[PATCH v3 11/15] drm/panfrost: Disable the AS on unhandled page faults

[Steven Price]

On 25/06/2021 14:33, Boris Brezillon wrote:
> If we don't do that, we have to wait for the job timeout to expire
> before the fault jobs gets killed.
> 
> v3:
> * Make sure the AS is re-enabled when new jobs are submitted to the
>   context
> 
> Signed-off-by: Boris Brezillon <boris.brezillon at collabora.com>

Reviewed-by: Steven Price <steven.price at arm.com>

> ---
>  drivers/gpu/drm/panfrost/panfrost_device.h |  1 +
>  drivers/gpu/drm/panfrost/panfrost_mmu.c    | 34 ++++++++++++++++++++--
>  2 files changed, 32 insertions(+), 3 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panfrost/panfrost_device.h b/drivers/gpu/drm/panfrost/panfrost_device.h
> index bfe32907ba6b..efe9a675b614 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_device.h
> +++ b/drivers/gpu/drm/panfrost/panfrost_device.h
> @@ -96,6 +96,7 @@ struct panfrost_device {
>  	spinlock_t as_lock;
>  	unsigned long as_in_use_mask;
>  	unsigned long as_alloc_mask;
> +	unsigned long as_faulty_mask;
>  	struct list_head as_lru_list;
>  
>  	struct panfrost_job_slot *js;
> diff --git a/drivers/gpu/drm/panfrost/panfrost_mmu.c b/drivers/gpu/drm/panfrost/panfrost_mmu.c
> index b4f0c673cd7f..65e98c51cb66 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_mmu.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_mmu.c
> @@ -154,6 +154,7 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
>  	as = mmu->as;
>  	if (as >= 0) {
>  		int en = atomic_inc_return(&mmu->as_count);
> +		u32 mask = BIT(as) | BIT(16 + as);
>  
>  		/*
>  		 * AS can be retained by active jobs or a perfcnt context,
> @@ -162,6 +163,18 @@ u32 panfrost_mmu_as_get(struct panfrost_device *pfdev, struct panfrost_mmu *mmu)
>  		WARN_ON(en >= (NUM_JOB_SLOTS + 1));
>  
>  		list_move(&mmu->list, &pfdev->as_lru_list);
> +
> +		if (pfdev->as_faulty_mask & mask) {
> +			/* Unhandled pagefault on this AS, the MMU was
> +			 * disabled. We need to re-enable the MMU after
> +			 * clearing+unmasking the AS interrupts.
> +			 */
> +			mmu_write(pfdev, MMU_INT_CLEAR, mask);
> +			mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask);
> +			pfdev->as_faulty_mask &= ~mask;
> +			panfrost_mmu_enable(pfdev, mmu);
> +		}
> +
>  		goto out;
>  	}
>  
> @@ -211,6 +224,7 @@ void panfrost_mmu_reset(struct panfrost_device *pfdev)
>  	spin_lock(&pfdev->as_lock);
>  
>  	pfdev->as_alloc_mask = 0;
> +	pfdev->as_faulty_mask = 0;
>  
>  	list_for_each_entry_safe(mmu, mmu_tmp, &pfdev->as_lru_list, list) {
>  		mmu->as = -1;
> @@ -662,7 +676,7 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
>  		if ((status & mask) == BIT(as) && (exception_type & 0xF8) == 0xC0)
>  			ret = panfrost_mmu_map_fault_addr(pfdev, as, addr);
>  
> -		if (ret)
> +		if (ret) {
>  			/* terminal fault, print info about the fault */
>  			dev_err(pfdev->dev,
>  				"Unhandled Page fault in AS%d at VA 0x%016llX\n"
> @@ -680,14 +694,28 @@ static irqreturn_t panfrost_mmu_irq_handler_thread(int irq, void *data)
>  				access_type, access_type_name(pfdev, fault_status),
>  				source_id);
>  
> +			spin_lock(&pfdev->as_lock);
> +			/* Ignore MMU interrupts on this AS until it's been
> +			 * re-enabled.
> +			 */
> +			pfdev->as_faulty_mask |= mask;
> +
> +			/* Disable the MMU to kill jobs on this AS. */
> +			panfrost_mmu_disable(pfdev, as);
> +			spin_unlock(&pfdev->as_lock);
> +		}
> +
>  		status &= ~mask;
>  
>  		/* If we received new MMU interrupts, process them before returning. */
>  		if (!status)
> -			status = mmu_read(pfdev, MMU_INT_RAWSTAT);
> +			status = mmu_read(pfdev, MMU_INT_RAWSTAT) & ~pfdev->as_faulty_mask;
>  	}
>  
> -	mmu_write(pfdev, MMU_INT_MASK, ~0);
> +	spin_lock(&pfdev->as_lock);
> +	mmu_write(pfdev, MMU_INT_MASK, ~pfdev->as_faulty_mask);
> +	spin_unlock(&pfdev->as_lock);
> +
>  	return IRQ_HANDLED;
>  };
>  
>