[PATCH v3 1/2] Revert "mlxsw: core: Use different get_trend() callbacks for different thermal zones"

[PATCH v3 1/2] Revert "mlxsw: core: Use different get_trend() callbacks for different thermal zones"

[Daniel Lezcano]

This reverts commit 2dc2f760052da4925482ecdcdc5c94d4a599153c.

As discussed in the thread:

https://lore.kernel.org/all/f3c62ebe-7d59-c537-a010-bff366c8aeba@linaro.org/

the feature provided by commits 2dc2f760052da and 6f73862fabd93 is
actually already handled by the thermal framework via the cooling
device state aggregation, thus all this code is pointless.

No conflict happened when reverting the patch.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Tested-by: Vadim Pasternak <vadimp@nvidia.com>
---
 .../ethernet/mellanox/mlxsw/core_thermal.c    | 23 ++++---------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 3548fe1df7c8..0eb52665b994 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -352,7 +352,8 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
 static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
 				   int trip, enum thermal_trend *trend)
 {
-	struct mlxsw_thermal *thermal = tzdev->devdata;
+	struct mlxsw_thermal_module *tz = tzdev->devdata;
+	struct mlxsw_thermal *thermal = tz->parent;
 
 	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
 		return -EINVAL;
@@ -546,22 +547,6 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
 	return 0;
 }
 
-static int mlxsw_thermal_module_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_module_ops = {
 	.bind		= mlxsw_thermal_module_bind,
 	.unbind		= mlxsw_thermal_module_unbind,
@@ -571,7 +556,7 @@ 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_module_trend_get,
+	.get_trend	= mlxsw_thermal_trend_get,
 };
 
 static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
@@ -608,7 +593,7 @@ static struct thermal_zone_device_ops mlxsw_thermal_gearbox_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_module_trend_get,
+	.get_trend	= mlxsw_thermal_trend_get,
 };
 
 static int mlxsw_thermal_get_max_state(struct thermal_cooling_device *cdev,
-- 
2.34.1

[PATCH v3 2/2] Revert "mlxsw: core: Add the hottest thermal zone detection"

[Daniel Lezcano]

This reverts commit 6f73862fabd93213de157d9cc6ef76084311c628.

As discussed in the thread:

https://lore.kernel.org/all/f3c62ebe-7d59-c537-a010-bff366c8aeba@linaro.org/

the feature provided by commits 2dc2f760052da and 6f73862fabd93 is
actually already handled by the thermal framework via the cooling
device state aggregation, thus all this code is pointless.

The revert conflicts with the following changes:
 - 7f4957be0d5b8: thermal: Use mode helpers in drivers
 - 6a79507cfe94c: mlxsw: core: Extend thermal module with per QSFP module thermal zones

These conflicts were fixed and the resulting changes are in this patch.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Tested-by: Vadim Pasternak <vadimp@nvidia.com>
---
  -v3:
   - Respin against v6.0-rc1
  -v2
   - Fix 'err' not used as reported by kbuild test:
   https://lore.kernel.org/all/202208150708.fk6sfd8u-lkp@intel.com/
---
 .../ethernet/mellanox/mlxsw/core_thermal.c    | 64 ++-----------------
 1 file changed, 4 insertions(+), 60 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 0eb52665b994..2ec3b162dc6c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -21,7 +21,6 @@
 #define MLXSW_THERMAL_ASIC_TEMP_HOT	105000	/* 105C */
 #define MLXSW_THERMAL_HYSTERESIS_TEMP	5000	/* 5C */
 #define MLXSW_THERMAL_MODULE_TEMP_SHIFT	(MLXSW_THERMAL_HYSTERESIS_TEMP * 2)
-#define MLXSW_THERMAL_TEMP_SCORE_MAX	GENMASK(31, 0)
 #define MLXSW_THERMAL_MAX_STATE	10
 #define MLXSW_THERMAL_MIN_STATE	2
 #define MLXSW_THERMAL_MAX_DUTY	255
@@ -101,8 +100,6 @@ struct mlxsw_thermal {
 	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
 	u8 cooling_levels[MLXSW_THERMAL_MAX_STATE + 1];
 	struct mlxsw_thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
-	unsigned int tz_highest_score;
-	struct thermal_zone_device *tz_highest_dev;
 	struct mlxsw_thermal_area line_cards[];
 };
 
@@ -193,34 +190,6 @@ 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 hot
-	 * 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)
 {
@@ -285,10 +254,8 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
 		dev_err(dev, "Failed to query temp sensor\n");
 		return err;
 	}
+
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
-	if (temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
-					      temp);
 
