[PATCH v5 4/4] nvme: notify thermal framework when temperature threshold events occur

[akinobu.mita@gmail.com (Akinobu Mita)]

The NVMe controller supports the temperature threshold feature (Feature
Identifier 04h) that enables to configure the asynchronous event request
command to complete when the temperature is crossed its corresponding
temperature threshold.

This enables the reporting of asynchronous events from the controller when
the temperature reached or exceeded a temperature threshold.
In the case of the temperature threshold conditions, this notifies the
thermal framework.

The main purpose of this is to turn on a fan when overheated without
polling the device for the smart log that could prevent the lower power
state transitions.

Cc: Rob Herring <robh at kernel.org>
Cc: Zhang Rui <rui.zhang at intel.com>
Cc: Eduardo Valentin <edubezval at gmail.com>
Cc: Daniel Lezcano <daniel.lezcano at linaro.org>
Cc: Keith Busch <kbusch at kernel.org>
Cc: Jens Axboe <axboe at fb.com>
Cc: Christoph Hellwig <hch at lst.de>
Cc: Sagi Grimberg <sagi at grimberg.me>
Cc: Minwoo Im <minwoo.im.dev at gmail.com>
Cc: Kenneth Heitke <kenneth.heitke at intel.com>
Cc: Chaitanya Kulkarni <Chaitanya.Kulkarni at wdc.com>
Signed-off-by: Akinobu Mita <akinobu.mita at gmail.com>
---
* v5
- use thermal_zone_device_update() instead of thermal_notify_framework()

 drivers/nvme/host/core.c    | 14 ++++++++++++++
 drivers/nvme/host/nvme.h    |  5 +++++
 drivers/nvme/host/thermal.c | 14 ++++++++++++++
 include/linux/nvme.h        |  7 +++++++
 4 files changed, 40 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 1d84685..80403c3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1186,6 +1186,9 @@ static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 	u32 result, supported_aens = ctrl->oaes & NVME_AEN_SUPPORTED;
 	int status;
 
+	if (IS_ENABLED(CONFIG_THERMAL))
+		supported_aens |= NVME_SMART_CRIT_TEMPERATURE;
+
 	if (!supported_aens)
 		return;
 
@@ -3561,6 +3564,16 @@ void nvme_remove_namespaces(struct nvme_ctrl *ctrl)
 }
 EXPORT_SYMBOL_GPL(nvme_remove_namespaces);
 
+static void nvme_handle_aen_smart(struct nvme_ctrl *ctrl, u32 result)
+{
+	u32 aer_type = result & NVME_AER_TYPE_MASK;
+	u32 aer_info = (result >> NVME_AER_INFO_SHIFT) & NVME_AER_INFO_MASK;
+
+	if (aer_type == NVME_AER_SMART &&
+	    aer_info == NVME_AER_SMART_TEMP_THRESH)
+		nvme_thermal_zones_update(ctrl);
+}
+
 static void nvme_aen_uevent(struct nvme_ctrl *ctrl)
 {
 	char *envp[2] = { NULL, NULL };
@@ -3582,6 +3595,7 @@ static void nvme_async_event_work(struct work_struct *work)
 	struct nvme_ctrl *ctrl =
 		container_of(work, struct nvme_ctrl, async_event_work);
 
+	nvme_handle_aen_smart(ctrl, ctrl->aen_result);
 	nvme_aen_uevent(ctrl);
 	ctrl->ops->submit_async_event(ctrl);
 }
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index d501567..f29bc77 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -611,6 +611,7 @@ static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
 
 int nvme_thermal_zones_register(struct nvme_ctrl *ctrl);
 void nvme_thermal_zones_unregister(struct nvme_ctrl *ctrl);
+void nvme_thermal_zones_update(struct nvme_ctrl *ctrl);
 
 #else
 
@@ -623,6 +624,10 @@ static inline void nvme_thermal_zones_unregister(struct nvme_ctrl *ctrl)
 {
 }
 
+static inline void nvme_thermal_zones_update(struct nvme_ctrl *ctrl)
+{
+}
+
 #endif /* CONFIG_THERMAL */
 
 #endif /* _NVME_H */
diff --git a/drivers/nvme/host/thermal.c b/drivers/nvme/host/thermal.c
index 431aeb4..9dcc1dc 100644
--- a/drivers/nvme/host/thermal.c
+++ b/drivers/nvme/host/thermal.c
@@ -327,3 +327,17 @@ void nvme_thermal_zones_unregister(struct nvme_ctrl *ctrl)
 		__clear_bit(i, ctrl->tz_enabled);
 	}
 }
+
+void nvme_thermal_zones_update(struct nvme_ctrl *ctrl)
+{
+	int i;
+
+	for_each_set_bit(i, ctrl->tz_enabled, ARRAY_SIZE(ctrl->tz)) {
+		if (ctrl->tz[i].dev)
+			thermal_zone_device_update(ctrl->tz[i].dev,
+						   THERMAL_EVENT_UNSPECIFIED);
+		if (ctrl->tz[i].of_dev)
+			thermal_zone_device_update(ctrl->tz[i].of_dev,
+						   THERMAL_EVENT_UNSPECIFIED);
+	}
+}
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index f29728b..069b962 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -476,6 +476,7 @@ enum {
 };
 
 enum {
+	NVME_AER_TYPE_MASK		= 0x7,
 	NVME_AER_ERROR			= 0,
 	NVME_AER_SMART			= 1,
 	NVME_AER_NOTICE			= 2,
@@ -484,6 +485,12 @@ enum {
 };
 
 enum {
+	NVME_AER_INFO_SHIFT		= 8,
+	NVME_AER_INFO_MASK		= 0xff,
+	NVME_AER_SMART_TEMP_THRESH	= 0x01,
+};
+
+enum {
 	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
 	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
 	NVME_AER_NOTICE_ANA		= 0x03,
-- 
2.7.4