2020-10-13 12:03:59

by Michael Kao

[permalink] [raw]
Subject: [v5 0/3] mt8183: Add Mediatek thermal driver and dtsi

This patchset supports for MT8183 chip to mtk_thermal.c.
Add thermal zone of all the thermal sensor in SoC for
another get temperatrue. They don't need to thermal throttle.
And we bind coolers for thermal zone nodes of cpu_thermal.

Changes in v5:
- Rebase to kernel-5.9-rc1.
- Revise the title of cover letter.
- Drop "[v4,7/7] thermal: mediatek: use spinlock to protect PTPCORESEL"
- [2/2]
- Add the judgement to the version of raw_to_mcelsius.

Changes in v4:
- Rebase to kernel-5.6-rc1.
- [1/7]
- Squash thermal zone settings in the dtsi from [v3,5/8]
arm64: dts: mt8183: Increase polling frequency for CPU thermal zone.
- Remove the property of interrupts and mediatek,hw-reset-temp.
- [2/7]
- Correct commit message.
- [4/7]
- Change the target temperature to the 80C and change the commit message.
- [6/7]
- Adjust newline alignment.
- Fix the judgement on the return value of registering thermal zone.

Changes in v3:
- Rebase to kernel-5.5-rc1.
- [1/8]
- Update sustainable power of cpu, tzts1~5 and tztsABB.
- [7/8]
- Bypass the failure that non cpu_thermal sensor is not find in thermal-zones
in dts, which is normal for mt8173, so prompt a warning here instead of
failing.

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)

Changes in v2:
- [1/8]
- Add the sustainable-power,trips,cooling-maps to the tzts1~tztsABB.
- [4/8]
- Add the min opp of cpu throttle.


Matthias Kaehlcke (1):
arm64: dts: mt8183: Configure CPU cooling

Michael Kao (2):
thermal: mediatek: add another get_temp ops for thermal sensors
arm64: dts: mt8183: add thermal zone node

arch/arm64/boot/dts/mediatek/mt8183.dtsi | 140 +++++++++++++++++++++++
drivers/thermal/mtk_thermal.c | 99 ++++++++++++----
2 files changed, 216 insertions(+), 23 deletions(-)



2020-10-13 18:25:28

by Michael Kao

[permalink] [raw]
Subject: [v5 2/3] arm64: dts: mt8183: Configure CPU cooling

From: Matthias Kaehlcke <[email protected]>

Add two passive trip points at 68°C and 80°C for the CPU temperature.

Signed-off-by: Matthias Kaehlcke <[email protected]>
Signed-off-by: Michael Kao <[email protected]>
---
arch/arm64/boot/dts/mediatek/mt8183.dtsi | 56 ++++++++++++++++++++++++
1 file changed, 56 insertions(+)

diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
index 1cd093cf33f3..0614f18a1ea2 100644
--- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi
+++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
@@ -10,6 +10,7 @@
#include <dt-bindings/interrupt-controller/irq.h>
#include <dt-bindings/reset-controller/mt8183-resets.h>
#include <dt-bindings/phy/phy.h>
+#include <dt-bindings/thermal/thermal.h>
#include "mt8183-pinfunc.h"

/ {
@@ -450,6 +451,61 @@
polling-delay = <500>;
thermal-sensors = <&thermal 0>;
sustainable-power = <5000>;
+
+ trips {
+ threshold: trip-point@0 {
+ temperature = <68000>;
+ hysteresis = <2000>;
+ type = "passive";
+ };
+
+ target: trip-point@1 {
+ temperature = <80000>;
+ hysteresis = <2000>;
+ type = "passive";
+ };
+
+ cpu_crit: cpu-crit {
+ temperature = <115000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
+
+ cooling-maps {
+ map0 {
+ trip = <&target>;
+ cooling-device = <&cpu0
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>,
+ <&cpu1
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>,
+ <&cpu2
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>,
+ <&cpu3
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>;
+ contribution = <3072>;
+ };
+ map1 {
+ trip = <&target>;
+ cooling-device = <&cpu4
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>,
+ <&cpu5
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>,
+ <&cpu6
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>,
+ <&cpu7
+ THERMAL_NO_LIMIT
+ THERMAL_NO_LIMIT>;
+ contribution = <1024>;
+ };
+ };
};

