How to handle illegal multicast addresses in IPoIB?
Hi,
The problem in short: Illegal multicast addresses can be passed to ib_ipoib which will add them to the queue of multicast addresses it needs to join. From this point on ib_ipoib will get stuck in the attempt to join an illegal multicast group and without a giving a chance for other groups to try.
Recently 2 patches were sent to to deal with this problem. Both of them were rejectedm mainly from technical reasons.
Since I think that it is important to have the problem fixed I want to revive the discussion and resubmit one of them or both, according to the opinions here.
One patch (http://lists.openfabrics.org/pipermail/general/2009-August/061663.html) checks each multicast address for validity before it lets it get into the queue.
The other patch (http://lists.openfabrics.org/pipermail/general/2009-August/061693.html) queues all addresses it gets but adds fairness to the join attempts.
My questions is: Do we need both patches? If not, which one to choose?
I think that the first patch (check validity) is good enough.
thanks
MoniS
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): 4AB78040.9000606-hKgKHo2Ms0F+cjeuK/[email protected]
Quoted 2 lines · Moni Shoua
One patch (http://lists.openfabrics.org/pipermail/general/2009-August/061663.html) checks each multicast address for validity before it lets it get into the queue.
isn't it the below commit which appears in Linus tree?
Or.
Quoted 6 lines
commit
5e47596bee12597824a3b5b21e20f80b61e58a35Author: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org> Date: Sat Sep 5 20:23:40 2009 -0700IPoIB: Check multicast address format
Quoted 7 lines
Check that the format of multicast link addresses is correct before taking them from
dev->mc_listtopriv->multicast_list. This way we never try to send a bogus address to the SA, which prevents badness from erronous 'ip maddr addr add', broken bonding drivers, etc.Signed-off-by Roland Dreier <[email protected]>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): 4AB78EC9.7020805-hKgKHo2Ms0FWk0Htik3J/[email protected]
Quoted 9 lines · Or Gerlitz
Quoted 2 lines · Moni Shoua
One patch (http://lists.openfabrics.org/pipermail/general/2009-August/061663.html) checks each multicast address for validity before it lets it get into the queue.
isn't it the below commit which appears in Linus tree?
Or.
Quoted 2 lines
commit
5e47596bee12597824a3b5b21e20f80b61e58a35
Author: Jason Gunthorpe <jgunthorpe-ePGOBjL8dl3ta4EC/59zMFaTQe2KTcn/@public.gmane.org>
Yes, thanks you...
I must have missed it.
So there is only one question left. Do we also need the other patch?
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
A message that is not in the archive (sent off-list or not yet received): 4AB7900F.2020406-hKgKHo2Ms0F+cjeuK/[email protected]
Quoted 1 line · Moni Shoua
So there is only one question left. Do we also need the other patch?
Yes, we need something like the other patch to handle the case where the SM is unwilling to create a group for some reason. Right now that is exactly the same failure mode as an invalid MGID and wrecks ipoib if it happens.
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html