diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/Makefile | 1 | ||||
| -rw-r--r-- | kernel/sched/core.c | 188 | ||||
| -rw-r--r-- | kernel/sched/cpufreq.c | 9 | ||||
| -rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 97 | ||||
| -rw-r--r-- | kernel/sched/cputime.c | 2 | ||||
| -rw-r--r-- | kernel/sched/deadline.c | 31 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 10 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 894 | ||||
| -rw-r--r-- | kernel/sched/isolation.c | 16 | ||||
| -rw-r--r-- | kernel/sched/loadavg.c | 139 | ||||
| -rw-r--r-- | kernel/sched/membarrier.c | 6 | ||||
| -rw-r--r-- | kernel/sched/pelt.c | 45 | ||||
| -rw-r--r-- | kernel/sched/pelt.h | 114 | ||||
| -rw-r--r-- | kernel/sched/psi.c | 785 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 36 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 331 | ||||
| -rw-r--r-- | kernel/sched/stats.h | 86 | ||||
| -rw-r--r-- | kernel/sched/swait.c | 2 | ||||
| -rw-r--r-- | kernel/sched/topology.c | 268 | ||||
| -rw-r--r-- | kernel/sched/wait.c | 2 |
20 files changed, 2428 insertions, 634 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 7fe183404c38..21fb5a5662b5 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_CPU_ISOLATION) += isolation.o +obj-$(CONFIG_PSI) += psi.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2e696b03e99d..ead464a0f2e5 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -24,7 +24,7 @@ DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) /* * Debugging: various feature bits * @@ -107,11 +107,12 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) * [L] ->on_rq * RELEASE (rq->lock) * - * If we observe the old CPU in task_rq_lock, the acquire of + * If we observe the old CPU in task_rq_lock(), the acquire of * the old rq->lock will fully serialize against the stores. * - * If we observe the new CPU in task_rq_lock, the acquire will - * pair with the WMB to ensure we must then also see migrating. + * If we observe the new CPU in task_rq_lock(), the address + * dependency headed by '[L] rq = task_rq()' and the acquire + * will pair with the WMB to ensure we then also see migrating. */ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { rq_pin_lock(rq, rf); @@ -180,6 +181,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) update_irq_load_avg(rq, irq_delta + steal); #endif + update_rq_clock_pelt(rq, delta); } void update_rq_clock(struct rq *rq) @@ -396,7 +398,7 @@ static bool set_nr_if_polling(struct task_struct *p) #endif #endif -void wake_q_add(struct wake_q_head *head, struct task_struct *task) +static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) { struct wake_q_node *node = &task->wake_q; @@ -405,19 +407,60 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task) * its already queued (either by us or someone else) and will get the * wakeup due to that. * - * This cmpxchg() executes a full barrier, which pairs with the full - * barrier executed by the wakeup in wake_up_q(). + * In order to ensure that a pending wakeup will observe our pending + * state, even in the failed case, an explicit smp_mb() must be used. */ - if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) - return; - - get_task_struct(task); + smp_mb__before_atomic(); + if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL))) + return false; /* * The head is context local, there can be no concurrency. */ *head->lastp = node; head->lastp = &node->next; + return true; +} + +/** + * wake_q_add() - queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + */ +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + if (__wake_q_add(head, task)) + get_task_struct(task); +} + +/** + * wake_q_add_safe() - safely queue a wakeup for 'later' waking. + * @head: the wake_q_head to add @task to + * @task: the task to queue for 'later' wakeup + * + * Queue a task for later wakeup, most likely by the wake_up_q() call in the + * same context, _HOWEVER_ this is not guaranteed, the wakeup can come + * instantly. + * + * This function must be used as-if it were wake_up_process(); IOW the task + * must be ready to be woken at this location. + * + * This function is essentially a task-safe equivalent to wake_q_add(). Callers + * that already hold reference to @task can call the 'safe' version and trust + * wake_q to do the right thing depending whether or not the @task is already + * queued for wakeup. + */ +void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task) +{ + if (!__wake_q_add(head, task)) + put_task_struct(task); } void wake_up_q(struct wake_q_head *head) @@ -697,7 +740,7 @@ static void set_load_weight(struct task_struct *p, bool update_load) /* * SCHED_IDLE tasks get minimal weight: */ - if (idle_policy(p->policy)) { + if (task_has_idle_policy(p)) { load->weight = scale_load(WEIGHT_IDLEPRIO); load->inv_weight = WMULT_IDLEPRIO; p->se.runnable_weight = load->weight; @@ -722,8 +765,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & ENQUEUE_RESTORE)) + if (!(flags & ENQUEUE_RESTORE)) { sched_info_queued(rq, p); + psi_enqueue(p, flags & ENQUEUE_WAKEUP); + } p->sched_class->enqueue_task(rq, p, flags); } @@ -733,8 +778,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & DEQUEUE_SAVE)) + if (!(flags & DEQUEUE_SAVE)) { sched_info_dequeued(rq, p); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + } p->sched_class->dequeue_task(rq, p, flags); } @@ -911,7 +958,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, { lockdep_assert_held(&rq->lock); - p->on_rq = TASK_ON_RQ_MIGRATING; + WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING); dequeue_task(rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, new_cpu); rq_unlock(rq, rf); @@ -2037,6 +2084,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } @@ -2172,6 +2220,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) INIT_HLIST_HEAD(&p->preempt_notifiers); #endif +#ifdef CONFIG_COMPACTION + p->capture_control = NULL; +#endif init_numa_balancing(clone_flags, p); } @@ -2413,7 +2464,7 @@ void wake_up_new_task(struct task_struct *p) #endif rq = __task_rq_lock(p, &rf); update_rq_clock(rq); - post_init_entity_util_avg(&p->se); + post_init_entity_util_avg(p); activate_task(rq, p, ENQUEUE_NOCLOCK); p->on_rq = TASK_ON_RQ_QUEUED; @@ -2852,7 +2903,7 @@ unsigned long nr_running(void) * preemption, thus the result might have a time-of-check-to-time-of-use * race. The caller is responsible to use it correctly, for example: * - * - from a non-preemptable section (of course) + * - from a non-preemptible section (of course) * * - from a thread that is bound to a single CPU * @@ -2876,6 +2927,18 @@ unsigned long long nr_context_switches(void) } /* + * Consumers of these two interfaces, like for example the cpuidle menu + * governor, are using nonsensical data. Preferring shallow idle state selection + * for a CPU that has IO-wait which might not even end up running the task when + * it does become runnable. + */ + +unsigned long nr_iowait_cpu(int cpu) +{ + return atomic_read(&cpu_rq(cpu)->nr_iowait); +} + +/* * IO-wait accounting, and how its mostly bollocks (on SMP). * * The idea behind IO-wait account is to account the idle time that we could @@ -2910,31 +2973,11 @@ unsigned long nr_iowait(void) unsigned long i, sum = 0; for_each_possible_cpu(i) - sum += atomic_read(&cpu_rq(i)->nr_iowait); + sum += nr_iowait_cpu(i); return sum; } -/* - * Consumers of these two interfaces, like for example the cpuidle menu - * governor, are using nonsensical data. Preferring shallow idle state selection - * for a CPU that has IO-wait which might not even end up running the task when - * it does become runnable. - */ - -unsigned long nr_iowait_cpu(int cpu) -{ - struct rq *this = cpu_rq(cpu); - return atomic_read(&this->nr_iowait); -} - -void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) -{ - struct rq *rq = this_rq(); - *nr_waiters = atomic_read(&rq->nr_iowait); - *load = rq->load.weight; -} - #ifdef CONFIG_SMP /* @@ -3051,6 +3094,7 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); cpu_load_update_active(rq); calc_global_load_tick(rq); + psi_task_tick(rq); rq_unlock(rq, &rf); @@ -3418,7 +3462,7 @@ static void __sched notrace __schedule(bool preempt) switch_count = &prev->nivcsw; if (!preempt && prev->state) { - if (unlikely(signal_pending_state(prev->state, prev))) { + if (signal_pending_state(prev->state, prev)) { prev->state = TASK_RUNNING; } else { deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK); @@ -4193,7 +4237,7 @@ recheck: * Treat SCHED_IDLE as nice 20. Only allow a switch to * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. */ - if (idle_policy(p->policy) && !idle_policy(policy)) { + if (task_has_idle_policy(p) && !idle_policy(policy)) { if (!can_nice(p, task_nice(p))) return -EPERM; } @@ -4452,7 +4496,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a u32 size; int ret; - if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) + if (!access_ok(uattr, SCHED_ATTR_SIZE_VER0)) return -EFAULT; /* Zero the full structure, so that a short copy will be nice: */ @@ -4652,7 +4696,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, { int ret; - if (!access_ok(VERIFY_WRITE, uattr, usize)) + if (!access_ok(uattr, usize)) return -EFAULT; /* @@ -4933,9 +4977,7 @@ static void do_sched_yield(void) struct rq_flags rf; struct rq *rq; - local_irq_disable(); - rq = this_rq(); - rq_lock(rq, &rf); + rq = this_rq_lock_irq(&rf); schedstat_inc(rq->yld_count); current->sched_class->yield_task(rq); @@ -5256,9 +5298,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, } #ifdef CONFIG_COMPAT_32BIT_TIME -COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, - compat_pid_t, pid, - struct old_timespec32 __user *, interval) +SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid, + struct old_timespec32 __user *, interval) { struct timespec64 t; int retval = sched_rr_get_interval(pid, &t); @@ -5742,15 +5783,10 @@ int sched_cpu_activate(unsigned int cpu) #ifdef CONFIG_SCHED_SMT /* - * The sched_smt_present static key needs to be evaluated on every - * hotplug event because at boot time SMT might be disabled when - * the number of booted CPUs is limited. - * - * If then later a sibling gets hotplugged, then the key would stay - * off and SMT scheduling would never be functional. + * When going up, increment the number of cores with SMT present. */ - if (cpumask_weight(cpu_smt_mask(cpu)) > 1) - static_branch_enable_cpuslocked(&sched_smt_present); + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_inc_cpuslocked(&sched_smt_present); #endif set_cpu_active(cpu, true); @@ -5792,7 +5828,15 @@ int sched_cpu_deactivate(unsigned int cpu) * * Do sync before park smpboot threads to take care the rcu boost case. */ - synchronize_rcu_mult(call_rcu, call_rcu_sched); + synchronize_rcu(); + +#ifdef CONFIG_SCHED_SMT + /* + * When going down, decrement the number of cores with SMT present. + */ + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_dec_cpuslocked(&sched_smt_present); +#endif if (!sched_smp_initialized) return 0; @@ -6069,6 +6113,8 @@ void __init sched_init(void) init_schedstats(); + psi_init(); + scheduler_running = 1; } @@ -6145,6 +6191,34 @@ void ___might_sleep(const char *file, int line, int preempt_offset) add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } EXPORT_SYMBOL(___might_sleep); + +void __cant_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; + + if (irqs_disabled()) + return; + + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return; + + if (preempt_count() > preempt_offset) + return; + + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line); + printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + debug_show_held_locks(current); + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} +EXPORT_SYMBOL_GPL(__cant_sleep); #endif #ifdef CONFIG_MAGIC_SYSRQ diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c index 5e54cbcae673..835671f0f917 100644 --- a/kernel/sched/cpufreq.c +++ b/kernel/sched/cpufreq.c @@ -1,12 +1,9 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Scheduler code and data structures related to cpufreq. * * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #include "sched.h" @@ -51,8 +48,8 @@ EXPORT_SYMBOL_GPL(cpufreq_add_update_util_hook); * * Clear the update_util_data pointer for the given CPU. * - * Callers must use RCU-sched callbacks to free any memory that might be - * accessed via the old update_util_data pointer or invoke synchronize_sched() + * Callers must use RCU callbacks to free any memory that might be + * accessed via the old update_util_data pointer or invoke synchronize_rcu() * right after this function to avoid use-after-free. */ void cpufreq_remove_update_util_hook(int cpu) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3fffad3bc8a8..2efe629425be 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -1,18 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0 /* * CPUFreq governor based on scheduler-provided CPU utilization data. * * Copyright (C) 2016, Intel Corporation * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include "sched.h" +#include <linux/sched/cpufreq.h> #include <trace/events/power.h> struct sugov_tunables { @@ -167,7 +165,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; - freq = (freq + (freq >> 2)) * util / max; + freq = map_util_freq(util, freq, max); if (freq == sg_policy->cached_raw_freq && !sg_policy->need_freq_update) return sg_policy->next_freq; @@ -197,15 +195,13 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, * based on the task model parameters and gives the minimal utilization * required to meet deadlines. */ -static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) +unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type) { - struct rq *rq = cpu_rq(sg_cpu->cpu); - unsigned long util, irq, max; - - sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); - sg_cpu->bw_dl = cpu_bw_dl(rq); + unsigned long dl_util, util, irq; + struct rq *rq = cpu_rq(cpu); - if (rt_rq_is_runnable(&rq->rt)) + if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) return max; /* @@ -223,22 +219,31 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) * utilization (PELT windows are synchronized) we can directly add them * to obtain the CPU's actual utilization. */ - util = cpu_util_cfs(rq); + util = util_cfs; util += cpu_util_rt(rq); + dl_util = cpu_util_dl(rq); + /* - * We do not make cpu_util_dl() a permanent part of this sum because we - * want to use cpu_bw_dl() later on, but we need to check if the - * CFS+RT+DL sum is saturated (ie. no idle time) such that we select - * f_max when there is no idle time. + * For frequency selection we do not make cpu_util_dl() a permanent part + * of this sum because we want to use cpu_bw_dl() later on, but we need + * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such + * that we select f_max when there is no idle time. * * NOTE: numerical errors or stop class might cause us to not quite hit * saturation when we should -- something for later. */ - if ((util + cpu_util_dl(rq)) >= max) + if (util + dl_util >= max) return max; /* + * OTOH, for energy computation we need the estimated running time, so + * include util_dl and ignore dl_bw. + */ + if (type == ENERGY_UTIL) + util += dl_util; + + /* * There is still idle time; further improve the number by using the * irq metric. Because IRQ/steal time is hidden from the task clock we * need to scale the task numbers: @@ -260,7 +265,22 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) * bw_dl as requested freq. However, cpufreq is not yet ready for such * an interface. So, we only do the latter for now. */ - return min(max, util + sg_cpu->bw_dl); + if (type == FREQUENCY_UTIL) + util += cpu_bw_dl(rq); + + return min(max, util); +} + +static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) +{ + struct rq *rq = cpu_rq(sg_cpu->cpu); + unsigned long util = cpu_util_cfs(rq); + unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); + + sg_cpu->max = max; + sg_cpu->bw_dl = cpu_bw_dl(rq); + + return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL); } /** @@ -601,7 +621,7 @@ static struct kobj_type sugov_tunables_ktype = { /********************** cpufreq governor interface *********************/ -static struct cpufreq_governor schedutil_gov; +struct cpufreq_governor schedutil_gov; static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) { @@ -839,7 +859,7 @@ static void sugov_stop(struct cpufreq_policy *policy) for_each_cpu(cpu, policy->cpus) cpufreq_remove_update_util_hook(cpu); - synchronize_sched(); + synchronize_rcu(); if (!policy->fast_switch_enabled) { irq_work_sync(&sg_policy->irq_work); @@ -860,7 +880,7 @@ static void sugov_limits(struct cpufreq_policy *policy) sg_policy->need_freq_update = true; } -static struct cpufreq_governor schedutil_gov = { +struct cpufreq_governor schedutil_gov = { .name = "schedutil", .owner = THIS_MODULE, .dynamic_switching = true, @@ -883,3 +903,36 @@ static int __init sugov_register(void) return cpufreq_register_governor(&schedutil_gov); } fs_initcall(sugov_register); + +#ifdef CONFIG_ENERGY_MODEL +extern bool sched_energy_update; +extern