3 files changed, 70 insertions, 29 deletions

diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 52821485371a..ddcfc116b19a 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -37,6 +37,7 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	const struct mlx5_ib_profile *profile;
 	struct mlx5_core_dev *peer_dev;
 	struct mlx5_ib_dev *ibdev;
+	int second_uplink = false;
 	u32 peer_num_ports;
 	int vport_index;
 	int ret;
@@ -47,17 +48,24 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 		peer_dev = mlx5_lag_get_peer_mdev(dev);
 		peer_num_ports = mlx5_eswitch_get_total_vports(peer_dev);
 		if (mlx5_lag_is_master(dev)) {
-			/* Only 1 ib port is the representor for both uplinks */
-			num_ports += peer_num_ports - 1;
+			if (mlx5_lag_is_mpesw(dev))
+				num_ports += peer_num_ports;
+			else
+				num_ports += peer_num_ports - 1;
+
 		} else {
-			if (rep->vport == MLX5_VPORT_UPLINK)
-				return 0;
+			if (rep->vport == MLX5_VPORT_UPLINK) {
+				if (!mlx5_lag_is_mpesw(dev))
+					return 0;
+				second_uplink = true;
+			}
+
 			vport_index += peer_num_ports;
 			dev = peer_dev;
 		}
 	}
 
-	if (rep->vport == MLX5_VPORT_UPLINK)
+	if (rep->vport == MLX5_VPORT_UPLINK && !second_uplink)
 		profile = &raw_eth_profile;
 	else
 		return mlx5_ib_set_vport_rep(dev, rep, vport_index);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c669ef6e47e7..dc32e4518a28 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -3012,26 +3012,63 @@ static void mlx5_eth_lag_cleanup(struct mlx5_ib_dev *dev)
 	}
 }
 
-static int mlx5_add_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num)
+static void mlx5_netdev_notifier_register(struct mlx5_roce *roce,
+					  struct net_device *netdev)
 {
 	int err;
 
-	dev->port[port_num].roce.nb.notifier_call = mlx5_netdev_event;
-	err = register_netdevice_notifier(&dev->port[port_num].roce.nb);
-	if (err) {
-		dev->port[port_num].roce.nb.notifier_call = NULL;
-		return err;
-	}
+	if (roce->tracking_netdev)
+		return;
+	roce->tracking_netdev = netdev;
+	roce->nb.notifier_call = mlx5_netdev_event;
+	err = register_netdevice_notifier_dev_net(netdev, &roce->nb, &roce->nn);
+	WARN_ON(err);
+}
 
-	return 0;
+static void mlx5_netdev_notifier_unregister(struct mlx5_roce *roce)
+{
+	if (!roce->tracking_netdev)
+		return;
+	unregister_netdevice_notifier_dev_net(roce->tracking_netdev, &roce->nb,
+					      &roce->nn);
+	roce->tracking_netdev = NULL;
 }
 
-static void mlx5_remove_netdev_notifier(struct mlx5_ib_dev *dev, u32 port_num)
+static int mlx5e_mdev_notifier_event(struct notifier_block *nb,
+				     unsigned long event, void *data)
 {
-	if (dev->port[port_num].roce.nb.notifier_call) {
-		unregister_netdevice_notifier(&dev->port[port_num].roce.nb);
-		dev->port[port_num].roce.nb.notifier_call = NULL;
+	struct mlx5_roce *roce = container_of(nb, struct mlx5_roce, mdev_nb);
+	struct net_device *netdev = data;
+
+	switch (event) {
+	case MLX5_DRIVER_EVENT_UPLINK_NETDEV:
+		if (netdev)
+			mlx5_netdev_notifier_register(roce, netdev);
+		else
+			mlx5_netdev_notifier_unregister(roce);
+		break;
+	default:
+		return NOTIFY_DONE;
 	}
+
+	return NOTIFY_OK;
+}
+
+static void mlx5_mdev_netdev_track(struct mlx5_ib_dev *dev, u32 port_num)
+{
+	struct mlx5_roce *roce = &dev->port[port_num].roce;
+
+	roce->mdev_nb.notifier_call = mlx5e_mdev_notifier_event;
+	mlx5_blocking_notifier_register(dev->mdev, &roce->mdev_nb);
+	mlx5_core_uplink_netdev_event_replay(dev->mdev);
+}
+
+static void mlx5_mdev_netdev_untrack(struct mlx5_ib_dev *dev, u32 port_num)
+{
+	struct mlx5_roce *roce = &dev->port[port_num].roce;
+
+	mlx5_blocking_notifier_unregister(dev->mdev, &roce->mdev_nb);
+	mlx5_netdev_notifier_unregister(roce);
 }
 
 static int mlx5_enable_eth(struct mlx5_ib_dev *dev)
@@ -3138,7 +3175,7 @@ static void mlx5_ib_unbind_slave_port(struct mlx5_ib_dev *ibdev,
 	if (mpi->mdev_events.notifier_call)
 		mlx5_notifier_unregister(mpi->mdev, &mpi->mdev_events);
 	mpi->mdev_events.notifier_call = NULL;
-	mlx5_remove_netdev_notifier(ibdev, port_num);
+	mlx5_mdev_netdev_untrack(ibdev, port_num);
 	spin_lock(&port->mp.mpi_lock);
 
 	comps = mpi->mdev_refcnt;
@@ -3196,12 +3233,7 @@ static bool mlx5_ib_bind_slave_port(struct mlx5_ib_dev *ibdev,
 	if (err)
 		goto unbind;
 
-	err = mlx5_add_netdev_notifier(ibdev, port_num);
-	if (err) {
-		mlx5_ib_err(ibdev, "failed adding netdev notifier for port %u\n",
-			    port_num + 1);
-		goto unbind;
-	}
+	mlx5_mdev_netdev_track(ibdev, port_num);
 
 	mpi->mdev_events.notifier_call = mlx5_ib_event_slave_port;
 	mlx5_notifier_register(mpi->mdev, &mpi->mdev_events);
@@ -3909,9 +3941,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev)
 		port_num = mlx5_core_native_port_num(dev->mdev) - 1;
 
 		/* Register only for native ports */
-		err = mlx5_add_netdev_notifier(dev, port_num);
-		if (err)
-			return err;
+		mlx5_mdev_netdev_track(dev, port_num);
 
 		err = mlx5_enable_eth(dev);
 		if (err)
@@ -3920,7 +3950,7 @@ static int mlx5_ib_roce_init(struct mlx5_ib_dev *dev)
 
 	return 0;
 cleanup:
-	mlx5_remove_netdev_notifier(dev, port_num);
+	mlx5_mdev_netdev_untrack(dev, port_num);
 	return err;
 }
 
@@ -3938,7 +3968,7 @@ static void mlx5_ib_roce_cleanup(struct mlx5_ib_dev *dev)
 		mlx5_disable_eth(dev);
 
 		port_num = mlx5_core_native_port_num(dev->mdev) - 1;
-		mlx5_remove_netdev_notifier(dev, port_num);
+		mlx5_mdev_netdev_untrack(dev, port_num);
 	}
 }
 
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 8b91babdd4c0..7394e7f36ba7 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -832,6 +832,9 @@ struct mlx5_roce {
 	rwlock_t		netdev_lock;
 	struct net_device	*netdev;
 	struct notifier_block	nb;
+	struct netdev_net_notifier nn;
+	struct notifier_block	mdev_nb;
+	struct net_device	*tracking_netdev;
 	atomic_t		tx_port_affinity;
 	enum ib_port_state last_port_state;
 	struct mlx5_ib_dev	*dev;