[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANn89iLiv0O9UeDDfhfQ=o3MY56BXhKN2piAJ9XztLTt_YK=5Q@mail.gmail.com>
Date: Tue, 20 Nov 2018 13:39:49 -0800
From: Eric Dumazet <edumazet@...gle.com>
To: dcaratti@...hat.com
Cc: Jamal Hadi Salim <jhs@...atatu.com>,
Cong Wang <xiyou.wangcong@...il.com>,
Jiri Pirko <jiri@...nulli.us>,
David Miller <davem@...emloft.net>,
netdev <netdev@...r.kernel.org>, ivecera@...hat.com
Subject: Re: [PATCH net v2] net/sched: act_police: fix race condition on state variables
On Tue, Nov 20, 2018 at 1:19 PM Davide Caratti <dcaratti@...hat.com> wrote:
>
> after 'police' configuration parameters were converted to use RCU instead
> of spinlock, the state variables used to compute the traffic rate (namely
> 'tcfp_toks', 'tcfp_ptoks' and 'tcfp_t_c') are erroneously read/updated in
> the traffic path without any protection.
>
> Use a dedicated spinlock to avoid race conditions on these variables, and
> ensure proper cache-line alignment. In this way, 'police' is still faster
> than what we observed when 'tcf_lock' was used in the traffic path _ i.e.
> reverting commit 2d550dbad83c ("net/sched: act_police: don't use spinlock
> in the data path"). Moreover, we preserve the throughput improvement that
> was obtained after 'police' started using per-cpu counters, when 'avrate'
> is used instead of 'rate'.
>
> Changes since v1 (thanks to Eric Dumazet):
> - call ktime_get_ns() before acquiring the lock in the traffic path
> - use a dedicated spinlock instead of tcf_lock
> - improve cache-line usage
>
> Fixes: 2d550dbad83c ("net/sched: act_police: don't use spinlock in the data path")
> Reported-and-suggested-by: Eric Dumazet <eric.dumazet@...il.com>
> Signed-off-by: Davide Caratti <dcaratti@...hat.com>
> ---
Thanks a lot for taking care of this.
Reviewed-by: Eric Dumazet <edumazet@...gle.com>
Powered by blists - more mailing lists