I am not yet familar with how Linux skb processing, but:
One thing I notice is that you do not verify the size of the GRE packets
before trying to grab the encapsulated one, so if the router sends you a
bad WCCP packet (no encapsulated packet) then oops a negative packet
size... Bbad WCCP packets has been seen from certain IOS versions in
certain path configurations.
and why is the module cleanup code removed?
/Henrik
Joe Cooper wrote:
> 
> Hi folks,
> 
> We've got WCCP v2 working with Squid, thanks to some fast coding by
> Kevin Wormington.
> 
> Would someone (hopefully with more Linux kernel hacking knowledge than
> I) take a look at this ip_wccp.c module:
> 
> http://www.swelltech.com/pengies/joe/patches/ip_wccp.c
> 
> It's only a couple of lines bigger than the original ip_wccp.c for v1 of
> WCCP, where it checks for the extra 4 octets of the v2 GRE header and
> then skips them for the decapsulation...but something is causing an oops
> on our test box.  We're not real sure exactly what is going on, but this
> seems as likely a candidate as any, since the box doesn't crash until it
> starts seeing WCCP traffic.  Unfortunately...because Kevin's router only
> has WCCP v2 and my router only has v1, we can't do any cross-testing.
> And the Squid in testing has not yet been made both v2 and v1 aware (it
> can currently do v2 just fine...but v1 is broken, I'll be fixing that
> over the next few days).
> 
> I'd welcome some comments from you guys, if you see anything problematic
> in the module...
>                                    --
>                       Joe Cooper <joe@swelltech.com>
>                   Affordable Web Caching Proxy Appliances
>                          http://www.swelltech.com
Received on Fri Mar 16 2001 - 23:48:49 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:13:38 MST