[Mellanox] Backport patch to remove critical trip point from thermal zones (#201)

1. 0027-mlxsw-core-Remove-critical-trip-point-from-thermal-z.patch

    Disable software thermal protection by removing critical trip points
    for the all thermal zones.

    According to the system requirements software should never perform
    system thermal protection, since all the systems implement two levels
    of thermal protection: the first one is performed by firmware, the
    second, in case firmware was not able to perform protection, by
    hardware, while the temperature threshold for hardware protection is
    higher than for firmware.

    In both cases, when critical temperature is reached, system will be
    shutdown.

    Signed-off-by: Vadim Pasternak <[email protected]>

It has been verified on Mellanox devices

Signed-off-by: Stephen Sun <[email protected]>

Author: stephenxs

patch/0027-mlxsw-core-Remove-critical-trip-point-from-thermal-z.patch

@@ -0,0 +1,105 @@
+From 97a18fe05a59a76513ea4e11560760d0450e6f6c Mon Sep 17 00:00:00 2001
+From: Vadim Pasternak <[email protected]>
+Date: Sun, 10 Jan 2021 19:27:52 +0200
+Subject: [PATCH net-next 1/1] mlxsw: core: Remove critical trip point from
+ thermal zones
+
+Disable software thermal protection by removing critical trip points
+for the all thermal zones.
+
+According to the system requirements software should never perform
+system thermal protection, since all the systems implement two levels
+of thermal protection: the first one is performed by firmware, the
+second, in case firmware was not able to perform protection, by
+hardware, while the temperature threshold for hardware protection is
+higher than for firmware.
+
+In both cases, when critical temperature is reached, system will be
+shutdown.
+
+Signed-off-by: Vadim Pasternak <[email protected]>
+---
+ drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 19 ++-----------------
+ 1 file changed, 2 insertions(+), 17 deletions(-)
+
+diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+index 477c3ed53..9afac8a04 100644
+--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
++++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+@@ -19,11 +19,9 @@
+ #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	140000	/* 140C */
+ #define MLXSW_THERMAL_MODULE_TEMP_NORM	60000	/* 60C */
+ #define MLXSW_THERMAL_MODULE_TEMP_HIGH	70000	/* 70C */
+ #define MLXSW_THERMAL_MODULE_TEMP_HOT	80000	/* 80C */
+-#define MLXSW_THERMAL_MODULE_TEMP_CRIT	90000	/* 90C */
+ #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
+@@ -49,7 +47,6 @@ enum mlxsw_thermal_trips {
+ 	MLXSW_THERMAL_TEMP_TRIP_NORM,
+ 	MLXSW_THERMAL_TEMP_TRIP_HIGH,
+ 	MLXSW_THERMAL_TEMP_TRIP_HOT,
+-	MLXSW_THERMAL_TEMP_TRIP_CRIT,
+ };
+ 
+ struct mlxsw_thermal_trip {
+@@ -79,16 +76,9 @@ static const struct mlxsw_thermal_trip default_thermal_trips[] = {
+ 	{	/* Warning */
+ 		.type		= THERMAL_TRIP_HOT,
+ 		.temp		= MLXSW_THERMAL_ASIC_TEMP_HOT,
+-		.hyst		= MLXSW_THERMAL_HYSTERESIS_TEMP,
+ 		.min_state	= MLXSW_THERMAL_MAX_STATE,
+ 		.max_state	= MLXSW_THERMAL_MAX_STATE,
+ 	},
+-	{	/* Critical - soft poweroff */
+-		.type		= THERMAL_TRIP_CRITICAL,
+-		.temp		= MLXSW_THERMAL_ASIC_TEMP_CRIT,
+-		.min_state	= MLXSW_THERMAL_MAX_STATE,
+-		.max_state	= MLXSW_THERMAL_MAX_STATE,
+-	}
+ };
+ 
+ #define MLXSW_THERMAL_NUM_TRIPS	ARRAY_SIZE(default_thermal_trips)
+@@ -161,7 +151,6 @@ mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz)
+ 	tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = MLXSW_THERMAL_MODULE_TEMP_NORM;
+ 	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = MLXSW_THERMAL_MODULE_TEMP_HIGH;
+ 	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = MLXSW_THERMAL_MODULE_TEMP_HOT;
+-	tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = MLXSW_THERMAL_MODULE_TEMP_CRIT;
+ }
+ 
+ static int
+@@ -203,8 +192,6 @@ 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;
+-	tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = emerg_temp +
+-					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
+ 
+ 	return 0;
+ }
+@@ -376,8 +363,7 @@ static int mlxsw_thermal_set_trip_temp(struct thermal_zone_device *tzdev,
+ {
+ 	struct mlxsw_thermal *thermal = tzdev->devdata;
+ 
+-	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS ||
+-	    temp > MLXSW_THERMAL_ASIC_TEMP_CRIT)
++	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+ 		return -EINVAL;
+ 
+ 	thermal->trips[trip].temp = temp;
+@@ -588,8 +574,7 @@ mlxsw_thermal_module_trip_temp_set(struct thermal_zone_device *tzdev,
+ {
+ 	struct mlxsw_thermal_module *tz = tzdev->devdata;
+ 
+-	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS ||
+-	    temp > tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp)
++	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+ 		return -EINVAL;
+ 
+ 	tz->trips[trip].temp = temp;
+-- 
+2.11.0
+

patch/series

@@ -76,6 +76,7 @@ driver-ixgbe-external-phy.patch
 0024-mlxsw-core-Fix-memory-leak-on-module-removal.patch
 0025-platform-x86-mlx-platform-Remove-PSU-EEPROM-configur.patch
 0026-platform-x86-mlx-platform-Remove-PSU-EEPROM-configur.patch
+0027-mlxsw-core-Remove-critical-trip-point-from-thermal-z.patch
 ############################################################
 #
 # Internal patches will be added below (placeholder)