3.5.0-rc5: BUG: soft lockup - CPU#0 stuck for 22s

[Paul E. McKenney]

On Sun, Jul 01, 2012 at 11:30:40PM -0700, Christian Kujau wrote:
> On Mon, 2 Jul 2012 at 14:50, Benjamin Herrenschmidt wrote:
> > Interesting... I observed something roughly similar on a dual G4
> > the other day associated with a 30s to 1mn pause during boot. RCU
> > was complaining loudly.
> > 
> > In my case, it did continue booting normally, is that the case for you ?
> 
> No, in my case it stopped booting, though there was no "panic" message.
> 
> > Also if I compile the kernel without CONFIG_SMP, it did go away as well,
> > do you observe that too ?
> 
> This PoweBook G4 is UP anyway and I'm always building w/o CONFIG_SMP.
> 
> > I don't have a spare cycle to investigate this problem this week I'm
> > afraid, it might help if you could try a bisection though.
> 
> Yes, I've started a bisection already and will report back.
> 
> FYI, I've put a netconsole-log below from another boot (in the 
> middle of a bisection), the instruction dump is slightly more complete.

Li Zhong posted a patch to fix this (async_synchronize_full() below):

	https://lkml.org/lkml/2012/7/2/32

This gets rid of this problem on my UP testing.  If it works for you,
please give Li Zhong a Tested-by.

							Thanx, Paul

> Thanks!
> Christian.
> 
> [   40.345973] BUG: soft lockup - CPU#0 stuck for 22s! [modprobe:691]
> [   40.347737] Modules linked in: sd_mod arc4 firewire_sbp2 scsi_mod b43 mac80211 cfg80211
> [   40.349443] irq event stamp: 65779272
> [   40.351156] hardirqs last  enabled at (65779271): [<c052fae8>] _raw_spin_unlock_irqrestore+0x40/0x9c
> [   40.352911] hardirqs last disabled at (65779272): [<c0011648>] reenable_mmu+0x40/0x98
> [   40.354649] softirqs last  enabled at (65769864): [<c000f3c0>] call_do_softirq+0x14/0x24
> [   40.356386] softirqs last disabled at (65769857): [<c000f3c0>] call_do_softirq+0x14/0x24
> [   40.358098] NIP: c005ee64 LR: c005ee54 CTR: c009c578
> [   40.359788] REGS: eece3d70 TRAP: 0901   Not tainted  (3.4.0-05609-gc80ddb5)
> [   40.361517] MSR: 00009032 <EE,ME,IR,DR,RI>  CR: 24042482  XER: 00000000
> [   40.363261] TASK = eec30b80[691] 'modprobe' THREAD: eece2000#012
> [   40.363261] GPR00: c005ee54 eece3e20 eec30b80 00000000 00000002 c005edd0 00000000 00000000 #012
> [   40.363261] GPR08: 00000000 eece2000 00000000 00000001 24042488 
> [   40.368310] NIP [c005ee64] async_synchronize_cookie_domain+0x70/0x1f4
> [   40.369978] LR [c005ee54] async_synchronize_cookie_domain+0x60/0x1f4
> [   40.371614] Call Trace:
> [   40.373226] [eece3e20] [c005ee54] async_synchronize_cookie_domain+0x60/0x1f4 (unreliable)
> [   40.374884] [eece3e70] [c005f034] async_synchronize_full+0x3c/0x74
> [   40.376524] [eece3e90] [c0082790] sys_init_module+0x178/0x1164
> [   40.378151] [eece3f40] [c00117a8] ret_from_syscall+0x0/0x38
> [   40.379783] --- Exception: c01 at 0xff5d694#012[   40.379783]     LR = 0x100041c0
> [   40.382928] Instruction dump:
> [   40.384489] 93a10044 419e0014 3d20c06f 8009d020 2f800000 419e017c 7fc3f378 4bfffed9 
> [   40.386081] 7f9f1840 419d0060 7f9f1800 419e0050 <881bf008> 2f800000 419e0014 3d20c06f
> 
> 
> -- 
> BOFH excuse #241:
> 
> _Rosin_ core solder? But...
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo at vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/
>