mbox series

[v3,0/9] thermal: tsens: Handle critical interrupts

Message ID cover.1577976221.git.amit.kucheria@linaro.org
Headers show
Series thermal: tsens: Handle critical interrupts | expand

Message

Amit Kucheria Jan. 2, 2020, 2:54 p.m. UTC
TSENS IP v2.x supports critical interrupts and v2.3+ adds watchdog support
in case the FSM is stuck. Enable support in the driver.

This series was generated on top of linux-next from 20191202 to capture
const changes for msm8976 that is queued currently.

Changes from v2:
- Handle old DTBs w/o critical irq in the same way as fix sent for 5.5

Changes from v1:
- Make tsens_features non-const to allow run time detection of features
- Pass tsens_sensor around as a const
- Fix a bug to release dev pointer in success path
- Address review comments from Bjorn and Stephen (thanks for the review)
- Add msm8998 and msm8996 DTSI changes for critical interrupts


Amit Kucheria (9):
  drivers: thermal: tsens: De-constify struct tsens_features
  drivers: thermal: tsens: Pass around struct tsens_sensor as a constant
  drivers: thermal: tsens: use simpler variables
  drivers: thermal: tsens: Release device in success path
  drivers: thermal: tsens: Add critical interrupt support
  drivers: thermal: tsens: Add watchdog support
  arm64: dts: sdm845: thermal: Add critical interrupt support
  arm64: dts: msm8996: thermal: Add critical interrupt support
  arm64: dts: msm8998: thermal: Add critical interrupt support

 arch/arm64/boot/dts/qcom/msm8996.dtsi |  10 +-
 arch/arm64/boot/dts/qcom/msm8998.dtsi |  10 +-
 arch/arm64/boot/dts/qcom/sdm845.dtsi  |  10 +-
 drivers/thermal/qcom/tsens-8960.c     |   4 +-
 drivers/thermal/qcom/tsens-common.c   | 188 +++++++++++++++++++++++---
 drivers/thermal/qcom/tsens-v0_1.c     |   6 +-
 drivers/thermal/qcom/tsens-v1.c       |   6 +-
 drivers/thermal/qcom/tsens-v2.c       |  24 +++-
 drivers/thermal/qcom/tsens.c          |  24 +++-
 drivers/thermal/qcom/tsens.h          | 104 ++++++++++++--
 10 files changed, 330 insertions(+), 56 deletions(-)

Comments

Bjorn Andersson Jan. 2, 2020, 7:18 p.m. UTC | #1
On Thu 02 Jan 06:54 PST 2020, Amit Kucheria wrote:

> We already dereference the sensor and save it into a variable. Use the
> variable directly to make the code easier to read.
> 

Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>

> Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
> ---
>  drivers/thermal/qcom/tsens-common.c | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
> 
> diff --git a/drivers/thermal/qcom/tsens-common.c b/drivers/thermal/qcom/tsens-common.c
> index c2df30a08b9e..1cbc5a6e5b4f 100644
> --- a/drivers/thermal/qcom/tsens-common.c
> +++ b/drivers/thermal/qcom/tsens-common.c
> @@ -368,7 +368,7 @@ irqreturn_t tsens_irq_thread(int irq, void *data)
>  			tsens_set_interrupt(priv, hw_id, UPPER, disable);
>  			if (d.up_thresh > temp) {
>  				dev_dbg(priv->dev, "[%u] %s: re-arm upper\n",
> -					priv->sensor[i].hw_id, __func__);
> +					hw_id, __func__);
>  				tsens_set_interrupt(priv, hw_id, UPPER, enable);
>  			} else {
>  				trigger = true;
> @@ -379,7 +379,7 @@ irqreturn_t tsens_irq_thread(int irq, void *data)
>  			tsens_set_interrupt(priv, hw_id, LOWER, disable);
>  			if (d.low_thresh < temp) {
>  				dev_dbg(priv->dev, "[%u] %s: re-arm low\n",
> -					priv->sensor[i].hw_id, __func__);
> +					hw_id, __func__);
>  				tsens_set_interrupt(priv, hw_id, LOWER, enable);
>  			} else {
>  				trigger = true;
> @@ -392,7 +392,7 @@ irqreturn_t tsens_irq_thread(int irq, void *data)
>  		if (trigger) {
>  			dev_dbg(priv->dev, "[%u] %s: TZ update trigger (%d mC)\n",
>  				hw_id, __func__, temp);
> -			thermal_zone_device_update(priv->sensor[i].tzd,
> +			thermal_zone_device_update(s->tzd,
>  						   THERMAL_EVENT_UNSPECIFIED);
>  		} else {
>  			dev_dbg(priv->dev, "[%u] %s: no violation:  %d\n",
> @@ -435,7 +435,7 @@ int tsens_set_trips(void *_sensor, int low, int high)
>  	spin_unlock_irqrestore(&priv->ul_lock, flags);
>  
>  	dev_dbg(dev, "[%u] %s: (%d:%d)->(%d:%d)\n",
> -		s->hw_id, __func__, d.low_thresh, d.up_thresh, cl_low, cl_high);
> +		hw_id, __func__, d.low_thresh, d.up_thresh, cl_low, cl_high);
>  
>  	return 0;
>  }
> -- 
> 2.20.1
>
Bjorn Andersson Jan. 2, 2020, 7:45 p.m. UTC | #2
On Thu 02 Jan 06:54 PST 2020, Amit Kucheria wrote:
[..]
> @@ -189,6 +197,9 @@ static void tsens_set_interrupt_v1(struct tsens_priv *priv, u32 hw_id,
>  	case LOWER:
>  		index = LOW_INT_CLEAR_0 + hw_id;
>  		break;
> +	case CRITICAL:
> +		/* No critical interrupts before v2 */
> +		break;

You need to break harder, right now you're just attempting to write
"enable" to VER_MAJOR in this case.

>  	}
>  	regmap_field_write(priv->rf[index], enable ? 0 : 1);
>  }
[..]
> @@ -321,6 +357,64 @@ static inline u32 masked_irq(u32 hw_id, u32 mask, enum tsens_ver ver)
>  	return 0;
>  }
>  
> +/**
> + * tsens_critical_irq_thread - Threaded interrupt handler for critical interrupts

() on the function name to denote it being a function.

> + * @irq: irq number
> + * @data: tsens controller private data
> + *
> + * Check all sensors to find ones that violated their critical threshold limits.
> + * Clear and then re-enable the interrupt.
> + *
> + * The level-triggered interrupt might deassert if the temperature returned to
> + * within the threshold limits by the time the handler got scheduled. We
> + * consider the irq to have been handled in that case.
> + *
> + * Return: IRQ_HANDLED
> + */
> +irqreturn_t tsens_critical_irq_thread(int irq, void *data)
> +{
> +	struct tsens_priv *priv = data;
> +	struct tsens_irq_data d;
> +	unsigned long flags;
> +	int temp, ret, i;
> +
> +	for (i = 0; i < priv->num_sensors; i++) {
> +		const struct tsens_sensor *s = &priv->sensor[i];
> +		u32 hw_id = s->hw_id;
> +
> +		if (IS_ERR(s->tzd))
> +			continue;
> +		if (!tsens_threshold_violated(priv, hw_id, &d))
> +			continue;
> +		ret = get_temp_tsens_valid(s, &temp);
> +		if (ret) {
> +			dev_err(priv->dev, "[%u] %s: error reading sensor\n", hw_id, __func__);
> +			continue;
> +		}
> +
> +		spin_lock_irqsave(&priv->ul_lock, flags);

You meant crit_lock here?

But perhaps more importantly, why do you need a lock here?

> +
> +		tsens_read_irq_state(priv, hw_id, s, &d);
> +
> +		if (d.crit_viol &&
> +		    !masked_irq(hw_id, d.crit_irq_mask, tsens_version(priv))) {
> +			tsens_set_interrupt(priv, hw_id, CRITICAL, false);
> +			if (d.crit_thresh > temp) {
> +				dev_dbg(priv->dev, "[%u] %s: re-arm upper\n",
> +					hw_id, __func__);
> +			} else {
> +				dev_dbg(priv->dev, "[%u] %s: TZ update trigger (%d mC)\n",
> +					hw_id, __func__, temp);
> +			}
> +			tsens_set_interrupt(priv, hw_id, CRITICAL, true);
> +		}
> +
> +		spin_unlock_irqrestore(&priv->crit_lock, flags);
> +	}
> +
> +	return IRQ_HANDLED;
> +}
[..]
> @@ -125,6 +125,28 @@ static int tsens_register(struct tsens_priv *priv)
>  		goto err_put_device;
>  	}
>  
> +	if (priv->feat->crit_int) {
> +		irq_crit = platform_get_irq_byname(pdev, "critical");
> +		if (irq_crit < 0) {
> +			ret = irq_crit;
> +			/* For old DTs with no IRQ defined */
> +			if (irq_crit == -ENXIO)
> +				ret = 0;
> +			goto err_crit_int;
> +		}
> +		ret = devm_request_threaded_irq(&pdev->dev, irq_crit,
> +						NULL, tsens_critical_irq_thread,
> +						IRQF_TRIGGER_HIGH | IRQF_ONESHOT,

You should omit the IRQF_TRIGGER_HIGH here, it will be provided by the
system configuration (DT).

