diff options
Diffstat (limited to 'kernel/time')
-rw-r--r-- | kernel/time/alarmtimer.c | 17 | ||||
-rw-r--r-- | kernel/time/posix-cpu-timers.c | 14 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 6 | ||||
-rw-r--r-- | kernel/time/timer.c | 52 |
4 files changed, 65 insertions, 24 deletions
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 0b8ff7d257ea..ec09ce9a6012 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -28,6 +28,7 @@ #include <linux/workqueue.h> #include <linux/freezer.h> #include <linux/compat.h> +#include <linux/module.h> #include "posix-timers.h" @@ -56,9 +57,9 @@ static ktime_t freezer_delta; static DEFINE_SPINLOCK(freezer_delta_lock); #endif +#ifdef CONFIG_RTC_CLASS static struct wakeup_source *ws; -#ifdef CONFIG_RTC_CLASS /* rtc timer and device for setting alarm wakeups at suspend */ static struct rtc_timer rtctimer; static struct rtc_device *rtcdev; @@ -89,6 +90,7 @@ static int alarmtimer_rtc_add_device(struct device *dev, { unsigned long flags; struct rtc_device *rtc = to_rtc_device(dev); + struct wakeup_source *__ws; if (rtcdev) return -EBUSY; @@ -98,13 +100,25 @@ static int alarmtimer_rtc_add_device(struct device *dev, if (!device_may_wakeup(rtc->dev.parent)) return -1; + __ws = wakeup_source_register("alarmtimer"); + spin_lock_irqsave(&rtcdev_lock, flags); if (!rtcdev) { + if (!try_module_get(rtc->owner)) { + spin_unlock_irqrestore(&rtcdev_lock, flags); + return -1; + } + rtcdev = rtc; /* hold a reference so it doesn't go away */ get_device(dev); + ws = __ws; + __ws = NULL; } spin_unlock_irqrestore(&rtcdev_lock, flags); + + wakeup_source_unregister(__ws); + return 0; } @@ -860,7 +874,6 @@ static int __init alarmtimer_init(void) error = PTR_ERR(pdev); goto out_drv; } - ws = wakeup_source_register("alarmtimer"); return 0; out_drv: diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index a3bd5dbe0dc4..8585ad6e472a 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -799,7 +799,6 @@ static void check_thread_timers(struct task_struct *tsk, struct list_head *firing) { struct list_head *timers = tsk->cpu_timers; - struct signal_struct *const sig = tsk->signal; struct task_cputime *tsk_expires = &tsk->cputime_expires; u64 expires; unsigned long soft; @@ -823,10 +822,9 @@ static void check_thread_timers(struct task_struct *tsk, /* * Check for the special case thread timers. */ - soft = READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_cur); + soft = task_rlimit(tsk, RLIMIT_RTTIME); if (soft != RLIM_INFINITY) { - unsigned long hard = - READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); + unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME); if (hard != RLIM_INFINITY && tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { @@ -847,7 +845,8 @@ static void check_thread_timers(struct task_struct *tsk, */ if (soft < hard) { soft += USEC_PER_SEC; - sig->rlim[RLIMIT_RTTIME].rlim_cur = soft; + tsk->signal->rlim[RLIMIT_RTTIME].rlim_cur = + soft; } if (print_fatal_signals) { pr_info("RT Watchdog Timeout (soft): %s[%d]\n", @@ -938,11 +937,10 @@ static void check_process_timers(struct task_struct *tsk, SIGPROF); check_cpu_itimer(tsk, &sig->it[CPUCLOCK_VIRT], &virt_expires, utime, SIGVTALRM); - soft = READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_cur); + soft = task_rlimit(tsk, RLIMIT_CPU); if (soft != RLIM_INFINITY) { unsigned long psecs = div_u64(ptime, NSEC_PER_SEC); - unsigned long hard = - READ_ONCE(sig->rlim[RLIMIT_CPU].rlim_max); + unsigned long hard = task_rlimit_max(tsk, RLIMIT_CPU); u64 x; if (psecs >= hard) { /* diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index cedafa008de5..8ea4fb315719 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -637,9 +637,7 @@ static inline void tk_update_ktime_data(struct timekeeper *tk) tk->ktime_sec = seconds; /* Update the monotonic raw base */ - seconds = tk->raw_sec; - nsec = (u32)(tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift); - tk->tkr_raw.