struct mutex sched_energy_mutex; + +static void rebuild_sd_workfn(struct work_struct *work) +{ + mutex_lock(&sched_energy_mutex); + sched_energy_update = true; + rebuild_sched_domains(); + sched_energy_update = false; + mutex_unlock(&sched_energy_mutex); +} +static DECLARE_WORK(rebuild_sd_work, rebuild_sd_workfn); + +/* + * EAS shouldn't be attempted without sugov, so rebuild the sched_domains + * on governor changes to make sure the scheduler knows about it. + */ +void sched_cpufreq_governor_change(struct cpufreq_policy *policy, + struct cpufreq_governor *old_gov) +{ + if (old_gov == &schedutil_gov || policy->governor == &schedutil_gov) { + /* + * When called from the cpufreq_register_driver() path, the + * cpu_hotplug_lock is already held, so use a work item to + * avoid nested locking in rebuild_sched_domains(). + */ + schedule_work(&rebuild_sd_work); + } + +} +#endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 0796f938c4f0..ba4a143bdcf3 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -525,7 +525,7 @@ void account_idle_ticks(unsigned long ticks) /* * Perform (stime * rtime) / total, but avoid multiplication overflow by - * loosing precision when the numbers are big. + * losing precision when the numbers are big. */ static u64 scale_stime(u64 stime, u64 rtime, u64 total) { diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 91e4202b0634..6a73e41a2016 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -727,7 +727,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * 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). + * Documentation/scheduler/sched-deadline.txt for more information). * * This function returns true if: * @@ -1695,6 +1695,14 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p) } #endif +static inline void set_next_task(struct rq *rq, struct task_struct *p) +{ + p->se.exec_start = rq_clock_task(rq); + + /* You can't push away the running task */ + dequeue_pushable_dl_task(rq, p); +} + static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, struct dl_rq *dl_rq) { @@ -1750,10 +1758,8 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) 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); + set_next_task(rq, p); if (hrtick_enabled(rq)) start_hrtick_dl(rq, p); @@ -1761,7 +1767,7 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) deadline_queue_push_tasks(rq); if (rq->curr->sched_class != &dl_sched_class) - update_dl_rq_load_avg(rq_clock_task(rq), rq, 0); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); return p; } @@ -1770,7 +1776,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1787,7 +1793,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued) { update_curr_dl(rq); - update_dl_rq_load_avg(rq_clock_task(rq), rq, 1); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); /* * Even when we have runtime, update_curr_dl() might have resulted in us * not being the leftmost task anymore. In that case NEED_RESCHED will @@ -1808,12 +1814,7 @@ static void task_fork_dl(struct task_struct *p) 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); + set_next_task(rq, rq->curr); } #ifdef CONFIG_SMP @@ -2041,10 +2042,8 @@ static int push_dl_task(struct rq *rq) return 0; retry: - if (unlikely(next_task == rq->curr)) { - WARN_ON(1); + if (WARN_ON(next_task == rq->curr)) return 0; - } /* * If next_task preempts rq->curr, and rq->curr diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 6383aa6a60ca..8039d62ae36e 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -73,7 +73,7 @@ static int sched_feat_show(struct seq_file *m, void *v) return 0; } -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL #define jump_label_key__true STATIC_KEY_INIT_TRUE #define jump_label_key__false STATIC_KEY_INIT_FALSE @@ -99,7 +99,7 @@ static void sched_feat_enable(int i) #else static void sched_feat_disable(int i) { }; static void sched_feat_enable(int i) { }; -#endif /* HAVE_JUMP_LABEL */ +#endif /* CONFIG_JUMP_LABEL */ static int sched_feat_set(char *cmp) { @@ -315,6 +315,7 @@ void register_sched_domain_sysctl(void) { static struct ctl_table *cpu_entries; static struct ctl_table **cpu_idx; + static bool init_done = false; char buf[32]; int i; @@ -344,7 +345,10 @@ void register_sched_domain_sysctl(void) if (!cpumask_available(sd_sysctl_cpus)) { if (!alloc_cpumask_var(&sd_sysctl_cpus, GFP_KERNEL)) return; + } + if (!init_done) { + init_done = true; /* init to possible to not have holes in @cpu_entries */ cpumask_copy(sd_sysctl_cpus, cpu_possible_mask); } @@ -974,7 +978,7 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns, #endif P(policy); P(prio); - if (p->policy == SCHED_DEADLINE) { + if (task_has_dl_policy(p)) { P(dl.runtime); P(dl.deadline); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ee271bb661cc..ea74d43924b2 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -38,7 +38,7 @@ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) */ unsigned int sysctl_sched_latency = 6000000ULL; -unsigned int normalized_sysctl_sched_latency = 6000000ULL; +static unsigned int normalized_sysctl_sched_latency = 6000000ULL; /* * The initial- and re-scaling of tunables is configurable @@ -58,8 +58,8 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_L * * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_min_granularity = 750000ULL; -unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; +unsigned int sysctl_sched_min_granularity = 750000ULL; +static unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; /* * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity @@ -81,8 +81,8 @@ unsigned int sysctl_sched_child_runs_first __read_mostly; * * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_wakeup_granularity = 1000000UL; -unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +static unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; @@ -94,6 +94,14 @@ int __weak arch_asym_cpu_priority(int cpu) { return -cpu; } + +/* + * The margin used when comparing utilization with CPU capacity: + * util * margin < capacity * 1024 + * + * (default: ~20%) + */ +static unsigned int capacity_margin = 1280; #endif #ifdef CONFIG_CFS_BANDWIDTH @@ -110,14 +118,6 @@ int __weak arch_asym_cpu_priority(int cpu) unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; #endif -/* - * The margin used when comparing utilization with CPU capacity: - * util * margin < capacity * 1024 - * - * (default: ~20%) - */ -unsigned int capacity_margin = 1280; - static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; @@ -248,13 +248,6 @@ const struct sched_class fair_sched_class; */ #ifdef CONFIG_FAIR_GROUP_SCHED - -/* cpu runqueue to which this cfs_rq is attached */ -static inline struct rq *rq_of(struct cfs_rq *cfs_rq) -{ - return cfs_rq->rq; -} - static inline struct task_struct *task_of(struct sched_entity *se) { SCHED_WARN_ON(!entity_is_task(se)); @@ -282,76 +275,99 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return grp->my_q; } -static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { - if (!cfs_rq->on_list) { - struct rq *rq = rq_of(cfs_rq); - int cpu = cpu_of(rq); + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); + + if (cfs_rq->on_list) + return rq->tmp_alone_branch == &rq->leaf_cfs_rq_list; + + cfs_rq->on_list = 1; + + /* + * Ensure we either appear before our parent (if already + * enqueued) or force our parent to appear after us when it is + * enqueued. The fact that we always enqueue bottom-up + * reduces this to two cases and a special case for the root + * cfs_rq. Furthermore, it also means that we will always reset + * tmp_alone_branch either when the branch is connected + * to a tree or when we reach the top of the tree + */ + if (cfs_rq->tg->parent && + cfs_rq->tg->parent->cfs_rq[cpu]->on_list) { /* - * Ensure we either appear before our parent (if already - * enqueued) or force our parent to appear after us when it is - * enqueued. The fact that we always enqueue bottom-up - * reduces this to two cases and a special case for the root - * cfs_rq. Furthermore, it also means that we will always reset - * tmp_alone_branch either when the branch is connected - * to a tree or when we reach the beg of the tree + * If parent is already on the list, we add the child + * just before. Thanks to circular linked property of + * the list, this means to put the child at the tail + * of the list that starts by parent. */ - if (cfs_rq->tg->parent && - cfs_rq->tg->parent->cfs_rq[cpu]->on_list) { - /* - * If parent is already on the list, we add the child - * just before. Thanks to circular linked property of - * the list, this means to put the child at the tail - * of the list that starts by parent. - */ - list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, - &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list)); - /* - * The branch is now connected to its tree so we can - * reset tmp_alone_branch to the beginning of the - * list. - */ - rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; - } else if (!cfs_rq->tg->parent) { - /* - * cfs rq without parent should be put - * at the tail of the list. - */ - list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, - &rq->leaf_cfs_rq_list); - /* - * We have reach the beg of a tree so we can reset - * tmp_alone_branch to the beginning of the list. - */ - rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; - } else { - /* - * The parent has not already been added so we want to - * make sure that it will be put after us. - * tmp_alone_branch points to the beg of the branch - * where we will add parent. - */ - list_add_rcu(&cfs_rq->leaf_cfs_rq_list, - rq->tmp_alone_branch); - /* - * update tmp_alone_branch to points to the new beg - * of the branch - */ - rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list; - } + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list)); + /* + * The branch is now connected to its tree so we can + * reset tmp_alone_branch to the beginning of the + * list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + return true; + } - cfs_rq->on_list = 1; + if (!cfs_rq->tg->parent) { + /* + * cfs rq without parent should be put + * at the tail of the list. + */ + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &rq->leaf_cfs_rq_list); + /* + * We have reach the top of a tree so we can reset + * tmp_alone_branch to the beginning of the list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + return true; } + + /* + * The parent has not already been added so we want to + * make sure that it will be put after us. + * tmp_alone_branch points to the begin of the branch + * where we will add parent. + */ + list_add_rcu(&cfs_rq->leaf_cfs_rq_list, rq->tmp_alone_branch); + /* + * update tmp_alone_branch to points to the new begin + * of the branch + */ + rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list; + return false; } static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) { if (cfs_rq->on_list) { + struct rq *rq = rq_of(cfs_rq); + + /* + * With cfs_rq being unthrottled/throttled during an enqueue, + * it can happen the tmp_alone_branch points the a leaf that + * we finally want to del. In this case, tmp_alone_branch moves + * to the prev element but it will point to rq->leaf_cfs_rq_list + * at the end of the enqueue. + */ + if (rq->tmp_alone_branch == &cfs_rq->leaf_cfs_rq_list) + rq->tmp_alone_branch = cfs_rq->leaf_cfs_rq_list.prev; + list_del_rcu(&cfs_rq->leaf_cfs_rq_list); cfs_rq->on_list = 0; } } +static inline void assert_list_leaf_cfs_rq(struct rq *rq) +{ + SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list); +} + /* Iterate thr' all leaf cfs_rq's on a runqueue */ #define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list, \ @@ -411,12 +427,6 @@ static inline struct task_struct *task_of(struct sched_entity *se) return container_of(se, struct task_struct, se); } -static inline struct rq *rq_of(struct cfs_rq *cfs_rq) -{ - return container_of(cfs_rq, struct rq, cfs); -} - - #define for_each_sched_entity(se) \ for (; se; se = NULL) @@ -439,14 +449,19 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return NULL; } -static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { + return true; } static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) { } +static inline void assert_list_leaf_cfs_rq(struct rq *rq) +{ +} + #define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos) @@ -687,9 +702,8 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) return calc_delta_fair(sched_slice(cfs_rq, se), se); } -#ifdef CONFIG_SMP #include "pelt.h" -#include "sched-pelt.h" +#ifdef CONFIG_SMP static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); static unsigned long task_h_load(struct task_struct *p); @@ -703,9 +717,9 @@ void init_entity_runnable_average(struct sched_entity *se) memset(sa, 0, sizeof(*sa)); /* - * Tasks are intialized with full load to be seen as heavy tasks until + * Tasks are initialized with full load to be seen as heavy tasks until * they get a chance to stabilize to their real load level. - * Group entities are intialized with zero load to reflect the fact that + * Group entities are initialized with zero load to reflect the fact that * nothing has been attached to the task group yet. */ if (entity_is_task(se)) @@ -745,8 +759,9 @@ static void attach_entity_cfs_rq(struct sched_entity *se); * Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap) * if util_avg > util_avg_cap. */ -void post_init_entity_util_avg(struct sched_entity *se) +void post_init_entity_util_avg(struct task_struct *p) { + struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); @@ -764,22 +779,19 @@ void post_init_entity_util_avg(struct sched_entity *se) } } - if (entity_is_task(se)) { - struct task_struct *p = task_of(se); - if (p->sched_class != &fair_sched_class) { - /* - * For !fair tasks do: - * - update_cfs_rq_load_avg(now, cfs_rq); - attach_entity_load_avg(cfs_rq, se, 0); - switched_from_fair(rq, p); - * - * such that the next switched_to_fair() has the - * expected state. - */ - se->avg.last_update_time = cfs_rq_clock_task(cfs_rq); - return; - } + if (p->sched_class != &fair_sched_class) { + /* + * For !fair tasks do: + * + update_cfs_rq_load_avg(now, cfs_rq); + attach_entity_load_avg(cfs_rq, se, 0); + switched_from_fair(rq, p); + * + * such that the next switched_to_fair() has the + * expected state. + */ + se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq); + return; } attach_entity_cfs_rq(se); @@ -789,7 +801,7 @@ void post_init_entity_util_avg(struct sched_entity *se) void init_entity_runnable_average(struct sched_entity *se) { } -void post_init_entity_util_avg(struct sched_entity *se) +void post_init_entity_util_avg(struct task_struct *p) { } static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) @@ -1036,7 +1048,7 @@ unsigned int sysctl_numa_balancing_scan_size = 256; unsigned int sysctl_numa_balancing_scan_delay = 1000; struct numa_group { - atomic_t refcount; + refcount_t refcount; spinlock_t lock; /* nr_tasks, tasks */ int nr_tasks; @@ -1105,7 +1117,7 @@ static unsigned int task_scan_start(struct task_struct *p) unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); - period *= atomic_read(&ng->refcount); + period *= refcount_read(&ng->refcount); period *= shared + 1; period /= private + shared + 1; } @@ -1128,7 +1140,7 @@ static unsigned int task_scan_max(struct task_struct *p) unsigned long private = group_faults_priv(ng); unsigned long period = smax; - period *= atomic_read(&ng->refcount); + period *= refcount_read(&ng->refcount); period *= shared + 1; period /= private + shared + 1; @@ -1161,7 +1173,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) /* New address space, reset the preferred nid */ if (!