[1/6] PCI/AER: fix pci_ops return NULL when hotplug a pci bus doing aer error inject

When we inject aer errors to the target pcie device by aer_inject module, the pci_ops of pci
bus which the target device is on will be assigned to pci_ops_aer.So if the target pci device
is a bridge, once we hot-remove and hot-add the bridge, the newly created child bus's pci_ops
will be assigned to pci_ops_aer too.Now every access to the child bus's devices will result to
system panic, because it get a NULL pci_ops in pci_read_aer/pci_write_aer.

Signed-off-by: Yijing Wang <wangyijing@huawei.com>
Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
Reviewed-by: Sven Dietrich <Sven.Dietrich@huawei.com>
---
 drivers/pci/pcie/aer/aer_inject.c |   27 ++++++++++++++++++++++++++-
 1 files changed, 26 insertions(+), 1 deletions(-)

On Wed, 2012-09-19 at 10:40 +0800, Yijing Wang wrote:
> When we inject aer errors to the target pcie device by aer_inject module, the pci_ops of pci
> bus which the target device is on will be assigned to pci_ops_aer.So if the target pci device
> is a bridge, once we hot-remove and hot-add the bridge, the newly created child bus's pci_ops
> will be assigned to pci_ops_aer too.Now every access to the child bus's devices will result to
> system panic, because it get a NULL pci_ops in pci_read_aer/pci_write_aer.
> 
> Signed-off-by: Yijing Wang <wangyijing@huawei.com>
> Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
> Reviewed-by: Sven Dietrich <Sven.Dietrich@huawei.com>
> ---
>  drivers/pci/pcie/aer/aer_inject.c |   27 ++++++++++++++++++++++++++-
>  1 files changed, 26 insertions(+), 1 deletions(-)
> 
> diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
> index 4e24cb8..0f00a27 100644
> --- a/drivers/pci/pcie/aer/aer_inject.c
> +++ b/drivers/pci/pcie/aer/aer_inject.c
> @@ -109,6 +109,26 @@ static struct aer_error *__find_aer_error_by_dev(struct pci_dev *dev)
>  	return __find_aer_error((u16)domain, dev->bus->number, dev->devfn);
>  }
>  
> +/* find pci_ops of the nearest parent bus */
> +static struct pci_ops *__find_pci_bus_ops_parent(struct pci_bus *bus)
> +{
> +	struct pci_bus_ops *bus_ops;
> +	struct pci_bus *pbus = bus->parent;
> +
> +	if (!pbus)
> +		return NULL;
> +
> +	while (pbus) {
> +		list_for_each_entry(bus_ops, &pci_bus_ops_list, list)
> +			if (bus_ops->bus == pbus)
> +				return bus_ops->ops;
> +
> +		pbus = pbus->parent;
> +	}
> +
> +	return NULL;
> +}
> +
>  /* inject_lock must be held before calling */
>  static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
>  {
> @@ -118,7 +138,9 @@ static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
>  		if (bus_ops->bus == bus)
>  			return bus_ops->ops;
>  	}
> -	return NULL;
> +
> +	/* can't find bus_ops, fall back to get bus_ops of upstream bus */
> +	return __find_pci_bus_ops_parent(bus);
>  }
>  
>  static struct pci_bus_ops *pci_bus_ops_pop(void)
> @@ -208,6 +230,7 @@ static int pci_read_aer(struct pci_bus *bus, unsigned int devfn, int where,
>  	}
>  out:
>  	ops = __find_pci_bus_ops(bus);
> +	BUG_ON(!ops);
>  	spin_unlock_irqrestore(&inject_lock, flags);
>  	return ops->read(bus, devfn, where, size, val);
>  }
> @@ -243,6 +266,7 @@ int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where, int size,
>  	}
>  out:
>  	ops = __find_pci_bus_ops(bus);
> +	BUG_ON(!ops);
>  	spin_unlock_irqrestore(&inject_lock, flags);
>  	return ops->write(bus, devfn, where, size, val);
>  }
> @@ -506,6 +530,7 @@ static struct miscdevice aer_inject_device = {
>  	.fops = &aer_inject_fops,
>  };
>  
> +

unnecessary new line?

