diff options
Diffstat (limited to 'kernel/sched/core.c')
| -rw-r--r-- | kernel/sched/core.c | 5003 |
1 files changed, 2477 insertions, 2526 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5255c9d2e05..bc1638b3344 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -71,7 +71,11 @@ #include <linux/ftrace.h> #include <linux/slab.h> #include <linux/init_task.h> +#include <linux/binfmts.h> +#include <linux/context_tracking.h> +#include <linux/compiler.h> +#include <asm/switch_to.h> #include <asm/tlb.h> #include <asm/irq_regs.h> #include <asm/mutex.h> @@ -80,11 +84,28 @@ #endif #include "sched.h" -#include "../workqueue_sched.h" +#include "../workqueue_internal.h" +#include "../smpboot.h" #define CREATE_TRACE_POINTS #include <trace/events/sched.h> +#ifdef smp_mb__before_atomic +void __smp_mb__before_atomic(void) +{ + smp_mb__before_atomic(); +} +EXPORT_SYMBOL(__smp_mb__before_atomic); +#endif + +#ifdef smp_mb__after_atomic +void __smp_mb__after_atomic(void) +{ + smp_mb__after_atomic(); +} +EXPORT_SYMBOL(__smp_mb__after_atomic); +#endif + void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period) { unsigned long delta; @@ -139,9 +160,8 @@ const_debug unsigned int sysctl_sched_features = #define SCHED_FEAT(name, enabled) \ #name , -static __read_mostly char *sched_feat_names[] = { +static const char * const sched_feat_names[] = { #include "features.h" - NULL }; #undef SCHED_FEAT @@ -162,13 +182,13 @@ static int sched_feat_show(struct seq_file *m, void *v) #ifdef HAVE_JUMP_LABEL -#define jump_label_key__true jump_label_key_enabled -#define jump_label_key__false jump_label_key_disabled +#define jump_label_key__true STATIC_KEY_INIT_TRUE +#define jump_label_key__false STATIC_KEY_INIT_FALSE #define SCHED_FEAT(name, enabled) \ jump_label_key__##enabled , -struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = { +struct static_key sched_feat_keys[__SCHED_FEAT_NR] = { #include "features.h" }; @@ -176,37 +196,24 @@ struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = { static void sched_feat_disable(int i) { - if (jump_label_enabled(&sched_feat_keys[i])) - jump_label_dec(&sched_feat_keys[i]); + if (static_key_enabled(&sched_feat_keys[i])) + static_key_slow_dec(&sched_feat_keys[i]); } static void sched_feat_enable(int i) { - if (!jump_label_enabled(&sched_feat_keys[i])) - jump_label_inc(&sched_feat_keys[i]); + if (!static_key_enabled(&sched_feat_keys[i])) + static_key_slow_inc(&sched_feat_keys[i]); } #else static void sched_feat_disable(int i) { }; static void sched_feat_enable(int i) { }; #endif /* HAVE_JUMP_LABEL */ -static ssize_t -sched_feat_write(struct file *filp, const char __user *ubuf, - size_t cnt, loff_t *ppos) +static int sched_feat_set(char *cmp) { - char buf[64]; - char *cmp; - int neg = 0; int i; - - if (cnt > 63) - cnt = 63; - - if (copy_from_user(&buf, ubuf, cnt)) - return -EFAULT; - - buf[cnt] = 0; - cmp = strstrip(buf); + int neg = 0; if (strncmp(cmp, "NO_", 3) == 0) { neg = 1; @@ -226,6 +233,27 @@ sched_feat_write(struct file *filp, const char __user *ubuf, } } + return i; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp; + int i; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + cmp = strstrip(buf); + + i = sched_feat_set(cmp); if (i == __SCHED_FEAT_NR) return -EINVAL; @@ -285,8 +313,6 @@ __read_mostly int scheduler_running; */ int sysctl_sched_rt_runtime = 950000; - - /* * __task_rq_lock - lock the rq @p resides on. */ @@ -359,13 +385,6 @@ static struct rq *this_rq_lock(void) #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. - * - * Its all a bit involved since we cannot program an hrt while holding the - * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a - * reschedule event. - * - * When we get rescheduled we reprogram the hrtick_timer outside of the - * rq->lock. */ static void hrtick_clear(struct rq *rq) @@ -393,6 +412,15 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) } #ifdef CONFIG_SMP + +static int __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); +} + /* * called from hardirq (IPI) context */ @@ -401,7 +429,7 @@ static void __hrtick_start(void *arg) struct rq *rq = arg; raw_spin_lock(&rq->lock); - hrtimer_restart(&rq->hrtick_timer); + __hrtick_restart(rq); rq->hrtick_csd_pending = 0; raw_spin_unlock(&rq->lock); } @@ -419,9 +447,9 @@ void hrtick_start(struct rq *rq, u64 delay) hrtimer_set_expires(timer, time); if (rq == this_rq()) { - hrtimer_restart(timer); + __hrtick_restart(rq); } else if (!rq->hrtick_csd_pending) { - __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); + smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd); rq->hrtick_csd_pending = 1; } } @@ -494,37 +522,98 @@ static inline void init_hrtick(void) #endif /* CONFIG_SCHED_HRTICK */ /* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, val) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (val)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) + +#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} + +/* + * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set. + * + * If this returns true, then the idle task promises to call + * sched_ttwu_pending() and reschedule soon. + */ +static bool set_nr_if_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags); + + for (;;) { + if (!(val & _TIF_POLLING_NRFLAG)) + return false; + if (val & _TIF_NEED_RESCHED) + return true; + old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); + if (old == val) + break; + val = old; + } + return true; +} + +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} + +#ifdef CONFIG_SMP +static bool set_nr_if_polling(struct task_struct *p) +{ + return false; +} +#endif +#endif + +/* * resched_task - mark a task 'to be rescheduled now'. * * On UP this means the setting of the need_resched flag, on SMP it * might also involve a cross-CPU call to trigger the scheduler on * the target CPU. */ -#ifdef CONFIG_SMP - -#ifndef tsk_is_polling -#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) -#endif - void resched_task(struct task_struct *p) { int cpu; - assert_raw_spin_locked(&task_rq(p)->lock); + lockdep_assert_held(&task_rq(p)->lock); if (test_tsk_need_resched(p)) return; - set_tsk_need_resched(p); - cpu = task_cpu(p); - if (cpu == smp_processor_id()) + + if (cpu == smp_processor_id()) { + set_tsk_need_resched(p); + set_preempt_need_resched(); return; + } - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(p)) + if (set_nr_and_not_polling(p)) smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } void resched_cpu(int cpu) @@ -538,7 +627,8 @@ void resched_cpu(int cpu) raw_spin_unlock_irqrestore(&rq->lock, flags); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ_COMMON /* * In the semi idle case, use the nearest busy cpu for migrating timers * from an idle cpu. This is good for power-savings. @@ -547,12 +637,15 @@ 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(void) +int get_nohz_timer_target(int pinned) { int cpu = smp_processor_id(); int i; struct sched_domain *sd; + if (pinned || !get_sysctl_timer_migration() || !idle_cpu(cpu)) + return cpu; + rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu(i, sched_domain_span(sd)) { @@ -576,56 +669,87 @@ unlock: * account when the CPU goes back to idle and evaluates the timer * wheel for the next timer event. */ -void wake_up_idle_cpu(int cpu) +static void wake_up_idle_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); if (cpu == smp_processor_id()) return; - /* - * This is safe, as this function is called with the timer - * wheel base lock of (cpu) held. When the CPU is on the way - * to idle and has not yet set rq->curr to idle then it will - * be serialized on the timer wheel base lock and take the new - * timer into account automatically. - */ - if (rq->curr != rq->idle) - return; + if (set_nr_and_not_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); +} - /* - * We can set TIF_RESCHED on the idle task of the other CPU - * lockless. The worst case is that the other CPU runs the - * idle task through an additional NOOP schedule() - */ - set_tsk_need_resched(rq->idle); +static bool wake_up_full_nohz_cpu(int cpu) +{ + if (tick_nohz_full_cpu(cpu)) { + if (cpu != smp_processor_id() || + tick_nohz_tick_stopped()) + smp_send_reschedule(cpu); + return true; + } - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(rq->idle)) - smp_send_reschedule(cpu); + return false; +} + +void wake_up_nohz_cpu(int cpu) +{ + if (!wake_up_full_nohz_cpu(cpu)) + wake_up_idle_cpu(cpu); } static inline bool got_nohz_idle_kick(void) { int cpu = smp_processor_id(); - return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + + if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu))) + return false; + + if (idle_cpu(cpu) && !need_resched()) + return true; + + /* + * We can't run Idle Load Balance on this CPU for this time so we + * cancel it and clear NOHZ_BALANCE_KICK + */ + clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); + return false; } -#else /* CONFIG_NO_HZ */ +#else /* CONFIG_NO_HZ_COMMON */ static inline bool got_nohz_idle_kick(void) { return false; } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ + +#ifdef CONFIG_NO_HZ_FULL +bool sched_can_stop_tick(void) +{ + struct rq *rq; + + rq = this_rq(); + + /* Make sure rq->nr_running update is visible after the IPI */ + smp_rmb(); + + /* More than one running task need preemption */ + if (rq->nr_running > 1) + return false; + + return true; +} +#endif /* CONFIG_NO_HZ_FULL */ void sched_avg_update(struct rq *rq) { s64 period = sched_avg_period(); - while ((s64)(rq->clock - rq->age_stamp) > period) { + while ((s64)(rq_clock(rq) - rq->age_stamp) > period) { /* * Inline assembly required to prevent the compiler * optimising this loop into a divmod call. @@ -637,12 +761,6 @@ void sched_avg_update(struct rq *rq) } } -#else /* !CONFIG_SMP */ -void resched_task(struct task_struct *p) -{ - assert_raw_spin_locked(&task_rq(p)->lock); - set_tsk_need_resched(p); -} #endif /* CONFIG_SMP */ #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ @@ -690,8 +808,6 @@ int tg_nop(struct task_group *tg, void *data) } #endif -void update_cpu_load(struct rq *this_rq); - static void set_load_weight(struct task_struct *p) { int prio = p->static_prio - MAX_RT_PRIO; @@ -713,14 +829,14 @@ static void set_load_weight(struct task_struct *p) static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { update_rq_clock(rq); - sched_info_queued(p); + sched_info_queued(rq, p); p->sched_class->enqueue_task(rq, p, flags); } static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) { update_rq_clock(rq); - sched_info_dequeued(p); + sched_info_dequeued(rq, p); p->sched_class->dequeue_task(rq, p, flags); } @@ -740,126 +856,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -#ifdef CONFIG_IRQ_TIME_ACCOUNTING - -/* - * There are no locks covering percpu hardirq/softirq time. - * They are only modified in account_system_vtime, on corresponding CPU - * with interrupts disabled. So, writes are safe. - * They are read and saved off onto struct rq in update_rq_clock(). - * This may result in other CPU reading this CPU's irq time and can - * race with irq/account_system_vtime on this CPU. We would either get old - * or new value with a side effect of accounting a slice of irq time to wrong - * task when irq is in progress while we read rq->clock. That is a worthy - * compromise in place of having locks on each irq in account_system_time. - */ -static DEFINE_PER_CPU(u64, cpu_hardirq_time); -static DEFINE_PER_CPU(u64, cpu_softirq_time); - -static DEFINE_PER_CPU(u64, irq_start_time); -static int sched_clock_irqtime; - -void enable_sched_clock_irqtime(void) -{ - sched_clock_irqtime = 1; -} - -void disable_sched_clock_irqtime(void) -{ - sched_clock_irqtime = 0; -} - -#ifndef CONFIG_64BIT -static DEFINE_PER_CPU(seqcount_t, irq_time_seq); - -static inline void irq_time_write_begin(void) -{ - __this_cpu_inc(irq_time_seq.sequence); - smp_wmb(); -} - -static inline void irq_time_write_end(void) -{ - smp_wmb(); - __this_cpu_inc(irq_time_seq.sequence); -} - -static inline u64 irq_time_read(int cpu) -{ - u64 irq_time; - unsigned seq; - - do { - seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); - irq_time = per_cpu(cpu_softirq_time, cpu) + - per_cpu(cpu_hardirq_time, cpu); - } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); - - return irq_time; -} -#else /* CONFIG_64BIT */ -static inline void irq_time_write_begin(void) -{ -} - -static inline void irq_time_write_end(void) -{ -} - -static inline u64 irq_time_read(int cpu) -{ - return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); -} -#endif /* CONFIG_64BIT */ - -/* - * Called before incrementing preempt_count on {soft,}irq_enter - * and before decrementing preempt_count on {soft,}irq_exit. - */ -void account_system_vtime(struct task_struct *curr) -{ - unsigned long flags; - s64 delta; - int cpu; - - if (!sched_clock_irqtime) - return; - - local_irq_save(flags); - - cpu = smp_processor_id(); - delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); - __this_cpu_add(irq_start_time, delta); - - irq_time_write_begin(); - /* - * We do not account for softirq time from ksoftirqd here. - * We want to continue accounting softirq time to ksoftirqd thread - * in that case, so as not to confuse scheduler with a special task - * that do not consume any time, but still wants to run. - */ - if (hardirq_count()) - __this_cpu_add(cpu_hardirq_time, delta); - else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) - __this_cpu_add(cpu_softirq_time, delta); - - irq_time_write_end(); - local_irq_restore(flags); -} -EXPORT_SYMBOL_GPL(account_system_vtime); - -#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ - -#ifdef CONFIG_PARAVIRT -static inline u64 steal_ticks(u64 steal) -{ - if (unlikely(steal > NSEC_PER_SEC)) - return div_u64(steal, TICK_NSEC); - - return __iter_div_u64_rem(steal, TICK_NSEC, &steal); -} -#endif - static void update_rq_clock_task(struct rq *rq, s64 delta) { /* @@ -894,20 +890,14 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) delta -= irq_delta; #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING - if (static_branch((¶virt_steal_rq_enabled))) { - u64 st; - + if (static_key_false((¶virt_steal_rq_enabled))) { steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - st = steal_ticks(steal); - steal = st * TICK_NSEC; - rq->prev_steal_time_rq += steal; - delta -= steal; } #endif @@ -915,48 +905,11 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->clock_task += delta; #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - if ((irq_delta + steal) && sched_feat(NONTASK_POWER)) + if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) sched_rt_avg_update(rq, irq_delta + steal); #endif } -#ifdef CONFIG_IRQ_TIME_ACCOUNTING -static int irqtime_account_hi_update(void) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - unsigned long flags; - u64 latest_ns; - int ret = 0; - - local_irq_save(flags); - latest_ns = this_cpu_read(cpu_hardirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ]) - ret = 1; - local_irq_restore(flags); - return ret; -} - -static int irqtime_account_si_update(void) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - unsigned long flags; - u64 latest_ns; - int ret = 0; - - local_irq_save(flags); - latest_ns = this_cpu_read(cpu_softirq_time); - if (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ]) - ret = 1; - local_irq_restore(flags); - return ret; -} - -#else /* CONFIG_IRQ_TIME_ACCOUNTING */ - -#define sched_clock_irqtime (0) - -#endif - void sched_set_stop_task(int cpu, struct task_struct *stop) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -1006,7 +959,9 @@ static inline int normal_prio(struct task_struct *p) { int prio; - if (task_has_rt_policy(p)) + if (task_has_dl_policy(p)) + prio = MAX_DL_PRIO-1; + else if (task_has_rt_policy(p)) prio = MAX_RT_PRIO-1 - p->rt_priority; else prio = __normal_prio(p); @@ -1036,6 +991,8 @@ static int effective_prio(struct task_struct *p) /** * task_curr - is this task currently executing on a CPU? * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. */ inline int task_curr(const struct task_struct *p) { @@ -1050,7 +1007,7 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, if (prev_class->switched_from) prev_class->switched_from(rq, p); p->sched_class->switched_to(rq, p); - } else if (oldprio != p->prio) + } else if (oldprio != p->prio || dl_task(p)) p->sched_class->prio_changed(rq, p, oldprio); } @@ -1088,7 +1045,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) * ttwu() will sort out the placement. */ WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && - !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); + !(task_preempt_count(p) & PREEMPT_ACTIVE)); #ifdef CONFIG_LOCKDEP /* @@ -1096,7 +1053,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks. * * sched_move_task() holds both and thus holding either pins the cgroup, - * see set_task_rq(). + * see task_group(). * * Furthermore, all task_rq users should acquire both locks, see * task_rq_lock(). @@ -1109,6 +1066,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { + if (p->sched_class->migrate_task_rq) + p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, NULL, 0); } @@ -1116,6 +1075,108 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) __set_task_cpu(p, new_cpu); } +static void __migrate_swap_task(struct task_struct *p, int cpu) +{ + if (p->on_rq) { + struct rq *src_rq, *dst_rq; + + src_rq = task_rq(p); + dst_rq = cpu_rq(cpu); + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, cpu); + activate_task(dst_rq, p, 0); + check_preempt_curr(dst_rq, p, 0); + } else { + /* + * Task isn't running anymore; make it appear like we migrated + * it before it went to sleep. This means on wakeup we make the + * previous cpu our targer instead of where it really is. + */ + p->wake_cpu = cpu; + } +} + +struct migration_swap_arg { + struct task_struct *src_task, *dst_task; + int src_cpu, dst_cpu; +}; + +static int migrate_swap_stop(void *data) +{ + struct migration_swap_arg *arg = data; + struct rq *src_rq, *dst_rq; + int ret = -EAGAIN; + + src_rq = cpu_rq(arg->src_cpu); + dst_rq = cpu_rq(arg->dst_cpu); + + double_raw_lock(&arg->src_task->pi_lock, + &arg->dst_task->pi_lock); + double_rq_lock(src_rq, dst_rq); + if (task_cpu(arg->dst_task) != arg->dst_cpu) + goto unlock; + + if (task_cpu(arg->src_task) != arg->src_cpu) + goto unlock; + + if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task))) + goto unlock; + + if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task))) + goto unlock; + + __migrate_swap_task(arg->src_task, arg->dst_cpu); + __migrate_swap_task(arg->dst_task, arg->src_cpu); + + ret = 0; + +unlock: + double_rq_unlock(src_rq, dst_rq); + raw_spin_unlock(&arg->dst_task->pi_lock); + raw_spin_unlock(&arg->src_task->pi_lock); + + return ret; +} + +/* + * Cross migrate two tasks + */ +int migrate_swap(struct task_struct *cur, struct task_struct *p) +{ + struct migration_swap_arg arg; + int ret = -EINVAL; + + arg = (struct migration_swap_arg){ + .src_task = cur, + .src_cpu = task_cpu(cur), + .dst_task = p, + .dst_cpu = task_cpu(p), + }; + + if (arg.src_cpu == arg.dst_cpu) + goto out; + + /* + * These three tests are all lockless; this is OK since all of them + * will be re-checked with proper locks held further down the line. + */ + if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) + goto out; + + if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task))) + goto out; + + if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task))) + goto out; + + trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); + ret = stop_two_cpus(arg.dst_cpu, arg.src_cpu, migrate_swap_stop, &arg); + +out: + return ret; +} + struct migration_arg { struct task_struct *task; int dest_cpu; @@ -1263,29 +1324,69 @@ EXPORT_SYMBOL_GPL(kick_process); */ static int select_fallback_rq(int cpu, struct task_struct *p) { + int nid = cpu_to_node(cpu); + const struct cpumask *nodemask = NULL; + enum { cpuset, possible, fail } state = cpuset; int dest_cpu; - const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); - - /* Look for allowed, online CPU in same node. */ - for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) - if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) - return dest_cpu; - /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(tsk_cpus_allowed(p), cpu_active_mask); - if (dest_cpu < nr_cpu_ids) - return dest_cpu; - - /* No more Mr. Nice Guy. */ - dest_cpu = cpuset_cpus_allowed_fallback(p); /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. + * If the node that the cpu is on has been offlined, cpu_to_node() + * will return -1. There is no cpu on the node, and we should + * select the cpu on the other node. */ - if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", - task_pid_nr(p), p->comm, cpu); + if (nid != -1) { + nodemask = cpumask_of_node(nid); + + /* Look for allowed, online CPU in same node. */ + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + return dest_cpu; + } + } + + for (;;) { + /* Any allowed, online CPU? */ + for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { + if (!cpu_online(dest_cpu)) + continue; + if (!cpu_active(dest_cpu)) + continue; + goto out; + } + + switch (state) { + case cpuset: + /* No more Mr. Nice Guy. */ + cpuset_cpus_allowed_fallback(p); + state = possible; + break; + + case possible: + do_set_cpus_allowed(p, cpu_possible_mask); + state = fail; + break; + + case fail: + BUG(); + break; + } + } + +out: + if (state != cpuset) { + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk_deferred("process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } } return dest_cpu; @@ -1295,9 +1396,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) +int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) { - int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); + cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); /* * In order not to call set_task_cpu() on a blocking task we need @@ -1379,8 +1480,8 @@ static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { - trace_sched_wakeup(p, true); check_preempt_curr(rq, p, wake_flags); + trace_sched_wakeup(p, true); p->state = TASK_RUNNING; #ifdef CONFIG_SMP @@ -1388,13 +1489,14 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) p->sched_class->task_woken(rq, p); if (rq->idle_stamp) { - u64 delta = rq->clock - rq->idle_stamp; - u64 max = 2*sysctl_sched_migration_cost; + u64 delta = rq_clock(rq) - rq->idle_stamp; + u64 max = 2*rq->max_idle_balance_cost; - if (delta > max) + update_avg(&rq->avg_idle, delta); + + if (rq->avg_idle > max) rq->avg_idle = max; - else - update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; } #endif @@ -1425,6 +1527,8 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) rq = __task_rq_lock(p); if (p->on_rq) { + /* check_preempt_curr() may use rq clock */ + update_rq_clock(rq); ttwu_do_wakeup(rq, p, wake_flags); ret = 1; } @@ -1434,13 +1538,17 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) } #ifdef CONFIG_SMP -static void sched_ttwu_pending(void) +void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); struct task_struct *p; + unsigned long flags; - raw_spin_lock(&rq->lock); + if (!llist) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); while (llist) { p = llist_entry(llist, struct task_struct, wake_entry); @@ -1448,12 +1556,21 @@ static void sched_ttwu_pending(void) ttwu_do_activate(rq, p, 0); } - raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&rq->lock, flags); } void scheduler_ipi(void) { - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); + + if (llist_empty(&this_rq()->wake_list) + && !tick_nohz_full_cpu(smp_processor_id()) + && !got_nohz_idle_kick()) return; /* @@ -1470,12 +1587,13 @@ void scheduler_ipi(void) * somewhat pessimize the simple resched case. */ irq_enter(); + tick_nohz_full_check(); sched_ttwu_pending(); /* * Check if someone kicked us for doing the nohz idle load balance. */ - if (unlikely(got_nohz_idle_kick() && !need_resched())) { + if (unlikely(got_nohz_idle_kick())) { this_rq()->idle_balance = 1; raise_softirq_irqoff(SCHED_SOFTIRQ); } @@ -1484,30 +1602,17 @@ void scheduler_ipi(void) static void ttwu_queue_remote(struct task_struct *p, int cpu) { - if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) - smp_send_reschedule(cpu); -} - -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW -static int ttwu_activate_remote(struct task_struct *p, int wake_flags) -{ - struct rq *rq; - int ret = 0; + struct rq *rq = cpu_rq(cpu); - rq = __task_rq_lock(p); - if (p->on_cpu) { - ttwu_activate(rq, p, ENQUEUE_WAKEUP); - ttwu_do_wakeup(rq, p, wake_flags); - ret = 1; + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { + if (!set_nr_if_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } - __task_rq_unlock(rq); - - return ret; - } -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ -static inline int ttwu_share_cache(int this_cpu, int that_cpu) +bool cpus_share_cache(int this_cpu, int that_cpu) { return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } @@ -1518,7 +1623,7 @@ static void ttwu_queue(struct task_struct *p, int cpu) struct rq *rq = cpu_rq(cpu); #if defined(CONFIG_SMP) - if (sched_feat(TTWU_QUEUE) && !ttwu_share_cache(smp_processor_id(), cpu)) { + if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { sched_clock_cpu(cpu); /* sync clocks x-cpu */ ttwu_queue_remote(p, cpu); return; @@ -1542,7 +1647,7 @@ static void ttwu_queue(struct task_struct *p, int cpu) * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * Returns %true if @p was woken up, %false if it was already running + * Return: %true if @p was woken up, %false if it was already running. * or @state didn't match @p's state. */ static int @@ -1551,7 +1656,13 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) unsigned long flags; int cpu, success = 0; - smp_wmb(); + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + smp_mb__before_spinlock(); raw_spin_lock_irqsave(&p->pi_lock, flags); if (!(p->state & state)) goto out; @@ -1567,21 +1678,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * If the owning (remote) cpu is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. */ - while (p->on_cpu) { -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - /* - * In case the architecture enables interrupts in - * context_switch(), we cannot busy wait, since that - * would lead to deadlocks when an interrupt hits and - * tries to wake up @prev. So bail and do a complete - * remote wakeup. - */ - if (ttwu_activate_remote(p, wake_flags)) - goto stat; -#else + while (p->on_cpu) cpu_relax(); -#endif - } /* * Pairs with the smp_wmb() in finish_lock_switch(). */ @@ -1593,7 +1691,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) if (p->sched_class->task_waking) p->sched_class->task_waking(p); - cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); + cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; set_task_cpu(p, cpu); @@ -1621,8 +1719,10 @@ static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - BUG_ON(rq != this_rq()); - BUG_ON(p == current); + if (WARN_ON_ONCE(rq != this_rq()) || + WARN_ON_ONCE(p == current)) + return; + lockdep_assert_held(&rq->lock); if (!raw_spin_trylock(&p->pi_lock)) { @@ -1648,15 +1748,17 @@ out: * @p: The process to be woken up. * * Attempt to wake up the nominated process and move it to the set of runnable - * processes. Returns 1 if the process was woken up, 0 if it was already - * running. + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. * * It may be assumed that this function implies a write memory barrier before * changing the task state if and only if any tasks are woken up. */ int wake_up_process(struct task_struct *p) { - return try_to_wake_up(p, TASK_ALL, 0); + WARN_ON(task_is_stopped_or_traced(p)); + return try_to_wake_up(p, TASK_NORMAL, 0); } EXPORT_SYMBOL(wake_up_process); @@ -1671,7 +1773,7 @@ int wake_up_state(struct task_struct *p, unsigned int state) * * __sched_fork() is basic setup used by init_idle() too: */ -static void __sched_fork(struct task_struct *p) +static void __sched_fork(unsigned long clone_flags, struct task_struct *p) { p->on_rq = 0; @@ -1687,22 +1789,94 @@ static void __sched_fork(struct task_struct *p) memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif + RB_CLEAR_NODE(&p->dl.rb_node); + hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + p->dl.dl_runtime = p->dl.runtime = 0; + p->dl.dl_deadline = p->dl.deadline = 0; + p->dl.dl_period = 0; + p->dl.flags = 0; + INIT_LIST_HEAD(&p->rt.run_list); #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); #endif + +#ifdef CONFIG_NUMA_BALANCING + if (p->mm && atomic_read(&p->mm->mm_users) == 1) { + p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + p->mm->numa_scan_seq = 0; + } + + if (clone_flags & CLONE_VM) + p->numa_preferred_nid = current->numa_preferred_nid; + else + p->numa_preferred_nid = -1; + + p->node_stamp = 0ULL; + p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; + p->numa_work.next = &p->numa_work; + p->numa_faults_memory = NULL; + p->numa_faults_buffer_memory = NULL; + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; + + INIT_LIST_HEAD(&p->numa_entry); + p->numa_group = NULL; +#endif /* CONFIG_NUMA_BALANCING */ +} + +#ifdef CONFIG_NUMA_BALANCING +#ifdef CONFIG_SCHED_DEBUG +void set_numabalancing_state(bool enabled) +{ + if (enabled) + sched_feat_set("NUMA"); + else + sched_feat_set("NO_NUMA"); +} +#else +__read_mostly bool numabalancing_enabled; + +void set_numabalancing_state(bool enabled) +{ + numabalancing_enabled = enabled; } +#endif /* CONFIG_SCHED_DEBUG */ + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_numa_balancing(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = numabalancing_enabled; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_numabalancing_state(state); + return err; +} +#endif +#endif /* * fork()/clone()-time setup: */ -void sched_fork(struct task_struct *p) +int sched_fork(unsigned long clone_flags, struct task_struct *p) { unsigned long flags; int cpu = get_cpu(); - __sched_fork(p); + __sched_fork(clone_flags, p); /* * We mark the process as running here. This guarantees that * nobody will actually run it, and a signal or other external @@ -1719,7 +1893,7 @@ void sched_fork(struct task_struct *p) * Revert to default priority/policy on fork if requested. */ if (unlikely(p->sched_reset_on_fork)) { - if (task_has_rt_policy(p)) { + if (task_has_dl_policy(p) || task_has_rt_policy(p)) { p->policy = SCHED_NORMAL; p->static_prio = NICE_TO_PRIO(0); p->rt_priority = 0; @@ -1736,8 +1910,14 @@ void sched_fork(struct task_struct *p) p->sched_reset_on_fork = 0; } - if (!rt_prio(p->prio)) + if (dl_prio(p->prio)) { + put_cpu(); + return -EAGAIN; + } else if (rt_prio(p->prio)) { + p->sched_class = &rt_sched_class; + } else { p->sched_class = &fair_sched_class; + } if (p->sched_class->task_fork) p->sched_class->task_fork(p); @@ -1760,18 +1940,128 @@ void sched_fork(struct task_struct *p) #if defined(CONFIG_SMP) p->on_cpu = 0; #endif -#ifdef CONFIG_PREEMPT_COUNT - /* Want to start with kernel preemption disabled. */ - task_thread_info(p)->preempt_count = 1; -#endif + init_task_preempt_count(p); #ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); #endif put_cpu(); + return 0; +} + +unsigned long to_ratio(u64 period, u64 runtime) +{ + if (runtime == RUNTIME_INF) + return 1ULL << 20; + + /* + * Doing this here saves a lot of checks in all + * the calling paths, and returning zero seems + * safe for them anyway. + */ + if (period == 0) + return 0; + + return div64_u64(runtime << 20, period); +} + +#ifdef CONFIG_SMP +inline struct dl_bw *dl_bw_of(int i) +{ + return &cpu_rq(i)->rd->dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + struct root_domain *rd = cpu_rq(i)->rd; + int cpus = 0; + + for_each_cpu_and(i, rd->span, cpu_active_mask) + cpus++; + + return cpus; +} +#else +inline struct dl_bw *dl_bw_of(int i) +{ + return &cpu_rq(i)->dl.dl_bw; +} + +static inline int dl_bw_cpus(int i) +{ + return 1; +} +#endif + +static inline +void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw) +{ + dl_b->total_bw -= tsk_bw; +} + +static inline +void __dl_add(struct dl_bw *dl_b, u64 tsk_bw) +{ + dl_b->total_bw += tsk_bw; +} + +static inline +bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) +{ + return dl_b->bw != -1 && + dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; } /* + * We must be sure that accepting a new task (or allowing changing the + * parameters of an existing one) is consistent with the bandwidth + * constraints. If yes, this function also accordingly updates the currently + * allocated bandwidth to reflect the new situation. + * + * This function is called while holding p's rq->lock. + */ +static int dl_overflow(struct task_struct *p, int policy, + const struct sched_attr *attr) +{ + + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + u64 period = attr->sched_period ?: attr->sched_deadline; + u64 runtime = attr->sched_runtime; + u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0; + int cpus, err = -1; + + if (new_bw == p->dl.dl_bw) + return 0; + + /* + * Either if a task, enters, leave, or stays -deadline but changes + * its parameters, we may need to update accordingly the total + * allocated bandwidth of the container. + */ + raw_spin_lock(&dl_b->lock); + cpus = dl_bw_cpus(task_cpu(p)); + if (dl_policy(policy) && !task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, 0, new_bw)) { + __dl_add(dl_b, new_bw); + err = 0; + } else if (dl_policy(policy) && task_has_dl_policy(p) && + !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) { + __dl_clear(dl_b, p->dl.dl_bw); + __dl_add(dl_b, new_bw); + err = 0; + } else if (!dl_policy(policy) && task_has_dl_policy(p)) { + __dl_clear(dl_b, p->dl.dl_bw); + err = 0; + } + raw_spin_unlock(&dl_b->lock); + + return err; +} + +extern void init_dl_bw(struct dl_bw *dl_b); + +/* * wake_up_new_task - wake up a newly created task for the first time. * * This function will do some initial scheduler statistics housekeeping @@ -1790,9 +2080,11 @@ void wake_up_new_task(struct task_struct *p) * - cpus_allowed can change in the fork path * - any previously selected cpu might disappear through hotplug */ - set_task_cpu(p, select_task_rq(p, SD_BALANCE_FORK, 0)); + set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif + /* Initialize new task's runnable average */ + init_task_runnable_average(p); rq = __task_rq_lock(p); activate_task(rq, p, 0); p->on_rq = 1; @@ -1832,9 +2124,8 @@ EXPORT_SYMBOL_GPL(preempt_notifier_unregister); static void fire_sched_in_preempt_notifiers(struct task_struct *curr) { struct preempt_notifier *notifier; - struct hlist_node *node; - hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) notifier->ops->sched_in(notifier, raw_smp_processor_id()); } @@ -1843,9 +2134,8 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, struct task_struct *next) { struct preempt_notifier *notifier; - struct hlist_node *node; - hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) notifier->ops->sched_out(notifier, next); } @@ -1880,12 +2170,12 @@ static inline void prepare_task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { - sched_info_switch(prev, next); + trace_sched_switch(prev, next); + sched_info_switch(rq, prev, next); perf_event_task_sched_out(prev, next); fire_sched_out_preempt_notifiers(prev, next); prepare_lock_switch(rq, next); prepare_arch_switch(next); - trace_sched_switch(prev, next); } /** @@ -1923,21 +2213,19 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) * Manfred Spraul <manfred@colorfullife.com> */ prev_state = prev->state; + vtime_task_switch(prev); finish_arch_switch(prev); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_disable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ perf_event_task_sched_in(prev, current); -#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - local_irq_enable(); -#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ finish_lock_switch(rq, prev); - trace_sched_stat_sleeptime(current, rq->clock); + finish_arch_post_lock_switch(); fire_sched_in_preempt_notifiers(current); if (mm) mmdrop(mm); if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); + /* * Remove function-return probe instances associated with this * task and put them back on the free list. @@ -1945,17 +2233,12 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) kprobe_flush_task(prev); put_task_struct(prev); } + + tick_nohz_task_switch(current); } #ifdef CONFIG_SMP -/* assumes rq->lock is held */ -static inline void pre_schedule(struct rq *rq, struct task_struct *prev) -{ - if (prev->sched_class->pre_schedule) - prev->sched_class->pre_schedule(rq, prev); -} - /* rq->lock is NOT held, but preemption is disabled */ static inline void post_schedule(struct rq *rq) { @@ -1973,10 +2256,6 @@ static inline void post_schedule(struct rq *rq) #else -static inline void pre_schedule(struct rq *rq, struct task_struct *p) -{ -} - static inline void post_schedule(struct rq *rq) { } @@ -1987,7 +2266,7 @@ static inline void post_schedule(struct rq *rq) * schedule_tail - first thing a freshly forked thread must call. * @prev: the thread we just switched away from. */ -asmlinkage void schedule_tail(struct task_struct *prev) +asmlinkage __visible void schedule_tail(struct task_struct *prev) __releases(rq->lock) { struct rq *rq = this_rq(); @@ -2050,6 +2329,7 @@ context_switch(struct rq *rq, struct task_struct *prev, spin_release(&rq->lock.dep_map, 1, _THIS_IP_); #endif + context_tracking_task_switch(prev, next); /* Here we just switch the register state and the stack. */ switch_to(prev, next, prev); @@ -2063,11 +2343,10 @@ context_switch(struct rq *rq, struct task_struct *prev, } /* - * nr_running, nr_uninterruptible and nr_context_switches: + * nr_running and nr_context_switches: * * externally visible scheduler statistics: current number of runnable - * threads, current number of uninterruptible-sleeping threads, total - * number of context switches performed since bootup. + * threads, total number of context switches performed since bootup. */ unsigned long nr_running(void) { @@ -2079,23 +2358,6 @@ unsigned long nr_running(void) return sum; } -unsigned long nr_uninterruptible(void) -{ - unsigned long i, sum = 0; - - for_each_possible_cpu(i) - sum += cpu_rq(i)->nr_uninterruptible; - - /* - * Since we read the counters lockless, it might be slightly - * inaccurate. Do not allow it to go below zero though: - */ - if (unlikely((long)sum < 0)) - sum = 0; - - return sum; -} - unsigned long long nr_context_switches(void) { int i; @@ -2123,385 +2385,6 @@ unsigned long nr_iowait_cpu(int cpu) return atomic_read(&this->nr_iowait); } -unsigned long this_cpu_load(void) -{ - struct rq *this = this_rq(); - return this->cpu_load[0]; -} - - -/* Variables and functions for calc_load */ -static atomic_long_t calc_load_tasks; -static unsigned long calc_load_update; -unsigned long avenrun[3]; -EXPORT_SYMBOL(avenrun); - -static long calc_load_fold_active(struct rq *this_rq) -{ - long nr_active, delta = 0; - - nr_active = this_rq->nr_running; - nr_active += (long) this_rq->nr_uninterruptible; - - if (nr_active != this_rq->calc_load_active) { - delta = nr_active - this_rq->calc_load_active; - this_rq->calc_load_active = nr_active; - } - - return delta; -} - -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) -{ - load *= exp; - load += active * (FIXED_1 - exp); - load += 1UL << (FSHIFT - 1); - return load >> FSHIFT; -} - -#ifdef CONFIG_NO_HZ -/* - * For NO_HZ we delay the active fold to the next LOAD_FREQ update. - * - * When making the ILB scale, we should try to pull this in as well. - */ -static atomic_long_t calc_load_tasks_idle; - -void calc_load_account_idle(struct rq *this_rq) -{ - long delta; - - delta = calc_load_fold_active(this_rq); - if (delta) - atomic_long_add(delta, &calc_load_tasks_idle); -} - -static long calc_load_fold_idle(void) -{ - long delta = 0; - - /* - * Its got a race, we don't care... - */ - if (atomic_long_read(&calc_load_tasks_idle)) - delta = atomic_long_xchg(&calc_load_tasks_idle, 0); - - return delta; -} - -/** - * fixed_power_int - compute: x^n, in O(log n) time - * - * @x: base of the power - * @frac_bits: fractional bits of @x - * @n: power to raise @x to. - * - * By exploiting the relation between the definition of the natural power - * function: x^n := x*x*...*x (x multiplied by itself for n times), and - * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, - * (where: n_i \elem {0, 1}, the binary vector representing n), - * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is - * of course trivially computable in O(log_2 n), the length of our binary - * vector. - */ -static unsigned long -fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) -{ - unsigned long result = 1UL << frac_bits; - - if (n) for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; - } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; - } - - return result; -} - -/* - * a1 = a0 * e + a * (1 - e) - * - * a2 = a1 * e + a * (1 - e) - * = (a0 * e + a * (1 - e)) * e + a * (1 - e) - * = a0 * e^2 + a * (1 - e) * (1 + e) - * - * a3 = a2 * e + a * (1 - e) - * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) - * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) - * - * ... - * - * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] - * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) - * = a0 * e^n + a * (1 - e^n) - * - * [1] application of the geometric series: - * - * n 1 - x^(n+1) - * S_n := \Sum x^i = ------------- - * i=0 1 - x - */ -static unsigned long -calc_load_n(unsigned long load, unsigned long exp, - unsigned long active, unsigned int n) -{ - - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); -} - -/* - * NO_HZ can leave us missing all per-cpu ticks calling - * calc_load_account_active(), but since an idle CPU folds its delta into - * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold - * in the pending idle delta if our idle period crossed a load cycle boundary. - * - * Once we've updated the global active value, we need to apply the exponential - * weights adjusted to the number of cycles missed. - */ -static void calc_global_nohz(unsigned long ticks) -{ - long delta, active, n; - - if (time_before(jiffies, calc_load_update)) - return; - - /* - * If we crossed a calc_load_update boundary, make sure to fold - * any pending idle changes, the respective CPUs might have - * missed the tick driven calc_load_account_active() update - * due to NO_HZ. - */ - delta = calc_load_fold_idle(); - if (delta) - atomic_long_add(delta, &calc_load_tasks); - - /* - * If we were idle for multiple load cycles, apply them. - */ - if (ticks >= LOAD_FREQ) { - n = ticks / LOAD_FREQ; - - active = atomic_long_read(&calc_load_tasks); - active = active > 0 ? active * FIXED_1 : 0; - - avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); - avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); - avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - - calc_load_update += n * LOAD_FREQ; - } - - /* - * Its possible the remainder of the above division also crosses - * a LOAD_FREQ period, the regular check in calc_global_load() - * which comes after this will take care of that. - * - * Consider us being 11 ticks before a cycle completion, and us - * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will - * age us 4 cycles, and the test in calc_global_load() will - * pick up the final one. - */ -} -#else -void calc_load_account_idle(struct rq *this_rq) -{ -} - -static inline long calc_load_fold_idle(void) -{ - return 0; -} - -static void calc_global_nohz(unsigned long ticks) -{ -} -#endif - -/** - * get_avenrun - get the load average array - * @loads: pointer to dest load array - * @offset: offset to add - * @shift: shift count to shift the result left - * - * These values are estimates at best, so no need for locking. - */ -void get_avenrun(unsigned long *loads, unsigned long offset, int shift) -{ - loads[0] = (avenrun[0] + offset) << shift; - loads[1] = (avenrun[1] + offset) << shift; - loads[2] = (avenrun[2] + offset) << shift; -} - -/* - * calc_load - update the avenrun load estimates 10 ticks after the - * CPUs have updated calc_load_tasks. - */ -void calc_global_load(unsigned long ticks) -{ - long active; - - calc_global_nohz(ticks); - - if (time_before(jiffies, calc_load_update + 10)) - return; - - active = atomic_long_read(&calc_load_tasks); - active = active > 0 ? active * FIXED_1 : 0; - - avenrun[0] = calc_load(avenrun[0], EXP_1, active); - avenrun[1] = calc_load(avenrun[1], EXP_5, active); - avenrun[2] = calc_load(avenrun[2], EXP_15, active); - - calc_load_update += LOAD_FREQ; -} - -/* - * Called from update_cpu_load() to periodically update this CPU's - * active count. - */ -static void calc_load_account_active(struct rq *this_rq) -{ - long delta; - - if (time_before(jiffies, this_rq->calc_load_update)) - return; - - delta = calc_load_fold_active(this_rq); - delta += calc_load_fold_idle(); - if (delta) - atomic_long_add(delta, &calc_load_tasks); - - this_rq->calc_load_update += LOAD_FREQ; -} - -/* - * The exact cpuload at various idx values, calculated at every tick would be - * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load - * - * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called - * on nth tick when cpu may be busy, then we have: - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load - * - * decay_load_missed() below does efficient calculation of - * load = ((2^idx - 1) / 2^idx)^(n-1) * load - * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load - * - * The calculation is approximated on a 128 point scale. - * degrade_zero_ticks is the number of ticks after which load at any - * particular idx is approximated to be zero. - * degrade_factor is a precomputed table, a row for each load idx. - * Each column corresponds to degradation factor for a power of two ticks, - * based on 128 point scale. - * Example: - * row 2, col 3 (=12) says that the degradation at load idx 2 after - * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). - * - * With this power of 2 load factors, we can degrade the load n times - * by looking at 1 bits in n and doing as many mult/shift instead of - * n mult/shifts needed by the exact degradation. - */ -#define DEGRADE_SHIFT 7 -static const unsigned char - degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; -static const unsigned char - degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { - {0, 0, 0, 0, 0, 0, 0, 0}, - {64, 32, 8, 0, 0, 0, 0, 0}, - {96, 72, 40, 12, 1, 0, 0}, - {112, 98, 75, 43, 15, 1, 0}, - {120, 112, 98, 76, 45, 16, 2} }; - -/* - * Update cpu_load for any missed ticks, due to tickless idle. The backlog - * would be when CPU is idle and so we just decay the old load without - * adding any new load. - */ -static unsigned long -decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) -{ - int j = 0; - - if (!missed_updates) - return load; - - if (missed_updates >= degrade_zero_ticks[idx]) - return 0; - - if (idx == 1) - return load >> missed_updates; - - while (missed_updates) { - if (missed_updates % 2) - load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; - - missed_updates >>= 1; - j++; - } - return load; -} - -/* - * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). With tickless idle this will not be called - * every tick. We fix it up based on jiffies. - */ -void update_cpu_load(struct rq *this_rq) -{ - unsigned long this_load = this_rq->load.weight; - unsigned long curr_jiffies = jiffies; - unsigned long pending_updates; - int i, scale; - - this_rq->nr_load_updates++; - - /* Avoid repeated calls on same jiffy, when moving in and out of idle */ - if (curr_jiffies == this_rq->last_load_update_tick) - return; - - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - this_rq->last_load_update_tick = curr_jiffies; - - /* Update our load: */ - this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ - for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { - unsigned long old_load, new_load; - - /* scale is effectively 1 << i now, and >> i divides by scale */ - - old_load = this_rq->cpu_load[i]; - old_load = decay_load_missed(old_load, pending_updates - 1, i); - new_load = this_load; - /* - * Round up the averaging division if load is increasing. This - * prevents us from getting stuck on 9 if the load is 10, for - * example. - */ - if (new_load > old_load) - new_load += scale - 1; - - this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; - } - - sched_avg_update(this_rq); -} - -static void update_cpu_load_active(struct rq *this_rq) -{ - update_cpu_load(this_rq); - - calc_load_account_active(this_rq); -} - #ifdef CONFIG_SMP /* @@ -2515,7 +2398,7 @@ void sched_exec(void) int dest_cpu; raw_spin_lock_irqsave(&p->pi_lock, flags); - dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); + dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0); if (dest_cpu == smp_processor_id()) goto unlock; @@ -2550,7 +2433,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) if (task_current(rq, p)) { update_rq_clock(rq); - ns = rq->clock_task - p->se.exec_start; + ns = rq_clock_task(rq) - p->se.exec_start; if ((s64)ns < 0) ns = 0; } @@ -2582,404 +2465,26 @@ unsigned long long task_sched_runtime(struct task_struct *p) struct rq *rq; u64 ns = 0; - rq = task_rq_lock(p, &flags); - ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); - task_rq_unlock(rq, p, &flags); - - return ns; -} - -#ifdef CONFIG_CGROUP_CPUACCT -struct cgroup_subsys cpuacct_subsys; -struct cpuacct root_cpuacct; -#endif - -static inline void task_group_account_field(struct task_struct *p, int index, - u64 tmp) -{ -#ifdef CONFIG_CGROUP_CPUACCT - struct kernel_cpustat *kcpustat; - struct cpuacct *ca; -#endif +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) /* - * Since all updates are sure to touch the root cgroup, we - * get ourselves ahead and touch it first. If the root cgroup - * is the only cgroup, then nothing else should be necessary. + * 64-bit doesn't need locks to atomically read a 64bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. * + * If we race with it leaving cpu, we'll take a lock. So we're correct. + * If we race with it entering cpu, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. */ - __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; - -#ifdef CONFIG_CGROUP_CPUACCT - if (unlikely(!cpuacct_subsys.active)) - return; - - rcu_read_lock(); - ca = task_ca(p); - while (ca && (ca != &root_cpuacct)) { - kcpustat = this_cpu_ptr(ca->cpustat); - kcpustat->cpustat[index] += tmp; - ca = parent_ca(ca); - } - rcu_read_unlock(); + if (!p->on_cpu) + return p->se.sum_exec_runtime; #endif -} - - -/* - * Account user cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in user space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_user_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - int index; - - /* Add user time to process. */ - p->utime += cputime; - p->utimescaled += cputime_scaled; - account_group_user_time(p, cputime); - - index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; - - /* Add user time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); - - /* Account for user time used */ - acct_update_integrals(p); -} - -/* - * Account guest cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in virtual machine since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -static void account_guest_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - - /* Add guest time to process. */ - p->utime += cputime; - p->utimescaled += cputime_scaled; - account_group_user_time(p, cputime); - p->gtime += cputime; - - /* Add guest time to cpustat. */ - if (TASK_NICE(p) > 0) { - cpustat[CPUTIME_NICE] += (__force u64) cputime; - cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; - } else { - cpustat[CPUTIME_USER] += (__force u64) cputime; - cpustat[CPUTIME_GUEST] += (__force u64) cputime; - } -} - -/* - * Account system cpu time to a process and desired cpustat field - * @p: the process that the cpu time gets accounted to - * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - * @target_cputime64: pointer to cpustat field that has to be updated - */ -static inline -void __account_system_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled, int index) -{ - /* Add system time to process. */ - p->stime += cputime; - p->stimescaled += cputime_scaled; - account_group_system_time(p, cputime); - - /* Add system time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); - - /* Account for system time used */ - acct_update_integrals(p); -} - -/* - * Account system cpu time to a process. - * @p: the process that the cpu time gets accounted to - * @hardirq_offset: the offset to subtract from hardirq_count() - * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - */ -void account_system_time(struct task_struct *p, int hardirq_offset, - cputime_t cputime, cputime_t cputime_scaled) -{ - int index; - - if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { - account_guest_time(p, cputime, cputime_scaled); - return; - } - - if (hardirq_count() - hardirq_offset) - index = CPUTIME_IRQ; - else if (in_serving_softirq()) - index = CPUTIME_SOFTIRQ; - else - index = CPUTIME_SYSTEM; - - __account_system_time(p, cputime, cputime_scaled, index); -} - -/* - * Account for involuntary wait time. - * @cputime: the cpu time spent in involuntary wait - */ -void account_steal_time(cputime_t cputime) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - - cpustat[CPUTIME_STEAL] += (__force u64) cputime; -} - -/* - * Account for idle time. - * @cputime: the cpu time spent in idle wait - */ -void account_idle_time(cputime_t cputime) -{ - u64 *cpustat = kcpustat_this_cpu->cpustat; - struct rq *rq = this_rq(); - - if (atomic_read(&rq->nr_iowait) > 0) - cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; - else - cpustat[CPUTIME_IDLE] += (__force u64) cputime; -} - -static __always_inline bool steal_account_process_tick(void) -{ -#ifdef CONFIG_PARAVIRT - if (static_branch(¶virt_steal_enabled)) { - u64 steal, st = 0; - - steal = paravirt_steal_clock(smp_processor_id()); - steal -= this_rq()->prev_steal_time; - - st = steal_ticks(steal); - this_rq()->prev_steal_time += st * TICK_NSEC; - - account_steal_time(st); - return st; - } -#endif - return false; -} - -#ifndef CONFIG_VIRT_CPU_ACCOUNTING - -#ifdef CONFIG_IRQ_TIME_ACCOUNTING -/* - * Account a tick to a process and cpustat - * @p: the process that the cpu time gets accounted to - * @user_tick: is the tick from userspace - * @rq: the pointer to rq - * - * Tick demultiplexing follows the order - * - pending hardirq update - * - pending softirq update - * - user_time - * - idle_time - * - system time - * - check for guest_time - * - else account as system_time - * - * Check for hardirq is done both for system and user time as there is - * no timer going off while we are on hardirq and hence we may never get an - * opportunity to update it solely in system time. - * p->stime and friends are only updated on system time and not on irq - * softirq as those do not count in task exec_runtime any more. - */ -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) -{ - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - u64 *cpustat = kcpustat_this_cpu->cpustat; - - if (steal_account_process_tick()) - return; - - if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; - } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; - } else if (this_cpu_ksoftirqd() == p) { - /* - * ksoftirqd time do not get accounted in cpu_softirq_time. - * So, we have to handle it separately here. - * Also, p->stime needs to be updated for ksoftirqd. - */ - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SOFTIRQ); - } else if (user_tick) { - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); - } else if (p == rq->idle) { - account_idle_time(cputime_one_jiffy); - } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); - } else { - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SYSTEM); - } -} - -static void irqtime_account_idle_ticks(int ticks) -{ - int i; - struct rq *rq = this_rq(); - - for (i = 0; i < ticks; i++) - irqtime_account_process_tick(current, 0, rq); -} -#else /* CONFIG_IRQ_TIME_ACCOUNTING */ -static void irqtime_account_idle_ticks(int ticks) {} -static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) {} -#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ - -/* - * Account a single tick of cpu time. - * @p: the process that the cpu time gets accounted to - * @user_tick: indicates if the tick is a user or a system tick - */ -void account_process_tick(struct task_struct *p, int user_tick) -{ - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); - struct rq *rq = this_rq(); - - if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); - return; - } - - if (steal_account_process_tick()) - return; - - if (user_tick) - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); - else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, - one_jiffy_scaled); - else - account_idle_time(cputime_one_jiffy); -} - -/* - * Account multiple ticks of steal time. - * @p: the process from which the cpu time has been stolen - * @ticks: number of stolen ticks - */ -void account_steal_ticks(unsigned long ticks) -{ - account_steal_time(jiffies_to_cputime(ticks)); -} - -/* - * Account multiple ticks of idle time. - * @ticks: number of stolen ticks - */ -void account_idle_ticks(unsigned long ticks) -{ - - if (sched_clock_irqtime) { - irqtime_account_idle_ticks(ticks); - return; - } - - account_idle_time(jiffies_to_cputime(ticks)); -} - -#endif - -/* - * Use precise platform statistics if available: - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - *ut = p->utime; - *st = p->stime; -} - -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct task_cputime cputime; - - thread_group_cputime(p, &cputime); - - *ut = cputime.utime; - *st = cputime.stime; -} -#else -#ifndef nsecs_to_cputime -# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) -#endif - -void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - cputime_t rtime, utime = p->utime, total = utime + p->stime; - - /* - * Use CFS's precise accounting: - */ - rtime = nsecs_to_cputime(p->se.sum_exec_runtime); - - if (total) { - u64 temp = (__force u64) rtime; - - temp *= (__force u64) utime; - do_div(temp, (__force u32) total); - utime = (__force cputime_t) temp; - } else - utime = rtime; - - /* - * Compare with previous values, to keep monotonicity: - */ - p->prev_utime = max(p->prev_utime, utime); - p->prev_stime = max(p->prev_stime, rtime - p->prev_utime); - - *ut = p->prev_utime; - *st = p->prev_stime; -} - -/* - * Must be called with siglock held. - */ -void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct signal_struct *sig = p->signal; - struct task_cputime cputime; - cputime_t rtime, utime, total; - - thread_group_cputime(p, &cputime); - - total = cputime.utime + cputime.stime; - rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - - if (total) { - u64 temp = (__force u64) rtime; - - temp *= (__force u64) cputime.utime; - do_div(temp, (__force u32) total); - utime = (__force cputime_t) temp; - } else - utime = rtime; - - sig->prev_utime = max(sig->prev_utime, utime); - sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime); + rq = task_rq_lock(p, &flags); + ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); + task_rq_unlock(rq, p, &flags); - *ut = sig->prev_utime; - *st = sig->prev_stime; + return ns; } -#endif /* * This function gets called by the timer code, with HZ frequency. @@ -2995,18 +2500,47 @@ void scheduler_tick(void) raw_spin_lock(&rq->lock); update_rq_clock(rq); - update_cpu_load_active(rq); curr->sched_class->task_tick(rq, curr, 0); + update_cpu_load_active(rq); raw_spin_unlock(&rq->lock); perf_event_task_tick(); #ifdef CONFIG_SMP rq->idle_balance = idle_cpu(cpu); - trigger_load_balance(rq, cpu); + trigger_load_balance(rq); #endif + rq_last_tick_reset(rq); } +#ifdef CONFIG_NO_HZ_FULL +/** + * scheduler_tick_max_deferment + * + * Keep at least one tick per second when a single + * active task is running because the scheduler doesn't + * yet completely support full dynticks environment. + * + * This makes sure that uptime, CFS vruntime, load + * balancing, etc... continue to move forward, even + * with a very low granularity. + * + * Return: Maximum deferment in nanoseconds. + */ +u64 scheduler_tick_max_deferment(void) +{ + struct rq *rq = this_rq(); + unsigned long next, now = ACCESS_ONCE(jiffies); + + next = rq->last_sched_tick + HZ; + + if (time_before_eq(next, now)) + return 0; + + return jiffies_to_nsecs(next - now); +} +#endif + notrace unsigned long get_parent_ip(unsigned long addr) { if (in_lock_functions(addr)) { @@ -3020,7 +2554,7 @@ notrace unsigned long get_parent_ip(unsigned long addr) #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_PREEMPT_TRACER)) -void __kprobes add_preempt_count(int val) +void preempt_count_add(int val) { #ifdef CONFIG_DEBUG_PREEMPT /* @@ -3029,7 +2563,7 @@ void __kprobes add_preempt_count(int val) if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) return; #endif - preempt_count() += val; + __preempt_count_add(val); #ifdef CONFIG_DEBUG_PREEMPT /* * Spinlock count overflowing soon? @@ -3037,12 +2571,18 @@ void __kprobes add_preempt_count(int val) DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK - 10); #endif - if (preempt_count() == val) - trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + if (preempt_count() == val) { + unsigned long ip = get_parent_ip(CALLER_ADDR1); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } } -EXPORT_SYMBOL(add_preempt_count); +EXPORT_SYMBOL(preempt_count_add); +NOKPROBE_SYMBOL(preempt_count_add); -void __kprobes sub_preempt_count(int val) +void preempt_count_sub(int val) { #ifdef CONFIG_DEBUG_PREEMPT /* @@ -3060,9 +2600,10 @@ void __kprobes sub_preempt_count(int val) if (preempt_count() == val) trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); - preempt_count() -= val; + __preempt_count_sub(val); } -EXPORT_SYMBOL(sub_preempt_count); +EXPORT_SYMBOL(preempt_count_sub); +NOKPROBE_SYMBOL(preempt_count_sub); #endif @@ -3071,8 +2612,6 @@ EXPORT_SYMBOL(sub_preempt_count); */ static noinline void __schedule_bug(struct task_struct *prev) { - struct pt_regs *regs = get_irq_regs(); - if (oops_in_progress) return; @@ -3083,11 +2622,15 @@ static noinline void __schedule_bug(struct task_struct *prev) print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); - - if (regs) - show_regs(regs); - else - dump_stack(); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } /* @@ -3097,10 +2640,10 @@ static inline void schedule_debug(struct task_struct *prev) { /* * Test if we are atomic. Since do_exit() needs to call into - * schedule() atomically, we ignore that path for now. - * Otherwise, whine if we are scheduling when we should not be. + * schedule() atomically, we ignore that path. Otherwise whine + * if we are scheduling when we should not. */ - if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) + if (unlikely(in_atomic_preempt_off() && prev->state != TASK_DEAD)) __schedule_bug(prev); rcu_sleep_check(); @@ -3109,36 +2652,40 @@ static inline void schedule_debug(struct task_struct *prev) schedstat_inc(this_rq(), sched_count); } -static void put_prev_task(struct rq *rq, struct task_struct *prev) -{ - if (prev->on_rq || rq->skip_clock_update < 0) - update_rq_clock(rq); - prev->sched_class->put_prev_task(rq, prev); -} - /* * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq) +pick_next_task(struct rq *rq, struct task_struct *prev) { - const struct sched_class *class; + const struct sched_class *class = &fair_sched_class; struct task_struct *p; /* * Optimization: we know that if all tasks are in * the fair class we can call that function directly: */ - if (likely(rq->nr_running == rq->cfs.h_nr_running)) { - p = fair_sched_class.pick_next_task(rq); - if (likely(p)) - return p; + if (likely(prev->sched_class == class && + rq->nr_running == rq->cfs.h_nr_running)) { + p = fair_sched_class.pick_next_task(rq, prev); + if (unlikely(p == RETRY_TASK)) + goto again; + + /* assumes fair_sched_class->next == idle_sched_class */ + if (unlikely(!p)) + p = idle_sched_class.pick_next_task(rq, prev); + + return p; } +again: for_each_class(class) { - p = class->pick_next_task(rq); - if (p) + p = class->pick_next_task(rq, prev); + if (p) { + if (unlikely(p == RETRY_TASK)) + goto again; return p; + } } BUG(); /* the idle class will always have a runnable task */ @@ -3146,6 +2693,40 @@ pick_next_task(struct rq *rq) /* * __schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space */ static void __sched __schedule(void) { @@ -3166,6 +2747,12 @@ need_resched: if (sched_feat(HRTICK)) hrtick_clear(rq); + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + */ + smp_mb__before_spinlock(); raw_spin_lock_irq(&rq->lock); switch_count = &prev->nivcsw; @@ -3192,14 +2779,12 @@ need_resched: switch_count = &prev->nvcsw; } - pre_schedule(rq, prev); - - if (unlikely(!rq->nr_running)) - idle_balance(cpu, rq); + if (prev->on_rq || rq->skip_clock_update < 0) + update_rq_clock(rq); - put_prev_task(rq, prev); - next = pick_next_task(rq); + next = pick_next_task(rq, prev); clear_tsk_need_resched(prev); + clear_preempt_need_resched(); rq->skip_clock_update = 0; if (likely(prev != next)) { @@ -3221,14 +2806,14 @@ need_resched: post_schedule(rq); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); if (need_resched()) goto need_resched; } static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state) + if (!tsk->state || tsk_is_pi_blocked(tsk)) return; /* * If we are going to sleep and we have plugged IO queued, @@ -3238,7 +2823,7 @@ static inline void sched_submit_work(struct task_struct *tsk) blk_schedule_flush_plug(tsk); } -asmlinkage void __sched schedule(void) +asmlinkage __visible void __sched schedule(void) { struct task_struct *tsk = current; @@ -3247,50 +2832,32 @@ asmlinkage void __sched schedule(void) } EXPORT_SYMBOL(schedule); -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER - -static inline bool owner_running(struct mutex *lock, struct task_struct *owner) +#ifdef CONFIG_CONTEXT_TRACKING +asmlinkage __visible void __sched schedule_user(void) { - if (lock->owner != owner) - return false; - /* - * Ensure we emit the owner->on_cpu, dereference _after_ checking - * lock->owner still matches owner, if that fails, owner might - * point to free()d memory, if it still matches, the rcu_read_lock() - * ensures the memory stays valid. + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. */ - barrier(); - - return owner->on_cpu; + user_exit(); + schedule(); + user_enter(); } +#endif -/* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 */ -int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) +void __sched schedule_preempt_disabled(void) { - if (!sched_feat(OWNER_SPIN)) - return 0; - - rcu_read_lock(); - while (owner_running(lock, owner)) { - if (need_resched()) - break; - - arch_mutex_cpu_relax(); - } - rcu_read_unlock(); - - /* - * We break out the loop above on need_resched() and when the - * owner changed, which is a sign for heavy contention. Return - * success only when lock->owner is NULL. - */ - return lock->owner == NULL; + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); } -#endif #ifdef CONFIG_PREEMPT /* @@ -3298,21 +2865,19 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) * off of preempt_enable. Kernel preemptions off return from interrupt * occur there and call schedule directly. */ -asmlinkage void __sched notrace preempt_schedule(void) +asmlinkage __visible void __sched notrace preempt_schedule(void) { - struct thread_info *ti = current_thread_info(); - /* * If there is a non-zero preempt_count or interrupts are disabled, * we do not want to preempt the current task. Just return.. */ - if (likely(ti->preempt_count || irqs_disabled())) + if (likely(!preemptible())) return; do { - add_preempt_count_notrace(PREEMPT_ACTIVE); + __preempt_count_add(PREEMPT_ACTIVE); __schedule(); - sub_preempt_count_notrace(PREEMPT_ACTIVE); + __preempt_count_sub(PREEMPT_ACTIVE); /* * Check again in case we missed a preemption opportunity @@ -3321,7 +2886,9 @@ asmlinkage void __sched notrace preempt_schedule(void) barrier(); } while (need_resched()); } +NOKPROBE_SYMBOL(preempt_schedule); EXPORT_SYMBOL(preempt_schedule); +#endif /* CONFIG_PREEMPT */ /* * this is the entry point to schedule() from kernel preemption @@ -3329,19 +2896,21 @@ EXPORT_SYMBOL(preempt_schedule); * Note, that this is called and return with irqs disabled. This will * protect us against recursive calling from irq. */ -asmlinkage void __sched preempt_schedule_irq(void) +asmlinkage __visible void __sched preempt_schedule_irq(void) { - struct thread_info *ti = current_thread_info(); + enum ctx_state prev_state; /* Catch callers which need to be fixed */ - BUG_ON(ti->preempt_count || !irqs_disabled()); + BUG_ON(preempt_count() || !irqs_disabled()); + + prev_state = exception_enter(); do { - add_preempt_count(PREEMPT_ACTIVE); + __preempt_count_add(PREEMPT_ACTIVE); local_irq_enable(); __schedule(); local_irq_disable(); - sub_preempt_count(PREEMPT_ACTIVE); + __preempt_count_sub(PREEMPT_ACTIVE); /* * Check again in case we missed a preemption opportunity @@ -3349,9 +2918,9 @@ asmlinkage void __sched preempt_schedule_irq(void) */ barrier(); } while (need_resched()); -} -#endif /* CONFIG_PREEMPT */ + exception_exit(prev_state); +} int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, void *key) @@ -3360,392 +2929,6 @@ int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, } EXPORT_SYMBOL(default_wake_function); -/* - * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just - * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve - * number) then we wake all the non-exclusive tasks and one exclusive task. - * - * There are circumstances in which we can try to wake a task which has already - * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns - * zero in this (rare) case, and we handle it by continuing to scan the queue. - */ -static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, int wake_flags, void *key) -{ - wait_queue_t *curr, *next; - - list_for_each_entry_safe(curr, next, &q->task_list, task_list) { - unsigned flags = curr->flags; - - if (curr->func(curr, mode, wake_flags, key) && - (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) - break; - } -} - -/** - * __wake_up - wake up threads blocked on a waitqueue. - * @q: the waitqueue - * @mode: which threads - * @nr_exclusive: how many wake-one or wake-many threads to wake up - * @key: is directly passed to the wakeup function - * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. - */ -void __wake_up(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, void *key) -{ - unsigned long flags; - - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, 0, key); - spin_unlock_irqrestore(&q->lock, flags); -} -EXPORT_SYMBOL(__wake_up); - -/* - * Same as __wake_up but called with the spinlock in wait_queue_head_t held. - */ -void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) -{ - __wake_up_common(q, mode, 1, 0, NULL); -} -EXPORT_SYMBOL_GPL(__wake_up_locked); - -void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) -{ - __wake_up_common(q, mode, 1, 0, key); -} -EXPORT_SYMBOL_GPL(__wake_up_locked_key); - -/** - * __wake_up_sync_key - wake up threads blocked on a waitqueue. - * @q: the waitqueue - * @mode: which threads - * @nr_exclusive: how many wake-one or wake-many threads to wake up - * @key: opaque value to be passed to wakeup targets - * - * The sync wakeup differs that the waker knows that it will schedule - * away soon, so while the target thread will be woken up, it will not - * be migrated to another CPU - ie. the two threads are 'synchronized' - * with each other. This can prevent needless bouncing between CPUs. - * - * On UP it can prevent extra preemption. - * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. - */ -void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, void *key) -{ - unsigned long flags; - int wake_flags = WF_SYNC; - - if (unlikely(!q)) - return; - - if (unlikely(!nr_exclusive)) - wake_flags = 0; - - spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, wake_flags, key); - spin_unlock_irqrestore(&q->lock, flags); -} -EXPORT_SYMBOL_GPL(__wake_up_sync_key); - -/* - * __wake_up_sync - see __wake_up_sync_key() - */ -void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) -{ - __wake_up_sync_key(q, mode, nr_exclusive, NULL); -} -EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ - -/** - * complete: - signals a single thread waiting on this completion - * @x: holds the state of this particular completion - * - * This will wake up a single thread waiting on this completion. Threads will be - * awakened in the same order in which they were queued. - * - * See also complete_all(), wait_for_completion() and related routines. - * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. - */ -void complete(struct completion *x) -{ - unsigned long flags; - - spin_lock_irqsave(&x->wait.lock, flags); - x->done++; - __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); -} -EXPORT_SYMBOL(complete); - -/** - * complete_all: - signals all threads waiting on this completion - * @x: holds the state of this particular completion - * - * This will wake up all threads waiting on this particular completion event. - * - * It may be assumed that this function implies a write memory barrier before - * changing the task state if and only if any tasks are woken up. - */ -void complete_all(struct completion *x) -{ - unsigned long flags; - - spin_lock_irqsave(&x->wait.lock, flags); - x->done += UINT_MAX/2; - __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); - spin_unlock_irqrestore(&x->wait.lock, flags); -} -EXPORT_SYMBOL(complete_all); - -static inline long __sched -do_wait_for_common(struct completion *x, long timeout, int state) -{ - if (!x->done) { - DECLARE_WAITQUEUE(wait, current); - - __add_wait_queue_tail_exclusive(&x->wait, &wait); - do { - if (signal_pending_state(state, current)) { - timeout = -ERESTARTSYS; - break; - } - __set_current_state(state); - spin_unlock_irq(&x->wait.lock); - timeout = schedule_timeout(timeout); - spin_lock_irq(&x->wait.lock); - } while (!x->done && timeout); - __remove_wait_queue(&x->wait, &wait); - if (!x->done) - return timeout; - } - x->done--; - return timeout ?: 1; -} - -static long __sched -wait_for_common(struct completion *x, long timeout, int state) -{ - might_sleep(); - - spin_lock_irq(&x->wait.lock); - timeout = do_wait_for_common(x, timeout, state); - spin_unlock_irq(&x->wait.lock); - return timeout; -} - -/** - * wait_for_completion: - waits for completion of a task - * @x: holds the state of this particular completion - * - * This waits to be signaled for completion of a specific task. It is NOT - * interruptible and there is no timeout. - * - * See also similar routines (i.e. wait_for_completion_timeout()) with timeout - * and interrupt capability. Also see complete(). - */ -void __sched wait_for_completion(struct completion *x) -{ - wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); -} -EXPORT_SYMBOL(wait_for_completion); - -/** - * wait_for_completion_timeout: - waits for completion of a task (w/timeout) - * @x: holds the state of this particular completion - * @timeout: timeout value in jiffies - * - * This waits for either a completion of a specific task to be signaled or for a - * specified timeout to expire. The timeout is in jiffies. It is not - * interruptible. - * - * The return value is 0 if timed out, and positive (at least 1, or number of - * jiffies left till timeout) if completed. - */ -unsigned long __sched -wait_for_completion_timeout(struct completion *x, unsigned long timeout) -{ - return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); -} -EXPORT_SYMBOL(wait_for_completion_timeout); - -/** - * wait_for_completion_interruptible: - waits for completion of a task (w/intr) - * @x: holds the state of this particular completion - * - * This waits for completion of a specific task to be signaled. It is - * interruptible. - * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. - */ -int __sched wait_for_completion_interruptible(struct completion *x) -{ - long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); - if (t == -ERESTARTSYS) - return t; - return 0; -} -EXPORT_SYMBOL(wait_for_completion_interruptible); - -/** - * wait_for_completion_interruptible_timeout: - waits for completion (w/(to,intr)) - * @x: holds the state of this particular completion - * @timeout: timeout value in jiffies - * - * This waits for either a completion of a specific task to be signaled or for a - * specified timeout to expire. It is interruptible. The timeout is in jiffies. - * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. - */ -long __sched -wait_for_completion_interruptible_timeout(struct completion *x, - unsigned long timeout) -{ - return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); -} -EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); - -/** - * wait_for_completion_killable: - waits for completion of a task (killable) - * @x: holds the state of this particular completion - * - * This waits to be signaled for completion of a specific task. It can be - * interrupted by a kill signal. - * - * The return value is -ERESTARTSYS if interrupted, 0 if completed. - */ -int __sched wait_for_completion_killable(struct completion *x) -{ - long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); - if (t == -ERESTARTSYS) - return t; - return 0; -} -EXPORT_SYMBOL(wait_for_completion_killable); - -/** - * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable)) - * @x: holds the state of this particular completion - * @timeout: timeout value in jiffies - * - * This waits for either a completion of a specific task to be - * signaled or for a specified timeout to expire. It can be - * interrupted by a kill signal. The timeout is in jiffies. - * - * The return value is -ERESTARTSYS if interrupted, 0 if timed out, - * positive (at least 1, or number of jiffies left till timeout) if completed. - */ -long __sched -wait_for_completion_killable_timeout(struct completion *x, - unsigned long timeout) -{ - return wait_for_common(x, timeout, TASK_KILLABLE); -} -EXPORT_SYMBOL(wait_for_completion_killable_timeout); - -/** - * try_wait_for_completion - try to decrement a completion without blocking - * @x: completion structure - * - * Returns: 0 if a decrement cannot be done without blocking - * 1 if a decrement succeeded. - * - * If a completion is being used as a counting completion, - * attempt to decrement the counter without blocking. This - * enables us to avoid waiting if the resource the completion - * is protecting is not available. - */ -bool try_wait_for_completion(struct completion *x) -{ - unsigned long flags; - int ret = 1; - - spin_lock_irqsave(&x->wait.lock, flags); - if (!x->done) - ret = 0; - else - x->done--; - spin_unlock_irqrestore(&x->wait.lock, flags); - return ret; -} -EXPORT_SYMBOL(try_wait_for_completion); - -/** - * completion_done - Test to see if a completion has any waiters - * @x: completion structure - * - * Returns: 0 if there are waiters (wait_for_completion() in progress) - * 1 if there are no waiters. - * - */ -bool completion_done(struct completion *x) -{ - unsigned long flags; - int ret = 1; - - spin_lock_irqsave(&x->wait.lock, flags); - if (!x->done) - ret = 0; - spin_unlock_irqrestore(&x->wait.lock, flags); - return ret; -} -EXPORT_SYMBOL(completion_done); - -static long __sched -sleep_on_common(wait_queue_head_t *q, int state, long timeout) -{ - unsigned long flags; - wait_queue_t wait; - - init_waitqueue_entry(&wait, current); - - __set_current_state(state); - - spin_lock_irqsave(&q->lock, flags); - __add_wait_queue(q, &wait); - spin_unlock(&q->lock); - timeout = schedule_timeout(timeout); - spin_lock_irq(&q->lock); - __remove_wait_queue(q, &wait); - spin_unlock_irqrestore(&q->lock, flags); - - return timeout; -} - -void __sched interruptible_sleep_on(wait_queue_head_t *q) -{ - sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -} -EXPORT_SYMBOL(interruptible_sleep_on); - -long __sched -interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) -{ - return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); -} -EXPORT_SYMBOL(interruptible_sleep_on_timeout); - -void __sched sleep_on(wait_queue_head_t *q) -{ - sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); -} -EXPORT_SYMBOL(sleep_on); - -long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) -{ - return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); -} -EXPORT_SYMBOL(sleep_on_timeout); - #ifdef CONFIG_RT_MUTEXES /* @@ -3756,19 +2939,39 @@ EXPORT_SYMBOL(sleep_on_timeout); * This function changes the 'effective' priority of a task. It does * not touch ->normal_prio like __setscheduler(). * - * Used by the rt_mutex code to implement priority inheritance logic. + * Used by the rt_mutex code to implement priority inheritance + * logic. Call site only calls if the priority of the task changed. */ void rt_mutex_setprio(struct task_struct *p, int prio) { - int oldprio, on_rq, running; + int oldprio, on_rq, running, enqueue_flag = 0; struct rq *rq; const struct sched_class *prev_class; - BUG_ON(prio < 0 || prio > MAX_PRIO); + BUG_ON(prio > MAX_PRIO); rq = __task_rq_lock(p); + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + trace_sched_pi_setprio(p, prio); + p->pi_top_task = rt_mutex_get_top_task(p); oldprio = p->prio; prev_class = p->sched_class; on_rq = p->on_rq; @@ -3778,22 +2981,47 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->put_prev_task(rq, p); - if (rt_prio(prio)) + /* + * Boosting condition are: + * 1. -rt task is running and holds mutex A + * --> -dl task blocks on mutex A + * + * 2. -dl task is running and holds mutex A + * --> -dl task blocks on mutex A and could preempt the + * running task + */ + if (dl_prio(prio)) { + if (!dl_prio(p->normal_prio) || (p->pi_top_task && + dl_entity_preempt(&p->pi_top_task->dl, &p->dl))) { + p->dl.dl_boosted = 1; + p->dl.dl_throttled = 0; + enqueue_flag = ENQUEUE_REPLENISH; + } else + p->dl.dl_boosted = 0; + p->sched_class = &dl_sched_class; + } else if (rt_prio(prio)) { + if (dl_prio(oldprio)) + p->dl.dl_boosted = 0; + if (oldprio < prio) + enqueue_flag = ENQUEUE_HEAD; p->sched_class = &rt_sched_class; - else + } else { + if (dl_prio(oldprio)) + p->dl.dl_boosted = 0; p->sched_class = &fair_sched_class; + } p->prio = prio; if (running) p->sched_class->set_curr_task(rq); if (on_rq) - enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); + enqueue_task(rq, p, enqueue_flag); check_class_changed(rq, p, prev_class, oldprio); +out_unlock: __task_rq_unlock(rq); } - #endif void set_user_nice(struct task_struct *p, long nice) @@ -3802,7 +3030,7 @@ void set_user_nice(struct task_struct *p, long nice) unsigned long flags; struct rq *rq; - if (TASK_NICE(p) == nice || nice < -20 || nice > 19) + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) return; /* * We have to be careful, if called from sys_setpriority(), @@ -3813,9 +3041,9 @@ void set_user_nice(struct task_struct *p, long nice) * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected * it wont have any effect on scheduling until the task is - * SCHED_FIFO/SCHED_RR: + * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: */ - if (task_has_rt_policy(p)) { + if (task_has_dl_policy(p) || task_has_rt_policy(p)) { p->static_prio = NICE_TO_PRIO(nice); goto out_unlock; } @@ -3851,7 +3079,7 @@ EXPORT_SYMBOL(set_user_nice); int can_nice(const struct task_struct *p, const int nice) { /* convert nice value [19,-20] to rlimit style value [1,40] */ - int nice_rlim = 20 - nice; + int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); @@ -3875,17 +3103,10 @@ SYSCALL_DEFINE1(nice, int, increment) * We don't have to worry. Conceptually one call occurs first * and we have a single winner. */ - if (increment < -40) - increment = -40; - if (increment > 40) - increment = 40; - - nice = TASK_NICE(current) + increment; - if (nice < -20) - nice = -20; - if (nice > 19) - nice = 19; + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); + nice = task_nice(current) + increment; + nice = clamp_val(nice, MIN_NICE, MAX_NICE); if (increment < 0 && !can_nice(current, nice)) return -EPERM; @@ -3903,7 +3124,7 @@ SYSCALL_DEFINE1(nice, int, increment) * task_prio - return the priority value of a given task. * @p: the task in question. * - * This is the priority value as seen by users in /proc. + * Return: The priority value as seen by users in /proc. * RT tasks are offset by -200. Normal tasks are centered * around 0, value goes from -16 to +15. */ @@ -3913,18 +3134,10 @@ int task_prio(const struct task_struct *p) } /** - * task_nice - return the nice value of a given task. - * @p: the task in question. - */ -int task_nice(const struct task_struct *p) -{ - return TASK_NICE(p); -} -EXPORT_SYMBOL(task_nice); - -/** * idle_cpu - is a given cpu idle currently? * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. */ int idle_cpu(int cpu) { @@ -3947,6 +3160,8 @@ int idle_cpu(int cpu) /** * idle_task - return the idle task for a given cpu. * @cpu: the processor in question. + * + * Return: The idle task for the cpu @cpu. */ struct task_struct *idle_task(int cpu) { @@ -3956,26 +3171,134 @@ struct task_struct *idle_task(int cpu) /** * find_process_by_pid - find a process with a matching PID value. * @pid: the pid in question. + * + * The task of @pid, if found. %NULL otherwise. */ static struct task_struct *find_process_by_pid(pid_t pid) { return pid ? find_task_by_vpid(pid) : current; } -/* Actually do priority change: must hold rq lock. */ +/* + * This function initializes the sched_dl_entity of a newly becoming + * SCHED_DEADLINE task. + * + * Only the static values are considered here, the actual runtime and the + * absolute deadline will be properly calculated when the task is enqueued + * for the first time with its new policy. + */ static void -__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) +__setparam_dl(struct task_struct *p, const struct sched_attr *attr) { + struct sched_dl_entity *dl_se = &p->dl; + + init_dl_task_timer(dl_se); + dl_se->dl_runtime = attr->sched_runtime; + dl_se->dl_deadline = attr->sched_deadline; + dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline; + dl_se->flags = attr->sched_flags; + dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); + dl_se->dl_throttled = 0; + dl_se->dl_new = 1; + dl_se->dl_yielded = 0; +} + +static void __setscheduler_params(struct task_struct *p, + const struct sched_attr *attr) +{ + int policy = attr->sched_policy; + + if (policy == -1) /* setparam */ + policy = p->policy; + p->policy = policy; - p->rt_priority = prio; + + if (dl_policy(policy)) + __setparam_dl(p, attr); + else if (fair_policy(policy)) + p->static_prio = NICE_TO_PRIO(attr->sched_nice); + + /* + * __sched_setscheduler() ensures attr->sched_priority == 0 when + * !rt_policy. Always setting this ensures that things like + * getparam()/getattr() don't report silly values for !rt tasks. + */ + p->rt_priority = attr->sched_priority; p->normal_prio = normal_prio(p); - /* we are holding p->pi_lock already */ - p->prio = rt_mutex_getprio(p); - if (rt_prio(p->prio)) + set_load_weight(p); +} + +/* Actually do priority change: must hold pi & rq lock. */ +static void __setscheduler(struct rq *rq, struct task_struct *p, + const struct sched_attr *attr) +{ + __setscheduler_params(p, attr); + + /* + * If we get here, there was no pi waiters boosting the + * task. It is safe to use the normal prio. + */ + p->prio = normal_prio(p); + + if (dl_prio(p->prio)) + p->sched_class = &dl_sched_class; + else if (rt_prio(p->prio)) p->sched_class = &rt_sched_class; else p->sched_class = &fair_sched_class; - set_load_weight(p); +} + +static void +__getparam_dl(struct task_struct *p, struct sched_attr *attr) +{ + struct sched_dl_entity *dl_se = &p->dl; + + attr->sched_priority = p->rt_priority; + attr->sched_runtime = dl_se->dl_runtime; + attr->sched_deadline = dl_se->dl_deadline; + attr->sched_period = dl_se->dl_period; + attr->sched_flags = dl_se->flags; +} + +/* + * This function validates the new parameters of a -deadline task. + * We ask for the deadline not being zero, and greater or equal + * than the runtime, as well as the period of being zero or + * greater than deadline. Furthermore, we have to be sure that + * user parameters are above the internal resolution of 1us (we + * check sched_runtime only since it is always the smaller one) and + * below 2^63 ns (we have to check both sched_deadline and + * sched_period, as the latter can be zero). + */ +static bool +__checkparam_dl(const struct sched_attr *attr) +{ + /* deadline != 0 */ + if (attr->sched_deadline == 0) + return false; + + /* + * Since we truncate DL_SCALE bits, make sure we're at least + * that big. + */ + if (attr->sched_runtime < (1ULL << DL_SCALE)) + return false; + + /* + * Since we use the MSB for wrap-around and sign issues, make + * sure it's not set (mind that period can be equal to zero). + */ + if (attr->sched_deadline & (1ULL << 63) || + attr->sched_period & (1ULL << 63)) + return false; + + /* runtime <= deadline <= period (if period != 0) */ + if ((attr->sched_period != 0 && + attr->sched_period < attr->sched_deadline) || + attr->sched_deadline < attr->sched_runtime) + return false; + + return true; } /* @@ -3988,19 +3311,20 @@ static bool check_same_owner(struct task_struct *p) rcu_read_lock(); pcred = __task_cred(p); - if (cred->user->user_ns == pcred->user->user_ns) - match = (cred->euid == pcred->euid || - cred->euid == pcred->uid); - else - match = false; + match = (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); rcu_read_unlock(); return match; } -static int __sched_setscheduler(struct task_struct *p, int policy, - const struct sched_param *param, bool user) +static int __sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + bool user) { + int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : + MAX_RT_PRIO - 1 - attr->sched_priority; int retval, oldprio, oldpolicy = -1, on_rq, running; + int policy = attr->sched_policy; unsigned long flags; const struct sched_class *prev_class; struct rq *rq; @@ -4014,31 +3338,40 @@ recheck: reset_on_fork = p->sched_reset_on_fork; policy = oldpolicy = p->policy; } else { - reset_on_fork = !!