Merge branch 'nf-hw-offload'

Pablo Neira Ayuso says:

====================
netfilter: add hardware offload infrastructure

This patchset adds support for Netfilter hardware offloads.

This patchset reuses the existing block infrastructure, the
netdev_ops->ndo_setup_tc() interface, TC_SETUP_CLSFLOWER classifier and
the flow rule API.

Patch #1 adds flow_block_cb_setup_simple(), most drivers do the same thing
         to set up flow blocks, to reduce the number of changes, consolidate
         codebase. Use _simple() postfix as requested by Jakub Kicinski.
         This new function resides in net/core/flow_offload.c

Patch #2 renames TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND.

Patch #3 renames TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*.

Patch #4 adds flow_block_cb_alloc() and flow_block_cb_free() helper
         functions, this is the first patch of the flow block API.

Patch #5 adds the helper to deal with list operations in the flow block API.
         This includes flow_block_cb_lookup(), flow_block_cb_add() and
	 flow_block_cb_remove().

Patch #6 adds flow_block_cb_priv(), flow_block_cb_incref() and
         flow_block_cb_decref() which completes the flow block API.

Patch #7 updates the cls_api to use the flow block API from the new
         tcf_block_setup(). This infrastructure transports these objects
         via list (through the tc_block_offload object) back to the core
	 for registration.

            CLS_API                           DRIVER
        TC_SETUP_BLOCK    ---------->  setup flow_block_cb object &
                                 it adds object to flow_block_offload->cb_list
                                                |
            CLS_API     <-----------------------'
           registers                     list with flow blocks
         flow_block_cb &                   travels back to
       calls ->reoffload               the core for registration

         drivers allocate and sets up (configure the blocks), then
	 registration happens from the core (cls_api and netfilter).

Patch #8 updates drivers to use the flow block API.

Patch #9 removes the tcf block callback API, which is replaced by the
         flow block API.

Patch #10 adds the flow_block_cb_is_busy() helper to check if the block
	  is already used by a subsystem. This helper is invoked from
	  drivers. Once drivers are updated to support for multiple
	  subsystems, they can remove this check.

Patch #11 rename tc structure and definitions for the block bind/unbind
	  path.

Patch #12 introduces basic netfilter hardware offload infrastructure
          for the ingress chain. This includes 5-tuple exact matching
          and accept / drop rule actions. Only basechains are supported
          at this stage, no .reoffload callback is implemented either.
          Default policy to "accept" is only supported for now.

        table netdev filter {
                chain ingress {
                        type filter hook ingress device eth0 priority 0; flags offload;

                        ip daddr 192.168.0.10 tcp dport 22 drop
                }
        }

This patchset reuses the existing tcf block callback API and it places it
in the flow block callback API in net/core/flow_offload.c.

This series aims to address Jakub and Jiri's feedback, please see specific
patches in this batch for changelog in this v4.
====================

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

56 files changed, 1579 insertions, 880 deletions

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2b5b0ab8961a..3f632028eff0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9907,32 +9907,19 @@ static int bnxt_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int bnxt_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct bnxt *bp = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
-					     bp, bp, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(bnxt_block_cb_list);
 
 static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			 void *type_data)
 {
+	struct bnxt *bp = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return bnxt_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &bnxt_block_cb_list,
+						  bnxt_setup_tc_block_cb,
+						  bp, bp, true);
 	case TC_SETUP_QDISC_MQPRIO: {
 		struct tc_mqprio_qopt *mqprio = type_data;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 44d6c5743fb9..6fe4a7174271 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -170,10 +170,10 @@ static int bnxt_tc_parse_actions(struct bnxt *bp,
 }
 
 static int bnxt_tc_parse_flow(struct bnxt *bp,
-			      struct tc_cls_flower_offload *tc_flow_cmd,
+			      struct flow_cls_offload *tc_flow_cmd,
 			      struct bnxt_tc_flow *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(tc_flow_cmd);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(tc_flow_cmd);
 	struct flow_dissector *dissector = rule->match.dissector;
 
 	/* KEY_CONTROL and KEY_BASIC are needed for forming a meaningful key */
@@ -1262,7 +1262,7 @@ static void bnxt_tc_set_src_fid(struct bnxt *bp, struct bnxt_tc_flow *flow,
  * The hash-tables are already protected by the rhashtable API.
  */
 static int bnxt_tc_add_flow(struct bnxt *bp, u16 src_fid,
-			    struct tc_cls_flower_offload *tc_flow_cmd)
+			    struct flow_cls_offload *tc_flow_cmd)
 {
 	struct bnxt_tc_flow_node *new_node, *old_node;
 	struct bnxt_tc_info *tc_info = bp->tc_info;
@@ -1348,7 +1348,7 @@ done:
 }
 
 static int bnxt_tc_del_flow(struct bnxt *bp,
-			    struct tc_cls_flower_offload *tc_flow_cmd)
+			    struct flow_cls_offload *tc_flow_cmd)
 {
 	struct bnxt_tc_info *tc_info = bp->tc_info;
 	struct bnxt_tc_flow_node *flow_node;
@@ -1363,7 +1363,7 @@ static int bnxt_tc_del_flow(struct bnxt *bp,
 }
 
 static int bnxt_tc_get_flow_stats(struct bnxt *bp,
-				  struct tc_cls_flower_offload *tc_flow_cmd)
+				  struct flow_cls_offload *tc_flow_cmd)
 {
 	struct bnxt_tc_flow_stats stats, *curr_stats, *prev_stats;
 	struct bnxt_tc_info *tc_info = bp->tc_info;
@@ -1585,14 +1585,14 @@ void bnxt_tc_flow_stats_work(struct bnxt *bp)
 }
 
 int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
-			 struct tc_cls_flower_offload *cls_flower)
+			 struct flow_cls_offload *cls_flower)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return bnxt_tc_add_flow(bp, src_fid, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return bnxt_tc_del_flow(bp, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return bnxt_tc_get_flow_stats(bp, cls_flower);
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
index 8a0968967bc5..ffec57d1a5ec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.h
@@ -196,7 +196,7 @@ struct bnxt_tc_flow_node {
 };
 
 int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
-			 struct tc_cls_flower_offload *cls_flower);
+			 struct flow_cls_offload *cls_flower);
 int bnxt_init_tc(struct bnxt *bp);
 void bnxt_shutdown_tc(struct bnxt *bp);
 void bnxt_tc_flow_stats_work(struct bnxt *bp);
@@ -209,7 +209,7 @@ static inline bool bnxt_tc_flower_enabled(struct bnxt *bp)
 #else /* CONFIG_BNXT_FLOWER_OFFLOAD */
 
 static inline int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
-				       struct tc_cls_flower_offload *cls_flower)
+				       struct flow_cls_offload *cls_flower)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index f760921389a3..f9bf7d7250ab 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -161,34 +161,19 @@ static int bnxt_vf_rep_setup_tc_block_cb(enum tc_setup_type type,
 	}
 }
 
-static int bnxt_vf_rep_setup_tc_block(struct net_device *dev,
-				      struct tc_block_offload *f)
-{
-	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     bnxt_vf_rep_setup_tc_block_cb,
-					     vf_rep, vf_rep, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block,
-					bnxt_vf_rep_setup_tc_block_cb, vf_rep);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(bnxt_vf_block_cb_list);
 
 static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 				void *type_data)
 {
+	struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return bnxt_vf_rep_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &bnxt_vf_block_cb_list,
+						  bnxt_vf_rep_setup_tc_block_cb,
+						  vf_rep, vf_rep, true);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index b08efc48d42f..67202b6f352e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3135,14 +3135,14 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate)
 }
 
 static int cxgb_setup_tc_flower(struct net_device *dev,
-				struct tc_cls_flower_offload *cls_flower)
+				struct flow_cls_offload *cls_flower)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return cxgb4_tc_flower_replace(dev, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return cxgb4_tc_flower_destroy(dev, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return cxgb4_tc_flower_stats(dev, cls_flower);
 	default:
 		return -EOPNOTSUPP;
@@ -3190,32 +3190,19 @@ static int cxgb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int cxgb_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct port_info *pi = netdev2pinfo(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb,
-					     pi, dev, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(cxgb_block_cb_list);
 
 static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			 void *type_data)
 {
+	struct port_info *pi = netdev2pinfo(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return cxgb_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &cxgb_block_cb_list,
+						  cxgb_setup_tc_block_cb,
+						  pi, dev, true);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index cfaf8f618d1f..312599c6b35a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -80,10 +80,10 @@ static struct ch_tc_flower_entry *ch_flower_lookup(struct adapter *adap,
 }
 
 static void cxgb4_process_flow_match(struct net_device *dev,
-				     struct tc_cls_flower_offload *cls,
+				     struct flow_cls_offload *cls,
 				     struct ch_filter_specification *fs)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	u16 addr_type = 0;
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
@@ -223,9 +223,9 @@ static void cxgb4_process_flow_match(struct net_device *dev,
 }
 
 static int cxgb4_validate_flow_match(struct net_device *dev,
-				     struct tc_cls_flower_offload *cls)
+				     struct flow_cls_offload *cls)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	struct flow_dissector *dissector = rule->match.dissector;
 	u16 ethtype_mask = 0;
 	u16 ethtype_key = 0;
@@ -378,10 +378,10 @@ static void process_pedit_field(struct ch_filter_specification *fs, u32 val,
 }
 
 static void cxgb4_process_flow_actions(struct net_device *in,
-				       struct tc_cls_flower_offload *cls,
+				       struct flow_cls_offload *cls,
 				       struct ch_filter_specification *fs)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	struct flow_action_entry *act;
 	int i;
 
@@ -544,9 +544,9 @@ static bool valid_pedit_action(struct net_device *dev,
 }
 
 static int cxgb4_validate_flow_actions(struct net_device *dev,
-				       struct tc_cls_flower_offload *cls)
+				       struct flow_cls_offload *cls)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(cls);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(cls);
 	struct flow_action_entry *act;
 	bool act_redir = false;
 	bool act_pedit = false;
@@ -633,7 +633,7 @@ static int cxgb4_validate_flow_actions(struct net_device *dev,
 }
 
 int cxgb4_tc_flower_replace(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls)
+			    struct flow_cls_offload *cls)
 {
 	struct adapter *adap = netdev2adap(dev);
 	struct ch_tc_flower_entry *ch_flower;
@@ -709,7 +709,7 @@ free_entry:
 }
 
 int cxgb4_tc_flower_destroy(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls)
+			    struct flow_cls_offload *cls)
 {
 	struct adapter *adap = netdev2adap(dev);
 	struct ch_tc_flower_entry *ch_flower;
@@ -783,7 +783,7 @@ static void ch_flower_stats_cb(struct timer_list *t)
 }
 
 int cxgb4_tc_flower_stats(struct net_device *dev,
-			  struct tc_cls_flower_offload *cls)
+			  struct flow_cls_offload *cls)
 {
 	struct adapter *adap = netdev2adap(dev);
 	struct ch_tc_flower_stats *ofld_stats;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
index 050c8a50ae41..eb4c95248baf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.h
@@ -109,11 +109,11 @@ struct ch_tc_pedit_fields {
 #define PEDIT_UDP_SPORT_DPORT		0x0
 
 int cxgb4_tc_flower_replace(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls);
+			    struct flow_cls_offload *cls);
 int cxgb4_tc_flower_destroy(struct net_device *dev,
-			    struct tc_cls_flower_offload *cls);
+			    struct flow_cls_offload *cls);
 int cxgb4_tc_flower_stats(struct net_device *dev,
-			  struct tc_cls_flower_offload *cls);
+			  struct flow_cls_offload *cls);
 
 int cxgb4_init_tc_flower(struct adapter *adap);
 void cxgb4_cleanup_tc_flower(struct adapter *adap);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5361c08328f7..9ebbe3da61bb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7759,15 +7759,15 @@ int i40e_add_del_cloud_filter_big_buf(struct i40e_vsi *vsi,
 /**
  * i40e_parse_cls_flower - Parse tc flower filters provided by kernel
  * @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  * @filter: Pointer to cloud filter structure
  *
  **/
 static int i40e_parse_cls_flower(struct i40e_vsi *vsi,
-				 struct tc_cls_flower_offload *f,
+				 struct flow_cls_offload *f,
 				 struct i40e_cloud_filter *filter)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0, n_proto_key = 0, addr_type = 0;
 	struct i40e_pf *pf = vsi->back;
@@ -8001,11 +8001,11 @@ static int i40e_handle_tclass(struct i40e_vsi *vsi, u32 tc,
 /**
  * i40e_configure_clsflower - Configure tc flower filters
  * @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  *
  **/
 static int i40e_configure_clsflower(struct i40e_vsi *vsi,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	int tc = tc_classid_to_hwtc(vsi->netdev, cls_flower->classid);
 	struct i40e_cloud_filter *filter = NULL;
@@ -8097,11 +8097,11 @@ static struct i40e_cloud_filter *i40e_find_cloud_filter(struct i40e_vsi *vsi,
 /**
  * i40e_delete_clsflower - Remove tc flower filters
  * @vsi: Pointer to VSI
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  *
  **/
 static int i40e_delete_clsflower(struct i40e_vsi *vsi,
-				 struct tc_cls_flower_offload *cls_flower)
+				 struct flow_cls_offload *cls_flower)
 {
 	struct i40e_cloud_filter *filter = NULL;
 	struct i40e_pf *pf = vsi->back;
@@ -8144,16 +8144,16 @@ static int i40e_delete_clsflower(struct i40e_vsi *vsi,
  * @type_data: offload data
  **/
 static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	struct i40e_vsi *vsi = np->vsi;
 
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return i40e_configure_clsflower(vsi, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return i40e_delete_clsflower(vsi, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return -EOPNOTSUPP;
 	default:
 		return -EOPNOTSUPP;
@@ -8177,34 +8177,21 @@ static int i40e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int i40e_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct i40e_netdev_priv *np = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
-					     np, np, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(i40e_block_cb_list);
 
 static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 			   void *type_data)
 {
+	struct i40e_netdev_priv *np = netdev_priv(netdev);
+
 	switch (type) {
 	case TC_SETUP_QDISC_MQPRIO:
 		return i40e_setup_tc(netdev, type_data);
 	case TC_SETUP_BLOCK:
-		return i40e_setup_tc_block(netdev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &i40e_block_cb_list,
+						  i40e_setup_tc_block_cb,
+						  np, np, true);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 881561b36083..9d2b50964a08 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2699,14 +2699,14 @@ exit:
 /**
  * iavf_parse_cls_flower - Parse tc flower filters provided by kernel
  * @adapter: board private structure
- * @cls_flower: pointer to struct tc_cls_flower_offload
+ * @cls_flower: pointer to struct flow_cls_offload
  * @filter: pointer to cloud filter structure
  */
 static int iavf_parse_cls_flower(struct iavf_adapter *adapter,
-				 struct tc_cls_flower_offload *f,
+				 struct flow_cls_offload *f,
 				 struct iavf_cloud_filter *filter)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0;
 	u16 n_proto_key = 0;
@@ -2971,10 +2971,10 @@ static int iavf_handle_tclass(struct iavf_adapter *adapter, u32 tc,
 /**
  * iavf_configure_clsflower - Add tc flower filters
  * @adapter: board private structure
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  */
 static int iavf_configure_clsflower(struct iavf_adapter *adapter,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid);
 	struct iavf_cloud_filter *filter = NULL;
@@ -3050,10 +3050,10 @@ static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter,
 /**
  * iavf_delete_clsflower - Remove tc flower filters
  * @adapter: board private structure
- * @cls_flower: Pointer to struct tc_cls_flower_offload
+ * @cls_flower: Pointer to struct flow_cls_offload
  */
 static int iavf_delete_clsflower(struct iavf_adapter *adapter,
-				 struct tc_cls_flower_offload *cls_flower)
+				 struct flow_cls_offload *cls_flower)
 {
 	struct iavf_cloud_filter *filter = NULL;
 	int err = 0;
@@ -3077,17 +3077,17 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter,
  * @type_data: offload data
  */
 static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter,
-				    struct tc_cls_flower_offload *cls_flower)
+				    struct flow_cls_offload *cls_flower)
 {
 	if (cls_flower->common.chain_index)
 		return -EOPNOTSUPP;
 
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return iavf_configure_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return iavf_delete_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return -EOPNOTSUPP;
 	default:
 		return -EOPNOTSUPP;
@@ -3113,34 +3113,7 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-/**
- * iavf_setup_tc_block - register callbacks for tc
- * @netdev: network interface device structure
- * @f: tc offload data
- *
- * This function registers block callbacks for tc
- * offloads
- **/
-static int iavf_setup_tc_block(struct net_device *dev,
-			       struct tc_block_offload *f)
-{
-	struct iavf_adapter *adapter = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, iavf_setup_tc_block_cb,
-					     adapter, adapter, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, iavf_setup_tc_block_cb,
-					adapter);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(iavf_block_cb_list);
 
