net/mlx5: Refactor multi chains and prios support

Decouple the chains infrastructure from eswitch and make
it generic to support other steering namespaces.

The change defines an agnostic data structure to keep
all the relevant information for maintaining flow table
chaining in any steering namespace. Each namespace that
requires table chaining will be required to allocate
such data structure.

The chains creation code will receive the steering namespace
and flow table parameters from the caller so it will operate
agnosticly when creating the required resources to
maintain the table chaining function while Parts of the code
that are relevant to eswitch specific functionality are moved
to eswitch files.
Signed-off-by: Ariel Levkovich <lariel@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

drivers/net/ethernet/mellanox/mlx5/core/Makefile

@@ -37,7 +37,7 @@ mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
 mlx5_core-$(CONFIG_MLX5_ESWITCH)     += lag_mp.o lib/geneve.o lib/port_tun.o \
 					en_rep.o en/rep/bond.o en/mod_hdr.o
 mlx5_core-$(CONFIG_MLX5_CLS_ACT)     += en_tc.o en/rep/tc.o en/rep/neigh.o \
-					en/mapping.o esw/chains.o en/tc_tun.o \
+					en/mapping.o lib/fs_chains.o en/tc_tun.o \
 					en/tc_tun_vxlan.o en/tc_tun_gre.o en/tc_tun_geneve.o \
 					en/tc_tun_mplsoudp.o diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o

drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c

@@ -12,7 +12,7 @@
 #include "neigh.h"
 #include "en_rep.h"
 #include "eswitch.h"
-#include "esw/chains.h"
+#include "lib/fs_chains.h"
 #include "en/tc_ct.h"
 #include "en/mapping.h"
 #include "en/tc_tun.h"
@@ -191,7 +191,7 @@ static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
 	case TC_SETUP_CLSFLOWER:
 		memcpy(&tmp, f, sizeof(*f));
 
-		if (!mlx5_esw_chains_prios_supported(esw))
+		if (!mlx5_chains_prios_supported(esw_chains(esw)))
 			return -EOPNOTSUPP;
 
 		/* Re-use tc offload path by moving the ft flow to the
@@ -203,12 +203,12 @@ static int mlx5e_rep_setup_ft_cb(enum tc_setup_type type, void *type_data,
 		 *
 		 * We only support chain 0 of FT offload.
 		 */
-		if (tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw))
+		if (tmp.common.prio >= mlx5_chains_get_prio_range(esw_chains(esw)))
 			return -EOPNOTSUPP;
 		if (tmp.common.chain_index != 0)
 			return -EOPNOTSUPP;
 
-		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
+		tmp.common.chain_index = mlx5_chains_get_nf_ft_chain(esw_chains(esw));
 		tmp.common.prio++;
 		err = mlx5e_rep_setup_tc_cls_flower(priv, &tmp, flags);
 		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
@@ -378,12 +378,12 @@ static int mlx5e_rep_indr_setup_ft_cb(enum tc_setup_type type,
 		 *
 		 * We only support chain 0 of FT offload.
 		 */
-		if (!mlx5_esw_chains_prios_supported(esw) ||
-		    tmp.common.prio >= mlx5_esw_chains_get_prio_range(esw) ||
+		if (!mlx5_chains_prios_supported(esw_chains(esw)) ||
+		    tmp.common.prio >= mlx5_chains_get_prio_range(esw_chains(esw)) ||
 		    tmp.common.chain_index)
 			return -EOPNOTSUPP;
 
-		tmp.common.chain_index = mlx5_esw_chains_get_ft_chain(esw);
+		tmp.common.chain_index = mlx5_chains_get_nf_ft_chain(esw_chains(esw));
 		tmp.common.prio++;
 		err = mlx5e_rep_indr_offload(priv->netdev, &tmp, priv, flags);
 		memcpy(&f->stats, &tmp.stats, sizeof(f->stats));
@@ -626,7 +626,7 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	priv = netdev_priv(skb->dev);
 	esw = priv->mdev->priv.eswitch;
 
-	err = mlx5_eswitch_get_chain_for_tag(esw, reg_c0, &chain);
+	err = mlx5_get_chain_for_tag(esw_chains(esw), reg_c0, &chain);
 	if (err) {
 		netdev_dbg(priv->netdev,
 			   "Couldn't find chain for chain tag: %d, err: %d\n",

