From b6e0b6bebe0732d5cac51f0791f269d2413b8980 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 7 May 2020 09:32:53 +0300 Subject: net/mlx5: Fix fatal error handling during device load Currently, in case of fatal error during mlx5_load_one(), we cannot enter error state until mlx5_load_one() is finished, what can take several minutes until commands will get timeouts, because these commands can't be processed due to the fatal error. Fix it by setting dev->state as MLX5_DEVICE_STATE_INTERNAL_ERROR before requesting the lock. Fixes: c1d4d2e92ad6 ("net/mlx5: Avoid calling sleeping function by the health poll thread") Signed-off-by: Shay Drory Reviewed-by: Moshe Shemesh Signed-off-by: Saeed Mahameed --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (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 c0cfbab15fe9..b31f769d2df9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -192,15 +192,23 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev) void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force) { + bool err_detected = false; + + /* Mark the device as fatal in order to abort FW commands */ + if ((check_fatal_sensors(dev) || force) && + dev->state == MLX5_DEVICE_STATE_UP) { + dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; + err_detected = true; + } mutex_lock(&dev->intf_state_mutex); - if (dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) - goto unlock; + if (!err_detected && dev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) + goto unlock;/* a previous error is still being handled */ if (dev->state == MLX5_DEVICE_STATE_UNINITIALIZED) { dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; goto unlock; } - if (check_fatal_sensors(dev) || force) { + if (check_fatal_sensors(dev) || force) { /* protected state setting */ dev->state = MLX5_DEVICE_STATE_INTERNAL_ERROR; mlx5_cmd_flush(dev); } -- cgit