From: Shay Drory <shayd@xxxxxxxxxxxx>
[ Upstream commit b6e0b6bebe0732d5cac51f0791f269d2413b8980 ]
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 <shayd@xxxxxxxxxxxx>
Reviewed-by: Moshe Shemesh <moshe@xxxxxxxxxxxx>
Signed-off-by: Saeed Mahameed <saeedm@xxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/net/ethernet/mellanox/mlx5/core/health.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -193,15 +193,23 @@ static bool reset_fw_if_needed(struct ml
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);
}
