[PATCH 1/3] thermal: core: Add indication for userspace usage

[PATCH 1/3] thermal: core: Add indication for userspace usage

[Kai-Heng Feng]

We are seeing thermal shutdown on Intel based mobile workstations, the
shutdown happens during the first trip handle in
thermal_zone_device_register():
kernel: thermal thermal_zone15: critical temperature reached (101 C), shutting down

However, we shouldn't do a thermal shutdown here, since
1) We may want to use a dedicated daemon, Intel's thermald in this case,
to handle thermal shutdown.

2) For ACPI based system, _CRT doesn't mean shutdown unless it's inside
ThermalZone. ACPI Spec, 11.4.4 _CRT (Critical Temperature):
"... If this object it present under a device, the device’s driver
evaluates this object to determine the device’s critical cooling
temperature trip point. This value may then be used by the device’s
driver to program an internal device temperature sensor trip point."

So a "critical trip" here merely means we should take a more aggressive
cooling method.

So add an indication to let thermal core know it should leave thermal
device to userspace to handle.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
---
 drivers/thermal/thermal_core.c | 3 +++
 include/linux/thermal.h        | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index c6d74bc1c90b..6561e3767529 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1477,6 +1477,9 @@ thermal_zone_device_register(const char *type, int trips, int mask,
 			goto unregister;
 	}
 
+	if (tz->tzp && tz->tzp->userspace)
+		thermal_zone_device_disable(tz);
+
 	mutex_lock(&thermal_list_lock);
 	list_add_tail(&tz->node, &thermal_tz_list);
 	mutex_unlock(&thermal_list_lock);
diff --git a/include/linux/thermal.h b/include/linux/thermal.h
index d07ea27e72a9..e8e8fac78fc8 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -247,6 +247,8 @@ struct thermal_zone_params {
 	 */
 	bool no_hwmon;
 
+	bool userspace;
+
 	int num_tbps;	/* Number of tbp entries */
 	struct thermal_bind_params *tbp;
 
-- 
2.29.2

[PATCH 2/3] thermal: int340x: Indicate userspace usage

[Kai-Heng Feng]

The device isn't present under ACPI ThermalZone, and there's a dedicated
userspace daemon for this thermal device.

Let thermal core know it shouldn't handle trips to avoid surprising
thermal shutdown.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
---
 drivers/thermal/intel/int340x_thermal/int3400_thermal.c     | 1 +
 .../thermal/intel/int340x_thermal/int340x_thermal_zone.c    | 6 +-----
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index 0966551cbaaa..2002bc96eb3c 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -439,6 +439,7 @@ static struct thermal_zone_device_ops int3400_thermal_ops = {
 static struct thermal_zone_params int3400_thermal_params = {
 	.governor_name = "user_space",
 	.no_hwmon = true,
+	.userspace = true,
 };
 
 static void int3400_setup_gddv(struct int3400_thermal_priv *priv)
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 6e479deff76b..a103eb42ef2d 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -208,6 +208,7 @@ EXPORT_SYMBOL_GPL(int340x_thermal_read_trips);
 static struct thermal_zone_params int340x_thermal_params = {
 	.governor_name = "user_space",
 	.no_hwmon = true,
+	.userspace = true,
 };
 
 struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
@@ -259,14 +260,9 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
 		ret = PTR_ERR(int34x_thermal_zone->zone);
 		goto err_thermal_zone;
 	}
-	ret = thermal_zone_device_enable(int34x_thermal_zone->zone);
-	if (ret)
-		goto err_enable;
 
 	return int34x_thermal_zone;
 
-err_enable:
-	thermal_zone_device_unregister(int34x_thermal_zone->zone);
 err_thermal_zone:
 	acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
 	kfree(int34x_thermal_zone->aux_trips);
-- 
2.29.2

[PATCH 3/3] thermal: intel: intel_pch_thermal: Indicate userspace usage

[Kai-Heng Feng]

The device isn't present under ACPI ThermalZone, and there's a dedicated
userspace daemon for this thermal device.

Let thermal core know it shouldn't handle trips to avoid surprising
thermal shutdown.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
---
 drivers/thermal/intel/intel_pch_thermal.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c
index 3b813ebb6ca1..e55e6318d733 100644
--- a/drivers/thermal/intel/intel_pch_thermal.c
+++ b/drivers/thermal/intel/intel_pch_thermal.c
@@ -270,6 +270,10 @@ static struct thermal_zone_device_ops tzd_ops = {
 	.get_trip_temp = pch_get_trip_temp,
 };
 
