There are three thermal stages defined in the PMIC:
stage 1: warning
stage 2: system should shut down
stage 3: emergency shut down
By default the PMIC assumes that the OS isn't doing anything and thus
at stage 2 it does a partial PMIC shutdown and at stage 3 it kills
all power. When switching between thermal stages the PMIC generates an
interrupt which is handled by the driver. The partial PMIC shutdown at
stage 2 can be disabled by software, which allows the OS to initiate a
shutdown at stage 2 with a thermal zone configured accordingly.
If a critical trip point is configured in the thermal zone the driver
adjusts the stage 1-3 temperature thresholds to (closely) match the
critical temperature with a stage 2 threshold (125/130/135/140 °C).
If a suitable match is found the partial shutdown at stage 2 is
disabled. If for some reason the system doesn't shutdown at stage 2
the emergency shutdown at stage 3 kicks in.
The partial shutdown at stage 2 remains enabled in these cases:
- no critical trip point defined
- the temperature of the critical trip point is < 125°C
- the temperature of the critical trip point is > 140°C and no
ADC channel is configured (thus the OS is not notified when the critical
temperature is reached)
Suggested-by: Douglas Anderson <[email protected]>
Signed-off-by: Matthias Kaehlcke <[email protected]>
---
Changes in v5:
- patch added to the series
---
drivers/thermal/qcom-spmi-temp-alarm.c | 161 ++++++++++++++++++++++---
1 file changed, 142 insertions(+), 19 deletions(-)
diff --git a/drivers/thermal/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom-spmi-temp-alarm.c
index ad4f3a8d6560..936e4dde4298 100644
--- a/drivers/thermal/qcom-spmi-temp-alarm.c
+++ b/drivers/thermal/qcom-spmi-temp-alarm.c
@@ -23,6 +23,8 @@
#include <linux/regmap.h>
#include <linux/thermal.h>
+#include "thermal_core.h"
+
#define QPNP_TM_REG_TYPE 0x04
#define QPNP_TM_REG_SUBTYPE 0x05
#define QPNP_TM_REG_STATUS 0x08
@@ -37,9 +39,11 @@
#define STATUS_GEN2_STATE_MASK GENMASK(6, 4)
#define STATUS_GEN2_STATE_SHIFT 4
-#define SHUTDOWN_CTRL1_OVERRIDE_MASK GENMASK(7, 6)
+#define SHUTDOWN_CTRL1_OVERRIDE_S2 BIT(6)
#define SHUTDOWN_CTRL1_THRESHOLD_MASK GENMASK(1, 0)
+#define SHUTDOWN_CTRL1_RATE_25HZ BIT(3)
+
#define ALARM_CTRL_FORCE_ENABLE BIT(7)
/*
@@ -56,12 +60,17 @@
#define TEMP_THRESH_STEP 5000 /* Threshold step: 5 C */
#define THRESH_MIN 0
+#define THRESH_MAX 3
+
+#define STAGE2_THRESHOLD_MIN 125000 /* Stage 2 Threshold Min: 125 C */
+#define STAGE2_THRESHOLD_MAX 140000 /* Stage 2 Threshold Max: 140 C */
/* Temperature in Milli Celsius reported during stage 0 if no ADC is present */
#define DEFAULT_TEMP 37000
struct qpnp_tm_chip {
struct regmap *map;
+ struct device *dev;
struct thermal_zone_device *tz_dev;
unsigned int subtype;
long temp;
@@ -69,6 +78,10 @@ struct qpnp_tm_chip {
unsigned int stage;
unsigned int prev_stage;
unsigned int base;
+ /* protects .thresh, .stage and chip registers */
+ struct mutex lock;
+ bool initialized;
+
struct iio_channel *adc;
};
@@ -125,6 +138,8 @@ static int qpnp_tm_update_temp_no_adc(struct qpnp_tm_chip *chip)
unsigned int stage, stage_new, stage_old;
int ret;
+ WARN_ON(!mutex_is_locked(&chip->lock));
+
ret = qpnp_tm_get_temp_stage(chip);
if (ret < 0)
return ret;
@@ -163,8 +178,15 @@ static int qpnp_tm_get_temp(void *data, int *temp)
if (!temp)
return -EINVAL;
- if (!chip->adc) {
+ if (!chip->initialized) {
+ *temp = DEFAULT_TEMP;
+ return 0;
+ }
+
+ if (!chip->adc)) {
+ mutex_lock(&chip->lock);
ret = qpnp_tm_update_temp_no_adc(chip);
+ mutex_unlock(&chip->lock);
if (ret < 0)
return ret;
} else {
@@ -180,8 +202,77 @@ static int qpnp_tm_get_temp(void *data, int *temp)
return 0;
}
+static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
+ int temp)
+{
+ u8 reg;
+ bool disable_s2_shutdown = false;
+ int ret;
+
+ WARN_ON(!mutex_is_locked(&chip->lock));
+
+ /*
+ * Default: S2 and S3 shutdown enabled, thresholds at
+ * 105C/125C/145C, monitoring at 25Hz
+ */
+ reg = SHUTDOWN_CTRL1_RATE_25HZ;
+
+ if ((temp == THERMAL_TEMP_INVALID) ||
+ (temp < STAGE2_THRESHOLD_MIN)) {
+ chip->thresh = THRESH_MIN;
+ goto skip;
+ }
+
+ if (temp <= STAGE2_THRESHOLD_MAX) {
+ chip->thresh = THRESH_MAX -
+ ((STAGE2_THRESHOLD_MAX - temp) /
+ TEMP_THRESH_STEP);
+ disable_s2_shutdown = true;
+ } else {
+ chip->thresh = THRESH_MAX;
+
+ if (!IS_ERR(chip->adc))
+ disable_s2_shutdown = true;
+ else
+ dev_warn(chip->dev,
+ "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140°C! Configuring stage 2 shutdown at 140°C.\n");
+ }
+
+skip:
+ reg |= chip->thresh;
+ if (disable_s2_shutdown)
+ reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
+
+ ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
+ if (ret < 0)
+ return ret;
+
+ return ret;
+}
+
+static int qpnp_tm_set_trip_temp(void *data, int trip, int temp)
+{
+ struct qpnp_tm_chip *chip = data;
+ const struct thermal_trip *trip_points;
+ int ret;
+
+ trip_points = of_thermal_get_trip_points(chip->tz_dev);
+ if (!trip_points)
+ return -EINVAL;
+
+ if (trip_points[trip].type != THERMAL_TRIP_CRITICAL)
+ return 0;
+
+ mutex_lock(&chip->lock);
+ ret = qpnp_tm_update_critical_trip_temp(chip, temp);
+ mutex_unlock(&chip->lock);
+
+ return ret;
+}
+
static const struct thermal_zone_of_device_ops qpnp_tm_sensor_ops = {
.get_temp = qpnp_tm_get_temp,
+ .set_trip_temp = qpnp_tm_set_trip_temp,
};
static irqreturn_t qpnp_tm_isr(int irq, void *data)
