RDMA/mlx5: Use IB set_netdev and get_netdev functions

The IB layer provides a common interface to store and get net
devices associated to an IB device port (ib_device_set_netdev()
and ib_device_get_netdev()).
Previously, mlx5_ib stored and managed the associated net devices
internally.

Replace internal net device management in mlx5_ib with
ib_device_set_netdev() when attaching/detaching  a net device and
ib_device_get_netdev() when retrieving the net device.

Export ib_device_get_netdev().

For mlx5 representors/PFs/VFs and lag creation we replace the netdev
assignments with the IB set/get netdev functions.

In active-backup mode lag the active slave net device is stored in the
lag itself. To assure the net device stored in a lag bond IB device is
the active slave we implement the following:
- mlx5_core: when modifying the slave of a bond we send the internal driver event
  MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE.
- mlx5_ib: when catching the event call ib_device_set_netdev()

This patch also ensures the correct IB events are sent in switchdev lag.

While at it, when in multiport eswitch mode, only a single IB device is
created for all ports. The said IB device will receive all netdev events
of its VFs once loaded, thus to avoid overwriting the mapping of PF IB
device to PF netdev, ignore NETDEV_REGISTER events if the ib device has
already been mapped to a netdev.

Signed-off-by: Chiara Meiohas <cmeiohas@nvidia.com>
Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/20240909173025.30422-6-michaelgur@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

1 files changed, 41 insertions, 35 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index cf8045b92689..8577db3308cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -445,6 +445,34 @@ static int _mlx5_modify_lag(struct mlx5_lag *ldev, u8 *ports)
 	return mlx5_cmd_modify_lag(dev0, ldev->ports, ports);
 }
 
+static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev *dev)
+{
+	struct net_device *ndev = NULL;
+	struct mlx5_lag *ldev;
+	unsigned long flags;
+	int i;
+
+	spin_lock_irqsave(&lag_lock, flags);
+	ldev = mlx5_lag_dev(dev);
+
+	if (!ldev)
+		goto unlock;
+
+	for (i = 0; i < ldev->ports; i++)
+		if (ldev->tracker.netdev_state[i].tx_enabled)
+			ndev = ldev->pf[i].netdev;
+	if (!ndev)
+		ndev = ldev->pf[ldev->ports - 1].netdev;
+
+	if (ndev)
+		dev_hold(ndev);
+
+unlock:
+	spin_unlock_irqrestore(&lag_lock, flags);
+
+	return ndev;
+}
+
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker)
 {
@@ -477,9 +505,18 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 		}
 	}
 
-	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP &&
-	    !(ldev->mode == MLX5_LAG_MODE_ROCE))
-		mlx5_lag_drop_rule_setup(ldev, tracker);
+	if (tracker->tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
+		struct net_device *ndev = mlx5_lag_active_backup_get_netdev(dev0);
+
+		if(!(ldev->mode == MLX5_LAG_MODE_ROCE))
+			mlx5_lag_drop_rule_setup(ldev, tracker);
+		/** Only sriov and roce lag should have tracker->tx_type set so
+		 *  no need to check the mode
+		 */
+		blocking_notifier_call_chain(&dev0->priv.lag_nh,
+					     MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE,
+					     ndev);
+	}
 }
 
 static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
@@ -613,6 +650,7 @@ static int mlx5_create_lag(struct mlx5_lag *ldev,
 			mlx5_core_err(dev0,
 				      "Failed to deactivate RoCE LAG; driver restart required\n");
 	}
+	BLOCKING_INIT_NOTIFIER_HEAD(&dev0->priv.lag_nh);
 
 	return err;
 }
@@ -1492,38 +1530,6 @@ void mlx5_lag_enable_change(struct mlx5_core_dev *dev)
 	mlx5_queue_bond_work(ldev, 0);
 }
 
-struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev)
-{
-	struct net_device *ndev = NULL;
-	struct mlx5_lag *ldev;
-	unsigned long flags;
-	int i;
-
-	spin_lock_irqsave(&lag_lock, flags);
-	ldev = mlx5_lag_dev(dev);
-
-	if (!(ldev && __mlx5_lag_is_roce(ldev)))
-		goto unlock;
-
-	if (ldev->tracker.tx_type == NETDEV_LAG_TX_TYPE_ACTIVEBACKUP) {
-		for (i = 0; i < ldev->ports; i++)
-			if (ldev->tracker.netdev_state[i].tx_enabled)
-				ndev = ldev->pf[i].netdev;
-		if (!ndev)
-			ndev = ldev->pf[ldev->ports - 1].netdev;
-	} else {
-		ndev = ldev->pf[MLX5_LAG_P1].netdev;
-	}
-	if (ndev)
-		dev_hold(ndev);
-
-unlock:
-	spin_unlock_irqrestore(&lag_lock, flags);
-
-	return ndev;
-}
-EXPORT_SYMBOL(mlx5_lag_get_roce_netdev);
-
 u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 			   struct net_device *slave)
 {