netdev - Re: [PATCH net] tcp_cubic: fix incorrect HyStart round start detection

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] [day] [month] [year] [list]

Message-ID: <CADVnQy=n8VvNONU74GqB9a8HbbPxGj-C3KO=nREEKrTf+p+hYg@mail.gmail.com>
Date: Tue, 14 Jan 2025 09:16:38 -0500
From: Neal Cardwell <ncardwell@...gle.com>
To: Mahdi Arghavani <ma.arghavani@...oo.com>
Cc: netdev@...r.kernel.org, edumazet@...gle.com, haibo.zhang@...go.ac.nz, 
	david.eyers@...go.ac.nz, abbas.arghavani@....se
Subject: Re: [PATCH net] tcp_cubic: fix incorrect HyStart round start detection

On Mon, Jan 13, 2025 at 11:31 PM Mahdi Arghavani <ma.arghavani@...oo.com> wrote:
>
> I noticed that HyStart incorrectly marks the start of rounds,
> resulting in inaccurate measurements of ACK train lengths.
> Since HyStart relies on ACK train lengths as one of two thresholds
> to terminate exponential cwnd growth during Slow-Start, this
> inaccuracy renders that threshold ineffective, potentially degrading
> TCP performance.
>
> The issue arises because the changes introduced in commit 4e1fddc98d25
> ("tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows")
> moved the caller of the `bictcp_hystart_reset` function inside the `hystart_update` function.
> This modification added an additional condition for triggering the caller,
> requiring that (tcp_snd_cwnd(tp) >= hystart_low_window) must also
> be satisfied before invoking `bictcp_hystart_reset`.
>
> This fix ensures that `bictcp_hystart_reset` is correctly called
> at the start of a new round, regardless of the congestion window size.
> This is achieved by moving the condition
> (tcp_snd_cwnd(tp) >= hystart_low_window)
> from before calling `bictcp_hystart_reset` to after it.
>
> Fixes: 4e1fddc98d25 ("tcp_cubic: fix spurious Hystart ACK train detections for not-cwnd-limited flows")
>
> Signed-off-by: Mahdi Arghavani <ma.arghavani@...oo.com>
> Cc: Neal Cardwell <ncardwell@...gle.com>
> Cc: Eric Dumazet <edumazet@...gle.com>
> Cc: Haibo Zhang <haibo.zhang@...go.ac.nz>
> Cc: David Eyers <david.eyers@...go.ac.nz>
> Cc: Abbas Arghavani <abbas.arghavani@....se>
> ---

Thanks for the patch!

To comply with Linux commit description policy, please remove the
empty line between the Fixes: footer and Signed-off-by footer, so
tools and readers can be sure to correctly parse all the footers.

Note that this page:

https://patchwork.kernel.org/project/netdevbpf/patch/20250114043131.2035-1-ma.arghavani@yahoo.com/

...highlights that issue in the "netdev/verify_fixesfailProblems with
Fixes tag: 1" row:

https://netdev.bots.linux.dev/static/nipa/925140/13938399/verify_fixes/summary

Commit: 08181a887689 ("tcp_cubic: fix incorrect HyStart round start detection")
Fixes tag: Fixes: 4e1fddc98d25 ("tcp_cubic: fix spurious Hystart ACK
train detections for not-cwnd-limited flows")
Has these problem(s):
- empty lines surround the Fixes tag

To help maintainers understand the relationship between your next post
of the patch, and the current one, can you please use the following to
apply a "v2" in your git format-patch command line:
  --subject-prefix='PATCH net v2'

Also, can you please either (a) respond in the other email thread on
this topic, attaching your updated packetdrill tests, or (b) post a
pull request on the packetdrill github repo at
https://github.com/google/packetdrill with your updated tests?

thanks,
neal


>  net/ipv4/tcp_cubic.c | 8 +++++---
>  1 file changed, 5 insertions(+), 3 deletions(-)
>
> diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
> index 5dbed91c6178..76c23675ae50 100644
> --- a/net/ipv4/tcp_cubic.c
> +++ b/net/ipv4/tcp_cubic.c
> @@ -392,6 +392,10 @@ static void hystart_update(struct sock *sk, u32 delay)
>         if (after(tp->snd_una, ca->end_seq))
>                 bictcp_hystart_reset(sk);
>
> +       /* hystart triggers when cwnd is larger than some threshold */
> +       if (tcp_snd_cwnd(tp) < hystart_low_window)
> +               return;
> +
>         if (hystart_detect & HYSTART_ACK_TRAIN) {
>                 u32 now = bictcp_clock_us(sk);
>
> @@ -467,9 +471,7 @@ __bpf_kfunc static void cubictcp_acked(struct sock *sk, const struct ack_sample
>         if (ca->delay_min == 0 || ca->delay_min > delay)
>                 ca->delay_min = delay;
>
> -       /* hystart triggers when cwnd is larger than some threshold */
> -       if (!ca->found && tcp_in_slow_start(tp) && hystart &&
> -           tcp_snd_cwnd(tp) >= hystart_low_window)
> +       if (!ca->found && tcp_in_slow_start(tp) && hystart)
>                 hystart_update(sk, delay);
>  }
>
> --
> 2.45.2
>