(policy & SCHED_RESET_ON_FORK); - policy &= ~SCHED_RESET_ON_FORK; + reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK); - if (policy != SCHED_FIFO && policy != SCHED_RR && + if (policy != SCHED_DEADLINE && + policy != SCHED_FIFO && policy != SCHED_RR && policy != SCHED_NORMAL && policy != SCHED_BATCH && policy != SCHED_IDLE) return -EINVAL; } + if (attr->sched_flags & ~(SCHED_FLAG_RESET_ON_FORK)) + return -EINVAL; + /* * Valid priorities for SCHED_FIFO and SCHED_RR are * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, * SCHED_BATCH and SCHED_IDLE is 0. */ - if (param->sched_priority < 0 || - (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || - (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) + if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) || + (!p->mm && attr->sched_priority > MAX_RT_PRIO-1)) return -EINVAL; - if (rt_policy(policy) != (param->sched_priority != 0)) + if ((dl_policy(policy) && !__checkparam_dl(attr)) || + (rt_policy(policy) != (attr->sched_priority != 0))) return -EINVAL; /* * Allow unprivileged RT tasks to decrease priority: */ if (user && !capable(CAP_SYS_NICE)) { + if (fair_policy(policy)) { + if (attr->sched_nice < task_nice(p) && + !can_nice(p, attr->sched_nice)) + return -EPERM; + } + if (rt_policy(policy)) { unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); @@ -4048,17 +3381,26 @@ recheck: return -EPERM; /* can't increase priority */ - if (param->sched_priority > p->rt_priority && - param->sched_priority > rlim_rtprio) + if (attr->sched_priority > p->rt_priority && + attr->sched_priority > rlim_rtprio) return -EPERM; } + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + return -EPERM; + /* * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) { - if (!can_nice(p, TASK_NICE(p))) + if (!can_nice(p, task_nice(p))) return -EPERM; } @@ -4095,18 +3437,25 @@ recheck: } /* - * If not changing anything there's no need to proceed further: + * If not changing anything there's no need to proceed further, + * but store a possible modification of reset_on_fork. */ - if (unlikely(policy == p->policy && (!rt_policy(policy) || - param->sched_priority == p->rt_priority))) { - - __task_rq_unlock(rq); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + if (unlikely(policy == p->policy)) { + if (fair_policy(policy) && attr->sched_nice != task_nice(p)) + goto change; + if (rt_policy(policy) && attr->sched_priority != p->rt_priority) + goto change; + if (dl_policy(policy)) + goto change; + + p->sched_reset_on_fork = reset_on_fork; + task_rq_unlock(rq, p, &flags); return 0; } +change: -#ifdef CONFIG_RT_GROUP_SCHED if (user) { +#ifdef CONFIG_RT_GROUP_SCHED /* * Do not allow realtime tasks into groups that have no runtime * assigned. @@ -4117,8 +3466,24 @@ recheck: task_rq_unlock(rq, p, &flags); return -EPERM; } - } #endif +#ifdef CONFIG_SMP + if (dl_bandwidth_enabled() && dl_policy(policy)) { + cpumask_t *span = rq->rd->span; + + /* + * Don't allow tasks with an affinity mask smaller than + * the entire root_domain to become SCHED_DEADLINE. We + * will also fail if there's no bandwidth available. + */ + if (!cpumask_subset(span, &p->cpus_allowed) || + rq->rd->dl_bw.bw == 0) { + task_rq_unlock(rq, p, &flags); + return -EPERM; + } + } +#endif + } /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { @@ -4126,6 +3491,35 @@ recheck: task_rq_unlock(rq, p, &flags); goto recheck; } + + /* + * If setscheduling to SCHED_DEADLINE (or changing the parameters + * of a SCHED_DEADLINE task) we need to check if enough bandwidth + * is available. + */ + if ((dl_policy(policy) || dl_task(p)) && dl_overflow(p, policy, attr)) { + task_rq_unlock(rq, p, &flags); + return -EBUSY; + } + + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + + /* + * Special case for priority boosted tasks. + * + * If the new priority is lower or equal (user space view) + * than the current (boosted) priority, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + if (rt_mutex_check_prio(p, newprio)) { + __setscheduler_params(p, attr); + task_rq_unlock(rq, p, &flags); + return 0; + } + on_rq = p->on_rq; running = task_current(rq, p); if (on_rq) @@ -4133,16 +3527,18 @@ recheck: if (running) p->sched_class->put_prev_task(rq, p); - p->sched_reset_on_fork = reset_on_fork; - - oldprio = p->prio; prev_class = p->sched_class; - __setscheduler(rq, p, policy, param->sched_priority); + __setscheduler(rq, p, attr); if (running) p->sched_class->set_curr_task(rq); - if (on_rq) - enqueue_task(rq, p, 0); + if (on_rq) { + /* + * We enqueue to tail when the priority of a task is + * increased (user space view). + */ + enqueue_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0); + } check_class_changed(rq, p, prev_class, oldprio); task_rq_unlock(rq, p, &flags); @@ -4152,21 +3548,49 @@ recheck: return 0; } +static int _sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool check) +{ + struct sched_attr attr = { + .sched_policy = policy, + .sched_priority = param->sched_priority, + .sched_nice = PRIO_TO_NICE(p->static_prio), + }; + + /* + * Fixup the legacy SCHED_RESET_ON_FORK hack + */ + if (policy & SCHED_RESET_ON_FORK) { + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + policy &= ~SCHED_RESET_ON_FORK; + attr.sched_policy = policy; + } + + return __sched_setscheduler(p, &attr, check); +} /** * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. * @p: the task in question. * @policy: new policy. * @param: structure containing the new RT priority. * + * Return: 0 on success. An error code otherwise. + * * NOTE that the task may be already dead. */ int sched_setscheduler(struct task_struct *p, int policy, const struct sched_param *param) { - return __sched_setscheduler(p, policy, param, true); + return _sched_setscheduler(p, policy, param, true); } EXPORT_SYMBOL_GPL(sched_setscheduler); +int sched_setattr(struct task_struct *p, const struct sched_attr *attr) +{ + return __sched_setscheduler(p, attr, true); +} +EXPORT_SYMBOL_GPL(sched_setattr); + /** * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. * @p: the task in question. @@ -4177,11 +3601,13 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); * current context has permission. For example, this is needed in * stop_machine(): we create temporary high priority worker threads, * but our caller might not have that capability. + * + * Return: 0 on success. An error code otherwise. */ int sched_setscheduler_nocheck(struct task_struct *p, int policy, const struct sched_param *param) { - return __sched_setscheduler(p, policy, param, false); + return _sched_setscheduler(p, policy, param, false); } static int @@ -4206,11 +3632,84 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) return retval; } +/* + * Mimics kernel/events/core.c perf_copy_attr(). + */ +static int sched_copy_attr(struct sched_attr __user *uattr, + struct sched_attr *attr) +{ + u32 size; + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) + return -EFAULT; + + /* + * zero the full structure, so that a short copy will be nice. + */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + if (size > PAGE_SIZE) /* silly large */ + goto err_size; + + if (!size) /* abi compat */ + size = SCHED_ATTR_SIZE_VER0; + + if (size < SCHED_ATTR_SIZE_VER0) + goto err_size; + + /* + * If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(*attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(*attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + ret = get_user(val, addr); + if (ret) + return ret; + if (val) + goto err_size; + } + size = sizeof(*attr); + } + + ret = copy_from_user(attr, uattr, size); + if (ret) + return -EFAULT; + + /* + * XXX: do we want to be lenient like existing syscalls; or do we want + * to be strict and return an error on out-of-bounds values? + */ + attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); + + return 0; + +err_size: + put_user(sizeof(*attr), &uattr->size); + return -E2BIG; +} + /** * sys_sched_setscheduler - set/change the scheduler policy and RT priority * @pid: the pid in question. * @policy: new policy. * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) @@ -4226,6 +3725,8 @@ SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, * sys_sched_setparam - set/change the RT priority of a thread * @pid: the pid in question. * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) { @@ -4233,8 +3734,44 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) } /** + * sys_sched_setattr - same as above, but with extended sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @flags: for future extension. + */ +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) +{ + struct sched_attr attr; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || flags) + return -EINVAL; + + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setattr(p, &attr); + rcu_read_unlock(); + + return retval; +} + +/** * sys_sched_getscheduler - get the policy (scheduling class) of a thread * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. */ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) { @@ -4261,10 +3798,13 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) * sys_sched_getparam - get the RT priority of a thread * @pid: the pid in question. * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. */ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) { - struct sched_param lp; + struct sched_param lp = { .sched_priority = 0 }; struct task_struct *p; int retval; @@ -4281,7 +3821,8 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) if (retval) goto out_unlock; - lp.sched_priority = p->rt_priority; + if (task_has_rt_policy(p)) + lp.sched_priority = p->rt_priority; rcu_read_unlock(); /* @@ -4296,19 +3837,103 @@ out_unlock: return retval; } +static int sched_read_attr(struct sched_attr __user *uattr, + struct sched_attr *attr, + unsigned int usize) +{ + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, usize)) + return -EFAULT; + + /* + * If we're handed a smaller struct than we know of, + * ensure all the unknown bits are 0 - i.e. old + * user-space does not get uncomplete information. + */ + if (usize < sizeof(*attr)) { + unsigned char *addr; + unsigned char *end; + + addr = (void *)attr + usize; + end = (void *)attr + sizeof(*attr); + + for (; addr < end; addr++) { + if (*addr) + return -EFBIG; + } + + attr->size = usize; + } + + ret = copy_to_user(uattr, attr, attr->size); + if (ret) + return -EFAULT; + + return 0; +} + +/** + * sys_sched_getattr - similar to sched_getparam, but with sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @size: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. + */ +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) +{ + struct sched_attr attr = { + .size = sizeof(struct sched_attr), + }; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || size > PAGE_SIZE || + size < SCHED_ATTR_SIZE_VER0 || flags) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + attr.sched_policy = p->policy; + if (p->sched_reset_on_fork) + attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + if (task_has_dl_policy(p)) + __getparam_dl(p, &attr); + else if (task_has_rt_policy(p)) + attr.sched_priority = p->rt_priority; + else + attr.sched_nice = task_nice(p); + + rcu_read_unlock(); + + retval = sched_read_attr(uattr, &attr, size); + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) { cpumask_var_t cpus_allowed, new_mask; struct task_struct *p; int retval; - get_online_cpus(); rcu_read_lock(); p = find_process_by_pid(pid); if (!p) { rcu_read_unlock(); - put_online_cpus(); return -ESRCH; } @@ -4316,6 +3941,10 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) get_task_struct(p); rcu_read_unlock(); + if (p->flags & PF_NO_SETAFFINITY) { + retval = -EINVAL; + goto out_put_task; + } if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { retval = -ENOMEM; goto out_put_task; @@ -4325,15 +3954,39 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) goto out_free_cpus_allowed; } retval = -EPERM; - if (!check_same_owner(p) && !ns_capable(task_user_ns(p), CAP_SYS_NICE)) - goto out_unlock; + if (!check_same_owner(p)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); + goto out_unlock; + } + rcu_read_unlock(); + } retval = security_task_setscheduler(p); if (retval) goto out_unlock; + cpuset_cpus_allowed(p, cpus_allowed); cpumask_and(new_mask, in_mask, cpus_allowed); + + /* + * Since bandwidth control happens on root_domain basis, + * if admission test is enabled, we only admit -deadline + * tasks allowed to run on all the CPUs in the task's + * root_domain. + */ +#ifdef CONFIG_SMP + if (task_has_dl_policy(p)) { + const struct cpumask *span = task_rq(p)->rd->span; + + if (dl_bandwidth_enabled() && !cpumask_subset(span, new_mask)) { + retval = -EBUSY; + goto out_unlock; + } + } +#endif again: retval = set_cpus_allowed_ptr(p, new_mask); @@ -4355,7 +4008,6 @@ out_free_cpus_allowed: free_cpumask_var(cpus_allowed); out_put_task: put_task_struct(p); - put_online_cpus(); return retval; } @@ -4375,6 +4027,8 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr * @user_mask_ptr: user-space pointer to the new cpu mask + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, unsigned long __user *, user_mask_ptr) @@ -4398,7 +4052,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) unsigned long flags; int retval; - get_online_cpus(); rcu_read_lock(); retval = -ESRCH; @@ -4411,12 +4064,11 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) goto out_unlock; raw_spin_lock_irqsave(&p->pi_lock, flags); - cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); + cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); raw_spin_unlock_irqrestore(&p->pi_lock, flags); out_unlock: rcu_read_unlock(); - put_online_cpus(); return retval; } @@ -4426,6 +4078,8 @@ out_unlock: * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr * @user_mask_ptr: user-space pointer to hold the current cpu mask + * + * Return: 0 on success. An error code otherwise. */ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, unsigned long __user *, user_mask_ptr) @@ -4460,6 +4114,8 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, * * This function yields the current CPU to other tasks. If there are no * other threads running on this CPU then this function will return. + * + * Return: 0. */ SYSCALL_DEFINE0(sched_yield) { @@ -4475,23 +4131,18 @@ SYSCALL_DEFINE0(sched_yield) __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); do_raw_spin_unlock(&rq->lock); - preempt_enable_no_resched(); + sched_preempt_enable_no_resched(); schedule(); return 0; } -static inline int should_resched(void) -{ - return need_resched() && !(preempt_count() & PREEMPT_ACTIVE); -} - static void __cond_resched(void) { - add_preempt_count(PREEMPT_ACTIVE); + __preempt_count_add(PREEMPT_ACTIVE); __schedule(); - sub_preempt_count(PREEMPT_ACTIVE); + __preempt_count_sub(PREEMPT_ACTIVE); } int __sched _cond_resched(void) @@ -4549,8 +4200,24 @@ EXPORT_SYMBOL(__cond_resched_softirq); /** * yield - yield the current processor to other threads. * - * This is a shortcut for kernel-space yielding - it marks the - * thread runnable and calls sys_sched_yield(). + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! */ void __sched yield(void) { @@ -4569,34 +4236,46 @@ EXPORT_SYMBOL(yield); * It's the caller's job to ensure that the target task struct * can't go away on us before we can do any checks. * - * Returns true if we indeed boosted the target task. + * Return: + * true (>0) if we indeed boosted the target task. + * false (0) if we failed to boost the target. + * -ESRCH if there's no task to yield to. */ -bool __sched yield_to(struct task_struct *p, bool preempt) +int __sched yield_to(struct task_struct *p, bool preempt) { struct task_struct *curr = current; struct rq *rq, *p_rq; unsigned long flags; - bool yielded = 0; + int yielded = 0; local_irq_save(flags); rq = this_rq(); again: p_rq = task_rq(p); + /* + * If we're the only runnable task on the rq and target rq also + * has only one task, there's absolutely no point in yielding. + */ + if (rq->nr_running == 1 && p_rq->nr_running == 1) { + yielded = -ESRCH; + goto out_irq; + } + double_rq_lock(rq, p_rq); - while (task_rq(p) != p_rq) { + if (task_rq(p) != p_rq) { double_rq_unlock(rq, p_rq); goto again; } if (!curr->sched_class->yield_to_task) - goto out; + goto out_unlock; if (curr->sched_class != p->sched_class) - goto out; + goto out_unlock; if (task_running(p_rq, p) || p->state) - goto out; + goto out_unlock; yielded = curr->sched_class->yield_to_task(rq, p, preempt); if (yielded) { @@ -4607,20 +4286,14 @@ again: */ if (preempt && rq != p_rq) resched_task(p_rq->curr); - } else { - /* - * We might have set it in task_yield_fair(), but are - * not going to schedule(), so don't want to skip - * the next update. - */ - rq->skip_clock_update = 0; } -out: +out_unlock: double_rq_unlock(rq, p_rq); +out_irq: local_irq_restore(flags); - if (yielded) + if (yielded > 0) schedule(); return yielded; @@ -4666,8 +4339,9 @@ long __sched io_schedule_timeout(long timeout) * sys_sched_get_priority_max - return maximum RT priority. * @policy: scheduling class. * - * this syscall returns the maximum rt_priority that can be used - * by a given scheduling class. + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. */ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) { @@ -4678,6 +4352,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) case SCHED_RR: ret = MAX_USER_RT_PRIO-1; break; + case SCHED_DEADLINE: case SCHED_NORMAL: case SCHED_BATCH: case SCHED_IDLE: @@ -4691,8 +4366,9 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) * sys_sched_get_priority_min - return minimum RT priority. * @policy: scheduling class. * - * this syscall returns the minimum rt_priority that can be used - * by a given scheduling class. + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. */ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) { @@ -4703,6 +4379,7 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) case SCHED_RR: ret = 1; break; + case SCHED_DEADLINE: case SCHED_NORMAL: case SCHED_BATCH: case SCHED_IDLE: @@ -4718,6 +4395,9 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) * * this syscall writes the default timeslice value of a given process * into the user-space timespec buffer. A value of '0' means infinity. + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. */ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, struct timespec __user *, interval) @@ -4743,7 +4423,9 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, goto out_unlock; rq = task_rq_lock(p, &flags); - time_slice = p->sched_class->get_rr_interval(rq, p); + time_slice = 0; + if (p->sched_class->get_rr_interval) + time_slice = p->sched_class->get_rr_interval(rq, p); task_rq_unlock(rq, p, &flags); rcu_read_unlock(); @@ -4761,6 +4443,7 @@ static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; void sched_show_task(struct task_struct *p) { unsigned long free = 0; + int ppid; unsigned state; state = p->state ? __ffs(p->state) + 1 : 0; @@ -4780,10 +4463,14 @@ void sched_show_task(struct task_struct *p) #ifdef CONFIG_DEBUG_STACK_USAGE free = stack_not_used(p); #endif + rcu_read_lock(); + ppid = task_pid_nr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, - task_pid_nr(p), task_pid_nr(rcu_dereference(p->real_parent)), + task_pid_nr(p), ppid, (unsigned long)task_thread_info(p)->flags); + print_worker_info(KERN_INFO, p); show_stack(p, NULL); } @@ -4822,7 +4509,7 @@ void show_state_filter(unsigned long state_filter) debug_show_all_locks(); } -void __cpuinit init_idle_bootup_task(struct task_struct *idle) +void init_idle_bootup_task(struct task_struct *idle) { idle->sched_class = &idle_sched_class; } @@ -4835,14 +4522,14 @@ void __cpuinit init_idle_bootup_task(struct task_struct *idle) * NOTE: this function does not set the idle thread's NEED_RESCHED * flag, to make booting more robust. */ -void __cpuinit init_idle(struct task_struct *idle, int cpu) +void init_idle(struct task_struct *idle, int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long flags; raw_spin_lock_irqsave(&rq->lock, flags); - __sched_fork(idle); + __sched_fork(0, idle); idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); @@ -4862,19 +4549,21 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->curr = rq->idle = idle; + idle->on_rq = 1; #if defined(CONFIG_SMP) idle->on_cpu = 1; #endif raw_spin_unlock_irqrestore(&rq->lock, flags); /* Set the preempt count _outside_ the spinlocks! */ - task_thread_info(idle)->preempt_count = 0; + init_idle_preempt_count(idle, cpu); /* * The idle tasks have their own, simple scheduling class: */ idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); + vtime_init_idle(idle, cpu); #if defined(CONFIG_SMP) sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); #endif @@ -4887,7 +4576,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) p->sched_class->set_cpus_allowed(p, new_mask); cpumask_copy(&p->cpus_allowed, new_mask); - p->rt.nr_cpus_allowed = cpumask_weight(new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); } /* @@ -4930,11 +4619,6 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) goto out; } - if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) { - ret = -EINVAL; - goto out; - } - do_set_cpus_allowed(p, new_mask); /* Can the task run on the task's current CPU? If so, we're done */ @@ -5006,6 +4690,54 @@ fail: return ret; } +#ifdef CONFIG_NUMA_BALANCING +/* Migrate current task p to target_cpu */ +int migrate_task_to(struct task_struct *p, int target_cpu) +{ + struct migration_arg arg = { p, target_cpu }; + int curr_cpu = task_cpu(p); + + if (curr_cpu == target_cpu) + return 0; + + if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p))) + return -EINVAL; + + /* TODO: This is not properly updating schedstats */ + + trace_sched_move_numa(p, curr_cpu, target_cpu); + return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg); +} + +/* + * Requeue a task on a given node and accurately track the number of NUMA + * tasks on the runqueues + */ +void sched_setnuma(struct task_struct *p, int nid) +{ + struct rq *rq; + unsigned long flags; + bool on_rq, running; + + rq = task_rq_lock(p, &flags); + on_rq = p->on_rq; + running = task_current(rq, p); + + if (on_rq) + dequeue_task(rq, p, 0); + if (running) + p->sched_class->put_prev_task(rq, p); + + p->numa_preferred_nid = nid; + + if (running) + p->sched_class->set_curr_task(rq); + if (on_rq) + enqueue_task(rq, p, 0); + task_rq_unlock(rq, p, &flags); +} +#endif + /* * migration_cpu_stop - this will be executed by a highprio stopper thread * and performs thread migration by bumping thread off CPU then @@ -5037,35 +4769,43 @@ void idle_task_exit(void) BUG_ON(cpu_online(smp_processor_id())); - if (mm != &init_mm) + if (mm != &init_mm) { switch_mm(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } mmdrop(mm); } /* - * While a dead CPU has no uninterruptible tasks queued at this point, - * it might still have a nonzero ->nr_uninterruptible counter, because - * for performance reasons the counter is not stricly tracking tasks to - * their home CPUs. So we just add the counter to another CPU's counter, - * to keep the global sum constant after CPU-down: + * Since this CPU is going 'away' for a while, fold any nr_active delta + * we might have. Assumes we're called after migrate_tasks() so that the + * nr_active count is stable. + * + * Also see the comment "Global load-average calculations". */ -static void migrate_nr_uninterruptible(struct rq *rq_src) +static void calc_load_migrate(struct rq *rq) { - struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); - - rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; - rq_src->nr_uninterruptible = 0; + long delta = calc_load_fold_active(rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks); } -/* - * remove the tasks which were accounted by rq from calc_load_tasks. - */ -static void calc_global_load_remove(struct rq *rq) +static void put_prev_task_fake(struct rq *rq, struct task_struct *prev) { - atomic_long_sub(rq->calc_load_active, &calc_load_tasks); - rq->calc_load_active = 0; } +static const struct sched_class fake_sched_class = { + .put_prev_task = put_prev_task_fake, +}; + +static struct task_struct fake_task = { + /* + * Avoid pull_{rt,dl}_task() + */ + .prio = MAX_PRIO + 1, + .sched_class = &fake_sched_class, +}; + /* * Migrate all tasks from the rq, sleeping tasks will be migrated by * try_to_wake_up()->select_task_rq(). @@ -5091,8 +4831,12 @@ static void migrate_tasks(unsigned int dead_cpu) */ rq->stop = NULL; - /* Ensure any throttled groups are reachable by pick_next_task */ - unthrottle_offline_cfs_rqs(rq); + /* + * put_prev_task() and pick_next_task() sched + * class method both need to have an up-to-date + * value of rq->clock[_task] + */ + update_rq_clock(rq); for ( ; ; ) { /* @@ -5102,7 +4846,7 @@ static void migrate_tasks(unsigned int dead_cpu) if (rq->nr_running == 1) break; - next = pick_next_task(rq); + next = pick_next_task(rq, &fake_task); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); @@ -5168,57 +4912,69 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) *tablep = NULL; } +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler) + umode_t mode, proc_handler *proc_handler, + bool load_idx) { entry->procname = procname; entry->data = data; entry->maxlen = maxlen; entry->mode = mode; entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } } static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { - struct ctl_table *table = sd_alloc_ctl_entry(13); + struct ctl_table *table = sd_alloc_ctl_entry(14); if (table == NULL) return NULL; set_table_entry(&table[0], "min_interval", &sd->min_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[1], "max_interval", &sd->max_interval, - sizeof(long), 0644, proc_doulongvec_minmax); + sizeof(long), 0644, proc_doulongvec_minmax, false); set_table_entry(&table[2], "busy_idx", &sd->busy_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[3], "idle_idx", &sd->idle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[5], "wake_idx", &sd->wake_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, true); set_table_entry(&table[7], "busy_factor", &sd->busy_factor, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[9], "cache_nice_tries", &sd->cache_nice_tries, - sizeof(int), 0644, proc_dointvec_minmax); + sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[10], "flags", &sd->flags, - sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[11], "name", sd->name, - CORENAME_MAX_SIZE, 0444, proc_dostring); - /* &table[12] is terminator */ + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring, false); + /* &table[13] is terminator */ return table; } -static ctl_table *sd_alloc_ctl_cpu_table(int cpu) +static struct ctl_table *sd_alloc_ctl_cpu_table(int cpu) { struct ctl_table *entry, *table; struct sched_domain *sd; @@ -5320,7 +5076,7 @@ static void set_rq_offline(struct rq *rq) * migration_call - callback that gets triggered when a CPU is added. * Here we can start up the necessary migration thread for the new CPU. */ -static int __cpuinit +static int migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { int cpu = (long)hcpu; @@ -5356,9 +5112,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_tasks(cpu); BUG_ON(rq->nr_running != 1); /* the migration thread */ raw_spin_unlock_irqrestore(&rq->lock, flags); + break; - migrate_nr_uninterruptible(rq); - calc_global_load_remove(rq); + case CPU_DEAD: + calc_load_migrate(rq); break; #endif } @@ -5373,16 +5130,25 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) * happens before everything else. This has to be lower priority than * the notifier in the perf_event subsystem, though. */ -static struct notifier_block __cpuinitdata migration_notifier = { +static struct notifier_block migration_notifier = { .notifier_call = migration_call, .priority = CPU_PRI_MIGRATION, }; -static int __cpuinit sched_cpu_active(struct notifier_block *nfb, +static void __cpuinit set_cpu_rq_start_time(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + rq->age_stamp = sched_clock_cpu(cpu); +} + +static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { - case CPU_ONLINE: + case CPU_STARTING: + set_cpu_rq_start_time(); + return NOTIFY_OK; case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -5391,16 +5157,34 @@ static int __cpuinit sched_cpu_active(struct notifier_block *nfb, } } -static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, +static int sched_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { + unsigned long flags; + long cpu = (long)hcpu; + switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: - set_cpu_active((long)hcpu, false); + set_cpu_active(cpu, false); + + /* explicitly allow suspend */ + if (!(action & CPU_TASKS_FROZEN)) { + struct dl_bw *dl_b = dl_bw_of(cpu); + bool overflow; + int cpus; + + raw_spin_lock_irqsave(&dl_b->lock, flags); + cpus = dl_bw_cpus(cpu); + overflow = __dl_overflow(dl_b, cpus, 0, 0); + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + if (overflow) + return notifier_from_errno(-EBUSY); + } return NOTIFY_OK; - default: - return NOTIFY_DONE; } + + return NOTIFY_DONE; } static int __init migration_init(void) @@ -5429,15 +5213,20 @@ static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ #ifdef CONFIG_SCHED_DEBUG -static __read_mostly int sched_domain_debug_enabled; +static __read_mostly int sched_debug_enabled; -static int __init sched_domain_debug_setup(char *str) +static int __init sched_debug_setup(char *str) { - sched_domain_debug_enabled = 1; + sched_debug_enabled = 1; return 0; } -early_param("sched_debug", sched_domain_debug_setup); +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, struct cpumask *groupmask) @@ -5477,10 +5266,14 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!group->sgp->power) { + /* + * Even though we initialize ->capacity to something semi-sane, + * we leave capacity_orig unset. This allows us to detect if + * domain iteration is still funny without causing /0 traps. + */ + if (!group->sgc->capacity_orig) { printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_power not " - "set\n"); + printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n"); break; } @@ -5490,7 +5283,8 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (cpumask_intersects(groupmask, sched_group_cpus(group))) { + if (!(sd->flags & SD_OVERLAP) && + cpumask_intersects(groupmask, sched_group_cpus(group))) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: repeated CPUs\n"); break; @@ -5501,9 +5295,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); - if (group->sgp->power != SCHED_POWER_SCALE) { - printk(KERN_CONT " (cpu_power = %d)", - group->sgp->power); + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { + printk(KERN_CONT " (cpu_capacity = %d)", + group->sgc->capacity); } group = group->next; @@ -5524,7 +5318,7 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) { int level = 0; - if (!sched_domain_debug_enabled) + if (!sched_debug_enabled) return; if (!sd) { @@ -5545,6 +5339,10 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) } #else /* !CONFIG_SCHED_DEBUG */ # define sched_domain_debug(sd, cpu) do { } while (0) +static inline bool sched_debug(void) +{ + return false; +} #endif /* CONFIG_SCHED_DEBUG */ static int sd_degenerate(struct sched_domain *sd) @@ -5557,8 +5355,9 @@ static int sd_degenerate(struct sched_domain *sd) SD_BALANCE_NEWIDLE | SD_BALANCE_FORK | SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES)) { + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { if (sd->groups != sd->groups->next) return 0; } @@ -5587,8 +5386,10 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_NEWIDLE | SD_BALANCE_FORK | SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES); + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -5603,6 +5404,8 @@ static void free_rootdomain(struct rcu_head *rcu) struct root_domain *rd = container_of(rcu, struct root_domain, rcu); cpupri_cleanup(&rd->cpupri); + cpudl_cleanup(&rd->cpudl); + free_cpumask_var(rd->dlo_mask); free_cpumask_var(rd->rto_mask); free_cpumask_var(rd->online); free_cpumask_var(rd->span); @@ -5625,7 +5428,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) cpumask_clear_cpu(rq->cpu, old_rd->span); /* - * If we dont want to free the old_rt yet then + * If we dont want to free the old_rd yet then * set old_rd to NULL to skip the freeing later * in this function: */ @@ -5654,8 +5457,14 @@ static int init_rootdomain(struct root_domain *rd) goto out; if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; - if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) goto free_online; + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_dlo_mask; + + init_dl_bw(&rd->dl_bw); + if (cpudl_init(&rd->cpudl) != 0) + goto free_dlo_mask; if (cpupri_init(&rd->cpupri) != 0) goto free_rto_mask; @@ -5663,6 +5472,8 @@ static int init_rootdomain(struct root_domain *rd) free_rto_mask: free_cpumask_var(rd->rto_mask); +free_dlo_mask: + free_cpumask_var(rd->dlo_mask); free_online: free_cpumask_var(rd->online); free_span: @@ -5700,7 +5511,7 @@ static struct root_domain *alloc_rootdomain(void) return rd; } -static void free_sched_groups(struct sched_group *sg, int free_sgp) +static void free_sched_groups(struct sched_group *sg, int free_sgc) { struct sched_group *tmp, *first; @@ -5711,8 +5522,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgp) do { tmp = sg->next; - if (free_sgp && atomic_dec_and_test(&sg->sgp->ref)) - kfree(sg->sgp); + if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) + kfree(sg->sgc); kfree(sg); sg = tmp; @@ -5730,7 +5541,7 @@ static void free_sched_domain(struct rcu_head *rcu) if (sd->flags & SD_OVERLAP) { free_sched_groups(sd->groups, 1); } else if (atomic_dec_and_test(&sd->groups->ref)) { - kfree(sd->groups->sgp); + kfree(sd->groups->sgc); kfree(sd->groups); } kfree(sd); @@ -5754,22 +5565,39 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu) * * Also keep a unique ID per domain (we use the first cpu number in * the cpumask of the domain), this allows us to quickly tell if - * two cpus are in the same cache domain, see ttwu_share_cache(). + * two cpus are in the same cache domain, see cpus_share_cache(). */ DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(int, sd_llc_size); DEFINE_PER_CPU(int, sd_llc_id); +DEFINE_PER_CPU(struct sched_domain *, sd_numa); +DEFINE_PER_CPU(struct sched_domain *, sd_busy); +DEFINE_PER_CPU(struct sched_domain *, sd_asym); static void update_top_cache_domain(int cpu) { struct sched_domain *sd; + struct sched_domain *busy_sd = NULL; int id = cpu; + int size = 1; sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); - if (sd) + if (sd) { id = cpumask_first(sched_domain_span(sd)); + size = cpumask_weight(sched_domain_span(sd)); + busy_sd = sd->parent; /* sd_busy */ + } + rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd); rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); + per_cpu(sd_llc_size, cpu) = size; per_cpu(sd_llc_id, cpu) = id; + + sd = lowest_flag_domain(cpu, SD_NUMA); + rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); + + sd = highest_flag_domain(cpu, SD_ASYM_PACKING); + rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); } /* @@ -5792,6 +5620,13 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) tmp->parent = parent->parent; if (parent->parent) parent->parent->child = tmp; + /* + * Transfer SD_PREFER_SIBLING down in case of a + * degenerate parent; the spans match for this + * so the property transfers. + */ + if (parent->flags & SD_PREFER_SIBLING) + tmp->flags |= SD_PREFER_SIBLING; destroy_sched_domain(parent, cpu); } else tmp = tmp->parent; @@ -5828,105 +5663,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -#ifdef CONFIG_NUMA - -/** - * find_next_best_node - find the next node to include in a sched_domain - * @node: node whose sched_domain we're building - * @used_nodes: nodes already in the sched_domain - * - * Find the next node to include in a given scheduling domain. Simply - * finds the closest node not already in the @used_nodes map. - * - * Should use nodemask_t. - */ -static int find_next_best_node(int node, nodemask_t *used_nodes) -{ - int i, n, val, min_val, best_node = -1; - - min_val = INT_MAX; - - for (i = 0; i < nr_node_ids; i++) { - /* Start at @node */ - n = (node + i) % nr_node_ids; - - if (!nr_cpus_node(n)) - continue; - - /* Skip already used nodes */ - if (node_isset(n, *used_nodes)) - continue; - - /* Simple min distance search */ - val = node_distance(node, n); - - if (val < min_val) { - min_val = val; - best_node = n; - } - } - - if (best_node != -1) - node_set(best_node, *used_nodes); - return best_node; -} - -/** - * sched_domain_node_span - get a cpumask for a node's sched_domain - * @node: node whose cpumask we're constructing - * @span: resulting cpumask - * - * Given a node, construct a good cpumask for its sched_domain to span. It - * should be one that prevents unnecessary balancing, but also spreads tasks - * out optimally. - */ -static void sched_domain_node_span(int node, struct cpumask *span) -{ - nodemask_t used_nodes; - int i; - - cpumask_clear(span); - nodes_clear(used_nodes); - - cpumask_or(span, span, cpumask_of_node(node)); - node_set(node, used_nodes); - - for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { - int next_node = find_next_best_node(node, &used_nodes); - if (next_node < 0) - break; - cpumask_or(span, span, cpumask_of_node(next_node)); - } -} - -static const struct cpumask *cpu_node_mask(int cpu) -{ - lockdep_assert_held(&sched_domains_mutex); - - sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask); - - return sched_domains_tmpmask; -} - -static const struct cpumask *cpu_allnodes_mask(int cpu) -{ - return cpu_possible_mask; -} -#endif /* CONFIG_NUMA */ - -static const struct cpumask *cpu_cpu_mask(int cpu) -{ - return cpumask_of_node(cpu_to_node(cpu)); -} - -int sched_smt_power_savings = 0, sched_mc_power_savings = 0; - -struct sd_data { - struct sched_domain **__percpu sd; - struct sched_group **__percpu sg; - struct sched_group_power **__percpu sgp; -}; - struct s_data { struct sched_domain ** __percpu sd; struct root_domain *rd; @@ -5939,19 +5675,43 @@ enum s_alloc { sa_none, }; -struct sched_domain_topology_level; +/* + * Build an iteration mask that can exclude certain CPUs from the upwards + * domain traversal. + * + * Asymmetric node setups can result in situations where the domain tree is of + * unequal depth, make sure to skip domains that already cover the entire + * range. + * + * In that case build_sched_domains() will have terminated the iteration early + * and our sibling sd spans will be empty. Domains should always include the + * cpu they're built on, so check that. + * + */ +static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) +{ + const struct cpumask *span = sched_domain_span(sd); + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; -typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu); -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); + for_each_cpu(i, span) { + sibling = *per_cpu_ptr(sdd->sd, i); + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; -#define SDTL_OVERLAP 0x01 + cpumask_set_cpu(i, sched_group_mask(sg)); + } +} -struct sched_domain_topology_level { - sched_domain_init_f init; - sched_domain_mask_f mask; - int flags; - struct sd_data data; -}; +/* + * Return the canonical balance cpu for this group, this is the first cpu + * of this group that's also in the iteration mask. + */ +int group_balance_cpu(struct sched_group *sg) +{ + return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); +} static int build_overlap_sched_groups(struct sched_domain *sd, int cpu) @@ -5971,6 +5731,12 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) if (cpumask_test_cpu(i, covered)) continue; + child = *per_cpu_ptr(sdd->sd, i); + + /* See the comment near build_group_mask(). */ + if (!cpumask_test_cpu(i, sched_domain_span(child))) + continue; + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), GFP_KERNEL, cpu_to_node(cpu)); @@ -5978,8 +5744,6 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) goto fail; sg_span = sched_group_cpus(sg); - - child = *per_cpu_ptr(sdd->sd, i); if (child->child) { child = child->child; cpumask_copy(sg_span, sched_domain_span(child)); @@ -5988,10 +5752,25 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) cpumask_or(covered, covered, sg_span); - sg->sgp = *per_cpu_ptr(sdd->sgp, cpumask_first(sg_span)); - atomic_inc(&sg->sgp->ref); + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) + build_group_mask(sd, sg); - if (cpumask_test_cpu(cpu, sg_span)) + /* + * Initialize sgc->capacity such that even if we mess up the + * domains and no possible iteration will get us here, we won't + * die on a /0 trap. + */ + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + sg->sgc->capacity_orig = sg->sgc->capacity; + + /* + * Make sure the first group of this domain contains the + * canonical balance cpu. Otherwise the sched_domain iteration + * breaks. See update_sg_lb_stats(). + */ + if ((!groups && cpumask_test_cpu(cpu, sg_span)) || + group_balance_cpu(sg) == cpu) groups = sg; if (!first) @@ -6021,8 +5800,8 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) if (sg) { *sg = *per_cpu_ptr(sdd->sg, cpu); - (*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu); - atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */ + (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */ } return cpu; @@ -6031,7 +5810,7 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) /* * build_sched_groups will build a circular linked list of the groups * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_power