diff options
Diffstat (limited to 'kernel/sched/core.c')
| -rw-r--r-- | kernel/sched/core.c | 5290 |
1 files changed, 4266 insertions, 1024 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 1a9983da4408..cb2aa2b54c7a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -6,23 +6,94 @@ * * Copyright (C) 1991-2002 Linus Torvalds */ -#include "sched.h" - +#include <linux/highmem.h> +#include <linux/hrtimer_api.h> +#include <linux/ktime_api.h> +#include <linux/sched/signal.h> +#include <linux/syscalls_api.h> +#include <linux/debug_locks.h> +#include <linux/prefetch.h> +#include <linux/capability.h> +#include <linux/pgtable_api.h> +#include <linux/wait_bit.h> +#include <linux/jiffies.h> +#include <linux/spinlock_api.h> +#include <linux/cpumask_api.h> +#include <linux/lockdep_api.h> +#include <linux/hardirq.h> +#include <linux/softirq.h> +#include <linux/refcount_api.h> +#include <linux/topology.h> +#include <linux/sched/clock.h> +#include <linux/sched/cond_resched.h> +#include <linux/sched/cputime.h> +#include <linux/sched/debug.h> +#include <linux/sched/hotplug.h> +#include <linux/sched/init.h> +#include <linux/sched/isolation.h> +#include <linux/sched/loadavg.h> +#include <linux/sched/mm.h> +#include <linux/sched/nohz.h> +#include <linux/sched/rseq_api.h> +#include <linux/sched/rt.h> + +#include <linux/blkdev.h> +#include <linux/context_tracking.h> +#include <linux/cpuset.h> +#include <linux/delayacct.h> +#include <linux/init_task.h> +#include <linux/interrupt.h> +#include <linux/ioprio.h> +#include <linux/kallsyms.h> +#include <linux/kcov.h> +#include <linux/kprobes.h> +#include <linux/llist_api.h> +#include <linux/mmu_context.h> +#include <linux/mmzone.h> +#include <linux/mutex_api.h> +#include <linux/nmi.h> #include <linux/nospec.h> +#include <linux/perf_event_api.h> +#include <linux/profile.h> +#include <linux/psi.h> +#include <linux/rcuwait_api.h> +#include <linux/sched/wake_q.h> +#include <linux/scs.h> +#include <linux/slab.h> +#include <linux/syscalls.h> +#include <linux/vtime.h> +#include <linux/wait_api.h> +#include <linux/workqueue_api.h> + +#ifdef CONFIG_PREEMPT_DYNAMIC +# ifdef CONFIG_GENERIC_ENTRY +# include <linux/entry-common.h> +# endif +#endif -#include <linux/kcov.h> +#include <uapi/linux/sched/types.h> +#include <asm/irq_regs.h> #include <asm/switch_to.h> #include <asm/tlb.h> -#include "../workqueue_internal.h" -#include "../../fs/io-wq.h" -#include "../smpboot.h" +#define CREATE_TRACE_POINTS +#include <linux/sched/rseq_api.h> +#include <trace/events/sched.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" -#define CREATE_TRACE_POINTS -#include <trace/events/sched.h> +#include "../workqueue_internal.h" +#include "../../io_uring/io-wq.h" +#include "../smpboot.h" /* * Export tracepoints that act as a bare tracehook (ie: have no trace event @@ -33,11 +104,16 @@ 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(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); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL) +#ifdef CONFIG_SCHED_DEBUG /* * Debugging: various feature bits * @@ -51,27 +127,478 @@ const_debug unsigned int sysctl_sched_features = #include "features.h" 0; #undef SCHED_FEAT -#endif + +/* + * Print a warning if need_resched is set for the given duration (if + * LATENCY_WARN is enabled). + * + * If sysctl_resched_latency_warn_once is set, only one warning will be shown + * per boot. + */ +__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 = 32; +const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK; + +__read_mostly int scheduler_running; + +#ifdef CONFIG_SCHED_CORE + +DEFINE_STATIC_KEY_FALSE(__sched_core_enabled); + +/* kernel prio, less is more */ +static inline int __task_prio(struct task_struct *p) +{ + if (p->sched_class == &stop_sched_class) /* trumps deadline */ + return -2; + + if (rt_prio(p->prio)) /* includes deadline */ + 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 */ +} /* - * period over which we measure -rt task CPU usage in us. - * default: 1s + * l(a,b) + * le(a,b) := !l(b,a) + * g(a,b) := l(b,a) + * ge(a,b) := !l(a,b) */ -unsigned int sysctl_sched_rt_period = 1000000; -__read_mostly int scheduler_running; +/* real prio, less is less */ +static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool in_fi) +{ + + int pa = __task_prio(a), pb = __task_prio(b); + + if (-pa < -pb) + return true; + + 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 == MAX_RT_PRIO + MAX_NICE) /* fair */ + return cfs_prio_less(a, b, in_fi); + + return false; +} + +static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b) +{ + if (a->core_cookie < b->core_cookie) + return true; + + if (a->core_cookie > b->core_cookie) + return false; + + /* flip prio, so high prio is leftmost */ + if (prio_less(b, a, !!task_rq(a)->core->core_forceidle_count)) + return true; + + return false; +} + +#define __node_2_sc(node) rb_entry((node), struct task_struct, core_node) + +static inline bool rb_sched_core_less(struct rb_node *a, const struct rb_node *b) +{ + return __sched_core_less(__node_2_sc(a), __node_2_sc(b)); +} + +static inline int rb_sched_core_cmp(const void *key, const struct rb_node *node) +{ + const struct task_struct *p = __node_2_sc(node); + unsigned long cookie = (unsigned long)key; + + if (cookie < p->core_cookie) + return -1; + + if (cookie > p->core_cookie) + return 1; + + return 0; +} + +void sched_core_enqueue(struct rq *rq, struct task_struct *p) +{ + rq->core->core_task_seq++; + + if (!p->core_cookie) + return; + + rb_add(&p->core_node, &rq->core_tree, rb_sched_core_less); +} + +void sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) +{ + rq->core->core_task_seq++; + + if (sched_core_enqueued(p)) { + rb_erase(&p->core_node, &rq->core_tree); + RB_CLEAR_NODE(&p->core_node); + } + + /* + * Migrating the last task off the cpu, with the cpu in forced idle + * state. Reschedule to create an accounting edge for forced idle, + * and re-examine whether the core is still in forced idle state. + */ + if (!(flags & DEQUEUE_SAVE) && rq->nr_running == 1 && + rq->core->core_forceidle_count && rq->curr == rq->idle) + 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) +{ + 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); + + return __node_2_sc(node); +} + +static struct task_struct *sched_core_next(struct task_struct *p, unsigned long cookie) +{ + struct rb_node *node = &p->core_node; + + node = rb_next(node); + if (!node) + return NULL; + + p = container_of(node, struct task_struct, core_node); + if (p->core_cookie != cookie) + return NULL; + + return p; +} + +/* + * Magic required such that: + * + * raw_spin_rq_lock(rq); + * ... + * raw_spin_rq_unlock(rq); + * + * ends up locking and unlocking the _same_ lock, and all CPUs + * always agree on what rq has what lock. + * + * XXX entirely possible to selectively enable cores, don't bother for now. + */ + +static DEFINE_MUTEX(sched_core_mutex); +static atomic_t sched_core_count; +static struct cpumask sched_core_mask; + +static void sched_core_lock(int cpu, unsigned long *flags) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + int t, i = 0; + + local_irq_save(*flags); + for_each_cpu(t, smt_mask) + raw_spin_lock_nested(&cpu_rq(t)->__lock, i++); +} + +static void sched_core_unlock(int cpu, unsigned long *flags) +{ + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + int t; + + for_each_cpu(t, smt_mask) + raw_spin_unlock(&cpu_rq(t)->__lock); + local_irq_restore(*flags); +} + +static void __sched_core_flip(bool enabled) +{ + unsigned long flags; + int cpu, t; + + cpus_read_lock(); + + /* + * Toggle the online cores, one by one. + */ + cpumask_copy(&sched_core_mask, cpu_online_mask); + for_each_cpu(cpu, &sched_core_mask) { + const struct cpumask *smt_mask = cpu_smt_mask(cpu); + + sched_core_lock(cpu, &flags); + + for_each_cpu(t, smt_mask) + cpu_rq(t)->core_enabled = enabled; + + cpu_rq(cpu)->core->core_forceidle_start = 0; + + sched_core_unlock(cpu, &flags); + + cpumask_andnot(&sched_core_mask, &sched_core_mask, smt_mask); + } + + /* + * Toggle the offline CPUs. + */ + for_each_cpu_andnot(cpu, cpu_possible_mask, cpu_online_mask) + cpu_rq(cpu)->core_enabled = enabled; + + cpus_read_unlock(); +} + +static void sched_core_assert_empty(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + WARN_ON_ONCE(!RB_EMPTY_ROOT(&cpu_rq(cpu)->core_tree)); +} + +static void __sched_core_enable(void) +{ + static_branch_enable(&__sched_core_enabled); + /* + * Ensure all previous instances of raw_spin_rq_*lock() have finished + * and future ones will observe !sched_core_disabled(). + */ + synchronize_rcu(); + __sched_core_flip(true); + sched_core_assert_empty(); +} + +static void __sched_core_disable(void) +{ + sched_core_assert_empty(); + __sched_core_flip(false); + static_branch_disable(&__sched_core_enabled); +} + +void sched_core_get(void) +{ + if (atomic_inc_not_zero(&sched_core_count)) + return; + + mutex_lock(&sched_core_mutex); + if (!atomic_read(&sched_core_count)) + __sched_core_enable(); + + smp_mb__before_atomic(); + atomic_inc(&sched_core_count); + mutex_unlock(&sched_core_mutex); +} + +static void __sched_core_put(struct work_struct *work) +{ + if (atomic_dec_and_mutex_lock(&sched_core_count, &sched_core_mutex)) { + __sched_core_disable(); + mutex_unlock(&sched_core_mutex); + } +} + +void sched_core_put(void) +{ + static DECLARE_WORK(_work, __sched_core_put); + + /* + * "There can be only one" + * + * Either this is the last one, or we don't actually need to do any + * 'work'. If it is the last *again*, we rely on + * WORK_STRUCT_PENDING_BIT. + */ + if (!atomic_add_unless(&sched_core_count, -1, 1)) + schedule_work(&_work); +} + +#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 */ + +/* + * Serialization rules: + * + * Lock order: + * + * p->pi_lock + * rq->lock + * hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls) + * + * rq1->lock + * rq2->lock where: rq1 < rq2 + * + * Regular state: + * + * Normal scheduling state is serialized by rq->lock. __schedule() takes the + * local CPU's rq->lock, it optionally removes the task from the runqueue and + * always looks at the local rq data structures to find the most eligible task + * to run next. + * + * Task enqueue is also under rq->lock, possibly taken from another CPU. + * Wakeups from another LLC domain might use an IPI to transfer the enqueue to + * the local CPU to avoid bouncing the runqueue state around [ see + * ttwu_queue_wakelist() ] + * + * Task wakeup, specifically wakeups that involve migration, are horribly + * complicated to avoid having to take two rq->locks. + * + * Special state: + * + * System-calls and anything external will use task_rq_lock() which acquires + * both p->pi_lock and rq->lock. As a consequence the state they change is + * stable while holding either lock: + * + * - sched_setaffinity()/ + * set_cpus_allowed_ptr(): p->cpus_ptr, p->nr_cpus_allowed + * - set_user_nice(): p->se.load, p->*prio + * - __sched_setscheduler(): p->sched_class, p->policy, p->*prio, + * p->se.load, p->rt_priority, + * p->dl.dl_{runtime, deadline, period, flags, bw, density} + * - sched_setnuma(): p->numa_preferred_nid + * - sched_move_task(): p->sched_task_group + * - uclamp_update_active() p->uclamp* + * + * p->state <- TASK_*: + * + * is changed locklessly using set_current_state(), __set_current_state() or + * set_special_state(), see their respective comments, or by + * try_to_wake_up(). This latter uses p->pi_lock to serialize against + * concurrent self. + * + * 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 + * ON_RQ_MIGRATING state is used for migration without holding both + * rq->locks. It indicates task_cpu() is not stable, see task_rq_lock(). + * + * p->on_cpu <- { 0, 1 }: + * + * is set by prepare_task() and cleared by finish_task() such that it will be + * set before p is scheduled-in and cleared after p is scheduled-out, both + * under rq->lock. Non-zero indicates the task is running on its CPU. + * + * [ The astute reader will observe that it is possible for two tasks on one + * CPU to have ->on_cpu = 1 at the same time. ] + * + * task_cpu(p): is changed by set_task_cpu(), the rules are: + * + * - Don't call set_task_cpu() on a blocked task: + * + * We don't care what CPU we're not running on, this simplifies hotplug, + * the CPU assignment of blocked tasks isn't required to be valid. + * + * - for try_to_wake_up(), called under p->pi_lock: + * + * This allows try_to_wake_up() to only take one rq->lock, see its comment. + * + * - for migration called under rq->lock: + * [ see task_on_rq_migrating() in task_rq_lock() ] + * + * o move_queued_task() + * o detach_task() + * + * - for migration called under double_rq_lock(): + * + * o __migrate_swap_task() + * o push_rt_task() / pull_rt_task() + * o push_dl_task() / pull_dl_task() + * o dl_task_offline_migration() + * + */ + +void raw_spin_rq_lock_nested(struct rq *rq, int subclass) +{ + raw_spinlock_t *lock; + + /* Matches synchronize_rcu() in __sched_core_enable() */ + preempt_disable(); + if (sched_core_disabled()) { + raw_spin_lock_nested(&rq->__lock, subclass); + /* preempt_count *MUST* be > 1 */ + preempt_enable_no_resched(); + return; + } + + for (;;) { + lock = __rq_lockp(rq); + raw_spin_lock_nested(lock, subclass); + if (likely(lock == __rq_lockp(rq))) { + /* preempt_count *MUST* be > 1 */ + preempt_enable_no_resched(); + return; + } + raw_spin_unlock(lock); + } +} + +bool raw_spin_rq_trylock(struct rq *rq) +{ + raw_spinlock_t *lock; + bool ret; + + /* Matches synchronize_rcu() in __sched_core_enable() */ + preempt_disable(); + if (sched_core_disabled()) { + ret = raw_spin_trylock(&rq->__lock); + preempt_enable(); + return ret; + } + + for (;;) { + lock = __rq_lockp(rq); + ret = raw_spin_trylock(lock); + if (!ret || (likely(lock == __rq_lockp(rq)))) { + preempt_enable(); + return ret; + } + raw_spin_unlock(lock); + } +} + +void raw_spin_rq_unlock(struct rq *rq) +{ + raw_spin_unlock(rq_lockp(rq)); +} +#ifdef CONFIG_SMP /* - * part of the period that we allow rt tasks to run in us. - * default: 0.95s + * double_rq_lock - safely lock two runqueues */ -int sysctl_sched_rt_runtime = 950000; +void double_rq_lock(struct rq *rq1, struct rq *rq2) +{ + lockdep_assert_irqs_disabled(); + + if (rq_order_less(rq2, rq1)) + swap(rq1, rq2); + + raw_spin_rq_lock(rq1); + if (__rq_lockp(rq1) != __rq_lockp(rq2)) + raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING); + + double_rq_clock_clear_update(rq1, rq2); +} +#endif /* * __task_rq_lock - lock the rq @p resides on. @@ -85,12 +612,12 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) for (;;) { rq = task_rq(p); - raw_spin_lock(&rq->lock); + raw_spin_rq_lock(rq); if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { rq_pin_lock(rq, rf); return rq; } - raw_spin_unlock(&rq->lock); + raw_spin_rq_unlock(rq); while (unlikely(task_on_rq_migrating(p))) cpu_relax(); @@ -109,7 +636,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) for (;;) { raw_spin_lock_irqsave(&p->pi_lock, rf->flags); rq = task_rq(p); - raw_spin_lock(&rq->lock); + raw_spin_rq_lock(rq); /* * move_queued_task() task_rq_lock() * @@ -131,7 +658,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) rq_pin_lock(rq, rf); return rq; } - raw_spin_unlock(&rq->lock); + raw_spin_rq_unlock(rq); raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); while (unlikely(task_on_rq_migrating(p))) @@ -174,6 +701,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->prev_irq_time += irq_delta; delta -= irq_delta; + psi_account_irqtime(rq->curr, irq_delta); #endif #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING if (static_key_false((¶virt_steal_rq_enabled))) { @@ -201,7 +729,7 @@ void update_rq_clock(struct rq *rq) { s64 delta; - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); if (rq->clock_update_flags & RQCF_ACT_SKIP) return; @@ -219,7 +747,6 @@ void update_rq_clock(struct rq *rq) update_rq_clock_task(rq, delta); } - #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. @@ -255,8 +782,9 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) static void __hrtick_restart(struct rq *rq) { struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time = rq->hrtick_time; - hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD); + hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD); } /* @@ -269,7 +797,6 @@ static void __hrtick_start(void *arg) rq_lock(rq, &rf); __hrtick_restart(rq); - rq->hrtick_csd_pending = 0; rq_unlock(rq, &rf); } @@ -281,7 +808,6 @@ static void __hrtick_start(void *arg) void hrtick_start(struct rq *rq, u64 delay) { struct hrtimer *timer = &rq->hrtick_timer; - ktime_t time; s64 delta; /* @@ -289,16 +815,12 @@ void hrtick_start(struct rq *rq, u64 delay) * doesn't make sense and can cause timer DoS. */ delta = max_t(s64, delay, 10000LL); - time = ktime_add_ns(timer->base->get_time(), delta); - - hrtimer_set_expires(timer, time); + rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta); - if (rq == this_rq()) { + if (rq == this_rq()) __hrtick_restart(rq); - } else if (!rq->hrtick_csd_pending) { + else smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd); - rq->hrtick_csd_pending = 1; - } } #else @@ -317,18 +839,14 @@ void hrtick_start(struct rq *rq, u64 delay) 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 - rq->hrtick_csd_pending = 0; - - rq->hrtick_csd.flags = 0; - rq->hrtick_csd.func = __hrtick_start; - rq->hrtick_csd.info = rq; + 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; } @@ -349,15 +867,11 @@ static inline void hrtick_rq_init(struct rq *rq) ({ \ typeof(ptr) _ptr = (ptr); \ typeof(mask) _mask = (mask); \ - typeof(*_ptr) _old, _val = *_ptr; \ + typeof(*_ptr) _val = *_ptr; \ \ - for (;;) { \ - _old = cmpxchg(_ptr, _val, _val | _mask); \ - if (_old == _val) \ - break; \ - _val = _old; \ - } \ - _old; \ + do { \ + } while (!try_cmpxchg(_ptr, &_val, _val | _mask)); \ + _val; \ }) #if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) @@ -366,7 +880,7 @@ static inline void hrtick_rq_init(struct rq *rq) * this avoids any races wrt polling state changes and thereby avoids * spurious IPIs. */ -static bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct task_struct *p) { struct thread_info *ti = task_thread_info(p); return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); @@ -381,30 +895,28 @@ static bool set_nr_and_not_polling(struct task_struct *p) static bool set_nr_if_polling(struct task_struct *p) { struct thread_info *ti = task_thread_info(p); - typeof(ti->flags) old, val = READ_ONCE(ti->flags); + typeof(ti->flags) val = READ_ONCE(ti->flags); for (;;) { if (!(val & _TIF_POLLING_NRFLAG)) return false; if (val & _TIF_NEED_RESCHED) return true; - old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); - if (old == val) + if (try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED)) break; - val = old; } return true; } #else -static bool set_nr_and_not_polling(struct task_struct *p) +static inline bool set_nr_and_not_polling(struct task_struct *p) { set_tsk_need_resched(p); return true; } #ifdef CONFIG_SMP -static bool set_nr_if_polling(struct task_struct *p) +static inline bool set_nr_if_polling(struct task_struct *p) { return false; } @@ -417,7 +929,7 @@ static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task) /* * Atomically grab the task, if ->wake_q is !nil already it means - * its already queued (either by us or someone else) and will get the + * it's already queued (either by us or someone else) and will get the * wakeup due to that. * * In order to ensure that a pending wakeup will observe our pending @@ -484,7 +996,6 @@ void wake_up_q(struct wake_q_head *head) struct task_struct *task; task = container_of(node, struct task_struct, wake_q); - BUG_ON(!task); /* Task can safely be re-inserted now: */ node = node->next; task->wake_q.next = NULL; @@ -510,7 +1021,7 @@ void resched_curr(struct rq *rq) struct task_struct *curr = rq->curr; int cpu; - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); if (test_tsk_need_resched(curr)) return; @@ -534,10 +1045,10 @@ void resched_cpu(int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - raw_spin_lock_irqsave(&rq->lock, flags); + raw_spin_rq_lock_irqsave(rq, flags); if (cpu_online(cpu) || cpu == smp_processor_id()) resched_curr(rq); - raw_spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_rq_unlock_irqrestore(rq, flags); } #ifdef CONFIG_SMP @@ -554,17 +1065,19 @@ int get_nohz_timer_target(void) { int i, cpu = smp_processor_id(), default_cpu = -1; struct sched_domain *sd; + const struct cpumask *hk_mask; - if (housekeeping_cpu(cpu, HK_FLAG_TIMER)) { + if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) { if (!idle_cpu(cpu)) return cpu; default_cpu = cpu; } + hk_mask = housekeeping_cpumask(HK_TYPE_TIMER); + rcu_read_lock(); for_each_domain(cpu, sd) { - for_each_cpu_and(i, sched_domain_span(sd), - housekeeping_cpumask(HK_FLAG_TIMER)) { + for_each_cpu_and(i, sched_domain_span(sd), hk_mask) { if (cpu == i) continue; @@ -576,7 +1089,7 @@ int get_nohz_timer_target(void) } if (default_cpu == -1) - default_cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER); cpu = default_cpu; unlock: rcu_read_unlock(); @@ -637,29 +1150,23 @@ void wake_up_nohz_cpu(int cpu) wake_up_idle_cpu(cpu); } -static inline bool got_nohz_idle_kick(void) +static void nohz_csd_func(void *info) { - int cpu = smp_processor_id(); - - if (!(atomic_read(nohz_flags(cpu)) & NOHZ_KICK_MASK)) - return false; - - if (idle_cpu(cpu) && !need_resched()) - return true; + struct rq *rq = info; + int cpu = cpu_of(rq); + unsigned int flags; /* - * We can't run Idle Load Balance on this CPU for this time so we - * cancel it and clear NOHZ_BALANCE_KICK + * Release the rq::nohz_csd. */ - atomic_andnot(NOHZ_KICK_MASK, nohz_flags(cpu)); - return false; -} - -#else /* CONFIG_NO_HZ_COMMON */ + flags = atomic_fetch_andnot(NOHZ_KICK_MASK | NOHZ_NEWILB_KICK, nohz_flags(cpu)); + WARN_ON(!(flags & NOHZ_KICK_MASK)); -static inline bool got_nohz_idle_kick(void) -{ - return false; + rq->idle_balance = idle_cpu(cpu); + if (rq->idle_balance && !need_resched()) { + rq->nohz_idle_balance = flags; + raise_softirq_irqoff(SCHED_SOFTIRQ); + } } #endif /* CONFIG_NO_HZ_COMMON */ @@ -674,7 +1181,7 @@ bool sched_can_stop_tick(struct rq *rq) return false; /* - * If there are more than one RR tasks, we need the tick to effect the + * If there are more than one RR tasks, we need the tick to affect the * actual RR behaviour. */ if (rq->rt.rr_nr_running) { @@ -761,7 +1268,6 @@ static void set_load_weight(struct task_struct *p, bool update_load) if (task_has_idle_policy(p)) { load->weight = scale_load(WEIGHT_IDLEPRIO); load->inv_weight = WMULT_IDLEPRIO; - p->se.runnable_weight = load->weight; return; } @@ -774,7 +1280,6 @@ static void set_load_weight(struct task_struct *p, bool update_load) } else { load->weight = scale_load(sched_prio_to_weight[prio]); load->inv_weight = sched_prio_to_wmult[prio]; - p->se.runnable_weight = load->weight; } } @@ -792,14 +1297,51 @@ static void set_load_weight(struct task_struct *p, bool update_load) static DEFINE_MUTEX(uclamp_mutex); /* Max allowed minimum utilization */ -unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; +static unsigned int __maybe_unused sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE; /* Max allowed maximum utilization */ -unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; +static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE; + +/* + * By default RT tasks run at the maximum performance point/capacity of the + * system. Uclamp enforces this by always setting UCLAMP_MIN of RT tasks to + * SCHED_CAPACITY_SCALE. + * + * This knob allows admins to change the default behavior when uclamp is being + * used. In battery powered devices, particularly, running at the maximum + * capacity and frequency will increase energy consumption and shorten the + * battery life. + * + * This knob only affects RT tasks that their uclamp_se->user_defined == false. + * + * 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; /* All clamps are required to be less or equal than these values */ static struct uclamp_se uclamp_default[UCLAMP_CNT]; +/* + * This static key is used to reduce the uclamp overhead in the fast path. It + * primarily disables the call to uclamp_rq_{inc, dec}() in + * enqueue/dequeue_task(). + * + * This allows users to continue to enable uclamp in their kernel config with + * minimum uclamp overhead in the fast path. + * + * As soon as userspace modifies any of the uclamp knobs, the static key is + * enabled, since we have an actual users that make use of uclamp + * functionality. + * + * The knobs that would enable this static key are: + * + * * A task modifying its uclamp value with sched_setattr(). + * * An admin modifying the sysctl_sched_uclamp_{min, max} via procfs. + * * An admin modifying the cgroup cpu.uclamp.{min, max} + */ +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) @@ -808,12 +1350,7 @@ static struct uclamp_se uclamp_default[UCLAMP_CNT]; static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) { - return clamp_value / UCLAMP_BUCKET_DELTA; -} - -static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value) -{ - return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value); + return min_t(unsigned int, clamp_value / UCLAMP_BUCKET_DELTA, UCLAMP_BUCKETS - 1); } static inline unsigned int uclamp_none(enum uclamp_id clamp_id) @@ -879,12 +1416,44 @@ unsigned int uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id, return uclamp_idle_value(rq, clamp_id, clamp_value); } +static void __uclamp_update_util_min_rt_default(struct task_struct *p) +{ + unsigned int default_util_min; + struct uclamp_se *uc_se; + + lockdep_assert_held(&p->pi_lock); + + uc_se = &p->uclamp_req[UCLAMP_MIN]; + + /* Only sync if user didn't override the default */ + if (uc_se->user_defined) + return; + + default_util_min = sysctl_sched_uclamp_util_min_rt_default; + uclamp_se_set(uc_se, default_util_min, false); +} + +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); + __uclamp_update_util_min_rt_default(p); + task_rq_unlock(rq, p, &rf); +} + static inline struct uclamp_se uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id) { + /* Copy by value as we could modify it */ struct uclamp_se uc_req = p->uclamp_req[clamp_id]; #ifdef CONFIG_UCLAMP_TASK_GROUP - struct uclamp_se uc_max; + unsigned int tg_min, tg_max, value; /* * Tasks in autogroups or root task group will be @@ -895,9 +1464,11 @@ uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id) if (task_group(p) == &root_task_group) return uc_req; - uc_max = task_group(p)->uclamp[clamp_id]; - if (uc_req.value > uc_max.value || !uc_req.user_defined) - return uc_max; + tg_min = task_group(p)->uclamp[UCLAMP_MIN].value; + tg_max = task_group(p)->uclamp[UCLAMP_MAX].value; + value = uc_req.value; + value = clamp(value, tg_min, tg_max); + uclamp_se_set(&uc_req, value, false); #endif return uc_req; @@ -954,7 +1525,7 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, struct uclamp_se *uc_se = &p->uclamp[clamp_id]; struct uclamp_bucket *bucket; - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); /* Update task effective clamp */ p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id); @@ -994,12 +1565,40 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, unsigned int bkt_clamp; unsigned int rq_clamp; - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); + + /* + * If sched_uclamp_used was enabled after task @p was enqueued, + * we could end up with unbalanced call to uclamp_rq_dec_id(). + * + * In this case the uc_se->active flag should be false since no uclamp + * accounting was performed at enqueue time and we can just return + * here. + * + * Need to be careful of the following enqueue/dequeue ordering + * problem too + * + * enqueue(taskA) + * // sched_uclamp_used gets enabled + * enqueue(taskB) + * dequeue(taskA) + * // Must not decrement bucket->tasks here + * dequeue(taskB) + * + * where we could end up with stale data in uc_se and + * bucket[uc_se->bucket_id]. + * + * The following check here eliminates the possibility of such race. + */ + if (unlikely(!uc_se->active)) + return; bucket = &uc_rq->bucket[uc_se->bucket_id]; + SCHED_WARN_ON(!bucket->tasks); if (likely(bucket->tasks)) bucket->tasks--; + uc_se->active = false; /* @@ -1027,6 +1626,15 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { enum uclamp_id clamp_id; + /* + * Avoid any overhead until uclamp is actually used by the userspace. + * + * The condition is constructed such that a NOP is generated when + * sched_uclamp_used is disabled. + */ + if (!static_branch_unlikely(&sched_uclamp_used)) + return; + if (unlikely(!p->sched_class->uclamp_enabled)) return; @@ -1042,6 +1650,15 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { enum uclamp_id clamp_id; + /* + * Avoid any overhead until uclamp is actually used by the userspace. + * + * The condition is constructed such that a NOP is generated when + * sched_uclamp_used is disabled. + */ + if (!static_branch_unlikely(&sched_uclamp_used)) + return; + if (unlikely(!p->sched_class->uclamp_enabled)) return; @@ -1049,9 +1666,27 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) uclamp_rq_dec_id(rq, p, clamp_id); } +static inline void uclamp_rq_reinc_id(struct rq *rq, struct task_struct *p, + enum uclamp_id clamp_id) +{ + if (!p->uclamp[clamp_id].active) + return; + + uclamp_rq_dec_id(rq, p, clamp_id); + uclamp_rq_inc_id(rq, p, clamp_id); + + /* + * Make sure to clear the idle flag if we've transiently reached 0 + * active tasks on rq. + */ + if (clamp_id == UCLAMP_MAX && (rq->uclamp_flags & UCLAMP_FLAG_IDLE)) + rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE; +} + static inline void -uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) +uclamp_update_active(struct task_struct *p) { + enum uclamp_id clamp_id; struct rq_flags rf; struct rq *rq; @@ -1071,34 +1706,31 @@ uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id) * affecting a valid clamp bucket, the next time it's enqueued, * it will already see the updated clamp bucket value. */ - if (p->uclamp[clamp_id].active) { - uclamp_rq_dec_id(rq, p, clamp_id); - uclamp_rq_inc_id(rq, p, clamp_id); - } + for_each_clamp_id(clamp_id) + uclamp_rq_reinc_id(rq, p, clamp_id); task_rq_unlock(rq, p, &rf); } #ifdef CONFIG_UCLAMP_TASK_GROUP static inline void -uclamp_update_active_tasks(struct cgroup_subsys_state *css, - unsigned int clamps) +uclamp_update_active_tasks(struct cgroup_subsys_state *css) { - enum uclamp_id clamp_id; struct css_task_iter it; struct task_struct *p; css_task_iter_start(css, 0, &it); - while ((p = css_task_iter_next(&it))) { - for_each_clamp_id(clamp_id) { - if ((0x1 << clamp_id) & clamps) - uclamp_update_active(p, clamp_id); - } - } + while ((p = css_task_iter_next(&it))) + uclamp_update_active(p); css_task_iter_end(&it); } 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) { struct task_group *tg = &root_task_group; @@ -1116,17 +1748,44 @@ static void uclamp_update_root_tg(void) static void uclamp_update_root_tg(void) { } #endif -int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, - loff_t *ppos) +static void uclamp_sync_util_min_rt_default(void) +{ + struct task_struct *g, *p; + + /* + * copy_process() sysctl_uclamp + * uclamp_min_rt = X; + * write_lock(&tasklist_lock) read_lock(&tasklist_lock) + * // link thread smp_mb__after_spinlock() + * write_unlock(&tasklist_lock) read_unlock(&tasklist_lock); + * sched_post_fork() for_each_process_thread() + * __uclamp_sync_rt() __uclamp_sync_rt() + * + * Ensures that either sched_post_fork() will observe the new + * uclamp_min_rt or for_each_process_thread() will observe the new + * task. + */ + read_lock(&tasklist_lock); + smp_mb__after_spinlock(); + read_unlock(&tasklist_lock); + + rcu_read_lock(); + 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, + void *buffer, size_t *lenp, loff_t *ppos) { bool update_root_tg = false; - int old_min, old_max; + int old_min, old_max, old_min_rt; int result; mutex_lock(&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; result = proc_dointvec(table, write, buffer, lenp, ppos); if (result) @@ -1135,7 +1794,9 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, goto done; if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max || - sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) { + sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE || + sysctl_sched_uclamp_util_min_rt_default > SCHED_CAPACITY_SCALE) { + result = -EINVAL; goto undo; } @@ -1151,8 +1812,15 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, update_root_tg = true; } - if (update_root_tg) + if (update_root_tg) { + static_branch_enable(&sched_uclamp_used); uclamp_update_root_tg(); + } + + if (old_min_rt != sysctl_sched_uclamp_util_min_rt_default) { + static_branch_enable(&sched_uclamp_used); + uclamp_sync_util_min_rt_default(); + } /* * We update all RUNNABLE tasks only when task groups are in use. @@ -1165,64 +1833,111 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write, 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) { - unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value; - unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value; + 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) - lower_bound = attr->sched_util_min; - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) - upper_bound = attr->sched_util_max; + if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { + util_min = attr->sched_util_min; - if (lower_bound > upper_bound) - return -EINVAL; - if (upper_bound > SCHED_CAPACITY_SCALE) + 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; - /* - * On scheduling class change, reset to default clamps for tasks - * without a task-specific value. - */ for_each_clamp_id(clamp_id) { struct uclamp_se *uc_se = &p->uclamp_req[clamp_id]; - unsigned int clamp_value = uclamp_none(clamp_id); + unsigned int value; - /* Keep using defined clamps across class changes */ - if (uc_se->user_defined) + if (!uclamp_reset(attr, clamp_id, uc_se)) continue; - /* By default, RT tasks always get 100% boost */ + /* + * RT by default have a 100% boost value that could be modified + * at runtime. + */ if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) - clamp_value = uclamp_none(UCLAMP_MAX); + value = sysctl_sched_uclamp_util_min_rt_default; + else + value = uclamp_none(clamp_id); + + uclamp_se_set(uc_se, value, false); - uclamp_se_set(uc_se, clamp_value, false); } if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP))) return; - if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) { + 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) { + 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); } @@ -1232,6 +1947,10 @@ static void uclamp_fork(struct task_struct *p) { enum uclamp_id clamp_id; + /* + * We don't need to hold task_rq_lock() when updating p->uclamp_* here + * as the task is still at its early fork stages. + */ for_each_clamp_id(clamp_id) p->uclamp[clamp_id].active = false; @@ -1239,14 +1958,28 @@ static void uclamp_fork(struct task_struct *p) return; for_each_clamp_id(clamp_id) { - unsigned int clamp_value = uclamp_none(clamp_id); + uclamp_se_set(&p->uclamp_req[clamp_id], + uclamp_none(clamp_id), false); + } +} - /* By default, RT tasks always get 100% boost */ - if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN)) - clamp_value = uclamp_none(UCLAMP_MAX); +static void uclamp_post_fork(struct task_struct *p) +{ + uclamp_update_util_min_rt_default(p); +} + +static void __init init_uclamp_rq(struct rq *rq) +{ + enum uclamp_id clamp_id; + struct uclamp_rq *uc_rq = rq->uclamp; - uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false); + for_each_clamp_id(clamp_id) { + uc_rq[clamp_id] = (struct uclamp_rq) { + .value = uclamp_none(clamp_id) + }; } + + rq->uclamp_flags = UCLAMP_FLAG_IDLE; } static void __init init_uclamp(void) @@ -1255,13 +1988,8 @@ static void __init init_uclamp(void) enum uclamp_id clamp_id; int cpu; - mutex_init(&uclamp_mutex); - - for_each_possible_cpu(cpu) { - memset(&cpu_rq(cpu)->uclamp, 0, - sizeof(struct uclamp_rq)*UCLAMP_CNT); - cpu_rq(cpu)->uclamp_flags = 0; - } + for_each_possible_cpu(cpu) + init_uclamp_rq(cpu_rq(cpu)); for_each_clamp_id(clamp_id) { uclamp_se_set(&init_task.uclamp_req[clamp_id], @@ -1290,30 +2018,61 @@ static inline int uclamp_validate(struct task_struct *p, 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 */ +bool sched_task_on_rq(struct task_struct *p) +{ + return task_on_rq_queued(p); +} + +unsigned long get_wchan(struct task_struct *p) +{ + unsigned long ip = 0; + unsigned int state; + + if (!p || p == current) + return 0; + + /* Only get wchan if task is blocked and we can keep it that way. */ + raw_spin_lock_irq(&p->pi_lock); + state = READ_ONCE(p->__state); + smp_rmb(); /* see try_to_wake_up() */ + if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq) + ip = __get_wchan(p); + raw_spin_unlock_irq(&p->pi_lock); + + return ip; +} + static inline 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_queued(rq, p); + sched_info_enqueue(rq, p); psi_enqueue(p, flags & ENQUEUE_WAKEUP); } uclamp_rq_inc(rq, p); p->sched_class->enqueue_task(rq, p, flags); + + if (sched_core_enabled(rq)) + sched_core_enqueue(rq, p); } static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) { + if (sched_core_enabled(rq)) + sched_core_dequeue(rq, p, flags); + if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); if (!(flags & DEQUEUE_SAVE)) { - sched_info_dequeued(rq, p); + sched_info_dequeue(rq, p); psi_dequeue(p, flags & DEQUEUE_SLEEP); } @@ -1323,9 +2082,6 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) void activate_task(struct rq *rq, struct task_struct *p, int flags) { - if (task_contributes_to_load(p)) - rq->nr_uninterruptible--; - enqueue_task(rq, p, flags); p->on_rq = TASK_ON_RQ_QUEUED; @@ -1335,18 +2091,21 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) { p->on_rq = (flags & DEQUEUE_SLEEP) ? 0 : TASK_ON_RQ_MIGRATING; - if (task_contributes_to_load(p)) - rq->nr_uninterruptible++; - dequeue_task(rq, p, flags); } -/* - * __normal_prio - return the priority that is based on the static prio - */ -static inline int __normal_prio(struct task_struct *p) +static inline int __normal_prio(int policy, int rt_prio, int nice) { - return p->static_prio; + int prio; + + 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); + + return prio; } /* @@ -1358,15 +2117,7 @@ static inline int __normal_prio(struct task_struct *p) */ static inline int normal_prio(struct task_struct *p) { - int prio; - - if (task_has_dl_policy(p)) - prio = MAX_DL_PRIO-1; - else if (task_has_rt_policy(p)) - prio = MAX_RT_PRIO-1 - p->rt_priority; - else - prio = __normal_prio(p); - return prio; + return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); } /* @@ -1422,20 +2173,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) { - const struct sched_class *class; - - if (p->sched_class == rq->curr->sched_class) { + if (p->sched_class == rq->curr->sched_class) rq->curr->sched_class->check_preempt_curr(rq, p, flags); - } else { - for_each_class(class) { - if (class == rq->curr->sched_class) - break; - if (class == p->sched_class) { - resched_curr(rq); - break; - } - } - } + else if (sched_class_above(p->sched_class, rq->curr->sched_class)) + resched_curr(rq); /* * A queue event has occurred, and we're going to schedule. In @@ -1447,19 +2188,107 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP +static void +__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags); + +static int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, + u32 flags); + +static void migrate_disable_switch(struct rq *rq, struct task_struct *p) +{ + if (likely(!p->migration_disabled)) + return; + + if (p->cpus_ptr != &p->cpus_mask) + return; + + /* + * Violates locking rules! see comment in __do_set_cpus_allowed(). + */ + __do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE); +} + +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) +{ + struct task_struct *p = current; + + if (p->migration_disabled > 1) { + p->migration_disabled--; + return; + } + + if (WARN_ON_ONCE(!p->migration_disabled)) + return; + + /* + * 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, &p->cpus_mask, SCA_MIGRATE_ENABLE); + /* + * 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(); +} +EXPORT_SYMBOL_GPL(migrate_enable); + +static inline bool rq_has_pinned_tasks(struct rq *rq) +{ + return rq->nr_pinned; +} + /* * Per-CPU kthreads are allowed to run on !active && online CPUs, see * __set_cpus_allowed_ptr() and select_fallback_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)) return false; - if (is_per_cpu_kthread(p)) + /* migrate_disabled() must be allowed to finish. */ + if (is_migration_disabled(p)) + return cpu_online(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); + + /* KTHREAD_IS_PER_CPU is always allowed. */ + if (kthread_is_per_cpu(p)) return cpu_online(cpu); - return cpu_active(cpu); + /* Regular kernel threads don't get to stay during offline. */ + if (cpu_dying(cpu)) + return false; + + /* But are allowed during online. */ + return cpu_online(cpu); } /* @@ -1484,27 +2313,38 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, struct task_struct *p, int new_cpu) { - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); - WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING); - dequeue_task(rq, p, DEQUEUE_NOCLOCK); + deactivate_task(rq, p, DEQUEUE_NOCLOCK); set_task_cpu(p, new_cpu); rq_unlock(rq, rf); rq = cpu_rq(new_cpu); rq_lock(rq, rf); - BUG_ON(task_cpu(p) != new_cpu); - enqueue_task(rq, p, 0); - p->on_rq = TASK_ON_RQ_QUEUED; + WARN_ON_ONCE(task_cpu(p) != new_cpu); + activate_task(rq, p, 0); check_preempt_curr(rq, p, 0); return rq; } struct migration_arg { - struct task_struct *task; - int dest_cpu; + struct task_struct *task; + int dest_cpu; + struct set_affinity_pending *pending; +}; + +/* + * @refs: number of wait_for_completion() + * @stop_pending: is @stop_work in use + */ +struct set_affinity_pending { + refcount_t refs; + unsigned int stop_pending; + struct completion done; + struct cpu_stop_work stop_work; + struct migration_arg arg; }; /* @@ -1537,39 +2377,145 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf, static int migration_cpu_stop(void *data) { struct migration_arg *arg = data; + struct set_affinity_pending *pending = arg->pending; struct task_struct *p = arg->task; struct rq *rq = this_rq(); + bool complete = false; struct rq_flags rf; /* * The original target CPU might have gone down and we might * be on another CPU but it doesn't matter. */ - local_irq_disable(); + local_irq_save(rf.flags); /* * We need to explicitly wake pending tasks before running * __migrate_task() such that we will not miss enforcing cpus_ptr * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. */ - sched_ttwu_pending(); + flush_smp_call_function_queue(); raw_spin_lock(&p->pi_lock); rq_lock(rq, &rf); + + /* + * If we were passed a pending, then ->stop_pending was set, thus + * p->migration_pending must have remained stable. + */ + WARN_ON_ONCE(pending && pending != p->migration_pending); + /* * If task_rq(p) != rq, it cannot be migrated here, because we're * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because * we're holding p->pi_lock. */ if (task_rq(p) == rq) { + if (is_migration_disabled(p)) + goto out; + + if (pending) { + p->migration_pending = NULL; + complete = true; + + if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) + goto out; + } + if (task_on_rq_queued(p)) rq = __migrate_task(rq, &rf, p, arg->dest_cpu); else p->wake_cpu = arg->dest_cpu; + + /* + * XXX __migrate_task() can fail, at which point we might end + * up running on a dodgy CPU, AFAICT this can only happen + * during CPU hotplug, at which point we'll get pushed out + * anyway, so it's probably not a big deal. + */ + + } else if (pending) { + /* + * This happens when we get migrated between migrate_enable()'s + * preempt_enable() and scheduling the stopper task. At that + * point we're a regular task again and not current anymore. + * + * A !PREEMPT kernel has a giant hole here, which makes it far + * more likely. + */ + + /* + * The task moved before the stopper got to run. We're holding + * ->pi_lock, so the allowed mask is stable - if it got + * somewhere allowed, we're done. + */ + if (cpumask_test_cpu(task_cpu(p), p->cpus_ptr)) { + p->migration_pending = NULL; + complete = true; + goto out; + } + + /* + * When migrate_enable() hits a rq mis-match we can't reliably + * determine is_migration_disabled() and so have to chase after + * it. + */ + WARN_ON_ONCE(!pending->stop_pending); + task_rq_unlock(rq, p, &rf); + stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop, + &pending->arg, &pending->stop_work); + return 0; } - rq_unlock(rq, &rf); - raw_spin_unlock(&p->pi_lock); +out: + if (pending) + pending->stop_pending = false; + task_rq_unlock(rq, p, &rf); + + if (complete) + complete_all(&pending->done); - local_irq_enable(); + return 0; +} + +int push_cpu_stop(void *arg) +{ + struct rq *lowest_rq = NULL, *rq = this_rq(); + struct task_struct *p = arg; + + raw_spin_lock_irq(&p->pi_lock); + raw_spin_rq_lock(rq); + + if (task_rq(p) != rq) + goto out_unlock; + + if (is_migration_disabled(p)) { + p->migration_flags |= MDF_PUSH; + goto out_unlock; + } + + p->migration_flags &= ~MDF_PUSH; + + if (p->sched_class->find_lock_rq) + lowest_rq = p->sched_class->find_lock_rq(p, rq); + + if (!lowest_rq) + goto out_unlock; + + // 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); + resched_curr(lowest_rq); + } + + double_unlock_balance(rq, lowest_rq); + +out_unlock: + rq->push_busy = false; + raw_spin_rq_unlock(rq); + raw_spin_unlock_irq(&p->pi_lock); + + put_task_struct(p); return 0; } @@ -1577,18 +2523,39 @@ static int migration_cpu_stop(void *data) * sched_class::set_cpus_allowed must do the below, but is not required to * actually call this function. */ -void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) +void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags) { + if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) { + p->cpus_ptr = new_mask; + return; + } + cpumask_copy(&p->cpus_mask, new_mask); p->nr_cpus_allowed = cpumask_weight(new_mask); } -void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +static void +__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags) { struct rq *rq = task_rq(p); bool queued, running; - lockdep_assert_held(&p->pi_lock); + /* + * 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 (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); @@ -1598,13 +2565,13 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) * Because __kthread_bind() calls this on blocked tasks without * holding rq->lock. */ - lockdep_assert_held(&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, new_mask); + p->sched_class->set_cpus_allowed(p, new_mask, flags); if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); @@ -1612,109 +2579,517 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) set_next_task(rq, p); } +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + __do_set_cpus_allowed(p, new_mask, 0); +} + +int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, + int node) +{ + if (!src->user_cpus_ptr) + return 0; + + dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node); + if (!dst->user_cpus_ptr) + return -ENOMEM; + + cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr); + return 0; +} + +static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p) +{ + struct cpumask *user_mask = NULL; + + swap(p->user_cpus_ptr, user_mask); + + return user_mask; +} + +void release_user_cpus_ptr(struct task_struct *p) +{ + kfree(clear_user_cpus_ptr(p)); +} + /* - * Change a given task's CPU affinity. Migrate the thread to a - * proper CPU and schedule it away if the CPU it's executing on - * is removed from the allowed bitmask. - * - * NOTE: the caller must have a valid reference to the task, the - * task must not exit() & deallocate itself prematurely. The - * call is not atomic; no spinlocks may be held. + * This function is wildly self concurrent; here be dragons. + * + * + * When given a valid mask, __set_cpus_allowed_ptr() must block until the + * designated task is enqueued on an allowed CPU. If that task is currently + * running, we have to kick it out using the CPU stopper. + * + * Migrate-Disable comes along and tramples all over our nice sandcastle. + * Consider: + * + * Initial conditions: P0->cpus_mask = [0, 1] + * + * P0@CPU0 P1 + * + * migrate_disable(); + * <preempted> + * set_cpus_allowed_ptr(P0, [1]); + * + * P1 *cannot* return from this set_cpus_allowed_ptr() call until P0 executes + * its outermost migrate_enable() (i.e. it exits its Migrate-Disable region). + * This means we need the following scheme: + * + * P0@CPU0 P1 + * + * migrate_disable(); + * <preempted> + * set_cpus_allowed_ptr(P0, [1]); + * <blocks> + * <resumes> + * migrate_enable(); + * __set_cpus_allowed_ptr(); + * <wakes local stopper> + * `--> <woken on migration completion> + * + * Now the fun stuff: there may be several P1-like tasks, i.e. multiple + * concurrent set_cpus_allowed_ptr(P0, [*]) calls. CPU affinity changes of any + * task p are serialized by p->pi_lock, which we can leverage: the one that + * should come into effect at the end of the Migrate-Disable region is the last + * one. This means we only need to track a single cpumask (i.e. p->cpus_mask), + * but we still need to properly signal those waiting tasks at the appropriate + * moment. + * + * This is implemented using struct set_affinity_pending. The first + * __set_cpus_allowed_ptr() caller within a given Migrate-Disable region will + * setup an instance of that struct and install it on the targeted task_struct. + * Any and all further callers will reuse that instance. Those then wait for + * a completion signaled at the tail of the CPU stopper callback (1), triggered + * on the end of the Migrate-Disable region (i.e. outermost migrate_enable()). + * + * + * (1) In the cases covered above. There is one more where the completion is + * signaled within affine_move_task() itself: when a subsequent affinity request + * occurs after the stopper bailed out due to the targeted task still being + * Migrate-Disable. Consider: + * + * Initial conditions: P0->cpus_mask = [0, 1] + * + * CPU0 P1 P2 + * <P0> + * migrate_disable(); + * <preempted> + * set_cpus_allowed_ptr(P0, [1]); + * <blocks> + * <migration/0> + * migration_cpu_stop() + * is_migration_disabled() + * <bails> + * set_cpus_allowed_ptr(P0, [0, 1]); + * <signal completion> + * <awakes> + * + * Note that the above is safe vs a concurrent migrate_enable(), as any + * pending affinity completion is preceded by an uninstallation of + * p->migration_pending done with p->pi_lock held. + */ +static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf, + int dest_cpu, unsigned int flags) +{ + 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)) { + struct task_struct *push_task = NULL; + + if ((flags & SCA_MIGRATE_ENABLE) && + (p->migration_flags & MDF_PUSH) && !rq->push_busy) { + rq->push_busy = true; + push_task = get_task_struct(p); + } + + /* + * If there are pending waiters, but no pending stop_work, + * then complete now. + */ + pending = p->migration_pending; + if (pending && !pending->stop_pending) { + p->migration_pending = NULL; + complete = true; + } + + task_rq_unlock(rq, p, rf); + + if (push_task) { + stop_one_cpu_nowait(rq->cpu, push_cpu_stop, + p, &rq->push_work); + } + + if (complete) + complete_all(&pending->done); + + return 0; + } + + if (!(flags & SCA_MIGRATE_ENABLE)) { + /* serialized by p->pi_lock */ + if (!p->migration_pending) { + /* Install the request */ + refcount_set(&my_pending.refs, 1); + init_completion(&my_pending.done); + my_pending.arg = (struct migration_arg) { + .task = p, + .dest_cpu = dest_cpu, + .pending = &my_pending, + }; + + p->migration_pending = &my_pending; + } else { + pending = p->migration_pending; + refcount_inc(&pending->refs); + /* + * Affinity has changed, but we've already installed a + * pending. migration_cpu_stop() *must* see this, else + * we risk a completion of the pending despite having a + * task on a disallowed CPU. + * + * Serialized by p->pi_lock, so this is safe. + */ + pending->arg.dest_cpu = dest_cpu; + } + } + pending = p->migration_pending; + /* + * - !MIGRATE_ENABLE: + * we'll have installed a pending if there wasn't one already. + * + * - MIGRATE_ENABLE: + * we're here because the current CPU isn't matching anymore, + * the only way that can happen is because of a concurrent + * set_cpus_allowed_ptr() call, which should then still be + * pending completion. + * + * Either way, we really should have a @pending here. + */ + if (WARN_ON_ONCE(!pending)) { + task_rq_unlock(rq, p, rf); + return -EINVAL; + } + + if (task_on_cpu(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) { + /* + * MIGRATE_ENABLE gets here because 'p == current', but for + * anything else we cannot do is_migration_disabled(), punt + * and have the stopper function handle it all race-free. + */ + stop_pending = pending->stop_pending; + if (!stop_pending) + pending->stop_pending = true; + + if (flags & SCA_MIGRATE_ENABLE) + p->migration_flags &= ~MDF_PUSH; + + task_rq_unlock(rq, p, rf); + + if (!stop_pending) { + stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop, + &pending->arg, &pending->stop_work); + } + + if (flags & SCA_MIGRATE_ENABLE) + return 0; + } else { + + if (!is_migration_disabled(p)) { + if (task_on_rq_queued(p)) + rq = move_queued_task(rq, rf, p, dest_cpu); + + if (!pending->stop_pending) { + p->migration_pending = NULL; + complete = true; + } + } + task_rq_unlock(rq, p, rf); + + if (complete) + complete_all(&pending->done); + } + + wait_for_completion(&pending->done); + + if (refcount_dec_and_test(&pending->refs)) + wake_up_var(&pending->refs); /* No UaF, just an address */ + + /* + * Block the original owner of &pending until all subsequent callers + * have seen the completion and decremented the refcount + */ + wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs)); + + /* ARGH */ + WARN_ON_ONCE(my_pending.stop_pending); + + return 0; +} + +/* + * Called with both p->pi_lock and rq->lock held; drops both before returning. */ -static int __set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask, bool check) +static int __set_cpus_allowed_ptr_locked(struct task_struct *p, + const struct cpumask *new_mask, + u32 flags, + struct rq *rq, + struct rq_flags *rf) + __releases(rq->lock) + __releases(p->pi_lock) { + const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p); const struct cpumask *cpu_valid_mask = cpu_active_mask; + bool kthread = p->flags & PF_KTHREAD; + struct cpumask *user_mask = NULL; unsigned int dest_cpu; - struct rq_flags rf; - struct rq *rq; int ret = 0; - rq = task_rq_lock(p, &rf); update_rq_clock(rq); - if (p->flags & PF_KTHREAD) { + if (kthread || is_migration_disabled(p)) { /* - * Kernel threads are allowed on online && !active CPUs + * Kernel threads are allowed on online && !active CPUs, + * however, during cpu-hot-unplug, even these might get pushed + * away if not KTHREAD_IS_PER_CPU. + * + * Specifically, migration_disabled() tasks must not fail the + * cpumask_any_and_distribute() pick below, esp. so on + * SCA_MIGRATE_ENABLE, otherwise we'll not call + * set_cpus_allowed_common() and actually reset p->cpus_ptr. */ cpu_valid_mask = cpu_online_mask; } + if (!kthread && !cpumask_subset(new_mask, cpu_allowed_mask)) { + ret = -EINVAL; + goto out; + } + /* * Must re-check here, to close a race against __kthread_bind(), * sched_setaffinity() is not guaranteed to observe the flag. */ - if (check && (p->flags & PF_NO_SETAFFINITY)) { + if ((flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; goto out; } - if (cpumask_equal(p->cpus_ptr, new_mask)) - goto out; + if (!(flags & SCA_MIGRATE_ENABLE)) { + if (cpumask_equal(&p->cpus_mask, new_mask)) + goto out; + + if (WARN_ON_ONCE(p == current && + is_migration_disabled(p) && + !cpumask_test_cpu(task_cpu(p), new_mask))) { + ret = -EBUSY; + goto out; + } + } - dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); + /* + * Picking a ~random cpu helps in cases where we are changing affinity + * for groups of tasks (ie. cpuset), so that load balancing is not + * immediately required to distribute the tasks within their new mask. + */ + dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask); if (dest_cpu >= nr_cpu_ids) { ret = -EINVAL; goto out; } - do_set_cpus_allowed(p, new_mask); + __do_set_cpus_allowed(p, new_mask, flags); - if (p->flags & PF_KTHREAD) { - /* - * For kernel threads that do indeed end up on online && - * !active we want to ensure they are strict per-CPU threads. - */ - WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && - !cpumask_intersects(new_mask, cpu_active_mask) && - p->nr_cpus_allowed != 1); - } + if (flags & SCA_USER) + user_mask = clear_user_cpus_ptr(p); - /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), new_mask)) - goto out; + ret = affine_move_task(rq, p, rf, dest_cpu, flags); + + kfree(user_mask); + + return ret; - if (task_running(rq, p) || p->state == TASK_WAKING) { - struct migration_arg arg = { p, dest_cpu }; - /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, p, &rf); - stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); - return 0; - } else if (task_on_rq_queued(p)) { - /* - * OK, since we're going to drop the lock immediately - * afterwards anyway. - */ - rq = move_queued_task(rq, &rf, p, dest_cpu); - } out: - task_rq_unlock(rq, p, &rf); + task_rq_unlock(rq, p, rf); return ret; } +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * 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, + const struct cpumask *new_mask, u32 flags) +{ + struct rq_flags rf; + struct rq *rq; + + rq = task_rq_lock(p, &rf); + return __set_cpus_allowed_ptr_locked(p, new_mask, flags, rq, &rf); +} + int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { - return __set_cpus_allowed_ptr(p, new_mask, false); + return __set_cpus_allowed_ptr(p, new_mask, 0); } EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); +/* + * Change a given task's CPU affinity to the intersection of its current + * affinity mask and @subset_mask, writing the resulting mask to @new_mask + * and pointing @p->user_cpus_ptr to a copy of the old mask. + * If the resulting mask is empty, leave the affinity unchanged and return + * -EINVAL. + */ +static int restrict_cpus_allowed_ptr(struct task_struct *p, + struct cpumask *new_mask, + const struct cpumask *subset_mask) +{ + struct cpumask *user_mask = NULL; + struct rq_flags rf; + struct rq *rq; + int err; + + if (!p->user_cpus_ptr) { + user_mask = kmalloc(cpumask_size(), GFP_KERNEL); + if (!user_mask) + return -ENOMEM; + } + + rq = task_rq_lock(p, &rf); + + /* + * Forcefully restricting the affinity of a deadline task is + * likely to cause problems, so fail and noisily override the + * mask entirely. + */ + if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { + err = -EPERM; + goto err_unlock; + } + + if (!cpumask_and(new_mask, &p->cpus_mask, subset_mask)) { + err = -EINVAL; + goto err_unlock; + } + + /* + * We're about to butcher the task affinity, so keep track of what + * the user asked for in case we're able to restore it later on. + */ + if (user_mask) { + cpumask_copy(user_mask, p->cpus_ptr); + p->user_cpus_ptr = user_mask; + } + + return __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf); + +err_unlock: + task_rq_unlock(rq, p, &rf); + kfree(user_mask); + return err; +} + +/* + * Restrict the CPU affinity of task @p so that it is a subset of + * task_cpu_possible_mask() and point @p->user_cpu_ptr to a copy of the + * old affinity mask. If the resulting mask is empty, we warn and walk + * up the cpuset hierarchy until we find a suitable mask. + */ +void force_compatible_cpus_allowed_ptr(struct task_struct *p) +{ + cpumask_var_t new_mask; + const struct cpumask *override_mask = task_cpu_possible_mask(p); + + alloc_cpumask_var(&new_mask, GFP_KERNEL); + + /* + * __migrate_task() can fail silently in the face of concurrent + * offlining of the chosen destination CPU, so take the hotplug + * lock to ensure that the migration succeeds. + */ + cpus_read_lock(); + if (!cpumask_available(new_mask)) + goto out_set_mask; + + if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask)) + goto out_free_mask; + + /* + * We failed to find a valid subset of the affinity mask for the + * task, so override it based on its cpuset hierarchy. + */ + cpuset_cpus_allowed(p, new_mask); + override_mask = new_mask; + +out_set_mask: + if (printk_ratelimit()) { + printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n", + task_pid_nr(p), p->comm, + cpumask_pr_args(override_mask)); + } + + WARN_ON(set_cpus_allowed_ptr(p, override_mask)); +out_free_mask: + cpus_read_unlock(); + free_cpumask_var(new_mask); +} + +static int +__sched_setaffinity(struct task_struct *p, const struct cpumask *mask); + +/* + * Restore the affinity of a task @p which was previously restricted by a + * call to force_compatible_cpus_allowed_ptr(). This will clear (and free) + * @p->user_cpus_ptr. + * + * It is the caller's responsibility to serialise this with any calls to + * force_compatible_cpus_allowed_ptr(@p). + */ +void relax_compatible_cpus_allowed_ptr(struct task_struct *p) +{ + struct cpumask *user_mask = p->user_cpus_ptr; + unsigned long flags; + + /* + * Try to restore the old affinity mask. If this fails, then + * we free the mask explicitly to avoid it being inherited across + * a subsequent fork(). + */ + if (!user_mask || !__sched_setaffinity(p, user_mask)) + return; + + raw_spin_lock_irqsave(&p->pi_lock, flags); + user_mask = clear_user_cpus_ptr(p); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + kfree(user_mask); +} + void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { #ifdef CONFIG_SCHED_DEBUG + unsigned int state = READ_ONCE(p->__state); + /* * We should never call set_task_cpu() on a blocked task, * ttwu() will sort out the placement. */ - WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && - !p->on_rq); + WARN_ON_ONCE(state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq); /* * Migrating fair class task must have p->on_rq = TASK_ON_RQ_MIGRATING, * because schedstat_wait_{start,end} rebase migrating task's wait_start * time relying on p->on_rq. */ - WARN_ON_ONCE(p->state == TASK_RUNNING && + WARN_ON_ONCE(state == TASK_RUNNING && p->sched_class == &fair_sched_class && (p->on_rq && !task_on_rq_migrating(p))); @@ -1730,12 +3105,14 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) * task_rq_lock(). */ WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || - lockdep_is_held(&task_rq(p)->lock))); + lockdep_is_held(__rq_lockp(task_rq(p))))); #endif /* * Clearly, migrating tasks to offline CPUs is a fairly daft thing. */ WARN_ON_ONCE(!cpu_online(new_cpu)); + + WARN_ON_ONCE(is_migration_disabled(p)); #endif trace_sched_migrate_task(p, new_cpu); @@ -1871,12 +3248,12 @@ out: /* * wait_task_inactive - wait for a thread to unschedule. * - * If @match_state is nonzero, it's the @p->state value just checked and - * not expected to change. 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. + * 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 @@ -1884,7 +3261,7 @@ out: * 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, long match_state) +unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state) { int running, queued; struct rq_flags rf; @@ -1907,12 +3284,12 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * * 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_running()" will + * 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_running(rq, p)) { - if (match_state && unlikely(p->state != match_state)) + while (task_on_cpu(rq, p)) { + if (!(READ_ONCE(p->__state) & match_state)) return 0; cpu_relax(); } @@ -1924,10 +3301,10 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) */ rq = task_rq_lock(p, &rf); trace_sched_wait_task(p); - running = task_running(rq, p); + running = task_on_cpu(rq, p); queued = task_on_rq_queued(p); ncsw = 0; - if (!match_state || p->state == match_state) + if (READ_ONCE(p->__state) & match_state) ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ task_rq_unlock(rq, p, &rf); @@ -1961,7 +3338,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) ktime_t to = NSEC_PER_SEC / HZ; set_current_state(TASK_UNINTERRUPTIBLE); - schedule_hrtimeout(&to, HRTIMER_MODE_REL); + schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD); continue; } @@ -2040,9 +3417,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* Look for allowed, online CPU in same node. */ for_each_cpu(dest_cpu, nodemask) { - if (!cpu_active(dest_cpu)) - continue; - if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) + if (is_cpu_allowed(p, dest_cpu)) return dest_cpu; } } @@ -2059,17 +3434,21 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* No more Mr. Nice Guy. */ switch (state) { case cpuset: - if (IS_ENABLED(CONFIG_CPUSETS)) { - cpuset_cpus_allowed_fallback(p); + if (cpuset_cpus_allowed_fallback(p)) { state = possible; break; } - /* Fall-through */ + fallthrough; case possible: - do_set_cpus_allowed(p, cpu_possible_mask); + /* + * 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)); state = fail; break; - case fail: BUG(); break; @@ -2096,12 +3475,12 @@ 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 sd_flags, 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) - cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) + cpu = p->sched_class->select_task_rq(p, cpu, wake_flags); else cpu = cpumask_any(p->cpus_ptr); @@ -2121,14 +3500,9 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) return cpu; } -static void update_avg(u64 *avg, u64 sample) -{ - s64 diff = sample - *avg; - *avg += diff >> 3; -} - void sched_set_stop_task(int cpu, struct task_struct *stop) { + static struct lock_class_key stop_pi_lock; struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; struct task_struct *old_stop = cpu_rq(cpu)->stop; @@ -2144,6 +3518,20 @@ void sched_set_stop_task(int cpu, struct task_struct *stop) sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); stop->sched_class = &stop_sched_class; + + /* + * The PI code calls rt_mutex_setprio() with ->pi_lock held to + * adjust the effective priority of a task. As a result, + * rt_mutex_setprio() can trigger (RT) balancing operations, + * which can then trigger wakeups of the stop thread to push + * around the current task. + * + * The stop task itself will never be part of the PI-chain, it + * never blocks, therefore that ->pi_lock recursion is safe. + * Tell lockdep about this by placing the stop->pi_lock in its + * own class. + */ + lockdep_set_class(&stop->pi_lock, &stop_pi_lock); } cpu_rq(cpu)->stop = stop; @@ -2157,15 +3545,23 @@ void sched_set_stop_task(int cpu, struct task_struct *stop) } } -#else +#else /* CONFIG_SMP */ static inline int __set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask, bool check) + const struct cpumask *new_mask, + u32 flags) { return set_cpus_allowed_ptr(p, new_mask); } -#endif /* CONFIG_SMP */ +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; +} + +#endif /* !CONFIG_SMP */ static void ttwu_stat(struct task_struct *p, int cpu, int wake_flags) @@ -2180,11 +3576,11 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) #ifdef CONFIG_SMP if (cpu == rq->cpu) { __schedstat_inc(rq->ttwu_local); - __schedstat_inc(p->se.statistics.nr_wakeups_local); + __schedstat_inc(p->stats.nr_wakeups_local); } else { struct sched_domain *sd; - __schedstat_inc(p->se.statistics.nr_wakeups_remote); + __schedstat_inc(p->stats.nr_wakeups_remote); rcu_read_lock(); for_each_domain(rq->cpu, sd) { if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { @@ -2196,14 +3592,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags) } if (wake_flags & WF_MIGRATED) - __schedstat_inc(p->se.statistics.nr_wakeups_migrate); + __schedstat_inc(p->stats.nr_wakeups_migrate); #endif /* CONFIG_SMP */ __schedstat_inc(rq->ttwu_count); - __schedstat_inc(p->se.statistics.nr_wakeups); + __schedstat_inc(p->stats.nr_wakeups); if (wake_flags & WF_SYNC) - __schedstat_inc(p->se.statistics.nr_wakeups_sync); + __schedstat_inc(p->stats.nr_wakeups_sync); } /* @@ -2213,13 +3609,13 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, struct rq_flags *rf) { check_preempt_curr(rq, p, wake_flags); - p->state = TASK_RUNNING; + 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 its safe to + * 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); @@ -2236,6 +3632,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, 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 @@ -2247,27 +3646,51 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, { int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK; - lockdep_assert_held(&rq->lock); + lockdep_assert_rq_held(rq); -#ifdef CONFIG_SMP if (p->sched_contributes_to_load) rq->nr_uninterruptible--; +#ifdef CONFIG_SMP 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); } /* - * Called in case the task @p isn't fully descheduled from its runqueue, - * in this case we must do a remote wakeup. Its a 'light' wakeup though, - * since all we need to do is flip p->state to TASK_RUNNING, since - * the task is still ->on_rq. + * Consider @p being inside a wait loop: + * + * for (;;) { + * set_current_state(TASK_UNINTERRUPTIBLE); + * + * if (CONDITION) + * break; + * + * schedule(); + * } + * __set_current_state(TASK_RUNNING); + * + * between set_current_state() and schedule(). In this case @p is still + * runnable, so all that needs doing is change p->state back to TASK_RUNNING in + * an atomic manner. + * + * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq + * then schedule() must still happen and p->state can be changed to + * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we + * need to do a full wakeup with enqueue. + * + * Returns: %true when the wakeup is done, + * %false otherwise. */ -static int ttwu_remote(struct task_struct *p, int wake_flags) +static int ttwu_runnable(struct task_struct *p, int wake_flags) { struct rq_flags rf; struct rq *rq; @@ -2286,75 +3709,63 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) } #ifdef CONFIG_SMP -void sched_ttwu_pending(void) +void sched_ttwu_pending(void *arg) { + struct llist_node *llist = arg; struct rq *rq = this_rq(); - struct llist_node *llist = llist_del_all(&rq->wake_list); struct task_struct *p, *t; struct rq_flags rf; if (!llist) return; + /* + * rq::ttwu_pending racy indication of out-standing wakeups. + * Races such that false-negatives are possible, since they + * are shorter lived that false-positives would be. + */ + WRITE_ONCE(rq->ttwu_pending, 0); + rq_lock_irqsave(rq, &rf); update_rq_clock(rq); - llist_for_each_entry_safe(p, t, llist, wake_entry) + llist_for_each_entry_safe(p, t, llist, wake_entry.llist) { + if (WARN_ON_ONCE(p->on_cpu)) + smp_cond_load_acquire(&p->on_cpu, !VAL); + + if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq))) + set_task_cpu(p, cpu_of(rq)); + ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf); + } rq_unlock_irqrestore(rq, &rf); } -void scheduler_ipi(void) +void send_call_function_single_ipi(int cpu) { - /* - * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting - * TIF_NEED_RESCHED remotely (for the first time) will also send - * this IPI. - */ - preempt_fold_need_resched(); - - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) - return; - - /* - * Not all reschedule IPI handlers call irq_enter/irq_exit, since - * traditionally all their work was done from the interrupt return - * path. Now that we actually do some work, we need to make sure - * we do call them. - * - * Some archs already do call them, luckily irq_enter/exit nest - * properly. - * - * Arguably we should visit all archs and update all handlers, - * however a fair share of IPIs are still resched only so this would - * somewhat pessimize the simple resched case. - */ - irq_enter(); - sched_ttwu_pending(); + struct rq *rq = cpu_rq(cpu); - /* - * Check if someone kicked us for doing the nohz idle load balance. - */ - if (unlikely(got_nohz_idle_kick())) { - this_rq()->idle_balance = 1; - raise_softirq_irqoff(SCHED_SOFTIRQ); - } - irq_exit(); + if (!set_nr_if_polling(rq->idle)) + arch_send_call_function_single_ipi(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } -static void ttwu_queue_remote(struct task_struct *p, int cpu, int wake_flags) +/* + * Queue a task on the target CPUs wake_list and wake the CPU via IPI if + * necessary. The wakee CPU on receipt of the IPI will queue the task + * via sched_ttwu_wakeup() for activation so the wakee incurs the cost + * of the wakeup instead of the waker. + */ +static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED); - if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { - if (!set_nr_if_polling(rq->idle)) - smp_send_reschedule(cpu); - else - trace_sched_wake_idle_without_ipi(cpu); - } + WRITE_ONCE(rq->ttwu_pending, 1); + __smp_call_single_queue(cpu, &p->wake_entry.llist); } void wake_up_if_idle(int cpu) @@ -2367,15 +3778,11 @@ void wake_up_if_idle(int cpu) if (!is_idle_task(rcu_dereference(rq->curr))) goto out; - if (set_nr_if_polling(rq->idle)) { - trace_sched_wake_idle_without_ipi(cpu); - } else { - rq_lock_irqsave(rq, &rf); - if (is_idle_task(rq->curr)) - smp_send_reschedule(cpu); - /* Else CPU is not idle, do nothing here: */ - rq_unlock_irqrestore(rq, &rf); - } + 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); out: rcu_read_unlock(); @@ -2383,8 +3790,70 @@ out: bool cpus_share_cache(int this_cpu, int that_cpu) { + if (this_cpu == that_cpu) + return true; + return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu); } + +static inline bool ttwu_queue_cond(struct task_struct *p, int cpu) +{ + /* + * Do not complicate things with the async wake_list while the CPU is + * in hotplug state. + */ + if (!cpu_active(cpu)) + return false; + + /* Ensure the task will still be allowed to run on the CPU. */ + if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + + /* + * If the CPU does not share cache, then queue the task on the + * remote rqs wakelist to avoid accessing remote data. + */ + if (!cpus_share_cache(smp_processor_id(), cpu)) + return true; + + if (cpu == smp_processor_id()) + return false; + + /* + * If the wakee cpu is idle, or the task is descheduling and the + * only running task on the CPU, then use the wakelist to offload + * the task activation to the idle (or soon-to-be-idle) CPU as + * the current CPU is likely busy. nr_running is checked to + * avoid unnecessary task stacking. + * + * Note that we can only get here with (wakee) p->on_rq=0, + * p->on_cpu can be whatever, we've done the dequeue, so + * the wakee has been accounted out of ->nr_running. + */ + if (!cpu_rq(cpu)->nr_running) + return true; + + return false; +} + +static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags) +{ + if (sched_feat(TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) { + sched_clock_cpu(cpu); /* Sync clocks across CPUs */ + __ttwu_queue_wakelist(p, cpu, wake_flags); + return true; + } + + 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) @@ -2392,13 +3861,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) struct rq *rq = cpu_rq(cpu); struct rq_flags rf; -#if defined(CONFIG_SMP) - if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { - sched_clock_cpu(cpu); /* Sync clocks across CPUs */ - ttwu_queue_remote(p, cpu, wake_flags); + if (ttwu_queue_wakelist(p, cpu, wake_flags)) return; - } -#endif rq_lock(rq, &rf); update_rq_clock(rq); @@ -2407,6 +3871,55 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) } /* + * Invoked from try_to_wake_up() to check whether the task can be woken up. + * + * The caller holds p::pi_lock if p != current or has preemption + * disabled when p == current. + * + * The rules of PREEMPT_RT 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. + */ +static __always_inline +bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success) +{ + 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; + } + +#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. + * + * After acquiring the lock the task will restore p::__state + * from p::saved_state which ensures that the regular + * wakeup is not lost. The restore will also set + * p::saved_state to TASK_RUNNING so any further tests will + * not result in false positives vs. @success + */ + if (p->saved_state & state) { + p->saved_state = TASK_RUNNING; + *success = 1; + } +#endif + return false; +} + +/* * Notes on Program-Order guarantees on SMP systems. * * MIGRATION @@ -2454,8 +3967,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * migration. However the means are completely different as there is no lock * chain to provide order. Instead we do: * - * 1) smp_store_release(X->on_cpu, 0) - * 2) smp_cond_load_acquire(!X->on_cpu) + * 1) smp_store_release(X->on_cpu, 0) -- finish_task() + * 2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up() * * Example: * @@ -2495,15 +4008,33 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * @state: the mask of task states that can be woken * @wake_flags: wake modifier flags (WF_*) * - * If (@state & @p->state) @p->state = TASK_RUNNING. + * Conceptually does: + * + * If (@state & @p->state) @p->state = TASK_RUNNING. * * If the task was not queued/runnable, also place it back on a runqueue. * - * Atomic against schedule() which would dequeue a task, also see - * set_current_state(). + * This function is atomic against schedule() which would dequeue the task. + * + * It issues a full memory barrier before accessing @p->state, see the comment + * with set_current_state(). + * + * Uses p->pi_lock to serialize against concurrent wake-ups. * - * This function executes a full memory barrier before accessing the task - * state; see set_current_state(). + * Relies on p->pi_lock stabilizing: + * - p->sched_class + * - p->cpus_ptr + * - p->sched_task_group + * in order to do migration, see its use of select_task_rq()/set_task_cpu(). + * + * Tries really hard to only take one task_rq(p)->lock for performance. + * Takes rq->lock in: + * - ttwu_runnable() -- old rq, unavoidable, see comment there; + * - ttwu_queue() -- new rq, for enqueue of the task; + * - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us. + * + * As a consequence we race really badly with just about everything. See the + * many memory barriers and their comments for details. * * Return: %true if @p->state changes (an actual wakeup was done), * %false otherwise. @@ -2519,7 +4050,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) /* * We're waking current, this means 'p->on_rq' and 'task_cpu(p) * == smp_processor_id()'. Together this means we can special - * case the whole 'p->on_rq && ttwu_remote()' case below + * case the whole 'p->on_rq && ttwu_runnable()' case below * without taking any locks. * * In particular: @@ -2527,13 +4058,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * - we're serialized against set_special_state() by virtue of * it disabling IRQs (this allows not taking ->pi_lock). */ - if (!(p->state & state)) + if (!ttwu_state_match(p, state, &success)) goto out; - success = 1; - cpu = task_cpu(p); trace_sched_waking(p); - p->state = TASK_RUNNING; + WRITE_ONCE(p->__state, TASK_RUNNING); trace_sched_wakeup(p); goto out; } @@ -2541,20 +4070,16 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) /* * If we are going to wake up a thread waiting for CONDITION we * need to ensure that CONDITION=1 done by the caller can not be - * reordered with p->state check below. This pairs with mb() in - * set_current_state() the waiting thread does. + * 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 (!(p->state & state)) + if (!ttwu_state_match(p, state, &success)) goto unlock; trace_sched_waking(p); - /* We're going to change ->state: */ - success = 1; - cpu = task_cpu(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 @@ -2574,9 +4099,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * * 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 (p->on_rq && ttwu_remote(p, wake_flags)) + if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags)) goto unlock; #ifdef CONFIG_SMP @@ -2598,12 +4125,47 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * * 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_rmb(); + 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); + + /* + * 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, wait until its done referencing the task. + * this task as prev, wait until it's done referencing the task. * * Pairs with the smp_store_release() in finish_task(). * @@ -2612,28 +4174,19 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) */ smp_cond_load_acquire(&p->on_cpu, !VAL); - p->sched_contributes_to_load = !!task_contributes_to_load(p); - p->state = TASK_WAKING; - - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - - cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); + 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); + } + wake_flags |= WF_MIGRATED; psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } - -#else /* CONFIG_SMP */ - - if (p->in_iowait) { - delayacct_blkio_end(p); - atomic_dec(&task_rq(p)->nr_iowait); - } - +#else + cpu = task_cpu(p); #endif /* CONFIG_SMP */ ttwu_queue(p, cpu, wake_flags); @@ -2641,13 +4194,105 @@ unlock: raw_spin_unlock_irqrestore(&p->pi_lock, flags); out: if (success) - ttwu_stat(p, cpu, wake_flags); + ttwu_stat(p, task_cpu(p), wake_flags); preempt_enable(); return success; } /** + * task_call_func - Invoke a function on task in fixed state + * @p: Process for which the function is to be invoked, can be @current. + * @func: Function to invoke. + * @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. + * + * Returns: + * Whatever @func returns + */ +int task_call_func(struct task_struct *p, task_call_f func, void *arg) +{ + struct rq *rq = NULL; + unsigned int state; + struct rq_flags rf; + int ret; + + raw_spin_lock_irqsave(&p->pi_lock, rf.flags); + + state = READ_ONCE(p->__state); + + /* + * Ensure we load p->on_rq after p->__state, otherwise it would be + * possible to, falsely, observe p->on_rq == 0. + * + * See try_to_wake_up() for a longer comment. + */ + smp_rmb(); + + /* + * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when + * the task is blocked. Make sure to check @state since ttwu() can drop + * locks at the end, see ttwu_queue_wakelist(). + */ + if (state == TASK_RUNNING || state == TASK_WAKING || p->on_rq) + rq = __task_rq_lock(p, &rf); + + /* + * At this point the task is pinned; either: + * - blocked and we're holding off wakeups (pi->lock) + * - woken, and we're holding off enqueue (rq->lock) + * - queued, and we're holding off schedule (rq->lock) + * - running, and we're holding off de-schedule (rq->lock) + * + * The called function (@func) can use: task_curr(), p->on_rq and + * p->__state to differentiate between these states. + */ + ret = func(p, arg); + + if (rq) + rq_unlock(rq, &rf); + + raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags); + return ret; +} + +/** + * cpu_curr_snapshot - Return a snapshot of the currently running task + * @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. + * + * 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 + * task, but there is no guarantee. Callers wishing a useful return + * value must take some action to ensure that the specified CPU remains + * online throughout. + * + * This function executes full memory barriers before and after fetching + * the pointer, which permits the caller to confine this function's fetch + * with respect to the caller's accesses to other shared variables. + */ +struct task_struct *cpu_curr_snapshot(int cpu) +{ + struct task_struct *t; + + smp_mb(); /* Pairing determined by caller's synchronization design. */ + t = rcu_dereference(cpu_curr(cpu)); + smp_mb(); /* Pairing determined by caller's synchronization design. */ + return t; +} + +/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -2693,7 +4338,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) #ifdef CONFIG_SCHEDSTATS /* Even if schedstat is disabled, there should not be garbage */ - memset(&p->se.statistics, 0, sizeof(p->se.statistics)); + memset(&p->stats, 0, sizeof(p->stats)); #endif RB_CLEAR_NODE(&p->dl.rb_node); @@ -2715,13 +4360,19 @@ 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); #ifdef CONFIG_NUMA_BALANCING -void set_numabalancing_state(bool enabled) +int sysctl_numa_balancing_mode; + +static void __set_numabalancing_state(bool enabled) { if (enabled) static_branch_enable(&sched_numa_balancing); @@ -2729,13 +4380,33 @@ void set_numabalancing_state(bool enabled) static_branch_disable(&sched_numa_balancing); } +void set_numabalancing_state(bool enabled) +{ + if (enabled) + sysctl_numa_balancing_mode = NUMA_BALANCING_NORMAL; + else + sysctl_numa_balancing_mode = NUMA_BALANCING_DISABLED; + __set_numabalancing_state(enabled); +} + #ifdef CONFIG_PROC_SYSCTL +static void reset_memory_tiering(void) +{ + struct pglist_data *pgdat; + + for_each_online_pgdat(pgdat) { + pgdat->nbp_threshold = 0; + pgdat->nbp_th_nr_cand = node_page_state(pgdat, PGPROMOTE_CANDIDATE); + pgdat->nbp_th_start = jiffies_to_msecs(jiffies); + } +} + int sysctl_numa_balancing(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) + void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int err; - int state = static_branch_likely(&sched_numa_balancing); + int state = sysctl_numa_balancing_mode; if (write && !capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2745,8 +4416,13 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (err < 0) return err; - if (write) - set_numabalancing_state(state); + if (write) { + if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING) && + (state & NUMA_BALANCING_MEMORY_TIERING)) + reset_memory_tiering(); + sysctl_numa_balancing_mode = state; + __set_numabalancing_state(state); + } return err; } #endif @@ -2755,7 +4431,6 @@ int sysctl_numa_balancing(struct ctl_table *table, int write, #ifdef CONFIG_SCHEDSTATS DEFINE_STATIC_KEY_FALSE(sched_schedstats); -static bool __initdata __sched_schedstats = false; static void set_schedstats(bool enabled) { @@ -2779,16 +4454,11 @@ static int __init setup_schedstats(char *str) if (!str) goto out; - /* - * This code is called before jump labels have been set up, so we can't - * change the static branch directly just yet. Instead set a temporary - * variable so init_schedstats() can do it later. - */ if (!strcmp(str, "enable")) { - __sched_schedstats = true; + set_schedstats(true); ret = 1; } else if (!strcmp(str, "disable")) { - __sched_schedstats = false; + set_schedstats(false); ret = 1; } out: @@ -2799,14 +4469,9 @@ out: } __setup("schedstats=", setup_schedstats); -static void __init init_schedstats(void) -{ - set_schedstats(__sched_schedstats); -} - #ifdef CONFIG_PROC_SYSCTL -int sysctl_schedstats(struct ctl_table *table, int write, - void __user *buffer, size_t *lenp, loff_t *ppos) +static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer, + size_t *lenp, loff_t *ppos) { struct ctl_table t; int err; @@ -2825,24 +4490,66 @@ int sysctl_schedstats(struct ctl_table *table, int write, return err; } #endif /* CONFIG_PROC_SYSCTL */ -#else /* !CONFIG_SCHEDSTATS */ -static inline void init_schedstats(void) {} #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_SYSCTL +static struct ctl_table sched_core_sysctls[] = { +#ifdef CONFIG_SCHEDSTATS + { + .procname = "sched_schedstats", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_schedstats, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_UCLAMP_TASK + { + .procname = "sched_util_clamp_min", + .data = &sysctl_sched_uclamp_util_min, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_max", + .data = &sysctl_sched_uclamp_util_max, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, + { + .procname = "sched_util_clamp_min_rt_default", + .data = &sysctl_sched_uclamp_util_min_rt_default, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = sysctl_sched_uclamp_handler, + }, +#endif /* CONFIG_UCLAMP_TASK */ + {} +}; +static int __init sched_core_sysctl_init(void) +{ + register_sysctl_init("kernel", sched_core_sysctls); + return 0; +} +late_initcall(sched_core_sysctl_init); +#endif /* CONFIG_SYSCTL */ + /* * fork()/clone()-time setup: */ int sched_fork(unsigned long clone_flags, struct task_struct *p) { - unsigned long flags; - __sched_fork(clone_flags, p); /* * We mark the process as NEW here. This guarantees that * nobody will actually run it, and a signal or other external * event cannot wake it up and insert it on the runqueue either. */ - p->state = TASK_NEW; + p->__state = TASK_NEW; /* * Make sure we do not leak PI boosting priority to the child. @@ -2862,7 +4569,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) } else if (PRIO_TO_NICE(p->static_prio) < 0) p->static_prio = NICE_TO_PRIO(0); - p->prio = p->normal_prio = __normal_prio(p); + p->prio = p->normal_prio = p->static_prio; set_load_weight(p, false); /* @@ -2881,22 +4588,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) init_entity_runnable_average(&p->se); - /* - * The child is not yet in the pid-hash so no cgroup attach races, - * and the cgroup is pinned to this child due to cgroup_fork() - * is ran before sched_fork(). - * - * Silence PROVE_RCU. - */ - raw_spin_lock_irqsave(&p->pi_lock, flags); - /* - * We're setting the CPU for the first time, we don't migrate, - * so use __set_task_cpu(). - */ - __set_task_cpu(p, smp_processor_id()); - if (p->sched_class->task_fork) - p->sched_class->task_fork(p); - raw_spin_unlock_irqrestore(&p->pi_lock, flags); #ifdef CONFIG_SCHED_INFO if (likely(sched_info_on())) @@ -2913,6 +4604,40 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) return 0; } +void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs) +{ + unsigned long flags; + + /* + * Because we're not yet on the pid-hash, p->pi_lock isn't strictly + * required yet, but lockdep gets upset if rules are violated. + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); +#ifdef CONFIG_CGROUP_SCHED + if (1) { + struct task_group *tg; + tg = container_of(kargs->cset->subsys[cpu_cgrp_id], + struct task_group, css); + tg = autogroup_task_group(p, tg); + 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(). + */ + __set_task_cpu(p, smp_processor_id()); + if (p->sched_class->task_fork) + p->sched_class->task_fork(p); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); +} + +void sched_post_fork(struct task_struct *p) +{ + uclamp_post_fork(p); +} + unsigned long to_ratio(u64 period, u64 runtime) { if (runtime == RUNTIME_INF) @@ -2942,7 +4667,7 @@ void wake_up_new_task(struct task_struct *p) struct rq *rq; raw_spin_lock_irqsave(&p->pi_lock, rf.flags); - p->state = TASK_RUNNING; + WRITE_ONCE(p->__state, TASK_RUNNING); #ifdef CONFIG_SMP /* * Fork balancing, do it here and not earlier because: @@ -2953,7 +4678,8 @@ void wake_up_new_task(struct task_struct *p) * as we're not fully set-up yet. */ p->recent_used_cpu = task_cpu(p); - __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); + rseq_migrate(p); + __set_task_cpu(p, select_task_rq(p, task_cpu(p), WF_FORK)); #endif rq = __task_rq_lock(p, &rf); update_rq_clock(rq); @@ -2965,7 +4691,7 @@ void wake_up_new_task(struct task_struct *p) #ifdef CONFIG_SMP if (p->sched_class->task_woken) { /* - * Nothing relies on rq->lock after this, so its fine to + * Nothing relies on rq->lock after this, so it's fine to * drop it. */ rq_unpin_lock(rq, &rf); @@ -3069,8 +4795,11 @@ static inline void prepare_task(struct task_struct *next) /* * Claim the task as running, we do this before switching to it * such that any running task will have this set. + * + * See the smp_load_acquire(&p->on_cpu) case in ttwu() and + * its ordering comment. */ - next->on_cpu = 1; + WRITE_ONCE(next->on_cpu, 1); #endif } @@ -3078,8 +4807,9 @@ static inline void finish_task(struct task_struct *prev) { #ifdef CONFIG_SMP /* - * After ->on_cpu is cleared, the task can be moved to a different CPU. - * We must ensure this doesn't happen until the switch is completely + * 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 + * must ensure this doesn't happen until the switch is completely * finished. * * In particular, the load of prev->state in finish_task_switch() must @@ -3091,6 +4821,106 @@ static inline void finish_task(struct task_struct *prev) #endif } +#ifdef CONFIG_SMP + +static void do_balance_callbacks(struct rq *rq, struct balance_callback *head) +{ + void (*func)(struct rq *rq); + struct balance_callback *next; + + lockdep_assert_rq_held(rq); + + while (head) { + func = (void (*)(struct rq *))head->func; + next = head->next; + head->next = NULL; + head = next; + + func(rq); + } +} + +static void balance_push(struct rq *rq); + +/* + * balance_push_callback is a right abuse of the callback interface and plays + * by significantly different rules. + * + * Where the normal balance_callback's purpose is to be ran in the same context + * that queued it (only later, when it's safe to drop rq->lock again), + * balance_push_callback is specifically targeted at __schedule(). + * + * This abuse is tolerated because it places all the unlikely/odd cases behind + * a single test, namely: rq->balance_callback == NULL. + */ +struct balance_callback balance_push_callback = { + .next = NULL, + .func = balance_push, +}; + +static inline struct balance_callback * +__splice_balance_callbacks(struct rq *rq, bool split) +{ + struct balance_callback *head = rq->balance_callback; + + if (likely(!head)) + return NULL; + + lockdep_assert_rq_held(rq); + /* + * Must not take balance_push_callback off the list when + * splice_balance_callbacks() and balance_callbacks() are not + * in the same rq->lock section. + * + * In that case it would be possible for __schedule() to interleave + * and observe the list empty. + */ + if (split && head == &balance_push_callback) + head = NULL; + else + rq->balance_callback = NULL; + + return head; +} + +static inline struct balance_callback *splice_balance_callbacks(struct rq *rq) +{ + return __splice_balance_callbacks(rq, true); +} + +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) +{ + unsigned long flags; + + if (unlikely(head)) { + raw_spin_rq_lock_irqsave(rq, flags); + do_balance_callbacks(rq, head); + raw_spin_rq_unlock_irqrestore(rq, flags); + } +} + +#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) { @@ -3101,10 +4931,10 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf * do an early lockdep release here: */ rq_unpin_lock(rq, rf); - spin_release(&rq->lock.dep_map, _THIS_IP_); + spin_release(&__rq_lockp(rq)->dep_map, _THIS_IP_); #ifdef CONFIG_DEBUG_SPINLOCK /* this is a valid case when another task releases the spinlock */ - rq->lock.owner = next; + rq_lockp(rq)->owner = next; #endif } @@ -3115,8 +4945,9 @@ static inline void finish_lock_switch(struct rq *rq) * fix up the runqueue lock - which gets 'carried over' from * prev into current: */ - spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - raw_spin_unlock_irq(&rq->lock); + spin_acquire(&__rq_lockp(rq)->dep_map, 0, 0, _THIS_IP_); + __balance_callbacks(rq); + raw_spin_rq_unlock_irq(rq); } /* @@ -3131,6 +4962,22 @@ static inline void finish_lock_switch(struct rq *rq) # define finish_arch_post_lock_switch() do { } while (0) #endif +static inline void kmap_local_sched_out(void) +{ +#ifdef CONFIG_KMAP_LOCAL + if (unlikely(current->kmap_ctrl.idx)) + __kmap_local_sched_out(); +#endif +} + +static inline void kmap_local_sched_in(void) +{ +#ifdef CONFIG_KMAP_LOCAL + if (unlikely(current->kmap_ctrl.idx)) + __kmap_local_sched_in(); +#endif +} + /** * prepare_task_switch - prepare to switch tasks * @rq: the runqueue preparing to switch @@ -3153,6 +5000,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev, perf_event_task_sched_out(prev, next); rseq_preempt(prev); fire_sched_out_preempt_notifiers(prev, next); + kmap_local_sched_out(); prepare_task(next); prepare_arch_switch(next); } @@ -3181,7 +5029,7 @@ static struct rq *finish_task_switch(struct task_struct *prev) { struct rq *rq = this_rq(); struct mm_struct *mm = rq->prev_mm; - long prev_state; + unsigned int prev_state; /* * The previous task will have left us with a preempt_count of 2 @@ -3212,13 +5060,22 @@ static struct rq *finish_task_switch(struct task_struct *prev) * running on another CPU and we could rave with its RUNNING -> DEAD * transition, resulting in a double drop. */ - prev_state = prev->state; + prev_state = READ_ONCE(prev->__state); vtime_task_switch(prev); perf_event_task_sched_in(prev, current); finish_task(prev); + tick_nohz_task_switch(); finish_lock_switch(rq); finish_arch_post_lock_switch(); kcov_finish_switch(current); + /* + * kmap_local_sched_out() is invoked with rq::lock held and + * interrupts disabled. There is no requirement for that, but the + * sched out code does not have an interrupt enabled section. + * Restoring the maps on sched in does not require interrupts being + * disabled either. + */ + kmap_local_sched_in(); fire_sched_in_preempt_notifiers(current); /* @@ -3235,65 +5092,21 @@ static struct rq *finish_task_switch(struct task_struct *prev) */ if (mm) { membarrier_mm_sync_core_before_usermode(mm); - mmdrop(mm); + mmdrop_sched(mm); } if (unlikely(prev_state == TASK_DEAD)) { if (prev->sched_class->task_dead) prev->sched_class->task_dead(prev); - /* - * Remove function-return probe instances associated with this - * task and put them back on the free list. - */ - kprobe_flush_task(prev); - /* Task is done with its stack. */ put_task_stack(prev); put_task_struct_rcu_user(prev); } - tick_nohz_task_switch(); return rq; } -#ifdef CONFIG_SMP - -/* rq->lock is NOT held, but preemption is disabled */ -static void __balance_callback(struct rq *rq) -{ - struct callback_head *head, *next; - void (*func)(struct rq *rq); - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - head = rq->balance_callback; - rq->balance_callback = NULL; - while (head) { - func = (void (*)(struct rq *))head->func; - next = head->next; - head->next = NULL; - head = next; - - func(rq); - } - raw_spin_unlock_irqrestore(&rq->lock, flags); -} - -static inline void balance_callback(struct rq *rq) -{ - if (unlikely(rq->balance_callback)) - __balance_callback(rq); -} - -#else - -static inline void balance_callback(struct rq *rq) -{ -} - -#endif - /** * schedule_tail - first thing a freshly forked thread must call. * @prev: the thread we just switched away from. @@ -3301,8 +5114,6 @@ static inline void balance_callback(struct rq *rq) asmlinkage __visible void schedule_tail(struct task_struct *prev) __releases(rq->lock) { - struct rq *rq; - /* * New tasks start with FORK_PREEMPT_COUNT, see there and * finish_task_switch() for details. @@ -3312,8 +5123,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) * PREEMPT_COUNT kernels). */ - rq = finish_task_switch(prev); - balance_callback(rq); + finish_task_switch(prev); preempt_enable(); if (current->set_child_tid) @@ -3364,6 +5174,7 @@ context_switch(struct rq *rq, struct task_struct *prev, * finish_task_switch()'s mmdrop(). */ 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(). */ @@ -3389,9 +5200,9 @@ context_switch(struct rq *rq, struct task_struct *prev, * externally visible scheduler statistics: current number of runnable * threads, total number of context switches performed since bootup. */ -unsigned long nr_running(void) +unsigned int nr_running(void) { - unsigned long i, sum = 0; + unsigned int i, sum = 0; for_each_online_cpu(i) sum += cpu_rq(i)->nr_running; @@ -3436,13 +5247,13 @@ unsigned long long nr_context_switches(void) * it does become runnable. */ -unsigned long nr_iowait_cpu(int cpu) +unsigned int nr_iowait_cpu(int cpu) { return atomic_read(&cpu_rq(cpu)->nr_iowait); } /* - * IO-wait accounting, and how its mostly bollocks (on SMP). + * IO-wait accounting, and how it's mostly bollocks (on SMP). * * The idea behind IO-wait account is to account the idle time that we could * have spend running if it were not for IO. That is, if we were to improve the @@ -3471,9 +5282,9 @@ unsigned long nr_iowait_cpu(int cpu) * Task CPU affinities can make all that even more 'interesting'. */ -unsigned long nr_iowait(void) +unsigned int nr_iowait(void) { - unsigned long i, sum = 0; + unsigned int i, sum = 0; for_each_possible_cpu(i) sum += nr_iowait_cpu(i); @@ -3494,7 +5305,7 @@ void sched_exec(void) int dest_cpu; raw_spin_lock_irqsave(&p->pi_lock, flags); - dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), SD_BALANCE_EXEC, 0); + dest_cpu = p->sched_class->select_task_rq(p, task_cpu(p), WF_EXEC); if (dest_cpu == smp_processor_id()) goto unlock; @@ -3578,6 +5389,55 @@ 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); + u64 resched_latency, now = rq_clock(rq); + static bool warned_once; + + if (sysctl_resched_latency_warn_once && warned_once) + return 0; + + if (!need_resched() || !latency_warn_ms) + return 0; + + if (system_state == SYSTEM_BOOTING) + return 0; + + if (!rq->last_seen_need_resched_ns) { + rq->last_seen_need_resched_ns = now; + rq->ticks_without_resched = 0; + return 0; + } + + rq->ticks_without_resched++; + resched_latency = now - rq->last_seen_need_resched_ns; + if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC) + return 0; + + warned_once = true; + + return resched_latency; +} + +static int __init setup_resched_latency_warn_ms(char *str) +{ + long val; + + if ((kstrtol(str, 0, &val))) { + pr_warn("Unable to set resched_latency_warn_ms\n"); + return 1; + } + + sysctl_resched_latency_warn_ms = val; + 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. @@ -3588,18 +5448,28 @@ void scheduler_tick(void) struct rq *rq = cpu_rq(cpu); struct task_struct *curr = rq->curr; struct rq_flags rf; + unsigned long thermal_pressure; + u64 resched_latency; + arch_scale_freq_tick(); sched_clock_tick(); rq_lock(rq, &rf); 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); + if (sched_feat(LATENCY_WARN)) + resched_latency = cpu_resched_latency(rq); calc_global_load_tick(rq); - psi_task_tick(rq); + sched_core_tick(rq); rq_unlock(rq, &rf); + if (sched_feat(LATENCY_WARN) && resched_latency) + resched_latency_warn(cpu, resched_latency); + perf_event_task_tick(); #ifdef CONFIG_SMP @@ -3671,7 +5541,6 @@ static void sched_tick_remote(struct work_struct *work) if (cpu_is_offline(cpu)) goto out_unlock; - curr = rq->curr; update_rq_clock(rq); if (!is_idle_task(curr)) { @@ -3706,7 +5575,7 @@ static void sched_tick_start(int cpu) int os; struct tick_work *twork; - if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -3727,7 +5596,7 @@ static void sched_tick_stop(int cpu) struct tick_work *twork; int os; - if (housekeeping_cpu(cpu, HK_FLAG_TICK)) + if (housekeeping_cpu(cpu, HK_TYPE_TICK)) return; WARN_ON_ONCE(!tick_work_cpu); @@ -3858,8 +5727,7 @@ static noinline void __schedule_bug(struct task_struct *prev) if (IS_ENABLED(CONFIG_DEBUG_PREEMPT) && in_atomic_preempt_off()) { pr_err("Preemption disabled at:"); - print_ip_sym(preempt_disable_ip); - pr_cont("\n"); + print_ip_sym(KERN_ERR, preempt_disable_ip); } if (panic_on_warn) panic("scheduling while atomic\n"); @@ -3876,10 +5744,13 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt) #ifdef CONFIG_SCHED_STACK_END_CHECK if (task_stack_end_corrupted(prev)) panic("corrupted stack end detected inside scheduler\n"); + + if (task_scs_end_corrupted(prev)) + panic("corrupted shadow stack detected inside scheduler\n"); #endif #ifdef CONFIG_DEBUG_ATOMIC_SLEEP - if (!preempt && prev->state && prev->non_block_count) { + if (!preempt && READ_ONCE(prev->__state) && prev->non_block_count) { printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n", prev->comm, prev->pid, prev->non_block_count); dump_stack(); @@ -3892,17 +5763,40 @@ 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); 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) +{ +#ifdef CONFIG_SMP + 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 + * state as before we took rq->lock. + * + * 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)) + break; + } +#endif + + put_prev_task(rq, prev); +} + /* * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) +__pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { const struct sched_class *class; struct task_struct *p; @@ -3910,18 +5804,17 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) /* * 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 - * higher scheduling class, because otherwise those loose the + * higher scheduling class, because otherwise those lose the * opportunity to pull in more work from other CPUs. */ - if (likely((prev->sched_class == &idle_sched_class || - prev->sched_class == &fair_sched_class) && + if (likely(!sched_class_above(prev->sched_class, &fair_sched_class) && rq->nr_running == rq->cfs.h_nr_running)) { p = pick_next_task_fair(rq, prev, rf); if (unlikely(p == RETRY_TASK)) goto restart; - /* Assumes fair_sched_class->next == idle_sched_class */ + /* Assume the next prioritized class is idle_sched_class */ if (!p) { put_prev_task(rq, prev); p = pick_next_task_idle(rq); @@ -3931,33 +5824,524 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) } restart: -#ifdef CONFIG_SMP + put_prev_task_balance(rq, prev, rf); + + for_each_class(class) { + p = class->pick_next_task(rq); + if (p) + return p; + } + + BUG(); /* The idle class should always have a runnable task. */ +} + +#ifdef CONFIG_SCHED_CORE +static inline bool is_task_rq_idle(struct task_struct *t) +{ + return (task_rq(t)->idle == t); +} + +static inline bool cookie_equals(struct task_struct *a, unsigned long cookie) +{ + return is_task_rq_idle(a) || (a->core_cookie == cookie); +} + +static inline bool cookie_match(struct task_struct *a, struct task_struct *b) +{ + if (is_task_rq_idle(a) || is_task_rq_idle(b)) + return true; + + return a->core_cookie == b->core_cookie; +} + +static inline struct task_struct *pick_task(struct rq *rq) +{ + const struct sched_class *class; + struct task_struct *p; + + for_each_class(class) { + p = class->pick_task(rq); + if (p) + return p; + } + + BUG(); /* The idle class should always have a runnable task. */ +} + +extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi); + +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; + const struct cpumask *smt_mask; + bool fi_before = false; + bool core_clock_updated = (rq == rq->core); + unsigned long cookie; + int i, cpu, occ = 0; + struct rq *rq_i; + bool need_sync; + + if (!sched_core_enabled(rq)) + return __pick_next_task(rq, prev, rf); + + cpu = cpu_of(rq); + + /* Stopper task is switching into idle, no need core-wide selection. */ + if (cpu_is_offline(cpu)) { + /* + * Reset core_pick so that we don't enter the fastpath when + * coming online. core_pick would already be migrated to + * another cpu during offline. + */ + rq->core_pick = NULL; + return __pick_next_task(rq, prev, rf); + } + /* - * We must do the balancing pass before put_next_task(), such - * that when we release the rq->lock the task is in the same - * state as before we took rq->lock. + * If there were no {en,de}queues since we picked (IOW, the task + * pointers are all still valid), and we haven't scheduled the last + * pick yet, do so now. * - * We can terminate the balance pass as soon as we know there is - * a runnable task of @class priority or higher. + * rq->core_pick can be NULL if no selection was made for a CPU because + * it was either offline or went offline during a sibling's core-wide + * selection. In this case, do a core-wide selection. */ - for_class_range(class, prev->sched_class, &idle_sched_class) { - if (class->balance(rq, prev, rf)) + if (rq->core->core_pick_seq == rq->core->core_task_seq && + rq->core->core_pick_seq != rq->core_sched_seq && + rq->core_pick) { + 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->core_pick = NULL; + goto out; + } + + put_prev_task_balance(rq, prev, rf); + + smt_mask = cpu_smt_mask(cpu); + need_sync = !!rq->core->core_cookie; + + /* reset state */ + rq->core->core_cookie = 0UL; + if (rq->core->core_forceidle_count) { + if (!core_clock_updated) { + update_rq_clock(rq->core); + core_clock_updated = true; + } + sched_core_account_forceidle(rq); + /* reset after accounting force idle */ + rq->core->core_forceidle_start = 0; + rq->core->core_forceidle_count = 0; + rq->core->core_forceidle_occupation = 0; + need_sync = true; + fi_before = true; + } + + /* + * core->core_task_seq, core->core_pick_seq, rq->core_sched_seq + * + * @task_seq guards the task state ({en,de}queues) + * @pick_seq is the @task_seq we did a selection on + * @sched_seq is the @pick_seq we scheduled + * + * However, preemptions can cause multiple picks on the same task set. + * 'Fix' this by also increasing @task_seq for every pick. + */ + rq->core->core_task_seq++; + + /* + * Optimize for common case where this CPU has no cookies + * and there are no cookied tasks running on siblings. + */ + if (!need_sync) { + next = pick_task(rq); + if (!next->core_cookie) { + rq->core_pick = NULL; + /* + * For robustness, update the min_vruntime_fi for + * unconstrained picks as well. + */ + WARN_ON_ONCE(fi_before); + task_vruntime_update(rq, next, false); + goto out_set_next; + } + } + + /* + * For each thread: do the regular task pick and find the max prio task + * amongst them. + * + * Tie-break prio towards the current CPU + */ + for_each_cpu_wrap(i, smt_mask, cpu) { + rq_i = cpu_rq(i); + + /* + * Current cpu always has its clock updated on entrance to + * pick_next_task(). If the current cpu is not the core, + * the core may also have been updated above. + */ + if (i != cpu && (rq_i != rq->core || !core_clock_updated)) + update_rq_clock(rq_i); + + p = rq_i->core_pick = pick_task(rq_i); + if (!max || prio_less(max, p, fi_before)) + max = p; + } + + cookie = rq->core->core_cookie = max->core_cookie; + + /* + * For each thread: try and find a runnable task that matches @max or + * force idle. + */ + for_each_cpu(i, smt_mask) { + rq_i = cpu_rq(i); + p = rq_i->core_pick; + + if (!cookie_equals(p, cookie)) { + p = NULL; + if (cookie) + p = sched_core_find(rq_i, cookie); + if (!p) + p = idle_sched_class.pick_task(rq_i); + } + + rq_i->core_pick = p; + + if (p == rq_i->idle) { + if (rq_i->nr_running) { + rq->core->core_forceidle_count++; + if (!fi_before) + rq->core->core_forceidle_seq++; + } + } else { + occ++; + } + } + + if (schedstat_enabled() && rq->core->core_forceidle_count) { + rq->core->core_forceidle_start = rq_clock(rq->core); + rq->core->core_forceidle_occupation = occ; + } + + rq->core->core_pick_seq = rq->core->core_task_seq; + next = rq->core_pick; + rq->core_sched_seq = rq->core->core_pick_seq; + + /* Something should have been selected for current CPU */ + WARN_ON_ONCE(!next); + + /* + * Reschedule siblings + * + * NOTE: L1TF -- at this point we're no longer running the old task and + * sending an IPI (below) ensures the sibling will no longer be running + * their task. This ensures there is no inter-sibling overlap between + * non-matching user state. + */ + for_each_cpu(i, smt_mask) { + rq_i = cpu_rq(i); + + /* + * An online sibling might have gone offline before a task + * could be picked for it, or it might be offline but later + * happen to come online, but its too late and nothing was + * picked for it. That's Ok - it will pick tasks for itself, + * so ignore it. + */ + if (!rq_i->core_pick) + continue; + + /* + * Update for new !FI->FI transitions, or if continuing to be in !FI: + * fi_before fi update? + * 0 0 1 + * 0 1 1 + * 1 0 1 + * 1 1 0 + */ + if (!