Merge branch 'mlxsw-core-thermal-control-fixes'

Ido Schimmel says:

====================
mlxsw: core: Thermal control fixes

This series includes two fixes for thermal control in mlxsw.

Patch #1 validates that the alarm temperature threshold read from a
transceiver is above the warning temperature threshold. If not, the
current thresholds are maintained. It was observed that some transceiver
might be unreliable and sometimes report a too low alarm temperature
threshold which would result in thermal shutdown of the system.

Patch #2 increases the temperature threshold above which thermal
shutdown is triggered for the ASIC thermal zone. It is currently too low
and might result in thermal shutdown under perfectly fine operational
conditions.
====================

Link: https://lore.kernel.org/r/20210108145210.1229820-1-idosch@idosch.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

drivers/net/ethernet/mellanox/mlxsw/core_thermal.c

@@ -19,7 +19,7 @@
 #define MLXSW_THERMAL_ASIC_TEMP_NORM	75000	/* 75C */
 #define MLXSW_THERMAL_ASIC_TEMP_HIGH	85000	/* 85C */
 #define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
-#define MLXSW_THERMAL_ASIC_TEMP_CRIT	110000	/* 110C */
+#define MLXSW_THERMAL_ASIC_TEMP_CRIT	140000	/* 140C */
 #define MLXSW_THERMAL_HYSTERESIS_TEMP	5000	/* 5C */
 #define MLXSW_THERMAL_MODULE_TEMP_SHIFT	(MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
 #define MLXSW_THERMAL_ZONE_MAX_NAME	16
@@ -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 +
 					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
-	else
-		tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp;
 
 	return 0;
 }