[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210919092002.GG15906@breakpoint.cc>
Date: Sun, 19 Sep 2021 11:20:02 +0200
From: Florian Westphal <fw@...len.de>
To: Eric Dumazet <eric.dumazet@...il.com>
Cc: Pablo Neira Ayuso <pablo@...filter.org>,
Jozsef Kadlecsik <kadlec@...ckhole.kfki.hu>,
Florian Westphal <fw@...len.de>,
netfilter-devel@...r.kernel.org, netdev <netdev@...r.kernel.org>,
Eric Dumazet <edumazet@...gle.com>,
syzbot <syzkaller@...glegroups.com>
Subject: Re: [PATCH nf] netfilter: conntrack: serialize hash resizes and
cleanups
Eric Dumazet <eric.dumazet@...il.com> wrote:
> From: Eric Dumazet <edumazet@...gle.com>
>
> Syzbot was able to trigger the following warning [1]
>
> No repro found by syzbot yet but I was able to trigger similar issue
> by having 2 scripts running in parallel, changing conntrack hash sizes,
> and:
>
> for j in `seq 1 1000` ; do unshare -n /bin/true >/dev/null ; done
>
> It would take more than 5 minutes for net_namespace structures
> to be cleaned up.
>
> This is because nf_ct_iterate_cleanup() has to restart everytime
> a resize happened.
>
> By adding a mutex, we can serialize hash resizes and cleanups
> and also make get_next_corpse() faster by skipping over empty
> buckets.
>
> Even without resizes in the picture, this patch considerably
> speeds up network namespace dismantles.
LGTM, thanks Eric.
I have been working on patches to make hash table pernet again,
but they will take a bit more time to finish and are not suited for -net.
Powered by blists - more mailing lists