diff options
Diffstat (limited to 'kernel/sched/fair.c')
| -rw-r--r-- | kernel/sched/fair.c | 12506 |
1 files changed, 12506 insertions, 0 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c new file mode 100644 index 000000000..2558ab903 --- /dev/null +++ b/kernel/sched/fair.c @@ -0,0 +1,12506 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH) + * + * Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com> + * + * Interactivity improvements by Mike Galbraith + * (C) 2007 Mike Galbraith <efault@gmx.de> + * + * Various enhancements by Dmitry Adamushko. + * (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com> + * + * Group scheduling enhancements by Srivatsa Vaddagiri + * Copyright IBM Corporation, 2007 + * Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> + * + * Scaled math optimizations by Thomas Gleixner + * Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de> + * + * Adaptive scheduling granularity, math enhancements by Peter Zijlstra + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra + */ +#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 "sched.h" +#include "stats.h" +#include "autogroup.h" + +/* + * Targeted preemption latency for CPU-bound tasks: + * + * NOTE: this latency value is not the same as the concept of + * 'timeslice length' - timeslices in CFS are of variable length + * and have no persistent notion like in traditional, time-slice + * based scheduling concepts. + * + * (to see the precise effective timeslice length of your workload, + * run vmstat and monitor the context-switches (cs) field) + * + * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) + */ +unsigned int sysctl_sched_latency = 6000000ULL; +static unsigned int normalized_sysctl_sched_latency = 6000000ULL; + +/* + * The initial- and re-scaling of tunables is configurable + * + * Options are: + * + * SCHED_TUNABLESCALING_NONE - unscaled, always *1 + * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus) + * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus + * + * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus)) + */ +unsigned int sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG; + +/* + * Minimal preemption granularity for CPU-bound tasks: + * + * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds) + */ +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; + +/* + * After fork, child runs first. If set to 0 (default) then + * parent will (try to) run first. + */ +unsigned int sysctl_sched_child_runs_first __read_mostly; + +/* + * SCHED_OTHER wake-up granularity. + * + * This option delays the preemption effects of decoupled workloads + * and reduces their over-scheduling. Synchronous workloads will still + * have immediate wakeup/sleep latencies. + * + * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) + */ +unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +static unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; + +const_debug unsigned int sysctl_sched_migration_cost = 500000UL; + +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. + */ +int __weak arch_asym_cpu_priority(int cpu) +{ + return -cpu; +} + +/* + * The margin used when comparing utilization with CPU capacity. + * + * (default: ~20%) + */ +#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 +/* + * Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool + * each time a cfs_rq requests quota. + * + * Note: in the case that the slice exceeds the runtime remaining (either due + * to consumption or the quota being specified to be smaller than the slice) + * we will always only issue the remaining available time. + * + * (default: 5 msec, units: microseconds) + */ +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) +{ + lw->weight += inc; + lw->inv_weight = 0; +} + +static inline void update_load_sub(struct load_weight *lw, unsigned long dec) +{ + lw->weight -= dec; + lw->inv_weight = 0; +} + +static inline void update_load_set(struct load_weight *lw, unsigned long w) +{ + lw->weight = w; + lw->inv_weight = 0; +} + +/* + * Increase the granularity value when there are more CPUs, + * because with more CPUs the 'effective latency' as visible + * to users decreases. But the relationship is not linear, + * so pick a second-best guess by going with the log2 of the + * number of CPUs. + * + * This idea comes from the SD scheduler of Con Kolivas: + */ +static unsigned int get_update_sysctl_factor(void) +{ + unsigned int cpus = min_t(unsigned int, num_online_cpus(), 8); + unsigned int factor; + + switch (sysctl_sched_tunable_scaling) { + case SCHED_TUNABLESCALING_NONE: + factor = 1; + break; + case SCHED_TUNABLESCALING_LINEAR: + factor = cpus; + break; + case SCHED_TUNABLESCALING_LOG: + default: + factor = 1 + ilog2(cpus); + break; + } + + return factor; +} + +static void update_sysctl(void) +{ + unsigned int factor = get_update_sysctl_factor(); + +#define SET_SYSCTL(name) \ + (sysctl_##name = (factor) * normalized_sysctl_##name) + SET_SYSCTL(sched_min_granularity); + SET_SYSCTL(sched_latency); + SET_SYSCTL(sched_wakeup_granularity); +#undef SET_SYSCTL +} + +void __init sched_init_granularity(void) +{ + update_sysctl(); +} + +#define WMULT_CONST (~0U) +#define WMULT_SHIFT 32 + +static void __update_inv_weight(struct load_weight *lw) +{ + unsigned long w; + + if (likely(lw->inv_weight)) + return; + + w = scale_load_down(lw->weight); + + if (BITS_PER_LONG > 32 && unlikely(w >= WMULT_CONST)) + lw->inv_weight = 1; + else if (unlikely(!w)) + lw->inv_weight = WMULT_CONST; + else + lw->inv_weight = WMULT_CONST / w; +} + +/* + * delta_exec * weight / lw.weight + * OR + * (delta_exec * (weight * lw->inv_weight)) >> WMULT_SHIFT + * + * Either weight := NICE_0_LOAD and lw \e sched_prio_to_wmult[], in which case + * we're guaranteed shift stays positive because inv_weight is guaranteed to + * fit 32 bits, and NICE_0_LOAD gives another 10 bits; therefore shift >= 22. + * + * Or, weight =< lw.weight (because lw.weight is the runqueue weight), thus + * weight/lw.weight <= 1, and therefore our shift will also be positive. + */ +static 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_hi)) { + fs = fls(fact_hi); + shift -= fs; + fact >>= fs; + } + + fact = mul_u32_u32(fact, lw->inv_weight); + + 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); +} + + +const struct sched_class fair_sched_class; + +/************************************************************** + * CFS operations on generic schedulable entities: + */ + +#ifdef CONFIG_FAIR_GROUP_SCHED + +/* Walk up scheduling entities hierarchy */ +#define for_each_sched_entity(se) \ + for (; se; se = se->parent) + +static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); + + if (cfs_rq->on_list) + return rq->tmp_alone_branch == &rq->leaf_cfs_rq_list; + + cfs_rq->on_list = 1; + + /* + * Ensure we either appear before our parent (if already + * enqueued) or force our parent to appear after us when it is + * enqueued. The fact that we always enqueue bottom-up + * reduces this to two cases and a special case for the root + * cfs_rq. Furthermore, it also means that we will always reset + * tmp_alone_branch either when the branch is connected + * to a tree or when we reach the top of the tree + */ + if (cfs_rq->tg->parent && + cfs_rq->tg->parent->cfs_rq[cpu]->on_list) { + /* + * If parent is already on the list, we add the child + * just before. Thanks to circular linked property of + * the list, this means to put the child at the tail + * of the list that starts by parent. + */ + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list)); + /* + * The branch is now connected to its tree so we can + * reset tmp_alone_branch to the beginning of the + * list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + return true; + } + + if (!cfs_rq->tg->parent) { + /* + * cfs rq without parent should be put + * at the tail of the list. + */ + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &rq->leaf_cfs_rq_list); + /* + * We have reach the top of a tree so we can reset + * tmp_alone_branch to the beginning of the list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + return true; + } + + /* + * The parent has not already been added so we want to + * make sure that it will be put after us. + * tmp_alone_branch points to the begin of the branch + * where we will add parent. + */ + list_add_rcu(&cfs_rq->leaf_cfs_rq_list, rq->tmp_alone_branch); + /* + * update tmp_alone_branch to points to the new begin + * of the branch + */ + rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list; + return false; +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->on_list) { + struct rq *rq = rq_of(cfs_rq); + + /* + * With cfs_rq being unthrottled/throttled during an enqueue, + * it can happen the tmp_alone_branch points the a leaf that + * we finally want to del. In this case, tmp_alone_branch moves + * to the prev element but it will point to rq->leaf_cfs_rq_list + * at the end of the enqueue. + */ + if (rq->tmp_alone_branch == &cfs_rq->leaf_cfs_rq_list) + rq->tmp_alone_branch = cfs_rq->leaf_cfs_rq_list.prev; + + list_del_rcu(&cfs_rq->leaf_cfs_rq_list); + cfs_rq->on_list = 0; + } +} + +static inline void assert_list_leaf_cfs_rq(struct rq *rq) +{ + SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list); +} + +/* Iterate thr' all leaf cfs_rq's on a runqueue */ +#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ + list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list, \ + leaf_cfs_rq_list) + +/* Do the two (enqueued) entities belong to the same group ? */ +static inline struct cfs_rq * +is_same_group(struct sched_entity *se, struct sched_entity *pse) +{ + if (se->cfs_rq == pse->cfs_rq) + return se->cfs_rq; + + return NULL; +} + +static inline struct sched_entity *parent_entity(struct sched_entity *se) +{ + return se->parent; +} + +static void +find_matching_se(struct sched_entity **se, struct sched_entity **pse) +{ + int se_depth, pse_depth; + + /* + * preemption test can be made between sibling entities who are in the + * same cfs_rq i.e who have a common parent. Walk up the hierarchy of + * both tasks until we find their ancestors who are siblings of common + * parent. + */ + + /* First walk up until both entities are at same depth */ + se_depth = (*se)->depth; + pse_depth = (*pse)->depth; + + while (se_depth > pse_depth) { + se_depth--; + *se = parent_entity(*se); + } + + while (pse_depth > se_depth) { + pse_depth--; + *pse = parent_entity(*pse); + } + + while (!is_same_group(*se, *pse)) { + *se = parent_entity(*se); + *pse = parent_entity(*pse); + } +} + +static int tg_is_idle(struct task_group *tg) +{ + return tg->idle > 0; +} + +static int cfs_rq_is_idle(struct cfs_rq *cfs_rq) +{ + return cfs_rq->idle > 0; +} + +static int se_is_idle(struct sched_entity *se) +{ + if (entity_is_task(se)) + return task_has_idle_policy(task_of(se)); + return cfs_rq_is_idle(group_cfs_rq(se)); +} + +#else /* !CONFIG_FAIR_GROUP_SCHED */ + +#define for_each_sched_entity(se) \ + for (; se; se = NULL) + +static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ + return true; +} + +static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq) +{ +} + +static inline void assert_list_leaf_cfs_rq(struct rq *rq) +{ +} + +#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \ + for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos) + +static inline struct sched_entity *parent_entity(struct sched_entity *se) +{ + return NULL; +} + +static inline void +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 +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec); + +/************************************************************** + * Scheduling class tree data structure manipulation methods: + */ + +static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime) +{ + s64 delta = (s64)(vruntime - max_vruntime); + if (delta > 0) + max_vruntime = vruntime; + + return max_vruntime; +} + +static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) +{ + s64 delta = (s64)(vruntime - min_vruntime); + if (delta < 0) + min_vruntime = vruntime; + + return min_vruntime; +} + +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; + struct rb_node *leftmost = rb_first_cached(&cfs_rq->tasks_timeline); + + u64 vruntime = cfs_rq->min_vruntime; + + if (curr) { + if (curr->on_rq) + vruntime = curr->vruntime; + else + curr = NULL; + } + + if (leftmost) { /* non-empty tree */ + struct sched_entity *se = __node_2_se(leftmost); + + if (!curr) + vruntime = se->vruntime; + else + vruntime = min_vruntime(vruntime, se->vruntime); + } + + /* ensure we never gain time by being placed backwards. */ + 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)); +} + +/* + * Enqueue an entity into the rb-tree: + */ +static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + 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) +{ + rb_erase_cached(&se->run_node, &cfs_rq->tasks_timeline); +} + +struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) +{ + struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline); + + if (!left) + return NULL; + + return __node_2_se(left); +} + +static struct sched_entity *__pick_next_entity(struct sched_entity *se) +{ + struct rb_node *next = rb_next(&se->run_node); + + if (!next) + return NULL; + + return __node_2_se(next); +} + +#ifdef CONFIG_SCHED_DEBUG +struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) +{ + struct rb_node *last = rb_last(&cfs_rq->tasks_timeline.rb_root); + + if (!last) + return NULL; + + return __node_2_se(last); +} + +/************************************************************** + * Scheduling class statistics methods: + */ + +int sched_update_scaling(void) +{ + unsigned int factor = get_update_sysctl_factor(); + + sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency, + sysctl_sched_min_granularity); + +#define WRT_SYSCTL(name) \ + (normalized_sysctl_##name = sysctl_##name / (factor)) + WRT_SYSCTL(sched_min_granularity); + WRT_SYSCTL(sched_latency); + WRT_SYSCTL(sched_wakeup_granularity); +#undef WRT_SYSCTL + + return 0; +} +#endif + +/* + * delta /= w + */ +static inline u64 calc_delta_fair(u64 delta, struct sched_entity *se) +{ + if (unlikely(se->load.weight != NICE_0_LOAD)) + delta = __calc_delta(delta, NICE_0_LOAD, &se->load); + + return delta; +} + +/* + * The idea is to set a period in which each task runs once. + * + * When there are too many tasks (sched_nr_latency) we have to stretch + * this period because otherwise the slices get too small. + * + * p = (nr <= nl) ? l : l*nr/nl + */ +static u64 __sched_period(unsigned long nr_running) +{ + if (unlikely(nr_running > sched_nr_latency)) + return nr_running * sysctl_sched_min_granularity; + else + 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. + * + * s = p*P[w/rw] + */ +static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + 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; + + qcfs_rq = cfs_rq_of(se); + load = &qcfs_rq->load; + + if (unlikely(!se->on_rq)) { + 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; +} + +/* + * We calculate the vruntime slice of a to-be-inserted task. + * + * vs = s/w + */ +static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + return calc_delta_fair(sched_slice(cfs_rq, se), se); +} + +#include "pelt.h" +#ifdef CONFIG_SMP + +static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); +static unsigned long task_h_load(struct task_struct *p); +static unsigned long capacity_of(int cpu); + +/* Give new sched_entity start runnable values to heavy its load in infant time */ +void init_entity_runnable_average(struct sched_entity *se) +{ + struct sched_avg *sa = &se->avg; + + memset(sa, 0, sizeof(*sa)); + + /* + * Tasks are initialized with full load to be seen as heavy tasks until + * they get a chance to stabilize to their real load level. + * Group entities are initialized with zero load to reflect the fact that + * nothing has been attached to the task group yet. + */ + if (entity_is_task(se)) + sa->load_avg = scale_load_down(se->load.weight); + + /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ +} + +/* + * With new tasks being created, their initial util_avgs are extrapolated + * based on the cfs_rq's current util_avg: + * + * util_avg = cfs_rq->util_avg / (cfs_rq->load_avg + 1) * se.load.weight + * + * However, in many cases, the above util_avg does not give a desired + * value. Moreover, the sum of the util_avgs may be divergent, such + * as when the series is a harmonic series. + * + * To solve this problem, we also cap the util_avg of successive tasks to + * only 1/2 of the left utilization budget: + * + * util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n + * + * where n denotes the nth task and cpu_scale the CPU capacity. + * + * For example, for a CPU with 1024 of capacity, a simplest series from + * the beginning would be like: + * + * task util_avg: 512, 256, 128, 64, 32, 16, 8, ... + * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ... + * + * Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap) + * if util_avg > util_avg_cap. + */ +void post_init_entity_util_avg(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + struct sched_avg *sa = &se->avg; + long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))); + long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2; + + if (p->sched_class != &fair_sched_class) { + /* + * For !fair tasks do: + * + update_cfs_rq_load_avg(now, cfs_rq); + attach_entity_load_avg(cfs_rq, se); + switched_from_fair(rq, p); + * + * such that the next switched_to_fair() has the + * expected state. + */ + se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq); + return; + } + + 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 */ +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) +{ +} +#endif /* CONFIG_SMP */ + +/* + * Update the current task's runtime statistics. + */ +static void update_curr(struct cfs_rq *cfs_rq) +{ + struct sched_entity *curr = cfs_rq->curr; + u64 now = rq_clock_task(rq_of(cfs_rq)); + u64 delta_exec; + + if (unlikely(!curr)) + return; + + delta_exec = now - curr->exec_start; + if (unlikely((s64)delta_exec <= 0)) + return; + + curr->exec_start = now; + + 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); + + curr->vruntime += calc_delta_fair(delta_exec, curr); + update_min_vruntime(cfs_rq); + + if (entity_is_task(curr)) { + struct task_struct *curtask = task_of(curr); + + trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime); + cgroup_account_cputime(curtask, delta_exec); + account_group_exec_runtime(curtask, delta_exec); + } + + account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +static void update_curr_fair(struct rq *rq) +{ + update_curr(cfs_rq_of(&rq->curr->se)); +} + +static inline void +update_stats_wait_start_fair(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct sched_statistics *stats; + struct task_struct *p = NULL; + + if (!schedstat_enabled()) + return; + + stats = __schedstats_from_se(se); + + if (entity_is_task(se)) + p = task_of(se); + + __update_stats_wait_start(rq_of(cfs_rq), p, stats); +} + +static inline void +update_stats_wait_end_fair(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct sched_statistics *stats; + struct task_struct *p = NULL; + + if (!schedstat_enabled()) + return; + + stats = __schedstats_from_se(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); + + __update_stats_wait_end(rq_of(cfs_rq), p, stats); +} + +static inline void +update_stats_enqueue_sleeper_fair(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct sched_statistics *stats; + struct task_struct *tsk = NULL; + + if (!schedstat_enabled()) + return; + + stats = __schedstats_from_se(se); + + if (entity_is_task(se)) + tsk = task_of(se); + + __update_stats_enqueue_sleeper(rq_of(cfs_rq), tsk, stats); +} + +/* + * Task is being enqueued - update stats: + */ +static inline void +update_stats_enqueue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ + if (!schedstat_enabled()) + return; + + /* + * Are we enqueueing a waiting task? (for current tasks + * a dequeue/enqueue event is a NOP) + */ + if (se != cfs_rq->curr) + update_stats_wait_start_fair(cfs_rq, se); + + if (flags & ENQUEUE_WAKEUP) + update_stats_enqueue_sleeper_fair(cfs_rq, se); +} + +static inline void +update_stats_dequeue_fair(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ + + if (!schedstat_enabled()) + return; + + /* + * Mark the end of the wait period if dequeueing a + * waiting task: + */ + if (se != cfs_rq->curr) + 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; + + /* 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 (state & TASK_UNINTERRUPTIBLE) + __schedstat_set(tsk->stats.block_start, + rq_clock(rq_of(cfs_rq))); + } +} + +/* + * We are picking a new current task - update its stats: + */ +static inline void +update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + /* + * We are starting a new run period: + */ + se->exec_start = rq_clock_task(rq_of(cfs_rq)); +} + +/************************************************** + * 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 + * calculated based on the tasks virtual memory size and + * numa_balancing_scan_size. + */ +unsigned int sysctl_numa_balancing_scan_period_min = 1000; +unsigned int sysctl_numa_balancing_scan_period_max = 60000; + +/* Portion of address space to scan in MB */ +unsigned int sysctl_numa_balancing_scan_size = 256; + +/* 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; + + spinlock_t lock; /* nr_tasks, tasks */ + int nr_tasks; + pid_t gid; + int active_nodes; + + struct rcu_head rcu; + 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[]; +}; + +/* + * For functions that can be called in multiple contexts that permit reading + * ->numa_group (see struct task_struct for locking rules). + */ +static struct numa_group *deref_task_numa_group(struct task_struct *p) +{ + return rcu_dereference_check(p->numa_group, p == current || + (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) +{ + return rcu_dereference_protected(p->numa_group, p == current); +} + +static inline unsigned long group_faults_priv(struct numa_group *ng); +static inline unsigned long group_faults_shared(struct numa_group *ng); + +static unsigned int task_nr_scan_windows(struct task_struct *p) +{ + unsigned long rss = 0; + unsigned long nr_scan_pages; + + /* + * Calculations based on RSS as non-present and empty pages are skipped + * by the PTE scanner and NUMA hinting faults should be trapped based + * on resident pages + */ + nr_scan_pages = sysctl_numa_balancing_scan_size << (20 - PAGE_SHIFT); + rss = get_mm_rss(p->mm); + if (!rss) + rss = nr_scan_pages; + + rss = round_up(rss, nr_scan_pages); + return rss / nr_scan_pages; +} + +/* For 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) +{ + unsigned int scan_size = READ_ONCE(sysctl_numa_balancing_scan_size); + unsigned int scan, floor; + unsigned int windows = 1; + + if (scan_size < MAX_SCAN_WINDOW) + windows = MAX_SCAN_WINDOW / scan_size; + floor = 1000 / windows; + + scan = sysctl_numa_balancing_scan_period_min / task_nr_scan_windows(p); + return max_t(unsigned int, floor, scan); +} + +static unsigned int task_scan_start(struct task_struct *p) +{ + unsigned long smin = task_scan_min(p); + unsigned long period = smin; + struct numa_group *ng; + + /* Scale the maximum scan period with the amount of shared memory. */ + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) { + unsigned long shared = group_faults_shared(ng); + unsigned long private = group_faults_priv(ng); + + period *= refcount_read(&ng->refcount); + period *= shared + 1; + period /= private + shared + 1; + } + rcu_read_unlock(); + + return max(smin, period); +} + +static unsigned int task_scan_max(struct task_struct *p) +{ + unsigned long smin = task_scan_min(p); + unsigned long smax; + struct numa_group *ng; + + /* Watch for min being lower than max due to floor calculations */ + smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); + + /* Scale the maximum scan period with the amount of shared memory. */ + ng = deref_curr_numa_group(p); + if (ng) { + unsigned long shared = group_faults_shared(ng); + unsigned long private = group_faults_priv(ng); + unsigned long period = smax; + + period *= refcount_read(&ng->refcount); + period *= shared + 1; + period /= private + shared + 1; + + smax = max(smax, period); + } + + return max(smin, smax); +} + +static void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE); + rq->nr_preferred_running += (p->numa_preferred_nid == task_node(p)); +} + +static void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ + rq->nr_numa_running -= (p->numa_preferred_nid != NUMA_NO_NODE); + rq->nr_preferred_running -= (p->numa_preferred_nid == task_node(p)); +} + +/* Shared or private faults. */ +#define NR_NUMA_HINT_FAULT_TYPES 2 + +/* Memory and CPU locality */ +#define NR_NUMA_HINT_FAULT_STATS (NR_NUMA_HINT_FAULT_TYPES * 2) + +/* Averaged statistics, and temporary buffers. */ +#define NR_NUMA_HINT_FAULT_BUCKETS (NR_NUMA_HINT_FAULT_STATS * 2) + +pid_t task_numa_group_id(struct task_struct *p) +{ + struct numa_group *ng; + pid_t gid = 0; + + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) + gid = ng->gid; + rcu_read_unlock(); + + return gid; +} + +/* + * The averaged statistics, shared & private, memory & CPU, + * occupy the first half of the array. The second half of the + * array is for current counters, which are averaged into the + * first set by task_numa_placement. + */ +static inline int task_faults_idx(enum numa_faults_stats s, int nid, int priv) +{ + return NR_NUMA_HINT_FAULT_TYPES * (s * nr_node_ids + nid) + priv; +} + +static inline unsigned long task_faults(struct task_struct *p, int nid) +{ + if (!p->numa_faults) + return 0; + + return p->numa_faults[task_faults_idx(NUMA_MEM, nid, 0)] + + p->numa_faults[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +static inline unsigned long group_faults(struct task_struct *p, int nid) +{ + struct numa_group *ng = deref_task_numa_group(p); + + if (!ng) + return 0; + + return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + ng->faults[task_faults_idx(NUMA_MEM, nid, 1)]; +} + +static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) +{ + 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) +{ + unsigned long faults = 0; + int node; + + for_each_online_node(node) { + faults += ng->faults[task_faults_idx(NUMA_MEM, node, 1)]; + } + + return faults; +} + +static inline unsigned long group_faults_shared(struct numa_group *ng) +{ + unsigned long faults = 0; + int node; + + for_each_online_node(node) { + faults += ng->faults[task_faults_idx(NUMA_MEM, node, 0)]; + } + + return faults; +} + +/* + * A node triggering more than 1/3 as many NUMA faults as the maximum is + * considered part of a numa group's pseudo-interleaving set. Migrations + * between these nodes are slowed down, to allow things to settle down. + */ +#define ACTIVE_NODE_FRACTION 3 + +static bool numa_is_active_node(int nid, struct numa_group *ng) +{ + return group_faults_cpu(ng, nid) * ACTIVE_NODE_FRACTION > ng->max_faults_cpu; +} + +/* Handle placement on systems where not all nodes are directly connected. */ +static unsigned long score_nearby_nodes(struct task_struct *p, int nid, + int lim_dist, bool task) +{ + unsigned long score = 0; + int node, max_dist; + + /* + * All nodes are directly connected, and the same distance + * from each other. No need for fancy placement algorithms. + */ + 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. + */ + for_each_online_node(node) { + unsigned long faults; + int dist = node_distance(nid, node); + + /* + * The furthest away nodes in the system are not interesting + * for placement; nid was already counted. + */ + if (dist >= max_dist || node == nid) + continue; + + /* + * On systems with a backplane NUMA topology, compare groups + * of nodes, and move tasks towards the group with the most + * memory accesses. When comparing two nodes at distance + * "hoplimit", only nodes closer by than "hoplimit" are part + * of each group. Skip other nodes. + */ + if (sched_numa_topology_type == NUMA_BACKPLANE && dist >= lim_dist) + continue; + + /* Add up the faults from nearby nodes. */ + if (task) + faults = task_faults(p, node); + else + faults = group_faults(p, node); + + /* + * On systems with a glueless mesh NUMA topology, there are + * no fixed "groups of nodes". Instead, nodes that are not + * directly connected bounce traffic through intermediate + * nodes; a numa_group can occupy any set of nodes. + * The further away a node is, the less the faults count. + * This seems to result in good task placement. + */ + if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { + faults *= (max_dist - dist); + faults /= (max_dist - LOCAL_DISTANCE); + } + + score += faults; + } + + return score; +} + +/* + * These return the fraction of accesses done by a particular task, or + * task group, on a particular numa node. The group weight is given a + * larger multiplier, in order to group tasks together that are almost + * evenly spread out between numa nodes. + */ +static inline unsigned long task_weight(struct task_struct *p, int nid, + int dist) +{ + unsigned long faults, total_faults; + + if (!p->numa_faults) + return 0; + + total_faults = p->total_numa_faults; + + if (!total_faults) + return 0; + + faults = task_faults(p, nid); + faults += score_nearby_nodes(p, nid, dist, true); + + return 1000 * faults / total_faults; +} + +static inline unsigned long group_weight(struct task_struct *p, int nid, + int dist) +{ + struct numa_group *ng = deref_task_numa_group(p); + unsigned long faults, total_faults; + + if (!ng) + return 0; + + total_faults = ng->total_faults; + + if (!total_faults) + return 0; + + faults = group_faults(p, nid); + faults += score_nearby_nodes(p, nid, dist, false); + + 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) +{ + struct numa_group *ng = deref_curr_numa_group(p); + 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 + * two full passes of the "multi-stage node selection" test that is + * executed below. + */ + if ((p->numa_preferred_nid == NUMA_NO_NODE || p->numa_scan_seq <= 4) && + (cpupid_pid_unset(last_cpupid) || cpupid_match_pid(p, last_cpupid))) + return true; + + /* + * Multi-stage node selection is used in conjunction with a periodic + * migration fault to build a temporal