Commit b2cf7507 authored by Anna-Maria Behnsen's avatar Anna-Maria Behnsen Committed by Thomas Gleixner
Browse files

timers: Always queue timers on the local CPU 



The timer pull model is in place so we can remove the heuristics which try
to guess the best target CPU at enqueue/modification time.

All non pinned timers are queued on the local CPU in the separate storage
and eventually pulled at expiry time to a remote CPU.

Originally-by: default avatarRichard Cochran (linutronix GmbH) <richardcochran@gmail.com>
Signed-off-by: default avatarAnna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: default avatarThomas Gleixner <tglx@linutronix.de>
Reviewed-by: default avatarFrederic Weisbecker <frederic@kernel.org>
Link: https://lore.kernel.org/r/20240221090548.36600-21-anna-maria@linutronix.de
parent 36e40df3

include/linux/timer.h

+4 −10
Original line number Diff line number Diff line
@@ -36,16 +36,10 @@ 
 * workqueue locking issues. It's not meant for executing random crap

 * with interrupts disabled. Abuse is monitored!

 *

 * @TIMER_PINNED: A pinned timer will not be affected by any timer

 * placement heuristics (like, NOHZ) and will always expire on the CPU

 * on which the timer was enqueued.

 *

 * Note: Because enqueuing of timers can migrate the timer from one

 * CPU to another, pinned timers are not guaranteed to stay on the

 * initialy selected CPU.  They move to the CPU on which the enqueue

 * function is invoked via mod_timer() or add_timer().  If the timer

 * should be placed on a particular CPU, then add_timer_on() has to be

 * used.

 * @TIMER_PINNED: A pinned timer will always expire on the CPU on which the

 * timer was enqueued. When a particular CPU is required, add_timer_on()

 * has to be used. Enqueue via mod_timer() and add_timer() is always done

 * on the local CPU.

 */

#define TIMER_CPUMASK		0x0003FFFF

#define TIMER_MIGRATING		0x00040000

kernel/time/timer.c

+15 −21
Original line number Diff line number Diff line
@@ -635,12 +635,17 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) 


	/*

	 * We might have to IPI the remote CPU if the base is idle and the

	 * timer is not deferrable. If the other CPU is on the way to idle

	 * then it can't set base->is_idle as we hold the base lock:

	 */

	if (base->is_idle)

	 * timer is pinned. If it is a non pinned timer, it is only queued

	 * on the remote CPU, when timer was running during queueing. Then

	 * everything is handled by remote CPU anyway. If the other CPU is

	 * on the way to idle then it can't set base->is_idle as we hold

	 * the base lock:

	 */

	if (base->is_idle) {

		WARN_ON_ONCE(!(timer->flags & TIMER_PINNED));

		wake_up_nohz_cpu(base->cpu);

	}

}



/*

 * Enqueue the timer into the hash bucket, mark it pending in
@@ -986,17 +991,6 @@ static inline struct timer_base *get_timer_base(u32 tflags) 
	return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK);

}



static inline struct timer_base *

get_target_base(struct timer_base *base, unsigned tflags)

{

#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)

	if (static_branch_likely(&timers_migration_enabled) &&

	    !(tflags & TIMER_PINNED))

		return get_timer_cpu_base(tflags, get_nohz_timer_target());

#endif

	return get_timer_this_cpu_base(tflags);

}



static inline void __forward_timer_base(struct timer_base *base,

					unsigned long basej)

{
@@ -1151,7 +1145,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option 
	if (!ret && (options & MOD_TIMER_PENDING_ONLY))

		goto out_unlock;



	new_base = get_target_base(base, timer->flags);

	new_base = get_timer_this_cpu_base(timer->flags);



	if (base != new_base) {

		/*
@@ -2297,7 +2291,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, 
		 * granularity skew (by design).

		 */

		if (!base_local->is_idle && time_after(nextevt, basej + 1)) {

			base_local->is_idle = base_global->is_idle = true;

			base_local->is_idle = true;

			trace_timer_base_idle(true, base_local->cpu);

		}

		*idle = base_local->is_idle;
@@ -2363,13 +2357,13 @@ u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) 
void timer_clear_idle(void)

{

	/*

	 * We do this unlocked. The worst outcome is a remote enqueue sending

	 * a pointless IPI, but taking the lock would just make the window for

	 * sending the IPI a few instructions smaller for the cost of taking

	 * the lock in the exit from idle path.

	 * We do this unlocked. The worst outcome is a remote pinned timer

	 * enqueue sending a pointless IPI, but taking the lock would just

	 * make the window for sending the IPI a few instructions smaller

	 * for the cost of taking the lock in the exit from idle

	 * path. Required for BASE_LOCAL only.

	 */

	__this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false);

	__this_cpu_write(timer_bases[BASE_GLOBAL].is_idle, false);

	trace_timer_base_idle(false, smp_processor_id());



	/* Activate without holding the timer_base->lock */