From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934197AbcCHAwj (ORCPT ); Mon, 7 Mar 2016 19:52:39 -0500 Received: from youngberry.canonical.com ([91.189.89.112]:38469 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753711AbcCGWvr (ORCPT ); Mon, 7 Mar 2016 17:51:47 -0500 From: Kamal Mostafa To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Christoph Lameter , Tejun Heo , Linus Torvalds , Kamal Mostafa Subject: [PATCH 4.2.y-ckt 011/273] vmstat: explicitly schedule per-cpu work on the CPU we need it to run on Date: Mon, 7 Mar 2016 14:46:42 -0800 Message-Id: <1457391064-6660-12-git-send-email-kamal@canonical.com> X-Mailer: git-send-email 2.7.0 In-Reply-To: <1457391064-6660-1-git-send-email-kamal@canonical.com> References: <1457391064-6660-1-git-send-email-kamal@canonical.com> X-Extended-Stable: 4.2 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 4.2.8-ckt5 -stable review patch. If anyone has any objections, please let me know. ---8<------------------------------------------------------------ From: Linus Torvalds commit 176bed1de5bf977938cad26551969eca8f0883b1 upstream. The vmstat code uses "schedule_delayed_work_on()" to do the initial startup of the delayed work on the right CPU, but then once it was started it would use the non-cpu-specific "schedule_delayed_work()" to re-schedule it on that CPU. That just happened to schedule it on the same CPU historically (well, in almost all situations), but the code _requires_ this work to be per-cpu, and should say so explicitly rather than depend on the non-cpu-specific scheduling to schedule on the current CPU. The timer code is being changed to not be as single-minded in always running things on the calling CPU. See also commit 874bbfe600a6 ("workqueue: make sure delayed work run in local cpu") that for now maintains the local CPU guarantees just in case there are other broken users that depended on the accidental behavior. Cc: Christoph Lameter Cc: Tejun Heo Signed-off-by: Linus Torvalds [ kamal: backport to 3.19-stable: use queue_delayed_work_on() ] Signed-off-by: Kamal Mostafa --- mm/vmstat.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/mm/vmstat.c b/mm/vmstat.c index 2139b23..6c9749b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1366,16 +1366,16 @@ static cpumask_var_t cpu_stat_off; static void vmstat_update(struct work_struct *w) { - if (refresh_cpu_vm_stats(true)) + if (refresh_cpu_vm_stats(true)) { /* * Counters were updated so we expect more updates * to occur in the future. Keep on running the * update worker thread. */ - queue_delayed_work(vmstat_wq, + queue_delayed_work_on(smp_processor_id(), vmstat_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); - else { + } else { /* * We did not update any counters so the app may be in * a mode where it does not cause counter updates. -- 2.7.0