Re: console_cpu_notify can cause scheduling BUG during CPU hotplug
From: canquan.shen
Date: Mon Sep 05 2011 - 04:35:37 EST
Hi mbohan and petkovbb,
The dead lock scenario is the following:
In my test enviroment. It has two cpus. cpu#0 just complete to run
the following stack(in top tool).
#0 [ffff880079223b68] schedule at ffffffff813acda2
#1 [ffff880079223cb0] __cond_resched at ffffffff8104a3f5
#2 [ffff880079223cd0] _cond_resched at ffffffff813ad56d
#3 [ffff880079223ce0] console_conditional_schedule at ffffffff813ad5cd
#4 [ffff880079223cf0] do_con_write at ffffffff8127ed24
#5 [ffff880079223de0] con_write at ffffffff81281109
#6 [ffff880079223e00] n_tty_write at ffffffff8126bd40
#7 [ffff880079223ea0] tty_write at ffffffff81268530
#8 [ffff880079223f10] vfs_write at ffffffff811124db
#9 [ffff880079223f40] sys_write at ffffffff81112680
#10 [ffff880079223f80] system_call_fastpath at ffffffff813b5812
It has locked the console_sem in console_lock function(do_con_write
call the console_lock). and it does not unlock the console_sem because
it run sheduler function (because it check need_schedule flag) before unlock
And then cpu remove has happened. all cpu execute the
stop_machine_cpu_stop in cpu_stopper_thread. In the
stop_machine_cpu_stop function. cpu#0 is warting cpu#1 run compelte, but
cpu#1 has schedule because it wait for console_sem lock. please see the
following stack.
#0 [ffff88007afd3ae0] schedule at ffffffff813acda2
#1 [ffff88007afd3c28] schedule_timeout at ffffffff813ad785
#2 [ffff88007afd3cc8] __down at ffffffff813ae621
#3 [ffff88007afd3d18] down at ffffffff81072587
#4 [ffff88007afd3d38] console_lock at ffffffff81051977
#5 [ffff88007afd3d48] console_cpu_notify at ffffffff813a7650
#6 [ffff88007afd3d58] notifier_call_chain at ffffffff813b2cdf
#7 [ffff88007afd3d98] __raw_notifier_call_chain at ffffffff810726d9
#8 [ffff88007afd3da8] take_cpu_down at ffffffff81395a75
#9 [ffff88007afd3dc8] stop_machine_cpu_stop at ffffffff8109df7e
#10 [ffff88007afd3df8] cpu_stopper_thread at ffffffff8109de1d
#11 [ffff88007afd3ee8] kthread at ffffffff8106cff6
#12 [ffff88007afd3f48] kernel_thread_helper at ffffffff813b6944
However the console_sem lock is wait for cpu#0 to unlock. it cause
dead lock.
--
canquan.shen
On 2011/8/30 16:37, Shen Canquan wrote:
Hi Mike ,
I found the previous email about "console_cpu_notify can cause scheduling BUG during CPU hotplug" .
Now I have the same problem . My test enviroment is the following:
I am in xen virtualization environment. and I install the lastest stable kernel(linux 3.0.3) in domU . When I use the
xm vcpu-set<n> to test vcpu add and remove function . and when I run the above command more than 100 times.
and use the top tool to look the cpu info. It will hang of linux.
When I dump the core of linux kernel and analyse it , I found the reason is the same of this email.
Can you tell me the progress of this problem. Thanks.
---------
On 4/30/2011 1:38 AM, Borislav Petkov wrote:
On Wed, Apr 27, 2011 at 03:12:19PM -0700, Michael Bohan wrote:
On 4/27/2011 12:38 AM, Borislav Petkov wrote:
Great, whatever you guys come up with, we'd like to give it a run too.
We (AMD) hit the same issue in one of our tests but in our case we end
up in an endless loop of the state machine at stop_machine_cpu_stop()
since the core being offlined cannot ack the state transition to
STOPMACHINE_EXIT due to a similar reason.
One possible fix is dropping CPU_DYING from console_cpu_notify()
since it is called into by the offlining path in
kernel/cpu.c::take_cpu_down().
This seems to be a different problem. Could you elaborate about why
removing CPU_DYING from console_cpu_notify resolves your problem?
Ok, I have to admit, I haven't spent a whole lot of time debugging this
but here's what I know:
First of all, how we trigger this? Our crazy testers have a script that
takes cores off- and online in a random manner repeatedly and, if you go
to another tty and do 'dmesg' in the same time, you can be absolutely
sure that after a few times, you end up in the endless loop scenario
above.
Our test scenario is similar to this. In the crash I reported, there
needs to be contention for the console semaphore to trigger the BUG().
I get the impression that this sort of scenario is not tested
extensively in Linux. Otherwise I think others would have reported the
BUG I hit.
Wait... I'm looking at the code now and it looks like Tejun changed the
state machine implementation (3fc1f1e27a5b807791d72e5d992aa33b668a6626)
so we'll have to retest to see whether this still happens.
Tejen's change (3fc1f1e27a5b807791d72e5d992aa33b668a6626) was first in
v2.6.35, so it looks like you're using a pretty old kernel. Kevin's
change (034260d6779087431a8b2f67589c68b919299e5c) was not in until
v2.6.36, so therefore I'm a bit confused what code base you're running.
You mentioned before that one possible fix is dropping CPU_DYING from
console_cpu_notify, but based on what you said, it doesn't seem like
your kernel should be new enough have this functionality. Did you
cherry-pick Kevin's change on top of an older code base? If so, that is
likely dangerous.
Please keep me in loop with your findings on a more recent kernel.
Can you trigger your crash with latest kernel too?
The latest I've tested is v2.6.38, but the code related to blocking on
the console semaphore with preemption disabled does not appear changed
on the most recent code base.
Thanks,
Mike
--
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/
.
--
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/