timer.c 42.2 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
/*
 *  linux/kernel/timer.c
 *
4
 *  Kernel internal timers, basic process system calls
L
Linus Torvalds 已提交
5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  1997-01-28  Modified by Finn Arne Gangstad to make timers scale better.
 *
 *  1997-09-10  Updated NTP code according to technical memorandum Jan '96
 *              "A Kernel Model for Precision Timekeeping" by Dave Mills
 *  1998-12-24  Fixed a xtime SMP race (we need the xtime_lock rw spinlock to
 *              serialize accesses to xtime/lost_ticks).
 *                              Copyright (C) 1998  Andrea Arcangeli
 *  1999-03-10  Improved NTP compatibility by Ulrich Windl
 *  2002-05-31	Move sys_sysinfo here and make its locking sane, Robert Love
 *  2000-10-05  Implemented scalable SMP per-CPU timer handling.
 *                              Copyright (C) 2000, 2001, 2002  Ingo Molnar
 *              Designed by David S. Miller, Alexey Kuznetsov and Ingo Molnar
 */

#include <linux/kernel_stat.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/swap.h>
29
#include <linux/pid_namespace.h>
L
Linus Torvalds 已提交
30 31 32 33 34 35 36
#include <linux/notifier.h>
#include <linux/thread_info.h>
#include <linux/time.h>
#include <linux/jiffies.h>
#include <linux/posix-timers.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
A
Adrian Bunk 已提交
37
#include <linux/delay.h>
38
#include <linux/tick.h>
39
#include <linux/kallsyms.h>
L
Linus Torvalds 已提交
40 41 42 43 44 45 46

#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/div64.h>
#include <asm/timex.h>
#include <asm/io.h>

T
Thomas Gleixner 已提交
47 48 49 50
u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;

EXPORT_SYMBOL(jiffies_64);

L
Linus Torvalds 已提交
51 52 53 54 55 56 57 58 59 60
/*
 * per-CPU timer vector definitions:
 */
#define TVN_BITS (CONFIG_BASE_SMALL ? 4 : 6)
#define TVR_BITS (CONFIG_BASE_SMALL ? 6 : 8)
#define TVN_SIZE (1 << TVN_BITS)
#define TVR_SIZE (1 << TVR_BITS)
#define TVN_MASK (TVN_SIZE - 1)
#define TVR_MASK (TVR_SIZE - 1)

61
struct tvec {
L
Linus Torvalds 已提交
62
	struct list_head vec[TVN_SIZE];
63
};
L
Linus Torvalds 已提交
64

65
struct tvec_root {
L
Linus Torvalds 已提交
66
	struct list_head vec[TVR_SIZE];
67
};
L
Linus Torvalds 已提交
68

69
struct tvec_base {
70 71
	spinlock_t lock;
	struct timer_list *running_timer;
L
Linus Torvalds 已提交
72
	unsigned long timer_jiffies;
73 74 75 76 77
	struct tvec_root tv1;
	struct tvec tv2;
	struct tvec tv3;
	struct tvec tv4;
	struct tvec tv5;
78
} ____cacheline_aligned;
L
Linus Torvalds 已提交
79

80
struct tvec_base boot_tvec_bases;
81
EXPORT_SYMBOL(boot_tvec_bases);
82
static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
L
Linus Torvalds 已提交
83

84
/*
85
 * Note that all tvec_bases are 2 byte aligned and lower bit of
86 87 88 89 90 91
 * base in timer_list is guaranteed to be zero. Use the LSB for
 * the new flag to indicate whether the timer is deferrable
 */
#define TBASE_DEFERRABLE_FLAG		(0x1)

/* Functions below help us manage 'deferrable' flag */
92
static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
93
{
94
	return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG);
95 96
}

97
static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
98
{
99
	return ((struct tvec_base *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG));
100 101 102 103
}

static inline void timer_set_deferrable(struct timer_list *timer)
{
104
	timer->base = ((struct tvec_base *)((unsigned long)(timer->base) |
105
				       TBASE_DEFERRABLE_FLAG));
106 107 108
}

static inline void
109
timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
110
{
111
	timer->base = (struct tvec_base *)((unsigned long)(new_base) |
112
				      tbase_get_deferrable(timer->base));
113 114
}

115 116
static unsigned long round_jiffies_common(unsigned long j, int cpu,
		bool force_up)
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137
{
	int rem;
	unsigned long original = j;

	/*
	 * We don't want all cpus firing their timers at once hitting the
	 * same lock or cachelines, so we skew each extra cpu with an extra
	 * 3 jiffies. This 3 jiffies came originally from the mm/ code which
	 * already did this.
	 * The skew is done by adding 3*cpunr, then round, then subtract this
	 * extra offset again.
	 */
	j += cpu * 3;

	rem = j % HZ;

	/*
	 * If the target jiffie is just after a whole second (which can happen
	 * due to delays of the timer irq, long irq off times etc etc) then
	 * we should round down to the whole second, not up. Use 1/4th second
	 * as cutoff for this rounding as an extreme upper bound for this.
138
	 * But never round down if @force_up is set.
139
	 */
140
	if (rem < HZ/4 && !force_up) /* round down */
141 142 143 144 145 146 147 148 149 150 151
		j = j - rem;
	else /* round up */
		j = j - rem + HZ;

	/* now that we have rounded, subtract the extra skew again */
	j -= cpu * 3;

	if (j <= jiffies) /* rounding ate our timeout entirely; */
		return original;
	return j;
}
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176

/**
 * __round_jiffies - function to round jiffies to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * __round_jiffies() rounds an absolute time in the future (in jiffies)
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The exact rounding is skewed for each processor to avoid all
 * processors firing at the exact same time, which could lead
 * to lock contention or spurious cache line bouncing.
 *
 * The return value is the rounded version of the @j parameter.
 */
unsigned long __round_jiffies(unsigned long j, int cpu)
{
	return round_jiffies_common(j, cpu, false);
}
177 178 179 180 181 182 183
EXPORT_SYMBOL_GPL(__round_jiffies);

/**
 * __round_jiffies_relative - function to round jiffies to a full second
 * @j: the time in (relative) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
184
 * __round_jiffies_relative() rounds a time delta  in the future (in jiffies)
185 186 187 188 189 190 191 192 193 194 195 196
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
 * The exact rounding is skewed for each processor to avoid all
 * processors firing at the exact same time, which could lead
 * to lock contention or spurious cache line bouncing.
 *
197
 * The return value is the rounded version of the @j parameter.
198 199 200
 */
unsigned long __round_jiffies_relative(unsigned long j, int cpu)
{
201 202 203 204
	unsigned long j0 = jiffies;

	/* Use j0 because jiffies might change while we run */
	return round_jiffies_common(j + j0, cpu, false) - j0;
205 206 207 208 209 210 211
}
EXPORT_SYMBOL_GPL(__round_jiffies_relative);

/**
 * round_jiffies - function to round jiffies to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 *
212
 * round_jiffies() rounds an absolute time in the future (in jiffies)
213 214 215 216 217 218 219 220
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
221
 * The return value is the rounded version of the @j parameter.
222 223 224
 */
unsigned long round_jiffies(unsigned long j)
{
225
	return round_jiffies_common(j, raw_smp_processor_id(), false);
226 227 228 229 230 231 232
}
EXPORT_SYMBOL_GPL(round_jiffies);

