netdev - [PATCH net-next 0/2] tcp: final work on SYNFLOOD behavior

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-next>] [day] [month] [year] [list]

Message-Id: <1460610340-22163-1-git-send-email-edumazet@google.com>
Date:	Wed, 13 Apr 2016 22:05:38 -0700
From:	Eric Dumazet <edumazet@...gle.com>
To:	"David S . Miller" <davem@...emloft.net>
Cc:	netdev <netdev@...r.kernel.org>,
	Eric Dumazet <edumazet@...gle.com>,
	Eric Dumazet <eric.dumazet@...il.com>
Subject: [PATCH net-next 0/2] tcp: final work on SYNFLOOD behavior

In the first patch, I remove the costly association of SYNACK+COOKIES
to a listener. I believe other parts of the stack should be ready.

The second patch removes a useless write into listener socket
in tcp_rcv_state_process(), incurring false sharing in
tcp_conn_request()

Performance under SYNFLOOD goes from 3.2 Mpps to 6 Mpps.

Test was using a single TCP listener, on a host with 8 RX queues
on the NIC, and 24 cores (48 ht)

Eric Dumazet (2):
  tcp: do not mess with listener sk_wmem_alloc
  tcp: remove false sharing in tcp_rcv_state_process()

 include/net/tcp.h     |  9 +++++++--
 net/ipv4/tcp_input.c  | 11 ++++++-----
 net/ipv4/tcp_ipv4.c   |  4 ++--
 net/ipv4/tcp_output.c | 16 ++++++++++++----
 net/ipv6/tcp_ipv6.c   |  4 ++--
 5 files changed, 29 insertions(+), 15 deletions(-)

-- 
2.8.0.rc3.226.g39d4020