diff options
Diffstat (limited to 'kernel')
33 files changed, 1142 insertions, 1263 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c index f2003b97ddc9..8e13f3e54ec3 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -51,9 +51,11 @@ static struct workqueue_struct *perf_wq; +typedef int (*remote_function_f)(void *); + struct remote_function_call { struct task_struct *p; - int (*func)(void *info); + remote_function_f func; void *info; int ret; }; @@ -86,7 +88,7 @@ static void remote_function(void *data) * -EAGAIN - when the process moved away */ static int -task_function_call(struct task_struct *p, int (*func) (void *info), void *info) +task_function_call(struct task_struct *p, remote_function_f func, void *info) { struct remote_function_call data = { .p = p, @@ -110,7 +112,7 @@ task_function_call(struct task_struct *p, int (*func) (void *info), void *info) * * returns: @func return value or -ENXIO when the cpu is offline */ -static int cpu_function_call(int cpu, int (*func) (void *info), void *info) +static int cpu_function_call(int cpu, remote_function_f func, void *info) { struct remote_function_call data = { .p = NULL, @@ -747,62 +749,31 @@ perf_cgroup_mark_enabled(struct perf_event *event, /* * function must be called with interrupts disbled */ -static enum hrtimer_restart perf_cpu_hrtimer_handler(struct hrtimer *hr) +static enum hrtimer_restart perf_mux_hrtimer_handler(struct hrtimer *hr) { struct perf_cpu_context *cpuctx; - enum hrtimer_restart ret = HRTIMER_NORESTART; int rotations = 0; WARN_ON(!irqs_disabled()); cpuctx = container_of(hr, struct perf_cpu_context, hrtimer); - rotations = perf_rotate_context(cpuctx); - /* - * arm timer if needed - */ - if (rotations) { + raw_spin_lock(&cpuctx->hrtimer_lock); + if (rotations) hrtimer_forward_now(hr, cpuctx->hrtimer_interval); - ret = HRTIMER_RESTART; - } - - return ret; -} - -/* CPU is going down */ -void perf_cpu_hrtimer_cancel(int cpu) -{ - struct perf_cpu_context *cpuctx; - struct pmu *pmu; - unsigned long flags; - - if (WARN_ON(cpu != smp_processor_id())) - return; - - local_irq_save(flags); - - rcu_read_lock(); - - list_for_each_entry_rcu(pmu, &pmus, entry) { - cpuctx = this_cpu_ptr(pmu->pmu_cpu_context); - - if (pmu->task_ctx_nr == perf_sw_context) - continue; - - hrtimer_cancel(&cpuctx->hrtimer); - } - - rcu_read_unlock(); + else + cpuctx->hrtimer_active = 0; + raw_spin_unlock(&cpuctx->hrtimer_lock); - local_irq_restore(flags); + return rotations ? HRTIMER_RESTART : HRTIMER_NORESTART; } -static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu) +static void __perf_mux_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu) { - struct hrtimer *hr = &cpuctx->hrtimer; + struct hrtimer *timer = &cpuctx->hrtimer; struct pmu *pmu = cpuctx->ctx.pmu; - int timer; + u64 interval; /* no multiplexing needed for SW PMU */ if (pmu->task_ctx_nr == perf_sw_context) @@ -812,31 +783,36 @@ static void __perf_cpu_hrtimer_init(struct perf_cpu_context *cpuctx, int cpu) * check default is sane, if not set then force to * default interval (1/tick) */ - timer = pmu->hrtimer_interval_ms; - if (timer < 1) - timer = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER; + interval = pmu->hrtimer_interval_ms; + if (interval < 1) + interval = pmu->hrtimer_interval_ms = PERF_CPU_HRTIMER; - cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer); + cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval); - hrtimer_init(hr, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); - hr->function = perf_cpu_hrtimer_handler; + raw_spin_lock_init(&cpuctx->hrtimer_lock); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); + timer->function = perf_mux_hrtimer_handler; } -static void perf_cpu_hrtimer_restart(struct perf_cpu_context *cpuctx) +static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx) { - struct hrtimer *hr = &cpuctx->hrtimer; + struct hrtimer *timer = &cpuctx->hrtimer; struct pmu *pmu = cpuctx->ctx.pmu; + unsigned long flags; /* not for SW PMU */ if (pmu->task_ctx_nr == perf_sw_context) - return; + return 0; - if (hrtimer_active(hr)) - return; + raw_spin_lock_irqsave(&cpuctx->hrtimer_lock, flags); + if (!cpuctx->hrtimer_active) { + cpuctx->hrtimer_active = 1; + hrtimer_forward_now(timer, cpuctx->hrtimer_interval); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); + } + raw_spin_unlock_irqrestore(&cpuctx->hrtimer_lock, flags); - if (!hrtimer_callback_running(hr)) - __hrtimer_start_range_ns(hr, cpuctx->hrtimer_interval, - 0, HRTIMER_MODE_REL_PINNED, 0); + return 0; } void perf_pmu_disable(struct pmu *pmu) @@ -1935,7 +1911,7 @@ group_sched_in(struct perf_event *group_event, if (event_sched_in(group_event, cpuctx, ctx)) { pmu->cancel_txn(pmu); - perf_cpu_hrtimer_restart(cpuctx); + perf_mux_hrtimer_restart(cpuctx); return -EAGAIN; } @@ -1982,7 +1958,7 @@ group_error: pmu->cancel_txn(pmu); - perf_cpu_hrtimer_restart(cpuctx); + perf_mux_hrtimer_restart(cpuctx); return -EAGAIN; } @@ -2255,7 +2231,7 @@ static int __perf_event_enable(void *info) */ if (leader != event) { group_sched_out(leader, cpuctx, ctx); - perf_cpu_hrtimer_restart(cpuctx); + perf_mux_hrtimer_restart(cpuctx); } if (leader->attr.pinned) { update_group_times(leader); @@ -6897,9 +6873,8 @@ static void perf_swevent_start_hrtimer(struct perf_event *event) } else { period = max_t(u64, 10000, hwc->sample_period); } - __hrtimer_start_range_ns(&hwc->hrtimer, - ns_to_ktime(period), 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&hwc->hrtimer, ns_to_ktime(period), + HRTIMER_MODE_REL_PINNED); } static void perf_swevent_cancel_hrtimer(struct perf_event *event) @@ -7200,6 +7175,8 @@ perf_event_mux_interval_ms_show(struct device *dev, return snprintf(page, PAGE_SIZE-1, "%d\n", pmu->hrtimer_interval_ms); } +static DEFINE_MUTEX(mux_interval_mutex); + static ssize_t perf_event_mux_interval_ms_store(struct device *dev, struct device_attribute *attr, @@ -7219,17 +7196,21 @@ perf_event_mux_interval_ms_store(struct device *dev, if (timer == pmu->hrtimer_interval_ms) return count; + mutex_lock(&mux_interval_mutex); pmu->hrtimer_interval_ms = timer; /* update all cpuctx for this PMU */ - for_each_possible_cpu(cpu) { + get_online_cpus(); + for_each_online_cpu(cpu) { struct perf_cpu_context *cpuctx; cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu); cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * timer); - if (hrtimer_active(&cpuctx->hrtimer)) - hrtimer_forward_now(&cpuctx->hrtimer, cpuctx->hrtimer_interval); + cpu_function_call(cpu, + (remote_function_f)perf_mux_hrtimer_restart, cpuctx); } + put_online_cpus(); + mutex_unlock(&mux_interval_mutex); return count; } @@ -7334,7 +7315,7 @@ skip_type: lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock); cpuctx->ctx.pmu = pmu; - __perf_cpu_hrtimer_init(cpuctx, cpu); + __perf_mux_hrtimer_init(cpuctx, cpu); cpuctx->unique_pmu = pmu; } diff --git a/kernel/futex.c b/kernel/futex.c index aacc706f85fc..ea6ca0bca525 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -2064,11 +2064,8 @@ static void futex_wait_queue_me(struct futex_hash_bucket *hb, struct futex_q *q, queue_me(q, hb); /* Arm the timer */ - if (timeout) { + if (timeout) hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); - if (!hrtimer_active(&timeout->timer)) - timeout->task = NULL; - } /* * If we have been removed from the hash list, then another task diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 30ec5b46cd8c..36573e96a477 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -1182,11 +1182,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state, set_current_state(state); /* Setup the timer, when timeout != NULL */ - if (unlikely(timeout)) { + if (unlikely(timeout)) hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); - if (!hrtimer_active(&timeout->timer)) - timeout->task = NULL; - } ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 32664347091a..013485fb2b06 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1375,9 +1375,9 @@ static void rcu_prepare_kthreads(int cpu) * Because we not have RCU_FAST_NO_HZ, just check whether this CPU needs * any flavor of RCU. */ -int rcu_needs_cpu(unsigned long *delta_jiffies) +int rcu_needs_cpu(u64 basemono, u64 *nextevt) { - *delta_jiffies = ULONG_MAX; + *nextevt = KTIME_MAX; return IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL) ? 0 : rcu_cpu_has_callbacks(NULL); } @@ -1439,8 +1439,6 @@ module_param(rcu_idle_gp_delay, int, 0644); static int rcu_idle_lazy_gp_delay = RCU_IDLE_LAZY_GP_DELAY; module_param(rcu_idle_lazy_gp_delay, int, 0644); -extern int tick_nohz_active; - /* * Try to advance callbacks for all flavors of RCU on the current CPU, but * only if it has been awhile since the last time we did so. Afterwards, @@ -1487,12 +1485,13 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void) * * The caller must have disabled interrupts. */ -int rcu_needs_cpu(unsigned long *dj) +int rcu_needs_cpu(u64 basemono, u64 *nextevt) { struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks); + unsigned long dj; if (IS_ENABLED(CONFIG_RCU_NOCB_CPU_ALL)) { - *dj = ULONG_MAX; + *nextevt = KTIME_MAX; return 0; } @@ -1501,7 +1500,7 @@ int rcu_needs_cpu(unsigned long *dj) /* If no callbacks, RCU doesn't need the CPU. */ if (!rcu_cpu_has_callbacks(&rdtp->all_lazy)) { - *dj = ULONG_MAX; + *nextevt = KTIME_MAX; return 0; } @@ -1515,11 +1514,12 @@ int rcu_needs_cpu(unsigned long *dj) /* Request timer delay depending on laziness, and round. */ if (!rdtp->all_lazy) { - *dj = round_up(rcu_idle_gp_delay + jiffies, + dj = round_up(rcu_idle_gp_delay + jiffies, rcu_idle_gp_delay) - jiffies; } else { - *dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies; + dj = round_jiffies(rcu_idle_lazy_gp_delay + jiffies) - jiffies; } + *nextevt = basemono + dj * TICK_NSEC; return 0; } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f89ca9bcf42a..c9a707b59331 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -90,26 +90,6 @@ #define CREATE_TRACE_POINTS #include <trace/events/sched.h> -void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period) -{ - unsigned long delta; - ktime_t soft, hard, now; - - for (;;) { - if (hrtimer_active(period_timer)) - break; - - now = hrtimer_cb_get_time(period_timer); - hrtimer_forward(period_timer, now, period); - - soft = hrtimer_get_softexpires(period_timer); - hard = hrtimer_get_expires(period_timer); - delta = ktime_to_ns(ktime_sub(hard, soft)); - __hrtimer_start_range_ns(period_timer, soft, delta, - HRTIMER_MODE_ABS_PINNED, 0); - } -} - DEFINE_MUTEX(sched_domains_mutex); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); @@ -355,12 +335,11 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) #ifdef CONFIG_SMP -static int __hrtick_restart(struct rq *rq) +static void __hrtick_restart(struct rq *rq) { struct hrtimer *timer = &rq->hrtick_timer; - ktime_t time = hrtimer_get_softexpires(timer); - return __hrtimer_start_range_ns(timer, time, 0, HRTIMER_MODE_ABS_PINNED, 0); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); } /* @@ -440,8 +419,8 @@ void hrtick_start(struct rq *rq, u64 delay) * doesn't make sense. Rely on vruntime for fairness. */ delay = max_t(u64, delay, 10000LL); - __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, - HRTIMER_MODE_REL_PINNED, 0); + hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), + HRTIMER_MODE_REL_PINNED); } static inline void init_hrtick(void) @@ -639,13 +618,12 @@ void resched_cpu(int cpu) * selecting an idle cpu will add more delays to the timers than intended * (as that cpu's timer base may not be uptodate wrt jiffies etc). */ -int get_nohz_timer_target(int pinned) +int get_nohz_timer_target(void) { - int cpu = smp_processor_id(); - int i; + int i, cpu = smp_processor_id(); struct sched_domain *sd; - if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) + if (!idle_cpu(cpu)) return cpu; rcu_read_lock(); @@ -7126,8 +7104,6 @@ void __init sched_init_smp(void) } #endif /* CONFIG_SMP */ -const_debug unsigned int sysctl_timer_migration = 1; - int in_sched_functions(unsigned long addr) { return in_lock_functions(addr) || @@ -8163,10 +8139,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) __refill_cfs_bandwidth_runtime(cfs_b); /* restart the period timer (if active) to handle new period expiry */ - if (runtime_enabled && cfs_b->timer_active) { - /* force a reprogram */ - __start_cfs_bandwidth(cfs_b, true); - } + if (runtime_enabled) + start_cfs_bandwidth(cfs_b); raw_spin_unlock_irq(&cfs_b->lock); for_each_online_cpu(i) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 392e8fb94db3..eac20c557a55 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -503,8 +503,6 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted) struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); ktime_t now, act; - ktime_t soft, hard; - unsigned long range; s64 delta; if (boosted) @@ -527,15 +525,9 @@ static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted) if (ktime_us_delta(act, now) < 0) return 0; - hrtimer_set_expires(&dl_se->dl_timer, act); + hrtimer_start(&dl_se->dl_timer, act, HRTIMER_MODE_ABS); - soft = hrtimer_get_softexpires(&dl_se->dl_timer); - hard = hrtimer_get_expires(&dl_se->dl_timer); - range = ktime_to_ns(ktime_sub(hard, soft)); - __hrtimer_start_range_ns(&dl_se->dl_timer, soft, - range, HRTIMER_MODE_ABS, 0); - - return hrtimer_active(&dl_se->dl_timer); + return 1; } /* diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 704683cc9042..315c68e015d9 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -232,8 +232,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) #endif #endif #ifdef CONFIG_CFS_BANDWIDTH - SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active", - cfs_rq->tg->cfs_bandwidth.timer_active); SEQ_printf(m, " .%-30s: %d\n", "throttled", cfs_rq->throttled); SEQ_printf(m, " .%-30s: %d\n", "throttle_count", diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 433061d984ea..40a7fcbf491e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3504,16 +3504,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) if (cfs_b->quota == RUNTIME_INF) amount = min_amount; else { - /* - * If the bandwidth pool has become inactive, then at least one - * period must have elapsed since the last consumption. - * Refresh the global state and ensure bandwidth timer becomes - * active. - */ - if (!cfs_b->timer_active) { - __refill_cfs_bandwidth_runtime(cfs_b); - __start_cfs_bandwidth(cfs_b, false); - } + start_cfs_bandwidth(cfs_b); if (cfs_b->runtime > 0) { amount = min(cfs_b->runtime, min_amount); @@ -3662,6 +3653,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; long task_delta, dequeue = 1; + bool empty; se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -3691,13 +3683,21 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) cfs_rq->throttled = 1; cfs_rq->throttled_clock = rq_clock(rq); raw_spin_lock(&cfs_b->lock); + empty = list_empty(&cfs_rq->throttled_list); + /* * Add to the _head_ of the list, so that an already-started * distribute_cfs_runtime will not see us */ list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); - if (!cfs_b->timer_active) - __start_cfs_bandwidth(cfs_b, false); + + /* + * If we're the first throttled task, make sure the bandwidth + * timer is running. + */ + if (empty) + start_cfs_bandwidth(cfs_b); + raw_spin_unlock(&cfs_b->lock); } @@ -3812,13 +3812,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) if (cfs_b->idle && !throttled) goto out_deactivate; - /* - * if we have relooped after returning idle once, we need to update our - * status as actually running, so that other cpus doing - * __start_cfs_bandwidth will stop trying to cancel us. - */ - cfs_b->timer_active = 1; - __refill_cfs_bandwidth_runtime(cfs_b); if (!throttled) { @@ -3863,7 +3856,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) return 0; out_deactivate: - cfs_b->timer_active = 0; return 1; } @@ -3878,7 +3870,7 @@ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; * Are we near the end of the current quota period? * * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the - * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of + * hrtimer base being cleared by hrtimer_start. In the case of * migrate_hrtimers, base is never cleared, so we are fine. */ static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) @@ -3906,8 +3898,9 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b) if (runtime_refresh_within(cfs_b, min_left)) return; - start_bandwidth_timer(&cfs_b->slack_timer, - ns_to_ktime(cfs_bandwidth_slack_period)); + hrtimer_start(&cfs_b->slack_timer, + ns_to_ktime(cfs_bandwidth_slack_period), + HRTIMER_MODE_REL); } /* we know any runtime found here is valid as update_curr() precedes return */ @@ -4027,6 +4020,7 @@ static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = container_of(timer, struct cfs_bandwidth, slack_timer); + do_sched_cfs_slack_timer(cfs_b); return HRTIMER_NORESTART; @@ -4036,20 +4030,19 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = container_of(timer, struct cfs_bandwidth, period_timer); - ktime_t now; int overrun; int idle = 0; raw_spin_lock(&cfs_b->lock); for (;;) { - now = hrtimer_cb_get_time(timer); - overrun = hrtimer_forward(timer, now, cfs_b->period); - + overrun = hrtimer_forward_now(timer, cfs_b->period); if (!overrun) break; idle = do_sched_cfs_period_timer(cfs_b, overrun); } + if (idle) + cfs_b->period_active = 