Re: [PATCH] thermal: qoriq: Only enable sites that actually exist

[Daniel Lezcano]

Hi Sebastian,

thanks for the fix.

On 29/11/2021 12:02, Sebastian Krzyszkowiak wrote:
> On i.MX8MQ, enabling monitoring sites that aren't connected to anything
> can cause unwanted side effects on some units. This seems to happen
> once some of these sites report out-of-range readings and results in
> sensor misbehavior, such as thermal zone readings getting stuck or even
> suddenly reporting an impossibly high value, triggering emergency
> shutdowns.
> 
> The datasheet lists all non-existent sites as "reserved" and doesn't
> make any guarantees about being able to enable them at all, so let's
> not do that.

The description of what does the patch is missing here.

> Fixes: 45038e03d633 ("thermal: qoriq: Enable all sensors before registering them")
> 
> Signed-off-by: Sebastian Krzyszkowiak <sebastian.krzyszkowiak@xxxxxxx>
> ---
>  drivers/thermal/qoriq_thermal.c | 63 ++++++++++++++++++++++-----------
>  1 file changed, 43 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/thermal/qoriq_thermal.c b/drivers/thermal/qoriq_thermal.c
> index 73049f9bea25..ef0848849ee2 100644
> --- a/drivers/thermal/qoriq_thermal.c
> +++ b/drivers/thermal/qoriq_thermal.c
> @@ -32,7 +32,6 @@
>  #define TMR_DISABLE	0x0
>  #define TMR_ME		0x80000000
>  #define TMR_ALPF	0x0c000000
> -#define TMR_MSITE_ALL	GENMASK(15, 0)
>  
>  #define REGS_TMTMIR	0x008	/* Temperature measurement interval Register */
>  #define TMTMIR_DEFAULT	0x0000000f
> @@ -129,33 +128,51 @@ static const struct thermal_zone_of_device_ops tmu_tz_ops = {
>  static int qoriq_tmu_register_tmu_zone(struct device *dev,
>  				       struct qoriq_tmu_data *qdata)
>  {
> -	int id;
> +	int ret = 0;
> +	struct device_node *np, *child, *sensor_np;
>  
> -	if (qdata->ver == TMU_VER1) {
> -		regmap_write(qdata->regmap, REGS_TMR,
> -			     TMR_MSITE_ALL | TMR_ME | TMR_ALPF);
> -	} else {
> -		regmap_write(qdata->regmap, REGS_V2_TMSR, TMR_MSITE_ALL);
> -		regmap_write(qdata->regmap, REGS_TMR, TMR_ME | TMR_ALPF_V2);
> -	}
> +	np = of_find_node_by_name(NULL, "thermal-zones");
> +	if (!np)
> +		return -ENODEV;
> +
> +	sensor_np = of_node_get(dev->of_node);
>  
> -	for (id = 0; id < SITES_MAX; id++) {
> +	for_each_available_child_of_node(np, child) {
>  		struct thermal_zone_device *tzd;
> -		struct qoriq_sensor *sensor = &qdata->sensor[id];
> -		int ret;
> +		struct qoriq_sensor *sensor;
> +		int id, site;
> +
> +		ret = thermal_zone_of_get_sensor_id(child, sensor_np, &id);
> +
> +		if (ret < 0) {
> +			dev_err(dev, "failed to get valid sensor id: %d\n", ret);
> +			of_node_put(child);
> +			break;
> +		}
>  
> +		sensor = &qdata->sensor[id];
>  		sensor->id = id;
>  
> +		/* Enable monitoring */
> +		if (qdata->ver == TMU_VER1) {
> +			site = 0x1 << (15 - id);
> +			regmap_update_bits(qdata->regmap, REGS_TMR,
> +					   site | TMR_ME | TMR_ALPF,
> +					   site | TMR_ME | TMR_ALPF);
> +		} else {
> +			site = 0x1 << id;
> +			regmap_update_bits(qdata->regmap, REGS_V2_TMSR, site, site);
> +			regmap_write(qdata->regmap, REGS_TMR, TMR_ME | TMR_ALPF_V2);
> +		}

Why not create the site mask in the loop and then call once the block
above out this loop?

>  		tzd = devm_thermal_zone_of_sensor_register(dev, id,
>  							   sensor,
>  							   &tmu_tz_ops);
> -		ret = PTR_ERR_OR_ZERO(tzd);
> -		if (ret) {
> -			if (ret == -ENODEV)
> -				continue;
> -
> -			regmap_write(qdata->regmap, REGS_TMR, TMR_DISABLE);
> -			return ret;
> +		if (IS_ERR(tzd)) {
> +			ret = PTR_ERR(tzd);
> +			dev_err(dev, "failed to register thermal zone: %d\n", ret);
> +			of_node_put(child);
> +			break;
>  		}
>  
>  		if (devm_thermal_add_hwmon_sysfs(tzd))
> @@ -164,7 +181,13 @@ static int qoriq_tmu_register_tmu_zone(struct device *dev,
>  
>  	}
>  
> -	return 0;
> +	of_node_put(sensor_np);
> +	of_node_put(np);
> +
> +	if (ret)
> +		regmap_write(qdata->regmap, REGS_TMR, TMR_DISABLE);
> +
> +	return ret;
>  }
>  
>  static int qoriq_tmu_calibration(struct device *dev,
> 


-- 
<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