/**
 * round_jiffies_relative - function to round jiffies to a full second
 * @j: the time in (relative) jiffies that should be rounded
 *
233
 * round_jiffies_relative() rounds a time delta  in the future (in jiffies)
234 235 236 237 238 239 240 241
 * up or down to (approximately) full seconds. This is useful for timers
 * for which the exact time they fire does not matter too much, as long as
 * they fire approximately every X seconds.
 *
 * By rounding these timers to whole seconds, all such timers will fire
 * at the same time, rather than at various times spread out. The goal
 * of this is to have the CPU wake up less, which saves power.
 *
242
 * The return value is the rounded version of the @j parameter.
243 244 245 246 247 248 249
 */
unsigned long round_jiffies_relative(unsigned long j)
{
	return __round_jiffies_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_relative);

250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314
/**
 * __round_jiffies_up - function to round jiffies up to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * This is the same as __round_jiffies() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long __round_jiffies_up(unsigned long j, int cpu)
{
	return round_jiffies_common(j, cpu, true);
}
EXPORT_SYMBOL_GPL(__round_jiffies_up);

/**
 * __round_jiffies_up_relative - function to round jiffies up to a full second
 * @j: the time in (relative) jiffies that should be rounded
 * @cpu: the processor number on which the timeout will happen
 *
 * This is the same as __round_jiffies_relative() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long __round_jiffies_up_relative(unsigned long j, int cpu)
{
	unsigned long j0 = jiffies;

	/* Use j0 because jiffies might change while we run */
	return round_jiffies_common(j + j0, cpu, true) - j0;
}
EXPORT_SYMBOL_GPL(__round_jiffies_up_relative);

/**
 * round_jiffies_up - function to round jiffies up to a full second
 * @j: the time in (absolute) jiffies that should be rounded
 *
 * This is the same as round_jiffies() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long round_jiffies_up(unsigned long j)
{
	return round_jiffies_common(j, raw_smp_processor_id(), true);
}
EXPORT_SYMBOL_GPL(round_jiffies_up);

/**
 * round_jiffies_up_relative - function to round jiffies up to a full second
 * @j: the time in (relative) jiffies that should be rounded
 *
 * This is the same as round_jiffies_relative() except that it will never
 * round down.  This is useful for timeouts for which the exact time
 * of firing does not matter too much, as long as they don't fire too
 * early.
 */
unsigned long round_jiffies_up_relative(unsigned long j)
{
	return __round_jiffies_up_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_up_relative);

315

316
static inline void set_running_timer(struct tvec_base *base,
L
Linus Torvalds 已提交
317 318 319
					struct timer_list *timer)
{
#ifdef CONFIG_SMP
320
	base->running_timer = timer;
L
Linus Torvalds 已提交
321 322 323
#endif
}

324
static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
L
Linus Torvalds 已提交
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365
{
	unsigned long expires = timer->expires;
	unsigned long idx = expires - base->timer_jiffies;
	struct list_head *vec;

	if (idx < TVR_SIZE) {
		int i = expires & TVR_MASK;
		vec = base->tv1.vec + i;
	} else if (idx < 1 << (TVR_BITS + TVN_BITS)) {
		int i = (expires >> TVR_BITS) & TVN_MASK;
		vec = base->tv2.vec + i;
	} else if (idx < 1 << (TVR_BITS + 2 * TVN_BITS)) {
		int i = (expires >> (TVR_BITS + TVN_BITS)) & TVN_MASK;
		vec = base->tv3.vec + i;
	} else if (idx < 1 << (TVR_BITS + 3 * TVN_BITS)) {
		int i = (expires >> (TVR_BITS + 2 * TVN_BITS)) & TVN_MASK;
		vec = base->tv4.vec + i;
	} else if ((signed long) idx < 0) {
		/*
		 * Can happen if you add a timer with expires == jiffies,
		 * or you set a timer to go off in the past
		 */
		vec = base->tv1.vec + (base->timer_jiffies & TVR_MASK);
	} else {
		int i;
		/* If the timeout is larger than 0xffffffff on 64-bit
		 * architectures then we use the maximum timeout:
		 */
		if (idx > 0xffffffffUL) {
			idx = 0xffffffffUL;
			expires = idx + base->timer_jiffies;
		}
		i = (expires >> (TVR_BITS + 3 * TVN_BITS)) & TVN_MASK;
		vec = base->tv5.vec + i;
	}
	/*
	 * Timers are FIFO:
	 */
	list_add_tail(&timer->entry, vec);
}

366 367 368 369 370 371 372 373 374 375
#ifdef CONFIG_TIMER_STATS
void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
{
	if (timer->start_site)
		return;

	timer->start_site = addr;
	memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
	timer->start_pid = current->pid;
}
376 377 378 379 380 381 382 383 384 385 386 387 388 389

static void timer_stats_account_timer(struct timer_list *timer)
{
	unsigned int flag = 0;

	if (unlikely(tbase_get_deferrable(timer->base)))
		flag |= TIMER_STATS_FLAG_DEFERRABLE;

	timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
				 timer->function, timer->start_comm, flag);
}

#else
static void timer_stats_account_timer(struct timer_list *timer) {}
390 391
#endif

392 393 394 395 396 397 398
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS

static struct debug_obj_descr timer_debug_descr;

/*
 * fixup_init is called when:
 * - an active object is initialized
399
 */
400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515
static int timer_fixup_init(void *addr, enum debug_obj_state state)
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		del_timer_sync(timer);
		debug_object_init(timer, &timer_debug_descr);
		return 1;
	default:
		return 0;
	}
}

/*
 * fixup_activate is called when:
 * - an active object is activated
 * - an unknown object is activated (might be a statically initialized object)
 */
static int timer_fixup_activate(void *addr, enum debug_obj_state state)
{
	struct timer_list *timer = addr;

	switch (state) {

	case ODEBUG_STATE_NOTAVAILABLE:
		/*
		 * This is not really a fixup. The timer was
		 * statically initialized. We just make sure that it
		 * is tracked in the object tracker.
		 */
		if (timer->entry.next == NULL &&
		    timer->entry.prev == TIMER_ENTRY_STATIC) {
			debug_object_init(timer, &timer_debug_descr);
			debug_object_activate(timer, &timer_debug_descr);
			return 0;
		} else {
			WARN_ON_ONCE(1);
		}
		return 0;

	case ODEBUG_STATE_ACTIVE:
		WARN_ON(1);

	default:
		return 0;
	}
}

/*
 * fixup_free is called when:
 * - an active object is freed
 */
static int timer_fixup_free(void *addr, enum debug_obj_state state)
{
	struct timer_list *timer = addr;

	switch (state) {
	case ODEBUG_STATE_ACTIVE:
		del_timer_sync(timer);
		debug_object_free(timer, &timer_debug_descr);
		return 1;
	default:
		return 0;
	}
}

static struct debug_obj_descr timer_debug_descr = {
	.name		= "timer_list",
	.fixup_init	= timer_fixup_init,
	.fixup_activate	= timer_fixup_activate,
	.fixup_free	= timer_fixup_free,
};

static inline void debug_timer_init(struct timer_list *timer)
{
	debug_object_init(timer, &timer_debug_descr);
}

static inline void debug_timer_activate(struct timer_list *timer)
{
	debug_object_activate(timer, &timer_debug_descr);
}

static inline void debug_timer_deactivate(struct timer_list *timer)
{
	debug_object_deactivate(timer, &timer_debug_descr);
}

static inline void debug_timer_free(struct timer_list *timer)
{
	debug_object_free(timer, &timer_debug_descr);
}

static void __init_timer(struct timer_list *timer);

void init_timer_on_stack(struct timer_list *timer)
{
	debug_object_init_on_stack(timer, &timer_debug_descr);
	__init_timer(timer);
}
EXPORT_SYMBOL_GPL(init_timer_on_stack);

void destroy_timer_on_stack(struct timer_list *timer)
{
	debug_object_free(timer, &timer_debug_descr);
}
EXPORT_SYMBOL_GPL(destroy_timer_on_stack);

