT_SYMBOL(flow_indr_block_dev_lookup);
 
+static flow_indr_get_default_block_t *flow_indr_get_default_block;
+
+void flow_indr_set_default_block_cb(flow_indr_get_default_block_t *cb)
+{
+	flow_indr_get_default_block = cb;
+}
+EXPORT_SYMBOL(flow_indr_set_default_block_cb);
+
 static struct flow_indr_block_dev *flow_indr_block_dev_get(struct net_device *dev)
 {
 	struct flow_indr_block_dev *indr_dev;
@@ -312,6 +320,10 @@ static struct flow_indr_block_dev *flow_indr_block_dev_get(struct net_device *de
 
 	INIT_LIST_HEAD(&indr_dev->cb_list);
 	indr_dev->dev = dev;
+
+	if (flow_indr_get_default_block)
+		flow_indr_get_default_block(indr_dev);
+
 	if (rhashtable_insert_fast(&indr_setup_block_ht, &indr_dev->ht_node,
 				   flow_indr_setup_block_ht_params)) {
 		kfree(indr_dev);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d370c52..8d4d7f0 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -576,6 +576,38 @@ static void tc_indr_block_ing_cmd(struct net_device *dev,
 	tcf_block_setup(block, &bo);
 }
 
+static struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
+{
+	const struct Qdisc_class_ops *cops;
+	struct Qdisc *qdisc;
+
+	if (!dev_ingress_queue(dev))
+		return NULL;
+
+	qdisc = dev_ingress_queue(dev)->qdisc_sleeping;
+	if (!qdisc)
+		return NULL;
+
+	cops = qdisc->ops->cl_ops;
+	if (!cops)
+		return NULL;
+
+	if (!cops->tcf_block)
+		return NULL;
+
+	return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
+}
+
+static void tc_indr_get_default_block(struct flow_indr_block_dev *indr_dev)
+{
+	struct tcf_block *block = tc_dev_ingress_block(indr_dev->dev);
+
+	if (block) {
+		indr_dev->flow_block = &block->flow_block;
+		indr_dev->ing_cmd_cb = tc_indr_block_ing_cmd;
+	}
+}
+
 static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
 			       struct tcf_block_ext_info *ei,
 			       enum flow_block_command command,
@@ -3172,6 +3204,8 @@ static int __init tc_filter_init(void)
 	if (err)
 		goto err_rhash_setup_block_ht;
 
+	flow_indr_set_default_block_cb(tc_indr_get_default_block);
+
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL,
 		      RTNL_FLAG_DOIT_UNLOCKED);
 	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL,
-- 
1.8.3.1

[PATCH net-next v2 3/3] netfilter: nf_tables_offload: support indr block call

[wenxu]

From: wenxu <wenxu@ucloud.cn>

nftable support indr-block call. It makes nftable an offload vlan
and tunnel device.

nft add table netdev firewall
nft add chain netdev firewall aclout { type filter hook ingress offload device mlx_pf0vf0 priority - 300 \; }
nft add rule netdev firewall aclout ip daddr 10.0.0.1 fwd to vlan0
nft add chain netdev firewall aclin { type filter hook ingress device vlan0 priority - 300 \; }
nft add rule netdev firewall aclin ip daddr 10.0.0.7 fwd to mlx_pf0vf0

Signed-off-by: wenxu <wenxu@ucloud.cn>
---
v2: make use of flow_block

 net/netfilter/nf_tables_api.c     |   6 ++
 net/netfilter/nf_tables_offload.c | 128 +++++++++++++++++++++++++++++++-------
 2 files changed, 110 insertions(+), 24 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 605a7cf..a8ab3e9 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -7623,8 +7623,14 @@ static int __init nf_tables_module_init(void)
 	if (err < 0)
 		goto err5;
 
+	err = flow_indr_rhashtable_init();
+	if (err)
+		goto err6;
+
 	nft_chain_route_init();
 	return err;
+err6:
+	nfnetlink_subsys_unregister(&nf_tables_subsys);
 err5:
 	rhltable_destroy(&nft_objname_ht);
 err4:
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 64f5fd5..09a5efe 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -171,24 +171,120 @@ static int nft_flow_offload_unbind(struct flow_block_offload *bo,
 	return 0;
 }
 
