Commit 46fd50cf authored by Shahar Shitrit's avatar Shahar Shitrit Committed by Jakub Kicinski
Browse files

net/mlx5: Add sensor name to temperature event message 



Previously, a temperature event message included a bitmap indicating
which sensors detect high temperatures.

To enhance clarity, we modify the message format to explicitly list
the names of the overheating sensors, alongside the sensors bitmap.
If HWMON is not configured, the event message remains unchanged.

Signed-off-by: default avatarShahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: default avatarCarolina Jubran <cjubran@nvidia.com>
Signed-off-by: default avatarTariq Toukan <tariqt@nvidia.com>
Reviewed-by: default avatarSimon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250213094641.226501-5-tariqt@nvidia.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 633f16d7

drivers/net/ethernet/mellanox/mlx5/core/events.c

+28 −3
Original line number Diff line number Diff line
@@ -6,6 +6,7 @@ 
#include "mlx5_core.h"

#include "lib/eq.h"

#include "lib/events.h"

#include "hwmon.h"



struct mlx5_event_nb {

	struct mlx5_nb  nb;
@@ -153,11 +154,28 @@ static int any_notifier(struct notifier_block *nb, 
	return NOTIFY_OK;

}



#if IS_ENABLED(CONFIG_HWMON)

static void print_sensor_names_in_bit_set(struct mlx5_core_dev *dev, struct mlx5_hwmon *hwmon,

					  u64 bit_set, int bit_set_offset)

{

	unsigned long *bit_set_ptr = (unsigned long *)&bit_set;

	int num_bits = sizeof(bit_set) * BITS_PER_BYTE;

	int i;



	for_each_set_bit(i, bit_set_ptr, num_bits) {

		const char *sensor_name = hwmon_get_sensor_name(hwmon, i + bit_set_offset);



		mlx5_core_warn(dev, "Sensor name[%d]: %s\n", i + bit_set_offset, sensor_name);

	}

}

#endif /* CONFIG_HWMON */



/* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */

static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)

{

	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);

	struct mlx5_events   *events   = event_nb->ctx;

	struct mlx5_core_dev *dev      = events->dev;

	struct mlx5_eqe      *eqe      = data;

	u64 value_lsb;

	u64 value_msb;
@@ -169,10 +187,17 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data) 
	value_lsb &= 0x1;

	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);



	if (net_ratelimit())

		mlx5_core_warn(events->dev,

			       "High temperature on sensors with bit set %#llx %#llx",

	if (net_ratelimit()) {

		mlx5_core_warn(dev, "High temperature on sensors with bit set %#llx %#llx.\n",

			       value_msb, value_lsb);

#if IS_ENABLED(CONFIG_HWMON)

		if (dev->hwmon) {

			print_sensor_names_in_bit_set(dev, dev->hwmon, value_lsb, 0);

			print_sensor_names_in_bit_set(dev, dev->hwmon, value_msb,

						      sizeof(value_lsb) * BITS_PER_BYTE);

		}

#endif

	}



	return NOTIFY_OK;

}

drivers/net/ethernet/mellanox/mlx5/core/hwmon.c

+5 −0
Original line number Diff line number Diff line
@@ -416,3 +416,8 @@ void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev) 
	mlx5_hwmon_free(hwmon);

	mdev->hwmon = NULL;

}



const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel)

{

	return hwmon->temp_channel_desc[channel].sensor_name;

}

drivers/net/ethernet/mellanox/mlx5/core/hwmon.h

+1 −0
Original line number Diff line number Diff line
@@ -10,6 +10,7 @@ 


int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev);

void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev);

const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel);



#else

static inline int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev)