diff options
Diffstat (limited to 'kernel/sched/core.c')
| -rw-r--r-- | kernel/sched/core.c | 6153 |
1 files changed, 2809 insertions, 3344 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e838feb6adc5..41ba0be16911 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2,10 +2,13 @@ /* * kernel/sched/core.c * - * Core kernel scheduler code and related syscalls + * Core kernel CPU scheduler code * * Copyright (C) 1991-2002 Linus Torvalds + * Copyright (C) 1998-2024 Ingo Molnar, Red Hat */ +#define INSTANTIATE_EXPORTED_MIGRATE_DISABLE +#include <linux/sched.h> #include <linux/highmem.h> #include <linux/hrtimer_api.h> #include <linux/ktime_api.h> @@ -57,6 +60,7 @@ #include <linux/profile.h> #include <linux/psi.h> #include <linux/rcuwait_api.h> +#include <linux/rseq.h> #include <linux/sched/wake_q.h> #include <linux/scs.h> #include <linux/slab.h> @@ -64,10 +68,11 @@ #include <linux/vtime.h> #include <linux/wait_api.h> #include <linux/workqueue_api.h> +#include <linux/livepatch_sched.h> #ifdef CONFIG_PREEMPT_DYNAMIC -# ifdef CONFIG_GENERIC_ENTRY -# include <linux/entry-common.h> +# ifdef CONFIG_GENERIC_IRQ_ENTRY +# include <linux/irq-entry-common.h> # endif #endif @@ -80,20 +85,23 @@ #define CREATE_TRACE_POINTS #include <linux/sched/rseq_api.h> #include <trace/events/sched.h> +#include <trace/events/ipi.h> #undef CREATE_TRACE_POINTS #include "sched.h" #include "stats.h" -#include "autogroup.h" #include "autogroup.h" #include "pelt.h" #include "smp.h" -#include "stats.h" #include "../workqueue_internal.h" #include "../../io_uring/io-wq.h" #include "../smpboot.h" +#include "../locking/mutex.h" + +EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu); +EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask); /* * Export tracepoints that act as a bare tracehook (ie: have no trace event @@ -104,16 +112,46 @@ 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(pelt_thermal_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_hw_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +DEFINE_PER_CPU(struct rnd_state, sched_rnd_state); + +#ifdef CONFIG_SCHED_PROXY_EXEC +DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec); +static int __init setup_proxy_exec(char *str) +{ + bool proxy_enable = true; + + if (*str && kstrtobool(str + 1, &proxy_enable)) { + pr_warn("Unable to parse sched_proxy_exec=\n"); + return 0; + } + + if (proxy_enable) { + pr_info("sched_proxy_exec enabled via boot arg\n"); + static_branch_enable(&__sched_proxy_exec); + } else { + pr_info("sched_proxy_exec disabled via boot arg\n"); + static_branch_disable(&__sched_proxy_exec); + } + return 1; +} +#else +static int __init setup_proxy_exec(char *str) +{ + pr_warn("CONFIG_SCHED_PROXY_EXEC=n, so it cannot be enabled or disabled at boot time\n"); + return 0; +} +#endif +__setup("sched_proxy_exec", setup_proxy_exec); -#ifdef CONFIG_SCHED_DEBUG /* * Debugging: various feature bits * @@ -123,7 +161,7 @@ DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); */ #define SCHED_FEAT(name, enabled) \ (1UL << __SCHED_FEAT_##name) * enabled | -const_debug unsigned int sysctl_sched_features = +__read_mostly unsigned int sysctl_sched_features = #include "features.h" 0; #undef SCHED_FEAT @@ -137,13 +175,12 @@ const_debug unsigned int sysctl_sched_features = */ __read_mostly int sysctl_resched_latency_warn_ms = 100; __read_mostly int sysctl_resched_latency_warn_once = 1; -#endif /* CONFIG_SCHED_DEBUG */ /* * Number of tasks to iterate in a single balance run. * Limited because this is done with IRQs disabled. */ -const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK; +__read_mostly unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK; __read_mostly int scheduler_running; @@ -152,18 +189,24 @@ __read_mostly int scheduler_running; DEFINE_STATIC_KEY_FALSE(__sched_core_enabled); /* kernel prio, less is more */ -static inline int __task_prio(struct task_struct *p) +static inline int __task_prio(const struct task_struct *p) { if (p->sched_class == &stop_sched_class) /* trumps deadline */ return -2; - if (rt_prio(p->prio)) /* includes deadline */ + if (p->dl_server) + return -1; /* deadline */ + + if (rt_or_dl_prio(p->prio)) return p->prio; /* [-1, 99] */ if (p->sched_class == &idle_sched_class) return MAX_RT_PRIO + NICE_WIDTH; /* 140 */ - return MAX_RT_PRIO + MAX_NICE; /* 120, squash fair */ + if (task_on_scx(p)) + return MAX_RT_PRIO + MAX_NICE + 1; /* 120, squash ext */ + + return MAX_RT_PRIO + MAX_NICE; /* 119, squash fair */ } /* @@ -174,7 +217,8 @@ static inline int __task_prio(struct task_struct *p) */ /* real prio, less is less */ -static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool in_fi) +static inline bool prio_less(const struct task_struct *a, + const struct task_struct *b, bool in_fi) { int pa = __task_prio(a), pb = __task_prio(b); @@ -185,16 +229,38 @@ static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool if (-pb < -pa) return false; - if (pa == -1) /* dl_prio() doesn't work because of stop_class above */ - return !dl_time_before(a->dl.deadline, b->dl.deadline); + if (pa == -1) { /* dl_prio() doesn't work because of stop_class above */ + const struct sched_dl_entity *a_dl, *b_dl; + + a_dl = &a->dl; + /* + * Since,'a' and 'b' can be CFS tasks served by DL server, + * __task_prio() can return -1 (for DL) even for those. In that + * case, get to the dl_server's DL entity. + */ + if (a->dl_server) + a_dl = a->dl_server; + + b_dl = &b->dl; + if (b->dl_server) + b_dl = b->dl_server; + + return !dl_time_before(a_dl->deadline, b_dl->deadline); + } if (pa == MAX_RT_PRIO + MAX_NICE) /* fair */ return cfs_prio_less(a, b, in_fi); +#ifdef CONFIG_SCHED_CLASS_EXT + if (pa == MAX_RT_PRIO + MAX_NICE + 1) /* ext */ + return scx_prio_less(a, b, in_fi); +#endif + return false; } -static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b) +static inline bool __sched_core_less(const struct task_struct *a, + const struct task_struct *b) { if (a->core_cookie < b->core_cookie) return true; @@ -232,6 +298,9 @@ static inline int rb_sched_core_cmp(const void *key, const struct rb_node *node) void sched_core_enqueue(struct rq *rq, struct task_struct *p) { + if (p->se.sched_delayed) + return; + rq->core->core_task_seq++; if (!p->core_cookie) @@ -242,6 +311,9 @@ void sched_core_enqueue(struct rq *rq, struct task_struct *p) void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { + if (p->se.sched_delayed) + return; + rq->core->core_task_seq++; if (sched_core_enqueued(p)) { @@ -259,36 +331,51 @@ void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) resched_curr(rq); } -/* - * Find left-most (aka, highest priority) task matching @cookie. - */ -static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie) +static int sched_task_is_throttled(struct task_struct *p, int cpu) { - struct rb_node *node; - - node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp); - /* - * The idle task always matches any cookie! - */ - if (!node) - return idle_sched_class.pick_task(rq); + if (p->sched_class->task_is_throttled) + return p->sched_class->task_is_throttled(p, cpu); - return __node_2_sc(node); + return 0; } static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie) { struct rb_node *node = &p->core_node; + int cpu = task_cpu(p); + + do { + node = rb_next(node); + if (!node) + return NULL; - node = rb_next(node); + p = __node_2_sc(node); + if (p->core_cookie != cookie) + return NULL; + + } while (sched_task_is_throttled(p, cpu)); + + return p; +} + +/* + * Find left-most (aka, highest priority) and unthrottled task matching @cookie. + * If no suitable task is found, NULL will be returned. + */ +static struct task_struct *sched_core_find(struct rq *rq, unsigned long cookie) +{ + struct task_struct *p; + struct rb_node *node; + + node = rb_find_first((void *)cookie, &rq->core_tree, rb_sched_core_cmp); if (!node) return NULL; - p = container_of(node, struct task_struct, core_node); - if (p->core_cookie != cookie) - return NULL; + p = __node_2_sc(node); + if (!sched_task_is_throttled(p, rq->cpu)) + return p; - return p; + return sched_core_next(p, cookie); } /* @@ -427,13 +514,23 @@ void sched_core_put(void) schedule_work(&_work); } -#else /* !CONFIG_SCHED_CORE */ +#else /* !CONFIG_SCHED_CORE: */ static inline void sched_core_enqueue(struct rq *rq, struct task_struct *p) { } static inline void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } -#endif /* CONFIG_SCHED_CORE */ +#endif /* !CONFIG_SCHED_CORE */ + +/* need a wrapper since we may need to trace from modules */ +EXPORT_TRACEPOINT_SYMBOL(sched_set_state_tp); + +/* Call via the helper macro trace_set_current_state. */ +void __trace_set_current_state(int state_value) +{ + trace_sched_set_state_tp(current, state_value); +} +EXPORT_SYMBOL(__trace_set_current_state); /* * Serialization rules: @@ -487,11 +584,16 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { } * * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }: * - * is set by activate_task() and cleared by deactivate_task(), under - * rq->lock. Non-zero indicates the task is runnable, the special + * is set by activate_task() and cleared by deactivate_task()/block_task(), + * under rq->lock. Non-zero indicates the task is runnable, the special * ON_RQ_MIGRATING state is used for migration without holding both * rq->locks. It indicates task_cpu() is not stable, see task_rq_lock(). * + * Additionally it is possible to be ->on_rq but still be considered not + * runnable when p->se.sched_delayed is true. These tasks are on the runqueue + * but will be dequeued as soon as they get picked again. See the + * task_is_runnable() helper. + * * p->on_cpu <- { 0, 1 }: * * is set by prepare_task() and cleared by finish_task() such that it will be @@ -581,7 +683,6 @@ void raw_spin_rq_unlock(struct rq *rq) raw_spin_unlock(rq_lockp(rq)); } -#ifdef CONFIG_SMP /* * double_rq_lock - safely lock two runqueues */ @@ -598,7 +699,6 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2) double_rq_clock_clear_update(rq1, rq2); } -#endif /* * __task_rq_lock - lock the rq @p resides on. @@ -679,39 +779,43 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) s64 __maybe_unused steal = 0, irq_delta = 0; #ifdef CONFIG_IRQ_TIME_ACCOUNTING - irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + if (irqtime_enabled()) { + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; - /* - * Since irq_time is only updated on {soft,}irq_exit, we might run into - * this case when a previous update_rq_clock() happened inside a - * {soft,}irq region. - * - * When this happens, we stop ->clock_task and only update the - * prev_irq_time stamp to account for the part that fit, so that a next - * update will consume the rest. This ensures ->clock_task is - * monotonic. - * - * It does however cause some slight miss-attribution of {soft,}irq - * time, a more accurate solution would be to update the irq_time using - * the current rq->clock timestamp, except that would require using - * atomic ops. - */ - if (irq_delta > delta) - irq_delta = delta; + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}IRQ region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}IRQ + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; - rq->prev_irq_time += irq_delta; - delta -= irq_delta; - psi_account_irqtime(rq->curr, irq_delta); + rq->prev_irq_time += irq_delta; + delta -= irq_delta; + delayacct_irq(rq->curr, irq_delta); + } #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); + u64 prev_steal; + + steal = prev_steal = paravirt_steal_clock(cpu_of(rq)); steal -= rq->prev_steal_time_rq; if (unlikely(steal > delta)) steal = delta; - rq->prev_steal_time_rq += steal; + rq->prev_steal_time_rq = prev_steal; delta -= steal; } #endif @@ -728,22 +832,25 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) void update_rq_clock(struct rq *rq) { s64 delta; + u64 clock; lockdep_assert_rq_held(rq); if (rq->clock_update_flags & RQCF_ACT_SKIP) return; -#ifdef CONFIG_SCHED_DEBUG if (sched_feat(WARN_DOUBLE_CLOCK)) - SCHED_WARN_ON(rq->clock_update_flags & RQCF_UPDATED); + WARN_ON_ONCE(rq->clock_update_flags & RQCF_UPDATED); rq->clock_update_flags |= RQCF_UPDATED; -#endif - delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + clock = sched_clock_cpu(cpu_of(rq)); + scx_rq_clock_update(rq, clock); + + delta = clock - rq->clock; if (delta < 0) return; rq->clock += delta; + update_rq_clock_task(rq, delta); } @@ -771,14 +878,12 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) rq_lock(rq, &rf); update_rq_clock(rq); - rq->curr->sched_class->task_tick(rq, rq->curr, 1); + rq->donor->sched_class->task_tick(rq, rq->donor, 1); rq_unlock(rq, &rf); return HRTIMER_NORESTART; } -#ifdef CONFIG_SMP - static void __hrtick_restart(struct rq *rq) { struct hrtimer *timer = &rq->hrtick_timer; @@ -803,7 +908,7 @@ static void __hrtick_start(void *arg) /* * Called to set the hrtick timer state. * - * called with rq->lock held and irqs disabled + * called with rq->lock held and IRQs disabled */ void hrtick_start(struct rq *rq, u64 delay) { @@ -815,7 +920,7 @@ void hrtick_start(struct rq *rq, u64 delay) * doesn't make sense and can cause timer DoS. */ delta = max_t(s64, delay, 10000LL); - rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta); + rq->hrtick_time = ktime_add_ns(hrtimer_cb_get_time(timer), delta); if (rq == this_rq()) __hrtick_restart(rq); @@ -823,34 +928,12 @@ void hrtick_start(struct rq *rq, u64 delay) smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd); } -#else -/* - * Called to set the hrtick timer state. - * - * called with rq->lock held and irqs disabled - */ -void hrtick_start(struct rq *rq, u64 delay) -{ - /* - * Don't schedule slices shorter than 10000ns, that just - * doesn't make sense. Rely on vruntime for fairness. - */ - delay = max_t(u64, delay, 10000LL); - hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), - HRTIMER_MODE_REL_PINNED_HARD); -} - -#endif /* CONFIG_SMP */ - static void hrtick_rq_init(struct rq *rq) { -#ifdef CONFIG_SMP INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq); -#endif - hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); - rq->hrtick_timer.function = hrtick; + hrtimer_setup(&rq->hrtick_timer, hrtick, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); } -#else /* CONFIG_SCHED_HRTICK */ +#else /* !CONFIG_SCHED_HRTICK: */ static inline void hrtick_clear(struct rq *rq) { } @@ -858,10 +941,10 @@ static inline void hrtick_clear(struct rq *rq) static inline void hrtick_rq_init(struct rq *rq) { } -#endif /* CONFIG_SCHED_HRTICK */ +#endif /* !CONFIG_SCHED_HRTICK */ /* - * cmpxchg based fetch_or, macro so it works for different integer types + * try_cmpxchg based fetch_or() macro so it works for different integer types: */ #define fetch_or(ptr, mask) \ ({ \ @@ -874,16 +957,15 @@ static inline void hrtick_rq_init(struct rq *rq) _val; \ }) -#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) +#ifdef TIF_POLLING_NRFLAG /* * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, * this avoids any races wrt polling state changes and thereby avoids * spurious IPIs. */ -static inline bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct thread_info *ti, int tif) { - struct thread_info *ti = task_thread_info(p); - return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); + return !(fetch_or(&ti->flags, 1 << tif) & _TIF_POLLING_NRFLAG); } /* @@ -897,31 +979,28 @@ static bool set_nr_if_polling(struct task_struct *p) struct thread_info *ti = task_thread_info(p); typeof(ti->flags) val = READ_ONCE(ti->flags); - for (;;) { + do { if (!(val & _TIF_POLLING_NRFLAG)) return false; if (val & _TIF_NEED_RESCHED) return true; - if (try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED)) - break; - } + } while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED)); + return true; } #else -static inline bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct thread_info *ti, int tif) { - set_tsk_need_resched(p); + set_ti_thread_flag(ti, tif); return true; } -#ifdef CONFIG_SMP static inline bool set_nr_if_polling(struct task_struct *p) { return false; } #endif -#endif static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) { @@ -996,9 +1075,10 @@ void wake_up_q(struct wake_q_head *head) struct task_struct *task; task = container_of(node, struct task_struct, wake_q); - /* Task can safely be re-inserted now: */ node = node->next; - task->wake_q.next = NULL; + /* pairs with cmpxchg_relaxed() in __wake_q_add() */ + WRITE_ONCE(task->wake_q.next, NULL); + /* Task can safely be re-inserted now. */ /* * wake_up_process() executes a full barrier, which pairs with @@ -1016,28 +1096,76 @@ void wake_up_q(struct wake_q_head *head) * might also involve a cross-CPU call to trigger the scheduler on * the target CPU. */ -void resched_curr(struct rq *rq) +static void __resched_curr(struct rq *rq, int tif) { struct task_struct *curr = rq->curr; + struct thread_info *cti = task_thread_info(curr); int cpu; lockdep_assert_rq_held(rq); - if (test_tsk_need_resched(curr)) + /* + * Always immediately preempt the idle task; no point in delaying doing + * actual work. + */ + if (is_idle_task(curr) && tif == TIF_NEED_RESCHED_LAZY) + tif = TIF_NEED_RESCHED; + + if (cti->flags & ((1 << tif) | _TIF_NEED_RESCHED)) return; cpu = cpu_of(rq); + trace_sched_set_need_resched_tp(curr, cpu, tif); if (cpu == smp_processor_id()) { - set_tsk_need_resched(curr); - set_preempt_need_resched(); + set_ti_thread_flag(cti, tif); + if (tif == TIF_NEED_RESCHED) + set_preempt_need_resched(); return; } - if (set_nr_and_not_polling(curr)) - smp_send_reschedule(cpu); - else + if (set_nr_and_not_polling(cti, tif)) { + if (tif == TIF_NEED_RESCHED) + smp_send_reschedule(cpu); + } else { trace_sched_wake_idle_without_ipi(cpu); + } +} + +void __trace_set_need_resched(struct task_struct *curr, int tif) +{ + trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif); +} + +void resched_curr(struct rq *rq) +{ + __resched_curr(rq, TIF_NEED_RESCHED); +} + +#ifdef CONFIG_PREEMPT_DYNAMIC +static DEFINE_STATIC_KEY_FALSE(sk_dynamic_preempt_lazy); +static __always_inline bool dynamic_preempt_lazy(void) +{ + return static_branch_unlikely(&sk_dynamic_preempt_lazy); +} +#else +static __always_inline bool dynamic_preempt_lazy(void) +{ + return IS_ENABLED(CONFIG_PREEMPT_LAZY); +} +#endif + +static __always_inline int get_lazy_tif_bit(void) +{ + if (dynamic_preempt_lazy()) + return TIF_NEED_RESCHED_LAZY; + + return TIF_NEED_RESCHED; +} + +void resched_curr_lazy(struct rq *rq) +{ + __resched_curr(rq, get_lazy_tif_bit()); } void resched_cpu(int cpu) @@ -1051,7 +1179,6 @@ void resched_cpu(int cpu) raw_spin_rq_unlock_irqrestore(rq, flags); } -#ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ_COMMON /* * In the semi idle case, use the nearest busy CPU for migrating timers @@ -1059,7 +1186,7 @@ void resched_cpu(int cpu) * * We don't do similar optimization for completely idle system, as * selecting an idle CPU will add more delays to the timers than intended - * (as that CPU's timer base may not be uptodate wrt jiffies etc). + * (as that CPU's timer base may not be up to date wrt jiffies etc). */ int get_nohz_timer_target(void) { @@ -1067,33 +1194,30 @@ int get_nohz_timer_target(void) struct sched_domain *sd; const struct cpumask *hk_mask; - if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) { + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) { if (!idle_cpu(cpu)) return cpu; default_cpu = cpu; } - hk_mask = housekeeping_cpumask(HK_TYPE_TIMER); + hk_mask = housekeeping_cpumask(HK_TYPE_KERNEL_NOISE); + + guard(rcu)(); - rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu_and(i, sched_domain_span(sd), hk_mask) { if (cpu == i) continue; - if (!idle_cpu(i)) { - cpu = i; - goto unlock; - } + if (!idle_cpu(i)) + return i; } } if (default_cpu == -1) - default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER); - cpu = default_cpu; -unlock: - rcu_read_unlock(); - return cpu; + default_cpu = housekeeping_any_cpu(HK_TYPE_KERNEL_NOISE); + + return default_cpu; } /* @@ -1113,7 +1237,29 @@ static void wake_up_idle_cpu(int cpu) if (cpu == smp_processor_id()) return; - if (set_nr_and_not_polling(rq->idle)) + /* + * Set TIF_NEED_RESCHED and send an IPI if in the non-polling + * part of the idle loop. This forces an exit from the idle loop + * and a round trip to schedule(). Now this could be optimized + * because a simple new idle loop iteration is enough to + * re-evaluate the next tick. Provided some re-ordering of tick + * nohz functions that would need to follow TIF_NR_POLLING + * clearing: + * + * - On most architectures, a simple fetch_or on ti::flags with a + * "0" value would be enough to know if an IPI needs to be sent. + * + * - x86 needs to perform a last need_resched() check between + * monitor and mwait which doesn't take timers into account. + * There a dedicated TIF_TIMER flag would be required to + * fetch_or here and be checked along with TIF_NEED_RESCHED + * before mwait(). + * + * However, remote timer enqueue is not such a frequent event + * and testing of the above solutions didn't appear to report + * much benefits. + */ + if (set_nr_and_not_polling(task_thread_info(rq->idle), TIF_NEED_RESCHED)) smp_send_reschedule(cpu); else trace_sched_wake_idle_without_ipi(cpu); @@ -1163,15 +1309,29 @@ static void nohz_csd_func(void *info) WARN_ON(!(flags & NOHZ_KICK_MASK)); rq->idle_balance = idle_cpu(cpu); - if (rq->idle_balance && !need_resched()) { + if (rq->idle_balance) { rq->nohz_idle_balance = flags; - raise_softirq_irqoff(SCHED_SOFTIRQ); + __raise_softirq_irqoff(SCHED_SOFTIRQ); } } #endif /* CONFIG_NO_HZ_COMMON */ #ifdef CONFIG_NO_HZ_FULL +static inline bool __need_bw_check(struct rq *rq, struct task_struct *p) +{ + if (rq->nr_running != 1) + return false; + + if (p->sched_class != &fair_sched_class) + return false; + + if (!task_on_rq_queued(p)) + return false; + + return true; +} + bool sched_can_stop_tick(struct rq *rq) { int fifo_nr_running; @@ -1200,20 +1360,33 @@ bool sched_can_stop_tick(struct rq *rq) return true; /* - * If there are no DL,RR/FIFO tasks, there must only be CFS tasks left; - * if there's more than one we need the tick for involuntary - * preemption. + * If there are no DL,RR/FIFO tasks, there must only be CFS or SCX tasks + * left. For CFS, if there's more than one we need the tick for + * involuntary preemption. For SCX, ask. */ - if (rq->nr_running > 1) + if (scx_enabled() && !scx_can_stop_tick(rq)) + return false; + + if (rq->cfs.h_nr_queued > 1) return false; + /* + * If there is one task and it has CFS runtime bandwidth constraints + * and it's on the cpu now we don't want to stop the tick. + * This check prevents clearing the bit if a newly enqueued task here is + * dequeued by migrating while the constrained task continues to run. + * E.g. going from 2->1 without going through pick_next_task(). + */ + if (__need_bw_check(rq, rq->curr)) { + if (cfs_task_bw_constrained(rq->curr)) + return false; + } + return true; } #endif /* CONFIG_NO_HZ_FULL */ -#endif /* CONFIG_SMP */ -#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \ - (defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH))) +#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_FAIR_GROUP_SCHED) /* * Iterate task_group tree rooted at *from, calling @down when first entering a * node and @up when leaving it for the final time. @@ -1257,30 +1430,27 @@ int tg_nop(struct task_group *tg, void *data) } #endif -static void set_load_weight(struct task_struct *p, bool update_load) +void set_load_weight(struct task_struct *p, bool update_load) { int prio = p->static_prio - MAX_RT_PRIO; - struct load_weight *load = &p->se.load; + struct load_weight lw; - /* - * SCHED_IDLE tasks get minimal weight: - */ if (task_has_idle_policy(p)) { - load->weight = scale_load(WEIGHT_IDLEPRIO); - load->inv_weight = WMULT_IDLEPRIO; - return; + lw.weight = scale_load(WEIGHT_IDLEPRIO); + lw.inv_weight = WMULT_IDLEPRIO; + } else { + lw.weight = scale_load(sched_prio_to_weight[prio]); + lw.inv_weight = sched_prio_to_wmult[prio]; } /* * SCHED_OTHER tasks have to update their load when changing their * weight */ - if (update_load && p->sched_class == &fair_sched_class) { - reweight_task(p, prio); - } else { - load->weight = scale_load(sched_prio_to_weight[prio]); - load->inv_weight = sched_prio_to_wmult[prio]; - } + if (update_load && p->sched_class->reweight_task) + p->sched_class->reweight_task(task_rq(p), p, &lw); + else + p->se.load = lw; } #ifdef CONFIG_UCLAMP_TASK @@ -1294,7 +1464,7 @@ static void set_load_weight(struct task_struct *p, bool update_load) * requests are serialized using a mutex to reduce the risk of conflicting * updates or API abuses. */ -static DEFINE_MUTEX(uclamp_mutex); +static __maybe_unused DEFINE_MUTEX(uclamp_mutex); /* Max allowed minimum utilization */ static unsigned int __maybe_unused sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; @@ -1317,7 +1487,7 @@ static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = SCHED_CAPACITY * This knob will not override the system default sched_util_clamp_min defined * above. */ -static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; +unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE; /* All clamps are required to be less or equal than these values */ static struct uclamp_se uclamp_default[UCLAMP_CNT]; @@ -1342,32 +1512,6 @@ static struct uclamp_se uclamp_default[UCLAMP_CNT]; */ DEFINE_STATIC_KEY_FALSE(sched_uclamp_used); -/* 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 min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1); -} - -static inline unsigned int 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) @@ -1435,16 +1579,12 @@ static void __uclamp_update_util_min_rt_default(struct task_struct *p) static void uclamp_update_util_min_rt_default(struct task_struct *p) { - struct rq_flags rf; - struct rq *rq; - if (!rt_task(p)) return; /* Protect updates to p->uclamp_* */ - rq = task_rq_lock(p, &rf); + guard(task_rq_lock)(p); __uclamp_update_util_min_rt_default(p); - task_rq_unlock(rq, p, &rf); } static inline struct uclamp_se @@ -1595,7 +1735,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, bucket = &uc_rq->bucket[uc_se->bucket_id]; - SCHED_WARN_ON(!bucket->tasks); + WARN_ON_ONCE(!bucket->tasks); if (likely(bucket->tasks)) bucket->tasks--; @@ -1613,16 +1753,16 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, rq_clamp = uclamp_rq_get(rq, clamp_id); /* * Defensive programming: this should never happen. If it happens, - * e.g. due to future modification, warn and fixup the expected value. + * e.g. due to future modification, warn and fix up the expected value. */ - SCHED_WARN_ON(bucket->value > rq_clamp); + WARN_ON_ONCE(bucket->value > rq_clamp); if (bucket->value >= rq_clamp) { bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value); uclamp_rq_set(rq, clamp_id, bkt_clamp); } } -static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) +static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags) { enum uclamp_id clamp_id; @@ -1632,12 +1772,16 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) * The condition is constructed such that a NOP is generated when * sched_uclamp_used is disabled. */ - if (!static_branch_unlikely(&sched_uclamp_used)) + if (!uclamp_is_used()) return; if (unlikely(!p->sched_class->uclamp_enabled)) return; + /* Only inc the delayed task which being woken up. */ + if (p->se.sched_delayed && !