From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752529Ab0EHIa5 (ORCPT ); Sat, 8 May 2010 04:30:57 -0400 Received: from ozlabs.org ([203.10.76.45]:60027 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752126Ab0EHIaz (ORCPT ); Sat, 8 May 2010 04:30:55 -0400 From: Rusty Russell To: Arnd Bergmann Subject: Re: cpumask: fix compat getaffinity Date: Sat, 8 May 2010 18:00:47 +0930 User-Agent: KMail/1.13.2 (Linux/2.6.32-21-generic; KDE/4.4.2; i686; ; ) Cc: linux-kernel@vger.kernel.org, stable@kernel.org, Andi Kleen , Ken Werner References: <201005071445.50147.arnd@arndb.de> In-Reply-To: <201005071445.50147.arnd@arndb.de> MIME-Version: 1.0 Content-Type: Text/Plain; charset="utf-8" Content-Transfer-Encoding: 7bit Message-Id: <201005081800.48240.rusty@rustcorp.com.au> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 7 May 2010 10:15:49 pm Arnd Bergmann wrote: > Commit a45185d2d "cpumask: convert kernel/compat.c" broke > libnuma, which abuses sched_getaffinity to find out NR_CPUS > in order to parse /sys/devices/system/node/node*/cpumap. > > On NUMA systems with less than 32 possibly CPUs, the > current compat_sys_sched_getaffinity now returns '4' > instead of the actual NR_CPUS/8, which makes libnuma > bail out when parsing the cpumap. Really? AFAICT the cpumap is printed using nr_cpu_ids too. Can you give an example of what cpumap is on this system? Confused, Rusty.