net/mlx5e: Support CT offload for tc nic flows

Adding support to perform CT related tc actions and
matching on CT states for nic flows.

The ct flows management and handling will be done using a new
instance of the ct database that is declared in this patch to
keep it separate from the eswitch ct flows database.
Offloading and unoffloading ct flows will be done using the
existing ct offload api by providing it the relevant ct
database reference in each mode.

In addition, refactoring the tc ct api is introduced to make it
agnostic to the flow type and perform the resource allocations
and rule insertion to the proper steering domain in the device.

In the initialization call, the api requests and stores in the ct
database instance all the relevant information that distinguishes
between nic flows and esw flows, such as chains database, steering
namespace and mod hdr table.
This way the operations of adding and removing ct flows to the device
can later performed agnostically to the flow type.
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/en/fs.h

@@ -27,6 +27,8 @@ struct mlx5e_tc_table {
 
 	struct notifier_block     netdevice_nb;
 	struct netdev_net_notifier	netdevice_nn;
+
+	struct mlx5_tc_ct_priv         *ct;
 };
 
 struct mlx5e_flow_table {

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

@@ -612,7 +612,6 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 	struct tc_skb_ext *tc_skb_ext;
 	struct mlx5_eswitch *esw;
 	struct mlx5e_priv *priv;
-	int tunnel_moffset;
 	int err;
 
 	reg_c0 = (be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK);
@@ -647,13 +646,12 @@ bool mlx5e_rep_tc_update_skb(struct mlx5_cqe64 *cqe,
 
 		uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 		uplink_priv = &uplink_rpriv->uplink_priv;
-		if (!mlx5e_tc_ct_restore_flow(uplink_priv, skb,
+		if (!mlx5e_tc_ct_restore_flow(uplink_priv->ct_priv, skb,
 					      zone_restore_id))
 			return false;
 	}
 
-	tunnel_moffset = mlx5e_tc_attr_to_reg_mappings[TUNNEL_TO_REG].moffset;
-	tunnel_id = reg_c1 >> (8 * tunnel_moffset);
+	tunnel_id = reg_c1 >> REG_MAPPING_SHIFT(TUNNEL_TO_REG);
 	return mlx5e_restore_tunnel(priv, skb, tc_priv, tunnel_id);
 #endif /* CONFIG_NET_TC_SKB_EXT */
 

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

@@ -16,6 +16,8 @@ struct mlx5_rep_uplink_priv;
 struct mlx5e_tc_flow;
 struct mlx5e_priv;
 
+struct mlx5_fs_chains;
+struct mlx5_tc_ct_priv;
 struct mlx5_ct_flow;
 
 struct nf_flowtable;
@@ -76,22 +78,32 @@ struct mlx5_ct_attr {
 				 misc_parameters_2.metadata_reg_c_1) + 3,\
 }
 
+#define nic_zone_restore_to_reg_ct {\
+	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_B,\
+	.moffset = 2,\
+	.mlen = 1,\
+}
+
 #define REG_MAPPING_MLEN(reg) (mlx5e_tc_attr_to_reg_mappings[reg].mlen)
+#define REG_MAPPING_MOFFSET(reg) (mlx5e_tc_attr_to_reg_mappings[reg].moffset)
+#define REG_MAPPING_SHIFT(reg) (REG_MAPPING_MOFFSET(reg) * 8)
 #define ZONE_RESTORE_BITS (REG_MAPPING_MLEN(ZONE_RESTORE_TO_REG) * 8)
 #define ZONE_RESTORE_MAX GENMASK(ZONE_RESTORE_BITS - 1, 0)
 
 #if IS_ENABLED(CONFIG_MLX5_TC_CT)
 
-int
-mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv);
+struct mlx5_tc_ct_priv *
+mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
+		struct mod_hdr_tbl *mod_hdr,
+		enum mlx5_flow_namespace_type ns_type);
 void
-mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv);
+mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv);
 
 void
-mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr);
+mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_attr);
 
 int
-mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
 		     struct mlx5_flow_spec *spec,
 		     struct flow_cls_offload *f,
 		     struct mlx5_ct_attr *ct_attr,
@@ -100,44 +112,46 @@ int
 mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
 			    struct mlx5_flow_spec *spec);
 int
-mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
+mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 			struct mlx5_flow_attr *attr,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack);
 
 struct mlx5_flow_handle *
-mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
+mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
 			struct mlx5e_tc_flow *flow,
 			struct mlx5_flow_spec *spec,
 			struct mlx5_flow_attr *attr,
 			struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 void
-mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv,
+mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
 		       struct mlx5e_tc_flow *flow,
 		       struct mlx5_flow_attr *attr);
 
 bool
-mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv,
+mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 			 struct sk_buff *skb, u8 zone_restore_id);
 
