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:

nvme0-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
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Keith Busch <kbusch@kernel.org>

drivers/nvme/host/Kconfig

@@ -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

@@ -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)		+= hwmon.o
 
 nvme-y					+= pci.o
 

drivers/nvme/host/core.c

@@ -2760,6 +2760,9 @@ 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)
@@ -2859,6 +2862,9 @@ 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/hwmon.c

+// 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) {
+	case hwmon_temp_max:
+		*val = (data->ctrl->wctemp - 273) * 1000;
+		return 0;
+	case hwmon_temp_crit:
+		*val = (data->ctrl->cctemp - 273) * 1000;
+		return 0;
+	default:
+		break;
+	}
+
+	mutex_lock(&data->read_lock);
+	err = nvme_hwmon_get_smart_log(data);
+	if (err)
+		goto unlock;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		if (!channel)
+			temp = get_unaligned_le16(log->temperature);
+		else
+			temp = le16_to_cpu(log->temp_sensor[channel - 1]);
+		*val = (temp - 273) * 1000;
+		break;
+	case hwmon_temp_alarm:
+		*val = !!(log->critical_warning & NVME_SMART_CRIT_TEMPERATURE);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+unlock:
+	mutex_unlock(&data->read_lock);
+	return err;
+}
+
+static const char * const nvme_hwmon_sensor_names[] = {
+	"Composite",
+	"Sensor 1",
+	"Sensor 2",
+	"Sensor 3",
+	"Sensor 4",
+	"Sensor 5",
+	"Sensor 6",
+	"Sensor 7",
+	"Sensor 8",
+};
+
+static int nvme_hwmon_read_string(struct device *dev,
+				  enum hwmon_sensor_types type, u32 attr,
+				  int channel, const char **str)
+{
+	*str = nvme_hwmon_sensor_names[channel];
+	return 0;
+}
+
+static umode_t nvme_hwmon_is_visible(const void *_data,
+				     enum hwmon_sensor_types type,
+				     u32 attr, int channel)
+{
+	const struct nvme_hwmon_data *data = _data;
+
+	switch (attr) {
+	case hwmon_temp_crit:
+		if (!channel && data->ctrl->cctemp)
+			return 0444;
+		break;
+	case hwmon_temp_max:
+		if (!channel && data->ctrl->wctemp)
+			return 0444;
+		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])
+			return 0444;
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
+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_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),
+	NULL
+};
+
+static const struct hwmon_ops nvme_hwmon_ops = {
+	.is_visible	= nvme_hwmon_is_visible,
+	.read		= nvme_hwmon_read,
+	.read_string	= nvme_hwmon_read_string,
+};
+
+static const struct hwmon_chip_info nvme_hwmon_chip_info = {
+	.ops	= &nvme_hwmon_ops,
+	.info	= nvme_hwmon_info,
+};
+
+void nvme_hwmon_init(struct nvme_ctrl *ctrl)
+{
+	struct device *dev = ctrl->dev;
+	struct nvme_hwmon_data *data;
+	struct device *hwmon;
+	int err;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return;
+
+	data->ctrl = ctrl;
+	mutex_init(&data->read_lock);
+
+	err = nvme_hwmon_get_smart_log(data);
+	if (err) {
+		dev_warn(dev, "Failed to read smart log (error %d)\n", err);
+		devm_kfree(dev, data);
+		return;
+	}
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "nvme", data,
+						     &nvme_hwmon_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon)) {
+		dev_warn(dev, "Failed to instantiate hwmon device\n");
+		devm_kfree(dev, data);
+	}
+}

drivers/nvme/host/nvme.h

@@ -230,6 +230,8 @@ struct nvme_ctrl {
 	u16 kas;
 	u8 npss;
 	u8 apsta;
+	u16 wctemp;
+	u16 cctemp;
 	u32 oaes;
 	u32 aen_result;
 	u32 ctratt;
@@ -665,4 +667,10 @@ 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 */