android_kernel_xiaomi_sm8350/kernel/timer.c
Michael Neuling c66f08be7e Add scaled time to taskstats based process accounting
This adds items to the taststats struct to account for user and system
time based on scaling the CPU frequency and instruction issue rates.

Adds account_(user|system)_time_scaled callbacks which architectures
can use to account for time using this mechanism.

Signed-off-by: Michael Neuling <mikey@neuling.org>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-10-18 14:37:28 -07:00

1383 lines
36 KiB
C

/*
* linux/kernel/timer.c
*
* Kernel internal timers, 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 <linux/delay.h>
#include <linux/tick.h>
#include <linux/kallsyms.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/div64.h>
#include <asm/timex.h>
#include <asm/io.h>
u64 jiffies_64 __cacheline_aligned_in_smp = INITIAL_JIFFIES;
EXPORT_SYMBOL(jiffies_64);
/*
* 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)
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 {
spinlock_t lock;
struct timer_list *running_timer;
unsigned long timer_jiffies;
tvec_root_t tv1;
tvec_t tv2;
tvec_t tv3;
tvec_t tv4;
tvec_t tv5;
} ____cacheline_aligned;
typedef struct tvec_t_base_s tvec_base_t;
tvec_base_t boot_tvec_bases;
EXPORT_SYMBOL(boot_tvec_bases);
static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = &boot_tvec_bases;
/*
* Note that all tvec_bases is 2 byte aligned and lower bit of
* base in timer_list is guaranteed to be zero. Use the LSB for
* the new flag to indicate whether the timer is deferrable
*/
#define TBASE_DEFERRABLE_FLAG (0x1)
/* Functions below help us manage 'deferrable' flag */
static inline unsigned int tbase_get_deferrable(tvec_base_t *base)
{
return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG);
}
static inline tvec_base_t *tbase_get_base(tvec_base_t *base)
{
return ((tvec_base_t *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG));
}
static inline void timer_set_deferrable(struct timer_list *timer)
{
timer->base = ((tvec_base_t *)((unsigned long)(timer->base) |
TBASE_DEFERRABLE_FLAG));
}
static inline void
timer_set_base(struct timer_list *timer, tvec_base_t *new_base)
{
timer->base = (tvec_base_t *)((unsigned long)(new_base) |
tbase_get_deferrable(timer->base));
}
/**
* __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);
static inline void set_running_timer(tvec_base_t *base,
struct timer_list *timer)
{
#ifdef CONFIG_SMP
base->running_timer = timer;
#endif
}
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);
}
#ifdef CONFIG_TIMER_STATS
void __timer_stats_timer_set_start_info(struct timer_list *timer, void *addr)
{
if (timer->start_site)
return;
timer->start_site = addr;
memcpy(timer->start_comm, current->comm, TASK_COMM_LEN);
timer->start_pid = current->pid;
}
static void timer_stats_account_timer(struct timer_list *timer)
{
unsigned int flag = 0;
if (unlikely(tbase_get_deferrable(timer->base)))
flag |= TIMER_STATS_FLAG_DEFERRABLE;
timer_stats_update_stats(timer, timer->start_pid, timer->start_site,
timer->function, timer->start_comm, flag);
}
#else
static void timer_stats_account_timer(struct timer_list *timer) {}
#endif
/**
* 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 = __raw_get_cpu_var(tvec_bases);
#ifdef CONFIG_TIMER_STATS
timer->start_site = NULL;
timer->start_pid = -1;
memset(timer->start_comm, 0, TASK_COMM_LEN);
#endif
}
EXPORT_SYMBOL(init_timer);
void fastcall init_timer_deferrable(struct timer_list *timer)
{
init_timer(timer);
timer_set_deferrable(timer);
}
EXPORT_SYMBOL(init_timer_deferrable);
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).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 tvec_base_t *lock_timer_base(struct timer_list *timer,
unsigned long *flags)
__acquires(timer->base->lock)
{
tvec_base_t *base;
for (;;) {
tvec_base_t *prelock_base = timer->base;
base = tbase_get_base(prelock_base);
if (likely(base != NULL)) {
spin_lock_irqsave(&base->lock, *flags);
if (likely(prelock_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)
{
tvec_base_t *base, *new_base;
unsigned long flags;
int ret = 0;
timer_stats_timer_set_start_info(timer);
BUG_ON(!timer->function);
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) {
/*
* 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 (likely(base->running_timer != timer)) {
/* See the comment in lock_timer_base() */
timer_set_base(timer, NULL);
spin_unlock(&base->lock);
base = new_base;
spin_lock(&base->lock);
timer_set_base(timer, base);
}
}
timer->expires = expires;
internal_add_timer(base, timer);
spin_unlock_irqrestore(&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;
timer_stats_timer_set_start_info(timer);
BUG_ON(timer_pending(timer) || !timer->function);
spin_lock_irqsave(&base->lock, flags);
timer_set_base(timer, base);
internal_add_timer(base, timer);
spin_unlock_irqrestore(&base->lock, flags);
}
/**
* mod_timer - modify a timer's timeout
* @timer: the timer to be modified
* @expires: new timeout in jiffies
*
* 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);
timer_stats_timer_set_start_info(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)
{
tvec_base_t *base;
unsigned long flags;
int ret = 0;
timer_stats_timer_clear_start_info(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
/**
* try_to_del_timer_sync - Try to deactivate a timer
* @timer: timer do del
*
* 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)
{
tvec_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;
}
EXPORT_SYMBOL(try_to_del_timer_sync);
/**
* 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)
{
for (;;) {
int ret = try_to_del_timer_sync(timer);
if (ret >= 0)
return ret;
cpu_relax();
}
}
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 timer_list *timer, *tmp;
struct list_head tv_list;
list_replace_init(tv->vec + index, &tv_list);
/*
* We are removing _all_ timers from the list, so we
* don't have to detach them individually.
*/
list_for_each_entry_safe(timer, tmp, &tv_list, entry) {
BUG_ON(tbase_get_base(timer->base) != base);
internal_add_timer(base, timer);
}
return index;
}
#define INDEX(N) ((base->timer_jiffies >> (TVR_BITS + (N) * TVN_BITS)) & TVN_MASK)
/**
* __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.
*/
static inline void __run_timers(tvec_base_t *base)
{
struct timer_list *timer;
spin_lock_irq(&base->lock);
while (time_after_eq(jiffies, base->timer_jiffies)) {
struct list_head 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_replace_init(base->tv1.vec + index, &work_list);
while (!list_empty(head)) {
void (*fn)(unsigned long);
unsigned long data;
timer = list_first_entry(head, struct timer_list,entry);
fn = timer->function;
data = timer->data;
timer_stats_account_timer(timer);
set_running_timer(base, timer);
detach_timer(timer, 1);
spin_unlock_irq(&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->lock);
}
}
set_running_timer(base, NULL);
spin_unlock_irq(&base->lock);
}
#if defined(CONFIG_NO_IDLE_HZ) || defined(CONFIG_NO_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.
*/
static unsigned long __next_timer_interrupt(tvec_base_t *base)
{
unsigned long timer_jiffies = base->timer_jiffies;
unsigned long expires = timer_jiffies + NEXT_TIMER_MAX_DELTA;
int index, slot, array, found = 0;
struct timer_list *nte;
tvec_t *varray[4];
/* Look for timer events in tv1. */
index = slot = timer_jiffies & TVR_MASK;
do {
list_for_each_entry(nte, base->tv1.vec + slot, entry) {
if (tbase_get_deferrable(nte->base))
continue;
found = 1;
expires = nte->expires;
/* Look at the cascade bucket(s)? */
if (!index || slot < index)
goto cascade;
return expires;
}
slot = (slot + 1) & TVR_MASK;
} while (slot != index);
cascade:
/* Calculate the next cascade event */
if (index)
timer_jiffies += TVR_SIZE - index;
timer_jiffies >>= TVR_BITS;
/* Check tv2-tv5. */
varray[0] = &base->tv2;
varray[1] = &base->tv3;
varray[2] = &base->tv4;
varray[3] = &base->tv5;
for (array = 0; array < 4; array++) {
tvec_t *varp = varray[array];
index = slot = timer_jiffies & TVN_MASK;
do {
list_for_each_entry(nte, varp->vec + slot, entry) {
found = 1;
if (time_before(nte->expires, expires))
expires = nte->expires;
}
/*
* Do we still search for the first timer or are
* we looking up the cascade buckets ?
