diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/Makefile | 6 | ||||
| -rw-r--r-- | kernel/sched/auto_group.c | 2 | ||||
| -rw-r--r-- | kernel/sched/clock.c | 110 | ||||
| -rw-r--r-- | kernel/sched/completion.c | 299 | ||||
| -rw-r--r-- | kernel/sched/core.c | 2376 | ||||
| -rw-r--r-- | kernel/sched/cpuacct.c | 26 | ||||
| -rw-r--r-- | kernel/sched/cpudeadline.c | 229 | ||||
| -rw-r--r-- | kernel/sched/cpudeadline.h | 33 | ||||
| -rw-r--r-- | kernel/sched/cpupri.c | 16 | ||||
| -rw-r--r-- | kernel/sched/cpupri.h | 2 | ||||
| -rw-r--r-- | kernel/sched/cputime.c | 52 | ||||
| -rw-r--r-- | kernel/sched/deadline.c | 1676 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 82 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 2625 | ||||
| -rw-r--r-- | kernel/sched/features.h | 27 | ||||
| -rw-r--r-- | kernel/sched/idle.c | 273 | ||||
| -rw-r--r-- | kernel/sched/idle_task.c | 27 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 251 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 307 | ||||
| -rw-r--r-- | kernel/sched/stats.c | 2 | ||||
| -rw-r--r-- | kernel/sched/stats.h | 51 | ||||
| -rw-r--r-- | kernel/sched/stop_task.c | 23 | ||||
| -rw-r--r-- | kernel/sched/wait.c | 504 |
23 files changed, 7229 insertions, 1770 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 54adcf35f49..ab32b7b0db5 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -11,8 +11,10 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y) CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif -obj-y += core.o proc.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o -obj-$(CONFIG_SMP) += cpupri.o +obj-y += core.o proc.o clock.o cputime.o +obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o +obj-y += wait.o completion.o idle.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o diff --git a/kernel/sched/auto_group.c b/kernel/sched/auto_group.c index 4a073539c58..e73efba9830 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/auto_group.c @@ -203,7 +203,7 @@ int proc_sched_autogroup_set_nice(struct task_struct *p, int nice) struct autogroup *ag; int err; - if (nice < -20 || nice > 19) + if (nice < MIN_NICE || nice > MAX_NICE) return -EINVAL; err = security_task_setnice(current, nice); diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c3ae1446461..3ef6451e972 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -26,9 +26,10 @@ * at 0 on boot (but people really shouldn't rely on that). * * cpu_clock(i) -- can be used from any context, including NMI. - * sched_clock_cpu(i) -- must be used with local IRQs disabled (implied by NMI) * local_clock() -- is cpu_clock() on the current cpu. * + * sched_clock_cpu(i) + * * How: * * The implementation either uses sched_clock() when @@ -50,15 +51,6 @@ * Furthermore, explicit sleep and wakeup hooks allow us to account for time * that is otherwise invisible (TSC gets stopped). * - * - * Notes: - * - * The !IRQ-safetly of sched_clock() and sched_clock_cpu() comes from things - * like cpufreq interrupts that can change the base clock (TSC) multiplier - * and cause funny jumps in time -- although the filtering provided by - * sched_clock_cpu() should mitigate serious artifacts we cannot rely on it - * in general since for !CONFIG_HAVE_UNSTABLE_SCHED_CLOCK we fully rely on - * sched_clock(). */ #include <linux/spinlock.h> #include <linux/hardirq.h> @@ -66,13 +58,16 @@ #include <linux/percpu.h> #include <linux/ktime.h> #include <linux/sched.h> +#include <linux/static_key.h> +#include <linux/workqueue.h> +#include <linux/compiler.h> /* * Scheduler clock - returns current time in nanosec units. * This is default implementation. * Architectures and sub-architectures can override this. */ -unsigned long long __attribute__((weak)) sched_clock(void) +unsigned long long __weak sched_clock(void) { return (unsigned long long)(jiffies - INITIAL_JIFFIES) * (NSEC_PER_SEC / HZ); @@ -82,7 +77,52 @@ EXPORT_SYMBOL_GPL(sched_clock); __read_mostly int sched_clock_running; #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -__read_mostly int sched_clock_stable; +static struct static_key __sched_clock_stable = STATIC_KEY_INIT; +static int __sched_clock_stable_early; + +int sched_clock_stable(void) +{ + return static_key_false(&__sched_clock_stable); +} + +static void __set_sched_clock_stable(void) +{ + if (!sched_clock_stable()) + static_key_slow_inc(&__sched_clock_stable); +} + +void set_sched_clock_stable(void) +{ + __sched_clock_stable_early = 1; + + smp_mb(); /* matches sched_clock_init() */ + + if (!sched_clock_running) + return; + + __set_sched_clock_stable(); +} + +static void __clear_sched_clock_stable(struct work_struct *work) +{ + /* XXX worry about clock continuity */ + if (sched_clock_stable()) + static_key_slow_dec(&__sched_clock_stable); +} + +static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); + +void clear_sched_clock_stable(void) +{ + __sched_clock_stable_early = 0; + + smp_mb(); /* matches sched_clock_init() */ + + if (!sched_clock_running) + return; + + schedule_work(&sched_clock_work); +} struct sched_clock_data { u64 tick_raw; @@ -116,6 +156,20 @@ void sched_clock_init(void) } sched_clock_running = 1; + + /* + * Ensure that it is impossible to not do a static_key update. + * + * Either {set,clear}_sched_clock_stable() must see sched_clock_running + * and do the update, or we must see their __sched_clock_stable_early + * and do the update, or both. + */ + smp_mb(); /* matches {set,clear}_sched_clock_stable() */ + + if (__sched_clock_stable_early) + __set_sched_clock_stable(); + else + __clear_sched_clock_stable(NULL); } /* @@ -242,20 +296,20 @@ u64 sched_clock_cpu(int cpu) struct sched_clock_data *scd; u64 clock; - WARN_ON_ONCE(!irqs_disabled()); - - if (sched_clock_stable) + if (sched_clock_stable()) return sched_clock(); if (unlikely(!sched_clock_running)) return 0ull; + preempt_disable_notrace(); scd = cpu_sdc(cpu); if (cpu != smp_processor_id()) clock = sched_clock_remote(scd); else clock = sched_clock_local(scd); + preempt_enable_notrace(); return clock; } @@ -265,7 +319,7 @@ void sched_clock_tick(void) struct sched_clock_data *scd; u64 now, now_gtod; - if (sched_clock_stable) + if (sched_clock_stable()) return; if (unlikely(!sched_clock_running)) @@ -316,14 +370,10 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); */ u64 cpu_clock(int cpu) { - u64 clock; - unsigned long flags; - - local_irq_save(flags); - clock = sched_clock_cpu(cpu); - local_irq_restore(flags); + if (!sched_clock_stable()) + return sched_clock_cpu(cpu); - return clock; + return sched_clock(); } /* @@ -335,14 +385,10 @@ u64 cpu_clock(int cpu) */ u64 local_clock(void) { - u64 clock; - unsigned long flags; + if (!sched_clock_stable()) + return sched_clock_cpu(raw_smp_processor_id()); - local_irq_save(flags); - clock = sched_clock_cpu(smp_processor_id()); - local_irq_restore(flags); - - return clock; + return sched_clock(); } #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ @@ -362,12 +408,12 @@ u64 sched_clock_cpu(int cpu) u64 cpu_clock(int cpu) { - return sched_clock_cpu(cpu); + return sched_clock(); } u64 local_clock(void) { - return sched_clock_cpu(0); + return sched_clock(); } #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c new file mode 100644 index 00000000000..a63f4dc2790 --- /dev/null +++ b/kernel/sched/completion.c @@ -0,0 +1,299 @@ +/* + * Generic wait-for-completion handler; + * + * It differs from semaphores in that their default case is the opposite, + * wait_for_completion default blocks whereas semaphore default non-block. The + * interface also makes it easy to 'complete' multiple waiting threads, + * something which isn't entirely natural for semaphores. + * + * But more importantly, the primitive documents the usage. Semaphores would + * typically be used for exclusion which gives rise to priority inversion. + * Waiting for completion is a typically sync point, but not an exclusion point. + */ + +#include <linux/sched.h> +#include <linux/completion.h> + +/** + * 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_locked(&x->wait, TASK_NORMAL, 1); + 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_locked(&x->wait, TASK_NORMAL, 0); + spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete_all); + +static inline long __sched +do_wait_for_common(struct completion *x, + long (*action)(long), 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 = action(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 inline long __sched +__wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) +{ + might_sleep(); + + spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); + spin_unlock_irq(&x->wait.lock); + return timeout; +} + +static long __sched +wait_for_common(struct completion *x, long timeout, int state) +{ + return __wait_for_common(x, schedule_timeout, timeout, state); +} + +static long __sched +wait_for_common_io(struct completion *x, long timeout, int state) +{ + return __wait_for_common(x, io_schedule_timeout, timeout, state); +} + +/** + * 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. + * + * Return: 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_io: - 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. The caller is accounted as waiting + * for IO. + */ +void __sched wait_for_completion_io(struct completion *x) +{ + wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_io); + +/** + * wait_for_completion_io_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 caller is accounted as waiting for IO. + * + * Return: 0 if timed out, and positive (at least 1, or number of jiffies left + * till timeout) if completed. + */ +unsigned long __sched +wait_for_completion_io_timeout(struct completion *x, unsigned long timeout) +{ + return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_io_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. + * + * Return: -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. + * + * Return: -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. + * + * Return: -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. + * + * Return: -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 + * + * Return: 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 + * + * Return: 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); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 5ac63c9a995..bc1638b3344 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -73,6 +73,7 @@ #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> @@ -89,6 +90,22 @@ #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; @@ -296,8 +313,6 @@ __read_mostly int scheduler_running; */ int sysctl_sched_rt_runtime = 950000; - - /* * __task_rq_lock - lock the rq @p resides on. */ @@ -434,7 +449,7 @@ void hrtick_start(struct rq *rq, u64 delay) if (rq == this_rq()) { __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; } } @@ -507,32 +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 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) @@ -546,6 +627,7 @@ void resched_cpu(int cpu) raw_spin_unlock_irqrestore(&rq->lock, flags); } +#ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ_COMMON /* * In the semi idle case, use the nearest busy cpu for migrating timers @@ -555,12 +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)) { @@ -591,27 +676,10 @@ static void wake_up_idle_cpu(int 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; - - /* - * 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); - - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(rq->idle)) + if (set_nr_and_not_polling(rq->idle)) smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } static bool wake_up_full_nohz_cpu(int cpu) @@ -693,12 +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) && \ @@ -767,14 +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); } @@ -829,19 +891,13 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { - u64 st; - 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 @@ -849,7 +905,7 @@ 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 } @@ -903,7 +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); @@ -949,7 +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); } @@ -987,7 +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 /* @@ -1017,6 +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; @@ -1224,7 +1384,7 @@ out: * leave kernel. */ if (p->mm && printk_ratelimit()) { - printk_sched("process %d (%s) no longer affine to cpu%d\n", + printk_deferred("process %d (%s) no longer affine to cpu%d\n", task_pid_nr(p), p->comm, cpu); } } @@ -1236,9 +1396,9 @@ out: * 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 @@ -1330,12 +1490,13 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) if (rq->idle_stamp) { u64 delta = rq_clock(rq) - rq->idle_stamp; - u64 max = 2*sysctl_sched_migration_cost; + u64 max = 2*rq->max_idle_balance_cost; + + update_avg(&rq->avg_idle, delta); - if (delta > max) + if (rq->avg_idle > max) rq->avg_idle = max; - else - update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; } #endif @@ -1377,13 +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); @@ -1391,11 +1556,18 @@ 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) { + /* + * 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()) @@ -1430,8 +1602,14 @@ 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); + struct rq *rq = cpu_rq(cpu); + + 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); + } } bool cpus_share_cache(int this_cpu, int that_cpu) @@ -1513,7 +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); @@ -1595,7 +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; @@ -1611,6 +1789,13 @@ 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 @@ -1619,16 +1804,26 @@ static void __sched_fork(struct task_struct *p) #ifdef CONFIG_NUMA_BALANCING if (p->mm && atomic_read(&p->mm->mm_users) == 1) { - p->mm->numa_next_scan = jiffies; - p->mm->numa_next_reset = jiffies; + 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_migrate_seq = p->mm ? p->mm->numa_scan_seq - 1 : 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 */ } @@ -1649,17 +1844,39 @@ void set_numabalancing_state(bool enabled) numabalancing_enabled = enabled; } #endif /* CONFIG_SCHED_DEBUG */ -#endif /* CONFIG_NUMA_BALANCING */ + +#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 @@ -1676,7 +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; @@ -1693,8 +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); @@ -1717,17 +1940,127 @@ 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. * @@ -1747,7 +2080,7 @@ 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 */ @@ -1838,7 +2171,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { trace_sched_switch(prev, next); - sched_info_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); @@ -1890,6 +2223,9 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) 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. @@ -1903,13 +2239,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) #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) { @@ -1927,10 +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) { } @@ -1941,7 +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(); @@ -2073,7 +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; @@ -2140,6 +2465,20 @@ unsigned long long task_sched_runtime(struct task_struct *p) struct rq *rq; u64 ns = 0; +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 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. + */ + if (!p->on_cpu) + return p->se.sum_exec_runtime; +#endif + rq = task_rq_lock(p, &flags); ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); task_rq_unlock(rq, p, &flags); @@ -2169,7 +2508,7 @@ void scheduler_tick(void) #ifdef CONFIG_SMP rq->idle_balance = idle_cpu(cpu); - trigger_load_balance(rq, cpu); + trigger_load_balance(rq); #endif rq_last_tick_reset(rq); } @@ -2198,7 +2537,7 @@ u64 scheduler_tick_max_deferment(void) if (time_before_eq(next, now)) return 0; - return jiffies_to_usecs(next - now) * NSEC_PER_USEC; + return jiffies_to_nsecs(next - now); } #endif @@ -2215,7 +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 /* @@ -2224,7 +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? @@ -2232,12 +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 /* @@ -2255,9 +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 @@ -2276,6 +2622,13 @@ static noinline void __schedule_bug(struct task_struct *prev) print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); +#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); } @@ -2287,10 +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(); @@ -2299,36 +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 */ @@ -2422,14 +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)) { @@ -2468,7 +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; @@ -2478,7 +2833,7 @@ asmlinkage void __sched schedule(void) EXPORT_SYMBOL(schedule); #ifdef CONFIG_CONTEXT_TRACKING -asmlinkage void __sched schedule_user(void) +asmlinkage __visible void __sched schedule_user(void) { /* * If we come here after a random call to set_need_resched(), @@ -2510,7 +2865,7 @@ void __sched schedule_preempt_disabled(void) * 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) { /* * If there is a non-zero preempt_count or interrupts are disabled, @@ -2520,9 +2875,9 @@ asmlinkage void __sched notrace preempt_schedule(void) 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 @@ -2531,7 +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 @@ -2539,22 +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 @@ -2566,8 +2922,6 @@ asmlinkage void __sched preempt_schedule_irq(void) exception_exit(prev_state); } -#endif /* CONFIG_PREEMPT */ - int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, void *key) { @@ -2575,439 +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, int nr) -{ - __wake_up_common(q, mode, nr, 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 != 1)) - 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 (*action)(long), 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 = action(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 inline long __sched -__wait_for_common(struct completion *x, - long (*action)(long), long timeout, int state) -{ - might_sleep(); - - spin_lock_irq(&x->wait.lock); - timeout = do_wait_for_common(x, action, timeout, state); - spin_unlock_irq(&x->wait.lock); - return timeout; -} - -static long __sched -wait_for_common(struct completion *x, long timeout, int state) -{ - return __wait_for_common(x, schedule_timeout, timeout, state); -} - -static long __sched -wait_for_common_io(struct completion *x, long timeout, int state) -{ - return __wait_for_common(x, io_schedule_timeout, timeout, state); -} - -/** - * 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. - * - * Return: 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_io: - 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. The caller is accounted as waiting - * for IO. - */ -void __sched wait_for_completion_io(struct completion *x) -{ - wait_for_common_io(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); -} -EXPORT_SYMBOL(wait_for_completion_io); - -/** - * wait_for_completion_io_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 caller is accounted as waiting for IO. - * - * Return: 0 if timed out, and positive (at least 1, or number of jiffies left - * till timeout) if completed. - */ -unsigned long __sched -wait_for_completion_io_timeout(struct completion *x, unsigned long timeout) -{ - return wait_for_common_io(x, timeout, TASK_UNINTERRUPTIBLE); -} -EXPORT_SYMBOL(wait_for_completion_io_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. - * - * Return: -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. - * - * Return: -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. - * - * Return: -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. - * - * Return: -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 - * - * Return: 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 - * - * Return: 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 /* @@ -3018,15 +2939,16 @@ 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); @@ -3049,6 +2971,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } 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; @@ -3058,30 +2981,56 @@ 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) { int old_prio, delta, on_rq; 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(), @@ -3092,9 +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; } @@ -3130,7 +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)); @@ -3154,17 +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; @@ -3192,18 +3134,6 @@ int task_prio(const struct task_struct *p) } /** - * task_nice - return the nice value of a given task. - * @p: the task in question. - * - * Return: The nice value [ -20 ... 0 ... 19 ]. - */ -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. * @@ -3249,20 +3179,126 @@ 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; } /* @@ -3281,10 +3317,14 @@ static bool check_same_owner(struct task_struct *p) 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; @@ -3298,31 +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); @@ -3332,17 +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; } @@ -3379,16 +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))) { + 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. @@ -3399,8 +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)) { @@ -3408,6 +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) @@ -3415,16 +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); @@ -3434,6 +3548,26 @@ 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. @@ -3447,10 +3581,16 @@ recheck: 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. @@ -3467,7 +3607,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); 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 @@ -3492,6 +3632,77 @@ 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. @@ -3523,6 +3734,39 @@ 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. * @@ -3560,7 +3804,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) */ 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; @@ -3577,7 +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(); /* @@ -3592,19 +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; } @@ -3638,8 +3967,26 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) 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); @@ -3661,7 +4008,6 @@ out_free_cpus_allowed: free_cpumask_var(cpus_allowed); out_put_task: put_task_struct(p); - put_online_cpus(); return retval; } @@ -3706,7 +4052,6 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) unsigned long flags; int retval; - get_online_cpus(); rcu_read_lock(); retval = -ESRCH; @@ -3719,12 +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; } @@ -3794,16 +4138,11 @@ SYSCALL_DEFINE0(sched_yield) 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) @@ -3902,7 +4241,7 @@ EXPORT_SYMBOL(yield); * 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; @@ -3924,7 +4263,7 @@ again: } 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; } @@ -4013,6 +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: @@ -4039,6 +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: @@ -4082,7 +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(); @@ -4186,7 +4529,7 @@ void init_idle(struct task_struct *idle, int cpu) raw_spin_lock_irqsave(&rq->lock, flags); - __sched_fork(idle); + __sched_fork(0, idle); idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); @@ -4206,13 +4549,14 @@ void 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: @@ -4346,6 +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 @@ -4377,8 +4769,10 @@ 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); } @@ -4396,6 +4790,22 @@ static void calc_load_migrate(struct rq *rq) atomic_long_add(delta, &calc_load_tasks); } +static void put_prev_task_fake(struct rq *rq, struct task_struct *prev) +{ +} + +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(). @@ -4436,7 +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); @@ -4526,7 +4936,7 @@ set_table_entry(struct ctl_table *entry, 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; @@ -4554,9 +4964,12 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) sizeof(int), 0644, proc_dointvec_minmax, false); set_table_entry(&table[10], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "name", sd->name, + 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[12] is terminator */ + /* &table[13] is terminator */ return table; } @@ -4722,11 +5135,20 @@ static struct notifier_block migration_notifier = { .priority = CPU_PRI_MIGRATION, }; +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_STARTING: + set_cpu_rq_start_time(); + return NOTIFY_OK; case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -4738,13 +5160,31 @@ static int sched_cpu_active(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) @@ -4827,14 +5267,13 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, } /* - * Even though we initialize ->power to something semi-sane, - * we leave power_orig unset. This allows us to detect if + * 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->sgp->power_orig) { + 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; } @@ -4856,9 +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; @@ -4916,8 +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; } @@ -4946,9 +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_CPUCAPACITY | SD_SHARE_PKG_RESOURCES | - SD_PREFER_SIBLING); + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -4963,6 +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); @@ -4985,7 +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: */ @@ -5014,8 +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; @@ -5023,6 +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: @@ -5060,7 +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; @@ -5071,8 +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; @@ -5090,7 +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); @@ -5119,10 +5570,14 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu) 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; @@ -5130,11 +5585,19 @@ static void update_top_cache_domain(int cpu) 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); } /* @@ -5200,17 +5663,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -static const struct cpumask *cpu_cpu_mask(int cpu) -{ - return cpumask_of_node(cpu_to_node(cpu)); -} - -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; @@ -5223,21 +5675,6 @@ enum s_alloc { sa_none, }; -struct sched_domain_topology_level; - -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); - -#define SDTL_OVERLAP 0x01 - -struct sched_domain_topology_level { - sched_domain_init_f init; - sched_domain_mask_f mask; - int flags; - int numa_level; - struct sd_data data; -}; - /* * Build an iteration mask that can exclude certain CPUs from the upwards * domain traversal. @@ -5315,16 +5752,17 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) cpumask_or(covered, covered, sg_span); - sg->sgp = *per_cpu_ptr(sdd->sgp, i); - if (atomic_inc_return(&sg->sgp->ref) == 1) + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) build_group_mask(sd, sg); /* - * Initialize sgp->power such that even if we mess up the + * 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->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span); + 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 @@ -5362,8 +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; @@ -5372,7 +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 */ @@ -5404,8 +5842,6 @@ build_sched_groups(struct sched_domain *sd, int cpu) continue; group = get_group(i, sdd, &sg); - cpumask_clear(sched_group_cpus(sg)); - sg->sgp->power = 0; cpumask_setall(sched_group_mask(sg)); for_each_cpu(j, span) { @@ -5428,16 +5864,16 @@ 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; @@ -5451,13 +5887,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) 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); } /* @@ -5465,34 +5896,6 @@ 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_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; @@ -5576,100 +5979,158 @@ 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; -} - -#ifdef CONFIG_SCHED_SMT -static const struct cpumask *cpu_smt_mask(int cpu) -{ - return topology_thread_cpumask(cpu); + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; } -#endif - -/* - * Topology list, bottom-up. - */ -static struct sched_domain_topology_level default_topology[] = { -#ifdef CONFIG_SCHED_SMT - { sd_init_SIBLING, cpu_smt_mask, }, -#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, }, - { NULL, }, -}; - -static struct sched_domain_topology_level *sched_domain_topology = default_topology; - -#define for_each_sd_topology(tl) \ - for (tl = sched_domain_topology; tl->init; tl++) #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 -static inline int sd_local_flags(int level) -{ - if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE) - return 0; - - return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE; -} +/* + * 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_numa_init(struct sched_domain_topology_level *tl, int cpu) +sd_init(struct sched_domain_topology_level *tl, int cpu) { struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); - int level = tl->numa_level; - int sd_weight = cpumask_weight( - sched_domains_numa_masks[level][cpu_to_node(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 = 2, - .busy_idx = 3, - .idle_idx = 2, + + .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 - | 0*SD_BALANCE_EXEC - | 0*SD_BALANCE_FORK + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK | 0*SD_BALANCE_WAKE - | 0*SD_WAKE_AFFINE - | 0*SD_SHARE_CPUPOWER + | 1*SD_WAKE_AFFINE + | 0*SD_SHARE_CPUCAPACITY | 0*SD_SHARE_PKG_RESOURCES - | 1*SD_SERIALIZE + | 0*SD_SERIALIZE | 0*SD_PREFER_SIBLING - | sd_local_flags(level) + | 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 }; - SD_INIT_NAME(sd, NUMA); - sd->private = &tl->data; /* - * Ugly hack to pass state to sd_numa_mask()... + * Convert topological properties into behaviour. */ - sched_domains_curr_level = tl->numa_level; + + 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 + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +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)]; @@ -5813,7 +6274,10 @@ static void sched_init_numa(void) } } - tl = kzalloc((ARRAY_SIZE(default_topology) + level) * + /* 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; @@ -5821,18 +6285,19 @@ static void sched_init_numa(void) /* * Copy the default topology bits.. */ - for (i = 0; default_topology[i].init; i++) - tl[i] = default_topology[i]; + 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){ - .init = sd_numa_init, .