diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 524eb5805995..c71adb1f1f41 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -521,7 +521,7 @@ struct mac80211_hwsim_data { unsigned int rx_filter; bool started, idle, scanning; struct mutex mutex; - struct tasklet_hrtimer beacon_timer; + struct hrtimer beacon_timer; enum ps_mode { PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL } ps; @@ -1460,7 +1460,7 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw) { struct mac80211_hwsim_data *data = hw->priv; data->started = false; - tasklet_hrtimer_cancel(&data->beacon_timer); + hrtimer_cancel(&data->beacon_timer); wiphy_dbg(hw->wiphy, "%s\n", __func__); } @@ -1583,14 +1583,12 @@ static enum hrtimer_restart mac80211_hwsim_beacon(struct hrtimer *timer) { struct mac80211_hwsim_data *data = - container_of(timer, struct mac80211_hwsim_data, - beacon_timer.timer); + container_of(timer, struct mac80211_hwsim_data, beacon_timer); struct ieee80211_hw *hw = data->hw; u64 bcn_int = data->beacon_int; - ktime_t next_bcn; if (!data->started) - goto out; + return HRTIMER_NORESTART; ieee80211_iterate_active_interfaces_atomic( hw, IEEE80211_IFACE_ITER_NORMAL, @@ -1601,12 +1599,9 @@ mac80211_hwsim_beacon(struct hrtimer *timer) bcn_int -= data->bcn_delta; data->bcn_delta = 0; } - - next_bcn = ktime_add(hrtimer_get_expires(timer), - ns_to_ktime(bcn_int * 1000)); - tasklet_hrtimer_start(&data->beacon_timer, next_bcn, HRTIMER_MODE_ABS); -out: - return HRTIMER_NORESTART; + hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer), + ns_to_ktime(bcn_int * NSEC_PER_USEC)); + return HRTIMER_RESTART; } static const char * const hwsim_chanwidths[] = { @@ -1680,15 +1675,15 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed) mutex_unlock(&data->mutex); if (!data->started || !data->beacon_int) - tasklet_hrtimer_cancel(&data->beacon_timer); - else if (!hrtimer_is_queued(&data->beacon_timer.timer)) { + hrtimer_cancel(&data->beacon_timer); + else if (!hrtimer_is_queued(&data->beacon_timer)) { u64 tsf = mac80211_hwsim_get_tsf(hw, NULL); u32 bcn_int = data->beacon_int; u64 until_tbtt = bcn_int - do_div(tsf, bcn_int); - tasklet_hrtimer_start(&data->beacon_timer, - ns_to_ktime(until_tbtt * 1000), - HRTIMER_MODE_REL); + hrtimer_start(&data->beacon_timer, + ns_to_ktime(until_tbtt * NSEC_PER_USEC), + HRTIMER_MODE_REL_SOFT); } return 0; @@ -1751,7 +1746,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, info->enable_beacon, info->beacon_int); vp->bcn_en = info->enable_beacon; if (data->started && - !hrtimer_is_queued(&data->beacon_timer.timer) && + !hrtimer_is_queued(&data->beacon_timer) && info->enable_beacon) { u64 tsf, until_tbtt; u32 bcn_int; @@ -1759,9 +1754,10 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, tsf = mac80211_hwsim_get_tsf(hw, vif); bcn_int = data->beacon_int; until_tbtt = bcn_int - do_div(tsf, bcn_int); - tasklet_hrtimer_start(&data->beacon_timer, - ns_to_ktime(until_tbtt * 1000), - HRTIMER_MODE_REL); + + hrtimer_start(&data->beacon_timer, + ns_to_ktime(until_tbtt * NSEC_PER_USEC), + HRTIMER_MODE_REL_SOFT); } else if (!info->enable_beacon) { unsigned int count = 0; ieee80211_iterate_active_interfaces_atomic( @@ -1770,7 +1766,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw, wiphy_dbg(hw->wiphy, " beaconing vifs remaining: %u", count); if (count == 0) { - tasklet_hrtimer_cancel(&data->beacon_timer); + hrtimer_cancel(&data->beacon_timer); data->beacon_int = 0; } } @@ -2933,9 +2929,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info, wiphy_ext_feature_set(hw->wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST); - tasklet_hrtimer_init(&data->beacon_timer, - mac80211_hwsim_beacon, - CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + hrtimer_init(&data->beacon_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_SOFT); + data->beacon_timer.function = mac80211_hwsim_beacon; err = ieee80211_register_hw(hw); if (err < 0) { diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 690b238a44d5..c7eef32e7739 