public inbox for netdev@vger.kernel.org
 help / color / mirror / Atom feed
From: Eric Dumazet <edumazet@google.com>
To: "David S . Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	 Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>,
	Neal Cardwell <ncardwell@google.com>,
	 Kuniyuki Iwashima <kuniyu@google.com>,
	David Ahern <dsahern@kernel.org>,
	netdev@vger.kernel.org,  eric.dumazet@gmail.com,
	Eric Dumazet <edumazet@google.com>
Subject: [PATCH net-next 0/7] ipv6: tcp: no longer rebuild fl6 at each transmit
Date: Fri,  6 Feb 2026 17:34:19 +0000	[thread overview]
Message-ID: <20260206173426.1638518-1-edumazet@google.com> (raw)

TCP v6 spends a good amount of time rebuilding a fresh fl6 at each
transmit in inet6_csk_xmit()/inet6_csk_route_socket().

TCP v4 caches the information in inet->cork.fl.u.ip4 instead.

This series changes TCP v6 to behave the same, saving cpu cycles
and reducing cache line misses and stack use.

Eric Dumazet (7):
  ipv6: add daddr/final storage in struct ipv6_pinfo
  ipv6: use np->final in inet6_sk_rebuild_header()
  ipv6: use inet->cork.fl.u.ip6 and np->final in
    ip6_datagram_dst_update()
  ipv6: inet6_csk_xmit() and inet6_csk_update_pmtu() use
    inet->cork.fl.u.ip6
  tcp: populate inet->cork.fl.u.ip6 in tcp_v6_connect()
  tcp: populate inet->cork.fl.u.ip6 in tcp_v6_syn_recv_sock()
  tcp: inet6_csk_xmit() optimization

 include/linux/ipv6.h                |  4 ++
 include/net/inet6_connection_sock.h |  4 +-
 net/ipv6/af_inet6.c                 |  4 +-
 net/ipv6/datagram.c                 | 21 +++++-----
 net/ipv6/inet6_connection_sock.c    | 57 +++++++++++++------------
 net/ipv6/tcp_ipv6.c                 | 64 ++++++++++++++---------------
 6 files changed, 82 insertions(+), 72 deletions(-)

-- 
2.53.0.rc2.204.g2597b5adb4-goog


             reply	other threads:[~2026-02-06 17:34 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-06 17:34 Eric Dumazet [this message]
2026-02-06 17:34 ` [PATCH net-next 1/7] ipv6: add daddr/final storage in struct ipv6_pinfo Eric Dumazet
2026-02-07 21:36   ` Kuniyuki Iwashima
2026-02-06 17:34 ` [PATCH net-next 2/7] ipv6: use np->final in inet6_sk_rebuild_header() Eric Dumazet
2026-02-07 21:37   ` Kuniyuki Iwashima
2026-02-06 17:34 ` [PATCH net-next 3/7] ipv6: use inet->cork.fl.u.ip6 and np->final in ip6_datagram_dst_update() Eric Dumazet
2026-02-07 21:38   ` Kuniyuki Iwashima
2026-02-06 17:34 ` [PATCH net-next 4/7] ipv6: inet6_csk_xmit() and inet6_csk_update_pmtu() use inet->cork.fl.u.ip6 Eric Dumazet
2026-02-07 21:40   ` Kuniyuki Iwashima
2026-02-06 17:34 ` [PATCH net-next 5/7] tcp: populate inet->cork.fl.u.ip6 in tcp_v6_connect() Eric Dumazet
2026-02-07 21:41   ` Kuniyuki Iwashima
2026-02-06 17:34 ` [PATCH net-next 6/7] tcp: populate inet->cork.fl.u.ip6 in tcp_v6_syn_recv_sock() Eric Dumazet
2026-02-07 21:49   ` Kuniyuki Iwashima
2026-02-06 17:34 ` [PATCH net-next 7/7] tcp: inet6_csk_xmit() optimization Eric Dumazet
2026-02-07 21:50   ` Kuniyuki Iwashima
2026-02-11  5:10 ` [PATCH net-next 0/7] ipv6: tcp: no longer rebuild fl6 at each transmit patchwork-bot+netdevbpf

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260206173426.1638518-1-edumazet@google.com \
    --to=edumazet@google.com \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=eric.dumazet@gmail.com \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=kuniyu@google.com \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox