From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755734AbaIIHGj (ORCPT ); Tue, 9 Sep 2014 03:06:39 -0400 Received: from mail-lb0-f179.google.com ([209.85.217.179]:48721 "EHLO mail-lb0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751747AbaIIHGi (ORCPT ); Tue, 9 Sep 2014 03:06:38 -0400 Message-ID: <1410246392.5088.18.camel@marge.simpson.net> Subject: Re: [PATCH RESEND v4] sched: fix llc shared map unreleased during cpu hotplug From: Mike Galbraith To: Wanpeng Li Cc: linux-kernel@vger.kernel.org, hpa@zytor.com, Ingo Molnar , Peter Zijlstra , x86@kernel.org, Borislav Petkov , Yasuaki Ishimatsu , David Rientjes , Prarit Bhargava , Steven Rostedt , Jan Kiszka , Toshi Kani , Zhang Yang Date: Tue, 09 Sep 2014 09:06:32 +0200 In-Reply-To: <1408945776-92404-1-git-send-email-wanpeng.li@linux.intel.com> References: <1408945776-92404-1-git-send-email-wanpeng.li@linux.intel.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.2.3 Content-Transfer-Encoding: 7bit Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hm, this patchlet seems to be having trouble taking wing. (tosses it up in the air.. flap yer little wings patchlet) I thought you had changed the title to.. x86,cpu-hotplug: clear llc_shared_mask at CPU hotplug ..due to Peter saying sched is only a consumer, but v4 somehow reverted back to being a sched patch. On Mon, 2014-08-25 at 13:49 +0800, Wanpeng Li wrote: > [ 220.262245] Call Trace: > [ 220.262252] [] load_balance+0x156/0x980 > [ 220.262259] [] ? _raw_spin_unlock_irqrestore+0x2e/0xa0 > [ 220.262266] [] idle_balance+0xe3/0x150 > [ 220.262270] [] __schedule+0x797/0x8d0 > [ 220.262277] [] schedule+0x24/0x70 > [ 220.262283] [] schedule_timeout+0x119/0x1f0 > [ 220.262294] [] ? lock_timer_base+0x70/0x70 > [ 220.262301] [] schedule_timeout_uninterruptible+0x19/0x20 > [ 220.262308] [] msleep+0x18/0x20 > [ 220.262317] [] lock_device_hotplug_sysfs+0x2a/0x50 > [ 220.262323] [] online_store+0x2e/0x80 > [ 220.262358] [] dev_attr_store+0x1b/0x20 > > Last level cache shared map is built during cpu up and build sched domain > routine takes advantage of it to setup sched domain cpu topology, however, > llc shared map is unreleased during cpu disable which lead to invalid sched > domain cpu topology. This patch fix it by release llc shared map correctly > during cpu disable. > > Reviewed-by: Toshi Kani > Reviewed-by: Yasuaki Ishimatsu > Tested-by: Linn Crosetto > Signed-off-by: Wanpeng Li > --- > v3 -> v4: > * simplify backtrace > v2 -> v3: > * simplify backtrace > v1 -> v2: > * fix subject line > > arch/x86/kernel/smpboot.c | 3 +++ > 1 file changed, 3 insertions(+) > > diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c > index 5492798..0134ec7 100644 > --- a/arch/x86/kernel/smpboot.c > +++ b/arch/x86/kernel/smpboot.c > @@ -1292,6 +1292,9 @@ static void remove_siblinginfo(int cpu) > > for_each_cpu(sibling, cpu_sibling_mask(cpu)) > cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling)); > + for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) > + cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling)); > + cpumask_clear(cpu_llc_shared_mask(cpu)); > cpumask_clear(cpu_sibling_mask(cpu)); > cpumask_clear(cpu_core_mask(cpu)); > c->phys_proc_id = 0;