Re: RCU lockup in the SMP idle thread, help...

[Paul E. McKenney]

On Thu, Sep 20, 2012 at 11:07:37AM +0200, Linus Walleij wrote:
> On Thu, Sep 20, 2012 at 2:03 AM, Paul E. McKenney
> <paulmck@xxxxxxxxxxxxxxxxxx> wrote:
> 
> > In the meantime, a crude fallback is for the CPU that detected the stall
> > to trace the stack of the task running on the other CPU.  See below for
> > a crude (and untested) patch.
> 
> OK now I get this:
> 
>  INFO: rcu_preempt detected stalls on CPUs/tasks: { 0} (detected by 1,
> t=29508 jiffies)
> Task dump for CPU 0:
> swapper/0       R running      0     0      0 0x00000000
> [<c02da614>] (__schedule+0x238/0x52c) from [<c000f238>] (default_idle+0x28/0x30)
> [<c000f238>] (default_idle+0x28/0x30) from [<ffffffff>] (0xffffffff)
> INFO: rcu_preempt detected stalls on CPUs/tasks: { 0} (detected by 1,
> t=29851 jiffies)
> Task dump for CPU 0:
> swapper/0       R running      0     0      0 0x00000000
> [<c02da614>] (__schedule+0x238/0x52c) from [<c000f238>] (default_idle+0x28/0x30)
> [<c000f238>] (default_idle+0x28/0x30) from [<ffffffff>] (0xffffffff)
> 
> So the swapper thread is the culprit?
> Hm, I'm not very smart with this no...

Can we convince ARM to dump the stack of the swapper thread in this case?
That would get us valuable information.

							Thanx, Paul

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/