sched.c 155.6 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 *  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>
30
#include <linux/capability.h>
L
Linus Torvalds 已提交
31 32 33 34 35 36
#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>
37
#include <linux/vmalloc.h>
L
Linus Torvalds 已提交
38 39 40 41 42 43 44 45 46 47 48 49 50 51
#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>
52
#include <linux/kprobes.h>
L
Linus Torvalds 已提交
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
#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) \
148 149
	(SCALE(TASK_NICE(p) + 20, 40, MAX_BONUS) - 20 * MAX_BONUS / 40 + \
		INTERACTIVE_DELTA)
L
Linus Torvalds 已提交
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172

#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)

173
static unsigned int task_timeslice(task_t *p)
L
Linus Torvalds 已提交
174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212
{
	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
N
Nick Piggin 已提交
213
	unsigned long cpu_load[3];
L
Linus Torvalds 已提交
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
#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;
A
Anton Blanchard 已提交
242
	int cpu;
L
Linus Torvalds 已提交
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
#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);

N
Nick Piggin 已提交
268 269
/*
 * The domain tree (rq->sd) is protected by RCU's quiescent state transition.
270
 * See detach_destroy_domains: synchronize_sched for details.
N
Nick Piggin 已提交
271 272 273 274
 *
 * The domain tree of any CPU may only be accessed from within
 * preempt-disabled sections.
 */
L
Linus Torvalds 已提交
275
#define for_each_domain(cpu, domain) \
N
Nick Piggin 已提交
276
for (domain = rcu_dereference(cpu_rq(cpu)->sd); domain; domain = domain->parent)
L
Linus Torvalds 已提交
277 278 279 280 281 282 283

#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
284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301
# 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)
{
302 303 304 305
#ifdef CONFIG_DEBUG_SPINLOCK
	/* this is a valid case when another task releases the spinlock */
	rq->lock.owner = current;
#endif
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348
	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();
L
Linus Torvalds 已提交
349
#endif
350 351
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
L
Linus Torvalds 已提交
352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384

/*
 * 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)
 */
385
#define SCHEDSTAT_VERSION 12
L
Linus Torvalds 已提交
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413

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 */
N
Nick Piggin 已提交
414
		preempt_disable();
L
Linus Torvalds 已提交
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432
		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]);
			}
433
			seq_printf(seq, " %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu %lu\n",
L
Linus Torvalds 已提交
434
			    sd->alb_cnt, sd->alb_failed, sd->alb_pushed,
435 436
			    sd->sbe_cnt, sd->sbe_balanced, sd->sbe_pushed,
			    sd->sbf_cnt, sd->sbf_balanced, sd->sbf_pushed,
L
Linus Torvalds 已提交
437 438
			    sd->ttwu_wake_remote, sd->ttwu_move_affine, sd->ttwu_move_balance);
		}
N
Nick Piggin 已提交
439
		preempt_enable();
L
Linus Torvalds 已提交
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
#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.
 */
519
static void sched_info_arrive(task_t *t)
L
Linus Torvalds 已提交
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
{
	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;
}

667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708
/*
 * We place interactive tasks back into the active array, if possible.
 *
 * To guarantee that this does not starve expired tasks we ignore the
 * interactivity of a task if the first expired task had to wait more
 * than a 'reasonable' amount of time. This deadline timeout is
 * load-dependent, as the frequency of array switched decreases with
 * increasing number of running tasks. We also ignore the interactivity
 * if a better static_prio task has expired, and switch periodically
 * regardless, to ensure that highly interactive tasks do not starve
 * the less fortunate for unreasonably long periods.
 */
static inline int expired_starving(runqueue_t *rq)
{
	int limit;

	/*
	 * Arrays were recently switched, all is well
	 */
	if (!rq->expired_timestamp)
		return 0;

	limit = STARVATION_LIMIT * rq->nr_running;

	/*
	 * It's time to switch arrays
	 */
	if (jiffies - rq->expired_timestamp >= limit)
		return 1;

	/*
	 * There's a better selection in the expired array
	 */
	if (rq->curr->static_prio > rq->best_expired_prio)
		return 1;

	/*
	 * All is well
	 */
	return 0;
}

L
Linus Torvalds 已提交
709 710 711
/*
 * __activate_task - move a task to the runqueue.
 */
712
static void __activate_task(task_t *p, runqueue_t *rq)
L
Linus Torvalds 已提交
713
{
714 715
	prio_array_t *target = rq->active;

716
	if (unlikely(batch_task(p) || expired_starving(rq)))
717 718
		target = rq->expired;
	enqueue_task(p, target);
N
Nick Piggin 已提交
719
	rq->nr_running++;
L
Linus Torvalds 已提交
720 721 722 723 724 725 726 727
}

/*
 * __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);
N
Nick Piggin 已提交
728
	rq->nr_running++;
L
Linus Torvalds 已提交
729 730
}

731
static int recalc_task_prio(task_t *p, unsigned long long now)
L
Linus Torvalds 已提交
732 733 734 735 736
{
	/* Caller must always ensure 'now >= p->timestamp' */
	unsigned long long __sleep_time = now - p->timestamp;
	unsigned long sleep_time;

737
	if (batch_task(p))
738 739 740 741 742 743 744
		sleep_time = 0;
	else {
		if (__sleep_time > NS_MAX_SLEEP_AVG)
			sleep_time = NS_MAX_SLEEP_AVG;
		else
			sleep_time = (unsigned long)__sleep_time;
	}
L
Linus Torvalds 已提交
745 746 747 748

	if (likely(sleep_time > 0)) {
		/*
		 * User tasks that sleep a long time are categorised as
749 750 751 752
		 * idle. They will only have their sleep_avg increased to a
		 * level that makes them just interactive priority to stay
		 * active yet prevent them suddenly becoming cpu hogs and
		 * starving other processes.
L
Linus Torvalds 已提交
753
		 */
754
		if (p->mm && sleep_time > INTERACTIVE_SLEEP(p)) {
755 756 757 758 759 760
				unsigned long ceiling;

				ceiling = JIFFIES_TO_NS(MAX_SLEEP_AVG -
					DEF_TIMESLICE);
				if (p->sleep_avg < ceiling)
					p->sleep_avg = ceiling;
L
Linus Torvalds 已提交
761 762 763 764 765 766
		} else {
			/*
			 * Tasks waking from uninterruptible sleep are
			 * limited in their sleep_avg rise as they
			 * are likely to be waiting on I/O
			 */
767
			if (p->sleep_type == SLEEP_NONINTERACTIVE && p->mm) {
L
Linus Torvalds 已提交
768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791
				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;
		}
	}

792
	return effective_prio(p);
L
Linus Torvalds 已提交
793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814
}

/*
 * 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

C
Chen, Kenneth W 已提交
815 816
	if (!rt_task(p))
		p->prio = recalc_task_prio(p, now);
L
Linus Torvalds 已提交
817 818 819 820 821

	/*
	 * This checks to make sure it's not an uninterruptible task
	 * that is now waking up.
	 */
822
	if (p->sleep_type == SLEEP_NORMAL) {
L
Linus Torvalds 已提交
823 824 825 826 827 828 829 830
		/*
		 * 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())
831
			p->sleep_type = SLEEP_INTERRUPTED;
L
Linus Torvalds 已提交
832 833 834 835 836
		else {
			/*
			 * Normal first-time wakeups get a credit too for
			 * on-runqueue time, but it will be weighted down:
			 */
837
			p->sleep_type = SLEEP_INTERACTIVE;
L
Linus Torvalds 已提交
838 839 840 841 842 843 844 845 846 847 848 849
		}
	}
	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)
{
N
Nick Piggin 已提交
850
	rq->nr_running--;
L
Linus Torvalds 已提交
851 852 853 854 855 856 857 858 859 860 861 862 863 864
	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)
{
865
	int cpu;
L
Linus Torvalds 已提交
866 867 868

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

869 870 871 872
	if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED)))
		return;

	set_tsk_thread_flag(p, TIF_NEED_RESCHED);
L
Linus Torvalds 已提交
873

874 875 876 877 878 879 880 881
	cpu = task_cpu(p);
	if (cpu == smp_processor_id())
		return;

	/* NEED_RESCHED must be visible before we test POLLING_NRFLAG */
	smp_mb();
	if (!test_tsk_thread_flag(p, TIF_POLLING_NRFLAG))
		smp_send_reschedule(cpu);
L
Linus Torvalds 已提交
882 883 884 885
}
#else
static inline void resched_task(task_t *p)
{
886
	assert_spin_locked(&task_rq(p)->lock);
L
Linus Torvalds 已提交
887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942
	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.
 */
I
Ingo Molnar 已提交
943
void wait_task_inactive(task_t *p)
L
Linus Torvalds 已提交
944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
{
	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.
 */
N
Nick Piggin 已提交
994
static inline unsigned long source_load(int cpu, int type)
L
Linus Torvalds 已提交
995 996
{
	runqueue_t *rq = cpu_rq(cpu);
N
Nick Piggin 已提交
997
	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
998
	if (type == 0)
N
Nick Piggin 已提交
999
		return load_now;
1000

N
Nick Piggin 已提交
1001
	return min(rq->cpu_load[type-1], load_now);
L
Linus Torvalds 已提交
1002 1003 1004 1005 1006
}

/*
 * Return a high guess at the load of a migration-target cpu
 */
N
Nick Piggin 已提交
1007
static inline unsigned long target_load(int cpu, int type)
L
Linus Torvalds 已提交
1008 1009
{
	runqueue_t *rq = cpu_rq(cpu);
N
Nick Piggin 已提交
1010
	unsigned long load_now = rq->nr_running * SCHED_LOAD_SCALE;
N
Nick Piggin 已提交
1011
	if (type == 0)
N
Nick Piggin 已提交
1012
		return load_now;
1013

N
Nick Piggin 已提交
1014
	return max(rq->cpu_load[type-1], load_now);
L
Linus Torvalds 已提交
1015 1016
}

N
Nick Piggin 已提交
1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033
/*
 * 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;

1034 1035 1036 1037
		/* Skip over this group if it has no CPUs allowed */
		if (!cpus_intersects(group->cpumask, p->cpus_allowed))
			goto nextgroup;

N
Nick Piggin 已提交
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
		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;
		}
1063
nextgroup:
N
Nick Piggin 已提交
1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074
		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.
 */
I
Ingo Molnar 已提交
1075 1076
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
N
Nick Piggin 已提交
1077
{
1078
	cpumask_t tmp;
N
Nick Piggin 已提交
1079 1080 1081 1082
	unsigned long load, min_load = ULONG_MAX;
	int idlest = -1;
	int i;

1083 1084 1085 1086
	/* Traverse only the allowed CPUs */
	cpus_and(tmp, group->cpumask, p->cpus_allowed);

	for_each_cpu_mask(i, tmp) {
N
Nick Piggin 已提交
1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
		load = source_load(i, 0);

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

	return idlest;
}

N
Nick Piggin 已提交
1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112
/*
 * 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;
N
Nick Piggin 已提交
1113

N
Nick Piggin 已提交
1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128
	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;

1129
		new_cpu = find_idlest_cpu(group, t, cpu);
N
Nick Piggin 已提交
1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150
		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 */
L
Linus Torvalds 已提交
1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171

/*
 * 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) {
N
Nick Piggin 已提交
1172
			cpus_and(tmp, sd->span, p->cpus_allowed);
L
Linus Torvalds 已提交
1173 1174 1175 1176 1177
			for_each_cpu_mask(i, tmp) {
				if (idle_cpu(i))
					return i;
			}
		}
N
Nick Piggin 已提交
1178 1179
		else
			break;
L
Linus Torvalds 已提交
1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203
	}
	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.
 */
I
Ingo Molnar 已提交
1204
static int try_to_wake_up(task_t *p, unsigned int state, int sync)
L
Linus Torvalds 已提交
1205 1206 1207 1208 1209 1210 1211
{
	int cpu, this_cpu, success = 0;
	unsigned long flags;
	long old_state;
	runqueue_t *rq;
#ifdef CONFIG_SMP
	unsigned long load, this_load;
N
Nick Piggin 已提交
1212
	struct sched_domain *sd, *this_sd = NULL;
L
Linus Torvalds 已提交
1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230
	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;

N
Nick Piggin 已提交
1231 1232
	new_cpu = cpu;

L
Linus Torvalds 已提交
1233 1234 1235
	schedstat_inc(rq, ttwu_cnt);
	if (cpu == this_cpu) {
		schedstat_inc(rq, ttwu_local);
N
Nick Piggin 已提交
1236 1237 1238 1239 1240 1241 1242 1243
		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;
L
Linus Torvalds 已提交
1244 1245 1246
		}
	}

N
Nick Piggin 已提交
1247
	if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
L
Linus Torvalds 已提交
1248 1249 1250
		goto out_set_cpu;

	/*
N
Nick Piggin 已提交
1251
	 * Check for affine wakeup and passive balancing possibilities.
L
Linus Torvalds 已提交
1252
	 */
N
Nick Piggin 已提交
1253 1254 1255
	if (this_sd) {
		int idx = this_sd->wake_idx;
		unsigned int imbalance;
L
Linus Torvalds 已提交
1256

1257 1258
		imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;

N
Nick Piggin 已提交
1259 1260
		load = source_load(cpu, idx);
		this_load = target_load(this_cpu, idx);
L
Linus Torvalds 已提交
1261

N
Nick Piggin 已提交
1262 1263
		new_cpu = this_cpu; /* Wake to this CPU if we can */

1264 1265
		if (this_sd->flags & SD_WAKE_AFFINE) {
			unsigned long tl = this_load;
L
Linus Torvalds 已提交
1266
			/*
1267 1268 1269
			 * If sync wakeup then subtract the (maximum possible)
			 * effect of the currently running task from the load
			 * of the current CPU:
L
Linus Torvalds 已提交
1270
			 */
1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295
			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;
			}
L
Linus Torvalds 已提交
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
		}
	}

	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.
		 */
1325
		p->sleep_type = SLEEP_NONINTERACTIVE;
1326
	} else
L
Linus Torvalds 已提交
1327

I
Ingo Molnar 已提交
1328 1329
	/*
	 * Tasks that have marked their sleep as noninteractive get
1330 1331
	 * woken up with their sleep average not weighted in an
	 * interactive way.
I
Ingo Molnar 已提交
1332
	 */
1333 1334 1335 1336 1337
		if (old_state & TASK_NONINTERACTIVE)
			p->sleep_type = SLEEP_NONINTERACTIVE;


	activate_task(p, rq, cpu == this_cpu);
L
Linus Torvalds 已提交
1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359
	/*
	 * 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;
}

I
Ingo Molnar 已提交
1360
int fastcall wake_up_process(task_t *p)
L
Linus Torvalds 已提交
1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376
{
	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.
 */
N
Nick Piggin 已提交
1377
void fastcall sched_fork(task_t *p, int clone_flags)
L
Linus Torvalds 已提交
1378
{
N
Nick Piggin 已提交
1379 1380 1381 1382 1383 1384 1385
	int cpu = get_cpu();

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

L
Linus Torvalds 已提交
1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397
	/*
	 * 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
1398
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
1399 1400
	p->oncpu = 0;
#endif
L
Linus Torvalds 已提交
1401
#ifdef CONFIG_PREEMPT
1402
	/* Want to start with kernel preemption disabled. */
A
Al Viro 已提交
1403
	task_thread_info(p)->preempt_count = 1;
L
Linus Torvalds 已提交
1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426
#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();
N
Nick Piggin 已提交
1427 1428 1429
	}
	local_irq_enable();
	put_cpu();
L
Linus Torvalds 已提交
1430 1431 1432 1433 1434 1435 1436 1437 1438
}

/*
 * 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.
 */
I
Ingo Molnar 已提交
1439
void fastcall wake_up_new_task(task_t *p, unsigned long clone_flags)
L
Linus Torvalds 已提交
1440 1441 1442 1443 1444 1445
{
	unsigned long flags;
	int this_cpu, cpu;
	runqueue_t *rq, *this_rq;

	rq = task_rq_lock(p, &flags);
N
Nick Piggin 已提交
1446
	BUG_ON(p->state != TASK_RUNNING);
L
Linus Torvalds 已提交
1447
	this_cpu = smp_processor_id();
N
Nick Piggin 已提交
1448
	cpu = task_cpu(p);
L
Linus Torvalds 已提交
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

	/*
	 * 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++;
N
Nick Piggin 已提交
1475
				rq->nr_running++;
L
Linus Torvalds 已提交
1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521
			}
			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.)
 */
I
Ingo Molnar 已提交
1522
void fastcall sched_exit(task_t *p)
L
Linus Torvalds 已提交
1523 1524 1525 1526 1527 1528 1529 1530 1531
{
	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);
1532
	if (p->first_time_slice && task_cpu(p) == task_cpu(p->parent)) {
L
Linus Torvalds 已提交
1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543
		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);
}

1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561
/**
 * 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);
}

L
Linus Torvalds 已提交
1562 1563
/**
 * finish_task_switch - clean up after a task-switch
1564
 * @rq: runqueue associated with task-switch
L
Linus Torvalds 已提交
1565 1566
 * @prev: the thread we just switched away from.
 *
1567 1568 1569 1570
 * 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.
L
Linus Torvalds 已提交
1571 1572 1573 1574 1575 1576
 *
 * 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.)
 */
1577
static inline void finish_task_switch(runqueue_t *rq, task_t *prev)
L
Linus Torvalds 已提交
1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596
	__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;
1597 1598
	finish_arch_switch(prev);
	finish_lock_switch(rq, prev);
L
Linus Torvalds 已提交
1599 1600
	if (mm)
		mmdrop(mm);
1601 1602 1603 1604 1605 1606
	if (unlikely(prev_task_flags & PF_DEAD)) {
		/*
		 * Remove function-return probe instances associated with this
		 * task and put them back on the free list.
	 	 */
		kprobe_flush_task(prev);
L
Linus Torvalds 已提交
1607
		put_task_struct(prev);
1608
	}
L
Linus Torvalds 已提交
1609 1610 1611 1612 1613 1614 1615 1616 1617
}

/**
 * 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)
{
1618 1619 1620 1621 1622 1623
	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
L
Linus Torvalds 已提交
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
	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;

1678
	for_each_possible_cpu(i)
L
Linus Torvalds 已提交
1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694
		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;

1695
	for_each_possible_cpu(i)
L
Linus Torvalds 已提交
1696 1697 1698 1699 1700 1701 1702 1703 1704
		sum += cpu_rq(i)->nr_switches;

	return sum;
}

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

1705
	for_each_possible_cpu(i)
L
Linus Torvalds 已提交
1706 1707 1708 1709 1710
		sum += atomic_read(&cpu_rq(i)->nr_iowait);

	return sum;
}

1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725
unsigned long nr_active(void)
{
	unsigned long i, running = 0, uninterruptible = 0;

	for_each_online_cpu(i) {
		running += cpu_rq(i)->nr_running;
		uninterruptible += cpu_rq(i)->nr_uninterruptible;
	}

	if (unlikely((long)uninterruptible < 0))
		uninterruptible = 0;

	return running + uninterruptible;
}

L
Linus Torvalds 已提交
1726 1727 1728 1729 1730
#ifdef CONFIG_SMP

/*
 * double_rq_lock - safely lock two runqueues
 *
A
Anton Blanchard 已提交
1731 1732 1733
 * We must take them in cpu order to match code in
 * dependent_sleeper and wake_dependent_sleeper.
 *
L
Linus Torvalds 已提交
1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744
 * 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 {
A
Anton Blanchard 已提交
1745
		if (rq1->cpu < rq2->cpu) {
L
Linus Torvalds 已提交
1746 1747 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 1778 1779 1780
			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))) {
A
Anton Blanchard 已提交
1781
		if (busiest->cpu < this_rq->cpu) {
L
Linus Torvalds 已提交
1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822
			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);
}

