Blame view
kernel/timer.c
47.9 KB
1da177e4c
|
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 |
/* * linux/kernel/timer.c * * Kernel internal timers, kernel timekeeping, basic process system calls * * 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> #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> |
97a41e261
|
36 |
#include <linux/delay.h> |
1da177e4c
|
37 38 39 40 41 42 |
#include <asm/uaccess.h> #include <asm/unistd.h> #include <asm/div64.h> #include <asm/timex.h> #include <asm/io.h> |
ecea8d19c
|
43 44 45 |
u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES; EXPORT_SYMBOL(jiffies_64); |
1da177e4c
|
46 47 48 |
/* * per-CPU timer vector definitions: */ |
1da177e4c
|
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
#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) typedef struct tvec_s { struct list_head vec[TVN_SIZE]; } tvec_t; typedef struct tvec_root_s { struct list_head vec[TVR_SIZE]; } tvec_root_t; struct tvec_t_base_s { |
3691c5199
|
65 66 |
spinlock_t lock; struct timer_list *running_timer; |
1da177e4c
|
67 |
unsigned long timer_jiffies; |
1da177e4c
|
68 69 70 71 72 73 74 75 |
tvec_root_t tv1; tvec_t tv2; tvec_t tv3; tvec_t tv4; tvec_t tv5; } ____cacheline_aligned_in_smp; typedef struct tvec_t_base_s tvec_base_t; |
ba6edfcd1
|
76 |
|
3691c5199
|
77 78 |
tvec_base_t boot_tvec_bases; EXPORT_SYMBOL(boot_tvec_bases); |
51d8c5edd
|
79 |
static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = &boot_tvec_bases; |
1da177e4c
|
80 |
|
4c36a5dec
|
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 |
/** * __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) { 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. */ if (rem < HZ/4) /* round down */ 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; } 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 * * __round_jiffies_relative rounds a time delta 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_relative(unsigned long j, int cpu) { /* * In theory the following code can skip a jiffy in case jiffies * increments right between the addition and the later subtraction. * However since the entire point of this function is to use approximate * timeouts, it's entirely ok to not handle that. */ return __round_jiffies(j + jiffies, cpu) - jiffies; } 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 * * 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 return value is the rounded version of the "j" parameter. */ unsigned long round_jiffies(unsigned long j) { return __round_jiffies(j, raw_smp_processor_id()); } 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 * * round_jiffies_relative rounds a time delta 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 return value is the rounded version of the "j" parameter. */ unsigned long round_jiffies_relative(unsigned long j) { return __round_jiffies_relative(j, raw_smp_processor_id()); } EXPORT_SYMBOL_GPL(round_jiffies_relative); |
1da177e4c
|
211 212 213 214 |
static inline void set_running_timer(tvec_base_t *base, struct timer_list *timer) { #ifdef CONFIG_SMP |
3691c5199
|
215 |
base->running_timer = timer; |
1da177e4c
|
216 217 |
#endif } |
1da177e4c
|
218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 |
static void internal_add_timer(tvec_base_t *base, struct timer_list *timer) { 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); } |
2aae4a108
|
259 |
/** |
55c888d6d
|
260 261 262 263 264 265 266 267 268 |
* 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 fastcall init_timer(struct timer_list *timer) { timer->entry.next = NULL; |
bfe5d8341
|
269 |
timer->base = __raw_get_cpu_var(tvec_bases); |
55c888d6d
|
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 |
} EXPORT_SYMBOL(init_timer); static inline void detach_timer(struct timer_list *timer, int clear_pending) { struct list_head *entry = &timer->entry; __list_del(entry->prev, entry->next); if (clear_pending) entry->next = NULL; entry->prev = LIST_POISON2; } /* |
3691c5199
|
285 |
* We are using hashed locking: holding per_cpu(tvec_bases).lock |
55c888d6d
|
286 287 288 289 290 291 292 293 294 295 |
* 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. */ |
3691c5199
|
296 |
static tvec_base_t *lock_timer_base(struct timer_list *timer, |
55c888d6d
|
297 |
unsigned long *flags) |
89e7e374d
|
298 |
__acquires(timer->base->lock) |
55c888d6d
|
299 |
{ |
3691c5199
|
300 |
tvec_base_t *base; |
55c888d6d
|
301 302 303 304 305 306 307 308 309 310 311 312 313 |
for (;;) { base = timer->base; if (likely(base != NULL)) { spin_lock_irqsave(&base->lock, *flags); if (likely(base == timer->base)) return base; /* The timer has migrated to another CPU */ spin_unlock_irqrestore(&base->lock, *flags); } cpu_relax(); } } |
1da177e4c
|
314 315 |
int __mod_timer(struct timer_list *timer, unsigned long expires) { |
3691c5199
|
316 |
tvec_base_t *base, *new_base; |
1da177e4c
|
317 318 319 320 |
unsigned long flags; int ret = 0; BUG_ON(!timer->function); |
1da177e4c
|
321 |
|
55c888d6d
|
322 323 324 325 326 327 |
base = lock_timer_base(timer, &flags); if (timer_pending(timer)) { detach_timer(timer, 0); ret = 1; } |
a4a6198b8
|
328 |
new_base = __get_cpu_var(tvec_bases); |
1da177e4c
|
329 |
|
3691c5199
|
330 |
if (base != new_base) { |
1da177e4c
|
331 |
/* |
55c888d6d
|
332 333 334 335 336 |
* 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. |
1da177e4c
|
337 |
*/ |
a2c348fe0
|
338 |
if (likely(base->running_timer != timer)) { |
55c888d6d
|
339 340 341 |
/* See the comment in lock_timer_base() */ timer->base = NULL; spin_unlock(&base->lock); |
a2c348fe0
|
342 343 344 |
