Re: [PATCH 2/6] posix-cpu-timers: Don't start process wide cputime counter if timer is disabled

[Peter Zijlstra]

On Fri, Jun 04, 2021 at 01:31:55PM +0200, Frederic Weisbecker wrote:
> If timer_settime() is called with a 0 expiration on a timer that is
> already disabled, the process wide cputime counter will be started
> and won't ever get a chance to be stopped by stop_process_timer() since
> no timer is actually armed to be processed.
> 
> This process wide counter might bring some performance hit due to the
> concurrent atomic additions at the thread group scope.
> 
> The following snippet is enough to trigger the issue.
> 
> 	void trigger_process_counter(void)
> 	{
> 		timer_t id;
> 		struct itimerspec val = { };
> 
> 		timer_create(CLOCK_PROCESS_CPUTIME_ID, NULL, &id);
> 		timer_settime(id, TIMER_ABSTIME, &val, NULL);
> 		timer_delete(id);
> 	}
> 
> So make sure we don't needlessly start it.
> 
> Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
> Cc: Oleg Nesterov <oleg@xxxxxxxxxx>
> Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> Cc: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
> Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> Cc: Eric W. Biederman <ebiederm@xxxxxxxxxxxx>
> ---
>  kernel/time/posix-cpu-timers.c | 11 ++++++++---
>  1 file changed, 8 insertions(+), 3 deletions(-)
> 
> diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
> index aa52fc85dbcb..132fd56fb1cd 100644
> --- a/kernel/time/posix-cpu-timers.c
> +++ b/kernel/time/posix-cpu-timers.c
> @@ -632,10 +632,15 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
>  	 * times (in arm_timer).  With an absolute time, we must
>  	 * check if it's already passed.  In short, we need a sample.
>  	 */
> -	if (CPUCLOCK_PERTHREAD(timer->it_clock))
> +	if (CPUCLOCK_PERTHREAD(timer->it_clock)) {
>  		val = cpu_clock_sample(clkid, p);
> -	else
> -		val = cpu_clock_sample_group(clkid, p, true);
> +	} else {
> +		/*
> +		 * Sample group but only start the process wide cputime counter
> +		 * if the timer is to be enabled.
> +		 */
> +		val = cpu_clock_sample_group(clkid, p, !!new_expires);
> +	}

The cpu_timer_enqueue() is in arm_timer() and the condition for calling
that is:

  'new_expires != 0 && val < new_expires'

Which is not the same as the one you add.

I'm thinking the fundamental problem here is the disconnect between
cpu_timer_enqueue() and pct->timers_active ?