task<->page relation. By using + * a two-stage filter we remove short/unlikely relations. + * + * Using P(p) ~ n_p / n_t as per frequentist probability, we can equate + * a task's usage of a particular page (n_p) per total usage of this + * page (n_t) (in a given time-span) to a probability. + * + * Our periodic faults will sample this probability and getting the + * same result twice in a row, given these samples are fully + * independent, is then given by P(n)^2, provided our sample period + * is sufficiently short compared to the usage pattern. + * + * This quadric squishes small probabilities, making it less likely we + * act on an unlikely task<->page relation. + */ + if (!cpupid_pid_unset(last_cpupid) && + cpupid_to_nid(last_cpupid) != dst_nid) + return false; + + /* Always allow migrate on private faults */ + if (cpupid_match_pid(p, last_cpupid)) + return true; + + /* A shared fault, but p->numa_group has not been set up yet. */ + if (!ng) + return true; + + /* + * Destination node is much more heavily used than the source + * node? Allow migration. + */ + if (group_faults_cpu(ng, dst_nid) > group_faults_cpu(ng, src_nid) * + ACTIVE_NODE_FRACTION) + return true; + + /* + * Distribute memory according to CPU & memory use on each node, + * with 3/4 hysteresis to avoid unnecessary memory migrations: + * + * faults_cpu(dst) 3 faults_cpu(src) + * --------------- * - > --------------- + * faults_mem(dst) 4 faults_mem(src) + */ + return group_faults_cpu(ng, dst_nid) * group_faults(p, src_nid) * 3 > + group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4; +} + +/* + * '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; +}; + +static inline bool is_core_idle(int cpu) +{ +#ifdef CONFIG_SCHED_SMT + int sibling; + + for_each_cpu(sibling, cpu_smt_mask(cpu)) { + if (cpu == sibling) + continue; + + if (!idle_cpu(sibling)) + return false; + } +#endif + + return true; +} + +struct task_numa_env { + struct task_struct *p; + + int src_cpu, src_nid; + int dst_cpu, dst_nid; + int imb_numa_nr; + + struct numa_stats src_stats, dst_stats; + + int imbalance_pct; + int dist; + + struct task_struct *best_task; + long best_imp; + 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); + + /* 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 && env->best_cpu != env->dst_cpu) { + rq = cpu_rq(env->best_cpu); + WRITE_ONCE(rq->numa_migrate_on, 0); + } + + if (env->best_task) + put_task_struct(env->best_task); + if (p) + get_task_struct(p); + + env->best_task = p; + env->best_imp = imp; + env->best_cpu = env->dst_cpu; +} + +static bool load_too_imbalanced(long src_load, long dst_load, + struct task_numa_env *env) +{ + long imb, old_imb; + long orig_src_load, orig_dst_load; + long src_capacity, dst_capacity; + + /* + * The load is corrected for the CPU capacity available on each node. + * + * src_load dst_load + * ------------ vs --------- + * src_capacity dst_capacity + */ + src_capacity = env->src_stats.compute_capacity; + dst_capacity = env->dst_stats.compute_capacity; + + imb = abs(dst_load * src_capacity - src_load * dst_capacity); + + orig_src_load = env->src_stats.load; + orig_dst_load = env->dst_stats.load; + + old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity); + + /* Would this change make things worse? */ + return (imb > old_imb); +} + +/* + * Maximum NUMA importance can be 1998 (2*999); + * SMALLIMP @ 30 would be close to 1998/64. + * Used to deter task migration. + */ +#define SMALLIMP 30 + +/* + * This checks if the overall compute and NUMA accesses of the system would + * be improved if the source tasks was migrated to the target dst_cpu taking + * into account that it might be best if task running on the dst_cpu should + * be exchanged with the source task + */ +static 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); + struct rq *dst_rq = cpu_rq(env->dst_cpu); + long imp = p_ng ? groupimp : taskimp; + struct task_struct *cur; + long src_load, dst_load; + int dist = env->dist; + long moveimp = imp; + long load; + bool stopsearch = false; + + if (READ_ONCE(dst_rq->numa_migrate_on)) + return false; + + rcu_read_lock(); + cur = rcu_dereference(dst_rq->curr); + if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur))) + cur = NULL; + + /* + * 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) { + stopsearch = true; + goto unlock; + } + + if (!cur) { + if (maymove && moveimp >= env->best_imp) + goto assign; + else + 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. + * + * 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); + /* + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. + */ + if (cur_ng) + imp -= imp / 16; + } else { + /* + * Compare the group weights. If a task is all by itself + * (not part of a group), use the task weight instead. + */ + if (cur_ng && p_ng) + imp += group_weight(cur, env->src_nid, dist) - + group_weight(cur, env->dst_nid, dist); + else + imp += task_weight(cur, env->src_nid, dist) - + 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; + goto assign; + } + + /* + * 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 + * misses. + */ + if (imp < SMALLIMP || imp <= env->best_imp + SMALLIMP / 2) + goto unlock; + + /* + * In the overloaded case, try and keep the load balanced. + */ + load = task_h_load(env->p) - task_h_load(cur); + if (!load) + goto assign; + + dst_load = env->dst_stats.load + load; + src_load = env->src_stats.load - load; + + if (load_too_imbalanced(src_load, dst_load, env)) + goto unlock; + +assign: + /* 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; + + /* + * If the CPU is no longer truly idle and the previous best CPU + * is, keep using it. + */ + 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) +{ + bool maymove = false; + int cpu; + + /* + * If dst node has spare capacity, then check if there is an + * imbalance that would be overruled by the load balancer. + */ + 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 */ + if (!cpumask_test_cpu(cpu, env->p->cpus_ptr)) + continue; + + env->dst_cpu = cpu; + if (task_numa_compare(env, taskimp, groupimp, maymove)) + break; + } +} + +static int task_numa_migrate(struct task_struct *p) +{ + struct task_numa_env env = { + .p = p, + + .src_cpu = task_cpu(p), + .src_nid = task_node(p), + + .imbalance_pct = 112, + + .best_task = NULL, + .best_imp = 0, + .best_cpu = -1, + }; + unsigned long taskweight, groupweight; + struct sched_domain *sd; + long taskimp, groupimp; + struct numa_group *ng; + struct rq *best_rq; + int nid, ret, dist; + + /* + * Pick the lowest SD_NUMA domain, as that would have the smallest + * imbalance and would be the first to start moving tasks about. + * + * And we want to avoid any moving of tasks about, as that would create + * random movement of tasks -- counter the numa conditions we're trying + * to satisfy here. + */ + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_numa, env.src_cpu)); + if (sd) { + env.imbalance_pct = 100 + (sd->imbalance_pct - 100) / 2; + env.imb_numa_nr = sd->imb_numa_nr; + } + rcu_read_unlock(); + + /* + * Cpusets can break the scheduler domain tree into smaller + * balance domains, some of which do not cross NUMA boundaries. + * Tasks that are "trapped" in such domains cannot be migrated + * elsewhere, so there is no point in (re)trying. + */ + if (unlikely(!sd)) { + sched_setnuma(p, task_node(p)); + return -EINVAL; + } + + env.dst_nid = p->numa_preferred_nid; + 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, &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, &env.dst_stats, env.dst_nid, true); + + /* Try to find a spot on the preferred nid. */ + task_numa_find_cpu(&env, taskimp, groupimp); + + /* + * Look at other nodes in these cases: + * - there is no space available on the preferred_nid + * - the task is part of a numa_group that is interleaved across + * multiple NUMA nodes; in order to better consolidate the group, + * we need to check other locations. + */ + ng = deref_curr_numa_group(p); + if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) { + for_each_node_state(nid, N_CPU) { + if (nid == env.src_nid || nid == p->numa_preferred_nid) + continue; + + dist = node_distance(env.src_nid, env.dst_nid); + if (sched_numa_topology_type == NUMA_BACKPLANE && + dist != env.dist) { + taskweight = task_weight(p, env.src_nid, dist); + groupweight = group_weight(p, env.src_nid, dist); + } + + /* Only consider nodes where both task and groups benefit */ + taskimp = task_weight(p, nid, dist) - taskweight; + groupimp = group_weight(p, nid, dist) - groupweight; + if (taskimp < 0 && groupimp < 0) + continue; + + env.dist = dist; + env.dst_nid = nid; + update_numa_stats(&env, &env.dst_stats, env.dst_nid, true); + task_numa_find_cpu(&env, taskimp, groupimp); + } + } + + /* + * If the task is part of a workload that spans multiple NUMA nodes, + * and is migrating into one of the workload's active nodes, remember + * this node as the task's preferred numa node, so the workload can + * settle down. + * A task that migrated to a second choice node will be better off + * trying for a better one later. Do not set the preferred node here. + */ + if (ng) { + if (env.best_cpu == -1) + nid = env.src_nid; + else + nid = cpu_to_node(env.best_cpu); + + if (nid != p->numa_preferred_nid) + sched_setnuma(p, nid); + } + + /* No better CPU than the current one was found. */ + 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, NULL, env.best_cpu); + return ret; + } + + ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu); + WRITE_ONCE(best_rq->numa_migrate_on, 0); + + if (ret != 0) + trace_sched_stick_numa(p, env.src_cpu, env.best_task, env.best_cpu); + put_task_struct(env.best_task); + return ret; +} + +/* Attempt to migrate a task to a CPU on the preferred node. */ +static void numa_migrate_preferred(struct task_struct *p) +{ + unsigned long interval = HZ; + + /* This task has no NUMA fault statistics yet */ + if (unlikely(p->numa_preferred_nid == NUMA_NO_NODE || !p->numa_faults)) + return; + + /* Periodically retry migrating the task to the preferred node */ + interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16); + p->numa_migrate_retry = jiffies + interval; + + /* Success if task is already running on preferred CPU */ + if (task_node(p) == p->numa_preferred_nid) + return; + + /* Otherwise, try migrate to a CPU on the preferred node */ + task_numa_migrate(p); +} + +/* + * Find 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. + */ +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_node_state(nid, N_CPU) { + faults = group_faults_cpu(numa_group, nid); + if (faults > max_faults) + max_faults = faults; + } + + for_each_node_state(nid, N_CPU) { + faults = group_faults_cpu(numa_group, nid); + if (faults * ACTIVE_NODE_FRACTION > max_faults) + active_nodes++; + } + + numa_group->max_faults_cpu = max_faults; + numa_group->active_nodes = active_nodes; +} + +/* + * When adapting the scan rate, the period is divided into NUMA_PERIOD_SLOTS + * increments. The more local the fault statistics are, the higher the scan + * period will be for the next scan window. If local/(local+remote) ratio is + * below NUMA_PERIOD_THRESHOLD (where range of ratio is 1..NUMA_PERIOD_SLOTS) + * the scan period will decrease. Aim for 70% local accesses. + */ +#define NUMA_PERIOD_SLOTS 10 +#define NUMA_PERIOD_THRESHOLD 7 + +/* + * Increase the scan period (slow down scanning) if the majority of + * our memory is already on our local node, or if the majority of + * the page accesses are shared with other processes. + * Otherwise, decrease the scan period. + */ +static void update_task_scan_period(struct task_struct *p, + unsigned long shared, unsigned long private) +{ + unsigned int period_slot; + int lr_ratio, ps_ratio; + int diff; + + unsigned long remote = p->numa_faults_locality[0]; + unsigned long local = p->numa_faults_locality[1]; + + /* + * If there were no record hinting faults then either the task is + * completely idle or all activity is 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 + */ + if (local + shared == 0 || p->numa_faults_locality[2]) { + p->numa_scan_period = min(p->numa_scan_period_max, + p->numa_scan_period << 1); + + p->mm->numa_next_scan = jiffies + + msecs_to_jiffies(p->numa_scan_period); + + return; + } + + /* + * Prepare to scale scan period relative to the current period. + * == NUMA_PERIOD_THRESHOLD scan period stays the same + * < NUMA_PERIOD_THRESHOLD scan period decreases (scan faster) + * >= NUMA_PERIOD_THRESHOLD scan period increases (scan slower) + */ + period_slot = DIV_ROUND_UP(p->numa_scan_period, NUMA_PERIOD_SLOTS); + lr_ratio = (local * NUMA_PERIOD_SLOTS) / (local + remote); + ps_ratio = (private * NUMA_PERIOD_SLOTS) / (private + shared); + + if (ps_ratio >= NUMA_PERIOD_THRESHOLD) { + /* + * Most memory accesses are local. There is no need to + * do fast NUMA scanning, since memory is already local. + */ + int slot = ps_ratio - NUMA_PERIOD_THRESHOLD; + if (!slot) + slot = 1; + diff = slot * period_slot; + } else if (lr_ratio >= NUMA_PERIOD_THRESHOLD) { + /* + * Most memory accesses are shared with other tasks. + * There is no point in continuing fast NUMA scanning, + * since other tasks may just move the memory elsewhere. + */ + int slot = lr_ratio - NUMA_PERIOD_THRESHOLD; + if (!slot) + slot = 1; + diff = slot * period_slot; + } else { + /* + * Private memory faults exceed (SLOTS-THRESHOLD)/SLOTS, + * yet they are not on the local NUMA node. Speed up + * NUMA scanning to get the memory moved over. + */ + int ratio = max(lr_ratio, ps_ratio); + diff = -(NUMA_PERIOD_THRESHOLD - ratio) * period_slot; + } + + p->numa_scan_period = clamp(p->numa_scan_period + diff, + task_scan_min(p), task_scan_max(p)); + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); +} + +/* + * Get the fraction of time the task has been running since the last + * NUMA placement cycle. The scheduler keeps similar statistics, but + * decays those on a 32ms period, which is orders of magnitude off + * from the dozens-of-seconds NUMA balancing period. Use the scheduler + * stats only if the task is so new there are no NUMA statistics yet. + */ +static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period) +{ + u64 runtime, delta, now; + /* Use the start of this time slice to avoid calculations. */ + now = p->se.exec_start; + runtime = p->se.sum_exec_runtime; + + if (p->last_task_numa_placement) { + delta = runtime - p->last_sum_exec_runtime; + *period = now - p->last_task_numa_placement; + + /* Avoid time going backwards, prevent potential divide error: */ + if (unlikely((s64)*period < 0)) + *period = 0; + } else { + delta = p->se.avg.load_sum; + *period = LOAD_AVG_MAX; + } + + p->last_sum_exec_runtime = runtime; + p->last_task_numa_placement = now; + + return delta; +} + +/* + * Determine the preferred nid for a task in a numa_group. This needs to + * be done in a way that produces consistent results with group_weight, + * otherwise workloads might not converge. + */ +static int preferred_group_nid(struct task_struct *p, int nid) +{ + nodemask_t nodes; + int dist; + + /* Direct connections between all NUMA nodes. */ + if (sched_numa_topology_type == NUMA_DIRECT) + return nid; + + /* + * On a system with glueless mesh NUMA topology, group_weight + * scores nodes according to the number of NUMA hinting faults on + * both the node itself, and on nearby nodes. + */ + if (sched_numa_topology_type == NUMA_GLUELESS_MESH) { + unsigned long score, max_score = 0; + int node, max_node = nid; + + dist = sched_max_numa_distance; + + for_each_node_state(node, N_CPU) { + score = group_weight(p, node, dist); + if (score > max_score) { + max_score = score; + max_node = node; + } + } + return max_node; + } + + /* + * Finding the preferred nid in a system with NUMA backplane + * interconnect topology is more involved. The goal is to locate + * tasks from numa_groups near each other in the system, and + * untangle workloads from different sides of the system. This requires + * searching down the hierarchy of node groups, recursively searching + * inside the highest scoring group of nodes. The nodemask tricks + * keep the complexity of the search down. + */ + 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; + int a, b; + + /* Are there nodes at this distance from each other? */ + if (!find_numa_distance(dist)) + continue; + + for_each_node_mask(a, nodes) { + unsigned long faults = 0; + nodemask_t this_group; + nodes_clear(this_group); + + /* Sum group's NUMA faults; includes a==b case. */ + for_each_node_mask(b, nodes) { + if (node_distance(a, b) < dist) { + faults += group_faults(p, b); + node_set(b, this_group); + node_clear(b, nodes); + } + } + + /* Remember the top group. */ + if (faults > max_faults) { + max_faults = faults; + max_group = this_group; + /* + * subtle: at the smallest distance there is + * just one node left in each "group", the + * winner is the preferred nid. + */ + nid = a; + } + } + /* Next round, evaluate the nodes within max_group. */ + if (!max_faults) + break; + nodes = max_group; + } + return nid; +} + +static void task_numa_placement(struct task_struct *p) +{ + int seq, nid, max_nid = NUMA_NO_NODE; + unsigned long max_faults = 0; + unsigned long fault_types[2] = { 0, 0 }; + unsigned long total_faults; + u64 runtime, period; + spinlock_t *group_lock = NULL; + struct numa_group *ng; + + /* + * The p->mm->numa_scan_seq field gets updated without + * exclusive access. Use READ_ONCE() here to ensure + * that the field is read in a single access: + */ + seq = READ_ONCE(p->mm->numa_scan_seq); + if (p->numa_scan_seq == seq) + return; + p->numa_scan_seq = seq; + p->numa_scan_period_max = task_scan_max(p); + + total_faults = p->numa_faults_locality[0] + + p->numa_faults_locality[1]; + runtime = numa_get_avg_runtime(p, &period); + + /* If the task is part of a group prevent parallel updates to group stats */ + ng = deref_curr_numa_group(p); + if (ng) { + group_lock = &ng->lock; + spin_lock_irq(group_lock); + } + + /* Find the node with the highest number of faults */ + for_each_online_node(nid) { + /* Keep track of the offsets in numa_faults array */ + int mem_idx, membuf_idx, cpu_idx, cpubuf_idx; + unsigned long faults = 0, group_faults = 0; + int priv; + + for (priv = 0; priv < NR_NUMA_HINT_FAULT_TYPES; priv++) { + long diff, f_diff, f_weight; + + mem_idx = task_faults_idx(NUMA_MEM, nid, priv); + membuf_idx = task_faults_idx(NUMA_MEMBUF, nid, priv); + cpu_idx = task_faults_idx(NUMA_CPU, nid, priv); + cpubuf_idx = task_faults_idx(NUMA_CPUBUF, nid, priv); + + /* Decay existing window, copy faults since last scan */ + diff = p->numa_faults[membuf_idx] - p->numa_faults[mem_idx] / 2; + fault_types[priv] += p->numa_faults[membuf_idx]; + p->numa_faults[membuf_idx] = 0; + + /* + * Normalize the faults_from, so all tasks in a group + * count according to CPU use, instead of by the raw + * number of faults. Tasks with little runtime have + * little over-all impact on throughput, and thus their + * faults are less important. + */ + f_weight = div64_u64(runtime << 16, period + 1); + f_weight = (f_weight * p->numa_faults[cpubuf_idx]) / + (total_faults + 1); + f_diff = f_weight - p->numa_faults[cpu_idx] / 2; + p->numa_faults[cpubuf_idx] = 0; + + p->numa_faults[mem_idx] += diff; + p->numa_faults[cpu_idx] += f_diff; + faults += p->numa_faults[mem_idx]; + p->total_numa_faults += diff; + if (ng) { + /* + * safe because we can only change our own group + * + * mem_idx represents the offset for a given + * nid and priv in a specific region because it + * is at the beginning of the numa_faults array. + */ + ng->faults[mem_idx] += diff; + ng->faults[cpu_idx] += f_diff; + ng->total_faults += diff; + group_faults += ng->faults[mem_idx]; + } + } + + if (!ng) { + if (faults > max_faults) { + max_faults = faults; + max_nid = nid; + } + } else if (group_faults > max_faults) { + max_faults = group_faults; + max_nid = nid; + } + } + + /* 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); + max_nid = preferred_group_nid(p, max_nid); + } + + if (max_faults) { + /* Set the new preferred node */ + if (max_nid != p->numa_preferred_nid) + sched_setnuma(p, max_nid); + } + + update_task_scan_period(p, fault_types[0], fault_types[1]); +} + +static inline int get_numa_group(struct numa_group *grp) +{ + return refcount_inc_not_zero(&grp->refcount); +} + +static inline void put_numa_group(struct numa_group *grp) +{ + if (refcount_dec_and_test(&grp->refcount)) + kfree_rcu(grp, rcu); +} + +static void task_numa_group(struct task_struct *p, int cpupid, int flags, + int *priv) +{ + struct numa_group *grp, *my_grp; + struct task_struct *tsk; + bool join = false; + int cpu = cpupid_to_cpu(cpupid); + int i; + + if (unlikely(!deref_curr_numa_group(p))) { + unsigned int size = sizeof(struct numa_group) + + NR_NUMA_HINT_FAULT_STATS * + nr_node_ids * sizeof(unsigned long); + + grp = kzalloc(size, GFP_KERNEL | __GFP_NOWARN); + if (!grp) + return; + + refcount_set(&grp->refcount, 1); + grp->active_nodes = 1; + grp->max_faults_cpu = 0; + spin_lock_init(&grp->lock); + grp->gid = p->pid; + + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] = p->numa_faults[i]; + + grp->total_faults = p->total_numa_faults; + + grp->nr_tasks++; + rcu_assign_pointer(p->numa_group, grp); + } + + rcu_read_lock(); + tsk = READ_ONCE(cpu_rq(cpu)->curr); + + if (!cpupid_match_pid(tsk, cpupid)) + goto no_join; + + grp = rcu_dereference(tsk->numa_group); + if (!grp) + goto no_join; + + my_grp = deref_curr_numa_group(p); + if (grp == my_grp) + goto no_join; + + /* + * Only join the other group if its bigger; if we're the bigger group, + * the other task will join us. + */ + if (my_grp->nr_tasks > grp->nr_tasks) + goto no_join; + + /* + * Tie-break on the grp address. + */ + if (my_grp->nr_tasks == grp->nr_tasks && my_grp > grp) + goto no_join; + + /* Always join threads in the same process. */ + if (tsk->mm == current->mm) + join = true; + + /* Simple filter to avoid false positives due to PID collisions */ + if (flags & TNF_SHARED) + join = true; + + /* Update priv based on whether false sharing was detected */ + *priv = !join; + + if (join && !get_numa_group(grp)) + goto no_join; + + rcu_read_unlock(); + + if (!join) + return; + + 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++) { + my_grp->faults[i] -= p->numa_faults[i]; + grp->faults[i] += p->numa_faults[i]; + } + my_grp->total_faults -= p->total_numa_faults; + grp->total_faults += p->total_numa_faults; + + my_grp->nr_tasks--; + grp->nr_tasks++; + + spin_unlock(&my_grp->lock); + spin_unlock_irq(&grp->lock); + + rcu_assign_pointer(p->numa_group, grp); + + put_numa_group(my_grp); + return; + +no_join: + rcu_read_unlock(); + return; +} + +/* + * 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 + * reset the data back to default state without freeing ->numa_faults. + */ +void task_numa_free(struct task_struct *p, bool final) +{ + /* safe: p either is current or is being freed by current */ + struct numa_group *grp = rcu_dereference_raw(p->numa_group); + unsigned long *numa_faults = p->numa_faults; + unsigned long flags; + int i; + + if (!numa_faults) + return; + + if (grp) { + spin_lock_irqsave(&grp->lock, flags); + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + grp->faults[i] -= p->numa_faults[i]; + grp->total_faults -= p->total_numa_faults; + + grp->nr_tasks--; + spin_unlock_irqrestore(&grp->lock, flags); + RCU_INIT_POINTER(p->numa_group, NULL); + put_numa_group(grp); + } + + if (final) { + p->numa_faults = NULL; + kfree(numa_faults); + } else { + p->total_numa_faults = 0; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + numa_faults[i] = 0; + } +} + +/* + * Got a PROT_NONE fault for a page on @node. + */ +void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) +{ + struct task_struct *p = current; + bool migrated = flags & TNF_MIGRATED; + int cpu_node = task_node(current); + int local = !!(flags & TNF_FAULT_LOCAL); + struct numa_group *ng; + int priv; + + if (!static_branch_likely(&sched_numa_balancing)) + return; + + /* for example, ksmd faulting in a user's mm */ + 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) * + NR_NUMA_HINT_FAULT_BUCKETS * nr_node_ids; + + p->numa_faults = kzalloc(size, GFP_KERNEL|__GFP_NOWARN); + if (!p->numa_faults) + return; + + p->total_numa_faults = 0; + memset(p->numa_faults_locality, 0, sizeof(p->numa_faults_locality)); + } + + /* + * First accesses are treated as private, otherwise consider accesses + * to be private if the accessing pid has not changed + */ + if (unlikely(last_cpupid == (-1 & LAST_CPUPID_MASK))) { + priv = 1; + } else { + priv = cpupid_match_pid(p, last_cpupid); + if (!priv && !(flags & TNF_NO_GROUP)) + task_numa_group(p, last_cpupid, flags, &priv); + } + + /* + * If a workload spans multiple NUMA nodes, a shared fault that + * occurs wholly within the set of nodes that the workload is + * actively using should be counted as local. This allows the + * scan rate to slow down when a workload has settled down. + */ + ng = deref_curr_numa_group(p); + if (!priv && !local && ng && ng->active_nodes > 1 && + numa_is_active_node(cpu_node, ng) && + numa_is_active_node(mem_node, ng)) + local = 1; + + /* + * Retry to migrate task to preferred node periodically, in case it + * previously failed, or the scheduler moved us. + */ + if (time_after(jiffies, p->numa_migrate_retry)) { + task_numa_placement(p); + numa_migrate_preferred(p); + } + + if (migrated) + p->numa_pages_migrated += pages; + if (flags & TNF_MIGRATE_FAIL) + p->numa_faults_locality[2] += pages; + + p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; + p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; + p->numa_faults_locality[local] += pages; +} + +static void reset_ptenuma_scan(struct task_struct *p) +{ + /* + * We only did a read acquisition of the mmap sem, so + * p->mm->numa_scan_seq is written to without exclusive access + * and the update is not guaranteed to be atomic. That's not + * much of an issue though, since this is just used for + * statistical sampling. Use READ_ONCE/WRITE_ONCE, which are not + * expensive, to avoid any form of compiler optimizations: + */ + WRITE_ONCE(p->mm->numa_scan_seq, READ_ONCE(p->mm->numa_scan_seq) + 1); + p->mm->numa_scan_offset = 0; +} + +/* + * The expensive part of numa migration is done from task_work context. + * Triggered from task_tick_numa(). + */ +static void task_numa_work(struct callback_head *work) +{ + unsigned long migrate, next_scan, now = jiffies; + 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; + long pages, virtpages; + + SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work)); + + work->next = work; + /* + * Who cares about NUMA placement when they're dying. + * + * NOTE: make sure not to dereference p->mm before this check, + * exit_task_work() happens _after_ exit_mm() so we could be called + * without p->mm even though we still had it when we enqueued this + * work. + */ + if (p->flags & PF_EXITING) + return; + + if (!mm->numa_next_scan) { + mm->numa_next_scan = now + + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + } + + /* + * Enforce maximal scan/migration frequency.. + */ + migrate = mm->numa_next_scan; + if (time_before(now, migrate)) + return; + + if (p->numa_scan_period == 0) { + p->numa_scan_period_max = task_scan_max(p); + p->numa_scan_period = task_scan_start(p); + } + + next_scan = now + msecs_to_jiffies(p->numa_scan_period); + if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate) + return; + + /* + * Delay this task enough that another task of this mm will likely win + * the next time around. + */ + p->node_stamp += 2 * TICK_NSEC; + + start = mm->numa_scan_offset; + pages = sysctl_numa_balancing_scan_size; + pages <<= 20 - PAGE_SHIFT; /* MB in pages */ + virtpages = pages * 8; /* Scan up to this much virtual space */ + if (!pages) + return; + + + if (!mmap_read_trylock(mm)) + return; + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); + if (!vma) { + reset_ptenuma_scan(p); + start = 0; + mas_set(&mas, start); + vma = mas_find(&mas, ULONG_MAX); + } + + 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; + } + + /* + * Shared library pages mapped by multiple processes are not + * migrated as it is expected they are cache replicated. Avoid + * hinting faults in read-only file-backed mappings or the vdso + * as migrating the pages will be of marginal benefit. + */ + if (!vma->vm_mm || + (vma->vm_file && (vma->vm_flags & (VM_READ|VM_WRITE)) == (VM_READ))) + continue; + + /* + * Skip inaccessible VMAs to avoid any confusion between + * PROT_NONE and NUMA hinting ptes + */ + if (!vma_is_accessible(vma)) + continue; + + do { + start = max(start, vma->vm_start); + end = ALIGN(start + (pages << PAGE_SHIFT), HPAGE_SIZE); + end = min(end, vma->vm_end); + nr_pte_updates = change_prot_numa(vma, start, end); + + /* + * Try to scan sysctl_numa_balancing_size worth of + * hpages that have at least one present PTE that + * is not already pte-numa. If the VMA contains + * areas that are unused or already full of prot_numa + * PTEs, scan up to virtpages, to skip through those + * areas faster. + */ + if (nr_pte_updates) + pages -= (end - start) >> PAGE_SHIFT; + virtpages -= (end - start) >> PAGE_SHIFT; + + start = end; + if (pages <= 0 || virtpages <= 0) + goto out; + + cond_resched(); + } while (end != vma->vm_end); + } + +out: + /* + * It is possible to reach the end of the VMA list but the last few + * VMAs are not guaranteed to the vma_migratable. If they are not, we + * would find the !migratable VMA on the next scan but not reset the + * scanner to the start so check it now. + */ + if (vma) + mm->numa_scan_offset = start; + else + reset_ptenuma_scan(p); + mmap_read_unlock(mm); + + /* + * Make sure tasks use at least 32x as much time to run other code + * than they used here, to limit NUMA PTE scanning overhead to 3% max. + * Usually update_task_scan_period slows down scanning enough; on an + * overloaded system we need to limit overhead on a per task basis. + */ + if (unlikely(p->se.sum_exec_runtime != runtime)) { + u64 diff = p->se.sum_exec_runtime - runtime; + p->node_stamp += 32 * diff; + } +} + +void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) +{ + int mm_users = 0; + struct mm_struct *mm = p->mm; + + if (mm) { + mm_users = atomic_read(&mm->mm_users); + if (mm_users == 1) { + mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + mm->numa_scan_seq = 0; + } + } + 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; + + init_task_work(&p->numa_work, task_numa_work); + + /* New address space, reset the preferred nid */ + if (!