net/mlx5e: Don't attach netdev profile while handling internal error

As part of switchdev mode disablement, driver changes port netdevice
profile from uplink to nic. If this process is triggered by health
recovery flow (PCI reset, for ex.) profile attach would fail because all
fw commands aborted when internal error flag is set. As a result, nic
netdevice profile is not attached and driver fails to rollback to uplink
profile, which leave driver in broken state and cause crash later.

To handle broken state do netdevice profile initialization only instead
of full attachment and release mdev resources on driver suspend as
expected. Actual netdevice attachment is done during driver load.

Fixes: c4d7eb57687f ("net/mxl5e: Add change profile method")
Signed-off-by: Dmytro Linkin <dlinkin@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0235adcbc609063a72ac8eaf24509d983199006c..a07bbe9a61bef1b393943153c007be7a79cd15f6 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5833,8 +5833,8 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv)
 }
 
 static int
-mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
-                           const struct mlx5e_profile *new_profile, void *new_ppriv)
+mlx5e_netdev_init_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
+                         const struct mlx5e_profile *new_profile, void *new_ppriv)
 {
        struct mlx5e_priv *priv = netdev_priv(netdev);
        int err;
@@ -5850,6 +5850,25 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde
        err = new_profile->init(priv->mdev, priv->netdev);
        if (err)
                goto priv_cleanup;
+
+       return 0;
+
+priv_cleanup:
+       mlx5e_priv_cleanup(priv);
+       return err;
+}
+
+static int
+mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
+                           const struct mlx5e_profile *new_profile, void *new_ppriv)
+{
+       struct mlx5e_priv *priv = netdev_priv(netdev);
+       int err;
+
+       err = mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv);
+       if (err)
+               return err;
+
        err = mlx5e_attach_netdev(priv);
        if (err)
                goto profile_cleanup;
@@ -5857,7 +5876,6 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde
 
 profile_cleanup:
        new_profile->cleanup(priv);
-priv_cleanup:
        mlx5e_priv_cleanup(priv);
        return err;
 }
@@ -5876,6 +5894,12 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
        priv->profile->cleanup(priv);
        mlx5e_priv_cleanup(priv);
 
+       if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+               mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv);
+               set_bit(MLX5E_STATE_DESTROYING, &priv->state);
+               return -EIO;
+       }
+
        err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv);
        if (err) { /* roll back to original profile */
                netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err);
@@ -5937,8 +5961,11 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
        struct net_device *netdev = priv->netdev;
        struct mlx5_core_dev *mdev = priv->mdev;
 
-       if (!netif_device_present(netdev))
+       if (!netif_device_present(netdev)) {
+               if (test_bit(MLX5E_STATE_DESTROYING, &priv->state))
+                       mlx5e_destroy_mdev_resources(mdev);
                return -ENODEV;
+       }
 
        mlx5e_detach_netdev(priv);
        mlx5e_destroy_mdev_resources(mdev);