nvme: Add hardware monitoring support
PATCH 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 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
--- drivers/nvme/host/Kconfig | 10 +++ drivers/nvme/host/Makefile | 1 + drivers/nvme/host/core.c | 5 ++ drivers/nvme/host/nvme-hwmon.c | 160 +++++++++++++++++++++++++++++++++ drivers/nvme/host/nvme.h | 8 ++ 5 files changed, 184 insertions(+) create mode 100644 drivers/nvme/host/nvme-hwmon.c
drivers/nvme/host/Kconfig +10 -0
@@ -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
@@ -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 +5 -0
@@ -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)
@@ -2897,6 +2900,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->identified = true; +nvme_hwmon_init (ctrl); +return 0 ; out_free:
drivers/nvme/host/nvme-hwmon.c new file +160 -0
160 lines not on this page · raw message
drivers/nvme/host/nvme.h +8 -0
@@ -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; } +#if IS_ENABLED (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
Christoph Hellwig
maintainerQuoted 5 lines · Guenter Roeck
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.
Quoted 7 lines
At the same time, it would be desirable 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.
So these reported values seem to generate some interest. Adding Akinobu Mita who also planned to wire them up to the thermal framework. I don't really know either upper layer so I'm not sure which is the right one, but with this just like with the previous series I am quite worried that we add a lot of kernel boilerplate code for information people can trivially get using nvme-cli.
Keith Busch
maintainerQuoted 14 lines · Christoph Hellwig
Quoted 5 lines · Guenter Roeck
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.
Quoted 7 lines
At the same time, it would be desirable 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.
Quoted 6 lines
So these reported values seem to generate some interest. Adding Akinobu Mita who also planned to wire them up to the thermal framework. I don't really know either upper layer so I'm not sure which is the right one, but with this just like with the previous series I am quite worried that we add a lot of kernel boilerplate code for information people can trivially get using nvme-cli.
I think it's nvme-cli requires root, where this conveniently doesn't need those elevated rights.
I'm not familiar with either upper level framework either; my only review comment for this patch is to use devm_kfree() for the error cases.
Quoted 15 lines · Keith Busch
Quoted 14 lines · Christoph Hellwig
Quoted 12 lines · Guenter Roeck
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 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.
Quoted 9 lines
Quoted 7 lines
So these reported values seem to generate some interest. Adding Akinobu Mita who also planned to wire them up to the thermal framework. I don't really know either upper layer so I'm not sure which is the right one, but with this just like with the previous series I am quite worried that we add a lot of kernel boilerplate code for information people can trivially get using nvme-cli.
I think it's nvme-cli requires root, where this conveniently doesn'tneed those elevated rights.
The other point here is the thermal framework. One can not wire that up through userspace, and even if it was possible to do it, that would defeat the idea of having the thermal subsystem in the kernel running on its own, without requiring userspace attention.
Quoted 3 lines
I'm not familiar with either upper level framework either; my only review comment for this patch is to use
devm_kfree()for the error cases.
Makes sense. I'll address that in v2.
Guenter
Quoted 14 lines · Guenter Roeck
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 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.
Quoted 8 lines
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
Tried this on ZII i.MX8MQ Ultra Zest Board with NVMe device attached. Seems to work as advertised, so:
Quoted 259 lines
Signed-off-by Guenter Roeck <[email protected]>--- drivers/nvme/host/Kconfig | 10 +++ drivers/nvme/host/Makefile | 1 + drivers/nvme/host/core.c | 5 ++ drivers/nvme/host/nvme-hwmon.c | 160 +++++++++++++++++++++++++++++++++ drivers/nvme/host/nvme.h | 8 ++ 5 files changed, 184 insertions(+) create mode 100644 drivers/nvme/host/nvme-hwmon.cdrivers/nvme/host/Kconfig +10
-0@@ -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 tristatedrivers/nvme/host/Makefile +1
-0@@ -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.odrivers/nvme/host/core.c +5
-0@@ -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)@@ -2897,6 +2900,8 @@ int nvme_init_identify(struct nvme_ctrl *ctrl) ctrl->identified = true; +nvme_hwmon_init (ctrl); +return 0 ; out_free:drivers/nvme/host/nvme-hwmon.c new file +160
-0@@ -0,0 +1,160 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* NVM Express hardware monitoring support +* Copyright (c) 2019, Guenter Roeck +*/ + +#include <linux/hwmon.h> + +#include "nvme.h" + +struct nvme_hwmon_data { +struct nvme_ctrl *ctrl; +struct nvme_smart_log log; +}; + +static int nvme_hwmon_get_smart_log (struct nvme_hwmon_data *data) +{ +return nvme_get_log (data->ctrl,NVME_NSID_ALL ,NVME_LOG_SMART ,0 , + &data->log,sizeof (data->log),0 ); +} + +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 err; +int temp; + + err =nvme_hwmon_get_smart_log (data); +if (err) +return err <0 ? err : -EPROTO ; + +switch (attr) { +case hwmon_temp_max: + *val = (data->ctrl->wctemp -273 ) *1000 ; +break ; +case hwmon_temp_crit: + *val = (data->ctrl->cctemp -273 ) *1000 ; +break ; +case hwmon_temp_input: +if (!channel) + temp =le16_to_cpup ((__le16 *)log->temperature); +else + temp =le16_to_cpu (log->temp_sensor[channel -1 ]); + *val = (temp -273 ) *1000 ; +break ; +case hwmon_temp_crit_alarm: + *val = !!(log->critical_warning &NVME_SMART_CRIT_TEMPERATURE ); +break ; +default : + err = -EOPNOTSUPP ; +break ; + } +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_crit_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_CRIT_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->device; +struct nvme_hwmon_data *data; +struct device *hwmon; +int err; + + data =devm_kzalloc (dev,sizeof (*data),GFP_KERNEL ); +if (!data) +return ; + + data->ctrl = ctrl; + + err =nvme_hwmon_get_smart_log (data); +if (err) { +dev_warn (dev,"Failed to read smart log (error %d)\n" , err); +return ; + } + + hwmon =devm_hwmon_device_register_with_info (dev,dev_name (dev), + data, + &nvme_hwmon_chip_info, +NULL ); +if (IS_ERR (hwmon)) +dev_warn (dev,"Failed to instantiate hwmon device\n" ); +}drivers/nvme/host/nvme.h +8
-1@@ -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; } +#if IS_ENABLED (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 */ --2.17.1