 	*p_temp = temp;
 	return 0;
@@ -349,22 +316,6 @@ 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_params mlxsw_thermal_params = {
 	.no_hwmon = true,
 };
@@ -378,7 +329,6 @@ 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,
@@ -464,7 +414,6 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 	int temp, crit_temp, emerg_temp;
 	struct device *dev;
 	u16 sensor_index;
-	int err;
 
 	dev = thermal->bus_info->dev;
 	sensor_index = MLXSW_REG_MTMP_MODULE_INDEX_MIN + tz->module;
@@ -480,10 +429,8 @@ static int mlxsw_thermal_module_temp_get(struct thermal_zone_device *tzdev,
 		return 0;
 
 	/* Update trip points. */
-	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);
+	mlxsw_thermal_module_trips_update(dev, thermal->core, tz,
+					  crit_temp, emerg_temp);
 
 	return 0;
 }
@@ -556,7 +503,6 @@ 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,
@@ -577,8 +523,6 @@ static int mlxsw_thermal_gearbox_temp_get(struct thermal_zone_device *tzdev,
 		return err;
 
 	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
-	if (temp > 0)
-		mlxsw_thermal_tz_score_update(thermal, tzdev, tz->trips, temp);
 
 	*p_temp = temp;
 	return 0;
@@ -593,7 +537,6 @@ static struct thermal_zone_device_ops mlxsw_thermal_gearbox_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_get_max_state(struct thermal_cooling_device *cdev,
@@ -680,6 +623,7 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
 							MLXSW_THERMAL_TRIP_MASK,
 							module_tz,
 							&mlxsw_thermal_module_ops,
+
 							&mlxsw_thermal_params,
 							0,
 							module_tz->parent->polling_delay);
-- 
2.34.1

Re: [PATCH v3 1/2] Revert "mlxsw: core: Use different get_trend() callbacks for different thermal zones"

[Ido Schimmel]

On Wed, Aug 17, 2022 at 03:02:26PM +0200, Daniel Lezcano wrote:
> This reverts commit 2dc2f760052da4925482ecdcdc5c94d4a599153c.
> 
> As discussed in the thread:
> 
> https://lore.kernel.org/all/f3c62ebe-7d59-c537-a010-bff366c8aeba@linaro.org/
> 
> the feature provided by commits 2dc2f760052da and 6f73862fabd93 is
> actually already handled by the thermal framework via the cooling
> device state aggregation, thus all this code is pointless.
> 
> No conflict happened when reverting the patch.
> 
> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
> Tested-by: Vadim Pasternak <vadimp@nvidia.com>
> ---
>  .../ethernet/mellanox/mlxsw/core_thermal.c    | 23 ++++---------------
>  1 file changed, 4 insertions(+), 19 deletions(-)
> 
> diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
> index 3548fe1df7c8..0eb52665b994 100644
> --- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
> +++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
> @@ -352,7 +352,8 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
>  static int mlxsw_thermal_trend_get(struct thermal_zone_device *tzdev,
>  				   int trip, enum thermal_trend *trend)
>  {
> -	struct mlxsw_thermal *thermal = tzdev->devdata;
> +	struct mlxsw_thermal_module *tz = tzdev->devdata;
> +	struct mlxsw_thermal *thermal = tz->parent;

The reverted commit is a fix, so only reverting it is a problem. It
makes the get_trend() callback assume the wrong type of
'tsdev->devdata'. Patch #2 completely removes these callbacks, so I
suggest squashing both patches.

>  
>  	if (trip < 0 || trip >= MLXSW_THERMAL_NUM_TRIPS)
>  		return -EINVAL;
> @@ -546,22 +547,6 @@ mlxsw_thermal_module_trip_hyst_set(struct thermal_zone_device *tzdev, int trip,
>  	return 0;
>  }

Re: [PATCH v3 2/2] Revert "mlxsw: core: Add the hottest thermal zone detection"

[Ido Schimmel]

On Wed, Aug 17, 2022 at 03:02:27PM +0200, Daniel Lezcano wrote:
> @@ -285,10 +254,8 @@ static int mlxsw_thermal_get_temp(struct thermal_zone_device *tzdev,
>  		dev_err(dev, "Failed to query temp sensor\n");
>  		return err;
>  	}
> +

Unnecessary blank line

>  	mlxsw_reg_mtmp_unpack(mtmp_pl, &temp, NULL, NULL, NULL, NULL);
> -	if (temp > 0)
> -		mlxsw_thermal_tz_score_update(thermal, tzdev, thermal->trips,
> -					      temp);
>  
>  	*p_temp = temp;
>  	return 0;
> @@ -349,22 +316,6 @@ static int mlxsw_thermal_set_trip_hyst(struct thermal_zone_device *tzdev,
>  	return 0;
>  }

[...]

> @@ -680,6 +623,7 @@ mlxsw_thermal_module_tz_init(struct mlxsw_thermal_module *module_tz)
>  							MLXSW_THERMAL_TRIP_MASK,
>  							module_tz,
>  							&mlxsw_thermal_module_ops,
> +

Likewise

>  							&mlxsw_thermal_params,
>  							0,
>  							module_tz->parent->polling_delay);
> -- 
> 2.34.1
>