Re: Extensible hashing and RCU

[Evgeniy Polyakov <johnpol@2ka.mipt.ru>]

On Tue, Feb 20, 2007 at 05:08:12PM +0100, Eric Dumazet (dada1@cosmosbay.com) wrote:
> > Adding XOR with constant value does not change distribution.
> > Variable salt will end up with differnet buckets for the same flow.
> > It is forbidden - it is not the situation created for passwd/des decades
> > ago.
> 
> Adding a random hint to jhash (random value picked at boot time, not known by 
> attacker) permits to have a secure hash table : An attacker cannot build an 
> attack to fill one particular hash chain.
> 
> See net/ipv4/route.c (function rt_hash_code()) to see how its used for route 
> cache.

It is secrecy, not security - attacker will check the source and find
where constant per-boot value is added and recalculate attack vector -
we all were college students, it would be even more fun to crack.

In that regard Jenkins ahsh and XOR one have _exactly_ the same attack
vector, only Jenkins is a bit more sophisticated. I even think that
example in rt_hash_code() will endup with heavy problems when one of the
addresses is constant - my tests show problem exactly in the case of
jhash_2words() with random third parameter and constant one of the first
like in rt_hash_code().

-- 
	Evgeniy Polyakov