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, .flags = SDTL_OVERLAP, .numa_level = j, + SD_INIT_NAME(NUMA) }; } @@ -5917,14 +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)); @@ -5942,12 +6407,12 @@ static int __sdt_alloc(const struct cpumask *cpu_map) *per_cpu_ptr(sdd->sg, j) = sg; - sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(), + 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; } } @@ -5974,15 +6439,15 @@ static void __sdt_free(const struct cpumask *cpu_map) if (sdd->sg) kfree(*per_cpu_ptr(sdd->sg, j)); - if (sdd->sgp) - kfree(*per_cpu_ptr(sdd->sgp, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); } free_percpu(sdd->sd); sdd->sd = NULL; free_percpu(sdd->sg); sdd->sg = NULL; - free_percpu(sdd->sgp); - sdd->sgp = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; } } @@ -5990,7 +6455,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, 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; @@ -6052,14 +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); } } @@ -6094,7 +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; } @@ -6335,14 +6800,17 @@ void __init sched_init_smp(void) sched_init_numa(); - get_online_cpus(); + /* + * 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); @@ -6357,6 +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) @@ -6426,13 +6895,15 @@ void __init sched_init(void) #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()); @@ -6456,6 +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); @@ -6484,7 +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 @@ -6496,7 +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; @@ -6505,6 +6976,7 @@ 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); @@ -6526,10 +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: */ @@ -6557,6 +7025,7 @@ void __init sched_init(void) 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(); @@ -6576,7 +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) @@ -6594,6 +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); @@ -6603,13 +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); @@ -6639,12 +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; } @@ -6812,7 +7292,7 @@ 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_cgroup_subsys_id, + 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); @@ -6834,16 +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. @@ -7017,24 +7487,13 @@ static 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); @@ -7057,17 +7516,7 @@ static 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) { @@ -7079,36 +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 */ -int sched_rr_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) +static int sched_dl_global_constraints(void) { - int ret; - static DEFINE_MUTEX(mutex); + u64 runtime = global_rt_runtime(); + u64 period = global_rt_period(); + u64 new_bw = to_ratio(period, runtime); + int cpu, ret = 0; + unsigned long flags; - 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); + /* + * 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; } - mutex_unlock(&mutex); + 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; @@ -7117,21 +7621,50 @@ 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 static inline struct task_group *css_tg(struct cgroup_subsys_state *css) @@ -7160,7 +7693,7 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) 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(css)); + struct task_group *parent = css_tg(css->parent); if (parent) sched_online_group(tg, parent); @@ -7186,7 +7719,7 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css, tset) { + cgroup_taskset_for_each(task, tset) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; @@ -7204,7 +7737,7 @@ static void cpu_cgroup_attach(struct cgroup_subsys_state *css, { struct task_struct *task; - cgroup_taskset_for_each(task, css, tset) + cgroup_taskset_for_each(task, tset) sched_move_task(task); } @@ -7277,7 +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; @@ -7286,8 +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); @@ -7303,6 +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); @@ -7457,15 +7996,14 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) return ret; } -static int cpu_stats_show(struct cgroup_subsys_state *css, struct cftype *cft, - struct cgroup_map_cb *cb) +static int cpu_stats_show(struct seq_file *sf, void *v) { - struct task_group *tg = css_tg(css); + 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; } @@ -7519,7 +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 @@ -7537,8 +8075,7 @@ static struct cftype cpu_files[] = { { } /* terminate */ }; -struct cgroup_subsys cpu_cgroup_subsys = { - .name = "cpu", +struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, .css_free = cpu_cgroup_css_free, .css_online = cpu_cgroup_css_online, @@ -7546,7 +8083,6 @@ struct cgroup_subsys cpu_cgroup_subsys = { .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, .exit = cpu_cgroup_exit, - .subsys_id = cpu_cgroup_subsys_id, .base_cftypes = cpu_files, .early_init = 1, }; diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index f64722ff029..9cf350c94ec 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -41,12 +41,12 @@ static inline struct cpuacct *css_ca(struct cgroup_subsys_state *css) /* return cpu accounting group to which this task belongs */ static inline struct cpuacct *task_ca(struct task_struct *tsk) { - return css_ca(task_css(tsk, cpuacct_subsys_id)); + return css_ca(task_css(tsk, cpuacct_cgrp_id)); } static inline struct cpuacct *parent_ca(struct cpuacct *ca) { - return css_ca(css_parent(&ca->css)); + return css_ca(ca->css.parent); } static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); @@ -163,10 +163,9 @@ out: return err; } -static int cpuacct_percpu_seq_read(struct cgroup_subsys_state *css, - struct cftype *cft, struct seq_file *m) +static int cpuacct_percpu_seq_show(struct seq_file *m, void *V) { - struct cpuacct *ca = css_ca(css); + struct cpuacct *ca = css_ca(seq_css(m)); u64 percpu; int i; @@ -183,10 +182,9 @@ static const char * const cpuacct_stat_desc[] = { [CPUACCT_STAT_SYSTEM] = "system", }; -static int cpuacct_stats_show(struct cgroup_subsys_state *css, - struct cftype *cft, struct cgroup_map_cb *cb) +static int cpuacct_stats_show(struct seq_file *sf, void *v) { - struct cpuacct *ca = css_ca(css); + struct cpuacct *ca = css_ca(seq_css(sf)); int cpu; s64 val = 0; @@ -196,7 +194,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css, val += kcpustat->cpustat[CPUTIME_NICE]; } val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val); + seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_USER], val); val = 0; for_each_online_cpu(cpu) { @@ -207,7 +205,7 @@ static int cpuacct_stats_show(struct cgroup_subsys_state *css, } val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); + seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); return 0; } @@ -220,11 +218,11 @@ static struct cftype files[] = { }, { .name = "usage_percpu", - .read_seq_string = cpuacct_percpu_seq_read, + .seq_show = cpuacct_percpu_seq_show, }, { .name = "stat", - .read_map = cpuacct_stats_show, + .seq_show = cpuacct_stats_show, }, { } /* terminate */ }; @@ -277,11 +275,9 @@ void cpuacct_account_field(struct task_struct *p, int index, u64 val) rcu_read_unlock(); } -struct cgroup_subsys cpuacct_subsys = { - .name = "cpuacct", +struct cgroup_subsys cpuacct_cgrp_subsys = { .css_alloc = cpuacct_css_alloc, .css_free = cpuacct_css_free, - .subsys_id = cpuacct_subsys_id, .base_cftypes = files, .early_init = 1, }; diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c new file mode 100644 index 00000000000..bd95963dae8 --- /dev/null +++ b/kernel/sched/cpudeadline.c @@ -0,0 +1,229 @@ +/* + * kernel/sched/cpudl.c + * + * Global CPU deadline management + * + * Author: Juri Lelli <j.lelli@sssup.it> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; version 2 + * of the License. + */ + +#include <linux/gfp.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include "cpudeadline.h" + +static inline int parent(int i) +{ + return (i - 1) >> 1; +} + +static inline int left_child(int i) +{ + return (i << 1) + 1; +} + +static inline int right_child(int i) +{ + return (i << 1) + 2; +} + +static inline int dl_time_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + +static void cpudl_exchange(struct cpudl *cp, int a, int b) +{ + int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu; + + swap(cp->elements[a].cpu, cp->elements[b].cpu); + swap(cp->elements[a].dl , cp->elements[b].dl ); + + swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx); +} + +static void cpudl_heapify(struct cpudl *cp, int idx) +{ + int l, r, largest; + + /* adapted from lib/prio_heap.c */ + while(1) { + l = left_child(idx); + r = right_child(idx); + largest = idx; + + if ((l < cp->size) && dl_time_before(cp->elements[idx].dl, + cp->elements[l].dl)) + largest = l; + if ((r < cp->size) && dl_time_before(cp->elements[largest].dl, + cp->elements[r].dl)) + largest = r; + if (largest == idx) + break; + + /* Push idx down the heap one level and bump one up */ + cpudl_exchange(cp, largest, idx); + idx = largest; + } +} + +static void cpudl_change_key(struct cpudl *cp, int idx, u64 new_dl) +{ + WARN_ON(idx == IDX_INVALID || !cpu_present(idx)); + + if (dl_time_before(new_dl, cp->elements[idx].dl)) { + cp->elements[idx].dl = new_dl; + cpudl_heapify(cp, idx); + } else { + cp->elements[idx].dl = new_dl; + while (idx > 0 && dl_time_before(cp->elements[parent(idx)].dl, + cp->elements[idx].dl)) { + cpudl_exchange(cp, idx, parent(idx)); + idx = parent(idx); + } + } +} + +static inline int cpudl_maximum(struct cpudl *cp) +{ + return cp->elements[0].cpu; +} + +/* + * cpudl_find - find the best (later-dl) CPU in the system + * @cp: the cpudl max-heap context + * @p: the task + * @later_mask: a mask to fill in with the selected CPUs (or NULL) + * + * Returns: int - best CPU (heap maximum if suitable) + */ +int cpudl_find(struct cpudl *cp, struct task_struct *p, + struct cpumask *later_mask) +{ + int best_cpu = -1; + const struct sched_dl_entity *dl_se = &p->dl; + + if (later_mask && cpumask_and(later_mask, cp->free_cpus, + &p->cpus_allowed) && cpumask_and(later_mask, + later_mask, cpu_active_mask)) { + best_cpu = cpumask_any(later_mask); + goto out; + } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && + dl_time_before(dl_se->deadline, cp->elements[0].dl)) { + best_cpu = cpudl_maximum(cp); + if (later_mask) + cpumask_set_cpu(best_cpu, later_mask); + } + +out: + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); + + return best_cpu; +} + +/* + * cpudl_set - update the cpudl max-heap + * @cp: the cpudl max-heap context + * @cpu: the target cpu + * @dl: the new earliest deadline for this cpu + * + * Notes: assumes cpu_rq(cpu)->lock is locked + * + * Returns: (void) + */ +void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) +{ + int old_idx, new_cpu; + unsigned long flags; + + WARN_ON(!cpu_present(cpu)); + + raw_spin_lock_irqsave(&cp->lock, flags); + old_idx = cp->elements[cpu].idx; + if (!is_valid) { + /* remove item */ + if (old_idx == IDX_INVALID) { + /* + * Nothing to remove if old_idx was invalid. + * This could happen if a rq_offline_dl is + * called for a CPU without -dl tasks running. + */ + goto out; + } + new_cpu = cp->elements[cp->size - 1].cpu; + cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl; + cp->elements[old_idx].cpu = new_cpu; + cp->size--; + cp->elements[new_cpu].idx = old_idx; + cp->elements[cpu].idx = IDX_INVALID; + while (old_idx > 0 && dl_time_before( + cp->elements[parent(old_idx)].dl, + cp->elements[old_idx].dl)) { + cpudl_exchange(cp, old_idx, parent(old_idx)); + old_idx = parent(old_idx); + } + cpumask_set_cpu(cpu, cp->free_cpus); + cpudl_heapify(cp, old_idx); + + goto out; + } + + if (old_idx == IDX_INVALID) { + cp->size++; + cp->elements[cp->size - 1].dl = 0; + cp->elements[cp->size - 1].cpu = cpu; + cp->elements[cpu].idx = cp->size - 1; + cpudl_change_key(cp, cp->size - 1, dl); + cpumask_clear_cpu(cpu, cp->free_cpus); + } else { + cpudl_change_key(cp, old_idx, dl); + } + +out: + raw_spin_unlock_irqrestore(&cp->lock, flags); +} + +/* + * cpudl_init - initialize the cpudl structure + * @cp: the cpudl max-heap context + */ +int cpudl_init(struct cpudl *cp) +{ + int i; + + memset(cp, 0, sizeof(*cp)); + raw_spin_lock_init(&cp->lock); + cp->size = 0; + + cp->elements = kcalloc(nr_cpu_ids, + sizeof(struct cpudl_item), + GFP_KERNEL); + if (!cp->elements) + return -ENOMEM; + + if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) { + kfree(cp->elements); + return -ENOMEM; + } + + for_each_possible_cpu(i) + cp->elements[i].idx = IDX_INVALID; + + cpumask_setall(cp->free_cpus); + + return 0; +} + +/* + * cpudl_cleanup - clean up the cpudl structure + * @cp: the cpudl max-heap context + */ +void cpudl_cleanup(struct cpudl *cp) +{ + free_cpumask_var(cp->free_cpus); + kfree(cp->elements); +} diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h new file mode 100644 index 00000000000..538c9796ad4 --- /dev/null +++ b/kernel/sched/cpudeadline.h @@ -0,0 +1,33 @@ +#ifndef _LINUX_CPUDL_H +#define _LINUX_CPUDL_H + +#include <linux/sched.h> + +#define IDX_INVALID -1 + +struct cpudl_item { + u64 dl; + int cpu; + int idx; +}; + +struct cpudl { + raw_spinlock_t lock; + int size; + cpumask_var_t free_cpus; + struct cpudl_item *elements; +}; + + +#ifdef CONFIG_SMP +int cpudl_find(struct cpudl *cp, struct task_struct *p, + struct cpumask *later_mask); +void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid); +int cpudl_init(struct cpudl *cp); +void cpudl_cleanup(struct cpudl *cp); +#else +#define cpudl_set(cp, cpu, dl) do { } while (0) +#define cpudl_init() do { } while (0) +#endif /* CONFIG_SMP */ + +#endif /* _LINUX_CPUDL_H */ diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 8b836b376d9..981fcd7dc39 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -30,6 +30,7 @@ #include <linux/gfp.h> #include <linux/sched.h> #include <linux/sched/rt.h> +#include <linux/slab.h> #include "cpupri.h" /* Convert between a 140 based task->prio, and our 102 based cpupri */ @@ -70,8 +71,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, int idx = 0; int task_pri = convert_prio(p->prio); - if (task_pri >= MAX_RT_PRIO) - return 0; + BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES); for (idx = 0; idx < task_pri; idx++) { struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; @@ -165,7 +165,7 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * do a write memory barrier, and then update the count, to * make sure the vector is visible when count is set. */ - smp_mb__before_atomic_inc(); + smp_mb__before_atomic(); atomic_inc(&(vec)->count); do_mb = 1; } @@ -185,14 +185,14 @@ void cpupri_set(struct cpupri *cp, int cpu, int newpri) * the new priority vec. */ if (do_mb) - smp_mb__after_atomic_inc(); + smp_mb__after_atomic(); /* * When removing from the vector, we decrement the counter first * do a memory barrier and then clear the mask. */ atomic_dec(&(vec)->count); - smp_mb__after_atomic_inc(); + smp_mb__after_atomic(); cpumask_clear_cpu(cpu, vec->mask); } @@ -219,8 +219,13 @@ int cpupri_init(struct cpupri *cp) goto cleanup; } + cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL); + if (!cp->cpu_to_pri) + goto cleanup; + for_each_possible_cpu(i) cp->cpu_to_pri[i] = CPUPRI_INVALID; + return 0; cleanup: @@ -237,6 +242,7 @@ void cpupri_cleanup(struct cpupri *cp) { int i; + kfree(cp->cpu_to_pri); for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) free_cpumask_var(cp->pri_to_cpu[i].mask); } diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h index f6d75617349..6b033347fdf 100644 --- a/kernel/sched/cpupri.h +++ b/kernel/sched/cpupri.h @@ -17,7 +17,7 @@ struct cpupri_vec { struct cpupri { struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES]; - int cpu_to_pri[NR_CPUS]; + int *cpu_to_pri; }; #ifdef CONFIG_SMP diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 99947919e30..72fdf06ef86 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -142,7 +142,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime, p->utimescaled += cputime_scaled; account_group_user_time(p, cputime); - index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; + index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; /* Add user time to cpustat. */ task_group_account_field(p, index, (__force u64) cputime); @@ -169,7 +169,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, p->gtime += cputime; /* Add guest time to cpustat. */ - if (TASK_NICE(p) > 0) { + if (task_nice(p) > 0) { cpustat[CPUTIME_NICE] += (__force u64) cputime; cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; } else { @@ -258,16 +258,22 @@ static __always_inline bool steal_account_process_tick(void) { #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { - u64 steal, st = 0; + u64 steal; + cputime_t steal_ct; 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; + /* + * cputime_t may be less precise than nsecs (eg: if it's + * based on jiffies). Lets cast the result to cputime + * granularity and account the rest on the next rounds. + */ + steal_ct = nsecs_to_cputime(steal); + this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); - account_steal_time(st); - return st; + account_steal_time(steal_ct); + return steal_ct; } #endif return false; @@ -326,50 +332,50 @@ out: * 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) + struct rq *rq, int ticks) { - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + cputime_t scaled = cputime_to_scaled(cputime_one_jiffy); + u64 cputime = (__force u64) cputime_one_jiffy; u64 *cpustat = kcpustat_this_cpu->cpustat; if (steal_account_process_tick()) return; + cputime *= ticks; + scaled *= ticks; + if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_IRQ] += cputime; } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_SOFTIRQ] += cputime; } 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); + __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ); } else if (user_tick) { - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_user_time(p, cputime, scaled); } else if (p == rq->idle) { - account_idle_time(cputime_one_jiffy); + account_idle_time(cputime); } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_guest_time(p, cputime, scaled); } else { - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SYSTEM); + __account_system_time(p, cputime, 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); + irqtime_account_process_tick(current, 0, rq, ticks); } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ static inline void irqtime_account_idle_ticks(int ticks) {} static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) {} + struct rq *rq, int nr_ticks) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ /* @@ -458,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick) return; if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); + irqtime_account_process_tick(p, user_tick, rq, 1); return; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c new file mode 100644 index 00000000000..fc4f98b1258 --- /dev/null +++ b/kernel/sched/deadline.c @@ -0,0 +1,1676 @@ +/* + * Deadline Scheduling Class (SCHED_DEADLINE) + * + * Earliest Deadline First (EDF) + Constant Bandwidth Server (CBS). + * + * Tasks that periodically executes their instances for less than their + * runtime won't miss any of their deadlines. + * Tasks that are not periodic or sporadic or that tries to execute more + * than their reserved bandwidth will be slowed down (and may potentially + * miss some of their deadlines), and won't affect any other task. + * + * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>, + * Juri Lelli <juri.lelli@gmail.com>, + * Michael Trimarchi <michael@amarulasolutions.com>, + * Fabio Checconi <fchecconi@gmail.com> + */ +#include "sched.h" + +#include <linux/slab.h> + +struct dl_bandwidth def_dl_bandwidth; + +static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) +{ + return container_of(dl_se, struct task_struct, dl); +} + +static inline struct rq *rq_of_dl_rq(struct dl_rq *dl_rq) +{ + return container_of(dl_rq, struct rq, dl); +} + +static inline struct dl_rq *dl_rq_of_se(struct sched_dl_entity *dl_se) +{ + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq = task_rq(p); + + return &rq->dl; +} + +static inline int on_dl_rq(struct sched_dl_entity *dl_se) +{ + return !RB_EMPTY_NODE(&dl_se->rb_node); +} + +static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) +{ + struct sched_dl_entity *dl_se = &p->dl; + + return dl_rq->rb_leftmost == &dl_se->rb_node; +} + +void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime) +{ + raw_spin_lock_init(&dl_b->dl_runtime_lock); + dl_b->dl_period = period; + dl_b->dl_runtime = runtime; +} + +void init_dl_bw(struct dl_bw *dl_b) +{ + raw_spin_lock_init(&dl_b->lock); + raw_spin_lock(&def_dl_bandwidth.dl_runtime_lock); + if (global_rt_runtime() == RUNTIME_INF) + dl_b->bw = -1; + else + dl_b->bw = to_ratio(global_rt_period(), global_rt_runtime()); + raw_spin_unlock(&def_dl_bandwidth.dl_runtime_lock); + dl_b->total_bw = 0; +} + +void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq) +{ + dl_rq->rb_root = RB_ROOT; + +#ifdef CONFIG_SMP + /* zero means no -deadline tasks */ + dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0; + + dl_rq->dl_nr_migratory = 0; + dl_rq->overloaded = 0; + dl_rq->pushable_dl_tasks_root = RB_ROOT; +#else + init_dl_bw(&dl_rq->dl_bw); +#endif +} + +#ifdef CONFIG_SMP + +static inline int dl_overloaded(struct rq *rq) +{ + return atomic_read(&rq->rd->dlo_count); +} + +static inline void dl_set_overload(struct rq *rq) +{ + if (!rq->online) + return; + + cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask); + /* + * Must be visible before the overload count is + * set (as in sched_rt.c). + * + * Matched by the barrier in pull_dl_task(). + */ + smp_wmb(); + atomic_inc(&rq->rd->dlo_count); +} + +static inline void dl_clear_overload(struct rq *rq) +{ + if (!rq->online) + return; + + atomic_dec(&rq->rd->dlo_count); + cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask); +} + +static void update_dl_migration(struct dl_rq *dl_rq) +{ + if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_running > 1) { + if (!dl_rq->overloaded) { + dl_set_overload(rq_of_dl_rq(dl_rq)); + dl_rq->overloaded = 1; + } + } else if (dl_rq->overloaded) { + dl_clear_overload(rq_of_dl_rq(dl_rq)); + dl_rq->overloaded = 0; + } +} + +static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + struct task_struct *p = dl_task_of(dl_se); + + if (p->nr_cpus_allowed > 1) + dl_rq->dl_nr_migratory++; + + update_dl_migration(dl_rq); +} + +static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + struct task_struct *p = dl_task_of(dl_se); + + if (p->nr_cpus_allowed > 1) + dl_rq->dl_nr_migratory--; + + update_dl_migration(dl_rq); +} + +/* + * The list of pushable -deadline task is not a plist, like in + * sched_rt.c, it is an rb-tree with tasks ordered by deadline. + */ +static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ + struct dl_rq *dl_rq = &rq->dl; + struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node; + struct rb_node *parent = NULL; + struct task_struct *entry; + int leftmost = 1; + + BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks)); + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct task_struct, + pushable_dl_tasks); + if (dl_entity_preempt(&p->dl, &entry->dl)) + link = &parent->rb_left; + else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks; + + rb_link_node(&p->pushable_dl_tasks, parent, link); + rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); +} + +static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ + struct dl_rq *dl_rq = &rq->dl; + + if (RB_EMPTY_NODE(&p->pushable_dl_tasks)) + return; + + if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) { + struct rb_node *next_node; + + next_node = rb_next(&p->pushable_dl_tasks); + dl_rq->pushable_dl_tasks_leftmost = next_node; + } + + rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +} + +static inline int has_pushable_dl_tasks(struct rq *rq) +{ + return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root); +} + +static int push_dl_task(struct rq *rq); + +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return dl_task(prev); +} + +static inline void set_post_schedule(struct rq *rq) +{ + rq->post_schedule = has_pushable_dl_tasks(rq); +} + +#else + +static inline +void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p) +{ +} + +static inline +void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ +} + +static inline +void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ +} + +static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_dl_task(struct rq *rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} +#endif /* CONFIG_SMP */ + +static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags); +static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags); +static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, + int flags); + +/* + * We are being explicitly informed that a new instance is starting, + * and this means that: + * - the absolute deadline of the entity has to be placed at + * current time + relative deadline; + * - the runtime of the entity has to be set to the maximum value. + * + * The capability of specifying such event is useful whenever a -deadline + * entity wants to (try to!) synchronize its behaviour with the scheduler's + * one, and to (try to!) reconcile itself with its own scheduling + * parameters. + */ +static inline void setup_new_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + WARN_ON(!dl_se->dl_new || dl_se->dl_throttled); + + /* + * We use the regular wall clock time to set deadlines in the + * future; in fact, we must consider execution overheads (time + * spent on hardirq context, etc.). + */ + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + dl_se->dl_new = 0; +} + +/* + * Pure Earliest Deadline First (EDF) scheduling does not deal with the + * possibility of a entity lasting more than what it declared, and thus + * exhausting its runtime. + * + * Here we are interested in making runtime overrun possible, but we do + * not want a entity which is misbehaving to affect the scheduling of all + * other entities. + * Therefore, a budgeting strategy called Constant Bandwidth Server (CBS) + * is used, in order to confine each entity within its own bandwidth. + * + * This function deals exactly with that, and ensures that when the runtime + * of a entity is replenished, its deadline is also postponed. That ensures + * the overrunning entity can't interfere with other entity in the system and + * can't make them miss their deadlines. Reasons why this kind of overruns + * could happen are, typically, a entity voluntarily trying to overcome its + * runtime, or it just underestimated it during sched_setscheduler_ex(). + */ +static void replenish_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + BUG_ON(pi_se->dl_runtime <= 0); + + /* + * This could be the case for a !-dl task that is boosted. + * Just go with full inherited parameters. + */ + if (dl_se->dl_deadline == 0) { + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } + + /* + * We keep moving the deadline away until we get some + * available runtime for the entity. This ensures correct + * handling of situations where the runtime overrun is + * arbitrary large. + */ + while (dl_se->runtime <= 0) { + dl_se->deadline += pi_se->dl_period; + dl_se->runtime += pi_se->dl_runtime; + } + + /* + * At this point, the deadline really should be "in + * the future" with respect to rq->clock. If it's + * not, we are, for some reason, lagging too much! + * Anyway, after having warn userspace abut that, + * we still try to keep the things running by + * resetting the deadline and the budget of the + * entity. + */ + if (dl_time_before(dl_se->deadline, rq_clock(rq))) { + printk_deferred_once("sched: DL replenish lagged to much\n"); + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } +} + +/* + * Here we check if --at time t-- an entity (which is probably being + * [re]activated or, in general, enqueued) can use its remaining runtime + * and its current deadline _without_ exceeding the bandwidth it is + * assigned (function returns true if it can't). We are in fact applying + * one of the CBS rules: when a task wakes up, if the residual runtime + * over residual deadline fits within the allocated bandwidth, then we + * can keep the current (absolute) deadline and residual budget without + * disrupting the schedulability of the system. Otherwise, we should + * refill the runtime and set the deadline a period in the future, + * because keeping the current (absolute) deadline of the task would + * result in breaking guarantees promised to other tasks (refer to + * Documentation/scheduler/sched-deadline.txt for more informations). + * + * This function returns true if: + * + * runtime / (deadline - t) > dl_runtime / dl_period , + * + * IOW we can't recycle current parameters. + * + * Notice that the bandwidth check is done against the period. For + * task with deadline equal to period this is the same of using + * dl_deadline instead of dl_period in the equation above. + */ +static bool dl_entity_overflow(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se, u64 t) +{ + u64 left, right; + + /* + * left and right are the two sides of the equation above, + * after a bit of shuffling to use multiplications instead + * of divisions. + * + * Note that none of the time values involved in the two + * multiplications are absolute: dl_deadline and dl_runtime + * are the relative deadline and the maximum runtime of each + * instance, runtime is the runtime left for the last instance + * and (deadline - t), since t is rq->clock, is the time left + * to the (absolute) deadline. Even if overflowing the u64 type + * is very unlikely to occur in both cases, here we scale down + * as we want to avoid that risk at all. Scaling down by 10 + * means that we reduce granularity to 1us. We are fine with it, + * since this is only a true/false check and, anyway, thinking + * of anything below microseconds resolution is actually fiction + * (but still we want to give the user that illusion >;). + */ + left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + right = ((dl_se->deadline - t) >> DL_SCALE) * + (pi_se->dl_runtime >> DL_SCALE); + + return dl_time_before(right, left); +} + +/* + * When a -deadline entity is queued back on the runqueue, its runtime and + * deadline might need updating. + * + * The policy here is that we update the deadline of the entity only if: + * - the current deadline is in the past, + * - using the remaining runtime with the current deadline would make + * the entity exceed its bandwidth. + */ +static void update_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + + /* + * The arrival of a new instance needs special treatment, i.e., + * the actual scheduling parameters have to be "renewed". + */ + if (dl_se->dl_new) { + setup_new_dl_entity(dl_se, pi_se); + return; + } + + if (dl_time_before(dl_se->deadline, rq_clock(rq)) || + dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { + dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline; + dl_se->runtime = pi_se->dl_runtime; + } +} + +/* + * If the entity depleted all its runtime, and if we want it to sleep + * while waiting for some new execution time to become available, we + * set the bandwidth enforcement timer to the replenishment instant + * and try to activate it. + * + * Notice that it is important for the caller to know if the timer + * actually started or not (i.e., the replenishment instant is in + * the future or in the past). + */ +static int start_dl_timer(struct sched_dl_entity *dl_se, bool boosted) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + ktime_t now, act; + ktime_t soft, hard; + unsigned long range; + s64 delta; + + if (boosted) + return 0; + /* + * We want the timer to fire at the deadline, but considering + * that it is actually coming from rq->clock and not from + * hrtimer's time base reading. + */ + act = ns_to_ktime(dl_se->deadline); + now = hrtimer_cb_get_time(&dl_se->dl_timer); + delta = ktime_to_ns(now) - rq_clock(rq); + act = ktime_add_ns(act, delta); + + /* + * If the expiry time already passed, e.g., because the value + * chosen as the deadline is too small, don't even try to + * start the timer in the past! + */ + if (ktime_us_delta(act, now) < 0) + return 0; + + hrtimer_set_expires(&dl_se->dl_timer, act); + + soft = hrtimer_get_softexpires(&dl_se->dl_timer); + hard = hrtimer_get_expires(&dl_se->dl_timer); + range = ktime_to_ns(ktime_sub(hard, soft)); + __hrtimer_start_range_ns(&dl_se->dl_timer, soft, + range, HRTIMER_MODE_ABS, 0); + + return hrtimer_active(&dl_se->dl_timer); +} + +/* + * This is the bandwidth enforcement timer callback. If here, we know + * a task is not on its dl_rq, since the fact that the timer was running + * means the task is throttled and needs a runtime replenishment. + * + * However, what we actually do depends on the fact the task is active, + * (it is on its rq) or has been removed from there by a call to + * dequeue_task_dl(). In the former case we must issue the runtime + * replenishment and add the task back to the dl_rq; in the latter, we just + * do nothing but clearing dl_throttled, so that runtime and deadline + * updating (and the queueing back to dl_rq) will be done by the + * next call to enqueue_task_dl(). + */ +static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) +{ + struct sched_dl_entity *dl_se = container_of(timer, + struct sched_dl_entity, + dl_timer); + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq; +again: + rq = task_rq(p); + raw_spin_lock(&rq->lock); + + if (rq != task_rq(p)) { + /* Task was moved, retrying. */ + raw_spin_unlock(&rq->lock); + goto again; + } + + /* + * We need to take care of a possible races here. In fact, the + * task might have changed its scheduling policy to something + * different from SCHED_DEADLINE or changed its reservation + * parameters (through sched_setattr()). + */ + if (!dl_task(p) || dl_se->dl_new) + goto unlock; + + sched_clock_tick(); + update_rq_clock(rq); + dl_se->dl_throttled = 0; + dl_se->dl_yielded = 0; + if (p->on_rq) { + enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); + if (task_has_dl_policy(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + else + resched_task(rq->curr); +#ifdef CONFIG_SMP + /* + * Queueing this task back might have overloaded rq, + * check if we need to kick someone away. + */ + if (has_pushable_dl_tasks(rq)) + push_dl_task(rq); +#endif + } +unlock: + raw_spin_unlock(&rq->lock); + + return HRTIMER_NORESTART; +} + +void init_dl_task_timer(struct sched_dl_entity *dl_se) +{ + struct hrtimer *timer = &dl_se->dl_timer; + + if (hrtimer_active(timer)) { + hrtimer_try_to_cancel(timer); + return; + } + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = dl_task_timer; +} + +static +int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se) +{ + int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq)); + int rorun = dl_se->runtime <= 0; + + if (!rorun && !dmiss) + return 0; + + /* + * If we are beyond our current deadline and we are still + * executing, then we have already used some of the runtime of + * the next instance. Thus, if we do not account that, we are + * stealing bandwidth from the system at each deadline miss! + */ + if (dmiss) { + dl_se->runtime = rorun ? dl_se->runtime : 0; + dl_se->runtime -= rq_clock(rq) - dl_se->deadline; + } + + return 1; +} + +extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq); + +/* + * Update the current task's runtime