diff options
Diffstat (limited to 'kernel/time/clocksource.c')
| -rw-r--r-- | kernel/time/clocksource.c | 1034 |
1 files changed, 795 insertions, 239 deletions
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 093d4acf993..ba3e502c955 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -21,60 +21,178 @@ * * TODO WishList: * o Allow clocksource drivers to be unregistered - * o get rid of clocksource_jiffies extern */ +#include <linux/device.h> #include <linux/clocksource.h> -#include <linux/sysdev.h> #include <linux/init.h> #include <linux/module.h> #include <linux/sched.h> /* for spin_unlock_irq() using preempt_count() m68k */ #include <linux/tick.h> +#include <linux/kthread.h> -/* XXX - Would like a better way for initializing curr_clocksource */ -extern struct clocksource clocksource_jiffies; +#include "tick-internal.h" + +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 + * @maxsec: 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 @maxsec 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 maxsec) +{ + u64 tmp; + u32 sft, sftacc= 32; + + /* + * Calculate the shift factor which is limiting the conversion + * range: + */ + tmp = ((u64)maxsec * 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; + tmp += from / 2; + 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 *clocksource_override; +static struct clocksource *curr_clocksource; static LIST_HEAD(clocksource_list); -static DEFINE_SPINLOCK(clocksource_lock); -static char override_name[32]; +static DEFINE_MUTEX(clocksource_mutex); +static char override_name[CS_NAME_LEN]; static int finished_booting; -/* 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) -{ - finished_booting = 1; - return 0; -} -fs_initcall(clocksource_done_booting); - #ifdef CONFIG_CLOCKSOURCE_WATCHDOG +static void clocksource_watchdog_work(struct work_struct *work); +static void clocksource_select(void); + 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 unsigned long watchdog_resumed; +static int watchdog_running; +static atomic_t watchdog_reset_pending; + +static int clocksource_watchdog_kthread(void *data); +static void __clocksource_change_rating(struct clocksource *cs, int rating); /* * Interval: 0.5sec Threshold: 0.0625s @@ -82,134 +200,300 @@ static unsigned long watchdog_resumed; #define WATCHDOG_INTERVAL (HZ >> 1) #define WATCHDOG_THRESHOLD (NSEC_PER_SEC >> 4) -static void clocksource_ratewd(struct clocksource *cs, int64_t delta) +static void clocksource_watchdog_work(struct work_struct *work) { - if (delta > -WATCHDOG_THRESHOLD && delta < WATCHDOG_THRESHOLD) - return; + /* + * 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"); +} + +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); - cs->flags &= ~(CLOCK_SOURCE_VALID_FOR_HRES | CLOCK_SOURCE_WATCHDOG); - clocksource_change_rating(cs, 0); - list_del(&cs->wd_list); + __clocksource_unstable(cs); +} + +/** + * 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. + */ +void clocksource_mark_unstable(struct clocksource *cs) +{ + unsigned long flags; + + 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, *tmp; + struct clocksource *cs; cycle_t csnow, wdnow; int64_t wd_nsec, cs_nsec; - int resumed; + int next_cpu, reset_pending; spin_lock(&watchdog_lock); + if (!watchdog_running) + goto out; - resumed = test_and_clear_bit(0, &watchdog_resumed); + reset_pending = atomic_read(&watchdog_reset_pending); - wdnow = watchdog->read(); - wd_nsec = cyc2ns(watchdog, (wdnow - watchdog_last) & watchdog->mask); - watchdog_last = wdnow; + list_for_each_entry(cs, &watchdog_list, wd_list) { - list_for_each_entry_safe(cs, tmp, &watchdog_list, wd_list) { - csnow = cs->read(); + /* Clocksource already marked unstable? */ + if (cs->flags & CLOCK_SOURCE_UNSTABLE) { + if (finished_booting) + schedule_work(&watchdog_work); + continue; + } + + local_irq_disable(); + csnow = cs->read(cs); + wdnow = watchdog->read(watchdog); + local_irq_enable(); + + /* Clocksource initialized ? */ + if (!(cs->flags & CLOCK_SOURCE_WATCHDOG) || + atomic_read(&watchdog_reset_pending)) { + cs->flags |= CLOCK_SOURCE_WATCHDOG; + cs->wd_last = wdnow; + cs->cs_last = csnow; + continue; + } + + wd_nsec = clocksource_cyc2ns((wdnow - cs->wd_last) & watchdog->mask, + watchdog->mult, watchdog->shift); + + cs_nsec = clocksource_cyc2ns((csnow - cs->cs_last) & + cs->mask, cs->mult, cs->shift); + cs->cs_last = csnow; + cs->wd_last = wdnow; - if (unlikely(resumed)) { - cs->wd_last = csnow; + if (atomic_read(&watchdog_reset_pending)) + continue; + + /* Check the deviation from the watchdog clocksource. */ + if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) { + clocksource_unstable(cs, cs_nsec - wd_nsec); continue; } - /* Initialized ? */ - if (!(cs->flags & CLOCK_SOURCE_WATCHDOG)) { - if ((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: - */ + if (!(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES) && + (cs->flags & CLOCK_SOURCE_IS_CONTINUOUS) && + (watchdog->flags & CLOCK_SOURCE_IS_CONTINUOUS)) { + /* Mark it valid for high-res. */ + cs->flags |= CLOCK_SOURCE_VALID_FOR_HRES; + + /* + * clocksource_done_booting() will sort it if + * finished_booting is not set yet. + */ + if (!finished_booting) + continue; + + /* + * If this is not the current clocksource let + * the watchdog thread reselect it. Due to the + * change to high res this clocksource might + * be preferred now. If it is the current + * clocksource let the tick code know about + * that change. + */ + if (cs != curr_clocksource) { + cs->flags |= CLOCK_SOURCE_RESELECT; + schedule_work(&watchdog_work); + } else { tick_clock_notify(); } - cs->flags |= CLOCK_SOURCE_WATCHDOG; - cs->wd_last = csnow; - } else { - cs_nsec = cyc2ns(cs, (csnow - cs->wd_last) & cs->mask); - cs->wd_last = csnow; - /* Check the delta. Might remove from the list ! */ - clocksource_ratewd(cs, cs_nsec - wd_nsec); } } - if (!list_empty(&watchdog_list)) { - /* - * Cycle through CPUs to check if the CPUs stay - * synchronized to each other. - */ - int next_cpu = next_cpu_nr(raw_smp_processor_id(), cpu_online_map); - - if (next_cpu >= nr_cpu_ids) - next_cpu = first_cpu(cpu_online_map); - watchdog_timer.expires += WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, next_cpu); - } + /* + * We only clear the watchdog_reset_pending, when we did a + * full cycle through all clocksources. + */ + if (reset_pending) + atomic_dec(&watchdog_reset_pending); + + /* + * 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); } + +static inline void clocksource_start_watchdog(void) +{ + if (watchdog_running || !watchdog || list_empty(&watchdog_list)) + return; + init_timer(&watchdog_timer); + watchdog_timer.function = clocksource_watchdog; + watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; + add_timer_on(&watchdog_timer, cpumask_first(cpu_online_mask)); + watchdog_running = 1; +} + +static inline void clocksource_stop_watchdog(void) +{ + if (!watchdog_running || (watchdog && !list_empty(&watchdog_list))) + return; + del_timer(&watchdog_timer); + watchdog_running = 0; +} + +static inline void clocksource_reset_watchdog(void) +{ + struct clocksource *cs; + + list_for_each_entry(cs, &watchdog_list, wd_list) + cs->flags &= ~CLOCK_SOURCE_WATCHDOG; +} + static void clocksource_resume_watchdog(void) { - set_bit(0, &watchdog_resumed); + atomic_inc(&watchdog_reset_pending); } -static void clocksource_check_watchdog(struct clocksource *cs) +static void clocksource_enqueue_watchdog(struct clocksource *cs) { - struct clocksource *cse; unsigned long