(clone_flags & CLONE_VM)) { - p->numa_preferred_nid = -1; + p->numa_preferred_nid = NUMA_NO_NODE; return; } @@ -1181,13 +1193,13 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) static void account_numa_enqueue(struct rq *rq, struct task_struct *p) { - rq->nr_numa_running += (p->numa_preferred_nid != -1); + rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE); 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_numa_running -= (p->numa_preferred_nid != NUMA_NO_NODE); rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); } @@ -1401,7 +1413,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, * two full passes of the "multi-stage node selection" test that is * executed below. */ - if ((p->numa_preferred_nid == -1 || p->numa_scan_seq <= 4) && + if ((p->numa_preferred_nid == NUMA_NO_NODE || p->numa_scan_seq <= 4) && (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid))) return true; @@ -1849,7 +1861,7 @@ static void numa_migrate_preferred(struct task_struct *p) unsigned long interval = HZ; /* This task has no NUMA fault statistics yet */ - if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults)) + if (unlikely(p->numa_preferred_nid == NUMA_NO_NODE || !p->numa_faults)) return; /* Periodically retry migrating the task to the preferred node */ @@ -2096,7 +2108,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) static void task_numa_placement(struct task_struct *p) { - int seq, nid, max_nid = -1; + int seq, nid, max_nid = NUMA_NO_NODE; unsigned long max_faults = 0; unsigned long fault_types[2] = { 0, 0 }; unsigned long total_faults; @@ -2204,12 +2216,12 @@ static void task_numa_placement(struct task_struct *p) static inline int get_numa_group(struct numa_group *grp) { - return atomic_inc_not_zero(&grp->refcount); + return refcount_inc_not_zero(&grp->refcount); } static inline void put_numa_group(struct numa_group *grp) { - if (atomic_dec_and_test(&grp->refcount)) + if (refcount_dec_and_test(&grp->refcount)) kfree_rcu(grp, rcu); } @@ -2230,7 +2242,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!grp) return; - atomic_set(&grp->refcount, 1); + refcount_set(&grp->refcount, 1); grp->active_nodes = 1; grp->max_faults_cpu = 0; spin_lock_init(&grp->lock); @@ -2400,8 +2412,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) local = 1; /* - * Retry task to preferred node migration periodically, in case it - * case it previously failed, or the scheduler moved us. + * Retry to migrate task to preferred node periodically, in case it + * previously failed, or the scheduler moved us. */ if (time_after(jiffies, p->numa_migrate_retry)) { task_numa_placement(p); @@ -2639,7 +2651,8 @@ static void update_scan_period(struct task_struct *p, int new_cpu) * the preferred node. */ if (dst_nid == p->numa_preferred_nid || - (p->numa_preferred_nid != -1 && src_nid != p->numa_preferred_nid)) + (p->numa_preferred_nid != NUMA_NO_NODE && + src_nid != p->numa_preferred_nid)) return; } @@ -2734,6 +2747,17 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) WRITE_ONCE(*ptr, res); \ } while (0) +/* + * Remove and clamp on negative, from a local variable. + * + * A variant of sub_positive(), which does not use explicit load-store + * and is thus optimized for local variable updates. + */ +#define lsub_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + *ptr -= min_t(typeof(*ptr), *ptr, _val); \ +} while (0) + #ifdef CONFIG_SMP static inline void enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -3112,7 +3136,7 @@ void set_task_rq_fair(struct sched_entity *se, p_last_update_time = prev->avg.last_update_time; n_last_update_time = next->avg.last_update_time; #endif - __update_load_avg_blocked_se(p_last_update_time, cpu_of(rq_of(prev)), se); + __update_load_avg_blocked_se(p_last_update_time, se); se->avg.last_update_time = n_last_update_time; } @@ -3247,11 +3271,11 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf /* * runnable_sum can't be lower than running_sum - * As running sum is scale with CPU capacity wehreas the runnable sum - * is not we rescale running_sum 1st + * Rescale running sum to be in the same range as runnable sum + * running_sum is in [0 : LOAD_AVG_MAX << SCHED_CAPACITY_SHIFT] + * runnable_sum is in [0 : LOAD_AVG_MAX] */ - running_sum = se->avg.util_sum / - arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; runnable_sum = max(runnable_sum, running_sum); load_sum = (s64)se_weight(se) * runnable_sum; @@ -3354,7 +3378,7 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum /** * update_cfs_rq_load_avg - update the cfs_rq's load/util averages - * @now: current time, as per cfs_rq_clock_task() + * @now: current time, as per cfs_rq_clock_pelt() * @cfs_rq: cfs_rq to update * * The cfs_rq avg is the direct sum of all its entities (blocked and runnable) @@ -3399,7 +3423,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) decayed = 1; } - decayed |= __update_load_avg_cfs_rq(now, cpu_of(rq_of(cfs_rq)), cfs_rq); + decayed |= __update_load_avg_cfs_rq(now, cfs_rq); #ifndef CONFIG_64BIT smp_wmb(); @@ -3489,9 +3513,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s /* Update task and its cfs_rq load average */ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { - u64 now = cfs_rq_clock_task(cfs_rq); - struct rq *rq = rq_of(cfs_rq); - int cpu = cpu_of(rq); + u64 now = cfs_rq_clock_pelt(cfs_rq); int decayed; /* @@ -3499,7 +3521,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s * track group sched_entity load average for task_h_load calc in migration */ if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) - __update_load_avg_se(now, cpu, cfs_rq, se); + __update_load_avg_se(now, cfs_rq, se); decayed = update_cfs_rq_load_avg(now, cfs_rq); decayed |= propagate_entity_load_avg(se); @@ -3551,7 +3573,7 @@ void sync_entity_load_avg(struct sched_entity *se) u64 last_update_time; last_update_time = cfs_rq_last_update_time(cfs_rq); - __update_load_avg_blocked_se(last_update_time, cpu_of(rq_of(cfs_rq)), se); + __update_load_avg_blocked_se(last_update_time, se); } /* @@ -3567,10 +3589,6 @@ void remove_entity_load_avg(struct sched_entity *se) * tasks cannot exit without having gone through wake_up_new_task() -> * post_init_entity_util_avg() which will have added things to the * cfs_rq, so we can remove unconditionally. - * - * Similarly for groups, they will have passed through - * post_init_entity_util_avg() before unregister_sched_fair_group() - * calls this. */ sync_entity_load_avg(se); @@ -3604,7 +3622,7 @@ static inline unsigned long _task_util_est(struct task_struct *p) { struct util_est ue = READ_ONCE(p->se.avg.util_est); - return max(ue.ewma, ue.enqueued); + return (max(ue.ewma, ue.enqueued) | UTIL_AVG_UNCHANGED); } static inline unsigned long task_util_est(struct task_struct *p) @@ -3622,7 +3640,7 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq, /* Update root cfs_rq's estimated utilization */ enqueued = cfs_rq->avg.util_est.enqueued; - enqueued += (_task_util_est(p) | UTIL_AVG_UNCHANGED); + enqueued += _task_util_est(p); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued); } @@ -3644,14 +3662,14 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) { long last_ewma_diff; struct util_est ue; + int cpu; if (!sched_feat(UTIL_EST)) return; /* Update root cfs_rq's estimated utilization */ ue.enqueued = cfs_rq->avg.util_est.enqueued; - ue.enqueued -= min_t(unsigned int, ue.enqueued, - (_task_util_est(p) | UTIL_AVG_UNCHANGED)); + ue.enqueued -= min_t(unsigned int, ue.enqueued, _task_util_est(p)); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued); /* @@ -3679,6 +3697,14 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) return; /* + * To avoid overestimation of actual task utilization, skip updates if + * we cannot grant there is idle time in this CPU. + */ + cpu = cpu_of(rq_of(cfs_rq)); + if (task_util(p) > capacity_orig_of(cpu)) + return; + + /* * Update Task's estimated utilization * * When *p completes an activation we can consolidate another sample @@ -3966,8 +3992,8 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* * When dequeuing a sched_entity, we must: * - Update loads to have both entity and cfs_rq synced with now. - * - Substract its load from the cfs_rq->runnable_avg. - * - Substract its previous weight from cfs_rq->load.weight. + * - Subtract its load from the cfs_rq->runnable_avg. + * - Subtract its previous weight from cfs_rq->load.weight. * - For group entity, update its weight to reflect the new share * of its group cfs_rq. */ @@ -4208,7 +4234,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) #ifdef CONFIG_CFS_BANDWIDTH -#ifdef HAVE_JUMP_LABEL +#ifdef CONFIG_JUMP_LABEL static struct static_key __cfs_bandwidth_used; static inline bool cfs_bandwidth_used(void) @@ -4225,7 +4251,7 @@ void cfs_bandwidth_usage_dec(void) { static_key_slow_dec_cpuslocked(&__cfs_bandwidth_used); } -#else /* HAVE_JUMP_LABEL */ +#else /* CONFIG_JUMP_LABEL */ static bool cfs_bandwidth_used(void) { return true; @@ -4233,7 +4259,7 @@ static bool cfs_bandwidth_used(void) void cfs_bandwidth_usage_inc(void) {} void cfs_bandwidth_usage_dec(void) {} -#endif /* HAVE_JUMP_LABEL */ +#endif /* CONFIG_JUMP_LABEL */ /* * default period for cfs group bandwidth. @@ -4420,6 +4446,10 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) /* adjust cfs_rq_clock_task() */ cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - cfs_rq->throttled_clock_task; + + /* Add cfs_rq with already running entity in the list */ + if (cfs_rq->nr_running >= 1) + list_add_leaf_cfs_rq(cfs_rq); } return 0; @@ -4431,8 +4461,10 @@ static int tg_throttle_down(struct task_group *tg, void *data) struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; /* group is entering throttled state, stop time */ - if (!cfs_rq->throttle_count) + if (!cfs_rq->throttle_count) { cfs_rq->throttled_clock_task = rq_clock_task(rq); + list_del_leaf_cfs_rq(cfs_rq); + } cfs_rq->throttle_count++; return 0; @@ -4535,6 +4567,8 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) break; } + assert_list_leaf_cfs_rq(rq); + if (!se) add_nr_running(rq, task_delta); @@ -4556,7 +4590,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, struct rq *rq = rq_of(cfs_rq); struct rq_flags rf; - rq_lock(rq, &rf); + rq_lock_irqsave(rq, &rf); if (!cfs_rq_throttled(cfs_rq)) goto next; @@ -4573,7 +4607,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, unthrottle_cfs_rq(cfs_rq); next: - rq_unlock(rq, &rf); + rq_unlock_irqrestore(rq, &rf); if (!remaining) break; @@ -4589,7 +4623,7 @@ next: * period the timer is deactivated until scheduling resumes; cfs_b->idle is * used to track this state. */ -static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) { u64 runtime, runtime_expires; int throttled; @@ -4631,16 +4665,16 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) { runtime = cfs_b->runtime; cfs_b->distribute_running = 1; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ runtime = distribute_cfs_runtime(cfs_b, runtime, runtime_expires); - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->distribute_running = 0; throttled = !list_empty(&cfs_b->throttled_cfs_rq); - cfs_b->runtime -= min(runtime, cfs_b->runtime); + lsub_positive(&cfs_b->runtime, runtime); } /* @@ -4744,17 +4778,18 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) { u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); + unsigned long flags; u64 expires; /* confirm we're still not at a refresh boundary */ - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); if (cfs_b->distribute_running) { - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return; } if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return; } @@ -4765,18 +4800,18 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (runtime) cfs_b->distribute_running = 1; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); if (!runtime) return; runtime = distribute_cfs_runtime(cfs_b, runtime, expires); - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); if (expires == cfs_b->runtime_expires) - cfs_b->runtime -= min(runtime, cfs_b->runtime); + lsub_positive(&cfs_b->runtime, runtime); cfs_b->distribute_running = 0; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); } /* @@ -4854,20 +4889,21 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = container_of(timer, struct cfs_bandwidth, period_timer); + unsigned long flags; int overrun; int idle = 0; - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { overrun = hrtimer_forward_now(timer, cfs_b->period); if (!overrun) break; - idle = do_sched_cfs_period_timer(cfs_b, overrun); + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) cfs_b->period_active = 0; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; } @@ -4977,6 +5013,12 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) } #else /* CONFIG_CFS_BANDWIDTH */ + +static inline bool cfs_bandwidth_used(void) +{ + return false; +} + static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) { return rq_clock_task(rq_of(cfs_rq)); @@ -5072,6 +5114,24 @@ static inline void hrtick_update(struct rq *rq) } #endif +#ifdef CONFIG_SMP +static inline unsigned long cpu_util(int cpu); +static unsigned long capacity_of(int cpu); + +static inline bool cpu_overutilized(int cpu) +{ + return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin); +} + +static inline void update_overutilized_status(struct rq *rq) +{ + if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) + WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); +} +#else +static inline void update_overutilized_status(struct rq *rq) { } +#endif + /* * The enqueue_task method is called before nr_running is * increased. Here we update the fair scheduling stats and @@ -5129,8 +5189,43 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) update_cfs_group(se); } - if (!se) + if (!se) { add_nr_running(rq, 1); + /* + * Since new tasks are assigned an initial util_avg equal to + * half of the spare capacity of their CPU, tiny tasks have the + * ability to cross the overutilized threshold, which will + * result in the load balancer ruining all the task placement + * done by EAS. As a way to mitigate that effect, do not account + * for the first enqueue operation of new tasks during the + * overutilized flag detection. + * + * A better way of solving this problem would be to wait for + * the PELT signals of tasks to converge before taking them + * into account, but that is not straightforward to implement, + * and the following generally works well enough in practice. + */ + if (flags & ENQUEUE_WAKEUP) + update_overutilized_status(rq); + + } + + if (cfs_bandwidth_used()) { + /* + * When bandwidth control is enabled; the cfs_rq_throttled() + * breaks in the above iteration can result in incomplete + * leaf list maintenance, resulting in triggering the assertion + * below. + */ + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + + if (list_add_leaf_cfs_rq(cfs_rq)) + break; + } + } + + assert_list_leaf_cfs_rq(rq); hrtick_update(rq); } @@ -5511,11 +5606,6 @@ static unsigned long capacity_of(int cpu) return cpu_rq(cpu)->cpu_capacity; } -static unsigned long capacity_orig_of(int cpu) -{ - return cpu_rq(cpu)->cpu_capacity_orig; -} - static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -5674,11 +5764,11 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, return target; } -static unsigned long cpu_util_wake(int cpu, struct task_struct *p); +static unsigned long cpu_util_without(int cpu, struct task_struct *p); -static unsigned long capacity_spare_wake(int cpu, struct task_struct *p) +static unsigned long capacity_spare_without(int cpu, struct task_struct *p) { - return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0); + return max_t(long, capacity_of(cpu) - cpu_util_without(cpu, p), 0); } /* @@ -5738,7 +5828,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); - spare_cap = capacity_spare_wake(i, p); + spare_cap = capacity_spare_without(i, p); if (spare_cap > max_spare_cap) max_spare_cap = spare_cap; @@ -5889,8 +5979,8 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p return prev_cpu; /* - * We need task's util for capacity_spare_wake, sync it up to prev_cpu's - * last_update_time. + * We need task's util for capacity_spare_without, sync it up to + * prev_cpu's last_update_time. */ if (!