123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614 |
- /*
- * 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>
- #include <asm/uaccess.h>
- #include <asm/unistd.h>
- #include <asm/div64.h>
- #include <asm/timex.h>
- #include <asm/io.h>
- #ifdef CONFIG_TIME_INTERPOLATION
- static void time_interpolator_update(long delta_nsec);
- #else
- #define time_interpolator_update(x)
- #endif
- /*
- * 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)
- struct timer_base_s {
- spinlock_t lock;
- struct timer_list *running_timer;
- };
- 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 {
- struct timer_base_s t_base;
- unsigned long timer_jiffies;
- 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;
- static DEFINE_PER_CPU(tvec_base_t, tvec_bases);
- static inline void set_running_timer(tvec_base_t *base,
- struct timer_list *timer)
- {
- #ifdef CONFIG_SMP
- base->t_base.running_timer = timer;
- #endif
- }
- static void check_timer_failed(struct timer_list *timer)
- {
- static int whine_count;
- if (whine_count < 16) {
- whine_count++;
- printk("Uninitialised timer!\n");
- printk("This is just a warning. Your computer is OK\n");
- printk("function=0x%p, data=0x%lx\n",
- timer->function, timer->data);
- dump_stack();
- }
- /*
- * Now fix it up
- */
- timer->magic = TIMER_MAGIC;
- }
- static inline void check_timer(struct timer_list *timer)
- {
- if (timer->magic != TIMER_MAGIC)
- check_timer_failed(timer);
- }
- 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);
- }
- typedef struct timer_base_s timer_base_t;
- /*
- * Used by TIMER_INITIALIZER, we can't use per_cpu(tvec_bases)
- * at compile time, and we need timer->base to lock the timer.
- */
- timer_base_t __init_timer_base
- ____cacheline_aligned_in_smp = { .lock = SPIN_LOCK_UNLOCKED };
- EXPORT_SYMBOL(__init_timer_base);
- /***
- * 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;
- timer->base = &per_cpu(tvec_bases, raw_smp_processor_id()).t_base;
- timer->magic = TIMER_MAGIC;
- }
- 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;
- }
- /*
- * We are using hashed locking: holding per_cpu(tvec_bases).t_base.lock
- * 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.
- */
- static timer_base_t *lock_timer_base(struct timer_list *timer,
- unsigned long *flags)
- {
- timer_base_t *base;
- 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();
- }
- }
- int __mod_timer(struct timer_list *timer, unsigned long expires)
- {
- timer_base_t *base;
- tvec_base_t *new_base;
- unsigned long flags;
- int ret = 0;
- BUG_ON(!timer->function);
- check_timer(timer);
- base = lock_timer_base(timer, &flags);
- if (timer_pending(timer)) {
- detach_timer(timer, 0);
- ret = 1;
- }
- new_base = &__get_cpu_var(tvec_bases);
- if (base != &new_base->t_base) {
- /*
- * 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.
- */
- if (unlikely(base->running_timer == timer)) {
- /* The timer remains on a former base */
- new_base = container_of(base, tvec_base_t, t_base);
- } else {
- /* See the comment in lock_timer_base() */
- timer->base = NULL;
- spin_unlock(&base->lock);
- spin_lock(&new_base->t_base.lock);
- timer->base = &new_base->t_base;
- }
- }
- timer->expires = expires;
- internal_add_timer(new_base, timer);
- spin_unlock_irqrestore(&new_base->t_base.lock, flags);
- return ret;
- }
- EXPORT_SYMBOL(__mod_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)
- {
- tvec_base_t *base = &per_cpu(tvec_bases, cpu);
- unsigned long flags;
- BUG_ON(timer_pending(timer) || !timer->function);
- check_timer(timer);
- spin_lock_irqsave(&base->t_base.lock, flags);
- timer->base = &base->t_base;
- internal_add_timer(base, timer);
- spin_unlock_irqrestore(&base->t_base.lock, flags);
- }
- /***
- * mod_timer - modify a timer's timeout
- * @timer: the timer to be modified
- *
- * 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);
- check_timer(timer);
- /*
- * 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);
- /***
- * 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)
- {
- timer_base_t *base;
- unsigned long flags;
- int ret = 0;
- check_timer(timer);
- if (timer_pending(timer)) {
- base = lock_timer_base(timer, &flags);
- if (timer_pending(timer)) {
- detach_timer(timer, 1);
- ret = 1;
- }
- spin_unlock_irqrestore(&base->lock, flags);
- }
- return ret;
- }
- EXPORT_SYMBOL(del_timer);
- #ifdef CONFIG_SMP
- /*
- * 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)
- {
- timer_base_t *base;
- 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;
- }
- /***
- * 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
- * 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.