0; raw_spin_unlock(&cfs_b->lock); return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; @@ -4063,7 +4056,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) cfs_b->period = ns_to_ktime(default_cfs_period()); INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); - hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); cfs_b->period_timer.function = sched_cfs_period_timer; hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cfs_b->slack_timer.function = sched_cfs_slack_timer; @@ -4075,28 +4068,15 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) INIT_LIST_HEAD(&cfs_rq->throttled_list); } -/* requires cfs_b->lock, may release to reprogram timer */ -void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force) +void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) { - /* - * The timer may be active because we're trying to set a new bandwidth - * period or because we're racing with the tear-down path - * (timer_active==0 becomes visible before the hrtimer call-back - * terminates). In either case we ensure that it's re-programmed - */ - while (unlikely(hrtimer_active(&cfs_b->period_timer)) && - hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) { - /* bounce the lock to allow do_sched_cfs_period_timer to run */ - raw_spin_unlock(&cfs_b->lock); - cpu_relax(); - raw_spin_lock(&cfs_b->lock); - /* if someone else restarted the timer then we're done */ - if (!force && cfs_b->timer_active) - return; - } + lockdep_assert_held(&cfs_b->lock); - cfs_b->timer_active = 1; - start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period); + if (!cfs_b->period_active) { + cfs_b->period_active = 1; + hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); + hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); + } } static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 560d2fa623c3..7d7093c51f8d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -18,19 +18,22 @@ static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) { struct rt_bandwidth *rt_b = container_of(timer, struct rt_bandwidth, rt_period_timer); - ktime_t now; - int overrun; int idle = 0; + int overrun; + raw_spin_lock(&rt_b->rt_runtime_lock); for (;;) { - now = hrtimer_cb_get_time(timer); - overrun = hrtimer_forward(timer, now, rt_b->rt_period); - + overrun = hrtimer_forward_now(timer, rt_b->rt_period); if (!overrun) break; + raw_spin_unlock(&rt_b->rt_runtime_lock); idle = do_sched_rt_period_timer(rt_b, overrun); + raw_spin_lock(&rt_b->rt_runtime_lock); } + if (idle) + rt_b->rt_period_active = 0; + raw_spin_unlock(&rt_b->rt_runtime_lock); return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; } @@ -52,11 +55,12 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF) return; - if (hrtimer_active(&rt_b->rt_period_timer)) - return; - raw_spin_lock(&rt_b->rt_runtime_lock); - start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period); + if (!rt_b->rt_period_active) { + rt_b->rt_period_active = 1; + hrtimer_forward_now(&rt_b->rt_period_timer, rt_b->rt_period); + hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED); + } raw_spin_unlock(&rt_b->rt_runtime_lock); } diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index d62b2882232b..aea7c1f393cb 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -137,6 +137,7 @@ struct rt_bandwidth { ktime_t rt_period; u64 rt_runtime; struct hrtimer rt_period_timer; + unsigned int rt_period_active; }; void __dl_clear_params(struct task_struct *p); @@ -221,7 +222,7 @@ struct cfs_bandwidth { s64 hierarchical_quota; u64 runtime_expires; - int idle, timer_active; + int idle, period_active; struct hrtimer period_timer, slack_timer; struct list_head throttled_cfs_rq; @@ -312,7 +313,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); -extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force); +extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b); extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq); extern void free_rt_sched_group(struct task_group *tg); @@ -1409,8 +1410,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } static inline void sched_avg_update(struct rq *rq) { } #endif -extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period); - /* * __task_rq_lock - lock the rq @p resides on. */ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 2082b1a88fb9..b13e9d2de302 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -349,15 +349,6 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, - { - .procname = "timer_migration", - .data = &sysctl_timer_migration, - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, - .extra2 = &one, - }, #endif /* CONFIG_SMP */ #ifdef CONFIG_NUMA_BALANCING { @@ -1132,6 +1123,15 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) + { + .procname = "timer_migration", + .data = &sysctl_timer_migration, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = timer_migration_handler, + }, +#endif { } }; diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 01f0312419b3..ffc4cc3dcd47 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -13,19 +13,4 @@ obj-$(CONFIG_TIMER_STATS) += timer_stats.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o -$(obj)/time.o: $(obj)/timeconst.h - -quiet_cmd_hzfile = HZFILE $@ - cmd_hzfile = echo "hz=$(CONFIG_HZ)" > $@ - -targets += hz.bc -$(obj)/hz.bc: $(objtree)/include/config/hz.h FORCE - $(call if_changed,hzfile) - -quiet_cmd_bc = BC $@ - cmd_bc = bc -q $(filter-out FORCE,$^) > $@ - -targets += timeconst.h -$(obj)/timeconst.h: $(obj)/hz.bc $(src)/timeconst.bc FORCE - $(call if_changed,bc) - +$(obj)/time.o: $(objtree)/include/config/ diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 1b001ed1edb9..7fbba635a549 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -317,19 +317,16 @@ EXPORT_SYMBOL_GPL(alarm_init); * @alarm: ptr to alarm to set * @start: time to run the alarm */ -int alarm_start(struct alarm *alarm, ktime_t start) +void alarm_start(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; unsigned long flags; - int ret; spin_lock_irqsave(&base->lock, flags); alarm->node.expires = start; alarmtimer_enqueue(base, alarm); - ret = hrtimer_start(&alarm->timer, alarm->node.expires, - HRTIMER_MODE_ABS); + hrtimer_start(&alarm->timer, alarm->node.expires, HRTIMER_MODE_ABS); spin_unlock_irqrestore(&base->lock, flags); - return ret; } EXPORT_SYMBOL_GPL(alarm_start); @@ -338,12 +335,12 @@ EXPORT_SYMBOL_GPL(alarm_start); * @alarm: ptr to alarm to set * @start: time relative to now to run the alarm */ -int alarm_start_relative(struct alarm *alarm, ktime_t start) +void alarm_start_relative(struct alarm *alarm, ktime_t start) { struct alarm_base *base = &alarm_bases[alarm->type]; start = ktime_add(start, base->gettime()); - return alarm_start(alarm, start); + alarm_start(alarm, start); } EXPORT_SYMBOL_GPL(alarm_start_relative); @@ -495,12 +492,12 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, */ static int alarm_clock_getres(const clockid_t which_clock, struct timespec *tp) { - clockid_t baseid = alarm_bases[clock2alarm(which_clock)].base_clockid; - if (!alarmtimer_get_rtcdev()) return -EINVAL; - return hrtimer_get_res(baseid, tp); + tp->tv_sec = 0; + tp->tv_nsec = hrtimer_resolution; + return 0; } /** diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 637a09461c1d..08ccc3da3ca0 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -94,8 +94,8 @@ u64 clockevent_delta2ns(unsigned long latch, struct clock_event_device *evt) } EXPORT_SYMBOL_GPL(clockevent_delta2ns); -static int __clockevents_set_state(struct clock_event_device *dev, - enum clock_event_state state) +static int __clockevents_switch_state(struct clock_event_device *dev, + enum clock_event_state state) { /* Transition with legacy set_mode() callback */ if (dev->set_mode) { @@ -134,32 +134,44 @@ static int __clockevents_set_state(struct clock_event_device *dev, return -ENOSYS; return dev->set_state_oneshot(dev); + case CLOCK_EVT_STATE_ONESHOT_STOPPED: + /* Core internal bug */ + if (WARN_ONCE(!clockevent_state_oneshot(dev), + "Current state: %d\n", + clockevent_get_state(dev))) + return -EINVAL; + + if (dev->set_state_oneshot_stopped) + return dev->set_state_oneshot_stopped(dev); + else + return -ENOSYS; + default: return -ENOSYS; } } /** - * clockevents_set_state - set the operating state of a clock event device + * clockevents_switch_state - set the operating state of a clock event device * @dev: device to modify * @state: new state * * Must be called with interrupts disabled ! */ -void clockevents_set_state(struct clock_event_device *dev, - enum clock_event_state state) +void clockevents_switch_state(struct clock_event_device *dev, + enum clock_event_state state) { - if (dev->state != state) { - if (__clockevents_set_state(dev, state)) + if (clockevent_get_state(dev) != state) { + if (__clockevents_switch_state(dev, state)) return; - dev->state = state; + clockevent_set_state(dev, state); /* * A nsec2cyc multiplicator of 0 is invalid and we'd crash * on it, so fix it up and emit a warning: */ - if (state == CLOCK_EVT_STATE_ONESHOT) { + if (clockevent_state_oneshot(dev)) { if (unlikely(!dev->mult)) { dev->mult = 1; WARN_ON(1); @@ -174,7 +186,7 @@ void clockevents_set_state(struct clock_event_device *dev, */ void clockevents_shutdown(struct clock_event_device *dev) { - clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); + clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); dev->next_event.tv64 = KTIME_MAX; } @@ -248,7 +260,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) + if (clockevent_state_shutdown(dev)) return 0; dev->retries++; @@ -285,7 +297,7 @@ static int clockevents_program_min_delta(struct clock_event_device *dev) delta = dev->min_delta_ns; dev->next_event = ktime_add_ns(ktime_get(), delta); - if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) + if (clockevent_state_shutdown(dev)) return 0; dev->retries++; @@ -317,9 +329,13 @@ int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, dev->next_event = expires; - if (dev->state == CLOCK_EVT_STATE_SHUTDOWN) + if (clockevent_state_shutdown(dev)) return 0; + /* We must be in ONESHOT state here */ + WARN_ONCE(!clockevent_state_oneshot(dev), "Current state: %d\n", + clockevent_get_state(dev)); + /* Shortcut for clockevent devices that can deal with ktime. */ if (dev->features & CLOCK_EVT_FEAT_KTIME) return dev->set_next_ktime(expires, dev); @@ -362,7 +378,7 @@ static int clockevents_replace(struct clock_event_device *ced) struct clock_event_device *dev, *newdev = NULL; list_for_each_entry(dev, &clockevent_devices, list) { - if (dev == ced || dev->state != CLOCK_EVT_STATE_DETACHED) + if (dev == ced || !clockevent_state_detached(dev)) continue; if (!tick_check_replacement(newdev, dev)) @@ -388,7 +404,7 @@ static int clockevents_replace(struct clock_event_device *ced) static int __clockevents_try_unbind(struct clock_event_device *ced, int cpu) { /* Fast track. Device is unused */ - if (ced->state == CLOCK_EVT_STATE_DETACHED) { + if (clockevent_state_detached(ced)) { list_del_init(&ced->list); return 0; } @@ -445,7 +461,8 @@ static int clockevents_sanity_check(struct clock_event_device *dev) if (dev->set_mode) { /* We shouldn't be supporting new modes now */ WARN_ON(dev->set_state_periodic || dev->set_state_oneshot || - dev->set_state_shutdown || dev->tick_resume); + dev->set_state_shutdown || dev->tick_resume || + dev->set_state_oneshot_stopped); BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED); return 0; @@ -480,7 +497,7 @@ void clockevents_register_device(struct clock_event_device *dev) BUG_ON(clockevents_sanity_check(dev)); /* Initialize state to DETACHED */ - dev->state = CLOCK_EVT_STATE_DETACHED; + clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED); if (!dev->cpumask) { WARN_ON(num_possible_cpus() > 1); @@ -545,11 +562,11 @@ int __clockevents_update_freq(struct clock_event_device *dev, u32 freq) { clockevents_config(dev, freq); - if (dev->state == CLOCK_EVT_STATE_ONESHOT) + if (clockevent_state_oneshot(dev)) return clockevents_program_event(dev, dev->next_event, false); - if (dev->state == CLOCK_EVT_STATE_PERIODIC) - return __clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); + if (clockevent_state_periodic(dev)) + return __clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); return 0; } @@ -603,13 +620,13 @@ void clockevents_exchange_device(struct clock_event_device *old, */ if (old) { module_put(old->owner); - clockevents_set_state(old, CLOCK_EVT_STATE_DETACHED); + clockevents_switch_state(old, CLOCK_EVT_STATE_DETACHED); list_del(&old->list); list_add(&old->list, &clockevents_released); } if (new) { - BUG_ON(new->state != CLOCK_EVT_STATE_DETACHED); + BUG_ON(!clockevent_state_detached(new)); clockevents_shutdown(new); } } @@ -622,7 +639,7 @@ void clockevents_suspend(void) struct clock_event_device *dev; list_for_each_entry_reverse(dev, &clockevent_devices, list) - if (dev->suspend) + if (dev->suspend && !clockevent_state_detached(dev)) dev->suspend(dev); } @@ -634,7 +651,7 @@ void clockevents_resume(void) struct clock_event_device *dev; list_for_each_entry(dev, &clockevent_devices, list) - if (dev->resume) + if (dev->resume && !clockevent_state_detached(dev)) dev->resume(dev); } @@ -665,7 +682,7 @@ void tick_cleanup_dead_cpu(int cpu) if (cpumask_test_cpu(cpu, dev->cpumask) && cpumask_weight(dev->cpumask) == 1 && !tick_is_broadcast_device(dev)) { - BUG_ON(dev->state != CLOCK_EVT_STATE_DETACHED); + BUG_ON(!clockevent_state_detached(dev)); list_del(&dev->list); } } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 15facb1b9c60..841b72f720e8 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -23,6 +23,8 @@ * o Allow clocksource drivers to be unregistered */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/device.h> #include <linux/clocksource.h> #include <linux/init.h> @@ -216,10 +218,11 @@ static void clocksource_watchdog(unsigned long data) /* Check the deviation from the watchdog clocksource. */ if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { - pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable, because the skew is too large:\n", cs->name); - pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", + pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n", + cs->name); + pr_warn(" '%s' wd_now: %llx wd_last: %llx mask: %llx\n", watchdog->name, wdnow, wdlast, watchdog->mask); - pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n", + pr_warn(" '%s' cs_now: %llx cs_last: %llx mask: %llx\n", cs->name, csnow, cslast, cs->mask); __clocksource_unstable(cs); continue; @@ -567,9 +570,8 @@ static void __clocksource_select(bool skipcur) */ if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && oneshot) { /* Override clocksource cannot be used. */ - printk(KERN_WARNING "Override clocksource %s is not " - "HRT compatible. Cannot switch while in " - "HRT/NOHZ mode\n", cs->name); + pr_warn("Override clocksource %s is not HRT compatible - cannot switch while in HRT/NOHZ mode\n", + cs->name); override_name[0] = 0; } else /* Override clocksource can be used. */ @@ -708,8 +710,8 @@ void __clocksource_update_freq_scale(struct clocksource *cs, u32 scale, u32 freq clocksource_update_max_deferment(cs); - pr_info("clocksource %s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n", - cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns); + pr_info("%s: mask: 0x%llx max_cycles: 0x%llx, max_idle_ns: %lld ns\n", + cs->name, cs->mask, cs->max_cycles, cs->max_idle_ns); } EXPORT_SYMBOL_GPL(__clocksource_update_freq_scale); @@ -1008,12 +1010,10 @@ __setup("clocksource=", boot_override_clocksource); static int __init boot_override_clock(char* str) { if (!strcmp(str, "pmtmr")) { - printk("Warning: clock=pmtmr is deprecated. " - "Use clocksource=acpi_pm.