diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c index f5eced0842b3..6a88eb7e9f75 100644 --- a/drivers/powercap/dtpm_cpu.c +++ b/drivers/powercap/dtpm_cpu.c @@ -71,34 +71,19 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power) { - unsigned long max = 0, sum_util = 0; + unsigned long max, sum_util = 0; int cpu; - for_each_cpu_and(cpu, pd_mask, cpu_online_mask) { - - /* - * The capacity is the same for all CPUs belonging to - * the same perf domain, so a single call to - * arch_scale_cpu_capacity() is enough. However, we - * need the CPU parameter to be initialized by the - * loop, so the call ends up in this block. - * - * We can initialize 'max' with a cpumask_first() call - * before the loop but the bits computation is not - * worth given the arch_scale_cpu_capacity() just - * returns a value where the resulting assembly code - * will be optimized by the compiler. - */ - max = arch_scale_cpu_capacity(cpu); - sum_util += sched_cpu_util(cpu, max); - } - /* - * In the improbable case where all the CPUs of the perf - * domain are offline, 'max' will be zero and will lead to an - * illegal operation with a zero division. + * The capacity is the same for all CPUs belonging to + * the same perf domain. */ - return max ? (power * ((sum_util << 10) / max)) >> 10 : 0; + max = arch_scale_cpu_capacity(cpumask_first(pd_mask)); + + for_each_cpu_and(cpu, pd_mask, cpu_online_mask) + sum_util += sched_cpu_util(cpu); + + return (power * ((sum_util << 10) / max)) >> 10; } static u64 get_pd_power_uw(struct dtpm *dtpm) diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c index b8151d95a806..b263b0fde03c 100644 --- a/drivers/thermal/cpufreq_cooling.c +++ b/drivers/thermal/cpufreq_cooling.c @@ -137,11 +137,9 @@ static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev, static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu, int cpu_idx) { - unsigned long max = arch_scale_cpu_capacity(cpu); - unsigned long util; + unsigned long util = sched_cpu_util(cpu); - util = sched_cpu_util(cpu, max); - return (util * 100) / max; + return (util * 100) / arch_scale_cpu_capacity(cpu); } #else /* !CONFIG_SMP */ static u32 get_load(struct cpufreq_cooling_device *cpufreq_cdev, int cpu, diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index d4427d0a0e18..187b54a9567e 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -288,6 +288,10 @@ struct css_set { struct cgroup_base_stat { struct task_cputime cputime; + +#ifdef CONFIG_SCHED_CORE + u64 forceidle_sum; +#endif }; /* diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h index 69ae6b278464..ddb5a358fd82 100644 --- a/include/linux/kernel_stat.h +++ b/include/linux/kernel_stat.h @@ -28,6 +28,9 @@ enum cpu_usage_stat { CPUTIME_STEAL, CPUTIME_GUEST, CPUTIME_GUEST_NICE, +#ifdef CONFIG_SCHED_CORE + CPUTIME_FORCEIDLE, +#endif NR_STATS, }; @@ -115,4 +118,8 @@ extern void account_process_tick(struct task_struct *, int user); extern void account_idle_ticks(unsigned long ticks); +#ifdef CONFIG_SCHED_CORE +extern void __account_forceidle_time(struct task_struct *tsk, u64 delta); +#endif + #endif /* _LINUX_KERNEL_STAT_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index c46f3a63b758..88b8817b827d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2257,7 +2257,7 @@ static inline bool owner_on_cpu(struct task_struct *owner) } /* Returns effective CPU energy utilization, as seen by the scheduler */ -unsigned long sched_cpu_util(int cpu, unsigned long max); +unsigned long sched_cpu_util(int cpu); #endif /* CONFIG_SMP */ #ifdef CONFIG_RSEQ diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index e5af028c08b4..994c25640e15 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -39,20 +39,12 @@ static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p) } extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task); extern void rt_mutex_adjust_pi(struct task_struct *p); -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return tsk->pi_blocked_on != NULL; -} #else static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) { return NULL; } # define rt_mutex_adjust_pi(p) do { } while (0) -static inline bool tsk_is_pi_blocked(struct task_struct *tsk) -{ - return false; -} #endif extern void normalize_rt_tasks(void); diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 56cffe42abbc..816df6cc444e 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -81,6 +81,7 @@ struct sched_domain_shared { atomic_t ref; atomic_t nr_busy_cpus; int has_idle_cores; + int nr_idle_scan; }; struct sched_domain { diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index 24b5c2ab5598..feb59380c896 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -310,6 +310,9 @@ static void cgroup_base_stat_add(struct cgroup_base_stat *dst_bstat, dst_bstat->cputime.utime += src_bstat->cputime.utime; dst_bstat->cputime.stime += src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime += src_bstat->cputime.sum_exec_runtime; +#ifdef CONFIG_SCHED_CORE + dst_bstat->forceidle_sum += src_bstat->forceidle_sum; +#endif } static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, @@ -318,6 +321,9 @@ static void cgroup_base_stat_sub(struct cgroup_base_stat *dst_bstat, dst_bstat->cputime.utime -= src_bstat->cputime.utime; dst_bstat->cputime.stime -= src_bstat->cputime.stime; dst_bstat->cputime.sum_exec_runtime -= src_bstat->cputime.sum_exec_runtime; +#ifdef CONFIG_SCHED_CORE + dst_bstat->forceidle_sum -= src_bstat->forceidle_sum; +#endif } static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu) @@ -398,6 +404,11 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp, case CPUTIME_SOFTIRQ: rstatc->bstat.cputime.stime += delta_exec; break; +#ifdef CONFIG_SCHED_CORE + case CPUTIME_FORCEIDLE: + rstatc->bstat.forceidle_sum += delta_exec; + break; +#endif default: break; } @@ -411,8 +422,9 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp, * with how it is done by __cgroup_account_cputime_field for each bit of * cpu time attributed to a cgroup. */ -static void root_cgroup_cputime(struct task_cputime *cputime) +static void root_cgroup_cputime(struct cgroup_base_stat *bstat) { + struct task_cputime *cputime = &bstat->cputime; int i; cputime->stime = 0; @@ -438,6 +450,10 @@ static void root_cgroup_cputime(struct task_cputime *cputime) cputime->sum_exec_runtime += user; cputime->sum_exec_runtime += sys; cputime->sum_exec_runtime += cpustat[CPUTIME_STEAL]; + +#ifdef CONFIG_SCHED_CORE + bstat->forceidle_sum += cpustat[CPUTIME_FORCEIDLE]; +#endif } } @@ -445,27 +461,43 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; - struct task_cputime cputime; + struct cgroup_base_stat bstat; +#ifdef CONFIG_SCHED_CORE + u64 forceidle_time; +#endif if (cgroup_parent(cgrp)) { cgroup_rstat_flush_hold(cgrp); usage = cgrp->bstat.cputime.sum_exec_runtime; cputime_adjust(&cgrp->bstat.cputime, &cgrp->prev_cputime, &utime, &stime); +#ifdef CONFIG_SCHED_CORE + forceidle_time = cgrp->bstat.forceidle_sum; +#endif cgroup_rstat_flush_release(); } else { - root_cgroup_cputime(&cputime); - usage = cputime.sum_exec_runtime; - utime = cputime.utime; - stime = cputime.stime; + root_cgroup_cputime(&bstat); + usage = bstat.cputime.sum_exec_runtime; + utime = bstat.cputime.utime; + stime = bstat.cputime.stime; +#ifdef CONFIG_SCHED_CORE + forceidle_time = bstat.forceidle_sum; +#endif } do_div(usage, NSEC_PER_USEC); do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); +#ifdef CONFIG_SCHED_CORE + do_div(forceidle_time, NSEC_PER_USEC); +#endif seq_printf(seq, "usage_usec %llu\n" "user_usec %llu\n" "system_usec %llu\n", usage, utime, stime); + +#ifdef CONFIG_SCHED_CORE + seq_printf(seq, "core_sched.force_idle_usec %llu\n", forceidle_time); +#endif } diff --git a/kernel/rseq.c b/kernel/rseq.c index 97ac20b4f738..bda8175f8f99 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -18,8 +18,9 @@ #define CREATE_TRACE_POINTS #include -#define RSEQ_CS_PREEMPT_MIGRATE_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE | \ - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT) +#define RSEQ_CS_NO_RESTART_FLAGS (RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT | \ + RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL | \ + RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE) /* * @@ -175,23 +176,15 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags) u32 flags, event_mask; int ret; + if (WARN_ON_ONCE(cs_flags & RSEQ_CS_NO_RESTART_FLAGS) || cs_flags) + return -EINVAL; + /* Get thread flags. */ ret = get_user(flags, &t->rseq->flags); if (ret) return ret; - /* Take critical section flags into account. */ - flags |= cs_flags; - - /* - * Restart on signal can only be inhibited when restart on - * preempt and restart on migrate are inhibited too. Otherwise, - * a preempted signal handler could fail to restart the prior - * execution context on sigreturn. - */ - if (unlikely((flags & RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL) && - (flags & RSEQ_CS_PREEMPT_MIGRATE_FLAGS) != - RSEQ_CS_PREEMPT_MIGRATE_FLAGS)) + if (WARN_ON_ONCE(flags & RSEQ_CS_NO_RESTART_FLAGS) || flags) return -EINVAL; /* @@ -203,7 +196,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags) t->rseq_event_mask = 0; preempt_enable(); - return !!