diff options
Diffstat (limited to 'kernel/time')
| -rw-r--r-- | kernel/time/alarmtimer.c | 9 | ||||
| -rw-r--r-- | kernel/time/clockevents.c | 2 | ||||
| -rw-r--r-- | kernel/time/clocksource.c | 47 | ||||
| -rw-r--r-- | kernel/time/hrtimer.c | 24 | ||||
| -rw-r--r-- | kernel/time/ntp.c | 19 | ||||
| -rw-r--r-- | kernel/time/ntp_internal.h | 4 | ||||
| -rw-r--r-- | kernel/time/posix-cpu-timers.c | 207 | ||||
| -rw-r--r-- | kernel/time/posix-timers.c | 73 | ||||
| -rw-r--r-- | kernel/time/posix-timers.h | 3 | ||||
| -rw-r--r-- | kernel/time/tick-broadcast.c | 3 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 6 | ||||
| -rw-r--r-- | kernel/time/timer.c | 66 | ||||
| -rw-r--r-- | kernel/time/timer_migration.c | 393 | ||||
| -rw-r--r-- | kernel/time/timer_migration.h | 27 |
14 files changed, 460 insertions, 423 deletions
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 5abfa4390673..8bf888641694 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -493,7 +493,7 @@ static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throt * promised in the context of posix_timer_fn() never * materialized, but someone should really work on it. * - * To prevent DOS fake @now to be 1 jiffie out which keeps + * To prevent DOS fake @now to be 1 jiffy out which keeps * the overrun accounting correct but creates an * inconsistency vs. timer_gettime(2). */ @@ -574,15 +574,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, it.alarm.alarmtimer); enum alarmtimer_restart result = ALARMTIMER_NORESTART; unsigned long flags; - int si_private = 0; spin_lock_irqsave(&ptr->it_lock, flags); - ptr->it_active = 0; - if (ptr->it_interval) - si_private = ++ptr->it_requeue_pending; - - if (posix_timer_event(ptr, si_private) && ptr->it_interval) { + if (posix_timer_queue_signal(ptr) && ptr->it_interval) { /* * Handle ignored signals and rearm the timer. This will go * away once we handle ignored signals proper. Ensure that diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 60a6484831b1..78c7bd64d0dd 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -190,7 +190,7 @@ int clockevents_tick_resume(struct clock_event_device *dev) #ifdef CONFIG_GENERIC_CLOCKEVENTS_MIN_ADJUST -/* Limit min_delta to a jiffie */ +/* Limit min_delta to a jiffy */ #define MIN_DELTA_LIMIT (NSEC_PER_SEC / HZ) /** diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index d25ba49e313c..23336eecb4f4 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -113,7 +113,6 @@ static u64 suspend_start; /* * Threshold: 0.0312s, when doubled: 0.0625s. - * Also a default for cs->uncertainty_margin when registering clocks. */ #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 5) @@ -125,6 +124,13 @@ static u64 suspend_start; * * The default of 500 parts per million is based on NTP's limits. * If a clocksource is good enough for NTP, it is good enough for us! + * + * In other words, by default, even if a clocksource is extremely + * precise (for example, with a sub-nanosecond period), the maximum + * permissible skew between the clocksource watchdog and the clocksource + * under test is not permitted to go below the 500ppm minimum defined + * by MAX_SKEW_USEC. This 500ppm minimum may be overridden using the + * CLOCKSOURCE_WATCHDOG_MAX_SKEW_US Kconfig option. */ #ifdef CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US #define MAX_SKEW_USEC CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US @@ -132,6 +138,13 @@ static u64 suspend_start; #define MAX_SKEW_USEC (125 * WATCHDOG_INTERVAL / HZ) #endif +/* + * Default for maximum permissible skew when cs->uncertainty_margin is + * not specified, and the lower bound even when cs->uncertainty_margin + * is specified. This is also the default that is used when registering + * clocks with unspecifed cs->uncertainty_margin, so this macro is used + * even in CONFIG_CLOCKSOURCE_WATCHDOG=n kernels. + */ #define WATCHDOG_MAX_SKEW (MAX_SKEW_USEC * NSEC_PER_USEC) #ifdef CONFIG_CLOCKSOURCE_WATCHDOG @@ -231,6 +244,7 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { + int64_t md = 2 * watchdog->uncertainty_margin; unsigned int nretries, max_retries; int64_t wd_delay, wd_seq_delay; u64 wd_end, wd_end2; @@ -245,8 +259,8 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, local_irq_enable(); wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end); - if (wd_delay <= WATCHDOG_MAX_SKEW) { - if (nretries > 1 || nretries >= max_retries) { + if (wd_delay <= md + cs->uncertainty_margin) { + if (nretries > 1 && nretries >= max_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", smp_processor_id(), watchdog->name, nretries); } @@ -258,12 +272,12 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, * there is too much external interferences that cause * significant delay in reading both clocksource and watchdog. * - * If consecutive WD read-back delay > WATCHDOG_MAX_SKEW/2, - * report system busy, reinit the watchdog and skip the current + * If consecutive WD read-back delay > md, report + * system busy, reinit the watchdog and skip the current * watchdog test. */ wd_seq_delay = cycles_to_nsec_safe(watchdog, wd_end, wd_end2); - if (wd_seq_delay > WATCHDOG_MAX_SKEW/2) + if (wd_seq_delay > md) goto skip_test; } @@ -1146,14 +1160,19 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq } /* - * If the uncertainty margin is not specified, calculate it. - * If both scale and freq are non-zero, calculate the clock - * period, but bound below at 2*WATCHDOG_MAX_SKEW. However, - * if either of scale or freq is zero, be very conservative and - * take the tens-of-milliseconds WATCHDOG_THRESHOLD value for the - * uncertainty margin. Allow stupidly small uncertainty margins - * to be specified by the caller for testing purposes, but warn - * to discourage production use of this capability. + * If the uncertainty margin is not specified, calculate it. If + * both scale and freq are non-zero, calculate the clock period, but + * bound below at 2*WATCHDOG_MAX_SKEW, that is, 500ppm by default. + * However, if either of scale or freq is zero, be very conservative + * and take the tens-of-milliseconds WATCHDOG_THRESHOLD value + * for the uncertainty margin. Allow stupidly small uncertainty + * margins to be specified by the caller for testing purposes, + * but warn to discourage production use of this capability. + * + * Bottom line: The sum of the uncertainty margins of the + * watchdog clocksource and the clocksource under test will be at + * least 500ppm by default. For more information, please see the + * comment preceding CONFIG_CLOCKSOURCE_WATCHDOG_MAX_SKEW_US above. */ if (scale && freq && !cs->uncertainty_margin) { cs->uncertainty_margin = NSEC_PER_SEC / (scale * freq); diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index b8ee320208d4..12eb40d6290e 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -1177,7 +1177,7 @@ static inline ktime_t hrtimer_update_lowres(struct hrtimer *timer, ktime_t tim, /* * CONFIG_TIME_LOW_RES indicates that the system has no way to return * granular time values. For relative timers we add hrtimer_resolution - * (i.e. one jiffie) to prevent short timeouts. + * (i.e. one jiffy) to prevent short timeouts. */ timer->is_rel = mode & HRTIMER_MODE_REL; if (timer->is_rel) @@ -1351,11 +1351,13 @@ static void