Re: [PATCH v1 2/2] iio: adc: tsc2046: fix sleeping in atomic context warning and a deadlock after iio_trigger_poll() call

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



Hi Jonathan,

On Sun, Jul 04, 2021 at 06:57:10PM +0100, Jonathan Cameron wrote:
> On Fri, 25 Jun 2021 08:59:22 +0200
> Oleksij Rempel <o.rempel@xxxxxxxxxxxxxx> wrote:
> 
> > If iio_trigger_poll() is called after IRQ was disabled, we will call
> > reenable_trigger() directly from hard IRQ or hrtimer context instead of
> > IRQ thread. In this case we will run in to multiple issue as sleeping in atomic
> > context and a deadlock.
> 
> Hmm. This sounds like a problem that might bite us in other circumstances.
> 
> So do I have the basic issue right in thinking we have a race between
> calling iio_trigger_poll() and having no devices still using that trigger?
> Thus we end up with all of trig->subirqs not being enabled.
> 
> There was a previous discussion that the calls to iio_trigger_notify_done() in
> iio_trigger_poll() are only meant to decrement the counter, as the assumption
> was that the calls via threads would always happen later.  Unfortunately this
> is all clearly a little bit racy and I suspect not many of the reenable() callbacks
> are safe if they are called in interrupt context.
> 
> Perhaps an alternative would be to schedule the reenable() if we hit it from
> that path thus ensuring it doesn't happen in a place where we can't sleep?
> 
> Would something like that solve your problem?

Yes :)

> I'd do it by having a new function
> 
> iio_trigger_notify_done_schedule() that uses a work struct to call
> trig->ops->reenable(trig) from a context that can sleep.
> 
> It's a rare corner case so I don't really care that in theory we might have
> a device that was safe to reenable the trigger without sleeping.  That makes
> it easier to just have one path for this which allows sleeping.

Yes.

