timer.c 44.5 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>
40
#include <linux/perf_event.h>
41
#include <linux/sched.h>
L
Linus Torvalds 已提交
42 43 44 45 46 47 48

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

49 50 51
#define CREATE_TRACE_POINTS
#include <trace/events/timer.h>

T
Thomas Gleixner 已提交
52 53 54 55
u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;

EXPORT_SYMBOL(jiffies_64);

L
Linus Torvalds 已提交
56 57 58 59 60 61 62 63 64 65
/*
 * 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)

66
struct tvec {
L
Linus Torvalds 已提交
67
	struct list_head vec[TVN_SIZE];
68
};
L
Linus Torvalds 已提交
69

70
struct tvec_root {
L
Linus Torvalds 已提交
71
	struct list_head vec[TVR_SIZE];
72
};
L
Linus Torvalds 已提交
73

74
struct tvec_base {
75 76
	spinlock_t lock;
	struct timer_list *running_timer;
L
Linus Torvalds 已提交
77
	unsigned long timer_jiffies;
78
	unsigned long next_timer;
79 80 81 82 83
	struct tvec_root tv1;
	struct tvec tv2;
	struct tvec tv3;
	struct tvec tv4;
	struct tvec tv5;
84
} ____cacheline_aligned;
L
Linus Torvalds 已提交
85

86
struct tvec_base boot_tvec_bases;
87
EXPORT_SYMBOL(boot_tvec_bases);
88
static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases;
L
Linus Torvalds 已提交
89

90
/*
91
 * Note that all tvec_bases are 2 byte aligned and lower bit of
92 93 94 95 96 97
 * 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 */
98
static inline unsigned int tbase_get_deferrable(struct tvec_base *base)
99
{
100
	return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG);
101 102
}

103
static inline struct tvec_base *tbase_get_base(struct tvec_base *base)
104
{
105
	return ((struct tvec_base *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG));
106 107 108 109
}

static inline void timer_set_deferrable(struct timer_list *timer)
{
110
	timer->base = ((struct tvec_base *)((unsigned long)(timer->base) |
111
				       TBASE_DEFERRABLE_FLAG));
112 113 114
}

static inline void
115
timer_set_base(struct timer_list *timer, struct tvec_base *new_base)
116
{
117
	timer->base = (struct tvec_base *)((unsigned long)(new_base) |
118
				      tbase_get_deferrable(timer->base));
119 120
}

121 122
static unsigned long round_jiffies_common(unsigned long j, int cpu,
		bool force_up)
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143
{
	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.
144
	 * But never round down if @force_up is set.
145
	 */
146
	if (rem < HZ/4 && !force_up) /* round down */
147 148 149 150 151 152 153 154 155 156 157
		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;
}
158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182

/**
 * __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);
}
183 184 185 186 187 188 189
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
 *
190
 * __round_jiffies_relative() rounds a time delta  in the future (in jiffies)
191 192 193 194 195 196 197 198 199 200 201 202
 * 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.
 *
203
 * The return value is the rounded version of the @j parameter.
204 205 206
 */
unsigned long __round_jiffies_relative(unsigned long j, int cpu)
{
207 208 209 210
	unsigned long j0 = jiffies;

	/* Use j0 because jiffies might change while we run */
	return round_jiffies_common(j + j0, cpu, false) - j0;
211 212 213 214 215 216 217
}
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
 *
218
 * round_jiffies() rounds an absolute time in the future (in jiffies)
219 220 221 222 223 224 225 226
 * 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.
 *
227
 * The return value is the rounded version of the @j parameter.
228 229 230
 */
unsigned long round_jiffies(unsigned long j)
{
231
	return round_jiffies_common(j, raw_smp_processor_id(), false);
232 233 234 235 236 237 238
}
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
 *
239
 * round_jiffies_relative() rounds a time delta  in the future (in jiffies)
240 241 242 243 244 245 246 247
 * 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.
 *
248
 * The return value is the rounded version of the @j parameter.
249 250 251 252 253 254 255
 */
unsigned long round_jiffies_relative(unsigned long j)
{
	return __round_jiffies_relative(j, raw_smp_processor_id());
}
EXPORT_SYMBOL_GPL(round_jiffies_relative);

256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320
/**
 * __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);

321

322
static inline void set_running_timer(struct tvec_base *base,
L
Linus Torvalds 已提交
323 324 325
					struct timer_list *timer)
{
#ifdef CONFIG_SMP
326
	base->running_timer = timer;
L
Linus Torvalds 已提交
327 328 329
#endif
}

330
static void internal_add_timer(struct tvec_base *base, struct timer_list *timer)
L
Linus Torvalds 已提交
331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371
{
	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);
}

372 373 374 375 376 377 378 379 380 381
#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;
}
382 383 384 385 386

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

387 388
	if (likely(!timer->start_site))
		return;
389 390 391 392 393 394 395 396 397
	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) {}
398 399
#endif