base = new_base; spin_lock(&base->lock); timer->base = base; |
1da177e4c
|
345 346 |
} } |
1da177e4c
|
347 |
timer->expires = expires; |
a2c348fe0
|
348 349 |
internal_add_timer(base, timer); spin_unlock_irqrestore(&base->lock, flags); |
1da177e4c
|
350 351 352 353 354 |
return ret; } EXPORT_SYMBOL(__mod_timer); |
2aae4a108
|
355 |
/** |
1da177e4c
|
356 357 358 359 360 361 362 363 |
* 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) { |
a4a6198b8
|
364 |
tvec_base_t *base = per_cpu(tvec_bases, cpu); |
1da177e4c
|
365 |
unsigned long flags; |
55c888d6d
|
366 |
|
1da177e4c
|
367 |
BUG_ON(timer_pending(timer) || !timer->function); |
3691c5199
|
368 369 |
spin_lock_irqsave(&base->lock, flags); timer->base = base; |
1da177e4c
|
370 |
internal_add_timer(base, timer); |
3691c5199
|
371 |
spin_unlock_irqrestore(&base->lock, flags); |
1da177e4c
|
372 |
} |
2aae4a108
|
373 |
/** |
1da177e4c
|
374 375 |
* mod_timer - modify a timer's timeout * @timer: the timer to be modified |
2aae4a108
|
376 |
* @expires: new timeout in jiffies |
1da177e4c
|
377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 |
* * mod_timer is a more efficient way to update the expire field of an * 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) { BUG_ON(!timer->function); |
1da177e4c
|
396 397 398 399 400 401 402 403 404 405 406 407 |
/* * 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; return __mod_timer(timer, expires); } EXPORT_SYMBOL(mod_timer); |
2aae4a108
|
408 |
/** |
1da177e4c
|
409 410 411 412 413 414 415 416 417 418 419 420 |
* 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) { |
3691c5199
|
421 |
tvec_base_t *base; |
1da177e4c
|
422 |
unsigned long flags; |
55c888d6d
|
423 |
int ret = 0; |
1da177e4c
|
424 |
|
55c888d6d
|
425 426 427 428 429 430 |
if (timer_pending(timer)) { base = lock_timer_base(timer, &flags); if (timer_pending(timer)) { detach_timer(timer, 1); ret = 1; } |
1da177e4c
|
431 |
spin_unlock_irqrestore(&base->lock, flags); |
1da177e4c
|
432 |
} |
1da177e4c
|
433 |
|
55c888d6d
|
434 |
return ret; |
1da177e4c
|
435 436 437 438 439 |
} EXPORT_SYMBOL(del_timer); #ifdef CONFIG_SMP |
2aae4a108
|
440 441 442 443 |
/** * try_to_del_timer_sync - Try to deactivate a timer * @timer: timer do del * |
fd450b731
|
444 445 446 447 448 449 450 |
* 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) { |
3691c5199
|
451 |
tvec_base_t *base; |
fd450b731
|
452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 |
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; } |
2aae4a108
|
470 |
/** |
1da177e4c
|
471 472 473 474 475 476 477 478 479 480 |
* 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. * * Synchronization rules: callers must prevent restarting of the timer, * otherwise this function is meaningless. It must not be called from * interrupt contexts. The caller must not hold locks which would prevent |
55c888d6d
|
481 482 483 |
* 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. |
1da177e4c
|
484 485 |
* * The function returns whether it has deactivated a pending timer or not. |
1da177e4c
|
486 487 488 |
*/ int del_timer_sync(struct timer_list *timer) { |
fd450b731
|
489 490 491 492 |
for (;;) { int ret = try_to_del_timer_sync(timer); if (ret >= 0) return ret; |
a0009652a
|
493 |
cpu_relax(); |
fd450b731
|
494 |
} |
1da177e4c
|
495 |
} |
1da177e4c
|
496 |
|
55c888d6d
|
497 |
EXPORT_SYMBOL(del_timer_sync); |
1da177e4c
|
498 499 500 501 502 |
#endif static int cascade(tvec_base_t *base, tvec_t *tv, int index) { /* cascade all the timers from tv up one level */ |
3439dd86e
|
503 504 505 506 |
struct timer_list *timer, *tmp; struct list_head tv_list; list_replace_init(tv->vec + index, &tv_list); |
1da177e4c
|
507 |
|
1da177e4c
|
508 |
/* |
3439dd86e
|
509 510 |
* We are removing _all_ timers from the list, so we * don't have to detach them individually. |
1da177e4c
|
511 |
*/ |
3439dd86e
|
512 513 514 |
list_for_each_entry_safe(timer, tmp, &tv_list, entry) { BUG_ON(timer->base != base); internal_add_timer(base, timer); |
1da177e4c
|
515 |
} |
1da177e4c
|
516 517 518 |
return index; } |
2aae4a108
|
519 520 521 |
#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK) /** |
1da177e4c
|
522 523 524 525 526 527 |
* __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. */ |
1da177e4c
|
528 529 530 |
static inline void __run_timers(tvec_base_t *base) { struct timer_list *timer; |
3691c5199
|
531 |
spin_lock_irq(&base->lock); |
1da177e4c
|
532 |
while (time_after_eq(jiffies, base->timer_jiffies)) { |
626ab0e69
|
533 |
struct list_head work_list; |
1da177e4c
|
534 535 |
struct list_head *head = &work_list; int index = base->timer_jiffies & TVR_MASK; |
626ab0e69
|
536 |
|
1da177e4c
|
537 538 539 540 541 542 543 544 |
/* * 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)); |
626ab0e69
|
545 546 |
++base->timer_jiffies; list_replace_init(base->tv1.vec + index, &work_list); |
55c888d6d
|
547 |
while (!list_empty(head)) { |
1da177e4c
|
548 549 550 551 552 553 |
void (*fn)(unsigned long); unsigned long data; timer = list_entry(head->next,struct timer_list,entry); fn = timer->function; data = timer->data; |
1da177e4c
|
554 |
set_running_timer(base, timer); |
55c888d6d
|
555 |
detach_timer(timer, 1); |
3691c5199
|
556 |
spin_unlock_irq(&base->lock); |
1da177e4c
|
557 |
{ |
be5b4fbd0
|
558 |
int preempt_count = preempt_count(); |
1da177e4c
|
559 560 |
fn(data); if (preempt_count != preempt_count()) { |
be5b4fbd0
|
561 562 563 564 565 566 |
printk(KERN_WARNING "huh, entered %p " "with preempt_count %08x, exited" " with %08x? ", fn, preempt_count, preempt_count()); |
1da177e4c
|