#else
static inline void debug_timer_init(struct timer_list *timer) { }
static inline void debug_timer_activate(struct timer_list *timer) { }
static inline void debug_timer_deactivate(struct timer_list *timer) { }
#endif

static void __init_timer(struct timer_list *timer)
516 517
{
	timer->entry.next = NULL;
518
	timer->base = __raw_get_cpu_var(tvec_bases);
519 520 521 522 523
#ifdef CONFIG_TIMER_STATS
	timer->start_site = NULL;
	timer->start_pid = -1;
	memset(timer->start_comm, 0, TASK_COMM_LEN);
#endif
524
}
525 526 527 528 529 530 531 532 533 534 535 536 537

/**
 * init_timer - initialize a timer.
 * @timer: the timer to be initialized
 *
 * init_timer() must be done to a timer prior calling *any* of the
 * other timer functions.
 */
void init_timer(struct timer_list *timer)
{
	debug_timer_init(timer);
	__init_timer(timer);
}
538 539
EXPORT_SYMBOL(init_timer);

540
void init_timer_deferrable(struct timer_list *timer)
541 542 543 544 545 546
{
	init_timer(timer);
	timer_set_deferrable(timer);
}
EXPORT_SYMBOL(init_timer_deferrable);

547
static inline void detach_timer(struct timer_list *timer,
548
				int clear_pending)
549 550 551
{
	struct list_head *entry = &timer->entry;

552 553
	debug_timer_deactivate(timer);

554 555 556 557 558 559 560
	__list_del(entry->prev, entry->next);
	if (clear_pending)
		entry->next = NULL;
	entry->prev = LIST_POISON2;
}

/*
561
 * We are using hashed locking: holding per_cpu(tvec_bases).lock
562 563 564 565 566 567 568 569 570 571
 * means that all timers which are tied to this base via timer->base are
 * locked, and the base itself is locked too.
 *
 * So __run_timers/migrate_timers can safely modify all timers which could
 * be found on ->tvX lists.
 *
 * When the timer's base is locked, and the timer removed from list, it is
 * possible to set timer->base = NULL and drop the lock: the timer remains
 * locked.
 */
572
static struct tvec_base *lock_timer_base(struct timer_list *timer,
573
					unsigned long *flags)
574
	__acquires(timer->base->lock)
575
{
576
	struct tvec_base *base;
577 578

	for (;;) {
579
		struct tvec_base *prelock_base = timer->base;
580
		base = tbase_get_base(prelock_base);
581 582
		if (likely(base != NULL)) {
			spin_lock_irqsave(&base->lock, *flags);
583
			if (likely(prelock_base == timer->base))
584 585 586 587 588 589 590 591
				return base;
			/* The timer has migrated to another CPU */
			spin_unlock_irqrestore(&base->lock, *flags);
		}
		cpu_relax();
	}
}

I
Ingo Molnar 已提交
592 593
static inline int
__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only)
L
Linus Torvalds 已提交
594
{
595
	struct tvec_base *base, *new_base;
L
Linus Torvalds 已提交
596
	unsigned long flags;
I
Ingo Molnar 已提交
597 598 599
	int ret;

	ret = 0;
L
Linus Torvalds 已提交
600

601
	timer_stats_timer_set_start_info(timer);
L
Linus Torvalds 已提交
602 603
	BUG_ON(!timer->function);

604 605 606 607 608
	base = lock_timer_base(timer, &flags);

	if (timer_pending(timer)) {
		detach_timer(timer, 0);
		ret = 1;
I
Ingo Molnar 已提交
609 610 611
	} else {
		if (pending_only)
			goto out_unlock;
612 613
	}

614 615
	debug_timer_activate(timer);

616
	new_base = __get_cpu_var(tvec_bases);
L
Linus Torvalds 已提交
617

618
	if (base != new_base) {
L
Linus Torvalds 已提交
619
		/*
620 621 622 623 624
		 * We are trying to schedule the timer on the local CPU.
		 * However we can't change timer's base while it is running,
		 * otherwise del_timer_sync() can't detect that the timer's
		 * handler yet has not finished. This also guarantees that
		 * the timer is serialized wrt itself.
L
Linus Torvalds 已提交
625
		 */
626
		if (likely(base->running_timer != timer)) {
627
			/* See the comment in lock_timer_base() */
628
			timer_set_base(timer, NULL);
629
			spin_unlock(&base->lock);
630 631
			base = new_base;
			spin_lock(&base->lock);
632
			timer_set_base(timer, base);
L
Linus Torvalds 已提交
633 634 635 636
		}
	}

	timer->expires = expires;
637
	internal_add_timer(base, timer);
I
Ingo Molnar 已提交
638 639

out_unlock:
640
	spin_unlock_irqrestore(&base->lock, flags);
L
Linus Torvalds 已提交
641 642 643 644

	return ret;
}

645
/**
I
Ingo Molnar 已提交
646 647 648
 * mod_timer_pending - modify a pending timer's timeout
 * @timer: the pending timer to be modified
 * @expires: new timeout in jiffies
L
Linus Torvalds 已提交
649
 *
I
Ingo Molnar 已提交
650 651 652 653
 * mod_timer_pending() is the same for pending timers as mod_timer(),
 * but will not re-activate and modify already deleted timers.
 *
 * It is useful for unserialized use of timers.
L
Linus Torvalds 已提交
654
 */
I
Ingo Molnar 已提交
655
int mod_timer_pending(struct timer_list *timer, unsigned long expires)
L
Linus Torvalds 已提交
656
{
I
Ingo Molnar 已提交
657
	return __mod_timer(timer, expires, true);
L
Linus Torvalds 已提交
658
}
I
Ingo Molnar 已提交
659
EXPORT_SYMBOL(mod_timer_pending);
L
Linus Torvalds 已提交
660