statistics (provided it is still + * a -deadline task and has not been removed from the dl_rq). + */ +static void update_curr_dl(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct sched_dl_entity *dl_se = &curr->dl; + u64 delta_exec; + + if (!dl_task(curr) || !on_dl_rq(dl_se)) + return; + + /* + * Consumed budget is computed considering the time as + * observed by schedulable tasks (excluding time spent + * in hardirq context, etc.). Deadlines are instead + * computed using hard walltime. This seems to be the more + * natural solution, but the full ramifications of this + * approach need further study. + */ + delta_exec = rq_clock_task(rq) - curr->se.exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + schedstat_set(curr->se.statistics.exec_max, + max(curr->se.statistics.exec_max, delta_exec)); + + curr->se.sum_exec_runtime += delta_exec; + account_group_exec_runtime(curr, delta_exec); + + curr->se.exec_start = rq_clock_task(rq); + cpuacct_charge(curr, delta_exec); + + sched_rt_avg_update(rq, delta_exec); + + dl_se->runtime -= delta_exec; + if (dl_runtime_exceeded(rq, dl_se)) { + __dequeue_task_dl(rq, curr, 0); + if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted))) + dl_se->dl_throttled = 1; + else + enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH); + + if (!is_leftmost(curr, &rq->dl)) + resched_task(curr); + } + + /* + * Because -- for now -- we share the rt bandwidth, we need to + * account our runtime there too, otherwise actual rt tasks + * would be able to exceed the shared quota. + * + * Account to the root rt group for now. + * + * The solution we're working towards is having the RT groups scheduled + * using deadline servers -- however there's a few nasties to figure + * out before that can happen. + */ + if (rt_bandwidth_enabled()) { + struct rt_rq *rt_rq = &rq->rt; + + raw_spin_lock(&rt_rq->rt_runtime_lock); + /* + * We'll let actual RT tasks worry about the overflow here, we + * have our own CBS to keep us inline; only account when RT + * bandwidth is relevant. + */ + if (sched_rt_bandwidth_account(rt_rq)) + rt_rq->rt_time += delta_exec; + raw_spin_unlock(&rt_rq->rt_runtime_lock); + } +} + +#ifdef CONFIG_SMP + +static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu); + +static inline u64 next_deadline(struct rq *rq) +{ + struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu); + + if (next && dl_prio(next->prio)) + return next->dl.deadline; + else + return 0; +} + +static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) +{ + struct rq *rq = rq_of_dl_rq(dl_rq); + + if (dl_rq->earliest_dl.curr == 0 || + dl_time_before(deadline, dl_rq->earliest_dl.curr)) { + /* + * If the dl_rq had no -deadline tasks, or if the new task + * has shorter deadline than the current one on dl_rq, we + * know that the previous earliest becomes our next earliest, + * as the new task becomes the earliest itself. + */ + dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr; + dl_rq->earliest_dl.curr = deadline; + cpudl_set(&rq->rd->cpudl, rq->cpu, deadline, 1); + } else if (dl_rq->earliest_dl.next == 0 || + dl_time_before(deadline, dl_rq->earliest_dl.next)) { + /* + * On the other hand, if the new -deadline task has a + * a later deadline than the earliest one on dl_rq, but + * it is earlier than the next (if any), we must + * recompute the next-earliest. + */ + dl_rq->earliest_dl.next = next_deadline(rq); + } +} + +static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) +{ + struct rq *rq = rq_of_dl_rq(dl_rq); + + /* + * Since we may have removed our earliest (and/or next earliest) + * task we must recompute them. + */ + if (!dl_rq->dl_nr_running) { + dl_rq->earliest_dl.curr = 0; + dl_rq->earliest_dl.next = 0; + cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0); + } else { + struct rb_node *leftmost = dl_rq->rb_leftmost; + struct sched_dl_entity *entry; + + entry = rb_entry(leftmost, struct sched_dl_entity, rb_node); + dl_rq->earliest_dl.curr = entry->deadline; + dl_rq->earliest_dl.next = next_deadline(rq); + cpudl_set(&rq->rd->cpudl, rq->cpu, entry->deadline, 1); + } +} + +#else + +static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {} +static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {} + +#endif /* CONFIG_SMP */ + +static inline +void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + int prio = dl_task_of(dl_se)->prio; + u64 deadline = dl_se->deadline; + + WARN_ON(!dl_prio(prio)); + dl_rq->dl_nr_running++; + add_nr_running(rq_of_dl_rq(dl_rq), 1); + + inc_dl_deadline(dl_rq, deadline); + inc_dl_migration(dl_se, dl_rq); +} + +static inline +void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) +{ + int prio = dl_task_of(dl_se)->prio; + + WARN_ON(!dl_prio(prio)); + WARN_ON(!dl_rq->dl_nr_running); + dl_rq->dl_nr_running--; + sub_nr_running(rq_of_dl_rq(dl_rq), 1); + + dec_dl_deadline(dl_rq, dl_se->deadline); + dec_dl_migration(dl_se, dl_rq); +} + +static void __enqueue_dl_entity(struct sched_dl_entity *dl_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rb_node **link = &dl_rq->rb_root.rb_node; + struct rb_node *parent = NULL; + struct sched_dl_entity *entry; + int leftmost = 1; + + BUG_ON(!RB_EMPTY_NODE(&dl_se->rb_node)); + + while (*link) { + parent = *link; + entry = rb_entry(parent, struct sched_dl_entity, rb_node); + if (dl_time_before(dl_se->deadline, entry->deadline)) + link = &parent->rb_left; + else { + link = &parent->rb_right; + leftmost = 0; + } + } + + if (leftmost) + dl_rq->rb_leftmost = &dl_se->rb_node; + + rb_link_node(&dl_se->rb_node, parent, link); + rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root); + + inc_dl_tasks(dl_se, dl_rq); +} + +static void __dequeue_dl_entity(struct sched_dl_entity *dl_se) +{ + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + + if (RB_EMPTY_NODE(&dl_se->rb_node)) + return; + + if (dl_rq->rb_leftmost == &dl_se->rb_node) { + struct rb_node *next_node; + + next_node = rb_next(&dl_se->rb_node); + dl_rq->rb_leftmost = next_node; + } + + rb_erase(&dl_se->rb_node, &dl_rq->rb_root); + RB_CLEAR_NODE(&dl_se->rb_node); + + dec_dl_tasks(dl_se, dl_rq); +} + +static void +enqueue_dl_entity(struct sched_dl_entity *dl_se, + struct sched_dl_entity *pi_se, int flags) +{ + BUG_ON(on_dl_rq(dl_se)); + + /* + * If this is a wakeup or a new instance, the scheduling + * parameters of the task might need updating. Otherwise, + * we want a replenishment of its runtime. + */ + if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH) + replenish_dl_entity(dl_se, pi_se); + else + update_dl_entity(dl_se, pi_se); + + __enqueue_dl_entity(dl_se); +} + +static void dequeue_dl_entity(struct sched_dl_entity *dl_se) +{ + __dequeue_dl_entity(dl_se); +} + +static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + struct task_struct *pi_task = rt_mutex_get_top_task(p); + struct sched_dl_entity *pi_se = &p->dl; + + /* + * Use the scheduling parameters of the top pi-waiter + * task if we have one and its (relative) deadline is + * smaller than our one... OTW we keep our runtime and + * deadline. + */ + if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) + pi_se = &pi_task->dl; + + /* + * If p is throttled, we do nothing. In fact, if it exhausted + * its budget it needs a replenishment and, since it now is on + * its rq, the bandwidth timer callback (which clearly has not + * run yet) will take care of this. + */ + if (p->dl.dl_throttled) + return; + + enqueue_dl_entity(&p->dl, pi_se, flags); + + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) + enqueue_pushable_dl_task(rq, p); +} + +static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + dequeue_dl_entity(&p->dl); + dequeue_pushable_dl_task(rq, p); +} + +static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) +{ + update_curr_dl(rq); + __dequeue_task_dl(rq, p, flags); +} + +/* + * Yield task semantic for -deadline tasks is: + * + * get off from the CPU until our next instance, with + * a new runtime. This is of little use now, since we + * don't have a bandwidth reclaiming mechanism. Anyway, + * bandwidth reclaiming is planned for the future, and + * yield_task_dl will indicate that some spare budget + * is available for other task instances to use it. + */ +static void yield_task_dl(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + /* + * We make the task go to sleep until its current deadline by + * forcing its runtime to zero. This way, update_curr_dl() stops + * it and the bandwidth timer will wake it up and will give it + * new scheduling parameters (thanks to dl_yielded=1). + */ + if (p->dl.runtime > 0) { + rq->curr->dl.dl_yielded = 1; + p->dl.runtime = 0; + } + update_curr_dl(rq); +} + +#ifdef CONFIG_SMP + +static int find_later_rq(struct task_struct *task); + +static int +select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) +{ + struct task_struct *curr; + struct rq *rq; + + if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK) + goto out; + + rq = cpu_rq(cpu); + + rcu_read_lock(); + curr = ACCESS_ONCE(rq->curr); /* unlocked access */ + + /* + * If we are dealing with a -deadline task, we must + * decide where to wake it up. + * If it has a later deadline and the current task + * on this rq can't move (provided the waking task + * can!) we prefer to send it somewhere else. On the + * other hand, if it has a shorter deadline, we + * try to make it stay here, it might be important. + */ + if (unlikely(dl_task(curr)) && + (curr->nr_cpus_allowed < 2 || + !dl_entity_preempt(&p->dl, &curr->dl)) && + (p->nr_cpus_allowed > 1)) { + int target = find_later_rq(p); + + if (target != -1) + cpu = target; + } + rcu_read_unlock(); + +out: + return cpu; +} + +static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) +{ + /* + * Current can't be migrated, useless to reschedule, + * let's hope p can move out. + */ + if (rq->curr->nr_cpus_allowed == 1 || + cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1) + return; + + /* + * p is migratable, so let's not schedule it and + * see if it is pushed or pulled somewhere else. + */ + if (p->nr_cpus_allowed != 1 && + cpudl_find(&rq->rd->cpudl, p, NULL) != -1) + return; + + resched_task(rq->curr); +} + +static int pull_dl_task(struct rq *this_rq); + +#endif /* CONFIG_SMP */ + +/* + * Only called when both the current and waking task are -deadline + * tasks. + */ +static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p, + int flags) +{ + if (dl_entity_preempt(&p->dl, &rq->curr->dl)) { + resched_task(rq->curr); + return; + } + +#ifdef CONFIG_SMP + /* + * In the unlikely case current and p have the same deadline + * let us try to decide what's the best thing to do... + */ + if ((p->dl.deadline == rq->curr->dl.deadline) && + !test_tsk_need_resched(rq->curr)) + check_preempt_equal_dl(rq, p); +#endif /* CONFIG_SMP */ +} + +#ifdef CONFIG_SCHED_HRTICK +static void start_hrtick_dl(struct rq *rq, struct task_struct *p) +{ + s64 delta = p->dl.dl_runtime - p->dl.runtime; + + if (delta > 10000) + hrtick_start(rq, p->dl.runtime); +} +#endif + +static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, + struct dl_rq *dl_rq) +{ + struct rb_node *left = dl_rq->rb_leftmost; + + if (!left) + return NULL; + + return rb_entry(left, struct sched_dl_entity, rb_node); +} + +struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) +{ + struct sched_dl_entity *dl_se; + struct task_struct *p; + struct dl_rq *dl_rq; + + dl_rq = &rq->dl; + + if (need_pull_dl_task(rq, prev)) { + pull_dl_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a stop task can slip in, in which case we need to + * re-start task selection. + */ + if (rq->stop && rq->stop->on_rq) + return RETRY_TASK; + } + + /* + * When prev is DL, we may throttle it in put_prev_task(). + * So, we update time before we check for dl_nr_running. + */ + if (prev->sched_class == &dl_sched_class) + update_curr_dl(rq); + + if (unlikely(!dl_rq->dl_nr_running)) + return NULL; + + put_prev_task(rq, prev); + + dl_se = pick_next_dl_entity(rq, dl_rq); + BUG_ON(!dl_se); + + p = dl_task_of(dl_se); + p->se.exec_start = rq_clock_task(rq); + + /* Running task will never be pushed. */ + dequeue_pushable_dl_task(rq, p); + +#ifdef CONFIG_SCHED_HRTICK + if (hrtick_enabled(rq)) + start_hrtick_dl(rq, p); +#endif + + set_post_schedule(rq); + + return p; +} + +static void put_prev_task_dl(struct rq *rq, struct task_struct *p) +{ + update_curr_dl(rq); + + if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) + enqueue_pushable_dl_task(rq, p); +} + +static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) +{ + update_curr_dl(rq); + +#ifdef CONFIG_SCHED_HRTICK + if (hrtick_enabled(rq) && queued && p->dl.runtime > 0) + start_hrtick_dl(rq, p); +#endif +} + +static void task_fork_dl(struct task_struct *p) +{ + /* + * SCHED_DEADLINE tasks cannot fork and this is achieved through + * sched_fork() + */ +} + +static void task_dead_dl(struct task_struct *p) +{ + struct hrtimer *timer = &p->dl.dl_timer; + struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); + + /* + * Since we are TASK_DEAD we won't slip out of the domain! + */ + raw_spin_lock_irq(&dl_b->lock); + dl_b->total_bw -= p->dl.dl_bw; + raw_spin_unlock_irq(&dl_b->lock); + + hrtimer_cancel(timer); +} + +static void set_curr_task_dl(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + p->se.exec_start = rq_clock_task(rq); + + /* You can't push away the running task */ + dequeue_pushable_dl_task(rq, p); +} + +#ifdef CONFIG_SMP + +/* Only try algorithms three times */ +#define DL_MAX_TRIES 3 + +static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) +{ + if (!task_running(rq, p) && + (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) && + (p->nr_cpus_allowed > 1)) + return 1; + + return 0; +} + +/* Returns the second earliest -deadline task, NULL otherwise */ +static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu) +{ + struct rb_node *next_node = rq->dl.rb_leftmost; + struct sched_dl_entity *dl_se; + struct task_struct *p = NULL; + +next_node: + next_node = rb_next(next_node); + if (next_node) { + dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node); + p = dl_task_of(dl_se); + + if (pick_dl_task(rq, p, cpu)) + return p; + + goto next_node; + } + + return NULL; +} + +static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl); + +static int find_later_rq(struct task_struct *task) +{ + struct sched_domain *sd; + struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl); + int this_cpu = smp_processor_id(); + int best_cpu, cpu = task_cpu(task); + + /* Make sure the mask is initialized first */ + if (unlikely(!later_mask)) + return -1; + + if (task->nr_cpus_allowed == 1) + return -1; + + best_cpu = cpudl_find(&task_rq(task)->rd->cpudl, + task, later_mask); + if (best_cpu == -1) + return -1; + + /* + * If we are here, some target has been found, + * the most suitable of which is cached in best_cpu. + * This is, among the runqueues where the current tasks + * have later deadlines than the task's one, the rq + * with the latest possible one. + * + * Now we check how well this matches with task's + * affinity and system topology. + * + * The last cpu where the task run is our first + * guess, since it is most likely cache-hot there. + */ + if (cpumask_test_cpu(cpu, later_mask)) + return cpu; + /* + * Check if this_cpu is to be skipped (i.e., it is + * not in the mask) or not. + */ + if (!cpumask_test_cpu(this_cpu, later_mask)) + this_cpu = -1; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_AFFINE) { + + /* + * If possible, preempting this_cpu is + * cheaper than migrating. + */ + if (this_cpu != -1 && + cpumask_test_cpu(this_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return this_cpu; + } + + /* + * Last chance: if best_cpu is valid and is + * in the mask, that becomes our choice. + */ + if (best_cpu < nr_cpu_ids && + cpumask_test_cpu(best_cpu, sched_domain_span(sd))) { + rcu_read_unlock(); + return best_cpu; + } + } + } + rcu_read_unlock(); + + /* + * At this point, all our guesses failed, we just return + * 'something', and let the caller sort the things out. + */ + if (this_cpu != -1) + return this_cpu; + + cpu = cpumask_any(later_mask); + if (cpu < nr_cpu_ids) + return cpu; + + return -1; +} + +/* Locks the rq it finds */ +static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) +{ + struct rq *later_rq = NULL; + int tries; + int cpu; + + for (tries = 0; tries < DL_MAX_TRIES; tries++) { + cpu = find_later_rq(task); + + if ((cpu == -1) || (cpu == rq->cpu)) + break; + + later_rq = cpu_rq(cpu); + + /* Retry if something changed. */ + if (double_lock_balance(rq, later_rq)) { + if (unlikely(task_rq(task) != rq || + !cpumask_test_cpu(later_rq->cpu, + &task->cpus_allowed) || + task_running(rq, task) || !task->on_rq)) { + double_unlock_balance(rq, later_rq); + later_rq = NULL; + break; + } + } + + /* + * If the rq we found has no -deadline task, or + * its earliest one has a later deadline than our + * task, the rq is a good one. + */ + if (!later_rq->dl.dl_nr_running || + dl_time_before(task->dl.deadline, + later_rq->dl.earliest_dl.curr)) + break; + + /* Otherwise we try again. */ + double_unlock_balance(rq, later_rq); + later_rq = NULL; + } + + return later_rq; +} + +static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) +{ + struct task_struct *p; + + if (!has_pushable_dl_tasks(rq)) + return NULL; + + p = rb_entry(rq->dl.pushable_dl_tasks_leftmost, + struct task_struct, pushable_dl_tasks); + + BUG_ON(rq->cpu != task_cpu(p)); + BUG_ON(task_current(rq, p)); + BUG_ON(p->nr_cpus_allowed <= 1); + + BUG_ON(!p->on_rq); + BUG_ON(!dl_task(p)); + + return p; +} + +/* + * See if the non running -deadline tasks on this rq + * can be sent to some other CPU where they can preempt + * and start executing. + */ +static int push_dl_task(struct rq *rq) +{ + struct task_struct *next_task; + struct rq *later_rq; + + if (!rq->dl.overloaded) + return 0; + + next_task = pick_next_pushable_dl_task(rq); + if (!next_task) + return 0; + +retry: + if (unlikely(next_task == rq->curr)) { + WARN_ON(1); + return 0; + } + + /* + * If next_task preempts rq->curr, and rq->curr + * can move away, it makes sense to just reschedule + * without going further in pushing next_task. + */ + if (dl_task(rq->curr) && + dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && + rq->curr->nr_cpus_allowed > 1) { + resched_task(rq->curr); + return 0; + } + + /* We might release rq lock */ + get_task_struct(next_task); + + /* Will lock the rq it'll find */ + later_rq = find_lock_later_rq(next_task, rq); + if (!later_rq) { + struct task_struct *task; + + /* + * We must check all this again, since + * find_lock_later_rq releases rq->lock and it is + * then possible that next_task has migrated. + */ + task = pick_next_pushable_dl_task(rq); + if (task_cpu(next_task) == rq->cpu && task == next_task) { + /* + * The task is still there. We don't try + * again, some other cpu will pull it when ready. + */ + dequeue_pushable_dl_task(rq, next_task); + goto out; + } + + if (!task) + /* No more tasks */ + goto out; + + put_task_struct(next_task); + next_task = task; + goto retry; + } + + deactivate_task(rq, next_task, 0); + set_task_cpu(next_task, later_rq->cpu); + activate_task(later_rq, next_task, 0); + + resched_task(later_rq->curr); + + double_unlock_balance(rq, later_rq); + +out: + put_task_struct(next_task); + + return 1; +} + +static void push_dl_tasks(struct rq *rq) +{ + /* Terminates as it moves a -deadline task */ + while (push_dl_task(rq)) + ; +} + +static int pull_dl_task(struct rq *this_rq) +{ + int this_cpu = this_rq->cpu, ret = 0, cpu; + struct task_struct *p; + struct rq *src_rq; + u64 dmin = LONG_MAX; + + if (likely(!dl_overloaded(this_rq))) + return 0; + + /* + * Match the barrier from dl_set_overloaded; this guarantees that if we + * see overloaded we must also see the dlo_mask bit. + */ + smp_rmb(); + + for_each_cpu(cpu, this_rq->rd->dlo_mask) { + if (this_cpu == cpu) + continue; + + src_rq = cpu_rq(cpu); + + /* + * It looks racy, abd it is! However, as in sched_rt.c, + * we are fine with this. + */ + if (this_rq->dl.dl_nr_running && + dl_time_before(this_rq->dl.earliest_dl.curr, + src_rq->dl.earliest_dl.next)) + continue; + + /* Might drop this_rq->lock */ + double_lock_balance(this_rq, src_rq); + + /* + * If there are no more pullable tasks on the + * rq, we're done with it. + */ + if (src_rq->dl.dl_nr_running <= 1) + goto skip; + + p = pick_next_earliest_dl_task(src_rq, this_cpu); + + /* + * We found a task to be pulled if: + * - it preempts our current (if there's one), + * - it will preempt the last one we pulled (if any). + */ + if (p && dl_time_before(p->dl.deadline, dmin) && + (!this_rq->dl.dl_nr_running || + dl_time_before(p->dl.deadline, + this_rq->dl.earliest_dl.curr))) { + WARN_ON(p == src_rq->curr); + WARN_ON(!p->on_rq); + + /* + * Then we pull iff p has actually an earlier + * deadline than the current task of its runqueue. + */ + if (dl_time_before(p->dl.deadline, + src_rq->curr->dl.deadline)) + goto skip; + + ret = 1; + + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + dmin = p->dl.deadline; + + /* Is there any other task even earlier? */ + } +skip: + double_unlock_balance(this_rq, src_rq); + } + + return ret; +} + +static void post_schedule_dl(struct rq *rq) +{ + push_dl_tasks(rq); +} + +/* + * Since the task is not running and a reschedule is not going to happen + * anytime soon on its runqueue, we try pushing it away now. + */ +static void task_woken_dl(struct rq *rq, struct task_struct *p) +{ + if (!task_running(rq, p) && + !test_tsk_need_resched(rq->curr) && + has_pushable_dl_tasks(rq) && + p->nr_cpus_allowed > 1 && + dl_task(rq->curr) && + (rq->curr->nr_cpus_allowed < 2 || + dl_entity_preempt(&rq->curr->dl, &p->dl))) { + push_dl_tasks(rq); + } +} + +static void set_cpus_allowed_dl(struct task_struct *p, + const struct cpumask *new_mask) +{ + struct rq *rq; + int weight; + + BUG_ON(!dl_task(p)); + + /* + * Update only if the task is actually running (i.e., + * it is on the rq AND it is not throttled). + */ + if (!on_dl_rq(&p->dl)) + return; + + weight = cpumask_weight(new_mask); + + /* + * Only update if the process changes its state from whether it + * can migrate or not. + */ + if ((p->nr_cpus_allowed > 1) == (weight > 1)) + return; + + rq = task_rq(p); + + /* + * The process used to be able to migrate OR it can now migrate + */ + if (weight <= 1) { + if (!task_current(rq, p)) + dequeue_pushable_dl_task(rq, p); + BUG_ON(!rq->dl.dl_nr_migratory); + rq->dl.dl_nr_migratory--; + } else { + if (!task_current(rq, p)) + enqueue_pushable_dl_task(rq, p); + rq->dl.dl_nr_migratory++; + } + + update_dl_migration(&rq->dl); +} + +/* Assumes rq->lock is held */ +static void rq_online_dl(struct rq *rq) +{ + if (rq->dl.overloaded) + dl_set_overload(rq); + + if (rq->dl.dl_nr_running > 0) + cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1); +} + +/* Assumes rq->lock is held */ +static void rq_offline_dl(struct rq *rq) +{ + if (rq->dl.overloaded) + dl_clear_overload(rq); + + cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0); +} + +void init_sched_dl_class(void) +{ + unsigned int i; + + for_each_possible_cpu(i) + zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i), + GFP_KERNEL, cpu_to_node(i)); +} + +#endif /* CONFIG_SMP */ + +static void switched_from_dl(struct rq *rq, struct task_struct *p) +{ + if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy)) + hrtimer_try_to_cancel(&p->dl.dl_timer); + +#ifdef CONFIG_SMP + /* + * Since this might be the only -deadline task on the rq, + * this is the right place to try to pull some other one + * from an overloaded cpu, if any. + */ + if (!rq->dl.dl_nr_running) + pull_dl_task(rq); +#endif +} + +/* + * When switching to -deadline, we may overload the rq, then + * we try to push someone off, if possible. + */ +static void switched_to_dl(struct rq *rq, struct task_struct *p) +{ + int check_resched = 1; + + /* + * If p is throttled, don't consider the possibility + * of preempting rq->curr, the check will be done right + * after its runtime will get replenished. + */ + if (unlikely(p->dl.dl_throttled)) + return; + + if (p->on_rq && rq->curr != p) { +#ifdef CONFIG_SMP + if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p)) + /* Only reschedule if pushing failed */ + check_resched = 0; +#endif /* CONFIG_SMP */ + if (check_resched && task_has_dl_policy(rq->curr)) + check_preempt_curr_dl(rq, p, 0); + } +} + +/* + * If the scheduling parameters of a -deadline task changed, + * a push or pull operation might be needed. + */ +static void prio_changed_dl(struct rq *rq, struct task_struct *p, + int oldprio) +{ + if (p->on_rq || rq->curr == p) { +#ifdef CONFIG_SMP + /* + * This might be too much, but unfortunately + * we don't have the old deadline value, and + * we can't argue if the task is increasing + * or lowering its prio, so... + */ + if (!rq->dl.overloaded) + pull_dl_task(rq); + + /* + * If we now have a earlier deadline task than p, + * then reschedule, provided p is still on this + * runqueue. + */ + if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) && + rq->curr == p) + resched_task(p); +#else + /* + * Again, we don't know if p has a earlier + * or later deadline, so let's blindly set a + * (maybe not needed) rescheduling point. + */ + resched_task(p); +#endif /* CONFIG_SMP */ + } else + switched_to_dl(rq, p); +} + +const struct sched_class dl_sched_class = { + .next = &rt_sched_class, + .enqueue_task = enqueue_task_dl, + .dequeue_task = dequeue_task_dl, + .yield_task = yield_task_dl, + + .check_preempt_curr = check_preempt_curr_dl, + + .pick_next_task = pick_next_task_dl, + .put_prev_task = put_prev_task_dl, + +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_dl, + .set_cpus_allowed = set_cpus_allowed_dl, + .rq_online = rq_online_dl, + .rq_offline = rq_offline_dl, + .post_schedule = post_schedule_dl, + .task_woken = task_woken_dl, +#endif + + .set_curr_task = set_curr_task_dl, + .task_tick = task_tick_dl, + .task_fork = task_fork_dl, + .task_dead = task_dead_dl, + + .prio_changed = prio_changed_dl, + .switched_from = switched_from_dl, + .switched_to = switched_to_dl, +}; diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index e076bddd4c6..627b3c34b82 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -15,6 +15,7 @@ #include <linux/seq_file.h> #include <linux/kallsyms.h> #include <linux/utsname.h> +#include <linux/mempolicy.h> #include "sched.h" @@ -110,8 +111,7 @@ static char *task_group_path(struct task_group *tg) if (autogroup_path(tg, group_path, PATH_MAX)) return group_path; - cgroup_path(tg->css.cgroup, group_path, PATH_MAX); - return group_path; + return cgroup_path(tg->css.cgroup, group_path, PATH_MAX); } #endif @@ -124,7 +124,7 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) SEQ_printf(m, " "); SEQ_printf(m, "%15s %5d %9Ld.%06ld %9Ld %5d ", - p->comm, p->pid, + p->comm, task_pid_nr(p), SPLIT_NS(p->se.vruntime), (long long)(p->nvcsw + p->nivcsw), p->prio); @@ -137,6 +137,9 @@ print_task(struct seq_file *m, struct rq *rq, struct task_struct *p) SEQ_printf(m, "%15Ld %15Ld %15Ld.%06ld %15Ld.%06ld %15Ld.%06ld", 0LL, 0LL, 0LL, 0L, 0LL, 0L, 0LL, 0L); #endif +#ifdef CONFIG_NUMA_BALANCING + SEQ_printf(m, " %d", task_node(p)); +#endif #ifdef CONFIG_CGROUP_SCHED SEQ_printf(m, " %s", task_group_path(task_group(p))); #endif @@ -159,7 +162,7 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu) read_lock_irqsave(&tasklist_lock, flags); do_each_thread(g, p) { - if (!p->on_rq || task_cpu(p) != rq_cpu) + if (task_cpu(p) != rq_cpu) continue; print_task(m, rq, p); @@ -225,6 +228,14 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq) atomic_read(&cfs_rq->tg->runnable_avg)); #endif #endif +#ifdef CONFIG_CFS_BANDWIDTH + SEQ_printf(m, " .%-30s: %d\n", "tg->cfs_bandwidth.timer_active", + cfs_rq->tg->cfs_bandwidth.timer_active); + SEQ_printf(m, " .%-30s: %d\n", "throttled", + cfs_rq->throttled); + SEQ_printf(m, " .%-30s: %d\n", "throttle_count", + cfs_rq->throttle_count); +#endif #ifdef CONFIG_FAIR_GROUP_SCHED print_cfs_group_stats(m, cpu, cfs_rq->tg); @@ -289,7 +300,7 @@ do { \ P(nr_load_updates); P(nr_uninterruptible); PN(next_balance); - P(curr->pid); + SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); PN(clock); P(cpu_load[0]); P(cpu_load[1]); @@ -309,6 +320,7 @@ do { \ P(sched_goidle); #ifdef CONFIG_SMP P64(avg_idle); + P64(max_idle_balance_cost); #endif P(ttwu_count); @@ -345,7 +357,7 @@ static void sched_debug_header(struct seq_file *m) cpu_clk = local_clock(); local_irq_restore(flags); - SEQ_printf(m, "Sched Debug Version: v0.10, %s %.*s\n", + SEQ_printf(m, "Sched Debug Version: v0.11, %s %.*s\n", init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); @@ -359,7 +371,7 @@ static void sched_debug_header(struct seq_file *m) PN(cpu_clk); P(jiffies); #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK - P(sched_clock_stable); + P(sched_clock_stable()); #endif #undef PN #undef P @@ -488,11 +500,61 @@ static int __init init_sched_debug_procfs(void) __initcall(init_sched_debug_procfs); +#define __P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)F) +#define P(F) \ + SEQ_printf(m, "%-45s:%21Ld\n", #F, (long long)p->F) +#define __PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)F)) +#define PN(F) \ + SEQ_printf(m, "%-45s:%14Ld.%06ld\n", #F, SPLIT_NS((long long)p->F)) + + +static void sched_show_numa(struct task_struct *p, struct seq_file *m) +{ +#ifdef CONFIG_NUMA_BALANCING + struct mempolicy *pol; + int node, i; + + if (p->mm) + P(mm->numa_scan_seq); + + task_lock(p); + pol = p->mempolicy; + if (pol && !