X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Ftime%2Fclocksource.c;h=1f5dde637457e94e8a5bcdcda498044bbb9844c1;hb=eed63519e3e74d515d2007ecd895338d0ba2a85c;hp=a9f387ea83b0a52181b0f10ddb10c63ccd1ea2e7;hpb=5d0cf410e94b1f1ff852c3f210d22cc6c5a27ffa;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index a9f387e..1f5dde6 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -21,171 +21,663 @@ * * TODO WishList: * o Allow clocksource drivers to be unregistered - * o get rid of clocksource_jiffies extern */ #include #include #include #include +#include /* for spin_unlock_irq() using preempt_count() m68k */ +#include +#include -/* XXX - Would like a better way for initializing curr_clocksource */ -extern struct clocksource clocksource_jiffies; +void timecounter_init(struct timecounter *tc, + const struct cyclecounter *cc, + u64 start_tstamp) +{ + tc->cc = cc; + tc->cycle_last = cc->read(cc); + tc->nsec = start_tstamp; +} +EXPORT_SYMBOL_GPL(timecounter_init); + +/** + * timecounter_read_delta - get nanoseconds since last call of this function + * @tc: Pointer to time counter + * + * When the underlying cycle counter runs over, this will be handled + * correctly as long as it does not run over more than once between + * calls. + * + * The first call to this function for a new time counter initializes + * the time tracking and returns an undefined result. + */ +static u64 timecounter_read_delta(struct timecounter *tc) +{ + cycle_t cycle_now, cycle_delta; + u64 ns_offset; + + /* read cycle counter: */ + cycle_now = tc->cc->read(tc->cc); + + /* calculate the delta since the last timecounter_read_delta(): */ + cycle_delta = (cycle_now - tc->cycle_last) & tc->cc->mask; + + /* convert to nanoseconds: */ + ns_offset = cyclecounter_cyc2ns(tc->cc, cycle_delta); + + /* update time stamp of timecounter_read_delta() call: */ + tc->cycle_last = cycle_now; + + return ns_offset; +} + +u64 timecounter_read(struct timecounter *tc) +{ + u64 nsec; + + /* increment time by nanoseconds since last call */ + nsec = timecounter_read_delta(tc); + nsec += tc->nsec; + tc->nsec = nsec; + + return nsec; +} +EXPORT_SYMBOL_GPL(timecounter_read); + +u64 timecounter_cyc2time(struct timecounter *tc, + cycle_t cycle_tstamp) +{ + u64 cycle_delta = (cycle_tstamp - tc->cycle_last) & tc->cc->mask; + u64 nsec; + + /* + * Instead of always treating cycle_tstamp as more recent + * than tc->cycle_last, detect when it is too far in the + * future and treat it as old time stamp instead. + */ + if (cycle_delta > tc->cc->mask / 2) { + cycle_delta = (tc->cycle_last - cycle_tstamp) & tc->cc->mask; + nsec = tc->nsec - cyclecounter_cyc2ns(tc->cc, cycle_delta); + } else { + nsec = cyclecounter_cyc2ns(tc->cc, cycle_delta) + tc->nsec; + } + + return nsec; +} +EXPORT_SYMBOL_GPL(timecounter_cyc2time); + +/** + * clocks_calc_mult_shift - calculate mult/shift factors for scaled math of clocks + * @mult: pointer to mult variable + * @shift: pointer to shift variable + * @from: frequency to convert from + * @to: frequency to convert to + * @minsec: guaranteed runtime conversion range in seconds + * + * The function evaluates the shift/mult pair for the scaled math + * operations of clocksources and clockevents. + * + * @to and @from are frequency values in HZ. For clock sources @to is + * NSEC_PER_SEC == 1GHz and @from is the counter frequency. For clock + * event @to is the counter frequency and @from is NSEC_PER_SEC. + * + * The @minsec conversion range argument controls the time frame in + * seconds which must be covered by the runtime conversion with the + * calculated mult and shift factors. This guarantees that no 64bit + * overflow happens when the input value of the conversion is + * multiplied with the calculated mult factor. Larger ranges may + * reduce the conversion accuracy by chosing smaller mult and shift + * factors. + */ +void +clocks_calc_mult_shift(u32 *mult, u32 *shift, u32 from, u32 to, u32 minsec) +{ + u64 tmp; + u32 sft, sftacc= 32; + + /* + * Calculate the shift factor which is limiting the conversion + * range: + */ + tmp = ((u64)minsec * from) >> 32; + while (tmp) { + tmp >>=1; + sftacc--; + } + + /* + * Find the conversion shift/mult pair which has the best + * accuracy and fits the maxsec conversion range: + */ + for (sft = 32; sft > 0; sft--) { + tmp = (u64) to << sft; + do_div(tmp, from); + if ((tmp >> sftacc) == 0) + break; + } + *mult = tmp; + *shift = sft; +} /*[Clocksource internal variables]--------- * curr_clocksource: - * currently selected clocksource. Initialized to clocksource_jiffies. - * next_clocksource: - * pending next selected clocksource. + * currently selected clocksource. * clocksource_list: * linked list with the registered clocksources - * clocksource_lock: - * protects manipulations to curr_clocksource and next_clocksource - * and the clocksource_list + * clocksource_mutex: + * protects manipulations to curr_clocksource and the clocksource_list * override_name: * Name of the user-specified clocksource. */ -static struct clocksource *curr_clocksource = &clocksource_jiffies; -static struct clocksource *next_clocksource; +static struct clocksource *curr_clocksource; static LIST_HEAD(clocksource_list); -static DEFINE_SPINLOCK(clocksource_lock); +static DEFINE_MUTEX(clocksource_mutex); static char override_name[32]; static int finished_booting; -/* clocksource_done_booting - Called near the end of bootup - * - * Hack to avoid lots of clocksource churn at boot time +#ifdef CONFIG_CLOCKSOURCE_WATCHDOG +static void clocksource_watchdog_work(struct work_struct *work); + +static LIST_HEAD(watchdog_list); +static struct clocksource *watchdog; +static struct timer_list watchdog_timer; +static DECLARE_WORK(watchdog_work, clocksource_watchdog_work); +static DEFINE_SPINLOCK(watchdog_lock); +static cycle_t watchdog_last; +static int watchdog_running; + +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); + +/* + * Interval: 0.5sec Threshold: 0.0625s */ -static int __init clocksource_done_booting(void) +#define WATCHDOG_INTERVAL (HZ >> 1) +#define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) + +static void clocksource_watchdog_work(struct work_struct *work) { - finished_booting = 1; - return 0; + /* + * If kthread_run fails the next watchdog scan over the + * watchdog_list will find the unstable clock again. + */ + kthread_run(clocksource_watchdog_kthread, NULL, "kwatchdog"); } -late_initcall(clocksource_done_booting); +static void __clocksource_unstable(struct clocksource *cs) +{ + cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); + cs->flags |= CLOCK_SOURCE_UNSTABLE; + if (finished_booting) + schedule_work(&watchdog_work); +} + +static void clocksource_unstable(struct clocksource *cs, int64_t delta) +{ + printk(KERN_WARNING "Clocksource %s unstable (delta = %Ld ns)\n", + cs->name, delta); + __clocksource_unstable(cs); +} /** - * get_next_clocksource - Returns the selected clocksource + * clocksource_mark_unstable - mark clocksource unstable via watchdog + * @cs: clocksource to be marked unstable * + * This function is called instead of clocksource_change_rating from + * cpu hotplug code to avoid a deadlock between the clocksource mutex + * and the cpu hotplug mutex. It defers the update of the clocksource + * to the watchdog thread. */ -struct clocksource *get_next_clocksource(void) +void clocksource_mark_unstable(struct clocksource *cs) { unsigned long flags; - spin_lock_irqsave(&clocksource_lock, flags); - if (next_clocksource && finished_booting) { - curr_clocksource = next_clocksource; - next_clocksource = NULL; + spin_lock_irqsave(&watchdog_lock, flags); + if (!