net/mlx5e: Use correct eswitch for stack devices with lag

If link aggregation is used within stack devices driver rejects encap
rules if PF of the VF tunnel device is down. This happens because route
resolved for other PF and its eswitch instance is used to determine
correct vport.
To fix that use devcom feature to retrieve other eswitch instance if
failed to find vport for the 1st eswitch and LAG is active.

Fixes: 10742efc ("net/mlx5e: VF tunnel TX traffic offloading")
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

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

@@ -1338,6 +1338,7 @@ bool mlx5e_tc_is_vf_tunnel(struct net_device *out_dev, struct net_device *route_
 int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *route_dev, u16 *vport)
 {
 	struct mlx5e_priv *out_priv, *route_priv;
+	struct mlx5_devcom *devcom = NULL;
 	struct mlx5_core_dev *route_mdev;
 	struct mlx5_eswitch *esw;
 	u16 vhca_id;
@@ -1349,7 +1350,24 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro
 	route_mdev = route_priv->mdev;
 
 	vhca_id = MLX5_CAP_GEN(route_mdev, vhca_id);
+	if (mlx5_lag_is_active(out_priv->mdev)) {
+		/* In lag case we may get devices from different eswitch instances.
+		 * If we failed to get vport num, it means, mostly, that we on the wrong
+		 * eswitch.
+		 */
+		err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport);
+		if (err != -ENOENT)
+			return err;
+
+		devcom = out_priv->mdev->priv.devcom;
+		esw = mlx5_devcom_get_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
+		if (!esw)
+			return -ENODEV;
+	}
+
 	err = mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport);
+	if (devcom)
+		mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS);
 	return err;
 }