mlxsw: thermal: Read module temperature thresholds using MTMP register

mlxsw_thermal_module_trips_update() is used to update the trip points of
the module's thermal zone. Currently, this is done by querying the
thresholds from the module's EEPROM via MCIA register. This data does
not pass validation and in some cases can be unreliable. For example,
due to some problem with transceiver module.

Previous patch made it possible to read module's temperature and
thresholds via MTMP register. Therefore, extend
mlxsw_thermal_module_trips_update() to use the thresholds queried from
MTMP, if valid.

This is both more reliable and more efficient than current method, as
temperature and thresholds are queried in one transaction instead of
three. This is significant when working over a slow bus such as I2C.

Signed-off-by: Mykola Kostenok <c_mykolak@nvidia.com>
Acked-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 0983e4d4f88863fdf74c5271bd5631de155964ba..b96fb88aac0a0eb342f676e90aec8baf56a2ad8c 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -149,22 +149,27 @@ mlxsw_thermal_module_trips_reset(struct mlxsw_thermal_module *tz)
 
 static int
 mlxsw_thermal_module_trips_update(struct device *dev, struct mlxsw_core *core,
-                                 struct mlxsw_thermal_module *tz)
+                                 struct mlxsw_thermal_module *tz,
+                                 int crit_temp, int emerg_temp)
 {
-       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;
+       /* Do not try to query temperature thresholds directly from the module's
+        * EEPROM if we got valid thresholds from MTMP.
+        */
+       if (!emerg_temp || !crit_temp) {
+               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;
+               err = mlxsw_env_module_temp_thresholds_get(core, tz->module,
+                                                          SFP_TEMP_HIGH_ALARM,
+                                                          &emerg_temp);
+               if (err)
+                       return err;
+       }
 
        if (crit_temp > emerg_temp) {
                dev_warn(dev, "%s : Critical threshold %d is above emergency threshold %d\n",
@@ -451,9 +456,9 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 {
        struct mlxsw_thermal_module *tz = tzdev->devdata;
        struct mlxsw_thermal *thermal = tz->parent;
+       int temp, crit_temp, emerg_temp;
        struct device *dev;
        u16 sensor_index;
-       int temp;
        int err;
 
        dev = thermal->bus_info->dev;
@@ -461,15 +466,16 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 
        /* Read module temperature and thresholds. */
        mlxsw_thermal_module_temp_and_thresholds_get(thermal->core,
-                                                    sensor_index, &temp, NULL,
-                                                    NULL);
+                                                    sensor_index, &temp,
+                                                    &crit_temp, &emerg_temp);
        *p_temp = temp;
 
        if (!temp)
                return 0;
 
        /* Update trip points. */
-       err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz);
+       err = mlxsw_thermal_module_trips_update(dev, thermal->core, tz,
+                                               crit_temp, emerg_temp);
        if (!err && temp > 0)
                mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
 
@@ -736,7 +742,10 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
                          struct mlxsw_thermal *thermal, u8 module)
 {
        struct mlxsw_thermal_module *module_tz;
+       int crit_temp, emerg_temp;
+       u16 sensor_index;
 
+       sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + module;
        module_tz = &thermal->tz_module_arr[module];
        /* Skip if parent is already set (case of port split). */
        if (module_tz->parent)
@@ -747,8 +756,12 @@ mlxsw_thermal_module_init(struct device *dev, struct mlxsw_core *core,
               sizeof(thermal->trips));
        /* Initialize all trip point. */
        mlxsw_thermal_module_trips_reset(module_tz);
+       /* Read module temperature and thresholds. */
+       mlxsw_thermal_module_temp_and_thresholds_get(core, sensor_index, NULL,
+                                                    &crit_temp, &emerg_temp);
        /* Update trip point according to the module data. */
-       return mlxsw_thermal_module_trips_update(dev, core, module_tz);
+       return mlxsw_thermal_module_trips_update(dev, core, module_tz,
+                                                crit_temp, emerg_temp);
 }
 
 static void mlxsw_thermal_module_fini(struct mlxsw_thermal_module *module_tz)