This reverts commit 9d76931180557270796f9631e2c79b9c7bb3c9fb. Using unregister_netdev at shutdown flow prevents calling the netdev's ndos or trying to access its freed resources.
This fixes crashes like the following: Call Trace: [<ffffffff81587a6e>] dev_get_phys_port_id+0x1e/0x30 [<ffffffff815a36ce>] rtnl_fill_ifinfo+0x4be/0xff0 [<ffffffff815a53f3>] rtmsg_ifinfo_build_skb+0x73/0xe0 [<ffffffff815a5476>] rtmsg_ifinfo.part.27+0x16/0x50 [<ffffffff815a54c8>] rtmsg_ifinfo+0x18/0x20 [<ffffffff8158a6c6>] netdev_state_change+0x46/0x50 [<ffffffff815a5e78>] linkwatch_do_dev+0x38/0x50 [<ffffffff815a6165>] __linkwatch_run_queue+0xf5/0x170 [<ffffffff815a6205>] linkwatch_event+0x25/0x30 [<ffffffff81099a82>] process_one_work+0x152/0x400 [<ffffffff8109a325>] worker_thread+0x125/0x4b0 [<ffffffff8109a200>] ? rescuer_thread+0x350/0x350 [<ffffffff8109fc6a>] kthread+0xca/0xe0 [<ffffffff8109fba0>] ? kthread_park+0x60/0x60 [<ffffffff816a1285>] ret_from_fork+0x25/0x30 Fixes: 9d7693118055 ("net/mlx4_en: Avoid unregister_netdev at shutdown flow") Signed-off-by: Tariq Toukan <tar...@mellanox.com> Reported-by: Sebastian Ott <seb...@linux.vnet.ibm.com> Reported-by: Steve Wise <sw...@opengridcomputing.com> Cc: Jiri Pirko <j...@mellanox.com> --- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 17 ++--------------- drivers/net/ethernet/mellanox/mlx4/main.c | 5 +---- include/linux/mlx4/device.h | 1 - 3 files changed, 3 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index a60f635da78b..fb8bb027b69c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2079,13 +2079,6 @@ static int mlx4_en_alloc_resources(struct mlx4_en_priv *priv) return -ENOMEM; } -static void mlx4_en_shutdown(struct net_device *dev) -{ - rtnl_lock(); - netif_device_detach(dev); - mlx4_en_close(dev); - rtnl_unlock(); -} static int mlx4_en_copy_priv(struct mlx4_en_priv *dst, struct mlx4_en_priv *src, @@ -2162,8 +2155,6 @@ void mlx4_en_destroy_netdev(struct net_device *dev) { struct mlx4_en_priv *priv = netdev_priv(dev); struct mlx4_en_dev *mdev = priv->mdev; - bool shutdown = mdev->dev->persist->interface_state & - MLX4_INTERFACE_STATE_SHUTDOWN; en_dbg(DRV, priv, "Destroying netdev on port:%d\n", priv->port); @@ -2171,10 +2162,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) if (priv->registered) { devlink_port_type_clear(mlx4_get_devlink_port(mdev->dev, priv->port)); - if (shutdown) - mlx4_en_shutdown(dev); - else - unregister_netdev(dev); + unregister_netdev(dev); } if (priv->allocated) @@ -2203,8 +2191,7 @@ void mlx4_en_destroy_netdev(struct net_device *dev) kfree(priv->tx_ring); kfree(priv->tx_cq); - if (!shutdown) - free_netdev(dev); + free_netdev(dev); } static int mlx4_en_change_mtu(struct net_device *dev, int new_mtu) diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 6f4e67bc3538..75d07fa9d0b1 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4147,11 +4147,8 @@ static void mlx4_shutdown(struct pci_dev *pdev) mlx4_info(persist->dev, "mlx4_shutdown was called\n"); mutex_lock(&persist->interface_state_mutex); - if (persist->interface_state & MLX4_INTERFACE_STATE_UP) { - /* Notify mlx4 clients that the kernel is being shut down */ - persist->interface_state |= MLX4_INTERFACE_STATE_SHUTDOWN; + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) mlx4_unload_one(pdev); - } mutex_unlock(&persist->interface_state_mutex); } diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 3be7abd6e722..c9f379689dd0 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -476,7 +476,6 @@ enum { enum { MLX4_INTERFACE_STATE_UP = 1 << 0, MLX4_INTERFACE_STATE_DELETION = 1 << 1, - MLX4_INTERFACE_STATE_SHUTDOWN = 1 << 2, }; #define MSTR_SM_CHANGE_MASK (MLX4_EQ_PORT_INFO_MSTR_SM_SL_CHANGE_MASK | \ -- 1.8.3.1