sched.c 140 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
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
161
162
163
164
165
166
167
168
/*
 *  kernel/sched.c
 *
 *  Kernel scheduler and related syscalls
 *
 *  Copyright (C) 1991-2002  Linus Torvalds
 *
 *  1996-12-23  Modified by Dave Grothe to fix bugs in semaphores and
 *		make semaphores SMP safe
 *  1998-11-19	Implemented schedule_timeout() and related stuff
 *		by Andrea Arcangeli
 *  2002-01-04	New ultra-scalable O(1) scheduler by Ingo Molnar:
 *		hybrid priority-list and round-robin design with
 *		an array-switch method of distributing timeslices
 *		and per-CPU runqueues.  Cleanups and useful suggestions
 *		by Davide Libenzi, preemptible kernel bits by Robert Love.
 *  2003-09-03	Interactivity tuning by Con Kolivas.
 *  2004-04-02	Scheduler domains code by Nick Piggin
 */

#include <linux/mm.h>
#include <linux/module.h>
#include <linux/nmi.h>
#include <linux/init.h>
#include <asm/uaccess.h>
#include <linux/highmem.h>
#include <linux/smp_lock.h>
#include <asm/mmu_context.h>
#include <linux/interrupt.h>
#include <linux/completion.h>
#include <linux/kernel_stat.h>
#include <linux/security.h>
#include <linux/notifier.h>
#include <linux/profile.h>
#include <linux/suspend.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <linux/smp.h>
#include <linux/threads.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/percpu.h>
#include <linux/kthread.h>
#include <linux/seq_file.h>
#include <linux/syscalls.h>
#include <linux/times.h>
#include <linux/acct.h>
#include <asm/tlb.h>

#include <asm/unistd.h>

/*
 * Convert user-nice values [ -20 ... 0 ... 19 ]
 * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
 * and back.
 */
#define NICE_TO_PRIO(nice)	(MAX_RT_PRIO + (nice) + 20)
#define PRIO_TO_NICE(prio)	((prio) - MAX_RT_PRIO - 20)
#define TASK_NICE(p)		PRIO_TO_NICE((p)->static_prio)

/*
 * 'User priority' is the nice value converted to something we
 * can work with better when scaling various scheduler parameters,
 * it's a [ 0 ... 39 ] range.
 */
#define USER_PRIO(p)		((p)-MAX_RT_PRIO)
#define TASK_USER_PRIO(p)	USER_PRIO((p)->static_prio)
#define MAX_USER_PRIO		(USER_PRIO(MAX_PRIO))

/*
 * Some helpers for converting nanosecond timing to jiffy resolution
 */
#define NS_TO_JIFFIES(TIME)	((TIME) / (1000000000 / HZ))
#define JIFFIES_TO_NS(TIME)	((TIME) * (1000000000 / HZ))

/*
 * These are the 'tuning knobs' of the scheduler:
 *
 * Minimum timeslice is 5 msecs (or 1 jiffy, whichever is larger),
 * default timeslice is 100 msecs, maximum timeslice is 800 msecs.
 * Timeslices get refilled after they expire.
 */
#define MIN_TIMESLICE		max(5 * HZ / 1000, 1)
#define DEF_TIMESLICE		(100 * HZ / 1000)
#define ON_RUNQUEUE_WEIGHT	 30
#define CHILD_PENALTY		 95
#define PARENT_PENALTY		100
#define EXIT_WEIGHT		  3
#define PRIO_BONUS_RATIO	 25
#define MAX_BONUS		(MAX_USER_PRIO * PRIO_BONUS_RATIO / 100)
#define INTERACTIVE_DELTA	  2
#define MAX_SLEEP_AVG		(DEF_TIMESLICE * MAX_BONUS)
#define STARVATION_LIMIT	(MAX_SLEEP_AVG)
#define NS_MAX_SLEEP_AVG	(JIFFIES_TO_NS(MAX_SLEEP_AVG))

/*
 * If a task is 'interactive' then we reinsert it in the active
 * array after it has expired its current timeslice. (it will not
 * continue to run immediately, it will still roundrobin with
 * other interactive tasks.)
 *
 * This part scales the interactivity limit depending on niceness.
 *
 * We scale it linearly, offset by the INTERACTIVE_DELTA delta.
 * Here are a few examples of different nice levels:
 *
 *  TASK_INTERACTIVE(-20): [1,1,1,1,1,1,1,1,1,0,0]
 *  TASK_INTERACTIVE(-10): [1,1,1,1,1,1,1,0,0,0,0]
 *  TASK_INTERACTIVE(  0): [1,1,1,1,0,0,0,0,0,0,0]
 *  TASK_INTERACTIVE( 10): [1,1,0,0,0,0,0,0,0,0,0]
 *  TASK_INTERACTIVE( 19): [0,0,0,0,0,0,0,0,0,0,0]
 *
 * (the X axis represents the possible -5 ... 0 ... +5 dynamic
 *  priority range a task can explore, a value of '1' means the
 *  task is rated interactive.)
 *
 * Ie. nice +19 tasks can never get 'interactive' enough to be
 * reinserted into the active array. And only heavily CPU-hog nice -20
 * tasks will be expired. Default nice 0 tasks are somewhere between,
 * it takes some effort for them to get interactive, but it's not
 * too hard.
 */

#define CURRENT_BONUS(p) \
	(NS_TO_JIFFIES((p)->sleep_avg) * MAX_BONUS / \
		MAX_SLEEP_AVG)

#define GRANULARITY	(10 * HZ / 1000 ? : 1)

#ifdef CONFIG_SMP
#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)) * \
			num_online_cpus())
#else
#define TIMESLICE_GRANULARITY(p)	(GRANULARITY * \
		(1 << (((MAX_BONUS - CURRENT_BONUS(p)) ? : 1) - 1)))
#endif

#define SCALE(v1,v1_max,v2_max) \
	(v1) * (v2_max) / (v1_max)

#define DELTA(p) \
	(SCALE(TASK_NICE(p), 40, MAX_BONUS) + INTERACTIVE_DELTA)

#define TASK_INTERACTIVE(p) \
	((p)->prio <= (p)->static_prio - DELTA(p))

#define INTERACTIVE_SLEEP(p) \
	(JIFFIES_TO_NS(MAX_SLEEP_AVG * \
		(MAX_BONUS / 2 + DELTA((p)) + 1) / MAX_BONUS - 1))

#define TASK_PREEMPTS_CURR(p, rq) \
	((p)->prio < (rq)->curr->prio)

/*
 * task_timeslice() scales user-nice values [ -20 ... 0 ... 19 ]
 * to time slice values: [800ms ... 100ms ... 5ms]
 *
 * The higher a thread's priority, the bigger timeslices
 * it gets during one round of execution. But even the lowest
 * priority thread gets MIN_TIMESLICE worth of execution time.
 */

#define SCALE_PRIO(x, prio) \
	max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO/2), MIN_TIMESLICE)

169
static unsigned int task_timeslice(task_t *p)
Linus Torvalds's avatar
Linus Torvalds committed
170
171
172
173
174
175
176
177
178
179
180
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
{
	if (p->static_prio < NICE_TO_PRIO(0))
		return SCALE_PRIO(DEF_TIMESLICE*4, p->static_prio);
	else
		return SCALE_PRIO(DEF_TIMESLICE, p->static_prio);
}
#define task_hot(p, now, sd) ((long long) ((now) - (p)->last_ran)	\
				< (long long) (sd)->cache_hot_time)

/*
 * These are the runqueue data structures:
 */

#define BITMAP_SIZE ((((MAX_PRIO+1+7)/8)+sizeof(long)-1)/sizeof(long))

typedef struct runqueue runqueue_t;

struct prio_array {
	unsigned int nr_active;
	unsigned long bitmap[BITMAP_SIZE];
	struct list_head queue[MAX_PRIO];
};

/*
 * 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 runqueue {
	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.
	 */
	unsigned long nr_running;
#ifdef CONFIG_SMP
Nick Piggin's avatar
Nick Piggin committed
209
	unsigned long cpu_load[3];
Linus Torvalds's avatar
Linus Torvalds committed
210
211
212
213
214
215
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
#endif
	unsigned long long nr_switches;

	/*
	 * 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;

	unsigned long expired_timestamp;
	unsigned long long timestamp_last_tick;
	task_t *curr, *idle;
	struct mm_struct *prev_mm;
	prio_array_t *active, *expired, arrays[2];
	int best_expired_prio;
	atomic_t nr_iowait;

#ifdef CONFIG_SMP
	struct sched_domain *sd;

	/* For active balancing */
	int active_balance;
	int push_cpu;

	task_t *migration_thread;
	struct list_head migration_queue;
#endif

#ifdef CONFIG_SCHEDSTATS
	/* latency stats */
	struct sched_info rq_sched_info;

	/* sys_sched_yield() stats */
	unsigned long yld_exp_empty;
	unsigned long yld_act_empty;
	unsigned long yld_both_empty;
	unsigned long yld_cnt;

	/* schedule() stats */
	unsigned long sched_switch;
	unsigned long sched_cnt;
	unsigned long sched_goidle;

	/* try_to_wake_up() stats */
	unsigned long ttwu_cnt;
	unsigned long ttwu_local;
#endif
};

static DEFINE_PER_CPU(struct runqueue, runqueues);