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

@@ -14,7 +14,7 @@
 #include <linux/workqueue.h>
 #include <linux/xarray.h>
 
-#include "esw/chains.h"
+#include "lib/fs_chains.h"
 #include "en/tc_ct.h"
 #include "en/mod_hdr.h"
 #include "en/mapping.h"
@@ -1485,8 +1485,8 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	 * don't go though all prios of this chain as normal tc rules
 	 * miss.
 	 */
-	err = mlx5_esw_chains_get_chain_mapping(esw, attr->chain,
-						&chain_mapping);
+	err = mlx5_chains_get_chain_mapping(esw_chains(esw), attr->chain,
+					    &chain_mapping);
 	if (err) {
 		ct_dbg("Failed to get chain register mapping for chain");
 		goto err_get_chain;
@@ -1582,7 +1582,7 @@ __mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 	mlx5_modify_header_dealloc(priv->mdev, pre_ct_attr->modify_hdr);
 err_mapping:
 	dealloc_mod_hdr_actions(&pre_mod_acts);
-	mlx5_esw_chains_put_chain_mapping(esw, ct_flow->chain_mapping);
+	mlx5_chains_put_chain_mapping(esw_chains(esw), ct_flow->chain_mapping);
 err_get_chain:
 	idr_remove(&ct_priv->fte_ids, fte_id);
 err_idr:
@@ -1694,7 +1694,7 @@ __mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *ct_priv,
 	if (ct_flow->post_ct_rule) {
 		mlx5_eswitch_del_offloaded_rule(esw, ct_flow->post_ct_rule,
 						&ct_flow->post_ct_attr);
-		mlx5_esw_chains_put_chain_mapping(esw, ct_flow->chain_mapping);
+		mlx5_chains_put_chain_mapping(esw_chains(esw), ct_flow->chain_mapping);
 		idr_remove(&ct_priv->fte_ids, ct_flow->fte_id);
 		mlx5_tc_ct_del_ft_cb(ct_priv, ct_flow->ft);
 	}
@@ -1817,14 +1817,14 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
 
 	ct_priv->esw = esw;
 	ct_priv->netdev = rpriv->netdev;
-	ct_priv->ct = mlx5_esw_chains_create_global_table(esw);
+	ct_priv->ct = mlx5_chains_create_global_table(esw_chains(esw));
 	if (IS_ERR(ct_priv->ct)) {
 		err = PTR_ERR(ct_priv->ct);
 		mlx5_tc_ct_init_err(rpriv, "failed to create ct table", err);
 		goto err_ct_tbl;
 	}
 
-	ct_priv->ct_nat = mlx5_esw_chains_create_global_table(esw);
+	ct_priv->ct_nat = mlx5_chains_create_global_table(esw_chains(esw));
 	if (IS_ERR(ct_priv->ct_nat)) {
 		err = PTR_ERR(ct_priv->ct_nat);
 		mlx5_tc_ct_init_err(rpriv, "failed to create ct nat table",
@@ -1832,7 +1832,7 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
 		goto err_ct_nat_tbl;
 	}
 
-	ct_priv->post_ct = mlx5_esw_chains_create_global_table(esw);
+	ct_priv->post_ct = mlx5_chains_create_global_table(esw_chains(esw));
 	if (IS_ERR(ct_priv->post_ct)) {
 		err = PTR_ERR(ct_priv->post_ct);
 		mlx5_tc_ct_init_err(rpriv, "failed to create post ct table",
@@ -1852,9 +1852,9 @@ mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
 	return 0;
 
 err_post_ct_tbl:
-	mlx5_esw_chains_destroy_global_table(esw, ct_priv->ct_nat);
+	mlx5_chains_destroy_global_table(esw_chains(esw), ct_priv->ct_nat);
 err_ct_nat_tbl:
-	mlx5_esw_chains_destroy_global_table(esw, ct_priv->ct);
+	mlx5_chains_destroy_global_table(esw_chains(esw), ct_priv->ct);
 err_ct_tbl:
 	mapping_destroy(ct_priv->labels_mapping);
 err_mapping_labels:
@@ -1871,13 +1871,18 @@ void
 mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
 {
 	struct mlx5_tc_ct_priv *ct_priv = uplink_priv->ct_priv;
+	struct mlx5_fs_chains *chains;
+	struct mlx5_eswitch *esw;
 
 	if (!ct_priv)
 		return;
 
