> On Fri, Nov 23, 2007 at 12:59:43PM -0600, Matt Mackall (
mpm@selenic.com) wrote:
> > So I'd be surprised if that was a problem. But I can imagine having
> > problems for skbs without destructors which run into one of these in
> > __kfree_skb:
> >
> > dst_release
> > secpath_put
> > nf_conntrack_put
> > nf_conntrack_put_reasm
> > nf_bridge_put
> >
> > ..some or all of which assume a softirq context.
>
> bridging is ok, others require softirq context.
> I've sent a patch (the last one should be ok) to guard against xfrm and
> connection tracking.
>
> > > No matter if we are under memory pressure or whatever - it is not
> > > allowed - a lot of skbs are supposed to be freed in softirq context,
> > > that is why dev_kfree_skb_any() exists.
> >
> > Some skbs we definitely -can- free in irq context. The only ones we
> > care about are the ones generated by netpoll. If there's a reason you
> > think netpoll's own skbs can't be freed, please describe it.
>
> Only some and to distinguish them we can not use destructor - if it is
> set (even empty function) it will fire an alarm.