661
/**
L
Linus Torvalds 已提交
662 663
 * mod_timer - modify a timer's timeout
 * @timer: the timer to be modified
664
 * @expires: new timeout in jiffies
L
Linus Torvalds 已提交
665
 *
666
 * mod_timer() is a more efficient way to update the expire field of an
L
Linus Torvalds 已提交
667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690
 * active timer (if the timer is inactive it will be activated)
 *
 * mod_timer(timer, expires) is equivalent to:
 *
 *     del_timer(timer); timer->expires = expires; add_timer(timer);
 *
 * Note that if there are multiple unserialized concurrent users of the
 * same timer, then mod_timer() is the only safe way to modify the timeout,
 * since add_timer() cannot modify an already running timer.
 *
 * The function returns whether it has modified a pending timer or not.
 * (ie. mod_timer() of an inactive timer returns 0, mod_timer() of an
 * active timer returns 1.)
 */
int mod_timer(struct timer_list *timer, unsigned long expires)
{
	/*
	 * This is a common optimization triggered by the
	 * networking code - if the timer is re-modified
	 * to be the same thing then just return:
	 */
	if (timer->expires == expires && timer_pending(timer))
		return 1;

I
Ingo Molnar 已提交
691
	return __mod_timer(timer, expires, false);
L
Linus Torvalds 已提交
692 693 694
}
EXPORT_SYMBOL(mod_timer);

I
Ingo Molnar 已提交
695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745
/**
 * add_timer - start a timer
 * @timer: the timer to be added
 *
 * The kernel will do a ->function(->data) callback from the
 * timer interrupt at the ->expires point in the future. The
 * current time is 'jiffies'.
 *
 * The timer's ->expires, ->function (and if the handler uses it, ->data)
 * fields must be set prior calling this function.
 *
 * Timers with an ->expires field in the past will be executed in the next
 * timer tick.
 */
void add_timer(struct timer_list *timer)
{
	BUG_ON(timer_pending(timer));
	mod_timer(timer, timer->expires);
}
EXPORT_SYMBOL(add_timer);

/**
 * add_timer_on - start a timer on a particular CPU
 * @timer: the timer to be added
 * @cpu: the CPU to start it on
 *
 * This is not very scalable on SMP. Double adds are not possible.
 */
void add_timer_on(struct timer_list *timer, int cpu)
{
	struct tvec_base *base = per_cpu(tvec_bases, cpu);
	unsigned long flags;

	timer_stats_timer_set_start_info(timer);
	BUG_ON(timer_pending(timer) || !timer->function);
	spin_lock_irqsave(&base->lock, flags);
	timer_set_base(timer, base);
	debug_timer_activate(timer);
	internal_add_timer(base, timer);
	/*
	 * Check whether the other CPU is idle and needs to be
	 * triggered to reevaluate the timer wheel when nohz is
	 * active. We are protected against the other CPU fiddling
	 * with the timer by holding the timer base lock. This also
	 * makes sure that a CPU on the way to idle can not evaluate
	 * the timer wheel.
	 */
	wake_up_idle_cpu(cpu);
	spin_unlock_irqrestore(&base->lock, flags);
}

746
/**
L
Linus Torvalds 已提交
747 748 749 750 751 752 753 754 755 756 757 758
 * del_timer - deactive a timer.
 * @timer: the timer to be deactivated
 *
 * del_timer() deactivates a timer - this works on both active and inactive
 * timers.
 *
 * The function returns whether it has deactivated a pending timer or not.
 * (ie. del_timer() of an inactive timer returns 0, del_timer() of an
 * active timer returns 1.)
 */
int del_timer(struct timer_list *timer)
{
759
	struct tvec_base *base;
L
Linus Torvalds 已提交
760
	unsigned long flags;
761
	int ret = 0;
L
Linus Torvalds 已提交
762

763
	timer_stats_timer_clear_start_info(timer);
764 765 766 767 768 769
	if (timer_pending(timer)) {
		base = lock_timer_base(timer, &flags);
		if (timer_pending(timer)) {
			detach_timer(timer, 1);
			ret = 1;
		}
L
Linus Torvalds 已提交
770 771 772
		spin_unlock_irqrestore(&base->lock, flags);
	}

773
	return ret;
L
Linus Torvalds 已提交
774 775 776 777
}
EXPORT_SYMBOL(del_timer);

#ifdef CONFIG_SMP
778 779 780 781
/**
 * try_to_del_timer_sync - Try to deactivate a timer
 * @timer: timer do del
 *
782 783 784 785 786 787 788
 * This function tries to deactivate a timer. Upon successful (ret >= 0)
 * exit the timer is not queued and the handler is not running on any CPU.
 *
 * It must not be called from interrupt contexts.
 */
int try_to_del_timer_sync(struct timer_list *timer)
{
789
	struct tvec_base *base;
790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807
	unsigned long flags;
	int ret = -1;

	base = lock_timer_base(timer, &flags);

	if (base->running_timer == timer)
		goto out;

	ret = 0;
	if (timer_pending(timer)) {
		detach_timer(timer, 1);
		ret = 1;
	}
out:
	spin_unlock_irqrestore(&base->lock, flags);

	return ret;
}
808 809
EXPORT_SYMBOL(try_to_del_timer_sync);

810
/**
L
Linus Torvalds 已提交
811 812 813 814 815 816 817
 * del_timer_sync - deactivate a timer and wait for the handler to finish.
 * @timer: the timer to be deactivated
 *
 * This function only differs from del_timer() on SMP: besides deactivating
 * the timer it also makes sure the handler has finished executing on other
 * CPUs.
 *
818
 * Synchronization rules: Callers must prevent restarting of the timer,
L
Linus Torvalds 已提交
819 820
 * otherwise this function is meaningless. It must not be called from
 * interrupt contexts. The caller must not hold locks which would prevent
821 822 823
 * completion of the timer's handler. The timer's handler must not call
 * add_timer_on(). Upon exit the timer is not queued and the handler is
 * not running on any CPU.
L
Linus Torvalds 已提交
824 825 826 827 828
 *
 * The function returns whether it has deactivated a pending timer or not.
 */
int del_timer_sync(struct timer_list *timer)
{
829 830 831 832
	for (;;) {
		int ret = try_to_del_timer_sync(timer);
		if (ret >= 0)
			return ret;
833
		cpu_relax();
834
	}
L
Linus Torvalds 已提交
835
}
836
EXPORT_SYMBOL(del_timer_sync);
L
Linus Torvalds 已提交
837 838
#endif

839
static int cascade(struct tvec_base *base, struct tvec *tv, int index)
L
Linus Torvalds 已提交
840 841
{
	/* cascade all the timers from tv up one level */
842 843 844 845
	struct timer_list *timer, *tmp;
	struct list_head tv_list;

	list_replace_init(tv->vec + index, &tv_list);
L
Linus Torvalds 已提交
846 847

	/*
848 849
	 * We are removing _all_ timers from the list, so we
	 * don't have to detach them individually.
L
Linus Torvalds 已提交
850
	 */
851
	list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
852
		BUG_ON(tbase_get_base(timer->base) != base);
853
		internal_add_timer(base, timer);
L
Linus Torvalds 已提交
854 855 856 857 858
	}

	return index;
}

859 860 861
#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)

/**
L
Linus Torvalds 已提交
862 863 864 865 866 867
 * __run_timers - run all expired timers (if any) on this CPU.
 * @base: the timer vector to be processed.
 *
 * This function cascades all vectors and executes all expired timer
 * vectors.
 */
868
static inline void __run_timers(struct tvec_base *base)
L
Linus Torvalds 已提交
869 870 871
{
	struct timer_list *timer;