- *
- * The function returns whether it has deactivated a pending timer or not.
- */
- int del_timer_sync(struct timer_list *timer)
- {
- check_timer(timer);
- for (;;) {
- int ret = try_to_del_timer_sync(timer);
- if (ret >= 0)
- return ret;
- }
- }
- EXPORT_SYMBOL(del_timer_sync);
- #endif
- static int cascade(tvec_base_t *base, tvec_t *tv, int index)
- {
- /* cascade all the timers from tv up one level */
- struct list_head *head, *curr;
- head = tv->vec + index;
- curr = head->next;
- /*
- * We are removing _all_ timers from the list, so we don't have to
- * detach them individually, just clear the list afterwards.
- */
- while (curr != head) {
- struct timer_list *tmp;
- tmp = list_entry(curr, struct timer_list, entry);
- BUG_ON(tmp->base != &base->t_base);
- curr = curr->next;
- internal_add_timer(base, tmp);
- }
- INIT_LIST_HEAD(head);
- return index;
- }
- /***
- * __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.
- */
- #define INDEX(N) (base->timer_jiffies >> (TVR_BITS + N * TVN_BITS)) & TVN_MASK
- static inline void __run_timers(tvec_base_t *base)
- {
- struct timer_list *timer;
- spin_lock_irq(&base->t_base.lock);
- while (time_after_eq(jiffies, base->timer_jiffies)) {
- struct list_head work_list = LIST_HEAD_INIT(work_list);
- struct list_head *head = &work_list;
- int index = base->timer_jiffies & TVR_MASK;
-
- /*
- * 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));
- ++base->timer_jiffies;
- list_splice_init(base->tv1.vec + index, &work_list);
- while (!list_empty(head)) {
- void (*fn)(unsigned long);
- unsigned long data;
- timer = list_entry(head->next,struct timer_list,entry);
- fn = timer->function;
- data = timer->data;
- set_running_timer(base, timer);
- detach_timer(timer, 1);
- spin_unlock_irq(&base->t_base.lock);
- {
- int preempt_count = preempt_count();
- fn(data);
- if (preempt_count != preempt_count()) {
- printk(KERN_WARNING "huh, entered %p "
- "with preempt_count %08x, exited"
- " with %08x?\n",
- fn, preempt_count,
- preempt_count());
- BUG();
- }
- }
- spin_lock_irq(&base->t_base.lock);
- }
- }
- set_running_timer(base, NULL);
- spin_unlock_irq(&base->t_base.lock);
- }
- #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;
- tvec_t *varray[4];
- int i, j;
- base = &__get_cpu_var(tvec_bases);
- spin_lock(&base->t_base.lock);
- expires = base->timer_jiffies + (LONG_MAX >> 1);
- list = 0;
- /* 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;
- }
- }
- spin_unlock(&base->t_base.lock);
- return expires;
- }
- #endif
- /******************************************************************/
- /*
- * Timekeeping variables
- */
- unsigned long tick_usec = TICK_USEC; /* USER_HZ period (usec) */
- unsigned long tick_nsec = TICK_NSEC; /* ACTHZ period (nsec) */
- /*
- * 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);
- /* Don't completely fail for HZ > 500. */
- int tickadj = 500/HZ ? : 1; /* microsecs */
- /*
- * phase-lock loop variables
- */
- /* TIME_ERROR prevents overwriting the CMOS clock */
- int time_state = TIME_OK; /* clock synchronization status */
- int time_status = STA_UNSYNC; /* clock status bits */
- long time_offset; /* time adjustment (us) */
- long time_constant = 2; /* pll time constant */
- long time_tolerance = MAXFREQ; /* frequency tolerance (ppm) */
- long time_precision = 1; /* clock precision (us) */
- long time_maxerror = NTP_PHASE_LIMIT; /* maximum error (us) */
- long time_esterror = NTP_PHASE_LIMIT; /* estimated error (us) */
- static long time_phase; /* phase offset (scaled us) */
- long time_freq = (((NSEC_PER_SEC + HZ/2) % HZ - HZ/2) << SHIFT_USEC) / NSEC_PER_USEC;
- /* frequency offset (scaled ppm)*/
- static long time_adj; /* tick adjust (scaled 1 / HZ) */
- long time_reftime; /* time at last adjustment (s) */
- long time_adjust;
- long time_next_adjust;
- /*
- * this routine handles the overflow of the microsecond field
- *
- * The tricky bits of code to handle the accurate clock support
- * were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
- * They were originally developed for SUN and DEC kernels.