 #else /* CONFIG_MLX5_TC_CT */
 
-static inline int
-mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
+static inline struct mlx5_tc_ct_priv *
+mlx5_tc_ct_init(struct mlx5e_priv *priv, struct mlx5_fs_chains *chains,
+		struct mod_hdr_tbl *mod_hdr,
+		enum mlx5_flow_namespace_type ns_type)
 {
-	return 0;
+	return NULL;
 }
 
 static inline void
-mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
+mlx5_tc_ct_clean(struct mlx5_tc_ct_priv *ct_priv)
 {
 }
 
 static inline void
-mlx5_tc_ct_match_del(struct mlx5e_priv *priv, struct mlx5_ct_attr *ct_attr) {}
+mlx5_tc_ct_match_del(struct mlx5_tc_ct_priv *priv, struct mlx5_ct_attr *ct_attr) {}
 
 static inline int
-mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
+mlx5_tc_ct_match_add(struct mlx5_tc_ct_priv *priv,
 		     struct mlx5_flow_spec *spec,
 		     struct flow_cls_offload *f,
 		     struct mlx5_ct_attr *ct_attr,
@@ -149,7 +163,6 @@ mlx5_tc_ct_match_add(struct mlx5e_priv *priv,
 		return 0;
 
 	NL_SET_ERR_MSG_MOD(extack, "mlx5 tc ct offload isn't enabled.");
-	netdev_warn(priv->netdev, "mlx5 tc ct offload isn't enabled.\n");
 	return -EOPNOTSUPP;
 }
 
@@ -161,18 +174,17 @@ mlx5_tc_ct_add_no_trk_match(struct mlx5e_priv *priv,
 }
 
 static inline int
-mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
+mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 			struct mlx5_flow_attr *attr,
 			const struct flow_action_entry *act,
 			struct netlink_ext_ack *extack)
 {
 	NL_SET_ERR_MSG_MOD(extack, "mlx5 tc ct offload isn't enabled.");
-	netdev_warn(priv->netdev, "mlx5 tc ct offload isn't enabled.\n");
 	return -EOPNOTSUPP;
 }
 
 static inline struct mlx5_flow_handle *
-mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
+mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv,
 			struct mlx5e_tc_flow *flow,
 			struct mlx5_flow_spec *spec,
 			struct mlx5_flow_attr *attr,
@@ -182,14 +194,14 @@ mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
 }
 
 static inline void
-mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv,
+mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
 		       struct mlx5e_tc_flow *flow,
 		       struct mlx5_flow_attr *attr)
 {
 }
 
 static inline bool
-mlx5e_tc_ct_restore_flow(struct mlx5_rep_uplink_priv *uplink_priv,
+mlx5e_tc_ct_restore_flow(struct mlx5_tc_ct_priv *ct_priv,
 			 struct sk_buff *skb, u8 zone_restore_id)
 {
 	if (!zone_restore_id)

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

@@ -42,8 +42,14 @@
 
 #ifdef CONFIG_MLX5_ESWITCH
 
+#define NIC_FLOW_ATTR_SZ (sizeof(struct mlx5_flow_attr) +\
+			  sizeof(struct mlx5_nic_flow_attr))
 #define ESW_FLOW_ATTR_SZ (sizeof(struct mlx5_flow_attr) +\
 			  sizeof(struct mlx5_esw_flow_attr))
+#define ns_to_attr_sz(ns) (((ns) == MLX5_FLOW_NAMESPACE_FDB) ?\
+			    ESW_FLOW_ATTR_SZ :\
+			    NIC_FLOW_ATTR_SZ)
+
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags);
 
@@ -124,6 +130,7 @@ enum {
 
 int mlx5e_tc_esw_init(struct rhashtable *tc_ht);
 void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht);
+bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow);
 
 int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv,
 			   struct flow_cls_offload *f, unsigned long flags);
@@ -168,6 +175,7 @@ enum mlx5e_tc_attr_to_reg {
 	LABELS_TO_REG,
 	FTEID_TO_REG,
 	NIC_CHAIN_TO_REG,
+	NIC_ZONE_RESTORE_TO_REG,
 };
 
 struct mlx5e_tc_attr_to_reg_mapping {
@@ -185,6 +193,7 @@ bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv,
 
 int mlx5e_tc_match_to_reg_set(struct mlx5_core_dev *mdev,
 			      struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts,
+			      enum mlx5_flow_namespace_type ns,
 			      enum mlx5e_tc_attr_to_reg type,
 			      u32 data);
 
@@ -224,6 +233,15 @@ void mlx5e_del_offloaded_nic_rule(struct mlx5e_priv *priv,
 				  struct mlx5_flow_handle *rule,
 				  struct mlx5_flow_attr *attr);
 
+struct mlx5_flow_handle *
+mlx5_tc_rule_insert(struct mlx5e_priv *priv,
+		    struct mlx5_flow_spec *spec,
+		    struct mlx5_flow_attr *attr);
+void
+mlx5_tc_rule_delete(struct mlx5e_priv *priv,
+		    struct mlx5_flow_handle *rule,
+		    struct mlx5_flow_attr *attr);
+
 #else /* CONFIG_MLX5_CLS_ACT */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}
@@ -235,6 +253,14 @@ mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
 
 struct mlx5_flow_attr *mlx5_alloc_flow_attr(enum mlx5_flow_namespace_type type);
 
+struct mlx5_flow_handle *
+mlx5e_add_offloaded_nic_rule(struct mlx5e_priv *priv,
+			     struct mlx5_flow_spec *spec,
+			     struct mlx5_flow_attr *attr);
+void mlx5e_del_offloaded_nic_rule(struct mlx5e_priv *priv,
+				  struct mlx5_flow_handle *rule,
+				  struct mlx5_flow_attr *attr);
+
 #else /* CONFIG_MLX5_ESWITCH */
 static inline int  mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; }
 static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {}