From 8ce59b16b4b6eacedaec1f7b652b4781cdbfe15f Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Mon, 19 Jun 2017 18:25:59 +0300 Subject: net/mlx5: Fix driver load error flow when firmware is stuck When wait for firmware init fails, previous code would mistakenly return success and cause inconsistency in the driver state. Fixes: 6c780a0267b8 ("net/mlx5: Wait for FW readiness before initializing command interface") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index 13be264587f1..fd47b5134841 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1020,7 +1020,7 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, if (err) { dev_err(&dev->pdev->dev, "Firmware over %d MS in pre-initializing state, aborting\n", FW_PRE_INIT_TIMEOUT_MILI); - goto out; + goto out_err; } err = mlx5_cmd_init(dev); -- cgit v1.2.3 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 ++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- include/linux/mlx5/driver.h | 1 + 3 files changed, 16 insertions(+), 2 deletions(-) (limited to 'drivers') 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; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index fd47b5134841..524c16f72e83 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1228,7 +1228,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, int err = 0; if (cleanup) - mlx5_drain_health_wq(dev); + mlx5_drain_health_recovery(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 93273d9ea4d1..ba260330ce5e 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -925,6 +925,7 @@ int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); -- cgit v1.2.3 From 8ff93de7668bd81bc8efa819d1184ebd48fae72d Mon Sep 17 00:00:00 2001 From: Gal Pressman Date: Sun, 25 Jun 2017 16:46:25 +0300 Subject: net/mlx5e: Fix TX carrier errors report in get stats ndo Symbol error during carrier counter from PPCNT was mistakenly reported as TX carrier errors in get_stats ndo, although it's an RX counter. Fixes: 269e6b3af3bf ("net/mlx5e: Report additional error statistics in get stats ndo") Signed-off-by: Gal Pressman Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'drivers') diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 277f4de30375..7819fe9ede22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -3053,8 +3053,6 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats) PPORT_802_3_GET(pstats, a_frame_check_sequence_errors); stats->rx_frame_errors = PPORT_802_3_GET(pstats, a_alignment_errors); stats->tx_aborted_errors = PPORT_2863_GET(pstats, if_out_discards); - stats->tx_carrier_errors = - PPORT_802_3_GET(pstats, a_symbol_error_during_carrier); stats->rx_errors = stats->rx_length_errors + stats->rx_crc_errors + stats->rx_frame_errors; stats->tx_errors = stats->tx_aborted_errors + stats->tx_carrier_errors; -- cgit v1.2.3