sched.h 44.9 KB
Newer Older
1 2

#include <linux/sched.h>
3
#include <linux/sched/sysctl.h>
4
#include <linux/sched/rt.h>
5
#include <linux/sched/deadline.h>
6 7 8
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/stop_machine.h>
9
#include <linux/irq_work.h>
10
#include <linux/tick.h>
11
#include <linux/slab.h>
12

13
#include "cpupri.h"
14
#include "cpudeadline.h"
15
#include "cpuacct.h"
16

17
struct rq;
18
struct cpuidle_state;
19

20 21
/* task_struct::on_rq states: */
#define TASK_ON_RQ_QUEUED	1
22
#define TASK_ON_RQ_MIGRATING	2
23

24 25
extern __read_mostly int scheduler_running;

26 27 28
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;

29
extern void calc_global_load_tick(struct rq *this_rq);
30
extern long calc_load_fold_active(struct rq *this_rq);
31 32

#ifdef CONFIG_SMP
33
extern void update_cpu_load_active(struct rq *this_rq);
34 35 36
#else
static inline void update_cpu_load_active(struct rq *this_rq) { }
#endif
37

38 39 40 41 42
/*
 * Helpers for converting nanosecond timing to jiffy resolution
 */
#define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))

43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67
/*
 * Increase resolution of nice-level calculations for 64-bit architectures.
 * The extra resolution improves shares distribution and load balancing of
 * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
 * hierarchies, especially on larger systems. This is not a user-visible change
 * and does not change the user-interface for setting shares/weights.
 *
 * We increase resolution only if we have enough bits to allow this increased
 * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution
 * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the
 * increased costs.
 */
#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load  */
# define SCHED_LOAD_RESOLUTION	10
# define scale_load(w)		((w) << SCHED_LOAD_RESOLUTION)
# define scale_load_down(w)	((w) >> SCHED_LOAD_RESOLUTION)
#else
# define SCHED_LOAD_RESOLUTION	0
# define scale_load(w)		(w)
# define scale_load_down(w)	(w)
#endif

#define SCHED_LOAD_SHIFT	(10 + SCHED_LOAD_RESOLUTION)
#define SCHED_LOAD_SCALE	(1L << SCHED_LOAD_SHIFT)

68 69 70
#define NICE_0_LOAD		SCHED_LOAD_SCALE
#define NICE_0_SHIFT		SCHED_LOAD_SHIFT

71 72 73 74 75 76 77
/*
 * Single value that decides SCHED_DEADLINE internal math precision.
 * 10 -> just above 1us
 * 9  -> just above 0.5us
 */
#define DL_SCALE (10)

78 79 80 81 82 83 84 85 86
/*
 * These are the 'tuning knobs' of the scheduler:
 */

/*
 * single value that denotes runtime == period, ie unlimited time.
 */
#define RUNTIME_INF	((u64)~0ULL)

87 88 89 90
static inline int idle_policy(int policy)
{
	return policy == SCHED_IDLE;
}
91 92 93 94 95
static inline int fair_policy(int policy)
{
	return policy == SCHED_NORMAL || policy == SCHED_BATCH;
}

96 97
static inline int rt_policy(int policy)
{
98
	return policy == SCHED_FIFO || policy == SCHED_RR;
99 100
}

101 102 103 104
static inline int dl_policy(int policy)
{
	return policy == SCHED_DEADLINE;
}
105 106 107 108 109
static inline bool valid_policy(int policy)
{
	return idle_policy(policy) || fair_policy(policy) ||
		rt_policy(policy) || dl_policy(policy);
}
110

111 112 113 114 115
static inline int task_has_rt_policy(struct task_struct *p)
{
	return rt_policy(p->policy);
}

116 117 118 119 120
static inline int task_has_dl_policy(struct task_struct *p)
{
	return dl_policy(p->policy);
}

121 122 123
/*
 * Tells if entity @a should preempt entity @b.
 */
124 125
static inline bool
dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
126 127 128 129
{
	return dl_time_before(a->deadline, b->deadline);
}

130 131 132 133 134 135 136 137 138 139 140 141 142 143
/*
 * This is the priority-queue data structure of the RT scheduling class:
 */
struct rt_prio_array {
	DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */
	struct list_head queue[MAX_RT_PRIO];
};

struct rt_bandwidth {
	/* nests inside the rq lock: */
	raw_spinlock_t		rt_runtime_lock;
	ktime_t			rt_period;
	u64			rt_runtime;
	struct hrtimer		rt_period_timer;
P
Peter Zijlstra 已提交
144
	unsigned int		rt_period_active;
145
};
146 147 148

void __dl_clear_params(struct task_struct *p);

149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180
/*
 * To keep the bandwidth of -deadline tasks and groups under control
 * we need some place where:
 *  - store the maximum -deadline bandwidth of the system (the group);
 *  - cache the fraction of that bandwidth that is currently allocated.
 *
 * This is all done in the data structure below. It is similar to the
 * one used for RT-throttling (rt_bandwidth), with the main difference
 * that, since here we are only interested in admission control, we
 * do not decrease any runtime while the group "executes", neither we
 * need a timer to replenish it.
 *
 * With respect to SMP, the bandwidth is given on a per-CPU basis,
 * meaning that:
 *  - dl_bw (< 100%) is the bandwidth of the system (group) on each CPU;
 *  - dl_total_bw array contains, in the i-eth element, the currently
 *    allocated bandwidth on the i-eth CPU.
 * Moreover, groups consume bandwidth on each CPU, while tasks only
 * consume bandwidth on the CPU they're running on.
 * Finally, dl_total_bw_cpu is used to cache the index of dl_total_bw
 * that will be shown the next time the proc or cgroup controls will
 * be red. It on its turn can be changed by writing on its own
 * control.
 */
struct dl_bandwidth {
	raw_spinlock_t dl_runtime_lock;
	u64 dl_runtime;
	u64 dl_period;
};

static inline int dl_bandwidth_enabled(void)
{
181
	return sysctl_sched_rt_runtime >= 0;
182 183 184 185 186 187 188 189 190
}

extern struct dl_bw *dl_bw_of(int i);

struct dl_bw {
	raw_spinlock_t lock;
	u64 bw, total_bw;
};

191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
static inline
void __dl_clear(struct dl_bw *dl_b, u64 tsk_bw)
{
	dl_b->total_bw -= tsk_bw;
}

static inline
void __dl_add(struct dl_bw *dl_b, u64 tsk_bw)
{
	dl_b->total_bw += tsk_bw;
}

static inline
bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw)
{
	return dl_b->bw != -1 &&
	       dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw;
}

210 211 212 213 214 215 216 217 218
extern struct mutex sched_domains_mutex;

