From: Josh Hunt <redacted>
Date: Wed, 28 Dec 2011 17:23:07 -0600

lock_stat shows taking the write lock is causing the slowdown. Using
this info I decided to write a version of fib6_clean_all() which
replaces write_lock_bh(&table->tb6_lock) with
read_lock_bh(&table->tb6_lock). With this new function I see the same
results as with my rtnetlink iperf test. I guess my question is what
am I missing? Is there a reason you need to take the write lock when
reading the route table to display to proc?

You're not missing anything, it's just an oversight or laziness. :-)

I've applied your patch thanks.

Longer term we should make the ipv6 tree traversals RCU safe just
like net/ipv4/fib_trie.c is.  Then we can do away with even the
read locks for read-only traversals.