(flags & ENQUEUE_DELAYED)) + return; + for_each_clamp_id(clamp_id) uclamp_rq_inc_id(rq, p, clamp_id); @@ -1656,12 +1800,15 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) * The condition is constructed such that a NOP is generated when * sched_uclamp_used is disabled. */ - if (!static_branch_unlikely(&sched_uclamp_used)) + if (!uclamp_is_used()) return; if (unlikely(!p->sched_class->uclamp_enabled)) return; + if (p->se.sched_delayed) + return; + for_each_clamp_id(clamp_id) uclamp_rq_dec_id(rq, p, clamp_id); } @@ -1729,7 +1876,6 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css); #endif #ifdef CONFIG_SYSCTL -#ifdef CONFIG_UCLAMP_TASK #ifdef CONFIG_UCLAMP_TASK_GROUP static void uclamp_update_root_tg(void) { @@ -1740,9 +1886,8 @@ static void uclamp_update_root_tg(void) uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX], sysctl_sched_uclamp_util_max, false); - rcu_read_lock(); + guard(rcu)(); cpu_util_update_eff(&root_task_group.css); - rcu_read_unlock(); } #else static void uclamp_update_root_tg(void) { } @@ -1769,20 +1914,20 @@ static void uclamp_sync_util_min_rt_default(void) smp_mb__after_spinlock(); read_unlock(&tasklist_lock); - rcu_read_lock(); + guard(rcu)(); for_each_process_thread(g, p) uclamp_update_util_min_rt_default(p); - rcu_read_unlock(); } -static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, +static int sysctl_sched_uclamp_handler(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { bool update_root_tg = false; int old_min, old_max, old_min_rt; int result; - mutex_lock(&uclamp_mutex); + guard(mutex)(&uclamp_mutex); + old_min = sysctl_sched_uclamp_util_min; old_max = sysctl_sched_uclamp_util_max; old_min_rt = sysctl_sched_uclamp_util_min_rt_default; @@ -1791,7 +1936,7 @@ static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, if (result) goto undo; if (!write) - goto done; + return 0; if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max || sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE || @@ -1813,12 +1958,12 @@ static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, } if (update_root_tg) { - static_branch_enable(&sched_uclamp_used); + sched_uclamp_enable(); uclamp_update_root_tg(); } if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) { - static_branch_enable(&sched_uclamp_used); + sched_uclamp_enable(); uclamp_sync_util_min_rt_default(); } @@ -1827,121 +1972,15 @@ static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, * Otherwise, keep it simple and do just a lazy update at each next * task enqueue time. */ - - goto done; + return 0; undo: sysctl_sched_uclamp_util_min = old_min; sysctl_sched_uclamp_util_max = old_max; sysctl_sched_uclamp_util_min_rt_default = old_min_rt; -done: - mutex_unlock(&uclamp_mutex); - return result; } -#endif -#endif - -static int uclamp_validate(struct task_struct *p, - const struct sched_attr *attr) -{ - int util_min = p->uclamp_req[UCLAMP_MIN].value; - int util_max = p->uclamp_req[UCLAMP_MAX].value; - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { - util_min = attr->sched_util_min; - - if (util_min + 1 > SCHED_CAPACITY_SCALE + 1) - return -EINVAL; - } - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) { - util_max = attr->sched_util_max; - - if (util_max + 1 > SCHED_CAPACITY_SCALE + 1) - return -EINVAL; - } - - if (util_min != -1 && util_max != -1 && util_min > util_max) - return -EINVAL; - - /* - * We have valid uclamp attributes; make sure uclamp is enabled. - * - * We need to do that here, because enabling static branches is a - * blocking operation which obviously cannot be done while holding - * scheduler locks. - */ - static_branch_enable(&sched_uclamp_used); - - return 0; -} - -static bool uclamp_reset(const struct sched_attr *attr, - enum uclamp_id clamp_id, - struct uclamp_se *uc_se) -{ - /* Reset on sched class change for a non user-defined clamp value. */ - if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)) && - !uc_se->user_defined) - return true; - - /* Reset on sched_util_{min,max} == -1. */ - if (clamp_id == UCLAMP_MIN && - attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && - attr->sched_util_min == -1) { - return true; - } - - if (clamp_id == UCLAMP_MAX && - attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && - attr->sched_util_max == -1) { - return true; - } - - return false; -} - -static void __setscheduler_uclamp(struct task_struct *p, - const struct sched_attr *attr) -{ - enum uclamp_id clamp_id; - - for_each_clamp_id(clamp_id) { - struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; - unsigned int value; - - if (!uclamp_reset(attr, clamp_id, uc_se)) - continue; - - /* - * RT by default have a 100% boost value that could be modified - * at runtime. - */ - if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) - value = sysctl_sched_uclamp_util_min_rt_default; - else - value = uclamp_none(clamp_id); - - uclamp_se_set(uc_se, value, false); - - } - - if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) - return; - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN && - attr->sched_util_min != -1) { - uclamp_se_set(&p->uclamp_req[UCLAMP_MIN], - attr->sched_util_min, true); - } - - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX && - attr->sched_util_max != -1) { - uclamp_se_set(&p->uclamp_req[UCLAMP_MAX], - attr->sched_util_max, true); - } -} +#endif /* CONFIG_SYSCTL */ static void uclamp_fork(struct task_struct *p) { @@ -2007,20 +2046,13 @@ static void __init init_uclamp(void) } } -#else /* CONFIG_UCLAMP_TASK */ -static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { } +#else /* !CONFIG_UCLAMP_TASK: */ +static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p, int flags) { } 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 uclamp_post_fork(struct task_struct *p) { } static inline void init_uclamp(void) { } -#endif /* CONFIG_UCLAMP_TASK */ +#endif /* !CONFIG_UCLAMP_TASK */ bool sched_task_on_rq(struct task_struct *p) { @@ -2046,24 +2078,34 @@ unsigned long get_wchan(struct task_struct *p) return ip; } -static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) +void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & ENQUEUE_RESTORE)) { - sched_info_enqueue(rq, p); - psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED)); - } + /* + * Can be before ->enqueue_task() because uclamp considers the + * ENQUEUE_DELAYED task before its ->sched_delayed gets cleared + * in ->enqueue_task(). + */ + uclamp_rq_inc(rq, p, flags); - uclamp_rq_inc(rq, p); + rq->queue_mask |= p->sched_class->queue_mask; p->sched_class->enqueue_task(rq, p, flags); + psi_enqueue(p, flags); + + if (!(flags & ENQUEUE_RESTORE)) + sched_info_enqueue(rq, p); + if (sched_core_enabled(rq)) sched_core_enqueue(rq, p); } -static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) +/* + * Must only return false when DEQUEUE_SLEEP. + */ +inline bool dequeue_task(struct rq *rq, struct task_struct *p, int flags) { if (sched_core_enabled(rq)) sched_core_dequeue(rq, p, flags); @@ -2071,73 +2113,50 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & DEQUEUE_SAVE)) { + if (!(flags & DEQUEUE_SAVE)) sched_info_dequeue(rq, p); - psi_dequeue(p, flags & DEQUEUE_SLEEP); - } + psi_dequeue(p, flags); + + /* + * Must be before ->dequeue_task() because ->dequeue_task() can 'fail' + * and mark the task ->sched_delayed. + */ uclamp_rq_dec(rq, p); - p->sched_class->dequeue_task(rq, p, flags); + rq->queue_mask |= p->sched_class->queue_mask; + return p->sched_class->dequeue_task(rq, p, flags); } void activate_task(struct rq *rq, struct task_struct *p, int flags) { + if (task_on_rq_migrating(p)) + flags |= ENQUEUE_MIGRATED; + enqueue_task(rq, p, flags); - p->on_rq = TASK_ON_RQ_QUEUED; + WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED); + ASSERT_EXCLUSIVE_WRITER(p->on_rq); } void deactivate_task(struct rq *rq, struct task_struct *p, int flags) { - p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING; - - dequeue_task(rq, p, flags); -} - -static inline int __normal_prio(int policy, int rt_prio, int nice) -{ - int prio; + WARN_ON_ONCE(flags & DEQUEUE_SLEEP); - if (dl_policy(policy)) - prio = MAX_DL_PRIO - 1; - else if (rt_policy(policy)) - prio = MAX_RT_PRIO - 1 - rt_prio; - else - prio = NICE_TO_PRIO(nice); + WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING); + ASSERT_EXCLUSIVE_WRITER(p->on_rq); - return prio; -} + /* + * Code explicitly relies on TASK_ON_RQ_MIGRATING begin set *before* + * dequeue_task() and cleared *after* enqueue_task(). + */ -/* - * Calculate the expected normal priority: i.e. priority - * without taking RT-inheritance into account. Might be - * boosted by interactivity modifiers. Changes upon fork, - * setprio syscalls, and whenever the interactivity - * estimator recalculates. - */ -static inline int normal_prio(struct task_struct *p) -{ - return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); + dequeue_task(rq, p, flags); } -/* - * Calculate the current priority, i.e. the priority - * taken into account by the scheduler. This value might - * be boosted by RT tasks, or might be boosted by - * interactivity modifiers. Will be RT if the task got - * RT-boosted. If not then it returns p->normal_prio. - */ -static int effective_prio(struct task_struct *p) +static void block_task(struct rq *rq, struct task_struct *p, int flags) { - p->normal_prio = normal_prio(p); - /* - * If we are RT tasks or we were boosted to RT priority, - * keep the priority unchanged. Otherwise, update priority - * to the normal priority: - */ - if (!rt_prio(p->prio)) - return p->normal_prio; - return p->prio; + if (dequeue_task(rq, p, DEQUEUE_SLEEP | flags)) + __block_task(rq, p); } /** @@ -2151,48 +2170,169 @@ inline int task_curr(const struct task_struct *p) return cpu_curr(task_cpu(p)) == p; } -/* - * switched_from, switched_to and prio_changed must _NOT_ drop rq->lock, - * use the balance_callback list if you want balancing. - * - * this means any call to check_class_changed() must be followed by a call to - * balance_callback(). - */ -static inline void check_class_changed(struct rq *rq, struct task_struct *p, - const struct sched_class *prev_class, - int oldprio) +void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags) { - if (prev_class != p->sched_class) { - if (prev_class->switched_from) - prev_class->switched_from(rq, p); - - p->sched_class->switched_to(rq, p); - } else if (oldprio != p->prio || dl_task(p)) - p->sched_class->prio_changed(rq, p, oldprio); -} + struct task_struct *donor = rq->donor; -void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) -{ - if (p->sched_class == rq->curr->sched_class) - rq->curr->sched_class->check_preempt_curr(rq, p, flags); - else if (sched_class_above(p->sched_class, rq->curr->sched_class)) + if (p->sched_class == donor->sched_class) + donor->sched_class->wakeup_preempt(rq, p, flags); + else if (sched_class_above(p->sched_class, donor->sched_class)) resched_curr(rq); /* * A queue event has occurred, and we're going to schedule. In * this case, we can save a useless back to back clock update. */ - if (task_on_rq_queued(rq->curr) && test_tsk_need_resched(rq->curr)) + if (task_on_rq_queued(donor) && test_tsk_need_resched(rq->curr)) rq_clock_skip_update(rq); } -#ifdef CONFIG_SMP +static __always_inline +int __task_state_match(struct task_struct *p, unsigned int state) +{ + if (READ_ONCE(p->__state) & state) + return 1; -static void -__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx); + if (READ_ONCE(p->saved_state) & state) + return -1; -static int __set_cpus_allowed_ptr(struct task_struct *p, - struct affinity_context *ctx); + return 0; +} + +static __always_inline +int task_state_match(struct task_struct *p, unsigned int state) +{ + /* + * Serialize against current_save_and_set_rtlock_wait_state(), + * current_restore_rtlock_saved_state(), and __refrigerator(). + */ + guard(raw_spinlock_irq)(&p->pi_lock); + return __task_state_match(p, state); +} + +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * Wait for the thread to block in any of the states set in @match_state. + * If it changes, i.e. @p might have woken up, then return zero. When we + * succeed in waiting for @p to be off its CPU, we return a positive number + * (its total switch count). If a second call a short while later returns the + * same number, the caller can be sure that @p has remained unscheduled the + * whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) +{ + int running, queued, match; + struct rq_flags rf; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + /* + * We do the initial early heuristics without holding + * any task-queue locks at all. We'll only try to get + * the runqueue lock when things look like they will + * work out! + */ + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since "task_on_cpu()" will + * return false if the runqueue has changed and p + * is actually now running somewhere else! + */ + while (task_on_cpu(rq, p)) { + if (!task_state_match(p, match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_rq_lock(p, &rf); + /* + * If task is sched_delayed, force dequeue it, to avoid always + * hitting the tick timeout in the queued case + */ + if (p->se.sched_delayed) + dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED); + trace_sched_wait_task(p); + running = task_on_cpu(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; + if ((match = __task_state_match(p, match_state))) { + /* + * When matching on p->saved_state, consider this task + * still queued so it will wait. + */ + if (match < 0) + queued = 1; + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + } + task_rq_unlock(rq, p, &rf); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it was still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(queued)) { + ktime_t to = NSEC_PER_SEC / HZ; + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + +static void +do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx); static void migrate_disable_switch(struct rq *rq, struct task_struct *p) { @@ -2207,29 +2347,11 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p) if (p->cpus_ptr != &p->cpus_mask) return; - /* - * Violates locking rules! see comment in __do_set_cpus_allowed(). - */ - __do_set_cpus_allowed(p, &ac); + scoped_guard (task_rq_lock, p) + do_set_cpus_allowed(p, &ac); } -void migrate_disable(void) -{ - struct task_struct *p = current; - - if (p->migration_disabled) { - p->migration_disabled++; - return; - } - - preempt_disable(); - this_rq()->nr_pinned++; - p->migration_disabled = 1; - preempt_enable(); -} -EXPORT_SYMBOL_GPL(migrate_disable); - -void migrate_enable(void) +void ___migrate_enable(void) { struct task_struct *p = current; struct affinity_context ac = { @@ -2237,30 +2359,19 @@ void migrate_enable(void) .flags = SCA_MIGRATE_ENABLE, }; - if (p->migration_disabled > 1) { - p->migration_disabled--; - return; - } + __set_cpus_allowed_ptr(p, &ac); +} +EXPORT_SYMBOL_GPL(___migrate_enable); - if (WARN_ON_ONCE(!p->migration_disabled)) - return; +void migrate_disable(void) +{ + __migrate_disable(); +} +EXPORT_SYMBOL_GPL(migrate_disable); - /* - * Ensure stop_task runs either before or after this, and that - * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule(). - */ - preempt_disable(); - if (p->cpus_ptr != &p->cpus_mask) - __set_cpus_allowed_ptr(p, &ac); - /* - * Mustn't clear migration_disabled() until cpus_ptr points back at the - * regular cpus_mask, otherwise things that race (eg. - * select_fallback_rq) get confused. - */ - barrier(); - p->migration_disabled = 0; - this_rq()->nr_pinned--; - preempt_enable(); +void migrate_enable(void) +{ + __migrate_enable(); } EXPORT_SYMBOL_GPL(migrate_enable); @@ -2276,7 +2387,7 @@ static inline bool rq_has_pinned_tasks(struct rq *rq) static inline bool is_cpu_allowed(struct task_struct *p, int cpu) { /* When not in the task's cpumask, no point in looking further. */ - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + if (!task_allowed_on_cpu(p, cpu)) return false; /* migrate_disabled() must be allowed to finish. */ @@ -2285,7 +2396,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) /* Non kernel threads are not allowed during either online or offline. */ if (!(p->flags & PF_KTHREAD)) - return cpu_active(cpu) && task_cpu_possible(cpu, p); + return cpu_active(cpu); /* KTHREAD_IS_PER_CPU is always allowed. */ if (kthread_is_per_cpu(p)) @@ -2332,7 +2443,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, rq_lock(rq, rf); WARN_ON_ONCE(task_cpu(p) != new_cpu); activate_task(rq, p, 0); - check_preempt_curr(rq, p, 0); + wakeup_preempt(rq, p, 0); return rq; } @@ -2371,14 +2482,13 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf, if (!is_cpu_allowed(p, dest_cpu)) return rq; - update_rq_clock(rq); rq = move_queued_task(rq, rf, p, dest_cpu); return rq; } /* - * migration_cpu_stop - this will be executed by a highprio stopper thread + * migration_cpu_stop - this will be executed by a high-prio stopper thread * and performs thread migration by bumping thread off CPU then * 'pushing' onto another runqueue. */ @@ -2429,10 +2539,12 @@ static int migration_cpu_stop(void *data) goto out; } - if (task_on_rq_queued(p)) + if (task_on_rq_queued(p)) { + update_rq_clock(rq); rq = __migrate_task(rq, &rf, p, arg->dest_cpu); - else + } else { p->wake_cpu = arg->dest_cpu; + } /* * XXX __migrate_task() can fail, at which point we might end @@ -2468,15 +2580,19 @@ static int migration_cpu_stop(void *data) * it. */ WARN_ON_ONCE(!pending->stop_pending); - task_rq_unlock(rq, p, &rf); + preempt_disable(); + rq_unlock(rq, &rf); + raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags); stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop, &pending->arg, &pending->stop_work); + preempt_enable(); return 0; } out: if (pending) pending->stop_pending = false; - task_rq_unlock(rq, p, &rf); + rq_unlock(rq, &rf); + raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags); if (complete) complete_all(&pending->done); @@ -2510,9 +2626,7 @@ int push_cpu_stop(void *arg) // XXX validate p is still the highest prio task if (task_rq(p) == rq) { - deactivate_task(rq, p, 0); - set_task_cpu(p, lowest_rq->cpu); - activate_task(lowest_rq, p, 0); + move_queued_task_locked(rq, lowest_rq, p); resched_curr(lowest_rq); } @@ -2527,6 +2641,8 @@ out_unlock: return 0; } +static inline void mm_update_cpus_allowed(struct mm_struct *mm, const cpumask_t *affmask); + /* * sched_class::set_cpus_allowed must do the below, but is not required to * actually call this function. @@ -2540,6 +2656,7 @@ void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx cpumask_copy(&p->cpus_mask, ctx->new_mask); p->nr_cpus_allowed = cpumask_weight(ctx->new_mask); + mm_update_cpus_allowed(p->mm, ctx->new_mask); /* * Swap in a new user_cpus_ptr if SCA_USER flag set @@ -2549,55 +2666,17 @@ void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx } static void -__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx) +do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx) { - struct rq *rq = task_rq(p); - bool queued, running; - - /* - * This here violates the locking rules for affinity, since we're only - * supposed to change these variables while holding both rq->lock and - * p->pi_lock. - * - * HOWEVER, it magically works, because ttwu() is the only code that - * accesses these variables under p->pi_lock and only does so after - * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule() - * before finish_task(). - * - * XXX do further audits, this smells like something putrid. - */ - if (ctx->flags & SCA_MIGRATE_DISABLE) - SCHED_WARN_ON(!p->on_cpu); - else - lockdep_assert_held(&p->pi_lock); - - queued = task_on_rq_queued(p); - running = task_current(rq, p); - - if (queued) { - /* - * Because __kthread_bind() calls this on blocked tasks without - * holding rq->lock. - */ - lockdep_assert_rq_held(rq); - dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK); - } - if (running) - put_prev_task(rq, p); - - p->sched_class->set_cpus_allowed(p, ctx); - - if (queued) - enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); - if (running) - set_next_task(rq, p); + scoped_guard (sched_change, p, DEQUEUE_SAVE) + p->sched_class->set_cpus_allowed(p, ctx); } /* * Used for kthread_bind() and select_fallback_rq(), in both cases the user * affinity (if any) should be destroyed too. */ -void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask) { struct affinity_context ac = { .new_mask = new_mask, @@ -2609,7 +2688,8 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) struct rcu_head rcu; }; - __do_set_cpus_allowed(p, &ac); + scoped_guard (__task_rq_lock, p) + do_set_cpus_allowed(p, &ac); /* * Because this is called with p->pi_lock held, it is not possible @@ -2619,16 +2699,6 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu); } -static cpumask_t *alloc_user_cpus_ptr(int node) -{ - /* - * See do_set_cpus_allowed() above for the rcu_head usage. - */ - int size = max_t(int, cpumask_size(), sizeof(struct rcu_head)); - - return kmalloc_node(size, GFP_KERNEL, node); -} - int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node) { @@ -2657,7 +2727,7 @@ int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, * Use pi_lock to protect content of user_cpus_ptr * * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent - * do_set_cpus_allowed(). + * set_cpus_allowed_force(). */ raw_spin_lock_irqsave(&src->pi_lock, flags); if (src->user_cpus_ptr) { @@ -2770,8 +2840,15 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag struct set_affinity_pending my_pending = { }, *pending = NULL; bool stop_pending, complete = false; - /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) { + /* + * Can the task run on the task's current CPU? If so, we're done + * + * We are also done if the task is the current donor, boosting a lock- + * holding proxy, (and potentially has been migrated outside its + * current or previous affinity mask) + */ + if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask) || + (task_current_donor(rq, p) && !task_current(rq, p))) { struct task_struct *push_task = NULL; if ((flags & SCA_MIGRATE_ENABLE) && @@ -2790,12 +2867,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag complete = true; } + preempt_disable(); task_rq_unlock(rq, p, rf); - if (push_task) { stop_one_cpu_nowait(rq->cpu, push_cpu_stop, p, &rq->push_work); } + preempt_enable(); if (complete) complete_all(&pending->done); @@ -2861,12 +2939,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag if (flags & SCA_MIGRATE_ENABLE) p->migration_flags &= ~MDF_PUSH; + preempt_disable(); task_rq_unlock(rq, p, rf); - if (!stop_pending) { stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop, &pending->arg, &pending->stop_work); } + preempt_enable(); if (flags & SCA_MIGRATE_ENABLE) return 0; @@ -2920,8 +2999,6 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p, unsigned int dest_cpu; int ret = 0; - update_rq_clock(rq); - if (kthread || is_migration_disabled(p)) { /* * Kernel threads are allowed on online && !active CPUs, @@ -2951,8 +3028,11 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p, } if (!(ctx->flags & SCA_MIGRATE_ENABLE)) { - if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) + if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) { + if (ctx->flags & SCA_USER) + swap(p->user_cpus_ptr, ctx->user_mask); goto out; + } if (WARN_ON_ONCE(p == current && is_migration_disabled(p) && @@ -2973,7 +3053,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p, goto out; } - __do_set_cpus_allowed(p, ctx); + do_set_cpus_allowed(p, ctx); return affine_move_task(rq, p, rf, dest_cpu, ctx->flags); @@ -2992,8 +3072,7 @@ out: * task must not exit() & deallocate itself prematurely. The * call is not atomic; no spinlocks may be held. */ -static int __set_cpus_allowed_ptr(struct task_struct *p, - struct affinity_context *ctx) +int __set_cpus_allowed_ptr(struct task_struct *p, struct affinity_context *ctx) { struct rq_flags rf; struct rq *rq; @@ -3112,9 +3191,6 @@ out_free_mask: free_cpumask_var(new_mask); } -static int -__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx); - /* * Restore the affinity of a task @p which was previously restricted by a * call to force_compatible_cpus_allowed_ptr(). @@ -3138,9 +3214,10 @@ void relax_compatible_cpus_allowed_ptr(struct task_struct *p) WARN_ON_ONCE(ret); } +#ifdef CONFIG_SMP + void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { -#ifdef CONFIG_SCHED_DEBUG unsigned int state = READ_ONCE(p->__state); /* @@ -3178,7 +3255,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) WARN_ON_ONCE(!cpu_online(new_cpu)); WARN_ON_ONCE(is_migration_disabled(p)); -#endif trace_sched_migrate_task(p, new_cpu); @@ -3186,12 +3262,12 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; - rseq_migrate(p); perf_event_task_migrate(p); } __set_task_cpu(p, new_cpu); } +#endif /* CONFIG_SMP */ #ifdef CONFIG_NUMA_BALANCING static void __migrate_swap_task(struct task_struct *p, int cpu) @@ -3206,10 +3282,8 @@ static void __migrate_swap_task(struct task_struct *p, int cpu) rq_pin_lock(src_rq, &srf); rq_pin_lock(dst_rq, &drf); - deactivate_task(src_rq, p, 0); - set_task_cpu(p, cpu); - activate_task(dst_rq, p, 0); - check_preempt_curr(dst_rq, p, 0); + move_queued_task_locked(src_rq, dst_rq, p); + wakeup_preempt(dst_rq, p, 0); rq_unpin_lock(dst_rq, &drf); rq_unpin_lock(src_rq, &srf); @@ -3233,7 +3307,6 @@ static int migrate_swap_stop(void *data) { struct migration_swap_arg *arg = data; struct rq *src_rq, *dst_rq; - int ret = -EAGAIN; if (!cpu_active(arg->src_cpu) || !cpu_active(arg->dst_cpu)) return -EAGAIN; @@ -3241,33 +3314,25 @@ static int migrate_swap_stop(void *data) src_rq = cpu_rq(arg->src_cpu); dst_rq = cpu_rq(arg->dst_cpu); - double_raw_lock(&arg->src_task->pi_lock, - &arg->dst_task->pi_lock); - double_rq_lock(src_rq, dst_rq); + guard(double_raw_spinlock)(&arg->src_task->pi_lock, &arg->dst_task->pi_lock); + guard(double_rq_lock)(src_rq, dst_rq); if (task_cpu(arg->dst_task) != arg->dst_cpu) - goto unlock; + return -EAGAIN; if (task_cpu(arg->src_task) != arg->src_cpu) - goto unlock; + return -EAGAIN; if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr)) - goto unlock; + return -EAGAIN; if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr)) - goto unlock; + return -EAGAIN; __migrate_swap_task(arg->src_task, arg->dst_cpu); __migrate_swap_task(arg->dst_task, arg->src_cpu); - ret = 0; - -unlock: - double_rq_unlock(src_rq, dst_rq); - raw_spin_unlock(&arg->dst_task->pi_lock); - raw_spin_unlock(&arg->src_task->pi_lock); - - return ret; + return 0; } /* @@ -3310,114 +3375,6 @@ out: } #endif /* CONFIG_NUMA_BALANCING */ -/* - * wait_task_inactive - wait for a thread to unschedule. - * - * Wait for the thread to block in any of the states set in @match_state. - * If it changes, i.e. @p might have woken up, then return zero. When we - * succeed in waiting for @p to be off its CPU, we return a positive number - * (its total switch count). If a second call a short while later returns the - * same number, the caller can be sure that @p has remained unscheduled the - * whole time. - * - * The caller must ensure that the task *will* unschedule sometime soon, - * else this function might spin for a *long* time. This function can't - * be called with interrupts off, or it may introduce deadlock with - * smp_call_function() if an IPI is sent by the same process we are - * waiting to become inactive. - */ -unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) -{ - int running, queued; - struct rq_flags rf; - unsigned long ncsw; - struct rq *rq; - - for (;;) { - /* - * We do the initial early heuristics without holding - * any task-queue locks at all. We'll only try to get - * the runqueue lock when things look like they will - * work out! - */ - rq = task_rq(p); - - /* - * If the task is actively running on another CPU - * still, just relax and busy-wait without holding - * any locks. - * - * NOTE! Since we don't hold any locks, it's not - * even sure that "rq" stays as the right runqueue! - * But we don't care, since "task_on_cpu()" will - * return false if the runqueue has changed and p - * is actually now running somewhere else! - */ - while (task_on_cpu(rq, p)) { - if (!(READ_ONCE(p->__state) & match_state)) - return 0; - cpu_relax(); - } - - /* - * Ok, time to look more closely! We need the rq - * lock now, to be *sure*. If we're wrong, we'll - * just go back and repeat. - */ - rq = task_rq_lock(p, &rf); - trace_sched_wait_task(p); - running = task_on_cpu(rq, p); - queued = task_on_rq_queued(p); - ncsw = 0; - if (READ_ONCE(p->__state) & match_state) - ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ - task_rq_unlock(rq, p, &rf); - - /* - * If it changed from the expected state, bail out now. - */ - if (unlikely(!ncsw)) - break; - - /* - * Was it really running after all now that we - * checked with the proper locks actually held? - * - * Oops. Go back and try again.. - */ - if (unlikely(running)) { - cpu_relax(); - continue; - } - - /* - * It's not enough that it's not actively running, - * it must be off the runqueue _entirely_, and not - * preempted! - * - * So if it was still runnable (but just not actively - * running right now), it's preempted, and we should - * yield - it could be a while. - */ - if (unlikely(queued)) { - ktime_t to = NSEC_PER_SEC / HZ; - - set_current_state(TASK_UNINTERRUPTIBLE); - schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD); - continue; - } - - /* - * Ahh, all good. It wasn't running, and it wasn't - * runnable, which means that it will never become - * running in the future either. We're all done! - */ - break; - } - - return ncsw; -} - /*** * kick_process - kick a running thread to enter/exit the kernel * @p: the to-be-kicked thread @@ -3433,13 +3390,11 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state */ void kick_process(struct task_struct *p) { - int cpu; + guard(preempt)(); + int cpu = task_cpu(p); - preempt_disable(); - cpu = task_cpu(p); if ((cpu != smp_processor_id()) && task_curr(p)) smp_send_reschedule(cpu); - preempt_enable(); } EXPORT_SYMBOL_GPL(kick_process); @@ -3505,13 +3460,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) } fallthrough; case possible: - /* - * XXX When called from select_task_rq() we only - * hold p->pi_lock and again violate locking order. - * - * More yuck to audit. - */ - do_set_cpus_allowed(p, task_cpu_possible_mask(p)); + set_cpus_allowed_force(p, task_cpu_fallback_mask(p)); state = fail; break; case fail: @@ -3540,14 +3489,16 @@ out: * 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 wake_flags) +int select_task_rq(struct task_struct *p, int cpu, int *wake_flags) { lockdep_assert_held(&p->pi_lock); - if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) - cpu = p->sched_class->select_task_rq(p, cpu, wake_flags); - else + if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) { + cpu = p->sched_class->select_task_rq(p, cpu, *wake_flags); + *wake_flags |= WF_RQ_SELECTED; + } else { cpu = cpumask_any(p->cpus_ptr); + } /* * In order not to call set_task_cpu() on a blocking task we need @@ -3610,28 +3561,6 @@ void sched_set_stop_task(int cpu, struct task_struct *stop) } } -#else /* CONFIG_SMP */ - -static inline int __set_cpus_allowed_ptr(struct task_struct *p, - struct affinity_context *ctx) -{ - return set_cpus_allowed_ptr(p, ctx->new_mask); -} - -static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { } - -static inline bool rq_has_pinned_tasks(struct rq *rq) -{ - return false; -} - -static inline cpumask_t *alloc_user_cpus_ptr(int node) -{ - return NULL; -} - -#endif /* !CONFIG_SMP */ - static void ttwu_stat(struct task_struct *p, int cpu, int wake_flags) { @@ -3642,7 +3571,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) rq = this_rq(); -#ifdef CONFIG_SMP if (cpu == rq->cpu) { __schedstat_inc(rq->ttwu_local); __schedstat_inc(p->stats.nr_wakeups_local); @@ -3650,19 +3578,18 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) struct sched_domain *sd; __schedstat_inc(p->stats.nr_wakeups_remote); - rcu_read_lock(); + + guard(rcu)(); for_each_domain(rq->cpu, sd) { if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { __schedstat_inc(sd->ttwu_wake_remote); break; } } - rcu_read_unlock(); } if (wake_flags & WF_MIGRATED) __schedstat_inc(p->stats.nr_wakeups_migrate); -#endif /* CONFIG_SMP */ __schedstat_inc(rq->ttwu_count); __schedstat_inc(p->stats.nr_wakeups); @@ -3672,41 +3599,12 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) } /* - * Mark the task runnable and perform wakeup-preemption. + * Mark the task runnable. */ -static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, - struct rq_flags *rf) +static inline void ttwu_do_wakeup(struct task_struct *p) { - check_preempt_curr(rq, p, wake_flags); WRITE_ONCE(p->__state, TASK_RUNNING); trace_sched_wakeup(p); - -#ifdef CONFIG_SMP - if (p->sched_class->task_woken) { - /* - * Our task @p is fully woken up and running; so it's safe to - * drop the rq->lock, hereafter rq is only used for statistics. - */ - rq_unpin_lock(rq, rf); - p->sched_class->task_woken(rq, p); - rq_repin_lock(rq, rf); - } - - if (rq->idle_stamp) { - u64 delta = rq_clock(rq) - rq->idle_stamp; - u64 max = 2*rq->max_idle_balance_cost; - - update_avg(&rq->avg_idle, delta); - - if (rq->avg_idle > max) - rq->avg_idle = max; - - rq->wake_stamp = jiffies; - rq->wake_avg_idle = rq->avg_idle / 2; - - rq->idle_stamp = 0; - } -#endif } static void @@ -3720,18 +3618,42 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, if (p->sched_contributes_to_load) rq->nr_uninterruptible--; -#ifdef CONFIG_SMP + if (wake_flags & WF_RQ_SELECTED) + en_flags |= ENQUEUE_RQ_SELECTED; if (wake_flags & WF_MIGRATED) en_flags |= ENQUEUE_MIGRATED; else -#endif if (p->in_iowait) { delayacct_blkio_end(p); atomic_dec(&task_rq(p)->nr_iowait); } activate_task(rq, p, en_flags); - ttwu_do_wakeup(rq, p, wake_flags, rf); + wakeup_preempt(rq, p, wake_flags); + + ttwu_do_wakeup(p); + + if (p->sched_class->task_woken) { + /* + * Our task @p is fully woken up and running; so it's safe to + * drop the rq->lock, hereafter rq is only used for statistics. + */ + rq_unpin_lock(rq, rf); + p->sched_class->task_woken(rq, p); + rq_repin_lock(rq, rf); + } + + if (rq->idle_stamp) { + u64 delta = rq_clock(rq) - rq->idle_stamp; + u64 max = 2*rq->max_idle_balance_cost; + + update_avg(&rq->avg_idle, delta); + + if (rq->avg_idle > max) + rq->avg_idle = max; + + rq->idle_stamp = 0; + } } /* @@ -3767,17 +3689,24 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags) rq = __task_rq_lock(p, &rf); if (task_on_rq_queued(p)) { - /* check_preempt_curr() may use rq clock */ update_rq_clock(rq); - ttwu_do_wakeup(rq, p, wake_flags, &rf); + if (p->se.sched_delayed) + enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED); + if (!task_on_cpu(rq, p)) { + /* + * When on_rq && !on_cpu the task is preempted, see if + * it should preempt the task that is current now. + */ + wakeup_preempt(rq, p, wake_flags); + } + ttwu_do_wakeup(p); ret = 1; } - __task_rq_unlock(rq, &rf); + __task_rq_unlock(rq, p, &rf); return ret; } -#ifdef CONFIG_SMP void sched_ttwu_pending(void *arg) { struct llist_node *llist = arg; @@ -3807,22 +3736,28 @@ void sched_ttwu_pending(void *arg) * it is possible for select_idle_siblings() to stack a number * of tasks on this CPU during that window. * - * It is ok to clear ttwu_pending when another task pending. - * We will receive IPI after local irq enabled and then enqueue it. + * It is OK to clear ttwu_pending when another task pending. + * We will receive IPI after local IRQ enabled and then enqueue it. * Since now nr_running > 0, idle_cpu() will always get correct result. */ WRITE_ONCE(rq->ttwu_pending, 0); rq_unlock_irqrestore(rq, &rf); } -void send_call_function_single_ipi(int cpu) +/* + * Prepare the scene for sending an IPI for a remote smp_call + * + * Returns true if the caller can proceed with sending the IPI. + * Returns false otherwise. + */ +bool call_function_single_prep_ipi(int cpu) { - struct rq *rq = cpu_rq(cpu); - - if (!set_nr_if_polling(rq->idle)) - arch_send_call_function_single_ipi(cpu); - else + if (set_nr_if_polling(cpu_rq(cpu)->idle)) { trace_sched_wake_idle_without_ipi(cpu); + return false; + } + + return true; } /* @@ -3838,27 +3773,32 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED); WRITE_ONCE(rq->ttwu_pending, 1); +#ifdef CONFIG_SMP __smp_call_single_queue(cpu, &p->wake_entry.llist); +#endif } void wake_up_if_idle(int cpu) { struct rq *rq = cpu_rq(cpu); - struct rq_flags rf; - rcu_read_lock(); + guard(rcu)(); + if (is_idle_task(rcu_dereference(rq->curr))) { + guard(rq_lock_irqsave)(rq); + if (is_idle_task(rq->curr)) + resched_curr(rq); + } +} - if (!is_idle_task(rcu_dereference(rq->curr))) - goto out; +bool cpus_equal_capacity(int this_cpu, int that_cpu) +{ + if (!sched_asym_cpucap_active()) + return true; - rq_lock_irqsave(rq, &rf); - if (is_idle_task(rq->curr)) - resched_curr(rq); - /* Else CPU is not idle, do nothing here: */ - rq_unlock_irqrestore(rq, &rf); + if (this_cpu == that_cpu) + return true; -out: - rcu_read_unlock(); + return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu); } bool cpus_share_cache(int this_cpu, int that_cpu) @@ -3869,8 +3809,29 @@ 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); } +/* + * Whether CPUs are share cache resources, which means LLC on non-cluster + * machines and LLC tag or L2 on machines with clusters. + */ +bool cpus_share_resources(int this_cpu, int that_cpu) +{ + if (this_cpu == that_cpu) + return true; + + return per_cpu(sd_share_id, this_cpu) == per_cpu(sd_share_id, that_cpu); +} + static inline bool ttwu_queue_cond(struct task_struct *p, int cpu) { + /* See SCX_OPS_ALLOW_QUEUED_WAKEUP. */ + if (!scx_allow_ttwu_queue(p)) + return false; + +#ifdef CONFIG_SMP + if (p->sched_class == &stop_sched_class) + return false; +#endif + /* * Do not complicate things with the async wake_list while the CPU is * in hotplug state. @@ -3920,15 +3881,6 @@ static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags) return false; } -#else /* !CONFIG_SMP */ - -static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags) -{ - return false; -} - -#endif /* CONFIG_SMP */ - static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); @@ -3949,34 +3901,37 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * The caller holds p::pi_lock if p != current or has preemption * disabled when p == current. * - * The rules of PREEMPT_RT saved_state: + * The rules of saved_state: * * The related locking code always holds p::pi_lock when updating * p::saved_state, which means the code is fully serialized in both cases. * - * The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other - * bits set. This allows to distinguish all wakeup scenarios. + * For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. + * No other bits set. This allows to distinguish all wakeup scenarios. + * + * For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This + * allows us to prevent early wakeup of tasks before they can be run on + * asymmetric ISA architectures (eg ARMv9). */ static __always_inline bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success) { + int match; + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) { WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) && state != TASK_RTLOCK_WAIT); } - if (READ_ONCE(p->__state) & state) { - *success = 1; - return true; - } + *success = !!(match = __task_state_match(p, state)); -#ifdef CONFIG_PREEMPT_RT /* * Saved state preserves the task state across blocking on - * an RT lock. If the state matches, set p::saved_state to - * TASK_RUNNING, but do not wake the task because it waits - * for a lock wakeup. Also indicate success because from - * the regular waker's point of view this has succeeded. + * an RT lock or TASK_FREEZABLE tasks. If the state matches, + * set p::saved_state to TASK_RUNNING, but do not wake the task + * because it waits for a lock wakeup or __thaw_task(). Also + * indicate success because from the regular waker's point of + * view this has succeeded. * * After acquiring the lock the task will restore p::__state * from p::saved_state which ensures that the regular @@ -3984,12 +3939,10 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success) * p::saved_state to TASK_RUNNING so any further tests will * not result in false positives vs. @success */ - if (p->saved_state & state) { + if (match < 0) p->saved_state = TASK_RUNNING; - *success = 1; - } -#endif - return false; + + return match > 0; } /* @@ -4112,13 +4065,13 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success) * Return: %true if @p->state changes (an actual wakeup was done), * %false otherwise. */ -static int -try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) +int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) { - unsigned long flags; + guard(preempt)(); int cpu, success = 0; - preempt_disable(); + wake_flags |= WF_TTWU; + if (p == current) { /* * We're waking current, this means 'p->on_rq' and 'task_cpu(p) @@ -4126,17 +4079,21 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * case the whole 'p->on_rq && ttwu_runnable()' case below * without taking any locks. * + * Specifically, given current runs ttwu() we must be before + * schedule()'s block_task(), as such this must not observe + * sched_delayed. + * * 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). */ + WARN_ON_ONCE(p->se.sched_delayed); if (!ttwu_state_match(p, state, &success)) goto out; trace_sched_waking(p); - WRITE_ONCE(p->__state, TASK_RUNNING); - trace_sched_wakeup(p); + ttwu_do_wakeup(p); goto out; } @@ -4146,129 +4103,123 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * reordered with p->state check below. This pairs with smp_store_mb() * in set_current_state() that the waiting thread does. */ - raw_spin_lock_irqsave(&p->pi_lock, flags); - smp_mb__after_spinlock(); - if (!ttwu_state_match(p, state, &success)) - goto unlock; + scoped_guard (raw_spinlock_irqsave, &p->pi_lock) { + smp_mb__after_spinlock(); + if (!ttwu_state_match(p, state, &success)) + break; - trace_sched_waking(p); + trace_sched_waking(p); - /* - * Ensure we load p->on_rq _after_ p->state, otherwise it would - * be possible to, falsely, observe p->on_rq == 0 and get stuck - * in smp_cond_load_acquire() below. - * - * sched_ttwu_pending() try_to_wake_up() - * STORE p->on_rq = 1 LOAD p->state - * UNLOCK rq->lock - * - * __schedule() (switch to task 'p') - * LOCK rq->lock smp_rmb(); - * smp_mb__after_spinlock(); - * UNLOCK rq->lock - * - * [task p] - * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq - * - * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in - * __schedule(). See the comment for smp_mb__after_spinlock(). - * - * A similar smb_rmb() lives in try_invoke_on_locked_down_task(). - */ - smp_rmb(); - if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags)) - goto unlock; + /* + * Ensure we load p->on_rq _after_ p->state, otherwise it would + * be possible to, falsely, observe p->on_rq == 0 and get stuck + * in smp_cond_load_acquire() below. + * + * sched_ttwu_pending() try_to_wake_up() + * STORE p->on_rq = 1 LOAD p->state + * UNLOCK rq->lock + * + * __schedule() (switch to task 'p') + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * UNLOCK rq->lock + * + * [task p] + * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq + * + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). + * + * A similar smp_rmb() lives in __task_needs_rq_lock(). + */ + smp_rmb(); + if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags)) + break; -#ifdef CONFIG_SMP - /* - * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be - * possible to, falsely, observe p->on_cpu == 0. - * - * One must be running (->on_cpu == 1) in order to remove oneself - * from the runqueue. - * - * __schedule() (switch to task 'p') try_to_wake_up() - * STORE p->on_cpu = 1 LOAD p->on_rq - * UNLOCK rq->lock - * - * __schedule() (put 'p' to sleep) - * LOCK rq->lock smp_rmb(); - * smp_mb__after_spinlock(); - * STORE p->on_rq = 0 LOAD p->on_cpu - * - * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in - * __schedule(). See the comment for smp_mb__after_spinlock(). - * - * Form a control-dep-acquire with p->on_rq == 0 above, to ensure - * schedule()'s deactivate_task() has 'happened' and p will no longer - * care about it's own p->state. See the comment in __schedule(). - */ - smp_acquire__after_ctrl_dep(); + /* + * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be + * possible to, falsely, observe p->on_cpu == 0. + * + * One must be running (->on_cpu == 1) in order to remove oneself + * from the runqueue. + * + * __schedule() (switch to task 'p') try_to_wake_up() + * STORE p->on_cpu = 1 LOAD p->on_rq + * UNLOCK rq->lock + * + * __schedule() (put 'p' to sleep) + * LOCK rq->lock smp_rmb(); + * smp_mb__after_spinlock(); + * STORE p->on_rq = 0 LOAD p->on_cpu + * + * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in + * __schedule(). See the comment for smp_mb__after_spinlock(). + * + * Form a control-dep-acquire with p->on_rq == 0 above, to ensure + * schedule()'s block_task() has 'happened' and p will no longer + * care about it's own p->state. See the comment in __schedule(). + */ + smp_acquire__after_ctrl_dep(); - /* - * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq - * == 0), which means we need to do an enqueue, change p->state to - * TASK_WAKING such that we can unlock p->pi_lock before doing the - * enqueue, such as ttwu_queue_wakelist(). - */ - WRITE_ONCE(p->__state, TASK_WAKING); + /* + * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq + * == 0), which means we need to do an enqueue, change p->state to + * TASK_WAKING such that we can unlock p->pi_lock before doing the + * enqueue, such as ttwu_queue_wakelist(). + */ + WRITE_ONCE(p->__state, TASK_WAKING); - /* - * If the owning (remote) CPU is still in the middle of schedule() with - * this task as prev, considering queueing p on the remote CPUs wake_list - * which potentially sends an IPI instead of spinning on p->on_cpu to - * let the waker make forward progress. This is safe because IRQs are - * disabled and the IPI will deliver after on_cpu is cleared. - * - * Ensure we load task_cpu(p) after p->on_cpu: - * - * set_task_cpu(p, cpu); - * STORE p->cpu = @cpu - * __schedule() (switch to task 'p') - * LOCK rq->lock - * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu) - * STORE p->on_cpu = 1 LOAD p->cpu - * - * to ensure we observe the correct CPU on which the task is currently - * scheduling. - */ - if (smp_load_acquire(&p->on_cpu) && - ttwu_queue_wakelist(p, task_cpu(p), wake_flags)) - goto unlock; + /* + * If the owning (remote) CPU is still in the middle of schedule() with + * this task as prev, considering queueing p on the remote CPUs wake_list + * which potentially sends an IPI instead of spinning on p->on_cpu to + * let the waker make forward progress. This is safe because IRQs are + * disabled and the IPI will deliver after on_cpu is cleared. + * + * Ensure we load task_cpu(p) after p->on_cpu: + * + * set_task_cpu(p, cpu); + * STORE p->cpu = @cpu + * __schedule() (switch to task 'p') + * LOCK rq->lock + * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu) + * STORE p->on_cpu = 1 LOAD p->cpu + * + * to ensure we observe the correct CPU on which the task is currently + * scheduling. + */ + if (smp_load_acquire(&p->on_cpu) && + ttwu_queue_wakelist(p, task_cpu(p), wake_flags)) + break; - /* - * If the owning (remote) CPU is still in the middle of schedule() with - * this task as prev, wait until it's done referencing the task. - * - * Pairs with the smp_store_release() in finish_task(). - * - * This ensures that tasks getting woken will be fully ordered against - * their previous state and preserve Program Order. - */ - smp_cond_load_acquire(&p->on_cpu, !VAL); + /* + * If the owning (remote) CPU is still in the middle of schedule() with + * this task as prev, wait until it's done referencing the task. + * + * Pairs with the smp_store_release() in finish_task(). + * + * This ensures that tasks getting woken will be fully ordered against + * their previous state and preserve Program Order. + */ + smp_cond_load_acquire(&p->on_cpu, !VAL); - cpu = select_task_rq(p, p->wake_cpu, wake_flags | WF_TTWU); - if (task_cpu(p) != cpu) { - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); + cpu = select_task_rq(p, p->wake_cpu, &wake_flags); + if (task_cpu(p) != cpu) { + if (p->in_iowait) { + delayacct_blkio_end(p); + atomic_dec(&task_rq(p)->nr_iowait); + } + + wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); + set_task_cpu(p, cpu); } - wake_flags |= WF_MIGRATED; - psi_ttwu_dequeue(p); - set_task_cpu(p, cpu); + ttwu_queue(p, cpu, wake_flags); } -#else - cpu = task_cpu(p); -#endif /* CONFIG_SMP */ - - ttwu_queue(p, cpu, wake_flags); -unlock: - raw_spin_unlock_irqrestore(&p->pi_lock, flags); out: if (success) ttwu_stat(p, task_cpu(p), wake_flags); - preempt_enable(); return success; } @@ -4295,14 +4246,12 @@ static bool __task_needs_rq_lock(struct task_struct *p) if (p->on_rq) return true; -#ifdef CONFIG_SMP /* * Ensure the task has finished __schedule() and will not be referenced * anymore. Again, see try_to_wake_up() for a longer comment. */ smp_rmb(); smp_cond_load_acquire(&p->on_cpu, !VAL); -#endif return false; } @@ -4314,9 +4263,10 @@ static bool __task_needs_rq_lock(struct task_struct *p) * @arg: Argument to function. * * Fix the task in it's current state by avoiding wakeups and or rq operations - * and call @func(@arg) on it. This function can use ->on_rq and task_curr() - * to work out what the state is, if required. Given that @func can be invoked - * with a runqueue lock held, it had better be quite lightweight. + * and call @func(@arg) on it. This function can use task_is_runnable() and + * task_curr() to work out what the state is, if required. Given that @func + * can be invoked with a runqueue lock held, it had better be quite + * lightweight. * * Returns: * Whatever @func returns @@ -4345,7 +4295,7 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg) ret = func(p, arg); if (rq) - rq_unlock(rq, &rf); + __task_rq_unlock(rq, p, &rf); raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags); return ret; @@ -4356,12 +4306,7 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg) * @cpu: The CPU on which to snapshot the task. * * Returns the task_struct pointer of the task "currently" running on - * the specified CPU. If the same task is running on that CPU throughout, - * the return value will be a pointer to that task's task_struct structure. - * If the CPU did any context switches even vaguely concurrently with the - * execution of this function, the return value will be a pointer to the - * task_struct structure of a randomly chosen task that was running on - * that CPU somewhere around the time that this function was executing. + * the specified CPU. * * If the specified CPU was offline, the return value is whatever it * is, perhaps a pointer to the task_struct structure of that CPU's idle @@ -4375,11 +4320,16 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg) */ struct task_struct *cpu_curr_snapshot(int cpu) { + struct rq *rq = cpu_rq(cpu); struct task_struct *t; + struct rq_flags rf; - smp_mb(); /* Pairing determined by caller's synchronization design. */ + rq_lock_irqsave(rq, &rf); + smp_mb__after_spinlock(); /* Pairing determined by caller's synchronization design. */ t = rcu_dereference(cpu_curr(cpu)); + rq_unlock_irqrestore(rq, &rf); smp_mb(); /* Pairing determined by caller's synchronization design. */ + return t; } @@ -4409,9 +4359,10 @@ int wake_up_state(struct task_struct *p, unsigned int state) * Perform scheduler related setup for a newly forked process p. * p is forked by current. * - * __sched_fork() is basic setup used by init_idle() too: + * __sched_fork() is basic setup which is also used by sched_init() to + * initialize the boot CPU's idle task. */ -static void __sched_fork(unsigned long clone_flags, struct task_struct *p) +static void __sched_fork(u64 clone_flags, struct task_struct *p) { p->on_rq = 0; @@ -4421,10 +4372,17 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; p->se.vruntime = 0; + p->se.vlag = 0; INIT_LIST_HEAD(&p->se.group_node); + /* A delayed task cannot be in clone(). */ + WARN_ON_ONCE(p->se.sched_delayed); + #ifdef CONFIG_FAIR_GROUP_SCHED p->se.cfs_rq = NULL; +#ifdef CONFIG_CFS_BANDWIDTH + init_cfs_throttle_work(p); +#endif #endif #ifdef CONFIG_SCHEDSTATS @@ -4432,10 +4390,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) memset(&p->stats, 0, sizeof(p->stats)); #endif - RB_CLEAR_NODE(&p->dl.rb_node); - init_dl_task_timer(&p->dl); - init_dl_inactive_task_timer(&p->dl); - __dl_clear_params(p); + init_dl_entity(&p->dl); INIT_LIST_HEAD(&p->rt.run_list); p->rt.timeout = 0; @@ -4443,6 +4398,10 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->rt.on_rq = 0; p->rt.on_list = 0; +#ifdef CONFIG_SCHED_CLASS_EXT + init_scx_entity(&p->scx); +#endif + #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); #endif @@ -4451,10 +4410,8 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->capture_control = NULL; #endif init_numa_balancing(clone_flags, p); -#ifdef CONFIG_SMP p->wake_entry.u_flags = CSD_TYPE_TTWU; p->migration_pending = NULL; -#endif } DEFINE_STATIC_KEY_FALSE(sched_numa_balancing); @@ -4492,7 +4449,7 @@ static void reset_memory_tiering(void) } } -static int sysctl_numa_balancing(struct ctl_table *table, int write, +static int sysctl_numa_balancing(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -4516,8 +4473,8 @@ static int sysctl_numa_balancing(struct ctl_table *table, int write, } return err; } -#endif -#endif +#endif /* CONFIG_PROC_SYSCTL */ +#endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_SCHEDSTATS @@ -4561,7 +4518,7 @@ out: __setup("schedstats=", setup_schedstats); #ifdef CONFIG_PROC_SYSCTL -static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, +static int sysctl_schedstats(const struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; @@ -4584,7 +4541,7 @@ static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, #endif /* CONFIG_SCHEDSTATS */ #ifdef CONFIG_SYSCTL -static struct ctl_table sched_core_sysctls[] = { +static const struct ctl_table sched_core_sysctls[] = { #ifdef CONFIG_SCHEDSTATS { .procname = "sched_schedstats", @@ -4630,7 +4587,6 @@ static struct ctl_table sched_core_sysctls[] = { .extra2 = SYSCTL_FOUR, }, #endif /* CONFIG_NUMA_BALANCING */ - {} }; static int __init sched_core_sysctl_init(void) { @@ -4643,7 +4599,7 @@ late_initcall(sched_core_sysctl_init); /* * fork()/clone()-time setup: */ -int sched_fork(unsigned long clone_flags, struct task_struct *p) +int sched_fork(u64 clone_flags, struct task_struct *p) { __sched_fork(clone_flags, p); /* @@ -4673,6 +4629,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->prio = p->normal_prio = p->static_prio; set_load_weight(p, false); + p->se.custom_slice = 0; + p->se.slice = sysctl_sched_base_slice; /* * We don't need the reset flag anymore after the fork. It has @@ -4683,10 +4641,18 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) if (dl_prio(p->prio)) return -EAGAIN; - else if (rt_prio(p->prio)) + + scx_pre_fork(p); + + if (rt_prio(p->prio)) { p->sched_class = &rt_sched_class; - else +#ifdef CONFIG_SCHED_CLASS_EXT + } else if (task_should_scx(p->policy)) { + p->sched_class = &ext_sched_class; +#endif + } else { p->sched_class = &fair_sched_class; + } init_entity_runnable_average(&p->se); @@ -4695,18 +4661,15 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); #endif -#if defined(CONFIG_SMP) p->on_cpu = 0; -#endif init_task_preempt_count(p); -#ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); RB_CLEAR_NODE(&p->pushable_dl_tasks); -#endif + return 0; } -void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) +int sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) { unsigned long flags; @@ -4724,7 +4687,6 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) p->sched_task_group = tg; } #endif - rseq_migrate(p); /* * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). @@ -4733,11 +4695,19 @@ void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) if (p->sched_class->task_fork) p->sched_class->task_fork(p); raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + return scx_fork(p); +} + +void sched_cancel_fork(struct task_struct *p) +{ + scx_cancel_fork(p); } void sched_post_fork(struct task_struct *p) { uclamp_post_fork(p); + scx_post_fork(p); } unsigned long to_ratio(u64 period, u64 runtime) @@ -4767,10 +4737,10 @@ void wake_up_new_task(struct task_struct *p) { struct rq_flags rf; struct rq *rq; + int wake_flags = WF_FORK; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); WRITE_ONCE(p->__state, TASK_RUNNING); -#ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: * - cpus_ptr can change in the fork path @@ -4780,17 +4750,14 @@ void wake_up_new_task(struct task_struct *p) * as we're not fully set-up yet. */ p->recent_used_cpu = task_cpu(p); - rseq_migrate(p); - __set_task_cpu(p, select_task_rq(p, task_cpu(p), WF_FORK)); -#endif + __set_task_cpu(p, select_task_rq(p, task_cpu(p), &wake_flags)); rq = __task_rq_lock(p, &rf); update_rq_clock(rq); post_init_entity_util_avg(p); - activate_task(rq, p, ENQUEUE_NOCLOCK); + activate_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_INITIAL); trace_sched_wakeup_new(p); - check_preempt_curr(rq, p, WF_FORK); -#ifdef CONFIG_SMP + wakeup_preempt(rq, p, wake_flags); if (p->sched_class->task_woken) { /* * Nothing relies on rq->lock after this, so it's fine to @@ -4800,7 +4767,6 @@ void wake_up_new_task(struct task_struct *p) p->sched_class->task_woken(rq, p); rq_repin_lock(rq, &rf); } -#endif task_rq_unlock(rq, p, &rf); } @@ -4877,7 +4843,7 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, __fire_sched_out_preempt_notifiers(curr, next); } -#else /* !CONFIG_PREEMPT_NOTIFIERS */ +#else /* !CONFIG_PREEMPT_NOTIFIERS: */ static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr) { @@ -4889,11 +4855,10 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, { } -#endif /* CONFIG_PREEMPT_NOTIFIERS */ +#endif /* !CONFIG_PREEMPT_NOTIFIERS */ static inline void prepare_task(struct task_struct *next) { -#ifdef CONFIG_SMP /* * Claim the task as running, we do this before switching to it * such that any running task will have this set. @@ -4902,12 +4867,10 @@ static inline void prepare_task(struct task_struct *next) * its ordering comment. */ WRITE_ONCE(next->on_cpu, 1); -#endif } static inline void finish_task(struct task_struct *prev) { -#ifdef CONFIG_SMP /* * This must be the very last reference to @prev from this CPU. After * p->on_cpu is cleared, the task can be moved to a different CPU. We @@ -4920,11 +4883,8 @@ static inline void finish_task(struct task_struct *prev) * Pairs with the smp_cond_load_acquire() in try_to_wake_up(). */ smp_store_release(&prev->on_cpu, 0); -#endif } -#ifdef CONFIG_SMP - static void do_balance_callbacks(struct rq *rq, struct balance_callback *head) { void (*func)(struct rq *rq); @@ -4985,7 +4945,7 @@ __splice_balance_callbacks(struct rq *rq, bool split) return head; } -static inline struct balance_callback *splice_balance_callbacks(struct rq *rq) +struct balance_callback *splice_balance_callbacks(struct rq *rq) { return __splice_balance_callbacks(rq, true); } @@ -4995,7 +4955,7 @@ static void __balance_callbacks(struct rq *rq) do_balance_callbacks(rq, __splice_balance_callbacks(rq, false)); } -static inline void balance_callbacks(struct rq *rq, struct balance_callback *head) +void balance_callbacks(struct rq *rq, struct balance_callback *head) { unsigned long flags; @@ -5006,23 +4966,6 @@ static inline void balance_callbacks(struct rq *rq, struct balance_callback *hea } } -#else - -static inline void __balance_callbacks(struct rq *rq) -{ -} - -static inline struct balance_callback *splice_balance_callbacks(struct rq *rq) -{ - return NULL; -} - -static inline void balance_callbacks(struct rq *rq, struct balance_callback *head) -{ -} - -#endif - static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf) { @@ -5100,7 +5043,6 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, kcov_prepare_switch(prev); sched_info_switch(rq, prev, next); perf_event_task_sched_out(prev, next); - rseq_preempt(prev); fire_sched_out_preempt_notifiers(prev, next); kmap_local_sched_out(); prepare_task(next); @@ -5123,7 +5065,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, * * The context switch have flipped the stack from under us and restored the * local variables which were saved when this task called schedule() in the - * past. prev == current is still correct but we need to recalculate this_rq + * past. 