Nick Piggin's avatar
Nick Piggin committed
263
264
/*
 * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
265
 * See detach_destroy_domains: synchronize_sched for details.
Nick Piggin's avatar
Nick Piggin committed
266
267
268
269
 *
 * The domain tree of any CPU may only be accessed from within
 * preempt-disabled sections.
 */
Linus Torvalds's avatar
Linus Torvalds committed
270
#define for_each_domain(cpu, domain) \
Nick Piggin's avatar
Nick Piggin committed
271
for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent)
Linus Torvalds's avatar
Linus Torvalds committed
272
273
274
275
276
277
278

#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)

#ifndef prepare_arch_switch
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
# define prepare_arch_switch(next)	do { } while (0)
#endif
#ifndef finish_arch_switch
# define finish_arch_switch(prev)	do { } while (0)
#endif

#ifndef __ARCH_WANT_UNLOCKED_CTXSW
static inline int task_running(runqueue_t *rq, task_t *p)
{
	return rq->curr == p;
}

static inline void prepare_lock_switch(runqueue_t *rq, task_t *next)
{
}

static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
{
297
298
299
300
#ifdef CONFIG_DEBUG_SPINLOCK
	/* this is a valid case when another task releases the spinlock */
	rq->lock.owner = current;
#endif
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
	spin_unlock_irq(&rq->lock);
}

#else /* __ARCH_WANT_UNLOCKED_CTXSW */
static inline int task_running(runqueue_t *rq, task_t *p)
{
#ifdef CONFIG_SMP
	return p->oncpu;
#else
	return rq->curr == p;
#endif
}

static inline void prepare_lock_switch(runqueue_t *rq, task_t *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->oncpu = 1;
#endif
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
	spin_unlock_irq(&rq->lock);
#else
	spin_unlock(&rq->lock);
#endif
}

static inline void finish_lock_switch(runqueue_t *rq, task_t *prev)
{
#ifdef CONFIG_SMP
	/*
	 * After ->oncpu 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->oncpu = 0;
#endif
#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW
	local_irq_enable();
Linus Torvalds's avatar
Linus Torvalds committed
344
#endif
345
346
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
Linus Torvalds's avatar
Linus Torvalds committed
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379

/*
 * task_rq_lock - lock the runqueue a given task resides on and disable
 * interrupts.  Note the ordering: we can safely lookup the task_rq without
 * explicitly disabling preemption.
 */
static inline runqueue_t *task_rq_lock(task_t *p, unsigned long *flags)
	__acquires(rq->lock)
{
	struct runqueue *rq;

repeat_lock_task:
	local_irq_save(*flags);
	rq = task_rq(p);
	spin_lock(&rq->lock);
	if (unlikely(rq != task_rq(p))) {
		spin_unlock_irqrestore(&rq->lock, *flags);
		goto repeat_lock_task;
	}
	return rq;
}

static inline void task_rq_unlock(runqueue_t *rq, unsigned long *flags)
	__releases(rq->lock)
{
	spin_unlock_irqrestore(&rq->lock, *flags);
}

#ifdef CONFIG_SCHEDSTATS
/*
 * bump this up when changing the output format or the meaning of an existing
 * format, so that tools can adapt (or abort)
 */
380
#define SCHEDSTAT_VERSION 12
Linus Torvalds's avatar
Linus Torvalds committed
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408

static int show_schedstat(struct seq_file *seq, void *v)
{
	int cpu;

	seq_printf(seq, "version %d\n", SCHEDSTAT_VERSION);
	seq_printf(seq, "timestamp %lu\n", jiffies);
	for_each_online_cpu(cpu) {
		runqueue_t *rq = cpu_rq(cpu);
#ifdef CONFIG_SMP
		struct sched_domain *sd;
		int dcnt = 0;
#endif

		/* runqueue-specific stats */
		seq_printf(seq,
		    "cpu%d %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu",
		    cpu, rq->yld_both_empty,
		    rq->yld_act_empty, rq->yld_exp_empty, rq->yld_cnt,
		    rq->sched_switch, rq->sched_cnt, rq->sched_goidle,
		    rq->ttwu_cnt, rq->ttwu_local,
		    rq->rq_sched_info.cpu_time,
		    rq->rq_sched_info.run_delay, rq->rq_sched_info.pcnt);

		seq_printf(seq, "\n");

#ifdef CONFIG_SMP
		/* domain-specific stats */
Nick Piggin's avatar
Nick Piggin committed
409
		preempt_disable();
Linus Torvalds's avatar
Linus Torvalds committed
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
		for_each_domain(cpu, sd) {
			enum idle_type itype;
			char mask_str[NR_CPUS];

			cpumask_scnprintf(mask_str, NR_CPUS, sd->span);
			seq_printf(seq, "domain%d %s", dcnt++, mask_str);
			for (itype = SCHED_IDLE; itype < MAX_IDLE_TYPES;
					itype++) {
				seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu",
				    sd->lb_cnt[itype],
				    sd->lb_balanced[itype],
				    sd->lb_failed[itype],
				    sd->lb_imbalance[itype],
				    sd->lb_gained[itype],
				    sd->lb_hot_gained[itype],
				    sd->lb_nobusyq[itype],
				    sd->lb_nobusyg[itype]);
			}
428
			seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
Linus Torvalds's avatar
Linus Torvalds committed
429
			    sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
430
431
			    sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
			    sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
Linus Torvalds's avatar
Linus Torvalds committed
432
433
			    sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance);
		}
Nick Piggin's avatar
Nick Piggin committed
434
		preempt_enable();
Linus Torvalds's avatar
Linus Torvalds committed
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
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
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
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
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
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
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
#endif
	}
	return 0;
}

static int schedstat_open(struct inode *inode, struct file *file)
{
	unsigned int size = PAGE_SIZE * (1 + num_online_cpus() / 32);
	char *buf = kmalloc(size, GFP_KERNEL);
	struct seq_file *m;
	int res;

	if (!buf)
		return -ENOMEM;
	res = single_open(file, show_schedstat, NULL);
	if (!res) {
		m = file->private_data;
		m->buf = buf;
		m->size = size;
	} else
		kfree(buf);
	return res;
}

struct file_operations proc_schedstat_operations = {
	.open    = schedstat_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = single_release,
};

# define schedstat_inc(rq, field)	do { (rq)->field++; } while (0)
# define schedstat_add(rq, field, amt)	do { (rq)->field += (amt); } while (0)
#else /* !CONFIG_SCHEDSTATS */
# define schedstat_inc(rq, field)	do { } while (0)
# define schedstat_add(rq, field, amt)	do { } while (0)
#endif

/*
 * rq_lock - lock a given runqueue and disable interrupts.
 */
static inline runqueue_t *this_rq_lock(void)
	__acquires(rq->lock)
{
	runqueue_t *rq;

	local_irq_disable();
	rq = this_rq();
	spin_lock(&rq->lock);

	return rq;
}

#ifdef CONFIG_SCHEDSTATS
/*
 * Called when a process is dequeued from the active array and given
 * the cpu.  We should note that with the exception of interactive
 * tasks, the expired queue will become the active queue after the active
 * queue is empty, without explicitly dequeuing and requeuing tasks in the
 * expired queue.  (Interactive tasks may be requeued directly to the
 * active queue, thus delaying tasks in the expired queue from running;
 * see scheduler_tick()).
 *
 * This function is only called from sched_info_arrive(), rather than
 * dequeue_task(). Even though a task may be queued and dequeued multiple
 * times as it is shuffled about, we're really interested in knowing how
 * long it was from the *first* time it was queued to the time that it
 * finally hit a cpu.
 */
static inline void sched_info_dequeued(task_t *t)
{
	t->sched_info.last_queued = 0;
}

/*
 * Called when a task finally hits the cpu.  We can now calculate how
 * long it was waiting to run.  We also note when it began so that we
 * can keep stats on how long its timeslice is.
 */
static inline void sched_info_arrive(task_t *t)
{
	unsigned long now = jiffies, diff = 0;
	struct runqueue *rq = task_rq(t);

	if (t->sched_info.last_queued)
		diff = now - t->sched_info.last_queued;
	sched_info_dequeued(t);
	t->sched_info.run_delay += diff;
	t->sched_info.last_arrival = now;
	t->sched_info.pcnt++;

	if (!rq)
		return;

	rq->rq_sched_info.run_delay += diff;
	rq->rq_sched_info.pcnt++;
}

/*
 * Called when a process is queued into either the active or expired
 * array.  The time is noted and later used to determine how long we
 * had to wait for us to reach the cpu.  Since the expired queue will
 * become the active queue after active queue is empty, without dequeuing
 * and requeuing any tasks, we are interested in queuing to either. It
 * is unusual but not impossible for tasks to be dequeued and immediately
 * requeued in the same or another array: this can happen in sched_yield(),
 * set_user_nice(), and even load_balance() as it moves tasks from runqueue
 * to runqueue.
 *
 * This function is only called from enqueue_task(), but also only updates
 * the timestamp if it is already not set.  It's assumed that
 * sched_info_dequeued() will clear that stamp when appropriate.
 */
static inline void sched_info_queued(task_t *t)
{
	if (!t->sched_info.last_queued)
		t->sched_info.last_queued = jiffies;
}

/*
 * Called when a process ceases being the active-running process, either
 * voluntarily or involuntarily.  Now we can calculate how long we ran.
 */
static inline void sched_info_depart(task_t *t)
{
	struct runqueue *rq = task_rq(t);
	unsigned long diff = jiffies - t->sched_info.last_arrival;

	t->sched_info.cpu_time += diff;

	if (rq)
		rq->rq_sched_info.cpu_time += diff;
}

/*
 * Called when tasks are switched involuntarily due, typically, to expiring
 * their time slice.  (This may also be called when switching to or from
 * the idle task.)  We are only called when prev != next.
 */
static inline void sched_info_switch(task_t *prev, task_t *next)
{
	struct runqueue *rq = task_rq(prev);

	/*
	 * prev now departs the cpu.  It's not interesting to record
	 * stats about how efficient we were at scheduling the idle
	 * process, however.
	 */
	if (prev != rq->idle)
		sched_info_depart(prev);

	if (next != rq->idle)
		sched_info_arrive(next);
}
#else
#define sched_info_queued(t)		do { } while (0)
#define sched_info_switch(t, next)	do { } while (0)
#endif /* CONFIG_SCHEDSTATS */

/*
 * Adding/removing a task to/from a priority array:
 */
static void dequeue_task(struct task_struct *p, prio_array_t *array)
{
	array->nr_active--;
	list_del(&p->run_list);
	if (list_empty(array->queue + p->prio))
		__clear_bit(p->prio, array->bitmap);
}

static void enqueue_task(struct task_struct *p, prio_array_t *array)
{
	sched_info_queued(p);
	list_add_tail(&p->run_list, array->queue + p->prio);
	__set_bit(p->prio, array->bitmap);
	array->nr_active++;
	p->array = array;
}

/*
 * Put task to the end of the run list without the overhead of dequeue
 * followed by enqueue.
 */
static void requeue_task(struct task_struct *p, prio_array_t *array)
{
	list_move_tail(&p->run_list, array->queue + p->prio);
}

static inline void enqueue_task_head(struct task_struct *p, prio_array_t *array)
{
	list_add(&p->run_list, array->queue + p->prio);
	__set_bit(p->prio, array->bitmap);
	array->nr_active++;
	p->array = array;
}

/*
 * effective_prio - return the priority that is based on the static
 * priority but is modified by bonuses/penalties.
 *
 * We scale the actual sleep average [0 .... MAX_SLEEP_AVG]
 * into the -5 ... 0 ... +5 bonus/penalty range.
 *
 * We use 25% of the full 0...39 priority range so that:
 *
 * 1) nice +19 interactive tasks do not preempt nice 0 CPU hogs.
 * 2) nice -20 CPU hogs do not get preempted by nice 0 tasks.
 *
 * Both properties are important to certain workloads.
 */
static int effective_prio(task_t *p)
{
	int bonus, prio;

	if (rt_task(p))
		return p->prio;

	bonus = CURRENT_BONUS(p) - MAX_BONUS / 2;

	prio = p->static_prio - bonus;
	if (prio < MAX_RT_PRIO)
		prio = MAX_RT_PRIO;
	if (prio > MAX_PRIO-1)
		prio = MAX_PRIO-1;
	return prio;
}

/*
 * __activate_task - move a task to the runqueue.
 */
static inline void __activate_task(task_t *p, runqueue_t *rq)
{
	enqueue_task(p, rq->active);
	rq->nr_running++;
}

/*
 * __activate_idle_task - move idle task to the _front_ of runqueue.
 */
static inline void __activate_idle_task(task_t *p, runqueue_t *rq)
{
	enqueue_task_head(p, rq->active);
	rq->nr_running++;
}

680
static int recalc_task_prio(task_t *p, unsigned long long now)
Linus Torvalds's avatar
Linus Torvalds committed
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
{
	/* Caller must always ensure 'now >= p->timestamp' */
	unsigned long long __sleep_time = now - p->timestamp;
	unsigned long sleep_time;

	if (__sleep_time > NS_MAX_SLEEP_AVG)
		sleep_time = NS_MAX_SLEEP_AVG;
	else
		sleep_time = (unsigned long)__sleep_time;

	if (likely(sleep_time > 0)) {
		/*
		 * User tasks that sleep a long time are categorised as
		 * idle and will get just interactive status to stay active &
		 * prevent them suddenly becoming cpu hogs and starving
		 * other processes.
		 */
		if (p->mm && p->activated != -1 &&
			sleep_time > INTERACTIVE_SLEEP(p)) {
				p->sleep_avg = JIFFIES_TO_NS(MAX_SLEEP_AVG -
						DEF_TIMESLICE);
		} else {
			/*
			 * The lower the sleep avg a task has the more
			 * rapidly it will rise with sleep time.
			 */
			sleep_time *= (MAX_BONUS - CURRENT_BONUS(p)) ? : 1;

			/*
			 * Tasks waking from uninterruptible sleep are
			 * limited in their sleep_avg rise as they
			 * are likely to be waiting on I/O
			 */
			if (p->activated == -1 && p->mm) {
				if (p->sleep_avg >= INTERACTIVE_SLEEP(p))
					sleep_time = 0;
				else if (p->sleep_avg + sleep_time >=
						INTERACTIVE_SLEEP(p)) {
					p->sleep_avg = INTERACTIVE_SLEEP(p);
					sleep_time = 0;
				}
			}

			/*
			 * This code gives a bonus to interactive tasks.
			 *
			 * The boost works by updating the 'average sleep time'
			 * value here, based on ->timestamp. The more time a
			 * task spends sleeping, the higher the average gets -
			 * and the higher the priority boost gets as well.
			 */
			p->sleep_avg += sleep_time;

			if (p->sleep_avg > NS_MAX_SLEEP_AVG)
				p->sleep_avg = NS_MAX_SLEEP_AVG;
		}
	}

739
	return effective_prio(p);
Linus Torvalds's avatar
Linus Torvalds committed
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
}

/*
 * activate_task - move a task to the runqueue and do priority recalculation
 *
 * Update all the scheduling statistics stuff. (sleep average
 * calculation, priority modifiers, etc.)
 */
static void activate_task(task_t *p, runqueue_t *rq, int local)
{
	unsigned long long now;

	now = sched_clock();
#ifdef CONFIG_SMP
	if (!local) {
		/* Compensate for drifting sched_clock */
		runqueue_t *this_rq = this_rq();
		now = (now - this_rq->timestamp_last_tick)
			+ rq->timestamp_last_tick;
	}
#endif

762
	p->prio = recalc_task_prio(p, now);
Linus Torvalds's avatar
Linus Torvalds committed
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
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
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881

	/*
	 * This checks to make sure it's not an uninterruptible task
	 * that is now waking up.
	 */
	if (!p->activated) {
		/*
		 * Tasks which were woken up by interrupts (ie. hw events)
		 * are most likely of interactive nature. So we give them
		 * the credit of extending their sleep time to the period
		 * of time they spend on the runqueue, waiting for execution
		 * on a CPU, first time around:
		 */
		if (in_interrupt())
			p->activated = 2;
		else {
			/*
			 * Normal first-time wakeups get a credit too for
			 * on-runqueue time, but it will be weighted down:
			 */
			p->activated = 1;
		}
	}
	p->timestamp = now;

	__activate_task(p, rq);
}

/*
 * deactivate_task - remove a task from the runqueue.
 */
static void deactivate_task(struct task_struct *p, runqueue_t *rq)
{
	rq->nr_running--;
	dequeue_task(p, p->array);
	p->array = NULL;
}

/*
 * resched_task - mark a task 'to be rescheduled now'.
 *
 * On UP this means the setting of the need_resched flag, on SMP it
 * might also involve a cross-CPU call to trigger the scheduler on
 * the target CPU.
 */
#ifdef CONFIG_SMP
static void resched_task(task_t *p)
{
	int need_resched, nrpolling;

	assert_spin_locked(&task_rq(p)->lock);

	/* minimise the chance of sending an interrupt to poll_idle() */
	nrpolling = test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);
	need_resched = test_and_set_tsk_thread_flag(p,TIF_NEED_RESCHED);
	nrpolling |= test_tsk_thread_flag(p,TIF_POLLING_NRFLAG);

	if (!need_resched && !nrpolling && (task_cpu(p) != smp_processor_id()))
		smp_send_reschedule(task_cpu(p));
}
#else
static inline void resched_task(task_t *p)
{
	set_tsk_need_resched(p);
}
#endif

/**
 * task_curr - is this task currently executing on a CPU?
 * @p: the task in question.
 */
inline int task_curr(const task_t *p)
{
	return cpu_curr(task_cpu(p)) == p;
}

#ifdef CONFIG_SMP
typedef struct {
	struct list_head list;

	task_t *task;
	int dest_cpu;

	struct completion done;
} migration_req_t;

/*
 * The task's runqueue lock must be held.
 * Returns true if you have to wait for migration thread.
 */
static int migrate_task(task_t *p, int dest_cpu, migration_req_t *req)
{
	runqueue_t *rq = task_rq(p);

	/*
	 * If the task is not on a runqueue (and not running), then
	 * it is sufficient to simply update the task's cpu field.
	 */
	if (!p->array && !task_running(rq, p)) {
		set_task_cpu(p, dest_cpu);
		return 0;
	}

	init_completion(&req->done);
	req->task = p;
	req->dest_cpu = dest_cpu;
	list_add(&req->list, &rq->migration_queue);
	return 1;
}