 /**
  * iavf_setup_tc - configure multiple traffic classes
@@ -3156,11 +3129,16 @@ static int iavf_setup_tc_block(struct net_device *dev,
 static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
 			 void *type_data)
 {
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
 	switch (type) {
 	case TC_SETUP_QDISC_MQPRIO:
 		return __iavf_setup_tc(netdev, type_data);
 	case TC_SETUP_BLOCK:
-		return iavf_setup_tc_block(netdev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &iavf_block_cb_list,
+						  iavf_setup_tc_block_cb,
+						  adapter, adapter, true);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f66dae72fe37..b4df3e319467 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2578,11 +2578,11 @@ static int igb_offload_cbs(struct igb_adapter *adapter,
 #define VLAN_PRIO_FULL_MASK (0x07)
 
 static int igb_parse_cls_flower(struct igb_adapter *adapter,
-				struct tc_cls_flower_offload *f,
+				struct flow_cls_offload *f,
 				int traffic_class,
 				struct igb_nfc_filter *input)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
 	struct netlink_ext_ack *extack = f->common.extack;
 
@@ -2660,7 +2660,7 @@ static int igb_parse_cls_flower(struct igb_adapter *adapter,
 }
 
 static int igb_configure_clsflower(struct igb_adapter *adapter,
-				   struct tc_cls_flower_offload *cls_flower)
+				   struct flow_cls_offload *cls_flower)
 {
 	struct netlink_ext_ack *extack = cls_flower->common.extack;
 	struct igb_nfc_filter *filter, *f;
@@ -2722,7 +2722,7 @@ err_parse:
 }
 
 static int igb_delete_clsflower(struct igb_adapter *adapter,
-				struct tc_cls_flower_offload *cls_flower)
+				struct flow_cls_offload *cls_flower)
 {
 	struct igb_nfc_filter *filter;
 	int err;
@@ -2752,14 +2752,14 @@ out:
 }
 
 static int igb_setup_tc_cls_flower(struct igb_adapter *adapter,
-				   struct tc_cls_flower_offload *cls_flower)
+				   struct flow_cls_offload *cls_flower)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return igb_configure_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return igb_delete_clsflower(adapter, cls_flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return -EOPNOTSUPP;
 	default:
 		return -EOPNOTSUPP;
@@ -2783,25 +2783,6 @@ static int igb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int igb_setup_tc_block(struct igb_adapter *adapter,
-			      struct tc_block_offload *f)
-{
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
-					     adapter, adapter, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
-					adapter);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int igb_offload_txtime(struct igb_adapter *adapter,
 			      struct tc_etf_qopt_offload *qopt)
 {
@@ -2825,6 +2806,8 @@ static int igb_offload_txtime(struct igb_adapter *adapter,
 	return 0;
 }
 
+static LIST_HEAD(igb_block_cb_list);
+
 static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			void *type_data)
 {
@@ -2834,7 +2817,11 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 	case TC_SETUP_QDISC_CBS:
 		return igb_offload_cbs(adapter, type_data);
 	case TC_SETUP_BLOCK:
-		return igb_setup_tc_block(adapter, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &igb_block_cb_list,
+						  igb_setup_tc_block_cb,
+						  adapter, adapter, true);
+
 	case TC_SETUP_QDISC_ETF:
 		return igb_offload_txtime(adapter, type_data);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index b613e72c8ee4..cbaf712d6529 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9607,27 +9607,6 @@ static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int ixgbe_setup_tc_block(struct net_device *dev,
-				struct tc_block_offload *f)
-{
-	struct ixgbe_adapter *adapter = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
-					     adapter, adapter, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
-					adapter);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int ixgbe_setup_tc_mqprio(struct net_device *dev,
 				 struct tc_mqprio_qopt *mqprio)
 {
@@ -9635,12 +9614,19 @@ static int ixgbe_setup_tc_mqprio(struct net_device *dev,
 	return ixgbe_setup_tc(dev, mqprio->num_tc);
 }
 
+static LIST_HEAD(ixgbe_block_cb_list);
+
 static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			    void *type_data)
 {
+	struct ixgbe_adapter *adapter = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return ixgbe_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &ixgbe_block_cb_list,
+						  ixgbe_setup_tc_block_cb,
+						  adapter, adapter, true);
 	case TC_SETUP_QDISC_MQPRIO:
 		return ixgbe_setup_tc_mqprio(dev, type_data);
 	default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 3739646b653f..a6a52806be45 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -452,7 +452,7 @@ int mlx5e_tc_tun_init_encap_attr(struct net_device *tunnel_dev,
 int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 		       struct mlx5e_priv *priv,
 		       struct mlx5_flow_spec *spec,
-		       struct tc_cls_flower_offload *f,
+		       struct flow_cls_offload *f,
 		       void *headers_c,
 		       void *headers_v, u8 *match_level)
 {
@@ -489,11 +489,11 @@ out:
 
 int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv,
 				 struct mlx5_flow_spec *spec,
-				 struct tc_cls_flower_offload *f,
+				 struct flow_cls_offload *f,
 				 void *headers_c,
 				 void *headers_v)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct flow_match_ports enc_ports;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
index 3c48f7e62505..c362b9225dc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.h
@@ -33,12 +33,12 @@ struct mlx5e_tc_tunnel {
 				   struct mlx5e_encap_entry *e);
 	int (*parse_udp_ports)(struct mlx5e_priv *priv,
 			       struct mlx5_flow_spec *spec,
-			       struct tc_cls_flower_offload *f,
+			       struct flow_cls_offload *f,
 			       void *headers_c,
 			       void *headers_v);
 	int (*parse_tunnel)(struct mlx5e_priv *priv,
 			    struct mlx5_flow_spec *spec,
-			    struct tc_cls_flower_offload *f,
+			    struct flow_cls_offload *f,
 			    void *headers_c,
 			    void *headers_v);
 };
@@ -68,13 +68,13 @@ bool mlx5e_tc_tun_device_to_offload(struct mlx5e_priv *priv,
 int mlx5e_tc_tun_parse(struct net_device *filter_dev,
 		       struct mlx5e_priv *priv,
 		       struct mlx5_flow_spec *spec,
-		       struct tc_cls_flower_offload *f,
+		       struct flow_cls_offload *f,
 		       void *headers_c,
 		       void *headers_v, u8 *match_level);
 
 int mlx5e_tc_tun_parse_udp_ports(struct mlx5e_priv *priv,
 				 struct mlx5_flow_spec *spec,
-				 struct tc_cls_flower_offload *f,
+				 struct flow_cls_offload *f,
 				 void *headers_c,
 				 void *headers_v);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
index 238ae85d07cc..951ea26d96bc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_geneve.c
@@ -20,9 +20,9 @@ static int mlx5e_tc_tun_calc_hlen_geneve(struct mlx5e_encap_entry *e)
 }
 
 static int mlx5e_tc_tun_check_udp_dport_geneve(struct mlx5e_priv *priv,
-					       struct tc_cls_flower_offload *f)
+					       struct flow_cls_offload *f)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct flow_match_ports enc_ports;
 
@@ -48,7 +48,7 @@ static int mlx5e_tc_tun_check_udp_dport_geneve(struct mlx5e_priv *priv,
 
 static int mlx5e_tc_tun_parse_udp_ports_geneve(struct mlx5e_priv *priv,
 					       struct mlx5_flow_spec *spec,
-					       struct tc_cls_flower_offload *f,
+					       struct flow_cls_offload *f,
 					       void *headers_c,
 					       void *headers_v)
 {
@@ -122,9 +122,9 @@ static int mlx5e_gen_ip_tunnel_header_geneve(char buf[],
 
 static int mlx5e_tc_tun_parse_geneve_vni(struct mlx5e_priv *priv,
 					 struct mlx5_flow_spec *spec,
-					 struct tc_cls_flower_offload *f)
+					 struct flow_cls_offload *f)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct flow_match_enc_keyid enc_keyid;
 	void *misc_c, *misc_v;
@@ -154,11 +154,11 @@ static int mlx5e_tc_tun_parse_geneve_vni(struct mlx5e_priv *priv,
 
 static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv,
 					     struct mlx5_flow_spec *spec,
-					     struct tc_cls_flower_offload *f)
+					     struct flow_cls_offload *f)
 {
 	u8 max_tlv_option_data_len = MLX5_CAP_GEN(priv->mdev, max_geneve_tlv_option_data_len);
 	u8 max_tlv_options = MLX5_CAP_GEN(priv->mdev, max_geneve_tlv_options);
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	void *misc_c, *misc_v, *misc_3_c, *misc_3_v;
 	struct geneve_opt *option_key, *option_mask;
@@ -277,7 +277,7 @@ static int mlx5e_tc_tun_parse_geneve_options(struct mlx5e_priv *priv,
 
 static int mlx5e_tc_tun_parse_geneve_params(struct mlx5e_priv *priv,
 					    struct mlx5_flow_spec *spec,
-					    struct tc_cls_flower_offload *f)
+					    struct flow_cls_offload *f)
 {
 	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
 	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,  misc_parameters);
@@ -306,7 +306,7 @@ static int mlx5e_tc_tun_parse_geneve_params(struct mlx5e_priv *priv,
 
 static int mlx5e_tc_tun_parse_geneve(struct mlx5e_priv *priv,
 				     struct mlx5_flow_spec *spec,
-				     struct tc_cls_flower_offload *f,
+				     struct flow_cls_offload *f,
 				     void *headers_c,
 				     void *headers_v)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
index 06908441d932..58b13192df23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_gre.c
@@ -54,13 +54,13 @@ static int mlx5e_gen_ip_tunnel_header_gretap(char buf[],
 
 static int mlx5e_tc_tun_parse_gretap(struct mlx5e_priv *priv,
 				     struct mlx5_flow_spec *spec,
-				     struct tc_cls_flower_offload *f,
+				     struct flow_cls_offload *f,
 				     void *headers_c,
 				     void *headers_v)
 {
 	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
 	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value, misc_parameters);
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 
 	MLX5_SET_TO_ONES(fte_match_set_lyr_2_4, headers_c, ip_protocol);
 	MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_protocol, IPPROTO_GRE);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index 2857b38527d6..37b176801bcc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -16,9 +16,9 @@ static int mlx5e_tc_tun_calc_hlen_vxlan(struct mlx5e_encap_entry *e)
 }
 
 static int mlx5e_tc_tun_check_udp_dport_vxlan(struct mlx5e_priv *priv,
-					      struct tc_cls_flower_offload *f)
+					      struct flow_cls_offload *f)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct flow_match_ports enc_ports;
 
@@ -44,7 +44,7 @@ static int mlx5e_tc_tun_check_udp_dport_vxlan(struct mlx5e_priv *priv,
 
 static int mlx5e_tc_tun_parse_udp_ports_vxlan(struct mlx5e_priv *priv,
 					      struct mlx5_flow_spec *spec,
-					      struct tc_cls_flower_offload *f,
+					      struct flow_cls_offload *f,
 					      void *headers_c,
 					      void *headers_v)
 {
@@ -100,11 +100,11 @@ static int mlx5e_gen_ip_tunnel_header_vxlan(char buf[],
 
 static int mlx5e_tc_tun_parse_vxlan(struct mlx5e_priv *priv,
 				    struct mlx5_flow_spec *spec,
-				    struct tc_cls_flower_offload *f,
+				    struct flow_cls_offload *f,
 				    void *headers_c,
 				    void *headers_v)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct flow_match_enc_keyid enc_keyid;
 	void *misc_c, *misc_v;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 10efd69de7ef..6d0ae87c8ded 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3426,17 +3426,17 @@ out:
 
 #ifdef CONFIG_MLX5_ESWITCH
 static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv,
-				     struct tc_cls_flower_offload *cls_flower,
+				     struct flow_cls_offload *cls_flower,
 				     int flags)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
 					      flags);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
 					   flags);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
 					  flags);
 	default:
@@ -3457,36 +3457,22 @@ static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 		return -EOPNOTSUPP;
 	}
 }
-
-static int mlx5e_setup_tc_block(struct net_device *dev,
-				struct tc_block_offload *f)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
-					     priv, priv, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
-					priv);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
 #endif
 
+static LIST_HEAD(mlx5e_block_cb_list);
+
 static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			  void *type_data)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
 	switch (type) {
 #ifdef CONFIG_MLX5_ESWITCH
 	case TC_SETUP_BLOCK:
-		return mlx5e_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &mlx5e_block_cb_list,
+						  mlx5e_setup_tc_block_cb,
+						  priv, priv, true);
 #endif
 	case TC_SETUP_QDISC_MQPRIO:
 		return mlx5e_setup_tc_mqprio(dev, type_data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 6810b9fa0705..10ef90a7bddd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -656,7 +656,7 @@ static void mlx5e_rep_indr_clean_block_privs(struct mlx5e_rep_priv *rpriv)
 
 static int
 mlx5e_rep_indr_offload(struct net_device *netdev,
-		       struct tc_cls_flower_offload *flower,
+		       struct flow_cls_offload *flower,
 		       struct mlx5e_rep_indr_block_priv *indr_priv)
 {
 	struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev);
@@ -664,13 +664,13 @@ mlx5e_rep_indr_offload(struct net_device *netdev,
 	int err = 0;
 
 	switch (flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		err = mlx5e_configure_flower(netdev, priv, flower, flags);
 		break;
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		err = mlx5e_delete_flower(netdev, priv, flower, flags);
 		break;
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		err = mlx5e_stats_flower(netdev, priv, flower, flags);
 		break;
 	default:
@@ -693,23 +693,39 @@ static int mlx5e_rep_indr_setup_block_cb(enum tc_setup_type type,
 	}
 }
 
+static void mlx5e_rep_indr_tc_block_unbind(void *cb_priv)
+{
+	struct mlx5e_rep_indr_block_priv *indr_priv = cb_priv;
+
+	list_del(&indr_priv->list);
+	kfree(indr_priv);
+}
+
+static LIST_HEAD(mlx5e_block_cb_list);
+
 static int
 mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
 			      struct mlx5e_rep_priv *rpriv,
-			      struct tc_block_offload *f)
+			      struct flow_block_offload *f)
 {
 	struct mlx5e_rep_indr_block_priv *indr_priv;
-	int err = 0;
+	struct flow_block_cb *block_cb;
 
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
+	f->driver_block_list = &mlx5e_block_cb_list;
+
 	switch (f->command) {
-	case TC_BLOCK_BIND:
+	case FLOW_BLOCK_BIND:
 		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
 		if (indr_priv)
 			return -EEXIST;
 
+		if (flow_block_cb_is_busy(mlx5e_rep_indr_setup_block_cb,
+					  indr_priv, &mlx5e_block_cb_list))
+			return -EBUSY;
+
 		indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL);
 		if (!indr_priv)
 			return -ENOMEM;
@@ -719,26 +735,32 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev,
 		list_add(&indr_priv->list,
 			 &rpriv->uplink_priv.tc_indr_block_priv_list);
 
-		err = tcf_block_cb_register(f->block,
-					    mlx5e_rep_indr_setup_block_cb,
-					    indr_priv, indr_priv, f->extack);
-		if (err) {
+		block_cb = flow_block_cb_alloc(f->net,
+					       mlx5e_rep_indr_setup_block_cb,
+					       indr_priv, indr_priv,
+					       mlx5e_rep_indr_tc_block_unbind);
+		if (IS_ERR(block_cb)) {
 			list_del(&indr_priv->list);
 			kfree(indr_priv);
+			return PTR_ERR(block_cb);
 		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlx5e_block_cb_list);
 
-		return err;
-	case TC_BLOCK_UNBIND:
+		return 0;
+	case FLOW_BLOCK_UNBIND:
 		indr_priv = mlx5e_rep_indr_block_priv_lookup(rpriv, netdev);
 		if (!indr_priv)
 			return -ENOENT;
 
-		tcf_block_cb_unregister(f->block,
-					mlx5e_rep_indr_setup_block_cb,
-					indr_priv);
-		list_del(&indr_priv->list);
-		kfree(indr_priv);
+		block_cb = flow_block_cb_lookup(f,
+						mlx5e_rep_indr_setup_block_cb,
+						indr_priv);
+		if (!block_cb)
+			return -ENOENT;
 
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -1122,16 +1144,16 @@ static int mlx5e_rep_close(struct net_device *dev)
 
 static int
 mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv,
-			      struct tc_cls_flower_offload *cls_flower, int flags)
+			      struct flow_cls_offload *cls_flower, int flags)
 {
 	switch (cls_flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return mlx5e_configure_flower(priv->netdev, priv, cls_flower,
 					      flags);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return mlx5e_delete_flower(priv->netdev, priv, cls_flower,
 					   flags);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return mlx5e_stats_flower(priv->netdev, priv, cls_flower,
 					  flags);
 	default:
@@ -1153,32 +1175,16 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int mlx5e_rep_setup_tc_block(struct net_device *dev,
-				    struct tc_block_offload *f)
-{
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
-					     priv, priv, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			      void *type_data)
 {
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return mlx5e_rep_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data, NULL,
+						  mlx5e_rep_setup_tc_cb,
+						  priv, priv, true);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 3ac9b1e423ee..2d6436257f9d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1350,7 +1350,7 @@ static void mlx5e_tc_del_flow(struct mlx5e_priv *priv,
 