567 568 569 |
BUG(); } } |
3691c5199
|
570 |
spin_lock_irq(&base->lock); |
1da177e4c
|
571 572 573 |
} } set_running_timer(base, NULL); |
3691c5199
|
574 |
spin_unlock_irq(&base->lock); |
1da177e4c
|
575 576 577 578 579 580 581 582 583 584 585 586 587 588 |
} #ifdef CONFIG_NO_IDLE_HZ /* * 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. */ unsigned long next_timer_interrupt(void) { tvec_base_t *base; struct list_head *list; struct timer_list *nte; unsigned long expires; |
69239749e
|
589 590 |
unsigned long hr_expires = MAX_JIFFY_OFFSET; ktime_t hr_delta; |
1da177e4c
|
591 592 |
tvec_t *varray[4]; int i, j; |
69239749e
|
593 594 595 596 597 598 599 600 601 |
hr_delta = hrtimer_get_next_event(); if (hr_delta.tv64 != KTIME_MAX) { struct timespec tsdelta; tsdelta = ktime_to_timespec(hr_delta); hr_expires = timespec_to_jiffies(&tsdelta); if (hr_expires < 3) return hr_expires + jiffies; } hr_expires += jiffies; |
a4a6198b8
|
602 |
base = __get_cpu_var(tvec_bases); |
3691c5199
|
603 |
spin_lock(&base->lock); |
1da177e4c
|
604 |
expires = base->timer_jiffies + (LONG_MAX >> 1); |
53f087feb
|
605 |
list = NULL; |
1da177e4c
|
606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 |
/* Look for timer events in tv1. */ j = base->timer_jiffies & TVR_MASK; do { list_for_each_entry(nte, base->tv1.vec + j, entry) { expires = nte->expires; if (j < (base->timer_jiffies & TVR_MASK)) list = base->tv2.vec + (INDEX(0)); goto found; } j = (j + 1) & TVR_MASK; } while (j != (base->timer_jiffies & TVR_MASK)); /* Check tv2-tv5. */ varray[0] = &base->tv2; varray[1] = &base->tv3; varray[2] = &base->tv4; varray[3] = &base->tv5; for (i = 0; i < 4; i++) { j = INDEX(i); do { if (list_empty(varray[i]->vec + j)) { j = (j + 1) & TVN_MASK; continue; } list_for_each_entry(nte, varray[i]->vec + j, entry) if (time_before(nte->expires, expires)) expires = nte->expires; if (j < (INDEX(i)) && i < 3) list = varray[i + 1]->vec + (INDEX(i + 1)); goto found; } while (j != (INDEX(i))); } found: if (list) { /* * The search wrapped. We need to look at the next list * from next tv element that would cascade into tv element * where we found the timer element. */ list_for_each_entry(nte, list, entry) { if (time_before(nte->expires, expires)) expires = nte->expires; } } |
3691c5199
|
651 |
spin_unlock(&base->lock); |
69239749e
|
652 |
|
0662b7132
|
653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 |
/* * It can happen that other CPUs service timer IRQs and increment * jiffies, but we have not yet got a local timer tick to process * the timer wheels. In that case, the expiry time can be before * jiffies, but since the high-resolution timer here is relative to * jiffies, the default expression when high-resolution timers are * not active, * * time_before(MAX_JIFFY_OFFSET + jiffies, expires) * * would falsely evaluate to true. If that is the case, just * return jiffies so that we can immediately fire the local timer */ if (time_before(expires, jiffies)) return jiffies; |
69239749e
|
668 669 |
if (time_before(hr_expires, expires)) return hr_expires; |
1da177e4c
|
670 671 672 673 674 |
return expires; } #endif /******************************************************************/ |
1da177e4c
|
675 676 677 678 679 680 681 682 683 684 685 686 |
/* * The current time * wall_to_monotonic is what we need to add to xtime (or xtime corrected * for sub jiffie times) to get to monotonic time. Monotonic is pegged * at zero at system boot time, so wall_to_monotonic will be negative, * however, we will ALWAYS keep the tv_nsec part positive so we can use * the usual normalization. */ struct timespec xtime __attribute__ ((aligned (16))); struct timespec wall_to_monotonic __attribute__ ((aligned (16))); EXPORT_SYMBOL(xtime); |
726c14bf4
|
687 |
|
ad596171e
|
688 689 690 |
/* XXX - all of this timekeeping code should be later moved to time.c */ #include <linux/clocksource.h> static struct clocksource *clock; /* pointer to current clocksource */ |
cf3c769b4
|
691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 |
#ifdef CONFIG_GENERIC_TIME /** * __get_nsec_offset - Returns nanoseconds since last call to periodic_hook * * private function, must hold xtime_lock lock when being * called. Returns the number of nanoseconds since the * last call to update_wall_time() (adjusted by NTP scaling) */ static inline s64 __get_nsec_offset(void) { cycle_t cycle_now, cycle_delta; s64 ns_offset; /* read clocksource: */ |
a27525497
|
706 |
cycle_now = clocksource_read(clock); |
cf3c769b4
|
707 708 |
/* calculate the delta since the last update_wall_time: */ |
19923c190
|
709 |
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask; |
cf3c769b4
|
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 |
/* convert to nanoseconds: */ ns_offset = cyc2ns(clock, cycle_delta); return ns_offset; } /** * __get_realtime_clock_ts - Returns the time of day in a timespec * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec. Used by * do_gettimeofday() and get_realtime_clock_ts(). */ static inline void __get_realtime_clock_ts(struct timespec *ts) { unsigned long seq; s64 nsecs; do { seq = read_seqbegin(&xtime_lock); *ts = xtime; nsecs = __get_nsec_offset(); } while (read_seqretry(&xtime_lock, seq)); timespec_add_ns(ts, nsecs); } /** |
a27525497
|
741 |
* getnstimeofday - Returns the time of day in a timespec |
cf3c769b4
|
742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 |
