From: Alexei Lazar mlx5e_attach_netdev() sets rx_mode_active before calling init_rx(), so any init_rx() failure after mlx5e_create_flow_steering() has succeeded makes mlx5e_destroy_flow_steering() trip WARN_ON_ONCE(fs->rx_mode_active) in mlx5e_del_vlan_rules(). Hit in internal regression testing, so kthread creation failed with -EINTR: WARNING: CPU: 3 PID: 170 at drivers/net/ethernet/mellanox/mlx5/core/en_fs.c:564 mlx5e_del_vlan_rules+0x295/0x2b0 [mlx5_core] mlx5e_destroy_flow_steering+0x34/0xc0 [mlx5_core] mlx5e_init_nic_rx+0x137/0x200 [mlx5_core] mlx5e_attach_netdev+0x105/0x360 [mlx5_core] Fix it by creating NIC flow steering with rx_mode_active cleared and setting it only after profile->init_rx() succeeds. This also lets the internal error paths of mlx5e_create_flow_steering() destroy partially created steering without warning. The flag is set in mlx5e_attach_netdev() rather than mlx5e_init_nic_rx() so that non-NIC profiles, such as representors, also get it set after a detach/attach cycle. Fixes: 8c7353b6f716 ("net/mlx5e: Fix VLAN cleanup flow") Signed-off-by: Alexei Lazar Signed-off-by: Gal Pressman Reviewed-by: Shahar Shitrit Signed-off-by: Tariq Toukan --- .../net/ethernet/mellanox/mlx5/core/en_main.c | 23 ++++++++----------- 1 file changed, 9 insertions(+), 14 deletions(-) V2: - Rebased. - Updated commit message. V1: https://lore.kernel.org/all/20261026072253.4118892-1-tariqt@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 72bca10c579d..990d2fa6a914 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -6041,9 +6041,7 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, priv->dfs_root = debugfs_create_dir("nic", mlx5_debugfs_get_dev_root(mdev)); - fs = mlx5e_fs_init(priv->profile, mdev, - !test_bit(MLX5E_STATE_DESTROYING, &priv->state), - priv->dfs_root); + fs = mlx5e_fs_init(priv->profile, mdev, false, priv->dfs_root); if (!fs) { err = -ENOMEM; mlx5_core_err(mdev, "FS initialization failed, %d\n", err); @@ -6558,10 +6556,6 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) int err; clear_bit(MLX5E_STATE_DESTROYING, &priv->state); - if (priv->fs) - mlx5e_fs_set_rx_mode_active(priv->fs, - !test_bit(MLX5E_STATE_DESTROYING, - &priv->state)); /* Validate the max_wqe_size_sq capability. */ if (WARN_ON_ONCE(mlx5e_get_max_sq_wqebbs(priv->mdev) < MLX5E_MAX_TX_WQEBBS)) { @@ -6622,6 +6616,9 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) if (err) goto err_cleanup_tx; + if (priv->fs) + mlx5e_fs_set_rx_mode_active(priv->fs, true); + if (profile->enable) { err = profile->enable(priv); if (err) @@ -6633,6 +6630,10 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) return 0; err_cleanup_rx: + if (priv->fs) { + mlx5e_fs_set_rx_mode_active(priv->fs, false); + cancel_work_sync(&priv->set_rx_mode_work); + } profile->cleanup_rx(priv); err_cleanup_tx: profile->cleanup_tx(priv); @@ -6640,10 +6641,6 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv) out: mlx5e_reset_channels(priv->netdev); set_bit(MLX5E_STATE_DESTROYING, &priv->state); - if (priv->fs) - mlx5e_fs_set_rx_mode_active(priv->fs, - !test_bit(MLX5E_STATE_DESTROYING, - &priv->state)); cancel_work_sync(&priv->update_stats_work); return err; } @@ -6654,9 +6651,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv) set_bit(MLX5E_STATE_DESTROYING, &priv->state); if (priv->fs) - mlx5e_fs_set_rx_mode_active(priv->fs, - !test_bit(MLX5E_STATE_DESTROYING, - &priv->state)); + mlx5e_fs_set_rx_mode_active(priv->fs, false); if (profile->disable) profile->disable(priv); base-commit: b71c101bbb9814d163c00234d43c41f0a17907d4 -- 2.44.0