net/mlx5e: CT: Introduce connection tracking

Add support for offloading tc ct action and ct matches.
We translate the tc filter with CT action the following HW model:

+-------------------+      +--------------------+    +--------------+
+ pre_ct (tc chain) +----->+ CT (nat or no nat) +--->+ post_ct      +----->
+ original match    +  |   + tuple + zone match + |  + fte_id match +  |
+-------------------+  |   +--------------------+ |  +--------------+  |
                       v                          v                    v
                      set chain miss mapping  set mark             original
                      set fte_id              set label            filter
                      set zone                set established      actions
                      set tunnel_id           do nat (if needed)
                      do decap
Signed-off-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Oz Shlomo <ozsh@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/mellanox/mlx5/core/Kconfig

@@ -78,6 +78,16 @@ config MLX5_ESWITCH
 	        Legacy SRIOV mode (L2 mac vlan steering based).
 	        Switchdev mode (eswitch offloads).
 
+config MLX5_TC_CT
+	bool "MLX5 TC connection tracking offload support"
+	depends on MLX5_CORE_EN && NET_SWITCHDEV && NF_FLOW_TABLE && NET_ACT_CT && NET_TC_SKB_EXT
+	default y
+	help
+	  Say Y here if you want to support offloading connection tracking rules
+	  via tc ct action.
+
+	  If unsure, set to Y
+
 config MLX5_CORE_EN_DCB
 	bool "Data Center Bridging (DCB) Support"
 	default y

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

@@ -37,6 +37,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o en/tc_tun.o lib/port_tu
 					lib/geneve.o en/mapping.o en/tc_tun_vxlan.o en/tc_tun_gre.o \
 					en/tc_tun_geneve.o diag/en_tc_tracepoint.o
 mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o
+mlx5_core-$(CONFIG_MLX5_TC_CT)	     += en/tc_ct.o
 
 #
 # Core extra

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

+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5_EN_TC_CT_H__
+#define __MLX5_EN_TC_CT_H__
+
+#include <net/pkt_cls.h>
+#include <linux/mlx5/fs.h>
+#include <net/tc_act/tc_ct.h>
+
+struct mlx5_esw_flow_attr;
+struct mlx5_rep_uplink_priv;
+struct mlx5e_tc_flow;
+struct mlx5e_priv;
+
+struct mlx5_ct_flow;
+
+struct mlx5_ct_attr {
+	u16 zone;
+	u16 ct_action;
+	struct mlx5_ct_flow *ct_flow;
+};
+
+#define zone_to_reg_ct {\
+	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_2,\
+	.moffset = 0,\
+	.mlen = 2,\
+	.soffset = MLX5_BYTE_OFF(fte_match_param,\
+				 misc_parameters_2.metadata_reg_c_2) + 2,\
+}
+
+#define ctstate_to_reg_ct {\
+	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_2,\
+	.moffset = 2,\
+	.mlen = 2,\
+	.soffset = MLX5_BYTE_OFF(fte_match_param,\
+				 misc_parameters_2.metadata_reg_c_2),\
+}
+
+#define mark_to_reg_ct {\
+	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_3,\
+	.moffset = 0,\
+	.mlen = 4,\
+	.soffset = MLX5_BYTE_OFF(fte_match_param,\
+				 misc_parameters_2.metadata_reg_c_3),\
+}
+
+#define labels_to_reg_ct {\
+	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_4,\
+	.moffset = 0,\
+	.mlen = 4,\
+	.soffset = MLX5_BYTE_OFF(fte_match_param,\
+				 misc_parameters_2.metadata_reg_c_4),\
+}
+
+#define fteid_to_reg_ct {\
+	.mfield = MLX5_ACTION_IN_FIELD_METADATA_REG_C_5,\
+	.moffset = 0,\
+	.mlen = 4,\
+	.soffset = MLX5_BYTE_OFF(fte_match_param,\
+				 misc_parameters_2.metadata_reg_c_5),\
+}
+
+#if IS_ENABLED(CONFIG_MLX5_TC_CT)
+
+int
+mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv);
+void
+mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv);
+
+int
+mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct flow_cls_offload *f,
+		       struct netlink_ext_ack *extack);
+int
+mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
+			struct mlx5_esw_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,
+			struct mlx5e_tc_flow *flow,
+			struct mlx5_flow_spec *spec,
+			struct mlx5_esw_flow_attr *attr);
+void
+mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv,
+		       struct mlx5e_tc_flow *flow,
+		       struct mlx5_esw_flow_attr *attr);
+
+#else /* CONFIG_MLX5_TC_CT */
+
+static inline int
+mlx5_tc_ct_init(struct mlx5_rep_uplink_priv *uplink_priv)
+{
+	return 0;
+}
+
+static inline void
+mlx5_tc_ct_clean(struct mlx5_rep_uplink_priv *uplink_priv)
+{
+}
+
+static inline int
+mlx5_tc_ct_parse_match(struct mlx5e_priv *priv,
+		       struct mlx5_flow_spec *spec,
+		       struct flow_cls_offload *f,
+		       struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+mlx5_tc_ct_parse_action(struct mlx5e_priv *priv,
+			struct mlx5_esw_flow_attr *attr,
+			const struct flow_action_entry *act,
+			struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline struct mlx5_flow_handle *
+mlx5_tc_ct_flow_offload(struct mlx5e_priv *priv,
+			struct mlx5e_tc_flow *flow,
+			struct mlx5_flow_spec *spec,
+			struct mlx5_esw_flow_attr *attr)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void
+mlx5_tc_ct_delete_flow(struct mlx5e_priv *priv,
+		       struct mlx5e_tc_flow *flow,
+		       struct mlx5_esw_flow_attr *attr)
+{
+}
+
+#endif /* !IS_ENABLED(CONFIG_MLX5_TC_CT) */
+#endif /* __MLX5_EN_TC_CT_H__ */

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

@@ -55,6 +55,7 @@ struct mlx5e_neigh_update_table {
 	unsigned long           min_interval; /* jiffies */
 };
 
+struct mlx5_tc_ct_priv;
 struct mlx5_rep_uplink_priv {
 	/* Filters DB - instantiated by the uplink representor and shared by
 	 * the uplink's VFs
@@ -86,6 +87,8 @@ struct mlx5_rep_uplink_priv {
 	struct mapping_ctx *tunnel_mapping;
 	/* maps tun_enc_opts to a unique id*/
 	struct mapping_ctx *tunnel_enc_opts_mapping;
+
+	struct mlx5_tc_ct_priv *ct_priv;
 };
 
 struct mlx5e_rep_priv {

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

@@ -56,6 +56,7 @@
 #include "en/port.h"
 #include "en/tc_tun.h"
 #include "en/mapping.h"
+#include "en/tc_ct.h"
 #include "lib/devcom.h"
 #include "lib/geneve.h"
 #include "diag/en_tc_tracepoint.h"
@@ -87,6 +88,7 @@ enum {
 	MLX5E_TC_FLOW_FLAG_DUP		= MLX5E_TC_FLOW_BASE + 4,
 	MLX5E_TC_FLOW_FLAG_NOT_READY	= MLX5E_TC_FLOW_BASE + 5,
 	MLX5E_TC_FLOW_FLAG_DELETED	= MLX5E_TC_FLOW_BASE + 6,
+	MLX5E_TC_FLOW_FLAG_CT		= MLX5E_TC_FLOW_BASE + 7,
 };
 
 #define MLX5E_TC_MAX_SPLITS 1
@@ -193,6 +195,11 @@ struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
 		.soffset = MLX5_BYTE_OFF(fte_match_param,
 					 misc_parameters_2.metadata_reg_c_1),
 	},
+	[ZONE_TO_REG] = zone_to_reg_ct,
+	[CTSTATE_TO_REG] = ctstate_to_reg_ct,
+	[MARK_TO_REG] = mark_to_reg_ct,
+	[LABELS_TO_REG] = labels_to_reg_ct,
+	[FTEID_TO_REG] = fteid_to_reg_ct,
 };
 
 static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow);
@@ -1144,6 +1151,10 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw,
 			   struct mlx5_esw_flow_attr *attr)
 {
 	struct mlx5_flow_handle *rule;
+	struct mlx5e_tc_mod_hdr_acts;
+
+	if (flow_flag_test(flow, CT))
+		return mlx5_tc_ct_flow_offload(flow->priv, flow, spec, attr);
 
 	rule = mlx5_eswitch_add_offloaded_rule(esw, spec, attr);
 	if (IS_ERR(rule))
@@ -1167,6 +1178,11 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw,
 {
 	flow_flag_clear(flow, OFFLOADED);
 