+static int nft_block_setup(struct nft_base_chain *basechain,
+			   struct flow_block_offload *bo,
+			   enum flow_block_command cmd)
+{
+	int err;
+
+	switch (cmd) {
+	case FLOW_BLOCK_BIND:
+		err = nft_flow_offload_bind(bo, basechain);
+		break;
+	case FLOW_BLOCK_UNBIND:
+		err = nft_flow_offload_unbind(bo, basechain);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int nft_block_offload_cmd(struct nft_base_chain *chain,
+				 struct net_device *dev,
+				 enum flow_block_command cmd)
+{
+	struct netlink_ext_ack extack = {};
+	struct flow_block_offload bo = {};
+	int err;
+
+	bo.net = dev_net(dev);
+	bo.block = &chain->flow_block;
+	bo.command = cmd;
+	bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	bo.extack = &extack;
+	INIT_LIST_HEAD(&bo.cb_list);
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+	if (err < 0)
+		return err;
+
+	return nft_block_setup(chain, &bo, cmd);
+}
+
+static void nft_indr_block_ing_cmd(struct net_device *dev,
+				   struct flow_block *flow_block,
+				   struct flow_indr_block_cb *indr_block_cb,
+				   enum flow_block_command cmd)
+{
+	struct netlink_ext_ack extack = {};
+	struct flow_block_offload bo = {};
+	struct nft_base_chain *chain;
+
+	if (flow_block)
+		return;
+
+	chain = container_of(flow_block, struct nft_base_chain, flow_block);
+
+	bo.net = dev_net(dev);
+	bo.block = flow_block;
+	bo.command = cmd;
+	bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	bo.extack = &extack;
+	INIT_LIST_HEAD(&bo.cb_list);
+
+	indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK, &bo);
+
+	nft_block_setup(chain, &bo, cmd);
+}
+
+static int nft_indr_block_offload_cmd(struct nft_base_chain *chain,
+				      struct net_device *dev,
+				      enum flow_block_command cmd)
+{
+	struct flow_indr_block_cb *indr_block_cb;
+	struct flow_indr_block_dev *indr_dev;
+	struct flow_block_offload bo = {};
+	struct netlink_ext_ack extack = {};
+
+	bo.net = dev_net(dev);
+	bo.block = &chain->flow_block;
+	bo.command = cmd;
+	bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	bo.extack = &extack;
+	INIT_LIST_HEAD(&bo.cb_list);
+
+	indr_dev = flow_indr_block_dev_lookup(dev);
+	if (!indr_dev)
+		return -EOPNOTSUPP;
+
+	indr_dev->flow_block = cmd == FLOW_BLOCK_BIND ? &chain->flow_block : NULL;
+	indr_dev->ing_cmd_cb = cmd == FLOW_BLOCK_BIND ? nft_indr_block_ing_cmd : NULL;
+
+	list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
+		indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
+				  &bo);
+
+	return nft_block_setup(chain, &bo, cmd);
+}
+
 #define FLOW_SETUP_BLOCK TC_SETUP_BLOCK
 
 static int nft_flow_offload_chain(struct nft_trans *trans,
 				  enum flow_block_command cmd)
 {
 	struct nft_chain *chain = trans->ctx.chain;
-	struct netlink_ext_ack extack = {};
-	struct flow_block_offload bo = {};
 	struct nft_base_chain *basechain;
 	struct net_device *dev;
-	int err;
 
 	if (!nft_is_base_chain(chain))
 		return -EOPNOTSUPP;
 
 	basechain = nft_base_chain(chain);
 	dev = basechain->ops.dev;
-	if (!dev || !dev->netdev_ops->ndo_setup_tc)
+	if (!dev)
 		return -EOPNOTSUPP;
 
 	/* Only default policy to accept is supported for now. */
@@ -197,26 +293,10 @@ static int nft_flow_offload_chain(struct nft_trans *trans,
 	    nft_trans_chain_policy(trans) != NF_ACCEPT)
 		return -EOPNOTSUPP;
 
-	bo.command = cmd;
-	bo.block = &basechain->flow_block;
-	bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
-	bo.extack = &extack;
-	INIT_LIST_HEAD(&bo.cb_list);
-
-	err = dev->netdev_ops->ndo_setup_tc(dev, FLOW_SETUP_BLOCK, &bo);
-	if (err < 0)
-		return err;
-
-	switch (cmd) {
-	case FLOW_BLOCK_BIND:
-		err = nft_flow_offload_bind(&bo, basechain);
-		break;
-	case FLOW_BLOCK_UNBIND:
-		err = nft_flow_offload_unbind(&bo, basechain);
-		break;
-	}
-
-	return err;
+	if (dev->netdev_ops->ndo_setup_tc)
+		return nft_block_offload_cmd(basechain, dev, cmd);
+	else
+		return nft_indr_block_offload_cmd(basechain, dev, cmd);
 }
 
 int nft_flow_rule_offload_commit(struct net *net)
-- 
1.8.3.1

Re: [PATCH net-next v2 1/3] flow_offload: move tc indirect block to flow offload

[Vlad Buslov]

On Fri 26 Jul 2019 at 09:17, wenxu@ucloud.cn wrote:
> From: wenxu <wenxu@ucloud.cn>
>
> move tc indirect block to flow_offload and rename
> it to flow indirect block.The nf_tables can use the
> indr block architecture.
>
> Signed-off-by: wenxu <wenxu@ucloud.cn>
> ---
> v2: make use of flow_block from Pablo
>     flow_indr_rhashtable_init advice by jakub.kicinski
>
>  drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  10 +-
>  .../net/ethernet/netronome/nfp/flower/offload.c    |  10 +-
>  include/net/flow_offload.h                         |  41 ++++
>  include/net/pkt_cls.h                              |  35 ----
>  include/net/sch_generic.h                          |   3 -
>  net/core/flow_offload.c                            | 190 +++++++++++++++++
>  net/sched/cls_api.c                                | 231 ++-------------------
>  7 files changed, 261 insertions(+), 259 deletions(-)
>

[...]

> +
> +int flow_indr_rhashtable_init(void)
> +{
> +	static bool rhash_table_init;
> +	int err = 0;
> +
> +	if (rhash_table_init)
> +		return 0;
> +
> +	err = rhashtable_init(&indr_setup_block_ht,
> +			      &flow_indr_setup_block_ht_params);
> +	if (err)
> +		return err;
> +
> +	rhash_table_init = true;
> +	return 0;
> +}
> +EXPORT_SYMBOL_GPL(flow_indr_rhashtable_init);

Shouldn't this be dedicated *_initcall function? That would remove the
necessity for rhash_table_init flag.