sched.h 40.0 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/tick.h>
10
#include <linux/slab.h>
11

12
#include "cpupri.h"
13
#include "cpudeadline.h"
14
#include "cpuacct.h"
15

16 17
struct rq;

18 19
extern __read_mostly int scheduler_running;

20 21 22 23 24 25
extern unsigned long calc_load_update;
extern atomic_long_t calc_load_tasks;

extern long calc_load_fold_active(struct rq *this_rq);
extern void update_cpu_load_active(struct rq *this_rq);

26 27 28 29 30
/*
 * Helpers for converting nanosecond timing to jiffy resolution
 */
#define NS_TO_JIFFIES(TIME)	((unsigned long)(TIME) / (NSEC_PER_SEC / HZ))

31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55
/*
 * 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)

56 57 58
#define NICE_0_LOAD		SCHED_LOAD_SCALE
#define NICE_0_SHIFT		SCHED_LOAD_SHIFT

59 60 61 62 63 64 65
/*
 * Single value that decides SCHED_DEADLINE internal math precision.
 * 10 -> just above 1us
 * 9  -> just above 0.5us
 */
#define DL_SCALE (10)

66 67 68 69 70 71 72 73 74
/*
 * These are the 'tuning knobs' of the scheduler:
 */

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

75 76 77 78 79
static inline int fair_policy(int policy)
{
	return policy == SCHED_NORMAL || policy == SCHED_BATCH;
}

80 81
static inline int rt_policy(int policy)
{
82
	return policy == SCHED_FIFO || policy == SCHED_RR;
83 84
}

85 86 87 88 89
static inline int dl_policy(int policy)
{
	return policy == SCHED_DEADLINE;
}

90 91 92 93 94
static inline int task_has_rt_policy(struct task_struct *p)
{
	return rt_policy(p->policy);
}

95 96 97 98 99
static inline int task_has_dl_policy(struct task_struct *p)
{
	return dl_policy(p->policy);
}

100
static inline bool dl_time_before(u64 a, u64 b)
101 102 103 104 105 106 107
{
	return (s64)(a - b) < 0;
}

/*
 * Tells if entity @a should preempt entity @b.
 */
108 109
static inline bool
dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
110 111 112 113
{
	return dl_time_before(a->deadline, b->deadline);
}

114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
/*
 * 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;
};
129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
/*
 * 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)
{
161
	return sysctl_sched_rt_runtime >= 0;
162 163 164 165 166 167 168 169 170
}

extern struct dl_bw *dl_bw_of(int i);

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

171 172 173 174 175 176 177 178 179
extern struct mutex sched_domains_mutex;

#ifdef CONFIG_CGROUP_SCHED

#include <linux/cgroup.h>

struct cfs_rq;
struct rt_rq;

180
extern struct list_head task_groups;
181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210

struct cfs_bandwidth {
#ifdef CONFIG_CFS_BANDWIDTH
	raw_spinlock_t lock;
	ktime_t period;
	u64 quota, runtime;
	s64 hierarchal_quota;
	u64 runtime_expires;

	int idle, timer_active;
	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;

211
#ifdef	CONFIG_SMP
212
	atomic_long_t load_avg;
213
	atomic_t runnable_avg;
214
#endif
215
#endif
216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280

#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);
281
extern void __start_cfs_bandwidth(struct cfs_bandwidth *cfs_b, bool force);
282 283 284 285 286 287 288 289
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);

290 291 292 293 294 295 296 297 298 299 300 301
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

302 303 304 305 306 307 308 309 310
#else /* CONFIG_CGROUP_SCHED */

struct cfs_bandwidth { };

#endif	/* CONFIG_CGROUP_SCHED */

/* CFS-related fields in a runqueue */
struct cfs_rq {
	struct load_weight load;
311
	unsigned int nr_running, h_nr_running;
312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331

	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

332 333 334 335 336 337 338
#ifdef CONFIG_SMP
	/*
	 * CFS Load tracking
	 * Under CFS, load is tracked on a per-entity basis and aggregated up.
	 * This allows for the description of both thread and group usage (in
	 * the FAIR_GROUP_SCHED case).
	 */
339
	unsigned long runnable_load_avg, blocked_load_avg;
340
	atomic64_t decay_counter;
341
	u64 last_decay;
342
	atomic_long_t removed_load;
343

344
#ifdef CONFIG_FAIR_GROUP_SCHED
345
	/* Required to track per-cpu representation of a task_group */
346
	u32 tg_runnable_contrib;
347
	unsigned long tg_load_contrib;
348 349 350 351 352 353 354 355

