Re: list corruption in IPOIB

[Jack Wang <jinpu.wang-EIkl63zCoXaH+58JC4qpiA@public.gmane.org>]

On 2013年05月18日 21:37, Or Gerlitz wrote:
> On Fri, May 17, 2013 at 10:36 PM, Jack Wang <jinpu.wang@profitbricks.com> wrote:
>> We've seen below neigh->list list corruption warning during testing,
> 
> So about little heads up on what kernel you are using? what's the way
> to trigger this warning?
Hi Or,

I tried 3.4.23, and mainline kernel from Roland's rdma-for-linus, we
added bug injection interface,  run multithread iperf, and switched ib
mode between connected and datagram in sync on each side as Shlomo
suggested.
> 
>>  From Dongsu's and my opinion, several place also need
>> netif_tx_lock(_bh)/netif_tx_unlock(_bh) pairs around neigh->list , I
>> tried to add netif_tx_lock/netif_tx_unlock into ipoib_cm_destroy_tx, it
>> improved the situation, there're some other places in ipoib_main.c and
>> ipoib_mcast.c, but I don't know which lock should be added, if you can
>> take some time to look into it, that will be great.
> 
> 
> what do you mean by improved the situation? the waring is gone? and if
> yes, what's remain?
> 
I mean it take longer time to reproduce this warning.

Regards
Jack
> Or.
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html