(pol->flags & MPOL_F_MORON)) + pol = NULL; + mpol_get(pol); + task_unlock(p); + + SEQ_printf(m, "numa_migrations, %ld\n", xchg(&p->numa_pages_migrated, 0)); + + for_each_online_node(node) { + for (i = 0; i < 2; i++) { + unsigned long nr_faults = -1; + int cpu_current, home_node; + + if (p->numa_faults_memory) + nr_faults = p->numa_faults_memory[2*node + i]; + + cpu_current = !i ? (task_node(p) == node) : + (pol && node_isset(node, pol->v.nodes)); + + home_node = (p->numa_preferred_nid == node); + + SEQ_printf(m, "numa_faults_memory, %d, %d, %d, %d, %ld\n", + i, node, cpu_current, home_node, nr_faults); + } + } + + mpol_put(pol); +#endif +} + void proc_sched_show_task(struct task_struct *p, struct seq_file *m) { unsigned long nr_switches; - SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, p->pid, + SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr(p), get_nr_threads(p)); SEQ_printf(m, "---------------------------------------------------------" @@ -546,7 +608,7 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) avg_atom = p->se.sum_exec_runtime; if (nr_switches) - do_div(avg_atom, nr_switches); + avg_atom = div64_ul(avg_atom, nr_switches); else avg_atom = -1LL; @@ -591,6 +653,8 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) SEQ_printf(m, "%-45s:%21Ld\n", "clock-delta", (long long)(t1-t0)); } + + sched_show_numa(p, m); } void proc_sched_set_task(struct task_struct *p) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9b3fe1cd8f4..fea7d3335e1 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -178,59 +178,61 @@ void sched_init_granularity(void) update_sysctl(); } -#if BITS_PER_LONG == 32 -# define WMULT_CONST (~0UL) -#else -# define WMULT_CONST (1UL << 32) -#endif - +#define WMULT_CONST (~0U) #define WMULT_SHIFT 32 -/* - * Shift right and round: - */ -#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) +static void __update_inv_weight(struct load_weight *lw) +{ + unsigned long w; + + if (likely(lw->inv_weight)) + return; + + w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) + lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; + else + lw->inv_weight = WMULT_CONST / w; +} /* - * delta *= weight / lw + * delta_exec * weight / lw.weight + * OR + * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT + * + * Either weight := NICE_0_LOAD and lw \e prio_to_wmult[], in which case + * we're guaranteed shift stays positive because inv_weight is guaranteed to + * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22. + * + * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus + * weight/lw.weight <= 1, and therefore our shift will also be positive. */ -static unsigned long -calc_delta_mine(unsigned long delta_exec, unsigned long weight, - struct load_weight *lw) +static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw) { - u64 tmp; + u64 fact = scale_load_down(weight); + int shift = WMULT_SHIFT; - /* - * weight can be less than 2^SCHED_LOAD_RESOLUTION for task group sched - * entities since MIN_SHARES = 2. Treat weight as 1 if less than - * 2^SCHED_LOAD_RESOLUTION. - */ - if (likely(weight > (1UL << SCHED_LOAD_RESOLUTION))) - tmp = (u64)delta_exec * scale_load_down(weight); - else - tmp = (u64)delta_exec; + __update_inv_weight(lw); - if (!lw->inv_weight) { - unsigned long w = scale_load_down(lw->weight); - - if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) - lw->inv_weight = 1; - else if (unlikely(!w)) - lw->inv_weight = WMULT_CONST; - else - lw->inv_weight = WMULT_CONST / w; + if (unlikely(fact >> 32)) { + while (fact >> 32) { + fact >>= 1; + shift--; + } } - /* - * Check whether we'd overflow the 64-bit multiplication: - */ - if (unlikely(tmp > WMULT_CONST)) - tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight, - WMULT_SHIFT/2); - else - tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT); + /* hint to use a 32x32->64 mul */ + fact = (u64)(u32)fact * lw->inv_weight; - return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); + while (fact >> 32) { + fact >>= 1; + shift--; + } + + return mul_u64_u32_shr(delta_exec, fact, shift); } @@ -320,13 +322,13 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) /* Do the two (enqueued) entities belong to the same group ? */ -static inline int +static inline struct cfs_rq * is_same_group(struct sched_entity *se, struct sched_entity *pse) { if (se->cfs_rq == pse->cfs_rq) - return 1; + return se->cfs_rq; - return 0; + return NULL; } static inline struct sched_entity *parent_entity(struct sched_entity *se) @@ -334,17 +336,6 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se) return se->parent; } -/* return depth at which a sched entity is present in the hierarchy */ -static inline int depth_se(struct sched_entity *se) -{ - int depth = 0; - - for_each_sched_entity(se) - depth++; - - return depth; -} - static void find_matching_se(struct sched_entity **se, struct sched_entity **pse) { @@ -358,8 +349,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) */ /* First walk up until both entities are at same depth */ - se_depth = depth_se(*se); - pse_depth = depth_se(*pse); + se_depth = (*se)->depth; + pse_depth = (*pse)->depth; while (se_depth > pse_depth) { se_depth--; @@ -424,12 +415,6 @@ static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) #define for_each_leaf_cfs_rq(rq, cfs_rq) \ for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL) -static inline int -is_same_group(struct sched_entity *se, struct sched_entity *pse) -{ - return 1; -} - static inline struct sched_entity *parent_entity(struct sched_entity *se) { return NULL; @@ -443,7 +428,7 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) #endif /* CONFIG_FAIR_GROUP_SCHED */ static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec); +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -612,11 +597,10 @@ int sched_proc_update_handler(struct ctl_table *table, int write, /* * delta /= w */ -static inline unsigned long -calc_delta_fair(unsigned long delta, struct sched_entity *se) +static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se) { if (unlikely(se->load.weight != NICE_0_LOAD)) - delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load); + delta = __calc_delta(delta, NICE_0_LOAD, &se->load); return delta; } @@ -665,7 +649,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) update_load_add(&lw, se->load.weight); load = &lw; } - slice = calc_delta_mine(slice, se->load.weight, load); + slice = __calc_delta(slice, se->load.weight, load); } return slice; } @@ -681,6 +665,8 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_SMP +static unsigned long task_h_load(struct task_struct *p); + static inline void __update_task_entity_contrib(struct sched_entity *se); /* Give new task start runnable values to heavy its load in infant time */ @@ -701,47 +687,32 @@ void init_task_runnable_average(struct task_struct *p) #endif /* - * Update the current task's runtime statistics. Skip current tasks that - * are not in our scheduling class. + * Update the current task's runtime statistics. */ -static inline void -__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, - unsigned long delta_exec) -{ - unsigned long delta_exec_weighted; - - schedstat_set(curr->statistics.exec_max, - max((u64)delta_exec, curr->statistics.exec_max)); - - curr->sum_exec_runtime += delta_exec; - schedstat_add(cfs_rq, exec_clock, delta_exec); - delta_exec_weighted = calc_delta_fair(delta_exec, curr); - - curr->vruntime += delta_exec_weighted; - update_min_vruntime(cfs_rq); -} - static void update_curr(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; u64 now = rq_clock_task(rq_of(cfs_rq)); - unsigned long delta_exec; + u64 delta_exec; if (unlikely(!curr)) return; - /* - * Get the amount of time the current task was running - * since the last time we changed load (this cannot - * overflow on 32 bits): - */ - delta_exec = (unsigned long)(now - curr->exec_start); - if (!delta_exec) + delta_exec = now - curr->exec_start; + if (unlikely((s64)delta_exec <= 0)) return; - __update_curr(cfs_rq, curr, delta_exec); curr->exec_start = now; + schedstat_set(curr->statistics.exec_max, + max(delta_exec, curr->statistics.exec_max)); + + curr->sum_exec_runtime += delta_exec; + schedstat_add(cfs_rq, exec_clock, delta_exec); + + curr->vruntime += calc_delta_fair(delta_exec, curr); + update_min_vruntime(cfs_rq); + if (entity_is_task(curr)) { struct task_struct *curtask = task_of(curr); @@ -818,11 +789,12 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) #ifdef CONFIG_NUMA_BALANCING /* - * numa task sample period in ms + * Approximate time to scan a full NUMA task in ms. The task scan period is + * calculated based on the tasks virtual memory size and + * numa_balancing_scan_size. */ -unsigned int sysctl_numa_balancing_scan_period_min = 100; -unsigned int sysctl_numa_balancing_scan_period_max = 100*50; -unsigned int sysctl_numa_balancing_scan_period_reset = 100*600; +unsigned int sysctl_numa_balancing_scan_period_min = 1000; +unsigned int sysctl_numa_balancing_scan_period_max = 60000; /* Portion of address space to scan in MB */ unsigned int sysctl_numa_balancing_scan_size = 256; @@ -830,41 +802,1057 @@ unsigned int sysctl_numa_balancing_scan_size = 256; /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ unsigned int sysctl_numa_balancing_scan_delay = 1000; -static void task_numa_placement(struct task_struct *p) +static unsigned int task_nr_scan_windows(struct task_struct *p) +{ + unsigned long rss = 0; + unsigned long nr_scan_pages; + + /* + * Calculations based on RSS as non-present and empty pages are skipped + * by the PTE scanner and NUMA hinting faults should be trapped based + * on resident pages + */ + nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT); + rss = get_mm_rss(p->mm); + if (!rss) + rss = nr_scan_pages; + + rss = round_up(rss, nr_scan_pages); + return rss / nr_scan_pages; +} + +/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */ +#define MAX_SCAN_WINDOW 2560 + +static unsigned int task_scan_min(struct task_struct *p) +{ + unsigned int scan, floor; + unsigned int windows = 1; + + if (sysctl_numa_balancing_scan_size < MAX_SCAN_WINDOW) + windows = MAX_SCAN_WINDOW / sysctl_numa_balancing_scan_size; + floor = 1000 / windows; + + scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p); + return max_t(unsigned int, floor, scan); +} + +static unsigned int task_scan_max(struct task_struct *p) +{ + unsigned int smin = task_scan_min(p); + unsigned int smax; + + /* Watch for min being lower than max due to floor calculations */ + smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); + return max(smin, smax); +} + +static void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running += (p->numa_preferred_nid != -1); + rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p)); +} + +static void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running -= (p->numa_preferred_nid != -1); + rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); +} + +struct numa_group { + atomic_t refcount; + + spinlock_t lock; /* nr_tasks, tasks */ + int nr_tasks; + pid_t gid; + struct list_head task_list; + + struct rcu_head rcu; + nodemask_t active_nodes; + unsigned long total_faults; + /* + * Faults_cpu is used to decide whether memory should move + * towards the CPU. As a consequence, these stats are weighted + * more by CPU use than by memory faults. + */ + unsigned long *faults_cpu; + unsigned long faults[0]; +}; + +/* Shared or private faults. */ +#define NR_NUMA_HINT_FAULT_TYPES 2 + +/* Memory and CPU locality */ +#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2) + +/* Averaged statistics, and temporary buffers. */ +#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2) + +pid_t task_numa_group_id(struct task_struct *p) +{ + return p->numa_group ? p->numa_group->gid : 0; +} + +static inline int task_faults_idx(int nid, int priv) +{ + return NR_NUMA_HINT_FAULT_TYPES * nid + priv; +} + +static inline unsigned long task_faults(struct task_struct *p, int nid) +{ + if (!p->numa_faults_memory) + return 0; + + return p->numa_faults_memory[task_faults_idx(nid, 0)] + + p->numa_faults_memory[task_faults_idx(nid, 1)]; +} + +static inline unsigned long group_faults(struct task_struct *p, int nid) +{ + if (!p->numa_group) + return 0; + + return p->numa_group->faults[task_faults_idx(nid, 0)] + + p->numa_group->faults[task_faults_idx(nid, 1)]; +} + +static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) +{ + return group->faults_cpu[task_faults_idx(nid, 0)] + + group->faults_cpu[task_faults_idx(nid, 1)]; +} + +/* + * These return the fraction of accesses done by a particular task, or + * task group, on a particular numa node. The group weight is given a + * larger multiplier, in order to group tasks together that are almost + * evenly spread out between numa nodes. + */ +static inline unsigned long task_weight(struct task_struct *p, int nid) +{ + unsigned long total_faults; + + if (!p->numa_faults_memory) + return 0; + + total_faults = p->total_numa_faults; + + if (!total_faults) + return 0; + + return 1000 * task_faults(p, nid) / total_faults; +} + +static inline unsigned long group_weight(struct task_struct *p, int nid) +{ + if (!p->numa_group || !p->numa_group->total_faults) + return 0; + + return 1000 * group_faults(p, nid) / p->numa_group->total_faults; +} + +bool should_numa_migrate_memory(struct task_struct *p, struct page * page, + int src_nid, int dst_cpu) +{ + struct numa_group *ng = p->numa_group; + int dst_nid = cpu_to_node(dst_cpu); + int last_cpupid, this_cpupid; + + this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); + + /* + * Multi-stage node selection is used in conjunction with a periodic + * migration fault to build a temporal task<->page relation. By using + * a two-stage filter we remove short/unlikely relations. + * + * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate + * a task's usage of a particular page (n_p) per total usage of this + * page (n_t) (in a given time-span) to a probability. + * + * Our periodic faults will sample this probability and getting the + * same result twice in a row, given these samples are fully + * independent, is then given by P(n)^2, provided our sample period + * is sufficiently short compared to the usage pattern. + * + * This quadric squishes small probabilities, making it less likely we + * act on an unlikely task<->page relation. + */ + last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + if (!cpupid_pid_unset(last_cpupid) && + cpupid_to_nid(last_cpupid) != dst_nid) + return false; + + /* Always allow migrate on private faults */ + if (cpupid_match_pid(p, last_cpupid)) + return true; + + /* A shared fault, but p->numa_group has not been set up yet. */ + if (!ng) + return true; + + /* + * Do not migrate if the destination is not a node that + * is actively used by this numa group. + */ + if (!node_isset(dst_nid, ng->active_nodes)) + return false; + + /* + * Source is a node that is not actively used by this + * numa group, while the destination is. Migrate. + */ + if (!node_isset(src_nid, ng->active_nodes)) + return true; + + /* + * Both source and destination are nodes in active + * use by this numa group. Maximize memory bandwidth + * by migrating from more heavily used groups, to less + * heavily used ones, spreading the load around. + * Use a 1/4 hysteresis to avoid spurious page movement. + */ + return group_faults(p, dst_nid) < (group_faults(p, src_nid) * 3 / 4); +} + +static unsigned long weighted_cpuload(const int cpu); +static unsigned long source_load(int cpu, int type); +static unsigned long target_load(int cpu, int type); +static unsigned long capacity_of(int cpu); +static long effective_load(struct task_group *tg, int cpu, long wl, long wg); + +/* Cached statistics for all CPUs within a node */ +struct numa_stats { + unsigned long nr_running; + unsigned long load; + + /* Total compute capacity of CPUs on a node */ + unsigned long compute_capacity; + + /* Approximate capacity in terms of runnable tasks on a node */ + unsigned long task_capacity; + int has_free_capacity; +}; + +/* + * XXX borrowed from update_sg_lb_stats + */ +static void update_numa_stats(struct numa_stats *ns, int nid) +{ + int cpu, cpus = 0; + + memset(ns, 0, sizeof(*ns)); + for_each_cpu(cpu, cpumask_of_node(nid)) { + struct rq *rq = cpu_rq(cpu); + + ns->nr_running += rq->nr_running; + ns->load += weighted_cpuload(cpu); + ns->compute_capacity += capacity_of(cpu); + + cpus++; + } + + /* + * If we raced with hotplug and there are no CPUs left in our mask + * the @ns structure is NULL'ed and task_numa_compare() will + * not find this node attractive. + * + * We'll either bail at !has_free_capacity, or we'll detect a huge + * imbalance and bail there. + */ + if (!cpus) + return; + + ns->load = (ns->load * SCHED_CAPACITY_SCALE) / ns->compute_capacity; + ns->task_capacity = + DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE); + ns->has_free_capacity = (ns->nr_running < ns->task_capacity); +} + +struct task_numa_env { + struct task_struct *p; + + int src_cpu, src_nid; + int dst_cpu, dst_nid; + + struct numa_stats src_stats, dst_stats; + + int imbalance_pct; + + struct task_struct *best_task; + long best_imp; + int best_cpu; +}; + +static void task_numa_assign(struct task_numa_env *env, + struct task_struct *p, long imp) +{ + if (env->best_task) + put_task_struct(env->best_task); + if (p) + get_task_struct(p); + + env->best_task = p; + env->best_imp = imp; + env->best_cpu = env->dst_cpu; +} + +static bool load_too_imbalanced(long orig_src_load, long orig_dst_load, + long src_load, long dst_load, + struct task_numa_env *env) +{ + long imb, old_imb; + + /* We care about the slope of the imbalance, not the direction. */ + if (dst_load < src_load) + swap(dst_load, src_load); + + /* Is the difference below the threshold? */ + imb = dst_load * 100 - src_load * env->imbalance_pct; + if (imb <= 0) + return false; + + /* + * The imbalance is above the allowed threshold. + * Compare it with the old imbalance. + */ + if (orig_dst_load < orig_src_load) + swap(orig_dst_load, orig_src_load); + + old_imb = orig_dst_load * 100 - orig_src_load * env->imbalance_pct; + + /* Would this change make things worse? */ + return (imb > old_imb); +} + +/* + * This checks if the overall compute and NUMA accesses of the system would + * be improved if the source tasks was migrated to the target dst_cpu taking + * into account that it might be best if task running on the dst_cpu should + * be exchanged with the source task + */ +static void task_numa_compare(struct task_numa_env *env, + long taskimp, long groupimp) +{ + struct rq *src_rq = cpu_rq(env->src_cpu); + struct rq *dst_rq = cpu_rq(env->dst_cpu); + struct task_struct *cur; + long orig_src_load, src_load; + long orig_dst_load, dst_load; + long load; + long imp = (groupimp > 0) ? groupimp : taskimp; + + rcu_read_lock(); + cur = ACCESS_ONCE(dst_rq->curr); + if (cur->pid == 0) /* idle */ + cur = NULL; + + /* + * "imp" is the fault differential for the source task between the + * source and destination node. Calculate the total differential for + * the source task and potential destination task. The more negative + * the value is, the more rmeote accesses that would be expected to + * be incurred if the tasks were swapped. + */ + if (cur) { + /* Skip this swap candidate if cannot move to the source cpu */ + if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur))) + goto unlock; + + /* + * If dst and source tasks are in the same NUMA group, or not + * in any group then look only at task weights. + */ + if (cur->numa_group == env->p->numa_group) { + imp = taskimp + task_weight(cur, env->src_nid) - + task_weight(cur, env->dst_nid); + /* + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. + */ + if (cur->numa_group) + imp -= imp/16; + } else { + /* + * Compare the group weights. If a task is all by + * itself (not part of a group), use the task weight + * instead. + */ + if (env->p->numa_group) + imp = groupimp; + else + imp = taskimp; + + if (cur->numa_group) + imp += group_weight(cur, env->src_nid) - + group_weight(cur, env->dst_nid); + else + imp += task_weight(cur, env->src_nid) - + task_weight(cur, env->dst_nid); + } + } + + if (imp < env->best_imp) + goto unlock; + + if (!cur) { + /* Is there capacity at our destination? */ + if (env->src_stats.has_free_capacity && + !env->dst_stats.has_free_capacity) + goto unlock; + + goto balance; + } + + /* Balance doesn't matter much if we're running a task per cpu */ + if (src_rq->nr_running == 1 && dst_rq->nr_running == 1) + goto assign; + + /* + * In the overloaded case, try and keep the load balanced. + */ +balance: + orig_dst_load = env->dst_stats.load; + orig_src_load = env->src_stats.load; + + /* XXX missing capacity terms */ + load = task_h_load(env->p); + dst_load = orig_dst_load + load; + src_load = orig_src_load - load; + + if (cur) { + load = task_h_load(cur); + dst_load -= load; + src_load += load; + } + + if (load_too_imbalanced(orig_src_load, orig_dst_load, + src_load, dst_load, env)) + goto unlock; + +assign: + task_numa_assign(env, cur, imp); +unlock: + rcu_read_unlock(); +} + +static void task_numa_find_cpu(struct task_numa_env *env, + long taskimp, long groupimp) +{ + int cpu; + + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { + /* Skip this CPU if the source task cannot migrate */ + if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p))) + continue; + + env->dst_cpu = cpu; + task_numa_compare(env, taskimp, groupimp); + } +} + +static int task_numa_migrate(struct task_struct *p) +{ + struct task_numa_env env = { + .p = p, + + .src_cpu = task_cpu(p), + .src_nid = task_node(p), + + .imbalance_pct = 112, + + .best_task = NULL, + .best_imp = 0, + .best_cpu = -1 + }; + struct sched_domain *sd; + unsigned long taskweight, groupweight; + int nid, ret; + long taskimp, groupimp; + + /* + * Pick the lowest SD_NUMA domain, as that would have the smallest + * imbalance and would be the first to start moving tasks about. + * + * And we want to avoid any moving of tasks about, as that would create + * random movement of tasks -- counter the numa conditions we're trying + * to satisfy here. + */ + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); + if (sd) + env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + rcu_read_unlock(); + + /* + * Cpusets can break the scheduler domain tree into smaller + * balance domains, some of which do not cross NUMA boundaries. + * Tasks that are "trapped" in such domains cannot be migrated + * elsewhere, so there is no point in (re)trying. + */ + if (unlikely(!sd)) { + p->numa_preferred_nid = task_node(p); + return -EINVAL; + } + + taskweight = task_weight(p, env.src_nid); + groupweight = group_weight(p, env.src_nid); + update_numa_stats(&env.src_stats, env.src_nid); + env.dst_nid = p->numa_preferred_nid; + taskimp = task_weight(p, env.dst_nid) - taskweight; + groupimp = group_weight(p, env.dst_nid) - groupweight; + update_numa_stats(&env.dst_stats, env.dst_nid); + + /* If the preferred nid has free capacity, try to use it. */ + if (env.dst_stats.has_free_capacity) + task_numa_find_cpu(&env, taskimp, groupimp); + + /* No space available on the preferred nid. Look elsewhere. */ + if (env.best_cpu == -1) { + for_each_online_node(nid) { + if (nid == env.src_nid || nid == p->numa_preferred_nid) + continue; + + /* Only consider nodes where both task and groups benefit */ + taskimp = task_weight(p, nid) - taskweight; + groupimp = group_weight(p, nid) - groupweight; + if (taskimp < 0 && groupimp < 0) + continue; + + env.dst_nid = nid; + update_numa_stats(&env.dst_stats, env.dst_nid); + task_numa_find_cpu(&env, taskimp, groupimp); + } + } + + /* No better CPU than the current one was found. */ + if (env.best_cpu == -1) + return -EAGAIN; + + /* + * If the task is part of a workload that spans multiple NUMA nodes, + * and is migrating into one of the workload's active nodes, remember + * this node as the task's preferred numa node, so the workload can + * settle down. + * A task that migrated to a second choice node will be better off + * trying for a better one later. Do not set the preferred node here. + */ + if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); + + /* + * Reset the scan period if the task is being rescheduled on an + * alternative node to recheck if the tasks is now properly placed. + */ + p->numa_scan_period = task_scan_min(p); + + if (env.best_task == NULL) { + ret = migrate_task_to(p, env.best_cpu); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, env.best_cpu); + return ret; + } + + ret = migrate_swap(p, env.best_task); + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); + put_task_struct(env.best_task); + return ret; +} + +/* Attempt to migrate a task to a CPU on the preferred node. */ +static void numa_migrate_preferred(struct task_struct *p) { - int seq; + unsigned long interval = HZ; - if (!p->mm) /* for example, ksmd faulting in a user's mm */ + /* This task has no NUMA fault statistics yet */ + if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory)) return; + + /* Periodically retry migrating the task to the preferred node */ + interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16); + p->numa_migrate_retry = jiffies + interval; + + /* Success if task is already running on preferred CPU */ + if (task_node(p) == p->numa_preferred_nid) + return; + + /* Otherwise, try migrate to a CPU on the preferred node */ + task_numa_migrate(p); +} + +/* + * Find the nodes on which the workload is actively running. We do this by + * tracking the nodes from which NUMA hinting faults are triggered. This can + * be different from the set of nodes where the workload's memory is currently + * located. + * + * The bitmask is used to make smarter decisions on when to do NUMA page + * migrations, To prevent flip-flopping, and excessive page migrations, nodes + * are added when they cause over 6/16 of the maximum number of faults, but + * only removed when they drop below 3/16. + */ +static void update_numa_active_node_mask(struct numa_group *numa_group) +{ + unsigned long faults, max_faults = 0; + int nid; + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (faults > max_faults) + max_faults = faults; + } + + for_each_online_node(nid) { + faults = group_faults_cpu(numa_group, nid); + if (!node_isset(nid, numa_group->active_nodes)) { + if (faults > max_faults * 6 / 16) + node_set(nid, numa_group->active_nodes); + } else if (faults < max_faults * 3 / 16) + node_clear(nid, numa_group->active_nodes); + } +} + +/* + * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS + * increments. The more local the fault statistics are, the higher the scan + * period will be for the next scan window. If local/remote ratio is below + * NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) the + * scan period will decrease + */ +#define NUMA_PERIOD_SLOTS 10 +#define NUMA_PERIOD_THRESHOLD 3 + +/* + * Increase the scan period (slow down scanning) if the majority of + * our memory is already on our local node, or if the majority of + * the page accesses are shared with other processes. + * Otherwise, decrease the scan period. + */ +static void update_task_scan_period(struct task_struct *p, + unsigned long shared, unsigned long private) +{ + unsigned int period_slot; + int ratio; + int diff; + + unsigned long remote = p->numa_faults_locality[0]; + unsigned long local = p->numa_faults_locality[1]; + + /* + * If there were no record hinting faults then either the task is + * completely idle or all activity is areas that are not of interest + * to automatic numa balancing. Scan slower + */ + if (local + shared == 0) { + p->numa_scan_period = min(p->numa_scan_period_max, + p->numa_scan_period << 1); + + p->mm->numa_next_scan = jiffies + + msecs_to_jiffies(p->numa_scan_period); + + return; + } + + /* + * Prepare to scale scan period relative to the current period. + * == NUMA_PERIOD_THRESHOLD scan period stays the same + * < NUMA_PERIOD_THRESHOLD scan period decreases (scan faster) + * >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower) + */ + period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS); + ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote); + if (ratio >= NUMA_PERIOD_THRESHOLD) { + int slot = ratio - NUMA_PERIOD_THRESHOLD; + if (!slot) + slot = 1; + diff = slot * period_slot; + } else { + diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot; + + /* + * Scale scan rate increases based on sharing. There is an + * inverse relationship between the degree of sharing and + * the adjustment made to the scanning period. Broadly + * speaking the intent is that there is little point + * scanning faster if shared accesses dominate as it may + * simply bounce migrations uselessly + */ + ratio = DIV_ROUND_UP(private * NUMA_PERIOD_SLOTS, (private + shared)); + diff = (diff * ratio) / NUMA_PERIOD_SLOTS; + } + + p->numa_scan_period = clamp(p->numa_scan_period + diff, + task_scan_min(p), task_scan_max(p)); + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); +} + +/* + * Get the fraction of time the task has been running since the last + * NUMA placement cycle. The scheduler keeps similar statistics, but + * decays those on a 32ms period, which is orders of magnitude off + * from the dozens-of-seconds NUMA balancing period. Use the scheduler + * stats only if the task is so new there are no NUMA statistics yet. + */ +static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) +{ + u64 runtime, delta, now; + /* Use the start of this time slice to avoid calculations. */ + now = p->se.exec_start; + runtime = p->se.sum_exec_runtime; + + if (p->last_task_numa_placement) { + delta = runtime - p->last_sum_exec_runtime; + *period = now - p->last_task_numa_placement; + } else { + delta = p->se.avg.runnable_avg_sum; + *period = p->se.avg.runnable_avg_period; + } + + p->last_sum_exec_runtime = runtime; + p->last_task_numa_placement = now; + + return delta; +} + +static void task_numa_placement(struct task_struct *p) +{ + int seq, nid, max_nid = -1, max_group_nid = -1; + unsigned long max_faults = 0, max_group_faults = 0; + unsigned long fault_types[2] = { 0, 0 }; + unsigned long total_faults; + u64 runtime, period; + spinlock_t *group_lock = NULL; + seq = ACCESS_ONCE(p->mm->numa_scan_seq); if (p->numa_scan_seq == seq) return; p->numa_scan_seq = seq; + p->numa_scan_period_max = task_scan_max(p); + + total_faults = p->numa_faults_locality[0] + + p->numa_faults_locality[1]; + runtime = numa_get_avg_runtime(p, &period); + + /* If the task is part of a group prevent parallel updates to group stats */ + if (p->numa_group) { + group_lock = &p->numa_group->lock; + spin_lock_irq(group_lock); + } + + /* Find the node with the highest number of faults */ + for_each_online_node(nid) { + unsigned long faults = 0, group_faults = 0; + int priv, i; + + for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) { + long diff, f_diff, f_weight; - /* FIXME: Scheduling placement policy hints go here */ + i = task_faults_idx(nid, priv); + + /* Decay existing window, copy faults since last scan */ + diff = p->numa_faults_buffer_memory[i] - p->numa_faults_memory[i] / 2; + fault_types[priv] += p->numa_faults_buffer_memory[i]; + p->numa_faults_buffer_memory[i] = 0; + + /* + * Normalize the faults_from, so all tasks in a group + * count according to CPU use, instead of by the raw + * number of faults. Tasks with little runtime have + * little over-all impact on throughput, and thus their + * faults are less important. + */ + f_weight = div64_u64(runtime << 16, period + 1); + f_weight = (f_weight * p->numa_faults_buffer_cpu[i]) / + (total_faults + 1); + f_diff = f_weight - p->numa_faults_cpu[i] / 2; + p->numa_faults_buffer_cpu[i] = 0; + + p->numa_faults_memory[i] += diff; + p->numa_faults_cpu[i] += f_diff; + faults += p->numa_faults_memory[i]; + p->total_numa_faults += diff; + if (p->numa_group) { + /* safe because we can only change our own group */ + p->numa_group->faults[i] += diff; + p->numa_group->faults_cpu[i] += f_diff; + p->numa_group->total_faults += diff; + group_faults += p->numa_group->faults[i]; + } + } + + if (faults > max_faults) { + max_faults = faults; + max_nid = nid; + } + + if (group_faults > max_group_faults) { + max_group_faults = group_faults; + max_group_nid = nid; + } + } + + update_task_scan_period(p, fault_types[0], fault_types[1]); + + if (p->numa_group) { + update_numa_active_node_mask(p->numa_group); + /* + * If the preferred task and group nids are different, + * iterate over the nodes again to find the best place. + */ + if (max_nid != max_group_nid) { + unsigned long weight, max_weight = 0; + + for_each_online_node(nid) { + weight = task_weight(p, nid) + group_weight(p, nid); + if (weight > max_weight) { + max_weight = weight; + max_nid = nid; + } + } + } + + spin_unlock_irq(group_lock); + } + + /* Preferred node as the node with the most faults */ + if (max_faults && max_nid != p->numa_preferred_nid) { + /* Update the preferred nid and migrate task if possible */ + sched_setnuma(p, max_nid); + numa_migrate_preferred(p); + } +} + +static inline int get_numa_group(struct numa_group *grp) +{ + return atomic_inc_not_zero(&grp->refcount); +} + +static inline void put_numa_group(struct numa_group *grp) +{ + if (atomic_dec_and_test(&grp->refcount)) + kfree_rcu(grp, rcu); +} + +static void task_numa_group(struct task_struct *p, int cpupid, int flags, + int *priv) +{ + struct numa_group *grp, *my_grp; + struct task_struct *tsk; + bool join = false; + int cpu = cpupid_to_cpu(cpupid); + int i; + + if (unlikely(!p->numa_group)) { + unsigned int size = sizeof(struct numa_group) + + 4*nr_node_ids*sizeof(unsigned long); + + grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!grp) + return; + + atomic_set(&grp->refcount, 1); + spin_lock_init(&grp->lock); + INIT_LIST_HEAD(&grp->task_list); + grp->gid = p->pid; + /* Second half of the array tracks nids where faults happen */ + grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * + nr_node_ids; + + node_set(task_node(current), grp->active_nodes); + + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] = p->numa_faults_memory[i]; + + grp->total_faults = p->total_numa_faults; + + list_add(&p->numa_entry, &grp->task_list); + grp->nr_tasks++; + rcu_assign_pointer(p->numa_group, grp); + } + + rcu_read_lock(); + tsk = ACCESS_ONCE(cpu_rq(cpu)->curr); + + if (!cpupid_match_pid(tsk, cpupid)) + goto no_join; + + grp = rcu_dereference(tsk->numa_group); + if (!grp) + goto no_join; + + my_grp = p->numa_group; + if (grp == my_grp) + goto no_join; + + /* + * Only join the other group if its bigger; if we're the bigger group, + * the other task will join us. + */ + if (my_grp->nr_tasks > grp->nr_tasks) + goto no_join; + + /* + * Tie-break on the grp address. + */ + if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp) + goto no_join; + + /* Always join threads in the same process. */ + if (tsk->mm == current->mm) + join = true; + + /* Simple filter to avoid false positives due to PID collisions */ + if (flags & TNF_SHARED) + join = true; + + /* Update priv based on whether false sharing was detected */ + *priv = !join; + + if (join && !get_numa_group(grp)) + goto no_join; + + rcu_read_unlock(); + + if (!join) + return; + + BUG_ON(irqs_disabled()); + double_lock_irq(&my_grp->lock, &grp->lock); + + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { + my_grp->faults[i] -= p->numa_faults_memory[i]; + grp->faults[i] += p->numa_faults_memory[i]; + } + my_grp->total_faults -= p->total_numa_faults; + grp->total_faults += p->total_numa_faults; + + list_move(&p->numa_entry, &grp->task_list); + my_grp->nr_tasks--; + grp->nr_tasks++; + + spin_unlock(&my_grp->lock); + spin_unlock_irq(&grp->lock); + + rcu_assign_pointer(p->numa_group, grp); + + put_numa_group(my_grp); + return; + +no_join: + rcu_read_unlock(); + return; +} + +void task_numa_free(struct task_struct *p) +{ + struct numa_group *grp = p->numa_group; + void *numa_faults = p->numa_faults_memory; + unsigned long flags; + int i; + + if (grp) { + spin_lock_irqsave(&grp->lock, flags); + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] -= p->numa_faults_memory[i]; + grp->total_faults -= p->total_numa_faults; + + list_del(&p->numa_entry); + grp->nr_tasks--; + spin_unlock_irqrestore(&grp->lock, flags); + rcu_assign_pointer(p->numa_group, NULL); + put_numa_group(grp); + } + + p->numa_faults_memory = NULL; + p->numa_faults_buffer_memory = NULL; + p->numa_faults_cpu= NULL; + p->numa_faults_buffer_cpu = NULL; + kfree(numa_faults); } /* * Got a PROT_NONE fault for a page on @node. */ -void task_numa_fault(int node, int pages, bool migrated) +void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) { struct task_struct *p = current; + bool migrated = flags & TNF_MIGRATED; + int cpu_node = task_node(current); + int local = !!