'prev == current' is still correct but we need to recalculate this_rq * because prev may have moved to another CPU. */ static struct rq *finish_task_switch(struct task_struct *prev) @@ -5189,17 +5131,26 @@ static struct rq *finish_task_switch(struct task_struct *prev) * rq->curr, before returning to userspace, so provide them here: * * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly - * provided by mmdrop(), + * provided by mmdrop_lazy_tlb(), * - a sync_core for SYNC_CORE. */ if (mm) { membarrier_mm_sync_core_before_usermode(mm); - mmdrop_sched(mm); + mmdrop_lazy_tlb_sched(mm); } + if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); + /* + * sched_ext_dead() must come before cgroup_task_dead() to + * prevent cgroups from being removed while its member tasks are + * visible to SCX schedulers. + */ + sched_ext_dead(prev); + cgroup_task_dead(prev); + /* Task is done with its stack. */ put_task_stack(prev); @@ -5226,6 +5177,12 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) */ finish_task_switch(prev); + /* + * This is a special case: the newly created task has just + * switched the context for the first time. It is returning from + * schedule for the first time in this path. + */ + trace_sched_exit_tp(true); preempt_enable(); if (current->set_child_tid) @@ -5252,20 +5209,20 @@ context_switch(struct rq *rq, struct task_struct *prev, /* * kernel -> kernel lazy + transfer active - * user -> kernel lazy + mmgrab() active + * user -> kernel lazy + mmgrab_lazy_tlb() active * - * kernel -> user switch + mmdrop() active + * kernel -> user switch + mmdrop_lazy_tlb() active * user -> user switch */ - if (!next->mm) { // to kernel + if (!next->mm) { // to kernel enter_lazy_tlb(prev->active_mm, next); next->active_mm = prev->active_mm; - if (prev->mm) // from user - mmgrab(prev->active_mm); + if (prev->mm) // from user + mmgrab_lazy_tlb(prev->active_mm); else prev->active_mm = NULL; - } else { // to user + } else { // to user membarrier_switch_mm(rq, prev->active_mm, next->mm); /* * sys_membarrier() requires an smp_mb() between setting @@ -5278,14 +5235,20 @@ context_switch(struct rq *rq, struct task_struct *prev, switch_mm_irqs_off(prev->active_mm, next->mm, next); lru_gen_use_mm(next->mm); - if (!prev->mm) { // from kernel - /* will mmdrop() in finish_task_switch(). */ + if (!prev->mm) { // from kernel + /* will mmdrop_lazy_tlb() in finish_task_switch(). */ rq->prev_mm = prev->active_mm; prev->active_mm = NULL; } } - rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); + mm_cid_switch_to(prev, next); + + /* + * Tell rseq that the task was scheduled in. Must be after + * switch_mm_cid() to get the TIF flag set. + */ + rseq_sched_switch_event(next); prepare_lock_switch(rq, next, rf); @@ -5331,6 +5294,11 @@ bool single_task_running(void) } EXPORT_SYMBOL(single_task_running); +unsigned long long nr_context_switches_cpu(int cpu) +{ + return cpu_rq(cpu)->nr_switches; +} + unsigned long long nr_context_switches(void) { int i; @@ -5394,8 +5362,6 @@ unsigned int nr_iowait(void) return sum; } -#ifdef CONFIG_SMP - /* * sched_exec - execve() is a valuable balancing opportunity, because at * this point the task has the smallest effective memory and cache footprint. @@ -5403,27 +5369,22 @@ unsigned int nr_iowait(void) void sched_exec(void) { struct task_struct *p = current; - unsigned long flags; + struct migration_arg arg; int dest_cpu; - raw_spin_lock_irqsave(&p->pi_lock, flags); - dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), WF_EXEC); - if (dest_cpu == smp_processor_id()) - goto unlock; + scoped_guard (raw_spinlock_irqsave, &p->pi_lock) { + dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), WF_EXEC); + if (dest_cpu == smp_processor_id()) + return; - if (likely(cpu_active(dest_cpu))) { - struct migration_arg arg = { p, dest_cpu }; + if (unlikely(!cpu_active(dest_cpu))) + return; - raw_spin_unlock_irqrestore(&p->pi_lock, flags); - stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); - return; + arg = (struct migration_arg){ p, dest_cpu }; } -unlock: - raw_spin_unlock_irqrestore(&p->pi_lock, flags); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); } -#endif - DEFINE_PER_CPU(struct kernel_stat, kstat); DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat); @@ -5439,9 +5400,9 @@ EXPORT_PER_CPU_SYMBOL(kernel_cpustat); static inline void prefetch_curr_exec_start(struct task_struct *p) { #ifdef CONFIG_FAIR_GROUP_SCHED - struct sched_entity *curr = (&p->se)->cfs_rq->curr; + struct sched_entity *curr = p->se.cfs_rq->curr; #else - struct sched_entity *curr = (&task_rq(p)->cfs)->curr; + struct sched_entity *curr = task_rq(p)->cfs.curr; #endif prefetch(curr); prefetch(&curr->exec_start); @@ -5458,11 +5419,11 @@ unsigned long long task_sched_runtime(struct task_struct *p) struct rq *rq; u64 ns; -#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) +#ifdef CONFIG_64BIT /* * 64-bit doesn't need locks to atomically read a 64-bit value. * So we have a optimization chance when the task's delta_exec is 0. - * Reading ->on_cpu is racy, but this is ok. + * Reading ->on_cpu is racy, but this is OK. * * If we race with it leaving CPU, we'll take a lock. So we're correct. * If we race with it entering CPU, unaccounted time is 0. This is @@ -5480,7 +5441,7 @@ unsigned long long task_sched_runtime(struct task_struct *p) * project cycles that may never be accounted to this * thread, breaking clock_gettime(). */ - if (task_current(rq, p) && task_on_rq_queued(p)) { + if (task_current_donor(rq, p) && task_on_rq_queued(p)) { prefetch_curr_exec_start(p); update_rq_clock(rq); p->sched_class->update_curr(rq); @@ -5491,7 +5452,6 @@ unsigned long long task_sched_runtime(struct task_struct *p) return ns; } -#ifdef CONFIG_SCHED_DEBUG static u64 cpu_resched_latency(struct rq *rq) { int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms); @@ -5536,38 +5496,44 @@ static int __init setup_resched_latency_warn_ms(char *str) return 1; } __setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms); -#else -static inline u64 cpu_resched_latency(struct rq *rq) { return 0; } -#endif /* CONFIG_SCHED_DEBUG */ /* * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. */ -void scheduler_tick(void) +void sched_tick(void) { int cpu = smp_processor_id(); struct rq *rq = cpu_rq(cpu); - struct task_struct *curr = rq->curr; + /* accounting goes to the donor task */ + struct task_struct *donor; struct rq_flags rf; - unsigned long thermal_pressure; + unsigned long hw_pressure; u64 resched_latency; - if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) arch_scale_freq_tick(); sched_clock_tick(); rq_lock(rq, &rf); + donor = rq->donor; + + psi_account_irqtime(rq, donor, NULL); update_rq_clock(rq); - thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq)); - update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure); - curr->sched_class->task_tick(rq, curr, 0); + hw_pressure = arch_scale_hw_pressure(cpu_of(rq)); + update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure); + + if (dynamic_preempt_lazy() && tif_test_bit(TIF_NEED_RESCHED_LAZY)) + resched_curr(rq); + + donor->sched_class->task_tick(rq, donor, 0); if (sched_feat(LATENCY_WARN)) resched_latency = cpu_resched_latency(rq); calc_global_load_tick(rq); sched_core_tick(rq); + scx_tick(rq); rq_unlock(rq, &rf); @@ -5576,10 +5542,13 @@ void scheduler_tick(void) perf_event_task_tick(); -#ifdef CONFIG_SMP - rq->idle_balance = idle_cpu(cpu); - trigger_load_balance(rq); -#endif + if (donor->flags & PF_WQ_WORKER) + wq_worker_tick(donor); + + if (!scx_switched_all()) { + rq->idle_balance = idle_cpu(cpu); + sched_balance_trigger(rq); + } } #ifdef CONFIG_NO_HZ_FULL @@ -5625,9 +5594,6 @@ static void sched_tick_remote(struct work_struct *work) struct tick_work *twork = container_of(dwork, struct tick_work, work); int cpu = twork->cpu; struct rq *rq = cpu_rq(cpu); - struct task_struct *curr; - struct rq_flags rf; - u64 delta; int os; /* @@ -5637,30 +5603,32 @@ static void sched_tick_remote(struct work_struct *work) * statistics and checks timeslices in a time-independent way, regardless * of when exactly it is running. */ - if (!tick_nohz_tick_stopped_cpu(cpu)) - goto out_requeue; - - rq_lock_irq(rq, &rf); - curr = rq->curr; - if (cpu_is_offline(cpu)) - goto out_unlock; + if (tick_nohz_tick_stopped_cpu(cpu)) { + guard(rq_lock_irq)(rq); + struct task_struct *curr = rq->curr; - update_rq_clock(rq); + if (cpu_online(cpu)) { + /* + * Since this is a remote tick for full dynticks mode, + * we are always sure that there is no proxy (only a + * single task is running). + */ + WARN_ON_ONCE(rq->curr != rq->donor); + update_rq_clock(rq); + + if (!is_idle_task(curr)) { + /* + * Make sure the next tick runs within a + * reasonable amount of time. + */ + u64 delta = rq_clock_task(rq) - curr->se.exec_start; + WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 30); + } + curr->sched_class->task_tick(rq, curr, 0); - if (!is_idle_task(curr)) { - /* - * Make sure the next tick runs within a reasonable - * amount of time. - */ - delta = rq_clock_task(rq) - curr->se.exec_start; - WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3); + calc_load_nohz_remote(rq); + } } - curr->sched_class->task_tick(rq, curr, 0); - - calc_load_nohz_remote(rq); -out_unlock: - rq_unlock_irq(rq, &rf); -out_requeue: /* * Run the remote tick once per second (1Hz). This arbitrary @@ -5679,7 +5647,7 @@ static void sched_tick_start(int cpu) int os; struct tick_work *twork; - if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -5700,7 +5668,7 @@ static void sched_tick_stop(int cpu) struct tick_work *twork; int os; - if (housekeeping_cpu(cpu, HK_TYPE_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_KERNEL_NOISE)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -5720,10 +5688,10 @@ int __init sched_tick_offload_init(void) return 0; } -#else /* !CONFIG_NO_HZ_FULL */ +#else /* !CONFIG_NO_HZ_FULL: */ static inline void sched_tick_start(int cpu) { } static inline void sched_tick_stop(int cpu) { } -#endif +#endif /* !CONFIG_NO_HZ_FULL */ #if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \ defined(CONFIG_TRACE_PREEMPT_TOGGLE)) @@ -5828,8 +5796,7 @@ static noinline void __schedule_bug(struct task_struct *prev) print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); - if (IS_ENABLED(CONFIG_DEBUG_PREEMPT) - && in_atomic_preempt_off()) { + if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) { pr_err("Preemption disabled at:"); print_ip_sym(KERN_ERR, preempt_disable_ip); } @@ -5866,18 +5833,19 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt) preempt_count_set(PREEMPT_DISABLED); } rcu_sleep_check(); - SCHED_WARN_ON(ct_state() == CONTEXT_USER); + WARN_ON_ONCE(ct_state() == CT_STATE_USER); profile_hit(SCHED_PROFILING, __builtin_return_address(0)); schedstat_inc(this_rq()->sched_count); } -static void put_prev_task_balance(struct rq *rq, struct task_struct *prev, - struct rq_flags *rf) +static void prev_balance(struct rq *rq, struct task_struct *prev, + struct rq_flags *rf) { -#ifdef CONFIG_SMP + const struct sched_class *start_class = prev->sched_class; const struct sched_class *class; + /* * We must do the balancing pass before put_prev_task(), such * that when we release the rq->lock the task is in the same @@ -5886,13 +5854,10 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev, * We can terminate the balance pass as soon as we know there is * a runnable task of @class priority or higher. */ - for_class_range(class, prev->sched_class, &idle_sched_class) { - if (class->balance(rq, prev, rf)) + for_active_class_range(class, start_class, &idle_sched_class) { + if (class->balance && class->balance(rq, prev, rf)) break; } -#endif - - put_prev_task(rq, prev); } /* @@ -5904,6 +5869,11 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) const struct sched_class *class; struct task_struct *p; + rq->dl_server = NULL; + + if (scx_enabled()) + goto restart; + /* * Optimization: we know that if all tasks are in the fair class we can * call that function directly, but only if the @prev task wasn't of a @@ -5911,7 +5881,7 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * opportunity to pull in more work from other CPUs. */ if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) && - rq->nr_running == rq->cfs.h_nr_running)) { + rq->nr_running == rq->cfs.h_nr_queued)) { p = pick_next_task_fair(rq, prev, rf); if (unlikely(p == RETRY_TASK)) @@ -5919,20 +5889,32 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) /* Assume the next prioritized class is idle_sched_class */ if (!p) { - put_prev_task(rq, prev); - p = pick_next_task_idle(rq); + p = pick_task_idle(rq, rf); + put_prev_set_next_task(rq, prev, p); } return p; } restart: - put_prev_task_balance(rq, prev, rf); - - for_each_class(class) { - p = class->pick_next_task(rq); - if (p) - return p; + prev_balance(rq, prev, rf); + + for_each_active_class(class) { + if (class->pick_next_task) { + p = class->pick_next_task(rq, prev, rf); + if (unlikely(p == RETRY_TASK)) + goto restart; + if (p) + return p; + } else { + p = class->pick_task(rq, rf); + if (unlikely(p == RETRY_TASK)) + goto restart; + if (p) { + put_prev_set_next_task(rq, prev, p); + return p; + } + } } BUG(); /* The idle class should always have a runnable task. */ @@ -5957,13 +5939,19 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b) return a->core_cookie == b->core_cookie; } -static inline struct task_struct *pick_task(struct rq *rq) +/* + * Careful; this can return RETRY_TASK, it does not include the retry-loop + * itself due to the whole SMT pick retry thing below. + */ +static inline struct task_struct *pick_task(struct rq *rq, struct rq_flags *rf) { const struct sched_class *class; struct task_struct *p; - for_each_class(class) { - p = class->pick_task(rq); + rq->dl_server = NULL; + + for_each_active_class(class) { + p = class->pick_task(rq, rf); if (p) return p; } @@ -5978,7 +5966,7 @@ static void queue_core_balance(struct rq *rq); static struct task_struct * pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { - struct task_struct *next, *p, *max = NULL; + struct task_struct *next, *p, *max; const struct cpumask *smt_mask; bool fi_before = false; bool core_clock_updated = (rq == rq->core); @@ -6000,6 +5988,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * another cpu during offline. */ rq->core_pick = NULL; + rq->core_dl_server = NULL; return __pick_next_task(rq, prev, rf); } @@ -6018,16 +6007,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) WRITE_ONCE(rq->core_sched_seq, rq->core->core_pick_seq); next = rq->core_pick; - if (next != prev) { - put_prev_task(rq, prev); - set_next_task(rq, next); - } - + rq->dl_server = rq->core_dl_server; rq->core_pick = NULL; - goto out; + rq->core_dl_server = NULL; + goto out_set_next; } - put_prev_task_balance(rq, prev, rf); + prev_balance(rq, prev, rf); smt_mask = cpu_smt_mask(cpu); need_sync = !!rq->core->core_cookie; @@ -6065,9 +6051,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * and there are no cookied tasks running on siblings. */ if (!need_sync) { - next = pick_task(rq); +restart_single: + next = pick_task(rq, rf); + if (unlikely(next == RETRY_TASK)) + goto restart_single; if (!next->core_cookie) { rq->core_pick = NULL; + rq->core_dl_server = NULL; /* * For robustness, update the min_vruntime_fi for * unconstrained picks as well. @@ -6084,6 +6074,8 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * * Tie-break prio towards the current CPU */ +restart_multi: + max = NULL; for_each_cpu_wrap(i, smt_mask, cpu) { rq_i = cpu_rq(i); @@ -6095,7 +6087,13 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) if (i != cpu && (rq_i != rq->core || !core_clock_updated)) update_rq_clock(rq_i); - p = rq_i->core_pick = pick_task(rq_i); + p = pick_task(rq_i, rf); + if (unlikely(p == RETRY_TASK)) + goto restart_multi; + + rq_i->core_pick = p; + rq_i->core_dl_server = rq_i->dl_server; + if (!max || prio_less(max, p, fi_before)) max = p; } @@ -6115,10 +6113,11 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) if (cookie) p = sched_core_find(rq_i, cookie); if (!p) - p = idle_sched_class.pick_task(rq_i); + p = idle_sched_class.pick_task(rq_i, rf); } rq_i->core_pick = p; + rq_i->core_dl_server = NULL; if (p == rq_i->idle) { if (rq_i->nr_running) { @@ -6179,6 +6178,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) if (i == cpu) { rq_i->core_pick = NULL; + rq_i->core_dl_server = NULL; continue; } @@ -6187,6 +6187,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) if (rq_i->curr == rq_i->core_pick) { rq_i->core_pick = NULL; + rq_i->core_dl_server = NULL; continue; } @@ -6194,8 +6195,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } out_set_next: - set_next_task(rq, next); -out: + put_prev_set_next_task(rq, prev, next); if (rq->core->core_forceidle_count && next == rq->idle) queue_core_balance(rq); @@ -6209,19 +6209,19 @@ static bool try_steal_cookie(int this, int that) unsigned long cookie; bool success = false; - local_irq_disable(); - double_rq_lock(dst, src); + guard(irq)(); + guard(double_rq_lock)(dst, src); cookie = dst->core->core_cookie; if (!cookie) - goto unlock; + return false; if (dst->curr != dst->idle) - goto unlock; + return false; p = sched_core_find(src, cookie); - if (p == src->idle) - goto unlock; + if (!p) + return false; do { if (p == src->core_pick || p == src->curr) @@ -6232,11 +6232,16 @@ static bool try_steal_cookie(int this, int that) if (p->core_occupation > dst->idle->core_occupation) goto next; + /* + * sched_core_find() and sched_core_next() will ensure + * that task @p is not throttled now, we also need to + * check whether the runqueue of the destination CPU is + * being throttled. + */ + if (sched_task_is_throttled(p, this)) + goto next; - deactivate_task(src, p, 0); - set_task_cpu(p, this); - activate_task(dst, p, 0); - + move_queued_task_locked(src, dst, p); resched_curr(dst); success = true; @@ -6246,10 +6251,6 @@ next: p = sched_core_next(p, cookie); } while (p); -unlock: - double_rq_unlock(dst, src); - local_irq_enable(); - return success; } @@ -6257,7 +6258,7 @@ static bool steal_cookie_task(int cpu, struct sched_domain *sd) { int i; - for_each_cpu_wrap(i, sched_domain_span(sd), cpu) { + for_each_cpu_wrap(i, sched_domain_span(sd), cpu + 1) { if (i == cpu) continue; @@ -6276,8 +6277,9 @@ static void sched_core_balance(struct rq *rq) struct sched_domain *sd; int cpu = cpu_of(rq); - preempt_disable(); - rcu_read_lock(); + guard(preempt)(); + guard(rcu)(); + raw_spin_rq_unlock_irq(rq); for_each_domain(cpu, sd) { if (need_resched()) @@ -6287,8 +6289,6 @@ static void sched_core_balance(struct rq *rq) break; } raw_spin_rq_lock_irq(rq); - rcu_read_unlock(); - preempt_enable(); } static DEFINE_PER_CPU(struct balance_callback, core_balance_head); @@ -6307,20 +6307,24 @@ static void queue_core_balance(struct rq *rq) queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance); } +DEFINE_LOCK_GUARD_1(core_lock, int, + sched_core_lock(*_T->lock, &_T->flags), + sched_core_unlock(*_T->lock, &_T->flags), + unsigned long flags) + static void sched_core_cpu_starting(unsigned int cpu) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); struct rq *rq = cpu_rq(cpu), *core_rq = NULL; - unsigned long flags; int t; - sched_core_lock(cpu, &flags); + guard(core_lock)(&cpu); WARN_ON_ONCE(rq->core != rq); /* if we're the first, we'll be our own leader */ if (cpumask_weight(smt_mask) == 1) - goto unlock; + return; /* find the leader */ for_each_cpu(t, smt_mask) { @@ -6334,7 +6338,7 @@ static void sched_core_cpu_starting(unsigned int cpu) } if (WARN_ON_ONCE(!core_rq)) /* whoopsie */ - goto unlock; + return; /* install and validate core_rq */ for_each_cpu(t, smt_mask) { @@ -6345,29 +6349,25 @@ static void sched_core_cpu_starting(unsigned int cpu) WARN_ON_ONCE(rq->core != core_rq); } - -unlock: - sched_core_unlock(cpu, &flags); } static void sched_core_cpu_deactivate(unsigned int cpu) { const struct cpumask *smt_mask = cpu_smt_mask(cpu); struct rq *rq = cpu_rq(cpu), *core_rq = NULL; - unsigned long flags; int t; - sched_core_lock(cpu, &flags); + guard(core_lock)(&cpu); /* if we're the last man standing, nothing to do */ if (cpumask_weight(smt_mask) == 1) { WARN_ON_ONCE(rq->core != rq); - goto unlock; + return; } /* if we're not the leader, nothing to do */ if (rq->core != rq) - goto unlock; + return; /* find a new leader */ for_each_cpu(t, smt_mask) { @@ -6378,7 +6378,7 @@ static void sched_core_cpu_deactivate(unsigned int cpu) } if (WARN_ON_ONCE(!core_rq)) /* impossible */ - goto unlock; + return; /* copy the shared state to the new leader */ core_rq->core_task_seq = rq->core_task_seq; @@ -6400,9 +6400,6 @@ static void sched_core_cpu_deactivate(unsigned int cpu) rq = cpu_rq(t); rq->core = core_rq; } - -unlock: - sched_core_unlock(cpu, &flags); } static inline void sched_core_cpu_dying(unsigned int cpu) @@ -6413,7 +6410,7 @@ static inline void sched_core_cpu_dying(unsigned int cpu) rq->core = rq; } -#else /* !CONFIG_SCHED_CORE */ +#else /* !CONFIG_SCHED_CORE: */ static inline void sched_core_cpu_starting(unsigned int cpu) {} static inline void sched_core_cpu_deactivate(unsigned int cpu) {} @@ -6425,25 +6422,259 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) return __pick_next_task(rq, prev, rf); } -#endif /* CONFIG_SCHED_CORE */ +#endif /* !CONFIG_SCHED_CORE */ /* * Constants for the sched_mode argument of __schedule(). * * The mode argument allows RT enabled kernels to differentiate a - * preemption from blocking on an 'sleeping' spin/rwlock. Note that - * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to - * optimize the AND operation out and just check for zero. + * preemption from blocking on an 'sleeping' spin/rwlock. */ -#define SM_NONE 0x0 -#define SM_PREEMPT 0x1 -#define SM_RTLOCK_WAIT 0x2 +#define SM_IDLE (-1) +#define SM_NONE 0 +#define SM_PREEMPT 1 +#define SM_RTLOCK_WAIT 2 -#ifndef CONFIG_PREEMPT_RT -# define SM_MASK_PREEMPT (~0U) -#else -# define SM_MASK_PREEMPT SM_PREEMPT -#endif +/* + * Helper function for __schedule() + * + * Tries to deactivate the task, unless the should_block arg + * is false or if a signal is pending. In the case a signal + * is pending, marks the task's __state as RUNNING (and clear + * blocked_on). + */ +static bool try_to_block_task(struct rq *rq, struct task_struct *p, + unsigned long *task_state_p, bool should_block) +{ + unsigned long task_state = *task_state_p; + int flags = DEQUEUE_NOCLOCK; + + if (signal_pending_state(task_state, p)) { + WRITE_ONCE(p->__state, TASK_RUNNING); + *task_state_p = TASK_RUNNING; + return false; + } + + /* + * We check should_block after signal_pending because we + * will want to wake the task in that case. But if + * should_block is false, its likely due to the task being + * blocked on a mutex, and we want to keep it on the runqueue + * to be selectable for proxy-execution. + */ + if (!should_block) + return false; + + p->sched_contributes_to_load = + (task_state & TASK_UNINTERRUPTIBLE) && + !(task_state & TASK_NOLOAD) && + !(task_state & TASK_FROZEN); + + if (unlikely(is_special_task_state(task_state))) + flags |= DEQUEUE_SPECIAL; + + /* + * __schedule() ttwu() + * prev_state = prev->state; if (p->on_rq && ...) + * if (prev_state) goto out; + * p->on_rq = 0; smp_acquire__after_ctrl_dep(); + * p->state = TASK_WAKING + * + * Where __schedule() and ttwu() have matching control dependencies. + * + * After this, schedule() must not care about p->state any more. + */ + block_task(rq, p, flags); + return true; +} + +#ifdef CONFIG_SCHED_PROXY_EXEC +static inline struct task_struct *proxy_resched_idle(struct rq *rq) +{ + put_prev_set_next_task(rq, rq->donor, rq->idle); + rq_set_donor(rq, rq->idle); + set_tsk_need_resched(rq->idle); + return rq->idle; +} + +static bool __proxy_deactivate(struct rq *rq, struct task_struct *donor) +{ + unsigned long state = READ_ONCE(donor->__state); + + /* Don't deactivate if the state has been changed to TASK_RUNNING */ + if (state == TASK_RUNNING) + return false; + /* + * Because we got donor from pick_next_task(), it is *crucial* + * that we call proxy_resched_idle() before we deactivate it. + * As once we deactivate donor, donor->on_rq is set to zero, + * which allows ttwu() to immediately try to wake the task on + * another rq. So we cannot use *any* references to donor + * after that point. So things like cfs_rq->curr or rq->donor + * need to be changed from next *before* we deactivate. + */ + proxy_resched_idle(rq); + return try_to_block_task(rq, donor, &state, true); +} + +static struct task_struct *proxy_deactivate(struct rq *rq, struct task_struct *donor) +{ + if (!__proxy_deactivate(rq, donor)) { + /* + * XXX: For now, if deactivation failed, set donor + * as unblocked, as we aren't doing proxy-migrations + * yet (more logic will be needed then). + */ + donor->blocked_on = NULL; + } + return NULL; +} + +/* + * Find runnable lock owner to proxy for mutex blocked donor + * + * Follow the blocked-on relation: + * task->blocked_on -> mutex->owner -> task... + * + * Lock order: + * + * p->pi_lock + * rq->lock + * mutex->wait_lock + * + * Returns the task that is going to be used as execution context (the one + * that is actually going to be run on cpu_of(rq)). + */ +static struct task_struct * +find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) +{ + struct task_struct *owner = NULL; + int this_cpu = cpu_of(rq); + struct task_struct *p; + struct mutex *mutex; + + /* Follow blocked_on chain. */ + for (p = donor; task_is_blocked(p); p = owner) { + mutex = p->blocked_on; + /* Something changed in the chain, so pick again */ + if (!mutex) + return NULL; + /* + * By taking mutex->wait_lock we hold off concurrent mutex_unlock() + * and ensure @owner sticks around. + */ + guard(raw_spinlock)(&mutex->wait_lock); + + /* Check again that p is blocked with wait_lock held */ + if (mutex != __get_task_blocked_on(p)) { + /* + * Something changed in the blocked_on chain and + * we don't know if only at this level. So, let's + * just bail out completely and let __schedule() + * figure things out (pick_again loop). + */ + return NULL; + } + + owner = __mutex_owner(mutex); + if (!owner) { + __clear_task_blocked_on(p, mutex); + return p; + } + + if (!READ_ONCE(owner->on_rq) || owner->se.sched_delayed) { + /* XXX Don't handle blocked owners/delayed dequeue yet */ + return proxy_deactivate(rq, donor); + } + + if (task_cpu(owner) != this_cpu) { + /* XXX Don't handle migrations yet */ + return proxy_deactivate(rq, donor); + } + + if (task_on_rq_migrating(owner)) { + /* + * One of the chain of mutex owners is currently migrating to this + * CPU, but has not yet been enqueued because we are holding the + * rq lock. As a simple solution, just schedule rq->idle to give + * the migration a chance to complete. Much like the migrate_task + * case we should end up back in find_proxy_task(), this time + * hopefully with all relevant tasks already enqueued. + */ + return proxy_resched_idle(rq); + } + + /* + * Its possible to race where after we check owner->on_rq + * but before we check (owner_cpu != this_cpu) that the + * task on another cpu was migrated back to this cpu. In + * that case it could slip by our checks. So double check + * we are still on this cpu and not migrating. If we get + * inconsistent results, try again. + */ + if (!task_on_rq_queued(owner) || task_cpu(owner) != this_cpu) + return NULL; + + if (owner == p) { + /* + * It's possible we interleave with mutex_unlock like: + * + * lock(&rq->lock); + * find_proxy_task() + * mutex_unlock() + * lock(&wait_lock); + * donor(owner) = current->blocked_donor; + * unlock(&wait_lock); + * + * wake_up_q(); + * ... + * ttwu_runnable() + * __task_rq_lock() + * lock(&wait_lock); + * owner == p + * + * Which leaves us to finish the ttwu_runnable() and make it go. + * + * So schedule rq->idle so that ttwu_runnable() can get the rq + * lock and mark owner as running. + */ + return proxy_resched_idle(rq); + } + /* + * OK, now we're absolutely sure @owner is on this + * rq, therefore holding @rq->lock is sufficient to + * guarantee its existence, as per ttwu_remote(). + */ + } + + WARN_ON_ONCE(owner && !owner->on_rq); + return owner; +} +#else /* SCHED_PROXY_EXEC */ +static struct task_struct * +find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf) +{ + WARN_ONCE(1, "This should never be called in the !SCHED_PROXY_EXEC case\n"); + return donor; +} +#endif /* SCHED_PROXY_EXEC */ + +static inline void proxy_tag_curr(struct rq *rq, struct task_struct *owner) +{ + if (!sched_proxy_exec()) + return; + /* + * pick_next_task() calls set_next_task() on the chosen task + * at some point, which ensures it is not push/pullable. + * However, the chosen/donor task *and* the mutex owner form an + * atomic pair wrt push/pull. + * + * Make sure owner we run is not pushable. Unfortunately we can + * only deal with that by means of a dequeue/enqueue cycle. :-/ + */ + dequeue_task(rq, owner, DEQUEUE_NOCLOCK | DEQUEUE_SAVE); + enqueue_task(rq, owner, ENQUEUE_NOCLOCK | ENQUEUE_RESTORE); +} /* * __schedule() is the main scheduler function. @@ -6456,7 +6687,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * paths. For example, see arch/x86/entry_64.S. * * To drive preemption between tasks, the scheduler sets the flag in timer - * interrupt handler scheduler_tick(). + * interrupt handler sched_tick(). * * 3. Wakeups don't really cause entry into schedule(). They add a * task to the run-queue and that's it. @@ -6484,26 +6715,38 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) * * WARNING: must be called with preemption disabled! */ -static void __sched notrace __schedule(unsigned int sched_mode) +static void __sched notrace __schedule(int sched_mode) { struct task_struct *prev, *next; + /* + * On PREEMPT_RT kernel, SM_RTLOCK_WAIT is noted + * as a preemption by schedule_debug() and RCU. + */ + bool preempt = sched_mode > SM_NONE; + bool is_switch = false; unsigned long *switch_count; unsigned long prev_state; struct rq_flags rf; struct rq *rq; int cpu; + /* Trace preemptions consistently with task switches */ + trace_sched_entry_tp(sched_mode == SM_PREEMPT); + cpu = smp_processor_id(); rq = cpu_rq(cpu); prev = rq->curr; - schedule_debug(prev, !!sched_mode); + schedule_debug(prev, preempt); if (sched_feat(HRTICK) || sched_feat(HRTICK_DL)) hrtick_clear(rq); + klp_sched_try_switch(prev); + local_irq_disable(); - rcu_note_context_switch(!!sched_mode); + rcu_note_context_switch(preempt); + migrate_disable_switch(rq, prev); /* * Make sure that signal_pending_state()->signal_pending() below @@ -6518,7 +6761,9 @@ static void __sched notrace __schedule(unsigned int sched_mode) * if (signal_pending_state()) if (p->state & @state) * * Also, the membarrier system call requires a full memory barrier - * after coming from user-space, before storing to rq->curr. + * after coming from user-space, before storing to rq->curr; this + * barrier matches a full barrier in the proximity of the membarrier + * system call exit. */ rq_lock(rq, &rf); smp_mb__after_spinlock(); @@ -6526,61 +6771,64 @@ static void __sched notrace __schedule(unsigned int sched_mode) /* Promote REQ to ACT */ rq->clock_update_flags <<= 1; update_rq_clock(rq); + rq->clock_update_flags = RQCF_UPDATED; switch_count = &prev->nivcsw; + /* Task state changes only considers SM_PREEMPT as preemption */ + preempt = sched_mode == SM_PREEMPT; + /* * We must load prev->state once (task_struct::state is volatile), such * that we form a control dependency vs deactivate_task() below. */ prev_state = READ_ONCE(prev->__state); - if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) { - if (signal_pending_state(prev_state, prev)) { - WRITE_ONCE(prev->__state, TASK_RUNNING); - } else { - prev->sched_contributes_to_load = - (prev_state & TASK_UNINTERRUPTIBLE) && - !(prev_state & TASK_NOLOAD) && - !