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5_flow_spec *spec,
-			     struct tc_cls_flower_offload *f,
+			     struct flow_cls_offload *f,
 			     struct net_device *filter_dev, u8 *match_level)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -1358,7 +1358,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 				       outer_headers);
 	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				       outer_headers);
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	int err;
 
 	err = mlx5e_tc_tun_parse(filter_dev, priv, spec, f,
@@ -1478,7 +1478,7 @@ static void *get_match_headers_value(u32 flags,
 
 static int __parse_cls_flower(struct mlx5e_priv *priv,
 			      struct mlx5_flow_spec *spec,
-			      struct tc_cls_flower_offload *f,
+			      struct flow_cls_offload *f,
 			      struct net_device *filter_dev,
 			      u8 *match_level, u8 *tunnel_match_level)
 {
@@ -1491,7 +1491,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				    misc_parameters);
 	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    misc_parameters);
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
@@ -1831,7 +1831,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 static int parse_cls_flower(struct mlx5e_priv *priv,
 			    struct mlx5e_tc_flow *flow,
 			    struct mlx5_flow_spec *spec,
-			    struct tc_cls_flower_offload *f,
+			    struct flow_cls_offload *f,
 			    struct net_device *filter_dev)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
@@ -3115,7 +3115,7 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow)
 
 static int
 mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size,
-		 struct tc_cls_flower_offload *f, u16 flow_flags,
+		 struct flow_cls_offload *f, u16 flow_flags,
 		 struct mlx5e_tc_flow_parse_attr **__parse_attr,
 		 struct mlx5e_tc_flow **__flow)
 {
@@ -3149,7 +3149,7 @@ static void
 mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr,
 			 struct mlx5e_priv *priv,
 			 struct mlx5e_tc_flow_parse_attr *parse_attr,
-			 struct tc_cls_flower_offload *f,
+			 struct flow_cls_offload *f,
 			 struct mlx5_eswitch_rep *in_rep,
 			 struct mlx5_core_dev *in_mdev)
 {
@@ -3171,13 +3171,13 @@ mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr,
 
 static struct mlx5e_tc_flow *
 __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
-		     struct tc_cls_flower_offload *f,
+		     struct flow_cls_offload *f,
 		     u16 flow_flags,
 		     struct net_device *filter_dev,
 		     struct mlx5_eswitch_rep *in_rep,
 		     struct mlx5_core_dev *in_mdev)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
@@ -3221,7 +3221,7 @@ out:
 	return ERR_PTR(err);
 }
 
-static int mlx5e_tc_add_fdb_peer_flow(struct tc_cls_flower_offload *f,
+static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f,
 				      struct mlx5e_tc_flow *flow,
 				      u16 flow_flags)
 {
@@ -3273,7 +3273,7 @@ out:
 
 static int
 mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
-		   struct tc_cls_flower_offload *f,
+		   struct flow_cls_offload *f,
 		   u16 flow_flags,
 		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
@@ -3307,12 +3307,12 @@ out:
 
 static int
 mlx5e_add_nic_flow(struct mlx5e_priv *priv,
-		   struct tc_cls_flower_offload *f,
+		   struct flow_cls_offload *f,
 		   u16 flow_flags,
 		   struct net_device *filter_dev,
 		   struct mlx5e_tc_flow **__flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 	struct mlx5e_tc_flow *flow;
@@ -3358,7 +3358,7 @@ out:
 
 static int
 mlx5e_tc_add_flow(struct mlx5e_priv *priv,
-		  struct tc_cls_flower_offload *f,
+		  struct flow_cls_offload *f,
 		  int flags,
 		  struct net_device *filter_dev,
 		  struct mlx5e_tc_flow **flow)
@@ -3383,7 +3383,7 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv,
 }
 
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			   struct tc_cls_flower_offload *f, int flags)
+			   struct flow_cls_offload *f, int flags)
 {
 	struct netlink_ext_ack *extack = f->common.extack;
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
@@ -3430,7 +3430,7 @@ static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags)
 }
 
 int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			struct tc_cls_flower_offload *f, int flags)
+			struct flow_cls_offload *f, int flags)
 {
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
 	struct mlx5e_tc_flow *flow;
@@ -3449,7 +3449,7 @@ int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
 }
 
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
-		       struct tc_cls_flower_offload *f, int flags)
+		       struct flow_cls_offload *f, int flags)
 {
 	struct mlx5_devcom *devcom = priv->mdev->priv.devcom;
 	struct rhashtable *tc_ht = get_tc_ht(priv, flags);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
index 8f288cc53cee..3ab39275ca7d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h
@@ -54,12 +54,12 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
 void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
 
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			   struct tc_cls_flower_offload *f, int flags);
+			   struct flow_cls_offload *f, int flags);
 int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv,
-			struct tc_cls_flower_offload *f, int flags);
+			struct flow_cls_offload *f, int flags);
 
 int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
-		       struct tc_cls_flower_offload *f, int flags);
+		       struct flow_cls_offload *f, int flags);
 
 struct mlx5e_encap_entry;
 void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ce285fbeebd3..4d34d42b3b0e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1508,21 +1508,21 @@ static int mlxsw_sp_setup_tc_cls_matchall(struct mlxsw_sp_port *mlxsw_sp_port,
 
 static int
 mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_acl_block *acl_block,
-			     struct tc_cls_flower_offload *f)
+			     struct flow_cls_offload *f)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_acl_block_mlxsw_sp(acl_block);
 
 	switch (f->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return mlxsw_sp_flower_replace(mlxsw_sp, acl_block, f);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		mlxsw_sp_flower_destroy(mlxsw_sp, acl_block, f);
 		return 0;
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return mlxsw_sp_flower_stats(mlxsw_sp, acl_block, f);
-	case TC_CLSFLOWER_TMPLT_CREATE:
+	case FLOW_CLS_TMPLT_CREATE:
 		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, acl_block, f);
-	case TC_CLSFLOWER_TMPLT_DESTROY:
+	case FLOW_CLS_TMPLT_DESTROY:
 		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, acl_block, f);
 		return 0;
 	default:
@@ -1585,33 +1585,45 @@ static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type,
 	}
 }
 
+static void mlxsw_sp_tc_block_flower_release(void *cb_priv)
+{
+	struct mlxsw_sp_acl_block *acl_block = cb_priv;
+
+	mlxsw_sp_acl_block_destroy(acl_block);
+}
+
+static LIST_HEAD(mlxsw_sp_block_cb_list);
+
 static int
 mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
-				    struct tcf_block *block, bool ingress,
-				    struct netlink_ext_ack *extack)
+			            struct flow_block_offload *f, bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_acl_block *acl_block;
-	struct tcf_block_cb *block_cb;
+	struct flow_block_cb *block_cb;
+	bool register_block = false;
 	int err;
 
-	block_cb = tcf_block_cb_lookup(block, mlxsw_sp_setup_tc_block_cb_flower,
-				       mlxsw_sp);
+	block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+					mlxsw_sp);
 	if (!block_cb) {
-		acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, block->net);
+		acl_block = mlxsw_sp_acl_block_create(mlxsw_sp, f->net);
 		if (!acl_block)
 			return -ENOMEM;
-		block_cb = __tcf_block_cb_register(block,
-						   mlxsw_sp_setup_tc_block_cb_flower,
-						   mlxsw_sp, acl_block, extack);
+		block_cb = flow_block_cb_alloc(f->net,
+					       mlxsw_sp_setup_tc_block_cb_flower,
+					       mlxsw_sp, acl_block,
+					       mlxsw_sp_tc_block_flower_release);
 		if (IS_ERR(block_cb)) {
+			mlxsw_sp_acl_block_destroy(acl_block);
 			err = PTR_ERR(block_cb);
 			goto err_cb_register;
 		}
+		register_block = true;
 	} else {
-		acl_block = tcf_block_cb_priv(block_cb);
+		acl_block = flow_block_cb_priv(block_cb);
 	}
-	tcf_block_cb_incref(block_cb);
+	flow_block_cb_incref(block_cb);
 	err = mlxsw_sp_acl_block_bind(mlxsw_sp, acl_block,
 				      mlxsw_sp_port, ingress);
 	if (err)
@@ -1622,28 +1634,31 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 	else
 		mlxsw_sp_port->eg_acl_block = acl_block;
 
+	if (register_block) {
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlxsw_sp_block_cb_list);
+	}
+
 	return 0;
 
 err_block_bind:
-	if (!tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block, block_cb);
+	if (!flow_block_cb_decref(block_cb))
+		flow_block_cb_free(block_cb);
 err_cb_register:
-		mlxsw_sp_acl_block_destroy(acl_block);
-	}
 	return err;
 }
 
 static void
 mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
-				      struct tcf_block *block, bool ingress)
+				      struct flow_block_offload *f, bool ingress)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_acl_block *acl_block;
-	struct tcf_block_cb *block_cb;
+	struct flow_block_cb *block_cb;
 	int err;
 
-	block_cb = tcf_block_cb_lookup(block, mlxsw_sp_setup_tc_block_cb_flower,
-				       mlxsw_sp);
+	block_cb = flow_block_cb_lookup(f, mlxsw_sp_setup_tc_block_cb_flower,
+					mlxsw_sp);
 	if (!block_cb)
 		return;
 
@@ -1652,50 +1667,63 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 	else
 		mlxsw_sp_port->eg_acl_block = NULL;
 
-	acl_block = tcf_block_cb_priv(block_cb);
+	acl_block = flow_block_cb_priv(block_cb);
 	err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block,
 					mlxsw_sp_port, ingress);
-	if (!err && !tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block, block_cb);
-		mlxsw_sp_acl_block_destroy(acl_block);
+	if (!err && !flow_block_cb_decref(block_cb)) {
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 	}
 }
 
 static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
-				   struct tc_block_offload *f)
+				   struct flow_block_offload *f)
 {
+	struct flow_block_cb *block_cb;
 	tc_setup_cb_t *cb;
 	bool ingress;
 	int err;
 
-	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
 		cb = mlxsw_sp_setup_tc_block_cb_matchall_ig;
 		ingress = true;
-	} else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
+	} else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
 		cb = mlxsw_sp_setup_tc_block_cb_matchall_eg;
 		ingress = false;
 	} else {
 		return -EOPNOTSUPP;
 	}
 
+	f->driver_block_list = &mlxsw_sp_block_cb_list;
+
 	switch (f->command) {
-	case TC_BLOCK_BIND:
-		err = tcf_block_cb_register(f->block, cb, mlxsw_sp_port,
-					    mlxsw_sp_port, f->extack);
-		if (err)
-			return err;
-		err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port,
-							  f->block, ingress,
-							  f->extack);
+	case FLOW_BLOCK_BIND:
+		if (flow_block_cb_is_busy(cb, mlxsw_sp_port,
+					  &mlxsw_sp_block_cb_list))
+			return -EBUSY;
+
+		block_cb = flow_block_cb_alloc(f->net, cb, mlxsw_sp_port,
+					       mlxsw_sp_port, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+		err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port, f,
+							  ingress);
 		if (err) {
-			tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
+			flow_block_cb_free(block_cb);
 			return err;
 		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &mlxsw_sp_block_cb_list);
 		return 0;
-	case TC_BLOCK_UNBIND:
+	case FLOW_BLOCK_UNBIND:
 		mlxsw_sp_setup_tc_block_flower_unbind(mlxsw_sp_port,
-						      f->block, ingress);
-		tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
+						      f, ingress);
+		block_cb = flow_block_cb_lookup(f, cb, mlxsw_sp_port);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index abbb563db440..a252b080dda9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -807,19 +807,19 @@ extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block,
-			    struct tc_cls_flower_offload *f);
+			    struct flow_cls_offload *f);
 void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_block *block,
-			     struct tc_cls_flower_offload *f);
+			     struct flow_cls_offload *f);
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_block *block,
-			  struct tc_cls_flower_offload *f);
+			  struct flow_cls_offload *f);
 int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_block *block,
-				 struct tc_cls_flower_offload *f);
+				 struct flow_cls_offload *f);
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_block *block,
-				   struct tc_cls_flower_offload *f);
+				   struct flow_cls_offload *f);
 
 /* spectrum_qdisc.c */
 int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index a83e1a986ef1..202e9a246019 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -121,10 +121,10 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 }
 
 static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei,
-				      struct tc_cls_flower_offload *f,
+				      struct flow_cls_offload *f,
 				      struct mlxsw_sp_acl_block *block)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	struct net_device *ingress_dev;
 	struct flow_match_meta match;
@@ -164,7 +164,7 @@ static int mlxsw_sp_flower_parse_meta(struct mlxsw_sp_acl_rule_info *rulei,
 }
 
 static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei,
-				       struct tc_cls_flower_offload *f)
+				       struct flow_cls_offload *f)
 {
 	struct flow_match_ipv4_addrs match;
 
@@ -179,7 +179,7 @@ static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei,
 }
 
 static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
-				       struct tc_cls_flower_offload *f)
+				       struct flow_cls_offload *f)
 {
 	struct flow_match_ipv6_addrs match;
 
@@ -213,10 +213,10 @@ static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
 
 static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_acl_rule_info *rulei,
-				       struct tc_cls_flower_offload *f,
+				       struct flow_cls_offload *f,
 				       u8 ip_proto)
 {
-	const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	const struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_match_ports match;
 
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS))
@@ -240,10 +240,10 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_rule_info *rulei,
-				     struct tc_cls_flower_offload *f,
+				     struct flow_cls_offload *f,
 				     u8 ip_proto)
 {
-	const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	const struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_match_tcp match;
 
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_TCP))
@@ -265,10 +265,10 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 
 static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 				    struct mlxsw_sp_acl_rule_info *rulei,
-				    struct tc_cls_flower_offload *f,
+				    struct flow_cls_offload *f,
 				    u16 n_proto)
 {
-	const struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	const struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_match_ip match;
 
 	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IP))
@@ -299,9 +299,9 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_block *block,
 				 struct mlxsw_sp_acl_rule_info *rulei,
-				 struct tc_cls_flower_offload *f)
+				 struct flow_cls_offload *f)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
 	u16 n_proto_mask = 0;
 	u16 n_proto_key = 0;
@@ -426,7 +426,7 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block,
-			    struct tc_cls_flower_offload *f)
+			    struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_rule_info *rulei;
 	struct mlxsw_sp_acl_ruleset *ruleset;
@@ -473,7 +473,7 @@ err_rule_create:
 
 void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 			     struct mlxsw_sp_acl_block *block,
-			     struct tc_cls_flower_offload *f)
+			     struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule *rule;
@@ -495,7 +495,7 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_block *block,
-			  struct tc_cls_flower_offload *f)
+			  struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule *rule;
@@ -531,7 +531,7 @@ err_rule_get_stats:
 
 int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_block *block,
-				 struct tc_cls_flower_offload *f)
+				 struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 	struct mlxsw_sp_acl_rule_info rulei;
@@ -552,7 +552,7 @@ int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_block *block,
-				   struct tc_cls_flower_offload *f)
+				   struct flow_cls_offload *f)
 {
 	struct mlxsw_sp_acl_ruleset *ruleset;
 
diff --git a/drivers/net/ethernet/mscc/ocelot_ace.h b/drivers/net/ethernet/mscc/ocelot_ace.h
index d621683643e1..e98944c87259 100644
--- a/drivers/net/ethernet/mscc/ocelot_ace.h
+++ b/drivers/net/ethernet/mscc/ocelot_ace.h
@@ -225,8 +225,8 @@ int ocelot_ace_init(struct ocelot *ocelot);
 void ocelot_ace_deinit(void);
 
 int ocelot_setup_tc_block_flower_bind(struct ocelot_port *port,
-				      struct tc_block_offload *f);
+				      struct flow_block_offload *f);
 void ocelot_setup_tc_block_flower_unbind(struct ocelot_port *port,
-					 struct tc_block_offload *f);
+					 struct flow_block_offload *f);
 
 #endif /* _MSCC_OCELOT_ACE_H_ */
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 8778dee5a471..7aaddc09c185 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -19,7 +19,7 @@ static u16 get_prio(u32 prio)
 	return prio >> 16;
 }
 
-static int ocelot_flower_parse_action(struct tc_cls_flower_offload *f,
+static int ocelot_flower_parse_action(struct flow_cls_offload *f,
 				      struct ocelot_ace_rule *rule)
 {
 	const struct flow_action_entry *a;
@@ -44,10 +44,10 @@ static int ocelot_flower_parse_action(struct tc_cls_flower_offload *f,
 	return 0;
 }
 
-static int ocelot_flower_parse(struct tc_cls_flower_offload *f,
+static int ocelot_flower_parse(struct flow_cls_offload *f,
 			       struct ocelot_ace_rule *ocelot_rule)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 	struct flow_dissector *dissector = rule->match.dissector;
 
 	if (dissector->used_keys &
@@ -174,7 +174,7 @@ finished_key_parsing:
 }
 
 static
-struct ocelot_ace_rule *ocelot_ace_rule_create(struct tc_cls_flower_offload *f,
+struct ocelot_ace_rule *ocelot_ace_rule_create(struct flow_cls_offload *f,
 					       struct ocelot_port_block *block)
 {
 	struct ocelot_ace_rule *rule;
@@ -188,7 +188,7 @@ struct ocelot_ace_rule *ocelot_ace_rule_create(struct tc_cls_flower_offload *f,
 	return rule;
 }
 