(flags & TNF_FAULT_LOCAL); + int priv; if (!numabalancing_enabled) return; - /* FIXME: Allocate task-specific structure for placement policy here */ + /* for example, ksmd faulting in a user's mm */ + if (!p->mm) + return; + + /* Do not worry about placement if exiting */ + if (p->state == TASK_DEAD) + return; + + /* Allocate buffer to track faults on a per-node basis */ + if (unlikely(!p->numa_faults_memory)) { + int size = sizeof(*p->numa_faults_memory) * + NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids; + + p->numa_faults_memory = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); + if (!p->numa_faults_memory) + return; + + BUG_ON(p->numa_faults_buffer_memory); + /* + * The averaged statistics, shared & private, memory & cpu, + * occupy the first half of the array. The second half of the + * array is for current counters, which are averaged into the + * first set by task_numa_placement. + */ + p->numa_faults_cpu = p->numa_faults_memory + (2 * nr_node_ids); + p->numa_faults_buffer_memory = p->numa_faults_memory + (4 * nr_node_ids); + p->numa_faults_buffer_cpu = p->numa_faults_memory + (6 * nr_node_ids); + p->total_numa_faults = 0; + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); + } /* - * If pages are properly placed (did not migrate) then scan slower. - * This is reset periodically in case of phase changes + * First accesses are treated as private, otherwise consider accesses + * to be private if the accessing pid has not changed */ - if (!migrated) - p->numa_scan_period = min(sysctl_numa_balancing_scan_period_max, - p->numa_scan_period + jiffies_to_msecs(10)); + if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) { + priv = 1; + } else { + priv = cpupid_match_pid(p, last_cpupid); + if (!priv && !(flags & TNF_NO_GROUP)) + task_numa_group(p, last_cpupid, flags, &priv); + } + + /* + * If a workload spans multiple NUMA nodes, a shared fault that + * occurs wholly within the set of nodes that the workload is + * actively using should be counted as local. This allows the + * scan rate to slow down when a workload has settled down. + */ + if (!priv && !local && p->numa_group && + node_isset(cpu_node, p->numa_group->active_nodes) && + node_isset(mem_node, p->numa_group->active_nodes)) + local = 1; task_numa_placement(p); + + /* + * Retry task to preferred node migration periodically, in case it + * case it previously failed, or the scheduler moved us. + */ + if (time_after(jiffies, p->numa_migrate_retry)) + numa_migrate_preferred(p); + + if (migrated) + p->numa_pages_migrated += pages; + + p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages; + p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages; + p->numa_faults_locality[local] += pages; } static void reset_ptenuma_scan(struct task_struct *p) @@ -884,6 +1872,7 @@ void task_numa_work(struct callback_head *work) struct mm_struct *mm = p->mm; struct vm_area_struct *vma; unsigned long start, end; + unsigned long nr_pte_updates = 0; long pages; WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work)); @@ -900,35 +1889,9 @@ void task_numa_work(struct callback_head *work) if (p->flags & PF_EXITING) return; - /* - * We do not care about task placement until a task runs on a node - * other than the first one used by the address space. This is - * largely because migrations are driven by what CPU the task - * is running on. If it's never scheduled on another node, it'll - * not migrate so why bother trapping the fault. - */ - if (mm->first_nid == NUMA_PTE_SCAN_INIT) - mm->first_nid = numa_node_id(); - if (mm->first_nid != NUMA_PTE_SCAN_ACTIVE) { - /* Are we running on a new node yet? */ - if (numa_node_id() == mm->first_nid && - !sched_feat_numa(NUMA_FORCE)) - return; - - mm->first_nid = NUMA_PTE_SCAN_ACTIVE; - } - - /* - * Reset the scan period if enough time has gone by. Objective is that - * scanning will be reduced if pages are properly placed. As tasks - * can enter different phases this needs to be re-examined. Lacking - * proper tracking of reference behaviour, this blunt hammer is used. - */ - migrate = mm->numa_next_reset; - if (time_after(now, migrate)) { - p->numa_scan_period = sysctl_numa_balancing_scan_period_min; - next_scan = now + msecs_to_jiffies(sysctl_numa_balancing_scan_period_reset); - xchg(&mm->numa_next_reset, next_scan); + if (!mm->numa_next_scan) { + mm->numa_next_scan = now + + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); } /* @@ -938,20 +1901,20 @@ void task_numa_work(struct callback_head *work) if (time_before(now, migrate)) return; - if (p->numa_scan_period == 0) - p->numa_scan_period = sysctl_numa_balancing_scan_period_min; + if (p->numa_scan_period == 0) { + p->numa_scan_period_max = task_scan_max(p); + p->numa_scan_period = task_scan_min(p); + } next_scan = now + msecs_to_jiffies(p->numa_scan_period); if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate) return; /* - * Do not set pte_numa if the current running node is rate-limited. - * This loses statistics on the fault but if we are unwilling to - * migrate to this node, it is less likely we can do useful work + * Delay this task enough that another task of this mm will likely win + * the next time around. */ - if (migrate_ratelimited(numa_node_id())) - return; + p->node_stamp += 2 * TICK_NSEC; start = mm->numa_scan_offset; pages = sysctl_numa_balancing_scan_size; @@ -967,31 +1930,54 @@ void task_numa_work(struct callback_head *work) vma = mm->mmap; } for (; vma; vma = vma->vm_next) { - if (!vma_migratable(vma)) + if (!vma_migratable(vma) || !vma_policy_mof(p, vma)) continue; - /* Skip small VMAs. They are not likely to be of relevance */ - if (vma->vm_end - vma->vm_start < HPAGE_SIZE) + /* + * Shared library pages mapped by multiple processes are not + * migrated as it is expected they are cache replicated. Avoid + * hinting faults in read-only file-backed mappings or the vdso + * as migrating the pages will be of marginal benefit. + */ + if (!vma->vm_mm || + (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) + continue; + + /* + * Skip inaccessible VMAs to avoid any confusion between + * PROT_NONE and NUMA hinting ptes + */ + if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) continue; do { start = max(start, vma->vm_start); end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); end = min(end, vma->vm_end); - pages -= change_prot_numa(vma, start, end); + nr_pte_updates += change_prot_numa(vma, start, end); + + /* + * Scan sysctl_numa_balancing_scan_size but ensure that + * at least one PTE is updated so that unused virtual + * address space is quickly skipped. + */ + if (nr_pte_updates) + pages -= (end - start) >> PAGE_SHIFT; start = end; if (pages <= 0) goto out; + + cond_resched(); } while (end != vma->vm_end); } out: /* - * It is possible to reach the end of the VMA list but the last few VMAs are - * not guaranteed to the vma_migratable. If they are not, we would find the - * !migratable VMA on the next scan but not reset the scanner to the start - * so check it now. + * It is possible to reach the end of the VMA list but the last few + * VMAs are not guaranteed to the vma_migratable. If they are not, we + * would find the !migratable VMA on the next scan but not reset the + * scanner to the start so check it now. */ if (vma) mm->numa_scan_offset = start; @@ -1025,8 +2011,8 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) if (now - curr->node_stamp > period) { if (!curr->node_stamp) - curr->numa_scan_period = sysctl_numa_balancing_scan_period_min; - curr->node_stamp = now; + curr->numa_scan_period = task_scan_min(curr); + curr->node_stamp += period; if (!time_before(jiffies, curr->mm->numa_next_scan)) { init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ @@ -1038,6 +2024,14 @@ void task_tick_numa(struct rq *rq, struct task_struct *curr) static void task_tick_numa(struct rq *rq, struct task_struct *curr) { } + +static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ +} + +static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ +} #endif /* CONFIG_NUMA_BALANCING */ static void @@ -1047,8 +2041,12 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) if (!parent_entity(se)) update_load_add(&rq_of(cfs_rq)->load, se->load.weight); #ifdef CONFIG_SMP - if (entity_is_task(se)) - list_add(&se->group_node, &rq_of(cfs_rq)->cfs_tasks); + if (entity_is_task(se)) { + struct rq *rq = rq_of(cfs_rq); + + account_numa_enqueue(rq, task_of(se)); + list_add(&se->group_node, &rq->cfs_tasks); + } #endif cfs_rq->nr_running++; } @@ -1059,8 +2057,10 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) update_load_sub(&cfs_rq->load, se->load.weight); if (!parent_entity(se)) update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); - if (entity_is_task(se)) + if (entity_is_task(se)) { + account_numa_dequeue(rq_of(cfs_rq), task_of(se)); list_del_init(&se->group_node); + } cfs_rq->nr_running--; } @@ -1378,7 +2378,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa, long contrib; /* The fraction of a cpu used by this cfs_rq */ - contrib = div_u64(sa->runnable_avg_sum << NICE_0_SHIFT, + contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT, sa->runnable_avg_period + 1); contrib -= cfs_rq->tg_runnable_contrib; @@ -1429,13 +2429,20 @@ static inline void __update_group_entity_contrib(struct sched_entity *se) se->avg.load_avg_contrib >>= NICE_0_SHIFT; } } -#else + +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) +{ + __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable); + __update_tg_runnable_avg(&rq->avg, &rq->cfs); +} +#else /* CONFIG_FAIR_GROUP_SCHED */ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq, int force_update) {} static inline void __update_tg_runnable_avg(struct sched_avg *sa, struct cfs_rq *cfs_rq) {} static inline void __update_group_entity_contrib(struct sched_entity *se) {} -#endif +static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} +#endif /* CONFIG_FAIR_GROUP_SCHED */ static inline void __update_task_entity_contrib(struct sched_entity *se) { @@ -1533,12 +2540,6 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) __update_cfs_rq_tg_load_contrib(cfs_rq, force_update); } -static inline void update_rq_runnable_avg(struct rq *rq, int runnable) -{ - __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable); - __update_tg_runnable_avg(&rq->avg, &rq->cfs); -} - /* Add the load generated by se into cfs_rq's child load-average */ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, @@ -1572,13 +2573,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, } wakeup = 0; } else { - /* - * Task re-woke on same cpu (or else migrate_task_rq_fair() - * would have made count negative); we must be careful to avoid - * double-accounting blocked time after synchronizing decays. - */ - se->avg.last_runnable_update += __synchronize_entity_decay(se) - << 20; + __synchronize_entity_decay(se); } /* migrated tasks did not contribute to our blocked load */ @@ -1632,7 +2627,10 @@ void idle_exit_fair(struct rq *this_rq) update_rq_runnable_avg(this_rq, 0); } -#else +static int idle_balance(struct rq *this_rq); + +#else /* CONFIG_SMP */ + static inline void update_entity_load_avg(struct sched_entity *se, int update_cfs_rq) {} static inline void update_rq_runnable_avg(struct rq *rq, int runnable) {} @@ -1644,7 +2642,13 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, int sleep) {} static inline void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update) {} -#endif + +static inline int idle_balance(struct rq *rq) +{ + return 0; +} + +#endif /* CONFIG_SMP */ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) { @@ -1794,10 +2798,10 @@ static void __clear_buddies_last(struct sched_entity *se) { for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - if (cfs_rq->last == se) - cfs_rq->last = NULL; - else + if (cfs_rq->last != se) break; + + cfs_rq->last = NULL; } } @@ -1805,10 +2809,10 @@ static void __clear_buddies_next(struct sched_entity *se) { for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - if (cfs_rq->next == se) - cfs_rq->next = NULL; - else + if (cfs_rq->next != se) break; + + cfs_rq->next = NULL; } } @@ -1816,10 +2820,10 @@ static void __clear_buddies_skip(struct sched_entity *se) { for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - if (cfs_rq->skip == se) - cfs_rq->skip = NULL; - else + if (cfs_rq->skip != se) break; + + cfs_rq->skip = NULL; } } @@ -1962,17 +2966,36 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); * 3) pick the "last" process, for cache locality * 4) do not run the "skip" process, if something else is available */ -static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) +static struct sched_entity * +pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) { - struct sched_entity *se = __pick_first_entity(cfs_rq); - struct sched_entity *left = se; + struct sched_entity *left = __pick_first_entity(cfs_rq); + struct sched_entity *se; + + /* + * If curr is set we have to see if its left of the leftmost entity + * still in the tree, provided there was anything in the tree at all. + */ + if (!left || (curr && entity_before(curr, left))) + left = curr; + + se = left; /* ideally we run the leftmost entity */ /* * Avoid running the skip buddy, if running something else can * be done without getting too unfair. */ if (cfs_rq->skip == se) { - struct sched_entity *second = __pick_next_entity(se); + struct sched_entity *second; + + if (se == curr) { + second = __pick_first_entity(cfs_rq); + } else { + second = __pick_next_entity(se); + if (!second || (curr && entity_before(curr, second))) + second = curr; + } + if (second && wakeup_preempt_entity(second, left) < 1) se = second; } @@ -1994,7 +3017,7 @@ static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) return se; } -static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq); +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq); static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) { @@ -2070,13 +3093,14 @@ static inline bool cfs_bandwidth_used(void) return static_key_false(&__cfs_bandwidth_used); } -void account_cfs_bandwidth_used(int enabled, int was_enabled) +void cfs_bandwidth_usage_inc(void) +{ + static_key_slow_inc(&__cfs_bandwidth_used); +} + +void cfs_bandwidth_usage_dec(void) { - /* only need to count groups transitioning between enabled/!enabled */ - if (enabled && !was_enabled) - static_key_slow_inc(&__cfs_bandwidth_used); - else if (!enabled && was_enabled) - static_key_slow_dec(&__cfs_bandwidth_used); + static_key_slow_dec(&__cfs_bandwidth_used); } #else /* HAVE_JUMP_LABEL */ static bool cfs_bandwidth_used(void) @@ -2084,7 +3108,8 @@ static bool cfs_bandwidth_used(void) return true; } -void account_cfs_bandwidth_used(int enabled, int was_enabled) {} +void cfs_bandwidth_usage_inc(void) {} +void cfs_bandwidth_usage_dec(void) {} #endif /* HAVE_JUMP_LABEL */ /* @@ -2156,7 +3181,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) */ if (!cfs_b->timer_active) { __refill_cfs_bandwidth_runtime(cfs_b); - __start_cfs_bandwidth(cfs_b); + __start_cfs_bandwidth(cfs_b, false); } if (cfs_b->runtime > 0) { @@ -2201,10 +3226,12 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) * has not truly expired. * * Fortunately we can check determine whether this the case by checking - * whether the global deadline has advanced. + * whether the global deadline has advanced. It is valid to compare + * cfs_b->runtime_expires without any locks since we only care about + * exact equality, so a partial write will still work. */ - if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) { + if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { /* extend local deadline, drift is bounded above by 2 ticks */ cfs_rq->runtime_expires += TICK_NSEC; } else { @@ -2213,8 +3240,7 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) } } -static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) +static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ cfs_rq->runtime_remaining -= delta_exec; @@ -2232,7 +3258,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, } static __always_inline -void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec) +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) return; @@ -2329,12 +3355,14 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) } if (!se) - rq->nr_running -= task_delta; + sub_nr_running(rq, task_delta); cfs_rq->throttled = 1; cfs_rq->throttled_clock = rq_clock(rq); raw_spin_lock(&cfs_b->lock); list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + if (!cfs_b->timer_active) + __start_cfs_bandwidth(cfs_b, false); raw_spin_unlock(&cfs_b->lock); } @@ -2378,7 +3406,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) } if (!se) - rq->nr_running += task_delta; + add_nr_running(rq, task_delta); /* determine whether we need to wake up potentially idle cpu */ if (rq->curr == rq->idle && rq->cfs.nr_running) @@ -2432,28 +3460,35 @@ next: static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) { u64 runtime, runtime_expires; - int idle = 1, throttled; + int throttled; - raw_spin_lock(&cfs_b->lock); /* no need to continue the timer with no bandwidth constraint */ if (cfs_b->quota == RUNTIME_INF) - goto out_unlock; + goto out_deactivate; throttled = !list_empty(&cfs_b->throttled_cfs_rq); - /* idle depends on !throttled (for the case of a large deficit) */ - idle = cfs_b->idle && !throttled; cfs_b->nr_periods += overrun; - /* if we're going inactive then everything else can be deferred */ - if (idle) - goto out_unlock; + /* + * idle depends on !throttled (for the case of a large deficit), and if + * we're going inactive then everything else can be deferred + */ + if (cfs_b->idle && !throttled) + goto out_deactivate; + + /* + * if we have relooped after returning idle once, we need to update our + * status as actually running, so that other cpus doing + * __start_cfs_bandwidth will stop trying to cancel us. + */ + cfs_b->timer_active = 1; __refill_cfs_bandwidth_runtime(cfs_b); if (!throttled) { /* mark as potentially idle for the upcoming period */ cfs_b->idle = 1; - goto out_unlock; + return 0; } /* account preceding periods in which throttling occurred */ @@ -2493,12 +3528,12 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) * timer to remain active while there are any throttled entities.) */ cfs_b->idle = 0; -out_unlock: - if (idle) - cfs_b->timer_active = 0; - raw_spin_unlock(&cfs_b->lock); - return idle; + return 0; + +out_deactivate: + cfs_b->timer_active = 0; + return 1; } /* a cfs_rq won't donate quota below this amount */ @@ -2508,7 +3543,13 @@ static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC; /* how long we wait to gather additional slack before distributing */ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; -/* are we near the end of the current quota period? */ +/* + * Are we near the end of the current quota period? + * + * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the + * hrtimer base being cleared by __hrtimer_start_range_ns. In the case of + * migrate_hrtimers, base is never cleared, so we are fine. + */ static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) { struct hrtimer *refresh_timer = &cfs_b->period_timer; @@ -2584,10 +3625,12 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) u64 expires; /* confirm we're still not at a refresh boundary */ - if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) + raw_spin_lock(&cfs_b->lock); + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { + raw_spin_unlock(&cfs_b->lock); return; + } - raw_spin_lock(&cfs_b->lock); if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) { runtime = cfs_b->runtime; cfs_b->runtime = 0; @@ -2631,22 +3674,23 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) } /* conditionally throttle active cfs_rq's from put_prev_entity() */ -static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { if (!cfs_bandwidth_used()) - return; + return false; if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)) - return; + return false; /* * it's possible for a throttled entity to be forced into a running * state (e.g. set_curr_task), in this case we're finished. */ if (cfs_rq_throttled(cfs_rq)) - return; + return true; throttle_cfs_rq(cfs_rq); + return true; } static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) @@ -2666,6 +3710,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) int overrun; int idle = 0; + raw_spin_lock(&cfs_b->lock); for (;;) { now = hrtimer_cb_get_time(timer); overrun = hrtimer_forward(timer, now, cfs_b->period); @@ -2675,6 +3720,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) idle = do_sched_cfs_period_timer(cfs_b, overrun); } + raw_spin_unlock(&cfs_b->lock); return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; } @@ -2700,7 +3746,7 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) } /* requires cfs_b->lock, may release to reprogram timer */ -void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force) { /* * The timer may be active because we're trying to set a new bandwidth @@ -2708,14 +3754,14 @@ void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) * (timer_active==0 becomes visible before the hrtimer call-back * terminates). In either case we ensure that it's re-programmed */ - while (unlikely(hrtimer_active(&cfs_b->period_timer))) { + while (unlikely(hrtimer_active(&cfs_b->period_timer)) && + hrtimer_try_to_cancel(&cfs_b->period_timer) < 0) { + /* bounce the lock to allow do_sched_cfs_period_timer to run */ raw_spin_unlock(&cfs_b->lock); - /* ensure cfs_b->lock is available while we wait */ - hrtimer_cancel(&cfs_b->period_timer); - + cpu_relax(); raw_spin_lock(&cfs_b->lock); /* if someone else restarted the timer then we're done */ - if (cfs_b->timer_active) + if (!force && cfs_b->timer_active) return; } @@ -2734,8 +3780,6 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) struct cfs_rq *cfs_rq; for_each_leaf_cfs_rq(rq, cfs_rq) { - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - if (!cfs_rq->runtime_enabled) continue; @@ -2743,7 +3787,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) * clock_task is not advancing so we just need to make sure * there's some valid quota amount */ - cfs_rq->runtime_remaining = cfs_b->quota; + cfs_rq->runtime_remaining = 1; if (cfs_rq_throttled(cfs_rq)) unthrottle_cfs_rq(cfs_rq); } @@ -2755,9 +3799,8 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) return rq_clock_task(rq_of(cfs_rq)); } -static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, - unsigned long delta_exec) {} -static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} @@ -2895,7 +3938,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!se) { update_rq_runnable_avg(rq, rq->nr_running); - inc_nr_running(rq); + add_nr_running(rq, 1); } hrtick_update(rq); } @@ -2955,7 +3998,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) } if (!se) { - dec_nr_running(rq); + sub_nr_running(rq, 1); update_rq_runnable_avg(rq, 1); } hrtick_update(rq); @@ -3001,9 +4044,9 @@ static unsigned long target_load(int cpu, int type) return max(rq->cpu_load[type-1], total); } -static unsigned long power_of(int cpu) +static unsigned long capacity_of(int cpu) { - return cpu_rq(cpu)->cpu_power; + return cpu_rq(cpu)->cpu_capacity; } static unsigned long cpu_avg_load_per_task(int cpu) @@ -3025,8 +4068,8 @@ static void record_wakee(struct task_struct *p) * about the boundary, really active task won't care * about the loss. */ - if (jiffies > current->wakee_flip_decay_ts + HZ) { - current->wakee_flips = 0; + if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { + current->wakee_flips >>= 1; current->wakee_flip_decay_ts = jiffies; } @@ -3166,8 +4209,7 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) } #else -static inline unsigned long effective_load(struct task_group *tg, int cpu, - unsigned long wl, unsigned long wg) +static long effective_load(struct task_group *tg, int cpu, long wl, long wg) { return wl; } @@ -3247,12 +4289,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) s64 this_eff_load, prev_eff_load; this_eff_load = 100; - this_eff_load *= power_of(prev_cpu); + this_eff_load *= capacity_of(prev_cpu); this_eff_load *= this_load + effective_load(tg, this_cpu, weight, weight); prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= power_of(this_cpu); + prev_eff_load *= capacity_of(this_cpu); prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); balanced = this_eff_load <= prev_eff_load; @@ -3292,12 +4334,16 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) */ static struct sched_group * find_idlest_group(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int load_idx) + int this_cpu, int sd_flag) { struct sched_group *idlest = NULL, *group = sd->groups; unsigned long min_load = ULONG_MAX, this_load = 0; + int load_idx = sd->forkexec_idx; int imbalance = 100 + (sd->imbalance_pct-100)/2; + if (sd_flag & SD_BALANCE_WAKE) + load_idx = sd->wake_idx; + do { unsigned long load, avg_load; int local_group; @@ -3324,8 +4370,8 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, avg_load += load; } - /* Adjust by relative CPU power of the group */ - avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power; + /* Adjust by relative CPU capacity of the group */ + avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity; if (local_group) { this_load = avg_load; @@ -3409,22 +4455,22 @@ done: } /* - * sched_balance_self: balance the current task (running on cpu) in domains - * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and - * SD_BALANCE_EXEC. + * select_task_rq_fair: Select target runqueue for the waking task in domains + * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE, + * SD_BALANCE_FORK, or SD_BALANCE_EXEC. * - * Balance, ie. select the least loaded group. + * Balances load by selecting the idlest cpu in the idlest group, or under + * certain conditions an idle sibling cpu if the domain has SD_WAKE_AFFINE set. * - * Returns the target CPU number, or the same CPU if no balancing is needed. + * Returns the target cpu number. * * preempt must be disabled. */ static int -select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags) { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); - int prev_cpu = task_cpu(p); int new_cpu = cpu; int want_affine = 0; int sync = wake_flags & WF_SYNC; @@ -3457,16 +4503,15 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) sd = tmp; } - if (affine_sd) { - if (cpu != prev_cpu && wake_affine(affine_sd, p, sync)) - prev_cpu = cpu; + if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync)) + prev_cpu = cpu; + if (sd_flag & SD_BALANCE_WAKE) { new_cpu = select_idle_sibling(p, prev_cpu); goto unlock; } while (sd) { - int load_idx = sd->forkexec_idx; struct sched_group *group; int weight; @@ -3475,10 +4520,7 @@ select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) continue; } - if (sd_flag & SD_BALANCE_WAKE) - load_idx = sd->wake_idx; - - group = find_idlest_group(sd, p, cpu, load_idx); + group = find_idlest_group(sd, p, cpu, sd_flag); if (!group) { sd = sd->child; continue; @@ -3532,6 +4574,9 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu) atomic_long_add(se->avg.load_avg_contrib, &cfs_rq->removed_load); } + + /* We have migrated, no longer consider this task hot */ + se->exec_start = 0; } #endif /* CONFIG_SMP */ @@ -3695,26 +4740,124 @@ preempt: set_last_buddy(se); } -static struct task_struct *pick_next_task_fair(struct rq *rq) +static struct task_struct * +pick_next_task_fair(struct rq *rq, struct task_struct *prev) { - struct task_struct *p; struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; + struct task_struct *p; + int new_tasks; +again: +#ifdef CONFIG_FAIR_GROUP_SCHED if (!cfs_rq->nr_running) - return NULL; + goto idle; + + if (prev->sched_class != &fair_sched_class) + goto simple; + + /* + * Because of the set_next_buddy() in dequeue_task_fair() it is rather + * likely that a next task is from the same cgroup as the current. + * + * Therefore attempt to avoid putting and setting the entire cgroup + * hierarchy, only change the part that actually changes. + */ do { - se = pick_next_entity(cfs_rq); + struct sched_entity *curr = cfs_rq->curr; + + /* + * Since we got here without doing put_prev_entity() we also + * have to consider cfs_rq->curr. If it is still a runnable + * entity, update_curr() will update its vruntime, otherwise + * forget we've ever seen it. + */ + if (curr && curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; + + /* + * This call to check_cfs_rq_runtime() will do the throttle and + * dequeue its entity in the parent(s). Therefore the 'simple' + * nr_running test will indeed be correct. + */ + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto simple; + + se = pick_next_entity(cfs_rq, curr); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + + /* + * Since we haven't yet done put_prev_entity and if the selected task + * is a different task than we started out with, try and touch the + * least amount of cfs_rqs. + */ + if (prev != p) { + struct sched_entity *pse = &prev->se; + + while (!(cfs_rq = is_same_group(se, pse))) { + int se_depth = se->depth; + int pse_depth = pse->depth; + + if (se_depth <= pse_depth) { + put_prev_entity(cfs_rq_of(pse), pse); + pse = parent_entity(pse); + } + if (se_depth >= pse_depth) { + set_next_entity(cfs_rq_of(se), se); + se = parent_entity(se); + } + } + + put_prev_entity(cfs_rq, pse); + set_next_entity(cfs_rq, se); + } + + if (hrtick_enabled(rq)) + hrtick_start_fair(rq, p); + + return p; +simple: + cfs_rq = &rq->cfs; +#endif + + if (!cfs_rq->nr_running) + goto idle; + + put_prev_task(rq, prev); + + do { + se = pick_next_entity(cfs_rq, NULL); set_next_entity(cfs_rq, se); cfs_rq = group_cfs_rq(se); } while (cfs_rq); p = task_of(se); + if (hrtick_enabled(rq)) hrtick_start_fair(rq, p); return p; + +idle: + new_tasks = idle_balance(rq); + /* + * Because idle_balance() releases (and re-acquires) rq->lock, it is + * possible for any higher priority task to appear. In that case we + * must re-start the pick_next_entity() loop. + */ + if (new_tasks < 0) + return RETRY_TASK; + + if (new_tasks > 0) + goto again; + + return NULL; } /* @@ -3808,14 +4951,14 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * * W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3) * - * P_i is the cpu power (or compute capacity) of cpu i, typically it is the + * C_i is the compute capacity of cpu i, typically it is the * fraction of 'recent' time available for SCHED_OTHER task execution. But it * can also include other factors [XXX]. * * To achieve this balance we define a measure of imbalance which follows * directly from (1): * - * imb_i,j = max{ avg(W/P), W_i/P_i } - min{ avg(W/P), W_j/P_j } (4) + * imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4) * * We them move tasks around to minimize the imbalance. In the continuous * function space it is obvious this converges, in the discrete case we get @@ -3904,9 +5047,12 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp static unsigned long __read_mostly max_load_balance_interval = HZ/10; +enum fbq_type { regular, remote, all }; + #define LBF_ALL_PINNED 0x01 #define LBF_NEED_BREAK 0x02 -#define LBF_SOME_PINNED 0x04 +#define LBF_DST_PINNED 0x04 +#define LBF_SOME_PINNED 0x08 struct lb_env { struct sched_domain *sd; @@ -3929,6 +5075,8 @@ struct lb_env { unsigned int loop; unsigned int loop_break; unsigned int loop_max; + + enum fbq_type fbq_type; }; /* @@ -3947,7 +5095,7 @@ static void move_task(struct task_struct *p, struct lb_env *env) * Is this task likely cache-hot: */ static int -task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) +task_hot(struct task_struct *p, u64 now) { s64 delta; @@ -3975,6 +5123,94 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) return delta < (s64)sysctl_sched_migration_cost; } +#ifdef CONFIG_NUMA_BALANCING +/* Returns true if the destination node has incurred more faults */ +static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) +{ + struct numa_group *numa_group = rcu_dereference(p->numa_group); + int src_nid, dst_nid; + + if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory || + !(env->sd->flags & SD_NUMA)) { + return false; + } + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid) + return false; + + if (numa_group) { + /* Task is already in the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return false; + + /* Task is moving into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) > group_faults(p, src_nid); + } + + /* Encourage migration to the preferred node. */ + if (dst_nid == p->numa_preferred_nid) + return true; + + return task_faults(p, dst_nid) > task_faults(p, src_nid); +} + + +static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) +{ + struct numa_group *numa_group = rcu_dereference(p->numa_group); + int src_nid, dst_nid; + + if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) + return false; + + if (!p->numa_faults_memory || !