diff options
Diffstat (limited to 'kernel/time/timer.c')
| -rw-r--r-- | kernel/time/timer.c | 85 |
1 files changed, 56 insertions, 29 deletions
diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 748f4b72fb6d..aabd13675723 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -187,12 +187,18 @@ EXPORT_SYMBOL(jiffies_64); #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON -# define NR_BASES 2 -# define BASE_STD 0 -# define BASE_DEF 1 +/* + * If multiple bases need to be locked, use the base ordering for lock + * nesting, i.e. lowest number first. + */ +# define NR_BASES 3 +# define BASE_LOCAL 0 +# define BASE_GLOBAL 1 +# define BASE_DEF 2 #else # define NR_BASES 1 -# define BASE_STD 0 +# define BASE_LOCAL 0 +# define BASE_GLOBAL 0 # define BASE_DEF 0 #endif @@ -944,7 +950,10 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base, static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { - struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); + int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; + struct timer_base *base; + + base = per_cpu_ptr(&timer_bases[index], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need @@ -957,7 +966,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; + struct timer_base *base; + + base = this_cpu_ptr(&timer_bases[index]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need @@ -2006,6 +2018,9 @@ static unsigned long next_timer_interrupt(struct timer_base *base, * Move next_expiry for the empty base into the future to prevent an * unnecessary raise of the timer softirq when the next_expiry value * will be reached even if there is no timer pending. + * + * This update is also required to make timer_base::next_expiry values + * easy comparable to find out which base holds the first pending timer. */ if (!base->timers_pending) base->next_expiry = basej + NEXT_TIMER_MAX_DELTA; @@ -2016,9 +2031,10 @@ static unsigned long next_timer_interrupt(struct timer_base *base, static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, bool *idle) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + unsigned long nextevt, nextevt_local, nextevt_global; + struct timer_base *base_local, *base_global; u64 expires = KTIME_MAX; - unsigned long nextevt; + bool local_first; /* * Pretend that there is no timer pending if the cpu is offline. @@ -2030,10 +2046,20 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, return expires; } - raw_spin_lock(&base->lock); - nextevt = next_timer_interrupt(base, basej); + base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]); + base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]); - if (base->timers_pending) { + raw_spin_lock(&base_local->lock); + raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); + + nextevt_local = next_timer_interrupt(base_local, basej); + nextevt_global = next_timer_interrupt(base_global, basej); + + local_first = time_before_eq(nextevt_local, nextevt_global); + + nextevt = local_first ? nextevt_local : nextevt_global; + + if (base_local->timers_pending || base_global->timers_pending) { /* If we missed a tick already, force 0 delta */ if (time_before(nextevt, basej)) nextevt = basej; @@ -2044,31 +2070,31 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, * We have a fresh next event. Check whether we can forward the * base. */ - __forward_timer_base(base, basej); + __forward_timer_base(base_local, basej); + __forward_timer_base(base_global, basej); /* * Set base->is_idle only when caller is timer_base_try_to_set_idle() */ if (idle) { /* - * Base is idle if the next event is more than a tick away. + * Bases are idle if the next event is more than a tick away. * * If the base is marked idle then any timer add operation must * forward the base clk itself to keep granularity small. This - * idle logic is only maintained for the BASE_STD base, - * deferrable timers may still see large granularity skew (by - * design). + * idle logic is only maintained for the BASE_LOCAL and + * BASE_GLOBAL base, deferrable timers may still see large + * granularity skew (by design). */ - if (!base->is_idle) { - if (time_after(nextevt, basej + 1)) { - base->is_idle = true; - trace_timer_base_idle(true, base->cpu); - } + if (!base_local->is_idle && time_after(nextevt, basej + 1)) { + base_local->is_idle = base_global->is_idle = true; + trace_timer_base_idle(true, base_local->cpu); } - *idle = base->is_idle; + *idle = base_local->is_idle; } - raw_spin_unlock(&base->lock); + raw_spin_unlock(&base_global->lock); + raw_spin_unlock(&base_local->lock); return cmp_next_hrtimer_event(basem, expires); } @@ -2112,15 +2138,14 @@ u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) */ void timer_clear_idle(void) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - /* * 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. */ - base->is_idle = false; + __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()); } #endif @@ -2171,11 +2196,13 @@ static inline void __run_timers(struct timer_base *base) */ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); __run_timers(base); - if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) + if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { + __run_timers(this_cpu_ptr(&timer_bases[BASE_GLOBAL])); __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); + } } /* @@ -2183,7 +2210,7 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) */ static void run_local_timers(void) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); hrtimer_run_queues(); |