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -668,31 +668,6 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); extern void tasklet_init(struct tasklet_struct *t, void (*func)(unsigned long), unsigned long data); -struct tasklet_hrtimer { - struct hrtimer timer; - struct tasklet_struct tasklet; - enum hrtimer_restart (*function)(struct hrtimer *); -}; - -extern void -tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, - enum hrtimer_restart (*function)(struct hrtimer *), - clockid_t which_clock, enum hrtimer_mode mode); - -static inline -void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time, - const enum hrtimer_mode mode) -{ - hrtimer_start(&ttimer->timer, time, mode); -} - -static inline -void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer) -{ - hrtimer_cancel(&ttimer->timer); - tasklet_kill(&ttimer->tasklet); -} - /* * Autoprobing for irqs: * diff --git a/include/linux/tick.h b/include/linux/tick.h index 55388ab45fd4..76acb48acdb7 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -68,6 +68,12 @@ extern void tick_broadcast_control(enum tick_broadcast_mode mode); static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { } #endif /* BROADCAST */ +#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_offline_cpu(unsigned int cpu); +#else +static inline void tick_offline_cpu(unsigned int cpu) { } +#endif + #ifdef CONFIG_GENERIC_CLOCKEVENTS extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state); #else diff --git a/include/linux/time64.h b/include/linux/time64.h index f38d382ffec1..a620ee610b9f 100644 --- a/include/linux/time64.h +++ b/include/linux/time64.h @@ -33,6 +33,17 @@ struct itimerspec64 { #define KTIME_MAX ((s64)~((u64)1 << 63)) #define KTIME_SEC_MAX (KTIME_MAX / NSEC_PER_SEC) +/* + * Limits for settimeofday(): + * + * To prevent setting the time close to the wraparound point time setting + * is limited so a reasonable uptime can be accomodated. Uptime of 30 years + * should be really sufficient, which means the cutoff is 2232. At that + * point the cutoff is just a small part of the larger problem. + */ +#define TIME_UPTIME_SEC_MAX (30LL * 365 * 24 *3600) +#define TIME_SETTOD_SEC_MAX (KTIME_SEC_MAX - TIME_UPTIME_SEC_MAX) + static inline int timespec64_equal(const struct timespec64 *a, const struct timespec64 *b) { @@ -100,6 +111,16 @@ static inline bool timespec64_valid_strict(const struct timespec64 *ts) return true; } +static inline bool timespec64_valid_settod(const struct timespec64 *ts) +{ + if (!timespec64_valid(ts)) + return false; + /* Disallow values which cause overflow issues vs. CLOCK_REALTIME */ + if ((unsigned long long)ts->tv_sec >= TIME_SETTOD_SEC_MAX) + return false; + return true; +} + /** * timespec64_to_ns - Convert timespec64 to nanoseconds * @ts: pointer to the timespec64 variable to be converted diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c9b0b2b5d672..99f722c4d804 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -219,7 +219,7 @@ struct xfrm_state { struct xfrm_stats stats; struct xfrm_lifetime_cur curlft; - struct tasklet_hrtimer mtimer; + struct hrtimer mtimer; struct xfrm_state_offload xso; diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h index a57e4ee989d6..b7a904825e7d 100644 --- a/include/trace/events/timer.h +++ b/include/trace/events/timer.h @@ -73,7 +73,7 @@ TRACE_EVENT(timer_start, __entry->flags = flags; ), - TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", + TP_printk("timer=%p function=%ps expires=%lu [timeout=%ld] cpu=%u idx=%u flags=%s", __entry->timer, __entry->function, __entry->expires, (long)__entry->expires - __entry->now, __entry->flags & TIMER_CPUMASK, @@ -89,23 +89,27 @@ TRACE_EVENT(timer_start, */ TRACE_EVENT(timer_expire_entry, - TP_PROTO(struct timer_list *timer), + TP_PROTO(struct timer_list *timer, unsigned long baseclk), - TP_ARGS(timer), + TP_ARGS(timer, baseclk), TP_STRUCT__entry( __field( void *, timer ) __field( unsigned long, now ) __field( void *, function) + __field( unsigned long, baseclk ) ), TP_fast_assign( __entry->timer = timer; __entry->now = jiffies; __entry->function = timer->function; + __entry->baseclk = baseclk; ), - TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now) + TP_printk("timer=%p function=%ps now=%lu baseclk=%lu", + __entry->timer, __entry->function, __entry->now, + __entry->baseclk) ); /** @@ -210,7 +214,7 @@ TRACE_EVENT(hrtimer_start, __entry->mode = mode; ), - TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu " + TP_printk("hrtimer=%p function=%ps expires=%llu softexpires=%llu " "mode=%s", __entry->hrtimer, __entry->function, (unsigned long long) __entry->expires, (unsigned long long) __entry->softexpires, @@ -243,7 +247,8 @@ TRACE_EVENT(hrtimer_expire_entry, __entry->function = hrtimer->function; ), - TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function, + TP_printk("hrtimer=%p function=%ps now=%llu", + __entry->hrtimer, __entry->function, (unsigned long long) __entry->now) ); diff --git a/kernel/cpu.c b/kernel/cpu.c index 291757ed10c1..f2ef10460698 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -861,6 +861,8 @@ static int take_cpu_down(void *_param) /* Give up timekeeping duties */ tick_handover_do_timer(); + /* Remove CPU from timer broadcasting */ + tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; diff --git a/kernel/softirq.c b/kernel/softirq.c index 10277429ed84..2c3382378d94 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -573,57 +573,6 @@ void tasklet_kill(struct tasklet_struct *t) } EXPORT_SYMBOL(tasklet_kill); -/* - * tasklet_hrtimer - */ - -/* - * The trampoline is called when the hrtimer expires. It schedules a tasklet - * to run __tasklet_hrtimer_trampoline() which in turn will call the intended - * hrtimer callback, but from softirq context. - */ -static enum hrtimer_restart __hrtimer_tasklet_trampoline(struct hrtimer *timer) -{ - struct tasklet_hrtimer *ttimer = - container_of(timer, struct tasklet_hrtimer, timer); - - tasklet_hi_schedule(&ttimer->tasklet); - return HRTIMER_NORESTART; -} - -/* - * Helper function which calls the hrtimer callback from - * tasklet/softirq context - */ -static void __tasklet_hrtimer_trampoline(unsigned long data) -{ - struct tasklet_hrtimer *ttimer = (void *)data; - enum hrtimer_restart restart; - - restart = ttimer->function(&ttimer->timer); - if (restart != HRTIMER_NORESTART) - hrtimer_restart(&ttimer->timer); -} - -/** - * tasklet_hrtimer_init - Init a tasklet/hrtimer combo for softirq callbacks - * @ttimer: tasklet_hrtimer which is initialized - * @function: hrtimer callback function which gets called from softirq context - * @which_clock: clock id (CLOCK_MONOTONIC/CLOCK_REALTIME) - * @mode: hrtimer mode (HRTIMER_MODE_ABS/HRTIMER_MODE_REL) - */ -void tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer, - enum hrtimer_restart (*function)(struct hrtimer *), - clockid_t which_clock, enum hrtimer_mode mode) -{ - hrtimer_init(&ttimer->timer, which_clock, mode); - ttimer->timer.function = __hrtimer_tasklet_trampoline; - tasklet_init(&ttimer->tasklet, __tasklet_hrtimer_trampoline, - (unsigned long)ttimer); - ttimer->function = function; -} -EXPORT_SYMBOL_GPL(tasklet_hrtimer_init); - void __init softirq_init(void) { int cpu; 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/jiffies.c b/kernel/time/jiffies.c index ac9c03dd6c7d..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 { diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c index 930113b9799a..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 { @@ -267,7 +267,7 @@ 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; } diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index ee834d4fb814..