Best Regards,
Huang Ying

>  static int __init aer_inject_init(void)
>  {
>  	return misc_register(&aer_inject_device);


--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

On 2012/9/19 13:13, Huang Ying wrote:
> On Wed, 2012-09-19 at 10:40 +0800, Yijing Wang wrote:
>> When we inject aer errors to the target pcie device by aer_inject module, the pci_ops of pci
>> bus which the target device is on will be assigned to pci_ops_aer.So if the target pci device
>> is a bridge, once we hot-remove and hot-add the bridge, the newly created child bus's pci_ops
>> will be assigned to pci_ops_aer too.Now every access to the child bus's devices will result to
>> system panic, because it get a NULL pci_ops in pci_read_aer/pci_write_aer.
>>
>> Signed-off-by: Yijing Wang <wangyijing@huawei.com>
>> Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
>> Reviewed-by: Sven Dietrich <Sven.Dietrich@huawei.com>
>> ---
>>  drivers/pci/pcie/aer/aer_inject.c |   27 ++++++++++++++++++++++++++-
>>  1 files changed, 26 insertions(+), 1 deletions(-)
>>
>> diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
>> index 4e24cb8..0f00a27 100644
>> --- a/drivers/pci/pcie/aer/aer_inject.c
>> +++ b/drivers/pci/pcie/aer/aer_inject.c
>> @@ -109,6 +109,26 @@ static struct aer_error *__find_aer_error_by_dev(struct pci_dev *dev)
>>  	return __find_aer_error((u16)domain, dev->bus->number, dev->devfn);
>>  }
>>  
>> +/* find pci_ops of the nearest parent bus */
>> +static struct pci_ops *__find_pci_bus_ops_parent(struct pci_bus *bus)
>> +{
>> +	struct pci_bus_ops *bus_ops;
>> +	struct pci_bus *pbus = bus->parent;
>> +
>> +	if (!pbus)
>> +		return NULL;
>> +
>> +	while (pbus) {
>> +		list_for_each_entry(bus_ops, &pci_bus_ops_list, list)
>> +			if (bus_ops->bus == pbus)
>> +				return bus_ops->ops;
>> +
>> +		pbus = pbus->parent;
>> +	}
>> +
>> +	return NULL;
>> +}
>> +
>>  /* inject_lock must be held before calling */
>>  static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
>>  {
>> @@ -118,7 +138,9 @@ static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
>>  		if (bus_ops->bus == bus)
>>  			return bus_ops->ops;
>>  	}
>> -	return NULL;
>> +
>> +	/* can't find bus_ops, fall back to get bus_ops of upstream bus */
>> +	return __find_pci_bus_ops_parent(bus);
>>  }
>>  
>>  static struct pci_bus_ops *pci_bus_ops_pop(void)
>> @@ -208,6 +230,7 @@ static int pci_read_aer(struct pci_bus *bus, unsigned int devfn, int where,
>>  	}
>>  out:
>>  	ops = __find_pci_bus_ops(bus);
>> +	BUG_ON(!ops);
>>  	spin_unlock_irqrestore(&inject_lock, flags);
>>  	return ops->read(bus, devfn, where, size, val);
>>  }
>> @@ -243,6 +266,7 @@ int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where, int size,
>>  	}
>>  out:
>>  	ops = __find_pci_bus_ops(bus);
>> +	BUG_ON(!ops);
>>  	spin_unlock_irqrestore(&inject_lock, flags);
>>  	return ops->write(bus, devfn, where, size, val);
>>  }
>> @@ -506,6 +530,7 @@ static struct miscdevice aer_inject_device = {
>>  	.fops = &aer_inject_fops,
>>  };
>>  
>> +
> 
> unnecessary new line?
> 

Yes, it's unnecessary, I will clean this later.