@@ -193,6 +284,29 @@ static irqreturn_t qpnp_tm_isr(int irq, void *data)
return IRQ_HANDLED;
}
+static int qpnp_tm_get_critical_trip_temp(struct qpnp_tm_chip *chip)
+{
+ int ntrips;
+ const struct thermal_trip *trips;
+ int i;
+
+ ntrips = of_thermal_get_ntrips(chip->tz_dev);
+ if (ntrips <= 0)
+ return THERMAL_TEMP_INVALID;
+
+ trips = of_thermal_get_trip_points(chip->tz_dev);
+ if (!trips)
+ return THERMAL_TEMP_INVALID;
+
+ for (i = 0; i < ntrips; i++) {
+ if (of_thermal_is_trip_valid(chip->tz_dev, i) &&
+ (trips[i].type == THERMAL_TRIP_CRITICAL))
+ return trips[i].temperature;
+ }
+
+ return THERMAL_TEMP_INVALID;
+}
+
/*
* This function initializes the internal temp value based on only the
* current thermal stage and threshold. Setup threshold control and
@@ -203,17 +317,20 @@ static int qpnp_tm_init(struct qpnp_tm_chip *chip)
unsigned int stage;
int ret;
u8 reg = 0;
+ int crit_temp;
+
+ mutex_lock(&chip->lock);
ret = qpnp_tm_read(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, ®);
if (ret < 0)
- return ret;
+ goto out;
chip->thresh = reg & SHUTDOWN_CTRL1_THRESHOLD_MASK;
chip->temp = DEFAULT_TEMP;
ret = qpnp_tm_get_temp_stage(chip);
if (ret < 0)
- return ret;
+ goto out;
chip->stage = ret;
stage = chip->subtype == QPNP_TM_SUBTYPE_GEN1
@@ -224,21 +341,17 @@ static int qpnp_tm_init(struct qpnp_tm_chip *chip)
(stage - 1) * TEMP_STAGE_STEP +
TEMP_THRESH_MIN;
- /*
- * Set threshold and disable software override of stage 2 and 3
- * shutdowns.
- */
- chip->thresh = THRESH_MIN;
- reg &= ~(SHUTDOWN_CTRL1_OVERRIDE_MASK | SHUTDOWN_CTRL1_THRESHOLD_MASK);
- reg |= chip->thresh & SHUTDOWN_CTRL1_THRESHOLD_MASK;
- ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
+ crit_temp = qpnp_tm_get_critical_trip_temp(chip);
+ ret = qpnp_tm_update_critical_trip_temp(chip, crit_temp);
if (ret < 0)
- return ret;
+ goto out;
/* Enable the thermal alarm PMIC module in always-on mode. */
reg = ALARM_CTRL_FORCE_ENABLE;
ret = qpnp_tm_write(chip, QPNP_TM_REG_ALARM_CTRL, reg);
+out:
+ mutex_unlock(&chip->lock);
return ret;
}
@@ -257,6 +370,9 @@ static int qpnp_tm_probe(struct platform_device *pdev)
return -ENOMEM;
dev_set_drvdata(&pdev->dev, chip);
+ chip->dev = &pdev->dev;
+
+ mutex_init(&chip->lock);
chip->map = dev_get_regmap(pdev->dev.parent, NULL);
if (!chip->map)
@@ -302,6 +418,18 @@ static int qpnp_tm_probe(struct platform_device *pdev)
chip->subtype = subtype;
+ /*
+ * Register the sensor before initializing the hardware to be able to
+ * read the trip points. get_temp() returns the default temperature
+ * before the hardware initialization is completed.
+ */
+ chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
+ &qpnp_tm_sensor_ops);
+ if (IS_ERR(chip->tz_dev)) {
+ dev_err(&pdev->dev, "failed to register sensor\n");
+ return PTR_ERR(chip->tz_dev);
+ }
+
ret = qpnp_tm_init(chip);
if (ret < 0) {
dev_err(&pdev->dev, "init failed\n");
@@ -313,12 +441,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
if (ret < 0)
return ret;
- chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
- &qpnp_tm_sensor_ops);
- if (IS_ERR(chip->tz_dev)) {
- dev_err(&pdev->dev, "failed to register sensor\n");
- return PTR_ERR(chip->tz_dev);
- }
+ chip->initialized = true;
return 0;
}
--
2.18.0.233.g985f88cf7e-goog
The thermal zone uses spmi-temp-alarm as sensor, the trip points
correspond to the PMIC thermal stages 1 and 2. The critical trip
point at 125°C disables the partial PMIC shutdown at stage 2.
Without an IIO input the sensor only reports a limited number of
temperatures:
- 37°C for temperatures below 105°C
- 107°C for temperatures >= 105°C and < 125°C
- 127°C for temperatures >= 125°C
(the numbers correspond to a stage 1 threshold of 105°C)
Signed-off-by: Matthias Kaehlcke <[email protected]>
---
Changes in v5:
- removed 'stage2-shutdown-disabled' property from spmi-temp-alarm
- updated commit message
Changes in v4:
- updated trip point temperatures to match stage 1 and 2 ones
- disabled stage 2 shutdown
- updated commit message
Changes in v3:
- moved 'thermal-zones' node to the beginning of the .dtsi
Changes in v2:
- defined 'thermal-zones' node in pm8998.dtsi instead of using a label
to refer to it
- use 105°C hardware trip point as critical trip point
- reduced number of trip points to 2
- lowered temperature of passive trip point
- updated trip point names and added labels
- updated commit message
---
arch/arm64/boot/dts/qcom/pm8998.dtsi | 25 +++++++++++++++++++++++++
1 file changed, 25 insertions(+)
diff --git a/arch/arm64/boot/dts/qcom/pm8998.dtsi b/arch/arm64/boot/dts/qcom/pm8998.dtsi
index 7eea94701b23..34c259ba3919 100644
--- a/arch/arm64/boot/dts/qcom/pm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm8998.dtsi
@@ -3,6 +3,31 @@
#include <dt-bindings/spmi/spmi.h>
#include <dt-bindings/interrupt-controller/irq.h>
+#include <dt-bindings/thermal/thermal.h>
+
+/ {
+ thermal-zones {
+ pm8998 {
+ polling-delay-passive = <250>;
+ polling-delay = <1000>;
+
+ thermal-sensors = <&pm8998_temp>;
+
+ trips {
+ pm8998_alert0: pm8998-alert0 {
+ temperature = <105000>;
+ hysteresis = <2000>;
+ type = "passive";
+ };
+ pm8998_crit: pm8998-crit {
+ temperature = <125000>;
+ hysteresis = <2000>;
+ type = "critical";
+ };
+ };
+ };
+ };
+};
&spmi_bus {
pm8998_lsid0: pmic@0 {
--
2.18.0.233.g985f88cf7e-goog
This adds the spmi-temp-alarm node to pm8998 based on the examples in the
bindings.