(event_mask & ~flags); + return !!event_mask; } static int clear_rseq_cs(struct task_struct *t) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index da0bf6fe9ecd..5555e49c4e12 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -873,15 +873,11 @@ static inline void hrtick_rq_init(struct rq *rq) ({ \ typeof(ptr) _ptr = (ptr); \ typeof(mask) _mask = (mask); \ - typeof(*_ptr) _old, _val = *_ptr; \ + typeof(*_ptr) _val = *_ptr; \ \ - for (;;) { \ - _old = cmpxchg(_ptr, _val, _val | _mask); \ - if (_old == _val) \ - break; \ - _val = _old; \ - } \ - _old; \ + do { \ + } while (!try_cmpxchg(_ptr, &_val, _val | _mask)); \ + _val; \ }) #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) @@ -890,7 +886,7 @@ static inline void hrtick_rq_init(struct rq *rq) * this avoids any races wrt polling state changes and thereby avoids * spurious IPIs. */ -static bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct task_struct *p) { struct thread_info *ti = task_thread_info(p); return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); @@ -905,30 +901,28 @@ static bool set_nr_and_not_polling(struct task_struct *p) static bool set_nr_if_polling(struct task_struct *p) { struct thread_info *ti = task_thread_info(p); - typeof(ti->flags) old, val = READ_ONCE(ti->flags); + typeof(ti->flags) val = READ_ONCE(ti->flags); for (;;) { if (!(val & _TIF_POLLING_NRFLAG)) return false; if (val & _TIF_NEED_RESCHED) return true; - old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); - if (old == val) + if (try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED)) break; - val = old; } return true; } #else -static bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct task_struct *p) { set_tsk_need_resched(p); return true; } #ifdef CONFIG_SMP -static bool set_nr_if_polling(struct task_struct *p) +static inline bool set_nr_if_polling(struct task_struct *p) { return false; } @@ -3808,7 +3802,7 @@ bool cpus_share_cache(int this_cpu, int that_cpu) return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } -static inline bool ttwu_queue_cond(int cpu, int wake_flags) +static inline bool ttwu_queue_cond(int cpu) { /* * Do not complicate things with the async wake_list while the CPU is @@ -3824,13 +3818,21 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags) if (!cpus_share_cache(smp_processor_id(), cpu)) return true; + if (cpu == smp_processor_id()) + return false; + /* - * If the task is descheduling and the only running task on the - * CPU then use the wakelist to offload the task activation to - * the soon-to-be-idle CPU as the current CPU is likely busy. - * nr_running is checked to avoid unnecessary task stacking. + * If the wakee cpu is idle, or the task is descheduling and the + * only running task on the CPU, then use the wakelist to offload + * the task activation to the idle (or soon-to-be-idle) CPU as + * the current CPU is likely busy. nr_running is checked to + * avoid unnecessary task stacking. + * + * Note that we can only get here with (wakee) p->on_rq=0, + * p->on_cpu can be whatever, we've done the dequeue, so + * the wakee has been accounted out of ->nr_running. */ - if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1) + if (!cpu_rq(cpu)->nr_running) return true; return false; @@ -3838,10 +3840,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags) static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags) { - if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu, wake_flags)) { - if (WARN_ON_ONCE(cpu == smp_processor_id())) - return false; - + if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(cpu)) { sched_clock_cpu(cpu); /* Sync clocks across CPUs */ __ttwu_queue_wakelist(p, cpu, wake_flags); return true; @@ -4163,7 +4162,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * scheduling. */ if (smp_load_acquire(&p->on_cpu) && - ttwu_queue_wakelist(p, task_cpu(p), wake_flags | WF_ON_CPU)) + ttwu_queue_wakelist(p, task_cpu(p), wake_flags)) goto unlock; /* @@ -4753,7 +4752,8 @@ static inline void prepare_task(struct task_struct *next) * Claim the task as running, we do this before switching to it * such that any running task will have this set. * - * See the ttwu() WF_ON_CPU case and its ordering comment. + * See the smp_load_acquire(&p->on_cpu) case in ttwu() and + * its ordering comment. */ WRITE_ONCE(next->on_cpu, 1); #endif @@ -6500,8 +6500,12 @@ static inline void sched_submit_work(struct task_struct *tsk) io_wq_worker_sleeping(tsk); } - if (tsk_is_pi_blocked(tsk)) - return; + /* + * spinlock and rwlock must not flush block requests. This will + * deadlock if the callback attempts to acquire a lock which is + * already acquired. + */ + SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT); /* * If we are going to sleep and we have plugged IO queued, @@ -6997,6 +7001,22 @@ out_unlock: } EXPORT_SYMBOL(set_user_nice); +/* + * is_nice_reduction - check if nice value is an actual reduction + * + * Similar to can_nice() but does not perform a capability check. + * + * @p: task + * @nice: nice value + */ +static bool is_nice_reduction(const struct task_struct *p, const int nice) +{ + /* Convert nice value [19,-20] to rlimit style value [1,40]: */ + int nice_rlim = nice_to_rlimit(nice); + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE)); +} + /* * can_nice - check if a task can reduce its nice value * @p: task @@ -7004,11 +7024,7 @@ EXPORT_SYMBOL(set_user_nice); */ int can_nice(const struct task_struct *p, const int nice) { - /* Convert nice value [19,-20] to rlimit style value [1,40]: */ - int nice_rlim = nice_to_rlimit(nice); - - return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || - capable(CAP_SYS_NICE)); + return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE); } #ifdef __ARCH_WANT_SYS_NICE @@ -7137,12 +7153,14 @@ struct task_struct *idle_task(int cpu) * required to meet deadlines. */ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, - unsigned long max, enum cpu_util_type type, + enum cpu_util_type type, struct task_struct *p) { - unsigned long dl_util, util, irq; + unsigned long dl_util, util, irq, max; struct rq *rq = cpu_rq(cpu); + max = arch_scale_cpu_capacity(cpu); + if (!uclamp_is_used() && type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) { return max; @@ -7222,10 +7240,9 @@ unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, return min(max, util); } -unsigned long sched_cpu_util(int cpu, unsigned long max) +unsigned long sched_cpu_util(int cpu) { - return effective_cpu_util(cpu, cpu_util_cfs(cpu), max, - ENERGY_UTIL, NULL); + return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL); } #endif /* CONFIG_SMP */ @@ -7287,6 +7304,69 @@ static bool check_same_owner(struct task_struct *p) return match; } +/* + * Allow unprivileged RT tasks to decrease priority. + * Only issue a capable test if needed and only once to avoid an audit + * event on permitted non-privileged operations: + */ +static int user_check_sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + int policy, int reset_on_fork) +{ + if (fair_policy(policy)) { + if (attr->sched_nice < task_nice(p) && + !is_nice_reduction(p, attr->sched_nice)) + goto req_priv; + } + + if (rt_policy(policy)) { + unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); + + /* Can't set/change the rt policy: */ + if (policy != p->policy && !rlim_rtprio) + goto req_priv; + + /* Can't increase priority: */ + if (attr->sched_priority > p->rt_priority && + attr->sched_priority > rlim_rtprio) + goto req_priv; + } + + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + goto req_priv; + + /* + * Treat SCHED_IDLE as nice 20. Only allow a switch to + * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. + */ + if (task_has_idle_policy(p) && !idle_policy(policy)) { + if (!is_nice_reduction(p, task_nice(p))) + goto req_priv; + } + + /* Can't change other user's priorities: */ + if (!check_same_owner(p)) + goto req_priv; + + /* Normal users shall not reset the sched_reset_on_fork flag: */ + if (p->sched_reset_on_fork && !reset_on_fork) + goto req_priv; + + return 0; + +req_priv: + if (!capable(CAP_SYS_NICE)) + return -EPERM; + + return 0; +} + static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) @@ -7328,58 +7408,11 @@ recheck: (rt_policy(policy) != (attr->sched_priority != 0))) return -EINVAL; - /* - * Allow unprivileged RT tasks to decrease priority: - */ - if (user && !capable(CAP_SYS_NICE)) { - if (fair_policy(policy)) { - if (attr->sched_nice < task_nice(p) && - !can_nice(p, attr->sched_nice)) - return -EPERM; - } - - if (rt_policy(policy)) { - unsigned long rlim_rtprio = - task_rlimit(p, RLIMIT_RTPRIO); - - /* Can't set/change the rt policy: */ - if (policy != p->policy && !rlim_rtprio) - return -EPERM; - - /* Can't increase priority: */ - if (attr->sched_priority > p->rt_priority && - attr->sched_priority > rlim_rtprio) - return -EPERM; - } - - /* - * Can't set/change SCHED_DEADLINE policy at all for now - * (safest behavior); in the future we would like to allow - * unprivileged DL tasks to increase their relative deadline - * or reduce their runtime (both ways reducing utilization) - */ - if (dl_policy(policy)) - return -EPERM; - - /* - * Treat SCHED_IDLE as nice 20. Only allow a switch to - * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. - */ - if (task_has_idle_policy(p) && !idle_policy(policy)) { - if (!can_nice(p, task_nice(p))) - return -EPERM; - } - - /* Can't change other user's priorities: */ - if (!check_same_owner(p)) - return -EPERM; - - /* Normal users shall not reset the sched_reset_on_fork flag: */ - if (p->sched_reset_on_fork && !reset_on_fork) - return -EPERM; - } - if (user) { + retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork); + if (retval) + return retval; + if (attr->sched_flags & SCHED_FLAG_SUGOV) return -EINVAL; @@ -9531,7 +9564,7 @@ static struct kmem_cache *task_group_cache __read_mostly; #endif DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); -DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); +DECLARE_PER_CPU(cpumask_var_t, select_rq_mask); void __init sched_init(void) { @@ -9580,7 +9613,7 @@ void __init sched_init(void) for_each_possible_cpu(i) { per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node( cpumask_size(), GFP_KERNEL, cpu_to_node(i)); - per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node( + per_cpu(select_rq_mask, i) = (cpumask_var_t)kzalloc_node( cpumask_size(), GFP_KERNEL, cpu_to_node(i)); } #endif /* CONFIG_CPUMASK_OFFSTACK */ diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 38a2cec21014..93878cb2a46d 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -56,7 +56,6 @@ static unsigned long sched_core_update_cookie(struct task_struct *p, unsigned long old_cookie; struct rq_flags rf; struct rq *rq; - bool enqueued; rq = task_rq_lock(p, &rf); @@ -68,14 +67,16 @@ static unsigned long sched_core_update_cookie(struct task_struct *p, */ SCHED_WARN_ON((p->core_cookie || cookie) && !sched_core_enabled(rq)); - enqueued = sched_core_enqueued(p); - if (enqueued) + if (sched_core_enqueued(p)) sched_core_dequeue(rq, p, DEQUEUE_SAVE); old_cookie = p->core_cookie; p->core_cookie = cookie; - if (enqueued) + /* + * Consider the cases: !prev_cookie and !cookie. + */ + if (cookie && task_on_rq_queued(p)) sched_core_enqueue(rq, p); /* @@ -277,7 +278,11 @@ void __sched_core_account_forceidle(struct rq *rq) if (p == rq_i->idle) continue; - __schedstat_add(p->stats.core_forceidle_sum, delta); + /* + * Note: this will account forceidle to the current cpu, even + * if it comes from our SMT sibling. + */ + __account_forceidle_time(p, delta); } } diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 3dbf351d12d5..1207c78f85c1 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -157,11 +157,10 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy, static void sugov_get_util(struct sugov_cpu *sg_cpu) { struct rq *rq = cpu_rq(sg_cpu->cpu); - unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu); - sg_cpu->max = max; + sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu); sg_cpu->bw_dl = cpu_bw_dl(rq); - sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), max, + sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu), FREQUENCY_UTIL, NULL); } diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 78a233d43757..95fc77853743 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -226,6 +226,21 @@ void account_idle_time(u64 cputime) cpustat[CPUTIME_IDLE] += cputime; } + +#ifdef CONFIG_SCHED_CORE +/* + * Account for forceidle time due to core scheduling. + * + * REQUIRES: schedstat is enabled. + */ +void __account_forceidle_time(struct task_struct *p, u64 delta) +{ + __schedstat_add(p->stats.core_forceidle_sum, delta); + + task_group_account_field(p, CPUTIME_FORCEIDLE, delta); +} +#endif + /* * When a guest is interrupted for a longer amount of time, missed clock * ticks are not redelivered later. Due to that, this function may on diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 7bf561262cb8..0ab79d819a0d 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -30,14 +30,16 @@ static struct ctl_table sched_dl_sysctls[] = { .data = &sysctl_sched_dl_period_max, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_douintvec_minmax, + .extra1 = (void *)&sysctl_sched_dl_period_min, }, { .procname = "sched_deadline_period_min_us", .data = &sysctl_sched_dl_period_min, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = proc_douintvec_minmax, + .extra2 = (void *)&sysctl_sched_dl_period_max, }, {} }; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 77b2048a9326..914096c5b1ae 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -612,11 +612,8 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) } /* ensure we never gain time by being placed backwards. */ - cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); -#ifndef CONFIG_64BIT - smp_wmb(); - cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; -#endif + u64_u32_store(cfs_rq->min_vruntime, + max_vruntime(cfs_rq->min_vruntime, vruntime)); } static inline bool __entity_less(struct rb_node *a, const struct rb_node *b) @@ -1055,6 +1052,33 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se) * Scheduling class queueing methods: */ +#ifdef CONFIG_NUMA +#define NUMA_IMBALANCE_MIN 2 + +static inline long +adjust_numa_imbalance(int imbalance, int dst_running, int imb_numa_nr) +{ + /* + * Allow a NUMA imbalance if busy CPUs is less than the maximum + * threshold. Above this threshold, individual tasks may be contending + * for both memory bandwidth and any shared HT resources. This is an + * approximation as the number of running tasks may not be related to + * the number of busy CPUs due to sched_setaffinity. + */ + if (dst_running > imb_numa_nr) + return imbalance; + + /* + * Allow a small imbalance based on a simple pair of communicating + * tasks that remain local when the destination is lightly loaded. + */ + if (imbalance <= NUMA_IMBALANCE_MIN) + return 0; + + return imbalance; +} +#endif /* CONFIG_NUMA */ + #ifdef CONFIG_NUMA_BALANCING /* * Approximate time to scan a full NUMA task in ms. The task scan period is @@ -1548,8 +1572,6 @@ struct task_numa_env { static unsigned long cpu_load(struct rq *rq); static unsigned long cpu_runnable(struct rq *rq); -static inline long adjust_numa_imbalance(int imbalance, - int dst_running, int imb_numa_nr); static inline enum numa_type numa_classify(unsigned int imbalance_pct, @@ -1790,6 +1812,15 @@ static bool task_numa_compare(struct task_numa_env *env, */ cur_ng = rcu_dereference(cur->numa_group); if (cur_ng == p_ng) { + /* + * Do not swap within a group or between tasks that have + * no group if there is spare capacity. Swapping does + * not address the load imbalance and helps one task at + * the cost of punishing another. + */ + if (env->dst_stats.node_type == node_has_spare) + goto unlock; + imp = taskimp + task_weight(cur, env->src_nid, dist) - task_weight(cur, env->dst_nid, dist); /* @@ -2885,6 +2916,7 @@ void init_numa_balancing(unsigned long clone_flags, struct task_struct *p) p->node_stamp = 0; p->numa_scan_seq = mm ? mm->numa_scan_seq : 0; p->numa_scan_period = sysctl_numa_balancing_scan_delay; + p->numa_migrate_retry = 0; /* Protect against double add, see task_tick_numa and task_numa_work */ p->numa_work.next = &p->numa_work; p->numa_faults = NULL; @@ -3144,6 +3176,8 @@ void reweight_task(struct task_struct *p, int prio) load->inv_weight = sched_prio_to_wmult[prio]; } +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); + #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_SMP /* @@ -3254,8 +3288,6 @@ static long calc_group_shares(struct cfs_rq *cfs_rq) } #endif /* CONFIG_SMP */ -static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); - /* * Recomputes the group entity based on the current state of its group * runqueue. @@ -3313,6 +3345,34 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) } #ifdef CONFIG_SMP +static inline bool load_avg_is_decayed(struct sched_avg *sa) +{ + if (sa->load_sum) + return false; + + if (sa->util_sum) + return false; + + if (sa->runnable_sum) + return false; + + /* + * _avg must be null when _sum are null because _avg = _sum / divider + * Make sure that rounding and/or propagation of PELT values never + * break this. + */ + SCHED_WARN_ON(sa->load_avg || + sa->util_avg || + sa->runnable_avg); + + return true; +} + +static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) +{ + return u64_u32_load_copy(cfs_rq->avg.last_update_time, + cfs_rq->last_update_time_copy); +} #ifdef CONFIG_FAIR_GROUP_SCHED /* * Because list_add_leaf_cfs_rq always places a child cfs_rq on the list @@ -3345,27 +3405,12 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq) if (cfs_rq->load.weight) return false; - if (cfs_rq->avg.load_sum) - return false; - - if (cfs_rq->avg.util_sum) - return false; - - if (cfs_rq->avg.runnable_sum) + if (!load_avg_is_decayed(&cfs_rq->avg)) return false; if (child_cfs_rq_on_list(cfs_rq)) return false; - /* - * _avg must be null when _sum are null because _avg = _sum / divider - * Make sure that rounding and/or propagation of PELT values never - * break this. - */ - SCHED_WARN_ON(cfs_rq->avg.load_avg || - cfs_rq->avg.util_avg || - cfs_rq->avg.runnable_avg); - return true; } @@ -3423,27 +3468,9 @@ void set_task_rq_fair(struct sched_entity *se, if (!