400 401 402 403 404 405 406
#ifdef CONFIG_DEBUG_OBJECTS_TIMERS

static struct debug_obj_descr timer_debug_descr;

/*
 * fixup_init is called when:
 * - an active object is initialized
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
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);
}

502 503 504
static void __init_timer(struct timer_list *timer,
			 const char *name,
			 struct lock_class_key *key);
505

506 507 508
void init_timer_on_stack_key(struct timer_list *timer,
			     const char *name,
			     struct lock_class_key *key)
509 510
{
	debug_object_init_on_stack(timer, &timer_debug_descr);
511
	__init_timer(timer, name, key);
512
}
513
EXPORT_SYMBOL_GPL(init_timer_on_stack_key);
514 515 516 517 518 519 520 521 522 523 524 525 526

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

527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545
static inline void debug_init(struct timer_list *timer)
{
	debug_timer_init(timer);
	trace_timer_init(timer);
}

static inline void
debug_activate(struct timer_list *timer, unsigned long expires)
{
	debug_timer_activate(timer);
	trace_timer_start(timer, expires);
}

static inline void debug_deactivate(struct timer_list *timer)
{
	debug_timer_deactivate(timer);
	trace_timer_cancel(timer);
}

546 547 548
static void __init_timer(struct timer_list *timer,
			 const char *name,
			 struct lock_class_key *key)
549 550
{
	timer->entry.next = NULL;
551
	timer->base = __raw_get_cpu_var(tvec_bases);
552 553 554 555 556
#ifdef CONFIG_TIMER_STATS
	timer->start_site = NULL;
	timer->start_pid = -1;
	memset(timer->start_comm, 0, TASK_COMM_LEN);
#endif
557
	lockdep_init_map(&timer->lockdep_map, name, key, 0);
558
}
559 560

/**
R
Randy Dunlap 已提交
561
 * init_timer_key - initialize a timer
562
 * @timer: the timer to be initialized
R
Randy Dunlap 已提交
563 564 565
 * @name: name of the timer
 * @key: lockdep class key of the fake lock used for tracking timer
 *       sync lock dependencies
566
 *
R
Randy Dunlap 已提交
567
 * init_timer_key() must be done to a timer prior calling *any* of the
568 569
 * other timer functions.
 */
570 571 572
void init_timer_key(struct timer_list *timer,
		    const char *name,
		    struct lock_class_key *key)
573
{
574
	debug_init(timer);
575
	__init_timer(timer, name, key);
576
}
577
EXPORT_SYMBOL(init_timer_key);
578

579 580 581
void init_timer_deferrable_key(struct timer_list *timer,
			       const char *name,
			       struct lock_class_key *key)
582
{
583
	init_timer_key(timer, name, key);
584 585
	timer_set_deferrable(timer);
}
586
EXPORT_SYMBOL(init_timer_deferrable_key);
587

588
static inline void detach_timer(struct timer_list *timer,
589
				int clear_pending)
590 591 592
{
	struct list_head *entry = &timer->entry;

593
	debug_deactivate(timer);
594

595 596 597 598 599 600 601
	__list_del(entry->prev, entry->next);
	if (clear_pending)
		entry->next = NULL;
	entry->prev = LIST_POISON2;
}

/*
602
 * We are using hashed locking: holding per_cpu(tvec_bases).lock
603 604 605 606 607 608 609 610 611 612
 * 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.
 */
613
static struct tvec_base *lock_timer_base(struct timer_list *timer,
614
					unsigned long *flags)
615
	__acquires(timer->base->lock)
616
{
617
	struct tvec_base *base;
618 619

	for (;;) {
620
		struct tvec_base *prelock_base = timer->base;
621
		base = tbase_get_base(prelock_base);
622 623
		if (likely(base != NULL)) {
			spin_lock_irqsave(&base->lock, *flags);
624
			if (likely(prelock_base == timer->base))
625 626 627 628 629 630 631 632
				return base;
			/* The timer has migrated to another CPU */
			spin_unlock_irqrestore(&base->lock, *flags);
		}
		cpu_relax();
	}
}

I
Ingo Molnar 已提交
633
static inline int
634 635
__mod_timer(struct timer_list *timer, unsigned long expires,
						bool pending_only, int pinned)
L
Linus Torvalds 已提交
636
{
637
	struct tvec_base *base, *new_base;
L
Linus Torvalds 已提交
638
	unsigned long flags;
639
	int ret = 0 , cpu;
L
Linus Torvalds 已提交
640

641
	timer_stats_timer_set_start_info(timer);
L
Linus Torvalds 已提交
642 643
	BUG_ON(!timer->function);