(cs->flags & CLOCK_SOURCE_UNSTABLE)) { + if (list_empty(&cs->wd_list)) + list_add(&cs->wd_list, &watchdog_list); + __clocksource_unstable(cs); + } + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_watchdog(unsigned long data) +{ + struct clocksource *cs; + cycle_t csnow, wdnow; + int64_t wd_nsec, cs_nsec; + int next_cpu; + + spin_lock(&watchdog_lock); + if (!watchdog_running) + goto out; + + wdnow = watchdog->read(watchdog); + wd_nsec = clocksource_cyc2ns((wdnow - watchdog_last) & watchdog->mask, + watchdog->mult, watchdog->shift); + watchdog_last = wdnow; + + list_for_each_entry(cs, &watchdog_list, wd_list) { + + /* Clocksource already marked unstable? */ + if (cs->flags & CLOCK_SOURCE_UNSTABLE) { + if (finished_booting) + schedule_work(&watchdog_work); + continue; + } + + csnow = cs->read(cs); + + /* Clocksource initialized ? */ + if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { + cs->flags |= CLOCK_SOURCE_WATCHDOG; + cs->wd_last = csnow; + continue; + } + + /* Check the deviation from the watchdog clocksource. */ + cs_nsec = clocksource_cyc2ns((csnow - cs->wd_last) & + cs->mask, cs->mult, cs->shift); + cs->wd_last = csnow; + if (abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) { + clocksource_unstable(cs, cs_nsec - wd_nsec); + continue; + } + + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && + (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && + (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + /* + * We just marked the clocksource as highres-capable, + * notify the rest of the system as well so that we + * transition into high-res mode: + */ + tick_clock_notify(); + } } - spin_unlock_irqrestore(&clocksource_lock, flags); - return curr_clocksource; + /* + * Cycle through CPUs to check if the CPUs stay synchronized + * to each other. + */ + next_cpu = cpumask_next(raw_smp_processor_id(), cpu_online_mask); + if (next_cpu >= nr_cpu_ids) + next_cpu = cpumask_first(cpu_online_mask); + watchdog_timer.expires += WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, next_cpu); +out: + spin_unlock(&watchdog_lock); } -/** - * select_clocksource - Finds the best registered clocksource. - * - * Private function. Must hold clocksource_lock when called. - * - * Looks through the list of registered clocksources, returning - * the one with the highest rating value. If there is a clocksource - * name that matches the override string, it returns that clocksource. - */ -static struct clocksource *select_clocksource(void) +static inline void clocksource_start_watchdog(void) { - struct clocksource *best = NULL; - struct list_head *tmp; + if (watchdog_running || !watchdog || list_empty(&watchdog_list)) + return; + init_timer(&watchdog_timer); + watchdog_timer.function = clocksource_watchdog; + watchdog_last = watchdog->read(watchdog); + watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); + watchdog_running = 1; +} - list_for_each(tmp, &clocksource_list) { - struct clocksource *src; +static inline void clocksource_stop_watchdog(void) +{ + if (!watchdog_running || (watchdog && !list_empty(&watchdog_list))) + return; + del_timer(&watchdog_timer); + watchdog_running = 0; +} - src = list_entry(tmp, struct clocksource, list); - if (!best) - best = src; +static inline void clocksource_reset_watchdog(void) +{ + struct clocksource *cs; - /* check for override: */ - if (strlen(src->name) == strlen(override_name) && - !strcmp(src->name, override_name)) { - best = src; - break; + list_for_each_entry(cs, &watchdog_list, wd_list) + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; +} + +static void clocksource_resume_watchdog(void) +{ + unsigned long flags; + + /* + * We use trylock here to avoid a potential dead lock when + * kgdb calls this code after