RE: ipoib lockdep warning

["Sean Hefty" <sean.hefty@intel.com>]

>Quoting r. Zach Brown <zach.brown@oracle.com>:
>> BC:
>>
>> query_idr.lock is taken with interrupts enabled and so is implicitly
>> ordered before dev->_xmit_lock which is taken in interrupt context.
>>
>> ipoib_mcast_join_task()
>>   ipoib_mcast_join()
>>     ib_sa_mcmember_rec_query()
>>       send_mad()
>>         idr_pre_get(&query_idr)
>>           spin_lock(&idp->lock)
>
>Got to check, but if that's true we have a simple deadlock here:
>ib_sa_mcmember_rec_query might get called from interrupt
>context as well, deadlocking on idp->lock?
>
>Sean?

As a side note, I believe that this is the upstream code and does not include
the latest multicast changes.

I'm not sure if anything calls into the sa_query interfaces from interrupt
context, but I doubt it.  From my brief look at the initially reported issue, I
can't determine if there's an actual problem without studying the ipoib code
more.

- Sean
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/