X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsched_fair.c;h=e2a530515619ee8f3b42b1ca246cd18ae05f5544;hb=343c00422d3296838927016750b18ead8aa8bf9a;hp=a9dfb7746c5c78c537588f746fd60c9c0e3f94e9;hpb=0702e3ebc1e42576a04d29f8adacf13be825b800;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index a9dfb77..e2a5305 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -20,33 +20,38 @@ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ +#include + /* * Targeted preemption latency for CPU-bound tasks: - * (default: 20ms, units: nanoseconds) + * (default: 20ms * (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. - * (to see the precise effective timeslice length of your workload, - * run vmstat and monitor the context-switches field) + * 'timeslice length' - timeslices in CFS are of variable length + * and have no persistent notion like in traditional, time-slice + * based scheduling concepts. * - * On SMP systems the value of this is multiplied by the log2 of the - * number of CPUs. (i.e. factor 2x on 2-way systems, 3x on 4-way - * systems, 4x on 8-way systems, 5x on 16-way systems, etc.) - * Targeted preemption latency for CPU-bound tasks: + * (to see the precise effective timeslice length of your workload, + * run vmstat and monitor the context-switches (cs) field) */ -const_debug unsigned int sysctl_sched_latency = 20000000ULL; +unsigned int sysctl_sched_latency = 20000000ULL; /* - * After fork, child runs first. (default) If set to 0 then - * parent will (try to) run first. + * Minimal preemption granularity for CPU-bound tasks: + * (default: 4 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -const_debug unsigned int sysctl_sched_child_runs_first = 1; +unsigned int sysctl_sched_min_granularity = 4000000ULL; /* - * Minimal preemption granularity for CPU-bound tasks: - * (default: 2 msec, units: nanoseconds) + * is kept at sysctl_sched_latency / sysctl_sched_min_granularity + */ +static unsigned int sched_nr_latency = 5; + +/* + * After fork, child runs first. (default) If set to 0 then + * parent will (try to) run first. */ -const_debug unsigned int sysctl_sched_nr_latency = 20; +const_debug unsigned int sysctl_sched_child_runs_first = 1; /* * sys_sched_yield() compat mode @@ -58,23 +63,25 @@ unsigned int __read_mostly sysctl_sched_compat_yield; /* * SCHED_BATCH wake-up granularity. - * (default: 10 msec, units: nanoseconds) + * (default: 10 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. */ -const_debug unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL; +unsigned int sysctl_sched_batch_wakeup_granularity = 10000000UL; /* * SCHED_OTHER wake-up granularity. - * (default: 10 msec, units: nanoseconds) + * (default: 10 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. */ -const_debug unsigned int sysctl_sched_wakeup_granularity = 10000000UL; +unsigned int sysctl_sched_wakeup_granularity = 10000000UL; + +const_debug unsigned int sysctl_sched_migration_cost = 500000UL; /************************************************************** * CFS operations on generic schedulable entities: @@ -195,23 +202,34 @@ static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq) static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) { - struct rb_node **link = &cfs_rq->tasks_timeline.rb_node; - struct sched_entity *se = NULL; - struct rb_node *parent; + struct rb_node *last = rb_last(&cfs_rq->tasks_timeline); - while (*link) { - parent = *link; - se = rb_entry(parent, struct sched_entity, run_node); - link = &parent->rb_right; - } + if (!last) + return NULL; - return se; + return rb_entry(last, struct sched_entity, run_node); } /************************************************************** * Scheduling class statistics methods: */ +#ifdef CONFIG_SCHED_DEBUG +int sched_nr_latency_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + + if (ret || !write) + return ret; + + sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency, + sysctl_sched_min_granularity); + + return 0; +} +#endif /* * The idea is to set a period in which each