(env->sd->flags & SD_NUMA)) + return false; + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid) + return false; + + if (numa_group) { + /* Task is moving within/into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return false; + + /* Task is moving out of the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) < group_faults(p, src_nid); + } + + /* Migrating away from the preferred node is always bad. */ + if (src_nid == p->numa_preferred_nid) + return true; + + return task_faults(p, dst_nid) < task_faults(p, src_nid); +} + +#else +static inline bool migrate_improves_locality(struct task_struct *p, + struct lb_env *env) +{ + return false; +} + +static inline bool migrate_degrades_locality(struct task_struct *p, + struct lb_env *env) +{ + return false; +} +#endif + /* * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? */ @@ -3997,6 +5233,8 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) schedstat_inc(p, se.statistics.nr_failed_migrations_affine); + env->flags |= LBF_SOME_PINNED; + /* * Remember if this task can be migrated to any other cpu in * our sched_group. We may want to revisit it if we couldn't @@ -4005,13 +5243,13 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * Also avoid computing new_dst_cpu if we have already computed * one in current iteration. */ - if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED)) + if (!env->dst_grpmask || (env->flags & LBF_DST_PINNED)) return 0; /* Prevent to re-select dst_cpu via env's cpus */ for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) { - env->flags |= LBF_SOME_PINNED; + env->flags |= LBF_DST_PINNED; env->new_dst_cpu = cpu; break; } @@ -4030,11 +5268,24 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* * Aggressive migration if: - * 1) task is cache cold, or - * 2) too many balance attempts have failed. + * 1) destination numa is preferred + * 2) task is cache cold, or + * 3) too many balance attempts have failed. */ + tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq)); + if (!tsk_cache_hot) + tsk_cache_hot = migrate_degrades_locality(p, env); + + if (migrate_improves_locality(p, env)) { +#ifdef CONFIG_SCHEDSTATS + if (tsk_cache_hot) { + schedstat_inc(env->sd, lb_hot_gained[env->idle]); + schedstat_inc(p, se.statistics.nr_forced_migrations); + } +#endif + return 1; + } - tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd); if (!tsk_cache_hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { @@ -4077,8 +5328,6 @@ static int move_one_task(struct lb_env *env) return 0; } -static unsigned long task_h_load(struct task_struct *p); - static const unsigned int sched_nr_migrate_break = 32; /* @@ -4242,7 +5491,7 @@ static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) } if (!se) { - cfs_rq->h_load = rq->avg.load_avg_contrib; + cfs_rq->h_load = cfs_rq->runnable_load_avg; cfs_rq->last_h_load_update = now; } @@ -4284,13 +5533,17 @@ struct sg_lb_stats { unsigned long group_load; /* Total load over the CPUs of the group */ unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long load_per_task; - unsigned long group_power; + unsigned long group_capacity; unsigned int sum_nr_running; /* Nr tasks running in the group */ - unsigned int group_capacity; + unsigned int group_capacity_factor; unsigned int idle_cpus; unsigned int group_weight; int group_imb; /* Is there an imbalance in the group ? */ - int group_has_capacity; /* Is there extra capacity in the group? */ + int group_has_free_capacity; +#ifdef CONFIG_NUMA_BALANCING + unsigned int nr_numa_running; + unsigned int nr_preferred_running; +#endif }; /* @@ -4301,7 +5554,7 @@ struct sd_lb_stats { struct sched_group *busiest; /* Busiest group in this sd */ struct sched_group *local; /* Local group in this sd */ unsigned long total_load; /* Total load of all groups in sd */ - unsigned long total_pwr; /* Total power of all groups in sd */ + unsigned long total_capacity; /* Total capacity of all groups in sd */ unsigned long avg_load; /* Average load across all groups in sd */ struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ @@ -4320,7 +5573,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) .busiest = NULL, .local = NULL, .total_load = 0UL, - .total_pwr = 0UL, + .total_capacity = 0UL, .busiest_stat = { .avg_load = 0UL, }, @@ -4330,7 +5583,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) /** * get_sd_load_idx - Obtain the load index for a given sched domain. * @sd: The sched_domain whose load_idx is to be obtained. - * @idle: The Idle status of the CPU for whose sd load_icx is obtained. + * @idle: The idle status of the CPU for whose sd load_idx is obtained. * * Return: The load index. */ @@ -4355,17 +5608,17 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu) { - return SCHED_POWER_SCALE; + return SCHED_CAPACITY_SCALE; } -unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) +unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu) { - return default_scale_freq_power(sd, cpu); + return default_scale_capacity(sd, cpu); } -static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_smt_capacity(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; unsigned long smt_gain = sd->smt_gain; @@ -4375,15 +5628,16 @@ static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) return smt_gain; } -unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) +unsigned long __weak arch_scale_smt_capacity(struct sched_domain *sd, int cpu) { - return default_scale_smt_power(sd, cpu); + return default_scale_smt_capacity(sd, cpu); } -static unsigned long scale_rt_power(int cpu) +static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); u64 total, available, age_stamp, avg; + s64 delta; /* * Since we're reading these variables without serialization make sure @@ -4392,74 +5646,78 @@ static unsigned long scale_rt_power(int cpu) age_stamp = ACCESS_ONCE(rq->age_stamp); avg = ACCESS_ONCE(rq->rt_avg); - total = sched_avg_period() + (rq_clock(rq) - age_stamp); + delta = rq_clock(rq) - age_stamp; + if (unlikely(delta < 0)) + delta = 0; + + total = sched_avg_period() + delta; if (unlikely(total < avg)) { - /* Ensures that power won't end up being negative */ + /* Ensures that capacity won't end up being negative */ available = 0; } else { available = total - avg; } - if (unlikely((s64)total < SCHED_POWER_SCALE)) - total = SCHED_POWER_SCALE; + if (unlikely((s64)total < SCHED_CAPACITY_SCALE)) + total = SCHED_CAPACITY_SCALE; - total >>= SCHED_POWER_SHIFT; + total >>= SCHED_CAPACITY_SHIFT; return div_u64(available, total); } -static void update_cpu_power(struct sched_domain *sd, int cpu) +static void update_cpu_capacity(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; - unsigned long power = SCHED_POWER_SCALE; + unsigned long capacity = SCHED_CAPACITY_SCALE; struct sched_group *sdg = sd->groups; - if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { - if (sched_feat(ARCH_POWER)) - power *= arch_scale_smt_power(sd, cpu); + if ((sd->flags & SD_SHARE_CPUCAPACITY) && weight > 1) { + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_smt_capacity(sd, cpu); else - power *= default_scale_smt_power(sd, cpu); + capacity *= default_scale_smt_capacity(sd, cpu); - power >>= SCHED_POWER_SHIFT; + capacity >>= SCHED_CAPACITY_SHIFT; } - sdg->sgp->power_orig = power; + sdg->sgc->capacity_orig = capacity; - if (sched_feat(ARCH_POWER)) - power *= arch_scale_freq_power(sd, cpu); + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_freq_capacity(sd, cpu); else - power *= default_scale_freq_power(sd, cpu); + capacity *= default_scale_capacity(sd, cpu); - power >>= SCHED_POWER_SHIFT; + capacity >>= SCHED_CAPACITY_SHIFT; - power *= scale_rt_power(cpu); - power >>= SCHED_POWER_SHIFT; + capacity *= scale_rt_capacity(cpu); + capacity >>= SCHED_CAPACITY_SHIFT; - if (!power) - power = 1; + if (!capacity) + capacity = 1; - cpu_rq(cpu)->cpu_power = power; - sdg->sgp->power = power; + cpu_rq(cpu)->cpu_capacity = capacity; + sdg->sgc->capacity = capacity; } -void update_group_power(struct sched_domain *sd, int cpu) +void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long power; + unsigned long capacity, capacity_orig; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); interval = clamp(interval, 1UL, max_load_balance_interval); - sdg->sgp->next_update = jiffies + interval; + sdg->sgc->next_update = jiffies + interval; if (!child) { - update_cpu_power(sd, cpu); + update_cpu_capacity(sd, cpu); return; } - power = 0; + capacity_orig = capacity = 0; if (child->flags & SD_OVERLAP) { /* @@ -4467,8 +5725,33 @@ void update_group_power(struct sched_domain *sd, int cpu) * span the current group. */ - for_each_cpu(cpu, sched_group_cpus(sdg)) - power += power_of(cpu); + for_each_cpu(cpu, sched_group_cpus(sdg)) { + struct sched_group_capacity *sgc; + struct rq *rq = cpu_rq(cpu); + + /* + * build_sched_domains() -> init_sched_groups_capacity() + * gets here before we've attached the domains to the + * runqueues. + * + * Use capacity_of(), which is set irrespective of domains + * in update_cpu_capacity(). + * + * This avoids capacity/capacity_orig from being 0 and + * causing divide-by-zero issues on boot. + * + * Runtime updates will correct capacity_orig. + */ + if (unlikely(!rq->sd)) { + capacity_orig += capacity_of(cpu); + capacity += capacity_of(cpu); + continue; + } + + sgc = rq->sd->groups->sgc; + capacity_orig += sgc->capacity_orig; + capacity += sgc->capacity; + } } else { /* * !SD_OVERLAP domains can assume that child groups @@ -4477,12 +5760,14 @@ void update_group_power(struct sched_domain *sd, int cpu) group = child->groups; do { - power += group->sgp->power; + capacity_orig += group->sgc->capacity_orig; + capacity += group->sgc->capacity; group = group->next; } while (group != child->groups); } - sdg->sgp->power_orig = sdg->sgp->power = power; + sdg->sgc->capacity_orig = capacity_orig; + sdg->sgc->capacity = capacity; } /* @@ -4496,15 +5781,15 @@ static inline int fix_small_capacity(struct sched_domain *sd, struct sched_group *group) { /* - * Only siblings can have significantly less than SCHED_POWER_SCALE + * Only siblings can have significantly less than SCHED_CAPACITY_SCALE */ - if (!(sd->flags & SD_SHARE_CPUPOWER)) + if (!(sd->flags & SD_SHARE_CPUCAPACITY)) return 0; /* - * If ~90% of the cpu_power is still there, we're good. + * If ~90% of the cpu_capacity is still there, we're good. */ - if (group->sgp->power * 32 > group->sgp->power_orig * 29) + if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29) return 1; return 0; @@ -4526,13 +5811,12 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) * cpu 3 and leave one of the cpus in the second group unused. * * The current solution to this issue is detecting the skew in the first group - * by noticing it has a cpu that is overloaded while the remaining cpus are - * idle -- or rather, there's a distinct imbalance in the cpus; see - * sg_imbalanced(). + * by noticing the lower domain failed to reach balance and had difficulty + * moving tasks due to affinity constraints. * * When this is so detected; this group becomes a candidate for busiest; see - * update_sd_pick_busiest(). And calculcate_imbalance() and - * find_busiest_group() avoid some of the usual balance conditional to allow it + * update_sd_pick_busiest(). And calculate_imbalance() and + * find_busiest_group() avoid some of the usual balance conditions to allow it * to create an effective group imbalance. * * This is a somewhat tricky proposition since the next run might not find the @@ -4540,49 +5824,37 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) * subtle and fragile situation. */ -struct sg_imb_stats { - unsigned long max_nr_running, min_nr_running; - unsigned long max_cpu_load, min_cpu_load; -}; - -static inline void init_sg_imb_stats(struct sg_imb_stats *sgi) +static inline int sg_imbalanced(struct sched_group *group) { - sgi->max_cpu_load = sgi->max_nr_running = 0UL; - sgi->min_cpu_load = sgi->min_nr_running = ~0UL; + return group->sgc->imbalance; } -static inline void -update_sg_imb_stats(struct sg_imb_stats *sgi, - unsigned long load, unsigned long nr_running) +/* + * Compute the group capacity factor. + * + * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by + * first dividing out the smt factor and computing the actual number of cores + * and limit unit capacity with that. + */ +static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group) { - if (load > sgi->max_cpu_load) - sgi->max_cpu_load = load; - if (sgi->min_cpu_load > load) - sgi->min_cpu_load = load; + unsigned int capacity_factor, smt, cpus; + unsigned int capacity, capacity_orig; - if (nr_running > sgi->max_nr_running) - sgi->max_nr_running = nr_running; - if (sgi->min_nr_running > nr_running) - sgi->min_nr_running = nr_running; -} + capacity = group->sgc->capacity; + capacity_orig = group->sgc->capacity_orig; + cpus = group->group_weight; -static inline int -sg_imbalanced(struct sg_lb_stats *sgs, struct sg_imb_stats *sgi) -{ - /* - * Consider the group unbalanced when the imbalance is larger - * than the average weight of a task. - * - * APZ: with cgroup the avg task weight can vary wildly and - * might not be a suitable number - should we keep a - * normalized nr_running number somewhere that negates - * the hierarchy? - */ - if ((sgi->max_cpu_load - sgi->min_cpu_load) >= sgs->load_per_task && - (sgi->max_nr_running - sgi->min_nr_running) > 1) - return 1; + /* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */ + smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig); + capacity_factor = cpus / smt; /* cores */ - return 0; + capacity_factor = min_t(unsigned, + capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE)); + if (!capacity_factor) + capacity_factor = fix_small_capacity(env->sd, group); + + return capacity_factor; } /** @@ -4597,56 +5869,45 @@ static inline void update_sg_lb_stats(struct lb_env *env, struct sched_group *group, int load_idx, int local_group, struct sg_lb_stats *sgs) { - struct sg_imb_stats sgi; - unsigned long nr_running; unsigned long load; int i; - init_sg_imb_stats(&sgi); + memset(sgs, 0, sizeof(*sgs)); for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { struct rq *rq = cpu_rq(i); - nr_running = rq->nr_running; - /* Bias balancing toward cpus of our domain */ - if (local_group) { + if (local_group) load = target_load(i, load_idx); - } else { + else load = source_load(i, load_idx); - update_sg_imb_stats(&sgi, load, nr_running); - } sgs->group_load += load; - sgs->sum_nr_running += nr_running; + sgs->sum_nr_running += rq->nr_running; +#ifdef CONFIG_NUMA_BALANCING + sgs->nr_numa_running += rq->nr_numa_running; + sgs->nr_preferred_running += rq->nr_preferred_running; +#endif sgs->sum_weighted_load += weighted_cpuload(i); if (idle_cpu(i)) sgs->idle_cpus++; } - if (local_group && (env->idle != CPU_NEWLY_IDLE || - time_after_eq(jiffies, group->sgp->next_update))) - update_group_power(env->sd, env->dst_cpu); - - /* Adjust by relative CPU power of the group */ - sgs->group_power = group->sgp->power; - sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power; + /* Adjust by relative CPU capacity of the group */ + sgs->group_capacity = group->sgc->capacity; + sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; if (sgs->sum_nr_running) sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; - sgs->group_imb = sg_imbalanced(sgs, &sgi); - - sgs->group_capacity = - DIV_ROUND_CLOSEST(sgs->group_power, SCHED_POWER_SCALE); - - if (!sgs->group_capacity) - sgs->group_capacity = fix_small_capacity(env->sd, group); - sgs->group_weight = group->group_weight; - if (sgs->group_capacity > sgs->sum_nr_running) - sgs->group_has_capacity = 1; + sgs->group_imb = sg_imbalanced(group); + sgs->group_capacity_factor = sg_capacity_factor(env, group); + + if (sgs->group_capacity_factor > sgs->sum_nr_running) + sgs->group_has_free_capacity = 1; } /** @@ -4670,7 +5931,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, if (sgs->avg_load <= sds->busiest_stat.avg_load) return false; - if (sgs->sum_nr_running > sgs->group_capacity) + if (sgs->sum_nr_running > sgs->group_capacity_factor) return true; if (sgs->group_imb) @@ -4693,14 +5954,42 @@ static bool update_sd_pick_busiest(struct lb_env *env, return false; } +#ifdef CONFIG_NUMA_BALANCING +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running > sgs->nr_numa_running) + return regular; + if (sgs->sum_nr_running > sgs->nr_preferred_running) + return remote; + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + if (rq->nr_running > rq->nr_numa_running) + return regular; + if (rq->nr_running > rq->nr_preferred_running) + return remote; + return all; +} +#else +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + return regular; +} +#endif /* CONFIG_NUMA_BALANCING */ + /** * update_sd_lb_stats - Update sched_domain's statistics for load balancing. * @env: The load balancing environment. - * @balance: Should we balance. * @sds: variable to hold the statistics for this sched_domain. */ -static inline void update_sd_lb_stats(struct lb_env *env, - struct sd_lb_stats *sds) +static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) { struct sched_domain *child = env->sd->child; struct sched_group *sg = env->sd->groups; @@ -4720,36 +6009,46 @@ static inline void update_sd_lb_stats(struct lb_env *env, if (local_group) { sds->local = sg; sgs = &sds->local_stat; + + if (env->idle != CPU_NEWLY_IDLE || + time_after_eq(jiffies, sg->sgc->next_update)) + update_group_capacity(env->sd, env->dst_cpu); } - memset(sgs, 0, sizeof(*sgs)); update_sg_lb_stats(env, sg, load_idx, local_group, sgs); + if (local_group) + goto next_group; + /* * In case the child domain prefers tasks go to siblings - * first, lower the sg capacity to one so that we'll try + * first, lower the sg capacity factor to one so that we'll try * and move all the excess tasks away. We lower the capacity * of a group only if the local group has the capacity to fit - * these excess tasks, i.e. nr_running < group_capacity. The + * these excess tasks, i.e. nr_running < group_capacity_factor. The * extra check prevents the case where you always pull from the * heaviest group when it is already under-utilized (possible * with a large weight task outweighs the tasks on the system). */ - if (prefer_sibling && !local_group && - sds->local && sds->local_stat.group_has_capacity) - sgs->group_capacity = min(sgs->group_capacity, 1U); - - /* Now, start updating sd_lb_stats */ - sds->total_load += sgs->group_load; - sds->total_pwr += sgs->group_power; + if (prefer_sibling && sds->local && + sds->local_stat.group_has_free_capacity) + sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U); - if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) { + if (update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; sds->busiest_stat = *sgs; } +next_group: + /* Now, start updating sd_lb_stats */ + sds->total_load += sgs->group_load; + sds->total_capacity += sgs->group_capacity; + sg = sg->next; } while (sg != env->sd->groups); + + if (env->sd->flags & SD_NUMA) + env->fbq_type = fbq_classify_group(&sds->busiest_stat); } /** @@ -4790,8 +6089,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) return 0; env->imbalance = DIV_ROUND_CLOSEST( - sds->busiest_stat.avg_load * sds->busiest_stat.group_power, - SCHED_POWER_SCALE); + sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity, + SCHED_CAPACITY_SCALE); return 1; } @@ -4806,7 +6105,7 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) static inline void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) { - unsigned long tmp, pwr_now = 0, pwr_move = 0; + unsigned long tmp, capa_now = 0, capa_move = 0; unsigned int imbn = 2; unsigned long scaled_busy_load_per_task; struct sg_lb_stats *local, *busiest; @@ -4820,51 +6119,49 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) imbn = 1; scaled_busy_load_per_task = - (busiest->load_per_task * SCHED_POWER_SCALE) / - busiest->group_power; + (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + busiest->group_capacity; - if (busiest->avg_load - local->avg_load + scaled_busy_load_per_task >= - (scaled_busy_load_per_task * imbn)) { + if (busiest->avg_load + scaled_busy_load_per_task >= + local->avg_load + (scaled_busy_load_per_task * imbn)) { env->imbalance = busiest->load_per_task; return; } /* * OK, we don't have enough imbalance to justify moving tasks, - * however we may be able to increase total CPU power used by + * however we may be able to increase total CPU capacity used by * moving them. */ - pwr_now += busiest->group_power * + capa_now += busiest->group_capacity * min(busiest->load_per_task, busiest->avg_load); - pwr_now += local->group_power * + capa_now += local->group_capacity * min(local->load_per_task, local->avg_load); - pwr_now /= SCHED_POWER_SCALE; + capa_now /= SCHED_CAPACITY_SCALE; /* Amount of load we'd subtract */ - tmp = (busiest->load_per_task * SCHED_POWER_SCALE) / - busiest->group_power; - if (busiest->avg_load > tmp) { - pwr_move += busiest->group_power * + if (busiest->avg_load > scaled_busy_load_per_task) { + capa_move += busiest->group_capacity * min(busiest->load_per_task, - busiest->avg_load - tmp); + busiest->avg_load - scaled_busy_load_per_task); } /* Amount of load we'd add */ - if (busiest->avg_load * busiest->group_power < - busiest->load_per_task * SCHED_POWER_SCALE) { - tmp = (busiest->avg_load * busiest->group_power) / - local->group_power; + if (busiest->avg_load * busiest->group_capacity < + busiest->load_per_task * SCHED_CAPACITY_SCALE) { + tmp = (busiest->avg_load * busiest->group_capacity) / + local->group_capacity; } else { - tmp = (busiest->load_per_task * SCHED_POWER_SCALE) / - local->group_power; + tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + local->group_capacity; } - pwr_move += local->group_power * + capa_move += local->group_capacity * min(local->load_per_task, local->avg_load + tmp); - pwr_move /= SCHED_POWER_SCALE; + capa_move /= SCHED_CAPACITY_SCALE; /* Move if we gain throughput */ - if (pwr_move > pwr_now) + if (capa_move > capa_now) env->imbalance = busiest->load_per_task; } @@ -4894,9 +6191,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* * In the presence of smp nice balancing, certain scenarios can have * max load less than avg load(as we skip the groups at or below - * its cpu_power, while calculating max_load..) + * its cpu_capacity, while calculating max_load..) */ - if (busiest->avg_load < sds->avg_load) { + if (busiest->avg_load <= sds->avg_load || + local->avg_load >= sds->avg_load) { env->imbalance = 0; return fix_small_imbalance(env, sds); } @@ -4908,10 +6206,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * have to drop below capacity to reach cpu-load equilibrium. */ load_above_capacity = - (busiest->sum_nr_running - busiest->group_capacity); + (busiest->sum_nr_running - busiest->group_capacity_factor); - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE); - load_above_capacity /= busiest->group_power; + load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE); + load_above_capacity /= busiest->group_capacity; } /* @@ -4926,9 +6224,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* How much load to actually move to equalise the imbalance */ env->imbalance = min( - max_pull * busiest->group_power, - (sds->avg_load - local->avg_load) * local->group_power - ) / SCHED_POWER_SCALE; + max_pull * busiest->group_capacity, + (sds->avg_load - local->avg_load) * local->group_capacity + ) / SCHED_CAPACITY_SCALE; /* * if *imbalance is less than the average load per runnable task @@ -4982,7 +6280,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (!sds.busiest || busiest->sum_nr_running == 0) goto out_balanced; - sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr; + sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load) + / sds.total_capacity; /* * If the busiest group is imbalanced the below checks don't @@ -4993,8 +6292,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && local->group_has_capacity && - !busiest->group_has_capacity) + if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity && + !busiest->group_has_free_capacity) goto force_balance; /* @@ -5048,42 +6347,66 @@ static struct rq *find_busiest_queue(struct lb_env *env, struct sched_group *group) { struct rq *busiest = NULL, *rq; - unsigned long busiest_load = 0, busiest_power = 1; + unsigned long busiest_load = 0, busiest_capacity = 1; int i; for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { - unsigned long power = power_of(i); - unsigned long capacity = DIV_ROUND_CLOSEST(power, - SCHED_POWER_SCALE); - unsigned long wl; - - if (!capacity) - capacity = fix_small_capacity(env->sd, group); + unsigned long capacity, capacity_factor, wl; + enum fbq_type rt; rq = cpu_rq(i); + rt = fbq_classify_rq(rq); + + /* + * We classify groups/runqueues into three groups: + * - regular: there are !numa tasks + * - remote: there are numa tasks that run on the 'wrong' node + * - all: there is no distinction + * + * In order to avoid migrating ideally placed numa tasks, + * ignore those when there's better options. + * + * If we ignore the actual busiest queue to migrate another + * task, the next balance pass can still reduce the busiest + * queue by moving tasks around inside the node. + * + * If we cannot move enough load due to this classification + * the next pass will adjust the group classification and + * allow migration of more tasks. + * + * Both cases only affect the total convergence complexity. + */ + if (rt > env->fbq_type) + continue; + + capacity = capacity_of(i); + capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE); + if (!capacity_factor) + capacity_factor = fix_small_capacity(env->sd, group); + wl = weighted_cpuload(i); /* * When comparing with imbalance, use weighted_cpuload() - * which is not scaled with the cpu power. + * which is not scaled with the cpu capacity. */ - if (capacity && rq->nr_running == 1 && wl > env->imbalance) + if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance) continue; /* * For the load comparisons with the other cpu's, consider - * the weighted_cpuload() scaled with the cpu power, so that - * the load can be moved away from the cpu that is potentially - * running at a lower capacity. + * the weighted_cpuload() scaled with the cpu capacity, so + * that the load can be moved away from the cpu that is + * potentially running at a lower capacity. * - * Thus we're looking for max(wl_i / power_i), crosswise + * Thus we're looking for max(wl_i / capacity_i), crosswise * multiplication to rid ourselves of the division works out - * to: wl_i * power_j > wl_j * power_i; where j is our - * previous maximum. + * to: wl_i * capacity_j > wl_j * capacity_i; where j is + * our previous maximum. */ - if (wl * busiest_power > busiest_load * power) { + if (wl * busiest_capacity > busiest_load * capacity) { busiest_load = wl; - busiest_power = power; + busiest_capacity = capacity; busiest = rq; } } @@ -5163,6 +6486,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, int *continue_balancing) { int ld_moved, cur_ld_moved, active_balance = 0; + struct sched_domain *sd_parent = sd->parent; struct sched_group *group; struct rq *busiest; unsigned long flags; @@ -5176,6 +6500,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, .idle = idle, .loop_break = sched_nr_migrate_break, .cpus = cpus, + .fbq_type = all, }; /* @@ -5267,17 +6592,17 @@ more_balance: * moreover subsequent load balance cycles should correct the * excess load moved. */ - if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) { + if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) { + + /* Prevent to re-select dst_cpu via env's cpus */ + cpumask_clear_cpu(env.dst_cpu, env.cpus); env.dst_rq = cpu_rq(env.new_dst_cpu); env.dst_cpu = env.new_dst_cpu; - env.flags &= ~LBF_SOME_PINNED; + env.flags &= ~LBF_DST_PINNED; env.loop = 0; env.loop_break = sched_nr_migrate_break; - /* Prevent to re-select dst_cpu via env's cpus */ - cpumask_clear_cpu(env.dst_cpu, env.cpus); - /* * Go back to "more_balance" rather than "redo" since we * need to continue with same src_cpu. @@ -5285,6 +6610,18 @@ more_balance: goto more_balance; } + /* + * We failed to reach balance because of affinity. + */ + if (sd_parent) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) { + *group_imbalance = 1; + } else if (*group_imbalance) + *group_imbalance = 0; + } + /* All tasks on this runqueue were pinned by CPU affinity */ if (unlikely(env.flags & LBF_ALL_PINNED)) { cpumask_clear_cpu(cpu_of(busiest), cpus); @@ -5383,20 +6720,62 @@ out: return ld_moved; } +static inline unsigned long +get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) +{ + unsigned long interval = sd->balance_interval; + + if (cpu_busy) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + + return interval; +} + +static inline void +update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance) +{ + unsigned long interval, next; + + interval = get_sd_balance_interval(sd, cpu_busy); + next = sd->last_balance + interval; + + if (time_after(*next_balance, next)) + *next_balance = next; +} + /* * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -void idle_balance(int this_cpu, struct rq *this_rq) +static int idle_balance(struct rq *this_rq) { + unsigned long next_balance = jiffies + HZ; + int this_cpu = this_rq->cpu; struct sched_domain *sd; int pulled_task = 0; - unsigned long next_balance = jiffies + HZ; + u64 curr_cost = 0; + idle_enter_fair(this_rq); + + /* + * We must set idle_stamp _before_ calling idle_balance(), such that we + * measure the duration of idle_balance() as idle time. + */ this_rq->idle_stamp = rq_clock(this_rq); - if (this_rq->avg_idle < sysctl_sched_migration_cost) - return; + if (this_rq->avg_idle < sysctl_sched_migration_cost) { + rcu_read_lock(); + sd = rcu_dereference_check_sched_domain(this_rq->sd); + if (sd) + update_next_balance(sd, 0, &next_balance); + rcu_read_unlock(); + + goto out; + } /* * Drop the rq->lock, but keep IRQ/preempt disabled. @@ -5406,38 +6785,70 @@ void idle_balance(int this_cpu, struct rq *this_rq) update_blocked_averages(this_cpu); rcu_read_lock(); for_each_domain(this_cpu, sd) { - unsigned long interval; int continue_balancing = 1; + u64 t0, domain_cost; if (!(sd->flags & SD_LOAD_BALANCE)) continue; + if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { + update_next_balance(sd, 0, &next_balance); + break; + } + if (sd->flags & SD_BALANCE_NEWIDLE) { - /* If we've pulled tasks over stop searching: */ + t0 = sched_clock_cpu(this_cpu); + pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, &continue_balancing); + + domain_cost = sched_clock_cpu(this_cpu) - t0; + if (domain_cost > sd->max_newidle_lb_cost) + sd->max_newidle_lb_cost = domain_cost; + + curr_cost += domain_cost; } - interval = msecs_to_jiffies(sd->balance_interval); - if (time_after(next_balance, sd->last_balance + interval)) - next_balance = sd->last_balance + interval; - if (pulled_task) { - this_rq->idle_stamp = 0; + update_next_balance(sd, 0, &next_balance); + + /* + * Stop searching for tasks to pull if there are + * now runnable tasks on this rq. + */ + if (pulled_task || this_rq->nr_running > 0) break; - } } rcu_read_unlock(); raw_spin_lock(&this_rq->lock); - if (pulled_task || time_after(jiffies, this_rq->next_balance)) { - /* - * We are going idle. next_balance may be set based on - * a busy processor. So reset next_balance. - */ + if (curr_cost > this_rq->max_idle_balance_cost) + this_rq->max_idle_balance_cost = curr_cost; + + /* + * While browsing the domains, we released the rq lock, a task could + * have been enqueued in the meantime. Since we're not going idle, + * pretend we pulled a task. + */ + if (this_rq->cfs.h_nr_running && !pulled_task) + pulled_task = 1; + +out: + /* Move the next balance forward */ + if (time_after(this_rq->next_balance, next_balance)) this_rq->next_balance = next_balance; + + /* Is there a task of a high priority class? */ + if (this_rq->nr_running != this_rq->cfs.h_nr_running) + pulled_task = -1; + + if (pulled_task) { + idle_exit_fair(this_rq); + this_rq->idle_stamp = 0; } + + return pulled_task; } /* @@ -5508,6 +6919,11 @@ out_unlock: return 0; } +static inline int on_null_domain(struct rq *rq) +{ + return unlikely(!rcu_dereference_sched(rq->sd)); +} + #ifdef CONFIG_NO_HZ_COMMON /* * idle load balancing details @@ -5521,7 +6937,7 @@ static struct { unsigned long next_balance; /* in jiffy units */ } nohz ____cacheline_aligned; -static inline int find_new_ilb(int call_cpu) +static inline int find_new_ilb(void) { int ilb = cpumask_first(nohz.idle_cpus_mask); @@ -5536,13 +6952,13 @@ static inline int find_new_ilb(int call_cpu) * nohz_load_balancer CPU (if there is one) otherwise fallback to any idle * CPU (if there is one). */ -static void nohz_balancer_kick(int cpu) +static void nohz_balancer_kick(void) { int ilb_cpu; nohz.next_balance++; - ilb_cpu = find_new_ilb(cpu); + ilb_cpu = find_new_ilb(); if (ilb_cpu >= nr_cpu_ids) return; @@ -5562,8 +6978,13 @@ static void nohz_balancer_kick(int cpu) static inline void nohz_balance_exit_idle(int cpu) { if (unlikely(test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))) { - cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); - atomic_dec(&nohz.nr_cpus); + /* + * Completely isolated CPUs don't ever set, so we must test. + */ + if (likely(cpumask_test_cpu(cpu, nohz.idle_cpus_mask))) { + cpumask_clear_cpu(cpu, nohz.idle_cpus_mask); + atomic_dec(&nohz.nr_cpus); + } clear_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); } } @@ -5571,16 +6992,16 @@ static inline void nohz_balance_exit_idle(int cpu) static inline void set_cpu_sd_state_busy(void) { struct sched_domain *sd; + int cpu = smp_processor_id(); rcu_read_lock(); - sd = rcu_dereference_check_sched_domain(this_rq()->sd); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); if (!sd || !sd->nohz_idle) goto unlock; sd->nohz_idle = 0; - for (; sd; sd = sd->parent) - atomic_inc(&sd->groups->sgp->nr_busy_cpus); + atomic_inc(&sd->groups->sgc->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -5588,16 +7009,16 @@ unlock: void set_cpu_sd_state_idle(void) { struct sched_domain *sd; + int cpu = smp_processor_id(); rcu_read_lock(); - sd = rcu_dereference_check_sched_domain(this_rq()->sd); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); if (!sd || sd->nohz_idle) goto unlock; sd->nohz_idle = 1; - for (; sd; sd = sd->parent) - atomic_dec(&sd->groups->sgp->nr_busy_cpus); + atomic_dec(&sd->groups->sgc->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -5617,6 +7038,12 @@ void nohz_balance_enter_idle(int cpu) if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu))) return; + /* + * If we're a completely isolated CPU, we don't play. + */ + if (on_null_domain(cpu_rq(cpu))) + return; + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); atomic_inc(&nohz.nr_cpus); set_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)); @@ -5652,34 +7079,51 @@ void update_max_interval(void) * * Balancing parameters are set up in init_sched_domains. */ -static void rebalance_domains(int cpu, enum cpu_idle_type idle) +static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) { int continue_balancing = 1; - struct rq *rq = cpu_rq(cpu); + int cpu = rq->cpu; unsigned long interval; struct sched_domain *sd; /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; - int need_serialize; + int need_serialize, need_decay = 0; + u64 max_cost = 0; update_blocked_averages(cpu); rcu_read_lock(); for_each_domain(cpu, sd) { + /* + * Decay the newidle max times here because this is a regular + * visit to all the domains. Decay ~1% per second. + */ + if (time_after(jiffies, sd->next_decay_max_lb_cost)) { + sd->max_newidle_lb_cost = + (sd->max_newidle_lb_cost * 253) / 256; + sd->next_decay_max_lb_cost = jiffies + HZ; + need_decay = 1; + } + max_cost += sd->max_newidle_lb_cost; + if (!