*/
if (found) {
/* Look at the cascade bucket(s)? */
if (!index || slot < index)
break;
return expires;
}
slot = (slot + 1) & TVN_MASK;
} while (slot != index);
if (index)
timer_jiffies += TVN_SIZE - index;
timer_jiffies >>= TVN_BITS;
}
return expires;
}
/*
* Check, if the next hrtimer event is before the next timer wheel
* event:
*/
static unsigned long cmp_next_hrtimer_event(unsigned long now,
unsigned long expires)
{
ktime_t hr_delta = hrtimer_get_next_event();
struct timespec tsdelta;
unsigned long delta;
if (hr_delta.tv64 == KTIME_MAX)
return expires;
/*
* Expired timer available, let it expire in the next tick
*/
if (hr_delta.tv64 <= 0)
return now + 1;
tsdelta = ktime_to_timespec(hr_delta);
delta = timespec_to_jiffies(&tsdelta);
/*
* Limit the delta to the max value, which is checked in
* tick_nohz_stop_sched_tick():
*/
if (delta > NEXT_TIMER_MAX_DELTA)
delta = NEXT_TIMER_MAX_DELTA;
/*
* Take rounding errors in to account and make sure, that it
* expires in the next tick. Otherwise we go into an endless
* ping pong due to tick_nohz_stop_sched_tick() retriggering
* the timer softirq
*/
if (delta < 1)
delta = 1;
now += delta;
if (time_before(now, expires))
return now;
return expires;
}
/**
* next_timer_interrupt - return the jiffy of the next pending timer
* @now: current time (in jiffies)
*/
unsigned long get_next_timer_interrupt(unsigned long now)
{
tvec_base_t *base = __get_cpu_var(tvec_bases);
unsigned long expires;
spin_lock(&base->lock);
expires = __next_timer_interrupt(base);
spin_unlock(&base->lock);
if (time_before_eq(expires, now))
return now;
return cmp_next_hrtimer_event(now, expires);
}
#ifdef CONFIG_NO_IDLE_HZ
unsigned long next_timer_interrupt(void)
{
return get_next_timer_interrupt(jiffies);
}
#endif
#endif
/*
* 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));
account_user_time_scaled(p, jiffies_to_cputime(1));
} else {
account_system_time(p, HARDIRQ_OFFSET, jiffies_to_cputime(1));
account_system_time_scaled(p, 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_active() * 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 (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);
}
}
/*
* 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);
hrtimer_run_queues();
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);
softlockup_tick();
}
/*
* Called by the timer interrupt. xtime_lock must already be taken
* by the timer IRQ!
*/
static inline void update_times(unsigned long ticks)
{
update_wall_time();
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(unsigned long ticks)
{
jiffies_64 += ticks;
update_times(ticks);
}
#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)
{
return alarm_setitimer(seconds);
}
#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 ->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).
*/
asmlinkage long sys_getppid(void)
{
int pid;
rcu_read_lock();
pid = rcu_dereference(current->real_parent)->tgid;
rcu_read_unlock();
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((struct task_struct *)__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\n", timeout);
dump_stack();
current->state = TASK_RUNNING;
goto out;
}
}
expire = timeout + jiffies;
setup_timer(&timer, process_timeout, (unsigned long)current);
__mod_timer(&timer, expire);
schedule();
del_singleshot_timer_sync(&timer);
timeout = expire - jiffies;
out:
return timeout < 0 ? 0 : timeout;
}
EXPORT_SYMBOL(schedule_timeout);
/*
* We can use __set_current_state() here because schedule_timeout() calls
* schedule() unconditionally.