644 645 646 647
	base = lock_timer_base(timer, &flags);

	if (timer_pending(timer)) {
		detach_timer(timer, 0);
648 649 650
		if (timer->expires == base->next_timer &&
		    !tbase_get_deferrable(timer->base))
			base->next_timer = base->timer_jiffies;
651
		ret = 1;
I
Ingo Molnar 已提交
652 653 654
	} else {
		if (pending_only)
			goto out_unlock;
655 656
	}

657
	debug_activate(timer, expires);
658

659 660 661 662 663 664 665 666 667 668 669 670
	cpu = smp_processor_id();

#if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
	if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu)) {
		int preferred_cpu = get_nohz_load_balancer();

		if (preferred_cpu >= 0)
			cpu = preferred_cpu;
	}
#endif
	new_base = per_cpu(tvec_bases, cpu);

671
	if (base != new_base) {
L
Linus Torvalds 已提交
672
		/*
673 674 675 676 677
		 * 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
678
		 */
679
		if (likely(base->running_timer != timer)) {
680
			/* See the comment in lock_timer_base() */
681
			timer_set_base(timer, NULL);
682
			spin_unlock(&base->lock);
683 684
			base = new_base;
			spin_lock(&base->lock);
685
			timer_set_base(timer, base);
L
Linus Torvalds 已提交
686 687 688 689
		}
	}

	timer->expires = expires;
690 691 692
	if (time_before(timer->expires, base->next_timer) &&
	    !tbase_get_deferrable(timer->base))
		base->next_timer = timer->expires;
693
	internal_add_timer(base, timer);
I
Ingo Molnar 已提交
694 695

out_unlock:
696
	spin_unlock_irqrestore(&base->lock, flags);
L
Linus Torvalds 已提交
697 698 699 700

	return ret;
}

701
/**
I
Ingo Molnar 已提交
702 703 704
 * 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
705
 *
I
Ingo Molnar 已提交
706 707 708 709
 * 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
710
 */
I
Ingo Molnar 已提交
711
int mod_timer_pending(struct timer_list *timer, unsigned long expires)
L
Linus Torvalds 已提交
712
{
713
	return __mod_timer(timer, expires, true, TIMER_NOT_PINNED);
L
Linus Torvalds 已提交
714
}
I
Ingo Molnar 已提交
715
EXPORT_SYMBOL(mod_timer_pending);
L
Linus Torvalds 已提交
716

717
/**
L
Linus Torvalds 已提交
718 719
 * mod_timer - modify a timer's timeout
 * @timer: the timer to be modified
720
 * @expires: new timeout in jiffies
L
Linus Torvalds 已提交
721
 *
722
 * mod_timer() is a more efficient way to update the expire field of an
L
Linus Torvalds 已提交
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743
 * 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:
	 */
744
	if (timer_pending(timer) && timer->expires == expires)
L
Linus Torvalds 已提交
745 746
		return 1;

747
	return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
L
Linus Torvalds 已提交
748 749 750
}
EXPORT_SYMBOL(mod_timer);

751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772
/**
 * mod_timer_pinned - modify a timer's timeout
 * @timer: the timer to be modified
 * @expires: new timeout in jiffies
 *
 * mod_timer_pinned() is a way to update the expire field of an
 * active timer (if the timer is inactive it will be activated)
 * and not allow the timer to be migrated to a different CPU.
 *
 * mod_timer_pinned(timer, expires) is equivalent to:
 *
 *     del_timer(timer); timer->expires = expires; add_timer(timer);
 */
int mod_timer_pinned(struct timer_list *timer, unsigned long expires)
{
	if (timer->expires == expires && timer_pending(timer))
		return 1;

	return __mod_timer(timer, expires, false, TIMER_PINNED);
}
EXPORT_SYMBOL(mod_timer_pinned);

I
Ingo Molnar 已提交
773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809
/**
 * 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);
810
	debug_activate(timer, timer->expires);
811 812 813
	if (time_before(timer->expires, base->next_timer) &&
	    !tbase_get_deferrable(timer->base))
		base->next_timer = timer->expires;
I
Ingo Molnar 已提交
814 815 816 817 818 819 820 821 822 823 824 825
	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);
}
A
Andi Kleen 已提交
826
EXPORT_SYMBOL_GPL(add_timer_on);
I
Ingo Molnar 已提交
827

828
/**
L
Linus Torvalds 已提交
829 830 831 832 833 834 835 836 837 838 839 840
 * 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)
{
841
	struct tvec_base *base;
L
Linus Torvalds 已提交
842
	unsigned long flags;
843
	int ret = 0;
L
Linus Torvalds 已提交
844

845
	timer_stats_timer_clear_start_info(timer);
846 847 848 849
	if (timer_pending(timer)) {
		base = lock_timer_base(timer, &flags);
		if (timer_pending(timer)) {
			detach_timer(timer, 1);
850 851 852
			if (timer->expires == base->next_timer &&
			    !tbase_get_deferrable(timer->base))
				base->next_timer = base->timer_jiffies;
853 854
			ret = 1;
		}
L
Linus Torvalds 已提交
855 856 857
		spin_unlock_irqrestore(&base->lock, flags);
	}