(clone_flags & CLONE_VM)) { + p->numa_preferred_nid = NUMA_NO_NODE; + return; + } + + /* + * New thread, keep existing numa_preferred_nid which should be copied + * already by arch_dup_task_struct but stagger when scans start. + */ + if (mm) { + unsigned int delay; + + delay = min_t(unsigned int, task_scan_max(current), + current->numa_scan_period * mm_users * NSEC_PER_MSEC); + delay += 2 * TICK_NSEC; + p->node_stamp = delay; + } +} + +/* + * Drive the periodic memory faults.. + */ +static void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ + struct callback_head *work = &curr->numa_work; + u64 period, now; + + /* + * We don't care about NUMA placement if we don't have memory. + */ + if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work) + return; + + /* + * Using runtime rather than walltime has the dual advantage that + * we (mostly) drive the selection from busy threads and that the + * task needs to have done some actual work before we bother with + * NUMA placement. + */ + now = curr->se.sum_exec_runtime; + period = (u64)curr->numa_scan_period * NSEC_PER_MSEC; + + if (now > curr->node_stamp + period) { + if (!curr->node_stamp) + curr->numa_scan_period = task_scan_start(curr); + curr->node_stamp += period; + + if (!time_before(jiffies, curr->mm->numa_next_scan)) + task_work_add(curr, work, TWA_RESUME); + } +} + +static void update_scan_period(struct task_struct *p, int new_cpu) +{ + int src_nid = cpu_to_node(task_cpu(p)); + int dst_nid = cpu_to_node(new_cpu); + + if (!static_branch_likely(&sched_numa_balancing)) + return; + + if (!p->mm || !p->numa_faults || (p->flags & PF_EXITING)) + return; + + if (src_nid == dst_nid) + return; + + /* + * Allow resets if faults have been trapped before one scan + * has completed. This is most likely due to a new task that + * is pulled cross-node due to wakeups or load balancing. + */ + if (p->numa_scan_seq) { + /* + * Avoid scan adjustments if moving to the preferred + * node or if the task was not previously running on + * the preferred node. + */ + if (dst_nid == p->numa_preferred_nid || + (p->numa_preferred_nid != NUMA_NO_NODE && + src_nid != p->numa_preferred_nid)) + return; + } + + p->numa_scan_period = task_scan_start(p); +} + +#else +static void task_tick_numa(struct rq *rq, struct task_struct *curr) +{ +} + +static inline void account_numa_enqueue(struct rq *rq, struct task_struct *p) +{ +} + +static inline void account_numa_dequeue(struct rq *rq, struct task_struct *p) +{ +} + +static inline void update_scan_period(struct task_struct *p, int new_cpu) +{ +} + +#endif /* CONFIG_NUMA_BALANCING */ + +static void +account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + update_load_add(&cfs_rq->load, se->load.weight); +#ifdef CONFIG_SMP + if (entity_is_task(se)) { + struct rq *rq = rq_of(cfs_rq); + + account_numa_enqueue(rq, task_of(se)); + list_add(&se->group_node, &rq->cfs_tasks); + } +#endif + cfs_rq->nr_running++; + if (se_is_idle(se)) + cfs_rq->idle_nr_running++; +} + +static void +account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + update_load_sub(&cfs_rq->load, se->load.weight); +#ifdef CONFIG_SMP + if (entity_is_task(se)) { + account_numa_dequeue(rq_of(cfs_rq), task_of(se)); + list_del_init(&se->group_node); + } +#endif + cfs_rq->nr_running--; + if (se_is_idle(se)) + cfs_rq->idle_nr_running--; +} + +/* + * Signed add and clamp on underflow. + * + * Explicitly do a load-store to ensure the intermediate value never hits + * memory. This allows lockless observations without ever seeing the negative + * values. + */ +#define add_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + typeof(_val) val = (_val); \ + typeof(*ptr) res, var = READ_ONCE(*ptr); \ + \ + res = var + val; \ + \ + if (val < 0 && res > var) \ + res = 0; \ + \ + WRITE_ONCE(*ptr, res); \ +} while (0) + +/* + * Unsigned subtract and clamp on underflow. + * + * Explicitly do a load-store to ensure the intermediate value never hits + * memory. This allows lockless observations without ever seeing the negative + * values. + */ +#define sub_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + typeof(*ptr) val = (_val); \ + typeof(*ptr) res, var = READ_ONCE(*ptr); \ + res = var - val; \ + if (res > var) \ + res = 0; \ + WRITE_ONCE(*ptr, res); \ +} while (0) + +/* + * Remove and clamp on negative, from a local variable. + * + * A variant of sub_positive(), which does not use explicit load-store + * and is thus optimized for local variable updates. + */ +#define lsub_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + *ptr -= min_t(typeof(*ptr), *ptr, _val); \ +} while (0) + +#ifdef CONFIG_SMP +static inline void +enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + cfs_rq->avg.load_avg += se->avg.load_avg; + cfs_rq->avg.load_sum += se_weight(se) * se->avg.load_sum; +} + +static inline void +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_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) +{ + if (se->on_rq) { + /* commit outstanding execution time */ + if (cfs_rq->curr == se) + update_curr(cfs_rq); + update_load_sub(&cfs_rq->load, se->load.weight); + } + dequeue_load_avg(cfs_rq, se); + + update_load_set(&se->load, weight); + +#ifdef CONFIG_SMP + do { + u32 divider = get_pelt_divider(&se->avg); + + se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider); + } while (0); +#endif + + enqueue_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) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + struct load_weight *load = &se->load; + unsigned long weight = scale_load(sched_prio_to_weight[prio]); + + 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 +/* + * All this does is approximate the hierarchical proportion which includes that + * global sum we all love to hate. + * + * That is, the weight of a group entity, is the proportional share of the + * group weight based on the group runqueue weights. That is: + * + * tg->weight * grq->load.weight + * ge->load.weight = ----------------------------- (1) + * \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 + * moves slower and therefore the approximation is cheaper and more stable. + * + * So instead of the above, we substitute: + * + * grq->load.weight -> grq->avg.load_avg (2) + * + * which yields the following: + * + * tg->weight * grq->avg.load_avg + * ge->load.weight = ------------------------------ (3) + * tg->load_avg + * + * Where: tg->load_avg ~= \Sum grq->avg.load_avg + * + * That is shares_avg, and it is right (given the approximation (2)). + * + * The problem with it is that because the average is slow -- it was designed + * to be exactly that of course -- this leads to transients in boundary + * conditions. In specific, the case where the group was idle and we start the + * one task. It takes time for our CPU's grq->avg.load_avg to build up, + * yielding bad latency etc.. + * + * Now, in that special case (1) reduces to: + * + * tg->weight * grq->load.weight + * ge->load.weight = ----------------------------- = tg->weight (4) + * grp->load.weight + * + * That is, the sum collapses because all other CPUs are idle; the UP scenario. + * + * So what we do is modify our approximation (3) to approach (4) in the (near) + * UP case, like: + * + * ge->load.weight = + * + * tg->weight * grq->load.weight + * --------------------------------------------------- (5) + * tg->load_avg - grq->avg.load_avg + grq->load.weight + * + * But because grq->load.weight can drop to 0, resulting in a divide by zero, + * we need to use grq->avg.load_avg as its lower bound, which then gives: + * + * + * tg->weight * grq->load.weight + * ge->load.weight = ----------------------------- (6) + * tg_load_avg' + * + * Where: + * + * tg_load_avg' = tg->load_avg - grq->avg.load_avg + + * max(grq->load.weight, grq->avg.load_avg) + * + * And that is shares_weight and is icky. In the (near) UP case it approaches + * (4) while in the normal case it approaches (3). It consistently + * overestimates the ge->load.weight and therefore: + * + * \Sum ge->load.weight >= tg->weight + * + * hence icky! + */ +static long calc_group_shares(struct cfs_rq *cfs_rq) +{ + long tg_weight, tg_shares, load, shares; + struct task_group *tg = cfs_rq->tg; + + tg_shares = READ_ONCE(tg->shares); + + load = max(scale_load_down(cfs_rq->load.weight), cfs_rq->avg.load_avg); + + tg_weight = atomic_long_read(&tg->load_avg); + + /* Ensure tg_weight >= load */ + tg_weight -= cfs_rq->tg_load_avg_contrib; + tg_weight += load; + + shares = (tg_shares * load); + if (tg_weight) + shares /= tg_weight; + + /* + * MIN_SHARES has to be unscaled here to support per-CPU partitioning + * of a group with small tg->shares value. It is a floor value which is + * assigned as a minimum load.weight to the sched_entity representing + * the group on a CPU. + * + * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024 + * on an 8-core system with 8 tasks each runnable on one CPU shares has + * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In + * case no task is runnable on a CPU MIN_SHARES=2 should be returned + * instead of 0. + */ + return clamp_t(long, shares, MIN_SHARES, tg_shares); +} +#endif /* CONFIG_SMP */ + +/* + * Recomputes the group entity based on the current state of its group + * runqueue. + */ +static void update_cfs_group(struct sched_entity *se) +{ + struct cfs_rq *gcfs_rq = group_cfs_rq(se); + long shares; + + if (!gcfs_rq) + return; + + if (throttled_hierarchy(gcfs_rq)) + return; + +#ifndef CONFIG_SMP + shares = READ_ONCE(gcfs_rq->tg->shares); + + if (likely(se->load.weight == shares)) + return; +#else + shares = calc_group_shares(gcfs_rq); +#endif + + reweight_entity(cfs_rq_of(se), se, shares); +} + +#else /* CONFIG_FAIR_GROUP_SCHED */ +static inline void update_cfs_group(struct sched_entity *se) +{ +} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) +{ + struct rq *rq = rq_of(cfs_rq); + + if (&rq->cfs == cfs_rq) { + /* + * There are a few boundary cases this might miss but it should + * get called often enough that that should (hopefully) not be + * a real problem. + * + * It will not get called when we go idle, because the idle + * thread is a different class (!fair), nor will the utilization + * number include things like RT tasks. + * + * As is, the util number is not freq-invariant (we'd have to + * implement arch_scale_freq_capacity() for that). + * + * 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 + * + * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load. + * However, because tg->load_avg is a global value there are performance + * considerations. + * + * In order to avoid having to look at the other cfs_rq's, we use a + * differential update where we store the last value we propagated. This in + * turn allows skipping updates if the differential is 'small'. + * + * Updating tg's load_avg is necessary before update_cfs_share(). + */ +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; + + /* + * No need to update load_avg for root_task_group as it is not used. + */ + if (cfs_rq->tg == &root_task_group) + return; + + 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; + } +} + +/* + * Called within set_task_rq() right before setting a task's CPU. The + * caller only guarantees p->pi_lock is held; no other assumptions, + * including the state of rq->lock, should be made. + */ +void set_task_rq_fair(struct sched_entity *se, + struct cfs_rq *prev, struct cfs_rq *next) +{ + u64 p_last_update_time; + u64 n_last_update_time; + + if (!sched_feat(ATTACH_AGE_LOAD)) + return; + + /* + * 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. + */ + if (!(se->avg.last_update_time && prev)) + return; + + p_last_update_time = cfs_rq_last_update_time(prev); + n_last_update_time = cfs_rq_last_update_time(next); + + __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 + * that for each group: + * + * ge->avg == grq->avg (1) + * + * _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() 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_load() is more complex. So we have: + * + * ge->avg.load_avg = ge->load.weight * ge->avg.runnable_avg (2) + * + * And since, like util, the runnable part should be directly transferable, + * the following would _appear_ to be the straight forward approach: + * + * grq->avg.load_avg = grq->load.weight * grq->avg.runnable_avg (3) + * + * And per (1) we have: + * + * ge->avg.runnable_avg == grq->avg.runnable_avg + * + * Which gives: + * + * ge->load.weight * grq->avg.load_avg + * ge->avg.load_avg = ----------------------------------- (4) + * grq->load.weight + * + * Except that is wrong! + * + * Because while for entities historical weight is not important and we + * really only care about our future and therefore can consider a pure + * runnable sum, runqueues can NOT do this. + * + * We specifically want runqueues to have a load_avg that includes + * historical weights. Those represent the blocked load, the load we expect + * to (shortly) return to us. This only works by keeping the weights as + * integral part of the sum. We therefore cannot decompose as per (3). + * + * Another reason this doesn't work is that runnable isn't a 0-sum entity. + * Imagine a rq with 2 tasks that each are runnable 2/3 of the time. Then the + * rq itself is runnable anywhere between 2/3 and 1 depending on how the + * runnable section of these tasks overlap (or not). If they were to perfectly + * align the rq as a whole would be runnable 2/3 of the time. If however we + * always have at least 1 runnable task, the rq as a whole is always runnable. + * + * So we'll have to approximate.. :/ + * + * Given the constraint: + * + * ge->avg.running_sum <= ge->avg.runnable_sum <= LOAD_AVG_MAX + * + * We can construct a rule that adds runnable to a rq by assuming minimal + * overlap. + * + * On removal, we'll assume each task is equally runnable; which yields: + * + * grq->avg.runnable_sum = grq->avg.load_sum / grq->load.weight + * + * 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_sum, delta_avg = gcfs_rq->avg.util_avg - se->avg.util_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 utilization */ + se->avg.util_avg = gcfs_rq->avg.util_avg; + 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_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 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_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_u64(gcfs_rq->avg.load_sum, + scale_load_down(gcfs_rq->load.weight)); + } + + /* But make sure to not inflate se's runnable */ + runnable_sum = min(se->avg.load_sum, load_sum); + } + + /* + * runnable_sum can't be lower than running_sum + * Rescale running sum to be in the same range as runnable sum + * running_sum is in [0 : LOAD_AVG_MAX << SCHED_CAPACITY_SHIFT] + * runnable_sum is in [0 : LOAD_AVG_MAX] + */ + running_sum = se->avg.util_sum >> SCHED_CAPACITY_SHIFT; + runnable_sum = max(runnable_sum, running_sum); + + load_sum = se_weight(se) * runnable_sum; + load_avg = div_u64(load_sum, divider); + + 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); + /* 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) +{ + cfs_rq->propagate = 1; + cfs_rq->prop_runnable_sum += runnable_sum; +} + +/* Update task and its cfs_rq load average */ +static inline int propagate_entity_load_avg(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq, *gcfs_rq; + + if (entity_is_task(se)) + return 0; + + gcfs_rq = group_cfs_rq(se); + if (!gcfs_rq->propagate) + return 0; + + gcfs_rq->propagate = 0; + + cfs_rq = cfs_rq_of(se); + + add_tg_cfs_propagate(cfs_rq, gcfs_rq->prop_runnable_sum); + + 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); + + return 1; +} + +/* + * Check if we need to update the load and the utilization of a blocked + * group_entity: + */ +static inline bool skip_blocked_update(struct sched_entity *se) +{ + struct cfs_rq *gcfs_rq = group_cfs_rq(se); + + /* + * If sched_entity still have not zero load or utilization, we have to + * decay it: + */ + if (se->avg.load_avg || se->avg.util_avg) + return false; + + /* + * If there is a pending propagation, we have to update the load and + * the utilization of the sched_entity: + */ + if (gcfs_rq->propagate) + return false; + + /* + * Otherwise, the load and the utilization of the sched_entity is + * already zero and there is no pending propagation, so it will be a + * waste of time to try to decay it: + */ + return true; +} + +#else /* CONFIG_FAIR_GROUP_SCHED */ + +static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {} + +static inline int propagate_entity_load_avg(struct sched_entity *se) +{ + return 0; +} + +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. + * + * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example. + * + * 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. + */ +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 = 0; + struct sched_avg *sa = &cfs_rq->avg; + int decayed = 0; + + if (cfs_rq->removed.nr) { + unsigned long r; + 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_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); + + 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); + u64_u32_store_copy(sa->last_update_time, + cfs_rq->last_update_time_copy, + sa->last_update_time); + return decayed; +} + +/** + * attach_entity_load_avg - attach this entity to its cfs_rq load avg + * @cfs_rq: cfs_rq to attach to + * @se: sched_entity to attach + * + * Must call update_cfs_rq_load_avg() before this, since we rely on + * cfs_rq->avg.last_update_time being current. + */ +static void attach_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); + + /* + * When we attach the @se to the @cfs_rq, we must align the decay + * window because without that, really weird and wonderful things can + * happen. + * + * XXX illustrate + */ + se->avg.last_update_time = cfs_rq->avg.last_update_time; + se->avg.period_contrib = cfs_rq->avg.period_contrib; + + /* + * Hell(o) Nasty stuff.. we need to recompute _sum based on the new + * period_contrib. This isn't strictly correct, but since we're + * entirely outside of the PELT hierarchy, nobody cares if we truncate + * _sum a little. + */ + se->avg.util_sum = se->avg.util_avg * divider; + + se->avg.runnable_sum = se->avg.runnable_avg * divider; + + 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); + + cfs_rq_util_change(cfs_rq, 0); + + trace_pelt_cfs_tp(cfs_rq); +} + +/** + * detach_entity_load_avg - detach this entity from its cfs_rq load avg + * @cfs_rq: cfs_rq to detach from + * @se: sched_entity to detach + * + * Must call update_cfs_rq_load_avg() before this, since we rely on + * cfs_rq->avg.last_update_time being current. + */ +static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + 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); + + cfs_rq_util_change(cfs_rq, 0); + + trace_pelt_cfs_tp(cfs_rq); +} + +/* + * Optional action to be done while updating the load average + */ +#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) +{ + u64 now = cfs_rq_clock_pelt(cfs_rq); + int decayed; + + /* + * Track task load average for carrying it to new CPU after migrated, and + * track group sched_entity load average for task_h_load calc in migration + */ + if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) + __update_load_avg_se(now, cfs_rq, se); + + decayed = update_cfs_rq_load_avg(now, cfs_rq); + decayed |= propagate_entity_load_avg(se); + + if (!se->avg.last_update_time && (flags & DO_ATTACH)) { + + /* + * DO_ATTACH means we're here from enqueue_entity(). + * !last_update_time means we've passed through + * migrate_task_rq_fair() indicating we migrated. + * + * IOW we're enqueueing a task on a new CPU. + */ + attach_entity_load_avg(cfs_rq, se); + 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); + } +} + +/* + * Synchronize entity load avg of dequeued entity without locking + * the previous rq. + */ +static void sync_entity_load_avg(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 last_update_time; + + last_update_time = cfs_rq_last_update_time(cfs_rq); + __update_load_avg_blocked_se(last_update_time, se); +} + +/* + * Task first catches up with cfs_rq, and then subtract + * itself from the cfs_rq (task must be off the queue now). + */ +static void remove_entity_load_avg(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + unsigned long flags; + + /* + * tasks cannot exit without having gone through wake_up_new_task() -> + * enqueue_task_fair() which will have added things to the cfs_rq, + * so we can remove unconditionally. + */ + + sync_entity_load_avg(se); + + raw_spin_lock_irqsave(&cfs_rq->removed.lock, flags); + ++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_avg += se->avg.runnable_avg; + raw_spin_unlock_irqrestore(&cfs_rq->removed.lock, flags); +} + +static inline unsigned long cfs_rq_runnable_avg(struct cfs_rq *cfs_rq) +{ + return cfs_rq->avg.runnable_avg; +} + +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); +} + +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)); +} + +static inline unsigned long task_util_est(struct task_struct *p) +{ + return max(task_util(p), _task_util_est(p)); +} + +static inline void util_est_enqueue(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 += _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 + margin < INT_MAX. + */ +static inline bool within_margin(int value, int margin) +{ + return ((unsigned int)(value + margin - 1) < (2 * margin - 1)); +} + +static inline void util_est_update(struct cfs_rq *cfs_rq, + struct task_struct *p, + bool task_sleep) +{ + long last_ewma_diff, last_enqueued_diff; + struct util_est ue; + + if (!sched_feat(UTIL_EST)) + return; + + /* + * Skip update of task's estimated utilization when the task has not + * yet completed an activation, e.g. being migrated. + */ + if (!task_sleep) + return; + + /* + * If the PELT values haven't changed since enqueue time, + * skip the util_est update. + */ + ue = p->se.avg.util_est; + 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); + if (sched_feat(UTIL_EST_FASTUP)) { + if (ue.ewma < ue.enqueued) { + ue.ewma = ue.enqueued; + goto done; + } + } + + /* + * 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; + 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. + */ + if (task_util(p) > capacity_orig_of(cpu_of(rq_of(cfs_rq)))) + return; + + /* + * Update Task's estimated utilization + * + * When *p completes an activation we can consolidate another sample + * of the task size. This is done by storing the current PELT value + * as ue.enqueued and by using this value to update the Exponential + * Weighted Moving Average (EWMA): + * + * ewma(t) = w * task_util(p) + (1-w) * ewma(t-1) + * = w * task_util(p) + ewma(t-1) - w * ewma(t-1) + * = w * (task_util(p) - ewma(t-1)) + ewma(t-1) + * = w * ( last_ewma_diff ) + ewma(t-1) + * = w * (last_ewma_diff + ewma(t-1) / w) + * + * Where 'w' is the weight of new samples, which is configured to be + * 0.25, thus making w=1/4 ( >>= UTIL_EST_WEIGHT_SHIFT) + */ + ue.ewma <<= UTIL_EST_WEIGHT_SHIFT; + 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 util_fits_cpu(unsigned long util, + unsigned long uclamp_min, + unsigned long uclamp_max, + int cpu) +{ + unsigned long capacity_orig, capacity_orig_thermal; + unsigned long capacity = capacity_of(cpu); + bool fits, uclamp_max_fits; + + /* + * Check if the real util fits without any uclamp boost/cap applied. + */ + fits = fits_capacity(util, capacity); + + if (!uclamp_is_used()) + return fits; + + /* + * We must use capacity_orig_of() for comparing against uclamp_min and + * uclamp_max. We only care about capacity pressure (by using + * capacity_of()) for comparing against the real util. + * + * If a task is boosted to 1024 for example, we don't want a tiny + * pressure to skew the check whether it fits a CPU or not. + * + * Similarly if a task is capped to capacity_orig_of(little_cpu), it + * should fit a little cpu even if there's some pressure. + * + * Only exception is for thermal pressure since it has a direct impact + * on available OPP of the system. + * + * We honour it for uclamp_min only as a drop in performance level + * could result in not getting the requested minimum performance level. + * + * For uclamp_max, we can tolerate a drop in performance level as the + * goal is to cap the task. So it's okay if it's getting less. + */ + capacity_orig = capacity_orig_of(cpu); + capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu); + + /* + * We want to force a task to fit a cpu as implied by uclamp_max. + * But we do have some corner cases to cater for.. + * + * + * C=z + * | ___ + * | C=y | | + * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max + * | C=x | | | | + * | ___ | | | | + * | | | | | | | (util somewhere in this region) + * | | | | | | | + * | | | | | | | + * +---------------------------------------- + * cpu0 cpu1 cpu2 + * + * In the above example if a task is capped to a specific performance + * point, y, then when: + * + * * util = 80% of x then it does not fit on cpu0 and should migrate + * to cpu1 + * * util = 80% of y then it is forced to fit on cpu1 to honour + * uclamp_max request. + * + * which is what we're enforcing here. A task always fits if + * uclamp_max <= capacity_orig. But when uclamp_max > capacity_orig, + * the normal upmigration rules should withhold still. + * + * Only exception is when we are on max capacity, then we need to be + * careful not to block overutilized state. This is so because: + * + * 1. There's no concept of capping at max_capacity! We can't go + * beyond this performance level anyway. + * 2. The system is being saturated when we're operating near + * max capacity, it doesn't make sense to block overutilized. + */ + uclamp_max_fits = (capacity_orig == SCHED_CAPACITY_SCALE) && (uclamp_max == SCHED_CAPACITY_SCALE); + uclamp_max_fits = !uclamp_max_fits && (uclamp_max <= capacity_orig); + fits = fits || uclamp_max_fits; + + /* + * + * C=z + * | ___ (region a, capped, util >= uclamp_max) + * | C=y | | + * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max + * | C=x | | | | + * | ___ | | | | (region b, uclamp_min <= util <= uclamp_max) + * |_ _ _|_ _|_ _ _ _| _ | _ _ _| _ | _ _ _ _ _ uclamp_min + * | | | | | | | + * | | | | | | | (region c, boosted, util < uclamp_min) + * +---------------------------------------- + * cpu0 cpu1 cpu2 + * + * a) If util > uclamp_max, then we're capped, we don't care about + * actual fitness value here. We only care if uclamp_max fits + * capacity without taking margin/pressure into account. + * See comment above. + * + * b) If uclamp_min <= util <= uclamp_max, then the normal + * fits_capacity() rules apply. Except we need to ensure that we + * enforce we remain within uclamp_max, see comment above. + * + * c) If util < uclamp_min, then we are boosted. Same as (b) but we + * need to take into account the boosted value fits the CPU without + * taking margin/pressure into account. + * + * Cases (a) and (b) are handled in the 'fits' variable already. We + * just need to consider an extra check for case (c) after ensuring we + * handle the case uclamp_min > uclamp_max. + */ + uclamp_min = min(uclamp_min, uclamp_max); + if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal)) + return -1; + + return fits; +} + +static inline int task_fits_cpu(struct task_struct *p, int cpu) +{ + unsigned long uclamp_min = uclamp_eff_value(p, UCLAMP_MIN); + unsigned long uclamp_max = uclamp_eff_value(p, UCLAMP_MAX); + unsigned long util = task_util_est(p); + /* + * Return true only if the cpu fully fits the task requirements, which + * include the utilization but also the performance hints. + */ + return (util_fits_cpu(util, uclamp_min, uclamp_max, cpu) > 0); +} + +static inline void update_misfit_status(struct task_struct *p, struct rq *rq) +{ + if (!sched_asym_cpucap_active()) + return; + + if (!p || p->nr_cpus_allowed == 1) { + rq->misfit_task_load = 0; + return; + } + + if (task_fits_cpu(p, cpu_of(rq))) { + rq->misfit_task_load = 0; + return; + } + + /* + * 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 !cfs_rq->nr_running; +} + +#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) +{ + cfs_rq_util_change(cfs_rq, 0); +} + +static inline void remove_entity_load_avg(struct sched_entity *se) {} + +static inline void +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 newidle_balance(struct rq *rq, struct rq_flags *rf) +{ + return 0; +} + +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) {} + +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 */ + +static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ +#ifdef CONFIG_SCHED_DEBUG + s64 d = se->vruntime - cfs_rq->min_vruntime; + + if (d < 0) + d = -d; + + if (d > 3*sysctl_sched_latency) + schedstat_inc(cfs_rq->nr_spread_over); +#endif +} + +static inline bool entity_is_long_sleeper(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq; + u64 sleep_time; + + if (se->exec_start == 0) + return false; + + cfs_rq = cfs_rq_of(se); + + sleep_time = rq_clock_task(rq_of(cfs_rq)); + + /* Happen while migrating because of clock task divergence */ + if (sleep_time <= se->exec_start) + return false; + + sleep_time -= se->exec_start; + if (sleep_time > ((1ULL << 63) / scale_load_down(NICE_0_LOAD))) + return true; + + return false; +} + +static void +place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) +{ + u64 vruntime = cfs_rq->min_vruntime; + + /* + * The 'current' period is already promised to the current tasks, + * however the extra weight of the new task will slow them down a + * little, place the new task so that it fits in the slot that + * stays open at the end. + */ + if (initial && sched_feat(START_DEBIT)) + vruntime += sched_vslice(cfs_rq, se); + + /* sleeps up to a single latency don't count. */ + if (!initial) { + 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 + * for a gentler effect of sleepers: + */ + if (sched_feat(GENTLE_FAIR_SLEEPERS)) + thresh >>= 1; + + vruntime -= thresh; + } + + /* + * Pull vruntime of the entity being placed to the base level of + * cfs_rq, to prevent boosting it if placed backwards. + * However, min_vruntime can advance much faster than real time, with + * the extreme being when an entity with the minimal weight always runs + * on the cfs_rq. If the waking entity slept for a long time, its + * vruntime difference from min_vruntime may overflow s64 and their + * comparison may get inversed, so ignore the entity's original + * vruntime in that case. + * The maximal vruntime speedup is given by the ratio of normal to + * minimal weight: scale_load_down(NICE_0_LOAD) / MIN_SHARES. + * When placing a migrated waking entity, its exec_start has been set + * from a different rq. In order to take into account a possible + * divergence between new and prev rq's clocks task because of irq and + * stolen time, we take an additional margin. + * So, cutting off on the sleep time of + * 2^63 / scale_load_down(NICE_0_LOAD) ~ 104 days + * should be safe. + */ + if (entity_is_long_sleeper(se)) + se->vruntime = vruntime; + else + se->vruntime = max_vruntime(se->vruntime, vruntime); +} + +static void check_enqueue_throttle(struct cfs_rq *cfs_rq); + +static inline bool cfs_bandwidth_used(void); + +/* + * MIGRATION + * + * dequeue + * update_curr() + * update_min_vruntime() + * vruntime -= min_vruntime + * + * enqueue + * update_curr() + * update_min_vruntime() + * vruntime += min_vruntime + * + * this way the vruntime transition between RQs is done when both + * min_vruntime are up-to-date. + * + * WAKEUP (remote) + * + * ->migrate_task_rq_fair() (p->state == TASK_WAKING) + * vruntime -= min_vruntime + * + * enqueue + * update_curr() + * update_min_vruntime() + * vruntime += min_vruntime + * + * this way we don't have the most up-to-date min_vruntime on the originating + * CPU and an up-to-date min_vruntime on the destination CPU. + */ + +static void +enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) +{ + bool renorm = !