the kernel has been stopped with + * watchdog_lock held. When watchdog_lock is held we just + * return and accept, that the watchdog might trigger and mark + * the monitored clock source (usually TSC) unstable. + * + * This does not affect the other caller clocksource_resume() + * because at this point the kernel is UP, interrupts are + * disabled and nothing can hold watchdog_lock. + */ + if (!spin_trylock_irqsave(&watchdog_lock, flags)) + return; + clocksource_reset_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_enqueue_watchdog(struct clocksource *cs) +{ + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a clocksource to be watched. */ + list_add(&cs->wd_list, &watchdog_list); + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; + } else { + /* cs is a watchdog. */ + if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + /* Pick the best watchdog. */ + if (!watchdog || cs->rating > watchdog->rating) { + watchdog = cs; + /* Reset watchdog cycles */ + clocksource_reset_watchdog(); } - /* pick the highest rating: */ - if (src->rating > best->rating) - best = src; } + /* Check if the watchdog timer needs to be started. */ + clocksource_start_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static void clocksource_dequeue_watchdog(struct clocksource *cs) +{ + struct clocksource *tmp; + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + } else if (cs == watchdog) { + /* Reset watchdog cycles */ + clocksource_reset_watchdog(); + /* Current watchdog is removed. Find an alternative. */ + watchdog = NULL; + list_for_each_entry(tmp, &clocksource_list, list) { + if (tmp == cs || tmp->flags & CLOCK_SOURCE_MUST_VERIFY) + continue; + if (!watchdog || tmp->rating > watchdog->rating) + watchdog = tmp; + } + } + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static int clocksource_watchdog_kthread(void *data) +{ + struct clocksource *cs, *tmp; + unsigned long flags; + LIST_HEAD(unstable); + + mutex_lock(&clocksource_mutex); + spin_lock_irqsave(&watchdog_lock, flags); + list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) + if (cs->flags & CLOCK_SOURCE_UNSTABLE) { + list_del_init(&cs->wd_list); + list_add(&cs->wd_list, &unstable); + } + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); + spin_unlock_irqrestore(&watchdog_lock, flags); + + /* Needs to be done outside of watchdog lock */ + list_for_each_entry_safe(cs, tmp, &unstable, wd_list) { + list_del_init(&cs->wd_list); + __clocksource_change_rating(cs, 0); + } + mutex_unlock(&clocksource_mutex); + return 0; +} + +#else /* CONFIG_CLOCKSOURCE_WATCHDOG */ + +static void clocksource_enqueue_watchdog(struct clocksource *cs) +{ + if (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; +} + +static inline void clocksource_dequeue_watchdog(struct clocksource *cs) { } +static inline void clocksource_resume_watchdog(void) { } +static inline int clocksource_watchdog_kthread(void *data) { return 0; } + +#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ - return best; +/** + * clocksource_suspend - suspend the clocksource(s) + */ +void clocksource_suspend(void) +{ + struct clocksource *cs; + + list_for_each_entry_reverse(cs, &clocksource_list, list) + if (cs->suspend) + cs->suspend(cs); +} + +/** + * clocksource_resume - resume the clocksource(s) + */ +void clocksource_resume(void) +{ + struct clocksource *cs; + + list_for_each_entry(cs, &clocksource_list, list) + if (cs->resume) + cs->resume(cs); + + clocksource_resume_watchdog(); } /** - * is_registered_source - Checks if clocksource is registered - * @c: pointer to a clocksource + * clocksource_touch_watchdog - Update watchdog * - * Private helper function. Must hold clocksource_lock when called. + * Update the watchdog after exception contexts such as kgdb so as not + * to incorrectly trip