	/*
	 *   h_load = weight * f(tg)
	 *
	 * Where f(tg) is the recursive weight fraction assigned to
	 * this group.
	 */
	unsigned long h_load;
356 357 358
	u64 last_h_load_update;
	struct sched_entity *h_load_next;
#endif /* CONFIG_FAIR_GROUP_SCHED */
359 360
#endif /* CONFIG_SMP */

361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
#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;

381 382
	u64 throttled_clock, throttled_clock_task;
	u64 throttled_clock_task_time;
383 384 385 386 387 388 389 390 391 392 393 394 395 396
	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;
}

/* Real-Time classes' related field in a runqueue: */
struct rt_rq {
	struct rt_prio_array active;
397
	unsigned int rt_nr_running;
398 399 400 401 402 403 404 405 406 407 408 409 410 411
#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;
#endif
412 413
	int rt_queued;

414 415 416 417 418 419 420 421 422 423 424 425 426 427
	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
};

428 429 430 431 432 433 434
/* 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;
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457

#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;
458 459
#else
	struct dl_bw dl_bw;
460
#endif
461 462
};

463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
#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;

480 481 482
	/* Indicate more than one runnable task for any CPU */
	bool overload;

483 484 485 486 487 488
	/*
	 * 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;
489
	struct dl_bw dl_bw;
490
	struct cpudl cpudl;
491

492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518
	/*
	 * 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.
	 */
519
	unsigned int nr_running;
520 521 522 523
#ifdef CONFIG_NUMA_BALANCING
	unsigned int nr_numa_running;
	unsigned int nr_preferred_running;
#endif
524 525 526
	#define CPU_LOAD_IDX_MAX 5
	unsigned long cpu_load[CPU_LOAD_IDX_MAX];
	unsigned long last_load_update_tick;
527
#ifdef CONFIG_NO_HZ_COMMON
528
	u64 nohz_stamp;
529
	unsigned long nohz_flags;
530 531 532
#endif
#ifdef CONFIG_NO_HZ_FULL
	unsigned long last_sched_tick;
533 534 535 536 537 538 539 540 541 542
#endif
	int skip_clock_update;

	/* 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;
543
	struct dl_rq dl;
544 545 546 547

#ifdef CONFIG_FAIR_GROUP_SCHED
	/* list of leaf cfs_rq on this cpu: */
	struct list_head leaf_cfs_rq_list;
548 549

	struct sched_avg avg;
550 551
#endif /* CONFIG_FAIR_GROUP_SCHED */

552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572
	/*
	 * 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;

	u64 clock;
	u64 clock_task;

	atomic_t nr_iowait;

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

573
	unsigned long cpu_capacity;
574 575 576 577 578 579 580 581 582 583 584

	unsigned char idle_balance;
	/* For active balancing */
	int post_schedule;
	int active_balance;
	int push_cpu;
	struct cpu_stop_work active_balance_work;
	/* cpu of this runqueue: */
	int cpu;
	int online;

585 586
	struct list_head cfs_tasks;

587 588 589 590
	u64 rt_avg;
	u64 age_stamp;
	u64 idle_stamp;
	u64 avg_idle;
591 592 593

	/* This is used to determine avg_idle's max value */
	u64 max_idle_balance_cost;
594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651
#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
};

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

DECLARE_PER_CPU(struct rq, runqueues);

652 653 654 655 656 657
#define cpu_rq(cpu)		(&per_cpu(runqueues, (cpu)))
#define this_rq()		(&__get_cpu_var(runqueues))
#define task_rq(p)		cpu_rq(task_cpu(p))
#define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
#define raw_rq()		(&__raw_get_cpu_var(runqueues))

658 659 660 661 662 663 664 665 666 667
static inline u64 rq_clock(struct rq *rq)
{
	return rq->clock;
}

static inline u64 rq_clock_task(struct rq *rq)
{
	return rq->clock_task;
}

668
#ifdef CONFIG_NUMA_BALANCING
669
extern void sched_setnuma(struct task_struct *p, int node);
670
extern int migrate_task_to(struct task_struct *p, int cpu);
671
extern int migrate_swap(struct task_struct *, struct task_struct *);
672 673
#endif /* CONFIG_NUMA_BALANCING */

674 675
#ifdef CONFIG_SMP

676 677
extern void sched_ttwu_pending(void);

678 679 680 681 682 683 684 685 686 687 688 689
#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) \
690 691
	for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); \
			__sd; __sd = __sd->parent)
692

693 694
#define for_each_lower_domain(sd) for (; sd; sd = sd->child)

695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716
/**
 * 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;
}

717 718 719 720 721 722 723 724 725 726 727 728
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;
}