(sd->flags & SD_LOAD_BALANCE)) continue; - interval = sd->balance_interval; - if (idle != CPU_IDLE) - interval *= sd->busy_factor; + /* + * Stop the load balance at this level. There is another + * CPU in our sched group which is doing load balancing more + * actively. + */ + if (!continue_balancing) { + if (need_decay) + continue; + break; + } - /* scale ms to jiffies */ - interval = msecs_to_jiffies(interval); - interval = clamp(interval, 1UL, max_load_balance_interval); + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); need_serialize = sd->flags & SD_SERIALIZE; - if (need_serialize) { if (!spin_trylock(&balancing)) goto out; @@ -5688,13 +7132,14 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (time_after_eq(jiffies, sd->last_balance + interval)) { if (load_balance(cpu, rq, sd, idle, &continue_balancing)) { /* - * The LBF_SOME_PINNED logic could have changed + * The LBF_DST_PINNED logic could have changed * env->dst_cpu, so we can't know our idle * state even if we migrated tasks. Update it. */ idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; } sd->last_balance = jiffies; + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); } if (need_serialize) spin_unlock(&balancing); @@ -5703,14 +7148,14 @@ out: next_balance = sd->last_balance + interval; update_next_balance = 1; } - + } + if (need_decay) { /* - * Stop the load balance at this level. There is another - * CPU in our sched group which is doing load balancing more - * actively. + * Ensure the rq-wide value also decays but keep it at a + * reasonable floor to avoid funnies with rq->avg_idle. */ - if (!continue_balancing) - break; + rq->max_idle_balance_cost = + max((u64)sysctl_sched_migration_cost, max_cost); } rcu_read_unlock(); @@ -5728,9 +7173,9 @@ out: * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the * rebalancing for all the cpus for whom scheduler ticks are stopped. */ -static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) +static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { - struct rq *this_rq = cpu_rq(this_cpu); + int this_cpu = this_rq->cpu; struct rq *rq; int balance_cpu; @@ -5752,12 +7197,17 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) rq = cpu_rq(balance_cpu); - raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); - update_idle_cpu_load(rq); - raw_spin_unlock_irq(&rq->lock); - - rebalance_domains(balance_cpu, CPU_IDLE); + /* + * If time for next balance is due, + * do the balance. + */ + if (time_after_eq(jiffies, rq->next_balance)) { + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); + rebalance_domains(rq, CPU_IDLE); + } if (time_after(this_rq->next_balance, rq->next_balance)) this_rq->next_balance = rq->next_balance; @@ -5772,16 +7222,18 @@ end: * of an idle cpu is the system. * - This rq has more than one task. * - At any scheduler domain level, this cpu's scheduler group has multiple - * busy cpu's exceeding the group's power. + * busy cpu's exceeding the group's capacity. * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler * domain span are idle. */ -static inline int nohz_kick_needed(struct rq *rq, int cpu) +static inline int nohz_kick_needed(struct rq *rq) { unsigned long now = jiffies; struct sched_domain *sd; + struct sched_group_capacity *sgc; + int nr_busy, cpu = rq->cpu; - if (unlikely(idle_cpu(cpu))) + if (unlikely(rq->idle_balance)) return 0; /* @@ -5805,22 +7257,22 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu) goto need_kick; rcu_read_lock(); - for_each_domain(cpu, sd) { - struct sched_group *sg = sd->groups; - struct sched_group_power *sgp = sg->sgp; - int nr_busy = atomic_read(&sgp->nr_busy_cpus); + sd = rcu_dereference(per_cpu(sd_busy, cpu)); - if (sd->flags & SD_SHARE_PKG_RESOURCES && nr_busy > 1) - goto need_kick_unlock; + if (sd) { + sgc = sd->groups->sgc; + nr_busy = atomic_read(&sgc->nr_busy_cpus); - if (sd->flags & SD_ASYM_PACKING && nr_busy != sg->group_weight - && (cpumask_first_and(nohz.idle_cpus_mask, - sched_domain_span(sd)) < cpu)) + if (nr_busy > 1) goto need_kick_unlock; - - if (!(sd->flags & (SD_SHARE_PKG_RESOURCES | SD_ASYM_PACKING))) - break; } + + sd = rcu_dereference(per_cpu(sd_asym, cpu)); + + if (sd && (cpumask_first_and(nohz.idle_cpus_mask, + sched_domain_span(sd)) < cpu)) + goto need_kick_unlock; + rcu_read_unlock(); return 0; @@ -5830,7 +7282,7 @@ need_kick: return 1; } #else -static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { } +static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { } #endif /* @@ -5839,38 +7291,34 @@ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) { } */ static void run_rebalance_domains(struct softirq_action *h) { - int this_cpu = smp_processor_id(); - struct rq *this_rq = cpu_rq(this_cpu); + struct rq *this_rq = this_rq(); enum cpu_idle_type idle = this_rq->idle_balance ? CPU_IDLE : CPU_NOT_IDLE; - rebalance_domains(this_cpu, idle); + rebalance_domains(this_rq, idle); /* * If this cpu has a pending nohz_balance_kick, then do the * balancing on behalf of the other idle cpus whose ticks are * stopped. */ - nohz_idle_balance(this_cpu, idle); -} - -static inline int on_null_domain(int cpu) -{ - return !rcu_dereference_sched(cpu_rq(cpu)->sd); + nohz_idle_balance(this_rq, idle); } /* * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. */ -void trigger_load_balance(struct rq *rq, int cpu) +void trigger_load_balance(struct rq *rq) { /* Don't need to rebalance while attached to NULL domain */ - if (time_after_eq(jiffies, rq->next_balance) && - likely(!on_null_domain(cpu))) + if (unlikely(on_null_domain(rq))) + return; + + if (time_after_eq(jiffies, rq->next_balance)) raise_softirq(SCHED_SOFTIRQ); #ifdef CONFIG_NO_HZ_COMMON - if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu))) - nohz_balancer_kick(cpu); + if (nohz_kick_needed(rq)) + nohz_balancer_kick(); #endif } @@ -5928,11 +7376,15 @@ static void task_fork_fair(struct task_struct *p) cfs_rq = task_cfs_rq(current); curr = cfs_rq->curr; - if (unlikely(task_cpu(p) != this_cpu)) { - rcu_read_lock(); - __set_task_cpu(p, this_cpu); - rcu_read_unlock(); - } + /* + * Not only the cpu but also the task_group of the parent might have + * been changed after parent->se.parent,cfs_rq were copied to + * child->se.parent,cfs_rq. So call __set_task_cpu() to make those + * of child point to valid ones. + */ + rcu_read_lock(); + __set_task_cpu(p, this_cpu); + rcu_read_unlock(); update_curr(cfs_rq); @@ -5982,15 +7434,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) struct cfs_rq *cfs_rq = cfs_rq_of(se); /* - * Ensure the task's vruntime is normalized, so that when its + * Ensure the task's vruntime is normalized, so that when it's * switched back to the fair class the enqueue_entity(.flags=0) will * do the right thing. * - * If it was on_rq, then the dequeue_entity(.flags=0) will already - * have normalized the vruntime, if it was !on_rq, then only when + * If it's on_rq, then the dequeue_entity(.flags=0) will already + * have normalized the vruntime, if it's !on_rq, then only when * the task is sleeping will it still have non-normalized vruntime. */ - if (!se->on_rq && p->state != TASK_RUNNING) { + if (!p->on_rq && p->state != TASK_RUNNING) { /* * Fix up our vruntime so that the current sleep doesn't * cause 'unlimited' sleep bonus. @@ -6017,7 +7469,15 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p) */ static void switched_to_fair(struct rq *rq, struct task_struct *p) { - if (!p->se.on_rq) + struct sched_entity *se = &p->se; +#ifdef CONFIG_FAIR_GROUP_SCHED + /* + * Since the real-depth could have been changed (only FAIR + * class maintain depth value), reset depth properly. + */ + se->depth = se->parent ? se->parent->depth + 1 : 0; +#endif + if (!se->on_rq) return; /* @@ -6065,7 +7525,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) #ifdef CONFIG_FAIR_GROUP_SCHED static void task_move_group_fair(struct task_struct *p, int on_rq) { + struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq; + /* * If the task was not on the rq at the time of this cgroup movement * it must have been asleep, sleeping tasks keep their ->vruntime @@ -6091,23 +7553,24 @@ static void task_move_group_fair(struct task_struct *p, int on_rq) * To prevent boost or penalty in the new cfs_rq caused by delta * min_vruntime between the two cfs_rqs, we skip vruntime adjustment. */ - if (!on_rq && (!p->se.sum_exec_runtime || p->state == TASK_WAKING)) + if (!on_rq && (!se->sum_exec_runtime || p->state == TASK_WAKING)) on_rq = 1; if (!on_rq) - p->se.vruntime -= cfs_rq_of(&p->se)->min_vruntime; + se->vruntime -= cfs_rq_of(se)->min_vruntime; set_task_rq(p, task_cpu(p)); + se->depth = se->parent ? se->parent->depth + 1 : 0; if (!on_rq) { - cfs_rq = cfs_rq_of(&p->se); - p->se.vruntime += cfs_rq->min_vruntime; + cfs_rq = cfs_rq_of(se); + se->vruntime += cfs_rq->min_vruntime; #ifdef CONFIG_SMP /* * migrate_task_rq_fair() will have removed our previous * contribution, but we must synchronize for ongoing future * decay. */ - p->se.avg.decay_count = atomic64_read(&cfs_rq->decay_counter); - cfs_rq->blocked_load_avg += p->se.avg.load_avg_contrib; + se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); + cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; #endif } } @@ -6203,13 +7666,17 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, if (!se) return; - if (!parent) + if (!parent) { se->cfs_rq = &rq->cfs; - else + se->depth = 0; + } else { se->cfs_rq = parent->my_q; + se->depth = parent->depth + 1; + } se->my_q = cfs_rq; - update_load_set(&se->load, 0); + /* guarantee group entities always have weight */ + update_load_set(&se->load, NICE_0_LOAD); se->parent = parent; } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 99399f8e479..90284d117fe 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -37,18 +37,18 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true) SCHED_FEAT(WAKEUP_PREEMPTION, true) /* - * Use arch dependent cpu power functions + * Use arch dependent cpu capacity functions */ -SCHED_FEAT(ARCH_POWER, true) +SCHED_FEAT(ARCH_CAPACITY, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) SCHED_FEAT(LB_BIAS, true) /* - * Decrement CPU power based on time not spent running tasks + * Decrement CPU capacity based on time not spent running tasks */ -SCHED_FEAT(NONTASK_POWER, true) +SCHED_FEAT(NONTASK_CAPACITY, true) /* * Queue remote wakeups on the target CPU and process them @@ -63,10 +63,23 @@ SCHED_FEAT(LB_MIN, false) /* * Apply the automatic NUMA scheduling policy. Enabled automatically * at runtime if running on a NUMA machine. Can be controlled via - * numa_balancing=. Allow PTE scanning to be forced on UMA machines - * for debugging the core machinery. + * numa_balancing= */ #ifdef CONFIG_NUMA_BALANCING SCHED_FEAT(NUMA, false) -SCHED_FEAT(NUMA_FORCE, false) + +/* + * NUMA_FAVOUR_HIGHER will favor moving tasks towards nodes where a + * higher number of hinting faults are recorded during active load + * balancing. + */ +SCHED_FEAT(NUMA_FAVOUR_HIGHER, true) + +/* + * NUMA_RESIST_LOWER will resist moving tasks towards nodes where a + * lower number of hinting faults have been recorded. As this has + * the potential to prevent a task ever migrating to a new node + * due to CPU overload it is disabled by default. + */ +SCHED_FEAT(NUMA_RESIST_LOWER, false) #endif diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c new file mode 100644 index 00000000000..cf009fb0bc2 --- /dev/null +++ b/kernel/sched/idle.c @@ -0,0 +1,273 @@ +/* + * Generic entry point for the idle threads + */ +#include <linux/sched.h> +#include <linux/cpu.h> +#include <linux/cpuidle.h> +#include <linux/tick.h> +#include <linux/mm.h> +#include <linux/stackprotector.h> + +#include <asm/tlb.h> + +#include <trace/events/power.h> + +#include "sched.h" + +static int __read_mostly cpu_idle_force_poll; + +void cpu_idle_poll_ctrl(bool enable) +{ + if (enable) { + cpu_idle_force_poll++; + } else { + cpu_idle_force_poll--; + WARN_ON_ONCE(cpu_idle_force_poll < 0); + } +} + +#ifdef CONFIG_GENERIC_IDLE_POLL_SETUP +static int __init cpu_idle_poll_setup(char *__unused) +{ + cpu_idle_force_poll = 1; + return 1; +} +__setup("nohlt", cpu_idle_poll_setup); + +static int __init cpu_idle_nopoll_setup(char *__unused) +{ + cpu_idle_force_poll = 0; + return 1; +} +__setup("hlt", cpu_idle_nopoll_setup); +#endif + +static inline int cpu_idle_poll(void) +{ + rcu_idle_enter(); + trace_cpu_idle_rcuidle(0, smp_processor_id()); + local_irq_enable(); + while (!tif_need_resched()) + cpu_relax(); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); + rcu_idle_exit(); + return 1; +} + +/* Weak implementations for optional arch specific functions */ +void __weak arch_cpu_idle_prepare(void) { } +void __weak arch_cpu_idle_enter(void) { } +void __weak arch_cpu_idle_exit(void) { } +void __weak arch_cpu_idle_dead(void) { } +void __weak arch_cpu_idle(void) +{ + cpu_idle_force_poll = 1; + local_irq_enable(); +} + +/** + * cpuidle_idle_call - the main idle function + * + * NOTE: no locks or semaphores should be used here + * + * On archs that support TIF_POLLING_NRFLAG, is called with polling + * set, and it returns with polling set. If it ever stops polling, it + * must clear the polling bit. + */ +static void cpuidle_idle_call(void) +{ + struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int next_state, entered_state; + bool broadcast; + + /* + * Check if the idle task must be rescheduled. If it is the + * case, exit the function after re-enabling the local irq. + */ + if (need_resched()) { + local_irq_enable(); + return; + } + + /* + * During the idle period, stop measuring the disabled irqs + * critical sections latencies + */ + stop_critical_timings(); + + /* + * Tell the RCU framework we are entering an idle section, + * so no more rcu read side critical sections and one more + * step to the grace period + */ + rcu_idle_enter(); + + /* + * Ask the cpuidle framework to choose a convenient idle state. + * Fall back to the default arch idle method on errors. + */ + next_state = cpuidle_select(drv, dev); + if (next_state < 0) { +use_default: + /* + * We can't use the cpuidle framework, let's use the default + * idle routine. + */ + if (current_clr_polling_and_test()) + local_irq_enable(); + else + arch_cpu_idle(); + + goto exit_idle; + } + + + /* + * The idle task must be scheduled, it is pointless to + * go to idle, just update no idle residency and get + * out of this function + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + entered_state = next_state; + local_irq_enable(); + goto exit_idle; + } + + broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP); + + /* + * Tell the time framework to switch to a broadcast timer + * because our local timer will be shutdown. If a local timer + * is used from another cpu as a broadcast timer, this call may + * fail if it is not available + */ + if (broadcast && + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu)) + goto use_default; + + trace_cpu_idle_rcuidle(next_state, dev->cpu); + + /* + * Enter the idle state previously returned by the governor decision. + * This function will block until an interrupt occurs and will take + * care of re-enabling the local interrupts + */ + entered_state = cpuidle_enter(drv, dev, next_state); + + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + + if (broadcast) + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + + /* + * Give the governor an opportunity to reflect on the outcome + */ + cpuidle_reflect(dev, entered_state); + +exit_idle: + __current_set_polling(); + + /* + * It is up to the idle functions to reenable local interrupts + */ + if (WARN_ON_ONCE(irqs_disabled())) + local_irq_enable(); + + rcu_idle_exit(); + start_critical_timings(); +} + +/* + * Generic idle loop implementation + * + * Called with polling cleared. + */ +static void cpu_idle_loop(void) +{ + while (1) { + /* + * If the arch has a polling bit, we maintain an invariant: + * + * Our polling bit is clear if we're not scheduled (i.e. if + * rq->curr != rq->idle). This means that, if rq->idle has + * the polling bit set, then setting need_resched is + * guaranteed to cause the cpu to reschedule. + */ + + __current_set_polling(); + tick_nohz_idle_enter(); + + while (!need_resched()) { + check_pgt_cache(); + rmb(); + + if (cpu_is_offline(smp_processor_id())) + arch_cpu_idle_dead(); + + local_irq_disable(); + arch_cpu_idle_enter(); + + /* + * In poll mode we reenable interrupts and spin. + * + * Also if we detected in the wakeup from idle + * path that the tick broadcast device expired + * for us, we don't want to go deep idle as we + * know that the IPI is going to arrive right + * away + */ + if (cpu_idle_force_poll || tick_check_broadcast_expired()) + cpu_idle_poll(); + else + cpuidle_idle_call(); + + arch_cpu_idle_exit(); + } + + /* + * Since we fell out of the loop above, we know + * TIF_NEED_RESCHED must be set, propagate it into + * PREEMPT_NEED_RESCHED. + * + * This is required because for polling idle loops we will + * not have had an IPI to fold the state for us. + */ + preempt_set_need_resched(); + tick_nohz_idle_exit(); + __current_clr_polling(); + + /* + * We promise to call sched_ttwu_pending and reschedule + * if need_resched is set while polling is set. That + * means that clearing polling needs to be visible + * before doing these things. + */ + smp_mb__after_atomic(); + + sched_ttwu_pending(); + schedule_preempt_disabled(); + } +} + +void cpu_startup_entry(enum cpuhp_state state) +{ + /* + * This #ifdef needs to die, but it's too late in the cycle to + * make this generic (arm and sh have never invoked the canary + * init for the non boot cpus!). Will be fixed in 3.11 + */ +#ifdef CONFIG_X86 + /* + * If we're the non-boot CPU, nothing set the stack canary up + * for us. The boot CPU already has it initialized but no harm + * in doing it again. This is a good place for updating it, as + * we wont ever return from this function (so the invalid + * canaries already on the stack wont ever trigger). + */ + boot_init_stack_canary(); +#endif + arch_cpu_idle_prepare(); + cpu_idle_loop(); +} diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index d8da01008d3..879f2b75266 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -9,22 +9,12 @@ #ifdef CONFIG_SMP static int -select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) +select_task_rq_idle(struct task_struct *p, int cpu, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } - -static void pre_schedule_idle(struct rq *rq, struct task_struct *prev) -{ - idle_exit_fair(rq); - rq_last_tick_reset(rq); -} - -static void post_schedule_idle(struct rq *rq) -{ - idle_enter_fair(rq); -} #endif /* CONFIG_SMP */ + /* * Idle tasks are unconditionally rescheduled: */ @@ -33,13 +23,12 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl resched_task(rq->idle); } -static struct task_struct *pick_next_task_idle(struct rq *rq) +static struct task_struct * +pick_next_task_idle(struct rq *rq, struct task_struct *prev) { + put_prev_task(rq, prev); + schedstat_inc(rq, sched_goidle); -#ifdef CONFIG_SMP - /* Trigger the post schedule to do an idle_enter for CFS */ - rq->post_schedule = 1; -#endif return rq->idle; } @@ -58,6 +47,8 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) { + idle_exit_fair(rq); + rq_last_tick_reset(rq); } static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued) @@ -101,8 +92,6 @@ const struct sched_class idle_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_idle, - .pre_schedule = pre_schedule_idle, - .post_schedule = post_schedule_idle, #endif .set_curr_task = set_curr_task_idle, diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 01970c8e64d..a49083192c6 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -79,6 +79,8 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) rt_rq->overloaded = 0; plist_head_init(&rt_rq->pushable_tasks); #endif + /* We start is dequeued state, because no RT tasks are queued */ + rt_rq->rt_queued = 0; rt_rq->rt_time = 0; rt_rq->rt_throttled = 0; @@ -112,6 +114,13 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) return rt_se->rt_rq; } +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = rt_se->rt_rq; + + return rt_rq->rq; +} + void free_rt_sched_group(struct task_group *tg) { int i; @@ -211,10 +220,16 @@ static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) return container_of(rt_rq, struct rq, rt); } -static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) { struct task_struct *p = rt_task_of(rt_se); - struct rq *rq = task_rq(p); + + return task_rq(p); +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + struct rq *rq = rq_of_rt_se(rt_se); return &rq->rt; } @@ -229,6 +244,14 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) #ifdef CONFIG_SMP +static int pull_rt_task(struct rq *this_rq); + +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + /* Try to pull RT tasks here if we lower this rq's prio */ + return rq->rt.highest_prio.curr > prev->prio; +} + static inline int rt_overloaded(struct rq *rq) { return atomic_read(&rq->rd->rto_count); @@ -246,8 +269,10 @@ static inline void rt_set_overload(struct rq *rq) * if we should look at the mask. It would be a shame * if we looked at the mask, but the mask was not * updated yet. + * + * Matched by the barrier in pull_rt_task(). */ - wmb(); + smp_wmb(); atomic_inc(&rq->rd->rto_count); } @@ -313,6 +338,15 @@ static inline int has_pushable_tasks(struct rq *rq) return !plist_head_empty(&rq->rt.pushable_tasks); } +static inline void set_post_schedule(struct rq *rq) +{ + /* + * We detect this state here so that we can avoid taking the RQ + * lock again later if there is no need to push + */ + rq->post_schedule = has_pushable_tasks(rq); +} + static void enqueue_pushable_task(struct rq *rq, struct task_struct *p) { plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks); @@ -357,8 +391,24 @@ void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { } +static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) +{ + return false; +} + +static inline int pull_rt_task(struct rq *this_rq) +{ + return 0; +} + +static inline void set_post_schedule(struct rq *rq) +{ +} #endif /* CONFIG_SMP */ +static void enqueue_top_rt_rq(struct rt_rq *rt_rq); +static void dequeue_top_rt_rq(struct rt_rq *rt_rq); + static inline int on_rt_rq(struct sched_rt_entity *rt_se) { return !list_empty(&rt_se->run_list); @@ -420,8 +470,11 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; if (rt_rq->rt_nr_running) { - if (rt_se && !on_rt_rq(rt_se)) + if (!rt_se) + enqueue_top_rt_rq(rt_rq); + else if (!on_rt_rq(rt_se)) enqueue_rt_entity(rt_se, false); + if (rt_rq->highest_prio.curr < curr->prio) resched_task(curr); } @@ -434,7 +487,9 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; - if (rt_se && on_rt_rq(rt_se)) + if (!rt_se) + dequeue_top_rt_rq(rt_rq); + else if (on_rt_rq(rt_se)) dequeue_rt_entity(rt_se); } @@ -505,12 +560,18 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { - if (rt_rq->rt_nr_running) - resched_task(rq_of_rt_rq(rt_rq)->curr); + struct rq *rq = rq_of_rt_rq(rt_rq); + + if (!rt_rq->rt_nr_running) + return; + + enqueue_top_rt_rq(rt_rq); + resched_task(rq->curr); } static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { + dequeue_top_rt_rq(rt_rq); } static inline int rt_rq_throttled(struct rt_rq *rt_rq) @@ -536,6 +597,14 @@ static inline struct rt_bandwidth *sched_rt_bandwidth(struct rt_rq *rt_rq) #endif /* CONFIG_RT_GROUP_SCHED */ +bool sched_rt_bandwidth_account(struct rt_rq *rt_rq) +{ + struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq); + + return (hrtimer_active(&rt_b->rt_period_timer) || + rt_rq->rt_time < rt_b->rt_runtime); +} + #ifdef CONFIG_SMP /* * We ran out of runtime, see if we can borrow some from our neighbours. @@ -821,14 +890,8 @@ static int sched_rt_runtime_exceeded(struct rt_rq *rt_rq) * but accrue some time due to boosting. */ if (likely(rt_b->rt_runtime)) { - static bool once = false; - rt_rq->rt_throttled = 1; - - if (!once) { - once = true; - printk_sched("sched: RT throttling activated\n"); - } + printk_deferred_once("sched: RT throttling activated\n"); } else { /* * In case we did anyway, make it go away, @@ -855,7 +918,6 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; - struct rt_rq *rt_rq = rt_rq_of_se(rt_se); u64 delta_exec; if (curr->sched_class != &rt_sched_class) @@ -880,7 +942,7 @@ static void update_curr_rt(struct rq *rq) return; for_each_sched_rt_entity(rt_se) { - rt_rq = rt_rq_of_se(rt_se); + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { raw_spin_lock(&rt_rq->rt_runtime_lock); @@ -892,6 +954,38 @@ static void update_curr_rt(struct rq *rq) } } +static void +dequeue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (!rt_rq->rt_queued) + return; + + BUG_ON(!rq->nr_running); + + sub_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 0; +} + +static void +enqueue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (rt_rq->rt_queued) + return; + if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + return; + + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; +} + #if defined CONFIG_SMP static void @@ -899,6 +993,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && prio < prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, prio); } @@ -908,6 +1009,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && rt_rq->highest_prio.curr != prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); } @@ -1001,12 +1109,23 @@ void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {} #endif /* CONFIG_RT_GROUP_SCHED */ static inline +unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + + if (group_rq) + return group_rq->rt_nr_running; + else + return 1; +} + +static inline void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { int prio = rt_se_prio(rt_se); WARN_ON(!rt_prio(prio)); - rt_rq->rt_nr_running++; + rt_rq->rt_nr_running += rt_se_nr_running(rt_se); inc_rt_prio(rt_rq, prio); inc_rt_migration(rt_se, rt_rq); @@ -1018,7 +1137,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { WARN_ON(!rt_prio(rt_se_prio(rt_se))); WARN_ON(!rt_rq->rt_nr_running); - rt_rq->rt_nr_running--; + rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); dec_rt_prio(rt_rq, rt_se_prio(rt_se)); dec_rt_migration(rt_se, rt_rq); @@ -1075,6 +1194,8 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) back = rt_se; } + dequeue_top_rt_rq(rt_rq_of_se(back)); + for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) __dequeue_rt_entity(rt_se); @@ -1083,13 +1204,18 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) { + struct rq *rq = rq_of_rt_se(rt_se); + dequeue_rt_stack(rt_se); for_each_sched_rt_entity(rt_se) __enqueue_rt_entity(rt_se, head); + enqueue_top_rt_rq(&rq->rt); } static void dequeue_rt_entity(struct sched_rt_entity *rt_se) { + struct rq *rq = rq_of_rt_se(rt_se); + dequeue_rt_stack(rt_se); for_each_sched_rt_entity(rt_se) { @@ -1098,6 +1224,7 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se) if (rt_rq && rt_rq->rt_nr_running) __enqueue_rt_entity(rt_se, false); } + enqueue_top_rt_rq(&rq->rt); } /* @@ -1115,8 +1242,6 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); - - inc_nr_running(rq); } static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) @@ -1127,8 +1252,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) dequeue_rt_entity(rt_se); dequeue_pushable_task(rq, p); - - dec_nr_running(rq); } /* @@ -1169,13 +1292,10 @@ static void yield_task_rt(struct rq *rq) static int find_lowest_rq(struct task_struct *task); static int -select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) +select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) { struct task_struct *curr; struct rq *rq; - int cpu; - - cpu = task_cpu(p); if (p->nr_cpus_allowed == 1) goto out; @@ -1213,8 +1333,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) */ if (curr && unlikely(rt_task(curr)) && (curr->nr_cpus_allowed < 2 || - curr->prio <= p->prio) && - (p->nr_cpus_allowed > 1)) { + curr->prio <= p->prio)) { int target = find_lowest_rq(p); if (target != -1) @@ -1298,15 +1417,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) { struct sched_rt_entity *rt_se; struct task_struct *p; - struct rt_rq *rt_rq; - - rt_rq = &rq->rt; - - if (!rt_rq->rt_nr_running) - return NULL; - - if (rt_rq_throttled(rt_rq)) - return NULL; + struct rt_rq *rt_rq = &rq->rt; do { rt_se = pick_next_rt_entity(rq, rt_rq); @@ -1320,21 +1431,43 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) return p; } -static struct task_struct *pick_next_task_rt(struct rq *rq) +static struct task_struct * +pick_next_task_rt(struct rq *rq, struct task_struct *prev) { - struct task_struct *p = _pick_next_task_rt(rq); + struct task_struct *p; + struct rt_rq *rt_rq = &rq->rt; + + if (need_pull_rt_task(rq, prev)) { + pull_rt_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a dl or stop task can slip in, in which case we need + * to re-start task selection. + */ + if (unlikely((rq->stop && rq->stop->on_rq) || + rq->dl.dl_nr_running)) + return RETRY_TASK; + } + + /* + * We may dequeue prev's rt_rq in put_prev_task(). + * So, we update time before rt_nr_running check. + */ + if (prev->sched_class == &rt_sched_class) + update_curr_rt(rq); + + if (!rt_rq->rt_queued) + return NULL; + + put_prev_task(rq, prev); + + p = _pick_next_task_rt(rq); /* The running task is never eligible for pushing */ if (p) dequeue_pushable_task(rq, p); -#ifdef CONFIG_SMP - /* - * We detect this state here so that we can avoid taking the RQ - * lock again later if there is no need to push - */ - rq->post_schedule = has_pushable_tasks(rq); -#endif + set_post_schedule(rq); return p; } @@ -1630,6 +1763,12 @@ static int pull_rt_task(struct rq *this_rq) if (likely(!rt_overloaded(this_rq))) return 0; + /* + * Match the barrier from rt_set_overloaded; this guarantees that if we + * see overloaded we must also see the rto_mask bit. + */ + smp_rmb(); + for_each_cpu(cpu, this_rq->rd->rto_mask) { if (this_cpu == cpu) continue; @@ -1698,13 +1837,6 @@ skip: return ret; } -static void pre_schedule_rt(struct rq *rq, struct task_struct *prev) -{ - /* Try to pull RT tasks here if we lower this rq's prio */ - if (rq->rt.highest_prio.curr > prev->prio) - pull_rt_task(rq); -} - static void post_schedule_rt(struct rq *rq) { push_rt_tasks(rq); @@ -1720,7 +1852,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p) !test_tsk_need_resched(rq->curr) && has_pushable_tasks(rq) && p->nr_cpus_allowed > 1 && - rt_task(rq->curr) && + (dl_task(rq->curr) || rt_task(rq->curr)) && (rq->curr->nr_cpus_allowed < 2 || rq->curr->prio <= p->prio)) push_rt_tasks(rq); @@ -1807,7 +1939,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p) resched_task(rq->curr); } -void init_sched_rt_class(void) +void __init init_sched_rt_class(void) { unsigned int i; @@ -1836,9 +1968,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) */ if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP - if (rq->rt.overloaded && push_rt_task(rq) && + if (p->nr_cpus_allowed > 1 && rq->rt.overloaded && /* Don't resched if we changed runqueues */ - rq != task_rq(p)) + push_rt_task(rq) && rq != task_rq(p)) check_resched = 0; #endif /* CONFIG_SMP */ if (check_resched && p->prio < rq->curr->prio) @@ -1931,8 +2063,8 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) p->rt.time_slice = sched_rr_timeslice; /* - * Requeue to the end of queue if we (and all of our ancestors) are the - * only element on the queue + * Requeue to the end of queue if we (and all of our ancestors) are not + * the only element on the queue */ for_each_sched_rt_entity(rt_se) { if (rt_se->run_list.prev != rt_se->run_list.next) { @@ -1981,7 +2113,6 @@ const struct sched_class rt_sched_class = { .set_cpus_allowed = set_cpus_allowed_rt, .rq_online = rq_online_rt, .rq_offline = rq_offline_rt, - .pre_schedule = pre_schedule_rt, .post_schedule = post_schedule_rt, .task_woken = task_woken_rt, .switched_from = switched_from_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b3c5653e1dc..31cc02ebc54 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2,12 +2,15 @@ #include <linux/sched.h> #include <linux/sched/sysctl.h> #include <linux/sched/rt.h> +#include <linux/sched/deadline.