diff options
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r-- | kernel/sched/fair.c | 4540 |
1 files changed, 2906 insertions, 1634 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c1217bfe5e81..e4a0b8bd941c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -20,9 +20,41 @@ * Adaptive scheduling granularity, math enhancements by Peter Zijlstra * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ -#include "sched.h" +#include <linux/energy_model.h> +#include <linux/mmap_lock.h> +#include <linux/hugetlb_inline.h> +#include <linux/jiffies.h> +#include <linux/mm_api.h> +#include <linux/highmem.h> +#include <linux/spinlock_api.h> +#include <linux/cpumask_api.h> +#include <linux/lockdep_api.h> +#include <linux/softirq.h> +#include <linux/refcount_api.h> +#include <linux/topology.h> +#include <linux/sched/clock.h> +#include <linux/sched/cond_resched.h> +#include <linux/sched/cputime.h> +#include <linux/sched/isolation.h> +#include <linux/sched/nohz.h> + +#include <linux/cpuidle.h> +#include <linux/interrupt.h> +#include <linux/memory-tiers.h> +#include <linux/mempolicy.h> +#include <linux/mutex_api.h> +#include <linux/profile.h> +#include <linux/psi.h> +#include <linux/ratelimit.h> +#include <linux/task_work.h> + +#include <asm/switch_to.h> + +#include <linux/sched/cond_resched.h> -#include <trace/events/sched.h> +#include "sched.h" +#include "stats.h" +#include "autogroup.h" /* * Targeted preemption latency for CPU-bound tasks: @@ -51,7 +83,7 @@ static unsigned int normalized_sysctl_sched_latency = 6000000ULL; * * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus)) */ -enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG; +unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG; /* * Minimal preemption granularity for CPU-bound tasks: @@ -62,6 +94,14 @@ unsigned int sysctl_sched_min_granularity = 750000ULL; static unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; /* + * Minimal preemption granularity for CPU-bound SCHED_IDLE tasks. + * Applies only when SCHED_IDLE tasks compete with normal tasks. + * + * (default: 0.75 msec) + */ +unsigned int sysctl_sched_idle_min_granularity = 750000ULL; + +/* * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity */ static unsigned int sched_nr_latency = 8; @@ -86,6 +126,19 @@ static unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +int sched_thermal_decay_shift; +static int __init setup_sched_thermal_decay_shift(char *str) +{ + int _shift = 0; + + if (kstrtoint(str, 0, &_shift)) + pr_warn("Unable to set scheduler thermal pressure decay shift parameter\n"); + + sched_thermal_decay_shift = clamp(_shift, 0, 10); + return 1; +} +__setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift); + #ifdef CONFIG_SMP /* * For asym packing, by default the lower numbered CPU has higher priority. @@ -102,6 +155,13 @@ int __weak arch_asym_cpu_priority(int cpu) */ #define fits_capacity(cap, max) ((cap) * 1280 < (max) * 1024) +/* + * The margin used when comparing CPU capacities. + * is 'cap1' noticeably greater than 'cap2' + * + * (default: ~5%) + */ +#define capacity_greater(cap1, cap2) ((cap1) * 1024 > (cap2) * 1078) #endif #ifdef CONFIG_CFS_BANDWIDTH @@ -115,7 +175,37 @@ int __weak arch_asym_cpu_priority(int cpu) * * (default: 5 msec, units: microseconds) */ -unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +static unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_fair_sysctls[] = { + { + .procname = "sched_child_runs_first", + .data = &sysctl_sched_child_runs_first, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_CFS_BANDWIDTH + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ONE, + }, +#endif + {} +}; + +static int __init sched_fair_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_fair_sysctls); + return 0; +} +late_initcall(sched_fair_sysctl_init); #endif static inline void update_load_add(struct load_weight *lw, unsigned long inc) @@ -178,7 +268,7 @@ static void update_sysctl(void) #undef SET_SYSCTL } -void sched_init_granularity(void) +void __init sched_init_granularity(void) { update_sysctl(); } @@ -218,22 +308,25 @@ static void __update_inv_weight(struct load_weight *lw) static u64 __calc_delta(u64 delta_exec, unsigned long weight, struct load_weight *lw) { u64 fact = scale_load_down(weight); + u32 fact_hi = (u32)(fact >> 32); int shift = WMULT_SHIFT; + int fs; __update_inv_weight(lw); - if (unlikely(fact >> 32)) { - while (fact >> 32) { - fact >>= 1; - shift--; - } + if (unlikely(fact_hi)) { + fs = fls(fact_hi); + shift -= fs; + fact >>= fs; } fact = mul_u32_u32(fact, lw->inv_weight); - while (fact >> 32) { - fact >>= 1; - shift--; + fact_hi = (u32)(fact >> 32); + if (fact_hi) { + fs = fls(fact_hi); + shift -= fs; + fact >>= fs; } return mul_u64_u32_shr(delta_exec, fact, shift); @@ -247,46 +340,11 @@ const struct sched_class fair_sched_class; */ #ifdef CONFIG_FAIR_GROUP_SCHED -static inline struct task_struct *task_of(struct sched_entity *se) -{ - SCHED_WARN_ON(!entity_is_task(se)); - return container_of(se, struct task_struct, se); -} /* Walk up scheduling entities hierarchy */ #define for_each_sched_entity(se) \ for (; se; se = se->parent) -static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) -{ - return p->se.cfs_rq; -} - -/* runqueue on which this entity is (to be) queued */ -static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) -{ - return se->cfs_rq; -} - -/* runqueue "owned" by this group */ -static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) -{ - return grp->my_q; -} - -static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) -{ - if (!path) - return; - - if (cfs_rq && task_group_is_autogroup(cfs_rq->tg)) - autogroup_path(cfs_rq->tg, path, len); - else if (cfs_rq && cfs_rq->tg->css.cgroup) - cgroup_path(cfs_rq->tg->css.cgroup, path, len); - else - strlcpy(path, "(null)", len); -} - static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); @@ -432,40 +490,27 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) } } -#else /* !CONFIG_FAIR_GROUP_SCHED */ - -static inline struct task_struct *task_of(struct sched_entity *se) +static int tg_is_idle(struct task_group *tg) { - return container_of(se, struct task_struct, se); + return tg->idle > 0; } -#define for_each_sched_entity(se) \ - for (; se; se = NULL) - -static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) +static int cfs_rq_is_idle(struct cfs_rq *cfs_rq) { - return &task_rq(p)->cfs; + return cfs_rq->idle > 0; } -static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) +static int se_is_idle(struct sched_entity *se) { - struct task_struct *p = task_of(se); - struct rq *rq = task_rq(p); - - return &rq->cfs; + if (entity_is_task(se)) + return task_has_idle_policy(task_of(se)); + return cfs_rq_is_idle(group_cfs_rq(se)); } -/* runqueue "owned" by this group */ -static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) -{ - return NULL; -} +#else /* !CONFIG_FAIR_GROUP_SCHED */ -static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) -{ - if (path) - strlcpy(path, "(null)", len); -} +#define for_each_sched_entity(se) \ + for (; se; se = NULL) static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { @@ -493,6 +538,21 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) { } +static inline int tg_is_idle(struct task_group *tg) +{ + return 0; +} + +static int cfs_rq_is_idle(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static int se_is_idle(struct sched_entity *se) +{ + return 0; +} + #endif /* CONFIG_FAIR_GROUP_SCHED */ static __always_inline @@ -520,12 +580,15 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) return min_vruntime; } -static inline int entity_before(struct sched_entity *a, +static inline bool entity_before(struct sched_entity *a, struct sched_entity *b) { return (s64)(a->vruntime - b->vruntime) < 0; } +#define __node_2_se(node) \ + rb_entry((node), struct sched_entity, run_node) + static void update_min_vruntime(struct cfs_rq *cfs_rq) { struct sched_entity *curr = cfs_rq->curr; @@ -541,8 +604,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) } if (leftmost) { /* non-empty tree */ - struct sched_entity *se; - se = rb_entry(leftmost, struct sched_entity, run_node); + struct sched_entity *se = __node_2_se(leftmost); if (!curr) vruntime = se->vruntime; @@ -551,11 +613,13 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) } /* ensure we never gain time by being placed backwards. */ - cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); -#ifndef CONFIG_64BIT - smp_wmb(); - cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; -#endif + u64_u32_store(cfs_rq->min_vruntime, + max_vruntime(cfs_rq->min_vruntime, vruntime)); +} + +static inline bool __entity_less(struct rb_node *a, const struct rb_node *b) +{ + return entity_before(__node_2_se(a), __node_2_se(b)); } /* @@ -563,32 +627,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) */ static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { - struct rb_node **link = &cfs_rq->tasks_timeline.rb_root.rb_node; - struct rb_node *parent = NULL; - struct sched_entity *entry; - bool leftmost = true; - - /* - * Find the right place in the rbtree: - */ - while (*link) { - parent = *link; - entry = rb_entry(parent, struct sched_entity, run_node); - /* - * We dont care about collisions. Nodes with - * the same key stay together. - */ - if (entity_before(se, entry)) { - link = &parent->rb_left; - } else { - link = &parent->rb_right; - leftmost = false; - } - } - - rb_link_node(&se->run_node, parent, link); - rb_insert_color_cached(&se->run_node, - &cfs_rq->tasks_timeline, leftmost); + rb_add_cached(&se->run_node, &cfs_rq->tasks_timeline, __entity_less); } static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) @@ -603,7 +642,7 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) if (!left) return NULL; - return rb_entry(left, struct sched_entity, run_node); + return __node_2_se(left); } static struct sched_entity *__pick_next_entity(struct sched_entity *se) @@ -613,7 +652,7 @@ static struct sched_entity *__pick_next_entity(struct sched_entity *se) if (!next) return NULL; - return rb_entry(next, struct sched_entity, run_node); + return __node_2_se(next); } #ifdef CONFIG_SCHED_DEBUG @@ -624,23 +663,17 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) if (!last) return NULL; - return rb_entry(last, struct sched_entity, run_node); + return __node_2_se(last); } /************************************************************** * Scheduling class statistics methods: */ -int sched_proc_update_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) +int sched_update_scaling(void) { - int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); unsigned int factor = get_update_sysctl_factor(); - if (ret || !write) - return ret; - sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency, sysctl_sched_min_granularity); @@ -682,6 +715,8 @@ static u64 __sched_period(unsigned long nr_running) return sysctl_sched_latency; } +static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq); + /* * We calculate the wall-time slice from the period by taking a part * proportional to the weight. @@ -690,23 +725,42 @@ static u64 __sched_period(unsigned long nr_running) */ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq); + unsigned int nr_running = cfs_rq->nr_running; + struct sched_entity *init_se = se; + unsigned int min_gran; + u64 slice; + + if (sched_feat(ALT_PERIOD)) + nr_running = rq_of(cfs_rq)->cfs.h_nr_running; + + slice = __sched_period(nr_running + !se->on_rq); for_each_sched_entity(se) { struct load_weight *load; struct load_weight lw; + struct cfs_rq *qcfs_rq; - cfs_rq = cfs_rq_of(se); - load = &cfs_rq->load; + qcfs_rq = cfs_rq_of(se); + load = &qcfs_rq->load; if (unlikely(!se->on_rq)) { - lw = cfs_rq->load; + lw = qcfs_rq->load; update_load_add(&lw, se->load.weight); load = &lw; } slice = __calc_delta(slice, se->load.weight, load); } + + if (sched_feat(BASE_SLICE)) { + if (se_is_idle(init_se) && !sched_idle_cfs_rq(cfs_rq)) + min_gran = sysctl_sched_idle_min_granularity; + else + min_gran = sysctl_sched_min_granularity; + + slice = max_t(u64, slice, min_gran); + } + return slice; } @@ -741,15 +795,11 @@ void init_entity_runnable_average(struct sched_entity *se) * nothing has been attached to the task group yet. */ if (entity_is_task(se)) - sa->runnable_load_avg = sa->load_avg = scale_load_down(se->load.weight); - - se->runnable_weight = se->load.weight; + sa->load_avg = scale_load_down(se->load.weight); /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } -static void attach_entity_cfs_rq(struct sched_entity *se); - /* * With new tasks being created, their initial util_avgs are extrapolated * based on the cfs_rq's current util_avg: @@ -784,18 +834,6 @@ void post_init_entity_util_avg(struct task_struct *p) long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))); long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2; - if (cap > 0) { - if (cfs_rq->avg.util_avg != 0) { - sa->util_avg = cfs_rq->avg.util_avg * se->load.weight; - sa->util_avg /= (cfs_rq->avg.load_avg + 1); - - if (sa->util_avg > cap) - sa->util_avg = cap; - } else { - sa->util_avg = cap; - } - } - if (p->sched_class != &fair_sched_class) { /* * For !fair tasks do: @@ -811,7 +849,19 @@ void post_init_entity_util_avg(struct task_struct *p) return; } - attach_entity_cfs_rq(se); + if (cap > 0) { + if (cfs_rq->avg.util_avg != 0) { + sa->util_avg = cfs_rq->avg.util_avg * se->load.weight; + sa->util_avg /= (cfs_rq->avg.load_avg + 1); + + if (sa->util_avg > cap) + sa->util_avg = cap; + } else { + sa->util_avg = cap; + } + } + + sa->runnable_avg = sa->util_avg; } #else /* !CONFIG_SMP */ @@ -821,7 +871,7 @@ void init_entity_runnable_average(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) +static void update_tg_load_avg(struct cfs_rq *cfs_rq) { } #endif /* CONFIG_SMP */ @@ -844,8 +894,13 @@ static void update_curr(struct cfs_rq *cfs_rq) curr->exec_start = now; - schedstat_set(curr->statistics.exec_max, - max(delta_exec, curr->statistics.exec_max)); + if (schedstat_enabled()) { + struct sched_statistics *stats; + + stats = __schedstats_from_se(curr); + __schedstat_set(stats->exec_max, + max(delta_exec, stats->exec_max)); + } curr->sum_exec_runtime += delta_exec; schedstat_add(cfs_rq->exec_clock, delta_exec); @@ -870,128 +925,70 @@ static void update_curr_fair(struct rq *rq) } static inline void -update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +update_stats_wait_start_fair(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u64 wait_start, prev_wait_start; + struct sched_statistics *stats; + struct task_struct *p = NULL; if (!schedstat_enabled()) return; - wait_start = rq_clock(rq_of(cfs_rq)); - prev_wait_start = schedstat_val(se->statistics.wait_start); + stats = __schedstats_from_se(se); - if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) && - likely(wait_start > prev_wait_start)) - wait_start -= prev_wait_start; + if (entity_is_task(se)) + p = task_of(se); - __schedstat_set(se->statistics.wait_start, wait_start); + __update_stats_wait_start(rq_of(cfs_rq), p, stats); } static inline void -update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) +update_stats_wait_end_fair(struct cfs_rq *cfs_rq, struct sched_entity *se) { - struct task_struct *p; - u64 delta; + struct sched_statistics *stats; + struct task_struct *p = NULL; if (!schedstat_enabled()) return; - delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start); + stats = __schedstats_from_se(se); - if (entity_is_task(se)) { + /* + * When the sched_schedstat changes from 0 to 1, some sched se + * maybe already in the runqueue, the se->statistics.wait_start + * will be 0.So it will let the delta wrong. We need to avoid this + * scenario. + */ + if (unlikely(!schedstat_val(stats->wait_start))) + return; + + if (entity_is_task(se)) p = task_of(se); - if (task_on_rq_migrating(p)) { - /* - * Preserve migrating task's wait time so wait_start - * time stamp can be adjusted to accumulate wait time - * prior to migration. - */ - __schedstat_set(se->statistics.wait_start, delta); - return; - } - trace_sched_stat_wait(p, delta); - } - __schedstat_set(se->statistics.wait_max, - max(schedstat_val(se->statistics.wait_max), delta)); - __schedstat_inc(se->statistics.wait_count); - __schedstat_add(se->statistics.wait_sum, delta); - __schedstat_set(se->statistics.wait_start, 0); + __update_stats_wait_end(rq_of(cfs_rq), p, stats); } static inline void -update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) +update_stats_enqueue_sleeper_fair(struct cfs_rq *cfs_rq, struct sched_entity *se) { + struct sched_statistics *stats; struct task_struct *tsk = NULL; - u64 sleep_start, block_start; if (!schedstat_enabled()) return; - sleep_start = schedstat_val(se->statistics.sleep_start); - block_start = schedstat_val(se->statistics.block_start); + stats = __schedstats_from_se(se); if (entity_is_task(se)) tsk = task_of(se); - if (sleep_start) { - u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start; - - if ((s64)delta < 0) - delta = 0; - - if (unlikely(delta > schedstat_val(se->statistics.sleep_max))) - __schedstat_set(se->statistics.sleep_max, delta); - - __schedstat_set(se->statistics.sleep_start, 0); - __schedstat_add(se->statistics.sum_sleep_runtime, delta); - - if (tsk) { - account_scheduler_latency(tsk, delta >> 10, 1); - trace_sched_stat_sleep(tsk, delta); - } - } - if (block_start) { - u64 delta = rq_clock(rq_of(cfs_rq)) - block_start; - - if ((s64)delta < 0) - delta = 0; - - if (unlikely(delta > schedstat_val(se->statistics.block_max))) - __schedstat_set(se->statistics.block_max, delta); - - __schedstat_set(se->statistics.block_start, 0); - __schedstat_add(se->statistics.sum_sleep_runtime, delta); - - if (tsk) { - if (tsk->in_iowait) { - __schedstat_add(se->statistics.iowait_sum, delta); - __schedstat_inc(se->statistics.iowait_count); - trace_sched_stat_iowait(tsk, delta); - } - - trace_sched_stat_blocked(tsk, delta); - - /* - * Blocking time is in units of nanosecs, so shift by - * 20 to get a milliseconds-range estimation of the - * amount of time that the task spent sleeping: - */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - profile_hits(SLEEP_PROFILING, - (void *)get_wchan(tsk), - delta >> 20); - } - account_scheduler_latency(tsk, delta >> 10, 0); - } - } + __update_stats_enqueue_sleeper(rq_of(cfs_rq), tsk, stats); } /* * Task is being enqueued - update stats: */ static inline void -update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +update_stats_enqueue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { if (!schedstat_enabled()) return; @@ -1001,14 +998,14 @@ update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * a dequeue/enqueue event is a NOP) */ if (se != cfs_rq->curr) - update_stats_wait_start(cfs_rq, se); + update_stats_wait_start_fair(cfs_rq, se); if (flags & ENQUEUE_WAKEUP) - update_stats_enqueue_sleeper(cfs_rq, se); + update_stats_enqueue_sleeper_fair(cfs_rq, se); } static inline void -update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +update_stats_dequeue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { if (!schedstat_enabled()) @@ -1019,16 +1016,19 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * waiting task: */ if (se != cfs_rq->curr) - update_stats_wait_end(cfs_rq, se); + update_stats_wait_end_fair(cfs_rq, se); if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) { struct task_struct *tsk = task_of(se); + unsigned int state; - if (tsk->state & TASK_INTERRUPTIBLE) - __schedstat_set(se->statistics.sleep_start, + /* XXX racy against TTWU */ + state = READ_ONCE(tsk->__state); + if (state & TASK_INTERRUPTIBLE) + __schedstat_set(tsk->stats.sleep_start, rq_clock(rq_of(cfs_rq))); - if (tsk->state & TASK_UNINTERRUPTIBLE) - __schedstat_set(se->statistics.block_start, + if (state & TASK_UNINTERRUPTIBLE) + __schedstat_set(tsk->stats.block_start, rq_clock(rq_of(cfs_rq))); } } @@ -1049,6 +1049,33 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ +#ifdef CONFIG_NUMA +#define NUMA_IMBALANCE_MIN 2 + +static inline long +adjust_numa_imbalance(int imbalance, int dst_running, int imb_numa_nr) +{ + /* + * Allow a NUMA imbalance if busy CPUs is less than the maximum + * threshold. Above this threshold, individual tasks may be contending + * for both memory bandwidth and any shared HT resources. This is an + * approximation as the number of running tasks may not be related to + * the number of busy CPUs due to sched_setaffinity. + */ + if (dst_running > imb_numa_nr) + return imbalance; + + /* + * Allow a small imbalance based on a simple pair of communicating + * tasks that remain local when the destination is lightly loaded. + */ + if (imbalance <= NUMA_IMBALANCE_MIN) + return 0; + + return imbalance; +} +#endif /* CONFIG_NUMA */ + #ifdef CONFIG_NUMA_BALANCING /* * Approximate time to scan a full NUMA task in ms. The task scan period is @@ -1064,6 +1091,12 @@ unsigned int sysctl_numa_balancing_scan_size = 256; /* Scan @scan_size MB every @scan_period after an initial @scan_delay in ms */ unsigned int sysctl_numa_balancing_scan_delay = 1000; +/* The page with hint page fault latency < threshold in ms is considered hot */ +unsigned int sysctl_numa_balancing_hot_threshold = MSEC_PER_SEC; + +/* Restrict the NUMA promotion throughput (MB/s) for each target node. */ +unsigned int sysctl_numa_balancing_promote_rate_limit = 65536; + struct numa_group { refcount_t refcount; @@ -1076,12 +1109,13 @@ struct numa_group { unsigned long total_faults; unsigned long max_faults_cpu; /* + * faults[] array is split into two regions: faults_mem and faults_cpu. + * * Faults_cpu is used to decide whether memory should move * towards the CPU. As a consequence, these stats are weighted * more by CPU use than by memory faults. */ - unsigned long *faults_cpu; - unsigned long faults[0]; + unsigned long faults[]; }; /* @@ -1091,7 +1125,7 @@ struct numa_group { static struct numa_group *deref_task_numa_group(struct task_struct *p) { return rcu_dereference_check(p->numa_group, p == current || - (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu))); + (lockdep_is_held(__rq_lockp(task_rq(p))) && !READ_ONCE(p->on_cpu))); } static struct numa_group *deref_curr_numa_group(struct task_struct *p) @@ -1121,7 +1155,7 @@ static unsigned int task_nr_scan_windows(struct task_struct *p) return rss / nr_scan_pages; } -/* For sanitys sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */ +/* For sanity's sake, never scan more PTEs than MAX_SCAN_WINDOW MB/sec. */ #define MAX_SCAN_WINDOW 2560 static unsigned int task_scan_min(struct task_struct *p) @@ -1254,8 +1288,8 @@ static inline unsigned long group_faults(struct task_struct *p, int nid) static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) { - return group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 0)] + - group->faults_cpu[task_faults_idx(NUMA_MEM, nid, 1)]; + return group->faults[task_faults_idx(NUMA_CPU, nid, 0)] + + group->faults[task_faults_idx(NUMA_CPU, nid, 1)]; } static inline unsigned long group_faults_priv(struct numa_group *ng) @@ -1296,10 +1330,10 @@ static bool numa_is_active_node(int nid, struct numa_group *ng) /* Handle placement on systems where not all nodes are directly connected. */ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, - int maxdist, bool task) + int lim_dist, bool task) { unsigned long score = 0; - int node; + int node, max_dist; /* * All nodes are directly connected, and the same distance @@ -1308,6 +1342,8 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, if (sched_numa_topology_type == NUMA_DIRECT) return 0; + /* sched_max_numa_distance may be changed in parallel. */ + max_dist = READ_ONCE(sched_max_numa_distance); /* * This code is called for each node, introducing N^2 complexity, * which should be ok given the number of nodes rarely exceeds 8. @@ -1320,7 +1356,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * The furthest away nodes in the system are not interesting * for placement; nid was already counted. */ - if (dist == sched_max_numa_distance || node == nid) + if (dist >= max_dist || node == nid) continue; /* @@ -1330,8 +1366,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * "hoplimit", only nodes closer by than "hoplimit" are part * of each group. Skip other nodes. */ - if (sched_numa_topology_type == NUMA_BACKPLANE && - dist >= maxdist) + if (sched_numa_topology_type == NUMA_BACKPLANE && dist >= lim_dist) continue; /* Add up the faults from nearby nodes. */ @@ -1349,8 +1384,8 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid, * This seems to result in good task placement. */ if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { - faults *= (sched_max_numa_distance - dist); - faults /= (sched_max_numa_distance - LOCAL_DISTANCE); + faults *= (max_dist - dist); + faults /= (max_dist - LOCAL_DISTANCE); } score += faults; @@ -1404,6 +1439,120 @@ static inline unsigned long group_weight(struct task_struct *p, int nid, return 1000 * faults / total_faults; } +/* + * If memory tiering mode is enabled, cpupid of slow memory page is + * used to record scan time instead of CPU and PID. When tiering mode + * is disabled at run time, the scan time (in cpupid) will be + * interpreted as CPU and PID. So CPU needs to be checked to avoid to + * access out of array bound. + */ +static inline bool cpupid_valid(int cpupid) +{ + return cpupid_to_cpu(cpupid) < nr_cpu_ids; +} + +/* + * For memory tiering mode, if there are enough free pages (more than + * enough watermark defined here) in fast memory node, to take full + * advantage of fast memory capacity, all recently accessed slow + * memory pages will be migrated to fast memory node without + * considering hot threshold. + */ +static bool pgdat_free_space_enough(struct pglist_data *pgdat) +{ + int z; + unsigned long enough_wmark; + + enough_wmark = max(1UL * 1024 * 1024 * 1024 >> PAGE_SHIFT, + pgdat->node_present_pages >> 4); + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + if (zone_watermark_ok(zone, 0, + wmark_pages(zone, WMARK_PROMO) + enough_wmark, + ZONE_MOVABLE, 0)) + return true; + } + return false; +} + +/* + * For memory tiering mode, when page tables are scanned, the scan + * time will be recorded in struct page in addition to make page + * PROT_NONE for slow memory page. So when the page is accessed, in + * hint page fault handler, the hint page fault latency is calculated + * via, + * + * hint page fault latency = hint page fault time - scan time + * + * The smaller the hint page fault latency, the higher the possibility + * for the page to be hot. + */ +static int numa_hint_fault_latency(struct page *page) +{ + int last_time, time; + + time = jiffies_to_msecs(jiffies); + last_time = xchg_page_access_time(page, time); + + return (time - last_time) & PAGE_ACCESS_TIME_MASK; +} + +/* + * For memory tiering mode, too high promotion/demotion throughput may + * hurt application latency. So we provide a mechanism to rate limit + * the number of pages that are tried to be promoted. + */ +static bool numa_promotion_rate_limit(struct pglist_data *pgdat, + unsigned long rate_limit, int nr) +{ + unsigned long nr_cand; + unsigned int now, start; + + now = jiffies_to_msecs(jiffies); + mod_node_page_state(pgdat, PGPROMOTE_CANDIDATE, nr); + nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE); + start = pgdat->nbp_rl_start; + if (now - start > MSEC_PER_SEC && + cmpxchg(&pgdat->nbp_rl_start, start, now) == start) + pgdat->nbp_rl_nr_cand = nr_cand; + if (nr_cand - pgdat->nbp_rl_nr_cand >= rate_limit) + return true; + return