diff mbox series

[1/2] thermal: int340x: Add critical callback to override default shutdown behavior

Message ID 20201221135206.17671-1-kai.heng.feng@canonical.com
State New
Headers show
Series [1/2] thermal: int340x: Add critical callback to override default shutdown behavior | expand

Commit Message

Kai-Heng Feng Dec. 21, 2020, 1:52 p.m. UTC
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 namespace. 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.

As int340x device isn't present under ACPI ThermalZone, override the
default .critical callback to prevent surprising thermal shutdown.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
---
 drivers/thermal/intel/int340x_thermal/int3400_thermal.c     | 6 ++++++
 .../thermal/intel/int340x_thermal/int340x_thermal_zone.c    | 6 ++++++
 2 files changed, 12 insertions(+)

Comments

Kai-Heng Feng Dec. 21, 2020, 3 p.m. UTC | #1
On Mon, Dec 21, 2020 at 9:59 PM Daniel Lezcano
<daniel.lezcano@linaro.org> wrote:
>
> On 21/12/2020 14:52, Kai-Heng Feng 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
> >
> > 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 namespace. 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.
> >
> > As int340x device isn't present under ACPI ThermalZone, override the
> > default .critical callback to prevent surprising thermal shutdown.
> >
> > Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
>
> I'll submit those changes for v5.11-rc1 and change the subject by:
>
> thermal: int340x: Fix unexpected shutdown at critical temperature
> thermal: pch: Fix unexpected shutdown at critical temperature
>
> Sounds good ?

Sounds good to me. Thanks!

Kai-Heng

>
> > ---
> >  drivers/thermal/intel/int340x_thermal/int3400_thermal.c     | 6 ++++++
> >  .../thermal/intel/int340x_thermal/int340x_thermal_zone.c    | 6 ++++++
> >  2 files changed, 12 insertions(+)
> >
> > diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> > index 823354a1a91a..9778a6dba939 100644
> > --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> > +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> > @@ -431,9 +431,15 @@ static int int3400_thermal_change_mode(struct thermal_zone_device *thermal,
> >       return result;
> >  }
> >
> > +static void int3400_thermal_critical(struct thermal_zone_device *thermal)
> > +{
> > +     dev_dbg(&thermal->device, "%s: critical temperature reached\n", thermal->type);
> > +}
> > +
> >  static struct thermal_zone_device_ops int3400_thermal_ops = {
> >       .get_temp = int3400_thermal_get_temp,
> >       .change_mode = int3400_thermal_change_mode,
> > +     .critical = int3400_thermal_critical,
> >  };
> >
> >  static struct thermal_zone_params int3400_thermal_params = {
> > diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> > index 6e479deff76b..d1248ba943a4 100644
> > --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> > +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> > @@ -146,12 +146,18 @@ static int int340x_thermal_get_trip_hyst(struct thermal_zone_device *zone,
> >       return 0;
> >  }
> >
> > +static void int340x_thermal_critical(struct thermal_zone_device *zone)
> > +{
> > +     dev_dbg(&zone->device, "%s: critical temperature reached\n", zone->type);
> > +}
> > +
> >  static struct thermal_zone_device_ops int340x_thermal_zone_ops = {
> >       .get_temp       = int340x_thermal_get_zone_temp,
> >       .get_trip_temp  = int340x_thermal_get_trip_temp,
> >       .get_trip_type  = int340x_thermal_get_trip_type,
> >       .set_trip_temp  = int340x_thermal_set_trip_temp,
> >       .get_trip_hyst =  int340x_thermal_get_trip_hyst,
> > +     .critical       = int340x_thermal_critical,
> >  };
> >
> >  static int int340x_thermal_get_trip_config(acpi_handle handle, char *name,
> >
>
>
> --
> <http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs
>
> Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
> <http://twitter.com/#!/linaroorg> Twitter |
> <http://www.linaro.org/linaro-blog/> Blog
Srinivas Pandruvada Dec. 21, 2020, 4:55 p.m. UTC | #2
On Mon, 2020-12-21 at 21:52 +0800, Kai-Heng Feng 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
> 
> 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 namespace. 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.
> 
> As int340x device isn't present under ACPI ThermalZone, override the
> default .critical callback to prevent surprising thermal shutdown.
> 
> Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> ---
>  drivers/thermal/intel/int340x_thermal/int3400_thermal.c     | 6
> ++++++
>  .../thermal/intel/int340x_thermal/int340x_thermal_zone.c    | 6
> ++++++
>  2 files changed, 12 insertions(+)
> 
> diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> index 823354a1a91a..9778a6dba939 100644
> --- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> +++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
> @@ -431,9 +431,15 @@ static int int3400_thermal_change_mode(struct
> thermal_zone_device *thermal,
>         return result;
>  }
>  
> +static void int3400_thermal_critical(struct thermal_zone_device
> *thermal)
> +{
> +       dev_dbg(&thermal->device, "%s: critical temperature
> reached\n", thermal->type);
> +}
> +
>  static struct thermal_zone_device_ops int3400_thermal_ops = {
>         .get_temp = int3400_thermal_get_temp,
>         .change_mode = int3400_thermal_change_mode,
> +       .critical = int3400_thermal_critical,
>  };

You don't need for int3400 device. This is a fake sensor.