hrtimer_cpu_base_init_expiry_lock(struct hrtimer_cpu_base *base) } static void hrtimer_cpu_base_lock_expiry(struct hrtimer_cpu_base *base) + __acquires(&base->softirq_expiry_lock) { spin_lock(&base->softirq_expiry_lock); } static void hrtimer_cpu_base_unlock_expiry(struct hrtimer_cpu_base *base) + __releases(&base->softirq_expiry_lock) { spin_unlock(&base->softirq_expiry_lock); } @@ -1757,7 +1759,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, } } -static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) +static __latent_entropy void hrtimer_run_softirq(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); unsigned long flags; @@ -2072,14 +2074,9 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode, struct restart_block *restart; struct hrtimer_sleeper t; int ret = 0; - u64 slack; - - slack = current->timer_slack_ns; - if (rt_task(current)) - slack = 0; hrtimer_init_sleeper_on_stack(&t, clockid, mode); - hrtimer_set_expires_range_ns(&t.timer, rqtp, slack); + hrtimer_set_expires_range_ns(&t.timer, rqtp, current->timer_slack_ns); ret = do_nanosleep(&t, mode); if (ret != -ERESTART_RESTARTBLOCK) goto out; @@ -2249,7 +2246,7 @@ void __init hrtimers_init(void) /** * schedule_hrtimeout_range_clock - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks + * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * @clock_id: timer clock to be used */ @@ -2276,13 +2273,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, u64 delta, return -EINTR; } - /* - * Override any slack passed by the user if under - * rt contraints. - */ - if (rt_task(current)) - delta = 0; - hrtimer_init_sleeper_on_stack(&t, clock_id, mode); hrtimer_set_expires_range_ns(&t.timer, *expires, delta); hrtimer_sleeper_start_expires(&t, mode); @@ -2302,7 +2292,7 @@ EXPORT_SYMBOL_GPL(schedule_hrtimeout_range_clock); /** * schedule_hrtimeout_range - sleep until timeout * @expires: timeout value (ktime_t) - * @delta: slack in expires timeout (ktime_t) for SCHED_OTHER tasks + * @delta: slack in expires timeout (ktime_t) * @mode: timer mode * * Make the current task sleep until the given expiry time has diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 406dccb79c2b..802b336f4b8c 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -660,9 +660,17 @@ rearm: sched_sync_hw_clock(offset_nsec, res != 0); } -void ntp_notify_cmos_timer(void) +void ntp_notify_cmos_timer(bool offset_set) { /* + * If the time jumped (using ADJ_SETOFFSET) cancels sync timer, + * which may have been running if the time was synchronized + * prior to the ADJ_SETOFFSET call. + */ + if (offset_set) + hrtimer_cancel(&sync_hrtimer); + + /* * When the work is currently executed but has not yet the timer * rearmed this queues the work immediately again. No big issue, * just a pointless work scheduled. @@ -727,17 +735,16 @@ static inline void process_adjtimex_modes(const struct __kernel_timex *txc, } if (txc->modes & ADJ_MAXERROR) - time_maxerror = txc->maxerror; + time_maxerror = clamp(txc->maxerror, 0, NTP_PHASE_LIMIT); if (txc->modes & ADJ_ESTERROR) - time_esterror = txc->esterror; + time_esterror = clamp(txc->esterror, 0, NTP_PHASE_LIMIT); if (txc->modes & ADJ_TIMECONST) { - time_constant = txc->constant; + time_constant = clamp(txc->constant, 0, MAXTC); if (!(time_status & STA_NANO)) time_constant += 4; - time_constant = min(time_constant, (long)MAXTC); - time_constant = max(time_constant, 0l); + time_constant = clamp(time_constant, 0, MAXTC); } if (txc->modes & ADJ_TAI && diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index 23d1b74c3065..5a633dce9057 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -14,9 +14,9 @@ extern int __do_adjtimex(struct __kernel_timex *txc, extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #if defined(CONFIG_GENERIC_CMOS_UPDATE) || defined(CONFIG_RTC_SYSTOHC) -extern void ntp_notify_cmos_timer(void); +extern void ntp_notify_cmos_timer(bool offset_set); #else -static inline void ntp_notify_cmos_timer(void) { } +static inline void ntp_notify_cmos_timer(bool offset_set) { } #endif #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index e9c6f9d0e42c..6bcee4704059 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -453,6 +453,7 @@ static void disarm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; struct posix_cputimer_base *base; + timer->it_active = 0; if (!cpu_timer_dequeue(ctmr)) return; @@ -559,6 +560,7 @@ static void arm_timer(struct k_itimer *timer, struct task_struct *p) struct cpu_timer *ctmr = &timer->it.cpu; u64 newexp = cpu_timer_getexpires(ctmr); + timer->it_active = 1; if (!cpu_timer_enqueue(&base->tqhead, ctmr)) return; @@ -584,12 +586,8 @@ static void cpu_timer_fire(struct k_itimer *timer) { struct cpu_timer *ctmr = &timer->it.cpu; - if ((timer->it_sigev_notify & ~SIGEV_THREAD_ID) == SIGEV_NONE) { - /* - * User don't want any signal. - */ - cpu_timer_setexpires(ctmr, 0); - } else if (unlikely(timer->sigq == NULL)) { + timer->it_active = 0; + if (unlikely(timer->sigq == NULL)) { /* * This a special case for clock_nanosleep, * not a normal timer from sys_timer_create. @@ -600,9 +598,9 @@ static void cpu_timer_fire(struct k_itimer *timer) /* * One-shot timer. Clear it as soon as it's fired. */ - posix_timer_event(timer, 0); + posix_timer_queue_signal(timer); cpu_timer_setexpires(ctmr, 0); - } else if (posix_timer_event(timer, ++timer->it_requeue_pending)) { + } else if (posix_timer_queue_signal(timer)) { /* * The signal did not get queued because the signal * was ignored, so we won't get any callback to @@ -614,6 +612,8 @@ static void cpu_timer_fire(struct k_itimer *timer) } } +static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now); + /* * Guts of sys_timer_settime for CPU timers. * This is called with the timer locked and interrupts disabled. @@ -623,9 +623,10 @@ static void cpu_timer_fire(struct k_itimer *timer) static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, struct itimerspec64 *new, struct itimerspec64 *old) { + bool sigev_none = timer->it_sigev_notify == SIGEV_NONE; clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); - u64 old_expires, new_expires, old_incr, val; struct cpu_timer *ctmr = &timer->it.cpu; + u64 old_expires, new_expires, now; struct sighand_struct *sighand; struct task_struct *p; unsigned long flags; @@ -662,10 +663,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, return -ESRCH; } - /* - * Disarm any old timer after extracting its expiry time. - */ - old_incr = timer->it_interval; + /* Retrieve the current expiry time before disarming the timer */ old_expires = cpu_timer_getexpires(ctmr); if (unlikely(timer->it.cpu.firing)) { @@ -673,157 +671,122 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, ret = TIMER_RETRY; } else { cpu_timer_dequeue(ctmr); + timer->it_active = 0; } /* - * We need to sample the current value to convert the new - * value from to relative and absolute, and to convert the - * old value from absolute to relative. To set a process - * timer, we need a sample to balance the thread expiry - * times (in arm_timer). With an absolute time, we must - * check if it's already passed. In short, we need a sample. + * Sample the current clock for saving the previous setting + * and for rearming the timer. */ if (CPUCLOCK_PERTHREAD(timer->it_clock)) - val = cpu_clock_sample(clkid, p); + now = cpu_clock_sample(clkid, p); else - val = cpu_clock_sample_group(clkid, p, true); + now = cpu_clock_sample_group(clkid, p, !sigev_none); + /* Retrieve the previous expiry value if requested. */ if (old) { - if (old_expires == 0) { - old->it_value.tv_sec = 0; - old->it_value.tv_nsec = 0; - } else { - /* - * Update the timer in case it has overrun already. - * If it has, we'll report it as having overrun and - * with the next reloaded timer already ticking, - * though we are swallowing that pending - * notification here to install the new setting. - */ - u64 exp = bump_cpu_timer(timer, val); - - if (val < exp) { - old_expires = exp - val; - old->it_value = ns_to_timespec64(old_expires); - } else { - old->it_value.tv_nsec = 1; - old->it_value.tv_sec = 0; - } - } + old->it_value = (struct timespec64){ }; + if (old_expires) + __posix_cpu_timer_get(timer, old, now); } + /* Retry if the timer expiry is running concurrently */ if (unlikely(ret)) { - /* - * We are colliding with the timer actually firing. - * Punt after filling in the timer's old value, and - * disable this firing since we are already reporting - * it as an overrun (thanks to bump_cpu_timer above). - */ unlock_task_sighand(p, &flags); goto out; } - if (new_expires != 0 && !(timer_flags & TIMER_ABSTIME)) { - new_expires += val; - } + /* Convert relative expiry time to absolute */ + if (new_expires && !(timer_flags & TIMER_ABSTIME)) + new_expires += now; + + /* Set the new expiry time (might be 0) */ + cpu_timer_setexpires(ctmr, new_expires); /* - * Install the new expiry time (or zero). - * For a timer with no notification action, we don't actually - * arm the timer (we'll just fake it for timer_gettime). + * Arm the timer if it is not disabled, the new expiry value has + * not yet expired and the timer requires signal delivery. + * SIGEV_NONE timers are never armed. In case the timer is not + * armed, enforce the reevaluation of the timer base so that the + * process wide cputime counter can be disabled eventually. */ - cpu_timer_setexpires(ctmr, new_expires); - if (new_expires != 0 && val < new_expires) { - arm_timer(timer, p); + if (likely(!sigev_none)) { + if (new_expires && now < new_expires) + arm_timer(timer, p); + else + trigger_base_recalc_expires(timer, p); } unlock_task_sighand(p, &flags); + + posix_timer_set_common(timer, new); + /* - * Install the new reload setting, and - * set up the signal and overrun bookkeeping. + * If the new expiry time was already in the past the timer was not + * queued. Fire it immediately even if the thread never runs to + * accumulate more time on this clock. */ - timer->it_interval = timespec64_to_ktime(new->it_interval); + if (!sigev_none && new_expires && now >= new_expires) + cpu_timer_fire(timer); +out: + rcu_read_unlock(); + return ret; +} + +static void __posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp, u64 now) +{ + bool sigev_none = timer->it_sigev_notify == SIGEV_NONE; + u64 expires, iv = timer->it_interval; /* - * This acts as a modification timestamp for the timer, - * so any automatic reload attempt will punt on seeing - * that we have reset the timer manually. + * Make sure that interval timers are moved forward for the + * following cases: + * - SIGEV_NONE timers which are never armed + * - Timers which expired, but the signal has not yet been + * delivered */ - timer->it_requeue_pending = (timer->it_requeue_pending + 2) & - ~REQUEUE_PENDING; - timer->it_overrun_last = 0; - timer->it_overrun = -1; - - if (val >= new_expires) { - if (new_expires != 0) { - /* - * The designated time already passed, so we notify - * immediately, even if the thread never runs to - * accumulate more time on this clock. - */ - cpu_timer_fire(timer); - } + if (iv && ((timer->it_requeue_pending & REQUEUE_PENDING) || sigev_none)) + expires = bump_cpu_timer(timer, now); + else + expires = cpu_timer_getexpires(&timer->it.cpu); + /* + * Expired interval timers cannot have a remaining time <= 0. + * The kernel has to move them forward so that the next + * timer expiry is > @now. + */ + if (now < expires) { + itp->it_value = ns_to_timespec64(expires - now); + } else { /* - * Make sure we don't keep around the process wide cputime - * counter or the tick dependency if they are not necessary. + * A single shot SIGEV_NONE timer must return 0, when it is + * expired! Timers which have a real signal delivery mode + * must return a remaining time greater than 0 because the + * signal has not yet been delivered. */ - sighand = lock_task_sighand(p, &flags); - if (!sighand) - goto out; - - if (!cpu_timer_queued(ctmr)) - trigger_base_recalc_expires(timer, p); - - unlock_task_sighand(p, &flags); + if (!sigev_none) + itp->it_value.tv_nsec = 1; } - out: - rcu_read_unlock(); - if (old) - old->it_interval = ns_to_timespec64(old_incr); - - return ret; } static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp) { clockid_t clkid = CPUCLOCK_WHICH(timer->it_clock); - struct cpu_timer *ctmr = &timer->it.cpu; - u64 now, expires = cpu_timer_getexpires(ctmr); struct task_struct *p; + u64 now; rcu_read_lock(); p = cpu_timer_task_rcu(timer); - if (!p) - goto out; + if (p && cpu_timer_getexpires(&timer->it.cpu)) { + itp->it_interval = ktime_to_timespec64(timer->it_interval); - /* - * Easy part: convert the reload time. - */ - itp->it_interval = ktime_to_timespec64(timer->it_interval); - - if (!expires) - goto out; - - /* - * Sample the clock to take the difference with the expiry time. - */ - if (CPUCLOCK_PERTHREAD(timer->it_clock)) - now = cpu_clock_sample(clkid, p); - else - now = cpu_clock_sample_group(clkid, p, false); + if (CPUCLOCK_PERTHREAD(timer->it_clock)) + now = cpu_clock_sample(clkid, p); + else + now = cpu_clock_sample_group(clkid, p, false); - if (now < expires) { - itp->it_value = ns_to_timespec64(expires - now); - } else { - /* - * The timer should have expired already, but the firing - * hasn't taken place yet. Say it's just about to expire. - */ - itp->it_value.tv_nsec = 1; - itp->it_value.tv_sec = 0; + __posix_cpu_timer_get(timer, itp, now); } -out: rcu_read_unlock(); } diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index b924f0f096fa..4576aaed13b2 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -277,10 +277,17 @@ void posixtimer_rearm(struct kernel_siginfo *info) unlock_timer(timr, flags); } -int posix_timer_event(struct k_itimer *timr, int si_private) +int posix_timer_queue_signal(struct k_itimer *timr) { + int ret, si_private = 0; enum pid_type type; - int ret; + + lockdep_assert_held(&timr->it_lock); + + timr->it_active = 0; + if (timr->it_interval) + si_private = ++timr->it_requeue_pending; + /* * FIXME: if ->sigq is queued we can race with * dequeue_signal()->posixtimer_rearm(). @@ -309,19 +316,13 @@ int posix_timer_event(struct k_itimer *timr, int si_private) */ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) { + struct k_itimer *timr = container_of(timer, struct k_itimer, it.real.timer); enum hrtimer_restart ret = HRTIMER_NORESTART; - struct k_itimer *timr; unsigned long flags; - int si_private = 0; - timr = container_of(timer, struct k_itimer, it.real.timer); spin_lock_irqsave(&timr->it_lock, flags); - timr->it_active = 0; - if (timr->it_interval != 0) - si_private = ++timr->it_requeue_pending; - - if (posix_timer_event(timr, si_private)) { + if (posix_timer_queue_signal(timr)) { /* * The signal was not queued due to SIG_IGN. As a * consequence the timer is not going to be rearmed from @@ -338,14 +339,14 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer) * change to the signal handling code. * * For now let timers with an interval less than a - * jiffie expire every jiffie and recheck for a + * jiffy expire every jiffy and recheck for a * valid signal handler. * * This avoids interrupt starvation in case of a * very small interval, which would expire the * timer immediately again. * - * Moving now ahead of time by one jiffie tricks + * Moving now ahead of time by one jiffy tricks * hrtimer_forward() to expire the timer later, * while it still maintains the overrun accuracy * for the price of a slight inconsistency in the @@ -515,7 +516,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event, spin_lock_irq(¤t->sighand->siglock); /* This makes the timer valid in the hash table */ WRITE_ONCE(new_timer->it_signal, current->signal); - list_add(&new_timer->list, ¤t->signal->posix_timers); + hlist_add_head(&new_timer->list, ¤t->signal->posix_timers); spin_unlock_irq(¤t->sighand->siglock); /* * After unlocking sighand::siglock @new_timer is subject to @@ -856,6 +857,23 @@ static struct k_itimer *timer_wait_running(struct k_itimer *timer, return lock_timer(timer_id, flags); } +/* + * Set up the new interval and reset the signal delivery data + */ +void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting) +{ + if (new_setting->it_value.tv_sec || new_setting->it_value.tv_nsec) + timer->it_interval = timespec64_to_ktime(new_setting->it_interval); + else + timer->it_interval = 0; + + /* Prevent reloading in case there is a signal pending */ + timer->it_requeue_pending = (timer->it_requeue_pending + 2) & ~REQUEUE_PENDING; + /* Reset overrun accounting */ + timer->it_overrun_last = 0; + timer->it_overrun = -1LL; +} + /* Set a POSIX.1b interval timer. */ int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec64 *new_setting, @@ -878,15 +896,12 @@ int common_timer_set(struct k_itimer *timr, int flags, return TIMER_RETRY; timr->it_active = 0; - timr->it_requeue_pending = (timr->it_requeue_pending + 2) & - ~REQUEUE_PENDING; - timr->it_overrun_last = 0; + posix_timer_set_common(timr, new_setting); - /* Switch off the timer when it_value is zero */ + /* Keep timer disarmed when it_value is zero */ if (!new_setting->it_value.tv_sec && !new_setting->it_value.tv_nsec) return 0; - timr->it_interval = timespec64_to_ktime(new_setting->it_interval); expires = timespec64_to_ktime(new_setting->it_value); if (flags & TIMER_ABSTIME) expires = timens_ktime_to_host(timr->it_clock, expires); @@ -904,7 +919,7 @@ static int do_timer_settime(timer_t timer_id, int tmr_flags, const struct k_clock *kc; struct k_itimer *timr; unsigned long flags; - int error = 0; + int error; if (!timespec64_valid(&new_spec64->it_interval) || !timespec64_valid(&new_spec64->it_value)) @@ -918,6 +933,9 @@ retry: if (!timr) return -EINVAL; + if (old_spec64) + old_spec64->it_interval = ktime_to_timespec64(timr->it_interval); + kc = timr->kclock; if (WARN_ON_ONCE(!kc || !kc->timer_set)) error = -EINVAL; @@ -1021,7 +1039,7 @@ retry_delete: } spin_lock(¤t->sighand->siglock); - list_del(&timer->list); + hlist_del(&timer->list); spin_unlock(¤t->sighand->siglock); /* * A concurrent lookup could check timer::it_signal lockless. It @@ -1071,7 +1089,7 @@ retry_delete: goto retry_delete; } - list_del(&timer->list); + hlist_del(&timer->list); /* * Setting timer::it_signal to NULL is technically not required @@ -1092,22 +1110,19 @@ retry_delete: */ void exit_itimers(struct task_struct *tsk) { - struct list_head timers; - struct k_itimer *tmr; + struct hlist_head timers; - if (list_empty(&tsk->signal->posix_timers)) + if (hlist_empty(&tsk->signal->posix_timers)) return; /* Protect against concurrent read via /proc/$PID/timers */ spin_lock_irq(&tsk->sighand->siglock); - list_replace_init(&tsk->signal->posix_timers, &timers); + hlist_move_list(&tsk->signal->posix_timers, &timers); spin_unlock_irq(&tsk->sighand->siglock); /* The timers are not longer accessible via tsk::signal */ - while (!list_empty(&timers)) { - tmr = list_first_entry(&timers, struct k_itimer, list); - itimer_delete(tmr); - } + while (!hlist_empty(&timers)) + itimer_delete(hlist_entry(timers.first, struct k_itimer, list)); } SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index f32a2ebba9b8..4784ea65f685 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -36,10 +36,11 @@ extern const struct k_clock clock_process; extern const struct k_clock clock_thread; extern const struct k_clock alarm_clock; -int posix_timer_event(struct k_itimer *timr, int si_private); +int posix_timer_queue_signal(struct k_itimer *timr); void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting); int common_timer_set(struct k_itimer *timr, int flags, struct itimerspec64 *new_setting, struct itimerspec64 *old_setting); +void posix_timer_set_common(struct k_itimer *timer, struct itimerspec64 *new_setting); int common_timer_del(struct k_itimer *timer); diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index b4843099a8da..ed58eebb4e8f 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -1141,7 +1141,6 @@ void tick_broadcast_switch_to_oneshot(void) #ifdef CONFIG_HOTPLUG_CPU void hotplug_cpu__broadcast_tick_pull(int deadcpu) { - struct tick_device *td = this_cpu_ptr(&tick_cpu_device); struct clock_event_device *bc; unsigned long flags; @@ -1167,6 +1166,8 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) * device to avoid the starvation. */ if (tick_check_broadcast_expired()) { + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask); tick_program_event(td->evtdev->next_event, 1); } diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 2fa87dcfeda9..7e6f409bf311 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -2553,6 +2553,7 @@ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; + bool offset_set = false; bool clock_set = false; struct timespec64 ts; unsigned long flags; @@ -2575,6 +2576,7 @@ int do_adjtimex(struct __kernel_timex *txc) if (ret) return ret; + offset_set = delta.tv_sec != 0; audit_tk_injoffset(delta); } @@ -2606,9 +2608,9 @@ int do_adjtimex(struct __kernel_timex *txc) clock_set |= timekeeping_advance(TK_ADV_FREQ); if (clock_set) - clock_was_set(CLOCK_REALTIME); + clock_was_set(CLOCK_SET_WALL); - ntp_notify_cmos_timer(); + ntp_notify_cmos_timer(offset_set); return ret; } diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 48288dd4a102..0fc9d066a7be 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -289,7 +289,7 @@ static void timers_update_migration(void) } #ifdef CONFIG_SYSCTL -static int timer_migration_handler(struct ctl_table *table, int write, +static int timer_migration_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -365,7 +365,7 @@ static unsigned long round_jiffies_common(unsigned long j, int cpu, rem = j % HZ; /* - * If the target jiffie is just after a whole second (which can happen + * If the target jiffy is just after a whole second (which can happen * due to delays of the timer irq, long irq off times etc etc) then * we should round down to the whole second, not up. Use 1/4th