mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-05-07 22:08:33 -04:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'mlx5-add-sensor-name-in-temperature-message'

Browse Source 
Tariq Toukan says:

====================
mlx5: Add sensor name in temperature message

This small series from Shahar adds the sensors names to the temperature
event messages, in addition to the existing bitmap indicators.
This improves human readability.

Series starts with simple refactoring and modifications. The top patch
adds the sensors names.
====================

Link: https://patch.msgid.link/20250213094641.226501-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Jakub Kicinski
2025-02-17 16:27:39 -08:00
parent 6626f11c51 46fd50cfcc
commit fe3340a94a
3 changed files with 39 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
drivers/net/ethernet/mellanox/mlx5/core/events.c
View File

@@ -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;
@@ -153,21 +154,50 @@ 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;
value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
/* bit 1-63 are not supported for NICs,
* hence read only bit 0 (asic) from lsb.
*/
value_lsb &= 0x1;
value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
mlx5_core_warn(events->dev,
"High temperature on sensors with bit set %llx %llx",
value_msb, value_lsb);
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;
}

5
drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
View File

@@ -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;
}

1
drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
View File

@@ -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)