diff options
Diffstat (limited to 'kernel/sched/fair.c')
| -rw-r--r-- | kernel/sched/fair.c | 1062 |
1 files changed, 706 insertions, 356 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 218f8e83db73..502e95a6e927 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -114,6 +114,12 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; #endif +/* + * The margin used when comparing utilization with CPU capacity: + * util * 1024 < capacity * margin + */ +unsigned int capacity_margin = 1280; /* ~20% */ + static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; @@ -256,9 +262,7 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq) static inline struct task_struct *task_of(struct sched_entity *se) { -#ifdef CONFIG_SCHED_DEBUG - WARN_ON_ONCE(!entity_is_task(se)); -#endif + SCHED_WARN_ON(!entity_is_task(se)); return container_of(se, struct task_struct, se); } @@ -456,17 +460,23 @@ static inline int entity_before(struct sched_entity *a, static void update_min_vruntime(struct cfs_rq *cfs_rq) { + struct sched_entity *curr = cfs_rq->curr; + u64 vruntime = cfs_rq->min_vruntime; - if (cfs_rq->curr) - vruntime = cfs_rq->curr->vruntime; + if (curr) { + if (curr->on_rq) + vruntime = curr->vruntime; + else + curr = NULL; + } if (cfs_rq->rb_leftmost) { struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost, struct sched_entity, run_node); - if (!cfs_rq->curr) + if (!curr) vruntime = se->vruntime; else vruntime = min_vruntime(vruntime, se->vruntime); @@ -656,7 +666,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se) } #ifdef CONFIG_SMP -static int select_idle_sibling(struct task_struct *p, int cpu); +static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu); static unsigned long task_h_load(struct task_struct *p); /* @@ -690,6 +700,11 @@ void init_entity_runnable_average(struct sched_entity *se) /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */ } +static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); +static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq); +static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force); +static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se); + /* * With new tasks being created, their initial util_avgs are extrapolated * based on the cfs_rq's current util_avg: @@ -720,6 +735,7 @@ void post_init_entity_util_avg(struct sched_entity *se) struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2; + u64 now = cfs_rq_clock_task(cfs_rq); if (cap > 0) { if (cfs_rq->avg.util_avg != 0) { @@ -733,18 +749,41 @@ void post_init_entity_util_avg(struct sched_entity *se) } sa->util_sum = sa->util_avg * LOAD_AVG_MAX; } + + if (entity_is_task(se)) { + struct task_struct *p = task_of(se); + if (p->sched_class != &fair_sched_class) { + /* + * For !fair tasks do: + * + update_cfs_rq_load_avg(now, cfs_rq, false); + attach_entity_load_avg(cfs_rq, se); + switched_from_fair(rq, p); + * + * such that the next switched_to_fair() has the + * expected state. + */ + se->avg.last_update_time = now; + return; + } + } + + update_cfs_rq_load_avg(now, cfs_rq, false); + attach_entity_load_avg(cfs_rq, se); + update_tg_load_avg(cfs_rq, false); } -static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq); -static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq); -#else +#else /* !CONFIG_SMP */ void init_entity_runnable_average(struct sched_entity *se) { } void post_init_entity_util_avg(struct sched_entity *se) { } -#endif +static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) +{ +} +#endif /* CONFIG_SMP */ /* * Update the current task's runtime statistics. @@ -768,7 +807,7 @@ static void update_curr(struct cfs_rq *cfs_rq) max(delta_exec, curr->statistics.exec_max)); curr->sum_exec_runtime += delta_exec; - schedstat_add(cfs_rq, exec_clock, delta_exec); + schedstat_add(cfs_rq->exec_clock, delta_exec); curr->vruntime += calc_delta_fair(delta_exec, curr); update_min_vruntime(cfs_rq); @@ -789,26 +828,34 @@ static void update_curr_fair(struct rq *rq) update_curr(cfs_rq_of(&rq->curr->se)); } -#ifdef CONFIG_SCHEDSTATS static inline void update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) { - u64 wait_start = rq_clock(rq_of(cfs_rq)); + u64 wait_start, prev_wait_start; + + if (!schedstat_enabled()) + return; + + wait_start = rq_clock(rq_of(cfs_rq)); + prev_wait_start = schedstat_val(se->statistics.wait_start); if (entity_is_task(se) && task_on_rq_migrating(task_of(se)) && - likely(wait_start > se->statistics.wait_start)) - wait_start -= se->statistics.wait_start; + likely(wait_start > prev_wait_start)) + wait_start -= prev_wait_start; - se->statistics.wait_start = wait_start; + schedstat_set(se->statistics.wait_start, wait_start); } -static void +static inline void update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) { struct task_struct *p; u64 delta; - delta = rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start; + if (!schedstat_enabled()) + return; + + delta = rq_clock(rq_of(cfs_rq)) - schedstat_val(se->statistics.wait_start); if (entity_is_task(se)) { p = task_of(se); @@ -818,35 +865,114 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) * time stamp can be adjusted to accumulate wait time * prior to migration. */ - se->statistics.wait_start = delta; + schedstat_set(se->statistics.wait_start, delta); return; } trace_sched_stat_wait(p, delta); } - se->statistics.wait_max = max(se->statistics.wait_max, delta); - se->statistics.wait_count++; - se->statistics.wait_sum += delta; - se->statistics.wait_start = 0; + schedstat_set(se->statistics.wait_max, + max(schedstat_val(se->statistics.wait_max), delta)); + schedstat_inc(se->statistics.wait_count); + schedstat_add(se->statistics.wait_sum, delta); + schedstat_set(se->statistics.wait_start, 0); +} + +static inline void +update_stats_enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct task_struct *tsk = NULL; + u64 sleep_start, block_start; + + if (!schedstat_enabled()) + return; + + sleep_start = schedstat_val(se->statistics.sleep_start); + block_start = schedstat_val(se->statistics.block_start); + + if (entity_is_task(se)) + tsk = task_of(se); + + if (sleep_start) { + u64 delta = rq_clock(rq_of(cfs_rq)) - sleep_start; + + if ((s64)delta < 0) + delta = 0; + + if (unlikely(delta > schedstat_val(se->statistics.sleep_max))) + schedstat_set(se->statistics.sleep_max, delta); + + schedstat_set(se->statistics.sleep_start, 0); + schedstat_add(se->statistics.sum_sleep_runtime, delta); + + if (tsk) { + account_scheduler_latency(tsk, delta >> 10, 1); + trace_sched_stat_sleep(tsk, delta); + } + } + if (block_start) { + u64 delta = rq_clock(rq_of(cfs_rq)) - block_start; + + if ((s64)delta < 0) + delta = 0; + + if (unlikely(delta > schedstat_val(se->statistics.block_max))) + schedstat_set(se->statistics.block_max, delta); + + schedstat_set(se->statistics.block_start, 0); + schedstat_add(se->statistics.sum_sleep_runtime, delta); + + if (tsk) { + if (tsk->in_iowait) { + schedstat_add(se->statistics.iowait_sum, delta); + schedstat_inc(se->statistics.iowait_count); + trace_sched_stat_iowait(tsk, delta); + } + + trace_sched_stat_blocked(tsk, delta); + + /* + * Blocking time is in units of nanosecs, so shift by + * 20 to get a milliseconds-range estimation of the + * amount of time that the task spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + profile_hits(SLEEP_PROFILING, + (void *)get_wchan(tsk), + delta >> 20); + } + account_scheduler_latency(tsk, delta >> 10, 0); + } + } } /* * Task is being enqueued - update stats: */ static inline void -update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) +update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { + if (!schedstat_enabled()) + return; + /* * Are we enqueueing a waiting task? (for current tasks * a dequeue/enqueue event is a NOP) */ if (se != cfs_rq->curr) update_stats_wait_start(cfs_rq, se); + + if (flags & ENQUEUE_WAKEUP) + update_stats_enqueue_sleeper(cfs_rq, se); } static inline void update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { + + if (!schedstat_enabled()) + return; + /* * Mark the end of the wait period if dequeueing a * waiting task: @@ -854,39 +980,17 @@ update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (se != cfs_rq->curr) update_stats_wait_end(cfs_rq, se); - if (flags & DEQUEUE_SLEEP) { - if (entity_is_task(se)) { - struct task_struct *tsk = task_of(se); + if ((flags & DEQUEUE_SLEEP) && entity_is_task(se)) { + struct task_struct *tsk = task_of(se); - if (tsk->state & TASK_INTERRUPTIBLE) - se->statistics.sleep_start = rq_clock(rq_of(cfs_rq)); - if (tsk->state & TASK_UNINTERRUPTIBLE) - se->statistics.block_start = rq_clock(rq_of(cfs_rq)); - } + if (tsk->state & TASK_INTERRUPTIBLE) + schedstat_set(se->statistics.sleep_start, + rq_clock(rq_of(cfs_rq))); + if (tsk->state & TASK_UNINTERRUPTIBLE) + schedstat_set(se->statistics.block_start, + rq_clock(rq_of(cfs_rq))); } - -} -#else -static inline void -update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} - -static inline void -update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} - -static inline void -update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -} - -static inline void -update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) -{ } -#endif /* * We are picking a new current task - update its stats: @@ -1305,6 +1409,8 @@ static void task_numa_assign(struct task_numa_env *env, { if (env->best_task) put_task_struct(env->best_task); + if (p) + get_task_struct(p); env->best_task = p; env->best_imp = imp; @@ -1372,31 +1478,11 @@ static void task_numa_compare(struct task_numa_env *env, long imp = env->p->numa_group ? groupimp : taskimp; long moveimp = imp; int dist = env->dist; - bool assigned = false; rcu_read_lock(); - - raw_spin_lock_irq(&dst_rq->lock); - cur = dst_rq->curr; - /* - * No need to move the exiting task or idle task. - */ - if ((cur->flags & PF_EXITING) || is_idle_task(cur)) + cur = task_rcu_dereference(&dst_rq->curr); + if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur))) cur = NULL; - else { - /* - * The task_struct must be protected here to protect the - * p->numa_faults access in the task_weight since the - * numa_faults could already be freed in the following path: - * finish_task_switch() - * --> put_task_struct() - * --> __put_task_struct() - * --> task_numa_free() - */ - get_task_struct(cur); - } - - raw_spin_unlock_irq(&dst_rq->lock); /* * Because we have preemption enabled we can get migrated around and @@ -1479,7 +1565,6 @@ balance: */ if (!load_too_imbalanced(src_load, dst_load, env)) { imp = moveimp - 1; - put_task_struct(cur); cur = NULL; goto assign; } @@ -1501,20 +1586,21 @@ balance: * One idle CPU per node is evaluated for a task numa move. * Call select_idle_sibling to maybe find a better one. */ - if (!cur) - env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu); + if (!cur) { + /* + * select_idle_siblings() uses an per-cpu cpumask that + * can be used from IRQ context. + */ + local_irq_disable(); + env->dst_cpu = select_idle_sibling(env->p, env->src_cpu, + env->dst_cpu); + local_irq_enable(); + } assign: - assigned = true; task_numa_assign(env, cur, imp); unlock: rcu_read_unlock(); - /* - * The dst_rq->curr isn't assigned. The protection for task_struct is - * finished. - */ - if (cur && !assigned) - put_task_struct(cur); } static void task_numa_find_cpu(struct task_numa_env *env, @@ -2287,7 +2373,7 @@ void task_numa_work(struct callback_head *work) unsigned long nr_pte_updates = 0; long pages, virtpages; - WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work)); + SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work)); work->next = work; /* protect against double add */ /* @@ -2499,28 +2585,22 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) #ifdef CONFIG_FAIR_GROUP_SCHED # ifdef CONFIG_SMP -static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq) +static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) { - long tg_weight; + long tg_weight, load, shares; /* - * Use this CPU's real-time load instead of the last load contribution - * as the updating of the contribution is delayed, and we will use the - * the real-time load to calc the share. See update_tg_load_avg(). + * This really should be: cfs_rq->avg.load_avg, but instead we use + * cfs_rq->load.weight, which is its upper bound. This helps ramp up + * the shares for small weight interactive tasks. */ - tg_weight = atomic_long_read(&tg->load_avg); - tg_weight -= cfs_rq->tg_load_avg_contrib; - tg_weight += cfs_rq->load.weight; - - return tg_weight; -} + load = scale_load_down(cfs_rq->load.weight); -static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) -{ - long tg_weight, load, shares; + tg_weight = atomic_long_read(&tg->load_avg); - tg_weight = calc_tg_weight(tg, cfs_rq); - load = cfs_rq->load.weight; + /* Ensure tg_weight >= load */ + tg_weight -= cfs_rq->tg_load_avg_contrib; + tg_weight += load; shares = (tg->shares * load); if (tg_weight) @@ -2539,6 +2619,7 @@ static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) return tg->shares; } # endif /* CONFIG_SMP */ + static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, unsigned long weight) { @@ -2803,9 +2884,21 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa, } #ifdef CONFIG_FAIR_GROUP_SCHED -/* - * Updating tg's load_avg is necessary before update_cfs_share (which is done) - * and effective_load (which is not done because it is too costly). +/** + * update_tg_load_avg - update the tg's load avg + * @cfs_rq: the cfs_rq whose avg changed + * @force: update regardless of how small the difference + * + * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load. + * However, because tg->load_avg is a global value there are performance + * considerations. + * + * In order to avoid having to look at the other cfs_rq's, we use a + * differential update where we store the last value we propagated. This in + * turn allows skipping updates if the differential is 'small'. + * + * Updating tg's load_avg is necessary before update_cfs_share() (which is + * done) and effective_load() (which is not done because it is too costly). */ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) { @@ -2873,16 +2966,9 @@ void set_task_rq_fair(struct sched_entity *se, static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} #endif /* CONFIG_FAIR_GROUP_SCHED */ -static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); - static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) { - struct rq *rq = rq_of(cfs_rq); - int cpu = cpu_of(rq); - - if (cpu == smp_processor_id() && &rq->cfs == cfs_rq) { - unsigned long max = rq->cpu_capacity_orig; - + if (&this_rq()->cfs == cfs_rq) { /* * There are a few boundary cases this might miss but it should * get called often enough that that should (hopefully) not be @@ -2899,12 +2985,44 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) * * See cpu_util(). */ - cpufreq_update_util(rq_clock(rq), - min(cfs_rq->avg.util_avg, max), max); + cpufreq_update_util(rq_of(cfs_rq), 0); } } -/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */ +/* + * Unsigned subtract and clamp on underflow. + * + * Explicitly do a load-store to ensure the intermediate value never hits + * memory. This allows lockless observations without ever seeing the negative + * values. + */ +#define sub_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + typeof(*ptr) val = (_val); \ + typeof(*ptr) res, var = READ_ONCE(*ptr); \ + res = var - val; \ + if (res > var) \ + res = 0; \ + WRITE_ONCE(*ptr, res); \ +} while (0) + +/** + * update_cfs_rq_load_avg - update the cfs_rq's load/util averages + * @now: current time, as per cfs_rq_clock_task() + * @cfs_rq: cfs_rq to update + * @update_freq: should we call cfs_rq_util_change() or will the call do so + * + * The cfs_rq avg is the direct sum of all its entities (blocked and runnable) + * avg. The immediate corollary is that all (fair) tasks must be attached, see + * post_init_entity_util_avg(). + * + * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example. + * + * Returns true if the load decayed or we removed load. + * + * Since both these conditions indicate a changed cfs_rq->avg.load we should + * call update_tg_load_avg() when this function returns true. + */ static inline int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) { @@ -2913,15 +3031,15 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) if (atomic_long_read(&cfs_rq->removed_load_avg)) { s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0); - sa->load_avg = max_t(long, sa->load_avg - r, 0); - sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0); + sub_positive(&sa->load_avg, r); + sub_positive(&sa->load_sum, r * LOAD_AVG_MAX); removed_load = 1; } if (atomic_long_read(&cfs_rq->removed_util_avg)) { long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0); - sa->util_avg = max_t(long, sa->util_avg - r, 0); - sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0); + sub_positive(&sa->util_avg, r); + sub_positive(&sa->util_sum, r * LOAD_AVG_MAX); removed_util = 1; } @@ -2959,6 +3077,14 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) update_tg_load_avg(cfs_rq, 0); } +/** + * attach_entity_load_avg - attach this entity to its cfs_rq load avg + * @cfs_rq: cfs_rq to attach to + * @se: sched_entity to attach + * + * Must call update_cfs_rq_load_avg() before this, since we rely on + * cfs_rq->avg.last_update_time being current. + */ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { if (!sched_feat(ATTACH_AGE_LOAD)) @@ -2967,6 +3093,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s /* * If we got migrated (either between CPUs or between cgroups) we'll * have aged the average right before clearing @last_update_time. + * + * Or we're fresh through post_init_entity_util_avg(). */ if (se->avg.last_update_time) { __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)), @@ -2988,16 +3116,24 @@ skip_aging: cfs_rq_util_change(cfs_rq); } +/** + * detach_entity_load_avg - detach this entity from its cfs_rq load avg + * @cfs_rq: cfs_rq to detach from + * @se: sched_entity to detach + * + * Must call update_cfs_rq_load_avg() before this, since we rely on + * cfs_rq->avg.last_update_time being current. + */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL); - cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0); - cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0); - cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0); - cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0); + sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); + sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum); + sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); + sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); cfs_rq_util_change(cfs_rq); } @@ -3072,11 +3208,14 @@ void remove_entity_load_avg(struct sched_entity *se) u64 last_update_time; /* - * Newly created task or never used group entity should not be removed - * from its (source) cfs_rq + * tasks cannot exit without having gone through wake_up_new_task() -> + * post_init_entity_util_avg() which will have added things to the + * cfs_rq, so we can remove unconditionally. + * + * Similarly for groups, they will have passed through + * post_init_entity_util_avg() before unregister_sched_fair_group() + * calls this. */ - if (se->avg.last_update_time == 0) - return; last_update_time = cfs_rq_last_update_time(cfs_rq); @@ -3099,12 +3238,15 @@ static int idle_balance(struct rq *this_rq); #else /* CONFIG_SMP */ -static inline void update_load_avg(struct sched_entity *se, int not_used) +static inline int +update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) { - struct cfs_rq *cfs_rq = cfs_rq_of(se); - struct rq *rq = rq_of(cfs_rq); + return 0; +} - cpufreq_trigger_update(rq_clock(rq)); +static inline void update_load_avg(struct sched_entity *se, int not_used) +{ + cpufreq_update_util(rq_of(cfs_rq_of(se)), 0); } static inline void @@ -3125,68 +3267,6 @@ static inline int idle_balance(struct rq *rq) #endif /* CONFIG_SMP */ -static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se) -{ -#ifdef CONFIG_SCHEDSTATS - struct task_struct *tsk = NULL; - - if (entity_is_task(se)) - tsk = task_of(se); - - if (se->statistics.sleep_start) { - u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start; - - if ((s64)delta < 0) - delta = 0; - - if (unlikely(delta > se->statistics.sleep_max)) - se->statistics.sleep_max = delta; - - se->statistics.sleep_start = 0; - se->statistics.sum_sleep_runtime += delta; - - if (tsk) { - account_scheduler_latency(tsk, delta >> 10, 1); - trace_sched_stat_sleep(tsk, delta); - } - } - if (se->statistics.block_start) { - u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start; - - if ((s64)delta < 0) - delta = 0; - - if (unlikely(delta > se->statistics.block_max)) - se->statistics.block_max = delta; - - se->statistics.block_start = 0; - se->statistics.sum_sleep_runtime += delta; - - if (tsk) { - if (tsk->in_iowait) { - se->statistics.iowait_sum += delta; - se->statistics.iowait_count++; - trace_sched_stat_iowait(tsk, delta); - } - - trace_sched_stat_blocked(tsk, delta); - - /* - * Blocking time is in units of nanosecs, so shift by - * 20 to get a milliseconds-range estimation of the - * amount of time that the task spent sleeping: - */ - if (unlikely(prof_on == SLEEP_PROFILING)) { - profile_hits(SLEEP_PROFILING, - (void *)get_wchan(tsk), - delta >> 20); - } - account_scheduler_latency(tsk, delta >> 10, 0); - } - } -#endif -} - static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) { #ifdef CONFIG_SCHED_DEBUG @@ -3196,7 +3276,7 @@ static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se) d = -d; if (d > 3*sysctl_sched_latency) - schedstat_inc(cfs_rq, nr_spread_over); + schedstat_inc(cfs_rq->nr_spread_over); #endif } @@ -3246,7 +3326,7 @@ static inline void check_schedstat_required(void) trace_sched_stat_iowait_enabled() || trace_sched_stat_blocked_enabled() || trace_sched_stat_runtime_enabled()) { - pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, " + printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, " "stat_blocked and stat_runtime require the " "kernel parameter schedstats=enabled or " "kernel.sched_schedstats=1\n"); @@ -3313,17 +3393,12 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) account_entity_enqueue(cfs_rq, se); update_cfs_shares(cfs_rq); - if (flags & ENQUEUE_WAKEUP) { + if (flags & ENQUEUE_WAKEUP) place_entity(cfs_rq, se, 0); - if (schedstat_enabled()) - enqueue_sleeper(cfs_rq, se); - } check_schedstat_required(); - if (schedstat_enabled()) { - update_stats_enqueue(cfs_rq, se); - check_spread(cfs_rq, se); - } + update_stats_enqueue(cfs_rq, se, flags); + check_spread(cfs_rq, se); if (!curr) __enqueue_entity(cfs_rq, se); se->on_rq = 1; @@ -3390,8 +3465,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) update_curr(cfs_rq); dequeue_entity_load_avg(cfs_rq, se); - if (schedstat_enabled()) - update_stats_dequeue(cfs_rq, se, flags); + update_stats_dequeue(cfs_rq, se, flags); clear_buddies(cfs_rq, se); @@ -3401,9 +3475,10 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) account_entity_dequeue(cfs_rq, se); /* - * 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. + * Normalize after update_curr(); which will also have moved + * min_vruntime if @se is the one holding it back. But before doing + * update_min_vruntime() again, which will discount @se's position and + * can move min_vruntime forward still more. */ if (!(flags & DEQUEUE_SLEEP)) se->vruntime -= cfs_rq->min_vruntime; @@ -3411,8 +3486,16 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* return excess runtime on last dequeue */ return_cfs_rq_runtime(cfs_rq); - update_min_vruntime(cfs_rq); update_cfs_shares(cfs_rq); + + /* + * Now advance min_vruntime if @se was the entity holding it back, + * except when: DEQUEUE_SAVE && !DEQUEUE_MOVE, in this case we'll be + * put back on, and if we advance min_vruntime, we'll be placed back + * further than we started -- ie. we'll be penalized. + */ + if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE) + update_min_vruntime(cfs_rq); } /* @@ -3465,25 +3548,25 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * a CPU. So account for the time it spent waiting on the * runqueue. */ - if (schedstat_enabled()) - update_stats_wait_end(cfs_rq, se); + update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); update_load_avg(se, 1); } update_stats_curr_start(cfs_rq, se); cfs_rq->curr = se; -#ifdef CONFIG_SCHEDSTATS + /* * Track our maximum slice length, if the CPU's load is at * least twice that of our own weight (i.e. dont track it * when there are only lesser-weight tasks around): */ if (schedstat_enabled() && rq_of(cfs_rq)->load.weight >= 2*se->load.weight) { - se->statistics.slice_max = max(se->statistics.slice_max, - se->sum_exec_runtime - se->prev_sum_exec_runtime); + schedstat_set(se->statistics.slice_max, + max((u64)schedstat_val(se->statistics.slice_max), + se->sum_exec_runtime - se->prev_sum_exec_runtime)); } -#endif + se->prev_sum_exec_runtime = se->sum_exec_runtime; } @@ -3562,13 +3645,10 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev) /* throttle cfs_rqs exceeding runtime */ check_cfs_rq_runtime(cfs_rq); - if (schedstat_enabled()) { - check_spread(cfs_rq, prev); - if (prev->on_rq) - update_stats_wait_start(cfs_rq, prev); - } + check_spread(cfs_rq, prev); if (prev->on_rq) { + update_stats_wait_start(cfs_rq, prev); /* Put 'current' back into the tree. */ __enqueue_entity(cfs_rq, prev); /* in !on_rq case, update occurred at dequeue */ @@ -3688,7 +3768,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) { if (unlikely(cfs_rq->throttle_count)) - return cfs_rq->throttled_clock_task; + return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time; return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time; } @@ -3826,13 +3906,11 @@ static int tg_unthrottle_up(struct task_group *tg, void *data) struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)]; cfs_rq->throttle_count--; -#ifdef CONFIG_SMP if (!cfs_rq->throttle_count) { /* adjust cfs_rq_clock_task() */ cfs_rq->throttled_clock_task_time += rq_clock_task(rq) - cfs_rq->throttled_clock_task; } -#endif return 0; } @@ -4199,6 +4277,23 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq) throttle_cfs_rq(cfs_rq); } +static void sync_throttle(struct task_group *tg, int cpu) +{ + struct cfs_rq *pcfs_rq, *cfs_rq; + + if (!cfs_bandwidth_used()) + return; + + if (!tg->parent) + return; + + cfs_rq = tg->cfs_rq[cpu]; + pcfs_rq = tg->parent->cfs_rq[cpu]; + + cfs_rq->throttle_count = pcfs_rq->throttle_count; + cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu)); +} + /* conditionally throttle active cfs_rq's from put_prev_entity() */ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { @@ -4338,6 +4433,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq) static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {} static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; } static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {} +static inline void sync_throttle(struct task_group *tg, int cpu) {} static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {} static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq) @@ -4382,9 +4478,9 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p) struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); - WARN_ON(task_rq(p) != rq); + SCHED_WARN_ON(task_rq(p) != rq); - if (cfs_rq->nr_running > 1) { + if (rq->cfs.h_nr_running > 1) { u64 slice = sched_slice(cfs_rq, se); u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime; s64 delta = slice - ran; @@ -4435,6 +4531,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + /* + * If in_iowait is set, the code below may not trigger any cpufreq + * utilization updates, so do it here explicitly with the IOWAIT flag + * passed. + */ + if (p->in_iowait) + cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT); + for_each_sched_entity(se) { if (se->on_rq) break; @@ -4446,7 +4550,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) * * note: in the case of encountering a throttled cfs_rq we will * post the final h_nr_running increment below. - */ + */ if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running++; @@ -4500,15 +4604,14 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { + /* Avoid re-evaluating load for this entity: */ + se = parent_entity(se); /* * Bias pick_next to pick a task from this cfs_rq, as * p is sleeping when it is within its sched_slice. */ - if (task_sleep && parent_entity(se)) - set_next_buddy(parent_entity(se)); - - /* avoid re-evaluating load for this entity */ - se = parent_entity(se); + if (task_sleep && se && !throttled_hierarchy(cfs_rq)) + set_next_buddy(se); break; } flags |= DEQUEUE_SLEEP; @@ -4532,6 +4635,11 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) } #ifdef CONFIG_SMP + +/* Working cpumask for: load_balance, load_balance_newidle. */ +DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); +DEFINE_PER_CPU(cpumask_var_t, select_idle_mask); + #ifdef CONFIG_NO_HZ_COMMON /* * per rq 'load' arrray crap; XXX kill this. @@ -4910,27 +5018,32 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg) return wl; for_each_sched_entity(se) { - long w, W; + struct cfs_rq *cfs_rq = se->my_q; + long W, w = cfs_rq_load_avg(cfs_rq); - tg = se->my_q->tg; + tg = cfs_rq->tg; /* * W = @wg + \Sum rw_j */ - W = wg + calc_tg_weight(tg, se->my_q); + W = wg + atomic_long_read(&tg->load_avg); + + /* Ensure \Sum rw_j >= rw_i */ + W -= cfs_rq->tg_load_avg_contrib; + W += w; /* * w = rw_i + @wl */ - w = cfs_rq_load_avg(se->my_q) + wl; + w += wl; /* * wl = S * s'_i; see (2) */ if (W > 0 && w < W) - wl = (w * (long)tg->shares) / W; + wl = (w * (long)scale_load_down(tg->shares)) / W; else - wl = tg->shares; + wl = scale_load_down(tg->shares); /* * Per the above, wl is the new se->load.weight value; since @@ -5013,18 +5126,18 @@ static int wake_wide(struct task_struct *p) return 1; } -static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) +static int wake_affine(struct sched_domain *sd, struct task_struct *p, + int prev_cpu, int sync) { s64 this_load, load; s64 this_eff_load, prev_eff_load; - int idx, this_cpu, prev_cpu; + int idx, this_cpu; struct task_group *tg; unsigned long weight; int balanced; 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); @@ -5068,13 +5181,13 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) balanced = this_eff_load <= prev_eff_load; - schedstat_inc(p, se.statistics.nr_wakeups_affine_attempts); + schedstat_inc(p->se.statistics.nr_wakeups_affine_attempts); if (!balanced) return 0; - schedstat_inc(sd, ttwu_move_affine); - schedstat_inc(p, se.statistics.nr_wakeups_affine); + schedstat_inc(sd->ttwu_move_affine); + schedstat_inc(p->se.statistics.nr_wakeups_affine); return 1; } @@ -5150,6 +5263,10 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) int shallowest_idle_cpu = -1; int i; + /* Check if we have any choice: */ + if (group->group_weight == 1) + return cpumask_first(sched_group_cpus(group)); + /* Traverse only the allowed CPUs */ for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) { if (idle_cpu(i)) { @@ -5187,64 +5304,237 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) } /* - * Try and locate an idle CPU in the sched_domain. + * Implement a for_each_cpu() variant that starts the scan at a given cpu + * (@start), and wraps around. + * + * This is used to scan for idle CPUs; such that not all CPUs looking for an + * idle CPU find the same CPU. The down-side is that tasks tend to cycle + * through the LLC domain. + * + * Especially tbench is found sensitive to this. + */ + +static int cpumask_next_wrap(int n, const struct cpumask *mask, int start, int *wrapped) +{ + int next; + +again: + next = find_next_bit(cpumask_bits(mask), nr_cpumask_bits, n+1); + + if (*wrapped) { + if (next >= start) + return nr_cpumask_bits; + } else { + if (next >= nr_cpumask_bits) { + *wrapped = 1; + n = -1; + goto again; + } + } + + return next; +} + +#define for_each_cpu_wrap(cpu, mask, start, wrap) \ + for ((wrap) = 0, (cpu) = (start)-1; \ + (cpu) = cpumask_next_wrap((cpu), (mask), (start), &(wrap)), \ + (cpu) < nr_cpumask_bits; ) + +#ifdef CONFIG_SCHED_SMT + +static