Re: [PATCH 27/37] iommu/arm-smmu-v3: Register fault workqueue

[Jonathan Cameron <Jonathan.Cameron-hv44wF8Li93QT0dZR+AlfA@public.gmane.org>]

On Mon, 12 Feb 2018 18:33:42 +0000
Jean-Philippe Brucker <jean-philippe.brucker-5wv7dgnIgG8@public.gmane.org> wrote:

> When using PRI or Stall, the PRI or event handler enqueues faults into the
> core fault queue. Register it based on the SMMU features.
> 
> When the core stops using a PASID, it notifies the SMMU to flush all
> instances of this PASID from the PRI queue. Add a way to flush the PRI and
> event queue. PRI and event thread now take a spinlock while processing the
> queue. The flush handler takes this lock to inspect the queue state.
> We avoid livelock, where the SMMU adds fault to the queue faster than we
> can consume them, by incrementing a 'batch' number on every cycle so the
> flush handler only has to wait a complete cycle (two batch increments.)
> 
> Signed-off-by: Jean-Philippe Brucker <jean-philippe.brucker-5wv7dgnIgG8@public.gmane.org>
I think you have a potential incorrect free issue... See inline.

Jonathan
> ---
>  drivers/iommu/Kconfig       |   1 +
>  drivers/iommu/arm-smmu-v3.c | 103 +++++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 103 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
> index d434f7085dc2..d79c68754bb9 100644
> --- a/drivers/iommu/Kconfig
> +++ b/drivers/iommu/Kconfig
> @@ -354,6 +354,7 @@ config ARM_SMMU_V3
>  	depends on ARM64
>  	select IOMMU_API
>  	select IOMMU_SVA
> +	select IOMMU_FAULT
>  	select IOMMU_IO_PGTABLE_LPAE
>  	select ARM_SMMU_V3_CONTEXT
>  	select GENERIC_MSI_IRQ_DOMAIN
> diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
> index 8528704627b5..c5b3a43becaf 100644
> --- a/drivers/iommu/arm-smmu-v3.c
> +++ b/drivers/iommu/arm-smmu-v3.c
> @@ -494,6 +494,10 @@ struct arm_smmu_queue {
>  
>  	u32 __iomem			*prod_reg;
>  	u32 __iomem			*cons_reg;
> +
> +	/* Event and PRI */
> +	u64				batch;
> +	wait_queue_head_t		wq;
>  };
>  
>  struct arm_smmu_cmdq {
> @@ -610,6 +614,9 @@ struct arm_smmu_device {
>  
>  	/* IOMMU core code handle */
>  	struct iommu_device		iommu;
> +
> +	/* Notifier for the fault queue */
> +	struct notifier_block		faultq_nb;
>  };
>  
>  /* SMMU private data for each master */
> @@ -1247,14 +1254,23 @@ static int arm_smmu_init_l2_strtab(struct arm_smmu_device *smmu, u32 sid)
>  static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
>  {
>  	int i;
> +	int num_handled = 0;
>  	struct arm_smmu_device *smmu = dev;
>  	struct arm_smmu_queue *q = &smmu->evtq.q;
> +	size_t queue_size = 1 << q->max_n_shift;
>  	u64 evt[EVTQ_ENT_DWORDS];
>  
> +	spin_lock(&q->wq.lock);
>  	do {
>  		while (!queue_remove_raw(q, evt)) {
>  			u8 id = evt[0] >> EVTQ_0_ID_SHIFT & EVTQ_0_ID_MASK;
>  
> +			if (++num_handled == queue_size) {
> +				q->batch++;
> +				wake_up_locked(&q->wq);
> +				num_handled = 0;
> +			}
> +
>  			dev_info(smmu->dev, "event 0x%02x received:\n", id);
>  			for (i = 0; i < ARRAY_SIZE(evt); ++i)
>  				dev_info(smmu->dev, "\t0x%016llx\n",
> @@ -1272,6 +1288,11 @@ static irqreturn_t arm_smmu_evtq_thread(int irq, void *dev)
>  
>  	/* Sync our overflow flag, as we believe we're up to speed */
>  	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
> +
> +	q->batch++;
> +	wake_up_locked(&q->wq);
> +	spin_unlock(&q->wq.lock);
> +
>  	return IRQ_HANDLED;
>  }
>  
> @@ -1315,13 +1336,24 @@ static void arm_smmu_handle_ppr(struct arm_smmu_device *smmu, u64 *evt)
>  
>  static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
>  {
> +	int num_handled = 0;
>  	struct arm_smmu_device *smmu = dev;
>  	struct arm_smmu_queue *q = &smmu->priq.q;
> +	size_t queue_size = 1 << q->max_n_shift;
>  	u64 evt[PRIQ_ENT_DWORDS];
>  
> +	spin_lock(&q->wq.lock);