the watchdog. This might fail when the kernel + * was stopped in code which holds watchdog_lock. + */ +void clocksource_touch_watchdog(void) +{ + clocksource_resume_watchdog(); +} + +/** + * clocksource_max_deferment - Returns max time the clocksource can be deferred + * @cs: Pointer to clocksource * - * Returns one if the clocksource is already registered, zero otherwise. */ -static int is_registered_source(struct clocksource *c) +static u64 clocksource_max_deferment(struct clocksource *cs) { - int len = strlen(c->name); - struct list_head *tmp; + u64 max_nsecs, max_cycles; + + /* + * Calculate the maximum number of cycles that we can pass to the + * cyc2ns function without overflowing a 64-bit signed result. The + * maximum number of cycles is equal to ULLONG_MAX/cs->mult which + * is equivalent to the below. + * max_cycles < (2^63)/cs->mult + * max_cycles < 2^(log2((2^63)/cs->mult)) + * max_cycles < 2^(log2(2^63) - log2(cs->mult)) + * max_cycles < 2^(63 - log2(cs->mult)) + * max_cycles < 1 << (63 - log2(cs->mult)) + * Please note that we add 1 to the result of the log2 to account for + * any rounding errors, ensure the above inequality is satisfied and + * no overflow will occur. + */ + max_cycles = 1ULL << (63 - (ilog2(cs->mult) + 1)); + + /* + * The actual maximum number of cycles we can defer the clocksource is + * determined by the minimum of max_cycles and cs->mask. + */ + max_cycles = min_t(u64, max_cycles, (u64) cs->mask); + max_nsecs = clocksource_cyc2ns(max_cycles, cs->mult, cs->shift); + + /* + * To ensure that the clocksource does not wrap whilst we are idle, + * limit the time the clocksource can be deferred by 12.5%. Please + * note a margin of 12.5% is used because this can be computed with + * a shift, versus say 10% which would require division. + */ + return max_nsecs - (max_nsecs >> 5); +} - list_for_each(tmp, &clocksource_list) { - struct clocksource *src; +#ifdef CONFIG_GENERIC_TIME - src = list_entry(tmp, struct clocksource, list); - if (strlen(src->name) == len && !strcmp(src->name, c->name)) - return 1; +/** + * clocksource_select - Select the best clocksource available + * + * Private function. Must hold clocksource_mutex when called. + * + * Select the clocksource with the best rating, or the clocksource, + * which is selected by userspace override. + */ +static void clocksource_select(void) +{ + struct clocksource *best, *cs; + + if (!finished_booting || list_empty(&clocksource_list)) + return; + /* First clocksource on the list has the best rating. */ + best = list_first_entry(&clocksource_list, struct clocksource, list); + /* Check for the override clocksource. */ + list_for_each_entry(cs, &clocksource_list, list) { + if (strcmp(cs->name, override_name) != 0) + continue; + /* + * Check to make sure we don't switch to a non-highres + * capable clocksource if the tick code is in oneshot + * mode (highres or nohz) + */ + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && + tick_oneshot_mode_active()) { + /* Override clocksource cannot be used. */ + printk(KERN_WARNING "Override clocksource %s is not " + "HRT compatible. Cannot switch while in " + "HRT/NOHZ mode\n", cs->name); + override_name[0] = 0; + } else + /* Override clocksource can be used. */ + best = cs; + break; + } + if (curr_clocksource != best) { + printk(KERN_INFO "Switching to clocksource %s\n", best->name); + curr_clocksource = best; + timekeeping_notify(curr_clocksource); } +} + +#else /* CONFIG_GENERIC_TIME */ + +static inline void clocksource_select(void) { } + +#endif +/* + * clocksource_done_booting - Called near the end of core bootup + * + * Hack to avoid lots of clocksource churn at boot time. + * We use fs_initcall because we want this to start before + * device_initcall but after subsys_initcall. + */ +static