+	if (flow_flag_test(flow, CT)) {
+		mlx5_tc_ct_delete_flow(flow->priv, flow, attr);
+		return;
+	}
+
 	if (attr->split_count)
 		mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr);
 
@@ -1938,6 +1954,11 @@ static void mlx5e_put_flow_tunnel_id(struct mlx5e_tc_flow *flow)
 			       enc_opts_id);
 }
 
+u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow)
+{
+	return flow->tunnel_id;
+}
+
 static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			     struct mlx5e_tc_flow *flow,
 			     struct mlx5_flow_spec *spec,
@@ -2103,6 +2124,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_TCP) |
 	      BIT(FLOW_DISSECTOR_KEY_IP)  |
+	      BIT(FLOW_DISSECTOR_KEY_CT) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_IP) |
 	      BIT(FLOW_DISSECTOR_KEY_ENC_OPTS))) {
 		NL_SET_ERR_MSG_MOD(extack, "Unsupported key");
@@ -2913,7 +2935,9 @@ struct ipv6_hoplimit_word {
 	__u8	hop_limit;
 };
 
-static bool is_action_keys_supported(const struct flow_action_entry *act)
+static int is_action_keys_supported(const struct flow_action_entry *act,
+				    bool ct_flow, bool *modify_ip_header,
+				    struct netlink_ext_ack *extack)
 {
 	u32 mask, offset;
 	u8 htype;
@@ -2932,7 +2956,13 @@ static bool is_action_keys_supported(const struct flow_action_entry *act)
 		if (offset != offsetof(struct iphdr, ttl) ||
 		    ttl_word->protocol ||
 		    ttl_word->check) {
-			return true;
+			*modify_ip_header = true;
+		}
+
+		if (ct_flow && offset >= offsetof(struct iphdr, saddr)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "can't offload re-write of ipv4 address with action ct");
+			return -EOPNOTSUPP;
 		}
 	} else if (htype == FLOW_ACT_MANGLE_HDR_TYPE_IP6) {
 		struct ipv6_hoplimit_word *hoplimit_word =
@@ -2941,15 +2971,27 @@ static bool is_action_keys_supported(const struct flow_action_entry *act)
 		if (offset != offsetof(struct ipv6hdr, payload_len) ||
 		    hoplimit_word->payload_len ||
 		    hoplimit_word->nexthdr) {
-			return true;
+			*modify_ip_header = true;
 		}
+
+		if (ct_flow && offset >= offsetof(struct ipv6hdr, saddr)) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "can't offload re-write of ipv6 address with action ct");
+			return -EOPNOTSUPP;
 		}
-	return false;
+	} else if (ct_flow && (htype == FLOW_ACT_MANGLE_HDR_TYPE_TCP ||
+			       htype == FLOW_ACT_MANGLE_HDR_TYPE_UDP)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "can't offload re-write of transport header ports with action ct");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
 }
 
 static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 					  struct flow_action *flow_action,
-					  u32 actions,
+					  u32 actions, bool ct_flow,
 					  struct netlink_ext_ack *extack)
 {
 	const struct flow_action_entry *act;
@@ -2957,7 +2999,7 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 	void *headers_v;
 	u16 ethertype;
 	u8 ip_proto;
-	int i;
+	int i, err;
 
 	headers_v = get_match_headers_value(actions, spec);
 	ethertype = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ethertype);
@@ -2972,10 +3014,10 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec,
 		    act->id != FLOW_ACTION_ADD)
 			continue;
 
-		if (is_action_keys_supported(act)) {
-			modify_ip_header = true;
-			break;
-		}
+		err = is_action_keys_supported(act, ct_flow,
+					       &modify_ip_header, extack);
+		if (err)
+			return err;
 	}
 
 	ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol);
@@ -2998,13 +3040,24 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 				    struct netlink_ext_ack *extack)
 {
 	struct net_device *filter_dev = parse_attr->filter_dev;
-	bool drop_action, pop_action;
+	bool drop_action, pop_action, ct_flow;
 	u32 actions;
 
