Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S965124Ab2EXVXw (ORCPT ); Thu, 24 May 2012 17:23:52 -0400 Received: from mail-qa0-f46.google.com ([209.85.216.46]:36219 "EHLO mail-qa0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964927Ab2EXVXu convert rfc822-to-8bit (ORCPT ); Thu, 24 May 2012 17:23:50 -0400 MIME-Version: 1.0 In-Reply-To: References: Date: Thu, 24 May 2012 14:23:49 -0700 X-Google-Sender-Auth: LxxAtu2mUZ2S6jmZFZJG9Txv4pA Message-ID: Subject: Re: [tip:sched/core] sched/numa: Rewrite the CONFIG_NUMA sched domain support From: Tony Luck To: mingo@kernel.org, a.p.zijlstra@chello.nl, torvalds@linux-foundation.org, cmetcalf@tilera.com, tony.luck@intel.com, sivanich@sgi.com, akpm@linux-foundation.org, ralf@linux-mips.org, greg.pearson@hp.com, ink@jurassic.park.msu.ru, tglx@linutronix.de, rth@twiddle.net, kamezawa.hiroyu@jp.fujitsu.com, paulus@samba.org, linux-kernel@vger.kernel.org, hpa@zytor.com, anton@samba.org, lethal@linux-sh.org, davem@davemloft.net, benh@kernel.crashing.org, dhowells@redhat.com, mattst88@gmail.com, fenghua.yu@intel.com Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2970 Lines: 56 On Wed, May 9, 2012 at 7:29 AM, tip-bot for Peter Zijlstra wrote: > Commit-ID: ?cb83b629bae0327cf9f44f096adc38d150ceb913 > Gitweb: ? ? http://git.kernel.org/tip/cb83b629bae0327cf9f44f096adc38d150ceb913 > Author: ? ? Peter Zijlstra > AuthorDate: Tue, 17 Apr 2012 15:49:36 +0200 > Committer: ?Ingo Molnar > CommitDate: Wed, 9 May 2012 15:00:55 +0200 > > sched/numa: Rewrite the CONFIG_NUMA sched domain support This is upstream in Linus' tree now - and seems to be the cause of an ia64 boot failure. The zonelist that arrives at __alloc_pages_nodemask is garbage. Changing both the kzalloc_node() calls in sched_init_numa() into plain kzalloc() calls seems to fix things. So it looks like we are trying to allocate on a node before the node has been fully set up. Call Trace: [] show_stack+0x80/0xa0 sp=e000000301b7f6f0 bsp=e000000301b71348 [] show_regs+0x640/0x920 sp=e000000301b7f8c0 bsp=e000000301b712f0 [] die+0x190/0x2c0 sp=e000000301b7f8d0 bsp=e000000301b712b0 [] ia64_do_page_fault+0x6b0/0xac0 sp=e000000301b7f8d0 bsp=e000000301b71258 [] ia64_native_leave_kernel+0x0/0x270 sp=e000000301b7f960 bsp=e000000301b71258 [] __alloc_pages_nodemask+0x140/0xce0 sp=e000000301b7fb30 bsp=e000000301b710f0 [] allocate_slab+0x130/0x3c0 sp=e000000301b7fb50 bsp=e000000301b71098 [] new_slab+0x40/0x680 sp=e000000301b7fb50 bsp=e000000301b71040 [] __slab_alloc+0x6e0/0x8e0 sp=e000000301b7fb50 bsp=e000000301b70fa8 [] kmem_cache_alloc_node+0xc0/0x3a0 sp=e000000301b7fb90 bsp=e000000301b70f70 [] sched_init_numa+0x360/0x780 sp=e000000301b7fb90 bsp=e000000301b70ed0 [] sched_init_smp+0x30/0x300 sp=e000000301b7fbb0 bsp=e000000301b70eb0 [] kernel_init+0x230/0x340 sp=e000000301b7fdb0 bsp=e000000301b70e88 [] kernel_thread_helper+0x30/0x60 sp=e000000301b7fe30 bsp=e000000301b70e60 [] start_kernel_thread+0x20/0x40 sp=e000000301b7fe30 bsp=e000000301b70e60 Disabling lock debugging due to kernel taint -Tony -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/