On Wed, Apr 26, 2017 at 09:27:38AM -0400, Doug Ledford wrote:
> On Wed, 2017-04-26 at 20:52 +0800, Honggang LI wrote:
> > On Wed, Apr 26, 2017 at 09:46:34AM +0200, Paolo Abeni wrote:
> > >
> > > On Wed, 2017-04-26 at 00:50 +0300, Or Gerlitz wrote:
> > > >
> > > > so maybe @ least for the time being, we should be picking Hong's
> > > > patch
> > > > with proper change log and without the giant stack dump till we
> > > > have
> > > > something better. If you agree, can you do the re-write of the
> > > > change
> > > > log?
> > >
> > > I think that Hong's patch is following the correct way to fix the
> > > issue: ipoib_hard_header() can't assume that the skb headroom is at
> > > least IPOIB_HARD_LEN bytes, as wrongly implied by commit
> > > fc791b633515
> > > (my fault, I'm sorry).
> > >
> > > Perhaps we can make the code a little more robust with something
> > > alongside the following (only compile tested):
> > > ---
> > > diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c
> > > b/drivers/infiniband/ulp/ipoib/ipoib_main.c
> > > index d1d3fb7..d53d2e1 100644
> > > --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
> > > +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
> > > @@ -1160,6 +1160,11 @@ static int ipoib_hard_header(struct sk_buff
> > > *skb,
> > > const void *daddr, const void *saddr,
> > > unsigned len)
> > > {
> > > struct ipoib_header *header;
> > > + int ret;
> > > +
> > > + ret = skb_cow_head(skb, IPOIB_HARD_LEN);
> >
> > I don't think so. When this skb_under_panic arise, all slaves had
> > been
> > removed from a busy bonding interface,
>
> I'm not sure this entirely makes sense. If all slaves had been
> removed, then we should never end up in ipoib_hard_header. That should
> only be called as long as there is at least one slave still attached to
> the bond. It might be during the process of removing the final slave,
Yes, it is during the process of removing the final slave. The
reproducer looks like this:
ping remote_ip_over_bonding_interface &
while 1; do
ifdown bond0
ifup bond0
done
> but I don't think it can be after the final slave has been fully
> removed from the bond. Paolo, what should the bond driver be doing
> once the slaves are gone? Wouldn't it just be dropping every skb on
> the floor without calling anyone's hard header routine?
>
> > so it is better to immediately
> > give up and return error.
> >
> > >
> > > + if (ret)
> > > + return ret;
> > >
> > > header = (struct ipoib_header *) skb_push(skb, sizeof
> > > *header);
> > > ---
> > >
> > > Paolo
> > > --
> > > To unsubscribe from this list: send the line "unsubscribe linux-
> > > rdma" in
> > > the body of a message to majordomo@xxxxxxxxxxxxxxx
> > > More majordomo info at http://vger.kernel.org/majordomo-info.html
> --
> Doug Ledford <dledford@xxxxxxxxxx>
> GPG KeyID: B826A3330E572FDD
>
> Key fingerprint = AE6B 1BDA 122B 23B4 265B 1274 B826 A333 0E57 2FDD
>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