(se->avg.last_update_time && prev)) return; -#ifndef CONFIG_64BIT - { - u64 p_last_update_time_copy; - u64 n_last_update_time_copy; + p_last_update_time = cfs_rq_last_update_time(prev); + n_last_update_time = cfs_rq_last_update_time(next); - do { - p_last_update_time_copy = prev->load_last_update_time_copy; - n_last_update_time_copy = next->load_last_update_time_copy; - - smp_rmb(); - - p_last_update_time = prev->avg.last_update_time; - n_last_update_time = next->avg.last_update_time; - - } while (p_last_update_time != p_last_update_time_copy || - n_last_update_time != n_last_update_time_copy); - } -#else - p_last_update_time = prev->avg.last_update_time; - n_last_update_time = next->avg.last_update_time; -#endif __update_load_avg_blocked_se(p_last_update_time, se); se->avg.last_update_time = n_last_update_time; } @@ -3722,6 +3749,89 @@ static inline void add_tg_cfs_propagate(struct cfs_rq *cfs_rq, long runnable_sum #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_NO_HZ_COMMON +static inline void migrate_se_pelt_lag(struct sched_entity *se) +{ + u64 throttled = 0, now, lut; + struct cfs_rq *cfs_rq; + struct rq *rq; + bool is_idle; + + if (load_avg_is_decayed(&se->avg)) + return; + + cfs_rq = cfs_rq_of(se); + rq = rq_of(cfs_rq); + + rcu_read_lock(); + is_idle = is_idle_task(rcu_dereference(rq->curr)); + rcu_read_unlock(); + + /* + * The lag estimation comes with a cost we don't want to pay all the + * time. Hence, limiting to the case where the source CPU is idle and + * we know we are at the greatest risk to have an outdated clock. + */ + if (!is_idle) + return; + + /* + * Estimated "now" is: last_update_time + cfs_idle_lag + rq_idle_lag, where: + * + * last_update_time (the cfs_rq's last_update_time) + * = cfs_rq_clock_pelt()@cfs_rq_idle + * = rq_clock_pelt()@cfs_rq_idle + * - cfs->throttled_clock_pelt_time@cfs_rq_idle + * + * cfs_idle_lag (delta between rq's update and cfs_rq's update) + * = rq_clock_pelt()@rq_idle - rq_clock_pelt()@cfs_rq_idle + * + * rq_idle_lag (delta between now and rq's update) + * = sched_clock_cpu() - rq_clock()@rq_idle + * + * We can then write: + * + * now = rq_clock_pelt()@rq_idle - cfs->throttled_clock_pelt_time + + * sched_clock_cpu() - rq_clock()@rq_idle + * Where: + * rq_clock_pelt()@rq_idle is rq->clock_pelt_idle + * rq_clock()@rq_idle is rq->clock_idle + * cfs->throttled_clock_pelt_time@cfs_rq_idle + * is cfs_rq->throttled_pelt_idle + */ + +#ifdef CONFIG_CFS_BANDWIDTH + throttled = u64_u32_load(cfs_rq->throttled_pelt_idle); + /* The clock has been stopped for throttling */ + if (throttled == U64_MAX) + return; +#endif + now = u64_u32_load(rq->clock_pelt_idle); + /* + * Paired with _update_idle_rq_clock_pelt(). It ensures at the worst case + * is observed the old clock_pelt_idle value and the new clock_idle, + * which lead to an underestimation. The opposite would lead to an + * overestimation. + */ + smp_rmb(); + lut = cfs_rq_last_update_time(cfs_rq); + + now -= throttled; + if (now < lut) + /* + * cfs_rq->avg.last_update_time is more recent than our + * estimation, let's use it. + */ + now = lut; + else + now += sched_clock_cpu(cpu_of(rq)) - u64_u32_load(rq->clock_idle); + + __update_load_avg_blocked_se(now, se); +} +#else +static void migrate_se_pelt_lag(struct sched_entity *se) {} +#endif + /** * update_cfs_rq_load_avg - update the cfs_rq's load/util averages * @now: current time, as per cfs_rq_clock_pelt() @@ -3796,12 +3906,9 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq) } decayed |= __update_load_avg_cfs_rq(now, cfs_rq); - -#ifndef CONFIG_64BIT - smp_wmb(); - cfs_rq->load_last_update_time_copy = sa->last_update_time; -#endif - + u64_u32_store_copy(sa->last_update_time, + cfs_rq->last_update_time_copy, + sa->last_update_time); return decayed; } @@ -3933,27 +4040,6 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s } } -#ifndef CONFIG_64BIT -static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) -{ - u64 last_update_time_copy; - u64 last_update_time; - - do { - last_update_time_copy = cfs_rq->load_last_update_time_copy; - smp_rmb(); - last_update_time = cfs_rq->avg.last_update_time; - } while (last_update_time != last_update_time_copy); - - return last_update_time; -} -#else -static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) -{ - return cfs_rq->avg.last_update_time; -} -#endif - /* * Synchronize entity load avg of dequeued entity without locking * the previous rq. @@ -4368,16 +4454,11 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) __enqueue_entity(cfs_rq, se); se->on_rq = 1; - /* - * When bandwidth control is enabled, cfs might have been removed - * because of a parent been throttled but cfs->nr_running > 1. Try to - * add it unconditionally. - */ - if (cfs_rq->nr_running == 1 || cfs_bandwidth_used()) - list_add_leaf_cfs_rq(cfs_rq); - - if (cfs_rq->nr_running == 1) + if (cfs_rq->nr_running == 1) { check_enqueue_throttle(cfs_rq); + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); + } } static void __clear_buddies_last(struct sched_entity *se) @@ -4477,6 +4558,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) */ if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE) update_min_vruntime(cfs_rq); + + if (cfs_rq->nr_running == 0) + update_idle_cfs_rq_clock_pelt(cfs_rq); } /* @@ -4992,11 +5076,18 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* update hierarchical throttle state */ walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq); - /* Nothing to run but something to decay (on_list)? Complete the branch */ if (!cfs_rq->load.weight) { - if (cfs_rq->on_list) - goto unthrottle_throttle; - return; + if (!cfs_rq->on_list) + return; + /* + * Nothing to run but something to decay (on_list)? + * Complete the branch. + */ + for_each_sched_entity(se) { + if (list_add_leaf_cfs_rq(cfs_rq_of(se))) + break; + } + goto unthrottle_throttle; } task_delta = cfs_rq->h_nr_running; @@ -5034,31 +5125,12 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(qcfs_rq)) goto unthrottle_throttle; - - /* - * One parent has been throttled and cfs_rq removed from the - * list. Add it back to not break the leaf list. - */ - if (throttled_hierarchy(qcfs_rq)) - list_add_leaf_cfs_rq(qcfs_rq); } /* At this point se is NULL and we are at root level*/ add_nr_running(rq, task_delta); unthrottle_throttle: - /* - * The cfs_rq_throttled() breaks in the above iteration can result in - * incomplete leaf list maintenance, resulting in triggering the - * assertion below. - */ - for_each_sched_entity(se) { - struct cfs_rq *qcfs_rq = cfs_rq_of(se); - - if (list_add_leaf_cfs_rq(qcfs_rq)) - break; - } - assert_list_leaf_cfs_rq(rq); /* Determine whether we need to wake up potentially idle CPU: */ @@ -5713,13 +5785,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) /* end evaluation on encountering a throttled cfs_rq */ if (cfs_rq_throttled(cfs_rq)) goto enqueue_throttle; - - /* - * One parent has been throttled and cfs_rq removed from the - * list. Add it back to not break the leaf list. - */ - if (throttled_hierarchy(cfs_rq)) - list_add_leaf_cfs_rq(cfs_rq); } /* At this point se is NULL and we are at root level*/ @@ -5743,21 +5808,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) update_overutilized_status(rq); enqueue_throttle: - if (cfs_bandwidth_used()) { - /* - * When bandwidth control is enabled; the cfs_rq_throttled() - * breaks in the above iteration can result in incomplete - * leaf list maintenance, resulting in triggering the assertion - * below. - */ - for_each_sched_entity(se) { - cfs_rq = cfs_rq_of(se); - - if (list_add_leaf_cfs_rq(cfs_rq)) - break; - } - } - assert_list_leaf_cfs_rq(rq); hrtick_update(rq); @@ -5844,7 +5894,7 @@ dequeue_throttle: /* Working cpumask for: load_balance, load_balance_newidle. */ DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); -DEFINE_PER_CPU(cpumask_var_t, select_idle_mask); +DEFINE_PER_CPU(cpumask_var_t, select_rq_mask); #ifdef CONFIG_NO_HZ_COMMON @@ -6334,8 +6384,9 @@ static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd */ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool has_idle_core, int target) { - struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask); + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); int i, cpu, idle_cpu = -1, nr = INT_MAX; + struct sched_domain_shared *sd_share; struct rq *this_rq = this_rq(); int this = smp_processor_id(); struct sched_domain *this_sd; @@ -6375,6 +6426,17 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool time = cpu_clock(this); } + if (sched_feat(SIS_UTIL)) { + sd_share = rcu_dereference(per_cpu(sd_llc_shared, target)); + if (sd_share) { + /* because !