From 2a0165a034ac024b60cca49c61e46f4afa2e4d98 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia Date: Thu, 30 Mar 2017 17:09:00 +0300 Subject: net/mlx5: Cancel delayed recovery work when unloading the driver Draining the health workqueue will ignore future health works including the one that report hardware failure and thus we can't enter error state Instead cancel the recovery flow and make sure only recovery flow won't be scheduled. Fixes: 5e44fca50470 ('net/mlx5: Only cancel recovery work when cleaning up device') Signed-off-by: Mohamad Haj Yahia Signed-off-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) (limited to 'drivers/net/ethernet/mellanox/mlx5/core/health.c') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index f27f84ffbc85..8a8b5f0e497c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -67,6 +67,7 @@ enum { enum { MLX5_DROP_NEW_HEALTH_WORK, + MLX5_DROP_NEW_RECOVERY_WORK, }; static u8 get_nic_state(struct mlx5_core_dev *dev) @@ -193,7 +194,7 @@ static void health_care(struct work_struct *work) mlx5_handle_bad_state(dev); spin_lock(&health->wq_lock); - if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) + if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags)) schedule_delayed_work(&health->recover_work, recover_delay); else dev_err(&dev->pdev->dev, @@ -313,6 +314,7 @@ void mlx5_start_health_poll(struct mlx5_core_dev *dev) init_timer(&health->timer); health->sick = 0; clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -335,11 +337,22 @@ void mlx5_drain_health_wq(struct mlx5_core_dev *dev) spin_lock(&health->wq_lock); set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); spin_unlock(&health->wq_lock); cancel_delayed_work_sync(&health->recover_work); cancel_work_sync(&health->work); } +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + + spin_lock(&health->wq_lock); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock(&health->wq_lock); + cancel_delayed_work_sync(&dev->priv.health.recover_work); +} + void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; -- cgit v1.2.3