net/mlx5: Add support to use SMFS in switchdev mode

In case that flow steering mode of the driver is SMFS (Software Managed
Flow Steering), then use the DR (SW steering) API to create the steering
objects.

In addition, add a call to the set peer namespace when switchdev gets
devcom pair event. It is required to support VF LAG in SMFS.
Signed-off-by: Maor Gottlieb <maorg@mellanox.com>
Reviewed-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>

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

@@ -153,6 +153,7 @@ struct mlx5_eswitch_fdb {
 		} legacy;
 
 		struct offloads_fdb {
+			struct mlx5_flow_namespace *ns;
 			struct mlx5_flow_table *slow_fdb;
 			struct mlx5_flow_group *send_to_vport_grp;
 			struct mlx5_flow_group *peer_miss_grp;

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

@@ -1068,6 +1068,13 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 		err = -EOPNOTSUPP;
 		goto ns_err;
 	}
+	esw->fdb_table.offloads.ns = root_ns;
+	err = mlx5_flow_namespace_set_mode(root_ns,
+					   esw->dev->priv.steering->mode);
+	if (err) {
+		esw_warn(dev, "Failed to set FDB namespace steering mode\n");
+		goto ns_err;
+	}
 
 	max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) |
 			    MLX5_CAP_GEN(dev, max_flow_counter_15_0);
@@ -1207,6 +1214,8 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports)
 	esw_destroy_offloads_fast_fdb_tables(esw);
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 slow_fdb_err:
+	/* Holds true only as long as DMFS is the default */
+	mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS);
 ns_err:
 	kvfree(flow_group_in);
 	return err;
@@ -1226,6 +1235,9 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw)
 
 	mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb);
 	esw_destroy_offloads_fast_fdb_tables(esw);
+	/* Holds true only as long as DMFS is the default */
+	mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns,
+				     MLX5_FLOW_STEERING_MODE_DMFS);
 }
 
 static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports)
@@ -1623,13 +1635,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw)
 	esw_del_fdb_peer_miss_rules(esw);
 }
 
+static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw,
+					 struct mlx5_eswitch *peer_esw,
+					 bool pair)
+{
+	struct mlx5_flow_root_namespace *peer_ns;
+	struct mlx5_flow_root_namespace *ns;
+	int err;
+
+	peer_ns = peer_esw->dev->priv.steering->fdb_root_ns;
+	ns = esw->dev->priv.steering->fdb_root_ns;
+
+	if (pair) {
+		err = mlx5_flow_namespace_set_peer(ns, peer_ns);
+		if (err)
+			return err;
+
+		mlx5_flow_namespace_set_peer(peer_ns, ns);
+		if (err) {
+			mlx5_flow_namespace_set_peer(ns, NULL);
+			return err;
+		}
+	} else {
+		mlx5_flow_namespace_set_peer(ns, NULL);
+		mlx5_flow_namespace_set_peer(peer_ns, NULL);
+	}
+
+	return 0;
+}
+
 static int mlx5_esw_offloads_devcom_event(int event,
 					  void *my_data,
 					  void *event_data)
 {
 	struct mlx5_eswitch *esw = my_data;
-	struct mlx5_eswitch *peer_esw = event_data;
 	struct mlx5_devcom *devcom = esw->dev->priv.devcom;
+	struct mlx5_eswitch *peer_esw = event_data;
 	int err;
 
 	switch (event) {
@@ -1638,9 +1679,12 @@ static int mlx5_esw_offloads_devcom_event(int event,
 		    mlx5_eswitch_vport_match_metadata_enabled(peer_esw))
 			break;
 
-		err = mlx5_esw_offloads_pair(esw, peer_esw);
+		err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true);
 		if (err)
 			goto err_out;
+		err = mlx5_esw_offloads_pair(esw, peer_esw);
+		if (err)
+			goto err_peer;
 
 		err = mlx5_esw_offloads_pair(peer_esw, esw);
 		if (err)
@@ -1656,6 +1700,7 @@ static int mlx5_esw_offloads_devcom_event(int event,
 		mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false);
 		mlx5_esw_offloads_unpair(peer_esw);
 		mlx5_esw_offloads_unpair(esw);
+		mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
 		break;
 	}
 
@@ -1663,7 +1708,8 @@ static int mlx5_esw_offloads_devcom_event(int event,
 
 err_pair:
 	mlx5_esw_offloads_unpair(esw);
-
+err_peer:
+	mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false);
 err_out:
 	mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d",
 		      event, err);
@@ -2115,9 +2161,10 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	else
 		esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 
+	mlx5_rdma_enable_roce(esw->dev);
 	err = esw_offloads_steering_init(esw);
 	if (err)
-		return err;
+		goto err_steering_init;
 
 	err = esw_set_passing_vport_metadata(esw, true);
 	if (err)
@@ -2132,8 +2179,6 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	esw_offloads_devcom_init(esw);
 	mutex_init(&esw->offloads.termtbl_mutex);
 
-	mlx5_rdma_enable_roce(esw->dev);
-
 	return 0;
 
 err_reps:
@@ -2141,6 +2186,8 @@ int esw_offloads_enable(struct mlx5_eswitch *esw)
 	esw_set_passing_vport_metadata(esw, false);
 err_vport_metadata:
 	esw_offloads_steering_cleanup(esw);
+err_steering_init:
+	mlx5_rdma_disable_roce(esw->dev);
 	return err;
 }
 
@@ -2165,12 +2212,12 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw,
 
 void esw_offloads_disable(struct mlx5_eswitch *esw)
 {
-	mlx5_rdma_disable_roce(esw->dev);
 	esw_offloads_devcom_cleanup(esw);
 	esw_offloads_unload_all_reps(esw);
 	mlx5_eswitch_disable_pf_vf_vports(esw);
 	esw_set_passing_vport_metadata(esw, false);
 	esw_offloads_steering_cleanup(esw);
+	mlx5_rdma_disable_roce(esw->dev);
 	esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE;
 }