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]
Message-ID: <CANn89iJsZ4z50KWh22wZyRHUj9rF3ef4HbMvmKez2xHLT=UT2g@mail.gmail.com>
Date: Mon, 17 Mar 2025 09:19:03 +0100
From: Eric Dumazet <edumazet@...gle.com>
To: Jason Xing <kerneljasonxing@...il.com>
Cc: davem@...emloft.net, kuba@...nel.org, pabeni@...hat.com, 
	dsahern@...nel.org, horms@...nel.org, kuniyu@...zon.com, ncardwell@...gle.com, 
	netdev@...r.kernel.org
Subject: Re: [PATCH net-next v3 1/2] tcp: support TCP_RTO_MIN_US for
 set/getsockopt use

On Sun, Mar 16, 2025 at 3:27 AM Jason Xing <kerneljasonxing@...il.com> wrote:
>
> Support adjusting RTO MIN for socket level by using setsockopt().


This changelog is small :/

You should clearly state that this option has no effect if the route
has a RTAX_RTO_MIN attribute set.

Also document what is the default socket value after a socket() system
call and/or accept() in the changelog.

>
> Signed-off-by: Jason Xing <kerneljasonxing@...il.com>
> ---
>  Documentation/networking/ip-sysctl.rst |  4 ++--
>  include/net/tcp.h                      |  2 +-
>  include/uapi/linux/tcp.h               |  1 +
>  net/ipv4/tcp.c                         | 16 +++++++++++++++-
>  4 files changed, 19 insertions(+), 4 deletions(-)
>
> diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
> index 054561f8dcae..5c63ab928b97 100644
> --- a/Documentation/networking/ip-sysctl.rst
> +++ b/Documentation/networking/ip-sysctl.rst
> @@ -1229,8 +1229,8 @@ tcp_pingpong_thresh - INTEGER
>  tcp_rto_min_us - INTEGER
>         Minimal TCP retransmission timeout (in microseconds). Note that the
>         rto_min route option has the highest precedence for configuring this
> -       setting, followed by the TCP_BPF_RTO_MIN socket option, followed by
> -       this tcp_rto_min_us sysctl.
> +       setting, followed by the TCP_BPF_RTO_MIN and TCP_RTO_MIN_US socket
> +       options, followed by this tcp_rto_min_us sysctl.
>
>         The recommended practice is to use a value less or equal to 200000
>         microseconds.
> diff --git a/include/net/tcp.h b/include/net/tcp.h
> index 7207c52b1fc9..6a7aab854b86 100644
> --- a/include/net/tcp.h
> +++ b/include/net/tcp.h
> @@ -806,7 +806,7 @@ u32 tcp_delack_max(const struct sock *sk);
>  static inline u32 tcp_rto_min(const struct sock *sk)
>  {
>         const struct dst_entry *dst = __sk_dst_get(sk);
> -       u32 rto_min = inet_csk(sk)->icsk_rto_min;
> +       u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min);
>
>         if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
>                 rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
> diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
> index 32a27b4a5020..b2476cf7058e 100644
> --- a/include/uapi/linux/tcp.h
> +++ b/include/uapi/linux/tcp.h
> @@ -137,6 +137,7 @@ enum {
>
>  #define TCP_IS_MPTCP           43      /* Is MPTCP being used? */
>  #define TCP_RTO_MAX_MS         44      /* max rto time in ms */
> +#define TCP_RTO_MIN_US         45      /* min rto time in us */
>
>  #define TCP_REPAIR_ON          1
>  #define TCP_REPAIR_OFF         0
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 46951e749308..f2249d712fcc 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -3352,7 +3352,7 @@ int tcp_disconnect(struct sock *sk, int flags)
>         icsk->icsk_probes_out = 0;
>         icsk->icsk_probes_tstamp = 0;
>         icsk->icsk_rto = TCP_TIMEOUT_INIT;
> -       icsk->icsk_rto_min = TCP_RTO_MIN;
> +       WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
>         icsk->icsk_delack_max = TCP_DELACK_MAX;
>         tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
>         tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
> @@ -3833,6 +3833,14 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
>                         return -EINVAL;
>                 WRITE_ONCE(inet_csk(sk)->icsk_rto_max, msecs_to_jiffies(val));
>                 return 0;
> +       case TCP_RTO_MIN_US: {
> +               int rto_min = usecs_to_jiffies(val);

> +
> +               if (rto_min > TCP_RTO_MIN || rto_min < TCP_TIMEOUT_MIN)
> +                       return -EINVAL;
> +               WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min);
> +               return 0;
> +       }
>         }
>
>         sockopt_lock_sock(sk);
> @@ -4672,6 +4680,12 @@ int do_tcp_getsockopt(struct sock *sk, int level,
>         case TCP_RTO_MAX_MS:
>                 val = jiffies_to_msecs(tcp_rto_max(sk));
>                 break;
> +       case TCP_RTO_MIN_US: {
> +               int rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min);
> +
> +               val = jiffies_to_usecs(rto_min);

Reuse val directly, no need for a temporary variable, there is no
fancy computation on it.

                   val =
jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min));
                   break;

> +               break;
> +       }
>         default:
>                 return -ENOPROTOOPT;
>         }
> --
> 2.43.5
>

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