Merge branch 'flow_offload-fixes'

Pablo Neira Ayuso says:

====================
flow_offload fixes

The following patchset contains fixes for the flow_offload infrastructure:

1) Fix possible build breakage before patch 3/4. Both the flow_offload
   infrastructure and OVS define the flow_stats structure. Patch 3/4 in
   this batch indirectly pulls in the flow_stats definition from
   include/net/flow_offload.h into OVS, leading to structure redefinition
   compile-time errors.

2) Remove netns parameter from flow_block_cb_alloc(), this is not
   required as Jiri suggests. The flow_block_cb_is_busy() function uses
   the per-driver block list to check for used blocks which was the
   original intention for this parameter.

3) Rename tc_setup_cb_t to flow_setup_cb_t. This callback is not
   exclusive of tc anymore, this might confuse the reader as Jiri
   suggests, fix this semantic inconsistency.

   Add #include <linux/list.h> to include/net/netfilter/nf_tables_offload.h
   to avoid a compile break with CONFIG_HEADER_TEST=y.

4) Fix block sharing feature: Add flow_block structure and use it,
   update flow_block_cb_lookup() to use this flow_block object.
====================

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

21 files changed, 94 insertions, 81 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 7245d287633d4a..7f747cb1a4f4b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -735,8 +735,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
 		list_add(&indr_priv->list,
 			 &rpriv->uplink_priv.tc_indr_block_priv_list);
 
-		block_cb = flow_block_cb_alloc(f->net,
-					       mlx5e_rep_indr_setup_block_cb,
+		block_cb = flow_block_cb_alloc(mlx5e_rep_indr_setup_block_cb,
 					       indr_priv, indr_priv,
 					       mlx5e_rep_indr_tc_block_unbind);
 		if (IS_ERR(block_cb)) {
@@ -753,7 +752,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
 		if (!indr_priv)
 			return -ENOENT;
 
-		block_cb = flow_block_cb_lookup(f,
+		block_cb = flow_block_cb_lookup(f->block,
 						mlx5e_rep_indr_setup_block_cb,
 						indr_priv);
 		if (!block_cb)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 4d34d42b3b0e87..650638152bbc5d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1604,14 +1604,14 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 	bool register_block = false;
 	int err;
 
-	block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+	block_cb = flow_block_cb_lookup(f->block,
+					mlxsw_sp_setup_tc_block_cb_flower,
 					mlxsw_sp);
 	if (!block_cb) {
 		acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, f->net);
 		if (!acl_block)
 			return -ENOMEM;
-		block_cb = flow_block_cb_alloc(f->net,
-					       mlxsw_sp_setup_tc_block_cb_flower,
+		block_cb = flow_block_cb_alloc(mlxsw_sp_setup_tc_block_cb_flower,
 					       mlxsw_sp, acl_block,
 					       mlxsw_sp_tc_block_flower_release);
 		if (IS_ERR(block_cb)) {
@@ -1657,7 +1657,8 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct flow_block_cb *block_cb;
 	int err;
 
-	block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+	block_cb = flow_block_cb_lookup(f->block,
+					mlxsw_sp_setup_tc_block_cb_flower,
 					mlxsw_sp);
 	if (!block_cb)
 		return;
@@ -1680,7 +1681,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
 				   struct flow_block_offload *f)
 {
 	struct flow_block_cb *block_cb;
-	tc_setup_cb_t *cb;
+	flow_setup_cb_t *cb;
 	bool ingress;
 	int err;
 
@@ -1702,7 +1703,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
 					  &mlxsw_sp_block_cb_list))
 			return -EBUSY;
 
-		block_cb = flow_block_cb_alloc(f->net, cb, mlxsw_sp_port,
+		block_cb = flow_block_cb_alloc(cb, mlxsw_sp_port,
 					       mlxsw_sp_port, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
@@ -1718,7 +1719,7 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
 	case FLOW_BLOCK_UNBIND:
 		mlxsw_sp_setup_tc_block_flower_unbind(mlxsw_sp_port,
 						      f, ingress);
-		block_cb = flow_block_cb_lookup(f, cb, mlxsw_sp_port);
+		block_cb = flow_block_cb_lookup(f->block, cb, mlxsw_sp_port);
 		if (!block_cb)
 			return -ENOENT;
 
