Re: [PATCH v9 2/3] reboot: Introduce thermal_zone_device_critical_reboot()

[Daniel Lezcano <daniel.lezcano@linaro.org>]

On 01/10/2023 05:00, Fabio Estevam wrote:
> From: Fabio Estevam <festevam@denx.de>
> 
> Introduce thermal_zone_device_critical_reboot() to trigger an
> emergency reboot.
> 
> It is a counterpart of thermal_zone_device_critical() with the
> difference that it will force a reboot instead of shutdown.
> 
> The motivation for doing this is to allow the thermal subystem
> to trigger a reboot when the temperature reaches the critical
> temperature.
> 
> Signed-off-by: Fabio Estevam <festevam@denx.de>
> ---
> Changes since v8:
> - Introduce thermal_zone_device_critical_reboot() to accomodate
> Daniel's suggestions.
> 
>   drivers/thermal/thermal_core.c | 19 +++++++++++++++++--
>   include/linux/reboot.h         | 13 ++++++++++++-
>   include/linux/thermal.h        |  1 +
>   kernel/reboot.c                | 32 +++++++++++++++++++-------------
>   4 files changed, 49 insertions(+), 16 deletions(-)
> 
> diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
> index 38d393f139d8..277aafb294db 100644
> --- a/drivers/thermal/thermal_core.c
> +++ b/drivers/thermal/thermal_core.c
> @@ -313,21 +313,36 @@ static void handle_non_critical_trips(struct thermal_zone_device *tz, int trip)
>   		       def_governor->throttle(tz, trip);
>   }
>   
> -void thermal_zone_device_critical(struct thermal_zone_device *tz)
> +static void thermal_zone_device_shutdown(struct thermal_zone_device *tz, bool shutdown)

Probably nit picking but is it possible to rename to:

static void thermal_zone_device_halt(struct thermal_zone_device *tz, 
bool shutdown)


>   {
>   	/*
>   	 * poweroff_delay_ms must be a carefully profiled positive value.
>   	 * Its a must for forced_emergency_poweroff_work to be scheduled.
>   	 */
>   	int poweroff_delay_ms = CONFIG_THERMAL_EMERGENCY_POWEROFF_DELAY_MS;
> +	static const char *msg = "Temperature too high";

Why use 'static' ?

>   	dev_emerg(&tz->device, "%s: critical temperature reached, "
>   		  "shutting down\n", tz->type);

Now the function can do 'shutdown' or 'reboot', so the message should 
reflect that.

However, the reason will be displayed in the 
hw_protection_shutdown/reboot, so having:

dev_emerg(&tz->device, "%s: critical temperature reached\n", tz->type);

> -	hw_protection_shutdown("Temperature too high", poweroff_delay_ms);
> +	if (shutdown)
> +		hw_protection_shutdown(msg, poweroff_delay_ms);
> +	else
> +		hw_protection_reboot(msg, poweroff_delay_ms);
> +}
> +
> +void thermal_zone_device_critical(struct thermal_zone_device *tz)
> +{
> +	thermal_zone_device_shutdown(tz, true);
>   }
>   EXPORT_SYMBOL(thermal_zone_device_critical);

Rename to thermal_zone_device_critical_shutdown() for consistency (in a 
separate patch).

>   
> +void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz)
> +{
> +	thermal_zone_device_shutdown(tz, false);
> +}
> +EXPORT_SYMBOL(thermal_zone_device_critical_reboot);
> +
>   static void handle_critical_trips(struct thermal_zone_device *tz,
>   				  int trip, int trip_temp, enum thermal_trip_type trip_type)
>   {
> diff --git a/include/linux/reboot.h b/include/linux/reboot.h
> index c4cc3b89ced1..4683e117c753 100644
> --- a/include/linux/reboot.h
> +++ b/include/linux/reboot.h
> @@ -177,7 +177,18 @@ void ctrl_alt_del(void);
>   
>   extern void orderly_poweroff(bool force);
>   extern void orderly_reboot(void);
> -void hw_protection_shutdown(const char *reason, int ms_until_forced);
> +
> +void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown);
> +
> +static inline void hw_protection_reboot(const char *reason, int ms_until_forced)
> +{
> +	__hw_protection_shutdown(reason, ms_until_forced, false);
> +}
> +
> +static inline void hw_protection_shutdown(const char *reason, int ms_until_forced)
> +{
> +	__hw_protection_shutdown(reason, ms_until_forced, true);
> +}


Those changes should be in a separate patch.

