Net work bug. More info.

We have been looking more closely at the failure.  Attached is a gdb log...  As turns out, the failure is actually one level lower than
tcp_v4_destroy_sock() in __kfree_skb().  It attempts to call a destructor which has a
bogus address.  The failing instruction is the call *(reg).

tcp_writequeue_purge(sk)-> tcp_free_skb(sk, skb)-> __kfree_skb()

The attached log has the sk and the "bad" skb as rendered by gdb.
-- 
George Anzinger   george@mvista.com
High-res-timers:  http://sourceforge.net/projects/high-res-timers/
Real time sched:  http://sourceforge.net/projects/rtsched/
Preemption patch: http://www.kernel.org/pub/linux/kernel/people/rml