--nr is the condition to stop scan */ + nr = READ_ONCE(sd_share->nr_idle_scan) + 1; + /* overloaded LLC is unlikely to have idle cpu/core */ + if (nr == 1) + return -1; + } + } + for_each_cpu_wrap(cpu, cpus, target + 1) { if (has_idle_core) { i = select_idle_core(p, cpu, cpus, &idle_cpu); @@ -6420,7 +6482,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target) int cpu, best_cpu = -1; struct cpumask *cpus; - cpus = this_cpu_cpumask_var_ptr(select_idle_mask); + cpus = this_cpu_cpumask_var_ptr(select_rq_mask); cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); task_util = uclamp_task_util(p); @@ -6470,7 +6532,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) } /* - * per-cpu select_idle_mask usage + * per-cpu select_rq_mask usage */ lockdep_assert_irqs_disabled(); @@ -6640,62 +6702,96 @@ static unsigned long cpu_util_without(int cpu, struct task_struct *p) } /* - * 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 @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. + * energy_env - Utilization landscape for energy estimation. + * @task_busy_time: Utilization contribution by the task for which we test the + * placement. Given by eenv_task_busy_time(). + * @pd_busy_time: Utilization of the whole perf domain without the task + * contribution. Given by eenv_pd_busy_time(). + * @cpu_cap: Maximum CPU capacity for the perf domain. + * @pd_cap: Entire perf domain capacity. (pd->nr_cpus * cpu_cap). */ -static long -compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) +struct energy_env { + unsigned long task_busy_time; + unsigned long pd_busy_time; + unsigned long cpu_cap; + unsigned long pd_cap; +}; + +/* + * Compute the task busy time for compute_energy(). This time cannot be + * injected directly into effective_cpu_util() because of the IRQ scaling. + * The latter only makes sense with the most recent CPUs where the task has + * run. + */ +static inline void eenv_task_busy_time(struct energy_env *eenv, + struct task_struct *p, int prev_cpu) { - 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; - unsigned long _cpu_cap = cpu_cap; + unsigned long busy_time, max_cap = arch_scale_cpu_capacity(prev_cpu); + unsigned long irq = cpu_util_irq(cpu_rq(prev_cpu)); + + if (unlikely(irq >= max_cap)) + busy_time = max_cap; + else + busy_time = scale_irq_capacity(task_util_est(p), irq, max_cap); + + eenv->task_busy_time = busy_time; +} + +/* + * Compute the perf_domain (PD) busy time for compute_energy(). Based on the + * utilization for each @pd_cpus, it however doesn't take into account + * clamping since the ratio (utilization / cpu_capacity) is already enough to + * scale the EM reported power consumption at the (eventually clamped) + * cpu_capacity. + * + * The contribution of the task @p for which we want to estimate the + * energy cost is removed (by cpu_util_next()) and must be calculated + * separately (see eenv_task_busy_time). This ensures: + * + * - A stable PD utilization, no matter which CPU of that PD we want to place + * the task on. + * + * - A fair comparison between CPUs as the task contribution (task_util()) + * will always be the same no matter which CPU utilization we rely on + * (util_avg or util_est). + * + * Set @eenv busy time for the PD that spans @pd_cpus. This busy time can't + * exceed @eenv->pd_cap. + */ +static inline void eenv_pd_busy_time(struct energy_env *eenv, + struct cpumask *pd_cpus, + struct task_struct *p) +{ + unsigned long busy_time = 0; int cpu; - _cpu_cap -= arch_scale_thermal_pressure(cpumask_first(pd_mask)); + for_each_cpu(cpu, pd_cpus) { + unsigned long util = cpu_util_next(cpu, p, -1); - /* - * 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 util_freq = cpu_util_next(cpu, p, dst_cpu); - unsigned long cpu_util, util_running = util_freq; - struct task_struct *tsk = NULL; + busy_time += effective_cpu_util(cpu, util, ENERGY_UTIL, NULL); + } - /* - * When @p is placed on @cpu: - * - * util_running = max(cpu_util, cpu_util_est) + - * max(task_util, _task_util_est) - * - * while cpu_util_next is: max(cpu_util + task_util, - * cpu_util_est + _task_util_est) - */ - if (cpu == dst_cpu) { - tsk = p; - util_running = - cpu_util_next(cpu, p, -1) + task_util_est(p); - } + eenv->pd_busy_time = min(eenv->pd_cap, busy_time); +} - /* - * 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. - */ - cpu_util = effective_cpu_util(cpu, util_running, cpu_cap, - ENERGY_UTIL, NULL); +/* + * Compute the maximum utilization for compute_energy() when the task @p + * is placed on the cpu @dst_cpu. + * + * Returns the maximum utilization among @eenv->cpus. This utilization can't + * exceed @eenv->cpu_cap. + */ +static inline unsigned long +eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus, + struct task_struct *p, int dst_cpu) +{ + unsigned long max_util = 0; + int cpu; - sum_util += min(cpu_util, _cpu_cap); + for_each_cpu(cpu, pd_cpus) { + struct task_struct *tsk = (cpu == dst_cpu) ? p : NULL; + unsigned long util = cpu_util_next(cpu, p, dst_cpu); + unsigned long cpu_util; /* * Performance domain frequency: utilization clamping @@ -6704,12 +6800,29 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) * NOTE: in case RT tasks are running, by default the * FREQUENCY_UTIL's utilization can be max OPP. */ - cpu_util = effective_cpu_util(cpu, util_freq, cpu_cap, - FREQUENCY_UTIL, tsk); - max_util = max(max_util, min(cpu_util, _cpu_cap)); + cpu_util = effective_cpu_util(cpu, util, FREQUENCY_UTIL, tsk); + max_util = max(max_util, cpu_util); } - return em_cpu_energy(pd->em_pd, max_util, sum_util, _cpu_cap); + return min(max_util, eenv->cpu_cap); +} + +/* + * compute_energy(): Use the Energy Model to estimate the energy that @pd would + * consume for a given utilization landscape @eenv. When @dst_cpu < 0, the task + * contribution is ignored. + */ +static inline unsigned long +compute_energy(struct energy_env *eenv, struct perf_domain *pd, + struct cpumask *pd_cpus, struct task_struct *p, int dst_cpu) +{ + unsigned long max_util = eenv_pd_max_util(eenv, pd_cpus, p, dst_cpu); + unsigned long busy_time = eenv->pd_busy_time; + + if (dst_cpu >= 0) + busy_time = min(eenv->pd_cap, busy_time + eenv->task_busy_time); + + return em_cpu_energy(pd->em_pd, max_util, busy_time, eenv->cpu_cap); } /* @@ -6753,12 +6866,13 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd) */ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX; - struct root_domain *rd = cpu_rq(smp_processor_id())->rd; - int cpu, best_energy_cpu = prev_cpu, target = -1; - unsigned long cpu_cap, util, base_energy = 0; + struct root_domain *rd = this_rq()->rd; + int cpu, best_energy_cpu, target = -1; struct sched_domain *sd; struct perf_domain *pd; + struct energy_env eenv; rcu_read_lock(); pd = rcu_dereference(rd->pd); @@ -6781,20 +6895,39 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (!task_util_est(p)) goto unlock; - for (; pd; pd = pd->next) { - unsigned long cur_delta, spare_cap, max_spare_cap = 0; - bool compute_prev_delta = false; - unsigned long base_energy_pd; - int max_spare_cap_cpu = -1; + eenv_task_busy_time(&eenv, p, prev_cpu); + + for (; pd; pd = pd->next) { + unsigned long cpu_cap, cpu_thermal_cap, util; + unsigned long cur_delta, max_spare_cap = 0; + bool compute_prev_delta = false; + int max_spare_cap_cpu = -1; + unsigned long base_energy; + + cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask); + + if (cpumask_empty(cpus)) + continue; + + /* Account thermal pressure for the energy estimation */ + cpu = cpumask_first(cpus); + cpu_thermal_cap = arch_scale_cpu_capacity(cpu); + cpu_thermal_cap -= arch_scale_thermal_pressure(cpu); + + eenv.cpu_cap = cpu_thermal_cap; + eenv.pd_cap = 0; + + for_each_cpu(cpu, cpus) { + eenv.pd_cap += cpu_thermal_cap; + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; - for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) { if (!cpumask_test_cpu(cpu, p->cpus_ptr)) continue; util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); - spare_cap = cpu_cap; - lsub_positive(&spare_cap, util); /* * Skip CPUs that cannot satisfy the capacity request. @@ -6807,15 +6940,17 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (!fits_capacity(util, cpu_cap)) continue; + lsub_positive(&cpu_cap, util); + if (cpu == prev_cpu) { /* Always use prev_cpu as a candidate. */ compute_prev_delta = true; - } else if (spare_cap > max_spare_cap) { + } else if (cpu_cap > max_spare_cap) { /* * Find the CPU with the maximum spare capacity * in the performance domain. */ - max_spare_cap = spare_cap; + max_spare_cap = cpu_cap; max_spare_cap_cpu = cpu; } } @@ -6823,25 +6958,29 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) if (max_spare_cap_cpu < 0 && !compute_prev_delta) continue; + eenv_pd_busy_time(&eenv, cpus, p); /* Compute the 'base' energy of the pd, without @p */ - base_energy_pd = compute_energy(p, -1, pd); - base_energy += base_energy_pd; + base_energy = compute_energy(&eenv, pd, cpus, p, -1); /* Evaluate the energy impact of using prev_cpu. */ if (compute_prev_delta) { - prev_delta = compute_energy(p, prev_cpu, pd); - if (prev_delta < base_energy_pd) + prev_delta = compute_energy(&eenv, pd, cpus, p, + prev_cpu); + /* CPU utilization has changed */ + if (prev_delta < base_energy) goto unlock; - prev_delta -= base_energy_pd; + prev_delta -= base_energy; best_delta = min(best_delta, prev_delta); } /* Evaluate the energy impact of using max_spare_cap_cpu. */ if (max_spare_cap_cpu >= 0) { - cur_delta = compute_energy(p, max_spare_cap_cpu, pd); - if (cur_delta < base_energy_pd) + cur_delta = compute_energy(&eenv, pd, cpus, p, + max_spare_cap_cpu); + /* CPU utilization has changed */ + if (cur_delta < base_energy) goto unlock; - cur_delta -= base_energy_pd; + cur_delta -= base_energy; if (cur_delta < best_delta) { best_delta = cur_delta; best_energy_cpu = max_spare_cap_cpu; @@ -6850,12 +6989,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) } rcu_read_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_delta == ULONG_MAX) || - (prev_delta - best_delta) > ((prev_delta + base_energy) >> 4)) + if (best_delta < prev_delta) target = best_energy_cpu; return target; @@ -6951,6 +7085,8 @@ static void detach_entity_cfs_rq(struct sched_entity *se); */ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) { + struct sched_entity *se = &p->se; + /* * As blocked tasks retain absolute vruntime the migration needs to * deal with this by subtracting the old and adding the new @@ -6958,23 +7094,9 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) * the task on the new runqueue. */ if (READ_ONCE(p->__state) == TASK_WAKING) { - struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 min_vruntime; -#ifndef CONFIG_64BIT - u64 min_vruntime_copy; - - do { - min_vruntime_copy = cfs_rq->min_vruntime_copy; - smp_rmb(); - min_vruntime = cfs_rq->min_vruntime; - } while (min_vruntime != min_vruntime_copy); -#else - min_vruntime = cfs_rq->min_vruntime; -#endif - - se->vruntime -= min_vruntime; + se->vruntime -= u64_u32_load(cfs_rq->min_vruntime); } if (p->on_rq == TASK_ON_RQ_MIGRATING) { @@ -6983,25 +7105,29 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu) * rq->lock and can modify state directly. */ lockdep_assert_rq_held(task_rq(p)); - detach_entity_cfs_rq(&p->se); + detach_entity_cfs_rq(se); } else { + remove_entity_load_avg(se); + /* - * We are supposed to update the task to "current" time, then - * its up to date and ready to go to new CPU/cfs_rq. But we - * have difficulty in getting what current time is, so simply - * throw away the out-of-date time. This will result in the - * wakee task is less decayed, but giving the wakee more load - * sounds not bad. + * Here, the task's PELT values have been updated according to + * the current rq's clock. But if that clock hasn't been + * updated in a while, a substantial idle time will be missed, + * leading to an inflation after wake-up on the new rq. + * + * Estimate the missing time from the cfs_rq last_update_time + * and update sched_avg to improve the PELT continuity after + * migration. */ - remove_entity_load_avg(&p->se); + migrate_se_pelt_lag(se); } /* Tell new CPU we are migrated */ - p->se.avg.last_update_time = 0; + se->avg.last_update_time = 0; /* We have migrated, no longer consider this task hot */ - p->se.exec_start = 0; + se->exec_start = 0; update_scan_period(p, new_cpu); } @@ -7585,8 +7711,8 @@ enum group_type { */ group_fully_busy, /* - * SD_ASYM_CPUCAPACITY only: One task doesn't fit with CPU's capacity - * and must be migrated to a more powerful CPU. + * One task doesn't fit with CPU's capacity and must be migrated to a + * more powerful CPU. */ group_misfit_task, /* @@ -8167,6 +8293,9 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) { update_tg_load_avg(cfs_rq); + if (cfs_rq->nr_running == 0) + update_idle_cfs_rq_clock_pelt(cfs_rq); + if (cfs_rq == &rq->cfs) decayed = true; } @@ -8500,7 +8629,7 @@ static inline int sg_imbalanced(struct sched_group *group) /* * group_has_capacity returns true if the group has spare capacity that could * be used by some tasks. - * We consider that a group has spare capacity if the * number of task is + * We consider that a group has spare capacity if the number of task is * smaller than the number of CPUs or if the utilization is lower than the * available capacity for CFS tasks. * For the latter, we use a threshold to stabilize the state, to take into @@ -8669,6 +8798,19 @@ sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu); } +static inline bool +sched_reduced_capacity(struct rq *rq, struct sched_domain *sd) +{ + /* + * When there is more than 1 task, the group_overloaded case already + * takes care of cpu with reduced capacity + */ + if (rq->cfs.h_nr_running != 1) + return false; + + return check_cpu_capacity(rq, sd); +} + /** * update_sg_lb_stats - Update sched_group's statistics for load balancing. * @env: The load balancing environment. @@ -8691,8 +8833,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, for_each_cpu_and(i, sched_group_span(group), env->cpus) { struct rq *rq = cpu_rq(i); + unsigned long load = cpu_load(rq); - sgs->group_load += cpu_load(rq); + sgs->group_load += load; sgs->group_util += cpu_util_cfs(i); sgs->group_runnable += cpu_runnable(rq); sgs->sum_h_nr_running += rq->cfs.h_nr_running; @@ -8722,11 +8865,17 @@ static inline void update_sg_lb_stats(struct lb_env *env, if (local_group) continue; - /* Check for a misfit task on the cpu */ - if (env->sd->flags & SD_ASYM_CPUCAPACITY && - sgs->group_misfit_task_load < rq->misfit_task_load) { - sgs->group_misfit_task_load = rq->misfit_task_load; - *sg_status |= SG_OVERLOAD; + if (env->sd->flags & SD_ASYM_CPUCAPACITY) { + /* Check for a misfit task on the cpu */ + if (sgs->group_misfit_task_load < rq->misfit_task_load) { + sgs->group_misfit_task_load = rq->misfit_task_load; + *sg_status |= SG_OVERLOAD; + } + } else if ((env->idle != CPU_NOT_IDLE) && + sched_reduced_capacity(rq, env->sd)) { + /* Check for a task running on a CPU with reduced capacity */ + if (sgs->group_misfit_task_load < load) + sgs->group_misfit_task_load = load; } } @@ -8779,7 +8928,8 @@ static bool update_sd_pick_busiest(struct lb_env *env, * CPUs in the group should either be possible to resolve * internally or be covered by avg_load imbalance (eventually). */ - if (sgs->group_type == group_misfit_task && + if ((env->sd->flags & SD_ASYM_CPUCAPACITY) && + (sgs->group_type == group_misfit_task) && (!capacity_greater(capacity_of(env->dst_cpu), sg->sgc->max_capacity) || sds->local_stat.group_type != group_has_spare)) return false; @@ -9057,16 +9207,6 @@ static bool update_pick_idlest(struct sched_group *idlest, return true; } -/* - * Allow a NUMA imbalance if busy CPUs is less than 25% of the domain. - * This is an approximation as the number of running tasks may not be - * related to the number of busy CPUs due to sched_setaffinity. - */ -static inline bool allow_numa_imbalance(int running, int imb_numa_nr) -{ - return running <= imb_numa_nr; -} - /* * find_idlest_group() finds and returns the least busy CPU group within the * domain. @@ -9183,7 +9323,9 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) break; case group_has_spare: +#ifdef CONFIG_NUMA if (sd->flags & SD_NUMA) { + int imb_numa_nr = sd->imb_numa_nr; #ifdef CONFIG_NUMA_BALANCING int idlest_cpu; /* @@ -9196,17 +9338,31 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) idlest_cpu = cpumask_first(sched_group_span(idlest)); if (cpu_to_node(idlest_cpu) == p->numa_preferred_nid) return idlest; -#endif +#endif /* CONFIG_NUMA_BALANCING */ /* * Otherwise, keep the task close to the wakeup source * and improve locality if the number of running tasks * would remain below threshold where an imbalance is - * allowed. If there is a real need of migration, - * periodic load balance will take care of it. + * allowed while accounting for the possibility the + * task is pinned to a subset of CPUs. If there is a + * real need of migration, periodic load balance will + * take care of it. */ - if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, sd->imb_numa_nr)) + if (p->nr_cpus_allowed != NR_CPUS) { + struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask); + + cpumask_and(cpus, sched_group_span(local), p->cpus_ptr); + imb_numa_nr = min(cpumask_weight(cpus), sd->imb_numa_nr); + } + + imbalance = abs(local_sgs.idle_cpus - idlest_sgs.idle_cpus); + if (!adjust_numa_imbalance(imbalance, + local_sgs.sum_nr_running + 1, + imb_numa_nr)) { return NULL; + } } +#endif /* CONFIG_NUMA */ /* * Select group with highest number of idle CPUs. We could also @@ -9222,6 +9378,77 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) return idlest; } +static void update_idle_cpu_scan(struct lb_env *env, + unsigned long sum_util) +{ + struct sched_domain_shared *sd_share; + int llc_weight, pct; + u64 x, y, tmp; + /* + * Update the number of CPUs to scan in LLC domain, which could + * be used as a hint in select_idle_cpu(). The update of sd_share + * could be expensive because it is within a shared cache line. + * So the write of this hint only occurs during periodic load + * balancing, rather than CPU_NEWLY_IDLE, because the latter + * can fire way more frequently than the former. + */ + if (!sched_feat(SIS_UTIL) || env->idle == CPU_NEWLY_IDLE) + return; + + llc_weight = per_cpu(sd_llc_size, env->dst_cpu); + if (env->sd->span_weight != llc_weight) + return; + + sd_share = rcu_dereference(per_cpu(sd_llc_shared, env->dst_cpu)); + if (!sd_share) + return; + + /* + * The number of CPUs to search drops as sum_util increases, when + * sum_util hits 85% or above, the scan stops. + * The reason to choose 85% as the threshold is because this is the + * imbalance_pct(117) when a LLC sched group is overloaded. + * + * let y = SCHED_CAPACITY_SCALE - p * x^2 [1] + * and y'= y / SCHED_CAPACITY_SCALE + * + * x is the ratio of sum_util compared to the CPU capacity: + * x = sum_util / (llc_weight * SCHED_CAPACITY_SCALE) + * y' is the ratio of CPUs to be scanned in the LLC domain, + * and the number of CPUs to scan is calculated by: + * + * nr_scan = llc_weight * y' [2] + * + * When x hits the threshold of overloaded, AKA, when + * x = 100 / pct, y drops to 0. According to [1], + * p should be SCHED_CAPACITY_SCALE * pct^2 / 10000 + * + * Scale x by SCHED_CAPACITY_SCALE: + * x' = sum_util / llc_weight; [3] + * + * and finally [1] becomes: + * y = SCHED_CAPACITY_SCALE - + * x'^2 * pct^2 / (10000 * SCHED_CAPACITY_SCALE) [4] + * + */ + /* equation [3] */ + x = sum_util; + do_div(x, llc_weight); + + /* equation [4] */ + pct = env->sd->imbalance_pct; + tmp = x * x * pct * pct; + do_div(tmp, 10000 * SCHED_CAPACITY_SCALE); + tmp = min_t(long, tmp, SCHED_CAPACITY_SCALE); + y = SCHED_CAPACITY_SCALE - tmp; + + /* equation [2] */ + y *= llc_weight; + do_div(y, SCHED_CAPACITY_SCALE); + if ((int)y != sd_share->nr_idle_scan) + WRITE_ONCE(sd_share->nr_idle_scan, (int)y); +} + /** * update_sd_lb_stats - Update sched_domain's statistics for load balancing. * @env: The load balancing environment. @@ -9234,6 +9461,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd struct sched_group *sg = env->sd->groups; struct sg_lb_stats *local = &sds->local_stat; struct sg_lb_stats tmp_sgs; + unsigned long sum_util = 0; int sg_status = 0; do { @@ -9266,6 +9494,7 @@ next_group: sds->total_load += sgs->group_load; sds->total_capacity += sgs->group_capacity; + sum_util += sgs->group_util; sg = sg->next; } while (sg != env->sd->groups); @@ -9291,24 +9520,8 @@ next_group: WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED); trace_sched_overutilized_tp(rd, SG_OVERUTILIZED); } -} -#define NUMA_IMBALANCE_MIN 2 - -static inline long adjust_numa_imbalance(int imbalance, - int dst_running, int imb_numa_nr) -{ - if (!allow_numa_imbalance(dst_running, imb_numa_nr)) - return imbalance; - - /* - * Allow a small imbalance based on a simple pair of communicating - * tasks that remain local when the destination is lightly loaded. - */ - if (imbalance <= NUMA_IMBALANCE_MIN) - return 0; - - return imbalance; + update_idle_cpu_scan(env, sum_util); } /** @@ -9325,9 +9538,18 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s busiest = &sds->busiest_stat; if (busiest->group_type == group_misfit_task) { - /* Set imbalance to allow misfit tasks to be balanced. */ - env->migration_type = migrate_misfit; - env->imbalance = 1; + if (env->sd->flags & SD_ASYM_CPUCAPACITY) { + /* Set imbalance to allow misfit tasks to be balanced. */ + env->migration_type = migrate_misfit; + env->imbalance = 1; + } else { + /* + * Set load imbalance to allow moving task from cpu + * with reduced capacity. + */ + env->migration_type = migrate_load; + env->imbalance = busiest->group_misfit_task_load; + } return; } @@ -9395,7 +9617,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ env->migration_type = migrate_task; lsub_positive(&nr_diff, local->sum_nr_running); - env->imbalance = nr_diff >> 1; + env->imbalance = nr_diff; } else { /* @@ -9403,15 +9625,21 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * idle cpus. */ env->migration_type = migrate_task; - env->imbalance = max_t(long, 0, (local->idle_cpus - - busiest->idle_cpus) >> 1); + env->imbalance = max_t(long, 0, + (local->idle_cpus - busiest->idle_cpus)); } +#ifdef CONFIG_NUMA /* Consider allowing a small imbalance between NUMA groups */ if (env->sd->flags & SD_NUMA) { env->imbalance = adjust_numa_imbalance(env->imbalance, - local->sum_nr_running + 1, env->sd->imb_numa_nr); + local->sum_nr_running + 1, + env->sd->imb_numa_nr); } +#endif + + /* Number of tasks to move to restore balance */ + env->imbalance >>= 1; return; } @@ -9834,9 +10062,15 @@ static int should_we_balance(struct lb_env *env) /* * In the newly idle case, we will allow all the CPUs * to do the newly idle load balance. + * + * However, we bail out if we already have tasks or a wakeup pending, + * to optimize wakeup latency. */ - if (env->idle == CPU_NEWLY_IDLE) + if (env->idle == CPU_NEWLY_IDLE) { + if (env->dst_rq->nr_running > 0 || env->dst_rq->ttwu_pending) + return 0; return 1; + } /* Try to find first idle CPU */ for_each_cpu_and(cpu, group_balance_mask(sg), env->cpus) { @@ -11287,9 +11521,13 @@ static inline bool vruntime_normalized(struct task_struct *p) */ static void propagate_entity_cfs_rq(struct sched_entity *se) { - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq = cfs_rq_of(se); - list_add_leaf_cfs_rq(cfs_rq_of(se)); + if (cfs_rq_throttled(cfs_rq)) + return; + + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); /* Start to propagate at parent */ se = se->parent; @@ -11297,14 +11535,13 @@ static void propagate_entity_cfs_rq(struct sched_entity *se) for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - if (!cfs_rq_throttled(cfs_rq)){ - update_load_avg(cfs_rq, se, UPDATE_TG); - list_add_leaf_cfs_rq(cfs_rq); - continue; - } + update_load_avg(cfs_rq, se, UPDATE_TG); - if (list_add_leaf_cfs_rq(cfs_rq)) + if (cfs_rq_throttled(cfs_rq)) break; + + if (!throttled_hierarchy(cfs_rq)) + list_add_leaf_cfs_rq(cfs_rq); } } #else @@ -11422,10 +11659,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first) void init_cfs_rq(struct cfs_rq *cfs_rq) { cfs_rq->tasks_timeline = RB_ROOT_CACHED; - cfs_rq->min_vruntime = (u64)(-(1LL << 20)); -#ifndef CONFIG_64BIT - cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; -#endif + u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20))); #ifdef CONFIG_SMP raw_spin_lock_init(&cfs_rq->removed.lock); #endif diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 1cf435bbcd9c..ee7f23c76bd3 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -60,7 +60,8 @@ SCHED_FEAT(TTWU_QUEUE, true) /* * When doing wakeups, attempt to limit superfluous scans of the LLC domain. */ -SCHED_FEAT(SIS_PROP, true) +SCHED_FEAT(SIS_PROP, false) +SCHED_FEAT(SIS_UTIL, true) /* * Issue a WARN when we do multiple update_rq_clock() calls diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h index 4ff2ed4f8fa1..3a0e0dc28721 100644 --- a/kernel/sched/pelt.h +++ b/kernel/sched/pelt.h @@ -61,6 +61,25 @@ static inline void cfs_se_util_change(struct sched_avg *avg) WRITE_ONCE(avg->util_est.enqueued, enqueued); } +static inline u64 rq_clock_pelt(struct rq *rq) +{ + lockdep_assert_rq_held(rq); + assert_clock_updated(rq); + + return rq->clock_pelt - rq->lost_idle_time; +} + +/* The rq is idle, we can sync to clock_task */ +static inline void _update_idle_rq_clock_pelt(struct rq *rq) +{ + rq->clock_pelt = rq_clock_task(rq); + + u64_u32_store(rq->clock_idle, rq_clock(rq)); + /* Paired with smp_rmb in migrate_se_pelt_lag() */ + smp_wmb(); + u64_u32_store(rq->clock_pelt_idle, rq_clock_pelt(rq)); +} + /* * The clock_pelt scales the time to reflect the effective amount of * computation done during the running delta time but then sync back to @@ -76,8 +95,7 @@ static inline void cfs_se_util_change(struct sched_avg *avg) static inline void update_rq_clock_pelt(struct rq *rq, s64 delta) { if (unlikely(is_idle_task(rq->curr))) { - /* The rq is idle, we can sync to clock_task */ - rq->clock_pelt = rq_clock_task(rq); + _update_idle_rq_clock_pelt(rq); return; } @@ -130,17 +148,23 @@ static inline void update_idle_rq_clock_pelt(struct rq *rq) */ if (util_sum >= divider) rq->lost_idle_time += rq_clock_task(rq) - rq->clock_pelt; -} -static inline u64 rq_clock_pelt(struct rq *rq) -{ - lockdep_assert_rq_held(rq); - assert_clock_updated(rq); - - return rq->clock_pelt - rq->lost_idle_time; + _update_idle_rq_clock_pelt(rq); } #ifdef CONFIG_CFS_BANDWIDTH +static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) +{ + u64 throttled; + + if (unlikely(cfs_rq->throttle_count)) + throttled = U64_MAX; + else + throttled = cfs_rq->throttled_clock_pelt_time; + + u64_u32_store(cfs_rq->throttled_pelt_idle, throttled); +} + /* rq->task_clock normalized against any time this cfs_rq has spent throttled */ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { @@ -150,6 +174,7 @@ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) return rq_clock_pelt(rq_of(cfs_rq)) - cfs_rq->throttled_clock_pelt_time; } #else +static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { } static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { return rq_clock_pelt(rq_of(cfs_rq)); @@ -204,6 +229,7 @@ update_rq_clock_pelt(struct rq *rq, s64 delta) { } static inline void update_idle_rq_clock_pelt(struct rq *rq) { } +static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { } #endif diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 8c9ed9664840..55f39c8f4203 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -480,7 +480,7 @@ static inline void rt_queue_push_tasks(struct rq *rq) #endif /* CONFIG_SMP */ static void enqueue_top_rt_rq(struct rt_rq *rt_rq); -static void dequeue_top_rt_rq(struct rt_rq *rt_rq); +static void dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count); static inline int on_rt_rq(struct sched_rt_entity *rt_se) { @@ -601,7 +601,7 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; if (!rt_se) { - dequeue_top_rt_rq(rt_rq); + dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running); /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ cpufreq_update_util(rq_of_rt_rq(rt_rq), 0); } @@ -687,7 +687,7 @@ static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { - dequeue_top_rt_rq(rt_rq); + dequeue_top_rt_rq(rt_rq, rt_rq->rt_nr_running); } static inline int rt_rq_throttled(struct rt_rq *rt_rq) @@ -1089,7 +1089,7 @@ static void update_curr_rt(struct rq *rq) } static void -dequeue_top_rt_rq(struct rt_rq *rt_rq) +dequeue_top_rt_rq(struct rt_rq *rt_rq, unsigned int count) { struct rq *rq = rq_of_rt_rq(rt_rq); @@ -1100,7 +1100,7 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq) BUG_ON(!rq->nr_running); - sub_nr_running(rq, rt_rq->rt_nr_running); + sub_nr_running(rq, count); rt_rq->rt_queued = 0; } @@ -1486,18 +1486,21 