858
	return ret;
L
Linus Torvalds 已提交
859 860 861 862
}
EXPORT_SYMBOL(del_timer);

#ifdef CONFIG_SMP
863 864 865 866
/**
 * try_to_del_timer_sync - Try to deactivate a timer
 * @timer: timer do del
 *
867 868 869 870 871 872 873
 * 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)
{
874
	struct tvec_base *base;
875 876 877 878 879 880 881 882
	unsigned long flags;
	int ret = -1;

	base = lock_timer_base(timer, &flags);

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

883
	timer_stats_timer_clear_start_info(timer);
884 885 886
	ret = 0;
	if (timer_pending(timer)) {
		detach_timer(timer, 1);
887 888 889
		if (timer->expires == base->next_timer &&
		    !tbase_get_deferrable(timer->base))
			base->next_timer = base->timer_jiffies;
890 891 892 893 894 895 896
		ret = 1;
	}
out:
	spin_unlock_irqrestore(&base->lock, flags);

	return ret;
}
897 898
EXPORT_SYMBOL(try_to_del_timer_sync);

899
/**
L
Linus Torvalds 已提交
900 901 902 903 904 905 906
 * 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.
 *
907
 * Synchronization rules: Callers must prevent restarting of the timer,
L
Linus Torvalds 已提交
908 909
 * otherwise this function is meaningless. It must not be called from
 * interrupt contexts. The caller must not hold locks which would prevent
910 911 912
 * 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
913 914 915 916 917
 *
 * The function returns whether it has deactivated a pending timer or not.
 */
int del_timer_sync(struct timer_list *timer)
{
918 919 920 921 922 923 924 925 926
#ifdef CONFIG_LOCKDEP
	unsigned long flags;

	local_irq_save(flags);
	lock_map_acquire(&timer->lockdep_map);
	lock_map_release(&timer->lockdep_map);
	local_irq_restore(flags);
#endif

927 928 929 930
	for (;;) {
		int ret = try_to_del_timer_sync(timer);
		if (ret >= 0)
			return ret;
931
		cpu_relax();
932
	}
L
Linus Torvalds 已提交
933
}
934
EXPORT_SYMBOL(del_timer_sync);
L
Linus Torvalds 已提交
935 936
#endif

937
static int cascade(struct tvec_base *base, struct tvec *tv, int index)
L
Linus Torvalds 已提交
938 939
{
	/* cascade all the timers from tv up one level */
940 941 942 943
	struct timer_list *timer, *tmp;
	struct list_head tv_list;

	list_replace_init(tv->vec + index, &tv_list);
L
Linus Torvalds 已提交
944 945

	/*
946 947
	 * We are removing _all_ timers from the list, so we
	 * don't have to detach them individually.
L
Linus Torvalds 已提交
948
	 */
949
	list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
950
		BUG_ON(tbase_get_base(timer->base) != base);
951
		internal_add_timer(base, timer);
L
Linus Torvalds 已提交
952 953 954 955 956
	}

	return index;
}

957 958 959
#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)

/**
L
Linus Torvalds 已提交
960 961 962 963 964 965
 * __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.
 */
966
static inline void __run_timers(struct tvec_base *base)
L
Linus Torvalds 已提交
967 968 969
{
	struct timer_list *timer;

970
	spin_lock_irq(&base->lock);
L
Linus Torvalds 已提交
971
	while (time_after_eq(jiffies, base->timer_jiffies)) {
972
		struct list_head work_list;
L
Linus Torvalds 已提交
973
		struct list_head *head = &work_list;
974
		int index = base->timer_jiffies & TVR_MASK;
975

L
Linus Torvalds 已提交
976 977 978 979 980 981 982 983
		/*
		 * 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));
984 985
		++base->timer_jiffies;
		list_replace_init(base->tv1.vec + index, &work_list);
986
		while (!list_empty(head)) {
L
Linus Torvalds 已提交
987 988 989
			void (*fn)(unsigned long);
			unsigned long data;

990
			timer = list_first_entry(head, struct timer_list,entry);
991 992
			fn = timer->function;
			data = timer->data;
L
Linus Torvalds 已提交
993

994 995
			timer_stats_account_timer(timer);

L
Linus Torvalds 已提交
996
			set_running_timer(base, timer);
997
			detach_timer(timer, 1);
998

999
			spin_unlock_irq(&base->lock);
L
Linus Torvalds 已提交
1000
			{
1001
				int preempt_count = preempt_count();
1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023

#ifdef CONFIG_LOCKDEP
				/*
				 * It is permissible to free the timer from
				 * inside the function that is called from
				 * it, this we need to take into account for
				 * lockdep too. To avoid bogus "held lock
				 * freed" warnings as well as problems when
				 * looking into timer->lockdep_map, make a
				 * copy and use that here.
				 */
				struct lockdep_map lockdep_map =
					timer->lockdep_map;
#endif
				/*
				 * Couple the lock chain with the lock chain at
				 * del_timer_sync() by acquiring the lock_map
				 * around the fn() call here and in
				 * del_timer_sync().
				 */
				lock_map_acquire(&lockdep_map);

