0 Replies Latest reply on Jul 31, 2018 4:05 AM by vivienne

    why not just BUG_ON(!pci_channel_offline(dev->persist->pdev))

    vivienne

      diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c

      index 715de8a..e866082 100644

      --- a/drivers/net/ethernet/mellanox/mlx4/catas.c

      +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c

      @@ -182,10 +182,17 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)

             err = mlx4_reset_slave(dev);

        else

             err = mlx4_reset_master(dev);

      - BUG_ON(err != 0);

      +

      + if (!err)

      +      mlx4_err(dev, "device was reset successfully\n");

      + else

      +      /* EEH could have disabled the PCI channel during reset. That's

      +      * recoverable and the PCI error flow will handle it.

      +      */

      +      if (!pci_channel_offline(dev->persist->pdev))

      +           BUG_ON(1);

       

        dev->persist->state |= MLX4_DEVICE_STATE_INTERNAL_ERROR;

      - mlx4_err(dev, "device was reset successfully\n");

        mutex_unlock(&persist->device_state_mutex);