872
	spin_lock_irq(&base->lock);
L
Linus Torvalds 已提交
873
	while (time_after_eq(jiffies, base->timer_jiffies)) {
874
		struct list_head work_list;
L
Linus Torvalds 已提交
875
		struct list_head *head = &work_list;
876
		int index = base->timer_jiffies & TVR_MASK;
877

L
Linus Torvalds 已提交
878 879 880 881 882 883 884 885
		/*
		 * Cascade timers:
		 */
		if (!index &&
			(!cascade(base, &base->tv2, INDEX(0))) &&
				(!cascade(base, &base->tv3, INDEX(1))) &&
					!cascade(base, &base->tv4, INDEX(2)))
			cascade(base, &base->tv5, INDEX(3));
886 887
		++base->timer_jiffies;
		list_replace_init(base->tv1.vec + index, &work_list);
888
		while (!list_empty(head)) {
L
Linus Torvalds 已提交
889 890 891
			void (*fn)(unsigned long);
			unsigned long data;

892
			timer = list_first_entry(head, struct timer_list,entry);
893 894
			fn = timer->function;
			data = timer->data;
L
Linus Torvalds 已提交
895

896 897
			timer_stats_account_timer(timer);

L
Linus Torvalds 已提交
898
			set_running_timer(base, timer);
899
			detach_timer(timer, 1);
900
			spin_unlock_irq(&base->lock);
L
Linus Torvalds 已提交
901
			{
902
				int preempt_count = preempt_count();
L
Linus Torvalds 已提交
903 904
				fn(data);
				if (preempt_count != preempt_count()) {
P
Pavel Machek 已提交
905
					printk(KERN_ERR "huh, entered %p "
906 907 908 909
					       "with preempt_count %08x, exited"
					       " with %08x?\n",
					       fn, preempt_count,
					       preempt_count());
L
Linus Torvalds 已提交
910 911 912
					BUG();
				}
			}
913
			spin_lock_irq(&base->lock);
L
Linus Torvalds 已提交
914 915 916
		}
	}
	set_running_timer(base, NULL);
917
	spin_unlock_irq(&base->lock);
L
Linus Torvalds 已提交
918 919
}

920
#ifdef CONFIG_NO_HZ
L
Linus Torvalds 已提交
921 922 923 924 925
/*
 * Find out when the next timer event is due to happen. This
 * is used on S/390 to stop all activity when a cpus is idle.
 * This functions needs to be called disabled.
 */
926
static unsigned long __next_timer_interrupt(struct tvec_base *base)
L
Linus Torvalds 已提交
927
{
928
	unsigned long timer_jiffies = base->timer_jiffies;
929
	unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA;
930
	int index, slot, array, found = 0;
L
Linus Torvalds 已提交
931
	struct timer_list *nte;
932
	struct tvec *varray[4];
L
Linus Torvalds 已提交
933 934

	/* Look for timer events in tv1. */
935
	index = slot = timer_jiffies & TVR_MASK;
L
Linus Torvalds 已提交
936
	do {
937
		list_for_each_entry(nte, base->tv1.vec + slot, entry) {
938 939
			if (tbase_get_deferrable(nte->base))
				continue;
940

941
			found = 1;
L
Linus Torvalds 已提交
942
			expires = nte->expires;
943 944 945 946
			/* Look at the cascade bucket(s)? */
			if (!index || slot < index)
				goto cascade;
			return expires;
L
Linus Torvalds 已提交
947
		}
948 949 950 951 952 953 954 955
		slot = (slot + 1) & TVR_MASK;
	} while (slot != index);

cascade:
	/* Calculate the next cascade event */
	if (index)
		timer_jiffies += TVR_SIZE - index;
	timer_jiffies >>= TVR_BITS;
L
Linus Torvalds 已提交
956 957 958 959 960 961

	/* Check tv2-tv5. */
	varray[0] = &base->tv2;
	varray[1] = &base->tv3;
	varray[2] = &base->tv4;
	varray[3] = &base->tv5;
962 963

	for (array = 0; array < 4; array++) {
964
		struct tvec *varp = varray[array];
965 966

		index = slot = timer_jiffies & TVN_MASK;
L
Linus Torvalds 已提交
967
		do {
968 969
			list_for_each_entry(nte, varp->vec + slot, entry) {
				found = 1;
L
Linus Torvalds 已提交
970 971
				if (time_before(nte->expires, expires))
					expires = nte->expires;
972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988
			}
			/*
			 * Do we still search for the first timer or are
			 * we looking up the cascade buckets ?
			 */
			if (found) {
				/* Look at the cascade bucket(s)? */
				if (!index || slot < index)
					break;
				return expires;
			}
			slot = (slot + 1) & TVN_MASK;
		} while (slot != index);

		if (index)
			timer_jiffies += TVN_SIZE - index;
		timer_jiffies >>= TVN_BITS;
L
Linus Torvalds 已提交
989
	}
990 991
	return expires;
}
992

993 994 995 996 997 998 999 1000 1001
/*
 * Check, if the next hrtimer event is before the next timer wheel
 * event:
 */
static unsigned long cmp_next_hrtimer_event(unsigned long now,
					    unsigned long expires)
{
	ktime_t hr_delta = hrtimer_get_next_event();
	struct timespec tsdelta;
1002
	unsigned long delta;
1003 1004 1005

	if (hr_delta.tv64 == KTIME_MAX)
		return expires;
1006

1007 1008 1009 1010 1011
	/*
	 * Expired timer available, let it expire in the next tick
	 */
	if (hr_delta.tv64 <= 0)
		return now + 1;
1012

1013
	tsdelta = ktime_to_timespec(hr_delta);
1014
	delta = timespec_to_jiffies(&tsdelta);
1015 1016 1017 1018 1019 1020 1021 1022

	/*
	 * Limit the delta to the max value, which is checked in
	 * tick_nohz_stop_sched_tick():
	 */
	if (delta > NEXT_TIMER_MAX_DELTA)
		delta = NEXT_TIMER_MAX_DELTA;

1023 1024 1025 1026 1027 1028 1029 1030 1031
	/*
	 * Take rounding errors in to account and make sure, that it
	 * expires in the next tick. Otherwise we go into an endless
	 * ping pong due to tick_nohz_stop_sched_tick() retriggering
	 * the timer softirq
	 */
	if (delta < 1)
		delta = 1;
	now += delta;
1032 1033
	if (time_before(now, expires))
		return now;
L
Linus Torvalds 已提交
1034 1035
	return expires;
}
1036 1037

/**
1038
 * get_next_timer_interrupt - return the jiffy of the next pending timer
1039
 * @now: current time (in jiffies)
1040
 */
1041
unsigned long get_next_timer_interrupt(unsigned long now)
1042
{
1043
	struct tvec_base *base = __get_cpu_var(tvec_bases);
1044
	unsigned long expires;
1045 1046 1047 1048 1049 1050 1051 1052 1053 1054

	spin_lock(&base->lock);
	expires = __next_timer_interrupt(base);
	spin_unlock(&base->lock);

	if (time_before_eq(expires, now))
		return now;

	return cmp_next_hrtimer_event(now, expires);
}
L
Linus Torvalds 已提交
1055 1056 1057
#endif