second * as cutoff for this rounding as an extreme upper bound for this. @@ -672,7 +672,7 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, * Set the next expiry time and kick the CPU so it * can reevaluate the wheel: */ - base->next_expiry = bucket_expiry; + WRITE_ONCE(base->next_expiry, bucket_expiry); base->timers_pending = true; base->next_expiry_recalc = false; trigger_dyntick_cpu(base, timer); @@ -1561,6 +1561,8 @@ static inline void timer_base_unlock_expiry(struct timer_base *base) * the waiter to acquire the lock and make progress. */ static void timer_sync_wait_running(struct timer_base *base) + __releases(&base->lock) __releases(&base->expiry_lock) + __acquires(&base->expiry_lock) __acquires(&base->lock) { if (atomic_read(&base->timer_waiters)) { raw_spin_unlock_irq(&base->lock); @@ -1898,7 +1900,7 @@ static int next_pending_bucket(struct timer_base *base, unsigned offset, * * Store next expiry time in base->next_expiry. */ -static void next_expiry_recalc(struct timer_base *base) +static void timer_recalc_next_expiry(struct timer_base *base) { unsigned long clk, next, adj; unsigned lvl, offset = 0; @@ -1928,7 +1930,7 @@ static void next_expiry_recalc(struct timer_base *base) * bits are zero, we look at the next level as is. If not we * need to advance it by one because that's going to be the * next expiring bucket in that level. base->clk is the next - * expiring jiffie. So in case of: + * expiring jiffy. So in case of: * * LVL5 LVL4 LVL3 LVL2 LVL1 LVL0 * 0 0 0 0 0 0 @@ -1964,7 +1966,7 @@ static void next_expiry_recalc(struct timer_base *base) clk += adj; } - base->next_expiry = next; + WRITE_ONCE(base->next_expiry, next); base->next_expiry_recalc = false; base->timers_pending = !(next == base->clk + NEXT_TIMER_MAX_DELTA); } @@ -1993,7 +1995,7 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) return basem; /* - * Round up to the next jiffie. High resolution timers are + * Round up to the next jiffy. High resolution timers are * off, so the hrtimers are expired in the tick and we need to * make sure that this tick really expires the timer to avoid * a ping pong of the nohz stop code. @@ -2007,7 +2009,7 @@ static unsigned long next_timer_interrupt(struct timer_base *base, unsigned long basej) { if (base->next_expiry_recalc) - next_expiry_recalc(base); + timer_recalc_next_expiry(base); /* * Move next_expiry for the empty base into the future to prevent an @@ -2018,7 +2020,7 @@ static unsigned long next_timer_interrupt(struct timer_base *base, * easy comparable to find out which base holds the first pending timer. */ if (!base->timers_pending) - base->next_expiry = basej + NEXT_TIMER_MAX_DELTA; + WRITE_ONCE(base->next_expiry, basej + NEXT_TIMER_MAX_DELTA); return base->next_expiry; } @@ -2252,7 +2254,7 @@ static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, base_global, &tevt); /* - * If the next event is only one jiffie ahead there is no need to call + * If the next event is only one jiffy ahead there is no need to call * timer migration hierarchy related functions. The value for the next * global timer in @tevt struct equals then KTIME_MAX. This is also * true, when the timer base is idle. @@ -2411,7 +2413,7 @@ static inline void __run_timers(struct timer_base *base) * jiffies to avoid endless requeuing to current jiffies. */ base->clk++; - next_expiry_recalc(base); + timer_recalc_next_expiry(base); while (levels--) expire_timers(base, heads + levels); @@ -2440,7 +2442,7 @@ static void run_timer_base(int index) /* * This function runs timers and the timer-tq in bottom half context. */ -static __latent_entropy void run_timer_softirq(struct softirq_action *h) +static __latent_entropy void run_timer_softirq(void) { run_timer_base(BASE_LOCAL); if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { @@ -2462,8 +2464,40 @@ static void run_local_timers(void) hrtimer_run_queues(); for (int i = 0; i < NR_BASES; i++, base++) { - /* Raise the softirq only if required. */ - if (time_after_eq(jiffies, base->next_expiry) || + /* + * Raise the softirq only if required. + * + * timer_base::next_expiry can be written by a remote CPU while + * holding the lock. If this write happens at the same time than + * the lockless local read, sanity checker could complain about + * data corruption. + * + * There are two possible situations where + * timer_base::next_expiry is written by a remote CPU: + * + * 1. Remote CPU expires global timers of this CPU and updates + * timer_base::next_expiry of BASE_GLOBAL afterwards in + * next_timer_interrupt() or timer_recalc_next_expiry(). The + * worst outcome is a superfluous raise of the timer softirq + * when the not yet updated value is read. + * + * 2. A new first pinned timer is enqueued by a remote CPU + * and therefore timer_base::next_expiry of BASE_LOCAL is + * updated. When this update is missed, this isn't a + * problem, as an IPI is executed nevertheless when the CPU + * was idle before. When the CPU wasn't idle but the update + * is missed, then the timer would expire one jiffy late - + * bad luck. + * + * Those unlikely corner cases where the worst outcome is only a + * one jiffy delay or a superfluous raise of the softirq are + * not that expensive as doing the check always while holding + * the lock. + * + * Possible remote writers are using WRITE_ONCE(). Local reader + * uses therefore READ_ONCE(). + */ + if (time_after_eq(jiffies, READ_ONCE(base->next_expiry)) || (i == BASE_DEF && tmigr_requires_handle_remote())) { raise_softirq(TIMER_SOFTIRQ); return; @@ -2730,7 +2764,7 @@ void __init init_timers(void) */ void msleep(unsigned int msecs) { - unsigned long timeout = msecs_to_jiffies(msecs) + 1; + unsigned long timeout = msecs_to_jiffies(msecs); while (timeout) timeout = schedule_timeout_uninterruptible(timeout); @@ -2744,7 +2778,7 @@ EXPORT_SYMBOL(msleep); */ unsigned long msleep_interruptible(unsigned int msecs) { - unsigned long timeout = msecs_to_jiffies(msecs) + 1; + unsigned long timeout = msecs_to_jiffies(msecs); while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c index 84413114db5c..8d57f7686bb0 100644 --- a/kernel/time/timer_migration.c +++ b/kernel/time/timer_migration.c @@ -475,9 +475,54 @@ static bool tmigr_check_lonely(struct tmigr_group *group) return bitmap_weight(&active, BIT_CNT) <= 1; } -typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *); +/** + * struct tmigr_walk - data required for walking the hierarchy + * @nextexp: Next CPU event expiry information which is handed into + * the timer migration code by the timer code + * (get_next_timer_interrupt()) + * @firstexp: Contains the first event expiry information when + * hierarchy is completely idle. When CPU itself was the + * last going idle, information makes sure, that CPU will + * be back in time. When using this value in the remote + * expiry case, firstexp is stored in the per CPU tmigr_cpu + * struct of CPU which expires remote timers. It is updated + * in top level group only. Be aware, there could occur a + * new top level of the hierarchy between the 'top level + * call' in tmigr_update_events() and the check for the + * parent group in walk_groups(). Then @firstexp might + * contain a value != KTIME_MAX even if it was not the + * final top level. This is not a problem, as the