#ifdef CONFIG_CGROUP_SCHED

#include <linux/cgroup.h>

struct cfs_rq;
struct rt_rq;

219
extern struct list_head task_groups;
220 221 222 223 224 225

struct cfs_bandwidth {
#ifdef CONFIG_CFS_BANDWIDTH
	raw_spinlock_t lock;
	ktime_t period;
	u64 quota, runtime;
226
	s64 hierarchical_quota;
227 228
	u64 runtime_expires;

P
Peter Zijlstra 已提交
229
	int idle, period_active;
230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249
	struct hrtimer period_timer, slack_timer;
	struct list_head throttled_cfs_rq;

	/* statistics */
	int nr_periods, nr_throttled;
	u64 throttled_time;
#endif
};

/* task group related information */
struct task_group {
	struct cgroup_subsys_state css;

#ifdef CONFIG_FAIR_GROUP_SCHED
	/* schedulable entities of this group on each cpu */
	struct sched_entity **se;
	/* runqueue "owned" by this group on each cpu */
	struct cfs_rq **cfs_rq;
	unsigned long shares;

250
#ifdef	CONFIG_SMP
251
	atomic_long_t load_avg;
252
#endif
253
#endif
254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318

#ifdef CONFIG_RT_GROUP_SCHED
	struct sched_rt_entity **rt_se;
	struct rt_rq **rt_rq;

	struct rt_bandwidth rt_bandwidth;
#endif

	struct rcu_head rcu;
	struct list_head list;

	struct task_group *parent;
	struct list_head siblings;
	struct list_head children;

#ifdef CONFIG_SCHED_AUTOGROUP
	struct autogroup *autogroup;
#endif

	struct cfs_bandwidth cfs_bandwidth;
};

#ifdef CONFIG_FAIR_GROUP_SCHED
#define ROOT_TASK_GROUP_LOAD	NICE_0_LOAD

/*
 * A weight of 0 or 1 can cause arithmetics problems.
 * A weight of a cfs_rq is the sum of weights of which entities
 * are queued on this cfs_rq, so a weight of a entity should not be
 * too large, so as the shares value of a task group.
 * (The default weight is 1024 - so there's no practical
 *  limitation from this.)
 */
#define MIN_SHARES	(1UL <<  1)
#define MAX_SHARES	(1UL << 18)
#endif

typedef int (*tg_visitor)(struct task_group *, void *);

extern int walk_tg_tree_from(struct task_group *from,
			     tg_visitor down, tg_visitor up, void *data);

/*
 * Iterate the full tree, calling @down when first entering a node and @up when
 * leaving it for the final time.
 *
 * Caller must hold rcu_lock or sufficient equivalent.
 */
static inline int walk_tg_tree(tg_visitor down, tg_visitor up, void *data)
{
	return walk_tg_tree_from(&root_task_group, down, up, data);
}

extern int tg_nop(struct task_group *tg, void *data);

extern void free_fair_sched_group(struct task_group *tg);
extern int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent);
extern void unregister_fair_sched_group(struct task_group *tg, int cpu);
extern void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
			struct sched_entity *se, int cpu,
			struct sched_entity *parent);
extern void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);

extern void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b);
P
Peter Zijlstra 已提交
319
extern void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b);
320 321 322 323 324 325 326 327
extern void unthrottle_cfs_rq(struct cfs_rq *cfs_rq);

extern void free_rt_sched_group(struct task_group *tg);
extern int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent);
extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq,
		struct sched_rt_entity *rt_se, int cpu,
		struct sched_rt_entity *parent);

328 329 330 331 332 333 334 335 336 337 338 339
extern struct task_group *sched_create_group(struct task_group *parent);
extern void sched_online_group(struct task_group *tg,
			       struct task_group *parent);
extern void sched_destroy_group(struct task_group *tg);
extern void sched_offline_group(struct task_group *tg);

extern void sched_move_task(struct task_struct *tsk);

#ifdef CONFIG_FAIR_GROUP_SCHED
extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
#endif

340 341 342 343 344 345 346 347 348
#else /* CONFIG_CGROUP_SCHED */

struct cfs_bandwidth { };

#endif	/* CONFIG_CGROUP_SCHED */

/* CFS-related fields in a runqueue */
struct cfs_rq {
	struct load_weight load;
349
	unsigned int nr_running, h_nr_running;
350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369

	u64 exec_clock;
	u64 min_vruntime;
#ifndef CONFIG_64BIT
	u64 min_vruntime_copy;
#endif

	struct rb_root tasks_timeline;
	struct rb_node *rb_leftmost;

	/*
	 * 'curr' points to currently running entity on this cfs_rq.
	 * It is set to NULL otherwise (i.e when none are currently running).
	 */
	struct sched_entity *curr, *next, *last, *skip;

#ifdef	CONFIG_SCHED_DEBUG
	unsigned int nr_spread_over;
#endif

370 371
#ifdef CONFIG_SMP
	/*
372
	 * CFS load tracking
373
	 */
374
	struct sched_avg avg;
375 376
	u64 runnable_load_sum;
	unsigned long runnable_load_avg;
377
#ifdef CONFIG_FAIR_GROUP_SCHED
378 379 380 381 382 383
	unsigned long tg_load_avg_contrib;
#endif
	atomic_long_t removed_load_avg, removed_util_avg;
#ifndef CONFIG_64BIT
	u64 load_last_update_time_copy;
#endif
384

385
#ifdef CONFIG_FAIR_GROUP_SCHED
386 387 388 389 390 391 392
	/*
	 *   h_load = weight * f(tg)
	 *
	 * Where f(tg) is the recursive weight fraction assigned to
	 * this group.
	 */
	unsigned long h_load;
393 394 395
	u64 last_h_load_update;
	struct sched_entity *h_load_next;
#endif /* CONFIG_FAIR_GROUP_SCHED */
396 397
#endif /* CONFIG_SMP */

398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
#ifdef CONFIG_FAIR_GROUP_SCHED
	struct rq *rq;	/* cpu runqueue to which this cfs_rq is attached */

	/*
	 * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
	 * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
	 * (like users, containers etc.)
	 *
	 * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
	 * list is used during load balance.
	 */
	int on_list;
	struct list_head leaf_cfs_rq_list;
	struct task_group *tg;	/* group that "owns" this runqueue */

#ifdef CONFIG_CFS_BANDWIDTH
	int runtime_enabled;
	u64 runtime_expires;
	s64 runtime_remaining;

418 419
	u64 throttled_clock, throttled_clock_task;
	u64 throttled_clock_task_time;
420 421 422 423 424 425 426 427 428 429 430
	int throttled, throttle_count;
	struct list_head throttled_list;
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};

static inline int rt_bandwidth_enabled(void)
{
	return sysctl_sched_rt_runtime >= 0;
}

