On Tue, Oct 13, 2020 at 6:24 PM Michael Kao <michael.kao@xxxxxxxxxxxx> wrote:
>
> Provide thermal zone to read thermal sensor
> in the SoC. We can read all the thermal sensors
> value in the SoC by the node /sys/class/thermal/
>
> In mtk_thermal_bank_temperature, return -EAGAIN instead of -EACCESS
> on the first read of sensor that often are bogus values.
>
> This can avoid following warning on boot:
>
> thermal thermal_zone6: failed to read out thermal zone (-13)
>
> Signed-off-by: Michael Kao <michael.kao@xxxxxxxxxxxx>
> Signed-off-by: Hsin-Yi Wang <hsinyi@xxxxxxxxxxxx>
> ---
> drivers/thermal/mtk_thermal.c | 99 +++++++++++++++++++++++++++--------
> 1 file changed, 76 insertions(+), 23 deletions(-)
>
> diff --git a/drivers/thermal/mtk_thermal.c b/drivers/thermal/mtk_thermal.c
> index 0bd7aa564bc2..43c7bdbc147f 100644
> --- a/drivers/thermal/mtk_thermal.c
> +++ b/drivers/thermal/mtk_thermal.c
> @@ -245,6 +245,11 @@ enum mtk_thermal_version {
>
> struct mtk_thermal;
>
> +struct mtk_thermal_zone {
> + struct mtk_thermal *mt;
> + int id;
> +};
> +
> struct thermal_bank_cfg {
> unsigned int num_sensors;
> const int *sensors;
> @@ -637,6 +642,32 @@ static void mtk_thermal_put_bank(struct mtk_thermal_bank *bank)
> mutex_unlock(&mt->lock);
> }
>
> +static u32 _get_sensor_temp(struct mtk_thermal *mt, int id)
> +{
> + u32 raw;
> + int temp;
> +
> + const struct mtk_thermal_data *conf = mt->conf;
nit: You only use conf once, so I'd just use mt->conf->msr[id] below.
(or at least use conf->version instead of mt->conf->version just below)
> +
> + raw = readl(mt->thermal_base + conf->msr[id]);
> +
> + if (mt->conf->version == MTK_THERMAL_V1)
> + temp = raw_to_mcelsius_v1(mt, id, raw);
> + else
> + temp = raw_to_mcelsius_v2(mt, id, raw);
> +
> + /*
> + * The first read of a sensor often contains very high bogus
> + * temperature value. Filter these out so that the system does
> + * not immediately shut down.
> + */
> +
> + if (temp > 200000)
> + return -EAGAIN;
nit: one space between return and -EAGAIN.
> + else
> + return temp;
ditto.
> +}
> +
> /**
> * mtk_thermal_bank_temperature - get the temperature of a bank
> * @bank: The bank
> @@ -649,26 +680,10 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank)
> struct mtk_thermal *mt = bank->mt;
> const struct mtk_thermal_data *conf = mt->conf;
nit: Since this is now only used once, drop this variable?
> int i, temp = INT_MIN, max = INT_MIN;
> - u32 raw;
>
> for (i = 0; i < conf->bank_data[bank->id].num_sensors; i++) {
> - raw = readl(mt->thermal_base + conf->msr[i]);
> -
> - if (mt->conf->version == MTK_THERMAL_V1) {
> - temp = raw_to_mcelsius_v1(
> - mt, conf->bank_data[bank->id].sensors[i], raw);
The new version of the code does this instead:
temp = raw_to_mcelsius_v1(mt, i, raw);
What's the difference between conf->bank_data[bank->id].sensors[i] and i?
> - } else {
> - temp = raw_to_mcelsius_v2(
> - mt, conf->bank_data[bank->id].sensors[i], raw);
> - }
>
> - /*
> - * The first read of a sensor often contains very high bogus
> - * temperature value. Filter these out so that the system does
> - * not immediately shut down.
> - */
> - if (temp > 200000)
> - temp = 0;
> + temp = _get_sensor_temp(mt, i);
>
> if (temp > max)
> max = temp;
> @@ -679,7 +694,8 @@ static int mtk_thermal_bank_temperature(struct mtk_thermal_bank *bank)
>
> static int mtk_read_temp(void *data, int *temperature)
> {
> - struct mtk_thermal *mt = data;
> + struct mtk_thermal_zone *tz = data;
> + struct mtk_thermal *mt = tz->mt;
> int i;
> int tempmax = INT_MIN;
>
> @@ -698,10 +714,28 @@ static int mtk_read_temp(void *data, int *temperature)
> return 0;
> }
>
> +static int mtk_read_sensor_temp(void *data, int *temperature)
> +{
> + struct mtk_thermal_zone *tz = data;
> + struct mtk_thermal *mt = tz->mt;
> + int id = tz->id - 1;
> +
> + if (id < 0)
> + return -EACCES;
nit: one space after return.
> +
> + *temperature = _get_sensor_temp(mt, id);
> +
> + return 0;
> +}
> +
> static const struct thermal_zone_of_device_ops mtk_thermal_ops = {
> .get_temp = mtk_read_temp,
> };
>
> +static const struct thermal_zone_of_device_ops mtk_thermal_sensor_ops = {
> + .get_temp = mtk_read_sensor_temp,
> +};
> +
> static void mtk_thermal_init_bank(struct mtk_thermal *mt, int num,
> u32 apmixed_phys_base, u32 auxadc_phys_base,
> int ctrl_id)
> @@ -992,6 +1026,7 @@ static int mtk_thermal_probe(struct platform_device *pdev)
> u64 auxadc_phys_base, apmixed_phys_base;
> struct thermal_zone_device *tzdev;
> void __iomem *apmixed_base, *auxadc_base;
> + struct mtk_thermal_zone *tz;
>
> mt = devm_kzalloc(&pdev->dev, sizeof(*mt), GFP_KERNEL);
> if (!mt)
> @@ -1080,11 +1115,29 @@ static int mtk_thermal_probe(struct platform_device *pdev)
>
> platform_set_drvdata(pdev, mt);
>
> - tzdev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, mt,
> - &mtk_thermal_ops);
> - if (IS_ERR(tzdev)) {
> - ret = PTR_ERR(tzdev);
> - goto err_disable_clk_peri_therm;
> + for (i = 0; i < mt->conf->num_sensors + 1; i++) {
> + tz = kmalloc(sizeof(*tz), GFP_KERNEL);
I don't see those structures being freed on error, or on driver unbind.
Maybe use dev_kmalloc instead?
> + if (!tz)
> + return -ENOMEM;
> +
> + tz->mt = mt;
> + tz->id = i;
> +
> + tzdev = devm_thermal_zone_of_sensor_register(&pdev->dev, i, tz, (i == 0) ?
> + &mtk_thermal_ops :
> + &mtk_thermal_sensor_ops);
> +
> + if (IS_ERR(tzdev)) {
> + if (PTR_ERR(tzdev) == -ENODEV) {
> + dev_warn(&pdev->dev,
> + "sensor %d not registered in thermal zone in dt\n", i);
> + continue;
> + }
> + if (PTR_ERR(tzdev) == -EACCES) {
> + ret = PTR_ERR(tzdev);
> + goto err_disable_clk_peri_therm;
> + }
> + }
> }
>
> return 0;
> --
> 2.18.0