/*
 * wait_task_inactive - wait for a thread to unschedule.
 *
 * The caller must ensure that the task *will* unschedule sometime soon,
 * else this function might spin for a *long* time. This function can't
 * be called with interrupts off, or it may introduce deadlock with
 * smp_call_function() if an IPI is sent by the same process we are
 * waiting to become inactive.
 */
Ingo Molnar's avatar
Ingo Molnar committed
882
void wait_task_inactive(task_t *p)
Linus Torvalds's avatar
Linus Torvalds committed
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
{
	unsigned long flags;
	runqueue_t *rq;
	int preempted;

repeat:
	rq = task_rq_lock(p, &flags);
	/* Must be off runqueue entirely, not preempted. */
	if (unlikely(p->array || task_running(rq, p))) {
		/* If it's preempted, we yield.  It could be a while. */
		preempted = !task_running(rq, p);
		task_rq_unlock(rq, &flags);
		cpu_relax();
		if (preempted)
			yield();
		goto repeat;
	}
	task_rq_unlock(rq, &flags);
}

/***
 * kick_process - kick a running thread to enter/exit the kernel
 * @p: the to-be-kicked thread
 *
 * Cause a process which is running on another CPU to enter
 * kernel-mode, without any delay. (to get signals handled.)
 *
 * NOTE: this function doesnt have to take the runqueue lock,
 * because all it wants to ensure is that the remote task enters
 * the kernel. If the IPI races and the task has been migrated
 * to another CPU then no harm is done and the purpose has been
 * achieved as well.
 */
void kick_process(task_t *p)
{
	int cpu;

	preempt_disable();
	cpu = task_cpu(p);
	if ((cpu != smp_processor_id()) && task_curr(p))
		smp_send_reschedule(cpu);
	preempt_enable();
}

/*
 * Return a low guess at the load of a migration-source cpu.
 *
 * We want to under-estimate the load of migration sources, to
 * balance conservatively.
 */
Nick Piggin's avatar
Nick Piggin committed
933
static inline unsigned long source_load(int cpu, int type)
Linus Torvalds's avatar
Linus Torvalds committed
934
935
936
{
	runqueue_t *rq = cpu_rq(cpu);
	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
Nick Piggin's avatar
Nick Piggin committed
937
938
	if (type == 0)
		return load_now;
Linus Torvalds's avatar
Linus Torvalds committed
939

Nick Piggin's avatar
Nick Piggin committed
940
	return min(rq->cpu_load[type-1], load_now);
Linus Torvalds's avatar
Linus Torvalds committed
941
942
943
944
945
}

/*
 * Return a high guess at the load of a migration-target cpu
 */
Nick Piggin's avatar
Nick Piggin committed
946
static inline unsigned long target_load(int cpu, int type)
Linus Torvalds's avatar
Linus Torvalds committed
947
948
949
{
	runqueue_t *rq = cpu_rq(cpu);
	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
Nick Piggin's avatar
Nick Piggin committed
950
951
	if (type == 0)
		return load_now;
Linus Torvalds's avatar
Linus Torvalds committed
952

Nick Piggin's avatar
Nick Piggin committed
953
	return max(rq->cpu_load[type-1], load_now);
Linus Torvalds's avatar
Linus Torvalds committed
954
955
}

Nick Piggin's avatar
Nick Piggin committed
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
/*
 * find_idlest_group finds and returns the least busy CPU group within the
 * domain.
 */
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
{
	struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
	unsigned long min_load = ULONG_MAX, this_load = 0;
	int load_idx = sd->forkexec_idx;
	int imbalance = 100 + (sd->imbalance_pct-100)/2;

	do {
		unsigned long load, avg_load;
		int local_group;
		int i;

973
974
975
976
		/* Skip over this group if it has no CPUs allowed */
		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
			goto nextgroup;

Nick Piggin's avatar
Nick Piggin committed
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
		local_group = cpu_isset(this_cpu, group->cpumask);

		/* Tally up the load of all CPUs in the group */
		avg_load = 0;

		for_each_cpu_mask(i, group->cpumask) {
			/* Bias balancing toward cpus of our domain */
			if (local_group)
				load = source_load(i, load_idx);
			else
				load = target_load(i, load_idx);

			avg_load += load;
		}

		/* Adjust by relative CPU power of the group */
		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;

		if (local_group) {
			this_load = avg_load;
			this = group;
		} else if (avg_load < min_load) {
			min_load = avg_load;
			idlest = group;
		}
1002
nextgroup:
Nick Piggin's avatar
Nick Piggin committed
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
		group = group->next;
	} while (group != sd->groups);

	if (!idlest || 100*this_load < imbalance*min_load)
		return NULL;
	return idlest;
}

/*
 * find_idlest_queue - find the idlest runqueue among the cpus in group.
 */
Ingo Molnar's avatar
Ingo Molnar committed
1014
1015
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
Nick Piggin's avatar
Nick Piggin committed
1016
{
1017
	cpumask_t tmp;
Nick Piggin's avatar
Nick Piggin committed
1018
1019
1020
1021
	unsigned long load, min_load = ULONG_MAX;
	int idlest = -1;
	int i;

1022
1023
1024
1025
	/* Traverse only the allowed CPUs */
	cpus_and(tmp, group->cpumask, p->cpus_allowed);

	for_each_cpu_mask(i, tmp) {
Nick Piggin's avatar
Nick Piggin committed
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
		load = source_load(i, 0);

		if (load < min_load || (load == min_load && i == this_cpu)) {
			min_load = load;
			idlest = i;
		}
	}

	return idlest;
}

1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
/*
 * sched_balance_self: balance the current task (running on cpu) in domains
 * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
 * SD_BALANCE_EXEC.
 *
 * Balance, ie. select the least loaded group.
 *
 * Returns the target CPU number, or the same CPU if no balancing is needed.
 *
 * preempt must be disabled.
 */
static int sched_balance_self(int cpu, int flag)
{
	struct task_struct *t = current;
	struct sched_domain *tmp, *sd = NULL;
Nick Piggin's avatar
Nick Piggin committed
1052

1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
	for_each_domain(cpu, tmp)
		if (tmp->flags & flag)
			sd = tmp;

	while (sd) {
		cpumask_t span;
		struct sched_group *group;
		int new_cpu;
		int weight;

		span = sd->span;
		group = find_idlest_group(sd, t, cpu);
		if (!group)
			goto nextlevel;

1068
		new_cpu = find_idlest_cpu(group, t, cpu);
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
		if (new_cpu == -1 || new_cpu == cpu)
			goto nextlevel;

		/* Now try balancing at a lower domain level */
		cpu = new_cpu;
nextlevel:
		sd = NULL;
		weight = cpus_weight(span);
		for_each_domain(cpu, tmp) {
			if (weight <= cpus_weight(tmp->span))
				break;
			if (tmp->flags & flag)
				sd = tmp;
		}
		/* while loop will break here if sd == NULL */
	}

	return cpu;
}

#endif /* CONFIG_SMP */
Linus Torvalds's avatar
Linus Torvalds committed
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110

/*
 * wake_idle() will wake a task on an idle cpu if task->cpu is
 * not idle and an idle cpu is available.  The span of cpus to
 * search starts with cpus closest then further out as needed,
 * so we always favor a closer, idle cpu.
 *
 * Returns the CPU we should wake onto.
 */
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, task_t *p)
{
	cpumask_t tmp;
	struct sched_domain *sd;
	int i;

	if (idle_cpu(cpu))
		return cpu;

	for_each_domain(cpu, sd) {
		if (sd->flags & SD_WAKE_IDLE) {
Nick Piggin's avatar
Nick Piggin committed
1111
			cpus_and(tmp, sd->span, p->cpus_allowed);
Linus Torvalds's avatar
Linus Torvalds committed
1112
1113
1114
1115
1116
			for_each_cpu_mask(i, tmp) {
				if (idle_cpu(i))
					return i;
			}
		}
Nick Piggin's avatar
Nick Piggin committed
1117
1118
		else
			break;
Linus Torvalds's avatar
Linus Torvalds committed
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
	}
	return cpu;
}
#else
static inline int wake_idle(int cpu, task_t *p)
{
	return cpu;
}
#endif

/***
 * try_to_wake_up - wake up a thread
 * @p: the to-be-woken-up thread
 * @state: the mask of task states that can be woken
 * @sync: do a synchronous wakeup?
 *
 * Put it on the run-queue if it's not already there. The "current"
 * thread is always on the run-queue (except when the actual
 * re-schedule is in progress), and as such you're allowed to do
 * the simpler "current->state = TASK_RUNNING" to mark yourself
 * runnable without the overhead of this.
 *
 * returns failure only if the task is already active.
 */
Ingo Molnar's avatar
Ingo Molnar committed
1143
static int try_to_wake_up(task_t *p, unsigned int state, int sync)
Linus Torvalds's avatar
Linus Torvalds committed
1144
1145
1146
1147
1148
1149
1150
{
	int cpu, this_cpu, success = 0;
	unsigned long flags;
	long old_state;
	runqueue_t *rq;
#ifdef CONFIG_SMP
	unsigned long load, this_load;
Nick Piggin's avatar
Nick Piggin committed
1151
	struct sched_domain *sd, *this_sd = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
	int new_cpu;
#endif

	rq = task_rq_lock(p, &flags);
	old_state = p->state;
	if (!(old_state & state))
		goto out;

	if (p->array)
		goto out_running;

	cpu = task_cpu(p);
	this_cpu = smp_processor_id();

#ifdef CONFIG_SMP
	if (unlikely(task_running(rq, p)))
		goto out_activate;

Nick Piggin's avatar
Nick Piggin committed
1170
1171
	new_cpu = cpu;