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 7aaddc09c1851e..59487d446a098d 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -316,15 +316,14 @@ int ocelot_setup_tc_block_flower_bind(struct ocelot_port *port,
 	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
 		return -EOPNOTSUPP;
 
-	block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
-					port);
+	block_cb = flow_block_cb_lookup(f->block,
+					ocelot_setup_tc_block_cb_flower, port);
 	if (!block_cb) {
 		port_block = ocelot_port_block_create(port);
 		if (!port_block)
 			return -ENOMEM;
 
-		block_cb = flow_block_cb_alloc(f->net,
-					       ocelot_setup_tc_block_cb_flower,
+		block_cb = flow_block_cb_alloc(ocelot_setup_tc_block_cb_flower,
 					       port, port_block,
 					       ocelot_tc_block_unbind);
 		if (IS_ERR(block_cb)) {
@@ -351,8 +350,8 @@ void ocelot_setup_tc_block_flower_unbind(struct ocelot_port *port,
 {
 	struct flow_block_cb *block_cb;
 
-	block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
-					port);
+	block_cb = flow_block_cb_lookup(f->block,
+					ocelot_setup_tc_block_cb_flower, port);
 	if (!block_cb)
 		return;
 
diff --git a/drivers/net/ethernet/mscc/ocelot_tc.c b/drivers/net/ethernet/mscc/ocelot_tc.c
index 9e6464ffae5d1d..16a6db71ca5e7e 100644
--- a/drivers/net/ethernet/mscc/ocelot_tc.c
+++ b/drivers/net/ethernet/mscc/ocelot_tc.c
@@ -134,7 +134,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port,
 				 struct flow_block_offload *f)
 {
 	struct flow_block_cb *block_cb;
-	tc_setup_cb_t *cb;
+	flow_setup_cb_t *cb;
 	int err;
 
 	netdev_dbg(port->dev, "tc_block command %d, binder_type %d\n",
@@ -156,7 +156,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port,
 		if (flow_block_cb_is_busy(cb, port, &ocelot_block_cb_list))
 			return -EBUSY;
 
-		block_cb = flow_block_cb_alloc(f->net, cb, port, port, NULL);
+		block_cb = flow_block_cb_alloc(cb, port, port, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
 
@@ -169,7 +169,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port,
 		list_add_tail(&block_cb->driver_list, f->driver_block_list);
 		return 0;
 	case FLOW_BLOCK_UNBIND:
-		block_cb = flow_block_cb_lookup(f, cb, port);
+		block_cb = flow_block_cb_lookup(f->block, cb, port);
 		if (!block_cb)
 			return -ENOENT;
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index faa8ba012a374f..e209f150c5f25e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1318,8 +1318,7 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 					  &nfp_block_cb_list))
 			return -EBUSY;
 
-		block_cb = flow_block_cb_alloc(f->net,
-					       nfp_flower_setup_tc_block_cb,
+		block_cb = flow_block_cb_alloc(nfp_flower_setup_tc_block_cb,
 					       repr, repr, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
@@ -1328,7 +1327,8 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 		list_add_tail(&block_cb->driver_list, &nfp_block_cb_list);
 		return 0;
 	case FLOW_BLOCK_UNBIND:
-		block_cb = flow_block_cb_lookup(f, nfp_flower_setup_tc_block_cb,
+		block_cb = flow_block_cb_lookup(f->block,
+						nfp_flower_setup_tc_block_cb,
 						repr);
 		if (!block_cb)
 			return -ENOENT;
@@ -1424,8 +1424,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 		cb_priv->app = app;
 		list_add(&cb_priv->list, &priv->indr_block_cb_priv);
 
-		block_cb = flow_block_cb_alloc(f->net,
-					       nfp_flower_setup_indr_block_cb,
+		block_cb = flow_block_cb_alloc(nfp_flower_setup_indr_block_cb,
 					       cb_priv, cb_priv,
 					       nfp_flower_setup_indr_tc_release);
 		if (IS_ERR(block_cb)) {
@@ -1442,7 +1441,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 		if (!cb_priv)
 			return -ENOENT;
 
-		block_cb = flow_block_cb_lookup(f,
+		block_cb = flow_block_cb_lookup(f->block,
 						nfp_flower_setup_indr_block_cb,
 						cb_priv);
 		if (!block_cb)
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index db337299e81e87..b16d21636d6969 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -2,8 +2,8 @@
 #define _NET_FLOW_OFFLOAD_H
 
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <net/flow_dissector.h>
-#include <net/sch_generic.h>
 
 struct flow_match {
 	struct flow_dissector	*dissector;
@@ -249,6 +249,10 @@ enum flow_block_binder_type {
 	FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
 };
 
+struct flow_block {
+	struct list_head cb_list;
+};
+
 struct netlink_ext_ack;
 
 struct flow_block_offload {
@@ -256,29 +260,33 @@ struct flow_block_offload {
 	enum flow_block_binder_type binder_type;
 	bool block_shared;
 	struct net *net;
+	struct flow_block *block;
 	struct list_head cb_list;
 	struct list_head *driver_block_list;
 	struct netlink_ext_ack *extack;
 };
 
+enum tc_setup_type;
+typedef int flow_setup_cb_t(enum tc_setup_type type, void *type_data,
+			    void *cb_priv);
+
 struct flow_block_cb {
 	struct list_head	driver_list;
 	struct list_head	list;
-	struct net		*net;
-	tc_setup_cb_t		*cb;
+	flow_setup_cb_t		*cb;
 	void			*cb_ident;
 	void			*cb_priv;
 	void			(*release)(void *cb_priv);
 	unsigned int		refcnt;
 };
 
-struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
+struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
 					  void *cb_ident, void *cb_priv,
 					  void (*release)(void *cb_priv));
 void flow_block_cb_free(struct flow_block_cb *block_cb);
 
-struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *offload,
-					   tc_setup_cb_t *cb, void *cb_ident);
+struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
+					   flow_setup_cb_t *cb, void *cb_ident);
 
 void *flow_block_cb_priv(struct flow_block_cb *block_cb);
 void flow_block_cb_incref(struct flow_block_cb *block_cb);
@@ -296,11 +304,12 @@ static inline void flow_block_cb_remove(struct flow_block_cb *block_cb,
 	list_move(&block_cb->list, &offload->cb_list);
 }
 
-bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident,
+bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
 			   struct list_head *driver_block_list);
 
 int flow_block_cb_setup_simple(struct flow_block_offload *f,
-			       struct list_head *driver_list, tc_setup_cb_t *cb,
+			       struct list_head *driver_list,
+			       flow_setup_cb_t *cb,
 			       void *cb_ident, void *cb_priv, bool ingress_only);
 
 enum flow_cls_command {
@@ -333,4 +342,9 @@ flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd)
 	return flow_cmd->rule;
 }
 
+static inline void flow_block_init(struct flow_block *flow_block)
+{
+	INIT_LIST_HEAD(&flow_block->cb_list);
+}
+
 #endif /* _NET_FLOW_OFFLOAD_H */
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 35dfdd9f69b379..9b624566b82d30 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -11,6 +11,7 @@
 #include <linux/rhashtable.h>
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netlink.h>
+#include <net/flow_offload.h>
 
 struct module;
 
@@ -951,7 +952,7 @@ struct nft_stats {
  *	@stats: per-cpu chain stats
  *	@chain: the chain
  *	@dev_name: device name that this base chain is attached to (if any)
- *	@cb_list: list of flow block callbacks (for hardware offload)
+ *	@flow_block: flow block (for hardware offload)
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops;
@@ -961,7 +962,7 @@ struct nft_base_chain {
 	struct nft_stats __percpu	*stats;
 	struct nft_chain		chain;
 	char 				dev_name[IFNAMSIZ];
-	struct list_head		cb_list;
+	struct flow_block		flow_block;
 };
 
 static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 841faadceb6ee4..e429809ca90d84 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -6,7 +6,6 @@
 #include <linux/workqueue.h>
 #include <net/sch_generic.h>
 #include <net/act_api.h>
-#include <net/flow_offload.h>
 #include <net/net_namespace.h>
 
 /* TC action not accessible from user space */
@@ -126,14 +125,14 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 }
 
 static inline
-int tc_setup_cb_block_register(struct tcf_block *block, tc_setup_cb_t *cb,
+int tc_setup_cb_block_register(struct tcf_block *block, flow_setup_cb_t *cb,
 			       void *cb_priv)
 {
 	return 0;
 }
 
 static inline
-void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
+void tc_setup_cb_block_unregister(struct tcf_block *block, flow_setup_cb_t *cb,
 				  void *cb_priv)
 {
 }
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 855167bbc37299..6b6b01234dd9d9 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -15,6 +15,7 @@
 #include <linux/mutex.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
+#include <net/flow_offload.h>
 
 struct Qdisc_ops;
 struct qdisc_walker;
@@ -22,9 +23,6 @@ struct tcf_walker;
 struct module;
 struct bpf_flow_keys;
 
-typedef int tc_setup_cb_t(enum tc_setup_type type,
-			  void *type_data, void *cb_priv);
-
 typedef int tc_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
 				    enum tc_setup_type type, void *type_data);
 
@@ -313,7 +311,7 @@ struct tcf_proto_ops {
 	void			(*walk)(struct tcf_proto *tp,
 					struct tcf_walker *arg, bool rtnl_held);
 	int			(*reoffload)(struct tcf_proto *tp, bool add,
-					     tc_setup_cb_t *cb, void *cb_priv,
+					     flow_setup_cb_t *cb, void *cb_priv,
 					     struct netlink_ext_ack *extack);
 	void			(*bind_class)(void *, u32, unsigned long);
 	void *			(*tmplt_create)(struct net *net,
@@ -401,7 +399,7 @@ struct tcf_block {
 	refcount_t refcnt;
 	struct net *net;
 	struct Qdisc *q;
-	struct list_head cb_list;
+	struct flow_block flow_block;
 	struct list_head owner_list;
 	bool keep_dst;
 	unsigned int offloadcnt; /* Number of oddloaded filters */
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index 76f8db3841d7a3..d63b970784dc74 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -165,7 +165,7 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule,
 }
 EXPORT_SYMBOL(flow_rule_match_enc_opts);
 
-struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
+struct flow_block_cb *flow_block_cb_alloc(flow_setup_cb_t *cb,
 					  void *cb_ident, void *cb_priv,
 					  void (*release)(void *cb_priv))
 {
@@ -175,7 +175,6 @@ struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
 	if (!block_cb)
 		return ERR_PTR(-ENOMEM);
 
-	block_cb->net = net;
 	block_cb->cb = cb;
 	block_cb->cb_ident = cb_ident;
 	block_cb->cb_priv = cb_priv;
@@ -194,14 +193,13 @@ void flow_block_cb_free(struct flow_block_cb *block_cb)
 }
 EXPORT_SYMBOL(flow_block_cb_free);
 
-struct flow_block_cb *flow_block_cb_lookup(struct flow_block_offload *f,
-					   tc_setup_cb_t *cb, void *cb_ident)
+struct flow_block_cb *flow_block_cb_lookup(struct flow_block *block,
+					   flow_setup_cb_t *cb, void *cb_ident)
 {
 	struct flow_block_cb *block_cb;
 
-	list_for_each_entry(block_cb, f->driver_block_list, driver_list) {
-		if (block_cb->net == f->net &&
-		    block_cb->cb == 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;
 	}
@@ -228,7 +226,7 @@ unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb)
 }
 EXPORT_SYMBOL(flow_block_cb_decref);
 
-bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident,
+bool flow_block_cb_is_busy(flow_setup_cb_t *cb, void *cb_ident,
 			   struct list_head *driver_block_list)
 {
 	struct flow_block_cb *block_cb;
@@ -245,7 +243,8 @@ EXPORT_SYMBOL(flow_block_cb_is_busy);
 
 int flow_block_cb_setup_simple(struct flow_block_offload *f,
 			       struct list_head *driver_block_list,
-			       tc_setup_cb_t *cb, void *cb_ident, void *cb_priv,
+			       flow_setup_cb_t *cb,
+			       void *cb_ident, void *cb_priv,
 			       bool ingress_only)
 {
 	struct flow_block_cb *block_cb;
@@ -261,8 +260,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 		if (flow_block_cb_is_busy(cb, cb_ident, driver_block_list))
 			return -EBUSY;
 
-		block_cb = flow_block_cb_alloc(f->net, cb, cb_ident,
-					       cb_priv, NULL);
+		block_cb = flow_block_cb_alloc(cb, cb_ident, cb_priv, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
 
@@ -270,7 +268,7 @@ int flow_block_cb_setup_simple(struct flow_block_offload *f,
 		list_add_tail(&block_cb->driver_list, driver_block_list);
 		return 0;
 	case FLOW_BLOCK_UNBIND:
-		block_cb = flow_block_cb_lookup(f, cb, cb_ident);
+		block_cb = flow_block_cb_lookup(f->block, cb, cb_ident);
 		if (!block_cb)
 			return -ENOENT;
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 614c38ece10430..33f41178afccf2 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -951,7 +951,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 				    struct flow_block_offload *f)
 {
 	struct flow_block_cb *block_cb;
-	tc_setup_cb_t *cb;
+	flow_setup_cb_t *cb;
 
 	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		cb = dsa_slave_setup_tc_block_cb_ig;
@@ -967,7 +967,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 		if (flow_block_cb_is_busy(cb, dev, &dsa_slave_block_cb_list))
 			return -EBUSY;
 
-		block_cb = flow_block_cb_alloc(f->net, cb, dev, dev, NULL);
+		block_cb = flow_block_cb_alloc(cb, dev, dev, NULL);
 		if (IS_ERR(block_cb))
 			return PTR_ERR(block_cb);
 
@@ -975,7 +975,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 		list_add_tail(&block_cb->driver_list, &dsa_slave_block_cb_list);
 		return 0;
 	case FLOW_BLOCK_UNBIND:
-		block_cb = flow_block_cb_lookup(f, cb, dev);
+		block_cb = flow_block_cb_lookup(f->block, cb, dev);
 		if (!block_cb)
 			return -ENOENT;
 
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 014e06b0b5cfb0..605a7cfe7ca79e 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1662,7 +1662,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 		chain->flags |= NFT_BASE_CHAIN | flags;
 		basechain->policy = NF_ACCEPT;
-		INIT_LIST_HEAD(&basechain->cb_list);
+		flow_block_init(&basechain->flow_block);
 	} else {
 		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 		if (chain == NULL)
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 2c3302845f6753..64f5fd5f240e26 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -116,7 +116,7 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain,
 	struct flow_block_cb *block_cb;
 	int err;
 
-	list_for_each_entry(block_cb, &basechain->cb_list, list) {
+	list_for_each_entry(block_cb, &basechain->flow_block.cb_list, list) {
 		err = block_cb->cb(type, type_data, block_cb->cb_priv);
 		if (err < 0)
 			return err;
@@ -154,7 +154,7 @@ static int nft_flow_offload_rule(struct nft_trans *trans,
 static int nft_flow_offload_bind(struct flow_block_offload *bo,
 				 struct nft_base_chain *basechain)
 {
-	list_splice(&bo->cb_list, &basechain->cb_list);
+	list_splice(&bo->cb_list, &basechain->flow_block.cb_list);
 	return 0;
 }
 