* @ts: pointer to the timespec to be set * * Returns the time of day in a timespec. */ void getnstimeofday(struct timespec *ts) { __get_realtime_clock_ts(ts); } EXPORT_SYMBOL(getnstimeofday); /** * do_gettimeofday - Returns the time of day in a timeval * @tv: pointer to the timeval to be set * * NOTE: Users should be converted to using get_realtime_clock_ts() */ void do_gettimeofday(struct timeval *tv) { struct timespec now; __get_realtime_clock_ts(&now); tv->tv_sec = now.tv_sec; tv->tv_usec = now.tv_nsec/1000; } EXPORT_SYMBOL(do_gettimeofday); /** * do_settimeofday - Sets the time of day * @tv: pointer to the timespec variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday(struct timespec *tv) { unsigned long flags; time_t wtm_sec, sec = tv->tv_sec; long wtm_nsec, nsec = tv->tv_nsec; if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC) return -EINVAL; write_seqlock_irqsave(&xtime_lock, flags); nsec -= __get_nsec_offset(); wtm_sec = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec); wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec); set_normalized_timespec(&xtime, sec, nsec); set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec); |
e154ff3d2
|
793 |
clock->error = 0; |
cf3c769b4
|
794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 |
ntp_clear(); write_sequnlock_irqrestore(&xtime_lock, flags); /* signal hrtimers about time change */ clock_was_set(); return 0; } EXPORT_SYMBOL(do_settimeofday); /** * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void) { struct clocksource *new; cycle_t now; u64 nsec; |
a27525497
|
816 |
new = clocksource_get_next(); |
cf3c769b4
|
817 |
if (clock != new) { |
a27525497
|
818 |
now = clocksource_read(new); |
cf3c769b4
|
819 820 821 822 |
nsec = __get_nsec_offset(); timespec_add_ns(&xtime, nsec); clock = new; |
19923c190
|
823 |
clock->cycle_last = now; |
cf3c769b4
|
824 825 |
printk(KERN_INFO "Time: %s clocksource has been installed. ", |
f5f1a24a2
|
826 |
clock->name); |
cf3c769b4
|
827 828 829 830 831 832 833 |
return 1; } else if (clock->update_callback) { return clock->update_callback(); } return 0; } #else |
f5f1a24a2
|
834 835 836 837 |
static inline int change_clocksource(void) { return 0; } |
cf3c769b4
|
838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 |
#endif /** * timeofday_is_continuous - check to see if timekeeping is free running */ int timekeeping_is_continuous(void) { unsigned long seq; int ret; do { seq = read_seqbegin(&xtime_lock); ret = clock->is_continuous; } while (read_seqretry(&xtime_lock, seq)); return ret; } |
726c14bf4
|
857 |
/* |
ad596171e
|
858 |
* timekeeping_init - Initializes the clocksource and common timekeeping values |
1da177e4c
|
859 |
*/ |
ad596171e
|
860 |
void __init timekeeping_init(void) |
1da177e4c
|
861 |
{ |
ad596171e
|
862 863 864 |
unsigned long flags; write_seqlock_irqsave(&xtime_lock, flags); |
b0ee75561
|
865 866 |
ntp_clear(); |
a27525497
|
867 868 |
clock = clocksource_get_next(); clocksource_calculate_interval(clock, tick_nsec); |
19923c190
|
869 |
clock->cycle_last = clocksource_read(clock); |
b0ee75561
|
870 |
|
ad596171e
|
871 872 |
write_sequnlock_irqrestore(&xtime_lock, flags); } |
3e143475c
|
873 |
static int timekeeping_suspended; |
2aae4a108
|
874 |
/** |
ad596171e
|
875 876 877 878 |
* timekeeping_resume - Resumes the generic timekeeping subsystem. * @dev: unused * * This is for the generic clocksource timekeeping. |
8ef386092
|
879 |
* xtime/wall_to_monotonic/jiffies/etc are |
ad596171e
|
880 881 882 883 884 885 886 887 |
* still managed by arch specific suspend/resume code. */ static int timekeeping_resume(struct sys_device *dev) { unsigned long flags; write_seqlock_irqsave(&xtime_lock, flags); /* restart the last cycle value */ |
19923c190
|
888 |
clock->cycle_last = clocksource_read(clock); |
3e143475c
|
889 890 891 892 893 894 895 896 897 898 899 900 |
clock->error = 0; timekeeping_suspended = 0; write_sequnlock_irqrestore(&xtime_lock, flags); return 0; } static int timekeeping_suspend(struct sys_device *dev, pm_message_t state) { unsigned long flags; write_seqlock_irqsave(&xtime_lock, flags); timekeeping_suspended = 1; |
ad596171e
|
901 902 903 904 905 906 907 |
write_sequnlock_irqrestore(&xtime_lock, flags); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct sysdev_class timekeeping_sysclass = { .resume = timekeeping_resume, |
3e143475c
|
908 |
.suspend = timekeeping_suspend, |
ad596171e
|
909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 |
set_kset_name("timekeeping"), }; static struct sys_device device_timer = { .id = 0, .cls = &timekeeping_sysclass, }; static int __init timekeeping_init_device(void) { int error = sysdev_class_register(&timekeeping_sysclass); if (!error) error = sysdev_register(&device_timer); return error; } device_initcall(timekeeping_init_device); /* |
e154ff3d2
|
928 |
* If the error is already larger, we look ahead even further |
19923c190
|
929 930 |
* to compensate for late or lost adjustments. */ |
f5f1a24a2
|
931 932 |
static __always_inline int clocksource_bigadjust(s64 error, s64 *interval, s64 *offset) |
19923c190
|
933 |
{ |
e154ff3d2
|
934 935 936 |
s64 tick_error, i; u32 look_ahead, adj; s32 error2, mult; |
19923c190
|
937 938 |
/* |
e154ff3d2
|
939 940 941 942 943 944 945 |
* Use the current error value to determine how much to look ahead. * The larger the error the slower we adjust for it to avoid problems * with losing too many ticks, otherwise we would overadjust and * produce an even larger error. The smaller the adjustment the * faster we try to adjust for it, as lost ticks can do less harm * here. This is tuned so that an error of about 1 msec is adusted * within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks). |
19923c190
|
946 |
*/ |
e154ff3d2
|
947 948 949 950 |