Linus Torvalds's avatar
Linus Torvalds committed
1172
1173
1174
	schedstat_inc(rq, ttwu_cnt);
	if (cpu == this_cpu) {
		schedstat_inc(rq, ttwu_local);
Nick Piggin's avatar
Nick Piggin committed
1175
1176
1177
1178
1179
1180
1181
1182
		goto out_set_cpu;
	}

	for_each_domain(this_cpu, sd) {
		if (cpu_isset(cpu, sd->span)) {
			schedstat_inc(sd, ttwu_wake_remote);
			this_sd = sd;
			break;
Linus Torvalds's avatar
Linus Torvalds committed
1183
1184
1185
		}
	}

Nick Piggin's avatar
Nick Piggin committed
1186
	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
Linus Torvalds's avatar
Linus Torvalds committed
1187
1188
1189
		goto out_set_cpu;

	/*
Nick Piggin's avatar
Nick Piggin committed
1190
	 * Check for affine wakeup and passive balancing possibilities.
Linus Torvalds's avatar
Linus Torvalds committed
1191
	 */
Nick Piggin's avatar
Nick Piggin committed
1192
1193
1194
	if (this_sd) {
		int idx = this_sd->wake_idx;
		unsigned int imbalance;
Linus Torvalds's avatar
Linus Torvalds committed
1195

1196
1197
		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;

Nick Piggin's avatar
Nick Piggin committed
1198
1199
		load = source_load(cpu, idx);
		this_load = target_load(this_cpu, idx);
Linus Torvalds's avatar
Linus Torvalds committed
1200

Nick Piggin's avatar
Nick Piggin committed
1201
1202
		new_cpu = this_cpu; /* Wake to this CPU if we can */

1203
1204
		if (this_sd->flags & SD_WAKE_AFFINE) {
			unsigned long tl = this_load;
Linus Torvalds's avatar
Linus Torvalds committed
1205
			/*
1206
1207
1208
			 * If sync wakeup then subtract the (maximum possible)
			 * effect of the currently running task from the load
			 * of the current CPU:
Linus Torvalds's avatar
Linus Torvalds committed
1209
			 */
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
			if (sync)
				tl -= SCHED_LOAD_SCALE;

			if ((tl <= load &&
				tl + target_load(cpu, idx) <= SCHED_LOAD_SCALE) ||
				100*(tl + SCHED_LOAD_SCALE) <= imbalance*load) {
				/*
				 * This domain has SD_WAKE_AFFINE and
				 * p is cache cold in this domain, and
				 * there is no bad imbalance.
				 */
				schedstat_inc(this_sd, ttwu_move_affine);
				goto out_set_cpu;
			}
		}

		/*
		 * Start passive balancing when half the imbalance_pct
		 * limit is reached.
		 */
		if (this_sd->flags & SD_WAKE_BALANCE) {
			if (imbalance*this_load <= 100*load) {
				schedstat_inc(this_sd, ttwu_move_balance);
				goto out_set_cpu;
			}
Linus Torvalds's avatar
Linus Torvalds committed
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
		}
	}

	new_cpu = cpu; /* Could not wake to this_cpu. Wake to cpu instead */
out_set_cpu:
	new_cpu = wake_idle(new_cpu, p);
	if (new_cpu != cpu) {
		set_task_cpu(p, new_cpu);
		task_rq_unlock(rq, &flags);
		/* might preempt at this point */
		rq = task_rq_lock(p, &flags);
		old_state = p->state;
		if (!(old_state & state))
			goto out;
		if (p->array)
			goto out_running;

		this_cpu = smp_processor_id();
		cpu = task_cpu(p);
	}

out_activate:
#endif /* CONFIG_SMP */
	if (old_state == TASK_UNINTERRUPTIBLE) {
		rq->nr_uninterruptible--;
		/*
		 * Tasks on involuntary sleep don't earn
		 * sleep_avg beyond just interactive state.
		 */
		p->activated = -1;
	}

1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
	/*
	 * Tasks that have marked their sleep as noninteractive get
	 * woken up without updating their sleep average. (i.e. their
	 * sleep is handled in a priority-neutral manner, no priority
	 * boost and no penalty.)
	 */
	if (old_state & TASK_NONINTERACTIVE)
		__activate_task(p, rq);
	else
		activate_task(p, rq, cpu == this_cpu);
Linus Torvalds's avatar
Linus Torvalds committed
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
	/*
	 * Sync wakeups (i.e. those types of wakeups where the waker
	 * has indicated that it will leave the CPU in short order)
	 * don't trigger a preemption, if the woken up task will run on
	 * this cpu. (in this case the 'I will reschedule' promise of
	 * the waker guarantees that the freshly woken up task is going
	 * to be considered on this CPU.)
	 */
	if (!sync || cpu != this_cpu) {
		if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);
	}
	success = 1;

out_running:
	p->state = TASK_RUNNING;
out:
	task_rq_unlock(rq, &flags);

	return success;
}

Ingo Molnar's avatar
Ingo Molnar committed
1299
int fastcall wake_up_process(task_t *p)
Linus Torvalds's avatar
Linus Torvalds committed
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
{
	return try_to_wake_up(p, TASK_STOPPED | TASK_TRACED |
				 TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE, 0);
}

EXPORT_SYMBOL(wake_up_process);

int fastcall wake_up_state(task_t *p, unsigned int state)
{
	return try_to_wake_up(p, state, 0);
}

/*
 * Perform scheduler related setup for a newly forked process p.
 * p is forked by current.
 */
1316
void fastcall sched_fork(task_t *p, int clone_flags)
Linus Torvalds's avatar
Linus Torvalds committed
1317
{
1318
1319
1320
1321
1322
1323
1324
	int cpu = get_cpu();

#ifdef CONFIG_SMP
	cpu = sched_balance_self(cpu, SD_BALANCE_FORK);
#endif
	set_task_cpu(p, cpu);

Linus Torvalds's avatar
Linus Torvalds committed
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
	/*
	 * We mark the process as running here, but have not actually
	 * inserted it onto the runqueue yet. This guarantees that
	 * nobody will actually run it, and a signal or other external
	 * event cannot wake it up and insert it on the runqueue either.
	 */
	p->state = TASK_RUNNING;
	INIT_LIST_HEAD(&p->run_list);
	p->array = NULL;
#ifdef CONFIG_SCHEDSTATS
	memset(&p->sched_info, 0, sizeof(p->sched_info));
#endif
1337
1338
1339
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
	p->oncpu = 0;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
1340
#ifdef CONFIG_PREEMPT
1341
	/* Want to start with kernel preemption disabled. */
Linus Torvalds's avatar
Linus Torvalds committed
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
	p->thread_info->preempt_count = 1;
#endif
	/*
	 * Share the timeslice between parent and child, thus the
	 * total amount of pending timeslices in the system doesn't change,
	 * resulting in more scheduling fairness.
	 */
	local_irq_disable();
	p->time_slice = (current->time_slice + 1) >> 1;
	/*
	 * The remainder of the first timeslice might be recovered by
	 * the parent if the child exits early enough.
	 */
	p->first_time_slice = 1;
	current->time_slice >>= 1;
	p->timestamp = sched_clock();
	if (unlikely(!current->time_slice)) {
		/*
		 * This case is rare, it happens when the parent has only
		 * a single jiffy left from its timeslice. Taking the
		 * runqueue lock is not a problem.
		 */
		current->time_slice = 1;
		scheduler_tick();
1366
1367
1368
	}
	local_irq_enable();
	put_cpu();
Linus Torvalds's avatar
Linus Torvalds committed
1369
1370
1371
1372
1373
1374
1375
1376
1377
}

/*
 * wake_up_new_task - wake up a newly created task for the first time.
 *
 * This function will do some initial scheduler statistics housekeeping
 * that must be done for every newly created context, then puts the task
 * on the runqueue and wakes it.
 */
Ingo Molnar's avatar
Ingo Molnar committed
1378
void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags)
Linus Torvalds's avatar
Linus Torvalds committed
1379
1380
1381
1382
1383
1384
{
	unsigned long flags;
	int this_cpu, cpu;
	runqueue_t *rq, *this_rq;

	rq = task_rq_lock(p, &flags);
Nick Piggin's avatar
Nick Piggin committed
1385
	BUG_ON(p->state != TASK_RUNNING);
Linus Torvalds's avatar
Linus Torvalds committed
1386
	this_cpu = smp_processor_id();
Nick Piggin's avatar
Nick Piggin committed
1387
	cpu = task_cpu(p);
Linus Torvalds's avatar
Linus Torvalds committed
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
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

	/*
	 * We decrease the sleep average of forking parents
	 * and children as well, to keep max-interactive tasks
	 * from forking tasks that are max-interactive. The parent
	 * (current) is done further down, under its lock.
	 */
	p->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(p) *
		CHILD_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);

	p->prio = effective_prio(p);

	if (likely(cpu == this_cpu)) {
		if (!(clone_flags & CLONE_VM)) {
			/*
			 * The VM isn't cloned, so we're in a good position to
			 * do child-runs-first in anticipation of an exec. This
			 * usually avoids a lot of COW overhead.
			 */
			if (unlikely(!current->array))
				__activate_task(p, rq);
			else {
				p->prio = current->prio;
				list_add_tail(&p->run_list, &current->run_list);
				p->array = current->array;
				p->array->nr_active++;
				rq->nr_running++;
			}
			set_need_resched();
		} else
			/* Run child last */
			__activate_task(p, rq);
		/*
		 * We skip the following code due to cpu == this_cpu
	 	 *
		 *   task_rq_unlock(rq, &flags);
		 *   this_rq = task_rq_lock(current, &flags);
		 */
		this_rq = rq;
	} else {
		this_rq = cpu_rq(this_cpu);

