kernel panic on device removal when using a workqueue and delayed_work

kernel panic on device removal when using a workqueue and delayed_work

[Frank Schäfer]

Hi,

with the following simple kernel module, I have a good chance to get a 
kernel panic when I unplug the device:


#include <linux/workqueue.h>
#include <linux/usb.h>
#include <linux/module.h>

MODULE_AUTHOR("Nobody");
MODULE_DESCRIPTION("example driver for causing kernel panic");
MODULE_LICENSE("GPL");

static struct delayed_work poll_work;

static void poll(struct work_struct *work)
{
     schedule_delayed_work(&poll_work,
                   msecs_to_jiffies(100));
}

static int test_probe(struct usb_interface *intf,
               const struct usb_device_id *id)
{
     INIT_DELAYED_WORK(&poll_work, poll);
     schedule_delayed_work(&poll_work,
                   msecs_to_jiffies(100));
     return 0;
}

static void test_disconnect(struct usb_interface *intf)
{
     cancel_delayed_work_sync(&poll_work);
}

static const struct usb_device_id device_table[] = {
     {USB_DEVICE(0x1234, 0x5678)},
     {}
};

MODULE_DEVICE_TABLE(usb, device_table);

static struct usb_driver test_driver = {
     .name       = "test",
     .id_table   = device_table,
     .probe      = test_probe,
     .disconnect = test_disconnect,
};

static int __init test_mod_init(void)
{
     return usb_register(&test_driver);
}

static void __exit test_mod_exit(void)
{
     usb_deregister(&test_driver);
}

module_init(test_mod_init);
module_exit(test_mod_exit);




A picture of the backtrace (the machine immediately turns off without 
saving a backtrace) can be found at

http://imageshack.us/photo/my-images/823/img075gv.jpg

Kernel version is 3.1.0.


This is the first time I'm using a workqueue, so there is a good chance 
that I missed something...
Or is this a kernel bug ?


Regards,
Frank Schaefer

Re: kernel panic on device removal when using a workqueue and delayed_work

[Yong Zhang]

On Sun, Oct 30, 2011 at 08:19:10PM +0100, Frank Sch�fer wrote:
> Hi,
> 
> with the following simple kernel module, I have a good chance to get
> a kernel panic when I unplug the device:
> 
> 
> #include <linux/workqueue.h>
> #include <linux/usb.h>
> #include <linux/module.h>
> 
> MODULE_AUTHOR("Nobody");
> MODULE_DESCRIPTION("example driver for causing kernel panic");
> MODULE_LICENSE("GPL");
> 
> static struct delayed_work poll_work;
> 
> static void poll(struct work_struct *work)
> {
>     schedule_delayed_work(&poll_work,
>                   msecs_to_jiffies(100));
> }
> 
> static int test_probe(struct usb_interface *intf,
>               const struct usb_device_id *id)
> {
>     INIT_DELAYED_WORK(&poll_work, poll);
>     schedule_delayed_work(&poll_work,
>                   msecs_to_jiffies(100));
>     return 0;
> }
> 
> static void test_disconnect(struct usb_interface *intf)
> {
>     cancel_delayed_work_sync(&poll_work);
> }
> 
> static const struct usb_device_id device_table[] = {
>     {USB_DEVICE(0x1234, 0x5678)},
>     {}
> };
> 
> MODULE_DEVICE_TABLE(usb, device_table);
> 
> static struct usb_driver test_driver = {
>     .name       = "test",
>     .id_table   = device_table,
>     .probe      = test_probe,
>     .disconnect = test_disconnect,
> };
> 
> static int __init test_mod_init(void)
> {
>     return usb_register(&test_driver);
> }
> 
> static void __exit test_mod_exit(void)
> {
>     usb_deregister(&test_driver);
> }
> 
> module_init(test_mod_init);
> module_exit(test_mod_exit);
> 
> 
> 
> 
> A picture of the backtrace (the machine immediately turns off
> without saving a backtrace) can be found at
> 
> http://imageshack.us/photo/my-images/823/img075gv.jpg
> 
> Kernel version is 3.1.0.
> 
> 
> This is the first time I'm using a workqueue, so there is a good
> chance that I missed something...

You should cancel the work you have armed before exit.
See cancel_delayed_work().

> Or is this a kernel bug ?

I don't think so.

