Merge branch 'mlxsw-Thermal-and-hwmon-extensions'

Ido Schimmel says:

====================
mlxsw: Thermal and hwmon extensions

This patchset from Vadim includes various enhancements to thermal and
hwmon code in mlxsw.

Patch #1 adds a thermal zone for each inter-connect device (gearbox).
These devices are present in SN3800 systems and code to expose their
temperature via hwmon was added in commit 2e265a8 ("mlxsw: core:
Extend hwmon interface with inter-connect temperature attributes").

Currently, there are multiple thermal zones in mlxsw and only a few
cooling devices. Patch #2 detects the hottest thermal zone and the
cooling devices are switched to follow its trends. RFC was sent last
month [1].

Patch #3 allows to read and report negative temperature of the sensors
mlxsw exposes via hwmon and thermal subsystems.

v2 (Andrew Lunn):
* In patch #3, replace '%u' with '%d' in mlxsw_hwmon_module_temp_show()

[1] https://patchwork.ozlabs.org/patch/1107161/
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

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

@@ -52,8 +52,7 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
 			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
 	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp;
-	int index;
+	int temp, index;
 	int err;
 
 	index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
@@ -65,7 +64,7 @@ static ssize_t mlxsw_hwmon_temp_show(struct device *dev,
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
-	return sprintf(buf, "%u\n", temp);
+	return sprintf(buf, "%d\n", temp);
 }
 
 static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
@@ -76,8 +75,7 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
 			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
 	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp_max;
-	int index;
+	int temp_max, index;
 	int err;
 
 	index = mlxsw_hwmon_get_attr_index(mlwsw_hwmon_attr->type_index,
@@ -89,7 +87,7 @@ static ssize_t mlxsw_hwmon_temp_max_show(struct device *dev,
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, NULL, &temp_max, NULL);
-	return sprintf(buf, "%u\n", temp_max);
+	return sprintf(buf, "%d\n", temp_max);
 }
 
 static ssize_t mlxsw_hwmon_temp_rst_store(struct device *dev,
@@ -215,8 +213,8 @@ static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev,
 			container_of(attr, struct mlxsw_hwmon_attr, dev_attr);
 	struct mlxsw_hwmon *mlxsw_hwmon = mlwsw_hwmon_attr->hwmon;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp;
 	u8 module;
+	int temp;
 	int err;
 
 	module = mlwsw_hwmon_attr->type_index - mlxsw_hwmon->sensor_count;
@@ -227,7 +225,7 @@ static ssize_t mlxsw_hwmon_module_temp_show(struct device *dev,
 		return err;
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
 
-	return sprintf(buf, "%u\n", temp);
+	return sprintf(buf, "%d\n", temp);
 }
 
 static ssize_t mlxsw_hwmon_module_temp_fault_show(struct device *dev,

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

@@ -23,6 +23,7 @@
 #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
+#define MLXSW_THERMAL_TEMP_SCORE_MAX	GENMASK(31, 0)
 #define MLXSW_THERMAL_MAX_STATE	10
 #define MLXSW_THERMAL_MAX_DUTY	255
 /* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values
@@ -98,7 +99,7 @@ struct mlxsw_thermal_module {
 	struct thermal_zone_device *tzdev;
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	enum thermal_device_mode mode;
-	int module;
+	int module; /* Module or gearbox number */
 };
 
 struct mlxsw_thermal {
@@ -111,6 +112,10 @@ struct mlxsw_thermal {
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	enum thermal_device_mode mode;
 	struct mlxsw_thermal_module *tz_module_arr;
+	struct mlxsw_thermal_module *tz_gearbox_arr;
+	u8 tz_gearbox_num;
+	unsigned int tz_highest_score;
+	struct thermal_zone_device *tz_highest_dev;
 };
 
 static inline u8 mlxsw_state_to_duty(int state)
@@ -195,6 +200,34 @@ mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
 	return 0;
 }
 
+static void mlxsw_thermal_tz_score_update(struct mlxsw_thermal *thermal,
+					  struct thermal_zone_device *tzdev,
+					  struct mlxsw_thermal_trip *trips,
+					  int temp)
+{
+	struct mlxsw_thermal_trip *trip = trips;
+	unsigned int score, delta, i, shift = 1;
+
+	/* Calculate thermal zone score, if temperature is above the critical
+	 * threshold score is set to MLXSW_THERMAL_TEMP_SCORE_MAX.
+	 */
+	score = MLXSW_THERMAL_TEMP_SCORE_MAX;
+	for (i = MLXSW_THERMAL_TEMP_TRIP_NORM; i < MLXSW_THERMAL_NUM_TRIPS;
+	     i++, trip++) {
+		if (temp < trip->temp) {
+			delta = DIV_ROUND_CLOSEST(temp, trip->temp - temp);
+			score = delta * shift;
+			break;
+		}
+		shift *= 256;
+	}
+
+	if (score > thermal->tz_highest_score) {
+		thermal->tz_highest_score = score;
+		thermal->tz_highest_dev = tzdev;
+	}
+}
+
 static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev,
 			      struct thermal_cooling_device *cdev)
 {
@@ -279,7 +312,7 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 	struct mlxsw_thermal *thermal = tzdev->devdata;
 	struct device *dev = thermal->bus_info->dev;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp;
+	int temp;
 	int err;
 