431 432 433 434 435
/* RT IPI pull logic requires IRQ_WORK */
#ifdef CONFIG_IRQ_WORK
# define HAVE_RT_PUSH_IPI
#endif

436 437 438
/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
	struct rt_prio_array active;
439
	unsigned int rt_nr_running;
440 441 442 443 444 445 446 447 448 449 450 451 452
#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
	struct {
		int curr; /* highest queued rt task prio */
#ifdef CONFIG_SMP
		int next; /* next highest */
#endif
	} highest_prio;
#endif
#ifdef CONFIG_SMP
	unsigned long rt_nr_migratory;
	unsigned long rt_nr_total;
	int overloaded;
	struct plist_head pushable_tasks;
453 454 455 456 457
#ifdef HAVE_RT_PUSH_IPI
	int push_flags;
	int push_cpu;
	struct irq_work push_work;
	raw_spinlock_t push_lock;
458
#endif
459
#endif /* CONFIG_SMP */
460 461
	int rt_queued;

462 463 464 465 466 467 468 469 470 471 472 473 474 475
	int rt_throttled;
	u64 rt_time;
	u64 rt_runtime;
	/* Nests inside the rq lock: */
	raw_spinlock_t rt_runtime_lock;

#ifdef CONFIG_RT_GROUP_SCHED
	unsigned long rt_nr_boosted;

	struct rq *rq;
	struct task_group *tg;
#endif
};

476 477 478 479 480 481 482
/* Deadline class' related fields in a runqueue */
struct dl_rq {
	/* runqueue is an rbtree, ordered by deadline */
	struct rb_root rb_root;
	struct rb_node *rb_leftmost;

	unsigned long dl_nr_running;
483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505

#ifdef CONFIG_SMP
	/*
	 * Deadline values of the currently executing and the
	 * earliest ready task on this rq. Caching these facilitates
	 * the decision wether or not a ready but not running task
	 * should migrate somewhere else.
	 */
	struct {
		u64 curr;
		u64 next;
	} earliest_dl;

	unsigned long dl_nr_migratory;
	int overloaded;

	/*
	 * Tasks on this rq that can be pushed away. They are kept in
	 * an rb-tree, ordered by tasks' deadlines, with caching
	 * of the leftmost (earliest deadline) element.
	 */
	struct rb_root pushable_dl_tasks_root;
	struct rb_node *pushable_dl_tasks_leftmost;
506 507
#else
	struct dl_bw dl_bw;
508
#endif
509 510
};

511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527
#ifdef CONFIG_SMP

/*
 * We add the notion of a root-domain which will be used to define per-domain
 * variables. Each exclusive cpuset essentially defines an island domain by
 * fully partitioning the member cpus from any other cpuset. Whenever a new
 * exclusive cpuset is created, we also create and attach a new root-domain
 * object.
 *
 */
struct root_domain {
	atomic_t refcount;
	atomic_t rto_count;
	struct rcu_head rcu;
	cpumask_var_t span;
	cpumask_var_t online;

528 529 530
	/* Indicate more than one runnable task for any CPU */
	bool overload;

531 532 533 534 535 536
	/*
	 * The bit corresponding to a CPU gets set here if such CPU has more
	 * than one runnable -deadline task (as it is below for RT tasks).
	 */
	cpumask_var_t dlo_mask;
	atomic_t dlo_count;
537
	struct dl_bw dl_bw;
538
	struct cpudl cpudl;
539

540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566
	/*
	 * The "RT overload" flag: it gets set if a CPU has more than
	 * one runnable RT task.
	 */
	cpumask_var_t rto_mask;
	struct cpupri cpupri;
};

extern struct root_domain def_root_domain;

#endif /* CONFIG_SMP */

/*
 * This is the main, per-CPU runqueue data structure.
 *
 * Locking rule: those places that want to lock multiple runqueues
 * (such as the load balancing or the thread migration code), lock
 * acquire operations must be ordered by ascending &runqueue.
 */
struct rq {
	/* runqueue lock: */
	raw_spinlock_t lock;

	/*
	 * nr_running and cpu_load should be in the same cacheline because
	 * remote CPUs use both these fields when doing load calculation.
	 */
567
	unsigned int nr_running;
568 569 570 571
#ifdef CONFIG_NUMA_BALANCING
	unsigned int nr_numa_running;
	unsigned int nr_preferred_running;
#endif
572 573 574
	#define CPU_LOAD_IDX_MAX 5
	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
	unsigned long last_load_update_tick;
575
#ifdef CONFIG_NO_HZ_COMMON
576
	u64 nohz_stamp;
577
	unsigned long nohz_flags;
578 579 580
#endif
#ifdef CONFIG_NO_HZ_FULL
	unsigned long last_sched_tick;
581 582 583 584 585 586 587 588
#endif
	/* capture load from *all* tasks on this cpu: */
	struct load_weight load;
	unsigned long nr_load_updates;
	u64 nr_switches;

	struct cfs_rq cfs;
	struct rt_rq rt;
589
	struct dl_rq dl;
590 591 592 593

#ifdef CONFIG_FAIR_GROUP_SCHED
	/* list of leaf cfs_rq on this cpu: */
	struct list_head leaf_cfs_rq_list;
594 595
#endif /* CONFIG_FAIR_GROUP_SCHED */

596 597 598 599 600 601 602 603 604 605 606 607
	/*
	 * This is part of a global counter where only the total sum
	 * over all CPUs matters. A task can increase this counter on
	 * one CPU and if it got migrated afterwards it may decrease
	 * it on another CPU. Always updated under the runqueue lock:
	 */
	unsigned long nr_uninterruptible;

	struct task_struct *curr, *idle, *stop;
	unsigned long next_balance;
	struct mm_struct *prev_mm;

608
	unsigned int clock_skip_update;
609 610 611 612 613 614 615 616 617
	u64 clock;
	u64 clock_task;

	atomic_t nr_iowait;

#ifdef CONFIG_SMP
	struct root_domain *rd;
	struct sched_domain *sd;

618
	unsigned long cpu_capacity;
619
	unsigned long cpu_capacity_orig;
620

621 622
	struct callback_head *balance_callback;

623 624 625 626 627 628 629 630 631
	unsigned char idle_balance;
	/* For active balancing */
	int active_balance;
	int push_cpu;
	struct cpu_stop_work active_balance_work;
	/* cpu of this runqueue: */
	int cpu;
	int online;

632 633
	struct list_head cfs_tasks;

634 635 636 637
	u64 rt_avg;
	u64 age_stamp;
	u64 idle_stamp;
	u64 avg_idle;
638 639 640

