linux-kernel - Re: 2.6.20-git15 BUG: soft lockup detected on CPU#0!

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <45DCF644.9040009@googlemail.com>
Date:	Thu, 22 Feb 2007 02:47:48 +0100
From:	Michal Piotrowski <michal.k.k.piotrowski@...il.com>
To:	tglx@...utronix.de
CC:	Michal Piotrowski <michal.k.k.piotrowski@...il.com>,
	LKML <linux-kernel@...r.kernel.org>, Ingo Molnar <mingo@...e.hu>
Subject: Re: 2.6.20-git15 BUG: soft lockup detected on CPU#0! - timers?

Thomas Gleixner napisał(a):
> Michal,
> 
> On Wed, 2007-02-21 at 16:38 +0100, Michal Piotrowski wrote:
>>> But you still have those softirq pending messages, right ?
>> Yes
>>
>> (+ new NOHZ: local_softirq_pending 02)
> 
> Yike, that's the timer softirq.
> 
> Can you add the patch below, maybe it gives us some useful info. Please
> enable lockdep (your last config had it already)
> 

I hope this helps.

irq event stamp: 103630856
hardirqs last  enabled at (103630855): [<c031356a>] _spin_unlock_irq+0x22/0x43
hardirqs last disabled at (103630856): [<c013a00e>] tick_nohz_stop_sched_tick+0x13/0x1fd
softirqs last  enabled at (103630824): [<c01265df>] __do_softirq+0xe4/0xea
softirqs last disabled at (103630819): [<c0106a75>] do_softirq+0x64/0xd1
NOHZ: local_softirq_pending 20, 00000001

(gdb) l *0xc031356a
0xc031356a is in _spin_unlock_irq (include2/asm/irqflags.h:48).
43              __asm__ __volatile__("cli" : : : "memory");
44      }
45
46      static inline void raw_local_irq_enable(void)
47      {
48              __asm__ __volatile__("sti" : : : "memory");
49      }
50
51      /*
52       * Used in the idle loop; sti takes one instruction cycle
(gdb) l *0xc013a00e
0xc013a00e is in tick_nohz_stop_sched_tick (/mnt/md0/devel/linux-git/kernel/time/tick-sched.c:158).
153             ktime_t last_update, expires, now, delta;
154             int cpu;
155
156             local_irq_save(flags);
157
158             cpu = smp_processor_id();
159             ts = &per_cpu(tick_cpu_sched, cpu);
160
161             if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
162                     goto end;
(gdb) l *0xc01265df
0xc01265df is in __do_softirq (/mnt/md0/devel/linux-git/kernel/softirq.c:251).
246
247             trace_softirq_exit();
248
249             account_system_vtime(current);
250             _local_bh_enable();
251     }
252
253     #ifndef __ARCH_HAS_DO_SOFTIRQ
254
255     asmlinkage void do_softirq(void)
(gdb) l *0xc0106a75
0xc0106a75 is in do_softirq (/mnt/md0/devel/linux-git/arch/i386/kernel/irq.c:222).
217                     irqctx->tinfo.previous_esp = current_stack_pointer;
218
219                     /* build the stack frame on the softirq stack */
220                     isp = (u32*) ((char*)irqctx + sizeof(*irqctx));
221
222                     asm volatile(
223                             "       xchgl   %%ebx,%%esp     \n"
224                             "       call    __do_softirq    \n"
225                             "       movl    %%ebx,%%esp     \n"
226                             : "=b"(isp)

http://www.stardust.webpages.pl/files/tbf/bitis-gabonica/2.6.21-rc1/git-config
http://www.stardust.webpages.pl/files/tbf/bitis-gabonica/2.6.21-rc1/git-dmesg

Regards,
Michal

-- 
Michal K. K. Piotrowski
LTG - Linux Testers Group (PL)
(http://www.stardust.webpages.pl/ltg/)
LTG - Linux Testers Group (EN)
(http://www.stardust.webpages.pl/linux_testers_group_en/)
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/