false; +} + +#define NUMA_MIGRATION_ADJUST_STEPS 16 + +static void numa_promotion_adjust_threshold(struct pglist_data *pgdat, + unsigned long rate_limit, + unsigned int ref_th) +{ + unsigned int now, start, th_period, unit_th, th; + unsigned long nr_cand, ref_cand, diff_cand; + + now = jiffies_to_msecs(jiffies); + th_period = sysctl_numa_balancing_scan_period_max; + start = pgdat->nbp_th_start; + if (now - start > th_period && + cmpxchg(&pgdat->nbp_th_start, start, now) == start) { + ref_cand = rate_limit * + sysctl_numa_balancing_scan_period_max / MSEC_PER_SEC; + nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE); + diff_cand = nr_cand - pgdat->nbp_th_nr_cand; + unit_th = ref_th * 2 / NUMA_MIGRATION_ADJUST_STEPS; + th = pgdat->nbp_threshold ? : ref_th; + if (diff_cand > ref_cand * 11 / 10) + th = max(th - unit_th, unit_th); + else if (diff_cand < ref_cand * 9 / 10) + th = min(th + unit_th, ref_th * 2); + pgdat->nbp_th_nr_cand = nr_cand; + pgdat->nbp_threshold = th; + } +} + bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int src_nid, int dst_cpu) { @@ -1411,9 +1560,44 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int dst_nid = cpu_to_node(dst_cpu); int last_cpupid, this_cpupid; + /* + * The pages in slow memory node should be migrated according + * to hot/cold instead of private/shared. + */ + if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && + !node_is_toptier(src_nid)) { + struct pglist_data *pgdat; + unsigned long rate_limit; + unsigned int latency, th, def_th; + + pgdat = NODE_DATA(dst_nid); + if (pgdat_free_space_enough(pgdat)) { + /* workload changed, reset hot threshold */ + pgdat->nbp_threshold = 0; + return true; + } + + def_th = sysctl_numa_balancing_hot_threshold; + rate_limit = sysctl_numa_balancing_promote_rate_limit << \ + (20 - PAGE_SHIFT); + numa_promotion_adjust_threshold(pgdat, rate_limit, def_th); + + th = pgdat->nbp_threshold ? : def_th; + latency = numa_hint_fault_latency(page); + if (latency >= th) + return false; + + return !numa_promotion_rate_limit(pgdat, rate_limit, + thp_nr_pages(page)); + } + this_cpupid = cpu_pid_to_cpupid(dst_cpu, current->pid); last_cpupid = page_cpupid_xchg_last(page, this_cpupid); + if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && + !node_is_toptier(src_nid) && !cpupid_valid(last_cpupid)) + return false; + /* * Allow first faults or private faults to migrate immediately early in * the lifetime of a task. The magic number 4 is based on waiting for @@ -1473,36 +1657,52 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4; } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); - -static unsigned long cpu_runnable_load(struct rq *rq) -{ - return cfs_rq_runnable_load_avg(&rq->cfs); -} +/* + * 'numa_type' describes the node at the moment of load balancing. + */ +enum numa_type { + /* The node has spare capacity that can be used to run more tasks. */ + node_has_spare = 0, + /* + * The node is fully used and the tasks don't compete for more CPU + * cycles. Nevertheless, some tasks might wait before running. + */ + node_fully_busy, + /* + * The node is overloaded and can't provide expected CPU cycles to all + * tasks. + */ + node_overloaded +}; /* Cached statistics for all CPUs within a node */ struct numa_stats { unsigned long load; - + unsigned long runnable; + unsigned long util; /* Total compute capacity of CPUs on a node */ unsigned long compute_capacity; + unsigned int nr_running; + unsigned int weight; + enum numa_type node_type; + int idle_cpu; }; -/* - * XXX borrowed from update_sg_lb_stats - */ -static void update_numa_stats(struct numa_stats *ns, int nid) +static inline bool is_core_idle(int cpu) { - int cpu; +#ifdef CONFIG_SCHED_SMT + int sibling; - memset(ns, 0, sizeof(*ns)); - for_each_cpu(cpu, cpumask_of_node(nid)) { - struct rq *rq = cpu_rq(cpu); + for_each_cpu(sibling, cpu_smt_mask(cpu)) { + if (cpu == sibling) + continue; - ns->load += cpu_runnable_load(rq); - ns->compute_capacity += capacity_of(cpu); + if (!idle_cpu(sibling)) + return false; } +#endif + return true; } struct task_numa_env { @@ -1510,6 +1710,7 @@ struct task_numa_env { int src_cpu, src_nid; int dst_cpu, dst_nid; + int imb_numa_nr; struct numa_stats src_stats, dst_stats; @@ -1521,20 +1722,130 @@ struct task_numa_env { int best_cpu; }; +static unsigned long cpu_load(struct rq *rq); +static unsigned long cpu_runnable(struct rq *rq); + +static inline enum +numa_type numa_classify(unsigned int imbalance_pct, + struct numa_stats *ns) +{ + if ((ns->nr_running > ns->weight) && + (((ns->compute_capacity * 100) < (ns->util * imbalance_pct)) || + ((ns->compute_capacity * imbalance_pct) < (ns->runnable * 100)))) + return node_overloaded; + + if ((ns->nr_running < ns->weight) || + (((ns->compute_capacity * 100) > (ns->util * imbalance_pct)) && + ((ns->compute_capacity * imbalance_pct) > (ns->runnable * 100)))) + return node_has_spare; + + return node_fully_busy; +} + +#ifdef CONFIG_SCHED_SMT +/* Forward declarations of select_idle_sibling helpers */ +static inline bool test_idle_cores(int cpu); +static inline int numa_idle_core(int idle_core, int cpu) +{ + if (!static_branch_likely(&sched_smt_present) || + idle_core >= 0 || !test_idle_cores(cpu)) + return idle_core; + + /* + * Prefer cores instead of packing HT siblings + * and triggering future load balancing. + */ + if (is_core_idle(cpu)) + idle_core = cpu; + + return idle_core; +} +#else +static inline int numa_idle_core(int idle_core, int cpu) +{ + return idle_core; +} +#endif + +/* + * Gather all necessary information to make NUMA balancing placement + * decisions that are compatible with standard load balancer. This + * borrows code and logic from update_sg_lb_stats but sharing a + * common implementation is impractical. + */ +static void update_numa_stats(struct task_numa_env *env, + struct numa_stats *ns, int nid, + bool find_idle) +{ + int cpu, idle_core = -1; + + memset(ns, 0, sizeof(*ns)); + ns->idle_cpu = -1; + + rcu_read_lock(); + for_each_cpu(cpu, cpumask_of_node(nid)) { + struct rq *rq = cpu_rq(cpu); + + ns->load += cpu_load(rq); + ns->runnable += cpu_runnable(rq); + ns->util += cpu_util_cfs(cpu); + ns->nr_running += rq->cfs.h_nr_running; + ns->compute_capacity += capacity_of(cpu); + + if (find_idle && !rq->nr_running && idle_cpu(cpu)) { + if (READ_ONCE(rq->numa_migrate_on) || + !cpumask_test_cpu(cpu, env->p->cpus_ptr)) + continue; + + if (ns->idle_cpu == -1) + ns->idle_cpu = cpu; + + idle_core = numa_idle_core(idle_core, cpu); + } + } + rcu_read_unlock(); + + ns->weight = cpumask_weight(cpumask_of_node(nid)); + + ns->node_type = numa_classify(env->imbalance_pct, ns); + + if (idle_core >= 0) + ns->idle_cpu = idle_core; +} + static void task_numa_assign(struct task_numa_env *env, struct task_struct *p, long imp) { struct rq *rq = cpu_rq(env->dst_cpu); - /* Bail out if run-queue part of active NUMA balance. */ - if (xchg(&rq->numa_migrate_on, 1)) + /* Check if run-queue part of active NUMA balance. */ + if (env->best_cpu != env->dst_cpu && xchg(&rq->numa_migrate_on, 1)) { + int cpu; + int start = env->dst_cpu; + + /* Find alternative idle CPU. */ + for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start) { + if (cpu == env->best_cpu || !idle_cpu(cpu) || + !cpumask_test_cpu(cpu, env->p->cpus_ptr)) { + continue; + } + + env->dst_cpu = cpu; + rq = cpu_rq(env->dst_cpu); + if (!xchg(&rq->numa_migrate_on, 1)) + goto assign; + } + + /* Failed to find an alternative idle CPU */ return; + } +assign: /* * Clear previous best_cpu/rq numa-migrate flag, since task now * found a better CPU to move/swap. */ - if (env->best_cpu != -1) { + if (env->best_cpu != -1 && env->best_cpu != env->dst_cpu) { rq = cpu_rq(env->best_cpu); WRITE_ONCE(rq->numa_migrate_on, 0); } @@ -1590,7 +1901,7 @@ static bool load_too_imbalanced(long src_load, long dst_load, * into account that it might be best if task running on the dst_cpu should * be exchanged with the source task */ -static void task_numa_compare(struct task_numa_env *env, +static bool task_numa_compare(struct task_numa_env *env, long taskimp, long groupimp, bool maymove) { struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p); @@ -1601,9 +1912,10 @@ static void task_numa_compare(struct task_numa_env *env, int dist = env->dist; long moveimp = imp; long load; + bool stopsearch = false; if (READ_ONCE(dst_rq->numa_migrate_on)) - return; + return false; rcu_read_lock(); cur = rcu_dereference(dst_rq->curr); @@ -1614,8 +1926,10 @@ static void task_numa_compare(struct task_numa_env *env, * Because we have preemption enabled we can get migrated around and * end try selecting ourselves (current == env->p) as a swap candidate. */ - if (cur == env->p) + if (cur == env->p) { + stopsearch = true; goto unlock; + } if (!cur) { if (maymove && moveimp >= env->best_imp) @@ -1624,23 +1938,41 @@ static void task_numa_compare(struct task_numa_env *env, goto unlock; } + /* Skip this swap candidate if cannot move to the source cpu. */ + if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr)) + goto unlock; + + /* + * Skip this swap candidate if it is not moving to its preferred + * node and the best task is. + */ + if (env->best_task && + env->best_task->numa_preferred_nid == env->src_nid && + cur->numa_preferred_nid != env->src_nid) { + goto unlock; + } + /* * "imp" is the fault differential for the source task between the * source and destination node. Calculate the total differential for * the source task and potential destination task. The more negative * the value is, the more remote accesses that would be expected to * be incurred if the tasks were swapped. - */ - /* Skip this swap candidate if cannot move to the source cpu */ - if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr)) - goto unlock; - - /* + * * If dst and source tasks are in the same NUMA group, or not * in any group then look only at task weights. */ cur_ng = rcu_dereference(cur->numa_group); if (cur_ng == p_ng) { + /* + * Do not swap within a group or between tasks that have + * no group if there is spare capacity. Swapping does + * not address the load imbalance and helps one task at + * the cost of punishing another. + */ + if (env->dst_stats.node_type == node_has_spare) + goto unlock; + imp = taskimp + task_weight(cur, env->src_nid, dist) - task_weight(cur, env->dst_nid, dist); /* @@ -1662,6 +1994,19 @@ static void task_numa_compare(struct task_numa_env *env, task_weight(cur, env->dst_nid, dist); } + /* Discourage picking a task already on its preferred node */ + if (cur->numa_preferred_nid == env->dst_nid) + imp -= imp / 16; + + /* + * Encourage picking a task that moves to its preferred node. + * This potentially makes imp larger than it's maximum of + * 1998 (see SMALLIMP and task_weight for why) but in this + * case, it does not matter. + */ + if (cur->numa_preferred_nid == env->src_nid) + imp += imp / 8; + if (maymove && moveimp > imp && moveimp > env->best_imp) { imp = moveimp; cur = NULL; @@ -1669,6 +2014,15 @@ static void task_numa_compare(struct task_numa_env *env, } /* + * Prefer swapping with a task moving to its preferred node over a + * task that is not. + */ + if (env->best_task && cur->numa_preferred_nid == env->src_nid && + env->best_task->numa_preferred_nid != env->src_nid) { + goto assign; + } + + /* * If the NUMA importance is less than SMALLIMP, * task migration might only result in ping pong * of tasks and also hurt performance due to cache @@ -1691,42 +2045,96 @@ static void task_numa_compare(struct task_numa_env *env, goto unlock; assign: - /* - * One idle CPU per node is evaluated for a task numa move. - * Call select_idle_sibling to maybe find a better one. - */ + /* Evaluate an idle CPU for a task numa move. */ if (!cur) { + int cpu = env->dst_stats.idle_cpu; + + /* Nothing cached so current CPU went idle since the search. */ + if (cpu < 0) + cpu = env->dst_cpu; + /* - * select_idle_siblings() uses an per-CPU cpumask that - * can be used from IRQ context. + * If the CPU is no longer truly idle and the previous best CPU + * is, keep using it. */ - local_irq_disable(); - env->dst_cpu = select_idle_sibling(env->p, env->src_cpu, - env->dst_cpu); - local_irq_enable(); + if (!idle_cpu(cpu) && env->best_cpu >= 0 && + idle_cpu(env->best_cpu)) { + cpu = env->best_cpu; + } + + env->dst_cpu = cpu; } task_numa_assign(env, cur, imp); + + /* + * If a move to idle is allowed because there is capacity or load + * balance improves then stop the search. While a better swap + * candidate may exist, a search is not free. + */ + if (maymove && !cur && env->best_cpu >= 0 && idle_cpu(env->best_cpu)) + stopsearch = true; + + /* + * If a swap candidate must be identified and the current best task + * moves its preferred node then stop the search. + */ + if (!maymove && env->best_task && + env->best_task->numa_preferred_nid == env->src_nid) { + stopsearch = true; + } unlock: rcu_read_unlock(); + + return stopsearch; } static void task_numa_find_cpu(struct task_numa_env *env, long taskimp, long groupimp) { - long src_load, dst_load, load; bool maymove = false; int cpu; - load = task_h_load(env->p); - dst_load = env->dst_stats.load + load; - src_load = env->src_stats.load - load; - /* - * If the improvement from just moving env->p direction is better - * than swapping tasks around, check if a move is possible. + * If dst node has spare capacity, then check if there is an + * imbalance that would be overruled by the load balancer. */ - maymove = !load_too_imbalanced(src_load, dst_load, env); + if (env->dst_stats.node_type == node_has_spare) { + unsigned int imbalance; + int src_running, dst_running; + + /* + * Would movement cause an imbalance? Note that if src has + * more running tasks that the imbalance is ignored as the + * move improves the imbalance from the perspective of the + * CPU load balancer. + * */ + src_running = env->src_stats.nr_running - 1; + dst_running = env->dst_stats.nr_running + 1; + imbalance = max(0, dst_running - src_running); + imbalance = adjust_numa_imbalance(imbalance, dst_running, + env->imb_numa_nr); + + /* Use idle CPU if there is no imbalance */ + if (!imbalance) { + maymove = true; + if (env->dst_stats.idle_cpu >= 0) { + env->dst_cpu = env->dst_stats.idle_cpu; + task_numa_assign(env, NULL, 0); + return; + } + } + } else { + long src_load, dst_load, load; + /* + * If the improvement from just moving env->p direction is better + * than swapping tasks around, check if a move is possible. + */ + load = task_h_load(env->p); + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + maymove = !load_too_imbalanced(src_load, dst_load, env); + } for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ @@ -1734,7 +2142,8 @@ static void task_numa_find_cpu(struct task_numa_env *env, continue; env->dst_cpu = cpu; - task_numa_compare(env, taskimp, groupimp, maymove); + if (task_numa_compare(env, taskimp, groupimp, maymove)) + break; } } @@ -1769,8 +2178,10 @@ static int task_numa_migrate(struct task_struct *p) */ rcu_read_lock(); sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); - if (sd) + if (sd) { env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + env.imb_numa_nr = sd->imb_numa_nr; + } rcu_read_unlock(); /* @@ -1788,10 +2199,10 @@ static int task_numa_migrate(struct task_struct *p) dist = env.dist = node_distance(env.src_nid, env.dst_nid); taskweight = task_weight(p, env.src_nid, dist); groupweight = group_weight(p, env.src_nid, dist); - update_numa_stats(&env.src_stats, env.src_nid); + update_numa_stats(&env, &env.src_stats, env.src_nid, false); taskimp = task_weight(p, env.dst_nid, dist) - taskweight; groupimp = group_weight(p, env.dst_nid, dist) - groupweight; - update_numa_stats(&env.dst_stats, env.dst_nid); + update_numa_stats(&env, &env.dst_stats, env.dst_nid, true); /* Try to find a spot on the preferred nid. */ task_numa_find_cpu(&env, taskimp, groupimp); @@ -1805,7 +2216,7 @@ static int task_numa_migrate(struct task_struct *p) */ ng = deref_curr_numa_group(p); if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) { - for_each_online_node(nid) { + for_each_node_state(nid, N_CPU) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1824,7 +2235,7 @@ static int task_numa_migrate(struct task_struct *p) env.dist = dist; env.dst_nid = nid; - update_numa_stats(&env.dst_stats, env.dst_nid); + update_numa_stats(&env, &env.dst_stats, env.dst_nid, true); task_numa_find_cpu(&env, taskimp, groupimp); } } @@ -1848,15 +2259,17 @@ static int task_numa_migrate(struct task_struct *p) } /* No better CPU than the current one was found. */ - if (env.best_cpu == -1) + if (env.best_cpu == -1) { + trace_sched_stick_numa(p, env.src_cpu, NULL, -1); return -EAGAIN; + } best_rq = cpu_rq(env.best_cpu); if (env.best_task == NULL) { ret = migrate_task_to(p, env.best_cpu); WRITE_ONCE(best_rq->numa_migrate_on, 0); if (ret != 0) - trace_sched_stick_numa(p, env.src_cpu, env.best_cpu); + trace_sched_stick_numa(p, env.src_cpu, NULL, env.best_cpu); return ret; } @@ -1864,7 +2277,7 @@ static int task_numa_migrate(struct task_struct *p) WRITE_ONCE(best_rq->numa_migrate_on, 0); if (ret != 0) - trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task)); + trace_sched_stick_numa(p, env.src_cpu, env.best_task, env.best_cpu); put_task_struct(env.best_task); return ret; } @@ -1891,7 +2304,7 @@ static void numa_migrate_preferred(struct task_struct *p) } /* - * Find out how many nodes on the workload is actively running on. Do this by + * Find out how many nodes the workload is actively running on. Do this by * tracking the nodes from which NUMA hinting faults are triggered. This can * be different from the set of nodes where the workload's memory is currently * located. @@ -1901,13 +2314,13 @@ static void numa_group_count_active_nodes(struct numa_group *numa_group) unsigned long faults, max_faults = 0; int nid, active_nodes = 0; - for_each_online_node(nid) { + for_each_node_state(nid, N_CPU) { faults = group_faults_cpu(numa_group, nid); if (faults > max_faults) max_faults = faults; } - for_each_online_node(nid) { + for_each_node_state(nid, N_CPU) { faults = group_faults_cpu(numa_group, nid); if (faults * ACTIVE_NODE_FRACTION > max_faults) active_nodes++; @@ -1945,7 +2358,7 @@ static void update_task_scan_period(struct task_struct *p, /* * If there were no record hinting faults then either the task is - * completely idle or all activity is areas that are not of interest + * completely idle or all activity is in areas that are not of interest * to automatic numa balancing. Related to that, if there were failed * migration then it implies we are migrating too quickly or the local * node is overloaded. In either case, scan slower @@ -2061,7 +2474,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) dist = sched_max_numa_distance; - for_each_online_node(node) { + for_each_node_state(node, N_CPU) { score = group_weight(p, node, dist); if (score > max_score) { max_score = score; @@ -2080,7 +2493,7 @@ static int preferred_group_nid(struct task_struct *p, int nid) * inside the highest scoring group of nodes. The nodemask tricks * keep the complexity of the search down. */ - nodes = node_online_map; + nodes = node_states[N_CPU]; for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) { unsigned long max_faults = 0; nodemask_t max_group = NODE_MASK_NONE; @@ -2202,7 +2615,7 @@ static void task_numa_placement(struct task_struct *p) * is at the beginning of the numa_faults array. */ ng->faults[mem_idx] += diff; - ng->faults_cpu[mem_idx] += f_diff; + ng->faults[cpu_idx] += f_diff; ng->total_faults += diff; group_faults += ng->faults[mem_idx]; } @@ -2219,6 +2632,21 @@ static void task_numa_placement(struct task_struct *p) } } + /* Cannot migrate task to CPU-less node */ + if (max_nid != NUMA_NO_NODE && !node_state(max_nid, N_CPU)) { + int near_nid = max_nid; + int distance, near_distance = INT_MAX; + + for_each_node_state(nid, N_CPU) { + distance = node_distance(max_nid, nid); + if (distance < near_distance) { + near_nid = nid; + near_distance = distance; + } + } + max_nid = near_nid; + } + if (ng) { numa_group_count_active_nodes(ng); spin_unlock_irq(group_lock); @@ -2256,7 +2684,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (unlikely(!deref_curr_numa_group(p))) { unsigned int size = sizeof(struct numa_group) + - 4*nr_node_ids*sizeof(unsigned long); + NR_NUMA_HINT_FAULT_STATS * + nr_node_ids * sizeof(unsigned long); grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); if (!grp) @@ -2267,9 +2696,6 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, grp->max_faults_cpu = 0; spin_lock_init(&grp->lock); grp->gid = p->pid; - /* Second half of the array tracks nids where faults happen */ - grp->faults_cpu = grp->faults + NR_NUMA_HINT_FAULT_TYPES * - nr_node_ids; for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) grp->faults[i] = p->numa_faults[i]; @@ -2326,7 +2752,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!join) return; - BUG_ON(irqs_disabled()); + WARN_ON_ONCE(irqs_disabled()); double_lock_irq(&my_grp->lock, &grp->lock); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { @@ -2353,7 +2779,7 @@ no_join: } /* - * Get rid of NUMA staticstics associated with a task (either current or dead). + * Get rid of NUMA statistics associated with a task (either current or dead). * If @final is set, the task is dead and has reached refcount zero, so we can * safely free all relevant data structures. Otherwise, there might be * concurrent reads from places like load balancing and procfs, and we should @@ -2411,6 +2837,15 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (!p->mm) return; + /* + * NUMA faults statistics are unnecessary for the slow memory + * node for memory tiering mode. + */ + if (!node_is_toptier(mem_node) && + (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING || + !cpupid_valid(last_cpupid))) + return; + /* Allocate buffer to track faults on a per-node basis */ if (unlikely(!p->numa_faults)) { int size = sizeof(*p->numa_faults) * @@ -2491,6 +2926,7 @@ static void task_numa_work(struct callback_head *work) struct task_struct *p = current; struct mm_struct *mm = p->mm; u64 runtime = p->se.sum_exec_runtime; + MA_STATE(mas, &mm->mm_mt, 0, 0); struct vm_area_struct *vma; unsigned long start, end; unsigned long nr_pte_updates = 0; @@ -2545,15 +2981,18 @@ static void task_numa_work(struct callback_head *work) return; - if (!down_read_trylock(&mm->mmap_sem)) + if (!mmap_read_trylock(mm)) return; - vma = find_vma(mm, start); + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); if (!vma) { reset_ptenuma_scan(p); start = 0; - vma = mm->mmap; + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); } - for (; vma; vma = vma->vm_next) { + + for (; vma; vma = mas_find(&mas, ULONG_MAX)) { if (!vma_migratable(vma) || !vma_policy_mof(vma) || is_vm_hugetlb_page(vma) || (vma->vm_flags & VM_MIXEDMAP)) { continue; @@ -2573,7 +3012,7 @@ static void task_numa_work(struct callback_head *work) * Skip inaccessible VMAs to avoid any confusion between * PROT_NONE and NUMA hinting ptes */ - if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))) + if (!vma_is_accessible(vma)) continue; do { @@ -2613,7 +3052,7 @@ out: mm->numa_scan_offset = start; else reset_ptenuma_scan(p); - up_read(&mm->mmap_sem); + mmap_read_unlock(mm); /* * Make sure tasks use at least 32x as much time to run other code @@ -2642,9 +3081,12 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) p->node_stamp = 0; p->numa_scan_seq = mm ? mm->numa_scan_seq : 0; p->numa_scan_period = sysctl_numa_balancing_scan_delay; + p->numa_migrate_retry = 0; /* Protect against double add, see task_tick_numa and task_numa_work */ p->numa_work.next = &p->numa_work; p->numa_faults = NULL; + p->numa_pages_migrated = 0; + p->total_numa_faults = 0; RCU_INIT_POINTER(p->numa_group, NULL); p->last_task_numa_placement = 0; p->last_sum_exec_runtime = 0; @@ -2682,7 +3124,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) /* * We don't care about NUMA placement if we don't have memory. */ - if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work) + if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work) return; /* @@ -2700,7 +3142,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) curr->node_stamp += period; if (!time_before(jiffies, curr->mm->numa_next_scan)) - task_work_add(curr, work, true); + task_work_add(curr, work, TWA_RESUME); } } @@ -2770,6 +3212,8 @@ account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) } #endif cfs_rq->nr_running++; + if (se_is_idle(se)) + cfs_rq->idle_nr_running++; } static void @@ -2783,6 +3227,8 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) } #endif cfs_rq->nr_running--; + if (se_is_idle(se)) + cfs_rq->idle_nr_running--; } /* @@ -2835,25 +3281,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) #ifdef CONFIG_SMP static inline void -enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - cfs_rq->runnable_weight += se->runnable_weight; - - cfs_rq->avg.runnable_load_avg += se->avg.runnable_load_avg; - cfs_rq->avg.runnable_load_sum += se_runnable(se) * se->avg.runnable_load_sum; -} - -static inline void -dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - cfs_rq->runnable_weight -= se->runnable_weight; - - sub_positive(&cfs_rq->avg.runnable_load_avg, se->avg.runnable_load_avg); - sub_positive(&cfs_rq->avg.runnable_load_sum, - se_runnable(se) * se->avg.runnable_load_sum); -} - -static inline void enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { cfs_rq->avg.load_avg += se->avg.load_avg; @@ -2865,48 +3292,42 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); sub_positive(&cfs_rq->avg.load_sum, se_weight(se) * se->avg.load_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } #else static inline void -enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } -static inline void -dequeue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } -static inline void enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } static inline void dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { } #endif static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, - unsigned long weight, unsigned long runnable) + unsigned long weight) { if (se->on_rq) { /* commit outstanding execution time */ if (cfs_rq->curr == se) update_curr(cfs_rq); - account_entity_dequeue(cfs_rq, se); - dequeue_runnable_load_avg(cfs_rq, se); + update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); - se->runnable_weight = runnable; update_load_set(&se->load, weight); #ifdef CONFIG_SMP do { - u32 divider = LOAD_AVG_MAX - 1024 + se->avg.period_contrib; + u32 divider = get_pelt_divider(&se->avg); se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider); - se->avg.runnable_load_avg = - div_u64(se_runnable(se) * se->avg.runnable_load_sum, divider); } while (0); #endif enqueue_load_avg(cfs_rq, se); - if (se->on_rq) { - account_entity_enqueue(cfs_rq, se); - enqueue_runnable_load_avg(cfs_rq, se); - } + if (se->on_rq) + update_load_add(&cfs_rq->load, se->load.weight); + } void reweight_task(struct task_struct *p, int prio) @@ -2916,10 +3337,12 @@ void reweight_task(struct task_struct *p, int prio) struct load_weight *load = &se->load; unsigned long weight = scale_load(sched_prio_to_weight[prio]); - reweight_entity(cfs_rq, se, weight, weight); + reweight_entity(cfs_rq, se, weight); load->inv_weight = sched_prio_to_wmult[prio]; } +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); + #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_SMP /* @@ -2931,7 +3354,7 @@ void reweight_task(struct task_struct *p, int