worst + * outcome is a CPU which might wake up a little early. + * @evt: Pointer to tmigr_event which needs to be queued (of idle + * child group) + * @childmask: groupmask of child group + * @remote: Is set, when the new timer path is executed in + * tmigr_handle_remote_cpu() + * @basej: timer base in jiffies + * @now: timer base monotonic + * @check: is set if there is the need to handle remote timers; + * required in tmigr_requires_handle_remote() only + * @tmc_active: this flag indicates, whether the CPU which triggers + * the hierarchy walk is !idle in the timer migration + * hierarchy. When the CPU is idle and the whole hierarchy is + * idle, only the first event of the top level has to be + * considered. + */ +struct tmigr_walk { + u64 nextexp; + u64 firstexp; + struct tmigr_event *evt; + u8 childmask; + bool remote; + unsigned long basej; + u64 now; + bool check; + bool tmc_active; +}; + +typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, struct tmigr_walk *); -static void __walk_groups(up_f up, void *data, +static void __walk_groups(up_f up, struct tmigr_walk *data, struct tmigr_cpu *tmc) { struct tmigr_group *child = NULL, *group = tmc->tmgroup; @@ -490,64 +535,17 @@ static void __walk_groups(up_f up, void *data, child = group; group = group->parent; + data->childmask = child->groupmask; } while (group); } -static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc) +static void walk_groups(up_f up, struct tmigr_walk *data, struct tmigr_cpu *tmc) { lockdep_assert_held(&tmc->lock); __walk_groups(up, data, tmc); } -/** - * struct tmigr_walk - data required for walking the hierarchy - * @nextexp: Next CPU event expiry information which is handed into - * the timer migration code by the timer code - * (get_next_timer_interrupt()) - * @firstexp: Contains the first event expiry information when last - * active CPU of hierarchy is on the way to idle to make - * sure CPU will be back in time. - * @evt: Pointer to tmigr_event which needs to be queued (of idle - * child group) - * @childmask: childmask of child group - * @remote: Is set, when the new timer path is executed in - * tmigr_handle_remote_cpu() - */ -struct tmigr_walk { - u64 nextexp; - u64 firstexp; - struct tmigr_event *evt; - u8 childmask; - bool remote; -}; - -/** - * struct tmigr_remote_data - data required for remote expiry hierarchy walk - * @basej: timer base in jiffies - * @now: timer base monotonic - * @firstexp: returns expiry of the first timer in the idle timer - * migration hierarchy to make sure the timer is handled in - * time; it is stored in the per CPU tmigr_cpu struct of - * CPU which expires remote timers - * @childmask: childmask of child group - * @check: is set if there is the need to handle remote timers; - * required in tmigr_requires_handle_remote() only - * @tmc_active: this flag indicates, whether the CPU which triggers - * the hierarchy walk is !idle in the timer migration - * hierarchy. When the CPU is idle and the whole hierarchy is - * idle, only the first event of the top level has to be - * considered. - */ -struct tmigr_remote_data { - unsigned long basej; - u64 now; - u64 firstexp; - u8 childmask; - bool check; - bool tmc_active; -}; - /* * Returns the next event of the timerqueue @group->events * @@ -618,10 +616,9 @@ static u64 tmigr_next_groupevt_expires(struct tmigr_group *group) static bool tmigr_active_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { union tmigr_state curstate, newstate; - struct tmigr_walk *data = ptr; bool walk_done; u8 childmask; @@ -649,8 +646,7 @@ static bool tmigr_active_up(struct tmigr_group *group, } while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)); - if ((walk_done == false) && group->parent) - data->childmask = group->childmask; + trace_tmigr_group_set_cpu_active(group, newstate, childmask); /* * The group is active (again). The group event might be still queued @@ -666,8 +662,6 @@ static bool tmigr_active_up(struct tmigr_group *group, */ group->groupevt.ignore = true; - trace_tmigr_group_set_cpu_active(group, newstate, childmask); - return walk_done; } @@ -675,7 +669,7 @@ static void __tmigr_cpu_activate(struct tmigr_cpu *tmc) { struct tmigr_walk data; - data.childmask = tmc->childmask; + data.childmask = tmc->groupmask; trace_tmigr_cpu_active(tmc); @@ -860,10 +854,8 @@ unlock: static bool tmigr_new_timer_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { - struct tmigr_walk *data = ptr; - return tmigr_update_events(group, child, data); } @@ -995,9 +987,8 @@ unlock: static bool tmigr_handle_remote_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { - struct tmigr_remote_data *data = ptr; struct tmigr_event *evt; unsigned long jif; u8 childmask; @@ -1034,12 +1025,10 @@ again: } /* - * Update of childmask for the next level and keep track of the expiry - * of the first event that needs to be handled (group->next_expiry was - * updated by tmigr_next_expired_groupevt(), next was set by - * tmigr_handle_remote_cpu()). + * Keep track of the expiry of the first event that needs to be handled + * (group->next_expiry was updated by tmigr_next_expired_groupevt(), + * next was set by tmigr_handle_remote_cpu()). */ - data->childmask = group->childmask; data->firstexp = group->next_expiry; raw_spin_unlock_irq(&group->lock); @@ -1055,12 +1044,12 @@ again: void tmigr_handle_remote(void) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - struct tmigr_remote_data data; + struct tmigr_walk data; if (tmigr_is_not_available(tmc)) return; - data.childmask = tmc->childmask; + data.childmask = tmc->groupmask; data.firstexp = KTIME_MAX; /* @@ -1068,7 +1057,7 @@ void tmigr_handle_remote(void) * in tmigr_handle_remote_up() anyway. Keep this check to speed up the * return when nothing has to be done. */ - if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) { + if (!tmigr_check_migrator(tmc->tmgroup, tmc->groupmask)) { /* * If this CPU was an idle migrator, make sure to clear its wakeup * value so it won't chase timers that have already expired elsewhere. @@ -1097,9 +1086,8 @@ void tmigr_handle_remote(void) static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { - struct tmigr_remote_data *data = ptr; u8 childmask; childmask = data->childmask; @@ -1118,7 +1106,7 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, * group before reading the next_expiry value. */ if (group->parent && !data->tmc_active) - goto out; + return false; /* * The lock is required on 32bit architectures to read the variable @@ -1143,9 +1131,6 @@ static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, raw_spin_unlock(&group->lock); } -out: - /* Update of childmask for the next level */ - data->childmask = group->childmask; return false; } @@ -1157,7 +1142,7 @@ out: bool tmigr_requires_handle_remote(void) { struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - struct tmigr_remote_data data; + struct tmigr_walk data; unsigned long jif; bool ret = false; @@ -1165,7 +1150,7 @@ bool tmigr_requires_handle_remote(void) return ret; data.now = get_jiffies_update(&jif); - data.childmask = tmc->childmask; + data.childmask = tmc->groupmask; data.firstexp = KTIME_MAX; data.tmc_active = !tmc->idle; data.check = false; @@ -1230,14 +1215,13 @@ u64 tmigr_cpu_new_timer(u64 nextexp) if (nextexp != tmc->cpuevt.nextevt.expires || tmc->cpuevt.ignore) { ret = tmigr_new_timer(tmc, nextexp); + /* + * Make sure the reevaluation of timers in idle path + * will not miss an event. + */ + WRITE_ONCE(tmc->wakeup, ret); } } - /* - * Make sure the reevaluation of timers in idle path will not miss an - * event. - */ - WRITE_ONCE(tmc->wakeup, ret); - trace_tmigr_cpu_new_timer_idle(tmc, nextexp); raw_spin_unlock(&tmc->lock); return ret; @@ -1245,10 +1229,9 @@ u64 tmigr_cpu_new_timer(u64 nextexp) static bool tmigr_inactive_up(struct tmigr_group *group, struct tmigr_group *child, - void *ptr) + struct tmigr_walk *data) { union tmigr_state curstate, newstate, childstate; - struct tmigr_walk *data = ptr; bool walk_done; u8 childmask; @@ -1299,9 +1282,10 @@ static bool tmigr_inactive_up(struct tmigr_group *group, WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active)); - if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, - newstate.state)) + if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)) { + trace_tmigr_group_set_cpu_inactive(group, newstate, childmask); break; + } /* * The memory barrier is paired with the cmpxchg() in @@ -1317,22 +1301,6 @@ static bool tmigr_inactive_up(struct tmigr_group *group, /* Event Handling */ tmigr_update_events(group, child, data); - if (group->parent && (walk_done == false)) - data->childmask = group->childmask; - - /* - * data->firstexp was set by tmigr_update_events() and contains the - * expiry of the first global event which needs to be handled. It - * differs from KTIME_MAX if: - * - group is the top level group and - * - group is idle (which means CPU was the last active CPU in the - * hierarchy) and - * - there is a pending event in the hierarchy - */ - WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent); - - trace_tmigr_group_set_cpu_inactive(group, newstate, childmask); - return walk_done; } @@ -1341,7 +1309,7 @@ static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp) struct tmigr_walk data = { .nextexp = nextexp, .firstexp = KTIME_MAX, .evt = &tmc->cpuevt, - .childmask = tmc->childmask }; + .childmask = tmc->groupmask }; /* * If nextexp is KTIME_MAX, the CPU event will be ignored because the @@ -1400,7 +1368,7 @@ u64 tmigr_cpu_deactivate(u64 nextexp) * the only one in the level 0 group; and if it is the * only one in level 0 group, but there are more than a * single group active on the way to top level) - * * nextevt - when CPU is offline and has to handle timer on his own + * * nextevt - when CPU is offline and has to handle timer on its own * or when on the way to top in every group only a single * child is active but @nextevt is before the lowest * next_expiry encountered while walking up to top level. @@ -1419,7 +1387,7 @@ u64 tmigr_quick_check(u64 nextevt) if (WARN_ON_ONCE(tmc->idle)) return nextevt; - if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask)) + if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->groupmask)) return KTIME_MAX; do { @@ -1442,6 +1410,66 @@ u64 tmigr_quick_check(u64 nextevt) return KTIME_MAX; } +/* + * tmigr_trigger_active() - trigger a CPU to become active again + * + * This function is executed on a CPU which is part of cpu_online_mask, when the + * last active CPU in the hierarchy is offlining. With this, it is ensured that + * the other CPU is active and takes over the migrator duty. + */ +static long tmigr_trigger_active(void *unused) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + WARN_ON_ONCE(!tmc->online || tmc->idle); + + return 0; +} + +static int tmigr_cpu_offline(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + int migrator; + u64 firstexp; + + raw_spin_lock_irq(&tmc->lock); + tmc->online = false; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + /* + * CPU has to handle the local events on his own, when on the way to + * offline; Therefore nextevt value is set to KTIME_MAX + */ + firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX); + trace_tmigr_cpu_offline(tmc); + raw_spin_unlock_irq(&tmc->lock); + + if (firstexp != KTIME_MAX) { + migrator = cpumask_any_but(cpu_online_mask, cpu); + work_on_cpu(migrator, tmigr_trigger_active, NULL); + } + + return 0; +} + +static int tmigr_cpu_online(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + /* Check whether CPU data was successfully initialized */ + if (WARN_ON_ONCE(!tmc->tmgroup)) + return -EINVAL; + + raw_spin_lock_irq(&tmc->lock); + trace_tmigr_cpu_online(tmc); + tmc->idle = timer_base_is_idle(); + if (!tmc->idle) + __tmigr_cpu_activate(tmc); + tmc->online = true; + raw_spin_unlock_irq(&tmc->lock); + return 0; +} + static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, int node) { @@ -1514,21 +1542,25 @@ static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node, } static void tmigr_connect_child_parent(struct tmigr_group *child, - struct tmigr_group *parent) + struct tmigr_group *parent, + bool activate) { - union tmigr_state childstate; + struct tmigr_walk data; raw_spin_lock_irq(&child->lock); raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); child->parent = parent; - child->childmask = BIT(parent->num_children++); + child->groupmask = BIT(parent->num_children++); raw_spin_unlock(&parent->lock); raw_spin_unlock_irq(&child->lock); trace_tmigr_connect_child_parent(child); + if (!activate) + return; + /* * To prevent inconsistent states, active children need to be active in * the new parent as well. Inactive children are already marked inactive @@ -1544,21 +1576,24 @@ static void tmigr_connect_child_parent(struct tmigr_group *child, * child to the new parent. So tmigr_connect_child_parent() is * executed with the formerly top level group (child) and the newly * created group (parent). + * + * * It is ensured that the child is active, as this setup path is + * executed in hotplug prepare callback. This is exectued by an + * already connected and !idle CPU. Even if all other CPUs go idle, + * the CPU executing the setup will be responsible up to current top + * level group. And the next time it goes inactive, it will release + * the new childmask and parent to subsequent walkers through this + * @child. Therefore propagate active state unconditionally. */ - childstate.state = atomic_read(&child->migr_state); - if (childstate.migrator != TMIGR_NONE) { - struct tmigr_walk data; - - data.childmask = child->childmask; + data.childmask = child->groupmask; - /* - * There is only one new level per time. When connecting the - * child and the parent and set the child active when the parent - * is inactive, the parent needs to be the uppermost - * level. Otherwise there went something wrong! - */ - WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent); - } + /* + * There is only one new level per time (which is protected by + * tmigr_mutex). When connecting the child and the parent and set the + * child active when the parent is inactive, the parent needs to be the + * uppermost level. Otherwise there went something wrong! + */ + WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent); } static int tmigr_setup_groups(unsigned int cpu, unsigned int node) @@ -1611,12 +1646,12 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) * Update tmc -> group / child -> group connection */ if (i == 0) { - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu); raw_spin_lock_irq(&group->lock); tmc->tmgroup = group; - tmc->childmask = BIT(group->num_children++); + tmc->groupmask = BIT(group->num_children++); raw_spin_unlock_irq(&group->lock); @@ -1626,7 +1661,8 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) continue; } else { child = stack[i - 1]; - tmigr_connect_child_parent(child, group); + /* Will be activated at online time */ + tmigr_connect_child_parent(child, group, false); } /* check if uppermost level was newly created */ @@ -1637,12 +1673,21 @@ static int tmigr_setup_groups(unsigned int cpu, unsigned int node) lvllist = &tmigr_level_list[top]; if (group->num_children == 1 && list_is_singular(lvllist)) { + /* + * The target CPU must never do the prepare work, except + * on early boot when the boot CPU is the target. Otherwise + * it may spuriously activate the old top level group inside + * the new one (nevertheless whether old top level group is + * active or not) and/or release an uninitialized childmask. + */ + WARN_ON_ONCE(cpu == raw_smp_processor_id()); + lvllist = &tmigr_level_list[top - 1]; list_for_each_entry(child, lvllist, list) { if (child->parent) continue; - tmigr_connect_child_parent(child, group); + tmigr_connect_child_parent(child, group, true); } } } @@ -1664,80 +1709,31 @@ static int tmigr_add_cpu(unsigned int cpu) return ret; } -static int tmigr_cpu_online(unsigned int cpu) -{ - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - int ret; - - /* First online attempt? Initialize CPU data */ - if (!tmc->tmgroup) { - raw_spin_lock_init(&tmc->lock); - - ret = tmigr_add_cpu(cpu); - if (ret < 0) - return ret; - - if (tmc->childmask == 0) - return -EINVAL; - - timerqueue_init(&tmc->cpuevt.nextevt); - tmc->cpuevt.nextevt.expires = KTIME_MAX; - tmc->cpuevt.ignore = true; - tmc->cpuevt.cpu = cpu; - - tmc->remote = false; - WRITE_ONCE(tmc->wakeup, KTIME_MAX); - } - raw_spin_lock_irq(&tmc->lock); - trace_tmigr_cpu_online(tmc); - tmc->idle = timer_base_is_idle(); - if (!tmc->idle) - __tmigr_cpu_activate(tmc); - tmc->online = true; - raw_spin_unlock_irq(&tmc->lock); - return 0; -} - -/* - * tmigr_trigger_active() - trigger a CPU to become active again - * - * This function is executed on a CPU which is part of cpu_online_mask, when the - * last active CPU in the hierarchy is offlining. With this, it is ensured that - * the other CPU is active and takes over the migrator duty. - */ -static long tmigr_trigger_active(void *unused) +static int tmigr_cpu_prepare(unsigned int cpu) { - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_cpu *tmc = per_cpu_ptr(&tmigr_cpu, cpu); + int ret = 0; - WARN_ON_ONCE(!tmc->online || tmc->idle); - - return 0; -} - -static int tmigr_cpu_offline(unsigned int cpu) -{ - struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); - int migrator; - u64 firstexp; + /* Not first online attempt? */ + if (tmc->tmgroup) + return ret; - raw_spin_lock_irq(&tmc->lock); - tmc->online = false; + raw_spin_lock_init(&tmc->lock); + timerqueue_init(&tmc->cpuevt.nextevt); + tmc->cpuevt.nextevt.expires = KTIME_MAX; + tmc->cpuevt.ignore = true; + tmc->cpuevt.cpu = cpu; + tmc->remote = false; WRITE_ONCE(tmc->wakeup, KTIME_MAX); - /* - * CPU has to handle the local events on his own, when on the way to - * offline; Therefore nextevt value is set to KTIME_MAX - */ - firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX); - trace_tmigr_cpu_offline(tmc); - raw_spin_unlock_irq(&tmc->lock); + ret = tmigr_add_cpu(cpu); + if (ret < 0) + return ret; - if (firstexp != KTIME_MAX) { - migrator = cpumask_any_but(cpu_online_mask, cpu); - work_on_cpu(migrator, tmigr_trigger_active, NULL); - } + if (tmc->groupmask == 0) + return -EINVAL; - return 0; + return ret; } static int __init tmigr_init(void) @@ -1796,6 +1792,11 @@ static int __init tmigr_init(void) tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP, tmigr_crossnode_level); + ret = cpuhp_setup_state(CPUHP_TMIGR_PREPARE, "tmigr:prepare", + tmigr_cpu_prepare, NULL); + if (ret) + goto err; + ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online", tmigr_cpu_online, tmigr_cpu_offline); if (ret) @@ -1807,4 +1808,4 @@ err: pr_err("Timer migration setup failed\n"); return ret; } -late_initcall(tmigr_init); +early_initcall(tmigr_init); diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h index 6c37d94a37d9..154accc7a543 100644 --- a/kernel/time/timer_migration.h +++ b/kernel/time/timer_migration.h @@ -22,7 +22,17 @@ struct tmigr_event { * struct tmigr_group - timer migration hierarchy group * @lock: Lock protecting the event information and group hierarchy * information during setup - * @parent: Pointer to the parent group + * @parent: Pointer to the parent group. Pointer is updated when a + * new hierarchy level is added because of a CPU coming + * online the first time. Once it is set, the pointer will + * not be removed or updated. When accessing parent pointer + * lock less to decide whether to abort a propagation or + * not, it is not a problem. The worst outcome is an + * unnecessary/early CPU wake up. But do not access parent + * pointer several times in the same 'action' (like + * activation, deactivation, check for remote expiry,...) + * without holding the lock as it is not ensured that value + * will not change. * @groupevt: Next event of the group which is only used when the * group is !active. The group event is then queued into * the parent timer queue. @@ -41,9 +51,8 @@ struct tmigr_event { * @num_children: Counter of group children to make sure the group is only * filled with TMIGR_CHILDREN_PER_GROUP; Required for setup * only - * @childmask: childmask of the group in the parent group; is set - * during setup and will never change; can be read - * lockless + * @groupmask: mask of the group in the parent group; is set during + * setup and will never change; can be read lockless * @list: List head that is added to the per level * tmigr_level_list; is required during setup when a * new group needs to be connected to the existing @@ -59,7 +68,7 @@ struct tmigr_group { unsigned int level; int numa_node; unsigned int num_children; - u8 childmask; + u8 groupmask; struct list_head list; }; @@ -79,7 +88,7 @@ struct tmigr_group { * hierarchy * @remote: Is set when timers of the CPU are expired remotely * @tmgroup: Pointer to the parent group - * @childmask: childmask of tmigr_cpu in the parent group + * @groupmask: mask of tmigr_cpu in the parent group * @wakeup: Stores the first timer when the timer migration * hierarchy is completely idle and remote expiry was done; * is returned to timer code in the idle path and is only @@ -92,7 +101,7 @@ struct tmigr_cpu { bool idle; bool remote; struct tmigr_group *tmgroup; - u8 childmask; + u8 groupmask; u64 wakeup; struct tmigr_event cpuevt; }; @@ -108,8 +117,8 @@ union tmigr_state { u32 state; /** * struct - split state of tmigr_group - * @active: Contains each childmask bit of the active children - * @migrator: Contains childmask of the child which is migrator + * @active: Contains each mask bit of the active children + * @migrator: Contains mask of the child which is migrator * @seq: Sequence counter needs to be increased when an update * to the tmigr_state is done. It prevents a race when * updates in the child groups are propagated in changed |