\n"); + pr_warn("clock=pmtmr is deprecated - use clocksource=acpi_pm\n"); return boot_override_clocksource("acpi_pm"); } - printk("Warning! clock= boot option is deprecated. " - "Use clocksource=xyz\n"); + pr_warn("clock= boot option is deprecated - use clocksource=xyz\n"); return boot_override_clocksource(str); } diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 93ef7190bdea..5c7ae4b641c4 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -66,33 +66,29 @@ */ DEFINE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases) = { - .lock = __RAW_SPIN_LOCK_UNLOCKED(hrtimer_bases.lock), + .seq = SEQCNT_ZERO(hrtimer_bases.seq), .clock_base = { { .index = HRTIMER_BASE_MONOTONIC, .clockid = CLOCK_MONOTONIC, .get_time = &ktime_get, - .resolution = KTIME_LOW_RES, }, { .index = HRTIMER_BASE_REALTIME, .clockid = CLOCK_REALTIME, .get_time = &ktime_get_real, - .resolution = KTIME_LOW_RES, }, { .index = HRTIMER_BASE_BOOTTIME, .clockid = CLOCK_BOOTTIME, .get_time = &ktime_get_boottime, - .resolution = KTIME_LOW_RES, }, { .index = HRTIMER_BASE_TAI, .clockid = CLOCK_TAI, .get_time = &ktime_get_clocktai, - .resolution = KTIME_LOW_RES, }, } }; @@ -109,27 +105,6 @@ static inline int hrtimer_clockid_to_base(clockid_t clock_id) return hrtimer_clock_to_base_table[clock_id]; } - -/* - * Get the coarse grained time at the softirq based on xtime and - * wall_to_monotonic. - */ -static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) -{ - ktime_t xtim, mono, boot, tai; - ktime_t off_real, off_boot, off_tai; - - mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai); - boot = ktime_add(mono, off_boot); - xtim = ktime_add(mono, off_real); - tai = ktime_add(mono, off_tai); - - base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim; - base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono; - base->clock_base[HRTIMER_BASE_BOOTTIME].softirq_time = boot; - base->clock_base[HRTIMER_BASE_TAI].softirq_time = tai; -} - /* * Functions and macros which are different for UP/SMP systems are kept in a * single place @@ -137,6 +112,18 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) #ifdef CONFIG_SMP /* + * We require the migration_base for lock_hrtimer_base()/switch_hrtimer_base() + * such that hrtimer_callback_running() can unconditionally dereference + * timer->base->cpu_base + */ +static struct hrtimer_cpu_base migration_cpu_base = { + .seq = SEQCNT_ZERO(migration_cpu_base), + .clock_base = { { .cpu_base = &migration_cpu_base, }, }, +}; + +#define migration_base migration_cpu_base.clock_base[0] + +/* * We are using hashed locking: holding per_cpu(hrtimer_bases)[n].lock * means that all timers which are tied to this base via timer->base are * locked, and the base itself is locked too. @@ -145,8 +132,8 @@ static void hrtimer_get_softirq_time(struct hrtimer_cpu_base *base) * be found on the lists/queues. * * When the timer's base is locked, and the timer removed from list, it is - * possible to set timer->base = NULL and drop the lock: the timer remains - * locked. + * possible to set timer->base = &migration_base and drop the lock: the timer + * remains locked. */ static struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, @@ -156,7 +143,7 @@ struct hrtimer_clock_base *lock_hrtimer_base(const struct hrtimer *timer, for (;;) { base = timer->base; - if (likely(base != NULL)) { + if (likely(base != &migration_base)) { raw_spin_lock_irqsave(&base->cpu_base->lock, *flags); if (likely(base == timer->base)) return base; @@ -190,6 +177,24 @@ hrtimer_check_target(struct hrtimer *timer, struct hrtimer_clock_base *new_base) #endif } +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +static inline +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 &per_cpu(hrtimer_bases, get_nohz_timer_target()); +} +#else +static inline +struct hrtimer_cpu_base *get_target_base(struct hrtimer_cpu_base *base, + int pinned) +{ + return this_cpu_ptr(&hrtimer_bases); +} +#endif + /* * Switch the timer base to the current CPU when possible. */ @@ -197,14 +202,13 @@ 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_clock_base *new_base; - struct hrtimer_cpu_base *new_cpu_base; - int this_cpu = smp_processor_id(); - int cpu = get_nohz_timer_target(pinned); int basenum = base->index; + this_base = this_cpu_ptr(&hrtimer_bases); + new_cpu_base = get_target_base(this_base, pinned); again: - new_cpu_base = &per_cpu(hrtimer_bases, cpu); new_base = &new_cpu_base->clock_base[basenum]; if (base != new_base) { @@ -220,22 +224,24 @@ again: if (unlikely(hrtimer_callback_running(timer))) return base; - /* See the comment in lock_timer_base() */ - timer->base = NULL; + /* See the comment in lock_hrtimer_base() */ + timer->base = &migration_base; raw_spin_unlock(&base->cpu_base->lock); raw_spin_lock(&new_base->cpu_base->lock); - if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { - cpu = this_cpu; + if (new_cpu_base != this_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; timer->base = base; goto again; } timer->base = new_base; } else { - if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { - cpu = this_cpu; + if (new_cpu_base != this_base && + hrtimer_check_target(timer, new_base)) { + new_cpu_base = this_base; goto again; } } @@ -443,24 +449,35 @@ static inline void debug_deactivate(struct hrtimer *timer) } #if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) +static inline void hrtimer_update_next_timer(struct hrtimer_cpu_base *cpu_base, + struct hrtimer *timer) +{ +#ifdef CONFIG_HIGH_RES_TIMERS + cpu_base->next_timer = timer; +#endif +} + static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) { struct hrtimer_clock_base *base = cpu_base->clock_base; ktime_t expires, expires_next = { .tv64 = KTIME_MAX }; - int i; + unsigned int active = cpu_base->active_bases; - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++, base++) { + hrtimer_update_next_timer(cpu_base, NULL); + for (; active; base++, active >>= 1) { struct timerqueue_node *next; struct hrtimer *timer; - next = timerqueue_getnext(&base->active); - if (!next) + if (!(active & 0x01)) continue; + next = timerqueue_getnext(&base->active); timer = container_of(next, struct hrtimer, node); expires = ktime_sub(hrtimer_get_expires(timer), base->offset); - if (expires.tv64 < expires_next.tv64) + if (expires.tv64 < expires_next.tv64) { expires_next = expires; + hrtimer_update_next_timer(cpu_base, timer); + } } /* * clock_was_set() might have changed base->offset of any of @@ -473,6 +490,16 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) } #endif +static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) +{ + ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; + ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; + ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; + + return ktime_get_update_offsets_now(&base->clock_was_set_seq, + offs_real, offs_boot, offs_tai); +} + /* High resolution timer related functions */ #ifdef CONFIG_HIGH_RES_TIMERS @@ -480,6 +507,8 @@ static ktime_t __hrtimer_get_next_event(struct hrtimer_cpu_base *cpu_base) * High resolution timer enabled ? */ static int hrtimer_hres_enabled __read_mostly = 1; +unsigned int hrtimer_resolution __read_mostly = LOW_RES_NSEC; +EXPORT_SYMBOL_GPL(hrtimer_resolution); /* * Enable / Disable high resolution mode @@ -508,9 +537,14 @@ static inline int hrtimer_is_hres_enabled(void) /* * Is the high resolution mode active ? */ +static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) +{ + return cpu_base->hres_active; +} + static inline int hrtimer_hres_active(void) { - return __this_cpu_read(hrtimer_bases.hres_active); + return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases)); } /* @@ -521,7 +555,12 @@ static inline int hrtimer_hres_active(void) static void hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) { - ktime_t expires_next = __hrtimer_get_next_event(cpu_base); + ktime_t expires_next; + + if (!cpu_base->hres_active) + return; + + expires_next = __hrtimer_get_next_event(cpu_base); if (skip_equal && expires_next.tv64 == cpu_base->expires_next.tv64) return; @@ -545,63 +584,53 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) if (cpu_base->hang_detected) return; - if (cpu_base->expires_next.tv64 != KTIME_MAX) - tick_program_event(cpu_base->expires_next, 1); + tick_program_event(cpu_base->expires_next, 1); } /* - * Shared reprogramming for clock_realtime and clock_monotonic - * * When a timer is enqueued and expires earlier than the already enqueued * timers, we have to check, whether it expires earlier than the timer for * which the clock event device was armed. * - * Note, that in case the state has HRTIMER_STATE_CALLBACK set, no reprogramming - * and no expiry check happens. The timer gets enqueued into the rbtree. The - * reprogramming and expiry check is done in the hrtimer_interrupt or in the - * softirq. - * * Called with interrupts disabled and base->cpu_base.lock held */ -static int hrtimer_reprogram(struct hrtimer *timer, - struct hrtimer_clock_base *base) +static void hrtimer_reprogram(struct hrtimer *timer, + struct hrtimer_clock_base *base) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); ktime_t expires = ktime_sub(hrtimer_get_expires(timer), base->offset); - int res; WARN_ON_ONCE(hrtimer_get_expires_tv64(timer) < 0); /* - * When the callback is running, we do not reprogram the clock event - * device. The timer callback is either running on a different CPU or - * the callback is executed in the hrtimer_interrupt context. The - * reprogramming is handled either by the softirq, which called the - * callback or at the end of the hrtimer_interrupt. + * If the timer is not on the current cpu, we cannot reprogram + * the other cpus clock event device. */ - if (hrtimer_callback_running(timer)) - return 0; + if (base->cpu_base != cpu_base) + return; + + /* + * If the hrtimer interrupt is running, then it will + * reevaluate the clock bases and reprogram the clock event + * device. The callbacks are always executed in hard interrupt + * context so we don't need an extra check for a running + * callback. + */ + if (cpu_base->in_hrtirq) + return; /* * CLOCK_REALTIME timer might be requested with an absolute - * expiry time which is less than base->offset. Nothing wrong - * about that, just avoid to call into the tick code, which - * has now objections against negative expiry values. + * expiry time which is less than base->offset. Set it to 0. */ if (expires.tv64 < 0) - return -ETIME; + expires.tv64 = 0; if (expires.tv64 >= cpu_base->expires_next.tv64) - return 0; + return; - /* - * When the target cpu of the timer is currently executing - * hrtimer_interrupt(), then we do not touch the clock event - * device. hrtimer_interrupt() will reevaluate all clock bases - * before reprogramming the device. - */ - if (cpu_base->in_hrtirq) - return 0; + /* Update the pointer to the next expiring timer */ + cpu_base->next_timer = timer; /* * If a hang was detected in the last timer interrupt then we @@ -610,15 +639,14 @@ static int hrtimer_reprogram(struct hrtimer *timer, * to make progress. */ if (cpu_base->hang_detected) - return 0; + return; /* - * Clockevents returns -ETIME, when the event was in the past. + * Program the timer hardware. We enforce the expiry for + * events which are already in the past. */ - res = tick_program_event(expires, 0); - if (!IS_ERR_VALUE(res)) - cpu_base->expires_next = expires; - return res; + cpu_base->expires_next = expires; + tick_program_event(expires, 1); } /* @@ -630,15 +658,6 @@ static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) base->hres_active = 0; } -static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) -{ - ktime_t *offs_real = &base->clock_base[HRTIMER_BASE_REALTIME].offset; - ktime_t *offs_boot = &base->clock_base[HRTIMER_BASE_BOOTTIME].offset; - ktime_t *offs_tai = &base->clock_base[HRTIMER_BASE_TAI].offset; - - return ktime_get_update_offsets_now(offs_real, offs_boot, offs_tai); -} - /* * Retrigger next event is called after clock was set * @@ -648,7 +667,7 @@ static void retrigger_next_event(void *arg) { struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); - if (!hrtimer_hres_active()) + if (!base->hres_active) return; raw_spin_lock(&base->lock); @@ -662,29 +681,19 @@ static void retrigger_next_event(void *arg) */ static int hrtimer_switch_to_hres(void) { - int i, cpu = smp_processor_id(); - struct hrtimer_cpu_base *base = &per_cpu(hrtimer_bases, cpu); - unsigned long flags; - - if (base->hres_active) - return 1; - - local_irq_save(flags); + struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases); if (tick_init_highres()) { - local_irq_restore(flags); printk(KERN_WARNING "Could not switch to high resolution " - "mode on CPU %d\n", cpu); + "mode on CPU %d\n", base->cpu); return 0; } base->hres_active = 1; - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) - base->clock_base[i].resolution = KTIME_HIGH_RES; + hrtimer_resolution = HIGH_RES_NSEC; tick_setup_sched_timer(); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); - local_irq_restore(flags); return 1; } @@ -706,6 +715,7 @@ void clock_was_set_delayed(void) #else +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; } @@ -803,6 +813,14 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) * * Forward the timer expiry so it will expire in the future. * Returns the number of overruns. + * + * Can be safely called from the callback function of @timer. If + * called from other contexts @timer must neither be enqueued nor + * running the callback and the caller needs to take care of + * serialization. + * + * Note: This only updates the timer expiry value and does not requeue + * the timer. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { @@ -814,8 +832,11 @@ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) if (delta.tv64 < 0) return 0; - if (interval.tv64 < timer->base->resolution.tv64) - interval.tv64 = timer->base->resolution.tv64; + if (WARN_ON(timer->state & HRTIMER_STATE_ENQUEUED)) + return 0; + + if (interval.tv64 < hrtimer_resolution) + interval.tv64 = hrtimer_resolution; if (unlikely(delta.tv64 >= interval.tv64)) { s64 incr = ktime_to_ns(interval); @@ -849,16 +870,11 @@ static int enqueue_hrtimer(struct hrtimer *timer, { debug_activate(timer); - timerqueue_add(&base->active, &timer->node); base->cpu_base->active_bases |= 1 << base->index; - /* - * HRTIMER_STATE_ENQUEUED is or'ed to the current state to preserve the - * state of a possibly running callback. - */ - timer->state |= HRTIMER_STATE_ENQUEUED; + timer->state = HRTIMER_STATE_ENQUEUED; - return (&timer->node == base->active.next); + return timerqueue_add(&base->active, &timer->node); } /* @@ -875,39 +891,38 @@ static void __remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, unsigned long newstate, int reprogram) { - struct timerqueue_node *next_timer; - if (!(timer->state & HRTIMER_STATE_ENQUEUED)) - goto out; + struct hrtimer_cpu_base *cpu_base = base->cpu_base; + unsigned int state = timer->state; + + timer->state = newstate; + if (!(state & HRTIMER_STATE_ENQUEUED)) + return; + + if (!timerqueue_del(&base->active, &timer->node)) + cpu_base->active_bases &= ~(1 << base->index); - next_timer = timerqueue_getnext(&base->active); - timerqueue_del(&base->active, &timer->node); - if (&timer->node == next_timer) { #ifdef CONFIG_HIGH_RES_TIMERS - /* Reprogram the clock event device. if enabled */ - if (reprogram && hrtimer_hres_active()) { - ktime_t expires; - - expires = ktime_sub(hrtimer_get_expires(timer), - base->offset); - if (base->cpu_base->expires_next.tv64 == expires.tv64) - hrtimer_force_reprogram(base->cpu_base, 1); - } + /* + * Note: If reprogram is false we do not update + * cpu_base->next_timer. This happens when we remove the first + * timer on a remote cpu. No harm as we never dereference + * cpu_base->next_timer. So the worst thing what can happen is + * an superflous call to hrtimer_force_reprogram() on the + * remote cpu later on if the same timer gets enqueued again. + */ + if (reprogram && timer == cpu_base->next_timer) + hrtimer_force_reprogram(cpu_base, 1); #endif - } - if (!timerqueue_getnext(&base->active)) - base->cpu_base->active_bases &= ~(1 << base->index); -out: - timer->state = newstate; } /* * remove hrtimer, called with base lock held */ static inline int -remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) +remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base, bool restart) { if (hrtimer_is_queued(timer)) { - unsigned long state; + unsigned long state = timer->state; int reprogram; /* @@ -921,30 +936,35 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base) debug_deactivate(timer); timer_stats_hrtimer_clear_start_info(timer); reprogram = base->cpu_base == this_cpu_ptr(&hrtimer_bases); - /* - * We must preserve the CALLBACK state flag here, - * otherwise we could move the timer base in - * switch_hrtimer_base. - */ - state = timer->state & HRTIMER_STATE_CALLBACK; + + if (!restart) + state = HRTIMER_STATE_INACTIVE; + __remove_hrtimer(timer, base, state, reprogram); return 1; } return 0; } -int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long delta_ns, const enum hrtimer_mode mode, - int wakeup) +/** + * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU + * @timer: the timer to be added + * @tim: expiry time + * @delta_ns: "slack" range for the timer + * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or + * relative (HRTIMER_MODE_REL) + */ +void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, + unsigned long delta_ns, const enum hrtimer_mode mode) { struct hrtimer_clock_base *base, *new_base; unsigned long flags; - int ret, leftmost; + int leftmost; base = lock_hrtimer_base(timer, &flags); /* Remove an active timer from the queue: */ - ret = remove_hrtimer(timer, base); + remove_hrtimer(timer, base, true); if (mode & HRTIMER_MODE_REL) { tim = ktime_add_safe(tim, base->get_time()); @@ -956,7 +976,7 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, * timeouts. This will go away with the GTOD framework. */ #ifdef CONFIG_TIME_LOW_RES - tim = ktime_add_safe(tim, base->resolution); + tim = ktime_add_safe(tim, ktime_set(0, hrtimer_resolution)); #endif } @@ -968,85 +988,25 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, timer_stats_hrtimer_set_start_info(timer); leftmost = enqueue_hrtimer(timer, new_base); - - if (!leftmost) { - unlock_hrtimer_base(timer, &flags); - return ret; - } + if (!leftmost) + goto unlock; if (!hrtimer_is_hres_active(timer)) { /* * Kick to reschedule the next tick to handle the new timer * on dynticks target. */ - wake_up_nohz_cpu(new_base->cpu_base->cpu); - } else if (new_base->cpu_base == this_cpu_ptr(&hrtimer_bases) && - hrtimer_reprogram(timer, new_base)) { - /* - * Only allow reprogramming if the new base is on this CPU. - * (it might still be on another CPU if the timer was pending) - * - * XXX send_remote_softirq() ? - */ - if (wakeup) { - /* - * We need to drop cpu_base->lock to avoid a - * lock ordering issue vs. rq->lock. - */ - raw_spin_unlock(&new_base->cpu_base->lock); - raise_softirq_irqoff(HRTIMER_SOFTIRQ); - local_irq_restore(flags); - return ret; - } else { - __raise_softirq_irqoff(HRTIMER_SOFTIRQ); - } + if (new_base->cpu_base->nohz_active) + wake_up_nohz_cpu(new_base->cpu_base->cpu); + } else { + hrtimer_reprogram(timer, new_base); } - +unlock: unlock_hrtimer_base(timer, &flags); - - return ret; -} -EXPORT_SYMBOL_GPL(__hrtimer_start_range_ns); - -/** - * hrtimer_start_range_ns - (re)start an hrtimer on the current CPU - * @timer: the timer to be added - * @tim: expiry time - * @delta_ns: "slack" range for the timer - * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or - * relative (HRTIMER_MODE_REL) - * - * Returns: - * 0 on success - * 1 when the timer was active - */ -int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, - unsigned long delta_ns, const enum hrtimer_mode mode) -{ - return __hrtimer_start_range_ns(timer, tim, delta_ns, mode, 1); } EXPORT_SYMBOL_GPL(hrtimer_start_range_ns); /** - * hrtimer_start - (re)start an hrtimer on the current CPU - * @timer: the timer to be added - * @tim: expiry time - * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or - * relative (HRTIMER_MODE_REL) - * - * Returns: - * 0 on success - * 1 when the timer was active - */ -int -hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode) -{ - return __hrtimer_start_range_ns(timer, tim, 0, mode, 1); -} -EXPORT_SYMBOL_GPL(hrtimer_start); - - -/** * hrtimer_try_to_cancel - try to deactivate a timer * @timer: hrtimer to stop * @@ -1062,10 +1022,19 @@ int hrtimer_try_to_cancel(struct hrtimer *timer) unsigned long flags; int ret = -1; + /* + * Check lockless first. If the timer is not active (neither + * enqueued nor running the callback, nothing to do here. The + * base lock does not serialize against a concurrent enqueue, + * so we can avoid taking it. + */ + if (!hrtimer_active(timer)) + return 0; + base = lock_hrtimer_base(timer, &flags); if (!hrtimer_callback_running(timer)) - ret = remove_hrtimer(timer, base); + ret = remove_hrtimer(timer, base, false); unlock_hrtimer_base(timer, &flags); @@ -1115,26 +1084,22 @@ EXPORT_SYMBOL_GPL(hrtimer_get_remaining); /** * hrtimer_get_next_event - get the time until next expiry event * - * Returns the delta to the next expiry event or KTIME_MAX if no timer - * is pending. + * Returns the next expiry time or KTIME_MAX if no timer is pending. */ -ktime_t hrtimer_get_next_event(void) +u64 hrtimer_get_next_event(void) { struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - ktime_t mindelta = { .tv64 = KTIME_MAX }; + u64 expires = KTIME_MAX; unsigned long flags; raw_spin_lock_irqsave(&cpu_base->lock, flags); - if (!hrtimer_hres_active()) - mindelta = ktime_sub(__hrtimer_get_next_event(cpu_base), - ktime_get()); + if (!__hrtimer_hres_active(cpu_base)) + expires = __hrtimer_get_next_event(cpu_base).tv64; raw_spin_unlock_irqrestore(&cpu_base->lock, flags); - if (mindelta.tv64 < 0) - mindelta.tv64 = 0; - return mindelta; + return expires; } #endif @@ -1176,37 +1141,73 @@ void hrtimer_init(struct hrtimer *timer, clockid_t clock_id, } EXPORT_SYMBOL_GPL(hrtimer_init); -/** - * hrtimer_get_res - get the timer resolution for a clock - * @which_clock: which clock to query - * @tp: pointer to timespec variable to store the resolution +/* + * A timer is active, when it is enqueued into the rbtree or the + * callback function is running or it's in the state of being migrated + * to another cpu. * - * Store the resolution of the clock selected by @which_clock in the - * variable pointed to by @tp. + * It is important for this function to not return a false negative. */ -int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp) +bool hrtimer_active(const struct hrtimer *timer) { struct hrtimer_cpu_base *cpu_base; - int base = hrtimer_clockid_to_base(which_clock); + unsigned int seq; - cpu_base = raw_cpu_ptr(&hrtimer_bases); - *tp = ktime_to_timespec(cpu_base->clock_base[base].resolution); + do { + cpu_base = READ_ONCE(timer->base->cpu_base); + seq = raw_read_seqcount_begin(&cpu_base->seq); - return 0; + if (timer->state != HRTIMER_STATE_INACTIVE || + cpu_base->running == timer) + return true; + + } while (read_seqcount_retry(&cpu_base->seq, seq) || + cpu_base != READ_ONCE(timer->base->cpu_base)); + + return false; } -EXPORT_SYMBOL_GPL(hrtimer_get_res); +EXPORT_SYMBOL_GPL(hrtimer_active); -static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) +/* + * The write_seqcount_barrier()s in __run_hrtimer() split the thing into 3 + * distinct sections: + * + * - queued: the timer is queued + * - callback: the timer is being ran + * - post: the timer is inactive or (re)queued + * + * On the read side we ensure we observe timer->state and cpu_base->running + * from the same section, if anything changed while we looked at it, we retry. + * This includes timer->base changing because sequence numbers alone are + * insufficient for that. + * + * The sequence numbers are required because otherwise we could still observe + * a false negative if the read side got smeared over multiple consequtive + * __run_hrtimer() invocations. + */ + +static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base, + struct hrtimer_clock_base *base, + struct hrtimer *timer, ktime_t *now) { - struct hrtimer_clock_base *base = timer->base; - struct hrtimer_cpu_base *cpu_base = base->cpu_base; enum hrtimer_restart (*fn)(struct hrtimer *); int restart; - WARN_ON(!irqs_disabled()); + lockdep_assert_held(&cpu_base->lock); debug_deactivate(timer); - __remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0); + cpu_base->running = timer; + + /* + * Separate the ->running assignment from the ->state assignment. + * + * As with a regular write barrier, this ensures the read side in + * hrtimer_active() cannot observe cpu_base->running == NULL && + * timer->state == INACTIVE. + */ + raw_write_seqcount_barrier(&cpu_base->seq); + + __remove_hrtimer(timer, base, HRTIMER_STATE_INACTIVE, 0); timer_stats_account_hrtimer(timer); fn = timer->function; @@ -1222,58 +1223,43 @@ static void __run_hrtimer(struct hrtimer *timer, ktime_t *now) raw_spin_lock(&cpu_base->lock); /* - * Note: We clear the CALLBACK bit after enqueue_hrtimer and + * Note: We clear the running state after enqueue_hrtimer and * we do not reprogramm the event hardware. Happens either in * hrtimer_start_range_ns() or in hrtimer_interrupt() + * + * Note: Because we dropped the cpu_base->lock above, + * hrtimer_start_range_ns() can have popped in and enqueued the timer + * for us already. */ - if (restart != HRTIMER_NORESTART) { - BUG_ON(timer->state != HRTIMER_STATE_CALLBACK); + if (restart != HRTIMER_NORESTART && + !(timer->state & HRTIMER_STATE_ENQUEUED)) enqueue_hrtimer(timer, base); - } - WARN_ON_ONCE(!(timer->state & HRTIMER_STATE_CALLBACK)); + /* + * Separate the ->running assignment from the ->state assignment. + * + * As with a regular write barrier, this ensures the read side in + * hrtimer_active() cannot observe cpu_base->running == NULL && + * timer->state == INACTIVE. + */ + raw_write_seqcount_barrier(&cpu_base->seq); - timer->state &= ~HRTIMER_STATE_CALLBACK; + WARN_ON_ONCE(cpu_base->running != timer); + cpu_base->running = NULL; } -#ifdef CONFIG_HIGH_RES_TIMERS - -/* - * High resolution timer interrupt - * Called with interrupts disabled - */ -void hrtimer_interrupt(struct clock_event_device *dev) +static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now) { - struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - ktime_t expires_next, now, entry_time, delta; - int i, retries = 0; - - BUG_ON(!cpu_base->hres_active); - cpu_base->nr_events++; - dev->next_event.tv64 = KTIME_MAX; - - raw_spin_lock(&cpu_base->lock); - entry_time = now = hrtimer_update_base(cpu_base); -retry: - cpu_base->in_hrtirq = 1; - /* - * We set expires_next to KTIME_MAX here with cpu_base->lock - * held to prevent that a timer is enqueued in our queue via - * the migration code. This does not affect enqueueing of - * timers which run their callback and need to be requeued on - * this CPU. - */ - cpu_base->expires_next.tv64 = KTIME_MAX; + struct hrtimer_clock_base *base = cpu_base->clock_base; + unsigned int active = cpu_base->active_bases; - for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) { - struct hrtimer_clock_base *base; + for (; active; base++, active >>= 1) { struct timerqueue_node *node; ktime_t basenow; - if (!(cpu_base->active_bases & (1 << i))) + if (!(active & 0x01)) continue; - base = cpu_base->clock_base + i; basenow = ktime_add(now, base->offset); while ((node = timerqueue_getnext(&base->active))) { @@ -1296,9 +1282,42 @@ retry: if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) break; - __run_hrtimer(timer, &basenow); + __run_hrtimer(cpu_base, base, timer, &basenow); } } +} + +#ifdef CONFIG_HIGH_RES_TIMERS + +/* + * High resolution timer interrupt + * Called with interrupts disabled + */ +void hrtimer_interrupt(struct clock_event_device *dev) +{ + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + ktime_t expires_next, now, entry_time, delta; + int retries = 0; + + BUG_ON(!cpu_base->hres_active); + cpu_base->nr_events++; + dev->next_event.tv64 = KTIME_MAX; + + raw_spin_lock(&cpu_base->lock); + entry_time = now = hrtimer_update_base(cpu_base); +retry: + cpu_base->in_hrtirq = 1; + /* + * We set expires_next to KTIME_MAX here with cpu_base->lock + * held to prevent that a timer is enqueued in our queue via + * the migration code. This does not affect enqueueing of + * timers which run their callback and need to be requeued on + * this CPU. + */ + cpu_base->expires_next.tv64 = KTIME_MAX; + + __hrtimer_run_queues(cpu_base, now); + /* Reevaluate the clock bases for the next expiry */ expires_next = __hrtimer_get_next_event(cpu_base); /* @@ -1310,8 +1329,7 @@ retry: raw_spin_unlock(&cpu_base->lock); /* Reprogramming necessary ? */ - if (expires_next.tv64 == KTIME_MAX || - !tick_program_event(expires_next, 0)) { + if (!tick_program_event(expires_next, 0)) { cpu_base->hang_detected = 0; return; } @@ -1344,8 +1362,8 @@ retry: cpu_base->hang_detected = 1; raw_spin_unlock(&cpu_base->lock); delta = ktime_sub(now, entry_time); - if (delta.tv64 > cpu_base->max_hang_time.tv64) - cpu_base->max_hang_time = delta; + if ((unsigned int)delta.tv64 > cpu_base->max_hang_time) + cpu_base->max_hang_time = (unsigned int) delta.tv64; /* * Limit it to a sensible value as we enforce a longer * delay. Give the CPU at least 100ms to catch up. @@ -1363,7 +1381,7 @@ retry: * local version of hrtimer_peek_ahead_timers() called with interrupts * disabled. */ -static void __hrtimer_peek_ahead_timers(void) +static inline void __hrtimer_peek_ahead_timers(void) { struct tick_device *td; @@ -1375,29 +1393,6 @@ static void __hrtimer_peek_ahead_timers(void) hrtimer_interrupt(td->evtdev); } -/** - * hrtimer_peek_ahead_timers -- run soft-expired timers now - * - * hrtimer_peek_ahead_timers will peek at the timer queue of - * the current cpu and check if there are any timers for which - * the soft expires time has passed. If any such timers exist, - * they are run immediately and then removed from the timer queue. - * - */ -void hrtimer_peek_ahead_timers(void) -{ - unsigned long flags; - - local_irq_save(flags); - __hrtimer_peek_ahead_timers(); - local_irq_restore(flags); -} - -static void run_hrtimer_softirq(struct softirq_action *h) -{ - hrtimer_peek_ahead_timers(); -} - #else /* CONFIG_HIGH_RES_TIMERS */ static inline void __hrtimer_peek_ahead_timers(void) { } @@ -1405,66 +1400,32 @@ static inline void __hrtimer_peek_ahead_timers(void) { } #endif /* !CONFIG_HIGH_RES_TIMERS */ /* - * Called from timer softirq every jiffy, expire hrtimers: - * - * For HRT its the fall back code to run the softirq in the timer - * softirq context in case the hrtimer initialization failed or has - * not been done yet. + * Called from run_local_timers in hardirq context every jiffy */ -void hrtimer_run_pending(void) +void hrtimer_run_queues(void) { - if (hrtimer_hres_active()) + struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); + ktime_t now; + + if (__hrtimer_hres_active(cpu_base)) return; /* - * This _is_ ugly: We have to check in the softirq context, - * whether we can switch to highres and / or nohz mode. The - * clocksource switch happens in the timer interrupt with - * xtime_lock held. Notification from there only sets the - * check bit in the tick_oneshot code, otherwise we might - * deadlock vs. xtime_lock. + * This _is_ ugly: We have to check periodically, whether we + * can switch to highres and / or nohz mode. The clocksource + * switch happens with xtime_lock held. Notification from + * there only sets the check bit in the tick_oneshot code, + * otherwise we might deadlock vs. xtime_lock. */ - if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) + if (tick_check_oneshot_change(!hrtimer_is_hres_enabled())) { hrtimer_switch_to_hres(); -} - -/* - * Called from hardirq context every jiffy - */ -void hrtimer_run_queues(void) -{ - struct timerqueue_node *node; - struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - struct hrtimer_clock_base *base; - int index, gettime = 1; - - if (hrtimer_hres_active()) return; - - for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) { - base = &cpu_base->clock_base[index]; - if (!timerqueue_getnext(&base->active)) - continue; - - if (gettime) { - hrtimer_get_softirq_time(cpu_base); - gettime = 0; - } - - raw_spin_lock(&cpu_base->lock); - - while ((node = timerqueue_getnext(&base->active))) { - struct hrtimer *timer; - - timer = container_of(node, struct hrtimer, node); - if (base->softirq_time.tv64 <= - hrtimer_get_expires_tv64(timer)) - break; - - __run_hrtimer(timer, &base->softirq_time); - } - raw_spin_unlock(&cpu_base->lock); } + + raw_spin_lock(&cpu_base->lock); + now = hrtimer_update_base(cpu_base); + __hrtimer_run_queues(cpu_base, now); + raw_spin_unlock(&cpu_base->lock); } /* @@ -1497,8 +1458,6 @@ static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mod do { set_current_state(TASK_INTERRUPTIBLE); hrtimer_start_expires(&t->timer, mode); - if (!hrtimer_active(&t->timer)) - t->task = NULL; if (likely(t->task)) freezable_schedule(); @@ -1642,11 +1601,11 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, debug_deactivate(timer); /* - * Mark it as STATE_MIGRATE not INACTIVE otherwise the + * Mark it as ENQUEUED not INACTIVE otherwise the * timer could be seen as !active and just vanish away * under us on another CPU */ - __remove_hrtimer(timer, old_base, HRTIMER_STATE_MIGRATE, 0); + __remove_hrtimer(timer, old_base, HRTIMER_STATE_ENQUEUED, 0); timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not @@ -1657,9 +1616,6 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, * event device. */ enqueue_hrtimer(timer, new_base); - - /* Clear the migration state bit */ - timer->state &= ~HRTIMER_STATE_MIGRATE; } } @@ -1731,9 +1687,6 @@ void __init hrtimers_init(void) hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE, (void *)(long)smp_processor_id()); register_cpu_notifier(&hrtimers_nb); -#ifdef CONFIG_HIGH_RES_TIMERS - open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq); -#endif } /** @@ -1772,8 +1725,6 @@ schedule_hrtimeout_range_clock(ktime_t *expires, unsigned long delta, hrtimer_init_sleeper(&t, current); hrtimer_start_expires(&t.timer, mode); - if (!hrtimer_active(&t.timer)) - t.task = NULL; if (likely(t.task)) schedule(); diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c index 7a681003001c..fb4d98c7fd43 100644 --- a/kernel/time/ntp.c +++ b/kernel/time/ntp.c @@ -35,6 +35,7 @@ unsigned long tick_nsec; static u64 tick_length; static u64 tick_length_base; +#define SECS_PER_DAY 86400 #define MAX_TICKADJ 500LL /* usecs */ #define MAX_TICKADJ_SCALED \ (((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ) @@ -76,6 +77,9 @@ static long time_adjust; /* constant (boot-param configurable) NTP tick adjustment (upscaled) */ static s64 ntp_tick_adj; +/* second value of the next pending leapsecond, or TIME64_MAX if no leap */ +static time64_t ntp_next_leap_sec = TIME64_MAX; + #ifdef CONFIG_NTP_PPS /* @@ -349,6 +353,7 @@ void ntp_clear(void) tick_length = tick_length_base; time_offset = 0; + ntp_next_leap_sec = TIME64_MAX; /* Clear PPS state variables */ pps_clear(); } @@ -359,6 +364,21 @@ u64 ntp_tick_length(void) return tick_length; } +/** + * ntp_get_next_leap - Returns the next leapsecond in CLOCK_REALTIME ktime_t + * + * Provides the time of the next leapsecond against CLOCK_REALTIME in + * a ktime_t format. Returns KTIME_MAX if no leapsecond is pending. + */ +ktime_t ntp_get_next_leap(void) +{ + ktime_t ret; + + if ((time_state == TIME_INS) && (time_status & STA_INS)) + return ktime_set(ntp_next_leap_sec, 0); + ret.tv64 = KTIME_MAX; + return ret; +} /* * this routine handles the overflow of the microsecond field @@ -382,15 +402,21 @@ int second_overflow(unsigned long secs) */ switch (time_state) { case TIME_OK: - if (time_status & STA_INS) + if (time_status & STA_INS) { time_state = TIME_INS; - else if (time_status & STA_DEL) + ntp_next_leap_sec = secs + SECS_PER_DAY - + (secs % SECS_PER_DAY); + } else if (time_status & STA_DEL) { time_state = TIME_DEL; + ntp_next_leap_sec = secs + SECS_PER_DAY - + ((secs+1) % SECS_PER_DAY); + } break; case TIME_INS: - if (!(time_status & STA_INS)) + if (!