> +						dev_name(&pdev->dev), priv);
> +		if (ret) {
> +			dev_err(&pdev->dev, "%s: failed to get critical irq\n", __func__);
> +			goto err_crit_int;
> +		}
> +
> +		enable_irq_wake(irq_crit);
> +	}
> +
> +err_crit_int:
>  	enable_irq_wake(irq);
>  
>  err_put_device:
> diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h
[..]
> @@ -460,6 +526,8 @@ struct tsens_context {
>   * @srot_map: pointer to SROT register address space
>   * @tm_offset: deal with old device trees that don't address TM and SROT
>   *             address space separately
> + * @ul_lock: lock while processing upper/lower threshold interrupts

This looks like an unrelated fixup to a previous patch? Please keep it
separate.

> + * @crit_lock: lock while processing critical threshold interrupts
>   * @rf: array of regmap_fields used to store value of the field
>   * @ctx: registers to be saved and restored during suspend/resume
>   * @feat: features of the IP
> @@ -479,6 +547,9 @@ struct tsens_priv {
>  	/* lock for upper/lower threshold interrupts */
>  	spinlock_t			ul_lock;
>  
> +	/* lock for critical threshold interrupts */
> +	spinlock_t			crit_lock;

You're lacking a spin_lock_init() of this.

> +
>  	struct regmap_field		*rf[MAX_REGFIELDS];
>  	struct tsens_context		ctx;
>  	struct tsens_features		*feat;
> @@ -500,6 +571,7 @@ int tsens_enable_irq(struct tsens_priv *priv);
>  void tsens_disable_irq(struct tsens_priv *priv);
>  int tsens_set_trips(void *_sensor, int low, int high);
>  irqreturn_t tsens_irq_thread(int irq, void *data);
> +irqreturn_t tsens_critical_irq_thread(int irq, void *data);

I think you should squash tsens.c and tsens-common.c into one file, so
you don't need to keep adding these extern declarations for every
function - separate of this series of course.

Regards,
Bjorn

>  
>  /* TSENS target */
>  extern struct tsens_plat_data data_8960;
> -- 
> 2.20.1
>
Amit Kucheria Jan. 30, 2020, 12:07 p.m. UTC | #3
On Fri, Jan 3, 2020 at 1:15 AM Bjorn Andersson
<bjorn.andersson@linaro.org> wrote:
>
> On Thu 02 Jan 06:54 PST 2020, Amit Kucheria wrote:
> [..]
> > @@ -189,6 +197,9 @@ static void tsens_set_interrupt_v1(struct tsens_priv *priv, u32 hw_id,
> >       case LOWER:
> >               index = LOW_INT_CLEAR_0 + hw_id;
> >               break;
> > +     case CRITICAL:
> > +             /* No critical interrupts before v2 */
> > +             break;
>
> You need to break harder, right now you're just attempting to write
> "enable" to VER_MAJOR in this case.

Will fix.

>
> >       }
> >       regmap_field_write(priv->rf[index], enable ? 0 : 1);
> >  }
> [..]
> > @@ -321,6 +357,64 @@ static inline u32 masked_irq(u32 hw_id, u32 mask, enum tsens_ver ver)
> >       return 0;
> >  }
> >
> > +/**
> > + * tsens_critical_irq_thread - Threaded interrupt handler for critical interrupts
>
> () on the function name to denote it being a function.

Will fix.

>
> > + * @irq: irq number
> > + * @data: tsens controller private data
> > + *
> > + * Check all sensors to find ones that violated their critical threshold limits.
> > + * Clear and then re-enable the interrupt.
> > + *
> > + * The level-triggered interrupt might deassert if the temperature returned to
> > + * within the threshold limits by the time the handler got scheduled. We
> > + * consider the irq to have been handled in that case.
> > + *
> > + * Return: IRQ_HANDLED
> > + */
> > +irqreturn_t tsens_critical_irq_thread(int irq, void *data)
> > +{
> > +     struct tsens_priv *priv = data;
> > +     struct tsens_irq_data d;
> > +     unsigned long flags;
> > +     int temp, ret, i;
> > +
> > +     for (i = 0; i < priv->num_sensors; i++) {
> > +             const struct tsens_sensor *s = &priv->sensor[i];
> > +             u32 hw_id = s->hw_id;
> > +
> > +             if (IS_ERR(s->tzd))
> > +                     continue;
> > +             if (!tsens_threshold_violated(priv, hw_id, &d))
> > +                     continue;
> > +             ret = get_temp_tsens_valid(s, &temp);
> > +             if (ret) {
> > +                     dev_err(priv->dev, "[%u] %s: error reading sensor\n", hw_id, __func__);
> > +                     continue;
> > +             }
> > +
> > +             spin_lock_irqsave(&priv->ul_lock, flags);
>
> You meant crit_lock here?

Good catch, will fix.

>
> But perhaps more importantly, why do you need a lock here?

