Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <c07b9fe7-5d28-c72a-a9d9-e612b07b0b75@linaro.org>
Date:   Wed, 16 Feb 2022 19:44:26 +0100
MIME-Version: 1.0
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.5.0
Subject: Re: [PATCH v5] drivers: thermal: clear all mitigation when thermal
 zone is disabled
Content-Language: en-US
To:     Manaf Meethalavalappu Pallikunhi <quic_manafm@quicinc.com>,
        Lukasz Luba <lukasz.luba@arm.com>,
        "Rafael J . Wysocki" <rafael@kernel.org>,
        Amit Kucheria <amitk@kernel.org>,
        Zhang Rui <rui.zhang@intel.com>
Cc:     linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org
References: <1643307093-22501-1-git-send-email-quic_manafm@quicinc.com>
From:   Daniel Lezcano <daniel.lezcano@linaro.org>
In-Reply-To: <1643307093-22501-1-git-send-email-quic_manafm@quicinc.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Precedence: bulk

On 27/01/2022 19:11, Manaf Meethalavalappu Pallikunhi wrote:
> Whenever a thermal zone is in trip violated state, there is a chance
> that the same thermal zone mode can be disabled either via
> thermal core API or via thermal zone sysfs. Once it is disabled,
> the framework bails out any re-evaluation of thermal zone. It leads
> to a case where if it is already in mitigation state, it will stay
> the same state forever.
> 
> To avoid above mentioned issue, add support to bind/unbind
> governor from thermal zone during thermal zone mode change request
> and clear all existing throttling in governor unbind_from_tz()
> callback.

Manaf,

can you clarify when / why is needed to disable a thermal zone at runtime?


> Suggested-by: Daniel Lezcano <daniel.lezcano@linaro.org>
> Signed-off-by: Manaf Meethalavalappu Pallikunhi <quic_manafm@quicinc.com>
> ---
>   drivers/thermal/gov_power_allocator.c |  3 +++
>   drivers/thermal/gov_step_wise.c       | 26 ++++++++++++++++++++++++++
>   drivers/thermal/thermal_core.c        | 31 +++++++++++++++++++++++++++----
>   3 files changed, 56 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
> index 13e3757..9ff0c5f 100644
> --- a/drivers/thermal/gov_power_allocator.c
> +++ b/drivers/thermal/gov_power_allocator.c
> @@ -696,6 +696,9 @@ static void power_allocator_unbind(struct thermal_zone_device *tz)
>   
>   	dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
>   
> +	tz->passive = 0;
> +	allow_maximum_power(tz, true);
> +
>   	if (params->allocated_tzp) {
>   		kfree(tz->tzp);
>   		tz->tzp = NULL;
> diff --git a/drivers/thermal/gov_step_wise.c b/drivers/thermal/gov_step_wise.c
> index 12acb12..2d2186b 100644
> --- a/drivers/thermal/gov_step_wise.c
> +++ b/drivers/thermal/gov_step_wise.c
> @@ -168,6 +168,31 @@ static void thermal_zone_trip_update(struct thermal_zone_device *tz, int trip)
>   }
>   
>   /**
> + * step_wise_unbind() - unbind the step_wise governor to a thermal zone
> + * @tz:	thermal zone to unbind it to
> + *
> + * Clear all previous throttling and reset passive counter.
> + *
> + */
> +static void step_wise_unbind(struct thermal_zone_device *tz)
> +{
> +	struct thermal_instance *instance;
> +
> +	dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
> +
> +	mutex_lock(&tz->lock);
> +	tz->passive = 0;
> +	list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
> +		instance->initialized = false;
> +		instance->target = THERMAL_NO_TARGET;
> +		mutex_lock(&instance->cdev->lock);
> +		__thermal_cdev_update(instance->cdev);
> +		mutex_unlock(&instance->cdev->lock);
> +	}
> +	mutex_unlock(&tz->lock);
> +}
> +
> +/**
>    * step_wise_throttle - throttles devices associated with the given zone
>    * @tz: thermal_zone_device
>    * @trip: trip point index
> @@ -196,6 +221,7 @@ static int step_wise_throttle(struct thermal_zone_device *tz, int trip)
>   
>   static struct thermal_governor thermal_gov_step_wise = {
>   	.name		= "step_wise",
> +	.unbind_from_tz	= step_wise_unbind,
>   	.throttle	= step_wise_throttle,
>   };
>   THERMAL_GOVERNOR_DECLARE(thermal_gov_step_wise);
> diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
> index 82654dc..34726d3 100644
> --- a/drivers/thermal/thermal_core.c
> +++ b/drivers/thermal/thermal_core.c
> @@ -274,6 +274,26 @@ static int __init thermal_register_governors(void)
>   	return ret;
>   }
>   
> +static void thermal_governor_attach(struct thermal_zone_device *tz)
> +{
> +	mutex_lock(&thermal_governor_lock);
> +	if (tz->governor && tz->governor->bind_to_tz) {
> +		if (tz->governor->bind_to_tz(tz))
> +			dev_err(&tz->device,
> +				"governor %s failed to bind to thermal zone %s\n",
> +				tz->governor->name, tz->type);
> +	}
> +	mutex_unlock(&thermal_governor_lock);
> +}
> +
> +static void thermal_governor_detach(struct thermal_zone_device *tz)
> +{
> +	mutex_lock(&thermal_governor_lock);
> +	if (tz->governor && tz->governor->unbind_from_tz)
> +		tz->governor->unbind_from_tz(tz);
> +	mutex_unlock(&thermal_governor_lock);
> +}
> +
>   /*
>    * Zone update section: main control loop applied to each zone while monitoring
>    *
> @@ -449,12 +469,15 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
>   
>   	mutex_unlock(&tz->lock);
>   
> -	thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
> -
> -	if (mode == THERMAL_DEVICE_ENABLED)
> +	if (mode == THERMAL_DEVICE_ENABLED) {
> +		thermal_governor_attach(tz);
> +		thermal_zone_device_init(tz);
> +		thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
>   		thermal_notify_tz_enable(tz->id);
> -	else
> +	} else {
> +		thermal_governor_detach(tz);
>   		thermal_notify_tz_disable(tz->id);
> +	}
>   
>   	return ret;
>   }


-- 
<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