X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ftimer.c;h=9fbb472b8cf0a4e3016480fb205c42eda38dabf8;hb=82a96f5790ac93a406be72ed8f308dd29ad7e6af;hp=1258371e0d2be3323ed7cb661c16a93355d30a2f;hpb=c5c061b8f9726bc2c25e19dec227933a13d1e6b7;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/timer.c b/kernel/timer.c index 1258371..9fbb472 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -26,6 +26,7 @@ #include #include #include +#include #include #include #include @@ -57,60 +58,58 @@ EXPORT_SYMBOL(jiffies_64); #define TVN_MASK (TVN_SIZE - 1) #define TVR_MASK (TVR_SIZE - 1) -typedef struct tvec_s { +struct tvec { struct list_head vec[TVN_SIZE]; -} tvec_t; +}; -typedef struct tvec_root_s { +struct tvec_root { struct list_head vec[TVR_SIZE]; -} tvec_root_t; +}; -struct tvec_t_base_s { +struct tvec_base { 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; + struct tvec_root tv1; + struct tvec tv2; + struct tvec tv3; + struct tvec tv4; + struct tvec tv5; } ____cacheline_aligned; -typedef struct tvec_t_base_s tvec_base_t; - -tvec_base_t boot_tvec_bases; +struct tvec_base boot_tvec_bases; EXPORT_SYMBOL(boot_tvec_bases); -static DEFINE_PER_CPU(tvec_base_t *, tvec_bases) = &boot_tvec_bases; +static DEFINE_PER_CPU(struct tvec_base *, tvec_bases) = &boot_tvec_bases; /* - * Note that all tvec_bases is 2 byte aligned and lower bit of + * Note that all tvec_bases are 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) +static inline unsigned int tbase_get_deferrable(struct tvec_base *base) { return ((unsigned int)(unsigned long)base & TBASE_DEFERRABLE_FLAG); } -static inline tvec_base_t *tbase_get_base(tvec_base_t *base) +static inline struct tvec_base *tbase_get_base(struct tvec_base *base) { - return ((tvec_base_t *)((unsigned long)base & ~TBASE_DEFERRABLE_FLAG)); + return ((struct tvec_base *)((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)); + timer->base = ((struct tvec_base *)((unsigned long)(timer->base) | + TBASE_DEFERRABLE_FLAG)); } static inline void -timer_set_base(struct timer_list *timer, tvec_base_t *new_base) +timer_set_base(struct timer_list *timer, struct tvec_base *new_base) { - timer->base = (tvec_base_t *)((unsigned long)(new_base) | - tbase_get_deferrable(timer->base)); + timer->base = (struct tvec_base *)((unsigned long)(new_base) | + tbase_get_deferrable(timer->base)); } /** @@ -245,7 +244,7 @@ unsigned long round_jiffies_relative(unsigned long j) EXPORT_SYMBOL_GPL(round_jiffies_relative); -static inline void set_running_timer(tvec_base_t *base, +static inline void set_running_timer(struct tvec_base *base, struct timer_list *timer) { #ifdef CONFIG_SMP @@ -253,7 +252,7 @@ static inline void set_running_timer(tvec_base_t *base, #endif } -static void internal_add_timer(tvec_base_t *base, struct timer_list *timer) +static void internal_add_timer(struct tvec_base *base, struct timer_list *timer) { unsigned long expires = timer->expires; unsigned long idx = expires - base->timer_jiffies; @@ -370,14 +369,14 @@ static inline void detach_timer(struct timer_list *timer, * 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, +static struct tvec_base *lock_timer_base(struct timer_list *timer, unsigned long *flags) __acquires(timer->base->lock) { - tvec_base_t *base; + struct tvec_base *base; for (;;) { - tvec_base_t *prelock_base = timer->base; + struct tvec_base *prelock_base = timer->base; base = tbase_get_base(prelock_base); if (likely(base != NULL)) { spin_lock_irqsave(&base->lock, *flags); @@ -392,7 +391,7 @@ static tvec_base_t *lock_timer_base(struct timer_list *timer, int __mod_timer(struct timer_list *timer, unsigned long expires) { - tvec_base_t *base, *new_base; + struct tvec_base *base, *new_base; unsigned long flags; int ret = 0; @@ -444,11 +443,11 @@ EXPORT_SYMBOL(__mod_timer); */ void add_timer_on(struct timer_list *timer, int cpu) { - tvec_base_t *base = per_cpu(tvec_bases, cpu); - unsigned long flags; + struct tvec_base *base = per_cpu(tvec_bases, cpu); + unsigned long flags; timer_stats_timer_set_start_info(timer); - BUG_ON(timer_pending(timer) || !timer->function); + BUG_ON(timer_pending(timer) || !timer->function); spin_lock_irqsave(&base->lock, flags); timer_set_base(timer, base); internal_add_timer(base, timer); @@ -507,7 +506,7 @@ EXPORT_SYMBOL(mod_timer); */ int del_timer(struct timer_list *timer) { - tvec_base_t *base; + struct tvec_base *base; unsigned long flags; int ret = 0; @@ -538,7 +537,7 @@ EXPORT_SYMBOL(del_timer); */ int try_to_del_timer_sync(struct timer_list *timer) { - tvec_base_t *base; + struct tvec_base *base; unsigned long flags; int ret = -1; @@ -590,7 +589,7 @@ int del_timer_sync(struct timer_list *timer) EXPORT_SYMBOL(del_timer_sync); #endif -static int cascade(tvec_base_t *base, tvec_t *tv, int index) +static int cascade(struct tvec_base *base, struct tvec *tv, int index) { /* cascade all the timers from tv up one level */ struct timer_list *timer, *tmp; @@ -619,7 +618,7 @@ static int cascade(tvec_base_t *base, tvec_t *tv, int index) * This function cascades all vectors and executes all expired timer * vectors. */ -static inline void __run_timers(tvec_base_t *base) +static inline void __run_timers(struct tvec_base *base) { struct timer_list *timer; @@ -627,7 +626,7 @@ static inline void __run_timers(tvec_base_t *base) 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; + int index = base->timer_jiffies & TVR_MASK; /* * Cascade timers: @@ -644,8 +643,8 @@ static inline void __run_timers(tvec_base_t *base) unsigned long data; timer = list_first_entry(head, struct timer_list,entry); - fn = timer->function; - data = timer->data; + fn = timer->function; + data = timer->data; timer_stats_account_timer(timer); @@ -656,7 +655,7 @@ static inline void __run_timers(tvec_base_t *base) int preempt_count = preempt_count(); fn(data); if (preempt_count != preempt_count()) { - printk(KERN_WARNING "huh, entered %p " + printk(KERN_ERR "huh, entered %p " "with preempt_count %08x, exited" " with %08x?\n", fn, preempt_count, @@ -677,20 +676,20 @@ static inline void __run_timers(tvec_base_t *base) * 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) +static unsigned long __next_timer_interrupt(struct tvec_base *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]; + struct tvec *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; + if (tbase_get_deferrable(nte->base)) + continue; found = 1; expires = nte->expires; @@ -715,7 +714,7 @@ cascade: varray[3] = &base->tv5; for (array = 0; array < 4; array++) { - tvec_t *varp = varray[array]; + struct tvec *varp = varray[array]; index = slot = timer_jiffies & TVN_MASK; do { @@ -789,12 +788,12 @@ static unsigned long cmp_next_hrtimer_event(unsigned long now, } /** - * next_timer_interrupt - return the jiffy of the next pending timer + * get_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); + struct tvec_base *base = __get_cpu_var(tvec_bases); unsigned long expires; spin_lock(&base->lock); @@ -816,8 +815,21 @@ unsigned long next_timer_interrupt(void) #endif +#ifndef CONFIG_VIRT_CPU_ACCOUNTING +void account_process_tick(struct task_struct *p, int user_tick) +{ + 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)); + } +} +#endif + /* - * Called from the timer interrupt handler to charge one tick to the current + * 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) @@ -826,15 +838,12 @@ void update_process_times(int user_tick) 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)); + account_process_tick(p, user_tick); run_local_timers(); if (rcu_pending(cpu)) rcu_check_callbacks(cpu, user_tick); scheduler_tick(); - run_posix_cpu_timers(p); + run_posix_cpu_timers(p); } /* @@ -883,9 +892,9 @@ static inline void calc_load(unsigned long ticks) */ static void run_timer_softirq(struct softirq_action *h) { - tvec_base_t *base = __get_cpu_var(tvec_bases); + struct tvec_base *base = __get_cpu_var(tvec_bases); - hrtimer_run_queues(); + hrtimer_run_pending(); if (time_after_eq(jiffies, base->timer_jiffies)) __run_timers(base); @@ -896,6 +905,7 @@ static void run_timer_softirq(struct softirq_action *h) */ void run_local_timers(void) { + hrtimer_run_queues(); raise_softirq(TIMER_SOFTIRQ); softlockup_tick(); } @@ -909,7 +919,7 @@ 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. @@ -953,7 +963,7 @@ asmlinkage unsigned long sys_alarm(unsigned int seconds) */ asmlinkage long sys_getpid(void) { - return current->tgid; + return task_tgid_vnr(current); } /* @@ -967,7 +977,7 @@ asmlinkage long sys_getppid(void) int pid; rcu_read_lock(); - pid = rcu_dereference(current->real_parent)->tgid; + pid = task_tgid_nr_ns(current->real_parent, current->nsproxy->pid_ns); rcu_read_unlock(); return pid; @@ -1089,6 +1099,13 @@ signed long __sched schedule_timeout_interruptible(signed long timeout) } EXPORT_SYMBOL(schedule_timeout_interruptible); +signed long __sched schedule_timeout_killable(signed long timeout) +{ + __set_current_state(TASK_KILLABLE); + return schedule_timeout(timeout); +} +EXPORT_SYMBOL(schedule_timeout_killable); + signed long __sched schedule_timeout_uninterruptible(signed long timeout) { __set_current_state(TASK_UNINTERRUPTIBLE); @@ -1099,13 +1116,13 @@ EXPORT_SYMBOL(schedule_timeout_uninterruptible); /* Thread ID - the internal kernel "pid" */ asmlinkage long sys_gettid(void) { - return current->pid; + return task_pid_vnr(current); } /** * do_sysinfo - fill in sysinfo struct * @info: pointer to buffer to fill - */ + */ int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; @@ -1208,11 +1225,11 @@ asmlinkage long sys_sysinfo(struct sysinfo __user *info) */ static struct lock_class_key base_lock_keys[NR_CPUS]; -static int __devinit init_timers_cpu(int cpu) +static int __cpuinit init_timers_cpu(int cpu) { int j; - tvec_base_t *base; - static char __devinitdata tvec_base_done[NR_CPUS]; + struct tvec_base *base; + static char __cpuinitdata tvec_base_done[NR_CPUS]; if (!tvec_base_done[cpu]) { static char boot_done; @@ -1221,7 +1238,8 @@ static int __devinit init_timers_cpu(int cpu) /* * The APs use this path later in boot */ - base = kmalloc_node(sizeof(*base), GFP_KERNEL, + base = kmalloc_node(sizeof(*base), + GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu)); if (!base) return -ENOMEM; @@ -1232,7 +1250,6 @@ static int __devinit init_timers_cpu(int cpu) kfree(base); return -ENOMEM; } - memset(base, 0, sizeof(*base)); per_cpu(tvec_bases, cpu) = base; } else { /* @@ -1266,7 +1283,7 @@ static int __devinit init_timers_cpu(int cpu) } #ifdef CONFIG_HOTPLUG_CPU -static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head) +static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head) { struct timer_list *timer; @@ -1278,10 +1295,10 @@ static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head) } } -static void __devinit migrate_timers(int cpu) +static void __cpuinit migrate_timers(int cpu) { - tvec_base_t *old_base; - tvec_base_t *new_base; + struct tvec_base *old_base; + struct tvec_base *new_base; int i; BUG_ON(cpu_online(cpu)); @@ -1349,194 +1366,6 @@ void __init init_timers(void) open_softirq(TIMER_SOFTIRQ, run_timer_softirq, NULL); } -#ifdef CONFIG_TIME_INTERPOLATION - -struct time_interpolator *time_interpolator __read_mostly; -static struct time_interpolator *time_interpolator_list __read_mostly; -static DEFINE_SPINLOCK(time_interpolator_lock); - -static inline cycles_t 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_relaxed((void __iomem *)time_interpolator->addr); - - case TIME_SOURCE_MMIO32 : - return readl_relaxed((void __iomem *)time_interpolator->addr); - - default: return get_cycles(); - } -} - -static inline u64 time_interpolator_get_counter(int writelock) -{ - unsigned int src = time_interpolator->source; - - if (time_interpolator->jitter) - { - cycles_t lcycle; - cycles_t now; - - do { - lcycle = time_interpolator->last_cycle; - now = time_interpolator_get_cycles(src); - if (lcycle && time_after(lcycle, now)) - return lcycle; - - /* 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; - } - /* 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(1); -} - -#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(0), time_interpolator); -} - -#define INTERPOLATOR_ADJUST 65536 -#define INTERPOLATOR_MAX_SKIP 10*INTERPOLATOR_ADJUST - -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(1); - 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 */ - BUG_ON(ti->frequency == 0 || ti->mask == 0); - - 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