flags; spin_lock_irqsave(&watchdog_lock, flags); if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { - int started = !list_empty(&watchdog_list); - + /* cs is a clocksource to be watched. */ list_add(&cs->wd_list, &watchdog_list); - if (!started && watchdog) { - watchdog_last = watchdog->read(); - watchdog_timer.expires = jiffies + WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, - first_cpu(cpu_online_map)); - } + 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) { - if (watchdog) - del_timer(&watchdog_timer); watchdog = cs; - init_timer(&watchdog_timer); - watchdog_timer.function = clocksource_watchdog; - /* Reset watchdog cycles */ - list_for_each_entry(cse, &watchdog_list, wd_list) - cse->flags &= ~CLOCK_SOURCE_WATCHDOG; - /* Start if list is not empty */ - if (!list_empty(&watchdog_list)) { - watchdog_last = watchdog->read(); - watchdog_timer.expires = - jiffies + WATCHDOG_INTERVAL; - add_timer_on(&watchdog_timer, - first_cpu(cpu_online_map)); - } + clocksource_reset_watchdog(); + } + } + /* 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) +{ + unsigned long flags; + + spin_lock_irqsave(&watchdog_lock, flags); + if (cs != watchdog) { + if (cs->flags & CLOCK_SOURCE_MUST_VERIFY) { + /* cs is a watched clocksource. */ + list_del_init(&cs->wd_list); + /* Check if the watchdog timer needs to be stopped. */ + clocksource_stop_watchdog(); + } + } + spin_unlock_irqrestore(&watchdog_lock, flags); +} + +static int __clocksource_watchdog_kthread(void) +{ + struct clocksource *cs, *tmp; + unsigned long flags; + LIST_HEAD(unstable); + int select = 0; + + 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); + select = 1; + } + if (cs->flags & CLOCK_SOURCE_RESELECT) { + cs->flags &= ~CLOCK_SOURCE_RESELECT; + select = 1; } } + /* 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); + } + return select; +} + +static int clocksource_watchdog_kthread(void *data) +{ + mutex_lock(&clocksource_mutex); + if (__clocksource_watchdog_kthread()) + clocksource_select(); + mutex_unlock(&clocksource_mutex); + return 0; } -#else -static void clocksource_check_watchdog(struct clocksource *cs) + +static bool clocksource_is_watchdog(struct clocksource *cs) +{ + return cs == watchdog; +} + +#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) { } -#endif +static inline int __clocksource_watchdog_kthread(void) { return 0; } +static bool clocksource_is_watchdog(struct clocksource *cs) { return false; } +void clocksource_mark_unstable(struct clocksource *cs) { } + +#endif /* CONFIG_CLOCKSOURCE_WATCHDOG */ + +/** + * 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) @@ -217,26 +501,20 @@ static inline void clocksource_resume_watchdog(void) { } void clocksource_resume(void) { struct clocksource *cs; - unsigned long flags; - spin_lock_irqsave(&clocksource_lock, flags); - - list_for_each_entry(cs, &clocksource_list, list) { + list_for_each_entry(cs, &clocksource_list, list) if (cs->resume) - cs->resume(); - } + cs->resume(cs); clocksource_resume_watchdog(); - - spin_unlock_irqrestore(&clocksource_lock, flags); } /** * clocksource_touch_watchdog - Update watchdog * * Update the watchdog after exception contexts such as kgdb so as not - * to incorrectly trip the watchdog. - * + * to incorrectly trip the watchdog. This might fail when the kernel + * was stopped in code which holds watchdog_lock. */ void clocksource_touch_watchdog(void) { @@ -244,227 +522,500 @@ void clocksource_touch_watchdog(void) } /** - * clocksource_get_next - Returns the selected clocksource + * clocksource_max_adjustment- Returns max adjustment amount + * @cs: Pointer to clocksource * */ -struct clocksource *clocksource_get_next(void) +static u32 clocksource_max_adjustment(struct clocksource *cs) { - unsigned long