-static int ocelot_flower_replace(struct tc_cls_flower_offload *f,
+static int ocelot_flower_replace(struct flow_cls_offload *f,
 				 struct ocelot_port_block *port_block)
 {
 	struct ocelot_ace_rule *rule;
@@ -212,7 +212,7 @@ static int ocelot_flower_replace(struct tc_cls_flower_offload *f,
 	return 0;
 }
 
-static int ocelot_flower_destroy(struct tc_cls_flower_offload *f,
+static int ocelot_flower_destroy(struct flow_cls_offload *f,
 				 struct ocelot_port_block *port_block)
 {
 	struct ocelot_ace_rule rule;
@@ -230,7 +230,7 @@ static int ocelot_flower_destroy(struct tc_cls_flower_offload *f,
 	return 0;
 }
 
-static int ocelot_flower_stats_update(struct tc_cls_flower_offload *f,
+static int ocelot_flower_stats_update(struct flow_cls_offload *f,
 				      struct ocelot_port_block *port_block)
 {
 	struct ocelot_ace_rule rule;
@@ -247,15 +247,15 @@ static int ocelot_flower_stats_update(struct tc_cls_flower_offload *f,
 	return 0;
 }
 
-static int ocelot_setup_tc_cls_flower(struct tc_cls_flower_offload *f,
+static int ocelot_setup_tc_cls_flower(struct flow_cls_offload *f,
 				      struct ocelot_port_block *port_block)
 {
 	switch (f->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return ocelot_flower_replace(f, port_block);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return ocelot_flower_destroy(f, port_block);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return ocelot_flower_stats_update(f, port_block);
 	default:
 		return -EOPNOTSUPP;
@@ -299,36 +299,45 @@ static void ocelot_port_block_destroy(struct ocelot_port_block *block)
 	kfree(block);
 }
 
+static void ocelot_tc_block_unbind(void *cb_priv)
+{
+	struct ocelot_port_block *port_block = cb_priv;
+
+	ocelot_port_block_destroy(port_block);
+}
+
 int ocelot_setup_tc_block_flower_bind(struct ocelot_port *port,
-				      struct tc_block_offload *f)
+				      struct flow_block_offload *f)
 {
 	struct ocelot_port_block *port_block;
-	struct tcf_block_cb *block_cb;
+	struct flow_block_cb *block_cb;
 	int ret;
 
-	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
 		return -EOPNOTSUPP;
 
-	block_cb = tcf_block_cb_lookup(f->block,
-				       ocelot_setup_tc_block_cb_flower, port);
+	block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
+					port);
 	if (!block_cb) {
 		port_block = ocelot_port_block_create(port);
 		if (!port_block)
 			return -ENOMEM;
 
-		block_cb =
-			__tcf_block_cb_register(f->block,
-						ocelot_setup_tc_block_cb_flower,
-						port, port_block, f->extack);
+		block_cb = flow_block_cb_alloc(f->net,
+					       ocelot_setup_tc_block_cb_flower,
+					       port, port_block,
+					       ocelot_tc_block_unbind);
 		if (IS_ERR(block_cb)) {
 			ret = PTR_ERR(block_cb);
 			goto err_cb_register;
 		}
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, f->driver_block_list);
 	} else {
-		port_block = tcf_block_cb_priv(block_cb);
+		port_block = flow_block_cb_priv(block_cb);
 	}
 
-	tcf_block_cb_incref(block_cb);
+	flow_block_cb_incref(block_cb);
 	return 0;
 
 err_cb_register:
@@ -338,20 +347,17 @@ err_cb_register:
 }
 
 void ocelot_setup_tc_block_flower_unbind(struct ocelot_port *port,
-					 struct tc_block_offload *f)
+					 struct flow_block_offload *f)
 {
-	struct ocelot_port_block *port_block;
-	struct tcf_block_cb *block_cb;
+	struct flow_block_cb *block_cb;
 
-	block_cb = tcf_block_cb_lookup(f->block,
-				       ocelot_setup_tc_block_cb_flower, port);
+	block_cb = flow_block_cb_lookup(f, ocelot_setup_tc_block_cb_flower,
+					port);
 	if (!block_cb)
 		return;
 
-	port_block = tcf_block_cb_priv(block_cb);
-	if (!tcf_block_cb_decref(block_cb)) {
-		tcf_block_cb_unregister(f->block,
-					ocelot_setup_tc_block_cb_flower, port);
-		ocelot_port_block_destroy(port_block);
+	if (!flow_block_cb_decref(block_cb)) {
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 	}
 }
diff --git a/drivers/net/ethernet/mscc/ocelot_tc.c b/drivers/net/ethernet/mscc/ocelot_tc.c
index 72084306240d..9e6464ffae5d 100644
--- a/drivers/net/ethernet/mscc/ocelot_tc.c
+++ b/drivers/net/ethernet/mscc/ocelot_tc.c
@@ -128,35 +128,54 @@ static int ocelot_setup_tc_block_cb_eg(enum tc_setup_type type,
 					cb_priv, false);
 }
 
+static LIST_HEAD(ocelot_block_cb_list);
+
 static int ocelot_setup_tc_block(struct ocelot_port *port,
-				 struct tc_block_offload *f)
+				 struct flow_block_offload *f)
 {
+	struct flow_block_cb *block_cb;
 	tc_setup_cb_t *cb;
-	int ret;
+	int err;
 
 	netdev_dbg(port->dev, "tc_block command %d, binder_type %d\n",
 		   f->command, f->binder_type);
 
-	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
 		cb = ocelot_setup_tc_block_cb_ig;
-		port->tc.block_shared = tcf_block_shared(f->block);
-	} else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
+		port->tc.block_shared = f->block_shared;
+	} else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
 		cb = ocelot_setup_tc_block_cb_eg;
 	} else {
 		return -EOPNOTSUPP;
 	}
 
+	f->driver_block_list = &ocelot_block_cb_list;
+
 	switch (f->command) {
-	case TC_BLOCK_BIND:
-		ret = tcf_block_cb_register(f->block, cb, port,
-					    port, f->extack);
-		if (ret)
-			return ret;
-
-		return ocelot_setup_tc_block_flower_bind(port, f);
-	case TC_BLOCK_UNBIND:
+	case FLOW_BLOCK_BIND:
+		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);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		err = ocelot_setup_tc_block_flower_bind(port, f);
+		if (err < 0) {
+			flow_block_cb_free(block_cb);
+			return err;
+		}
+		flow_block_cb_add(block_cb, f);
+		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);
+		if (!block_cb)
+			return -ENOENT;
+
 		ocelot_setup_tc_block_flower_unbind(port, f);
-		tcf_block_cb_unregister(f->block, cb, port);
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c
index ff3913085665..23ebddfb9532 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/cls.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c
@@ -262,22 +262,12 @@ static int nfp_abm_setup_tc_block_cb(enum tc_setup_type type,
 	}
 }
 
+static LIST_HEAD(nfp_abm_block_cb_list);
+
 int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
-			    struct tc_block_offload *f)
+			    struct flow_block_offload *f)
 {
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     nfp_abm_setup_tc_block_cb,
-					     repr, repr, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, nfp_abm_setup_tc_block_cb,
-					repr);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
+	return flow_block_cb_setup_simple(f, &nfp_abm_block_cb_list,
+					  nfp_abm_setup_tc_block_cb,
+					  repr, repr, true);
 }
diff --git a/drivers/net/ethernet/netronome/nfp/abm/main.h b/drivers/net/ethernet/netronome/nfp/abm/main.h
index 49749c60885e..48746c9c6224 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/main.h
+++ b/drivers/net/ethernet/netronome/nfp/abm/main.h
@@ -247,7 +247,7 @@ int nfp_abm_setup_tc_mq(struct net_device *netdev, struct nfp_abm_link *alink,
 int nfp_abm_setup_tc_gred(struct net_device *netdev, struct nfp_abm_link *alink,
 			  struct tc_gred_qopt_offload *opt);
 int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
-			    struct tc_block_offload *opt);
+			    struct flow_block_offload *opt);
 
 int nfp_abm_ctrl_read_params(struct nfp_abm_link *alink);
 int nfp_abm_ctrl_find_addrs(struct nfp_abm *abm);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 9c136da25221..1c9fb11470df 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -160,35 +160,19 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type,
 	return 0;
 }
 
-static int nfp_bpf_setup_tc_block(struct net_device *netdev,
-				  struct tc_block_offload *f)
-{
-	struct nfp_net *nn = netdev_priv(netdev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     nfp_bpf_setup_tc_block_cb,
-					     nn, nn, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block,
-					nfp_bpf_setup_tc_block_cb,
-					nn);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(nfp_bpf_block_cb_list);
 
 static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev,
 			    enum tc_setup_type type, void *type_data)
 {
+	struct nfp_net *nn = netdev_priv(netdev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return nfp_bpf_setup_tc_block(netdev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &nfp_bpf_block_cb_list,
+						  nfp_bpf_setup_tc_block_cb,
+						  nn, nn, true);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index b6bd31fe44b2..5a54fe848de4 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -171,7 +171,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output,
 }
 
 static bool
-nfp_flower_tun_is_gre(struct tc_cls_flower_offload *flow, int start_idx)
+nfp_flower_tun_is_gre(struct flow_cls_offload *flow, int start_idx)
 {
 	struct flow_action_entry *act = flow->rule->action.entries;
 	int num_act = flow->rule->action.num_entries;
@@ -188,7 +188,7 @@ nfp_flower_tun_is_gre(struct tc_cls_flower_offload *flow, int start_idx)
 
 static enum nfp_flower_tun_type
 nfp_fl_get_tun_from_act(struct nfp_app *app,
-			struct tc_cls_flower_offload *flow,
+			struct flow_cls_offload *flow,
 			const struct flow_action_entry *act, int act_idx)
 {
 	const struct ip_tunnel_info *tun = act->tunnel;
@@ -669,11 +669,11 @@ struct nfp_flower_pedit_acts {
 };
 
 static int
-nfp_fl_commit_mangle(struct tc_cls_flower_offload *flow, char *nfp_action,
+nfp_fl_commit_mangle(struct flow_cls_offload *flow, char *nfp_action,
 		     int *a_len, struct nfp_flower_pedit_acts *set_act,
 		     u32 *csum_updated)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	size_t act_size = 0;
 	u8 ip_proto = 0;
 
@@ -771,7 +771,7 @@ nfp_fl_commit_mangle(struct tc_cls_flower_offload *flow, char *nfp_action,
 
 static int
 nfp_fl_pedit(const struct flow_action_entry *act,
-	     struct tc_cls_flower_offload *flow, char *nfp_action, int *a_len,
+	     struct flow_cls_offload *flow, char *nfp_action, int *a_len,
 	     u32 *csum_updated, struct nfp_flower_pedit_acts *set_act,
 	     struct netlink_ext_ack *extack)
 {
@@ -858,7 +858,7 @@ nfp_flower_output_action(struct nfp_app *app,
 
 static int
 nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act,
-		       struct tc_cls_flower_offload *flow,
+		       struct flow_cls_offload *flow,
 		       struct nfp_fl_payload *nfp_fl, int *a_len,
 		       struct net_device *netdev,
 		       enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
@@ -1021,7 +1021,7 @@ static bool nfp_fl_check_mangle_end(struct flow_action *flow_act,
 }
 
 int nfp_flower_compile_action(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct net_device *netdev,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct netlink_ext_ack *extack)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index 1f165d89582d..af9441d5787f 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -343,19 +343,19 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 				     struct nfp_fl_payload *sub_flow1,
 				     struct nfp_fl_payload *sub_flow2);
 int nfp_flower_compile_flow_match(struct nfp_app *app,
-				  struct tc_cls_flower_offload *flow,
+				  struct flow_cls_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
 				  enum nfp_flower_tun_type tun_type,
 				  struct netlink_ext_ack *extack);
 int nfp_flower_compile_action(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct net_device *netdev,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct netlink_ext_ack *extack);
 int nfp_compile_flow_metadata(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct net_device *netdev,
 			      struct netlink_ext_ack *extack);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index c1690de19172..9cc3ba17ff69 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -10,9 +10,9 @@
 static void
 nfp_flower_compile_meta_tci(struct nfp_flower_meta_tci *ext,
 			    struct nfp_flower_meta_tci *msk,
-			    struct tc_cls_flower_offload *flow, u8 key_type)
+			    struct flow_cls_offload *flow, u8 key_type)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	u16 tmp_tci;
 
 	memset(ext, 0, sizeof(struct nfp_flower_meta_tci));
@@ -78,9 +78,9 @@ nfp_flower_compile_port(struct nfp_flower_in_port *frame, u32 cmsg_port,
 static void
 nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
 		       struct nfp_flower_mac_mpls *msk,
-		       struct tc_cls_flower_offload *flow)
+		       struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	memset(ext, 0, sizeof(struct nfp_flower_mac_mpls));
 	memset(msk, 0, sizeof(struct nfp_flower_mac_mpls));
@@ -130,9 +130,9 @@ nfp_flower_compile_mac(struct nfp_flower_mac_mpls *ext,
 static void
 nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext,
 			 struct nfp_flower_tp_ports *msk,
-			 struct tc_cls_flower_offload *flow)
+			 struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	memset(ext, 0, sizeof(struct nfp_flower_tp_ports));
 	memset(msk, 0, sizeof(struct nfp_flower_tp_ports));
@@ -151,9 +151,9 @@ nfp_flower_compile_tport(struct nfp_flower_tp_ports *ext,
 static void
 nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext,
 			  struct nfp_flower_ip_ext *msk,
-			  struct tc_cls_flower_offload *flow)
+			  struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_match_basic match;
@@ -225,9 +225,9 @@ nfp_flower_compile_ip_ext(struct nfp_flower_ip_ext *ext,
 static void
 nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext,
 			struct nfp_flower_ipv4 *msk,
-			struct tc_cls_flower_offload *flow)
+			struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct flow_match_ipv4_addrs match;
 
 	memset(ext, 0, sizeof(struct nfp_flower_ipv4));
@@ -247,9 +247,9 @@ nfp_flower_compile_ipv4(struct nfp_flower_ipv4 *ext,
 static void
 nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext,
 			struct nfp_flower_ipv6 *msk,
-			struct tc_cls_flower_offload *flow)
+			struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	memset(ext, 0, sizeof(struct nfp_flower_ipv6));
 	memset(msk, 0, sizeof(struct nfp_flower_ipv6));
@@ -269,7 +269,7 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *ext,
 
 static int
 nfp_flower_compile_geneve_opt(void *ext, void *msk,
-			      struct tc_cls_flower_offload *flow)
+			      struct flow_cls_offload *flow)
 {
 	struct flow_match_enc_opts match;
 
@@ -283,9 +283,9 @@ nfp_flower_compile_geneve_opt(void *ext, void *msk,
 static void
 nfp_flower_compile_tun_ipv4_addrs(struct nfp_flower_tun_ipv4 *ext,
 				  struct nfp_flower_tun_ipv4 *msk,
-				  struct tc_cls_flower_offload *flow)
+				  struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS)) {
 		struct flow_match_ipv4_addrs match;
@@ -301,9 +301,9 @@ nfp_flower_compile_tun_ipv4_addrs(struct nfp_flower_tun_ipv4 *ext,
 static void
 nfp_flower_compile_tun_ip_ext(struct nfp_flower_tun_ip_ext *ext,
 			      struct nfp_flower_tun_ip_ext *msk,
-			      struct tc_cls_flower_offload *flow)
+			      struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_IP)) {
 		struct flow_match_ip match;
@@ -319,9 +319,9 @@ nfp_flower_compile_tun_ip_ext(struct nfp_flower_tun_ip_ext *ext,
 static void
 nfp_flower_compile_ipv4_gre_tun(struct nfp_flower_ipv4_gre_tun *ext,
 				struct nfp_flower_ipv4_gre_tun *msk,
-				struct tc_cls_flower_offload *flow)
+				struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	memset(ext, 0, sizeof(struct nfp_flower_ipv4_gre_tun));
 	memset(msk, 0, sizeof(struct nfp_flower_ipv4_gre_tun));
@@ -348,9 +348,9 @@ nfp_flower_compile_ipv4_gre_tun(struct nfp_flower_ipv4_gre_tun *ext,
 static void
 nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext,
 				struct nfp_flower_ipv4_udp_tun *msk,
-				struct tc_cls_flower_offload *flow)
+				struct flow_cls_offload *flow)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 
 	memset(ext, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
 	memset(msk, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
@@ -371,7 +371,7 @@ nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *ext,
 }
 
 int nfp_flower_compile_flow_match(struct nfp_app *app,
-				  struct tc_cls_flower_offload *flow,
+				  struct flow_cls_offload *flow,
 				  struct nfp_fl_key_ls *key_ls,
 				  struct net_device *netdev,
 				  struct nfp_fl_payload *nfp_flow,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index dae60961c1eb..7c4a15e967df 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -290,7 +290,7 @@ nfp_check_mask_remove(struct nfp_app *app, char *mask_data, u32 mask_len,
 }
 
 int nfp_compile_flow_metadata(struct nfp_app *app,
-			      struct tc_cls_flower_offload *flow,
+			      struct flow_cls_offload *flow,
 			      struct nfp_fl_payload *nfp_flow,
 			      struct net_device *netdev,
 			      struct netlink_ext_ack *extack)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 6dbe947269c3..7e725fa60347 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -121,9 +121,9 @@ nfp_flower_xmit_flow(struct nfp_app *app, struct nfp_fl_payload *nfp_flow,
 	return 0;
 }
 
