[Xen-devel] Re: [PATCH] xen/blkfront: allow xenbus state transition to Closing->Closed when not Connected.

[Jens Axboe <jens.axboe@xxxxxxxxxx>]

On Mon, May 18 2009, Jeremy Fitzhardinge wrote:
> Ian Campbell wrote:
>> This situation can occur when attempting to attach a block device whose 
>> backend
>> is an empty physical CD-ROM driver. The backend in this case will go directly
>> from the Initialising state to Closing->Closed. Previously this would result 
>> in
>> a NULL pointer deref on info->gd (xenbus_dev_fatal does not return as 
>> a1a15ac5
>> seems to expect)
>>
>> Signed-off-by: Ian Campbell <ian.campbell@xxxxxxxxxx>
>> Cc: Jeremy Fitzhardinge <jeremy@xxxxxxxx>
>>   
>
> Jens, does this look OK to you?
>
> Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>

Looks fine, shall I add it for 2.6.30? Does it need a stable backport?

>>  drivers/block/xen-blkfront.c |    6 ++++--
>>  1 files changed, 4 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
>> index aa0c94b..a6cbf7b 100644
>> --- a/drivers/block/xen-blkfront.c
>> +++ b/drivers/block/xen-blkfront.c
>> @@ -977,8 +977,10 @@ static void backend_changed(struct xenbus_device *dev,
>>              break;
>>      case XenbusStateClosing:
>> -            if (info->gd == NULL)
>> -                    xenbus_dev_fatal(dev, -ENODEV, "gd is NULL");
>> +            if (info->gd == NULL) {
>> +                    xenbus_frontend_closed(dev);
>> +                    break;
>> +            }
>>              bd = bdget_disk(info->gd, 0);
>>              if (bd == NULL)
>>                      xenbus_dev_fatal(dev, -ENODEV, "bdget failed");
>>   
>

-- 
Jens Axboe


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel