ipv6 lock contention with parallel socket io

[Eric van Gyzen]

>> However, the assertion in in6_lltable_lookup() seems insufficient.  It
>> asserts any lock on afdata.  I think it should also assert a write-lock
>> in the LLE_CREATE case.
>>
>> Granted, this is not strictly related to your change.
>
> Would you mind doing up a quick patch to demonstrate?

Sure.

http://www.vangyzen.net/FreeBSD/patches/in6_lltable_lookup_wlock_assert.diff

This is not even compile-tested.

> I've heard mumblings at work that ipv6 panics if you change the
> routing tables during active traffic so if we're missing lock
> assertions I'd like to add them now and try to pick up the problem as
> it happens in testing.

Excellent idea.  Good luck, and thank you.

Eric