diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/autogroup.c | 2 | ||||
| -rw-r--r-- | kernel/sched/core.c | 1215 | ||||
| -rw-r--r-- | kernel/sched/cpudeadline.c | 4 | ||||
| -rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 51 | ||||
| -rw-r--r-- | kernel/sched/cpupri.c | 4 | ||||
| -rw-r--r-- | kernel/sched/deadline.c | 160 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 43 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 1114 | ||||
| -rw-r--r-- | kernel/sched/features.h | 1 | ||||
| -rw-r--r-- | kernel/sched/idle.c | 44 | ||||
| -rw-r--r-- | kernel/sched/isolation.c | 18 | ||||
| -rw-r--r-- | kernel/sched/pelt.c | 13 | ||||
| -rw-r--r-- | kernel/sched/pelt.h | 2 | ||||
| -rw-r--r-- | kernel/sched/psi.c | 14 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 95 | ||||
| -rw-r--r-- | kernel/sched/sched-pelt.h | 2 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 195 | ||||
| -rw-r--r-- | kernel/sched/stats.h | 7 | ||||
| -rw-r--r-- | kernel/sched/stop_task.c | 22 | ||||
| -rw-r--r-- | kernel/sched/topology.c | 71 | ||||
| -rw-r--r-- | kernel/sched/wait.c | 8 |
21 files changed, 2001 insertions, 1084 deletions
diff --git a/kernel/sched/autogroup.c b/kernel/sched/autogroup.c index 2d4ff5353ded..2067080bb235 100644 --- a/kernel/sched/autogroup.c +++ b/kernel/sched/autogroup.c @@ -259,7 +259,6 @@ out: } #endif /* CONFIG_PROC_FS */ -#ifdef CONFIG_SCHED_DEBUG int autogroup_path(struct task_group *tg, char *buf, int buflen) { if (!task_group_is_autogroup(tg)) @@ -267,4 +266,3 @@ int autogroup_path(struct task_group *tg, char *buf, int buflen) return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id); } -#endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 874c427742a9..f9a1346a5fa9 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -23,6 +23,17 @@ #define CREATE_TRACE_POINTS #include <trace/events/sched.h> +/* + * Export tracepoints that act as a bare tracehook (ie: have no trace event + * associated with them) to allow external modules to probe them. + */ +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_cfs_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); + DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) @@ -244,7 +255,7 @@ static void __hrtick_restart(struct rq *rq) { struct hrtimer *timer = &rq->hrtick_timer; - hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD); } /* @@ -303,7 +314,7 @@ void hrtick_start(struct rq *rq, u64 delay) */ delay = max_t(u64, delay, 10000LL); hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_REL_PINNED_HARD); } #endif /* CONFIG_SMP */ @@ -317,7 +328,7 @@ static void hrtick_rq_init(struct rq *rq) rq->hrtick_csd.info = rq; #endif - hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); rq->hrtick_timer.function = hrtick; } #else /* CONFIG_SCHED_HRTICK */ @@ -761,6 +772,520 @@ static void set_load_weight(struct task_struct *p, bool update_load) } } +#ifdef CONFIG_UCLAMP_TASK +/* + * Serializes updates of utilization clamp values + * + * The (slow-path) user-space triggers utilization clamp value updates which + * can require updates on (fast-path) scheduler's data structures used to + * support enqueue/dequeue operations. + * While the per-CPU rq lock protects fast-path update operations, user-space + * requests are serialized using a mutex to reduce the risk of conflicting + * updates or API abuses. + */ +static DEFINE_MUTEX(uclamp_mutex); + +/* Max allowed minimum utilization */ +unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; + +/* Max allowed maximum utilization */ +unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; + +/* All clamps are required to be less or equal than these values */ +static struct uclamp_se uclamp_default[UCLAMP_CNT]; + +/* Integer rounded range for each bucket */ +#define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS) + +#define for_each_clamp_id(clamp_id) \ + for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++) + +static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) +{ + return clamp_value / UCLAMP_BUCKET_DELTA; +} + +static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value) +{ + return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value); +} + +static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id) +{ + if (clamp_id == UCLAMP_MIN) + return 0; + return SCHED_CAPACITY_SCALE; +} + +static inline void uclamp_se_set(struct uclamp_se *uc_se, + unsigned int value, bool user_defined) +{ + uc_se->value = value; + uc_se->bucket_id = uclamp_bucket_id(value); + uc_se->user_defined = user_defined; +} + +static inline unsigned int +uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id, + unsigned int clamp_value) +{ + /* + * Avoid blocked utilization pushing up the frequency when we go + * idle (which drops the max-clamp) by retaining the last known + * max-clamp. + */ + if (clamp_id == UCLAMP_MAX) { + rq->uclamp_flags |= UCLAMP_FLAG_IDLE; + return clamp_value; + } + + return uclamp_none(UCLAMP_MIN); +} + +static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id, + unsigned int clamp_value) +{ + /* Reset max-clamp retention only on idle exit */ + if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE)) + return; + + WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value); +} + +static inline +enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id, + unsigned int clamp_value) +{ + struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket; + int bucket_id = UCLAMP_BUCKETS - 1; + + /* + * Since both min and max clamps are max aggregated, find the + * top most bucket with tasks in. + */ + for ( ; bucket_id >= 0; bucket_id--) { + if (!bucket[bucket_id].tasks) + continue; + return bucket[bucket_id].value; + } + + /* No tasks -- default clamp values */ + return uclamp_idle_value(rq, clamp_id, clamp_value); +} + +static inline struct uclamp_se +uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id) +{ + struct uclamp_se uc_req = p->uclamp_req[clamp_id]; +#ifdef CONFIG_UCLAMP_TASK_GROUP + struct uclamp_se uc_max; + + /* + * Tasks in autogroups or root task group will be + * restricted by system defaults. + */ + if (task_group_is_autogroup(task_group(p))) + return uc_req; + if (task_group(p) == &root_task_group) + return uc_req; + + uc_max = task_group(p)->uclamp[clamp_id]; + if (uc_req.value > uc_max.value || !uc_req.user_defined) + return uc_max; +#endif + + return uc_req; +} + +/* + * The effective clamp bucket index of a task depends on, by increasing + * priority: + * - the task specific clamp value, when explicitly requested from userspace + * - the task group effective clamp value, for tasks not either in the root + * group or in an autogroup + * - the system default clamp value, defined by the sysadmin + */ +static inline struct uclamp_se +uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id) +{ + struct uclamp_se uc_req = uclamp_tg_restrict(p, clamp_id); + struct uclamp_se uc_max = uclamp_default[clamp_id]; + + /* System default restrictions always apply */ + if (unlikely(uc_req.value > uc_max.value)) + return uc_max; + + return uc_req; +} + +enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id) +{ + struct uclamp_se uc_eff; + + /* Task currently refcounted: use back-annotated (effective) value */ + if (p->uclamp[clamp_id].active) + return p->uclamp[clamp_id].value; + + uc_eff = uclamp_eff_get(p, clamp_id); + + return uc_eff.value; +} + +/* + * When a task is enqueued on a rq, the clamp bucket currently defined by the + * task's uclamp::bucket_id is refcounted on that rq. This also immediately + * updates the rq's clamp value if required. + * + * Tasks can have a task-specific value requested from user-space, track + * within each bucket the maximum value for tasks refcounted in it. + * This "local max aggregation" allows to track the exact "requested" value + * for each bucket when all its RUNNABLE tasks require the same clamp. + */ +static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, + enum uclamp_id clamp_id) +{ + struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id]; + struct uclamp_se *uc_se = &p->uclamp[clamp_id]; + struct uclamp_bucket *bucket; + + lockdep_assert_held(&rq->lock); + + /* Update task effective clamp */ + p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id); + + bucket = &uc_rq->bucket[uc_se->bucket_id]; + bucket->tasks++; + uc_se->active = true; + + uclamp_idle_reset(rq, clamp_id, uc_se->value); + + /* + * Local max aggregation: rq buckets always track the max + * "requested" clamp value of its RUNNABLE tasks. + */ + if (bucket->tasks == 1 || uc_se->value > bucket->value) + bucket->value = uc_se->value; + + if (uc_se->value > READ_ONCE(uc_rq->value)) + WRITE_ONCE(uc_rq->value, uc_se->value); +} + +/* + * When a task is dequeued from a rq, the clamp bucket refcounted by the task + * is released. If this is the last task reference counting the rq's max + * active clamp value, then the rq's clamp value is updated. + * + * Both refcounted tasks and rq's cached clamp values are expected to be + * always valid. If it's detected they are not, as defensive programming, + * enforce the expected state and warn. + */ +static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, + enum uclamp_id clamp_id) +{ + struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id]; + struct uclamp_se *uc_se = &p->uclamp[clamp_id]; + struct uclamp_bucket *bucket; + unsigned int bkt_clamp; + unsigned int rq_clamp; + + lockdep_assert_held(&rq->lock); + + bucket = &uc_rq->bucket[uc_se->bucket_id]; + SCHED_WARN_ON(!bucket->tasks); + if (likely(bucket->tasks)) + bucket->tasks--; + uc_se->active = false; + + /* + * Keep "local max aggregation" simple and accept to (possibly) + * overboost some RUNNABLE tasks in the same bucket. + * The rq clamp bucket value is reset to its base value whenever + * there are no more RUNNABLE tasks refcounting it. + */ + if (likely(bucket->tasks)) + return; + + rq_clamp = READ_ONCE(uc_rq->value); + /* + * Defensive programming: this should never happen. If it happens, + * e.g. due to future modification, warn and fixup the expected value. + */ + SCHED_WARN_ON(bucket->value > rq_clamp); + if (bucket->value >= rq_clamp) { + bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value); + WRITE_ONCE(uc_rq->value, bkt_clamp); + } +} + +static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) +{ + enum uclamp_id clamp_id; + + if (unlikely(!p->sched_class->uclamp_enabled)) + return; + + for_each_clamp_id(clamp_id) + uclamp_rq_inc_id(rq, p, clamp_id); + + /* Reset clamp idle holding when there is one RUNNABLE task */ + if (rq->uclamp_flags & UCLAMP_FLAG_IDLE) + rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE; +} + +static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) +{ + enum uclamp_id clamp_id; + + if (unlikely(!p->sched_class->uclamp_enabled)) + return; + + for_each_clamp_id(clamp_id) + uclamp_rq_dec_id(rq, p, clamp_id); +} + +static inline void +uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) +{ + struct rq_flags rf; + struct rq *rq; + + /* + * Lock the task and the rq where the task is (or was) queued. + * + * We might lock the (previous) rq of a !RUNNABLE task, but that's the + * price to pay to safely serialize util_{min,max} updates with + * enqueues, dequeues and migration operations. + * This is the same locking schema used by __set_cpus_allowed_ptr(). + */ + rq = task_rq_lock(p, &rf); + + /* + * Setting the clamp bucket is serialized by task_rq_lock(). + * If the task is not yet RUNNABLE and its task_struct is not + * affecting a valid clamp bucket, the next time it's enqueued, + * it will already see the updated clamp bucket value. + */ + if (!p->uclamp[clamp_id].active) { + uclamp_rq_dec_id(rq, p, clamp_id); + uclamp_rq_inc_id(rq, p, clamp_id); + } + + task_rq_unlock(rq, p, &rf); +} + +static inline void +uclamp_update_active_tasks(struct cgroup_subsys_state *css, + unsigned int clamps) +{ + enum uclamp_id clamp_id; + struct css_task_iter it; + struct task_struct *p; + + css_task_iter_start(css, 0, &it); + while ((p = css_task_iter_next(&it))) { + for_each_clamp_id(clamp_id) { + if ((0x1 << clamp_id) & clamps) + uclamp_update_active(p, clamp_id); + } + } + css_task_iter_end(&it); +} + +#ifdef CONFIG_UCLAMP_TASK_GROUP +static void cpu_util_update_eff(struct cgroup_subsys_state *css); +static void uclamp_update_root_tg(void) +{ + struct task_group *tg = &root_task_group; + + uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN], + sysctl_sched_uclamp_util_min, false); + uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX], + sysctl_sched_uclamp_util_max, false); + + rcu_read_lock(); + cpu_util_update_eff(&root_task_group.css); + rcu_read_unlock(); +} +#else +static void uclamp_update_root_tg(void) { } +#endif + +int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + bool update_root_tg = false; + int old_min, old_max; + int result; + + mutex_lock(&uclamp_mutex); + old_min = sysctl_sched_uclamp_util_min; + old_max = sysctl_sched_uclamp_util_max; + + result = proc_dointvec(table, write, buffer, lenp, ppos); + if (result) + goto undo; + if (!write) + goto done; + + if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max || + sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) { + result = -EINVAL; + goto undo; + } + + if (old_min != sysctl_sched_uclamp_util_min) { + uclamp_se_set(&uclamp_default[UCLAMP_MIN], + sysctl_sched_uclamp_util_min, false); + update_root_tg = true; + } + if (old_max != sysctl_sched_uclamp_util_max) { + uclamp_se_set(&uclamp_default[UCLAMP_MAX], + sysctl_sched_uclamp_util_max, false); + update_root_tg = true; + } + + if (update_root_tg) + uclamp_update_root_tg(); + + /* + * We update all RUNNABLE tasks only when task groups are in use. + * Otherwise, keep it simple and do just a lazy update at each next + * task enqueue time. + */ + + goto done; + +undo: + sysctl_sched_uclamp_util_min = old_min; + sysctl_sched_uclamp_util_max = old_max; +done: + mutex_unlock(&uclamp_mutex); + + return result; +} + +static int uclamp_validate(struct task_struct *p, + const struct sched_attr *attr) +{ + unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value; + unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value; + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) + lower_bound = attr->sched_util_min; + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) + upper_bound = attr->sched_util_max; + + if (lower_bound > upper_bound) + return -EINVAL; + if (upper_bound > SCHED_CAPACITY_SCALE) + return -EINVAL; + + return 0; +} + +static void __setscheduler_uclamp(struct task_struct *p, + const struct sched_attr *attr) +{ + enum uclamp_id clamp_id; + + /* + * On scheduling class change, reset to default clamps for tasks + * without a task-specific value. + */ + for_each_clamp_id(clamp_id) { + struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; + unsigned int clamp_value = uclamp_none(clamp_id); + + /* Keep using defined clamps across class changes */ + if (uc_se->user_defined) + continue; + + /* By default, RT tasks always get 100% boost */ + if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) + clamp_value = uclamp_none(UCLAMP_MAX); + + uclamp_se_set(uc_se, clamp_value, false); + } + + if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) + return; + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { + uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], + attr->sched_util_min, true); + } + + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) { + uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], + attr->sched_util_max, true); + } +} + +static void uclamp_fork(struct task_struct *p) +{ + enum uclamp_id clamp_id; + + for_each_clamp_id(clamp_id) + p->uclamp[clamp_id].active = false; + + if (likely(!p->sched_reset_on_fork)) + return; + + for_each_clamp_id(clamp_id) { + unsigned int clamp_value = uclamp_none(clamp_id); + + /* By default, RT tasks always get 100% boost */ + if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) + clamp_value = uclamp_none(UCLAMP_MAX); + + uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false); + } +} + +static void __init init_uclamp(void) +{ + struct uclamp_se uc_max = {}; + enum uclamp_id clamp_id; + int cpu; + + mutex_init(&uclamp_mutex); + + for_each_possible_cpu(cpu) { + memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq)); + cpu_rq(cpu)->uclamp_flags = 0; + } + + for_each_clamp_id(clamp_id) { + uclamp_se_set(&init_task.uclamp_req[clamp_id], + uclamp_none(clamp_id), false); + } + + /* System defaults allow max clamp values for both indexes */ + uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false); + for_each_clamp_id(clamp_id) { + uclamp_default[clamp_id] = uc_max; +#ifdef CONFIG_UCLAMP_TASK_GROUP + root_task_group.uclamp_req[clamp_id] = uc_max; + root_task_group.uclamp[clamp_id] = uc_max; +#endif + } +} + +#else /* CONFIG_UCLAMP_TASK */ +static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { } +static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { } +static inline int uclamp_validate(struct task_struct *p, + const struct sched_attr *attr) +{ + return -EOPNOTSUPP; +} +static void __setscheduler_uclamp(struct task_struct *p, + const struct sched_attr *attr) { } +static inline void uclamp_fork(struct task_struct *p) { } +static inline void init_uclamp(void) { } +#endif /* CONFIG_UCLAMP_TASK */ + static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { if (!(flags & ENQUEUE_NOCLOCK)) @@ -771,6 +1296,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) psi_enqueue(p, flags & ENQUEUE_WAKEUP); } + uclamp_rq_inc(rq, p); p->sched_class->enqueue_task(rq, p, flags); } @@ -784,6 +1310,7 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) psi_dequeue(p, flags & DEQUEUE_SLEEP); } + uclamp_rq_dec(rq, p); p->sched_class->dequeue_task(rq, p, flags); } @@ -930,7 +1457,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p) */ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) return false; if (is_per_cpu_kthread(p)) @@ -1025,7 +1552,7 @@ static int migration_cpu_stop(void *data) local_irq_disable(); /* * We need to explicitly wake pending tasks before running - * __migrate_task() such that we will not miss enforcing cpus_allowed + * __migrate_task() such that we will not miss enforcing cpus_ptr * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. */ sched_ttwu_pending(); @@ -1056,7 +1583,7 @@ static int migration_cpu_stop(void *data) */ void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) { - cpumask_copy(&p->cpus_allowed, new_mask); + cpumask_copy(&p->cpus_mask, new_mask); p->nr_cpus_allowed = cpumask_weight(new_mask); } @@ -1086,7 +1613,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); if (running) - set_curr_task(rq, p); + set_next_task(rq, p); } /* @@ -1126,7 +1653,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, goto out; } - if (cpumask_equal(&p->cpus_allowed, new_mask)) + if (cpumask_equal(p->cpus_ptr, new_mask)) goto out; if (!cpumask_intersects(new_mask, cpu_valid_mask)) { @@ -1286,10 +1813,10 @@ static int migrate_swap_stop(void *data) if (task_cpu(arg->src_task) != arg->src_cpu) goto unlock; - if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed)) + if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr)) goto unlock; - if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed)) + if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr)) goto unlock; __migrate_swap_task(arg->src_task, arg->dst_cpu); @@ -1331,10 +1858,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p, if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) goto out; - if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed)) + if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr)) goto out; - if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed)) + if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr)) goto out; trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); @@ -1479,7 +2006,7 @@ void kick_process(struct task_struct *p) EXPORT_SYMBOL_GPL(kick_process); /* - * ->cpus_allowed is protected by both rq->lock and p->pi_lock + * ->cpus_ptr is protected by both rq->lock and p->pi_lock * * A few notes on cpu_active vs cpu_online: * @@ -1519,14 +2046,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for_each_cpu(dest_cpu, nodemask) { if (!cpu_active(dest_cpu)) continue; - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) return dest_cpu; } } for (;;) { /* Any allowed, online CPU? */ - for_each_cpu(dest_cpu, &p->cpus_allowed) { + for_each_cpu(dest_cpu, p->cpus_ptr) { if (!is_cpu_allowed(p, dest_cpu)) continue; @@ -1570,7 +2097,7 @@ out: } /* - * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. + * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable. */ static inline int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) @@ -1580,11 +2107,11 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) if (p->nr_cpus_allowed > 1) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); else - cpu = cpumask_any(&p->cpus_allowed); + cpu = cpumask_any(p->cpus_ptr); /* * In order not to call set_task_cpu() on a blocking task we need - * to rely on ttwu() to place the task on a valid ->cpus_allowed + * to rely on ttwu() to place the task on a valid ->cpus_ptr * CPU. * * Since this is common to all placement strategies, this lives here. @@ -1991,6 +2518,30 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) unsigned long flags; int cpu, success = 0; + preempt_disable(); + if (p == current) { + /* + * We're waking current, this means 'p->on_rq' and 'task_cpu(p) + * == smp_processor_id()'. Together this means we can special + * case the whole 'p->on_rq && ttwu_remote()' case below + * without taking any locks. + * + * In particular: + * - we rely on Program-Order guarantees for all the ordering, + * - we're serialized against set_special_state() by virtue of + * it disabling IRQs (this allows not taking ->pi_lock). + */ + if (!