(fi_before && rq->core->core_forceidle_count)) + task_vruntime_update(rq_i, rq_i->core_pick, !!rq->core->core_forceidle_count); + + rq_i->core_pick->core_occupation = occ; + + if (i == cpu) { + rq_i->core_pick = NULL; + continue; + } + + /* Did we break L1TF mitigation requirements? */ + WARN_ON_ONCE(!cookie_match(next, rq_i->core_pick)); + + if (rq_i->curr == rq_i->core_pick) { + rq_i->core_pick = NULL; + continue; + } + + resched_curr(rq_i); + } + +out_set_next: + set_next_task(rq, next); +out: + if (rq->core->core_forceidle_count && next == rq->idle) + queue_core_balance(rq); + + return next; +} + +static bool try_steal_cookie(int this, int that) +{ + struct rq *dst = cpu_rq(this), *src = cpu_rq(that); + struct task_struct *p; + unsigned long cookie; + bool success = false; + + local_irq_disable(); + double_rq_lock(dst, src); + + cookie = dst->core->core_cookie; + if (!cookie) + goto unlock; + + if (dst->curr != dst->idle) + goto unlock; + + p = sched_core_find(src, cookie); + if (p == src->idle) + goto unlock; + + do { + if (p == src->core_pick || p == src->curr) + goto next; + + if (!is_cpu_allowed(p, this)) + goto next; + + if (p->core_occupation > dst->idle->core_occupation) + goto next; + + deactivate_task(src, p, 0); + set_task_cpu(p, this); + activate_task(dst, p, 0); + + resched_curr(dst); + + success = true; + break; + +next: + p = sched_core_next(p, cookie); + } while (p); + +unlock: + double_rq_unlock(dst, src); + local_irq_enable(); + + return success; +} + +static bool steal_cookie_task(int cpu, struct sched_domain *sd) +{ + int i; + + for_each_cpu_wrap(i, sched_domain_span(sd), cpu) { + if (i == cpu) + continue; + + if (need_resched()) break; + + if (try_steal_cookie(cpu, i)) + return true; } -#endif - put_prev_task(rq, prev); + return false; +} - for_each_class(class) { - p = class->pick_next_task(rq); - if (p) - return p; +static void sched_core_balance(struct rq *rq) +{ + struct sched_domain *sd; + int cpu = cpu_of(rq); + + preempt_disable(); + rcu_read_lock(); + raw_spin_rq_unlock_irq(rq); + for_each_domain(cpu, sd) { + if (need_resched()) + break; + + if (steal_cookie_task(cpu, sd)) + break; } + raw_spin_rq_lock_irq(rq); + rcu_read_unlock(); + preempt_enable(); +} - /* The idle class should always have a runnable task: */ - BUG(); +static DEFINE_PER_CPU(struct balance_callback, core_balance_head); + +static void queue_core_balance(struct rq *rq) +{ + if (!sched_core_enabled(rq)) + return; + + if (!rq->core->core_cookie) + return; + + if (!rq->nr_running) /* not forced idle */ + return; + + queue_balance_callback(rq, &per_cpu(core_balance_head, rq->cpu), sched_core_balance); +} + +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); + + 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; + + /* find the leader */ + for_each_cpu(t, smt_mask) { + if (t == cpu) + continue; + rq = cpu_rq(t); + if (rq->core == rq) { + core_rq = rq; + break; + } + } + + if (WARN_ON_ONCE(!core_rq)) /* whoopsie */ + goto unlock; + + /* install and validate core_rq */ + for_each_cpu(t, smt_mask) { + rq = cpu_rq(t); + + if (t == cpu) + rq->core = core_rq; + + 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); + + /* if we're the last man standing, nothing to do */ + if (cpumask_weight(smt_mask) == 1) { + WARN_ON_ONCE(rq->core != rq); + goto unlock; + } + + /* if we're not the leader, nothing to do */ + if (rq->core != rq) + goto unlock; + + /* find a new leader */ + for_each_cpu(t, smt_mask) { + if (t == cpu) + continue; + core_rq = cpu_rq(t); + break; + } + + if (WARN_ON_ONCE(!core_rq)) /* impossible */ + goto unlock; + + /* copy the shared state to the new leader */ + core_rq->core_task_seq = rq->core_task_seq; + core_rq->core_pick_seq = rq->core_pick_seq; + core_rq->core_cookie = rq->core_cookie; + core_rq->core_forceidle_count = rq->core_forceidle_count; + core_rq->core_forceidle_seq = rq->core_forceidle_seq; + core_rq->core_forceidle_occupation = rq->core_forceidle_occupation; + + /* + * Accounting edge for forced idle is handled in pick_next_task(). + * Don't need another one here, since the hotplug thread shouldn't + * have a cookie. + */ + core_rq->core_forceidle_start = 0; + + /* install new leader */ + for_each_cpu(t, smt_mask) { + rq = cpu_rq(t); + rq->core = core_rq; + } + +unlock: + sched_core_unlock(cpu, &flags); +} + +static inline void sched_core_cpu_dying(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->core != rq) + rq->core = rq; } +#else /* !CONFIG_SCHED_CORE */ + +static inline void sched_core_cpu_starting(unsigned int cpu) {} +static inline void sched_core_cpu_deactivate(unsigned int cpu) {} +static inline void sched_core_cpu_dying(unsigned int cpu) {} + +static struct task_struct * +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 */ + +/* + * 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. + */ +#define SM_NONE 0x0 +#define SM_PREEMPT 0x1 +#define SM_RTLOCK_WAIT 0x2 + +#ifndef CONFIG_PREEMPT_RT +# define SM_MASK_PREEMPT (~0U) +#else +# define SM_MASK_PREEMPT SM_PREEMPT +#endif + /* * __schedule() is the main scheduler function. * @@ -3997,10 +6381,11 @@ restart: * * WARNING: must be called with preemption disabled! */ -static void __sched notrace __schedule(bool preempt) +static void __sched notrace __schedule(unsigned int sched_mode) { struct task_struct *prev, *next; unsigned long *switch_count; + unsigned long prev_state; struct rq_flags rf; struct rq *rq; int cpu; @@ -4009,20 +6394,27 @@ static void __sched notrace __schedule(bool preempt) rq = cpu_rq(cpu); prev = rq->curr; - schedule_debug(prev, preempt); + schedule_debug(prev, !!sched_mode); - if (sched_feat(HRTICK)) + if (sched_feat(HRTICK) || sched_feat(HRTICK_DL)) hrtick_clear(rq); local_irq_disable(); - rcu_note_context_switch(preempt); + rcu_note_context_switch(!!sched_mode); /* * Make sure that signal_pending_state()->signal_pending() below * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) - * done by the caller to avoid the race with signal_wake_up(). + * done by the caller to avoid the race with signal_wake_up(): + * + * __set_current_state(@state) signal_wake_up() + * schedule() set_tsk_thread_flag(p, TIF_SIGPENDING) + * wake_up_state(p, state) + * LOCK rq->lock LOCK p->pi_state + * smp_mb__after_spinlock() smp_mb__after_spinlock() + * if (signal_pending_state()) if (p->state & @state) * - * The membarrier system call requires a full memory barrier + * Also, the membarrier system call requires a full memory barrier * after coming from user-space, before storing to rq->curr. */ rq_lock(rq, &rf); @@ -4033,10 +6425,35 @@ static void __sched notrace __schedule(bool preempt) update_rq_clock(rq); switch_count = &prev->nivcsw; - if (!preempt && prev->state) { - if (signal_pending_state(prev->state, prev)) { - prev->state = TASK_RUNNING; + + /* + * 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) { @@ -4050,6 +6467,9 @@ static void __sched notrace __schedule(bool preempt) next = pick_next_task(rq, prev, &rf); clear_tsk_need_resched(prev); clear_preempt_need_resched(); +#ifdef CONFIG_SCHED_DEBUG + rq->last_seen_need_resched_ns = 0; +#endif if (likely(prev != next)) { rq->nr_switches++; @@ -4074,16 +6494,20 @@ static void __sched notrace __schedule(bool preempt) */ ++*switch_count; - trace_sched_switch(preempt, prev, next); + migrate_disable_switch(rq, prev); + psi_sched_switch(prev, next, !task_on_rq_queued(prev)); + + trace_sched_switch(sched_mode & SM_MASK_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); - rq_unlock_irq(rq, &rf); - } - balance_callback(rq); + rq_unpin_lock(rq, &rf); + __balance_callbacks(rq); + raw_spin_rq_unlock_irq(rq); + } } void __noreturn do_task_dead(void) @@ -4094,7 +6518,7 @@ void __noreturn do_task_dead(void) /* Tell freezer to ignore us: */ current->flags |= PF_NOFREEZE; - __schedule(false); + __schedule(SM_NONE); BUG(); /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */ @@ -4104,34 +6528,35 @@ void __noreturn do_task_dead(void) static inline void sched_submit_work(struct task_struct *tsk) { - if (!tsk->state) + unsigned int task_flags; + + if (task_is_running(tsk)) return; + task_flags = tsk->flags; /* - * If a worker went to sleep, notify and ask workqueue whether - * it wants to wake up a task to maintain concurrency. - * As this function is called inside the schedule() context, - * we disable preemption to avoid it calling schedule() again - * in the possible wakeup of a kworker. + * If a worker goes to sleep, notify and ask workqueue whether it + * wants to wake up a task to maintain concurrency. */ - if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { - preempt_disable(); - if (tsk->flags & PF_WQ_WORKER) + 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); - preempt_enable_no_resched(); } - if (tsk_is_pi_blocked(tsk)) - return; + /* + * spinlock and rwlock must not flush block requests. This will + * deadlock if the callback attempts to acquire a lock which is + * already acquired. + */ + SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT); /* * If we are going to sleep and we have plugged IO queued, * make sure to submit it to avoid deadlocks. */ - if (blk_needs_flush_plug(tsk)) - blk_schedule_flush_plug(tsk); + blk_flush_plug(tsk->plug, true); } static void sched_update_worker(struct task_struct *tsk) @@ -4151,7 +6576,7 @@ asmlinkage __visible void __sched schedule(void) sched_submit_work(tsk); do { preempt_disable(); - __schedule(false); + __schedule(SM_NONE); sched_preempt_enable_no_resched(); } while (need_resched()); sched_update_worker(tsk); @@ -4177,13 +6602,13 @@ void __sched schedule_idle(void) * current task can be in any other state. Note, idle is always in the * TASK_RUNNING state. */ - WARN_ON_ONCE(current->state); + WARN_ON_ONCE(current->__state); do { - __schedule(false); + __schedule(SM_NONE); } while (need_resched()); } -#ifdef CONFIG_CONTEXT_TRACKING +#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) asmlinkage __visible void __sched schedule_user(void) { /* @@ -4214,6 +6639,18 @@ void __sched schedule_preempt_disabled(void) preempt_disable(); } +#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()); +} +NOKPROBE_SYMBOL(schedule_rtlock); +#endif + static void __sched notrace preempt_schedule_common(void) { do { @@ -4232,7 +6669,7 @@ static void __sched notrace preempt_schedule_common(void) */ preempt_disable_notrace(); preempt_latency_start(1); - __schedule(true); + __schedule(SM_PREEMPT); preempt_latency_stop(1); preempt_enable_no_resched_notrace(); @@ -4256,12 +6693,32 @@ asmlinkage __visible void __sched notrace preempt_schedule(void) */ if (likely(!preemptible())) return; - preempt_schedule_common(); } 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 +DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled); +EXPORT_STATIC_CALL_TRAMP(preempt_schedule); +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule); +void __sched notrace dynamic_preempt_schedule(void) +{ + if (!static_branch_unlikely(&sk_dynamic_preempt_schedule)) + return; + preempt_schedule(); +} +NOKPROBE_SYMBOL(dynamic_preempt_schedule); +EXPORT_SYMBOL(dynamic_preempt_schedule); +#endif +#endif + /** * preempt_schedule_notrace - preempt_schedule called by tracing * @@ -4305,7 +6762,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) * an infinite recursion. */ prev_ctx = exception_enter(); - __schedule(true); + __schedule(SM_PREEMPT); exception_exit(prev_ctx); preempt_latency_stop(1); @@ -4314,6 +6771,27 @@ 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 +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) +static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace); +void __sched notrace dynamic_preempt_schedule_notrace(void) +{ + if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace)) + return; + preempt_schedule_notrace(); +} +NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace); +EXPORT_SYMBOL(dynamic_preempt_schedule_notrace); +#endif +#endif + #endif /* CONFIG_PREEMPTION */ /* @@ -4334,7 +6812,7 @@ asmlinkage __visible void __sched preempt_schedule_irq(void) do { preempt_disable(); local_irq_enable(); - __schedule(true); + __schedule(SM_PREEMPT); local_irq_disable(); sched_preempt_enable_no_resched(); } while (need_resched()); @@ -4345,10 +6823,23 @@ 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); 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) +{ + 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; + + p->prio = prio; +} + #ifdef CONFIG_RT_MUTEXES static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) @@ -4404,7 +6895,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to * ensure a task is de-boosted (pi_task is set to NULL) before the * task is allowed to run again (and can exit). This ensures the pointer - * points to a blocked task -- which guaratees the task is present. + * points to a blocked task -- which guarantees the task is present. */ p->pi_top_task = pi_task; @@ -4457,27 +6948,26 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) */ if (dl_prio(prio)) { if (!dl_prio(p->normal_prio) || - (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) { - p->dl.dl_boosted = 1; + (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.dl_boosted = 0; - p->sched_class = &dl_sched_class; + } else { + p->dl.pi_se = &p->dl; + } } else if (rt_prio(prio)) { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; - p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) - p->dl.dl_boosted = 0; + p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; - p->sched_class = &fair_sched_class; } - p->prio = prio; + __setscheduler_prio(p, prio); if (queued) enqueue_task(rq, p, queue_flag); @@ -4488,9 +6978,11 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) out_unlock: /* Avoid rq from going away on us: */ preempt_disable(); - __task_rq_unlock(rq, &rf); - balance_callback(rq); + rq_unpin_lock(rq, &rf); + __balance_callbacks(rq); + raw_spin_rq_unlock(rq); + preempt_enable(); } #else @@ -4519,7 +7011,7 @@ void set_user_nice(struct task_struct *p, long nice) /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected - * it wont have any effect on scheduling until the task is + * 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)) { @@ -4555,17 +7047,29 @@ out_unlock: EXPORT_SYMBOL(set_user_nice); /* - * can_nice - check if a task can reduce its nice value + * 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 */ -int can_nice(const struct task_struct *p, const int nice) +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) || - capable(CAP_SYS_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 @@ -4608,8 +7112,12 @@ SYSCALL_DEFINE1(nice, int, increment) * @p: the task in question. * * Return: The priority value as seen by users in /proc. - * RT tasks are offset by -200. Normal tasks are centered - * around 0, value goes from -16 to +15. + * + * 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) { @@ -4633,7 +7141,7 @@ int idle_cpu(int cpu) return 0; #ifdef CONFIG_SMP - if (!llist_empty(&rq->wake_list)) + if (rq->ttwu_pending) return 0; #endif @@ -4668,6 +7176,121 @@ 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. @@ -4710,35 +7333,6 @@ static void __setscheduler_params(struct task_struct *p, set_load_weight(p, true); } -/* Actually do priority change: must hold pi & rq lock. */ -static void __setscheduler(struct rq *rq, struct task_struct *p, - const struct sched_attr *attr, bool keep_boost) -{ - /* - * If params can't change scheduling class changes aren't allowed - * either. - */ - if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS) - return; - - __setscheduler_params(p, attr); - - /* - * Keep a potential priority boosting if called from - * sched_setscheduler(). - */ - p->prio = normal_prio(p); - if (keep_boost) - p->prio = rt_effective_prio(p, p->prio); - - if (dl_prio(p->prio)) - p->sched_class = &dl_sched_class; - else if (rt_prio(p->prio)) - p->sched_class = &rt_sched_class; - else - p->sched_class = &fair_sched_class; -} - /* * Check the target process has a UID that matches the current process's: */ @@ -4755,15 +7349,77 @@ static bool check_same_owner(struct task_struct *p) return match; } +/* + * Allow unprivileged RT tasks to decrease priority. + * Only issue a capable test if needed and only once to avoid an audit + * event on permitted non-privileged operations: + */ +static int user_check_sched_setscheduler(struct task_struct *p, + const struct sched_attr *attr, + int policy, int reset_on_fork) +{ + if (fair_policy(policy)) { + if (attr->sched_nice < task_nice(p) && + !is_nice_reduction(p, attr->sched_nice)) + goto req_priv; + } + + if (rt_policy(policy)) { + unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); + + /* Can't set/change the rt policy: */ + if (policy != p->policy && !rlim_rtprio) + goto req_priv; + + /* Can't increase priority: */ + if (attr->sched_priority > p->rt_priority && + attr->sched_priority > rlim_rtprio) + goto req_priv; + } + + /* + * Can't set/change SCHED_DEADLINE policy at all for now + * (safest behavior); in the future we would like to allow + * unprivileged DL tasks to increase their relative deadline + * or reduce their runtime (both ways reducing utilization) + */ + if (dl_policy(policy)) + goto req_priv; + + /* + * Treat SCHED_IDLE as nice 20. Only allow a switch to + * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. + */ + if (task_has_idle_policy(p) && !idle_policy(policy)) { + if (!is_nice_reduction(p, task_nice(p))) + goto req_priv; + } + + /* Can't change other user's priorities: */ + if (!check_same_owner(p)) + goto req_priv; + + /* Normal users shall not reset the sched_reset_on_fork flag: */ + if (p->sched_reset_on_fork && !reset_on_fork) + goto req_priv; + + return 0; + +req_priv: + if (!capable(CAP_SYS_NICE)) + return -EPERM; + + return 0; +} + static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) { - int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : - MAX_RT_PRIO - 1 - attr->sched_priority; - int retval, oldprio, oldpolicy = -1, queued, running; - int new_effective_prio, policy = attr->sched_policy; + 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; @@ -4788,68 +7444,20 @@ recheck: /* * Valid priorities for SCHED_FIFO and SCHED_RR are - * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, + * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL, * SCHED_BATCH and SCHED_IDLE is 0. */ - if ((p->mm && attr->sched_priority > MAX_USER_RT_PRIO-1) || - (!p->mm && attr->sched_priority > MAX_RT_PRIO-1)) + 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; - /* - * Allow unprivileged RT tasks to decrease priority: - */ - if (user && !capable(CAP_SYS_NICE)) { - if (fair_policy(policy)) { - if (attr->sched_nice < task_nice(p) && - !can_nice(p, attr->sched_nice)) - return -EPERM; - } - - if (rt_policy(policy)) { - unsigned long rlim_rtprio = - task_rlimit(p, RLIMIT_RTPRIO); - - /* Can't set/change the rt policy: */ - if (policy != p->policy && !rlim_rtprio) - return -EPERM; - - /* Can't increase priority: */ - if (attr->sched_priority > p->rt_priority && - attr->sched_priority > rlim_rtprio) - return -EPERM; - } - - /* - * Can't set/change SCHED_DEADLINE policy at all for now - * (safest behavior); in the future we would like to allow - * unprivileged DL tasks to increase their relative deadline - * or reduce their runtime (both ways reducing utilization) - */ - if (dl_policy(policy)) - return -EPERM; - - /* - * Treat SCHED_IDLE as nice 20. Only allow a switch to - * SCHED_NORMAL if the RLIMIT_NICE would normally permit it. - */ - if (task_has_idle_policy(p) && !idle_policy(policy)) { - if (!can_nice(p, task_nice(p))) - return -EPERM; - } - - /* Can't change other user's priorities: */ - if (!check_same_owner(p)) - return -EPERM; - - /* Normal users shall not reset the sched_reset_on_fork flag: */ - if (p->sched_reset_on_fork && !reset_on_fork) - return -EPERM; - } - if (user) { + retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork); + if (retval) + return retval; + if (attr->sched_flags & SCHED_FLAG_SUGOV) return -EINVAL; @@ -4960,6 +7568,7 @@ change: 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 @@ -4968,8 +7577,8 @@ change: * the runqueue. This will be done when the task deboost * itself. */ - new_effective_prio = rt_effective_prio(p, newprio); - if (new_effective_prio == oldprio) + newprio = rt_effective_prio(p, newprio); + if (newprio == oldprio) queue_flags &= ~DEQUEUE_MOVE; } @@ -4982,7 +7591,10 @@ change: prev_class = p->sched_class; - __setscheduler(rq, p, attr, pi); + if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { + __setscheduler_params(p, attr); + __setscheduler_prio(p, newprio); + } __setscheduler_uclamp(p, attr); if (queued) { @@ -5002,6 +7614,7 @@ change: /* Avoid rq from going away on us: */ preempt_disable(); + head = splice_balance_callbacks(rq); task_rq_unlock(rq, p, &rf); if (pi) { @@ -5010,7 +7623,7 @@ change: } /* Run balance callbacks after we've adjusted the PI chain: */ - balance_callback(rq); + balance_callbacks(rq, head); preempt_enable(); return 0; @@ -5046,6 +7659,8 @@ static int _sched_setscheduler(struct task_struct *p, int policy, * @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. @@ -5055,18 +7670,17 @@ int sched_setscheduler(struct task_struct *p, int policy, { return _sched_setscheduler(p, policy, param, true); } -EXPORT_SYMBOL_GPL(sched_setscheduler); int sched_setattr(struct task_struct *p, const struct sched_attr *attr) { return __sched_setscheduler(p, attr, true, true); } -EXPORT_SYMBOL_GPL(sched_setattr); 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. @@ -5086,7 +7700,51 @@ int sched_setscheduler_nocheck(struct task_struct *p, int policy, { return _sched_setscheduler(p, policy, param, false); } -EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck); + +/* + * 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) @@ -5160,6 +7818,16 @@ err_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. @@ -5221,6 +7889,8 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, 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); } @@ -5369,14 +8039,15 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, kattr.sched_policy = p->policy; if (p->sched_reset_on_fork) kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK; - if (task_has_dl_policy(p)) - __getparam_dl(p, &kattr); - else if (task_has_rt_policy(p)) - kattr.sched_priority = p->rt_priority; - else - kattr.sched_nice = task_nice(p); + 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 @@ -5390,9 +8061,76 @@ out_unlock: return retval; } -long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +#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, const struct cpumask *mask) { + 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, mask, cpus_allowed); + + retval = dl_task_check_affinity(p, new_mask); + if (retval) + goto out_free_new_mask; +again: + retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER); + 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); + goto again; + } + +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 task_struct *p; int retval; @@ -5412,68 +8150,22 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) retval = -EINVAL; goto out_put_task; } - if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { - retval = -ENOMEM; - goto out_put_task; - } - if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { - retval = -ENOMEM; - goto out_free_cpus_allowed; - } - retval = -EPERM; + if (!check_same_owner(p)) { rcu_read_lock(); if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { rcu_read_unlock(); - goto out_free_new_mask; + retval = -EPERM; + goto out_put_task; } rcu_read_unlock(); } retval = security_task_setscheduler(p); if (retval) - goto out_free_new_mask; - - - cpuset_cpus_allowed(p, cpus_allowed); - cpumask_and(new_mask, in_mask, cpus_allowed); - - /* - * 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. - */ -#ifdef CONFIG_SMP - if (task_has_dl_policy(p) && dl_bandwidth_enabled()) { - rcu_read_lock(); - if (!cpumask_subset(task_rq(p)->rd->span, new_mask)) { - retval = -EBUSY; - rcu_read_unlock(); - goto out_free_new_mask; - } - rcu_read_unlock(); - } -#endif -again: - retval = __set_cpus_allowed_ptr(p, new_mask, true); + goto out_put_task; - if (!retval) { - 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 cpus_allowed to the - * cpuset's cpus_allowed - */ - cpumask_copy(new_mask, cpus_allowed); - goto again; - } - } -out_free_new_mask: - free_cpumask_var(new_mask); -out_free_cpus_allowed: - free_cpumask_var(cpus_allowed); + retval = __sched_setaffinity(p, in_mask); out_put_task: put_task_struct(p); return retval; @@ -5578,14 +8270,6 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, return ret; } -/** - * 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. - */ static void do_sched_yield(void) { struct rq_flags rf; @@ -5596,34 +8280,83 @@ static void do_sched_yield(void) schedstat_inc(rq->yld_count); current->sched_class->yield_task(rq); - /* - * Since we are going to call schedule() anyway, there's - * no need to preempt or enable interrupts: - */ preempt_disable(); - rq_unlock(rq, &rf); + 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; } -#ifndef CONFIG_PREEMPTION -int __sched _cond_resched(void) +#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC) +int __sched __cond_resched(void) { if (should_resched(0)) { preempt_schedule_common(); return 1; } + /* + * In preemptible 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, + * RCU readers leave no in-memory hints, which means that CPU-bound + * processes executing in kernel context might never report an + * 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. + */ +#ifndef CONFIG_PREEMPT_RCU rcu_all_qs(); +#endif return 0; } -EXPORT_SYMBOL(_cond_resched); +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) +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_STATIC_CALL_RET0(might_resched, __cond_resched); +EXPORT_STATIC_CALL_TRAMP(might_resched); +#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY) +static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched); +int __sched dynamic_cond_resched(void) +{ + if (!static_branch_unlikely(&sk_dynamic_cond_resched)) + return 0; + return __cond_resched(); +} +EXPORT_SYMBOL(dynamic_cond_resched); + +static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched); +int __sched dynamic_might_resched(void) +{ + if (!static_branch_unlikely(&sk_dynamic_might_resched)) + return 0; + return __cond_resched(); +} +EXPORT_SYMBOL(dynamic_might_resched); +#endif #endif /* @@ -5643,9 +8376,7 @@ int __cond_resched_lock(spinlock_t *lock) if (spin_needbreak(lock) || resched) { spin_unlock(lock); - if (resched) - preempt_schedule_common(); - else + if (!