/*
N
Nick Piggin 已提交
1823 1824
 * sched_exec - execve() is a valuable balancing opportunity, because at
 * this point the task has the smallest effective memory and cache footprint.
L
Linus Torvalds 已提交
1825 1826 1827 1828
 */
void sched_exec(void)
{
	int new_cpu, this_cpu = get_cpu();
N
Nick Piggin 已提交
1829
	new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC);
L
Linus Torvalds 已提交
1830
	put_cpu();
N
Nick Piggin 已提交
1831 1832
	if (new_cpu != this_cpu)
		sched_migrate_task(current, new_cpu);
L
Linus Torvalds 已提交
1833 1834 1835 1836 1837 1838
}

/*
 * pull_task - move a task from a remote runqueue to the local runqueue.
 * Both runqueues must be locked.
 */
1839
static
L
Linus Torvalds 已提交
1840 1841 1842 1843
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);
N
Nick Piggin 已提交
1844
	src_rq->nr_running--;
L
Linus Torvalds 已提交
1845
	set_task_cpu(p, this_cpu);
N
Nick Piggin 已提交
1846
	this_rq->nr_running++;
L
Linus Torvalds 已提交
1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860
	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?
 */
1861
static
L
Linus Torvalds 已提交
1862
int can_migrate_task(task_t *p, runqueue_t *rq, int this_cpu,
I
Ingo Molnar 已提交
1863 1864
		     struct sched_domain *sd, enum idle_type idle,
		     int *all_pinned)
L
Linus Torvalds 已提交
1865 1866 1867 1868 1869 1870 1871 1872 1873
{
	/*
	 * 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;
1874 1875 1876 1877
	*all_pinned = 0;

	if (task_running(rq, p))
		return 0;
L
Linus Torvalds 已提交
1878 1879 1880

	/*
	 * Aggressive migration if:
1881
	 * 1) task is cache cold, or
L
Linus Torvalds 已提交
1882 1883 1884
	 * 2) too many balance attempts have failed.
	 */

1885
	if (sd->nr_balance_failed > sd->cache_nice_tries)
L
Linus Torvalds 已提交
1886 1887 1888
		return 1;

	if (task_hot(p, rq->timestamp_last_tick, sd))
1889
		return 0;
L
Linus Torvalds 已提交
1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901
	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,
1902
		      enum idle_type idle, int *all_pinned)
L
Linus Torvalds 已提交
1903 1904 1905
{
	prio_array_t *array, *dst_array;
	struct list_head *head, *curr;
1906
	int idx, pulled = 0, pinned = 0;
L
Linus Torvalds 已提交
1907 1908
	task_t *tmp;

1909
	if (max_nr_move == 0)
L
Linus Torvalds 已提交
1910 1911
		goto out;

1912 1913
	pinned = 1;

L
Linus Torvalds 已提交
1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951
	/*
	 * 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;

1952
	if (!can_migrate_task(tmp, busiest, this_cpu, sd, idle, &pinned)) {
L
Linus Torvalds 已提交
1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980
		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);
1981 1982 1983

	if (all_pinned)
		*all_pinned = pinned;
L
Linus Torvalds 已提交
1984 1985 1986 1987 1988 1989 1990 1991 1992 1993
	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,
N
Nick Piggin 已提交
1994
		   unsigned long *imbalance, enum idle_type idle, int *sd_idle)
L
Linus Torvalds 已提交
1995 1996 1997
{
	struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
	unsigned long max_load, avg_load, total_load, this_load, total_pwr;
1998
	unsigned long max_pull;
N
Nick Piggin 已提交
1999
	int load_idx;
L
Linus Torvalds 已提交
2000 2001

	max_load = this_load = total_load = total_pwr = 0;
N
Nick Piggin 已提交
2002 2003 2004 2005 2006 2007
	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;
L
Linus Torvalds 已提交
2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019

	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) {
N
Nick Piggin 已提交
2020 2021 2022
			if (*sd_idle && !idle_cpu(i))
				*sd_idle = 0;

L
Linus Torvalds 已提交
2023 2024
			/* Bias balancing toward cpus of our domain */
			if (local_group)
N
Nick Piggin 已提交
2025
				load = target_load(i, load_idx);
L
Linus Torvalds 已提交
2026
			else
N
Nick Piggin 已提交
2027
				load = source_load(i, load_idx);
L
Linus Torvalds 已提交
2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047

			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);

2048
	if (!busiest || this_load >= max_load || max_load <= SCHED_LOAD_SCALE)
L
Linus Torvalds 已提交
2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067
		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.
	 */
2068 2069 2070 2071

	/* 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);

L
Linus Torvalds 已提交
2072
	/* How much load to actually move to equalise the imbalance */
2073
	*imbalance = min(max_pull * busiest->cpu_power,
L
Linus Torvalds 已提交
2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131
				(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.
 */
2132 2133
static runqueue_t *find_busiest_queue(struct sched_group *group,
	enum idle_type idle)
L
Linus Torvalds 已提交
2134 2135 2136 2137 2138 2139
{
	unsigned long load, max_load = 0;
	runqueue_t *busiest = NULL;
	int i;

	for_each_cpu_mask(i, group->cpumask) {
N
Nick Piggin 已提交
2140
		load = source_load(i, 0);
L
Linus Torvalds 已提交
2141 2142 2143 2144 2145 2146 2147 2148 2149 2150

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

	return busiest;
}

2151 2152 2153 2154 2155 2156
/*
 * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but
 * so long as it is large enough.
 */
#define MAX_PINNED_INTERVAL	512

L
Linus Torvalds 已提交
2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168
/*
 * 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;
2169
	int nr_moved, all_pinned = 0;
2170
	int active_balance = 0;
N
Nick Piggin 已提交
2171 2172 2173 2174
	int sd_idle = 0;

	if (idle != NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER)
		sd_idle = 1;
L
Linus Torvalds 已提交
2175 2176 2177

	schedstat_inc(sd, lb_cnt[idle]);

N
Nick Piggin 已提交
2178
	group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle);
L
Linus Torvalds 已提交
2179 2180 2181 2182 2183
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[idle]);
		goto out_balanced;
	}

2184
	busiest = find_busiest_queue(group, idle);
L
Linus Torvalds 已提交
2185 2186 2187 2188 2189
	if (!busiest) {
		schedstat_inc(sd, lb_nobusyq[idle]);
		goto out_balanced;
	}

N
Nick Piggin 已提交
2190
	BUG_ON(busiest == this_rq);
L
Linus Torvalds 已提交
2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201

	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.
		 */
N
Nick Piggin 已提交
2202
		double_rq_lock(this_rq, busiest);
L
Linus Torvalds 已提交
2203
		nr_moved = move_tasks(this_rq, this_cpu, busiest,
2204
					imbalance, sd, idle, &all_pinned);
N
Nick Piggin 已提交
2205
		double_rq_unlock(this_rq, busiest);
2206 2207 2208 2209

		/* All tasks on this runqueue were pinned by CPU affinity */
		if (unlikely(all_pinned))
			goto out_balanced;
L
Linus Torvalds 已提交
2210
	}
2211

L
Linus Torvalds 已提交
2212 2213 2214 2215 2216 2217 2218
	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);
2219 2220 2221 2222 2223 2224 2225 2226 2227 2228

			/* 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;
			}

L
Linus Torvalds 已提交
2229 2230 2231
			if (!busiest->active_balance) {
				busiest->active_balance = 1;
				busiest->push_cpu = this_cpu;
2232
				active_balance = 1;
L
Linus Torvalds 已提交
2233 2234
			}
			spin_unlock(&busiest->lock);
2235
			if (active_balance)
L
Linus Torvalds 已提交
2236 2237 2238 2239 2240 2241
				wake_up_process(busiest->migration_thread);

			/*
			 * We've kicked active balancing, reset the failure
			 * counter.
			 */
2242
			sd->nr_balance_failed = sd->cache_nice_tries+1;
L
Linus Torvalds 已提交
2243
		}
2244
	} else
L
Linus Torvalds 已提交
2245 2246
		sd->nr_balance_failed = 0;

2247
	if (likely(!active_balance)) {
L
Linus Torvalds 已提交
2248 2249
		/* We were unbalanced, so reset the balancing interval */
		sd->balance_interval = sd->min_interval;
2250 2251 2252 2253 2254 2255 2256 2257 2258
	} 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;
L
Linus Torvalds 已提交
2259 2260
	}

N
Nick Piggin 已提交
2261 2262
	if (!nr_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER)
		return -1;
L
Linus Torvalds 已提交
2263 2264 2265 2266 2267
	return nr_moved;

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

2268
	sd->nr_balance_failed = 0;
2269 2270

out_one_pinned:
L
Linus Torvalds 已提交
2271
	/* tune up the balancing interval */
2272 2273
	if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) ||
			(sd->balance_interval < sd->max_interval))
L
Linus Torvalds 已提交
2274 2275
		sd->balance_interval *= 2;

N
Nick Piggin 已提交
2276 2277
	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
		return -1;
L
Linus Torvalds 已提交
2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294
	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;
N
Nick Piggin 已提交
2295 2296 2297 2298
	int sd_idle = 0;

	if (sd->flags & SD_SHARE_CPUPOWER)
		sd_idle = 1;
L
Linus Torvalds 已提交
2299 2300

	schedstat_inc(sd, lb_cnt[NEWLY_IDLE]);
N
Nick Piggin 已提交
2301
	group = find_busiest_group(sd, this_cpu, &imbalance, NEWLY_IDLE, &sd_idle);
L
Linus Torvalds 已提交
2302 2303
	if (!group) {
		schedstat_inc(sd, lb_nobusyg[NEWLY_IDLE]);
2304
		goto out_balanced;
L
Linus Torvalds 已提交
2305 2306
	}

2307
	busiest = find_busiest_queue(group, NEWLY_IDLE);
N
Nick Piggin 已提交
2308
	if (!busiest) {
L
Linus Torvalds 已提交
2309
		schedstat_inc(sd, lb_nobusyq[NEWLY_IDLE]);
2310
		goto out_balanced;
L
Linus Torvalds 已提交
2311 2312
	}

N
Nick Piggin 已提交
2313 2314
	BUG_ON(busiest == this_rq);

L
Linus Torvalds 已提交
2315
	schedstat_add(sd, lb_imbalance[NEWLY_IDLE], imbalance);
2316 2317 2318 2319 2320 2321

	nr_moved = 0;
	if (busiest->nr_running > 1) {
		/* Attempt to move tasks */
		double_lock_balance(this_rq, busiest);
		nr_moved = move_tasks(this_rq, this_cpu, busiest,
2322
					imbalance, sd, NEWLY_IDLE, NULL);
2323 2324 2325
		spin_unlock(&busiest->lock);
	}

N
Nick Piggin 已提交
2326
	if (!nr_moved) {
L
Linus Torvalds 已提交
2327
		schedstat_inc(sd, lb_failed[NEWLY_IDLE]);
N
Nick Piggin 已提交
2328 2329 2330
		if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
			return -1;
	} else
2331
		sd->nr_balance_failed = 0;
L
Linus Torvalds 已提交
2332 2333

	return nr_moved;
2334 2335 2336

out_balanced:
	schedstat_inc(sd, lb_balanced[NEWLY_IDLE]);
N
Nick Piggin 已提交
2337 2338
	if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER)
		return -1;
2339 2340
	sd->nr_balance_failed = 0;
	return 0;
L
Linus Torvalds 已提交
2341 2342 2343 2344 2345 2346
}

/*
 * idle_balance is called by schedule() if this_cpu is about to become
 * idle. Attempts to pull tasks from other CPUs.
 */
2347
static void idle_balance(int this_cpu, runqueue_t *this_rq)
L
Linus Torvalds 已提交
2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372
{
	struct sched_domain *sd;

	for_each_domain(this_cpu, sd) {
		if (sd->flags & SD_BALANCE_NEWIDLE) {
			if (load_balance_newidle(this_cpu, this_rq, sd)) {
				/* We've pulled tasks over so stop searching */
				break;
			}
		}
	}
}

/*
 * active_load_balance is run by migration threads. It pushes running tasks
 * off the busiest CPU onto idle CPUs. It requires at least 1 task to be
 * running on each physical CPU where possible, and avoids physical /
 * logical imbalances.
 *
 * Called with busiest_rq locked.
 */
static void active_load_balance(runqueue_t *busiest_rq, int busiest_cpu)
{
	struct sched_domain *sd;
	runqueue_t *target_rq;
2373 2374 2375 2376 2377 2378 2379
	int target_cpu = busiest_rq->push_cpu;

	if (busiest_rq->nr_running <= 1)
		/* no task to move */
		return;

	target_rq = cpu_rq(target_cpu);
L
Linus Torvalds 已提交
2380 2381

	/*
2382 2383 2384
	 * This condition is "impossible", if it occurs
	 * we need to fix it.  Originally reported by
	 * Bjorn Helgaas on a 128-cpu setup.
L
Linus Torvalds 已提交
2385
	 */
2386
	BUG_ON(busiest_rq == target_rq);
L
Linus Torvalds 已提交
2387

2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407
	/* move a task from busiest_rq to target_rq */
	double_lock_balance(busiest_rq, target_rq);

	/* Search for an sd spanning us and the target CPU. */
	for_each_domain(target_cpu, sd)
		if ((sd->flags & SD_LOAD_BALANCE) &&
			cpu_isset(busiest_cpu, sd->span))
				break;

	if (unlikely(sd == NULL))
		goto out;

	schedstat_inc(sd, alb_cnt);

	if (move_tasks(target_rq, target_cpu, busiest_rq, 1, sd, SCHED_IDLE, NULL))
		schedstat_inc(sd, alb_pushed);
	else
		schedstat_inc(sd, alb_failed);
out:
	spin_unlock(&target_rq->lock);
L
Linus Torvalds 已提交
2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427
}

/*
 * rebalance_tick will get called every timer tick, on every CPU.
 *
 * It checks each scheduling domain to see if it is due to be balanced,
 * and initiates a balancing operation if so.
 *
 * Balancing parameters are set up in arch_init_sched_domains.
 */

/* Don't have all balancing operations going off at once */
#define CPU_OFFSET(cpu) (HZ * cpu / NR_CPUS)

static void rebalance_tick(int this_cpu, runqueue_t *this_rq,
			   enum idle_type idle)
{
	unsigned long old_load, this_load;
	unsigned long j = jiffies + CPU_OFFSET(this_cpu);
	struct sched_domain *sd;
N
Nick Piggin 已提交
2428
	int i;
L
Linus Torvalds 已提交
2429 2430

	this_load = this_rq->nr_running * SCHED_LOAD_SCALE;
N
Nick Piggin 已提交
2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444
	/* Update our load */
	for (i = 0; i < 3; i++) {
		unsigned long new_load = this_load;
		int scale = 1 << i;
		old_load = this_rq->cpu_load[i];
		/*
		 * Round up the averaging division if load is increasing. This
		 * prevents us from getting stuck on 9 if the load is 10, for
		 * example.
		 */
		if (new_load > old_load)
			new_load += scale-1;
		this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) / scale;
	}
L
Linus Torvalds 已提交
2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462

	for_each_domain(this_cpu, sd) {
		unsigned long interval;

		if (!(sd->flags & SD_LOAD_BALANCE))
			continue;

		interval = sd->balance_interval;
		if (idle != SCHED_IDLE)
			interval *= sd->busy_factor;

		/* scale ms to jiffies */
		interval = msecs_to_jiffies(interval);
		if (unlikely(!interval))
			interval = 1;

		if (j - sd->last_balance >= interval) {
			if (load_balance(this_cpu, this_rq, sd, idle)) {
2463 2464
				/*
				 * We've pulled tasks over so either we're no
N
Nick Piggin 已提交
2465 2466 2467
				 * longer idle, or one of our SMT siblings is
				 * not idle.
				 */
L
Linus Torvalds 已提交
2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668
				idle = NOT_IDLE;
			}
			sd->last_balance += interval;
		}
	}
}
#else
/*
 * on UP we do not need to balance between CPUs:
 */
static inline void rebalance_tick(int cpu, runqueue_t *rq, enum idle_type idle)
{
}
static inline void idle_balance(int cpu, runqueue_t *rq)
{
}
#endif

static inline int wake_priority_sleeper(runqueue_t *rq)
{
	int ret = 0;
#ifdef CONFIG_SCHED_SMT
	spin_lock(&rq->lock);
	/*
	 * If an SMT sibling task has been put to sleep for priority
	 * reasons reschedule the idle task to see if it can now run.
	 */
	if (rq->nr_running) {
		resched_task(rq->idle);
		ret = 1;
	}
	spin_unlock(&rq->lock);
#endif
	return ret;
}

DEFINE_PER_CPU(struct kernel_stat, kstat);

EXPORT_PER_CPU_SYMBOL(kstat);

/*
 * This is called on clock ticks and on context switches.
 * Bank in p->sched_time the ns elapsed since the last tick or switch.
 */
static inline void update_cpu_clock(task_t *p, runqueue_t *rq,
				    unsigned long long now)
{
	unsigned long long last = max(p->timestamp, rq->timestamp_last_tick);
	p->sched_time += now - last;
}

/*
 * Return current->sched_time plus any more ns on the sched_clock
 * that have not yet been banked.
 */
unsigned long long current_sched_time(const task_t *tsk)
{
	unsigned long long ns;
	unsigned long flags;
	local_irq_save(flags);
	ns = max(tsk->timestamp, task_rq(tsk)->timestamp_last_tick);
	ns = tsk->sched_time + (sched_clock() - ns);
	local_irq_restore(flags);
	return ns;
}

/*
 * Account user cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @hardirq_offset: the offset to subtract from hardirq_count()
 * @cputime: the cpu time spent in user space since the last update
 */
void account_user_time(struct task_struct *p, cputime_t cputime)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t tmp;

	p->utime = cputime_add(p->utime, cputime);

	/* Add user time to cpustat. */
	tmp = cputime_to_cputime64(cputime);
	if (TASK_NICE(p) > 0)
		cpustat->nice = cputime64_add(cpustat->nice, tmp);
	else
		cpustat->user = cputime64_add(cpustat->user, tmp);
}

/*
 * Account system cpu time to a process.
 * @p: the process that the cpu time gets accounted to
 * @hardirq_offset: the offset to subtract from hardirq_count()
 * @cputime: the cpu time spent in kernel space since the last update
 */
void account_system_time(struct task_struct *p, int hardirq_offset,
			 cputime_t cputime)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	runqueue_t *rq = this_rq();
	cputime64_t tmp;

	p->stime = cputime_add(p->stime, cputime);

	/* Add system time to cpustat. */
	tmp = cputime_to_cputime64(cputime);
	if (hardirq_count() - hardirq_offset)
		cpustat->irq = cputime64_add(cpustat->irq, tmp);
	else if (softirq_count())
		cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
	else if (p != rq->idle)
		cpustat->system = cputime64_add(cpustat->system, tmp);
	else if (atomic_read(&rq->nr_iowait) > 0)
		cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
	else
		cpustat->idle = cputime64_add(cpustat->idle, tmp);
	/* Account for system time used */
	acct_update_integrals(p);
}

/*
 * Account for involuntary wait time.
 * @p: the process from which the cpu time has been stolen
 * @steal: the cpu time spent in involuntary wait
 */
void account_steal_time(struct task_struct *p, cputime_t steal)
{
	struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
	cputime64_t tmp = cputime_to_cputime64(steal);
	runqueue_t *rq = this_rq();

	if (p == rq->idle) {
		p->stime = cputime_add(p->stime, steal);
		if (atomic_read(&rq->nr_iowait) > 0)
			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
		else
			cpustat->idle = cputime64_add(cpustat->idle, tmp);
	} else
		cpustat->steal = cputime64_add(cpustat->steal, tmp);
}

/*
 * This function gets called by the timer code, with HZ frequency.
 * We call it with interrupts disabled.
 *
 * It also gets called by the fork code, when changing the parent's
 * timeslices.
 */
void scheduler_tick(void)
{
	int cpu = smp_processor_id();
	runqueue_t *rq = this_rq();
	task_t *p = current;
	unsigned long long now = sched_clock();

	update_cpu_clock(p, rq, now);

	rq->timestamp_last_tick = now;

	if (p == rq->idle) {
		if (wake_priority_sleeper(rq))
			goto out;
		rebalance_tick(cpu, rq, SCHED_IDLE);
		return;
	}

	/* Task might have expired already, but not scheduled off yet */
	if (p->array != rq->active) {
		set_tsk_need_resched(p);
		goto out;
	}
	spin_lock(&rq->lock);
	/*
	 * The task was running during this tick - update the
	 * time slice counter. Note: we do not update a thread's
	 * priority until it either goes to sleep or uses up its
	 * timeslice. This makes it possible for interactive tasks
	 * to use up their timeslices at their highest priority levels.
	 */
	if (rt_task(p)) {
		/*
		 * RR tasks need a special form of timeslice management.
		 * FIFO tasks have no timeslices.
		 */
		if ((p->policy == SCHED_RR) && !--p->time_slice) {
			p->time_slice = task_timeslice(p);
			p->first_time_slice = 0;
			set_tsk_need_resched(p);

			/* put it at the end of the queue: */
			requeue_task(p, rq->active);
		}
		goto out_unlock;
	}
	if (!--p->time_slice) {
		dequeue_task(p, rq->active);
		set_tsk_need_resched(p);
		p->prio = effective_prio(p);
		p->time_slice = task_timeslice(p);
		p->first_time_slice = 0;

		if (!rq->expired_timestamp)
			rq->expired_timestamp = jiffies;
2669
		if (!TASK_INTERACTIVE(p) || expired_starving(rq)) {
L
Linus Torvalds 已提交
2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707
			enqueue_task(p, rq->expired);
			if (p->static_prio < rq->best_expired_prio)
				rq->best_expired_prio = p->static_prio;
		} else
			enqueue_task(p, rq->active);
	} else {
		/*
		 * Prevent a too long timeslice allowing a task to monopolize
		 * the CPU. We do this by splitting up the timeslice into
		 * smaller pieces.
		 *
		 * Note: this does not mean the task's timeslices expire or
		 * get lost in any way, they just might be preempted by
		 * another task of equal priority. (one with higher
		 * priority would have preempted this task already.) We
		 * requeue this task to the end of the list on this priority
		 * level, which is in essence a round-robin of tasks with
		 * equal priority.
		 *
		 * This only applies to tasks in the interactive
		 * delta range with at least TIMESLICE_GRANULARITY to requeue.
		 */
		if (TASK_INTERACTIVE(p) && !((task_timeslice(p) -
			p->time_slice) % TIMESLICE_GRANULARITY(p)) &&
			(p->time_slice >= TIMESLICE_GRANULARITY(p)) &&
			(p->array == rq->active)) {

			requeue_task(p, rq->active);
			set_tsk_need_resched(p);
		}
	}
out_unlock:
	spin_unlock(&rq->lock);
out:
	rebalance_tick(cpu, rq, NOT_IDLE);
}

#ifdef CONFIG_SCHED_SMT
2708 2709 2710 2711 2712 2713 2714
static inline void wakeup_busy_runqueue(runqueue_t *rq)
{
	/* If an SMT runqueue is sleeping due to priority reasons wake it up */
	if (rq->curr == rq->idle && rq->nr_running)
		resched_task(rq->idle);
}

2715
static void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
L
Linus Torvalds 已提交
2716
{
N
Nick Piggin 已提交
2717
	struct sched_domain *tmp, *sd = NULL;
L
Linus Torvalds 已提交
2718 2719 2720
	cpumask_t sibling_map;
	int i;

N
Nick Piggin 已提交
2721 2722 2723 2724 2725
	for_each_domain(this_cpu, tmp)
		if (tmp->flags & SD_SHARE_CPUPOWER)
			sd = tmp;

	if (!sd)
L
Linus Torvalds 已提交
2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747
		return;

	/*
	 * Unlock the current runqueue because we have to lock in
	 * CPU order to avoid deadlocks. Caller knows that we might
	 * unlock. We keep IRQs disabled.
	 */
	spin_unlock(&this_rq->lock);

	sibling_map = sd->span;

	for_each_cpu_mask(i, sibling_map)
		spin_lock(&cpu_rq(i)->lock);
	/*
	 * We clear this CPU from the mask. This both simplifies the
	 * inner loop and keps this_rq locked when we exit:
	 */
	cpu_clear(this_cpu, sibling_map);

	for_each_cpu_mask(i, sibling_map) {
		runqueue_t *smt_rq = cpu_rq(i);

2748
		wakeup_busy_runqueue(smt_rq);
L
Linus Torvalds 已提交
2749 2750 2751 2752 2753 2754 2755 2756 2757 2758
	}

	for_each_cpu_mask(i, sibling_map)
		spin_unlock(&cpu_rq(i)->lock);
	/*
	 * We exit with this_cpu's rq still held and IRQs
	 * still disabled:
	 */
}

2759 2760 2761 2762 2763 2764 2765 2766 2767 2768
/*
 * number of 'lost' timeslices this task wont be able to fully
 * utilize, if another task runs on a sibling. This models the
 * slowdown effect of other tasks running on siblings:
 */
static inline unsigned long smt_slice(task_t *p, struct sched_domain *sd)
{
	return p->time_slice * (100 - sd->per_cpu_gain) / 100;
}

2769
static int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
L
Linus Torvalds 已提交
2770
{
N
Nick Piggin 已提交
2771
	struct sched_domain *tmp, *sd = NULL;
L
Linus Torvalds 已提交
2772 2773 2774 2775 2776
	cpumask_t sibling_map;
	prio_array_t *array;
	int ret = 0, i;
	task_t *p;

N
Nick Piggin 已提交
2777 2778 2779 2780 2781
	for_each_domain(this_cpu, tmp)
		if (tmp->flags & SD_SHARE_CPUPOWER)
			sd = tmp;

	if (!sd)
L
Linus Torvalds 已提交
2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811
		return 0;

	/*
	 * The same locking rules and details apply as for
	 * wake_sleeping_dependent():
	 */
	spin_unlock(&this_rq->lock);
	sibling_map = sd->span;
	for_each_cpu_mask(i, sibling_map)
		spin_lock(&cpu_rq(i)->lock);
	cpu_clear(this_cpu, sibling_map);

	/*
	 * Establish next task to be run - it might have gone away because
	 * we released the runqueue lock above:
	 */
	if (!this_rq->nr_running)
		goto out_unlock;
	array = this_rq->active;
	if (!array->nr_active)
		array = this_rq->expired;
	BUG_ON(!array->nr_active);

	p = list_entry(array->queue[sched_find_first_bit(array->bitmap)].next,
		task_t, run_list);

	for_each_cpu_mask(i, sibling_map) {
		runqueue_t *smt_rq = cpu_rq(i);
		task_t *smt_curr = smt_rq->curr;

2812 2813 2814 2815
		/* Kernel threads do not participate in dependent sleeping */
		if (!p->mm || !smt_curr->mm || rt_task(p))
			goto check_smt_task;

L
Linus Torvalds 已提交
2816 2817 2818 2819 2820 2821 2822 2823
		/*
		 * If a user task with lower static priority than the
		 * running task on the SMT sibling is trying to schedule,
		 * delay it till there is proportionately less timeslice
		 * left of the sibling task to prevent a lower priority
		 * task from using an unfair proportion of the
		 * physical cpu's resources. -ck
		 */
2824 2825 2826 2827 2828 2829 2830 2831 2832
		if (rt_task(smt_curr)) {
			/*
			 * With real time tasks we run non-rt tasks only
			 * per_cpu_gain% of the time.
			 */
			if ((jiffies % DEF_TIMESLICE) >
				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
					ret = 1;
		} else
2833 2834 2835
			if (smt_curr->static_prio < p->static_prio &&
				!TASK_PREEMPTS_CURR(p, smt_rq) &&
				smt_slice(smt_curr, sd) > task_timeslice(p))
2836 2837 2838 2839 2840 2841 2842 2843 2844 2845
					ret = 1;

check_smt_task:
		if ((!smt_curr->mm && smt_curr != smt_rq->idle) ||
			rt_task(smt_curr))
				continue;
		if (!p->mm) {
			wakeup_busy_runqueue(smt_rq);
			continue;
		}
L
Linus Torvalds 已提交
2846 2847

		/*
2848 2849 2850
		 * Reschedule a lower priority task on the SMT sibling for
		 * it to be put to sleep, or wake it up if it has been put to
		 * sleep for priority reasons to see if it should run now.
L
Linus Torvalds 已提交
2851
		 */
2852 2853 2854 2855 2856
		if (rt_task(p)) {
			if ((jiffies % DEF_TIMESLICE) >
				(sd->per_cpu_gain * DEF_TIMESLICE / 100))
					resched_task(smt_curr);
		} else {
2857 2858
			if (TASK_PREEMPTS_CURR(p, smt_rq) &&
				smt_slice(p, sd) > task_timeslice(smt_curr))
2859 2860 2861 2862
					resched_task(smt_curr);
			else
				wakeup_busy_runqueue(smt_rq);
		}
L
Linus Torvalds 已提交
2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886
	}
out_unlock:
	for_each_cpu_mask(i, sibling_map)
		spin_unlock(&cpu_rq(i)->lock);
	return ret;
}
#else
static inline void wake_sleeping_dependent(int this_cpu, runqueue_t *this_rq)
{
}

static inline int dependent_sleeper(int this_cpu, runqueue_t *this_rq)
{
	return 0;
}
#endif

#if defined(CONFIG_PREEMPT) && defined(CONFIG_DEBUG_PREEMPT)

void fastcall add_preempt_count(int val)
{
	/*
	 * Underflow?
	 */
2887
	BUG_ON((preempt_count() < 0));
L
Linus Torvalds 已提交
2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911
	preempt_count() += val;
	/*
	 * Spinlock count overflowing soon?
	 */
	BUG_ON((preempt_count() & PREEMPT_MASK) >= PREEMPT_MASK-10);
}
EXPORT_SYMBOL(add_preempt_count);

void fastcall sub_preempt_count(int val)
{
	/*
	 * Underflow?
	 */
	BUG_ON(val > preempt_count());
	/*
	 * Is the spinlock portion underflowing?
	 */
	BUG_ON((val < PREEMPT_MASK) && !(preempt_count() & PREEMPT_MASK));
	preempt_count() -= val;
}
EXPORT_SYMBOL(sub_preempt_count);

#endif

2912 2913 2914 2915 2916 2917
static inline int interactive_sleep(enum sleep_type sleep_type)
{
	return (sleep_type == SLEEP_INTERACTIVE ||
		sleep_type == SLEEP_INTERRUPTED);
}

L
Linus Torvalds 已提交
2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929
/*
 * schedule() is the main scheduler function.
 */
asmlinkage void __sched schedule(void)
{
	long *switch_count;
	task_t *prev, *next;
	runqueue_t *rq;
	prio_array_t *array;
	struct list_head *queue;
	unsigned long long now;
	unsigned long run_time;
2930
	int cpu, idx, new_prio;
L
Linus Torvalds 已提交
2931 2932 2933 2934 2935 2936

	/*
	 * Test if we are atomic.  Since do_exit() needs to call into
	 * schedule() atomically, we ignore that path for now.
	 * Otherwise, whine if we are scheduling when we should not be.
	 */
2937 2938 2939 2940 2941
	if (unlikely(in_atomic() && !current->exit_state)) {
		printk(KERN_ERR "BUG: scheduling while atomic: "
			"%s/0x%08x/%d\n",
			current->comm, preempt_count(), current->pid);
		dump_stack();
L
Linus Torvalds 已提交
2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962
	}
	profile_hit(SCHED_PROFILING, __builtin_return_address(0));

need_resched:
	preempt_disable();
	prev = current;
	release_kernel_lock(prev);
need_resched_nonpreemptible:
	rq = this_rq();

	/*
	 * The idle thread is not allowed to schedule!
	 * Remove this check after it has been exercised a bit.
	 */
	if (unlikely(prev == rq->idle) && prev->state != TASK_RUNNING) {
		printk(KERN_ERR "bad: scheduling from the idle thread!\n");
		dump_stack();
	}

	schedstat_inc(rq, sched_cnt);
	now = sched_clock();
2963
	if (likely((long long)(now - prev->timestamp) < NS_MAX_SLEEP_AVG)) {
L
Linus Torvalds 已提交
2964
		run_time = now - prev->timestamp;
2965
		if (unlikely((long long)(now - prev->timestamp) < 0))
L
Linus Torvalds 已提交
2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040
			run_time = 0;
	} else
		run_time = NS_MAX_SLEEP_AVG;

	/*
	 * Tasks charged proportionately less run_time at high sleep_avg to
	 * delay them losing their interactive status
	 */
	run_time /= (CURRENT_BONUS(prev) ? : 1);

	spin_lock_irq(&rq->lock);

	if (unlikely(prev->flags & PF_DEAD))
		prev->state = EXIT_DEAD;

	switch_count = &prev->nivcsw;
	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
		switch_count = &prev->nvcsw;
		if (unlikely((prev->state & TASK_INTERRUPTIBLE) &&
				unlikely(signal_pending(prev))))
			prev->state = TASK_RUNNING;
		else {
			if (prev->state == TASK_UNINTERRUPTIBLE)
				rq->nr_uninterruptible++;
			deactivate_task(prev, rq);
		}
	}

	cpu = smp_processor_id();
	if (unlikely(!rq->nr_running)) {
go_idle:
		idle_balance(cpu, rq);
		if (!rq->nr_running) {
			next = rq->idle;
			rq->expired_timestamp = 0;
			wake_sleeping_dependent(cpu, rq);
			/*
			 * wake_sleeping_dependent() might have released
			 * the runqueue, so break out if we got new
			 * tasks meanwhile:
			 */
			if (!rq->nr_running)
				goto switch_tasks;
		}
	} else {
		if (dependent_sleeper(cpu, rq)) {
			next = rq->idle;
			goto switch_tasks;
		}
		/*
		 * dependent_sleeper() releases and reacquires the runqueue
		 * lock, hence go into the idle loop if the rq went
		 * empty meanwhile:
		 */
		if (unlikely(!rq->nr_running))
			goto go_idle;
	}

	array = rq->active;
	if (unlikely(!array->nr_active)) {
		/*
		 * Switch the active and expired arrays.
		 */
		schedstat_inc(rq, sched_switch);
		rq->active = rq->expired;
		rq->expired = array;
		array = rq->active;
		rq->expired_timestamp = 0;
		rq->best_expired_prio = MAX_PRIO;
	}

	idx = sched_find_first_bit(array->bitmap);
	queue = array->queue + idx;
	next = list_entry(queue->next, task_t, run_list);

3041
	if (!rt_task(next) && interactive_sleep(next->sleep_type)) {
L
Linus Torvalds 已提交
3042
		unsigned long long delta = now - next->timestamp;
3043
		if (unlikely((long long)(now - next->timestamp) < 0))
L
Linus Torvalds 已提交
3044 3045
			delta = 0;

3046
		if (next->sleep_type == SLEEP_INTERACTIVE)
L
Linus Torvalds 已提交
3047 3048 3049
			delta = delta * (ON_RUNQUEUE_WEIGHT * 128 / 100) / 128;

		array = next->array;
3050 3051 3052 3053 3054 3055
		new_prio = recalc_task_prio(next, next->timestamp + delta);

		if (unlikely(next->prio != new_prio)) {
			dequeue_task(next, array);
			next->prio = new_prio;
			enqueue_task(next, array);
3056
		}
L
Linus Torvalds 已提交
3057
	}
3058
	next->sleep_type = SLEEP_NORMAL;
L
Linus Torvalds 已提交
3059 3060 3061 3062
switch_tasks:
	if (next == rq->idle)
		schedstat_inc(rq, sched_goidle);
	prefetch(next);
3063
	prefetch_stack(next);
L
Linus Torvalds 已提交
3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080
	clear_tsk_need_resched(prev);
	rcu_qsctr_inc(task_cpu(prev));

	update_cpu_clock(prev, rq, now);

	prev->sleep_avg -= run_time;
	if ((long)prev->sleep_avg <= 0)
		prev->sleep_avg = 0;
	prev->timestamp = prev->last_ran = now;

	sched_info_switch(prev, next);
	if (likely(prev != next)) {
		next->timestamp = now;
		rq->nr_switches++;
		rq->curr = next;
		++*switch_count;

3081
		prepare_task_switch(rq, next);
L
Linus Torvalds 已提交
3082 3083
		prev = context_switch(rq, prev, next);
		barrier();
3084 3085 3086 3087 3088 3089
		/*
		 * this_rq must be evaluated again because prev may have moved
		 * CPUs since it called schedule(), thus the 'rq' on its stack
		 * frame will be invalid.
		 */
		finish_task_switch(this_rq(), prev);
L
Linus Torvalds 已提交
3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190
	} else
		spin_unlock_irq(&rq->lock);

	prev = current;
	if (unlikely(reacquire_kernel_lock(prev) < 0))
		goto need_resched_nonpreemptible;
	preempt_enable_no_resched();
	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
		goto need_resched;
}

EXPORT_SYMBOL(schedule);

#ifdef CONFIG_PREEMPT
/*
 * this is is the entry point to schedule() from in-kernel preemption
 * off of preempt_enable.  Kernel preemptions off return from interrupt
 * occur there and call schedule directly.
 */
asmlinkage void __sched preempt_schedule(void)
{
	struct thread_info *ti = current_thread_info();
#ifdef CONFIG_PREEMPT_BKL
	struct task_struct *task = current;
	int saved_lock_depth;
#endif
	/*
	 * If there is a non-zero preempt_count or interrupts are disabled,
	 * we do not want to preempt the current task.  Just return..
	 */
	if (unlikely(ti->preempt_count || irqs_disabled()))
		return;

need_resched:
	add_preempt_count(PREEMPT_ACTIVE);
	/*
	 * We keep the big kernel semaphore locked, but we
	 * clear ->lock_depth so that schedule() doesnt
	 * auto-release the semaphore:
	 */
#ifdef CONFIG_PREEMPT_BKL
	saved_lock_depth = task->lock_depth;
	task->lock_depth = -1;
#endif
	schedule();
#ifdef CONFIG_PREEMPT_BKL
	task->lock_depth = saved_lock_depth;
#endif
	sub_preempt_count(PREEMPT_ACTIVE);

	/* we could miss a preemption opportunity between schedule and now */
	barrier();
	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
		goto need_resched;
}

EXPORT_SYMBOL(preempt_schedule);

/*
 * this is is the entry point to schedule() from kernel preemption
 * off of irq context.
 * Note, that this is called and return with irqs disabled. This will
 * protect us against recursive calling from irq.
 */
asmlinkage void __sched preempt_schedule_irq(void)
{
	struct thread_info *ti = current_thread_info();
#ifdef CONFIG_PREEMPT_BKL
	struct task_struct *task = current;
	int saved_lock_depth;
#endif
	/* Catch callers which need to be fixed*/
	BUG_ON(ti->preempt_count || !irqs_disabled());

need_resched:
	add_preempt_count(PREEMPT_ACTIVE);
	/*
	 * We keep the big kernel semaphore locked, but we
	 * clear ->lock_depth so that schedule() doesnt
	 * auto-release the semaphore:
	 */
#ifdef CONFIG_PREEMPT_BKL
	saved_lock_depth = task->lock_depth;
	task->lock_depth = -1;
#endif
	local_irq_enable();
	schedule();
	local_irq_disable();
#ifdef CONFIG_PREEMPT_BKL
	task->lock_depth = saved_lock_depth;
#endif
	sub_preempt_count(PREEMPT_ACTIVE);

	/* we could miss a preemption opportunity between schedule and now */
	barrier();
	if (unlikely(test_thread_flag(TIF_NEED_RESCHED)))
		goto need_resched;
}

#endif /* CONFIG_PREEMPT */

I
Ingo Molnar 已提交
3191 3192
int default_wake_function(wait_queue_t *curr, unsigned mode, int sync,
			  void *key)
L
Linus Torvalds 已提交
3193
{
3194
	task_t *p = curr->private;
L
Linus Torvalds 已提交
3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230
	return try_to_wake_up(p, mode, sync);
}

EXPORT_SYMBOL(default_wake_function);

/*
 * The core wakeup function.  Non-exclusive wakeups (nr_exclusive == 0) just
 * wake everything up.  If it's an exclusive wakeup (nr_exclusive == small +ve
 * number) then we wake all the non-exclusive tasks and one exclusive task.
 *
 * There are circumstances in which we can try to wake a task which has already
 * started to run but is not in state TASK_RUNNING.  try_to_wake_up() returns
 * zero in this (rare) case, and we handle it by continuing to scan the queue.
 */
static void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
			     int nr_exclusive, int sync, void *key)
{
	struct list_head *tmp, *next;

	list_for_each_safe(tmp, next, &q->task_list) {
		wait_queue_t *curr;
		unsigned flags;
		curr = list_entry(tmp, wait_queue_t, task_list);
		flags = curr->flags;
		if (curr->func(curr, mode, sync, key) &&
		    (flags & WQ_FLAG_EXCLUSIVE) &&
		    !--nr_exclusive)
			break;
	}
}

/**
 * __wake_up - wake up threads blocked on a waitqueue.
 * @q: the waitqueue
 * @mode: which threads
 * @nr_exclusive: how many wake-one or wake-many threads to wake up
3231
 * @key: is directly passed to the wakeup function
L
Linus Torvalds 已提交
3232 3233
 */
void fastcall __wake_up(wait_queue_head_t *q, unsigned int mode,
I
Ingo Molnar 已提交
3234
			int nr_exclusive, void *key)
L
Linus Torvalds 已提交
3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253
{
	unsigned long flags;

	spin_lock_irqsave(&q->lock, flags);
	__wake_up_common(q, mode, nr_exclusive, 0, key);
	spin_unlock_irqrestore(&q->lock, flags);
}

EXPORT_SYMBOL(__wake_up);

/*
 * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
 */
void fastcall __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
{
	__wake_up_common(q, mode, 1, 0, NULL);
}

/**
3254
 * __wake_up_sync - wake up threads blocked on a waitqueue.
L
Linus Torvalds 已提交
3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265
 * @q: the waitqueue
 * @mode: which threads
 * @nr_exclusive: how many wake-one or wake-many threads to wake up
 *
 * The sync wakeup differs that the waker knows that it will schedule
 * away soon, so while the target thread will be woken up, it will not
 * be migrated to another CPU - ie. the two threads are 'synchronized'
 * with each other. This can prevent needless bouncing between CPUs.
 *
 * On UP it can prevent extra preemption.
 */
I
Ingo Molnar 已提交
3266 3267
void fastcall
__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive)
L
Linus Torvalds 已提交
3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457
{
	unsigned long flags;
	int sync = 1;

	if (unlikely(!q))
		return;

	if (unlikely(!nr_exclusive))
		sync = 0;

	spin_lock_irqsave(&q->lock, flags);
	__wake_up_common(q, mode, nr_exclusive, sync, NULL);
	spin_unlock_irqrestore(&q->lock, flags);
}
EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */

void fastcall complete(struct completion *x)
{
	unsigned long flags;

	spin_lock_irqsave(&x->wait.lock, flags);
	x->done++;
	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
			 1, 0, NULL);
	spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);

void fastcall complete_all(struct completion *x)
{
	unsigned long flags;

	spin_lock_irqsave(&x->wait.lock, flags);
	x->done += UINT_MAX/2;
	__wake_up_common(&x->wait, TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE,
			 0, 0, NULL);
	spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);

void fastcall __sched wait_for_completion(struct completion *x)
{
	might_sleep();
	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			__set_current_state(TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			schedule();
			spin_lock_irq(&x->wait.lock);
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
	spin_unlock_irq(&x->wait.lock);
}
EXPORT_SYMBOL(wait_for_completion);

unsigned long fastcall __sched
wait_for_completion_timeout(struct completion *x, unsigned long timeout)
{
	might_sleep();

	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			__set_current_state(TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			timeout = schedule_timeout(timeout);
			spin_lock_irq(&x->wait.lock);
			if (!timeout) {
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
out:
	spin_unlock_irq(&x->wait.lock);
	return timeout;
}
EXPORT_SYMBOL(wait_for_completion_timeout);

int fastcall __sched wait_for_completion_interruptible(struct completion *x)
{
	int ret = 0;

	might_sleep();

	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			if (signal_pending(current)) {
				ret = -ERESTARTSYS;
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
			__set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			schedule();
			spin_lock_irq(&x->wait.lock);
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
out:
	spin_unlock_irq(&x->wait.lock);

	return ret;
}
EXPORT_SYMBOL(wait_for_completion_interruptible);

unsigned long fastcall __sched
wait_for_completion_interruptible_timeout(struct completion *x,
					  unsigned long timeout)
{
	might_sleep();

	spin_lock_irq(&x->wait.lock);
	if (!x->done) {
		DECLARE_WAITQUEUE(wait, current);

		wait.flags |= WQ_FLAG_EXCLUSIVE;
		__add_wait_queue_tail(&x->wait, &wait);
		do {
			if (signal_pending(current)) {
				timeout = -ERESTARTSYS;
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
			__set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock_irq(&x->wait.lock);
			timeout = schedule_timeout(timeout);
			spin_lock_irq(&x->wait.lock);
			if (!timeout) {
				__remove_wait_queue(&x->wait, &wait);
				goto out;
			}
		} while (!x->done);
		__remove_wait_queue(&x->wait, &wait);
	}
	x->done--;
out:
	spin_unlock_irq(&x->wait.lock);
	return timeout;
}
EXPORT_SYMBOL(wait_for_completion_interruptible_timeout);


#define	SLEEP_ON_VAR					\
	unsigned long flags;				\
	wait_queue_t wait;				\
	init_waitqueue_entry(&wait, current);

#define SLEEP_ON_HEAD					\
	spin_lock_irqsave(&q->lock,flags);		\
	__add_wait_queue(q, &wait);			\
	spin_unlock(&q->lock);

#define	SLEEP_ON_TAIL					\
	spin_lock_irq(&q->lock);			\
	__remove_wait_queue(q, &wait);			\
	spin_unlock_irqrestore(&q->lock, flags);

void fastcall __sched interruptible_sleep_on(wait_queue_head_t *q)
{
	SLEEP_ON_VAR

	current->state = TASK_INTERRUPTIBLE;

	SLEEP_ON_HEAD
	schedule();
	SLEEP_ON_TAIL
}

EXPORT_SYMBOL(interruptible_sleep_on);

I
Ingo Molnar 已提交
3458 3459
long fastcall __sched
interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout)
L
Linus Torvalds 已提交
3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519
{
	SLEEP_ON_VAR

	current->state = TASK_INTERRUPTIBLE;

	SLEEP_ON_HEAD
	timeout = schedule_timeout(timeout);
	SLEEP_ON_TAIL

	return timeout;
}

EXPORT_SYMBOL(interruptible_sleep_on_timeout);

void fastcall __sched sleep_on(wait_queue_head_t *q)
{
	SLEEP_ON_VAR

	current->state = TASK_UNINTERRUPTIBLE;

	SLEEP_ON_HEAD
	schedule();
	SLEEP_ON_TAIL
}

EXPORT_SYMBOL(sleep_on);

long fastcall __sched sleep_on_timeout(wait_queue_head_t *q, long timeout)
{
	SLEEP_ON_VAR

	current->state = TASK_UNINTERRUPTIBLE;

	SLEEP_ON_HEAD
	timeout = schedule_timeout(timeout);
	SLEEP_ON_TAIL

	return timeout;
}

EXPORT_SYMBOL(sleep_on_timeout);

void set_user_nice(task_t *p, long nice)
{
	unsigned long flags;
	prio_array_t *array;
	runqueue_t *rq;
	int old_prio, new_prio, delta;

	if (TASK_NICE(p) == nice || nice < -20 || nice > 19)
		return;
	/*
	 * We have to be careful, if called from sys_setpriority(),
	 * the task might be in the middle of scheduling on another CPU.
	 */
	rq = task_rq_lock(p, &flags);
	/*
	 * The RT priorities are set via sched_setscheduler(), but we still
	 * allow the 'normal' nice value to be set - but as expected
	 * it wont have any effect on scheduling until the task is
3520
	 * not SCHED_NORMAL/SCHED_BATCH:
L
Linus Torvalds 已提交
3521 3522 3523 3524 3525 3526
	 */
	if (rt_task(p)) {
		p->static_prio = NICE_TO_PRIO(nice);
		goto out_unlock;
	}
	array = p->array;
N
Nick Piggin 已提交
3527
	if (array)
L
Linus Torvalds 已提交
3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550
		dequeue_task(p, array);

	old_prio = p->prio;
	new_prio = NICE_TO_PRIO(nice);
	delta = new_prio - old_prio;
	p->static_prio = NICE_TO_PRIO(nice);
	p->prio += delta;

	if (array) {
		enqueue_task(p, array);
		/*
		 * If the task increased its priority or is running and
		 * lowered its priority, then reschedule its CPU:
		 */
		if (delta < 0 || (delta > 0 && task_running(rq, p)))
			resched_task(rq->curr);
	}
out_unlock:
	task_rq_unlock(rq, &flags);
}

EXPORT_SYMBOL(set_user_nice);

M
Matt Mackall 已提交
3551 3552 3553 3554 3555 3556 3557
/*
 * can_nice - check if a task can reduce its nice value
 * @p: task
 * @nice: nice value
 */
int can_nice(const task_t *p, const int nice)
{
3558 3559
	/* convert nice value [19,-20] to rlimit style value [1,40] */
	int nice_rlim = 20 - nice;
M
Matt Mackall 已提交
3560 3561 3562 3563
	return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur ||
		capable(CAP_SYS_NICE));
}

L
Linus Torvalds 已提交
3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582
#ifdef __ARCH_WANT_SYS_NICE

/*
 * sys_nice - change the priority of the current process.
 * @increment: priority increment
 *
 * sys_setpriority is a more generic, but much slower function that
 * does similar things.
 */
asmlinkage long sys_nice(int increment)
{
	int retval;
	long nice;

	/*
	 * Setpriority might change our priority at the same moment.
	 * We don't have to worry. Conceptually one call occurs first
	 * and we have a single winner.
	 */
M
Matt Mackall 已提交
3583 3584
	if (increment < -40)
		increment = -40;
L
Linus Torvalds 已提交
3585 3586 3587 3588 3589 3590 3591 3592 3593
	if (increment > 40)
		increment = 40;

	nice = PRIO_TO_NICE(current->static_prio) + increment;
	if (nice < -20)
		nice = -20;
	if (nice > 19)
		nice = 19;

M
Matt Mackall 已提交
3594 3595 3596
	if (increment < 0 && !can_nice(current, nice))
		return -EPERM;

L
Linus Torvalds 已提交
3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662
	retval = security_task_setnice(current, nice);
	if (retval)
		return retval;

	set_user_nice(current, nice);
	return 0;
}

#endif

/**
 * task_prio - return the priority value of a given task.
 * @p: the task in question.
 *
 * This is the priority value as seen by users in /proc.
 * RT tasks are offset by -200. Normal tasks are centered
 * around 0, value goes from -16 to +15.
 */
int task_prio(const task_t *p)
{
	return p->prio - MAX_RT_PRIO;
}

/**
 * task_nice - return the nice value of a given task.
 * @p: the task in question.
 */
int task_nice(const task_t *p)
{
	return TASK_NICE(p);
}
EXPORT_SYMBOL_GPL(task_nice);

/**
 * idle_cpu - is a given cpu idle currently?
 * @cpu: the processor in question.
 */
int idle_cpu(int cpu)
{
	return cpu_curr(cpu) == cpu_rq(cpu)->idle;
}

/**
 * idle_task - return the idle task for a given cpu.
 * @cpu: the processor in question.
 */
task_t *idle_task(int cpu)
{
	return cpu_rq(cpu)->idle;
}

/**
 * find_process_by_pid - find a process with a matching PID value.
 * @pid: the pid in question.
 */
static inline task_t *find_process_by_pid(pid_t pid)
{
	return pid ? find_task_by_pid(pid) : current;
}

/* Actually do priority change: must hold rq lock. */
static void __setscheduler(struct task_struct *p, int policy, int prio)
{
	BUG_ON(p->array);
	p->policy = policy;
	p->rt_priority = prio;
3663
	if (policy != SCHED_NORMAL && policy != SCHED_BATCH) {
3664
		p->prio = MAX_RT_PRIO-1 - p->rt_priority;
3665
	} else {
L
Linus Torvalds 已提交
3666
		p->prio = p->static_prio;
3667 3668 3669 3670 3671 3672
		/*
		 * SCHED_BATCH tasks are treated as perpetual CPU hogs:
		 */
		if (policy == SCHED_BATCH)
			p->sleep_avg = 0;
	}
L
Linus Torvalds 已提交
3673 3674 3675 3676 3677 3678 3679 3680 3681
}

/**
 * sched_setscheduler - change the scheduling policy and/or RT priority of
 * a thread.
 * @p: the task in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 */
I
Ingo Molnar 已提交
3682 3683
int sched_setscheduler(struct task_struct *p, int policy,
		       struct sched_param *param)
L
Linus Torvalds 已提交
3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695
{
	int retval;
	int oldprio, oldpolicy = -1;
	prio_array_t *array;
	unsigned long flags;
	runqueue_t *rq;

recheck:
	/* double check policy once rq lock held */
	if (policy < 0)
		policy = oldpolicy = p->policy;
	else if (policy != SCHED_FIFO && policy != SCHED_RR &&
3696 3697
			policy != SCHED_NORMAL && policy != SCHED_BATCH)
		return -EINVAL;
L
Linus Torvalds 已提交
3698 3699
	/*
	 * Valid priorities for SCHED_FIFO and SCHED_RR are
3700 3701
	 * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and
	 * SCHED_BATCH is 0.
L
Linus Torvalds 已提交
3702 3703
	 */
	if (param->sched_priority < 0 ||
I
Ingo Molnar 已提交
3704
	    (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) ||
3705
	    (!p->mm && param->sched_priority > MAX_RT_PRIO-1))
L
Linus Torvalds 已提交
3706
		return -EINVAL;
3707 3708
	if ((policy == SCHED_NORMAL || policy == SCHED_BATCH)
					!= (param->sched_priority == 0))
L
Linus Torvalds 已提交
3709 3710
		return -EINVAL;

3711 3712 3713 3714
	/*
	 * Allow unprivileged RT tasks to decrease priority:
	 */
	if (!capable(CAP_SYS_NICE)) {
3715 3716 3717 3718 3719 3720 3721
		/*
		 * can't change policy, except between SCHED_NORMAL
		 * and SCHED_BATCH:
		 */
		if (((policy != SCHED_NORMAL && p->policy != SCHED_BATCH) &&
			(policy != SCHED_BATCH && p->policy != SCHED_NORMAL)) &&
				!p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
3722 3723
			return -EPERM;
		/* can't increase priority */
3724
		if ((policy != SCHED_NORMAL && policy != SCHED_BATCH) &&
3725 3726 3727 3728 3729 3730 3731 3732 3733
		    param->sched_priority > p->rt_priority &&
		    param->sched_priority >
				p->signal->rlim[RLIMIT_RTPRIO].rlim_cur)
			return -EPERM;
		/* can't change other user's priorities */
		if ((current->euid != p->euid) &&
		    (current->euid != p->uid))
			return -EPERM;
	}
L
Linus Torvalds 已提交
3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771

	retval = security_task_setscheduler(p, policy, param);
	if (retval)
		return retval;
	/*
	 * To be able to change p->policy safely, the apropriate
	 * runqueue lock must be held.
	 */
	rq = task_rq_lock(p, &flags);
	/* recheck policy now with rq lock held */
	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
		policy = oldpolicy = -1;
		task_rq_unlock(rq, &flags);
		goto recheck;
	}
	array = p->array;
	if (array)
		deactivate_task(p, rq);
	oldprio = p->prio;
	__setscheduler(p, policy, param->sched_priority);
	if (array) {
		__activate_task(p, rq);
		/*
		 * Reschedule if we are currently running on this runqueue and
		 * our priority decreased, or if we are not currently running on
		 * this runqueue and our priority is higher than the current's
		 */
		if (task_running(rq, p)) {
			if (p->prio > oldprio)
				resched_task(rq->curr);
		} else if (TASK_PREEMPTS_CURR(p, rq))
			resched_task(rq->curr);
	}
	task_rq_unlock(rq, &flags);
	return 0;
}
EXPORT_SYMBOL_GPL(sched_setscheduler);

I
Ingo Molnar 已提交
3772 3773
static int
do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
L
Linus Torvalds 已提交
3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802
{
	int retval;
	struct sched_param lparam;
	struct task_struct *p;

	if (!param || pid < 0)
		return -EINVAL;
	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
		return -EFAULT;
	read_lock_irq(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (!p) {
		read_unlock_irq(&tasklist_lock);
		return -ESRCH;
	}
	retval = sched_setscheduler(p, policy, &lparam);
	read_unlock_irq(&tasklist_lock);
	return retval;
}

/**
 * sys_sched_setscheduler - set/change the scheduler policy and RT priority
 * @pid: the pid in question.
 * @policy: new policy.
 * @param: structure containing the new RT priority.
 */
asmlinkage long sys_sched_setscheduler(pid_t pid, int policy,
				       struct sched_param __user *param)
{
3803 3804 3805 3806
	/* negative values for policy are not valid */
	if (policy < 0)
		return -EINVAL;

L
Linus Torvalds 已提交
3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961
	return do_sched_setscheduler(pid, policy, param);
}

/**
 * sys_sched_setparam - set/change the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the new RT priority.
 */
asmlinkage long sys_sched_setparam(pid_t pid, struct sched_param __user *param)
{
	return do_sched_setscheduler(pid, -1, param);
}