- * All the kudos should go to Dave for this stuff.
- *
- */
- static void second_overflow(void)
- {
- long ltemp;
- /* Bump the maxerror field */
- time_maxerror += time_tolerance >> SHIFT_USEC;
- if ( time_maxerror > NTP_PHASE_LIMIT ) {
- time_maxerror = NTP_PHASE_LIMIT;
- time_status |= STA_UNSYNC;
- }
- /*
- * Leap second processing. If in leap-insert state at
- * the end of the day, the system clock is set back one
- * second; if in leap-delete state, the system clock is
- * set ahead one second. The microtime() routine or
- * external clock driver will insure that reported time
- * is always monotonic. The ugly divides should be
- * replaced.
- */
- switch (time_state) {
- case TIME_OK:
- if (time_status & STA_INS)
- time_state = TIME_INS;
- else if (time_status & STA_DEL)
- time_state = TIME_DEL;
- break;
- case TIME_INS:
- if (xtime.tv_sec % 86400 == 0) {
- xtime.tv_sec--;
- wall_to_monotonic.tv_sec++;
- /* The timer interpolator will make time change gradually instead
- * of an immediate jump by one second.
- */
- time_interpolator_update(-NSEC_PER_SEC);
- time_state = TIME_OOP;
- clock_was_set();
- printk(KERN_NOTICE "Clock: inserting leap second 23:59:60 UTC\n");
- }
- break;
- case TIME_DEL:
- if ((xtime.tv_sec + 1) % 86400 == 0) {
- xtime.tv_sec++;
- wall_to_monotonic.tv_sec--;
- /* Use of time interpolator for a gradual change of time */
- time_interpolator_update(NSEC_PER_SEC);
- time_state = TIME_WAIT;
- clock_was_set();
- printk(KERN_NOTICE "Clock: deleting leap second 23:59:59 UTC\n");
- }
- break;
- case TIME_OOP:
- time_state = TIME_WAIT;
- break;
- case TIME_WAIT:
- if (!(time_status & (STA_INS | STA_DEL)))
- time_state = TIME_OK;
- }
- /*
- * Compute the phase adjustment for the next second. In
- * PLL mode, the offset is reduced by a fixed factor
- * times the time constant. In FLL mode the offset is
- * used directly. In either mode, the maximum phase
- * adjustment for each second is clamped so as to spread
- * the adjustment over not more than the number of
- * seconds between updates.
- */
- if (time_offset < 0) {
- ltemp = -time_offset;
- if (!(time_status & STA_FLL))
- ltemp >>= SHIFT_KG + time_constant;
- if (ltemp > (MAXPHASE / MINSEC) << SHIFT_UPDATE)
- ltemp = (MAXPHASE / MINSEC) << SHIFT_UPDATE;
- time_offset += ltemp;
- time_adj = -ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE);
- } else {
- ltemp = time_offset;
- if (!(time_status & STA_FLL))
- ltemp >>= SHIFT_KG + time_constant;
- if (ltemp > (MAXPHASE / MINSEC) << SHIFT_UPDATE)
- ltemp = (MAXPHASE / MINSEC) << SHIFT_UPDATE;
- time_offset -= ltemp;
- time_adj = ltemp << (SHIFT_SCALE - SHIFT_HZ - SHIFT_UPDATE);
- }
- /*
- * Compute the frequency estimate and additional phase
- * adjustment due to frequency error for the next
- * second. When the PPS signal is engaged, gnaw on the
- * watchdog counter and update the frequency computed by
- * the pll and the PPS signal.
- */
- pps_valid++;
- if (pps_valid == PPS_VALID) { /* PPS signal lost */
- pps_jitter = MAXTIME;
- pps_stabil = MAXFREQ;
- time_status &= ~(STA_PPSSIGNAL | STA_PPSJITTER |
- STA_PPSWANDER | STA_PPSERROR);
- }
- ltemp = time_freq + pps_freq;
- if (ltemp < 0)
- time_adj -= -ltemp >>
- (SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE);
- else
- time_adj += ltemp >>
- (SHIFT_USEC + SHIFT_HZ - SHIFT_SCALE);
- #if HZ == 100
- /* Compensate for (HZ==100) != (1 << SHIFT_HZ).
