X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsched_fair.c;h=3e1fd96c6cf9cef8de27f7ba41dad905986f1959;hb=830ec0458c390f29c6c99e1ff7feab9e36368d12;hp=342000b31ad65a89607ef1b783ac2f6057dca040;hpb=8f48894fcc89ddec62e1762f73a0825793e59e91;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 342000b..3e1fd96 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -21,10 +21,11 @@ */ #include +#include /* * Targeted preemption latency for CPU-bound tasks: - * (default: 20ms * (1 + ilog(ncpus)), units: nanoseconds) + * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds) * * NOTE: this latency value is not the same as the concept of * 'timeslice length' - timeslices in CFS are of variable length @@ -34,13 +35,27 @@ * (to see the precise effective timeslice length of your workload, * run vmstat and monitor the context-switches (cs) field) */ -unsigned int sysctl_sched_latency = 20000000ULL; +unsigned int sysctl_sched_latency = 5000000ULL; +unsigned int normalized_sysctl_sched_latency = 5000000ULL; + +/* + * The initial- and re-scaling of tunables is configurable + * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus)) + * + * Options are: + * SCHED_TUNABLESCALING_NONE - unscaled, always *1 + * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus) + * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus + */ +enum sched_tunable_scaling sysctl_sched_tunable_scaling + = SCHED_TUNABLESCALING_LOG; /* * Minimal preemption granularity for CPU-bound tasks: - * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds) + * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_min_granularity = 4000000ULL; +unsigned int sysctl_sched_min_granularity = 1000000ULL; +unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL; /* * is kept at sysctl_sched_latency / sysctl_sched_min_granularity @@ -48,10 +63,10 @@ unsigned int sysctl_sched_min_granularity = 4000000ULL; static unsigned int sched_nr_latency = 5; /* - * After fork, child runs first. (default) If set to 0 then + * After fork, child runs first. If set to 0 (default) then * parent will (try to) run first. */ -const_debug unsigned int sysctl_sched_child_runs_first = 1; +unsigned int sysctl_sched_child_runs_first __read_mostly; /* * sys_sched_yield() compat mode @@ -63,13 +78,14 @@ unsigned int __read_mostly sysctl_sched_compat_yield; /* * SCHED_OTHER wake-up granularity. - * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds) + * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still * have immediate wakeup/sleep latencies. */ -unsigned int sysctl_sched_wakeup_granularity = 5000000UL; +unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; const_debug unsigned int sysctl_sched_migration_cost = 500000UL; @@ -383,11 +399,12 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) */ #ifdef CONFIG_SCHED_DEBUG -int sched_nr_latency_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, +int sched_proc_update_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) { - int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + int factor = get_update_sysctl_factor(); if (ret || !write) return ret; @@ -395,6 +412,14 @@ int sched_nr_latency_handler(struct ctl_table *table, int write, 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); + WRT_SYSCTL(sched_shares_ratelimit); +#undef WRT_SYSCTL + return 0; } #endif @@ -485,6 +510,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr, curr->sum_exec_runtime += delta_exec; schedstat_add(cfs_rq, exec_clock, delta_exec); delta_exec_weighted = calc_delta_fair(delta_exec, curr); + curr->vruntime += delta_exec_weighted; update_min_vruntime(cfs_rq); } @@ -513,6 +539,7 @@ static void update_curr(struct cfs_rq *cfs_rq) if (entity_is_task(curr)) { struct task_struct *curtask = task_of(curr); + trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime); cpuacct_charge(curtask, delta_exec); account_group_exec_runtime(curtask, delta_exec); } @@ -545,6 +572,12 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) schedstat_set(se->wait_count, se->wait_count + 1); schedstat_set(se->wait_sum, se->wait_sum + rq_of(cfs_rq)->clock - se->wait_start); +#ifdef CONFIG_SCHEDSTATS + if (entity_is_task(se)) { + trace_sched_stat_wait(task_of(se), + rq_of(cfs_rq)->clock - se->wait_start); + } +#endif schedstat_set(se->wait_start, 0); } @@ -636,8 +669,10 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->sleep_start = 0; se->sum_sleep_runtime += delta; - if (tsk) + if (tsk) { account_scheduler_latency(tsk, delta >> 10, 1); + trace_sched_stat_sleep(tsk, delta); + } } if (se->block_start) { u64 delta = rq_of(cfs_rq)->clock - se->block_start; @@ -652,6 +687,12 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->sum_sleep_runtime += delta; if (tsk) { + if (tsk->in_iowait) { + se->iowait_sum += delta; + se->iowait_count++; + trace_sched_stat_iowait(tsk, delta); + } + /* * Blocking time is in units of nanosecs, so shift by * 20 to get a milliseconds-range estimation of the @@ -695,42 +736,56 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) if (initial && sched_feat(START_DEBIT)) vruntime += sched_vslice(cfs_rq, se); - if (!initial) { - /* sleeps upto a single latency don't count. */ - if (sched_feat(NEW_FAIR_SLEEPERS)) { - unsigned long thresh = sysctl_sched_latency; + /* sleeps up to a single latency don't count. */ + if (!initial && sched_feat(FAIR_SLEEPERS)) { + unsigned long thresh = sysctl_sched_latency; - /* - * Convert the sleeper threshold into virtual time. - * SCHED_IDLE is a special sub-class. We care about - * fairness only relative to other SCHED_IDLE tasks, - * all of which have the same weight. - */ - if (sched_feat(NORMALIZED_SLEEPER) && - (!entity_is_task(se) || - task_of(se)->policy != SCHED_IDLE)) - thresh = calc_delta_fair(thresh, se); + /* + * Convert the sleeper threshold into virtual time. + * SCHED_IDLE is a special sub-class. We care about + * fairness only relative to other SCHED_IDLE tasks, + * all of which have the same weight. + */ + if (sched_feat(NORMALIZED_SLEEPER) && (!entity_is_task(se) || + task_of(se)->policy != SCHED_IDLE)) + thresh = calc_delta_fair(thresh, se); - vruntime -= thresh; - } + /* + * Halve their sleep time's effect, to allow + * for a gentler effect of sleepers: + */ + if (sched_feat(GENTLE_FAIR_SLEEPERS)) + thresh >>= 1; - /* ensure we never gain time by being placed backwards. */ - vruntime = max_vruntime(se->vruntime, vruntime); + vruntime -= thresh; } + /* ensure we never gain time by being placed backwards. */ + vruntime = max_vruntime(se->vruntime, vruntime); + se->vruntime = vruntime; } +#define ENQUEUE_WAKEUP 1 +#define ENQUEUE_MIGRATE 2 + static void -enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup) +enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { /* + * Update the normalized vruntime before updating min_vruntime + * through callig update_curr(). + */ + if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATE)) + se->vruntime += cfs_rq->min_vruntime; + + /* * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); account_entity_enqueue(cfs_rq, se); - if (wakeup) { + if (flags & ENQUEUE_WAKEUP) { place_entity(cfs_rq, se, 0); enqueue_sleeper(cfs_rq, se); } @@ -743,10 +798,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup) static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (cfs_rq->last == se) + if (!se || cfs_rq->last == se) cfs_rq->last = NULL; - if (cfs_rq->next == se) + if (!se || cfs_rq->next == se) cfs_rq->next = NULL; } @@ -784,6 +839,14 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) __dequeue_entity(cfs_rq, se); account_entity_dequeue(cfs_rq, se); update_min_vruntime(cfs_rq); + + /* + * Normalize the entity after updating the min_vruntime because the + * update can refer to the ->curr item and we need to reflect this + * movement in our normalized position. + */ + if (!sleep) + se->vruntime -= cfs_rq->min_vruntime; } /* @@ -803,6 +866,26 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) * 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 (!sched_feat(WAKEUP_PREEMPT)) + return; + + if (delta_exec < sysctl_sched_min_granularity) + return; + + if (cfs_rq->nr_running > 1) { + struct sched_entity *se = __pick_next_entity(cfs_rq); + s64 delta = curr->vruntime - se->vruntime; + + if (delta > ideal_runtime) + resched_task(rq_of(cfs_rq)->curr); } } @@ -842,12 +925,18 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se); static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq) { struct sched_entity *se = __pick_next_entity(cfs_rq); + struct sched_entity *left = se; + + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) + se = cfs_rq->next; - if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1) - return cfs_rq->next; + /* + * Prefer last buddy, try to return the CPU to a preempted task. + */ + if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) + se = cfs_rq->last; - if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1) - return cfs_rq->last; + clear_buddies(cfs_rq, se); return se; } @@ -964,17 +1053,24 @@ static inline void hrtick_update(struct rq *rq) * 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 wakeup) +static void +enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + int flags = 0; + + if (wakeup) + flags |= ENQUEUE_WAKEUP; + if (p->state == TASK_WAKING) + flags |= ENQUEUE_MIGRATE; for_each_sched_entity(se) { if (se->on_rq) break; cfs_rq = cfs_rq_of(se); - enqueue_entity(cfs_rq, se, wakeup); - wakeup = 1; + enqueue_entity(cfs_rq, se, flags); + flags = ENQUEUE_WAKEUP; } hrtick_update(rq); @@ -1048,84 +1144,15 @@ static void yield_task_fair(struct rq *rq) se->vruntime = rightmost->vruntime + 1; } -/* - * wake_idle() will wake a task on an idle cpu if task->cpu is - * not idle and an idle cpu is available. The span of cpus to - * search starts with cpus closest then further out as needed, - * so we always favor a closer, idle cpu. - * Domains may include CPUs that are not usable for migration, - * hence we need to mask them out (rq->rd->online) - * - * Returns the CPU we should wake onto. - */ -#if defined(ARCH_HAS_SCHED_WAKE_IDLE) - -#define cpu_rd_active(cpu, rq) cpumask_test_cpu(cpu, rq->rd->online) +#ifdef CONFIG_SMP -static int wake_idle(int cpu, struct task_struct *p) +static void task_waking_fair(struct rq *rq, struct task_struct *p) { - struct sched_domain *sd; - int i; - unsigned int chosen_wakeup_cpu; - int this_cpu; - struct rq *task_rq = task_rq(p); - - /* - * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu - * are idle and this is not a kernel thread and this task's affinity - * allows it to be moved to preferred cpu, then just move! - */ - - this_cpu = smp_processor_id(); - chosen_wakeup_cpu = - cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu; - - if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP && - idle_cpu(cpu) && idle_cpu(this_cpu) && - p->mm && !