 	mlxsw_reg_mtmp_pack(mtmp_pl, 0, false, false);
@@ -290,8 +323,11 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 		return err;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	if (temp > 0)
+		mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
+					      temp);
 
-	*p_temp = (int) temp;
+	*p_temp = temp;
 	return 0;
 }
 
@@ -351,6 +387,22 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
 	return 0;
 }
 
+static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
+				   int trip, enum thermal_trend *trend)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	if (tzdev == thermal->tz_highest_dev)
+		return 1;
+
+	*trend = THERMAL_TREND_STABLE;
+	return 0;
+}
+
 static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.bind = mlxsw_thermal_bind,
 	.unbind = mlxsw_thermal_unbind,
@@ -362,6 +414,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.set_trip_temp	= mlxsw_thermal_set_trip_temp,
 	.get_trip_hyst	= mlxsw_thermal_get_trip_hyst,
 	.set_trip_hyst	= mlxsw_thermal_set_trip_hyst,
+	.get_trend	= mlxsw_thermal_trend_get,
 };
 
 static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev,
@@ -450,7 +503,7 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 	struct mlxsw_thermal *thermal = tz->parent;
 	struct device *dev = thermal->bus_info->dev;
 	char mtmp_pl[MLXSW_REG_MTMP_LEN];
-	unsigned int temp;
+	int temp;
 	int err;
 
 	/* Read module temperature. */
@@ -466,13 +519,15 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 		return 0;
 	}
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
-	*p_temp = (int) temp;
+	*p_temp = temp;
 
 	if (!temp)
 		return 0;
 
 	/* Update trip points. */
-	mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
+	err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
+	if (!err && temp > 0)
+		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
 
 	return 0;
 }
@@ -537,10 +592,6 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
 	return 0;
 }
 
-static struct thermal_zone_params mlxsw_thermal_module_params = {
-	.governor_name = "user_space",
-};
-
 static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
@@ -552,6 +603,46 @@ static struct thermal_zone_device_ops mlxsw_thermal_module_ops = {
 	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
 	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
 	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
+	.get_trend	= mlxsw_thermal_trend_get,
+};
+
+static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
+					  int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	char mtmp_pl[MLXSW_REG_MTMP_LEN];
+	u16 index;
+	int temp;
+	int err;
+
+	index = MLXSW_REG_MTMP_GBOX_INDEX_MIN + tz->module;
+	mlxsw_reg_mtmp_pack(mtmp_pl, index, false, false);
+
+	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtmp), mtmp_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL);
+	if (temp > 0)
+		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
+
+	*p_temp = temp;
+	return 0;
+}
+
+static struct thermal_zone_device_ops mlxsw_thermal_gearbox_ops = {
+	.bind		= mlxsw_thermal_module_bind,
+	.unbind		= mlxsw_thermal_module_unbind,
+	.get_mode	= mlxsw_thermal_module_mode_get,
+	.set_mode	= mlxsw_thermal_module_mode_set,
+	.get_temp	= mlxsw_thermal_gearbox_temp_get,
+	.get_trip_type	= mlxsw_thermal_module_trip_type_get,
+	.get_trip_temp	= mlxsw_thermal_module_trip_temp_get,
+	.set_trip_temp	= mlxsw_thermal_module_trip_temp_set,
+	.get_trip_hyst	= mlxsw_thermal_module_trip_hyst_get,
+	.set_trip_hyst	= mlxsw_thermal_module_trip_hyst_set,
+	.get_trend	= mlxsw_thermal_trend_get,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
@@ -667,13 +758,13 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
 							MLXSW_THERMAL_TRIP_MASK,
 							module_tz,
 							&mlxsw_thermal_module_ops,
-							&mlxsw_thermal_module_params,
-							0, 0);
+							NULL, 0, 0);
 	if (IS_ERR(module_tz->tzdev)) {
 		err = PTR_ERR(module_tz->tzdev);
 		return err;
 	}
 
