On Montag, 13. März 2017 20:51:11 CET Jiri Slaby wrote: > From: Linus Lüssing <linus.luessing@xxxxxxxxx> > > This patch has been added to the 3.12 stable tree. If you have any > objections, please let us know. > > =============== > > commit 9799c50372b23ed774791bdb87d700f1286ee8a9 upstream. > > As long as there is still a reference for a hard interface held, there might > still be a forwarding packet relying on its attributes. > > Therefore avoid setting hard_iface->soft_iface to NULL when disabling a hard > interface. > [....] > > What happened here is, that there was still a forw_packet (here: a BATMAN IV > OGM) in the queue of eth3 with the forw_packet->if_incoming set to eth1 and the > forw_packet->if_outgoing set to eth3. > > When eth3 is to be deactivated and removed, then this thread waits for the > forw_packet queued on eth3 to finish. Because eth1 was deactivated and removed > earlier and by that had forw_packet->if_incoming->soft_iface, set to NULL, the > splat when trying to send/flush the OGM on eth3 occures. Please drop this one. See following references for more details * https://patchwork.ozlabs.org/patch/696822/ * https://www.open-mesh.org/issues/307 * https://lkml.org/lkml/2016/11/17/245 * https://www.mail-archive.com/linux-kernel@xxxxxxxxxxxxxxx/msg1334742.html Kind regards, Sven
Attachment:
signature.asc
Description: This is a digitally signed message part.