Tim, I have similar crash, but probably different cause-vector, posted on this list, fedora bugzilla, rt-users but no response so far from anyone. Did you find any work around? I tried looking at smp code for hints on problem it looks like in my case it could be trying to reschedule work on different CPU at time of crash. However, I admit that I could be way, way off on that cause. In my case, if I hammer my network interface with packets while another app is reading packets, my host locks up and clients are reporting dest unreachables. I don't think I have the problem in non-rt kernel. Have you tried booting without smp support? http://lkml.org/lkml/headers/2009/11/23/548 -Bob > -----Original Message----- > From: linux-kernel-owner@xxxxxxxxxxxxxxx [mailto:linux-kernel- > owner@xxxxxxxxxxxxxxx] On Behalf Of Tim Blechmann > Sent: Monday, October 05, 2009 5:06 AM > To: linux-kernel@xxxxxxxxxxxxxxx; linux-ext4@xxxxxxxxxxxxxxx > Subject: ext4: smp_processor_id() in preemptible > > hi all, > > using 2.6.31.1 with CONFIG_PREEMPT=y, i got the following call traces > from ext4 related code, when doing some io-heavy tasks: > > [30477.126201] INFO: task gconfd-2:2296 blocked for more than 120 > seconds. > [30477.126205] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" > disables this message. > [30477.126208] gconfd-2 D ffff8800280436e8 0 2296 1 > 0x00000000 > [30477.126214] BUG: using smp_processor_id() in preemptible [00000000] > code: khungtaskd/72 [30477.126221] caller is > show_stack_log_lvl+0x32/0x170 > [30477.126224] Pid: 72, comm: khungtaskd Tainted: P 2.6.31.1 > #29 > [30477.126227] Call Trace: > [30477.126234] [<ffffffff81266881>] debug_smp_processor_id+0xd1/0xf0 > [30477.126238] [<ffffffff81014b62>] show_stack_log_lvl+0x32/0x170 > [30477.126242] [<ffffffff814f57c0>] ? printk+0x3c/0x44 [30477.126246] > [<ffffffff81015e17>] show_stack+0x17/0x20 [30477.126251] > [<ffffffff81045b52>] sched_show_task+0x92/0x100 [30477.126256] > [<ffffffff810ab66d>] watchdog+0x1fd/0x240 [30477.126260] > [<ffffffff810ab470>] ? watchdog+0x0/0x240 [30477.126264] > [<ffffffff81071216>] kthread+0xa6/0xb0 [30477.126268] > [<ffffffff8101303a>] child_rip+0xa/0x20 [30477.126272] > [<ffffffff81071170>] ? kthread+0x0/0xb0 [30477.126275] > [<ffffffff81013030>] ? child_rip+0x0/0x20 [30477.126278] ��.n��������+%������w��{.n�����{�����ܨ}���Ơz�j:+v�����w����ޙ��&�)ߡ�a����z�ޗ���ݢj��w�f