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 /* @@ -433,27 +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) @@ -801,13 +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 @@ -950,14 +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! @@ -965,8 +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 e49e8091f9ac..59225b484e4e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -157,7 +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 { 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 4aa917acbe1c..bdf00c763ee3 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -654,7 +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 { 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 c3f756f8534b..86656bbac232 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -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); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index f986e1918d12..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); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 2fce056f8a49..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 @@ -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); } } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 178baaa037e5..c62f712fdaf7 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -434,7 +434,7 @@ EXPORT_SYMBOL(xfrm_state_free); static void ___xfrm_state_destroy(struct xfrm_state *x) { - tasklet_hrtimer_cancel(&x->mtimer); + hrtimer_cancel(&x->mtimer); del_timer_sync(&x->rtimer); kfree(x->aead); kfree(x->aalg); @@ -479,8 +479,8 @@ static void xfrm_state_gc_task(struct work_struct *work) static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { - struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer); - struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer); + struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer); + enum hrtimer_restart ret = HRTIMER_NORESTART; time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; @@ -544,7 +544,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) km_state_expired(x, 0, 0); resched: if (next != TIME64_MAX) { - tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL); + hrtimer_forward_now(&x->mtimer, ktime_set(next, 0)); + ret = HRTIMER_RESTART; } goto out; @@ -561,7 +562,7 @@ expired: out: spin_unlock(&x->lock); - return HRTIMER_NORESTART; + return ret; } static void xfrm_replay_timer_handler(struct timer_list *t); @@ -580,8 +581,8 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); - tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler, - CLOCK_BOOTTIME, HRTIMER_MODE_ABS); + hrtimer_init(&x->mtimer, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT); + x->mtimer.function = xfrm_timer_handler; timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); x->curlft.add_time = ktime_get_real_seconds(); x->lft.soft_byte_limit = XFRM_INF; @@ -1047,7 +1048,9 @@ found: hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; - tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, + ktime_set(net->xfrm.sysctl_acq_expires, 0), + HRTIMER_MODE_REL_SOFT); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); spin_unlock_bh(&net->xfrm.xfrm_state_lock); @@ -1159,7 +1162,7 @@ static void __xfrm_state_insert(struct xfrm_state *x) hlist_add_head_rcu(&x->byspi, net->xfrm.state_byspi + h); } - tasklet_hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); @@ -1266,7 +1269,9 @@ static struct xfrm_state *__find_acq_core(struct net *net, x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; xfrm_state_hold(x); - tasklet_hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, + ktime_set(net->xfrm.sysctl_acq_expires, 0), + HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); hlist_add_head_rcu(&x->bydst, net->xfrm.state_bydst + h); h = xfrm_src_hash(net, daddr, saddr, family); @@ -1571,7 +1576,8 @@ out: memcpy(&x1->lft, &x->lft, sizeof(x1->lft)); x1->km.dying = 0; - tasklet_hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL); + hrtimer_start(&x1->mtimer, ktime_set(1, 0), + HRTIMER_MODE_REL_SOFT); if (x1->curlft.use_time) xfrm_state_check_expire(x1); @@ -1610,7 +1616,7 @@ int xfrm_state_check_expire(struct xfrm_state *x) if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; - tasklet_hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL); + hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT); return -EINVAL; }