/*
D
Daniel Walker 已提交
1058
 * Called from the timer interrupt handler to charge one tick to the current
L
Linus Torvalds 已提交
1059 1060 1061 1062 1063 1064 1065 1066
 * process.  user_tick is 1 if the tick is user time, 0 for system.
 */
void update_process_times(int user_tick)
{
	struct task_struct *p = current;
	int cpu = smp_processor_id();

	/* Note: this timer irq context must be accounted for as well. */
1067
	account_process_tick(p, user_tick);
L
Linus Torvalds 已提交
1068 1069 1070
	run_local_timers();
	if (rcu_pending(cpu))
		rcu_check_callbacks(cpu, user_tick);
P
Peter Zijlstra 已提交
1071
	printk_tick();
L
Linus Torvalds 已提交
1072
	scheduler_tick();
1073
	run_posix_cpu_timers(p);
L
Linus Torvalds 已提交
1074 1075 1076 1077 1078 1079 1080
}

/*
 * Nr of active tasks - counted in fixed-point numbers
 */
static unsigned long count_active_tasks(void)
{
1081
	return nr_active() * FIXED_1;
L
Linus Torvalds 已提交
1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104
}

/*
 * Hmm.. Changed this, as the GNU make sources (load.c) seems to
 * imply that avenrun[] is the standard name for this kind of thing.
 * Nothing else seems to be standardized: the fractional size etc
 * all seem to differ on different machines.
 *
 * Requires xtime_lock to access.
 */
unsigned long avenrun[3];

EXPORT_SYMBOL(avenrun);

/*
 * calc_load - given tick count, update the avenrun load estimates.
 * This is called while holding a write_lock on xtime_lock.
 */
static inline void calc_load(unsigned long ticks)
{
	unsigned long active_tasks; /* fixed-point */
	static int count = LOAD_FREQ;

E
Eric Dumazet 已提交
1105 1106 1107 1108 1109 1110 1111 1112 1113
	count -= ticks;
	if (unlikely(count < 0)) {
		active_tasks = count_active_tasks();
		do {
			CALC_LOAD(avenrun[0], EXP_1, active_tasks);
			CALC_LOAD(avenrun[1], EXP_5, active_tasks);
			CALC_LOAD(avenrun[2], EXP_15, active_tasks);
			count += LOAD_FREQ;
		} while (count < 0);
L
Linus Torvalds 已提交
1114 1115 1116 1117 1118 1119 1120 1121
	}
}

/*
 * This function runs timers and the timer-tq in bottom half context.
 */
static void run_timer_softirq(struct softirq_action *h)
{
1122
	struct tvec_base *base = __get_cpu_var(tvec_bases);
L
Linus Torvalds 已提交
1123

1124
	hrtimer_run_pending();
1125

L
Linus Torvalds 已提交
1126 1127 1128 1129 1130 1131 1132 1133 1134
	if (time_after_eq(jiffies, base->timer_jiffies))
		__run_timers(base);
}

/*
 * Called by the local, per-CPU timer interrupt on SMP.
 */
void run_local_timers(void)
{
1135
	hrtimer_run_queues();
L
Linus Torvalds 已提交
1136
	raise_softirq(TIMER_SOFTIRQ);
1137
	softlockup_tick();
L
Linus Torvalds 已提交
1138 1139 1140 1141 1142 1143
}

/*
 * Called by the timer interrupt. xtime_lock must already be taken
 * by the timer IRQ!
 */
1144
static inline void update_times(unsigned long ticks)
L
Linus Torvalds 已提交
1145
{
1146
	update_wall_time();
L
Linus Torvalds 已提交
1147 1148
	calc_load(ticks);
}
1149

L
Linus Torvalds 已提交
1150 1151 1152 1153 1154 1155
/*
 * The 64-bit jiffies value is not atomic - you MUST NOT read it
 * without sampling the sequence number in xtime_lock.
 * jiffies is defined in the linker script...
 */

1156
void do_timer(unsigned long ticks)
L
Linus Torvalds 已提交
1157
{
1158 1159
	jiffies_64 += ticks;
	update_times(ticks);
L
Linus Torvalds 已提交
1160 1161 1162 1163 1164 1165 1166 1167
}

#ifdef __ARCH_WANT_SYS_ALARM

/*
 * For backwards compatibility?  This can be done in libc so Alpha
 * and all newer ports shouldn't need it.
 */
1168
SYSCALL_DEFINE1(alarm, unsigned int, seconds)
L
Linus Torvalds 已提交
1169
{
1170
	return alarm_setitimer(seconds);
L
Linus Torvalds 已提交
1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190
}

#endif

#ifndef __alpha__

/*
 * The Alpha uses getxpid, getxuid, and getxgid instead.  Maybe this
 * should be moved into arch/i386 instead?
 */

/**
 * sys_getpid - return the thread group id of the current process
 *
 * Note, despite the name, this returns the tgid not the pid.  The tgid and
 * the pid are identical unless CLONE_THREAD was specified on clone() in
 * which case the tgid is the same in all threads of the same group.
 *
 * This is SMP safe as current->tgid does not change.
 */
1191
SYSCALL_DEFINE0(getpid)
L
Linus Torvalds 已提交
1192
{
1193
	return task_tgid_vnr(current);
L
Linus Torvalds 已提交
1194 1195 1196
}

/*
1197 1198 1199 1200
 * Accessing ->real_parent is not SMP-safe, it could
 * change from under us. However, we can use a stale
 * value of ->real_parent under rcu_read_lock(), see
 * release_task()->call_rcu(delayed_put_task_struct).
L
Linus Torvalds 已提交
1201
 */
1202
SYSCALL_DEFINE0(getppid)
L
Linus Torvalds 已提交
1203 1204 1205
{
	int pid;

1206
	rcu_read_lock();
1207
	pid = task_tgid_vnr(current->real_parent);
1208
	rcu_read_unlock();
L
Linus Torvalds 已提交
1209 1210 1211 1212

	return pid;
}

1213
SYSCALL_DEFINE0(getuid)
L
Linus Torvalds 已提交
1214 1215
{
	/* Only we change this so SMP safe */
1216
	return current_uid();
L
Linus Torvalds 已提交
1217 1218
}

1219
SYSCALL_DEFINE0(geteuid)
L
Linus Torvalds 已提交
1220 1221
{
	/* Only we change this so SMP safe */
1222
	return current_euid();
L
Linus Torvalds 已提交
1223 1224
}

1225
SYSCALL_DEFINE0(getgid)
L
Linus Torvalds 已提交
1226 1227
{
	/* Only we change this so SMP safe */
1228
	return current_gid();
L
Linus Torvalds 已提交
1229 1230
}

1231
SYSCALL_DEFINE0(getegid)
L
Linus Torvalds 已提交
1232 1233
{
	/* Only we change this so SMP safe */
1234
	return  current_egid();
L
Linus Torvalds 已提交
1235 1236 1237 1238 1239 1240
}

#endif

static void process_timeout(unsigned long __data)
{
1241
	wake_up_process((struct task_struct *)__data);
L
Linus Torvalds 已提交
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269
}