1024
				trace_timer_expire_entry(timer);
L
Linus Torvalds 已提交
1025
				fn(data);
1026
				trace_timer_expire_exit(timer);
1027 1028 1029

				lock_map_release(&lockdep_map);

L
Linus Torvalds 已提交
1030
				if (preempt_count != preempt_count()) {
P
Pavel Machek 已提交
1031
					printk(KERN_ERR "huh, entered %p "
1032 1033 1034 1035
					       "with preempt_count %08x, exited"
					       " with %08x?\n",
					       fn, preempt_count,
					       preempt_count());
L
Linus Torvalds 已提交
1036 1037 1038
					BUG();
				}
			}
1039
			spin_lock_irq(&base->lock);
L
Linus Torvalds 已提交
1040 1041 1042
		}
	}
	set_running_timer(base, NULL);
1043
	spin_unlock_irq(&base->lock);
L
Linus Torvalds 已提交
1044 1045
}

1046
#ifdef CONFIG_NO_HZ
L
Linus Torvalds 已提交
1047 1048
/*
 * Find out when the next timer event is due to happen. This
R
Randy Dunlap 已提交
1049 1050
 * is used on S/390 to stop all activity when a CPU is idle.
 * This function needs to be called with interrupts disabled.
L
Linus Torvalds 已提交
1051
 */
1052
static unsigned long __next_timer_interrupt(struct tvec_base *base)
L
Linus Torvalds 已提交
1053
{
1054
	unsigned long timer_jiffies = base->timer_jiffies;
1055
	unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA;
1056
	int index, slot, array, found = 0;
L
Linus Torvalds 已提交
1057
	struct timer_list *nte;
1058
	struct tvec *varray[4];
L
Linus Torvalds 已提交
1059 1060

	/* Look for timer events in tv1. */
1061
	index = slot = timer_jiffies & TVR_MASK;
L
Linus Torvalds 已提交
1062
	do {
1063
		list_for_each_entry(nte, base->tv1.vec + slot, entry) {
1064 1065
			if (tbase_get_deferrable(nte->base))
				continue;
1066

1067
			found = 1;
L
Linus Torvalds 已提交
1068
			expires = nte->expires;
1069 1070 1071 1072
			/* Look at the cascade bucket(s)? */
			if (!index || slot < index)
				goto cascade;
			return expires;
L
Linus Torvalds 已提交
1073
		}
1074 1075 1076 1077 1078 1079 1080 1081
		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
1082 1083 1084 1085 1086 1087

	/* Check tv2-tv5. */
	varray[0] = &base->tv2;
	varray[1] = &base->tv3;
	varray[2] = &base->tv4;
	varray[3] = &base->tv5;
1088 1089

	for (array = 0; array < 4; array++) {
1090
		struct tvec *varp = varray[array];
1091 1092

		index = slot = timer_jiffies & TVN_MASK;
L
Linus Torvalds 已提交
1093
		do {
1094
			list_for_each_entry(nte, varp->vec + slot, entry) {
1095 1096 1097
				if (tbase_get_deferrable(nte->base))
					continue;

1098
				found = 1;
L
Linus Torvalds 已提交
1099 1100
				if (time_before(nte->expires, expires))
					expires = nte->expires;
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117
			}
			/*
			 * 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
1118
	}
1119 1120
	return expires;
}
1121

1122 1123 1124 1125 1126 1127 1128 1129 1130
/*
 * 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;
1131
	unsigned long delta;
1132 1133 1134

	if (hr_delta.tv64 == KTIME_MAX)
		return expires;
1135

1136 1137 1138 1139 1140
	/*
	 * Expired timer available, let it expire in the next tick
	 */
	if (hr_delta.tv64 <= 0)
		return now + 1;
1141

1142
	tsdelta = ktime_to_timespec(hr_delta);
1143
	delta = timespec_to_jiffies(&tsdelta);
1144 1145 1146 1147 1148 1149 1150 1151

	/*
	 * 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;

1152 1153 1154 1155 1156 1157 1158 1159 1160
	/*
	 * 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;
1161 1162
	if (time_before(now, expires))
		return now;
L
Linus Torvalds 已提交
1163 1164
	return expires;
}
1165 1166

/**
1167
 * get_next_timer_interrupt - return the jiffy of the next pending timer
1168
 * @now: current time (in jiffies)
1169
 */
1170
unsigned long get_next_timer_interrupt(unsigned long now)
1171
{
1172
	struct tvec_base *base = __get_cpu_var(tvec_bases);
1173
	unsigned long expires;
1174 1175

	spin_lock(&base->lock);
1176 1177 1178
	if (time_before_eq(base->next_timer, base->timer_jiffies))
		base->next_timer = __next_timer_interrupt(base);
	expires = base->next_timer;
1179 1180 1181 1182 1183 1184 1185
	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
1186 1187 1188
#endif