Regards,
Oleksij

> 
> > 
> > To avoid this issue, rework the trigger to use state machine. All state
> > changes are done over the hrtimer, so it allows us to drop fsleep() and
> > avoid the deadlock.
> > 
> > Fixes: 9374e8f5a38d ("iio: adc: add ADC driver for the TI TSC2046 controller")
> > Signed-off-by: Oleksij Rempel <o.rempel@xxxxxxxxxxxxxx>
> > ---
> >  drivers/iio/adc/ti-tsc2046.c | 102 ++++++++++++++++++++---------------
> >  1 file changed, 58 insertions(+), 44 deletions(-)
> > 
> > diff --git a/drivers/iio/adc/ti-tsc2046.c b/drivers/iio/adc/ti-tsc2046.c
> > index d84ae6b008c1..91f6bd5effe7 100644
> > --- a/drivers/iio/adc/ti-tsc2046.c
> > +++ b/drivers/iio/adc/ti-tsc2046.c
> > @@ -123,14 +123,21 @@ struct tsc2046_adc_ch_cfg {
> >  	unsigned int oversampling_ratio;
> >  };
> >  
> > +enum tsc2046_state {
> > +	TSC2046_STATE_STANDBY,
> > +	TSC2046_STATE_ENABLE_IRQ_POLL,
> > +	TSC2046_STATE_POLL,
> > +	TSC2046_STATE_ENABLE_IRQ,
> > +};
> > +
> >  struct tsc2046_adc_priv {
> >  	struct spi_device *spi;
> >  	const struct tsc2046_adc_dcfg *dcfg;
> >  
> >  	struct iio_trigger *trig;
> >  	struct hrtimer trig_timer;
> > -	spinlock_t trig_lock;
> > -	unsigned int trig_more_count;
> > +	enum tsc2046_state state;
> > +	spinlock_t state_lock;
> >  
> >  	struct spi_transfer xfer;
> >  	struct spi_message msg;
> > @@ -411,21 +418,47 @@ static const struct iio_info tsc2046_adc_info = {
> >  	.update_scan_mode = tsc2046_adc_update_scan_mode,
> >  };
> >  
> > -static enum hrtimer_restart tsc2046_adc_trig_more(struct hrtimer *hrtimer)
> > +static enum hrtimer_restart tsc2046_adc_timer(struct hrtimer *hrtimer)
> >  {
> >  	struct tsc2046_adc_priv *priv = container_of(hrtimer,
> >  						     struct tsc2046_adc_priv,
> >  						     trig_timer);
> >  	unsigned long flags;
> >  
> > -	spin_lock_irqsave(&priv->trig_lock, flags);
> > -
> > -	disable_irq_nosync(priv->spi->irq);
> > -
> > -	priv->trig_more_count++;
> > -	iio_trigger_poll(priv->trig);
> > -
> > -	spin_unlock_irqrestore(&priv->trig_lock, flags);
> > +	spin_lock_irqsave(&priv->state_lock, flags);
> > +	switch (priv->state) {
> > +	case TSC2046_STATE_ENABLE_IRQ_POLL:
> > +		/*
> > +		 * IRQ handler called iio_trigger_poll() to sample ADC.
> > +		 * Here we
> > +		 * - re-enable IRQs
> > +		 * - start hrtimer for timeout if no IRQ will occur
> > +		 */
> > +		priv->state = TSC2046_STATE_POLL;
> > +		enable_irq(priv->spi->irq);
> > +		hrtimer_start(&priv->trig_timer,
> > +			      ns_to_ktime(priv->scan_interval_us *
> > +					  NSEC_PER_USEC),
> > +			      HRTIMER_MODE_REL_SOFT);
> > +		break;
> > +	case TSC2046_STATE_POLL:
> > +		disable_irq_nosync(priv->spi->irq);
> > +		priv->state = TSC2046_STATE_ENABLE_IRQ;
> > +		/* iio_trigger_poll() starts hrtimer */
> > +		iio_trigger_poll(priv->trig);
> > +		break;
> > +	case TSC2046_STATE_ENABLE_IRQ:
> > +		priv->state = TSC2046_STATE_STANDBY;
> > +		enable_irq(priv->spi->irq);
> > +		break;
> > +	case TSC2046_STATE_STANDBY:
> > +		fallthrough;
> > +	default:
> > +		dev_warn(&priv->spi->dev, "Got unexpected state: %i\n",
> > +			 priv->state);
> > +		break;
> > +	}
> > +	spin_unlock_irqrestore(&priv->state_lock, flags);
> >  
> >  	return HRTIMER_NORESTART;
> >  }
> > @@ -434,16 +467,17 @@ static irqreturn_t tsc2046_adc_irq(int irq, void *dev_id)
> >  {
> >  	struct iio_dev *indio_dev = dev_id;
> >  	struct tsc2046_adc_priv *priv = iio_priv(indio_dev);
> > -
> > -	spin_lock(&priv->trig_lock);
> > +	unsigned long flags;
> >  
> >  	hrtimer_try_to_cancel(&priv->trig_timer);
> >  
> > -	priv->trig_more_count = 0;
> > +	spin_lock_irqsave(&priv->state_lock, flags);
> >  	disable_irq_nosync(priv->spi->irq);
> > -	iio_trigger_poll(priv->trig);
> > +	priv->state = TSC2046_STATE_ENABLE_IRQ_POLL;
> >  
> > -	spin_unlock(&priv->trig_lock);
> > +	/* iio_trigger_poll() starts hrtimer */
> > +	iio_trigger_poll(priv->trig);
> > +	spin_unlock_irqrestore(&priv->state_lock, flags);
> >  
> >  	return IRQ_HANDLED;
> >  }
> > @@ -452,37 +486,16 @@ static void tsc2046_adc_reenable_trigger(struct iio_trigger *trig)
> >  {
> >  	struct iio_dev *indio_dev = iio_trigger_get_drvdata(trig);
> >  	struct tsc2046_adc_priv *priv = iio_priv(indio_dev);
> > -	unsigned long flags;
> > -	int delta;
> > +	ktime_t tim;
> >  
> >  	/*
> >  	 * We can sample it as fast as we can, but usually we do not need so
> >  	 * many samples. Reduce the sample rate for default (touchscreen) use
> >  	 * case.
> > -	 * Currently we do not need a highly precise sample rate. It is enough
> > -	 * to have calculated numbers.
> > -	 */
> > -	delta = priv->scan_interval_us - priv->time_per_scan_us;
> > -	if (delta > 0)
> > -		fsleep(delta);
> > -
> > -	spin_lock_irqsave(&priv->trig_lock, flags);
> > -
> > -	/*
> > -	 * We need to trigger at least one extra sample to detect state
> > -	 * difference on ADC side.
> >  	 */
> > -	if (!priv->trig_more_count) {
> > -		int timeout_ms = DIV_ROUND_UP(priv->scan_interval_us,
> > -					      USEC_PER_MSEC);
> > -
> > -		hrtimer_start(&priv->trig_timer, ms_to_ktime(timeout_ms),
> > -			      HRTIMER_MODE_REL_SOFT);
> > -	}
> > -
> > -	enable_irq(priv->spi->irq);
> > -
> > -	spin_unlock_irqrestore(&priv->trig_lock, flags);
> > +	tim = ns_to_ktime((priv->scan_interval_us - priv->time_per_scan_us) *
> > +			  NSEC_PER_USEC);
> > +	hrtimer_start(&priv->trig_timer, tim, HRTIMER_MODE_REL_SOFT);
> >  }
> >  
> >  static int tsc2046_adc_set_trigger_state(struct iio_trigger *trig, bool enable)
> > @@ -493,8 +506,8 @@ static int tsc2046_adc_set_trigger_state(struct iio_trigger *trig, bool enable)
> >  	if (enable) {
> >  		enable_irq(priv->spi->irq);
> >  	} else {
> > +		hrtimer_cancel(&priv->trig_timer);
> >  		disable_irq(priv->spi->irq);
> > -		hrtimer_try_to_cancel(&priv->trig_timer);
> >  	}
> >  
> >  	return 0;
> > @@ -668,10 +681,11 @@ static int tsc2046_adc_probe(struct spi_device *spi)
> >  	iio_trigger_set_drvdata(trig, indio_dev);
> >  	trig->ops = &tsc2046_adc_trigger_ops;
> >  
> > -	spin_lock_init(&priv->trig_lock);
> > +	spin_lock_init(&priv->state_lock);
> > +	priv->state = TSC2046_STATE_STANDBY;
> >  	hrtimer_init(&priv->trig_timer, CLOCK_MONOTONIC,
> >  		     HRTIMER_MODE_REL_SOFT);
> > -	priv->trig_timer.function = tsc2046_adc_trig_more;
> > +	priv->trig_timer.function = tsc2046_adc_timer;
> >  
> >  	ret = devm_iio_trigger_register(dev, trig);
> >  	if (ret) {
> 
> 

-- 
Pengutronix e.K.                           |                             |
Steuerwalder Str. 21                       | http://www.pengutronix.de/  |
31137 Hildesheim, Germany                  | Phone: +49-5121-206917-0    |
Amtsgericht Hildesheim, HRA 2686           | Fax:   +49-5121-206917-5555 |



[Index of Archives]     [Device Tree Compilter]     [Device Tree Spec]     [Linux Driver Backports]     [Video for Linux]     [Linux USB Devel]     [Linux PCI Devel]     [Linux Audio Users]     [Linux Kernel]     [Linux SCSI]     [XFree86]     [Yosemite Backpacking]


  Powered by Linux