Re: linux-next: spinlock lockup with next-20081118 on powerpc

[Jens Axboe <jens.axboe@oracle.com>]

On Wed, Nov 19 2008, Stephen Rothwell wrote:
> Hi Jens,
> 
> On Wed, 19 Nov 2008 10:16:28 +0100 Jens Axboe <jens.axboe@oracle.com> wrote:
> >
> > Strange, so it gets stuck on the timer lock, very weird. You don't
> > happen to have output showing that the other CPU is up to at that point?
> 
> Unfortunately, no, but I will see what I can find tomorrow.
> 
> Today's linux-next still has a problem, but it is slightly different:
> 
> Unable to handle kernel paging request for data at address 0x00000000
> Faulting instruction address: 0xc000000000503030
> cpu 0x0: Vector: 300 (Data Access) at [c00000000ffffa40]
>     pc: c000000000503030: ._spin_lock_irqsave+0x40/0x110
>     lr: c0000000002571f8: .blk_rq_timed_out_timer+0x48/0x190
>     sp: c00000000ffffcc0
>    msr: 8000000000009032
>    dar: 0
>  dsisr: 40000000
>   current = 0xc000000022d31040
>   paca    = 0xc000000000897300
>     pid   = 3399, comm = ckbcomp
> enter ? for help
> [c00000000ffffd50] c0000000002571f8 .blk_rq_timed_out_timer+0x48/0x190
> [c00000000ffffe00] c00000000006c2f4 .run_timer_softirq+0x1c4/0x2a0
> [c00000000ffffed0] c000000000065298 .__do_softirq+0xe8/0x1f0
> [c00000000fffff90] c000000000029224 .call_do_softirq+0x14/0x24
> [c000000022ad3c80] c00000000000d420 .do_softirq+0xf0/0x140
> [c000000022ad3d20] c0000000000654a4 .irq_exit+0x74/0x90
> [c000000022ad3da0] c000000000025844 .timer_interrupt+0x134/0x150
> [c000000022ad3e30] c000000000003700 decrementer_common+0x100/0x180
> --- Exception: 901 (Decrementer) at 000000000ff52440

That's even more weird, how could 'data' passed in to the timer ever be
0? It's setup like this:

        setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q);

when we allocate the queue. How did this trigger?

-- 
Jens Axboe