/* The tzts1 ~ tzts6 don't need to polling */
--
2.18.0

2020-10-13 18:25:30

by Michael Kao

[permalink] [raw]
Subject: [v5 3/3] thermal: mediatek: add another get_temp ops for thermal sensors

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 <[email protected]>
Signed-off-by: Hsin-Yi Wang <[email protected]>
---
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;
+
+ 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;
+ else
+ return temp;
+}
+
/**
* 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;
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);
- } 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;
+
+ *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);
+ 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

2020-11-24 08:29:37

by Hsin-Yi Wang

[permalink] [raw]
Subject: Re: [v5 2/3] arm64: dts: mt8183: Configure CPU cooling

On Tue, Oct 13, 2020 at 6:24 PM Michael Kao <[email protected]> wrote:
>
> From: Matthias Kaehlcke <[email protected]>
>
> Add two passive trip points at 68°C and 80°C for the CPU temperature.
>
> Signed-off-by: Matthias Kaehlcke <[email protected]>
> Signed-off-by: Michael Kao <[email protected]>

Tested-by: Hsin-Yi Wang <[email protected]>

> ---
> arch/arm64/boot/dts/mediatek/mt8183.dtsi | 56 ++++++++++++++++++++++++
> 1 file changed, 56 insertions(+)
>
> diff --git a/arch/arm64/boot/dts/mediatek/mt8183.dtsi b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
> index 1cd093cf33f3..0614f18a1ea2 100644
> --- a/arch/arm64/boot/dts/mediatek/mt8183.dtsi
> +++ b/arch/arm64/boot/dts/mediatek/mt8183.dtsi
> @@ -10,6 +10,7 @@
> #include <dt-bindings/interrupt-controller/irq.h>
> #include <dt-bindings/reset-controller/mt8183-resets.h>
> #include <dt-bindings/phy/phy.h>
> +#include <dt-bindings/thermal/thermal.h>
> #include "mt8183-pinfunc.h"
>
> / {
> @@ -450,6 +451,61 @@
> polling-delay = <500>;
> thermal-sensors = <&thermal 0>;
> sustainable-power = <5000>;
> +
> + trips {
> + threshold: trip-point@0 {
> + temperature = <68000>;
> + hysteresis = <2000>;
> + type = "passive";
> + };
> +
> + target: trip-point@1 {
> + temperature = <80000>;
> + hysteresis = <2000>;
> + type = "passive";
> + };
> +
> + cpu_crit: cpu-crit {
> + temperature = <115000>;
> + hysteresis = <2000>;
> + type = "critical";
> + };
> + };
> +
> + cooling-maps {
> + map0 {
> + trip = <&target>;
> + cooling-device = <&cpu0
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>,
> + <&cpu1
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>,
> + <&cpu2
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>,
> + <&cpu3
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>;
> + contribution = <3072>;
> + };
> + map1 {
> + trip = <&target>;
> + cooling-device = <&cpu4
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>,
> + <&cpu5
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>,
> + <&cpu6
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>,
> + <&cpu7
> + THERMAL_NO_LIMIT
> + THERMAL_NO_LIMIT>;
> + contribution = <1024>;
> + };
> + };
> };
>
> /* The tzts1 ~ tzts6 don't need to polling */
> --
> 2.18.0

2021-01-11 00:42:19

by Nicolas Boichat

[permalink] [raw]
Subject: Re: [v5 3/3] thermal: mediatek: add another get_temp ops for thermal sensors

On Tue, Oct 13, 2020 at 6:24 PM Michael Kao <[email protected]> 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 <[email protected]>
> Signed-off-by: Hsin-Yi Wang <[email protected]>
> ---
> 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