/*
D
Daniel Walker 已提交
1189
 * Called from the timer interrupt handler to charge one tick to the current
L
Linus Torvalds 已提交
1190 1191 1192 1193 1194 1195 1196 1197
 * 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. */
1198
	account_process_tick(p, user_tick);
L
Linus Torvalds 已提交
1199
	run_local_timers();
1200
	rcu_check_callbacks(cpu, user_tick);
P
Peter Zijlstra 已提交
1201
	printk_tick();
1202
	perf_event_do_pending();
L
Linus Torvalds 已提交
1203
	scheduler_tick();
1204
	run_posix_cpu_timers(p);
L
Linus Torvalds 已提交
1205 1206 1207 1208 1209 1210 1211
}

/*
 * This function runs timers and the timer-tq in bottom half context.
 */
static void run_timer_softirq(struct softirq_action *h)
{
1212
	struct tvec_base *base = __get_cpu_var(tvec_bases);
L
Linus Torvalds 已提交
1213

1214
	hrtimer_run_pending();
1215

L
Linus Torvalds 已提交
1216 1217 1218 1219 1220 1221 1222 1223 1224
	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)
{
1225
	hrtimer_run_queues();
L
Linus Torvalds 已提交
1226
	raise_softirq(TIMER_SOFTIRQ);
1227
	softlockup_tick();
L
Linus Torvalds 已提交
1228 1229 1230 1231 1232 1233 1234 1235
}

/*
 * 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...
 */

1236
void do_timer(unsigned long ticks)
L
Linus Torvalds 已提交
1237
{
1238
	jiffies_64 += ticks;
1239 1240
	update_wall_time();
	calc_global_load();
L
Linus Torvalds 已提交
1241 1242 1243 1244 1245 1246 1247 1248
}

#ifdef __ARCH_WANT_SYS_ALARM

/*
 * For backwards compatibility?  This can be done in libc so Alpha
 * and all newer ports shouldn't need it.
 */
1249
SYSCALL_DEFINE1(alarm, unsigned int, seconds)
L
Linus Torvalds 已提交
1250
{
1251
	return alarm_setitimer(seconds);
L
Linus Torvalds 已提交
1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271
}

#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.
 */
1272
SYSCALL_DEFINE0(getpid)
L
Linus Torvalds 已提交
1273
{
1274
	return task_tgid_vnr(current);
L
Linus Torvalds 已提交
1275 1276 1277
}

/*
1278 1279 1280 1281
 * 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
1282
 */
1283
SYSCALL_DEFINE0(getppid)
L
Linus Torvalds 已提交
1284 1285 1286
{
	int pid;

1287
	rcu_read_lock();
1288
	pid = task_tgid_vnr(current->real_parent);
1289
	rcu_read_unlock();
L
Linus Torvalds 已提交
1290 1291 1292 1293

	return pid;
}

1294
SYSCALL_DEFINE0(getuid)
L
Linus Torvalds 已提交
1295 1296
{
	/* Only we change this so SMP safe */
1297
	return current_uid();
L
Linus Torvalds 已提交
1298 1299
}

1300
SYSCALL_DEFINE0(geteuid)
L
Linus Torvalds 已提交
1301 1302
{
	/* Only we change this so SMP safe */
1303
	return current_euid();
L
Linus Torvalds 已提交
1304 1305
}

1306
SYSCALL_DEFINE0(getgid)
L
Linus Torvalds 已提交
1307 1308
{
	/* Only we change this so SMP safe */
1309
	return current_gid();
L
Linus Torvalds 已提交
1310 1311
}

1312
SYSCALL_DEFINE0(getegid)
L
Linus Torvalds 已提交
1313 1314
{
	/* Only we change this so SMP safe */
1315
	return  current_egid();
L
Linus Torvalds 已提交
1316 1317 1318 1319 1320 1321
}

#endif

static void process_timeout(unsigned long __data)
{
1322
	wake_up_process((struct task_struct *)__data);
L
Linus Torvalds 已提交
1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350
}

/**
 * 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.
 */
1351
signed long __sched schedule_timeout(signed long timeout)
L
Linus Torvalds 已提交
1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375
{
	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.
		 */
1376
		if (timeout < 0) {
L
Linus Torvalds 已提交
1377
			printk(KERN_ERR "schedule_timeout: wrong timeout "
1378 1379
				"value %lx\n", timeout);
			dump_stack();
L
Linus Torvalds 已提交
1380 1381 1382 1383 1384 1385 1386
			current->state = TASK_RUNNING;
			goto out;
		}
	}

	expire = timeout + jiffies;