/**
 * sys_sched_getscheduler - get the policy (scheduling class) of a thread
 * @pid: the pid in question.
 */
asmlinkage long sys_sched_getscheduler(pid_t pid)
{
	int retval = -EINVAL;
	task_t *p;

	if (pid < 0)
		goto out_nounlock;

	retval = -ESRCH;
	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (p) {
		retval = security_task_getscheduler(p);
		if (!retval)
			retval = p->policy;
	}
	read_unlock(&tasklist_lock);

out_nounlock:
	return retval;
}

/**
 * sys_sched_getscheduler - get the RT priority of a thread
 * @pid: the pid in question.
 * @param: structure containing the RT priority.
 */
asmlinkage long sys_sched_getparam(pid_t pid, struct sched_param __user *param)
{
	struct sched_param lp;
	int retval = -EINVAL;
	task_t *p;

	if (!param || pid < 0)
		goto out_nounlock;

	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	retval = -ESRCH;
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	lp.sched_priority = p->rt_priority;
	read_unlock(&tasklist_lock);

	/*
	 * This one might sleep, we cannot do it with a spinlock held ...
	 */
	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;

out_nounlock:
	return retval;

out_unlock:
	read_unlock(&tasklist_lock);
	return retval;
}

long sched_setaffinity(pid_t pid, cpumask_t new_mask)
{
	task_t *p;
	int retval;
	cpumask_t cpus_allowed;

	lock_cpu_hotplug();
	read_lock(&tasklist_lock);

	p = find_process_by_pid(pid);
	if (!p) {
		read_unlock(&tasklist_lock);
		unlock_cpu_hotplug();
		return -ESRCH;
	}

	/*
	 * It is not safe to call set_cpus_allowed with the
	 * tasklist_lock held.  We will bump the task_struct's
	 * usage count and then drop tasklist_lock.
	 */
	get_task_struct(p);
	read_unlock(&tasklist_lock);

	retval = -EPERM;
	if ((current->euid != p->euid) && (current->euid != p->uid) &&
			!capable(CAP_SYS_NICE))
		goto out_unlock;

	cpus_allowed = cpuset_cpus_allowed(p);
	cpus_and(new_mask, new_mask, cpus_allowed);
	retval = set_cpus_allowed(p, new_mask);

out_unlock:
	put_task_struct(p);
	unlock_cpu_hotplug();
	return retval;
}

static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
			     cpumask_t *new_mask)
{
	if (len < sizeof(cpumask_t)) {
		memset(new_mask, 0, sizeof(cpumask_t));
	} else if (len > sizeof(cpumask_t)) {
		len = sizeof(cpumask_t);
	}
	return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
}

/**
 * sys_sched_setaffinity - set the cpu affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to the new cpu mask
 */
asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len,
				      unsigned long __user *user_mask_ptr)
{
	cpumask_t new_mask;
	int retval;

	retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask);
	if (retval)
		return retval;

	return sched_setaffinity(pid, new_mask);
}

/*
 * Represents all cpu's present in the system
 * In systems capable of hotplug, this map could dynamically grow
 * as new cpu's are detected in the system via any platform specific
 * method, such as ACPI for e.g.
 */

3962
cpumask_t cpu_present_map __read_mostly;
L
Linus Torvalds 已提交
3963 3964 3965
EXPORT_SYMBOL(cpu_present_map);

#ifndef CONFIG_SMP
3966 3967
cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL;
cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL;
L
Linus Torvalds 已提交
3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983
#endif

long sched_getaffinity(pid_t pid, cpumask_t *mask)
{
	int retval;
	task_t *p;

	lock_cpu_hotplug();
	read_lock(&tasklist_lock);

	retval = -ESRCH;
	p = find_process_by_pid(pid);
	if (!p)
		goto out_unlock;

	retval = 0;
3984
	cpus_and(*mask, p->cpus_allowed, cpu_online_map);
L
Linus Torvalds 已提交
3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043

out_unlock:
	read_unlock(&tasklist_lock);
	unlock_cpu_hotplug();
	if (retval)
		return retval;

	return 0;
}

/**
 * sys_sched_getaffinity - get the cpu affinity of a process
 * @pid: pid of the process
 * @len: length in bytes of the bitmask pointed to by user_mask_ptr
 * @user_mask_ptr: user-space pointer to hold the current cpu mask
 */
asmlinkage long sys_sched_getaffinity(pid_t pid, unsigned int len,
				      unsigned long __user *user_mask_ptr)
{
	int ret;
	cpumask_t mask;

	if (len < sizeof(cpumask_t))
		return -EINVAL;

	ret = sched_getaffinity(pid, &mask);
	if (ret < 0)
		return ret;

	if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t)))
		return -EFAULT;

	return sizeof(cpumask_t);
}

/**
 * sys_sched_yield - yield the current processor to other threads.
 *
 * this function yields the current CPU by moving the calling thread
 * to the expired array. If there are no other threads running on this
 * CPU then this function will return.
 */
asmlinkage long sys_sched_yield(void)
{
	runqueue_t *rq = this_rq_lock();
	prio_array_t *array = current->array;
	prio_array_t *target = rq->expired;

	schedstat_inc(rq, yld_cnt);
	/*
	 * We implement yielding by moving the task into the expired
	 * queue.
	 *
	 * (special rule: RT tasks will just roundrobin in the active
	 *  array.)
	 */
	if (rt_task(current))
		target = rq->active;

4044
	if (array->nr_active == 1) {
L
Linus Torvalds 已提交
4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074
		schedstat_inc(rq, yld_act_empty);
		if (!rq->expired->nr_active)
			schedstat_inc(rq, yld_both_empty);
	} else if (!rq->expired->nr_active)
		schedstat_inc(rq, yld_exp_empty);

	if (array != target) {
		dequeue_task(current, array);
		enqueue_task(current, target);
	} else
		/*
		 * requeue_task is cheaper so perform that if possible.
		 */
		requeue_task(current, array);

	/*
	 * Since we are going to call schedule() anyway, there's
	 * no need to preempt or enable interrupts:
	 */
	__release(rq->lock);
	_raw_spin_unlock(&rq->lock);
	preempt_enable_no_resched();

	schedule();

	return 0;
}

static inline void __cond_resched(void)
{
4075 4076 4077 4078 4079 4080 4081
	/*
	 * The BKS might be reacquired before we have dropped
	 * PREEMPT_ACTIVE, which could trigger a second
	 * cond_resched() call.
	 */
	if (unlikely(preempt_count()))
		return;
4082 4083
	if (unlikely(system_state != SYSTEM_RUNNING))
		return;
L
Linus Torvalds 已提交
4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109
	do {
		add_preempt_count(PREEMPT_ACTIVE);
		schedule();
		sub_preempt_count(PREEMPT_ACTIVE);
	} while (need_resched());
}

int __sched cond_resched(void)
{
	if (need_resched()) {
		__cond_resched();
		return 1;
	}
	return 0;
}

EXPORT_SYMBOL(cond_resched);

/*
 * cond_resched_lock() - if a reschedule is pending, drop the given lock,
 * call schedule, and on return reacquire the lock.
 *
 * This works OK both with and without CONFIG_PREEMPT.  We do strange low-level
 * operations here to prevent schedule() from being called twice (once via
 * spin_unlock(), once by hand).
 */
I
Ingo Molnar 已提交
4110
int cond_resched_lock(spinlock_t *lock)
L
Linus Torvalds 已提交
4111
{
J
Jan Kara 已提交
4112 4113
	int ret = 0;

L
Linus Torvalds 已提交
4114 4115 4116
	if (need_lockbreak(lock)) {
		spin_unlock(lock);
		cpu_relax();
J
Jan Kara 已提交
4117
		ret = 1;
L
Linus Torvalds 已提交
4118 4119 4120 4121 4122 4123
		spin_lock(lock);
	}
	if (need_resched()) {
		_raw_spin_unlock(lock);
		preempt_enable_no_resched();
		__cond_resched();
J
Jan Kara 已提交
4124
		ret = 1;
L
Linus Torvalds 已提交
4125 4126
		spin_lock(lock);
	}
J
Jan Kara 已提交
4127
	return ret;
L
Linus Torvalds 已提交
4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170
}

EXPORT_SYMBOL(cond_resched_lock);

int __sched cond_resched_softirq(void)
{
	BUG_ON(!in_softirq());

	if (need_resched()) {
		__local_bh_enable();
		__cond_resched();
		local_bh_disable();
		return 1;
	}
	return 0;
}

EXPORT_SYMBOL(cond_resched_softirq);


/**
 * yield - yield the current processor to other threads.
 *
 * this is a shortcut for kernel-space yielding - it marks the
 * thread runnable and calls sys_sched_yield().
 */
void __sched yield(void)
{
	set_current_state(TASK_RUNNING);
	sys_sched_yield();
}

EXPORT_SYMBOL(yield);

/*
 * This task is about to go to sleep on IO.  Increment rq->nr_iowait so
 * that process accounting knows that this is a task in IO wait state.
 *
 * But don't do that if it is a deliberate, throttling IO wait (this task
 * has set its backing_dev_info: the queue against which it should throttle)
 */
void __sched io_schedule(void)
{
I
Ingo Molnar 已提交
4171
	struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
L
Linus Torvalds 已提交
4172 4173 4174 4175 4176 4177 4178 4179 4180 4181

	atomic_inc(&rq->nr_iowait);
	schedule();
	atomic_dec(&rq->nr_iowait);
}

EXPORT_SYMBOL(io_schedule);

long __sched io_schedule_timeout(long timeout)
{
I
Ingo Molnar 已提交
4182
	struct runqueue *rq = &per_cpu(runqueues, raw_smp_processor_id());
L
Linus Torvalds 已提交
4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207
	long ret;

	atomic_inc(&rq->nr_iowait);
	ret = schedule_timeout(timeout);
	atomic_dec(&rq->nr_iowait);
	return ret;
}

/**
 * sys_sched_get_priority_max - return maximum RT priority.
 * @policy: scheduling class.
 *
 * this syscall returns the maximum rt_priority that can be used
 * by a given scheduling class.
 */
asmlinkage long sys_sched_get_priority_max(int policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = MAX_USER_RT_PRIO-1;
		break;
	case SCHED_NORMAL:
4208
	case SCHED_BATCH:
L
Linus Torvalds 已提交
4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231
		ret = 0;
		break;
	}
	return ret;
}

/**
 * sys_sched_get_priority_min - return minimum RT priority.
 * @policy: scheduling class.
 *
 * this syscall returns the minimum rt_priority that can be used
 * by a given scheduling class.
 */
asmlinkage long sys_sched_get_priority_min(int policy)
{
	int ret = -EINVAL;

	switch (policy) {
	case SCHED_FIFO:
	case SCHED_RR:
		ret = 1;
		break;
	case SCHED_NORMAL:
4232
	case SCHED_BATCH:
L
Linus Torvalds 已提交
4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294
		ret = 0;
	}
	return ret;
}

/**
 * sys_sched_rr_get_interval - return the default timeslice of a process.
 * @pid: pid of the process.
 * @interval: userspace pointer to the timeslice value.
 *
 * this syscall writes the default timeslice value of a given process
 * into the user-space timespec buffer. A value of '0' means infinity.
 */
asmlinkage
long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval)
{
	int retval = -EINVAL;
	struct timespec t;
	task_t *p;

	if (pid < 0)
		goto out_nounlock;

	retval = -ESRCH;
	read_lock(&tasklist_lock);
	p = find_process_by_pid(pid);
	if (!p)
		goto out_unlock;

	retval = security_task_getscheduler(p);
	if (retval)
		goto out_unlock;

	jiffies_to_timespec(p->policy & SCHED_FIFO ?
				0 : task_timeslice(p), &t);
	read_unlock(&tasklist_lock);
	retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0;
out_nounlock:
	return retval;
out_unlock:
	read_unlock(&tasklist_lock);
	return retval;
}

static inline struct task_struct *eldest_child(struct task_struct *p)
{
	if (list_empty(&p->children)) return NULL;
	return list_entry(p->children.next,struct task_struct,sibling);
}

static inline struct task_struct *older_sibling(struct task_struct *p)
{
	if (p->sibling.prev==&p->parent->children) return NULL;
	return list_entry(p->sibling.prev,struct task_struct,sibling);
}

static inline struct task_struct *younger_sibling(struct task_struct *p)
{
	if (p->sibling.next==&p->parent->children) return NULL;
	return list_entry(p->sibling.next,struct task_struct,sibling);
}

I
Ingo Molnar 已提交
4295
static void show_task(task_t *p)
L
Linus Torvalds 已提交
4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320
{
	task_t *relative;
	unsigned state;
	unsigned long free = 0;
	static const char *stat_nam[] = { "R", "S", "D", "T", "t", "Z", "X" };

	printk("%-13.13s ", p->comm);
	state = p->state ? __ffs(p->state) + 1 : 0;
	if (state < ARRAY_SIZE(stat_nam))
		printk(stat_nam[state]);
	else
		printk("?");
#if (BITS_PER_LONG == 32)
	if (state == TASK_RUNNING)
		printk(" running ");
	else
		printk(" %08lX ", thread_saved_pc(p));
#else
	if (state == TASK_RUNNING)
		printk("  running task   ");
	else
		printk(" %016lx ", thread_saved_pc(p));
#endif
#ifdef CONFIG_DEBUG_STACK_USAGE
	{
4321
		unsigned long *n = end_of_stack(p);
L
Linus Torvalds 已提交
4322 4323
		while (!*n)
			n++;
4324
		free = (unsigned long)n - (unsigned long)end_of_stack(p);
L
Linus Torvalds 已提交
4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372
	}
#endif
	printk("%5lu %5d %6d ", free, p->pid, p->parent->pid);
	if ((relative = eldest_child(p)))
		printk("%5d ", relative->pid);
	else
		printk("      ");
	if ((relative = younger_sibling(p)))
		printk("%7d", relative->pid);
	else
		printk("       ");
	if ((relative = older_sibling(p)))
		printk(" %5d", relative->pid);
	else
		printk("      ");
	if (!p->mm)
		printk(" (L-TLB)\n");
	else
		printk(" (NOTLB)\n");

	if (state != TASK_RUNNING)
		show_stack(p, NULL);
}

void show_state(void)
{
	task_t *g, *p;

#if (BITS_PER_LONG == 32)
	printk("\n"
	       "                                               sibling\n");
	printk("  task             PC      pid father child younger older\n");
#else
	printk("\n"
	       "                                                       sibling\n");
	printk("  task                 PC          pid father child younger older\n");
#endif
	read_lock(&tasklist_lock);
	do_each_thread(g, p) {
		/*
		 * reset the NMI-timeout, listing all files on a slow
		 * console might take alot of time:
		 */
		touch_nmi_watchdog();
		show_task(p);
	} while_each_thread(g, p);

	read_unlock(&tasklist_lock);
4373
	mutex_debug_show_all_locks();
L
Linus Torvalds 已提交
4374 4375
}

4376 4377 4378 4379 4380 4381 4382 4383
/**
 * init_idle - set up an idle thread for a given CPU
 * @idle: task in question
 * @cpu: cpu the idle task belongs to
 *
 * NOTE: this function does not set the idle thread's NEED_RESCHED
 * flag, to make booting more robust.
 */
L
Linus Torvalds 已提交
4384 4385 4386 4387 4388
void __devinit init_idle(task_t *idle, int cpu)
{
	runqueue_t *rq = cpu_rq(cpu);
	unsigned long flags;

4389
	idle->timestamp = sched_clock();
L
Linus Torvalds 已提交
4390 4391 4392 4393 4394 4395 4396 4397 4398
	idle->sleep_avg = 0;
	idle->array = NULL;
	idle->prio = MAX_PRIO;
	idle->state = TASK_RUNNING;
	idle->cpus_allowed = cpumask_of_cpu(cpu);
	set_task_cpu(idle, cpu);

	spin_lock_irqsave(&rq->lock, flags);
	rq->curr = rq->idle = idle;
4399 4400 4401
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
	idle->oncpu = 1;
#endif
L
Linus Torvalds 已提交
4402 4403 4404 4405
	spin_unlock_irqrestore(&rq->lock, flags);

	/* Set the preempt count _outside_ the spinlocks! */
#if defined(CONFIG_PREEMPT) && !defined(CONFIG_PREEMPT_BKL)
A
Al Viro 已提交
4406
	task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0);
L
Linus Torvalds 已提交
4407
#else
A
Al Viro 已提交
4408
	task_thread_info(idle)->preempt_count = 0;
L
Linus Torvalds 已提交
4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531
#endif
}

/*
 * In a system that switches off the HZ timer nohz_cpu_mask
 * indicates which cpus entered this state. This is used
 * in the rcu update to wait only for active cpus. For system
 * which do not switch off the HZ timer nohz_cpu_mask should
 * always be CPU_MASK_NONE.
 */
cpumask_t nohz_cpu_mask = CPU_MASK_NONE;

#ifdef CONFIG_SMP
/*
 * This is how migration works:
 *
 * 1) we queue a migration_req_t structure in the source CPU's
 *    runqueue and wake up that CPU's migration thread.
 * 2) we down() the locked semaphore => thread blocks.
 * 3) migration thread wakes up (implicitly it forces the migrated
 *    thread off the CPU)
 * 4) it gets the migration request and checks whether the migrated
 *    task is still in the wrong runqueue.
 * 5) if it's in the wrong runqueue then the migration thread removes
 *    it and puts it into the right queue.
 * 6) migration thread up()s the semaphore.
 * 7) we wake up and the migration is done.
 */

/*
 * Change a given task's CPU affinity. Migrate the thread to a
 * proper CPU and schedule it away if the CPU it's executing on
 * is removed from the allowed bitmask.
 *
 * NOTE: the caller must have a valid reference to the task, the
 * task must not exit() & deallocate itself prematurely.  The
 * call is not atomic; no spinlocks may be held.
 */
int set_cpus_allowed(task_t *p, cpumask_t new_mask)
{
	unsigned long flags;
	int ret = 0;
	migration_req_t req;
	runqueue_t *rq;

	rq = task_rq_lock(p, &flags);
	if (!cpus_intersects(new_mask, cpu_online_map)) {
		ret = -EINVAL;
		goto out;
	}

	p->cpus_allowed = new_mask;
	/* Can the task run on the task's current CPU? If so, we're done */
	if (cpu_isset(task_cpu(p), new_mask))
		goto out;

	if (migrate_task(p, any_online_cpu(new_mask), &req)) {
		/* Need help from migration thread: drop lock and wait. */
		task_rq_unlock(rq, &flags);
		wake_up_process(rq->migration_thread);
		wait_for_completion(&req.done);
		tlb_migrate_finish(p->mm);
		return 0;
	}
out:
	task_rq_unlock(rq, &flags);
	return ret;
}

EXPORT_SYMBOL_GPL(set_cpus_allowed);

