linux-kernel - [PATCH net-next 0/2 v2] netns: uevent performance tweaks

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: <20180424204335.12904-1-christian.brauner@ubuntu.com>
Date:   Tue, 24 Apr 2018 22:43:33 +0200
From:   Christian Brauner <christian.brauner@...ntu.com>
To:     ebiederm@...ssion.com, davem@...emloft.net, netdev@...r.kernel.org,
        linux-kernel@...r.kernel.org
Cc:     avagin@...tuozzo.com, ktkhai@...tuozzo.com, serge@...lyn.com,
        gregkh@...uxfoundation.org,
        Christian Brauner <christian.brauner@...ntu.com>
Subject: [PATCH net-next 0/2 v2] netns: uevent performance tweaks

Hey everyone,

This is v2 of "netns: uevent performance tweaks" which contains *no
functional changes* just a minor indendation fix as requested by David.

Like Eric requested, I did extensive testing that prove significant
performance improvements when using per-netns uevent sequence numbers
with decoupled locks. The results and test descriptions were added to
the commit message of
[PATCH 2/2 v1] netns: isolate seqnums to use per-netns locks.

This series deals with a bunch of performance improvements when sending
out uevents that have been extensively discussed here:
https://lkml.org/lkml/2018/4/10/592

- Only record uevent sockets from network namespaces owned by the
  initial user namespace in the global uevent socket list.
  Eric, this is the exact patch we agreed upon in
  https://lkml.org/lkml/2018/4/10/592.
  A very detailed rationale is present in the commit message for
  [PATCH 1/2] netns: restrict uevents
- Decouple the locking for network namespaces in the global uevent
  socket list from the locking for network namespaces not in the global
  uevent socket list.
  A very detailed rationale including performance test results is
  present in the commit message for
  [PATCH 2/2] netns: isolate seqnums to use per-netns locks

Thanks!
Christian

Christian Brauner (2):
  netns: restrict uevents
  netns: isolate seqnums to use per-netns locks

 include/linux/kobject.h     |   2 +
 include/net/net_namespace.h |   3 +
 kernel/ksysfs.c             |  11 +++-
 lib/kobject_uevent.c        | 122 ++++++++++++++++++++++++++++--------
 net/core/net_namespace.c    |  14 +++++
 5 files changed, 126 insertions(+), 26 deletions(-)

-- 
2.17.0