-	mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->post_ct);
-	mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->ct_nat);
-	mlx5_esw_chains_destroy_global_table(ct_priv->esw, ct_priv->ct);
+	esw = ct_priv->esw;
+	chains = esw_chains(esw);
+
+	mlx5_chains_destroy_global_table(chains, ct_priv->post_ct);
+	mlx5_chains_destroy_global_table(chains, ct_priv->ct_nat);
+	mlx5_chains_destroy_global_table(chains, ct_priv->ct);
 	mapping_destroy(ct_priv->zone_mapping);
 	mapping_destroy(ct_priv->labels_mapping);
 

drivers/net/ethernet/mellanox/mlx5/core/en_rep.c

@@ -39,7 +39,6 @@
 #include <net/ipv6_stubs.h>
 
 #include "eswitch.h"
-#include "esw/chains.h"
 #include "en.h"
 #include "en_rep.h"
 #include "en/txrx.h"

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -57,7 +57,6 @@
 #include "en/rep/neigh.h"
 #include "en_tc.h"
 #include "eswitch.h"
-#include "esw/chains.h"
 #include "fs_core.h"
 #include "en/port.h"
 #include "en/tc_tun.h"
@@ -66,6 +65,7 @@
 #include "en/mod_hdr.h"
 #include "lib/devcom.h"
 #include "lib/geneve.h"
+#include "lib/fs_chains.h"
 #include "diag/en_tc_tracepoint.h"
 
 #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_add_copy_action_in_auto)
@@ -1180,7 +1180,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	int err = 0;
 	int out_index;
 
-	if (!mlx5_esw_chains_prios_supported(esw) && attr->prio != 1) {
+	if (!mlx5_chains_prios_supported(esw_chains(esw)) && attr->prio != 1) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "E-switch priorities unsupported, upgrade FW");
 		return -EOPNOTSUPP;
@@ -1191,14 +1191,14 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv,
 	 * FDB_FT_CHAIN which is outside tc range.
 	 * See mlx5e_rep_setup_ft_cb().
 	 */
-	max_chain = mlx5_esw_chains_get_chain_range(esw);
+	max_chain = mlx5_chains_get_chain_range(esw_chains(esw));
 	if (!mlx5e_is_ft_flow(flow) && attr->chain > max_chain) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Requested chain is out of supported range");
 		return -EOPNOTSUPP;
 	}
 
-	max_prio = mlx5_esw_chains_get_prio_range(esw);
+	max_prio = mlx5_chains_get_prio_range(esw_chains(esw));
 	if (attr->prio > max_prio) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Requested priority is out of supported range");
@@ -3845,7 +3845,7 @@ static int mlx5_validate_goto_chain(struct mlx5_eswitch *esw,
 				    u32 actions,
 				    struct netlink_ext_ack *extack)
 {
-	u32 max_chain = mlx5_esw_chains_get_chain_range(esw);
+	u32 max_chain = mlx5_chains_get_chain_range(esw_chains(esw));
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	bool ft_flow = mlx5e_is_ft_flow(flow);
 	u32 dest_chain = act->chain_index;
@@ -3855,7 +3855,7 @@ static int mlx5_validate_goto_chain(struct mlx5_eswitch *esw,
 		return -EOPNOTSUPP;
 	}
 
-	if (!mlx5_esw_chains_backwards_supported(esw) &&
+	if (!mlx5_chains_backwards_supported(esw_chains(esw)) &&
 	    dest_chain <= attr->chain) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Goto lower numbered chain isn't supported");

drivers/net/ethernet/mellanox/mlx5/core/esw/chains.h

-/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
-/* Copyright (c) 2020 Mellanox Technologies. */
-
-#ifndef __ML5_ESW_CHAINS_H__
-#define __ML5_ESW_CHAINS_H__
-
-#include "eswitch.h"
-
-#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
-
-bool
-mlx5_esw_chains_prios_supported(struct mlx5_eswitch *esw);
-bool
-mlx5_esw_chains_backwards_supported(struct mlx5_eswitch *esw);
-u32
-mlx5_esw_chains_get_prio_range(struct mlx5_eswitch *esw);
-u32
-mlx5_esw_chains_get_chain_range(struct mlx5_eswitch *esw);
-u32
-mlx5_esw_chains_get_ft_chain(struct mlx5_eswitch *esw);
-
-struct mlx5_flow_table *
-mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level);
-void
-mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level);
-
-struct mlx5_flow_table *
-mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw);
-
-struct mlx5_flow_table *
-mlx5_esw_chains_create_global_table(struct mlx5_eswitch *esw);
-void
-mlx5_esw_chains_destroy_global_table(struct mlx5_eswitch *esw,
-				     struct mlx5_flow_table *ft);
-
-int
-mlx5_esw_chains_get_chain_mapping(struct mlx5_eswitch *esw, u32 chain,
-				  u32 *chain_mapping);
-int
-mlx5_esw_chains_put_chain_mapping(struct mlx5_eswitch *esw,
-				  u32 chain_mapping);
-
-int mlx5_esw_chains_create(struct mlx5_eswitch *esw);
-void mlx5_esw_chains_destroy(struct mlx5_eswitch *esw);
-
-int
-mlx5_eswitch_get_chain_for_tag(struct mlx5_eswitch *esw, u32 tag, u32 *chain);
-
-#else /* CONFIG_MLX5_CLS_ACT */
-
-static inline struct mlx5_flow_table *
-mlx5_esw_chains_get_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level) { return ERR_PTR(-EOPNOTSUPP); }
-static inline void
-mlx5_esw_chains_put_table(struct mlx5_eswitch *esw, u32 chain, u32 prio,
-			  u32 level) {}
-
-static inline struct mlx5_flow_table *
-mlx5_esw_chains_get_tc_end_ft(struct mlx5_eswitch *esw) { return ERR_PTR(-EOPNOTSUPP); }
-
-static inline int mlx5_esw_chains_create(struct mlx5_eswitch *esw) { return 0; }
-static inline void mlx5_esw_chains_destroy(struct mlx5_eswitch *esw) {}
-
-#endif /* CONFIG_MLX5_CLS_ACT */
-
-#endif /* __ML5_ESW_CHAINS_H__ */

drivers/net/ethernet/mellanox/mlx5/core/eswitch.h

@@ -42,6 +42,7 @@
 #include <linux/mlx5/vport.h>
 #include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
+#include "lib/fs_chains.h"
 #include "en/tc_ct.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
@@ -62,6 +63,9 @@
 #define mlx5_esw_has_fwd_fdb(dev) \
 	MLX5_CAP_ESW_FLOWTABLE(dev, fdb_multi_path_to_table)
 
+#define esw_chains(esw) \
+	((esw)->fdb_table.offloads.esw_chains_priv)
+
 struct vport_ingress {
 	struct mlx5_flow_table *acl;
 	struct mlx5_flow_handle *allow_rule;
@@ -154,12 +158,6 @@ struct mlx5_vport {
 	enum mlx5_eswitch_vport_event enabled_events;
 };
 
-enum offloads_fdb_flags {
-	ESW_FDB_CHAINS_AND_PRIOS_SUPPORTED = BIT(0),
-};
-
-struct mlx5_esw_chains_priv;
-
 struct mlx5_eswitch_fdb {
 	union {
 		struct legacy_fdb {
@@ -183,7 +181,7 @@ struct mlx5_eswitch_fdb {
 			struct mlx5_flow_handle *miss_rule_multi;
 			int vlan_push_pop_refcount;
 
-			struct mlx5_esw_chains_priv *esw_chains_priv;
+			struct mlx5_fs_chains *esw_chains_priv;
 			struct {
 				DECLARE_HASHTABLE(table, 8);
 				/* Protects vports.table */

drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c

@@ -39,12 +39,12 @@
 #include "mlx5_core.h"
 #include "eswitch.h"
 #include "esw/acl/ofld.h"
-#include "esw/chains.h"
 #include "rdma.h"
 #include "en.h"
 #include "fs_core.h"
 #include "lib/devcom.h"
 #include "lib/eq.h"
+#include "lib/fs_chains.h"
 