>  
>  static struct thermal_zone_params int3400_thermal_params = {
> diff --git
> a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> index 6e479deff76b..d1248ba943a4 100644
> --- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> +++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
> @@ -146,12 +146,18 @@ static int int340x_thermal_get_trip_hyst(struct
> thermal_zone_device *zone,
>         return 0;
>  }
>  
> +static void int340x_thermal_critical(struct thermal_zone_device
> *zone)
> +{
> +       dev_dbg(&zone->device, "%s: critical temperature reached\n",
> zone->type);
> +}
> +
>  static struct thermal_zone_device_ops int340x_thermal_zone_ops = {
>         .get_temp       = int340x_thermal_get_zone_temp,
>         .get_trip_temp  = int340x_thermal_get_trip_temp,
>         .get_trip_type  = int340x_thermal_get_trip_type,
>         .set_trip_temp  = int340x_thermal_set_trip_temp,
>         .get_trip_hyst =  int340x_thermal_get_trip_hyst,
> +       .critical       = int340x_thermal_critical,
>  };
>  
>  static int int340x_thermal_get_trip_config(acpi_handle handle, char
> *name,

Thanks,
Srinivas
Srinivas Pandruvada Dec. 21, 2020, 4:57 p.m. UTC | #3
On Mon, 2020-12-21 at 17:03 +0100, Daniel Lezcano wrote:
> On 21/12/2020 16:00, Kai-Heng Feng wrote:
> > On Mon, Dec 21, 2020 at 9:59 PM Daniel Lezcano
> > <daniel.lezcano@linaro.org> wrote:
> > > 
> > > On 21/12/2020 14:52, Kai-Heng Feng 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
> > > > 
> > > > 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 namespace. 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.
> > > > 
> > > > As int340x device isn't present under ACPI ThermalZone,
> > > > override the
> > > > default .critical callback to prevent surprising thermal
> > > > shutdown.
> > > > 
> > > > Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
> > > 
> > > I'll submit those changes for v5.11-rc1 and change the subject
> > > by:
> > > 
> > > thermal: int340x: Fix unexpected shutdown at critical temperature
> > > thermal: pch: Fix unexpected shutdown at critical temperature
> > > 
> > > Sounds good ?
> > 
> > Sounds good to me. Thanks!
> > 
> > Kai-Heng
> 
> Rui, Srinivas? Are you ok with the changes ?
I have minor comment in one of the patch. But that is harmless.
So changes are fine.

Thanks,
Srinivas


> 
>
diff mbox series

Patch

diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
index 823354a1a91a..9778a6dba939 100644
--- a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -431,9 +431,15 @@  static int int3400_thermal_change_mode(struct thermal_zone_device *thermal,
 	return result;
 }
 
+static void int3400_thermal_critical(struct thermal_zone_device *thermal)
+{
+	dev_dbg(&thermal->device, "%s: critical temperature reached\n", thermal->type);
+}
+
 static struct thermal_zone_device_ops int3400_thermal_ops = {
 	.get_temp = int3400_thermal_get_temp,
 	.change_mode = int3400_thermal_change_mode,
+	.critical = int3400_thermal_critical,
 };
 
 static struct thermal_zone_params int3400_thermal_params = {
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
index 6e479deff76b..d1248ba943a4 100644
--- a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -146,12 +146,18 @@  static int int340x_thermal_get_trip_hyst(struct thermal_zone_device *zone,
 	return 0;
 }
 
+static void int340x_thermal_critical(struct thermal_zone_device *zone)
+{
+	dev_dbg(&zone->device, "%s: critical temperature reached\n", zone->type);
+}
+
 static struct thermal_zone_device_ops int340x_thermal_zone_ops = {
 	.get_temp       = int340x_thermal_get_zone_temp,
 	.get_trip_temp	= int340x_thermal_get_trip_temp,
 	.get_trip_type	= int340x_thermal_get_trip_type,
 	.set_trip_temp	= int340x_thermal_set_trip_temp,
 	.get_trip_hyst =  int340x_thermal_get_trip_hyst,
+	.critical	= int340x_thermal_critical,
 };
 
 static int int340x_thermal_get_trip_config(acpi_handle handle, char *name,