Re: [PATCH v2 05/10] PM: sleep: stats: Call dpm_save_failed_step() at most once per phase

[Stanislaw Gruszka]

On Mon, Jan 29, 2024 at 05:24:04PM +0100, Rafael J. Wysocki wrote:
> From: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
> 
> If the handling of two or more devices fails in one suspend-resume
> phase, it should be counted once in the statistics which is not
> guaranteed to happen during system-wide resume of devices due to
> the possible asynchronous execution of device callbacks.
> 
> Address this by using the async_error static variable during system-wide
> device resume to indicate that there has been a device resume error and
> the given suspend-resume phase should be counted as failing.
> 
> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@xxxxxxxxxxxxxxx>

> ---
> 
> v1 -> v2: No changes.
> 
> ---
>  drivers/base/power/main.c |   20 +++++++++++++++++---
>  1 file changed, 17 insertions(+), 3 deletions(-)
> 
> Index: linux-pm/drivers/base/power/main.c
> ===================================================================
> --- linux-pm.orig/drivers/base/power/main.c
> +++ linux-pm/drivers/base/power/main.c
> @@ -685,7 +685,7 @@ Out:
>  	TRACE_RESUME(error);
>  
>  	if (error) {
> -		dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
> +		async_error = error;
>  		dpm_save_failed_dev(dev_name(dev));
>  		pm_dev_err(dev, state, async ? " async noirq" : " noirq", error);
>  	}
> @@ -705,6 +705,9 @@ static void dpm_noirq_resume_devices(pm_
>  	ktime_t starttime = ktime_get();
>  
>  	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, true);
> +
> +	async_error = 0;
> +
>  	mutex_lock(&dpm_list_mtx);
>  	pm_transition = state;
>  
> @@ -734,6 +737,9 @@ static void dpm_noirq_resume_devices(pm_
>  	mutex_unlock(&dpm_list_mtx);
>  	async_synchronize_full();
>  	dpm_show_time(starttime, state, 0, "noirq");
> +	if (async_error)
> +		dpm_save_failed_step(SUSPEND_RESUME_NOIRQ);
> +
>  	trace_suspend_resume(TPS("dpm_resume_noirq"), state.event, false);
>  }
>  
> @@ -815,7 +821,7 @@ Out:
>  	complete_all(&dev->power.completion);
>  
>  	if (error) {
> -		dpm_save_failed_step(SUSPEND_RESUME_EARLY);
> +		async_error = error;
>  		dpm_save_failed_dev(dev_name(dev));
>  		pm_dev_err(dev, state, async ? " async early" : " early", error);
>  	}
> @@ -839,6 +845,9 @@ void dpm_resume_early(pm_message_t state
>  	ktime_t starttime = ktime_get();
>  
>  	trace_suspend_resume(TPS("dpm_resume_early"), state.event, true);
> +
> +	async_error = 0;
> +
>  	mutex_lock(&dpm_list_mtx);
>  	pm_transition = state;
>  
> @@ -868,6 +877,9 @@ void dpm_resume_early(pm_message_t state
>  	mutex_unlock(&dpm_list_mtx);
>  	async_synchronize_full();
>  	dpm_show_time(starttime, state, 0, "early");
> +	if (async_error)
> +		dpm_save_failed_step(SUSPEND_RESUME_EARLY);
> +
>  	trace_suspend_resume(TPS("dpm_resume_early"), state.event, false);
>  }
>  
> @@ -971,7 +983,7 @@ static void device_resume(struct device
>  	TRACE_RESUME(error);
>  
>  	if (error) {
> -		dpm_save_failed_step(SUSPEND_RESUME);
> +		async_error = error;
>  		dpm_save_failed_dev(dev_name(dev));
>  		pm_dev_err(dev, state, async ? " async" : "", error);
>  	}
> @@ -1030,6 +1042,8 @@ void dpm_resume(pm_message_t state)
>  	mutex_unlock(&dpm_list_mtx);
>  	async_synchronize_full();
>  	dpm_show_time(starttime, state, 0, NULL);
> +	if (async_error)
> +		dpm_save_failed_step(SUSPEND_RESUME);
>  
>  	cpufreq_resume();
>  	devfreq_resume();
> 
> 
>