/*
 * Move (not current) task off this cpu, onto dest cpu.  We're doing
 * this because either it can't run here any more (set_cpus_allowed()
 * away from this CPU, or CPU going down), or because we're
 * attempting to rebalance this task on exec (sched_exec).
 *
 * So we race with normal scheduler movements, but that's OK, as long
 * as the task is no longer on this CPU.
 */
static void __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu)
{
	runqueue_t *rq_dest, *rq_src;

	if (unlikely(cpu_is_offline(dest_cpu)))
		return;

	rq_src = cpu_rq(src_cpu);
	rq_dest = cpu_rq(dest_cpu);

	double_rq_lock(rq_src, rq_dest);
	/* Already moved. */
	if (task_cpu(p) != src_cpu)
		goto out;
	/* Affinity changed (again). */
	if (!cpu_isset(dest_cpu, p->cpus_allowed))
		goto out;

	set_task_cpu(p, dest_cpu);
	if (p->array) {
		/*
		 * Sync timestamp with rq_dest's before activating.
		 * The same thing could be achieved by doing this step
		 * afterwards, and pretending it was a local activate.
		 * This way is cleaner and logically correct.
		 */
		p->timestamp = p->timestamp - rq_src->timestamp_last_tick
				+ rq_dest->timestamp_last_tick;
		deactivate_task(p, rq_src);
		activate_task(p, rq_dest, 0);
		if (TASK_PREEMPTS_CURR(p, rq_dest))
			resched_task(rq_dest->curr);
	}

out:
	double_rq_unlock(rq_src, rq_dest);
}

/*
 * migration_thread - this is a highprio system thread that performs
 * thread migration by bumping thread off CPU then 'pushing' onto
 * another runqueue.
 */
I
Ingo Molnar 已提交
4532
static int migration_thread(void *data)
L
Linus Torvalds 已提交
4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544
{
	runqueue_t *rq;
	int cpu = (long)data;

	rq = cpu_rq(cpu);
	BUG_ON(rq->migration_thread != current);

	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		struct list_head *head;
		migration_req_t *req;

4545
		try_to_freeze();
L
Linus Torvalds 已提交
4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569

		spin_lock_irq(&rq->lock);

		if (cpu_is_offline(cpu)) {
			spin_unlock_irq(&rq->lock);
			goto wait_to_die;
		}

		if (rq->active_balance) {
			active_load_balance(rq, cpu);
			rq->active_balance = 0;
		}

		head = &rq->migration_queue;

		if (list_empty(head)) {
			spin_unlock_irq(&rq->lock);
			schedule();
			set_current_state(TASK_INTERRUPTIBLE);
			continue;
		}
		req = list_entry(head->next, migration_req_t, list);
		list_del_init(head->next);

N
Nick Piggin 已提交
4570 4571 4572
		spin_unlock(&rq->lock);
		__migrate_task(req->task, cpu, req->dest_cpu);
		local_irq_enable();
L
Linus Torvalds 已提交
4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607

		complete(&req->done);
	}
	__set_current_state(TASK_RUNNING);
	return 0;

wait_to_die:
	/* Wait for kthread_stop */
	set_current_state(TASK_INTERRUPTIBLE);
	while (!kthread_should_stop()) {
		schedule();
		set_current_state(TASK_INTERRUPTIBLE);
	}
	__set_current_state(TASK_RUNNING);
	return 0;
}

#ifdef CONFIG_HOTPLUG_CPU
/* Figure out where task on dead CPU should go, use force if neccessary. */
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *tsk)
{
	int dest_cpu;
	cpumask_t mask;

	/* On same node? */
	mask = node_to_cpumask(cpu_to_node(dead_cpu));
	cpus_and(mask, mask, tsk->cpus_allowed);
	dest_cpu = any_online_cpu(mask);

	/* On any allowed CPU? */
	if (dest_cpu == NR_CPUS)
		dest_cpu = any_online_cpu(tsk->cpus_allowed);

	/* No more Mr. Nice Guy. */
	if (dest_cpu == NR_CPUS) {
4608
		cpus_setall(tsk->cpus_allowed);
L
Linus Torvalds 已提交
4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775
		dest_cpu = any_online_cpu(tsk->cpus_allowed);

		/*
		 * Don't tell them about moving exiting tasks or
		 * kernel threads (both mm NULL), since they never
		 * leave kernel.
		 */
		if (tsk->mm && printk_ratelimit())
			printk(KERN_INFO "process %d (%s) no "
			       "longer affine to cpu%d\n",
			       tsk->pid, tsk->comm, dead_cpu);
	}
	__migrate_task(tsk, dead_cpu, dest_cpu);
}

/*
 * While a dead CPU has no uninterruptible tasks queued at this point,
 * it might still have a nonzero ->nr_uninterruptible counter, because
 * for performance reasons the counter is not stricly tracking tasks to
 * their home CPUs. So we just add the counter to another CPU's counter,
 * to keep the global sum constant after CPU-down:
 */
static void migrate_nr_uninterruptible(runqueue_t *rq_src)
{
	runqueue_t *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
	unsigned long flags;

	local_irq_save(flags);
	double_rq_lock(rq_src, rq_dest);
	rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible;
	rq_src->nr_uninterruptible = 0;
	double_rq_unlock(rq_src, rq_dest);
	local_irq_restore(flags);
}

/* Run through task list and migrate tasks from the dead cpu. */
static void migrate_live_tasks(int src_cpu)
{
	struct task_struct *tsk, *t;

	write_lock_irq(&tasklist_lock);

	do_each_thread(t, tsk) {
		if (tsk == current)
			continue;

		if (task_cpu(tsk) == src_cpu)
			move_task_off_dead_cpu(src_cpu, tsk);
	} while_each_thread(t, tsk);

	write_unlock_irq(&tasklist_lock);
}

/* Schedules idle task to be the next runnable task on current CPU.
 * It does so by boosting its priority to highest possible and adding it to
 * the _front_ of runqueue. Used by CPU offline code.
 */
void sched_idle_next(void)
{
	int cpu = smp_processor_id();
	runqueue_t *rq = this_rq();
	struct task_struct *p = rq->idle;
	unsigned long flags;

	/* cpu has to be offline */
	BUG_ON(cpu_online(cpu));

	/* Strictly not necessary since rest of the CPUs are stopped by now
	 * and interrupts disabled on current cpu.
	 */
	spin_lock_irqsave(&rq->lock, flags);

	__setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
	/* Add idle task to _front_ of it's priority queue */
	__activate_idle_task(p, rq);

	spin_unlock_irqrestore(&rq->lock, flags);
}

/* Ensures that the idle task is using init_mm right before its cpu goes
 * offline.
 */
void idle_task_exit(void)
{
	struct mm_struct *mm = current->active_mm;

	BUG_ON(cpu_online(smp_processor_id()));

	if (mm != &init_mm)
		switch_mm(mm, &init_mm, current);
	mmdrop(mm);
}

static void migrate_dead(unsigned int dead_cpu, task_t *tsk)
{
	struct runqueue *rq = cpu_rq(dead_cpu);

	/* Must be exiting, otherwise would be on tasklist. */
	BUG_ON(tsk->exit_state != EXIT_ZOMBIE && tsk->exit_state != EXIT_DEAD);

	/* Cannot have done final schedule yet: would have vanished. */
	BUG_ON(tsk->flags & PF_DEAD);

	get_task_struct(tsk);

	/*
	 * Drop lock around migration; if someone else moves it,
	 * that's OK.  No task can be added to this CPU, so iteration is
	 * fine.
	 */
	spin_unlock_irq(&rq->lock);
	move_task_off_dead_cpu(dead_cpu, tsk);
	spin_lock_irq(&rq->lock);

	put_task_struct(tsk);
}

/* release_task() removes task from tasklist, so we won't find dead tasks. */
static void migrate_dead_tasks(unsigned int dead_cpu)
{
	unsigned arr, i;
	struct runqueue *rq = cpu_rq(dead_cpu);

	for (arr = 0; arr < 2; arr++) {
		for (i = 0; i < MAX_PRIO; i++) {
			struct list_head *list = &rq->arrays[arr].queue[i];
			while (!list_empty(list))
				migrate_dead(dead_cpu,
					     list_entry(list->next, task_t,
							run_list));
		}
	}
}
#endif /* CONFIG_HOTPLUG_CPU */

/*
 * migration_call - callback that gets triggered when a CPU is added.
 * Here we can start up the necessary migration thread for the new CPU.
 */
static int migration_call(struct notifier_block *nfb, unsigned long action,
			  void *hcpu)
{
	int cpu = (long)hcpu;
	struct task_struct *p;
	struct runqueue *rq;
	unsigned long flags;

	switch (action) {
	case CPU_UP_PREPARE:
		p = kthread_create(migration_thread, hcpu, "migration/%d",cpu);
		if (IS_ERR(p))
			return NOTIFY_BAD;
		p->flags |= PF_NOFREEZE;
		kthread_bind(p, cpu);
		/* Must be high prio: stop_machine expects to yield to it. */
		rq = task_rq_lock(p, &flags);
		__setscheduler(p, SCHED_FIFO, MAX_RT_PRIO-1);
		task_rq_unlock(rq, &flags);
		cpu_rq(cpu)->migration_thread = p;
		break;
	case CPU_ONLINE:
		/* Strictly unneccessary, as first user will wake it. */
		wake_up_process(cpu_rq(cpu)->migration_thread);
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_UP_CANCELED:
		/* Unbind it from offline cpu so it can run.  Fall thru. */
4776 4777
		kthread_bind(cpu_rq(cpu)->migration_thread,
			     any_online_cpu(cpu_online_map));
L
Linus Torvalds 已提交
4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833
		kthread_stop(cpu_rq(cpu)->migration_thread);
		cpu_rq(cpu)->migration_thread = NULL;
		break;
	case CPU_DEAD:
		migrate_live_tasks(cpu);
		rq = cpu_rq(cpu);
		kthread_stop(rq->migration_thread);
		rq->migration_thread = NULL;
		/* Idle task back to normal (off runqueue, low prio) */
		rq = task_rq_lock(rq->idle, &flags);
		deactivate_task(rq->idle, rq);
		rq->idle->static_prio = MAX_PRIO;
		__setscheduler(rq->idle, SCHED_NORMAL, 0);
		migrate_dead_tasks(cpu);
		task_rq_unlock(rq, &flags);
		migrate_nr_uninterruptible(rq);
		BUG_ON(rq->nr_running != 0);

		/* No need to migrate the tasks: it was best-effort if
		 * they didn't do lock_cpu_hotplug().  Just wake up
		 * the requestors. */
		spin_lock_irq(&rq->lock);
		while (!list_empty(&rq->migration_queue)) {
			migration_req_t *req;
			req = list_entry(rq->migration_queue.next,
					 migration_req_t, list);
			list_del_init(&req->list);
			complete(&req->done);
		}
		spin_unlock_irq(&rq->lock);
		break;
#endif
	}
	return NOTIFY_OK;
}

/* Register at highest priority so that task migration (migrate_all_tasks)
 * happens before everything else.
 */
static struct notifier_block __devinitdata migration_notifier = {
	.notifier_call = migration_call,
	.priority = 10
};

int __init migration_init(void)
{
	void *cpu = (void *)(long)smp_processor_id();
	/* Start one for boot CPU. */
	migration_call(&migration_notifier, CPU_UP_PREPARE, cpu);
	migration_call(&migration_notifier, CPU_ONLINE, cpu);
	register_cpu_notifier(&migration_notifier);
	return 0;
}
#endif

#ifdef CONFIG_SMP
4834
#undef SCHED_DOMAIN_DEBUG
L
Linus Torvalds 已提交
4835 4836 4837 4838 4839
#ifdef SCHED_DOMAIN_DEBUG
static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
	int level = 0;

N
Nick Piggin 已提交
4840 4841 4842 4843 4844
	if (!sd) {
		printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
		return;
	}

L
Linus Torvalds 已提交
4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926
	printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);

	do {
		int i;
		char str[NR_CPUS];
		struct sched_group *group = sd->groups;
		cpumask_t groupmask;

		cpumask_scnprintf(str, NR_CPUS, sd->span);
		cpus_clear(groupmask);

		printk(KERN_DEBUG);
		for (i = 0; i < level + 1; i++)
			printk(" ");
		printk("domain %d: ", level);

		if (!(sd->flags & SD_LOAD_BALANCE)) {
			printk("does not load-balance\n");
			if (sd->parent)
				printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain has parent");
			break;
		}

		printk("span %s\n", str);

		if (!cpu_isset(cpu, sd->span))
			printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
		if (!cpu_isset(cpu, group->cpumask))
			printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);

		printk(KERN_DEBUG);
		for (i = 0; i < level + 2; i++)
			printk(" ");
		printk("groups:");
		do {
			if (!group) {
				printk("\n");
				printk(KERN_ERR "ERROR: group is NULL\n");
				break;
			}

			if (!group->cpu_power) {
				printk("\n");
				printk(KERN_ERR "ERROR: domain->cpu_power not set\n");
			}

			if (!cpus_weight(group->cpumask)) {
				printk("\n");
				printk(KERN_ERR "ERROR: empty group\n");
			}

			if (cpus_intersects(groupmask, group->cpumask)) {
				printk("\n");
				printk(KERN_ERR "ERROR: repeated CPUs\n");
			}

			cpus_or(groupmask, groupmask, group->cpumask);

			cpumask_scnprintf(str, NR_CPUS, group->cpumask);
			printk(" %s", str);

			group = group->next;
		} while (group != sd->groups);
		printk("\n");

		if (!cpus_equal(sd->span, groupmask))
			printk(KERN_ERR "ERROR: groups don't span domain->span\n");

		level++;
		sd = sd->parent;

		if (sd) {
			if (!cpus_subset(groupmask, sd->span))
				printk(KERN_ERR "ERROR: parent span is not a superset of domain->span\n");
		}

	} while (sd);
}
#else
#define sched_domain_debug(sd, cpu) {}
#endif

4927
static int sd_degenerate(struct sched_domain *sd)
4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949
{
	if (cpus_weight(sd->span) == 1)
		return 1;

	/* Following flags need at least 2 groups */
	if (sd->flags & (SD_LOAD_BALANCE |
			 SD_BALANCE_NEWIDLE |
			 SD_BALANCE_FORK |
			 SD_BALANCE_EXEC)) {
		if (sd->groups != sd->groups->next)
			return 0;
	}

	/* Following flags don't use groups */
	if (sd->flags & (SD_WAKE_IDLE |
			 SD_WAKE_AFFINE |
			 SD_WAKE_BALANCE))
		return 0;

	return 1;
}

4950
static int sd_parent_degenerate(struct sched_domain *sd,
4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977
						struct sched_domain *parent)
{
	unsigned long cflags = sd->flags, pflags = parent->flags;

	if (sd_degenerate(parent))
		return 1;

	if (!cpus_equal(sd->span, parent->span))
		return 0;

	/* Does parent contain flags not in child? */
	/* WAKE_BALANCE is a subset of WAKE_AFFINE */
	if (cflags & SD_WAKE_AFFINE)
		pflags &= ~SD_WAKE_BALANCE;
	/* Flags needing groups don't count if only 1 group in parent */
	if (parent->groups == parent->groups->next) {
		pflags &= ~(SD_LOAD_BALANCE |
				SD_BALANCE_NEWIDLE |
				SD_BALANCE_FORK |
				SD_BALANCE_EXEC);
	}
	if (~cflags & pflags)
		return 0;

	return 1;
}

L
Linus Torvalds 已提交
4978 4979 4980 4981
/*
 * Attach the domain 'sd' to 'cpu' as its base domain.  Callers must
 * hold the hotplug lock.
 */
4982
static void cpu_attach_domain(struct sched_domain *sd, int cpu)
L
Linus Torvalds 已提交
4983 4984
{
	runqueue_t *rq = cpu_rq(cpu);
4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997
	struct sched_domain *tmp;

	/* Remove the sched domains which do not contribute to scheduling. */
	for (tmp = sd; tmp; tmp = tmp->parent) {
		struct sched_domain *parent = tmp->parent;
		if (!parent)
			break;
		if (sd_parent_degenerate(tmp, parent))
			tmp->parent = parent->parent;
	}

	if (sd && sd_degenerate(sd))
		sd = sd->parent;
L
Linus Torvalds 已提交
4998 4999 5000

	sched_domain_debug(sd, cpu);

N
Nick Piggin 已提交
5001
	rcu_assign_pointer(rq->sd, sd);
L
Linus Torvalds 已提交
5002 5003 5004
}

/* cpus with isolated domains */
5005
static cpumask_t __devinitdata cpu_isolated_map = CPU_MASK_NONE;
L
Linus Torvalds 已提交
5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032

/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
	int ints[NR_CPUS], i;

	str = get_options(str, ARRAY_SIZE(ints), ints);
	cpus_clear(cpu_isolated_map);
	for (i = 1; i <= ints[0]; i++)
		if (ints[i] < NR_CPUS)
			cpu_set(ints[i], cpu_isolated_map);
	return 1;
}

__setup ("isolcpus=", isolated_cpu_setup);

/*
 * init_sched_build_groups takes an array of groups, the cpumask we wish
 * to span, and a pointer to a function which identifies what group a CPU
 * belongs to. The return value of group_fn must be a valid index into the
 * groups[] array, and must be >= 0 and < NR_CPUS (due to the fact that we
 * keep track of groups covered with a cpumask_t).
 *
 * init_sched_build_groups will build a circular linked list of the groups
 * covered by the given span, and will set each group's ->cpumask correctly,
 * and ->cpu_power to 0.
 */
5033 5034
static void init_sched_build_groups(struct sched_group groups[], cpumask_t span,
				    int (*group_fn)(int cpu))
L
Linus Torvalds 已提交
5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066
{
	struct sched_group *first = NULL, *last = NULL;
	cpumask_t covered = CPU_MASK_NONE;
	int i;

	for_each_cpu_mask(i, span) {
		int group = group_fn(i);
		struct sched_group *sg = &groups[group];
		int j;

		if (cpu_isset(i, covered))
			continue;

		sg->cpumask = CPU_MASK_NONE;
		sg->cpu_power = 0;

		for_each_cpu_mask(j, span) {
			if (group_fn(j) != group)
				continue;

			cpu_set(j, covered);
			cpu_set(j, sg->cpumask);
		}
		if (!first)
			first = sg;
		if (last)
			last->next = sg;
		last = sg;
	}
	last->next = first;
}

5067
#define SD_NODES_PER_DOMAIN 16
L
Linus Torvalds 已提交
5068

5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096
/*
 * Self-tuning task migration cost measurement between source and target CPUs.
 *
 * This is done by measuring the cost of manipulating buffers of varying
 * sizes. For a given buffer-size here are the steps that are taken:
 *
 * 1) the source CPU reads+dirties a shared buffer
 * 2) the target CPU reads+dirties the same shared buffer
 *
 * We measure how long they take, in the following 4 scenarios:
 *
 *  - source: CPU1, target: CPU2 | cost1
 *  - source: CPU2, target: CPU1 | cost2
 *  - source: CPU1, target: CPU1 | cost3
 *  - source: CPU2, target: CPU2 | cost4
 *
 * We then calculate the cost3+cost4-cost1-cost2 difference - this is
 * the cost of migration.
 *
 * We then start off from a small buffer-size and iterate up to larger
 * buffer sizes, in 5% steps - measuring each buffer-size separately, and
 * doing a maximum search for the cost. (The maximum cost for a migration
 * normally occurs when the working set size is around the effective cache
 * size.)
 */
#define SEARCH_SCOPE		2
#define MIN_CACHE_SIZE		(64*1024U)
#define DEFAULT_CACHE_SIZE	(5*1024*1024U)
5097
#define ITERATIONS		1
5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114
#define SIZE_THRESH		130
#define COST_THRESH		130