 /* There are two match-all miss flows, one for unicast dst mac and
  * one for multicast.
@@ -294,6 +294,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 {
 	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
 	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
+	struct mlx5_fs_chains *chains = esw_chains(esw);
 	bool split = !!(attr->split_count);
 	struct mlx5_flow_handle *rule;
 	struct mlx5_flow_table *fdb;
@@ -329,12 +330,12 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		} else if (attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) {
 			flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
 			dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-			dest[i].ft = mlx5_esw_chains_get_tc_end_ft(esw);
+			dest[i].ft = mlx5_chains_get_tc_end_ft(chains);
 			i++;
 		} else if (attr->dest_chain) {
 			flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
-			ft = mlx5_esw_chains_get_table(esw, attr->dest_chain,
-						       1, 0);
+			ft = mlx5_chains_get_table(chains, attr->dest_chain,
+						   1, 0);
 			if (IS_ERR(ft)) {
 				rule = ERR_CAST(ft);
 				goto err_create_goto_table;
@@ -385,8 +386,8 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		fdb = esw_vport_tbl_get(esw, attr);
 	} else {
 		if (attr->chain || attr->prio)
-			fdb = mlx5_esw_chains_get_table(esw, attr->chain,
-							attr->prio, 0);
+			fdb = mlx5_chains_get_table(chains, attr->chain,
+						    attr->prio, 0);
 		else
 			fdb = attr->fdb;
 
@@ -416,10 +417,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 	if (split)
 		esw_vport_tbl_put(esw, attr);
 	else if (attr->chain || attr->prio)
-		mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
+		mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 err_esw_get:
 	if (!(attr->flags & MLX5_ESW_ATTR_FLAG_SLOW_PATH) && attr->dest_chain)
-		mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0);
+		mlx5_chains_put_table(chains, attr->dest_chain, 1, 0);
 err_create_goto_table:
 	return rule;
 }
@@ -431,12 +432,13 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 {
 	struct mlx5_flow_destination dest[MLX5_MAX_FLOW_FWD_VPORTS + 1] = {};
 	struct mlx5_flow_act flow_act = { .flags = FLOW_ACT_NO_APPEND, };
+	struct mlx5_fs_chains *chains = esw_chains(esw);
 	struct mlx5_flow_table *fast_fdb;
 	struct mlx5_flow_table *fwd_fdb;
 	struct mlx5_flow_handle *rule;
 	int i;
 
-	fast_fdb = mlx5_esw_chains_get_table(esw, attr->chain, attr->prio, 0);
+	fast_fdb = mlx5_chains_get_table(chains, attr->chain, attr->prio, 0);
 	if (IS_ERR(fast_fdb)) {
 		rule = ERR_CAST(fast_fdb);
 		goto err_get_fast;
@@ -483,7 +485,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw,
 add_err:
 	esw_vport_tbl_put(esw, attr);
 err_get_fwd:
-	mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
+	mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 err_get_fast:
 	return rule;
 }
@@ -494,6 +496,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 			struct mlx5_esw_flow_attr *attr,
 			bool fwd_rule)
 {
+	struct mlx5_fs_chains *chains = esw_chains(esw);
 	bool split = (attr->split_count > 0);
 	int i;
 
@@ -511,15 +514,14 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw,
 
 	if (fwd_rule)  {
 		esw_vport_tbl_put(esw, attr);
-		mlx5_esw_chains_put_table(esw, attr->chain, attr->prio, 0);
+		mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 	} else {
 		if (split)
 			esw_vport_tbl_put(esw, attr);
 		else if (attr->chain || attr->prio)
-			mlx5_esw_chains_put_table(esw, attr->chain, attr->prio,
-						  0);
+			mlx5_chains_put_table(chains, attr->chain, attr->prio, 0);
 		if (attr->dest_chain)
-			mlx5_esw_chains_put_table(esw, attr->dest_chain, 1, 0);
+			mlx5_chains_put_table(chains, attr->dest_chain, 1, 0);
 	}
 }
 