(p->state & state)) + goto out; + + success = 1; + cpu = task_cpu(p); + trace_sched_waking(p); + p->state = TASK_RUNNING; + trace_sched_wakeup(p); + goto out; + } + /* * If we are going to wake up a thread waiting for CONDITION we * need to ensure that CONDITION=1 done by the caller can not be @@ -2000,7 +2551,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) raw_spin_lock_irqsave(&p->pi_lock, flags); smp_mb__after_spinlock(); if (!(p->state & state)) - goto out; + goto unlock; trace_sched_waking(p); @@ -2030,7 +2581,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ smp_rmb(); if (p->on_rq && ttwu_remote(p, wake_flags)) - goto stat; + goto unlock; #ifdef CONFIG_SMP /* @@ -2090,10 +2641,12 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) #endif /* CONFIG_SMP */ ttwu_queue(p, cpu, wake_flags); -stat: - ttwu_stat(p, cpu, wake_flags); -out: +unlock: raw_spin_unlock_irqrestore(&p->pi_lock, flags); +out: + if (success) + ttwu_stat(p, cpu, wake_flags); + preempt_enable(); return success; } @@ -2300,6 +2853,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) */ p->prio = current->normal_prio; + uclamp_fork(p); + /* * Revert to default priority/policy on fork if requested. */ @@ -2395,7 +2950,7 @@ void wake_up_new_task(struct task_struct *p) #ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: - * - cpus_allowed can change in the fork path + * - cpus_ptr can change in the fork path * - any previously selected CPU might disappear through hotplug * * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, @@ -2778,12 +3333,8 @@ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next, struct rq_flags *rf) { - struct mm_struct *mm, *oldmm; - prepare_task_switch(rq, prev, next); - mm = next->mm; - oldmm = prev->active_mm; /* * For paravirt, this is coupled with an exit in switch_to to * combine the page table reload and the switch backend into @@ -2792,22 +3343,37 @@ context_switch(struct rq *rq, struct task_struct *prev, arch_start_context_switch(prev); /* - * If mm is non-NULL, we pass through switch_mm(). If mm is - * NULL, we will pass through mmdrop() in finish_task_switch(). - * Both of these contain the full memory barrier required by - * membarrier after storing to rq->curr, before returning to - * user-space. + * kernel -> kernel lazy + transfer active + * user -> kernel lazy + mmgrab() active + * + * kernel -> user switch + mmdrop() active + * user -> user switch */ - if (!mm) { - next->active_mm = oldmm; - mmgrab(oldmm); - enter_lazy_tlb(oldmm, next); - } else - switch_mm_irqs_off(oldmm, mm, next); + if (!next->mm) { // to kernel + enter_lazy_tlb(prev->active_mm, next); - if (!prev->mm) { - prev->active_mm = NULL; - rq->prev_mm = oldmm; + next->active_mm = prev->active_mm; + if (prev->mm) // from user + mmgrab(prev->active_mm); + else + prev->active_mm = NULL; + } else { // to user + /* + * sys_membarrier() requires an smp_mb() between setting + * rq->curr and returning to userspace. + * + * The below provides this either through switch_mm(), or in + * case 'prev->active_mm == next->mm' through + * finish_task_switch()'s mmdrop(). + */ + + switch_mm_irqs_off(prev->active_mm, next->mm, next); + + if (!prev->mm) { // from kernel + /* will mmdrop() in finish_task_switch(). */ + rq->prev_mm = prev->active_mm; + prev->active_mm = NULL; + } } rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); @@ -3033,7 +3599,6 @@ void scheduler_tick(void) update_rq_clock(rq); curr->sched_class->task_tick(rq, curr, 0); - cpu_load_update_active(rq); calc_global_load_tick(rq); psi_task_tick(rq); @@ -3051,8 +3616,36 @@ void scheduler_tick(void) struct tick_work { int cpu; + atomic_t state; struct delayed_work work; }; +/* Values for ->state, see diagram below. */ +#define TICK_SCHED_REMOTE_OFFLINE 0 +#define TICK_SCHED_REMOTE_OFFLINING 1 +#define TICK_SCHED_REMOTE_RUNNING 2 + +/* + * State diagram for ->state: + * + * + * TICK_SCHED_REMOTE_OFFLINE + * | ^ + * | | + * | | sched_tick_remote() + * | | + * | | + * +--TICK_SCHED_REMOTE_OFFLINING + * | ^ + * | | + * sched_tick_start() | | sched_tick_stop() + * | | + * V | + * TICK_SCHED_REMOTE_RUNNING + * + * + * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote() + * and sched_tick_start() are happy to leave the state in RUNNING. + */ static struct tick_work __percpu *tick_work_cpu; @@ -3065,6 +3658,7 @@ static void sched_tick_remote(struct work_struct *work) struct task_struct *curr; struct rq_flags rf; u64 delta; + int os; /* * Handle the tick only if it appears the remote CPU is running in full @@ -3078,7 +3672,7 @@ static void sched_tick_remote(struct work_struct *work) rq_lock_irq(rq, &rf); curr = rq->curr; - if (is_idle_task(curr)) + if (is_idle_task(curr) || cpu_is_offline(cpu)) goto out_unlock; update_rq_clock(rq); @@ -3098,13 +3692,18 @@ out_requeue: /* * Run the remote tick once per second (1Hz). This arbitrary * frequency is large enough to avoid overload but short enough - * to keep scheduler internal stats reasonably up to date. + * to keep scheduler internal stats reasonably up to date. But + * first update state to reflect hotplug activity if required. */ - queue_delayed_work(system_unbound_wq, dwork, HZ); + os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE); + if (os == TICK_SCHED_REMOTE_RUNNING) + queue_delayed_work(system_unbound_wq, dwork, HZ); } static void sched_tick_start(int cpu) { + int os; struct tick_work *twork; if (housekeeping_cpu(cpu, HK_FLAG_TICK)) @@ -3113,15 +3712,20 @@ static void sched_tick_start(int cpu) WARN_ON_ONCE(!tick_work_cpu); twork = per_cpu_ptr(tick_work_cpu, cpu); - twork->cpu = cpu; - INIT_DELAYED_WORK(&twork->work, sched_tick_remote); - queue_delayed_work(system_unbound_wq, &twork->work, HZ); + os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING); + WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING); + if (os == TICK_SCHED_REMOTE_OFFLINE) { + twork->cpu = cpu; + INIT_DELAYED_WORK(&twork->work, sched_tick_remote); + queue_delayed_work(system_unbound_wq, &twork->work, HZ); + } } #ifdef CONFIG_HOTPLUG_CPU static void sched_tick_stop(int cpu) { struct tick_work *twork; + int os; if (housekeeping_cpu(cpu, HK_FLAG_TICK)) return; @@ -3129,7 +3733,10 @@ static void sched_tick_stop(int cpu) WARN_ON_ONCE(!tick_work_cpu); twork = per_cpu_ptr(tick_work_cpu, cpu); - cancel_delayed_work_sync(&twork->work); + /* There cannot be competing actions, but don't rely on stop-machine. */ + os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING); + WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING); + /* Don't cancel, as this would mess up the state machine. */ } #endif /* CONFIG_HOTPLUG_CPU */ @@ -3137,7 +3744,6 @@ int __init sched_tick_offload_init(void) { tick_work_cpu = alloc_percpu(struct tick_work); BUG_ON(!tick_work_cpu); - return 0; } @@ -3146,7 +3752,7 @@ static inline void sched_tick_start(int cpu) { } static inline void sched_tick_stop(int cpu) { } #endif -#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ +#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_TRACE_PREEMPT_TOGGLE)) /* * If the value passed in is equal to the current preempt count @@ -3265,13 +3871,22 @@ static noinline void __schedule_bug(struct task_struct *prev) /* * Various schedule()-time debugging checks and statistics: */ -static inline void schedule_debug(struct task_struct *prev) +static inline void schedule_debug(struct task_struct *prev, bool preempt) { #ifdef CONFIG_SCHED_STACK_END_CHECK if (task_stack_end_corrupted(prev)) panic("corrupted stack end detected inside scheduler\n"); #endif +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP + if (!preempt && prev->state && prev->non_block_count) { + printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n", + prev->comm, prev->pid, prev->non_block_count); + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); + } +#endif + if (unlikely(in_atomic_preempt_off())) { __schedule_bug(prev); preempt_count_set(PREEMPT_DISABLED); @@ -3304,7 +3919,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) p = fair_sched_class.pick_next_task(rq, prev, rf); if (unlikely(p == RETRY_TASK)) - goto again; + goto restart; /* Assumes fair_sched_class->next == idle_sched_class */ if (unlikely(!p)) @@ -3313,14 +3928,19 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) return p; } -again: +restart: + /* + * Ensure that we put DL/RT tasks before the pick loop, such that they + * can PULL higher prio tasks when we lower the RQ 'priority'. + */ + prev->sched_class->put_prev_task(rq, prev, rf); + if (!rq->nr_running) + newidle_balance(rq, rf); + for_each_class(class) { - p = class->pick_next_task(rq, prev, rf); - if (p) { - if (unlikely(p == RETRY_TASK)) - goto again; + p = class->pick_next_task(rq, NULL, NULL); + if (p) return p; - } } /* The idle class should always have a runnable task: */ @@ -3347,7 +3967,7 @@ again: * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets * called on the nearest possible occasion: * - * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * - If the kernel is preemptible (CONFIG_PREEMPTION=y): * * - in syscall or exception context, at the next outmost * preempt_enable(). (this might be as soon as the wake_up()'s @@ -3356,7 +3976,7 @@ again: * - in IRQ context, return from interrupt-handler to * preemptible context * - * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set) * then at the next: * * - cond_resched() call @@ -3378,7 +3998,7 @@ static void __sched notrace __schedule(bool preempt) rq = cpu_rq(cpu); prev = rq->curr; - schedule_debug(prev); + schedule_debug(prev, preempt); if (sched_feat(HRTICK)) hrtick_clear(rq); @@ -3469,7 +4089,7 @@ void __noreturn do_task_dead(void) static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state || tsk_is_pi_blocked(tsk)) + if (!tsk->state) return; /* @@ -3485,6 +4105,9 @@ static inline void sched_submit_work(struct task_struct *tsk) preempt_enable_no_resched(); } + if (tsk_is_pi_blocked(tsk)) + return; + /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. @@ -3598,7 +4221,7 @@ static void __sched notrace preempt_schedule_common(void) } while (need_resched()); } -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * this is the entry point to schedule() from in-kernel preemption * off of preempt_enable. Kernel preemptions off return from interrupt @@ -3670,7 +4293,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) } EXPORT_SYMBOL_GPL(preempt_schedule_notrace); -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ /* * this is the entry point to schedule() from kernel preemption @@ -3838,7 +4461,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) if (queued) enqueue_task(rq, p, queue_flag); if (running) - set_curr_task(rq, p); + set_next_task(rq, p); check_class_changed(rq, p, prev_class, oldprio); out_unlock: @@ -3905,7 +4528,7 @@ void set_user_nice(struct task_struct *p, long nice) resched_curr(rq); } if (running) - set_curr_task(rq, p); + set_next_task(rq, p); out_unlock: task_rq_unlock(rq, p, &rf); } @@ -4071,6 +4694,13 @@ static void __setscheduler_params(struct task_struct *p, static void __setscheduler(struct rq *rq, struct task_struct *p, const struct sched_attr *attr, bool keep_boost) { + /* + * If params can't change scheduling class changes aren't allowed + * either. + */ + if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS) + return; + __setscheduler_params(p, attr); /* @@ -4208,6 +4838,16 @@ recheck: return retval; } + /* Update task specific "requested" clamps */ + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) { + retval = uclamp_validate(p, attr); + if (retval) + return retval; + } + + if (pi) + cpuset_read_lock(); + /* * Make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: @@ -4222,8 +4862,8 @@ recheck: * Changing the policy of the stop threads its a very bad idea: */ if (p == rq->stop) { - task_rq_unlock(rq, p, &rf); - return -EINVAL; + retval = -EINVAL; + goto unlock; } /* @@ -4237,10 +4877,12 @@ recheck: goto change; if (dl_policy(policy) && dl_param_changed(p, attr)) goto change; + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) + goto change; p->sched_reset_on_fork = reset_on_fork; - task_rq_unlock(rq, p, &rf); - return 0; + retval = 0; + goto unlock; } change: @@ -4253,8 +4895,8 @@ change: if (rt_bandwidth_enabled() && rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0 && !task_group_is_autogroup(task_group(p))) { - task_rq_unlock(rq, p, &rf); - return -EPERM; + retval = -EPERM; + goto unlock; } #endif #ifdef CONFIG_SMP @@ -4267,10 +4909,10 @@ change: * the entire root_domain to become SCHED_DEADLINE. We * will also fail if there's no bandwidth available. */ - if (!cpumask_subset(span, &p->cpus_allowed) || + if (!cpumask_subset(span, p->cpus_ptr) || rq->rd->dl_bw.bw == 0) { - task_rq_unlock(rq, p, &rf); - return -EPERM; + retval = -EPERM; + goto unlock; } } #endif @@ -4280,6 +4922,8 @@ change: if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); + if (pi) + cpuset_read_unlock(); goto recheck; } @@ -4289,8 +4933,8 @@ change: * is available. */ if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) { - task_rq_unlock(rq, p, &rf); - return -EBUSY; + retval = -EBUSY; + goto unlock; } p->sched_reset_on_fork = reset_on_fork; @@ -4317,7 +4961,9 @@ change: put_prev_task(rq, p); prev_class = p->sched_class; + __setscheduler(rq, p, attr, pi); + __setscheduler_uclamp(p, attr); if (queued) { /* @@ -4330,7 +4976,7 @@ change: enqueue_task(rq, p, queue_flags); } if (running) - set_curr_task(rq, p); + set_next_task(rq, p); check_class_changed(rq, p, prev_class, oldprio); @@ -4338,14 +4984,22 @@ change: preempt_disable(); task_rq_unlock(rq, p, &rf); - if (pi) + if (pi) { + cpuset_read_unlock(); rt_mutex_adjust_pi(p); + } /* Run balance callbacks after we've adjusted the PI chain: */ balance_callback(rq); preempt_enable(); return 0; + +unlock: + task_rq_unlock(rq, p, &rf); + if (pi) + cpuset_read_unlock(); + return retval; } static int _sched_setscheduler(struct task_struct *p, int policy, @@ -4429,10 +5083,15 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); - if (p != NULL) - retval = sched_setscheduler(p, policy, &lparam); + if (likely(p)) + get_task_struct(p); rcu_read_unlock(); + if (likely(p)) { + retval = sched_setscheduler(p, policy, &lparam); + put_task_struct(p); + } + return retval; } @@ -4493,6 +5152,10 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a if (ret) return -EFAULT; + if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) && + size < SCHED_ATTR_SIZE_VER1) + return -EINVAL; + /* * XXX: Do we want to be lenient like existing syscalls; or do we want * to be strict and return an error on out-of-bounds values? @@ -4556,14 +5219,21 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, if ((int)attr.sched_policy < 0) return -EINVAL; + if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY) + attr.sched_policy = SETPARAM_POLICY; rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); - if (p != NULL) - retval = sched_setattr(p, &attr); + if (likely(p)) + get_task_struct(p); rcu_read_unlock(); + if (likely(p)) { + retval = sched_setattr(p, &attr); + put_task_struct(p); + } + return retval; } @@ -4638,37 +5308,40 @@ out_unlock: return retval; } -static int sched_read_attr(struct sched_attr __user *uattr, - struct sched_attr *attr, - unsigned int usize) +/* + * Copy the kernel size attribute structure (which might be larger + * than what user-space knows about) to user-space. + * + * Note that all cases are valid: user-space buffer can be larger or + * smaller than the kernel-space buffer. The usual case is that both + * have the same size. + */ +static int +sched_attr_copy_to_user(struct sched_attr __user *uattr, + struct sched_attr *kattr, + unsigned int usize) { - int ret; + unsigned int ksize = sizeof(*kattr); if (!access_ok(uattr, usize)) return -EFAULT; /* - * If we're handed a smaller struct than we know of, - * ensure all the unknown bits are 0 - i.e. old - * user-space does not get uncomplete information. + * sched_getattr() ABI forwards and backwards compatibility: + * + * If usize == ksize then we just copy everything to user-space and all is good. + * + * If usize < ksize then we only copy as much as user-space has space for, + * this keeps ABI compatibility as well. We skip the rest. + * + * If usize > ksize then user-space is using a newer version of the ABI, + * which part the kernel doesn't know about. Just ignore it - tooling can + * detect the kernel's knowledge of attributes from the attr->size value + * which is set to ksize in this case. */ - if (usize < sizeof(*attr)) { - unsigned char *addr; - unsigned char *end; - - addr = (void *)attr + usize; - end = (void *)attr + sizeof(*attr); - - for (; addr < end; addr++) { - if (*addr) - return -EFBIG; - } - - attr->size = usize; - } + kattr->size = min(usize, ksize); - ret = copy_to_user(uattr, attr, attr->size); - if (ret) + if (copy_to_user(uattr, kattr, kattr->size)) return -EFAULT; return 0; @@ -4678,20 +5351,18 @@ static int sched_read_attr(struct sched_attr __user *uattr, * sys_sched_getattr - similar to sched_getparam, but with sched_attr * @pid: the pid in question. * @uattr: structure containing the extended parameters. - * @size: sizeof(attr) for fwd/bwd comp. + * @usize: sizeof(attr) that user-space knows about, for forwards and backwards compatibility. * @flags: for future extension. */ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, size, unsigned int, flags) + unsigned int, usize, unsigned int, flags) { - struct sched_attr attr = { - .size = sizeof(struct sched_attr), - }; + struct sched_attr kattr = { }; struct task_struct *p; int retval; - if (!uattr || pid < 0 || size > PAGE_SIZE || - size < SCHED_ATTR_SIZE_VER0 || flags) + if (!uattr || pid < 0 || usize > PAGE_SIZE || + usize < SCHED_ATTR_SIZE_VER0 || flags) return -EINVAL; rcu_read_lock(); @@ -4704,20 +5375,24 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, if (retval) goto out_unlock; - attr.sched_policy = p->policy; + kattr.sched_policy = p->policy; if (p->sched_reset_on_fork) - attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; + kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; if (task_has_dl_policy(p)) - __getparam_dl(p, &attr); + __getparam_dl(p, &kattr); else if (task_has_rt_policy(p)) - attr.sched_priority = p->rt_priority; + kattr.sched_priority = p->rt_priority; else - attr.sched_nice = task_nice(p); + kattr.sched_nice = task_nice(p); + +#ifdef CONFIG_UCLAMP_TASK + kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; + kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; +#endif rcu_read_unlock(); - retval = sched_read_attr(uattr, &attr, size); - return retval; + return sched_attr_copy_to_user(uattr, &kattr, usize); out_unlock: rcu_read_unlock(); @@ -4866,7 +5541,7 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) goto out_unlock; raw_spin_lock_irqsave(&p->pi_lock, flags); - cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); + cpumask_and(mask, &p->cpus_mask, cpu_active_mask); raw_spin_unlock_irqrestore(&p->pi_lock, flags); out_unlock: @@ -4947,7 +5622,7 @@ SYSCALL_DEFINE0(sched_yield) return 0; } -#ifndef CONFIG_PREEMPT +#ifndef CONFIG_PREEMPTION int __sched _cond_resched(void) { if (should_resched(0)) { @@ -4964,7 +5639,7 @@ EXPORT_SYMBOL(_cond_resched); * __cond_resched_lock() - if a reschedule is pending, drop the given lock, * call schedule, and on return reacquire the lock. * - * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level * operations here to prevent schedule() from being called twice (once via * spin_unlock(), once by hand). */ @@ -5123,7 +5798,7 @@ long __sched io_schedule_timeout(long timeout) } EXPORT_SYMBOL(io_schedule_timeout); -void io_schedule(void) +void __sched io_schedule(void) { int token; @@ -5443,7 +6118,7 @@ int task_can_attach(struct task_struct *p, * allowed nodes is unnecessary. Thus, cpusets are not * applicable for such threads. This prevents checking for * success of set_cpus_allowed_ptr() on all attached tasks - * before cpus_allowed may be changed. + * before cpus_mask may be changed. */ if (p->flags & PF_NO_SETAFFINITY) { ret = -EINVAL; @@ -5470,7 +6145,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu) if (curr_cpu == target_cpu) return 0; - if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) return -EINVAL; /* TODO: This is not properly updating schedstats */ @@ -5503,7 +6178,7 @@ void sched_setnuma(struct task_struct *p, int nid) if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); if (running) - set_curr_task(rq, p); + set_next_task(rq, p); task_rq_unlock(rq, p, &rf); } #endif /* CONFIG_NUMA_BALANCING */ @@ -5543,21 +6218,22 @@ static void calc_load_migrate(struct rq *rq) atomic_long_add(delta, &calc_load_tasks); } -static void put_prev_task_fake(struct rq *rq, struct task_struct *prev) +static struct task_struct *__pick_migrate_task(struct rq *rq) { -} + const struct sched_class *class; + struct task_struct *next; -static const struct sched_class fake_sched_class = { - .put_prev_task = put_prev_task_fake, -}; + for_each_class(class) { + next = class->pick_next_task(rq, NULL, NULL); + if (next) { + next->sched_class->put_prev_task(rq, next, NULL); + return next; + } + } -static struct task_struct fake_task = { - /* - * Avoid pull_{rt,dl}_task() - */ - .prio = MAX_PRIO + 1, - .sched_class = &fake_sched_class, -}; + /* The idle class should always have a runnable task */ + BUG(); +} /* * Migrate all tasks from the rq, sleeping tasks will be migrated by @@ -5600,15 +6276,10 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) if (rq->nr_running == 1) break; - /* - * pick_next_task() assumes pinned rq->lock: - */ - next = pick_next_task(rq, &fake_task, rf); - BUG_ON(!next); - put_prev_task(rq, next); + next = __pick_migrate_task(rq); /* - * Rules for changing task_struct::cpus_allowed are holding + * Rules for changing task_struct::cpus_mask are holding * both pi_lock and rq->lock, such that holding either * stabilizes the mask. * @@ -5902,19 +6573,19 @@ DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); void __init sched_init(void) { - int i, j; - unsigned long alloc_size = 0, ptr; + unsigned long ptr = 0; + int i; wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED - alloc_size += 2 * nr_cpu_ids * sizeof(void **); + ptr += 2 * nr_cpu_ids * sizeof(void **); #endif #ifdef CONFIG_RT_GROUP_SCHED - alloc_size += 2 * nr_cpu_ids * sizeof(void **); + ptr += 2 * nr_cpu_ids * sizeof(void **); #endif - if (alloc_size) { - ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); + if (ptr) { + ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT); #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.se = (struct sched_entity **)ptr; @@ -6005,10 +6676,6 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); #endif - - for (j = 0; j < CPU_LOAD_IDX_MAX; j++) - rq->cpu_load[j] = 0; - #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; @@ -6063,6 +6730,8 @@ void __init sched_init(void) psi_init(); + init_uclamp(); + scheduler_running = 1; } @@ -6103,7 +6772,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset) rcu_sleep_check(); if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && - !is_idle_task(current)) || + !is_idle_task(current) && !current->non_block_count) || system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING || oops_in_progress) return; @@ -6119,8 +6788,8 @@ void ___might_sleep(const char *file, int line, int preempt_offset) "BUG: sleeping function called from invalid context at %s:%d\n", file, line); printk(KERN_ERR - "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", - in_atomic(), irqs_disabled(), + "in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), current->non_block_count, current->pid, current->comm); if (task_stack_end_corrupted(current)) @@ -6235,7 +6904,7 @@ struct task_struct *curr_task(int cpu) #ifdef CONFIG_IA64 /** - * set_curr_task - set the current task for a given CPU. + * ia64_set_curr_task - set the current task for a given CPU. * @cpu: the processor in question. * @p: the task pointer to set. * @@ -6260,6 +6929,20 @@ void ia64_set_curr_task(int cpu, struct task_struct *p) /* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); +static inline void alloc_uclamp_sched_group(struct task_group *tg, + struct task_group *parent) +{ +#ifdef CONFIG_UCLAMP_TASK_GROUP + enum uclamp_id clamp_id; + + for_each_clamp_id(clamp_id) { + uclamp_se_set(&tg->uclamp_req[clamp_id], + uclamp_none(clamp_id), false); + tg->uclamp[clamp_id] = parent->uclamp[clamp_id]; + } +#endif +} + static void sched_free_group(struct task_group *tg) { free_fair_sched_group(tg); @@ -6283,6 +6966,8 @@ struct task_group *sched_create_group(struct task_group *parent) if (!alloc_rt_sched_group(tg, parent)) goto err; + alloc_uclamp_sched_group(tg, parent); + return tg; err: @@ -6386,7 +7071,7 @@ void sched_move_task(struct task_struct *tsk) if (queued) enqueue_task(rq, tsk, queue_flags); if (running) - set_curr_task(rq, tsk); + set_next_task(rq, tsk); task_rq_unlock(rq, tsk, &rf); } @@ -6469,10 +7154,6 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; -#else - /* We don't support RT-tasks being in separate groups */ - if (task->sched_class != &fair_sched_class) - return -EINVAL; #endif /* * Serialize against wake_up_new_task() such that if its @@ -6503,6 +7184,178 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) sched_move_task(task); } +#ifdef CONFIG_UCLAMP_TASK_GROUP +static void cpu_util_update_eff(struct cgroup_subsys_state *css) +{ + struct cgroup_subsys_state *top_css = css; + struct uclamp_se *uc_parent = NULL; + struct uclamp_se *uc_se = NULL; + unsigned int eff[UCLAMP_CNT]; + enum uclamp_id clamp_id; + unsigned int clamps; + + css_for_each_descendant_pre(css, top_css) { + uc_parent = css_tg(css)->parent + ? css_tg(css)->parent->uclamp : NULL; + + for_each_clamp_id(clamp_id) { + /* Assume effective clamps matches requested clamps */ + eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value; + /* Cap effective clamps with parent's effective clamps */ + if (uc_parent && + eff[clamp_id] > uc_parent[clamp_id].value) { + eff[clamp_id] = uc_parent[clamp_id].value; + } + } + /* Ensure protection is always capped by limit */ + eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]); + + /* Propagate most restrictive effective clamps */ + clamps = 0x0; + uc_se = css_tg(css)->uclamp; + for_each_clamp_id(clamp_id) { + if (eff[clamp_id] == uc_se[clamp_id].value) + continue; + uc_se[clamp_id].value = eff[clamp_id]; + uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]); + clamps |= (0x1 << clamp_id); + } + if (!clamps) { + css = css_rightmost_descendant(css); + continue; + } + + /* Immediately update descendants RUNNABLE tasks */ + uclamp_update_active_tasks(css, clamps); + } +} + +/* + * Integer 10^N with a given N exponent by casting to integer the literal "1eN" + * C expression. Since there is no way to convert a macro argument (N) into a + * character constant, use two levels of macros. + */ +#define _POW10(exp) ((unsigned int)1e##exp) +#define POW10(exp) _POW10(exp) + +struct uclamp_request { +#define UCLAMP_PERCENT_SHIFT 2 +#define UCLAMP_PERCENT_SCALE (100 * POW10(UCLAMP_PERCENT_SHIFT)) + s64 percent; + u64 util; + int ret; +}; + +static inline struct uclamp_request +capacity_from_percent(char *buf) +{ + struct uclamp_request req = { + .percent = UCLAMP_PERCENT_SCALE, + .util = SCHED_CAPACITY_SCALE, + .ret = 0, + }; + + buf = strim(buf); + if (strcmp(buf, "max")) { + req.ret = cgroup_parse_float(buf, UCLAMP_PERCENT_SHIFT, + &req.percent); + if (req.ret) + return req; + if (req.percent > UCLAMP_PERCENT_SCALE) { + req.ret = -ERANGE; + return req; + } + + req.util = req.percent << SCHED_CAPACITY_SHIFT; + req.util = DIV_ROUND_CLOSEST_ULL(req.util, UCLAMP_PERCENT_SCALE); + } + + return req; +} + +static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off, + enum uclamp_id clamp_id) +{ + struct uclamp_request req; + struct task_group *tg; + + req = capacity_from_percent(buf); + if (req.ret) + return req.ret; + + mutex_lock(&uclamp_mutex); + rcu_read_lock(); + + tg = css_tg(of_css(of)); + if (tg->uclamp_req[clamp_id].value != req.util) + uclamp_se_set(&tg->uclamp_req[clamp_id], req.util, false); + + /* + * Because of not recoverable conversion rounding we keep track of the + * exact requested value + */ + tg->uclamp_pct[clamp_id] = req.percent; + + /* Update effective clamps to track the most restrictive value */ + cpu_util_update_eff(of_css(of)); + + rcu_read_unlock(); + mutex_unlock(&uclamp_mutex); + + return nbytes; +} + +static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MIN); +} + +static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, + loff_t off) +{ + return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MAX); +} + +static inline void cpu_uclamp_print(struct seq_file *sf, + enum uclamp_id clamp_id) +{ + struct task_group *tg; + u64 util_clamp; + u64 percent; + u32 rem; + + rcu_read_lock(); + tg = css_tg(seq_css(sf)); + util_clamp = tg->uclamp_req[clamp_id].value; + rcu_read_unlock(); + + if (util_clamp == SCHED_CAPACITY_SCALE) { + seq_puts(sf, "max\n"); + return; + } + + percent = tg->uclamp_pct[clamp_id]; + percent = div_u64_rem(percent, POW10(UCLAMP_PERCENT_SHIFT), &rem); + seq_printf(sf, "%llu.%0*u\n", percent, UCLAMP_PERCENT_SHIFT, rem); +} + +static int cpu_uclamp_min_show(struct seq_file *sf, void *v) +{ + cpu_uclamp_print(sf, UCLAMP_MIN); + return 0; +} + +static int cpu_uclamp_max_show(struct seq_file *sf, void *v) +{ + cpu_uclamp_print(sf, UCLAMP_MAX); + return 0; +} +#endif /* CONFIG_UCLAMP_TASK_GROUP */ + #ifdef CONFIG_FAIR_GROUP_SCHED static int cpu_shares_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 shareval) @@ -6848,6 +7701,20 @@ static struct cftype cpu_legacy_files[] = { .write_u64 = cpu_rt_period_write_uint, }, #endif +#ifdef CONFIG_UCLAMP_TASK_GROUP + { + .name = "uclamp.min", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_min_show, + .write = cpu_uclamp_min_write, + }, + { + .name = "uclamp.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_max_show, + .write = cpu_uclamp_max_write, + }, +#endif { } /* Terminate */ }; @@ -7015,6 +7882,20 @@ static struct cftype cpu_files[] = { .write = cpu_max_write, }, #endif +#ifdef CONFIG_UCLAMP_TASK_GROUP + { + .name = "uclamp.min", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_min_show, + .write = cpu_uclamp_min_write, + }, + { + .name = "uclamp.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_uclamp_max_show, + .write = cpu_uclamp_max_write, + }, +#endif { } /* terminate */ }; diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index ec4e4a9aab5f..5cc4012572ec 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -120,14 +120,14 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, const struct sched_dl_entity *dl_se = &p->dl; if (later_mask && - cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { + cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) { return 1; } else { int best_cpu = cpudl_maximum(cp); WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); - if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) && + if (cpumask_test_cpu(best_cpu, p->cpus_ptr) && dl_time_before(dl_se->deadline, cp->elements[0].dl)) { if (later_mask) cpumask_set_cpu(best_cpu, later_mask); diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 962cf343f798..86800b4d5453 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -40,6 +40,7 @@ struct sugov_policy { struct task_struct *thread; bool work_in_progress; + bool limits_changed; bool need_freq_update; }; @@ -89,8 +90,11 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) !cpufreq_this_cpu_can_update(sg_policy->policy)) return false; - if (unlikely(sg_policy->need_freq_update)) + if (unlikely(sg_policy->limits_changed)) { + sg_policy->limits_changed = false; + sg_policy->need_freq_update = true; return true; + } delta_ns = time - sg_policy->last_freq_update_time; @@ -113,6 +117,7 @@ static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time, unsigned int next_freq) { struct cpufreq_policy *policy = sg_policy->policy; + int cpu; if (!sugov_update_next_freq(sg_policy, time, next_freq)) return; @@ -122,7 +127,11 @@ static void sugov_fast_switch(struct sugov_policy *sg_policy, u64 time, return; policy->cur = next_freq; - trace_cpu_frequency(next_freq, smp_processor_id()); + + if (trace_cpu_frequency_enabled()) { + for_each_cpu(cpu, policy->cpus) + trace_cpu_frequency(next_freq, cpu); + } } static void sugov_deferred_update(struct sugov_policy *sg_policy, u64 time, @@ -196,14 +205,17 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, * based on the task model parameters and gives the minimal utilization * required to meet deadlines. */ -unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, - unsigned long max, enum schedutil_type type) +unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type, + struct task_struct *p) { unsigned long dl_util, util, irq; struct rq *rq = cpu_rq(cpu); - if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) + if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) && + type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) { return max; + } /* * Early check to see if IRQ/steal time saturates the CPU, can be @@ -219,9 +231,16 @@ unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, * CFS tasks and we use the same metric to track the effective * utilization (PELT windows are synchronized) we can directly add them * to obtain the CPU's actual utilization. + * + * CFS and RT utilization can be boosted or capped, depending on + * utilization clamp constraints requested by currently RUNNABLE + * tasks. + * When there are no CFS RUNNABLE tasks, clamps are released and + * frequency will be gracefully reduced with the utilization decay. */ - util = util_cfs; - util += cpu_util_rt(rq); + util = util_cfs + cpu_util_rt(rq); + if (type == FREQUENCY_UTIL) + util = uclamp_util_with(rq, util, p); dl_util = cpu_util_dl(rq); @@ -249,9 +268,9 @@ unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, * irq metric. Because IRQ/steal time is hidden from the task clock we * need to scale the task numbers: * - * 1 - irq - * U' = irq + ------- * U - * max + * max - irq + * U' = irq + --------- * U + * max */ util = scale_irq_capacity(util, irq, max); util += irq; @@ -276,12 +295,12 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); unsigned long util = cpu_util_cfs(rq); - unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu); + unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->max = max; sg_cpu->bw_dl = cpu_bw_dl(rq); - return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL); + return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL); } /** @@ -427,7 +446,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; } static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy) { if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl) - sg_policy->need_freq_update = true; + sg_policy->limits_changed = true; } static void sugov_update_single(struct update_util_data *hook, u64 time, @@ -447,7 +466,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, if (!sugov_should_update_freq(sg_policy, time)) return; - busy = sugov_cpu_is_busy(sg_cpu); + /* Limits may have changed, don't skip frequency update */ + busy = !sg_policy->need_freq_update && sugov_cpu_is_busy(sg_cpu); util = sugov_get_util(sg_cpu); max = sg_cpu->max; @@ -821,6 +841,7 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->last_freq_update_time = 0; sg_policy->next_freq = 0; sg_policy->work_in_progress = false; + sg_policy->limits_changed = false; sg_policy->need_freq_update = false; sg_policy->cached_raw_freq = 0; @@ -869,7 +890,7 @@ static void sugov_limits(struct cpufreq_policy *policy) mutex_unlock(&sg_policy->work_lock); } - sg_policy->need_freq_update = true; + sg_policy->limits_changed = true; } struct cpufreq_governor schedutil_gov = { diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 9c6480e6d62d..b7abca987d94 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -94,11 +94,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (skip) continue; - if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) + if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids) continue; if (lowest_mask) { - cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); + cpumask_and(lowest_mask, p->cpus_ptr, vec->mask); /* * We have to ensure that we have at least one bit diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 43901fa3f269..2dc48720f189 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -287,7 +287,7 @@ static void task_non_contending(struct task_struct *p) dl_se->dl_non_contending = 1; get_task_struct(p); - hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL); + hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD); } static void task_contending(struct sched_dl_entity *dl_se, int flags) @@ -529,6 +529,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq); static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p) { struct rq *later_rq = NULL; + struct dl_bw *dl_b; later_rq = find_lock_later_rq(p, rq); if (!later_rq) { @@ -538,7 +539,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p * If we cannot preempt any rq, fall back to pick any * online CPU: */ - cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); + cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr); if (cpu >= nr_cpu_ids) { /* * Failed to find any suitable CPU. @@ -557,6 +558,38 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p double_lock_balance(rq, later_rq); } + if (p->dl.dl_non_contending || p->dl.dl_throttled) { + /* + * Inactive timer is armed (or callback is running, but + * waiting for us to release rq locks). In any case, when it + * will fire (or continue), it will see running_bw of this + * task migrated to later_rq (and correctly handle it). + */ + sub_running_bw(&p->dl, &rq->dl); + sub_rq_bw(&p->dl, &rq->dl); + + add_rq_bw(&p->dl, &later_rq->dl); + add_running_bw(&p->dl, &later_rq->dl); + } else { + sub_rq_bw(&p->dl, &rq->dl); + add_rq_bw(&p->dl, &later_rq->dl); + } + + /* + * And we finally need to fixup root_domain(s) bandwidth accounting, + * since p is still hanging out in the old (now moved to default) root + * domain. + */ + dl_b = &rq->rd->dl_bw; + raw_spin_lock(&dl_b->lock); + __dl_sub(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span)); + raw_spin_unlock(&dl_b->lock); + + dl_b = &later_rq->rd->dl_bw; + raw_spin_lock(&dl_b->lock); + __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(later_rq->rd->span)); + raw_spin_unlock(&dl_b->lock); + set_task_cpu(p, later_rq->cpu); double_unlock_balance(later_rq, rq); @@ -726,7 +759,7 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * refill the runtime and set the deadline a period in the future, * because keeping the current (absolute) deadline of the task would * result in breaking guarantees promised to other tasks (refer to - * Documentation/scheduler/sched-deadline.txt for more information). + * Documentation/scheduler/sched-deadline.rst for more information). * * This function returns true if: * @@ -923,7 +956,7 @@ static int start_dl_timer(struct task_struct *p) */ if (!hrtimer_is_queued(timer)) { get_task_struct(p); - hrtimer_start(timer, act, HRTIMER_MODE_ABS); + hrtimer_start(timer, act, HRTIMER_MODE_ABS_HARD); } return 1; @@ -1053,7 +1086,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) { struct hrtimer *timer = &dl_se->dl_timer; - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); timer->function = dl_task_timer; } @@ -1195,7 +1228,7 @@ static void update_curr_dl(struct rq *rq) &curr->dl); } else { unsigned long scale_freq = arch_scale_freq_capacity(cpu); - unsigned long scale_cpu = arch_scale_cpu_capacity(NULL, cpu); + unsigned long scale_cpu = arch_scale_cpu_capacity(cpu); scaled_delta_exec = cap_scale(delta_exec, scale_freq); scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu); @@ -1292,7 +1325,7 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se) { struct hrtimer *timer = &dl_se->inactive_timer; - hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); timer->function = inactive_task_timer; } @@ -1694,12 +1727,20 @@ static void start_hrtick_dl(struct rq *rq, struct task_struct *p) } #endif -static inline void set_next_task(struct rq *rq, struct task_struct *p) +static void set_next_task_dl(struct rq *rq, struct task_struct *p) { p->se.exec_start = rq_clock_task(rq); /* You can't push away the running task */ dequeue_pushable_dl_task(rq, p); + + if (hrtick_enabled(rq)) + start_hrtick_dl(rq, p); + + if (rq->curr->sched_class != &dl_sched_class) + update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); + + deadline_queue_push_tasks(rq); } static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, @@ -1720,64 +1761,42 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *p; struct dl_rq *dl_rq; - dl_rq = &rq->dl; + WARN_ON_ONCE(prev || rf); - if (need_pull_dl_task(rq, prev)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we're - * being very careful to re-start the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_dl_task(rq); - rq_repin_lock(rq, rf); - /* - * pull_dl_task() can drop (and re-acquire) rq->lock; this - * means a stop task can slip in, in which case we need to - * re-start task selection. - */ - if (rq->stop && task_on_rq_queued(rq->stop)) - return RETRY_TASK; - } - - /* - * When prev is DL, we may throttle it in put_prev_task(). - * So, we update time before we check for dl_nr_running. - */ - if (prev->sched_class == &dl_sched_class) - update_curr_dl(rq); + dl_rq = &rq->dl; if (unlikely(!dl_rq->dl_nr_running)) return NULL; - put_prev_task(rq, prev); - dl_se = pick_next_dl_entity(rq, dl_rq); BUG_ON(!dl_se); p = dl_task_of(dl_se); - set_next_task(rq, p); - - if (hrtick_enabled(rq)) - start_hrtick_dl(rq, p); - - deadline_queue_push_tasks(rq); - - if (rq->curr->sched_class != &dl_sched_class) - update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 0); + set_next_task_dl(rq, p); return p; } -static void put_prev_task_dl(struct rq *rq, struct task_struct *p) +static void put_prev_task_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf) { update_curr_dl(rq); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, 1); if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); + + if (rf && !on_dl_rq(&p->dl) && need_pull_dl_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_dl_task(rq); + rq_repin_lock(rq, rf); + } } /* @@ -1811,11 +1830,6 @@ static void task_fork_dl(struct task_struct *p) */ } -static void set_curr_task_dl(struct rq *rq) -{ - set_next_task(rq, rq->curr); -} - #ifdef CONFIG_SMP /* Only try algorithms three times */ @@ -1824,7 +1838,7 @@ static void set_curr_task_dl(struct rq *rq) static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, &p->cpus_allowed)) + cpumask_test_cpu(cpu, p->cpus_ptr)) return 1; return 0; } @@ -1974,7 +1988,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) /* Retry if something changed. */ if (double_lock_balance(rq, later_rq)) { if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || + !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) || task_running(rq, task) || !dl_task(task) || !task_on_rq_queued(task))) { @@ -2088,17 +2102,13 @@ retry: } deactivate_task(rq, next_task, 0); - sub_running_bw(&next_task->dl, &rq->dl); - sub_rq_bw(&next_task->dl, &rq->dl); set_task_cpu(next_task, later_rq->cpu); - add_rq_bw(&next_task->dl, &later_rq->dl); /* * Update the later_rq clock here, because the clock is used * by the cpufreq_update_util() inside __add_running_bw(). */ update_rq_clock(later_rq); - add_running_bw(&next_task->dl, &later_rq->dl); activate_task(later_rq, next_task, ENQUEUE_NOCLOCK); ret = 1; @@ -2186,11 +2196,7 @@ static void pull_dl_task(struct rq *this_rq) resched = true; deactivate_task(src_rq, p, 0); - sub_running_bw(&p->dl, &src_rq->dl); - sub_rq_bw(&p->dl, &src_rq->dl); set_task_cpu(p, this_cpu); - add_rq_bw(&p->dl, &this_rq->dl); - add_running_bw(&p->dl, &this_rq->dl); activate_task(this_rq, p, 0); dmin = p->dl.deadline; @@ -2283,6 +2289,36 @@ void __init init_sched_dl_class(void) GFP_KERNEL, cpu_to_node(i)); } +void dl_add_task_root_domain(struct task_struct *p) +{ + struct rq_flags rf; + struct rq *rq; + struct dl_bw *dl_b; + + rq = task_rq_lock(p, &rf); + if (!dl_task(p)) + goto unlock; + + dl_b = &rq->rd->dl_bw; + raw_spin_lock(&dl_b->lock); + + __dl_add(dl_b, p->dl.dl_bw, cpumask_weight(rq->rd->span)); + + raw_spin_unlock(&dl_b->lock); + +unlock: + task_rq_unlock(rq, p, &rf); +} + +void dl_clear_root_domain(struct root_domain *rd) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&rd->dl_bw.lock, flags); + rd->dl_bw.total_bw = 0; + raw_spin_unlock_irqrestore(&rd->dl_bw.lock, flags); +} + #endif /* CONFIG_SMP */ static void switched_from_dl(struct rq *rq, struct task_struct *p) @@ -2403,6 +2439,7 @@ const struct sched_class dl_sched_class = { .pick_next_task = pick_next_task_dl, .put_prev_task = put_prev_task_dl, + .set_next_task = set_next_task_dl, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_dl, @@ -2413,7 +2450,6 @@ const struct sched_class dl_sched_class = { .task_woken = task_woken_dl, #endif - .set_curr_task = set_curr_task_dl, .task_tick = task_tick_dl, .task_fork = task_fork_dl, diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 14c6a8716ba1..f7e4579e746c 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -233,49 +233,35 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) *tablep = NULL; } -static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX-1; - static void set_table_entry(struct ctl_table *entry, const char *procname, void *data, int maxlen, - umode_t mode, proc_handler *proc_handler, - bool load_idx) + umode_t mode, proc_handler *proc_handler) { entry->procname = procname; entry->data = data; entry->maxlen = maxlen; entry->mode = mode; entry->proc_handler = proc_handler; - - if (load_idx) { - entry->extra1 = &min_load_idx; - entry->extra2 = &max_load_idx; - } } static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { - struct ctl_table *table = sd_alloc_ctl_entry(14); + struct ctl_table *table = sd_alloc_ctl_entry(9); if (table == NULL) return NULL; - set_table_entry(&table[0] , "min_interval", &sd->min_interval, sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[1] , "max_interval", &sd->max_interval, sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[2] , "busy_idx", &sd->busy_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[3] , "idle_idx", &sd->idle_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[4] , "newidle_idx", &sd->newidle_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[5] , "wake_idx", &sd->wake_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[6] , "forkexec_idx", &sd->forkexec_idx, sizeof(int) , 0644, proc_dointvec_minmax, true ); - set_table_entry(&table[7] , "busy_factor", &sd->busy_factor, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[8] , "imbalance_pct", &sd->imbalance_pct, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[9] , "cache_nice_tries", &sd->cache_nice_tries, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[10], "flags", &sd->flags, sizeof(int) , 0644, proc_dointvec_minmax, false); - set_table_entry(&table[11], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax, false); - set_table_entry(&table[12], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring, false); - /* &table[13] is terminator */ + set_table_entry(&table[0], "min_interval", &sd->min_interval, sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[1], "max_interval", &sd->max_interval, sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[2], "busy_factor", &sd->busy_factor, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[3], "imbalance_pct", &sd->imbalance_pct, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[4], "cache_nice_tries", &sd->cache_nice_tries, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[7], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring); + /* &table[8] is terminator */ return table; } @@ -653,8 +639,6 @@ do { \ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x)) P(nr_running); - SEQ_printf(m, " .%-30s: %lu\n", "load", - rq->load.weight); P(nr_switches); P(nr_load_updates); P(nr_uninterruptible); @@ -662,11 +646,6 @@ do { \ SEQ_printf(m, " .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr))); PN(clock); PN(clock_task); - P(cpu_load[0]); - P(cpu_load[1]); - P(cpu_load[2]); - P(cpu_load[3]); - P(cpu_load[4]); #undef P #undef PN diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index f35930f5e528..d4bbf68c3161 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -96,12 +96,12 @@ int __weak arch_asym_cpu_priority(int cpu) } /* - * The margin used when comparing utilization with CPU capacity: - * util * margin < capacity * 1024 + * The margin used when comparing utilization with CPU capacity. * * (default: ~20%) */ -static unsigned int capacity_margin = 1280; +#define fits_capacity(cap, max) ((cap) * 1280 < (max) * 1024) + #endif #ifdef CONFIG_CFS_BANDWIDTH @@ -275,6 +275,19 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return grp->my_q; } +static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) +{ + if (!path) + return; + + if (cfs_rq && task_group_is_autogroup(cfs_rq->tg)) + autogroup_path(cfs_rq->tg, path, len); + else if (cfs_rq && cfs_rq->tg->css.cgroup) + cgroup_path(cfs_rq->tg->css.cgroup, path, len); + else + strlcpy(path, "(null)", len); +} + static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); @@ -449,6 +462,12 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) return NULL; } +static inline void cfs_rq_tg_path(struct cfs_rq *cfs_rq, char *path, int len) +{ + if (path) + strlcpy(path, "(null)", len); +} + static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { return true; @@ -764,7 +783,7 @@ void post_init_entity_util_avg(struct task_struct *p) struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; - long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq))); long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2; if (cap > 0) { @@ -1067,6 +1086,21 @@ struct numa_group { unsigned long faults[0]; }; +/* + * For functions that can be called in multiple contexts that permit reading + * ->numa_group (see struct task_struct for locking rules). + */ +static struct numa_group *deref_task_numa_group(struct task_struct *p) +{ + return rcu_dereference_check(p->numa_group, p == current || + (lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu))); +} + +static struct numa_group *deref_curr_numa_group(struct task_struct *p) +{ + return rcu_dereference_protected(p->numa_group, p == current); +} + static inline unsigned long group_faults_priv(struct numa_group *ng); static inline unsigned long group_faults_shared(struct numa_group *ng); @@ -1110,10 +1144,12 @@ static unsigned int task_scan_start(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long period = smin; + struct numa_group *ng; /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); @@ -1121,6 +1157,7 @@ static unsigned int task_scan_start(struct task_struct *p) period *= shared + 1; period /= private + shared + 1; } + rcu_read_unlock(); return max(smin, period); } @@ -1129,13 +1166,14 @@ static unsigned int task_scan_max(struct task_struct *p) { unsigned long smin = task_scan_min(p); unsigned long smax; + struct numa_group *ng; /* Watch for min being lower than max due to floor calculations */ smax = sysctl_numa_balancing_scan_period_max / task_nr_scan_windows(p); /* Scale the maximum scan period with the amount of shared memory. */ - if (p->numa_group) { - struct numa_group *ng = p->numa_group; + ng = deref_curr_numa_group(p); + if (ng) { unsigned long shared = group_faults_shared(ng); unsigned long private = group_faults_priv(ng); unsigned long period = smax; @@ -1150,47 +1188,6 @@ static unsigned int task_scan_max(struct task_struct *p) return max(smin, smax); } -void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) -{ - int mm_users = 0; - struct mm_struct *mm = p->mm; - - if (mm) { - mm_users = atomic_read(&mm->mm_users); - if (mm_users == 1) { - mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); - mm->numa_scan_seq = 0; - } - } - p->node_stamp = 0; - p->numa_scan_seq = mm ? mm->numa_scan_seq : 0; - p->numa_scan_period = sysctl_numa_balancing_scan_delay; - p->numa_work.next = &p->numa_work; - p->numa_faults = NULL; - p->numa_group = NULL; - p->last_task_numa_placement = 0; - p->last_sum_exec_runtime = 0; - - /* New address space, reset the preferred nid */ - if (!(clone_flags & CLONE_VM)) { - p->numa_preferred_nid = NUMA_NO_NODE; - return; - } - - /* - * New thread, keep existing numa_preferred_nid which should be copied - * already by arch_dup_task_struct but stagger when scans start. - */ - if (mm) { - unsigned int delay; - - delay = min_t(unsigned int, task_scan_max(current), - current->numa_scan_period * mm_users * NSEC_PER_MSEC); - delay += 2 * TICK_NSEC; - p->node_stamp = delay; - } -} - static void account_numa_enqueue(struct rq *rq, struct task_struct *p) { rq->nr_numa_running += (p->numa_preferred_nid != NUMA_NO_NODE); @@ -1214,7 +1211,16 @@ static void account_numa_dequeue(struct rq *rq, struct task_struct *p) pid_t task_numa_group_id(struct task_struct *p) { - return p->numa_group ? p->numa_group->gid : 0; + struct numa_group *ng; + pid_t gid = 0; + + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); + if (ng) + gid = ng->gid; + rcu_read_unlock(); + + return gid; } /* @@ -1239,11 +1245,13 @@ static inline unsigned long task_faults(struct task_struct *p, int nid) static inline unsigned long group_faults(struct task_struct *p, int nid) { - if (!p->numa_group) + struct numa_group *ng = deref_task_numa_group(p); + + if (!ng) return 0; - return p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 0)] + - p->numa_group->faults[task_faults_idx(NUMA_MEM, nid, 1)]; + return ng->faults[task_faults_idx(NUMA_MEM, nid, 0)] + + ng->faults[task_faults_idx(NUMA_MEM, nid, 1)]; } static inline unsigned long group_faults_cpu(struct numa_group *group, int nid) @@ -1381,12 +1389,13 @@ static inline unsigned long task_weight(struct task_struct *p, int nid, static inline unsigned long group_weight(struct task_struct *p, int nid, int dist) { + struct numa_group *ng = deref_task_numa_group(p); unsigned long faults, total_faults; - if (!p->numa_group) + if (!ng) return 0; - total_faults = p->numa_group->total_faults; + total_faults = ng->total_faults; if (!total_faults) return 0; @@ -1400,7 +1409,7 @@ static inline unsigned long group_weight(struct task_struct *p, int nid, bool should_numa_migrate_memory(struct task_struct *p, struct page * page, int src_nid, int dst_cpu) { - struct numa_group *ng = p->numa_group; + struct numa_group *ng = deref_curr_numa_group(p); int dst_nid = cpu_to_node(dst_cpu); int last_cpupid, this_cpupid; @@ -1466,9 +1475,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, group_faults_cpu(ng, src_nid) * group_faults(p, dst_nid) * 4; } -static unsigned long weighted_cpuload(struct rq *rq); -static unsigned long source_load(int cpu, int type); -static unsigned long target_load(int cpu, int type); +static unsigned long cpu_runnable_load(struct rq *rq); /* Cached statistics for all CPUs within a node */ struct numa_stats { @@ -1489,7 +1496,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid) for_each_cpu(cpu, cpumask_of_node(nid)) { struct rq *rq = cpu_rq(cpu); - ns->load += weighted_cpuload(rq); + ns->load += cpu_runnable_load(rq); ns->compute_capacity += capacity_of(cpu); } @@ -1583,13 +1590,14 @@ static bool load_too_imbalanced(long src_load, long dst_load, static void task_numa_compare(struct task_numa_env *env, long taskimp, long groupimp, bool maymove) { + struct numa_group *cur_ng, *p_ng = deref_curr_numa_group(env->p); struct rq *dst_rq = cpu_rq(env->dst_cpu); + long imp = p_ng ? groupimp : taskimp; struct task_struct *cur; long src_load, dst_load; - long load; - long imp = env->p->numa_group ? groupimp : taskimp; - long moveimp = imp; int dist = env->dist; + long moveimp = imp; + long load; if (READ_ONCE(dst_rq->numa_migrate_on)) return; @@ -1621,28 +1629,29 @@ static void task_numa_compare(struct task_numa_env *env, * be incurred if the tasks were swapped. */ /* Skip this swap candidate if cannot move to the source cpu */ - if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) + if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr)) goto unlock; /* * If dst and source tasks are in the same NUMA group, or not * in any group then look only at task weights. */ - if (cur->numa_group == env->p->numa_group) { + cur_ng = rcu_dereference(cur->numa_group); + if (cur_ng == p_ng) { imp = taskimp + task_weight(cur, env->src_nid, dist) - task_weight(cur, env->dst_nid, dist); /* * Add some hysteresis to prevent swapping the * tasks within a group over tiny differences. */ - if (cur->numa_group) + if (cur_ng) imp -= imp / 16; } else { /* * Compare the group weights. If a task is all by itself * (not part of a group), use the task weight instead. */ - if (cur->numa_group && env->p->numa_group) + if (cur_ng && p_ng) imp += group_weight(cur, env->src_nid, dist) - group_weight(cur, env->dst_nid, dist); else @@ -1718,7 +1727,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ - if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, env->p->cpus_ptr)) continue; env->dst_cpu = cpu; @@ -1740,11 +1749,12 @@ static int task_numa_migrate(struct task_struct *p) .best_imp = 0, .best_cpu = -1, }; + unsigned long taskweight, groupweight; struct sched_domain *sd; + long taskimp, groupimp; + struct numa_group *ng; struct rq *best_rq; - unsigned long taskweight, groupweight; int nid, ret, dist; - long taskimp, groupimp; /* * Pick the lowest SD_NUMA domain, as that would have the smallest @@ -1790,7 +1800,8 @@ static int task_numa_migrate(struct task_struct *p) * multiple NUMA nodes; in order to better consolidate the group, * we need to check other locations. */ - if (env.best_cpu == -1 || (p->numa_group && p->numa_group->active_nodes > 1)) { + ng = deref_curr_numa_group(p); + if (env.best_cpu == -1 || (ng && ng->active_nodes > 1)) { for_each_online_node(nid) { if (nid == env.src_nid || nid == p->numa_preferred_nid) continue; @@ -1823,7 +1834,7 @@ static int task_numa_migrate(struct task_struct *p) * A task that migrated to a second choice node will be better off * trying for a better one later. Do not set the preferred node here. */ - if (p->numa_group) { + if (ng) { if (env.best_cpu == -1) nid = env.src_nid; else @@ -2118,6 +2129,7 @@ static void task_numa_placement(struct task_struct *p) unsigned long total_faults; u64 runtime, period; spinlock_t *group_lock = NULL; + struct numa_group *ng; /* * The p->mm->numa_scan_seq field gets updated without @@ -2135,8 +2147,9 @@ static void task_numa_placement(struct task_struct *p) runtime = numa_get_avg_runtime(p, &period); /* If the task is part of a group prevent parallel updates to group stats */ - if (p->numa_group) { - group_lock = &p->numa_group->lock; + ng = deref_curr_numa_group(p); + if (ng) { + group_lock = &ng->lock; spin_lock_irq(group_lock); } @@ -2177,7 +2190,7 @@ static void task_numa_placement(struct task_struct *p) p->numa_faults[cpu_idx] += f_diff; faults += p->numa_faults[mem_idx]; p->total_numa_faults += diff; - if (p->numa_group) { + if (ng) { /* * safe because we can only change our own group * @@ -2185,14 +2198,14 @@ static void task_numa_placement(struct task_struct *p) * nid and priv in a specific region because it * is at the beginning of the numa_faults array. */ - p->numa_group->faults[mem_idx] += diff; - p->numa_group->faults_cpu[mem_idx] += f_diff; - p->numa_group->total_faults += diff; - group_faults += p->numa_group->faults[mem_idx]; + ng->faults[mem_idx] += diff; + ng->faults_cpu[mem_idx] += f_diff; + ng->total_faults += diff; + group_faults += ng->faults[mem_idx]; } } - if (!p->numa_group) { + if (!ng) { if (faults > max_faults) { max_faults = faults; max_nid = nid; @@ -2203,8 +2216,8 @@ static void task_numa_placement(struct task_struct *p) } } - if (p->numa_group) { - numa_group_count_active_nodes(p->numa_group); + if (ng) { + numa_group_count_active_nodes(ng); spin_unlock_irq(group_lock); max_nid = preferred_group_nid(p, max_nid); } @@ -2238,7 +2251,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, int cpu = cpupid_to_cpu(cpupid); int i; - if (unlikely(!p->numa_group)) { + if (unlikely(!deref_curr_numa_group(p))) { unsigned int size = sizeof(struct numa_group) + 4*nr_node_ids*sizeof(unsigned long); @@ -2274,7 +2287,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!grp) goto no_join; - my_grp = p->numa_group; + my_grp = deref_curr_numa_group(p); if (grp == my_grp) goto no_join; @@ -2336,13 +2349,24 @@ no_join: return; } -void task_numa_free(struct task_struct *p) +/* + * Get rid of NUMA staticstics associated with a task (either current or dead). + * If @final is set, the task is dead and has reached refcount zero, so we can + * safely free all relevant data structures. Otherwise, there might be + * concurrent reads from places like load balancing and procfs, and we should + * reset the data back to default state without freeing ->numa_faults. + */ +void task_numa_free(struct task_struct *p, bool final) { - struct numa_group *grp = p->numa_group; - void *numa_faults = p->numa_faults; + /* safe: p either is current or is being freed by current */ + struct numa_group *grp = rcu_dereference_raw(p->numa_group); + unsigned long *numa_faults = p->numa_faults; unsigned long flags; int i; + if (!numa_faults) + return; + if (grp) { spin_lock_irqsave(&grp->lock, flags); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) @@ -2355,8 +2379,14 @@ void task_numa_free(struct task_struct *p) put_numa_group(grp); } - p->numa_faults = NULL; - kfree(numa_faults); + if (final) { + p->numa_faults = NULL; + kfree(numa_faults); + } else { + p->total_numa_faults = 0; + for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) + numa_faults[i] = 0; + } } /* @@ -2409,7 +2439,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) * actively using should be counted as local. This allows the * scan rate to slow down when a workload has settled down. */ - ng = p->numa_group; + ng = deref_curr_numa_group(p); if (!priv && !local && ng && ng->active_nodes > 1 && numa_is_active_node(cpu_node, ng) && numa_is_active_node(mem_node, ng)) @@ -2452,7 +2482,7 @@ static void reset_ptenuma_scan(struct task_struct *p) * The expensive part of numa migration is done from task_work context. * Triggered from task_tick_numa(). */ -void task_numa_work(struct callback_head *work) +static void task_numa_work(struct callback_head *work) { unsigned long migrate, next_scan, now = jiffies; struct task_struct *p = current; @@ -2465,7 +2495,7 @@ void task_numa_work(struct callback_head *work) SCHED_WARN_ON(p != container_of(work, struct task_struct, numa_work)); - work->next = work; /* protect against double add */ + work->next = work; /* * Who cares about NUMA placement when they're dying. * @@ -2594,6 +2624,50 @@ out: } } +void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) +{ + int mm_users = 0; + struct mm_struct *mm = p->mm; + + if (mm) { + mm_users = atomic_read(&mm->mm_users); + if (mm_users == 1) { + mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay); + mm->numa_scan_seq = 0; + } + } + p->node_stamp = 0; + p->numa_scan_seq = mm ? mm->numa_scan_seq : 0; + p->numa_scan_period = sysctl_numa_balancing_scan_delay; + /* Protect against double add, see task_tick_numa and task_numa_work */ + p->numa_work.next = &p->numa_work; + p->numa_faults = NULL; + RCU_INIT_POINTER(p->numa_group, NULL); + p->last_task_numa_placement = 0; + p->last_sum_exec_runtime = 0; + + init_task_work(&p->numa_work, task_numa_work); + + /* New address space, reset the preferred nid */ + if (!