		/*
		 * Not the local CPU - must adjust timestamp. This should
		 * get optimised away in the !CONFIG_SMP case.
		 */
		p->timestamp = (p->timestamp - this_rq->timestamp_last_tick)
					+ rq->timestamp_last_tick;
		__activate_task(p, rq);
		if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);

		/*
		 * Parent and child are on different CPUs, now get the
		 * parent runqueue to update the parent's ->sleep_avg:
		 */
		task_rq_unlock(rq, &flags);
		this_rq = task_rq_lock(current, &flags);
	}
	current->sleep_avg = JIFFIES_TO_NS(CURRENT_BONUS(current) *
		PARENT_PENALTY / 100 * MAX_SLEEP_AVG / MAX_BONUS);
	task_rq_unlock(this_rq, &flags);
}

/*
 * Potentially available exiting-child timeslices are
 * retrieved here - this way the parent does not get
 * penalized for creating too many threads.
 *
 * (this cannot be used to 'generate' timeslices
 * artificially, because any timeslice recovered here
 * was given away by the parent in the first place.)
 */
Ingo Molnar's avatar
Ingo Molnar committed
1461
void fastcall sched_exit(task_t *p)
Linus Torvalds's avatar
Linus Torvalds committed
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
{
	unsigned long flags;
	runqueue_t *rq;

	/*
	 * If the child was a (relative-) CPU hog then decrease
	 * the sleep_avg of the parent as well.
	 */
	rq = task_rq_lock(p->parent, &flags);
	if (p->first_time_slice) {
		p->parent->time_slice += p->time_slice;
		if (unlikely(p->parent->time_slice > task_timeslice(p)))
			p->parent->time_slice = task_timeslice(p);
	}
	if (p->sleep_avg < p->parent->sleep_avg)
		p->parent->sleep_avg = p->parent->sleep_avg /
		(EXIT_WEIGHT + 1) * EXIT_WEIGHT + p->sleep_avg /
		(EXIT_WEIGHT + 1);
	task_rq_unlock(rq, &flags);
}

1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
/**
 * prepare_task_switch - prepare to switch tasks
 * @rq: the runqueue preparing to switch
 * @next: the task we are going to switch to.
 *
 * This is called with the rq lock held and interrupts off. It must
 * be paired with a subsequent finish_task_switch after the context
 * switch.
 *
 * prepare_task_switch sets up locking and calls architecture specific
 * hooks.
 */
static inline void prepare_task_switch(runqueue_t *rq, task_t *next)
{
	prepare_lock_switch(rq, next);
	prepare_arch_switch(next);
}

Linus Torvalds's avatar
Linus Torvalds committed
1501
1502
/**
 * finish_task_switch - clean up after a task-switch
1503
 * @rq: runqueue associated with task-switch
Linus Torvalds's avatar
Linus Torvalds committed
1504
1505
 * @prev: the thread we just switched away from.
 *
1506
1507
1508
1509
 * finish_task_switch must be called after the context switch, paired
 * with a prepare_task_switch call before the context switch.
 * finish_task_switch will reconcile locking set up by prepare_task_switch,
 * and do any other architecture-specific cleanup actions.
Linus Torvalds's avatar
Linus Torvalds committed
1510
1511
1512
1513
1514
1515
 *
 * Note that we may have delayed dropping an mm in context_switch(). If
 * so, we finish that here outside of the runqueue lock.  (Doing it
 * with the lock held can cause deadlocks; see schedule() for
 * details.)
 */
1516
static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
Linus Torvalds's avatar
Linus Torvalds committed
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
	__releases(rq->lock)
{
	struct mm_struct *mm = rq->prev_mm;
	unsigned long prev_task_flags;

	rq->prev_mm = NULL;

	/*
	 * A task struct has one reference for the use as "current".
	 * If a task dies, then it sets EXIT_ZOMBIE in tsk->exit_state and
	 * calls schedule one last time. The schedule call will never return,
	 * and the scheduled task must drop that reference.
	 * The test for EXIT_ZOMBIE must occur while the runqueue locks are
	 * still held, otherwise prev could be scheduled on another cpu, die
	 * there before we look at prev->state, and then the reference would
	 * be dropped twice.
	 *		Manfred Spraul <manfred@colorfullife.com>
	 */
	prev_task_flags = prev->flags;
1536
1537
	finish_arch_switch(prev);
	finish_lock_switch(rq, prev);
Linus Torvalds's avatar
Linus Torvalds committed
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
	if (mm)
		mmdrop(mm);
	if (unlikely(prev_task_flags & PF_DEAD))
		put_task_struct(prev);
}

/**
 * schedule_tail - first thing a freshly forked thread must call.
 * @prev: the thread we just switched away from.
 */
asmlinkage void schedule_tail(task_t *prev)
	__releases(rq->lock)
{
1551
1552
1553
1554
1555
1556
	runqueue_t *rq = this_rq();
	finish_task_switch(rq, prev);
#ifdef __ARCH_WANT_UNLOCKED_CTXSW
	/* In this case, finish_task_switch does not reenable preemption */
	preempt_enable();
#endif
Linus Torvalds's avatar
Linus Torvalds committed
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
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
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
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
	if (current->set_child_tid)
		put_user(current->pid, current->set_child_tid);
}

/*
 * context_switch - switch to the new MM and the new
 * thread's register state.
 */
static inline
task_t * context_switch(runqueue_t *rq, task_t *prev, task_t *next)
{
	struct mm_struct *mm = next->mm;
	struct mm_struct *oldmm = prev->active_mm;

	if (unlikely(!mm)) {
		next->active_mm = oldmm;
		atomic_inc(&oldmm->mm_count);
		enter_lazy_tlb(oldmm, next);
	} else
		switch_mm(oldmm, mm, next);

	if (unlikely(!prev->mm)) {
		prev->active_mm = NULL;
		WARN_ON(rq->prev_mm);
		rq->prev_mm = oldmm;
	}

	/* Here we just switch the register state and the stack. */
	switch_to(prev, next, prev);

	return prev;
}

/*
 * nr_running, nr_uninterruptible and nr_context_switches:
 *
 * externally visible scheduler statistics: current number of runnable
 * threads, current number of uninterruptible-sleeping threads, total
 * number of context switches performed since bootup.
 */
unsigned long nr_running(void)
{
	unsigned long i, sum = 0;

	for_each_online_cpu(i)
		sum += cpu_rq(i)->nr_running;

	return sum;
}

unsigned long nr_uninterruptible(void)
{
	unsigned long i, sum = 0;

	for_each_cpu(i)
		sum += cpu_rq(i)->nr_uninterruptible;

	/*
	 * Since we read the counters lockless, it might be slightly
	 * inaccurate. Do not allow it to go below zero though:
	 */
	if (unlikely((long)sum < 0))
		sum = 0;

	return sum;
}

unsigned long long nr_context_switches(void)
{
	unsigned long long i, sum = 0;

	for_each_cpu(i)
		sum += cpu_rq(i)->nr_switches;

	return sum;
}

unsigned long nr_iowait(void)
{
	unsigned long i, sum = 0;

	for_each_cpu(i)
		sum += atomic_read(&cpu_rq(i)->nr_iowait);

	return sum;
}

#ifdef 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 void double_rq_lock(runqueue_t *rq1, runqueue_t *rq2)
	__acquires(rq1->lock)
	__acquires(rq2->lock)
{
	if (rq1 == rq2) {
		spin_lock(&rq1->lock);
		__acquire(rq2->lock);	/* Fake it out ;) */
	} else {
		if (rq1 < rq2) {
			spin_lock(&rq1->lock);
			spin_lock(&rq2->lock);
		} else {
			spin_lock(&rq2->lock);
			spin_lock(&rq1->lock);
		}
	}
}

/*
 * 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 void double_rq_unlock(runqueue_t *rq1, runqueue_t *rq2)
	__releases(rq1->lock)
	__releases(rq2->lock)
{
	spin_unlock(&rq1->lock);
	if (rq1 != rq2)
		spin_unlock(&rq2->lock);
	else
		__release(rq2->lock);
}

/*
 * double_lock_balance - lock the busiest runqueue, this_rq is locked already.
 */
static void double_lock_balance(runqueue_t *this_rq, runqueue_t *busiest)
	__releases(this_rq->lock)
	__acquires(busiest->lock)
	__acquires(this_rq->lock)
{
	if (unlikely(!spin_trylock(&busiest->lock))) {
		if (busiest < this_rq) {
			spin_unlock(&this_rq->lock);
			spin_lock(&busiest->lock);
			spin_lock(&this_rq->lock);
		} else
			spin_lock(&busiest->lock);
	}
}

/*
 * If dest_cpu is allowed for this process, migrate the task to it.
 * This is accomplished by forcing the cpu_allowed mask to only
 * allow dest_cpu, which will force the cpu onto dest_cpu.  Then
 * the cpu_allowed mask is restored.
 */
static void sched_migrate_task(task_t *p, int dest_cpu)
{
	migration_req_t req;
	runqueue_t *rq;
	unsigned long flags;

	rq = task_rq_lock(p, &flags);
	if (!cpu_isset(dest_cpu, p->cpus_allowed)
	    || unlikely(cpu_is_offline(dest_cpu)))
		goto out;

	/* force the process onto the specified CPU */
	if (migrate_task(p, dest_cpu, &req)) {
		/* Need to wait for migration thread (might exit: take ref). */
		struct task_struct *mt = rq->migration_thread;
		get_task_struct(mt);
		task_rq_unlock(rq, &flags);
		wake_up_process(mt);
		put_task_struct(mt);
		wait_for_completion(&req.done);
		return;
	}
out:
	task_rq_unlock(rq, &flags);
}

/*
1738
1739
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
Linus Torvalds's avatar
Linus Torvalds committed
1740
1741
1742
1743
 */
void sched_exec(void)
{
	int new_cpu, this_cpu = get_cpu();
1744
	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
Linus Torvalds's avatar
Linus Torvalds committed
1745
	put_cpu();
1746
1747
	if (new_cpu != this_cpu)
		sched_migrate_task(current, new_cpu);
Linus Torvalds's avatar
Linus Torvalds committed
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
}

/*
 * pull_task - move a task from a remote runqueue to the local runqueue.
 * Both runqueues must be locked.
 */
static inline
void pull_task(runqueue_t *src_rq, prio_array_t *src_array, task_t *p,
	       runqueue_t *this_rq, prio_array_t *this_array, int this_cpu)
{
	dequeue_task(p, src_array);
	src_rq->nr_running--;
	set_task_cpu(p, this_cpu);
	this_rq->nr_running++;
	enqueue_task(p, this_array);
	p->timestamp = (p->timestamp - src_rq->timestamp_last_tick)
				+ this_rq->timestamp_last_tick;
	/*
	 * Note that idle threads have a prio of MAX_PRIO, for this test
	 * to be always true for them.
	 */
	if (TASK_PREEMPTS_CURR(p, this_rq))
		resched_task(this_rq->curr);
}

/*
 * can_migrate_task - may task p from runqueue rq be migrated to this_cpu?
 */
static inline
int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu,
Ingo Molnar's avatar
Ingo Molnar committed
1778
1779
		     struct sched_domain *sd, enum idle_type idle,
		     int *all_pinned)
Linus Torvalds's avatar
Linus Torvalds committed
1780
1781
1782
1783
1784
1785
1786
1787
1788
{
	/*
	 * We do not migrate tasks that are:
	 * 1) running (obviously), or
	 * 2) cannot be migrated to this CPU due to cpus_allowed, or
	 * 3) are cache-hot on their current CPU.
	 */
	if (!cpu_isset(this_cpu, p->cpus_allowed))
		return 0;
1789
1790
1791
1792
	*all_pinned = 0;

	if (task_running(rq, p))
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed
1793
1794
1795

	/*
	 * Aggressive migration if:
1796
	 * 1) task is cache cold, or
Linus Torvalds's avatar
Linus Torvalds committed
1797
1798
1799
	 * 2) too many balance attempts have failed.
	 */

1800
	if (sd->nr_balance_failed > sd->cache_nice_tries)
Linus Torvalds's avatar
Linus Torvalds committed
1801
1802
1803
		return 1;

	if (task_hot(p, rq->timestamp_last_tick, sd))
1804
		return 0;
Linus Torvalds's avatar
Linus Torvalds committed
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
	return 1;
}

/*
 * move_tasks tries to move up to max_nr_move tasks from busiest to this_rq,
 * as part of a balancing operation within "domain". Returns the number of
 * tasks moved.
 *
 * Called with both runqueues locked.
 */
static int move_tasks(runqueue_t *this_rq, int this_cpu, runqueue_t *busiest,
		      unsigned long max_nr_move, struct sched_domain *sd,
1817
		      enum idle_type idle, int *all_pinned)
Linus Torvalds's avatar
Linus Torvalds committed
1818
1819
1820
{
	prio_array_t *array, *dst_array;
	struct list_head *head, *curr;
1821
	int idx, pulled = 0, pinned = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1822
1823
	task_t *tmp;

1824
	if (max_nr_move == 0)
Linus Torvalds's avatar
Linus Torvalds committed
1825
1826
		goto out;

1827
1828
	pinned = 1;

Linus Torvalds's avatar
Linus Torvalds committed
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
	/*
	 * We first consider expired tasks. Those will likely not be
	 * executed in the near future, and they are most likely to
	 * be cache-cold, thus switching CPUs has the least effect
	 * on them.
	 */
	if (busiest->expired->nr_active) {
		array = busiest->expired;
		dst_array = this_rq->expired;
	} else {
		array = busiest->active;
		dst_array = this_rq->active;
	}

new_array:
	/* Start searching at priority 0: */
	idx = 0;
skip_bitmap:
	if (!idx)
		idx = sched_find_first_bit(array->bitmap);
	else
		idx = find_next_bit(array->bitmap, MAX_PRIO, idx);
	if (idx >= MAX_PRIO) {
		if (array == busiest->expired && busiest->active->nr_active) {
			array = busiest->active;
			dst_array = this_rq->active;
			goto new_array;
		}
		goto out;
	}

	head = array->queue + idx;
	curr = head->prev;
skip_queue:
	tmp = list_entry(curr, task_t, run_list);

	curr = curr->prev;

1867
	if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
Linus Torvalds's avatar
Linus Torvalds committed
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
		if (curr != head)
			goto skip_queue;
		idx++;
		goto skip_bitmap;
	}

#ifdef CONFIG_SCHEDSTATS
	if (task_hot(tmp, busiest->timestamp_last_tick, sd))
		schedstat_inc(sd, lb_hot_gained[idle]);
#endif

	pull_task(busiest, array, tmp, this_rq, dst_array, this_cpu);
	pulled++;

	/* We only want to steal up to the prescribed number of tasks. */
	if (pulled < max_nr_move) {
		if (curr != head)
			goto skip_queue;
		idx++;
		goto skip_bitmap;
	}
out:
	/*
	 * Right now, this is the only place pull_task() is called,
	 * so we can safely collect pull_task() stats here rather than
	 * inside pull_task().
	 */
	schedstat_add(sd, lb_gained[idle], pulled);
1896
1897
1898

	if (all_pinned)
		*all_pinned = pinned;
Linus Torvalds's avatar
Linus Torvalds committed
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
	return pulled;
}

/*
 * find_busiest_group finds and returns the busiest CPU group within the
 * domain. It calculates and returns the number of tasks which should be
 * moved to restore balance via the imbalance parameter.
 */
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
Nick Piggin's avatar
Nick Piggin committed
1909
		   unsigned long *imbalance, enum idle_type idle, int *sd_idle)
Linus Torvalds's avatar
Linus Torvalds committed
1910
1911
1912
{
	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
1913
	unsigned long max_pull;
Nick Piggin's avatar
Nick Piggin committed
1914
	int load_idx;
Linus Torvalds's avatar
Linus Torvalds committed
1915
1916

	max_load = this_load = total_load = total_pwr = 0;
Nick Piggin's avatar
Nick Piggin committed
1917
1918
1919
1920
1921
1922
	if (idle == NOT_IDLE)
		load_idx = sd->busy_idx;
	else if (idle == NEWLY_IDLE)
		load_idx = sd->newidle_idx;
	else
		load_idx = sd->idle_idx;
Linus Torvalds's avatar
Linus Torvalds committed
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934

	do {
		unsigned long load;
		int local_group;
		int i;

		local_group = cpu_isset(this_cpu, group->cpumask);

		/* Tally up the load of all CPUs in the group */
		avg_load = 0;

		for_each_cpu_mask(i, group->cpumask) {
Nick Piggin's avatar
Nick Piggin committed
1935
1936
1937
			if (*sd_idle && !idle_cpu(i))
				*sd_idle = 0;

Linus Torvalds's avatar
Linus Torvalds committed
1938
1939
			/* Bias balancing toward cpus of our domain */
			if (local_group)
Nick Piggin's avatar
Nick Piggin committed
1940
				load = target_load(i, load_idx);
Linus Torvalds's avatar
Linus Torvalds committed
1941
			else
Nick Piggin's avatar
Nick Piggin committed
1942
				load = source_load(i, load_idx);
Linus Torvalds's avatar
Linus Torvalds committed
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962

			avg_load += load;
		}

		total_load += avg_load;
		total_pwr += group->cpu_power;

		/* Adjust by relative CPU power of the group */
		avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;

		if (local_group) {
			this_load = avg_load;
			this = group;
		} else if (avg_load > max_load) {
			max_load = avg_load;
			busiest = group;
		}
		group = group->next;
	} while (group != sd->groups);

1963
	if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE)
Linus Torvalds's avatar
Linus Torvalds committed
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
		goto out_balanced;

	avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr;

	if (this_load >= avg_load ||
			100*max_load <= sd->imbalance_pct*this_load)
		goto out_balanced;

	/*
	 * We're trying to get all the cpus to the average_load, so we don't
	 * want to push ourselves above the average load, nor do we wish to
	 * reduce the max loaded cpu below the average load, as either of these
	 * actions would just result in more rebalancing later, and ping-pong
	 * tasks around. Thus we look for the minimum possible imbalance.
	 * Negative imbalances (*we* are more loaded than anyone else) will
	 * be counted as no imbalance for these purposes -- we can't fix that
	 * by pulling tasks to us.  Be careful of negative numbers as they'll
	 * appear as very large values with unsigned longs.
	 */
1983
1984
1985
1986