- * Add 25% and 3.125% to get 128.125; => only 0.125% error (p. 14)
- */
- if (time_adj < 0)
- time_adj -= (-time_adj >> 2) + (-time_adj >> 5);
- else
- time_adj += (time_adj >> 2) + (time_adj >> 5);
- #endif
- #if HZ == 1000
- /* Compensate for (HZ==1000) != (1 << SHIFT_HZ).
- * Add 1.5625% and 0.78125% to get 1023.4375; => only 0.05% error (p. 14)
- */
- if (time_adj < 0)
- time_adj -= (-time_adj >> 6) + (-time_adj >> 7);
- else
- time_adj += (time_adj >> 6) + (time_adj >> 7);
- #endif
- }
- /* in the NTP reference this is called "hardclock()" */
- static void update_wall_time_one_tick(void)
- {
- long time_adjust_step, delta_nsec;
- if ( (time_adjust_step = time_adjust) != 0 ) {
- /* We are doing an adjtime thing.
- *
- * Prepare time_adjust_step to be within bounds.
- * Note that a positive time_adjust means we want the clock
- * to run faster.
- *
- * Limit the amount of the step to be in the range
- * -tickadj .. +tickadj
- */
- if (time_adjust > tickadj)
- time_adjust_step = tickadj;
- else if (time_adjust < -tickadj)
- time_adjust_step = -tickadj;
- /* Reduce by this step the amount of time left */
- time_adjust -= time_adjust_step;
- }
- delta_nsec = tick_nsec + time_adjust_step * 1000;
- /*
- * Advance the phase, once it gets to one microsecond, then
- * advance the tick more.
- */
- time_phase += time_adj;
- if (time_phase <= -FINENSEC) {
- long ltemp = -time_phase >> (SHIFT_SCALE - 10);
- time_phase += ltemp << (SHIFT_SCALE - 10);
- delta_nsec -= ltemp;
- }
- else if (time_phase >= FINENSEC) {
- long ltemp = time_phase >> (SHIFT_SCALE - 10);
- time_phase -= ltemp << (SHIFT_SCALE - 10);
- delta_nsec += ltemp;
- }
- xtime.tv_nsec += delta_nsec;
- time_interpolator_update(delta_nsec);
- /* Changes by adjtime() do not take effect till next tick. */
- if (time_next_adjust != 0) {
- time_adjust = time_next_adjust;
- time_next_adjust = 0;
- }
- }
- /*
- * Using a loop looks inefficient, but "ticks" is
- * usually just one (we shouldn't be losing ticks,
- * we're doing this this way mainly for interrupt
- * latency reasons, not because we think we'll
- * have lots of lost timer ticks
- */
- static void update_wall_time(unsigned long ticks)
- {
- do {
- ticks--;
- update_wall_time_one_tick();
- if (xtime.tv_nsec >= 1000000000) {
- xtime.tv_nsec -= 1000000000;
- xtime.tv_sec++;
- second_overflow();
- }
- } while (ticks);
- }
- /*
- * 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)
- {
- return (nr_running() + nr_uninterruptible()) * FIXED_1;
- }
- /*
- * 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;
- count -= ticks;
- if (count < 0) {
- count += LOAD_FREQ;
- active_tasks = count_active_tasks();
- CALC_LOAD(avenrun[0], EXP_1, active_tasks);
- CALC_LOAD(avenrun[1], EXP_5, active_tasks);
- CALC_LOAD(avenrun[2], EXP_15, active_tasks);
- }
- }
- /* jiffies at the most recent update of wall time */
- unsigned long wall_jiffies = INITIAL_JIFFIES;
- /*
- * This read-write spinlock protects us from races in SMP while
- * playing with xtime and avenrun.
- */
- #ifndef ARCH_HAVE_XTIME_LOCK
- seqlock_t xtime_lock __cacheline_aligned_in_smp = SEQLOCK_UNLOCKED;
- 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)
- {
- tvec_base_t *base = &__get_cpu_var(tvec_bases);
- 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);
- }
- /*
- * Called by the timer interrupt. xtime_lock must already be taken
- * by the timer IRQ!
- */
- static inline void update_times(void)
- {
- unsigned long ticks;
- ticks = jiffies - wall_jiffies;
- if (ticks) {
- wall_jiffies += ticks;
- update_wall_time(ticks);
- }
- 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...