/**
 * schedule_timeout - sleep until timeout
 * @timeout: timeout value in jiffies
 *
 * Make the current task sleep until @timeout jiffies have
 * elapsed. The routine will return immediately unless
 * the current task state has been set (see set_current_state()).
 *
 * You can set the task state as follows -
 *
 * %TASK_UNINTERRUPTIBLE - at least @timeout jiffies are guaranteed to
 * pass before the routine returns. The routine will return 0
 *
 * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
 * delivered to the current task. In this case the remaining time
 * in jiffies will be returned, or 0 if the timer expired in time
 *
 * The current task state is guaranteed to be TASK_RUNNING when this
 * routine returns.
 *
 * Specifying a @timeout value of %MAX_SCHEDULE_TIMEOUT will schedule
 * the CPU away without a bound on the timeout. In this case the return
 * value will be %MAX_SCHEDULE_TIMEOUT.
 *
 * In all cases the return value is guaranteed to be non-negative.
 */
1270
signed long __sched schedule_timeout(signed long timeout)
L
Linus Torvalds 已提交
1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294
{
	struct timer_list timer;
	unsigned long expire;

	switch (timeout)
	{
	case MAX_SCHEDULE_TIMEOUT:
		/*
		 * These two special cases are useful to be comfortable
		 * in the caller. Nothing more. We could take
		 * MAX_SCHEDULE_TIMEOUT from one of the negative value
		 * but I' d like to return a valid offset (>=0) to allow
		 * the caller to do everything it want with the retval.
		 */
		schedule();
		goto out;
	default:
		/*
		 * Another bit of PARANOID. Note that the retval will be
		 * 0 since no piece of kernel is supposed to do a check
		 * for a negative retval of schedule_timeout() (since it
		 * should never happens anyway). You just have the printk()
		 * that will tell you if something is gone wrong and where.
		 */
1295
		if (timeout < 0) {
L
Linus Torvalds 已提交
1296
			printk(KERN_ERR "schedule_timeout: wrong timeout "
1297 1298
				"value %lx\n", timeout);
			dump_stack();
L
Linus Torvalds 已提交
1299 1300 1301 1302 1303 1304 1305
			current->state = TASK_RUNNING;
			goto out;
		}
	}

	expire = timeout + jiffies;

1306
	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
I
Ingo Molnar 已提交
1307
	__mod_timer(&timer, expire, false);
L
Linus Torvalds 已提交
1308 1309 1310
	schedule();
	del_singleshot_timer_sync(&timer);

1311 1312 1313
	/* Remove the timer from the object tracker */
	destroy_timer_on_stack(&timer);

L
Linus Torvalds 已提交
1314 1315 1316 1317 1318 1319 1320
	timeout = expire - jiffies;

 out:
	return timeout < 0 ? 0 : timeout;
}
EXPORT_SYMBOL(schedule_timeout);

1321 1322 1323 1324
/*
 * We can use __set_current_state() here because schedule_timeout() calls
 * schedule() unconditionally.
 */
1325 1326
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
A
Andrew Morton 已提交
1327 1328
	__set_current_state(TASK_INTERRUPTIBLE);
	return schedule_timeout(timeout);
1329 1330 1331
}
EXPORT_SYMBOL(schedule_timeout_interruptible);

M
Matthew Wilcox 已提交
1332 1333 1334 1335 1336 1337 1338
signed long __sched schedule_timeout_killable(signed long timeout)
{
	__set_current_state(TASK_KILLABLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_killable);

1339 1340
signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
A
Andrew Morton 已提交
1341 1342
	__set_current_state(TASK_UNINTERRUPTIBLE);
	return schedule_timeout(timeout);
1343 1344 1345
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);

L
Linus Torvalds 已提交
1346
/* Thread ID - the internal kernel "pid" */
1347
SYSCALL_DEFINE0(gettid)
L
Linus Torvalds 已提交
1348
{
1349
	return task_pid_vnr(current);
L
Linus Torvalds 已提交
1350 1351
}

1352
/**
1353
 * do_sysinfo - fill in sysinfo struct
1354
 * @info: pointer to buffer to fill
1355
 */
1356
int do_sysinfo(struct sysinfo *info)
L
Linus Torvalds 已提交
1357 1358 1359 1360 1361
{
	unsigned long mem_total, sav_total;
	unsigned int mem_unit, bitcount;
	unsigned long seq;

1362
	memset(info, 0, sizeof(struct sysinfo));
L
Linus Torvalds 已提交
1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377

	do {
		struct timespec tp;
		seq = read_seqbegin(&xtime_lock);

		/*
		 * This is annoying.  The below is the same thing
		 * posix_get_clock_monotonic() does, but it wants to
		 * take the lock which we want to cover the loads stuff
		 * too.
		 */

		getnstimeofday(&tp);
		tp.tv_sec += wall_to_monotonic.tv_sec;
		tp.tv_nsec += wall_to_monotonic.tv_nsec;
1378
		monotonic_to_bootbased(&tp);
L
Linus Torvalds 已提交
1379 1380 1381 1382
		if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
			tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
			tp.tv_sec++;
		}
1383
		info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
L
Linus Torvalds 已提交
1384

1385 1386 1387
		info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
		info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
		info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);
L
Linus Torvalds 已提交
1388

1389
		info->procs = nr_threads;
L
Linus Torvalds 已提交
1390 1391
	} while (read_seqretry(&xtime_lock, seq));

1392 1393
	si_meminfo(info);
	si_swapinfo(info);
L
Linus Torvalds 已提交
1394 1395 1396 1397 1398 1399 1400 1401 1402 1403

	/*
	 * If the sum of all the available memory (i.e. ram + swap)
	 * is less than can be stored in a 32 bit unsigned long then
	 * we can be binary compatible with 2.2.x kernels.  If not,
	 * well, in that case 2.2.x was broken anyways...
	 *
	 *  -Erik Andersen <andersee@debian.org>
	 */

1404 1405
	mem_total = info->totalram + info->totalswap;
	if (mem_total < info->totalram || mem_total < info->totalswap)
L
Linus Torvalds 已提交
1406 1407
		goto out;
	bitcount = 0;
1408
	mem_unit = info->mem_unit;
L
Linus Torvalds 已提交
1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419
	while (mem_unit > 1) {
		bitcount++;
		mem_unit >>= 1;
		sav_total = mem_total;
		mem_total <<= 1;
		if (mem_total < sav_total)
			goto out;
	}

	/*
	 * If mem_total did not overflow, multiply all memory values by
1420
	 * info->mem_unit and set it to 1.  This leaves things compatible
L
Linus Torvalds 已提交
1421 1422 1423 1424
	 * with 2.2.x, and also retains compatibility with earlier 2.4.x
	 * kernels...
	 */

1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438
	info->mem_unit = 1;
	info->totalram <<= bitcount;
	info->freeram <<= bitcount;
	info->sharedram <<= bitcount;
	info->bufferram <<= bitcount;
	info->totalswap <<= bitcount;
	info->freeswap <<= bitcount;
	info->totalhigh <<= bitcount;
	info->freehigh <<= bitcount;

out:
	return 0;
}

1439
SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
1440 1441 1442 1443
{
	struct sysinfo val;

	do_sysinfo(&val);
L
Linus Torvalds 已提交
1444 1445 1446 1447 1448 1449 1450

	if (copy_to_user(info, &val, sizeof(struct sysinfo)))
		return -EFAULT;

	return 0;
}

A
Adrian Bunk 已提交
1451
static int __cpuinit init_timers_cpu(int cpu)
L
Linus Torvalds 已提交
1452 1453
{
	int j;
1454
	struct tvec_base *base;
A
Adrian Bunk 已提交
1455
	static char __cpuinitdata tvec_base_done[NR_CPUS];
1456