_cond_resched()) cpu_relax(); ret = 1; spin_lock(lock); @@ -5654,6 +8385,202 @@ int __cond_resched_lock(spinlock_t *lock) } EXPORT_SYMBOL(__cond_resched_lock); +int __cond_resched_rwlock_read(rwlock_t *lock) +{ + int resched = should_resched(PREEMPT_LOCK_OFFSET); + int ret = 0; + + lockdep_assert_held_read(lock); + + if (rwlock_needbreak(lock) || resched) { + read_unlock(lock); + if (!_cond_resched()) + cpu_relax(); + ret = 1; + read_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(__cond_resched_rwlock_read); + +int __cond_resched_rwlock_write(rwlock_t *lock) +{ + int resched = should_resched(PREEMPT_LOCK_OFFSET); + int ret = 0; + + lockdep_assert_held_write(lock); + + if (rwlock_needbreak(lock) || resched) { + write_unlock(lock); + if (!_cond_resched()) + cpu_relax(); + ret = 1; + write_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(__cond_resched_rwlock_write); + +#ifdef CONFIG_PREEMPT_DYNAMIC + +#ifdef CONFIG_GENERIC_ENTRY +#include <linux/entry-common.h> +#endif + +/* + * SC:cond_resched + * SC:might_resched + * SC:preempt_schedule + * SC:preempt_schedule_notrace + * SC:irqentry_exit_cond_resched + * + * + * NONE: + * cond_resched <- __cond_resched + * might_resched <- RET0 + * preempt_schedule <- NOP + * preempt_schedule_notrace <- NOP + * irqentry_exit_cond_resched <- NOP + * + * VOLUNTARY: + * cond_resched <- __cond_resched + * might_resched <- __cond_resched + * preempt_schedule <- NOP + * preempt_schedule_notrace <- NOP + * irqentry_exit_cond_resched <- NOP + * + * FULL: + * cond_resched <- RET0 + * might_resched <- RET0 + * preempt_schedule <- preempt_schedule + * preempt_schedule_notrace <- preempt_schedule_notrace + * irqentry_exit_cond_resched <- irqentry_exit_cond_resched + */ + +enum { + preempt_dynamic_undefined = -1, + preempt_dynamic_none, + preempt_dynamic_voluntary, + preempt_dynamic_full, +}; + +int preempt_dynamic_mode = preempt_dynamic_undefined; + +int sched_dynamic_mode(const char *str) +{ + if (!strcmp(str, "none")) + return preempt_dynamic_none; + + if (!strcmp(str, "voluntary")) + return preempt_dynamic_voluntary; + + if (!strcmp(str, "full")) + return preempt_dynamic_full; + + 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 + +void sched_dynamic_update(int mode) +{ + /* + * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in + * the ZERO state, which is invalid. + */ + preempt_dynamic_enable(cond_resched); + preempt_dynamic_enable(might_resched); + preempt_dynamic_enable(preempt_schedule); + preempt_dynamic_enable(preempt_schedule_notrace); + preempt_dynamic_enable(irqentry_exit_cond_resched); + + switch (mode) { + case preempt_dynamic_none: + preempt_dynamic_enable(cond_resched); + preempt_dynamic_disable(might_resched); + preempt_dynamic_disable(preempt_schedule); + preempt_dynamic_disable(preempt_schedule_notrace); + preempt_dynamic_disable(irqentry_exit_cond_resched); + pr_info("Dynamic Preempt: none\n"); + break; + + case preempt_dynamic_voluntary: + preempt_dynamic_enable(cond_resched); + preempt_dynamic_enable(might_resched); + preempt_dynamic_disable(preempt_schedule); + preempt_dynamic_disable(preempt_schedule_notrace); + preempt_dynamic_disable(irqentry_exit_cond_resched); + pr_info("Dynamic Preempt: voluntary\n"); + break; + + case preempt_dynamic_full: + 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); + pr_info("Dynamic Preempt: full\n"); + break; + } + + preempt_dynamic_mode = mode; +} + +static int __init setup_preempt_mode(char *str) +{ + int mode = sched_dynamic_mode(str); + if (mode < 0) { + pr_warn("Dynamic Preempt: unsupported mode: %s\n", str); + return 0; + } + + sched_dynamic_update(mode); + return 1; +} +__setup("preempt=", setup_preempt_mode); + +static void __init preempt_dynamic_init(void) +{ + if (preempt_dynamic_mode == preempt_dynamic_undefined) { + if (IS_ENABLED(CONFIG_PREEMPT_NONE)) { + sched_dynamic_update(preempt_dynamic_none); + } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) { + sched_dynamic_update(preempt_dynamic_voluntary); + } else { + /* Default static call setting, nothing to do */ + WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT)); + preempt_dynamic_mode = preempt_dynamic_full; + pr_info("Dynamic Preempt: full\n"); + } + } +} + +#define PREEMPT_MODEL_ACCESSOR(mode) \ + bool preempt_model_##mode(void) \ + { \ + WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \ + return preempt_dynamic_mode == preempt_dynamic_##mode; \ + } \ + EXPORT_SYMBOL_GPL(preempt_model_##mode) + +PREEMPT_MODEL_ACCESSOR(none); +PREEMPT_MODEL_ACCESSOR(voluntary); +PREEMPT_MODEL_ACCESSOR(full); + +#else /* !CONFIG_PREEMPT_DYNAMIC */ + +static inline void preempt_dynamic_init(void) { } + +#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */ + /** * yield - yield the current processor to other threads. * @@ -5661,7 +8588,7 @@ EXPORT_SYMBOL(__cond_resched_lock); * * 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, its already broken. + * it, it's already broken. * * Typical broken usage is: * @@ -5731,10 +8658,10 @@ again: if (curr->sched_class != p->sched_class) goto out_unlock; - if (task_running(p_rq, p) || p->state) + if (task_on_cpu(p_rq, p) || !task_is_running(p)) goto out_unlock; - yielded = curr->sched_class->yield_to_task(rq, p, preempt); + yielded = curr->sched_class->yield_to_task(rq, p); if (yielded) { schedstat_inc(rq->yld_count); /* @@ -5762,8 +8689,7 @@ int io_schedule_prepare(void) int old_iowait = current->in_iowait; current->in_iowait = 1; - blk_schedule_flush_plug(current); - + blk_flush_plug(current->plug, true); return old_iowait; } @@ -5814,7 +8740,7 @@ SYSCALL_DEFINE1(sched_get_priority_max, int, policy) switch (policy) { case SCHED_FIFO: case SCHED_RR: - ret = MAX_USER_RT_PRIO-1; + ret = MAX_RT_PRIO-1; break; case SCHED_DEADLINE: case SCHED_NORMAL: @@ -5932,10 +8858,10 @@ void sched_show_task(struct task_struct *p) if (!try_get_task_stack(p)) return; - printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p)); + pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p)); - if (p->state == TASK_RUNNING) - printk(KERN_CONT " running task "); + if (task_is_running(p)) + pr_cont(" running task "); #ifdef CONFIG_DEBUG_STACK_USAGE free = stack_not_used(p); #endif @@ -5944,12 +8870,13 @@ void sched_show_task(struct task_struct *p) if (pid_alive(p)) ppid = task_pid_nr(rcu_dereference(p->real_parent)); rcu_read_unlock(); - printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, - task_pid_nr(p), ppid, - (unsigned long)task_thread_info(p)->flags); + pr_cont(" stack:%-5lu pid:%-5d ppid:%-6d flags:0x%08lx\n", + free, task_pid_nr(p), ppid, + read_task_thread_flags(p)); print_worker_info(KERN_INFO, p); - show_stack(p, NULL); + print_stop_info(KERN_INFO, p); + show_stack(p, NULL, KERN_INFO); put_task_stack(p); } EXPORT_SYMBOL_GPL(sched_show_task); @@ -5957,36 +8884,31 @@ EXPORT_SYMBOL_GPL(sched_show_task); static inline bool state_filter_match(unsigned long state_filter, struct task_struct *p) { + unsigned int state = READ_ONCE(p->__state); + /* no filter, everything matches */ if (!state_filter) return true; /* filter, but doesn't match */ - if (!(p->state & state_filter)) + if (!(state & state_filter)) return false; /* * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows * TASK_KILLABLE). */ - if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD)) return false; return true; } -void show_state_filter(unsigned long state_filter) +void show_state_filter(unsigned int state_filter) { struct task_struct *g, *p; -#if BITS_PER_LONG == 32 - printk(KERN_INFO - " task PC stack pid father\n"); -#else - printk(KERN_INFO - " task PC stack pid father\n"); -#endif rcu_read_lock(); for_each_process_thread(g, p) { /* @@ -6022,7 +8944,7 @@ void show_state_filter(unsigned long state_filter) * NOTE: this function does not set the idle thread's NEED_RESCHED * flag, to make booting more robust. */ -void init_idle(struct task_struct *idle, int cpu) +void __init init_idle(struct task_struct *idle, int cpu) { struct rq *rq = cpu_rq(cpu); unsigned long flags; @@ -6030,22 +8952,25 @@ void init_idle(struct task_struct *idle, int cpu) __sched_fork(0, idle); raw_spin_lock_irqsave(&idle->pi_lock, flags); - raw_spin_lock(&rq->lock); + raw_spin_rq_lock(rq); - idle->state = TASK_RUNNING; + idle->__state = TASK_RUNNING; idle->se.exec_start = sched_clock(); - idle->flags |= PF_IDLE; - - kasan_unpoison_task_stack(idle); + /* + * 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; + kthread_set_per_cpu(idle, cpu); #ifdef CONFIG_SMP /* - * Its possible that init_idle() gets called multiple times on a task, + * 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. */ - set_cpus_allowed_common(idle, cpumask_of(cpu)); + set_cpus_allowed_common(idle, cpumask_of(cpu), 0); #endif /* * We're having a chicken and egg problem, even though we are @@ -6067,7 +8992,7 @@ void init_idle(struct task_struct *idle, int cpu) #ifdef CONFIG_SMP idle->on_cpu = 1; #endif - raw_spin_unlock(&rq->lock); + raw_spin_rq_unlock(rq); raw_spin_unlock_irqrestore(&idle->pi_lock, flags); /* Set the preempt count _outside_ the spinlocks! */ @@ -6091,7 +9016,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, { int ret = 1; - if (!cpumask_weight(cur)) + if (cpumask_empty(cur)) return ret; ret = dl_cpuset_cpumask_can_shrink(cur, trial); @@ -6100,7 +9025,7 @@ int cpuset_cpumask_can_shrink(const struct cpumask *cur, } int task_can_attach(struct task_struct *p, - const struct cpumask *cs_cpus_allowed) + const struct cpumask *cs_effective_cpus) { int ret = 0; @@ -6119,8 +9044,13 @@ int task_can_attach(struct task_struct *p, } if (dl_task(p) && !cpumask_intersects(task_rq(p)->rd->span, - cs_cpus_allowed)) - ret = dl_task_can_attach(p, cs_cpus_allowed); + 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; @@ -6186,128 +9116,154 @@ void idle_task_exit(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); - current->active_mm = &init_mm; finish_arch_post_lock_switch(); } - mmdrop(mm); -} -/* - * Since this CPU is going 'away' for a while, fold any nr_active delta - * we might have. Assumes we're called after migrate_tasks() so that the - * nr_active count is stable. We need to take the teardown 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". - */ -static void calc_load_migrate(struct rq *rq) -{ - long delta = calc_load_fold_active(rq, 1); - if (delta) - atomic_long_add(delta, &calc_load_tasks); + /* finish_cpu(), as ran on the BP, will clean up the active_mm state */ } -static struct task_struct *__pick_migrate_task(struct rq *rq) +static int __balance_push_cpu_stop(void *arg) { - const struct sched_class *class; - struct task_struct *next; + struct task_struct *p = arg; + struct rq *rq = this_rq(); + struct rq_flags rf; + int cpu; - for_each_class(class) { - next = class->pick_next_task(rq); - if (next) { - next->sched_class->put_prev_task(rq, next); - return next; - } + 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)) { + cpu = select_fallback_rq(rq->cpu, p); + rq = __migrate_task(rq, &rf, p, cpu); } - /* The idle class should always have a runnable task */ - BUG(); + rq_unlock(rq, &rf); + raw_spin_unlock_irq(&p->pi_lock); + + put_task_struct(p); + + return 0; } +static DEFINE_PER_CPU(struct cpu_stop_work, push_work); + /* - * Migrate all tasks from the rq, sleeping tasks will be migrated by - * try_to_wake_up()->select_task_rq(). + * Ensure we only run per-cpu kthreads once the CPU goes !active. * - * Called with rq->lock held even though we'er in stop_machine() and - * there's no concurrency possible, we hold the required locks anyway - * because of lock validation efforts. + * This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only + * effective when the hotplug motion is down. */ -static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) +static void balance_push(struct rq *rq) { - struct rq *rq = dead_rq; - struct task_struct *next, *stop = rq->stop; - struct rq_flags orf = *rf; - int dest_cpu; + struct task_struct *push_task = rq->curr; + + lockdep_assert_rq_held(rq); /* - * Fudge the rq selection such that the below task selection loop - * doesn't get stuck on the currently eligible stop task. - * - * We're currently inside stop_machine() and the rq is either stuck - * in the stop_machine_cpu_stop() loop, or we're executing this code, - * either way we should never end up calling schedule() until we're - * done here. + * Ensure the thing is persistent until balance_push_set(.on = false); */ - rq->stop = NULL; + rq->balance_callback = &balance_push_callback; /* - * put_prev_task() and pick_next_task() sched - * class method both need to have an up-to-date - * value of rq->clock[_task] + * Only active while going offline and when invoked on the outgoing + * CPU. */ - update_rq_clock(rq); - - for (;;) { - /* - * There's this thread running, bail when that's the only - * remaining thread: - */ - if (rq->nr_running == 1) - break; + if (!cpu_dying(rq->cpu) || rq != this_rq()) + return; - next = __pick_migrate_task(rq); + /* + * Both the cpu-hotplug and stop task are in this case and are + * required to complete the hotplug process. + */ + if (kthread_is_per_cpu(push_task) || + is_migration_disabled(push_task)) { /* - * Rules for changing task_struct::cpus_mask are holding - * both pi_lock and rq->lock, such that holding either - * stabilizes the mask. + * If this is the idle task on the outgoing CPU try to wake + * up the hotplug control thread which might wait for the + * last task to vanish. The rcuwait_active() check is + * accurate here because the waiter is pinned on this CPU + * and can't obviously be running in parallel. * - * Drop rq->lock is not quite as disastrous as it usually is - * because !cpu_active at this point, which means load-balance - * will not interfere. Also, stop-machine. + * On RT kernels this also has to check whether there are + * pinned and scheduled out tasks on the runqueue. They + * need to leave the migrate disabled section first. */ - rq_unlock(rq, rf); - raw_spin_lock(&next->pi_lock); - rq_relock(rq, rf); - - /* - * Since we're inside stop-machine, _nothing_ should have - * changed the task, WARN if weird stuff happened, because in - * that case the above rq->lock drop is a fail too. - */ - if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) { - raw_spin_unlock(&next->pi_lock); - continue; + if (!rq->nr_running && !rq_has_pinned_tasks(rq) && + rcuwait_active(&rq->hotplug_wait)) { + raw_spin_rq_unlock(rq); + rcuwait_wake_up(&rq->hotplug_wait); + raw_spin_rq_lock(rq); } + return; + } - /* Find suitable destination for @next, with force if needed. */ - dest_cpu = select_fallback_rq(dead_rq->cpu, next); - rq = __migrate_task(rq, rf, next, dest_cpu); - if (rq != dead_rq) { - rq_unlock(rq, rf); - rq = dead_rq; - *rf = orf; - rq_relock(rq, rf); - } - raw_spin_unlock(&next->pi_lock); + get_task_struct(push_task); + /* + * Temporarily drop rq->lock such that we can wake-up the stop task. + * Both preemption and IRQs are still disabled. + */ + raw_spin_rq_unlock(rq); + stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task, + this_cpu_ptr(&push_work)); + /* + * 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 + * which kthread_is_per_cpu() and will push this task away. + */ + raw_spin_rq_lock(rq); +} + +static void balance_push_set(int cpu, bool on) +{ + struct rq *rq = cpu_rq(cpu); + struct rq_flags rf; + + rq_lock_irqsave(rq, &rf); + if (on) { + WARN_ON_ONCE(rq->balance_callback); + rq->balance_callback = &balance_push_callback; + } else if (rq->balance_callback == &balance_push_callback) { + rq->balance_callback = NULL; } + rq_unlock_irqrestore(rq, &rf); +} + +/* + * Invoked from a CPUs hotplug control thread after the CPU has been marked + * inactive. All tasks which are not per CPU kernel threads are either + * pushed off this CPU now via balance_push() or placed on a different CPU + * during wakeup. Wait until the CPU is quiescent. + */ +static void balance_hotplug_wait(void) +{ + struct rq *rq = this_rq(); - rq->stop = stop; + rcuwait_wait_event(&rq->hotplug_wait, + rq->nr_running == 1 && !rq_has_pinned_tasks(rq), + TASK_UNINTERRUPTIBLE); } + +#else + +static inline void balance_push(struct rq *rq) +{ +} + +static inline void balance_push_set(int cpu, bool on) +{ +} + +static inline void balance_hotplug_wait(void) +{ +} + #endif /* CONFIG_HOTPLUG_CPU */ void set_rq_online(struct rq *rq) @@ -6378,8 +9334,10 @@ static void cpuset_cpu_active(void) static int cpuset_cpu_inactive(unsigned int cpu) { if (!cpuhp_tasks_frozen) { - if (dl_cpu_busy(cpu)) - return -EBUSY; + int ret = dl_cpu_busy(cpu, NULL); + + if (ret) + return ret; cpuset_update_active_cpus(); } else { num_cpus_frozen++; @@ -6393,6 +9351,12 @@ 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 + * regular tasks. + */ + balance_push_set(cpu, false); + #ifdef CONFIG_SCHED_SMT /* * When going up, increment the number of cores with SMT present. @@ -6403,6 +9367,7 @@ int sched_cpu_activate(unsigned int cpu) set_cpu_active(cpu, true); if (sched_smp_initialized) { + sched_update_numa(cpu, true); sched_domains_numa_masks_set(cpu); cpuset_cpu_active(); } @@ -6428,32 +9393,65 @@ 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; + /* + * Remove CPU from nohz.idle_cpus_mask to prevent participating in + * load balancing when not active + */ + nohz_balance_exit_idle(rq); + set_cpu_active(cpu, false); + /* - * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU - * users of this state to go away such that all new such users will - * observe it. + * From this point forward, this CPU will refuse to run any task that + * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively + * push those tasks away until this gets cleared, see + * sched_cpu_dying(). + */ + balance_push_set(cpu, true); + + /* + * We've cleared cpu_active_mask / set balance_push, wait for all + * preempt-disabled and RCU users of this state to go away such that + * all new such users will observe it. + * + * 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. */ 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); + #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_core_cpu_deactivate(cpu); #endif if (!sched_smp_initialized) 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; } sched_domains_numa_masks_clear(cpu); @@ -6470,41 +9468,93 @@ static void sched_rq_cpu_starting(unsigned int cpu) int sched_cpu_starting(unsigned int cpu) { + sched_core_cpu_starting(cpu); sched_rq_cpu_starting(cpu); sched_tick_start(cpu); return 0; } #ifdef CONFIG_HOTPLUG_CPU + +/* + * Invoked immediately before the stopper thread is invoked to bring the + * CPU down completely. At this point all per CPU kthreads except the + * hotplug thread (current) and the stopper thread (inactive) have been + * either parked or have been unbound from the outgoing CPU. Ensure that + * any of those which might be on the way out are gone. + * + * If after this point a bound task is being woken on this CPU then the + * responsible hotplug callback has failed to do it's job. + * sched_cpu_dying() will catch it with the appropriate fireworks. + */ +int sched_cpu_wait_empty(unsigned int cpu) +{ + balance_hotplug_wait(); + return 0; +} + +/* + * 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 + * account, so we hand in adjust = 1 to the load calculation. + * + * Also see the comment "Global load-average calculations". + */ +static void calc_load_migrate(struct rq *rq) +{ + long delta = calc_load_fold_active(rq, 1); + + if (delta) + atomic_long_add(delta, &calc_load_tasks); +} + +static void dump_rq_tasks(struct rq *rq, const char *loglvl) +{ + struct task_struct *g, *p; + int cpu = cpu_of(rq); + + lockdep_assert_rq_held(rq); + + printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running); + for_each_process_thread(g, p) { + if (task_cpu(p) != cpu) + continue; + + if (!task_on_rq_queued(p)) + continue; + + printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm); + } +} + int sched_cpu_dying(unsigned int cpu) { struct rq *rq = cpu_rq(cpu); struct rq_flags rf; /* Handle pending