Messages in this thread | | | Date | Thu, 14 Feb 2013 15:45:10 +0100 | From | Ingo Molnar <> | Subject | Re: [-rc7 regression] Block IO/VFS/ext3/timer spinlock lockup? |
| |
* Thomas Gleixner <tglx@linutronix.de> wrote:
> On Wed, 13 Feb 2013, Linus Torvalds wrote: > > > On Wed, Feb 13, 2013 at 3:10 AM, Ingo Molnar <mingo@kernel.org> wrote: > > > > > > > > > Setting up Logical Volume Management: [ 13.140000] BUG: spinlock lockup suspected on CPU#1, lvm.static/139 > > > [ 13.140000] BUG: spinlock lockup suspected on CPU#1, lvm.static/139 > > > [ 13.140000] lock: 0x97fe9fc0, .magic: dead4ead, .owner: <none>/-1, .owner_cpu: -1 > > > [ 13.140000] Pid: 139, comm: lvm.static Not tainted 3.8.0-rc7 #216702 > > > [ 13.140000] Call Trace: > > > [ 13.140000] [<792b5e66>] spin_dump+0x73/0x7d > > > [ 13.140000] [<7916a347>] do_raw_spin_lock+0xb2/0xe8 > > > [ 13.140000] [<792b9412>] _raw_spin_lock_irqsave+0x35/0x3e > > > [ 13.140000] [<790391e8>] prepare_to_wait+0x18/0x57 > > > > The wait-queue spinlock? That sounds *very* unlikely to deadlock due > > to any bugs in block layer or filesystems. There are never any > > downcalls to those from within that spinlock or any other locks taken > > inside of it. > > The way more interesting information is: > > [ 13.140000] lock: 0x97fe9fc0, .magic: dead4ead, .owner: <none>/-1, .owner_cpu: -1 > > That lock is not contended, which makes no sense at all. The only > explanation for such a behaviour would be a tight spin_lock/unlock > loop on the other core which is exposed through the spinlock debugging > code (it uses trylocks instead of queueing in the ticket lock). > > Ingo, can you provide the backtrace of CPU0 please?
CPU0 appears to be idle:
[ 118.510000] Call Trace: [ 118.510000] [<7900844b>] cpu_idle+0x86/0xb4 [ 118.510000] [<792a91df>] rest_init+0x103/0x108 [ 118.510000] [<794558cc>] start_kernel+0x2c7/0x2cc [ 118.510000] [<7945528e>] i386_start_kernel+0x44/0x46
which suggests memory corruption - but, if then it's a special type of memory corruption because AFAIR I always saw similar patterns to the lockup, never other signs of memory corruption.
Thanks,
Ingo
| |