diff options
Diffstat (limited to 'kernel/time')
-rw-r--r-- | kernel/time/Kconfig | 29 | ||||
-rw-r--r-- | kernel/time/alarmtimer.c | 2 | ||||
-rw-r--r-- | kernel/time/clockevents.c | 18 | ||||
-rw-r--r-- | kernel/time/hrtimer.c | 4 | ||||
-rw-r--r-- | kernel/time/jiffies.c | 4 | ||||
-rw-r--r-- | kernel/time/ntp.c | 18 | ||||
-rw-r--r-- | kernel/time/ntp_internal.h | 2 | ||||
-rw-r--r-- | kernel/time/posix-clock.c | 2 | ||||
-rw-r--r-- | kernel/time/posix-cpu-timers.c | 12 | ||||
-rw-r--r-- | kernel/time/posix-stubs.c | 25 | ||||
-rw-r--r-- | kernel/time/posix-timers.c | 72 | ||||
-rw-r--r-- | kernel/time/posix-timers.h | 2 | ||||
-rw-r--r-- | kernel/time/sched_clock.c | 8 | ||||
-rw-r--r-- | kernel/time/tick-broadcast.c | 49 | ||||
-rw-r--r-- | kernel/time/tick-common.c | 54 | ||||
-rw-r--r-- | kernel/time/tick-internal.h | 10 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 49 | ||||
-rw-r--r-- | kernel/time/tick-sched.h | 13 | ||||
-rw-r--r-- | kernel/time/time.c | 94 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 28 | ||||
-rw-r--r-- | kernel/time/timekeeping.h | 7 | ||||
-rw-r--r-- | kernel/time/timekeeping_debug.c | 11 | ||||
-rw-r--r-- | kernel/time/timer.c | 34 |
23 files changed, 368 insertions, 179 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 58b981f4bb5d..e2c038d6c13c 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -117,6 +117,35 @@ config NO_HZ_FULL endchoice +config CONTEXT_TRACKING + bool + +config CONTEXT_TRACKING_FORCE + bool "Force context tracking" + depends on CONTEXT_TRACKING + default y if !NO_HZ_FULL + help + The major pre-requirement for full dynticks to work is to + support the context tracking subsystem. But there are also + other dependencies to provide in order to make the full + dynticks working. + + This option stands for testing when an arch implements the + context tracking backend but doesn't yet fullfill all the + requirements to make the full dynticks feature working. + Without the full dynticks, there is no way to test the support + for context tracking and the subsystems that rely on it: RCU + userspace extended quiescent state and tickless cputime + accounting. This option copes with the absence of the full + dynticks subsystem by forcing the context tracking on all + CPUs in the system. + + Say Y only if you're working on the development of an + architecture backend for the context tracking. + + Say N otherwise, this option brings an overhead that you + don't want in production. + config NO_HZ bool "Old Idle dynticks config" depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 2c97e8c2d29f..0519a8805aab 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -594,7 +594,7 @@ static ktime_t alarm_timer_remaining(struct k_itimer *timr, ktime_t now) { struct alarm *alarm = &timr->it.alarm.alarmtimer; - return ktime_sub(now, alarm->node.expires); + return ktime_sub(alarm->node.expires, now); } /** diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 5e77662dd2d9..f5490222e134 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -611,6 +611,22 @@ void clockevents_resume(void) } #ifdef CONFIG_HOTPLUG_CPU + +# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +/** + * tick_offline_cpu - Take CPU out of the broadcast mechanism + * @cpu: The outgoing CPU + * + * Called on the outgoing CPU after it took itself offline. + */ +void tick_offline_cpu(unsigned int cpu) +{ + raw_spin_lock(&clockevents_lock); + tick_broadcast_offline(cpu); + raw_spin_unlock(&clockevents_lock); +} +# endif + /** * tick_cleanup_dead_cpu - Cleanup the tick and clockevents of a dead cpu */ @@ -621,8 +637,6 @@ void tick_cleanup_dead_cpu(int cpu) raw_spin_lock_irqsave(&clockevents_lock, flags); - tick_shutdown_broadcast_oneshot(cpu); - tick_shutdown_broadcast(cpu); tick_shutdown(cpu); /* * Unregister the clock event devices which were diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index f5cfa1b73d6f..41dfff23c1f9 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -364,7 +364,7 @@ static bool hrtimer_fixup_activate(void *addr, enum debug_obj_state state) switch (state) { case ODEBUG_STATE_ACTIVE: WARN_ON(1); - + /* fall through */ default: return false; } @@ -1771,7 +1771,7 @@ SYSCALL_DEFINE2(nanosleep, struct __kernel_timespec __user *, rqtp, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(nanosleep, struct old_timespec32 __user *, rqtp, +SYSCALL_DEFINE2(nanosleep_time32, struct old_timespec32 __user *, rqtp, struct old_timespec32 __user *, rmtp) { struct timespec64 tu; diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c index dc1b6f1929f9..d23b434c2ca7 100644 --- a/kernel/time/jiffies.c +++ b/kernel/time/jiffies.c @@ -63,7 +63,7 @@ __cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); #if (BITS_PER_LONG < 64) u64 get_jiffies_64(void) { - unsigned long seq; + unsigned int seq; u64 ret; do { @@ -89,7 +89,7 @@ struct clocksource * __init __weak clocksource_default_clock(void) return &clocksource_jiffies; } -struct clocksource refined_jiffies; +static struct clocksource refined_jiffies; int register_refined_jiffies(long cycles_per_second) { diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 36a2bef00125..92a90014a925 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -188,13 +188,13 @@ static inline int is_error_status(int status) && (status & (STA_PPSWANDER|STA_PPSERROR))); } -static inline void pps_fill_timex(struct timex *txc) +static inline void pps_fill_timex(struct __kernel_timex *txc) { txc->ppsfreq = shift_right((pps_freq >> PPM_SCALE_INV_SHIFT) * PPM_SCALE_INV, NTP_SCALE_SHIFT); txc->jitter = pps_jitter; if (!