(clone_flags & CLONE_VM)) { + p->numa_preferred_nid = NUMA_NO_NODE; + return; + } + + /* + * New thread, keep existing numa_preferred_nid which should be copied + * already by arch_dup_task_struct but stagger when scans start. + */ + if (mm) { + unsigned int delay; + + delay = min_t(unsigned int, task_scan_max(current), + current->numa_scan_period * mm_users * NSEC_PER_MSEC); + delay += 2 * TICK_NSEC; + p->node_stamp = delay; + } +} + /* * Drive the periodic memory faults.. */ @@ -2622,10 +2696,8 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr) curr->numa_scan_period = task_scan_start(curr); curr->node_stamp += period; - if (!time_before(jiffies, curr->mm->numa_next_scan)) { - init_task_work(work, task_numa_work); /* TODO: move this into sched_fork() */ + if (!time_before(jiffies, curr->mm->numa_next_scan)) task_work_add(curr, work, true); - } } } @@ -2686,8 +2758,6 @@ static void account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_add(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - update_load_add(&rq_of(cfs_rq)->load, se->load.weight); #ifdef CONFIG_SMP if (entity_is_task(se)) { struct rq *rq = rq_of(cfs_rq); @@ -2703,8 +2773,6 @@ static void account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se) { update_load_sub(&cfs_rq->load, se->load.weight); - if (!parent_entity(se)) - update_load_sub(&rq_of(cfs_rq)->load, se->load.weight); #ifdef CONFIG_SMP if (entity_is_task(se)) { account_numa_dequeue(rq_of(cfs_rq), task_of(se)); @@ -3334,6 +3402,9 @@ static inline int propagate_entity_load_avg(struct sched_entity *se) update_tg_cfs_util(cfs_rq, se, gcfs_rq); update_tg_cfs_runnable(cfs_rq, se, gcfs_rq); + trace_pelt_cfs_tp(cfs_rq); + trace_pelt_se_tp(se); + return 1; } @@ -3486,6 +3557,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s add_tg_cfs_propagate(cfs_rq, se->avg.load_sum); cfs_rq_util_change(cfs_rq, flags); + + trace_pelt_cfs_tp(cfs_rq); } /** @@ -3505,6 +3578,8 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s add_tg_cfs_propagate(cfs_rq, -se->avg.load_sum); cfs_rq_util_change(cfs_rq, 0); + + trace_pelt_cfs_tp(cfs_rq); } /* @@ -3615,8 +3690,6 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) return cfs_rq->avg.load_avg; } -static int idle_balance(struct rq *this_rq, struct rq_flags *rf); - static inline unsigned long task_util(struct task_struct *p) { return READ_ONCE(p->se.avg.util_avg); @@ -3733,7 +3806,7 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) static inline int task_fits_capacity(struct task_struct *p, long capacity) { - return capacity * 1024 > task_util_est(p) * capacity_margin; + return fits_capacity(task_util_est(p), capacity); } static inline void update_misfit_status(struct task_struct *p, struct rq *rq) @@ -4100,7 +4173,8 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) * 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) { + if (schedstat_enabled() && + rq_of(cfs_rq)->cfs.load.weight >= 2*se->load.weight) { schedstat_set(se->statistics.slice_max, max((u64)schedstat_val(se->statistics.slice_max), se->sum_exec_runtime - se->prev_sum_exec_runtime)); @@ -4295,8 +4369,6 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) now = sched_clock_cpu(smp_processor_id()); cfs_b->runtime = cfs_b->quota; - cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); - cfs_b->expires_seq++; } static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg) @@ -4318,8 +4390,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) { struct task_group *tg = cfs_rq->tg; struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); - u64 amount = 0, min_amount, expires; - int expires_seq; + u64 amount = 0, min_amount; /* note: this is a positive sum as runtime_remaining <= 0 */ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; @@ -4336,65 +4407,23 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) cfs_b->idle = 0; } } - expires_seq = cfs_b->expires_seq; - expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += amount; - /* - * we may have advanced our local expiration to account for allowed - * spread between our sched_clock and the one on which runtime was - * issued. - */ - if (cfs_rq->expires_seq != expires_seq) { - cfs_rq->expires_seq = expires_seq; - cfs_rq->runtime_expires = expires; - } return cfs_rq->runtime_remaining > 0; } -/* - * Note: This depends on the synchronization provided by sched_clock and the - * fact that rq->clock snapshots this value. - */ -static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) -{ - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - - /* if the deadline is ahead of our clock, nothing to do */ - if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0)) - return; - - if (cfs_rq->runtime_remaining < 0) - return; - - /* - * If the local deadline has passed we have to consider the - * possibility that our sched_clock is 'fast' and the global deadline - * has not truly expired. - * - * Fortunately we can check determine whether this the case by checking - * whether the global deadline(cfs_b->expires_seq) has advanced. - */ - if (cfs_rq->expires_seq == cfs_b->expires_seq) { - /* extend local deadline, drift is bounded above by 2 ticks */ - cfs_rq->runtime_expires += TICK_NSEC; - } else { - /* global deadline is ahead, expiration has passed */ - cfs_rq->runtime_remaining = 0; - } -} - static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) { /* dock delta_exec before expiring quota (as it could span periods) */ cfs_rq->runtime_remaining -= delta_exec; - expire_cfs_rq_runtime(cfs_rq); if (likely(cfs_rq->runtime_remaining > 0)) return; + if (cfs_rq->throttled) + return; /* * if we're unable to extend our runtime we resched so that the active * hierarchy can be throttled @@ -4479,7 +4508,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) struct rq *rq = rq_of(cfs_rq); struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; - long task_delta, dequeue = 1; + long task_delta, idle_task_delta, dequeue = 1; bool empty; se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -4490,6 +4519,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) rcu_read_unlock(); task_delta = cfs_rq->h_nr_running; + idle_task_delta = cfs_rq->idle_h_nr_running; for_each_sched_entity(se) { struct cfs_rq *qcfs_rq = cfs_rq_of(se); /* throttled entity or throttle-on-deactivate */ @@ -4499,6 +4529,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) if (dequeue) dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP); qcfs_rq->h_nr_running -= task_delta; + qcfs_rq->idle_h_nr_running -= idle_task_delta; if (qcfs_rq->load.weight) dequeue = 0; @@ -4538,7 +4569,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); struct sched_entity *se; int enqueue = 1; - long task_delta; + long task_delta, idle_task_delta; se = cfs_rq->tg->se[cpu_of(rq)]; @@ -4558,6 +4589,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) return; task_delta = cfs_rq->h_nr_running; + idle_task_delta = cfs_rq->idle_h_nr_running; for_each_sched_entity(se) { if (se->on_rq) enqueue = 0; @@ -4566,6 +4598,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) if (enqueue) enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP); cfs_rq->h_nr_running += task_delta; + cfs_rq->idle_h_nr_running += idle_task_delta; if (cfs_rq_throttled(cfs_rq)) break; @@ -4581,8 +4614,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) resched_curr(rq); } -static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, - u64 remaining, u64 expires) +static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) { struct cfs_rq *cfs_rq; u64 runtime; @@ -4598,13 +4630,15 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, if (!cfs_rq_throttled(cfs_rq)) goto next; + /* By the above check, this should never be true */ + SCHED_WARN_ON(cfs_rq->runtime_remaining > 0); + runtime = -cfs_rq->runtime_remaining + 1; if (runtime > remaining) runtime = remaining; remaining -= runtime; cfs_rq->runtime_remaining += runtime; - cfs_rq->runtime_expires = expires; /* we check whether we're throttled above */ if (cfs_rq->runtime_remaining > 0) @@ -4629,7 +4663,7 @@ next: */ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) { - u64 runtime, runtime_expires; + u64 runtime; int throttled; /* no need to continue the timer with no bandwidth constraint */ @@ -4657,8 +4691,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u /* account preceding periods in which throttling occurred */ cfs_b->nr_throttled += overrun; - runtime_expires = cfs_b->runtime_expires; - /* * This check is repeated as we are holding onto the new bandwidth while * we unthrottle. This can potentially race with an unthrottled group @@ -4671,8 +4703,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u cfs_b->distribute_running = 1; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ - runtime = distribute_cfs_runtime(cfs_b, runtime, - runtime_expires); + runtime = distribute_cfs_runtime(cfs_b, runtime); raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->distribute_running = 0; @@ -4734,6 +4765,11 @@ static void start_cfs_slack_bandwidth(struct cfs_bandwidth *cfs_b) if (runtime_refresh_within(cfs_b, min_left)) return; + /* don't push forwards an existing deferred unthrottle */ + if (cfs_b->slack_started) + return; + cfs_b->slack_started = true; + hrtimer_start(&cfs_b->slack_timer, ns_to_ktime(cfs_bandwidth_slack_period), HRTIMER_MODE_REL); @@ -4749,8 +4785,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq) return; raw_spin_lock(&cfs_b->lock); - if (cfs_b->quota != RUNTIME_INF && - cfs_rq->runtime_expires == cfs_b->runtime_expires) { + if (cfs_b->quota != RUNTIME_INF) { cfs_b->runtime += slack_runtime; /* we are under rq->lock, defer unthrottling using a timer */ @@ -4783,10 +4818,10 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) { u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); unsigned long flags; - u64 expires; /* confirm we're still not at a refresh boundary */ raw_spin_lock_irqsave(&cfs_b->lock, flags); + cfs_b->slack_started = false; if (cfs_b->distribute_running) { raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return; @@ -4800,7 +4835,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice) runtime = cfs_b->runtime; - expires = cfs_b->runtime_expires; if (runtime) cfs_b->distribute_running = 1; @@ -4809,11 +4843,10 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (!runtime) return; - runtime = distribute_cfs_runtime(cfs_b, runtime, expires); + runtime = distribute_cfs_runtime(cfs_b, runtime); raw_spin_lock_irqsave(&cfs_b->lock, flags); - if (expires == cfs_b->runtime_expires) - lsub_positive(&cfs_b->runtime, runtime); + lsub_positive(&cfs_b->runtime, runtime); cfs_b->distribute_running = 0; raw_spin_unlock_irqrestore(&cfs_b->lock, flags); } @@ -4950,6 +4983,7 @@ void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); cfs_b->slack_timer.function = sched_cfs_slack_timer; cfs_b->distribute_running = 0; + cfs_b->slack_started = false; } static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq) @@ -4969,8 +5003,6 @@ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b) cfs_b->period_active = 1; overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period); - cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period); - cfs_b->expires_seq++; hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED); } @@ -5148,13 +5180,15 @@ static inline unsigned long cpu_util(int cpu); static inline bool cpu_overutilized(int cpu) { - return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin); + return !fits_capacity(cpu_util(cpu), capacity_of(cpu)); } static inline void update_overutilized_status(struct rq *rq) { - if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) + if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) { WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED); + trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED); + } } #else static inline void update_overutilized_status(struct rq *rq) { } @@ -5170,6 +5204,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; + int idle_h_nr_running = task_has_idle_policy(p); /* * The code below (indirectly) updates schedutil which looks at @@ -5202,6 +5237,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; flags = ENQUEUE_WAKEUP; } @@ -5209,6 +5245,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running++; + cfs_rq->idle_h_nr_running += idle_h_nr_running; if (cfs_rq_throttled(cfs_rq)) break; @@ -5270,6 +5307,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; int task_sleep = flags & DEQUEUE_SLEEP; + int idle_h_nr_running = task_has_idle_policy(p); for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); @@ -5284,6 +5322,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; cfs_rq->h_nr_running--; + cfs_rq->idle_h_nr_running -= idle_h_nr_running; /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) { @@ -5303,6 +5342,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); cfs_rq->h_nr_running--; + cfs_rq->idle_h_nr_running -= idle_h_nr_running; if (cfs_rq_throttled(cfs_rq)) break; @@ -5325,71 +5365,6 @@ 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. - */ - -/* - * The exact cpuload calculated at every tick would be: - * - * load' = (1 - 1/2^i) * load + (1/2^i) * cur_load - * - * If a CPU misses updates for n ticks (as it was idle) and update gets - * called on the n+1-th tick when CPU may be busy, then we have: - * - * load_n = (1 - 1/2^i)^n * load_0 - * load_n+1 = (1 - 1/2^i) * load_n + (1/2^i) * cur_load - * - * decay_load_missed() below does efficient calculation of - * - * load' = (1 - 1/2^i)^n * load - * - * Because x^(n+m) := x^n * x^m we can decompose any x^n in power-of-2 factors. - * This allows us to precompute the above in said factors, thereby allowing the - * reduction of an arbitrary n in O(log_2 n) steps. (See also - * fixed_power_int()) - * - * The calculation is approximated on a 128 point scale. - */ -#define DEGRADE_SHIFT 7 - -static const u8 degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; -static const u8 degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { - { 0, 0, 0, 0, 0, 0, 0, 0 }, - { 64, 32, 8, 0, 0, 0, 0, 0 }, - { 96, 72, 40, 12, 1, 0, 0, 0 }, - { 112, 98, 75, 43, 15, 1, 0, 0 }, - { 120, 112, 98, 76, 45, 16, 2, 0 } -}; - -/* - * Update cpu_load for any missed ticks, due to tickless idle. The backlog - * would be when CPU is idle and so we just decay the old load without - * adding any new load. - */ -static unsigned long -decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) -{ - int j = 0; - - if (!missed_updates) - return load; - - if (missed_updates >= degrade_zero_ticks[idx]) - return 0; - - if (idx == 1) - return load >> missed_updates; - - while (missed_updates) { - if (missed_updates % 2) - load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; - - missed_updates >>= 1; - j++; - } - return load; -} static struct { cpumask_var_t idle_cpus_mask; @@ -5401,232 +5376,18 @@ static struct { #endif /* CONFIG_NO_HZ_COMMON */ -/** - * __cpu_load_update - update the rq->cpu_load[] statistics - * @this_rq: The rq to update statistics for - * @this_load: The current load - * @pending_updates: The number of missed updates - * - * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). - * - * This function computes a decaying average: - * - * load[i]' = (1 - 1/2^i) * load[i] + (1/2^i) * load - * - * Because of NOHZ it might not get called on every tick which gives need for - * the @pending_updates argument. - * - * load[i]_n = (1 - 1/2^i) * load[i]_n-1 + (1/2^i) * load_n-1 - * = A * load[i]_n-1 + B ; A := (1 - 1/2^i), B := (1/2^i) * load - * = A * (A * load[i]_n-2 + B) + B - * = A * (A * (A * load[i]_n-3 + B) + B) + B - * = A^3 * load[i]_n-3 + (A^2 + A + 1) * B - * = A^n * load[i]_0 + (A^(n-1) + A^(n-2) + ... + 1) * B - * = A^n * load[i]_0 + ((1 - A^n) / (1 - A)) * B - * = (1 - 1/2^i)^n * (load[i]_0 - load) + load - * - * In the above we've assumed load_n := load, which is true for NOHZ_FULL as - * any change in load would have resulted in the tick being turned back on. - * - * For regular NOHZ, this reduces to: - * - * load[i]_n = (1 - 1/2^i)^n * load[i]_0 - * - * see decay_load_misses(). For NOHZ_FULL we get to subtract and add the extra - * term. - */ -static void cpu_load_update(struct rq *this_rq, unsigned long this_load, - unsigned long pending_updates) -{ - unsigned long __maybe_unused tickless_load = this_rq->cpu_load[0]; - int i, scale; - - this_rq->nr_load_updates++; - - /* Update our load: */ - this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ - for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { - unsigned long old_load, new_load; - - /* scale is effectively 1 << i now, and >> i divides by scale */ - - old_load = this_rq->cpu_load[i]; -#ifdef CONFIG_NO_HZ_COMMON - old_load = decay_load_missed(old_load, pending_updates - 1, i); - if (tickless_load) { - old_load -= decay_load_missed(tickless_load, pending_updates - 1, i); - /* - * old_load can never be a negative value because a - * decayed tickless_load cannot be greater than the - * original tickless_load. - */ - old_load += tickless_load; - } -#endif - new_load = this_load; - /* - * Round up the averaging division if load is increasing. This - * prevents us from getting stuck on 9 if the load is 10, for - * example. - */ - if (new_load > old_load) - new_load += scale - 1; - - this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; - } -} - -/* Used instead of source_load when we know the type == 0 */ -static unsigned long weighted_cpuload(struct rq *rq) -{ - return cfs_rq_runnable_load_avg(&rq->cfs); -} - -#ifdef CONFIG_NO_HZ_COMMON -/* - * There is no sane way to deal with nohz on smp when using jiffies because the - * CPU doing the jiffies update might drift wrt the CPU doing the jiffy reading - * causing off-by-one errors in observed deltas; {0,2} instead of {1,1}. - * - * Therefore we need to avoid the delta approach from the regular tick when - * possible since that would seriously skew the load calculation. This is why we - * use cpu_load_update_periodic() for CPUs out of nohz. However we'll rely on - * jiffies deltas for updates happening while in nohz mode (idle ticks, idle - * loop exit, nohz_idle_balance, nohz full exit...) - * - * This means we might still be one tick off for nohz periods. - */ - -static void cpu_load_update_nohz(struct rq *this_rq, - unsigned long curr_jiffies, - unsigned long load) -{ - unsigned long pending_updates; - - pending_updates = curr_jiffies - this_rq->last_load_update_tick; - if (pending_updates) { - this_rq->last_load_update_tick = curr_jiffies; - /* - * In the regular NOHZ case, we were idle, this means load 0. - * In the NOHZ_FULL case, we were non-idle, we should consider - * its weighted load. - */ - cpu_load_update(this_rq, load, pending_updates); - } -} - -/* - * Called from nohz_idle_balance() to update the load ratings before doing the - * idle balance. - */ -static void cpu_load_update_idle(struct rq *this_rq) -{ - /* - * bail if there's load or we're actually up-to-date. - */ - if (weighted_cpuload(this_rq)) - return; - - cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), 0); -} - -/* - * Record CPU load on nohz entry so we know the tickless load to account - * on nohz exit. cpu_load[0] happens then to be updated more frequently - * than other cpu_load[idx] but it should be fine as cpu_load readers - * shouldn't rely into synchronized cpu_load[*] updates. - */ -void cpu_load_update_nohz_start(void) -{ - struct rq *this_rq = this_rq(); - - /* - * This is all lockless but should be fine. If weighted_cpuload changes - * concurrently we'll exit nohz. And cpu_load write can race with - * cpu_load_update_idle() but both updater would be writing the same. - */ - this_rq->cpu_load[0] = weighted_cpuload(this_rq); -} - -/* - * Account the tickless load in the end of a nohz frame. - */ -void cpu_load_update_nohz_stop(void) -{ - unsigned long curr_jiffies = READ_ONCE(jiffies); - struct rq *this_rq = this_rq(); - unsigned long load; - struct rq_flags rf; - - if (curr_jiffies == this_rq->last_load_update_tick) - return; - - load = weighted_cpuload(this_rq); - rq_lock(this_rq, &rf); - update_rq_clock(this_rq); - cpu_load_update_nohz(this_rq, curr_jiffies, load); - rq_unlock(this_rq, &rf); -} -#else /* !CONFIG_NO_HZ_COMMON */ -static inline void cpu_load_update_nohz(struct rq *this_rq, - unsigned long curr_jiffies, - unsigned long load) { } -#endif /* CONFIG_NO_HZ_COMMON */ - -static void cpu_load_update_periodic(struct rq *this_rq, unsigned long load) -{ -#ifdef CONFIG_NO_HZ_COMMON - /* See the mess around cpu_load_update_nohz(). */ - this_rq->last_load_update_tick = READ_ONCE(jiffies); -#endif - cpu_load_update(this_rq, load, 1); -} - -/* - * Called from scheduler_tick() - */ -void cpu_load_update_active(struct rq *this_rq) -{ - unsigned long load = weighted_cpuload(this_rq); - - if (tick_nohz_tick_stopped()) - cpu_load_update_nohz(this_rq, READ_ONCE(jiffies), load); - else - cpu_load_update_periodic(this_rq, load); -} - -/* - * Return a low guess at the load of a migration-source CPU weighted - * according to the scheduling class and "nice" value. - * - * We want to