mlxsw: core: Extend thermal module with per QSFP module thermal zones

Add a dedicated thermal zone for each QSFP/SFP module. The current
temperature is obtained from the module's temperature sensor and the
trip points are set based on the warning and critical thresholds
read from the module.

A cooling device (fan) is bound to all the thermal zones. The
thermal zone governor is set to user space in order to avoid
collisions between thermal zones.
For example, one thermal zone might want to increase the speed of
the fan, whereas another one would like to decrease it.

Deferring this decision to user space allows the user to the take
the most suitable decision.

Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 400 insertions, 0 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 821fef2e2230..0b85c7252f9e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -9,8 +9,10 @@
 #include <linux/sysfs.h>
 #include <linux/thermal.h>
 #include <linux/err.h>
+#include <linux/sfp.h>
 
 #include "core.h"
+#include "core_env.h"
 
 #define MLXSW_THERMAL_POLL_INT	1000	/* ms */
 #define MLXSW_THERMAL_SLOW_POLL_INT	20000	/* ms */
@@ -19,6 +21,8 @@
 #define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
 #define MLXSW_THERMAL_ASIC_TEMP_CRIT	110000	/* 110C */
 #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_MAX_STATE	10
 #define MLXSW_THERMAL_MAX_DUTY	255
 /* Minimum and maximum fan allowed speed in percent: from 20% to 100%. Values
@@ -36,6 +40,13 @@ static char * const mlxsw_thermal_external_allowed_cdev[] = {
 	"mlxreg_fan",
 };
 
+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 {
 	int	type;
 	int	temp;
@@ -80,6 +91,16 @@ static const struct mlxsw_thermal_trip default_thermal_trips[] = {
 /* Make sure all trips are writable */
 #define MLXSW_THERMAL_TRIP_MASK	(BIT(MLXSW_THERMAL_NUM_TRIPS) - 1)
 
+struct mlxsw_thermal;
+
+struct mlxsw_thermal_module {
+	struct mlxsw_thermal *parent;
+	struct thermal_zone_device *tzdev;
+	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
+	enum thermal_device_mode mode;
+	int module;
+};
+
 struct mlxsw_thermal {
 	struct mlxsw_core *core;
 	const struct mlxsw_bus_info *bus_info;
@@ -89,6 +110,8 @@ struct mlxsw_thermal {
 	u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	enum thermal_device_mode mode;
+	struct mlxsw_thermal_module *tz_module_arr;
+	unsigned int tz_module_num;
 };
 
 static inline u8 mlxsw_state_to_duty(int state)
@@ -122,6 +145,57 @@ static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal,
 	return -ENODEV;
 }
 
+static void
+mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz)
+{
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HIGH].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_HOT].temp = 0;
+	tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp = 0;
+}
+
+static int
+mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
+				  struct mlxsw_thermal_module *tz)
+{
+	int crit_temp, emerg_temp;
+	int err;
+
+	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+						   SFP_TEMP_HIGH_WARN,
+						   &crit_temp);
+	if (err)
+		return err;
+
+	err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+						   SFP_TEMP_HIGH_ALARM,
+						   &emerg_temp);
+	if (err)
+		return err;
+
+	/* 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"
+	 * and "hot" trip points, "normal" and "critical" trip points are
+	 * derived from "active" and "hot" by subtracting or adding double
+	 * hysteresis value.
+	 */
+	if (crit_temp >= MLXSW_THERMAL_MODULE_TEMP_SHIFT)
+		tz->trips[MLXSW_THERMAL_TEMP_TRIP_NORM].temp = crit_temp -
+					MLXSW_THERMAL_MODULE_TEMP_SHIFT;
+	else
+		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;
+}
+
 static int mlxsw_thermal_bind(struct thermal_zone_device *tzdev,
 			      struct thermal_cooling_device *cdev)
 {
@@ -291,6 +365,204 @@ static struct thermal_zone_device_ops mlxsw_thermal_ops = {
 	.set_trip_hyst	= mlxsw_thermal_set_trip_hyst,
 };
 
+static int mlxsw_thermal_module_bind(struct thermal_zone_device *tzdev,
+				     struct thermal_cooling_device *cdev)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	int i, j, err;
+
+	/* If the cooling device is one of ours bind it */
+	if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0)
+		return 0;
+
+	for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) {
+		const struct mlxsw_thermal_trip *trip = &tz->trips[i];
+
+		err = thermal_zone_bind_cooling_device(tzdev, i, cdev,
+						       trip->max_state,
+						       trip->min_state,
+						       THERMAL_WEIGHT_DEFAULT);
+		if (err < 0)
+			goto err_bind_cooling_device;
+	}
+	return 0;
+
+err_bind_cooling_device:
+	for (j = i - 1; j >= 0; j--)
+		thermal_zone_unbind_cooling_device(tzdev, j, cdev);
+	return err;
+}
+
+static int mlxsw_thermal_module_unbind(struct thermal_zone_device *tzdev,
+				       struct thermal_cooling_device *cdev)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	int i;
+	int err;
+
+	/* If the cooling device is one of ours unbind it */
+	if (mlxsw_get_cooling_device_idx(thermal, cdev) < 0)
+		return 0;
+
+	for (i = 0; i < MLXSW_THERMAL_NUM_TRIPS; i++) {
+		err = thermal_zone_unbind_cooling_device(tzdev, i, cdev);
+		WARN_ON(err);
+	}
+	return err;
+}
+
+static int mlxsw_thermal_module_mode_get(struct thermal_zone_device *tzdev,
+					 enum thermal_device_mode *mode)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	*mode = tz->mode;
+
+	return 0;
+}
+
+static int mlxsw_thermal_module_mode_set(struct thermal_zone_device *tzdev,
+					 enum thermal_device_mode mode)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+
+	mutex_lock(&tzdev->lock);
+
+	if (mode == THERMAL_DEVICE_ENABLED)
+		tzdev->polling_delay = thermal->polling_delay;
+	else
+		tzdev->polling_delay = 0;
+
+	mutex_unlock(&tzdev->lock);
+
+	tz->mode = mode;
+	thermal_zone_device_update(tzdev, THERMAL_EVENT_UNSPECIFIED);
+
+	return 0;
+}
+
+static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
+					 int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
+	struct device *dev = thermal->bus_info->dev;
+	char mtbr_pl[MLXSW_REG_MTBR_LEN];
+	u16 temp;
+	int err;
+
+	/* Read module temperature. */
+	mlxsw_reg_mtbr_pack(mtbr_pl, MLXSW_REG_MTBR_BASE_MODULE_INDEX +
+			    tz->module, 1);
+	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mtbr), mtbr_pl);
+	if (err)
+		return err;
+
+	mlxsw_reg_mtbr_temp_unpack(mtbr_pl, 0, &temp, NULL);
+	/* Update temperature. */
+	switch (temp) {
+	case MLXSW_REG_MTBR_NO_CONN: /* fall-through */
+	case MLXSW_REG_MTBR_NO_TEMP_SENS: /* fall-through */
+	case MLXSW_REG_MTBR_INDEX_NA: /* fall-through */
+	case MLXSW_REG_MTBR_BAD_SENS_INFO:
+		temp = 0;
+		break;
+	default:
+		temp = MLXSW_REG_MTMP_TEMP_TO_MC(temp);
+		/* Reset all trip point. */
+		mlxsw_thermal_module_trips_reset(tz);
+		/* Update trip points. */
+		err = mlxsw_thermal_module_trips_update(dev, thermal->core,
+							tz);
+		if (err)
+			return err;
+		break;
+	}
+
+	*p_temp = (int) temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_type_get(struct thermal_zone_device *tzdev, int trip,
+				   enum thermal_trip_type *p_type)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	*p_type = tz->trips[trip].type;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_temp_get(struct thermal_zone_device *tzdev,
+				   int trip, int *p_temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
+		return -EINVAL;
+
+	*p_temp = tz->trips[trip].temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_temp_set(struct thermal_zone_device *tzdev,
+				   int trip, int temp)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS ||
+	    temp > tz->trips[MLXSW_THERMAL_TEMP_TRIP_CRIT].temp)
+		return -EINVAL;
+
+	tz->trips[trip].temp = temp;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_hyst_get(struct thermal_zone_device *tzdev, int trip,
+				   int *p_hyst)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	*p_hyst = tz->trips[trip].hyst;
+	return 0;
+}
+
+static int
+mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
+				   int hyst)
+{
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+
+	tz->trips[trip].hyst = hyst;
+	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,
+	.get_mode	= mlxsw_thermal_module_mode_get,
+	.set_mode	= mlxsw_thermal_module_mode_set,
+	.get_temp	= mlxsw_thermal_module_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,
+};
+
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
 				       unsigned long *p_state)
 {
@@ -391,6 +663,123 @@ static const struct thermal_cooling_device_ops mlxsw_cooling_ops = {
 	.set_cur_state	= mlxsw_thermal_set_cur_state,
 };
 
