[ofa-general] 2.6.30.1: possible irq lock inversion dependency detected

[Bart Van Assche]

It would be great if someone could have a look at this issue.

See also http://bugzilla.kernel.org/show_bug.cgi?id=13757

=========================================================
[ INFO: possible irq lock inversion dependency detected ]
2.6.30.1-scst-debug #5
---------------------------------------------------------
swapper/0 just changed the state of lock:
 (&priv->lock){-.-...}, at: [<ffffffffa0485c2f>]
ipoib_cm_rx_event_handler+0x4f/0xa0 [ib_ipoib]
but this lock took another, HARDIRQ-unsafe lock in the past:
 (&(&mad_agent_priv->timed_work)->timer){+.-...}

and interrupts could create inverse lock ordering between them.


other info that might help us debug this:
no locks held by swapper/0.

the first lock's dependencies:
-> (&priv->lock){-.-...} ops: 0 {
   IN-HARDIRQ-W at:
                        [<ffffffffffffffff>] 0xffffffffffffffff
   IN-SOFTIRQ-W at:
                        [<ffffffffffffffff>] 0xffffffffffffffff
   INITIAL USE at:
                       [<ffffffff80273661>] __lock_acquire+0x171/0x1b50
                       [<ffffffff80275148>] lock_acquire+0x108/0x150
                       [<ffffffff805142fc>] _spin_lock_irq+0x3c/0x50
                       [<ffffffffa048365e>]
ipoib_mcast_join_task+0x1fe/0x380 [ib_ipoib]
                       [<ffffffff8025c66d>] worker_thread+0x21d/0x390
                       [<ffffffff802612e6>] kthread+0x56/0x90
                       [<ffffffff8020cffa>] child_rip+0xa/0x20
                       [<ffffffffffffffff>] 0xffffffffffffffff
 }

[ ... ]