Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753949AbeAAOhj (ORCPT + 1 other); Mon, 1 Jan 2018 09:37:39 -0500 Received: from mail.linuxfoundation.org ([140.211.169.12]:44082 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752825AbeAAOhg (ORCPT ); Mon, 1 Jan 2018 09:37:36 -0500 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Sebastian Siewior , Thomas Gleixner , Frederic Weisbecker , Peter Zijlstra , Paul McKenney , Anna-Maria Gleixner , Sebastian Siewior Subject: [PATCH 4.9 72/75] nohz: Prevent a timer interrupt storm in tick_nohz_stop_sched_tick() Date: Mon, 1 Jan 2018 15:32:49 +0100 Message-Id: <20180101140108.467945021@linuxfoundation.org> X-Mailer: git-send-email 2.15.1 In-Reply-To: <20180101140056.475827799@linuxfoundation.org> References: <20180101140056.475827799@linuxfoundation.org> User-Agent: quilt/0.65 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Return-Path: 4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Thomas Gleixner commit 5d62c183f9e9df1deeea0906d099a94e8a43047a upstream. The conditions in irq_exit() to invoke tick_nohz_irq_exit() which subsequently invokes tick_nohz_stop_sched_tick() are: if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) If need_resched() is not set, but a timer softirq is pending then this is an indication that the softirq code punted and delegated the execution to softirqd. need_resched() is not true because the current interrupted task takes precedence over softirqd. Invoking tick_nohz_irq_exit() in this case can cause an endless loop of timer interrupts because the timer wheel contains an expired timer, but softirqs are not yet executed. So it returns an immediate expiry request, which causes the timer to fire immediately again. Lather, rinse and repeat.... Prevent that by adding a check for a pending timer soft interrupt to the conditions in tick_nohz_stop_sched_tick() which avoid calling get_next_timer_interrupt(). That keeps the tick sched timer on the tick and prevents a repetitive programming of an already expired timer. Reported-by: Sebastian Siewior Signed-off-by: Thomas Gleixner Acked-by: Frederic Weisbecker Cc: Peter Zijlstra Cc: Paul McKenney Cc: Anna-Maria Gleixner Cc: Sebastian Siewior Link: https://lkml.kernel.org/r/alpine.DEB.2.20.1712272156050.2431@nanos Signed-off-by: Greg Kroah-Hartman --- kernel/time/tick-sched.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -663,6 +663,11 @@ static void tick_nohz_restart(struct tic tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); } +static inline bool local_timer_softirq_pending(void) +{ + return local_softirq_pending() & TIMER_SOFTIRQ; +} + static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ktime_t now, int cpu) { @@ -679,8 +684,18 @@ static ktime_t tick_nohz_stop_sched_tick } while (read_seqretry(&jiffies_lock, seq)); ts->last_jiffies = basejiff; - if (rcu_needs_cpu(basemono, &next_rcu) || - arch_needs_cpu() || irq_work_needs_cpu()) { + /* + * Keep the periodic tick, when RCU, architecture or irq_work + * requests it. + * Aside of that check whether the local timer softirq is + * pending. If so its a bad idea to call get_next_timer_interrupt() + * because there is an already expired timer, so it will request + * immeditate expiry, which rearms the hardware timer with a + * minimal delta which brings us back to this place + * immediately. Lather, rinse and repeat... + */ + if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() || + irq_work_needs_cpu() || local_timer_softirq_pending()) { next_tick = basemono + TICK_NSEC; } else { /*