Thanks,
Yong

Re: kernel panic on device removal when using a workqueue and delayed_work

[Frank Schäfer]

Am 31.10.2011 04:11, schrieb Yong Zhang:
> On Sun, Oct 30, 2011 at 08:19:10PM +0100, Frank Sch�fer wrote:
>> Hi,
>>
>> with the following simple kernel module, I have a good chance to get
>> a kernel panic when I unplug the device:
>>
>>
>> #include<linux/workqueue.h>
>> #include<linux/usb.h>
>> #include<linux/module.h>
>>
>> MODULE_AUTHOR("Nobody");
>> MODULE_DESCRIPTION("example driver for causing kernel panic");
>> MODULE_LICENSE("GPL");
>>
>> static struct delayed_work poll_work;
>>
>> static void poll(struct work_struct *work)
>> {
>>      schedule_delayed_work(&poll_work,
>>                    msecs_to_jiffies(100));
>> }
>>
>> static int test_probe(struct usb_interface *intf,
>>                const struct usb_device_id *id)
>> {
>>      INIT_DELAYED_WORK(&poll_work, poll);
>>      schedule_delayed_work(&poll_work,
>>                    msecs_to_jiffies(100));
>>      return 0;
>> }
>>
>> static void test_disconnect(struct usb_interface *intf)
>> {
>>      cancel_delayed_work_sync(&poll_work);
>> }
...
>> static const struct usb_device_id device_table[] = {
>>      {USB_DEVICE(0x1234, 0x5678)},
>>      {}
>> };
>>
>> MODULE_DEVICE_TABLE(usb, device_table);
>>
>> static struct usb_driver test_driver = {
>>      .name       = "test",
>>      .id_table   = device_table,
>>      .probe      = test_probe,
>>      .disconnect = test_disconnect,
>> };
>>
>> static int __init test_mod_init(void)
>> {
>>      return usb_register(&test_driver);
>> }
>>
>> static void __exit test_mod_exit(void)
>> {
>>      usb_deregister(&test_driver);
>> }
>>
>> module_init(test_mod_init);
>> module_exit(test_mod_exit);
>>
>>
>>
>>
>> A picture of the backtrace (the machine immediately turns off
>> without saving a backtrace) can be found at
>>
>> http://imageshack.us/photo/my-images/823/img075gv.jpg
>>
>> Kernel version is 3.1.0.
>>
>>
>> This is the first time I'm using a workqueue, so there is a good
>> chance that I missed something...
> You should cancel the work you have armed before exit.
> See cancel_delayed_work().
That's what I'm doing (see above).
Did you read the code ? ;-)

Regards,
Frank Schaefer
>> Or is this a kernel bug ?
> I don't think so.
>
> Thanks,
> Yong

Re: kernel panic on device removal when using a workqueue and delayed_work

[Oliver Neukum]

Am Montag, 31. Oktober 2011, 11:26:58 schrieb Frank Schäfer:
> Am 31.10.2011 04:11, schrieb Yong Zhang:

> >> This is the first time I'm using a workqueue, so there is a good
> >> chance that I missed something...
> > You should cancel the work you have armed before exit.
> > See cancel_delayed_work().
> That's what I'm doing (see above).
> Did you read the code ? ;-)

Does it work if you set a flag and resubmit the work only conditionally
on it?

	Regards
		Oliver

Re: kernel panic on device removal when using a workqueue and delayed_work

[Yong Zhang]

On Mon, Oct 31, 2011 at 11:26:58AM +0100, Frank Schäfer wrote:
> Am 31.10.2011 04:11, schrieb Yong Zhang:
> That's what I'm doing (see above).
> Did you read the code ? ;-)

Oh, blind me.

Maybe you can enable DEBUG_OBJECTS_TIMERS && DEBUG_OBJECTS_WORK
to check if anything is broken.

Thanks,
Yong

Re: kernel panic on device removal when using a workqueue and delayed_work

[Frank Schäfer]

Am 31.10.2011 11:29, schrieb Oliver Neukum:
> Am Montag, 31. Oktober 2011, 11:26:58 schrieb Frank Schäfer:
>> Am 31.10.2011 04:11, schrieb Yong Zhang:
>>>> This is the first time I'm using a workqueue, so there is a good
>>>> chance that I missed something...
>>> You should cancel the work you have armed before exit.
>>> See cancel_delayed_work().
>> That's what I'm doing (see above).
>> Did you read the code ? ;-)
> Does it work if you set a flag and resubmit the work only conditionally
> on it?
What do you mean ? Which flag should I set and what's the condition to 
check for ?

Regards,
Frank
> 	Regards
> 		Oliver

Re: kernel panic on device removal when using a workqueue and delayed_work

[Frank Schäfer]

Am 02.11.2011 07:31, schrieb Yong Zhang:
> On Mon, Oct 31, 2011 at 11:26:58AM +0100, Frank Schäfer wrote:
>> Am 31.10.2011 04:11, schrieb Yong Zhang:
>> That's what I'm doing (see above).
>> Did you read the code ? ;-)
> Oh, blind me.
>
> Maybe you can enable DEBUG_OBJECTS_TIMERS&&  DEBUG_OBJECTS_WORK
> to check if anything is broken.
I enabled both debug options but nothing changed (nothing new in the logs).
Any other ideas to debug this further ?

Thanks,
Frank
> Thanks,
> Yong