(p->flags & PF_KTHREAD) && - cpu_isset(chosen_wakeup_cpu, p->cpus_allowed)) - return chosen_wakeup_cpu; - - /* - * If it is idle, then it is the best cpu to run this task. - * - * This cpu is also the best, if it has more than one task already. - * Siblings must be also busy(in most cases) as they didn't already - * pickup the extra load from this cpu and hence we need not check - * sibling runqueue info. This will avoid the checks and cache miss - * penalities associated with that. - */ - if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1) - return cpu; + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); - for_each_domain(cpu, sd) { - if ((sd->flags & SD_WAKE_IDLE) - || ((sd->flags & SD_WAKE_IDLE_FAR) - && !task_hot(p, task_rq->clock, sd))) { - for_each_cpu_and(i, sched_domain_span(sd), - &p->cpus_allowed) { - if (cpu_rd_active(i, task_rq) && idle_cpu(i)) { - if (i != task_cpu(p)) { - schedstat_inc(p, - se.nr_wakeups_idle); - } - return i; - } - } - } else { - break; - } - } - return cpu; -} -#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/ -static inline int wake_idle(int cpu, struct task_struct *p) -{ - return cpu; + se->vruntime -= cfs_rq->min_vruntime; } -#endif - -#ifdef CONFIG_SMP #ifdef CONFIG_FAIR_GROUP_SCHED /* @@ -1211,25 +1238,34 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu, #endif -static int -wake_affine(struct sched_domain *this_sd, struct rq *this_rq, - struct task_struct *p, int prev_cpu, int this_cpu, int sync, - int idx, unsigned long load, unsigned long this_load, - unsigned int imbalance) +static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) { - struct task_struct *curr = this_rq->curr; - struct task_group *tg; - unsigned long tl = this_load; + struct task_struct *curr = current; + unsigned long this_load, load; + int idx, this_cpu, prev_cpu; unsigned long tl_per_task; + unsigned int imbalance; + struct task_group *tg; unsigned long weight; int balanced; - if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS)) - return 0; + idx = sd->wake_idx; + this_cpu = smp_processor_id(); + prev_cpu = task_cpu(p); + load = source_load(prev_cpu, idx); + this_load = target_load(this_cpu, idx); - if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost || - p->se.avg_overlap > sysctl_sched_migration_cost)) - sync = 0; + if (sync) { + if (sched_feat(SYNC_LESS) && + (curr->se.avg_overlap > sysctl_sched_migration_cost || + p->se.avg_overlap > sysctl_sched_migration_cost)) + sync = 0; + } else { + if (sched_feat(SYNC_MORE) && + (curr->se.avg_overlap < sysctl_sched_migration_cost && + p->se.avg_overlap < sysctl_sched_migration_cost)) + sync = 1; + } /* * If sync wakeup then subtract the (maximum possible) @@ -1240,14 +1276,26 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq, tg = task_group(current); weight = current->se.load.weight; - tl += effective_load(tg, this_cpu, -weight, -weight); + this_load += effective_load(tg, this_cpu, -weight, -weight); load += effective_load(tg, prev_cpu, 0, -weight); } tg = task_group(p); weight = p->se.load.weight; - balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <= + imbalance = 100 + (sd->imbalance_pct - 100) / 2; + + /* + * In low-load situations, where prev_cpu is idle and this_cpu is idle + * due to the sync cause above having dropped this_load to 0, we'll + * always have an imbalance, but there's really nothing you can do + * about that, so that's good too. + * + * Otherwise check if either cpus are near enough in load to allow this + * task to be woken on this_cpu. + */ + balanced = !this_load || + 100*(this_load + effective_load(tg, this_cpu, weight, weight)) <= imbalance*(load + effective_load(tg, prev_cpu, 0, weight)); /* @@ -1261,14 +1309,15 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq, schedstat_inc(p, se.nr_wakeups_affine_attempts); tl_per_task = cpu_avg_load_per_task(this_cpu); - if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <= - tl_per_task)) { + if (balanced || + (this_load <= load && + this_load + target_load(prev_cpu, idx) <= tl_per_task)) { /* * This domain has SD_WAKE_AFFINE and * p is cache cold in this domain, and * there is no bad imbalance. */ - schedstat_inc(this_sd, ttwu_move_affine); + schedstat_inc(sd, ttwu_move_affine); schedstat_inc(p, se.nr_wakeups_affine); return 1; @@ -1276,67 +1325,269 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq, return 0; } -static int select_task_rq_fair(struct task_struct *p, int sync) +/* + * find_idlest_group finds and returns the least busy CPU group within the + * domain. + */ +static struct sched_group * +find_idlest_group(struct sched_domain *sd, struct task_struct *p, + int this_cpu, int load_idx) { - struct sched_domain *sd, *this_sd = NULL; - int prev_cpu, this_cpu, new_cpu; - unsigned long load, this_load; - struct rq *this_rq; - unsigned int imbalance; - int idx; + struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups; + unsigned long min_load = ULONG_MAX, this_load = 0; + int imbalance = 100 + (sd->imbalance_pct-100)/2; - prev_cpu = task_cpu(p); - this_cpu = smp_processor_id(); - this_rq = cpu_rq(this_cpu); - new_cpu = prev_cpu; + do { + unsigned long load, avg_load; + int local_group; + int i; + + /* Skip over this group if it has no CPUs allowed */ + if (!cpumask_intersects(sched_group_cpus(group), + &p->cpus_allowed)) + continue; + + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); + + /* Tally up the load of all CPUs in the group */ + avg_load = 0; + + for_each_cpu(i, sched_group_cpus(group)) { + /* Bias balancing toward cpus of our domain */ + if (local_group) + load = source_load(i, load_idx); + else + load = target_load(i, load_idx); + + avg_load += load; + } + + /* Adjust by relative CPU power of the group */ + avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power; + + if (local_group) { + this_load = avg_load; + this = group; + } else if (avg_load < min_load) { + min_load = avg_load; + idlest = group; + } + } while (group = group->next, group != sd->groups); + + if (!idlest || 100*this_load < imbalance*min_load) + return NULL; + return idlest; +} + +/* + * find_idlest_cpu - find the idlest cpu among the cpus in group. + */ +static int +find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) +{ + unsigned long load, min_load = ULONG_MAX; + int idlest = -1; + int i; + + /* Traverse only the allowed CPUs */ + for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { + load = weighted_cpuload(i); + + if (load < min_load || (load == min_load && i == this_cpu)) { + min_load = load; + idlest = i; + } + } + + return idlest; +} + +/* + * Try and locate an idle CPU in the sched_domain. + */ +static int +select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target) +{ + int cpu = smp_processor_id(); + int prev_cpu = task_cpu(p); + int i; - if (prev_cpu == this_cpu) - goto out; /* - * 'this_sd' is the first domain that both - * this_cpu and prev_cpu are present in: + * If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE + * test in select_task_rq_fair) and the prev_cpu is idle then that's + * always a better target than the current cpu. */ - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) { - this_sd = sd; + if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running) + return prev_cpu; + + /* + * Otherwise, iterate the domain and find an elegible idle cpu. + */ + for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) { + if (!cpu_rq(i)->cfs.nr_running) { + target = i; break; } } - if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed))) - goto out; + return target; +} - /* - * Check for affine wakeup and passive balancing possibilities. - */ - if (!this_sd) - goto out; +/* + * sched_balance_self: balance the current task (running on cpu) in domains + * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and + * SD_BALANCE_EXEC. + * + * Balance, ie. select the least loaded group. + * + * Returns the target CPU number, or the same CPU if no balancing is needed. + * + * preempt must be disabled. + */ +static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) +{ + struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; + int cpu = smp_processor_id(); + int prev_cpu = task_cpu(p); + int new_cpu = cpu; + int want_affine = 0; + int want_sd = 1; + int sync = wake_flags & WF_SYNC; + + if (sd_flag & SD_BALANCE_WAKE) { + if (sched_feat(AFFINE_WAKEUPS) && + cpumask_test_cpu(cpu, &p->cpus_allowed)) + want_affine = 1; + new_cpu = prev_cpu; + } + + for_each_domain(cpu, tmp) { + if (!