linux-kernel - [rfc patch 0/2] Kill hotplug_lock()/hotplug

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: <1459860578.7776.0.camel@gmail.com>
Date:	Tue, 05 Apr 2016 14:49:38 +0200
From:	Mike Galbraith <umgwanakikbuti@...il.com>
To:	Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Cc:	Thomas Gleixner <tglx@...utronix.de>,
	linux-rt-users@...r.kernel.org, linux-kernel@...r.kernel.org,
	Steven Rostedt <rostedt@...dmis.org>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>
Subject: [rfc patch 0/2]  Kill hotplug_lock()/hotplug_unlock()

This is my stab at whacking $subject without adding any duct tape.  My
desktop box has run a thousand iterations of Steven's hotplug stress
script accompanied with stockfish, futextest, hackbench and tbench to
give hotplug lots of opportunity to prove this broken.  So far, it has
failed.  64 core DL980 is nowhere near as quick at iteration increment,
but has been happily chugging along all the while.

Patches are against 4.6-rc2-rt13.  Barring any frozen projectiles
lobbed by either humans or hotplug, I'll see what a backport to 4.4-rt
would look like.  This one has lots of minus signs.

patch1:
 kernel/cpu.c |  267 ++++++++++-------------------------------------------------
 1 file changed, 47 insertions(+), 220 deletions(-)
patch2:
 kernel/locking/rtmutex.c |   37 +++++++++++++++++--------------------
 1 file changed, 17 insertions(+), 20 deletions(-)