Signed-off-by: Matthias Kaehlcke <[email protected]>
Reviewed-by: Douglas Anderson <[email protected]>
---
Changes in v5:
- added tag 'Reviewed-by: Douglas Anderson <[email protected]>'
Changes in v4:
- none
Changes in v3:
- changed node name from 'qcom,temp-alarm@2400' to 'temp-alarm@2400'
- removed controller register length value from 'reg'
Changes in v2:
- none
---
arch/arm64/boot/dts/qcom/pm8998.dtsi | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/arch/arm64/boot/dts/qcom/pm8998.dtsi b/arch/arm64/boot/dts/qcom/pm8998.dtsi
index 92bed1e7d4bb..7eea94701b23 100644
--- a/arch/arm64/boot/dts/qcom/pm8998.dtsi
+++ b/arch/arm64/boot/dts/qcom/pm8998.dtsi
@@ -11,6 +11,13 @@
#address-cells = <1>;
#size-cells = <0>;
+ pm8998_temp: temp-alarm@2400 {
+ compatible = "qcom,spmi-temp-alarm";
+ reg = <0x2400>;
+ interrupts = <0x0 0x24 0x0 IRQ_TYPE_EDGE_RISING>;
+ #thermal-sensor-cells = <0>;
+ };
+
pm8998_gpio: gpios@c000 {
compatible = "qcom,pm8998-gpio", "qcom,spmi-gpio";
reg = <0xc000>;
--
2.18.0.233.g985f88cf7e-goog
On Tue, Jul 24, 2018 at 04:46:34PM -0700, Matthias Kaehlcke wrote:
> There are three thermal stages defined in the PMIC:
>
> stage 1: warning
> stage 2: system should shut down
> stage 3: emergency shut down
>
> By default the PMIC assumes that the OS isn't doing anything and thus
> at stage 2 it does a partial PMIC shutdown and at stage 3 it kills
> all power. When switching between thermal stages the PMIC generates an
> interrupt which is handled by the driver. The partial PMIC shutdown at
> stage 2 can be disabled by software, which allows the OS to initiate a
> shutdown at stage 2 with a thermal zone configured accordingly.
>
> If a critical trip point is configured in the thermal zone the driver
> adjusts the stage 1-3 temperature thresholds to (closely) match the
> critical temperature with a stage 2 threshold (125/130/135/140 °C).
> If a suitable match is found the partial shutdown at stage 2 is
> disabled. If for some reason the system doesn't shutdown at stage 2
> the emergency shutdown at stage 3 kicks in.
>
> The partial shutdown at stage 2 remains enabled in these cases:
> - no critical trip point defined
> - the temperature of the critical trip point is < 125°C
> - the temperature of the critical trip point is > 140°C and no
> ADC channel is configured (thus the OS is not notified when the critical
> temperature is reached)
>
> Suggested-by: Douglas Anderson <[email protected]>
> Signed-off-by: Matthias Kaehlcke <[email protected]>
> ---
> Changes in v5:
> - patch added to the series
> ---
> drivers/thermal/qcom-spmi-temp-alarm.c | 161 ++++++++++++++++++++++---
> 1 file changed, 142 insertions(+), 19 deletions(-)
>
> diff --git a/drivers/thermal/qcom-spmi-temp-alarm.c b/drivers/thermal/qcom-spmi-temp-alarm.c
> index ad4f3a8d6560..936e4dde4298 100644
> --- a/drivers/thermal/qcom-spmi-temp-alarm.c
> +++ b/drivers/thermal/qcom-spmi-temp-alarm.c
>
> ...
>
> +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
> + int temp)
> +{
> + u8 reg;
> + bool disable_s2_shutdown = false;
> + int ret;
> +
> + WARN_ON(!mutex_is_locked(&chip->lock));
> +
> + /*
> + * Default: S2 and S3 shutdown enabled, thresholds at
> + * 105C/125C/145C, monitoring at 25Hz
> + */
> + reg = SHUTDOWN_CTRL1_RATE_25HZ;
> +
> + if ((temp == THERMAL_TEMP_INVALID) ||
> + (temp < STAGE2_THRESHOLD_MIN)) {
> + chip->thresh = THRESH_MIN;
> + goto skip;
> + }
> +
> + if (temp <= STAGE2_THRESHOLD_MAX) {
> + chip->thresh = THRESH_MAX -
> + ((STAGE2_THRESHOLD_MAX - temp) /
> + TEMP_THRESH_STEP);
> + disable_s2_shutdown = true;
> + } else {
> + chip->thresh = THRESH_MAX;
> +
> + if (!IS_ERR(chip->adc))
Note to self: with commit 7a4ca51b7040 ("thermal/drivers/qcom-spmi:
Use devm_iio_channel_get") this should be 'if (chip->adc)'.
Hi,
On Tue, Jul 24, 2018 at 4:46 PM, Matthias Kaehlcke <[email protected]> wrote:
> The thermal zone uses spmi-temp-alarm as sensor, the trip points
> correspond to the PMIC thermal stages 1 and 2. The critical trip
> point at 125°C disables the partial PMIC shutdown at stage 2.
>
> Without an IIO input the sensor only reports a limited number of
> temperatures:
>
> - 37°C for temperatures below 105°C
> - 107°C for temperatures >= 105°C and < 125°C
> - 127°C for temperatures >= 125°C
>
> (the numbers correspond to a stage 1 threshold of 105°C)
>
> Signed-off-by: Matthias Kaehlcke <[email protected]>
> ---
> Changes in v5:
> - removed 'stage2-shutdown-disabled' property from spmi-temp-alarm
> - updated commit message
>
> Changes in v4:
> - updated trip point temperatures to match stage 1 and 2 ones
> - disabled stage 2 shutdown
> - updated commit message
>
> Changes in v3:
> - moved 'thermal-zones' node to the beginning of the .dtsi
>
> Changes in v2:
> - defined 'thermal-zones' node in pm8998.dtsi instead of using a label
> to refer to it
> - use 105°C hardware trip point as critical trip point
> - reduced number of trip points to 2
> - lowered temperature of passive trip point
> - updated trip point names and added labels
> - updated commit message
> ---
> arch/arm64/boot/dts/qcom/pm8998.dtsi | 25 +++++++++++++++++++++++++
> 1 file changed, 25 insertions(+)
Looks great!
Reviewed-by: Douglas Anderson <[email protected]>
Hi,
On Tue, Jul 24, 2018 at 4:46 PM, Matthias Kaehlcke <[email protected]> wrote:
> +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
> + int temp)
> +{
> + u8 reg;
> + bool disable_s2_shutdown = false;
> + int ret;
> +
> + WARN_ON(!mutex_is_locked(&chip->lock));
> +
> + /*
> + * Default: S2 and S3 shutdown enabled, thresholds at
> + * 105C/125C/145C, monitoring at 25Hz
> + */
> + reg = SHUTDOWN_CTRL1_RATE_25HZ;
> +
> + if ((temp == THERMAL_TEMP_INVALID) ||
> + (temp < STAGE2_THRESHOLD_MIN)) {
> + chip->thresh = THRESH_MIN;
> + goto skip;
> + }
> +
> + if (temp <= STAGE2_THRESHOLD_MAX) {
> + chip->thresh = THRESH_MAX -
> + ((STAGE2_THRESHOLD_MAX - temp) /
> + TEMP_THRESH_STEP);
> + disable_s2_shutdown = true;
> + } else {
> + chip->thresh = THRESH_MAX;
> +
> + if (!IS_ERR(chip->adc))
> + disable_s2_shutdown = true;
> + else
> + dev_warn(chip->dev,
> + "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140°C! Configuring stage 2 shutdown at 140°C.\n");
Putting a non-ASCII character (the degree symbol) in your commit
message is one thing, but are you sure it's wise to put it in the
kernel logs?
> + }
> +
> +skip:
> + reg |= chip->thresh;
> + if (disable_s2_shutdown)
> + reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
> +
> + ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> + if (ret < 0)
> + return ret;
> +
> + return ret;
Simplify the above lines to:
return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> @@ -313,12 +441,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
> if (ret < 0)
> return ret;
>
> - chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
> - &qpnp_tm_sensor_ops);
> - if (IS_ERR(chip->tz_dev)) {
> - dev_err(&pdev->dev, "failed to register sensor\n");
> - return PTR_ERR(chip->tz_dev);
> - }
> + chip->initialized = true;
Should we add "thermal_zone_device_update(chip->tz_dev,
THERMAL_EVENT_UNSPECIFIED);" here
...also: do we care about any type of locking for chip->initialized?
Technically we can be running on weakly ordered memory so if
qpnp_tm_update_temp_no_adc() is running on a different processor then
possibly it could still keep returning the default temperature for a
little while. We could try to analyze whether there's some sort of
implicit barrier or we could add manual memory barriers, but generally
I try to avoid that and just do the simple locking... What about just
setting chip-Initialized = true at the end of qpnp_tm_init() while the
mutex is still held?
I'd also love to hear from someone with more thermal framework
experience to make sure it's legit to return a default value if
someone calls us while we're initting. It seems sane to me but nice
to confirm it's OK.
Overall I like the idea of this patch so hopefully others do too.
Thanks for sending it out!
-Doug
Hi Doug,
On Wed, Jul 25, 2018 at 04:19:56PM -0700, Doug Anderson wrote:
> On Tue, Jul 24, 2018 at 4:46 PM, Matthias Kaehlcke <[email protected]> wrote:
> > +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
> > + int temp)
> > +{
> > + u8 reg;
> > + bool disable_s2_shutdown = false;
> > + int ret;
> > +
> > + WARN_ON(!mutex_is_locked(&chip->lock));
> > +
> > + /*
> > + * Default: S2 and S3 shutdown enabled, thresholds at
> > + * 105C/125C/145C, monitoring at 25Hz
> > + */
> > + reg = SHUTDOWN_CTRL1_RATE_25HZ;
> > +
> > + if ((temp == THERMAL_TEMP_INVALID) ||
> > + (temp < STAGE2_THRESHOLD_MIN)) {
> > + chip->thresh = THRESH_MIN;
> > + goto skip;
> > + }
> > +
> > + if (temp <= STAGE2_THRESHOLD_MAX) {
> > + chip->thresh = THRESH_MAX -
> > + ((STAGE2_THRESHOLD_MAX - temp) /
> > + TEMP_THRESH_STEP);
> > + disable_s2_shutdown = true;
> > + } else {
> > + chip->thresh = THRESH_MAX;
> > +
> > + if (!IS_ERR(chip->adc))
> > + disable_s2_shutdown = true;
> > + else
> > + dev_warn(chip->dev,
> > + "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140°C! Configuring stage 2 shutdown at 140°C.\n");
>
> Putting a non-ASCII character (the degree symbol) in your commit
> message is one thing, but are you sure it's wise to put it in the
> kernel logs?
A few other drivers also do this
(drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c,
drivers/macintosh/windfarm_pm121.c), however that doesn't mean it's a
good idea. Will change to degC or C.
> > + }
> > +
> > +skip:
> > + reg |= chip->thresh;
> > + if (disable_s2_shutdown)
> > + reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
> > +
> > + ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> > + if (ret < 0)
> > + return ret;
> > +
> > + return ret;
>
> Simplify the above lines to:
>
> return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
Ouch, my code is indeed dumb ...
> > @@ -313,12 +441,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
> > if (ret < 0)
> > return ret;
> >
> > - chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
> > - &qpnp_tm_sensor_ops);
> > - if (IS_ERR(chip->tz_dev)) {
> > - dev_err(&pdev->dev, "failed to register sensor\n");
> > - return PTR_ERR(chip->tz_dev);
> > - }
> > + chip->initialized = true;
>
> Should we add "thermal_zone_device_update(chip->tz_dev,
> THERMAL_EVENT_UNSPECIFIED);" here
Seems reasonable, will do.
> ...also: do we care about any type of locking for chip->initialized?
> Technically we can be running on weakly ordered memory so if
> qpnp_tm_update_temp_no_adc() is running on a different processor then
> possibly it could still keep returning the default temperature for a
> little while. We could try to analyze whether there's some sort of
> implicit barrier or we could add manual memory barriers, but generally
> I try to avoid that and just do the simple locking... What about just
> setting chip-Initialized = true at the end of qpnp_tm_init() while the
> mutex is still held?