>  	do {
> -		while (!queue_remove_raw(q, evt))
> +		while (!queue_remove_raw(q, evt)) {
> +			spin_unlock(&q->wq.lock);
>  			arm_smmu_handle_ppr(smmu, evt);
> +			spin_lock(&q->wq.lock);
> +			if (++num_handled == queue_size) {
> +				q->batch++;
> +				wake_up_locked(&q->wq);
> +				num_handled = 0;
> +			}
> +		}
>  
>  		if (queue_sync_prod(q) == -EOVERFLOW)
>  			dev_err(smmu->dev, "PRIQ overflow detected -- requests lost\n");
> @@ -1329,9 +1361,65 @@ static irqreturn_t arm_smmu_priq_thread(int irq, void *dev)
>  
>  	/* Sync our overflow flag, as we believe we're up to speed */
>  	q->cons = Q_OVF(q, q->prod) | Q_WRP(q, q->cons) | Q_IDX(q, q->cons);
> +
> +	q->batch++;
> +	wake_up_locked(&q->wq);
> +	spin_unlock(&q->wq.lock);
> +
>  	return IRQ_HANDLED;
>  }
>  
> +/*
> + * arm_smmu_flush_queue - wait until all events/PPRs currently in the queue have
> + * been consumed.
> + *
> + * Wait until the queue thread finished a batch, or until the queue is empty.
> + * Note that we don't handle overflows on q->batch. If it occurs, just wait for
> + * the queue to be empty.
> + */
> +static int arm_smmu_flush_queue(struct arm_smmu_device *smmu,
> +				struct arm_smmu_queue *q, const char *name)
> +{
> +	int ret;
> +	u64 batch;
> +
> +	spin_lock(&q->wq.lock);
> +	if (queue_sync_prod(q) == -EOVERFLOW)
> +		dev_err(smmu->dev, "%s overflow detected -- requests lost\n", name);
> +
> +	batch = q->batch;
> +	ret = wait_event_interruptible_locked(q->wq, queue_empty(q) ||
> +					      q->batch >= batch + 2);
> +	spin_unlock(&q->wq.lock);
> +
> +	return ret;
> +}
> +
> +static int arm_smmu_flush_queues(struct notifier_block *nb,
> +				 unsigned long action, void *data)
> +{
> +	struct arm_smmu_device *smmu = container_of(nb, struct arm_smmu_device,
> +						    faultq_nb);
> +	struct device *dev = data;
> +	struct arm_smmu_master_data *master = NULL;
> +
> +	if (dev)
> +		master = dev->iommu_fwspec->iommu_priv;
> +
> +	if (master) {
> +		/* TODO: add support for PRI and Stall */
> +		return 0;
> +	}
> +
> +	/* No target device, flush all queues. */
> +	if (smmu->features & ARM_SMMU_FEAT_STALLS)
> +		arm_smmu_flush_queue(smmu, &smmu->evtq.q, "evtq");
> +	if (smmu->features & ARM_SMMU_FEAT_PRI)
> +		arm_smmu_flush_queue(smmu, &smmu->priq.q, "priq");
> +
> +	return 0;
> +}
> +
>  static int arm_smmu_device_disable(struct arm_smmu_device *smmu);
>  
>  static irqreturn_t arm_smmu_gerror_handler(int irq, void *dev)
> @@ -2288,6 +2376,10 @@ static int arm_smmu_init_one_queue(struct arm_smmu_device *smmu,
>  		     << Q_BASE_LOG2SIZE_SHIFT;
>  
>  	q->prod = q->cons = 0;
> +
> +	init_waitqueue_head(&q->wq);
> +	q->batch = 0;
> +
>  	return 0;
>  }
>  
> @@ -3168,6 +3260,13 @@ static int arm_smmu_device_probe(struct platform_device *pdev)
>  	if (ret)
>  		return ret;
>  
> +	if (smmu->features & (ARM_SMMU_FEAT_STALLS | ARM_SMMU_FEAT_PRI)) {
> +		smmu->faultq_nb.notifier_call = arm_smmu_flush_queues;
> +		ret = iommu_fault_queue_register(&smmu->faultq_nb);
Here you register only if this smmu supports stalls or pri which is fine, but
see the unregister path.

> +		if (ret)
> +			return ret;
> +	}
> +
>  	/* And we're up. Go go go! */
>  	ret = iommu_device_sysfs_add(&smmu->iommu, dev, NULL,
>  				     "smmu3.%pa", &ioaddr);
> @@ -3210,6 +3309,8 @@ static int arm_smmu_device_remove(struct platform_device *pdev)
>  {
>  	struct arm_smmu_device *smmu = platform_get_drvdata(pdev);
>  
> +	iommu_fault_queue_unregister(&smmu->faultq_nb);

Here you unregister from the fault queue unconditionally.  That is mostly
safe but it seems to decrement and potentially destroy the work queue that
is in use by another smmu instance that does support page faulting.

> +
>  	arm_smmu_device_disable(smmu);
>  
>  	return 0;