(time_status & STA_NANO)) - txc->jitter /= NSEC_PER_USEC; + txc->jitter = pps_jitter / NSEC_PER_USEC; txc->shift = pps_shift; txc->stabil = pps_stabil; txc->jitcnt = pps_jitcnt; @@ -220,7 +220,7 @@ static inline int is_error_status(int status) return status & (STA_UNSYNC|STA_CLOCKERR); } -static inline void pps_fill_timex(struct timex *txc) +static inline void pps_fill_timex(struct __kernel_timex *txc) { /* PPS is not implemented, so these are zero */ txc->ppsfreq = 0; @@ -633,7 +633,7 @@ void ntp_notify_cmos_timer(void) /* * Propagate a new txc->status value into the NTP state: */ -static inline void process_adj_status(const struct timex *txc) +static inline void process_adj_status(const struct __kernel_timex *txc) { if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; @@ -656,7 +656,8 @@ static inline void process_adj_status(const struct timex *txc) } -static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai) +static inline void process_adjtimex_modes(const struct __kernel_timex *txc, + s32 *time_tai) { if (txc->modes & ADJ_STATUS) process_adj_status(txc); @@ -707,7 +708,8 @@ static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai * adjtimex mainly allows reading (and writing, if superuser) of * kernel time-keeping variables. used by xntpd. */ -int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) +int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, + s32 *time_tai) { int result; @@ -729,7 +731,7 @@ int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ, NTP_SCALE_SHIFT); if (!(time_status & STA_NANO)) - txc->offset /= NSEC_PER_USEC; + txc->offset = (u32)txc->offset / NSEC_PER_USEC; } result = time_state; /* mostly `TIME_OK' */ @@ -754,7 +756,7 @@ int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai) txc->time.tv_sec = (time_t)ts->tv_sec; txc->time.tv_usec = ts->tv_nsec; if (!(time_status & STA_NANO)) - txc->time.tv_usec /= NSEC_PER_USEC; + txc->time.tv_usec = ts->tv_nsec / NSEC_PER_USEC; /* Handle leapsec adjustments */ if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) { diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index c24b0e13f011..40e6122e634e 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -8,6 +8,6 @@ extern void ntp_clear(void); extern u64 ntp_tick_length(void); extern ktime_t ntp_get_next_leap(void); extern int second_overflow(time64_t secs); -extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai); +extern int __do_adjtimex(struct __kernel_timex *txc, const struct timespec64 *ts, s32 *time_tai); extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts); #endif /* _LINUX_NTP_INTERNAL_H */ diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c index 425bbfce6819..ec960bb939fd 100644 --- a/kernel/time/posix-clock.c +++ b/kernel/time/posix-clock.c @@ -228,7 +228,7 @@ static void put_clock_desc(struct posix_clock_desc *cd) fput(cd->fp); } -static int pc_clock_adjtime(clockid_t id, struct timex *tx) +static int pc_clock_adjtime(clockid_t id, struct __kernel_timex *tx) { struct posix_clock_desc cd; int err; diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c index 8f0644af40be..0a426f4e3125 100644 --- a/kernel/time/posix-cpu-timers.c +++ b/kernel/time/posix-cpu-timers.c @@ -67,13 +67,13 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now) int i; u64 delta, incr; - if (timer->it.cpu.incr == 0) + if (!timer->it_interval) return; if (now < timer->it.cpu.expires) return; - incr = timer->it.cpu.incr; + incr = timer->it_interval; delta = now + incr - timer->it.cpu.expires; /* Don't use (incr*2 < delta), incr*2 might overflow. */ @@ -520,7 +520,7 @@ static void cpu_timer_fire(struct k_itimer *timer) */ wake_up_process(timer->it_process); timer->it.cpu.expires = 0; - } else if (timer->it.cpu.incr == 0) { + } else if (!timer->it_interval) { /* * One-shot timer. Clear it as soon as it's fired. */ @@ -606,7 +606,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, */ ret = 0; - old_incr = timer->it.cpu.incr; + old_incr = timer->it_interval; old_expires = timer->it.cpu.expires; if (unlikely(timer->it.cpu.firing)) { timer->it.cpu.firing = -1; @@ -684,7 +684,7 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags, * Install the new reload setting, and * set up the signal and overrun bookkeeping. */ - timer->it.cpu.incr = timespec64_to_ns(&new->it_interval); + timer->it_interval = timespec64_to_ktime(new->it_interval); /* * This acts as a modification timestamp for the timer, @@ -723,7 +723,7 @@ static void posix_cpu_timer_get(struct k_itimer *timer, struct itimerspec64 *itp /* * Easy part: convert the reload time. */ - itp->it_interval = ns_to_timespec64(timer->it.cpu.incr); + itp->it_interval = ktime_to_timespec64(timer->it_interval); if (!timer->it.cpu.expires) return; diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c index a51895486e5e..67df65f887ac 100644 --- a/kernel/time/posix-stubs.c +++ b/kernel/time/posix-stubs.c @@ -45,6 +45,7 @@ SYS_NI(timer_delete); SYS_NI(clock_adjtime); SYS_NI(getitimer); SYS_NI(setitimer); +SYS_NI(clock_adjtime32); #ifdef __ARCH_WANT_SYS_ALARM