Thanks for pointing that out. I agree that we should keep things
simple, chip->initialized to true at the end of qpnp_tm_init() sounds
good to me.
> I'd also love to hear from someone with more thermal framework
> experience to make sure it's legit to return a default value if
> someone calls us while we're initting. It seems sane to me but nice
> to confirm it's OK.
An alternative could be to return THERMAL_TEMP_INVALID, however I
don't see this handled outside of thermal_core.c, not sure if it could
throw some other code off.
Comments from thermal folks on either approach (or alternatives) are
definitely welcome :)
> Overall I like the idea of this patch so hopefully others do too.
> Thanks for sending it out!
Thanks for the review!
Matthias
On Wed, Jul 25, 2018 at 06:12:28PM -0700, Matthias Kaehlcke wrote:
> Hi Doug,
>
> On Wed, Jul 25, 2018 at 04:19:56PM -0700, Doug Anderson wrote:
>
> > On Tue, Jul 24, 2018 at 4:46 PM, Matthias Kaehlcke <[email protected]> wrote:
> > > +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
> > > + int temp)
> > > +{
> > > + u8 reg;
> > > + bool disable_s2_shutdown = false;
> > > + int ret;
> > > +
> > > + WARN_ON(!mutex_is_locked(&chip->lock));
> > > +
> > > + /*
> > > + * Default: S2 and S3 shutdown enabled, thresholds at
> > > + * 105C/125C/145C, monitoring at 25Hz
> > > + */
> > > + reg = SHUTDOWN_CTRL1_RATE_25HZ;
> > > +
> > > + if ((temp == THERMAL_TEMP_INVALID) ||
> > > + (temp < STAGE2_THRESHOLD_MIN)) {
> > > + chip->thresh = THRESH_MIN;
> > > + goto skip;
> > > + }
> > > +
> > > + if (temp <= STAGE2_THRESHOLD_MAX) {
> > > + chip->thresh = THRESH_MAX -
> > > + ((STAGE2_THRESHOLD_MAX - temp) /
> > > + TEMP_THRESH_STEP);
> > > + disable_s2_shutdown = true;
> > > + } else {
> > > + chip->thresh = THRESH_MAX;
> > > +
> > > + if (!IS_ERR(chip->adc))
> > > + disable_s2_shutdown = true;
> > > + else
> > > + dev_warn(chip->dev,
> > > + "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140?C! Configuring stage 2 shutdown at 140?C.\n");
> >
> > Putting a non-ASCII character (the degree symbol) in your commit
> > message is one thing, but are you sure it's wise to put it in the
> > kernel logs?
>
> A few other drivers also do this
> (drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c,
> drivers/macintosh/windfarm_pm121.c), however that doesn't mean it's a
> good idea. Will change to degC or C.
>
> > > + }
> > > +
> > > +skip:
> > > + reg |= chip->thresh;
> > > + if (disable_s2_shutdown)
> > > + reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
> > > +
> > > + ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> > > + if (ret < 0)
> > > + return ret;
> > > +
> > > + return ret;
> >
> > Simplify the above lines to:
> >
> > return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
>
> Ouch, my code is indeed dumb ...
>
> > > @@ -313,12 +441,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
> > > if (ret < 0)
> > > return ret;
> > >
> > > - chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
> > > - &qpnp_tm_sensor_ops);
> > > - if (IS_ERR(chip->tz_dev)) {
> > > - dev_err(&pdev->dev, "failed to register sensor\n");
> > > - return PTR_ERR(chip->tz_dev);
> > > - }
> > > + chip->initialized = true;
> >
> > Should we add "thermal_zone_device_update(chip->tz_dev,
> > THERMAL_EVENT_UNSPECIFIED);" here
>
> Seems reasonable, will do.
>
> > ...also: do we care about any type of locking for chip->initialized?
> > Technically we can be running on weakly ordered memory so if
> > qpnp_tm_update_temp_no_adc() is running on a different processor then
> > possibly it could still keep returning the default temperature for a
> > little while. We could try to analyze whether there's some sort of
> > implicit barrier or we could add manual memory barriers, but generally
> > I try to avoid that and just do the simple locking... What about just
> > setting chip-Initialized = true at the end of qpnp_tm_init() while the
> > mutex is still held?
>
> Thanks for pointing that out. I agree that we should keep things
> simple, chip->initialized to true at the end of qpnp_tm_init() sounds
> good to me.
>
> > I'd also love to hear from someone with more thermal framework
> > experience to make sure it's legit to return a default value if
> > someone calls us while we're initting. It seems sane to me but nice
> > to confirm it's OK.
>
> An alternative could be to return THERMAL_TEMP_INVALID, however I
> don't see this handled outside of thermal_core.c, not sure if it could
> throw some other code off.
>
> Comments from thermal folks on either approach (or alternatives) are
> definitely welcome :)
>
> > Overall I like the idea of this patch so hopefully others do too.
> > Thanks for sending it out!
>
minor ask for next version
WARNING: line over 80 characters
#159: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:65:
+#define STAGE2_THRESHOLD_MIN 125000 /* Stage 2 Threshold
Min: 125 C */
WARNING: line over 80 characters
#160: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:66:
+#define STAGE2_THRESHOLD_MAX 140000 /* Stage 2 Threshold
Max: 140 C */
ERROR: trailing statements should be on next line
#201: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:186:
+ if (!chip->adc)) {
CHECK: Unnecessary parentheses around 'temp == THERMAL_TEMP_INVALID'
#227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
+ if ((temp == THERMAL_TEMP_INVALID) ||
+ (temp < STAGE2_THRESHOLD_MIN)) {
CHECK: Unnecessary parentheses around 'temp < STAGE2_THRESHOLD_MIN'
#227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
+ if ((temp == THERMAL_TEMP_INVALID) ||
+ (temp < STAGE2_THRESHOLD_MIN)) {
CHECK: Unnecessary parentheses around 'trips[i].type ==
THERMAL_TRIP_CRITICAL'
#305: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:302:
+ if (of_thermal_is_trip_valid(chip->tz_dev, i) &&
+ (trips[i].type == THERMAL_TRIP_CRITICAL))
CHECK: Alignment should match open parenthesis
#386: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:427:
+ chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev,
0, chip,
+
&qpnp_tm_sensor_ops);
> Thanks for the review!