	/* This is used to determine avg_idle's max value */
	u64 max_idle_balance_cost;
641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685
#endif

#ifdef CONFIG_IRQ_TIME_ACCOUNTING
	u64 prev_irq_time;
#endif
#ifdef CONFIG_PARAVIRT
	u64 prev_steal_time;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
	u64 prev_steal_time_rq;
#endif

	/* calc_load related fields */
	unsigned long calc_load_update;
	long calc_load_active;

#ifdef CONFIG_SCHED_HRTICK
#ifdef CONFIG_SMP
	int hrtick_csd_pending;
	struct call_single_data hrtick_csd;
#endif
	struct hrtimer hrtick_timer;
#endif

#ifdef CONFIG_SCHEDSTATS
	/* latency stats */
	struct sched_info rq_sched_info;
	unsigned long long rq_cpu_time;
	/* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */

	/* sys_sched_yield() stats */
	unsigned int yld_count;

	/* schedule() stats */
	unsigned int sched_count;
	unsigned int sched_goidle;

	/* try_to_wake_up() stats */
	unsigned int ttwu_count;
	unsigned int ttwu_local;
#endif

#ifdef CONFIG_SMP
	struct llist_head wake_list;
#endif
686 687 688 689 690

#ifdef CONFIG_CPU_IDLE
	/* Must be inspected within a rcu lock section */
	struct cpuidle_state *idle_state;
#endif
691 692 693 694 695 696 697 698 699 700 701
};

static inline int cpu_of(struct rq *rq)
{
#ifdef CONFIG_SMP
	return rq->cpu;
#else
	return 0;
#endif
}

702
DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
703

704
#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
705
#define this_rq()		this_cpu_ptr(&runqueues)
706 707
#define task_rq(p)		cpu_rq(task_cpu(p))
#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
708
#define raw_rq()		raw_cpu_ptr(&runqueues)
709

710 711
static inline u64 __rq_clock_broken(struct rq *rq)
{
712
	return READ_ONCE(rq->clock);
713 714
}

715 716
static inline u64 rq_clock(struct rq *rq)
{
717
	lockdep_assert_held(&rq->lock);
718 719 720 721 722
	return rq->clock;
}

static inline u64 rq_clock_task(struct rq *rq)
{
723
	lockdep_assert_held(&rq->lock);
724 725 726
	return rq->clock_task;
}

727 728 729 730 731 732 733 734 735 736 737 738
#define RQCF_REQ_SKIP	0x01
#define RQCF_ACT_SKIP	0x02

static inline void rq_clock_skip_update(struct rq *rq, bool skip)
{
	lockdep_assert_held(&rq->lock);
	if (skip)
		rq->clock_skip_update |= RQCF_REQ_SKIP;
	else
		rq->clock_skip_update &= ~RQCF_REQ_SKIP;
}

739
#ifdef CONFIG_NUMA
740 741 742 743 744 745
enum numa_topology_type {
	NUMA_DIRECT,
	NUMA_GLUELESS_MESH,
	NUMA_BACKPLANE,
};
extern enum numa_topology_type sched_numa_topology_type;
746 747 748 749
extern int sched_max_numa_distance;
extern bool find_numa_distance(int distance);
#endif

750
#ifdef CONFIG_NUMA_BALANCING
751 752 753 754 755 756 757
/* The regions in numa_faults array from task_struct */
enum numa_faults_stats {
	NUMA_MEM = 0,
	NUMA_CPU,
	NUMA_MEMBUF,
	NUMA_CPUBUF
};
758
extern void sched_setnuma(struct task_struct *p, int node);
759
extern int migrate_task_to(struct task_struct *p, int cpu);
760
extern int migrate_swap(struct task_struct *, struct task_struct *);
761 762
#endif /* CONFIG_NUMA_BALANCING */

763 764
#ifdef CONFIG_SMP

765 766 767 768 769 770 771 772 773 774 775 776 777 778 779
static inline void
queue_balance_callback(struct rq *rq,
		       struct callback_head *head,
		       void (*func)(struct rq *rq))
{
	lockdep_assert_held(&rq->lock);

	if (unlikely(head->next))
		return;

	head->func = (void (*)(struct callback_head *))func;
	head->next = rq->balance_callback;
	rq->balance_callback = head;
}

780 781
extern void sched_ttwu_pending(void);

782 783 784 785 786 787 788 789 790 791 792 793
#define rcu_dereference_check_sched_domain(p) \
	rcu_dereference_check((p), \
			      lockdep_is_held(&sched_domains_mutex))

/*
 * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
 * See detach_destroy_domains: synchronize_sched for details.
 *
 * The domain tree of any CPU may only be accessed from within
 * preempt-disabled sections.
 */
#define for_each_domain(cpu, __sd) \
794 795
	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
			__sd; __sd = __sd->parent)
796

797 798
#define for_each_lower_domain(sd) for (; sd; sd = sd->child)

799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820
/**
 * highest_flag_domain - Return highest sched_domain containing flag.
 * @cpu:	The cpu whose highest level of sched domain is to
 *		be returned.
 * @flag:	The flag to check for the highest sched_domain
 *		for the given cpu.
 *
 * Returns the highest sched_domain of a cpu which contains the given flag.
 */
static inline struct sched_domain *highest_flag_domain(int cpu, int flag)
{
	struct sched_domain *sd, *hsd = NULL;

	for_each_domain(cpu, sd) {
		if (!(sd->flags & flag))
			break;
		hsd = sd;
	}

	return hsd;
}

821 822 823 824 825 826 827 828 829 830 831 832
static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
{
	struct sched_domain *sd;

	for_each_domain(cpu, sd) {
		if (sd->flags & flag)
			break;
	}

	return sd;
}

833
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
834
DECLARE_PER_CPU(int, sd_llc_size);
835
DECLARE_PER_CPU(int, sd_llc_id);
836
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
837 838
DECLARE_PER_CPU(struct sched_domain *, sd_busy);
DECLARE_PER_CPU(struct sched_domain *, sd_asym);
839

840
struct sched_group_capacity {
841 842
	atomic_t ref;
	/*
843 844
	 * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity
	 * for a single CPU.
845
	 */
846
	unsigned int capacity;
847
	unsigned long next_update;
848
	int imbalance; /* XXX unrelated to capacity but shared group state */
849 850 851 852 853 854 855 856 857 858 859 860 861
	/*
	 * Number of busy cpus in this group.
	 */
	atomic_t nr_busy_cpus;

	unsigned long cpumask[0]; /* iteration mask */
};

struct sched_group {
	struct sched_group *next;	/* Must be a circular list */
	atomic_t ref;

	unsigned int group_weight;
862
	struct sched_group_capacity *sgc;
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884

	/*
	 * The CPUs this group covers.
	 *
	 * NOTE: this field is variable length. (Allocated dynamically
	 * by attaching extra space to the end of the structure,
	 * depending on how many CPUs the kernel has booted up with)
	 */
	unsigned long cpumask[0];
};

static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
{
	return to_cpumask(sg->cpumask);
}

/*
 * cpumask masking which cpus in the group are allowed to iterate up the domain
 * tree.
 */
static inline struct cpumask *sched_group_mask(struct sched_group *sg)
{
885
	return to_cpumask(sg->sgc->cpumask);
886 887 888 889 890 891 892 893 894 895 896
}

/**
 * group_first_cpu - Returns the first cpu in the cpumask of a sched_group.
 * @group: The group whose first cpu is to be returned.
 */
static inline unsigned int group_first_cpu(struct sched_group *group)
{
	return cpumask_first(sched_group_cpus(group));
}

P
Peter Zijlstra 已提交
897 898
extern int group_balance_cpu(struct sched_group *sg);

899 900 901 902
#else

static inline void sched_ttwu_pending(void) { }

903
#endif /* CONFIG_SMP */
904

905 906
#include "stats.h"
#include "auto_group.h"
907 908 909 910 911 912

#ifdef CONFIG_CGROUP_SCHED

/*
 * Return the group to which this tasks belongs.
 *
913 914 915
 * We cannot use task_css() and friends because the cgroup subsystem
 * changes that value before the cgroup_subsys::attach() method is called,
 * therefore we cannot pin it and might observe the wrong value.
P
Peter Zijlstra 已提交
916 917 918 919 920 921
 *
 * The same is true for autogroup's p->signal->autogroup->tg, the autogroup
 * core changes this before calling sched_move_task().
 *
 * Instead we use a 'copy' which is updated from sched_move_task() while
 * holding both task_struct::pi_lock and rq::lock.
922 923 924
 */
static inline struct task_group *task_group(struct task_struct *p)
{
P
Peter Zijlstra 已提交
925
	return p->sched_task_group;
926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966
}

/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
static inline void set_task_rq(struct task_struct *p, unsigned int cpu)
{
#if defined(CONFIG_FAIR_GROUP_SCHED) || defined(CONFIG_RT_GROUP_SCHED)
	struct task_group *tg = task_group(p);
#endif

#ifdef CONFIG_FAIR_GROUP_SCHED
	p->se.cfs_rq = tg->cfs_rq[cpu];
	p->se.parent = tg->se[cpu];
#endif

#ifdef CONFIG_RT_GROUP_SCHED
	p->rt.rt_rq  = tg->rt_rq[cpu];
	p->rt.parent = tg->rt_se[cpu];
#endif
}

#else /* CONFIG_CGROUP_SCHED */

static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { }
static inline struct task_group *task_group(struct task_struct *p)
{
	return NULL;
}

#endif /* CONFIG_CGROUP_SCHED */

static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
	set_task_rq(p, cpu);
#ifdef CONFIG_SMP
	/*
	 * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
	 * successfuly executed on another CPU. We must ensure that updates of
	 * per-task data have been completed by this moment.
	 */
	smp_wmb();
	task_thread_info(p)->cpu = cpu;
967
	p->wake_cpu = cpu;
968 969 970 971 972 973 974
#endif
}

/*
 * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
 */
#ifdef CONFIG_SCHED_DEBUG
975
# include <linux/static_key.h>
976 977 978 979 980 981 982 983 984 985 986
# define const_debug __read_mostly
#else
# define const_debug const
#endif

extern const_debug unsigned int sysctl_sched_features;

#define SCHED_FEAT(name, enabled)	\
	__SCHED_FEAT_##name ,

enum {
987
#include "features.h"
988
	__SCHED_FEAT_NR,
989 990 991 992
};

#undef SCHED_FEAT

993 994
#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
#define SCHED_FEAT(name, enabled)					\
995
static __always_inline bool static_branch_##name(struct static_key *key) \
996
{									\
997
	return static_key_##enabled(key);				\
998 999 1000 1001 1002 1003
}

#include "features.h"

#undef SCHED_FEAT

1004
extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
1005 1006
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
1007
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
1008
#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
1009

1010
extern struct static_key_false sched_numa_balancing;
1011

1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
static inline u64 global_rt_period(void)
{
	return (u64)sysctl_sched_rt_period * NSEC_PER_USEC;
}

static inline u64 global_rt_runtime(void)
{
	if (sysctl_sched_rt_runtime < 0)
		return RUNTIME_INF;

	return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC;
}

static inline int task_current(struct rq *rq, struct task_struct *p)
{
	return rq->curr == p;
}

static inline int task_running(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP
	return p->on_cpu;
#else
	return task_current(rq, p);
#endif
}

1039 1040 1041 1042
static inline int task_on_rq_queued(struct task_struct *p)
{
	return p->on_rq == TASK_ON_RQ_QUEUED;
}
1043

1044 1045 1046 1047 1048
static inline int task_on_rq_migrating(struct task_struct *p)
{
	return p->on_rq == TASK_ON_RQ_MIGRATING;
}

1049 1050 1051
#ifndef prepare_arch_switch
# define prepare_arch_switch(next)	do { } while (0)
#endif
1052 1053 1054
#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch()	do { } while (0)
#endif
1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074

static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next)
{
#ifdef CONFIG_SMP
	/*
	 * We can optimise this out completely for !SMP, because the
	 * SMP rebalancing from interrupt is the only thing that cares
	 * here.
	 */
	next->on_cpu = 1;
#endif
}

static inline void finish_lock_switch(struct rq *rq, 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
	 * finished.
1075 1076
	 *
	 * Pairs with the control dependency and rmb in try_to_wake_up().
1077
	 */
1078
	smp_store_release(&prev->on_cpu, 0);
1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
	/* this is a valid case when another task releases the spinlock */
	rq->lock.owner = current;
#endif
	/*
	 * If we are tracking spinlock dependencies then we have to
	 * 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);
}

1094 1095 1096 1097 1098 1099 1100
/*
 * wake flags
 */
#define WF_SYNC		0x01		/* waker goes to sleep after wakeup */
#define WF_FORK		0x02		/* child wakeup after fork */
#define WF_MIGRATED	0x4		/* internal use, task got migrated */

1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153
/*
 * To aid in avoiding the subversion of "niceness" due to uneven distribution
 * of tasks with abnormal "nice" values across CPUs the contribution that
 * each task makes to its run queue's load is weighted according to its
 * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a
 * scaled version of the new time slice allocation that they receive on time
 * slice expiry etc.
 */