@@ -1137,6 +1139,126 @@ static void esw_set_flow_group_source_port(struct mlx5_eswitch *esw,
 	}
 }
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+#define fdb_modify_header_fwd_to_table_supported(esw) \
+	(MLX5_CAP_ESW_FLOWTABLE((esw)->dev, fdb_modify_header_fwd_to_table))
+static void esw_init_chains_offload_flags(struct mlx5_eswitch *esw, u32 *flags)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+
+	if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev, ignore_flow_level))
+		*flags |= MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED;
+
+	if (!MLX5_CAP_ESW_FLOWTABLE(dev, multi_fdb_encap) &&
+	    esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE) {
+		*flags &= ~MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+		esw_warn(dev, "Tc chains and priorities offload aren't supported, update firmware if needed\n");
+	} else if (!mlx5_eswitch_reg_c1_loopback_enabled(esw)) {
+		*flags &= ~MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+		esw_warn(dev, "Tc chains and priorities offload aren't supported\n");
+	} else if (!fdb_modify_header_fwd_to_table_supported(esw)) {
+		/* Disabled when ttl workaround is needed, e.g
+		 * when ESWITCH_IPV4_TTL_MODIFY_ENABLE = true in mlxconfig
+		 */
+		esw_warn(dev,
+			 "Tc chains and priorities offload aren't supported, check firmware version, or mlxconfig settings\n");
+		*flags &= ~MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+	} else {
+		*flags |= MLX5_CHAINS_AND_PRIOS_SUPPORTED;
+		esw_info(dev, "Supported tc chains and prios offload\n");
+	}
+
+	if (esw->offloads.encap != DEVLINK_ESWITCH_ENCAP_MODE_NONE)
+		*flags |= MLX5_CHAINS_FT_TUNNEL_SUPPORTED;
+}
+
+static int
+esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb)
+{
+	struct mlx5_core_dev *dev = esw->dev;
+	struct mlx5_flow_table *nf_ft, *ft;
+	struct mlx5_chains_attr attr = {};
+	struct mlx5_fs_chains *chains;
+	u32 fdb_max;
+	int err;
+
+	fdb_max = 1 << MLX5_CAP_ESW_FLOWTABLE_FDB(dev, log_max_ft_size);
+
+	esw_init_chains_offload_flags(esw, &attr.flags);
+	attr.ns = MLX5_FLOW_NAMESPACE_FDB;
+	attr.max_ft_sz = fdb_max;
+	attr.max_grp_num = esw->params.large_group_num;
+	attr.default_ft = miss_fdb;
+	attr.max_restore_tag = esw_get_max_restore_tag(esw);
+
+	chains = mlx5_chains_create(dev, &attr);
+	if (IS_ERR(chains)) {
+		err = PTR_ERR(chains);
+		esw_warn(dev, "Failed to create fdb chains err(%d)\n", err);
+		return err;
+	}
+
+	esw->fdb_table.offloads.esw_chains_priv = chains;
+
+	/* Create tc_end_ft which is the always created ft chain */
+	nf_ft = mlx5_chains_get_table(chains, mlx5_chains_get_nf_ft_chain(chains),
+				      1, 0);
+	if (IS_ERR(nf_ft)) {
+		err = PTR_ERR(nf_ft);
+		goto nf_ft_err;
+	}
+
+	/* Always open the root for fast path */
+	ft = mlx5_chains_get_table(chains, 0, 1, 0);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		goto level_0_err;
+	}
+
+	/* Open level 1 for split fdb rules now if prios isn't supported  */
+	if (!mlx5_chains_prios_supported(chains)) {
+		err = mlx5_esw_vport_tbl_get(esw);
+		if (err)
+			goto level_1_err;
+	}
+
+	mlx5_chains_set_end_ft(chains, nf_ft);
+
+	return 0;
+
+level_1_err:
+	mlx5_chains_put_table(chains, 0, 1, 0);
+level_0_err:
+	mlx5_chains_put_table(chains, mlx5_chains_get_nf_ft_chain(chains), 1, 0);
+nf_ft_err:
+	mlx5_chains_destroy(chains);
+	esw->fdb_table.offloads.esw_chains_priv = NULL;
+
+	return err;
+}
+
+static void
+esw_chains_destroy(struct mlx5_eswitch *esw, struct mlx5_fs_chains *chains)
+{
+	if (!mlx5_chains_prios_supported(chains))
+		mlx5_esw_vport_tbl_put(esw);
+	mlx5_chains_put_table(chains, 0, 1, 0);
+	mlx5_chains_put_table(chains, mlx5_chains_get_nf_ft_chain(chains), 1, 0);
+	mlx5_chains_destroy(chains);
+}
+
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static int
+esw_chains_create(struct mlx5_eswitch *esw, struct mlx5_flow_table *miss_fdb)
+{ return 0; }
+
+static void
+esw_chains_destroy(struct mlx5_eswitch *esw, struct mlx5_fs_chains *chains)
+{}
+
+#endif
+
 static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
@@ -1192,9 +1314,9 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 	}
 	esw->fdb_table.offloads.slow_fdb = fdb;
 
-	err = mlx5_esw_chains_create(esw);
+	err = esw_chains_create(esw, fdb);
 	if (err) {
-		esw_warn(dev, "Failed to create fdb chains err(%d)\n", err);
+		esw_warn(dev, "Failed to open fdb chains err(%d)\n", err);
 		goto fdb_chains_err;
 	}
 