Thanks
Yijing

> Best Regards,
> Huang Ying
> 
>>  static int __init aer_inject_init(void)
>>  {
>>  	return misc_register(&aer_inject_device);
> 
> 
> 
> .
>

On 2012-9-19 10:40, Yijing Wang wrote:
> When we inject aer errors to the target pcie device by aer_inject module, the pci_ops of pci
> bus which the target device is on will be assigned to pci_ops_aer.So if the target pci device
> is a bridge, once we hot-remove and hot-add the bridge, the newly created child bus's pci_ops
> will be assigned to pci_ops_aer too.Now every access to the child bus's devices will result to
> system panic, because it get a NULL pci_ops in pci_read_aer/pci_write_aer.
> 
> Signed-off-by: Yijing Wang <wangyijing@huawei.com>
> Signed-off-by: Jiang Liu <jiang.liu@huawei.com>
> Reviewed-by: Sven Dietrich <Sven.Dietrich@huawei.com>
> ---
>  drivers/pci/pcie/aer/aer_inject.c |   27 ++++++++++++++++++++++++++-
>  1 files changed, 26 insertions(+), 1 deletions(-)
> 
> diff --git a/drivers/pci/pcie/aer/aer_inject.c b/drivers/pci/pcie/aer/aer_inject.c
> index 4e24cb8..0f00a27 100644
> --- a/drivers/pci/pcie/aer/aer_inject.c
> +++ b/drivers/pci/pcie/aer/aer_inject.c
> @@ -109,6 +109,26 @@ static struct aer_error *__find_aer_error_by_dev(struct pci_dev *dev)
>  	return __find_aer_error((u16)domain, dev->bus->number, dev->devfn);
>  }
>  
> +/* find pci_ops of the nearest parent bus */
> +static struct pci_ops *__find_pci_bus_ops_parent(struct pci_bus *bus)
> +{
> +	struct pci_bus_ops *bus_ops;
> +	struct pci_bus *pbus = bus->parent;
> +
> +	if (!pbus)
> +		return NULL;
> +
> +	while (pbus) {
> +		list_for_each_entry(bus_ops, &pci_bus_ops_list, list)
> +			if (bus_ops->bus == pbus)
> +				return bus_ops->ops;
> +
> +		pbus = pbus->parent;
> +	}
> +
> +	return NULL;
> +}
> +
>  /* inject_lock must be held before calling */
>  static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
>  {
> @@ -118,7 +138,9 @@ static struct pci_ops *__find_pci_bus_ops(struct pci_bus *bus)
>  		if (bus_ops->bus == bus)
>  			return bus_ops->ops;
>  	}
> -	return NULL;
> +
> +	/* can't find bus_ops, fall back to get bus_ops of upstream bus */
> +	return __find_pci_bus_ops_parent(bus);
>  }
>  
>  static struct pci_bus_ops *pci_bus_ops_pop(void)
> @@ -208,6 +230,7 @@ static int pci_read_aer(struct pci_bus *bus, unsigned int devfn, int where,
>  	}
>  out:
>  	ops = __find_pci_bus_ops(bus);
> +	BUG_ON(!ops);
>  	spin_unlock_irqrestore(&inject_lock, flags);
>  	return ops->read(bus, devfn, where, size, val);
>  }
> @@ -243,6 +266,7 @@ int pci_write_aer(struct pci_bus *bus, unsigned int devfn, int where, int size,
>  	}
>  out:
>  	ops = __find_pci_bus_ops(bus);
> +	BUG_ON(!ops);
How about move BUG_ON(!ops)into __find_pci_bus_ops?

>  	spin_unlock_irqrestore(&inject_lock, flags);
>  	return ops->write(bus, devfn, where, size, val);
>  }
> @@ -506,6 +530,7 @@ static struct miscdevice aer_inject_device = {
>  	.fops = &aer_inject_fops,
>  };
>  
> +
Please remove this above line.

>  static int __init aer_inject_init(void)
>  {
>  	return misc_register(&aer_inject_device);


--
To unsubscribe from this list: send the line "unsubscribe linux-pci" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html