>
> Matthias
On Fri, Jul 27, 2018 at 03:40:52PM -0700, Eduardo Valentin wrote:
> On Wed, Jul 25, 2018 at 06:12:28PM -0700, Matthias Kaehlcke wrote:
> > Hi Doug,
> >
> > On Wed, Jul 25, 2018 at 04:19:56PM -0700, Doug Anderson wrote:
> >
> > > On Tue, Jul 24, 2018 at 4:46 PM, Matthias Kaehlcke <[email protected]> wrote:
> > > > +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
> > > > + int temp)
> > > > +{
> > > > + u8 reg;
> > > > + bool disable_s2_shutdown = false;
> > > > + int ret;
> > > > +
> > > > + WARN_ON(!mutex_is_locked(&chip->lock));
> > > > +
> > > > + /*
> > > > + * Default: S2 and S3 shutdown enabled, thresholds at
> > > > + * 105C/125C/145C, monitoring at 25Hz
> > > > + */
> > > > + reg = SHUTDOWN_CTRL1_RATE_25HZ;
> > > > +
> > > > + if ((temp == THERMAL_TEMP_INVALID) ||
> > > > + (temp < STAGE2_THRESHOLD_MIN)) {
> > > > + chip->thresh = THRESH_MIN;
> > > > + goto skip;
> > > > + }
> > > > +
> > > > + if (temp <= STAGE2_THRESHOLD_MAX) {
> > > > + chip->thresh = THRESH_MAX -
> > > > + ((STAGE2_THRESHOLD_MAX - temp) /
> > > > + TEMP_THRESH_STEP);
> > > > + disable_s2_shutdown = true;
> > > > + } else {
> > > > + chip->thresh = THRESH_MAX;
> > > > +
> > > > + if (!IS_ERR(chip->adc))
> > > > + disable_s2_shutdown = true;
> > > > + else
> > > > + dev_warn(chip->dev,
> > > > + "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140?C! Configuring stage 2 shutdown at 140?C.\n");
> > >
> > > Putting a non-ASCII character (the degree symbol) in your commit
> > > message is one thing, but are you sure it's wise to put it in the
> > > kernel logs?
> >
> > A few other drivers also do this
> > (drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c,
> > drivers/macintosh/windfarm_pm121.c), however that doesn't mean it's a
> > good idea. Will change to degC or C.
> >
> > > > + }
> > > > +
> > > > +skip:
> > > > + reg |= chip->thresh;
> > > > + if (disable_s2_shutdown)
> > > > + reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
> > > > +
> > > > + ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> > > > + if (ret < 0)
> > > > + return ret;
> > > > +
> > > > + return ret;
> > >
> > > Simplify the above lines to:
> > >
> > > return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> >
> > Ouch, my code is indeed dumb ...
> >
> > > > @@ -313,12 +441,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
> > > > if (ret < 0)
> > > > return ret;
> > > >
> > > > - chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
> > > > - &qpnp_tm_sensor_ops);
> > > > - if (IS_ERR(chip->tz_dev)) {
> > > > - dev_err(&pdev->dev, "failed to register sensor\n");
> > > > - return PTR_ERR(chip->tz_dev);
> > > > - }
> > > > + chip->initialized = true;
> > >
> > > Should we add "thermal_zone_device_update(chip->tz_dev,
> > > THERMAL_EVENT_UNSPECIFIED);" here
> >
> > Seems reasonable, will do.
> >
> > > ...also: do we care about any type of locking for chip->initialized?
> > > Technically we can be running on weakly ordered memory so if
> > > qpnp_tm_update_temp_no_adc() is running on a different processor then
> > > possibly it could still keep returning the default temperature for a
> > > little while. We could try to analyze whether there's some sort of
> > > implicit barrier or we could add manual memory barriers, but generally
> > > I try to avoid that and just do the simple locking... What about just
> > > setting chip-Initialized = true at the end of qpnp_tm_init() while the
> > > mutex is still held?
> >
> > Thanks for pointing that out. I agree that we should keep things
> > simple, chip->initialized to true at the end of qpnp_tm_init() sounds
> > good to me.
> >
> > > I'd also love to hear from someone with more thermal framework
> > > experience to make sure it's legit to return a default value if
> > > someone calls us while we're initting. It seems sane to me but nice
> > > to confirm it's OK.
> >
> > An alternative could be to return THERMAL_TEMP_INVALID, however I
> > don't see this handled outside of thermal_core.c, not sure if it could
> > throw some other code off.
> >
> > Comments from thermal folks on either approach (or alternatives) are
> > definitely welcome :)
> >
> > > Overall I like the idea of this patch so hopefully others do too.
> > > Thanks for sending it out!
> >
>
> minor ask for next version
>
>
> WARNING: line over 80 characters
> #159: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:65:
> +#define STAGE2_THRESHOLD_MIN 125000 /* Stage 2 Threshold
> Min: 125 C */
>
> WARNING: line over 80 characters
> #160: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:66:
> +#define STAGE2_THRESHOLD_MAX 140000 /* Stage 2 Threshold
> Max: 140 C */
>
> ERROR: trailing statements should be on next line
> #201: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:186:
> + if (!chip->adc)) {
>
> CHECK: Unnecessary parentheses around 'temp == THERMAL_TEMP_INVALID'
> #227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
> + if ((temp == THERMAL_TEMP_INVALID) ||
> + (temp < STAGE2_THRESHOLD_MIN)) {
>
> CHECK: Unnecessary parentheses around 'temp < STAGE2_THRESHOLD_MIN'
> #227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
> + if ((temp == THERMAL_TEMP_INVALID) ||
> + (temp < STAGE2_THRESHOLD_MIN)) {
>
> CHECK: Unnecessary parentheses around 'trips[i].type ==
> THERMAL_TRIP_CRITICAL'
> #305: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:302:
> + if (of_thermal_is_trip_valid(chip->tz_dev, i) &&
> + (trips[i].type == THERMAL_TRIP_CRITICAL))
>
> CHECK: Alignment should match open parenthesis
> #386: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:427:
> + chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev,
> 0, chip,
> +
> &qpnp_tm_sensor_ops);
And it would be great if you could combine these two in your a single
series, say when you fix this patch and send a new version of this
series, please include these too:
https://patchwork.kernel.org/patch/10543335/
https://patchwork.kernel.org/patch/10543333/
>
> > Thanks for the review!
