linux-kernel - [patch 0/3] [-rt] Fixes the timeout-bug in the rtmutex/PI-futex.

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <Pine.LNX.4.64.0607230215480.11861@localhost.localdomain>
Date:	Sun, 23 Jul 2006 02:18:11 +0100 (BST)
From:	Esben Nielsen <nielsen.esben@...glemail.com>
To:	Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...e.hu>,
	Steven Rostedt <rostedt@...dmis.org>,
	LKML <linux-kernel@...r.kernel.org>
Subject: [patch 0/3] [-rt] Fixes the timeout-bug in the rtmutex/PI-futex.

--
Hi,
  I finally got around to send in the a new version of my fixes to PI. The main 
purpose is to fix the timeout bug of the rtmutex/PI-futex. To refresh:

If you try to take a rtmutex or a PI-futex with a timeout on UP machine you
will not get the lock before the owner is done with it anyway. This is because
the owner is boosted to the same priority as your task. When your task gets
the timeout it will not get the CPU and the owner will not be de-boosted
before it releases the lock on it's own.

This series of patches fixes that bug and in general secures the PI code 
against similar problems, which might be there, due to the preemptive 
PI-walking. Furthermore, it makes setscheduler() do the PI-walking - or
rather make the target task do it.

Esben
-
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/