@@ -1288,7 +1410,7 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw)
 peer_miss_err:
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.send_to_vport_grp);
 send_vport_err:
-	mlx5_esw_chains_destroy(esw);
+	esw_chains_destroy(esw, esw_chains(esw));
 fdb_chains_err:
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 slow_fdb_err:
@@ -1312,7 +1434,8 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 		mlx5_destroy_flow_group(esw->fdb_table.offloads.peer_miss_grp);
 	mlx5_destroy_flow_group(esw->fdb_table.offloads.miss_grp);
 
-	mlx5_esw_chains_destroy(esw);
+	esw_chains_destroy(esw, esw_chains(esw));
+
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 	/* Holds true only as long as DMFS is the default */
 	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,

drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.h

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2020 Mellanox Technologies. */
+
+#ifndef __ML5_ESW_CHAINS_H__
+#define __ML5_ESW_CHAINS_H__
+
+#include <linux/mlx5/fs.h>
+
+struct mlx5_fs_chains;
+
+enum mlx5_chains_flags {
+	MLX5_CHAINS_AND_PRIOS_SUPPORTED = BIT(0),
+	MLX5_CHAINS_IGNORE_FLOW_LEVEL_SUPPORTED = BIT(1),
+	MLX5_CHAINS_FT_TUNNEL_SUPPORTED = BIT(2),
+};
+
+struct mlx5_chains_attr {
+	enum mlx5_flow_namespace_type ns;
+	u32 flags;
+	u32 max_ft_sz;
+	u32 max_grp_num;
+	struct mlx5_flow_table *default_ft;
+	u32 max_restore_tag;
+};
+
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
+bool
+mlx5_chains_prios_supported(struct mlx5_fs_chains *chains);
+bool
+mlx5_chains_backwards_supported(struct mlx5_fs_chains *chains);
+u32
+mlx5_chains_get_prio_range(struct mlx5_fs_chains *chains);
+u32
+mlx5_chains_get_chain_range(struct mlx5_fs_chains *chains);
+u32
+mlx5_chains_get_nf_ft_chain(struct mlx5_fs_chains *chains);
+
+struct mlx5_flow_table *
+mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level);
+void
+mlx5_chains_put_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level);
+
+struct mlx5_flow_table *
+mlx5_chains_get_tc_end_ft(struct mlx5_fs_chains *chains);
+
+struct mlx5_flow_table *
+mlx5_chains_create_global_table(struct mlx5_fs_chains *chains);
+void
+mlx5_chains_destroy_global_table(struct mlx5_fs_chains *chains,
+				 struct mlx5_flow_table *ft);
+
+int
+mlx5_chains_get_chain_mapping(struct mlx5_fs_chains *chains, u32 chain,
+			      u32 *chain_mapping);
+int
+mlx5_chains_put_chain_mapping(struct mlx5_fs_chains *chains,
+			      u32 chain_mapping);
+
+struct mlx5_fs_chains *
+mlx5_chains_create(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr);
+void mlx5_chains_destroy(struct mlx5_fs_chains *chains);
+
+int
+mlx5_get_chain_for_tag(struct mlx5_fs_chains *chains, u32 tag, u32 *chain);
+
+void
+mlx5_chains_set_end_ft(struct mlx5_fs_chains *chains,
+		       struct mlx5_flow_table *ft);
+
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static inline struct mlx5_flow_table *
+mlx5_chains_get_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level) { return ERR_PTR(-EOPNOTSUPP); }
+static inline void
+mlx5_chains_put_table(struct mlx5_fs_chains *chains, u32 chain, u32 prio,
+		      u32 level) {};
+
+static inline struct mlx5_flow_table *
+mlx5_chains_get_tc_end_ft(struct mlx5_fs_chains *chains) { return ERR_PTR(-EOPNOTSUPP); }
+
+static inline struct mlx5_fs_chains *
+mlx5_chains_create(struct mlx5_core_dev *dev, struct mlx5_chains_attr *attr)
+{ return NULL; }
+static inline void
+mlx5_chains_destroy(struct mlx5_fs_chains *chains) {};
+
+#endif /* CONFIG_MLX5_CLS_ACT */
+
+#endif /* __ML5_ESW_CHAINS_H__ */