729
DECLARE_PER_CPU(struct sched_domain *, sd_llc);
730
DECLARE_PER_CPU(int, sd_llc_size);
731
DECLARE_PER_CPU(int, sd_llc_id);
732
DECLARE_PER_CPU(struct sched_domain *, sd_numa);
733 734
DECLARE_PER_CPU(struct sched_domain *, sd_busy);
DECLARE_PER_CPU(struct sched_domain *, sd_asym);
735

736
struct sched_group_capacity {
737 738
	atomic_t ref;
	/*
739 740
	 * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity
	 * for a single CPU.
741
	 */
742
	unsigned int capacity, capacity_orig;
743
	unsigned long next_update;
744
	int imbalance; /* XXX unrelated to capacity but shared group state */
745 746 747 748 749 750 751 752 753 754 755 756 757
	/*
	 * 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;
758
	struct sched_group_capacity *sgc;
759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780

	/*
	 * 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)
{
781
	return to_cpumask(sg->sgc->cpumask);
782 783 784 785 786 787 788 789 790 791 792
}

/**
 * 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
793 794
extern int group_balance_cpu(struct sched_group *sg);

795 796 797 798
#else

static inline void sched_ttwu_pending(void) { }

799
#endif /* CONFIG_SMP */
800

801 802
#include "stats.h"
#include "auto_group.h"
803 804 805 806 807 808

#ifdef CONFIG_CGROUP_SCHED

/*
 * Return the group to which this tasks belongs.
 *
809 810 811
 * 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
812 813 814 815 816 817
 *
 * 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.
818 819 820
 */
static inline struct task_group *task_group(struct task_struct *p)
{
P
Peter Zijlstra 已提交
821
	return p->sched_task_group;
822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862
}

/* 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;
863
	p->wake_cpu = cpu;
864 865 866 867 868 869 870
#endif
}

/*
 * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
 */
#ifdef CONFIG_SCHED_DEBUG
871
# include <linux/static_key.h>
872 873 874 875 876 877 878 879 880 881 882
# 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 {
883
#include "features.h"
884
	__SCHED_FEAT_NR,
885 886 887 888
};

#undef SCHED_FEAT

889 890
#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
#define SCHED_FEAT(name, enabled)					\
891
static __always_inline bool static_branch_##name(struct static_key *key) \
892
{									\
893
	return static_key_##enabled(key);				\
894 895 896 897 898 899
}

#include "features.h"

#undef SCHED_FEAT

900
extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
901 902
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
903
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
904
#endif /* SCHED_DEBUG && HAVE_JUMP_LABEL */
905

906 907
#ifdef CONFIG_NUMA_BALANCING
#define sched_feat_numa(x) sched_feat(x)
908 909 910 911 912
#ifdef CONFIG_SCHED_DEBUG
#define numabalancing_enabled sched_feat_numa(NUMA)
#else
extern bool numabalancing_enabled;
#endif /* CONFIG_SCHED_DEBUG */
913 914
#else
#define sched_feat_numa(x) (0)
915 916
#define numabalancing_enabled (0)
#endif /* CONFIG_NUMA_BALANCING */
917

918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
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
}


#ifndef prepare_arch_switch
# define prepare_arch_switch(next)	do { } while (0)
#endif
#ifndef finish_arch_switch
# define finish_arch_switch(prev)	do { } while (0)
#endif
952 953 954
#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch()	do { } while (0)
#endif
955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
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.
	 */
	smp_wmb();
	prev->on_cpu = 0;
#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);
}

#else /* __ARCH_WANT_UNLOCKED_CTXSW */
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
	raw_spin_unlock(&rq->lock);
}

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.
	 */
	smp_wmb();
	prev->on_cpu = 0;
#endif
	local_irq_enable();
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */

1023 1024 1025 1026 1027 1028 1029
/*
 * 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 */

1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082
/*
 * 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,
};

1083 1084 1085 1086 1087 1088 1089
#define ENQUEUE_WAKEUP		1
#define ENQUEUE_HEAD		2
#ifdef CONFIG_SMP
#define ENQUEUE_WAKING		4	/* sched_class::task_waking was called */
#else
#define ENQUEUE_WAKING		0
#endif
1090
#define ENQUEUE_REPLENISH	8
1091 1092 1093

#define DEQUEUE_SLEEP		1

1094 1095
#define RETRY_TASK		((void *)-1UL)

1096 1097 1098 1099 1100 1101 1102 1103 1104 1105
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);

1106 1107 1108 1109
	/*
	 * 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.
1110 1111 1112
	 *
	 * May return RETRY_TASK when it finds a higher prio class has runnable
	 * tasks.
1113 1114 1115
	 */
	struct task_struct * (*pick_next_task) (struct rq *rq,
						struct task_struct *prev);
1116 1117 1118
	void (*put_prev_task) (struct rq *rq, struct task_struct *p);

