Re: [PATCH v5 06/19] irqdomain: Fix mapping-creation race

[Marc Zyngier]

On Thu, 09 Feb 2023 13:23:10 +0000,
Johan Hovold <johan+linaro@xxxxxxxxxx> wrote:
> 
> Parallel probing of devices that share interrupts (e.g. when a driver
> uses asynchronous probing) can currently result in two mappings for the
> same hardware interrupt to be created due to missing serialisation.
> 
> Make sure to hold the irq_domain_mutex when creating mappings so that
> looking for an existing mapping before creating a new one is done
> atomically.
> 
> Fixes: 765230b5f084 ("driver-core: add asynchronous probing support for drivers")
> Fixes: b62b2cf5759b ("irqdomain: Fix handling of type settings for existing mappings")
> Link: https://lore.kernel.org/r/YuJXMHoT4ijUxnRb@xxxxxxxxxxxxxxxxxxxx
> Cc: stable@xxxxxxxxxxxxxxx      # 4.8
> Cc: Dmitry Torokhov <dtor@xxxxxxxxxxxx>
> Cc: Jon Hunter <jonathanh@xxxxxxxxxx>
> Tested-by: Hsin-Yi Wang <hsinyi@xxxxxxxxxxxx>
> Tested-by: Mark-PK Tsai <mark-pk.tsai@xxxxxxxxxxxx>
> Signed-off-by: Johan Hovold <johan+linaro@xxxxxxxxxx>
> ---
>  kernel/irq/irqdomain.c | 55 ++++++++++++++++++++++++++++++------------
>  1 file changed, 40 insertions(+), 15 deletions(-)
> 
> diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
> index 7b57949bc79c..1ddb01bd49a4 100644
> --- a/kernel/irq/irqdomain.c
> +++ b/kernel/irq/irqdomain.c
> @@ -25,6 +25,9 @@ static DEFINE_MUTEX(irq_domain_mutex);
>  
>  static struct irq_domain *irq_default_domain;
>  
> +static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base,
> +					unsigned int nr_irqs, int node, void *arg,
> +					bool realloc, const struct irq_affinity_desc *affinity);
>  static void irq_domain_check_hierarchy(struct irq_domain *domain);
>  
>  struct irqchip_fwid {
> @@ -682,9 +685,9 @@ unsigned int irq_create_direct_mapping(struct irq_domain *domain)
>  EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
>  #endif
>  
> -static unsigned int __irq_create_mapping_affinity(struct irq_domain *domain,
> -						  irq_hw_number_t hwirq,
> -						  const struct irq_affinity_desc *affinity)
> +static unsigned int irq_create_mapping_affinity_locked(struct irq_domain *domain,
> +						       irq_hw_number_t hwirq,
> +						       const struct irq_affinity_desc *affinity)
>  {
>  	struct device_node *of_node = irq_domain_get_of_node(domain);
>  	int virq;
> @@ -699,7 +702,7 @@ static unsigned int __irq_create_mapping_affinity(struct irq_domain *domain,
>  		return 0;
>  	}
>  
> -	if (irq_domain_associate(domain, virq, hwirq)) {
> +	if (irq_domain_associate_locked(domain, virq, hwirq)) {
>  		irq_free_desc(virq);
>  		return 0;
>  	}
> @@ -735,14 +738,20 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
>  		return 0;
>  	}
>  
> +	mutex_lock(&irq_domain_mutex);
> +
>  	/* Check if mapping already exists */
>  	virq = irq_find_mapping(domain, hwirq);
>  	if (virq) {
>  		pr_debug("existing mapping on virq %d\n", virq);
> -		return virq;
> +		goto out;
>  	}
>  
> -	return __irq_create_mapping_affinity(domain, hwirq, affinity);
> +	virq = irq_create_mapping_affinity_locked(domain, hwirq, affinity);
> +out:
> +	mutex_unlock(&irq_domain_mutex);
> +
> +	return virq;
>  }
>  EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
>  
> @@ -809,6 +818,8 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
>  	if (WARN_ON(type & ~IRQ_TYPE_SENSE_MASK))
>  		type &= IRQ_TYPE_SENSE_MASK;
>  
> +	mutex_lock(&irq_domain_mutex);
> +
>  	/*
>  	 * If we've already configured this interrupt,
>  	 * don't do it again, or hell will break loose.
> @@ -821,7 +832,7 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
>  		 * interrupt number.
>  		 */
>  		if (type == IRQ_TYPE_NONE || type == irq_get_trigger_type(virq))
> -			return virq;
> +			goto out;
>  
>  		/*
>  		 * If the trigger type has not been set yet, then set
> @@ -830,36 +841,43 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec)
>  		if (irq_get_trigger_type(virq) == IRQ_TYPE_NONE) {
>  			irq_data = irq_get_irq_data(virq);
>  			if (!irq_data)
> -				return 0;
> +				goto err;
>  
>  			irqd_set_trigger_type(irq_data, type);
> -			return virq;
> +			goto out;
>  		}
>  
>  		pr_warn("type mismatch, failed to map hwirq-%lu for %s!\n",
>  			hwirq, of_node_full_name(to_of_node(fwspec->fwnode)));
> -		return 0;
> +		goto err;
>  	}
>  
>  	if (irq_domain_is_hierarchy(domain)) {
> -		virq = irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, fwspec);
> +		virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE,
> +						    fwspec, false, NULL);
>  		if (virq <= 0)
> -			return 0;
> +			goto err;
>  	} else {
>  		/* Create mapping */
> -		virq = __irq_create_mapping_affinity(domain, hwirq, NULL);
> +		virq = irq_create_mapping_affinity_locked(domain, hwirq, NULL);
>  		if (!virq)
> -			return virq;
> +			goto err;
>  	}
>  
>  	irq_data = irq_get_irq_data(virq);
>  	if (WARN_ON(!irq_data))
> -		return 0;
> +		goto err;
>  
>  	/* Store trigger type */
>  	irqd_set_trigger_type(irq_data, type);
> +out:
> +	mutex_unlock(&irq_domain_mutex);
>  
>  	return virq;
> +err:
> +	mutex_unlock(&irq_domain_mutex);
> +
> +	return 0;

nit: it'd look better if we had a single exit path with the unlock,
setting virq to 0 on failure. Not a big deal, as this can be tidied up
when applied.

Thanks,

	M.

-- 
Without deviation from the norm, progress is not possible.