- */
- void do_timer(struct pt_regs *regs)
- {
- jiffies_64++;
- update_times();
- }
- #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)
- {
- struct itimerval it_new, it_old;
- unsigned int oldalarm;
- it_new.it_interval.tv_sec = it_new.it_interval.tv_usec = 0;
- it_new.it_value.tv_sec = seconds;
- it_new.it_value.tv_usec = 0;
- do_setitimer(ITIMER_REAL, &it_new, &it_old);
- oldalarm = it_old.it_value.tv_sec;
- /* ehhh.. We can't return 0 if we have an alarm pending.. */
- /* And we'd better return too much than too little anyway */
- if ((!oldalarm && it_old.it_value.tv_usec) || it_old.it_value.tv_usec >= 500000)
- oldalarm++;
- return oldalarm;
- }
- #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;
- }
- /*
- * Accessing ->group_leader->real_parent is not SMP-safe, it could
- * change from under us. However, rather than getting any lock
- * we can use an optimistic algorithm: get the parent
- * pid, and go back and check that the parent is still
- * the same. If it has changed (which is extremely unlikely
- * indeed), we just try again..
- *
- * NOTE! This depends on the fact that even if we _do_
- * get an old value of "parent", we can happily dereference
- * the pointer (it was and remains a dereferencable kernel pointer
- * no matter what): we just can't necessarily trust the result
- * until we know that the parent pointer is valid.
- *
- * NOTE2: ->group_leader never changes from under us.
- */
- asmlinkage long sys_getppid(void)
- {
- int pid;
- struct task_struct *me = current;
- struct task_struct *parent;
- parent = me->group_leader->real_parent;
- for (;;) {
- pid = parent->tgid;
- #ifdef CONFIG_SMP
- {
- struct task_struct *old = parent;
- /*
- * Make sure we read the pid before re-reading the
- * parent pointer:
- */
- smp_rmb();
- parent = me->group_leader->real_parent;
- if (old != parent)
- continue;
- }
- #endif
- break;
- }
- 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)
- {
- wake_up_process((task_t *)__data);
- }
- /**
- * 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.
- */
- if (timeout < 0)
- {
- printk(KERN_ERR "schedule_timeout: wrong timeout "
- "value %lx from %p\n", timeout,
- __builtin_return_address(0));
- current->state = TASK_RUNNING;
- goto out;
- }
- }
- expire = timeout + jiffies;
- init_timer(&timer);
- timer.expires = expire;
- timer.data = (unsigned long) current;
- timer.function = process_timeout;
- add_timer(&timer);
- schedule();
- del_singleshot_timer_sync(&timer);
- timeout = expire - jiffies;
- out:
- return timeout < 0 ? 0 : timeout;
- }
- EXPORT_SYMBOL(schedule_timeout);
- /* Thread ID - the internal kernel "pid" */
- asmlinkage long sys_gettid(void)
- {
- return current->pid;
- }
- static long __sched nanosleep_restart(struct restart_block *restart)
- {
- unsigned long expire = restart->arg0, now = jiffies;
- struct timespec __user *rmtp = (struct timespec __user *) restart->arg1;
- long ret;
- /* Did it expire while we handled signals? */
- if (!time_after(expire, now))
- return 0;
- current->state = TASK_INTERRUPTIBLE;
- expire = schedule_timeout(expire - now);
- ret = 0;
- if (expire) {
- struct timespec t;
- jiffies_to_timespec(expire, &t);
- ret = -ERESTART_RESTARTBLOCK;
- if (rmtp && copy_to_user(rmtp, &t, sizeof(t)))
- ret = -EFAULT;
- /* The 'restart' block is already filled in */
- }
- return ret;
- }
- asmlinkage long sys_nanosleep(struct timespec __user *rqtp, struct timespec __user *rmtp)
- {
- struct timespec t;
- unsigned long expire;
- long ret;
- if (copy_from_user(&t, rqtp, sizeof(t)))
- return -EFAULT;
- if ((t.tv_nsec >= 1000000000L) || (t.tv_nsec < 0) || (t.tv_sec < 0))
- return -EINVAL;
- expire = timespec_to_jiffies(&t) + (t.tv_sec || t.tv_nsec);
- current->state = TASK_INTERRUPTIBLE;
- expire = schedule_timeout(expire);
- ret = 0;
- if (expire) {
- struct restart_block *restart;
- jiffies_to_timespec(expire, &t);
- if (rmtp && copy_to_user(rmtp, &t, sizeof(t)))
- return -EFAULT;
- restart = ¤t_thread_info()->restart_block;
- restart->fn = nanosleep_restart;
- restart->arg0 = jiffies + expire;
- restart->arg1 = (unsigned long) rmtp;
- ret = -ERESTART_RESTARTBLOCK;