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flag static void dequeue_rt_stack(struct sched_rt_entity *rt_se, unsigned int flags) { struct sched_rt_entity *back = NULL; + unsigned int rt_nr_running; for_each_sched_rt_entity(rt_se) { rt_se->back = back; back = rt_se; } - dequeue_top_rt_rq(rt_rq_of_se(back)); + rt_nr_running = rt_rq_of_se(back)->rt_nr_running; for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) __dequeue_rt_entity(rt_se, flags); } + + dequeue_top_rt_rq(rt_rq_of_se(back), rt_nr_running); } static void enqueue_rt_entity(struct sched_rt_entity *rt_se, unsigned int flags) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 47b89a0fc6e5..aad7f5ee9666 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -520,6 +520,45 @@ struct cfs_bandwidth { }; #endif /* CONFIG_CGROUP_SCHED */ +/* + * u64_u32_load/u64_u32_store + * + * Use a copy of a u64 value to protect against data race. This is only + * applicable for 32-bits architectures. + */ +#ifdef CONFIG_64BIT +# define u64_u32_load_copy(var, copy) var +# define u64_u32_store_copy(var, copy, val) (var = val) +#else +# define u64_u32_load_copy(var, copy) \ +({ \ + u64 __val, __val_copy; \ + do { \ + __val_copy = copy; \ + /* \ + * paired with u64_u32_store_copy(), ordering access \ + * to var and copy. \ + */ \ + smp_rmb(); \ + __val = var; \ + } while (__val != __val_copy); \ + __val; \ +}) +# define u64_u32_store_copy(var, copy, val) \ +do { \ + typeof(val) __val = (val); \ + var = __val; \ + /* \ + * paired with u64_u32_load_copy(), ordering access to var and \ + * copy. \ + */ \ + smp_wmb(); \ + copy = __val; \ +} while (0) +#endif +# define u64_u32_load(var) u64_u32_load_copy(var, var##_copy) +# define u64_u32_store(var, val) u64_u32_store_copy(var, var##_copy, val) + /* CFS-related fields in a runqueue */ struct cfs_rq { struct load_weight load; @@ -560,7 +599,7 @@ struct cfs_rq { */ struct sched_avg avg; #ifndef CONFIG_64BIT - u64 load_last_update_time_copy; + u64 last_update_time_copy; #endif struct { raw_spinlock_t lock ____cacheline_aligned; @@ -609,6 +648,10 @@ struct cfs_rq { int runtime_enabled; s64 runtime_remaining; + u64 throttled_pelt_idle; +#ifndef CONFIG_64BIT + u64 throttled_pelt_idle_copy; +#endif u64 throttled_clock; u64 throttled_clock_pelt; u64 throttled_clock_pelt_time; @@ -981,6 +1024,12 @@ struct rq { u64 clock_task ____cacheline_aligned; u64 clock_pelt; unsigned long lost_idle_time; + u64 clock_pelt_idle; + u64 clock_idle; +#ifndef CONFIG_64BIT + u64 clock_pelt_idle_copy; + u64 clock_idle_copy; +#endif atomic_t nr_iowait; @@ -1815,15 +1864,6 @@ static inline struct cpumask *group_balance_mask(struct sched_group *sg) return to_cpumask(sg->sgc->cpumask); } -/** - * group_first_cpu - Returns the first CPU in the cpumask of a sched_group. - * @group: The group whose first CPU is to be returned. - */ -static inline unsigned int group_first_cpu(struct sched_group *group) -{ - return cpumask_first(sched_group_span(group)); -} - extern int group_balance_cpu(struct sched_group *sg); #ifdef CONFIG_SCHED_DEBUG @@ -2044,7 +2084,6 @@ static inline int task_on_rq_migrating(struct task_struct *p) #define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */ #define WF_MIGRATED 0x20 /* Internal use, task got migrated */ -#define WF_ON_CPU 0x40 /* Wakee is on_cpu */ #ifdef CONFIG_SMP static_assert(WF_EXEC == SD_BALANCE_EXEC); @@ -2852,7 +2891,7 @@ enum cpu_util_type { }; unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, - unsigned long max, enum cpu_util_type type, + enum cpu_util_type type, struct task_struct *p); static inline unsigned long cpu_bw_dl(struct rq *rq) diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 05b6c2ad90b9..8739c2a5a54e 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2316,23 +2316,30 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att /* * For a single LLC per node, allow an - * imbalance up to 25% of the node. This is an - * arbitrary cutoff based on SMT-2 to balance - * between memory bandwidth and avoiding - * premature sharing of HT resources and SMT-4 - * or SMT-8 *may* benefit from a different - * cutoff. + * imbalance up to 12.5% of the node. This is + * arbitrary cutoff based two factors -- SMT and + * memory channels. For SMT-2, the intent is to + * avoid premature sharing of HT resources but + * SMT-4 or SMT-8 *may* benefit from a different + * cutoff. For memory channels, this is a very + * rough estimate of how many channels may be + * active and is based on recent CPUs with + * many cores. * * For multiple LLCs, allow an imbalance * until multiple tasks would share an LLC * on one node while LLCs on another node - * remain idle. + * remain idle. This assumes that there are + * enough logical CPUs per LLC to avoid SMT + * factors and that there is a correlation + * between LLCs and memory channels. */ nr_llcs = sd->span_weight / child->span_weight; if (nr_llcs == 1) - imb = sd->span_weight >> 2; + imb = sd->span_weight >> 3; else imb = nr_llcs; + imb = max(1U, imb); sd->imb_numa_nr = imb; /* Set span based on the first NUMA domain. */ diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h index b86642f90d7f..3a391c9bf468 100644 --- a/tools/testing/selftests/rseq/rseq-riscv.h +++ b/tools/testing/selftests/rseq/rseq-riscv.h @@ -86,7 +86,7 @@ do { \ #define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs) \ RSEQ_INJECT_ASM(1) \ - "la "RSEQ_ASM_TMP_REG_1 ", " __rseq_str(cs_label) "\n" \ + "la " RSEQ_ASM_TMP_REG_1 ", " __rseq_str(cs_label) "\n" \ REG_S RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(rseq_cs) "]\n" \ __rseq_str(label) ":\n" @@ -103,17 +103,17 @@ do { \ #define RSEQ_ASM_OP_CMPEQ(var, expect, label) \ REG_L RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ - "bne "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ + "bne " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ __rseq_str(label) "\n" #define RSEQ_ASM_OP_CMPEQ32(var, expect, label) \ - "lw "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ - "bne "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ + "lw " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ + "bne " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ __rseq_str(label) "\n" #define RSEQ_ASM_OP_CMPNE(var, expect, label) \ REG_L RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" \ - "beq "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ + "beq " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(expect) "] ," \ __rseq_str(label) "\n" #define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label) \ @@ -127,12 +127,12 @@ do { \ REG_S RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(var) "]\n" #define RSEQ_ASM_OP_R_LOAD_OFF(offset) \ - "add "RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(offset) "], " \ + "add " RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(offset) "], " \ RSEQ_ASM_TMP_REG_1 "\n" \ REG_L RSEQ_ASM_TMP_REG_1 ", (" RSEQ_ASM_TMP_REG_1 ")\n" #define RSEQ_ASM_OP_R_ADD(count) \ - "add "RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 \ + "add " RSEQ_ASM_TMP_REG_1 ", " RSEQ_ASM_TMP_REG_1 \ ", %[" __rseq_str(count) "]\n" #define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label) \ @@ -194,8 +194,8 @@ int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [newv] "r" (newv) @@ -251,8 +251,8 @@ int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expectnot] "r" (expectnot), [load] "m" (*load), @@ -301,8 +301,8 @@ int rseq_addv(intptr_t *v, intptr_t count, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [count] "r" (count) RSEQ_INJECT_INPUT @@ -352,8 +352,8 @@ int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "m" (*v), [newv] "r" (newv), @@ -411,8 +411,8 @@ int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "m" (*v), [newv] "r" (newv), @@ -472,8 +472,8 @@ int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [v] "m" (*v), [expect] "r" (expect), [v2] "m" (*v2), @@ -532,8 +532,8 @@ int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "m" (*v), [newv] "r" (newv), @@ -593,8 +593,8 @@ int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect, RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [expect] "r" (expect), [v] "m" (*v), [newv] "r" (newv), @@ -651,8 +651,8 @@ int rseq_offset_deref_addv(intptr_t *ptr, off_t off, intptr_t inc, int cpu) RSEQ_ASM_DEFINE_ABORT(4, abort) : /* gcc asm goto does not allow outputs */ : [cpu_id] "r" (cpu), - [current_cpu_id] "m" (__rseq_abi.cpu_id), - [rseq_cs] "m" (__rseq_abi.rseq_cs), + [current_cpu_id] "m" (rseq_get_abi()->cpu_id), + [rseq_cs] "m" (rseq_get_abi()->rseq_cs.arch.ptr), [ptr] "r" (ptr), [off] "er" (off), [inc] "er" (inc) diff --git a/tools/testing/selftests/rseq/rseq.c b/tools/testing/selftests/rseq/rseq.c index 986b9458efb2..4177f9507bbe 100644 --- a/tools/testing/selftests/rseq/rseq.c +++ b/tools/testing/selftests/rseq/rseq.c @@ -111,7 +111,8 @@ void rseq_init(void) libc_rseq_offset_p = dlsym(RTLD_NEXT, "__rseq_offset"); libc_rseq_size_p = dlsym(RTLD_NEXT, "__rseq_size"); libc_rseq_flags_p = dlsym(RTLD_NEXT, "__rseq_flags"); - if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p) { + if (libc_rseq_size_p && libc_rseq_offset_p && libc_rseq_flags_p && + *libc_rseq_size_p != 0) { /* rseq registration owned by glibc */ rseq_offset = *libc_rseq_offset_p; rseq_size = *libc_rseq_size_p;