prio) * * tg->weight * grq->load.weight * ge->load.weight = ----------------------------- (1) - * \Sum grq->load.weight + * \Sum grq->load.weight * * Now, because computing that sum is prohibitively expensive to compute (been * there, done that) we approximate it with this average stuff. The average @@ -2945,7 +3368,7 @@ void reweight_task(struct task_struct *p, int prio) * * tg->weight * grq->avg.load_avg * ge->load.weight = ------------------------------ (3) - * tg->load_avg + * tg->load_avg * * Where: tg->load_avg ~= \Sum grq->avg.load_avg * @@ -2961,7 +3384,7 @@ void reweight_task(struct task_struct *p, int prio) * * tg->weight * grq->load.weight * ge->load.weight = ----------------------------- = tg->weight (4) - * grp->load.weight + * grp->load.weight * * That is, the sum collapses because all other CPUs are idle; the UP scenario. * @@ -2980,7 +3403,7 @@ void reweight_task(struct task_struct *p, int prio) * * tg->weight * grq->load.weight * ge->load.weight = ----------------------------- (6) - * tg_load_avg' + * tg_load_avg' * * Where: * @@ -3028,54 +3451,8 @@ static long calc_group_shares(struct cfs_rq *cfs_rq) */ return clamp_t(long, shares, MIN_SHARES, tg_shares); } - -/* - * This calculates the effective runnable weight for a group entity based on - * the group entity weight calculated above. - * - * Because of the above approximation (2), our group entity weight is - * an load_avg based ratio (3). This means that it includes blocked load and - * does not represent the runnable weight. - * - * Approximate the group entity's runnable weight per ratio from the group - * runqueue: - * - * grq->avg.runnable_load_avg - * ge->runnable_weight = ge->load.weight * -------------------------- (7) - * grq->avg.load_avg - * - * However, analogous to above, since the avg numbers are slow, this leads to - * transients in the from-idle case. Instead we use: - * - * ge->runnable_weight = ge->load.weight * - * - * max(grq->avg.runnable_load_avg, grq->runnable_weight) - * ----------------------------------------------------- (8) - * max(grq->avg.load_avg, grq->load.weight) - * - * Where these max() serve both to use the 'instant' values to fix the slow - * from-idle and avoid the /0 on to-idle, similar to (6). - */ -static long calc_group_runnable(struct cfs_rq *cfs_rq, long shares) -{ - long runnable, load_avg; - - load_avg = max(cfs_rq->avg.load_avg, - scale_load_down(cfs_rq->load.weight)); - - runnable = max(cfs_rq->avg.runnable_load_avg, - scale_load_down(cfs_rq->runnable_weight)); - - runnable *= shares; - if (load_avg) - runnable /= load_avg; - - return clamp_t(long, runnable, MIN_SHARES, shares); -} #endif /* CONFIG_SMP */ -static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); - /* * Recomputes the group entity based on the current state of its group * runqueue. @@ -3083,7 +3460,7 @@ static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); static void update_cfs_group(struct sched_entity *se) { struct cfs_rq *gcfs_rq = group_cfs_rq(se); - long shares, runnable; + long shares; if (!gcfs_rq) return; @@ -3092,16 +3469,15 @@ static void update_cfs_group(struct sched_entity *se) return; #ifndef CONFIG_SMP - runnable = shares = READ_ONCE(gcfs_rq->tg->shares); + shares = READ_ONCE(gcfs_rq->tg->shares); if (likely(se->load.weight == shares)) return; #else shares = calc_group_shares(gcfs_rq); - runnable = calc_group_runnable(gcfs_rq, shares); #endif - reweight_entity(cfs_rq_of(se), se, shares, runnable); + reweight_entity(cfs_rq_of(se), se, shares); } #else /* CONFIG_FAIR_GROUP_SCHED */ @@ -3127,18 +3503,85 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) * As is, the util number is not freq-invariant (we'd have to * implement arch_scale_freq_capacity() for that). * - * See cpu_util(). + * See cpu_util_cfs(). */ cpufreq_update_util(rq, flags); } } #ifdef CONFIG_SMP +static inline bool load_avg_is_decayed(struct sched_avg *sa) +{ + if (sa->load_sum) + return false; + + if (sa->util_sum) + return false; + + if (sa->runnable_sum) + return false; + + /* + * _avg must be null when _sum are null because _avg = _sum / divider + * Make sure that rounding and/or propagation of PELT values never + * break this. + */ + SCHED_WARN_ON(sa->load_avg || + sa->util_avg || + sa->runnable_avg); + + return true; +} + +static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) +{ + return u64_u32_load_copy(cfs_rq->avg.last_update_time, + cfs_rq->last_update_time_copy); +} #ifdef CONFIG_FAIR_GROUP_SCHED +/* + * Because list_add_leaf_cfs_rq always places a child cfs_rq on the list + * immediately before a parent cfs_rq, and cfs_rqs are removed from the list + * bottom-up, we only have to test whether the cfs_rq before us on the list + * is our child. + * If cfs_rq is not on the list, test whether a child needs its to be added to + * connect a branch to the tree * (see list_add_leaf_cfs_rq() for details). + */ +static inline bool child_cfs_rq_on_list(struct cfs_rq *cfs_rq) +{ + struct cfs_rq *prev_cfs_rq; + struct list_head *prev; + + if (cfs_rq->on_list) { + prev = cfs_rq->leaf_cfs_rq_list.prev; + } else { + struct rq *rq = rq_of(cfs_rq); + + prev = rq->tmp_alone_branch; + } + + prev_cfs_rq = container_of(prev, struct cfs_rq, leaf_cfs_rq_list); + + return (prev_cfs_rq->tg->parent == cfs_rq->tg); +} + +static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->load.weight) + return false; + + if (!load_avg_is_decayed(&cfs_rq->avg)) + return false; + + if (child_cfs_rq_on_list(cfs_rq)) + return false; + + return true; +} + /** * update_tg_load_avg - update the tg's load avg * @cfs_rq: the cfs_rq whose avg changed - * @force: update regardless of how small the difference * * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load. * However, because tg->load_avg is a global value there are performance @@ -3150,7 +3593,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) * * Updating tg's load_avg is necessary before update_cfs_share(). */ -static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) +static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) { long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib; @@ -3160,7 +3603,7 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) if (cfs_rq->tg == &root_task_group) return; - if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) { + if (abs(delta) > cfs_rq->tg_load_avg_contrib / 64) { atomic_long_add(delta, &cfs_rq->tg->load_avg); cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg; } @@ -3190,32 +3633,13 @@ void set_task_rq_fair(struct sched_entity *se, if (!(se->avg.last_update_time && prev)) return; -#ifndef CONFIG_64BIT - { - u64 p_last_update_time_copy; - u64 n_last_update_time_copy; - - do { - p_last_update_time_copy = prev->load_last_update_time_copy; - n_last_update_time_copy = next->load_last_update_time_copy; + p_last_update_time = cfs_rq_last_update_time(prev); + n_last_update_time = cfs_rq_last_update_time(next); - smp_rmb(); - - p_last_update_time = prev->avg.last_update_time; - n_last_update_time = next->avg.last_update_time; - - } while (p_last_update_time != p_last_update_time_copy || - n_last_update_time != n_last_update_time_copy); - } -#else - 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, se); se->avg.last_update_time = n_last_update_time; } - /* * When on migration a sched_entity joins/leaves the PELT hierarchy, we need to * propagate its contribution. The key to this propagation is the invariant @@ -3226,11 +3650,11 @@ void set_task_rq_fair(struct sched_entity *se, * _IFF_ we look at the pure running and runnable sums. Because they * represent the very same entity, just at different points in the hierarchy. * - * Per the above update_tg_cfs_util() is trivial and simply copies the running - * sum over (but still wrong, because the group entity and group rq do not have - * their PELT windows aligned). + * Per the above update_tg_cfs_util() and update_tg_cfs_runnable() are trivial + * and simply copies the running/runnable sum over (but still wrong, because + * the group entity and group rq do not have their PELT windows aligned). * - * However, update_tg_cfs_runnable() is more complex. So we have: + * However, update_tg_cfs_load() is more complex. So we have: * * ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg (2) * @@ -3283,60 +3707,102 @@ void set_task_rq_fair(struct sched_entity *se, * XXX: only do this for the part of runnable > running ? * */ - static inline void update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long delta = gcfs_rq->avg.util_avg - se->avg.util_avg; + long delta_sum, delta_avg = gcfs_rq->avg.util_avg - se->avg.util_avg; + u32 new_sum, divider; /* Nothing to update */ - if (!delta) + if (!delta_avg) return; /* - * The relation between sum and avg is: - * - * LOAD_AVG_MAX - 1024 + sa->period_contrib - * - * however, the PELT windows are not aligned between grq and gse. + * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. + * See ___update_load_avg() for details. */ + divider = get_pelt_divider(&cfs_rq->avg); + /* Set new sched_entity's utilization */ se->avg.util_avg = gcfs_rq->avg.util_avg; - se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX; + new_sum = se->avg.util_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.util_sum; + se->avg.util_sum = new_sum; /* Update parent cfs_rq utilization */ - add_positive(&cfs_rq->avg.util_avg, delta); - cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX; + add_positive(&cfs_rq->avg.util_avg, delta_avg); + add_positive(&cfs_rq->avg.util_sum, delta_sum); + + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); } static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { + long delta_sum, delta_avg = gcfs_rq->avg.runnable_avg - se->avg.runnable_avg; + u32 new_sum, divider; + + /* Nothing to update */ + if (!delta_avg) + return; + + /* + * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. + * See ___update_load_avg() for details. + */ + divider = get_pelt_divider(&cfs_rq->avg); + + /* Set new sched_entity's runnable */ + se->avg.runnable_avg = gcfs_rq->avg.runnable_avg; + new_sum = se->avg.runnable_avg * divider; + delta_sum = (long)new_sum - (long)se->avg.runnable_sum; + se->avg.runnable_sum = new_sum; + + /* Update parent cfs_rq runnable */ + add_positive(&cfs_rq->avg.runnable_avg, delta_avg); + add_positive(&cfs_rq->avg.runnable_sum, delta_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); +} + +static inline void +update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) +{ long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; - unsigned long runnable_load_avg, load_avg; - u64 runnable_load_sum, load_sum = 0; + unsigned long load_avg; + u64 load_sum = 0; s64 delta_sum; + u32 divider; if (!runnable_sum) return; gcfs_rq->prop_runnable_sum = 0; + /* + * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. + * See ___update_load_avg() for details. + */ + divider = get_pelt_divider(&cfs_rq->avg); + if (runnable_sum >= 0) { /* * Add runnable; clip at LOAD_AVG_MAX. Reflects that until * the CPU is saturated running == runnable. */ runnable_sum += se->avg.load_sum; - runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX); + runnable_sum = min_t(long, runnable_sum, divider); } else { /* * Estimate the new unweighted runnable_sum of the gcfs_rq by * assuming all tasks are equally runnable. */ if (scale_load_down(gcfs_rq->load.weight)) { - load_sum = div_s64(gcfs_rq->avg.load_sum, + load_sum = div_u64(gcfs_rq->avg.load_sum, scale_load_down(gcfs_rq->load.weight)); } @@ -3353,30 +3819,22 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; runnable_sum = max(runnable_sum, running_sum); - load_sum = (s64)se_weight(se) * runnable_sum; - load_avg = div_s64(load_sum, LOAD_AVG_MAX); + load_sum = se_weight(se) * runnable_sum; + load_avg = div_u64(load_sum, divider); - delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; delta_avg = load_avg - se->avg.load_avg; + if (!delta_avg) + return; + + delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; se->avg.load_sum = runnable_sum; se->avg.load_avg = load_avg; add_positive(&cfs_rq->avg.load_avg, delta_avg); add_positive(&cfs_rq->avg.load_sum, delta_sum); - - runnable_load_sum = (s64)se_runnable(se) * runnable_sum; - runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX); - - if (se->on_rq) { - delta_sum = runnable_load_sum - - se_weight(se) * se->avg.runnable_load_sum; - delta_avg = runnable_load_avg - se->avg.runnable_load_avg; - add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg); - add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum); - } - - se->avg.runnable_load_sum = runnable_sum; - se->avg.runnable_load_avg = runnable_load_avg; + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum, + cfs_rq->avg.load_avg * PELT_MIN_DIVIDER); } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3405,6 +3863,7 @@ static inline int propagate_entity_load_avg(struct sched_entity *se) update_tg_cfs_util(cfs_rq, se, gcfs_rq); update_tg_cfs_runnable(cfs_rq, se, gcfs_rq); + update_tg_cfs_load(cfs_rq, se, gcfs_rq); trace_pelt_cfs_tp(cfs_rq); trace_pelt_se_tp(se); @@ -3444,7 +3903,7 @@ static inline bool skip_blocked_update(struct sched_entity *se) #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} +static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {} static inline int propagate_entity_load_avg(struct sched_entity *se) { @@ -3455,18 +3914,100 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_NO_HZ_COMMON +static inline void migrate_se_pelt_lag(struct sched_entity *se) +{ + u64 throttled = 0, now, lut; + struct cfs_rq *cfs_rq; + struct rq *rq; + bool is_idle; + + if (load_avg_is_decayed(&se->avg)) + return; + + cfs_rq = cfs_rq_of(se); + rq = rq_of(cfs_rq); + + rcu_read_lock(); + is_idle = is_idle_task(rcu_dereference(rq->curr)); + rcu_read_unlock(); + + /* + * The lag estimation comes with a cost we don't want to pay all the + * time. Hence, limiting to the case where the source CPU is idle and + * we know we are at the greatest risk to have an outdated clock. + */ + if (!is_idle) + return; + + /* + * Estimated "now" is: last_update_time + cfs_idle_lag + rq_idle_lag, where: + * + * last_update_time (the cfs_rq's last_update_time) + * = cfs_rq_clock_pelt()@cfs_rq_idle + * = rq_clock_pelt()@cfs_rq_idle + * - cfs->throttled_clock_pelt_time@cfs_rq_idle + * + * cfs_idle_lag (delta between rq's update and cfs_rq's update) + * = rq_clock_pelt()@rq_idle - rq_clock_pelt()@cfs_rq_idle + * + * rq_idle_lag (delta between now and rq's update) + * = sched_clock_cpu() - rq_clock()@rq_idle + * + * We can then write: + * + * now = rq_clock_pelt()@rq_idle - cfs->throttled_clock_pelt_time + + * sched_clock_cpu() - rq_clock()@rq_idle + * Where: + * rq_clock_pelt()@rq_idle is rq->clock_pelt_idle + * rq_clock()@rq_idle is rq->clock_idle + * cfs->throttled_clock_pelt_time@cfs_rq_idle + * is cfs_rq->throttled_pelt_idle + */ + +#ifdef CONFIG_CFS_BANDWIDTH + throttled = u64_u32_load(cfs_rq->throttled_pelt_idle); + /* The clock has been stopped for throttling */ + if (throttled == U64_MAX) + return; +#endif + now = u64_u32_load(rq->clock_pelt_idle); + /* + * Paired with _update_idle_rq_clock_pelt(). It ensures at the worst case + * is observed the old clock_pelt_idle value and the new clock_idle, + * which lead to an underestimation. The opposite would lead to an + * overestimation. + */ + smp_rmb(); + lut = cfs_rq_last_update_time(cfs_rq); + + now -= throttled; + if (now < lut) + /* + * cfs_rq->avg.last_update_time is more recent than our + * estimation, let's use it. + */ + now = lut; + else + now += sched_clock_cpu(cpu_of(rq)) - u64_u32_load(rq->clock_idle); + + __update_load_avg_blocked_se(now, se); +} +#else +static void migrate_se_pelt_lag(struct sched_entity *se) {} +#endif + /** * update_cfs_rq_load_avg - update the cfs_rq's load/util averages * @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) - * avg. The immediate corollary is that all (fair) tasks must be attached, see - * post_init_entity_util_avg(). + * avg. The immediate corollary is that all (fair) tasks must be attached. * * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example. * - * Returns true if the load decayed or we removed load. + * Return: true if the load decayed or we removed load. * * Since both these conditions indicate a changed cfs_rq->avg.load we should * call update_tg_load_avg() when this function returns true. @@ -3474,41 +4015,64 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) { - unsigned long removed_load = 0, removed_util = 0, removed_runnable_sum = 0; + unsigned long removed_load = 0, removed_util = 0, removed_runnable = 0; struct sched_avg *sa = &cfs_rq->avg; int decayed = 0; if (cfs_rq->removed.nr) { unsigned long r; - u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib; + u32 divider = get_pelt_divider(&cfs_rq->avg); raw_spin_lock(&cfs_rq->removed.lock); swap(cfs_rq->removed.util_avg, removed_util); swap(cfs_rq->removed.load_avg, removed_load); - swap(cfs_rq->removed.runnable_sum, removed_runnable_sum); + swap(cfs_rq->removed.runnable_avg, removed_runnable); cfs_rq->removed.nr = 0; raw_spin_unlock(&cfs_rq->removed.lock); r = removed_load; sub_positive(&sa->load_avg, r); sub_positive(&sa->load_sum, r * divider); + /* See sa->util_sum below */ + sa->load_sum = max_t(u32, sa->load_sum, sa->load_avg * PELT_MIN_DIVIDER); r = removed_util; sub_positive(&sa->util_avg, r); sub_positive(&sa->util_sum, r * divider); + /* + * Because of rounding, se->util_sum might ends up being +1 more than + * cfs->util_sum. Although this is not a problem by itself, detaching + * a lot of tasks with the rounding problem between 2 updates of + * util_avg (~1ms) can make cfs->util_sum becoming null whereas + * cfs_util_avg is not. + * Check that util_sum is still above its lower bound for the new + * util_avg. Given that period_contrib might have moved since the last + * sync, we are only sure that util_sum must be above or equal to + * util_avg * minimum possible divider + */ + sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER); - add_tg_cfs_propagate(cfs_rq, -(long)removed_runnable_sum); + r = removed_runnable; + sub_positive(&sa->runnable_avg, r); + sub_positive(&sa->runnable_sum, r * divider); + /* See sa->util_sum above */ + sa->runnable_sum = max_t(u32, sa->runnable_sum, + sa->runnable_avg * PELT_MIN_DIVIDER); + + /* + * removed_runnable is the unweighted version of removed_load so we + * can use it to estimate removed_load_sum. + */ + add_tg_cfs_propagate(cfs_rq, + -(long)(removed_runnable * divider) >> SCHED_CAPACITY_SHIFT); decayed = 1; } decayed |= __update_load_avg_cfs_rq(now, cfs_rq); - -#ifndef CONFIG_64BIT - smp_wmb(); - cfs_rq->load_last_update_time_copy = sa->last_update_time; -#endif - + u64_u32_store_copy(sa->last_update_time, + cfs_rq->last_update_time_copy, + sa->last_update_time); return decayed; } @@ -3522,7 +4086,11 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) */ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u32 divider = LOAD_AVG_MAX - 1024 + cfs_rq->avg.period_contrib; + /* + * cfs_rq->avg.period_contrib can be used for both cfs_rq and se. + * See ___update_load_avg() for details. + */ + u32 divider = get_pelt_divider(&cfs_rq->avg); /* * When we attach the @se to the @cfs_rq, we must align the decay @@ -3542,17 +4110,19 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ se->avg.util_sum = se->avg.util_avg * divider; - se->avg.load_sum = divider; - if (se_weight(se)) { - se->avg.load_sum = - div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se)); - } + se->avg.runnable_sum = se->avg.runnable_avg * divider; - se->avg.runnable_load_sum = se->avg.load_sum; + se->avg.load_sum = se->avg.load_avg * divider; + if (se_weight(se) < se->avg.load_sum) + se->avg.load_sum = div_u64(se->avg.load_sum, se_weight(se)); + else + se->avg.load_sum = 1; enqueue_load_avg(cfs_rq, se); cfs_rq->avg.util_avg += se->avg.util_avg; cfs_rq->avg.util_sum += se->avg.util_sum; + cfs_rq->avg.runnable_avg += se->avg.runnable_avg; + cfs_rq->avg.runnable_sum += se->avg.runnable_sum; add_tg_cfs_propagate(cfs_rq, se->avg.load_sum); @@ -3574,6 +4144,15 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s dequeue_load_avg(cfs_rq, se); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.util_sum = max_t(u32, cfs_rq->avg.util_sum, + cfs_rq->avg.util_avg * PELT_MIN_DIVIDER); + + sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); + sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + /* See update_cfs_rq_load_avg() */ + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum, + cfs_rq->avg.runnable_avg * PELT_MIN_DIVIDER); add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); @@ -3588,6 +4167,7 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s #define UPDATE_TG 0x1 #define SKIP_AGE_LOAD 0x2 #define DO_ATTACH 0x4 +#define DO_DETACH 0x8 /* 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) @@ -3615,37 +4195,23 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s * IOW we're enqueueing a task on a new CPU. */ attach_entity_load_avg(cfs_rq, se); - update_tg_load_avg(cfs_rq, 0); + update_tg_load_avg(cfs_rq); + } else if (flags & DO_DETACH) { + /* + * DO_DETACH means we're here from dequeue_entity() + * and we are migrating task out of the CPU. + */ + detach_entity_load_avg(cfs_rq, se); + update_tg_load_avg(cfs_rq); } else if (decayed) { cfs_rq_util_change(cfs_rq, 0); if (flags & UPDATE_TG) - update_tg_load_avg(cfs_rq, 0); + update_tg_load_avg(cfs_rq); } } -#ifndef CONFIG_64BIT -static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) -{ - u64 last_update_time_copy; - u64 last_update_time; - - do { - last_update_time_copy = cfs_rq->load_last_update_time_copy; - smp_rmb(); - last_update_time = cfs_rq->avg.last_update_time; - } while (last_update_time != last_update_time_copy); - - return last_update_time; -} -#else -static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) -{ - return cfs_rq->avg.last_update_time; -} -#endif - /* * Synchronize entity load avg of dequeued entity without locking * the previous rq. @@ -3670,8 +4236,8 @@ static 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. + * enqueue_task_fair() which will have added things to the cfs_rq, + * so we can remove unconditionally. */ sync_entity_load_avg(se); @@ -3680,13 +4246,13 @@ static void remove_entity_load_avg(struct sched_entity *se) ++cfs_rq->removed.nr; cfs_rq->removed.util_avg += se->avg.util_avg; cfs_rq->removed.load_avg += se->avg.load_avg; - cfs_rq->removed.runnable_sum += se->avg.load_sum; /* == runnable_sum */ + cfs_rq->removed.runnable_avg += se->avg.runnable_avg; raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags); } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq) +static inline unsigned long cfs_rq_runnable_avg(struct cfs_rq *cfs_rq) { - return cfs_rq->avg.runnable_load_avg; + return cfs_rq->avg.runnable_avg; } static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) @@ -3694,6 +4260,8 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) return cfs_rq->avg.load_avg; } +static int newidle_balance(struct rq *this_rq, struct rq_flags *rf); + static inline unsigned long task_util(struct task_struct *p) { return READ_ONCE(p->se.avg.util_avg); @@ -3703,7 +4271,7 @@ 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) | UTIL_AVG_UNCHANGED); + return max(ue.ewma, (ue.enqueued & ~UTIL_AVG_UNCHANGED)); } static inline unsigned long task_util_est(struct task_struct *p) @@ -3737,36 +4305,51 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq, enqueued = cfs_rq->avg.util_est.enqueued; enqueued += _task_util_est(p); WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued); + + trace_sched_util_est_cfs_tp(cfs_rq); +} + +static inline void util_est_dequeue(struct cfs_rq *cfs_rq, + struct task_struct *p) +{ + unsigned int enqueued; + + if (!sched_feat(UTIL_EST)) + return; + + /* Update root cfs_rq's estimated utilization */ + enqueued = cfs_rq->avg.util_est.enqueued; + enqueued -= min_t(unsigned int, enqueued, _task_util_est(p)); + WRITE_ONCE(cfs_rq->avg.util_est.enqueued, enqueued); + + trace_sched_util_est_cfs_tp(cfs_rq); } +#define UTIL_EST_MARGIN (SCHED_CAPACITY_SCALE / 100) + /* * Check if a (signed) value is within a specified (unsigned) margin, * based on the observation that: * * abs(x) < y := (unsigned)(x + y - 1) < (2 * y - 1) * - * NOTE: this only works when value + maring < INT_MAX. + * NOTE: this only works when value + margin < INT_MAX. */ static inline bool within_margin(int value, int margin) { return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); } -static void -util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) +static inline void util_est_update(struct cfs_rq *cfs_rq, + struct task_struct *p, + bool task_sleep) { - long last_ewma_diff; + long last_ewma_diff, last_enqueued_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)); - WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued); - /* * Skip update of task's estimated utilization when the task has not * yet completed an activation, e.g. being migrated. @@ -3782,11 +4365,13 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) if (ue.enqueued & UTIL_AVG_UNCHANGED) return; + last_enqueued_diff = ue.enqueued; + /* * Reset EWMA on utilization increases, the moving average is used only * to smooth utilization decreases. */ - ue.enqueued = (task_util(p) | UTIL_AVG_UNCHANGED); + ue.enqueued = task_util(p); if (sched_feat(UTIL_EST_FASTUP)) { if (ue.ewma < ue.enqueued) { ue.ewma = ue.enqueued; @@ -3795,19 +4380,23 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) } /* - * Skip update of task's estimated utilization when its EWMA is + * Skip update of task's estimated utilization when its members are * already ~1% close to its last activation value. */ last_ewma_diff = ue.enqueued - ue.ewma; - if (within_margin(last_ewma_diff, (SCHED_CAPACITY_SCALE / 100))) + last_enqueued_diff -= ue.enqueued; + if (within_margin(last_ewma_diff, UTIL_EST_MARGIN)) { + if (!within_margin(last_enqueued_diff, UTIL_EST_MARGIN)) + goto done; + 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)) + if (task_util(p) > capacity_orig_of(cpu_of(rq_of(cfs_rq)))) return; /* @@ -3831,20 +4420,24 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) ue.ewma += last_ewma_diff; ue.ewma >>= UTIL_EST_WEIGHT_SHIFT; done: + ue.enqueued |= UTIL_AVG_UNCHANGED; WRITE_ONCE(p->se.avg.util_est, ue); + + trace_sched_util_est_se_tp(&p->se); } -static inline int task_fits_capacity(struct task_struct *p, long capacity) +static inline int task_fits_capacity(struct task_struct *p, + unsigned long capacity) { return fits_capacity(uclamp_task_util(p), capacity); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) { - if (!static_branch_unlikely(&sched_asym_cpucapacity)) + if (!sched_asym_cpucap_active()) return; - if (!p) { + if (!p || p->nr_cpus_allowed == 1) { rq->misfit_task_load = 0; return; } @@ -3854,14 +4447,24 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) return; } - rq->misfit_task_load = task_h_load(p); + /* + * Make sure that misfit_task_load will not be null even if + * task_h_load() returns 0. + */ + rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1); } #else /* CONFIG_SMP */ +static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) +{ + return true; +} + #define UPDATE_TG 0x0 #define SKIP_AGE_LOAD 0x0 #define DO_ATTACH 0x0 +#define DO_DETACH 0x0 static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int not_used1) { @@ -3875,7 +4478,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} static