(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATED); + bool curr = cfs_rq->curr == se; + + /* + * If we're the current task, we must renormalise before calling + * update_curr(). + */ + if (renorm && curr) + se->vruntime += cfs_rq->min_vruntime; + + update_curr(cfs_rq); + + /* + * Otherwise, renormalise after, such that we're placed at the current + * moment in time, instead of some random moment in the past. Being + * placed in the past could significantly boost this task to the + * fairness detriment of existing tasks. + */ + if (renorm && !curr) + se->vruntime += cfs_rq->min_vruntime; + + /* + * When enqueuing a sched_entity, we must: + * - Update loads to have both entity and cfs_rq synced with now. + * - 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); + account_entity_enqueue(cfs_rq, se); + + if (flags & ENQUEUE_WAKEUP) + place_entity(cfs_rq, se, 0); + /* Entity has migrated, no longer consider this task hot */ + if (flags & ENQUEUE_MIGRATED) + se->exec_start = 0; + + check_schedstat_required(); + 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) { + check_enqueue_throttle(cfs_rq); + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); + } +} + +static void __clear_buddies_last(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->last != se) + break; + + cfs_rq->last = NULL; + } +} + +static void __clear_buddies_next(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->next != se) + break; + + cfs_rq->next = NULL; + } +} + +static void __clear_buddies_skip(struct sched_entity *se) +{ + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + if (cfs_rq->skip != se) + break; + + cfs_rq->skip = NULL; + } +} + +static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + if (cfs_rq->last == se) + __clear_buddies_last(se); + + if (cfs_rq->next == se) + __clear_buddies_next(se); + + if (cfs_rq->skip == se) + __clear_buddies_skip(se); +} + +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'. + */ + update_curr(cfs_rq); + + /* + * When dequeuing a sched_entity, we must: + * - Update loads to have both entity and cfs_rq synced with now. + * - 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, action); + se_update_runnable(se); + + update_stats_dequeue_fair(cfs_rq, se, flags); + + clear_buddies(cfs_rq, se); + + if (se != cfs_rq->curr) + __dequeue_entity(cfs_rq, se); + se->on_rq = 0; + account_entity_dequeue(cfs_rq, se); + + /* + * Normalize after update_curr(); which will also have moved + * min_vruntime if @se is the one holding it back. But before doing + * update_min_vruntime() again, which will discount @se's position and + * can move min_vruntime forward still more. + */ + if (!(flags & DEQUEUE_SLEEP)) + se->vruntime -= cfs_rq->min_vruntime; + + /* return excess runtime on last dequeue */ + return_cfs_rq_runtime(cfs_rq); + + update_cfs_group(se); + + /* + * Now advance min_vruntime if @se was the entity holding it back, + * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be + * put back on, and if we advance min_vruntime, we'll be placed back + * further than we started -- ie. we'll be penalized. + */ + 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); +} + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void +check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) +{ + unsigned long ideal_runtime, delta_exec; + struct sched_entity *se; + s64 delta; + + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { + resched_curr(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. + */ + clear_buddies(cfs_rq, curr); + return; + } + + /* + * Ensure that a task that missed wakeup preemption by a + * narrow margin doesn't have to wait for a full slice. + * This also mitigates buddy induced latencies under load. + */ + if (delta_exec < sysctl_sched_min_granularity) + return; + + se = __pick_first_entity(cfs_rq); + delta = curr->vruntime - se->vruntime; + + if (delta < 0) + return; + + if (delta > ideal_runtime) + resched_curr(rq_of(cfs_rq)); +} + +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) { + /* + * Any task has to be enqueued before it get to execute on + * a CPU. So account for the time it spent waiting on the + * runqueue. + */ + update_stats_wait_end_fair(cfs_rq, se); + __dequeue_entity(cfs_rq, se); + update_load_avg(cfs_rq, se, UPDATE_TG); + } + + update_stats_curr_start(cfs_rq, se); + cfs_rq->curr = se; + + /* + * Track our maximum slice length, if the CPU's load is at + * least twice that of our own weight (i.e. dont track it + * when there are only lesser-weight tasks around): + */ + if (schedstat_enabled() && + rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) { + 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; +} + +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); + +/* + * Pick the next process, keeping these things in mind, in this order: + * 1) keep things fair between processes/task groups + * 2) pick the "next" process, since someone really wants that to run + * 3) pick the "last" process, for cache locality + * 4) do not run the "skip" process, if something else is available + */ +static struct sched_entity * +pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) +{ + struct sched_entity *left = __pick_first_entity(cfs_rq); + struct sched_entity *se; + + /* + * If curr is set we have to see if its left of the leftmost entity + * still in the tree, provided there was anything in the tree at all. + */ + if (!left || (curr && entity_before(curr, left))) + left = curr; + + se = left; /* ideally we run the leftmost entity */ + + /* + * Avoid running the skip buddy, if running something else can + * be done without getting too unfair. + */ + if (cfs_rq->skip && cfs_rq->skip == se) { + struct sched_entity *second; + + if (se == curr) { + second = __pick_first_entity(cfs_rq); + } else { + second = __pick_next_entity(se); + if (!second || (curr && entity_before(curr, second))) + second = curr; + } + + if (second && wakeup_preempt_entity(second, left) < 1) + se = second; + } + + 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; + } 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; +} + +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq); + +static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) +{ + /* + * If still on the runqueue then deactivate_task() + * was not called and update_curr() has to be done: + */ + if (prev->on_rq) + update_curr(cfs_rq); + + /* throttle cfs_rqs exceeding runtime */ + check_cfs_rq_runtime(cfs_rq); + + check_spread(cfs_rq, prev); + + if (prev->on_rq) { + 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 */ + update_load_avg(cfs_rq, prev, 0); + } + cfs_rq->curr = NULL; +} + +static void +entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) +{ + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + + /* + * Ensure that runnable average is periodically updated. + */ + update_load_avg(cfs_rq, curr, UPDATE_TG); + update_cfs_group(curr); + +#ifdef CONFIG_SCHED_HRTICK + /* + * queued ticks are scheduled to match the slice, so don't bother + * validating it and just reschedule. + */ + if (queued) { + resched_curr(rq_of(cfs_rq)); + return; + } + /* + * don't let the period tick interfere with the hrtick preemption + */ + if (!sched_feat(DOUBLE_TICK) && + hrtimer_active(&rq_of(cfs_rq)->hrtick_timer)) + return; +#endif + + if (cfs_rq->nr_running > 1) + check_preempt_tick(cfs_rq, curr); +} + + +/************************************************** + * CFS bandwidth control machinery + */ + +#ifdef CONFIG_CFS_BANDWIDTH + +#ifdef CONFIG_JUMP_LABEL +static struct static_key __cfs_bandwidth_used; + +static inline bool cfs_bandwidth_used(void) +{ + return static_key_false(&__cfs_bandwidth_used); +} + +void cfs_bandwidth_usage_inc(void) +{ + static_key_slow_inc_cpuslocked(&__cfs_bandwidth_used); +} + +void cfs_bandwidth_usage_dec(void) +{ + static_key_slow_dec_cpuslocked(&__cfs_bandwidth_used); +} +#else /* CONFIG_JUMP_LABEL */ +static bool cfs_bandwidth_used(void) +{ + return true; +} + +void cfs_bandwidth_usage_inc(void) {} +void cfs_bandwidth_usage_dec(void) {} +#endif /* CONFIG_JUMP_LABEL */ + +/* + * default period for cfs group bandwidth. + * default: 0.1s, units: nanoseconds + */ +static inline u64 default_cfs_period(void) +{ + return 100000000ULL; +} + +static inline u64 sched_cfs_bandwidth_slice(void) +{ + return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; +} + +/* + * Replenish runtime according to assigned quota. We use sched_clock_cpu + * directly instead of rq->clock to avoid adding additional synchronization + * around rq->lock. + * + * requires cfs_b->lock + */ +void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) +{ + 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) +{ + return &tg->cfs_bandwidth; +} + +/* returns 0 on failure to allocate runtime */ +static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b, + struct cfs_rq *cfs_rq, u64 target_runtime) +{ + u64 min_amount, amount = 0; + + lockdep_assert_held(&cfs_b->lock); + + /* note: this is a positive sum as runtime_remaining <= 0 */ + min_amount = target_runtime - cfs_rq->runtime_remaining; + + if (cfs_b->quota == RUNTIME_INF) + amount = min_amount; + else { + start_cfs_bandwidth(cfs_b); + + if (cfs_b->runtime > 0) { + amount = min(cfs_b->runtime, min_amount); + cfs_b->runtime -= amount; + cfs_b->idle = 0; + } + } + + 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) */ + cfs_rq->runtime_remaining -= delta_exec; + + if (likely(cfs_rq->runtime_remaining > 0)) + return; + + if (cfs_rq->throttled) + return; + /* + * if we're unable to extend our runtime we resched so that the active + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) + resched_curr(rq_of(cfs_rq)); +} + +static __always_inline +void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) +{ + if (!cfs_bandwidth_used() || !cfs_rq->runtime_enabled) + return; + + __account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return cfs_bandwidth_used() && cfs_rq->throttled; +} + +/* check whether cfs_rq, or any parent, is throttled */ +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return cfs_bandwidth_used() && cfs_rq->throttle_count; +} + +/* + * Ensure that neither of the group entities corresponding to src_cpu or + * dest_cpu are members of a throttled hierarchy when performing group + * load-balance operations. + */ +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + struct cfs_rq *src_cfs_rq, *dest_cfs_rq; + + src_cfs_rq = tg->cfs_rq[src_cpu]; + dest_cfs_rq = tg->cfs_rq[dest_cpu]; + + return throttled_hierarchy(src_cfs_rq) || + throttled_hierarchy(dest_cfs_rq); +} + +static int tg_unthrottle_up(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + cfs_rq->throttle_count--; + if (!cfs_rq->throttle_count) { + cfs_rq->throttled_clock_pelt_time += rq_clock_pelt(rq) - + cfs_rq->throttled_clock_pelt; + + /* 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); + } + + return 0; +} + +static int tg_throttle_down(struct task_group *tg, void *data) +{ + struct rq *rq = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + /* group is entering throttled state, stop time */ + if (!cfs_rq->throttle_count) { + cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq); + list_del_leaf_cfs_rq(cfs_rq); + } + cfs_rq->throttle_count++; + + return 0; +} + +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; + + 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))]; + + /* freeze hierarchy runnable averages while throttled */ + rcu_read_lock(); + walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, (void *)rq); + rcu_read_unlock(); + + 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); + /* throttled entity or throttle-on-deactivate */ + if (!se->on_rq) + 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; + + qcfs_rq->h_nr_running -= task_delta; + qcfs_rq->idle_h_nr_running -= idle_task_delta; + + if (qcfs_rq->load.weight) { + /* Avoid re-evaluating load for this entity: */ + se = parent_entity(se); + break; + } + } + + 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; + + update_load_avg(qcfs_rq, se, 0); + 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; + } + + /* At this point se is NULL and we are at root level*/ + sub_nr_running(rq, task_delta); + +done: + /* + * Note: distribution will already see us throttled via the + * throttled-list. rq->lock protects completion. + */ + cfs_rq->throttled = 1; + cfs_rq->throttled_clock = rq_clock(rq); + return true; +} + +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; + long task_delta, idle_task_delta; + + se = cfs_rq->tg->se[cpu_of(rq)]; + + cfs_rq->throttled = 0; + + update_rq_clock(rq); + + raw_spin_lock(&cfs_b->lock); + cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock; + list_del_rcu(&cfs_rq->throttled_list); + raw_spin_unlock(&cfs_b->lock); + + /* update hierarchical throttle state */ + walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); + + 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) + break; + enqueue_entity(qcfs_rq, se, ENQUEUE_WAKEUP); + + 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; + } + + for_each_sched_entity(se) { + struct cfs_rq *qcfs_rq = cfs_rq_of(se); + + 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 void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b) +{ + struct cfs_rq *cfs_rq; + u64 runtime, remaining = 1; + + rcu_read_lock(); + list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq, + throttled_list) { + struct rq *rq = rq_of(cfs_rq); + struct rq_flags rf; + + rq_lock_irqsave(rq, &rf); + if (!cfs_rq_throttled(cfs_rq)) + goto next; + + /* 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 > 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; + + /* we check whether we're throttled above */ + if (cfs_rq->runtime_remaining > 0) + unthrottle_cfs_rq(cfs_rq); + +next: + rq_unlock_irqrestore(rq, &rf); + + if (!remaining) + break; + } + rcu_read_unlock(); +} + +/* + * Responsible for refilling a task_group's bandwidth and unthrottling its + * cfs_rqs as appropriate. If there has been no activity within the last + * period the timer is deactivated until scheduling resumes; cfs_b->idle is + * used to track this state. + */ +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) +{ + int throttled; + + /* no need to continue the timer with no bandwidth constraint */ + if (cfs_b->quota == RUNTIME_INF) + goto out_deactivate; + + 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 + */ + if (cfs_b->idle && !throttled) + goto out_deactivate; + + if (!throttled) { + /* mark as potentially idle for the upcoming period */ + cfs_b->idle = 1; + return 0; + } + + /* account preceding periods in which throttling occurred */ + cfs_b->nr_throttled += overrun; + + /* + * This check is repeated as we release cfs_b->lock while we unthrottle. + */ + while (throttled && cfs_b->runtime > 0) { + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + /* we can't nest cfs_b->lock while distributing bandwidth */ + distribute_cfs_runtime(cfs_b); + raw_spin_lock_irqsave(&cfs_b->lock, flags); + + throttled = !list_empty(&cfs_b->throttled_cfs_rq); + } + + /* + * While we are ensured activity in the period following an + * unthrottle, this also covers the case in which the new bandwidth is + * insufficient to cover the existing bandwidth deficit. (Forcing the + * timer to remain active while there are any throttled entities.) + */ + cfs_b->idle = 0; + + return 0; + +out_deactivate: + return 1; +} + +/* a cfs_rq won't donate quota below this amount */ +static const u64 min_cfs_rq_runtime = 1 * NSEC_PER_MSEC; +/* minimum remaining period time to redistribute slack quota */ +static const u64 min_bandwidth_expiration = 2 * NSEC_PER_MSEC; +/* how long we wait to gather additional slack before distributing */ +static const u64 cfs_bandwidth_slack_period = 5 * NSEC_PER_MSEC; + +/* + * Are we near the end of the current quota period? + * + * Requires cfs_b->lock for hrtimer_expires_remaining to be safe against the + * hrtimer base being cleared by hrtimer_start. In the case of + * migrate_hrtimers, base is never cleared, so we are fine. + */ +static int runtime_refresh_within(struct cfs_bandwidth *cfs_b, u64 min_expire) +{ + struct hrtimer *refresh_timer = &cfs_b->period_timer; + s64 remaining; + + /* if the call-back is running a quota refresh is already occurring */ + if (hrtimer_callback_running(refresh_timer)) + return 1; + + /* is a quota refresh about to occur? */ + remaining = ktime_to_ns(hrtimer_expires_remaining(refresh_timer)); + if (remaining < (s64)min_expire) + return 1; + + return 0; +} + +static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b) +{ + u64 min_left = cfs_bandwidth_slack_period + min_bandwidth_expiration; + + /* if there's a quota refresh soon don't bother with slack */ + if (runtime_refresh_within(cfs_b, min_left)) + return; + + /* don't push forwards an existing deferred unthrottle */ + if (cfs_b->slack_started) + return; + cfs_b->slack_started = true; + + hrtimer_start(&cfs_b->slack_timer, + ns_to_ktime(cfs_bandwidth_slack_period), + HRTIMER_MODE_REL); +} + +/* we know any runtime found here is valid as update_curr() precedes return */ +static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + s64 slack_runtime = cfs_rq->runtime_remaining - min_cfs_rq_runtime; + + if (slack_runtime <= 0) + return; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota != RUNTIME_INF) { + cfs_b->runtime += slack_runtime; + + /* we are under rq->lock, defer unthrottling using a timer */ + if (cfs_b->runtime > sched_cfs_bandwidth_slice() && + !list_empty(&cfs_b->throttled_cfs_rq)) + start_cfs_slack_bandwidth(cfs_b); + } + raw_spin_unlock(&cfs_b->lock); + + /* even if it's not valid for return we don't want to try again */ + cfs_rq->runtime_remaining -= slack_runtime; +} + +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return; + + if (!cfs_rq->runtime_enabled || cfs_rq->nr_running) + return; + + __return_cfs_rq_runtime(cfs_rq); +} + +/* + * This is done with a timer (instead of inline with bandwidth return) since + * it's necessary to juggle rq->locks to unthrottle their respective cfs_rqs. + */ +static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) +{ + u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); + unsigned long flags; + + /* confirm we're still not at a refresh boundary */ + raw_spin_lock_irqsave(&cfs_b->lock, flags); + cfs_b->slack_started = false; + + if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + return; + } + + if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) + runtime = cfs_b->runtime; + + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + + if (!runtime) + return; + + 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 trigger until it's on-rq. + */ +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return; + + /* an active group must be handled by the update_curr()->put() path */ + if (!cfs_rq->runtime_enabled || cfs_rq->curr) + return; + + /* ensure the group is not already throttled */ + if (cfs_rq_throttled(cfs_rq)) + return; + + /* update runtime allocation */ + account_cfs_rq_runtime(cfs_rq, 0); + if (cfs_rq->runtime_remaining <= 0) + throttle_cfs_rq(cfs_rq); +} + +static void sync_throttle(struct task_group *tg, int cpu) +{ + struct cfs_rq *pcfs_rq, *cfs_rq; + + if (!cfs_bandwidth_used()) + return; + + if (!tg->parent) + return; + + cfs_rq = tg->cfs_rq[cpu]; + pcfs_rq = tg->parent->cfs_rq[cpu]; + + cfs_rq->throttle_count = pcfs_rq->throttle_count; + cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu)); +} + +/* conditionally throttle active cfs_rq's from put_prev_entity() */ +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + if (!cfs_bandwidth_used()) + return false; + + if (likely(!cfs_rq->runtime_enabled || cfs_rq->runtime_remaining > 0)) + return false; + + /* + * it's possible for a throttled entity to be forced into a running + * state (e.g. set_curr_task), in this case we're finished. + */ + if (cfs_rq_throttled(cfs_rq)) + return true; + + return throttle_cfs_rq(cfs_rq); +} + +static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, slack_timer); + + do_sched_cfs_slack_timer(cfs_b); + + return HRTIMER_NORESTART; +} + +extern const u64 max_cfs_quota_period; + +static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) +{ + struct cfs_bandwidth *cfs_b = + container_of(timer, struct cfs_bandwidth, period_timer); + unsigned long flags; + int overrun; + int idle = 0; + int count = 0; + + raw_spin_lock_irqsave(&cfs_b->lock, flags); + for (;;) { + overrun = hrtimer_forward_now(timer, cfs_b->period); + if (!overrun) + break; + + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); + + if (++count > 3) { + u64 new, old = ktime_to_ns(cfs_b->period); + + /* + * Grow period by a factor of 2 to avoid losing precision. + * Precision loss in the quota/period ratio can cause __cfs_schedulable + * to fail. + */ + new = old * 2; + 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", + smp_processor_id(), + div_u64(new, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + } else { + pr_warn_ratelimited( + "cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n", + smp_processor_id(), + div_u64(old, NSEC_PER_USEC), + div_u64(cfs_b->quota, NSEC_PER_USEC)); + } + + /* reset count so we don't come right back in here */ + count = 0; + } + } + if (idle) + cfs_b->period_active = 0; + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; +} + +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + raw_spin_lock_init(&cfs_b->lock); + 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->slack_started = false; +} + +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + cfs_rq->runtime_enabled = 0; + INIT_LIST_HEAD(&cfs_rq->throttled_list); +} + +void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + lockdep_assert_held(&cfs_b->lock); + + if (cfs_b->period_active) + return; + + cfs_b->period_active = 1; + hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); + hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); +} + +static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) +{ + /* init_cfs_bandwidth() was not called */ + if (!cfs_b->throttled_cfs_rq.next) + return; + + hrtimer_cancel(&cfs_b->period_timer); + hrtimer_cancel(&cfs_b->slack_timer); +} + +/* + * Both these CPU hotplug callbacks race against unregister_fair_sched_group() + * + * The race is harmless, since modifying bandwidth settings of unhooked group + * bits doesn't do much. + */ + +/* cpu online callback */ +static void __maybe_unused update_runtime_enabled(struct rq *rq) +{ + struct task_group *tg; + + lockdep_assert_rq_held(rq); + + rcu_read_lock(); + list_for_each_entry_rcu(tg, &task_groups, list) { + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + raw_spin_lock(&cfs_b->lock); + cfs_rq->runtime_enabled = cfs_b->quota != RUNTIME_INF; + raw_spin_unlock(&cfs_b->lock); + } + rcu_read_unlock(); +} + +/* cpu offline callback */ +static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) +{ + struct task_group *tg; + + lockdep_assert_rq_held(rq); + + rcu_read_lock(); + list_for_each_entry_rcu(tg, &task_groups, list) { + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; + + if (!cfs_rq->runtime_enabled) + continue; + + /* + * clock_task is not advancing so we just need to make sure + * there's some valid quota amount + */ + cfs_rq->runtime_remaining = 1; + /* + * Offline rq is schedulable till CPU is completely disabled + * in take_cpu_down(), so we prevent new cfs throttling here. + */ + cfs_rq->runtime_enabled = 0; + + if (cfs_rq_throttled(cfs_rq)) + unthrottle_cfs_rq(cfs_rq); + } + rcu_read_unlock(); +} + +#else /* CONFIG_CFS_BANDWIDTH */ + +static inline bool cfs_bandwidth_used(void) +{ + return false; +} + +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} +static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } +static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} +static inline void sync_throttle(struct task_group *tg, int cpu) {} +static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} + +static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return 0; +} + +static inline int throttled_lb_pair(struct task_group *tg, + int src_cpu, int dest_cpu) +{ + return 0; +} + +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} +#endif + +static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) +{ + return NULL; +} +static inline void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b) {} +static inline void update_runtime_enabled(struct rq *rq) {} +static inline void unthrottle_offline_cfs_rqs(struct rq *rq) {} + +#endif /* CONFIG_CFS_BANDWIDTH */ + +/************************************************** + * CFS operations on tasks: + */ + +#ifdef CONFIG_SCHED_HRTICK +static void hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + SCHED_WARN_ON(task_rq(p) != rq); + + if (rq->cfs.h_nr_running > 1) { + u64 slice = sched_slice(cfs_rq, se); + u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime; + s64 delta = slice - ran; + + if (delta < 0) { + if (task_current(rq, p)) + resched_curr(rq); + return; + } + hrtick_start(rq, delta); + } +} + +/* + * called from enqueue/dequeue and updates the hrtick when the + * current task is from our class and nr_running is low enough + * to matter. + */ +static void hrtick_update(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + + if (!hrtick_enabled_fair(rq) || curr->sched_class != &fair_sched_class) + return; + + if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency) + hrtick_start_fair(rq, curr); +} +#else /* !CONFIG_SCHED_HRTICK */ +static inline void +hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ +} + +static inline void hrtick_update(struct rq *rq) +{ +} +#endif + +#ifdef CONFIG_SMP +static inline bool cpu_overutilized(int cpu) +{ + unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN); + unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX); + + /* Return true only if the utilization doesn't fit CPU's capacity */ + return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu); +} + +static inline void update_overutilized_status(struct rq *rq) +{ + if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) { + WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); + trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED); + } +} +#else +static inline void update_overutilized_status(struct rq *rq) { } +#endif + +/* Runqueue only has SCHED_IDLE tasks enqueued */ +static int sched_idle_rq(struct rq *rq) +{ + return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && + 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) +{ + return sched_idle_rq(cpu_rq(cpu)); +} +#endif + +/* + * The enqueue_task method is called before nr_running is + * increased. Here we update the fair scheduling stats and + * then put the task into the rbtree: + */ +static void +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 + * the cfs_rq utilization to select a frequency. + * Let's add the task's estimated utilization to the cfs_rq's + * estimated utilization, before we update schedutil. + */ + util_est_enqueue(&rq->cfs, p); + + /* + * If in_iowait is set, the code below may not trigger any cpufreq + * utilization updates, so do it here explicitly with the IOWAIT flag + * passed. + */ + if (p->in_iowait) + cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT); + + for_each_sched_entity(se) { + if (se->on_rq) + break; + cfs_rq = cfs_rq_of(se); + enqueue_entity(cfs_rq, se, flags); + + 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); + + 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)) + goto enqueue_throttle; + } + + /* At this point se is NULL and we are at root level*/ + 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 (!task_new) + update_overutilized_status(rq); + +enqueue_throttle: + assert_list_leaf_cfs_rq(rq); + + hrtick_update(rq); +} + +static void set_next_buddy(struct sched_entity *se); + +/* + * The dequeue_task method is called before nr_running is + * decreased. We remove the task from the rbtree and + * update the fair scheduling stats: + */ +static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se; + int task_sleep = flags & DEQUEUE_SLEEP; + 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); + + 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: */ + se = parent_entity(se); + /* + * Bias pick_next to pick a task from this cfs_rq, as + * p is sleeping when it is within its sched_slice. + */ + if (task_sleep && se && !throttled_hierarchy(cfs_rq)) + set_next_buddy(se); + break; + } + flags |= DEQUEUE_SLEEP; + } + + 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)) + goto dequeue_throttle; + + } + + /* 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; + +dequeue_throttle: + util_est_update(&rq->cfs, p, task_sleep); + hrtick_update(rq); +} + +#ifdef CONFIG_SMP + +/* Working cpumask for: load_balance, load_balance_newidle. */ +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 + +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; + +#endif /* CONFIG_NO_HZ_COMMON */ + +static unsigned long cpu_load(struct rq *rq) +{ + return cfs_rq_load_avg(&rq->cfs); +} + +/* + * cpu_load_without - compute CPU load without any contributions from *p + * @cpu: the CPU which load is requested + * @p: the task which load should be discounted + * + * The load of a CPU is defined by the load of tasks currently enqueued on that + * CPU as well as tasks which are currently sleeping after an execution on that + * CPU. + * + * This method returns the load of the specified CPU by discounting the load of + * the specified task, whenever the task is currently contributing to the CPU + * load. + */ +static unsigned long cpu_load_without(struct rq *rq, struct task_struct *p) +{ + struct cfs_rq *cfs_rq; + unsigned int load; + + /* Task has no contribution or is new */ + if (cpu_of(rq) != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) + return cpu_load(rq); + + cfs_rq = &rq->cfs; + load = READ_ONCE(cfs_rq->avg.load_avg); + + /* Discount task's util from CPU's util */ + lsub_positive(&load, task_h_load(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; +} + +static void record_wakee(struct task_struct *p) +{ + /* + * Only decay a single time; tasks that have less then 1 wakeup per + * jiffy will not have built up many flips. + */ + if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { + current->wakee_flips >>= 1; + current->wakee_flip_decay_ts = jiffies; + } + + if (current->last_wakee != p) { + current->last_wakee = p; + current->wakee_flips++; + } +} + +/* + * Detect M:N waker/wakee relationships via a switching-frequency heuristic. + * + * A waker of many should wake a different task than the one last awakened + * at a frequency roughly N times higher than one of its wakees. + * + * In order to determine whether we should let the load spread vs consolidating + * to shared cache, we look for a minimum 'flip' frequency of llc_size in one + * partner, and a factor of lls_size higher frequency in the other. + * + * With both conditions met, we can be relatively sure that the relationship is + * non-monogamous, with partner count exceeding socket size. + * + * Waker/wakee being client/server, worker/dispatcher, interrupt source or + * whatever is irrelevant, spread criteria is apparent partner count exceeds + * socket size. + */ +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); + + if (master < slave) + swap(master, slave); + if (slave < factor || master < slave * factor) + return 0; + return 1; +} + +/* + * The purpose of wake_affine() is to quickly determine on which CPU we can run + * soonest. For the purpose of speed we only consider the waking and previous + * CPU. + * + * wake_affine_idle() - only considers 'now', it check if the waking CPU is + * cache-affine and is (or will be) idle. + * + * wake_affine_weight() - considers the weight to reflect the average + * scheduling latency of the CPUs. This seems to work + * for the overloaded case. + */ +static int +wake_affine_idle(int this_cpu, int prev_cpu, int sync) +{ + /* + * If this_cpu is idle, it implies the wakeup is from interrupt + * context. Only allow the move if cache is shared. Otherwise an + * interrupt intensive workload could force all tasks onto one + * node depending on the IO topology or IRQ affinity settings. + * + * If the prev_cpu is idle and cache affine then avoid a migration. + * There is no guarantee that the cache hot data from an interrupt + * is more important than cache hot data on the prev_cpu and from + * a cpufreq perspective, it's better to have higher utilisation + * on one CPU. + */ + if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu)) + return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu; + + 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; +} + +static int +wake_affine_weight(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) +{ + s64 this_eff_load, prev_eff_load; + unsigned long task_load; + + this_eff_load = cpu_load(cpu_rq(this_cpu)); + + if (sync) { + unsigned long current_load = task_h_load(current); + + if (current_load > this_eff_load) + return this_cpu; + + this_eff_load -= current_load; + } + + task_load = task_h_load(p); + + this_eff_load += task_load; + if (sched_feat(WA_BIAS)) + this_eff_load *= 100; + this_eff_load *= capacity_of(prev_cpu); + + prev_eff_load = cpu_load(cpu_rq(prev_cpu)); + prev_eff_load -= task_load; + if (sched_feat(WA_BIAS)) + prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; + prev_eff_load *= capacity_of(this_cpu); + + /* + * If sync, adjust the weight of prev_eff_load such that if + * prev_eff == this_eff that select_idle_sibling() will consider + * stacking the wakee on top of the waker if no other CPU is + * idle. + */ + if (sync) + prev_eff_load += 1; + + return this_eff_load < prev_eff_load ? this_cpu : nr_cpumask_bits; +} + +static int wake_affine(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int prev_cpu, int sync) +{ + int target = nr_cpumask_bits; + + if (sched_feat(WA_IDLE)) + target = wake_affine_idle(this_cpu, prev_cpu, sync); + + if (sched_feat(WA_WEIGHT) && target == nr_cpumask_bits) + target = wake_affine_weight(sd, p, this_cpu, prev_cpu, sync); + + schedstat_inc(p->stats.nr_wakeups_affine_attempts); + if (target != this_cpu) + return prev_cpu; + + schedstat_inc(sd->ttwu_move_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); + +/* + * find_idlest_group_cpu - find the idlest CPU among the CPUs in the group. + */ +static int +find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) +{ + unsigned long load, min_load = ULONG_MAX; + unsigned int min_exit_latency = UINT_MAX; + u64 latest_idle_timestamp = 0; + int least_loaded_cpu = this_cpu; + int shallowest_idle_cpu = -1; + int i; + + /* Check if we have any choice: */ + if (group->group_weight == 1) + return cpumask_first(sched_group_span(group)); + + /* 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 cpuidle_state *idle = idle_get_state(rq); + if (idle && idle->exit_latency < min_exit_latency) { + /* + * We give priority to a CPU whose idle state + * has the smallest exit latency irrespective + * of any idle timestamp. + */ + min_exit_latency = idle->exit_latency; + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } else if ((!idle || idle->exit_latency == min_exit_latency) && + rq->idle_stamp > latest_idle_timestamp) { + /* + * If equal or no active idle state, then + * the most recently idled CPU might have + * a warmer cache. + */ + latest_idle_timestamp = rq->idle_stamp; + shallowest_idle_cpu = i; + } + } else if (shallowest_idle_cpu == -1) { + load = cpu_load(cpu_rq(i)); + if (load < min_load) { + min_load = load; + least_loaded_cpu = i; + } + } + } + + return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; +} + +static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p, + int cpu, int prev_cpu, int sd_flag) +{ + int new_cpu = cpu; + + if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr)) + return prev_cpu; + + /* + * We need task's util for cpu_util_without, sync it up to + * prev_cpu's last_update_time. + */ + if (!(sd_flag & SD_BALANCE_FORK)) + sync_entity_load_avg(&p->se); + + while (sd) { + struct sched_group *group; + struct sched_domain *tmp; + int weight; + + if (!(sd->flags & sd_flag)) { + sd = sd->child; + continue; + } + + group = find_idlest_group(sd, p, cpu); + if (!group) { + sd = sd->child; + continue; + } + + new_cpu = find_idlest_group_cpu(group, p, cpu); + if (new_cpu == cpu) { + /* Now try balancing at a lower domain level of 'cpu': */ + sd = sd->child; + continue; + } + + /* Now try balancing at a lower domain level of 'new_cpu': */ + cpu = new_cpu; + weight = sd->span_weight; + sd = NULL; + for_each_domain(cpu, tmp) { + if (weight <= tmp->span_weight) + break; + if (tmp->flags & sd_flag) + sd = tmp; + } + } + + 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); + +static inline void set_idle_cores(int cpu, int val) +{ + struct sched_domain_shared *sds; + + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) + WRITE_ONCE(sds->has_idle_cores, val); +} + +static inline bool test_idle_cores(int cpu) +{ + struct sched_domain_shared *sds; + + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) + return READ_ONCE(sds->has_idle_cores); + + return false; +} + +/* + * Scans the local SMT mask to see if the entire core is idle, and records this + * information in sd_llc_shared->has_idle_cores. + * + * Since SMT siblings share all cache levels, inspecting this limited remote + * state should be fairly cheap. + */ +void __update_idle_core(struct rq *rq) +{ + int core = cpu_of(rq); + int cpu; + + rcu_read_lock(); + if (test_idle_cores(core)) + goto unlock; + + for_each_cpu(cpu, cpu_smt_mask(core)) { + if (cpu == core) + continue; + + if (!available_idle_cpu(cpu)) + goto unlock; + } + + set_idle_cores(core, 1); +unlock: + rcu_read_unlock(); +} + +/* + * Scan the entire LLC domain for idle cores; this dynamically switches off if + * 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, int core, struct cpumask *cpus, int *idle_cpu) +{ + bool idle = true; + int cpu; + + 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_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr)) + *idle_cpu = cpu; + } + + if (idle) + return core; + + cpumask_andnot(cpus, cpus, cpu_smt_mask(core)); + return -1; +} + +/* + * Scan the local SMT mask for idle CPUs. + */ +static int select_idle_smt(struct task_struct *p, int target) +{ + int cpu; + + 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; + } + + return -1; +} + +#else /* CONFIG_SCHED_SMT */ + +static inline void set_idle_cores(int cpu, int val) +{ +} + +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) +{ + return -1; +} + +#endif /* CONFIG_SCHED_SMT */ + +/* + * Scan the LLC domain for idle CPUs; this is dynamically regulated by + * 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, bool has_idle_core, int target) +{ + 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(); + struct sched_domain *this_sd = NULL; + u64 time = 0; + + cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + + if (sched_feat(SIS_PROP) && !has_idle_core) { + u64 avg_cost, avg_idle, span_avg; + unsigned long now = jiffies; + + 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; + + 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; + } + } + + 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, util_min, util_max, best_cap = 0; + int fits, best_fits = 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 = task_util_est(p); + util_min = uclamp_eff_value(p, UCLAMP_MIN); + util_max = uclamp_eff_value(p, UCLAMP_MAX); + + for_each_cpu_wrap(cpu, cpus, target) { + unsigned long cpu_cap = capacity_of(cpu); + + if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu)) + continue; + + fits = util_fits_cpu(task_util, util_min, util_max, cpu); + + /* This CPU fits with all requirements */ + if (fits > 0) + return cpu; + /* + * Only the min performance hint (i.e. uclamp_min) doesn't fit. + * Look for the CPU with best capacity. + */ + else if (fits < 0) + cpu_cap = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu)); + + /* + * First, select CPU which fits better (-1 being better than 0). + * Then, select the one with best capacity at same level. + */ + if ((fits < best_fits) || + ((fits == best_fits) && (cpu_cap > best_cap))) { + best_cap = cpu_cap; + best_cpu = cpu; + best_fits = fits; + } + } + + return best_cpu; +} + +static inline bool asym_fits_cpu(unsigned long util, + unsigned long util_min, + unsigned long util_max, + int cpu) +{ + if (sched_asym_cpucap_active()) + /* + * Return true only if the cpu fully fits the task requirements + * which include the utilization and the performance hints. + */ + return (util_fits_cpu(util, util_min, util_max, cpu) > 0); + + return true; +} + +/* + * Try and locate an idle core/thread in the LLC cache domain. + */ +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, util_min, util_max; + int i, recent_used_cpu; + + /* + * 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 = task_util_est(p); + util_min = uclamp_eff_value(p, UCLAMP_MIN); + util_max = uclamp_eff_value(p, UCLAMP_MAX); + } + + /* + * per-cpu select_rq_mask usage + */ + lockdep_assert_irqs_disabled(); + + if ((available_idle_cpu(target) || sched_idle_cpu(target)) && + asym_fits_cpu(task_util, util_min, util_max, 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)) && + asym_fits_cpu(task_util, util_min, util_max, prev)) + return prev; + + /* + * Allow a per-cpu kthread to stack with the wakee if the + * kworker thread and the tasks previous CPUs are the same. + * The assumption is that the wakee queued work for the + * per-cpu kthread that is now complete and the wakeup is + * essentially a sync wakeup. An obvious example of this + * pattern is IO completions. + */ + if (is_per_cpu_kthread(current) && + in_task() && + prev == smp_processor_id() && + this_rq()->nr_running <= 1 && + asym_fits_cpu(task_util, util_min, util_max, 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(recent_used_cpu, p->cpus_ptr) && + asym_fits_cpu(task_util, util_min, util_max, 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)); + /* + * 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. + */ + 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; + + if (sched_smt_active()) { + has_idle_core = test_idle_cores(target); + + 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_cpu(p, sd, has_idle_core, target); + if ((unsigned)i < nr_cpumask_bits) + return i; + + return target; +} + +/* + * 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 = &cpu_rq(cpu)->cfs; + unsigned long 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; + + util_est = READ_ONCE(cfs_rq->avg.util_est.enqueued); + + /* + * 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)); +} + +/* + * cpu_util_without: compute cpu utilization without any contributions from *p + * @cpu: the CPU which utilization is requested + * @p: the task which utilization should be discounted + * + * The utilization of a CPU is defined by the utilization of tasks currently + * enqueued on that CPU as well as tasks which are currently sleeping after an + * execution on that CPU. + * + * This method returns the utilization of the specified CPU by discounting the + * utilization of the specified task, whenever the task is currently + * contributing to the CPU utilization. + */ +static unsigned long cpu_util_without(int cpu, struct task_struct *p) +{ + /* Task has no contribution or is new */ + if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) + return cpu_util_cfs(cpu); + + return cpu_util_next(cpu, p, -1); +} + +/* + * 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). + */ +struct energy_env { + unsigned long task_busy_time; + unsigned long pd_busy_time; + unsigned long cpu_cap; + unsigned long pd_cap; +}; + +/* + * 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)); + + if (unlikely(irq >= max_cap)) + busy_time = max_cap; + else + busy_time = scale_irq_capacity(task_util_est(p), irq, max_cap); + + eenv->task_busy_time = busy_time; +} + +/* + * 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 inline void eenv_pd_busy_time(struct energy_env *eenv, + struct cpumask *pd_cpus, + struct task_struct *p) +{ + unsigned long busy_time = 0; + int cpu; + + for_each_cpu(cpu, pd_cpus) { + unsigned long util = cpu_util_next(cpu, p, -1); + + busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL); + } + + eenv->pd_busy_time = min(eenv->pd_cap, busy_time); +} + +/* + * 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 inline unsigned long +eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus, + struct task_struct *p, int dst_cpu) +{ + unsigned long max_util = 0; + int cpu; + + 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 + * must be considered since it affects the selection + * of the performance domain frequency. + * 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, FREQUENCY_UTIL, tsk); + max_util = max(max_util, cpu_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); +} + +/* + * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the + * waking task. find_energy_efficient_cpu() looks for the CPU with maximum + * spare capacity in each performance domain and uses it as a potential + * candidate to execute the task. Then, it uses the Energy Model to figure + * out which of the CPU candidates is the most energy-efficient. + * + * The rationale for this heuristic is as follows. In a performance domain, + * all the most energy efficient CPU candidates (according to the Energy + * Model) are those for which we'll request a low frequency. When there are + * several CPUs for which the frequency request will be the same, we don't + * have enough data to break the tie between them, because the Energy Model + * only includes active power costs. With this model, if we assume that + * frequency requests follow utilization (e.g. using schedutil), the CPU with + * the maximum spare capacity in a performance domain is guaranteed to be among + * the best candidates of the performance domain. + * + * In practice, it could be preferable from an energy standpoint to pack + * small tasks on a CPU in order to let other CPUs go in deeper idle states, + * but that could also hurt our chances to go cluster idle, and we have no + * ways to tell with the current Energy Model if this is actually a good + * idea or not. So, find_energy_efficient_cpu() basically favors + * cluster-packing, and spreading inside a cluster. That should at least be + * a good thing for latency, and this is consistent with the idea that most + * of the energy savings of EAS come from the asymmetry of the system, and + * not so much from breaking the tie between identical CPUs. That's also the + * reason why EAS is enabled in the topology code only for systems where + * SD_ASYM_CPUCAPACITY is set. + * + * NOTE: Forkees are not accepted in the energy-aware wake-up path because + * they don't have any useful utilization data yet and it's not possible to + * forecast their impact on energy consumption. Consequently, they will be + * placed by find_idlest_cpu() on the least loaded CPU, which might turn out + * to be energy-inefficient in some use-cases. The alternative would be to + * bias new tasks towards specific types of CPUs first, or to try to infer + * their util_avg from the parent task, but those heuristics could hurt + * other use-cases too. So, until someone finds a better way to solve this, + * let's keep things simple by re-using the existing slow path. + */ +static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) +{ + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); + unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; + unsigned long p_util_min = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MIN) : 0; + unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024; + struct root_domain *rd = this_rq()->rd; + int cpu, best_energy_cpu, target = -1; + int prev_fits = -1, best_fits = -1; + unsigned long best_thermal_cap = 0; + unsigned long prev_thermal_cap = 0; + 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 unlock; + + /* + * Energy-aware wake-up happens on the lowest sched_domain starting + * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu. + */ + sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity)); + while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) + sd = sd->parent; + if (!sd) + goto unlock; + + target = prev_cpu; + + sync_entity_load_avg(&p->se); + if (!task_util_est(p) && p_util_min == 0) + goto unlock; + + eenv_task_busy_time(&eenv, p, prev_cpu); + + for (; pd; pd = pd->next) { + unsigned long util_min = p_util_min, util_max = p_util_max; + unsigned long cpu_cap, cpu_thermal_cap, util; + long prev_spare_cap = -1, max_spare_cap = -1; + unsigned long rq_util_min, rq_util_max; + unsigned long cur_delta, base_energy; + int max_spare_cap_cpu = -1; + int fits, max_fits = -1; + + 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) { + struct rq *rq = cpu_rq(cpu); + + eenv.pd_cap += cpu_thermal_cap; + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; + + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + continue; + + util = cpu_util_next(cpu, p, cpu); + cpu_cap = capacity_of(cpu); + + /* + * 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 sched_cpu_util(). + */ + if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) { + /* + * Open code uclamp_rq_util_with() except for + * the clamp() part. Ie: apply max aggregation + * only. util_fits_cpu() logic requires to + * operate on non clamped util but must use the + * max-aggregated uclamp_{min, max}. + */ + rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN); + rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX); + + util_min = max(rq_util_min, p_util_min); + util_max = max(rq_util_max, p_util_max); + } + + fits = util_fits_cpu(util, util_min, util_max, cpu); + if (!fits) + continue; + + lsub_positive(&cpu_cap, util); + + if (cpu == prev_cpu) { + /* Always use prev_cpu as a candidate. */ + prev_spare_cap = cpu_cap; + prev_fits = fits; + } else if ((fits > max_fits) || + ((fits == max_fits) && ((long)cpu_cap > max_spare_cap))) { + /* + * Find the CPU with the maximum spare capacity + * among the remaining CPUs in the performance + * domain. + */ + max_spare_cap = cpu_cap; + max_spare_cap_cpu = cpu; + max_fits = fits; + } + } + + if (max_spare_cap_cpu < 0 && prev_spare_cap < 0) + 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 (prev_spare_cap > -1) { + 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; + prev_thermal_cap = cpu_thermal_cap; + best_delta = min(best_delta, prev_delta); + } + + /* Evaluate the energy impact of using max_spare_cap_cpu. */ + if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) { + /* Current best energy cpu fits better */ + if (max_fits < best_fits) + continue; + + /* + * Both don't fit performance hint (i.e. uclamp_min) + * but best energy cpu has better capacity. + */ + if ((max_fits < 0) && + (cpu_thermal_cap <= best_thermal_cap)) + continue; + + 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; + + /* + * Both fit for the task but best energy cpu has lower + * energy impact. + */ + if ((max_fits > 0) && (best_fits > 0) && + (cur_delta >= best_delta)) + continue; + + best_delta = cur_delta; + best_energy_cpu = max_spare_cap_cpu; + best_fits = max_fits; + best_thermal_cap = cpu_thermal_cap; + } + } + rcu_read_unlock(); + + if ((best_fits > prev_fits) || + ((best_fits > 0) && (best_delta < prev_delta)) || + ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap))) + target = best_energy_cpu; + + return target; + +unlock: + rcu_read_unlock(); + + return target; +} + +/* + * select_task_rq_fair: Select target runqueue for the waking task in domains + * 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. + */ +static int +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; + /* 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); + + if (sched_energy_enabled()) { + new_cpu = find_energy_efficient_cpu(p, prev_cpu); + if (new_cpu >= 0) + return new_cpu; + new_cpu = prev_cpu; + } + + want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, p->cpus_ptr); + } + + rcu_read_lock(); + for_each_domain(cpu, tmp) { + /* + * If both 'cpu' and 'prev_cpu' are part of this domain, + * cpu is a valid SD_WAKE_AFFINE target. + */ + if (want_affine && (tmp->flags & SD_WAKE_AFFINE) && + cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) { + if (cpu != prev_cpu) + new_cpu = wake_affine(tmp, p, cpu, prev_cpu, sync); + + sd = NULL; /* Prefer wake_affine over balance flags */ + 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) + break; + } + + if (unlikely(sd)) { + /* Slow path */ + new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag); + } else if (wake_flags & WF_TTWU) { /* XXX always ? */ + /* Fast path */ + new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); + } + rcu_read_unlock(); + + return new_cpu; +} + +/* + * 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 + * previous CPU. The caller guarantees p->pi_lock or task_rq(p)->lock is held. + */ +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 (READ_ONCE(p->__state) == TASK_WAKING) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + se->vruntime -= u64_u32_load(cfs_rq->min_vruntime); + } + + if (!task_on_rq_migrating(p)) { + remove_entity_load_avg(se); + + /* + * 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. + */ + migrate_se_pelt_lag(se); + } + + /* Tell new CPU we are migrated */ + se->avg.last_update_time = 0; + + update_scan_period(p, new_cpu); +} + +static void task_dead_fair(struct task_struct *p) +{ + remove_entity_load_avg(&p->se); +} + +static int +balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + if (rq->nr_running) + return 1; + + return newidle_balance(rq, rf) != 0; +} +#endif /* CONFIG_SMP */ + +static unsigned long wakeup_gran(struct sched_entity *se) +{ + unsigned long gran = sysctl_sched_wakeup_granularity; + + /* + * Since its curr running now, convert the gran from real-time + * to virtual-time in his units. + * + * By using 'se' instead of 'curr' we penalize light tasks, so + * they get preempted easier. That is, if 'se' < 'curr' then + * the resulting gran will be larger, therefore penalizing the + * lighter, if otoh 'se' > 'curr' then the resulting gran will + * be smaller, again penalizing the lighter task. + * + * This is especially important for buddies when the leftmost + * task is higher priority than the buddy. + */ + return calc_delta_fair(gran, se); +} + +/* + * Should 'se' preempt 'curr'. + * + * |s1 + * |s2 + * |s3 + * g + * |<--->|c + * + * w(c, s1) = -1 + * w(c, s2) = 0 + * w(c, s3) = 1 + * + */ +static int +wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) +{ + s64 gran, vdiff = curr->vruntime - se->vruntime; + + if (vdiff <= 0) + return -1; + + gran = wakeup_gran(se); + if (vdiff > gran) + return 1; + + return 0; +} + +static void set_last_buddy(struct sched_entity *se) +{ + 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) +{ + 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; + } +} + +static void set_skip_buddy(struct sched_entity *se) +{ + for_each_sched_entity(se) + cfs_rq_of(se)->skip = se; +} + +/* + * Preempt the current task with a newly woken task if needed: + */ +static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) +{ + struct task_struct *curr = rq->curr; + struct sched_entity *se = &curr->se, *pse = &p->se; + 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_preempt_curr() after an enqueue (which may have + * lead to a throttle). This both saves work and prevents false + * next-buddy nomination below. + */ + if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) + return; + + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) { + set_next_buddy(pse); + next_buddy_marked = 1; + } + + /* + * We can come here with TIF_NEED_RESCHED already set from new task + * wake up path. + * + * Note: this also catches the edge-case of curr being in a throttled + * group (e.g. via set_curr_task), since update_curr() (in the + * enqueue of curr) will have resulted in resched being set. This + * prevents us from potentially nominating it as a false LAST_BUDDY + * below. + */ + if (test_tsk_need_resched(curr)) + return; + + /* Idle tasks are by definition preempted by non-idle tasks. */ + if (unlikely(task_has_idle_policy(curr)) && + likely(!task_has_idle_policy(p))) + goto preempt; + + /* + * Batch and idle tasks do not preempt non-idle tasks (their preemption + * is driven by the tick): + */ + if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION)) + 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)); + if (wakeup_preempt_entity(se, pse) == 1) { + /* + * Bias pick_next to pick the sched entity that is + * triggering this preemption. + */ + if (!next_buddy_marked) + set_next_buddy(pse); + goto preempt; + } + + return; + +preempt: + resched_curr(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved + * with schedule on the ->pre_schedule() or idle_balance() + * point, either of which can * drop the rq lock. + * + * Also, during early boot the idle thread is in the fair class, + * for obvious reasons its a bad idea to schedule back to it. + */ + if (unlikely(!se->on_rq || curr == rq->idle)) + return; + + if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se)) + 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) +{ + struct cfs_rq *cfs_rq = &rq->cfs; + struct sched_entity *se; + struct task_struct *p; + int new_tasks; + +again: + if (!sched_fair_runnable(rq)) + goto idle; + +#ifdef CONFIG_FAIR_GROUP_SCHED + if (!prev || prev->sched_class != &fair_sched_class) + goto simple; + + /* + * Because of the set_next_buddy() in dequeue_task_fair() it is rather + * likely that a next task is from the same cgroup as the current. + * + * Therefore attempt to avoid putting and setting the entire cgroup + * hierarchy, only change the part that actually changes. + */ + + do { + struct sched_entity *curr = cfs_rq->curr; + + /* + * Since we got here without doing put_prev_entity() we also + * have to consider cfs_rq->curr. If it is still a runnable + * entity, update_curr() will update its vruntime, otherwise + * forget we've ever seen it. + */ + if (curr) { + if (curr->on_rq) + update_curr(cfs_rq); + else + curr = NULL; + + /* + * This call to check_cfs_rq_runtime() will do the + * throttle and dequeue its entity in the parent(s). + * Therefore the nr_running test will indeed + * be correct. + */ + if (unlikely(check_cfs_rq_runtime(cfs_rq))) { + cfs_rq = &rq->cfs; + + if (!cfs_rq->nr_running) + goto idle; + + goto simple; + } + } + + se = pick_next_entity(cfs_rq, curr); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + + /* + * Since we haven't yet done put_prev_entity and if the selected task + * is a different task than we started out with, try and touch the + * least amount of cfs_rqs. + */ + if (prev != p) { + struct sched_entity *pse = &prev->se; + + while (!