Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Thu, 28 Jul 2022 12:48:23 +0100
Message-ID: <87wnbxwj94.wl-maz@kernel.org>
From:   Marc Zyngier <maz@kernel.org>
To:     Johan Hovold <johan+linaro@kernel.org>
Cc:     Thomas Gleixner <tglx@linutronix.de>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        Rob Herring <robh@kernel.org>, linux-kernel@vger.kernel.org,
        Dmitry Torokhov <dtor@chromium.org>,
        Jon Hunter <jonathanh@nvidia.com>
Subject: Re: [PATCH] irqdomain: Fix mapping-creation race
In-Reply-To: <20220728092710.21190-1-johan+linaro@kernel.org>
References: <20220728092710.21190-1-johan+linaro@kernel.org>
User-Agent: Wanderlust/2.15.9 (Almost Unreal) SEMI-EPG/1.14.7 (Harue)
 FLIM-LB/1.14.9 (=?UTF-8?B?R29qxY0=?=) APEL-LB/10.8 EasyPG/1.0.0 Emacs/27.1
 (x86_64-pc-linux-gnu) MULE/6.0 (HANACHIRUSATO)
MIME-Version: 1.0 (generated by SEMI-EPG 1.14.7 - "Harue")
Content-Type: text/plain; charset=US-ASCII
Precedence: bulk

On Thu, 28 Jul 2022 10:27:10 +0100,
Johan Hovold <johan+linaro@kernel.org> wrote:
> 
> Parallel probing (e.g. due to asynchronous probing) of devices that share
> interrupts can currently result in two mappings for the same hardware
> interrupt to be created.

And I thought nobody would be using shared interrupts anymore. Turns
out people are still building braindead HW... :-/

> 
> Add a serialising mapping mutex so that looking for an existing mapping
> before creating a new one is done atomically.
> 
> Note that serialising the lookup and creation in
> irq_create_mapping_affinity() would have been enough to prevent the
> duplicate mapping, but that could instead cause
> irq_create_fwspec_mapping() to fail when there is a race.
> 
> Fixes: 765230b5f084 ("driver-core: add asynchronous probing support for drivers")
> Fixes: b62b2cf5759b ("irqdomain: Fix handling of type settings for existing mappings")
> Cc: Dmitry Torokhov <dtor@chromium.org>
> Cc: Jon Hunter <jonathanh@nvidia.com>
> Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
> ---
>  kernel/irq/irqdomain.c | 46 +++++++++++++++++++++++++++++++-----------
>  1 file changed, 34 insertions(+), 12 deletions(-)
> 
> diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
> index 8fe1da9614ee..d263a7dd4170 100644
> --- a/kernel/irq/irqdomain.c
> +++ b/kernel/irq/irqdomain.c
> @@ -22,6 +22,7 @@
>  
>  static LIST_HEAD(irq_domain_list);
>  static DEFINE_MUTEX(irq_domain_mutex);
> +static DEFINE_MUTEX(irq_mapping_mutex);

I'd really like to avoid a global mutex. At the very least this should
be a per-domain mutex, otherwise this will serialise a lot more than
what is needed.

>  
>  static struct irq_domain *irq_default_domain;
>  
> @@ -669,7 +670,7 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
>  #endif
>  
>  /**
> - * irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space
> + * __irq_create_mapping_affinity() - Map a hardware interrupt into linux irq space
>   * @domain: domain owning this hardware interrupt or NULL for default domain
>   * @hwirq: hardware irq number in that domain space
>   * @affinity: irq affinity
> @@ -679,9 +680,9 @@ EXPORT_SYMBOL_GPL(irq_create_direct_mapping);
>   * If the sense/trigger is to be specified, set_irq_type() should be called
>   * on the number returned from that call.
>   */

This comment should be moved to the exported function, instead of
documenting something that nobody can call...

> -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(struct irq_domain *domain,
> +						  irq_hw_number_t hwirq,
> +						  const struct irq_affinity_desc *affinity)
>  {
>  	struct device_node *of_node;
>  	int virq;
> @@ -724,6 +725,19 @@ unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
>  
>  	return virq;
>  }
> +
> +unsigned int irq_create_mapping_affinity(struct irq_domain *domain,
> +					 irq_hw_number_t hwirq,
> +					 const struct irq_affinity_desc *affinity)
> +{
> +	unsigned int virq;
> +
> +	mutex_lock(&irq_mapping_mutex);
> +	virq = __irq_create_mapping_affinity(domain, hwirq, affinity);
> +	mutex_unlock(&irq_mapping_mutex);
> +
> +	return virq;
> +}
>  EXPORT_SYMBOL_GPL(irq_create_mapping_affinity);
>  
>  static int irq_domain_translate(struct irq_domain *d,
> @@ -789,6 +803,8 @@ 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_mapping_mutex);
> +
>  	/*
>  	 * If we've already configured this interrupt,
>  	 * don't do it again, or hell will break loose.
> @@ -801,7 +817,7 @@ 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
> @@ -810,26 +826,26 @@ 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);
>  		if (virq <= 0)
> -			return 0;
> +			goto err;
>  	} else {
>  		/* Create mapping */
> -		virq = irq_create_mapping(domain, hwirq);
> +		virq = __irq_create_mapping_affinity(domain, hwirq, NULL);

This rechecks for the existence of the mapping. Surely we can do a bit
better by rejigging this (admittedly bitrotting) code.

Thanks,

	M.

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