(time_status & STA_INS)) { + ntp_next_leap_sec = TIME64_MAX; time_state = TIME_OK; - else if (secs % 86400 == 0) { + } else if (secs % SECS_PER_DAY == 0) { leap = -1; time_state = TIME_OOP; printk(KERN_NOTICE @@ -398,19 +424,21 @@ int second_overflow(unsigned long secs) } break; case TIME_DEL: - if (!(time_status & STA_DEL)) + if (!(time_status & STA_DEL)) { + ntp_next_leap_sec = TIME64_MAX; time_state = TIME_OK; - else if ((secs + 1) % 86400 == 0) { + } else if ((secs + 1) % SECS_PER_DAY == 0) { leap = 1; + ntp_next_leap_sec = TIME64_MAX; time_state = TIME_WAIT; printk(KERN_NOTICE "Clock: deleting leap second 23:59:59 UTC\n"); } break; case TIME_OOP: + ntp_next_leap_sec = TIME64_MAX; time_state = TIME_WAIT; break; - case TIME_WAIT: if (!(time_status & (STA_INS | STA_DEL))) time_state = TIME_OK; @@ -547,6 +575,7 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts) if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) { time_state = TIME_OK; time_status = STA_UNSYNC; + ntp_next_leap_sec = TIME64_MAX; /* restart PPS frequency calibration */ pps_reset_freq_interval(); } @@ -711,6 +740,24 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai) if (!(time_status & STA_NANO)) txc->time.tv_usec /= NSEC_PER_USEC; + /* Handle leapsec adjustments */ + if (unlikely(ts->tv_sec >= ntp_next_leap_sec)) { + if ((time_state == TIME_INS) && (time_status & STA_INS)) { + result = TIME_OOP; + txc->tai++; + txc->time.tv_sec--; + } + if ((time_state == TIME_DEL) && (time_status & STA_DEL)) { + result = TIME_WAIT; + txc->tai--; + txc->time.tv_sec++; + } + if ((time_state == TIME_OOP) && + (ts->tv_sec == ntp_next_leap_sec)) { + result = TIME_WAIT; + } + } + return result; } diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h index bbd102ad9df7..65430504ca26 100644 --- a/kernel/time/ntp_internal.h +++ b/kernel/time/ntp_internal.h @@ -5,6 +5,7 @@ extern void ntp_init(void); extern void ntp_clear(void); /* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */ extern u64 ntp_tick_length(void); +extern ktime_t ntp_get_next_leap(void); extern int second_overflow(unsigned long secs); extern int ntp_validate_timex(struct timex *); extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *); diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c index 31ea01f42e1f..31d11ac9fa47 100644 --- a/kernel/time/posix-timers.c +++ b/kernel/time/posix-timers.c @@ -272,13 +272,20 @@ static int posix_get_tai(clockid_t which_clock, struct timespec *tp) return 0; } +static int posix_get_hrtimer_res(clockid_t which_clock, struct timespec *tp) +{ + tp->tv_sec = 0; + tp->tv_nsec = hrtimer_resolution; + return 0; +} + /* * Initialize everything, well, just everything in Posix clocks/timers ;) */ static __init int init_posix_timers(void) { struct k_clock clock_realtime = { - .clock_getres = hrtimer_get_res, + .clock_getres = posix_get_hrtimer_res, .clock_get = posix_clock_realtime_get, .clock_set = posix_clock_realtime_set, .clock_adj = posix_clock_realtime_adj, @@ -290,7 +297,7 @@ static __init int init_posix_timers(void) .timer_del = common_timer_del, }; struct k_clock clock_monotonic = { - .clock_getres = hrtimer_get_res, + .clock_getres = posix_get_hrtimer_res, .clock_get = posix_ktime_get_ts, .nsleep = common_nsleep, .nsleep_restart = hrtimer_nanosleep_restart, @@ -300,7 +307,7 @@ static __init int init_posix_timers(void) .timer_del = common_timer_del, }; struct k_clock clock_monotonic_raw = { - .clock_getres = hrtimer_get_res, + .clock_getres = posix_get_hrtimer_res, .clock_get = posix_get_monotonic_raw, }; struct k_clock clock_realtime_coarse = { @@ -312,7 +319,7 @@ static __init int init_posix_timers(void) .clock_get = posix_get_monotonic_coarse, }; struct k_clock clock_tai = { - .clock_getres = hrtimer_get_res, + .clock_getres = posix_get_hrtimer_res, .clock_get = posix_get_tai, .nsleep = common_nsleep, .nsleep_restart = hrtimer_nanosleep_restart, @@ -322,7 +329,7 @@ static __init int init_posix_timers(void) .timer_del = common_timer_del, }; struct k_clock clock_boottime = { - .clock_getres = hrtimer_get_res, + .clock_getres = posix_get_hrtimer_res, .clock_get = posix_get_boottime, .nsleep = common_nsleep, .nsleep_restart = hrtimer_nanosleep_restart, diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index 6aac4beedbbe..3e7db49a2381 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -22,6 +22,7 @@ static void bc_set_mode(enum clock_event_mode mode, struct clock_event_device *bc) { switch (mode) { + case CLOCK_EVT_MODE_UNUSED: case CLOCK_EVT_MODE_SHUTDOWN: /* * Note, we cannot cancel the timer here as we might @@ -66,9 +67,11 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) * hrtimer_{start/cancel} functions call into tracing, * calls to these functions must be bound within RCU_NONIDLE. */ - RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ? - !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) : - 0); + RCU_NONIDLE({ + bc_moved = hrtimer_try_to_cancel(&bctimer) >= 0; + if (bc_moved) + hrtimer_start(&bctimer, expires, + HRTIMER_MODE_ABS_PINNED);}); if (bc_moved) { /* Bind the "device" to the cpu */ bc->bound_on = smp_processor_id(); @@ -99,10 +102,13 @@ static enum hrtimer_restart bc_handler(struct hrtimer *t) { ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer); - if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX) + switch (ce_broadcast_hrtimer.mode) { + case CLOCK_EVT_MODE_ONESHOT: + if (ce_broadcast_hrtimer.next_event.tv64 != KTIME_MAX) + return HRTIMER_RESTART; + default: return HRTIMER_NORESTART; - - return HRTIMER_RESTART; + } } void tick_setup_hrtimer_broadcast(void) diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c index 7e8ca4f448a8..d39f32cdd1b5 100644 --- a/kernel/time/tick-broadcast.c +++ b/kernel/time/tick-broadcast.c @@ -255,18 +255,18 @@ int tick_receive_broadcast(void) /* * Broadcast the event to the cpus, which are set in the mask (mangled). */ -static void tick_do_broadcast(struct cpumask *mask) +static bool tick_do_broadcast(struct cpumask *mask) { int cpu = smp_processor_id(); struct tick_device *td; + bool local = false; /* * Check, if the current cpu is in the mask */ if (cpumask_test_cpu(cpu, mask)) { cpumask_clear_cpu(cpu, mask); - td = &per_cpu(tick_cpu_device, cpu); - td->evtdev->event_handler(td->evtdev); + local = true; } if (!cpumask_empty(mask)) { @@ -279,16 +279,17 @@ static void tick_do_broadcast(struct cpumask *mask) td = &per_cpu(tick_cpu_device, cpumask_first(mask)); td->evtdev->broadcast(mask); } + return local; } /* * Periodic broadcast: * - invoke the broadcast handlers */ -static void tick_do_periodic_broadcast(void) +static bool tick_do_periodic_broadcast(void) { cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask); - tick_do_broadcast(tmpmask); + return tick_do_broadcast(tmpmask); } /* @@ -296,34 +297,26 @@ static void tick_do_periodic_broadcast(void) */ static void tick_handle_periodic_broadcast(struct clock_event_device *dev) { - ktime_t next; + struct tick_device *td = this_cpu_ptr(&tick_cpu_device); + bool bc_local; raw_spin_lock(&tick_broadcast_lock); + bc_local = tick_do_periodic_broadcast(); - tick_do_periodic_broadcast(); + if (clockevent_state_oneshot(dev)) { + ktime_t next = ktime_add(dev->next_event, tick_period); - /* - * The device is in periodic mode. No reprogramming necessary: - */ - if (dev->state == CLOCK_EVT_STATE_PERIODIC) - goto unlock; + clockevents_program_event(dev, next, true); + } + raw_spin_unlock(&tick_broadcast_lock); /* - * Setup the next period for devices, which do not have - * periodic mode. We read dev->next_event first and add to it - * when the event already expired. clockevents_program_event() - * sets dev->next_event only when the event is really - * programmed to the device. + * We run the handler of the local cpu after dropping + * tick_broadcast_lock because the handler might deadlock when + * trying to switch to oneshot mode. */ - for (next = dev->next_event; ;) { - next = ktime_add(next, tick_period); - - if (!clockevents_program_event(dev, next, false)) - goto unlock; - tick_do_periodic_broadcast(); - } -unlock: - raw_spin_unlock(&tick_broadcast_lock); + if (bc_local) + td->evtdev->event_handler(td->evtdev); } /** @@ -532,23 +525,19 @@ static void tick_broadcast_set_affinity(struct clock_event_device *bc, irq_set_affinity(bc->irq, bc->cpumask); } -static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu, - ktime_t expires, int force) +static void tick_broadcast_set_event(struct clock_event_device *bc, int cpu, + ktime_t expires) { - int ret; - - if (bc->state != CLOCK_EVT_STATE_ONESHOT) - clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); + if (!clockevent_state_oneshot(bc)) + clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); - ret = clockevents_program_event(bc, expires, force); - if (!ret) - tick_broadcast_set_affinity(bc, cpumask_of(cpu)); - return ret; + clockevents_program_event(bc, expires, 1); + tick_broadcast_set_affinity(bc, cpumask_of(cpu)); } static void tick_resume_broadcast_oneshot(struct clock_event_device *bc) { - clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); + clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); } /* @@ -566,7 +555,7 @@ void tick_check_oneshot_broadcast_this_cpu(void) * switched over, leave the device alone. */ if (td->mode == TICKDEV_MODE_ONESHOT) { - clockevents_set_state(td->evtdev, + clockevents_switch_state(td->evtdev, CLOCK_EVT_STATE_ONESHOT); } } @@ -580,9 +569,9 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev) struct tick_device *td; ktime_t now, next_event; int cpu, next_cpu = 0; + bool bc_local; raw_spin_lock(&tick_broadcast_lock); -again: dev->next_event.tv64 = KTIME_MAX; next_event.tv64 = KTIME_MAX; cpumask_clear(tmpmask); @@ -624,7 +613,7 @@ again: /* * Wakeup the cpus which have an expired event. */ - tick_do_broadcast(tmpmask); + bc_local = tick_do_broadcast(tmpmask); /* * Two reasons for reprogram: @@ -636,15 +625,15 @@ again: * - There are pending events on sleeping CPUs which were not * in the event mask */ - if (next_event.tv64 != KTIME_MAX) { - /* - * Rearm the broadcast device. If event expired, - * repeat the above - */ - if (tick_broadcast_set_event(dev, next_cpu, next_event, 0)) - goto again; - } + if (next_event.tv64 != KTIME_MAX) + tick_broadcast_set_event(dev, next_cpu, next_event); + raw_spin_unlock(&tick_broadcast_lock); + + if (bc_local) { + td = this_cpu_ptr(&tick_cpu_device); + td->evtdev->event_handler(td->evtdev); + } } static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu) @@ -670,7 +659,7 @@ static void broadcast_shutdown_local(struct clock_event_device *bc, if (dev->next_event.tv64 < bc->next_event.tv64) return; } - clockevents_set_state(dev, CLOCK_EVT_STATE_SHUTDOWN); + clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN); } /** @@ -726,7 +715,7 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state) */ if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) && dev->next_event.tv64 < bc->next_event.tv64) - tick_broadcast_set_event(bc, cpu, dev->next_event, 1); + tick_broadcast_set_event(bc, cpu, dev->next_event); } /* * If the current CPU owns the hrtimer broadcast @@ -740,7 +729,7 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state) cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask); } else { if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) { - clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); /* * The cpu which was handling the broadcast * timer marked this cpu in the broadcast @@ -842,7 +831,7 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) /* Set it up only once ! */ if (bc->event_handler != tick_handle_oneshot_broadcast) { - int was_periodic = bc->state == CLOCK_EVT_STATE_PERIODIC; + int was_periodic = clockevent_state_periodic(bc); bc->event_handler = tick_handle_oneshot_broadcast; @@ -858,10 +847,10 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc) tick_broadcast_oneshot_mask, tmpmask); if (was_periodic && !cpumask_empty(tmpmask)) { - clockevents_set_state(bc, CLOCK_EVT_STATE_ONESHOT); + clockevents_switch_state(bc, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_init_next_event(tmpmask, tick_next_period); - tick_broadcast_set_event(bc, cpu, tick_next_period, 1); + tick_broadcast_set_event(bc, cpu, tick_next_period); } else bc->next_event.tv64 = KTIME_MAX; } else { diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 3ae6afa1eb98..17f144450050 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -102,7 +102,17 @@ void tick_handle_periodic(struct clock_event_device *dev) tick_periodic(cpu); - if (dev->state != CLOCK_EVT_STATE_ONESHOT) +#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON) + /* + * The cpu might have transitioned to HIGHRES or NOHZ mode via + * update_process_times() -> run_local_timers() -> + * hrtimer_run_queues(). + */ + if (dev->event_handler != tick_handle_periodic) + return; +#endif + + if (!clockevent_state_oneshot(dev)) return; for (;;) { /* @@ -140,7 +150,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) && !tick_broadcast_oneshot_active()) { - clockevents_set_state(dev, CLOCK_EVT_STATE_PERIODIC); + clockevents_switch_state(dev, CLOCK_EVT_STATE_PERIODIC); } else { unsigned long seq; ktime_t next; @@ -150,7 +160,7 @@ void tick_setup_periodic(struct clock_event_device *dev, int broadcast) next = tick_next_period; } while (read_seqretry(&jiffies_lock, seq)); - clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); for (;;) { if (!clockevents_program_event(dev, next, false)) @@ -367,7 +377,7 @@ void tick_shutdown(unsigned int cpu) * Prevent that the clock events layer tries to call * the set mode function! */ - dev->state = CLOCK_EVT_STATE_DETACHED; + clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED); dev->mode = CLOCK_EVT_MODE_UNUSED; clockevents_exchange_device(dev, NULL); dev->event_handler = clockevents_handle_noop; diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index b64fdd8054c5..966a5a6fdd0a 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -36,11 +36,22 @@ static inline int tick_device_is_functional(struct clock_event_device *dev) return !(dev->features & CLOCK_EVT_FEAT_DUMMY); } +static inline enum clock_event_state clockevent_get_state(struct clock_event_device *dev) +{ + return dev->state_use_accessors; +} + +static inline void clockevent_set_state(struct clock_event_device *dev, + enum clock_event_state state) +{ + dev->state_use_accessors = state; +} + extern void clockevents_shutdown(struct clock_event_device *dev); extern void clockevents_exchange_device(struct clock_event_device *old, struct clock_event_device *new); -extern void clockevents_set_state(struct clock_event_device *dev, - enum clock_event_state state); +extern void clockevents_switch_state(struct clock_event_device *dev, + enum clock_event_state state); extern int clockevents_program_event(struct clock_event_device *dev, ktime_t expires, bool force); extern void clockevents_handle_noop(struct clock_event_device *dev); @@ -137,3 +148,19 @@ extern void tick_nohz_init(void); # else static inline void tick_nohz_init(void) { } #endif + +#ifdef CONFIG_NO_HZ_COMMON +extern unsigned long tick_nohz_active; +#else +#define tick_nohz_active (0) +#endif + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void timers_update_migration(bool update_nohz); +#else +static inline void timers_update_migration(bool update_nohz) { } +#endif + +DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); + +extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem); diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c index 67a64b1670bf..b51344652330 100644 --- a/kernel/time/tick-oneshot.c +++ b/kernel/time/tick-oneshot.c @@ -28,6 +28,22 @@ int tick_program_event(ktime_t expires, int force) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + if (unlikely(expires.tv64 == KTIME_MAX)) { + /* + * We don't need the clock event device any more, stop it. + */ + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT_STOPPED); + return 0; + } + + if (unlikely(clockevent_state_oneshot_stopped(dev))) { + /* + * We need the clock event again, configure it in ONESHOT mode + * before using it. + */ + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); + } + return clockevents_program_event(dev, expires, force); } @@ -38,7 +54,7 @@ void tick_resume_oneshot(void) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(dev, ktime_get(), true); } @@ -50,7 +66,7 @@ void tick_setup_oneshot(struct clock_event_device *newdev, ktime_t next_event) { newdev->event_handler = handler; - clockevents_set_state(newdev, CLOCK_EVT_STATE_ONESHOT); + clockevents_switch_state(newdev, CLOCK_EVT_STATE_ONESHOT); clockevents_program_event(newdev, next_event, true); } @@ -81,7 +97,7 @@ int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *)) td->mode = TICKDEV_MODE_ONESHOT; dev->event_handler = handler; - clockevents_set_state(dev, CLOCK_EVT_STATE_ONESHOT); + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); tick_broadcast_switch_to_oneshot(); return 0; } diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 914259128145..c792429e98c6 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -399,7 +399,7 @@ void __init tick_nohz_init(void) * NO HZ enabled ? */ static int tick_nohz_enabled __read_mostly = 1; -int tick_nohz_active __read_mostly; +unsigned long tick_nohz_active __read_mostly; /* * Enable / Disable tickless