From: Saeed Mahameed mlx5e_priv is an unstable structure that can be memset(0) if profile attaching fails. Pass netdev to mlx5e_destroy_netdev() to guarantee it will work on a valid netdev. On mlx5e_remove: Check validity of priv->profile, before attempting to cleanup any resources that might be not there. This fixes a kernel oops in mlx5e_remove when switchdev mode fails due to change profile failure. $ devlink dev eswitch set pci/0000:00:03.0 mode switchdev Error: mlx5_core: Failed setting eswitch to offloads. dmesg: workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: new profile init failed, -12 workqueue: Failed to create a rescuer kthread for wq "mlx5e": -EINTR mlx5_core 0012:03:00.1: mlx5e_netdev_init_profile:6214:(pid 37199): mlx5e_priv_init failed, err=-12 mlx5_core 0012:03:00.1 gpu3rdma1: mlx5e_netdev_change_profile: failed to rollback to orig profile, -12 $ devlink dev reload pci/0000:00:03.0 ==> oops BUG: kernel NULL pointer dereference, address: 0000000000000370 PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 15 UID: 0 PID: 520 Comm: devlink Not tainted 6.18.0-rc5+ #115 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:mlx5e_dcbnl_dscp_app+0x23/0x100 RSP: 0018:ffffc9000083f8b8 EFLAGS: 00010286 RAX: ffff8881126fc380 RBX: ffff8881015ac400 RCX: ffffffff826ffc45 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8881035109c0 RBP: ffff8881035109c0 R08: ffff888101e3e838 R09: ffff888100264e10 R10: ffffc9000083f898 R11: ffffc9000083f8a0 R12: ffff888101b921a0 R13: ffff888101b921a0 R14: ffff8881015ac9a0 R15: ffff8881015ac400 FS: 00007f789a3c8740(0000) GS:ffff88856aa59000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000370 CR3: 000000010b6c0001 CR4: 0000000000370ef0 Call Trace: mlx5e_remove+0x57/0x110 device_release_driver_internal+0x19c/0x200 bus_remove_device+0xc6/0x130 device_del+0x160/0x3d0 ? devl_param_driverinit_value_get+0x2d/0x90 mlx5_detach_device+0x89/0xe0 mlx5_unload_one_devl_locked+0x3a/0x70 mlx5_devlink_reload_down+0xc8/0x220 devlink_reload+0x7d/0x260 devlink_nl_reload_doit+0x45b/0x5a0 genl_family_rcv_msg_doit+0xe8/0x140 Fixes: c4d7eb57687f ("net/mxl5e: Add change profile method") Signed-off-by: Saeed Mahameed Reviewed-by: Shay Drori Reviewed-by: Tariq Toukan --- drivers/net/ethernet/mellanox/mlx5/core/en.h | 2 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++------ drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 4 ++-- 3 files changed, 12 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index be52c30c2ad6..ff4ab4691baf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -1242,7 +1242,7 @@ struct net_device * mlx5e_create_netdev(struct mlx5_core_dev *mdev, const struct mlx5e_profile *profile); int mlx5e_attach_netdev(struct mlx5e_priv *priv); void mlx5e_detach_netdev(struct mlx5e_priv *priv); -void mlx5e_destroy_netdev(struct mlx5e_priv *priv); +void mlx5e_destroy_netdev(struct net_device *netdev); int mlx5e_netdev_change_profile(struct net_device *netdev, struct mlx5_core_dev *mdev, const struct mlx5e_profile *new_profile, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9f8d95f8915e..2c06a4abea04 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6643,11 +6643,12 @@ void mlx5e_netdev_attach_nic_profile(struct net_device *netdev, mlx5e_netdev_change_profile(netdev, mdev, &mlx5e_nic_profile, NULL); } -void mlx5e_destroy_netdev(struct mlx5e_priv *priv) +void mlx5e_destroy_netdev(struct net_device *netdev) { - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); - mlx5e_priv_cleanup(priv); + if (priv->profile) + mlx5e_priv_cleanup(priv); free_netdev(netdev); } @@ -6804,7 +6805,7 @@ static int _mlx5e_probe(struct auxiliary_device *adev) err_profile_cleanup: profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); err_devlink_port_unregister: mlx5e_devlink_port_unregister(mlx5e_dev); err_devlink_unregister: @@ -6839,7 +6840,9 @@ static void _mlx5e_remove(struct auxiliary_device *adev) struct mlx5_core_dev *mdev = edev->mdev; mlx5_core_uplink_netdev_set(mdev, NULL); - mlx5e_dcbnl_delete_app(priv); + + if (priv->profile) + mlx5e_dcbnl_delete_app(priv); /* When unload driver, the netdev is in registered state * if it's from legacy mode. If from switchdev mode, it * is already unregistered before changing to NIC profile. @@ -6860,7 +6863,7 @@ static void _mlx5e_remove(struct auxiliary_device *adev) /* Avoid cleanup if profile rollback failed. */ if (priv->profile) priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); mlx5e_devlink_port_unregister(mlx5e_dev); mlx5e_destroy_devlink(mlx5e_dev); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 52d3ad0b9cd9..6eec88fa6d10 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1611,7 +1611,7 @@ mlx5e_vport_vf_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep) priv->profile->cleanup(priv); err_destroy_netdev: - mlx5e_destroy_netdev(netdev_priv(netdev)); + mlx5e_destroy_netdev(netdev); return err; } @@ -1666,7 +1666,7 @@ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep) mlx5e_rep_vnic_reporter_destroy(priv); mlx5e_detach_netdev(priv); priv->profile->cleanup(priv); - mlx5e_destroy_netdev(priv); + mlx5e_destroy_netdev(netdev); free_ppriv: kvfree(ppriv); /* mlx5e_rep_priv */ } -- 2.52.0