-static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f)
+static bool nfp_flower_check_higher_than_mac(struct flow_cls_offload *f)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 
 	return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS) ||
 	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS) ||
@@ -131,9 +131,9 @@ static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f)
 	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP);
 }
 
-static bool nfp_flower_check_higher_than_l3(struct tc_cls_flower_offload *f)
+static bool nfp_flower_check_higher_than_l3(struct flow_cls_offload *f)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(f);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
 
 	return flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS) ||
 	       flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ICMP);
@@ -212,11 +212,11 @@ static int
 nfp_flower_calculate_key_layers(struct nfp_app *app,
 				struct net_device *netdev,
 				struct nfp_fl_key_ls *ret_key_ls,
-				struct tc_cls_flower_offload *flow,
+				struct flow_cls_offload *flow,
 				enum nfp_flower_tun_type *tun_type,
 				struct netlink_ext_ack *extack)
 {
-	struct flow_rule *rule = tc_cls_flower_offload_flow_rule(flow);
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct flow_dissector *dissector = rule->match.dissector;
 	struct flow_match_basic basic = { NULL, NULL};
 	struct nfp_flower_priv *priv = app->priv;
@@ -866,7 +866,7 @@ int nfp_flower_merge_offloaded_flows(struct nfp_app *app,
 				     struct nfp_fl_payload *sub_flow1,
 				     struct nfp_fl_payload *sub_flow2)
 {
-	struct tc_cls_flower_offload merge_tc_off;
+	struct flow_cls_offload merge_tc_off;
 	struct nfp_flower_priv *priv = app->priv;
 	struct netlink_ext_ack *extack = NULL;
 	struct nfp_fl_payload *merge_flow;
@@ -962,7 +962,7 @@ err_destroy_merge_flow:
  */
 static int
 nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow)
+		       struct flow_cls_offload *flow)
 {
 	enum nfp_flower_tun_type tun_type = NFP_FL_TUNNEL_NONE;
 	struct nfp_flower_priv *priv = app->priv;
@@ -1125,7 +1125,7 @@ nfp_flower_del_linked_merge_flows(struct nfp_app *app,
  */
 static int
 nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev,
-		       struct tc_cls_flower_offload *flow)
+		       struct flow_cls_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct netlink_ext_ack *extack = NULL;
@@ -1232,7 +1232,7 @@ nfp_flower_update_merge_stats(struct nfp_app *app,
  */
 static int
 nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
-		     struct tc_cls_flower_offload *flow)
+		     struct flow_cls_offload *flow)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct netlink_ext_ack *extack = NULL;
@@ -1265,17 +1265,17 @@ nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev,
 
 static int
 nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
-			struct tc_cls_flower_offload *flower)
+			struct flow_cls_offload *flower)
 {
 	if (!eth_proto_is_802_3(flower->common.protocol))
 		return -EOPNOTSUPP;
 
 	switch (flower->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return nfp_flower_add_offload(app, netdev, flower);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return nfp_flower_del_offload(app, netdev, flower);
-	case TC_CLSFLOWER_STATS:
+	case FLOW_CLS_STATS:
 		return nfp_flower_get_stats(app, netdev, flower);
 	default:
 		return -EOPNOTSUPP;
@@ -1302,27 +1302,45 @@ static int nfp_flower_setup_tc_block_cb(enum tc_setup_type type,
 	}
 }
 
+static LIST_HEAD(nfp_block_cb_list);
+
 static int nfp_flower_setup_tc_block(struct net_device *netdev,
-				     struct tc_block_offload *f)
+				     struct flow_block_offload *f)
 {
 	struct nfp_repr *repr = netdev_priv(netdev);
 	struct nfp_flower_repr_priv *repr_priv;
+	struct flow_block_cb *block_cb;
 
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
 	repr_priv = repr->app_priv;
-	repr_priv->block_shared = tcf_block_shared(f->block);
+	repr_priv->block_shared = f->block_shared;
+	f->driver_block_list = &nfp_block_cb_list;
 
 	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     nfp_flower_setup_tc_block_cb,
-					     repr, repr, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block,
-					nfp_flower_setup_tc_block_cb,
-					repr);
+	case FLOW_BLOCK_BIND:
+		if (flow_block_cb_is_busy(nfp_flower_setup_tc_block_cb, repr,
+					  &nfp_block_cb_list))
+			return -EBUSY;
+
+		block_cb = flow_block_cb_alloc(f->net,
+					       nfp_flower_setup_tc_block_cb,
+					       repr, repr, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_add(block_cb, f);
+		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,
+						repr);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
@@ -1367,7 +1385,7 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 					  void *type_data, void *cb_priv)
 {
 	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
-	struct tc_cls_flower_offload *flower = type_data;
+	struct flow_cls_offload *flower = type_data;
 
 	if (flower->common.chain_index)
 		return -EOPNOTSUPP;
@@ -1381,21 +1399,29 @@ static int nfp_flower_setup_indr_block_cb(enum tc_setup_type type,
 	}
 }
 
+static void nfp_flower_setup_indr_tc_release(void *cb_priv)
+{
+	struct nfp_flower_indr_block_cb_priv *priv = cb_priv;
+
+	list_del(&priv->list);
+	kfree(priv);
+}
+
 static int
 nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
-			       struct tc_block_offload *f)
+			       struct flow_block_offload *f)
 {
 	struct nfp_flower_indr_block_cb_priv *cb_priv;
 	struct nfp_flower_priv *priv = app->priv;
-	int err;
+	struct flow_block_cb *block_cb;
 
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
-	    !(f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
+	    !(f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS &&
 	      nfp_flower_internal_port_can_offload(app, netdev)))
 		return -EOPNOTSUPP;
 
 	switch (f->command) {
-	case TC_BLOCK_BIND:
+	case FLOW_BLOCK_BIND:
 		cb_priv = kmalloc(sizeof(*cb_priv), GFP_KERNEL);
 		if (!cb_priv)
 			return -ENOMEM;
@@ -1404,26 +1430,32 @@ 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);
 
-		err = tcf_block_cb_register(f->block,
-					    nfp_flower_setup_indr_block_cb,
-					    cb_priv, cb_priv, f->extack);
-		if (err) {
+		block_cb = flow_block_cb_alloc(f->net,
+					       nfp_flower_setup_indr_block_cb,
+					       cb_priv, cb_priv,
+					       nfp_flower_setup_indr_tc_release);
+		if (IS_ERR(block_cb)) {
 			list_del(&cb_priv->list);
 			kfree(cb_priv);
+			return PTR_ERR(block_cb);
 		}
 
-		return err;
-	case TC_BLOCK_UNBIND:
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &nfp_block_cb_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
 		cb_priv = nfp_flower_indr_block_cb_priv_lookup(app, netdev);
 		if (!cb_priv)
 			return -ENOENT;
 
-		tcf_block_cb_unregister(f->block,
-					nfp_flower_setup_indr_block_cb,
-					cb_priv);
-		list_del(&cb_priv->list);
-		kfree(cb_priv);
+		block_cb = flow_block_cb_lookup(f,
+						nfp_flower_setup_indr_block_cb,
+						cb_priv);
+		if (!block_cb)
+			return -ENOENT;
 
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index b972ab07c18b..0e931c04fecf 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -551,7 +551,7 @@ int qede_txq_has_work(struct qede_tx_queue *txq);
 void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, u8 count);
 void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
 int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
-			    struct tc_cls_flower_offload *f);
+			    struct flow_cls_offload *f);
 
 #define RX_RING_SIZE_POW	13
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index add922b93d2c..9a6a9a008714 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1943,7 +1943,7 @@ qede_parse_flow_attr(struct qede_dev *edev, __be16 proto,
 }
 
 int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
-			    struct tc_cls_flower_offload *f)
+			    struct flow_cls_offload *f)
 {
 	struct qede_arfs_fltr_node *n;
 	int min_hlen, rc = -EINVAL;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index d4a29660751d..8d1c208f778f 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -548,13 +548,13 @@ static int qede_setup_tc(struct net_device *ndev, u8 num_tc)
 }
 
 static int
-qede_set_flower(struct qede_dev *edev, struct tc_cls_flower_offload *f,
+qede_set_flower(struct qede_dev *edev, struct flow_cls_offload *f,
 		__be16 proto)
 {
 	switch (f->command) {
-	case TC_CLSFLOWER_REPLACE:
+	case FLOW_CLS_REPLACE:
 		return qede_add_tc_flower_fltr(edev, proto, f);
-	case TC_CLSFLOWER_DESTROY:
+	case FLOW_CLS_DESTROY:
 		return qede_delete_flow_filter(edev, f->cookie);
 	default:
 		return -EOPNOTSUPP;
@@ -564,7 +564,7 @@ qede_set_flower(struct qede_dev *edev, struct tc_cls_flower_offload *f,
 static int qede_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 				  void *cb_priv)
 {
-	struct tc_cls_flower_offload *f;
+	struct flow_cls_offload *f;
 	struct qede_dev *edev = cb_priv;
 
 	if (!tc_cls_can_offload_and_chain0(edev->ndev, type_data))
@@ -579,24 +579,7 @@ static int qede_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	}
 }
 
-static int qede_setup_tc_block(struct qede_dev *edev,
-			       struct tc_block_offload *f)
-{
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block,
-					     qede_setup_tc_block_cb,
-					     edev, edev, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, qede_setup_tc_block_cb, edev);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(qede_block_cb_list);
 
 static int
 qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
@@ -607,7 +590,10 @@ qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return qede_setup_tc_block(edev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &qede_block_cb_list,
+						  qede_setup_tc_block_cb,
+						  edev, edev, true);
 	case TC_SETUP_QDISC_MQPRIO:
 		mqprio = type_data;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e4b06dc484b7..c7c9e5f162e6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3769,23 +3769,7 @@ static int stmmac_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 	return ret;
 }
 
-static int stmmac_setup_tc_block(struct stmmac_priv *priv,
-				 struct tc_block_offload *f)
-{
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb,
-				priv, priv, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
+static LIST_HEAD(stmmac_block_cb_list);
 
 static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 			   void *type_data)
@@ -3794,7 +3778,10 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return stmmac_setup_tc_block(priv, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &stmmac_block_cb_list,
+						  stmmac_setup_tc_block_cb,
+						  priv, priv, true);
 	case TC_SETUP_QDISC_CBS:
 		return stmmac_tc_setup_cbs(priv, priv, type_data);
 	default:
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index e5c8aa08e1cd..0740940f41b1 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -78,26 +78,6 @@ nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
 	return nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
 }
 
-static int
-nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
-{
-	struct netdevsim *ns = netdev_priv(dev);
-
-	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		return -EOPNOTSUPP;
-
-	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
-					     ns, ns, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
-		return 0;
-	default:
-		return -EOPNOTSUPP;
-	}
-}
-
 static int nsim_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
 {
 	struct netdevsim *ns = netdev_priv(dev);
@@ -223,12 +203,19 @@ static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state)
 	return 0;
 }
 
+static LIST_HEAD(nsim_block_cb_list);
+
 static int
 nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
 {
+	struct netdevsim *ns = netdev_priv(dev);
+
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return nsim_setup_tc_block(dev, type_data);
+		return flow_block_cb_setup_simple(type_data,
+						  &nsim_block_cb_list,
+						  nsim_setup_tc_block_cb,
+						  ns, ns, true);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h
index a09e256d2b27..db337299e81e 100644
--- a/include/net/flow_offload.h
+++ b/include/net/flow_offload.h
@@ -3,6 +3,7 @@
 
 #include <linux/kernel.h>
 #include <net/flow_dissector.h>
+#include <net/sch_generic.h>
 
 struct flow_match {
 	struct flow_dissector	*dissector;
@@ -237,4 +238,99 @@ static inline void flow_stats_update(struct flow_stats *flow_stats,
 	flow_stats->lastused	= max_t(u64, flow_stats->lastused, lastused);
 }
 
+enum flow_block_command {
+	FLOW_BLOCK_BIND,
+	FLOW_BLOCK_UNBIND,
+};
+
+enum flow_block_binder_type {
+	FLOW_BLOCK_BINDER_TYPE_UNSPEC,
+	FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
+	FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
+};
+
+struct netlink_ext_ack;
+
+struct flow_block_offload {
+	enum flow_block_command command;
+	enum flow_block_binder_type binder_type;
+	bool block_shared;
+	struct net *net;
+	struct list_head cb_list;
+	struct list_head *driver_block_list;
+	struct netlink_ext_ack *extack;
+};
+
+struct flow_block_cb {
+	struct list_head	driver_list;
+	struct list_head	list;
+	struct net		*net;
+	tc_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,
+					  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);
+
+void *flow_block_cb_priv(struct flow_block_cb *block_cb);
+void flow_block_cb_incref(struct flow_block_cb *block_cb);
+unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb);
+
+static inline void flow_block_cb_add(struct flow_block_cb *block_cb,
+				     struct flow_block_offload *offload)
+{
+	list_add_tail(&block_cb->list, &offload->cb_list);
+}
+
+static inline void flow_block_cb_remove(struct flow_block_cb *block_cb,
+					struct flow_block_offload *offload)
+{
+	list_move(&block_cb->list, &offload->cb_list);
+}
+
+bool flow_block_cb_is_busy(tc_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,
+			       void *cb_ident, void *cb_priv, bool ingress_only);
+
+enum flow_cls_command {
+	FLOW_CLS_REPLACE,
+	FLOW_CLS_DESTROY,
+	FLOW_CLS_STATS,
+	FLOW_CLS_TMPLT_CREATE,
+	FLOW_CLS_TMPLT_DESTROY,
+};
+
+struct flow_cls_common_offload {
+	u32 chain_index;
+	__be16 protocol;
+	u32 prio;
+	struct netlink_ext_ack *extack;
+};
+
+struct flow_cls_offload {
+	struct flow_cls_common_offload common;
+	enum flow_cls_command command;
+	unsigned long cookie;
+	struct flow_rule *rule;
+	struct flow_stats stats;
+	u32 classid;
+};
+
+static inline struct flow_rule *
+flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd)
+{
+	return flow_cmd->rule;
+}
+
 #endif /* _NET_FLOW_OFFLOAD_H */
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 9e8493aad49d..35dfdd9f69b3 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -161,6 +161,7 @@ struct nft_ctx {
 	const struct nlattr * const 	*nla;
 	u32				portid;
 	u32				seq;
+	u16				flags;
 	u8				family;
 	u8				level;
 	bool				report;
@@ -735,6 +736,9 @@ enum nft_trans_phase {
 	NFT_TRANS_RELEASE
 };
 
+struct nft_flow_rule;
+struct nft_offload_ctx;
+
 /**
  *	struct nft_expr_ops - nf_tables expression operations
  *
@@ -777,6 +781,10 @@ struct nft_expr_ops {
 						    const struct nft_data **data);
 	bool				(*gc)(struct net *net,
 					      const struct nft_expr *expr);
+	int				(*offload)(struct nft_offload_ctx *ctx,
+						   struct nft_flow_rule *flow,
+						   const struct nft_expr *expr);
+	u32				offload_flags;
 	const struct nft_expr_type	*type;
 	void				*data;
 };
@@ -859,6 +867,7 @@ static inline struct nft_userdata *nft_userdata(const struct nft_rule *rule)
 
 enum nft_chain_flags {
 	NFT_BASE_CHAIN			= 0x1,
+	NFT_CHAIN_HW_OFFLOAD		= 0x2,
 };
 
 /**
@@ -942,6 +951,7 @@ 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)
  */
 struct nft_base_chain {
 	struct nf_hook_ops		ops;
@@ -951,6 +961,7 @@ struct nft_base_chain {
 	struct nft_stats __percpu	*stats;
 	struct nft_chain		chain;
 	char 				dev_name[IFNAMSIZ];
+	struct list_head		cb_list;
 };
 
 static inline struct nft_base_chain *nft_base_chain(const struct nft_chain *chain)
@@ -1322,11 +1333,14 @@ struct nft_trans {
 
 struct nft_trans_rule {
 	struct nft_rule			*rule;
+	struct nft_flow_rule		*flow;
 	u32				rule_id;
 };
 