I'm reading and changing interrupt state registers in this section and
there can be multiple interrupts occurring simultaneously. Without a
lock, the interrupt threads could potentially stomp over each other's
register state.

Having said that, I think I found a potential problem in porting the
downstream driver code. Basically, we only need critical interrupt to
enable watchdog support. The critical interrupt HW line can be
asserted by watchdog and by actual critical interrupts. One to one
mapping of tsens critical interrupts to trip type CRITICAL in Linux
leads to a HW shutdown. And we can use the trip type PASSIVE with
multiple ranges of temperatures to handle several levels of trip.

So I'll change the code below to mask the critical interrupts in the
event it is triggered and only use the irq thread to handle watchdog
interrupts.

> > +
> > +             tsens_read_irq_state(priv, hw_id, s, &d);
> > +
> > +             if (d.crit_viol &&
> > +                 !masked_irq(hw_id, d.crit_irq_mask, tsens_version(priv))) {
> > +                     tsens_set_interrupt(priv, hw_id, CRITICAL, false);
> > +                     if (d.crit_thresh > temp) {
> > +                             dev_dbg(priv->dev, "[%u] %s: re-arm upper\n",
> > +                                     hw_id, __func__);
> > +                     } else {
> > +                             dev_dbg(priv->dev, "[%u] %s: TZ update trigger (%d mC)\n",
> > +                                     hw_id, __func__, temp);
> > +                     }
> > +                     tsens_set_interrupt(priv, hw_id, CRITICAL, true);
> > +             }
> > +
> > +             spin_unlock_irqrestore(&priv->crit_lock, flags);
> > +     }
> > +
> > +     return IRQ_HANDLED;
> > +}
> [..]
> > @@ -125,6 +125,28 @@ static int tsens_register(struct tsens_priv *priv)
> >               goto err_put_device;
> >       }
> >
> > +     if (priv->feat->crit_int) {
> > +             irq_crit = platform_get_irq_byname(pdev, "critical");
> > +             if (irq_crit < 0) {
> > +                     ret = irq_crit;
> > +                     /* For old DTs with no IRQ defined */
> > +                     if (irq_crit == -ENXIO)
> > +                             ret = 0;
> > +                     goto err_crit_int;
> > +             }
> > +             ret = devm_request_threaded_irq(&pdev->dev, irq_crit,
> > +                                             NULL, tsens_critical_irq_thread,
> > +                                             IRQF_TRIGGER_HIGH | IRQF_ONESHOT,
>
> You should omit the IRQF_TRIGGER_HIGH here, it will be provided by the
> system configuration (DT).

Will fix.

>
> > +                                             dev_name(&pdev->dev), priv);
> > +             if (ret) {
> > +                     dev_err(&pdev->dev, "%s: failed to get critical irq\n", __func__);
> > +                     goto err_crit_int;
> > +             }
> > +
> > +             enable_irq_wake(irq_crit);
> > +     }
> > +
> > +err_crit_int:
> >       enable_irq_wake(irq);
> >
> >  err_put_device:
> > diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h
> [..]
> > @@ -460,6 +526,8 @@ struct tsens_context {
> >   * @srot_map: pointer to SROT register address space
> >   * @tm_offset: deal with old device trees that don't address TM and SROT
> >   *             address space separately
> > + * @ul_lock: lock while processing upper/lower threshold interrupts
>
> This looks like an unrelated fixup to a previous patch? Please keep it
> separate.

Will remove.


> > + * @crit_lock: lock while processing critical threshold interrupts
> >   * @rf: array of regmap_fields used to store value of the field
> >   * @ctx: registers to be saved and restored during suspend/resume
> >   * @feat: features of the IP
> > @@ -479,6 +547,9 @@ struct tsens_priv {
> >       /* lock for upper/lower threshold interrupts */
> >       spinlock_t                      ul_lock;
> >
> > +     /* lock for critical threshold interrupts */
> > +     spinlock_t                      crit_lock;
>
> You're lacking a spin_lock_init() of this.

Will fix.

> > +
> >       struct regmap_field             *rf[MAX_REGFIELDS];
> >       struct tsens_context            ctx;
> >       struct tsens_features           *feat;
> > @@ -500,6 +571,7 @@ int tsens_enable_irq(struct tsens_priv *priv);
> >  void tsens_disable_irq(struct tsens_priv *priv);
> >  int tsens_set_trips(void *_sensor, int low, int high);
> >  irqreturn_t tsens_irq_thread(int irq, void *data);
> > +irqreturn_t tsens_critical_irq_thread(int irq, void *data);
>
> I think you should squash tsens.c and tsens-common.c into one file, so
> you don't need to keep adding these extern declarations for every
> function - separate of this series of course.

Agreed. The separation no longer makes sense.

Thanks for the review.