net/mlx5: E-Switch, add logic to enable shared FDB

Shared FDB allows to direct traffic from all the vports in the HCA to a
single eswitch. In order to do that three things are needed.

1) Point the ingress ACL of the slave uplink to that of the master.
   With this, wire traffic from both uplinks will reach the same eswitch
   with the same metadata where a single steering rule can catch traffic
   from both ports.

2) Set the FDB root flow table of the slave's eswitch to that of the
   master. As this flow table can change dynamically make sure to
   sync it on any set root flow table FDB command.
   This will make sure traffic from SFs, VFs, ECPFs and PFs reach the
   master eswitch.

3) Split wire traffic at the eswitch manager egress ACL so that it's
   directed to the native eswitch manager. We only treat wire traffic
   from both ports the same at the eswitch level. If such traffic wasn't
   handled in the eswitch it needs to reach the right representor to be
   processed by software. For example LACP packets should *always*
   reach the right uplink representor for correct operation.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

Author: mark-bloch

drivers/net/ethernet/mellanox/mlx5/core/esw/acl/egress_ofld.c

@@ -15,6 +15,15 @@ static void esw_acl_egress_ofld_fwd2vport_destroy(struct mlx5_vport *vport)
 	vport->egress.offloads.fwd_rule = NULL;
 }
 
+static void esw_acl_egress_ofld_bounce_rule_destroy(struct mlx5_vport *vport)
+{
+	if (!vport->egress.offloads.bounce_rule)
+		return;
+
+	mlx5_del_flow_rules(vport->egress.offloads.bounce_rule);
+	vport->egress.offloads.bounce_rule = NULL;
+}
+
 static int esw_acl_egress_ofld_fwd2vport_create(struct mlx5_eswitch *esw,
 						struct mlx5_vport *vport,
 						struct mlx5_flow_destination *fwd_dest)
@@ -87,6 +96,7 @@ static void esw_acl_egress_ofld_rules_destroy(struct mlx5_vport *vport)
 {
 	esw_acl_egress_vlan_destroy(vport);
 	esw_acl_egress_ofld_fwd2vport_destroy(vport);
+	esw_acl_egress_ofld_bounce_rule_destroy(vport);
 }
 
 static int esw_acl_egress_ofld_groups_create(struct mlx5_eswitch *esw,
@@ -145,6 +155,12 @@ static void esw_acl_egress_ofld_groups_destroy(struct mlx5_vport *vport)
 		mlx5_destroy_flow_group(vport->egress.offloads.fwd_grp);
 		vport->egress.offloads.fwd_grp = NULL;
 	}
+
+	if (!IS_ERR_OR_NULL(vport->egress.offloads.bounce_grp)) {
+		mlx5_destroy_flow_group(vport->egress.offloads.bounce_grp);
+		vport->egress.offloads.bounce_grp = NULL;
+	}
+
 	esw_acl_egress_vlan_grp_destroy(vport);
 }
 

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

@@ -132,6 +132,8 @@ struct vport_egress {
 		struct {
 			struct mlx5_flow_group *fwd_grp;
 			struct mlx5_flow_handle *fwd_rule;
+			struct mlx5_flow_handle *bounce_rule;
+			struct mlx5_flow_group *bounce_grp;
 		} offloads;
 	};
 };
@@ -714,6 +716,12 @@ void esw_vport_change_handle_locked(struct mlx5_vport *vport);
 
 bool mlx5_esw_offloads_controller_valid(const struct mlx5_eswitch *esw, u32 controller);
 
+int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
+					    struct mlx5_eswitch *slave_esw);
+void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw,
+					      struct mlx5_eswitch *slave_esw);
+int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw);
+
 #else  /* CONFIG_MLX5_ESWITCH */
 /* eswitch API stubs */
 static inline int  mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; }
@@ -744,6 +752,23 @@ mlx5_esw_vport_to_devlink_port_index(const struct mlx5_core_dev *dev,
 {
 	return vport_num;
 }
+
+static inline int
+mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
+					struct mlx5_eswitch *slave_esw)
+{
+	return 0;
+}
+
+static inline void
+mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw,
+					 struct mlx5_eswitch *slave_esw) {}
+
+static inline int
+mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
+{
+	return 0;
+}
 #endif /* CONFIG_MLX5_ESWITCH */
 
 #endif /* __MLX5_ESWITCH_H__ */

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

@@ -2325,6 +2325,274 @@ void esw_offloads_unload_rep(struct mlx5_eswitch *esw, u16 vport_num)
 		mlx5_esw_offloads_devlink_port_unregister(esw, vport_num);
 }
 