#ifdef CONFIG_SMP
1119
	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int sd_flag, int flags);
1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135
	void (*migrate_task_rq)(struct task_struct *p, int next_cpu);

	void (*post_schedule) (struct rq *this_rq);
	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);
1136
	void (*task_dead) (struct task_struct *p);
1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149

	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);

#ifdef CONFIG_FAIR_GROUP_SCHED
	void (*task_move_group) (struct task_struct *p, int on_rq);
#endif
};
1150

1151 1152 1153 1154 1155
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
	prev->sched_class->put_prev_task(rq, prev);
}

1156 1157 1158 1159 1160
#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;
1161
extern const struct sched_class dl_sched_class;
1162 1163 1164 1165 1166 1167 1168
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

1169
extern void update_group_capacity(struct sched_domain *sd, int cpu);
1170

1171
extern void trigger_load_balance(struct rq *rq);
1172

1173 1174 1175
extern void idle_enter_fair(struct rq *this_rq);
extern void idle_exit_fair(struct rq *this_rq);

P
Peter Zijlstra 已提交
1176 1177 1178 1179 1180
#else

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

1181 1182 1183 1184 1185
#endif

extern void sysrq_sched_debug_show(void);
extern void sched_init_granularity(void);
extern void update_max_interval(void);
1186 1187

extern void init_sched_dl_class(void);
1188 1189
extern void init_sched_rt_class(void);
extern void init_sched_fair_class(void);
1190
extern void init_sched_dl_class(void);
1191

1192
extern void resched_curr(struct rq *rq);
1193 1194 1195 1196 1197
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);

1198 1199
extern struct dl_bandwidth def_dl_bandwidth;
extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime);
1200 1201
extern void init_dl_task_timer(struct sched_dl_entity *dl_se);

1202 1203
unsigned long to_ratio(u64 period, u64 runtime);

1204
extern void update_idle_cpu_load(struct rq *this_rq);
1205

1206 1207
extern void init_task_runnable_average(struct task_struct *p);

1208
static inline void add_nr_running(struct rq *rq, unsigned count)
1209
{
1210 1211 1212
	unsigned prev_nr = rq->nr_running;

	rq->nr_running = prev_nr + count;
1213

1214
	if (prev_nr < 2 && rq->nr_running >= 2) {
1215 1216 1217 1218 1219 1220
#ifdef CONFIG_SMP
		if (!rq->rd->overload)
			rq->rd->overload = true;
#endif

#ifdef CONFIG_NO_HZ_FULL
1221
		if (tick_nohz_full_cpu(rq->cpu)) {
1222 1223 1224 1225 1226 1227 1228 1229
			/*
			 * 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.
			 */
1230
			tick_nohz_full_kick_cpu(rq->cpu);
1231 1232
		}
#endif
1233
	}
1234 1235
}

1236
static inline void sub_nr_running(struct rq *rq, unsigned count)
1237
{
1238
	rq->nr_running -= count;
1239 1240
}

1241 1242 1243 1244 1245 1246 1247
static inline void rq_last_tick_reset(struct rq *rq)
{
#ifdef CONFIG_NO_HZ_FULL
	rq->last_sched_tick = jiffies;
#endif
}

1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281
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);

1282 1283 1284 1285 1286 1287 1288
#else

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

1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 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
#endif /* CONFIG_SCHED_HRTICK */

#ifdef CONFIG_SMP
extern void sched_avg_update(struct rq *rq);
static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
{
	rq->rt_avg += rt_delta;
	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

extern void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period);

#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_);
}

1381 1382 1383 1384 1385 1386 1387 1388 1389
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);
}

1390 1391 1392 1393 1394 1395 1396 1397 1398
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);
}

1399 1400 1401 1402 1403 1404 1405 1406 1407
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);
}

1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 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 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491
/*
 * 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);
extern void print_cfs_stats(struct seq_file *m, int cpu);
extern void print_rt_stats(struct seq_file *m, int cpu);

extern void init_cfs_rq(struct cfs_rq *cfs_rq);
extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq);
1492
extern void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq);
1493

1494 1495
extern void cfs_bandwidth_usage_inc(void);
extern void cfs_bandwidth_usage_dec(void);
1496

1497
#ifdef CONFIG_NO_HZ_COMMON
1498 1499 1500 1501 1502 1503 1504
enum rq_nohz_flag_bits {
	NOHZ_TICK_STOPPED,
	NOHZ_BALANCE_KICK,
};

#define nohz_flags(cpu)	(&cpu_rq(cpu)->nohz_flags)
#endif
1505 1506 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

#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 */