*/
signed long __sched schedule_timeout_interruptible(signed long timeout)
{
__set_current_state(TASK_INTERRUPTIBLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_interruptible);
signed long __sched schedule_timeout_uninterruptible(signed long timeout)
{
__set_current_state(TASK_UNINTERRUPTIBLE);
return schedule_timeout(timeout);
}
EXPORT_SYMBOL(schedule_timeout_uninterruptible);
/* Thread ID - the internal kernel "pid" */
asmlinkage long sys_gettid(void)
{
return current->pid;
}
/**
* do_sysinfo - fill in sysinfo struct
* @info: pointer to buffer to fill
*/
int do_sysinfo(struct sysinfo *info)
{
unsigned long mem_total, sav_total;
unsigned int mem_unit, bitcount;
unsigned long seq;
memset(info, 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;
monotonic_to_bootbased(&tp);
if (tp.tv_nsec - NSEC_PER_SEC >= 0) {
tp.tv_nsec = tp.tv_nsec - NSEC_PER_SEC;
tp.tv_sec++;
}
info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
info->loads[0] = avenrun[0] << (SI_LOAD_SHIFT - FSHIFT);
info->loads[1] = avenrun[1] << (SI_LOAD_SHIFT - FSHIFT);
info->loads[2] = avenrun[2] << (SI_LOAD_SHIFT - FSHIFT);
info->procs = nr_threads;
} while (read_seqretry(&xtime_lock, seq));
si_meminfo(info);
si_swapinfo(info);
/*
* 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 = info->totalram + info->totalswap;
if (mem_total < info->totalram || mem_total < info->totalswap)
goto out;
bitcount = 0;
mem_unit = info->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
* info->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...
*/
info->mem_unit = 1;
info->totalram <<= bitcount;
info->freeram <<= bitcount;
info->sharedram <<= bitcount;
info->bufferram <<= bitcount;
info->totalswap <<= bitcount;
info->freeswap <<= bitcount;
info->totalhigh <<= bitcount;
info->freehigh <<= bitcount;
out:
return 0;
}
asmlinkage long sys_sysinfo(struct sysinfo __user *info)
{
struct sysinfo val;
do_sysinfo(&val);
if (copy_to_user(info, &val, sizeof(struct sysinfo)))
return -EFAULT;
return 0;
}
/*
* 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];
static int __devinit init_timers_cpu(int cpu)
{
int j;
tvec_base_t *base;
static char __devinitdata tvec_base_done[NR_CPUS];
if (!tvec_base_done[cpu]) {
static char boot_done;
if (boot_done) {
/*
* The APs use this path later in boot
*/
base = kmalloc_node(sizeof(*base),
GFP_KERNEL | __GFP_ZERO,
cpu_to_node(cpu));
if (!base)
return -ENOMEM;
/* Make sure that tvec_base is 2 byte aligned */
if (tbase_get_deferrable(base)) {
WARN_ON(1);
kfree(base);
return -ENOMEM;
}
per_cpu(tvec_bases, cpu) = base;
} else {
/*
* 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.
*/
boot_done = 1;
base = &boot_tvec_bases;
}
tvec_base_done[cpu] = 1;
} else {
base = per_cpu(tvec_bases, cpu);
}
spin_lock_init(&base->lock);
lockdep_set_class(&base->lock, base_lock_keys + cpu);
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;
return 0;
}
#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_first_entry(head, struct timer_list, entry);
detach_timer(timer, 0);
timer_set_base(timer, new_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();
double_spin_lock(&new_base->lock, &old_base->lock,
smp_processor_id() < cpu);
BUG_ON(old_base->running_timer);
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);
}
double_spin_unlock(&new_base->lock, &old_base->lock,
smp_processor_id() < cpu);
local_irq_enable();
put_cpu_var(tvec_bases);
}
#endif /* CONFIG_HOTPLUG_CPU */
static int __cpuinit timer_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
switch(action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
if (init_timers_cpu(cpu) < 0)
return NOTIFY_BAD;
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DEAD:
case CPU_DEAD_FROZEN:
migrate_timers(cpu);
break;
#endif
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block __cpuinitdata timers_nb = {
.notifier_call = timer_cpu_notify,
};
void __init init_timers(void)
{
int err = timer_cpu_notify(&timers_nb, (unsigned long)CPU_UP_PREPARE,
(void *)(long)smp_processor_id());
init_timer_stats();
BUG_ON(err == NOTIFY_BAD);
register_cpu_notifier(&timers_nb);
open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL);
}
/**
* 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)
timeout = schedule_timeout_uninterruptible(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))
timeout = schedule_timeout_interruptible(timeout);
return jiffies_to_msecs(timeout);
}
EXPORT_SYMBOL(msleep_interruptible);