SYS_NI(alarm); #endif @@ -150,16 +151,16 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, #ifdef CONFIG_COMPAT COMPAT_SYS_NI(timer_create); -COMPAT_SYS_NI(clock_adjtime); -COMPAT_SYS_NI(timer_settime); -COMPAT_SYS_NI(timer_gettime); COMPAT_SYS_NI(getitimer); COMPAT_SYS_NI(setitimer); #endif #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYS_NI(timer_settime32); +SYS_NI(timer_gettime32); + +SYSCALL_DEFINE2(clock_settime32, const clockid_t, which_clock, + struct old_timespec32 __user *, tp) { struct timespec64 new_tp; @@ -171,8 +172,8 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, const clockid_t, which_clock, return do_sys_settimeofday64(&new_tp, NULL); } -COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { int ret; struct timespec64 kernel_tp; @@ -186,8 +187,8 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, return 0; } -COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { struct timespec64 rtn_tp = { .tv_sec = 0, @@ -206,9 +207,9 @@ COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, } } -COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct old_timespec32 __user *, rqtp, - struct old_timespec32 __user *, rmtp) +SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { struct timespec64 t; diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 0e84bb72a3da..29176635991f 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -179,7 +179,7 @@ static int posix_clock_realtime_set(const clockid_t which_clock, } static int posix_clock_realtime_adj(const clockid_t which_clock, - struct timex *t) + struct __kernel_timex *t) { return do_adjtimex(t); } @@ -730,8 +730,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id, - struct old_itimerspec32 __user *, setting) +SYSCALL_DEFINE2(timer_gettime32, timer_t, timer_id, + struct old_itimerspec32 __user *, setting) { struct itimerspec64 cur_setting; @@ -903,9 +903,9 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags, - struct old_itimerspec32 __user *, new, - struct old_itimerspec32 __user *, old) +SYSCALL_DEFINE4(timer_settime32, timer_t, timer_id, int, flags, + struct old_itimerspec32 __user *, new, + struct old_itimerspec32 __user *, old) { struct itimerspec64 new_spec, old_spec; struct itimerspec64 *rtn = old ? &old_spec : NULL; @@ -1047,22 +1047,28 @@ SYSCALL_DEFINE2(clock_gettime, const clockid_t, which_clock, return error; } -SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, - struct timex __user *, utx) +int do_clock_adjtime(const clockid_t which_clock, struct __kernel_timex * ktx) { const struct k_clock *kc = clockid_to_kclock(which_clock); - struct timex ktx; - int err; if (!kc) return -EINVAL; if (!kc->clock_adj) return -EOPNOTSUPP; + return kc->clock_adj(which_clock, ktx); +} + +SYSCALL_DEFINE2(clock_adjtime, const clockid_t, which_clock, + struct __kernel_timex __user *, utx) +{ + struct __kernel_timex ktx; + int err; + if (copy_from_user(&ktx, utx, sizeof(ktx))) return -EFAULT; - err = kc->clock_adj(which_clock, &ktx); + err = do_clock_adjtime(which_clock, &ktx); if (err >= 0 && copy_to_user(utx, &ktx, sizeof(ktx))) return -EFAULT; @@ -1090,8 +1096,8 @@ SYSCALL_DEFINE2(clock_getres, const clockid_t, which_clock, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_settime32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1105,8 +1111,8 @@ COMPAT_SYSCALL_DEFINE2(clock_settime, clockid_t, which_clock, return kc->clock_set(which_clock, &ts); } -COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_gettime32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1123,40 +1129,26 @@ COMPAT_SYSCALL_DEFINE2(clock_gettime, clockid_t, which_clock, return err; } -#endif - -#ifdef CONFIG_COMPAT - -COMPAT_SYSCALL_DEFINE2(clock_adjtime, clockid_t, which_clock, - struct compat_timex __user *, utp) +SYSCALL_DEFINE2(clock_adjtime32, clockid_t, which_clock, + struct old_timex32 __user *, utp) { - const struct k_clock *kc = clockid_to_kclock(which_clock); - struct timex ktx; + struct __kernel_timex ktx; int err; - if (!kc) - return -EINVAL; - if (!kc->clock_adj) - return -EOPNOTSUPP; - - err = compat_get_timex(&ktx, utp); + err = get_old_timex32(&ktx, utp); if (err) return err; - err = kc->clock_adj(which_clock, &ktx); + err = do_clock_adjtime(which_clock, &ktx); if (err >= 0) - err = compat_put_timex(utp, &ktx); + err = put_old_timex32(utp, &ktx); return err; } -#endif - -#ifdef CONFIG_COMPAT_32BIT_TIME - -COMPAT_SYSCALL_DEFINE2(clock_getres, clockid_t, which_clock, - struct old_timespec32 __user *, tp) +SYSCALL_DEFINE2(clock_getres_time32, clockid_t, which_clock, + struct old_timespec32 __user *, tp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 ts; @@ -1212,9 +1204,9 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags, #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags, - struct old_timespec32 __user *, rqtp, - struct old_timespec32 __user *, rmtp) +SYSCALL_DEFINE4(clock_nanosleep_time32, clockid_t, which_clock, int, flags, + struct old_timespec32 __user *, rqtp, + struct old_timespec32 __user *, rmtp) { const struct k_clock *kc = clockid_to_kclock(which_clock); struct timespec64 t; diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h index ddb21145211a..de5daa6d975a 100644 --- a/kernel/time/posix-timers.h +++ b/kernel/time/posix-timers.h @@ -8,7 +8,7 @@ struct k_clock { const struct timespec64 *tp); int (*clock_get)(const clockid_t which_clock, struct timespec64 *tp); - int (*clock_adj)(const clockid_t which_clock, struct timex *tx); + int (*clock_adj)(const clockid_t which_clock, struct __kernel_timex *tx); int (*timer_create)(struct k_itimer *timer); int (*nsleep)(const clockid_t which_clock, int flags, const struct timespec64 *); diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 094b82ca95e5..968e4b07918e 100644 --- a/kernel/time/sched_clock.c +++ b/kernel/time/sched_clock.c @@ -94,7 +94,7 @@ static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift) unsigned long long notrace sched_clock(void) { u64 cyc, res; - unsigned long seq; + unsigned int seq; struct clock_read_data *rd; do { @@ -267,12 +267,12 @@ void __init generic_sched_clock_init(void) */ static u64 notrace suspended_sched_clock_read(void) { - unsigned long seq = raw_read_seqcount(&cd.seq); + unsigned int seq = raw_read_seqcount(&cd.seq); return cd.read_data[seq & 1].epoch_cyc; } -static int sched_clock_suspend(void) +int sched_clock_suspend(void) { struct clock_read_data *rd = &cd.read_data[0]; @@ -283,7 +283,7 @@ static int sched_clock_suspend(void) return 0; } -static void sched_clock_resume(void) +void sched_clock_resume(void) { struct clock_read_data *rd = &cd.read_data[0]; diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 803fa67aace9..e51778c312f1 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -36,10 +36,16 @@ static __cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(tick_broadcast_lock); static void tick_broadcast_setup_oneshot(struct clock_event_device *bc); static void tick_broadcast_clear_oneshot(int cpu); static void tick_resume_broadcast_oneshot(struct clock_event_device *bc); +# ifdef CONFIG_HOTPLUG_CPU +static void tick_broadcast_oneshot_offline(unsigned int cpu); +# endif #else static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc) { BUG(); } static inline void tick_broadcast_clear_oneshot(int cpu) { } static inline void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { } +# ifdef CONFIG_HOTPLUG_CPU +static inline void tick_broadcast_oneshot_offline(unsigned int cpu) { } +# endif #endif /* @@ -375,6 +381,7 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) switch (mode) { case TICK_BROADCAST_FORCE: tick_broadcast_forced = 1; + /* fall through */ case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { @@ -432,27 +439,29 @@ void tick_set_periodic_handler(struct clock_event_device *dev, int broadcast) } #ifdef CONFIG_HOTPLUG_CPU -/* - * Remove a CPU from broadcasting - */ -void tick_shutdown_broadcast(unsigned int cpu) +static void tick_shutdown_broadcast(void) { - struct clock_event_device *bc; - unsigned long flags; - - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - - bc = tick_broadcast_device.evtdev; - cpumask_clear_cpu(cpu, tick_broadcast_mask); - cpumask_clear_cpu(cpu, tick_broadcast_on); + struct clock_event_device *bc = tick_broadcast_device.evtdev; if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { if (bc && cpumask_empty(tick_broadcast_mask)) clockevents_shutdown(bc); } +} - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); +/* + * Remove a CPU from broadcasting + */ +void tick_broadcast_offline(unsigned int cpu) +{ + raw_spin_lock(&tick_broadcast_lock); + cpumask_clear_cpu(cpu, tick_broadcast_mask); + cpumask_clear_cpu(cpu, tick_broadcast_on); + tick_broadcast_oneshot_offline(cpu); + tick_shutdown_broadcast(); + raw_spin_unlock(&tick_broadcast_lock); } + #endif void tick_suspend_broadcast(void) @@ -800,13 +809,13 @@ int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) * either the CPU handling the broadcast * interrupt or we got woken by something else. * - * We are not longer in the broadcast mask, so + * We are no longer in the broadcast mask, so * if the cpu local expiry time is already * reached, we would reprogram the cpu local * timer with an already expired event. * * This can lead to a ping-pong when we return - * to idle and therefor rearm the broadcast + * to idle and therefore rearm the broadcast * timer before the cpu local timer was able * to fire. This happens because the forced * reprogramming makes sure that the event @@ -949,14 +958,10 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu) } /* - * Remove a dead CPU from broadcasting + * Remove a dying CPU from broadcasting */ -void tick_shutdown_broadcast_oneshot(unsigned int cpu) +static void tick_broadcast_oneshot_offline(unsigned int cpu) { - unsigned long flags; - - raw_spin_lock_irqsave(&tick_broadcast_lock, flags); - /* * Clear the broadcast masks for the dead cpu, but do not stop * the broadcast device! @@ -964,8 +969,6 @@ void tick_shutdown_broadcast_oneshot(unsigned int cpu) cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); cpumask_clear_cpu(cpu, tick_broadcast_pending_mask); cpumask_clear_cpu(cpu, tick_broadcast_force_mask); - - raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags); } #endif diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 529143b4c8d2..59225b484e4e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -46,6 +46,14 @@ ktime_t tick_period; * procedure also covers cpu hotplug. */ int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT; +#ifdef CONFIG_NO_HZ_FULL +/* + * tick_do_timer_boot_cpu indicates the boot CPU temporarily owns + * tick_do_timer_cpu and it should be taken over by an eligible secondary + * when one comes online. + */ +static int tick_do_timer_boot_cpu __read_mostly = -1; +#endif /* * Debugging: see timer_list.c @@ -149,7 +157,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) !tick_broadcast_oneshot_active()) { clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); } else { - unsigned long seq; + unsigned int seq; ktime_t next; do { @@ -167,6 +175,26 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) } } +#ifdef CONFIG_NO_HZ_FULL +static void giveup_do_timer(void *info) +{ + int cpu = *(unsigned int *)info; + + WARN_ON(tick_do_timer_cpu != smp_processor_id()); + + tick_do_timer_cpu = cpu; +} + +static void tick_take_do_timer_from_boot(void) +{ + int cpu = smp_processor_id(); + int from = tick_do_timer_boot_cpu; + + if (from >= 0 && from != cpu) + smp_call_function_single(from, giveup_do_timer, &cpu, 1); +} +#endif + /* * Setup the tick device */ @@ -186,12 +214,26 @@ static void tick_setup_device(struct tick_device *td, * this cpu: */ if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) { - if (!tick_nohz_full_cpu(cpu)) - tick_do_timer_cpu = cpu; - else - tick_do_timer_cpu = TICK_DO_TIMER_NONE; + tick_do_timer_cpu = cpu; + tick_next_period = ktime_get(); tick_period = NSEC_PER_SEC / HZ; +#ifdef CONFIG_NO_HZ_FULL + /* + * The boot CPU may be nohz_full, in which case set + * tick_do_timer_boot_cpu so the first housekeeping + * secondary that comes up will take do_timer from + * us. + */ + if (tick_nohz_full_cpu(cpu)) + tick_do_timer_boot_cpu = cpu; + + } else if (tick_do_timer_boot_cpu != -1 && + !tick_nohz_full_cpu(cpu)) { + tick_take_do_timer_from_boot(); + tick_do_timer_boot_cpu = -1; + WARN_ON(tick_do_timer_cpu != cpu); +#endif } /* @@ -487,6 +529,7 @@ void tick_freeze(void) trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), true); system_state = SYSTEM_SUSPEND; + sched_clock_suspend(); timekeeping_suspend(); } else { tick_suspend_local(); @@ -510,6 +553,7 @@ void tick_unfreeze(void) if (tick_freeze_depth == num_online_cpus()) { timekeeping_resume(); + sched_clock_resume(); system_state = SYSTEM_RUNNING; trace_suspend_resume(TPS("timekeeping_freeze"), smp_processor_id(), false); diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index e277284c2831..7b2496136729 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -64,7 +64,6 @@ extern ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt); extern int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu); extern void tick_install_broadcast_device(struct clock_event_device *dev); extern int tick_is_broadcast_device(struct clock_event_device *dev); -extern void tick_shutdown_broadcast(unsigned int cpu); extern void tick_suspend_broadcast(void); extern void tick_resume_broadcast(void); extern bool tick_resume_check_broadcast(void); @@ -78,7 +77,6 @@ static inline void tick_install_broadcast_device(struct clock_event_device *dev) static inline int tick_is_broadcast_device(struct clock_event_device *dev) { return 0; } static inline int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { return 0; } static inline void tick_do_periodic_broadcast(struct clock_event_device *d) { } -static inline void tick_shutdown_broadcast(unsigned int cpu) { } static inline void tick_suspend_broadcast(void) { } static inline void tick_resume_broadcast(void) { } static inline bool tick_resume_check_broadcast(void) { return false; } @@ -128,19 +126,23 @@ static inline int tick_check_oneshot_change(int allow_nohz) { return 0; } /* Functions related to oneshot broadcasting */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT) extern void tick_broadcast_switch_to_oneshot(void); -extern void tick_shutdown_broadcast_oneshot(unsigned int cpu); extern int tick_broadcast_oneshot_active(void); extern void tick_check_oneshot_broadcast_this_cpu(void); bool tick_broadcast_oneshot_available(void); extern struct cpumask *tick_get_broadcast_oneshot_mask(void); #else /* !(BROADCAST && ONESHOT): */ static inline void tick_broadcast_switch_to_oneshot(void) { } -static inline void tick_shutdown_broadcast_oneshot(unsigned int cpu) { } static inline int tick_broadcast_oneshot_active(void) { return 0; } static inline void tick_check_oneshot_broadcast_this_cpu(void) { } static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_possible(); } #endif /* !(BROADCAST && ONESHOT) */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_broadcast_offline(unsigned int cpu); +#else +static inline void tick_broadcast_offline(unsigned int cpu) { } +#endif + /* NO_HZ_FULL internal */ #ifdef CONFIG_NO_HZ_FULL extern void tick_nohz_init(void); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 6fa52cd6df0b..f4ee1a3428ae 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -121,10 +121,16 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) * into a long sleep. If two CPUs happen to assign themselves to * this duty, then the jiffies update is still serialized by * jiffies_lock. + * + * If nohz_full is enabled, this should not happen because the + * tick_do_timer_cpu never relinquishes. */ - if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE) - && !tick_nohz_full_cpu(cpu)) + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { +#ifdef CONFIG_NO_HZ_FULL + WARN_ON(tick_nohz_full_running); +#endif