> >
> > Matthias
On Fri, Jul 27, 2018 at 03:40:52PM -0700, Eduardo Valentin wrote:
> On Wed, Jul 25, 2018 at 06:12:28PM -0700, Matthias Kaehlcke wrote:
> > Hi Doug,
> >
> > On Wed, Jul 25, 2018 at 04:19:56PM -0700, Doug Anderson wrote:
> >
> > > On Tue, Jul 24, 2018 at 4:46 PM, Matthias Kaehlcke <[email protected]> wrote:
> > > > +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
> > > > + int temp)
> > > > +{
> > > > + u8 reg;
> > > > + bool disable_s2_shutdown = false;
> > > > + int ret;
> > > > +
> > > > + WARN_ON(!mutex_is_locked(&chip->lock));
> > > > +
> > > > + /*
> > > > + * Default: S2 and S3 shutdown enabled, thresholds at
> > > > + * 105C/125C/145C, monitoring at 25Hz
> > > > + */
> > > > + reg = SHUTDOWN_CTRL1_RATE_25HZ;
> > > > +
> > > > + if ((temp == THERMAL_TEMP_INVALID) ||
> > > > + (temp < STAGE2_THRESHOLD_MIN)) {
> > > > + chip->thresh = THRESH_MIN;
> > > > + goto skip;
> > > > + }
> > > > +
> > > > + if (temp <= STAGE2_THRESHOLD_MAX) {
> > > > + chip->thresh = THRESH_MAX -
> > > > + ((STAGE2_THRESHOLD_MAX - temp) /
> > > > + TEMP_THRESH_STEP);
> > > > + disable_s2_shutdown = true;
> > > > + } else {
> > > > + chip->thresh = THRESH_MAX;
> > > > +
> > > > + if (!IS_ERR(chip->adc))
> > > > + disable_s2_shutdown = true;
> > > > + else
> > > > + dev_warn(chip->dev,
> > > > + "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140°C! Configuring stage 2 shutdown at 140°C.\n");
> > >
> > > Putting a non-ASCII character (the degree symbol) in your commit
> > > message is one thing, but are you sure it's wise to put it in the
> > > kernel logs?
> >
> > A few other drivers also do this
> > (drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c,
> > drivers/macintosh/windfarm_pm121.c), however that doesn't mean it's a
> > good idea. Will change to degC or C.
> >
> > > > + }
> > > > +
> > > > +skip:
> > > > + reg |= chip->thresh;
> > > > + if (disable_s2_shutdown)
> > > > + reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
> > > > +
> > > > + ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> > > > + if (ret < 0)
> > > > + return ret;
> > > > +
> > > > + return ret;
> > >
> > > Simplify the above lines to:
> > >
> > > return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> >
> > Ouch, my code is indeed dumb ...
> >
> > > > @@ -313,12 +441,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
> > > > if (ret < 0)
> > > > return ret;
> > > >
> > > > - chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
> > > > - &qpnp_tm_sensor_ops);
> > > > - if (IS_ERR(chip->tz_dev)) {
> > > > - dev_err(&pdev->dev, "failed to register sensor\n");
> > > > - return PTR_ERR(chip->tz_dev);
> > > > - }
> > > > + chip->initialized = true;
> > >
> > > Should we add "thermal_zone_device_update(chip->tz_dev,
> > > THERMAL_EVENT_UNSPECIFIED);" here
> >
> > Seems reasonable, will do.
> >
> > > ...also: do we care about any type of locking for chip->initialized?
> > > Technically we can be running on weakly ordered memory so if
> > > qpnp_tm_update_temp_no_adc() is running on a different processor then
> > > possibly it could still keep returning the default temperature for a
> > > little while. We could try to analyze whether there's some sort of
> > > implicit barrier or we could add manual memory barriers, but generally
> > > I try to avoid that and just do the simple locking... What about just
> > > setting chip-Initialized = true at the end of qpnp_tm_init() while the
> > > mutex is still held?
> >
> > Thanks for pointing that out. I agree that we should keep things
> > simple, chip->initialized to true at the end of qpnp_tm_init() sounds
> > good to me.
> >
> > > I'd also love to hear from someone with more thermal framework
> > > experience to make sure it's legit to return a default value if
> > > someone calls us while we're initting. It seems sane to me but nice
> > > to confirm it's OK.
> >
> > An alternative could be to return THERMAL_TEMP_INVALID, however I
> > don't see this handled outside of thermal_core.c, not sure if it could
> > throw some other code off.
> >
> > Comments from thermal folks on either approach (or alternatives) are
> > definitely welcome :)
> >
> > > Overall I like the idea of this patch so hopefully others do too.
> > > Thanks for sending it out!
> >
>
> minor ask for next version
>
>
> WARNING: line over 80 characters
> #159: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:65:
> +#define STAGE2_THRESHOLD_MIN 125000 /* Stage 2 Threshold
> Min: 125 C */
>
> WARNING: line over 80 characters
> #160: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:66:
> +#define STAGE2_THRESHOLD_MAX 140000 /* Stage 2 Threshold
> Max: 140 C */
>
> ERROR: trailing statements should be on next line
> #201: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:186:
> + if (!chip->adc)) {
>
> CHECK: Unnecessary parentheses around 'temp == THERMAL_TEMP_INVALID'
> #227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
> + if ((temp == THERMAL_TEMP_INVALID) ||
> + (temp < STAGE2_THRESHOLD_MIN)) {
>
> CHECK: Unnecessary parentheses around 'temp < STAGE2_THRESHOLD_MIN'
> #227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
> + if ((temp == THERMAL_TEMP_INVALID) ||
> + (temp < STAGE2_THRESHOLD_MIN)) {
>
> CHECK: Unnecessary parentheses around 'trips[i].type ==
> THERMAL_TRIP_CRITICAL'
> #305: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:302:
> + if (of_thermal_is_trip_valid(chip->tz_dev, i) &&
> + (trips[i].type == THERMAL_TRIP_CRITICAL))
>
> CHECK: Alignment should match open parenthesis
> #386: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:427:
> + chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev,
> 0, chip,
> +
> &qpnp_tm_sensor_ops);
Thanks for the review, I'll fix these in the next version.
Right after sending the patches I realized that I forgot to run
checkpatch.pl :( Will try to do better in the future.