mode */ @@ -565,156 +565,144 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time) } EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us); +static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) +{ + hrtimer_cancel(&ts->sched_timer); + hrtimer_set_expires(&ts->sched_timer, ts->last_tick); + + /* Forward the time to expire in the future */ + hrtimer_forward(&ts->sched_timer, now, tick_period); + + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); + else + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); +} + static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, ktime_t now, int cpu) { - unsigned long seq, last_jiffies, next_jiffies, delta_jiffies; - ktime_t last_update, expires, ret = { .tv64 = 0 }; - unsigned long rcu_delta_jiffies; struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); - u64 time_delta; - - time_delta = timekeeping_max_deferment(); + u64 basemono, next_tick, next_tmr, next_rcu, delta, expires; + unsigned long seq, basejiff; + ktime_t tick; /* Read jiffies and the time when jiffies were updated last */ do { seq = read_seqbegin(&jiffies_lock); - last_update = last_jiffies_update; - last_jiffies = jiffies; + basemono = last_jiffies_update.tv64; + basejiff = jiffies; } while (read_seqretry(&jiffies_lock, seq)); + ts->last_jiffies = basejiff; - if (rcu_needs_cpu(&rcu_delta_jiffies) || + if (rcu_needs_cpu(basemono, &next_rcu) || arch_needs_cpu() || irq_work_needs_cpu()) { - next_jiffies = last_jiffies + 1; - delta_jiffies = 1; + next_tick = basemono + TICK_NSEC; } else { - /* Get the next timer wheel timer */ - next_jiffies = get_next_timer_interrupt(last_jiffies); - delta_jiffies = next_jiffies - last_jiffies; - if (rcu_delta_jiffies < delta_jiffies) { - next_jiffies = last_jiffies + rcu_delta_jiffies; - delta_jiffies = rcu_delta_jiffies; - } + /* + * Get the next pending timer. If high resolution + * timers are enabled this only takes the timer wheel + * timers into account. If high resolution timers are + * disabled this also looks at the next expiring + * hrtimer. + */ + next_tmr = get_next_timer_interrupt(basejiff, basemono); + ts->next_timer = next_tmr; + /* Take the next rcu event into account */ + next_tick = next_rcu < next_tmr ? next_rcu : next_tmr; } /* - * Do not stop the tick, if we are only one off (or less) - * or if the cpu is required for RCU: + * If the tick is due in the next period, keep it ticking or + * restart it proper. */ - if (!ts->tick_stopped && delta_jiffies <= 1) - goto out; - - /* Schedule the tick, if we are at least one jiffie off */ - if ((long)delta_jiffies >= 1) { - - /* - * If this cpu is the one which updates jiffies, then - * give up the assignment and let it be taken by the - * cpu which runs the tick timer next, which might be - * this cpu as well. If we don't drop this here the - * jiffies might be stale and do_timer() never - * invoked. Keep track of the fact that it was the one - * which had the do_timer() duty last. If this cpu is - * the one which had the do_timer() duty last, we - * limit the sleep time to the timekeeping - * max_deferement value which we retrieved - * above. Otherwise we can sleep as long as we want. - */ - if (cpu == tick_do_timer_cpu) { - tick_do_timer_cpu = TICK_DO_TIMER_NONE; - ts->do_timer_last = 1; - } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { - time_delta = KTIME_MAX; - ts->do_timer_last = 0; - } else if (!ts->do_timer_last) { - time_delta = KTIME_MAX; + delta = next_tick - basemono; + if (delta <= (u64)TICK_NSEC) { + tick.tv64 = 0; + if (!ts->tick_stopped) + goto out; + if (delta == 0) { + /* Tick is stopped, but required now. Enforce it */ + tick_nohz_restart(ts, now); + goto out; } + } + + /* + * If this cpu is the one which updates jiffies, then give up + * the assignment and let it be taken by the cpu which runs + * the tick timer next, which might be this cpu as well. If we + * don't drop this here the jiffies might be stale and + * do_timer() never invoked. Keep track of the fact that it + * was the one which had the do_timer() duty last. If this cpu + * is the one which had the do_timer() duty last, we limit the + * sleep time to the timekeeping max_deferement value. + * Otherwise we can sleep as long as we want. + */ + delta = timekeeping_max_deferment(); + if (cpu == tick_do_timer_cpu) { + tick_do_timer_cpu = TICK_DO_TIMER_NONE; + ts->do_timer_last = 1; + } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { + delta = KTIME_MAX; + ts->do_timer_last = 0; + } else if (!ts->do_timer_last) { + delta = KTIME_MAX; + } #ifdef CONFIG_NO_HZ_FULL - if (!ts->inidle) { - time_delta = min(time_delta, - scheduler_tick_max_deferment()); - } + /* Limit the tick delta to the maximum scheduler deferment */ + if (!ts->inidle) + delta = min(delta, scheduler_tick_max_deferment()); #endif - /* - * calculate the expiry time for the next timer wheel - * timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals - * that there is no timer pending or at least extremely - * far into the future (12 days for HZ=1000). In this - * case we set the expiry to the end of time. - */ - if (likely(delta_jiffies < NEXT_TIMER_MAX_DELTA)) { - /* - * Calculate the time delta for the next timer event. - * If the time delta exceeds the maximum time delta - * permitted by the current clocksource then adjust - * the time delta accordingly to ensure the - * clocksource does not wrap. - */ - time_delta = min_t(u64, time_delta, - tick_period.tv64 * delta_jiffies); - } - - if (time_delta < KTIME_MAX) - expires = ktime_add_ns(last_update, time_delta); - else - expires.tv64 = KTIME_MAX; - - /* Skip reprogram of event if its not changed */ - if (ts->tick_stopped && ktime_equal(expires, dev->next_event)) - goto out; + /* Calculate the next expiry time */ + if (delta < (KTIME_MAX - basemono)) + expires = basemono + delta; + else + expires = KTIME_MAX; - ret = expires; + expires = min_t(u64, expires, next_tick); + tick.tv64 = expires; - /* - * nohz_stop_sched_tick can be called several times before - * the nohz_restart_sched_tick is called. This happens when - * interrupts arrive which do not cause a reschedule. In the - * first call we save the current tick time, so we can restart - * the scheduler tick in nohz_restart_sched_tick. - */ - if (!ts->tick_stopped) { - nohz_balance_enter_idle(cpu); - calc_load_enter_idle(); + /* Skip reprogram of event if its not changed */ + if (ts->tick_stopped && (expires == dev->next_event.tv64)) + goto out; - ts->last_tick = hrtimer_get_expires(&ts->sched_timer); - ts->tick_stopped = 1; - trace_tick_stop(1, " "); - } + /* + * nohz_stop_sched_tick can be called several times before + * the nohz_restart_sched_tick is called. This happens when + * interrupts arrive which do not cause a reschedule. In the + * first call we save the current tick time, so we can restart + * the scheduler tick in nohz_restart_sched_tick. + */ + if (!ts->tick_stopped) { + nohz_balance_enter_idle(cpu); + calc_load_enter_idle(); - /* - * If the expiration time == KTIME_MAX, then - * in this case we simply stop the tick timer. - */ - if (unlikely(expires.tv64 == KTIME_MAX)) { - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_cancel(&ts->sched_timer); - goto out; - } + ts->last_tick = hrtimer_get_expires(&ts->sched_timer); + ts->tick_stopped = 1; + trace_tick_stop(1, " "); + } - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start(&ts->sched_timer, expires, - HRTIMER_MODE_ABS_PINNED); - /* Check, if the timer was already in the past */ - if (hrtimer_active(&ts->sched_timer)) - goto out; - } else if (!tick_program_event(expires, 0)) - goto out; - /* - * We are past the event already. So we crossed a - * jiffie boundary. Update jiffies and raise the - * softirq. - */ - tick_do_update_jiffies64(ktime_get()); + /* + * If the expiration time == KTIME_MAX, then we simply stop + * the tick timer. + */ + if (unlikely(expires == KTIME_MAX)) { + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) + hrtimer_cancel(&ts->sched_timer); + goto out; } - raise_softirq_irqoff(TIMER_SOFTIRQ); + + if (ts->nohz_mode == NOHZ_MODE_HIGHRES) + hrtimer_start(&ts->sched_timer, tick, HRTIMER_MODE_ABS_PINNED); + else + tick_program_event(tick, 1); out: - ts->next_jiffies = next_jiffies; - ts->last_jiffies = last_jiffies; + /* Update the estimated sleep length */ ts->sleep_length = ktime_sub(dev->next_event, now); - - return ret; + return tick; } static void tick_nohz_full_stop_tick(struct tick_sched *ts) @@ -876,32 +864,6 @@ ktime_t tick_nohz_get_sleep_length(void) return ts->sleep_length; } -static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) -{ - hrtimer_cancel(&ts->sched_timer); - hrtimer_set_expires(&ts->sched_timer, ts->last_tick); - - while (1) { - /* Forward the time to expire in the future */ - hrtimer_forward(&ts->sched_timer, now, tick_period); - - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { - hrtimer_start_expires(&ts->sched_timer, - HRTIMER_MODE_ABS_PINNED); - /* Check, if the timer was already in the past */ - if (hrtimer_active(&ts->sched_timer)) - break; - } else { - if (!tick_program_event( - hrtimer_get_expires(&ts->sched_timer), 0)) - break; - } - /* Reread time and update jiffies */ - now = ktime_get(); - tick_do_update_jiffies64(now); - } -} - static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) { /* Update jiffies first */ @@ -972,12 +934,6 @@ void tick_nohz_idle_exit(void) local_irq_enable(); } -static int tick_nohz_reprogram(struct tick_sched *ts, ktime_t now) -{ - hrtimer_forward(&ts->sched_timer, now, tick_period); - return tick_program_event(hrtimer_get_expires(&ts->sched_timer), 0); -} - /* * The nohz low res interrupt handler */ @@ -996,10 +952,18 @@ static void tick_nohz_handler(struct clock_event_device *dev) if (unlikely(ts->tick_stopped)) return; - while (tick_nohz_reprogram(ts, now)) { - now = ktime_get(); - tick_do_update_jiffies64(now); - } + hrtimer_forward(&ts->sched_timer, now, tick_period); + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); +} + +static inline void tick_nohz_activate(struct tick_sched *ts, int mode) +{ + if (!tick_nohz_enabled) + return; + ts->nohz_mode = mode; + /* One update is enough */ + if (!test_and_set_bit(0, &tick_nohz_active)) + timers_update_migration(true); } /** @@ -1013,13 +977,8 @@ static void tick_nohz_switch_to_nohz(void) if (!tick_nohz_enabled) return; - local_irq_disable(); - if (tick_switch_to_oneshot(tick_nohz_handler)) { - local_irq_enable(); + if (tick_switch_to_oneshot(tick_nohz_handler)) return; - } - tick_nohz_active = 1; - ts->nohz_mode = NOHZ_MODE_LOWRES; /* * Recycle the hrtimer in ts, so we can share the @@ -1029,13 +988,10 @@ static void tick_nohz_switch_to_nohz(void) /* Get the next period */ next = tick_init_jiffy_update(); - for (;;) { - hrtimer_set_expires(&ts->sched_timer, next); - if (!tick_program_event(next, 0)) - break; - next = ktime_add(next, tick_period); - } - local_irq_enable(); + hrtimer_forward_now(&ts->sched_timer, tick_period); + hrtimer_set_expires(&ts->sched_timer, next); + tick_program_event(next, 1); + tick_nohz_activate(ts, NOHZ_MODE_LOWRES); } /* @@ -1087,6 +1043,7 @@ static inline void tick_nohz_irq_enter(void) static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } +static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -1167,22 +1124,9 @@ void tick_setup_sched_timer(void) hrtimer_add_expires_ns(&ts->sched_timer, offset); } - for (;;) { - hrtimer_forward(&ts->sched_timer, now, tick_period); - hrtimer_start_expires(&ts->sched_timer, - HRTIMER_MODE_ABS_PINNED); - /* Check, if the timer was already in the past */ - if (hrtimer_active(&ts->sched_timer)) - break; - now = ktime_get(); - } - -#ifdef CONFIG_NO_HZ_COMMON - if (tick_nohz_enabled) { - ts->nohz_mode = NOHZ_MODE_HIGHRES; - tick_nohz_active = 1; - } -#endif + hrtimer_forward(&ts->sched_timer, now, tick_period); + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED); + tick_nohz_activate(ts, NOHZ_MODE_HIGHRES); } #endif /* HIGH_RES_TIMERS */ @@ -1227,7 +1171,7 @@ void tick_oneshot_notify(void) * Called cyclic from the hrtimer softirq (driven by the timer * softirq) allow_nohz signals, that we can switch into low-res nohz * mode, because high resolution timers are disabled (either compile - * or runtime). + * or runtime). Called with interrupts disabled. */ int tick_check_oneshot_change(int allow_nohz) { diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 28b5da3e1a17..42fdf4958bcc 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -57,7 +57,7 @@ struct tick_sched { ktime_t iowait_sleeptime; ktime_t sleep_length; unsigned long last_jiffies; - unsigned long next_jiffies; + u64 next_timer; ktime_t idle_expires; int do_timer_last; }; diff --git a/kernel/time/time.c b/kernel/time/time.c index 2c85b7724af4..85d5bb1d67eb 100644 --- a/kernel/time/time.c +++ b/kernel/time/time.c @@ -41,7 +41,7 @@ #include <asm/uaccess.h> #include <asm/unistd.h> -#include "timeconst.h" +#include <generated/timeconst.h> #include "timekeeping.h" /* @@ -173,6 +173,10 @@ int do_sys_settimeofday(const struct timespec *tv, const struct timezone *tz) return error; if (tz) { + /* Verify we're witin the +-15 hrs range */ + if (tz->tz_minuteswest > 15*60 || tz->tz_minuteswest < -15*60) + return -EINVAL; + sys_tz = *tz; update_vsyscall_tz(); if (firsttime) { @@ -483,9 +487,11 @@ struct timespec64 ns_to_timespec64(const s64 nsec) } EXPORT_SYMBOL(ns_to_timespec64); #endif -/* - * When we convert to jiffies then we interpret incoming values - * the following way: +/** + * msecs_to_jiffies: - convert milliseconds to jiffies + * @m: time in milliseconds + * + * conversion is done as follows: * * - negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET) * @@ -493,66 +499,36 @@ EXPORT_SYMBOL(ns_to_timespec64); * MAX_JIFFY_OFFSET values] mean 'infinite timeout' too. * * - all other values are converted to jiffies by either multiplying - * the input value by a factor or dividing it with a factor - * - * We must also be careful about 32-bit overflows. + * the input value by a factor or dividing it with a factor and + * handling any 32-bit overflows. + * for the details see __msecs_to_jiffies() + * + * msecs_to_jiffies() checks for the passed in value being a constant + * via __builtin_constant_p() allowing gcc to eliminate most of the + * code, __msecs_to_jiffies() is called if the value passed does not + * allow constant folding and the actual conversion must be done at + * runtime. + * the _msecs_to_jiffies helpers are the HZ dependent conversion + * routines found in include/linux/jiffies.h */ -unsigned long msecs_to_jiffies(const unsigned int m) +unsigned long __msecs_to_jiffies(const unsigned int m) { /* * Negative value, means infinite timeout: */ if ((int)m < 0) return MAX_JIFFY_OFFSET; - -#if HZ <= MSEC_PER_SEC && !(MSEC_PER_SEC % HZ) - /* - * HZ is equal to or smaller than 1000, and 1000 is a nice - * round multiple of HZ, divide with the factor between them, - * but round upwards: - */ - return (m + (MSEC_PER_SEC / HZ) - 1) / (MSEC_PER_SEC / HZ); -#elif HZ > MSEC_PER_SEC && !(HZ % MSEC_PER_SEC) - /* - * HZ is larger than 1000, and HZ is a nice round multiple of - * 1000 - simply multiply with the factor between them. - * - * But first make sure the multiplication result cannot - * overflow: - */ - if (m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) - return MAX_JIFFY_OFFSET; - - return m * (HZ / MSEC_PER_SEC); -#else - /* - * Generic case - multiply, round and divide. But first - * check that if we are doing a net multiplication, that - * we wouldn't overflow: - */ - if (HZ > MSEC_PER_SEC && m > jiffies_to_msecs(MAX_JIFFY_OFFSET)) - return MAX_JIFFY_OFFSET; - - return (MSEC_TO_HZ_MUL32 * m + MSEC_TO_HZ_ADJ32) - >> MSEC_TO_HZ_SHR32; -#endif + return _msecs_to_jiffies(m); } -EXPORT_SYMBOL(msecs_to_jiffies); +EXPORT_SYMBOL(__msecs_to_jiffies); -unsigned long usecs_to_jiffies(const unsigned int u) +unsigned long __usecs_to_jiffies(const unsigned int u) { if (u > jiffies_to_usecs(MAX_JIFFY_OFFSET)) return MAX_JIFFY_OFFSET; -#if HZ <= USEC_PER_SEC && !(USEC_PER_SEC % HZ) - return (u + (USEC_PER_SEC / HZ) - 1) / (USEC_PER_SEC / HZ); -#elif HZ > USEC_PER_SEC && !(HZ % USEC_PER_SEC) - return u * (HZ / USEC_PER_SEC); -#else - return (USEC_TO_HZ_MUL32 * u + USEC_TO_HZ_ADJ32) - >> USEC_TO_HZ_SHR32; -#endif + return _usecs_to_jiffies(u); } -EXPORT_SYMBOL(usecs_to_jiffies); +EXPORT_SYMBOL(__usecs_to_jiffies); /* * The TICK_NSEC - 1 rounds up the value to the next resolution. Note diff --git a/kernel/time/timeconst.bc b/kernel/time/timeconst.bc index 511bdf2cafda..c7388dee8635 100644 --- a/kernel/time/timeconst.bc +++ b/kernel/time/timeconst.bc @@ -50,7 +50,7 @@ define timeconst(hz) { print "#include <linux/types.h>\n\n" print "#if HZ != ", hz, "\n" - print "#error \qkernel/timeconst.h has the wrong HZ value!\q\n" + print "#error \qinclude/generated/timeconst.h has the wrong HZ value!