+	module_tz->mode = THERMAL_DEVICE_ENABLED;
 	return 0;
 }
 
@@ -779,6 +870,92 @@ mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal)
 	kfree(thermal->tz_module_arr);
 }
 
+static int
+mlxsw_thermal_gearbox_tz_init(struct mlxsw_thermal_module *gearbox_tz)
+{
+	char tz_name[MLXSW_THERMAL_ZONE_MAX_NAME];
+
+	snprintf(tz_name, sizeof(tz_name), "mlxsw-gearbox%d",
+		 gearbox_tz->module + 1);
+	gearbox_tz->tzdev = thermal_zone_device_register(tz_name,
+						MLXSW_THERMAL_NUM_TRIPS,
+						MLXSW_THERMAL_TRIP_MASK,
+						gearbox_tz,
+						&mlxsw_thermal_gearbox_ops,
+						NULL, 0, 0);
+	if (IS_ERR(gearbox_tz->tzdev))
+		return PTR_ERR(gearbox_tz->tzdev);
+
+	gearbox_tz->mode = THERMAL_DEVICE_ENABLED;
+	return 0;
+}
+
+static void
+mlxsw_thermal_gearbox_tz_fini(struct mlxsw_thermal_module *gearbox_tz)
+{
+	thermal_zone_device_unregister(gearbox_tz->tzdev);
+}
+
+static int
+mlxsw_thermal_gearboxes_init(struct device *dev, struct mlxsw_core *core,
+			     struct mlxsw_thermal *thermal)
+{
+	struct mlxsw_thermal_module *gearbox_tz;
+	char mgpir_pl[MLXSW_REG_MGPIR_LEN];
+	int i;
+	int err;
+
+	if (!mlxsw_core_res_query_enabled(core))
+		return 0;
+
+	mlxsw_reg_mgpir_pack(mgpir_pl);
+	err = mlxsw_reg_query(core, MLXSW_REG(mgpir), mgpir_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mgpir_unpack(mgpir_pl, &thermal->tz_gearbox_num, NULL, NULL);
+	if (!thermal->tz_gearbox_num)
+		return 0;
+
+	thermal->tz_gearbox_arr = kcalloc(thermal->tz_gearbox_num,
+					  sizeof(*thermal->tz_gearbox_arr),
+					  GFP_KERNEL);
+	if (!thermal->tz_gearbox_arr)
+		return -ENOMEM;
+
+	for (i = 0; i < thermal->tz_gearbox_num; i++) {
+		gearbox_tz = &thermal->tz_gearbox_arr[i];
+		memcpy(gearbox_tz->trips, default_thermal_trips,
+		       sizeof(thermal->trips));
+		gearbox_tz->module = i;
+		gearbox_tz->parent = thermal;
+		err = mlxsw_thermal_gearbox_tz_init(gearbox_tz);
+		if (err)
+			goto err_unreg_tz_gearbox;
+	}
+
+	return 0;
+
+err_unreg_tz_gearbox:
+	for (i--; i >= 0; i--)
+		mlxsw_thermal_gearbox_tz_fini(&thermal->tz_gearbox_arr[i]);
+	kfree(thermal->tz_gearbox_arr);
+	return err;
+}
+
+static void
+mlxsw_thermal_gearboxes_fini(struct mlxsw_thermal *thermal)
+{
+	int i;
+
+	if (!mlxsw_core_res_query_enabled(thermal->core))
+		return;
+
+	for (i = thermal->tz_gearbox_num - 1; i >= 0; i--)
+		mlxsw_thermal_gearbox_tz_fini(&thermal->tz_gearbox_arr[i]);
+	kfree(thermal->tz_gearbox_arr);
+}
+
 int mlxsw_thermal_init(struct mlxsw_core *core,
 		       const struct mlxsw_bus_info *bus_info,
 		       struct mlxsw_thermal **p_thermal)
@@ -869,10 +1046,16 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 	if (err)
 		goto err_unreg_tzdev;
 
+	err = mlxsw_thermal_gearboxes_init(dev, core, thermal);
+	if (err)
+		goto err_unreg_modules_tzdev;
+
 	thermal->mode = THERMAL_DEVICE_ENABLED;
 	*p_thermal = thermal;
 	return 0;
 
+err_unreg_modules_tzdev:
+	mlxsw_thermal_modules_fini(thermal);
 err_unreg_tzdev:
 	if (thermal->tzdev) {
 		thermal_zone_device_unregister(thermal->tzdev);
@@ -891,6 +1074,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 {
 	int i;
 
+	mlxsw_thermal_gearboxes_fini(thermal);
 	mlxsw_thermal_modules_fini(thermal);
 	if (thermal->tzdev) {
 		thermal_zone_device_unregister(thermal->tzdev);