inline void set_idle_cores(int cpu, int val) +{ + struct sched_domain_shared *sds; + + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) + WRITE_ONCE(sds->has_idle_cores, val); +} + +static inline bool test_idle_cores(int cpu, bool def) +{ + struct sched_domain_shared *sds; + + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) + return READ_ONCE(sds->has_idle_cores); + + return def; +} + +/* + * Scans the local SMT mask to see if the entire core is idle, and records this + * information in sd_llc_shared->has_idle_cores. + * + * Since SMT siblings share all cache levels, inspecting this limited remote + * state should be fairly cheap. + */ +void __update_idle_core(struct rq *rq) +{ + int core = cpu_of(rq); + int cpu; + + rcu_read_lock(); + if (test_idle_cores(core, true)) + goto unlock; + + for_each_cpu(cpu, cpu_smt_mask(core)) { + if (cpu == core) + continue; + + if (!idle_cpu(cpu)) + goto unlock; + } + + set_idle_cores(core, 1); +unlock: + rcu_read_unlock(); +} + +/* + * Scan the entire LLC domain for idle cores; this dynamically switches off if + * there are no idle cores left in the system; tracked through + * sd_llc->shared->has_idle_cores and enabled through update_idle_core() above. + */ +static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target) +{ + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); + int core, cpu, wrap; + + if (!static_branch_likely(&sched_smt_present)) + return -1; + + if (!test_idle_cores(target, false)) + return -1; + + cpumask_and(cpus, sched_domain_span(sd), tsk_cpus_allowed(p)); + + for_each_cpu_wrap(core, cpus, target, wrap) { + bool idle = true; + + for_each_cpu(cpu, cpu_smt_mask(core)) { + cpumask_clear_cpu(cpu, cpus); + if (!idle_cpu(cpu)) + idle = false; + } + + if (idle) + return core; + } + + /* + * Failed to find an idle core; stop looking for one. + */ + set_idle_cores(target, 0); + + return -1; +} + +/* + * Scan the local SMT mask for idle CPUs. + */ +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) +{ + int cpu; + + if (!static_branch_likely(&sched_smt_present)) + return -1; + + for_each_cpu(cpu, cpu_smt_mask(target)) { + if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + continue; + if (idle_cpu(cpu)) + return cpu; + } + + return -1; +} + +#else /* CONFIG_SCHED_SMT */ + +static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target) +{ + return -1; +} + +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) +{ + return -1; +} + +#endif /* CONFIG_SCHED_SMT */ + +/* + * Scan the LLC domain for idle CPUs; this is dynamically regulated by + * comparing the average scan cost (tracked in sd->avg_scan_cost) against the + * average idle time for this rq (as found in rq->avg_idle). */ -static int select_idle_sibling(struct task_struct *p, int target) +static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target) +{ + struct sched_domain *this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); + u64 avg_idle = this_rq()->avg_idle; + u64 avg_cost = this_sd->avg_scan_cost; + u64 time, cost; + s64 delta; + int cpu, wrap; + + /* + * Due to large variance we need a large fuzz factor; hackbench in + * particularly is sensitive here. + */ + if ((avg_idle / 512) < avg_cost) + return -1; + + time = local_clock(); + + for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) { + if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + continue; + if (idle_cpu(cpu)) + break; + } + + time = local_clock() - time; + cost = this_sd->avg_scan_cost; + delta = (s64)(time - cost) / 8; + this_sd->avg_scan_cost += delta; + + return cpu; +} + +/* + * Try and locate an idle core/thread in the LLC cache domain. + */ +static int select_idle_sibling(struct task_struct *p, int prev, int target) { struct sched_domain *sd; - struct sched_group *sg; - int i = task_cpu(p); + int i; if (idle_cpu(target)) return target; /* - * If the prevous cpu is cache affine and idle, don't be stupid. + * If the previous cpu is cache affine and idle, don't be stupid. */ - if (i != target && cpus_share_cache(i, target) && idle_cpu(i)) - return i; + if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev)) + return prev; - /* - * Otherwise, iterate the domains and find an eligible idle cpu. - * - * A completely idle sched group at higher domains is more - * desirable than an idle group at a lower level, because lower - * domains have smaller groups and usually share hardware - * resources which causes tasks to contend on them, e.g. x86 - * hyperthread siblings in the lowest domain (SMT) can contend - * on the shared cpu pipeline. - * - * However, while we prefer idle groups at higher domains - * finding an idle cpu at the lowest domain is still better than - * returning 'target', which we've already established, isn't - * idle. - */ sd = rcu_dereference(per_cpu(sd_llc, target)); - for_each_lower_domain(sd) { - sg = sd->groups; - do { - if (!cpumask_intersects(sched_group_cpus(sg), - tsk_cpus_allowed(p))) - goto next; - - /* Ensure the entire group is idle */ - for_each_cpu(i, sched_group_cpus(sg)) { - if (i == target || !idle_cpu(i)) - goto next; - } + if (!sd) + return target; + + i = select_idle_core(p, sd, target); + if ((unsigned)i < nr_cpumask_bits) + return i; + + i = select_idle_cpu(p, sd, target); + if ((unsigned)i < nr_cpumask_bits) + return i; + + i = select_idle_smt(p, sd, target); + if ((unsigned)i < nr_cpumask_bits) + return i; - /* - * It doesn't matter which cpu we pick, the - * whole group is idle. - */ - target = cpumask_first_and(sched_group_cpus(sg), - tsk_cpus_allowed(p)); - goto done; -next: - sg = sg->next; - } while (sg != sd->groups); - } -done: return target; } @@ -5282,6 +5572,32 @@ static int cpu_util(int cpu) return (util >= capacity) ? capacity : util; } +static inline int task_util(struct task_struct *p) +{ + return p->se.avg.util_avg; +} + +/* + * Disable WAKE_AFFINE in the case where task @p doesn't fit in the + * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu. + * + * In that case WAKE_AFFINE doesn't make sense and we'll let + * BALANCE_WAKE sort things out. + */ +static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) +{ + long min_cap, max_cap; + + min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu)); + max_cap = cpu_rq(cpu)->rd->max_cpu_capacity; + + /* Minimum capacity is close to max, no need to abort wake_affine */ + if (max_cap - min_cap < max_cap >> 3) + return 0; + + return min_cap * 1024 < task_util(p) * capacity_margin; +} + /* * select_task_rq_fair: Select target runqueue for the waking task in domains * that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE, @@ -5305,7 +5621,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (sd_flag & SD_BALANCE_WAKE) { record_wakee(p); - want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); + want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) + && cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); } rcu_read_lock(); @@ -5331,13 +5648,13 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (affine_sd) { sd = NULL; /* Prefer wake_affine over balance flags */ - if (cpu != prev_cpu && wake_affine(affine_sd, p, sync)) + if (cpu != prev_cpu && wake_affine(affine_sd, p, prev_cpu, sync)) new_cpu = cpu; } if (!sd) { if (sd_flag & SD_BALANCE_WAKE) /* XXX always ? */ - new_cpu = select_idle_sibling(p, new_cpu); + new_cpu = select_idle_sibling(p, prev_cpu, new_cpu); } else while (sd) { struct sched_group *group; @@ -5861,7 +6178,7 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * * The adjacency matrix of the resulting graph is given by: * - * log_2 n + * log_2 n * A_i,j = \Union (i % 2^k == 0) && i / 2^(k+1) == j / 2^(k+1) (6) * k = 0 * @@ -5907,7 +6224,7 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * * [XXX write more on how we solve this.. _after_ merging pjt's patches that * rewrite all of this once again.] - */ + */ static unsigned long __read_mostly max_load_balance_interval = HZ/10; @@ -6055,7 +6372,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { int cpu; - schedstat_inc(p, se.statistics.nr_failed_migrations_affine); + schedstat_inc(p->se.statistics.nr_failed_migrations_affine); env->flags |= LBF_SOME_PINNED; @@ -6086,7 +6403,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) env->flags &= ~LBF_ALL_PINNED; if (task_running(env->src_rq, p)) { - schedstat_inc(p, se.statistics.nr_failed_migrations_running); + schedstat_inc(p->se.statistics.nr_failed_migrations_running); return 0; } @@ -6103,13 +6420,13 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (tsk_cache_hot <= 0 || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { if (tsk_cache_hot == 1) { - schedstat_inc(env->sd, lb_hot_gained[env->idle]); - schedstat_inc(p, se.statistics.nr_forced_migrations); + schedstat_inc(env->sd->lb_hot_gained[env->idle]); + schedstat_inc(p->se.statistics.nr_forced_migrations); } return 1; } - schedstat_inc(p, se.statistics.nr_failed_migrations_hot); + schedstat_inc(p->se.statistics.nr_failed_migrations_hot); return 0; } @@ -6149,7 +6466,7 @@ static struct task_struct *detach_one_task(struct lb_env *env) * so we can safely collect stats here rather than * inside detach_tasks(). */ - schedstat_inc(env->sd, lb_gained[env->idle]); + schedstat_inc(env->sd->lb_gained[env->idle]); return p; } return NULL; @@ -6241,7 +6558,7 @@ next: * so we can safely collect detach_one_task() stats here rather * than inside detach_one_task(). */ - schedstat_add(env->sd, lb_gained[env->idle], detached); + schedstat_add(env->sd->lb_gained[env->idle], detached); return detached; } @@ -6569,7 +6886,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) /* * !SD_OVERLAP domains can assume that child groups * span the current group. - */ + */ group = child->groups; do { @@ -7069,7 +7386,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s load_above_capacity = busiest->sum_nr_running * SCHED_CAPACITY_SCALE; if (load_above_capacity > busiest->group_capacity) { load_above_capacity -= busiest->group_capacity; - load_above_capacity *= NICE_0_LOAD; + load_above_capacity *= scale_load_down(NICE_0_LOAD); load_above_capacity /= busiest->group_capacity; } else load_above_capacity = ~0UL; @@ -7276,9 +7593,6 @@ static struct rq *find_busiest_queue(struct lb_env *env, */ #define MAX_PINNED_INTERVAL 512 -/* Working cpumask for load_balance and load_balance_newidle. */ -DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); - static int need_active_balance(struct lb_env *env) { struct sched_domain *sd = env->sd; @@ -7382,7 +7696,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, cpumask_copy(cpus, cpu_active_mask); - schedstat_inc(sd, lb_count[idle]); + schedstat_inc(sd->lb_count[idle]); redo: if (!should_we_balance(&env)) { @@ -7392,19 +7706,19 @@ redo: group = find_busiest_group(&env); if (!group) { - schedstat_inc(sd, lb_nobusyg[idle]); + schedstat_inc(sd->lb_nobusyg[idle]); goto out_balanced; } busiest = find_busiest_queue(&env, group); if (!busiest) { - schedstat_inc(sd, lb_nobusyq[idle]); + schedstat_inc(sd->lb_nobusyq[idle]); goto out_balanced; } BUG_ON(busiest == env.dst_rq); - schedstat_add(sd, lb_imbalance[idle], env.imbalance); + schedstat_add(sd->lb_imbalance[idle], env.imbalance); env.src_cpu = busiest->cpu; env.src_rq = busiest; @@ -7511,7 +7825,7 @@ more_balance: } if (!ld_moved) { - schedstat_inc(sd, lb_failed[idle]); + schedstat_inc(sd->lb_failed[idle]); /* * Increment the failure counter only on periodic balance. * We do not want newidle balance, which can be very @@ -7594,7 +7908,7 @@ out_all_pinned: * we can't migrate them. Let the imbalance flag set so parent level * can try to migrate them. */ - schedstat_inc(sd, lb_balanced[idle]); + schedstat_inc(sd->lb_balanced[idle]); sd->nr_balance_failed = 0; @@ -7626,11 +7940,12 @@ get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) } static inline void -update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance) +update_next_balance(struct sched_domain *sd, unsigned long *next_balance) { unsigned long interval, next; - interval = get_sd_balance_interval(sd, cpu_busy); + /* used by idle balance, so cpu_busy = 0 */ + interval = get_sd_balance_interval(sd, 0); next = sd->last_balance + interval; if (time_after(*next_balance, next)) @@ -7660,7 +7975,7 @@ static int idle_balance(struct rq *this_rq) rcu_read_lock(); sd = rcu_dereference_check_sched_domain(this_rq->sd); if (sd) - update_next_balance(sd, 0, &next_balance); + update_next_balance(sd, &next_balance); rcu_read_unlock(); goto out; @@ -7678,7 +7993,7 @@ static int idle_balance(struct rq *this_rq) continue; if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { - update_next_balance(sd, 0, &next_balance); + update_next_balance(sd, &next_balance); break; } @@ -7696,7 +8011,7 @@ static int idle_balance(struct rq *this_rq) curr_cost += domain_cost; } - update_next_balance(sd, 0, &next_balance); + update_next_balance(sd, &next_balance); /* * Stop searching for tasks to pull if there are @@ -7786,15 +8101,15 @@ static int active_load_balance_cpu_stop(void *data) .idle = CPU_IDLE, }; - schedstat_inc(sd, alb_count); + schedstat_inc(sd->alb_count); p = detach_one_task(&env); if (p) { - schedstat_inc(sd, alb_pushed); + schedstat_inc(sd->alb_pushed); /* Active balancing done, reset the failure counter. */ sd->nr_balance_failed = 0; } else { - schedstat_inc(sd, alb_failed); + schedstat_inc(sd->alb_failed); } } rcu_read_unlock(); @@ -7886,13 +8201,13 @@ static inline void set_cpu_sd_state_busy(void) int cpu = smp_processor_id(); rcu_read_lock(); - sd = rcu_dereference(per_cpu(sd_busy, cpu)); + sd = rcu_dereference(per_cpu(sd_llc, cpu)); if (!sd || !sd->nohz_idle) goto unlock; sd->nohz_idle = 0; - atomic_inc(&sd->groups->sgc->nr_busy_cpus); + atomic_inc(&sd->shared->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -7903,13 +8218,13 @@ void set_cpu_sd_state_idle(void) int cpu = smp_processor_id(); rcu_read_lock(); - sd = rcu_dereference(per_cpu(sd_busy, cpu)); + sd = rcu_dereference(per_cpu(sd_llc, cpu)); if (!sd || sd->nohz_idle) goto unlock; sd->nohz_idle = 1; - atomic_dec(&sd->groups->sgc->nr_busy_cpus); + atomic_dec(&sd->shared->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -8136,8 +8451,8 @@ end: static inline bool nohz_kick_needed(struct rq *rq) { unsigned long now = jiffies; + struct sched_domain_shared *sds; struct sched_domain *sd; - struct sched_group_capacity *sgc; int nr_busy, cpu = rq->cpu; bool kick = false; @@ -8165,11 +8480,13 @@ static inline bool nohz_kick_needed(struct rq *rq) return true; rcu_read_lock(); - sd = rcu_dereference(per_cpu(sd_busy, cpu)); - if (sd) { - sgc = sd->groups->sgc; - nr_busy = atomic_read(&sgc->nr_busy_cpus); - + sds = rcu_dereference(per_cpu(sd_llc_shared, cpu)); + if (sds) { + /* + * XXX: write a coherent comment on why we do this. + * See also: http://lkml.kernel.org/r/20111202010832.602203411@sbsiddha-desk.sc.intel.com + */ + nr_busy = atomic_read(&sds->nr_busy_cpus); if (nr_busy > 1) { kick = true; goto unlock; @@ -8283,31 +8600,17 @@ static void task_fork_fair(struct task_struct *p) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se, *curr; - int this_cpu = smp_processor_id(); struct rq *rq = this_rq(); - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock(&rq->lock); update_rq_clock(rq); cfs_rq = task_cfs_rq(current); curr = cfs_rq->curr; - - /* - * Not only the cpu but also the task_group of the parent might have - * been changed after parent->se.parent,cfs_rq were copied to - * child->se.parent,cfs_rq. So call __set_task_cpu() to make those - * of child point to valid ones. - */ - rcu_read_lock(); - __set_task_cpu(p, this_cpu); - rcu_read_unlock(); - - update_curr(cfs_rq); - - if (curr) + if (curr) { + update_curr(cfs_rq); se->vruntime = curr->vruntime; + } place_entity(cfs_rq, se, 1); if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) { @@ -8320,8 +8623,7 @@ static void task_fork_fair(struct task_struct *p) } se->vruntime -= cfs_rq->min_vruntime; - - raw_spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock(&rq->lock); } /* @@ -8377,6 +8679,7 @@ static void detach_task_cfs_rq(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 now = cfs_rq_clock_task(cfs_rq); if (!vruntime_normalized(p)) { /* @@ -8388,13 +8691,16 @@ static void detach_task_cfs_rq(struct task_struct *p) } /* Catch up with the cfs_rq and remove our load when we leave */ + update_cfs_rq_load_avg(now, cfs_rq, false); detach_entity_load_avg(cfs_rq, se); + update_tg_load_avg(cfs_rq, false); } static void attach_task_cfs_rq(struct task_struct *p) { struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 now = cfs_rq_clock_task(cfs_rq); #ifdef CONFIG_FAIR_GROUP_SCHED /* @@ -8405,7 +8711,9 @@ static void attach_task_cfs_rq(struct task_struct *p) #endif /* Synchronize task with its cfs_rq */ + update_cfs_rq_load_avg(now, cfs_rq, false); attach_entity_load_avg(cfs_rq, se); + update_tg_load_avg(cfs_rq, false); if (!vruntime_normalized(p)) se->vruntime += cfs_rq->min_vruntime; @@ -8465,6 +8773,14 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) } #ifdef CONFIG_FAIR_GROUP_SCHED +static void task_set_group_fair(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + + set_task_rq(p, task_cpu(p)); + se->depth = se->parent ? se->parent->depth + 1 : 0; +} + static void task_move_group_fair(struct task_struct *p) { detach_task_cfs_rq(p); @@ -8477,6 +8793,19 @@ static void task_move_group_fair(struct task_struct *p) attach_task_cfs_rq(p); } +static void task_change_group_fair(struct task_struct *p, int type) +{ + switch (type) { + case TASK_SET_GROUP: + task_set_group_fair(p); + break; + + case TASK_MOVE_GROUP: + task_move_group_fair(p); + break; + } +} + void free_fair_sched_group(struct task_group *tg) { int i; @@ -8496,8 +8825,9 @@ void free_fair_sched_group(struct task_group *tg) int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) { - struct cfs_rq *cfs_rq; struct sched_entity *se; + struct cfs_rq *cfs_rq; + struct rq *rq; int i; tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); @@ -8512,6 +8842,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_bandwidth(tg_cfs_bandwidth(tg)); for_each_possible_cpu(i) { + rq = cpu_rq(i); + cfs_rq = kzalloc_node(sizeof(struct cfs_rq), GFP_KERNEL, cpu_to_node(i)); if (!cfs_rq) @@ -8525,7 +8857,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) init_cfs_rq(cfs_rq); init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); init_entity_runnable_average(se); - post_init_entity_util_avg(se); } return 1; @@ -8536,6 +8867,23 @@ err: return 0; } +void online_fair_sched_group(struct task_group *tg) +{ + struct sched_entity *se; + struct rq *rq; + int i; + + for_each_possible_cpu(i) { + rq = cpu_rq(i); + se = tg->se[i]; + + raw_spin_lock_irq(&rq->lock); + post_init_entity_util_avg(se); + sync_throttle(tg, i); + raw_spin_unlock_irq(&rq->lock); + } +} + void unregister_fair_sched_group(struct task_group *tg) { unsigned long flags; @@ -8640,6 +8988,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) return 1; } +void online_fair_sched_group(struct task_group *tg) { } + void unregister_fair_sched_group(struct task_group *tg) { } #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -8699,7 +9049,7 @@ const struct sched_class fair_sched_class = { .update_curr = update_curr_fair, #ifdef CONFIG_FAIR_GROUP_SCHED - .task_move_group = task_move_group_fair, + .task_change_group = task_change_group_fair, #endif }; |