(prev_state & TASK_FROZEN); - - if (prev->sched_contributes_to_load) - rq->nr_uninterruptible++; - - /* - * __schedule() ttwu() - * prev_state = prev->state; if (p->on_rq && ...) - * if (prev_state) goto out; - * p->on_rq = 0; smp_acquire__after_ctrl_dep(); - * p->state = TASK_WAKING - * - * Where __schedule() and ttwu() have matching control dependencies. - * - * After this, schedule() must not care about p->state any more. - */ - deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK); - - if (prev->in_iowait) { - atomic_inc(&rq->nr_iowait); - delayacct_blkio_start(); - } + if (sched_mode == SM_IDLE) { + /* SCX must consult the BPF scheduler to tell if rq is empty */ + if (!rq->nr_running && !scx_enabled()) { + next = prev; + goto picked; } + } else if (!preempt && prev_state) { + /* + * We pass task_is_blocked() as the should_block arg + * in order to keep mutex-blocked tasks on the runqueue + * for slection with proxy-exec (without proxy-exec + * task_is_blocked() will always be false). + */ + try_to_block_task(rq, prev, &prev_state, + !task_is_blocked(prev)); switch_count = &prev->nvcsw; } - next = pick_next_task(rq, prev, &rf); +pick_again: + next = pick_next_task(rq, rq->donor, &rf); + rq_set_donor(rq, next); + if (unlikely(task_is_blocked(next))) { + next = find_proxy_task(rq, next, &rf); + if (!next) + goto pick_again; + if (next == rq->idle) + goto keep_resched; + } +picked: clear_tsk_need_resched(prev); clear_preempt_need_resched(); -#ifdef CONFIG_SCHED_DEBUG +keep_resched: rq->last_seen_need_resched_ns = 0; -#endif - if (likely(prev != next)) { + is_switch = prev != next; + if (likely(is_switch)) { rq->nr_switches++; /* * RCU users of rcu_dereference(rq->curr) may not see * changes to task_struct made by pick_next_task(). */ RCU_INIT_POINTER(rq->curr, next); + + if (!task_current_donor(rq, next)) + proxy_tag_curr(rq, next); + /* * The membarrier system call requires each architecture * to have a full memory barrier after updating @@ -6588,29 +6836,41 @@ static void __sched notrace __schedule(unsigned int sched_mode) * * Here are the schemes providing that barrier on the * various architectures: - * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC. - * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC. + * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC, + * RISC-V. switch_mm() relies on membarrier_arch_switch_mm() + * on PowerPC and on RISC-V. * - finish_lock_switch() for weakly-ordered * architectures where spin_unlock is a full barrier, * - switch_to() for arm64 (weakly-ordered, spin_unlock * is a RELEASE barrier), + * + * The barrier matches a full barrier in the proximity of + * the membarrier system call entry. + * + * On RISC-V, this barrier pairing is also needed for the + * SYNC_CORE command when switching between processes, cf. + * the inline comments in membarrier_arch_switch_mm(). */ ++*switch_count; - migrate_disable_switch(rq, prev); - psi_sched_switch(prev, next, !task_on_rq_queued(prev)); + psi_account_irqtime(rq, prev, next); + psi_sched_switch(prev, next, !task_on_rq_queued(prev) || + prev->se.sched_delayed); - trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state); + trace_sched_switch(preempt, prev, next, prev_state); /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); } else { - rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); + /* In case next was already curr but just got blocked_donor */ + if (!task_current_donor(rq, next)) + proxy_tag_curr(rq, next); rq_unpin_lock(rq, &rf); __balance_callbacks(rq); raw_spin_rq_unlock_irq(rq); } + trace_sched_exit_tp(is_switch); } void __noreturn do_task_dead(void) @@ -6631,57 +6891,73 @@ void __noreturn do_task_dead(void) static inline void sched_submit_work(struct task_struct *tsk) { + static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG); unsigned int task_flags; - if (task_is_running(tsk)) - return; + /* + * Establish LD_WAIT_CONFIG context to ensure none of the code called + * will use a blocking primitive -- which would lead to recursion. + */ + lock_map_acquire_try(&sched_map); task_flags = tsk->flags; /* * If a worker goes to sleep, notify and ask workqueue whether it * wants to wake up a task to maintain concurrency. */ - if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) { - if (task_flags & PF_WQ_WORKER) - wq_worker_sleeping(tsk); - else - io_wq_worker_sleeping(tsk); - } + if (task_flags & PF_WQ_WORKER) + wq_worker_sleeping(tsk); + else if (task_flags & PF_IO_WORKER) + io_wq_worker_sleeping(tsk); /* * 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); + WARN_ON_ONCE(current->__state & TASK_RTLOCK_WAIT); /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. */ blk_flush_plug(tsk->plug, true); + + lock_map_release(&sched_map); } static void sched_update_worker(struct task_struct *tsk) { - if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) { + if (tsk->flags & PF_BLOCK_TS) + blk_plug_invalidate_ts(tsk); if (tsk->flags & PF_WQ_WORKER) wq_worker_running(tsk); - else + else if (tsk->flags & PF_IO_WORKER) io_wq_worker_running(tsk); } } -asmlinkage __visible void __sched schedule(void) +static __always_inline void __schedule_loop(int sched_mode) { - struct task_struct *tsk = current; - - sched_submit_work(tsk); do { preempt_disable(); - __schedule(SM_NONE); + __schedule(sched_mode); sched_preempt_enable_no_resched(); } while (need_resched()); +} + +asmlinkage __visible void __sched schedule(void) +{ + struct task_struct *tsk = current; + +#ifdef CONFIG_RT_MUTEXES + lockdep_assert(!tsk->sched_rt_mutex); +#endif + + if (!task_is_running(tsk)) + sched_submit_work(tsk); + __schedule_loop(SM_NONE); sched_update_worker(tsk); } EXPORT_SYMBOL(schedule); @@ -6700,14 +6976,14 @@ void __sched schedule_idle(void) { /* * As this skips calling sched_submit_work(), which the idle task does - * regardless because that function is a nop when the task is in a + * regardless because that function is a NOP when the task is in a * TASK_RUNNING state, make sure this isn't used someplace that the * current task can be in any other state. Note, idle is always in the * TASK_RUNNING state. */ WARN_ON_ONCE(current->__state); do { - __schedule(SM_NONE); + __schedule(SM_IDLE); } while (need_resched()); } @@ -6721,7 +6997,7 @@ asmlinkage __visible void __sched schedule_user(void) * we find a better solution. * * NB: There are buggy callers of this function. Ideally we - * should warn if prev_state != CONTEXT_USER, but that will trigger + * should warn if prev_state != CT_STATE_USER, but that will trigger * too frequently to make sense yet. */ enum ctx_state prev_state = exception_enter(); @@ -6745,11 +7021,7 @@ void __sched schedule_preempt_disabled(void) #ifdef CONFIG_PREEMPT_RT void __sched notrace schedule_rtlock(void) { - do { - preempt_disable(); - __schedule(SM_RTLOCK_WAIT); - sched_preempt_enable_no_resched(); - } while (need_resched()); + __schedule_loop(SM_RTLOCK_WAIT); } NOKPROBE_SYMBOL(schedule_rtlock); #endif @@ -6802,14 +7074,14 @@ NOKPROBE_SYMBOL(preempt_schedule); EXPORT_SYMBOL(preempt_schedule); #ifdef CONFIG_PREEMPT_DYNAMIC -#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) -#ifndef preempt_schedule_dynamic_enabled -#define preempt_schedule_dynamic_enabled preempt_schedule -#define preempt_schedule_dynamic_disabled NULL -#endif +# ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL +# ifndef preempt_schedule_dynamic_enabled +# define preempt_schedule_dynamic_enabled preempt_schedule +# define preempt_schedule_dynamic_disabled NULL +# endif DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled); EXPORT_STATIC_CALL_TRAMP(preempt_schedule); -#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule); void __sched notrace dynamic_preempt_schedule(void) { @@ -6819,8 +7091,8 @@ void __sched notrace dynamic_preempt_schedule(void) } NOKPROBE_SYMBOL(dynamic_preempt_schedule); EXPORT_SYMBOL(dynamic_preempt_schedule); -#endif -#endif +# endif +#endif /* CONFIG_PREEMPT_DYNAMIC */ /** * preempt_schedule_notrace - preempt_schedule called by tracing @@ -6875,14 +7147,14 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) EXPORT_SYMBOL_GPL(preempt_schedule_notrace); #ifdef CONFIG_PREEMPT_DYNAMIC -#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) -#ifndef preempt_schedule_notrace_dynamic_enabled -#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace -#define preempt_schedule_notrace_dynamic_disabled NULL -#endif +# if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +# ifndef preempt_schedule_notrace_dynamic_enabled +# define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace +# define preempt_schedule_notrace_dynamic_disabled NULL +# endif DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled); EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace); -#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace); void __sched notrace dynamic_preempt_schedule_notrace(void) { @@ -6892,16 +7164,16 @@ void __sched notrace dynamic_preempt_schedule_notrace(void) } NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace); EXPORT_SYMBOL(dynamic_preempt_schedule_notrace); -#endif +# endif #endif #endif /* CONFIG_PREEMPTION */ /* * This is the entry point to schedule() from kernel preemption - * off of irq context. - * Note, that this is called and return with irqs disabled. This will - * protect us against recursive calling from irq. + * off of IRQ context. + * Note, that this is called and return with IRQs disabled. This will + * protect us against recursive calling from IRQ contexts. */ asmlinkage __visible void __sched preempt_schedule_irq(void) { @@ -6926,38 +7198,53 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags, void *key) { - WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~WF_SYNC); + WARN_ON_ONCE(wake_flags & ~(WF_SYNC|WF_CURRENT_CPU)); return try_to_wake_up(curr->private, mode, wake_flags); } EXPORT_SYMBOL(default_wake_function); -static void __setscheduler_prio(struct task_struct *p, int prio) +const struct sched_class *__setscheduler_class(int policy, int prio) { if (dl_prio(prio)) - p->sched_class = &dl_sched_class; - else if (rt_prio(prio)) - p->sched_class = &rt_sched_class; - else - p->sched_class = &fair_sched_class; + return &dl_sched_class; - p->prio = prio; + if (rt_prio(prio)) + return &rt_sched_class; + +#ifdef CONFIG_SCHED_CLASS_EXT + if (task_should_scx(policy)) + return &ext_sched_class; +#endif + + return &fair_sched_class; } #ifdef CONFIG_RT_MUTEXES -static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) -{ - if (pi_task) - prio = min(prio, pi_task->prio); +/* + * Would be more useful with typeof()/auto_type but they don't mix with + * bit-fields. Since it's a local thing, use int. Keep the generic sounding + * name such that if someone were to implement this function we get to compare + * notes. + */ +#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; }) - return prio; +void rt_mutex_pre_schedule(void) +{ + lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1)); + sched_submit_work(current); } -static inline int rt_effective_prio(struct task_struct *p, int prio) +void rt_mutex_schedule(void) { - struct task_struct *pi_task = rt_mutex_get_top_task(p); + lockdep_assert(current->sched_rt_mutex); + __schedule_loop(SM_NONE); +} - return __rt_effective_prio(pi_task, prio); +void rt_mutex_post_schedule(void) +{ + sched_update_worker(current); + lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0)); } /* @@ -6973,9 +7260,9 @@ static inline int rt_effective_prio(struct task_struct *p, int prio) */ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) { - int prio, oldprio, queued, running, queue_flag = + int prio, oldprio, queue_flag = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; - const struct sched_class *prev_class; + const struct sched_class *prev_class, *next_class; struct rq_flags rf; struct rq *rq; @@ -7009,7 +7296,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) goto out_unlock; /* - * Idle task boosting is a nono in general. There is one + * Idle task boosting is a no-no in general. There is one * exception, when PREEMPT_RT and NOHZ is active: * * The idle task calls get_next_timer_interrupt() and holds @@ -7033,1428 +7320,64 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) queue_flag &= ~DEQUEUE_MOVE; prev_class = p->sched_class; - queued = task_on_rq_queued(p); - running = task_current(rq, p); - if (queued) - dequeue_task(rq, p, queue_flag); - if (running) - put_prev_task(rq, p); - - /* - * Boosting condition are: - * 1. -rt task is running and holds mutex A - * --> -dl task blocks on mutex A - * - * 2. -dl task is running and holds mutex A - * --> -dl task blocks on mutex A and could preempt the - * running task - */ - if (dl_prio(prio)) { - if (!dl_prio(p->normal_prio) || - (pi_task && dl_prio(pi_task->prio) && - dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.pi_se = pi_task->dl.pi_se; - queue_flag |= ENQUEUE_REPLENISH; - } else { - p->dl.pi_se = &p->dl; - } - } else if (rt_prio(prio)) { - if (dl_prio(oldprio)) - p->dl.pi_se = &p->dl; - if (oldprio < prio) - queue_flag |= ENQUEUE_HEAD; - } else { - if (dl_prio(oldprio)) - p->dl.pi_se = &p->dl; - if (rt_prio(oldprio)) - p->rt.timeout = 0; - } - - __setscheduler_prio(p, prio); - - if (queued) - enqueue_task(rq, p, queue_flag); - if (running) - set_next_task(rq, p); - - check_class_changed(rq, p, prev_class, oldprio); -out_unlock: - /* Avoid rq from going away on us: */ - preempt_disable(); - - rq_unpin_lock(rq, &rf); - __balance_callbacks(rq); - raw_spin_rq_unlock(rq); - - preempt_enable(); -} -#else -static inline int rt_effective_prio(struct task_struct *p, int prio) -{ - return prio; -} -#endif - -void set_user_nice(struct task_struct *p, long nice) -{ - bool queued, running; - int old_prio; - struct rq_flags rf; - struct rq *rq; - - if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) - return; - /* - * We have to be careful, if called from sys_setpriority(), - * the task might be in the middle of scheduling on another CPU. - */ - rq = task_rq_lock(p, &rf); - update_rq_clock(rq); - - /* - * The RT priorities are set via sched_setscheduler(), but we still - * allow the 'normal' nice value to be set - but as expected - * it won't have any effect on scheduling until the task is - * SCHED_DEADLINE, SCHED_FIFO or SCHED_RR: - */ - if (task_has_dl_policy(p) || task_has_rt_policy(p)) { - p->static_prio = NICE_TO_PRIO(nice); - goto out_unlock; - } - queued = task_on_rq_queued(p); - running = task_current(rq, p); - if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK); - if (running) - put_prev_task(rq, p); - - p->static_prio = NICE_TO_PRIO(nice); - set_load_weight(p, true); - old_prio = p->prio; - p->prio = effective_prio(p); - - if (queued) - enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); - if (running) - set_next_task(rq, p); - - /* - * If the task increased its priority or is running and - * lowered its priority, then reschedule its CPU: - */ - p->sched_class->prio_changed(rq, p, old_prio); - -out_unlock: - task_rq_unlock(rq, p, &rf); -} -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 - * @nice: nice value - */ -int can_nice(const struct task_struct *p, const int nice) -{ - return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE); -} - -#ifdef __ARCH_WANT_SYS_NICE - -/* - * sys_nice - change the priority of the current process. - * @increment: priority increment - * - * sys_setpriority is a more generic, but much slower function that - * does similar things. - */ -SYSCALL_DEFINE1(nice, int, increment) -{ - long nice, retval; - - /* - * Setpriority might change our priority at the same moment. - * We don't have to worry. Conceptually one call occurs first - * and we have a single winner. - */ - increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); - nice = task_nice(current) + increment; - - nice = clamp_val(nice, MIN_NICE, MAX_NICE); - if (increment < 0 && !can_nice(current, nice)) - return -EPERM; - - retval = security_task_setnice(current, nice); - if (retval) - return retval; - - set_user_nice(current, nice); - return 0; -} - -#endif - -/** - * task_prio - return the priority value of a given task. - * @p: the task in question. - * - * Return: The priority value as seen by users in /proc. - * - * sched policy return value kernel prio user prio/nice - * - * normal, batch, idle [0 ... 39] [100 ... 139] 0/[-20 ... 19] - * fifo, rr [-2 ... -100] [98 ... 0] [1 ... 99] - * deadline -101 -1 0 - */ -int task_prio(const struct task_struct *p) -{ - return p->prio - MAX_RT_PRIO; -} - -/** - * idle_cpu - is a given CPU idle currently? - * @cpu: the processor in question. - * - * Return: 1 if the CPU is currently idle. 0 otherwise. - */ -int idle_cpu(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - - if (rq->curr != rq->idle) - return 0; - - if (rq->nr_running) - return 0; - -#ifdef CONFIG_SMP - if (rq->ttwu_pending) - return 0; -#endif - - return 1; -} - -/** - * available_idle_cpu - is a given CPU idle for enqueuing work. - * @cpu: the CPU in question. - * - * Return: 1 if the CPU is currently idle. 0 otherwise. - */ -int available_idle_cpu(int cpu) -{ - if (!idle_cpu(cpu)) - return 0; - - if (vcpu_is_preempted(cpu)) - return 0; - - return 1; -} - -/** - * idle_task - return the idle task for a given CPU. - * @cpu: the processor in question. - * - * Return: The idle task for the CPU @cpu. - */ -struct task_struct *idle_task(int cpu) -{ - return cpu_rq(cpu)->idle; -} - -#ifdef CONFIG_SMP -/* - * This function computes an effective utilization for the given CPU, to be - * used for frequency selection given the linear relation: f = u * f_max. - * - * The scheduler tracks the following metrics: - * - * cpu_util_{cfs,rt,dl,irq}() - * cpu_bw_dl() - * - * Where the cfs,rt and dl util numbers are tracked with the same metric and - * synchronized windows and are thus directly comparable. - * - * The cfs,rt,dl utilization are the running times measured with rq->clock_task - * which excludes things like IRQ and steal-time. These latter are then accrued - * in the irq utilization. - * - * The DL bandwidth number otoh is not a measured metric but a value computed - * based on the task model parameters and gives the minimal utilization - * required to meet deadlines. - */ -unsigned long effective_cpu_util(int cpu, unsigned long util_cfs, - enum cpu_util_type type, - struct task_struct *p) -{ - 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; - } - - /* - * Early check to see if IRQ/steal time saturates the CPU, can be - * because of inaccuracies in how we track these -- see - * update_irq_load_avg(). - */ - irq = cpu_util_irq(rq); - if (unlikely(irq >= max)) - return max; - - /* - * Because the time spend on RT/DL tasks is visible as 'lost' time to - * 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 + cpu_util_rt(rq); - if (type == FREQUENCY_UTIL) - util = uclamp_rq_util_with(rq, util, p); - - dl_util = cpu_util_dl(rq); - - /* - * For frequency selection we do not make cpu_util_dl() a permanent part - * of this sum because we want to use cpu_bw_dl() later on, but we need - * to check if the CFS+RT+DL sum is saturated (ie. no idle time) such - * that we select f_max when there is no idle time. - * - * NOTE: numerical errors or stop class might cause us to not quite hit - * saturation when we should -- something for later. - */ - if (util + dl_util >= max) - return max; - - /* - * OTOH, for energy computation we need the estimated running time, so - * include util_dl and ignore dl_bw. - */ - if (type == ENERGY_UTIL) - util += dl_util; - - /* - * There is still idle time; further improve the number by using the - * irq metric. Because IRQ/steal time is hidden from the task clock we - * need to scale the task numbers: - * - * max - irq - * U' = irq + --------- * U - * max - */ - util = scale_irq_capacity(util, irq, max); - util += irq; - - /* - * Bandwidth required by DEADLINE must always be granted while, for - * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism - * to gracefully reduce the frequency when no tasks show up for longer - * periods of time. - * - * Ideally we would like to set bw_dl as min/guaranteed freq and util + - * bw_dl as requested freq. However, cpufreq is not yet ready for such - * an interface. So, we only do the latter for now. - */ - if (type == FREQUENCY_UTIL) - util += cpu_bw_dl(rq); - - return min(max, util); -} - -unsigned long sched_cpu_util(int cpu) -{ - return effective_cpu_util(cpu, cpu_util_cfs(cpu), ENERGY_UTIL, NULL); -} -#endif /* CONFIG_SMP */ - -/** - * find_process_by_pid - find a process with a matching PID value. - * @pid: the pid in question. - * - * The task of @pid, if found. %NULL otherwise. - */ -static struct task_struct *find_process_by_pid(pid_t pid) -{ - return pid ? find_task_by_vpid(pid) : current; -} - -/* - * sched_setparam() passes in -1 for its policy, to let the functions - * it calls know not to change it. - */ -#define SETPARAM_POLICY -1 - -static void __setscheduler_params(struct task_struct *p, - const struct sched_attr *attr) -{ - int policy = attr->sched_policy; - - if (policy == SETPARAM_POLICY) - policy = p->policy; - - p->policy = policy; - - if (dl_policy(policy)) - __setparam_dl(p, attr); - else if (fair_policy(policy)) - p->static_prio = NICE_TO_PRIO(attr->sched_nice); - - /* - * __sched_setscheduler() ensures attr->sched_priority == 0 when - * !rt_policy. Always setting this ensures that things like - * getparam()/getattr() don't report silly values for !rt tasks. - */ - p->rt_priority = attr->sched_priority; - p->normal_prio = normal_prio(p); - set_load_weight(p, true); -} - -/* - * Check the target process has a UID that matches the current process's: - */ -static bool check_same_owner(struct task_struct *p) -{ - const struct cred *cred = current_cred(), *pcred; - bool match; - - rcu_read_lock(); - pcred = __task_cred(p); - match = (uid_eq(cred->euid, pcred->euid) || - uid_eq(cred->euid, pcred->uid)); - rcu_read_unlock(); - 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) -{ - int oldpolicy = -1, policy = attr->sched_policy; - int retval, oldprio, newprio, queued, running; - const struct sched_class *prev_class; - struct balance_callback *head; - struct rq_flags rf; - int reset_on_fork; - int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; - struct rq *rq; - - /* The pi code expects interrupts enabled */ - BUG_ON(pi && in_interrupt()); -recheck: - /* Double check policy once rq lock held: */ - if (policy < 0) { - reset_on_fork = p->sched_reset_on_fork; - policy = oldpolicy = p->policy; - } else { - reset_on_fork = !!(attr->sched_flags & SCHED_FLAG_RESET_ON_FORK); - - if (!valid_policy(policy)) - return -EINVAL; - } - - if (attr->sched_flags & ~(SCHED_FLAG_ALL | SCHED_FLAG_SUGOV)) - return -EINVAL; - - /* - * Valid priorities for SCHED_FIFO and SCHED_RR are - * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL, - * SCHED_BATCH and SCHED_IDLE is 0. - */ - if (attr->sched_priority > MAX_RT_PRIO-1) - return -EINVAL; - if ((dl_policy(policy) && !__checkparam_dl(attr)) || - (rt_policy(policy) != (attr->sched_priority != 0))) - return -EINVAL; - - 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; - - retval = security_task_setscheduler(p); - if (retval) - 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: - * - * To be able to change p->policy safely, the appropriate - * runqueue lock must be held. - */ - rq = task_rq_lock(p, &rf); - update_rq_clock(rq); - - /* - * Changing the policy of the stop threads its a very bad idea: - */ - if (p == rq->stop) { - retval = -EINVAL; - goto unlock; - } - - /* - * If not changing anything there's no need to proceed further, - * but store a possible modification of reset_on_fork. - */ - if (unlikely(policy == p->policy)) { - if (fair_policy(policy) && attr->sched_nice != task_nice(p)) - goto change; - if (rt_policy(policy) && attr->sched_priority != p->rt_priority) - 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; - retval = 0; - goto unlock; - } -change: - - if (user) { -#ifdef CONFIG_RT_GROUP_SCHED - /* - * Do not allow realtime tasks into groups that have no runtime - * assigned. - */ - if (rt_bandwidth_enabled() && rt_policy(policy) && - task_group(p)->rt_bandwidth.rt_runtime == 0 && - !task_group_is_autogroup(task_group(p))) { - retval = -EPERM; - goto unlock; - } -#endif -#ifdef CONFIG_SMP - if (dl_bandwidth_enabled() && dl_policy(policy) && - !(attr->sched_flags & SCHED_FLAG_SUGOV)) { - cpumask_t *span = rq->rd->span; - - /* - * Don't allow tasks with an affinity mask smaller than - * the entire root_domain to become SCHED_DEADLINE. We - * will also fail if there's no bandwidth available. - */ - if (!cpumask_subset(span, p->cpus_ptr) || - rq->rd->dl_bw.bw == 0) { - retval = -EPERM; - goto unlock; - } - } -#endif - } - - /* Re-check policy now with rq lock held: */ - if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { - policy = oldpolicy = -1; - task_rq_unlock(rq, p, &rf); - if (pi) - cpuset_read_unlock(); - goto recheck; - } - - /* - * If setscheduling to SCHED_DEADLINE (or changing the parameters - * of a SCHED_DEADLINE task) we need to check if enough bandwidth - * is available. - */ - if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) { - retval = -EBUSY; - goto unlock; - } - - p->sched_reset_on_fork = reset_on_fork; - oldprio = p->prio; - - newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice); - if (pi) { - /* - * Take priority boosted tasks into account. If the new - * effective priority is unchanged, we just store the new - * normal parameters and do not touch the scheduler class and - * the runqueue. This will be done when the task deboost - * itself. - */ - newprio = rt_effective_prio(p, newprio); - if (newprio == oldprio) - queue_flags &= ~DEQUEUE_MOVE; - } - - queued = task_on_rq_queued(p); - running = task_current(rq, p); - if (queued) - dequeue_task(rq, p, queue_flags); - if (running) - put_prev_task(rq, p); - - prev_class = p->sched_class; + next_class = __setscheduler_class(p->policy, prio); - if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { - __setscheduler_params(p, attr); - __setscheduler_prio(p, newprio); - } - __setscheduler_uclamp(p, attr); + if (prev_class != next_class) + queue_flag |= DEQUEUE_CLASS; - if (queued) { + scoped_guard (sched_change, p, queue_flag) { /* - * We enqueue to tail when the priority of a task is - * increased (user space view). - */ - if (oldprio < p->prio) - queue_flags |= ENQUEUE_HEAD; - - enqueue_task(rq, p, queue_flags); - } - if (running) - set_next_task(rq, p); - - check_class_changed(rq, p, prev_class, oldprio); - - /* Avoid rq from going away on us: */ - preempt_disable(); - head = splice_balance_callbacks(rq); - task_rq_unlock(rq, p, &rf); - - if (pi) { - cpuset_read_unlock(); - rt_mutex_adjust_pi(p); - } - - /* Run balance callbacks after we've adjusted the PI chain: */ - balance_callbacks(rq, head); - 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, - const struct sched_param *param, bool check) -{ - struct sched_attr attr = { - .sched_policy = policy, - .sched_priority = param->sched_priority, - .sched_nice = PRIO_TO_NICE(p->static_prio), - }; - - /* Fixup the legacy SCHED_RESET_ON_FORK hack. */ - if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) { - attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; - policy &= ~SCHED_RESET_ON_FORK; - attr.sched_policy = policy; - } - - return __sched_setscheduler(p, &attr, check, true); -} -/** - * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. - * @p: the task in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * Use sched_set_fifo(), read its comment. - * - * Return: 0 on success. An error code otherwise. - * - * NOTE that the task may be already dead. - */ -int sched_setscheduler(struct task_struct *p, int policy, - const struct sched_param *param) -{ - return _sched_setscheduler(p, policy, param, true); -} - -int sched_setattr(struct task_struct *p, const struct sched_attr *attr) -{ - return __sched_setscheduler(p, attr, true, true); -} - -int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr) -{ - return __sched_setscheduler(p, attr, false, true); -} -EXPORT_SYMBOL_GPL(sched_setattr_nocheck); - -/** - * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. - * @p: the task in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * Just like sched_setscheduler, only don't bother checking if the - * current context has permission. For example, this is needed in - * stop_machine(): we create temporary high priority worker threads, - * but our caller might not have that capability. - * - * Return: 0 on success. An error code otherwise. - */ -int sched_setscheduler_nocheck(struct task_struct *p, int policy, - const struct sched_param *param) -{ - return _sched_setscheduler(p, policy, param, false); -} - -/* - * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally - * incapable of resource management, which is the one thing an OS really should - * be doing. - * - * This is of course the reason it is limited to privileged users only. - * - * Worse still; it is fundamentally impossible to compose static priority - * workloads. You cannot take two correctly working static prio workloads - * and smash them together and still expect them to work. - * - * For this reason 'all' FIFO tasks the kernel creates are basically at: - * - * MAX_RT_PRIO / 2 - * - * The administrator _MUST_ configure the system, the kernel simply doesn't - * know enough information to make a sensible choice. - */ -void sched_set_fifo(struct task_struct *p) -{ - struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 }; - WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); -} -EXPORT_SYMBOL_GPL(sched_set_fifo); - -/* - * For when you don't much care about FIFO, but want to be above SCHED_NORMAL. - */ -void sched_set_fifo_low(struct task_struct *p) -{ - struct sched_param sp = { .sched_priority = 1 }; - WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0); -} -EXPORT_SYMBOL_GPL(sched_set_fifo_low); - -void sched_set_normal(struct task_struct *p, int nice) -{ - struct sched_attr attr = { - .sched_policy = SCHED_NORMAL, - .sched_nice = nice, - }; - WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0); -} -EXPORT_SYMBOL_GPL(sched_set_normal); - -static int -do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) -{ - struct sched_param lparam; - struct task_struct *p; - int retval; - - if (!param || pid < 0) - return -EINVAL; - if (copy_from_user(&lparam, param, sizeof(struct sched_param))) - return -EFAULT; - - rcu_read_lock(); - retval = -ESRCH; - p = find_process_by_pid(pid); - 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; -} - -/* - * Mimics kernel/events/core.c perf_copy_attr(). - */ -static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr) -{ - u32 size; - int ret; - - /* Zero the full structure, so that a short copy will be nice: */ - memset(attr, 0, sizeof(*attr)); - - ret = get_user(size, &uattr->size); - if (ret) - return ret; - - /* ABI compatibility quirk: */ - if (!size) - size = SCHED_ATTR_SIZE_VER0; - if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE) - goto err_size; - - ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size); - if (ret) { - if (ret == -E2BIG) - goto err_size; - return ret; - } - - 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? - */ - attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); - - return 0; - -err_size: - put_user(sizeof(*attr), &uattr->size); - return -E2BIG; -} - -static void get_params(struct task_struct *p, struct sched_attr *attr) -{ - if (task_has_dl_policy(p)) - __getparam_dl(p, attr); - else if (task_has_rt_policy(p)) - attr->sched_priority = p->rt_priority; - else - attr->sched_nice = task_nice(p); -} - -/** - * sys_sched_setscheduler - set/change the scheduler policy and RT priority - * @pid: the pid in question. - * @policy: new policy. - * @param: structure containing the new RT priority. - * - * Return: 0 on success. An error code otherwise. - */ -SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) -{ - if (policy < 0) - return -EINVAL; - - return do_sched_setscheduler(pid, policy, param); -} - -/** - * sys_sched_setparam - set/change the RT priority of a thread - * @pid: the pid in question. - * @param: structure containing the new RT priority. - * - * Return: 0 on success. An error code otherwise. - */ -SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) -{ - return do_sched_setscheduler(pid, SETPARAM_POLICY, param); -} - -/** - * sys_sched_setattr - same as above, but with extended sched_attr - * @pid: the pid in question. - * @uattr: structure containing the extended parameters. - * @flags: for future extension. - */ -SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, flags) -{ - struct sched_attr attr; - struct task_struct *p; - int retval; - - if (!uattr || pid < 0 || flags) - return -EINVAL; - - retval = sched_copy_attr(uattr, &attr); - if (retval) - return retval; - - 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 (likely(p)) - get_task_struct(p); - rcu_read_unlock(); - - if (likely(p)) { - if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS) - get_params(p, &attr); - retval = sched_setattr(p, &attr); - put_task_struct(p); - } - - return retval; -} - -/** - * sys_sched_getscheduler - get the policy (scheduling class) of a thread - * @pid: the pid in question. - * - * Return: On success, the policy of the thread. Otherwise, a negative error - * code. - */ -SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) -{ - struct task_struct *p; - int retval; - - if (pid < 0) - return -EINVAL; - - retval = -ESRCH; - rcu_read_lock(); - p = find_process_by_pid(pid); - if (p) { - retval = security_task_getscheduler(p); - if (!retval) - retval = p->policy - | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); - } - rcu_read_unlock(); - return retval; -} - -/** - * sys_sched_getparam - get the RT priority of a thread - * @pid: the pid in question. - * @param: structure containing the RT priority. - * - * Return: On success, 0 and the RT priority is in @param. Otherwise, an error - * code. - */ -SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) -{ - struct sched_param lp = { .sched_priority = 0 }; - struct task_struct *p; - int retval; - - if (!param || pid < 0) - return -EINVAL; - - rcu_read_lock(); - p = find_process_by_pid(pid); - retval = -ESRCH; - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - if (task_has_rt_policy(p)) - lp.sched_priority = p->rt_priority; - rcu_read_unlock(); - - /* - * This one might sleep, we cannot do it with a spinlock held ... - */ - retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; - - return retval; - -out_unlock: - rcu_read_unlock(); - return retval; -} - -/* - * 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) -{ - unsigned int ksize = sizeof(*kattr); - - if (!access_ok(uattr, usize)) - return -EFAULT; - - /* - * 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. - */ - kattr->size = min(usize, ksize); - - if (copy_to_user(uattr, kattr, kattr->size)) - return -EFAULT; - - return 0; -} - -/** - * sys_sched_getattr - similar to sched_getparam, but with sched_attr - * @pid: the pid in question. - * @uattr: structure containing the extended parameters. - * @usize: sizeof(attr) for fwd/bwd comp. - * @flags: for future extension. - */ -SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, - unsigned int, usize, unsigned int, flags) -{ - struct sched_attr kattr = { }; - struct task_struct *p; - int retval; - - if (!uattr || pid < 0 || usize > PAGE_SIZE || - usize < SCHED_ATTR_SIZE_VER0 || flags) - return -EINVAL; - - rcu_read_lock(); - p = find_process_by_pid(pid); - retval = -ESRCH; - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - kattr.sched_policy = p->policy; - if (p->sched_reset_on_fork) - kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; - get_params(p, &kattr); - kattr.sched_flags &= SCHED_FLAG_ALL; - -#ifdef CONFIG_UCLAMP_TASK - /* - * This could race with another potential updater, but this is fine - * because it'll correctly read the old or the new value. We don't need - * to guarantee who wins the race as long as it doesn't return garbage. - */ - kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value; - kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value; -#endif - - rcu_read_unlock(); - - return sched_attr_copy_to_user(uattr, &kattr, usize); - -out_unlock: - rcu_read_unlock(); - return retval; -} - -#ifdef CONFIG_SMP -int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask) -{ - int ret = 0; - - /* - * If the task isn't a deadline task or admission control is - * disabled then we don't care about affinity changes. - */ - if (!task_has_dl_policy(p) || !dl_bandwidth_enabled()) - return 0; - - /* - * Since bandwidth control happens on root_domain basis, - * if admission test is enabled, we only admit -deadline - * tasks allowed to run on all the CPUs in the task's - * root_domain. - */ - rcu_read_lock(); - if (!cpumask_subset(task_rq(p)->rd->span, mask)) - ret = -EBUSY; - rcu_read_unlock(); - return ret; -} -#endif - -static int -__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx) -{ - int retval; - cpumask_var_t cpus_allowed, new_mask; - - if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) - return -ENOMEM; - - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { - retval = -ENOMEM; - goto out_free_cpus_allowed; - } - - cpuset_cpus_allowed(p, cpus_allowed); - cpumask_and(new_mask, ctx->new_mask, cpus_allowed); - - ctx->new_mask = new_mask; - ctx->flags |= SCA_CHECK; - - retval = dl_task_check_affinity(p, new_mask); - if (retval) - goto out_free_new_mask; - - retval = __set_cpus_allowed_ptr(p, ctx); - if (retval) - goto out_free_new_mask; - - cpuset_cpus_allowed(p, cpus_allowed); - if (!cpumask_subset(new_mask, cpus_allowed)) { - /* - * We must have raced with a concurrent cpuset update. - * Just reset the cpumask to the cpuset's cpus_allowed. - */ - cpumask_copy(new_mask, cpus_allowed); - - /* - * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr() - * will restore the previous user_cpus_ptr value. + * Boosting condition are: + * 1. -rt task is running and holds mutex A + * --> -dl task blocks on mutex A * - * In the unlikely event a previous user_cpus_ptr exists, - * we need to further restrict the mask to what is allowed - * by that old user_cpus_ptr. + * 2. -dl task is running and holds mutex A + * --> -dl task blocks on mutex A and could preempt the + * running task */ - if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) { - bool empty = !cpumask_and(new_mask, new_mask, - ctx->user_mask); - - if (WARN_ON_ONCE(empty)) - cpumask_copy(new_mask, cpus_allowed); - } - __set_cpus_allowed_ptr(p, ctx); - retval = -EINVAL; - } - -out_free_new_mask: - free_cpumask_var(new_mask); -out_free_cpus_allowed: - free_cpumask_var(cpus_allowed); - return retval; -} - -long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) -{ - struct affinity_context ac; - struct cpumask *user_mask; - struct task_struct *p; - int retval; - - rcu_read_lock(); - - p = find_process_by_pid(pid); - if (!p) { - rcu_read_unlock(); - return -ESRCH; - } - - /* Prevent p going away */ - get_task_struct(p); - rcu_read_unlock(); - - if (p->flags & PF_NO_SETAFFINITY) { - retval = -EINVAL; - goto out_put_task; - } - - if (!check_same_owner(p)) { - rcu_read_lock(); - if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { - rcu_read_unlock(); - retval = -EPERM; - goto out_put_task; + if (dl_prio(prio)) { + if (!dl_prio(p->normal_prio) || + (pi_task && dl_prio(pi_task->prio) && + dl_entity_preempt(&pi_task->dl, &p->dl))) { + p->dl.pi_se = pi_task->dl.pi_se; + scope->flags |= ENQUEUE_REPLENISH; + } else { + p->dl.pi_se = &p->dl; + } + } else if (rt_prio(prio)) { + if (dl_prio(oldprio)) + p->dl.pi_se = &p->dl; + if (oldprio < prio) + scope->flags |= ENQUEUE_HEAD; + } else { + if (dl_prio(oldprio)) + p->dl.pi_se = &p->dl; + if (rt_prio(oldprio)) + p->rt.timeout = 0; } - rcu_read_unlock(); - } - retval = security_task_setscheduler(p); - if (retval) - goto out_put_task; - - /* - * With non-SMP configs, user_cpus_ptr/user_mask isn't used and - * alloc_user_cpus_ptr() returns NULL. - */ - user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE); - if (user_mask) { - cpumask_copy(user_mask, in_mask); - } else if (IS_ENABLED(CONFIG_SMP)) { - retval = -ENOMEM; - goto out_put_task; + p->sched_class = next_class; + p->prio = prio; } - - ac = (struct affinity_context){ - .new_mask = in_mask, - .user_mask = user_mask, - .flags = SCA_USER, - }; - - retval = __sched_setaffinity(p, &ac); - kfree(ac.user_mask); - -out_put_task: - put_task_struct(p); - return retval; -} - -static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, - struct cpumask *new_mask) -{ - if (len < cpumask_size()) - cpumask_clear(new_mask); - else if (len > cpumask_size()) - len = cpumask_size(); - - return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; -} - -/** - * sys_sched_setaffinity - set the CPU affinity of a process - * @pid: pid of the process - * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to the new CPU mask - * - * Return: 0 on success. An error code otherwise. - */ -SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, - unsigned long __user *, user_mask_ptr) -{ - cpumask_var_t new_mask; - int retval; - - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) - return -ENOMEM; - - retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); - if (retval == 0) - retval = sched_setaffinity(pid, new_mask); - free_cpumask_var(new_mask); - return retval; -} - -long sched_getaffinity(pid_t pid, struct cpumask *mask) -{ - struct task_struct *p; - unsigned long flags; - int retval; - - rcu_read_lock(); - - retval = -ESRCH; - p = find_process_by_pid(pid); - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - raw_spin_lock_irqsave(&p->pi_lock, flags); - cpumask_and(mask, &p->cpus_mask, cpu_active_mask); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); - out_unlock: - rcu_read_unlock(); - - return retval; -} - -/** - * sys_sched_getaffinity - get the CPU affinity of a process - * @pid: pid of the process - * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to hold the current CPU mask - * - * Return: size of CPU mask copied to user_mask_ptr on success. An - * error code otherwise. - */ -SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, - unsigned long __user *, user_mask_ptr) -{ - int ret; - cpumask_var_t mask; - - if ((len * BITS_PER_BYTE) < nr_cpu_ids) - return -EINVAL; - if (len & (sizeof(unsigned long)-1)) - return -EINVAL; - - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) - return -ENOMEM; - - ret = sched_getaffinity(pid, mask); - if (ret == 0) { - unsigned int retlen = min(len, cpumask_size()); - - if (copy_to_user(user_mask_ptr, mask, retlen)) - ret = -EFAULT; - else - ret = retlen; - } - free_cpumask_var(mask); - - return ret; -} + /* Caller holds task_struct::pi_lock, IRQs are still disabled */ -static void do_sched_yield(void) -{ - struct rq_flags rf; - struct rq *rq; - - rq = this_rq_lock_irq(&rf); - - schedstat_inc(rq->yld_count); - current->sched_class->yield_task(rq); - - preempt_disable(); - rq_unlock_irq(rq, &rf); - sched_preempt_enable_no_resched(); - - schedule(); -} - -/** - * sys_sched_yield - yield the current processor to other threads. - * - * This function yields the current CPU to other tasks. If there are no - * other threads running on this CPU then this function will return. - * - * Return: 0. - */ -SYSCALL_DEFINE0(sched_yield) -{ - do_sched_yield(); - return 0; + rq_unpin_lock(rq, &rf); + __balance_callbacks(rq); + rq_repin_lock(rq, &rf); + __task_rq_unlock(rq, p, &rf); } +#endif /* CONFIG_RT_MUTEXES */ #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) int __sched __cond_resched(void) { - if (should_resched(0)) { + if (should_resched(0) && !irqs_disabled()) { preempt_schedule_common(); return 1; } /* - * In preemptible kernels, ->rcu_read_lock_nesting tells the tick + * In PREEMPT_RCU kernels, ->rcu_read_lock_nesting tells the tick * whether the current CPU is in an RCU read-side critical section, * so the tick can report quiescent states even for CPUs looping * in kernel context. In contrast, in non-preemptible kernels, @@ -8463,6 +7386,8 @@ int __sched __cond_resched(void) * RCU quiescent state. Therefore, the following code causes * cond_resched() to report a quiescent state, but only when RCU * is in urgent need of one. + * A third case, preemptible, but non-PREEMPT_RCU provides for + * urgently needed quiescent states via rcu_flavor_sched_clock_irq(). */ #ifndef CONFIG_PREEMPT_RCU rcu_all_qs(); @@ -8473,17 +7398,17 @@ EXPORT_SYMBOL(__cond_resched); #endif #ifdef CONFIG_PREEMPT_DYNAMIC -#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) -#define cond_resched_dynamic_enabled __cond_resched -#define cond_resched_dynamic_disabled ((void *)&__static_call_return0) +# ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL +# define cond_resched_dynamic_enabled __cond_resched +# define cond_resched_dynamic_disabled ((void *)&__static_call_return0) DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched); EXPORT_STATIC_CALL_TRAMP(cond_resched); -#define might_resched_dynamic_enabled __cond_resched -#define might_resched_dynamic_disabled ((void *)&__static_call_return0) +# define might_resched_dynamic_enabled __cond_resched +# define might_resched_dynamic_disabled ((void *)&__static_call_return0) DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched); EXPORT_STATIC_CALL_TRAMP(might_resched); -#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched); int __sched dynamic_cond_resched(void) { @@ -8501,8 +7426,8 @@ int __sched dynamic_might_resched(void) return __cond_resched(); } EXPORT_SYMBOL(dynamic_might_resched); -#endif -#endif +# endif +#endif /* CONFIG_PREEMPT_DYNAMIC */ /* * __cond_resched_lock() - if a reschedule is pending, drop the given lock, @@ -8568,9 +7493,9 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write); #ifdef CONFIG_PREEMPT_DYNAMIC -#ifdef CONFIG_GENERIC_ENTRY -#include <linux/entry-common.h> -#endif +# ifdef CONFIG_GENERIC_IRQ_ENTRY +# include <linux/irq-entry-common.h> +# endif /* * SC:cond_resched @@ -8586,6 +7511,7 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write); * preempt_schedule <- NOP * preempt_schedule_notrace <- NOP * irqentry_exit_cond_resched <- NOP + * dynamic_preempt_lazy <- false * * VOLUNTARY: * cond_resched <- __cond_resched @@ -8593,6 +7519,7 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write); * preempt_schedule <- NOP * preempt_schedule_notrace <- NOP * irqentry_exit_cond_resched <- NOP + * dynamic_preempt_lazy <- false * * FULL: * cond_resched <- RET0 @@ -8600,6 +7527,15 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write); * preempt_schedule <- preempt_schedule * preempt_schedule_notrace <- preempt_schedule_notrace * irqentry_exit_cond_resched <- irqentry_exit_cond_resched + * dynamic_preempt_lazy <- false + * + * LAZY: + * cond_resched <- RET0 + * might_resched <- RET0 + * preempt_schedule <- preempt_schedule + * preempt_schedule_notrace <- preempt_schedule_notrace + * irqentry_exit_cond_resched <- irqentry_exit_cond_resched + * dynamic_preempt_lazy <- true */ enum { @@ -8607,35 +7543,48 @@ enum { preempt_dynamic_none, preempt_dynamic_voluntary, preempt_dynamic_full, + preempt_dynamic_lazy, }; int preempt_dynamic_mode = preempt_dynamic_undefined; int sched_dynamic_mode(const char *str) { +# ifndef CONFIG_PREEMPT_RT if (!strcmp(str, "none")) return preempt_dynamic_none; if (!strcmp(str, "voluntary")) return preempt_dynamic_voluntary; +# endif if (!strcmp(str, "full")) return preempt_dynamic_full; +# ifdef CONFIG_ARCH_HAS_PREEMPT_LAZY + if (!strcmp(str, "lazy")) + return preempt_dynamic_lazy; +# endif + return -EINVAL; } -#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) -#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled) -#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled) -#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) -#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key) -#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key) -#else -#error "Unsupported PREEMPT_DYNAMIC mechanism" -#endif +# define preempt_dynamic_key_enable(f) static_key_enable(&sk_dynamic_##f.key) +# define preempt_dynamic_key_disable(f) static_key_disable(&sk_dynamic_##f.key) -void sched_dynamic_update(int mode) +# if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) +# define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled) +# define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled) +# elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +# define preempt_dynamic_enable(f) preempt_dynamic_key_enable(f) +# define preempt_dynamic_disable(f) preempt_dynamic_key_disable(f) +# else +# error "Unsupported PREEMPT_DYNAMIC mechanism" +# endif + +static DEFINE_MUTEX(sched_dynamic_mutex); + +static void __sched_dynamic_update(int mode) { /* * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in @@ -8646,6 +7595,7 @@ void sched_dynamic_update(int mode) preempt_dynamic_enable(preempt_schedule); preempt_dynamic_enable(preempt_schedule_notrace); preempt_dynamic_enable(irqentry_exit_cond_resched); + preempt_dynamic_key_disable(preempt_lazy); switch (mode) { case preempt_dynamic_none: @@ -8654,7 +7604,9 @@ void sched_dynamic_update(int mode) preempt_dynamic_disable(preempt_schedule); preempt_dynamic_disable(preempt_schedule_notrace); preempt_dynamic_disable(irqentry_exit_cond_resched); - pr_info("Dynamic Preempt: none\n"); + preempt_dynamic_key_disable(preempt_lazy); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: none\n"); break; case preempt_dynamic_voluntary: @@ -8663,7 +7615,9 @@ void sched_dynamic_update(int mode) preempt_dynamic_disable(preempt_schedule); preempt_dynamic_disable(preempt_schedule_notrace); preempt_dynamic_disable(irqentry_exit_cond_resched); - pr_info("Dynamic Preempt: voluntary\n"); + preempt_dynamic_key_disable(preempt_lazy); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: voluntary\n"); break; case preempt_dynamic_full: @@ -8672,13 +7626,33 @@ void sched_dynamic_update(int mode) preempt_dynamic_enable(preempt_schedule); preempt_dynamic_enable(preempt_schedule_notrace); preempt_dynamic_enable(irqentry_exit_cond_resched); - pr_info("Dynamic Preempt: full\n"); + preempt_dynamic_key_disable(preempt_lazy); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: full\n"); + break; + + case preempt_dynamic_lazy: + preempt_dynamic_disable(cond_resched); + preempt_dynamic_disable(might_resched); + preempt_dynamic_enable(preempt_schedule); + preempt_dynamic_enable(preempt_schedule_notrace); + preempt_dynamic_enable(irqentry_exit_cond_resched); + preempt_dynamic_key_enable(preempt_lazy); + if (mode != preempt_dynamic_mode) + pr_info("Dynamic Preempt: lazy\n"); break; } preempt_dynamic_mode = mode; } +void sched_dynamic_update(int mode) +{ + mutex_lock(&sched_dynamic_mutex); + __sched_dynamic_update(mode); + mutex_unlock(&sched_dynamic_mutex); +} + static int __init setup_preempt_mode(char *str) { int mode = sched_dynamic_mode(str); @@ -8699,6 +7673,8 @@ static void __init preempt_dynamic_init(void) sched_dynamic_update(preempt_dynamic_none); } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { sched_dynamic_update(preempt_dynamic_voluntary); + } else if (IS_ENABLED(CONFIG_PREEMPT_LAZY)) { + sched_dynamic_update(preempt_dynamic_lazy); } else { /* Default static call setting, nothing to do */ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); @@ -8708,7 +7684,7 @@ static void __init preempt_dynamic_init(void) } } -#define PREEMPT_MODEL_ACCESSOR(mode) \ +# define PREEMPT_MODEL_ACCESSOR(mode) \ bool preempt_model_##mode(void) \ { \ WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \ @@ -8719,115 +7695,60 @@ static void __init preempt_dynamic_init(void) PREEMPT_MODEL_ACCESSOR(none); PREEMPT_MODEL_ACCESSOR(voluntary); PREEMPT_MODEL_ACCESSOR(full); +PREEMPT_MODEL_ACCESSOR(lazy); + +#else /* !CONFIG_PREEMPT_DYNAMIC: */ -#else /* !CONFIG_PREEMPT_DYNAMIC */ +#define preempt_dynamic_mode -1 static inline void preempt_dynamic_init(void) { } -#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */ +#endif /* CONFIG_PREEMPT_DYNAMIC */ -/** - * yield - yield the current processor to other threads. - * - * Do not ever use this function, there's a 99% chance you're doing it wrong. - * - * The scheduler is at all times free to pick the calling task as the most - * eligible task to run, if removing the yield() call from your code breaks - * it, it's already broken. - * - * Typical broken usage is: - * - * while (!event) - * yield(); - * - * where one assumes that yield() will let 'the other' process run that will - * make event true. If the current task is a SCHED_FIFO task that will never - * happen. Never use yield() as a progress guarantee!! - * - * If you want to use yield() to wait for something, use wait_event(). - * If you want to use yield() to be 'nice' for others, use cond_resched(). - * If you still want to use yield(), do not! - */ -void __sched yield(void) -{ - set_current_state(TASK_RUNNING); - do_sched_yield(); -} -EXPORT_SYMBOL(yield); +const char *preempt_modes[] = { + "none", "voluntary", "full", "lazy", NULL, +}; -/** - * yield_to - yield the current processor to another thread in - * your thread group, or accelerate that thread toward the - * processor it's on. - * @p: target task - * @preempt: whether task preemption is allowed or not - * - * It's the caller's job to ensure that the target task struct - * can't go away on us before we can do any checks. - * - * Return: - * true (>0) if we indeed boosted the target task. - * false (0) if we failed to boost the target. - * -ESRCH if there's no task to yield to. - */ -int __sched yield_to(struct task_struct *p, bool preempt) +const char *preempt_model_str(void) { - struct task_struct *curr = current; - struct rq *rq, *p_rq; - unsigned long flags; - int yielded = 0; - - local_irq_save(flags); - rq = this_rq(); + bool brace = IS_ENABLED(CONFIG_PREEMPT_RT) && + (IS_ENABLED(CONFIG_PREEMPT_DYNAMIC) || + IS_ENABLED(CONFIG_PREEMPT_LAZY)); + static char buf[128]; -again: - p_rq = task_rq(p); - /* - * If we're the only runnable task on the rq and target rq also - * has only one task, there's absolutely no point in yielding. - */ - if (rq->nr_running == 1 && p_rq->nr_running == 1) { - yielded = -ESRCH; - goto out_irq; - } + if (IS_ENABLED(CONFIG_PREEMPT_BUILD)) { + struct seq_buf s; - double_rq_lock(rq, p_rq); - if (task_rq(p) != p_rq) { - double_rq_unlock(rq, p_rq); - goto again; - } + seq_buf_init(&s, buf, sizeof(buf)); + seq_buf_puts(&s, "PREEMPT"); - if (!curr->sched_class->yield_to_task) - goto out_unlock; + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + seq_buf_printf(&s, "%sRT%s", + brace ? "_{" : "_", + brace ? "," : ""); - if (curr->sched_class != p->sched_class) - goto out_unlock; + if (IS_ENABLED(CONFIG_PREEMPT_DYNAMIC)) { + seq_buf_printf(&s, "(%s)%s", + preempt_dynamic_mode >= 0 ? + preempt_modes[preempt_dynamic_mode] : "undef", + brace ? "}" : ""); + return seq_buf_str(&s); + } - if (task_on_cpu(p_rq, p) || !task_is_running(p)) - goto out_unlock; + if (IS_ENABLED(CONFIG_PREEMPT_LAZY)) { + seq_buf_printf(&s, "LAZY%s", + brace ? "}" : ""); + return seq_buf_str(&s); + } - yielded = curr->sched_class->yield_to_task(rq, p); - if (yielded) { - schedstat_inc(rq->yld_count); - /* - * Make p's CPU reschedule; pick_next_entity takes care of - * fairness. - */ - if (preempt && rq != p_rq) - resched_curr(p_rq); + return seq_buf_str(&s); } -out_unlock: - double_rq_unlock(rq, p_rq); -out_irq: - local_irq_restore(flags); - - if (yielded > 0) - schedule(); + if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BUILD)) + return "VOLUNTARY"; - return yielded; + return "NONE"; } -EXPORT_SYMBOL_GPL(yield_to); int io_schedule_prepare(void) { @@ -8870,134 +7791,9 @@ void __sched io_schedule(void) } EXPORT_SYMBOL(io_schedule); -/** - * sys_sched_get_priority_max - return maximum RT priority. - * @policy: scheduling class. - * - * Return: On success, this syscall returns the maximum - * rt_priority that can be used by a given scheduling class. - * On failure, a negative error code is returned. - */ -SYSCALL_DEFINE1(sched_get_priority_max, int, policy) -{ - int ret = -EINVAL; - - switch (policy) { - case SCHED_FIFO: - case SCHED_RR: - ret = MAX_RT_PRIO-1; - break; - case SCHED_DEADLINE: - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - ret = 0; - break; - } - return ret; -} - -/** - * sys_sched_get_priority_min - return minimum RT priority. - * @policy: scheduling class. - * - * Return: On success, this syscall returns the minimum - * rt_priority that can be used by a given scheduling class. - * On failure, a negative error code is returned. - */ -SYSCALL_DEFINE1(sched_get_priority_min, int, policy) -{ - int ret = -EINVAL; - - switch (policy) { - case SCHED_FIFO: - case SCHED_RR: - ret = 1; - break; - case SCHED_DEADLINE: - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - ret = 0; - } - return ret; -} - -static int sched_rr_get_interval(pid_t pid, struct timespec64 *t) -{ - struct task_struct *p; - unsigned int time_slice; - struct rq_flags rf; - struct rq *rq; - int retval; - - if (pid < 0) - return -EINVAL; - - retval = -ESRCH; - rcu_read_lock(); - p = find_process_by_pid(pid); - if (!p) - goto out_unlock; - - retval = security_task_getscheduler(p); - if (retval) - goto out_unlock; - - rq = task_rq_lock(p, &rf); - time_slice = 0; - if (p->sched_class->get_rr_interval) - time_slice = p->sched_class->get_rr_interval(rq, p); - task_rq_unlock(rq, p, &rf); - - rcu_read_unlock(); - jiffies_to_timespec64(time_slice, t); - return 0; - -out_unlock: - rcu_read_unlock(); - return retval; -} - -/** - * sys_sched_rr_get_interval - return the default timeslice of a process. - * @pid: pid of the process. - * @interval: userspace pointer to the timeslice value. - * - * this syscall writes the default timeslice value of a given process - * into the user-space timespec buffer. A value of '0' means infinity. - * - * Return: On success, 0 and the timeslice is in @interval. Otherwise, - * an error code. - */ -SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, - struct __kernel_timespec __user *, interval) -{ - struct timespec64 t; - int retval = sched_rr_get_interval(pid, &t); - - if (retval == 0) - retval = put_timespec64(&t, interval); - - return retval; -} - -#ifdef CONFIG_COMPAT_32BIT_TIME -SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid, - struct old_timespec32 __user *, interval) -{ - struct timespec64 t; - int retval = sched_rr_get_interval(pid, &t); - - if (retval == 0) - retval = put_old_timespec32(&t, interval); - return retval; -} -#endif - void sched_show_task(struct task_struct *p) { - unsigned long free = 0; + unsigned long free; int ppid; if (!try_get_task_stack(p)) @@ -9007,20 +7803,19 @@ void sched_show_task(struct task_struct *p) if (task_is_running(p)) pr_cont(" running task "); -#ifdef CONFIG_DEBUG_STACK_USAGE free = stack_not_used(p); -#endif ppid = 0; rcu_read_lock(); if (pid_alive(p)) ppid = task_pid_nr(rcu_dereference(p->real_parent)); rcu_read_unlock(); - pr_cont(" stack:%-5lu pid:%-5d ppid:%-6d flags:0x%08lx\n", - free, task_pid_nr(p), ppid, - read_task_thread_flags(p)); + pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d task_flags:0x%04x flags:0x%08lx\n", + free, task_pid_nr(p), task_tgid_nr(p), + ppid, p->flags, read_task_thread_flags(p)); print_worker_info(KERN_INFO, p); print_stop_info(KERN_INFO, p); + print_scx_info(KERN_INFO, p); show_stack(p, NULL, KERN_INFO); put_task_stack(p); } @@ -9069,10 +7864,9 @@ void show_state_filter(unsigned int state_filter) sched_show_task(p); } -#ifdef CONFIG_SCHED_DEBUG if (!state_filter) sysrq_sched_debug_show(); -#endif + rcu_read_unlock(); /* * Only show locks if all tasks are dumped: @@ -9091,17 +7885,13 @@ void show_state_filter(unsigned int state_filter) */ void __init init_idle(struct task_struct *idle, int cpu) { -#ifdef CONFIG_SMP struct affinity_context ac = (struct affinity_context) { .new_mask = cpumask_of(cpu), .flags = 0, }; -#endif struct rq *rq = cpu_rq(cpu); unsigned long flags; - __sched_fork(0, idle); - raw_spin_lock_irqsave(&idle->pi_lock, flags); raw_spin_rq_lock(rq); @@ -9111,18 +7901,14 @@ void __init init_idle(struct task_struct *idle, int cpu) * PF_KTHREAD should already be set at this point; regardless, make it * look like a proper per-CPU kthread. */ - idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; + idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); -#ifdef CONFIG_SMP /* - * It's possible that init_idle() gets called multiple times on a task, - * in that case do_set_cpus_allowed() will not do the right thing. - * - * And since this is boot we can forgo the serialization. + * No validation and serialization required at boot time and for + * setting up the idle tasks of not yet online CPUs. */ set_cpus_allowed_common(idle, &ac); -#endif /* * We're having a chicken and egg problem, even though we are * holding rq->lock, the CPU isn't yet set to this CPU so the @@ -9138,11 +7924,10 @@ void __init init_idle(struct task_struct *idle, int cpu) rcu_read_unlock(); rq->idle = idle; + rq_set_donor(rq, idle); rcu_assign_pointer(rq->curr, idle); idle->on_rq = TASK_ON_RQ_QUEUED; -#ifdef CONFIG_SMP idle->on_cpu = 1; -#endif raw_spin_rq_unlock(rq); raw_spin_unlock_irqrestore(&idle->pi_lock, flags); @@ -9155,13 +7940,9 @@ void __init init_idle(struct task_struct *idle, int cpu) idle->sched_class = &idle_sched_class; ftrace_graph_init_idle_task(idle, cpu); vtime_init_idle(idle, cpu); -#ifdef CONFIG_SMP sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); -#endif } -#ifdef CONFIG_SMP - int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial) { @@ -9175,8 +7956,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, return ret; } -int task_can_attach(struct task_struct *p, - const struct cpumask *cs_effective_cpus) +int task_can_attach(struct task_struct *p) { int ret = 0; @@ -9189,21 +7969,9 @@ int task_can_attach(struct task_struct *p, * success of set_cpus_allowed_ptr() on all attached tasks * before cpus_mask may be changed. */ - if (p->flags & PF_NO_SETAFFINITY) { + if (p->flags & PF_NO_SETAFFINITY) ret = -EINVAL; - goto out; - } - if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_effective_cpus)) { - int cpu = cpumask_any_and(cpu_active_mask, cs_effective_cpus); - - if (unlikely(cpu >= nr_cpu_ids)) - return -EINVAL; - ret = dl_cpu_busy(cpu, p); - } - -out: return ret; } @@ -9234,44 +8002,34 @@ int migrate_task_to(struct task_struct *p, int target_cpu) */ void sched_setnuma(struct task_struct *p, int nid) { - bool queued, running; - struct rq_flags rf; - struct rq *rq; - - rq = task_rq_lock(p, &rf); - queued = task_on_rq_queued(p); - running = task_current(rq, p); - - if (queued) - dequeue_task(rq, p, DEQUEUE_SAVE); - if (running) - put_prev_task(rq, p); - - p->numa_preferred_nid = nid; - - if (queued) - enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); - if (running) - set_next_task(rq, p); - task_rq_unlock(rq, p, &rf); + guard(task_rq_lock)(p); + scoped_guard (sched_change, p, DEQUEUE_SAVE) + p->numa_preferred_nid = nid; } #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_HOTPLUG_CPU /* - * Ensure that the idle task is using init_mm right before its CPU goes - * offline. + * Invoked on the outgoing CPU in context of the CPU hotplug thread + * after ensuring that there are no user space tasks left on the CPU. + * + * If there is a lazy mm in use on the hotplug thread, drop it and + * switch to init_mm. + * + * The reference count on init_mm is dropped in finish_cpu(). */ -void idle_task_exit(void) +static void sched_force_init_mm(void) { struct mm_struct *mm = current->active_mm; - BUG_ON(cpu_online(smp_processor_id())); - BUG_ON(current != this_rq()->idle); - if (mm != &init_mm) { - switch_mm(mm, &init_mm, current); + mmgrab_lazy_tlb(&init_mm); + local_irq_disable(); + current->active_mm = &init_mm; + switch_mm_irqs_off(mm, &init_mm, current); + local_irq_enable(); finish_arch_post_lock_switch(); + mmdrop_lazy_tlb(mm); } /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ @@ -9284,18 +8042,15 @@ static int __balance_push_cpu_stop(void *arg) struct rq_flags rf; int cpu; - raw_spin_lock_irq(&p->pi_lock); - rq_lock(rq, &rf); - - update_rq_clock(rq); - - if (task_rq(p) == rq && task_on_rq_queued(p)) { + scoped_guard (raw_spinlock_irq, &p->pi_lock) { cpu = select_fallback_rq(rq->cpu, p); - rq = __migrate_task(rq, &rf, p, cpu); - } - rq_unlock(rq, &rf); - raw_spin_unlock_irq(&p->pi_lock); + rq_lock(rq, &rf); + update_rq_clock(rq); + if (task_rq(p) == rq && task_on_rq_queued(p)) + rq = __migrate_task(rq, &rf, p, cpu); + rq_unlock(rq, &rf); + } put_task_struct(p); @@ -9360,9 +8115,11 @@ static void balance_push(struct rq *rq) * Temporarily drop rq->lock such that we can wake-up the stop task. * Both preemption and IRQs are still disabled. */ + preempt_disable(); raw_spin_rq_unlock(rq); stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task, this_cpu_ptr(&push_work)); + preempt_enable(); /* * At this point need_resched() is true and we'll take the loop in * schedule(). The next pick is obviously going to be the stop task @@ -9401,7 +8158,7 @@ static void balance_hotplug_wait(void) TASK_UNINTERRUPTIBLE); } -#else +#else /* !CONFIG_HOTPLUG_CPU: */ static inline void balance_push(struct rq *rq) { @@ -9415,7 +8172,7 @@ static inline void balance_hotplug_wait(void) { } -#endif /* CONFIG_HOTPLUG_CPU */ +#endif /* !CONFIG_HOTPLUG_CPU */ void set_rq_online(struct rq *rq) { @@ -9437,6 +8194,7 @@ void set_rq_offline(struct rq *rq) if (rq->online) { const struct sched_class *class; + update_rq_clock(rq); for_each_class(class) { if (class->rq_offline) class->rq_offline(rq); @@ -9447,6 +8205,30 @@ void set_rq_offline(struct rq *rq) } } +static inline void sched_set_rq_online(struct rq *rq, int cpu) +{ + struct rq_flags rf; + + rq_lock_irqsave(rq, &rf); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_online(rq); + } + rq_unlock_irqrestore(rq, &rf); +} + +static inline void sched_set_rq_offline(struct rq *rq, int cpu) +{ + struct rq_flags rf; + + rq_lock_irqsave(rq, &rf); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + rq_unlock_irqrestore(rq, &rf); +} + /* * used to mark begin/end of suspend/resume: */ @@ -9469,7 +8251,7 @@ static void cpuset_cpu_active(void) * operation in the resume sequence, just build a single sched * domain, ignoring cpusets. */ - partition_sched_domains(1, NULL, NULL); + cpuset_reset_sched_domains(); if (--num_cpus_frozen) return; /* @@ -9482,25 +8264,35 @@ static void cpuset_cpu_active(void) cpuset_update_active_cpus(); } -static int cpuset_cpu_inactive(unsigned int cpu) +static void cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - int ret = dl_cpu_busy(cpu, NULL); - - if (ret) - return ret; cpuset_update_active_cpus(); } else { num_cpus_frozen++; - partition_sched_domains(1, NULL, NULL); + cpuset_reset_sched_domains(); } - return 0; +} + +static inline void sched_smt_present_inc(int cpu) +{ +#ifdef CONFIG_SCHED_SMT + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_inc_cpuslocked(&sched_smt_present); +#endif +} + +static inline void sched_smt_present_dec(int cpu) +{ +#ifdef CONFIG_SCHED_SMT + if (cpumask_weight(cpu_smt_mask(cpu)) == 2) + static_branch_dec_cpuslocked(&sched_smt_present); +#endif } int sched_cpu_activate(unsigned int cpu) { struct rq *rq = cpu_rq(cpu); - struct rq_flags rf; /* * Clear the balance_push callback and prepare to schedule @@ -9508,13 +8300,10 @@ int sched_cpu_activate(unsigned int cpu) */ balance_push_set(cpu, false); -#ifdef CONFIG_SCHED_SMT /* * When going up, increment the number of cores with SMT present. */ - if (cpumask_weight(cpu_smt_mask(cpu)) == 2) - static_branch_inc_cpuslocked(&sched_smt_present); -#endif + sched_smt_present_inc(cpu); set_cpu_active(cpu, true); if (sched_smp_initialized) { @@ -9523,6 +8312,8 @@ int sched_cpu_activate(unsigned int cpu) cpuset_cpu_active(); } + scx_rq_activate(rq); + /* * Put the rq online, if not already. This happens: * @@ -9532,12 +8323,7 @@ int sched_cpu_activate(unsigned int cpu) * 2) At runtime, if cpuset_cpu_active() fails to rebuild the * domains. */ - rq_lock_irqsave(rq, &rf); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - set_rq_online(rq); - } - rq_unlock_irqrestore(rq, &rf); + sched_set_rq_online(rq, cpu); return 0; } @@ -9545,9 +8331,13 @@ int sched_cpu_activate(unsigned int cpu) int sched_cpu_deactivate(unsigned int cpu) { struct rq *rq = cpu_rq(cpu); - struct rq_flags rf; int ret; + ret = dl_bw_deactivate(cpu); + + if (ret) + return ret; + /* * Remove CPU from nohz.idle_cpus_mask to prevent participating in * load balancing when not active @@ -9572,25 +8362,20 @@ int sched_cpu_deactivate(unsigned int cpu) * Specifically, we rely on ttwu to no longer target this CPU, see * ttwu_queue_cond() and is_cpu_allowed(). * - * Do sync before park smpboot threads to take care the rcu boost case. + * Do sync before park smpboot threads to take care the RCU boost case. */ synchronize_rcu(); - rq_lock_irqsave(rq, &rf); - if (rq->rd) { - update_rq_clock(rq); - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - set_rq_offline(rq); - } - rq_unlock_irqrestore(rq, &rf); + sched_set_rq_offline(rq, cpu); + + scx_rq_deactivate(rq); -#ifdef CONFIG_SCHED_SMT /* * When going down, decrement the number of cores with SMT present. */ - if (cpumask_weight(cpu_smt_mask(cpu)) == 2) - static_branch_dec_cpuslocked(&sched_smt_present); + sched_smt_present_dec(cpu); +#ifdef CONFIG_SCHED_SMT sched_core_cpu_deactivate(cpu); #endif @@ -9598,13 +8383,7 @@ int sched_cpu_deactivate(unsigned int cpu) return 0; sched_update_numa(cpu, false); - ret = cpuset_cpu_inactive(cpu); - if (ret) { - balance_push_set(cpu, false); - set_cpu_active(cpu, true); - sched_update_numa(cpu, true); - return ret; - } + cpuset_cpu_inactive(cpu); sched_domains_numa_masks_clear(cpu); return 0; } @@ -9641,6 +8420,7 @@ int sched_cpu_starting(unsigned int cpu) int sched_cpu_wait_empty(unsigned int cpu) { balance_hotplug_wait(); + sched_force_init_mm(); return 0; } @@ -9648,7 +8428,7 @@ int sched_cpu_wait_empty(unsigned int cpu) * Since this CPU is going 'away' for a while, fold any nr_active delta we * might have. Called from the CPU stopper task after ensuring that the * stopper is the last running task on the CPU, so nr_active count is - * stable. We need to take the teardown thread which is calling this into + * stable. We need to take the tear-down thread which is calling this into * account, so we hand in adjust = 1 to the load calculation. * * Also see the comment "Global load-average calculations". @@ -9689,10 +8469,12 @@ int sched_cpu_dying(unsigned int cpu) sched_tick_stop(cpu); rq_lock_irqsave(rq, &rf); + update_rq_clock(rq); if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) { WARN(true, "Dying CPU not properly vacated!"); dump_rq_tasks(rq, KERN_WARNING); } + dl_server_stop(&rq->fair_server); rq_unlock_irqrestore(rq, &rf); calc_load_migrate(rq); @@ -9701,20 +8483,22 @@ int sched_cpu_dying(unsigned int cpu) sched_core_cpu_dying(cpu); return 0; } -#endif +#endif /* CONFIG_HOTPLUG_CPU */ void __init sched_init_smp(void) { sched_init_numa(NUMA_NO_NODE); + prandom_init_once(&sched_rnd_state); + /* * There's no userspace yet to cause hotplug operations; hence all the * CPU masks are stable and all blatant races in the below code cannot * happen. */ - mutex_lock(&sched_domains_mutex); + sched_domains_mutex_lock(); sched_init_domains(cpu_active_mask); - mutex_unlock(&sched_domains_mutex); + sched_domains_mutex_unlock(); /* Move init over to a non-isolated CPU */ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0) @@ -9725,6 +8509,8 @@ void __init sched_init_smp(void) init_sched_rt_class(); init_sched_dl_class(); + sched_init_dl_servers(); + sched_smp_initialized = true; } @@ -9735,13 +8521,6 @@ static int __init migration_init(void) } early_initcall(migration_init); -#else -void __init sched_init_smp(void) -{ - sched_init_granularity(); -} -#endif /* CONFIG_SMP */ - int in_sched_functions(unsigned long addr) { return in_lock_functions(addr) || @@ -9758,7 +8537,7 @@ struct task_group root_task_group; LIST_HEAD(task_groups); /* Cacheline aligned slab cache for task_group */ -static struct kmem_cache *task_group_cache __read_mostly; +static struct kmem_cache *task_group_cache __ro_after_init; #endif void __init sched_init(void) @@ -9767,11 +8546,13 @@ void __init sched_init(void) int i; /* Make sure the linker didn't screw up */ - BUG_ON(&idle_sched_class != &fair_sched_class + 1 || - &fair_sched_class != &rt_sched_class + 1 || - &rt_sched_class != &dl_sched_class + 1); -#ifdef CONFIG_SMP - BUG_ON(&dl_sched_class != &stop_sched_class + 1); + BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class)); + BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class)); + BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class)); + BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class)); +#ifdef CONFIG_SCHED_CLASS_EXT + BUG_ON(!sched_class_above(&fair_sched_class, &ext_sched_class)); + BUG_ON(!sched_class_above(&ext_sched_class, &idle_sched_class)); #endif wait_bit_init(); @@ -9793,8 +8574,11 @@ void __init sched_init(void) ptr += nr_cpu_ids * sizeof(void **); root_task_group.shares = ROOT_TASK_GROUP_LOAD; - init_cfs_bandwidth(&root_task_group.cfs_bandwidth); + init_cfs_bandwidth(&root_task_group.cfs_bandwidth, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_EXT_GROUP_SCHED + scx_tg_init(&root_task_group); +#endif /* CONFIG_EXT_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED root_task_group.rt_se = (struct sched_rt_entity **)ptr; ptr += nr_cpu_ids * sizeof(void **); @@ -9805,11 +8589,7 @@ void __init sched_init(void) #endif /* CONFIG_RT_GROUP_SCHED */ } - init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime()); - -#ifdef CONFIG_SMP init_defrootdomain(); -#endif #ifdef CONFIG_RT_GROUP_SCHED init_rt_bandwidth(&root_task_group.rt_bandwidth, @@ -9842,7 +8622,7 @@ void __init sched_init(void) /* * How much CPU bandwidth does root_task_group get? * - * In case of task-groups formed thr' the cgroup filesystem, it + * In case of task-groups formed through the cgroup filesystem, it * gets 100% of the CPU resources in the system. This overall * system CPU resource is divided among the tasks of * root_task_group and its child task-groups in a fair manner, @@ -9861,14 +8641,18 @@ void __init sched_init(void) init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ - rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; #ifdef CONFIG_RT_GROUP_SCHED + /* + * This is required for init cpu because rt.c:__enable_runtime() + * starts working after scheduler_running, which is not the case + * yet. + */ + rq->rt.rt_runtime = global_rt_runtime(); init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); #endif -#ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; + rq->cpu_capacity = SCHED_CAPACITY_SCALE; rq->balance_callback = &balance_push_callback; rq->active_balance = 0; rq->next_balance = jiffies; @@ -9877,8 +8661,6 @@ void __init sched_init(void) rq->online = 0; rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; - rq->wake_stamp = jiffies; - rq->wake_avg_idle = rq->avg_idle; rq->max_idle_balance_cost = sysctl_sched_migration_cost; INIT_LIST_HEAD(&rq->cfs_tasks); @@ -9893,13 +8675,14 @@ void __init sched_init(void) #ifdef CONFIG_HOTPLUG_CPU rcuwait_init(&rq->hotplug_wait); #endif -#endif /* CONFIG_SMP */ hrtick_rq_init(rq); atomic_set(&rq->nr_iowait, 0); + fair_server_init(rq); #ifdef CONFIG_SCHED_CORE rq->core = rq; rq->core_pick = NULL; + rq->core_dl_server = NULL; rq->core_enabled = 0; rq->core_tree = RB_ROOT; rq->core_forceidle_count = 0; @@ -9912,11 +8695,12 @@ void __init sched_init(void) } set_load_weight(&init_task, false); + init_task.se.slice = sysctl_sched_base_slice, /* * The boot idle thread does lazy MMU switching as well: */ - mmgrab(&init_mm); + mmgrab_lazy_tlb(&init_mm); enter_lazy_tlb(&init_mm, current); /* @@ -9933,15 +8717,16 @@ void __init sched_init(void) * but because we are the idle thread, we just pick up running again * when this runqueue becomes "idle". */ + __sched_fork(0, current); init_idle(current, smp_processor_id()); calc_load_update = jiffies + LOAD_FREQ; -#ifdef CONFIG_SMP idle_thread_set_boot_cpu(); + balance_push_set(smp_processor_id(), false); -#endif init_sched_fair_class(); + init_sched_ext_class(); psi_init(); @@ -10072,7 +8857,7 @@ void __cant_sleep(const char *file, int line, int preempt_offset) } EXPORT_SYMBOL_GPL(__cant_sleep); -#ifdef CONFIG_SMP +# ifdef CONFIG_SMP void __cant_migrate(const char *file, int line) { static unsigned long prev_jiffy; @@ -10103,8 +8888,8 @@ void __cant_migrate(const char *file, int line) add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } EXPORT_SYMBOL_GPL(__cant_migrate); -#endif -#endif +# endif /* CONFIG_SMP */ +#endif /* CONFIG_DEBUG_ATOMIC_SLEEP */ #ifdef CONFIG_MAGIC_SYSRQ void normalize_rt_tasks(void) @@ -10127,7 +8912,7 @@ void normalize_rt_tasks(void) schedstat_set(p->stats.sleep_start, 0); schedstat_set(p->stats.block_start, 0); - if (!dl_task(p) && !rt_task(p)) { + if (!rt_or_dl_task(p)) { /* * Renice negative nice level userspace * tasks back to 0: @@ -10144,9 +8929,9 @@ void normalize_rt_tasks(void) #endif /* CONFIG_MAGIC_SYSRQ */ -#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) +#ifdef CONFIG_KGDB_KDB /* - * These functions are only useful for the IA64 MCA handling, or kdb. + * These functions are only useful for KDB. * * They can only be called when the whole system has been * stopped - every CPU needs to be quiescent, and no scheduling @@ -10168,30 +8953,7 @@ struct task_struct *curr_task(int cpu) return cpu_curr(cpu); } -#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ - -#ifdef CONFIG_IA64 -/** - * ia64_set_curr_task - set the current task for a given CPU. - * @cpu: the processor in question. - * @p: the task pointer to set. - * - * Description: This function must only be used when non-maskable interrupts - * are serviced on a separate stack. It allows the architecture to switch the - * notion of the current task on a CPU in a non-blocking manner. This function - * must be called with all CPU's synchronized, and interrupts disabled, the - * and caller must save the original value of the current task (see - * curr_task() above) and restore that value before reenabling interrupts and - * re-starting the system. - * - * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! - */ -void ia64_set_curr_task(int cpu, struct task_struct *p) -{ - cpu_curr(cpu) = p; -} - -#endif +#endif /* CONFIG_KGDB_KDB */ #ifdef CONFIG_CGROUP_SCHED /* task_group_lock serializes the addition/removal of task groups */ @@ -10250,6 +9012,7 @@ struct task_group *sched_create_group(struct task_group *parent) if (!alloc_rt_sched_group(tg, parent)) goto err; + scx_tg_init(tg); alloc_uclamp_sched_group(tg, parent); return tg; @@ -10264,7 +9027,7 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) unsigned long flags; spin_lock_irqsave(&task_group_lock, flags); - list_add_rcu(&tg->list, &task_groups); + list_add_tail_rcu(&tg->list, &task_groups); /* Root should already exist: */ WARN_ON(!parent); @@ -10277,7 +9040,7 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) online_fair_sched_group(tg); } -/* rcu callback to free various structures associated with a task group */ +/* RCU callback to free various structures associated with a task group */ static void sched_unregister_group_rcu(struct rcu_head *rhp) { /* Now it should be safe to free those cfs_rqs: */ @@ -10342,44 +9105,25 @@ static void sched_change_group(struct task_struct *tsk) * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect * its new group. */ -void sched_move_task(struct task_struct *tsk) +void sched_move_task(struct task_struct *tsk, bool for_autogroup) { - int queued, running, queue_flags = - DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK; - struct rq_flags rf; + unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; + bool resched = false; struct rq *rq; - rq = task_rq_lock(tsk, &rf); - update_rq_clock(rq); - - running = task_current(rq, tsk); - queued = task_on_rq_queued(tsk); + CLASS(task_rq_lock, rq_guard)(tsk); + rq = rq_guard.rq; - if (queued) - dequeue_task(rq, tsk, queue_flags); - if (running) - put_prev_task(rq, tsk); - - sched_change_group(tsk); - - if (queued) - enqueue_task(rq, tsk, queue_flags); - if (running) { - set_next_task(rq, tsk); - /* - * After changing group, the running task may have joined a - * throttled one but it's still the running task. Trigger a - * resched to make sure that task can still run. - */ - resched_curr(rq); + scoped_guard (sched_change, tsk, queue_flags) { + sched_change_group(tsk); + if (!for_autogroup) + scx_cgroup_move_task(tsk); + if (scope->running) + resched = true; } - task_rq_unlock(rq, tsk, &rf); -} - -static inline struct task_group *css_tg(struct cgroup_subsys_state *css) -{ - return css ? container_of(css, struct task_group, css) : NULL; + if (resched) + resched_curr(rq); } static struct cgroup_subsys_state * @@ -10405,22 +9149,32 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); struct task_group *parent = css_tg(css->parent); + int ret; + + ret = scx_tg_online(tg); + if (ret) + return ret; if (parent) sched_online_group(tg, parent); #ifdef CONFIG_UCLAMP_TASK_GROUP /* Propagate the effective uclamp value for the new group */ - mutex_lock(&uclamp_mutex); - rcu_read_lock(); + guard(mutex)(&uclamp_mutex); + guard(rcu)(); cpu_util_update_eff(css); - rcu_read_unlock(); - mutex_unlock(&uclamp_mutex); #endif return 0; } +static void cpu_cgroup_css_offline(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + + scx_tg_offline(tg); +} + static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); @@ -10438,19 +9192,23 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) sched_unregister_group(tg); } -#ifdef CONFIG_RT_GROUP_SCHED static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { +#ifdef CONFIG_RT_GROUP_SCHED struct task_struct *task; struct cgroup_subsys_state *css; + if (!rt_group_sched_enabled()) + goto scx_check; + cgroup_taskset_for_each(task, css, tset) { if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; } - return 0; +scx_check: +#endif /* CONFIG_RT_GROUP_SCHED */ + return scx_cgroup_can_attach(tset); } -#endif static void cpu_cgroup_attach(struct cgroup_taskset *tset) { @@ -10458,7 +9216,12 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset) struct cgroup_subsys_state *css; cgroup_taskset_for_each(task, css, tset) - sched_move_task(task); + sched_move_task(task, false); +} + +static void cpu_cgroup_cancel_attach(struct cgroup_taskset *tset) +{ + scx_cgroup_cancel_attach(tset); } #ifdef CONFIG_UCLAMP_TASK_GROUP @@ -10472,7 +9235,7 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css) unsigned int clamps; lockdep_assert_held(&uclamp_mutex); - SCHED_WARN_ON(!rcu_read_lock_held()); + WARN_ON_ONCE(!rcu_read_lock_held()); css_for_each_descendant_pre(css, top_css) { uc_parent = css_tg(css)->parent @@ -10564,10 +9327,10 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf, if (req.ret) return req.ret; - static_branch_enable(&sched_uclamp_used); + sched_uclamp_enable(); - mutex_lock(&uclamp_mutex); - rcu_read_lock(); + guard(mutex)(&uclamp_mutex); + guard(rcu)(); tg = css_tg(of_css(of)); if (tg->uclamp_req[clamp_id].value != req.util) @@ -10582,9 +9345,6 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf, /* 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; } @@ -10610,10 +9370,10 @@ static inline void cpu_uclamp_print(struct seq_file *sf, u64 percent; u32 rem; - rcu_read_lock(); - tg = css_tg(seq_css(sf)); - util_clamp = tg->uclamp_req[clamp_id].value; - rcu_read_unlock(); + scoped_guard (rcu) { + tg = css_tg(seq_css(sf)); + util_clamp = tg->uclamp_req[clamp_id].value; + } if (util_clamp == SCHED_CAPACITY_SCALE) { seq_puts(sf, "max\n"); @@ -10638,77 +9398,68 @@ static int cpu_uclamp_max_show(struct seq_file *sf, void *v) } #endif /* CONFIG_UCLAMP_TASK_GROUP */ +#ifdef CONFIG_GROUP_SCHED_WEIGHT +static unsigned long tg_weight(struct task_group *tg) +{ #ifdef CONFIG_FAIR_GROUP_SCHED + return scale_load_down(tg->shares); +#else + return sched_weight_from_cgroup(tg->scx.weight); +#endif +} + static int cpu_shares_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype, u64 shareval) { + int ret; + if (shareval > scale_load_down(ULONG_MAX)) shareval = MAX_SHARES; - return sched_group_set_shares(css_tg(css), scale_load(shareval)); + ret = sched_group_set_shares(css_tg(css), scale_load(shareval)); + if (!ret) + scx_group_set_weight(css_tg(css), + sched_weight_to_cgroup(shareval)); + return ret; } static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { - struct task_group *tg = css_tg(css); - - return (u64) scale_load_down(tg->shares); + return tg_weight(css_tg(css)); } +#endif /* CONFIG_GROUP_SCHED_WEIGHT */ #ifdef CONFIG_CFS_BANDWIDTH static DEFINE_MUTEX(cfs_constraints_mutex); -const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */ -static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */ -/* More than 203 days if BW_SHIFT equals 20. */ -static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC; - static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime); -static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota, - u64 burst) +static int tg_set_cfs_bandwidth(struct task_group *tg, + u64 period_us, u64 quota_us, u64 burst_us) { int i, ret = 0, runtime_enabled, runtime_was_enabled; struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + u64 period, quota, burst; - if (tg == &root_task_group) - return -EINVAL; - - /* - * Ensure we have at some amount of bandwidth every period. This is - * to prevent reaching a state of large arrears when throttled via - * entity_tick() resulting in prolonged exit starvation. - */ - if (quota < min_cfs_quota_period || period < min_cfs_quota_period) - return -EINVAL; - - /* - * Likewise, bound things on the other side by preventing insane quota - * periods. This also allows us to normalize in computing quota - * feasibility. - */ - if (period > max_cfs_quota_period) - return -EINVAL; + period = (u64)period_us * NSEC_PER_USEC; - /* - * Bound quota to defend quota against overflow during bandwidth shift. - */ - if (quota != RUNTIME_INF && quota > max_cfs_runtime) - return -EINVAL; + if (quota_us == RUNTIME_INF) + quota = RUNTIME_INF; + else + quota = (u64)quota_us * NSEC_PER_USEC; - if (quota != RUNTIME_INF && (burst > quota || - burst + quota > max_cfs_runtime)) - return -EINVAL; + burst = (u64)burst_us * NSEC_PER_USEC; /* * Prevent race between setting of cfs_rq->runtime_enabled and * unthrottle_offline_cfs_rqs(). */ - cpus_read_lock(); - mutex_lock(&cfs_constraints_mutex); + guard(cpus_read_lock)(); + guard(mutex)(&cfs_constraints_mutex); + ret = __cfs_schedulable(tg, period, quota); if (ret) - goto out_unlock; + return ret; runtime_enabled = quota != RUNTIME_INF; runtime_was_enabled = cfs_b->quota != RUNTIME_INF; @@ -10718,63 +9469,56 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota, */ if (runtime_enabled && !runtime_was_enabled) cfs_bandwidth_usage_inc(); - raw_spin_lock_irq(&cfs_b->lock); - cfs_b->period = ns_to_ktime(period); - cfs_b->quota = quota; - cfs_b->burst = burst; - __refill_cfs_bandwidth_runtime(cfs_b); + scoped_guard (raw_spinlock_irq, &cfs_b->lock) { + cfs_b->period = ns_to_ktime(period); + cfs_b->quota = quota; + cfs_b->burst = burst; - /* Restart the period timer (if active) to handle new period expiry: */ - if (runtime_enabled) - start_cfs_bandwidth(cfs_b); + __refill_cfs_bandwidth_runtime(cfs_b); - raw_spin_unlock_irq(&cfs_b->lock); + /* + * Restart the period timer (if active) to handle new + * period expiry: + */ + if (runtime_enabled) + start_cfs_bandwidth(cfs_b); + } for_each_online_cpu(i) { struct cfs_rq *cfs_rq = tg->cfs_rq[i]; struct rq *rq = cfs_rq->rq; - struct rq_flags rf; - rq_lock_irq(rq, &rf); + guard(rq_lock_irq)(rq); cfs_rq->runtime_enabled = runtime_enabled; - cfs_rq->runtime_remaining = 0; + cfs_rq->runtime_remaining = 1; if (cfs_rq->throttled) unthrottle_cfs_rq(cfs_rq); - rq_unlock_irq(rq, &rf); } + if (runtime_was_enabled && !runtime_enabled) cfs_bandwidth_usage_dec(); -out_unlock: - mutex_unlock(&cfs_constraints_mutex); - cpus_read_unlock(); - return ret; + return 0; } -static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) +static u64 tg_get_cfs_period(struct task_group *tg) { - u64 quota, period, burst; + u64 cfs_period_us; - period = ktime_to_ns(tg->cfs_bandwidth.period); - burst = tg->cfs_bandwidth.burst; - if (cfs_quota_us < 0) - quota = RUNTIME_INF; - else if ((u64)cfs_quota_us <= U64_MAX / NSEC_PER_USEC) - quota = (u64)cfs_quota_us * NSEC_PER_USEC; - else - return -EINVAL; + cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period); + do_div(cfs_period_us, NSEC_PER_USEC); - return tg_set_cfs_bandwidth(tg, period, quota, burst); + return cfs_period_us; } -static long tg_get_cfs_quota(struct task_group *tg) +static u64 tg_get_cfs_quota(struct task_group *tg) { u64 quota_us; if (tg->cfs_bandwidth.quota == RUNTIME_INF) - return -1; + return RUNTIME_INF; quota_us = tg->cfs_bandwidth.quota; do_div(quota_us, NSEC_PER_USEC); @@ -10782,45 +9526,7 @@ static long tg_get_cfs_quota(struct task_group *tg) return quota_us; } -static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us) -{ - u64 quota, period, burst; - - if ((u64)cfs_period_us > U64_MAX / NSEC_PER_USEC) - return -EINVAL; - - period = (u64)cfs_period_us * NSEC_PER_USEC; - quota = tg->cfs_bandwidth.quota; - burst = tg->cfs_bandwidth.burst; - - return tg_set_cfs_bandwidth(tg, period, quota, burst); -} - -static long tg_get_cfs_period(struct task_group *tg) -{ - u64 cfs_period_us; - - cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period); - do_div(cfs_period_us, NSEC_PER_USEC); - - return cfs_period_us; -} - -static int tg_set_cfs_burst(struct task_group *tg, long cfs_burst_us) -{ - u64 quota, period, burst; - - if ((u64)cfs_burst_us > U64_MAX / NSEC_PER_USEC) - return -EINVAL; - - burst = (u64)cfs_burst_us * NSEC_PER_USEC; - period = ktime_to_ns(tg->cfs_bandwidth.period); - quota = tg->cfs_bandwidth.quota; - - return tg_set_cfs_bandwidth(tg, period, quota, burst); -} - -static long tg_get_cfs_burst(struct task_group *tg) +static u64 tg_get_cfs_burst(struct task_group *tg) { u64 burst_us; @@ -10830,42 +9536,6 @@ static long tg_get_cfs_burst(struct task_group *tg) return burst_us; } -static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return tg_get_cfs_quota(css_tg(css)); -} - -static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css, - struct cftype *cftype, s64 cfs_quota_us) -{ - return tg_set_cfs_quota(css_tg(css), cfs_quota_us); -} - -static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return tg_get_cfs_period(css_tg(css)); -} - -static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css, - struct cftype *cftype, u64 cfs_period_us) -{ - return tg_set_cfs_period(css_tg(css), cfs_period_us); -} - -static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css, - struct cftype *cft) -{ - return tg_get_cfs_burst(css_tg(css)); -} - -static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css, - struct cftype *cftype, u64 cfs_burst_us) -{ - return tg_set_cfs_burst(css_tg(css), cfs_burst_us); -} - struct cfs_schedulable_data { struct task_group *tg; u64 period, quota; @@ -10911,11 +9581,16 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) /* * Ensure max(child_quota) <= parent_quota. On cgroup2, - * always take the min. On cgroup1, only inherit when no - * limit is set: + * always take the non-RUNTIME_INF min. On cgroup1, only + * inherit when no limit is set. In both cases this is used + * by the scheduler to determine if a given CFS task has a + * bandwidth constraint at some higher level. */ if (cgroup_subsys_on_dfl(cpu_cgrp_subsys)) { - quota = min(quota, parent_quota); + if (quota == RUNTIME_INF) + quota = parent_quota; + else if (parent_quota != RUNTIME_INF) + quota = min(quota, parent_quota); } else { if (quota == RUNTIME_INF) quota = parent_quota; @@ -10930,7 +9605,6 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) { - int ret; struct cfs_schedulable_data data = { .tg = tg, .period = period, @@ -10942,11 +9616,8 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) do_div(data.quota, NSEC_PER_USEC); } - rcu_read_lock(); - ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data); - rcu_read_unlock(); - - return ret; + guard(rcu)(); + return walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data); } static int cpu_cfs_stat_show(struct seq_file *sf, void *v) @@ -10976,8 +9647,165 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v) return 0; } + +static u64 throttled_time_self(struct task_group *tg) +{ + int i; + u64 total = 0; + + for_each_possible_cpu(i) { + total += READ_ONCE(tg->cfs_rq[i]->throttled_clock_self_time); + } + + return total; +} + +static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v) +{ + struct task_group *tg = css_tg(seq_css(sf)); + + seq_printf(sf, "throttled_time %llu\n", throttled_time_self(tg)); + + return 0; +} #endif /* CONFIG_CFS_BANDWIDTH */ -#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_GROUP_SCHED_BANDWIDTH +const u64 max_bw_quota_period_us = 1 * USEC_PER_SEC; /* 1s */ +static const u64 min_bw_quota_period_us = 1 * USEC_PER_MSEC; /* 1ms */ +/* More than 203 days if BW_SHIFT equals 20. */ +static const u64 max_bw_runtime_us = MAX_BW; + +static void tg_bandwidth(struct task_group *tg, + u64 *period_us_p, u64 *quota_us_p, u64 *burst_us_p) +{ +#ifdef CONFIG_CFS_BANDWIDTH + if (period_us_p) + *period_us_p = tg_get_cfs_period(tg); + if (quota_us_p) + *quota_us_p = tg_get_cfs_quota(tg); + if (burst_us_p) + *burst_us_p = tg_get_cfs_burst(tg); +#else /* !CONFIG_CFS_BANDWIDTH */ + if (period_us_p) + *period_us_p = tg->scx.bw_period_us; + if (quota_us_p) + *quota_us_p = tg->scx.bw_quota_us; + if (burst_us_p) + *burst_us_p = tg->scx.bw_burst_us; +#endif /* CONFIG_CFS_BANDWIDTH */ +} + +static u64 cpu_period_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + u64 period_us; + + tg_bandwidth(css_tg(css), &period_us, NULL, NULL); + return period_us; +} + +static int tg_set_bandwidth(struct task_group *tg, + u64 period_us, u64 quota_us, u64 burst_us) +{ + const u64 max_usec = U64_MAX / NSEC_PER_USEC; + int ret = 0; + + if (tg == &root_task_group) + return -EINVAL; + + /* Values should survive translation to nsec */ + if (period_us > max_usec || + (quota_us != RUNTIME_INF && quota_us > max_usec) || + burst_us > max_usec) + return -EINVAL; + + /* + * Ensure we have some amount of bandwidth every period. This is to + * prevent reaching a state of large arrears when throttled via + * entity_tick() resulting in prolonged exit starvation. + */ + if (quota_us < min_bw_quota_period_us || + period_us < min_bw_quota_period_us) + return -EINVAL; + + /* + * Likewise, bound things on the other side by preventing insane quota + * periods. This also allows us to normalize in computing quota + * feasibility. + */ + if (period_us > max_bw_quota_period_us) + return -EINVAL; + + /* + * Bound quota to defend quota against overflow during bandwidth shift. + */ + if (quota_us != RUNTIME_INF && quota_us > max_bw_runtime_us) + return -EINVAL; + + if (quota_us != RUNTIME_INF && (burst_us > quota_us || + burst_us + quota_us > max_bw_runtime_us)) + return -EINVAL; + +#ifdef CONFIG_CFS_BANDWIDTH + ret = tg_set_cfs_bandwidth(tg, period_us, quota_us, burst_us); +#endif /* CONFIG_CFS_BANDWIDTH */ + if (!ret) + scx_group_set_bandwidth(tg, period_us, quota_us, burst_us); + return ret; +} + +static s64 cpu_quota_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + u64 quota_us; + + tg_bandwidth(css_tg(css), NULL, "a_us, NULL); + return quota_us; /* (s64)RUNTIME_INF becomes -1 */ +} + +static u64 cpu_burst_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + u64 burst_us; + + tg_bandwidth(css_tg(css), NULL, NULL, &burst_us); + return burst_us; +} + +static int cpu_period_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 period_us) +{ + struct task_group *tg = css_tg(css); + u64 quota_us, burst_us; + + tg_bandwidth(tg, NULL, "a_us, &burst_us); + return tg_set_bandwidth(tg, period_us, quota_us, burst_us); +} + +static int cpu_quota_write_s64(struct cgroup_subsys_state *css, + struct cftype *cftype, s64 quota_us) +{ + struct task_group *tg = css_tg(css); + u64 period_us, burst_us; + + if (quota_us < 0) + quota_us = RUNTIME_INF; + + tg_bandwidth(tg, &period_us, NULL, &burst_us); + return tg_set_bandwidth(tg, period_us, quota_us, burst_us); +} + +static int cpu_burst_write_u64(struct cgroup_subsys_state *css, + struct cftype *cftype, u64 burst_us) +{ + struct task_group *tg = css_tg(css); + u64 period_us, quota_us; + + tg_bandwidth(tg, &period_us, "a_us, NULL); + return tg_set_bandwidth(tg, period_us, quota_us, burst_us); +} +#endif /* CONFIG_GROUP_SCHED_BANDWIDTH */ #ifdef CONFIG_RT_GROUP_SCHED static int cpu_rt_runtime_write(struct cgroup_subsys_state *css, @@ -11005,7 +9833,7 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, } #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -11015,12 +9843,17 @@ static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css, static int cpu_idle_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 idle) { - return sched_group_set_idle(css_tg(css), idle); + int ret; + + ret = sched_group_set_idle(css_tg(css), idle); + if (!ret) + scx_group_set_idle(css_tg(css), idle); + return ret; } -#endif +#endif /* CONFIG_GROUP_SCHED_WEIGHT */ static struct cftype cpu_legacy_files[] = { -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT { .name = "shares", .read_u64 = cpu_shares_read_u64, @@ -11032,37 +9865,31 @@ static struct cftype cpu_legacy_files[] = { .write_s64 = cpu_idle_write_s64, }, #endif -#ifdef CONFIG_CFS_BANDWIDTH +#ifdef CONFIG_GROUP_SCHED_BANDWIDTH { - .name = "cfs_quota_us", - .read_s64 = cpu_cfs_quota_read_s64, - .write_s64 = cpu_cfs_quota_write_s64, + .name = "cfs_period_us", + .read_u64 = cpu_period_read_u64, + .write_u64 = cpu_period_write_u64, }, { - .name = "cfs_period_us", - .read_u64 = cpu_cfs_period_read_u64, - .write_u64 = cpu_cfs_period_write_u64, + .name = "cfs_quota_us", + .read_s64 = cpu_quota_read_s64, + .write_s64 = cpu_quota_write_s64, }, { .name = "cfs_burst_us", - .read_u64 = cpu_cfs_burst_read_u64, - .write_u64 = cpu_cfs_burst_write_u64, + .read_u64 = cpu_burst_read_u64, + .write_u64 = cpu_burst_write_u64, }, +#endif +#ifdef CONFIG_CFS_BANDWIDTH { .name = "stat", .seq_show = cpu_cfs_stat_show, }, -#endif -#ifdef CONFIG_RT_GROUP_SCHED - { - .name = "rt_runtime_us", - .read_s64 = cpu_rt_runtime_read, - .write_s64 = cpu_rt_runtime_write, - }, { - .name = "rt_period_us", - .read_u64 = cpu_rt_period_read_uint, - .write_u64 = cpu_rt_period_write_uint, + .name = "stat.local", + .seq_show = cpu_cfs_local_stat_show, }, #endif #ifdef CONFIG_UCLAMP_TASK_GROUP @@ -11082,6 +9909,55 @@ static struct cftype cpu_legacy_files[] = { { } /* Terminate */ }; +#ifdef CONFIG_RT_GROUP_SCHED +static struct cftype rt_group_files[] = { + { + .name = "rt_runtime_us", + .read_s64 = cpu_rt_runtime_read, + .write_s64 = cpu_rt_runtime_write, + }, + { + .name = "rt_period_us", + .read_u64 = cpu_rt_period_read_uint, + .write_u64 = cpu_rt_period_write_uint, + }, + { } /* Terminate */ +}; + +# ifdef CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED +DEFINE_STATIC_KEY_FALSE(rt_group_sched); +# else +DEFINE_STATIC_KEY_TRUE(rt_group_sched); +# endif + +static int __init setup_rt_group_sched(char *str) +{ + long val; + + if (kstrtol(str, 0, &val) || val < 0 || val > 1) { + pr_warn("Unable to set rt_group_sched\n"); + return 1; + } + if (val) + static_branch_enable(&rt_group_sched); + else + static_branch_disable(&rt_group_sched); + + return 1; +} +__setup("rt_group_sched=", setup_rt_group_sched); + +static int __init cpu_rt_group_init(void) +{ + if (!rt_group_sched_enabled()) + return 0; + + WARN_ON(cgroup_add_legacy_cftypes(&cpu_cgrp_subsys, rt_group_files)); + return 0; +} +subsys_initcall(cpu_rt_group_init); +#endif /* CONFIG_RT_GROUP_SCHED */ + static int cpu_extra_stat_show(struct seq_file *sf, struct cgroup_subsys_state *css) { @@ -11104,42 +9980,57 @@ static int cpu_extra_stat_show(struct seq_file *sf, cfs_b->nr_periods, cfs_b->nr_throttled, throttled_usec, cfs_b->nr_burst, burst_usec); } +#endif /* CONFIG_CFS_BANDWIDTH */ + return 0; +} + +static int cpu_local_stat_show(struct seq_file *sf, + struct cgroup_subsys_state *css) +{ +#ifdef CONFIG_CFS_BANDWIDTH + { + struct task_group *tg = css_tg(css); + u64 throttled_self_usec; + + throttled_self_usec = throttled_time_self(tg); + do_div(throttled_self_usec, NSEC_PER_USEC); + + seq_printf(sf, "throttled_usec %llu\n", + throttled_self_usec); + } #endif return 0; } -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT + static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { - struct task_group *tg = css_tg(css); - u64 weight = scale_load_down(tg->shares); - - return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024); + return sched_weight_to_cgroup(tg_weight(css_tg(css))); } static int cpu_weight_write_u64(struct cgroup_subsys_state *css, - struct cftype *cft, u64 weight) + struct cftype *cft, u64 cgrp_weight) { - /* - * cgroup weight knobs should use the common MIN, DFL and MAX - * values which are 1, 100 and 10000 respectively. While it loses - * a bit of range on both ends, it maps pretty well onto the shares - * value used by scheduler and the round-trip conversions preserve - * the original value over the entire range. - */ - if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX) + unsigned long weight; + int ret; + + if (cgrp_weight < CGROUP_WEIGHT_MIN || cgrp_weight > CGROUP_WEIGHT_MAX) return -ERANGE; - weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL); + weight = sched_weight_from_cgroup(cgrp_weight); - return sched_group_set_shares(css_tg(css), scale_load(weight)); + ret = sched_group_set_shares(css_tg(css), scale_load(weight)); + if (!ret) + scx_group_set_weight(css_tg(css), cgrp_weight); + return ret; } static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { - unsigned long weight = scale_load_down(css_tg(css)->shares); + unsigned long weight = tg_weight(css_tg(css)); int last_delta = INT_MAX; int prio, delta; @@ -11158,7 +10049,7 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 nice) { unsigned long weight; - int idx; + int idx, ret; if (nice < MIN_NICE || nice > MAX_NICE) return -ERANGE; @@ -11167,9 +10058,13 @@ static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, idx = array_index_nospec(idx, 40); weight = sched_prio_to_weight[idx]; - return sched_group_set_shares(css_tg(css), scale_load(weight)); + ret = sched_group_set_shares(css_tg(css), scale_load(weight)); + if (!ret) + scx_group_set_weight(css_tg(css), + sched_weight_to_cgroup(weight)); + return ret; } -#endif +#endif /* CONFIG_GROUP_SCHED_WEIGHT */ static void __maybe_unused cpu_period_quota_print(struct seq_file *sf, long period, long quota) @@ -11183,32 +10078,32 @@ static void __maybe_unused cpu_period_quota_print(struct seq_file *sf, } /* caller should put the current value in *@periodp before calling */ -static int __maybe_unused cpu_period_quota_parse(char *buf, - u64 *periodp, u64 *quotap) +static int __maybe_unused cpu_period_quota_parse(char *buf, u64 *period_us_p, + u64 *quota_us_p) { char tok[21]; /* U64_MAX */ - if (sscanf(buf, "%20s %llu", tok, periodp) < 1) + if (sscanf(buf, "%20s %llu", tok, period_us_p) < 1) return -EINVAL; - *periodp *= NSEC_PER_USEC; - - if (sscanf(tok, "%llu", quotap)) - *quotap *= NSEC_PER_USEC; - else if (!strcmp(tok, "max")) - *quotap = RUNTIME_INF; - else - return -EINVAL; + if (sscanf(tok, "%llu", quota_us_p) < 1) { + if (!strcmp(tok, "max")) + *quota_us_p = RUNTIME_INF; + else + return -EINVAL; + } return 0; } -#ifdef CONFIG_CFS_BANDWIDTH +#ifdef CONFIG_GROUP_SCHED_BANDWIDTH static int cpu_max_show(struct seq_file *sf, void *v) { struct task_group *tg = css_tg(seq_css(sf)); + u64 period_us, quota_us; - cpu_period_quota_print(sf, tg_get_cfs_period(tg), tg_get_cfs_quota(tg)); + tg_bandwidth(tg, &period_us, "a_us, NULL); + cpu_period_quota_print(sf, period_us, quota_us); return 0; } @@ -11216,20 +10111,19 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct task_group *tg = css_tg(of_css(of)); - u64 period = tg_get_cfs_period(tg); - u64 burst = tg_get_cfs_burst(tg); - u64 quota; + u64 period_us, quota_us, burst_us; int ret; - ret = cpu_period_quota_parse(buf, &period, "a); + tg_bandwidth(tg, &period_us, NULL, &burst_us); + ret = cpu_period_quota_parse(buf, &period_us, "a_us); if (!ret) - ret = tg_set_cfs_bandwidth(tg, period, quota, burst); + ret = tg_set_bandwidth(tg, period_us, quota_us, burst_us); return ret ?: nbytes; } -#endif +#endif /* CONFIG_CFS_BANDWIDTH */ static struct cftype cpu_files[] = { -#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_GROUP_SCHED_WEIGHT { .name = "weight", .flags = CFTYPE_NOT_ON_ROOT, @@ -11249,7 +10143,7 @@ static struct cftype cpu_files[] = { .write_s64 = cpu_idle_write_s64, }, #endif -#ifdef CONFIG_CFS_BANDWIDTH +#ifdef CONFIG_GROUP_SCHED_BANDWIDTH { .name = "max", .flags = CFTYPE_NOT_ON_ROOT, @@ -11259,10 +10153,10 @@ static struct cftype cpu_files[] = { { .name = "max.burst", .flags = CFTYPE_NOT_ON_ROOT, - .read_u64 = cpu_cfs_burst_read_u64, - .write_u64 = cpu_cfs_burst_write_u64, + .read_u64 = cpu_burst_read_u64, + .write_u64 = cpu_burst_write_u64, }, -#endif +#endif /* CONFIG_CFS_BANDWIDTH */ #ifdef CONFIG_UCLAMP_TASK_GROUP { .name = "uclamp.min", @@ -11276,31 +10170,32 @@ static struct cftype cpu_files[] = { .seq_show = cpu_uclamp_max_show, .write = cpu_uclamp_max_write, }, -#endif +#endif /* CONFIG_UCLAMP_TASK_GROUP */ { } /* terminate */ }; struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, .css_online = cpu_cgroup_css_online, + .css_offline = cpu_cgroup_css_offline, .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, .css_extra_stat_show = cpu_extra_stat_show, -#ifdef CONFIG_RT_GROUP_SCHED + .css_local_stat_show = cpu_local_stat_show, .can_attach = cpu_cgroup_can_attach, -#endif .attach = cpu_cgroup_attach, + .cancel_attach = cpu_cgroup_cancel_attach, .legacy_cftypes = cpu_legacy_files, .dfl_cftypes = cpu_files, .early_init = true, .threaded = true, }; -#endif /* CONFIG_CGROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ void dump_cpu_task(int cpu) { - if (cpu == smp_processor_id() && in_hardirq()) { + if (in_hardirq() && cpu == smp_processor_id()) { struct pt_regs *regs; regs = get_irq_regs(); @@ -11341,10 +10236,10 @@ const int sched_prio_to_weight[40] = { }; /* - * Inverse (2^32/x) values of the sched_prio_to_weight[] array, precalculated. + * Inverse (2^32/x) values of the sched_prio_to_weight[] array, pre-calculated. * * In cases where the weight does not change often, we can use the - * precalculated inverse to speed up arithmetics by turning divisions + * pre-calculated inverse to speed up arithmetics by turning divisions * into multiplications: */ const u32 sched_prio_to_wmult[40] = { @@ -11362,3 +10257,573 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count) { trace_sched_update_nr_running_tp(rq, count); } + +#ifdef CONFIG_SCHED_MM_CID +/* + * Concurrency IDentifier management + * + * Serialization rules: + * + * mm::mm_cid::mutex: Serializes fork() and exit() and therefore + * protects mm::mm_cid::users. + * + * mm::mm_cid::lock: Serializes mm_update_max_cids() and + * mm_update_cpus_allowed(). Nests in mm_cid::mutex + * and runqueue lock. + * + * The mm_cidmask bitmap is not protected by any of the mm::mm_cid locks + * and can only be modified with atomic operations. + * + * The mm::mm_cid:pcpu per CPU storage is protected by the CPUs runqueue + * lock. + * + * CID ownership: + * + * A CID is either owned by a task (stored in task_struct::mm_cid.cid) or + * by a CPU (stored in mm::mm_cid.pcpu::cid). CIDs owned by CPUs have the + * MM_CID_ONCPU bit set. During transition from CPU to task ownership mode, + * MM_CID_TRANSIT is set on the per task CIDs. When this bit is set the + * task needs to drop the CID into the pool when scheduling out. Both bits + * (ONCPU and TRANSIT) are filtered out by task_cid() when the CID is + * actually handed over to user space in the RSEQ memory. + * + * Mode switching: + * + * Switching to per CPU mode happens when the user count becomes greater + * than the maximum number of CIDs, which is calculated by: + * + * opt_cids = min(mm_cid::nr_cpus_allowed, mm_cid::users); + * max_cids = min(1.25 * opt_cids, num_possible_cpus()); + * + * The +25% allowance is useful for tight CPU masks in scenarios where only + * a few threads are created and destroyed to avoid frequent mode + * switches. Though this allowance shrinks, the closer opt_cids becomes to + * num_possible_cpus(), which is the (unfortunate) hard ABI limit. + * + * At the point of switching to per CPU mode the new user is not yet + * visible in the system, so the task which initiated the fork() runs the + * fixup function: mm_cid_fixup_tasks_to_cpu() walks the thread list and + * either transfers each tasks owned CID to the CPU the task runs on or + * drops it into the CID pool if a task is not on a CPU at that point in + * time. Tasks which schedule in before the task walk reaches them do the + * handover in mm_cid_schedin(). When mm_cid_fixup_tasks_to_cpus() completes + * it's guaranteed that no task related to that MM owns a CID anymore. + * + * Switching back to task mode happens when the user count goes below the + * threshold which was recorded on the per CPU mode switch: + * + * pcpu_thrs = min(opt_cids - (opt_cids / 4), num_possible_cpus() / 2); + * + * This threshold is updated when a affinity change increases the number of + * allowed CPUs for the MM, which might cause a switch back to per task + * mode. + * + * If the switch back was initiated by a exiting task, then that task runs + * the fixup function. If it was initiated by a affinity change, then it's + * run either in the deferred update function in context of a workqueue or + * by a task which forks a new one or by a task which exits. Whatever + * happens first. mm_cid_fixup_cpus_to_task() walks through the possible + * CPUs and either transfers the CPU owned CIDs to a related task which + * runs on the CPU or drops it into the pool. Tasks which schedule in on a + * CPU which the walk did not cover yet do the handover themself. + * + * This transition from CPU to per task ownership happens in two phases: + * + * 1) mm:mm_cid.transit contains MM_CID_TRANSIT This is OR'ed on the task + * CID and denotes that the CID is only temporarily owned by the + * task. When it schedules out the task drops the CID back into the + * pool if this bit is set. + * + * 2) The initiating context walks the per CPU space and after completion + * clears mm:mm_cid.transit. So after that point the CIDs are strictly + * task owned again. + * + * This two phase transition is required to prevent CID space exhaustion + * during the transition as a direct transfer of ownership would fail if + * two tasks are scheduled in on the same CPU before the fixup freed per + * CPU CIDs. + * + * When mm_cid_fixup_cpus_to_tasks() completes it's guaranteed that no CID + * related to that MM is owned by a CPU anymore. + */ + +/* + * Update the CID range properties when the constraints change. Invoked via + * fork(), exit() and affinity changes + */ +static void __mm_update_max_cids(struct mm_mm_cid *mc) +{ + unsigned int opt_cids, max_cids; + + /* Calculate the new optimal constraint */ + opt_cids = min(mc->nr_cpus_allowed, mc->users); + + /* Adjust the maximum CIDs to +25% limited by the number of possible CPUs */ + max_cids = min(opt_cids + (opt_cids / 4), num_possible_cpus()); + WRITE_ONCE(mc->max_cids, max_cids); +} + +static inline unsigned int mm_cid_calc_pcpu_thrs(struct mm_mm_cid *mc) +{ + unsigned int opt_cids; + + opt_cids = min(mc->nr_cpus_allowed, mc->users); + /* Has to be at least 1 because 0 indicates PCPU mode off */ + return max(min(opt_cids - opt_cids / 4, num_possible_cpus() / 2), 1); +} + +static bool mm_update_max_cids(struct mm_struct *mm) +{ + struct mm_mm_cid *mc = &mm->mm_cid; + + lockdep_assert_held(&mm->mm_cid.lock); + + /* Clear deferred mode switch flag. A change is handled by the caller */ + mc->update_deferred = false; + __mm_update_max_cids(mc); + + /* Check whether owner mode must be changed */ + if (!mc->percpu) { + /* Enable per CPU mode when the number of users is above max_cids */ + if (mc->users > mc->max_cids) + mc->pcpu_thrs = mm_cid_calc_pcpu_thrs(mc); + } else { + /* Switch back to per task if user count under threshold */ + if (mc->users < mc->pcpu_thrs) + mc->pcpu_thrs = 0; + } + + /* Mode change required? */ + if (!!mc->percpu == !!mc->pcpu_thrs) + return false; + /* When switching back to per TASK mode, set the transition flag */ + if (!mc->pcpu_thrs) + WRITE_ONCE(mc->transit, MM_CID_TRANSIT); + WRITE_ONCE(mc->percpu, !!mc->pcpu_thrs); + return true; +} + +static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) +{ + struct cpumask *mm_allowed; + struct mm_mm_cid *mc; + unsigned int weight; + + if (!mm || !READ_ONCE(mm->mm_cid.users)) + return; + /* + * mm::mm_cid::mm_cpus_allowed is the superset of each threads + * allowed CPUs mask which means it can only grow. + */ + mc = &mm->mm_cid; + guard(raw_spinlock)(&mc->lock); + mm_allowed = mm_cpus_allowed(mm); + weight = cpumask_weighted_or(mm_allowed, mm_allowed, affmsk); + if (weight == mc->nr_cpus_allowed) + return; + + WRITE_ONCE(mc->nr_cpus_allowed, weight); + __mm_update_max_cids(mc); + if (!mc->percpu) + return; + + /* Adjust the threshold to the wider set */ + mc->pcpu_thrs = mm_cid_calc_pcpu_thrs(mc); + /* Switch back to per task mode? */ + if (mc->users >= mc->pcpu_thrs) + return; + + /* Don't queue twice */ + if (mc->update_deferred) + return; + + /* Queue the irq work, which schedules the real work */ + mc->update_deferred = true; + irq_work_queue(&mc->irq_work); +} + +static inline void mm_cid_transit_to_task(struct task_struct *t, struct mm_cid_pcpu *pcp) +{ + if (cid_on_cpu(t->mm_cid.cid)) { + unsigned int cid = cpu_cid_to_cid(t->mm_cid.cid); + + t->mm_cid.cid = cid_to_transit_cid(cid); + pcp->cid = t->mm_cid.cid; + } +} + +static void mm_cid_fixup_cpus_to_tasks(struct mm_struct *mm) +{ + unsigned int cpu; + + /* Walk the CPUs and fixup all stale CIDs */ + for_each_possible_cpu(cpu) { + struct mm_cid_pcpu *pcp = per_cpu_ptr(mm->mm_cid.pcpu, cpu); + struct rq *rq = cpu_rq(cpu); + + /* Remote access to mm::mm_cid::pcpu requires rq_lock */ + guard(rq_lock_irq)(rq); + /* Is the CID still owned by the CPU? */ + if (cid_on_cpu(pcp->cid)) { + /* + * If rq->curr has @mm, transfer it with the + * transition bit set. Otherwise drop it. + */ + if (rq->curr->mm == mm && rq->curr->mm_cid.active) + mm_cid_transit_to_task(rq->curr, pcp); + else + mm_drop_cid_on_cpu(mm, pcp); + + } else if (rq->curr->mm == mm && rq->curr->mm_cid.active) { + unsigned int cid = rq->curr->mm_cid.cid; + + /* Ensure it has the transition bit set */ + if (!cid_in_transit(cid)) { + cid = cid_to_transit_cid(cid); + rq->curr->mm_cid.cid = cid; + pcp->cid = cid; + } + } + } + /* Clear the transition bit */ + WRITE_ONCE(mm->mm_cid.transit, 0); +} + +static inline void mm_cid_transfer_to_cpu(struct task_struct *t, struct mm_cid_pcpu *pcp) +{ + if (cid_on_task(t->mm_cid.cid)) { + t->mm_cid.cid = cid_to_cpu_cid(t->mm_cid.cid); + pcp->cid = t->mm_cid.cid; + } +} + +static bool mm_cid_fixup_task_to_cpu(struct task_struct *t, struct mm_struct *mm) +{ + /* Remote access to mm::mm_cid::pcpu requires rq_lock */ + guard(task_rq_lock)(t); + /* If the task is not active it is not in the users count */ + if (!t->mm_cid.active) + return false; + if (cid_on_task(t->mm_cid.cid)) { + /* If running on the CPU, transfer the CID, otherwise drop it */ + if (task_rq(t)->curr == t) + mm_cid_transfer_to_cpu(t, per_cpu_ptr(mm->mm_cid.pcpu, task_cpu(t))); + else + mm_unset_cid_on_task(t); + } + return true; +} + +static void mm_cid_fixup_tasks_to_cpus(void) +{ + struct mm_struct *mm = current->mm; + struct task_struct *p, *t; + unsigned int users; + + /* + * This can obviously race with a concurrent affinity change, which + * increases the number of allowed CPUs for this mm, but that does + * not affect the mode and only changes the CID constraints. A + * possible switch back to per task mode happens either in the + * deferred handler function or in the next fork()/exit(). + * + * The caller has already transferred. The newly incoming task is + * already accounted for, but not yet visible. + */ + users = mm->mm_cid.users - 2; + if (!users) + return; + + guard(rcu)(); + for_other_threads(current, t) { + if (mm_cid_fixup_task_to_cpu(t, mm)) + users--; + } + + if (!users) + return; + + /* Happens only for VM_CLONE processes. */ + for_each_process_thread(p, t) { + if (t == current || t->mm != mm) + continue; + if (mm_cid_fixup_task_to_cpu(t, mm)) { + if (--users == 0) + return; + } + } +} + +static bool sched_mm_cid_add_user(struct task_struct *t, struct mm_struct *mm) +{ + t->mm_cid.active = 1; + mm->mm_cid.users++; + return mm_update_max_cids(mm); +} + +void sched_mm_cid_fork(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + bool percpu; + + WARN_ON_ONCE(!mm || t->mm_cid.cid != MM_CID_UNSET); + + guard(mutex)(&mm->mm_cid.mutex); + scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) { + struct mm_cid_pcpu *pcp = this_cpu_ptr(mm->mm_cid.pcpu); + + /* First user ? */ + if (!mm->mm_cid.users) { + sched_mm_cid_add_user(t, mm); + t->mm_cid.cid = mm_get_cid(mm); + /* Required for execve() */ + pcp->cid = t->mm_cid.cid; + return; + } + + if (!sched_mm_cid_add_user(t, mm)) { + if (!mm->mm_cid.percpu) + t->mm_cid.cid = mm_get_cid(mm); + return; + } + + /* Handle the mode change and transfer current's CID */ + percpu = !!mm->mm_cid.percpu; + if (!percpu) + mm_cid_transit_to_task(current, pcp); + else + mm_cid_transfer_to_cpu(current, pcp); + } + + if (percpu) { + mm_cid_fixup_tasks_to_cpus(); + } else { + mm_cid_fixup_cpus_to_tasks(mm); + t->mm_cid.cid = mm_get_cid(mm); + } +} + +static bool sched_mm_cid_remove_user(struct task_struct *t) +{ + t->mm_cid.active = 0; + scoped_guard(preempt) { + /* Clear the transition bit */ + t->mm_cid.cid = cid_from_transit_cid(t->mm_cid.cid); + mm_unset_cid_on_task(t); + } + t->mm->mm_cid.users--; + return mm_update_max_cids(t->mm); +} + +static bool __sched_mm_cid_exit(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + + if (!sched_mm_cid_remove_user(t)) + return false; + /* + * Contrary to fork() this only deals with a switch back to per + * task mode either because the above decreased users or an + * affinity change increased the number of allowed CPUs and the + * deferred fixup did not run yet. + */ + if (WARN_ON_ONCE(mm->mm_cid.percpu)) + return false; + /* + * A failed fork(2) cleanup never gets here, so @current must have + * the same MM as @t. That's true for exit() and the failed + * pthread_create() cleanup case. + */ + if (WARN_ON_ONCE(current->mm != mm)) + return false; + return true; +} + +/* + * When a task exits, the MM CID held by the task is not longer required as + * the task cannot return to user space. + */ +void sched_mm_cid_exit(struct task_struct *t) +{ + struct mm_struct *mm = t->mm; + + if (!mm || !t->mm_cid.active) + return; + /* + * Ensure that only one instance is doing MM CID operations within + * a MM. The common case is uncontended. The rare fixup case adds + * some overhead. + */ + scoped_guard(mutex, &mm->mm_cid.mutex) { + /* mm_cid::mutex is sufficient to protect mm_cid::users */ + if (likely(mm->mm_cid.users > 1)) { + scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) { + if (!__sched_mm_cid_exit(t)) + return; + /* Mode change required. Transfer currents CID */ + mm_cid_transit_to_task(current, this_cpu_ptr(mm->mm_cid.pcpu)); + } + mm_cid_fixup_cpus_to_tasks(mm); + return; + } + /* Last user */ + scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) { + /* Required across execve() */ + if (t == current) + mm_cid_transit_to_task(t, this_cpu_ptr(mm->mm_cid.pcpu)); + /* Ignore mode change. There is nothing to do. */ + sched_mm_cid_remove_user(t); + } + } + + /* + * As this is the last user (execve(), process exit or failed + * fork(2)) there is no concurrency anymore. + * + * Synchronize eventually pending work to ensure that there are no + * dangling references left. @t->mm_cid.users is zero so nothing + * can queue this work anymore. + */ + irq_work_sync(&mm->mm_cid.irq_work); + cancel_work_sync(&mm->mm_cid.work); +} + +/* Deactivate MM CID allocation across execve() */ +void sched_mm_cid_before_execve(struct task_struct *t) +{ + sched_mm_cid_exit(t); +} + +/* Reactivate MM CID after successful execve() */ +void sched_mm_cid_after_execve(struct task_struct *t) +{ + sched_mm_cid_fork(t); +} + +static void mm_cid_work_fn(struct work_struct *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, mm_cid.work); + + guard(mutex)(&mm->mm_cid.mutex); + /* Did the last user task exit already? */ + if (!mm->mm_cid.users) + return; + + scoped_guard(raw_spinlock_irq, &mm->mm_cid.lock) { + /* Have fork() or exit() handled it already? */ + if (!mm->mm_cid.update_deferred) + return; + /* This clears mm_cid::update_deferred */ + if (!mm_update_max_cids(mm)) + return; + /* Affinity changes can only switch back to task mode */ + if (WARN_ON_ONCE(mm->mm_cid.percpu)) + return; + } + mm_cid_fixup_cpus_to_tasks(mm); +} + +static void mm_cid_irq_work(struct irq_work *work) +{ + struct mm_struct *mm = container_of(work, struct mm_struct, mm_cid.irq_work); + + /* + * Needs to be unconditional because mm_cid::lock cannot be held + * when scheduling work as mm_update_cpus_allowed() nests inside + * rq::lock and schedule_work() might end up in wakeup... + */ + schedule_work(&mm->mm_cid.work); +} + +void mm_init_cid(struct mm_struct *mm, struct task_struct *p) +{ + mm->mm_cid.max_cids = 0; + mm->mm_cid.percpu = 0; + mm->mm_cid.transit = 0; + mm->mm_cid.nr_cpus_allowed = p->nr_cpus_allowed; + mm->mm_cid.users = 0; + mm->mm_cid.pcpu_thrs = 0; + mm->mm_cid.update_deferred = 0; + raw_spin_lock_init(&mm->mm_cid.lock); + mutex_init(&mm->mm_cid.mutex); + mm->mm_cid.irq_work = IRQ_WORK_INIT_HARD(mm_cid_irq_work); + INIT_WORK(&mm->mm_cid.work, mm_cid_work_fn); + cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); + bitmap_zero(mm_cidmask(mm), num_possible_cpus()); +} +#else /* CONFIG_SCHED_MM_CID */ +static inline void mm_update_cpus_allowed(struct mm_struct *mm, const struct cpumask *affmsk) { } +#endif /* !CONFIG_SCHED_MM_CID */ + +static DEFINE_PER_CPU(struct sched_change_ctx, sched_change_ctx); + +struct sched_change_ctx *sched_change_begin(struct task_struct *p, unsigned int flags) +{ + struct sched_change_ctx *ctx = this_cpu_ptr(&sched_change_ctx); + struct rq *rq = task_rq(p); + + /* + * Must exclusively use matched flags since this is both dequeue and + * enqueue. + */ + WARN_ON_ONCE(flags & 0xFFFF0000); + + lockdep_assert_rq_held(rq); + + if (!(flags & DEQUEUE_NOCLOCK)) { + update_rq_clock(rq); + flags |= DEQUEUE_NOCLOCK; + } + + if (flags & DEQUEUE_CLASS) { + if (p->sched_class->switching_from) + p->sched_class->switching_from(rq, p); + } + + *ctx = (struct sched_change_ctx){ + .p = p, + .flags = flags, + .queued = task_on_rq_queued(p), + .running = task_current_donor(rq, p), + }; + + if (!(flags & DEQUEUE_CLASS)) { + if (p->sched_class->get_prio) + ctx->prio = p->sched_class->get_prio(rq, p); + else + ctx->prio = p->prio; + } + + if (ctx->queued) + dequeue_task(rq, p, flags); + if (ctx->running) + put_prev_task(rq, p); + + if ((flags & DEQUEUE_CLASS) && p->sched_class->switched_from) + p->sched_class->switched_from(rq, p); + + return ctx; +} + +void sched_change_end(struct sched_change_ctx *ctx) +{ + struct task_struct *p = ctx->p; + struct rq *rq = task_rq(p); + + lockdep_assert_rq_held(rq); + + if ((ctx->flags & ENQUEUE_CLASS) && p->sched_class->switching_to) + p->sched_class->switching_to(rq, p); + + if (ctx->queued) + enqueue_task(rq, p, ctx->flags); + if (ctx->running) + set_next_task(rq, p); + + if (ctx->flags & ENQUEUE_CLASS) { + if (p->sched_class->switched_to) + p->sched_class->switched_to(rq, p); + } else { + p->sched_class->prio_changed(rq, p, ctx->prio); + } +} |