+static int esw_set_uplink_slave_ingress_root(struct mlx5_core_dev *master,
+					     struct mlx5_core_dev *slave)
+{
+	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {};
+	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {};
+	struct mlx5_eswitch *esw;
+	struct mlx5_flow_root_namespace *root;
+	struct mlx5_flow_namespace *ns;
+	struct mlx5_vport *vport;
+	int err;
+
+	MLX5_SET(set_flow_table_root_in, in, opcode,
+		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
+	MLX5_SET(set_flow_table_root_in, in, table_type, FS_FT_ESW_INGRESS_ACL);
+	MLX5_SET(set_flow_table_root_in, in, other_vport, 1);
+	MLX5_SET(set_flow_table_root_in, in, vport_number, MLX5_VPORT_UPLINK);
+
+	if (master) {
+		esw = master->priv.eswitch;
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+		MLX5_SET(set_flow_table_root_in, in, table_of_other_vport, 1);
+		MLX5_SET(set_flow_table_root_in, in, table_vport_number,
+			 MLX5_VPORT_UPLINK);
+
+		ns = mlx5_get_flow_vport_acl_namespace(master,
+						       MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+						       vport->index);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id_valid, 1);
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(master, vhca_id));
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 root->root_ft->id);
+	} else {
+		esw = slave->priv.eswitch;
+		vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_UPLINK);
+		ns = mlx5_get_flow_vport_acl_namespace(slave,
+						       MLX5_FLOW_NAMESPACE_ESW_INGRESS,
+						       vport->index);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+		MLX5_SET(set_flow_table_root_in, in, table_id, root->root_ft->id);
+	}
+
+	err = mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out));
+	mutex_unlock(&root->chain_lock);
+
+	return err;
+}
+
+static int esw_set_slave_root_fdb(struct mlx5_core_dev *master,
+				  struct mlx5_core_dev *slave)
+{
+	u32 in[MLX5_ST_SZ_DW(set_flow_table_root_in)]   = {};
+	u32 out[MLX5_ST_SZ_DW(set_flow_table_root_out)] = {};
+	struct mlx5_flow_root_namespace *root;
+	struct mlx5_flow_namespace *ns;
+	int err;
+
+	MLX5_SET(set_flow_table_root_in, in, opcode,
+		 MLX5_CMD_OP_SET_FLOW_TABLE_ROOT);
+	MLX5_SET(set_flow_table_root_in, in, table_type,
+		 FS_FT_FDB);
+
+	if (master) {
+		ns = mlx5_get_flow_namespace(master,
+					     MLX5_FLOW_NAMESPACE_FDB);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id_valid, 1);
+		MLX5_SET(set_flow_table_root_in, in,
+			 table_eswitch_owner_vhca_id,
+			 MLX5_CAP_GEN(master, vhca_id));
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 root->root_ft->id);
+	} else {
+		ns = mlx5_get_flow_namespace(slave,
+					     MLX5_FLOW_NAMESPACE_FDB);
+		root = find_root(&ns->node);
+		mutex_lock(&root->chain_lock);
+		MLX5_SET(set_flow_table_root_in, in, table_id,
+			 root->root_ft->id);
+	}
+
+	err = mlx5_cmd_exec(slave, in, sizeof(in), out, sizeof(out));
+	mutex_unlock(&root->chain_lock);
+
+	return err;
+}
+
+static int __esw_set_master_egress_rule(struct mlx5_core_dev *master,
+					struct mlx5_core_dev *slave,
+					struct mlx5_vport *vport,
+					struct mlx5_flow_table *acl)
+{
+	struct mlx5_flow_handle *flow_rule = NULL;
+	struct mlx5_flow_destination dest = {};
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+	void *misc;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS;
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+			    misc_parameters);
+	MLX5_SET(fte_match_set_misc, misc, source_port, MLX5_VPORT_UPLINK);
+	MLX5_SET(fte_match_set_misc, misc, source_eswitch_owner_vhca_id,
+		 MLX5_CAP_GEN(slave, vhca_id));
+
+	misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, misc_parameters);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port);
+	MLX5_SET_TO_ONES(fte_match_set_misc, misc,
+			 source_eswitch_owner_vhca_id);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_VPORT;
+	dest.vport.num = slave->priv.eswitch->manager_vport;
+	dest.vport.vhca_id = MLX5_CAP_GEN(slave, vhca_id);
+	dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID;
+
+	flow_rule = mlx5_add_flow_rules(acl, spec, &flow_act,
+					&dest, 1);
+	if (IS_ERR(flow_rule))
+		err = PTR_ERR(flow_rule);
+	else
+		vport->egress.offloads.bounce_rule = flow_rule;
+
+	kvfree(spec);
+	return err;
+}
+
+static int esw_set_master_egress_rule(struct mlx5_core_dev *master,
+				      struct mlx5_core_dev *slave)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_eswitch *esw = master->priv.eswitch;
+	struct mlx5_flow_table_attr ft_attr = {
+		.max_fte = 1, .prio = 0, .level = 0,
+	};
+	struct mlx5_flow_namespace *egress_ns;
+	struct mlx5_flow_table *acl;
+	struct mlx5_flow_group *g;
+	struct mlx5_vport *vport;
+	void *match_criteria;
+	u32 *flow_group_in;
+	int err;
+
+	vport = mlx5_eswitch_get_vport(esw, esw->manager_vport);
+	if (IS_ERR(vport))
+		return PTR_ERR(vport);
+
+	egress_ns = mlx5_get_flow_vport_acl_namespace(master,
+						      MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+						      vport->index);
+	if (!egress_ns)
+		return -EINVAL;
+
+	if (vport->egress.acl)
+		return -EINVAL;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	acl = mlx5_create_vport_flow_table(egress_ns, &ft_attr, vport->vport);
+	if (IS_ERR(acl)) {
+		err = PTR_ERR(acl);
+		goto out;
+	}
+
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_port);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters.source_eswitch_owner_vhca_id);
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS);
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 source_eswitch_owner_vhca_id_valid, 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index, 0);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index, 0);
+
+	g = mlx5_create_flow_group(acl, flow_group_in);
+	if (IS_ERR(g)) {
+		err = PTR_ERR(g);
+		goto err_group;
+	}
+
+	err = __esw_set_master_egress_rule(master, slave, vport, acl);
+	if (err)
+		goto err_rule;
+
+	vport->egress.acl = acl;
+	vport->egress.offloads.bounce_grp = g;
+
+	kvfree(flow_group_in);
+
+	return 0;
+
+err_rule:
+	mlx5_destroy_flow_group(g);
+err_group:
+	mlx5_destroy_flow_table(acl);
+out:
+	kvfree(flow_group_in);
+	return err;
+}
+
+static void esw_unset_master_egress_rule(struct mlx5_core_dev *dev)
+{
+	struct mlx5_vport *vport;
+
+	vport = mlx5_eswitch_get_vport(dev->priv.eswitch,
+				       dev->priv.eswitch->manager_vport);
+
+	esw_acl_egress_ofld_cleanup(vport);
+}
+
+int mlx5_eswitch_offloads_config_single_fdb(struct mlx5_eswitch *master_esw,
+					    struct mlx5_eswitch *slave_esw)
+{
+	int err;
+
+	err = esw_set_uplink_slave_ingress_root(master_esw->dev,
+						slave_esw->dev);
+	if (err)
+		return -EINVAL;
+
+	err = esw_set_slave_root_fdb(master_esw->dev,
+				     slave_esw->dev);
+	if (err)
+		goto err_fdb;
+
+	err = esw_set_master_egress_rule(master_esw->dev,
+					 slave_esw->dev);
+	if (err)
+		goto err_acl;
+
+	return err;
+
+err_acl:
+	esw_set_slave_root_fdb(NULL, slave_esw->dev);
+
+err_fdb:
+	esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev);
+
+	return err;
+}
+
+void mlx5_eswitch_offloads_destroy_single_fdb(struct mlx5_eswitch *master_esw,
+					      struct mlx5_eswitch *slave_esw)
+{
+	esw_unset_master_egress_rule(master_esw->dev);
+	esw_set_slave_root_fdb(NULL, slave_esw->dev);
+	esw_set_uplink_slave_ingress_root(NULL, slave_esw->dev);
+}
+
 #define ESW_OFFLOADS_DEVCOM_PAIR	(0)
 #define ESW_OFFLOADS_DEVCOM_UNPAIR	(1)
 