inline void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} -static inline int idle_balance(struct rq *rq, struct rq_flags *rf) +static inline int newidle_balance(struct rq *rq, struct rq_flags *rf) { return 0; } @@ -3884,8 +4487,11 @@ static inline void util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {} static inline void -util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, - bool task_sleep) {} +util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p) {} + +static inline void +util_est_update(struct cfs_rq *cfs_rq, struct task_struct *p, + bool task_sleep) {} static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {} #endif /* CONFIG_SMP */ @@ -3919,7 +4525,12 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) /* sleeps up to a single latency don't count. */ if (!initial) { - unsigned long thresh = sysctl_sched_latency; + unsigned long thresh; + + if (se_is_idle(se)) + thresh = sysctl_sched_min_granularity; + else + thresh = sysctl_sched_latency; /* * Halve their sleep time's effect, to allow @@ -3937,26 +4548,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) static void check_enqueue_throttle(struct cfs_rq *cfs_rq); -static inline void check_schedstat_required(void) -{ -#ifdef CONFIG_SCHEDSTATS - if (schedstat_enabled()) - return; - - /* Force schedstat enabled if a dependent tracepoint is active */ - if (trace_sched_stat_wait_enabled() || - trace_sched_stat_sleep_enabled() || - trace_sched_stat_iowait_enabled() || - trace_sched_stat_blocked_enabled() || - trace_sched_stat_runtime_enabled()) { - printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, " - "stat_blocked and stat_runtime require the " - "kernel parameter schedstats=enable or " - "kernel.sched_schedstats=1\n"); - } -#endif -} - +static inline bool cfs_bandwidth_used(void); /* * MIGRATION @@ -4015,29 +4607,31 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* * When enqueuing a sched_entity, we must: * - Update loads to have both entity and cfs_rq synced with now. - * - Add its load to cfs_rq->runnable_avg + * - For group_entity, update its runnable_weight to reflect the new + * h_nr_running of its group cfs_rq. * - For group_entity, update its weight to reflect the new share of * its group cfs_rq * - Add its new weight to cfs_rq->load.weight */ update_load_avg(cfs_rq, se, UPDATE_TG | DO_ATTACH); + se_update_runnable(se); update_cfs_group(se); - enqueue_runnable_load_avg(cfs_rq, se); account_entity_enqueue(cfs_rq, se); if (flags & ENQUEUE_WAKEUP) place_entity(cfs_rq, se, 0); check_schedstat_required(); - update_stats_enqueue(cfs_rq, se, flags); + update_stats_enqueue_fair(cfs_rq, se, flags); check_spread(cfs_rq, se); if (!curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; if (cfs_rq->nr_running == 1) { - list_add_leaf_cfs_rq(cfs_rq); check_enqueue_throttle(cfs_rq); + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); } } @@ -4091,6 +4685,11 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq); static void dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { + int action = UPDATE_TG; + + if (entity_is_task(se) && task_on_rq_migrating(task_of(se))) + action |= DO_DETACH; + /* * Update run-time statistics of the 'current'. */ @@ -4099,15 +4698,16 @@ 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. - * - Subtract its load from the cfs_rq->runnable_avg. + * - For group_entity, update its runnable_weight to reflect the new + * h_nr_running of its group cfs_rq. * - 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. */ - update_load_avg(cfs_rq, se, UPDATE_TG); - dequeue_runnable_load_avg(cfs_rq, se); + update_load_avg(cfs_rq, se, action); + se_update_runnable(se); - update_stats_dequeue(cfs_rq, se, flags); + update_stats_dequeue_fair(cfs_rq, se, flags); clear_buddies(cfs_rq, se); @@ -4138,6 +4738,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) */ if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE) update_min_vruntime(cfs_rq); + + if (cfs_rq->nr_running == 0) + update_idle_cfs_rq_clock_pelt(cfs_rq); } /* @@ -4183,6 +4786,8 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) static void set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) { + clear_buddies(cfs_rq, se); + /* 'current' is not kept within the tree. */ if (se->on_rq) { /* @@ -4190,7 +4795,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * a CPU. So account for the time it spent waiting on the * runqueue. */ - update_stats_wait_end(cfs_rq, se); + update_stats_wait_end_fair(cfs_rq, se); __dequeue_entity(cfs_rq, se); update_load_avg(cfs_rq, se, UPDATE_TG); } @@ -4205,9 +4810,12 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) */ if (schedstat_enabled() && rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) { - schedstat_set(se->statistics.slice_max, - max((u64)schedstat_val(se->statistics.slice_max), - se->sum_exec_runtime - se->prev_sum_exec_runtime)); + struct sched_statistics *stats; + + stats = __schedstats_from_se(se); + __schedstat_set(stats->slice_max, + max((u64)stats->slice_max, + se->sum_exec_runtime - se->prev_sum_exec_runtime)); } se->prev_sum_exec_runtime = se->sum_exec_runtime; @@ -4242,7 +4850,7 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) * Avoid running the skip buddy, if running something else can * be done without getting too unfair. */ - if (cfs_rq->skip == se) { + if (cfs_rq->skip && cfs_rq->skip == se) { struct sched_entity *second; if (se == curr) { @@ -4257,19 +4865,17 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) se = second; } - /* - * Prefer last buddy, try to return the CPU to a preempted task. - */ - if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) - se = cfs_rq->last; - - /* - * Someone really wants this to run. If it's not unfair, run it. - */ - if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) { + /* + * Someone really wants this to run. If it's not unfair, run it. + */ se = cfs_rq->next; - - clear_buddies(cfs_rq, se); + } else if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) { + /* + * Prefer last buddy, try to return the CPU to a preempted task. + */ + se = cfs_rq->last; + } return se; } @@ -4291,7 +4897,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) check_spread(cfs_rq, prev); if (prev->on_rq) { - update_stats_wait_start(cfs_rq, prev); + update_stats_wait_start_fair(cfs_rq, prev); /* Put 'current' back into the tree. */ __enqueue_entity(cfs_rq, prev); /* in !on_rq case, update occurred at dequeue */ @@ -4392,8 +4998,20 @@ static inline u64 sched_cfs_bandwidth_slice(void) */ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) { - if (cfs_b->quota != RUNTIME_INF) - cfs_b->runtime = cfs_b->quota; + s64 runtime; + + if (unlikely(cfs_b->quota == RUNTIME_INF)) + return; + + cfs_b->runtime += cfs_b->quota; + runtime = cfs_b->runtime_snap - cfs_b->runtime; + if (runtime > 0) { + cfs_b->burst_time += runtime; + cfs_b->nr_burst++; + } + + cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst); + cfs_b->runtime_snap = cfs_b->runtime; } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4402,16 +5020,16 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) } /* returns 0 on failure to allocate runtime */ -static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b, + struct cfs_rq *cfs_rq, u64 target_runtime) { - struct task_group *tg = cfs_rq->tg; - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); - u64 amount = 0, min_amount; + u64 min_amount, amount = 0; + + lockdep_assert_held(&cfs_b->lock); /* note: this is a positive sum as runtime_remaining <= 0 */ - min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; + min_amount = target_runtime - cfs_rq->runtime_remaining; - raw_spin_lock(&cfs_b->lock); if (cfs_b->quota == RUNTIME_INF) amount = min_amount; else { @@ -4423,13 +5041,25 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } - raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += amount; return cfs_rq->runtime_remaining > 0; } +/* returns 0 on failure to allocate runtime */ +static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + int ret; + + raw_spin_lock(&cfs_b->lock); + ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice()); + raw_spin_unlock(&cfs_b->lock); + + return ret; +} + static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ @@ -4492,11 +5122,11 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) cfs_rq->throttle_count--; if (!cfs_rq->throttle_count) { - cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - - cfs_rq->throttled_clock_task; + cfs_rq->throttled_clock_pelt_time += rq_clock_pelt(rq) - + cfs_rq->throttled_clock_pelt; - /* Add cfs_rq with already running entity in the list */ - if (cfs_rq->nr_running >= 1) + /* Add cfs_rq with load or one or more already running entities to the list */ + if (!cfs_rq_is_decayed(cfs_rq)) list_add_leaf_cfs_rq(cfs_rq); } @@ -4510,7 +5140,7 @@ static int tg_throttle_down(struct task_group *tg, void *data) /* group is entering throttled state, stop time */ if (!cfs_rq->throttle_count) { - cfs_rq->throttled_clock_task = rq_clock_task(rq); + cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq); list_del_leaf_cfs_rq(cfs_rq); } cfs_rq->throttle_count++; @@ -4518,13 +5148,33 @@ static int tg_throttle_down(struct task_group *tg, void *data) return 0; } -static void throttle_cfs_rq(struct cfs_rq *cfs_rq) +static bool throttle_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; long task_delta, idle_task_delta, dequeue = 1; - bool empty; + + raw_spin_lock(&cfs_b->lock); + /* This will start the period timer if necessary */ + if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) { + /* + * We have raced with bandwidth becoming available, and if we + * actually throttled the timer might not unthrottle us for an + * entire period. We additionally needed to make sure that any + * subsequent check_cfs_rq_runtime calls agree not to throttle + * us, as we may commit to do cfs put_prev+pick_next, so we ask + * for 1ns of runtime rather than just check cfs_b. + */ + dequeue = 0; + } else { + list_add_tail_rcu(&cfs_rq->throttled_list, + &cfs_b->throttled_cfs_rq); + } + raw_spin_unlock(&cfs_b->lock); + + if (!dequeue) + return false; /* Throttle no longer required. */ se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -4539,43 +5189,50 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) struct cfs_rq *qcfs_rq = cfs_rq_of(se); /* throttled entity or throttle-on-deactivate */ if (!se->on_rq) - break; + goto done; + + dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); + + if (cfs_rq_is_idle(group_cfs_rq(se))) + idle_task_delta = cfs_rq->h_nr_running; - if (dequeue) - dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); qcfs_rq->h_nr_running -= task_delta; qcfs_rq->idle_h_nr_running -= idle_task_delta; - if (qcfs_rq->load.weight) - dequeue = 0; + if (qcfs_rq->load.weight) { + /* Avoid re-evaluating load for this entity: */ + se = parent_entity(se); + break; + } } - if (!se) - sub_nr_running(rq, task_delta); + for_each_sched_entity(se) { + struct cfs_rq *qcfs_rq = cfs_rq_of(se); + /* throttled entity or throttle-on-deactivate */ + if (!se->on_rq) + goto done; - cfs_rq->throttled = 1; - cfs_rq->throttled_clock = rq_clock(rq); - raw_spin_lock(&cfs_b->lock); - empty = list_empty(&cfs_b->throttled_cfs_rq); + update_load_avg(qcfs_rq, se, 0); + se_update_runnable(se); - /* - * Add to the _head_ of the list, so that an already-started - * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is - * not running add to the tail so that later runqueues don't get starved. - */ - if (cfs_b->distribute_running) - list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); - else - list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq); + if (cfs_rq_is_idle(group_cfs_rq(se))) + idle_task_delta = cfs_rq->h_nr_running; + + qcfs_rq->h_nr_running -= task_delta; + qcfs_rq->idle_h_nr_running -= idle_task_delta; + } + /* At this point se is NULL and we are at root level*/ + sub_nr_running(rq, task_delta); + +done: /* - * If we're the first throttled task, make sure the bandwidth - * timer is running. + * Note: distribution will already see us throttled via the + * throttled-list. rq->lock protects completion. */ - if (empty) - start_cfs_bandwidth(cfs_b); - - raw_spin_unlock(&cfs_b->lock); + cfs_rq->throttled = 1; + cfs_rq->throttled_clock = rq_clock(rq); + return true; } void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) @@ -4583,7 +5240,6 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - int enqueue = 1; long task_delta, idle_task_delta; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -4600,40 +5256,72 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); - if (!cfs_rq->load.weight) - return; + if (!cfs_rq->load.weight) { + if (!cfs_rq->on_list) + return; + /* + * Nothing to run but something to decay (on_list)? + * Complete the branch. + */ + for_each_sched_entity(se) { + if (list_add_leaf_cfs_rq(cfs_rq_of(se))) + break; + } + goto unthrottle_throttle; + } task_delta = cfs_rq->h_nr_running; idle_task_delta = cfs_rq->idle_h_nr_running; for_each_sched_entity(se) { + struct cfs_rq *qcfs_rq = cfs_rq_of(se); + if (se->on_rq) - enqueue = 0; + break; + enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP); - cfs_rq = cfs_rq_of(se); - if (enqueue) - enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP); - cfs_rq->h_nr_running += task_delta; - cfs_rq->idle_h_nr_running += idle_task_delta; + if (cfs_rq_is_idle(group_cfs_rq(se))) + idle_task_delta = cfs_rq->h_nr_running; - if (cfs_rq_throttled(cfs_rq)) - break; + qcfs_rq->h_nr_running += task_delta; + qcfs_rq->idle_h_nr_running += idle_task_delta; + + /* end evaluation on encountering a throttled cfs_rq */ + if (cfs_rq_throttled(qcfs_rq)) + goto unthrottle_throttle; } - assert_list_leaf_cfs_rq(rq); + for_each_sched_entity(se) { + struct cfs_rq *qcfs_rq = cfs_rq_of(se); - if (!se) - add_nr_running(rq, task_delta); + update_load_avg(qcfs_rq, se, UPDATE_TG); + se_update_runnable(se); + + if (cfs_rq_is_idle(group_cfs_rq(se))) + idle_task_delta = cfs_rq->h_nr_running; + + qcfs_rq->h_nr_running += task_delta; + qcfs_rq->idle_h_nr_running += idle_task_delta; + + /* end evaluation on encountering a throttled cfs_rq */ + if (cfs_rq_throttled(qcfs_rq)) + goto unthrottle_throttle; + } + + /* At this point se is NULL and we are at root level*/ + add_nr_running(rq, task_delta); + +unthrottle_throttle: + assert_list_leaf_cfs_rq(rq); /* Determine whether we need to wake up potentially idle CPU: */ if (rq->curr == rq->idle && rq->cfs.nr_running) resched_curr(rq); } -static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) +static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) { struct cfs_rq *cfs_rq; - u64 runtime; - u64 starting_runtime = remaining; + u64 runtime, remaining = 1; rcu_read_lock(); list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, @@ -4648,10 +5336,13 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) /* By the above check, this should never be true */ SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); + raw_spin_lock(&cfs_b->lock); runtime = -cfs_rq->runtime_remaining + 1; - if (runtime > remaining) - runtime = remaining; - remaining -= runtime; + if (runtime > cfs_b->runtime) + runtime = cfs_b->runtime; + cfs_b->runtime -= runtime; + remaining = cfs_b->runtime; + raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += runtime; @@ -4666,8 +5357,6 @@ next: break; } rcu_read_unlock(); - - return starting_runtime - remaining; } /* @@ -4678,7 +5367,6 @@ next: */ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) { - u64 runtime; int throttled; /* no need to continue the timer with no bandwidth constraint */ @@ -4688,6 +5376,9 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u throttled = !list_empty(&cfs_b->throttled_cfs_rq); cfs_b->nr_periods += overrun; + /* Refill extra burst quota even if cfs_b->idle */ + __refill_cfs_bandwidth_runtime(cfs_b); + /* * idle depends on !throttled (for the case of a large deficit), and if * we're going inactive then everything else can be deferred @@ -4695,8 +5386,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u if (cfs_b->idle && !throttled) goto out_deactivate; - __refill_cfs_bandwidth_runtime(cfs_b); - if (!throttled) { /* mark as potentially idle for the upcoming period */ cfs_b->idle = 1; @@ -4707,24 +5396,15 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u cfs_b->nr_throttled += overrun; /* - * This check is repeated as we are holding onto the new bandwidth while - * we unthrottle. This can potentially race with an unthrottled group - * trying to acquire new bandwidth from the global pool. This can result - * in us over-using our runtime if it is all used during this loop, but - * only by limited amounts in that extreme case. + * This check is repeated as we release cfs_b->lock while we unthrottle. */ - while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) { - runtime = cfs_b->runtime; - cfs_b->distribute_running = 1; + while (throttled && cfs_b->runtime > 0) { 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); + distribute_cfs_runtime(cfs_b); raw_spin_lock_irqsave(&cfs_b->lock, flags); - cfs_b->distribute_running = 0; throttled = !list_empty(&cfs_b->throttled_cfs_rq); - - lsub_positive(&cfs_b->runtime, runtime); } /* @@ -4758,7 +5438,7 @@ static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) { struct hrtimer *refresh_timer = &cfs_b->period_timer; - u64 remaining; + s64 remaining; /* if the call-back is running a quota refresh is already occurring */ if (hrtimer_callback_running(refresh_timer)) @@ -4766,7 +5446,7 @@ static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) /* is a quota refresh about to occur? */ remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer)); - if (remaining < min_expire) + if (remaining < (s64)min_expire) return 1; return 0; @@ -4837,10 +5517,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) /* confirm we're still not at a refresh boundary */ raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->slack_started = false; - if (cfs_b->distribute_running) { - raw_spin_unlock_irqrestore(&cfs_b->lock, flags); - return; - } if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { raw_spin_unlock_irqrestore(&cfs_b->lock, flags); @@ -4850,26 +5526,18 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) runtime = cfs_b->runtime; - if (runtime) - cfs_b->distribute_running = 1; - raw_spin_unlock_irqrestore(&cfs_b->lock, flags); if (!runtime) return; - runtime = distribute_cfs_runtime(cfs_b, runtime); - - raw_spin_lock_irqsave(&cfs_b->lock, flags); - lsub_positive(&cfs_b->runtime, runtime); - cfs_b->distribute_running = 0; - raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + distribute_cfs_runtime(cfs_b); } /* * When a group wakes up we want to make sure that its quota is not already * expired/exceeded, otherwise it may be allowed to steal additional ticks of - * runtime as update_curr() throttling can not not trigger until it's on-rq. + * runtime as update_curr() throttling can not trigger until it's on-rq. */ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) { @@ -4904,7 +5572,7 @@ static void sync_throttle(struct task_group *tg, int cpu) pcfs_rq = tg->parent->cfs_rq[cpu]; cfs_rq->throttle_count = pcfs_rq->throttle_count; - cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu)); + cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu)); } /* conditionally throttle active cfs_rq's from put_prev_entity() */ @@ -4923,8 +5591,7 @@ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) if (cfs_rq_throttled(cfs_rq)) return true; - throttle_cfs_rq(cfs_rq); - return true; + return throttle_cfs_rq(cfs_rq); } static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) @@ -4954,6 +5621,8 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (!overrun) break; + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); + if (++count > 3) { u64 new, old = ktime_to_ns(cfs_b->period); @@ -4966,6 +5635,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) if (new < max_cfs_quota_period) { cfs_b->period = ns_to_ktime(new); cfs_b->quota *= 2; + cfs_b->burst *= 2; pr_warn_ratelimited( "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n", @@ -4983,8 +5653,6 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) /* reset count so we don't come right back in here */ count = 0; } - - idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) cfs_b->period_active = 0; @@ -4999,13 +5667,13 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) cfs_b->runtime = 0; cfs_b->quota = RUNTIME_INF; cfs_b->period = ns_to_ktime(default_cfs_period()); + cfs_b->burst = 0; INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); cfs_b->period_timer.function = sched_cfs_period_timer; hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cfs_b->slack_timer.function = sched_cfs_slack_timer; - cfs_b->distribute_running = 0; cfs_b->slack_started = false; } @@ -5044,12 +5712,12 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) * bits doesn't do much. */ -/* cpu online calback */ +/* cpu online callback */ static void __maybe_unused update_runtime_enabled(struct rq *rq) { struct task_group *tg; - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); rcu_read_lock(); list_for_each_entry_rcu(tg, &task_groups, list) { @@ -5068,7 +5736,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) { struct task_group *tg; - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); rcu_read_lock(); list_for_each_entry_rcu(tg, &task_groups, list) { @@ -5157,7 +5825,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) s64 delta = slice - ran; if (delta < 0) { - if (rq->curr == p) + if (task_current(rq, p)) resched_curr(rq); return; } @@ -5174,7 +5842,7 @@ static void hrtick_update(struct rq *rq) { struct task_struct *curr = rq->curr; - if (!hrtick_enabled(rq) || curr->sched_class != &fair_sched_class) + if (!hrtick_enabled_fair(rq) || curr->sched_class != &fair_sched_class) return; if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency) @@ -5192,11 +5860,9 @@ static inline void hrtick_update(struct rq *rq) #endif #ifdef CONFIG_SMP -static inline unsigned long cpu_util(int cpu); - static inline bool cpu_overutilized(int cpu) { - return !fits_capacity(cpu_util(cpu), capacity_of(cpu)); + return !fits_capacity(cpu_util_cfs(cpu), capacity_of(cpu)); } static inline void update_overutilized_status(struct rq *rq) @@ -5217,6 +5883,17 @@ static int sched_idle_rq(struct rq *rq) rq->nr_running); } +/* + * Returns true if cfs_rq only has SCHED_IDLE entities enqueued. Note the use + * of idle_nr_running, which does not consider idle descendants of normal + * entities. + */ +static bool sched_idle_cfs_rq(struct cfs_rq *cfs_rq) +{ + return cfs_rq->nr_running && + cfs_rq->nr_running == cfs_rq->idle_nr_running; +} + #ifdef CONFIG_SMP static int sched_idle_cpu(int cpu) { @@ -5235,6 +5912,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int idle_h_nr_running = task_has_idle_policy(p); + int task_new = !(flags & ENQUEUE_WAKEUP); /* * The code below (indirectly) updates schedutil which looks at @@ -5258,68 +5936,58 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) cfs_rq = cfs_rq_of(se); enqueue_entity(cfs_rq, se, flags); - /* - * end evaluation on encountering a throttled cfs_rq - * - * note: in the case of encountering a throttled cfs_rq we will - * post the final h_nr_running increment below. - */ - if (cfs_rq_throttled(cfs_rq)) - break; cfs_rq->h_nr_running++; cfs_rq->idle_h_nr_running += idle_h_nr_running; + if (cfs_rq_is_idle(cfs_rq)) + idle_h_nr_running = 1; + + /* end evaluation on encountering a throttled cfs_rq */ + if (cfs_rq_throttled(cfs_rq)) + goto enqueue_throttle; + flags = ENQUEUE_WAKEUP; } for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - cfs_rq->h_nr_running++; - cfs_rq->idle_h_nr_running += idle_h_nr_running; - - if (cfs_rq_throttled(cfs_rq)) - break; update_load_avg(cfs_rq, se, UPDATE_TG); + se_update_runnable(se); update_cfs_group(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); + cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; + if (cfs_rq_is_idle(cfs_rq)) + idle_h_nr_running = 1; + + /* end evaluation on encountering a throttled cfs_rq */ + if (cfs_rq_throttled(cfs_rq)) + goto enqueue_throttle; } - 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); + /* At this point se is NULL and we are at root level*/ + add_nr_running(rq, 1); - if (list_add_leaf_cfs_rq(cfs_rq)) - break; - } - } + /* + * 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 (!task_new) + update_overutilized_status(rq); +enqueue_throttle: assert_list_leaf_cfs_rq(rq); hrtick_update(rq); @@ -5340,21 +6008,22 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) int idle_h_nr_running = task_has_idle_policy(p); bool was_sched_idle = sched_idle_rq(rq); + util_est_dequeue(&rq->cfs, p); + for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); dequeue_entity(cfs_rq, se, flags); - /* - * end evaluation on encountering a throttled cfs_rq - * - * note: in the case of encountering a throttled cfs_rq we will - * post the final h_nr_running decrement below. - */ - if (cfs_rq_throttled(cfs_rq)) - break; cfs_rq->h_nr_running--; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + if (cfs_rq_is_idle(cfs_rq)) + idle_h_nr_running = 1; + + /* end evaluation on encountering a throttled cfs_rq */ + if (cfs_rq_throttled(cfs_rq)) + goto dequeue_throttle; + /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { /* Avoid re-evaluating load for this entity: */ @@ -5372,32 +6041,40 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); + + update_load_avg(cfs_rq, se, UPDATE_TG); + se_update_runnable(se); + update_cfs_group(se); + cfs_rq->h_nr_running--; cfs_rq->idle_h_nr_running -= idle_h_nr_running; + if (cfs_rq_is_idle(cfs_rq)) + idle_h_nr_running = 1; + + /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) - break; + goto dequeue_throttle; - update_load_avg(cfs_rq, se, UPDATE_TG); - update_cfs_group(se); } - if (!se) - sub_nr_running(rq, 1); + /* At this point se is NULL and we are at root level*/ + sub_nr_running(rq, 1); /* balance early to pull high priority tasks */ if (unlikely(!was_sched_idle && sched_idle_rq(rq))) rq->next_balance = jiffies; - util_est_dequeue(&rq->cfs, p, task_sleep); +dequeue_throttle: + util_est_update(&rq->cfs, p, task_sleep); hrtick_update(rq); } #ifdef CONFIG_SMP /* Working cpumask for: load_balance, load_balance_newidle. */ -DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); -DEFINE_PER_CPU(cpumask_var_t, select_idle_mask); +static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); +static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask); #ifdef CONFIG_NO_HZ_COMMON @@ -5405,6 +6082,7 @@ static struct { cpumask_var_t idle_cpus_mask; atomic_t nr_cpus; int has_blocked; /* Idle CPUS has blocked load */ + int needs_update; /* Newly idle CPUs need their next_balance collated */ unsigned long next_balance; /* in jiffy units */ unsigned long next_blocked; /* Next update of blocked load in jiffies */ } nohz ____cacheline_aligned; @@ -5447,6 +6125,29 @@ static unsigned long cpu_load_without(struct rq *rq, struct task_struct *p) return load; } +static unsigned long cpu_runnable(struct rq *rq) +{ + return cfs_rq_runnable_avg(&rq->cfs); +} + +static unsigned long cpu_runnable_without(struct rq *rq, struct task_struct *p) +{ + struct cfs_rq *cfs_rq; + unsigned int runnable; + + /* Task has no contribution or is new */ + if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) + return cpu_runnable(rq); + + cfs_rq = &rq->cfs; + runnable = READ_ONCE(cfs_rq->avg.runnable_avg); + + /* Discount