error2 = clock->error >> (TICK_LENGTH_SHIFT + 22 - 2 * SHIFT_HZ); error2 = abs(error2); for (look_ahead = 0; error2 > 0; look_ahead++) error2 >>= 2; |
19923c190
|
951 952 |
/* |
e154ff3d2
|
953 954 |
* Now calculate the error in (1 << look_ahead) ticks, but first * remove the single look ahead already included in the error. |
19923c190
|
955 |
*/ |
f5f1a24a2
|
956 957 |
tick_error = current_tick_length() >> (TICK_LENGTH_SHIFT - clock->shift + 1); |
e154ff3d2
|
958 959 960 961 962 963 964 965 966 967 968 |
tick_error -= clock->xtime_interval >> 1; error = ((error - tick_error) >> look_ahead) + tick_error; /* Finally calculate the adjustment shift value. */ i = *interval; mult = 1; if (error < 0) { error = -error; *interval = -*interval; *offset = -*offset; mult = -1; |
19923c190
|
969 |
} |
e154ff3d2
|
970 971 |
for (adj = 0; error > i; adj++) error >>= 1; |
19923c190
|
972 973 974 |
*interval <<= adj; *offset <<= adj; |
e154ff3d2
|
975 |
return mult << adj; |
19923c190
|
976 977 978 979 980 981 982 983 984 985 986 987 988 989 |
} /* * Adjust the multiplier to reduce the error value, * this is optimized for the most common adjustments of -1,0,1, * for other values we can do a bit more work. */ static void clocksource_adjust(struct clocksource *clock, s64 offset) { s64 error, interval = clock->cycle_interval; int adj; error = clock->error >> (TICK_LENGTH_SHIFT - clock->shift - 1); if (error > interval) { |
e154ff3d2
|
990 991 992 993 994 |
error >>= 2; if (likely(error <= interval)) adj = 1; else adj = clocksource_bigadjust(error, &interval, &offset); |
19923c190
|
995 |
} else if (error < -interval) { |
e154ff3d2
|
996 997 998 999 1000 1001 1002 |
error >>= 2; if (likely(error >= -interval)) { adj = -1; interval = -interval; offset = -offset; } else adj = clocksource_bigadjust(error, &interval, &offset); |
19923c190
|
1003 1004 1005 1006 1007 1008 |
} else return; clock->mult += adj; clock->xtime_interval += interval; clock->xtime_nsec -= offset; |
f5f1a24a2
|
1009 1010 |
clock->error -= (interval - offset) << (TICK_LENGTH_SHIFT - clock->shift); |
19923c190
|
1011 |
} |
2aae4a108
|
1012 |
/** |
ad596171e
|
1013 1014 1015 1016 1017 1018 |
* update_wall_time - Uses the current clocksource to increment the wall time * * Called from the timer interrupt, must hold a write on xtime_lock. */ static void update_wall_time(void) { |
19923c190
|
1019 |
cycle_t offset; |
ad596171e
|
1020 |
|
3e143475c
|
1021 1022 1023 |
/* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) return; |
5eb6d2053
|
1024 |
|
19923c190
|
1025 1026 1027 1028 1029 |
#ifdef CONFIG_GENERIC_TIME offset = (clocksource_read(clock) - clock->cycle_last) & clock->mask; #else offset = clock->cycle_interval; #endif |
3e143475c
|
1030 |
clock->xtime_nsec += (s64)xtime.tv_nsec << clock->shift; |
ad596171e
|
1031 1032 1033 1034 |
/* normally this loop will run just once, however in the * case of lost or late ticks, it will accumulate correctly. */ |
19923c190
|
1035 |
while (offset >= clock->cycle_interval) { |
ad596171e
|
1036 |
/* accumulate one interval */ |
19923c190
|
1037 1038 1039 1040 1041 1042 1043 1044 1045 |
clock->xtime_nsec += clock->xtime_interval; clock->cycle_last += clock->cycle_interval; offset -= clock->cycle_interval; if (clock->xtime_nsec >= (u64)NSEC_PER_SEC << clock->shift) { clock->xtime_nsec -= (u64)NSEC_PER_SEC << clock->shift; xtime.tv_sec++; second_overflow(); } |
ad596171e
|
1046 |
|
5eb6d2053
|
1047 |
/* interpolator bits */ |
19923c190
|
1048 |
time_interpolator_update(clock->xtime_interval |
5eb6d2053
|
1049 |
>> clock->shift); |
5eb6d2053
|
1050 1051 |
/* accumulate error between NTP and clock interval */ |
19923c190
|
1052 1053 1054 |
clock->error += current_tick_length(); clock->error -= clock->xtime_interval << (TICK_LENGTH_SHIFT - clock->shift); } |
5eb6d2053
|
1055 |
|
19923c190
|
1056 1057 |
/* correct the clock when NTP error is too big */ clocksource_adjust(clock, offset); |
5eb6d2053
|
1058 |
|
5eb6d2053
|
1059 |
/* store full nanoseconds into xtime */ |
e154ff3d2
|
1060 |
xtime.tv_nsec = (s64)clock->xtime_nsec >> clock->shift; |
19923c190
|
1061 |
clock->xtime_nsec -= (s64)xtime.tv_nsec << clock->shift; |
cf3c769b4
|
1062 1063 1064 |
/* check to see if there is a new clocksource to use */ if (change_clocksource()) { |
19923c190
|
1065 1066 |
clock->error = 0; clock->xtime_nsec = 0; |
a27525497
|
1067 |
clocksource_calculate_interval(clock, tick_nsec); |
cf3c769b4
|
1068 |
} |
1da177e4c
|
1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 |
} /* * Called from the timer interrupt handler to charge one tick to the current * 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. */ if (user_tick) account_user_time(p, jiffies_to_cputime(1)); else account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1)); run_local_timers(); if (rcu_pending(cpu)) rcu_check_callbacks(cpu, user_tick); scheduler_tick(); run_posix_cpu_timers(p); } /* * Nr of active tasks - counted in fixed-point numbers */ static unsigned long count_active_tasks(void) { |
db1b1fefc
|
1097 |
return nr_active() * FIXED_1; |
1da177e4c
|
1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 |
} /* * 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; |
cd7175edf
|
1120 1121 1122 1123 1124 1125 1126 1127 1128 |
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); |
1da177e4c
|
1129 1130 |
} } |
1da177e4c
|
1131 1132 1133 1134 1135 |
/* * This read-write spinlock protects us from races in SMP while * playing with xtime and avenrun. */ #ifndef ARCH_HAVE_XTIME_LOCK |
e4d919188
|
1136 |
