From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755618AbbILXNc (ORCPT ); Sat, 12 Sep 2015 19:13:32 -0400 Received: from wtarreau.pck.nerim.net ([62.212.114.60]:9386 "EHLO 1wt.eu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754748AbbILXNZ (ORCPT ); Sat, 12 Sep 2015 19:13:25 -0400 Message-Id: <20150912225607.857682577@1wt.eu> User-Agent: quilt/0.63-1 Date: Sun, 13 Sep 2015 00:56:36 +0200 From: Willy Tarreau To: linux-kernel@vger.kernel.org, stable@vger.kernel.org Cc: Feng Tang , Don Zickus , Peter Zijlstra , Ingo Molnar , Ben Hutchings , Vinson Lee , Willy Tarreau Subject: [PATCH 2.6.32 30/62] x86/reboot: Fix a warning message triggered by stop_other_cpus() MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 In-Reply-To: <08d3b586eb2e764308c3de9ee398a17c@local> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 2.6.32-longterm review patch. If anyone has any objections, please let me know. ------------------ From: Feng Tang commit 55c844a4dd16a4d1fdc0cf2a283ec631a02ec448 upstream. When rebooting our 24 CPU Westmere servers with 3.4-rc6, we always see this warning msg: Restarting system. machine restart ------------[ cut here ]------------ WARNING: at arch/x86/kernel/smp.c:125 native_smp_send_reschedule+0x74/0xa7() Hardware name: X8DTN Modules linked in: igb [last unloaded: scsi_wait_scan] Pid: 1, comm: systemd-shutdow Not tainted 3.4.0-rc6+ #22 Call Trace: [] warn_slowpath_common+0x7e/0x96 [] warn_slowpath_null+0x15/0x17 [] native_smp_send_reschedule+0x74/0xa7 [] trigger_load_balance+0x279/0x2a6 [] scheduler_tick+0xe0/0xe9 [] update_process_times+0x60/0x70 [] tick_sched_timer+0x68/0x92 [] __run_hrtimer+0xb3/0x13c [] ? tick_nohz_handler+0xd0/0xd0 [] hrtimer_interrupt+0xdb/0x198 [] smp_apic_timer_interrupt+0x81/0x94 [] apic_timer_interrupt+0x67/0x70 [] ? default_send_IPI_mask_allbutself_phys+0xb4/0xc4 [] physflat_send_IPI_allbutself+0x12/0x14 [] native_nmi_stop_other_cpus+0x8a/0xd6 [] native_machine_shutdown+0x50/0x67 [] machine_shutdown+0xa/0xc [] native_machine_restart+0x20/0x32 [] machine_restart+0xa/0xc [] kernel_restart+0x47/0x4c [] sys_reboot+0x13e/0x17c [] ? _raw_spin_unlock_bh+0x10/0x12 [] ? bdi_queue_work+0xcf/0xd8 [] ? __bdi_start_writeback+0xae/0xb7 [] ? iterate_supers+0xa3/0xb7 [] system_call_fastpath+0x16/0x1b ---[ end trace 320af5cb1cb60c5b ]--- The root cause seems to be the default_send_IPI_mask_allbutself_phys() takes quite some time (I measured it could be several ms) to complete sending NMIs to all the other 23 CPUs, and for HZ=250/1000 system, the time is long enough for a timer interrupt to happen, which will in turn trigger to kick load balance to a stopped CPU and cause this warning in native_smp_send_reschedule(). So disabling the local irq before stop_other_cpu() can fix this problem (tested 25 times reboot ok), and it is fine as there should be nobody caring the timer interrupt in such reboot stage. The latest 3.4 kernel slightly changes this behavior by sending REBOOT_VECTOR first and only send NMI_VECTOR if the REBOOT_VCTOR fails, and this patch is still needed to prevent the problem. Signed-off-by: Feng Tang Acked-by: Don Zickus Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/20120530231541.4c13433a@feng-i7 Signed-off-by: Ingo Molnar [bwh: Backported to 3.2: adjust context] Signed-off-by: Ben Hutchings Cc: Vinson Lee (cherry picked from commit ea475029e76a0b7fc6e96baf4d414079dec8a90a) Signed-off-by: Willy Tarreau --- arch/x86/kernel/reboot.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c index cf98100..93a933f 100644 --- a/arch/x86/kernel/reboot.c +++ b/arch/x86/kernel/reboot.c @@ -638,9 +638,12 @@ void native_machine_shutdown(void) /* Make certain I only run on the appropriate processor */ set_cpus_allowed_ptr(current, cpumask_of(reboot_cpu_id)); - /* O.K Now that I'm on the appropriate processor, - * stop all of the others. + /* + * O.K Now that I'm on the appropriate processor, stop all of the + * others. Also disable the local irq to not receive the per-cpu + * timer interrupt which may trigger scheduler's load balance. */ + local_irq_disable(); stop_other_cpus(); #endif -- 1.7.12.2.21.g234cd45.dirty