diff options
Diffstat (limited to 'kernel/time')
| -rw-r--r-- | kernel/time/Kconfig | 2 | ||||
| -rw-r--r-- | kernel/time/clockevents.c | 24 | ||||
| -rw-r--r-- | kernel/time/hrtimer.c | 36 | ||||
| -rw-r--r-- | kernel/time/ntp.c | 5 | ||||
| -rw-r--r-- | kernel/time/tick-broadcast-hrtimer.c | 49 | ||||
| -rw-r--r-- | kernel/time/tick-broadcast.c | 164 | ||||
| -rw-r--r-- | kernel/time/tick-common.c | 25 | ||||
| -rw-r--r-- | kernel/time/tick-sched.c | 72 | ||||
| -rw-r--r-- | kernel/time/tick-sched.h | 10 | ||||
| -rw-r--r-- | kernel/time/time.c | 53 | ||||
| -rw-r--r-- | kernel/time/timekeeping.c | 19 | ||||
| -rw-r--r-- | kernel/time/timer.c | 4 | ||||
| -rw-r--r-- | kernel/time/timer_list.c | 2 |
13 files changed, 267 insertions, 198 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index 579ce1b929af..4008d9f95dd7 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -92,12 +92,10 @@ config NO_HZ_FULL depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS # We need at least one periodic CPU for timekeeping depends on SMP - # RCU_USER_QS dependency depends on HAVE_CONTEXT_TRACKING # VIRT_CPU_ACCOUNTING_GEN dependency depends on HAVE_VIRT_CPU_ACCOUNTING_GEN select NO_HZ_COMMON - select RCU_USER_QS select RCU_NOCB_CPU select VIRT_CPU_ACCOUNTING_GEN select IRQ_WORK diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 08ccc3da3ca0..50eb107f1198 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -120,19 +120,25 @@ static int __clockevents_switch_state(struct clock_event_device *dev, /* The clockevent device is getting replaced. Shut it down. */ case CLOCK_EVT_STATE_SHUTDOWN: - return dev->set_state_shutdown(dev); + if (dev->set_state_shutdown) + return dev->set_state_shutdown(dev); + return 0; case CLOCK_EVT_STATE_PERIODIC: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC)) return -ENOSYS; - return dev->set_state_periodic(dev); + if (dev->set_state_periodic) + return dev->set_state_periodic(dev); + return 0; case CLOCK_EVT_STATE_ONESHOT: /* Core internal bug */ if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT)) return -ENOSYS; - return dev->set_state_oneshot(dev); + if (dev->set_state_oneshot) + return dev->set_state_oneshot(dev); + return 0; case CLOCK_EVT_STATE_ONESHOT_STOPPED: /* Core internal bug */ @@ -471,18 +477,6 @@ static int clockevents_sanity_check(struct clock_event_device *dev) if (dev->features & CLOCK_EVT_FEAT_DUMMY) return 0; - /* New state-specific callbacks */ - if (!dev->set_state_shutdown) - return -EINVAL; - - if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && - !dev->set_state_periodic) - return -EINVAL; - - if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) && - !dev->set_state_oneshot) - return -EINVAL; - return 0; } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 5c7ae4b641c4..457a373e2181 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -183,7 +183,7 @@ struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { if (pinned || !base->migration_enabled) - return this_cpu_ptr(&hrtimer_bases); + return base; return &per_cpu(hrtimer_bases, get_nohz_timer_target()); } #else @@ -191,23 +191,32 @@ static inline struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, int pinned) { - return this_cpu_ptr(&hrtimer_bases); + return base; } #endif /* - * Switch the timer base to the current CPU when possible. + * We switch the timer base to a power-optimized selected CPU target, + * if: + * - NO_HZ_COMMON is enabled + * - timer migration is enabled + * - the timer callback is not running + * - the timer is not the first expiring timer on the new target + * + * If one of the above requirements is not fulfilled we move the timer + * to the current CPU or leave it on the previously assigned CPU if + * the timer callback is currently running. */ static inline struct hrtimer_clock_base * switch_hrtimer_base(struct hrtimer *timer, struct hrtimer_clock_base *base, int pinned) { - struct hrtimer_cpu_base *new_cpu_base, *this_base; + struct hrtimer_cpu_base *new_cpu_base, *this_cpu_base; struct hrtimer_clock_base *new_base; int basenum = base->index; - this_base = this_cpu_ptr(&hrtimer_bases); - new_cpu_base = get_target_base(this_base, pinned); + this_cpu_base = this_cpu_ptr(&hrtimer_bases); + new_cpu_base = get_target_base(this_cpu_base, pinned); again: new_base = &new_cpu_base->clock_base[basenum]; @@ -229,19 +238,19 @@ again: raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); - if (new_cpu_base != this_base && + if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { raw_spin_unlock(&new_base->cpu_base->lock); raw_spin_lock(&base->cpu_base->lock); - new_cpu_base = this_base; + new_cpu_base = this_cpu_base; timer->base = base; goto again; } timer->base = new_base; } else { - if (new_cpu_base != this_base && + if (new_cpu_base != this_cpu_base && hrtimer_check_target(timer, new_base)) { - new_cpu_base = this_base; + new_cpu_base = this_cpu_base; goto again; } } @@ -679,14 +688,14 @@ static void retrigger_next_event(void *arg) /* * Switch to high resolution mode */ -static int hrtimer_switch_to_hres(void) +static void hrtimer_switch_to_hres(void) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { printk(KERN_WARNING "Could not switch to high resolution " "mode on CPU %d\n", base->cpu); - return 0; + return; } base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; @@ -694,7 +703,6 @@ static int hrtimer_switch_to_hres(void) tick_setup_sched_timer(); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); - return 1; } static void clock_was_set_work(struct work_struct *work) @@ -718,7 +726,7 @@ void clock_was_set_delayed(void) static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *b) { return 0; } static inline int hrtimer_hres_active(void) { return 0; } static inline int hrtimer_is_hres_enabled(void) { return 0; } -static inline int hrtimer_switch_to_hres(void) { return 0; } +static inline void hrtimer_switch_to_hres(void) { } static inline void hrtimer_force_reprogram(struct hrtimer_cpu_base *base, int skip_equal) { } static inline int hrtimer_reprogram(struct hrtimer *timer, diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index fb4d98c7fd43..df68cb875248 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -487,6 +487,11 @@ out: } #ifdef CONFIG_GENERIC_CMOS_UPDATE +int __weak update_persistent_clock(struct timespec now) +{ + return -ENODEV; +} + int __weak update_persistent_clock64(struct timespec64 now64) { struct timespec now; diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 3e7db49a2381..53d7184da0be 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -18,30 +18,23 @@ static struct hrtimer bctimer; -static void bc_set_mode(enum clock_event_mode mode, - struct clock_event_device *bc) +static int bc_shutdown(struct clock_event_device *evt) { - switch (mode) { - case CLOCK_EVT_MODE_UNUSED: - case CLOCK_EVT_MODE_SHUTDOWN: - /* - * Note, we cannot cancel the timer here as we might - * run into the following live lock scenario: - * - * cpu 0 cpu1 - * lock(broadcast_lock); - * hrtimer_interrupt() - * bc_handler() - * tick_handle_oneshot_broadcast(); - * lock(broadcast_lock); - * hrtimer_cancel() - * wait_for_callback() - */ - hrtimer_try_to_cancel(&bctimer); - break; - default: - break; - } + /* + * Note, we cannot cancel the timer here as we might + * run into the following live lock scenario: + * + * cpu 0 cpu1 + * lock(broadcast_lock); + * hrtimer_interrupt() + * bc_handler() + * tick_handle_oneshot_broadcast(); + * lock(broadcast_lock); + * hrtimer_cancel() + * wait_for_callback() + */ + hrtimer_try_to_cancel(&bctimer); + return 0; } /* @@ -82,7 +75,7 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) } static struct clock_event_device ce_broadcast_hrtimer = { - .set_mode = bc_set_mode, + .set_state_shutdown = bc_shutdown, .set_next_ktime = bc_set_next, .features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_KTIME | @@ -102,13 +95,11 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) { ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); - switch (ce_broadcast_hrtimer.mode) { - case CLOCK_EVT_MODE_ONESHOT: + if (clockevent_state_oneshot(&ce_broadcast_hrtimer)) if (ce_broadcast_hrtimer.next_event.tv64 != KTIME_MAX) return HRTIMER_RESTART; - default: - return HRTIMER_NORESTART; - } + + return HRTIMER_NORESTART; } void tick_setup_hrtimer_broadcast(void) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index d39f32cdd1b5..f6aae7977824 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -159,7 +159,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) { struct clock_event_device *bc = tick_broadcast_device.evtdev; unsigned long flags; - int ret; + int ret = 0; raw_spin_lock_irqsave(&tick_broadcast_lock, flags); @@ -221,13 +221,14 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu) * If