(tmp->flags & SD_LOAD_BALANCE)) + continue; - idx = this_sd->wake_idx; + /* + * If power savings logic is enabled for a domain, see if we + * are not overloaded, if so, don't balance wider. + */ + if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) { + unsigned long power = 0; + unsigned long nr_running = 0; + unsigned long capacity; + int i; + + for_each_cpu(i, sched_domain_span(tmp)) { + power += power_of(i); + nr_running += cpu_rq(i)->cfs.nr_running; + } - imbalance = 100 + (this_sd->imbalance_pct - 100) / 2; + capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); - load = source_load(prev_cpu, idx); - this_load = target_load(this_cpu, idx); + if (tmp->flags & SD_POWERSAVINGS_BALANCE) + nr_running /= 2; - if (wake_affine(this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx, - load, this_load, imbalance)) - return this_cpu; + if (nr_running < capacity) + want_sd = 0; + } - /* - * Start passive balancing when half the imbalance_pct - * limit is reached. - */ - if (this_sd->flags & SD_WAKE_BALANCE) { - if (imbalance*this_load <= 100*load) { - schedstat_inc(this_sd, ttwu_move_balance); - schedstat_inc(p, se.nr_wakeups_passive); - return this_cpu; + /* + * While iterating the domains looking for a spanning + * WAKE_AFFINE domain, adjust the affine target to any idle cpu + * in cache sharing domains along the way. + */ + if (want_affine) { + int target = -1; + + /* + * If both cpu and prev_cpu are part of this domain, + * cpu is a valid SD_WAKE_AFFINE target. + */ + if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) + target = cpu; + + /* + * If there's an idle sibling in this domain, make that + * the wake_affine target instead of the current cpu. + */ + if (tmp->flags & SD_SHARE_PKG_RESOURCES) + target = select_idle_sibling(p, tmp, target); + + if (target >= 0) { + if (tmp->flags & SD_WAKE_AFFINE) { + affine_sd = tmp; + want_affine = 0; + } + cpu = target; + } } + + if (!want_sd && !want_affine) + break; + + if (!(tmp->flags & sd_flag)) + continue; + + if (want_sd) + sd = tmp; } -out: - return wake_idle(new_cpu, p); + if (sched_feat(LB_SHARES_UPDATE)) { + /* + * Pick the largest domain to update shares over + */ + tmp = sd; + if (affine_sd && (!tmp || + cpumask_weight(sched_domain_span(affine_sd)) > + cpumask_weight(sched_domain_span(sd)))) + tmp = affine_sd; + + if (tmp) + update_shares(tmp); + } + + if (affine_sd && wake_affine(affine_sd, p, sync)) + return cpu; + + while (sd) { + int load_idx = sd->forkexec_idx; + struct sched_group *group; + int weight; + + if (!(sd->flags & sd_flag)) { + sd = sd->child; + continue; + } + + if (sd_flag & SD_BALANCE_WAKE) + load_idx = sd->wake_idx; + + group = find_idlest_group(sd, p, cpu, load_idx); + if (!group) { + sd = sd->child; + continue; + } + + new_cpu = find_idlest_cpu(group, p, cpu); + if (new_cpu == -1 || 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 = cpumask_weight(sched_domain_span(sd)); + sd = NULL; + for_each_domain(cpu, tmp) { + if (weight <= cpumask_weight(sched_domain_span(tmp))) + break; + if (tmp->flags & sd_flag) + sd = tmp; + } + /* while loop will break here if sd == NULL */ + } + + return new_cpu; } #endif /* CONFIG_SMP */ @@ -1449,18 +1700,16 @@ static void set_next_buddy(struct sched_entity *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 sync) +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 sync = wake_flags & WF_SYNC; + int scale = cfs_rq->nr_running >= sched_nr_latency; - update_curr(cfs_rq); - - if (unlikely(rt_prio(p->prio))) { - resched_task(curr); - return; - } + if (unlikely(rt_prio(p->prio))) + goto preempt; if (unlikely(p->sched_class != &fair_sched_class)) return; @@ -1468,18 +1717,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) if (unlikely(se == pse)) return; - /* - * 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 the idle thread. - */ - if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle)) - set_last_buddy(se); - set_next_buddy(pse); + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) + set_next_buddy(pse); /* * We can come here with TIF_NEED_RESCHED already set from new task @@ -1496,27 +1735,44 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync) return; /* Idle tasks are by definition preempted by everybody. */ - if (unlikely(curr->policy == SCHED_IDLE)) { - resched_task(curr); - return; - } + if (unlikely(curr->policy == SCHED_IDLE)) + goto preempt; - if (!sched_feat(WAKEUP_PREEMPT)) - return; + if (sched_feat(WAKEUP_SYNC) && sync) + goto preempt; + + if (sched_feat(WAKEUP_OVERLAP) && + se->avg_overlap < sysctl_sched_migration_cost && + pse->avg_overlap < sysctl_sched_migration_cost) + goto preempt; - if (sched_feat(WAKEUP_OVERLAP) && (sync || - (se->avg_overlap < sysctl_sched_migration_cost && - pse->avg_overlap < sysctl_sched_migration_cost))) { - resched_task(curr); + if (!sched_feat(WAKEUP_PREEMPT)) return; - } + update_curr(cfs_rq); find_matching_se(&se, &pse); - BUG_ON(!pse); - if (wakeup_preempt_entity(se, pse) == 1) - resched_task(curr); + goto preempt; + + return; + +preempt: + resched_task(curr); + /* + * 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); } static struct task_struct *pick_next_task_fair(struct rq *rq) @@ -1525,16 +1781,11 @@ static struct task_struct *pick_next_task_fair(struct rq *rq) struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; - if (unlikely(!cfs_rq->nr_running)) + if (!cfs_rq->nr_running) return NULL; do { se = pick_next_entity(cfs_rq); - /* - * If se was a buddy, clear it so that it will have to earn - * the favour again. - */ - __clear_buddies(cfs_rq, se); set_next_entity(cfs_rq, se); cfs_rq = group_cfs_rq(se); } while (cfs_rq); @@ -1565,142 +1816,1743 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) */ /* - * Load-balancing iterator. Note: while the runqueue stays locked - * during the whole iteration, the current task might be - * dequeued so the iterator has to be dequeue-safe. Here we - * achieve that by always pre-iterating before returning - * the current task: + * pull_task - move a task from a remote runqueue to the local runqueue. + * Both runqueues must be locked. */ -static struct task_struct * -__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next) +static void pull_task(struct rq *src_rq, struct task_struct *p, + struct rq *this_rq, int this_cpu) { - struct task_struct *p = NULL; - struct sched_entity *se; + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + check_preempt_curr(this_rq, p, 0); +} - if (next == &cfs_rq->tasks) - return NULL; +/* + * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? + */ +static +int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, + struct sched_domain *sd, enum cpu_idle_type idle, + int *all_pinned) +{ + int tsk_cache_hot = 0; + /* + * We do not migrate tasks that are: + * 1) running (obviously), or + * 2) cannot be migrated to this CPU due to cpus_allowed, or + * 3) are cache-hot on their current CPU. + */ + if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) { + schedstat_inc(p, se.nr_failed_migrations_affine); + return 0; + } + *all_pinned = 0; - se = list_entry(next, struct sched_entity, group_node); - p = task_of(se); - cfs_rq->balance_iterator = next->next; + if (task_running(rq, p)) { + schedstat_inc(p, se.nr_failed_migrations_running); + return 0; + } - return p; -} + /* + * Aggressive migration if: + * 1) task is cache cold, or + * 2) too many balance attempts have failed. + */ -static struct task_struct *load_balance_start_fair(void *arg) -{ - struct cfs_rq *cfs_rq = arg; + tsk_cache_hot = task_hot(p, rq->clock, sd); + if (!tsk_cache_hot || + sd->nr_balance_failed > sd->cache_nice_tries) { +#ifdef CONFIG_SCHEDSTATS + if (tsk_cache_hot) { + schedstat_inc(sd, lb_hot_gained[idle]); + schedstat_inc(p, se.nr_forced_migrations); + } +#endif + return 1; + } - return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next); + if (tsk_cache_hot) { + schedstat_inc(p, se.nr_failed_migrations_hot); + return 0; + } + return 1; } -static struct task_struct *load_balance_next_fair(void *arg) +/* + * move_one_task tries to move exactly one task from busiest to this_rq, as + * part of active balancing operations within "domain". + * Returns 1 if successful and 0 otherwise. + * + * Called with both runqueues locked. + */ +static int +move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle) { - struct cfs_rq *cfs_rq = arg; + struct task_struct *p, *n; + struct cfs_rq *cfs_rq; + int pinned = 0; + + for_each_leaf_cfs_rq(busiest, cfs_rq) { + list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) { + + if (!can_migrate_task(p, busiest, this_cpu, + sd, idle, &pinned)) + continue; - return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator); + pull_task(busiest, p, this_rq, this_cpu); + /* + * Right now, this is only the second place pull_task() + * is called, so we can safely collect pull_task() + * stats here rather than inside pull_task(). + */ + schedstat_inc(sd, lb_gained[idle]); + return 1; + } + } + + return 0; } static unsigned long -__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, struct sched_domain *sd, - enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, - struct cfs_rq *cfs_rq) +balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, + int *this_best_prio, struct cfs_rq *busiest_cfs_rq) { - struct rq_iterator cfs_rq_iterator; + int loops = 0, pulled = 0, pinned = 0; + long rem_load_move = max_load_move; + struct task_struct *p, *n; - cfs_rq_iterator.start = load_balance_start_fair; - cfs_rq_iterator.next = load_balance_next_fair; - cfs_rq_iterator.arg = cfs_rq; + if (max_load_move == 0) + goto out; + pinned = 1; + + list_for_each_entry_safe(p, n, &busiest_cfs_rq->tasks, se.group_node) { + if (loops++ > sysctl_sched_nr_migrate) + break; + + if ((p->se.load.weight >> 1) > rem_load_move || + !