Re: [PATCHv3 1/1] thermal: cpu_cooling: check for the readiness of cpufreq layer

[Russell King - ARM Linux <linux@arm.linux.org.uk>]

On Fri, Nov 28, 2014 at 10:53:30AM -0400, Eduardo Valentin wrote:
> diff --git a/drivers/thermal/samsung/exynos_thermal_common.c b/drivers/thermal/samsung/exynos_thermal_common.c
> index 3f5ad25..d4eaa1b 100644
> --- a/drivers/thermal/samsung/exynos_thermal_common.c
> +++ b/drivers/thermal/samsung/exynos_thermal_common.c
> @@ -371,9 +371,10 @@ int exynos_register_thermal(struct thermal_sensor_conf *sensor_conf)
>  		th_zone->cool_dev[th_zone->cool_dev_size] =
>  					cpufreq_cooling_register(&mask_val);
>  		if (IS_ERR(th_zone->cool_dev[th_zone->cool_dev_size])) {
> -			dev_err(sensor_conf->dev,
> -				"Failed to register cpufreq cooling device\n");
> -			ret = -EINVAL;
> +			ret = PTR_ERR(th_zone->cool_dev[th_zone->cool_dev_size]);
> +			if (ret != -EPROBE_DEFER)
> +				dev_err(sensor_conf->dev,
> +					"Failed to register cpufreq cooling device\n");

Something which bugs me quite a lot is when there is an error code (which
tells you why something didn't work) and you have an error message, and
the error message doesn't bother printing the error code.

You might as well just print "Failed\n" and leave it at that, or md5sum
the error message and print the sum instead. :)

Knowing why something failed allows you to read the source, and find
possible reasons for the failure (which could come down to one reason)
and allows faster resolution of the problem.

-- 
FTTC broadband for 0.8mile line: currently at 9.5Mbps down 400kbps up
according to speedtest.net.