#define WEIGHT_IDLEPRIO                3
#define WMULT_IDLEPRIO         1431655765

/*
 * Nice levels are multiplicative, with a gentle 10% change for every
 * nice level changed. I.e. when a CPU-bound task goes from nice 0 to
 * nice 1, it will get ~10% less CPU time than another CPU-bound task
 * that remained on nice 0.
 *
 * The "10% effect" is relative and cumulative: from _any_ nice level,
 * if you go up 1 level, it's -10% CPU usage, if you go down 1 level
 * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25.
 * If a task goes up by ~10% and another task goes down by ~10% then
 * the relative distance between them is ~25%.)
 */
static const int prio_to_weight[40] = {
 /* -20 */     88761,     71755,     56483,     46273,     36291,
 /* -15 */     29154,     23254,     18705,     14949,     11916,
 /* -10 */      9548,      7620,      6100,      4904,      3906,
 /*  -5 */      3121,      2501,      1991,      1586,      1277,
 /*   0 */      1024,       820,       655,       526,       423,
 /*   5 */       335,       272,       215,       172,       137,
 /*  10 */       110,        87,        70,        56,        45,
 /*  15 */        36,        29,        23,        18,        15,
};

/*
 * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated.
 *
 * In cases where the weight does not change often, we can use the
 * precalculated inverse to speed up arithmetics by turning divisions
 * into multiplications:
 */
static const u32 prio_to_wmult[40] = {
 /* -20 */     48388,     59856,     76040,     92818,    118348,
 /* -15 */    147320,    184698,    229616,    287308,    360437,
 /* -10 */    449829,    563644,    704093,    875809,   1099582,
 /*  -5 */   1376151,   1717300,   2157191,   2708050,   3363326,
 /*   0 */   4194304,   5237765,   6557202,   8165337,  10153587,
 /*   5 */  12820798,  15790321,  19976592,  24970740,  31350126,
 /*  10 */  39045157,  49367440,  61356676,  76695844,  95443717,
 /*  15 */ 119304647, 148102320, 186737708, 238609294, 286331153,
};

1154 1155
#define ENQUEUE_WAKEUP		0x01
#define ENQUEUE_HEAD		0x02
1156
#ifdef CONFIG_SMP
1157
#define ENQUEUE_WAKING		0x04	/* sched_class::task_waking was called */
1158
#else
1159
#define ENQUEUE_WAKING		0x00
1160
#endif
1161 1162
#define ENQUEUE_REPLENISH	0x08
#define ENQUEUE_RESTORE	0x10
1163

1164 1165
#define DEQUEUE_SLEEP		0x01
#define DEQUEUE_SAVE		0x02
1166

1167 1168
#define RETRY_TASK		((void *)-1UL)

1169 1170 1171 1172 1173 1174 1175 1176 1177 1178
struct sched_class {
	const struct sched_class *next;

	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
	void (*yield_task) (struct rq *rq);
	bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt);

	void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);

1179 1180 1181 1182
	/*
	 * It is the responsibility of the pick_next_task() method that will
	 * return the next task to call put_prev_task() on the @prev task or
	 * something equivalent.
1183 1184 1185
	 *
	 * May return RETRY_TASK when it finds a higher prio class has runnable
	 * tasks.
1186 1187 1188
	 */
	struct task_struct * (*pick_next_task) (struct rq *rq,
						struct task_struct *prev);
1189 1190 1191
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);

#ifdef CONFIG_SMP
1192
	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207
	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);

	void (*task_waking) (struct task_struct *task);
	void (*task_woken) (struct rq *this_rq, struct task_struct *task);

	void (*set_cpus_allowed)(struct task_struct *p,
				 const struct cpumask *newmask);

	void (*rq_online)(struct rq *rq);
	void (*rq_offline)(struct rq *rq);
#endif

	void (*set_curr_task) (struct rq *rq);
	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
	void (*task_fork) (struct task_struct *p);
1208
	void (*task_dead) (struct task_struct *p);
1209

1210 1211 1212 1213 1214
	/*
	 * The switched_from() call is allowed to drop rq->lock, therefore we
	 * cannot assume the switched_from/switched_to pair is serliazed by
	 * rq->lock. They are however serialized by p->pi_lock.
	 */
1215 1216 1217 1218 1219 1220 1221 1222
	void (*switched_from) (struct rq *this_rq, struct task_struct *task);
	void (*switched_to) (struct rq *this_rq, struct task_struct *task);
	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
			     int oldprio);

	unsigned int (*get_rr_interval) (struct rq *rq,
					 struct task_struct *task);

1223 1224
	void (*update_curr) (struct rq *rq);

1225
#ifdef CONFIG_FAIR_GROUP_SCHED
1226
	void (*task_move_group) (struct task_struct *p);
1227 1228
#endif
};
1229

1230 1231 1232 1233 1234
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
	prev->sched_class->put_prev_task(rq, prev);
}

1235 1236 1237 1238 1239
#define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
   for (class = sched_class_highest; class; class = class->next)

extern const struct sched_class stop_sched_class;
1240
extern const struct sched_class dl_sched_class;
1241 1242 1243 1244 1245 1246 1247
extern const struct sched_class rt_sched_class;
extern const struct sched_class fair_sched_class;
extern const struct sched_class idle_sched_class;


#ifdef CONFIG_SMP

1248
extern void update_group_capacity(struct sched_domain *sd, int cpu);
1249

1250
extern void trigger_load_balance(struct rq *rq);
1251

1252 1253 1254
extern void idle_enter_fair(struct rq *this_rq);
extern void idle_exit_fair(struct rq *this_rq);

1255 1256
extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask);

P
Peter Zijlstra 已提交
1257 1258 1259 1260 1261
#else

static inline void idle_enter_fair(struct rq *rq) { }
static inline void idle_exit_fair(struct rq *rq) { }

1262 1263
#endif

1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287
#ifdef CONFIG_CPU_IDLE
static inline void idle_set_state(struct rq *rq,
				  struct cpuidle_state *idle_state)
{
	rq->idle_state = idle_state;
}

static inline struct cpuidle_state *idle_get_state(struct rq *rq)
{
	WARN_ON(!rcu_read_lock_held());
	return rq->idle_state;
}
#else
static inline void idle_set_state(struct rq *rq,
				  struct cpuidle_state *idle_state)
{
}

static inline struct cpuidle_state *idle_get_state(struct rq *rq)
{
	return NULL;
}
#endif

1288 1289 1290
extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
1291 1292

extern void init_sched_dl_class(void);
1293 1294 1295
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);

1296
extern void resched_curr(struct rq *rq);
1297 1298 1299 1300 1301
extern void resched_cpu(int cpu);

extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);