+static int
+mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
+{
+	char tz_name[MLXSW_THERMAL_ZONE_MAX_NAME];
+	int err;
+
+	snprintf(tz_name, sizeof(tz_name), "mlxsw-module%d",
+		 module_tz->module + 1);
+	module_tz->tzdev = thermal_zone_device_register(tz_name,
+							MLXSW_THERMAL_NUM_TRIPS,
+							MLXSW_THERMAL_TRIP_MASK,
+							module_tz,
+							&mlxsw_thermal_module_ops,
+							&mlxsw_thermal_module_params,
+							0, 0);
+	if (IS_ERR(module_tz->tzdev)) {
+		err = PTR_ERR(module_tz->tzdev);
+		return err;
+	}
+
+	return 0;
+}
+
+static void mlxsw_thermal_module_tz_fini(struct thermal_zone_device *tzdev)
+{
+	thermal_zone_device_unregister(tzdev);
+}
+
+static int
+mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
+			  struct mlxsw_thermal *thermal, u8 local_port)
+{
+	struct mlxsw_thermal_module *module_tz;
+	char pmlp_pl[MLXSW_REG_PMLP_LEN];
+	u8 width, module;
+	int err;
+
+	mlxsw_reg_pmlp_pack(pmlp_pl, local_port);
+	err = mlxsw_reg_query(core, MLXSW_REG(pmlp), pmlp_pl);
+	if (err)
+		return err;
+
+	width = mlxsw_reg_pmlp_width_get(pmlp_pl);
+	if (!width)
+		return 0;
+
+	module = mlxsw_reg_pmlp_module_get(pmlp_pl, 0);
+	module_tz = &thermal->tz_module_arr[module];
+	module_tz->module = module;
+	module_tz->parent = thermal;
+	memcpy(module_tz->trips, default_thermal_trips,
+	       sizeof(thermal->trips));
+	/* Initialize all trip point. */
+	mlxsw_thermal_module_trips_reset(module_tz);
+	/* Update trip point according to the module data. */
+	err = mlxsw_thermal_module_trips_update(dev, core, module_tz);
+	if (err)
+		return err;
+
+	thermal->tz_module_num++;
+
+	return 0;
+}
+
+static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)
+{
+	if (module_tz && module_tz->tzdev) {
+		mlxsw_thermal_module_tz_fini(module_tz->tzdev);
+		module_tz->tzdev = NULL;
+	}
+}
+
+static int
+mlxsw_thermal_modules_init(struct device *dev, struct mlxsw_core *core,
+			   struct mlxsw_thermal *thermal)
+{
+	unsigned int module_count = mlxsw_core_max_ports(core);
+	int i, err;
+
+	thermal->tz_module_arr = kcalloc(module_count,
+					 sizeof(*thermal->tz_module_arr),
+					 GFP_KERNEL);
+	if (!thermal->tz_module_arr)
+		return -ENOMEM;
+
+	for (i = 1; i < module_count; i++) {
+		err = mlxsw_thermal_module_init(dev, core, thermal, i);
+		if (err)
+			goto err_unreg_tz_module_arr;
+	}
+
+	for (i = 0; i < thermal->tz_module_num; i++) {
+		err = mlxsw_thermal_module_tz_init(&thermal->tz_module_arr[i]);
+		if (err)
+			goto err_unreg_tz_module_arr;
+	}
+
+	return 0;
+
+err_unreg_tz_module_arr:
+	for (i = module_count - 1; i >= 0; i--)
+		mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]);
+	kfree(thermal->tz_module_arr);
+	return err;
+}
+
+static void
+mlxsw_thermal_modules_fini(struct mlxsw_thermal *thermal)
+{
+	unsigned int module_count = mlxsw_core_max_ports(thermal->core);
+	int i;
+
+	for (i = module_count - 1; i >= 0; i--)
+		mlxsw_thermal_module_fini(&thermal->tz_module_arr[i]);
+	kfree(thermal->tz_module_arr);
+}
+
 int mlxsw_thermal_init(struct mlxsw_core *core,
 		       const struct mlxsw_bus_info *bus_info,
 		       struct mlxsw_thermal **p_thermal)
@@ -477,9 +866,19 @@ int mlxsw_thermal_init(struct mlxsw_core *core,
 		goto err_unreg_cdevs;
 	}
 
+	err = mlxsw_thermal_modules_init(dev, core, thermal);
+	if (err)
+		goto err_unreg_tzdev;
+
 	thermal->mode = THERMAL_DEVICE_ENABLED;
 	*p_thermal = thermal;
 	return 0;
+
+err_unreg_tzdev:
+	if (thermal->tzdev) {
+		thermal_zone_device_unregister(thermal->tzdev);
+		thermal->tzdev = NULL;
+	}
 err_unreg_cdevs:
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
 		if (thermal->cdevs[i])
@@ -493,6 +892,7 @@ void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 {
 	int i;
 
+	mlxsw_thermal_modules_fini(thermal);
 	if (thermal->tzdev) {
 		thermal_zone_device_unregister(thermal->tzdev);
 		thermal->tzdev = NULL;