+static struct thermal_zone_params tzd_params = {
+	.userspace = true,
+};
+
 enum board_ids {
 	board_hsw,
 	board_wpt,
@@ -346,21 +350,16 @@ static int intel_pch_thermal_probe(struct pci_dev *pdev,
 		goto error_cleanup;
 
 	ptd->tzd = thermal_zone_device_register(bi->name, nr_trips, 0, ptd,
-						&tzd_ops, NULL, 0, 0);
+						&tzd_ops, &tzd_params, 0, 0);
 	if (IS_ERR(ptd->tzd)) {
 		dev_err(&pdev->dev, "Failed to register thermal zone %s\n",
 			bi->name);
 		err = PTR_ERR(ptd->tzd);
 		goto error_cleanup;
 	}
-	err = thermal_zone_device_enable(ptd->tzd);
-	if (err)
-		goto err_unregister;
 
 	return 0;
 
-err_unregister:
-	thermal_zone_device_unregister(ptd->tzd);
 error_cleanup:
 	iounmap(ptd->hw_base);
 error_release:
-- 
2.29.2

Re: [PATCH 1/3] thermal: core: Add indication for userspace usage

[Matthew Garrett]

On Sun, Nov 29, 2020 at 9:36 PM Kai-Heng Feng
<kai.heng.feng@canonical.com> wrote:
>
> We are seeing thermal shutdown on Intel based mobile workstations, the
> shutdown happens during the first trip handle in
> thermal_zone_device_register():
> kernel: thermal thermal_zone15: critical temperature reached (101 C), shutting down

Is the temperature reported by the thermal zone actually correct here?
101 C seems extremely excessive.

Re: [PATCH 1/3] thermal: core: Add indication for userspace usage

[Kai-Heng Feng]

On Tue, Dec 15, 2020 at 2:22 AM Matthew Garrett <mjg59@google.com> wrote:
>
> On Sun, Nov 29, 2020 at 9:36 PM Kai-Heng Feng
> <kai.heng.feng@canonical.com> wrote:
> >
> > We are seeing thermal shutdown on Intel based mobile workstations, the
> > shutdown happens during the first trip handle in
> > thermal_zone_device_register():
> > kernel: thermal thermal_zone15: critical temperature reached (101 C), shutting down
>
> Is the temperature reported by the thermal zone actually correct here?
> 101 C seems extremely excessive.

According to ODM/OEM, it's correct.
It's a short period when Intel Turbo Boost kicks in.

Kai-Heng

Re: [PATCH 2/3] thermal: int340x: Indicate userspace usage

[Kai-Heng Feng]

> On Nov 30, 2020, at 13:29, Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> wrote:
> 
> On Sun, 2020-11-29 at 01:54 +0800, Kai-Heng Feng wrote:
>> The device isn't present under ACPI ThermalZone, and there's a
>> dedicated
>> userspace daemon for this thermal device.
>> 
>> Let thermal core know it shouldn't handle trips to avoid surprising
>> thermal shutdown.
>> 
>> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
>> ---
>> drivers/thermal/intel/int340x_thermal/int3400_thermal.c     | 1 +
>> .../thermal/intel/int340x_thermal/int340x_thermal_zone.c    | 6 +---
>> --
>> 2 files changed, 2 insertions(+), 5 deletions(-)
>> 
>> diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
>> b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
>> index 0966551cbaaa..2002bc96eb3c 100644
>> --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
>> +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
>> @@ -439,6 +439,7 @@ static struct thermal_zone_device_ops
>> int3400_thermal_ops = {
>> static struct thermal_zone_params int3400_thermal_params = {
>> 	.governor_name = "user_space",
>> 	.no_hwmon = true,
>> +	.userspace = true,
> I am copied on only this patch, so I don't know what is this attribute?
> I think it is new.

Ok. The first one doesn't seem to be sent out correctly.

Series resent.

> 
>> };
>> 
>> static void int3400_setup_gddv(struct int3400_thermal_priv *priv)
>> diff --git
>> a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
>> b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
>> index 6e479deff76b..a103eb42ef2d 100644
>> --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
>> +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
>> @@ -208,6 +208,7 @@ EXPORT_SYMBOL_GPL(int340x_thermal_read_trips);
>> static struct thermal_zone_params int340x_thermal_params = {
>> 	.governor_name = "user_space",
>> 	.no_hwmon = true,
>> +	.userspace = true,
>> };
>> 
>> struct int34x_thermal_zone *int340x_thermal_zone_add(struct
>> acpi_device *adev,
>> @@ -259,14 +260,9 @@ struct int34x_thermal_zone
>> *int340x_thermal_zone_add(struct acpi_device *adev,
>> 		ret = PTR_ERR(int34x_thermal_zone->zone);
>> 		goto err_thermal_zone;
>> 	}
>> -	ret = thermal_zone_device_enable(int34x_thermal_zone->zone);
>> -	if (ret)
>> -		goto err_enable;
> 
> What is the effect of this?
> The INT340X zones don't need to poll for temperature. When HW notifies
> then user space gets notified via user space governor. Not sure if the
> not enabling break that path.

thermal_zone_device_disable()
  thermal_notify_tz_disable()
    thermal_genl_send_event(THERMAL_GENL_EVENT_TZ_DISABLE, &p)

I think it doesn't affect user_space governor.