__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock); |
1da177e4c
|
1137 1138 1139 1140 1141 1142 1143 1144 1145 |
EXPORT_SYMBOL(xtime_lock); #endif /* * This function runs timers and the timer-tq in bottom half context. */ static void run_timer_softirq(struct softirq_action *h) { |
a4a6198b8
|
1146 |
tvec_base_t *base = __get_cpu_var(tvec_bases); |
1da177e4c
|
1147 |
|
c0a313296
|
1148 |
hrtimer_run_queues(); |
1da177e4c
|
1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 |
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) { raise_softirq(TIMER_SOFTIRQ); |
6687a97d4
|
1159 |
softlockup_tick(); |
1da177e4c
|
1160 1161 1162 1163 1164 1165 |
} /* * Called by the timer interrupt. xtime_lock must already be taken * by the timer IRQ! */ |
3171a0305
|
1166 |
static inline void update_times(unsigned long ticks) |
1da177e4c
|
1167 |
{ |
ad596171e
|
1168 |
update_wall_time(); |
1da177e4c
|
1169 1170 1171 1172 1173 1174 1175 1176 |
calc_load(ticks); } /* * 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... */ |
3171a0305
|
1177 |
void do_timer(unsigned long ticks) |
1da177e4c
|
1178 |
{ |
3171a0305
|
1179 1180 |
jiffies_64 += ticks; update_times(ticks); |
1da177e4c
|
1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 |
} #ifdef __ARCH_WANT_SYS_ALARM /* * For backwards compatibility? This can be done in libc so Alpha * and all newer ports shouldn't need it. */ asmlinkage unsigned long sys_alarm(unsigned int seconds) { |
c08b8a491
|
1191 |
return alarm_setitimer(seconds); |
1da177e4c
|
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 |
} #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. */ asmlinkage long sys_getpid(void) { return current->tgid; } /* |
6997a6faa
|
1218 1219 1220 1221 |
* 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). |
1da177e4c
|
1222 1223 1224 1225 |
*/ asmlinkage long sys_getppid(void) { int pid; |
1da177e4c
|
1226 |
|
6997a6faa
|
1227 1228 1229 |
rcu_read_lock(); pid = rcu_dereference(current->real_parent)->tgid; rcu_read_unlock(); |
1da177e4c
|
1230 |
|
1da177e4c
|
1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 |
return pid; } asmlinkage long sys_getuid(void) { /* Only we change this so SMP safe */ return current->uid; } asmlinkage long sys_geteuid(void) { /* Only we change this so SMP safe */ return current->euid; } asmlinkage long sys_getgid(void) { /* Only we change this so SMP safe */ return current->gid; } asmlinkage long sys_getegid(void) { /* Only we change this so SMP safe */ return current->egid; } #endif static void process_timeout(unsigned long __data) { |
36c8b5868
|
1262 |
wake_up_process((struct task_struct *)__data); |
1da177e4c
|
1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 |
} /** * 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. */ fastcall signed long __sched schedule_timeout(signed long timeout) { 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. */ |
5b149bcc2
|
1316 |
if (timeout < 0) { |
1da177e4c
|
1317 |
printk(KERN_ERR "schedule_timeout: wrong timeout " |
5b149bcc2
|
1318 1319 1320 |
"value %lx ", timeout); dump_stack(); |
1da177e4c
|
1321 1322 1323 1324 1325 1326 |
current->state = TASK_RUNNING; goto out; } } expire = timeout + jiffies; |
a8db2db1e
|
1327 1328 |
setup_timer(&timer, process_timeout, (unsigned long)current); __mod_timer(&timer, expire); |
1da177e4c
|
1329 1330 1331 1332 1333 1334 1335 1336 |
schedule(); del_singleshot_timer_sync(&timer); timeout = expire - jiffies; out: return timeout < 0 ? 0 : timeout; } |
1da177e4c
|
1337 |
EXPORT_SYMBOL(schedule_timeout); |
8a1c17574
|
1338 1339 1340 1341 |
/* * We can use __set_current_state() here because schedule_timeout() calls * schedule() unconditionally. */ |
64ed93a26
|
1342 1343 |
signed long __sched schedule_timeout_interruptible(signed long timeout) { |
a5a0d52c7
|
1344 1345 |
__set_current_state(TASK_INTERRUPTIBLE); return schedule_timeout(timeout); |
64ed93a26
|
1346 1347 1348 1349 1350 |
} EXPORT_SYMBOL(schedule_timeout_interruptible); signed long __sched schedule_timeout_uninterruptible(signed long timeout) { |
a5a0d52c7
|
1351 1352 |
__set_current_state(TASK_UNINTERRUPTIBLE); return schedule_timeout(timeout); |
64ed93a26
|
1353 1354 |
} EXPORT_SYMBOL(schedule_timeout_uninterruptible); |
1da177e4c
|
1355 1356 1357 1358 1359 |
/* Thread ID - the internal kernel "pid" */ asmlinkage long sys_gettid(void) { return current->pid; } |
2aae4a108
|
1360 |
/** |
1da177e4c
|
1361 |
* sys_sysinfo - fill in sysinfo struct |
2aae4a108
|
1362 |
* @info: pointer to buffer to fill |
1da177e4c
|
1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 |
*/ asmlinkage long sys_sysinfo(struct sysinfo __user *info) { struct sysinfo val; unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; unsigned long seq; memset((char *)&val, 0, sizeof(struct sysinfo)); 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; if (tp.tv_nsec - NSEC_PER_SEC >= 0) { tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC; tp.tv_sec++; } val.uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); val.loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT); val.loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT); val.loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT); val.procs = nr_threads; } while (read_seqretry(&xtime_lock, seq)); si_meminfo(&val); si_swapinfo(&val); /* * 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> */ mem_total = val.totalram + val.totalswap; if (mem_total < val.totalram || mem_total < val.totalswap) goto out; bitcount = 0; mem_unit = val.mem_unit; 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 * val.mem_unit and set it to 1. This leaves things compatible * with 2.2.x, and also retains compatibility with earlier 2.4.x * kernels... */ val.mem_unit = 1; val.totalram <<= bitcount; val.freeram <<= bitcount; val.sharedram <<= bitcount; val.bufferram <<= bitcount; val.totalswap <<= bitcount; val.freeswap <<= bitcount; val.totalhigh <<= bitcount; val.freehigh <<= bitcount; out: if (copy_to_user(info, &val, sizeof(struct sysinfo))) return -EFAULT; return 0; } |