-	if (mlx5e_is_eswitch_flow(flow))
+	ct_flow = flow_flag_test(flow, CT);
+	if (mlx5e_is_eswitch_flow(flow)) {
 		actions = flow->esw_attr->action;
-	else
+
+		if (flow->esw_attr->split_count && ct_flow) {
+			/* All registers used by ct are cleared when using
+			 * split rules.
+			 */
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Can't offload mirroring with action ct");
+			return -EOPNOTSUPP;
+		}
+	} else {
 		actions = flow->nic_attr->action;
+	}
 
 	drop_action = actions & MLX5_FLOW_CONTEXT_ACTION_DROP;
 	pop_action = actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
@@ -3021,7 +3074,7 @@ static bool actions_match_supported(struct mlx5e_priv *priv,
 	if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR)
 		return modify_header_match_supported(&parse_attr->spec,
 						     flow_action, actions,
-						     extack);
+						     ct_flow, extack);
 
 	return true;
 }
@@ -3826,6 +3879,13 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv,
 			action |= MLX5_FLOW_CONTEXT_ACTION_COUNT;
 			attr->dest_chain = act->chain_index;
 			break;
+		case FLOW_ACTION_CT:
+			err = mlx5_tc_ct_parse_action(priv, attr, act, extack);
+			if (err)
+				return err;
+
+			flow_flag_set(flow, CT);
+			break;
 		default:
 			NL_SET_ERR_MSG_MOD(extack, "The offload action is not supported");
 			return -EOPNOTSUPP;
@@ -4066,6 +4126,10 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv,
 	if (err)
 		goto err_free;
 
+	err = mlx5_tc_ct_parse_match(priv, &parse_attr->spec, f, extack);
+	if (err)
+		goto err_free;
+
 	err = mlx5e_tc_add_fdb_flow(priv, flow, extack);
 	complete_all(&flow->init_done);
 	if (err) {
@@ -4350,7 +4414,7 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv,
 		goto errout;
 	}
 
-	if (mlx5e_is_offloaded_flow(flow)) {
+	if (mlx5e_is_offloaded_flow(flow) || flow_flag_test(flow, CT)) {
 		counter = mlx5e_tc_get_counter(flow);
 		if (!counter)
 			goto errout;
@@ -4622,6 +4686,10 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 	uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht);
 	priv = container_of(uplink_priv, struct mlx5e_rep_priv, uplink_priv);
 
+	err = mlx5_tc_ct_init(uplink_priv);
+	if (err)
+		goto err_ct;
+
 	mapping = mapping_create(sizeof(struct tunnel_match_key),
 				 TUNNEL_INFO_BITS_MASK, true);
 	if (IS_ERR(mapping)) {
@@ -4648,6 +4716,8 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht)
 err_enc_opts_mapping:
 	mapping_destroy(uplink_priv->tunnel_mapping);
 err_tun_mapping:
+	mlx5_tc_ct_clean(uplink_priv);
+err_ct:
 	netdev_warn(priv->netdev,
 		    "Failed to initialize tc (eswitch), err: %d", err);
 	return err;
@@ -4662,6 +4732,8 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht)
 	uplink_priv = container_of(tc_ht, struct mlx5_rep_uplink_priv, tc_ht);
 	mapping_destroy(uplink_priv->tunnel_enc_opts_mapping);
 	mapping_destroy(uplink_priv->tunnel_mapping);
+
+	mlx5_tc_ct_clean(uplink_priv);
 }
 
 int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags)

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

@@ -94,6 +94,11 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work);
 enum mlx5e_tc_attr_to_reg {
 	CHAIN_TO_REG,
 	TUNNEL_TO_REG,
+	CTSTATE_TO_REG,
+	ZONE_TO_REG,
+	MARK_TO_REG,
+	LABELS_TO_REG,
+	FTEID_TO_REG,
 };
 
 struct mlx5e_tc_attr_to_reg_mapping {
@@ -139,6 +144,9 @@ int alloc_mod_hdr_actions(struct mlx5_core_dev *mdev,
 			  struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 void dealloc_mod_hdr_actions(struct mlx5e_tc_mod_hdr_acts *mod_hdr_acts);
 
+struct mlx5e_tc_flow;
+u32 mlx5e_tc_get_flow_tun_id(struct mlx5e_tc_flow *flow);
+
 #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) {}

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 "en/tc_ct.h"
 
 #define FDB_TC_MAX_CHAIN 3
 #define FDB_FT_CHAIN (FDB_TC_MAX_CHAIN + 1)
@@ -424,6 +425,7 @@ struct mlx5_esw_flow_attr {
 	u32	flags;
 	struct mlx5_flow_table *fdb;
 	struct mlx5_flow_table *dest_ft;
+	struct mlx5_ct_attr ct_attr;
 	struct mlx5e_tc_flow_parse_attr *parse_attr;
 };