/*
 * The migration cost is a function of 'domain distance'. Domain
 * distance is the number of steps a CPU has to iterate down its
 * domain tree to share a domain with the other CPU. The farther
 * two CPUs are from each other, the larger the distance gets.
 *
 * Note that we use the distance only to cache measurement results,
 * the distance value is not used numerically otherwise. When two
 * CPUs have the same distance it is assumed that the migration
 * cost is the same. (this is a simplification but quite practical)
 */
#define MAX_DOMAIN_DISTANCE 32

static unsigned long long migration_cost[MAX_DOMAIN_DISTANCE] =
5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126
		{ [ 0 ... MAX_DOMAIN_DISTANCE-1 ] =
/*
 * Architectures may override the migration cost and thus avoid
 * boot-time calibration. Unit is nanoseconds. Mostly useful for
 * virtualized hardware:
 */
#ifdef CONFIG_DEFAULT_MIGRATION_COST
			CONFIG_DEFAULT_MIGRATION_COST
#else
			-1LL
#endif
};
5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446

/*
 * Allow override of migration cost - in units of microseconds.
 * E.g. migration_cost=1000,2000,3000 will set up a level-1 cost
 * of 1 msec, level-2 cost of 2 msecs and level3 cost of 3 msecs:
 */
static int __init migration_cost_setup(char *str)
{
	int ints[MAX_DOMAIN_DISTANCE+1], i;

	str = get_options(str, ARRAY_SIZE(ints), ints);

	printk("#ints: %d\n", ints[0]);
	for (i = 1; i <= ints[0]; i++) {
		migration_cost[i-1] = (unsigned long long)ints[i]*1000;
		printk("migration_cost[%d]: %Ld\n", i-1, migration_cost[i-1]);
	}
	return 1;
}

__setup ("migration_cost=", migration_cost_setup);

/*
 * Global multiplier (divisor) for migration-cutoff values,
 * in percentiles. E.g. use a value of 150 to get 1.5 times
 * longer cache-hot cutoff times.
 *
 * (We scale it from 100 to 128 to long long handling easier.)
 */

#define MIGRATION_FACTOR_SCALE 128

static unsigned int migration_factor = MIGRATION_FACTOR_SCALE;

static int __init setup_migration_factor(char *str)
{
	get_option(&str, &migration_factor);
	migration_factor = migration_factor * MIGRATION_FACTOR_SCALE / 100;
	return 1;
}

__setup("migration_factor=", setup_migration_factor);

/*
 * Estimated distance of two CPUs, measured via the number of domains
 * we have to pass for the two CPUs to be in the same span:
 */
static unsigned long domain_distance(int cpu1, int cpu2)
{
	unsigned long distance = 0;
	struct sched_domain *sd;

	for_each_domain(cpu1, sd) {
		WARN_ON(!cpu_isset(cpu1, sd->span));
		if (cpu_isset(cpu2, sd->span))
			return distance;
		distance++;
	}
	if (distance >= MAX_DOMAIN_DISTANCE) {
		WARN_ON(1);
		distance = MAX_DOMAIN_DISTANCE-1;
	}

	return distance;
}

static unsigned int migration_debug;

static int __init setup_migration_debug(char *str)
{
	get_option(&str, &migration_debug);
	return 1;
}

__setup("migration_debug=", setup_migration_debug);

/*
 * Maximum cache-size that the scheduler should try to measure.
 * Architectures with larger caches should tune this up during
 * bootup. Gets used in the domain-setup code (i.e. during SMP
 * bootup).
 */
unsigned int max_cache_size;

static int __init setup_max_cache_size(char *str)
{
	get_option(&str, &max_cache_size);
	return 1;
}

__setup("max_cache_size=", setup_max_cache_size);

/*
 * Dirty a big buffer in a hard-to-predict (for the L2 cache) way. This
 * is the operation that is timed, so we try to generate unpredictable
 * cachemisses that still end up filling the L2 cache:
 */
static void touch_cache(void *__cache, unsigned long __size)
{
	unsigned long size = __size/sizeof(long), chunk1 = size/3,
			chunk2 = 2*size/3;
	unsigned long *cache = __cache;
	int i;

	for (i = 0; i < size/6; i += 8) {
		switch (i % 6) {
			case 0: cache[i]++;
			case 1: cache[size-1-i]++;
			case 2: cache[chunk1-i]++;
			case 3: cache[chunk1+i]++;
			case 4: cache[chunk2-i]++;
			case 5: cache[chunk2+i]++;
		}
	}
}

/*
 * Measure the cache-cost of one task migration. Returns in units of nsec.
 */
static unsigned long long measure_one(void *cache, unsigned long size,
				      int source, int target)
{
	cpumask_t mask, saved_mask;
	unsigned long long t0, t1, t2, t3, cost;

	saved_mask = current->cpus_allowed;

	/*
	 * Flush source caches to RAM and invalidate them:
	 */
	sched_cacheflush();

	/*
	 * Migrate to the source CPU:
	 */
	mask = cpumask_of_cpu(source);
	set_cpus_allowed(current, mask);
	WARN_ON(smp_processor_id() != source);

	/*
	 * Dirty the working set:
	 */
	t0 = sched_clock();
	touch_cache(cache, size);
	t1 = sched_clock();

	/*
	 * Migrate to the target CPU, dirty the L2 cache and access
	 * the shared buffer. (which represents the working set
	 * of a migrated task.)
	 */
	mask = cpumask_of_cpu(target);
	set_cpus_allowed(current, mask);
	WARN_ON(smp_processor_id() != target);

	t2 = sched_clock();
	touch_cache(cache, size);
	t3 = sched_clock();

	cost = t1-t0 + t3-t2;

	if (migration_debug >= 2)
		printk("[%d->%d]: %8Ld %8Ld %8Ld => %10Ld.\n",
			source, target, t1-t0, t1-t0, t3-t2, cost);
	/*
	 * Flush target caches to RAM and invalidate them:
	 */
	sched_cacheflush();

	set_cpus_allowed(current, saved_mask);

	return cost;
}

/*
 * Measure a series of task migrations and return the average
 * result. Since this code runs early during bootup the system
 * is 'undisturbed' and the average latency makes sense.
 *
 * The algorithm in essence auto-detects the relevant cache-size,
 * so it will properly detect different cachesizes for different
 * cache-hierarchies, depending on how the CPUs are connected.
 *
 * Architectures can prime the upper limit of the search range via
 * max_cache_size, otherwise the search range defaults to 20MB...64K.
 */
static unsigned long long
measure_cost(int cpu1, int cpu2, void *cache, unsigned int size)
{
	unsigned long long cost1, cost2;
	int i;

	/*
	 * Measure the migration cost of 'size' bytes, over an
	 * average of 10 runs:
	 *
	 * (We perturb the cache size by a small (0..4k)
	 *  value to compensate size/alignment related artifacts.
	 *  We also subtract the cost of the operation done on
	 *  the same CPU.)
	 */
	cost1 = 0;

	/*
	 * dry run, to make sure we start off cache-cold on cpu1,
	 * and to get any vmalloc pagefaults in advance:
	 */
	measure_one(cache, size, cpu1, cpu2);
	for (i = 0; i < ITERATIONS; i++)
		cost1 += measure_one(cache, size - i*1024, cpu1, cpu2);

	measure_one(cache, size, cpu2, cpu1);
	for (i = 0; i < ITERATIONS; i++)
		cost1 += measure_one(cache, size - i*1024, cpu2, cpu1);

	/*
	 * (We measure the non-migrating [cached] cost on both
	 *  cpu1 and cpu2, to handle CPUs with different speeds)
	 */
	cost2 = 0;

	measure_one(cache, size, cpu1, cpu1);
	for (i = 0; i < ITERATIONS; i++)
		cost2 += measure_one(cache, size - i*1024, cpu1, cpu1);

	measure_one(cache, size, cpu2, cpu2);
	for (i = 0; i < ITERATIONS; i++)
		cost2 += measure_one(cache, size - i*1024, cpu2, cpu2);

	/*
	 * Get the per-iteration migration cost:
	 */
	do_div(cost1, 2*ITERATIONS);
	do_div(cost2, 2*ITERATIONS);

	return cost1 - cost2;
}

static unsigned long long measure_migration_cost(int cpu1, int cpu2)
{
	unsigned long long max_cost = 0, fluct = 0, avg_fluct = 0;
	unsigned int max_size, size, size_found = 0;
	long long cost = 0, prev_cost;
	void *cache;

	/*
	 * Search from max_cache_size*5 down to 64K - the real relevant
	 * cachesize has to lie somewhere inbetween.
	 */
	if (max_cache_size) {
		max_size = max(max_cache_size * SEARCH_SCOPE, MIN_CACHE_SIZE);
		size = max(max_cache_size / SEARCH_SCOPE, MIN_CACHE_SIZE);
	} else {
		/*
		 * Since we have no estimation about the relevant
		 * search range
		 */
		max_size = DEFAULT_CACHE_SIZE * SEARCH_SCOPE;
		size = MIN_CACHE_SIZE;
	}

	if (!cpu_online(cpu1) || !cpu_online(cpu2)) {
		printk("cpu %d and %d not both online!\n", cpu1, cpu2);
		return 0;
	}

	/*
	 * Allocate the working set:
	 */
	cache = vmalloc(max_size);
	if (!cache) {
		printk("could not vmalloc %d bytes for cache!\n", 2*max_size);
		return 1000000; // return 1 msec on very small boxen
	}

	while (size <= max_size) {
		prev_cost = cost;
		cost = measure_cost(cpu1, cpu2, cache, size);

		/*
		 * Update the max:
		 */
		if (cost > 0) {
			if (max_cost < cost) {
				max_cost = cost;
				size_found = size;
			}
		}
		/*
		 * Calculate average fluctuation, we use this to prevent
		 * noise from triggering an early break out of the loop:
		 */
		fluct = abs(cost - prev_cost);
		avg_fluct = (avg_fluct + fluct)/2;

		if (migration_debug)
			printk("-> [%d][%d][%7d] %3ld.%ld [%3ld.%ld] (%ld): (%8Ld %8Ld)\n",
				cpu1, cpu2, size,
				(long)cost / 1000000,
				((long)cost / 100000) % 10,
				(long)max_cost / 1000000,
				((long)max_cost / 100000) % 10,
				domain_distance(cpu1, cpu2),
				cost, avg_fluct);

		/*
		 * If we iterated at least 20% past the previous maximum,
		 * and the cost has dropped by more than 20% already,
		 * (taking fluctuations into account) then we assume to
		 * have found the maximum and break out of the loop early:
		 */
		if (size_found && (size*100 > size_found*SIZE_THRESH))
			if (cost+avg_fluct <= 0 ||
				max_cost*100 > (cost+avg_fluct)*COST_THRESH) {

				if (migration_debug)
					printk("-> found max.\n");
				break;
			}
		/*
5447
		 * Increase the cachesize in 10% steps:
5448
		 */
5449
		size = size * 10 / 9;
5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517
	}

	if (migration_debug)
		printk("[%d][%d] working set size found: %d, cost: %Ld\n",
			cpu1, cpu2, size_found, max_cost);

	vfree(cache);

	/*
	 * A task is considered 'cache cold' if at least 2 times
	 * the worst-case cost of migration has passed.
	 *
	 * (this limit is only listened to if the load-balancing
	 * situation is 'nice' - if there is a large imbalance we
	 * ignore it for the sake of CPU utilization and
	 * processing fairness.)
	 */
	return 2 * max_cost * migration_factor / MIGRATION_FACTOR_SCALE;
}

static void calibrate_migration_costs(const cpumask_t *cpu_map)
{
	int cpu1 = -1, cpu2 = -1, cpu, orig_cpu = raw_smp_processor_id();
	unsigned long j0, j1, distance, max_distance = 0;
	struct sched_domain *sd;

	j0 = jiffies;

	/*
	 * First pass - calculate the cacheflush times:
	 */
	for_each_cpu_mask(cpu1, *cpu_map) {
		for_each_cpu_mask(cpu2, *cpu_map) {
			if (cpu1 == cpu2)
				continue;
			distance = domain_distance(cpu1, cpu2);
			max_distance = max(max_distance, distance);
			/*
			 * No result cached yet?
			 */
			if (migration_cost[distance] == -1LL)
				migration_cost[distance] =
					measure_migration_cost(cpu1, cpu2);
		}
	}
	/*
	 * Second pass - update the sched domain hierarchy with
	 * the new cache-hot-time estimations:
	 */
	for_each_cpu_mask(cpu, *cpu_map) {
		distance = 0;
		for_each_domain(cpu, sd) {
			sd->cache_hot_time = migration_cost[distance];
			distance++;
		}
	}
	/*
	 * Print the matrix:
	 */
	if (migration_debug)
		printk("migration: max_cache_size: %d, cpu: %d MHz:\n",
			max_cache_size,
#ifdef CONFIG_X86
			cpu_khz/1000
#else
			-1
#endif
		);
5518 5519 5520 5521 5522 5523 5524 5525
	if (system_state == SYSTEM_BOOTING) {
		printk("migration_cost=");
		for (distance = 0; distance <= max_distance; distance++) {
			if (distance)
				printk(",");
			printk("%ld", (long)migration_cost[distance] / 1000);
		}
		printk("\n");
5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543
	}
	j1 = jiffies;
	if (migration_debug)
		printk("migration: %ld seconds\n", (j1-j0)/HZ);

	/*
	 * Move back to the original CPU. NUMA-Q gets confused
	 * if we migrate to another quad during bootup.
	 */
	if (raw_smp_processor_id() != orig_cpu) {
		cpumask_t mask = cpumask_of_cpu(orig_cpu),
			saved_mask = current->cpus_allowed;

		set_cpus_allowed(current, mask);
		set_cpus_allowed(current, saved_mask);
	}
}

5544
#ifdef CONFIG_NUMA
5545

5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621
/**
 * find_next_best_node - find the next node to include in a sched_domain
 * @node: node whose sched_domain we're building
 * @used_nodes: nodes already in the sched_domain
 *
 * Find the next node to include in a given scheduling domain.  Simply
 * finds the closest node not already in the @used_nodes map.
 *
 * Should use nodemask_t.
 */
static int find_next_best_node(int node, unsigned long *used_nodes)
{
	int i, n, val, min_val, best_node = 0;

	min_val = INT_MAX;

	for (i = 0; i < MAX_NUMNODES; i++) {
		/* Start at @node */
		n = (node + i) % MAX_NUMNODES;

		if (!nr_cpus_node(n))
			continue;

		/* Skip already used nodes */
		if (test_bit(n, used_nodes))
			continue;

		/* Simple min distance search */
		val = node_distance(node, n);

		if (val < min_val) {
			min_val = val;
			best_node = n;
		}
	}

	set_bit(best_node, used_nodes);
	return best_node;
}

/**
 * sched_domain_node_span - get a cpumask for a node's sched_domain
 * @node: node whose cpumask we're constructing
 * @size: number of nodes to include in this span
 *
 * Given a node, construct a good cpumask for its sched_domain to span.  It
 * should be one that prevents unnecessary balancing, but also spreads tasks
 * out optimally.
 */
static cpumask_t sched_domain_node_span(int node)
{
	int i;
	cpumask_t span, nodemask;
	DECLARE_BITMAP(used_nodes, MAX_NUMNODES);

	cpus_clear(span);
	bitmap_zero(used_nodes, MAX_NUMNODES);

	nodemask = node_to_cpumask(node);
	cpus_or(span, span, nodemask);
	set_bit(node, used_nodes);

	for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
		int next_node = find_next_best_node(node, used_nodes);
		nodemask = node_to_cpumask(next_node);
		cpus_or(span, span, nodemask);
	}

	return span;
}
#endif

/*
 * At the moment, CONFIG_SCHED_SMT is never defined, but leave it in so we
 * can switch it on easily if needed.
 */
L
Linus Torvalds 已提交
5622 5623 5624
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static struct sched_group sched_group_cpus[NR_CPUS];
5625
static int cpu_to_cpu_group(int cpu)
L
Linus Torvalds 已提交
5626 5627 5628 5629 5630
{
	return cpu;
}
#endif

5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647
#ifdef CONFIG_SCHED_MC
static DEFINE_PER_CPU(struct sched_domain, core_domains);
static struct sched_group sched_group_core[NR_CPUS];
#endif

#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
static int cpu_to_core_group(int cpu)
{
	return first_cpu(cpu_sibling_map[cpu]);
}
#elif defined(CONFIG_SCHED_MC)
static int cpu_to_core_group(int cpu)
{
	return cpu;
}
#endif

L
Linus Torvalds 已提交
5648 5649
static DEFINE_PER_CPU(struct sched_domain, phys_domains);
static struct sched_group sched_group_phys[NR_CPUS];
5650
static int cpu_to_phys_group(int cpu)
L
Linus Torvalds 已提交
5651
{
5652 5653 5654 5655
#if defined(CONFIG_SCHED_MC)
	cpumask_t mask = cpu_coregroup_map(cpu);
	return first_cpu(mask);
#elif defined(CONFIG_SCHED_SMT)
L
Linus Torvalds 已提交
5656 5657 5658 5659 5660 5661 5662 5663
	return first_cpu(cpu_sibling_map[cpu]);
#else
	return cpu;
#endif
}

#ifdef CONFIG_NUMA
/*
5664 5665 5666
 * The init_sched_build_groups can't handle what we want to do with node
 * groups, so roll our own. Now each node has its own list of groups which
 * gets dynamically allocated.
L
Linus Torvalds 已提交
5667
 */
5668
static DEFINE_PER_CPU(struct sched_domain, node_domains);
5669
static struct sched_group **sched_group_nodes_bycpu[NR_CPUS];
L
Linus Torvalds 已提交
5670

5671
static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
5672
static struct sched_group *sched_group_allnodes_bycpu[NR_CPUS];
5673 5674 5675 5676

static int cpu_to_allnodes_group(int cpu)
{
	return cpu_to_node(cpu);
L
Linus Torvalds 已提交
5677
}
5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703
static void init_numa_sched_groups_power(struct sched_group *group_head)
{
	struct sched_group *sg = group_head;
	int j;

	if (!sg)
		return;
next_sg:
	for_each_cpu_mask(j, sg->cpumask) {
		struct sched_domain *sd;

		sd = &per_cpu(phys_domains, j);
		if (j != first_cpu(sd->groups->cpumask)) {
			/*
			 * Only add "power" once for each
			 * physical package.
			 */
			continue;
		}

		sg->cpu_power += sd->groups->cpu_power;
	}
	sg = sg->next;
	if (sg != group_head)
		goto next_sg;
}
L
Linus Torvalds 已提交
5704 5705 5706
#endif

/*
5707 5708
 * Build sched domains for a given set of cpus and attach the sched domains
 * to the individual cpus
L
Linus Torvalds 已提交
5709
 */
5710
void build_sched_domains(const cpumask_t *cpu_map)
L
Linus Torvalds 已提交
5711 5712
{
	int i;
5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727
#ifdef CONFIG_NUMA
	struct sched_group **sched_group_nodes = NULL;
	struct sched_group *sched_group_allnodes = NULL;

	/*
	 * Allocate the per-node list of sched groups
	 */
	sched_group_nodes = kmalloc(sizeof(struct sched_group*)*MAX_NUMNODES,
					   GFP_ATOMIC);
	if (!sched_group_nodes) {
		printk(KERN_WARNING "Can not alloc sched group node list\n");
		return;
	}
	sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
#endif
L
Linus Torvalds 已提交
5728 5729

	/*
5730
	 * Set up domains for cpus specified by the cpu_map.
L
Linus Torvalds 已提交
5731
	 */
5732
	for_each_cpu_mask(i, *cpu_map) {
L
Linus Torvalds 已提交
5733 5734 5735 5736
		int group;
		struct sched_domain *sd = NULL, *p;
		cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));

