Skip to contentSkip to conversation

nvme: Add hardware monitoring support

PATCH Superseded Guenter Roeck 3 participants 5 messages Nov 2, 2019 – Nov 5, 2019 NVMe

v4 of 5 Superseded Latest is v5 →

lore
Share & tools
lore
#0 lore raw

PATCH v4 1/1 nvme: Add hardware monitoring support

nvme devices report temperature information in the controller information (for limits) and in the smart log. Currently, the only means to retrieve this information is the nvme command line interface, which requires super-user privileges.

At the same time, it would be desirable to be able to use NVMe temperature information for thermal control.

This patch adds support to read NVMe temperatures from the kernel using the hwmon API and adds temperature zones for NVMe drives. The thermal subsystem can use this information to set thermal policies, and userspace can access it using libsensors and/or the "sensors" command.

Example output from the "sensors" command:

nvme-pci-0100

Adapter: PCI adapter
Composite:    +39.0°C  (high = +85.0°C, crit = +85.0°C)
Sensor 1:     +39.0°C
Sensor 2:     +41.0°C

---
v4: Attach hwmon device to ctrl->dev instead of ctrl->device
Use "nvme" as hwmon device chip name

v3: NVME -> NVMe
Call nvme_hwmon_init() only once, when the controller is first identified
Protect call to nvme_get_log() and reading the log with mutex Convert error return from nvme_get_log() to Linux error code in nvme_hwmon_get_smart_log()
Don't read smart log for reporting warning and critical limits Use get_unaligned_le16() instead of le16_to_cpup() to read the composite temperature
Use #ifdef CONFIG_NVME_HWMON instead of IS_ENABLED(CONFIG_NVME_HWMON) -EPROTO -> -EIO for generic NVMe level errors
Tab-align '=' in data structure initializations

v2: Use devm_kfree() to release memory in error path

Tested with the following NVMe drives:
Intel SSDPEKKW512G7 500GB
Samsung SSD 960 EVO 500GB
Samsung SSD 970 EVO 500GB
Samsung SSD 970 EVO 1TB

 drivers/nvme/host/Kconfig      |  10 ++
 drivers/nvme/host/Makefile     |   1 +
 drivers/nvme/host/core.c       |   6 ++
 drivers/nvme/host/nvme-hwmon.c | 181 +++++++++++++++++++++++++++++++++
 drivers/nvme/host/nvme.h       |   8 ++
 5 files changed, 206 insertions(+)
 create mode 100644 drivers/nvme/host/nvme-hwmon.c
drivers/nvme/host/Kconfig +10 -0
index 2b36f052bfb9..c6439638a419 100644
@@ -23,6 +23,16 @@ config NVME_MULTIPATH
 	   /dev/nvmeXnY device will show up for each NVMe namespaces,
 	   even if it is accessible through multiple controllers.
 
+config NVME_HWMON
+	bool "NVMe hardware monitoring"
+	depends on (NVME_CORE=y && HWMON=y) || (NVME_CORE=m && HWMON)
+	help
+	  This provides support for NVMe hardware monitoring. If enabled,
+	  a hardware monitoring device will be created for each NVMe drive
+	  in the system.
+
+	  If unsure, say N.
+
 config NVME_FABRICS
 	tristate
 
drivers/nvme/host/Makefile +1 -0
index 8a4b671c5f0c..03de4797a877 100644
@@ -14,6 +14,7 @@ nvme-core-$(CONFIG_TRACING)		+= trace.o
 nvme-core-$(CONFIG_NVME_MULTIPATH)	+= multipath.o
 nvme-core-$(CONFIG_NVM)			+= lightnvm.o
 nvme-core-$(CONFIG_FAULT_INJECTION_DEBUG_FS)	+= fault_inject.o
+nvme-core-$(CONFIG_NVME_HWMON)		+= nvme-hwmon.o
 
 nvme-y					+= pci.o
 
drivers/nvme/host/core.c +6 -0
index fa7ba09dca77..d039e392de36 100644
@@ -2796,6 +2796,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	ctrl->oncs = le16_to_cpu(id->oncs);
 	ctrl->mtfa = le16_to_cpu(id->mtfa);
 	ctrl->oaes = le32_to_cpu(id->oaes);
+	ctrl->wctemp = le16_to_cpu(id->wctemp);
+	ctrl->cctemp = le16_to_cpu(id->cctemp);
+
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
 	ctrl->vwc = id->vwc;
 	if (id->mdts)
@@ -2895,6 +2898,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	if (ret < 0)
 		return ret;
 