@@ -198,6 +198,7 @@ static int nft_flow_offload_chain(struct nft_trans *trans,
 		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);
diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c
index dca3b1e2acf060..bc89e16e05050c 100644
--- a/net/openvswitch/flow.c
+++ b/net/openvswitch/flow.c
@@ -59,7 +59,7 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies)
 void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			   const struct sk_buff *skb)
 {
-	struct flow_stats *stats;
+	struct sw_flow_stats *stats;
 	unsigned int cpu = smp_processor_id();
 	int len = skb->len + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0);
 
@@ -87,7 +87,7 @@ void ovs_flow_stats_update(struct sw_flow *flow, __be16 tcp_flags,
 			if (likely(flow->stats_last_writer != -1) &&
 			    likely(!rcu_access_pointer(flow->stats[cpu]))) {
 				/* Try to allocate CPU-specific stats. */
-				struct flow_stats *new_stats;
+				struct sw_flow_stats *new_stats;
 
 				new_stats =
 					kmem_cache_alloc_node(flow_stats_cache,
@@ -134,7 +134,7 @@ void ovs_flow_stats_get(const struct sw_flow *flow,
 
 	/* We open code this to make sure cpu 0 is always considered */
 	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
-		struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
+		struct sw_flow_stats *stats = rcu_dereference_ovsl(flow->stats[cpu]);
 
 		if (stats) {
 			/* Local CPU may write on non-local stats, so we must
@@ -158,7 +158,7 @@ void ovs_flow_stats_clear(struct sw_flow *flow)
 
 	/* We open code this to make sure cpu 0 is always considered */
 	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask)) {
-		struct flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
+		struct sw_flow_stats *stats = ovsl_dereference(flow->stats[cpu]);
 
 		if (stats) {
 			spin_lock_bh(&stats->lock);
diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h
index 3e2cc2202d668c..a5506e2d4b7ae3 100644
--- a/net/openvswitch/flow.h
+++ b/net/openvswitch/flow.h
@@ -194,7 +194,7 @@ struct sw_flow_actions {
 	struct nlattr actions[];
 };
 
-struct flow_stats {
+struct sw_flow_stats {
 	u64 packet_count;		/* Number of packets matched. */
 	u64 byte_count;			/* Number of bytes matched. */
 	unsigned long used;		/* Last used time (in jiffies). */
@@ -216,7 +216,7 @@ struct sw_flow {
 	struct cpumask cpu_used_mask;
 	struct sw_flow_mask *mask;
 	struct sw_flow_actions __rcu *sf_acts;
-	struct flow_stats __rcu *stats[]; /* One for each CPU.  First one
+	struct sw_flow_stats __rcu *stats[]; /* One for each CPU.  First one
 					   * is allocated at flow creation time,
 					   * the rest are allocated on demand
 					   * while holding the 'stats[0].lock'.
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 988fd8a94e43ec..cf3582c5ed70c3 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -66,7 +66,7 @@ void ovs_flow_mask_key(struct sw_flow_key *dst, const struct sw_flow_key *src,
 struct sw_flow *ovs_flow_alloc(void)
 {
 	struct sw_flow *flow;
-	struct flow_stats *stats;
+	struct sw_flow_stats *stats;
 
 	flow = kmem_cache_zalloc(flow_cache, GFP_KERNEL);
 	if (!flow)
@@ -110,7 +110,7 @@ static void flow_free(struct sw_flow *flow)
 	for (cpu = 0; cpu < nr_cpu_ids; cpu = cpumask_next(cpu, &flow->cpu_used_mask))
 		if (flow->stats[cpu])
 			kmem_cache_free(flow_stats_cache,
-					(struct flow_stats __force *)flow->stats[cpu]);
+					(struct sw_flow_stats __force *)flow->stats[cpu]);
 	kmem_cache_free(flow_cache, flow);
 }
 
@@ -712,13 +712,13 @@ int ovs_flow_init(void)
 