1302 1303
extern struct dl_bandwidth def_dl_bandwidth;
extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
1304 1305
extern void init_dl_task_timer(struct sched_dl_entity *dl_se);

1306 1307
unsigned long to_ratio(u64 period, u64 runtime);

1308
extern void init_entity_runnable_average(struct sched_entity *se);
1309

1310
static inline void add_nr_running(struct rq *rq, unsigned count)
1311
{
1312 1313 1314
	unsigned prev_nr = rq->nr_running;

	rq->nr_running = prev_nr + count;
1315

1316
	if (prev_nr < 2 && rq->nr_running >= 2) {
1317 1318 1319 1320 1321 1322
#ifdef CONFIG_SMP
		if (!rq->rd->overload)
			rq->rd->overload = true;
#endif

#ifdef CONFIG_NO_HZ_FULL
1323
		if (tick_nohz_full_cpu(rq->cpu)) {
1324 1325 1326 1327 1328 1329 1330 1331
			/*
			 * Tick is needed if more than one task runs on a CPU.
			 * Send the target an IPI to kick it out of nohz mode.
			 *
			 * We assume that IPI implies full memory barrier and the
			 * new value of rq->nr_running is visible on reception
			 * from the target.
			 */
1332
			tick_nohz_full_kick_cpu(rq->cpu);
1333 1334
		}
#endif
1335
	}
1336 1337
}

1338
static inline void sub_nr_running(struct rq *rq, unsigned count)
1339
{
1340
	rq->nr_running -= count;
1341 1342
}

1343 1344 1345 1346 1347 1348 1349
static inline void rq_last_tick_reset(struct rq *rq)
{
#ifdef CONFIG_NO_HZ_FULL
	rq->last_sched_tick = jiffies;
#endif
}

1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383
extern void update_rq_clock(struct rq *rq);

extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);

extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);

extern const_debug unsigned int sysctl_sched_time_avg;
extern const_debug unsigned int sysctl_sched_nr_migrate;
extern const_debug unsigned int sysctl_sched_migration_cost;

static inline u64 sched_avg_period(void)
{
	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
}

#ifdef CONFIG_SCHED_HRTICK

/*
 * Use hrtick when:
 *  - enabled by features
 *  - hrtimer is actually high res
 */
static inline int hrtick_enabled(struct rq *rq)
{
	if (!sched_feat(HRTICK))
		return 0;
	if (!cpu_active(cpu_of(rq)))
		return 0;
	return hrtimer_is_hres_active(&rq->hrtick_timer);
}

void hrtick_start(struct rq *rq, u64 delay);

1384 1385 1386 1387 1388 1389 1390
#else

static inline int hrtick_enabled(struct rq *rq)
{
	return 0;
}

1391 1392 1393 1394
#endif /* CONFIG_SCHED_HRTICK */

#ifdef CONFIG_SMP
extern void sched_avg_update(struct rq *rq);
1395 1396 1397 1398 1399 1400 1401 1402

#ifndef arch_scale_freq_capacity
static __always_inline
unsigned long arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
{
	return SCHED_CAPACITY_SCALE;
}
#endif
1403

1404 1405 1406 1407
#ifndef arch_scale_cpu_capacity
static __always_inline
unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
{
1408
	if (sd && (sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
1409 1410 1411 1412 1413 1414
		return sd->smt_gain / sd->span_weight;

	return SCHED_CAPACITY_SCALE;
}
#endif

1415 1416
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
1417
	rq->rt_avg += rt_delta * arch_scale_freq_capacity(NULL, cpu_of(rq));
1418 1419 1420 1421 1422 1423 1424
	sched_avg_update(rq);
}
#else
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
static inline void sched_avg_update(struct rq *rq) { }
#endif

1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437
/*
 * __task_rq_lock - lock the rq @p resides on.
 */
static inline struct rq *__task_rq_lock(struct task_struct *p)
	__acquires(rq->lock)
{
	struct rq *rq;

	lockdep_assert_held(&p->pi_lock);

	for (;;) {
		rq = task_rq(p);
		raw_spin_lock(&rq->lock);
1438 1439
		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
			lockdep_pin_lock(&rq->lock);
1440
			return rq;
1441
		}
1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
		raw_spin_unlock(&rq->lock);

		while (unlikely(task_on_rq_migrating(p)))
			cpu_relax();
	}
}

/*
 * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
 */
static inline struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags)
	__acquires(p->pi_lock)
	__acquires(rq->lock)
{
	struct rq *rq;

	for (;;) {
		raw_spin_lock_irqsave(&p->pi_lock, *flags);
		rq = task_rq(p);
		raw_spin_lock(&rq->lock);
		/*
		 *	move_queued_task()		task_rq_lock()
		 *
		 *	ACQUIRE (rq->lock)
		 *	[S] ->on_rq = MIGRATING		[L] rq = task_rq()
		 *	WMB (__set_task_cpu())		ACQUIRE (rq->lock);
		 *	[S] ->cpu = new_cpu		[L] task_rq()
		 *					[L] ->on_rq
		 *	RELEASE (rq->lock)
		 *
		 * If we observe the old cpu in task_rq_lock, the acquire of
		 * the old rq->lock will fully serialize against the stores.
		 *
		 * If we observe the new cpu in task_rq_lock, the acquire will
		 * pair with the WMB to ensure we must then also see migrating.
		 */
1478 1479
		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
			lockdep_pin_lock(&rq->lock);
1480
			return rq;
1481
		}
1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492
		raw_spin_unlock(&rq->lock);
		raw_spin_unlock_irqrestore(&p->pi_lock, *flags);

		while (unlikely(task_on_rq_migrating(p)))
			cpu_relax();
	}
}

static inline void __task_rq_unlock(struct rq *rq)
	__releases(rq->lock)
{
1493
	lockdep_unpin_lock(&rq->lock);
1494 1495 1496 1497 1498 1499 1500 1501
	raw_spin_unlock(&rq->lock);
}

static inline void
task_rq_unlock(struct rq *rq, struct task_struct *p, unsigned long *flags)
	__releases(rq->lock)
	__releases(p->pi_lock)
{
1502
	lockdep_unpin_lock(&rq->lock);
1503 1504 1505 1506
	raw_spin_unlock(&rq->lock);
	raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
}

1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582
#ifdef CONFIG_SMP
#ifdef CONFIG_PREEMPT

static inline void double_rq_lock(struct rq *rq1, struct rq *rq2);