(sd_flag & SD_BALANCE_FORK)) sync_entity_load_avg(&p->se); @@ -5935,6 +6025,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p #ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); +EXPORT_SYMBOL_GPL(sched_smt_present); static inline void set_idle_cores(int cpu, int val) { @@ -6007,7 +6098,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int bool idle = true; for_each_cpu(cpu, cpu_smt_mask(core)) { - cpumask_clear_cpu(cpu, cpus); + __cpumask_clear_cpu(cpu, cpus); if (!available_idle_cpu(cpu)) idle = false; } @@ -6027,7 +6118,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int /* * Scan the local SMT mask for idle CPUs. */ -static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) +static int select_idle_smt(struct task_struct *p, int target) { int cpu; @@ -6051,7 +6142,7 @@ static inline int select_idle_core(struct task_struct *p, struct sched_domain *s return -1; } -static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) +static inline int select_idle_smt(struct task_struct *p, int target) { return -1; } @@ -6156,7 +6247,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) if ((unsigned)i < nr_cpumask_bits) return i; - i = select_idle_smt(p, sd, target); + i = select_idle_smt(p, target); if ((unsigned)i < nr_cpumask_bits) return i; @@ -6216,10 +6307,19 @@ static inline unsigned long cpu_util(int cpu) } /* - * cpu_util_wake: Compute CPU utilization with any contributions from - * the waking task p removed. + * cpu_util_without: compute cpu utilization without any contributions from *p + * @cpu: the CPU which utilization is requested + * @p: the task which utilization should be discounted + * + * The utilization of a CPU is defined by the utilization of tasks currently + * enqueued on that CPU as well as tasks which are currently sleeping after an + * execution on that CPU. + * + * This method returns the utilization of the specified CPU by discounting the + * utilization of the specified task, whenever the task is currently + * contributing to the CPU utilization. */ -static unsigned long cpu_util_wake(int cpu, struct task_struct *p) +static unsigned long cpu_util_without(int cpu, struct task_struct *p) { struct cfs_rq *cfs_rq; unsigned int util; @@ -6231,8 +6331,8 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) cfs_rq = &cpu_rq(cpu)->cfs; util = READ_ONCE(cfs_rq->avg.util_avg); - /* Discount task's blocked util from CPU's util */ - util -= min_t(unsigned int, util, task_util(p)); + /* Discount task's util from CPU's util */ + lsub_positive(&util, task_util(p)); /* * Covered cases: @@ -6240,14 +6340,14 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) * a) if *p is the only task sleeping on this CPU, then: * cpu_util (== task_util) > util_est (== 0) * and thus we return: - * cpu_util_wake = (cpu_util - task_util) = 0 + * cpu_util_without = (cpu_util - task_util) = 0 * * b) if other tasks are SLEEPING on this CPU, which is now exiting * IDLE, then: * cpu_util >= task_util * cpu_util > util_est (== 0) * and thus we discount *p's blocked utilization to return: - * cpu_util_wake = (cpu_util - task_util) >= 0 + * cpu_util_without = (cpu_util - task_util) >= 0 * * c) if other tasks are RUNNABLE on that CPU and * util_est > cpu_util @@ -6260,8 +6360,32 @@ static unsigned long cpu_util_wake(int cpu, struct task_struct *p) * covered by the following code when estimated utilization is * enabled. */ - if (sched_feat(UTIL_EST)) - util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued)); + if (sched_feat(UTIL_EST)) { + unsigned int estimated = + READ_ONCE(cfs_rq->avg.util_est.enqueued); + + /* + * Despite the following checks we still have a small window + * for a possible race, when an execl's select_task_rq_fair() + * races with LB's detach_task(): + * + * detach_task() + * p->on_rq = TASK_ON_RQ_MIGRATING; + * ---------------------------------- A + * deactivate_task() \ + * dequeue_task() + RaceTime + * util_est_dequeue() / + * ---------------------------------- B + * + * The additional check on "current == p" it's required to + * properly fix the execl regression and it helps in further + * reducing the chances for the above race. + */ + if (unlikely(task_on_rq_queued(p) || current == p)) + lsub_positive(&estimated, _task_util_est(p)); + + util = max(util, estimated); + } /* * Utilization (estimated) can exceed the CPU capacity, thus let's @@ -6299,6 +6423,213 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) } /* + * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued) + * to @dst_cpu. + */ +static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) +{ + struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; + unsigned long util_est, util = READ_ONCE(cfs_rq->avg.util_avg); + + /* + * If @p migrates from @cpu to another, remove its contribution. Or, + * if @p migrates from another CPU to @cpu, add its contribution. In + * the other cases, @cpu is not impacted by the migration, so the + * util_avg should already be correct. + */ + if (task_cpu(p) == cpu && dst_cpu != cpu) + sub_positive(&util, task_util(p)); + else if (task_cpu(p) != cpu && dst_cpu == cpu) + util += task_util(p); + + if (sched_feat(UTIL_EST)) { + util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued); + + /* + * During wake-up, the task isn't enqueued yet and doesn't + * appear in the cfs_rq->avg.util_est.enqueued of any rq, + * so just add it (if needed) to "simulate" what will be + * cpu_util() after the task has been enqueued. + */ + if (dst_cpu == cpu) + util_est += _task_util_est(p); + + util = max(util, util_est); + } + + return min(util, capacity_orig_of(cpu)); +} + +/* + * compute_energy(): Estimates the energy that would be consumed if @p was + * migrated to @dst_cpu. compute_energy() predicts what will be the utilization + * landscape of the * CPUs after the task migration, and uses the Energy Model + * to compute what would be the energy if we decided to actually migrate that + * task. + */ +static long +compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) +{ + long util, max_util, sum_util, energy = 0; + int cpu; + + for (; pd; pd = pd->next) { + max_util = sum_util = 0; + /* + * The capacity state of CPUs of the current rd can be driven by + * CPUs of another rd if they belong to the same performance + * domain. So, account for the utilization of these CPUs too + * by masking pd with cpu_online_mask instead of the rd span. + * + * If an entire performance domain is outside of the current rd, + * it will not appear in its pd list and will not be accounted + * by compute_energy(). + */ + for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) { + util = cpu_util_next(cpu, p, dst_cpu); + util = schedutil_energy_util(cpu, util); + max_util = max(util, max_util); + sum_util += util; + } + + energy += em_pd_energy(pd->em_pd, max_util, sum_util); + } + + return energy; +} + +/* + * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the + * waking task. find_energy_efficient_cpu() looks for the CPU with maximum + * spare capacity in each performance domain and uses it as a potential + * candidate to execute the task. Then, it uses the Energy Model to figure + * out which of the CPU candidates is the most energy-efficient. + * + * The rationale for this heuristic is as follows. In a performance domain, + * all the most energy efficient CPU candidates (according to the Energy + * Model) are those for which we'll request a low frequency. When there are + * several CPUs for which the frequency request will be the same, we don't + * have enough data to break the tie between them, because the Energy Model + * only includes active power costs. With this model, if we assume that + * frequency requests follow utilization (e.g. using schedutil), the CPU with + * the maximum spare capacity in a performance domain is guaranteed to be among + * the best candidates of the performance domain. + * + * In practice, it could be preferable from an energy standpoint to pack + * small tasks on a CPU in order to let other CPUs go in deeper idle states, + * but that could also hurt our chances to go cluster idle, and we have no + * ways to tell with the current Energy Model if this is actually a good + * idea or not. So, find_energy_efficient_cpu() basically favors + * cluster-packing, and spreading inside a cluster. That should at least be + * a good thing for latency, and this is consistent with the idea that most + * of the energy savings of EAS come from the asymmetry of the system, and + * not so much from breaking the tie between identical CPUs. That's also the + * reason why EAS is enabled in the topology code only for systems where + * SD_ASYM_CPUCAPACITY is set. + * + * NOTE: Forkees are not accepted in the energy-aware wake-up path because + * they don't have any useful utilization data yet and it's not possible to + * forecast their impact on energy consumption. Consequently, they will be + * placed by find_idlest_cpu() on the least loaded CPU, which might turn out + * to be energy-inefficient in some use-cases. The alternative would be to + * bias new tasks towards specific types of CPUs first, or to try to infer + * their util_avg from the parent task, but those heuristics could hurt + * other use-cases too. So, until someone finds a better way to solve this, + * let's keep things simple by re-using the existing slow path. + */ + +static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) +{ + unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX; + struct root_domain *rd = cpu_rq(smp_processor_id())->rd; + int cpu, best_energy_cpu = prev_cpu; + struct perf_domain *head, *pd; + unsigned long cpu_cap, util; + struct sched_domain *sd; + + rcu_read_lock(); + pd = rcu_dereference(rd->pd); + if (!pd || READ_ONCE(rd->overutilized)) + goto fail; + head = pd; + + /* + * Energy-aware wake-up happens on the lowest sched_domain starting + * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu. + */ + sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity)); + while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) + sd = sd->parent; + if (!sd) + goto fail; + + sync_entity_load_avg(&p->se); + if (!task_util_est(p)) + goto unlock; + + for (; pd; pd = pd->next) { + unsigned long cur_energy, spare_cap, max_spare_cap = 0; + int max_spare_cap_cpu = -1; + + for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { + if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + continue; + + /* Skip CPUs that will be overutilized. */ + util = cpu_util_next(cpu, p, cpu); + cpu_cap = capacity_of(cpu); + if (cpu_cap * 1024 < util * capacity_margin) + continue; + + /* Always use prev_cpu as a candidate. */ + if (cpu == prev_cpu) { + prev_energy = compute_energy(p, prev_cpu, head); + best_energy = min(best_energy, prev_energy); + continue; + } + + /* + * Find the CPU with the maximum spare capacity in + * the performance domain + */ + spare_cap = cpu_cap - util; + if (spare_cap > max_spare_cap) { + max_spare_cap = spare_cap; + max_spare_cap_cpu = cpu; + } + } + + /* Evaluate the energy impact of using this CPU. */ + if (max_spare_cap_cpu >= 0) { + cur_energy = compute_energy(p, max_spare_cap_cpu, head); + if (cur_energy < best_energy) { + best_energy = cur_energy; + best_energy_cpu = max_spare_cap_cpu; + } + } + } +unlock: + rcu_read_unlock(); + + /* + * Pick the best CPU if prev_cpu cannot be used, or if it saves at + * least 6% of the energy used by prev_cpu. + */ + if (prev_energy == ULONG_MAX) + return best_energy_cpu; + + if ((prev_energy - best_energy) > (prev_energy >> 4)) + return best_energy_cpu; + + return prev_cpu; + +fail: + rcu_read_unlock(); + + return -1; +} + +/* * 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. @@ -6321,8 +6652,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (sd_flag & SD_BALANCE_WAKE) { record_wakee(p); - want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) - && cpumask_test_cpu(cpu, &p->cpus_allowed); + + if (sched_energy_enabled()) { + new_cpu = find_energy_efficient_cpu(p, prev_cpu); + if (new_cpu >= 0) + return new_cpu; + new_cpu = prev_cpu; + } + + want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) && + cpumask_test_cpu(cpu, &p->cpus_allowed); } rcu_read_lock(); @@ -6486,7 +6825,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) static void set_last_buddy(struct sched_entity *se) { - if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se)))) return; for_each_sched_entity(se) { @@ -6498,7 +6837,7 @@ static void set_last_buddy(struct sched_entity *se) static void set_next_buddy(struct sched_entity *se) { - if (entity_is_task(se) && unlikely(task_of(se)->policy == SCHED_IDLE)) + if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se)))) return; for_each_sched_entity(se) { @@ -6556,8 +6895,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; /* Idle tasks are by definition preempted by non-idle tasks. */ - if (unlikely(curr->policy == SCHED_IDLE) && - likely(p->policy != SCHED_IDLE)) + if (unlikely(task_has_idle_policy(curr)) && + likely(!task_has_idle_policy(p))) goto preempt; /* @@ -6733,6 +7072,12 @@ idle: if (new_tasks > 0) goto again; + /* + * rq is about to be idle, check if we need to update the + * lost_idle_time of clock_pelt + */ + update_idle_rq_clock_pelt(rq); + return NULL; } @@ -6978,7 +7323,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env) if (p->sched_class != &fair_sched_class) return 0; - if (unlikely(p->policy == SCHED_IDLE)) + if (unlikely(task_has_idle_policy(p))) return 0; /* @@ -7388,11 +7733,7 @@ static void update_blocked_averages(int cpu) for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) { struct sched_entity *se; - /* throttled entities do not contribute to load */ - if (throttled_hierarchy(cfs_rq)) - continue; - - if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq)) + if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) update_tg_load_avg(cfs_rq, 0); /* Propagate pending load changes to the parent, if any: */ @@ -7413,8 +7754,8 @@ static void update_blocked_averages(int cpu) } curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); /* Don't need periodic decay once load/util_avg are null */ if (others_have_blocked(rq)) @@ -7484,11 +7825,11 @@ static inline void update_blocked_averages(int cpu) rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq); + update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); curr_class = rq->curr->sched_class; - update_rt_rq_load_avg(rq_clock_task(rq), rq, curr_class == &rt_sched_class); - update_dl_rq_load_avg(rq_clock_task(rq), rq, curr_class == &dl_sched_class); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); #ifdef CONFIG_NO_HZ_COMMON rq->last_blocked_load_update_tick = jiffies; @@ -7862,16 +8203,16 @@ static bool update_nohz_stats(struct rq *rq, bool force) * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. * @group: sched_group whose statistics are to be updated. - * @load_idx: Load index of sched_domain of this_cpu for load calc. - * @local_group: Does group contain this_cpu. * @sgs: variable to hold the statistics for this group. - * @overload: Indicate pullable load (e.g. >1 runnable task). + * @sg_status: Holds flag indicating the status of the sched_group */ 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, - bool *overload) + struct sched_group *group, + struct sg_lb_stats *sgs, + int *sg_status) { + int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group)); + int load_idx = get_sd_load_idx(env->sd, env->idle); unsigned long load; int i, nr_running; @@ -7895,7 +8236,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, nr_running = rq->nr_running; if (nr_running > 1) - *overload = true; + *sg_status |= SG_OVERLOAD; + + if (cpu_overutilized(i)) + *sg_status |= SG_OVERUTILIZED; #ifdef CONFIG_NUMA_BALANCING sgs->nr_numa_running += rq->nr_numa_running; @@ -7911,7 +8255,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, if (env->sd->flags & SD_ASYM_CPUCAPACITY && sgs->group_misfit_task_load < rq->misfit_task_load) { sgs->group_misfit_task_load = rq->misfit_task_load; - *overload = 1; + *sg_status |= SG_OVERLOAD; } } @@ -8056,17 +8400,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; struct sg_lb_stats tmp_sgs; - int load_idx; - bool overload = false; bool prefer_sibling = child && child->flags & SD_PREFER_SIBLING; + int sg_status = 0; #ifdef CONFIG_NO_HZ_COMMON if (env->idle == CPU_NEWLY_IDLE && READ_ONCE(nohz.has_blocked)) env->flags |= LBF_NOHZ_STATS; #endif - load_idx = get_sd_load_idx(env->sd, env->idle); - do { struct sg_lb_stats *sgs = &tmp_sgs; int local_group; @@ -8081,8 +8422,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_group_capacity(env->sd, env->dst_cpu); } - update_sg_lb_stats(env, sg, load_idx, local_group, sgs, - &overload); + update_sg_lb_stats(env, sg, sgs, &sg_status); if (local_group) goto next_group; @@ -8131,9 +8471,15 @@ next_group: env->fbq_type = fbq_classify_group(&sds->busiest_stat); if (!env->sd->parent) { + struct root_domain *rd = env->dst_rq->rd; + /* update overload indicator if we are at root domain */ - if (READ_ONCE(env->dst_rq->rd->overload) != overload) - WRITE_ONCE(env->dst_rq->rd->overload, overload); + WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD); + + /* Update over-utilization (tipping point, U >= 0) indicator */ + WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); + } else if (sg_status & SG_OVERUTILIZED) { + WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED); } } @@ -8177,9 +8523,7 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) if (sched_asym_prefer(busiest_cpu, env->dst_cpu)) return 0; - env->imbalance = DIV_ROUND_CLOSEST( - sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity, - SCHED_CAPACITY_SCALE); + env->imbalance = sds->busiest_stat.group_load; return 1; } @@ -8360,6 +8704,14 @@ static struct sched_group *find_busiest_group(struct lb_env *env) * this level. */ update_sd_lb_stats(env, &sds); + + if (sched_energy_enabled()) { + struct root_domain *rd = env->dst_rq->rd; + + if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) + goto out_balanced; + } + local = &sds.local_stat; busiest = &sds.busiest_stat; @@ -8544,21 +8896,25 @@ static struct rq *find_busiest_queue(struct lb_env *env, */ #define MAX_PINNED_INTERVAL 512 -static int need_active_balance(struct lb_env *env) +static inline bool +asym_active_balance(struct lb_env *env) { - struct sched_domain *sd = env->sd; + /* + * ASYM_PACKING needs to force migrate tasks from busy but + * lower priority CPUs in order to pack all tasks in the + * highest priority CPUs. + */ + return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) && + sched_asym_prefer(env->dst_cpu, env->src_cpu); +} - if (env->idle == CPU_NEWLY_IDLE) { +static inline bool +voluntary_active_balance(struct lb_env *env) +{ + struct sched_domain *sd = env->sd; - /* - * ASYM_PACKING needs to force migrate tasks from busy but - * lower priority CPUs in order to pack all tasks in the - * highest priority CPUs. - */ - if ((sd->flags & SD_ASYM_PACKING) && - sched_asym_prefer(env->dst_cpu, env->src_cpu)) - return 1; - } + if (asym_active_balance(env)) + return 1; /* * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task. @@ -8576,6 +8932,16 @@ static int need_active_balance(struct lb_env *env) if (env->src_grp_type == group_misfit_task) return 1; + return 0; +} + +static int need_active_balance(struct lb_env *env) +{ + struct sched_domain *sd = env->sd; + + if (voluntary_active_balance(env)) + return 1; + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); } @@ -8740,7 +9106,7 @@ more_balance: 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); + __cpumask_clear_cpu(env.dst_cpu, env.cpus); env.dst_rq = cpu_rq(env.new_dst_cpu); env.dst_cpu = env.new_dst_cpu; @@ -8767,7 +9133,7 @@ more_balance: /* All tasks on this runqueue were pinned by CPU affinity */ if (unlikely(env.flags & LBF_ALL_PINNED)) { - cpumask_clear_cpu(cpu_of(busiest), cpus); + __cpumask_clear_cpu(cpu_of(busiest), cpus); /* * Attempting to continue load balancing at the current * sched_domain level only makes sense if there are @@ -8837,7 +9203,7 @@ more_balance: } else sd->nr_balance_failed = 0; - if (likely(!active_balance)) { + if (likely(!active_balance) || voluntary_active_balance(&env)) { /* We were unbalanced, so reset the balancing interval */ sd->balance_interval = sd->min_interval; } else { @@ -8876,13 +9242,22 @@ out_all_pinned: sd->nr_balance_failed = 0; out_one_pinned: + ld_moved = 0; + + /* + * idle_balance() disregards balance intervals, so we could repeatedly + * reach this code, which would lead to balance_interval skyrocketting + * in a short amount of time. Skip the balance_interval increase logic + * to avoid that. + */ + if (env.idle == CPU_NEWLY_IDLE) + goto out; + /* tune up the balancing interval */ - if (((env.flags & LBF_ALL_PINNED) && - sd->balance_interval < MAX_PINNED_INTERVAL) || - (sd->balance_interval < sd->max_interval)) + if ((env.flags & LBF_ALL_PINNED && + sd->balance_interval < MAX_PINNED_INTERVAL) || + sd->balance_interval < sd->max_interval) sd->balance_interval *= 2; - - ld_moved = 0; out: return ld_moved; } @@ -9177,15 +9552,8 @@ static void kick_ilb(unsigned int flags) } /* - * Current heuristic for kicking the idle load balancer in the presence - * of an idle cpu in the system. - * - This rq has more than one task. - * - This rq has at least one CFS task and the capacity of the CPU is - * significantly reduced because of RT tasks or IRQs. - * - At parent of LLC scheduler domain level, this cpu's scheduler group has - * multiple busy cpu. - * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler - * domain span are idle. + * Current decision point for kicking the idle load balancer in the presence + * of idle CPUs in the system. */ static void nohz_balancer_kick(struct rq *rq) { @@ -9227,8 +9595,13 @@ static void nohz_balancer_kick(struct rq *rq) sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); if (sds) { /* - * XXX: write a coherent comment on why we do this. - * See also: http://lkml.kernel.org/r/20111202010832.602203411@sbsiddha-desk.sc.intel.com + * If there is an imbalance between LLC domains (IOW we could + * increase the overall cache use), we need some less-loaded LLC + * domain to pull some load. Likewise, we may need to spread + * load within the current LLC domain (e.g. packed SMT cores but + * other CPUs are idle). We can't really know from here how busy + * the others are - so just get a nohz balance going if it looks + * like this LLC domain has tasks we could move. */ nr_busy = atomic_read(&sds->nr_busy_cpus); if (nr_busy > 1) { @@ -9241,19 +9614,15 @@ static void nohz_balancer_kick(struct rq *rq) sd = rcu_dereference(rq->sd); if (sd) { if ((rq->cfs.h_nr_running >= 1) && - check_cpu_capacity(rq, sd)) { + check_cpu_capacity(rq, sd)) { flags = NOHZ_KICK_MASK; goto unlock; } } - sd = rcu_dereference(per_cpu(sd_asym, cpu)); + sd = rcu_dereference(per_cpu(sd_asym_packing, cpu)); if (sd) { - for_each_cpu(i, sched_domain_span(sd)) { - if (i == cpu || - !cpumask_test_cpu(i, nohz.idle_cpus_mask)) - continue; - + for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { if (sched_asym_prefer(i, cpu)) { flags = NOHZ_KICK_MASK; goto unlock; @@ -9499,9 +9868,7 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) return false; } - /* - * barrier, pairs with nohz_balance_enter_idle(), ensures ... - */ + /* could be _relaxed() */ flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu)); if (!(flags & NOHZ_KICK_MASK)) return false; @@ -9751,6 +10118,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) task_tick_numa(rq, curr); update_misfit_status(curr, rq); + update_overutilized_status(task_rq(curr)); } /* diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index e6802181900f..b02d148e7672 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -8,14 +8,14 @@ */ #include "sched.h" -DEFINE_STATIC_KEY_FALSE(housekeeping_overriden); -EXPORT_SYMBOL_GPL(housekeeping_overriden); +DEFINE_STATIC_KEY_FALSE(housekeeping_overridden); +EXPORT_SYMBOL_GPL(housekeeping_overridden); static cpumask_var_t housekeeping_mask; static unsigned int housekeeping_flags; int housekeeping_any_cpu(enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) return cpumask_any_and(housekeeping_mask, cpu_online_mask); return smp_processor_id(); @@ -24,7 +24,7 @@ EXPORT_SYMBOL_GPL(housekeeping_any_cpu); const struct cpumask *housekeeping_cpumask(enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) return housekeeping_mask; return cpu_possible_mask; @@ -33,7 +33,7 @@ EXPORT_SYMBOL_GPL(housekeeping_cpumask); void housekeeping_affine(struct task_struct *t, enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) set_cpus_allowed_ptr(t, housekeeping_mask); } @@ -41,7 +41,7 @@ EXPORT_SYMBOL_GPL(housekeeping_affine); bool housekeeping_test_cpu(int cpu, enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overriden)) + if (static_branch_unlikely(&housekeeping_overridden)) if (housekeeping_flags & flags) return cpumask_test_cpu(cpu, housekeeping_mask); return true; @@ -53,7 +53,7 @@ void __init housekeeping_init(void) if (!housekeeping_flags) return; - static_branch_enable(&housekeeping_overriden); + static_branch_enable(&housekeeping_overridden); if (housekeeping_flags & HK_FLAG_TICK) sched_tick_offload_init(); @@ -80,7 +80,7 @@ static int __init housekeeping_setup(char *str, enum hk_flags flags) cpumask_andnot(housekeeping_mask, cpu_possible_mask, non_housekeeping_mask); if (cpumask_empty(housekeeping_mask)) - cpumask_set_cpu(smp_processor_id(), housekeeping_mask); + __cpumask_set_cpu(smp_processor_id(), housekeeping_mask); } else { cpumask_var_t tmp; diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index a171c1258109..28a516575c18 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -91,19 +91,73 @@ long calc_load_fold_active(struct rq *this_rq, long adjust) return delta; } -/* - * a1 = a0 * e + a * (1 - e) +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. + * + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. */ static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) { - unsigned long newload; + unsigned long result = 1UL << frac_bits; + + if (n) { + for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; + } + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; + } + } - newload = load * exp + active * (FIXED_1 - exp); - if (active >= load) - newload += FIXED_1-1; + return result; +} - return newload / FIXED_1; +/* + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) + * + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x + */ +unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) +{ + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); } #ifdef CONFIG_NO_HZ_COMMON @@ -225,75 +279,6 @@ static long calc_load_nohz_fold(void) return delta; } -/** - * fixed_power_int - compute: x^n, in O(log n) time - * - * @x: base of the power - * @frac_bits: fractional bits of @x - * @n: power to raise @x to. - * - * By exploiting the relation between the definition of the natural power - * function: x^n := x*x*...*x (x multiplied by itself for n times), and - * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, - * (where: n_i \elem {0, 1}, the binary vector representing n), - * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is - * of course trivially computable in O(log_2 n), the length of our binary - * vector. - */ -static unsigned long -fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) -{ - unsigned long result = 1UL << frac_bits; - - if (n) { - for (;;) { - if (n & 1) { - result *= x; - result += 1UL << (frac_bits - 1); - result >>= frac_bits; - } - n >>= 1; - if (!n) - break; - x *= x; - x += 1UL << (frac_bits - 1); - x >>= frac_bits; - } - } - - return result; -} - -/* - * a1 = a0 * e + a * (1 - e) - * - * a2 = a1 * e + a * (1 - e) - * = (a0 * e + a * (1 - e)) * e + a * (1 - e) - * = a0 * e^2 + a * (1 - e) * (1 + e) - * - * a3 = a2 * e + a * (1 - e) - * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) - * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) - * - * ... - * - * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] - * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) - * = a0 * e^n + a * (1 - e^n) - * - * [1] application of the geometric series: - * - * n 1 - x^(n+1) - * S_n := \Sum x^i = ------------- - * i=0 1 - x - */ -static unsigned long -calc_load_n(unsigned long load, unsigned long exp, - unsigned long active, unsigned int n) -{ - return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); -} - /* * NO_HZ can leave us missing all per-CPU ticks calling * calc_load_fold_active(), but since a NO_HZ CPU folds its delta into diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 76e0eaf4654e..3cd8a3a795d2 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -210,7 +210,7 @@ static int membarrier_register_global_expedited(void) * future scheduler executions will observe the new * thread flag state for this mm. */ - synchronize_sched(); + synchronize_rcu(); } atomic_or(MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY, &mm->membarrier_state); @@ -246,7 +246,7 @@ static int membarrier_register_private_expedited(int flags) * Ensure all future scheduler executions will observe the * new thread flag state for this process. */ - synchronize_sched(); + synchronize_rcu(); } atomic_or(state, &mm->membarrier_state); @@ -298,7 +298,7 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags) if (tick_nohz_full_enabled()) return -EINVAL; if (num_online_cpus() > 1) - synchronize_sched(); + synchronize_rcu(); return 0; case MEMBARRIER_CMD_GLOBAL_EXPEDITED: return membarrier_global_expedited(); diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index 90fb5bc12ad4..befce29bd882 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -26,7 +26,6 @@ #include <linux/sched.h> #include "sched.h" -#include "sched-pelt.h" #include "pelt.h" /* @@ -106,16 +105,12 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) * n=1 */ static __always_inline u32 -accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, +accumulate_sum(u64 delta, struct sched_avg *sa, unsigned long load, unsigned long runnable, int running) { - unsigned long scale_freq, scale_cpu; u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ u64 periods; - scale_freq = arch_scale_freq_capacity(cpu); - scale_cpu = arch_scale_cpu_capacity(NULL, cpu); - delta += sa->period_contrib; periods = delta / 1024; /* A period is 1024us (~1ms) */ @@ -137,13 +132,12 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, } sa->period_contrib = delta; - contrib = cap_scale(contrib, scale_freq); if (load) sa->load_sum += load * contrib; if (runnable) sa->runnable_load_sum += runnable * contrib; if (running) - sa->util_sum += contrib * scale_cpu; + sa->util_sum += contrib << SCHED_CAPACITY_SHIFT; return periods; } @@ -177,7 +171,7 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, * = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}] */ static __always_inline int -___update_load_sum(u64 now, int cpu, struct sched_avg *sa, +___update_load_sum(u64 now, struct sched_avg *sa, unsigned long load, unsigned long runnable, int running) { u64 delta; @@ -221,7 +215,7 @@ ___update_load_sum(u64 now, int cpu, struct sched_avg *sa, * Step 1: accumulate *_sum since last_update_time. If we haven't * crossed period boundaries, finish. */ - if (!accumulate_sum(delta, cpu, sa, load, runnable, running)) + if (!accumulate_sum(delta, sa, load, runnable, running)) return 0; return 1; @@ -267,9 +261,9 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna * runnable_load_avg = \Sum se->avg.runable_load_avg */ -int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) +int __update_load_avg_blocked_se(u64 now, struct sched_entity *se) { - if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) { + if (___update_load_sum(now, &se->avg, 0, 0, 0)) { ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); return 1; } @@ -277,9 +271,9 @@ int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se) return 0; } -int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se) +int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq, + if (___update_load_sum(now, &se->avg, !!se->on_rq, !!se->on_rq, cfs_rq->curr == se)) { ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); @@ -290,9 +284,9 @@ int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_e return 0; } -int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) +int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) { - if (___update_load_sum(now, cpu, &cfs_rq->avg, + if (___update_load_sum(now, &cfs_rq->avg, scale_load_down(cfs_rq->load.weight), scale_load_down(cfs_rq->runnable_weight), cfs_rq->curr != NULL)) { @@ -317,7 +311,7 @@ int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq) int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) { - if (___update_load_sum(now, rq->cpu, &rq->avg_rt, + if (___update_load_sum(now, &rq->avg_rt, running, running, running)) { @@ -340,7 +334,7 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) { - if (___update_load_sum(now, rq->cpu, &rq->avg_dl, + if (___update_load_sum(now, &rq->avg_dl, running, running, running)) { @@ -365,22 +359,31 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) int update_irq_load_avg(struct rq *rq, u64 running) { int ret = 0; + + /* + * We can't use clock_pelt because irq time is not accounted in + * clock_task. Instead we directly scale the running time to + * reflect the real amount of computation + */ + running = cap_scale(running, arch_scale_freq_capacity(cpu_of(rq))); + running = cap_scale(running, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + /* * We know the time that has been used by interrupt since last update * but we don't when. Let be pessimistic and assume that interrupt has * happened just before the update. This is not so far from reality * because interrupt will most probably wake up task and trig an update - * of rq clock during which the metric si updated. + * of rq clock during which the metric is updated. * We start to decay with normal context time and then we add the * interrupt context time. * We can safely remove running from rq->clock because * rq->clock += delta with delta >= running */ - ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq, + ret = ___update_load_sum(rq->clock - running, &rq->avg_irq, 0, 0, 0); - ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq, + ret += ___update_load_sum(rq->clock, &rq->avg_irq, 1, 1, 1); diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 7e56b489ff32..7489d5f56960 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -1,8 +1,9 @@ #ifdef CONFIG_SMP +#include "sched-pelt.h" -int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se); -int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se); -int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq); +int __update_load_avg_blocked_se(u64 now, struct sched_entity *se); +int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se); +int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq); int update_rt_rq_load_avg(u64 now, struct rq *rq, int running); int update_dl_rq_load_avg(u64 now, struct rq *rq, int running); @@ -42,6 +43,101 @@ static inline void cfs_se_util_change(struct sched_avg *avg) WRITE_ONCE(avg->util_est.enqueued, enqueued); } +/* + * The clock_pelt scales the time to reflect the effective amount of + * computation done during the running delta time but then sync back to + * clock_task when rq is idle. + * + * + * absolute time | 1| 2| 3| 4| 5| 6| 7| 8| 9|10|11|12|13|14|15|16 + * @ max capacity ------******---------------******--------------- + * @ half capacity ------************---------************--------- + * clock pelt | 1| 2| 3| 4| 7| 8| 9| 10| 11|14|15|16 + * + */ +static inline void update_rq_clock_pelt(struct rq *rq, s64 delta) +{ + if (unlikely(is_idle_task(rq->curr))) { + /* The rq is idle, we can sync to clock_task */ + rq->clock_pelt = rq_clock_task(rq); + return; + } + + /* + * When a rq runs at a lower compute capacity, it will need + * more time to do the same amount of work than at max + * capacity. In order to be invariant, we scale the delta to + * reflect how much work has been really done. + * Running longer results in stealing idle time that will + * disturb the load signal compared to max capacity. This + * stolen idle time will be automatically reflected when the + * rq will be idle and the clock will be synced with + * rq_clock_task. + */ + + /* + * Scale the elapsed time to reflect the real amount of + * computation + */ + delta = cap_scale(delta, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + delta = cap_scale(delta, arch_scale_freq_capacity(cpu_of(rq))); + + rq->clock_pelt += delta; +} + +/* + * When rq becomes idle, we have to check if it has lost idle time + * because it was fully busy. A rq is fully used when the /Sum util_sum + * is greater or equal to: + * (LOAD_AVG_MAX - 1024 + rq->cfs.avg.period_contrib) << SCHED_CAPACITY_SHIFT; + * For optimization and computing rounding purpose, we don't take into account + * the position in the current window (period_contrib) and we use the higher + * bound of util_sum to decide. + */ +static inline void update_idle_rq_clock_pelt(struct rq *rq) +{ + u32 divider = ((LOAD_AVG_MAX - 1024) << SCHED_CAPACITY_SHIFT) - LOAD_AVG_MAX; + u32 util_sum = rq->cfs.avg.util_sum; + util_sum += rq->avg_rt.util_sum; + util_sum += rq->avg_dl.util_sum; + + /* + * Reflecting stolen time makes sense only if the idle + * phase would be present at max capacity. As soon as the + * utilization of a rq has reached the maximum value, it is + * considered as an always runnig rq without idle time to + * steal. This potential idle time is considered as lost in + * this case. We keep track of this lost idle time compare to + * rq's clock_task. + */ + if (util_sum >= divider) + rq->lost_idle_time += rq_clock_task(rq) - rq->clock_pelt; +} + +static inline u64 rq_clock_pelt(struct rq *rq) +{ + lockdep_assert_held(&rq->lock); + assert_clock_updated(rq); + + return rq->clock_pelt - rq->lost_idle_time; +} + +#ifdef CONFIG_CFS_BANDWIDTH +/* rq->task_clock normalized against any time this cfs_rq has spent throttled */ +static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) +{ + if (unlikely(cfs_rq->throttle_count)) + return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time; + + return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; +} +#else +static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) +{ + return rq_clock_pelt(rq_of(cfs_rq)); +} +#endif + #else static inline int @@ -67,6 +163,18 @@ update_irq_load_avg(struct rq *rq, u64 running) { return 0; } + +static inline u64 rq_clock_pelt(struct rq *rq) +{ + return rq_clock_task(rq); +} + +static inline void +update_rq_clock_pelt(struct rq *rq, s64 delta) { } + +static inline void +update_idle_rq_clock_pelt(struct rq *rq) { } + #endif diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c new file mode 100644 index 000000000000..0e97ca9306ef --- /dev/null +++ b/kernel/sched/psi.c @@ -0,0 +1,785 @@ +/* + * Pressure stall information for CPU, memory and IO + * + * Copyright (c) 2018 Facebook, Inc. + * Author: Johannes Weiner <hannes@cmpxchg.org> + * + * When CPU, memory and IO are contended, tasks experience delays that + * reduce throughput and introduce latencies into the workload. Memory + * and IO contention, in addition, can cause a full loss of forward + * progress in which the CPU goes idle. + * + * This code aggregates individual task delays into resource pressure + * metrics that indicate problems with both workload health and + * resource utilization. + * + * Model + * + * The time in which a task can execute on a CPU is our baseline for + * productivity. Pressure expresses the amount of time in which this + * potential cannot be realized due to resource contention. + * + * This concept of productivity has two components: the workload and + * the CPU. To measure the impact of pressure on both, we define two + * contention states for a resource: SOME and FULL. + * + * In the SOME state of a given resource, one or more tasks are + * delayed on that resource. This affects the workload's ability to + * perform work, but the CPU may still be executing other tasks. + * + * In the FULL state of a given resource, all non-idle tasks are + * delayed on that resource such that nobody is advancing and the CPU + * goes idle. This leaves both workload and CPU unproductive. + * + * (Naturally, the FULL state doesn't exist for the CPU resource.) + * + * SOME = nr_delayed_tasks != 0 + * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * + * The percentage of wallclock time spent in those compound stall + * states gives pressure numbers between 0 and 100 for each resource, + * where the SOME percentage indicates workload slowdowns and the FULL + * percentage indicates reduced CPU utilization: + * + * %SOME = time(SOME) / period + * %FULL = time(FULL) / period + * + * Multiple CPUs + * + * The more tasks and available CPUs there are, the more work can be + * performed concurrently. This means that the potential that can go + * unrealized due to resource contention *also* scales with non-idle + * tasks and CPUs. + * + * Consider a scenario where 257 number crunching tasks are trying to + * run concurrently on 256 CPUs. If we simply aggregated the task + * states, we would have to conclude a CPU SOME pressure number of + * 100%, since *somebody* is waiting on a runqueue at all + * times. However, that is clearly not the amount of contention the + * workload is experiencing: only one out of 256 possible exceution + * threads will be contended at any given time, or about 0.4%. + * + * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any + * given time *one* of the tasks is delayed due to a lack of memory. + * Again, looking purely at the task state would yield a memory FULL + * pressure number of 0%, since *somebody* is always making forward + * progress. But again this wouldn't capture the amount of execution + * potential lost, which is 1 out of 4 CPUs, or 25%. + * + * To calculate wasted potential (pressure) with multiple processors, + * we have to base our calculation on the number of non-idle tasks in + * conjunction with the number of available CPUs, which is the number + * of potential execution threads. SOME becomes then the proportion of + * delayed tasks to possibe threads, and FULL is the share of possible + * threads that are unproductive due to delays: + * + * threads = min(nr_nonidle_tasks, nr_cpus) + * SOME = min(nr_delayed_tasks / threads, 1) + * FULL = (threads - min(nr_running_tasks, threads)) / threads + * + * For the 257 number crunchers on 256 CPUs, this yields: + * + * threads = min(257, 256) + * SOME = min(1 / 256, 1) = 0.4% + * FULL = (256 - min(257, 256)) / 256 = 0% + * + * For the 1 out of 4 memory-delayed tasks, this yields: + * + * threads = min(4, 4) + * SOME = min(1 / 4, 1) = 25% + * FULL = (4 - min(3, 4)) / 4 = 25% + * + * [ Substitute nr_cpus with 1, and you can see that it's a natural + * extension of the single-CPU model. ] + * + * Implementation + * + * To assess the precise time spent in each such state, we would have + * to freeze the system on task changes and start/stop the state + * clocks accordingly. Obviously that doesn't scale in practice. + * + * Because the scheduler aims to distribute the compute load evenly + * among the available CPUs, we can track task state locally to each + * CPU and, at much lower frequency, extrapolate the global state for + * the cumulative stall times and the running averages. + * + * For each runqueue, we track: + * + * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) + * + * and then periodically aggregate: + * + * tNONIDLE = sum(tNONIDLE[i]) + * + * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE + * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE + * + * %SOME = tSOME / period + * %FULL = tFULL / period + * + * This gives us an approximation of pressure that is practical + * cost-wise, yet way more sensitive and accurate than periodic + * sampling of the aggregate task states would be. + */ + +#include "../workqueue_internal.h" +#include <linux/sched/loadavg.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> +#include <linux/seqlock.h> +#include <linux/cgroup.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/psi.h> +#include "sched.h" + +static int psi_bug __read_mostly; + +DEFINE_STATIC_KEY_FALSE(psi_disabled); + +#ifdef CONFIG_PSI_DEFAULT_DISABLED +bool psi_enable; +#else +bool psi_enable = true; +#endif +static int __init setup_psi(char *str) +{ + return kstrtobool(str, &psi_enable) == 0; +} +__setup("psi=", setup_psi); + +/* Running averages - we need to be higher-res than loadavg */ +#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ +#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */ +#define EXP_60s 1981 /* 1/exp(2s/60s) */ +#define EXP_300s 2034 /* 1/exp(2s/300s) */ + +/* Sampling frequency in nanoseconds */ +static u64 psi_period __read_mostly; + +/* System-level pressure and stall tracking */ +static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu); +static struct psi_group psi_system = { + .pcpu = &system_group_pcpu, +}; + +static void psi_update_work(struct work_struct *work); + +static void group_init(struct psi_group *group) +{ + int cpu; + + for_each_possible_cpu(cpu) + seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); + group->next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->clock_work, psi_update_work); + mutex_init(&group->stat_lock); +} + +void __init psi_init(void) +{ + if (!psi_enable) { + static_branch_enable(&psi_disabled); + return; + } + + psi_period = jiffies_to_nsecs(PSI_FREQ); + group_init(&psi_system); +} + +static bool test_state(unsigned int *tasks, enum psi_states state) +{ + switch (state) { + case PSI_IO_SOME: + return tasks[NR_IOWAIT]; + case PSI_IO_FULL: + return tasks[NR_IOWAIT] && !tasks[NR_RUNNING]; + case PSI_MEM_SOME: + return tasks[NR_MEMSTALL]; + case PSI_MEM_FULL: + return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]; + case PSI_CPU_SOME: + return tasks[NR_RUNNING] > 1; + case PSI_NONIDLE: + return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || + tasks[NR_RUNNING]; + default: + return false; + } +} + +static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +{ + struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); + unsigned int tasks[NR_PSI_TASK_COUNTS]; + u64 now, state_start; + unsigned int seq; + int s; + + /* Snapshot a coherent view of the CPU state */ + do { + seq = read_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + memcpy(times, groupc->times, sizeof(groupc->times)); + memcpy(tasks, groupc->tasks, sizeof(groupc->tasks)); + state_start = groupc->state_start; + } while (read_seqcount_retry(&groupc->seq, seq)); + + /* Calculate state time deltas against the previous snapshot */ + for (s = 0; s < NR_PSI_STATES; s++) { + u32 delta; + /* + * In addition to already concluded states, we also + * incorporate currently active states on the CPU, + * since states may last for many sampling periods. + * + * This way we keep our delta sampling buckets small + * (u32) and our reported pressure close to what's + * actually happening. + */ + if (test_state(tasks, s)) + times[s] += now - state_start; + + delta = times[s] - groupc->times_prev[s]; + groupc->times_prev[s] = times[s]; + + times[s] = delta; + } +} + +static void calc_avgs(unsigned long avg[3], int missed_periods, + u64 time, u64 period) +{ + unsigned long pct; + + /* Fill in zeroes for periods of no activity */ + if (missed_periods) { + avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods); + avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods); + avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods); + } + + /* Sample the most recent active period */ + pct = div_u64(time * 100, period); + pct *= FIXED_1; + avg[0] = calc_load(avg[0], EXP_10s, pct); + avg[1] = calc_load(avg[1], EXP_60s, pct); + avg[2] = calc_load(avg[2], EXP_300s, pct); +} + +static bool update_stats(struct psi_group *group) +{ + u64 deltas[NR_PSI_STATES - 1] = { 0, }; + unsigned long missed_periods = 0; + unsigned long nonidle_total = 0; + u64 now, expires, period; + int cpu; + int s; + + mutex_lock(&group->stat_lock); + + /* + * Collect the per-cpu time buckets and average them into a + * single time sample that is normalized to wallclock time. + * + * For averaging, each CPU is weighted by its non-idle time in + * the sampling period. This eliminates artifacts from uneven + * loading, or even entirely idle CPUs. + */ + for_each_possible_cpu(cpu) { + u32 times[NR_PSI_STATES]; + u32 nonidle; + + get_recent_times(group, cpu, times); + + nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); + nonidle_total += nonidle; + + for (s = 0; s < PSI_NONIDLE; s++) + deltas[s] += (u64)times[s] * nonidle; + } + + /* + * Integrate the sample into the running statistics that are + * reported to userspace: the cumulative stall times and the + * decaying averages. + * + * Pressure percentages are sampled at PSI_FREQ. We might be + * called more often when the user polls more frequently than + * that; we might be called less often when there is no task + * activity, thus no data, and clock ticks are sporadic. The + * below handles both. + */ + + /* total= */ + for (s = 0; s < NR_PSI_STATES - 1; s++) + group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + + /* avgX= */ + now = sched_clock(); + expires = group->next_update; + if (now < expires) + goto out; + if (now - expires >= psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + group->next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->last_update + (missed_periods * psi_period)); + group->last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[s] - group->total_prev[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->total_prev[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } +out: + mutex_unlock(&group->stat_lock); + return nonidle_total; +} + +static void psi_update_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + bool nonidle; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, clock_work); + + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + + nonidle = update_stats(group); + + if (nonidle) { + unsigned long delay = 0; + u64 now; + + now = sched_clock(); + if (group->next_update > now) + delay = nsecs_to_jiffies(group->next_update - now) + 1; + schedule_delayed_work(dwork, delay); + } +} + +static void record_times(struct psi_group_cpu *groupc, int cpu, + bool memstall_tick) +{ + u32 delta; + u64 now; + + now = cpu_clock(cpu); + delta = now - groupc->state_start; + groupc->state_start = now; + + if (test_state(groupc->tasks, PSI_IO_SOME)) { + groupc->times[PSI_IO_SOME] += delta; + if (test_state(groupc->tasks, PSI_IO_FULL)) + groupc->times[PSI_IO_FULL] += delta; + } + + if (test_state(groupc->tasks, PSI_MEM_SOME)) { + groupc->times[PSI_MEM_SOME] += delta; + if (test_state(groupc->tasks, PSI_MEM_FULL)) + groupc->times[PSI_MEM_FULL] += delta; + else if (memstall_tick) { + u32 sample; + /* + * Since we care about lost potential, a + * memstall is FULL when there are no other + * working tasks, but also when the CPU is + * actively reclaiming and nothing productive + * could run even if it were runnable. + * + * When the timer tick sees a reclaiming CPU, + * regardless of runnable tasks, sample a FULL + * tick (or less if it hasn't been a full tick + * since the last state change). + */ + sample = min(delta, (u32)jiffies_to_nsecs(1)); + groupc->times[PSI_MEM_FULL] += sample; + } + } + + if (test_state(groupc->tasks, PSI_CPU_SOME)) + groupc->times[PSI_CPU_SOME] += delta; + + if (test_state(groupc->tasks, PSI_NONIDLE)) + groupc->times[PSI_NONIDLE] += delta; +} + +static void psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) +{ + struct psi_group_cpu *groupc; + unsigned int t, m; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + /* + * First we assess the aggregate resource states this CPU's + * tasks have been in since the last change, and account any + * SOME and FULL time these may have resulted in. + * + * Then we update the task counts according to the state + * change requested through the @clear and @set bits. + */ + write_seqcount_begin(&groupc->seq); + + record_times(groupc, cpu, false); + + for (t = 0, m = clear; m; m &= ~(1 << t), t++) { + if (!(m & (1 << t))) + continue; + if (groupc->tasks[t] == 0 && !psi_bug) { + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n", + cpu, t, groupc->tasks[0], + groupc->tasks[1], groupc->tasks[2], + clear, set); + psi_bug = 1; + } + groupc->tasks[t]--; + } + + for (t = 0; set; set &= ~(1 << t), t++) + if (set & (1 << t)) + groupc->tasks[t]++; + + write_seqcount_end(&groupc->seq); +} + +static struct psi_group *iterate_groups(struct task_struct *task, void **iter) +{ +#ifdef CONFIG_CGROUPS + struct cgroup *cgroup = NULL; + + if (!