wakeups and then migrate everything off */ - sched_ttwu_pending(); sched_tick_stop(cpu); rq_lock_irqsave(rq, &rf); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - set_rq_offline(rq); + if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) { + WARN(true, "Dying CPU not properly vacated!"); + dump_rq_tasks(rq, KERN_WARNING); } - migrate_tasks(rq, &rf); - BUG_ON(rq->nr_running != 1); rq_unlock_irqrestore(rq, &rf); calc_load_migrate(rq); update_max_interval(); - nohz_balance_exit_idle(rq); hrtick_clear(rq); + sched_core_cpu_dying(cpu); return 0; } #endif void __init sched_init_smp(void) { - sched_init_numa(); + sched_init_numa(NUMA_NO_NODE); /* * There's no userspace yet to cause hotplug operations; hence all the @@ -6516,8 +9566,9 @@ void __init sched_init_smp(void) mutex_unlock(&sched_domains_mutex); /* Move init over to a non-isolated CPU */ - if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) + if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0) BUG(); + current->flags &= ~PF_NO_SETAFFINITY; sched_init_granularity(); init_sched_rt_class(); @@ -6559,14 +9610,19 @@ LIST_HEAD(task_groups); static struct kmem_cache *task_group_cache __read_mostly; #endif -DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); -DECLARE_PER_CPU(cpumask_var_t, select_idle_mask); - void __init sched_init(void) { unsigned long ptr = 0; 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); +#endif + wait_bit_init(); #ifdef CONFIG_FAIR_GROUP_SCHED @@ -6585,6 +9641,8 @@ void __init sched_init(void) root_task_group.cfs_rq = (struct cfs_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); + root_task_group.shares = ROOT_TASK_GROUP_LOAD; + init_cfs_bandwidth(&root_task_group.cfs_bandwidth); #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED root_task_group.rt_se = (struct sched_rt_entity **)ptr; @@ -6595,17 +9653,8 @@ void __init sched_init(void) #endif /* CONFIG_RT_GROUP_SCHED */ } -#ifdef CONFIG_CPUMASK_OFFSTACK - for_each_possible_cpu(i) { - per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node( - cpumask_size(), GFP_KERNEL, cpu_to_node(i)); - per_cpu(select_idle_mask, i) = (cpumask_var_t)kzalloc_node( - cpumask_size(), GFP_KERNEL, cpu_to_node(i)); - } -#endif /* CONFIG_CPUMASK_OFFSTACK */ init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime()); - init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime()); #ifdef CONFIG_SMP init_defrootdomain(); @@ -6629,7 +9678,7 @@ void __init sched_init(void) struct rq *rq; rq = cpu_rq(i); - raw_spin_lock_init(&rq->lock); + raw_spin_lock_init(&rq->__lock); rq->nr_running = 0; rq->calc_load_active = 0; rq->calc_load_update = jiffies + LOAD_FREQ; @@ -6637,7 +9686,6 @@ void __init sched_init(void) init_rt_rq(&rq->rt); init_dl_rq(&rq->dl); #ifdef CONFIG_FAIR_GROUP_SCHED - root_task_group.shares = ROOT_TASK_GROUP_LOAD; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; /* @@ -6659,7 +9707,6 @@ void __init sched_init(void) * We achieve this by letting root_task_group's tasks sit * directly in rq->cfs (i.e root_task_group->se[] = NULL). */ - init_cfs_bandwidth(&root_task_group.cfs_bandwidth); init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -6671,7 +9718,7 @@ void __init sched_init(void) rq->sd = NULL; rq->rd = NULL; rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE; - rq->balance_callback = NULL; + rq->balance_callback = &balance_push_callback; rq->active_balance = 0; rq->next_balance = jiffies; rq->push_cpu = 0; @@ -6679,19 +9726,37 @@ 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); rq_attach_root(rq, &def_root_domain); #ifdef CONFIG_NO_HZ_COMMON - rq->last_load_update_tick = jiffies; rq->last_blocked_load_update_tick = jiffies; atomic_set(&rq->nohz_flags, 0); + + INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq); +#endif +#ifdef CONFIG_HOTPLUG_CPU + rcuwait_init(&rq->hotplug_wait); #endif #endif /* CONFIG_SMP */ hrtick_rq_init(rq); atomic_set(&rq->nr_iowait, 0); + +#ifdef CONFIG_SCHED_CORE + rq->core = rq; + rq->core_pick = NULL; + rq->core_enabled = 0; + rq->core_tree = RB_ROOT; + rq->core_forceidle_count = 0; + rq->core_forceidle_occupation = 0; + rq->core_forceidle_start = 0; + + rq->core_cookie = 0UL; +#endif } set_load_weight(&init_task, false); @@ -6703,6 +9768,14 @@ void __init sched_init(void) enter_lazy_tlb(&init_mm, current); /* + * The idle task doesn't need the kthread struct to function, but it + * is dressed up as a per-CPU kthread and thus needs to play the part + * if we want to avoid special-casing it in code that deals with per-CPU + * kthreads. + */ + WARN_ON(!set_kthread_struct(current)); + + /* * Make us the idle thread. Technically, schedule() should not be * called from this thread, however somewhere below it might be, * but because we are the idle thread, we just pick up running again @@ -6714,45 +9787,61 @@ void __init sched_init(void) #ifdef CONFIG_SMP idle_thread_set_boot_cpu(); + balance_push_set(smp_processor_id(), false); #endif init_sched_fair_class(); - init_schedstats(); - psi_init(); init_uclamp(); + preempt_dynamic_init(); + scheduler_running = 1; } #ifdef CONFIG_DEBUG_ATOMIC_SLEEP -static inline int preempt_count_equals(int preempt_offset) -{ - int nested = preempt_count() + rcu_preempt_depth(); - - return (nested == preempt_offset); -} -void __might_sleep(const char *file, int line, int preempt_offset) +void __might_sleep(const char *file, int line) { + unsigned int state = get_current_state(); /* * Blocking primitives will set (and therefore destroy) current->state, * since we will exit with TASK_RUNNING make sure we enter with it, * otherwise we will destroy state. */ - WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change, + WARN_ONCE(state != TASK_RUNNING && current->task_state_change, "do not call blocking ops when !TASK_RUNNING; " - "state=%lx set at [<%p>] %pS\n", - current->state, + "state=%x set at [<%p>] %pS\n", state, (void *)current->task_state_change, (void *)current->task_state_change); - ___might_sleep(file, line, preempt_offset); + __might_resched(file, line, 0); } EXPORT_SYMBOL(__might_sleep); -void ___might_sleep(const char *file, int line, int preempt_offset) +static void print_preempt_disable_ip(int preempt_offset, unsigned long ip) +{ + if (!IS_ENABLED(CONFIG_DEBUG_PREEMPT)) + return; + + if (preempt_count() == preempt_offset) + return; + + pr_err("Preemption disabled at:"); + print_ip_sym(KERN_ERR, ip); +} + +static inline bool resched_offsets_ok(unsigned int offsets) +{ + unsigned int nested = preempt_count(); + + nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT; + + return nested == offsets; +} + +void __might_resched(const char *file, int line, unsigned int offsets) { /* Ratelimiting timestamp: */ static unsigned long prev_jiffy; @@ -6762,7 +9851,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset) /* WARN_ON_ONCE() by default, no rate limit required: */ rcu_sleep_check(); - if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + if ((resched_offsets_ok(offsets) && !irqs_disabled() && !is_idle_task(current) && !current->non_block_count) || system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING || oops_in_progress) @@ -6775,30 +9864,33 @@ void ___might_sleep(const char *file, int line, int preempt_offset) /* Save this before calling printk(), since that will clobber it: */ preempt_disable_ip = get_preempt_disable_ip(current); - printk(KERN_ERR - "BUG: sleeping function called from invalid context at %s:%d\n", - file, line); - printk(KERN_ERR - "in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n", - in_atomic(), irqs_disabled(), current->non_block_count, - current->pid, current->comm); + pr_err("BUG: sleeping function called from invalid context at %s:%d\n", + file, line); + pr_err("in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), current->non_block_count, + current->pid, current->comm); + pr_err("preempt_count: %x, expected: %x\n", preempt_count(), + offsets & MIGHT_RESCHED_PREEMPT_MASK); + + if (IS_ENABLED(CONFIG_PREEMPT_RCU)) { + pr_err("RCU nest depth: %d, expected: %u\n", + rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT); + } if (task_stack_end_corrupted(current)) - printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); + pr_emerg("Thread overran stack, or stack corrupted\n"); debug_show_held_locks(current); if (irqs_disabled()) print_irqtrace_events(current); - if (IS_ENABLED(CONFIG_DEBUG_PREEMPT) - && !preempt_count_equals(preempt_offset)) { - pr_err("Preemption disabled at:"); - print_ip_sym(preempt_disable_ip); - pr_cont("\n"); - } + + print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK, + preempt_disable_ip); + dump_stack(); add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } -EXPORT_SYMBOL(___might_sleep); +EXPORT_SYMBOL(__might_resched); void __cant_sleep(const char *file, int line, int preempt_offset) { @@ -6827,6 +9919,39 @@ void __cant_sleep(const char *file, int line, int preempt_offset) add_taint(TAINT_WARN, LOCKDEP_STILL_OK); } EXPORT_SYMBOL_GPL(__cant_sleep); + +#ifdef CONFIG_SMP +void __cant_migrate(const char *file, int line) +{ + static unsigned long prev_jiffy; + + if (irqs_disabled()) + return; + + if (is_migration_disabled(current)) + return; + + if (!IS_ENABLED(CONFIG_PREEMPT_COUNT)) + return; + + if (preempt_count() > 0) + return; + + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + + pr_err("BUG: assuming non migratable context at %s:%d\n", file, line); + pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), is_migration_disabled(current), + current->pid, current->comm); + + debug_show_held_locks(current); + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} +EXPORT_SYMBOL_GPL(__cant_migrate); +#endif #endif #ifdef CONFIG_MAGIC_SYSRQ @@ -6846,9 +9971,9 @@ void normalize_rt_tasks(void) continue; p->se.exec_start = 0; - schedstat_set(p->se.statistics.wait_start, 0); - schedstat_set(p->se.statistics.sleep_start, 0); - schedstat_set(p->se.statistics.block_start, 0); + schedstat_set(p->stats.wait_start, 0); + schedstat_set(p->stats.sleep_start, 0); + schedstat_set(p->stats.block_start, 0); if (!dl_task(p) && !rt_task(p)) { /* @@ -6942,6 +10067,22 @@ static void sched_free_group(struct task_group *tg) kmem_cache_free(task_group_cache, tg); } +static void sched_free_group_rcu(struct rcu_head *rcu) +{ + sched_free_group(container_of(rcu, struct task_group, rcu)); +} + +static void sched_unregister_group(struct task_group *tg) +{ + unregister_fair_sched_group(tg); + unregister_rt_sched_group(tg); + /* + * We have to wait for yet another RCU grace period to expire, as + * print_cfs_stats() might run concurrently. + */ + call_rcu(&tg->rcu, sched_free_group_rcu); +} + /* allocate runqueue etc for a new task group */ struct task_group *sched_create_group(struct task_group *parent) { @@ -6985,32 +10126,42 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) } /* rcu callback to free various structures associated with a task group */ -static void sched_free_group_rcu(struct rcu_head *rhp) +static void sched_unregister_group_rcu(struct rcu_head *rhp) { /* Now it should be safe to free those cfs_rqs: */ - sched_free_group(container_of(rhp, struct task_group, rcu)); + sched_unregister_group(container_of(rhp, struct task_group, rcu)); } void sched_destroy_group(struct task_group *tg) { /* Wait for possible concurrent references to cfs_rqs complete: */ - call_rcu(&tg->rcu, sched_free_group_rcu); + call_rcu(&tg->rcu, sched_unregister_group_rcu); } -void sched_offline_group(struct task_group *tg) +void sched_release_group(struct task_group *tg) { unsigned long flags; - /* End participation in shares distribution: */ - unregister_fair_sched_group(tg); - + /* + * Unlink first, to avoid walk_tg_tree_from() from finding us (via + * sched_cfs_period_timer()). + * + * For this to be effective, we have to wait for all pending users of + * this task group to leave their RCU critical section to ensure no new + * user will see our dying task group any more. Specifically ensure + * that tg_unthrottle_up() won't add decayed cfs_rq's to it. + * + * We therefore defer calling unregister_fair_sched_group() to + * sched_unregister_group() which is guarantied to get called only after the + * current RCU grace period has expired. + */ spin_lock_irqsave(&task_group_lock, flags); list_del_rcu(&tg->list); list_del_rcu(&tg->siblings); spin_unlock_irqrestore(&task_group_lock, flags); } -static void sched_change_group(struct task_struct *tsk, int type) +static void sched_change_group(struct task_struct *tsk) { struct task_group *tg; @@ -7026,7 +10177,7 @@ static void sched_change_group(struct task_struct *tsk, int type) #ifdef CONFIG_FAIR_GROUP_SCHED if (tsk->sched_class->task_change_group) - tsk->sched_class->task_change_group(tsk, type); + tsk->sched_class->task_change_group(tsk); else #endif set_task_rq(tsk, task_cpu(tsk)); @@ -7057,7 +10208,7 @@ void sched_move_task(struct task_struct *tsk) if (running) put_prev_task(rq, tsk); - sched_change_group(tsk, TASK_MOVE_GROUP); + sched_change_group(tsk); if (queued) enqueue_task(rq, tsk, queue_flags); @@ -7108,7 +10259,11 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) #ifdef CONFIG_UCLAMP_TASK_GROUP /* Propagate the effective uclamp value for the new group */ + mutex_lock(&uclamp_mutex); + rcu_read_lock(); cpu_util_update_eff(css); + rcu_read_unlock(); + mutex_unlock(&uclamp_mutex); #endif return 0; @@ -7118,7 +10273,7 @@ static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); - sched_offline_group(tg); + sched_release_group(tg); } static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) @@ -7128,56 +10283,22 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css) /* * Relies on the RCU grace period between css_released() and this. */ - sched_free_group(tg); -} - -/* - * This is called before wake_up_new_task(), therefore we really only - * have to set its group bits, all the other stuff does not apply. - */ -static void cpu_cgroup_fork(struct task_struct *task) -{ - struct rq_flags rf; - struct rq *rq; - - rq = task_rq_lock(task, &rf); - - update_rq_clock(rq); - sched_change_group(task, TASK_SET_GROUP); - - task_rq_unlock(rq, task, &rf); + sched_unregister_group(tg); } +#ifdef CONFIG_RT_GROUP_SCHED static int cpu_cgroup_can_attach(struct cgroup_taskset *tset) { struct task_struct *task; struct cgroup_subsys_state *css; - int ret = 0; cgroup_taskset_for_each(task, css, tset) { -#ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(css_tg(css), task)) return -EINVAL; -#endif - /* - * Serialize against wake_up_new_task() such that if its - * running, we're sure to observe its full state. - */ - raw_spin_lock_irq(&task->pi_lock); - /* - * Avoid calling sched_move_task() before wake_up_new_task() - * has happened. This would lead to problems with PELT, due to - * move wanting to detach+attach while we're not attached yet. - */ - if (task->state == TASK_NEW) - ret = -EINVAL; - raw_spin_unlock_irq(&task->pi_lock); - - if (ret) - break; } - return ret; + return 0; } +#endif static void cpu_cgroup_attach(struct cgroup_taskset *tset) { @@ -7198,6 +10319,9 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css) enum uclamp_id clamp_id; unsigned int clamps; + lockdep_assert_held(&uclamp_mutex); + SCHED_WARN_ON(!rcu_read_lock_held()); + css_for_each_descendant_pre(css, top_css) { uc_parent = css_tg(css)->parent ? css_tg(css)->parent->uclamp : NULL; @@ -7230,7 +10354,7 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css) } /* Immediately update descendants RUNNABLE tasks */ - uclamp_update_active_tasks(css, clamps); + uclamp_update_active_tasks(css); } } @@ -7288,6 +10412,8 @@ 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); + mutex_lock(&uclamp_mutex); rcu_read_lock(); @@ -7382,10 +10508,13 @@ 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) +static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota, + u64 burst) { int i, ret = 0, runtime_enabled, runtime_was_enabled; struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; @@ -7402,7 +10531,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) return -EINVAL; /* - * Likewise, bound things on the otherside by preventing insane quota + * Likewise, bound things on the other side by preventing insane quota * periods. This also allows us to normalize in computing quota * feasibility. */ @@ -7410,10 +10539,20 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) return -EINVAL; /* + * Bound quota to defend quota against overflow during bandwidth shift. + */ + if (quota != RUNTIME_INF && quota > max_cfs_runtime) + return -EINVAL; + + if (quota != RUNTIME_INF && (burst > quota || + burst + quota > max_cfs_runtime)) + return -EINVAL; + + /* * Prevent race between setting of cfs_rq->runtime_enabled and * unthrottle_offline_cfs_rqs(). */ - get_online_cpus(); + cpus_read_lock(); mutex_lock(&cfs_constraints_mutex); ret = __cfs_schedulable(tg, period, quota); if (ret) @@ -7430,6 +10569,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) 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); @@ -7456,16 +10596,17 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) cfs_bandwidth_usage_dec(); out_unlock: mutex_unlock(&cfs_constraints_mutex); - put_online_cpus(); + cpus_read_unlock(); return ret; } static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) { - u64 quota, period; + u64 quota, period, burst; 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) @@ -7473,7 +10614,7 @@ static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us) else return -EINVAL; - return tg_set_cfs_bandwidth(tg, period, quota); + return tg_set_cfs_bandwidth(tg, period, quota, burst); } static long tg_get_cfs_quota(struct task_group *tg) @@ -7491,15 +10632,16 @@ static long tg_get_cfs_quota(struct task_group *tg) static int tg_set_cfs_period(struct task_group *tg, long cfs_period_us) { - u64 quota, period; + 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); + return tg_set_cfs_bandwidth(tg, period, quota, burst); } static long tg_get_cfs_period(struct task_group *tg) @@ -7512,6 +10654,30 @@ static long tg_get_cfs_period(struct task_group *tg) 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) +{ + u64 burst_us; + + burst_us = tg->cfs_bandwidth.burst; + do_div(burst_us, NSEC_PER_USEC); + + return burst_us; +} + static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { @@ -7536,6 +10702,18 @@ static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css, 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; @@ -7629,15 +10807,21 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v) seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time); if (schedstat_enabled() && tg != &root_task_group) { + struct sched_statistics *stats; u64 ws = 0; int i; - for_each_possible_cpu(i) - ws += schedstat_val(tg->se[i]->statistics.wait_sum); + for_each_possible_cpu(i) { + stats = __schedstats_from_se(tg->se[i]); + ws += schedstat_val(stats->wait_sum); + } seq_printf(sf, "wait_sum %llu\n", ws); } + seq_printf(sf, "nr_bursts %d\n", cfs_b->nr_burst); + seq_printf(sf, "burst_time %llu\n", cfs_b->burst_time); + return 0; } #endif /* CONFIG_CFS_BANDWIDTH */ @@ -7669,6 +10853,20 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, } #endif /* CONFIG_RT_GROUP_SCHED */ +#ifdef CONFIG_FAIR_GROUP_SCHED +static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return css_tg(css)->idle; +} + +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); +} +#endif + static struct cftype cpu_legacy_files[] = { #ifdef CONFIG_FAIR_GROUP_SCHED { @@ -7676,6 +10874,11 @@ static struct cftype cpu_legacy_files[] = { .read_u64 = cpu_shares_read_u64, .write_u64 = cpu_shares_write_u64, }, + { + .name = "idle", + .read_s64 = cpu_idle_read_s64, + .write_s64 = cpu_idle_write_s64, + }, #endif #ifdef CONFIG_CFS_BANDWIDTH { @@ -7689,6 +10892,11 @@ static struct cftype cpu_legacy_files[] = { .write_u64 = cpu_cfs_period_write_u64, }, { + .name = "cfs_burst_us", + .read_u64 = cpu_cfs_burst_read_u64, + .write_u64 = cpu_cfs_burst_write_u64, + }, + { .name = "stat", .seq_show = cpu_cfs_stat_show, }, @@ -7729,16 +10937,20 @@ static int cpu_extra_stat_show(struct seq_file *sf, { struct task_group *tg = css_tg(css); struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; - u64 throttled_usec; + u64 throttled_usec, burst_usec; throttled_usec = cfs_b->throttled_time; do_div(throttled_usec, NSEC_PER_USEC); + burst_usec = cfs_b->burst_time; + do_div(burst_usec, NSEC_PER_USEC); seq_printf(sf, "nr_periods %d\n" "nr_throttled %d\n" - "throttled_usec %llu\n", + "throttled_usec %llu\n" + "nr_bursts %d\n" + "burst_usec %llu\n", cfs_b->nr_periods, cfs_b->nr_throttled, - throttled_usec); + throttled_usec, cfs_b->nr_burst, burst_usec); } #endif return 0; @@ -7853,12 +11065,13 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of, { 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; int ret; ret = cpu_period_quota_parse(buf, &period, "a); if (!ret) - ret = tg_set_cfs_bandwidth(tg, period, quota); + ret = tg_set_cfs_bandwidth(tg, period, quota, burst); return ret ?: nbytes; } #endif @@ -7877,6 +11090,12 @@ static struct cftype cpu_files[] = { .read_s64 = cpu_weight_nice_read_s64, .write_s64 = cpu_weight_nice_write_s64, }, + { + .name = "idle", + .flags = CFTYPE_NOT_ON_ROOT, + .read_s64 = cpu_idle_read_s64, + .write_s64 = cpu_idle_write_s64, + }, #endif #ifdef CONFIG_CFS_BANDWIDTH { @@ -7885,6 +11104,12 @@ static struct cftype cpu_files[] = { .seq_show = cpu_max_show, .write = cpu_max_write, }, + { + .name = "max.burst", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = cpu_cfs_burst_read_u64, + .write_u64 = cpu_cfs_burst_write_u64, + }, #endif #ifdef CONFIG_UCLAMP_TASK_GROUP { @@ -7909,8 +11134,9 @@ struct cgroup_subsys cpu_cgrp_subsys = { .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, .css_extra_stat_show = cpu_extra_stat_show, - .fork = cpu_cgroup_fork, +#ifdef CONFIG_RT_GROUP_SCHED .can_attach = cpu_cgroup_can_attach, +#endif .attach = cpu_cgroup_attach, .legacy_cftypes = cpu_legacy_files, .dfl_cftypes = cpu_files, @@ -7922,6 +11148,19 @@ struct cgroup_subsys cpu_cgrp_subsys = { void dump_cpu_task(int cpu) { + if (cpu == smp_processor_id() && in_hardirq()) { + struct pt_regs *regs; + + regs = get_irq_regs(); + if (regs) { + show_regs(regs); + return; + } + } + + if (trigger_single_cpu_backtrace(cpu)) + return; + pr_info("Task dump for CPU %d:\n", cpu); sched_show_task(cpu_curr(cpu)); } @@ -7967,4 +11206,7 @@ const u32 sched_prio_to_wmult[40] = { /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, }; -#undef CREATE_TRACE_POINTS +void call_trace_sched_update_nr_running(struct rq *rq, int count) +{ + trace_sched_update_nr_running_tp(rq, count); +} |