@@ -2674,6 +2942,31 @@ static void esw_destroy_uplink_offloads_acl_tables(struct mlx5_eswitch *esw)
 	esw_vport_destroy_offloads_acl_tables(esw, vport);
 }
 
+int mlx5_eswitch_reload_reps(struct mlx5_eswitch *esw)
+{
+	struct mlx5_eswitch_rep *rep;
+	unsigned long i;
+	int ret;
+
+	if (!esw || esw->mode != MLX5_ESWITCH_OFFLOADS)
+		return 0;
+
+	rep = mlx5_eswitch_get_rep(esw, MLX5_VPORT_UPLINK);
+	if (atomic_read(&rep->rep_data[REP_ETH].state) != REP_LOADED)
+		return 0;
+
+	ret = mlx5_esw_offloads_rep_load(esw, MLX5_VPORT_UPLINK);
+	if (ret)
+		return ret;
+
+	mlx5_esw_for_each_rep(esw, i, rep) {
+		if (atomic_read(&rep->rep_data[REP_ETH].state) == REP_LOADED)
+			mlx5_esw_offloads_rep_load(esw, rep->vport);
+	}
+
+	return 0;
+}
+
 static int esw_offloads_steering_init(struct mlx5_eswitch *esw)
 {
 	struct mlx5_esw_indir_table *indir;