1387
	setup_timer_on_stack(&timer, process_timeout, (unsigned long)current);
1388
	__mod_timer(&timer, expire, false, TIMER_NOT_PINNED);
L
Linus Torvalds 已提交
1389 1390 1391
	schedule();
	del_singleshot_timer_sync(&timer);

1392 1393 1394
	/* Remove the timer from the object tracker */
	destroy_timer_on_stack(&timer);

L
Linus Torvalds 已提交
1395 1396 1397 1398 1399 1400 1401
	timeout = expire - jiffies;

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

1402 1403 1404 1405
/*
 * We can use __set_current_state() here because schedule_timeout() calls
 * schedule() unconditionally.
 */
1406 1407
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
A
Andrew Morton 已提交
1408 1409
	__set_current_state(TASK_INTERRUPTIBLE);
	return schedule_timeout(timeout);
1410 1411 1412
}
EXPORT_SYMBOL(schedule_timeout_interruptible);

M
Matthew Wilcox 已提交
1413 1414 1415 1416 1417 1418 1419
signed long __sched schedule_timeout_killable(signed long timeout)
{
	__set_current_state(TASK_KILLABLE);
	return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_killable);

1420 1421
signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
A
Andrew Morton 已提交
1422 1423
	__set_current_state(TASK_UNINTERRUPTIBLE);
	return schedule_timeout(timeout);
1424 1425 1426
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);

L
Linus Torvalds 已提交
1427
/* Thread ID - the internal kernel "pid" */
1428
SYSCALL_DEFINE0(gettid)
L
Linus Torvalds 已提交
1429
{
1430
	return task_pid_vnr(current);
L
Linus Torvalds 已提交
1431 1432
}

1433
/**
1434
 * do_sysinfo - fill in sysinfo struct
1435
 * @info: pointer to buffer to fill
1436
 */
1437
int do_sysinfo(struct sysinfo *info)
L
Linus Torvalds 已提交
1438 1439 1440
{
	unsigned long mem_total, sav_total;
	unsigned int mem_unit, bitcount;
1441
	struct timespec tp;
L
Linus Torvalds 已提交
1442

1443
	memset(info, 0, sizeof(struct sysinfo));
L
Linus Torvalds 已提交
1444

1445 1446 1447
	ktime_get_ts(&tp);
	monotonic_to_bootbased(&tp);
	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
L
Linus Torvalds 已提交
1448

1449
	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
L
Linus Torvalds 已提交
1450

1451
	info->procs = nr_threads;
L
Linus Torvalds 已提交
1452

1453 1454
	si_meminfo(info);
	si_swapinfo(info);
L
Linus Torvalds 已提交
1455 1456 1457 1458 1459 1460 1461 1462 1463 1464

	/*
	 * 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>
	 */

1465 1466
	mem_total = info->totalram + info->totalswap;
	if (mem_total < info->totalram || mem_total < info->totalswap)
L
Linus Torvalds 已提交
1467 1468
		goto out;
	bitcount = 0;
1469
	mem_unit = info->mem_unit;
L
Linus Torvalds 已提交
1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480
	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
1481
	 * info->mem_unit and set it to 1.  This leaves things compatible
L
Linus Torvalds 已提交
1482 1483 1484 1485
	 * with 2.2.x, and also retains compatibility with earlier 2.4.x
	 * kernels...
	 */

1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499
	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;
}

1500
SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info)
1501 1502 1503 1504
{
	struct sysinfo val;

	do_sysinfo(&val);
L
Linus Torvalds 已提交
1505 1506 1507 1508 1509 1510 1511

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

	return 0;
}

A
Adrian Bunk 已提交
1512
static int __cpuinit init_timers_cpu(int cpu)
L
Linus Torvalds 已提交
1513 1514
{
	int j;
1515
	struct tvec_base *base;
A
Adrian Bunk 已提交
1516
	static char __cpuinitdata tvec_base_done[NR_CPUS];
1517

A
Andrew Morton 已提交
1518
	if (!tvec_base_done[cpu]) {
1519 1520 1521
		static char boot_done;

		if (boot_done) {
A
Andrew Morton 已提交
1522 1523 1524
			/*
			 * The APs use this path later in boot
			 */
1525 1526
			base = kmalloc_node(sizeof(*base),
						GFP_KERNEL | __GFP_ZERO,
1527 1528 1529
						cpu_to_node(cpu));
			if (!base)
				return -ENOMEM;
1530 1531 1532 1533 1534 1535 1536

			/* 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
1537
			per_cpu(tvec_bases, cpu) = base;
1538
		} else {
A
Andrew Morton 已提交
1539 1540 1541 1542 1543 1544
			/*
			 * 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.
			 */
1545
			boot_done = 1;
A
Andrew Morton 已提交
1546
			base = &boot_tvec_bases;
1547
		}
A
Andrew Morton 已提交
1548 1549 1550
		tvec_base_done[cpu] = 1;
	} else {
		base = per_cpu(tvec_bases, cpu);
1551
	}
A
Andrew Morton 已提交
1552

