From 57726ebe2733891c9f59105eff028735f73d05fb Mon Sep 17 00:00:00 2001 From: Vadim Pasternak Date: Fri, 8 Jan 2021 16:52:09 +0200 Subject: mlxsw: core: Add validation of transceiver temperature thresholds Validate thresholds to avoid a single failure due to some transceiver unreliability. Ignore the last readouts in case warning temperature is above alarm temperature, since it can cause unexpected thermal shutdown. Stay with the previous values and refresh threshold within the next iteration. This is a rare scenario, but it was observed at a customer site. Fixes: 6a79507cfe94 ("mlxsw: core: Extend thermal module with per QSFP module thermal zones") Signed-off-by: Vadim Pasternak Reviewed-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'drivers/net') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c index 8fa286ccdd6b..250a85049697 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c @@ -176,6 +176,12 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core, if (err) return err; + if (crit_temp > emerg_temp) { + dev_warn(dev, "%s : Critical threshold %d is above emergency threshold %d\n", + tz->tzdev->type, crit_temp, emerg_temp); + return 0; + } + /* According to the system thermal requirements, the thermal zones are * defined with four trip points. The critical and emergency * temperature thresholds, provided by QSFP module are set as "active" @@ -190,11 +196,8 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core, tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp; tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = crit_temp; tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = emerg_temp; - if (emerg_temp > crit_temp) - tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp + + tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp + MLXSW_THERMAL_MODULE_TEMP_SHIFT; - else - tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp; return 0; } -- cgit v1.2.3