*iter) + cgroup = task->cgroups->dfl_cgrp; + else if (*iter == &psi_system) + return NULL; + else + cgroup = cgroup_parent(*iter); + + if (cgroup && cgroup_parent(cgroup)) { + *iter = cgroup; + return cgroup_psi(cgroup); + } +#else + if (*iter) + return NULL; +#endif + *iter = &psi_system; + return &psi_system; +} + +void psi_task_change(struct task_struct *task, int clear, int set) +{ + int cpu = task_cpu(task); + struct psi_group *group; + bool wake_clock = true; + void *iter = NULL; + + if (!task->pid) + return; + + if (((task->psi_flags & set) || + (task->psi_flags & clear) != clear) && + !psi_bug) { + printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n", + task->pid, task->comm, cpu, + task->psi_flags, clear, set); + psi_bug = 1; + } + + task->psi_flags &= ~clear; + task->psi_flags |= set; + + /* + * Periodic aggregation shuts off if there is a period of no + * task changes, so we wake it back up if necessary. However, + * don't do this if the task change is the aggregation worker + * itself going to sleep, or we'll ping-pong forever. + */ + if (unlikely((clear & TSK_RUNNING) && + (task->flags & PF_WQ_WORKER) && + wq_worker_last_func(task) == psi_update_work)) + wake_clock = false; + + while ((group = iterate_groups(task, &iter))) { + psi_group_change(group, cpu, clear, set); + if (wake_clock && !delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); + } +} + +void psi_memstall_tick(struct task_struct *task, int cpu) +{ + struct psi_group *group; + void *iter = NULL; + + while ((group = iterate_groups(task, &iter))) { + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(group->pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); + } +} + +/** + * psi_memstall_enter - mark the beginning of a memory stall section + * @flags: flags to handle nested sections + * + * Marks the calling task as being stalled due to a lack of memory, + * such as waiting for a refault or performing reclaim. + */ +void psi_memstall_enter(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (static_branch_likely(&psi_disabled)) + return; + + *flags = current->flags & PF_MEMSTALL; + if (*flags) + return; + /* + * PF_MEMSTALL setting & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we can + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags |= PF_MEMSTALL; + psi_task_change(current, 0, TSK_MEMSTALL); + + rq_unlock_irq(rq, &rf); +} + +/** + * psi_memstall_leave - mark the end of an memory stall section + * @flags: flags to handle nested memdelay sections + * + * Marks the calling task as no longer stalled due to lack of memory. + */ +void psi_memstall_leave(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (static_branch_likely(&psi_disabled)) + return; + + if (*flags) + return; + /* + * PF_MEMSTALL clearing & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we could + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags &= ~PF_MEMSTALL; + psi_task_change(current, TSK_MEMSTALL, 0); + + rq_unlock_irq(rq, &rf); +} + +#ifdef CONFIG_CGROUPS +int psi_cgroup_alloc(struct cgroup *cgroup) +{ + if (static_branch_likely(&psi_disabled)) + return 0; + + cgroup->psi.pcpu = alloc_percpu(struct psi_group_cpu); + if (!cgroup->psi.pcpu) + return -ENOMEM; + group_init(&cgroup->psi); + return 0; +} + +void psi_cgroup_free(struct cgroup *cgroup) +{ + if (static_branch_likely(&psi_disabled)) + return; + + cancel_delayed_work_sync(&cgroup->psi.clock_work); + free_percpu(cgroup->psi.pcpu); +} + +/** + * cgroup_move_task - move task to a different cgroup + * @task: the task + * @to: the target css_set + * + * Move task to a new cgroup and safely migrate its associated stall + * state between the different groups. + * + * This function acquires the task's rq lock to lock out concurrent + * changes to the task's scheduling state and - in case the task is + * running - concurrent changes to its stall state. + */ +void cgroup_move_task(struct task_struct *task, struct css_set *to) +{ + unsigned int task_flags = 0; + struct rq_flags rf; + struct rq *rq; + + if (static_branch_likely(&psi_disabled)) { + /* + * Lame to do this here, but the scheduler cannot be locked + * from the outside, so we move cgroups from inside sched/. + */ + rcu_assign_pointer(task->cgroups, to); + return; + } + + rq = task_rq_lock(task, &rf); + + if (task_on_rq_queued(task)) + task_flags = TSK_RUNNING; + else if (task->in_iowait) + task_flags = TSK_IOWAIT; + + if (task->flags & PF_MEMSTALL) + task_flags |= TSK_MEMSTALL; + + if (task_flags) + psi_task_change(task, task_flags, 0); + + /* See comment above */ + rcu_assign_pointer(task->cgroups, to); + + if (task_flags) + psi_task_change(task, 0, task_flags); + + task_rq_unlock(rq, task, &rf); +} +#endif /* CONFIG_CGROUPS */ + +int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) +{ + int full; + + if (static_branch_likely(&psi_disabled)) + return -EOPNOTSUPP; + + update_stats(group); + + for (full = 0; full < 2 - (res == PSI_CPU); full++) { + unsigned long avg[3]; + u64 total; + int w; + + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC); + + seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", + full ? "full" : "some", + LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), + LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), + LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), + total); + } + + return 0; +} + +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_io_show, NULL); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_memory_show, NULL); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_cpu_show, NULL); +} + +static const struct file_operations psi_io_fops = { + .open = psi_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_memory_fops = { + .open = psi_memory_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_cpu_fops = { + .open = psi_cpu_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init psi_proc_init(void) +{ + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_fops); + proc_create("pressure/memory", 0, NULL, &psi_memory_fops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + return 0; +} +module_init(psi_proc_init); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2e2955a8cf8f..90fa23d36565 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1498,6 +1498,14 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag #endif } +static inline void set_next_task(struct rq *rq, struct task_struct *p) +{ + p->se.exec_start = rq_clock_task(rq); + + /* The running task is never eligible for pushing */ + dequeue_pushable_task(rq, p); +} + static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, struct rt_rq *rt_rq) { @@ -1518,7 +1526,6 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, 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 = &rq->rt; do { @@ -1527,10 +1534,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) rt_rq = group_rt_rq(rt_se); } while (rt_rq); - p = rt_task_of(rt_se); - p->se.exec_start = rq_clock_task(rq); - - return p; + return rt_task_of(rt_se); } static struct task_struct * @@ -1561,7 +1565,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) /* * We may dequeue prev's rt_rq in put_prev_task(). - * So, we update time before rt_nr_running check. + * So, we update time before rt_queued check. */ if (prev->sched_class == &rt_sched_class) update_curr_rt(rq); @@ -1573,8 +1577,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) p = _pick_next_task_rt(rq); - /* The running task is never eligible for pushing */ - dequeue_pushable_task(rq, p); + set_next_task(rq, p); rt_queue_push_tasks(rq); @@ -1584,7 +1587,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * rt task */ if (rq->curr->sched_class != &rt_sched_class) - update_rt_rq_load_avg(rq_clock_task(rq), rq, 0); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); return p; } @@ -1593,7 +1596,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) { update_curr_rt(rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1); /* * The previous task needs to be made eligible for pushing @@ -1810,10 +1813,8 @@ static int push_rt_task(struct rq *rq) return 0; retry: - if (unlikely(next_task == rq->curr)) { - WARN_ON(1); + if (WARN_ON(next_task == rq->curr)) return 0; - } /* * It's possible that the next_task slipped in of @@ -2324,7 +2325,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) struct sched_rt_entity *rt_se = &p->rt; update_curr_rt(rq); - update_rt_rq_load_avg(rq_clock_task(rq), rq, 1); + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1); watchdog(rq, p); @@ -2355,12 +2356,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) static void set_curr_task_rt(struct rq *rq) { - struct task_struct *p = rq->curr; - - p->se.exec_start = rq_clock_task(rq); - - /* The running task is never eligible for pushing */ - dequeue_pushable_task(rq, p); + set_next_task(rq, rq->curr); } static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b8c007713b3b..efa686eeff26 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -23,6 +23,7 @@ #include <linux/sched/prio.h> #include <linux/sched/rt.h> #include <linux/sched/signal.h> +#include <linux/sched/smt.h> #include <linux/sched/stat.h> #include <linux/sched/sysctl.h> #include <linux/sched/task.h> @@ -44,6 +45,7 @@ #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/delayacct.h> +#include <linux/energy_model.h> #include <linux/init_task.h> #include <linux/kprobes.h> #include <linux/kthread.h> @@ -54,6 +56,7 @@ #include <linux/proc_fs.h> #include <linux/prefetch.h> #include <linux/profile.h> +#include <linux/psi.h> #include <linux/rcupdate_wait.h> #include <linux/security.h> #include <linux/stop_machine.h> @@ -175,6 +178,11 @@ static inline bool valid_policy(int policy) rt_policy(policy) || dl_policy(policy); } +static inline int task_has_idle_policy(struct task_struct *p) +{ + return idle_policy(p->policy); +} + static inline int task_has_rt_policy(struct task_struct *p) { return rt_policy(p->policy); @@ -319,6 +327,7 @@ extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED #include <linux/cgroup.h> +#include <linux/psi.h> struct cfs_rq; struct rt_rq; @@ -629,7 +638,7 @@ struct dl_rq { /* * 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 + * the decision whether or not a ready but not running task * should migrate somewhere else. */ struct { @@ -701,6 +710,16 @@ static inline bool sched_asym_prefer(int a, int b) return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b); } +struct perf_domain { + struct em_perf_domain *em_pd; + struct perf_domain *next; + struct rcu_head rcu; +}; + +/* Scheduling group status flags */ +#define SG_OVERLOAD 0x1 /* More than one runnable task on a CPU. */ +#define SG_OVERUTILIZED 0x2 /* One or more CPUs are over-utilized. */ + /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by @@ -723,6 +742,9 @@ struct root_domain { */ int overload; + /* Indicate one or more cpus over-utilized (tipping point) */ + int overutilized; + /* * 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). @@ -753,6 +775,12 @@ struct root_domain { struct cpupri cpupri; unsigned long max_cpu_capacity; + + /* + * NULL-terminated list of performance domains intersecting with the + * CPUs of the rd. Protected by RCU. + */ + struct perf_domain *pd; }; extern struct root_domain def_root_domain; @@ -833,7 +861,10 @@ struct rq { unsigned int clock_update_flags; u64 clock; - u64 clock_task; + /* Ensure that all clocks are in the same cache line */ + u64 clock_task ____cacheline_aligned; + u64 clock_pelt; + unsigned long lost_idle_time; atomic_t nr_iowait; @@ -923,6 +954,22 @@ struct rq { #endif }; +#ifdef CONFIG_FAIR_GROUP_SCHED + +/* CPU runqueue to which this cfs_rq is attached */ +static inline struct rq *rq_of(struct cfs_rq *cfs_rq) +{ + return cfs_rq->rq; +} + +#else + +static inline struct rq *rq_of(struct cfs_rq *cfs_rq) +{ + return container_of(cfs_rq, struct rq, cfs); +} +#endif + static inline int cpu_of(struct rq *rq) { #ifdef CONFIG_SMP @@ -934,9 +981,6 @@ static inline int cpu_of(struct rq *rq) #ifdef CONFIG_SCHED_SMT - -extern struct static_key_false sched_smt_present; - extern void __update_idle_core(struct rq *rq); static inline void update_idle_core(struct rq *rq) @@ -957,6 +1001,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #define cpu_curr(cpu) (cpu_rq(cpu)->curr) #define raw_rq() raw_cpu_ptr(&runqueues) +extern void update_rq_clock(struct rq *rq); + static inline u64 __rq_clock_broken(struct rq *rq) { return READ_ONCE(rq->clock); @@ -1075,6 +1121,98 @@ static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) #endif } +struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(rq->lock); + +struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) + __acquires(p->pi_lock) + __acquires(rq->lock); + +static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline void +task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); +} + +static inline void +rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irqsave(&rq->lock, rf->flags); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock_irq(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock_irq(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_lock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_pin_lock(rq, rf); +} + +static inline void +rq_relock(struct rq *rq, struct rq_flags *rf) + __acquires(rq->lock) +{ + raw_spin_lock(&rq->lock); + rq_repin_lock(rq, rf); +} + +static inline void +rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irqrestore(&rq->lock, rf->flags); +} + +static inline void +rq_unlock_irq(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock_irq(&rq->lock); +} + +static inline void +rq_unlock(struct rq *rq, struct rq_flags *rf) + __releases(rq->lock) +{ + rq_unpin_lock(rq, rf); + raw_spin_unlock(&rq->lock); +} + +static inline struct rq * +this_rq_lock_irq(struct rq_flags *rf) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + rq_lock(rq, rf); + return rq; +} + #ifdef CONFIG_NUMA enum numa_topology_type { NUMA_DIRECT, @@ -1141,7 +1279,7 @@ extern void sched_ttwu_pending(void); /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. - * See detach_destroy_domains: synchronize_sched for details. + * See destroy_sched_domains: call_rcu for details. * * The domain tree of any CPU may only be accessed from within * preempt-disabled sections. @@ -1191,7 +1329,8 @@ DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); DECLARE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DECLARE_PER_CPU(struct sched_domain *, sd_numa); -DECLARE_PER_CPU(struct sched_domain *, sd_asym); +DECLARE_PER_CPU(struct sched_domain *, sd_asym_packing); +DECLARE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); extern struct static_key_false sched_asym_cpucapacity; struct sched_group_capacity { @@ -1335,14 +1474,14 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) #ifdef CONFIG_SMP /* * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be - * successfuly executed on another CPU. We must ensure that updates of + * successfully executed on another CPU. We must ensure that updates of * per-task data have been completed by this moment. */ smp_wmb(); #ifdef CONFIG_THREAD_INFO_IN_TASK - p->cpu = cpu; + WRITE_ONCE(p->cpu, cpu); #else - task_thread_info(p)->cpu = cpu; + WRITE_ONCE(task_thread_info(p)->cpu, cpu); #endif p->wake_cpu = cpu; #endif @@ -1368,7 +1507,7 @@ enum { #undef SCHED_FEAT -#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) /* * To support run-time toggling of sched features, all the translation units @@ -1388,7 +1527,7 @@ static __always_inline bool static_branch_##name(struct static_key *key) \ extern struct static_key sched_feat_keys[__SCHED_FEAT_NR]; #define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x])) -#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */ +#else /* !(SCHED_DEBUG && CONFIG_JUMP_LABEL) */ /* * Each translation unit has its own copy of sysctl_sched_features to allow @@ -1404,7 +1543,7 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features = #define sched_feat(x) !!(sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) -#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */ +#endif /* SCHED_DEBUG && CONFIG_JUMP_LABEL */ extern struct static_key_false sched_numa_balancing; extern struct static_key_false sched_schedstats; @@ -1443,7 +1582,7 @@ static inline int task_on_rq_queued(struct task_struct *p) static inline int task_on_rq_migrating(struct task_struct *p) { - return p->on_rq == TASK_ON_RQ_MIGRATING; + return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING; } /* @@ -1661,7 +1800,7 @@ extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq); unsigned long to_ratio(u64 period, u64 runtime); extern void init_entity_runnable_average(struct sched_entity *se); -extern void post_init_entity_util_avg(struct sched_entity *se); +extern void post_init_entity_util_avg(struct task_struct *p); #ifdef CONFIG_NO_HZ_FULL extern bool sched_can_stop_tick(struct rq *rq); @@ -1700,12 +1839,12 @@ static inline void add_nr_running(struct rq *rq, unsigned count) rq->nr_running = prev_nr + count; - if (prev_nr < 2 && rq->nr_running >= 2) { #ifdef CONFIG_SMP + if (prev_nr < 2 && rq->nr_running >= 2) { if (!READ_ONCE(rq->rd->overload)) WRITE_ONCE(rq->rd->overload, 1); -#endif } +#endif sched_update_tick_dependency(rq); } @@ -1717,8 +1856,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count) sched_update_tick_dependency(rq); } -extern void update_rq_clock(struct rq *rq); - extern void activate_task(struct rq *rq, struct task_struct *p, int flags); extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags); @@ -1763,107 +1900,6 @@ unsigned long arch_scale_freq_capacity(int cpu) #endif #ifdef CONFIG_SMP -#ifndef arch_scale_cpu_capacity -static __always_inline -unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu) -{ - if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1)) - return sd->smt_gain / sd->span_weight; - - return SCHED_CAPACITY_SCALE; -} -#endif -#else -#ifndef arch_scale_cpu_capacity -static __always_inline -unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu) -{ - return SCHED_CAPACITY_SCALE; -} -#endif -#endif - -struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(rq->lock); - -struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) - __acquires(p->pi_lock) - __acquires(rq->lock); - -static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - -static inline void -task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) - __releases(rq->lock) - __releases(p->pi_lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); - raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); -} - -static inline void -rq_lock_irqsave(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irqsave(&rq->lock, rf->flags); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock_irq(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock_irq(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_lock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_pin_lock(rq, rf); -} - -static inline void -rq_relock(struct rq *rq, struct rq_flags *rf) - __acquires(rq->lock) -{ - raw_spin_lock(&rq->lock); - rq_repin_lock(rq, rf); -} - -static inline void -rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irqrestore(&rq->lock, rf->flags); -} - -static inline void -rq_unlock_irq(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock_irq(&rq->lock); -} - -static inline void -rq_unlock(struct rq *rq, struct rq_flags *rf) - __releases(rq->lock) -{ - rq_unpin_lock(rq, rf); - raw_spin_unlock(&rq->lock); -} - -#ifdef CONFIG_SMP #ifdef CONFIG_PREEMPT static inline void double_rq_lock(struct rq *rq1, struct rq *rq2); @@ -2194,7 +2230,39 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} # define arch_scale_freq_invariant() false #endif +#ifdef CONFIG_SMP +static inline unsigned long capacity_orig_of(int cpu) +{ + return cpu_rq(cpu)->cpu_capacity_orig; +} +#endif + #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL +/** + * enum schedutil_type - CPU utilization type + * @FREQUENCY_UTIL: Utilization used to select frequency + * @ENERGY_UTIL: Utilization used during energy calculation + * + * The utilization signals of all scheduling classes (CFS/RT/DL) and IRQ time + * need to be aggregated differently depending on the usage made of them. This + * enum is used within schedutil_freq_util() to differentiate the types of + * utilization expected by the callers, and adjust the aggregation accordingly. + */ +enum schedutil_type { + FREQUENCY_UTIL, + ENERGY_UTIL, +}; + +unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type); + +static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) +{ + unsigned long max = arch_scale_cpu_capacity(NULL, cpu); + + return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL); +} + static inline unsigned long cpu_bw_dl(struct rq *rq) { return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT; @@ -2221,6 +2289,11 @@ static inline unsigned long cpu_util_rt(struct rq *rq) { return READ_ONCE(rq->avg_rt.util_avg); } +#else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ +static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) +{ + return cfs; +} #endif #ifdef CONFIG_HAVE_SCHED_AVG_IRQ @@ -2250,3 +2323,21 @@ unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned return util; } #endif + +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) + +#define perf_domain_span(pd) (to_cpumask(((pd)->em_pd->cpus))) + +DECLARE_STATIC_KEY_FALSE(sched_energy_present); + +static inline bool sched_energy_enabled(void) +{ + return static_branch_unlikely(&sched_energy_present); +} + +#else /* ! (CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL) */ + +#define perf_domain_span(pd) NULL +static inline bool sched_energy_enabled(void) { return false; } + +#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 8aea199a39b4..aa0de240fb41 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -55,6 +55,92 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt # define schedstat_val_or_zero(var) 0 #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_PSI +/* + * PSI tracks state that persists across sleeps, such as iowaits and + * memory stalls. As a result, it has to distinguish between sleeps, + * where a task's runnable state changes, and requeues, where a task + * and its state are being moved between CPUs and runqueues. + */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) +{ + int clear = 0, set = TSK_RUNNING; + + if (static_branch_likely(&psi_disabled)) + return; + + if (!wakeup || p->sched_psi_wake_requeue) { + if (p->flags & PF_MEMSTALL) + set |= TSK_MEMSTALL; + if (p->sched_psi_wake_requeue) + p->sched_psi_wake_requeue = 0; + } else { + if (p->in_iowait) + clear |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_dequeue(struct task_struct *p, bool sleep) +{ + int clear = TSK_RUNNING, set = 0; + + if (static_branch_likely(&psi_disabled)) + return; + + if (!sleep) { + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + } else { + if (p->in_iowait) + set |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_ttwu_dequeue(struct task_struct *p) +{ + if (static_branch_likely(&psi_disabled)) + return; + /* + * Is the task being migrated during a wakeup? Make sure to + * deregister its sleep-persistent psi states from the old + * queue, and let psi_enqueue() know it has to requeue. + */ + if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) { + struct rq_flags rf; + struct rq *rq; + int clear = 0; + + if (p->in_iowait) + clear |= TSK_IOWAIT; + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + + rq = __task_rq_lock(p, &rf); + psi_task_change(p, clear, 0); + p->sched_psi_wake_requeue = 1; + __task_rq_unlock(rq, &rf); + } +} + +static inline void psi_task_tick(struct rq *rq) +{ + if (static_branch_likely(&psi_disabled)) + return; + + if (unlikely(rq->curr->flags & PF_MEMSTALL)) + psi_memstall_tick(rq->curr, cpu_of(rq)); +} +#else /* CONFIG_PSI */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) {} +static inline void psi_dequeue(struct task_struct *p, bool sleep) {} +static inline void psi_ttwu_dequeue(struct task_struct *p) {} +static inline void psi_task_tick(struct rq *rq) {} +#endif /* CONFIG_PSI */ + #ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index 66b59ac77c22..e83a3f8449f6 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -93,7 +93,7 @@ long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait long ret = 0; raw_spin_lock_irqsave(&q->lock, flags); - if (unlikely(signal_pending_state(state, current))) { + if (signal_pending_state(state, current)) { /* * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one() * must not see us. diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 9d74371e4aad..ab7f371a3a17 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -201,6 +201,228 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) return 1; } +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) +DEFINE_STATIC_KEY_FALSE(sched_energy_present); +unsigned int sysctl_sched_energy_aware = 1; +DEFINE_MUTEX(sched_energy_mutex); +bool sched_energy_update; + +#ifdef CONFIG_PROC_SYSCTL +int sched_energy_aware_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret, state; + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + if (!ret && write) { + state = static_branch_unlikely(&sched_energy_present); + if (state != sysctl_sched_energy_aware) { + mutex_lock(&sched_energy_mutex); + sched_energy_update = 1; + rebuild_sched_domains(); + sched_energy_update = 0; + mutex_unlock(&sched_energy_mutex); + } + } + + return ret; +} +#endif + +static void free_pd(struct perf_domain *pd) +{ + struct perf_domain *tmp; + + while (pd) { + tmp = pd->next; + kfree(pd); + pd = tmp; + } +} + +static struct perf_domain *find_pd(struct perf_domain *pd, int cpu) +{ + while (pd) { + if (cpumask_test_cpu(cpu, perf_domain_span(pd))) + return pd; + pd = pd->next; + } + + return NULL; +} + +static struct perf_domain *pd_init(int cpu) +{ + struct em_perf_domain *obj = em_cpu_get(cpu); + struct perf_domain *pd; + + if (!obj) { + if (sched_debug()) + pr_info("%s: no EM found for CPU%d\n", __func__, cpu); + return NULL; + } + + pd = kzalloc(sizeof(*pd), GFP_KERNEL); + if (!pd) + return NULL; + pd->em_pd = obj; + + return pd; +} + +static void perf_domain_debug(const struct cpumask *cpu_map, + struct perf_domain *pd) +{ + if (!sched_debug() || !pd) + return; + + printk(KERN_DEBUG "root_domain %*pbl:", cpumask_pr_args(cpu_map)); + + while (pd) { + printk(KERN_CONT " pd%d:{ cpus=%*pbl nr_cstate=%d }", + cpumask_first(perf_domain_span(pd)), + cpumask_pr_args(perf_domain_span(pd)), + em_pd_nr_cap_states(pd->em_pd)); + pd = pd->next; + } + + printk(KERN_CONT "\n"); +} + +static void destroy_perf_domain_rcu(struct rcu_head *rp) +{ + struct perf_domain *pd; + + pd = container_of(rp, struct perf_domain, rcu); + free_pd(pd); +} + +static void sched_energy_set(bool has_eas) +{ + if (!has_eas && static_branch_unlikely(&sched_energy_present)) { + if (sched_debug()) + pr_info("%s: stopping EAS\n", __func__); + static_branch_disable_cpuslocked(&sched_energy_present); + } else if (has_eas && !static_branch_unlikely(&sched_energy_present)) { + if (sched_debug()) + pr_info("%s: starting EAS\n", __func__); + static_branch_enable_cpuslocked(&sched_energy_present); + } +} + +/* + * EAS can be used on a root domain if it meets all the following conditions: + * 1. an Energy Model (EM) is available; + * 2. the SD_ASYM_CPUCAPACITY flag is set in the sched_domain hierarchy. + * 3. the EM complexity is low enough to keep scheduling overheads low; + * 4. schedutil is driving the frequency of all CPUs of the rd; + * + * The complexity of the Energy Model is defined as: + * + * C = nr_pd * (nr_cpus + nr_cs) + * + * with parameters defined as: + * - nr_pd: the number of performance domains + * - nr_cpus: the number of CPUs + * - nr_cs: the sum of the number of capacity states of all performance + * domains (for example, on a system with 2 performance domains, + * with 10 capacity states each, nr_cs = 2 * 10 = 20). + * + * It is generally not a good idea to use such a model in the wake-up path on + * very complex platforms because of the associated scheduling overheads. The + * arbitrary constraint below prevents that. It makes EAS usable up to 16 CPUs + * with per-CPU DVFS and less than 8 capacity states each, for example. + */ +#define EM_MAX_COMPLEXITY 2048 + +extern struct cpufreq_governor schedutil_gov; +static bool build_perf_domains(const struct cpumask *cpu_map) +{ + int i, nr_pd = 0, nr_cs = 0, nr_cpus = cpumask_weight(cpu_map); + struct perf_domain *pd = NULL, *tmp; + int cpu = cpumask_first(cpu_map); + struct root_domain *rd = cpu_rq(cpu)->rd; + struct cpufreq_policy *policy; + struct cpufreq_governor *gov; + + if (!sysctl_sched_energy_aware) + goto free; + + /* EAS is enabled for asymmetric CPU capacity topologies. */ + if (!per_cpu(sd_asym_cpucapacity, cpu)) { + if (sched_debug()) { + pr_info("rd %*pbl: CPUs do not have asymmetric capacities\n", + cpumask_pr_args(cpu_map)); + } + goto free; + } + + for_each_cpu(i, cpu_map) { + /* Skip already covered CPUs. */ + if (find_pd(pd, i)) + continue; + + /* Do not attempt EAS if schedutil is not being used. */ + policy = cpufreq_cpu_get(i); + if (!policy) + goto free; + gov = policy->governor; + cpufreq_cpu_put(policy); + if (gov != &schedutil_gov) { + if (rd->pd) + pr_warn("rd %*pbl: Disabling EAS, schedutil is mandatory\n", + cpumask_pr_args(cpu_map)); + goto free; + } + + /* Create the new pd and add it to the local list. */ + tmp = pd_init(i); + if (!tmp) + goto free; + tmp->next = pd; + pd = tmp; + + /* + * Count performance domains and capacity states for the + * complexity check. + */ + nr_pd++; + nr_cs += em_pd_nr_cap_states(pd->em_pd); + } + + /* Bail out if the Energy Model complexity is too high. */ + if (nr_pd * (nr_cs + nr_cpus) > EM_MAX_COMPLEXITY) { + WARN(1, "rd %*pbl: Failed to start EAS, EM complexity is too high\n", + cpumask_pr_args(cpu_map)); + goto free; + } + + perf_domain_debug(cpu_map, pd); + + /* Attach the new list of performance domains to the root domain. */ + tmp = rd->pd; + rcu_assign_pointer(rd->pd, pd); + if (tmp) + call_rcu(&tmp->rcu, destroy_perf_domain_rcu); + + return !!pd; + +free: + free_pd(pd); + tmp = rd->pd; + rcu_assign_pointer(rd->pd, NULL); + if (tmp) + call_rcu(&tmp->rcu, destroy_perf_domain_rcu); + + return false; +} +#else +static void free_pd(struct perf_domain *pd) { } +#endif /* CONFIG_ENERGY_MODEL && CONFIG_CPU_FREQ_GOV_SCHEDUTIL*/ + static void free_rootdomain(struct rcu_head *rcu) { struct root_domain *rd = container_of(rcu, struct root_domain, rcu); @@ -211,6 +433,7 @@ static void free_rootdomain(struct rcu_head *rcu) free_cpumask_var(rd->rto_mask); free_cpumask_var(rd->online); free_cpumask_var(rd->span); + free_pd(rd->pd); kfree(rd); } @@ -248,7 +471,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd) raw_spin_unlock_irqrestore(&rq->lock, flags); if (old_rd) - call_rcu_sched(&old_rd->rcu, free_rootdomain); + call_rcu(&old_rd->rcu, free_rootdomain); } void sched_get_rd(struct root_domain *rd) @@ -261,7 +484,7 @@ void sched_put_rd(struct root_domain *rd) if (!atomic_dec_and_test(&rd->refcount)) return; - call_rcu_sched(&rd->rcu, free_rootdomain); + call_rcu(&rd->rcu, free_rootdomain); } static int init_rootdomain(struct root_domain *rd) @@ -397,7 +620,8 @@ DEFINE_PER_CPU(int, sd_llc_size); DEFINE_PER_CPU(int, sd_llc_id); DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); DEFINE_PER_CPU(struct sched_domain *, sd_numa); -DEFINE_PER_CPU(struct sched_domain *, sd_asym); +DEFINE_PER_CPU(struct sched_domain *, sd_asym_packing); +DEFINE_PER_CPU(struct sched_domain *, sd_asym_cpucapacity); DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity); static void update_top_cache_domain(int cpu) @@ -423,7 +647,10 @@ static void update_top_cache_domain(int cpu) 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); + rcu_assign_pointer(per_cpu(sd_asym_packing, cpu), sd); + + sd = lowest_flag_domain(cpu, SD_ASYM_CPUCAPACITY); + rcu_assign_pointer(per_cpu(sd_asym_cpucapacity, cpu), sd); } /* @@ -478,7 +705,7 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) } struct s_data { - struct sched_domain ** __percpu sd; + struct sched_domain * __percpu *sd; struct root_domain *rd; }; @@ -1133,7 +1360,6 @@ sd_init(struct sched_domain_topology_level *tl, .last_balance = jiffies, .balance_interval = sd_weight, - .smt_gain = 0, .max_newidle_lb_cost = 0, .next_decay_max_lb_cost = jiffies, .child = child, @@ -1164,7 +1390,6 @@ sd_init(struct sched_domain_topology_level *tl, 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; @@ -1337,7 +1562,7 @@ void sched_init_numa(void) int level = 0; int i, j, k; - sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + sched_domains_numa_distance = kzalloc(sizeof(int) * (nr_node_ids + 1), GFP_KERNEL); if (!sched_domains_numa_distance) return; @@ -1934,6 +2159,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { + bool __maybe_unused has_eas = false; int i, j, n; int new_topology; @@ -1961,8 +2187,8 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], /* Destroy deleted domains: */ for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_cur[i], doms_new[j]) - && dattrs_equal(dattr_cur, i, dattr_new, j)) + if (cpumask_equal(doms_cur[i], doms_new[j]) && + dattrs_equal(dattr_cur, i, dattr_new, j)) goto match1; } /* No match - a current sched domain not in new doms_new[] */ @@ -1982,8 +2208,8 @@ match1: /* Build new domains: */ for (i = 0; i < ndoms_new; i++) { for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_new[i], doms_cur[j]) - && dattrs_equal(dattr_new, i, dattr_cur, j)) + if (cpumask_equal(doms_new[i], doms_cur[j]) && + dattrs_equal(dattr_new, i, dattr_cur, j)) goto match2; } /* No match - add a new doms_new */ @@ -1992,6 +2218,24 @@ match2: ; } +#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) + /* Build perf. domains: */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n && !sched_energy_update; j++) { + if (cpumask_equal(doms_new[i], doms_cur[j]) && + cpu_rq(cpumask_first(doms_cur[j]))->rd->pd) { + has_eas = true; + goto match3; + } + } + /* No match - add perf. domains for a new rd */ + has_eas |= build_perf_domains(doms_new[i]); +match3: + ; + } + sched_energy_set(has_eas); +#endif + /* Remember the new sched domains: */ if (doms_cur != &fallback_doms) free_sched_domains(doms_cur, ndoms_cur); diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 5dd47f1103d1..6eb1f8efd221 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -264,7 +264,7 @@ long prepare_to_wait_event(struct wait_queue_head *wq_head, struct wait_queue_en long ret = 0; spin_lock_irqsave(&wq_head->lock, flags); - if (unlikely(signal_pending_state(state, current))) { + if (signal_pending_state(state, current)) { /* * Exclusive waiter must not fail if it was selected by wakeup, * it should "consume" the condition we were waiting for. |