int __init clocksource_done_booting(void) +{ + mutex_lock(&clocksource_mutex); + curr_clocksource = clocksource_default_clock(); + mutex_unlock(&clocksource_mutex); + + finished_booting = 1; + + /* + * Run the watchdog first to eliminate unstable clock sources + */ + clocksource_watchdog_kthread(NULL); + + mutex_lock(&clocksource_mutex); + clocksource_select(); + mutex_unlock(&clocksource_mutex); return 0; } +fs_initcall(clocksource_done_booting); + +/* + * Enqueue the clocksource sorted by rating + */ +static void clocksource_enqueue(struct clocksource *cs) +{ + struct list_head *entry = &clocksource_list; + struct clocksource *tmp; + + list_for_each_entry(tmp, &clocksource_list, list) + /* Keep track of the place, where to insert */ + if (tmp->rating >= cs->rating) + entry = &tmp->list; + list_add(&cs->list, entry); +} /** - * register_clocksource - Used to install new clocksources + * clocksource_register - Used to install new clocksources * @t: clocksource to be registered * * Returns -EBUSY if registration fails, zero otherwise. */ -int register_clocksource(struct clocksource *c) +int clocksource_register(struct clocksource *cs) { - int ret = 0; - unsigned long flags; - - spin_lock_irqsave(&clocksource_lock, flags); - /* check if clocksource is already registered */ - if (is_registered_source(c)) { - printk("register_clocksource: Cannot register %s. " - "Already registered!", c->name); - ret = -EBUSY; - } else { - /* register it */ - list_add(&c->list, &clocksource_list); - /* scan the registered clocksources, and pick the best one */ - next_clocksource = select_clocksource(); - } - spin_unlock_irqrestore(&clocksource_lock, flags); - return ret; + /* calculate max idle time permitted for this clocksource */ + cs->max_idle_ns = clocksource_max_deferment(cs); + + mutex_lock(&clocksource_mutex); + clocksource_enqueue(cs); + clocksource_select(); + clocksource_enqueue_watchdog(cs); + mutex_unlock(&clocksource_mutex); + return 0; } +EXPORT_SYMBOL(clocksource_register); -EXPORT_SYMBOL(register_clocksource); +static void __clocksource_change_rating(struct clocksource *cs, int rating) +{ + list_del(&cs->list); + cs->rating = rating; + clocksource_enqueue(cs); + clocksource_select(); +} /** - * reselect_clocksource - Rescan list for next clocksource - * - * A quick helper function to be used if a clocksource changes its - * rating. Forces the clocksource list to be re-scanned for the best - * clocksource. + * clocksource_change_rating - Change the rating of a registered clocksource */ -void reselect_clocksource(void) +void clocksource_change_rating(struct clocksource *cs, int rating) { - unsigned long flags; + mutex_lock(&clocksource_mutex); + __clocksource_change_rating(cs, rating); + mutex_unlock(&clocksource_mutex); +} +EXPORT_SYMBOL(clocksource_change_rating); - spin_lock_irqsave(&clocksource_lock, flags); - next_clocksource = select_clocksource(); - spin_unlock_irqrestore(&clocksource_lock, flags); +/** + * clocksource_unregister - remove a registered clocksource + */ +void clocksource_unregister(struct clocksource *cs) +{ + mutex_lock(&clocksource_mutex); + clocksource_dequeue_watchdog(cs); + list_del(&cs->list); + clocksource_select(); + mutex_unlock(&clocksource_mutex); } +EXPORT_SYMBOL(clocksource_unregister); +#ifdef CONFIG_SYSFS /** * sysfs_show_current_clocksources - sysfs interface for current clocksource * @dev: unused @@ -194,17 +686,16 @@ void reselect_clocksource(void) * Provides sysfs interface for listing current clocksource. */ static ssize_t -sysfs_show_current_clocksources(struct sys_device *dev, char *buf) +sysfs_show_current_clocksources(struct sys_device *dev, + struct sysdev_attribute *attr, char *buf) { - char *curr = buf; + ssize_t count = 0; - spin_lock_irq(&clocksource_lock); - curr += sprintf(curr, "%s ", curr_clocksource->name); - spin_unlock_irq(&clocksource_lock); + mutex_lock(&clocksource_mutex); + count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name); + mutex_unlock(&clocksource_mutex); - curr += sprintf(curr, "\n"); - - return curr - buf; + return count; } /** @@ -214,12 +705,14 @@ sysfs_show_current_clocksources(struct sys_device *dev, char *buf) * @count: length of buffer * * Takes input from sysfs interface for manually overriding the default - * clocksource selction. + * clocksource selection. */ static ssize_t sysfs_override_clocksource(struct sys_device *dev, + struct sysdev_attribute *attr, const char *buf, size_t count) { size_t ret = count; + /* strings from sysfs write are not 0 terminated! */ if (count >= sizeof(override_name)) return -EINVAL; @@ -227,19 +720,15 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, /* strip of \n: */ if (buf[count-1] == '\n') count--; - if (count < 1) - return -EINVAL; - spin_lock_irq(&clocksource_lock); + mutex_lock(&clocksource_mutex); - /* copy the name given: */ - memcpy(override_name, buf, count); + if (count > 0) + memcpy(override_name, buf, count); override_name[count] = 0; + clocksource_select(); - /* try to select it: */ - next_clocksource = select_clocksource(); - - spin_unlock_irq(&clocksource_lock); + mutex_unlock(&clocksource_mutex); return ret; } @@ -252,36 +741,44 @@ static ssize_t sysfs_override_clocksource(struct sys_device *dev, * Provides sysfs interface for listing registered clocksources */ static ssize_t -sysfs_show_available_clocksources(struct sys_device *dev, char *buf) +sysfs_show_available_clocksources(struct sys_device *dev, + struct sysdev_attribute *attr, + char *buf) { - struct list_head *tmp; - char *curr = buf; - - spin_lock_irq(&clocksource_lock); - list_for_each(tmp, &clocksource_list) { - struct clocksource *src; - - src = list_entry(tmp, struct clocksource, list); - curr += sprintf(curr, "%s ", src->name); + struct clocksource *src; + ssize_t count = 0; + + mutex_lock(&clocksource_mutex); + list_for_each_entry(src, &clocksource_list, list) { + /* + * Don't show non-HRES clocksource if the tick code is + * in one shot mode (highres=on or nohz=on) + */ + if (!tick_oneshot_mode_active() || + (src->flags & CLOCK_SOURCE_VALID_FOR_HRES)) + count += snprintf(buf + count, + max((ssize_t)PAGE_SIZE - count, (ssize_t)0), + "%s ", src->name); } - spin_unlock_irq(&clocksource_lock); + mutex_unlock(&clocksource_mutex); - curr += sprintf(curr, "\n"); + count += snprintf(buf + count, + max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n"); - return curr - buf; + return count; } /* * Sysfs setup bits: */ -static SYSDEV_ATTR(current_clocksource, 0600, sysfs_show_current_clocksources, - sysfs_override_clocksource); +static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, + sysfs_override_clocksource); -static SYSDEV_ATTR(available_clocksource, 0600, - sysfs_show_available_clocksources, NULL); +static SYSDEV_ATTR(available_clocksource, 0444, + sysfs_show_available_clocksources, NULL); static struct sysdev_class clocksource_sysclass = { - set_kset_name("clocksource"), + .name = "clocksource", }; static struct sys_device device_clocksource = { @@ -307,6 +804,7 @@ static int __init init_clocksource_sysfs(void) } device_initcall(init_clocksource_sysfs); +#endif /* CONFIG_SYSFS */ /** * boot_override_clocksource - boot clock override @@ -317,11 +815,10 @@ device_initcall(init_clocksource_sysfs); */ static int __init boot_override_clocksource(char* str) { - unsigned long flags; - spin_lock_irqsave(&clocksource_lock, flags); + mutex_lock(&clocksource_mutex); if (str) strlcpy(override_name, str, sizeof(override_name)); - spin_unlock_irqrestore(&clocksource_lock, flags); + mutex_unlock(&clocksource_mutex); return 1; }