netdev - Re: [PATCH net] ipv6: prevent fib6_run

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Tue, 11 Jun 2013 12:07:18 +0200
From:	Michal Kubecek <mkubecek@...e.cz>
To:	David Miller <davem@...emloft.net>
Cc:	netdev@...r.kernel.org, kuznet@....inr.ac.ru, jmorris@...ei.org,
	yoshfuji@...ux-ipv6.org, kaber@...sh.net
Subject: Re: [PATCH net] ipv6: prevent fib6_run_gc() contention

On Mon, Jun 10, 2013 at 02:26:42PM -0700, David Miller wrote:
> From: Michal Kubecek <mkubecek@...e.cz>
> Date: Tue, 4 Jun 2013 13:08:59 +0200
> 
> > On a high-traffic router with many processors and many IPv6 dst
> > entries, soft lockup in fib6_run_gc() can occur when number of
> > entries reaches gc_thresh.
> > 
> > This happens because fib6_run_gc() uses fib6_gc_lock to allow
> > only one thread to run the garbage collector but ip6_dst_gc()
> > doesn't update net->ipv6.ip6_rt_last_gc until fib6_run_gc()
> > returns. On a system with many entries, this can take some time
> > so that in the meantime, other threads pass the tests in
> > ip6_dst_gc() (ip6_rt_last_gc is still not updated) and wait for
> > the lock. They then have to run the garbage collector one after
> > another which blocks them for quite long.
> > 
> > Resolve this by replacing special value ~0UL of expire parameter
> > to fib6_run_gc() by explicit "force" parameter to choose between
> > spin_lock_bh() and spin_trylock_bh() and call fib6_run_gc() with
> > force=false if gc_thresh is reached but not max_size.
> > 
> > Signed-off-by: Michal Kubecek <mkubecek@...e.cz>
> 
> It seems to me that it would be much simpler to simply update
> ip6_rt_last_gc first, that way the other threads would elide the GC
> call.

That was my original idea but I was afraid that while the remaining
window in ip6_dst_gc() would be very short and probably safe, we could
still run into problem if fib6_gc_lock was locked by some other caller
of fib6_run_gc() which doesn't update net->ipv6.ip6_rt_last_gc,
especially via a timer.

                                                        Michal Kubecek

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html