 	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
 				       + (nr_cpu_ids
-					  * sizeof(struct flow_stats *)),
+					  * sizeof(struct sw_flow_stats *)),
 				       0, 0, NULL);
 	if (flow_cache == NULL)
 		return -ENOMEM;
 
 	flow_stats_cache
-		= kmem_cache_create("sw_flow_stats", sizeof(struct flow_stats),
+		= kmem_cache_create("sw_flow_stats", sizeof(struct sw_flow_stats),
 				    0, SLAB_HWCACHE_ALIGN, NULL);
 	if (flow_stats_cache == NULL) {
 		kmem_cache_destroy(flow_cache);
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index d144233423c5c9..15796fd47fdaff 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -691,6 +691,8 @@ static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
 	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);
@@ -775,6 +777,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
 		.command	= command,
 		.binder_type	= ei->binder_type,
 		.net		= dev_net(dev),
+		.block		= &block->flow_block,
 		.block_shared	= tcf_block_shared(block),
 		.extack		= extack,
 	};
@@ -810,6 +813,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
 	bo.net = dev_net(dev);
 	bo.command = command;
 	bo.binder_type = ei->binder_type;
+	bo.block = &block->flow_block;
 	bo.block_shared = tcf_block_shared(block);
 	bo.extack = extack;
 	INIT_LIST_HEAD(&bo.cb_list);
@@ -987,8 +991,8 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 		return ERR_PTR(-ENOMEM);
 	}
 	mutex_init(&block->lock);
+	flow_block_init(&block->flow_block);
 	INIT_LIST_HEAD(&block->chain_list);
-	INIT_LIST_HEAD(&block->cb_list);
 	INIT_LIST_HEAD(&block->owner_list);
 	INIT_LIST_HEAD(&block->chain0.filter_chain_list);
 
@@ -1514,7 +1518,7 @@ void tcf_block_put(struct tcf_block *block)
 EXPORT_SYMBOL(tcf_block_put);
 
 static int
-tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
+tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb,
 			    void *cb_priv, bool add, bool offload_in_use,
 			    struct netlink_ext_ack *extack)
 {
@@ -1570,7 +1574,7 @@ static int tcf_block_bind(struct tcf_block *block,
 
 		i++;
 	}
-	list_splice(&bo->cb_list, &block->cb_list);
+	list_splice(&bo->cb_list, &block->flow_block.cb_list);
 
 	return 0;
 
@@ -3156,7 +3160,7 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
 	if (block->nooffloaddevcnt && err_stop)
 		return -EOPNOTSUPP;
 
-	list_for_each_entry(block_cb, &block->cb_list, list) {
+	list_for_each_entry(block_cb, &block->flow_block.cb_list, list) {
 		err = block_cb->cb(type, type_data, block_cb->cb_priv);
 		if (err) {
 			if (err_stop)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 691f71830134be..3f7a9c02b70c57 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -651,7 +651,7 @@ skip:
 	}
 }
 
-static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			     void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct cls_bpf_head *head = rtnl_dereference(tp->root);
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 38d6e85693fc83..054123742e323b 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1800,7 +1800,7 @@ fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add)
 	return NULL;
 }
 
-static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int fl_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct tcf_block *block = tp->chain->block;
diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index a30d2f8feb3236..455ea2793f9b37 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -282,7 +282,7 @@ skip:
 	arg->count++;
 }
 
-static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int mall_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			  void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct cls_mall_head *head = rtnl_dereference(tp->root);
diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index be9e46c77e8be6..8614088edd1be0 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -1152,7 +1152,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg,
 }
 
 static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
-			       bool add, tc_setup_cb_t *cb, void *cb_priv,
+			       bool add, flow_setup_cb_t *cb, void *cb_priv,
 			       struct netlink_ext_ack *extack)
 {
 	struct tc_cls_u32_offload cls_u32 = {};
@@ -1172,7 +1172,7 @@ static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 }
 
 static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
-			       bool add, tc_setup_cb_t *cb, void *cb_priv,
+			       bool add, flow_setup_cb_t *cb, void *cb_priv,
 			       struct netlink_ext_ack *extack)
 {
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
@@ -1213,7 +1213,7 @@ static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 	return 0;
 }
 
-static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+static int u32_reoffload(struct tcf_proto *tp, bool add, flow_setup_cb_t *cb,
 			 void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct tc_u_common *tp_c = tp->data;