(cfs_rq = is_same_group(se, pse))) { + int se_depth = se->depth; + int pse_depth = pse->depth; + + if (se_depth <= pse_depth) { + put_prev_entity(cfs_rq_of(pse), pse); + pse = parent_entity(pse); + } + if (se_depth >= pse_depth) { + set_next_entity(cfs_rq_of(se), se); + se = parent_entity(se); + } + } + + put_prev_entity(cfs_rq, pse); + set_next_entity(cfs_rq, se); + } + + goto done; +simple: +#endif + if (prev) + put_prev_task(rq, prev); + + do { + se = pick_next_entity(cfs_rq, NULL); + set_next_entity(cfs_rq, se); + cfs_rq = group_cfs_rq(se); + } while (cfs_rq); + + p = task_of(se); + +done: __maybe_unused; +#ifdef CONFIG_SMP + /* + * Move the next running task to the front of + * the list, so our cfs_tasks list becomes MRU + * one. + */ + list_move(&p->se.group_node, &rq->cfs_tasks); +#endif + + if (hrtick_enabled_fair(rq)) + hrtick_start_fair(rq, p); + + update_misfit_status(p, rq); + + return p; + +idle: + if (!rf) + return NULL; + + new_tasks = newidle_balance(rq, rf); + + /* + * Because newidle_balance() releases (and re-acquires) rq->lock, it is + * possible for any higher priority task to appear. In that case we + * must re-start the pick_next_entity() loop. + */ + if (new_tasks < 0) + return RETRY_TASK; + + if (new_tasks > 0) + goto again; + + /* + * rq is about to be idle, check if we need to update the + * lost_idle_time of clock_pelt + */ + update_idle_rq_clock_pelt(rq); + + return NULL; +} + +static struct task_struct *__pick_next_task_fair(struct rq *rq) +{ + return pick_next_task_fair(rq, NULL, NULL); +} + +/* + * Account for a descheduled task: + */ +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) +{ + struct sched_entity *se = &prev->se; + struct cfs_rq *cfs_rq; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + put_prev_entity(cfs_rq, se); + } +} + +/* + * sched_yield() is very simple + * + * The magic of dealing with the ->skip buddy is in pick_next_entity. + */ +static void yield_task_fair(struct rq *rq) +{ + struct task_struct *curr = rq->curr; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + struct sched_entity *se = &curr->se; + + /* + * Are we the only task in the tree? + */ + if (unlikely(rq->nr_running == 1)) + return; + + clear_buddies(cfs_rq, se); + + if (curr->policy != SCHED_BATCH) { + update_rq_clock(rq); + /* + * Update run-time statistics of the 'current'. + */ + update_curr(cfs_rq); + /* + * Tell update_rq_clock() that we've just updated, + * so we don't do microscopic update in schedule() + * and double the fastpath cost. + */ + rq_clock_skip_update(rq); + } + + set_skip_buddy(se); +} + +static bool yield_to_task_fair(struct rq *rq, struct task_struct *p) +{ + struct sched_entity *se = &p->se; + + /* throttled hierarchies are not runnable */ + if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se))) + return false; + + /* Tell the scheduler that we'd really like pse to run next. */ + set_next_buddy(se); + + yield_task_fair(rq); + + return true; +} + +#ifdef CONFIG_SMP +/************************************************** + * Fair scheduling class load-balancing methods. + * + * BASICS + * + * The purpose of load-balancing is to achieve the same basic fairness the + * per-CPU scheduler provides, namely provide a proportional amount of compute + * time to each task. This is expressed in the following equation: + * + * W_i,n/P_i == W_j,n/P_j for all i,j (1) + * + * Where W_i,n is the n-th weight average for CPU i. The instantaneous weight + * W_i,0 is defined as: + * + * W_i,0 = \Sum_j w_i,j (2) + * + * Where w_i,j is the weight of the j-th runnable task on CPU i. This weight + * is derived from the nice value as per sched_prio_to_weight[]. + * + * The weight average is an exponential decay average of the instantaneous + * weight: + * + * W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3) + * + * C_i is the compute capacity of CPU i, typically it is the + * fraction of 'recent' time available for SCHED_OTHER task execution. But it + * can also include other factors [XXX]. + * + * To achieve this balance we define a measure of imbalance which follows + * directly from (1): + * + * imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4) + * + * We them move tasks around to minimize the imbalance. In the continuous + * function space it is obvious this converges, in the discrete case we get + * a few fun cases generally called infeasible weight scenarios. + * + * [XXX expand on: + * - infeasible weights; + * - local vs global optima in the discrete case. ] + * + * + * SCHED DOMAINS + * + * In order to solve the imbalance equation (4), and avoid the obvious O(n^2) + * for all i,j solution, we create a tree of CPUs that follows the hardware + * topology where each level pairs two lower groups (or better). This results + * in O(log n) layers. Furthermore we reduce the number of CPUs going up the + * tree to only the first of the previous level and we decrease the frequency + * of load-balance at each level inv. proportional to the number of CPUs in + * the groups. + * + * This yields: + * + * log_2 n 1 n + * \Sum { --- * --- * 2^i } = O(n) (5) + * i = 0 2^i 2^i + * `- size of each group + * | | `- number of CPUs doing load-balance + * | `- freq + * `- sum over all levels + * + * Coupled with a limit on how many tasks we can migrate every balance pass, + * this makes (5) the runtime complexity of the balancer. + * + * An important property here is that each CPU is still (indirectly) connected + * to every other CPU in at most O(log n) steps: + * + * The adjacency matrix of the resulting graph is given by: + * + * log_2 n + * A_i,j = \Union (i % 2^k == 0) && i / 2^(k+1) == j / 2^(k+1) (6) + * k = 0 + * + * And you'll find that: + * + * A^(log_2 n)_i,j != 0 for all i,j (7) + * + * Showing there's indeed a path between every CPU in at most O(log n) steps. + * The task movement gives a factor of O(m), giving a convergence complexity + * of: + * + * O(nm log n), n := nr_cpus, m := nr_tasks (8) + * + * + * WORK CONSERVING + * + * In order to avoid CPUs going idle while there's still work to do, new idle + * balancing is more aggressive and has the newly idle CPU iterate up the domain + * tree itself instead of relying on other CPUs to bring it work. + * + * This adds some complexity to both (5) and (8) but it reduces the total idle + * time. + * + * [XXX more?] + * + * + * CGROUPS + * + * Cgroups make a horror show out of (2), instead of a simple sum we get: + * + * s_k,i + * W_i,0 = \Sum_j \Prod_k w_k * ----- (9) + * S_k + * + * Where + * + * s_k,i = \Sum_j w_i,j,k and S_k = \Sum_i s_k,i (10) + * + * w_i,j,k is the weight of the j-th runnable task in the k-th cgroup on CPU i. + * + * The big problem is S_k, its a global sum needed to compute a local (W_i) + * property. + * + * [XXX write more on how we solve this.. _after_ merging pjt's patches that + * rewrite all of this once again.] + */ + +static unsigned long __read_mostly max_load_balance_interval = HZ/10; + +enum fbq_type { regular, remote, all }; + +/* + * 'group_type' describes the group of CPUs at the moment of load balancing. + * + * The enum is ordered by pulling priority, with the group with lowest priority + * first so the group_type can simply be compared when selecting the busiest + * group. See update_sd_pick_busiest(). + */ +enum group_type { + /* The group has spare capacity that can be used to run more tasks. */ + group_has_spare = 0, + /* + * The group is fully used and the tasks don't compete for more CPU + * cycles. Nevertheless, some tasks might wait before running. + */ + group_fully_busy, + /* + * One task doesn't fit with CPU's capacity and must be migrated to a + * more powerful CPU. + */ + group_misfit_task, + /* + * SD_ASYM_PACKING only: One local CPU with higher capacity is available, + * and the task should be migrated to it instead of running on the + * current CPU. + */ + group_asym_packing, + /* + * The tasks' affinity constraints previously prevented the scheduler + * from balancing the load across the system. + */ + group_imbalanced, + /* + * The CPU is overloaded and can't provide expected CPU cycles to all + * tasks. + */ + group_overloaded +}; + +enum migration_type { + migrate_load = 0, + migrate_util, + migrate_task, + migrate_misfit +}; + +#define LBF_ALL_PINNED 0x01 +#define LBF_NEED_BREAK 0x02 +#define LBF_DST_PINNED 0x04 +#define LBF_SOME_PINNED 0x08 +#define LBF_ACTIVE_LB 0x10 + +struct lb_env { + struct sched_domain *sd; + + struct rq *src_rq; + int src_cpu; + + int dst_cpu; + struct rq *dst_rq; + + struct cpumask *dst_grpmask; + int new_dst_cpu; + enum cpu_idle_type idle; + long imbalance; + /* The set of CPUs under consideration for load-balancing */ + struct cpumask *cpus; + + unsigned int flags; + + unsigned int loop; + unsigned int loop_break; + unsigned int loop_max; + + enum fbq_type fbq_type; + enum migration_type migration_type; + struct list_head tasks; +}; + +/* + * Is this task likely cache-hot: + */ +static int task_hot(struct task_struct *p, struct lb_env *env) +{ + s64 delta; + + lockdep_assert_rq_held(env->src_rq); + + if (p->sched_class != &fair_sched_class) + return 0; + + 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: + */ + if (sched_feat(CACHE_HOT_BUDDY) && env->dst_rq->nr_running && + (&p->se == cfs_rq_of(&p->se)->next || + &p->se == cfs_rq_of(&p->se)->last)) + return 1; + + 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; + + delta = rq_clock_task(env->src_rq) - p->se.exec_start; + + return delta < (s64)sysctl_sched_migration_cost; +} + +#ifdef CONFIG_NUMA_BALANCING +/* + * Returns 1, if task migration degrades locality + * Returns 0, if task migration improves locality i.e migration preferred. + * Returns -1, if task migration is not affected by locality. + */ +static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env) +{ + struct numa_group *numa_group = rcu_dereference(p->numa_group); + unsigned long src_weight, dst_weight; + int src_nid, dst_nid, dist; + + if (!static_branch_likely(&sched_numa_balancing)) + return -1; + + if (!p->numa_faults || !(env->sd->flags & SD_NUMA)) + return -1; + + src_nid = cpu_to_node(env->src_cpu); + dst_nid = cpu_to_node(env->dst_cpu); + + if (src_nid == dst_nid) + return -1; + + /* Migrating away from the preferred node is always bad. */ + if (src_nid == p->numa_preferred_nid) { + if (env->src_rq->nr_running > env->src_rq->nr_preferred_running) + return 1; + else + return -1; + } + + /* Encourage migration to the preferred node. */ + if (dst_nid == p->numa_preferred_nid) + return 0; + + /* Leaving a core idle is often worse than degrading locality. */ + if (env->idle == CPU_IDLE) + return -1; + + dist = node_distance(src_nid, dst_nid); + if (numa_group) { + src_weight = group_weight(p, src_nid, dist); + dst_weight = group_weight(p, dst_nid, dist); + } else { + src_weight = task_weight(p, src_nid, dist); + dst_weight = task_weight(p, dst_nid, dist); + } + + return dst_weight < src_weight; +} + +#else +static inline int migrate_degrades_locality(struct task_struct *p, + struct lb_env *env) +{ + return -1; +} +#endif + +/* + * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? + */ +static +int can_migrate_task(struct task_struct *p, struct lb_env *env) +{ + int tsk_cache_hot; + + lockdep_assert_rq_held(env->src_rq); + + /* + * We do not migrate tasks that are: + * 1) throttled_lb_pair, or + * 2) cannot be migrated to this CPU due to cpus_ptr, or + * 3) running (obviously), or + * 4) are cache-hot on their current CPU. + */ + 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->stats.nr_failed_migrations_affine); + + env->flags |= LBF_SOME_PINNED; + + /* + * Remember if this task can be migrated to any other CPU in + * our sched_group. We may want to revisit it if we couldn't + * meet load balance goals by pulling other tasks on src_cpu. + * + * 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 | LBF_ACTIVE_LB)) + return 0; + + /* Prevent to re-select dst_cpu via env's CPUs: */ + for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { + if (cpumask_test_cpu(cpu, p->cpus_ptr)) { + env->flags |= LBF_DST_PINNED; + env->new_dst_cpu = cpu; + break; + } + } + + return 0; + } + + /* Record that we found at least one task that could run on dst_cpu */ + env->flags &= ~LBF_ALL_PINNED; + + if (task_on_cpu(env->src_rq, p)) { + schedstat_inc(p->stats.nr_failed_migrations_running); + return 0; + } + + /* + * Aggressive migration if: + * 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); + + if (tsk_cache_hot <= 0 || + 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->stats.nr_forced_migrations); + } + return 1; + } + + schedstat_inc(p->stats.nr_failed_migrations_hot); + return 0; +} + +/* + * detach_task() -- detach the task for the migration specified in env + */ +static void detach_task(struct task_struct *p, struct lb_env *env) +{ + lockdep_assert_rq_held(env->src_rq); + + deactivate_task(env->src_rq, p, DEQUEUE_NOCLOCK); + set_task_cpu(p, env->dst_cpu); +} + +/* + * detach_one_task() -- tries to dequeue exactly one task from env->src_rq, as + * part of active balancing operations within "domain". + * + * Returns a task if successful and NULL otherwise. + */ +static struct task_struct *detach_one_task(struct lb_env *env) +{ + struct task_struct *p; + + lockdep_assert_rq_held(env->src_rq); + + list_for_each_entry_reverse(p, + &env->src_rq->cfs_tasks, se.group_node) { + if (!can_migrate_task(p, env)) + continue; + + detach_task(p, env); + + /* + * Right now, this is only the second place where + * lb_gained[env->idle] is updated (other is detach_tasks) + * so we can safely collect stats here rather than + * inside detach_tasks(). + */ + schedstat_inc(env->sd->lb_gained[env->idle]); + return p; + } + return NULL; +} + +/* + * detach_tasks() -- tries to detach up to imbalance load/util/tasks from + * busiest_rq, as part of a balancing operation within domain "sd". + * + * Returns number of detached tasks if successful and 0 otherwise. + */ +static int detach_tasks(struct lb_env *env) +{ + struct list_head *tasks = &env->src_rq->cfs_tasks; + unsigned long util, load; + struct task_struct *p; + int detached = 0; + + 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; + + while (!list_empty(tasks)) { + /* + * We don't want to steal all, otherwise we may be treated likewise, + * which could at worst lead to a livelock crash. + */ + if (env->idle != CPU_NOT_IDLE && env->src_rq->nr_running <= 1) + break; + + env->loop++; + /* + * 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->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: + /* + * 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) + goto next; + + /* + * Make sure that we don't migrate too much load. + * Nevertheless, let relax the constraint if + * scheduler fails to find a good waiting task to + * migrate. + */ + if (shr_bound(load, env->sd->nr_balance_failed) > env->imbalance) + goto next; + + env->imbalance -= load; + break; + + case migrate_util: + util = task_util_est(p); + + if (util > env->imbalance) + goto next; + + env->imbalance -= util; + break; + + case migrate_task: + env->imbalance--; + break; + + case migrate_misfit: + /* This is not a misfit task */ + if (task_fits_cpu(p, env->src_cpu)) + goto next; + + env->imbalance = 0; + break; + } + + detach_task(p, env); + list_add(&p->se.group_node, &env->tasks); + + detached++; + +#ifdef CONFIG_PREEMPTION + /* + * NEWIDLE balancing is a source of latency, so preemptible + * kernels will stop after the first task is detached to minimize + * the critical section. + */ + if (env->idle == CPU_NEWLY_IDLE) + break; +#endif + + /* + * We only want to steal up to the prescribed amount of + * load/util/tasks. + */ + if (env->imbalance <= 0) + break; + + continue; +next: + list_move(&p->se.group_node, tasks); + } + + /* + * Right now, this is one of only two places we collect this stat + * so we can safely collect detach_one_task() stats here rather + * than inside detach_one_task(). + */ + schedstat_add(env->sd->lb_gained[env->idle], detached); + + return detached; +} + +/* + * attach_task() -- attach the task detached by detach_task() to its new rq. + */ +static void attach_task(struct rq *rq, struct task_struct *p) +{ + lockdep_assert_rq_held(rq); + + WARN_ON_ONCE(task_rq(p) != rq); + activate_task(rq, p, ENQUEUE_NOCLOCK); + check_preempt_curr(rq, p, 0); +} + +/* + * attach_one_task() -- attaches the task returned from detach_one_task() to + * its new rq. + */ +static void attach_one_task(struct rq *rq, struct task_struct *p) +{ + struct rq_flags rf; + + rq_lock(rq, &rf); + update_rq_clock(rq); + attach_task(rq, p); + rq_unlock(rq, &rf); +} + +/* + * attach_tasks() -- attaches all tasks detached by detach_tasks() to their + * new rq. + */ +static void attach_tasks(struct lb_env *env) +{ + struct list_head *tasks = &env->tasks; + struct task_struct *p; + struct rq_flags rf; + + rq_lock(env->dst_rq, &rf); + update_rq_clock(env->dst_rq); + + while (!list_empty(tasks)) { + p = list_first_entry(tasks, struct task_struct, se.group_node); + list_del_init(&p->se.group_node); + + attach_task(env->dst_rq, p); + } + + rq_unlock(env->dst_rq, &rf); +} + +#ifdef CONFIG_NO_HZ_COMMON +static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) +{ + if (cfs_rq->avg.load_avg) + return true; + + if (cfs_rq->avg.util_avg) + return true; + + return false; +} + +static inline bool others_have_blocked(struct rq *rq) +{ + if (READ_ONCE(rq->avg_rt.util_avg)) + return true; + + 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; +#endif + + return false; +} + +static inline void update_blocked_load_tick(struct rq *rq) +{ + 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 + +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; + + /* + * update_load_avg() can call cpufreq_update_util(). Make sure that RT, + * DL and IRQ signals have been updated before updating CFS. + */ + 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)) + *done = false; + + return decayed; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED + +static bool __update_blocked_fair(struct rq *rq, bool *done) +{ + struct cfs_rq *cfs_rq, *pos; + bool decayed = false; + int cpu = cpu_of(rq); + + /* + * Iterates the task_group tree in a bottom up fashion, see + * list_add_leaf_cfs_rq() for details. + */ + for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) { + struct sched_entity *se; + + if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) { + 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; + } + + /* 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, UPDATE_TG); + + /* + * There can be a lot of idle CPU cgroups. Don't let fully + * decayed cfs_rqs linger on the list. + */ + if (cfs_rq_is_decayed(cfs_rq)) + list_del_leaf_cfs_rq(cfs_rq); + + /* Don't need periodic decay once load/util_avg are null */ + if (cfs_rq_has_blocked(cfs_rq)) + *done = false; + } + + return decayed; +} + +/* + * Compute the hierarchical load factor for cfs_rq and all its ascendants. + * This needs to be done in a top-down fashion because the load of a child + * group is a fraction of its parents load. + */ +static void update_cfs_rq_h_load(struct cfs_rq *cfs_rq) +{ + struct rq *rq = rq_of(cfs_rq); + struct sched_entity *se = cfs_rq->tg->se[cpu_of(rq)]; + unsigned long now = jiffies; + unsigned long load; + + if (cfs_rq->last_h_load_update == now) + return; + + WRITE_ONCE(cfs_rq->h_load_next, NULL); + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + WRITE_ONCE(cfs_rq->h_load_next, se); + if (cfs_rq->last_h_load_update == now) + break; + } + + if (!se) { + cfs_rq->h_load = cfs_rq_load_avg(cfs_rq); + cfs_rq->last_h_load_update = now; + } + + while ((se = READ_ONCE(cfs_rq->h_load_next)) != NULL) { + load = cfs_rq->h_load; + load = div64_ul(load * se->avg.load_avg, + cfs_rq_load_avg(cfs_rq) + 1); + cfs_rq = group_cfs_rq(se); + cfs_rq->h_load = load; + cfs_rq->last_h_load_update = now; + } +} + +static unsigned long task_h_load(struct task_struct *p) +{ + struct cfs_rq *cfs_rq = task_cfs_rq(p); + + update_cfs_rq_h_load(cfs_rq); + return div64_ul(p->se.avg.load_avg * cfs_rq->h_load, + cfs_rq_load_avg(cfs_rq) + 1); +} +#else +static bool __update_blocked_fair(struct rq *rq, bool *done) +{ + struct cfs_rq *cfs_rq = &rq->cfs; + bool decayed; + + decayed = update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq); + if (cfs_rq_has_blocked(cfs_rq)) + *done = false; + + return decayed; +} + +static unsigned long task_h_load(struct task_struct *p) +{ + return p->se.avg.load_avg; +} +#endif + +static void update_blocked_averages(int cpu) +{ + bool decayed = false, done = true; + struct rq *rq = cpu_rq(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); + decayed |= __update_blocked_fair(rq, &done); + + update_blocked_load_status(rq, !done); + if (decayed) + cpufreq_update_util(rq, 0); + rq_unlock_irqrestore(rq, &rf); +} + +/********** Helpers for find_busiest_group ************************/ + +/* + * sg_lb_stats - stats of a sched_group required for load_balancing + */ +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 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; + unsigned int group_weight; + enum group_type group_type; + unsigned int group_asym_packing; /* Tasks should be moved to preferred CPU */ + unsigned long group_misfit_task_load; /* A CPU has a task too big for its capacity */ +#ifdef CONFIG_NUMA_BALANCING + unsigned int nr_numa_running; + unsigned int nr_preferred_running; +#endif +}; + +/* + * sd_lb_stats - Structure to store the statistics of a sched_domain + * during load balancing. + */ +struct sd_lb_stats { + struct sched_group *busiest; /* Busiest group in this sd */ + struct sched_group *local; /* Local group in this sd */ + unsigned long total_load; /* Total load of all groups in sd */ + unsigned long total_capacity; /* Total capacity of all groups in sd */ + unsigned long avg_load; /* Average load across all groups in sd */ + unsigned int prefer_sibling; /* tasks should go to sibling first */ + + struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ + struct sg_lb_stats local_stat; /* Statistics of the local group */ +}; + +static inline void init_sd_lb_stats(struct sd_lb_stats *sds) +{ + /* + * Skimp on the clearing to avoid duplicate work. We can avoid clearing + * local_stat because update_sg_lb_stats() does a full clear/assignment. + * We must however set busiest_stat::group_type and + * busiest_stat::idle_cpus to the worst busiest group because + * update_sd_pick_busiest() reads these before assignment. + */ + *sds = (struct sd_lb_stats){ + .busiest = NULL, + .local = NULL, + .total_load = 0UL, + .total_capacity = 0UL, + .busiest_stat = { + .idle_cpus = UINT_MAX, + .group_type = group_has_spare, + }, + }; +} + +static unsigned long scale_rt_capacity(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long max = arch_scale_cpu_capacity(cpu); + unsigned long used, free; + unsigned long irq; + + irq = cpu_util_irq(rq); + + 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; + + free = max - used; + + return scale_irq_capacity(free, irq, max); +} + +static void update_cpu_capacity(struct sched_domain *sd, int 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); + + if (!capacity) + 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; +} + +void update_group_capacity(struct sched_domain *sd, int cpu) +{ + struct sched_domain *child = sd->child; + struct sched_group *group, *sdg = sd->groups; + unsigned long capacity, min_capacity, max_capacity; + unsigned long interval; + + interval = msecs_to_jiffies(sd->balance_interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + sdg->sgc->next_update = jiffies + interval; + + if (!child) { + update_cpu_capacity(sd, cpu); + return; + } + + capacity = 0; + min_capacity = ULONG_MAX; + max_capacity = 0; + + if (child->flags & SD_OVERLAP) { + /* + * SD_OVERLAP domains cannot assume that child groups + * span the current group. + */ + + for_each_cpu(cpu, sched_group_span(sdg)) { + unsigned long cpu_cap = capacity_of(cpu); + + capacity += cpu_cap; + min_capacity = min(cpu_cap, min_capacity); + max_capacity = max(cpu_cap, max_capacity); + } + } else { + /* + * !SD_OVERLAP domains can assume that child groups + * span the current group. + */ + + group = child->groups; + do { + struct sched_group_capacity *sgc = group->sgc; + + capacity += sgc->capacity; + min_capacity = min(sgc->min_capacity, min_capacity); + max_capacity = max(sgc->max_capacity, max_capacity); + group = group->next; + } while (group != child->groups); + } + + sdg->sgc->capacity = capacity; + sdg->sgc->min_capacity = min_capacity; + sdg->sgc->max_capacity = max_capacity; +} + +/* + * Check whether the capacity of the rq has been noticeably reduced by side + * activity. The imbalance_pct is used for the threshold. + * Return true is the capacity is reduced + */ +static inline int +check_cpu_capacity(struct rq *rq, struct sched_domain *sd) +{ + return ((rq->cpu_capacity * sd->imbalance_pct) < + (rq->cpu_capacity_orig * 100)); +} + +/* + * Check whether a rq has a misfit task and if it looks like we can actually + * help that task: we can migrate the task to a CPU of higher capacity, or + * the task's current CPU is heavily pressured. + */ +static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) +{ + return rq->misfit_task_load && + (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity || + check_cpu_capacity(rq, sd)); +} + +/* + * Group imbalance indicates (and tries to solve) the problem where balancing + * groups is inadequate due to ->cpus_ptr constraints. + * + * Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a + * cpumask covering 1 CPU of the first group and 3 CPUs of the second group. + * Something like: + * + * { 0 1 2 3 } { 4 5 6 7 } + * * * * * + * + * If we were to balance group-wise we'd place two tasks in the first group and + * two tasks in the second group. Clearly this is undesired as it will overload + * cpu 3 and leave one of the CPUs in the second group unused. + * + * The current solution to this issue is detecting the skew in the first group + * by noticing the lower domain failed to reach balance and had difficulty + * moving tasks due to affinity constraints. + * + * When this is so detected; this group becomes a candidate for busiest; see + * update_sd_pick_busiest(). And calculate_imbalance() and + * find_busiest_group() avoid some of the usual balance conditions to allow it + * to create an effective group imbalance. + * + * This is a somewhat tricky proposition since the next run might not find the + * group imbalance and decide the groups need to be balanced again. A most + * subtle and fragile situation. + */ + +static inline int sg_imbalanced(struct sched_group *group) +{ + return group->sgc->imbalance; +} + +/* + * 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 + * 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 + * account the variance of the tasks' load and to return true if the available + * capacity in meaningful for the load balancer. + * As an example, an available capacity of 1% can appear but it doesn't make + * any benefit for the load balance. + */ +static inline bool +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; + + return false; +} + +/* + * group_is_overloaded returns true if the group has more tasks than it can + * handle. + * group_is_overloaded is not equals to !group_has_capacity because a group + * with the exact right number of tasks, has no more spare capacity but is not + * overloaded so both group_has_capacity and group_is_overloaded return + * false. + */ +static inline bool +group_is_overloaded(unsigned int imbalance_pct, struct sg_lb_stats *sgs) +{ + if (sgs->sum_nr_running <= sgs->group_weight) + return false; + + if ((sgs->group_capacity * 100) < + (sgs->group_util * imbalance_pct)) + return true; + + if ((sgs->group_capacity * imbalance_pct) < + (sgs->group_runnable * 100)) + return true; + + return false; +} + +static inline enum +group_type group_classify(unsigned int imbalance_pct, + struct sched_group *group, + struct sg_lb_stats *sgs) +{ + if (group_is_overloaded(imbalance_pct, sgs)) + return group_overloaded; + + if (sg_imbalanced(group)) + return group_imbalanced; + + if (sgs->group_asym_packing) + return group_asym_packing; + + if (sgs->group_misfit_task_load) + return group_misfit_task; + + if (!group_has_capacity(imbalance_pct, sgs)) + return group_fully_busy; + + return group_has_spare; +} + +/** + * 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_SCHED_SMT + bool local_is_smt, sg_is_smt; + int sg_busy_cpus; + + local_is_smt = sds->local->flags & SD_SHARE_CPUCAPACITY; + sg_is_smt = sg->flags & SD_SHARE_CPUCAPACITY; + + sg_busy_cpus = sgs->group_weight - sgs->idle_cpus; + + 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; + + /* + * @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); + } + + /* @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) +{ + int i, nr_running, local_group; + + memset(sgs, 0, sizeof(*sgs)); + + 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); + + 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; + sgs->sum_nr_running += nr_running; + + if (nr_running > 1) + *sg_status |= SG_OVERLOAD; + + if (cpu_overutilized(i)) + *sg_status |= SG_OVERUTILIZED; + +#ifdef CONFIG_NUMA_BALANCING + sgs->nr_numa_running += rq->nr_numa_running; + sgs->nr_preferred_running += rq->nr_preferred_running; +#endif + /* + * No need to call idle_cpu() if nr_running is not 0 + */ + if (!nr_running && idle_cpu(i)) { + sgs->idle_cpus++; + /* Idle cpu can't have misfit task */ + continue; + } + + if (local_group) + continue; + + 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; + } + } + + 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 */ + if (sgs->group_type == group_overloaded) + sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) / + sgs->group_capacity; +} + +/** + * update_sd_pick_busiest - return 1 on busiest group + * @env: The load balancing environment. + * @sds: sched_domain statistics + * @sg: sched_group candidate to be checked for being the busiest + * @sgs: sched_group statistics + * + * Determine if @sg is a busier group