Kai-Heng

> 
> Thanks,
> Srinivas
> 
>> 
>> 	return int34x_thermal_zone;
>> 
>> -err_enable:
>> -	thermal_zone_device_unregister(int34x_thermal_zone->zone);
>> err_thermal_zone:
>> 	acpi_lpat_free_conversion_table(int34x_thermal_zone-
>>> lpat_table);
>> 	kfree(int34x_thermal_zone->aux_trips);

Re: [PATCH 2/3] thermal: int340x: Indicate userspace usage

[Srinivas Pandruvada]

On Sun, 2020-11-29 at 01:54 +0800, Kai-Heng Feng wrote:
> The device isn't present under ACPI ThermalZone, and there's a
> dedicated
> userspace daemon for this thermal device.
> 
> Let thermal core know it shouldn't handle trips to avoid surprising
> thermal shutdown.
> 
> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> ---
>  drivers/thermal/intel/int340x_thermal/int3400_thermal.c     | 1 +
>  .../thermal/intel/int340x_thermal/int340x_thermal_zone.c    | 6 +---
> --
>  2 files changed, 2 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> index 0966551cbaaa..2002bc96eb3c 100644
> --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> @@ -439,6 +439,7 @@ static struct thermal_zone_device_ops
> int3400_thermal_ops = {
>  static struct thermal_zone_params int3400_thermal_params = {
>  	.governor_name = "user_space",
>  	.no_hwmon = true,
> +	.userspace = true,
I am copied on only this patch, so I don't know what is this attribute?
I think it is new.

>  };
>  
>  static void int3400_setup_gddv(struct int3400_thermal_priv *priv)
> diff --git
> a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> index 6e479deff76b..a103eb42ef2d 100644
> --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> @@ -208,6 +208,7 @@ EXPORT_SYMBOL_GPL(int340x_thermal_read_trips);
>  static struct thermal_zone_params int340x_thermal_params = {
>  	.governor_name = "user_space",
>  	.no_hwmon = true,
> +	.userspace = true,
>  };
>  
>  struct int34x_thermal_zone *int340x_thermal_zone_add(struct
> acpi_device *adev,
> @@ -259,14 +260,9 @@ struct int34x_thermal_zone
> *int340x_thermal_zone_add(struct acpi_device *adev,
>  		ret = PTR_ERR(int34x_thermal_zone->zone);
>  		goto err_thermal_zone;
>  	}
> -	ret = thermal_zone_device_enable(int34x_thermal_zone->zone);
> -	if (ret)
> -		goto err_enable;

What is the effect of this?
The INT340X zones don't need to poll for temperature. When HW notifies
then user space gets notified via user space governor. Not sure if the
not enabling break that path.

Thanks,
Srinivas

>  
>  	return int34x_thermal_zone;
>  
> -err_enable:
> -	thermal_zone_device_unregister(int34x_thermal_zone->zone);
>  err_thermal_zone:
>  	acpi_lpat_free_conversion_table(int34x_thermal_zone-
> >lpat_table);
>  	kfree(int34x_thermal_zone->aux_trips);

[PATCH 2/3] thermal: int340x: Indicate userspace usage

[Kai-Heng Feng]

The device isn't present under ACPI ThermalZone, and there's a dedicated
userspace daemon for this thermal device.

Let thermal core know it shouldn't handle trips to avoid surprising
thermal shutdown.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
---
 drivers/thermal/intel/int340x_thermal/int3400_thermal.c     | 1 +
 .../thermal/intel/int340x_thermal/int340x_thermal_zone.c    | 6 +-----
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index 0966551cbaaa..2002bc96eb3c 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -439,6 +439,7 @@ static struct thermal_zone_device_ops int3400_thermal_ops = {
 static struct thermal_zone_params int3400_thermal_params = {
 	.governor_name = "user_space",
 	.no_hwmon = true,
+	.userspace = true,
 };
 
 static void int3400_setup_gddv(struct int3400_thermal_priv *priv)
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 6e479deff76b..a103eb42ef2d 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -208,6 +208,7 @@ EXPORT_SYMBOL_GPL(int340x_thermal_read_trips);
 static struct thermal_zone_params int340x_thermal_params = {
 	.governor_name = "user_space",
 	.no_hwmon = true,
+	.userspace = true,
 };
 
 struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
@@ -259,14 +260,9 @@ struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
 		ret = PTR_ERR(int34x_thermal_zone->zone);
 		goto err_thermal_zone;
 	}
-	ret = thermal_zone_device_enable(int34x_thermal_zone->zone);
-	if (ret)
-		goto err_enable;
 
 	return int34x_thermal_zone;
 
-err_enable:
-	thermal_zone_device_unregister(int34x_thermal_zone->zone);
 err_thermal_zone:
 	acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
 	kfree(int34x_thermal_zone->aux_trips);
-- 
2.29.2