task's runnable from CPU's runnable */ + lsub_positive(&runnable, p->se.avg.runnable_avg); + + return runnable; +} + static unsigned long capacity_of(int cpu) { return cpu_rq(cpu)->cpu_capacity; @@ -5490,7 +6191,7 @@ static int wake_wide(struct task_struct *p) { unsigned int master = current->wakee_flips; unsigned int slave = p->wakee_flips; - int factor = this_cpu_read(sd_llc_size); + int factor = __this_cpu_read(sd_llc_size); if (master < slave) swap(master, slave); @@ -5532,6 +6233,9 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync) if (sync && cpu_rq(this_cpu)->nr_running == 1) return this_cpu; + if (available_idle_cpu(prev_cpu)) + return prev_cpu; + return nr_cpumask_bits; } @@ -5589,18 +6293,17 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits) target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); - schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); + schedstat_inc(p->stats.nr_wakeups_affine_attempts); if (target == nr_cpumask_bits) return prev_cpu; schedstat_inc(sd->ttwu_move_affine); - schedstat_inc(p->se.statistics.nr_wakeups_affine); + schedstat_inc(p->stats.nr_wakeups_affine); return target; } static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int sd_flag); +find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu); /* * find_idlest_group_cpu - find the idlest CPU among the CPUs in the group. @@ -5621,11 +6324,15 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this /* Traverse only the allowed CPUs */ for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) { + struct rq *rq = cpu_rq(i); + + if (!sched_core_cookie_match(rq, p)) + continue; + if (sched_idle_cpu(i)) return i; if (available_idle_cpu(i)) { - struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); if (idle && idle->exit_latency < min_exit_latency) { /* @@ -5683,7 +6390,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p continue; } - group = find_idlest_group(sd, p, cpu, sd_flag); + group = find_idlest_group(sd, p, cpu); if (!group) { sd = sd->child; continue; @@ -5711,6 +6418,15 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p return new_cpu; } +static inline int __select_idle_cpu(int cpu, struct task_struct *p) +{ + if ((available_idle_cpu(cpu) || sched_idle_cpu(cpu)) && + sched_cpu_cookie_match(cpu_rq(cpu), p)) + return cpu; + + return -1; +} + #ifdef CONFIG_SCHED_SMT DEFINE_STATIC_KEY_FALSE(sched_smt_present); EXPORT_SYMBOL_GPL(sched_smt_present); @@ -5724,7 +6440,7 @@ static inline void set_idle_cores(int cpu, int val) WRITE_ONCE(sds->has_idle_cores, val); } -static inline bool test_idle_cores(int cpu, bool def) +static inline bool test_idle_cores(int cpu) { struct sched_domain_shared *sds; @@ -5732,7 +6448,7 @@ static inline bool test_idle_cores(int cpu, bool def) if (sds) return READ_ONCE(sds->has_idle_cores); - return def; + return false; } /* @@ -5748,7 +6464,7 @@ void __update_idle_core(struct rq *rq) int cpu; rcu_read_lock(); - if (test_idle_cores(core, true)) + if (test_idle_cores(core)) goto unlock; for_each_cpu(cpu, cpu_smt_mask(core)) { @@ -5769,37 +6485,31 @@ unlock: * there are no idle cores left in the system; tracked through * sd_llc->shared->has_idle_cores and enabled through update_idle_core() above. */ -static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target) +static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu) { - struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); - int core, cpu; - - if (!static_branch_likely(&sched_smt_present)) - return -1; - - if (!test_idle_cores(target, false)) - return -1; - - cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); - - for_each_cpu_wrap(core, cpus, target) { - bool idle = true; + bool idle = true; + int cpu; - for_each_cpu(cpu, cpu_smt_mask(core)) { - __cpumask_clear_cpu(cpu, cpus); - if (!available_idle_cpu(cpu)) - idle = false; + for_each_cpu(cpu, cpu_smt_mask(core)) { + if (!available_idle_cpu(cpu)) { + idle = false; + if (*idle_cpu == -1) { + if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) { + *idle_cpu = cpu; + break; + } + continue; + } + break; } - - if (idle) - return core; + if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr)) + *idle_cpu = cpu; } - /* - * Failed to find an idle core; stop looking for one. - */ - set_idle_cores(target, 0); + if (idle) + return core; + cpumask_andnot(cpus, cpus, cpu_smt_mask(core)); return -1; } @@ -5810,11 +6520,8 @@ static int select_idle_smt(struct task_struct *p, int target) { int cpu; - if (!static_branch_likely(&sched_smt_present)) - return -1; - - for_each_cpu(cpu, cpu_smt_mask(target)) { - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) { + if (cpu == target) continue; if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; @@ -5825,9 +6532,18 @@ static int select_idle_smt(struct task_struct *p, int target) #else /* CONFIG_SCHED_SMT */ -static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target) +static inline void set_idle_cores(int cpu, int val) { - return -1; +} + +static inline bool test_idle_cores(int cpu) +{ + return false; +} + +static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu) +{ + return __select_idle_cpu(core, p); } static inline int select_idle_smt(struct task_struct *p, int target) @@ -5842,55 +6558,134 @@ static inline int select_idle_smt(struct task_struct *p, int target) * comparing the average scan cost (tracked in sd->avg_scan_cost) against the * average idle time for this rq (as found in rq->avg_idle). */ -static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) +static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool has_idle_core, int target) { - struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); - struct sched_domain *this_sd; - u64 avg_cost, avg_idle; - u64 time, cost; - s64 delta; + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); + int i, cpu, idle_cpu = -1, nr = INT_MAX; + struct sched_domain_shared *sd_share; + struct rq *this_rq = this_rq(); int this = smp_processor_id(); - int cpu, nr = INT_MAX; + struct sched_domain *this_sd = NULL; + u64 time = 0; - this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); - if (!this_sd) - return -1; + cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); - /* - * Due to large variance we need a large fuzz factor; hackbench in - * particularly is sensitive here. - */ - avg_idle = this_rq()->avg_idle / 512; - avg_cost = this_sd->avg_scan_cost + 1; + if (sched_feat(SIS_PROP) && !has_idle_core) { + u64 avg_cost, avg_idle, span_avg; + unsigned long now = jiffies; - if (sched_feat(SIS_AVG_CPU) && avg_idle < avg_cost) - return -1; + this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); + if (!this_sd) + return -1; + + /* + * If we're busy, the assumption that the last idle period + * predicts the future is flawed; age away the remaining + * predicted idle time. + */ + if (unlikely(this_rq->wake_stamp < now)) { + while (this_rq->wake_stamp < now && this_rq->wake_avg_idle) { + this_rq->wake_stamp++; + this_rq->wake_avg_idle >>= 1; + } + } + + avg_idle = this_rq->wake_avg_idle; + avg_cost = this_sd->avg_scan_cost + 1; - if (sched_feat(SIS_PROP)) { - u64 span_avg = sd->span_weight * avg_idle; + span_avg = sd->span_weight * avg_idle; if (span_avg > 4*avg_cost) nr = div_u64(span_avg, avg_cost); else nr = 4; + + time = cpu_clock(this); + } + + if (sched_feat(SIS_UTIL)) { + sd_share = rcu_dereference(per_cpu(sd_llc_shared, target)); + if (sd_share) { + /* because !--nr is the condition to stop scan */ + nr = READ_ONCE(sd_share->nr_idle_scan) + 1; + /* overloaded LLC is unlikely to have idle cpu/core */ + if (nr == 1) + return -1; + } } - time = cpu_clock(this); + for_each_cpu_wrap(cpu, cpus, target + 1) { + if (has_idle_core) { + i = select_idle_core(p, cpu, cpus, &idle_cpu); + if ((unsigned int)i < nr_cpumask_bits) + return i; + } else { + if (!--nr) + return -1; + idle_cpu = __select_idle_cpu(cpu, p); + if ((unsigned int)idle_cpu < nr_cpumask_bits) + break; + } + } + + if (has_idle_core) + set_idle_cores(target, false); + + if (sched_feat(SIS_PROP) && this_sd && !has_idle_core) { + time = cpu_clock(this) - time; + + /* + * Account for the scan cost of wakeups against the average + * idle time. + */ + this_rq->wake_avg_idle -= min(this_rq->wake_avg_idle, time); + + update_avg(&this_sd->avg_scan_cost, time); + } + + return idle_cpu; +} + +/* + * Scan the asym_capacity domain for idle CPUs; pick the first idle one on which + * the task fits. If no CPU is big enough, but there are idle ones, try to + * maximize capacity. + */ +static int +select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) +{ + unsigned long task_util, best_cap = 0; + int cpu, best_cpu = -1; + struct cpumask *cpus; + + cpus = this_cpu_cpumask_var_ptr(select_rq_mask); cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + task_util = uclamp_task_util(p); + for_each_cpu_wrap(cpu, cpus, target) { - if (!--nr) - return -1; - if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) - break; + unsigned long cpu_cap = capacity_of(cpu); + + if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) + continue; + if (fits_capacity(task_util, cpu_cap)) + return cpu; + + if (cpu_cap > best_cap) { + best_cap = cpu_cap; + best_cpu = cpu; + } } - time = cpu_clock(this) - time; - cost = this_sd->avg_scan_cost; - delta = (s64)(time - cost) / 8; - this_sd->avg_scan_cost += delta; + return best_cpu; +} + +static inline bool asym_fits_capacity(unsigned long task_util, int cpu) +{ + if (sched_asym_cpucap_active()) + return fits_capacity(task_util, capacity_of(cpu)); - return cpu; + return true; } /* @@ -5898,17 +6693,35 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t */ static int select_idle_sibling(struct task_struct *p, int prev, int target) { + bool has_idle_core = false; struct sched_domain *sd; + unsigned long task_util; int i, recent_used_cpu; - if (available_idle_cpu(target) || sched_idle_cpu(target)) + /* + * On asymmetric system, update task utilization because we will check + * that the task fits with cpu's capacity. + */ + if (sched_asym_cpucap_active()) { + sync_entity_load_avg(&p->se); + task_util = uclamp_task_util(p); + } + + /* + * per-cpu select_rq_mask usage + */ + lockdep_assert_irqs_disabled(); + + if ((available_idle_cpu(target) || sched_idle_cpu(target)) && + asym_fits_capacity(task_util, target)) return target; /* * If the previous CPU is cache affine and idle, don't be stupid: */ if (prev != target && cpus_share_cache(prev, target) && - (available_idle_cpu(prev) || sched_idle_cpu(prev))) + (available_idle_cpu(prev) || sched_idle_cpu(prev)) && + asym_fits_capacity(task_util, prev)) return prev; /* @@ -5920,95 +6733,126 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) * pattern is IO completions. */ if (is_per_cpu_kthread(current) && + in_task() && prev == smp_processor_id() && - this_rq()->nr_running <= 1) { + this_rq()->nr_running <= 1 && + asym_fits_capacity(task_util, prev)) { return prev; } /* Check a recently used CPU as a potential idle candidate: */ recent_used_cpu = p->recent_used_cpu; + p->recent_used_cpu = prev; if (recent_used_cpu != prev && recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && - cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { + cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && + asym_fits_capacity(task_util, recent_used_cpu)) { + return recent_used_cpu; + } + + /* + * For asymmetric CPU capacity systems, our domain of interest is + * sd_asym_cpucapacity rather than sd_llc. + */ + if (sched_asym_cpucap_active()) { + sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, target)); /* - * Replace recent_used_cpu with prev as it is a potential - * candidate for the next wake: + * On an asymmetric CPU capacity system where an exclusive + * cpuset defines a symmetric island (i.e. one unique + * capacity_orig value through the cpuset), the key will be set + * but the CPUs within that cpuset will not have a domain with + * SD_ASYM_CPUCAPACITY. These should follow the usual symmetric + * capacity path. */ - p->recent_used_cpu = prev; - return recent_used_cpu; + if (sd) { + i = select_idle_capacity(p, sd, target); + return ((unsigned)i < nr_cpumask_bits) ? i : target; + } } sd = rcu_dereference(per_cpu(sd_llc, target)); if (!sd) return target; - i = select_idle_core(p, sd, target); - if ((unsigned)i < nr_cpumask_bits) - return i; + if (sched_smt_active()) { + has_idle_core = test_idle_cores(target); - i = select_idle_cpu(p, sd, target); - if ((unsigned)i < nr_cpumask_bits) - return i; + if (!has_idle_core && cpus_share_cache(prev, target)) { + i = select_idle_smt(p, prev); + if ((unsigned int)i < nr_cpumask_bits) + return i; + } + } - i = select_idle_smt(p, target); + i = select_idle_cpu(p, sd, has_idle_core, target); if ((unsigned)i < nr_cpumask_bits) return i; return target; } -/** - * Amount of capacity of a CPU that is (estimated to be) used by CFS tasks - * @cpu: the CPU to get the utilization of - * - * The unit of the return value must be the one of capacity so we can compare - * the utilization with the capacity of the CPU that is available for CFS task - * (ie cpu_capacity). - * - * cfs_rq.avg.util_avg is the sum of running time of runnable tasks plus the - * recent utilization of currently non-runnable tasks on a CPU. It represents - * the amount of utilization of a CPU in the range [0..capacity_orig] where - * capacity_orig is the cpu_capacity available at the highest frequency - * (arch_scale_freq_capacity()). - * The utilization of a CPU converges towards a sum equal to or less than the - * current capacity (capacity_curr <= capacity_orig) of the CPU because it is - * the running time on this CPU scaled by capacity_curr. - * - * The estimated utilization of a CPU is defined to be the maximum between its - * cfs_rq.avg.util_avg and the sum of the estimated utilization of the tasks - * currently RUNNABLE on that CPU. - * This allows to properly represent the expected utilization of a CPU which - * has just got a big task running since a long sleep period. At the same time - * however it preserves the benefits of the "blocked utilization" in - * describing the potential for other tasks waking up on the same CPU. - * - * Nevertheless, cfs_rq.avg.util_avg can be higher than capacity_curr or even - * higher than capacity_orig because of unfortunate rounding in - * cfs.avg.util_avg or just after migrating tasks and new task wakeups until - * the average stabilizes with the new running time. We need to check that the - * utilization stays within the range of [0..capacity_orig] and cap it if - * necessary. Without utilization capping, a group could be seen as overloaded - * (CPU0 utilization at 121% + CPU1 utilization at 80%) whereas CPU1 has 20% of - * available capacity. We allow utilization to overshoot capacity_curr (but not - * capacity_orig) as it useful for predicting the capacity required after task - * migrations (scheduler-driven DVFS). - * - * Return: the (estimated) utilization for the specified CPU - */ -static inline unsigned long cpu_util(int cpu) +/* + * Predicts what cpu_util(@cpu) would return if @p was removed from @cpu + * (@dst_cpu = -1) or migrated to @dst_cpu. + */ +static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) { - struct cfs_rq *cfs_rq; - unsigned int util; + struct cfs_rq *cfs_rq = &cpu_rq(cpu)->cfs; + unsigned long util = READ_ONCE(cfs_rq->avg.util_avg); - cfs_rq = &cpu_rq(cpu)->cfs; - util = READ_ONCE(cfs_rq->avg.util_avg); + /* + * If @dst_cpu is -1 or @p migrates from @cpu to @dst_cpu remove its + * contribution. If @p migrates from another CPU to @cpu add its + * contribution. In all the other cases @cpu is not impacted by the + * migration so its util_avg is already correct. + */ + if (task_cpu(p) == cpu && dst_cpu != cpu) + lsub_positive(&util, task_util(p)); + else if (task_cpu(p) != cpu && dst_cpu == cpu) + util += task_util(p); + + if (sched_feat(UTIL_EST)) { + unsigned long util_est; - if (sched_feat(UTIL_EST)) - util = max(util, READ_ONCE(cfs_rq->avg.util_est.enqueued)); + util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued); - return min_t(unsigned long, util, capacity_orig_of(cpu)); + /* + * During wake-up @p isn't enqueued yet and doesn't contribute + * to any cpu_rq(cpu)->cfs.avg.util_est.enqueued. + * If @dst_cpu == @cpu add it to "simulate" cpu_util after @p + * has been enqueued. + * + * During exec (@dst_cpu = -1) @p is enqueued and does + * contribute to cpu_rq(cpu)->cfs.util_est.enqueued. + * Remove it to "simulate" cpu_util without @p's contribution. + * + * Despite the task_on_rq_queued(@p) check there is still a + * small window for a possible race when an exec + * select_task_rq_fair() races with LB's detach_task(). + * + * detach_task() + * deactivate_task() + * p->on_rq = TASK_ON_RQ_MIGRATING; + * -------------------------------- A + * dequeue_task() \ + * dequeue_task_fair() + Race Time + * util_est_dequeue() / + * -------------------------------- B + * + * The additional check "current == p" is required to further + * reduce the race window. + */ + if (dst_cpu == cpu) + util_est += _task_util_est(p); + else if (unlikely(task_on_rq_queued(p) || current == p)) + lsub_positive(&util_est, _task_util_est(p)); + + util = max(util, util_est); + } + + return min(util, capacity_orig_of(cpu)); } /* @@ -6026,181 +6870,104 @@ static inline unsigned long cpu_util(int cpu) */ static unsigned long cpu_util_without(int cpu, struct task_struct *p) { - struct cfs_rq *cfs_rq; - unsigned int util; - /* Task has no contribution or is new */ if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) - return cpu_util(cpu); - - cfs_rq = &cpu_rq(cpu)->cfs; - util = READ_ONCE(cfs_rq->avg.util_avg); - - /* Discount task's util from CPU's util */ - lsub_positive(&util, task_util(p)); + return cpu_util_cfs(cpu); - /* - * Covered cases: - * - * 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_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_without = (cpu_util - task_util) >= 0 - * - * c) if other tasks are RUNNABLE on that CPU and - * util_est > cpu_util - * then we use util_est since it returns a more restrictive - * estimation of the spare capacity on that CPU, by just - * considering the expected utilization of tasks already - * runnable on that CPU. - * - * Cases a) and b) are covered by the above code, while case c) is - * covered by the following code when estimated utilization is - * enabled. - */ - 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 - * clamp to the maximum CPU capacity to ensure consistency with - * the cpu_util call. - */ - return min_t(unsigned long, util, capacity_orig_of(cpu)); + return cpu_util_next(cpu, p, -1); } /* - * Disable WAKE_AFFINE in the case where task @p doesn't fit in the - * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu. - * - * In that case WAKE_AFFINE doesn't make sense and we'll let - * BALANCE_WAKE sort things out. + * energy_env - Utilization landscape for energy estimation. + * @task_busy_time: Utilization contribution by the task for which we test the + * placement. Given by eenv_task_busy_time(). + * @pd_busy_time: Utilization of the whole perf domain without the task + * contribution. Given by eenv_pd_busy_time(). + * @cpu_cap: Maximum CPU capacity for the perf domain. + * @pd_cap: Entire perf domain capacity. (pd->nr_cpus * cpu_cap). */ -static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) -{ - long min_cap, max_cap; - - if (!static_branch_unlikely(&sched_asym_cpucapacity)) - return 0; - - min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu)); - max_cap = cpu_rq(cpu)->rd->max_cpu_capacity; +struct energy_env { + unsigned long task_busy_time; + unsigned long pd_busy_time; + unsigned long cpu_cap; + unsigned long pd_cap; +}; - /* Minimum capacity is close to max, no need to abort wake_affine */ - if (max_cap - min_cap < max_cap >> 3) - return 0; +/* + * Compute the task busy time for compute_energy(). This time cannot be + * injected directly into effective_cpu_util() because of the IRQ scaling. + * The latter only makes sense with the most recent CPUs where the task has + * run. + */ +static inline void eenv_task_busy_time(struct energy_env *eenv, + struct task_struct *p, int prev_cpu) +{ + unsigned long busy_time, max_cap = arch_scale_cpu_capacity(prev_cpu); + unsigned long irq = cpu_util_irq(cpu_rq(prev_cpu)); - /* Bring task utilization in sync with prev_cpu */ - sync_entity_load_avg(&p->se); + if (unlikely(irq >= max_cap)) + busy_time = max_cap; + else + busy_time = scale_irq_capacity(task_util_est(p), irq, max_cap); - return !task_fits_capacity(p, min_cap); + eenv->task_busy_time = busy_time; } /* - * Predicts what cpu_util(@cpu) would return if @p was migrated (and enqueued) - * to @dst_cpu. + * Compute the perf_domain (PD) busy time for compute_energy(). Based on the + * utilization for each @pd_cpus, it however doesn't take into account + * clamping since the ratio (utilization / cpu_capacity) is already enough to + * scale the EM reported power consumption at the (eventually clamped) + * cpu_capacity. + * + * The contribution of the task @p for which we want to estimate the + * energy cost is removed (by cpu_util_next()) and must be calculated + * separately (see eenv_task_busy_time). This ensures: + * + * - A stable PD utilization, no matter which CPU of that PD we want to place + * the task on. + * + * - A fair comparison between CPUs as the task contribution (task_util()) + * will always be the same no matter which CPU utilization we rely on + * (util_avg or util_est). + * + * Set @eenv busy time for the PD that spans @pd_cpus. This busy time can't + * exceed @eenv->pd_cap. */ -static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) +static inline void eenv_pd_busy_time(struct energy_env *eenv, + struct cpumask *pd_cpus, + struct task_struct *p) { - 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); + unsigned long busy_time = 0; + int cpu; - /* - * 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); + for_each_cpu(cpu, pd_cpus) { + unsigned long util = cpu_util_next(cpu, p, -1); - util = max(util, util_est); + busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL); } - return min(util, capacity_orig_of(cpu)); + eenv->pd_busy_time = min(eenv->pd_cap, busy_time); } /* - * compute_energy(): Estimates the energy that @pd would consume if @p was - * migrated to @dst_cpu. compute_energy() predicts what will be the utilization - * landscape of @pd's 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. + * Compute the maximum utilization for compute_energy() when the task @p + * is placed on the cpu @dst_cpu. + * + * Returns the maximum utilization among @eenv->cpus. This utilization can't + * exceed @eenv->cpu_cap. */ -static long -compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) +static inline unsigned long +eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus, + struct task_struct *p, int dst_cpu) { - struct cpumask *pd_mask = perf_domain_span(pd); - unsigned long cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); - unsigned long max_util = 0, sum_util = 0; + unsigned long max_util = 0; int cpu; - /* - * The capacity state of CPUs of the current rd can be driven by CPUs - * of another rd if they belong to the same pd. So, account for the - * utilization of these CPUs too by masking pd with cpu_online_mask - * instead of the rd span. - * - * If an entire pd 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, pd_mask, cpu_online_mask) { - unsigned long cpu_util, util_cfs = cpu_util_next(cpu, p, dst_cpu); - struct task_struct *tsk = cpu == dst_cpu ? p : NULL; - - /* - * Busy time computation: utilization clamping is not - * required since the ratio (sum_util / cpu_capacity) - * is already enough to scale the EM reported power - * consumption at the (eventually clamped) cpu_capacity. - */ - sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap, - ENERGY_UTIL, NULL); + for_each_cpu(cpu, pd_cpus) { + struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL; + unsigned long util = cpu_util_next(cpu, p, dst_cpu); + unsigned long cpu_util; /* * Performance domain frequency: utilization clamping @@ -6209,12 +6976,29 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * NOTE: in case RT tasks are running, by default the * FREQUENCY_UTIL's utilization can be max OPP. */ - cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap, - FREQUENCY_UTIL, tsk); + cpu_util = effective_cpu_util(cpu, util, FREQUENCY_UTIL, tsk); max_util = max(max_util, cpu_util); } - return em_pd_energy(pd->em_pd, max_util, sum_util); + return min(max_util, eenv->cpu_cap); +} + +/* + * compute_energy(): Use the Energy Model to estimate the energy that @pd would + * consume for a given utilization landscape @eenv. When @dst_cpu < 0, the task + * contribution is ignored. + */ +static inline unsigned long +compute_energy(struct energy_env *eenv, struct perf_domain *pd, + struct cpumask *pd_cpus, struct task_struct *p, int dst_cpu) +{ + unsigned long max_util = eenv_pd_max_util(eenv, pd_cpus, p, dst_cpu); + unsigned long busy_time = eenv->pd_busy_time; + + if (dst_cpu >= 0) + busy_time = min(eenv->pd_cap, busy_time + eenv->task_busy_time); + + return em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap); } /* @@ -6258,17 +7042,18 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) */ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; - struct root_domain *rd = cpu_rq(smp_processor_id())->rd; - unsigned long cpu_cap, util, base_energy = 0; - int cpu, best_energy_cpu = prev_cpu; + struct root_domain *rd = this_rq()->rd; + int cpu, best_energy_cpu, target = -1; struct sched_domain *sd; struct perf_domain *pd; + struct energy_env eenv; rcu_read_lock(); pd = rcu_dereference(rd->pd); if (!pd || READ_ONCE(rd->overutilized)) - goto fail; + goto unlock; /* * Energy-aware wake-up happens on the lowest sched_domain starting @@ -6278,110 +7063,145 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) sd = sd->parent; if (!sd) - goto fail; + goto unlock; + + target = prev_cpu; sync_entity_load_avg(&p->se); if (!task_util_est(p)) goto unlock; + eenv_task_busy_time(&eenv, p, prev_cpu); + for (; pd; pd = pd->next) { - unsigned long cur_delta, spare_cap, max_spare_cap = 0; - unsigned long base_energy_pd; + unsigned long cpu_cap, cpu_thermal_cap, util; + unsigned long cur_delta, max_spare_cap = 0; + bool compute_prev_delta = false; int max_spare_cap_cpu = -1; + unsigned long base_energy; - /* Compute the 'base' energy of the pd, without @p */ - base_energy_pd = compute_energy(p, -1, pd); - base_energy += base_energy_pd; + cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask); + + if (cpumask_empty(cpus)) + continue; + + /* Account thermal pressure for the energy estimation */ + cpu = cpumask_first(cpus); + cpu_thermal_cap = arch_scale_cpu_capacity(cpu); + cpu_thermal_cap -= arch_scale_thermal_pressure(cpu); + + eenv.cpu_cap = cpu_thermal_cap; + eenv.pd_cap = 0; + + for_each_cpu(cpu, cpus) { + eenv.pd_cap += cpu_thermal_cap; + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; - for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); - spare_cap = cpu_cap - util; /* * Skip CPUs that cannot satisfy the capacity request. * IOW, placing the task there would make the CPU * overutilized. Take uclamp into account to see how * much capacity we can get out of the CPU; this is - * aligned with schedutil_cpu_util(). + * aligned with sched_cpu_util(). */ util = uclamp_rq_util_with(cpu_rq(cpu), util, p); if (!fits_capacity(util, cpu_cap)) continue; - /* Always use prev_cpu as a candidate. */ - if (cpu == prev_cpu) { - prev_delta = compute_energy(p, prev_cpu, pd); - prev_delta -= base_energy_pd; - best_delta = min(best_delta, prev_delta); - } + lsub_positive(&cpu_cap, util); - /* - * Find the CPU with the maximum spare capacity in - * the performance domain - */ - if (spare_cap > max_spare_cap) { - max_spare_cap = spare_cap; + if (cpu == prev_cpu) { + /* Always use prev_cpu as a candidate. */ + compute_prev_delta = true; + } else if (cpu_cap > max_spare_cap) { + /* + * Find the CPU with the maximum spare capacity + * in the performance domain. + */ + max_spare_cap = cpu_cap; max_spare_cap_cpu = cpu; } } - /* Evaluate the energy impact of using this CPU. */ - if (max_spare_cap_cpu >= 0 && max_spare_cap_cpu != prev_cpu) { - cur_delta = compute_energy(p, max_spare_cap_cpu, pd); - cur_delta -= base_energy_pd; + if (max_spare_cap_cpu < 0 && !compute_prev_delta) + continue; + + eenv_pd_busy_time(&eenv, cpus, p); + /* Compute the 'base' energy of the pd, without @p */ + base_energy = compute_energy(&eenv, pd, cpus, p, -1); + + /* Evaluate the energy impact of using prev_cpu. */ + if (compute_prev_delta) { + prev_delta = compute_energy(&eenv, pd, cpus, p, + prev_cpu); + /* CPU utilization has changed */ + if (prev_delta < base_energy) + goto unlock; + prev_delta -= base_energy; + best_delta = min(best_delta, prev_delta); + } + + /* Evaluate the energy impact of using max_spare_cap_cpu. */ + if (max_spare_cap_cpu >= 0) { + cur_delta = compute_energy(&eenv, pd, cpus, p, + max_spare_cap_cpu); + /* CPU utilization has changed */ + if (cur_delta < base_energy) + goto unlock; + cur_delta -= base_energy; if (cur_delta < best_delta) { best_delta = cur_delta; 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_delta == ULONG_MAX) - return best_energy_cpu; - - if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4)) - return best_energy_cpu; + if (best_delta < prev_delta) + target = best_energy_cpu; - return prev_cpu; + return target; -fail: +unlock: rcu_read_unlock(); - return -1; + return target; } /* * 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, + * that have the relevant SD flag set. In practice, this is SD_BALANCE_WAKE, * SD_BALANCE_FORK, or SD_BALANCE_EXEC. * * Balances load by selecting the idlest CPU in the idlest group, or under * certain conditions an idle sibling CPU if the domain has SD_WAKE_AFFINE set. * * Returns the target CPU number. - * - * preempt must be disabled. */ static int -select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags) +select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags) { + int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING); struct sched_domain *tmp, *sd = NULL; int cpu = smp_processor_id(); int new_cpu = prev_cpu; int want_affine = 0; - int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING); + /* SD_flags and WF_flags share the first nibble */ + int sd_flag = wake_flags & 0xF; - if (sd_flag & SD_BALANCE_WAKE) { + /* + * required for stable ->cpus_allowed + */ + lockdep_assert_held(&p->pi_lock); + if (wake_flags & WF_TTWU) { record_wakee(p); if (sched_energy_enabled()) { @@ -6391,15 +7211,11 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f new_cpu = prev_cpu; } - want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) && - cpumask_test_cpu(cpu, p->cpus_ptr); + want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr); } rcu_read_lock(); for_each_domain(cpu, tmp) { - if (!