linux-kernel - Re: [GIT PULL] cputime patch for 2.6.30-rc6

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]

Date:	Tue, 19 May 2009 11:00:35 +0200
From:	Peter Zijlstra <peterz@...radead.org>
To:	Martin Schwidefsky <schwidefsky@...ibm.com>
Cc:	Linus Torvalds <torvalds@...ux-foundation.org>,
	linux-kernel <linux-kernel@...r.kernel.org>,
	Michael Abbott <michael@...neidae.co.uk>,
	Jan Engelhardt <jengelh@...ozas.de>
Subject: Re: [GIT PULL] cputime patch for 2.6.30-rc6

On Tue, 2009-05-19 at 10:49 +0200, Martin Schwidefsky wrote:

> Well, don't do stupid things like that. That falls into the same
> category as programs calling gettimeofday all the time.

Is gtod a global DoS? The worry I have about these cputime
for_each_cpu() loops in the proc code is that any odd unpriv user can
take the whole machine down (provided the machine is large enough).

Granted, this would only be a real problem for SGI and their insane
boxes atm, but it might very well be a problem for us in the near
future, given the rate Intel seems to increase cores.

So, I'm really not objecting too much to the patch at hand, but I'd love
to find a solution to this problem.

My personal favourite is to lower the resolution/accuracy of the answer
the bigger the box gets.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/