Hi...
On Tue, Jan 6, 2009 at 10:10 PM, Adrian Cornish wrote:
>> Hm,from the function's comment:
>>
>> /*
>> *This callback runs from the timer interrupt, and checks
>> * whether the watchdog thread has hung or not:
>> */
>>
>> that means,it runs in interrupt context, thus AFAIK it won't
>> be p
> Hm,from the function's comment:
>
> /*
> *This callback runs from the timer interrupt, and checks
> * whether the watchdog thread has hung or not:
> */
>
> that means,it runs in interrupt context, thus AFAIK it won't
> be preempted.
Thanks Mulyadi.
If I wanted to trace back through the code
Hi...
On Tue, Jan 6, 2009 at 8:42 PM, Adrian Cornish wrote:
> I am investigating why on 1 particular machine we get these soft lockup
> errors.
>
> When looking at following code in kernel/softlockup.c is it possible for
> the touch time stamps get swapped over due to pre-emption and the wrong
>
I am investigating why on 1 particular machine we get these soft lockup
errors.
When looking at following code in kernel/softlockup.c is it possible for
the touch time stamps get swapped over due to pre-emption and the wrong
touch_timestamp is compared against wrong current time, there by causing