(tmp->flags & SD_LOAD_BALANCE)) - break; - /* * If both 'cpu' and 'prev_cpu' are part of this domain, * cpu is a valid SD_WAKE_AFFINE target. @@ -6413,6 +7229,11 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f break; } + /* + * Usually only true for WF_EXEC and WF_FORK, as sched_domains + * usually do not have SD_BALANCE_WAKE set. That means wakeup + * will usually go to the fast path. + */ if (tmp->flags & sd_flag) sd = tmp; else if (!want_affine) @@ -6422,21 +7243,15 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (unlikely(sd)) { /* Slow path */ new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); - } else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */ + } else if (wake_flags & WF_TTWU) { /* XXX always ? */ /* Fast path */ - new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); - - if (want_affine) - current->recent_used_cpu = cpu; } rcu_read_unlock(); return new_cpu; } -static void detach_entity_cfs_rq(struct sched_entity *se); - /* * Called immediately before a task is migrated to a new CPU; task_cpu(p) and * cfs_rq_of(p) references at time of call are still valid and identify the @@ -6444,57 +7259,41 @@ static void detach_entity_cfs_rq(struct sched_entity *se); */ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) { + struct sched_entity *se = &p->se; + /* * As blocked tasks retain absolute vruntime the migration needs to * deal with this by subtracting the old and adding the new * min_vruntime -- the latter is done by enqueue_entity() when placing * the task on the new runqueue. */ - if (p->state == TASK_WAKING) { - struct sched_entity *se = &p->se; + if (READ_ONCE(p->__state) == TASK_WAKING) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 min_vruntime; - -#ifndef CONFIG_64BIT - u64 min_vruntime_copy; - - do { - min_vruntime_copy = cfs_rq->min_vruntime_copy; - smp_rmb(); - min_vruntime = cfs_rq->min_vruntime; - } while (min_vruntime != min_vruntime_copy); -#else - min_vruntime = cfs_rq->min_vruntime; -#endif - se->vruntime -= min_vruntime; + se->vruntime -= u64_u32_load(cfs_rq->min_vruntime); } - if (p->on_rq == TASK_ON_RQ_MIGRATING) { - /* - * In case of TASK_ON_RQ_MIGRATING we in fact hold the 'old' - * rq->lock and can modify state directly. - */ - lockdep_assert_held(&task_rq(p)->lock); - detach_entity_cfs_rq(&p->se); + if (!task_on_rq_migrating(p)) { + remove_entity_load_avg(se); - } else { /* - * We are supposed to update the task to "current" time, then - * its up to date and ready to go to new CPU/cfs_rq. But we - * have difficulty in getting what current time is, so simply - * throw away the out-of-date time. This will result in the - * wakee task is less decayed, but giving the wakee more load - * sounds not bad. + * Here, the task's PELT values have been updated according to + * the current rq's clock. But if that clock hasn't been + * updated in a while, a substantial idle time will be missed, + * leading to an inflation after wake-up on the new rq. + * + * Estimate the missing time from the cfs_rq last_update_time + * and update sched_avg to improve the PELT continuity after + * migration. */ - remove_entity_load_avg(&p->se); + migrate_se_pelt_lag(se); } /* Tell new CPU we are migrated */ - p->se.avg.last_update_time = 0; + se->avg.last_update_time = 0; /* We have migrated, no longer consider this task hot */ - p->se.exec_start = 0; + se->exec_start = 0; update_scan_period(p, new_cpu); } @@ -6565,24 +7364,22 @@ 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_has_idle_policy(task_of(se)))) - return; - for_each_sched_entity(se) { if (SCHED_WARN_ON(!se->on_rq)) return; + if (se_is_idle(se)) + return; cfs_rq_of(se)->last = se; } } static void set_next_buddy(struct sched_entity *se) { - if (entity_is_task(se) && unlikely(task_has_idle_policy(task_of(se)))) - return; - for_each_sched_entity(se) { if (SCHED_WARN_ON(!se->on_rq)) return; + if (se_is_idle(se)) + return; cfs_rq_of(se)->next = se; } } @@ -6603,13 +7400,14 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ struct cfs_rq *cfs_rq = task_cfs_rq(curr); int scale = cfs_rq->nr_running >= sched_nr_latency; int next_buddy_marked = 0; + int cse_is_idle, pse_is_idle; if (unlikely(se == pse)) return; /* * This is possible from callers such as attach_tasks(), in which we - * unconditionally check_prempt_curr() after an enqueue (which may have + * unconditionally check_preempt_curr() after an enqueue (which may have * lead to a throttle). This both saves work and prevents false * next-buddy nomination below. */ @@ -6647,8 +7445,21 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ return; find_matching_se(&se, &pse); + WARN_ON_ONCE(!pse); + + cse_is_idle = se_is_idle(se); + pse_is_idle = se_is_idle(pse); + + /* + * Preempt an idle group in favor of a non-idle group (and don't preempt + * in the inverse case). + */ + if (cse_is_idle && !pse_is_idle) + goto preempt; + if (cse_is_idle != pse_is_idle) + return; + update_curr(cfs_rq_of(se)); - BUG_ON(!pse); if (wakeup_preempt_entity(se, pse) == 1) { /* * Bias pick_next to pick the sched entity that is @@ -6679,6 +7490,39 @@ preempt: set_last_buddy(se); } +#ifdef CONFIG_SMP +static struct task_struct *pick_task_fair(struct rq *rq) +{ + struct sched_entity *se; + struct cfs_rq *cfs_rq; + +again: + cfs_rq = &rq->cfs; + if (!cfs_rq->nr_running) + return NULL; + + do { + struct sched_entity *curr = cfs_rq->curr; + + /* When we pick for a remote RQ, we'll not have done put_prev_entity() */ + if (curr) { + if (curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; + + if (unlikely(check_cfs_rq_runtime(cfs_rq))) + goto again; + } + + se = pick_next_entity(cfs_rq, curr); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + return task_of(se); +} +#endif + struct task_struct * pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { @@ -6790,7 +7634,7 @@ done: __maybe_unused; list_move(&p->se.group_node, &rq->cfs_tasks); #endif - if (hrtick_enabled(rq)) + if (hrtick_enabled_fair(rq)) hrtick_start_fair(rq, p); update_misfit_status(p, rq); @@ -6878,7 +7722,7 @@ static void yield_task_fair(struct rq *rq) set_skip_buddy(se); } -static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preempt) +static bool yield_to_task_fair(struct rq *rq, struct task_struct *p) { struct sched_entity *se = &p->se; @@ -7033,8 +7877,8 @@ enum group_type { */ group_fully_busy, /* - * SD_ASYM_CPUCAPACITY only: One task doesn't fit with CPU's capacity - * and must be migrated to a more powerful CPU. + * One task doesn't fit with CPU's capacity and must be migrated to a + * more powerful CPU. */ group_misfit_task, /* @@ -7066,8 +7910,7 @@ enum migration_type { #define LBF_NEED_BREAK 0x02 #define LBF_DST_PINNED 0x04 #define LBF_SOME_PINNED 0x08 -#define LBF_NOHZ_STATS 0x10 -#define LBF_NOHZ_AGAIN 0x20 +#define LBF_ACTIVE_LB 0x10 struct lb_env { struct sched_domain *sd; @@ -7103,7 +7946,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env) { s64 delta; - lockdep_assert_held(&env->src_rq->lock); + lockdep_assert_rq_held(env->src_rq); if (p->sched_class != &fair_sched_class) return 0; @@ -7111,6 +7954,10 @@ static int task_hot(struct task_struct *p, struct lb_env *env) if (unlikely(task_has_idle_policy(p))) return 0; + /* SMT siblings share cache */ + if (env->sd->flags & SD_SHARE_CPUCAPACITY) + return 0; + /* * Buddy candidates are cache hot: */ @@ -7121,6 +7968,14 @@ static int task_hot(struct task_struct *p, struct lb_env *env) if (sysctl_sched_migration_cost == -1) return 1; + + /* + * Don't migrate task if the task's cookie does not match + * with the destination CPU's core cookie. + */ + if (!sched_core_cookie_match(cpu_rq(env->dst_cpu), p)) + return 1; + if (sysctl_sched_migration_cost == 0) return 0; @@ -7197,7 +8052,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) { int tsk_cache_hot; - lockdep_assert_held(&env->src_rq->lock); + lockdep_assert_rq_held(env->src_rq); /* * We do not migrate tasks that are: @@ -7209,10 +8064,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) return 0; + /* Disregard pcpu kthreads; they are where they need to be. */ + if (kthread_is_per_cpu(p)) + return 0; + if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) { int cpu; - schedstat_inc(p->se.statistics.nr_failed_migrations_affine); + schedstat_inc(p->stats.nr_failed_migrations_affine); env->flags |= LBF_SOME_PINNED; @@ -7221,10 +8080,13 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) * our sched_group. We may want to revisit it if we couldn't * meet load balance goals by pulling other tasks on src_cpu. * - * Avoid computing new_dst_cpu for NEWLY_IDLE or if we have - * already computed one in current iteration. + * Avoid computing new_dst_cpu + * - for NEWLY_IDLE + * - if we have already computed one in current iteration + * - if it's an active balance */ - if (env->idle == CPU_NEWLY_IDLE || (env->flags & LBF_DST_PINNED)) + if (env->idle == CPU_NEWLY_IDLE || + env->flags & (LBF_DST_PINNED | LBF_ACTIVE_LB)) return 0; /* Prevent to re-select dst_cpu via env's CPUs: */ @@ -7239,20 +8101,24 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) return 0; } - /* Record that we found atleast one task that could run on dst_cpu */ + /* Record that we found at least one task that could run on dst_cpu */ env->flags &= ~LBF_ALL_PINNED; - if (task_running(env->src_rq, p)) { - schedstat_inc(p->se.statistics.nr_failed_migrations_running); + if (task_on_cpu(env->src_rq, p)) { + schedstat_inc(p->stats.nr_failed_migrations_running); return 0; } /* * Aggressive migration if: - * 1) destination numa is preferred - * 2) task is cache cold, or - * 3) too many balance attempts have failed. + * 1) active balance + * 2) destination numa is preferred + * 3) task is cache cold, or + * 4) too many balance attempts have failed. */ + if (env->flags & LBF_ACTIVE_LB) + return 1; + tsk_cache_hot = migrate_degrades_locality(p, env); if (tsk_cache_hot == -1) tsk_cache_hot = task_hot(p, env); @@ -7261,12 +8127,12 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) env->sd->nr_balance_failed > env->sd->cache_nice_tries) { if (tsk_cache_hot == 1) { schedstat_inc(env->sd->lb_hot_gained[env->idle]); - schedstat_inc(p->se.statistics.nr_forced_migrations); + schedstat_inc(p->stats.nr_forced_migrations); } return 1; } - schedstat_inc(p->se.statistics.nr_failed_migrations_hot); + schedstat_inc(p->stats.nr_failed_migrations_hot); return 0; } @@ -7275,7 +8141,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) */ static void detach_task(struct task_struct *p, struct lb_env *env) { - lockdep_assert_held(&env->src_rq->lock); + lockdep_assert_rq_held(env->src_rq); deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, env->dst_cpu); @@ -7291,7 +8157,7 @@ static struct task_struct *detach_one_task(struct lb_env *env) { struct task_struct *p; - lockdep_assert_held(&env->src_rq->lock); + lockdep_assert_rq_held(env->src_rq); list_for_each_entry_reverse(p, &env->src_rq->cfs_tasks, se.group_node) { @@ -7312,8 +8178,6 @@ static struct task_struct *detach_one_task(struct lb_env *env) return NULL; } -static const unsigned int sched_nr_migrate_break = 32; - /* * detach_tasks() -- tries to detach up to imbalance load/util/tasks from * busiest_rq, as part of a balancing operation within domain "sd". @@ -7327,7 +8191,16 @@ static int detach_tasks(struct lb_env *env) struct task_struct *p; int detached = 0; - lockdep_assert_held(&env->src_rq->lock); + lockdep_assert_rq_held(env->src_rq); + + /* + * Source run queue has been emptied by another CPU, clear + * LBF_ALL_PINNED flag as we will not test any task. + */ + if (env->src_rq->nr_running <= 1) { + env->flags &= ~LBF_ALL_PINNED; + return 0; + } if (env->imbalance <= 0) return 0; @@ -7340,26 +8213,37 @@ static int detach_tasks(struct lb_env *env) if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1) break; - p = list_last_entry(tasks, struct task_struct, se.group_node); - env->loop++; - /* We've more or less seen every task there is, call it quits */ - if (env->loop > env->loop_max) + /* + * We've more or less seen every task there is, call it quits + * unless we haven't found any movable task yet. + */ + if (env->loop > env->loop_max && + !(env->flags & LBF_ALL_PINNED)) break; /* take a breather every nr_migrate tasks */ if (env->loop > env->loop_break) { - env->loop_break += sched_nr_migrate_break; + env->loop_break += SCHED_NR_MIGRATE_BREAK; env->flags |= LBF_NEED_BREAK; break; } + p = list_last_entry(tasks, struct task_struct, se.group_node); + if (!can_migrate_task(p, env)) goto next; switch (env->migration_type) { case migrate_load: - load = task_h_load(p); + /* + * Depending of the number of CPUs and tasks and the + * cgroup hierarchy, task_h_load() can return a null + * value. Make sure that env->imbalance decreases + * otherwise detach_tasks() will stop only after + * detaching up to loop_max tasks. + */ + load = max_t(unsigned long, task_h_load(p), 1); if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed) @@ -7371,8 +8255,7 @@ static int detach_tasks(struct lb_env *env) * scheduler fails to find a good waiting task to * migrate. */ - if (load/2 > env->imbalance && - env->sd->nr_balance_failed <= env->sd->cache_nice_tries) + if (shr_bound(load, env->sd->nr_balance_failed) > env->imbalance) goto next; env->imbalance -= load; @@ -7442,9 +8325,9 @@ next: */ static void attach_task(struct rq *rq, struct task_struct *p) { - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); - BUG_ON(task_rq(p) != rq); + WARN_ON_ONCE(task_rq(p) != rq); activate_task(rq, p, ENQUEUE_NOCLOCK); check_preempt_curr(rq, p, 0); } @@ -7506,6 +8389,9 @@ static inline bool others_have_blocked(struct rq *rq) if (READ_ONCE(rq->avg_dl.util_avg)) return true; + if (thermal_load_avg(rq)) + return true; + #ifdef CONFIG_HAVE_SCHED_AVG_IRQ if (READ_ONCE(rq->avg_irq.util_avg)) return true; @@ -7514,16 +8400,20 @@ static inline bool others_have_blocked(struct rq *rq) return false; } -static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) +static inline void update_blocked_load_tick(struct rq *rq) { - rq->last_blocked_load_update_tick = jiffies; + WRITE_ONCE(rq->last_blocked_load_update_tick, jiffies); +} +static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) +{ if (!has_blocked) rq->has_blocked_load = 0; } #else static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { return false; } static inline bool others_have_blocked(struct rq *rq) { return false; } +static inline void update_blocked_load_tick(struct rq *rq) {} static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {} #endif @@ -7531,6 +8421,7 @@ static bool __update_blocked_others(struct rq *rq, bool *done) { const struct sched_class *curr_class; u64 now = rq_clock_pelt(rq); + unsigned long thermal_pressure; bool decayed; /* @@ -7539,8 +8430,11 @@ static bool __update_blocked_others(struct rq *rq, bool *done) */ curr_class = rq->curr->sched_class; + thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); + decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) | update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) | + update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure) | update_irq_load_avg(rq, 0); if (others_have_blocked(rq)) @@ -7551,23 +8445,6 @@ static bool __update_blocked_others(struct rq *rq, bool *done) #ifdef CONFIG_FAIR_GROUP_SCHED -static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) -{ - if (cfs_rq->load.weight) - return false; - - if (cfs_rq->avg.load_sum) - return false; - - if (cfs_rq->avg.util_sum) - return false; - - if (cfs_rq->avg.runnable_load_sum) - return false; - - return true; -} - static bool __update_blocked_fair(struct rq *rq, bool *done) { struct cfs_rq *cfs_rq, *pos; @@ -7582,7 +8459,10 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) struct sched_entity *se; if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) { - update_tg_load_avg(cfs_rq, 0); + update_tg_load_avg(cfs_rq); + + if (cfs_rq->nr_running == 0) + update_idle_cfs_rq_clock_pelt(cfs_rq); if (cfs_rq == &rq->cfs) decayed = true; @@ -7591,7 +8471,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) /* Propagate pending load changes to the parent, if any: */ se = cfs_rq->tg->se[cpu]; if (se && !skip_blocked_update(se)) - update_load_avg(cfs_rq_of(se), se, 0); + update_load_avg(cfs_rq_of(se), se, UPDATE_TG); /* * There can be a lot of idle CPU cgroups. Don't let fully @@ -7680,6 +8560,7 @@ static void update_blocked_averages(int cpu) struct rq_flags rf; rq_lock_irqsave(rq, &rf); + update_blocked_load_tick(rq); update_rq_clock(rq); decayed |= __update_blocked_others(rq, &done); @@ -7700,7 +8581,8 @@ struct sg_lb_stats { unsigned long avg_load; /*Avg load across the CPUs of the group */ unsigned long group_load; /* Total load over the CPUs of the group */ unsigned long group_capacity; - unsigned long group_util; /* Total utilization of the group */ + unsigned long group_util; /* Total utilization over the CPUs of the group */ + unsigned long group_runnable; /* Total runnable time over the CPUs of the group */ unsigned int sum_nr_running; /* Nr of tasks running in the group */ unsigned int sum_h_nr_running; /* Nr of CFS tasks running in the group */ unsigned int idle_cpus; @@ -7751,7 +8633,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) }; } -static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) +static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long max = arch_scale_cpu_capacity(cpu); @@ -7763,8 +8645,15 @@ static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) if (unlikely(irq >= max)) return 1; + /* + * avg_rt.util_avg and avg_dl.util_avg track binary signals + * (running and not running) with weights 0 and 1024 respectively. + * avg_thermal.load_avg tracks thermal pressure and the weighted + * average uses the actual delta max capacity(load). + */ used = READ_ONCE(rq->avg_rt.util_avg); used += READ_ONCE(rq->avg_dl.util_avg); + used += thermal_load_avg(rq); if (unlikely(used >= max)) return 1; @@ -7776,7 +8665,7 @@ static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) static void update_cpu_capacity(struct sched_domain *sd, int cpu) { - unsigned long capacity = scale_rt_capacity(sd, cpu); + unsigned long capacity = scale_rt_capacity(cpu); struct sched_group *sdg = sd->groups; cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); @@ -7785,6 +8674,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) capacity = 1; cpu_rq(cpu)->cpu_capacity = capacity; + trace_sched_cpu_capacity_tp(cpu_rq(cpu)); + sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; sdg->sgc->max_capacity = capacity; @@ -7906,7 +8797,7 @@ static inline int sg_imbalanced(struct sched_group *group) /* * group_has_capacity returns true if the group has spare capacity that could * be used by some tasks. - * We consider that a group has spare capacity if the * number of task is + * We consider that a group has spare capacity if the number of task is * smaller than the number of CPUs or if the utilization is lower than the * available capacity for CFS tasks. * For the latter, we use a threshold to stabilize the state, to take into @@ -7921,6 +8812,10 @@ group_has_capacity(unsigned int imbalance_pct, struct sg_lb_stats *sgs) if (sgs->sum_nr_running < sgs->group_weight) return true; + if ((sgs->group_capacity * imbalance_pct) < + (sgs->group_runnable * 100)) + return false; + if ((sgs->group_capacity * 100) > (sgs->group_util * imbalance_pct)) return true; @@ -7946,27 +8841,11 @@ group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs) (sgs->group_util * imbalance_pct)) return true; - return false; -} - -/* - * group_smaller_min_cpu_capacity: Returns true if sched_group sg has smaller - * per-CPU capacity than sched_group ref. - */ -static inline bool -group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) -{ - return fits_capacity(sg->sgc->min_capacity, ref->sgc->min_capacity); -} + if ((sgs->group_capacity * imbalance_pct) < + (sgs->group_runnable * 100)) + return true; -/* - * group_smaller_max_cpu_capacity: Returns true if sched_group sg has smaller - * per-CPU capacity_orig than sched_group ref. - */ -static inline bool -group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref) -{ - return fits_capacity(sg->sgc->max_capacity, ref->sgc->max_capacity); + return false; } static inline enum @@ -7992,36 +8871,124 @@ group_type group_classify(unsigned int imbalance_pct, return group_has_spare; } -static bool update_nohz_stats(struct rq *rq, bool force) +/** + * asym_smt_can_pull_tasks - Check whether the load balancing CPU can pull tasks + * @dst_cpu: Destination CPU of the load balancing + * @sds: Load-balancing data with statistics of the local group + * @sgs: Load-balancing statistics of the candidate busiest group + * @sg: The candidate busiest group + * + * Check the state of the SMT siblings of both @sds::local and @sg and decide + * if @dst_cpu can pull tasks. + * + * If @dst_cpu does not have SMT siblings, it can pull tasks if two or more of + * the SMT siblings of @sg are busy. If only one CPU in @sg is busy, pull tasks + * only if @dst_cpu has higher priority. + * + * If both @dst_cpu and @sg have SMT siblings, and @sg has exactly one more + * busy CPU than @sds::local, let @dst_cpu pull tasks if it has higher priority. + * Bigger imbalances in the number of busy CPUs will be dealt with in + * update_sd_pick_busiest(). + * + * If @sg does not have SMT siblings, only pull tasks if all of the SMT siblings + * of @dst_cpu are idle and @sg has lower priority. + * + * Return: true if @dst_cpu can pull tasks, false otherwise. + */ +static bool asym_smt_can_pull_tasks(int dst_cpu, struct sd_lb_stats *sds, + struct sg_lb_stats *sgs, + struct sched_group *sg) { -#ifdef CONFIG_NO_HZ_COMMON - unsigned int cpu = rq->cpu; +#ifdef CONFIG_SCHED_SMT + bool local_is_smt, sg_is_smt; + int sg_busy_cpus; - if (!rq->has_blocked_load) - return false; + local_is_smt = sds->local->flags & SD_SHARE_CPUCAPACITY; + sg_is_smt = sg->flags & SD_SHARE_CPUCAPACITY; - if (!cpumask_test_cpu(cpu, nohz.idle_cpus_mask)) - return false; + sg_busy_cpus = sgs->group_weight - sgs->idle_cpus; - if (!force && !time_after(jiffies, rq->last_blocked_load_update_tick)) - return true; + if (!local_is_smt) { + /* + * If we are here, @dst_cpu is idle and does not have SMT + * siblings. Pull tasks if candidate group has two or more + * busy CPUs. + */ + if (sg_busy_cpus >= 2) /* implies sg_is_smt */ + return true; - update_blocked_averages(cpu); + /* + * @dst_cpu does not have SMT siblings. @sg may have SMT + * siblings and only one is busy. In such case, @dst_cpu + * can help if it has higher priority and is idle (i.e., + * it has no running tasks). + */ + return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu); + } - return rq->has_blocked_load; + /* @dst_cpu has SMT siblings. */ + + if (sg_is_smt) { + int local_busy_cpus = sds->local->group_weight - + sds->local_stat.idle_cpus; + int busy_cpus_delta = sg_busy_cpus - local_busy_cpus; + + if (busy_cpus_delta == 1) + return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu); + + return false; + } + + /* + * @sg does not have SMT siblings. Ensure that @sds::local does not end + * up with more than one busy SMT sibling and only pull tasks if there + * are not busy CPUs (i.e., no CPU has running tasks). + */ + if (!sds->local_stat.sum_nr_running) + return sched_asym_prefer(dst_cpu, sg->asym_prefer_cpu); + + return false; #else + /* Always return false so that callers deal with non-SMT cases. */ return false; #endif } +static inline bool +sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs, + struct sched_group *group) +{ + /* Only do SMT checks if either local or candidate have SMT siblings */ + if ((sds->local->flags & SD_SHARE_CPUCAPACITY) || + (group->flags & SD_SHARE_CPUCAPACITY)) + return asym_smt_can_pull_tasks(env->dst_cpu, sds, sgs, group); + + return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu); +} + +static inline bool +sched_reduced_capacity(struct rq *rq, struct sched_domain *sd) +{ + /* + * When there is more than 1 task, the group_overloaded case already + * takes care of cpu with reduced capacity + */ + if (rq->cfs.h_nr_running != 1) + return false; + + return check_cpu_capacity(rq, sd); +} + /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. + * @sds: Load-balancing data with statistics of the local group. * @group: sched_group whose statistics are to be updated. * @sgs: variable to hold the statistics for this group. * @sg_status: Holds flag indicating the status of the sched_group */ static inline void update_sg_lb_stats(struct lb_env *env, + struct sd_lb_stats *sds, struct sched_group *group, struct sg_lb_stats *sgs, int *sg_status) @@ -8030,16 +8997,15 @@ static inline void update_sg_lb_stats(struct lb_env *env, memset(sgs, 0, sizeof(*sgs)); - local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group)); + local_group = group == sds->local; for_each_cpu_and(i, sched_group_span(group), env->cpus) { struct rq *rq = cpu_rq(i); + unsigned long load = cpu_load(rq); - if ((env->flags & LBF_NOHZ_STATS) && update_nohz_stats(rq, false)) - env->flags |= LBF_NOHZ_AGAIN; - - sgs->group_load += cpu_load(rq); - sgs->group_util += cpu_util(i); + sgs->group_load += load; + sgs->group_util += cpu_util_cfs(i); + sgs->group_runnable += cpu_runnable(rq); sgs->sum_h_nr_running += rq->cfs.h_nr_running; nr_running = rq->nr_running; @@ -8067,26 +9033,31 @@ static inline void update_sg_lb_stats(struct lb_env *env, if (local_group) continue; - /* Check for a misfit task on the cpu */ - 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; - *sg_status |= SG_OVERLOAD; + if (env->sd->flags & SD_ASYM_CPUCAPACITY) { + /* Check for a misfit task on the cpu */ + if (sgs->group_misfit_task_load < rq->misfit_task_load) { + sgs->group_misfit_task_load = rq->misfit_task_load; + *sg_status |= SG_OVERLOAD; + } + } else if ((env->idle != CPU_NOT_IDLE) && + sched_reduced_capacity(rq, env->sd)) { + /* Check for a task running on a CPU with reduced capacity */ + if (sgs->group_misfit_task_load < load) + sgs->group_misfit_task_load = load; } } - /* Check if dst CPU is idle and preferred to this group */ - if (env->sd->flags & SD_ASYM_PACKING && - env->idle != CPU_NOT_IDLE && - sgs->sum_h_nr_running && - sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu)) { - sgs->group_asym_packing = 1; - } - sgs->group_capacity = group->sgc->capacity; sgs->group_weight = group->group_weight; + /* Check if dst CPU is idle and preferred to this group */ + if (!local_group && env->sd->flags & SD_ASYM_PACKING && + env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running && + sched_asym(env, sds, sgs, group)) { + sgs->group_asym_packing = 1; + } + sgs->group_type = group_classify(env->sd->imbalance_pct, group, sgs); /* Computing avg_load makes sense only when group is overloaded */ @@ -8125,8 +9096,9 @@ static bool update_sd_pick_busiest(struct lb_env *env, * CPUs in the group should either be possible to resolve * internally or be covered by avg_load imbalance (eventually). */ - if (sgs->group_type == group_misfit_task && - (!group_smaller_max_cpu_capacity(sg, sds->local) || + if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && + (sgs->group_type == group_misfit_task) && + (!