linux-kernel - Re: CONFIG_NO_HZ_FULL + CONFIG_PREEMPT_RT

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date:	Sat, 21 Dec 2013 10:11:44 +0100
From:	Mike Galbraith <bitbucket@...ine.de>
To:	Sebastian Andrzej Siewior <sebastian@...akpoint.cc>
Cc:	Thomas Gleixner <tglx@...utronix.de>,
	Frederic Weisbecker <fweisbec@...il.com>,
	Peter Zijlstra <peterz@...radead.org>,
	LKML <linux-kernel@...r.kernel.org>,
	RT <linux-rt-users@...r.kernel.org>,
	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>
Subject: Re: CONFIG_NO_HZ_FULL + CONFIG_PREEMPT_RT_FULL = nogo

On Fri, 2013-12-20 at 16:41 +0100, Sebastian Andrzej Siewior wrote: 
> On 07.11.13, Thomas Gleixner wrote:
> > below should address that issue. If that works on mainline we can
> > adapt it for RT (needs a trylock(&base->lock) there).
> 
> okay, so this is waht I'm going to take for -RT:

Works, modulo noisy workqueues.

rtbox:~ # sleep 35 && killall pert& cgexec -g cpuset:rtcpus taskset -c 3 pert 5
[1] 5660
2400.05 MHZ CPU
perturbation threshold 0.018 usecs.
pert/s:       33 >15.75us:        2 min:  0.04 max: 24.14 avg:  2.51 sum/s:    84us overhead: 0.01%
pert/s:       35 >15.54us:        3 min:  0.04 max: 24.89 avg:  2.39 sum/s:    84us overhead: 0.01%
pert/s:       30 >15.27us:        2 min:  0.04 max: 23.03 avg:  2.64 sum/s:    80us overhead: 0.01%
pert/s:       34 >15.12us:        3 min:  0.04 max: 25.03 avg:  2.51 sum/s:    86us overhead: 0.01%
pert/s:       31 >14.93us:        2 min:  0.04 max: 23.86 avg:  2.60 sum/s:    83us overhead: 0.01%
Terminated

> diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
> index 79a7a35..bdbf77db 100644
> --- a/include/linux/hrtimer.h
> +++ b/include/linux/hrtimer.h
> @@ -461,9 +461,8 @@ extern int schedule_hrtimeout_range_clock(ktime_t *expires,
>  		unsigned long delta, const enum hrtimer_mode mode, int clock);
>  extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
>  
> -/* Soft interrupt function to run the hrtimer queues: */
> +/* Called from the periodic timer tick */
>  extern void hrtimer_run_queues(void);
> -extern void hrtimer_run_pending(void);
>  
>  /* Bootup initialization: */
>  extern void __init hrtimers_init(void);
> diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
> index c383841..7aa442e 100644
> --- a/kernel/hrtimer.c
> +++ b/kernel/hrtimer.c
> @@ -1694,30 +1694,6 @@ static void run_hrtimer_softirq(struct softirq_action *h)
>  }
>  
>  /*
> - * Called from timer softirq every jiffy, expire hrtimers:
> - *
> - * For HRT its the fall back code to run the softirq in the timer
> - * softirq context in case the hrtimer initialization failed or has
> - * not been done yet.
> - */
> -void hrtimer_run_pending(void)
> -{
> -	if (hrtimer_hres_active())
> -		return;
> -
> -	/*
> -	 * This _is_ ugly: We have to check in the softirq context,
> -	 * whether we can switch to highres and / or nohz mode. The
> -	 * clocksource switch happens in the timer interrupt with
> -	 * xtime_lock held. Notification from there only sets the
> -	 * check bit in the tick_oneshot code, otherwise we might
> -	 * deadlock vs. xtime_lock.
> -	 */
> -	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled()))
> -		hrtimer_switch_to_hres();
> -}
> -
> -/*
>   * Called from hardirq context every jiffy
>   */
>  void hrtimer_run_queues(void)
> @@ -1730,6 +1706,13 @@ void hrtimer_run_queues(void)
>  	if (hrtimer_hres_active())
>  		return;
>  
> +	/*
> +	 * Check whether we can switch to highres mode.
> +	 */
> +	if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())
> +	    && hrtimer_switch_to_hres())
> +		return;
> +
>  	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
>  		base = &cpu_base->clock_base[index];
>  		if (!timerqueue_getnext(&base->active))
> diff --git a/kernel/timer.c b/kernel/timer.c
> index b06c647..46467be 100644
> --- a/kernel/timer.c
> +++ b/kernel/timer.c
> @@ -1443,8 +1443,6 @@ static void run_timer_softirq(struct softirq_action *h)
>  	irq_work_run();
>  #endif
>  
> -	hrtimer_run_pending();
> -
>  	if (time_after_eq(jiffies, base->timer_jiffies))
>  		__run_timers(base);
>  }
> @@ -1454,8 +1452,27 @@ static void run_timer_softirq(struct softirq_action *h)
>   */
>  void run_local_timers(void)
>  {
> +	struct tvec_base *base = __this_cpu_read(tvec_bases);
> +
>  	hrtimer_run_queues();
> -	raise_softirq(TIMER_SOFTIRQ);
> +	/*
> +	 * We can access this lockless as we are in the timer
> +	 * interrupt. If there are no timers queued, nothing to do in
> +	 * the timer softirq.
> +	 */
> +	if (!spin_do_trylock(&base->lock)) {
> +		raise_softirq(TIMER_SOFTIRQ);
> +		return;
> +	}
> +	if (!base->active_timers)
> +		goto out;
> +
> +	/* Check whether the next pending timer has expired */
> +	if (time_before_eq(base->next_timer, jiffies))
> +		raise_softirq(TIMER_SOFTIRQ);
> +out:
> +	rt_spin_unlock_after_trylock_in_irq(&base->lock);
> +
>  }
>  
>  #ifdef __ARCH_WANT_SYS_ALARM


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/