Re: TCP-MD5 checksum failure on x86_64 SMP

[Stephen Hemminger <shemminger@vyatta.com>]

On Fri, 07 May 2010 07:32:09 +0200
Eric Dumazet <eric.dumazet@gmail.com> wrote:

> Le jeudi 06 mai 2010 à 22:04 -0700, David Miller a écrit :
> > From: Eric Dumazet <eric.dumazet@gmail.com>
> 
> > > This code should be completely rewritten for linux-2.6.35, its very ugly
> > > and over complex, yet it is not scalable.
> > > 
> > > It could use true percpu data, with no central lock or refcount.
> > 
> > Yes I've always disliked the way the TCP MD5 pool stuff is coded, it's
> > frankly crap and this is like the 5th major bug that had to get fixed
> > in it. :-)
> > 
> > But let's fix this as simply as possible in net-2.6 and -stable, so Eric
> > let me know when you have a tested patch for me to apply.
> 
> There are so many things ...
> 
> I am comtemplating commit aa133076
> 
> __tcp_alloc_md5sig_pool() now do a : 
> 
> p = kzalloc(sizeof(*p), sk->sk_allocation);
> 
> But later call :
> 
> hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
> 
> (GFP_KERNEL allocations for sure)
> 
> 
> tcp_v4_parse_md5_keys() also use :
> 
> p = kzalloc(sizeof(*p), sk->sk_allocation);
> 
> right after a (possibly sleeping) copy_from_user()
> 
> Oh well...
> 
> 
> I'll test the already suggested patch before official submission,
> thanks.

Forget the per cpu data; the pool should just be scrapped.

The only reason the pool exists is that the crypto hash state which
should just be moved into the md5_info (88 bytes).  The pseudo
header can just be generated on the stack before passing to the crypto
code.