+	if (!ctrl->identified)
+		nvme_hwmon_init(ctrl);
+
 	ctrl->identified = true;
 
 	return 0;
drivers/nvme/host/nvme-hwmon.c new file +181 -0

181 lines not on this page · raw message

drivers/nvme/host/nvme.h +8 -0
index 22e8401352c2..cb3b242a214e 100644
@@ -231,6 +231,8 @@ struct nvme_ctrl {
 	u16 kas;
 	u8 npss;
 	u8 apsta;
+	u16 wctemp;
+	u16 cctemp;
 	u32 oaes;
 	u32 aen_result;
 	u32 ctratt;
@@ -652,4 +654,10 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 	return dev_to_disk(dev)->private_data;
 }
 
+#ifdef CONFIG_NVME_HWMON
+void nvme_hwmon_init(struct nvme_ctrl *ctrl);
+#else
+static inline void nvme_hwmon_init(struct nvme_ctrl *ctrl) { }
+#endif
+
 #endif /* _NVME_H */
Signature · 1 line
2.17.1
#2 lore raw
In reply to Guenter Roeck

2019年11月2日(土) 23:55 Guenter Roeck <[email protected]>:

Quoted 41 lines
drivers/nvme/host/nvme-hwmon.c new file +35 -0
new file mode 100644
index 000000000000..28b4b7f43bb0
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express hardware monitoring support
+ * Copyright (c) 2019, Guenter Roeck
+ */
+
+#include <linux/hwmon.h>
+#include <asm/unaligned.h>
+
+#include "nvme.h"
+
+struct nvme_hwmon_data {
+       struct nvme_ctrl *ctrl;
+       struct nvme_smart_log log;
+       struct mutex read_lock;
+};
+
+static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
+{
+       int ret;
+
+       ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
+                          &data->log, sizeof(data->log), 0);
+
+       return ret <= 0 ? ret : -EIO;
+}
+
+static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+                          u32 attr, int channel, long *val)
+{
+       struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+       struct nvme_smart_log *log = &data->log;
+       int temp;
+       int err;
+

drivers/nvme/host/nvme-hwmon.c line 45

Quoted 10 lines
drivers/nvme/host/nvme-hwmon.c new file +10 -0
+       /*
+        * First handle attributes which don't require us to read
+        * the smart log.
+        */
+       switch (attr) {
+       case hwmon_temp_max:
+               *val = (data->ctrl->wctemp - 273) * 1000;
+               return 0;
+       case hwmon_temp_crit:
+               *val = (data->ctrl->cctemp - 273) * 1000;

This attribute should be 'hwmon_temp_max_alarm' rather than 'hwmon_temp_crit_alarm'?

The 'hwmon_temp_crit_alarm' indicates that the temperature is greater than CCTEMP.

But according to the description of the Critical Warning field in the NVMe spec, the bit 1 is set to '1' when the temperature is greater than or equal to an over temperature threshold. The default value of the over temperature threshold for Composite Temperature is WCTEMP.

That's why I think this attribute should be 'hwmon_temp_max_alarm' which indicates that the temperature is greater than WCTEMP.

#3 lore raw

2019年11月6日(水) 0:38 Akinobu Mita <[email protected]>:

Quoted 48 lines

2019年11月2日(土) 23:55 Guenter Roeck <[email protected]>:

Quoted 46 lines
drivers/nvme/host/nvme-hwmon.c new file +40 -0
new file mode 100644
index 000000000000..28b4b7f43bb0
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express hardware monitoring support
+ * Copyright (c) 2019, Guenter Roeck
+ */
+
+#include <linux/hwmon.h>
+#include <asm/unaligned.h>
+
+#include "nvme.h"
+
+struct nvme_hwmon_data {
+       struct nvme_ctrl *ctrl;
+       struct nvme_smart_log log;
+       struct mutex read_lock;
+};
+
+static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
+{
+       int ret;
+
+       ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
+                          &data->log, sizeof(data->log), 0);
+
+       return ret <= 0 ? ret : -EIO;
+}
+
+static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+                          u32 attr, int channel, long *val)
+{
+       struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+       struct nvme_smart_log *log = &data->log;
+       int temp;
+       int err;
+
+       /*
+        * First handle attributes which don't require us to read
+        * the smart log.
+        */
+       switch (attr) {
Quoted 8 lines

drivers/nvme/host/nvme-hwmon.c line 45

Quoted 5 lines
drivers/nvme/host/nvme-hwmon.c new file +5 -0
+       case hwmon_temp_max:
+               *val = (data->ctrl->wctemp - 273) * 1000;
+               return 0;
+       case hwmon_temp_crit:
+               *val = (data->ctrl->cctemp - 273) * 1000;

This attribute should be 'hwmon_temp_max_alarm' rather than 'hwmon_temp_crit_alarm'?

Oops, I misquoted the code.

This comment should be addressed to the code below:

+ case hwmon_temp_crit_alarm:
+ *val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE);
+ break;

#4 lore raw
Quoted 58 lines · Akinobu Mita

2019年11月6日(水) 0:38 Akinobu Mita <[email protected]>:

Quoted 56 lines

2019年11月2日(土) 23:55 Guenter Roeck <[email protected]>:

Quoted 41 lines
drivers/nvme/host/nvme-hwmon.c new file +35 -0
new file mode 100644
index 000000000000..28b4b7f43bb0
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * NVM Express hardware monitoring support
+ * Copyright (c) 2019, Guenter Roeck
+ */
+
+#include <linux/hwmon.h>
+#include <asm/unaligned.h>
+
+#include "nvme.h"
+
+struct nvme_hwmon_data {
+       struct nvme_ctrl *ctrl;
+       struct nvme_smart_log log;
+       struct mutex read_lock;
+};
+
+static int nvme_hwmon_get_smart_log(struct nvme_hwmon_data *data)
+{
+       int ret;
+
+       ret = nvme_get_log(data->ctrl, NVME_NSID_ALL, NVME_LOG_SMART, 0,
+                          &data->log, sizeof(data->log), 0);
+
+       return ret <= 0 ? ret : -EIO;
+}
+
+static int nvme_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+                          u32 attr, int channel, long *val)
+{
+       struct nvme_hwmon_data *data = dev_get_drvdata(dev);
+       struct nvme_smart_log *log = &data->log;
+       int temp;
+       int err;
+

drivers/nvme/host/nvme-hwmon.c line 45

Quoted 10 lines
drivers/nvme/host/nvme-hwmon.c new file +10 -0
+       /*
+        * First handle attributes which don't require us to read
+        * the smart log.
+        */
+       switch (attr) {
+       case hwmon_temp_max:
+               *val = (data->ctrl->wctemp - 273) * 1000;
+               return 0;
+       case hwmon_temp_crit:
+               *val = (data->ctrl->cctemp - 273) * 1000;

This attribute should be 'hwmon_temp_max_alarm' rather than 'hwmon_temp_crit_alarm'?

Yes, you are correct. Actually, re-reading the specification, the bit may also be set for under-temperature alarms, so I'll use the more generic hwmon_temp_alarm.

Thanks,
Guenter

Quoted 7 lines

Oops, I misquoted the code.

This comment should be addressed to the code below:

drivers/nvme/host/nvme-hwmon.c new file +3 -0
+       case hwmon_temp_crit_alarm:
+               *val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE);
+               break;