to 0. + * and ->cpu_capacity to 0. * * Assumes the sched_domain tree is fully constructed */ @@ -6047,7 +5826,7 @@ build_sched_groups(struct sched_domain *sd, int cpu) get_group(cpu, sdd, &sd->groups); atomic_inc(&sd->groups->ref); - if (cpu != cpumask_first(sched_domain_span(sd))) + if (cpu != cpumask_first(span)) return 0; lockdep_assert_held(&sched_domains_mutex); @@ -6057,14 +5836,13 @@ build_sched_groups(struct sched_domain *sd, int cpu) for_each_cpu(i, span) { struct sched_group *sg; - int group = get_group(i, sdd, &sg); - int j; + int group, j; if (cpumask_test_cpu(i, covered)) continue; - cpumask_clear(sched_group_cpus(sg)); - sg->sgp->power = 0; + group = get_group(i, sdd, &sg); + cpumask_setall(sched_group_mask(sg)); for_each_cpu(j, span) { if (get_group(j, sdd, NULL) != group) @@ -6086,36 +5864,31 @@ build_sched_groups(struct sched_domain *sd, int cpu) } /* - * Initialize sched groups cpu_power. + * Initialize sched groups cpu_capacity. * - * cpu_power indicates the capacity of sched group, which is used while + * cpu_capacity indicates the capacity of sched group, which is used while * distributing the load between different sched groups in a sched domain. - * Typically cpu_power for all the groups in a sched domain will be same unless - * there are asymmetries in the topology. If there are asymmetries, group - * having more cpu_power will pickup more load compared to the group having - * less cpu_power. + * Typically cpu_capacity for all the groups in a sched domain will be same + * unless there are asymmetries in the topology. If there are asymmetries, + * group having more cpu_capacity will pickup more load compared to the + * group having less cpu_capacity. */ -static void init_sched_groups_power(int cpu, struct sched_domain *sd) +static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) { struct sched_group *sg = sd->groups; - WARN_ON(!sd || !sg); + WARN_ON(!sg); do { sg->group_weight = cpumask_weight(sched_group_cpus(sg)); sg = sg->next; } while (sg != sd->groups); - if (cpu != group_first_cpu(sg)) + if (cpu != group_balance_cpu(sg)) return; - update_group_power(sd, cpu); - atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight); -} - -int __weak arch_sd_sibling_asym_packing(void) -{ - return 0*SD_ASYM_PACKING; + update_group_capacity(sd, cpu); + atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight); } /* @@ -6123,48 +5896,13 @@ int __weak arch_sd_sibling_asym_packing(void) * Non-inlined to reduce accumulated stack pressure in build_sched_domains() */ -#ifdef CONFIG_SCHED_DEBUG -# define SD_INIT_NAME(sd, type) sd->name = #type -#else -# define SD_INIT_NAME(sd, type) do { } while (0) -#endif - -#define SD_INIT_FUNC(type) \ -static noinline struct sched_domain * \ -sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ -{ \ - struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \ - *sd = SD_##type##_INIT; \ - SD_INIT_NAME(sd, type); \ - sd->private = &tl->data; \ - return sd; \ -} - -SD_INIT_FUNC(CPU) -#ifdef CONFIG_NUMA - SD_INIT_FUNC(ALLNODES) - SD_INIT_FUNC(NODE) -#endif -#ifdef CONFIG_SCHED_SMT - SD_INIT_FUNC(SIBLING) -#endif -#ifdef CONFIG_SCHED_MC - SD_INIT_FUNC(MC) -#endif -#ifdef CONFIG_SCHED_BOOK - SD_INIT_FUNC(BOOK) -#endif - static int default_relax_domain_level = -1; int sched_domain_level_max; static int __init setup_relax_domain_level(char *str) { - unsigned long val; - - val = simple_strtoul(str, NULL, 0); - if (val < sched_domain_level_max) - default_relax_domain_level = val; + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); return 1; } @@ -6241,46 +5979,399 @@ static void claim_allocations(int cpu, struct sched_domain *sd) if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) *per_cpu_ptr(sdd->sg, cpu) = NULL; - if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref)) - *per_cpu_ptr(sdd->sgp, cpu) = NULL; + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; } -#ifdef CONFIG_SCHED_SMT -static const struct cpumask *cpu_smt_mask(int cpu) +#ifdef CONFIG_NUMA +static int sched_domains_numa_levels; +static int *sched_domains_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; +#endif + +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUCAPACITY - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) + +static struct sched_domain * +sd_init(struct sched_domain_topology_level *tl, int cpu) { - return topology_thread_cpumask(cpu); -} + struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 125, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, + .newidle_idx = 0, + .wake_idx = 0, + .forkexec_idx = 0, + + .flags = 1*SD_LOAD_BALANCE + | 1*SD_BALANCE_NEWIDLE + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK + | 0*SD_BALANCE_WAKE + | 1*SD_WAKE_AFFINE + | 0*SD_SHARE_CPUCAPACITY + | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | 0*SD_NUMA + | sd_flags + , + + .last_balance = jiffies, + .balance_interval = sd_weight, + .smt_gain = 0, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, #endif + }; + + /* + * Convert topological properties into behaviour. + */ + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; + + return sd; +} /* * Topology list, bottom-up. */ static struct sched_domain_topology_level default_topology[] = { #ifdef CONFIG_SCHED_SMT - { sd_init_SIBLING, cpu_smt_mask, }, + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, #endif #ifdef CONFIG_SCHED_MC - { sd_init_MC, cpu_coregroup_mask, }, -#endif -#ifdef CONFIG_SCHED_BOOK - { sd_init_BOOK, cpu_book_mask, }, -#endif - { sd_init_CPU, cpu_cpu_mask, }, -#ifdef CONFIG_NUMA - { sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, }, - { sd_init_ALLNODES, cpu_allnodes_mask, }, + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, #endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, { NULL, }, }; -static struct sched_domain_topology_level *sched_domain_topology = default_topology; +struct sched_domain_topology_level *sched_domain_topology = default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_numa_warn(const char *str) +{ + static int done = false; + int i,j; + + if (done) + return; + + done = true; + + printk(KERN_WARNING "ERROR: %s\n\n", str); + + for (i = 0; i < nr_node_ids; i++) { + printk(KERN_WARNING " "); + for (j = 0; j < nr_node_ids; j++) + printk(KERN_CONT "%02d ", node_distance(i,j)); + printk(KERN_CONT "\n"); + } + printk(KERN_WARNING "\n"); +} + +static bool find_numa_distance(int distance) +{ + int i; + + if (distance == node_distance(0, 0)) + return true; + + for (i = 0; i < sched_domains_numa_levels; i++) { + if (sched_domains_numa_distance[i] == distance) + return true; + } + + return false; +} + +static void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + for (k = 0; k < nr_node_ids; k++) { + int distance = node_distance(i, k); + + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + + /* + * While not a strong assumption it would be nice to know + * about cases where if node A is connected to B, B is not + * equally connected to A. + */ + if (sched_debug() && node_distance(k, i) != distance) + sched_numa_warn("Node-distance not symmetric"); + + if (sched_debug() && i && !find_numa_distance(distance)) + sched_numa_warn("Node-0 not representative"); + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + + /* + * In case of sched_debug() we verify the above assumption. + */ + if (!sched_debug()) + break; + } + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_numa_distance[] array includes the actual distance + * numbers. + */ + + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * cpus of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for (k = 0; k < nr_node_ids; k++) { + if (node_distance(j, k) > sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; + + /* + * .. and append 'j' levels of NUMA goodness. + */ + for (j = 0; j < level; i++, j++) { + tl[i] = (struct sched_domain_topology_level){ + .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, + .flags = SDTL_OVERLAP, + .numa_level = j, + SD_INIT_NAME(NUMA) + }; + } + + sched_domain_topology = tl; + + sched_domains_numa_levels = level; +} + +static void sched_domains_numa_masks_set(int cpu) +{ + int i, j; + int node = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +static void sched_domains_numa_masks_clear(int cpu) +{ + int i, j; + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +/* + * Update sched_domains_numa_masks[level][node] array when new cpus + * are onlined. + */ +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + sched_domains_numa_masks_set(cpu); + break; + + case CPU_DEAD: + sched_domains_numa_masks_clear(cpu); + break; + + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} +#else +static inline void sched_init_numa(void) +{ +} + +static int sched_domains_numa_masks_update(struct notifier_block *nfb, + unsigned long action, + void *hcpu) +{ + return 0; +} +#endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) { struct sched_domain_topology_level *tl; int j; - for (tl = sched_domain_topology; tl->init; tl++) { + for_each_sd_topology(tl) { struct sd_data *sdd = &tl->data; sdd->sd = alloc_percpu(struct sched_domain *); @@ -6291,14 +6382,14 @@ static int __sdt_alloc(const struct cpumask *cpu_map) if (!sdd->sg) return -ENOMEM; - sdd->sgp = alloc_percpu(struct sched_group_power *); - if (!sdd->sgp) + sdd->sgc = alloc_percpu(struct sched_group_capacity *); + if (!sdd->sgc) return -ENOMEM; for_each_cpu(j, cpu_map) { struct sched_domain *sd; struct sched_group *sg; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); @@ -6312,14 +6403,16 @@ static int __sdt_alloc(const struct cpumask *cpu_map) if (!sg) return -ENOMEM; + sg->next = sg; + *per_cpu_ptr(sdd->sg, j) = sg; - sgp = kzalloc_node(sizeof(struct sched_group_power), + sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); - if (!sgp) + if (!sgc) return -ENOMEM; - *per_cpu_ptr(sdd->sgp, j) = sgp; + *per_cpu_ptr(sdd->sgc, j) = sgc; } } @@ -6331,40 +6424,49 @@ static void __sdt_free(const struct cpumask *cpu_map) struct sched_domain_topology_level *tl; int j; - for (tl = sched_domain_topology; tl->init; tl++) { + for_each_sd_topology(tl) { struct sd_data *sdd = &tl->data; for_each_cpu(j, cpu_map) { - struct sched_domain *sd = *per_cpu_ptr(sdd->sd, j); - if (sd && (sd->flags & SD_OVERLAP)) - free_sched_groups(sd->groups, 0); - kfree(*per_cpu_ptr(sdd->sd, j)); - kfree(*per_cpu_ptr(sdd->sg, j)); - kfree(*per_cpu_ptr(sdd->sgp, j)); + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + + if (sdd->sg) + kfree(*per_cpu_ptr(sdd->sg, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); } free_percpu(sdd->sd); + sdd->sd = NULL; free_percpu(sdd->sg); - free_percpu(sdd->sgp); + sdd->sg = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; } } struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, - struct s_data *d, const struct cpumask *cpu_map, - struct sched_domain_attr *attr, struct sched_domain *child, - int cpu) + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *child, int cpu) { - struct sched_domain *sd = tl->init(tl, cpu); + struct sched_domain *sd = sd_init(tl, cpu); if (!sd) return child; - set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); if (child) { sd->level = child->level + 1; sched_domain_level_max = max(sched_domain_level_max, sd->level); child->parent = sd; + sd->child = child; } - sd->child = child; + set_domain_attribute(sd, attr); return sd; } @@ -6376,7 +6478,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, static int build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) { - enum s_alloc alloc_state = sa_none; + enum s_alloc alloc_state; struct sched_domain *sd; struct s_data d; int i, ret = -ENOMEM; @@ -6390,18 +6492,15 @@ static int build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_topology_level *tl; sd = NULL; - for (tl = sched_domain_topology; tl->init; tl++) { - sd = build_sched_domain(tl, &d, cpu_map, attr, sd, i); + for_each_sd_topology(tl) { + sd = build_sched_domain(tl, cpu_map, attr, sd, i); + if (tl == sched_domain_topology) + *per_cpu_ptr(d.sd, i) = sd; if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) sd->flags |= SD_OVERLAP; if (cpumask_equal(cpu_map, sched_domain_span(sd))) break; } - - while (sd->child) - sd = sd->child; - - *per_cpu_ptr(d.sd, i) = sd; } /* Build the groups for the domains */ @@ -6418,14 +6517,14 @@ static int build_sched_domains(const struct cpumask *cpu_map, } } - /* Calculate CPU power for physical packages and nodes */ + /* Calculate CPU capacity for physical packages and nodes */ for (i = nr_cpumask_bits-1; i >= 0; i--) { if (!cpumask_test_cpu(i, cpu_map)) continue; for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { claim_allocations(i, sd); - init_sched_groups_power(i, sd); + init_sched_groups_capacity(i, sd); } } @@ -6460,7 +6559,7 @@ static cpumask_var_t fallback_doms; * cpu core maps. It is supposed to return 1 if the topology changed * or 0 if it stayed the same. */ -int __attribute__((weak)) arch_update_cpu_topology(void) +int __weak arch_update_cpu_topology(void) { return 0; } @@ -6505,7 +6604,6 @@ static int init_sched_domains(const struct cpumask *cpu_map) if (!doms_cur) doms_cur = &fallback_doms; cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); - dattr_cur = NULL; err = build_sched_domains(doms_cur[0], NULL); register_sched_domain_sysctl(); @@ -6597,8 +6695,9 @@ match1: ; } + n = ndoms_cur; if (doms_new == NULL) { - ndoms_cur = 0; + n = 0; doms_new = &fallback_doms; cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); WARN_ON_ONCE(dattr_new); @@ -6606,7 +6705,7 @@ match1: /* Build new domains */ for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < ndoms_cur && !new_topology; j++) { + for (j = 0; j < n && !new_topology; j++) { if (cpumask_equal(doms_new[i], doms_cur[j]) && dattrs_equal(dattr_new, i, dattr_cur, j)) goto match2; @@ -6630,125 +6729,66 @@ match2: mutex_unlock(&sched_domains_mutex); } -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) -static void reinit_sched_domains(void) -{ - get_online_cpus(); - - /* Destroy domains first to force the rebuild */ - partition_sched_domains(0, NULL, NULL); - - rebuild_sched_domains(); - put_online_cpus(); -} - -static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) -{ - unsigned int level = 0; - - if (sscanf(buf, "%u", &level) != 1) - return -EINVAL; - - /* - * level is always be positive so don't check for - * level < POWERSAVINGS_BALANCE_NONE which is 0 - * What happens on 0 or 1 byte write, - * need to check for count as well? - */ - - if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS) - return -EINVAL; - - if (smt) - sched_smt_power_savings = level; - else - sched_mc_power_savings = level; - - reinit_sched_domains(); - - return count; -} - -#ifdef CONFIG_SCHED_MC -static ssize_t sched_mc_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_mc_power_savings); -} -static ssize_t sched_mc_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 0); -} -static DEVICE_ATTR(sched_mc_power_savings, 0644, - sched_mc_power_savings_show, - sched_mc_power_savings_store); -#endif - -#ifdef CONFIG_SCHED_SMT -static ssize_t sched_smt_power_savings_show(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%u\n", sched_smt_power_savings); -} -static ssize_t sched_smt_power_savings_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t count) -{ - return sched_power_savings_store(buf, count, 1); -} -static DEVICE_ATTR(sched_smt_power_savings, 0644, - sched_smt_power_savings_show, - sched_smt_power_savings_store); -#endif - -int __init sched_create_sysfs_power_savings_entries(struct device *dev) -{ - int err = 0; - -#ifdef CONFIG_SCHED_SMT - if (smt_capable()) - err = device_create_file(dev, &dev_attr_sched_smt_power_savings); -#endif -#ifdef CONFIG_SCHED_MC - if (!err && mc_capable()) - err = device_create_file(dev, &dev_attr_sched_mc_power_savings); -#endif - return err; -} -#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ +static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ /* * Update cpusets according to cpu_active mask. If cpusets are * disabled, cpuset_update_active_cpus() becomes a simple wrapper * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. */ static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action & ~CPU_TASKS_FROZEN) { + switch (action) { + case CPU_ONLINE_FROZEN: + case CPU_DOWN_FAILED_FROZEN: + + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + num_cpus_frozen--; + if (likely(num_cpus_frozen)) { + partition_sched_domains(1, NULL, NULL); + break; + } + + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + case CPU_ONLINE: case CPU_DOWN_FAILED: - cpuset_update_active_cpus(); - return NOTIFY_OK; + cpuset_update_active_cpus(true); + break; default: return NOTIFY_DONE; } + return NOTIFY_OK; } static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, void *hcpu) { - switch (action & ~CPU_TASKS_FROZEN) { + switch (action) { case CPU_DOWN_PREPARE: - cpuset_update_active_cpus(); - return NOTIFY_OK; + cpuset_update_active_cpus(false); + break; + case CPU_DOWN_PREPARE_FROZEN: + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + break; default: return NOTIFY_DONE; } + return NOTIFY_OK; } void __init sched_init_smp(void) @@ -6758,21 +6798,24 @@ void __init sched_init_smp(void) alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); alloc_cpumask_var(&fallback_doms, GFP_KERNEL); - get_online_cpus(); + sched_init_numa(); + + /* + * There's no userspace yet to cause hotplug operations; hence all the + * cpu masks are stable and all blatant races in the below code cannot + * happen. + */ mutex_lock(&sched_domains_mutex); init_sched_domains(cpu_active_mask); cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); if (cpumask_empty(non_isolated_cpus)) cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); mutex_unlock(&sched_domains_mutex); - put_online_cpus(); + hotcpu_notifier(sched_domains_numa_masks_update, CPU_PRI_SCHED_ACTIVE); hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); - /* RT runtime code needs to handle some hotplug events */ - hotcpu_notifier(update_runtime, 0); - init_hrtick(); /* Move init over to a non-isolated CPU */ @@ -6782,6 +6825,7 @@ void __init sched_init_smp(void) free_cpumask_var(non_isolated_cpus); init_sched_rt_class(); + init_sched_dl_class(); } #else void __init sched_init_smp(void) @@ -6800,10 +6844,15 @@ int in_sched_functions(unsigned long addr) } #ifdef CONFIG_CGROUP_SCHED +/* + * Default task group. + * Every task in system belongs to this group at bootup. + */ struct task_group root_task_group; +LIST_HEAD(task_groups); #endif -DECLARE_PER_CPU(cpumask_var_t, load_balance_tmpmask); +DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); void __init sched_init(void) { @@ -6840,19 +6889,21 @@ void __init sched_init(void) #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CPUMASK_OFFSTACK for_each_possible_cpu(i) { - per_cpu(load_balance_tmpmask, i) = (void *)ptr; + per_cpu(load_balance_mask, i) = (void *)ptr; ptr += cpumask_size(); } #endif /* CONFIG_CPUMASK_OFFSTACK */ } + init_rt_bandwidth(&def_rt_bandwidth, + global_rt_period(), global_rt_runtime()); + init_dl_bandwidth(&def_dl_bandwidth, + global_rt_period(), global_rt_runtime()); + #ifdef CONFIG_SMP init_defrootdomain(); #endif - init_rt_bandwidth(&def_rt_bandwidth, - global_rt_period(), global_rt_runtime()); - #ifdef CONFIG_RT_GROUP_SCHED init_rt_bandwidth(&root_task_group.rt_bandwidth, global_rt_period(), global_rt_runtime()); @@ -6866,12 +6917,6 @@ void __init sched_init(void) #endif /* CONFIG_CGROUP_SCHED */ -#ifdef CONFIG_CGROUP_CPUACCT - root_cpuacct.cpustat = &kernel_cpustat; - root_cpuacct.cpuusage = alloc_percpu(u64); - /* Too early, not expected to fail */ - BUG_ON(!root_cpuacct.cpuusage); -#endif for_each_possible_cpu(i) { struct rq *rq; @@ -6882,6 +6927,7 @@ void __init sched_init(void) rq->calc_load_update = jiffies + LOAD_FREQ; init_cfs_rq(&rq->cfs); init_rt_rq(&rq->rt, rq); + init_dl_rq(&rq->dl, rq); #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.shares = ROOT_TASK_GROUP_LOAD; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); @@ -6910,7 +6956,6 @@ void __init sched_init(void) rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; #ifdef CONFIG_RT_GROUP_SCHED - INIT_LIST_HEAD(&rq->leaf_rt_rq_list); init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); #endif @@ -6922,7 +6967,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_power = SCHED_POWER_SCALE; + rq->cpu_capacity = SCHED_CAPACITY_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; @@ -6931,10 +6976,17 @@ void __init sched_init(void) rq->online = 0; rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; + rq->max_idle_balance_cost = sysctl_sched_migration_cost; + + INIT_LIST_HEAD(&rq->cfs_tasks); + rq_attach_root(rq, &def_root_domain); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON rq->nohz_flags = 0; #endif +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = 0; +#endif #endif init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); @@ -6946,10 +6998,6 @@ void __init sched_init(void) INIT_HLIST_HEAD(&init_task.preempt_notifiers); #endif -#ifdef CONFIG_RT_MUTEXES - plist_head_init(&init_task.pi_waiters); -#endif - /* * The boot idle thread does lazy MMU switching as well: */ @@ -6976,6 +7024,8 @@ void __init sched_init(void) /* May be allocated at isolcpus cmdline parse time */ if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + idle_thread_set_boot_cpu(); + set_cpu_rq_start_time(); #endif init_sched_fair_class(); @@ -6995,7 +7045,8 @@ void __might_sleep(const char *file, int line, int preempt_offset) static unsigned long prev_jiffy; /* ratelimiting */ rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ - if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || system_state != SYSTEM_RUNNING || oops_in_progress) return; if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) @@ -7013,6 +7064,13 @@ void __might_sleep(const char *file, int line, int preempt_offset) debug_show_held_locks(current); if (irqs_disabled()) print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif dump_stack(); } EXPORT_SYMBOL(__might_sleep); @@ -7022,13 +7080,16 @@ EXPORT_SYMBOL(__might_sleep); static void normalize_task(struct rq *rq, struct task_struct *p) { const struct sched_class *prev_class = p->sched_class; + struct sched_attr attr = { + .sched_policy = SCHED_NORMAL, + }; int old_prio = p->prio; int on_rq; on_rq = p->on_rq; if (on_rq) dequeue_task(rq, p, 0); - __setscheduler(rq, p, SCHED_NORMAL, 0); + __setscheduler(rq, p, &attr); if (on_rq) { enqueue_task(rq, p, 0); resched_task(rq->curr); @@ -7058,12 +7119,12 @@ void normalize_rt_tasks(void) p->se.statistics.block_start = 0; #endif - if (!rt_task(p)) { + if (!dl_task(p) && !rt_task(p)) { /* * Renice negative nice level userspace * tasks back to 0: */ - if (TASK_NICE(p) < 0 && p->mm) + if (task_nice(p) < 0 && p->mm) set_user_nice(p, 0); continue; } @@ -7098,6 +7159,8 @@ void normalize_rt_tasks(void) * @cpu: the processor in question. * * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + * + * Return: The current task for @cpu. */ struct task_struct *curr_task(int cpu) { @@ -7145,7 +7208,6 @@ static void free_sched_group(struct task_group *tg) struct task_group *sched_create_group(struct task_group *parent) { struct task_group *tg; - unsigned long flags; tg = kzalloc(sizeof(*tg), GFP_KERNEL); if (!tg) @@ -7157,6 +7219,17 @@ struct task_group *sched_create_group(struct task_group *parent) if (!alloc_rt_sched_group(tg, parent)) goto err; + return tg; + +err: + free_sched_group(tg); + return ERR_PTR(-ENOMEM); +} + +void sched_online_group(struct task_group *tg, struct task_group *parent) +{ + unsigned long flags; + spin_lock_irqsave(&task_group_lock, flags); list_add_rcu(&tg->list, &task_groups); @@ -7166,12 +7239,6 @@ struct task_group *sched_create_group(struct task_group *parent) INIT_LIST_HEAD(&tg->children); list_add_rcu(&tg->siblings, &parent->children); spin_unlock_irqrestore(&task_group_lock, flags); - - return tg; - -err: - free_sched_group(tg); - return ERR_PTR(-ENOMEM); } /* rcu callback to free various structures associated with a task group */ @@ -7184,6 +7251,12 @@ static void free_sched_group_rcu(struct rcu_head *rhp) /* Destroy runqueue etc associated with a task group */ void sched_destroy_group(struct task_group *tg) { + /* wait for possible concurrent references to cfs_rqs complete */ + call_rcu(&tg->rcu, free_sched_group_rcu); +} + +void sched_offline_group(struct task_group *tg) +{ unsigned long flags; int i; @@ -7195,9 +7268,6 @@ void sched_destroy_group(struct task_group *tg) list_del_rcu(&tg->list); list_del_rcu(&tg->siblings); spin_unlock_irqrestore(&task_group_lock, flags); - - /* wait for possible concurrent references to cfs_rqs complete */ - call_rcu(&tg->rcu, free_sched_group_rcu); } /* change task's runqueue when it moves between groups. @@ -7207,6 +7277,7 @@ void sched_destroy_group(struct task_group *tg) */ void sched_move_task(struct task_struct *tsk) { + struct task_group *tg; int on_rq, running; unsigned long flags; struct rq *rq; @@ -7221,6 +7292,12 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); + tg = container_of(task_css_check(tsk, cpu_cgrp_id, + lockdep_is_held(&tsk->sighand->siglock)), + struct task_group, css); + tg = autogroup_task_group(tsk, tg); + tsk->sched_task_group = tg; + #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_move_group) tsk->sched_class->task_move_group(tsk, on_rq); @@ -7237,16 +7314,6 @@ void sched_move_task(struct task_struct *tsk) } #endif /* CONFIG_CGROUP_SCHED */ -#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_CFS_BANDWIDTH) -static unsigned long to_ratio(u64 period, u64 runtime) -{ - if (runtime == RUNTIME_INF) - return 1ULL << 20; - - return div64_u64(runtime << 20, period); -} -#endif - #ifdef CONFIG_RT_GROUP_SCHED /* * Ensure that the real time constraints are schedulable. @@ -7375,7 +7442,7 @@ unlock: return err; } -int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) { u64 rt_runtime, rt_period; @@ -7387,7 +7454,7 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } -long sched_group_rt_runtime(struct task_group *tg) +static long sched_group_rt_runtime(struct task_group *tg) { u64 rt_runtime_us; @@ -7399,7 +7466,7 @@ long sched_group_rt_runtime(struct task_group *tg) return rt_runtime_us; } -int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) +static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) { u64 rt_runtime, rt_period; @@ -7412,7 +7479,7 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } -long sched_group_rt_period(struct task_group *tg) +static long sched_group_rt_period(struct task_group *tg) { u64 rt_period_us; @@ -7420,24 +7487,13 @@ long sched_group_rt_period(struct task_group *tg) do_div(rt_period_us, NSEC_PER_USEC); return rt_period_us; } +#endif /* CONFIG_RT_GROUP_SCHED */ +#ifdef CONFIG_RT_GROUP_SCHED static int sched_rt_global_constraints(void) { - u64 runtime, period; int ret = 0; - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - - runtime = global_rt_runtime(); - period = global_rt_period(); - - /* - * Sanity check on the sysctl variables. - */ - if (runtime > period && runtime != RUNTIME_INF) - return -EINVAL; - mutex_lock(&rt_constraints_mutex); read_lock(&tasklist_lock); ret = __rt_schedulable(NULL, 0, 0); @@ -7447,7 +7503,7 @@ static int sched_rt_global_constraints(void) return ret; } -int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) { /* Don't accept realtime tasks when there is no way for them to run */ if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) @@ -7460,17 +7516,7 @@ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) static int sched_rt_global_constraints(void) { unsigned long flags; - int i; - - if (sysctl_sched_rt_period <= 0) - return -EINVAL; - - /* - * There's always some RT tasks in the root group - * -- migration, kstopmachine etc.. - */ - if (sysctl_sched_rt_runtime == 0) - return -EBUSY; + int i, ret = 0; raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); for_each_possible_cpu(i) { @@ -7482,17 +7528,91 @@ static int sched_rt_global_constraints(void) } raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); - return 0; + return ret; } #endif /* CONFIG_RT_GROUP_SCHED */ +static int sched_dl_global_constraints(void) +{ + u64 runtime = global_rt_runtime(); + u64 period = global_rt_period(); + u64 new_bw = to_ratio(period, runtime); + int cpu, ret = 0; + unsigned long flags; + + /* + * Here we want to check the bandwidth not being set to some + * value smaller than the currently allocated bandwidth in + * any of the root_domains. + * + * FIXME: Cycling on all the CPUs is overdoing, but simpler than + * cycling on root_domains... Discussion on different/better + * solutions is welcome! + */ + for_each_possible_cpu(cpu) { + struct dl_bw *dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + if (new_bw < dl_b->total_bw) + ret = -EBUSY; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + + if (ret) + break; + } + + return ret; +} + +static void sched_dl_do_global(void) +{ + u64 new_bw = -1; + int cpu; + unsigned long flags; + + def_dl_bandwidth.dl_period = global_rt_period(); + def_dl_bandwidth.dl_runtime = global_rt_runtime(); + + if (global_rt_runtime() != RUNTIME_INF) + new_bw = to_ratio(global_rt_period(), global_rt_runtime()); + + /* + * FIXME: As above... + */ + for_each_possible_cpu(cpu) { + struct dl_bw *dl_b = dl_bw_of(cpu); + + raw_spin_lock_irqsave(&dl_b->lock, flags); + dl_b->bw = new_bw; + raw_spin_unlock_irqrestore(&dl_b->lock, flags); + } +} + +static int sched_rt_global_validate(void) +{ + if (sysctl_sched_rt_period <= 0) + return -EINVAL; + + if ((sysctl_sched_rt_runtime != RUNTIME_INF) && + (sysctl_sched_rt_runtime > sysctl_sched_rt_period)) + return -EINVAL; + + return 0; +} + +static void sched_rt_do_global(void) +{ + def_rt_bandwidth.rt_runtime = global_rt_runtime(); + def_rt_bandwidth.rt_period = ns_to_ktime(global_rt_period()); +} + int sched_rt_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret; int old_period, old_runtime; static DEFINE_MUTEX(mutex); + int ret; mutex_lock(&mutex); old_period = sysctl_sched_rt_period; @@ -7501,41 +7621,68 @@ int sched_rt_handler(struct ctl_table *table, int write, ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { + ret = sched_rt_global_validate(); + if (ret) + goto undo; + ret = sched_rt_global_constraints(); - if (ret) { - sysctl_sched_rt_period = old_period; - sysctl_sched_rt_runtime = old_runtime; - } else { - def_rt_bandwidth.rt_runtime = global_rt_runtime(); - def_rt_bandwidth.rt_period = - ns_to_ktime(global_rt_period()); - } + if (ret) + goto undo; + + ret = sched_dl_global_constraints(); + if (ret) + goto undo; + + sched_rt_do_global(); + sched_dl_do_global(); + } + if (0) { +undo: + sysctl_sched_rt_period = old_period; + sysctl_sched_rt_runtime = old_runtime; } mutex_unlock(&mutex); return ret; } +int sched_rr_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + ret = proc_dointvec(table, write, buffer, lenp, ppos); + /* make sure that internally we keep jiffies */ + /* also, writing zero resets timeslice to default */ + if (!ret && write) { + sched_rr_timeslice = sched_rr_timeslice <= 0 ? + RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice); + } + mutex_unlock(&mutex); + return ret; +} + #ifdef CONFIG_CGROUP_SCHED -/* return corresponding task_group object of a cgroup */ -static inline struct task_group *cgroup_tg(struct cgroup *cgrp) +static inline struct task_group *css_tg(struct cgroup_subsys_state *css) { - return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id), - struct task_group, css); + return css ? container_of(css, struct task_group, css) : NULL; } static struct cgroup_subsys_state * -cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) +cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { - struct task_group *tg, *parent; + struct task_group *parent = css_tg(parent_css); + struct task_group *tg; - if (!cgrp->parent) { + if (!parent) { /* This is early initialization for the top cgroup */ return &root_task_group.css; } - parent = cgroup_tg(cgrp->parent); tg = sched_create_group(parent); if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); @@ -7543,22 +7690,38 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) return &tg->css; } -static void -cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css->parent); + + if (parent) + sched_online_group(tg, parent); + return 0; +} + +static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); sched_destroy_group(tg); } -static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, +static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + sched_offline_group(tg); +} + +static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *task; - cgroup_taskset_for_each(task, cgrp, tset) { + cgroup_taskset_for_each(task, tset) { #ifdef CONFIG_RT_GROUP_SCHED - if (!sched_rt_can_attach(cgroup_tg(cgrp), task)) + if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; #else /* We don't support RT-tasks being in separate groups */ @@ -7569,18 +7732,18 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, return 0; } -static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, +static void cpu_cgroup_attach(struct cgroup_subsys_state *css, struct cgroup_taskset *tset) { struct task_struct *task; - cgroup_taskset_for_each(task, cgrp, tset) + cgroup_taskset_for_each(task, tset) sched_move_task(task); } -static void -cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cgrp, struct task_struct *task) +static void cpu_cgroup_exit(struct cgroup_subsys_state *css, + struct cgroup_subsys_state *old_css, + struct task_struct *task) { /* * cgroup_exit() is called in the copy_process() failure path. @@ -7594,15 +7757,16 @@ cpu_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp, } #ifdef CONFIG_FAIR_GROUP_SCHED -static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, - u64 shareval) +static int cpu_shares_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 shareval) { - return sched_group_set_shares(cgroup_tg(cgrp), scale_load(shareval)); + return sched_group_set_shares(css_tg(css), scale_load(shareval)); } -static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(css); return (u64) scale_load_down(tg->shares); } @@ -7646,7 +7810,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) runtime_enabled = quota != RUNTIME_INF; runtime_was_enabled = cfs_b->quota != RUNTIME_INF; - account_cfs_bandwidth_used(runtime_enabled, runtime_was_enabled); + /* + * If we need to toggle cfs_bandwidth_used, off->on must occur + * before making related changes, and on->off must occur afterwards + */ + if (runtime_enabled && !runtime_was_enabled) + cfs_bandwidth_usage_inc(); raw_spin_lock_irq(&cfs_b->lock); cfs_b->period = ns_to_ktime(period); cfs_b->quota = quota; @@ -7655,8 +7824,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) /* restart the period timer (if active) to handle new period expiry */ if (runtime_enabled && cfs_b->timer_active) { /* force a reprogram */ - cfs_b->timer_active = 0; - __start_cfs_bandwidth(cfs_b); + __start_cfs_bandwidth(cfs_b, true); } raw_spin_unlock_irq(&cfs_b->lock); @@ -7672,6 +7840,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) unthrottle_cfs_rq(cfs_rq); raw_spin_unlock_irq(&rq->lock); } + if (runtime_was_enabled && !runtime_enabled) + cfs_bandwidth_usage_dec(); out_unlock: mutex_unlock(&cfs_constraints_mutex); @@ -7724,26 +7894,28 @@ long tg_get_cfs_period(struct task_group *tg) return cfs_period_us; } -static s64 cpu_cfs_quota_read_s64(struct cgroup *cgrp, struct cftype *cft) +static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) { - return tg_get_cfs_quota(cgroup_tg(cgrp)); + return tg_get_cfs_quota(css_tg(css)); } -static int cpu_cfs_quota_write_s64(struct cgroup *cgrp, struct cftype *cftype, - s64 cfs_quota_us) +static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css, + struct cftype *cftype, s64 cfs_quota_us) { - return tg_set_cfs_quota(cgroup_tg(cgrp), cfs_quota_us); + return tg_set_cfs_quota(css_tg(css), cfs_quota_us); } -static u64 cpu_cfs_period_read_u64(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) { - return tg_get_cfs_period(cgroup_tg(cgrp)); + return tg_get_cfs_period(css_tg(css)); } -static int cpu_cfs_period_write_u64(struct cgroup *cgrp, struct cftype *cftype, - u64 cfs_period_us) +static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 cfs_period_us) { - return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us); + return tg_set_cfs_period(css_tg(css), cfs_period_us); } struct cfs_schedulable_data { @@ -7824,15 +7996,14 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) return ret; } -static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft, - struct cgroup_map_cb *cb) +static int cpu_stats_show(struct seq_file *sf, void *v) { - struct task_group *tg = cgroup_tg(cgrp); + struct task_group *tg = css_tg(seq_css(sf)); struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; - cb->fill(cb, "nr_periods", cfs_b->nr_periods); - cb->fill(cb, "nr_throttled", cfs_b->nr_throttled); - cb->fill(cb, "throttled_time", cfs_b->throttled_time); + seq_printf(sf, "nr_periods %d\n", cfs_b->nr_periods); + seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled); + seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); return 0; } @@ -7840,26 +8011,28 @@ static int cpu_stats_show(struct cgroup *cgrp, struct cftype *cft, #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED -static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, - s64 val) +static int cpu_rt_runtime_write(struct cgroup_subsys_state *css, + struct cftype *cft, s64 val) { - return sched_group_set_rt_runtime(cgroup_tg(cgrp), val); + return sched_group_set_rt_runtime(css_tg(css), val); } -static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft) +static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css, + struct cftype *cft) { - return sched_group_rt_runtime(cgroup_tg(cgrp)); + return sched_group_rt_runtime(css_tg(css)); } -static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype, - u64 rt_period_us) +static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 rt_period_us) { - return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us); + return sched_group_set_rt_period(css_tg(css), rt_period_us); } -static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) +static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, + struct cftype *cft) { - return sched_group_rt_period(cgroup_tg(cgrp)); + return sched_group_rt_period(css_tg(css)); } #endif /* CONFIG_RT_GROUP_SCHED */ @@ -7884,7 +8057,7 @@ static struct cftype cpu_files[] = { }, { .name = "stat", - .read_map = cpu_stats_show, + .seq_show = cpu_stats_show, }, #endif #ifdef CONFIG_RT_GROUP_SCHED @@ -7899,247 +8072,25 @@ static struct cftype cpu_files[] = { .write_u64 = cpu_rt_period_write_uint, }, #endif + { } /* terminate */ }; -static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) -{ - return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files)); -} - -struct cgroup_subsys cpu_cgroup_subsys = { - .name = "cpu", - .create = cpu_cgroup_create, - .destroy = cpu_cgroup_destroy, +struct cgroup_subsys cpu_cgrp_subsys = { + .css_alloc = cpu_cgroup_css_alloc, + .css_free = cpu_cgroup_css_free, + .css_online = cpu_cgroup_css_online, + .css_offline = cpu_cgroup_css_offline, .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, .exit = cpu_cgroup_exit, - .populate = cpu_cgroup_populate, - .subsys_id = cpu_cgroup_subsys_id, + .base_cftypes = cpu_files, .early_init = 1, }; #endif /* CONFIG_CGROUP_SCHED */ -#ifdef CONFIG_CGROUP_CPUACCT - -/* - * CPU accounting code for task groups. - * - * Based on the work by Paul Menage (menage@google.com) and Balbir Singh - * (balbir@in.ibm.com). - */ - -/* create a new cpu accounting group */ -static struct cgroup_subsys_state *cpuacct_create( - struct cgroup_subsys *ss, struct cgroup *cgrp) -{ - struct cpuacct *ca; - - if (!cgrp->parent) - return &root_cpuacct.css; - - ca = kzalloc(sizeof(*ca), GFP_KERNEL); - if (!ca) - goto out; - - ca->cpuusage = alloc_percpu(u64); - if (!ca->cpuusage) - goto out_free_ca; - - ca->cpustat = alloc_percpu(struct kernel_cpustat); - if (!ca->cpustat) - goto out_free_cpuusage; - - return &ca->css; - -out_free_cpuusage: - free_percpu(ca->cpuusage); -out_free_ca: - kfree(ca); -out: - return ERR_PTR(-ENOMEM); -} - -/* destroy an existing cpu accounting group */ -static void -cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - - free_percpu(ca->cpustat); - free_percpu(ca->cpuusage); - kfree(ca); -} - -static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - u64 data; - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit read safe on 32-bit platforms. - */ - raw_spin_lock_irq(&cpu_rq(cpu)->lock); - data = *cpuusage; - raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - data = *cpuusage; -#endif - - return data; -} - -static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit write safe on 32-bit platforms. - */ - raw_spin_lock_irq(&cpu_rq(cpu)->lock); - *cpuusage = val; - raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - *cpuusage = val; -#endif -} - -/* return total cpu usage (in nanoseconds) of a group */ -static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - u64 totalcpuusage = 0; - int i; - - for_each_present_cpu(i) - totalcpuusage += cpuacct_cpuusage_read(ca, i); - - return totalcpuusage; -} - -static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, - u64 reset) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int err = 0; - int i; - - if (reset) { - err = -EINVAL; - goto out; - } - - for_each_present_cpu(i) - cpuacct_cpuusage_write(ca, i, 0); - -out: - return err; -} - -static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, - struct seq_file *m) -{ - struct cpuacct *ca = cgroup_ca(cgroup); - u64 percpu; - int i; - - for_each_present_cpu(i) { - percpu = cpuacct_cpuusage_read(ca, i); - seq_printf(m, "%llu ", (unsigned long long) percpu); - } - seq_printf(m, "\n"); - return 0; -} - -static const char *cpuacct_stat_desc[] = { - [CPUACCT_STAT_USER] = "user", - [CPUACCT_STAT_SYSTEM] = "system", -}; - -static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, - struct cgroup_map_cb *cb) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int cpu; - s64 val = 0; - - for_each_online_cpu(cpu) { - struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); - val += kcpustat->cpustat[CPUTIME_USER]; - val += kcpustat->cpustat[CPUTIME_NICE]; - } - val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val); - - val = 0; - for_each_online_cpu(cpu) { - struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); - val += kcpustat->cpustat[CPUTIME_SYSTEM]; - val += kcpustat->cpustat[CPUTIME_IRQ]; - val += kcpustat->cpustat[CPUTIME_SOFTIRQ]; - } - - val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); - - return 0; -} - -static struct cftype files[] = { - { - .name = "usage", - .read_u64 = cpuusage_read, - .write_u64 = cpuusage_write, - }, - { - .name = "usage_percpu", - .read_seq_string = cpuacct_percpu_seq_read, - }, - { - .name = "stat", - .read_map = cpuacct_stats_show, - }, -}; - -static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) +void dump_cpu_task(int cpu) { - return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files)); + pr_info("Task dump for CPU %d:\n", cpu); + sched_show_task(cpu_curr(cpu)); } - -/* - * charge this task's execution time to its accounting group. - * - * called with rq->lock held. - */ -void cpuacct_charge(struct task_struct *tsk, u64 cputime) -{ - struct cpuacct *ca; - int cpu; - - if (unlikely(!cpuacct_subsys.active)) - return; - - cpu = task_cpu(tsk); - - rcu_read_lock(); - - ca = task_ca(tsk); - - for (; ca; ca = parent_ca(ca)) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - *cpuusage += cputime; - } - - rcu_read_unlock(); -} - -struct cgroup_subsys cpuacct_subsys = { - .name = "cpuacct", - .create = cpuacct_create, - .destroy = cpuacct_destroy, - .populate = cpuacct_populate, - .subsys_id = cpuacct_subsys_id, -}; -#endif /* CONFIG_CGROUP_CPUACCT */ |