task runs once. @@ -224,11 +242,11 @@ static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq) static u64 __sched_period(unsigned long nr_running) { u64 period = sysctl_sched_latency; - unsigned long nr_latency = sysctl_sched_nr_latency; + unsigned long nr_latency = sched_nr_latency; if (unlikely(nr_running > nr_latency)) { + period = sysctl_sched_min_granularity; period *= nr_running; - do_div(period, nr_latency); } return period; @@ -259,6 +277,7 @@ static u64 __sched_vslice(unsigned long rq_weight, unsigned long nr_running) { u64 vslice = __sched_period(nr_running); + vslice *= NICE_0_LOAD; do_div(vslice, rq_weight); return vslice; @@ -329,6 +348,12 @@ static void update_curr(struct cfs_rq *cfs_rq) __update_curr(cfs_rq, curr, delta_exec); curr->exec_start = now; + + if (entity_is_task(curr)) { + struct task_struct *curtask = task_of(curr); + + cpuacct_charge(curtask, delta_exec); + } } static inline void @@ -355,6 +380,9 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) { schedstat_set(se->wait_max, max(se->wait_max, rq_of(cfs_rq)->clock - se->wait_start)); + 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); schedstat_set(se->wait_start, 0); } @@ -381,15 +409,6 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) se->exec_start = rq_of(cfs_rq)->clock; } -/* - * We are descheduling a task - update its stats: - */ -static inline void -update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ - se->exec_start = 0; -} - /************************************************** * Scheduling class queueing methods: */ @@ -415,6 +434,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) #ifdef CONFIG_SCHEDSTATS if (se->sleep_start) { u64 delta = rq_of(cfs_rq)->clock - se->sleep_start; + struct task_struct *tsk = task_of(se); if ((s64)delta < 0) delta = 0; @@ -424,9 +444,12 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) se->sleep_start = 0; se->sum_sleep_runtime += delta; + + account_scheduler_latency(tsk, delta >> 10, 1); } if (se->block_start) { u64 delta = rq_of(cfs_rq)->clock - se->block_start; + struct task_struct *tsk = task_of(se); if ((s64)delta < 0) delta = 0; @@ -443,11 +466,11 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) * time that the task spent sleeping: */ if (unlikely(prof_on == SLEEP_PROFILING)) { - struct task_struct *tsk = task_of(se); profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk), delta >> 20); } + account_scheduler_latency(tsk, delta >> 10, 0); } #endif } @@ -481,18 +504,25 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) } else if (sched_feat(APPROX_AVG) && cfs_rq->nr_running) vruntime += sched_vslice(cfs_rq)/2; + /* + * 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_add(cfs_rq, se); if (!initial) { + /* sleeps upto a single latency don't count. */ if (sched_feat(NEW_FAIR_SLEEPERS)) vruntime -= sysctl_sched_latency; - vruntime = max_t(s64, vruntime, se->vruntime); + /* ensure we never gain time by being placed backwards. */ + vruntime = max_vruntime(se->vruntime, vruntime); } se->vruntime = vruntime; - } static void @@ -607,8 +637,6 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) if (prev->on_rq) update_curr(cfs_rq); - update_stats_curr_end(cfs_rq, prev); - check_spread(cfs_rq, prev); if (prev->on_rq) { update_stats_wait_start(cfs_rq, prev); @@ -618,14 +646,30 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) cfs_rq->curr = NULL; } -static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr) +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); - if (cfs_rq->nr_running > 1) +#ifdef CONFIG_SCHED_HRTICK + /* + * queued ticks are scheduled to match the slice, so don't bother + * validating it and just reschedule. + */ + if (queued) + return resched_task(rq_of(cfs_rq)->curr); + /* + * 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 || !sched_feat(WAKEUP_PREEMPT)) check_preempt_tick(cfs_rq, curr); } @@ -666,7 +710,7 @@ static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu) /* Iterate thr' all leaf cfs_rq's on a runqueue */ #define for_each_leaf_cfs_rq(rq, cfs_rq) \ - list_for_each_entry(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) + list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list) /* Do the two (enqueued) entities belong to the same group ? */ static inline int @@ -728,6 +772,43 @@ static inline struct sched_entity *parent_entity(struct sched_entity *se) #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_SCHED_HRTICK +static void hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ + int requeue = rq->curr == p; + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + WARN_ON(task_rq(p) != rq); + + if (hrtick_enabled(rq) && cfs_rq->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 (rq->curr == p) + resched_task(p); + return; + } + + /* + * Don't schedule slices shorter than 10000ns, that just + * doesn't make sense. Rely on vruntime for fairness. + */ + if (!requeue) + delta = max(10000LL, delta); + + hrtick_start(rq, delta, requeue); + } +} +#else +static inline void +hrtick_start_fair(struct rq *rq, struct task_struct *p) +{ +} +#endif + /* * The enqueue_task method is called before nr_running is * increased. Here we update the fair scheduling stats and @@ -745,6 +826,8 @@ static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup) enqueue_entity(cfs_rq, se, wakeup); wakeup = 1; } + + hrtick_start_fair(rq, rq->curr); } /* @@ -765,6 +848,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) break; sleep = 1; } + + hrtick_start_fair(rq, rq->curr); } /* @@ -774,8 +859,9 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) */ static void yield_task_fair(struct rq *rq) { - struct cfs_rq *cfs_rq = task_cfs_rq(rq->curr); - struct sched_entity *rightmost, *se = &rq->curr->se; + struct task_struct *curr = rq->curr; + struct cfs_rq *cfs_rq = task_cfs_rq(curr); + struct sched_entity *rightmost, *se = &curr->se; /* * Are we the only task in the tree? @@ -783,7 +869,7 @@ static void yield_task_fair(struct rq *rq) if (unlikely(cfs_rq->nr_running == 1)) return; - if (likely(!sysctl_sched_compat_yield)) { + if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) { __update_rq_clock(rq); /* * Update run-time statistics of the 'current'. @@ -811,6 +897,154 @@ static void yield_task_fair(struct rq *rq) } /* + * 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. + * + * Returns the CPU we should wake onto. + */ +#if defined(ARCH_HAS_SCHED_WAKE_IDLE) +static int wake_idle(int cpu, struct task_struct *p) +{ + cpumask_t tmp; + struct sched_domain *sd; + int i; + + /* + * 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)->nr_running > 1) + return cpu; + + for_each_domain(cpu, sd) { + if (sd->flags & SD_WAKE_IDLE) { + cpus_and(tmp, sd->span, p->cpus_allowed); + for_each_cpu_mask(i, tmp) { + if (idle_cpu(i)) { + if (i != task_cpu(p)) { + schedstat_inc(p, + se.nr_wakeups_idle); + } + return i; + } + } + } else { + break; + } + } + return cpu; +} +#else +static inline int wake_idle(int cpu, struct task_struct *p) +{ + return cpu; +} +#endif + +#ifdef CONFIG_SMP +static int select_task_rq_fair(struct task_struct *p, int sync) +{ + int cpu, this_cpu; + struct rq *rq; + struct sched_domain *sd, *this_sd = NULL; + int new_cpu; + + cpu = task_cpu(p); + rq = task_rq(p); + this_cpu = smp_processor_id(); + new_cpu = cpu; + + if (cpu == this_cpu) + goto out_set_cpu; + + for_each_domain(this_cpu, sd) { + if (cpu_isset(cpu, sd->span)) { + this_sd = sd; + break; + } + } + + if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed))) + goto out_set_cpu; + + /* + * Check for affine wakeup and passive balancing possibilities. + */ + if (this_sd) { + int idx = this_sd->wake_idx; + unsigned int imbalance; + unsigned long load, this_load; + + imbalance = 100 + (this_sd->imbalance_pct - 100) / 2; + + load = source_load(cpu, idx); + this_load = target_load(this_cpu, idx); + + new_cpu = this_cpu; /* Wake to this CPU if we can */ + + if (this_sd->flags & SD_WAKE_AFFINE) { + unsigned long tl = this_load; + unsigned long tl_per_task; + + /* + * Attract cache-cold tasks on sync wakeups: + */ + if (sync && !task_hot(p, rq->clock, this_sd)) + goto out_set_cpu; + + schedstat_inc(p, se.nr_wakeups_affine_attempts); + tl_per_task = cpu_avg_load_per_task(this_cpu); + + /* + * If sync wakeup then subtract the (maximum possible) + * effect of the currently running task from the load + * of the current CPU: + */ + if (sync) + tl -= current->se.load.weight; + + if ((tl <= load && + tl + target_load(cpu, idx) <= tl_per_task) || + 100*(tl + p->se.load.weight) <= imbalance*load) { + /* + * 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(p, se.nr_wakeups_affine); + goto out_set_cpu; + } + } + + /* + * 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); + goto out_set_cpu; + } + } + } + + new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */ +out_set_cpu: + return wake_idle(new_cpu, p); +} +#endif /* CONFIG_SMP */ + + +/* * Preempt the current task with a newly woken task if needed: */ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) @@ -818,7 +1052,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) struct task_struct *curr = rq->curr; struct cfs_rq *cfs_rq = task_cfs_rq(curr); struct sched_entity *se = &curr->se, *pse = &p->se; - s64 delta; + unsigned long gran; if (unlikely(rt_prio(p->prio))) { update_rq_clock(rq); @@ -826,20 +1060,36 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p) resched_task(curr); return; } + /* + * Batch tasks do not preempt (their preemption is driven by + * the tick): + */ + if (unlikely(p->policy == SCHED_BATCH)) + return; + + if (!sched_feat(WAKEUP_PREEMPT)) + return; while (!is_same_group(se, pse)) { se = parent_entity(se); pse = parent_entity(pse); } - delta = se->vruntime - pse->vruntime; + gran = sysctl_sched_wakeup_granularity; + /* + * More easily preempt - nice tasks, while not making + * it harder for + nice tasks. + */ + if (unlikely(se->load.weight > NICE_0_LOAD)) + gran = calc_delta_fair(gran, &se->load); - if (delta > (s64)sysctl_sched_wakeup_granularity) + if (pse->vruntime + gran < se->vruntime) resched_task(curr); } static struct task_struct *pick_next_task_fair(struct rq *rq) { + struct task_struct *p; struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; @@ -851,7 +1101,10 @@ static struct task_struct *pick_next_task_fair(struct rq *rq) cfs_rq = group_cfs_rq(se); } while (cfs_rq); - return task_of(se); + p = task_of(se); + hrtick_start_fair(rq, p); + + return p; } /* @@ -868,6 +1121,7 @@ static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) } } +#ifdef CONFIG_SMP /************************************************** * Fair scheduling class load-balancing methods: */ @@ -913,7 +1167,7 @@ static int cfs_rq_best_prio(struct cfs_rq *cfs_rq) struct sched_entity *curr; struct task_struct *p; - if (!cfs_rq->nr_running) + if (!cfs_rq->nr_running || !first_fair(cfs_rq)) return MAX_PRIO; curr = cfs_rq->curr; @@ -928,12 +1182,11 @@ static int cfs_rq_best_prio(struct cfs_rq *cfs_rq) static unsigned long load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, + unsigned long max_load_move, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio) { struct cfs_rq *busy_cfs_rq; - unsigned long load_moved, total_nr_moved = 0, nr_moved; long rem_load_move = max_load_move; struct rq_iterator cfs_rq_iterator; @@ -961,40 +1214,63 @@ load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest, #else # define maxload rem_load_move #endif - /* pass busy_cfs_rq argument into + /* + * pass busy_cfs_rq argument into * load_balance_[start|next]_fair iterators */ cfs_rq_iterator.arg = busy_cfs_rq; - nr_moved = balance_tasks(this_rq, this_cpu, busiest, - max_nr_move, maxload, sd, idle, all_pinned, - &load_moved, this_best_prio, &cfs_rq_iterator); + rem_load_move -= balance_tasks(this_rq, this_cpu, busiest, + maxload, sd, idle, all_pinned, + this_best_prio, + &cfs_rq_iterator); - total_nr_moved += nr_moved; - max_nr_move -= nr_moved; - rem_load_move -= load_moved; - - if (max_nr_move <= 0 || rem_load_move <= 0) + if (rem_load_move <= 0) break; } return max_load_move - rem_load_move; } +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) +{ + struct cfs_rq *busy_cfs_rq; + struct rq_iterator cfs_rq_iterator; + + cfs_rq_iterator.start = load_balance_start_fair; + cfs_rq_iterator.next = load_balance_next_fair; + + for_each_leaf_cfs_rq(busiest, busy_cfs_rq) { + /* + * pass busy_cfs_rq argument into + * load_balance_[start|next]_fair iterators + */ + cfs_rq_iterator.arg = busy_cfs_rq; + if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle, + &cfs_rq_iterator)) + return 1; + } + + return 0; +} +#endif + /* * scheduler tick hitting a task of our scheduling class: */ -static void task_tick_fair(struct rq *rq, struct task_struct *curr) +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); + entity_tick(cfs_rq, se, queued); } } -#define swap(a,b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0) +#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0) /* * Share the fairness runtime between parent and child, thus the @@ -1007,14 +1283,16 @@ static void task_new_fair(struct rq *rq, struct task_struct *p) { struct cfs_rq *cfs_rq = task_cfs_rq(p); struct sched_entity *se = &p->se, *curr = cfs_rq->curr; + int this_cpu = smp_processor_id(); sched_info_queued(p); update_curr(cfs_rq); place_entity(cfs_rq, se, 1); - if (sysctl_sched_child_runs_first && - curr->vruntime < se->vruntime) { + /* 'curr' will be NULL if the child belongs to a different group */ + if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) && + curr && curr->vruntime < se->vruntime) { /* * Upon rescheduling, sched_class::put_prev_task() will place * 'current' within the tree based on its new key value. @@ -1022,14 +1300,46 @@ static void task_new_fair(struct rq *rq, struct task_struct *p) swap(curr->vruntime, se->vruntime); } - update_stats_enqueue(cfs_rq, se); - check_spread(cfs_rq, se); - check_spread(cfs_rq, curr); - __enqueue_entity(cfs_rq, se); - account_entity_enqueue(cfs_rq, se); + enqueue_task_fair(rq, p, 0); resched_task(rq->curr); } +/* + * 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, int running) +{ + /* + * 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 (running) { + if (p->prio > oldprio) + resched_task(rq->curr); + } else + check_preempt_curr(rq, p); +} + +/* + * We switched to the sched_fair class. + */ +static void switched_to_fair(struct rq *rq, struct task_struct *p, + int running) +{ + /* + * 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 (running) + resched_task(rq->curr); + else + check_preempt_curr(rq, p); +} + /* Account for a task changing its policy or group. * * This routine is mostly called to set cfs_rq->curr field when a task @@ -1043,6 +1353,16 @@ static void set_curr_task_fair(struct rq *rq) set_next_entity(cfs_rq_of(se), se); } +#ifdef CONFIG_FAIR_GROUP_SCHED +static void moved_group_fair(struct task_struct *p) +{ + struct cfs_rq *cfs_rq = task_cfs_rq(p); + + update_curr(cfs_rq); + place_entity(cfs_rq, &p->se, 1); +} +#endif + /* * All the scheduling class methods: */ @@ -1051,17 +1371,30 @@ static const struct sched_class fair_sched_class = { .enqueue_task = enqueue_task_fair, .dequeue_task = dequeue_task_fair, .yield_task = yield_task_fair, +#ifdef CONFIG_SMP + .select_task_rq = select_task_rq_fair, +#endif /* CONFIG_SMP */ .check_preempt_curr = check_preempt_wakeup, .pick_next_task = pick_next_task_fair, .put_prev_task = put_prev_task_fair, +#ifdef CONFIG_SMP .load_balance = load_balance_fair, + .move_one_task = move_one_task_fair, +#endif .set_curr_task = set_curr_task_fair, .task_tick = task_tick_fair, .task_new = task_new_fair, + + .prio_changed = prio_changed_fair, + .switched_to = switched_to_fair, + +#ifdef CONFIG_FAIR_GROUP_SCHED + .moved_group = moved_group_fair, +#endif }; #ifdef CONFIG_SCHED_DEBUG @@ -1072,7 +1405,9 @@ static void print_cfs_stats(struct seq_file *m, int cpu) #ifdef CONFIG_FAIR_GROUP_SCHED print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs); #endif + rcu_read_lock(); for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq) print_cfs_rq(m, cpu, cfs_rq); + rcu_read_unlock(); } #endif