Re: [PATCH] tick: Detect and fix jiffies update stall

[Paul E. McKenney]

On Wed, Feb 02, 2022 at 01:01:07AM +0100, Frederic Weisbecker wrote:
> On some rare cases, the timekeeper CPU may be delaying its jiffies
> update duty for a while. Known causes include:
> 
> * The timekeeper is waiting on stop_machine in a MULTI_STOP_DISABLE_IRQ
>   or MULTI_STOP_RUN state. Disabled interrupts prevent from timekeeping
>   updates while waiting for the target CPU to complete its
>   stop_machine() callback.
> 
> * The timekeeper vcpu has VMEXIT'ed for a long while due to some overload
>   on the host.
> 
> Detect and fix these situations with emergency timekeeping catchups.
> 
> Original-patch-by: Paul E. McKenney <paulmck@xxxxxxxxxx>
> Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>

Nice, thank you!

So I should revert your earlier patch, apply this one, and then test
the result?

							Thanx, Paul

> ---
>  kernel/time/tick-sched.c | 17 +++++++++++++++++
>  kernel/time/tick-sched.h |  4 ++++
>  2 files changed, 21 insertions(+)
> 
> diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
> index 17a283ce2b20..c89f50a7e690 100644
> --- a/kernel/time/tick-sched.c
> +++ b/kernel/time/tick-sched.c
> @@ -169,6 +169,8 @@ static ktime_t tick_init_jiffy_update(void)
>  	return period;
>  }
>  
> +#define MAX_STALLED_JIFFIES 5
> +
>  static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
>  {
>  	int cpu = smp_processor_id();
> @@ -196,6 +198,21 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now)
>  	if (tick_do_timer_cpu == cpu)
>  		tick_do_update_jiffies64(now);
>  
> +	/*
> +	 * If jiffies update stalled for too long (timekeeper in stop_machine()
> +	 * or VMEXIT'ed for several msecs), force an update.
> +	 */
> +	if (ts->last_tick_jiffies != jiffies) {
> +		ts->stalled_jiffies = 0;
> +		ts->last_tick_jiffies = READ_ONCE(jiffies);
> +	} else {
> +		if (++ts->stalled_jiffies == MAX_STALLED_JIFFIES) {
> +			tick_do_update_jiffies64(now);
> +			ts->stalled_jiffies = 0;
> +			ts->last_tick_jiffies = READ_ONCE(jiffies);
> +		}
> +	}
> +
>  	if (ts->inidle)
>  		ts->got_idle_tick = 1;
>  }
> diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
> index d952ae393423..504649513399 100644
> --- a/kernel/time/tick-sched.h
> +++ b/kernel/time/tick-sched.h
> @@ -49,6 +49,8 @@ enum tick_nohz_mode {
>   * @timer_expires_base:	Base time clock monotonic for @timer_expires
>   * @next_timer:		Expiry time of next expiring timer for debugging purpose only
>   * @tick_dep_mask:	Tick dependency mask - is set, if someone needs the tick
> + * @last_tick_jiffies:	Value of jiffies seen on last tick
> + * @stalled_jiffies:	Number of stalled jiffies detected across ticks
>   */
>  struct tick_sched {
>  	struct hrtimer			sched_timer;
> @@ -77,6 +79,8 @@ struct tick_sched {
>  	u64				next_timer;
>  	ktime_t				idle_expires;
>  	atomic_t			tick_dep_mask;
> +	unsigned long			last_tick_jiffies;
> +	unsigned int			stalled_jiffies;
>  };
>  
>  extern struct tick_sched *tick_get_tick_sched(int cpu);
> -- 
> 2.25.1
>