 #define nft_trans_rule(trans)	\
 	(((struct nft_trans_rule *)trans->data)->rule)
+#define nft_trans_flow_rule(trans)	\
+	(((struct nft_trans_rule *)trans->data)->flow)
 #define nft_trans_rule_id(trans)	\
 	(((struct nft_trans_rule *)trans->data)->rule_id)
 
diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h
new file mode 100644
index 000000000000..3196663a10e3
--- /dev/null
+++ b/include/net/netfilter/nf_tables_offload.h
@@ -0,0 +1,76 @@
+#ifndef _NET_NF_TABLES_OFFLOAD_H
+#define _NET_NF_TABLES_OFFLOAD_H
+
+#include <net/flow_offload.h>
+#include <net/netfilter/nf_tables.h>
+
+struct nft_offload_reg {
+	u32		key;
+	u32		len;
+	u32		base_offset;
+	u32		offset;
+	struct nft_data	mask;
+};
+
+enum nft_offload_dep_type {
+	NFT_OFFLOAD_DEP_UNSPEC	= 0,
+	NFT_OFFLOAD_DEP_NETWORK,
+	NFT_OFFLOAD_DEP_TRANSPORT,
+};
+
+struct nft_offload_ctx {
+	struct {
+		enum nft_offload_dep_type	type;
+		__be16				l3num;
+		u8				protonum;
+	} dep;
+	unsigned int				num_actions;
+	struct nft_offload_reg			regs[NFT_REG32_15 + 1];
+};
+
+void nft_offload_set_dependency(struct nft_offload_ctx *ctx,
+				enum nft_offload_dep_type type);
+void nft_offload_update_dependency(struct nft_offload_ctx *ctx,
+				   const void *data, u32 len);
+
+struct nft_flow_key {
+	struct flow_dissector_key_basic			basic;
+	union {
+		struct flow_dissector_key_ipv4_addrs	ipv4;
+		struct flow_dissector_key_ipv6_addrs	ipv6;
+	};
+	struct flow_dissector_key_ports			tp;
+	struct flow_dissector_key_ip			ip;
+	struct flow_dissector_key_vlan			vlan;
+	struct flow_dissector_key_eth_addrs		eth_addrs;
+} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
+
+struct nft_flow_match {
+	struct flow_dissector	dissector;
+	struct nft_flow_key	key;
+	struct nft_flow_key	mask;
+};
+
+struct nft_flow_rule {
+	__be16			proto;
+	struct nft_flow_match	match;
+	struct flow_rule	*rule;
+};
+
+#define NFT_OFFLOAD_F_ACTION	(1 << 0)
+
+struct nft_rule;
+struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule);
+void nft_flow_rule_destroy(struct nft_flow_rule *flow);
+int nft_flow_rule_offload_commit(struct net *net);
+
+#define NFT_OFFLOAD_MATCH(__key, __base, __field, __len, __reg)		\
+	(__reg)->base_offset	=					\
+		offsetof(struct nft_flow_key, __base);			\
+	(__reg)->offset		=					\
+		offsetof(struct nft_flow_key, __base.__field);		\
+	(__reg)->len		= __len;				\
+	(__reg)->key		= __key;				\
+	memset(&(__reg)->mask, 0xff, (__reg)->len);
+
+#endif
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 1a7596ba0dbe..b03d466182db 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -26,14 +26,8 @@ struct tcf_walker {
 int register_tcf_proto_ops(struct tcf_proto_ops *ops);
 int unregister_tcf_proto_ops(struct tcf_proto_ops *ops);
 
-enum tcf_block_binder_type {
-	TCF_BLOCK_BINDER_TYPE_UNSPEC,
-	TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
-	TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS,
-};
-
 struct tcf_block_ext_info {
-	enum tcf_block_binder_type binder_type;
+	enum flow_block_binder_type binder_type;
 	tcf_chain_head_change_t *chain_head_change;
 	void *chain_head_change_priv;
 	u32 block_index;
@@ -72,22 +66,6 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 	return block->q;
 }
 
-void *tcf_block_cb_priv(struct tcf_block_cb *block_cb);
-struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
-					 tc_setup_cb_t *cb, void *cb_ident);
-void tcf_block_cb_incref(struct tcf_block_cb *block_cb);
-unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb);
-struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
-					     tc_setup_cb_t *cb, void *cb_ident,
-					     void *cb_priv,
-					     struct netlink_ext_ack *extack);
-int tcf_block_cb_register(struct tcf_block *block,
-			  tc_setup_cb_t *cb, void *cb_ident,
-			  void *cb_priv, struct netlink_ext_ack *extack);
-void __tcf_block_cb_unregister(struct tcf_block *block,
-			       struct tcf_block_cb *block_cb);
-void tcf_block_cb_unregister(struct tcf_block *block,
-			     tc_setup_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);
 int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
@@ -151,59 +129,6 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
 }
 
 static inline
-void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
-{
-	return NULL;
-}
-
-static inline
-struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
-					 tc_setup_cb_t *cb, void *cb_ident)
-{
-	return NULL;
-}
-
-static inline
-void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
-{
-}
-
-static inline
-unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
-{
-	return 0;
-}
-
-static inline
-struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
-					     tc_setup_cb_t *cb, void *cb_ident,
-					     void *cb_priv,
-					     struct netlink_ext_ack *extack)
-{
-	return NULL;
-}
-
-static inline
-int tcf_block_cb_register(struct tcf_block *block,
-			  tc_setup_cb_t *cb, void *cb_ident,
-			  void *cb_priv, struct netlink_ext_ack *extack)
-{
-	return 0;
-}
-
-static inline
-void __tcf_block_cb_unregister(struct tcf_block *block,
-			       struct tcf_block_cb *block_cb)
-{
-}
-
-static inline
-void tcf_block_cb_unregister(struct tcf_block *block,
-			     tc_setup_cb_t *cb, void *cb_ident)
-{
-}
-
-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)
 {
@@ -610,25 +535,6 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
 		     void *type_data, bool err_stop);
 unsigned int tcf_exts_num_actions(struct tcf_exts *exts);
 
-enum tc_block_command {
-	TC_BLOCK_BIND,
-	TC_BLOCK_UNBIND,
-};
-
-struct tc_block_offload {
-	enum tc_block_command command;
-	enum tcf_block_binder_type binder_type;
-	struct tcf_block *block;
-	struct netlink_ext_ack *extack;
-};
-
-struct tc_cls_common_offload {
-	u32 chain_index;
-	__be16 protocol;
-	u32 prio;
-	struct netlink_ext_ack *extack;
-};
-
 struct tc_cls_u32_knode {
 	struct tcf_exts *exts;
 	struct tcf_result *res;
@@ -656,7 +562,7 @@ enum tc_clsu32_command {
 };
 
 struct tc_cls_u32_offload {
-	struct tc_cls_common_offload common;
+	struct flow_cls_common_offload common;
 	/* knode values */
 	enum tc_clsu32_command command;
 	union {
@@ -683,7 +589,7 @@ static inline bool tc_can_offload_extack(const struct net_device *dev,
 
 static inline bool
 tc_cls_can_offload_and_chain0(const struct net_device *dev,
-			      struct tc_cls_common_offload *common)
+			      struct flow_cls_common_offload *common)
 {
 	if (!tc_can_offload_extack(dev, common->extack))
 		return false;
@@ -725,7 +631,7 @@ static inline bool tc_in_hw(u32 flags)
 }
 
 static inline void
-tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common,
+tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common,
 			   const struct tcf_proto *tp, u32 flags,
 			   struct netlink_ext_ack *extack)
 {
@@ -736,29 +642,6 @@ tc_cls_common_offload_init(struct tc_cls_common_offload *cls_common,
 		cls_common->extack = extack;
 }
 
-enum tc_fl_command {
-	TC_CLSFLOWER_REPLACE,
-	TC_CLSFLOWER_DESTROY,
-	TC_CLSFLOWER_STATS,
-	TC_CLSFLOWER_TMPLT_CREATE,
-	TC_CLSFLOWER_TMPLT_DESTROY,
-};
-
-struct tc_cls_flower_offload {
-	struct tc_cls_common_offload common;
-	enum tc_fl_command command;
-	unsigned long cookie;
-	struct flow_rule *rule;
-	struct flow_stats stats;
-	u32 classid;
-};
-
-static inline struct flow_rule *
-tc_cls_flower_offload_flow_rule(struct tc_cls_flower_offload *tc_flow_cmd)
-{
-	return tc_flow_cmd->rule;
-}
-
 enum tc_matchall_command {
 	TC_CLSMATCHALL_REPLACE,
 	TC_CLSMATCHALL_DESTROY,
@@ -766,7 +649,7 @@ enum tc_matchall_command {
 };
 
 struct tc_cls_matchall_offload {
-	struct tc_cls_common_offload common;
+	struct flow_cls_common_offload common;
 	enum tc_matchall_command command;
 	struct flow_rule *rule;
 	struct flow_stats stats;
@@ -779,7 +662,7 @@ enum tc_clsbpf_command {
 };
 
 struct tc_cls_bpf_offload {
-	struct tc_cls_common_offload common;
+	struct flow_cls_common_offload common;
 	enum tc_clsbpf_command command;
 	struct tcf_exts *exts;
 	struct bpf_prog *prog;
diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 0e3462dfb182..82abaa183fc3 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -192,6 +192,7 @@ enum nft_table_attributes {
  * @NFTA_CHAIN_USE: number of references to this chain (NLA_U32)
  * @NFTA_CHAIN_TYPE: type name of the string (NLA_NUL_STRING)
  * @NFTA_CHAIN_COUNTERS: counter specification of the chain (NLA_NESTED: nft_counter_attributes)
+ * @NFTA_CHAIN_FLAGS: chain flags
  */
 enum nft_chain_attributes {
 	NFTA_CHAIN_UNSPEC,
@@ -204,6 +205,7 @@ enum nft_chain_attributes {
 	NFTA_CHAIN_TYPE,
 	NFTA_CHAIN_COUNTERS,
 	NFTA_CHAIN_PAD,
+	NFTA_CHAIN_FLAGS,
 	__NFTA_CHAIN_MAX
 };
 #define NFTA_CHAIN_MAX		(__NFTA_CHAIN_MAX - 1)
diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c
index f52fe0bc4017..76f8db3841d7 100644
--- a/net/core/flow_offload.c
+++ b/net/core/flow_offload.c
@@ -164,3 +164,121 @@ void flow_rule_match_enc_opts(const struct flow_rule *rule,
 	FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_OPTS, out);
 }
 EXPORT_SYMBOL(flow_rule_match_enc_opts);
+
+struct flow_block_cb *flow_block_cb_alloc(struct net *net, tc_setup_cb_t *cb,
+					  void *cb_ident, void *cb_priv,
+					  void (*release)(void *cb_priv))
+{
+	struct flow_block_cb *block_cb;
+
+	block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
+	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;
+	block_cb->release = release;
+
+	return block_cb;
+}
+EXPORT_SYMBOL(flow_block_cb_alloc);
+
+void flow_block_cb_free(struct flow_block_cb *block_cb)
+{
+	if (block_cb->release)
+		block_cb->release(block_cb->cb_priv);
+
+	kfree(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 *block_cb;
+
+	list_for_each_entry(block_cb, f->driver_block_list, driver_list) {
+		if (block_cb->net == f->net &&
+		    block_cb->cb == cb &&
+		    block_cb->cb_ident == cb_ident)
+			return block_cb;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL(flow_block_cb_lookup);
+
+void *flow_block_cb_priv(struct flow_block_cb *block_cb)
+{
+	return block_cb->cb_priv;
+}
+EXPORT_SYMBOL(flow_block_cb_priv);
+
+void flow_block_cb_incref(struct flow_block_cb *block_cb)
+{
+	block_cb->refcnt++;
+}
+EXPORT_SYMBOL(flow_block_cb_incref);
+
+unsigned int flow_block_cb_decref(struct flow_block_cb *block_cb)
+{
+	return --block_cb->refcnt;
+}
+EXPORT_SYMBOL(flow_block_cb_decref);
+
+bool flow_block_cb_is_busy(tc_setup_cb_t *cb, void *cb_ident,
+			   struct list_head *driver_block_list)
+{
+	struct flow_block_cb *block_cb;
+
+	list_for_each_entry(block_cb, driver_block_list, driver_list) {
+		if (block_cb->cb == cb &&
+		    block_cb->cb_ident == cb_ident)
+			return true;
+	}
+
+	return false;
+}
+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,
+			       bool ingress_only)
+{
+	struct flow_block_cb *block_cb;
+
+	if (ingress_only &&
+	    f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	f->driver_block_list = driver_block_list;
+
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		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);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_add(block_cb, 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);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+EXPORT_SYMBOL(flow_block_cb_setup_simple);
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 99673f6b07f6..9bcb598fc840 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -942,23 +942,42 @@ static int dsa_slave_setup_tc_block_cb_eg(enum tc_setup_type type,
 	return dsa_slave_setup_tc_block_cb(type, type_data, cb_priv, false);
 }
 
+static LIST_HEAD(dsa_slave_block_cb_list);
+
 static int dsa_slave_setup_tc_block(struct net_device *dev,
-				    struct tc_block_offload *f)
+				    struct flow_block_offload *f)
 {
+	struct flow_block_cb *block_cb;
 	tc_setup_cb_t *cb;
 
-	if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		cb = dsa_slave_setup_tc_block_cb_ig;
-	else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+	else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
 		cb = dsa_slave_setup_tc_block_cb_eg;
 	else
 		return -EOPNOTSUPP;
 
+	f->driver_block_list = &dsa_slave_block_cb_list;
+
 	switch (f->command) {
-	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, cb, dev, dev, f->extack);
-	case TC_BLOCK_UNBIND:
-		tcf_block_cb_unregister(f->block, cb, dev);
+	case FLOW_BLOCK_BIND:
+		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);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_add(block_cb, f);
+		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);
+		if (!block_cb)
+			return -ENOENT;
+
+		flow_block_cb_remove(block_cb, f);
+		list_del(&block_cb->driver_list);
 		return 0;
 	default:
 		return -EOPNOTSUPP;
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index deada20975ff..9270a7fae484 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -78,7 +78,7 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \
 		  nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \
 		  nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \
 		  nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o \
-		  nft_chain_route.o
+		  nft_chain_route.o nf_tables_offload.o
 
 nf_tables_set-objs := nf_tables_set_core.o \
 		      nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index d22d00ca78c1..ed17a7c29b86 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -18,6 +18,7 @@
 #include <net/netfilter/nf_flow_table.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_offload.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
@@ -97,6 +98,7 @@ static void nft_ctx_init(struct nft_ctx *ctx,
 	ctx->nla   	= nla;
 	ctx->portid	= NETLINK_CB(skb).portid;
 	ctx->report	= nlmsg_report(nlh);
+	ctx->flags	= nlh->nlmsg_flags;
 	ctx->seq	= nlh->nlmsg_seq;
 }
 
@@ -1169,6 +1171,7 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = {
 	[NFTA_CHAIN_POLICY]	= { .type = NLA_U32 },
 	[NFTA_CHAIN_TYPE]	= { .type = NLA_STRING },
 	[NFTA_CHAIN_COUNTERS]	= { .type = NLA_NESTED },
+	[NFTA_CHAIN_FLAGS]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy nft_hook_policy[NFTA_HOOK_MAX + 1] = {
@@ -1603,7 +1606,7 @@ static struct nft_rule **nf_tables_chain_alloc_rules(const struct nft_chain *cha
 }
 
 static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
-			      u8 policy)
+			      u8 policy, u32 flags)
 {
 	const struct nlattr * const *nla = ctx->nla;
 	struct nft_table *table = ctx->table;
@@ -1657,8 +1660,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		ops->hook	= hook.type->hooks[ops->hooknum];
 		ops->dev	= hook.dev;
 
-		chain->flags |= NFT_BASE_CHAIN;
+		chain->flags |= NFT_BASE_CHAIN | flags;
 		basechain->policy = NF_ACCEPT;
+		INIT_LIST_HEAD(&basechain->cb_list);
 	} else {
 		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 		if (chain == NULL)
@@ -1718,7 +1722,8 @@ err1:
 	return err;
 }
 
-static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy)
+static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
+			      u32 flags)
 {
 	const struct nlattr * const *nla = ctx->nla;
 	struct nft_table *table = ctx->table;
@@ -1730,6 +1735,9 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy)
 	struct nft_trans *trans;
 	int err;
 
+	if (chain->flags ^ flags)
+		return -EOPNOTSUPP;
+
 	if (nla[NFTA_CHAIN_HOOK]) {
 		if (!nft_is_base_chain(chain))
 			return -EBUSY;
@@ -1835,6 +1843,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 	u8 policy = NF_ACCEPT;
 	struct nft_ctx ctx;
 	u64 handle = 0;
+	u32 flags = 0;
 
 	lockdep_assert_held(&net->nft.commit_mutex);
 
@@ -1889,6 +1898,9 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 		}
 	}
 
+	if (nla[NFTA_CHAIN_FLAGS])
+		flags = ntohl(nla_get_be32(nla[NFTA_CHAIN_FLAGS]));
+
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla);
 
 	if (chain != NULL) {
@@ -1899,10 +1911,10 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		return nf_tables_updchain(&ctx, genmask, policy);
+		return nf_tables_updchain(&ctx, genmask, policy, flags);
 	}
 
-	return nf_tables_addchain(&ctx, family, genmask, policy);
+	return nf_tables_addchain(&ctx, family, genmask, policy, flags);
 }
 
 static int nf_tables_delchain(struct net *net, struct sock *nlsk,
@@ -2658,6 +2670,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	u8 genmask = nft_genmask_next(net);
 	struct nft_expr_info *info = NULL;
 	int family = nfmsg->nfgen_family;
+	struct nft_flow_rule *flow;
 	struct nft_table *table;
 	struct nft_chain *chain;
 	struct nft_rule *rule, *old_rule = NULL;
@@ -2804,7 +2817,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 
 		list_add_tail_rcu(&rule->list, &old_rule->list);
 	} else {
-		if (nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule) == NULL) {
+		trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE, rule);
+		if (!trans) {
 			err = -ENOMEM;
 			goto err2;
 		}
@@ -2827,6 +2841,14 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	if (net->nft.validate_state == NFT_VALIDATE_DO)
 		return nft_table_validate(net, table);
 