>   /*
>    * Emergency restart, callable from an interrupt handler.
> diff --git a/include/linux/thermal.h b/include/linux/thermal.h
> index 6cfcae22ba12..c5ebb44ae8a6 100644
> --- a/include/linux/thermal.h
> +++ b/include/linux/thermal.h
> @@ -353,6 +353,7 @@ int thermal_zone_get_offset(struct thermal_zone_device *tz);
>   int thermal_zone_device_enable(struct thermal_zone_device *tz);
>   int thermal_zone_device_disable(struct thermal_zone_device *tz);
>   void thermal_zone_device_critical(struct thermal_zone_device *tz);
> +void thermal_zone_device_critical_reboot(struct thermal_zone_device *tz);
>   #else
>   static inline struct thermal_zone_device *thermal_zone_device_register_with_trips(
>   					const char *type,
> diff --git a/kernel/reboot.c b/kernel/reboot.c
> index 395a0ea3c7a8..8b3010b88ed6 100644
> --- a/kernel/reboot.c
> +++ b/kernel/reboot.c
> @@ -957,21 +957,25 @@ static void hw_failure_emergency_poweroff(int poweroff_delay_ms)
>   }
>   
>   /**
> - * hw_protection_shutdown - Trigger an emergency system poweroff
> + * __hw_protection_shutdown - Trigger an emergency system shutdown or reboot
>    *
> - * @reason:		Reason of emergency shutdown to be printed.
> - * @ms_until_forced:	Time to wait for orderly shutdown before tiggering a
> - *			forced shudown. Negative value disables the forced
> - *			shutdown.
> + * @reason:		Reason of emergency shutdown or reboot to be printed.
> + * @ms_until_forced:	Time to wait for orderly shutdown or reboot before
> + *			triggering it. Negative value disables the forced
> + *			shutdown or reboot.
> + * @shutdown:		If true, indicates that a shutdown will happen
> + *			after the critical tempeature is reached.
> + *			If false, indicates that a reboot will happen
> + *			after the critical tempeature is reached.
>    *
> - * Initiate an emergency system shutdown in order to protect hardware from
> - * further damage. Usage examples include a thermal protection or a voltage or
> - * current regulator failures.
> - * NOTE: The request is ignored if protection shutdown is already pending even
> - * if the previous request has given a large timeout for forced shutdown.
> + * Initiate an emergency system shutdown or reboot in order to protect
> + * hardware from further damage. Usage examples include a thermal protection.
> + * NOTE: The request is ignored if protection shutdown or reboot is already
> + * pending even if the previous request has given a large timeout for forced
> + * shutdown/reboot.
>    * Can be called from any context.
>    */
> -void hw_protection_shutdown(const char *reason, int ms_until_forced)
> +void __hw_protection_shutdown(const char *reason, int ms_until_forced, bool shutdown)
>   {
>   	static atomic_t allow_proceed = ATOMIC_INIT(1);
>   
> @@ -986,9 +990,11 @@ void hw_protection_shutdown(const char *reason, int ms_until_forced)
>   	 * orderly_poweroff failure
>   	 */
>   	hw_failure_emergency_poweroff(ms_until_forced);
> -	orderly_poweroff(true);
> +	if (shutdown)
> +		orderly_poweroff(true);
> +	else
> +		orderly_reboot();
>   }
> -EXPORT_SYMBOL_GPL(hw_protection_shutdown);
Same comment

>   static int __init reboot_setup(char *str)
>   {

-- 
<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