From: Saeed Mahameed Date: Thu, 8 Jan 2026 21:26:55 +0000 (-0800) Subject: net/mlx5e: Don't store mlx5e_priv in mlx5e_dev devlink priv X-Git-Tag: v6.19-rc6~34^2~13^2~2 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=123eda2e5b1638e298e3a66bb1e64a8da92de5e1;p=thirdparty%2Flinux.git net/mlx5e: Don't store mlx5e_priv in mlx5e_dev devlink priv mlx5e_priv is an unstable structure that can be memset(0) if profile attaching fails, mlx5e_priv in mlx5e_dev devlink private is used to reference the netdev and mdev associated with that struct. Instead, store netdev directly into mlx5e_dev and get mdev from the containing mlx5_adev aux device structure. 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: 0000000000000520 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: Oops: 0000 [#1] SMP NOPTI CPU: 3 UID: 0 PID: 521 Comm: devlink Not tainted 6.18.0-rc5+ #117 PREEMPT(voluntary) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014 RIP: 0010:mlx5e_remove+0x68/0x130 RSP: 0018:ffffc900034838f0 EFLAGS: 00010246 RAX: ffff88810283c380 RBX: ffff888101874400 RCX: ffffffff826ffc45 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000000 RBP: ffff888102d789c0 R08: ffff8881007137f0 R09: ffff888100264e10 R10: ffffc90003483898 R11: ffffc900034838a0 R12: ffff888100d261a0 R13: ffff888100d261a0 R14: ffff8881018749a0 R15: ffff888101874400 FS: 00007f8565fea740(0000) GS:ffff88856a759000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000520 CR3: 000000010b11a004 CR4: 0000000000370ef0 Call Trace: 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: ee75f1fc44dd ("net/mlx5e: Create separate devlink instance for ethernet auxiliary device") Fixes: c4d7eb57687f ("net/mxl5e: Add change profile method") Signed-off-by: Saeed Mahameed Link: https://patch.msgid.link/20260108212657.25090-3-saeed@kernel.org Signed-off-by: Jakub Kicinski --- diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index f42256768700..be52c30c2ad6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -962,7 +962,7 @@ struct mlx5e_priv { }; struct mlx5e_dev { - struct mlx5e_priv *priv; + struct net_device *netdev; struct devlink_port dl_port; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index e50525b771bc..9f8d95f8915e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6655,8 +6655,8 @@ static int _mlx5e_resume(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos, *to; int err, i; @@ -6702,10 +6702,11 @@ static int mlx5e_resume(struct auxiliary_device *adev) static int _mlx5e_suspend(struct auxiliary_device *adev, bool pre_netdev_reg) { + struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; - struct net_device *netdev = priv->netdev; - struct mlx5_core_dev *mdev = priv->mdev; + struct mlx5e_priv *priv = netdev_priv(mlx5e_dev->netdev); + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5_core_dev *mdev = edev->mdev; struct mlx5_core_dev *pos; int i; @@ -6766,11 +6767,11 @@ static int _mlx5e_probe(struct auxiliary_device *adev) goto err_devlink_port_unregister; } SET_NETDEV_DEVLINK_PORT(netdev, &mlx5e_dev->dl_port); + mlx5e_dev->netdev = netdev; mlx5e_build_nic_netdev(netdev); priv = netdev_priv(netdev); - mlx5e_dev->priv = priv; priv->profile = profile; priv->ppriv = NULL; @@ -6833,7 +6834,8 @@ static void _mlx5e_remove(struct auxiliary_device *adev) { struct mlx5_adev *edev = container_of(adev, struct mlx5_adev, adev); struct mlx5e_dev *mlx5e_dev = auxiliary_get_drvdata(adev); - struct mlx5e_priv *priv = mlx5e_dev->priv; + struct net_device *netdev = mlx5e_dev->netdev; + struct mlx5e_priv *priv = netdev_priv(netdev); struct mlx5_core_dev *mdev = edev->mdev; mlx5_core_uplink_netdev_set(mdev, NULL); @@ -6842,8 +6844,8 @@ static void _mlx5e_remove(struct auxiliary_device *adev) * if it's from legacy mode. If from switchdev mode, it * is already unregistered before changing to NIC profile. */ - if (priv->netdev->reg_state == NETREG_REGISTERED) { - unregister_netdev(priv->netdev); + if (netdev->reg_state == NETREG_REGISTERED) { + unregister_netdev(netdev); _mlx5e_suspend(adev, false); } else { struct mlx5_core_dev *pos;