than the previously selected + * busiest group. + * + * Return: %true if @sg is a busier group than the previously selected + * busiest group. %false otherwise. + */ +static bool update_sd_pick_busiest(struct lb_env *env, + struct sd_lb_stats *sds, + struct sched_group *sg, + struct sg_lb_stats *sgs) +{ + struct sg_lb_stats *busiest = &sds->busiest_stat; + + /* Make sure that there is at least one task to pull */ + if (!sgs->sum_h_nr_running) + return false; + + /* + * Don't try to pull misfit tasks we can't help. + * We can use max_capacity here as reduction in capacity on some + * CPUs in the group should either be possible to resolve + * internally or be covered by avg_load imbalance (eventually). + */ + 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; + + if (sgs->group_type > busiest->group_type) + return true; + + if (sgs->group_type < busiest->group_type) + return false; + + /* + * The candidate and the current busiest group are the same type of + * group. Let check which one is the busiest according to the type. + */ + + switch (sgs->group_type) { + case group_overloaded: + /* Select the overloaded group with highest avg_load. */ + if (sgs->avg_load <= busiest->avg_load) + return false; + break; + + case group_imbalanced: + /* + * Select the 1st imbalanced group as we don't have any way to + * choose one more than another. + */ + return false; + + case group_asym_packing: + /* Prefer to move from lowest priority CPU's work */ + if (sched_asym_prefer(sg->asym_prefer_cpu, sds->busiest->asym_prefer_cpu)) + return false; + break; + + case group_misfit_task: + /* + * If we have more than one misfit sg go with the biggest + * misfit. + */ + if (sgs->group_misfit_task_load < busiest->group_misfit_task_load) + return false; + break; + + case group_fully_busy: + /* + * Select the fully busy group with highest avg_load. In + * theory, there is no need to pull task from such kind of + * group because tasks have all compute capacity that they need + * but we can still improve the overall throughput by reducing + * contention when accessing shared HW resources. + * + * XXX for now avg_load is not computed and always 0 so we + * select the 1st one. + */ + if (sgs->avg_load <= busiest->avg_load) + return false; + break; + + case group_has_spare: + /* + * Select not overloaded group with lowest number of idle cpus + * and highest number of running tasks. We could also compare + * the spare capacity which is more stable but it can end up + * that the group has less spare capacity but finally more idle + * CPUs which means less opportunity to pull tasks. + */ + if (sgs->idle_cpus > busiest->idle_cpus) + return false; + else if ((sgs->idle_cpus == busiest->idle_cpus) && + (sgs->sum_nr_running <= busiest->sum_nr_running)) + return false; + + break; + } + + /* + * Candidate sg has no more than one task per CPU and has higher + * per-CPU capacity. Migrating tasks to less capable CPUs may harm + * throughput. Maximize throughput, power/energy consequences are not + * considered. + */ + if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && + (sgs->group_type <= group_fully_busy) && + (capacity_greater(sg->sgc->min_capacity, capacity_of(env->dst_cpu)))) + return false; + + return true; +} + +#ifdef CONFIG_NUMA_BALANCING +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + if (sgs->sum_h_nr_running > sgs->nr_numa_running) + return regular; + if (sgs->sum_h_nr_running > sgs->nr_preferred_running) + return remote; + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + if (rq->nr_running > rq->nr_numa_running) + return regular; + if (rq->nr_running > rq->nr_preferred_running) + return remote; + return all; +} +#else +static inline enum fbq_type fbq_classify_group(struct sg_lb_stats *sgs) +{ + return all; +} + +static inline enum fbq_type fbq_classify_rq(struct rq *rq) +{ + return regular; +} +#endif /* CONFIG_NUMA_BALANCING */ + + +struct sg_lb_stats; + +/* + * task_running_on_cpu - return 1 if @p is running on @cpu. + */ + +static unsigned int task_running_on_cpu(int cpu, struct task_struct *p) +{ + /* Task has no contribution or is new */ + if (cpu != task_cpu(p) || !READ_ONCE(p->se.avg.last_update_time)) + return 0; + + if (task_on_rq_queued(p)) + return 1; + + return 0; +} + +/** + * idle_cpu_without - would a given CPU be idle without p ? + * @cpu: the processor on which idleness is tested. + * @p: task which should be ignored. + * + * Return: 1 if the CPU would be idle. 0 otherwise. + */ +static int idle_cpu_without(int cpu, struct task_struct *p) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->curr != rq->idle && rq->curr != p) + return 0; + + /* + * rq->nr_running can't be used but an updated version without the + * impact of p on cpu must be used instead. The updated nr_running + * be computed and tested before calling idle_cpu_without(). + */ + +#ifdef CONFIG_SMP + if (rq->ttwu_pending) + return 0; +#endif + + return 1; +} + +/* + * update_sg_wakeup_stats - Update sched_group's statistics for wakeup. + * @sd: The sched_domain level to look for idlest group. + * @group: sched_group whose statistics are to be updated. + * @sgs: variable to hold the statistics for this group. + * @p: The task for which we look for the idlest group/CPU. + */ +static inline void update_sg_wakeup_stats(struct sched_domain *sd, + struct sched_group *group, + struct sg_lb_stats *sgs, + struct task_struct *p) +{ + int i, nr_running; + + memset(sgs, 0, sizeof(*sgs)); + + /* Assume that task can't fit any CPU of the group */ + if (sd->flags & SD_ASYM_CPUCAPACITY) + sgs->group_misfit_task_load = 1; + + for_each_cpu(i, sched_group_span(group)) { + struct rq *rq = cpu_rq(i); + unsigned int local; + + 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; + + nr_running = rq->nr_running - local; + sgs->sum_nr_running += nr_running; + + /* + * No need to call idle_cpu_without() if nr_running is not 0 + */ + if (!nr_running && idle_cpu_without(i, p)) + sgs->idle_cpus++; + + /* Check if task fits in the CPU */ + if (sd->flags & SD_ASYM_CPUCAPACITY && + sgs->group_misfit_task_load && + task_fits_cpu(p, i)) + sgs->group_misfit_task_load = 0; + + } + + sgs->group_capacity = group->sgc->capacity; + + sgs->group_weight = group->group_weight; + + sgs->group_type = group_classify(sd->imbalance_pct, group, sgs); + + /* + * Computing avg_load makes sense only when group is fully busy or + * overloaded + */ + if (sgs->group_type == group_fully_busy || + sgs->group_type == group_overloaded) + sgs->avg_load = (sgs->group_load * SCHED_CAPACITY_SCALE) / + sgs->group_capacity; +} + +static bool update_pick_idlest(struct sched_group *idlest, + struct sg_lb_stats *idlest_sgs, + struct sched_group *group, + struct sg_lb_stats *sgs) +{ + if (sgs->group_type < idlest_sgs->group_type) + return true; + + if (sgs->group_type > idlest_sgs->group_type) + return false; + + /* + * The candidate and the current idlest group are the same type of + * group. Let check which one is the idlest according to the type. + */ + + switch (sgs->group_type) { + case group_overloaded: + case group_fully_busy: + /* Select the group with lowest avg_load. */ + if (idlest_sgs->avg_load <= sgs->avg_load) + return false; + break; + + case group_imbalanced: + case group_asym_packing: + /* Those types are not used in the slow wakeup path */ + return false; + + case group_misfit_task: + /* Select group with the highest max capacity */ + if (idlest->sgc->max_capacity >= group->sgc->max_capacity) + return false; + break; + + case group_has_spare: + /* Select group with most 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; + } + + return true; +} + +/* + * find_idlest_group() finds and returns the least busy CPU group within the + * domain. + * + * 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) +{ + struct sched_group *idlest = NULL, *local = NULL, *group = sd->groups; + struct sg_lb_stats local_sgs, tmp_sgs; + struct sg_lb_stats *sgs; + unsigned long imbalance; + struct sg_lb_stats idlest_sgs = { + .avg_load = UINT_MAX, + .group_type = group_overloaded, + }; + + do { + int local_group; + + /* Skip over this group if it has no CPUs allowed */ + if (!cpumask_intersects(sched_group_span(group), + 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)); + + if (local_group) { + sgs = &local_sgs; + local = group; + } else { + sgs = &tmp_sgs; + } + + update_sg_wakeup_stats(sd, group, sgs, p); + + if (!local_group && update_pick_idlest(idlest, &idlest_sgs, group, sgs)) { + idlest = group; + idlest_sgs = *sgs; + } + + } while (group = group->next, group != sd->groups); + + + /* There is no idlest group to push tasks to */ + if (!idlest) + return NULL; + + /* The local group has been skipped because of CPU affinity */ + if (!local) + return idlest; + + /* + * If the local group is idler than the selected idlest group + * don't try and push the task. + */ + if (local_sgs.group_type < idlest_sgs.group_type) + return NULL; + + /* + * If the local group is busier than the selected idlest group + * try and push the task. + */ + if (local_sgs.group_type > idlest_sgs.group_type) + return idlest; + + 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 + * remote domains but "imbalance" skews the comparison making + * remote CPUs look much more favourable. When considering + * cross-domain, add imbalance to the load on the remote node + * and consider staying local. + */ + + if ((sd->flags & SD_NUMA) && + ((idlest_sgs.avg_load + imbalance) >= local_sgs.avg_load)) + return NULL; + + /* + * If the local group is less loaded than the selected + * idlest group don't try and push any tasks. + */ + if (idlest_sgs.avg_load >= (local_sgs.avg_load + imbalance)) + return NULL; + + if (100 * local_sgs.avg_load <= sd->imbalance_pct * idlest_sgs.avg_load) + return NULL; + break; + + case group_imbalanced: + case group_asym_packing: + /* Those type are not used in the slow wakeup path */ + return NULL; + + case group_misfit_task: + /* Select group with the highest max capacity */ + if (local->sgc->max_capacity >= idlest->sgc->max_capacity) + return NULL; + 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; + /* + * If there is spare capacity at NUMA, try to select + * the preferred node + */ + if (cpu_to_node(this_cpu) == p->numa_preferred_nid) + return NULL; + + idlest_cpu = cpumask_first(sched_group_span(idlest)); + if (cpu_to_node(idlest_cpu) == p->numa_preferred_nid) + return idlest; +#endif /* CONFIG_NUMA_BALANCING */ + /* + * 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 (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 + * compare the utilization which is more stable but it can end + * up that the group has less spare capacity but finally more + * idle CPUs which means more opportunity to run task. + */ + if (local_sgs.idle_cpus >= idlest_sgs.idle_cpus) + return NULL; + break; + } + + 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. + * @sds: variable to hold the statistics for this sched_domain. + */ + +static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sds) +{ + struct sched_domain *child = env->sd->child; + 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; + + do { + struct sg_lb_stats *sgs = &tmp_sgs; + int local_group; + + local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(sg)); + if (local_group) { + sds->local = sg; + sgs = local; + + if (env->idle != CPU_NEWLY_IDLE || + time_after_eq(jiffies, sg->sgc->next_update)) + update_group_capacity(env->sd, env->dst_cpu); + } + + update_sg_lb_stats(env, sds, sg, sgs, &sg_status); + + if (local_group) + goto next_group; + + + if (update_sd_pick_busiest(env, sds, sg, sgs)) { + sds->busiest = sg; + sds->busiest_stat = *sgs; + } + +next_group: + /* Now, start updating sd_lb_stats */ + sds->total_load += sgs->group_load; + sds->total_capacity += sgs->group_capacity; + + 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; + + + if (env->sd->flags & SD_NUMA) + env->fbq_type = fbq_classify_group(&sds->busiest_stat); + + if (!env->sd->parent) { + struct root_domain *rd = env->dst_rq->rd; + + /* update overload indicator if we are at root domain */ + WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD); + + /* Update over-utilization (tipping point, U >= 0) indicator */ + WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); + trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED); + } else if (sg_status & SG_OVERUTILIZED) { + struct root_domain *rd = env->dst_rq->rd; + + WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); + trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); + } + + update_idle_cpu_scan(env, sum_util); +} + +/** + * calculate_imbalance - Calculate the amount of imbalance present within the + * groups of a given sched_domain during load balance. + * @env: load balance environment + * @sds: statistics of the sched_domain whose imbalance is to be calculated. + */ +static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *sds) +{ + struct sg_lb_stats *local, *busiest; + + local = &sds->local_stat; + busiest = &sds->busiest_stat; + + if (busiest->group_type == group_misfit_task) { + 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; + } + + if (busiest->group_type == group_asym_packing) { + /* + * In case of asym capacity, we will try to migrate all load to + * the preferred CPU. + */ + env->migration_type = migrate_task; + env->imbalance = busiest->sum_h_nr_running; + return; + } + + if (busiest->group_type == group_imbalanced) { + /* + * In the group_imb case we cannot rely on group-wide averages + * to ensure CPU-load equilibrium, try to move any task to fix + * the imbalance. The next load balance will take care of + * balancing back the system. + */ + env->migration_type = migrate_task; + env->imbalance = 1; + return; + } + + /* + * Try to use spare capacity of local group without overloading it or + * emptying busiest. + */ + if (local->group_type == group_has_spare) { + 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 + * in busiest or busiest still being overloaded but + * there is no simple way to directly compute the + * amount of load to migrate in order to balance the + * system. + */ + env->migration_type = migrate_util; + env->imbalance = max(local->group_capacity, local->group_util) - + local->group_util; + + /* + * In some cases, the group's utilization is max or even + * higher than capacity because of migrations but the + * local CPU is (newly) idle. There is at least one + * waiting task in this overloaded busiest group. Let's + * try to pull it. + */ + if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) { + env->migration_type = migrate_task; + env->imbalance = 1; + } + + return; + } + + if (busiest->group_weight == 1 || sds->prefer_sibling) { + unsigned int nr_diff = busiest->sum_nr_running; + /* + * When prefer sibling, evenly spread running tasks on + * groups. + */ + env->migration_type = migrate_task; + lsub_positive(&nr_diff, local->sum_nr_running); + env->imbalance = nr_diff; + } else { + + /* + * If there is no overload, we just want to even the number of + * idle cpus. + */ + env->migration_type = migrate_task; + 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) { + 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; + } + + /* + * Local is fully busy but has to take more load to relieve the + * busiest group + */ + if (local->group_type < group_overloaded) { + /* + * Local will become overloaded so the avg_load metrics are + * finally needed. + */ + + 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; + + /* + * If the local group is more loaded than the average system + * load, don't try to pull any tasks. + */ + if (local->avg_load >= sds->avg_load) { + env->imbalance = 0; + return; + } + + } + + /* + * Both group are or will become overloaded and we're trying to get all + * the CPUs to the average_load, so we don't want to push ourselves + * above the average load, nor do we wish to reduce the max loaded CPU + * below the average load. At the same time, we also don't want to + * reduce the group load below the group capacity. Thus we look for + * the minimum possible imbalance. + */ + env->migration_type = migrate_load; + env->imbalance = min( + (busiest->avg_load - sds->avg_load) * busiest->group_capacity, + (sds->avg_load - local->avg_load) * local->group_capacity + ) / SCHED_CAPACITY_SCALE; +} + +/******* find_busiest_group() helpers end here *********************/ + +/* + * Decision matrix according to the local and busiest group type: + * + * 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 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 + * + * N/A : Not Applicable because already filtered while updating + * statistics. + * balanced : The system is balanced for these 2 groups. + * force : Calculate the imbalance as load migration is probably needed. + * avg_load : Only if imbalance is significant enough. + * nr_idle : dst_cpu is not busy and the number of idle CPUs is quite + * different in groups. + */ + +/** + * 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. + * + * Return: - The busiest group if imbalance exists. + */ +static struct sched_group *find_busiest_group(struct lb_env *env) +{ + struct sg_lb_stats *local, *busiest; + struct sd_lb_stats sds; + + init_sd_lb_stats(&sds); + + /* + * Compute the various statistics relevant for load balancing at + * this level. + */ + update_sd_lb_stats(env, &sds); + + /* There is no busy sibling group to pull tasks from */ + if (!sds.busiest) + goto out_balanced; + + busiest = &sds.busiest_stat; + + /* Misfit tasks should be dealt with regardless of the avg load */ + if (busiest->group_type == group_misfit_task) + goto force_balance; + + if (sched_energy_enabled()) { + struct root_domain *rd = env->dst_rq->rd; + + if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized)) + goto out_balanced; + } + + /* ASYM feature bypasses nice load balance check */ + if (busiest->group_type == group_asym_packing) + goto force_balance; + + /* + * If the busiest group is imbalanced the below checks don't + * work because they assume all things are equal, which typically + * isn't true due to cpus_ptr constraints and the like. + */ + if (busiest->group_type == group_imbalanced) + goto force_balance; + + local = &sds.local_stat; + /* + * If the local group is busier than the selected busiest group + * don't try and pull any tasks. + */ + if (local->group_type > busiest->group_type) + goto out_balanced; + + /* + * When groups are overloaded, use the avg_load to ensure fairness + * between tasks. + */ + if (local->group_type == group_overloaded) { + /* + * 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) + goto out_balanced; + + /* XXX broken for overlapping NUMA groups */ + sds.avg_load = (sds.total_load * SCHED_CAPACITY_SCALE) / + sds.total_capacity; + + /* + * Don't pull any tasks if this group is already above the + * domain average load. + */ + if (local->avg_load >= sds.avg_load) + goto out_balanced; + + /* + * If the busiest group is more loaded, use imbalance_pct to be + * conservative. + */ + if (100 * busiest->avg_load <= + env->sd->imbalance_pct * local->avg_load) + goto out_balanced; + } + + /* Try to move all excess tasks to child's sibling domain */ + if (sds.prefer_sibling && local->group_type == group_has_spare && + busiest->sum_nr_running > local->sum_nr_running + 1) + goto force_balance; + + if (busiest->group_type != group_overloaded) { + if (env->idle == CPU_NOT_IDLE) + /* + * If the busiest group is not overloaded (and as a + * result the local one too) but this CPU is already + * busy, let another idle CPU try to pull task. + */ + goto out_balanced; + + if (busiest->group_weight > 1 && + local->idle_cpus <= (busiest->idle_cpus + 1)) + /* + * If the busiest group is not overloaded + * and there is no imbalance between this and busiest + * group wrt idle CPUs, it is balanced. The imbalance + * becomes significant if the diff is greater than 1 + * otherwise we might end up to just move the imbalance + * on another group. Of course this applies only if + * there is more than 1 CPU per group. + */ + goto out_balanced; + + if (busiest->sum_h_nr_running == 1) + /* + * busiest doesn't have any tasks waiting to run + */ + goto out_balanced; + } + +force_balance: + /* Looks like there is an imbalance. Compute it */ + calculate_imbalance(env, &sds); + return env->imbalance ? sds.busiest : NULL; + +out_balanced: + env->imbalance = 0; + return NULL; +} + +/* + * find_busiest_queue - find the busiest runqueue among the CPUs in the group. + */ +static struct rq *find_busiest_queue(struct lb_env *env, + struct sched_group *group) +{ + struct rq *busiest = NULL, *rq; + unsigned long busiest_util = 0, busiest_load = 0, busiest_capacity = 1; + unsigned int busiest_nr = 0; + int i; + + for_each_cpu_and(i, sched_group_span(group), env->cpus) { + unsigned long capacity, load, util; + unsigned int nr_running; + enum fbq_type rt; + + rq = cpu_rq(i); + rt = fbq_classify_rq(rq); + + /* + * We classify groups/runqueues into three groups: + * - regular: there are !numa tasks + * - remote: there are numa tasks that run on the 'wrong' node + * - all: there is no distinction + * + * In order to avoid migrating ideally placed numa tasks, + * ignore those when there's better options. + * + * If we ignore the actual busiest queue to migrate another + * task, the next balance pass can still reduce the busiest + * queue by moving tasks around inside the node. + * + * If we cannot move enough load due to this classification + * the next pass will adjust the group classification and + * allow migration of more tasks. + * + * Both cases only affect the total convergence complexity. + */ + if (rt > env->fbq_type) + continue; + + 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 + * eventually lead to active_balancing high->low capacity. + * Higher per-CPU capacity is considered better than balancing + * average load. + */ + if (env->sd->flags & SD_ASYM_CPUCAPACITY && + !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; + + switch (env->migration_type) { + case migrate_load: + /* + * When comparing with load imbalance, use cpu_load() + * which is not scaled with the CPU capacity. + */ + load = cpu_load(rq); + + if (nr_running == 1 && load > env->imbalance && + !check_cpu_capacity(rq, env->sd)) + break; + + /* + * For the load comparisons with the other CPUs, + * consider the cpu_load() scaled with the CPU + * capacity, so that the load can be moved away + * from the CPU that is potentially running at a + * lower capacity. + * + * Thus we're looking for max(load_i / capacity_i), + * crosswise multiplication to rid ourselves of the + * division works out to: + * load_i * capacity_j > load_j * capacity_i; + * where j is our previous maximum. + */ + if (load * busiest_capacity > busiest_load * capacity) { + busiest_load = load; + busiest_capacity = capacity; + busiest = rq; + } + break; + + case migrate_util: + 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; + busiest = rq; + } + break; + + case migrate_task: + if (busiest_nr < nr_running) { + busiest_nr = nr_running; + busiest = rq; + } + break; + + case migrate_misfit: + /* + * For ASYM_CPUCAPACITY domains with misfit tasks we + * simply seek the "biggest" misfit task. + */ + if (rq->misfit_task_load > busiest_load) { + busiest_load = rq->misfit_task_load; + busiest = rq; + } + + break; + + } + } + + return busiest; +} + +/* + * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but + * so long as it is large enough. + */ +#define MAX_PINNED_INTERVAL 512 + +static inline bool +asym_active_balance(struct lb_env *env) +{ + /* + * ASYM_PACKING needs to force migrate tasks from busy but + * lower priority CPUs in order to pack all tasks in the + * highest priority CPUs. + */ + return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) && + sched_asym_prefer(env->dst_cpu, env->src_cpu); +} + +static inline bool +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 + * because of other sched_class or IRQs if more capacity stays + * available on dst_cpu. + */ + if ((env->idle != CPU_NOT_IDLE) && + (env->src_rq->cfs.h_nr_running == 1)) { + if ((check_cpu_capacity(env->src_rq, sd)) && + (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100)) + return 1; + } + + if (env->migration_type == migrate_misfit) + return 1; + + return 0; +} + +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; + + /* + * Ensure the balancing environment is consistent; can happen + * when the softirq triggers 'during' hotplug. + */ + if (!cpumask_test_cpu(env->dst_cpu, env->cpus)) + return 0; + + /* + * 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->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; + + /* Are we the first idle CPU? */ + return cpu == env->dst_cpu; + } + + /* Are we the first CPU of this group ? */ + return group_balance_cpu(sg) == env->dst_cpu; +} + +/* + * Check this_cpu to ensure it is balanced within domain. Attempt to move + * tasks if there is an imbalance. + */ +static int load_balance(int this_cpu, struct rq *this_rq, + struct sched_domain *sd, enum cpu_idle_type idle, + int *continue_balancing) +{ + int ld_moved, cur_ld_moved, active_balance = 0; + struct sched_domain *sd_parent = sd->parent; + struct sched_group *group; + struct rq *busiest; + 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 = group_balance_mask(sd->groups), + .idle = idle, + .loop_break = SCHED_NR_MIGRATE_BREAK, + .cpus = cpus, + .fbq_type = all, + .tasks = LIST_HEAD_INIT(env.tasks), + }; + + cpumask_and(cpus, sched_domain_span(sd), cpu_active_mask); + + schedstat_inc(sd->lb_count[idle]); + +redo: + if (!should_we_balance(&env)) { + *continue_balancing = 0; + goto out_balanced; + } + + group = find_busiest_group(&env); + if (!group) { + schedstat_inc(sd->lb_nobusyg[idle]); + goto out_balanced; + } + + busiest = find_busiest_queue(&env, group); + if (!busiest) { + schedstat_inc(sd->lb_nobusyq[idle]); + goto out_balanced; + } + + WARN_ON_ONCE(busiest == env.dst_rq); + + schedstat_add(sd->lb_imbalance[idle], env.imbalance); + + env.src_cpu = busiest->cpu; + 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 + * an imbalance but busiest->nr_running <= 1, the group is + * still unbalanced. ld_moved simply stays zero, so it is + * correctly treated as an imbalance. + */ + env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running); + +more_balance: + rq_lock_irqsave(busiest, &rf); + update_rq_clock(busiest); + + /* + * cur_ld_moved - load moved in current iteration + * ld_moved - cumulative load moved across iterations + */ + cur_ld_moved = detach_tasks(&env); + + /* + * We've detached some tasks from busiest_rq. Every + * task is masked "TASK_ON_RQ_MIGRATING", so we can safely + * unlock busiest->lock, and we are able to be sure + * that nobody can manipulate the tasks in parallel. + * See task_rq_lock() family for the details. + */ + + rq_unlock(busiest, &rf); + + if (cur_ld_moved) { + attach_tasks(&env); + ld_moved += cur_ld_moved; + } + + local_irq_restore(rf.flags); + + if (env.flags & LBF_NEED_BREAK) { + env.flags &= ~LBF_NEED_BREAK; + /* Stop if we tried all running tasks */ + if (env.loop < busiest->nr_running) + goto more_balance; + } + + /* + * Revisit (affine) tasks on src_cpu that couldn't be moved to + * us and move them to an alternate dst_cpu in our sched_group + * where they can run. The upper limit on how many times we + * iterate on same src_cpu is dependent on number of CPUs in our + * sched_group. + * + * This changes load balance semantics a bit on who can move + * load to a given_cpu. In addition to the given_cpu itself + * (or a ilb_cpu acting on its behalf where given_cpu is + * nohz-idle), we now have balance_cpu in a position to move + * 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 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. + */ + if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) { + + /* Prevent to re-select dst_cpu via env's CPUs */ + __cpumask_clear_cpu(env.dst_cpu, env.cpus); + + env.dst_rq = cpu_rq(env.new_dst_cpu); + env.dst_cpu = env.new_dst_cpu; + env.flags &= ~LBF_DST_PINNED; + env.loop = 0; + env.loop_break = SCHED_NR_MIGRATE_BREAK; + + /* + * Go back to "more_balance" rather than "redo" since we + * need to continue with same src_cpu. + */ + goto more_balance; + } + + /* + * We failed to reach balance because of affinity. + */ + if (sd_parent) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) + *group_imbalance = 1; + } + + /* All tasks on this runqueue were pinned by CPU affinity */ + if (unlikely(env.flags & LBF_ALL_PINNED)) { + __cpumask_clear_cpu(cpu_of(busiest), cpus); + /* + * Attempting to continue load balancing at the current + * sched_domain level only makes sense if there are + * active CPUs remaining as possible busiest CPUs to + * pull load from which are not contained within the + * destination group that is receiving any migrated + * load. + */ + if (!cpumask_subset(cpus, env.dst_grpmask)) { + env.loop = 0; + env.loop_break = SCHED_NR_MIGRATE_BREAK; + goto redo; + } + goto out_all_pinned; + } + } + + if (!ld_moved) { + schedstat_inc(sd->lb_failed[idle]); + /* + * Increment the failure counter only on periodic balance. + * We do not want newidle balance, which can be very + * frequent, pollute the failure counter causing + * excessive cache_hot migrations and active balances. + */ + if (idle != CPU_NEWLY_IDLE) + sd->nr_balance_failed++; + + if (need_active_balance(&env)) { + unsigned long flags; + + raw_spin_rq_lock_irqsave(busiest, flags); + + /* + * Don't kick the active_load_balance_cpu_stop, + * if the curr task on busiest CPU can't be + * moved to this_cpu: + */ + if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { + 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 + * only after active load balance is finished. + */ + if (!busiest->active_balance) { + busiest->active_balance = 1; + busiest->push_cpu = this_cpu; + active_balance = 1; + } + + preempt_disable(); + 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); + } + preempt_enable(); + } + } else { + sd->nr_balance_failed = 0; + } + + if (likely(!active_balance) || need_active_balance(&env)) { + /* We were unbalanced, so reset the balancing interval */ + sd->balance_interval = sd->min_interval; + } + + goto out; + +out_balanced: + /* + * We reach balance although we may have faced some affinity + * constraints. Clear the imbalance flag only if other tasks got + * a chance to move and fix the imbalance. + */ + if (sd_parent && !