/*
 * fair double_lock_balance: Safely acquires both rq->locks in a fair
 * way at the expense of forcing extra atomic operations in all
 * invocations.  This assures that the double_lock is acquired using the
 * same underlying policy as the spinlock_t on this architecture, which
 * reduces latency compared to the unfair variant below.  However, it
 * also adds more overhead and therefore may reduce throughput.
 */
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	raw_spin_unlock(&this_rq->lock);
	double_rq_lock(this_rq, busiest);

	return 1;
}

#else
/*
 * Unfair double_lock_balance: Optimizes throughput at the expense of
 * latency by eliminating extra atomic operations when the locks are
 * already in proper order on entry.  This favors lower cpu-ids and will
 * grant the double lock to lower cpus over higher ids under contention,
 * regardless of entry order into the function.
 */
static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	int ret = 0;

	if (unlikely(!raw_spin_trylock(&busiest->lock))) {
		if (busiest < this_rq) {
			raw_spin_unlock(&this_rq->lock);
			raw_spin_lock(&busiest->lock);
			raw_spin_lock_nested(&this_rq->lock,
					      SINGLE_DEPTH_NESTING);
			ret = 1;
		} else
			raw_spin_lock_nested(&busiest->lock,
					      SINGLE_DEPTH_NESTING);
	}
	return ret;
}

#endif /* CONFIG_PREEMPT */

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 */
static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
{
	if (unlikely(!irqs_disabled())) {
		/* printk() doesn't work good under rq->lock */
		raw_spin_unlock(&this_rq->lock);
		BUG_ON(1);
	}

	return _double_lock_balance(this_rq, busiest);
}

static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
	__releases(busiest->lock)
{
	raw_spin_unlock(&busiest->lock);
	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
}

1583 1584 1585 1586 1587 1588 1589 1590 1591
static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
{
	if (l1 > l2)
		swap(l1, l2);

	spin_lock(l1);
	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}

1592 1593 1594 1595 1596 1597 1598 1599 1600
static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2)
{
	if (l1 > l2)
		swap(l1, l2);

	spin_lock_irq(l1);
	spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}

1601 1602 1603 1604 1605 1606 1607 1608 1609
static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2)
{
	if (l1 > l2)
		swap(l1, l2);

	raw_spin_lock(l1);
	raw_spin_lock_nested(l2, SINGLE_DEPTH_NESTING);
}

1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688
/*
 * double_rq_lock - safely lock two runqueues
 *
 * Note this does not disable interrupts like task_rq_lock,
 * you need to do so manually before calling.
 */
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
	__acquires(rq1->lock)
	__acquires(rq2->lock)
{
	BUG_ON(!irqs_disabled());
	if (rq1 == rq2) {
		raw_spin_lock(&rq1->lock);
		__acquire(rq2->lock);	/* Fake it out ;) */
	} else {
		if (rq1 < rq2) {
			raw_spin_lock(&rq1->lock);
			raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
		} else {
			raw_spin_lock(&rq2->lock);
			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
		}
	}
}

/*
 * double_rq_unlock - safely unlock two runqueues
 *
 * Note this does not restore interrupts like task_rq_unlock,
 * you need to do so manually after calling.
 */
static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
	__releases(rq1->lock)
	__releases(rq2->lock)
{
	raw_spin_unlock(&rq1->lock);
	if (rq1 != rq2)
		raw_spin_unlock(&rq2->lock);
	else
		__release(rq2->lock);
}

#else /* CONFIG_SMP */

/*
 * double_rq_lock - safely lock two runqueues
 *
 * Note this does not disable interrupts like task_rq_lock,
 * you need to do so manually before calling.
 */
static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
	__acquires(rq1->lock)
	__acquires(rq2->lock)
{
	BUG_ON(!irqs_disabled());
	BUG_ON(rq1 != rq2);
	raw_spin_lock(&rq1->lock);
	__acquire(rq2->lock);	/* Fake it out ;) */
}

/*
 * double_rq_unlock - safely unlock two runqueues
 *
 * Note this does not restore interrupts like task_rq_unlock,
 * you need to do so manually after calling.
 */
static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
	__releases(rq1->lock)
	__releases(rq2->lock)
{
	BUG_ON(rq1 != rq2);
	raw_spin_unlock(&rq1->lock);
	__release(rq2->lock);
}

#endif

extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
1689 1690

#ifdef	CONFIG_SCHED_DEBUG
1691 1692
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);
1693
extern void print_dl_stats(struct seq_file *m, int cpu);
1694 1695
extern void
print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq);
1696 1697 1698 1699 1700 1701 1702 1703 1704

#ifdef CONFIG_NUMA_BALANCING
extern void
show_numa_stats(struct task_struct *p, struct seq_file *m);
extern void
print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
	unsigned long tpf, unsigned long gsf, unsigned long gpf);
#endif /* CONFIG_NUMA_BALANCING */
#endif /* CONFIG_SCHED_DEBUG */
1705 1706

extern void init_cfs_rq(struct cfs_rq *cfs_rq);
1707 1708
extern void init_rt_rq(struct rt_rq *rt_rq);
extern void init_dl_rq(struct dl_rq *dl_rq);
1709

1710 1711
extern void cfs_bandwidth_usage_inc(void);
extern void cfs_bandwidth_usage_dec(void);
1712

1713
#ifdef CONFIG_NO_HZ_COMMON
1714 1715 1716 1717 1718 1719 1720
enum rq_nohz_flag_bits {
	NOHZ_TICK_STOPPED,
	NOHZ_BALANCE_KICK,
};

#define nohz_flags(cpu)	(&cpu_rq(cpu)->nohz_flags)
#endif
1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769

#ifdef CONFIG_IRQ_TIME_ACCOUNTING

DECLARE_PER_CPU(u64, cpu_hardirq_time);
DECLARE_PER_CPU(u64, cpu_softirq_time);

#ifndef CONFIG_64BIT
DECLARE_PER_CPU(seqcount_t, irq_time_seq);

static inline void irq_time_write_begin(void)
{
	__this_cpu_inc(irq_time_seq.sequence);
	smp_wmb();
}

static inline void irq_time_write_end(void)
{
	smp_wmb();
	__this_cpu_inc(irq_time_seq.sequence);
}

static inline u64 irq_time_read(int cpu)
{
	u64 irq_time;
	unsigned seq;

	do {
		seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
		irq_time = per_cpu(cpu_softirq_time, cpu) +
			   per_cpu(cpu_hardirq_time, cpu);
	} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));

	return irq_time;
}
#else /* CONFIG_64BIT */
static inline void irq_time_write_begin(void)
{
}

static inline void irq_time_write_end(void)
{
}

static inline u64 irq_time_read(int cpu)
{
	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
}
#endif /* CONFIG_64BIT */
#endif /* CONFIG_IRQ_TIME_ACCOUNTING */