diff options
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r-- | kernel/sched/fair.c | 938 |
1 files changed, 603 insertions, 335 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 794c2cb945f8..fb469b26b00a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -49,7 +49,7 @@ 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: @@ -113,6 +113,13 @@ 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 @@ -229,22 +236,25 @@ 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); @@ -258,33 +268,11 @@ 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) @@ -445,33 +433,9 @@ 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) -{ - return container_of(se, struct task_struct, se); -} - #define for_each_sched_entity(se) \ for (; se; se = NULL) -static inline struct cfs_rq *task_cfs_rq(struct task_struct *p) -{ - return &task_rq(p)->cfs; -} - -static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se) -{ - struct task_struct *p = task_of(se); - struct rq *rq = task_rq(p); - - return &rq->cfs; -} - -/* runqueue "owned" by this group */ -static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) -{ - return NULL; -} - static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) { if (path) @@ -624,15 +588,10 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) * Scheduling class statistics methods: */ -int sched_proc_update_handler(struct ctl_table *table, int write, - void *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); @@ -682,7 +641,13 @@ 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; + 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; @@ -699,6 +664,10 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) } slice = __calc_delta(slice, se->load.weight, load); } + + if (sched_feat(BASE_SLICE)) + slice = max(slice, (u64)sysctl_sched_min_granularity); + return slice; } @@ -1024,11 +993,14 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) { struct task_struct *tsk = task_of(se); + unsigned int state; - if (tsk->state & TASK_INTERRUPTIBLE) + /* XXX racy against TTWU */ + state = READ_ONCE(tsk->__state); + if (state & TASK_INTERRUPTIBLE) __schedstat_set(se->statistics.sleep_start, rq_clock(rq_of(cfs_rq))); - if (tsk->state & TASK_UNINTERRUPTIBLE) + if (state & TASK_UNINTERRUPTIBLE) __schedstat_set(se->statistics.block_start, rq_clock(rq_of(cfs_rq))); } @@ -1092,7 +1064,7 @@ 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) @@ -1122,7 +1094,7 @@ 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) @@ -2574,7 +2546,7 @@ 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 @@ -3124,7 +3096,7 @@ 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 @@ -3138,7 +3110,7 @@ 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 * @@ -3154,7 +3126,7 @@ 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. * @@ -3173,7 +3145,7 @@ 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: * @@ -3283,6 +3255,61 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) #ifdef CONFIG_SMP #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 (cfs_rq->avg.load_sum) + return false; + + if (cfs_rq->avg.util_sum) + return false; + + if (cfs_rq->avg.runnable_sum) + return false; + + if (child_cfs_rq_on_list(cfs_rq)) + 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(cfs_rq->avg.load_avg || + cfs_rq->avg.util_avg || + cfs_rq->avg.runnable_avg); + + return true; +} + /** * update_tg_load_avg - update the tg's load avg * @cfs_rq: the cfs_rq whose avg changed @@ -3484,10 +3511,9 @@ update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cf 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; + long delta, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; unsigned long load_avg; u64 load_sum = 0; - s64 delta_sum; u32 divider; if (!runnable_sum) @@ -3534,13 +3560,16 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq load_sum = (s64)se_weight(se) * runnable_sum; load_avg = div_s64(load_sum, divider); - delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; - delta_avg = load_avg - se->avg.load_avg; - se->avg.load_sum = runnable_sum; + + delta = load_avg - se->avg.load_avg; + if (!delta) + return; + se->avg.load_avg = load_avg; - add_positive(&cfs_rq->avg.load_avg, delta_avg); - add_positive(&cfs_rq->avg.load_sum, delta_sum); + + add_positive(&cfs_rq->avg.load_avg, delta); + cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * divider; } static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum) @@ -3656,15 +3685,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) r = removed_load; sub_positive(&sa->load_avg, r); - sub_positive(&sa->load_sum, r * divider); + sa->load_sum = sa->load_avg * divider; r = removed_util; sub_positive(&sa->util_avg, r); - sub_positive(&sa->util_sum, r * divider); + sa->util_sum = sa->util_avg * divider; r = removed_runnable; sub_positive(&sa->runnable_avg, r); - sub_positive(&sa->runnable_sum, r * divider); + sa->runnable_sum = sa->runnable_avg * divider; /* * removed_runnable is the unweighted version of removed_load so we @@ -3751,11 +3780,17 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { + /* + * 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); + 