d730e882a
|
1449 1450 1451 1452 1453 1454 |
/* * lockdep: we want to track each per-CPU base as a separate lock-class, * but timer-bases are kmalloc()-ed, so we need to attach separate * keys to them: */ static struct lock_class_key base_lock_keys[NR_CPUS]; |
a4a6198b8
|
1455 |
static int __devinit init_timers_cpu(int cpu) |
1da177e4c
|
1456 1457 1458 |
{ int j; tvec_base_t *base; |
ba6edfcd1
|
1459 |
static char __devinitdata tvec_base_done[NR_CPUS]; |
55c888d6d
|
1460 |
|
ba6edfcd1
|
1461 |
if (!tvec_base_done[cpu]) { |
a4a6198b8
|
1462 |
static char boot_done; |
a4a6198b8
|
1463 |
if (boot_done) { |
ba6edfcd1
|
1464 1465 1466 |
/* * The APs use this path later in boot */ |
a4a6198b8
|
1467 1468 1469 1470 1471 |
base = kmalloc_node(sizeof(*base), GFP_KERNEL, cpu_to_node(cpu)); if (!base) return -ENOMEM; memset(base, 0, sizeof(*base)); |
ba6edfcd1
|
1472 |
per_cpu(tvec_bases, cpu) = base; |
a4a6198b8
|
1473 |
} else { |
ba6edfcd1
|
1474 1475 1476 1477 1478 1479 |
/* * 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. */ |
a4a6198b8
|
1480 |
boot_done = 1; |
ba6edfcd1
|
1481 |
base = &boot_tvec_bases; |
a4a6198b8
|
1482 |
} |
ba6edfcd1
|
1483 1484 1485 |
tvec_base_done[cpu] = 1; } else { base = per_cpu(tvec_bases, cpu); |
a4a6198b8
|
1486 |
} |
ba6edfcd1
|
1487 |
|
3691c5199
|
1488 |
spin_lock_init(&base->lock); |
d730e882a
|
1489 |
lockdep_set_class(&base->lock, base_lock_keys + cpu); |
1da177e4c
|
1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 |
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; |
a4a6198b8
|
1500 |
return 0; |
1da177e4c
|
1501 1502 1503 |
} #ifdef CONFIG_HOTPLUG_CPU |
55c888d6d
|
1504 |
static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head) |
1da177e4c
|
1505 1506 1507 1508 1509 |
{ struct timer_list *timer; while (!list_empty(head)) { timer = list_entry(head->next, struct timer_list, entry); |
55c888d6d
|
1510 |
detach_timer(timer, 0); |
3691c5199
|
1511 |
timer->base = new_base; |
1da177e4c
|
1512 |
internal_add_timer(new_base, timer); |
1da177e4c
|
1513 |
} |
1da177e4c
|
1514 1515 1516 1517 1518 1519 1520 1521 1522 |
} static void __devinit migrate_timers(int cpu) { tvec_base_t *old_base; tvec_base_t *new_base; int i; BUG_ON(cpu_online(cpu)); |
a4a6198b8
|
1523 1524 |
old_base = per_cpu(tvec_bases, cpu); new_base = get_cpu_var(tvec_bases); |
1da177e4c
|
1525 1526 |
local_irq_disable(); |
3691c5199
|
1527 1528 1529 1530 |
spin_lock(&new_base->lock); spin_lock(&old_base->lock); BUG_ON(old_base->running_timer); |
1da177e4c
|
1531 |
|
1da177e4c
|
1532 |
for (i = 0; i < TVR_SIZE; i++) |
55c888d6d
|
1533 1534 1535 1536 1537 1538 1539 |
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); } |
3691c5199
|
1540 1541 |
spin_unlock(&old_base->lock); spin_unlock(&new_base->lock); |
1da177e4c
|
1542 1543 |
local_irq_enable(); put_cpu_var(tvec_bases); |
1da177e4c
|
1544 1545 |
} #endif /* CONFIG_HOTPLUG_CPU */ |
8c78f3075
|
1546 |
static int __cpuinit timer_cpu_notify(struct notifier_block *self, |
1da177e4c
|
1547 1548 1549 1550 1551 |
unsigned long action, void *hcpu) { long cpu = (long)hcpu; switch(action) { case CPU_UP_PREPARE: |
a4a6198b8
|
1552 1553 |
if (init_timers_cpu(cpu) < 0) return NOTIFY_BAD; |
1da177e4c
|
1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 |
break; #ifdef CONFIG_HOTPLUG_CPU case CPU_DEAD: migrate_timers(cpu); break; #endif default: break; } return NOTIFY_OK; } |
8c78f3075
|
1565 |
static struct notifier_block __cpuinitdata timers_nb = { |
1da177e4c
|
1566 1567 1568 1569 1570 1571 |
.notifier_call = timer_cpu_notify, }; void __init init_timers(void) { |
07dccf334
|
1572 |
int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE, |
1da177e4c
|
1573 |
(void *)(long)smp_processor_id()); |
07dccf334
|
1574 1575 |
BUG_ON(err == NOTIFY_BAD); |
1da177e4c
|
1576 1577 1578 1579 1580 |
register_cpu_notifier(&timers_nb); open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL); } #ifdef CONFIG_TIME_INTERPOLATION |
67890d708
|
1581 1582 |
struct time_interpolator *time_interpolator __read_mostly; static struct time_interpolator *time_interpolator_list __read_mostly; |
1da177e4c
|
1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 |
static DEFINE_SPINLOCK(time_interpolator_lock); static inline u64 time_interpolator_get_cycles(unsigned int src) { unsigned long (*x)(void); switch (src) { case TIME_SOURCE_FUNCTION: x = time_interpolator->addr; return x(); case TIME_SOURCE_MMIO64 : |
685db65e4
|
1596 |
return readq_relaxed((void __iomem *)time_interpolator->addr); |
1da177e4c
|
1597 1598 |
case TIME_SOURCE_MMIO32 : |
685db65e4
|
1599 |
return readl_relaxed((void __iomem *)time_interpolator->addr); |
1da177e4c
|
1600 1601 1602 1603 |
default: return get_cycles(); } } |
486d46aef
|
1604 |
static inline u64 time_interpolator_get_counter(int writelock) |
1da177e4c
|
1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 |
{ unsigned int src = time_interpolator->source; if (time_interpolator->jitter) { u64 lcycle; u64 now; do { lcycle = time_interpolator->last_cycle; now = time_interpolator_get_cycles(src); if (lcycle && time_after(lcycle, now)) return lcycle; |
486d46aef
|
1618 1619 1620 1621 1622 1623 1624 1625 1626 |
/* When holding the xtime write lock, there's no need * to add the overhead of the cmpxchg. Readers are * force to retry until the write lock is released. */ if (writelock) { time_interpolator->last_cycle = now; return now; } |
1da177e4c
|
1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 |
/* Keep track of the last timer value returned. The use of cmpxchg here * will cause contention in an SMP environment. */ } while (unlikely(cmpxchg(&time_interpolator->last_cycle, lcycle, now) != lcycle)); return now; } else return time_interpolator_get_cycles(src); } void time_interpolator_reset(void) { time_interpolator->offset = 0; |
486d46aef
|
1640 |
time_interpolator->last_counter = time_interpolator_get_counter(1); |
1da177e4c
|
1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 |
} #define GET_TI_NSECS(count,i) (((((count) - i->last_counter) & (i)->mask) * (i)->nsec_per_cyc) >> (i)->shift) unsigned long time_interpolator_get_offset(void) { /* If we do not have a time interpolator set up then just return zero */ if (!time_interpolator) return 0; return time_interpolator->offset + |
486d46aef
|
1652 |
GET_TI_NSECS(time_interpolator_get_counter(0), time_interpolator); |
1da177e4c
|
1653 1654 1655 1656 |
} #define INTERPOLATOR_ADJUST 65536 #define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST |
4c7ee8de9
|
1657 |
void time_interpolator_update(long delta_nsec) |
1da177e4c
|
1658 1659 1660 1661 1662 1663 1664 |
{ u64 counter; unsigned long offset; /* If there is no time interpolator set up then do nothing */ if (!time_interpolator) return; |
a5a0d52c7
|
1665 1666 1667 1668 1669 1670 1671 1672 |
/* * The interpolator compensates for late ticks by accumulating the late * time in time_interpolator->offset. A tick earlier than expected will * lead to a reset of the offset and a corresponding jump of the clock * forward. Again this only works if the interpolator clock is running * slightly slower than the regular clock and the tuning logic insures * that. */ |
1da177e4c
|
1673 |
|
486d46aef
|
1674 |
counter = time_interpolator_get_counter(1); |
a5a0d52c7
|
1675 1676 |
offset = time_interpolator->offset + GET_TI_NSECS(counter, time_interpolator); |
1da177e4c
|
1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 |
if (delta_nsec < 0 || (unsigned long) delta_nsec < offset) time_interpolator->offset = offset - delta_nsec; else { time_interpolator->skips++; time_interpolator->ns_skipped += delta_nsec - offset; time_interpolator->offset = 0; } time_interpolator->last_counter = counter; /* Tuning logic for time interpolator invoked every minute or so. * Decrease interpolator clock speed if no skips occurred and an offset is carried. * Increase interpolator clock speed if we skip too much time. */ if (jiffies % INTERPOLATOR_ADJUST == 0) { |
b20367a6c
|
1693 |
if (time_interpolator->skips == 0 && time_interpolator->offset > tick_nsec) |
1da177e4c
|
1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 |
time_interpolator->nsec_per_cyc--; if (time_interpolator->ns_skipped > INTERPOLATOR_MAX_SKIP && time_interpolator->offset == 0) time_interpolator->nsec_per_cyc++; time_interpolator->skips = 0; time_interpolator->ns_skipped = 0; } } static inline int is_better_time_interpolator(struct time_interpolator *new) { if (!time_interpolator) return 1; return new->frequency > 2*time_interpolator->frequency || (unsigned long)new->drift < (unsigned long)time_interpolator->drift; } void register_time_interpolator(struct time_interpolator *ti) { unsigned long flags; /* Sanity check */ |
9f31252cb
|
1717 |
BUG_ON(ti->frequency == 0 || ti->mask == 0); |
1da177e4c
|
1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 |
ti->nsec_per_cyc = ((u64)NSEC_PER_SEC << ti->shift) / ti->frequency; spin_lock(&time_interpolator_lock); write_seqlock_irqsave(&xtime_lock, flags); if (is_better_time_interpolator(ti)) { time_interpolator = ti; time_interpolator_reset(); } write_sequnlock_irqrestore(&xtime_lock, flags); ti->next = time_interpolator_list; time_interpolator_list = ti; spin_unlock(&time_interpolator_lock); } void unregister_time_interpolator(struct time_interpolator *ti) { struct time_interpolator *curr, **prev; unsigned long flags; spin_lock(&time_interpolator_lock); prev = &time_interpolator_list; for (curr = *prev; curr; curr = curr->next) { if (curr == ti) { *prev = curr->next; break; } prev = &curr->next; } write_seqlock_irqsave(&xtime_lock, flags); if (ti == time_interpolator) { /* we lost the best time-interpolator: */ time_interpolator = NULL; /* find the next-best interpolator */ for (curr = time_interpolator_list; curr; curr = curr->next) if (is_better_time_interpolator(curr)) time_interpolator = curr; time_interpolator_reset(); } write_sequnlock_irqrestore(&xtime_lock, flags); spin_unlock(&time_interpolator_lock); } #endif /* CONFIG_TIME_INTERPOLATION */ /** * 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; |
75bcc8c5e
|
1771 1772 |
while (timeout) timeout = schedule_timeout_uninterruptible(timeout); |
1da177e4c
|
1773 1774 1775 1776 1777 |
} EXPORT_SYMBOL(msleep); /** |
96ec3efdc
|
1778 |
* msleep_interruptible - sleep waiting for signals |
1da177e4c
|
1779 1780 1781 1782 1783 |
* @msecs: Time in milliseconds to sleep for */ unsigned long msleep_interruptible(unsigned int msecs) { unsigned long timeout = msecs_to_jiffies(msecs) + 1; |
75bcc8c5e
|
1784 1785 |
while (timeout && !signal_pending(current)) timeout = schedule_timeout_interruptible(timeout); |
1da177e4c
|
1786 1787 1788 1789 |
return jiffies_to_msecs(timeout); } EXPORT_SYMBOL(msleep_interruptible); |