\q\n" print "#endif\n\n" if (hz < 2) { @@ -105,4 +105,5 @@ define timeconst(hz) { halt } +hz = read(); timeconst(hz) diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 946acb72179f..30b7a409bf1e 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -118,18 +118,6 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ -/* - * These simple flag variables are managed - * without locks, which is racy, but ok since - * we don't really care about being super - * precise about how many events were seen, - * just that a problem was observed. - */ -static int timekeeping_underflow_seen; -static int timekeeping_overflow_seen; - -/* last_warning is only modified under the timekeeping lock */ -static long timekeeping_last_warning; static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) { @@ -149,29 +137,30 @@ static void timekeeping_check_update(struct timekeeper *tk, cycle_t offset) } } - if (timekeeping_underflow_seen) { - if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + if (tk->underflow_seen) { + if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); - timekeeping_last_warning = jiffies; + tk->last_warning = jiffies; } - timekeeping_underflow_seen = 0; + tk->underflow_seen = 0; } - if (timekeeping_overflow_seen) { - if (jiffies - timekeeping_last_warning > WARNING_FREQ) { + if (tk->overflow_seen) { + if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); - timekeeping_last_warning = jiffies; + tk->last_warning = jiffies; } - timekeeping_overflow_seen = 0; + tk->overflow_seen = 0; } } static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) { + struct timekeeper *tk = &tk_core.timekeeper; cycle_t now, last, mask, max, delta; unsigned int seq; @@ -197,13 +186,13 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr) * mask-relative negative values. */ if (unlikely((~delta & mask) < (mask >> 3))) { - timekeeping_underflow_seen = 1; + tk->underflow_seen = 1; delta = 0; } /* Cap delta value to the max_cycles values to avoid mult overflows */ if (unlikely(delta > max)) { - timekeeping_overflow_seen = 1; + tk->overflow_seen = 1; delta = tkr->clock->max_cycles; } @@ -551,6 +540,17 @@ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* + * tk_update_leap_state - helper to update the next_leap_ktime + */ +static inline void tk_update_leap_state(struct timekeeper *tk) +{ + tk->next_leap_ktime = ntp_get_next_leap(); + if (tk->next_leap_ktime.tv64 != KTIME_MAX) + /* Convert to monotonic time */ + tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); +} + +/* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) @@ -591,17 +591,25 @@ static void timekeeping_update(struct timekeeper *tk, unsigned int action) ntp_clear(); } + tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); + update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); + update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); + + if (action & TK_CLOCK_WAS_SET) + tk->clock_was_set_seq++; + /* + * The mirroring of the data to the shadow-timekeeper needs + * to happen last here to ensure we don't over-write the + * timekeeper structure on the next update with stale data + */ if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); - - update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); - update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); } /** @@ -699,6 +707,23 @@ ktime_t ktime_get(void) } EXPORT_SYMBOL_GPL(ktime_get); +u32 ktime_get_resolution_ns(void) +{ + struct timekeeper *tk = &tk_core.timekeeper; + unsigned int seq; + u32 nsecs; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqcount_begin(&tk_core.seq); + nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; + } while (read_seqcount_retry(&tk_core.seq, seq)); + + return nsecs; +} +EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); + static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, @@ -1179,28 +1204,20 @@ void __weak read_persistent_clock64(struct timespec64 *ts64) } /** - * read_boot_clock - Return time of the system start. + * read_boot_clock64 - Return time of the system start. * * Weak dummy function for arches that do not yet support it. * Function to read the exact time the system has been started. - * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. + * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ -void __weak read_boot_clock(struct timespec *ts) +void __weak read_boot_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } -void __weak read_boot_clock64(struct timespec64 *ts64) -{ - struct timespec ts; - - read_boot_clock(&ts); - *ts64 = timespec_to_timespec64(ts); -} - /* Flag for if timekeeping_resume() has injected sleeptime */ static bool sleeptime_injected; @@ -1836,8 +1853,9 @@ void update_wall_time(void) * memcpy under the tk_core.seq against one before we start * updating. */ + timekeeping_update(tk, clock_set); memcpy(real_tk, tk, sizeof(*tk)); - timekeeping_update(real_tk, clock_set); + /* The memcpy must come last. Do not put anything here! */ write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); @@ -1926,47 +1944,20 @@ void do_timer(unsigned long ticks) } /** - * ktime_get_update_offsets_tick - hrtimer helper - * @offs_real: pointer to storage for monotonic -> realtime offset - * @offs_boot: pointer to storage for monotonic -> boottime offset - * @offs_tai: pointer to storage for monotonic -> clock tai offset - * - * Returns monotonic time at last tick and various offsets - */ -ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot, - ktime_t *offs_tai) -{ - struct timekeeper *tk = &tk_core.timekeeper; - unsigned int seq; - ktime_t base; - u64 nsecs; - - do { - seq = read_seqcount_begin(&tk_core.seq); - - base = tk->tkr_mono.base; - nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; - - *offs_real = tk->offs_real; - *offs_boot = tk->offs_boot; - *offs_tai = tk->offs_tai; - } while (read_seqcount_retry(&tk_core.seq, seq)); - - return ktime_add_ns(base, nsecs); -} - -#ifdef CONFIG_HIGH_RES_TIMERS -/** * ktime_get_update_offsets_now - hrtimer helper + * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * - * Returns current monotonic time and updates the offsets + * Returns current monotonic time and updates the offsets if the + * sequence number in @cwsseq and timekeeper.clock_was_set_seq are + * different. + * * Called from hrtimer_interrupt() or retrigger_next_event() */ -ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, - ktime_t *offs_tai) +ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, + ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; @@ -1978,15 +1969,23 @@ ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot, base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); + base = ktime_add_ns(base, nsecs); + + if (*cwsseq != tk->clock_was_set_seq) { + *cwsseq = tk->clock_was_set_seq; + *offs_real = tk->offs_real; + *offs_boot = tk->offs_boot; + *offs_tai = tk->offs_tai; + } + + /* Handle leapsecond insertion adjustments */ + if (unlikely(base.tv64 >= tk->next_leap_ktime.tv64)) + *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); - *offs_real = tk->offs_real; - *offs_boot = tk->offs_boot; - *offs_tai = tk->offs_tai; } while (read_seqcount_retry(&tk_core.seq, seq)); - return ktime_add_ns(base, nsecs); + return base; } -#endif /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function @@ -2027,6 +2026,8 @@ int do_adjtimex(struct timex *txc) __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); } + tk_update_leap_state(tk); + write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); diff --git a/kernel/time/timekeeping.h b/kernel/time/timekeeping.h index ead8794b9a4e..704f595ce83f 100644 --- a/kernel/time/timekeeping.h +++ b/kernel/time/timekeeping.h @@ -3,19 +3,16 @@ /* * Internal interfaces for kernel/time/ */ -extern ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, - ktime_t *offs_boot, - ktime_t *offs_tai); -extern ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, - ktime_t *offs_boot, - ktime_t *offs_tai); +extern ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, + ktime_t *offs_real, + ktime_t *offs_boot, + ktime_t *offs_tai); extern int timekeeping_valid_for_hres(void); extern u64 timekeeping_max_deferment(void); extern int timekeeping_inject_offset(struct timespec *ts); extern s32 timekeeping_get_tai_offset(void); extern void timekeeping_set_tai_offset(s32 tai_offset); -extern void timekeeping_clocktai(struct timespec *ts); extern int timekeeping_suspend(void); extern void timekeeping_resume(void); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 2ece3aa5069c..520499dd85af 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -49,6 +49,8 @@ #include <asm/timex.h> #include <asm/io.h> +#include "tick-internal.h" + #define CREATE_TRACE_POINTS #include <trace/events/timer.h> @@ -68,11 +70,11 @@ EXPORT_SYMBOL(jiffies_64); #define MAX_TVAL ((unsigned long)((1ULL << (TVR_BITS + 4*TVN_BITS)) - 1)) struct tvec { - struct list_head vec[TVN_SIZE]; + struct hlist_head vec[TVN_SIZE]; }; struct tvec_root { - struct list_head vec[TVR_SIZE]; + struct hlist_head vec[TVR_SIZE]; }; struct tvec_base { @@ -83,6 +85,8 @@ struct tvec_base { unsigned long active_timers; unsigned long all_timers; int cpu; + bool migration_enabled; + bool nohz_active; struct tvec_root tv1; struct tvec tv2; struct tvec tv3; @@ -90,43 +94,60 @@ struct tvec_base { struct tvec tv5; } ____cacheline_aligned; -/* - * __TIMER_INITIALIZER() needs to set ->base to a valid pointer (because we've - * made NULL special, hint: lock_timer_base()) and we cannot get a compile time - * pointer to per-cpu entries because we don't know where we'll map the section, - * even for the boot cpu. - * - * And so we use boot_tvec_bases for boot CPU and per-cpu __tvec_bases for the - * rest of them. - */ -struct tvec_base boot_tvec_bases; -EXPORT_SYMBOL(boot_tvec_bases); -static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; +static DEFINE_PER_CPU(struct tvec_base, tvec_bases); + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +unsigned int sysctl_timer_migration = 1; -/* Functions below help us manage 'deferrable' flag */ -static inline unsigned int tbase_get_deferrable(struct tvec_base *base) +void timers_update_migration(bool update_nohz) { - return ((unsigned int)(unsigned long)base & TIMER_DEFERRABLE); + bool on = sysctl_timer_migration && tick_nohz_active; + unsigned int cpu; + + /* Avoid the loop, if nothing to update */ + if (this_cpu_read(tvec_bases.migration_enabled) == on) + return; + + for_each_possible_cpu(cpu) { + per_cpu(tvec_bases.migration_enabled, cpu) = on; + per_cpu(hrtimer_bases.migration_enabled, cpu) = on; + if (!update_nohz) + continue; + per_cpu(tvec_bases.nohz_active, cpu) = true; + per_cpu(hrtimer_bases.nohz_active, cpu) = true; + } } -static inline unsigned int tbase_get_irqsafe(struct tvec_base *base) +int timer_migration_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) { - return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE); + static DEFINE_MUTEX(mutex); + int ret; + + mutex_lock(&mutex); + ret = proc_dointvec(table, write, buffer, lenp, ppos); + if (!ret && write) + timers_update_migration(false); + mutex_unlock(&mutex); + return ret; } -static inline struct tvec_base *tbase_get_base(struct tvec_base *base) +static inline struct tvec_base *get_target_base(struct tvec_base *base, + int pinned) { - return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK)); + if (pinned || !base->migration_enabled) + return this_cpu_ptr(&tvec_bases); + return per_cpu_ptr(&tvec_bases, get_nohz_timer_target()); } - -static inline void -timer_set_base(struct timer_list *timer, struct tvec_base *new_base) +#else +static inline struct tvec_base *get_target_base(struct tvec_base *base, + int pinned) { - unsigned long flags = (unsigned long)timer->base & TIMER_FLAG_MASK; - - timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags); + return this_cpu_ptr(&tvec_bases); } +#endif static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) @@ -349,26 +370,12 @@ void set_timer_slack(struct timer_list *timer, int slack_hz) } EXPORT_SYMBOL_GPL(set_timer_slack); -/* - * If the list is empty, catch up ->timer_jiffies to the current time. - * The caller must hold the tvec_base lock. Returns true if the list - * was empty and therefore ->timer_jiffies was updated. - */ -static bool catchup_timer_jiffies(struct tvec_base *base) -{ - if (!base->all_timers) { - base->timer_jiffies = jiffies; - return true; - } - return false; -} - static void __internal_add_timer(struct tvec_base *base, struct timer_list *timer) { unsigned long expires = timer->expires; unsigned long idx = expires - base->timer_jiffies; - struct list_head *vec; + struct hlist_head *vec; if (idx < TVR_SIZE) { int i = expires & TVR_MASK; @@ -401,25 +408,25 @@ __internal_add_timer(struct tvec_base *base, struct timer_list *timer) i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK; vec = base->tv5.vec + i; } - /* - * Timers are FIFO: - */ - list_add_tail(&timer->entry, vec); + + hlist_add_head(&timer->entry, vec); } static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) { - (void)catchup_timer_jiffies(base); + /* Advance base->jiffies, if the base is empty */ + if (!base->all_timers++) + base->timer_jiffies = jiffies; + __internal_add_timer(base, timer); /* * Update base->active_timers and base->next_timer */ - if (!tbase_get_deferrable(timer->base)) { + if (!(timer->flags & TIMER_DEFERRABLE)) { if (!base->active_timers++ || time_before(timer->expires, base->next_timer)) base->next_timer = timer->expires; } - base->all_timers++; /* * Check whether the other CPU is in dynticks mode and needs @@ -434,8 +441,11 @@ static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) * require special care against races with idle_cpu(), lets deal * with that later. */ - if (!tbase_get_deferrable(base) || tick_nohz_full_cpu(base->cpu)) - wake_up_nohz_cpu(base->cpu); + if (base->nohz_active) { + if (!(timer->flags & TIMER_DEFERRABLE) || + tick_nohz_full_cpu(base->cpu)) + wake_up_nohz_cpu(base->cpu); + } } #ifdef CONFIG_TIMER_STATS @@ -451,15 +461,12 @@ void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr) static void timer_stats_account_timer(struct timer_list *timer) { - unsigned int flag = 0; - if (likely(!timer->start_site)) return; - if (unlikely(tbase_get_deferrable(timer->base))) - flag |= TIMER_STATS_FLAG_DEFERRABLE; timer_stats_update_stats(timer, timer->start_pid, timer->start_site, - timer->function, timer->start_comm, flag); + timer->function, timer->start_comm, + timer->flags); } #else @@ -516,8 +523,8 @@ static int timer_fixup_activate(void *addr, enum debug_obj_state state) * statically initialized. We just make sure that it * is tracked in the object tracker. */ - if (timer->entry.next == NULL && - timer->entry.prev == TIMER_ENTRY_STATIC) { + if (timer->entry.pprev == NULL && + timer->entry.next == TIMER_ENTRY_STATIC) { debug_object_init(timer, &timer_debug_descr); debug_object_activate(timer, &timer_debug_descr); return 0; @@ -563,7 +570,7 @@ static int timer_fixup_assert_init(void *addr, enum debug_obj_state state) switch (state) { case ODEBUG_STATE_NOTAVAILABLE: - if (timer->entry.prev == TIMER_ENTRY_STATIC) { + if (timer->entry.next == TIMER_ENTRY_STATIC) { /* * This is not really a fixup. The timer was * statically initialized. We just make sure that it @@ -648,7 +655,7 @@ static inline void debug_activate(struct timer_list *timer, unsigned long expires) { debug_timer_activate(timer); - trace_timer_start(timer, expires); + trace_timer_start(timer, expires, timer->flags); } static inline void debug_deactivate(struct timer_list *timer) @@ -665,10 +672,8 @@ static inline void debug_assert_init(struct timer_list *timer) static void do_init_timer(struct timer_list *timer, unsigned int flags, const char *name, struct lock_class_key *key) { - struct tvec_base *base = raw_cpu_read(tvec_bases); - - timer->entry.next = NULL; - timer->base = (void *)((unsigned long)base | flags); + timer->entry.pprev = NULL; + timer->flags = flags | raw_smp_processor_id(); timer->slack = -1; #ifdef CONFIG_TIMER_STATS timer->start_site = NULL; @@ -699,24 +704,23 @@ EXPORT_SYMBOL(init_timer_key); static inline void detach_timer(struct timer_list *timer, bool clear_pending) { - struct list_head *entry = &timer->entry; + struct hlist_node *entry = &timer->entry; debug_deactivate(timer); - __list_del(entry->prev, entry->next); + __hlist_del(entry); if (clear_pending) - entry->next = NULL; - entry->prev = LIST_POISON2; + entry->pprev = NULL; + entry->next = LIST_POISON2; } static inline void detach_expired_timer(struct timer_list *timer, struct tvec_base *base) { detach_timer(timer, true); - if (!tbase_get_deferrable(timer->base)) + if (!(timer->flags & TIMER_DEFERRABLE)) base->active_timers--; base->all_timers--; - (void)catchup_timer_jiffies(base); } static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, @@ -726,13 +730,14 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, return 0; detach_timer(timer, clear_pending); - if (!tbase_get_deferrable(timer->base)) { + if (!(timer->flags & TIMER_DEFERRABLE)) { base->active_timers--; if (timer->expires == base->next_timer) base->next_timer = base->timer_jiffies; } - base->all_timers--; - (void)catchup_timer_jiffies(base); + /* If this was the last timer, advance base->jiffies */ + if (!--base->all_timers) + base->timer_jiffies = jiffies; return 1; } @@ -744,24 +749,22 @@ static int detach_if_pending(struct timer_list *timer, struct tvec_base *base, * So __run_timers/migrate_timers can safely modify all timers which could * be found on ->tvX lists. * - * When the timer's base is locked, and the timer removed from list, it is - * possible to set timer->base = NULL and drop the lock: the timer remains - * locked. + * When the timer's base is locked and removed from the list, the + * TIMER_MIGRATING flag is set, FIXME */ static struct tvec_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { - struct tvec_base *base; - for (;;) { - struct tvec_base *prelock_base = timer->base; - base = tbase_get_base(prelock_base); - if (likely(base != NULL)) { + u32 tf = timer->flags; + struct tvec_base *base; + + if (!