From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759667AbXGCTB7 (ORCPT ); Tue, 3 Jul 2007 15:01:59 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756789AbXGCTBw (ORCPT ); Tue, 3 Jul 2007 15:01:52 -0400 Received: from py-out-1112.google.com ([64.233.166.177]:60759 "EHLO py-out-1112.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756855AbXGCTBv convert rfc822-to-8bit (ORCPT ); Tue, 3 Jul 2007 15:01:51 -0400 DomainKey-Signature: a=rsa-sha1; c=nofws; d=gmail.com; s=beta; h=received:message-id:date:from:reply-to:to:subject:cc:mime-version:content-type:content-transfer-encoding:content-disposition; b=GqoOCxoSX/va0Mi+NDaKDrST0zV0f0xTlpzWLrfGGl7eEAOs4Vs37TXlDG48PNx6tcAd58N4gT2vwz0wwxoyU6X6KXHOBMcu3bSgVLXFXd/+kaHuIUoQwIpYDfwkCeIjdZP8uujVwyFtn6whazMT2uR+m1RGkLzza83Qyw8lc5M= Message-ID: <3efb10970707031201y7b7eefd3x60136770fcd167fa@mail.gmail.com> Date: Tue, 3 Jul 2007 21:01:50 +0200 From: "Remy Bohmer" Reply-To: linux@bohmer.net To: linux-arm-kernel@lists.arm.linux.org.uk, linux-kernel@vger.kernel.org Subject: Userland PI-futex does not work on ARM (2.6.21.5-rt18) Cc: andrew@sanpeople.com, "Ingo Molnar" , "Daniel Walker" MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 8BIT Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Hello All, I am using the 2.6.21.5-rt18 kernel on the ARM core Atmel at91rm9200 together with a Glibc 2.5+GCC4.2.0 toolchain, and I found out that the userland PI futexes (configured with PTHREAD_PRIO_INHERIT) do not work. What happens is: * Thread A claims the mutex, and gets the lock. * Thread B claims the mutex, and *also* gets the lock. (this is obviously already wrong) * Thread A wants to release the mutex and that fails because it does not own it... It looks like mutexes configured *without* PTHREAD_PRIO_INHERIT seem to work fine, but have not tested that thouroughly. Is this problem already known, or am I the first person running into it? Kind Regards, Remy Böhmer