5737
		cpus_and(nodemask, nodemask, *cpu_map);
L
Linus Torvalds 已提交
5738 5739

#ifdef CONFIG_NUMA
5740
		if (cpus_weight(*cpu_map)
5741
				> SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754
			if (!sched_group_allnodes) {
				sched_group_allnodes
					= kmalloc(sizeof(struct sched_group)
							* MAX_NUMNODES,
						  GFP_KERNEL);
				if (!sched_group_allnodes) {
					printk(KERN_WARNING
					"Can not alloc allnodes sched group\n");
					break;
				}
				sched_group_allnodes_bycpu[i]
						= sched_group_allnodes;
			}
5755 5756 5757 5758 5759 5760 5761 5762 5763
			sd = &per_cpu(allnodes_domains, i);
			*sd = SD_ALLNODES_INIT;
			sd->span = *cpu_map;
			group = cpu_to_allnodes_group(i);
			sd->groups = &sched_group_allnodes[group];
			p = sd;
		} else
			p = NULL;

L
Linus Torvalds 已提交
5764 5765
		sd = &per_cpu(node_domains, i);
		*sd = SD_NODE_INIT;
5766 5767 5768
		sd->span = sched_domain_node_span(cpu_to_node(i));
		sd->parent = p;
		cpus_and(sd->span, sd->span, *cpu_map);
L
Linus Torvalds 已提交
5769 5770 5771 5772 5773 5774 5775 5776 5777 5778
#endif

		p = sd;
		sd = &per_cpu(phys_domains, i);
		group = cpu_to_phys_group(i);
		*sd = SD_CPU_INIT;
		sd->span = nodemask;
		sd->parent = p;
		sd->groups = &sched_group_phys[group];

5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789
#ifdef CONFIG_SCHED_MC
		p = sd;
		sd = &per_cpu(core_domains, i);
		group = cpu_to_core_group(i);
		*sd = SD_MC_INIT;
		sd->span = cpu_coregroup_map(i);
		cpus_and(sd->span, sd->span, *cpu_map);
		sd->parent = p;
		sd->groups = &sched_group_core[group];
#endif

L
Linus Torvalds 已提交
5790 5791 5792 5793 5794 5795
#ifdef CONFIG_SCHED_SMT
		p = sd;
		sd = &per_cpu(cpu_domains, i);
		group = cpu_to_cpu_group(i);
		*sd = SD_SIBLING_INIT;
		sd->span = cpu_sibling_map[i];
5796
		cpus_and(sd->span, sd->span, *cpu_map);
L
Linus Torvalds 已提交
5797 5798 5799 5800 5801 5802 5803
		sd->parent = p;
		sd->groups = &sched_group_cpus[group];
#endif
	}

#ifdef CONFIG_SCHED_SMT
	/* Set up CPU (sibling) groups */
5804
	for_each_cpu_mask(i, *cpu_map) {
L
Linus Torvalds 已提交
5805
		cpumask_t this_sibling_map = cpu_sibling_map[i];
5806
		cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
L
Linus Torvalds 已提交
5807 5808 5809 5810 5811 5812 5813 5814
		if (i != first_cpu(this_sibling_map))
			continue;

		init_sched_build_groups(sched_group_cpus, this_sibling_map,
						&cpu_to_cpu_group);
	}
#endif

5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827
#ifdef CONFIG_SCHED_MC
	/* Set up multi-core groups */
	for_each_cpu_mask(i, *cpu_map) {
		cpumask_t this_core_map = cpu_coregroup_map(i);
		cpus_and(this_core_map, this_core_map, *cpu_map);
		if (i != first_cpu(this_core_map))
			continue;
		init_sched_build_groups(sched_group_core, this_core_map,
					&cpu_to_core_group);
	}
#endif


L
Linus Torvalds 已提交
5828 5829 5830 5831
	/* Set up physical groups */
	for (i = 0; i < MAX_NUMNODES; i++) {
		cpumask_t nodemask = node_to_cpumask(i);

5832
		cpus_and(nodemask, nodemask, *cpu_map);
L
Linus Torvalds 已提交
5833 5834 5835 5836 5837 5838 5839 5840 5841
		if (cpus_empty(nodemask))
			continue;

		init_sched_build_groups(sched_group_phys, nodemask,
						&cpu_to_phys_group);
	}

#ifdef CONFIG_NUMA
	/* Set up node groups */
5842 5843 5844
	if (sched_group_allnodes)
		init_sched_build_groups(sched_group_allnodes, *cpu_map,
					&cpu_to_allnodes_group);
5845 5846 5847 5848 5849 5850 5851 5852 5853 5854

	for (i = 0; i < MAX_NUMNODES; i++) {
		/* Set up node groups */
		struct sched_group *sg, *prev;
		cpumask_t nodemask = node_to_cpumask(i);
		cpumask_t domainspan;
		cpumask_t covered = CPU_MASK_NONE;
		int j;

		cpus_and(nodemask, nodemask, *cpu_map);
5855 5856
		if (cpus_empty(nodemask)) {
			sched_group_nodes[i] = NULL;
5857
			continue;
5858
		}
5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912

		domainspan = sched_domain_node_span(i);
		cpus_and(domainspan, domainspan, *cpu_map);

		sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
		sched_group_nodes[i] = sg;
		for_each_cpu_mask(j, nodemask) {
			struct sched_domain *sd;
			sd = &per_cpu(node_domains, j);
			sd->groups = sg;
			if (sd->groups == NULL) {
				/* Turn off balancing if we have no groups */
				sd->flags = 0;
			}
		}
		if (!sg) {
			printk(KERN_WARNING
			"Can not alloc domain group for node %d\n", i);
			continue;
		}
		sg->cpu_power = 0;
		sg->cpumask = nodemask;
		cpus_or(covered, covered, nodemask);
		prev = sg;

		for (j = 0; j < MAX_NUMNODES; j++) {
			cpumask_t tmp, notcovered;
			int n = (i + j) % MAX_NUMNODES;

			cpus_complement(notcovered, covered);
			cpus_and(tmp, notcovered, *cpu_map);
			cpus_and(tmp, tmp, domainspan);
			if (cpus_empty(tmp))
				break;

			nodemask = node_to_cpumask(n);
			cpus_and(tmp, tmp, nodemask);
			if (cpus_empty(tmp))
				continue;

			sg = kmalloc(sizeof(struct sched_group), GFP_KERNEL);
			if (!sg) {
				printk(KERN_WARNING
				"Can not alloc domain group for node %d\n", j);
				break;
			}
			sg->cpu_power = 0;
			sg->cpumask = tmp;
			cpus_or(covered, covered, tmp);
			prev->next = sg;
			prev = sg;
		}
		prev->next = sched_group_nodes[i];
	}
L
Linus Torvalds 已提交
5913 5914 5915
#endif

	/* Calculate CPU power for physical packages and nodes */
5916
	for_each_cpu_mask(i, *cpu_map) {
L
Linus Torvalds 已提交
5917 5918 5919 5920 5921 5922 5923
		int power;
		struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
		sd = &per_cpu(cpu_domains, i);
		power = SCHED_LOAD_SCALE;
		sd->groups->cpu_power = power;
#endif
5924 5925 5926 5927 5928 5929 5930
#ifdef CONFIG_SCHED_MC
		sd = &per_cpu(core_domains, i);
		power = SCHED_LOAD_SCALE + (cpus_weight(sd->groups->cpumask)-1)
					    * SCHED_LOAD_SCALE / 10;
		sd->groups->cpu_power = power;

		sd = &per_cpu(phys_domains, i);
L
Linus Torvalds 已提交
5931

5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943
 		/*
 		 * This has to be < 2 * SCHED_LOAD_SCALE
 		 * Lets keep it SCHED_LOAD_SCALE, so that
 		 * while calculating NUMA group's cpu_power
 		 * we can simply do
 		 *  numa_group->cpu_power += phys_group->cpu_power;
 		 *
 		 * See "only add power once for each physical pkg"
 		 * comment below
 		 */
 		sd->groups->cpu_power = SCHED_LOAD_SCALE;
#else
L
Linus Torvalds 已提交
5944 5945 5946 5947
		sd = &per_cpu(phys_domains, i);
		power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE *
				(cpus_weight(sd->groups->cpumask)-1) / 10;
		sd->groups->cpu_power = power;
5948
#endif
L
Linus Torvalds 已提交
5949 5950
	}

5951
#ifdef CONFIG_NUMA
5952 5953
	for (i = 0; i < MAX_NUMNODES; i++)
		init_numa_sched_groups_power(sched_group_nodes[i]);
5954

5955
	init_numa_sched_groups_power(sched_group_allnodes);
5956 5957
#endif

L
Linus Torvalds 已提交
5958
	/* Attach the domains */
5959
	for_each_cpu_mask(i, *cpu_map) {
L
Linus Torvalds 已提交
5960 5961 5962
		struct sched_domain *sd;
#ifdef CONFIG_SCHED_SMT
		sd = &per_cpu(cpu_domains, i);
5963 5964
#elif defined(CONFIG_SCHED_MC)
		sd = &per_cpu(core_domains, i);
L
Linus Torvalds 已提交
5965 5966 5967 5968 5969
#else
		sd = &per_cpu(phys_domains, i);
#endif
		cpu_attach_domain(sd, i);
	}
5970 5971 5972 5973
	/*
	 * Tune cache-hot values:
	 */
	calibrate_migration_costs(cpu_map);
L
Linus Torvalds 已提交
5974
}
5975 5976 5977
/*
 * Set up scheduler domains and groups.  Callers must hold the hotplug lock.
 */
5978
static void arch_init_sched_domains(const cpumask_t *cpu_map)
5979 5980
{
	cpumask_t cpu_default_map;
L
Linus Torvalds 已提交
5981

5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992
	/*
	 * Setup mask for cpus without special case scheduling requirements.
	 * For now this just excludes isolated cpus, but could be used to
	 * exclude other special cases in the future.
	 */
	cpus_andnot(cpu_default_map, *cpu_map, cpu_isolated_map);

	build_sched_domains(&cpu_default_map);
}

static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
L
Linus Torvalds 已提交
5993
{
5994 5995
#ifdef CONFIG_NUMA
	int i;
5996
	int cpu;
L
Linus Torvalds 已提交
5997

5998 5999 6000 6001 6002
	for_each_cpu_mask(cpu, *cpu_map) {
		struct sched_group *sched_group_allnodes
			= sched_group_allnodes_bycpu[cpu];
		struct sched_group **sched_group_nodes
			= sched_group_nodes_bycpu[cpu];
6003

6004 6005 6006 6007 6008 6009
		if (sched_group_allnodes) {
			kfree(sched_group_allnodes);
			sched_group_allnodes_bycpu[cpu] = NULL;
		}

		if (!sched_group_nodes)
6010
			continue;
6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022

		for (i = 0; i < MAX_NUMNODES; i++) {
			cpumask_t nodemask = node_to_cpumask(i);
			struct sched_group *oldsg, *sg = sched_group_nodes[i];

			cpus_and(nodemask, nodemask, *cpu_map);
			if (cpus_empty(nodemask))
				continue;

			if (sg == NULL)
				continue;
			sg = sg->next;
6023
next_sg:
6024 6025 6026 6027 6028 6029 6030 6031
			oldsg = sg;
			sg = sg->next;
			kfree(oldsg);
			if (oldsg != sched_group_nodes[i])
				goto next_sg;
		}
		kfree(sched_group_nodes);
		sched_group_nodes_bycpu[cpu] = NULL;
6032 6033 6034
	}
#endif
}
L
Linus Torvalds 已提交
6035

6036 6037 6038 6039
/*
 * Detach sched domains from a group of cpus specified in cpu_map
 * These cpus will now be attached to the NULL domain
 */
6040
static void detach_destroy_domains(const cpumask_t *cpu_map)
6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073
{
	int i;

	for_each_cpu_mask(i, *cpu_map)
		cpu_attach_domain(NULL, i);
	synchronize_sched();
	arch_destroy_sched_domains(cpu_map);
}

/*
 * Partition sched domains as specified by the cpumasks below.
 * This attaches all cpus from the cpumasks to the NULL domain,
 * waits for a RCU quiescent period, recalculates sched
 * domain information and then attaches them back to the
 * correct sched domains
 * Call with hotplug lock held
 */
void partition_sched_domains(cpumask_t *partition1, cpumask_t *partition2)
{
	cpumask_t change_map;

	cpus_and(*partition1, *partition1, cpu_online_map);
	cpus_and(*partition2, *partition2, cpu_online_map);
	cpus_or(change_map, *partition1, *partition2);

	/* Detach sched domains from all of the affected cpus */
	detach_destroy_domains(&change_map);
	if (!cpus_empty(*partition1))
		build_sched_domains(partition1);
	if (!cpus_empty(*partition2))
		build_sched_domains(partition2);
}

L
Linus Torvalds 已提交
6074 6075 6076 6077
#ifdef CONFIG_HOTPLUG_CPU
/*
 * Force a reinitialization of the sched domains hierarchy.  The domains
 * and groups cannot be updated in place without racing with the balancing
N
Nick Piggin 已提交
6078
 * code, so we temporarily attach all running cpus to the NULL domain
L
Linus Torvalds 已提交
6079 6080 6081 6082 6083 6084 6085 6086
 * which will prevent rebalancing while the sched domains are recalculated.
 */
static int update_sched_domains(struct notifier_block *nfb,
				unsigned long action, void *hcpu)
{
	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_DOWN_PREPARE:
6087
		detach_destroy_domains(&cpu_online_map);
L
Linus Torvalds 已提交
6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102
		return NOTIFY_OK;

	case CPU_UP_CANCELED:
	case CPU_DOWN_FAILED:
	case CPU_ONLINE:
	case CPU_DEAD:
		/*
		 * Fall through and re-initialise the domains.
		 */
		break;
	default:
		return NOTIFY_DONE;
	}

	/* The hotplug lock is already held by cpu_up/cpu_down */
6103
	arch_init_sched_domains(&cpu_online_map);
L
Linus Torvalds 已提交
6104 6105 6106 6107 6108 6109 6110 6111

	return NOTIFY_OK;
}
#endif

void __init sched_init_smp(void)
{
	lock_cpu_hotplug();
6112
	arch_init_sched_domains(&cpu_online_map);
L
Linus Torvalds 已提交
6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136
	unlock_cpu_hotplug();
	/* XXX: Theoretical race here - CPU may be hotplugged now */
	hotcpu_notifier(update_sched_domains, 0);
}
#else
void __init sched_init_smp(void)
{
}
#endif /* CONFIG_SMP */

int in_sched_functions(unsigned long addr)
{
	/* Linker adds these: start and end of __sched functions */
	extern char __sched_text_start[], __sched_text_end[];
	return in_lock_functions(addr) ||
		(addr >= (unsigned long)__sched_text_start
		&& addr < (unsigned long)__sched_text_end);
}

void __init sched_init(void)
{
	runqueue_t *rq;
	int i, j, k;

6137
	for_each_possible_cpu(i) {
L
Linus Torvalds 已提交
6138 6139 6140 6141
		prio_array_t *array;

		rq = cpu_rq(i);
		spin_lock_init(&rq->lock);
N
Nick Piggin 已提交
6142
		rq->nr_running = 0;
L
Linus Torvalds 已提交
6143 6144 6145 6146 6147
		rq->active = rq->arrays;
		rq->expired = rq->arrays + 1;
		rq->best_expired_prio = MAX_PRIO;

#ifdef CONFIG_SMP
N
Nick Piggin 已提交
6148
		rq->sd = NULL;
N
Nick Piggin 已提交
6149 6150
		for (j = 1; j < 3; j++)
			rq->cpu_load[j] = 0;
L
Linus Torvalds 已提交
6151 6152 6153 6154
		rq->active_balance = 0;
		rq->push_cpu = 0;
		rq->migration_thread = NULL;
		INIT_LIST_HEAD(&rq->migration_queue);
A
Anton Blanchard 已提交
6155
		rq->cpu = i;
L
Linus Torvalds 已提交
6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195
#endif
		atomic_set(&rq->nr_iowait, 0);

		for (j = 0; j < 2; j++) {
			array = rq->arrays + j;
			for (k = 0; k < MAX_PRIO; k++) {
				INIT_LIST_HEAD(array->queue + k);
				__clear_bit(k, array->bitmap);
			}
			// delimiter for bitsearch
			__set_bit(MAX_PRIO, array->bitmap);
		}
	}

	/*
	 * The boot idle thread does lazy MMU switching as well:
	 */
	atomic_inc(&init_mm.mm_count);
	enter_lazy_tlb(&init_mm, current);

	/*
	 * Make us the idle thread. Technically, schedule() should not be
	 * called from this thread, however somewhere below it might be,
	 * but because we are the idle thread, we just pick up running again
	 * when this runqueue becomes "idle".
	 */
	init_idle(current, smp_processor_id());
}

#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP
void __might_sleep(char *file, int line)
{
#if defined(in_atomic)
	static unsigned long prev_jiffy;	/* ratelimiting */

	if ((in_atomic() || irqs_disabled()) &&
	    system_state == SYSTEM_RUNNING && !oops_in_progress) {
		if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
			return;
		prev_jiffy = jiffies;
6196
		printk(KERN_ERR "BUG: sleeping function called from invalid"
L
Linus Torvalds 已提交
6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236
				" context at %s:%d\n", file, line);
		printk("in_atomic():%d, irqs_disabled():%d\n",
			in_atomic(), irqs_disabled());
		dump_stack();
	}
#endif
}
EXPORT_SYMBOL(__might_sleep);
#endif

#ifdef CONFIG_MAGIC_SYSRQ
void normalize_rt_tasks(void)
{
	struct task_struct *p;
	prio_array_t *array;
	unsigned long flags;
	runqueue_t *rq;

	read_lock_irq(&tasklist_lock);
	for_each_process (p) {
		if (!rt_task(p))
			continue;

		rq = task_rq_lock(p, &flags);

		array = p->array;
		if (array)
			deactivate_task(p, task_rq(p));
		__setscheduler(p, SCHED_NORMAL, 0);
		if (array) {
			__activate_task(p, task_rq(p));
			resched_task(rq->curr);
		}

		task_rq_unlock(rq, &flags);
	}
	read_unlock_irq(&tasklist_lock);
}

#endif /* CONFIG_MAGIC_SYSRQ */
6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280

#ifdef CONFIG_IA64
/*
 * These functions are only useful for the IA64 MCA handling.
 *
 * They can only be called when the whole system has been
 * stopped - every CPU needs to be quiescent, and no scheduling
 * activity can take place. Using them for anything else would
 * be a serious bug, and as a result, they aren't even visible
 * under any other configuration.
 */

/**
 * curr_task - return the current task for a given cpu.
 * @cpu: the processor in question.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 */
task_t *curr_task(int cpu)
{
	return cpu_curr(cpu);
}

/**
 * set_curr_task - set the current task for a given cpu.
 * @cpu: the processor in question.
 * @p: the task pointer to set.
 *
 * Description: This function must only be used when non-maskable interrupts
 * are serviced on a separate stack.  It allows the architecture to switch the
 * notion of the current task on a cpu in a non-blocking manner.  This function
 * must be called with all CPU's synchronized, and interrupts disabled, the
 * and caller must save the original value of the current task (see
 * curr_task() above) and restore that value before reenabling interrupts and
 * re-starting the system.
 *
 * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
 */
void set_curr_task(int cpu, task_t *p)
{
	cpu_curr(cpu) = p;
}

#endif