(tf & TIMER_MIGRATING)) { + base = per_cpu_ptr(&tvec_bases, tf & TIMER_CPUMASK); spin_lock_irqsave(&base->lock, *flags); - if (likely(prelock_base == timer->base)) + if (timer->flags == tf) return base; - /* The timer has migrated to another CPU */ spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); @@ -770,11 +773,11 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, static inline int __mod_timer(struct timer_list *timer, unsigned long expires, - bool pending_only, int pinned) + bool pending_only, int pinned) { struct tvec_base *base, *new_base; unsigned long flags; - int ret = 0 , cpu; + int ret = 0; timer_stats_timer_set_start_info(timer); BUG_ON(!timer->function); @@ -787,8 +790,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, debug_activate(timer, expires); - cpu = get_nohz_timer_target(pinned); - new_base = per_cpu(tvec_bases, cpu); + new_base = get_target_base(base, pinned); if (base != new_base) { /* @@ -800,11 +802,13 @@ __mod_timer(struct timer_list *timer, unsigned long expires, */ if (likely(base->running_timer != timer)) { /* See the comment in lock_timer_base() */ - timer_set_base(timer, NULL); + timer->flags |= TIMER_MIGRATING; + spin_unlock(&base->lock); base = new_base; spin_lock(&base->lock); - timer_set_base(timer, base); + timer->flags &= ~TIMER_BASEMASK; + timer->flags |= base->cpu; } } @@ -966,13 +970,13 @@ EXPORT_SYMBOL(add_timer); */ void add_timer_on(struct timer_list *timer, int cpu) { - struct tvec_base *base = per_cpu(tvec_bases, cpu); + struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu); unsigned long flags; timer_stats_timer_set_start_info(timer); BUG_ON(timer_pending(timer) || !timer->function); spin_lock_irqsave(&base->lock, flags); - timer_set_base(timer, base); + timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; debug_activate(timer, timer->expires); internal_add_timer(base, timer); spin_unlock_irqrestore(&base->lock, flags); @@ -1037,8 +1041,6 @@ int try_to_del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(try_to_del_timer_sync); #ifdef CONFIG_SMP -static DEFINE_PER_CPU(struct tvec_base, __tvec_bases); - /** * del_timer_sync - deactivate a timer and wait for the handler to finish. * @timer: the timer to be deactivated @@ -1093,7 +1095,7 @@ int del_timer_sync(struct timer_list *timer) * don't use it in hardirq context, because it * could lead to deadlock. */ - WARN_ON(in_irq() && !tbase_get_irqsafe(timer->base)); + WARN_ON(in_irq() && !(timer->flags & TIMER_IRQSAFE)); for (;;) { int ret = try_to_del_timer_sync(timer); if (ret >= 0) @@ -1107,17 +1109,17 @@ EXPORT_SYMBOL(del_timer_sync); static int cascade(struct tvec_base *base, struct tvec *tv, int index) { /* cascade all the timers from tv up one level */ - struct timer_list *timer, *tmp; - struct list_head tv_list; + struct timer_list *timer; + struct hlist_node *tmp; + struct hlist_head tv_list; - list_replace_init(tv->vec + index, &tv_list); + hlist_move_list(tv->vec + index, &tv_list); /* * We are removing _all_ timers from the list, so we * don't have to detach them individually. */ - list_for_each_entry_safe(timer, tmp, &tv_list, entry) { - BUG_ON(tbase_get_base(timer->base) != base); + hlist_for_each_entry_safe(timer, tmp, &tv_list, entry) { /* No accounting, while moving them */ __internal_add_timer(base, timer); } @@ -1182,14 +1184,18 @@ static inline void __run_timers(struct tvec_base *base) struct timer_list *timer; spin_lock_irq(&base->lock); - if (catchup_timer_jiffies(base)) { - spin_unlock_irq(&base->lock); - return; - } + while (time_after_eq(jiffies, base->timer_jiffies)) { - struct list_head work_list; - struct list_head *head = &work_list; - int index = base->timer_jiffies & TVR_MASK; + struct hlist_head work_list; + struct hlist_head *head = &work_list; + int index; + + if (!base->all_timers) { + base->timer_jiffies = jiffies; + break; + } + + index = base->timer_jiffies & TVR_MASK; /* * Cascade timers: @@ -1200,16 +1206,16 @@ static inline void __run_timers(struct tvec_base *base) !cascade(base, &base->tv4, INDEX(2))) cascade(base, &base->tv5, INDEX(3)); ++base->timer_jiffies; - list_replace_init(base->tv1.vec + index, head); - while (!list_empty(head)) { + hlist_move_list(base->tv1.vec + index, head); + while (!hlist_empty(head)) { void (*fn)(unsigned long); unsigned long data; bool irqsafe; - timer = list_first_entry(head, struct timer_list,entry); + timer = hlist_entry(head->first, struct timer_list, entry); fn = timer->function; data = timer->data; - irqsafe = tbase_get_irqsafe(timer->base); + irqsafe = timer->flags & TIMER_IRQSAFE; timer_stats_account_timer(timer); @@ -1248,8 +1254,8 @@ static unsigned long __next_timer_interrupt(struct tvec_base *base) /* Look for timer events in tv1. */ index = slot = timer_jiffies & TVR_MASK; do { - list_for_each_entry(nte, base->tv1.vec + slot, entry) { - if (tbase_get_deferrable(nte->base)) + hlist_for_each_entry(nte, base->tv1.vec + slot, entry) { + if (nte->flags & TIMER_DEFERRABLE) continue; found = 1; @@ -1279,8 +1285,8 @@ cascade: index = slot = timer_jiffies & TVN_MASK; do { - list_for_each_entry(nte, varp->vec + slot, entry) { - if (tbase_get_deferrable(nte->base)) + hlist_for_each_entry(nte, varp->vec + slot, entry) { + if (nte->flags & TIMER_DEFERRABLE) continue; found = 1; @@ -1311,54 +1317,48 @@ cascade: * Check, if the next hrtimer event is before the next timer wheel * event: */ -static unsigned long cmp_next_hrtimer_event(unsigned long now, - unsigned long expires) +static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) { - ktime_t hr_delta = hrtimer_get_next_event(); - struct timespec tsdelta; - unsigned long delta; - - if (hr_delta.tv64 == KTIME_MAX) - return expires; + u64 nextevt = hrtimer_get_next_event(); /* - * Expired timer available, let it expire in the next tick + * If high resolution timers are enabled + * hrtimer_get_next_event() returns KTIME_MAX. */ - if (hr_delta.tv64 <= 0) - return now + 1; - - tsdelta = ktime_to_timespec(hr_delta); - delta = timespec_to_jiffies(&tsdelta); + if (expires <= nextevt) + return expires; /* - * Limit the delta to the max value, which is checked in - * tick_nohz_stop_sched_tick(): + * If the next timer is already expired, return the tick base + * time so the tick is fired immediately. */ - if (delta > NEXT_TIMER_MAX_DELTA) - delta = NEXT_TIMER_MAX_DELTA; + if (nextevt <= basem) + return basem; /* - * Take rounding errors in to account and make sure, that it - * expires in the next tick. Otherwise we go into an endless - * ping pong due to tick_nohz_stop_sched_tick() retriggering - * the timer softirq + * Round up to the next jiffie. High resolution timers are + * off, so the hrtimers are expired in the tick and we need to + * make sure that this tick really expires the timer to avoid + * a ping pong of the nohz stop code. + * + * Use DIV_ROUND_UP_ULL to prevent gcc calling __divdi3 */ - if (delta < 1) - delta = 1; - now += delta; - if (time_before(now, expires)) - return now; - return expires; + return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } /** - * get_next_timer_interrupt - return the jiffy of the next pending timer - * @now: current time (in jiffies) + * get_next_timer_interrupt - return the time (clock mono) of the next timer + * @basej: base time jiffies + * @basem: base time clock monotonic + * + * Returns the tick aligned clock monotonic time of the next pending + * timer or KTIME_MAX if no timer is pending. */ -unsigned long get_next_timer_interrupt(unsigned long now) +u64 get_next_timer_interrupt(unsigned long basej, u64 basem) { - struct tvec_base *base = __this_cpu_read(tvec_bases); - unsigned long expires = now + NEXT_TIMER_MAX_DELTA; + struct tvec_base *base = this_cpu_ptr(&tvec_bases); + u64 expires = KTIME_MAX; + unsigned long nextevt; /* * Pretend that there is no timer pending if the cpu is offline. @@ -1371,14 +1371,15 @@ unsigned long get_next_timer_interrupt(unsigned long now) if (base->active_timers) { if (time_before_eq(base->next_timer, base->timer_jiffies)) base->next_timer = __next_timer_interrupt(base); - expires = base->next_timer; + nextevt = base->next_timer; + if (time_before_eq(nextevt, basej)) + expires = basem; + else + expires = basem + (nextevt - basej) * TICK_NSEC; } spin_unlock(&base->lock); - if (time_before_eq(expires, now)) - return now; - - return cmp_next_hrtimer_event(now, expires); + return cmp_next_hrtimer_event(basem, expires); } #endif @@ -1407,9 +1408,7 @@ void update_process_times(int user_tick) */ static void run_timer_softirq(struct softirq_action *h) { - struct tvec_base *base = __this_cpu_read(tvec_bases); - - hrtimer_run_pending(); + struct tvec_base *base = this_cpu_ptr(&tvec_bases); if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); @@ -1545,15 +1544,16 @@ signed long __sched schedule_timeout_uninterruptible(signed long timeout) EXPORT_SYMBOL(schedule_timeout_uninterruptible); #ifdef CONFIG_HOTPLUG_CPU -static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head) +static void migrate_timer_list(struct tvec_base *new_base, struct hlist_head *head) { struct timer_list *timer; + int cpu = new_base->cpu; - while (!list_empty(head)) { - timer = list_first_entry(head, struct timer_list, entry); + while (!hlist_empty(head)) { + timer = hlist_entry(head->first, struct timer_list, entry); /* We ignore the accounting on the dying cpu */ detach_timer(timer, false); - timer_set_base(timer, new_base); + timer->flags = (timer->flags & ~TIMER_BASEMASK) | cpu; internal_add_timer(new_base, timer); } } @@ -1565,8 +1565,8 @@ static void migrate_timers(int cpu) int i; BUG_ON(cpu_online(cpu)); - old_base = per_cpu(tvec_bases, cpu); - new_base = get_cpu_var(tvec_bases); + old_base = per_cpu_ptr(&tvec_bases, cpu); + new_base = this_cpu_ptr(&tvec_bases); /* * The caller is globally serialized and nobody else * takes two locks at once, deadlock is not possible. @@ -1590,7 +1590,6 @@ static void migrate_timers(int cpu) spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); - put_cpu_var(tvec_bases); } static int timer_cpu_notify(struct notifier_block *self, @@ -1616,52 +1615,27 @@ static inline void timer_register_cpu_notifier(void) static inline void timer_register_cpu_notifier(void) { } #endif /* CONFIG_HOTPLUG_CPU */ -static void __init init_timer_cpu(struct tvec_base *base, int cpu) +static void __init init_timer_cpu(int cpu) { - int j; - - BUG_ON(base != tbase_get_base(base)); + struct tvec_base *base = per_cpu_ptr(&tvec_bases, cpu); base->cpu = cpu; - per_cpu(tvec_bases, cpu) = base; spin_lock_init(&base->lock); - for (j = 0; j < TVN_SIZE; j++) { - INIT_LIST_HEAD(base->tv5.vec + j); - INIT_LIST_HEAD(base->tv4.vec + j); - INIT_LIST_HEAD(base->tv3.vec + j); - INIT_LIST_HEAD(base->tv2.vec + j); - } - for (j = 0; j < TVR_SIZE; j++) - INIT_LIST_HEAD(base->tv1.vec + j); - base->timer_jiffies = jiffies; base->next_timer = base->timer_jiffies; } static void __init init_timer_cpus(void) { - struct tvec_base *base; - int local_cpu = smp_processor_id(); int cpu; - for_each_possible_cpu(cpu) { - if (cpu == local_cpu) - base = &boot_tvec_bases; -#ifdef CONFIG_SMP - else - base = per_cpu_ptr(&__tvec_bases, cpu); -#endif - - init_timer_cpu(base, cpu); - } + for_each_possible_cpu(cpu) + init_timer_cpu(cpu); } void __init init_timers(void) { - /* ensure there are enough low bits for flags in timer->base pointer */ - BUILD_BUG_ON(__alignof__(struct tvec_base) & TIMER_FLAG_MASK); - init_timer_cpus(); init_timer_stats(); timer_register_cpu_notifier(); @@ -1697,14 +1671,14 @@ unsigned long msleep_interruptible(unsigned int msecs) EXPORT_SYMBOL(msleep_interruptible); -static int __sched do_usleep_range(unsigned long min, unsigned long max) +static void __sched do_usleep_range(unsigned long min, unsigned long max) { ktime_t kmin; unsigned long delta; kmin = ktime_set(0, min * NSEC_PER_USEC); delta = (max - min) * NSEC_PER_USEC; - return schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL); + schedule_hrtimeout_range(&kmin, delta, HRTIMER_MODE_REL); } /** @@ -1712,7 +1686,7 @@ static int __sched do_usleep_range(unsigned long min, unsigned long max) * @min: Minimum time in usecs to sleep * @max: Maximum time in usecs to sleep */ -void usleep_range(unsigned long min, unsigned long max) +void __sched usleep_range(unsigned long min, unsigned long max) { __set_current_state(TASK_UNINTERRUPTIBLE); do_usleep_range(min, max); diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index e878c2e0ba45..a4536e1e3e2a 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -29,19 +29,24 @@ struct timer_list_iter { typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes); -DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); - /* * This allows printing both to /proc/timer_list and * to the console (on SysRq-Q): */ -#define SEQ_printf(m, x...) \ - do { \ - if (m) \ - seq_printf(m, x); \ - else \ - printk(x); \ - } while (0) +__printf(2, 3) +static void SEQ_printf(struct seq_file *m, const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + + if (m) + seq_vprintf(m, fmt, args); + else + vprintk(fmt, args); + + va_end(args); +} static void print_name_offset(struct seq_file *m, void *sym) { @@ -120,10 +125,10 @@ static void print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now) { SEQ_printf(m, " .base: %pK\n", base); - SEQ_printf(m, " .index: %d\n", - base->index); - SEQ_printf(m, " .resolution: %Lu nsecs\n", - (unsigned long long)ktime_to_ns(base->resolution)); + SEQ_printf(m, " .index: %d\n", base->index); + + SEQ_printf(m, " .resolution: %u nsecs\n", (unsigned) hrtimer_resolution); + SEQ_printf(m, " .get_time: "); print_name_offset(m, base->get_time); SEQ_printf(m, "\n"); @@ -158,7 +163,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) P(nr_events); P(nr_retries); P(nr_hangs); - P_ns(max_hang_time); + P(max_hang_time); #endif #undef P #undef P_ns @@ -184,7 +189,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) P_ns(idle_sleeptime); P_ns(iowait_sleeptime); P(last_jiffies); - P(next_jiffies); + P(next_timer); P_ns(idle_expires); SEQ_printf(m, "jiffies: %Lu\n", (unsigned long long)jiffies); @@ -251,6 +256,12 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu) SEQ_printf(m, "\n"); } + if (dev->set_state_oneshot_stopped) { + SEQ_printf(m, " oneshot stopped: "); + print_name_offset(m, dev->set_state_oneshot_stopped); + SEQ_printf(m, "\n"); + } + if (dev->tick_resume) { SEQ_printf(m, " resume: "); print_name_offset(m, dev->tick_resume); @@ -269,11 +280,11 @@ static void timer_list_show_tickdevices_header(struct seq_file *m) { #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST print_tickdevice(m, tick_get_broadcast_device(), -1); - SEQ_printf(m, "tick_broadcast_mask: %08lx\n", - cpumask_bits(tick_get_broadcast_mask())[0]); + SEQ_printf(m, "tick_broadcast_mask: %*pb\n", + cpumask_pr_args(tick_get_broadcast_mask())); #ifdef CONFIG_TICK_ONESHOT - SEQ_printf(m, "tick_broadcast_oneshot_mask: %08lx\n", - cpumask_bits(tick_get_broadcast_oneshot_mask())[0]); + SEQ_printf(m, "tick_broadcast_oneshot_mask: %*pb\n", + cpumask_pr_args(tick_get_broadcast_oneshot_mask())); #endif SEQ_printf(m, "\n"); #endif @@ -282,7 +293,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m) static inline void timer_list_header(struct seq_file *m, u64 now) { - SEQ_printf(m, "Timer List Version: v0.7\n"); + SEQ_printf(m, "Timer List Version: v0.8\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); SEQ_printf(m, "\n"); diff --git a/kernel/time/timer_stats.c b/kernel/time/timer_stats.c index 1fb08f21302e..1adecb4b87c8 100644 --- a/kernel/time/timer_stats.c +++ b/kernel/time/timer_stats.c @@ -68,7 +68,7 @@ struct entry { * Number of timeout events: */ unsigned long count; - unsigned int timer_flag; + u32 flags; /* * We save the command-line string to preserve @@ -227,13 +227,13 @@ static struct entry *tstat_lookup(struct entry *entry, char *comm) * @startf: pointer to the function which did the timer setup * @timerf: pointer to the timer callback function of the timer * @comm: name of the process which set up the timer + * @tflags: The flags field of the timer * * When the timer is already registered, then the event counter is * incremented. Otherwise the timer is registered in a free slot. */ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, - void *timerf, char *comm, - unsigned int timer_flag) + void *timerf, char *comm, u32 tflags) { /* * It doesn't matter which lock we take: @@ -251,7 +251,7 @@ void timer_stats_update_stats(void *timer, pid_t pid, void *startf, input.start_func = startf; input.expire_func = timerf; input.pid = pid; - input.timer_flag = timer_flag; + input.flags = tflags; raw_spin_lock_irqsave(lock, flags); if (!timer_stats_active) @@ -306,7 +306,7 @@ static int tstats_show(struct seq_file *m, void *v) for (i = 0; i < nr_entries; i++) { entry = entries + i; - if (entry->timer_flag & TIMER_STATS_FLAG_DEFERRABLE) { + if (entry->flags & TIMER_DEFERRABLE) { seq_printf(m, "%4luD, %5d %-16s ", entry->count, entry->pid, entry->comm); } else { |