(env.flags & LBF_ALL_PINNED)) { + int *group_imbalance = &sd_parent->groups->sgc->imbalance; + + if (*group_imbalance) + *group_imbalance = 0; + } + +out_all_pinned: + /* + * We reach balance because all tasks are pinned at this level so + * we can't migrate them. Let the imbalance flag set so parent level + * can try to migrate them. + */ + schedstat_inc(sd->lb_balanced[idle]); + + sd->nr_balance_failed = 0; + +out_one_pinned: + ld_moved = 0; + + /* + * newidle_balance() disregards balance intervals, so we could + * repeatedly reach this code, which would lead to balance_interval + * skyrocketing in a short amount of time. Skip the balance_interval + * increase logic to avoid that. + */ + if (env.idle == CPU_NEWLY_IDLE) + goto out; + + /* tune up the balancing interval */ + if ((env.flags & LBF_ALL_PINNED && + sd->balance_interval < MAX_PINNED_INTERVAL) || + sd->balance_interval < sd->max_interval) + sd->balance_interval *= 2; +out: + return ld_moved; +} + +static inline unsigned long +get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) +{ + unsigned long interval = sd->balance_interval; + + if (cpu_busy) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + + /* + * 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; +} + +static inline void +update_next_balance(struct sched_domain *sd, unsigned long *next_balance) +{ + unsigned long interval, next; + + /* used by idle balance, so cpu_busy = 0 */ + interval = get_sd_balance_interval(sd, 0); + next = sd->last_balance + interval; + + if (time_after(*next_balance, next)) + *next_balance = next; +} + +/* + * active_load_balance_cpu_stop is run by the CPU stopper. It pushes + * running tasks off the busiest CPU onto idle CPUs. It requires at + * least 1 task to be running on each physical CPU where possible, and + * avoids physical / logical imbalances. + */ +static int active_load_balance_cpu_stop(void *data) +{ + struct rq *busiest_rq = data; + int busiest_cpu = cpu_of(busiest_rq); + int target_cpu = busiest_rq->push_cpu; + struct rq *target_rq = cpu_rq(target_cpu); + struct sched_domain *sd; + struct task_struct *p = NULL; + struct rq_flags rf; + + rq_lock_irq(busiest_rq, &rf); + /* + * Between queueing the stop-work and running it is a hole in which + * CPUs can become inactive. We should not move tasks from or to + * inactive CPUs. + */ + if (!cpu_active(busiest_cpu) || !cpu_active(target_cpu)) + goto out_unlock; + + /* Make sure the requested CPU hasn't gone down in the meantime: */ + if (unlikely(busiest_cpu != smp_processor_id() || + !busiest_rq->active_balance)) + goto out_unlock; + + /* Is there any task to move? */ + if (busiest_rq->nr_running <= 1) + goto out_unlock; + + /* + * This condition is "impossible", if it occurs + * we need to fix it. Originally reported by + * Bjorn Helgaas on a 128-CPU setup. + */ + 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 (cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) + break; + } + + if (likely(sd)) { + struct lb_env env = { + .sd = sd, + .dst_cpu = target_cpu, + .dst_rq = target_rq, + .src_cpu = busiest_rq->cpu, + .src_rq = busiest_rq, + .idle = CPU_IDLE, + .flags = LBF_ACTIVE_LB, + }; + + schedstat_inc(sd->alb_count); + update_rq_clock(busiest_rq); + + p = detach_one_task(&env); + if (p) { + schedstat_inc(sd->alb_pushed); + /* Active balancing done, reset the failure counter. */ + sd->nr_balance_failed = 0; + } else { + schedstat_inc(sd->alb_failed); + } + } + rcu_read_unlock(); +out_unlock: + busiest_rq->active_balance = 0; + rq_unlock(busiest_rq, &rf); + + if (p) + attach_one_task(target_rq, p); + + local_irq_enable(); + + return 0; +} + +static DEFINE_SPINLOCK(balancing); + +/* + * Scale the max load_balance interval with the number of CPUs in the system. + * This trades load-balance latency on larger machines for less cross talk. + */ +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. + * + * Balancing parameters are set up in init_sched_domains. + */ +static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) +{ + int continue_balancing = 1; + int cpu = rq->cpu; + int busy = idle != CPU_IDLE && !sched_idle_cpu(cpu); + unsigned long interval; + struct sched_domain *sd; + /* Earliest time when we have to do rebalance again */ + unsigned long next_balance = jiffies + 60*HZ; + int update_next_balance = 0; + int need_serialize, need_decay = 0; + u64 max_cost = 0; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + /* + * Decay the newidle max times here because this is a regular + * visit to all the domains. + */ + need_decay = update_newidle_cost(sd, 0); + max_cost += sd->max_newidle_lb_cost; + + /* + * Stop the load balance at this level. There is another + * CPU in our sched group which is doing load balancing more + * actively. + */ + if (!continue_balancing) { + if (need_decay) + continue; + break; + } + + interval = get_sd_balance_interval(sd, busy); + + need_serialize = sd->flags & SD_SERIALIZE; + if (need_serialize) { + if (!spin_trylock(&balancing)) + goto out; + } + + if (time_after_eq(jiffies, sd->last_balance + interval)) { + if (load_balance(cpu, rq, sd, idle, &continue_balancing)) { + /* + * The LBF_DST_PINNED logic could have changed + * env->dst_cpu, so we can't know our idle + * state even if we migrated tasks. Update it. + */ + idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; + busy = idle != CPU_IDLE && !sched_idle_cpu(cpu); + } + sd->last_balance = jiffies; + interval = get_sd_balance_interval(sd, busy); + } + if (need_serialize) + spin_unlock(&balancing); +out: + if (time_after(next_balance, sd->last_balance + interval)) { + next_balance = sd->last_balance + interval; + update_next_balance = 1; + } + } + if (need_decay) { + /* + * Ensure the rq-wide value also decays but keep it at a + * reasonable floor to avoid funnies with rq->avg_idle. + */ + rq->max_idle_balance_cost = + max((u64)sysctl_sched_migration_cost, max_cost); + } + rcu_read_unlock(); + + /* + * 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 + * updated. + */ + if (likely(update_next_balance)) + rq->next_balance = next_balance; + +} + +static inline int on_null_domain(struct rq *rq) +{ + return unlikely(!rcu_dereference_sched(rq->sd)); +} + +#ifdef CONFIG_NO_HZ_COMMON +/* + * idle load balancing details + * - 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_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; + + if (idle_cpu(ilb)) + return ilb; + } + + return nr_cpu_ids; +} + +/* + * Kick a CPU to do the nohz balancing, if it is time for it. We pick any + * idle CPU in the HK_TYPE_MISC housekeeping set (if there is one). + */ +static void kick_ilb(unsigned int flags) +{ + int ilb_cpu; + + /* + * 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; + + /* + * 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_call_function_single_async(ilb_cpu, &cpu_rq(ilb_cpu)->nohz_csd); +} + +/* + * Current decision point for kicking the idle load balancer in the presence + * of idle CPUs in the system. + */ +static void nohz_balancer_kick(struct rq *rq) +{ + unsigned long now = jiffies; + struct sched_domain_shared *sds; + struct sched_domain *sd; + int nr_busy, i, cpu = rq->cpu; + unsigned int flags = 0; + + if (unlikely(rq->idle_balance)) + return; + + /* + * We may be recently in ticked or tickless idle mode. At the first + * busy tick after returning from idle, we will update the busy stats. + */ + nohz_balance_exit_idle(rq); + + /* + * None are in tickless mode and hence no need for NOHZ idle load + * balancing. + */ + if (likely(!atomic_read(&nohz.nr_cpus))) + return; + + if (READ_ONCE(nohz.has_blocked) && + time_after(now, READ_ONCE(nohz.next_blocked))) + flags = NOHZ_STATS_KICK; + + if (time_before(now, nohz.next_balance)) + goto out; + + if (rq->nr_running >= 2) { + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; + goto out; + } + + rcu_read_lock(); + + sd = rcu_dereference(rq->sd); + if (sd) { + /* + * If there's a CFS task and the current CPU has reduced + * capacity; kick the ILB to see if there's a better CPU to run + * on. + */ + if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) { + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; + goto unlock; + } + } + + sd = rcu_dereference(per_cpu(sd_asym_packing, cpu)); + if (sd) { + /* + * When ASYM_PACKING; see if there's a more preferred CPU + * currently idle; in which case, kick the ILB to move tasks + * around. + */ + for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { + if (sched_asym_prefer(i, cpu)) { + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; + goto unlock; + } + } + } + + sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, cpu)); + if (sd) { + /* + * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU + * to run the misfit task on. + */ + if (check_misfit_status(rq, sd)) { + flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; + goto unlock; + } + + /* + * For asymmetric systems, we do not want to nicely balance + * cache use, instead we want to embrace asymmetry and only + * ensure tasks have enough CPU capacity. + * + * Skip the LLC logic because it's not relevant in that case. + */ + goto unlock; + } + + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) { + /* + * If there is an imbalance between LLC domains (IOW we could + * increase the overall cache use), we need some less-loaded LLC + * domain to pull some load. Likewise, we may need to spread + * load within the current LLC domain (e.g. packed SMT cores but + * other CPUs are idle). We can't really know from here how busy + * the others are - so just get a nohz balance going if it looks + * like this LLC domain has tasks we could move. + */ + nr_busy = atomic_read(&sds->nr_busy_cpus); + if (nr_busy > 1) { + 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); +} + +static void set_cpu_sd_state_busy(int cpu) +{ + struct sched_domain *sd; + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_llc, cpu)); + + if (!sd || !sd->nohz_idle) + goto unlock; + sd->nohz_idle = 0; + + atomic_inc(&sd->shared->nr_busy_cpus); +unlock: + rcu_read_unlock(); +} + +void nohz_balance_exit_idle(struct rq *rq) +{ + SCHED_WARN_ON(rq != this_rq()); + + if (likely(!rq->nohz_tick_stopped)) + return; + + rq->nohz_tick_stopped = 0; + cpumask_clear_cpu(rq->cpu, nohz.idle_cpus_mask); + atomic_dec(&nohz.nr_cpus); + + set_cpu_sd_state_busy(rq->cpu); +} + +static void set_cpu_sd_state_idle(int cpu) +{ + struct sched_domain *sd; + + rcu_read_lock(); + sd = rcu_dereference(per_cpu(sd_llc, cpu)); + + if (!sd || sd->nohz_idle) + goto unlock; + sd->nohz_idle = 1; + + atomic_dec(&sd->shared->nr_busy_cpus); +unlock: + rcu_read_unlock(); +} + +/* + * This routine will record that the CPU is going idle with tick stopped. + * This info will be used in performing idle load balancing in the future. + */ +void nohz_balance_enter_idle(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + SCHED_WARN_ON(cpu != smp_processor_id()); + + /* If this CPU is going down, then nothing needs to be done: */ + if (!cpu_active(cpu)) + return; + + /* Spare idle load balancing on CPUs that don't want to be disturbed: */ + if (!housekeeping_cpu(cpu, HK_TYPE_SCHED)) + return; + + /* + * Can be set safely without rq->lock held + * If a clear happens, it will have evaluated last additions because + * rq->lock is held during the check and the clear + */ + rq->has_blocked_load = 1; + + /* + * The tick is still stopped but load could have been added in the + * meantime. We set the nohz.has_blocked flag to trig a check of the + * *_avg. The CPU is already part of nohz.idle_cpus_mask so the clear + * of nohz.has_blocked can only happen after checking the new load + */ + if (rq->nohz_tick_stopped) + goto out; + + /* If we're a completely isolated CPU, we don't play: */ + if (on_null_domain(rq)) + return; + + rq->nohz_tick_stopped = 1; + + cpumask_set_cpu(cpu, nohz.idle_cpus_mask); + atomic_inc(&nohz.nr_cpus); + + /* + * Ensures that if nohz_idle_balance() fails to observe our + * @idle_cpus_mask store, it must observe the @has_blocked + * 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 + * enable the periodic update of the load of idle cpus + */ + 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. + */ +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; + unsigned long next_balance = now + 60*HZ; + bool has_blocked_load = false; + int update_next_balance = 0; + int this_cpu = this_rq->cpu; + int balance_cpu; + struct rq *rq; + + SCHED_WARN_ON((flags & NOHZ_KICK_MASK) == NOHZ_BALANCE_KICK); + + /* + * 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 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. + */ + 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 + * store from nohz_balance_enter_idle(). + */ + smp_mb(); + + /* + * 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; + + /* + * If this CPU gets work to do, stop the load balancing + * work being done for other CPUs. Next load + * balancing owner will pick it up. + */ + if (need_resched()) { + 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); + + if (flags & NOHZ_STATS_KICK) + has_blocked_load |= update_nohz_stats(rq); + + /* + * If time for next balance is due, + * do the balance. + */ + if (time_after_eq(jiffies, rq->next_balance)) { + struct rq_flags rf; + + rq_lock_irqsave(rq, &rf); + update_rq_clock(rq); + rq_unlock_irqrestore(rq, &rf); + + if (flags & NOHZ_BALANCE_KICK) + rebalance_domains(rq, CPU_IDLE); + } + + if (time_after(next_balance, rq->next_balance)) { + next_balance = rq->next_balance; + update_next_balance = 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 + * updated. + */ + if (likely(update_next_balance)) + nohz.next_balance = next_balance; + + 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); +} + +/* + * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the + * rebalancing for all the cpus for whom scheduler ticks are stopped. + */ +static bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) +{ + unsigned int flags = this_rq->nohz_idle_balance; + + if (!flags) + return false; + + this_rq->nohz_idle_balance = 0; + + if (idle != CPU_IDLE) + return false; + + _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; + + /* + * This CPU doesn't want to be disturbed by scheduler + * housekeeping + */ + if (!housekeeping_cpu(this_cpu, HK_TYPE_SCHED)) + return; + + /* Will wake up very soon. No time for doing anything else*/ + if (this_rq->avg_idle < sysctl_sched_migration_cost) + return; + + /* Don't need to update blocked load of idle CPUs*/ + if (!READ_ONCE(nohz.has_blocked) || + time_before(jiffies, READ_ONCE(nohz.next_blocked))) + return; + + /* + * Set the need to trigger ILB in order to update blocked load + * before entering idle state. + */ + atomic_or(NOHZ_NEWILB_KICK, nohz_flags(this_cpu)); +} + +#else /* !CONFIG_NO_HZ_COMMON */ +static inline void nohz_balancer_kick(struct rq *rq) { } + +static inline bool nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) +{ + return false; +} + +static inline void nohz_newidle_balance(struct rq *this_rq) { } +#endif /* CONFIG_NO_HZ_COMMON */ + +/* + * newidle_balance is called by schedule() if this_cpu is about to become + * idle. Attempts to pull tasks from other CPUs. + * + * Returns: + * < 0 - we released the lock and there are !fair tasks present + * 0 - failed, no new tasks + * > 0 - success, new (fair) tasks present + */ +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; + + 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. + */ + this_rq->idle_stamp = rq_clock(this_rq); + + /* + * Do not pull tasks towards !active CPUs... + */ + if (!cpu_active(this_cpu)) + return 0; + + /* + * This is OK, because current is on_cpu, which avoids it being picked + * for load-balance and preemption/IRQs are still disabled avoiding + * further scheduler activity on it and we're being very careful to + * re-start the picking loop. + */ + rq_unpin_lock(this_rq, rf); + + 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)) { + + if (sd) + update_next_balance(sd, &next_balance); + rcu_read_unlock(); + + goto out; + } + rcu_read_unlock(); + + 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 domain_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) { + + pulled_task = load_balance(this_cpu, this_rq, + sd, CPU_NEWLY_IDLE, + &continue_balancing); + + t1 = sched_clock_cpu(this_cpu); + domain_cost = t1 - t0; + update_newidle_cost(sd, domain_cost); + + curr_cost += domain_cost; + t0 = t1; + } + + /* + * Stop searching for tasks to pull if there are + * now runnable tasks on this rq. + */ + if (pulled_task || this_rq->nr_running > 0 || + this_rq->ttwu_pending) + break; + } + rcu_read_unlock(); + + raw_spin_rq_lock(this_rq); + + if (curr_cost > this_rq->max_idle_balance_cost) + this_rq->max_idle_balance_cost = curr_cost; + + /* + * While browsing the domains, we released the rq lock, a task could + * have been enqueued in the meantime. Since we're not going idle, + * pretend we pulled a task. + */ + if (this_rq->cfs.h_nr_running && !pulled_task) + pulled_task = 1; + + /* 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); + + return pulled_task; +} + +/* + * run_rebalance_domains is triggered when needed from the scheduler tick. + * Also triggered for nohz idle balancing (with nohz_balancing_kick set). + */ +static __latent_entropy void run_rebalance_domains(struct softirq_action *h) +{ + struct rq *this_rq = this_rq(); + enum cpu_idle_type idle = this_rq->idle_balance ? + CPU_IDLE : CPU_NOT_IDLE; + + /* + * If this CPU has a pending nohz_balance_kick, then do the + * balancing on behalf of the other idle CPUs whose ticks are + * stopped. Do nohz_idle_balance *before* rebalance_domains to + * give the idle CPUs a chance to load balance. Else we may + * load balance only within the local sched_domain hierarchy + * and abort nohz_idle_balance altogether if we pull some load. + */ + if (nohz_idle_balance(this_rq, idle)) + return; + + /* normal load balance */ + update_blocked_averages(this_rq->cpu); + rebalance_domains(this_rq, idle); +} + +/* + * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. + */ +void trigger_load_balance(struct rq *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)) + raise_softirq(SCHED_SOFTIRQ); + + nohz_balancer_kick(rq); +} + +static void rq_online_fair(struct rq *rq) +{ + update_sysctl(); + + update_runtime_enabled(rq); +} + +static void rq_offline_fair(struct rq *rq) +{ + update_sysctl(); + + /* Ensure any throttled groups are reachable by pick_next_task */ + unthrottle_offline_cfs_rqs(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. + * + * NOTE: This function can be called remotely by the tick offload that + * goes along full dynticks. Therefore no local assumption can be made + * and everything must be accessed through the @rq and @curr passed in + * parameters. + */ +static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &curr->se; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + entity_tick(cfs_rq, se, queued); + } + + if (static_branch_unlikely(&sched_numa_balancing)) + task_tick_numa(rq, curr); + + update_misfit_status(curr, rq); + update_overutilized_status(task_rq(curr)); + + task_tick_core(rq, curr); +} + +/* + * called on fork with the child task as argument from the parent's context + * - child not yet on the tasklist + * - preemption disabled + */ +static void task_fork_fair(struct task_struct *p) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se = &p->se, *curr; + struct rq *rq = this_rq(); + struct rq_flags rf; + + rq_lock(rq, &rf); + update_rq_clock(rq); + + cfs_rq = task_cfs_rq(current); + curr = cfs_rq->curr; + if (curr) { + update_curr(cfs_rq); + se->vruntime = curr->vruntime; + } + place_entity(cfs_rq, se, 1); + + if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) { + /* + * Upon rescheduling, sched_class::put_prev_task() will place + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); + resched_curr(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; + rq_unlock(rq, &rf); +} + +/* + * Priority of the task has changed. Check to see if we preempt + * the current task. + */ +static void +prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio) +{ + if (!task_on_rq_queued(p)) + return; + + if (rq->cfs.nr_running == 1) + return; + + /* + * Reschedule if we are currently running on this runqueue and + * our priority decreased, or if we are not currently running on + * this runqueue and our priority is higher than the current's + */ + if (task_current(rq, p)) { + if (p->prio > oldprio) + resched_curr(rq); + } else + check_preempt_curr(rq, p, 0); +} + +static inline bool vruntime_normalized(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + + /* + * In both the TASK_ON_RQ_QUEUED and TASK_ON_RQ_MIGRATING cases, + * the dequeue_entity(.flags=0) will already have normalized the + * vruntime. + */ + if (p->on_rq) + return true; + + /* + * When !on_rq, vruntime of the task has usually NOT been normalized. + * But there are some cases where it has already been normalized: + * + * - A forked child which is waiting for being woken up by + * wake_up_new_task(). + * - A task which has been woken up by try_to_wake_up() and + * waiting for actually being woken up by sched_ttwu_pending(). + */ + if (!se->sum_exec_runtime || + (READ_ONCE(p->__state) == TASK_WAKING && p->sched_remote_wakeup)) + return true; + + return false; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * Propagate the changes of the sched_entity across the tg tree to make it + * visible to the root + */ +static void propagate_entity_cfs_rq(struct sched_entity *se) +{ + 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; + + 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; + + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); + } +} +#else +static void propagate_entity_cfs_rq(struct sched_entity *se) { } +#endif + +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); + propagate_entity_cfs_rq(se); +} + +static void attach_entity_cfs_rq(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + /* 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); + propagate_entity_cfs_rq(se); +} + +static void detach_task_cfs_rq(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + if (!vruntime_normalized(p)) { + /* + * Fix up our vruntime so that the current sleep doesn't + * cause 'unlimited' sleep bonus. + */ + place_entity(cfs_rq, se, 0); + se->vruntime -= cfs_rq->min_vruntime; + } + + detach_entity_cfs_rq(se); +} + +static void attach_task_cfs_rq(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + attach_entity_cfs_rq(se); + + if (!vruntime_normalized(p)) + se->vruntime += cfs_rq->min_vruntime; +} + +static void switched_from_fair(struct rq *rq, struct task_struct *p) +{ + detach_task_cfs_rq(p); +} + +static void switched_to_fair(struct rq *rq, struct task_struct *p) +{ + attach_task_cfs_rq(p); + + if (task_on_rq_queued(p)) { + /* + * We were most likely switched from sched_rt, so + * kick off the schedule if running, otherwise just see + * if we can still preempt the current task. + */ + if (task_current(rq, p)) + resched_curr(rq); + else + check_preempt_curr(rq, p, 0); + } +} + +/* Account for a task changing its policy or group. + * + * This routine is mostly called to set cfs_rq->curr field when a task + * migrates between groups/classes. + */ +static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) +{ + struct sched_entity *se = &p->se; + +#ifdef CONFIG_SMP + if (task_on_rq_queued(p)) { + /* + * Move the next running task to the front of the list, so our + * cfs_tasks list becomes MRU one. + */ + list_move(&se->group_node, &rq->cfs_tasks); + } +#endif + + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + set_next_entity(cfs_rq, se); + /* ensure bandwidth has been allocated on our new cfs_rq */ + account_cfs_rq_runtime(cfs_rq, 0); + } +} + +void init_cfs_rq(struct cfs_rq *cfs_rq) +{ + cfs_rq->tasks_timeline = RB_ROOT_CACHED; + 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_change_group_fair(struct task_struct *p) +{ + /* + * 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; + + detach_task_cfs_rq(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); +} + +void free_fair_sched_group(struct task_group *tg) +{ + int i; + + for_each_possible_cpu(i) { + if (tg->cfs_rq) + kfree(tg->cfs_rq[i]); + if (tg->se) + kfree(tg->se[i]); + } + + kfree(tg->cfs_rq); + kfree(tg->se); +} + +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + struct sched_entity *se; + struct cfs_rq *cfs_rq; + int i; + + tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL); + if (!tg->cfs_rq) + goto err; + tg->se = kcalloc(nr_cpu_ids, sizeof(se), GFP_KERNEL); + if (!tg->se) + goto err; + + tg->shares = NICE_0_LOAD; + + init_cfs_bandwidth(tg_cfs_bandwidth(tg)); + + for_each_possible_cpu(i) { + cfs_rq = kzalloc_node(sizeof(struct cfs_rq), + GFP_KERNEL, cpu_to_node(i)); + if (!cfs_rq) + goto err; + + se = kzalloc_node(sizeof(struct sched_entity_stats), + GFP_KERNEL, cpu_to_node(i)); + if (!se) + goto err_free_rq; + + init_cfs_rq(cfs_rq); + init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); + init_entity_runnable_average(se); + } + + return 1; + +err_free_rq: + kfree(cfs_rq); +err: + return 0; +} + +void online_fair_sched_group(struct task_group *tg) +{ + struct sched_entity *se; + struct rq_flags rf; + struct rq *rq; + int i; + + for_each_possible_cpu(i) { + rq = cpu_rq(i); + se = tg->se[i]; + rq_lock_irq(rq, &rf); + update_rq_clock(rq); + attach_entity_cfs_rq(se); + sync_throttle(tg, i); + rq_unlock_irq(rq, &rf); + } +} + +void unregister_fair_sched_group(struct task_group *tg) +{ + unsigned long flags; + 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]); + + /* + * Only empty task groups can be destroyed; so we can speculatively + * check on_list without danger of it being re-added. + */ + if (!tg->cfs_rq[cpu]->on_list) + continue; + + rq = cpu_rq(cpu); + + raw_spin_rq_lock_irqsave(rq, flags); + list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); + raw_spin_rq_unlock_irqrestore(rq, flags); + } +} + +void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, + struct sched_entity *se, int cpu, + struct sched_entity *parent) +{ + struct rq *rq = cpu_rq(cpu); + + cfs_rq->tg = tg; + cfs_rq->rq = rq; + init_cfs_rq_runtime(cfs_rq); + + tg->cfs_rq[cpu] = cfs_rq; + tg->se[cpu] = se; + + /* se could be NULL for root_task_group */ + if (!se) + return; + + if (!parent) { + se->cfs_rq = &rq->cfs; + se->depth = 0; + } else { + se->cfs_rq = parent->my_q; + se->depth = parent->depth + 1; + } + + se->my_q = cfs_rq; + /* guarantee group entities always have weight */ + update_load_set(&se->load, NICE_0_LOAD); + se->parent = parent; +} + +static DEFINE_MUTEX(shares_mutex); + +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. + */ + if (!tg->se[0]) + return -EINVAL; + + shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES)); + + if (tg->shares == shares) + return 0; + + tg->shares = shares; + for_each_possible_cpu(i) { + struct rq *rq = cpu_rq(i); + struct sched_entity *se = tg->se[i]; + struct rq_flags rf; + + /* Propagate contribution to hierarchy */ + rq_lock_irqsave(rq, &rf); + update_rq_clock(rq); + for_each_sched_entity(se) { + update_load_avg(cfs_rq_of(se), se, UPDATE_TG); + update_cfs_group(se); + } + rq_unlock_irqrestore(rq, &rf); + } + + 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) { } + +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} + +void online_fair_sched_group(struct task_group *tg) { } + +void unregister_fair_sched_group(struct task_group *tg) { } + +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + +static unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task) +{ + struct sched_entity *se = &task->se; + unsigned int rr_interval = 0; + + /* + * Time slice is 0 for SCHED_OTHER tasks that are on an otherwise + * idle runqueue: + */ + if (rq->cfs.load.weight) + rr_interval = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); + + return rr_interval; +} + +/* + * All the scheduling class methods: + */ +DEFINE_SCHED_CLASS(fair) = { + + .enqueue_task = enqueue_task_fair, + .dequeue_task = dequeue_task_fair, + .yield_task = yield_task_fair, + .yield_to_task = yield_to_task_fair, + + .check_preempt_curr = check_preempt_wakeup, + + .pick_next_task = __pick_next_task_fair, + .put_prev_task = put_prev_task_fair, + .set_next_task = set_next_task_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, + + .rq_online = rq_online_fair, + .rq_offline = rq_offline_fair, + + .task_dead = task_dead_fair, + .set_cpus_allowed = set_cpus_allowed_common, +#endif + + .task_tick = task_tick_fair, + .task_fork = task_fork_fair, + + .prio_changed = prio_changed_fair, + .switched_from = switched_from_fair, + .switched_to = switched_to_fair, + + .get_rr_interval = get_rr_interval_fair, + + .update_curr = update_curr_fair, + +#ifdef CONFIG_FAIR_GROUP_SCHED + .task_change_group = task_change_group_fair, +#endif + +#ifdef CONFIG_UCLAMP_TASK + .uclamp_enabled = 1, +#endif +}; + +#ifdef CONFIG_SCHED_DEBUG +void print_cfs_stats(struct seq_file *m, int cpu) +{ + struct cfs_rq *cfs_rq, *pos; + + rcu_read_lock(); + for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos) + print_cfs_rq(m, cpu, cfs_rq); + rcu_read_unlock(); +} + +#ifdef CONFIG_NUMA_BALANCING +void show_numa_stats(struct task_struct *p, struct seq_file *m) +{ + int node; + unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0; + struct numa_group *ng; + + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + for_each_online_node(node) { + if (p->numa_faults) { + tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)]; + tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)]; + } + if (ng) { + gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)], + gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)]; + } + print_numa_stats(m, node, tsf, tpf, gsf, gpf); + } + rcu_read_unlock(); +} +#endif /* CONFIG_NUMA_BALANCING */ +#endif /* CONFIG_SCHED_DEBUG */ + +__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 + nohz.next_balance = jiffies; + nohz.next_blocked = jiffies; + zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); +#endif +#endif /* SMP */ + +} |