tick_do_timer_cpu = cpu; + } #endif /* Check, if the jiffies need an update */ @@ -395,8 +401,8 @@ void __init tick_nohz_full_setup(cpumask_var_t cpumask) static int tick_nohz_cpu_down(unsigned int cpu) { /* - * The boot CPU handles housekeeping duty (unbound timers, - * workqueues, timekeeping, ...) on behalf of full dynticks + * The tick_do_timer_cpu CPU handles housekeeping duty (unbound + * timers, workqueues, timekeeping, ...) on behalf of full dynticks * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && tick_do_timer_cpu == cpu) @@ -423,12 +429,15 @@ void __init tick_nohz_init(void) return; } - cpu = smp_processor_id(); + if (IS_ENABLED(CONFIG_PM_SLEEP_SMP) && + !IS_ENABLED(CONFIG_PM_SLEEP_SMP_NONZERO_CPU)) { + cpu = smp_processor_id(); - if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { - pr_warn("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", - cpu); - cpumask_clear_cpu(cpu, tick_nohz_full_mask); + if (cpumask_test_cpu(cpu, tick_nohz_full_mask)) { + pr_warn("NO_HZ: Clearing %d from nohz_full range " + "for timekeeping\n", cpu); + cpumask_clear_cpu(cpu, tick_nohz_full_mask); + } } for_each_cpu(cpu, tick_nohz_full_mask) @@ -645,7 +654,8 @@ static inline bool local_timer_softirq_pending(void) static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) { u64 basemono, next_tick, next_tmr, next_rcu, delta, expires; - unsigned long seq, basejiff; + unsigned long basejiff; + unsigned int seq; /* Read jiffies and the time when jiffies were updated last */ do { @@ -904,8 +914,13 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) /* * Boot safety: make sure the timekeeping duty has been * assigned before entering dyntick-idle mode, + * tick_do_timer_cpu is TICK_DO_TIMER_BOOT */ - if (tick_do_timer_cpu == TICK_DO_TIMER_NONE) + if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_BOOT)) + return false; + + /* Should not happen for nohz-full */ + if (WARN_ON_ONCE(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) return false; } @@ -1023,6 +1038,18 @@ bool tick_nohz_idle_got_tick(void) } /** + * tick_nohz_get_next_hrtimer - return the next expiration time for the hrtimer + * or the tick, whatever that expires first. Note that, if the tick has been + * stopped, it returns the next hrtimer. + * + * Called from power state control code with interrupts disabled + */ +ktime_t tick_nohz_get_next_hrtimer(void) +{ + return __this_cpu_read(tick_cpu_device.evtdev)->next_event; +} + +/** * tick_nohz_get_sleep_length - return the expected length of the current sleep * @delta_next: duration until the next event if the tick cannot be stopped * diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 6de959a854b2..4fb06527cf64 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -24,12 +24,19 @@ enum tick_nohz_mode { * struct tick_sched - sched tick emulation and no idle tick control/stats * @sched_timer: hrtimer to schedule the periodic tick in high * resolution mode + * @check_clocks: Notification mechanism about clocksource changes + * @nohz_mode: Mode - one state of tick_nohz_mode + * @inidle: Indicator that the CPU is in the tick idle mode + * @tick_stopped: Indicator that the idle tick has been stopped + * @idle_active: Indicator that the CPU is actively in the tick idle mode; + * it is resetted during irq handling phases. + * @do_timer_lst: CPU was the last one doing do_timer before going idle + * @got_idle_tick: Tick timer function has run with @inidle set * @last_tick: Store the last tick expiry time when the tick * timer is modified for nohz sleeps. This is necessary * to resume the tick timer operation in the timeline * when the CPU returns from nohz sleep. * @next_tick: Next tick to be fired when in dynticks mode. - * @tick_stopped: Indicator that the idle tick has been stopped * @idle_jiffies: jiffies at the entry to idle for idle time accounting * @idle_calls: Total number of idle calls * @idle_sleeps: Number of idle calls, where the sched tick was stopped @@ -40,8 +47,8 @@ enum tick_nohz_mode { * @iowait_sleeptime: Sum of the time slept in idle with sched tick stopped, with IO outstanding * @timer_expires: Anticipated timer expiration time (in case sched tick is stopped) * @timer_expires_base: Base time clock monotonic for @timer_expires - * @do_timer_lst: CPU was the last one doing do_timer before going idle - * @got_idle_tick: Tick timer function has run with @inidle set + * @next_timer: Expiry time of next expiring timer for debugging purpose only + * @tick_dep_mask: Tick dependency mask - is set, if someone needs the tick */ struct tick_sched { struct hrtimer sched_timer; diff --git a/kernel/time/time.c b/kernel/time/time.c index 2edb5088a70b..86656bbac232 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -98,11 +98,11 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr) #endif /* __ARCH_WANT_SYS_TIME */ -#ifdef CONFIG_COMPAT -#ifdef __ARCH_WANT_COMPAT_SYS_TIME +#ifdef CONFIG_COMPAT_32BIT_TIME +#ifdef __ARCH_WANT_SYS_TIME32 /* old_time32_t is a 32 bit "long" and needs to get converted. */ -COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc) +SYSCALL_DEFINE1(time32, old_time32_t __user *, tloc) { old_time32_t i; @@ -116,7 +116,7 @@ COMPAT_SYSCALL_DEFINE1(time, old_time32_t __user *, tloc) return i; } -COMPAT_SYSCALL_DEFINE1(stime, old_time32_t __user *, tptr) +SYSCALL_DEFINE1(stime32, old_time32_t __user *, tptr) { struct timespec64 tv; int err; @@ -134,7 +134,7 @@ COMPAT_SYSCALL_DEFINE1(stime, old_time32_t __user *, tptr) return 0; } -#endif /* __ARCH_WANT_COMPAT_SYS_TIME */ +#endif /* __ARCH_WANT_SYS_TIME32 */ #endif SYSCALL_DEFINE2(gettimeofday, struct timeval __user *, tv, @@ -171,7 +171,7 @@ int do_sys_settimeofday64(const struct timespec64 *tv, const struct timezone *tz static int firsttime = 1; int error = 0; - if (tv && !timespec64_valid(tv)) + if (tv && !timespec64_valid_settod(tv)) return -EINVAL; error = security_settime64(tv, tz); @@ -263,35 +263,99 @@ COMPAT_SYSCALL_DEFINE2(settimeofday, struct old_timeval32 __user *, tv, } #endif -SYSCALL_DEFINE1(adjtimex, struct timex __user *, txc_p) +#if !defined(CONFIG_64BIT_TIME) || defined(CONFIG_64BIT) +SYSCALL_DEFINE1(adjtimex, struct __kernel_timex __user *, txc_p) { - struct timex txc; /* Local copy of parameter */ + struct __kernel_timex txc; /* Local copy of parameter */ int ret; /* Copy the user data space into the kernel copy * structure. But bear in mind that the structures * may change */ - if (copy_from_user(&txc, txc_p, sizeof(struct timex))) + if (copy_from_user(&txc, txc_p, sizeof(struct __kernel_timex))) return -EFAULT; ret = do_adjtimex(&txc); - return copy_to_user(txc_p, &txc, sizeof(struct timex)) ? -EFAULT : ret; + return copy_to_user(txc_p, &txc, sizeof(struct __kernel_timex)) ? -EFAULT : ret; } +#endif -#ifdef CONFIG_COMPAT +#ifdef CONFIG_COMPAT_32BIT_TIME +int get_old_timex32(struct __kernel_timex *txc, const struct old_timex32 __user *utp) +{ + struct old_timex32 tx32; + + memset(txc, 0, sizeof(struct __kernel_timex)); + if (copy_from_user(&tx32, utp, sizeof(struct old_timex32))) + return -EFAULT; + + txc->modes = tx32.modes; + txc->offset = tx32.offset; + txc->freq = tx32.freq; + txc->maxerror = tx32.maxerror; + txc->esterror = tx32.esterror; + txc->status = tx32.status; + txc->constant = tx32.constant; + txc->precision = tx32.precision; + txc->tolerance = tx32.tolerance; + txc->time.tv_sec = tx32.time.tv_sec; + txc->time.tv_usec = tx32.time.tv_usec; + txc->tick = tx32.tick; + txc->ppsfreq = tx32.ppsfreq; + txc->jitter = tx32.jitter; + txc->shift = tx32.shift; + txc->stabil = tx32.stabil; + txc->jitcnt = tx32.jitcnt; + txc->calcnt = tx32.calcnt; + txc->errcnt = tx32.errcnt; + txc->stbcnt = tx32.stbcnt; + + return 0; +} + +int put_old_timex32(struct old_timex32 __user *utp, const struct __kernel_timex *txc) +{ + struct old_timex32 tx32; + + memset(&tx32, 0, sizeof(struct old_timex32)); + tx32.modes = txc->modes; + tx32.offset = txc->offset; + tx32.freq = txc->freq; + tx32.maxerror = txc->maxerror; + tx32.esterror = txc->esterror; + tx32.status = txc->status; + tx32.constant = txc->constant; + tx32.precision = txc->precision; + tx32.tolerance = txc->tolerance; + tx32.time.tv_sec = txc->time.tv_sec; + tx32.time.tv_usec = txc->time.tv_usec; + tx32.tick = txc->tick; + tx32.ppsfreq = txc->ppsfreq; + tx32.jitter = txc->jitter; + tx32.shift = txc->shift; + tx32.stabil = txc->stabil; + tx32.jitcnt = txc->jitcnt; + tx32.calcnt = txc->calcnt; + tx32.errcnt = txc->errcnt; + tx32.stbcnt = txc->stbcnt; + tx32.tai = txc->tai; + if (copy_to_user(utp, &tx32, sizeof(struct old_timex32))) + return -EFAULT; + return 0; +} -COMPAT_SYSCALL_DEFINE1(adjtimex, struct compat_timex __user *, utp) +SYSCALL_DEFINE1(adjtimex_time32, struct old_timex32 __user *, utp) { - struct timex txc; + struct __kernel_timex txc; int err, ret; - err = compat_get_timex(&txc, utp); + err = get_old_timex32(&txc, utp); if (err) return err; ret = do_adjtimex(&txc); - err = compat_put_timex(utp, &txc); + err = put_old_timex32(utp, &txc); if (err) return err; diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index ac5dbf2cd4a2..5716e28bfa3c 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -720,7 +720,7 @@ static void timekeeping_forward_now(struct timekeeper *tk) void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); @@ -829,7 +829,7 @@ EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; - unsigned long seq; + unsigned int seq; ktime_t tconv; do { @@ -960,7 +960,7 @@ time64_t __ktime_get_real_seconds(void) void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; @@ -1122,7 +1122,7 @@ int get_device_system_crosststamp(int (*get_time_fn) ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; - unsigned long seq; + unsigned int seq; bool do_interp; int ret; @@ -1221,7 +1221,7 @@ int do_settimeofday64(const struct timespec64 *ts) unsigned long flags; int ret = 0; - if (!timespec64_valid_strict(ts)) + if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); @@ -1278,7 +1278,7 @@ static int timekeeping_inject_offset(const struct timespec64 *ts) /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || - !timespec64_valid_strict(&tmp)) { + !