- }
- return ret;
- }
- /*
- * sys_sysinfo - fill in sysinfo struct
- */
- 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;
- }
- static void __devinit init_timers_cpu(int cpu)
- {
- int j;
- tvec_base_t *base;
- base = &per_cpu(tvec_bases, cpu);
- spin_lock_init(&base->t_base.lock);
- 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;
- }
- #ifdef CONFIG_HOTPLUG_CPU
- static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head)
- {
- struct timer_list *timer;
- while (!list_empty(head)) {
- timer = list_entry(head->next, struct timer_list, entry);
- detach_timer(timer, 0);
- timer->base = &new_base->t_base;
- internal_add_timer(new_base, timer);
- }
- }
- static void __devinit migrate_timers(int cpu)
- {
- tvec_base_t *old_base;
- tvec_base_t *new_base;
- int i;
- BUG_ON(cpu_online(cpu));
- old_base = &per_cpu(tvec_bases, cpu);
- new_base = &get_cpu_var(tvec_bases);
- local_irq_disable();
- spin_lock(&new_base->t_base.lock);
- spin_lock(&old_base->t_base.lock);
- if (old_base->t_base.running_timer)
- BUG();
- for (i = 0; i < TVR_SIZE; i++)
- 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);
- }
- spin_unlock(&old_base->t_base.lock);
- spin_unlock(&new_base->t_base.lock);
- local_irq_enable();
- put_cpu_var(tvec_bases);
- }
- #endif /* CONFIG_HOTPLUG_CPU */
- static int __devinit timer_cpu_notify(struct notifier_block *self,
- unsigned long action, void *hcpu)
- {
- long cpu = (long)hcpu;
- switch(action) {
- case CPU_UP_PREPARE:
- init_timers_cpu(cpu);
- break;
- #ifdef CONFIG_HOTPLUG_CPU
- case CPU_DEAD:
- migrate_timers(cpu);
- break;
- #endif
- default:
- break;
- }
- return NOTIFY_OK;
- }
- static struct notifier_block __devinitdata timers_nb = {
- .notifier_call = timer_cpu_notify,
- };
- void __init init_timers(void)
- {
- timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
- (void *)(long)smp_processor_id());
- register_cpu_notifier(&timers_nb);
- open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
- }
- #ifdef CONFIG_TIME_INTERPOLATION
- struct time_interpolator *time_interpolator;
- static struct time_interpolator *time_interpolator_list;
- 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 :
- return readq((void __iomem *) time_interpolator->addr);
- case TIME_SOURCE_MMIO32 :
- return readl((void __iomem *) time_interpolator->addr);
- default: return get_cycles();
- }
- }
- static inline u64 time_interpolator_get_counter(void)
- {
- 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;
- /* 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;
- time_interpolator->last_counter = time_interpolator_get_counter();
- }
- #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 +
- GET_TI_NSECS(time_interpolator_get_counter(), time_interpolator);
- }
- #define INTERPOLATOR_ADJUST 65536
- #define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST
- static void time_interpolator_update(long delta_nsec)
- {
- u64 counter;
- unsigned long offset;
- /* If there is no time interpolator set up then do nothing */
- if (!time_interpolator)
- return;
- /* 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.
- */
- counter = time_interpolator_get_counter();
- offset = time_interpolator->offset + GET_TI_NSECS(counter, time_interpolator);
- 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)
- {
- if (time_interpolator->skips == 0 && time_interpolator->offset > TICK_NSEC)
- 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 */
- if (ti->frequency == 0 || ti->mask == 0)
- BUG();
- 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;
- while (timeout) {
- set_current_state(TASK_UNINTERRUPTIBLE);
- timeout = schedule_timeout(timeout);
- }
- }
- EXPORT_SYMBOL(msleep);
- /**
- * msleep_interruptible - sleep waiting for signals
- * @msecs: Time in milliseconds to sleep for
- */
- unsigned long msleep_interruptible(unsigned int msecs)
- {
- unsigned long timeout = msecs_to_jiffies(msecs) + 1;
- while (timeout && !signal_pending(current)) {
- set_current_state(TASK_INTERRUPTIBLE);
- timeout = schedule_timeout(timeout);
- }
- return jiffies_to_msecs(timeout);
- }
- EXPORT_SYMBOL(msleep_interruptible);
|