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) + continue; + + pull_task(busiest, p, this_rq, this_cpu); + pulled++; + rem_load_move -= p->se.load.weight; + +#ifdef CONFIG_PREEMPT + /* + * NEWIDLE balancing is a source of latency, so preemptible + * kernels will stop after the first task is pulled to minimize + * the critical section. + */ + if (idle == CPU_NEWLY_IDLE) + break; +#endif + + /* + * We only want to steal up to the prescribed amount of + * weighted load. + */ + if (rem_load_move <= 0) + break; + + if (p->prio < *this_best_prio) + *this_best_prio = p->prio; + } +out: + /* + * Right now, this is one of only two places pull_task() is called, + * so we can safely collect pull_task() stats here rather than + * inside pull_task(). + */ + schedstat_add(sd, lb_gained[idle], pulled); + + if (all_pinned) + *all_pinned = pinned; + + return max_load_move - rem_load_move; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static unsigned long +load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, + struct sched_domain *sd, enum cpu_idle_type idle, + int *all_pinned, int *this_best_prio) +{ + long rem_load_move = max_load_move; + int busiest_cpu = cpu_of(busiest); + struct task_group *tg; + + rcu_read_lock(); + update_h_load(busiest_cpu); + + list_for_each_entry_rcu(tg, &task_groups, list) { + struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu]; + unsigned long busiest_h_load = busiest_cfs_rq->h_load; + unsigned long busiest_weight = busiest_cfs_rq->load.weight; + u64 rem_load, moved_load; + + /* + * empty group + */ + if (!busiest_cfs_rq->task_weight) + continue; + + rem_load = (u64)rem_load_move * busiest_weight; + rem_load = div_u64(rem_load, busiest_h_load + 1); + + moved_load = balance_tasks(this_rq, this_cpu, busiest, + rem_load, sd, idle, all_pinned, this_best_prio, + busiest_cfs_rq); + + if (!moved_load) + continue; + + moved_load *= busiest_h_load; + moved_load = div_u64(moved_load, busiest_weight + 1); + + rem_load_move -= moved_load; + if (rem_load_move < 0) + break; + } + rcu_read_unlock(); + + return max_load_move - rem_load_move; +} +#else +static unsigned long +load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, + struct sched_domain *sd, enum cpu_idle_type idle, + int *all_pinned, int *this_best_prio) +{ return balance_tasks(this_rq, this_cpu, busiest, max_load_move, sd, idle, all_pinned, - this_best_prio, &cfs_rq_iterator); + this_best_prio, &busiest->cfs); +} +#endif + +/* + * move_tasks tries to move up to max_load_move weighted load from busiest to + * this_rq, as part of a balancing operation within domain "sd". + * Returns 1 if successful and 0 otherwise. + * + * Called with both runqueues locked. + */ +static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, + struct sched_domain *sd, enum cpu_idle_type idle, + int *all_pinned) +{ + unsigned long total_load_moved = 0, load_moved; + int this_best_prio = this_rq->curr->prio; + + do { + load_moved = load_balance_fair(this_rq, this_cpu, busiest, + max_load_move - total_load_moved, + sd, idle, all_pinned, &this_best_prio); + + total_load_moved += load_moved; + +#ifdef CONFIG_PREEMPT + /* + * NEWIDLE balancing is a source of latency, so preemptible + * kernels will stop after the first task is pulled to minimize + * the critical section. + */ + if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) + break; + + if (raw_spin_is_contended(&this_rq->lock) || + raw_spin_is_contended(&busiest->lock)) + break; +#endif + } while (load_moved && max_load_move > total_load_moved); + + return total_load_moved > 0; +} + +/********** Helpers for find_busiest_group ************************/ +/* + * 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 *this; /* Local group in this sd */ + unsigned long total_load; /* Total load of all groups in sd */ + unsigned long total_pwr; /* Total power of all groups in sd */ + unsigned long avg_load; /* Average load across all groups in sd */ + + /** Statistics of this group */ + unsigned long this_load; + unsigned long this_load_per_task; + unsigned long this_nr_running; + + /* Statistics of the busiest group */ + unsigned long max_load; + unsigned long busiest_load_per_task; + unsigned long busiest_nr_running; + unsigned long busiest_group_capacity; + + int group_imb; /* Is there imbalance in this sd */ +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + int power_savings_balance; /* Is powersave balance needed for this sd */ + struct sched_group *group_min; /* Least loaded group in sd */ + struct sched_group *group_leader; /* Group which relieves group_min */ + unsigned long min_load_per_task; /* load_per_task in group_min */ + unsigned long leader_nr_running; /* Nr running of group_leader */ + unsigned long min_nr_running; /* Nr running of group_min */ +#endif +}; + +/* + * 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 sum_nr_running; /* Nr tasks running in the group */ + unsigned long sum_weighted_load; /* Weighted load of group's tasks */ + unsigned long group_capacity; + int group_imb; /* Is there an imbalance in the group ? */ +}; + +/** + * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. + * @group: The group whose first cpu is to be returned. + */ +static inline unsigned int group_first_cpu(struct sched_group *group) +{ + return cpumask_first(sched_group_cpus(group)); +} + +/** + * get_sd_load_idx - Obtain the load index for a given sched domain. + * @sd: The sched_domain whose load_idx is to be obtained. + * @idle: The Idle status of the CPU for whose sd load_icx is obtained. + */ +static inline int get_sd_load_idx(struct sched_domain *sd, + enum cpu_idle_type idle) +{ + int load_idx; + + switch (idle) { + case CPU_NOT_IDLE: + load_idx = sd->busy_idx; + break; + + case CPU_NEWLY_IDLE: + load_idx = sd->newidle_idx; + break; + default: + load_idx = sd->idle_idx; + break; + } + + return load_idx; +} + + +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +/** + * init_sd_power_savings_stats - Initialize power savings statistics for + * the given sched_domain, during load balancing. + * + * @sd: Sched domain whose power-savings statistics are to be initialized. + * @sds: Variable containing the statistics for sd. + * @idle: Idle status of the CPU at which we're performing load-balancing. + */ +static inline void init_sd_power_savings_stats(struct sched_domain *sd, + struct sd_lb_stats *sds, enum cpu_idle_type idle) +{ + /* + * Busy processors will not participate in power savings + * balance. + */ + if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) + sds->power_savings_balance = 0; + else { + sds->power_savings_balance = 1; + sds->min_nr_running = ULONG_MAX; + sds->leader_nr_running = 0; + } +} + +/** + * update_sd_power_savings_stats - Update the power saving stats for a + * sched_domain while performing load balancing. + * + * @group: sched_group belonging to the sched_domain under consideration. + * @sds: Variable containing the statistics of the sched_domain + * @local_group: Does group contain the CPU for which we're performing + * load balancing ? + * @sgs: Variable containing the statistics of the group. + */ +static inline void update_sd_power_savings_stats(struct sched_group *group, + struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) +{ + + if (!sds->power_savings_balance) + return; + + /* + * If the local group is idle or completely loaded + * no need to do power savings balance at this domain + */ + if (local_group && (sds->this_nr_running >= sgs->group_capacity || + !sds->this_nr_running)) + sds->power_savings_balance = 0; + + /* + * If a group is already running at full capacity or idle, + * don't include that group in power savings calculations + */ + if (!sds->power_savings_balance || + sgs->sum_nr_running >= sgs->group_capacity || + !sgs->sum_nr_running) + return; + + /* + * Calculate the group which has the least non-idle load. + * This is the group from where we need to pick up the load + * for saving power + */ + if ((sgs->sum_nr_running < sds->min_nr_running) || + (sgs->sum_nr_running == sds->min_nr_running && + group_first_cpu(group) > group_first_cpu(sds->group_min))) { + sds->group_min = group; + sds->min_nr_running = sgs->sum_nr_running; + sds->min_load_per_task = sgs->sum_weighted_load / + sgs->sum_nr_running; + } + + /* + * Calculate the group which is almost near its + * capacity but still has some space to pick up some load + * from other group and save more power + */ + if (sgs->sum_nr_running + 1 > sgs->group_capacity) + return; + + if (sgs->sum_nr_running > sds->leader_nr_running || + (sgs->sum_nr_running == sds->leader_nr_running && + group_first_cpu(group) < group_first_cpu(sds->group_leader))) { + sds->group_leader = group; + sds->leader_nr_running = sgs->sum_nr_running; + } +} + +/** + * check_power_save_busiest_group - see if there is potential for some power-savings balance + * @sds: Variable containing the statistics of the sched_domain + * under consideration. + * @this_cpu: Cpu at which we're currently performing load-balancing. + * @imbalance: Variable to store the imbalance. + * + * Description: + * Check if we have potential to perform some power-savings balance. + * If yes, set the busiest group to be the least loaded group in the + * sched_domain, so that it's CPUs can be put to idle. + * + * Returns 1 if there is potential to perform power-savings balance. + * Else returns 0. + */ +static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + if (!sds->power_savings_balance) + return 0; + + if (sds->this != sds->group_leader || + sds->group_leader == sds->group_min) + return 0; + + *imbalance = sds->min_load_per_task; + sds->busiest = sds->group_min; + + return 1; + +} +#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ +static inline void init_sd_power_savings_stats(struct sched_domain *sd, + struct sd_lb_stats *sds, enum cpu_idle_type idle) +{ + return; +} + +static inline void update_sd_power_savings_stats(struct sched_group *group, + struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) +{ + return; +} + +static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + return 0; +} +#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ + + +unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return SCHED_LOAD_SCALE; +} + +unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return default_scale_freq_power(sd, cpu); +} + +unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +{ + unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long smt_gain = sd->smt_gain; + + smt_gain /= weight; + + return smt_gain; +} + +unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) +{ + return default_scale_smt_power(sd, cpu); +} + +unsigned long scale_rt_power(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + u64 total, available; + + sched_avg_update(rq); + + total = sched_avg_period() + (rq->clock - rq->age_stamp); + available = total - rq->rt_avg; + + if (unlikely((s64)total < SCHED_LOAD_SCALE)) + total = SCHED_LOAD_SCALE; + + total >>= SCHED_LOAD_SHIFT; + + return div_u64(available, total); +} + +static void update_cpu_power(struct sched_domain *sd, int cpu) +{ + unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long power = SCHED_LOAD_SCALE; + struct sched_group *sdg = sd->groups; + + if (sched_feat(ARCH_POWER)) + power *= arch_scale_freq_power(sd, cpu); + else + power *= default_scale_freq_power(sd, cpu); + + power >>= SCHED_LOAD_SHIFT; + + if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { + if (sched_feat(ARCH_POWER)) + power *= arch_scale_smt_power(sd, cpu); + else + power *= default_scale_smt_power(sd, cpu); + + power >>= SCHED_LOAD_SHIFT; + } + + power *= scale_rt_power(cpu); + power >>= SCHED_LOAD_SHIFT; + + if (!power) + power = 1; + + sdg->cpu_power = power; +} + +static void update_group_power(struct sched_domain *sd, int cpu) +{ + struct sched_domain *child = sd->child; + struct sched_group *group, *sdg = sd->groups; + unsigned long power; + + if (!child) { + update_cpu_power(sd, cpu); + return; + } + + power = 0; + + group = child->groups; + do { + power += group->cpu_power; + group = group->next; + } while (group != child->groups); + + sdg->cpu_power = power; +} + +/** + * update_sg_lb_stats - Update sched_group's statistics for load balancing. + * @sd: The sched_domain whose statistics are to be updated. + * @group: sched_group whose statistics are to be updated. + * @this_cpu: Cpu for which load balance is currently performed. + * @idle: Idle status of this_cpu + * @load_idx: Load index of sched_domain of this_cpu for load calc. + * @sd_idle: Idle status of the sched_domain containing group. + * @local_group: Does group contain this_cpu. + * @cpus: Set of cpus considered for load balancing. + * @balance: Should we balance. + * @sgs: variable to hold the statistics for this group. + */ +static inline void update_sg_lb_stats(struct sched_domain *sd, + struct sched_group *group, int this_cpu, + enum cpu_idle_type idle, int load_idx, int *sd_idle, + int local_group, const struct cpumask *cpus, + int *balance, struct sg_lb_stats *sgs) +{ + unsigned long load, max_cpu_load, min_cpu_load; + int i; + unsigned int balance_cpu = -1, first_idle_cpu = 0; + unsigned long avg_load_per_task = 0; + + if (local_group) + balance_cpu = group_first_cpu(group); + + /* Tally up the load of all CPUs in the group */ + max_cpu_load = 0; + min_cpu_load = ~0UL; + + for_each_cpu_and(i, sched_group_cpus(group), cpus) { + struct rq *rq = cpu_rq(i); + + if (*sd_idle && rq->nr_running) + *sd_idle = 0; + + /* Bias balancing toward cpus of our domain */ + if (local_group) { + if (idle_cpu(i) && !first_idle_cpu) { + first_idle_cpu = 1; + balance_cpu = i; + } + + load = target_load(i, load_idx); + } else { + load = source_load(i, load_idx); + if (load > max_cpu_load) + max_cpu_load = load; + if (min_cpu_load > load) + min_cpu_load = load; + } + + sgs->group_load += load; + sgs->sum_nr_running += rq->nr_running; + sgs->sum_weighted_load += weighted_cpuload(i); + + } + + /* + * First idle cpu or the first cpu(busiest) in this sched group + * is eligible for doing load balancing at this and above + * domains. In the newly idle case, we will allow all the cpu's + * to do the newly idle load balance. + */ + if (idle != CPU_NEWLY_IDLE && local_group && + balance_cpu != this_cpu) { + *balance = 0; + return; + } + + update_group_power(sd, this_cpu); + + /* Adjust by relative CPU power of the group */ + sgs->avg_load = (sgs->group_load * SCHED_LOAD_SCALE) / group->cpu_power; + + /* + * Consider the group unbalanced when the imbalance is larger + * than the average weight of two tasks. + * + * APZ: with cgroup the avg task weight can vary wildly and + * might not be a suitable number - should we keep a + * normalized nr_running number somewhere that negates + * the hierarchy? + */ + if (sgs->sum_nr_running) + avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; + + if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) + sgs->group_imb = 1; + + sgs->group_capacity = + DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE); +} + +/** + * update_sd_lb_stats - Update sched_group's statistics for load balancing. + * @sd: sched_domain whose statistics are to be updated. + * @this_cpu: Cpu for which load balance is currently performed. + * @idle: Idle status of this_cpu + * @sd_idle: Idle status of the sched_domain containing group. + * @cpus: Set of cpus considered for load balancing. + * @balance: Should we balance. + * @sds: variable to hold the statistics for this sched_domain. + */ +static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, + enum cpu_idle_type idle, int *sd_idle, + const struct cpumask *cpus, int *balance, + struct sd_lb_stats *sds) +{ + struct sched_domain *child = sd->child; + struct sched_group *group = sd->groups; + struct sg_lb_stats sgs; + int load_idx, prefer_sibling = 0; + + if (child && child->flags & SD_PREFER_SIBLING) + prefer_sibling = 1; + + init_sd_power_savings_stats(sd, sds, idle); + load_idx = get_sd_load_idx(sd, idle); + + do { + int local_group; + + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); + memset(&sgs, 0, sizeof(sgs)); + update_sg_lb_stats(sd, group, this_cpu, idle, load_idx, sd_idle, + local_group, cpus, balance, &sgs); + + if (local_group && !(*balance)) + return; + + sds->total_load += sgs.group_load; + sds->total_pwr += group->cpu_power; + + /* + * In case the child domain prefers tasks go to siblings + * first, lower the group capacity to one so that we'll try + * and move all the excess tasks away. + */ + if (prefer_sibling) + sgs.group_capacity = min(sgs.group_capacity, 1UL); + + if (local_group) { + sds->this_load = sgs.avg_load; + sds->this = group; + sds->this_nr_running = sgs.sum_nr_running; + sds->this_load_per_task = sgs.sum_weighted_load; + } else if (sgs.avg_load > sds->max_load && + (sgs.sum_nr_running > sgs.group_capacity || + sgs.group_imb)) { + sds->max_load = sgs.avg_load; + sds->busiest = group; + sds->busiest_nr_running = sgs.sum_nr_running; + sds->busiest_group_capacity = sgs.group_capacity; + sds->busiest_load_per_task = sgs.sum_weighted_load; + sds->group_imb = sgs.group_imb; + } + + update_sd_power_savings_stats(group, sds, local_group, &sgs); + group = group->next; + } while (group != sd->groups); +} + +/** + * fix_small_imbalance - Calculate the minor imbalance that exists + * amongst the groups of a sched_domain, during + * load balancing. + * @sds: Statistics of the sched_domain whose imbalance is to be calculated. + * @this_cpu: The cpu at whose sched_domain we're performing load-balance. + * @imbalance: Variable to store the imbalance. + */ +static inline void fix_small_imbalance(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + unsigned long tmp, pwr_now = 0, pwr_move = 0; + unsigned int imbn = 2; + unsigned long scaled_busy_load_per_task; + + if (sds->this_nr_running) { + sds->this_load_per_task /= sds->this_nr_running; + if (sds->busiest_load_per_task > + sds->this_load_per_task) + imbn = 1; + } else + sds->this_load_per_task = + cpu_avg_load_per_task(this_cpu); + + scaled_busy_load_per_task = sds->busiest_load_per_task + * SCHED_LOAD_SCALE; + scaled_busy_load_per_task /= sds->busiest->cpu_power; + + if (sds->max_load - sds->this_load + scaled_busy_load_per_task >= + (scaled_busy_load_per_task * imbn)) { + *imbalance = sds->busiest_load_per_task; + return; + } + + /* + * OK, we don't have enough imbalance to justify moving tasks, + * however we may be able to increase total CPU power used by + * moving them. + */ + + pwr_now += sds->busiest->cpu_power * + min(sds->busiest_load_per_task, sds->max_load); + pwr_now += sds->this->cpu_power * + min(sds->this_load_per_task, sds->this_load); + pwr_now /= SCHED_LOAD_SCALE; + + /* Amount of load we'd subtract */ + tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / + sds->busiest->cpu_power; + if (sds->max_load > tmp) + pwr_move += sds->busiest->cpu_power * + min(sds->busiest_load_per_task, sds->max_load - tmp); + + /* Amount of load we'd add */ + if (sds->max_load * sds->busiest->cpu_power < + sds->busiest_load_per_task * SCHED_LOAD_SCALE) + tmp = (sds->max_load * sds->busiest->cpu_power) / + sds->this->cpu_power; + else + tmp = (sds->busiest_load_per_task * SCHED_LOAD_SCALE) / + sds->this->cpu_power; + pwr_move += sds->this->cpu_power * + min(sds->this_load_per_task, sds->this_load + tmp); + pwr_move /= SCHED_LOAD_SCALE; + + /* Move if we gain throughput */ + if (pwr_move > pwr_now) + *imbalance = sds->busiest_load_per_task; +} + +/** + * calculate_imbalance - Calculate the amount of imbalance present within the + * groups of a given sched_domain during load balance. + * @sds: statistics of the sched_domain whose imbalance is to be calculated. + * @this_cpu: Cpu for which currently load balance is being performed. + * @imbalance: The variable to store the imbalance. + */ +static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, + unsigned long *imbalance) +{ + unsigned long max_pull, load_above_capacity = ~0UL; + + sds->busiest_load_per_task /= sds->busiest_nr_running; + if (sds->group_imb) { + sds->busiest_load_per_task = + min(sds->busiest_load_per_task, sds->avg_load); + } + + /* + * In the presence of smp nice balancing, certain scenarios can have + * max load less than avg load(as we skip the groups at or below + * its cpu_power, while calculating max_load..) + */ + if (sds->max_load < sds->avg_load) { + *imbalance = 0; + return fix_small_imbalance(sds, this_cpu, imbalance); + } + + if (!sds->group_imb) { + /* + * Don't want to pull so many tasks that a group would go idle. + */ + load_above_capacity = (sds->busiest_nr_running - + sds->busiest_group_capacity); + + load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_LOAD_SCALE); + + load_above_capacity /= sds->busiest->cpu_power; + } + + /* + * 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 + * (so that we can implement power-savings policies etc). Thus we look + * for the minimum possible imbalance. + * Be careful of negative numbers as they'll appear as very large values + * with unsigned longs. + */ + max_pull = min(sds->max_load - sds->avg_load, load_above_capacity); + + /* How much load to actually move to equalise the imbalance */ + *imbalance = min(max_pull * sds->busiest->cpu_power, + (sds->avg_load - sds->this_load) * sds->this->cpu_power) + / SCHED_LOAD_SCALE; + + /* + * if *imbalance is less than the average load per runnable task + * there is no gaurantee that any tasks will be moved so we'll have + * a think about bumping its value to force at least one task to be + * moved + */ + if (*imbalance < sds->busiest_load_per_task) + return fix_small_imbalance(sds, this_cpu, imbalance); + +} +/******* find_busiest_group() helpers end here *********************/ + +/** + * find_busiest_group - Returns the busiest group within the sched_domain + * if there is an imbalance. If there isn't an imbalance, and + * the user has opted for power-savings, it returns a group whose + * CPUs can be put to idle by rebalancing those tasks elsewhere, if + * such a group exists. + * + * Also calculates the amount of weighted load which should be moved + * to restore balance. + * + * @sd: The sched_domain whose busiest group is to be returned. + * @this_cpu: The cpu for which load balancing is currently being performed. + * @imbalance: Variable which stores amount of weighted load which should + * be moved to restore balance/put a group to idle. + * @idle: The idle status of this_cpu. + * @sd_idle: The idleness of sd + * @cpus: The set of CPUs under consideration for load-balancing. + * @balance: Pointer to a variable indicating if this_cpu + * is the appropriate cpu to perform load balancing at this_level. + * + * Returns: - the busiest group if imbalance exists. + * - If no imbalance and user has opted for power-savings balance, + * return the least loaded group whose CPUs can be + * put to idle by rebalancing its tasks onto our group. + */ +static struct sched_group * +find_busiest_group(struct sched_domain *sd, int this_cpu, + unsigned long *imbalance, enum cpu_idle_type idle, + int *sd_idle, const struct cpumask *cpus, int *balance) +{ + struct sd_lb_stats sds; + + memset(&sds, 0, sizeof(sds)); + + /* + * Compute the various statistics relavent for load balancing at + * this level. + */ + update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus, + balance, &sds); + + /* Cases where imbalance does not exist from POV of this_cpu */ + /* 1) this_cpu is not the appropriate cpu to perform load balancing + * at this level. + * 2) There is no busy sibling group to pull from. + * 3) This group is the busiest group. + * 4) This group is more busy than the avg busieness at this + * sched_domain. + * 5) The imbalance is within the specified limit. + */ + if (!(*balance)) + goto ret; + + if (!sds.busiest || sds.busiest_nr_running == 0) + goto out_balanced; + + if (sds.this_load >= sds.max_load) + goto out_balanced; + + sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; + + if (sds.this_load >= sds.avg_load) + goto out_balanced; + + if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) + goto out_balanced; + + /* Looks like there is an imbalance. Compute it */ + calculate_imbalance(&sds, this_cpu, imbalance); + return sds.busiest; + +out_balanced: + /* + * There is no obvious imbalance. But check if we can do some balancing + * to save power. + */ + if (check_power_save_busiest_group(&sds, this_cpu, imbalance)) + return sds.busiest; +ret: + *imbalance = 0; + return NULL; +} + +/* + * find_busiest_queue - find the busiest runqueue among the cpus in group. + */ +static struct rq * +find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, + unsigned long imbalance, const struct cpumask *cpus) +{ + struct rq *busiest = NULL, *rq; + unsigned long max_load = 0; + int i; + + for_each_cpu(i, sched_group_cpus(group)) { + unsigned long power = power_of(i); + unsigned long capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE); + unsigned long wl; + + if (!cpumask_test_cpu(i, cpus)) + continue; + + rq = cpu_rq(i); + wl = weighted_cpuload(i); + + /* + * When comparing with imbalance, use weighted_cpuload() + * which is not scaled with the cpu power. + */ + if (capacity && rq->nr_running == 1 && wl > imbalance) + continue; + + /* + * For the load comparisons with the other cpu's, consider + * the weighted_cpuload() scaled with the cpu power, so that + * the load can be moved away from the cpu that is potentially + * running at a lower capacity. + */ + wl = (wl * SCHED_LOAD_SCALE) / power; + + if (wl > max_load) { + max_load = wl; + busiest = rq; + } + } + + 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 + +/* Working cpumask for load_balance and load_balance_newidle. */ +static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); + +static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle) +{ + if (idle == CPU_NEWLY_IDLE) { + /* + * The only task running in a non-idle cpu can be moved to this + * cpu in an attempt to completely freeup the other CPU + * package. + * + * The package power saving logic comes from + * find_busiest_group(). If there are no imbalance, then + * f_b_g() will return NULL. However when sched_mc={1,2} then + * f_b_g() will select a group from which a running task may be + * pulled to this cpu in order to make the other package idle. + * If there is no opportunity to make a package idle and if + * there are no imbalance, then f_b_g() will return NULL and no + * action will be taken in load_balance_newidle(). + * + * Under normal task pull operation due to imbalance, there + * will be more than one task in the source run queue and + * move_tasks() will succeed. ld_moved will be true and this + * active balance code will not be triggered. + */ + if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + return 0; + + if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) + return 0; + } + + return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); +} + +/* + * 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 *balance) +{ + int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; + struct sched_group *group; + unsigned long imbalance; + struct rq *busiest; + unsigned long flags; + struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); + + cpumask_copy(cpus, cpu_active_mask); + + /* + * When power savings policy is enabled for the parent domain, idle + * sibling can pick up load irrespective of busy siblings. In this case, + * let the state of idle sibling percolate up as CPU_IDLE, instead of + * portraying it as CPU_NOT_IDLE. + */ + if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + sd_idle = 1; + + schedstat_inc(sd, lb_count[idle]); + +redo: + update_shares(sd); + group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, + cpus, balance); + + if (*balance == 0) + goto out_balanced; + + if (!group) { + schedstat_inc(sd, lb_nobusyg[idle]); + goto out_balanced; + } + + busiest = find_busiest_queue(group, idle, imbalance, cpus); + if (!busiest) { + schedstat_inc(sd, lb_nobusyq[idle]); + goto out_balanced; + } + + BUG_ON(busiest == this_rq); + + schedstat_add(sd, lb_imbalance[idle], imbalance); + + ld_moved = 0; + 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. + */ + local_irq_save(flags); + double_rq_lock(this_rq, busiest); + ld_moved = move_tasks(this_rq, this_cpu, busiest, + imbalance, sd, idle, &all_pinned); + double_rq_unlock(this_rq, busiest); + local_irq_restore(flags); + + /* + * some other cpu did the load balance for us. + */ + if (ld_moved && this_cpu != smp_processor_id()) + resched_cpu(this_cpu); + + /* All tasks on this runqueue were pinned by CPU affinity */ + if (unlikely(all_pinned)) { + cpumask_clear_cpu(cpu_of(busiest), cpus); + if (!cpumask_empty(cpus)) + goto redo; + goto out_balanced; + } + } + + if (!ld_moved) { + schedstat_inc(sd, lb_failed[idle]); + sd->nr_balance_failed++; + + if (need_active_balance(sd, sd_idle, idle)) { + raw_spin_lock_irqsave(&busiest->lock, flags); + + /* don't kick the migration_thread, if the curr + * task on busiest cpu can't be moved to this_cpu + */ + if (!cpumask_test_cpu(this_cpu, + &busiest->curr->cpus_allowed)) { + raw_spin_unlock_irqrestore(&busiest->lock, + flags); + all_pinned = 1; + goto out_one_pinned; + } + + if (!busiest->active_balance) { + busiest->active_balance = 1; + busiest->push_cpu = this_cpu; + active_balance = 1; + } + raw_spin_unlock_irqrestore(&busiest->lock, flags); + if (active_balance) + wake_up_process(busiest->migration_thread); + + /* + * We've kicked active balancing, reset the failure + * counter. + */ + sd->nr_balance_failed = sd->cache_nice_tries+1; + } + } else + sd->nr_balance_failed = 0; + + if (likely(!active_balance)) { + /* We were unbalanced, so reset the balancing interval */ + sd->balance_interval = sd->min_interval; + } else { + /* + * If we've begun active balancing, start to back off. This + * case may not be covered by the all_pinned logic if there + * is only 1 task on the busy runqueue (because we don't call + * move_tasks). + */ + if (sd->balance_interval < sd->max_interval) + sd->balance_interval *= 2; + } + + if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + ld_moved = -1; + + goto out; + +out_balanced: + schedstat_inc(sd, lb_balanced[idle]); + + sd->nr_balance_failed = 0; + +out_one_pinned: + /* tune up the balancing interval */ + if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) || + (sd->balance_interval < sd->max_interval)) + sd->balance_interval *= 2; + + if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + ld_moved = -1; + else + ld_moved = 0; +out: + if (ld_moved) + update_shares(sd); + return ld_moved; } -#ifdef CONFIG_FAIR_GROUP_SCHED -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, int *this_best_prio) +/* + * idle_balance is called by schedule() if this_cpu is about to become + * idle. Attempts to pull tasks from other CPUs. + */ +static void idle_balance(int this_cpu, struct rq *this_rq) { - long rem_load_move = max_load_move; - int busiest_cpu = cpu_of(busiest); - struct task_group *tg; + struct sched_domain *sd; + int pulled_task = 0; + unsigned long next_balance = jiffies + HZ; - rcu_read_lock(); - update_h_load(busiest_cpu); + this_rq->idle_stamp = this_rq->clock; - list_for_each_entry_rcu(tg, &task_groups, list) { - struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu]; - unsigned long busiest_h_load = busiest_cfs_rq->h_load; - unsigned long busiest_weight = busiest_cfs_rq->load.weight; - u64 rem_load, moved_load; + if (this_rq->avg_idle < sysctl_sched_migration_cost) + return; + + /* + * Drop the rq->lock, but keep IRQ/preempt disabled. + */ + raw_spin_unlock(&this_rq->lock); + + for_each_domain(this_cpu, sd) { + unsigned long interval; + int balance = 1; + + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + if (sd->flags & SD_BALANCE_NEWIDLE) { + /* If we've pulled tasks over stop searching: */ + pulled_task = load_balance(this_cpu, this_rq, + sd, CPU_NEWLY_IDLE, &balance); + } + + interval = msecs_to_jiffies(sd->balance_interval); + if (time_after(next_balance, sd->last_balance + interval)) + next_balance = sd->last_balance + interval; + if (pulled_task) { + this_rq->idle_stamp = 0; + break; + } + } + + raw_spin_lock(&this_rq->lock); + if (pulled_task || time_after(jiffies, this_rq->next_balance)) { /* - * empty group + * We are going idle. next_balance may be set based on + * a busy processor. So reset next_balance. */ - if (!busiest_cfs_rq->task_weight) - continue; + this_rq->next_balance = next_balance; + } +} - rem_load = (u64)rem_load_move * busiest_weight; - rem_load = div_u64(rem_load, busiest_h_load + 1); +/* + * active_load_balance is run by migration threads. 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. + * + * Called with busiest_rq locked. + */ +static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) +{ + int target_cpu = busiest_rq->push_cpu; + struct sched_domain *sd; + struct rq *target_rq; - moved_load = __load_balance_fair(this_rq, this_cpu, busiest, - rem_load, sd, idle, all_pinned, this_best_prio, - tg->cfs_rq[busiest_cpu]); + /* Is there any task to move? */ + if (busiest_rq->nr_running <= 1) + return; - if (!moved_load) - continue; + target_rq = cpu_rq(target_cpu); - moved_load *= busiest_h_load; - moved_load = div_u64(moved_load, busiest_weight + 1); + /* + * This condition is "impossible", if it occurs + * we need to fix it. Originally reported by + * Bjorn Helgaas on a 128-cpu setup. + */ + BUG_ON(busiest_rq == target_rq); + + /* move a task from busiest_rq to target_rq */ + double_lock_balance(busiest_rq, target_rq); + update_rq_clock(busiest_rq); + update_rq_clock(target_rq); + + /* Search for an sd spanning us and the target CPU. */ + for_each_domain(target_cpu, sd) { + if ((sd->flags & SD_LOAD_BALANCE) && + cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) + break; + } - rem_load_move -= moved_load; - if (rem_load_move < 0) + if (likely(sd)) { + schedstat_inc(sd, alb_count); + + if (move_one_task(target_rq, target_cpu, busiest_rq, + sd, CPU_IDLE)) + schedstat_inc(sd, alb_pushed); + else + schedstat_inc(sd, alb_failed); + } + double_unlock_balance(busiest_rq, target_rq); +} + +#ifdef CONFIG_NO_HZ +static struct { + atomic_t load_balancer; + cpumask_var_t cpu_mask; + cpumask_var_t ilb_grp_nohz_mask; +} nohz ____cacheline_aligned = { + .load_balancer = ATOMIC_INIT(-1), +}; + +int get_nohz_load_balancer(void) +{ + return atomic_read(&nohz.load_balancer); +} + +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +/** + * lowest_flag_domain - Return lowest sched_domain containing flag. + * @cpu: The cpu whose lowest level of sched domain is to + * be returned. + * @flag: The flag to check for the lowest sched_domain + * for the given cpu. + * + * Returns the lowest sched_domain of a cpu which contains the given flag. + */ +static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd; + + for_each_domain(cpu, sd) + if (sd && (sd->flags & flag)) break; + + return sd; +} + +/** + * for_each_flag_domain - Iterates over sched_domains containing the flag. + * @cpu: The cpu whose domains we're iterating over. + * @sd: variable holding the value of the power_savings_sd + * for cpu. + * @flag: The flag to filter the sched_domains to be iterated. + * + * Iterates over all the scheduler domains for a given cpu that has the 'flag' + * set, starting from the lowest sched_domain to the highest. + */ +#define for_each_flag_domain(cpu, sd, flag) \ + for (sd = lowest_flag_domain(cpu, flag); \ + (sd && (sd->flags & flag)); sd = sd->parent) + +/** + * is_semi_idle_group - Checks if the given sched_group is semi-idle. + * @ilb_group: group to be checked for semi-idleness + * + * Returns: 1 if the group is semi-idle. 0 otherwise. + * + * We define a sched_group to be semi idle if it has atleast one idle-CPU + * and atleast one non-idle CPU. This helper function checks if the given + * sched_group is semi-idle or not. + */ +static inline int is_semi_idle_group(struct sched_group *ilb_group) +{ + cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask, + sched_group_cpus(ilb_group)); + + /* + * A sched_group is semi-idle when it has atleast one busy cpu + * and atleast one idle cpu. + */ + if (cpumask_empty(nohz.ilb_grp_nohz_mask)) + return 0; + + if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group))) + return 0; + + return 1; +} +/** + * find_new_ilb - Finds the optimum idle load balancer for nomination. + * @cpu: The cpu which is nominating a new idle_load_balancer. + * + * Returns: Returns the id of the idle load balancer if it exists, + * Else, returns >= nr_cpu_ids. + * + * This algorithm picks the idle load balancer such that it belongs to a + * semi-idle powersavings sched_domain. The idea is to try and avoid + * completely idle packages/cores just for the purpose of idle load balancing + * when there are other idle cpu's which are better suited for that job. + */ +static int find_new_ilb(int cpu) +{ + struct sched_domain *sd; + struct sched_group *ilb_group; + + /* + * Have idle load balancer selection from semi-idle packages only + * when power-aware load balancing is enabled + */ + if (!