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); + tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ @@ -2066,7 +2064,7 @@ void update_wall_time(void) goto out; /* Do some additional sanity checking */ - timekeeping_check_update(real_tk, offset); + timekeeping_check_update(tk, offset); /* * With NO_HZ we may have to accumulate many cycle_intervals diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 71ce3f4eead3..f2674a056c26 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -203,6 +203,7 @@ struct timer_base { bool migration_enabled; bool nohz_active; bool is_idle; + bool must_forward_clk; DECLARE_BITMAP(pending_map, WHEEL_SIZE); struct hlist_head vectors[WHEEL_SIZE]; } ____cacheline_aligned; @@ -856,13 +857,19 @@ get_target_base(struct timer_base *base, unsigned tflags) static inline void forward_timer_base(struct timer_base *base) { - unsigned long jnow = READ_ONCE(jiffies); + unsigned long jnow; /* - * We only forward the base when it's idle and we have a delta between - * base clock and jiffies. + * We only forward the base when we are idle or have just come out of + * idle (must_forward_clk logic), and have a delta between base clock + * and jiffies. In the common case, run_timers will take care of it. */ - if (!base->is_idle || (long) (jnow - base->clk) < 2) + if (likely(!base->must_forward_clk)) + return; + + jnow = READ_ONCE(jiffies); + base->must_forward_clk = base->is_idle; + if ((long)(jnow - base->clk) < 2) return; /* @@ -938,6 +945,11 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * same array bucket then just return: */ if (timer_pending(timer)) { + /* + * The downside of this optimization is that it can result in + * larger granularity than you would get from adding a new + * timer with this expiry. + */ if (timer->expires == expires) return 1; @@ -948,6 +960,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) * dequeue/enqueue dance. */ base = lock_timer_base(timer, &flags); + forward_timer_base(base); clk = base->clk; idx = calc_wheel_index(expires, clk); @@ -964,6 +977,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) } } else { base = lock_timer_base(timer, &flags); + forward_timer_base(base); } ret = detach_if_pending(timer, base, false); @@ -991,12 +1005,10 @@ __mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) raw_spin_lock(&base->lock); WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | base->cpu); + forward_timer_base(base); } } - /* Try to forward a stale timer base clock */ - forward_timer_base(base); - timer->expires = expires; /* * If 'idx' was calculated above and the base time did not advance @@ -1112,6 +1124,7 @@ void add_timer_on(struct timer_list *timer, int cpu) WRITE_ONCE(timer->flags, (timer->flags & ~TIMER_BASEMASK) | cpu); } + forward_timer_base(base); debug_activate(timer, timer->expires); internal_add_timer(base, timer); @@ -1495,12 +1508,18 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) base->is_idle = false; } else { if (!is_max_delta) - expires = basem + (nextevt - basej) * TICK_NSEC; + expires = basem + (u64)(nextevt - basej) * TICK_NSEC; /* - * If we expect to sleep more than a tick, mark the base idle: + * If we expect to sleep more than a tick, mark the base idle. + * Also the tick is stopped so any added timer 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). */ - if ((expires - basem) > TICK_NSEC) + if ((expires - basem) > TICK_NSEC) { + base->must_forward_clk = true; base->is_idle = true; + } } raw_spin_unlock(&base->lock); @@ -1611,6 +1630,19 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + /* + * must_forward_clk must be cleared before running timers so that any + * timer functions that call mod_timer will not try to forward the + * base. idle trcking / clock forwarding logic is only used with + * BASE_STD timers. + * + * The deferrable base does not do idle tracking at all, so we do + * not forward it. This can result in very large variations in + * granularity for deferrable timers, but they can be deferred for + * long periods due to idle. + */ + base->must_forward_clk = false; + __run_timers(base); if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && base->nohz_active) __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); |