__remove_hrtimer() needs to evaluate the expiry time to figure out whether the timer which is removed is eventually the first expiring timer on the cpu. Keep a pointer to it, which is lazily updated, so we can avoid the evaluation dance and retrieve the information from there. Generates slightly better code. Signed-off-by: Thomas Gleixner --- include/linux/hrtimer.h | 6 ++++++ kernel/time/hrtimer.c | 46 ++++++++++++++++++++++++++++------------------ 2 files changed, 34 insertions(+), 18 deletions(-) Index: tip/include/linux/hrtimer.h =================================================================== --- tip.orig/include/linux/hrtimer.h +++ tip/include/linux/hrtimer.h @@ -172,6 +172,7 @@ enum hrtimer_base_type { * @clock_was_set_seq: Sequence counter of clock was set events * @expires_next: absolute time of the next event which was scheduled * via clock_set_next_event() + * @next_timer: Pointer to the first expiring timer * @in_hrtirq: hrtimer_interrupt() is currently executing * @hres_active: State of high resolution mode * @hang_detected: The last hrtimer interrupt detected a hang @@ -180,6 +181,10 @@ enum hrtimer_base_type { * @nr_hangs: Total number of hrtimer interrupt hangs * @max_hang_time: Maximum time spent in hrtimer_interrupt * @clock_base: array of clock bases for this cpu + * + * Note: next_timer is just an optimization for __remove_hrtimer(). + * Do not dereference the pointer because it is not reliable on + * cross cpu removals. */ struct hrtimer_cpu_base { raw_spinlock_t lock; @@ -191,6 +196,7 @@ struct hrtimer_cpu_base { hres_active : 1, hang_detected : 1; ktime_t expires_next; + struct hrtimer *next_timer; unsigned int nr_events; unsigned int nr_retries; unsigned int nr_hangs; Index: tip/kernel/time/hrtimer.c =================================================================== --- tip.orig/kernel/time/hrtimer.c +++ tip/kernel/time/hrtimer.c @@ -415,12 +415,21 @@ static inline void debug_deactivate(stru } #if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base, + struct hrtimer *timer) +{ +#ifdef CONFIG_HIGH_RES_TIMERS + cpu_base->next_timer = timer; +#endif +} + static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) { struct hrtimer_clock_base *base = cpu_base->clock_base; ktime_t expires, expires_next = { .tv64 = KTIME_MAX }; unsigned int active = cpu_base->active_bases; + hrtimer_update_next_timer(cpu_base, NULL); for (; active; base++, active >>= 1) { struct timerqueue_node *next; struct hrtimer *timer; @@ -431,8 +440,10 @@ static ktime_t __hrtimer_get_next_event( next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); expires = ktime_sub(hrtimer_get_expires(timer), base->offset); - if (expires.tv64 < expires_next.tv64) + if (expires.tv64 < expires_next.tv64) { expires_next = expires; + hrtimer_update_next_timer(cpu_base, timer); + } } /* * clock_was_set() might have changed base->offset of any of @@ -597,6 +608,8 @@ static int hrtimer_reprogram(struct hrti if (cpu_base->in_hrtirq) return 0; + cpu_base->next_timer = timer; + /* * If a hang was detected in the last timer interrupt then we * do not schedule a timer which is earlier than the expiry @@ -860,30 +873,27 @@ static void __remove_hrtimer(struct hrti unsigned long newstate, int reprogram) { struct hrtimer_cpu_base *cpu_base = base->cpu_base; - struct timerqueue_node *next_timer; + unsigned int state = timer->state; - if (!(timer->state & HRTIMER_STATE_ENQUEUED)) - goto out; + timer->state = newstate; + if (!(state & HRTIMER_STATE_ENQUEUED)) + return; - next_timer = timerqueue_getnext(&base->active); if (!timerqueue_del(&base->active, &timer->node)) cpu_base->active_bases &= ~(1 << base->index); - if (&timer->node == next_timer) { #ifdef CONFIG_HIGH_RES_TIMERS - /* Reprogram the clock event device. if enabled */ - if (reprogram && cpu_base->hres_active) { - ktime_t expires; - - expires = ktime_sub(hrtimer_get_expires(timer), - base->offset); - if (cpu_base->expires_next.tv64 == expires.tv64) - hrtimer_force_reprogram(cpu_base, 1); - } + /* + * Note: If reprogram is false we do not update + * cpu_base->next_timer. This happens when we remove the first + * timer on a remote cpu. No harm as we never dereference + * cpu_base->next_timer. So the worst thing what can happen is + * an superflous call to hrtimer_force_reprogram() on the + * remote cpu later on if the same timer gets enqueued again. + */ + if (reprogram && timer == cpu_base->next_timer) + hrtimer_force_reprogram(cpu_base, 1); #endif - } -out: - timer->state = newstate; } /*