we kept the cpu in the broadcast mask, * tell the caller to leave the per cpu device * in shutdown state. The periodic interrupt - * is delivered by the broadcast device. + * is delivered by the broadcast device, if + * the broadcast device exists and is not + * hrtimer based. */ - ret = cpumask_test_cpu(cpu, tick_broadcast_mask); + if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER)) + ret = cpumask_test_cpu(cpu, tick_broadcast_mask); break; default: - /* Nothing to do */ - ret = 0; break; } } @@ -265,8 +266,22 @@ static bool tick_do_broadcast(struct cpumask *mask) * Check, if the current cpu is in the mask */ if (cpumask_test_cpu(cpu, mask)) { + struct clock_event_device *bc = tick_broadcast_device.evtdev; + cpumask_clear_cpu(cpu, mask); - local = true; + /* + * We only run the local handler, if the broadcast + * device is not hrtimer based. Otherwise we run into + * a hrtimer recursion. + * + * local timer_interrupt() + * local_handler() + * expire_hrtimers() + * bc_handler() + * local_handler() + * expire_hrtimers() + */ + local = !(bc->features & CLOCK_EVT_FEAT_HRTIMER); } if (!cpumask_empty(mask)) { @@ -301,6 +316,13 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) bool bc_local; raw_spin_lock(&tick_broadcast_lock); + + /* Handle spurious interrupts gracefully */ + if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) { + raw_spin_unlock(&tick_broadcast_lock); + return; + } + bc_local = tick_do_periodic_broadcast(); if (clockevent_state_oneshot(dev)) { @@ -359,8 +381,16 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) case TICK_BROADCAST_ON: cpumask_set_cpu(cpu, tick_broadcast_on); if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) { - if (tick_broadcast_device.mode == - TICKDEV_MODE_PERIODIC) + /* + * Only shutdown the cpu local device, if: + * + * - the broadcast device exists + * - the broadcast device is not a hrtimer based one + * - the broadcast device is in periodic mode to + * avoid a hickup during switch to oneshot mode + */ + if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) && + tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) clockevents_shutdown(dev); } break; @@ -379,14 +409,16 @@ void tick_broadcast_control(enum tick_broadcast_mode mode) break; } - if (cpumask_empty(tick_broadcast_mask)) { - if (!bc_stopped) - clockevents_shutdown(bc); - } else if (bc_stopped) { - if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) - tick_broadcast_start_periodic(bc); - else - tick_broadcast_setup_oneshot(bc); + if (bc) { + if (cpumask_empty(tick_broadcast_mask)) { + if (!bc_stopped) + clockevents_shutdown(bc); + } else if (bc_stopped) { + if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) + tick_broadcast_start_periodic(bc); + else + tick_broadcast_setup_oneshot(bc); + } } raw_spin_unlock(&tick_broadcast_lock); } @@ -662,71 +694,82 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } -/** - * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode - * @state: The target state (enter/exit) - * - * The system enters/leaves a state, where affected devices might stop - * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. - * - * Called with interrupts disabled, so clockevents_lock is not - * required here because the local clock event device cannot go away - * under us. - */ -int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) { struct clock_event_device *bc, *dev; - struct tick_device *td; int cpu, ret = 0; ktime_t now; /* - * Periodic mode does not care about the enter/exit of power - * states + * If there is no broadcast device, tell the caller not to go + * into deep idle. */ - if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) - return 0; + if (!tick_broadcast_device.evtdev) + return -EBUSY; - /* - * We are called with preemtion disabled from the depth of the - * idle code, so we can't be moved away. - */ - td = this_cpu_ptr(&tick_cpu_device); - dev = td->evtdev; - - if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) - return 0; + dev = this_cpu_ptr(&tick_cpu_device)->evtdev; raw_spin_lock(&tick_broadcast_lock); bc = tick_broadcast_device.evtdev; cpu = smp_processor_id(); if (state == TICK_BROADCAST_ENTER) { + /* + * If the current CPU owns the hrtimer broadcast + * mechanism, it cannot go deep idle and we do not add + * the CPU to the broadcast mask. We don't have to go + * through the EXIT path as the local