+	if (chain->flags & NFT_CHAIN_HW_OFFLOAD) {
+		flow = nft_flow_rule_create(rule);
+		if (IS_ERR(flow))
+			return PTR_ERR(flow);
+
+		nft_trans_flow_rule(trans) = flow;
+	}
+
 	return 0;
 err2:
 	nf_tables_rule_release(&ctx, rule);
@@ -6624,6 +6646,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	struct nft_trans_elem *te;
 	struct nft_chain *chain;
 	struct nft_table *table;
+	int err;
 
 	if (list_empty(&net->nft.commit_list)) {
 		mutex_unlock(&net->nft.commit_mutex);
@@ -6634,6 +6657,10 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 	if (nf_tables_validate(net) < 0)
 		return -EAGAIN;
 
+	err = nft_flow_rule_offload_commit(net);
+	if (err < 0)
+		return err;
+
 	/* 1.  Allocate space for next generation rules_gen_X[] */
 	list_for_each_entry_safe(trans, next, &net->nft.commit_list, list) {
 		int ret;
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
new file mode 100644
index 000000000000..2c3302845f67
--- /dev/null
+++ b/net/netfilter/nf_tables_offload.c
@@ -0,0 +1,267 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <net/flow_offload.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_offload.h>
+#include <net/pkt_cls.h>
+
+static struct nft_flow_rule *nft_flow_rule_alloc(int num_actions)
+{
+	struct nft_flow_rule *flow;
+
+	flow = kzalloc(sizeof(struct nft_flow_rule), GFP_KERNEL);
+	if (!flow)
+		return NULL;
+
+	flow->rule = flow_rule_alloc(num_actions);
+	if (!flow->rule) {
+		kfree(flow);
+		return NULL;
+	}
+
+	flow->rule->match.dissector	= &flow->match.dissector;
+	flow->rule->match.mask		= &flow->match.mask;
+	flow->rule->match.key		= &flow->match.key;
+
+	return flow;
+}
+
+struct nft_flow_rule *nft_flow_rule_create(const struct nft_rule *rule)
+{
+	struct nft_offload_ctx ctx = {
+		.dep	= {
+			.type	= NFT_OFFLOAD_DEP_UNSPEC,
+		},
+	};
+	struct nft_flow_rule *flow;
+	int num_actions = 0, err;
+	struct nft_expr *expr;
+
+	expr = nft_expr_first(rule);
+	while (expr->ops && expr != nft_expr_last(rule)) {
+		if (expr->ops->offload_flags & NFT_OFFLOAD_F_ACTION)
+			num_actions++;
+
+		expr = nft_expr_next(expr);
+	}
+
+	flow = nft_flow_rule_alloc(num_actions);
+	if (!flow)
+		return ERR_PTR(-ENOMEM);
+
+	expr = nft_expr_first(rule);
+	while (expr->ops && expr != nft_expr_last(rule)) {
+		if (!expr->ops->offload) {
+			err = -EOPNOTSUPP;
+			goto err_out;
+		}
+		err = expr->ops->offload(&ctx, flow, expr);
+		if (err < 0)
+			goto err_out;
+
+		expr = nft_expr_next(expr);
+	}
+	flow->proto = ctx.dep.l3num;
+
+	return flow;
+err_out:
+	nft_flow_rule_destroy(flow);
+
+	return ERR_PTR(err);
+}
+
+void nft_flow_rule_destroy(struct nft_flow_rule *flow)
+{
+	kfree(flow->rule);
+	kfree(flow);
+}
+
+void nft_offload_set_dependency(struct nft_offload_ctx *ctx,
+				enum nft_offload_dep_type type)
+{
+	ctx->dep.type = type;
+}
+
+void nft_offload_update_dependency(struct nft_offload_ctx *ctx,
+				   const void *data, u32 len)
+{
+	switch (ctx->dep.type) {
+	case NFT_OFFLOAD_DEP_NETWORK:
+		WARN_ON(len != sizeof(__u16));
+		memcpy(&ctx->dep.l3num, data, sizeof(__u16));
+		break;
+	case NFT_OFFLOAD_DEP_TRANSPORT:
+		WARN_ON(len != sizeof(__u8));
+		memcpy(&ctx->dep.protonum, data, sizeof(__u8));
+		break;
+	default:
+		break;
+	}
+	ctx->dep.type = NFT_OFFLOAD_DEP_UNSPEC;
+}
+
+static void nft_flow_offload_common_init(struct flow_cls_common_offload *common,
+					 __be16 proto,
+					struct netlink_ext_ack *extack)
+{
+	common->protocol = proto;
+	common->extack = extack;
+}
+
+static int nft_setup_cb_call(struct nft_base_chain *basechain,
+			     enum tc_setup_type type, void *type_data)
+{
+	struct flow_block_cb *block_cb;
+	int err;
+
+	list_for_each_entry(block_cb, &basechain->cb_list, list) {
+		err = block_cb->cb(type, type_data, block_cb->cb_priv);
+		if (err < 0)
+			return err;
+	}
+	return 0;
+}
+
+static int nft_flow_offload_rule(struct nft_trans *trans,
+				 enum flow_cls_command command)
+{
+	struct nft_flow_rule *flow = nft_trans_flow_rule(trans);
+	struct nft_rule *rule = nft_trans_rule(trans);
+	struct flow_cls_offload cls_flow = {};
+	struct nft_base_chain *basechain;
+	struct netlink_ext_ack extack;
+	__be16 proto = ETH_P_ALL;
+
+	if (!nft_is_base_chain(trans->ctx.chain))
+		return -EOPNOTSUPP;
+
+	basechain = nft_base_chain(trans->ctx.chain);
+
+	if (flow)
+		proto = flow->proto;
+
+	nft_flow_offload_common_init(&cls_flow.common, proto, &extack);
+	cls_flow.command = command;
+	cls_flow.cookie = (unsigned long) rule;
+	if (flow)
+		cls_flow.rule = flow->rule;
+
+	return nft_setup_cb_call(basechain, TC_SETUP_CLSFLOWER, &cls_flow);
+}
+
+static int nft_flow_offload_bind(struct flow_block_offload *bo,
+				 struct nft_base_chain *basechain)
+{
+	list_splice(&bo->cb_list, &basechain->cb_list);
+	return 0;
+}
+
+static int nft_flow_offload_unbind(struct flow_block_offload *bo,
+				   struct nft_base_chain *basechain)
+{
+	struct flow_block_cb *block_cb, *next;
+
+	list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) {
+		list_del(&block_cb->list);
+		flow_block_cb_free(block_cb);
+	}
+
+	return 0;
+}
+
+#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)
+		return -EOPNOTSUPP;
+
+	/* Only default policy to accept is supported for now. */
+	if (cmd == FLOW_BLOCK_BIND &&
+	    nft_trans_chain_policy(trans) != -1 &&
+	    nft_trans_chain_policy(trans) != NF_ACCEPT)
+		return -EOPNOTSUPP;
+
+	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, 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;
+}
+
+int nft_flow_rule_offload_commit(struct net *net)
+{
+	struct nft_trans *trans;
+	int err = 0;
+
+	list_for_each_entry(trans, &net->nft.commit_list, list) {
+		if (trans->ctx.family != NFPROTO_NETDEV)
+			continue;
+
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWCHAIN:
+			if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD))
+				continue;
+
+			err = nft_flow_offload_chain(trans, FLOW_BLOCK_BIND);
+			break;
+		case NFT_MSG_DELCHAIN:
+			if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD))
+				continue;
+
+			err = nft_flow_offload_chain(trans, FLOW_BLOCK_UNBIND);
+			break;
+		case NFT_MSG_NEWRULE:
+			if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD))
+				continue;
+
+			if (trans->ctx.flags & NLM_F_REPLACE ||
+			    !(trans->ctx.flags & NLM_F_APPEND))
+				return -EOPNOTSUPP;
+
+			err = nft_flow_offload_rule(trans, FLOW_CLS_REPLACE);
+			nft_flow_rule_destroy(nft_trans_flow_rule(trans));
+			break;
+		case NFT_MSG_DELRULE:
+			if (!(trans->ctx.chain->flags & NFT_CHAIN_HW_OFFLOAD))
+				continue;
+
+			err = nft_flow_offload_rule(trans, FLOW_CLS_DESTROY);
+			break;
+		}
+
+		if (err)
+			return err;
+	}
+
+	return err;
+}
diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c
index 411c0cf741e3..bd173b1824c6 100644
--- a/net/netfilter/nft_cmp.c
+++ b/net/netfilter/nft_cmp.c
@@ -12,6 +12,7 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tables_offload.h>
 #include <net/netfilter/nf_tables.h>
 
 struct nft_cmp_expr {
@@ -107,12 +108,44 @@ nla_put_failure:
 	return -1;
 }
 
+static int __nft_cmp_offload(struct nft_offload_ctx *ctx,
+			     struct nft_flow_rule *flow,
+			     const struct nft_cmp_expr *priv)
+{
+	struct nft_offload_reg *reg = &ctx->regs[priv->sreg];
+	u8 *mask = (u8 *)&flow->match.mask;
+	u8 *key = (u8 *)&flow->match.key;
+
+	if (priv->op != NFT_CMP_EQ)
+		return -EOPNOTSUPP;
+
+	memcpy(key + reg->offset, &priv->data, priv->len);
+	memcpy(mask + reg->offset, &reg->mask, priv->len);
+
+	flow->match.dissector.used_keys |= BIT(reg->key);
+	flow->match.dissector.offset[reg->key] = reg->base_offset;
+
+	nft_offload_update_dependency(ctx, &priv->data, priv->len);
+
+	return 0;
+}
+
+static int nft_cmp_offload(struct nft_offload_ctx *ctx,
+			   struct nft_flow_rule *flow,
+			   const struct nft_expr *expr)
+{
+	const struct nft_cmp_expr *priv = nft_expr_priv(expr);
+
+	return __nft_cmp_offload(ctx, flow, priv);
+}
+
 static const struct nft_expr_ops nft_cmp_ops = {
 	.type		= &nft_cmp_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_cmp_expr)),
 	.eval		= nft_cmp_eval,
 	.init		= nft_cmp_init,
 	.dump		= nft_cmp_dump,
+	.offload	= nft_cmp_offload,
 };
 
 static int nft_cmp_fast_init(const struct nft_ctx *ctx,
@@ -143,6 +176,25 @@ static int nft_cmp_fast_init(const struct nft_ctx *ctx,
 	return 0;
 }
 
+static int nft_cmp_fast_offload(struct nft_offload_ctx *ctx,
+				struct nft_flow_rule *flow,
+				const struct nft_expr *expr)
+{
+	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
+	struct nft_cmp_expr cmp = {
+		.data	= {
+			.data	= {
+				[0] = priv->data,
+			},
+		},
+		.sreg	= priv->sreg,
+		.len	= priv->len / BITS_PER_BYTE,
+		.op	= NFT_CMP_EQ,
+	};
+
+	return __nft_cmp_offload(ctx, flow, &cmp);
+}
+
 static int nft_cmp_fast_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_cmp_fast_expr *priv = nft_expr_priv(expr);
@@ -169,6 +221,7 @@ const struct nft_expr_ops nft_cmp_fast_ops = {
 	.eval		= NULL,	/* inlined */
 	.init		= nft_cmp_fast_init,
 	.dump		= nft_cmp_fast_dump,
+	.offload	= nft_cmp_fast_offload,
 };
 
 static const struct nft_expr_ops *
diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c
index cb8547f97220..ca2ae4b95a8d 100644
--- a/net/netfilter/nft_immediate.c
+++ b/net/netfilter/nft_immediate.c
@@ -13,6 +13,7 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_offload.h>
 
 void nft_immediate_eval(const struct nft_expr *expr,
 			struct nft_regs *regs,
@@ -124,6 +125,34 @@ static int nft_immediate_validate(const struct nft_ctx *ctx,
 	return 0;
 }
 
+static int nft_immediate_offload(struct nft_offload_ctx *ctx,
+				 struct nft_flow_rule *flow,
+				 const struct nft_expr *expr)
+{
+	const struct nft_immediate_expr *priv = nft_expr_priv(expr);
+	struct flow_action_entry *entry;
+	const struct nft_data *data;
+
+	if (priv->dreg != NFT_REG_VERDICT)
+		return -EOPNOTSUPP;
+
+	entry = &flow->rule->action.entries[ctx->num_actions++];
+
+	data = &priv->data;
+	switch (data->verdict.code) {
+	case NF_ACCEPT:
+		entry->id = FLOW_ACTION_ACCEPT;
+		break;
+	case NF_DROP:
+		entry->id = FLOW_ACTION_DROP;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static const struct nft_expr_ops nft_imm_ops = {
 	.type		= &nft_imm_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_immediate_expr)),
@@ -133,6 +162,8 @@ static const struct nft_expr_ops nft_imm_ops = {
 	.deactivate	= nft_immediate_deactivate,
 	.dump		= nft_immediate_dump,
 	.validate	= nft_immediate_validate,
+	.offload	= nft_immediate_offload,
+	.offload_flags	= NFT_OFFLOAD_F_ACTION,
 };
 
 struct nft_expr_type nft_imm_type __read_mostly = {
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 417f8d32e9a3..76866f77e343 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -22,6 +22,7 @@
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nft_meta.h>
+#include <net/netfilter/nf_tables_offload.h>
 
 #include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */
 
@@ -490,6 +491,31 @@ void nft_meta_set_destroy(const struct nft_ctx *ctx,
 }
 EXPORT_SYMBOL_GPL(nft_meta_set_destroy);
 
+static int nft_meta_get_offload(struct nft_offload_ctx *ctx,
+				struct nft_flow_rule *flow,
+				const struct nft_expr *expr)
+{
+	const struct nft_meta *priv = nft_expr_priv(expr);
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	switch (priv->key) {
+	case NFT_META_PROTOCOL:
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, n_proto,
+				  sizeof(__u16), reg);
+		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_NETWORK);
+		break;
+	case NFT_META_L4PROTO:
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
+				  sizeof(__u8), reg);
+		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static const struct nft_expr_ops nft_meta_get_ops = {
 	.type		= &nft_meta_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_meta)),
@@ -497,6 +523,7 @@ static const struct nft_expr_ops nft_meta_get_ops = {
 	.init		= nft_meta_get_init,
 	.dump		= nft_meta_get_dump,
 	.validate	= nft_meta_get_validate,
+	.offload	= nft_meta_get_offload,
 };
 
 static const struct nft_expr_ops nft_meta_set_ops = {
diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c
index 1260f78a034d..22a80eb60222 100644
--- a/net/netfilter/nft_payload.c
+++ b/net/netfilter/nft_payload.c
@@ -15,10 +15,13 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables_core.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_offload.h>
 /* For layer 4 checksum field offset. */
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/icmpv6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
 
 /* add vlan header into the user buffer for if tag was removed by offloads */
 static bool
@@ -150,12 +153,195 @@ nla_put_failure:
 	return -1;
 }
 