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> #include <linux/tick.h> +#include <linux/slab.h> #include "cpupri.h" +#include "cpudeadline.h" #include "cpuacct.h" struct rq; @@ -21,24 +24,6 @@ extern long calc_load_fold_active(struct rq *this_rq); extern void update_cpu_load_active(struct rq *this_rq); /* - * Convert user-nice values [ -20 ... 0 ... 19 ] - * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], - * and back. - */ -#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) -#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) -#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) - -/* - * 'User priority' is the nice value converted to something we - * can work with better when scaling various scheduler parameters, - * it's a [ 0 ... 39 ] range. - */ -#define USER_PRIO(p) ((p)-MAX_RT_PRIO) -#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) -#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) - -/* * Helpers for converting nanosecond timing to jiffy resolution */ #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) @@ -72,6 +57,13 @@ extern void update_cpu_load_active(struct rq *this_rq); #define NICE_0_SHIFT SCHED_LOAD_SHIFT /* + * Single value that decides SCHED_DEADLINE internal math precision. + * 10 -> just above 1us + * 9 -> just above 0.5us + */ +#define DL_SCALE (10) + +/* * These are the 'tuning knobs' of the scheduler: */ @@ -80,11 +72,19 @@ extern void update_cpu_load_active(struct rq *this_rq); */ #define RUNTIME_INF ((u64)~0ULL) +static inline int fair_policy(int policy) +{ + return policy == SCHED_NORMAL || policy == SCHED_BATCH; +} + static inline int rt_policy(int policy) { - if (policy == SCHED_FIFO || policy == SCHED_RR) - return 1; - return 0; + return policy == SCHED_FIFO || policy == SCHED_RR; +} + +static inline int dl_policy(int policy) +{ + return policy == SCHED_DEADLINE; } static inline int task_has_rt_policy(struct task_struct *p) @@ -92,6 +92,25 @@ static inline int task_has_rt_policy(struct task_struct *p) return rt_policy(p->policy); } +static inline int task_has_dl_policy(struct task_struct *p) +{ + return dl_policy(p->policy); +} + +static inline bool dl_time_before(u64 a, u64 b) +{ + return (s64)(a - b) < 0; +} + +/* + * Tells if entity @a should preempt entity @b. + */ +static inline bool +dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b) +{ + return dl_time_before(a->deadline, b->deadline); +} + /* * This is the priority-queue data structure of the RT scheduling class: */ @@ -107,6 +126,47 @@ struct rt_bandwidth { u64 rt_runtime; struct hrtimer rt_period_timer; }; +/* + * To keep the bandwidth of -deadline tasks and groups under control + * we need some place where: + * - store the maximum -deadline bandwidth of the system (the group); + * - cache the fraction of that bandwidth that is currently allocated. + * + * This is all done in the data structure below. It is similar to the + * one used for RT-throttling (rt_bandwidth), with the main difference + * that, since here we are only interested in admission control, we + * do not decrease any runtime while the group "executes", neither we + * need a timer to replenish it. + * + * With respect to SMP, the bandwidth is given on a per-CPU basis, + * meaning that: + * - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU; + * - dl_total_bw array contains, in the i-eth element, the currently + * allocated bandwidth on the i-eth CPU. + * Moreover, groups consume bandwidth on each CPU, while tasks only + * consume bandwidth on the CPU they're running on. + * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw + * that will be shown the next time the proc or cgroup controls will + * be red. It on its turn can be changed by writing on its own + * control. + */ +struct dl_bandwidth { + raw_spinlock_t dl_runtime_lock; + u64 dl_runtime; + u64 dl_period; +}; + +static inline int dl_bandwidth_enabled(void) +{ + return sysctl_sched_rt_runtime >= 0; +} + +extern struct dl_bw *dl_bw_of(int i); + +struct dl_bw { + raw_spinlock_t lock; + u64 bw, total_bw; +}; extern struct mutex sched_domains_mutex; @@ -218,7 +278,7 @@ extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b); extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b); -extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b); +extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force); extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq); extern void free_rt_sched_group(struct task_group *tg); @@ -349,6 +409,8 @@ struct rt_rq { int overloaded; struct plist_head pushable_tasks; #endif + int rt_queued; + int rt_throttled; u64 rt_time; u64 rt_runtime; @@ -363,6 +425,41 @@ struct rt_rq { #endif }; +/* Deadline class' related fields in a runqueue */ +struct dl_rq { + /* runqueue is an rbtree, ordered by deadline */ + struct rb_root rb_root; + struct rb_node *rb_leftmost; + + unsigned long dl_nr_running; + +#ifdef CONFIG_SMP + /* + * Deadline values of the currently executing and the + * earliest ready task on this rq. Caching these facilitates + * the decision wether or not a ready but not running task + * should migrate somewhere else. + */ + struct { + u64 curr; + u64 next; + } earliest_dl; + + unsigned long dl_nr_migratory; + int overloaded; + + /* + * Tasks on this rq that can be pushed away. They are kept in + * an rb-tree, ordered by tasks' deadlines, with caching + * of the leftmost (earliest deadline) element. + */ + struct rb_root pushable_dl_tasks_root; + struct rb_node *pushable_dl_tasks_leftmost; +#else + struct dl_bw dl_bw; +#endif +}; + #ifdef CONFIG_SMP /* @@ -381,6 +478,15 @@ struct root_domain { cpumask_var_t online; /* + * The bit corresponding to a CPU gets set here if such CPU has more + * than one runnable -deadline task (as it is below for RT tasks). + */ + cpumask_var_t dlo_mask; + atomic_t dlo_count; + struct dl_bw dl_bw; + struct cpudl cpudl; + + /* * The "RT overload" flag: it gets set if a CPU has more than * one runnable RT task. */ @@ -408,6 +514,10 @@ struct rq { * remote CPUs use both these fields when doing load calculation. */ unsigned int nr_running; +#ifdef CONFIG_NUMA_BALANCING + unsigned int nr_numa_running; + unsigned int nr_preferred_running; +#endif #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; unsigned long last_load_update_tick; @@ -427,15 +537,14 @@ struct rq { struct cfs_rq cfs; struct rt_rq rt; + struct dl_rq dl; #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; -#endif /* CONFIG_FAIR_GROUP_SCHED */ -#ifdef CONFIG_RT_GROUP_SCHED - struct list_head leaf_rt_rq_list; -#endif + struct sched_avg avg; +#endif /* CONFIG_FAIR_GROUP_SCHED */ /* * This is part of a global counter where only the total sum @@ -458,7 +567,7 @@ struct rq { struct root_domain *rd; struct sched_domain *sd; - unsigned long cpu_power; + unsigned long cpu_capacity; unsigned char idle_balance; /* For active balancing */ @@ -476,6 +585,9 @@ struct rq { u64 age_stamp; u64 idle_stamp; u64 avg_idle; + + /* This is used to determine avg_idle's max value */ + u64 max_idle_balance_cost; #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -521,8 +633,6 @@ struct rq { #ifdef CONFIG_SMP struct llist_head wake_list; #endif - - struct sched_avg avg; }; static inline int cpu_of(struct rq *rq) @@ -552,8 +662,16 @@ static inline u64 rq_clock_task(struct rq *rq) return rq->clock_task; } +#ifdef CONFIG_NUMA_BALANCING +extern void sched_setnuma(struct task_struct *p, int node); +extern int migrate_task_to(struct task_struct *p, int cpu); +extern int migrate_swap(struct task_struct *, struct task_struct *); +#endif /* CONFIG_NUMA_BALANCING */ + #ifdef CONFIG_SMP +extern void sched_ttwu_pending(void); + #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ lockdep_is_held(&sched_domains_mutex)) @@ -593,18 +711,34 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag) return hsd; } +static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd; + + for_each_domain(cpu, sd) { + if (sd->flags & flag) + break; + } + + return sd; +} + DECLARE_PER_CPU(struct sched_domain *, sd_llc); DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); +DECLARE_PER_CPU(struct sched_domain *, sd_numa); +DECLARE_PER_CPU(struct sched_domain *, sd_busy); +DECLARE_PER_CPU(struct sched_domain *, sd_asym); -struct sched_group_power { +struct sched_group_capacity { atomic_t ref; /* - * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. + * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity + * for a single CPU. */ - unsigned int power, power_orig; + unsigned int capacity, capacity_orig; unsigned long next_update; + int imbalance; /* XXX unrelated to capacity but shared group state */ /* * Number of busy cpus in this group. */ @@ -618,7 +752,7 @@ struct sched_group { atomic_t ref; unsigned int group_weight; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; /* * The CPUs this group covers. @@ -641,7 +775,7 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg) */ static inline struct cpumask *sched_group_mask(struct sched_group *sg) { - return to_cpumask(sg->sgp->cpumask); + return to_cpumask(sg->sgc->cpumask); } /** @@ -655,6 +789,10 @@ static inline unsigned int group_first_cpu(struct sched_group *group) extern int group_balance_cpu(struct sched_group *sg); +#else + +static inline void sched_ttwu_pending(void) { } + #endif /* CONFIG_SMP */ #include "stats.h" @@ -719,6 +857,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) */ smp_wmb(); task_thread_info(p)->cpu = cpu; + p->wake_cpu = cpu; #endif } @@ -796,8 +935,6 @@ static inline u64 global_rt_runtime(void) return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; } - - static inline int task_current(struct rq *rq, struct task_struct *p) { return rq->curr == p; @@ -957,9 +1094,12 @@ static const u32 prio_to_wmult[40] = { #else #define ENQUEUE_WAKING 0 #endif +#define ENQUEUE_REPLENISH 8 #define DEQUEUE_SLEEP 1 +#define RETRY_TASK ((void *)-1UL) + struct sched_class { const struct sched_class *next; @@ -970,14 +1110,22 @@ struct sched_class { void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); - struct task_struct * (*pick_next_task) (struct rq *rq); + /* + * It is the responsibility of the pick_next_task() method that will + * return the next task to call put_prev_task() on the @prev task or + * something equivalent. + * + * May return RETRY_TASK when it finds a higher prio class has runnable + * tasks. + */ + struct task_struct * (*pick_next_task) (struct rq *rq, + struct task_struct *prev); void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); + int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); void (*migrate_task_rq)(struct task_struct *p, int next_cpu); - void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); void (*task_waking) (struct task_struct *task); void (*task_woken) (struct rq *this_rq, struct task_struct *task); @@ -992,6 +1140,7 @@ struct sched_class { void (*set_curr_task) (struct rq *rq); void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); void (*task_fork) (struct task_struct *p); + void (*task_dead) (struct task_struct *p); void (*switched_from) (struct rq *this_rq, struct task_struct *task); void (*switched_to) (struct rq *this_rq, struct task_struct *task); @@ -1006,11 +1155,17 @@ struct sched_class { #endif }; +static inline void put_prev_task(struct rq *rq, struct task_struct *prev) +{ + prev->sched_class->put_prev_task(rq, prev); +} + #define sched_class_highest (&stop_sched_class) #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) extern const struct sched_class stop_sched_class; +extern const struct sched_class dl_sched_class; extern const struct sched_class rt_sched_class; extern const struct sched_class fair_sched_class; extern const struct sched_class idle_sched_class; @@ -1018,27 +1173,28 @@ extern const struct sched_class idle_sched_class; #ifdef CONFIG_SMP -extern void update_group_power(struct sched_domain *sd, int cpu); +extern void update_group_capacity(struct sched_domain *sd, int cpu); -extern void trigger_load_balance(struct rq *rq, int cpu); -extern void idle_balance(int this_cpu, struct rq *this_rq); +extern void trigger_load_balance(struct rq *rq); extern void idle_enter_fair(struct rq *this_rq); extern void idle_exit_fair(struct rq *this_rq); -#else /* CONFIG_SMP */ +#else -static inline void idle_balance(int cpu, struct rq *rq) -{ -} +static inline void idle_enter_fair(struct rq *rq) { } +static inline void idle_exit_fair(struct rq *rq) { } #endif extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); + +extern void init_sched_dl_class(void); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); +extern void init_sched_dl_class(void); extern void resched_task(struct task_struct *p); extern void resched_cpu(int cpu); @@ -1046,26 +1202,24 @@ extern void resched_cpu(int cpu); extern struct rt_bandwidth def_rt_bandwidth; extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); +extern struct dl_bandwidth def_dl_bandwidth; +extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); +extern void init_dl_task_timer(struct sched_dl_entity *dl_se); + +unsigned long to_ratio(u64 period, u64 runtime); + extern void update_idle_cpu_load(struct rq *this_rq); extern void init_task_runnable_average(struct task_struct *p); -#ifdef CONFIG_PARAVIRT -static inline u64 steal_ticks(u64 steal) +static inline void add_nr_running(struct rq *rq, unsigned count) { - if (unlikely(steal > NSEC_PER_SEC)) - return div_u64(steal, TICK_NSEC); + unsigned prev_nr = rq->nr_running; - return __iter_div_u64_rem(steal, TICK_NSEC, &steal); -} -#endif - -static inline void inc_nr_running(struct rq *rq) -{ - rq->nr_running++; + rq->nr_running = prev_nr + count; #ifdef CONFIG_NO_HZ_FULL - if (rq->nr_running == 2) { + if (prev_nr < 2 && rq->nr_running >= 2) { if (tick_nohz_full_cpu(rq->cpu)) { /* Order rq->nr_running write against the IPI */ smp_wmb(); @@ -1075,9 +1229,9 @@ static inline void inc_nr_running(struct rq *rq) #endif } -static inline void dec_nr_running(struct rq *rq) +static inline void sub_nr_running(struct rq *rq, unsigned count) { - rq->nr_running--; + rq->nr_running -= count; } static inline void rq_last_tick_reset(struct rq *rq) @@ -1220,6 +1374,33 @@ static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); } +static inline void double_lock(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock_irq(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + +static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + raw_spin_lock(l1); + raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + /* * double_rq_lock - safely lock two runqueues * @@ -1304,8 +1485,10 @@ extern void print_rt_stats(struct seq_file *m, int cpu); extern void init_cfs_rq(struct cfs_rq *cfs_rq); extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); +extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq); -extern void account_cfs_bandwidth_used(int enabled, int was_enabled); +extern void cfs_bandwidth_usage_inc(void); +extern void cfs_bandwidth_usage_dec(void); #ifdef CONFIG_NO_HZ_COMMON enum rq_nohz_flag_bits { diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index da98af347e8..a476bea17fb 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -142,4 +142,4 @@ static int __init proc_schedstat_init(void) proc_create("schedstat", 0, NULL, &proc_schedstat_operations); return 0; } -module_init(proc_schedstat_init); +subsys_initcall(proc_schedstat_init); diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 5aef494fc8b..4ab70433965 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -59,9 +59,9 @@ static inline void sched_info_reset_dequeued(struct task_struct *t) * from dequeue_task() to account for possible rq->clock skew across cpus. The * delta taken on each cpu would annul the skew. */ -static inline void sched_info_dequeued(struct task_struct *t) +static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t) { - unsigned long long now = rq_clock(task_rq(t)), delta = 0; + unsigned long long now = rq_clock(rq), delta = 0; if (unlikely(sched_info_on())) if (t->sched_info.last_queued) @@ -69,7 +69,7 @@ static inline void sched_info_dequeued(struct task_struct *t) sched_info_reset_dequeued(t); t->sched_info.run_delay += delta; - rq_sched_info_dequeued(task_rq(t), delta); + rq_sched_info_dequeued(rq, delta); } /* @@ -77,9 +77,9 @@ static inline void sched_info_dequeued(struct task_struct *t) * long it was waiting to run. We also note when it began so that we * can keep stats on how long its timeslice is. */ -static void sched_info_arrive(struct task_struct *t) +static void sched_info_arrive(struct rq *rq, struct task_struct *t) { - unsigned long long now = rq_clock(task_rq(t)), delta = 0; + unsigned long long now = rq_clock(rq), delta = 0; if (t->sched_info.last_queued) delta = now - t->sched_info.last_queued; @@ -88,7 +88,7 @@ static void sched_info_arrive(struct task_struct *t) t->sched_info.last_arrival = now; t->sched_info.pcount++; - rq_sched_info_arrive(task_rq(t), delta); + rq_sched_info_arrive(rq, delta); } /* @@ -96,29 +96,30 @@ static void sched_info_arrive(struct task_struct *t) * the timestamp if it is already not set. It's assumed that * sched_info_dequeued() will clear that stamp when appropriate. */ -static inline void sched_info_queued(struct task_struct *t) +static inline void sched_info_queued(struct rq *rq, struct task_struct *t) { if (unlikely(sched_info_on())) if (!t->sched_info.last_queued) - t->sched_info.last_queued = rq_clock(task_rq(t)); + t->sched_info.last_queued = rq_clock(rq); } /* - * Called when a process ceases being the active-running process, either - * voluntarily or involuntarily. Now we can calculate how long we ran. + * Called when a process ceases being the active-running process involuntarily + * due, typically, to expiring its time slice (this may also be called when + * switching to the idle task). Now we can calculate how long we ran. * Also, if the process is still in the TASK_RUNNING state, call * sched_info_queued() to mark that it has now again started waiting on * the runqueue. */ -static inline void sched_info_depart(struct task_struct *t) +static inline void sched_info_depart(struct rq *rq, struct task_struct *t) { - unsigned long long delta = rq_clock(task_rq(t)) - + unsigned long long delta = rq_clock(rq) - t->sched_info.last_arrival; - rq_sched_info_depart(task_rq(t), delta); + rq_sched_info_depart(rq, delta); if (t->state == TASK_RUNNING) - sched_info_queued(t); + sched_info_queued(rq, t); } /* @@ -127,32 +128,34 @@ static inline void sched_info_depart(struct task_struct *t) * the idle task.) We are only called when prev != next. */ static inline void -__sched_info_switch(struct task_struct *prev, struct task_struct *next) +__sched_info_switch(struct rq *rq, + struct task_struct *prev, struct task_struct *next) { - struct rq *rq = task_rq(prev); - /* * prev now departs the cpu. It's not interesting to record * stats about how efficient we were at scheduling the idle * process, however. */ if (prev != rq->idle) - sched_info_depart(prev); + sched_info_depart(rq, prev); if (next != rq->idle) - sched_info_arrive(next); + sched_info_arrive(rq, next); } static inline void -sched_info_switch(struct task_struct *prev, struct task_struct *next) +sched_info_switch(struct rq *rq, + struct task_struct *prev, struct task_struct *next) { if (unlikely(sched_info_on())) - __sched_info_switch(prev, next); + __sched_info_switch(rq, prev, next); } #else -#define sched_info_queued(t) do { } while (0) +#define sched_info_queued(rq, t) do { } while (0) #define sched_info_reset_dequeued(t) do { } while (0) -#define sched_info_dequeued(t) do { } while (0) -#define sched_info_switch(t, next) do { } while (0) +#define sched_info_dequeued(rq, t) do { } while (0) +#define sched_info_depart(rq, t) do { } while (0) +#define sched_info_arrive(rq, next) do { } while (0) +#define sched_info_switch(rq, t, next) do { } while (0) #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */ /* diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index e08fbeeb54b..bfe0edadbfb 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -11,7 +11,7 @@ #ifdef CONFIG_SMP static int -select_task_rq_stop(struct task_struct *p, int sd_flag, int flags) +select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags) { return task_cpu(p); /* stop tasks as never migrate */ } @@ -23,28 +23,31 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) /* we're never preempted */ } -static struct task_struct *pick_next_task_stop(struct rq *rq) +static struct task_struct * +pick_next_task_stop(struct rq *rq, struct task_struct *prev) { struct task_struct *stop = rq->stop; - if (stop && stop->on_rq) { - stop->se.exec_start = rq_clock_task(rq); - return stop; - } + if (!stop || !stop->on_rq) + return NULL; - return NULL; + put_prev_task(rq, prev); + + stop->se.exec_start = rq_clock_task(rq); + + return stop; } static void enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) { - inc_nr_running(rq); + add_nr_running(rq, 1); } static void dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) { - dec_nr_running(rq); + sub_nr_running(rq, 1); } static void yield_task_stop(struct rq *rq) @@ -103,7 +106,7 @@ get_rr_interval_stop(struct rq *rq, struct task_struct *task) * Simple, special scheduling class for the per-CPU stop tasks: */ const struct sched_class stop_sched_class = { - .next = &rt_sched_class, + .next = &dl_sched_class, .enqueue_task = enqueue_task_stop, .dequeue_task = dequeue_task_stop, diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c new file mode 100644 index 00000000000..0ffa20ae657 --- /dev/null +++ b/kernel/sched/wait.c @@ -0,0 +1,504 @@ +/* + * Generic waiting primitives. + * + * (C) 2004 Nadia Yvette Chambers, Oracle + */ +#include <linux/init.h> +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/wait.h> +#include <linux/hash.h> + +void __init_waitqueue_head(wait_queue_head_t *q, const char *name, struct lock_class_key *key) +{ + spin_lock_init(&q->lock); + lockdep_set_class_and_name(&q->lock, key, name); + INIT_LIST_HEAD(&q->task_list); +} + +EXPORT_SYMBOL(__init_waitqueue_head); + +void add_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + wait->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(add_wait_queue); + +void add_wait_queue_exclusive(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + wait->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue_tail(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(add_wait_queue_exclusive); + +void remove_wait_queue(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __remove_wait_queue(q, wait); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(remove_wait_queue); + + +/* + * 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, int nr) +{ + __wake_up_common(q, mode, nr, 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 = 1; /* XXX WF_SYNC */ + + if (unlikely(!q)) + return; + + if (unlikely(nr_exclusive != 1)) + 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 */ + +/* + * Note: we use "set_current_state()" _after_ the wait-queue add, + * because we need a memory barrier there on SMP, so that any + * wake-function that tests for the wait-queue being active + * will be guaranteed to see waitqueue addition _or_ subsequent + * tests in this thread will see the wakeup having taken place. + * + * The spin_unlock() itself is semi-permeable and only protects + * one way (it only protects stuff inside the critical region and + * stops them from bleeding out - it would still allow subsequent + * loads to move into the critical region). + */ +void +prepare_to_wait(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + wait->flags &= ~WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) + __add_wait_queue(q, wait); + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_wait); + +void +prepare_to_wait_exclusive(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + wait->flags |= WQ_FLAG_EXCLUSIVE; + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) + __add_wait_queue_tail(q, wait); + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(prepare_to_wait_exclusive); + +long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) +{ + unsigned long flags; + + if (signal_pending_state(state, current)) + return -ERESTARTSYS; + + wait->private = current; + wait->func = autoremove_wake_function; + + spin_lock_irqsave(&q->lock, flags); + if (list_empty(&wait->task_list)) { + if (wait->flags & WQ_FLAG_EXCLUSIVE) + __add_wait_queue_tail(q, wait); + else + __add_wait_queue(q, wait); + } + set_current_state(state); + spin_unlock_irqrestore(&q->lock, flags); + + return 0; +} +EXPORT_SYMBOL(prepare_to_wait_event); + +/** + * finish_wait - clean up after waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + */ +void finish_wait(wait_queue_head_t *q, wait_queue_t *wait) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + /* + * We can check for list emptiness outside the lock + * IFF: + * - we use the "careful" check that verifies both + * the next and prev pointers, so that there cannot + * be any half-pending updates in progress on other + * CPU's that we haven't seen yet (and that might + * still change the stack area. + * and + * - all other users take the lock (ie we can only + * have _one_ other CPU that looks at or modifies + * the list). + */ + if (!list_empty_careful(&wait->task_list)) { + spin_lock_irqsave(&q->lock, flags); + list_del_init(&wait->task_list); + spin_unlock_irqrestore(&q->lock, flags); + } +} +EXPORT_SYMBOL(finish_wait); + +/** + * abort_exclusive_wait - abort exclusive waiting in a queue + * @q: waitqueue waited on + * @wait: wait descriptor + * @mode: runstate of the waiter to be woken + * @key: key to identify a wait bit queue or %NULL + * + * Sets current thread back to running state and removes + * the wait descriptor from the given waitqueue if still + * queued. + * + * Wakes up the next waiter if the caller is concurrently + * woken up through the queue. + * + * This prevents waiter starvation where an exclusive waiter + * aborts and is woken up concurrently and no one wakes up + * the next waiter. + */ +void abort_exclusive_wait(wait_queue_head_t *q, wait_queue_t *wait, + unsigned int mode, void *key) +{ + unsigned long flags; + + __set_current_state(TASK_RUNNING); + spin_lock_irqsave(&q->lock, flags); + if (!list_empty(&wait->task_list)) + list_del_init(&wait->task_list); + else if (waitqueue_active(q)) + __wake_up_locked_key(q, mode, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(abort_exclusive_wait); + +int autoremove_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *key) +{ + int ret = default_wake_function(wait, mode, sync, key); + + if (ret) + list_del_init(&wait->task_list); + return ret; +} +EXPORT_SYMBOL(autoremove_wake_function); + +int wake_bit_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue *wait_bit + = container_of(wait, struct wait_bit_queue, wait); + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + test_bit(key->bit_nr, key->flags)) + return 0; + else + return autoremove_wake_function(wait, mode, sync, key); +} +EXPORT_SYMBOL(wake_bit_function); + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) + * waiting, the actions of __wait_on_bit() and __wait_on_bit_lock() are + * permitted return codes. Nonzero return codes halt waiting and return. + */ +int __sched +__wait_on_bit(wait_queue_head_t *wq, struct wait_bit_queue *q, + int (*action)(void *), unsigned mode) +{ + int ret = 0; + + do { + prepare_to_wait(wq, &q->wait, mode); + if (test_bit(q->key.bit_nr, q->key.flags)) + ret = (*action)(q->key.flags); + } while (test_bit(q->key.bit_nr, q->key.flags) && !ret); + finish_wait(wq, &q->wait); + return ret; +} +EXPORT_SYMBOL(__wait_on_bit); + +int __sched out_of_line_wait_on_bit(void *word, int bit, + int (*action)(void *), unsigned mode) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + return __wait_on_bit(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit); + +int __sched +__wait_on_bit_lock(wait_queue_head_t *wq, struct wait_bit_queue *q, + int (*action)(void *), unsigned mode) +{ + do { + int ret; + + prepare_to_wait_exclusive(wq, &q->wait, mode); + if (!test_bit(q->key.bit_nr, q->key.flags)) + continue; + ret = action(q->key.flags); + if (!ret) + continue; + abort_exclusive_wait(wq, &q->wait, mode, &q->key); + return ret; + } while (test_and_set_bit(q->key.bit_nr, q->key.flags)); + finish_wait(wq, &q->wait); + return 0; +} +EXPORT_SYMBOL(__wait_on_bit_lock); + +int __sched out_of_line_wait_on_bit_lock(void *word, int bit, + int (*action)(void *), unsigned mode) +{ + wait_queue_head_t *wq = bit_waitqueue(word, bit); + DEFINE_WAIT_BIT(wait, word, bit); + + return __wait_on_bit_lock(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_bit_lock); + +void __wake_up_bit(wait_queue_head_t *wq, void *word, int bit) +{ + struct wait_bit_key key = __WAIT_BIT_KEY_INITIALIZER(word, bit); + if (waitqueue_active(wq)) + __wake_up(wq, TASK_NORMAL, 1, &key); +} +EXPORT_SYMBOL(__wake_up_bit); + +/** + * wake_up_bit - wake up a waiter on a bit + * @word: the word being waited on, a kernel virtual address + * @bit: the bit of the word being waited on + * + * There is a standard hashed waitqueue table for generic use. This + * is the part of the hashtable's accessor API that wakes up waiters + * on a bit. For instance, if one were to have waiters on a bitflag, + * one would call wake_up_bit() after clearing the bit. + * + * In order for this to function properly, as it uses waitqueue_active() + * internally, some kind of memory barrier must be done prior to calling + * this. Typically, this will be smp_mb__after_atomic(), but in some + * cases where bitflags are manipulated non-atomically under a lock, one + * may need to use a less regular barrier, such fs/inode.c's smp_mb(), + * because spin_unlock() does not guarantee a memory barrier. + */ +void wake_up_bit(void *word, int bit) +{ + __wake_up_bit(bit_waitqueue(word, bit), word, bit); +} +EXPORT_SYMBOL(wake_up_bit); + +wait_queue_head_t *bit_waitqueue(void *word, int bit) +{ + const int shift = BITS_PER_LONG == 32 ? 5 : 6; + const struct zone *zone = page_zone(virt_to_page(word)); + unsigned long val = (unsigned long)word << shift | bit; + + return &zone->wait_table[hash_long(val, zone->wait_table_bits)]; +} +EXPORT_SYMBOL(bit_waitqueue); + +/* + * Manipulate the atomic_t address to produce a better bit waitqueue table hash + * index (we're keying off bit -1, but that would produce a horrible hash + * value). + */ +static inline wait_queue_head_t *atomic_t_waitqueue(atomic_t *p) +{ + if (BITS_PER_LONG == 64) { + unsigned long q = (unsigned long)p; + return bit_waitqueue((void *)(q & ~1), q & 1); + } + return bit_waitqueue(p, 0); +} + +static int wake_atomic_t_function(wait_queue_t *wait, unsigned mode, int sync, + void *arg) +{ + struct wait_bit_key *key = arg; + struct wait_bit_queue *wait_bit + = container_of(wait, struct wait_bit_queue, wait); + atomic_t *val = key->flags; + + if (wait_bit->key.flags != key->flags || + wait_bit->key.bit_nr != key->bit_nr || + atomic_read(val) != 0) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + +/* + * To allow interruptible waiting and asynchronous (i.e. nonblocking) waiting, + * the actions of __wait_on_atomic_t() are permitted return codes. Nonzero + * return codes halt waiting and return. + */ +static __sched +int __wait_on_atomic_t(wait_queue_head_t *wq, struct wait_bit_queue *q, + int (*action)(atomic_t *), unsigned mode) +{ + atomic_t *val; + int ret = 0; + + do { + prepare_to_wait(wq, &q->wait, mode); + val = q->key.flags; + if (atomic_read(val) == 0) + break; + ret = (*action)(val); + } while (!ret && atomic_read(val) != 0); + finish_wait(wq, &q->wait); + return ret; +} + +#define DEFINE_WAIT_ATOMIC_T(name, p) \ + struct wait_bit_queue name = { \ + .key = __WAIT_ATOMIC_T_KEY_INITIALIZER(p), \ + .wait = { \ + .private = current, \ + .func = wake_atomic_t_function, \ + .task_list = \ + LIST_HEAD_INIT((name).wait.task_list), \ + }, \ + } + +__sched int out_of_line_wait_on_atomic_t(atomic_t *p, int (*action)(atomic_t *), + unsigned mode) +{ + wait_queue_head_t *wq = atomic_t_waitqueue(p); + DEFINE_WAIT_ATOMIC_T(wait, p); + + return __wait_on_atomic_t(wq, &wait, action, mode); +} +EXPORT_SYMBOL(out_of_line_wait_on_atomic_t); + +/** + * wake_up_atomic_t - Wake up a waiter on a atomic_t + * @p: The atomic_t being waited on, a kernel virtual address + * + * Wake up anyone waiting for the atomic_t to go to zero. + * + * Abuse the bit-waker function and its waitqueue hash table set (the atomic_t + * check is done by the waiter's wake function, not the by the waker itself). + */ +void wake_up_atomic_t(atomic_t *p) +{ + __wake_up_bit(atomic_t_waitqueue(p), p, WAIT_ATOMIC_T_BIT_NR); +} +EXPORT_SYMBOL(wake_up_atomic_t); |