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) || sds->local_stat.group_type != group_has_spare)) return false; @@ -8210,7 +9182,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, */ if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && (sgs->group_type <= group_fully_busy) && - (group_smaller_min_cpu_capacity(sds->local, sg))) + (capacity_greater(sg->sgc->min_capacity, capacity_of(env->dst_cpu)))) return false; return true; @@ -8286,7 +9258,7 @@ static int idle_cpu_without(int cpu, struct task_struct *p) */ #ifdef CONFIG_SMP - if (!llist_empty(&rq->wake_list)) + if (rq->ttwu_pending) return 0; #endif @@ -8315,6 +9287,7 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, sgs->group_load += cpu_load_without(rq, p); sgs->group_util += cpu_util_without(i, p); + sgs->group_runnable += cpu_runnable_without(rq, p); local = task_running_on_cpu(i, p); sgs->sum_h_nr_running += rq->cfs.h_nr_running - local; @@ -8345,7 +9318,8 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd, * Computing avg_load makes sense only when group is fully busy or * overloaded */ - if (sgs->group_type < group_fully_busy) + if (sgs->group_type == group_fully_busy || + sgs->group_type == group_overloaded) sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) / sgs->group_capacity; } @@ -8387,8 +9361,14 @@ static bool update_pick_idlest(struct sched_group *idlest, case group_has_spare: /* Select group with most idle CPUs */ - if (idlest_sgs->idle_cpus >= sgs->idle_cpus) + if (idlest_sgs->idle_cpus > sgs->idle_cpus) return false; + + /* Select group with lowest group_util */ + if (idlest_sgs->idle_cpus == sgs->idle_cpus && + idlest_sgs->group_util <= sgs->group_util) + return false; + break; } @@ -8402,8 +9382,7 @@ static bool update_pick_idlest(struct sched_group *idlest, * Assumes p is allowed on at least one CPU in sd. */ static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, - int this_cpu, int sd_flag) +find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) { struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups; struct sg_lb_stats local_sgs, tmp_sgs; @@ -8414,9 +9393,6 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, .group_type = group_overloaded, }; - imbalance = scale_load_down(NICE_0_LOAD) * - (sd->imbalance_pct-100) / 100; - do { int local_group; @@ -8425,6 +9401,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, p->cpus_ptr)) continue; + /* Skip over this group if no cookie matched */ + if (!sched_group_cookie_match(cpu_rq(this_cpu), p, group)) + continue; + local_group = cpumask_test_cpu(this_cpu, sched_group_span(group)); @@ -8470,6 +9450,11 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, switch (local_sgs.group_type) { case group_overloaded: case group_fully_busy: + + /* Calculate allowed imbalance based on load */ + imbalance = scale_load_down(NICE_0_LOAD) * + (sd->imbalance_pct-100) / 100; + /* * When comparing groups across NUMA domains, it's possible for * the local domain to be very lightly loaded relative to the @@ -8506,7 +9491,9 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, break; case group_has_spare: +#ifdef CONFIG_NUMA if (sd->flags & SD_NUMA) { + int imb_numa_nr = sd->imb_numa_nr; #ifdef CONFIG_NUMA_BALANCING int idlest_cpu; /* @@ -8519,16 +9506,31 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, idlest_cpu = cpumask_first(sched_group_span(idlest)); if (cpu_to_node(idlest_cpu) == p->numa_preferred_nid) return idlest; -#endif +#endif /* CONFIG_NUMA_BALANCING */ /* - * Otherwise, keep the task on this node to stay close - * its wakeup source and improve locality. If there is - * a real need of migration, periodic load balance will + * Otherwise, keep the task close to the wakeup source + * and improve locality if the number of running tasks + * would remain below threshold where an imbalance is + * allowed while accounting for the possibility the + * task is pinned to a subset of CPUs. If there is a + * real need of migration, periodic load balance will * take care of it. */ - if (local_sgs.idle_cpus) + if (p->nr_cpus_allowed != NR_CPUS) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); + + cpumask_and(cpus, sched_group_span(local), p->cpus_ptr); + imb_numa_nr = min(cpumask_weight(cpus), sd->imb_numa_nr); + } + + imbalance = abs(local_sgs.idle_cpus - idlest_sgs.idle_cpus); + if (!adjust_numa_imbalance(imbalance, + local_sgs.sum_nr_running + 1, + imb_numa_nr)) { return NULL; + } } +#endif /* CONFIG_NUMA */ /* * Select group with highest number of idle CPUs. We could also @@ -8544,6 +9546,77 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, return idlest; } +static void update_idle_cpu_scan(struct lb_env *env, + unsigned long sum_util) +{ + struct sched_domain_shared *sd_share; + int llc_weight, pct; + u64 x, y, tmp; + /* + * Update the number of CPUs to scan in LLC domain, which could + * be used as a hint in select_idle_cpu(). The update of sd_share + * could be expensive because it is within a shared cache line. + * So the write of this hint only occurs during periodic load + * balancing, rather than CPU_NEWLY_IDLE, because the latter + * can fire way more frequently than the former. + */ + if (!sched_feat(SIS_UTIL) || env->idle == CPU_NEWLY_IDLE) + return; + + llc_weight = per_cpu(sd_llc_size, env->dst_cpu); + if (env->sd->span_weight != llc_weight) + return; + + sd_share = rcu_dereference(per_cpu(sd_llc_shared, env->dst_cpu)); + if (!sd_share) + return; + + /* + * The number of CPUs to search drops as sum_util increases, when + * sum_util hits 85% or above, the scan stops. + * The reason to choose 85% as the threshold is because this is the + * imbalance_pct(117) when a LLC sched group is overloaded. + * + * let y = SCHED_CAPACITY_SCALE - p * x^2 [1] + * and y'= y / SCHED_CAPACITY_SCALE + * + * x is the ratio of sum_util compared to the CPU capacity: + * x = sum_util / (llc_weight * SCHED_CAPACITY_SCALE) + * y' is the ratio of CPUs to be scanned in the LLC domain, + * and the number of CPUs to scan is calculated by: + * + * nr_scan = llc_weight * y' [2] + * + * When x hits the threshold of overloaded, AKA, when + * x = 100 / pct, y drops to 0. According to [1], + * p should be SCHED_CAPACITY_SCALE * pct^2 / 10000 + * + * Scale x by SCHED_CAPACITY_SCALE: + * x' = sum_util / llc_weight; [3] + * + * and finally [1] becomes: + * y = SCHED_CAPACITY_SCALE - + * x'^2 * pct^2 / (10000 * SCHED_CAPACITY_SCALE) [4] + * + */ + /* equation [3] */ + x = sum_util; + do_div(x, llc_weight); + + /* equation [4] */ + pct = env->sd->imbalance_pct; + tmp = x * x * pct * pct; + do_div(tmp, 10000 * SCHED_CAPACITY_SCALE); + tmp = min_t(long, tmp, SCHED_CAPACITY_SCALE); + y = SCHED_CAPACITY_SCALE - tmp; + + /* equation [2] */ + y *= llc_weight; + do_div(y, SCHED_CAPACITY_SCALE); + if ((int)y != sd_share->nr_idle_scan) + WRITE_ONCE(sd_share->nr_idle_scan, (int)y); +} + /** * update_sd_lb_stats - Update sched_domain's statistics for load balancing. * @env: The load balancing environment. @@ -8556,13 +9629,9 @@ 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; + unsigned long sum_util = 0; 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 - do { struct sg_lb_stats *sgs = &tmp_sgs; int local_group; @@ -8577,7 +9646,7 @@ 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, sgs, &sg_status); + update_sg_lb_stats(env, sds, sg, sgs, &sg_status); if (local_group) goto next_group; @@ -8593,20 +9662,13 @@ next_group: sds->total_load += sgs->group_load; sds->total_capacity += sgs->group_capacity; + sum_util += sgs->group_util; sg = sg->next; } while (sg != env->sd->groups); /* Tag domain that child domain prefers tasks go to siblings first */ sds->prefer_sibling = child && child->flags & SD_PREFER_SIBLING; -#ifdef CONFIG_NO_HZ_COMMON - if ((env->flags & LBF_NOHZ_AGAIN) && - cpumask_subset(nohz.idle_cpus_mask, sched_domain_span(env->sd))) { - - WRITE_ONCE(nohz.next_blocked, - jiffies + msecs_to_jiffies(LOAD_AVG_PERIOD)); - } -#endif if (env->sd->flags & SD_NUMA) env->fbq_type = fbq_classify_group(&sds->busiest_stat); @@ -8626,6 +9688,8 @@ next_group: WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); } + + update_idle_cpu_scan(env, sum_util); } /** @@ -8642,9 +9706,18 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s busiest = &sds->busiest_stat; if (busiest->group_type == group_misfit_task) { - /* Set imbalance to allow misfit tasks to be balanced. */ - env->migration_type = migrate_misfit; - env->imbalance = 1; + if (env->sd->flags & SD_ASYM_CPUCAPACITY) { + /* Set imbalance to allow misfit tasks to be balanced. */ + env->migration_type = migrate_misfit; + env->imbalance = 1; + } else { + /* + * Set load imbalance to allow moving task from cpu + * with reduced capacity. + */ + env->migration_type = migrate_load; + env->imbalance = busiest->group_misfit_task_load; + } return; } @@ -8675,7 +9748,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * emptying busiest. */ if (local->group_type == group_has_spare) { - if (busiest->group_type > group_fully_busy) { + if ((busiest->group_type > group_fully_busy) && + !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) { /* * If busiest is overloaded, try to fill spare * capacity. This might end up creating spare capacity @@ -8711,7 +9785,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ env->migration_type = migrate_task; lsub_positive(&nr_diff, local->sum_nr_running); - env->imbalance = nr_diff >> 1; + env->imbalance = nr_diff; } else { /* @@ -8719,29 +9793,21 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * idle cpus. */ env->migration_type = migrate_task; - env->imbalance = max_t(long, 0, (local->idle_cpus - - busiest->idle_cpus) >> 1); + env->imbalance = max_t(long, 0, + (local->idle_cpus - busiest->idle_cpus)); } +#ifdef CONFIG_NUMA /* Consider allowing a small imbalance between NUMA groups */ if (env->sd->flags & SD_NUMA) { - unsigned int imbalance_min; - - /* - * Compute an allowed imbalance based on a simple - * pair of communicating tasks that should remain - * local and ignore them. - * - * NOTE: Generally this would have been based on - * the domain size and this was evaluated. However, - * the benefit is similar across a range of workloads - * and machines but scaling by the domain size adds - * the risk that lower domains have to be rebalanced. - */ - imbalance_min = 2; - if (busiest->sum_nr_running <= imbalance_min) - env->imbalance = 0; + env->imbalance = adjust_numa_imbalance(env->imbalance, + local->sum_nr_running + 1, + env->sd->imb_numa_nr); } +#endif + + /* Number of tasks to move to restore balance */ + env->imbalance >>= 1; return; } @@ -8759,6 +9825,15 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s local->avg_load = (local->group_load * SCHED_CAPACITY_SCALE) / local->group_capacity; + /* + * If the local group is more loaded than the selected + * busiest group don't try to pull any tasks. + */ + if (local->avg_load >= busiest->avg_load) { + env->imbalance = 0; + return; + } + sds->avg_load = (sds->total_load * SCHED_CAPACITY_SCALE) / sds->total_capacity; } @@ -8786,7 +9861,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * busiest \ local has_spare fully_busy misfit asym imbalanced overloaded * has_spare nr_idle balanced N/A N/A balanced balanced * fully_busy nr_idle nr_idle N/A N/A balanced balanced - * misfit_task force N/A N/A N/A force force + * misfit_task force N/A N/A N/A N/A N/A * asym_packing force force N/A N/A force force * imbalanced force force N/A N/A force force * overloaded force force N/A N/A force avg_load @@ -8803,12 +9878,11 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /** * find_busiest_group - Returns the busiest group within the sched_domain * if there is an imbalance. + * @env: The load balancing environment. * * Also calculates the amount of runnable load which should be moved * to restore balance. * - * @env: The load balancing environment. - * * Return: - The busiest group if imbalance exists. */ static struct sched_group *find_busiest_group(struct lb_env *env) @@ -8978,8 +10052,11 @@ static struct rq *find_busiest_queue(struct lb_env *env, if (rt > env->fbq_type) continue; - capacity = capacity_of(i); nr_running = rq->cfs.h_nr_running; + if (!nr_running) + continue; + + capacity = capacity_of(i); /* * For ASYM_CPUCAPACITY domains, don't pick a CPU that could @@ -8988,7 +10065,13 @@ static struct rq *find_busiest_queue(struct lb_env *env, * average load. */ if (env->sd->flags & SD_ASYM_CPUCAPACITY && - capacity_of(env->dst_cpu) < capacity && + !capacity_greater(capacity_of(env->dst_cpu), capacity) && + nr_running == 1) + continue; + + /* Make sure we only pull tasks from a CPU of lower priority */ + if ((env->sd->flags & SD_ASYM_PACKING) && + sched_asym_prefer(i, env->dst_cpu) && nr_running == 1) continue; @@ -9025,7 +10108,15 @@ static struct rq *find_busiest_queue(struct lb_env *env, break; case migrate_util: - util = cpu_util(cpu_of(rq)); + util = cpu_util_cfs(i); + + /* + * Don't try to pull utilization from a CPU with one + * running task. Whatever its utilization, we will fail + * detach the task. + */ + if (nr_running <= 1) + continue; if (busiest_util < util) { busiest_util = util; @@ -9077,13 +10168,32 @@ asym_active_balance(struct lb_env *env) } static inline bool -voluntary_active_balance(struct lb_env *env) +imbalanced_active_balance(struct lb_env *env) +{ + struct sched_domain *sd = env->sd; + + /* + * The imbalanced case includes the case of pinned tasks preventing a fair + * distribution of the load on the system but also the even distribution of the + * threads on a system with spare capacity + */ + if ((env->migration_type == migrate_task) && + (sd->nr_balance_failed > sd->cache_nice_tries+2)) + return 1; + + return 0; +} + +static int need_active_balance(struct lb_env *env) { struct sched_domain *sd = env->sd; if (asym_active_balance(env)) return 1; + if (imbalanced_active_balance(env)) + return 1; + /* * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task. * It's worth migrating the task if the src_cpu's capacity is reduced @@ -9103,22 +10213,12 @@ voluntary_active_balance(struct lb_env *env) 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); -} - static int active_load_balance_cpu_stop(void *data); static int should_we_balance(struct lb_env *env) { struct sched_group *sg = env->sd->groups; - int cpu, balance_cpu = -1; + int cpu; /* * Ensure the balancing environment is consistent; can happen @@ -9130,27 +10230,27 @@ static int should_we_balance(struct lb_env *env) /* * In the newly idle case, we will allow all the CPUs * to do the newly idle load balance. + * + * However, we bail out if we already have tasks or a wakeup pending, + * to optimize wakeup latency. */ - if (env->idle == CPU_NEWLY_IDLE) + if (env->idle == CPU_NEWLY_IDLE) { + if (env->dst_rq->nr_running > 0 || env->dst_rq->ttwu_pending) + return 0; return 1; + } /* Try to find first idle CPU */ for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) { if (!idle_cpu(cpu)) continue; - balance_cpu = cpu; - break; + /* Are we the first idle CPU? */ + return cpu == env->dst_cpu; } - if (balance_cpu == -1) - balance_cpu = group_balance_cpu(sg); - - /* - * First idle CPU or the first CPU(busiest) in this sched group - * is eligible for doing load balancing at this and above domains. - */ - return balance_cpu == env->dst_cpu; + /* Are we the first CPU of this group ? */ + return group_balance_cpu(sg) == env->dst_cpu; } /* @@ -9167,14 +10267,13 @@ static int load_balance(int this_cpu, struct rq *this_rq, struct rq *busiest; struct rq_flags rf; struct cpumask *cpus = this_cpu_cpumask_var_ptr(load_balance_mask); - struct lb_env env = { .sd = sd, .dst_cpu = this_cpu, .dst_rq = this_rq, .dst_grpmask = sched_group_span(sd->groups), .idle = idle, - .loop_break = sched_nr_migrate_break, + .loop_break = SCHED_NR_MIGRATE_BREAK, .cpus = cpus, .fbq_type = all, .tasks = LIST_HEAD_INIT(env.tasks), @@ -9202,7 +10301,7 @@ redo: goto out_balanced; } - BUG_ON(busiest == env.dst_rq); + WARN_ON_ONCE(busiest == env.dst_rq); schedstat_add(sd->lb_imbalance[idle], env.imbalance); @@ -9210,6 +10309,8 @@ redo: env.src_rq = busiest; ld_moved = 0; + /* Clear this flag as soon as we find a pullable task */ + env.flags |= LBF_ALL_PINNED; if (busiest->nr_running > 1) { /* * Attempt to move tasks. If find_busiest_group has found @@ -9217,7 +10318,6 @@ redo: * still unbalanced. ld_moved simply stays zero, so it is * correctly treated as an imbalance. */ - env.flags |= LBF_ALL_PINNED; env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); more_balance: @@ -9249,7 +10349,9 @@ more_balance: if (env.flags & LBF_NEED_BREAK) { env.flags &= ~LBF_NEED_BREAK; - goto more_balance; + /* Stop if we tried all running tasks */ + if (env.loop < busiest->nr_running) + goto more_balance; } /* @@ -9266,7 +10368,7 @@ more_balance: * load to given_cpu. In rare situations, this may cause * conflicts (balance_cpu and given_cpu/ilb_cpu deciding * _independently_ and at _same_ time to move some load to - * given_cpu) causing exceess load to be moved to given_cpu. + * given_cpu) causing excess load to be moved to given_cpu. * This however should not happen so much in practice and * moreover subsequent load balance cycles should correct the * excess load moved. @@ -9280,7 +10382,7 @@ more_balance: env.dst_cpu = env.new_dst_cpu; env.flags &= ~LBF_DST_PINNED; env.loop = 0; - env.loop_break = sched_nr_migrate_break; + env.loop_break = SCHED_NR_MIGRATE_BREAK; /* * Go back to "more_balance" rather than "redo" since we @@ -9312,7 +10414,7 @@ more_balance: */ if (!cpumask_subset(cpus, env.dst_grpmask)) { env.loop = 0; - env.loop_break = sched_nr_migrate_break; + env.loop_break = SCHED_NR_MIGRATE_BREAK; goto redo; } goto out_all_pinned; @@ -9333,7 +10435,7 @@ more_balance: if (need_active_balance(&env)) { unsigned long flags; - raw_spin_lock_irqsave(&busiest->lock, flags); + raw_spin_rq_lock_irqsave(busiest, flags); /* * Don't kick the active_load_balance_cpu_stop, @@ -9341,12 +10443,13 @@ more_balance: * moved to this_cpu: */ if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { - raw_spin_unlock_irqrestore(&busiest->lock, - flags); - env.flags |= LBF_ALL_PINNED; + raw_spin_rq_unlock_irqrestore(busiest, flags); goto out_one_pinned; } + /* Record that we found at least one task that could run on this_cpu */ + env.flags &= ~LBF_ALL_PINNED; + /* * ->active_balance synchronizes accesses to * ->active_balance_work. Once set, it's cleared @@ -9357,32 +10460,21 @@ more_balance: busiest->push_cpu = this_cpu; active_balance = 1; } - raw_spin_unlock_irqrestore(&busiest->lock, flags); + raw_spin_rq_unlock_irqrestore(busiest, flags); if (active_balance) { stop_one_cpu_nowait(cpu_of(busiest), active_load_balance_cpu_stop, busiest, &busiest->active_balance_work); } - - /* We've kicked active balancing, force task migration. */ - sd->nr_balance_failed = sd->cache_nice_tries+1; } - } else + } else { sd->nr_balance_failed = 0; + } - if (likely(!active_balance) || voluntary_active_balance(&env)) { + if (likely(!active_balance) || need_active_balance(&env)) { /* We were unbalanced, so reset the balancing interval */ sd->balance_interval = sd->min_interval; - } else { - /* - * If we've begun active balancing, start to back off. This - * case may not be covered by the all_pinned logic if there - * is only 1 task on the busy runqueue (because we don't call - * detach_tasks). - */ - if (sd->balance_interval < sd->max_interval) - sd->balance_interval *= 2; } goto out; @@ -9416,7 +10508,7 @@ out_one_pinned: /* * newidle_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 + * skyrocketing in a short amount of time. Skip the balance_interval * increase logic to avoid that. */ if (env.idle == CPU_NEWLY_IDLE) @@ -9441,6 +10533,15 @@ get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) /* scale ms to jiffies */ interval = msecs_to_jiffies(interval); + + /* + * Reduce likelihood of busy balancing at higher domains racing with + * balancing at lower domains by preventing their balancing periods + * from being multiples of each other. + */ + if (cpu_busy) + interval -= 1; + interval = clamp(interval, 1UL, max_load_balance_interval); return interval; @@ -9498,14 +10599,13 @@ static int active_load_balance_cpu_stop(void *data) * we need to fix it. Originally reported by * Bjorn Helgaas on a 128-CPU setup. */ - BUG_ON(busiest_rq == target_rq); + WARN_ON_ONCE(busiest_rq == target_rq); /* Search for an sd spanning us and the target CPU. */ rcu_read_lock(); for_each_domain(target_cpu, sd) { - if ((sd->flags & SD_LOAD_BALANCE) && - cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) - break; + if (cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) + break; } if (likely(sd)) { @@ -9516,13 +10616,7 @@ static int active_load_balance_cpu_stop(void *data) .src_cpu = busiest_rq->cpu, .src_rq = busiest_rq, .idle = CPU_IDLE, - /* - * can_migrate_task() doesn't need to compute new_dst_cpu - * for active balancing. Since we have CPU_IDLE, but no - * @dst_grpmask we need to make that test go away with lying - * about DST_PINNED. - */ - .flags = LBF_DST_PINNED, + .flags = LBF_ACTIVE_LB, }; schedstat_inc(sd->alb_count); @@ -9561,6 +10655,30 @@ void update_max_interval(void) max_load_balance_interval = HZ*num_online_cpus()/10; } +static inline bool update_newidle_cost(struct sched_domain *sd, u64 cost) +{ + if (cost > sd->max_newidle_lb_cost) { + /* + * Track max cost of a domain to make sure to not delay the + * next wakeup on the CPU. + */ + sd->max_newidle_lb_cost = cost; + sd->last_decay_max_lb_cost = jiffies; + } else if (time_after(jiffies, sd->last_decay_max_lb_cost + HZ)) { + /* + * Decay the newidle max times by ~1% per second to ensure that + * it is not outdated and the current max cost is actually + * shorter. + */ + sd->max_newidle_lb_cost = (sd->max_newidle_lb_cost * 253) / 256; + sd->last_decay_max_lb_cost = jiffies; + + return true; + } + + return false; +} + /* * It checks each scheduling domain to see if it is due to be balanced, * and initiates a balancing operation if so. @@ -9584,19 +10702,11 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) for_each_domain(cpu, sd) { /* * Decay the newidle max times here because this is a regular - * visit to all the domains. Decay ~1% per second. + * visit to all the domains. */ - if (time_after(jiffies, sd->next_decay_max_lb_cost)) { - sd->max_newidle_lb_cost = - (sd->max_newidle_lb_cost * 253) / 256; - sd->next_decay_max_lb_cost = jiffies + HZ; - need_decay = 1; - } + need_decay = update_newidle_cost(sd, 0); max_cost += sd->max_newidle_lb_cost; - if (!(sd->flags & SD_LOAD_BALANCE)) - continue; - /* * Stop the load balance at this level. There is another * CPU in our sched group which is doing load balancing more @@ -9652,22 +10762,9 @@ out: * When the cpu is attached to null domain for ex, it will not be * updated. */ - if (likely(update_next_balance)) { + if (likely(update_next_balance)) rq->next_balance = next_balance; -#ifdef CONFIG_NO_HZ_COMMON - /* - * If this CPU has been elected to perform the nohz idle - * balance. Other idle CPUs have already rebalanced with - * nohz_idle_balance() and nohz.next_balance has been - * updated accordingly. This CPU is now running the idle load - * balance for itself and we need to update the - * nohz.next_balance accordingly. - */ - if ((idle == CPU_IDLE) && time_after(nohz.next_balance, rq->next_balance)) - nohz.next_balance = rq->next_balance; -#endif - } } static inline int on_null_domain(struct rq *rq) @@ -9681,16 +10778,22 @@ static inline int on_null_domain(struct rq *rq) * - When one of the busy CPUs notice that there may be an idle rebalancing * needed, they will kick the idle load balancer, which then does idle * load balancing for all the idle CPUs. - * - HK_FLAG_MISC CPUs are used for this task, because HK_FLAG_SCHED not set + * - HK_TYPE_MISC CPUs are used for this task, because HK_TYPE_SCHED not set * anywhere yet. */ static inline int find_new_ilb(void) { int ilb; + const struct cpumask *hk_mask; + + hk_mask = housekeeping_cpumask(HK_TYPE_MISC); + + for_each_cpu_and(ilb, nohz.idle_cpus_mask, hk_mask) { + + if (ilb == smp_processor_id()) + continue; - for_each_cpu_and(ilb, nohz.idle_cpus_mask, - housekeeping_cpumask(HK_FLAG_MISC)) { if (idle_cpu(ilb)) return ilb; } @@ -9700,30 +10803,38 @@ static inline int find_new_ilb(void) /* * Kick a CPU to do the nohz balancing, if it is time for it. We pick any - * idle CPU in the HK_FLAG_MISC housekeeping set (if there is one). + * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one). */ static void kick_ilb(unsigned int flags) { int ilb_cpu; - nohz.next_balance++; + /* + * Increase nohz.next_balance only when if full ilb is triggered but + * not if we only update stats. + */ + if (flags & NOHZ_BALANCE_KICK) + nohz.next_balance = jiffies+1; ilb_cpu = find_new_ilb(); if (ilb_cpu >= nr_cpu_ids) return; + /* + * Access to rq::nohz_csd is serialized by NOHZ_KICK_MASK; he who sets + * the first flag owns it; cleared by nohz_csd_func(). + */ flags = atomic_fetch_or(flags, nohz_flags(ilb_cpu)); if (flags & NOHZ_KICK_MASK) return; /* - * Use smp_send_reschedule() instead of resched_cpu(). - * This way we generate a sched IPI on the target CPU which + * This way we generate an IPI on the target CPU which * is idle. And the softirq performing nohz idle load balance * will be run before returning from the IPI. */ - smp_send_reschedule(ilb_cpu); + smp_call_function_single_async(ilb_cpu, &cpu_rq(ilb_cpu)->nohz_csd); } /* @@ -9762,7 +10873,7 @@ static void nohz_balancer_kick(struct rq *rq) goto out; if (rq->nr_running >= 2) { - flags = NOHZ_KICK_MASK; + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto out; } @@ -9776,7 +10887,7 @@ static void nohz_balancer_kick(struct rq *rq) * on. */ if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) { - flags = NOHZ_KICK_MASK; + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } } @@ -9790,7 +10901,7 @@ static void nohz_balancer_kick(struct rq *rq) */ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { if (sched_asym_prefer(i, cpu)) { - flags = NOHZ_KICK_MASK; + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } } @@ -9803,7 +10914,7 @@ static void nohz_balancer_kick(struct rq *rq) * to run the misfit task on. */ if (check_misfit_status(rq, sd)) { - flags = NOHZ_KICK_MASK; + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } @@ -9830,13 +10941,16 @@ static void nohz_balancer_kick(struct rq *rq) */ nr_busy = atomic_read(&sds->nr_busy_cpus); if (nr_busy > 1) { - flags = NOHZ_KICK_MASK; + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } } unlock: rcu_read_unlock(); out: + if (READ_ONCE(nohz.needs_update)) + flags |= NOHZ_NEXT_KICK; + if (flags) kick_ilb(flags); } @@ -9902,7 +11016,7 @@ void nohz_balance_enter_idle(int cpu) return; /* Spare idle load balancing on CPUs that don't want to be disturbed: */ - if (!housekeeping_cpu(cpu, HK_FLAG_SCHED)) + if (!housekeeping_cpu(cpu, HK_TYPE_SCHED)) return; /* @@ -9933,12 +11047,13 @@ void nohz_balance_enter_idle(int cpu) /* * Ensures that if nohz_idle_balance() fails to observe our * @idle_cpus_mask store, it must observe the @has_blocked - * store. + * and @needs_update stores. */ smp_mb__after_atomic(); set_cpu_sd_state_idle(cpu); + WRITE_ONCE(nohz.needs_update, 1); out: /* * Each time a cpu enter idle, we assume that it has blocked load and @@ -9947,15 +11062,30 @@ out: WRITE_ONCE(nohz.has_blocked, 1); } +static bool update_nohz_stats(struct rq *rq) +{ + unsigned int cpu = rq->cpu; + + if (!rq->has_blocked_load) + return false; + + if (!cpumask_test_cpu(cpu, nohz.idle_cpus_mask)) + return false; + + if (!time_after(jiffies, READ_ONCE(rq->last_blocked_load_update_tick))) + return true; + + update_blocked_averages(cpu); + + return rq->has_blocked_load; +} + /* * Internal function that runs load balance for all idle cpus. The load balance * can be a simple update of blocked load or a complete load balance with * tasks movement depending of flags. - * The function returns false if the loop has stopped before running - * through all idle CPUs. */ -static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, - enum cpu_idle_type idle) +static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags) { /* Earliest time when we have to do rebalance again */ unsigned long now = jiffies; @@ -9964,7 +11094,6 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, int update_next_balance = 0; int this_cpu = this_rq->cpu; int balance_cpu; - int ret = false; struct rq *rq; SCHED_WARN_ON((flags & NOHZ_KICK_MASK) == NOHZ_BALANCE_KICK); @@ -9972,12 +11101,17 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, /* * We assume there will be no idle load after this update and clear * the has_blocked flag. If a cpu enters idle in the mean time, it will - * set the has_blocked flag and trig another update of idle load. + * set the has_blocked flag and trigger another update of idle load. * Because a cpu that becomes idle, is added to idle_cpus_mask before * setting the flag, we are sure to not clear the state and not * check the load of an idle cpu. + * + * Same applies to idle_cpus_mask vs needs_update. */ - WRITE_ONCE(nohz.has_blocked, 0); + if (flags & NOHZ_STATS_KICK) + WRITE_ONCE(nohz.has_blocked, 0); + if (flags & NOHZ_NEXT_KICK) + WRITE_ONCE(nohz.needs_update, 0); /* * Ensures that if we miss the CPU, we must see the has_blocked @@ -9985,8 +11119,12 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, */ smp_mb(); - for_each_cpu(balance_cpu, nohz.idle_cpus_mask) { - if (balance_cpu == this_cpu || !idle_cpu(balance_cpu)) + /* + * Start with the next CPU after this_cpu so we will end with this_cpu and let a + * chance for other idle cpu to pull load. + */ + for_each_cpu_wrap(balance_cpu, nohz.idle_cpus_mask, this_cpu+1) { + if (!idle_cpu(balance_cpu)) continue; /* @@ -9995,13 +11133,17 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, * balancing owner will pick it up. */ if (need_resched()) { - has_blocked_load = true; + if (flags & NOHZ_STATS_KICK) + has_blocked_load = true; + if (flags & NOHZ_NEXT_KICK) + WRITE_ONCE(nohz.needs_update, 1); goto abort; } rq = cpu_rq(balance_cpu); - has_blocked_load |= update_nohz_stats(rq, true); + if (flags & NOHZ_STATS_KICK) + has_blocked_load |= update_nohz_stats(rq); /* * If time for next balance is due, @@ -10024,26 +11166,6 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, } } - /* Newly idle CPU doesn't need an update */ - if (idle != CPU_NEWLY_IDLE) { - update_blocked_averages(this_cpu); - has_blocked_load |= this_rq->has_blocked_load; - } - - if (flags & NOHZ_BALANCE_KICK) - rebalance_domains(this_rq, CPU_IDLE); - - WRITE_ONCE(nohz.next_blocked, - now + msecs_to_jiffies(LOAD_AVG_PERIOD)); - - /* The full idle balance loop has been done */ - ret = true; - -abort: - /* There is still blocked load, enable periodic update */ - if (has_blocked_load) - WRITE_ONCE(nohz.has_blocked, 1); - /* * next_balance will be updated only when there is a need. * When the CPU is attached to null domain for ex, it will not be @@ -10052,7 +11174,14 @@ abort: if (likely(update_next_balance)) nohz.next_balance = next_balance; - return ret; + if (flags & NOHZ_STATS_KICK) + WRITE_ONCE(nohz.next_blocked, + now + msecs_to_jiffies(LOAD_AVG_PERIOD)); + +abort: + /* There is still blocked load, enable periodic update */ + if (has_blocked_load) + WRITE_ONCE(nohz.has_blocked, 1); } /* @@ -10061,27 +11190,39 @@ abort: */ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { - int this_cpu = this_rq->cpu; - unsigned int flags; + unsigned int flags = this_rq->nohz_idle_balance; - if (!(atomic_read(nohz_flags(this_cpu)) & NOHZ_KICK_MASK)) + if (!flags) return false; - if (idle != CPU_IDLE) { - atomic_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu)); - return false; - } + this_rq->nohz_idle_balance = 0; - /* could be _relaxed() */ - flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(this_cpu)); - if (!(flags & NOHZ_KICK_MASK)) + if (idle != CPU_IDLE) return false; - _nohz_idle_balance(this_rq, flags, idle); + _nohz_idle_balance(this_rq, flags); return true; } +/* + * Check if we need to run the ILB for updating blocked load before entering + * idle state. + */ +void nohz_run_idle_balance(int cpu) +{ + unsigned int flags; + + flags = atomic_fetch_andnot(NOHZ_NEWILB_KICK, nohz_flags(cpu)); + + /* + * Update the blocked load only if no SCHED_SOFTIRQ is about to happen + * (ie NOHZ_STATS_KICK set) and will do the same. + */ + if ((flags == NOHZ_NEWILB_KICK) && !need_resched()) + _nohz_idle_balance(cpu_rq(cpu), NOHZ_STATS_KICK); +} + static void nohz_newidle_balance(struct rq *this_rq) { int this_cpu = this_rq->cpu; @@ -10090,7 +11231,7 @@ static void nohz_newidle_balance(struct rq *this_rq) * This CPU doesn't want to be disturbed by scheduler * housekeeping */ - if (!housekeeping_cpu(this_cpu, HK_FLAG_SCHED)) + if (!housekeeping_cpu(this_cpu, HK_TYPE_SCHED)) return; /* Will wake up very soon. No time for doing anything else*/ @@ -10102,16 +11243,11 @@ static void nohz_newidle_balance(struct rq *this_rq) time_before(jiffies, READ_ONCE(nohz.next_blocked))) return; - raw_spin_unlock(&this_rq->lock); /* - * This CPU is going to be idle and blocked load of idle CPUs - * need to be updated. Run the ilb locally as it is a good - * candidate for ilb instead of waking up another idle CPU. - * Kick an normal ilb if we failed to do the update. + * Set the need to trigger ILB in order to update blocked load + * before entering idle state. */ - if (!_nohz_idle_balance(this_rq, NOHZ_STATS_KICK, CPU_NEWLY_IDLE)) - kick_ilb(NOHZ_STATS_KICK); - raw_spin_lock(&this_rq->lock); + atomic_or(NOHZ_NEWILB_KICK, nohz_flags(this_cpu)); } #else /* !CONFIG_NO_HZ_COMMON */ @@ -10126,7 +11262,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { } #endif /* CONFIG_NO_HZ_COMMON */ /* - * idle_balance is called by schedule() if this_cpu is about to become + * newidle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. * * Returns: @@ -10134,15 +11270,23 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { } * 0 - failed, no new tasks * > 0 - success, new (fair) tasks present */ -int newidle_balance(struct rq *this_rq, struct rq_flags *rf) +static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { unsigned long next_balance = jiffies + HZ; int this_cpu = this_rq->cpu; + u64 t0, t1, curr_cost = 0; struct sched_domain *sd; int pulled_task = 0; - u64 curr_cost = 0; update_misfit_status(NULL, this_rq); + + /* + * There is a task waiting to run. No need to search for one. + * Return 0; the task will be enqueued when switching to idle. + */ + if (this_rq->ttwu_pending) + return 0; + /* * We must set idle_stamp _before_ calling idle_balance(), such that we * measure the duration of idle_balance() as idle time. @@ -10163,67 +11307,64 @@ int newidle_balance(struct rq *this_rq, struct rq_flags *rf) */ rq_unpin_lock(this_rq, rf); - if (this_rq->avg_idle < sysctl_sched_migration_cost || - !READ_ONCE(this_rq->rd->overload)) { + rcu_read_lock(); + sd = rcu_dereference_check_sched_domain(this_rq->sd); + + if (!READ_ONCE(this_rq->rd->overload) || + (sd && this_rq->avg_idle < sd->max_newidle_lb_cost)) { - rcu_read_lock(); - sd = rcu_dereference_check_sched_domain(this_rq->sd); if (sd) update_next_balance(sd, &next_balance); rcu_read_unlock(); - nohz_newidle_balance(this_rq); - goto out; } + rcu_read_unlock(); - raw_spin_unlock(&this_rq->lock); + raw_spin_rq_unlock(this_rq); + t0 = sched_clock_cpu(this_cpu); update_blocked_averages(this_cpu); + rcu_read_lock(); for_each_domain(this_cpu, sd) { int continue_balancing = 1; - u64 t0, domain_cost; + u64 domain_cost; - if (!(sd->flags & SD_LOAD_BALANCE)) - continue; + update_next_balance(sd, &next_balance); - if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { - update_next_balance(sd, &next_balance); + if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) break; - } if (sd->flags & SD_BALANCE_NEWIDLE) { - t0 = sched_clock_cpu(this_cpu); pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, &continue_balancing); - domain_cost = sched_clock_cpu(this_cpu) - t0; - if (domain_cost > sd->max_newidle_lb_cost) - sd->max_newidle_lb_cost = domain_cost; + t1 = sched_clock_cpu(this_cpu); + domain_cost = t1 - t0; + update_newidle_cost(sd, domain_cost); curr_cost += domain_cost; + t0 = t1; } - update_next_balance(sd, &next_balance); - /* * Stop searching for tasks to pull if there are * now runnable tasks on this rq. */ - if (pulled_task || this_rq->nr_running > 0) + if (pulled_task || this_rq->nr_running > 0 || + this_rq->ttwu_pending) break; } rcu_read_unlock(); - raw_spin_lock(&this_rq->lock); + raw_spin_rq_lock(this_rq); if (curr_cost > this_rq->max_idle_balance_cost) this_rq->max_idle_balance_cost = curr_cost; -out: /* * While browsing the domains, we released the rq lock, a task could * have been enqueued in the meantime. Since we're not going idle, @@ -10232,16 +11373,19 @@ out: if (this_rq->cfs.h_nr_running && !pulled_task) pulled_task = 1; - /* Move the next balance forward */ - if (time_after(this_rq->next_balance, next_balance)) - this_rq->next_balance = next_balance; - /* Is there a task of a high priority class? */ if (this_rq->nr_running != this_rq->cfs.h_nr_running) pulled_task = -1; +out: + /* Move the next balance forward */ + if (time_after(this_rq->next_balance, next_balance)) + this_rq->next_balance = next_balance; + if (pulled_task) this_rq->idle_stamp = 0; + else + nohz_newidle_balance(this_rq); rq_repin_lock(this_rq, rf); @@ -10279,8 +11423,11 @@ static __latent_entropy void run_rebalance_domains(struct softirq_action *h) */ void trigger_load_balance(struct rq *rq) { - /* Don't need to rebalance while attached to NULL domain */ - if (unlikely(on_null_domain(rq))) + /* + * Don't need to rebalance while attached to NULL domain or + * runqueue CPU is not active + */ + if (unlikely(on_null_domain(rq) || !cpu_active(cpu_of(rq)))) return; if (time_after_eq(jiffies, rq->next_balance)) @@ -10306,6 +11453,119 @@ static void rq_offline_fair(struct rq *rq) #endif /* CONFIG_SMP */ +#ifdef CONFIG_SCHED_CORE +static inline bool +__entity_slice_used(struct sched_entity *se, int min_nr_tasks) +{ + u64 slice = sched_slice(cfs_rq_of(se), se); + u64 rtime = se->sum_exec_runtime - se->prev_sum_exec_runtime; + + return (rtime * min_nr_tasks > slice); +} + +#define MIN_NR_TASKS_DURING_FORCEIDLE 2 +static inline void task_tick_core(struct rq *rq, struct task_struct *curr) +{ + if (!sched_core_enabled(rq)) + return; + + /* + * If runqueue has only one task which used up its slice and + * if the sibling is forced idle, then trigger schedule to + * give forced idle task a chance. + * + * sched_slice() considers only this active rq and it gets the + * whole slice. But during force idle, we have siblings acting + * like a single runqueue and hence we need to consider runnable + * tasks on this CPU and the forced idle CPU. Ideally, we should + * go through the forced idle rq, but that would be a perf hit. + * We can assume that the forced idle CPU has at least + * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check + * if we need to give up the CPU. + */ + if (rq->core->core_forceidle_count && rq->cfs.nr_running == 1 && + __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE)) + resched_curr(rq); +} + +/* + * se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed. + */ +static void se_fi_update(struct sched_entity *se, unsigned int fi_seq, bool forceidle) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + if (forceidle) { + if (cfs_rq->forceidle_seq == fi_seq) + break; + cfs_rq->forceidle_seq = fi_seq; + } + + cfs_rq->min_vruntime_fi = cfs_rq->min_vruntime; + } +} + +void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi) +{ + struct sched_entity *se = &p->se; + + if (p->sched_class != &fair_sched_class) + return; + + se_fi_update(se, rq->core->core_forceidle_seq, in_fi); +} + +bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool in_fi) +{ + struct rq *rq = task_rq(a); + struct sched_entity *sea = &a->se; + struct sched_entity *seb = &b->se; + struct cfs_rq *cfs_rqa; + struct cfs_rq *cfs_rqb; + s64 delta; + + SCHED_WARN_ON(task_rq(b)->core != rq->core); + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* + * Find an se in the hierarchy for tasks a and b, such that the se's + * are immediate siblings. + */ + while (sea->cfs_rq->tg != seb->cfs_rq->tg) { + int sea_depth = sea->depth; + int seb_depth = seb->depth; + + if (sea_depth >= seb_depth) + sea = parent_entity(sea); + if (sea_depth <= seb_depth) + seb = parent_entity(seb); + } + + se_fi_update(sea, rq->core->core_forceidle_seq, in_fi); + se_fi_update(seb, rq->core->core_forceidle_seq, in_fi); + + cfs_rqa = sea->cfs_rq; + cfs_rqb = seb->cfs_rq; +#else + cfs_rqa = &task_rq(a)->cfs; + cfs_rqb = &task_rq(b)->cfs; +#endif + + /* + * Find delta after normalizing se's vruntime with its cfs_rq's + * min_vruntime_fi, which would have been updated in prior calls + * to se_fi_update(). + */ + delta = (s64)(sea->vruntime - seb->vruntime) + + (s64)(cfs_rqb->min_vruntime_fi - cfs_rqa->min_vruntime_fi); + + return delta > 0; +} +#else +static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {} +#endif + /* * scheduler tick hitting a task of our scheduling class. * @@ -10329,6 +11589,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) update_misfit_status(curr, rq); update_overutilized_status(task_rq(curr)); + + task_tick_core(rq, curr); } /* @@ -10385,7 +11647,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) * our priority decreased, or if we are not currently running on * this runqueue and our priority is higher than the current's */ - if (rq->curr == p) { + if (task_current(rq, p)) { if (p->prio > oldprio) resched_curr(rq); } else @@ -10414,7 +11676,7 @@ static inline bool vruntime_normalized(struct task_struct *p) * waiting for actually being woken up by sched_ttwu_pending(). */ if (!se->sum_exec_runtime || - (p->state == TASK_WAKING && p->sched_remote_wakeup)) + (READ_ONCE(p->__state) == TASK_WAKING && p->sched_remote_wakeup)) return true; return false; @@ -10427,7 +11689,13 @@ static inline bool vruntime_normalized(struct task_struct *p) */ static void propagate_entity_cfs_rq(struct sched_entity *se) { - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + if (cfs_rq_throttled(cfs_rq)) + return; + + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); /* Start to propagate at parent */ se = se->parent; @@ -10435,10 +11703,13 @@ static void propagate_entity_cfs_rq(struct sched_entity *se) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); + update_load_avg(cfs_rq, se, UPDATE_TG); + if (cfs_rq_throttled(cfs_rq)) break; - update_load_avg(cfs_rq, se, UPDATE_TG); + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); } } #else @@ -10449,10 +11720,21 @@ static void detach_entity_cfs_rq(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); +#ifdef CONFIG_SMP + /* + * In case the task sched_avg hasn't been attached: + * - A forked task which hasn't been woken up by wake_up_new_task(). + * - A task which has been woken up by try_to_wake_up() but is + * waiting for actually being woken up by sched_ttwu_pending(). + */ + if (!se->avg.last_update_time) + return; +#endif + /* Catch up with the cfs_rq and remove our load when we leave */ update_load_avg(cfs_rq, se, 0); detach_entity_load_avg(cfs_rq, se); - update_tg_load_avg(cfs_rq, false); + update_tg_load_avg(cfs_rq); propagate_entity_cfs_rq(se); } @@ -10460,18 +11742,10 @@ static void attach_entity_cfs_rq(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); -#ifdef CONFIG_FAIR_GROUP_SCHED - /* - * Since the real-depth could have been changed (only FAIR - * class maintain depth value), reset depth properly. - */ - se->depth = se->parent ? se->parent->depth + 1 : 0; -#endif - /* Synchronize entity with its cfs_rq */ update_load_avg(cfs_rq, se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD); attach_entity_load_avg(cfs_rq, se); - update_tg_load_avg(cfs_rq, false); + update_tg_load_avg(cfs_rq); propagate_entity_cfs_rq(se); } @@ -10518,7 +11792,7 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) * kick off the schedule if running, otherwise just see * if we can still preempt the current task. */ - if (rq->curr == p) + if (task_current(rq, p)) resched_curr(rq); else check_preempt_curr(rq, p, 0); @@ -10556,55 +11830,36 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT_CACHED; - cfs_rq->min_vruntime = (u64)(-(1LL << 20)); -#ifndef CONFIG_64BIT - cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; -#endif + u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20))); #ifdef CONFIG_SMP raw_spin_lock_init(&cfs_rq->removed.lock); #endif } #ifdef CONFIG_FAIR_GROUP_SCHED -static void task_set_group_fair(struct task_struct *p) +static void task_change_group_fair(struct task_struct *p) { - struct sched_entity *se = &p->se; - - set_task_rq(p, task_cpu(p)); - se->depth = se->parent ? se->parent->depth + 1 : 0; -} + /* + * We couldn't detach or attach a forked task which + * hasn't been woken up by wake_up_new_task(). + */ + if (READ_ONCE(p->__state) == TASK_NEW) + return; -static void task_move_group_fair(struct task_struct *p) -{ detach_task_cfs_rq(p); - set_task_rq(p, task_cpu(p)); #ifdef CONFIG_SMP /* Tell se's cfs_rq has been changed -- migrated */ p->se.avg.last_update_time = 0; #endif + set_task_rq(p, task_cpu(p)); attach_task_cfs_rq(p); } -static void task_change_group_fair(struct task_struct *p, int type) -{ - switch (type) { - case TASK_SET_GROUP: - task_set_group_fair(p); - break; - - case TASK_MOVE_GROUP: - task_move_group_fair(p); - break; - } -} - void free_fair_sched_group(struct task_group *tg) { int i; - destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); - for_each_possible_cpu(i) { if (tg->cfs_rq) kfree(tg->cfs_rq[i]); @@ -10639,7 +11894,7 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) if (!cfs_rq) goto err; - se = kzalloc_node(sizeof(struct sched_entity), + se = kzalloc_node(sizeof(struct sched_entity_stats), GFP_KERNEL, cpu_to_node(i)); if (!se) goto err_free_rq; @@ -10681,6 +11936,8 @@ void unregister_fair_sched_group(struct task_group *tg) struct rq *rq; int cpu; + destroy_cfs_bandwidth(tg_cfs_bandwidth(tg)); + for_each_possible_cpu(cpu) { if (tg->se[cpu]) remove_entity_load_avg(tg->se[cpu]); @@ -10694,9 +11951,9 @@ void unregister_fair_sched_group(struct task_group *tg) rq = cpu_rq(cpu); - raw_spin_lock_irqsave(&rq->lock, flags); + raw_spin_rq_lock_irqsave(rq, flags); list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); - raw_spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_rq_unlock_irqrestore(rq, flags); } } @@ -10733,10 +11990,12 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, static DEFINE_MUTEX(shares_mutex); -int sched_group_set_shares(struct task_group *tg, unsigned long shares) +static int __sched_group_set_shares(struct task_group *tg, unsigned long shares) { int i; + lockdep_assert_held(&shares_mutex); + /* * We can't change the weight of the root cgroup. */ @@ -10745,9 +12004,8 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES)); - mutex_lock(&shares_mutex); if (tg->shares == shares) - goto done; + return 0; tg->shares = shares; for_each_possible_cpu(i) { @@ -10765,10 +12023,96 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) rq_unlock_irqrestore(rq, &rf); } -done: + return 0; +} + +int sched_group_set_shares(struct task_group *tg, unsigned long shares) +{ + int ret; + + mutex_lock(&shares_mutex); + if (tg_is_idle(tg)) + ret = -EINVAL; + else + ret = __sched_group_set_shares(tg, shares); + mutex_unlock(&shares_mutex); + + return ret; +} + +int sched_group_set_idle(struct task_group *tg, long idle) +{ + int i; + + if (tg == &root_task_group) + return -EINVAL; + + if (idle < 0 || idle > 1) + return -EINVAL; + + mutex_lock(&shares_mutex); + + if (tg->idle == idle) { + mutex_unlock(&shares_mutex); + return 0; + } + + tg->idle = idle; + + for_each_possible_cpu(i) { + struct rq *rq = cpu_rq(i); + struct sched_entity *se = tg->se[i]; + struct cfs_rq *parent_cfs_rq, *grp_cfs_rq = tg->cfs_rq[i]; + bool was_idle = cfs_rq_is_idle(grp_cfs_rq); + long idle_task_delta; + struct rq_flags rf; + + rq_lock_irqsave(rq, &rf); + + grp_cfs_rq->idle = idle; + if (WARN_ON_ONCE(was_idle == cfs_rq_is_idle(grp_cfs_rq))) + goto next_cpu; + + if (se->on_rq) { + parent_cfs_rq = cfs_rq_of(se); + if (cfs_rq_is_idle(grp_cfs_rq)) + parent_cfs_rq->idle_nr_running++; + else + parent_cfs_rq->idle_nr_running--; + } + + idle_task_delta = grp_cfs_rq->h_nr_running - + grp_cfs_rq->idle_h_nr_running; + if (!cfs_rq_is_idle(grp_cfs_rq)) + idle_task_delta *= -1; + + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + if (!se->on_rq) + break; + + cfs_rq->idle_h_nr_running += idle_task_delta; + + /* Already accounted at parent level and above. */ + if (cfs_rq_is_idle(cfs_rq)) + break; + } + +next_cpu: + rq_unlock_irqrestore(rq, &rf); + } + + /* Idle groups have minimum weight. */ + if (tg_is_idle(tg)) + __sched_group_set_shares(tg, scale_load(WEIGHT_IDLEPRIO)); + else + __sched_group_set_shares(tg, NICE_0_LOAD); + mutex_unlock(&shares_mutex); return 0; } + #else /* CONFIG_FAIR_GROUP_SCHED */ void free_fair_sched_group(struct task_group *tg) { } @@ -10803,8 +12147,8 @@ static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task /* * All the scheduling class methods: */ -const struct sched_class fair_sched_class = { - .next = &idle_sched_class, +DEFINE_SCHED_CLASS(fair) = { + .enqueue_task = enqueue_task_fair, .dequeue_task = dequeue_task_fair, .yield_task = yield_task_fair, @@ -10818,6 +12162,7 @@ const struct sched_class fair_sched_class = { #ifdef CONFIG_SMP .balance = balance_fair, + .pick_task = pick_task_fair, .select_task_rq = select_task_rq_fair, .migrate_task_rq = migrate_task_rq_fair, @@ -10887,6 +12232,13 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m) __init void init_sched_fair_class(void) { #ifdef CONFIG_SMP + int i; + + for_each_possible_cpu(i) { + zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i)); + zalloc_cpumask_var_node(&per_cpu(select_rq_mask, i), GFP_KERNEL, cpu_to_node(i)); + } + open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); #ifdef CONFIG_NO_HZ_COMMON @@ -10897,83 +12249,3 @@ __init void init_sched_fair_class(void) #endif /* SMP */ } - -/* - * Helper functions to facilitate extracting info from tracepoints. - */ - -const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq) -{ -#ifdef CONFIG_SMP - return cfs_rq ? &cfs_rq->avg : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_avg); - -char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len) -{ - if (!cfs_rq) { - if (str) - strlcpy(str, "(null)", len); - else - return NULL; - } - - cfs_rq_tg_path(cfs_rq, str, len); - return str; -} -EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_path); - -int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq) -{ - return cfs_rq ? cpu_of(rq_of(cfs_rq)) : -1; -} -EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_cpu); - -const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq) -{ -#ifdef CONFIG_SMP - return rq ? &rq->avg_rt : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rq_avg_rt); - -const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq) -{ -#ifdef CONFIG_SMP - return rq ? &rq->avg_dl : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rq_avg_dl); - -const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq) -{ -#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_SCHED_AVG_IRQ) - return rq ? &rq->avg_irq : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rq_avg_irq); - -int sched_trace_rq_cpu(struct rq *rq) -{ - return rq ? cpu_of(rq) : -1; -} -EXPORT_SYMBOL_GPL(sched_trace_rq_cpu); - -const struct cpumask *sched_trace_rd_span(struct root_domain *rd) -{ -#ifdef CONFIG_SMP - return rd ? rd->span : NULL; -#else - return NULL; -#endif -} -EXPORT_SYMBOL_GPL(sched_trace_rd_span); |