According to the NVMe specification, the over temperature threshold and
under temperature threshold features shall be implemented for Composite
Temperature if a non-zero WCTEMP field value is reported in the Identify
Controller data structure. The features are also implemented for all
implemented temperature sensors (i.e., all Temperature Sensor fields that
report a non-zero value).
This provides the over temperature threshold and under temperature
threshold for each sensor as temperature min and max values of hwmon
sysfs attributes.
The WCTEMP is already provided as a temperature max value for Composite
Temperature, but this change isn't incompatible. Because the default
value of the over temperature threshold for Composite Temperature is
the WCTEMP.
This also provides alarm attributes for each temperature sensor. But all
alarm conditions are same, because there is only a single bit in
Critical Warning field that indicates one of the temperature is outside of
a temperature threshold.
Example output from the "sensors" command:
nvme-pci-0100
Adapter: PCI adapter
Composite: +53.0 C (low = -273.0 C, high = +70.0 C)
(crit = +80.0 C)
Sensor 1: +56.0 C (low = -273.0 C, high = +65262.0 C)
Sensor 2: +51.0 C (low = -273.0 C, high = +65262.0 C)
Sensor 5: +73.0 C (low = -273.0 C, high = +65262.0 C)
Cc: Keith Busch <kbusch@xxxxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Sagi Grimberg <sagi@xxxxxxxxxxx>
Cc: Jean Delvare <jdelvare@xxxxxxxx>
Cc: Guenter Roeck <linux@xxxxxxxxxxxx>
Signed-off-by: Akinobu Mita <akinobu.mita@xxxxxxxxx>
---
This patch depends on the patch "nvme: Add hardware monitoring support" [1]
[1] http://lists.infradead.org/pipermail/linux-nvme/2019-November/027883.html
drivers/nvme/host/nvme-hwmon.c | 98 ++++++++++++++++++++++++++++++++++++------
include/linux/nvme.h | 6 +++
2 files changed, 90 insertions(+), 14 deletions(-)
diff --git a/drivers/nvme/host/nvme-hwmon.c b/drivers/nvme/host/nvme-hwmon.c
index 5480cbb..79323b2 100644
--- a/drivers/nvme/host/nvme-hwmon.c
+++ b/drivers/nvme/host/nvme-hwmon.c
@@ -15,6 +15,46 @@ struct nvme_hwmon_data {
struct mutex read_lock;
};
+static int nvme_get_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
+ long *temp)
+{
+ unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
+ int status;
+ int ret;
+
+ if (under)
+ threshold |= NVME_TEMP_THRESH_TYPE_UNDER;
+
+ ret = nvme_get_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0,
+ &status);
+ if (!ret)
+ *temp = ((status & NVME_TEMP_THRESH_MASK) - 273) * 1000;
+
+ return ret <= 0 ? ret : -EIO;
+}
+
+static int nvme_set_temp_thresh(struct nvme_ctrl *ctrl, int sensor, bool under,
+ long temp)
+{
+ unsigned int threshold = sensor << NVME_TEMP_THRESH_SELECT_SHIFT;
+ int status;
+ int ret;
+
+ temp = temp / 1000 + 273;
+ if (temp > NVME_TEMP_THRESH_MASK)
+ return -EINVAL;
+
+ threshold |= temp;
+
+ if (under)
+ threshold |= NVME_TEMP_THRESH_TYPE_UNDER;
+
+ ret = nvme_set_features(ctrl, NVME_FEAT_TEMP_THRESH, threshold, NULL, 0,
+ &status);
+
+ return ret <= 0 ? ret : -EIO;
+}
+
static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
{
int ret;
@@ -39,8 +79,12 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
*/
switch (attr) {
case hwmon_temp_max:
- *val = (data->ctrl->wctemp - 273) * 1000;
+ err = nvme_get_temp_thresh(data->ctrl, channel, false, val);
+ if (err)
+ *val = (data->ctrl->wctemp - 273) * 1000;
return 0;
+ case hwmon_temp_min:
+ return nvme_get_temp_thresh(data->ctrl, channel, true, val);
case hwmon_temp_crit:
*val = (data->ctrl->cctemp - 273) * 1000;
return 0;
@@ -73,6 +117,23 @@ static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
return err;
}
+static int nvme_hwmon_write(struct device *dev, enum hwmon_sensor_types type,
+ u32 attr, int channel, long val)
+{
+ struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+
+ switch (attr) {
+ case hwmon_temp_max:
+ return nvme_set_temp_thresh(data->ctrl, channel, false, val);
+ case hwmon_temp_min:
+ return nvme_set_temp_thresh(data->ctrl, channel, true, val);
+ default:
+ break;
+ }
+
+ return -EOPNOTSUPP;
+}
+
static const char * const nvme_hwmon_sensor_names[] = {
"Composite",
"Sensor 1",
@@ -105,13 +166,13 @@ static umode_t nvme_hwmon_is_visible(const void *_data,
return 0444;
break;
case hwmon_temp_max:
+ case hwmon_temp_min:
if (!channel && data->ctrl->wctemp)
- return 0444;
+ return 0644;
+ else if (data->log.temp_sensor[channel - 1])
+ return 0644;
break;
case hwmon_temp_alarm:
- if (!channel)
- return 0444;
- break;
case hwmon_temp_input:
case hwmon_temp_label:
if (!channel || data->log.temp_sensor[channel - 1])
@@ -126,16 +187,24 @@ static umode_t nvme_hwmon_is_visible(const void *_data,
static const struct hwmon_channel_info *nvme_hwmon_info[] = {
HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
HWMON_CHANNEL_INFO(temp,
- HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT |
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_CRIT | HWMON_T_LABEL | HWMON_T_ALARM,
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_LABEL | HWMON_T_ALARM,
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_LABEL | HWMON_T_ALARM,
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_LABEL | HWMON_T_ALARM,
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_LABEL | HWMON_T_ALARM,
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_LABEL | HWMON_T_ALARM,
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_LABEL | HWMON_T_ALARM,
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
HWMON_T_LABEL | HWMON_T_ALARM,
- HWMON_T_INPUT | HWMON_T_LABEL,
- HWMON_T_INPUT | HWMON_T_LABEL,
- HWMON_T_INPUT | HWMON_T_LABEL,
- HWMON_T_INPUT | HWMON_T_LABEL,
- HWMON_T_INPUT | HWMON_T_LABEL,
- HWMON_T_INPUT | HWMON_T_LABEL,
- HWMON_T_INPUT | HWMON_T_LABEL,
- HWMON_T_INPUT | HWMON_T_LABEL),
+ HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_MIN |
+ HWMON_T_LABEL | HWMON_T_ALARM),
NULL
};
@@ -143,6 +212,7 @@ static const struct hwmon_ops nvme_hwmon_ops = {
.is_visible = nvme_hwmon_is_visible,
.read = nvme_hwmon_read,
.read_string = nvme_hwmon_read_string,
+ .write = nvme_hwmon_write,
};
static const struct hwmon_chip_info nvme_hwmon_chip_info = {
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 269b2e8..347a44f 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -803,6 +803,12 @@ struct nvme_write_zeroes_cmd {
/* Features */
+enum {
+ NVME_TEMP_THRESH_MASK = 0xffff,
+ NVME_TEMP_THRESH_SELECT_SHIFT = 16,
+ NVME_TEMP_THRESH_TYPE_UNDER = 0x100000,
+};
+
struct nvme_feat_auto_pst {
__le64 entries[32];
};
--
2.7.4