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); + cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * divider; sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg); - sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum); + cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider; add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); @@ -3887,7 +3922,7 @@ 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) @@ -3941,13 +3976,15 @@ static inline void util_est_dequeue(struct cfs_rq *cfs_rq, 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) { @@ -3958,7 +3995,7 @@ 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; if (!sched_feat(UTIL_EST)) @@ -3979,11 +4016,13 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, 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; @@ -3992,12 +4031,17 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, } /* - * 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 @@ -4027,6 +4071,7 @@ static inline void util_est_update(struct cfs_rq *cfs_rq, 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); @@ -4061,6 +4106,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq) #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 @@ -4244,7 +4294,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* * When bandwidth control is enabled, cfs might have been removed * because of a parent been throttled but cfs->nr_running > 1. Try to - * add it unconditionnally. + * add it unconditionally. */ if (cfs_rq->nr_running == 1 || cfs_bandwidth_used()) list_add_leaf_cfs_rq(cfs_rq); @@ -4395,6 +4445,8 @@ 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) { /* @@ -4454,7 +4506,7 @@ 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) { @@ -4481,8 +4533,6 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) se = cfs_rq->last; } - clear_buddies(cfs_rq, se); - return se; } @@ -4604,8 +4654,11 @@ 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; + if (unlikely(cfs_b->quota == RUNTIME_INF)) + return; + + cfs_b->runtime += cfs_b->quota; + cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst); } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4719,8 +4772,8 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - cfs_rq->throttled_clock_task; - /* Add cfs_rq with already running entity in the list */ - if (cfs_rq->nr_running >= 1) + /* Add cfs_rq with load or one or more already running entities to the list */ + if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running) list_add_leaf_cfs_rq(cfs_rq); } @@ -4966,6 +5019,9 @@ 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 @@ -4973,8 +5029,6 @@ 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; @@ -5224,6 +5278,7 @@ 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", @@ -5255,6 +5310,7 @@ 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); @@ -5299,12 +5355,12 @@ 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) { @@ -5323,7 +5379,7 @@ 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) { @@ -5911,11 +5967,15 @@ 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) { /* @@ -6001,9 +6061,10 @@ 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) +static inline int __select_idle_cpu(int cpu, struct task_struct *p) { - if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) + if ((available_idle_cpu(cpu) || sched_idle_cpu(cpu)) && + sched_cpu_cookie_match(cpu_rq(cpu), p)) return cpu; return -1; @@ -6073,7 +6134,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu int cpu; if (!static_branch_likely(&sched_smt_present)) - return __select_idle_cpu(core); + return __select_idle_cpu(core, p); for_each_cpu(cpu, cpu_smt_mask(core)) { if (!available_idle_cpu(cpu)) { @@ -6098,6 +6159,24 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu return -1; } +/* + * Scan the local SMT mask for idle CPUs. + */ +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) +{ + int cpu; + + for_each_cpu(cpu, cpu_smt_mask(target)) { + if (!cpumask_test_cpu(cpu, p->cpus_ptr) || + !cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; + if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) + return cpu; + } + + return -1; +} + #else /* CONFIG_SCHED_SMT */ static inline void set_idle_cores(int cpu, int val) @@ -6111,7 +6190,12 @@ static inline bool test_idle_cores(int cpu, bool def) static inline int select_idle_core(struct task_struct *p, int core, struct cpumask *cpus, int *idle_cpu) { - return __select_idle_cpu(core); + return __select_idle_cpu(core, p); +} + +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) +{ + return -1; } #endif /* CONFIG_SCHED_SMT */ @@ -6121,14 +6205,14 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma * 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); int i, cpu, idle_cpu = -1, nr = INT_MAX; - bool smt = test_idle_cores(target, false); + struct rq *this_rq = this_rq(); int this = smp_processor_id(); struct sched_domain *this_sd; - u64 time; + u64 time = 0; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) @@ -6136,14 +6220,23 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); - if (sched_feat(SIS_PROP) && !smt) { + if (sched_feat(SIS_PROP) && !has_idle_core) { u64 avg_cost, avg_idle, span_avg; + unsigned long now = jiffies; /* - * Due to large variance we need a large fuzz factor; - * hackbench in particularly is sensitive here. + * If we're busy, the assumption that the last idle period + * predicts the future is flawed; age away the remaining + * predicted idle time. */ - avg_idle = this_rq()->avg_idle / 512; + 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; span_avg = sd->span_weight * avg_idle; @@ -6156,7 +6249,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t } for_each_cpu_wrap(cpu, cpus, target) { - if (smt) { + if (has_idle_core) { i = select_idle_core(p, cpu, cpus, &idle_cpu); if ((unsigned int)i < nr_cpumask_bits) return i; @@ -6164,17 +6257,24 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t } else { if (!--nr) return -1; - idle_cpu = __select_idle_cpu(cpu); + idle_cpu = __select_idle_cpu(cpu, p); if ((unsigned int)idle_cpu < nr_cpumask_bits) break; } } - if (smt) - set_idle_cores(this, false); + if (has_idle_core) + set_idle_cores(target, false); - if (sched_feat(SIS_PROP) && !smt) { + if (sched_feat(SIS_PROP) && !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); } @@ -6228,6 +6328,7 @@ static inline bool asym_fits_capacity(int task_util, int cpu) */ 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; @@ -6241,6 +6342,11 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) task_util = uclamp_task_util(p); } + /* + * per-cpu select_idle_mask usage + */ + lockdep_assert_irqs_disabled(); + if ((available_idle_cpu(target) || sched_idle_cpu(target)) && asym_fits_capacity(task_util, target)) return target; @@ -6307,7 +6413,17 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) if (!sd) return target; - i = select_idle_cpu(p, sd, target); + if (sched_smt_active()) { + has_idle_core = test_idle_cores(target, false); + + if (!has_idle_core && cpus_share_cache(prev, target)) { + i = select_idle_smt(p, sd, prev); + if ((unsigned int)i < nr_cpumask_bits) + return i; + } + } + + i = select_idle_cpu(p, sd, has_idle_core, target); if ((unsigned)i < nr_cpumask_bits) return i; @@ -6471,7 +6587,7 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) * util_avg should already be correct. */ if (task_cpu(p) == cpu && dst_cpu != cpu) - sub_positive(&util, task_util(p)); + lsub_positive(&util, task_util(p)); else if (task_cpu(p) != cpu && dst_cpu == cpu) util += task_util(p); @@ -6506,8 +6622,11 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) 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 _cpu_cap = cpu_cap; int cpu; + _cpu_cap -= arch_scale_thermal_pressure(cpumask_first(pd_mask)); + /* * 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 @@ -6518,8 +6637,24 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * 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; + unsigned long util_freq = cpu_util_next(cpu, p, dst_cpu); + unsigned long cpu_util, util_running = util_freq; + struct task_struct *tsk = NULL; + + /* + * When @p is placed on @cpu: + * + * util_running = max(cpu_util, cpu_util_est) + + * max(task_util, _task_util_est) + * + * while cpu_util_next is: max(cpu_util + task_util, + * cpu_util_est + _task_util_est) + */ + if (cpu == dst_cpu) { + tsk = p; + util_running = + cpu_util_next(cpu, p, -1) + task_util_est(p); + } /* * Busy time computation: utilization clamping is not @@ -6527,8 +6662,10 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * is already enough to scale the EM reported power * consumption at the (eventually clamped) cpu_capacity. */ - sum_util += effective_cpu_util(cpu, util_cfs, cpu_cap, - ENERGY_UTIL, NULL); + cpu_util = effective_cpu_util(cpu, util_running, cpu_cap, + ENERGY_UTIL, NULL); + + sum_util += min(cpu_util, _cpu_cap); /* * Performance domain frequency: utilization clamping @@ -6537,12 +6674,12 @@ 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 = effective_cpu_util(cpu, util_cfs, cpu_cap, + cpu_util = effective_cpu_util(cpu, util_freq, cpu_cap, FREQUENCY_UTIL, tsk); - max_util = max(max_util, cpu_util); + max_util = max(max_util, min(cpu_util, _cpu_cap)); } - return em_cpu_energy(pd->em_pd, max_util, sum_util); + return em_cpu_energy(pd->em_pd, max_util, sum_util, _cpu_cap); } /* @@ -6588,15 +6725,15 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; struct root_domain *rd = cpu_rq(smp_processor_id())->rd; + int cpu, best_energy_cpu = prev_cpu, target = -1; unsigned long cpu_cap, util, base_energy = 0; - int cpu, best_energy_cpu = prev_cpu; struct sched_domain *sd; struct perf_domain *pd; 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 @@ -6606,7 +6743,9 @@ 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)) @@ -6614,13 +6753,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) for (; pd; pd = pd->next) { unsigned long cur_delta, spare_cap, max_spare_cap = 0; + bool compute_prev_delta = false; unsigned long base_energy_pd; int max_spare_cap_cpu = -1; - /* Compute the 'base' energy of the pd, without @p */ - base_energy_pd = compute_energy(p, -1, pd); - base_energy += base_energy_pd; - for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; @@ -6641,26 +6777,40 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) 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); - } - - /* - * Find the CPU with the maximum spare capacity in - * the performance domain - */ - if (spare_cap > max_spare_cap) { + /* Always use prev_cpu as a candidate. */ + compute_prev_delta = true; + } else if (spare_cap > max_spare_cap) { + /* + * Find the CPU with the maximum spare capacity + * in the performance domain. + */ max_spare_cap = spare_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) { + if (max_spare_cap_cpu < 0 && !compute_prev_delta) + continue; + + /* Compute the 'base' energy of the pd, without @p */ + base_energy_pd = compute_energy(p, -1, pd); + base_energy += base_energy_pd; + + /* Evaluate the energy impact of using prev_cpu. */ + if (compute_prev_delta) { + prev_delta = compute_energy(p, prev_cpu, pd); + if (prev_delta < base_energy_pd) + goto unlock; + prev_delta -= base_energy_pd; + 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(p, max_spare_cap_cpu, pd); + if (cur_delta < base_energy_pd) + goto unlock; cur_delta -= base_energy_pd; if (cur_delta < best_delta) { best_delta = cur_delta; @@ -6668,25 +6818,22 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_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 == ULONG_MAX) || + (prev_delta - best_delta) > ((prev_delta + base_energy) >> 4)) + target = best_energy_cpu; - if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4)) - return best_energy_cpu; - - return prev_cpu; + return target; -fail: +unlock: rcu_read_unlock(); - return -1; + return target; } /* @@ -6698,8 +6845,6 @@ fail: * 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 wake_flags) @@ -6712,6 +6857,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int wake_flags) /* SD_flags and WF_flags share the first nibble */ int sd_flag = wake_flags & 0xF; + /* + * required for stable ->cpus_allowed + */ + lockdep_assert_held(&p->pi_lock); if (wake_flags & WF_TTWU) { record_wakee(p); @@ -6776,7 +6925,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) * min_vruntime -- the latter is done by enqueue_entity() when placing * the task on the new runqueue. */ - if (p->state == TASK_WAKING) { + if (READ_ONCE(p->__state) == TASK_WAKING) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); u64 min_vruntime; @@ -6801,7 +6950,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) * 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); + lockdep_assert_rq_held(task_rq(p)); detach_entity_cfs_rq(&p->se); } else { @@ -6935,7 +7084,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ /* * 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. */ @@ -7005,6 +7154,39 @@ 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) { @@ -7392,8 +7574,7 @@ 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; @@ -7429,7 +7610,7 @@ 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; @@ -7451,6 +7632,14 @@ 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; @@ -7527,7 +7716,7 @@ 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: @@ -7539,6 +7728,10 @@ 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; @@ -7551,10 +7744,13 @@ 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: */ @@ -7569,7 +7765,7 @@ 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)) { @@ -7579,10 +7775,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* * 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); @@ -7605,7 +7805,7 @@ 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); @@ -7621,7 +7821,7 @@ 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) { @@ -7657,7 +7857,16 @@ 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; @@ -7708,8 +7917,7 @@ static int detach_tasks(struct lb_env *env) * scheduler fails to find a good waiting task to * migrate. */ - - if ((load >> env->sd->nr_balance_failed) > env->imbalance) + if (shr_bound(load, env->sd->nr_balance_failed) > env->imbalance) goto next; env->imbalance -= load; @@ -7779,7 +7987,7 @@ 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); activate_task(rq, p, ENQUEUE_NOCLOCK); @@ -7854,16 +8062,20 @@ 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 @@ -7895,23 +8107,6 @@ 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_sum) - return false; - - return true; -} - static bool __update_blocked_fair(struct rq *rq, bool *done) { struct cfs_rq *cfs_rq, *pos; @@ -7935,7 +8130,7 @@ 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 @@ -8024,6 +8219,7 @@ 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); @@ -8311,26 +8507,6 @@ group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs) 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); -} - -/* - * 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); -} - static inline enum group_type group_classify(unsigned int imbalance_pct, struct sched_group *group, @@ -8354,28 +8530,6 @@ group_type group_classify(unsigned int imbalance_pct, return group_has_spare; } -static bool update_nohz_stats(struct rq *rq, bool force) -{ -#ifdef CONFIG_NO_HZ_COMMON - unsigned int cpu = rq->cpu; - - if (!rq->has_blocked_load) - return false; - - if (!cpumask_test_cpu(cpu, nohz.idle_cpus_mask)) - return false; - - if (!force && !time_after(jiffies, rq->last_blocked_load_update_tick)) - return true; - - update_blocked_averages(cpu); - - return rq->has_blocked_load; -#else - return false; -#endif -} - /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. @@ -8397,9 +8551,6 @@ static inline void update_sg_lb_stats(struct lb_env *env, for_each_cpu_and(i, sched_group_span(group), env->cpus) { struct rq *rq = cpu_rq(i); - 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_runnable += cpu_runnable(rq); @@ -8489,7 +8640,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, * internally or be covered by avg_load imbalance (eventually). */ if (sgs->group_type == group_misfit_task && - (!group_smaller_max_cpu_capacity(sg, sds->local) || + (!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) || sds->local_stat.group_type != group_has_spare)) return false; @@ -8573,7 +8724,7 @@ 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; @@ -8802,6 +8953,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) 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)); @@ -8940,11 +9095,6 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sg_lb_stats tmp_sgs; 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; @@ -8981,14 +9131,6 @@ next_group: /* 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); @@ -9386,7 +9528,7 @@ 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; @@ -9676,7 +9818,7 @@ 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. @@ -9743,7 +9885,7 @@ 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, @@ -9751,8 +9893,7 @@ more_balance: * moved to this_cpu: */ if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { - raw_spin_unlock_irqrestore(&busiest->lock, - flags); + raw_spin_rq_unlock_irqrestore(busiest, flags); goto out_one_pinned; } @@ -9769,16 +9910,13 @@ 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 { sd->nr_balance_failed = 0; @@ -9820,7 +9958,7 @@ 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) @@ -9928,13 +10066,7 @@ 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); @@ -10061,22 +10193,9 @@ 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) @@ -10368,14 +10487,30 @@ 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, +static void _nohz_idle_balance(struct rq *this_rq, unsigned int flags, enum cpu_idle_type idle) { /* Earliest time when we have to do rebalance again */ @@ -10385,7 +10520,6 @@ 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); @@ -10406,8 +10540,12 @@ 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; /* @@ -10422,7 +10560,7 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, rq = cpu_rq(balance_cpu); - has_blocked_load |= update_nohz_stats(rq, true); + has_blocked_load |= update_nohz_stats(rq); /* * If time for next balance is due, @@ -10453,27 +10591,13 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, if (likely(update_next_balance)) nohz.next_balance = next_balance; - /* 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); - - return ret; } /* @@ -10497,6 +10621,24 @@ static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) 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, CPU_IDLE); +} + static void nohz_newidle_balance(struct rq *this_rq) { int this_cpu = this_rq->cpu; @@ -10517,16 +10659,11 @@ 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 */ @@ -10558,6 +10695,14 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) 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. @@ -10587,12 +10732,10 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) update_next_balance(sd, &next_balance); rcu_read_unlock(); - nohz_newidle_balance(this_rq); - goto out; } - raw_spin_unlock(&this_rq->lock); + raw_spin_rq_unlock(this_rq); update_blocked_averages(this_cpu); rcu_read_lock(); @@ -10625,17 +10768,17 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) * 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, @@ -10644,16 +10787,19 @@ 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); @@ -10721,6 +10867,119 @@ 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 && 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. * @@ -10744,6 +11003,8 @@ 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); } /* @@ -10829,7 +11090,7 @@ 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; @@ -10844,16 +11105,22 @@ static void propagate_entity_cfs_rq(struct sched_entity *se) { struct cfs_rq *cfs_rq; + list_add_leaf_cfs_rq(cfs_rq_of(se)); + /* Start to propagate at parent */ se = se->parent; for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - if (cfs_rq_throttled(cfs_rq)) - break; + if (!cfs_rq_throttled(cfs_rq)){ + update_load_avg(cfs_rq, se, UPDATE_TG); + list_add_leaf_cfs_rq(cfs_rq); + continue; + } - update_load_avg(cfs_rq, se, UPDATE_TG); + if (list_add_leaf_cfs_rq(cfs_rq)) + break; } } #else @@ -11109,9 +11376,9 @@ 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); } } @@ -11233,6 +11500,7 @@ DEFINE_SCHED_CLASS(fair) = { #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, |