(sched_smt_power_savings || sched_mc_power_savings)) + goto out_done; + + /* + * Optimize for the case when we have no idle CPUs or only one + * idle CPU. Don't walk the sched_domain hierarchy in such cases + */ + if (cpumask_weight(nohz.cpu_mask) < 2) + goto out_done; + + for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { + ilb_group = sd->groups; + + do { + if (is_semi_idle_group(ilb_group)) + return cpumask_first(nohz.ilb_grp_nohz_mask); + + ilb_group = ilb_group->next; + + } while (ilb_group != sd->groups); } - rcu_read_unlock(); - return max_load_move - rem_load_move; +out_done: + return cpumask_first(nohz.cpu_mask); } -#else -static unsigned long -load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, int *this_best_prio) +#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ +static inline int find_new_ilb(int call_cpu) { - return __load_balance_fair(this_rq, this_cpu, busiest, - max_load_move, sd, idle, all_pinned, - this_best_prio, &busiest->cfs); + return cpumask_first(nohz.cpu_mask); } #endif -static int -move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) +/* + * This routine will try to nominate the ilb (idle load balancing) + * owner among the cpus whose ticks are stopped. ilb owner will do the idle + * load balancing on behalf of all those cpus. If all the cpus in the system + * go into this tickless mode, then there will be no ilb owner (as there is + * no need for one) and all the cpus will sleep till the next wakeup event + * arrives... + * + * For the ilb owner, tick is not stopped. And this tick will be used + * for idle load balancing. ilb owner will still be part of + * nohz.cpu_mask.. + * + * While stopping the tick, this cpu will become the ilb owner if there + * is no other owner. And will be the owner till that cpu becomes busy + * or if all cpus in the system stop their ticks at which point + * there is no need for ilb owner. + * + * When the ilb owner becomes busy, it nominates another owner, during the + * next busy scheduler_tick() + */ +int select_nohz_load_balancer(int stop_tick) +{ + int cpu = smp_processor_id(); + + if (stop_tick) { + cpu_rq(cpu)->in_nohz_recently = 1; + + if (!cpu_active(cpu)) { + if (atomic_read(&nohz.load_balancer) != cpu) + return 0; + + /* + * If we are going offline and still the leader, + * give up! + */ + if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + BUG(); + + return 0; + } + + cpumask_set_cpu(cpu, nohz.cpu_mask); + + /* time for ilb owner also to sleep */ + if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) { + if (atomic_read(&nohz.load_balancer) == cpu) + atomic_set(&nohz.load_balancer, -1); + return 0; + } + + if (atomic_read(&nohz.load_balancer) == -1) { + /* make me the ilb owner */ + if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) + return 1; + } else if (atomic_read(&nohz.load_balancer) == cpu) { + int new_ilb; + + if (!(sched_smt_power_savings || + sched_mc_power_savings)) + return 1; + /* + * Check to see if there is a more power-efficient + * ilb. + */ + new_ilb = find_new_ilb(cpu); + if (new_ilb < nr_cpu_ids && new_ilb != cpu) { + atomic_set(&nohz.load_balancer, -1); + resched_cpu(new_ilb); + return 0; + } + return 1; + } + } else { + if (!cpumask_test_cpu(cpu, nohz.cpu_mask)) + return 0; + + cpumask_clear_cpu(cpu, nohz.cpu_mask); + + if (atomic_read(&nohz.load_balancer) == cpu) + if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + BUG(); + } + return 0; +} +#endif + +static DEFINE_SPINLOCK(balancing); + +/* + * 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 arch_init_sched_domains. + */ +static void rebalance_domains(int cpu, enum cpu_idle_type idle) { - struct cfs_rq *busy_cfs_rq; - struct rq_iterator cfs_rq_iterator; + int balance = 1; + struct rq *rq = cpu_rq(cpu); + unsigned long interval; + struct sched_domain *sd; + /* Earliest time when we have to do rebalance again */ + unsigned long next_balance = jiffies + 60*HZ; + int update_next_balance = 0; + int need_serialize; + + for_each_domain(cpu, sd) { + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + interval = sd->balance_interval; + if (idle != CPU_IDLE) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + if (unlikely(!interval)) + interval = 1; + if (interval > HZ*NR_CPUS/10) + interval = HZ*NR_CPUS/10; + + need_serialize = sd->flags & SD_SERIALIZE; + + if (need_serialize) { + if (!spin_trylock(&balancing)) + goto out; + } - cfs_rq_iterator.start = load_balance_start_fair; - cfs_rq_iterator.next = load_balance_next_fair; + if (time_after_eq(jiffies, sd->last_balance + interval)) { + if (load_balance(cpu, rq, sd, idle, &balance)) { + /* + * We've pulled tasks over so either we're no + * longer idle, or one of our SMT siblings is + * not idle. + */ + idle = CPU_NOT_IDLE; + } + sd->last_balance = jiffies; + } + 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; + } - for_each_leaf_cfs_rq(busiest, busy_cfs_rq) { /* - * pass busy_cfs_rq argument into - * load_balance_[start|next]_fair iterators + * Stop the load balance at this level. There is another + * CPU in our sched group which is doing load balancing more + * actively. */ - cfs_rq_iterator.arg = busy_cfs_rq; - if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle, - &cfs_rq_iterator)) - return 1; + if (!balance) + break; } - return 0; + /* + * 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; +} + +/* + * run_rebalance_domains is triggered when needed from the scheduler tick. + * In CONFIG_NO_HZ case, the idle load balance owner will do the + * rebalancing for all the cpus for whom scheduler ticks are stopped. + */ +static void run_rebalance_domains(struct softirq_action *h) +{ + int this_cpu = smp_processor_id(); + struct rq *this_rq = cpu_rq(this_cpu); + enum cpu_idle_type idle = this_rq->idle_at_tick ? + CPU_IDLE : CPU_NOT_IDLE; + + rebalance_domains(this_cpu, idle); + +#ifdef CONFIG_NO_HZ + /* + * If this cpu is the owner for idle load balancing, then do the + * balancing on behalf of the other idle cpus whose ticks are + * stopped. + */ + if (this_rq->idle_at_tick && + atomic_read(&nohz.load_balancer) == this_cpu) { + struct rq *rq; + int balance_cpu; + + for_each_cpu(balance_cpu, nohz.cpu_mask) { + if (balance_cpu == this_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()) + break; + + rebalance_domains(balance_cpu, CPU_IDLE); + + rq = cpu_rq(balance_cpu); + if (time_after(this_rq->next_balance, rq->next_balance)) + this_rq->next_balance = rq->next_balance; + } + } +#endif +} + +static inline int on_null_domain(int cpu) +{ + return !rcu_dereference(cpu_rq(cpu)->sd); +} + +/* + * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. + * + * In case of CONFIG_NO_HZ, this is the place where we nominate a new + * idle load balancing owner or decide to stop the periodic load balancing, + * if the whole system is idle. + */ +static inline void trigger_load_balance(struct rq *rq, int cpu) +{ +#ifdef CONFIG_NO_HZ + /* + * If we were in the nohz mode recently and busy at the current + * scheduler tick, then check if we need to nominate new idle + * load balancer. + */ + if (rq->in_nohz_recently && !rq->idle_at_tick) { + rq->in_nohz_recently = 0; + + if (atomic_read(&nohz.load_balancer) == cpu) { + cpumask_clear_cpu(cpu, nohz.cpu_mask); + atomic_set(&nohz.load_balancer, -1); + } + + if (atomic_read(&nohz.load_balancer) == -1) { + int ilb = find_new_ilb(cpu); + + if (ilb < nr_cpu_ids) + resched_cpu(ilb); + } + } + + /* + * If this cpu is idle and doing idle load balancing for all the + * cpus with ticks stopped, is it time for that to stop? + */ + if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && + cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { + resched_cpu(cpu); + return; + } + + /* + * If this cpu is idle and the idle load balancing is done by + * someone else, then no need raise the SCHED_SOFTIRQ + */ + if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && + cpumask_test_cpu(cpu, nohz.cpu_mask)) + return; +#endif + /* Don't need to rebalance while attached to NULL domain */ + if (time_after_eq(jiffies, rq->next_balance) && + likely(!on_null_domain(cpu))) + raise_softirq(SCHED_SOFTIRQ); +} + +static void rq_online_fair(struct rq *rq) +{ + update_sysctl(); +} + +static void rq_offline_fair(struct rq *rq) +{ + update_sysctl(); +} + +#else /* CONFIG_SMP */ + +/* + * on UP we do not need to balance between CPUs: + */ +static inline void idle_balance(int cpu, struct rq *rq) +{ } + #endif /* CONFIG_SMP */ /* @@ -1718,26 +3570,30 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) } /* - * Share the fairness runtime between parent and child, thus the - * total amount of pressure for CPU stays equal - new tasks - * get a chance to run but frequent forkers are not allowed to - * monopolize the CPU. Note: the parent runqueue is locked, - * the child is not running yet. + * 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_new_fair(struct rq *rq, struct task_struct *p) +static void task_fork_fair(struct task_struct *p) { - struct cfs_rq *cfs_rq = task_cfs_rq(p); + struct cfs_rq *cfs_rq = task_cfs_rq(current); struct sched_entity *se = &p->se, *curr = cfs_rq->curr; int this_cpu = smp_processor_id(); + struct rq *rq = this_rq(); + unsigned long flags; - sched_info_queued(p); + raw_spin_lock_irqsave(&rq->lock, flags); + + if (unlikely(task_cpu(p) != this_cpu)) + __set_task_cpu(p, this_cpu); update_curr(cfs_rq); + + if (curr) + se->vruntime = curr->vruntime; place_entity(cfs_rq, se, 1); - /* 'curr' will be NULL if the child belongs to a different group */ - if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) && - curr && entity_before(curr, se)) { + 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. @@ -1746,7 +3602,9 @@ static void task_new_fair(struct rq *rq, struct task_struct *p) resched_task(rq->curr); } - enqueue_task_fair(rq, p, 0); + se->vruntime -= cfs_rq->min_vruntime; + + raw_spin_unlock_irqrestore(&rq->lock, flags); } /* @@ -1799,15 +3657,31 @@ static void set_curr_task_fair(struct rq *rq) } #ifdef CONFIG_FAIR_GROUP_SCHED -static void moved_group_fair(struct task_struct *p) +static void moved_group_fair(struct task_struct *p, int on_rq) { struct cfs_rq *cfs_rq = task_cfs_rq(p); update_curr(cfs_rq); - place_entity(cfs_rq, &p->se, 1); + if (!on_rq) + place_entity(cfs_rq, &p->se, 1); } #endif +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(&rq->cfs, se)); + + return rr_interval; +} + /* * All the scheduling class methods: */ @@ -1825,17 +3699,21 @@ static const struct sched_class fair_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_fair, - .load_balance = load_balance_fair, - .move_one_task = move_one_task_fair, + .rq_online = rq_online_fair, + .rq_offline = rq_offline_fair, + + .task_waking = task_waking_fair, #endif .set_curr_task = set_curr_task_fair, .task_tick = task_tick_fair, - .task_new = task_new_fair, + .task_fork = task_fork_fair, .prio_changed = prio_changed_fair, .switched_to = switched_to_fair, + .get_rr_interval = get_rr_interval_fair, + #ifdef CONFIG_FAIR_GROUP_SCHED .moved_group = moved_group_fair, #endif