under-estimate the load of migration sources, to - * balance conservatively. - */ -static unsigned long source_load(int cpu, int type) +/* CPU only has SCHED_IDLE tasks enqueued */ +static int sched_idle_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(rq); - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return min(rq->cpu_load[type-1], total); + return unlikely(rq->nr_running == rq->cfs.idle_h_nr_running && + rq->nr_running); } -/* - * Return a high guess at the load of a migration-target CPU weighted - * according to the scheduling class and "nice" value. - */ -static unsigned long target_load(int cpu, int type) +static unsigned long cpu_runnable_load(struct rq *rq) { - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(rq); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return max(rq->cpu_load[type-1], total); + return cfs_rq_runnable_load_avg(&rq->cfs); } static unsigned long capacity_of(int cpu) @@ -5638,7 +5399,7 @@ static unsigned long cpu_avg_load_per_task(int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long nr_running = READ_ONCE(rq->cfs.h_nr_running); - unsigned long load_avg = weighted_cpuload(rq); + unsigned long load_avg = cpu_runnable_load(rq); if (nr_running) return load_avg / nr_running; @@ -5736,7 +5497,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, s64 this_eff_load, prev_eff_load; unsigned long task_load; - this_eff_load = target_load(this_cpu, sd->wake_idx); + this_eff_load = cpu_runnable_load(cpu_rq(this_cpu)); if (sync) { unsigned long current_load = task_h_load(current); @@ -5754,7 +5515,7 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p, this_eff_load *= 100; this_eff_load *= capacity_of(prev_cpu); - prev_eff_load = source_load(prev_cpu, sd->wake_idx); + prev_eff_load = cpu_runnable_load(cpu_rq(prev_cpu)); prev_eff_load -= task_load; if (sched_feat(WA_BIAS)) prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2; @@ -5815,14 +5576,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, unsigned long this_runnable_load = ULONG_MAX; unsigned long min_avg_load = ULONG_MAX, this_avg_load = ULONG_MAX; unsigned long most_spare = 0, this_spare = 0; - int load_idx = sd->forkexec_idx; int imbalance_scale = 100 + (sd->imbalance_pct-100)/2; unsigned long imbalance = scale_load_down(NICE_0_LOAD) * (sd->imbalance_pct-100) / 100; - if (sd_flag & SD_BALANCE_WAKE) - load_idx = sd->wake_idx; - do { unsigned long load, avg_load, runnable_load; unsigned long spare_cap, max_spare_cap; @@ -5831,7 +5588,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, /* Skip over this group if it has no CPUs allowed */ if (!cpumask_intersects(sched_group_span(group), - &p->cpus_allowed)) + p->cpus_ptr)) continue; local_group = cpumask_test_cpu(this_cpu, @@ -5846,12 +5603,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, max_spare_cap = 0; for_each_cpu(i, sched_group_span(group)) { - /* Bias balancing toward CPUs of our domain */ - if (local_group) - load = source_load(i, load_idx); - else - load = target_load(i, load_idx); - + load = cpu_runnable_load(cpu_rq(i)); runnable_load += load; avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); @@ -5955,7 +5707,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this unsigned int min_exit_latency = UINT_MAX; u64 latest_idle_timestamp = 0; int least_loaded_cpu = this_cpu; - int shallowest_idle_cpu = -1; + int shallowest_idle_cpu = -1, si_cpu = -1; int i; /* Check if we have any choice: */ @@ -5963,7 +5715,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this return cpumask_first(sched_group_span(group)); /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { + for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) { if (available_idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); @@ -5986,8 +5738,13 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this latest_idle_timestamp = rq->idle_stamp; shallowest_idle_cpu = i; } - } else if (shallowest_idle_cpu == -1) { - load = weighted_cpuload(cpu_rq(i)); + } else if (shallowest_idle_cpu == -1 && si_cpu == -1) { + if (sched_idle_cpu(i)) { + si_cpu = i; + continue; + } + + load = cpu_runnable_load(cpu_rq(i)); if (load < min_load) { min_load = load; least_loaded_cpu = i; @@ -5995,7 +5752,11 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this } } - return shallowest_idle_cpu != -1 ? shallowest_idle_cpu : least_loaded_cpu; + if (shallowest_idle_cpu != -1) + return shallowest_idle_cpu; + if (si_cpu != -1) + return si_cpu; + return least_loaded_cpu; } static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p, @@ -6003,7 +5764,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p { int new_cpu = cpu; - if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed)) + if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr)) return prev_cpu; /* @@ -6120,7 +5881,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int if (!test_idle_cores(target, false)) return -1; - cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); + cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); for_each_cpu_wrap(core, cpus, target) { bool idle = true; @@ -6148,19 +5909,21 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int */ static int select_idle_smt(struct task_struct *p, int target) { - int cpu; + int cpu, si_cpu = -1; if (!static_branch_likely(&sched_smt_present)) return -1; for_each_cpu(cpu, cpu_smt_mask(target)) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) return cpu; + if (si_cpu == -1 && sched_idle_cpu(cpu)) + si_cpu = cpu; } - return -1; + return si_cpu; } #else /* CONFIG_SCHED_SMT */ @@ -6188,7 +5951,8 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t u64 avg_cost, avg_idle; u64 time, cost; s64 delta; - int cpu, nr = INT_MAX; + int this = smp_processor_id(); + int cpu, nr = INT_MAX, si_cpu = -1; this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc)); if (!this_sd) @@ -6212,18 +5976,20 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t nr = 4; } - time = local_clock(); + time = cpu_clock(this); for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { if (!--nr) - return -1; - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + return si_cpu; + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; if (available_idle_cpu(cpu)) break; + if (si_cpu == -1 && sched_idle_cpu(cpu)) + si_cpu = cpu; } - time = local_clock() - time; + time = cpu_clock(this) - time; cost = this_sd->avg_scan_cost; delta = (s64)(time - cost) / 8; this_sd->avg_scan_cost += delta; @@ -6239,13 +6005,14 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) struct sched_domain *sd; int i, recent_used_cpu; - if (available_idle_cpu(target)) + if (available_idle_cpu(target) || sched_idle_cpu(target)) return target; /* * If the previous CPU is cache affine and idle, don't be stupid: */ - if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev)) + if (prev != target && cpus_share_cache(prev, target) && + (available_idle_cpu(prev) || sched_idle_cpu(prev))) return prev; /* Check a recently used CPU as a potential idle candidate: */ @@ -6253,8 +6020,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) if (recent_used_cpu != prev && recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && - available_idle_cpu(recent_used_cpu) && - cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { + (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && + cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { /* * Replace recent_used_cpu with prev as it is a potential * candidate for the next wake: @@ -6489,41 +6256,55 @@ static unsigned long cpu_util_next(int cpu, struct task_struct *p, int dst_cpu) } /* - * compute_energy(): Estimates the energy that would be consumed if @p was + * compute_energy(): Estimates the energy that @pd would consume if @p was * migrated to @dst_cpu. compute_energy() predicts what will be the utilization - * landscape of the * CPUs after the task migration, and uses the Energy Model + * landscape of @pd's CPUs after the task migration, and uses the Energy Model * to compute what would be the energy if we decided to actually migrate that * task. */ static long compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) { - long util, max_util, sum_util, energy = 0; + struct cpumask *pd_mask = perf_domain_span(pd); + unsigned long cpu_cap = arch_scale_cpu_capacity(cpumask_first(pd_mask)); + unsigned long max_util = 0, sum_util = 0; int cpu; - for (; pd; pd = pd->next) { - max_util = sum_util = 0; + /* + * The capacity state of CPUs of the current rd can be driven by CPUs + * of another rd if they belong to the same pd. So, account for the + * utilization of these CPUs too by masking pd with cpu_online_mask + * instead of the rd span. + * + * If an entire pd is outside of the current rd, it will not appear in + * its pd list and will not be accounted by compute_energy(). + */ + for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { + unsigned long cpu_util, util_cfs = cpu_util_next(cpu, p, dst_cpu); + struct task_struct *tsk = cpu == dst_cpu ? p : NULL; + /* - * The capacity state of CPUs of the current rd can be driven by - * CPUs of another rd if they belong to the same performance - * domain. So, account for the utilization of these CPUs too - * by masking pd with cpu_online_mask instead of the rd span. - * - * If an entire performance domain is outside of the current rd, - * it will not appear in its pd list and will not be accounted - * by compute_energy(). + * Busy time computation: utilization clamping is not + * required since the ratio (sum_util / cpu_capacity) + * is already enough to scale the EM reported power + * consumption at the (eventually clamped) cpu_capacity. */ - for_each_cpu_and(cpu, perf_domain_span(pd), cpu_online_mask) { - util = cpu_util_next(cpu, p, dst_cpu); - util = schedutil_energy_util(cpu, util); - max_util = max(util, max_util); - sum_util += util; - } + sum_util += schedutil_cpu_util(cpu, util_cfs, cpu_cap, + ENERGY_UTIL, NULL); - energy += em_pd_energy(pd->em_pd, max_util, sum_util); + /* + * Performance domain frequency: utilization clamping + * must be considered since it affects the selection + * of the performance domain frequency. + * NOTE: in case RT tasks are running, by default the + * FREQUENCY_UTIL's utilization can be max OPP. + */ + cpu_util = schedutil_cpu_util(cpu, util_cfs, cpu_cap, + FREQUENCY_UTIL, tsk); + max_util = max(max_util, cpu_util); } - return energy; + return em_pd_energy(pd->em_pd, max_util, sum_util); } /* @@ -6565,21 +6346,19 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * other use-cases too. So, until someone finds a better way to solve this, * let's keep things simple by re-using the existing slow path. */ - static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { - unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX; + unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; struct root_domain *rd = cpu_rq(smp_processor_id())->rd; + unsigned long cpu_cap, util, base_energy = 0; int cpu, best_energy_cpu = prev_cpu; - struct perf_domain *head, *pd; - unsigned long cpu_cap, util; struct sched_domain *sd; + struct perf_domain *pd; rcu_read_lock(); pd = rcu_dereference(rd->pd); if (!pd || READ_ONCE(rd->overutilized)) goto fail; - head = pd; /* * Energy-aware wake-up happens on the lowest sched_domain starting @@ -6596,24 +6375,29 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) goto unlock; for (; pd; pd = pd->next) { - unsigned long cur_energy, spare_cap, max_spare_cap = 0; + unsigned long cur_delta, spare_cap, max_spare_cap = 0; + unsigned long base_energy_pd; int max_spare_cap_cpu = -1; + /* Compute the 'base' energy of the pd, without @p */ + base_energy_pd = compute_energy(p, -1, pd); + base_energy += base_energy_pd; + for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { - if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; /* Skip CPUs that will be overutilized. */ util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); - if (cpu_cap * 1024 < util * capacity_margin) + if (!fits_capacity(util, cpu_cap)) continue; /* Always use prev_cpu as a candidate. */ if (cpu == prev_cpu) { - prev_energy = compute_energy(p, prev_cpu, head); - best_energy = min(best_energy, prev_energy); - continue; + prev_delta = compute_energy(p, prev_cpu, pd); + prev_delta -= base_energy_pd; + best_delta = min(best_delta, prev_delta); } /* @@ -6629,9 +6413,10 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) /* Evaluate the energy impact of using this CPU. */ if (max_spare_cap_cpu >= 0) { - cur_energy = compute_energy(p, max_spare_cap_cpu, head); - if (cur_energy < best_energy) { - best_energy = cur_energy; + cur_delta = compute_energy(p, max_spare_cap_cpu, pd); + cur_delta -= base_energy_pd; + if (cur_delta < best_delta) { + best_delta = cur_delta; best_energy_cpu = max_spare_cap_cpu; } } @@ -6643,10 +6428,10 @@ unlock: * Pick the best CPU if prev_cpu cannot be used, or if it saves at * least 6% of the energy used by prev_cpu. */ - if (prev_energy == ULONG_MAX) + if (prev_delta == ULONG_MAX) return best_energy_cpu; - if ((prev_energy - best_energy) > (prev_energy >> 4)) + if ((prev_delta - best_delta) > ((prev_delta + base_energy) >> 4)) return best_energy_cpu; return prev_cpu; @@ -6689,7 +6474,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f } want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) && - cpumask_test_cpu(cpu, &p->cpus_allowed); + cpumask_test_cpu(cpu, p->cpus_ptr); } rcu_read_lock(); @@ -6980,7 +6765,7 @@ again: goto idle; #ifdef CONFIG_FAIR_GROUP_SCHED - if (prev->sched_class != &fair_sched_class) + if (!prev || prev->sched_class != &fair_sched_class) goto simple; /* @@ -7057,8 +6842,8 @@ again: goto done; simple: #endif - - put_prev_task(rq, prev); + if (prev) + put_prev_task(rq, prev); do { se = pick_next_entity(cfs_rq, NULL); @@ -7086,11 +6871,13 @@ done: __maybe_unused; return p; idle: - update_misfit_status(NULL, rq); - new_tasks = idle_balance(rq, rf); + if (!rf) + return NULL; + + new_tasks = newidle_balance(rq, rf); /* - * Because idle_balance() releases (and re-acquires) rq->lock, it is + * Because newidle_balance() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we * must re-start the pick_next_entity() loop. */ @@ -7112,7 +6899,7 @@ idle: /* * Account for a descheduled task: */ -static void put_prev_task_fair(struct rq *rq, struct task_struct *prev) +static void put_prev_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct sched_entity *se = &prev->se; struct cfs_rq *cfs_rq; @@ -7445,14 +7232,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* * We do not migrate tasks that are: * 1) throttled_lb_pair, or - * 2) cannot be migrated to this CPU due to cpus_allowed, or + * 2) cannot be migrated to this CPU due to cpus_ptr, or * 3) running (obviously), or * 4) are cache-hot on their current CPU. */ if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) return 0; - if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) { + if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) { int cpu; schedstat_inc(p->se.statistics.nr_failed_migrations_affine); @@ -7472,7 +7259,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* Prevent to re-select dst_cpu via env's CPUs: */ for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { - if (cpumask_test_cpu(cpu, &p->cpus_allowed)) { + if (cpumask_test_cpu(cpu, p->cpus_ptr)) { env->flags |= LBF_DST_PINNED; env->new_dst_cpu = cpu; break; @@ -7558,7 +7345,7 @@ static struct task_struct *detach_one_task(struct lb_env *env) static const unsigned int sched_nr_migrate_break = 32; /* - * detach_tasks() -- tries to detach up to imbalance weighted load from + * detach_tasks() -- tries to detach up to imbalance runnable load from * busiest_rq, as part of a balancing operation within domain "sd". * * Returns number of detached tasks if successful and 0 otherwise. @@ -7614,7 +7401,7 @@ static int detach_tasks(struct lb_env *env) detached++; env->imbalance -= load; -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION /* * NEWIDLE balancing is a source of latency, so preemptible * kernels will stop after the first task is detached to minimize @@ -7626,7 +7413,7 @@ static int detach_tasks(struct lb_env *env) /* * We only want to steal up to the prescribed amount of - * weighted load. + * runnable load. */ if (env->imbalance <= 0) break; @@ -7695,6 +7482,7 @@ static void attach_tasks(struct lb_env *env) rq_unlock(env->dst_rq, &rf); } +#ifdef CONFIG_NO_HZ_COMMON static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { if (cfs_rq->avg.load_avg) @@ -7722,6 +7510,19 @@ static inline bool others_have_blocked(struct rq *rq) return false; } +static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) +{ + rq->last_blocked_load_update_tick = jiffies; + + if (!has_blocked) + rq->has_blocked_load = 0; +} +#else +static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { return false; } +static inline bool others_have_blocked(struct rq *rq) { return false; } +static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {} +#endif + #ifdef CONFIG_FAIR_GROUP_SCHED static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) @@ -7787,11 +7588,7 @@ static void update_blocked_averages(int cpu) if (others_have_blocked(rq)) done = false; -#ifdef CONFIG_NO_HZ_COMMON - rq->last_blocked_load_update_tick = jiffies; - if (done) - rq->has_blocked_load = 0; -#endif + update_blocked_load_status(rq, !done); rq_unlock_irqrestore(rq, &rf); } @@ -7857,11 +7654,7 @@ static inline void update_blocked_averages(int cpu) update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class); update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class); update_irq_load_avg(rq, 0); -#ifdef CONFIG_NO_HZ_COMMON - rq->last_blocked_load_update_tick = jiffies; - if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq)) - rq->has_blocked_load = 0; -#endif + update_blocked_load_status(rq, cfs_rq_has_blocked(cfs_rq) || others_have_blocked(rq)); rq_unlock_irqrestore(rq, &rf); } @@ -7879,7 +7672,6 @@ static unsigned long task_h_load(struct task_struct *p) 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_weighted_load; /* Weighted load of group's tasks */ unsigned long load_per_task; unsigned long group_capacity; unsigned long group_util; /* Total utilization of the group */ @@ -7933,38 +7725,10 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) }; } -/** - * 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_idx is obtained. - * - * Return: The load index. - */ -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; -} - static unsigned long scale_rt_capacity(struct sched_domain *sd, int cpu) { struct rq *rq = cpu_rq(cpu); - unsigned long max = arch_scale_cpu_capacity(sd, cpu); + unsigned long max = arch_scale_cpu_capacity(cpu); unsigned long used, free; unsigned long irq; @@ -7989,7 +7753,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) unsigned long capacity = scale_rt_capacity(sd, cpu); struct sched_group *sdg = sd->groups; - cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu); + cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(cpu); if (!capacity) capacity = 1; @@ -8099,7 +7863,7 @@ static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd) /* * Group imbalance indicates (and tries to solve) the problem where balancing - * groups is inadequate due to ->cpus_allowed constraints. + * groups is inadequate due to ->cpus_ptr constraints. * * Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a * cpumask covering 1 CPU of the first group and 3 CPUs of the second group. @@ -8184,8 +7948,7 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) static inline bool group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { - return sg->sgc->min_capacity * capacity_margin < - ref->sgc->min_capacity * 1024; + return fits_capacity(sg->sgc->min_capacity, ref->sgc->min_capacity); } /* @@ -8195,8 +7958,7 @@ group_smaller_min_cpu_capacity(struct sched_group *sg, struct sched_group *ref) static inline bool group_smaller_max_cpu_capacity(struct sched_group *sg, struct sched_group *ref) { - return sg->sgc->max_capacity * capacity_margin < - ref->sgc->max_capacity * 1024; + return fits_capacity(sg->sgc->max_capacity, ref->sgc->max_capacity); } static inline enum @@ -8249,9 +8011,6 @@ static inline void update_sg_lb_stats(struct lb_env *env, struct sg_lb_stats *sgs, int *sg_status) { - int local_group = cpumask_test_cpu(env->dst_cpu, sched_group_span(group)); - int load_idx = get_sd_load_idx(env->sd, env->idle); - unsigned long load; int i, nr_running; memset(sgs, 0, sizeof(*sgs)); @@ -8262,13 +8021,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, if ((env->flags & LBF_NOHZ_STATS) && update_nohz_stats(rq, false)) env->flags |= LBF_NOHZ_AGAIN; - /* Bias balancing toward CPUs of our domain: */ - if (local_group) - load = target_load(i, load_idx); - else - load = source_load(i, load_idx); - - sgs->group_load += load; + sgs->group_load += cpu_runnable_load(rq); sgs->group_util += cpu_util(i); sgs->sum_nr_running += rq->cfs.h_nr_running; @@ -8283,7 +8036,6 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->nr_numa_running += rq->nr_numa_running; sgs->nr_preferred_running += rq->nr_preferred_running; #endif - sgs->sum_weighted_load += weighted_cpuload(rq); /* * No need to call idle_cpu() if nr_running is not 0 */ @@ -8302,7 +8054,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; if (sgs->sum_nr_running) - sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; + sgs->load_per_task = sgs->group_load / sgs->sum_nr_running; sgs->group_weight = group->group_weight; @@ -8516,8 +8268,12 @@ next_group: /* Update over-utilization (tipping point, U >= 0) indicator */ WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED); + trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED); } else if (sg_status & SG_OVERUTILIZED) { - WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED); + struct root_domain *rd = env->dst_rq->rd; + + WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); + trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); } } @@ -8723,7 +8479,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * find_busiest_group - Returns the busiest group within the sched_domain * if there is an imbalance. * - * Also calculates the amount of weighted load which should be moved + * Also calculates the amount of runnable load which should be moved * to restore balance. * * @env: The load balancing environment. @@ -8768,7 +8524,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env) /* * If the busiest group is imbalanced the below checks don't * work because they assume all things are equal, which typically - * isn't true due to cpus_allowed constraints and the like. + * isn't true due to cpus_ptr constraints and the like. */ if (busiest->group_type == group_imbalanced) goto force_balance; @@ -8842,7 +8598,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, int i; for_each_cpu_and(i, sched_group_span(group), env->cpus) { - unsigned long capacity, wl; + unsigned long capacity, load; enum fbq_type rt; rq = cpu_rq(i); @@ -8896,30 +8652,30 @@ static struct rq *find_busiest_queue(struct lb_env *env, rq->nr_running == 1) continue; - wl = weighted_cpuload(rq); + load = cpu_runnable_load(rq); /* - * When comparing with imbalance, use weighted_cpuload() + * When comparing with imbalance, use cpu_runnable_load() * which is not scaled with the CPU capacity. */ - if (rq->nr_running == 1 && wl > env->imbalance && + if (rq->nr_running == 1 && load > env->imbalance && !check_cpu_capacity(rq, env->sd)) continue; /* * For the load comparisons with the other CPU's, consider - * the weighted_cpuload() scaled with the CPU capacity, so + * the cpu_runnable_load() scaled with the CPU capacity, so * that the load can be moved away from the CPU that is * potentially running at a lower capacity. * - * Thus we're looking for max(wl_i / capacity_i), crosswise + * Thus we're looking for max(load_i / capacity_i), crosswise * multiplication to rid ourselves of the division works out - * to: wl_i * capacity_j > wl_j * capacity_i; where j is + * to: load_i * capacity_j > load_j * capacity_i; where j is * our previous maximum. */ - if (wl * busiest_capacity > busiest_load * capacity) { - busiest_load = wl; + if (load * busiest_capacity > busiest_load * capacity) { + busiest_load = load; busiest_capacity = capacity; busiest = rq; } @@ -9210,7 +8966,7 @@ more_balance: * if the curr task on busiest CPU can't be * moved to this_cpu: */ - if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { + if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { raw_spin_unlock_irqrestore(&busiest->lock, flags); env.flags |= LBF_ALL_PINNED; @@ -9260,9 +9016,10 @@ more_balance: out_balanced: /* * We reach balance although we may have faced some affinity - * constraints. Clear the imbalance flag if it was set. + * constraints. Clear the imbalance flag only if other tasks got + * a chance to move and fix the imbalance. */ - if (sd_parent) { + if (sd_parent && !(env.flags & LBF_ALL_PINNED)) { int *group_imbalance = &sd_parent->groups->sgc->imbalance; if (*group_imbalance) @@ -9283,10 +9040,10 @@ out_one_pinned: ld_moved = 0; /* - * idle_balance() disregards balance intervals, so we could repeatedly - * reach this code, which would lead to balance_interval skyrocketting - * in a short amount of time. Skip the balance_interval increase logic - * to avoid that. + * newidle_balance() disregards balance intervals, so we could + * repeatedly reach this code, which would lead to balance_interval + * skyrocketting in a short amount of time. Skip the balance_interval + * increase logic to avoid that. */ if (env.idle == CPU_NEWLY_IDLE) goto out; @@ -9879,7 +9636,6 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags, rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - cpu_load_update_idle(rq); rq_unlock_irqrestore(rq, &rf); if (flags & NOHZ_BALANCE_KICK) @@ -9997,7 +9753,7 @@ static inline void nohz_newidle_balance(struct rq *this_rq) { } * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ -static int idle_balance(struct rq *this_rq, struct rq_flags *rf) +int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { unsigned long next_balance = jiffies + HZ; int this_cpu = this_rq->cpu; @@ -10005,6 +9761,7 @@ static int idle_balance(struct rq *this_rq, struct rq_flags *rf) int pulled_task = 0; u64 curr_cost = 0; + update_misfit_status(NULL, this_rq); /* * We must set idle_stamp _before_ calling idle_balance(), such that we * measure the duration of idle_balance() as idle time. @@ -10389,9 +10146,19 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) * This routine is mostly called to set cfs_rq->curr field when a task * migrates between groups/classes. */ -static void set_curr_task_fair(struct rq *rq) +static void set_next_task_fair(struct rq *rq, struct task_struct *p) { - struct sched_entity *se = &rq->curr->se; + struct sched_entity *se = &p->se; + +#ifdef CONFIG_SMP + if (task_on_rq_queued(p)) { + /* + * Move the next running task to the front of the list, so our + * cfs_tasks list becomes MRU one. + */ + list_move(&se->group_node, &rq->cfs_tasks); + } +#endif for_each_sched_entity(se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); @@ -10509,18 +10276,18 @@ err: void online_fair_sched_group(struct task_group *tg) { struct sched_entity *se; + struct rq_flags rf; struct rq *rq; int i; for_each_possible_cpu(i) { rq = cpu_rq(i); se = tg->se[i]; - - raw_spin_lock_irq(&rq->lock); + rq_lock_irq(rq, &rf); update_rq_clock(rq); attach_entity_cfs_rq(se); sync_throttle(tg, i); - raw_spin_unlock_irq(&rq->lock); + rq_unlock_irq(rq, &rf); } } @@ -10662,7 +10429,9 @@ const struct sched_class fair_sched_class = { .check_preempt_curr = check_preempt_wakeup, .pick_next_task = pick_next_task_fair, + .put_prev_task = put_prev_task_fair, + .set_next_task = set_next_task_fair, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_fair, @@ -10675,7 +10444,6 @@ const struct sched_class fair_sched_class = { .set_cpus_allowed = set_cpus_allowed_common, #endif - .set_curr_task = set_curr_task_fair, .task_tick = task_tick_fair, .task_fork = task_fork_fair, @@ -10690,6 +10458,10 @@ const struct sched_class fair_sched_class = { #ifdef CONFIG_FAIR_GROUP_SCHED .task_change_group = task_change_group_fair, #endif + +#ifdef CONFIG_UCLAMP_TASK + .uclamp_enabled = 1, +#endif }; #ifdef CONFIG_SCHED_DEBUG @@ -10708,18 +10480,22 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m) { int node; unsigned long tsf = 0, tpf = 0, gsf = 0, gpf = 0; + struct numa_group *ng; + rcu_read_lock(); + ng = rcu_dereference(p->numa_group); for_each_online_node(node) { if (p->numa_faults) { tsf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 0)]; tpf = p->numa_faults[task_faults_idx(NUMA_MEM, node, 1)]; } - if (p->numa_group) { - gsf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 0)], - gpf = p->numa_group->faults[task_faults_idx(NUMA_MEM, node, 1)]; + if (ng) { + gsf = ng->faults[task_faults_idx(NUMA_MEM, node, 0)], + gpf = ng->faults[task_faults_idx(NUMA_MEM, node, 1)]; } print_numa_stats(m, node, tsf, tpf, gsf, gpf); } + rcu_read_unlock(); } #endif /* CONFIG_NUMA_BALANCING */ #endif /* CONFIG_SCHED_DEBUG */ @@ -10737,3 +10513,83 @@ __init void init_sched_fair_class(void) #endif /* SMP */ } + +/* + * Helper functions to facilitate extracting info from tracepoints. + */ + +const struct sched_avg *sched_trace_cfs_rq_avg(struct cfs_rq *cfs_rq) +{ +#ifdef CONFIG_SMP + return cfs_rq ? &cfs_rq->avg : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_avg); + +char *sched_trace_cfs_rq_path(struct cfs_rq *cfs_rq, char *str, int len) +{ + if (!cfs_rq) { + if (str) + strlcpy(str, "(null)", len); + else + return NULL; + } + + cfs_rq_tg_path(cfs_rq, str, len); + return str; +} +EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_path); + +int sched_trace_cfs_rq_cpu(struct cfs_rq *cfs_rq) +{ + return cfs_rq ? cpu_of(rq_of(cfs_rq)) : -1; +} +EXPORT_SYMBOL_GPL(sched_trace_cfs_rq_cpu); + +const struct sched_avg *sched_trace_rq_avg_rt(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq ? &rq->avg_rt : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rq_avg_rt); + +const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq ? &rq->avg_dl : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rq_avg_dl); + +const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq) +{ +#if defined(CONFIG_SMP) && defined(CONFIG_HAVE_SCHED_AVG_IRQ) + return rq ? &rq->avg_irq : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rq_avg_irq); + +int sched_trace_rq_cpu(struct rq *rq) +{ + return rq ? cpu_of(rq) : -1; +} +EXPORT_SYMBOL_GPL(sched_trace_rq_cpu); + +const struct cpumask *sched_trace_rd_span(struct root_domain *rd) +{ +#ifdef CONFIG_SMP + return rd ? rd->span : NULL; +#else + return NULL; +#endif +} +EXPORT_SYMBOL_GPL(sched_trace_rd_span); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 858589b83377..2410db5e9a35 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -39,7 +39,6 @@ SCHED_FEAT(WAKEUP_PREEMPTION, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) -SCHED_FEAT(LB_BIAS, false) /* * Decrement CPU capacity based on time not spent running tasks diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 80940939b733..8dad5aa600ea 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -238,16 +238,16 @@ static void do_idle(void) tick_nohz_idle_enter(); while (!need_resched()) { - check_pgt_cache(); rmb(); + local_irq_disable(); + if (cpu_is_offline(cpu)) { - tick_nohz_idle_stop_tick_protected(); + tick_nohz_idle_stop_tick(); cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } - local_irq_disable(); arch_cpu_idle_enter(); /* @@ -311,7 +311,7 @@ static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer) return HRTIMER_NORESTART; } -void play_idle(unsigned long duration_ms) +void play_idle(unsigned long duration_us) { struct idle_timer it; @@ -323,7 +323,7 @@ void play_idle(unsigned long duration_ms) WARN_ON_ONCE(current->nr_cpus_allowed != 1); WARN_ON_ONCE(!(current->flags & PF_KTHREAD)); WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY)); - WARN_ON_ONCE(!duration_ms); + WARN_ON_ONCE(!duration_us); rcu_sleep_check(); preempt_disable(); @@ -333,7 +333,8 @@ void play_idle(unsigned long duration_ms) it.done = 0; hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); it.timer.function = idle_inject_timer_fn; - hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED); + hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC), + HRTIMER_MODE_REL_PINNED); while (!READ_ONCE(it.done)) do_idle(); @@ -374,14 +375,27 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl resched_curr(rq); } -static struct task_struct * -pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ +} + +static void set_next_task_idle(struct rq *rq, struct task_struct *next) { - put_prev_task(rq, prev); update_idle_core(rq); schedstat_inc(rq->sched_goidle); +} + +static struct task_struct * +pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +{ + struct task_struct *next = rq->idle; - return rq->idle; + if (prev) + put_prev_task(rq, prev); + + set_next_task_idle(rq, next); + + return next; } /* @@ -397,10 +411,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) raw_spin_lock_irq(&rq->lock); } -static void put_prev_task_idle(struct rq *rq, struct task_struct *prev) -{ -} - /* * scheduler tick hitting a task of our scheduling class. * @@ -413,10 +423,6 @@ static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued) { } -static void set_curr_task_idle(struct rq *rq) -{ -} - static void switched_to_idle(struct rq *rq, struct task_struct *p) { BUG(); @@ -451,13 +457,13 @@ const struct sched_class idle_sched_class = { .pick_next_task = pick_next_task_idle, .put_prev_task = put_prev_task_idle, + .set_next_task = set_next_task_idle, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_idle, .set_cpus_allowed = set_cpus_allowed_common, #endif - .set_curr_task = set_curr_task_idle, .task_tick = task_tick_idle, .get_rr_interval = get_rr_interval_idle, diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index 123ea07a3f3b..9fcb2a695a41 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -14,11 +14,25 @@ EXPORT_SYMBOL_GPL(housekeeping_overridden); static cpumask_var_t housekeeping_mask; static unsigned int housekeeping_flags; +bool housekeeping_enabled(enum hk_flags flags) +{ + return !!(housekeeping_flags & flags); +} +EXPORT_SYMBOL_GPL(housekeeping_enabled); + int housekeeping_any_cpu(enum hk_flags flags) { - if (static_branch_unlikely(&housekeeping_overridden)) - if (housekeeping_flags & flags) + int cpu; + + if (static_branch_unlikely(&housekeeping_overridden)) { + if (housekeeping_flags & flags) { + cpu = sched_numa_find_closest(housekeeping_mask, smp_processor_id()); + if (cpu < nr_cpu_ids) + return cpu; + return cpumask_any_and(housekeeping_mask, cpu_online_mask); + } + } return smp_processor_id(); } EXPORT_SYMBOL_GPL(housekeeping_any_cpu); diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c index befce29bd882..a96db50d40e0 100644 --- a/kernel/sched/pelt.c +++ b/kernel/sched/pelt.c @@ -28,6 +28,8 @@ #include "sched.h" #include "pelt.h" +#include <trace/events/sched.h> + /* * Approximate: * val * y^n, where y^32 ~= 0.5 (~1 scheduling period) @@ -265,6 +267,7 @@ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se) { if (___update_load_sum(now, &se->avg, 0, 0, 0)) { ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); + trace_pelt_se_tp(se); return 1; } @@ -278,6 +281,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se ___update_load_avg(&se->avg, se_weight(se), se_runnable(se)); cfs_se_util_change(&se->avg); + trace_pelt_se_tp(se); return 1; } @@ -292,6 +296,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq) cfs_rq->curr != NULL)) { ___update_load_avg(&cfs_rq->avg, 1, 1); + trace_pelt_cfs_tp(cfs_rq); return 1; } @@ -317,6 +322,7 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running) running)) { ___update_load_avg(&rq->avg_rt, 1, 1); + trace_pelt_rt_tp(rq); return 1; } @@ -340,6 +346,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running) running)) { ___update_load_avg(&rq->avg_dl, 1, 1); + trace_pelt_dl_tp(rq); return 1; } @@ -366,7 +373,7 @@ int update_irq_load_avg(struct rq *rq, u64 running) * reflect the real amount of computation */ running = cap_scale(running, arch_scale_freq_capacity(cpu_of(rq))); - running = cap_scale(running, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + running = cap_scale(running, arch_scale_cpu_capacity(cpu_of(rq))); /* * We know the time that has been used by interrupt since last update @@ -388,8 +395,10 @@ int update_irq_load_avg(struct rq *rq, u64 running) 1, 1); - if (ret) + if (ret) { ___update_load_avg(&rq->avg_irq, 1, 1); + trace_pelt_irq_tp(rq); + } return ret; } diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 7489d5f56960..afff644da065 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -79,7 +79,7 @@ static inline void update_rq_clock_pelt(struct rq *rq, s64 delta) * Scale the elapsed time to reflect the real amount of * computation */ - delta = cap_scale(delta, arch_scale_cpu_capacity(NULL, cpu_of(rq))); + delta = cap_scale(delta, arch_scale_cpu_capacity(cpu_of(rq))); delta = cap_scale(delta, arch_scale_freq_capacity(cpu_of(rq))); rq->clock_pelt += delta; diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 7acc632c3b82..517e3719027e 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -1051,7 +1051,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, if (!rcu_access_pointer(group->poll_kworker)) { struct sched_param param = { - .sched_priority = MAX_RT_PRIO - 1, + .sched_priority = 1, }; struct kthread_worker *kworker; @@ -1061,7 +1061,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, mutex_unlock(&group->trigger_lock); return ERR_CAST(kworker); } - sched_setscheduler(kworker->task, SCHED_FIFO, ¶m); + sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m); kthread_init_delayed_work(&group->poll_work, psi_poll_work); rcu_assign_pointer(group->poll_kworker, kworker); @@ -1131,7 +1131,15 @@ static void psi_trigger_destroy(struct kref *ref) * deadlock while waiting for psi_poll_work to acquire trigger_lock */ if (kworker_to_destroy) { + /* + * After the RCU grace period has expired, the worker + * can no longer be found through group->poll_kworker. + * But it might have been already scheduled before + * that - deschedule it cleanly before destroying it. + */ kthread_cancel_delayed_work_sync(&group->poll_work); + atomic_set(&group->poll_scheduled, 0); + kthread_destroy_worker(kworker_to_destroy); } kfree(t); @@ -1190,7 +1198,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, if (static_branch_likely(&psi_disabled)) return -EOPNOTSUPP; - buf_size = min(nbytes, (sizeof(buf) - 1)); + buf_size = min(nbytes, sizeof(buf)); if (copy_from_user(buf, user_buf, buf_size)) return -EFAULT; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 1e6b909dca36..ebaa4e619684 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -45,8 +45,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) raw_spin_lock_init(&rt_b->rt_runtime_lock); - hrtimer_init(&rt_b->rt_period_timer, - CLOCK_MONOTONIC, HRTIMER_MODE_REL); + hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_HARD); rt_b->rt_period_timer.function = sched_rt_period_timer; } @@ -67,7 +67,8 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) * to update the period. */ hrtimer_forward_now(&rt_b->rt_period_timer, ns_to_ktime(0)); - hrtimer_start_expires(&rt_b->rt_period_timer, HRTIMER_MODE_ABS_PINNED); + hrtimer_start_expires(&rt_b->rt_period_timer, + HRTIMER_MODE_ABS_PINNED_HARD); } raw_spin_unlock(&rt_b->rt_runtime_lock); } @@ -1498,12 +1499,22 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag #endif } -static inline void set_next_task(struct rq *rq, struct task_struct *p) +static inline void set_next_task_rt(struct rq *rq, struct task_struct *p) { p->se.exec_start = rq_clock_task(rq); /* The running task is never eligible for pushing */ dequeue_pushable_task(rq, p); + + /* + * If prev task was rt, put_prev_task() has already updated the + * utilization. We only care of the case where we start to schedule a + * rt task + */ + if (rq->curr->sched_class != &rt_sched_class) + update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); + + rt_queue_push_tasks(rq); } static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, @@ -1543,56 +1554,19 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) struct task_struct *p; struct rt_rq *rt_rq = &rq->rt; - if (need_pull_rt_task(rq, prev)) { - /* - * This is OK, because current is on_cpu, which avoids it being - * picked for load-balance and preemption/IRQs are still - * disabled avoiding further scheduler activity on it and we're - * being very careful to re-start the picking loop. - */ - rq_unpin_lock(rq, rf); - pull_rt_task(rq); - rq_repin_lock(rq, rf); - /* - * pull_rt_task() can drop (and re-acquire) rq->lock; this - * means a dl or stop task can slip in, in which case we need - * to re-start task selection. - */ - if (unlikely((rq->stop && task_on_rq_queued(rq->stop)) || - rq->dl.dl_nr_running)) - return RETRY_TASK; - } - - /* - * We may dequeue prev's rt_rq in put_prev_task(). - * So, we update time before rt_queued check. - */ - if (prev->sched_class == &rt_sched_class) - update_curr_rt(rq); + WARN_ON_ONCE(prev || rf); if (!rt_rq->rt_queued) return NULL; - put_prev_task(rq, prev); - p = _pick_next_task_rt(rq); - set_next_task(rq, p); - - rt_queue_push_tasks(rq); - - /* - * If prev task was rt, put_prev_task() has already updated the - * utilization. We only care of the case where we start to schedule a - * rt task - */ - if (rq->curr->sched_class != &rt_sched_class) - update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0); + set_next_task_rt(rq, p); return p; } -static void put_prev_task_rt(struct rq *rq, struct task_struct *p) +static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf) { update_curr_rt(rq); @@ -1604,6 +1578,18 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) */ if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); + + if (rf && !on_rt_rq(&p->rt) && need_pull_rt_task(rq, p)) { + /* + * This is OK, because current is on_cpu, which avoids it being + * picked for load-balance and preemption/IRQs are still + * disabled avoiding further scheduler activity on it and we've + * not yet started the picking loop. + */ + rq_unpin_lock(rq, rf); + pull_rt_task(rq); + rq_repin_lock(rq, rf); + } } #ifdef CONFIG_SMP @@ -1614,7 +1600,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, &p->cpus_allowed)) + cpumask_test_cpu(cpu, p->cpus_ptr)) return 1; return 0; @@ -1751,7 +1737,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) * Also make sure that it wasn't scheduled on its rq. */ if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || + !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) || task_running(rq, task) || !rt_task(task) || !task_on_rq_queued(task))) { @@ -2304,8 +2290,10 @@ static void watchdog(struct rq *rq, struct task_struct *p) } next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ); - if (p->rt.timeout > next) - p->cputime_expires.sched_exp = p->se.sum_exec_runtime; + if (p->rt.timeout > next) { + posix_cputimers_rt_watchdog(&p->posix_cputimers, + p->se.sum_exec_runtime); + } } } #else @@ -2354,11 +2342,6 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) } } -static void set_curr_task_rt(struct rq *rq) -{ - set_next_task(rq, rq->curr); -} - static unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task) { /* @@ -2380,6 +2363,7 @@ const struct sched_class rt_sched_class = { .pick_next_task = pick_next_task_rt, .put_prev_task = put_prev_task_rt, + .set_next_task = set_next_task_rt, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_rt, @@ -2391,7 +2375,6 @@ const struct sched_class rt_sched_class = { .switched_from = switched_from_rt, #endif - .set_curr_task = set_curr_task_rt, .task_tick = task_tick_rt, .get_rr_interval = get_rr_interval_rt, @@ -2400,6 +2383,10 @@ const struct sched_class rt_sched_class = { .switched_to = switched_to_rt, .update_curr = update_curr_rt, + +#ifdef CONFIG_UCLAMP_TASK + .uclamp_enabled = 1, +#endif }; #ifdef CONFIG_RT_GROUP_SCHED diff --git a/kernel/sched/sched-pelt.h b/kernel/sched/sched-pelt.h index a26473674fb7..c529706bed11 100644 --- a/kernel/sched/sched-pelt.h +++ b/kernel/sched/sched-pelt.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Generated by Documentation/scheduler/sched-pelt; do not modify. */ -static const u32 runnable_avg_yN_inv[] = { +static const u32 runnable_avg_yN_inv[] __maybe_unused = { 0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6, 0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85, 0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b52ed1ada0be..b3cb895d14a2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -96,12 +96,6 @@ extern atomic_long_t calc_load_tasks; extern void calc_global_load_tick(struct rq *this_rq); extern long calc_load_fold_active(struct rq *this_rq, long adjust); -#ifdef CONFIG_SMP -extern void cpu_load_update_active(struct rq *this_rq); -#else -static inline void cpu_load_update_active(struct rq *this_rq) { } -#endif - /* * Helpers for converting nanosecond timing to jiffy resolution */ @@ -341,11 +335,11 @@ struct cfs_bandwidth { u64 quota; u64 runtime; s64 hierarchical_quota; - u64 runtime_expires; - int expires_seq; - short idle; - short period_active; + u8 idle; + u8 period_active; + u8 distribute_running; + u8 slack_started; struct hrtimer period_timer; struct hrtimer slack_timer; struct list_head throttled_cfs_rq; @@ -354,8 +348,6 @@ struct cfs_bandwidth { int nr_periods; int nr_throttled; u64 throttled_time; - - bool distribute_running; #endif }; @@ -399,6 +391,16 @@ struct task_group { #endif struct cfs_bandwidth cfs_bandwidth; + +#ifdef CONFIG_UCLAMP_TASK_GROUP + /* The two decimal precision [%] value requested from user-space */ + unsigned int uclamp_pct[UCLAMP_CNT]; + /* Clamp values requested for a task group */ + struct uclamp_se uclamp_req[UCLAMP_CNT]; + /* Effective clamp values used for a task group */ + struct uclamp_se uclamp[UCLAMP_CNT]; +#endif + }; #ifdef CONFIG_FAIR_GROUP_SCHED @@ -489,7 +491,8 @@ struct cfs_rq { struct load_weight load; unsigned long runnable_weight; unsigned int nr_running; - unsigned int h_nr_running; + unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */ + unsigned int idle_h_nr_running; /* SCHED_IDLE */ u64 exec_clock; u64 min_vruntime; @@ -562,8 +565,6 @@ struct cfs_rq { #ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; - int expires_seq; - u64 runtime_expires; s64 runtime_remaining; u64 throttled_clock; @@ -783,9 +784,6 @@ struct root_domain { struct perf_domain __rcu *pd; }; -extern struct root_domain def_root_domain; -extern struct mutex sched_domains_mutex; - extern void init_defrootdomain(void); extern int sched_init_domains(const struct cpumask *cpu_map); extern void rq_attach_root(struct rq *rq, struct root_domain *rd); @@ -797,6 +795,48 @@ extern void rto_push_irq_work_func(struct irq_work *work); #endif #endif /* CONFIG_SMP */ +#ifdef CONFIG_UCLAMP_TASK +/* + * struct uclamp_bucket - Utilization clamp bucket + * @value: utilization clamp value for tasks on this clamp bucket + * @tasks: number of RUNNABLE tasks on this clamp bucket + * + * Keep track of how many tasks are RUNNABLE for a given utilization + * clamp value. + */ +struct uclamp_bucket { + unsigned long value : bits_per(SCHED_CAPACITY_SCALE); + unsigned long tasks : BITS_PER_LONG - bits_per(SCHED_CAPACITY_SCALE); +}; + +/* + * struct uclamp_rq - rq's utilization clamp + * @value: currently active clamp values for a rq + * @bucket: utilization clamp buckets affecting a rq + * + * Keep track of RUNNABLE tasks on a rq to aggregate their clamp values. + * A clamp value is affecting a rq when there is at least one task RUNNABLE + * (or actually running) with that value. + * + * There are up to UCLAMP_CNT possible different clamp values, currently there + * are only two: minimum utilization and maximum utilization. + * + * All utilization clamping values are MAX aggregated, since: + * - for util_min: we want to run the CPU at least at the max of the minimum + * utilization required by its currently RUNNABLE tasks. + * - for util_max: we want to allow the CPU to run up to the max of the + * maximum utilization allowed by its currently RUNNABLE tasks. + * + * Since on each system we expect only a limited number of different + * utilization clamp values (UCLAMP_BUCKETS), use a simple array to track + * the metrics required to compute all the per-rq utilization clamp values. + */ +struct uclamp_rq { + unsigned int value; + struct uclamp_bucket bucket[UCLAMP_BUCKETS]; +}; +#endif /* CONFIG_UCLAMP_TASK */ + /* * This is the main, per-CPU runqueue data structure. * @@ -818,8 +858,6 @@ struct rq { unsigned int nr_preferred_running; unsigned int numa_migrate_on; #endif - #define CPU_LOAD_IDX_MAX 5 - unsigned long cpu_load[CPU_LOAD_IDX_MAX]; #ifdef CONFIG_NO_HZ_COMMON #ifdef CONFIG_SMP unsigned long last_load_update_tick; @@ -830,11 +868,16 @@ struct rq { atomic_t nohz_flags; #endif /* CONFIG_NO_HZ_COMMON */ - /* capture load from *all* tasks on this CPU: */ - struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; +#ifdef CONFIG_UCLAMP_TASK + /* Utilization clamp values based on CPU's RUNNABLE tasks */ + struct uclamp_rq uclamp[UCLAMP_CNT] ____cacheline_aligned; + unsigned int uclamp_flags; +#define UCLAMP_FLAG_IDLE 0x01 +#endif + struct cfs_rq cfs; struct rt_rq rt; struct dl_rq dl; @@ -1222,16 +1265,18 @@ enum numa_topology_type { extern enum numa_topology_type sched_numa_topology_type; extern int sched_max_numa_distance; extern bool find_numa_distance(int distance); -#endif - -#ifdef CONFIG_NUMA extern void sched_init_numa(void); extern void sched_domains_numa_masks_set(unsigned int cpu); extern void sched_domains_numa_masks_clear(unsigned int cpu); +extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu); #else static inline void sched_init_numa(void) { } static inline void sched_domains_numa_masks_set(unsigned int cpu) { } static inline void sched_domains_numa_masks_clear(unsigned int cpu) { } +static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu) +{ + return nr_cpu_ids; +} #endif #ifdef CONFIG_NUMA_BALANCING @@ -1410,10 +1455,14 @@ static inline void unregister_sched_domain_sysctl(void) } #endif +extern int newidle_balance(struct rq *this_rq, struct rq_flags *rf); + #else static inline void sched_ttwu_pending(void) { } +static inline int newidle_balance(struct rq *this_rq, struct rq_flags *rf) { return 0; } + #endif /* CONFIG_SMP */ #include "stats.h" @@ -1649,6 +1698,10 @@ extern const u32 sched_prio_to_wmult[40]; struct sched_class { const struct sched_class *next; +#ifdef CONFIG_UCLAMP_TASK + int uclamp_enabled; +#endif + void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); void (*yield_task) (struct rq *rq); @@ -1657,17 +1710,21 @@ struct sched_class { void (*check_preempt_curr)(struct rq *rq, struct task_struct *p, int flags); /* - * It is the responsibility of the pick_next_task() method that will - * return the next task to call put_prev_task() on the @prev task or - * something equivalent. + * Both @prev and @rf are optional and may be NULL, in which case the + * caller must already have invoked put_prev_task(rq, prev, rf). + * + * Otherwise it is the responsibility of the pick_next_task() to call + * put_prev_task() on the @prev task or something equivalent, IFF it + * returns a next task. * - * May return RETRY_TASK when it finds a higher prio class has runnable - * tasks. + * In that case (@rf != NULL) it may return RETRY_TASK when it finds a + * higher prio class has runnable tasks. */ struct task_struct * (*pick_next_task)(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); - void (*put_prev_task)(struct rq *rq, struct task_struct *p); + void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct rq_flags *rf); + void (*set_next_task)(struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP int (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags); @@ -1682,7 +1739,6 @@ struct sched_class { void (*rq_offline)(struct rq *rq); #endif - void (*set_curr_task)(struct rq *rq); void (*task_tick)(struct rq *rq, struct task_struct *p, int queued); void (*task_fork)(struct task_struct *p); void (*task_dead)(struct task_struct *p); @@ -1712,12 +1768,14 @@ struct sched_class { static inline void put_prev_task(struct rq *rq, struct task_struct *prev) { - prev->sched_class->put_prev_task(rq, prev); + WARN_ON_ONCE(rq->curr != prev); + prev->sched_class->put_prev_task(rq, prev, NULL); } -static inline void set_curr_task(struct rq *rq, struct task_struct *curr) +static inline void set_next_task(struct rq *rq, struct task_struct *next) { - curr->sched_class->set_curr_task(rq); + WARN_ON_ONCE(rq->curr != next); + next->sched_class->set_next_task(rq, next); } #ifdef CONFIG_SMP @@ -1900,7 +1958,7 @@ unsigned long arch_scale_freq_capacity(int cpu) #endif #ifdef CONFIG_SMP -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION static inline void double_rq_lock(struct rq *rq1, struct rq *rq2); @@ -1952,7 +2010,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) return ret; } -#endif /* CONFIG_PREEMPT */ +#endif /* CONFIG_PREEMPTION */ /* * double_lock_balance - lock the busiest runqueue, this_rq is locked already. @@ -2222,6 +2280,48 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {} #endif /* CONFIG_CPU_FREQ */ +#ifdef CONFIG_UCLAMP_TASK +enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id); + +static __always_inline +unsigned int uclamp_util_with(struct rq *rq, unsigned int util, + struct task_struct *p) +{ + unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value); + unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value); + + if (p) { + min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN)); + max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX)); + } + + /* + * Since CPU's {min,max}_util clamps are MAX aggregated considering + * RUNNABLE tasks with _different_ clamps, we can end up with an + * inversion. Fix it now when the clamps are applied. + */ + if (unlikely(min_util >= max_util)) + return min_util; + + return clamp(util, min_util, max_util); +} + +static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) +{ + return uclamp_util_with(rq, util, NULL); +} +#else /* CONFIG_UCLAMP_TASK */ +static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util, + struct task_struct *p) +{ + return util; +} +static inline unsigned int uclamp_util(struct rq *rq, unsigned int util) +{ + return util; +} +#endif /* CONFIG_UCLAMP_TASK */ + #ifdef arch_scale_freq_capacity # ifndef arch_scale_freq_invariant # define arch_scale_freq_invariant() true @@ -2237,7 +2337,6 @@ static inline unsigned long capacity_orig_of(int cpu) } #endif -#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL /** * enum schedutil_type - CPU utilization type * @FREQUENCY_UTIL: Utilization used to select frequency @@ -2253,15 +2352,11 @@ enum schedutil_type { ENERGY_UTIL, }; -unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs, - unsigned long max, enum schedutil_type type); +#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL -static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) -{ - unsigned long max = arch_scale_cpu_capacity(NULL, cpu); - - return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL); -} +unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type, + struct task_struct *p); static inline unsigned long cpu_bw_dl(struct rq *rq) { @@ -2290,11 +2385,13 @@ static inline unsigned long cpu_util_rt(struct rq *rq) return READ_ONCE(rq->avg_rt.util_avg); } #else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ -static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs) +static inline unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs, + unsigned long max, enum schedutil_type type, + struct task_struct *p) { - return cfs; + return 0; } -#endif +#endif /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */ #ifdef CONFIG_HAVE_SCHED_AVG_IRQ static inline unsigned long cpu_util_irq(struct rq *rq) diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index aa0de240fb41..ba683fe81a6e 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -157,9 +157,10 @@ static inline void sched_info_dequeued(struct rq *rq, struct task_struct *t) { unsigned long long now = rq_clock(rq), delta = 0; - if (unlikely(sched_info_on())) + if (sched_info_on()) { if (t->sched_info.last_queued) delta = now - t->sched_info.last_queued; + } sched_info_reset_dequeued(t); t->sched_info.run_delay += delta; @@ -192,7 +193,7 @@ static void sched_info_arrive(struct rq *rq, struct task_struct *t) */ static inline void sched_info_queued(struct rq *rq, struct task_struct *t) { - if (unlikely(sched_info_on())) { + if (sched_info_on()) { if (!t->sched_info.last_queued) t->sched_info.last_queued = rq_clock(rq); } @@ -239,7 +240,7 @@ __sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct static inline void sched_info_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next) { - if (unlikely(sched_info_on())) + if (sched_info_on()) __sched_info_switch(rq, prev, next); } diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index c183b790ca54..7e1cee4e65b2 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -23,17 +23,22 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) /* we're never preempted */ } +static void set_next_task_stop(struct rq *rq, struct task_struct *stop) +{ + stop->se.exec_start = rq_clock_task(rq); +} + static struct task_struct * pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *stop = rq->stop; + WARN_ON_ONCE(prev || rf); + if (!stop || !task_on_rq_queued(stop)) return NULL; - put_prev_task(rq, prev); - - stop->se.exec_start = rq_clock_task(rq); + set_next_task_stop(rq, stop); return stop; } @@ -55,7 +60,7 @@ static void yield_task_stop(struct rq *rq) BUG(); /* the stop task should never yield, its pointless. */ } -static void put_prev_task_stop(struct rq *rq, struct task_struct *prev) +static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *curr = rq->curr; u64 delta_exec; @@ -86,13 +91,6 @@ static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued) { } -static void set_curr_task_stop(struct rq *rq) -{ - struct task_struct *stop = rq->stop; - - stop->se.exec_start = rq_clock_task(rq); -} - static void switched_to_stop(struct rq *rq, struct task_struct *p) { BUG(); /* its impossible to change to this class */ @@ -128,13 +126,13 @@ const struct sched_class stop_sched_class = { .pick_next_task = pick_next_task_stop, .put_prev_task = put_prev_task_stop, + .set_next_task = set_next_task_stop, #ifdef CONFIG_SMP .select_task_rq = select_task_rq_stop, .set_cpus_allowed = set_cpus_allowed_common, #endif - .set_curr_task = set_curr_task_stop, .task_tick = task_tick_stop, .get_rr_interval = get_rr_interval_stop, diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index f53f89df837d..b5667a273bf6 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -1284,6 +1284,7 @@ static int sched_domains_curr_level; int sched_max_numa_distance; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; +int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE; #endif /* @@ -1344,11 +1345,6 @@ sd_init(struct sched_domain_topology_level *tl, .imbalance_pct = 125, .cache_nice_tries = 0, - .busy_idx = 0, - .idle_idx = 0, - .newidle_idx = 0, - .wake_idx = 0, - .forkexec_idx = 0, .flags = 1*SD_LOAD_BALANCE | 1*SD_BALANCE_NEWIDLE @@ -1400,17 +1396,14 @@ sd_init(struct sched_domain_topology_level *tl, } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { sd->imbalance_pct = 117; sd->cache_nice_tries = 1; - sd->busy_idx = 2; #ifdef CONFIG_NUMA } else if (sd->flags & SD_NUMA) { sd->cache_nice_tries = 2; - sd->busy_idx = 3; - sd->idle_idx = 2; sd->flags &= ~SD_PREFER_SIBLING; sd->flags |= SD_SERIALIZE; - if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + if (sched_domains_numa_distance[tl->numa_level] > node_reclaim_distance) { sd->flags &= ~(SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE); @@ -1419,8 +1412,6 @@ sd_init(struct sched_domain_topology_level *tl, #endif } else { sd->cache_nice_tries = 1; - sd->busy_idx = 2; - sd->idle_idx = 1; } /* @@ -1734,6 +1725,26 @@ void sched_domains_numa_masks_clear(unsigned int cpu) } } +/* + * sched_numa_find_closest() - given the NUMA topology, find the cpu + * closest to @cpu from @cpumask. + * cpumask: cpumask to find a cpu from + * cpu: cpu to be close to + * + * returns: cpu, or nr_cpu_ids when nothing found. + */ +int sched_numa_find_closest(const struct cpumask *cpus, int cpu) +{ + int i, j = cpu_to_node(cpu); + + for (i = 0; i < sched_domains_numa_levels; i++) { + cpu = cpumask_any_and(cpus, sched_domains_numa_masks[i][j]); + if (cpu < nr_cpu_ids) + return cpu; + } + return nr_cpu_ids; +} + #endif /* CONFIG_NUMA */ static int __sdt_alloc(const struct cpumask *cpu_map) @@ -1884,10 +1895,10 @@ static struct sched_domain_topology_level unsigned long cap; /* Is there any asymmetry? */ - cap = arch_scale_cpu_capacity(NULL, cpumask_first(cpu_map)); + cap = arch_scale_cpu_capacity(cpumask_first(cpu_map)); for_each_cpu(i, cpu_map) { - if (arch_scale_cpu_capacity(NULL, i) != cap) { + if (arch_scale_cpu_capacity(i) != cap) { asym = true; break; } @@ -1902,7 +1913,7 @@ static struct sched_domain_topology_level * to everyone. */ for_each_cpu(i, cpu_map) { - unsigned long max_capacity = arch_scale_cpu_capacity(NULL, i); + unsigned long max_capacity = arch_scale_cpu_capacity(i); int tl_id = 0; for_each_sd_topology(tl) { @@ -1912,7 +1923,7 @@ static struct sched_domain_topology_level for_each_cpu_and(j, tl->mask(i), cpu_map) { unsigned long capacity; - capacity = arch_scale_cpu_capacity(NULL, j); + capacity = arch_scale_cpu_capacity(j); if (capacity <= max_capacity) continue; @@ -2159,16 +2170,16 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * ndoms_new == 0 is a special case for destroying existing domains, * and it will not create the default domain. * - * Call with hotplug lock held + * Call with hotplug lock and sched_domains_mutex held */ -void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) +void partition_sched_domains_locked(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) { bool __maybe_unused has_eas = false; int i, j, n; int new_topology; - mutex_lock(&sched_domains_mutex); + lockdep_assert_held(&sched_domains_mutex); /* Always unregister in case we don't destroy any domains: */ unregister_sched_domain_sysctl(); @@ -2193,8 +2204,19 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { if (cpumask_equal(doms_cur[i], doms_new[j]) && - dattrs_equal(dattr_cur, i, dattr_new, j)) + dattrs_equal(dattr_cur, i, dattr_new, j)) { + struct root_domain *rd; + + /* + * This domain won't be destroyed and as such + * its dl_bw->total_bw needs to be cleared. It + * will be recomputed in function + * update_tasks_root_domain(). + */ + rd = cpu_rq(cpumask_any(doms_cur[i]))->rd; + dl_clear_root_domain(rd); goto match1; + } } /* No match - a current sched domain not in new doms_new[] */ detach_destroy_domains(doms_cur[i]); @@ -2251,6 +2273,15 @@ match3: ndoms_cur = ndoms_new; register_sched_domain_sysctl(); +} +/* + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + mutex_lock(&sched_domains_mutex); + partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); mutex_unlock(&sched_domains_mutex); } diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index fa0f9adfb752..c1e566a114ca 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -118,16 +118,12 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int bookmark.func = NULL; INIT_LIST_HEAD(&bookmark.entry); - spin_lock_irqsave(&wq_head->lock, flags); - nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key, &bookmark); - spin_unlock_irqrestore(&wq_head->lock, flags); - - while (bookmark.flags & WQ_FLAG_BOOKMARK) { + do { spin_lock_irqsave(&wq_head->lock, flags); nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key, &bookmark); spin_unlock_irqrestore(&wq_head->lock, flags); - } + } while (bookmark.flags & WQ_FLAG_BOOKMARK); } /** |