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } @@ -1409,7 +1409,7 @@ int timekeeping_notify(struct clocksource *clock) void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 nsecs; do { @@ -1431,7 +1431,7 @@ EXPORT_SYMBOL(ktime_get_raw_ts64); int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; int ret; do { @@ -1450,7 +1450,7 @@ int timekeeping_valid_for_hres(void) u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; u64 ret; do { @@ -1527,7 +1527,7 @@ void __init timekeeping_init(void) unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); - if (timespec64_valid_strict(&wall_time) && + if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { @@ -2150,7 +2150,7 @@ EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; - unsigned long seq; + unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); @@ -2164,7 +2164,7 @@ void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; - unsigned long seq; + unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); @@ -2234,7 +2234,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, /** * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ -static int timekeeping_validate_timex(const struct timex *txc) +static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ @@ -2300,7 +2300,7 @@ static int timekeeping_validate_timex(const struct timex *txc) /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ -int do_adjtimex(struct timex *txc) +int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index 7a9b4eb7a1d5..141ab3ab0354 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -14,6 +14,13 @@ extern u64 timekeeping_max_deferment(void); extern void timekeeping_warp_clock(void); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); +#ifdef CONFIG_GENERIC_SCHED_CLOCK +extern int sched_clock_suspend(void); +extern void sched_clock_resume(void); +#else +static inline int sched_clock_suspend(void) { return 0; } +static inline void sched_clock_resume(void) { } +#endif extern void do_timer(unsigned long ticks); extern void update_wall_time(void); diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c index 86489950d690..b73e8850e58d 100644 --- a/kernel/time/timekeeping_debug.c +++ b/kernel/time/timekeeping_debug.c @@ -37,15 +37,8 @@ DEFINE_SHOW_ATTRIBUTE(tk_debug_sleep_time); static int __init tk_debug_sleep_time_init(void) { - struct dentry *d; - - d = debugfs_create_file("sleep_time", 0444, NULL, NULL, - &tk_debug_sleep_time_fops); - if (!d) { - pr_err("Failed to create sleep_time debug file\n"); - return -ENOMEM; - } - + debugfs_create_file("sleep_time", 0444, NULL, NULL, + &tk_debug_sleep_time_fops); return 0; } late_initcall(tk_debug_sleep_time_init); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 444156debfa0..a9b1bbc2d88d 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -536,6 +536,8 @@ static void enqueue_timer(struct timer_base *base, struct timer_list *timer, hlist_add_head(&timer->entry, base->vectors + idx); __set_bit(idx, base->pending_map); timer_set_idx(timer, idx); + + trace_timer_start(timer, timer->expires, timer->flags); } static void @@ -647,7 +649,7 @@ static bool timer_fixup_activate(void *addr, enum debug_obj_state state) case ODEBUG_STATE_ACTIVE: WARN_ON(1); - + /* fall through */ default: return false; } @@ -757,13 +759,6 @@ static inline void debug_init(struct timer_list *timer) trace_timer_init(timer); } -static inline void -debug_activate(struct timer_list *timer, unsigned long expires) -{ - debug_timer_activate(timer); - trace_timer_start(timer, expires, timer->flags); -} - static inline void debug_deactivate(struct timer_list *timer) { debug_timer_deactivate(timer); @@ -1037,7 +1032,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option } } - debug_activate(timer, expires); + debug_timer_activate(timer); timer->expires = expires; /* @@ -1171,7 +1166,7 @@ void add_timer_on(struct timer_list *timer, int cpu) } forward_timer_base(base); - debug_activate(timer, timer->expires); + debug_timer_activate(timer); internal_add_timer(base, timer); raw_spin_unlock_irqrestore(&base->lock, flags); } @@ -1298,7 +1293,9 @@ int del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(del_timer_sync); #endif -static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list *)) +static void call_timer_fn(struct timer_list *timer, + void (*fn)(struct timer_list *), + unsigned long baseclk) { int count = preempt_count(); @@ -1321,7 +1318,7 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list */ lock_map_acquire(&lockdep_map); - trace_timer_expire_entry(timer); + trace_timer_expire_entry(timer, baseclk); fn(timer); trace_timer_expire_exit(timer); @@ -1342,6 +1339,13 @@ static void call_timer_fn(struct timer_list *timer, void (*fn)(struct timer_list static void expire_timers(struct timer_base *base, struct hlist_head *head) { + /* + * This value is required only for tracing. base->clk was + * incremented directly before expire_timers was called. But expiry + * is related to the old base->clk value. + */ + unsigned long baseclk = base->clk - 1; + while (!hlist_empty(head)) { struct timer_list *timer; void (*fn)(struct timer_list *); @@ -1355,11 +1359,11 @@ static void expire_timers(struct timer_base *base, struct hlist_head *head) if (timer->flags & TIMER_IRQSAFE) { raw_spin_unlock(&base->lock); - call_timer_fn(timer, fn); + call_timer_fn(timer, fn, baseclk); raw_spin_lock(&base->lock); } else { raw_spin_unlock_irq(&base->lock); - call_timer_fn(timer, fn); + call_timer_fn(timer, fn, baseclk); raw_spin_lock_irq(&base->lock); } } @@ -1632,7 +1636,7 @@ void update_process_times(int user_tick) /* Note: this timer irq context must be accounted for as well. */ account_process_tick(p, user_tick); run_local_timers(); - rcu_check_callbacks(user_tick); + rcu_sched_clock_irq(user_tick); #ifdef CONFIG_IRQ_WORK if (in_irq()) irq_work_tick(); |