On Fri, Jul 27, 2018 at 03:45:06PM -0700, Eduardo Valentin wrote:
> On Fri, Jul 27, 2018 at 03:40:52PM -0700, Eduardo Valentin wrote:
> > On Wed, Jul 25, 2018 at 06:12:28PM -0700, Matthias Kaehlcke wrote:
> > > Hi Doug,
> > >
> > > On Wed, Jul 25, 2018 at 04:19:56PM -0700, Doug Anderson wrote:
> > >
> > > > On Tue, Jul 24, 2018 at 4:46 PM, Matthias Kaehlcke <[email protected]> wrote:
> > > > > +static int qpnp_tm_update_critical_trip_temp(struct qpnp_tm_chip *chip,
> > > > > + int temp)
> > > > > +{
> > > > > + u8 reg;
> > > > > + bool disable_s2_shutdown = false;
> > > > > + int ret;
> > > > > +
> > > > > + WARN_ON(!mutex_is_locked(&chip->lock));
> > > > > +
> > > > > + /*
> > > > > + * Default: S2 and S3 shutdown enabled, thresholds at
> > > > > + * 105C/125C/145C, monitoring at 25Hz
> > > > > + */
> > > > > + reg = SHUTDOWN_CTRL1_RATE_25HZ;
> > > > > +
> > > > > + if ((temp == THERMAL_TEMP_INVALID) ||
> > > > > + (temp < STAGE2_THRESHOLD_MIN)) {
> > > > > + chip->thresh = THRESH_MIN;
> > > > > + goto skip;
> > > > > + }
> > > > > +
> > > > > + if (temp <= STAGE2_THRESHOLD_MAX) {
> > > > > + chip->thresh = THRESH_MAX -
> > > > > + ((STAGE2_THRESHOLD_MAX - temp) /
> > > > > + TEMP_THRESH_STEP);
> > > > > + disable_s2_shutdown = true;
> > > > > + } else {
> > > > > + chip->thresh = THRESH_MAX;
> > > > > +
> > > > > + if (!IS_ERR(chip->adc))
> > > > > + disable_s2_shutdown = true;
> > > > > + else
> > > > > + dev_warn(chip->dev,
> > > > > + "No ADC is configured and critical temperature is above the maximum stage 2 threshold of 140°C! Configuring stage 2 shutdown at 140°C.\n");
> > > >
> > > > Putting a non-ASCII character (the degree symbol) in your commit
> > > > message is one thing, but are you sure it's wise to put it in the
> > > > kernel logs?
> > >
> > > A few other drivers also do this
> > > (drivers/gpu/drm/nouveau/nvkm/subdev/clk/base.c,
> > > drivers/macintosh/windfarm_pm121.c), however that doesn't mean it's a
> > > good idea. Will change to degC or C.
> > >
> > > > > + }
> > > > > +
> > > > > +skip:
> > > > > + reg |= chip->thresh;
> > > > > + if (disable_s2_shutdown)
> > > > > + reg |= SHUTDOWN_CTRL1_OVERRIDE_S2;
> > > > > +
> > > > > + ret = qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> > > > > + if (ret < 0)
> > > > > + return ret;
> > > > > +
> > > > > + return ret;
> > > >
> > > > Simplify the above lines to:
> > > >
> > > > return qpnp_tm_write(chip, QPNP_TM_REG_SHUTDOWN_CTRL1, reg);
> > >
> > > Ouch, my code is indeed dumb ...
> > >
> > > > > @@ -313,12 +441,7 @@ static int qpnp_tm_probe(struct platform_device *pdev)
> > > > > if (ret < 0)
> > > > > return ret;
> > > > >
> > > > > - chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, chip,
> > > > > - &qpnp_tm_sensor_ops);
> > > > > - if (IS_ERR(chip->tz_dev)) {
> > > > > - dev_err(&pdev->dev, "failed to register sensor\n");
> > > > > - return PTR_ERR(chip->tz_dev);
> > > > > - }
> > > > > + chip->initialized = true;
> > > >
> > > > Should we add "thermal_zone_device_update(chip->tz_dev,
> > > > THERMAL_EVENT_UNSPECIFIED);" here
> > >
> > > Seems reasonable, will do.
> > >
> > > > ...also: do we care about any type of locking for chip->initialized?
> > > > Technically we can be running on weakly ordered memory so if
> > > > qpnp_tm_update_temp_no_adc() is running on a different processor then
> > > > possibly it could still keep returning the default temperature for a
> > > > little while. We could try to analyze whether there's some sort of
> > > > implicit barrier or we could add manual memory barriers, but generally
> > > > I try to avoid that and just do the simple locking... What about just
> > > > setting chip-Initialized = true at the end of qpnp_tm_init() while the
> > > > mutex is still held?
> > >
> > > Thanks for pointing that out. I agree that we should keep things
> > > simple, chip->initialized to true at the end of qpnp_tm_init() sounds
> > > good to me.
> > >
> > > > I'd also love to hear from someone with more thermal framework
> > > > experience to make sure it's legit to return a default value if
> > > > someone calls us while we're initting. It seems sane to me but nice
> > > > to confirm it's OK.
> > >
> > > An alternative could be to return THERMAL_TEMP_INVALID, however I
> > > don't see this handled outside of thermal_core.c, not sure if it could
> > > throw some other code off.
> > >
> > > Comments from thermal folks on either approach (or alternatives) are
> > > definitely welcome :)
> > >
> > > > Overall I like the idea of this patch so hopefully others do too.
> > > > Thanks for sending it out!
> > >
> >
> > minor ask for next version
> >
> >
> > WARNING: line over 80 characters
> > #159: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:65:
> > +#define STAGE2_THRESHOLD_MIN 125000 /* Stage 2 Threshold
> > Min: 125 C */
> >
> > WARNING: line over 80 characters
> > #160: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:66:
> > +#define STAGE2_THRESHOLD_MAX 140000 /* Stage 2 Threshold
> > Max: 140 C */
> >
> > ERROR: trailing statements should be on next line
> > #201: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:186:
> > + if (!chip->adc)) {
> >
> > CHECK: Unnecessary parentheses around 'temp == THERMAL_TEMP_INVALID'
> > #227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
> > + if ((temp == THERMAL_TEMP_INVALID) ||
> > + (temp < STAGE2_THRESHOLD_MIN)) {
> >
> > CHECK: Unnecessary parentheses around 'temp < STAGE2_THRESHOLD_MIN'
> > #227: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:220:
> > + if ((temp == THERMAL_TEMP_INVALID) ||
> > + (temp < STAGE2_THRESHOLD_MIN)) {
> >
> > CHECK: Unnecessary parentheses around 'trips[i].type ==
> > THERMAL_TRIP_CRITICAL'
> > #305: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:302:
> > + if (of_thermal_is_trip_valid(chip->tz_dev, i) &&
> > + (trips[i].type == THERMAL_TRIP_CRITICAL))
> >
> > CHECK: Alignment should match open parenthesis
> > #386: FILE: drivers/thermal/qcom-spmi-temp-alarm.c:427:
> > + chip->tz_dev = devm_thermal_zone_of_sensor_register(&pdev->dev,
> > 0, chip,
> > +
> > &qpnp_tm_sensor_ops);
>
>
> And it would be great if you could combine these two in your a single
> series, say when you fix this patch and send a new version of this
> series, please include these too:
> https://patchwork.kernel.org/patch/10543335/
> https://patchwork.kernel.org/patch/10543333/
Ok, will do