timer is not + * shutdown. + */ + ret = broadcast_needs_cpu(bc, cpu); + if (ret) + goto out; + + /* + * If the broadcast device is in periodic mode, we + * return. + */ + if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) { + /* If it is a hrtimer based broadcast, return busy */ + if (bc->features & CLOCK_EVT_FEAT_HRTIMER) + ret = -EBUSY; + goto out; + } + if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) { WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask)); + + /* Conditionally shut down the local timer. */ broadcast_shutdown_local(bc, dev); + /* * We only reprogram the broadcast timer if we * did not mark ourself in the force mask and * if the cpu local event is earlier than the * broadcast event. If the current CPU is in * the force mask, then we are going to be - * woken by the IPI right away. + * woken by the IPI right away; we return + * busy, so the CPU does not try to go deep + * idle. */ - if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) && - dev->next_event.tv64 < bc->next_event.tv64) + if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) { + ret = -EBUSY; + } else if (dev->next_event.tv64 < bc->next_event.tv64) { tick_broadcast_set_event(bc, cpu, dev->next_event); + /* + * In case of hrtimer broadcasts the + * programming might have moved the + * timer to this cpu. If yes, remove + * us from the broadcast mask and + * return busy. + */ + ret = broadcast_needs_cpu(bc, cpu); + if (ret) { + cpumask_clear_cpu(cpu, + tick_broadcast_oneshot_mask); + } + } } - /* - * If the current CPU owns the hrtimer broadcast - * mechanism, it cannot go deep idle and we remove the - * CPU from the broadcast mask. We don't have to go - * through the EXIT path as the local timer is not - * shutdown. - */ - ret = broadcast_needs_cpu(bc, cpu); - if (ret) - cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); @@ -796,7 +839,6 @@ out: raw_spin_unlock(&tick_broadcast_lock); return ret; } -EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); /* * Reset the one shot broadcast for a cpu @@ -938,6 +980,16 @@ bool tick_broadcast_oneshot_available(void) return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false; } +#else +int __tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + struct clock_event_device *bc = tick_broadcast_device.evtdev; + + if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER)) + return -EBUSY; + + return 0; +} #endif void __init tick_broadcast_init(void) diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 76446cb5dfe1..d11c55b6ab7d 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -304,9 +304,6 @@ void tick_check_new_device(struct clock_event_device *newdev) int cpu; cpu = smp_processor_id(); - if (!cpumask_test_cpu(cpu, newdev->cpumask)) - goto out_bc; - td = &per_cpu(tick_cpu_device, cpu); curdev = td->evtdev; @@ -343,6 +340,28 @@ out_bc: tick_install_broadcast_device(newdev); } +/** + * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode + * @state: The target state (enter/exit) + * + * The system enters/leaves a state, where affected devices might stop + * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups. + * + * Called with interrupts disabled, so clockevents_lock is not + * required here because the local clock event device cannot go away + * under us. + */ +int tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + + if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP)) + return 0; + + return __tick_broadcast_oneshot_control(state); +} +EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); + #ifdef CONFIG_HOTPLUG_CPU /* * Transfer the do_timer job away from a dying cpu. diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index c792429e98c6..3319e16f31e5 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -197,27 +197,9 @@ static bool can_stop_full_tick(void) return true; } -static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now); - -/* - * Re-evaluate the need for the tick on the current CPU - * and restart it if necessary. - */ -void __tick_nohz_full_check(void) -{ - struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - - if (tick_nohz_full_cpu(smp_processor_id())) { - if (ts->tick_stopped && !is_idle_task(current)) { - if (!can_stop_full_tick()) - tick_nohz_restart_sched_tick(ts, ktime_get()); - } - } -} - static void nohz_full_kick_work_func(struct irq_work *work) { - __tick_nohz_full_check(); + /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { @@ -252,7 +234,7 @@ void tick_nohz_full_kick_cpu(int cpu) static void nohz_full_kick_ipi(void *info) { - __tick_nohz_full_check(); + /* Empty, the tick restart happens on tick_nohz_irq_exit() */ } /* @@ -276,7 +258,7 @@ void tick_nohz_full_kick_all(void) * It might need the tick due to per task/process properties: * perf events, posix cpu timers, ... */ -void __tick_nohz_task_switch(struct task_struct *tsk) +void __tick_nohz_task_switch(void) { unsigned long flags; @@ -705,21 +687,38 @@ out: return tick; } -static void tick_nohz_full_stop_tick(struct tick_sched *ts) +static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) +{ + /* Update jiffies first */ + tick_do_update_jiffies64(now); + update_cpu_load_nohz(); + + calc_load_exit_idle(); + touch_softlockup_watchdog(); + /* + * Cancel the scheduled timer and restore the tick + */ + ts->tick_stopped = 0; + ts->idle_exittime = now; + + tick_nohz_restart(ts, now); +} + +static void tick_nohz_full_update_tick(struct tick_sched *ts) { #ifdef CONFIG_NO_HZ_FULL int cpu = smp_processor_id(); - if (!tick_nohz_full_cpu(cpu) || is_idle_task(current)) + if (!tick_nohz_full_cpu(cpu)) return; if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) return; - if (!can_stop_full_tick()) - return; - - tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); + if (can_stop_full_tick()) + tick_nohz_stop_sched_tick(ts, ktime_get(), cpu); + else if (ts->tick_stopped) + tick_nohz_restart_sched_tick(ts, ktime_get()); #endif } @@ -849,7 +848,7 @@ void tick_nohz_irq_exit(void) if (ts->inidle) __tick_nohz_idle_enter(ts); else - tick_nohz_full_stop_tick(ts); + tick_nohz_full_update_tick(ts); } /** @@ -864,23 +863,6 @@ ktime_t tick_nohz_get_sleep_length(void) return ts->sleep_length; } -static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) -{ - /* Update jiffies first */ - tick_do_update_jiffies64(now); - update_cpu_load_nohz(); - - calc_load_exit_idle(); - touch_softlockup_watchdog(); - /* - * Cancel the scheduled timer and restore the tick - */ - ts->tick_stopped = 0; - ts->idle_exittime = now; - - tick_nohz_restart(ts, now); -} - static void tick_nohz_account_idle_ticks(struct tick_sched *ts) { #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 42fdf4958bcc..a4a8d4e9baa1 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -71,4 +71,14 @@ extern void tick_cancel_sched_timer(int cpu); static inline void tick_cancel_sched_timer(int cpu) { } #endif +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +extern int __tick_broadcast_oneshot_control(enum tick_broadcast_state state); +#else +static inline int +__tick_broadcast_oneshot_control(enum tick_broadcast_state state) +{ + return -EBUSY; +} +#endif + #endif diff --git a/kernel/time/time.c b/kernel/time/time.c index 85d5bb1d67eb..86751c68e08d 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -268,10 +268,14 @@ EXPORT_SYMBOL(jiffies_to_msecs); unsigned int jiffies_to_usecs(const unsigned long j) { -#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) + /* + * Hz usually doesn't go much further MSEC_PER_SEC. + * jiffies_to_usecs() and usecs_to_jiffies() depend on that. + */ + BUILD_BUG_ON(HZ > USEC_PER_SEC); + +#if !(USEC_PER_SEC % HZ) return (USEC_PER_SEC / HZ) * j; -#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) - return (j + (HZ / USEC_PER_SEC) - 1)/(HZ / USEC_PER_SEC); #else # if BITS_PER_LONG == 32 return (HZ_TO_USEC_MUL32 * j) >> HZ_TO_USEC_SHR32; @@ -287,26 +291,20 @@ EXPORT_SYMBOL(jiffies_to_usecs); * @t: Timespec * @gran: Granularity in ns. * - * Truncate a timespec to a granularity. gran must be smaller than a second. - * Always rounds down. - * - * This function should be only used for timestamps returned by - * current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because - * it doesn't handle the better resolution of the latter. + * Truncate a timespec to a granularity. Always rounds down. gran must + * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec timespec_trunc(struct timespec t, unsigned gran) { - /* - * Division is pretty slow so avoid it for common cases. - * Currently current_kernel_time() never returns better than - * jiffies resolution. Exploit that. - */ - if (gran <= jiffies_to_usecs(1) * 1000) { + /* Avoid division in the common cases 1 ns and 1 s. */ + if (gran == 1) { /* nothing */ - } else if (gran == 1000000000) { + } else if (gran == NSEC_PER_SEC) { t.tv_nsec = 0; - } else { + } else if (gran > 1 && gran < NSEC_PER_SEC) { t.tv_nsec -= t.tv_nsec % gran; + } else { + WARN(1, "illegal file time granularity: %u", gran); } return t; } @@ -546,7 +544,7 @@ EXPORT_SYMBOL(__usecs_to_jiffies); * value to a scaled second value. */ static unsigned long -__timespec_to_jiffies(unsigned long sec, long nsec) +__timespec64_to_jiffies(u64 sec, long nsec) { nsec = nsec + TICK_NSEC - 1; @@ -554,22 +552,27 @@ __timespec_to_jiffies(unsigned long sec, long nsec) sec = MAX_SEC_IN_JIFFIES; nsec = 0; } - return (((u64)sec * SEC_CONVERSION) + + return ((sec * SEC_CONVERSION) + (((u64)nsec * NSEC_CONVERSION) >> (NSEC_JIFFIE_SC - SEC_JIFFIE_SC))) >> SEC_JIFFIE_SC; } -unsigned long -timespec_to_jiffies(const struct timespec *value) +static unsigned long +__timespec_to_jiffies(unsigned long sec, long nsec) { - return __timespec_to_jiffies(value->tv_sec, value->tv_nsec); + return __timespec64_to_jiffies((u64)sec, nsec); } -EXPORT_SYMBOL(timespec_to_jiffies); +unsigned long +timespec64_to_jiffies(const struct timespec64 *value) +{ + return __timespec64_to_jiffies(value->tv_sec, value->tv_nsec); +} +EXPORT_SYMBOL(timespec64_to_jiffies); void -jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) +jiffies_to_timespec64(const unsigned long jiffies, struct timespec64 *value) { /* * Convert jiffies to nanoseconds and separate with @@ -580,7 +583,7 @@ jiffies_to_timespec(const unsigned long jiffies, struct timespec *value) NSEC_PER_SEC, &rem); value->tv_nsec = rem; } -EXPORT_SYMBOL(jiffies_to_timespec); +EXPORT_SYMBOL(jiffies_to_timespec64); /* * We could use a similar algorithm to timespec_to_jiffies (with a diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index bca3667a2de1..f6ee2e6b6f5d 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -911,6 +911,7 @@ int do_settimeofday64(const struct timespec64 *ts) struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; + int ret = 0; if (!timespec64_valid_strict(ts)) return -EINVAL; @@ -924,10 +925,15 @@ int do_settimeofday64(const struct timespec64 *ts) ts_delta.tv_sec = ts->tv_sec - xt.tv_sec; ts_delta.tv_nsec = ts->tv_nsec - xt.tv_nsec; + if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { + ret = -EINVAL; + goto out; + } + tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); - +out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); @@ -936,7 +942,7 @@ int do_settimeofday64(const struct timespec64 *ts) /* signal hrtimers about time change */ clock_was_set(); - return 0; + return ret; } EXPORT_SYMBOL(do_settimeofday64); @@ -965,7 +971,8 @@ int timekeeping_inject_offset(struct timespec *ts) /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), ts64); - if (!timespec64_valid_strict(&tmp)) { + if (timespec64_compare(&tk->wall_to_monotonic, &ts64) > 0 || + !timespec64_valid_strict(&tmp)) { ret = -EINVAL; goto error; } @@ -1874,7 +1881,7 @@ struct timespec __current_kernel_time(void) return timespec64_to_timespec(tk_xtime(tk)); } -struct timespec current_kernel_time(void) +struct timespec64 current_kernel_time64(void) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now; @@ -1886,9 +1893,9 @@ struct timespec current_kernel_time(void) now = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); - return timespec64_to_timespec(now); + return now; } -EXPORT_SYMBOL(current_kernel_time); +EXPORT_SYMBOL(current_kernel_time64); struct timespec64 get_monotonic_coarse64(void) { diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 5e097fa9faf7..84190f02b521 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -807,8 +807,8 @@ __mod_timer(struct timer_list *timer, unsigned long expires, spin_unlock(&base->lock); base = new_base; spin_lock(&base->lock); - timer->flags &= ~TIMER_BASEMASK; - timer->flags |= base->cpu; + WRITE_ONCE(timer->flags, + (timer->flags & ~TIMER_BASEMASK) | base->cpu); } } diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index a4536e1e3e2a..129c96033e46 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -137,7 +137,7 @@ print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) (unsigned long long) ktime_to_ns(base->offset)); #endif SEQ_printf(m, "active timers:\n"); - print_active_timers(m, base, now); + print_active_timers(m, base, now + ktime_to_ns(base->offset)); } static void print_cpu(struct seq_file *m, int cpu, u64 now) |