A
Andrew Morton 已提交
1457
	if (!tvec_base_done[cpu]) {
1458 1459 1460
		static char boot_done;

		if (boot_done) {
A
Andrew Morton 已提交
1461 1462 1463
			/*
			 * The APs use this path later in boot
			 */
1464 1465
			base = kmalloc_node(sizeof(*base),
						GFP_KERNEL | __GFP_ZERO,
1466 1467 1468
						cpu_to_node(cpu));
			if (!base)
				return -ENOMEM;
1469 1470 1471 1472 1473 1474 1475

			/* Make sure that tvec_base is 2 byte aligned */
			if (tbase_get_deferrable(base)) {
				WARN_ON(1);
				kfree(base);
				return -ENOMEM;
			}
A
Andrew Morton 已提交
1476
			per_cpu(tvec_bases, cpu) = base;
1477
		} else {
A
Andrew Morton 已提交
1478 1479 1480 1481 1482 1483
			/*
			 * This is for the boot CPU - we use compile-time
			 * static initialisation because per-cpu memory isn't
			 * ready yet and because the memory allocators are not
			 * initialised either.
			 */
1484
			boot_done = 1;
A
Andrew Morton 已提交
1485
			base = &boot_tvec_bases;
1486
		}
A
Andrew Morton 已提交
1487 1488 1489
		tvec_base_done[cpu] = 1;
	} else {
		base = per_cpu(tvec_bases, cpu);
1490
	}
A
Andrew Morton 已提交
1491

1492
	spin_lock_init(&base->lock);
1493

L
Linus Torvalds 已提交
1494 1495 1496 1497 1498 1499 1500 1501 1502 1503
	for (j = 0; j < TVN_SIZE; j++) {
		INIT_LIST_HEAD(base->tv5.vec + j);
		INIT_LIST_HEAD(base->tv4.vec + j);
		INIT_LIST_HEAD(base->tv3.vec + j);
		INIT_LIST_HEAD(base->tv2.vec + j);
	}
	for (j = 0; j < TVR_SIZE; j++)
		INIT_LIST_HEAD(base->tv1.vec + j);

	base->timer_jiffies = jiffies;
1504
	return 0;
L
Linus Torvalds 已提交
1505 1506 1507
}

#ifdef CONFIG_HOTPLUG_CPU
1508
static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
L
Linus Torvalds 已提交
1509 1510 1511 1512
{
	struct timer_list *timer;

	while (!list_empty(head)) {
1513
		timer = list_first_entry(head, struct timer_list, entry);
1514
		detach_timer(timer, 0);
1515
		timer_set_base(timer, new_base);
L
Linus Torvalds 已提交
1516 1517 1518 1519
		internal_add_timer(new_base, timer);
	}
}

R
Randy Dunlap 已提交
1520
static void __cpuinit migrate_timers(int cpu)
L
Linus Torvalds 已提交
1521
{
1522 1523
	struct tvec_base *old_base;
	struct tvec_base *new_base;
L
Linus Torvalds 已提交
1524 1525 1526
	int i;

	BUG_ON(cpu_online(cpu));
1527 1528
	old_base = per_cpu(tvec_bases, cpu);
	new_base = get_cpu_var(tvec_bases);
1529 1530 1531 1532 1533
	/*
	 * The caller is globally serialized and nobody else
	 * takes two locks at once, deadlock is not possible.
	 */
	spin_lock_irq(&new_base->lock);
1534
	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
1535 1536

	BUG_ON(old_base->running_timer);
L
Linus Torvalds 已提交
1537 1538

	for (i = 0; i < TVR_SIZE; i++)
1539 1540 1541 1542 1543 1544 1545 1546
		migrate_timer_list(new_base, old_base->tv1.vec + i);
	for (i = 0; i < TVN_SIZE; i++) {
		migrate_timer_list(new_base, old_base->tv2.vec + i);
		migrate_timer_list(new_base, old_base->tv3.vec + i);
		migrate_timer_list(new_base, old_base->tv4.vec + i);
		migrate_timer_list(new_base, old_base->tv5.vec + i);
	}

1547
	spin_unlock(&old_base->lock);
1548
	spin_unlock_irq(&new_base->lock);
L
Linus Torvalds 已提交
1549 1550 1551 1552
	put_cpu_var(tvec_bases);
}
#endif /* CONFIG_HOTPLUG_CPU */

1553
static int __cpuinit timer_cpu_notify(struct notifier_block *self,
L
Linus Torvalds 已提交
1554 1555 1556 1557 1558
				unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	switch(action) {
	case CPU_UP_PREPARE:
1559
	case CPU_UP_PREPARE_FROZEN:
1560 1561
		if (init_timers_cpu(cpu) < 0)
			return NOTIFY_BAD;
L
Linus Torvalds 已提交
1562 1563 1564
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
1565
	case CPU_DEAD_FROZEN:
L
Linus Torvalds 已提交
1566 1567 1568 1569 1570 1571 1572 1573 1574
		migrate_timers(cpu);
		break;
#endif
	default:
		break;
	}
	return NOTIFY_OK;
}

1575
static struct notifier_block __cpuinitdata timers_nb = {
L
Linus Torvalds 已提交
1576 1577 1578 1579 1580 1581
	.notifier_call	= timer_cpu_notify,
};


void __init init_timers(void)
{
1582
	int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
L
Linus Torvalds 已提交
1583
				(void *)(long)smp_processor_id());
1584

1585 1586
	init_timer_stats();

1587
	BUG_ON(err == NOTIFY_BAD);
L
Linus Torvalds 已提交
1588
	register_cpu_notifier(&timers_nb);
1589
	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
L
Linus Torvalds 已提交
1590 1591 1592 1593 1594 1595 1596 1597 1598 1599
}

/**
 * msleep - sleep safely even with waitqueue interruptions
 * @msecs: Time in milliseconds to sleep for
 */
void msleep(unsigned int msecs)
{
	unsigned long timeout = msecs_to_jiffies(msecs) + 1;

1600 1601
	while (timeout)
		timeout = schedule_timeout_uninterruptible(timeout);
L
Linus Torvalds 已提交
1602 1603 1604 1605 1606
}

EXPORT_SYMBOL(msleep);

/**
1607
 * msleep_interruptible - sleep waiting for signals
L
Linus Torvalds 已提交
1608 1609 1610 1611 1612 1613
 * @msecs: Time in milliseconds to sleep for
 */
unsigned long msleep_interruptible(unsigned int msecs)
{
	unsigned long timeout = msecs_to_jiffies(msecs) + 1;

1614 1615
	while (timeout && !signal_pending(current))
		timeout = schedule_timeout_interruptible(timeout);
L
Linus Torvalds 已提交
1616 1617 1618 1619
	return jiffies_to_msecs(timeout);
}

EXPORT_SYMBOL(msleep_interruptible);