+static int nft_payload_offload_ll(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_payload *priv)
+{
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	switch (priv->offset) {
+	case offsetof(struct ethhdr, h_source):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
+				  src, ETH_ALEN, reg);
+		break;
+	case offsetof(struct ethhdr, h_dest):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_ETH_ADDRS, eth_addrs,
+				  dst, ETH_ALEN, reg);
+		break;
+	}
+
+	return 0;
+}
+
+static int nft_payload_offload_ip(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_payload *priv)
+{
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	switch (priv->offset) {
+	case offsetof(struct iphdr, saddr):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, src,
+				  sizeof(struct in_addr), reg);
+		break;
+	case offsetof(struct iphdr, daddr):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4, dst,
+				  sizeof(struct in_addr), reg);
+		break;
+	case offsetof(struct iphdr, protocol):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
+				  sizeof(__u8), reg);
+		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int nft_payload_offload_ip6(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_payload *priv)
+{
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	switch (priv->offset) {
+	case offsetof(struct ipv6hdr, saddr):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, src,
+				  sizeof(struct in6_addr), reg);
+		break;
+	case offsetof(struct ipv6hdr, daddr):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6, dst,
+				  sizeof(struct in6_addr), reg);
+		break;
+	case offsetof(struct ipv6hdr, nexthdr):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_BASIC, basic, ip_proto,
+				  sizeof(__u8), reg);
+		nft_offload_set_dependency(ctx, NFT_OFFLOAD_DEP_TRANSPORT);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int nft_payload_offload_nh(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_payload *priv)
+{
+	int err;
+
+	switch (ctx->dep.l3num) {
+	case htons(ETH_P_IP):
+		err = nft_payload_offload_ip(ctx, flow, priv);
+		break;
+	case htons(ETH_P_IPV6):
+		err = nft_payload_offload_ip6(ctx, flow, priv);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int nft_payload_offload_tcp(struct nft_offload_ctx *ctx,
+				   struct nft_flow_rule *flow,
+				   const struct nft_payload *priv)
+{
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	switch (priv->offset) {
+	case offsetof(struct tcphdr, source):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
+				  sizeof(__be16), reg);
+		break;
+	case offsetof(struct tcphdr, dest):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
+				  sizeof(__be16), reg);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int nft_payload_offload_udp(struct nft_offload_ctx *ctx,
+				   struct nft_flow_rule *flow,
+				   const struct nft_payload *priv)
+{
+	struct nft_offload_reg *reg = &ctx->regs[priv->dreg];
+
+	switch (priv->offset) {
+	case offsetof(struct udphdr, source):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, src,
+				  sizeof(__be16), reg);
+		break;
+	case offsetof(struct udphdr, dest):
+		NFT_OFFLOAD_MATCH(FLOW_DISSECTOR_KEY_PORTS, tp, dst,
+				  sizeof(__be16), reg);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int nft_payload_offload_th(struct nft_offload_ctx *ctx,
+				  struct nft_flow_rule *flow,
+				  const struct nft_payload *priv)
+{
+	int err;
+
+	switch (ctx->dep.protonum) {
+	case IPPROTO_TCP:
+		err = nft_payload_offload_tcp(ctx, flow, priv);
+		break;
+	case IPPROTO_UDP:
+		err = nft_payload_offload_udp(ctx, flow, priv);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int nft_payload_offload(struct nft_offload_ctx *ctx,
+			       struct nft_flow_rule *flow,
+			       const struct nft_expr *expr)
+{
+	const struct nft_payload *priv = nft_expr_priv(expr);
+	int err;
+
+	switch (priv->base) {
+	case NFT_PAYLOAD_LL_HEADER:
+		err = nft_payload_offload_ll(ctx, flow, priv);
+		break;
+	case NFT_PAYLOAD_NETWORK_HEADER:
+		err = nft_payload_offload_nh(ctx, flow, priv);
+		break;
+	case NFT_PAYLOAD_TRANSPORT_HEADER:
+		err = nft_payload_offload_th(ctx, flow, priv);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+	return err;
+}
+
 static const struct nft_expr_ops nft_payload_ops = {
 	.type		= &nft_payload_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_payload)),
 	.eval		= nft_payload_eval,
 	.init		= nft_payload_init,
 	.dump		= nft_payload_dump,
+	.offload	= nft_payload_offload,
 };
 
 const struct nft_expr_ops nft_payload_fast_ops = {
@@ -164,6 +350,7 @@ const struct nft_expr_ops nft_payload_fast_ops = {
 	.eval		= nft_payload_eval,
 	.init		= nft_payload_init,
 	.dump		= nft_payload_dump,
+	.offload	= nft_payload_offload,
 };
 
 static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 4a7331ce830d..638c1bc1ea1b 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -673,21 +673,27 @@ static void tc_indr_block_cb_del(struct tc_indr_block_cb *indr_block_cb)
 	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,
-				  enum tc_block_command command)
+				  enum flow_block_command command)
 {
-	struct tc_block_offload bo = {
+	struct flow_block_offload bo = {
 		.command	= command,
-		.binder_type	= TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
-		.block		= indr_dev->block,
+		.binder_type	= FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
+		.net		= dev_net(indr_dev->dev),
+		.block_shared	= tcf_block_shared(indr_dev->block),
 	};
+	INIT_LIST_HEAD(&bo.cb_list);
 
 	if (!indr_dev->block)
 		return;
 
 	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,
@@ -706,7 +712,7 @@ int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
 	if (err)
 		goto err_dev_put;
 
-	tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_BIND);
+	tc_indr_block_ing_cmd(indr_dev, indr_block_cb, FLOW_BLOCK_BIND);
 	return 0;
 
 err_dev_put:
@@ -743,7 +749,7 @@ void __tc_indr_block_cb_unregister(struct net_device *dev,
 		return;
 
 	/* Send unbind message if required to free any block cbs. */
-	tc_indr_block_ing_cmd(indr_dev, indr_block_cb, TC_BLOCK_UNBIND);
+	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);
 }
@@ -760,27 +766,31 @@ 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 tc_block_command command,
+			       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 tc_block_offload bo = {
+	struct flow_block_offload bo = {
 		.command	= command,
 		.binder_type	= ei->binder_type,
-		.block		= block,
+		.net		= dev_net(dev),
+		.block_shared	= tcf_block_shared(block),
 		.extack		= extack,
 	};
+	INIT_LIST_HEAD(&bo.cb_list);
 
 	indr_dev = tc_indr_block_dev_lookup(dev);
 	if (!indr_dev)
 		return;
 
-	indr_dev->block = command == TC_BLOCK_BIND ? block : NULL;
+	indr_dev->block = command == FLOW_BLOCK_BIND ? block : 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);
+
+	tcf_block_setup(block, &bo);
 }
 
 static bool tcf_block_offload_in_use(struct tcf_block *block)
@@ -791,16 +801,24 @@ static bool tcf_block_offload_in_use(struct tcf_block *block)
 static int tcf_block_offload_cmd(struct tcf_block *block,
 				 struct net_device *dev,
 				 struct tcf_block_ext_info *ei,
-				 enum tc_block_command command,
+				 enum flow_block_command command,
 				 struct netlink_ext_ack *extack)
 {
-	struct tc_block_offload bo = {};
+	struct flow_block_offload bo = {};
+	int err;
 
+	bo.net = dev_net(dev);
 	bo.command = command;
 	bo.binder_type = ei->binder_type;
-	bo.block = block;
+	bo.block_shared = tcf_block_shared(block);
 	bo.extack = extack;
-	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+	INIT_LIST_HEAD(&bo.cb_list);
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+	if (err < 0)
+		return err;
+
+	return tcf_block_setup(block, &bo);
 }
 
 static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
@@ -821,20 +839,20 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
 		return -EOPNOTSUPP;
 	}
 
-	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack);
+	err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_BIND, extack);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_inc;
 	if (err)
 		return err;
 
-	tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack);
+	tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
 	return 0;
 
 no_offload_dev_inc:
 	if (tcf_block_offload_in_use(block))
 		return -EOPNOTSUPP;
 	block->nooffloaddevcnt++;
-	tc_indr_block_call(block, dev, ei, TC_BLOCK_BIND, extack);
+	tc_indr_block_call(block, dev, ei, FLOW_BLOCK_BIND, extack);
 	return 0;
 }
 
@@ -844,11 +862,11 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
 	struct net_device *dev = q->dev_queue->dev;
 	int err;
 
-	tc_indr_block_call(block, dev, ei, TC_BLOCK_UNBIND, NULL);
+	tc_indr_block_call(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
 
 	if (!dev->netdev_ops->ndo_setup_tc)
 		goto no_offload_dev_dec;
-	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL);
+	err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_dec;
 	return;
@@ -1341,17 +1359,17 @@ static void tcf_block_release(struct Qdisc *q, struct tcf_block *block,
 struct tcf_block_owner_item {
 	struct list_head list;
 	struct Qdisc *q;
-	enum tcf_block_binder_type binder_type;
+	enum flow_block_binder_type binder_type;
 };
 
 static void
 tcf_block_owner_netif_keep_dst(struct tcf_block *block,
 			       struct Qdisc *q,
-			       enum tcf_block_binder_type binder_type)
+			       enum flow_block_binder_type binder_type)
 {
 	if (block->keep_dst &&
-	    binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
-	    binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
+	    binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS &&
+	    binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
 		netif_keep_dst(qdisc_dev(q));
 }
 
@@ -1368,7 +1386,7 @@ EXPORT_SYMBOL(tcf_block_netif_keep_dst);
 
 static int tcf_block_owner_add(struct tcf_block *block,
 			       struct Qdisc *q,
-			       enum tcf_block_binder_type binder_type)
+			       enum flow_block_binder_type binder_type)
 {
 	struct tcf_block_owner_item *item;
 
@@ -1383,7 +1401,7 @@ static int tcf_block_owner_add(struct tcf_block *block,
 
 static void tcf_block_owner_del(struct tcf_block *block,
 				struct Qdisc *q,
-				enum tcf_block_binder_type binder_type)
+				enum flow_block_binder_type binder_type)
 {
 	struct tcf_block_owner_item *item;
 
@@ -1495,43 +1513,6 @@ void tcf_block_put(struct tcf_block *block)
 
 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);
-
 static int
 tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
 			    void *cb_priv, bool add, bool offload_in_use,
@@ -1573,66 +1554,76 @@ err_playback_remove:
 	return err;
 }
 
-struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
-					     tc_setup_cb_t *cb, void *cb_ident,
-					     void *cb_priv,
-					     struct netlink_ext_ack *extack)
+static int tcf_block_bind(struct tcf_block *block,
+			  struct flow_block_offload *bo)
 {
-	struct tcf_block_cb *block_cb;
-	int err;
+	struct flow_block_cb *block_cb, *next;
+	int err, i = 0;
 
-	/* Replay any already present rules */
-	err = tcf_block_playback_offloads(block, cb, cb_priv, true,
-					  tcf_block_offload_in_use(block),
-					  extack);
-	if (err)
-		return ERR_PTR(err);
+	list_for_each_entry(block_cb, &bo->cb_list, list) {
+		err = tcf_block_playback_offloads(block, block_cb->cb,
+						  block_cb->cb_priv, true,
+						  tcf_block_offload_in_use(block),
+						  bo->extack);
+		if (err)
+			goto err_unroll;
 
-	block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
-	if (!block_cb)
-		return ERR_PTR(-ENOMEM);
-	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);
+		i++;
+	}
+	list_splice(&bo->cb_list, &block->cb_list);
 
-int tcf_block_cb_register(struct tcf_block *block,
-			  tc_setup_cb_t *cb, void *cb_ident,
-			  void *cb_priv, struct netlink_ext_ack *extack)
-{
-	struct tcf_block_cb *block_cb;
+	return 0;
+
+err_unroll:
+	list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) {
+		if (i-- > 0) {
+			list_del(&block_cb->list);
+			tcf_block_playback_offloads(block, block_cb->cb,
+						    block_cb->cb_priv, false,
+						    tcf_block_offload_in_use(block),
+						    NULL);
+		}
+		flow_block_cb_free(block_cb);
+	}
 
-	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
-					   extack);
-	return PTR_ERR_OR_ZERO(block_cb);
+	return err;
 }
-EXPORT_SYMBOL(tcf_block_cb_register);
 
-void __tcf_block_cb_unregister(struct tcf_block *block,
-			       struct tcf_block_cb *block_cb)
+static void tcf_block_unbind(struct tcf_block *block,
+			     struct flow_block_offload *bo)
 {
-	tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv,
-				    false, tcf_block_offload_in_use(block),
-				    NULL);
-	list_del(&block_cb->list);
-	kfree(block_cb);
+	struct flow_block_cb *block_cb, *next;
+
+	list_for_each_entry_safe(block_cb, next, &bo->cb_list, list) {
+		tcf_block_playback_offloads(block, block_cb->cb,
+					    block_cb->cb_priv, false,
+					    tcf_block_offload_in_use(block),
+					    NULL);
+		list_del(&block_cb->list);
+		flow_block_cb_free(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)
+static int tcf_block_setup(struct tcf_block *block,
+			   struct flow_block_offload *bo)
 {
-	struct tcf_block_cb *block_cb;
+	int err;
 
-	block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
-	if (!block_cb)
-		return;
-	__tcf_block_cb_unregister(block, block_cb);
+	switch (bo->command) {
+	case FLOW_BLOCK_BIND:
+		err = tcf_block_bind(block, bo);
+		break;
+	case FLOW_BLOCK_UNBIND:
+		err = 0;
+		tcf_block_unbind(block, bo);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
 }
-EXPORT_SYMBOL(tcf_block_cb_unregister);
 
 /* Main classifier routine: scans classifier chain attached
  * to this qdisc, (optionally) tests for protocol and asks
@@ -3156,7 +3147,7 @@ EXPORT_SYMBOL(tcf_exts_dump_stats);
 int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type,
 		     void *type_data, bool err_stop)
 {
-	struct tcf_block_cb *block_cb;
+	struct flow_block_cb *block_cb;
 	int ok_count = 0;
 	int err;
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index bec37e16347f..38d6e85693fc 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -409,14 +409,14 @@ static void fl_destroy_filter_work(struct work_struct *work)
 static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f,
 				 bool rtnl_held, struct netlink_ext_ack *extack)
 {
-	struct tc_cls_flower_offload cls_flower = {};
 	struct tcf_block *block = tp->chain->block;
+	struct flow_cls_offload cls_flower = {};
 
 	if (!rtnl_held)
 		rtnl_lock();
 
 	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack);
-	cls_flower.command = TC_CLSFLOWER_DESTROY;
+	cls_flower.command = FLOW_CLS_DESTROY;
 	cls_flower.cookie = (unsigned long) f;
 
 	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
@@ -434,8 +434,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 				struct netlink_ext_ack *extack)
 {
 	struct cls_fl_head *head = fl_head_dereference(tp);
-	struct tc_cls_flower_offload cls_flower = {};
 	struct tcf_block *block = tp->chain->block;
+	struct flow_cls_offload cls_flower = {};
 	bool skip_sw = tc_skip_sw(f->flags);
 	int err = 0;
 
@@ -449,7 +449,7 @@ 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.command = FLOW_CLS_REPLACE;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.rule->match.dissector = &f->mask->dissector;
 	cls_flower.rule->match.mask = &f->mask->key;
@@ -498,14 +498,14 @@ errout:
 static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f,
 			       bool rtnl_held)
 {
-	struct tc_cls_flower_offload cls_flower = {};
 	struct tcf_block *block = tp->chain->block;
+	struct flow_cls_offload cls_flower = {};
 
 	if (!rtnl_held)
 		rtnl_lock();
 
 	tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL);
-	cls_flower.command = TC_CLSFLOWER_STATS;
+	cls_flower.command = FLOW_CLS_STATS;
 	cls_flower.cookie = (unsigned long) f;
 	cls_flower.classid = f->res.classid;
 
@@ -1803,8 +1803,8 @@ fl_get_next_hw_filter(struct tcf_proto *tp, struct cls_fl_filter *f, bool add)
 static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 			void *cb_priv, struct netlink_ext_ack *extack)
 {
-	struct tc_cls_flower_offload cls_flower = {};
 	struct tcf_block *block = tp->chain->block;
+	struct flow_cls_offload cls_flower = {};
 	struct cls_fl_filter *f = NULL;
 	int err;
 
@@ -1825,7 +1825,7 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 		tc_cls_common_offload_init(&cls_flower.common, tp, f->flags,
 					   extack);
 		cls_flower.command = add ?
-			TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
+			FLOW_CLS_REPLACE : FLOW_CLS_DESTROY;
 		cls_flower.cookie = (unsigned long)f;
 		cls_flower.rule->match.dissector = &f->mask->dissector;
 		cls_flower.rule->match.mask = &f->mask->key;
@@ -1869,7 +1869,7 @@ next_flow:
 static int fl_hw_create_tmplt(struct tcf_chain *chain,
 			      struct fl_flow_tmplt *tmplt)
 {
-	struct tc_cls_flower_offload cls_flower = {};
+	struct flow_cls_offload cls_flower = {};
 	struct tcf_block *block = chain->block;
 
 	cls_flower.rule = flow_rule_alloc(0);
@@ -1877,7 +1877,7 @@ static int fl_hw_create_tmplt(struct tcf_chain *chain,
 		return -ENOMEM;
 
 	cls_flower.common.chain_index = chain->index;
-	cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE;
+	cls_flower.command = FLOW_CLS_TMPLT_CREATE;
 	cls_flower.cookie = (unsigned long) tmplt;
 	cls_flower.rule->match.dissector = &tmplt->dissector;
 	cls_flower.rule->match.mask = &tmplt->mask;
@@ -1895,11 +1895,11 @@ static int fl_hw_create_tmplt(struct tcf_chain *chain,
 static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
 				struct fl_flow_tmplt *tmplt)
 {
-	struct tc_cls_flower_offload cls_flower = {};
+	struct flow_cls_offload cls_flower = {};
 	struct tcf_block *block = chain->block;
 
 	cls_flower.common.chain_index = chain->index;
-	cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY;
+	cls_flower.command = FLOW_CLS_TMPLT_DESTROY;
 	cls_flower.cookie = (unsigned long) tmplt;
 
 	tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false);
diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c
index 599730f804d7..bf56aa519797 100644
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -83,7 +83,7 @@ static int ingress_init(struct Qdisc *sch, struct nlattr *opt,
 
 	mini_qdisc_pair_init(&q->miniqp, sch, &dev->miniq_ingress);
 
-	q->block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	q->block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->block_info.chain_head_change = clsact_chain_head_change;
 	q->block_info.chain_head_change_priv = &q->miniqp;
 
@@ -217,7 +217,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 
 	mini_qdisc_pair_init(&q->miniqp_ingress, sch, &dev->miniq_ingress);
 
-	q->ingress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
+	q->ingress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS;
 	q->ingress_block_info.chain_head_change = clsact_chain_head_change;
 	q->ingress_block_info.chain_head_change_priv = &q->miniqp_ingress;
 
@@ -228,7 +228,7 @@ static int clsact_init(struct Qdisc *sch, struct nlattr *opt,
 
 	mini_qdisc_pair_init(&q->miniqp_egress, sch, &dev->miniq_egress);
 
-	q->egress_block_info.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
+	q->egress_block_info.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS;
 	q->egress_block_info.chain_head_change = clsact_chain_head_change;
 	q->egress_block_info.chain_head_change_priv = &q->miniqp_egress;