	/* Don't want to pull so many tasks that a group would go idle */
	max_pull = min(max_load - avg_load, max_load - SCHED_LOAD_SCALE);

Linus Torvalds's avatar
Linus Torvalds committed
1987
	/* How much load to actually move to equalise the imbalance */
1988
	*imbalance = min(max_pull * busiest->cpu_power,
Linus Torvalds's avatar
Linus Torvalds committed
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
				(avg_load - this_load) * this->cpu_power)
			/ SCHED_LOAD_SCALE;

	if (*imbalance < SCHED_LOAD_SCALE) {
		unsigned long pwr_now = 0, pwr_move = 0;
		unsigned long tmp;

		if (max_load - this_load >= SCHED_LOAD_SCALE*2) {
			*imbalance = 1;
			return busiest;
		}

		/*
		 * OK, we don't have enough imbalance to justify moving tasks,
		 * however we may be able to increase total CPU power used by
		 * moving them.
		 */

		pwr_now += busiest->cpu_power*min(SCHED_LOAD_SCALE, max_load);
		pwr_now += this->cpu_power*min(SCHED_LOAD_SCALE, this_load);
		pwr_now /= SCHED_LOAD_SCALE;

		/* Amount of load we'd subtract */
		tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/busiest->cpu_power;
		if (max_load > tmp)
			pwr_move += busiest->cpu_power*min(SCHED_LOAD_SCALE,
							max_load - tmp);

		/* Amount of load we'd add */
		if (max_load*busiest->cpu_power <
				SCHED_LOAD_SCALE*SCHED_LOAD_SCALE)
			tmp = max_load*busiest->cpu_power/this->cpu_power;
		else
			tmp = SCHED_LOAD_SCALE*SCHED_LOAD_SCALE/this->cpu_power;
		pwr_move += this->cpu_power*min(SCHED_LOAD_SCALE, this_load + tmp);
		pwr_move /= SCHED_LOAD_SCALE;

		/* Move if we gain throughput */
		if (pwr_move <= pwr_now)
			goto out_balanced;

		*imbalance = 1;
		return busiest;
	}

	/* Get rid of the scaling factor, rounding down as we divide */
	*imbalance = *imbalance / SCHED_LOAD_SCALE;
	return busiest;

out_balanced:

	*imbalance = 0;
	return NULL;
}

/*
 * find_busiest_queue - find the busiest runqueue among the cpus in group.
 */
static runqueue_t *find_busiest_queue(struct sched_group *group)
{
	unsigned long load, max_load = 0;
	runqueue_t *busiest = NULL;
	int i;

	for_each_cpu_mask(i, group->cpumask) {
Nick Piggin's avatar
Nick Piggin committed
2054
		load = source_load(i, 0);
Linus Torvalds's avatar
Linus Torvalds committed
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064

		if (load > max_load) {
			max_load = load;
			busiest = cpu_rq(i);
		}
	}

	return busiest;
}

2065
2066
2067
2068
2069
2070
/*
 * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
 * so long as it is large enough.
 */
#define MAX_PINNED_INTERVAL	512

Linus Torvalds's avatar
Linus Torvalds committed
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 *
 * Called with this_rq unlocked.
 */
static int load_balance(int this_cpu, runqueue_t *this_rq,
			struct sched_domain *sd, enum idle_type idle)
{
	struct sched_group *group;
	runqueue_t *busiest;
	unsigned long imbalance;
2083
	int nr_moved, all_pinned = 0;
2084
	int active_balance = 0;
Nick Piggin's avatar
Nick Piggin committed
2085
2086
2087
2088
	int sd_idle = 0;

	if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER)
		sd_idle = 1;
Linus Torvalds's avatar
Linus Torvalds committed
2089
2090
2091

	schedstat_inc(sd, lb_cnt[idle]);

Nick Piggin's avatar
Nick Piggin committed
2092
	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle);
Linus Torvalds's avatar
Linus Torvalds committed
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[idle]);
		goto out_balanced;
	}

	busiest = find_busiest_queue(group);
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[idle]);
		goto out_balanced;
	}

Nick Piggin's avatar
Nick Piggin committed
2104
	BUG_ON(busiest == this_rq);
Linus Torvalds's avatar
Linus Torvalds committed
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115

	schedstat_add(sd, lb_imbalance[idle], imbalance);

	nr_moved = 0;
	if (busiest->nr_running > 1) {
		/*
		 * Attempt to move tasks. If find_busiest_group has found
		 * an imbalance but busiest->nr_running <= 1, the group is
		 * still unbalanced. nr_moved simply stays zero, so it is
		 * correctly treated as an imbalance.
		 */
Nick Piggin's avatar
Nick Piggin committed
2116
		double_rq_lock(this_rq, busiest);
Linus Torvalds's avatar
Linus Torvalds committed
2117
		nr_moved = move_tasks(this_rq, this_cpu, busiest,
2118
					imbalance, sd, idle, &all_pinned);
Nick Piggin's avatar
Nick Piggin committed
2119
		double_rq_unlock(this_rq, busiest);
2120
2121
2122
2123

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(all_pinned))
			goto out_balanced;
Linus Torvalds's avatar
Linus Torvalds committed
2124
	}
2125

Linus Torvalds's avatar
Linus Torvalds committed
2126
2127
2128
2129
2130
2131
2132
	if (!nr_moved) {
		schedstat_inc(sd, lb_failed[idle]);
		sd->nr_balance_failed++;

		if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) {

			spin_lock(&busiest->lock);
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142

			/* don't kick the migration_thread, if the curr
			 * task on busiest cpu can't be moved to this_cpu
			 */
			if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) {
				spin_unlock(&busiest->lock);
				all_pinned = 1;
				goto out_one_pinned;
			}

Linus Torvalds's avatar
Linus Torvalds committed
2143
2144
2145
			if (!busiest->active_balance) {
				busiest->active_balance = 1;
				busiest->push_cpu = this_cpu;
2146
				active_balance = 1;
Linus Torvalds's avatar
Linus Torvalds committed
2147
2148
			}
			spin_unlock(&busiest->lock);
2149
			if (active_balance)
Linus Torvalds's avatar
Linus Torvalds committed
2150
2151
2152
2153
2154
2155
				wake_up_process(busiest->migration_thread);

			/*
			 * We've kicked active balancing, reset the failure
			 * counter.
			 */
2156
			sd->nr_balance_failed = sd->cache_nice_tries+1;
Linus Torvalds's avatar
Linus Torvalds committed
2157
		}
2158
	} else
Linus Torvalds's avatar
Linus Torvalds committed
2159
2160
		sd->nr_balance_failed = 0;

2161
	if (likely(!active_balance)) {
Linus Torvalds's avatar
Linus Torvalds committed
2162
2163
		/* We were unbalanced, so reset the balancing interval */
		sd->balance_interval = sd->min_interval;
2164
2165
2166
2167
2168
2169
2170
2171
2172
	} else {
		/*
		 * If we've begun active balancing, start to back off. This
		 * case may not be covered by the all_pinned logic if there
		 * is only 1 task on the busy runqueue (because we don't call
		 * move_tasks).
		 */
		if (sd->balance_interval < sd->max_interval)
			sd->balance_interval *= 2;
Linus Torvalds's avatar
Linus Torvalds committed
2173
2174
	}

Nick Piggin's avatar
Nick Piggin committed
2175
2176
	if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER)
		return -1;
Linus Torvalds's avatar
Linus Torvalds committed
2177
2178
2179
2180
2181
	return nr_moved;

out_balanced:
	schedstat_inc(sd, lb_balanced[idle]);

2182
	sd->nr_balance_failed = 0;
2183
2184

out_one_pinned:
Linus Torvalds's avatar
Linus Torvalds committed
2185
	/* tune up the balancing interval */
2186
2187
	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
			(sd->balance_interval < sd->max_interval))
Linus Torvalds's avatar
Linus Torvalds committed
2188
2189
		sd->balance_interval *= 2;

Nick Piggin's avatar
Nick Piggin committed
2190
2191
	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
		return -1;
Linus Torvalds's avatar
Linus Torvalds committed
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
	return 0;
}

/*
 * Check this_cpu to ensure it is balanced within domain. Attempt to move
 * tasks if there is an imbalance.
 *
 * Called from schedule when this_rq is about to become idle (NEWLY_IDLE).
 * this_rq is locked.
 */
static int load_balance_newidle(int this_cpu, runqueue_t *this_rq,
				struct sched_domain *sd)
{
	struct sched_group *group;
	runqueue_t *busiest = NULL;
	unsigned long imbalance;
	int nr_moved = 0;
Nick Piggin's avatar
Nick Piggin committed
2209
2210
2211
2212
	int sd_idle = 0;

	if (sd->flags & SD_SHARE_CPUPOWER)
		sd_idle = 1;
Linus Torvalds's avatar
Linus Torvalds committed
2213
2214

	schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
Nick Piggin's avatar
Nick Piggin committed
2215
	group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle);
Linus Torvalds's avatar
Linus Torvalds committed
2216
2217
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
2218
		goto out_balanced;
Linus Torvalds's avatar
Linus Torvalds committed
2219
2220
2221
	}

	busiest = find_busiest_queue(group);
Nick Piggin's avatar
Nick Piggin committed
2222
	if (!busiest) {
Linus Torvalds's avatar
Linus Torvalds committed
2223
		schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
2224
		goto out_balanced;
Linus Torvalds's avatar
Linus Torvalds committed
2225
2226
	}