1553
	spin_lock_init(&base->lock);
1554

L
Linus Torvalds 已提交
1555 1556 1557 1558 1559 1560 1561 1562 1563 1564
	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;
1565
	base->next_timer = base->timer_jiffies;
1566
	return 0;
L
Linus Torvalds 已提交
1567 1568 1569
}

#ifdef CONFIG_HOTPLUG_CPU
1570
static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head)
L
Linus Torvalds 已提交
1571 1572 1573 1574
{
	struct timer_list *timer;

	while (!list_empty(head)) {
1575
		timer = list_first_entry(head, struct timer_list, entry);
1576
		detach_timer(timer, 0);
1577
		timer_set_base(timer, new_base);
1578 1579 1580
		if (time_before(timer->expires, new_base->next_timer) &&
		    !tbase_get_deferrable(timer->base))
			new_base->next_timer = timer->expires;
L
Linus Torvalds 已提交
1581 1582 1583 1584
		internal_add_timer(new_base, timer);
	}
}

R
Randy Dunlap 已提交
1585
static void __cpuinit migrate_timers(int cpu)
L
Linus Torvalds 已提交
1586
{
1587 1588
	struct tvec_base *old_base;
	struct tvec_base *new_base;
L
Linus Torvalds 已提交
1589 1590 1591
	int i;

	BUG_ON(cpu_online(cpu));
1592 1593
	old_base = per_cpu(tvec_bases, cpu);
	new_base = get_cpu_var(tvec_bases);
1594 1595 1596 1597 1598
	/*
	 * The caller is globally serialized and nobody else
	 * takes two locks at once, deadlock is not possible.
	 */
	spin_lock_irq(&new_base->lock);
1599
	spin_lock_nested(&old_base->lock, SINGLE_DEPTH_NESTING);
1600 1601

	BUG_ON(old_base->running_timer);
L
Linus Torvalds 已提交
1602 1603

	for (i = 0; i < TVR_SIZE; i++)
1604 1605 1606 1607 1608 1609 1610 1611
		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);
	}

1612
	spin_unlock(&old_base->lock);
1613
	spin_unlock_irq(&new_base->lock);
L
Linus Torvalds 已提交
1614 1615 1616 1617
	put_cpu_var(tvec_bases);
}
#endif /* CONFIG_HOTPLUG_CPU */

1618
static int __cpuinit timer_cpu_notify(struct notifier_block *self,
L
Linus Torvalds 已提交
1619 1620 1621 1622 1623
				unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	switch(action) {
	case CPU_UP_PREPARE:
1624
	case CPU_UP_PREPARE_FROZEN:
1625 1626
		if (init_timers_cpu(cpu) < 0)
			return NOTIFY_BAD;
L
Linus Torvalds 已提交
1627 1628 1629
		break;
#ifdef CONFIG_HOTPLUG_CPU
	case CPU_DEAD:
1630
	case CPU_DEAD_FROZEN:
L
Linus Torvalds 已提交
1631 1632 1633 1634 1635 1636 1637 1638 1639
		migrate_timers(cpu);
		break;
#endif
	default:
		break;
	}
	return NOTIFY_OK;
}

1640
static struct notifier_block __cpuinitdata timers_nb = {
L
Linus Torvalds 已提交
1641 1642 1643 1644 1645 1646
	.notifier_call	= timer_cpu_notify,
};


void __init init_timers(void)
{
1647
	int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
L
Linus Torvalds 已提交
1648
				(void *)(long)smp_processor_id());
1649

1650 1651
	init_timer_stats();

1652
	BUG_ON(err == NOTIFY_BAD);
L
Linus Torvalds 已提交
1653
	register_cpu_notifier(&timers_nb);
1654
	open_softirq(TIMER_SOFTIRQ, run_timer_softirq);
L
Linus Torvalds 已提交
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664
}

/**
 * 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;

1665 1666
	while (timeout)
		timeout = schedule_timeout_uninterruptible(timeout);
L
Linus Torvalds 已提交
1667 1668 1669 1670 1671
}

EXPORT_SYMBOL(msleep);

/**
1672
 * msleep_interruptible - sleep waiting for signals
L
Linus Torvalds 已提交
1673 1674 1675 1676 1677 1678
 * @msecs: Time in milliseconds to sleep for
 */
unsigned long msleep_interruptible(unsigned int msecs)
{
	unsigned long timeout = msecs_to_jiffies(msecs) + 1;

1679 1680
	while (timeout && !signal_pending(current))
		timeout = schedule_timeout_interruptible(timeout);
L
Linus Torvalds 已提交
1681 1682 1683 1684
	return jiffies_to_msecs(timeout);
}

EXPORT_SYMBOL(msleep_interruptible);