flags; + u64 ret; + /* + * We won't try to correct for more than 11% adjustments (110,000 ppm), + */ + ret = (u64)cs->mult * 11; + do_div(ret,100); + return (u32)ret; +} + +/** + * clocks_calc_max_nsecs - Returns maximum nanoseconds that can be converted + * @mult: cycle to nanosecond multiplier + * @shift: cycle to nanosecond divisor (power of two) + * @maxadj: maximum adjustment value to mult (~11%) + * @mask: bitmask for two's complement subtraction of non 64 bit counters + */ +u64 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask) +{ + 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/(mult+maxadj) + * which is equivalent to the below. + * max_cycles < (2^63)/(mult + maxadj) + * max_cycles < 2^(log2((2^63)/(mult + maxadj))) + * max_cycles < 2^(log2(2^63) - log2(mult + maxadj)) + * max_cycles < 2^(63 - log2(mult + maxadj)) + * max_cycles < 1 << (63 - log2(mult + maxadj)) + * 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(mult + maxadj) + 1)); + + /* + * The actual maximum number of cycles we can defer the clocksource is + * determined by the minimum of max_cycles and mask. + * Note: Here we subtract the maxadj to make sure we don't sleep for + * too long if there's a large negative adjustment. + */ + max_cycles = min(max_cycles, mask); + max_nsecs = clocksource_cyc2ns(max_cycles, mult - maxadj, shift); + + return max_nsecs; +} + +/** + * clocksource_max_deferment - Returns max time the clocksource can be deferred + * @cs: Pointer to clocksource + * + */ +static u64 clocksource_max_deferment(struct clocksource *cs) +{ + u64 max_nsecs; + + max_nsecs = clocks_calc_max_nsecs(cs->mult, cs->shift, cs->maxadj, + cs->mask); + /* + * 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 >> 3); +} + +#ifndef CONFIG_ARCH_USES_GETTIMEOFFSET + +static struct clocksource *clocksource_find_best(bool oneshot, bool skipcur) +{ + struct clocksource *cs; + + if (!finished_booting || list_empty(&clocksource_list)) + return NULL; + + /* + * We pick the clocksource with the highest rating. If oneshot + * mode is active, we pick the highres valid clocksource with + * the best rating. + */ + list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; + if (oneshot && !(cs->flags & CLOCK_SOURCE_VALID_FOR_HRES)) + continue; + return cs; + } + return NULL; +} + +static void __clocksource_select(bool skipcur) +{ + bool oneshot = tick_oneshot_mode_active(); + struct clocksource *best, *cs; + + /* Find the best suitable clocksource */ + best = clocksource_find_best(oneshot, skipcur); + if (!best) + return; - spin_lock_irqsave(&clocksource_lock, flags); - if (next_clocksource && finished_booting) { - curr_clocksource = next_clocksource; - next_clocksource = NULL; + /* Check for the override clocksource. */ + list_for_each_entry(cs, &clocksource_list, list) { + if (skipcur && cs == curr_clocksource) + continue; + 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) && oneshot) { + /* 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; } - spin_unlock_irqrestore(&clocksource_lock, flags); - return curr_clocksource; + if (curr_clocksource != best && !timekeeping_notify(best)) { + pr_info("Switched to clocksource %s\n", best->name); + curr_clocksource = best; + } } /** - * select_clocksource - Selects the best registered clocksource. + * clocksource_select - Select the best clocksource available * - * Private function. Must hold clocksource_lock when called. + * 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 struct clocksource *select_clocksource(void) +static void clocksource_select(void) { - struct clocksource *next; + return __clocksource_select(false); +} - if (list_empty(&clocksource_list)) - return NULL; +static void clocksource_select_fallback(void) +{ + return __clocksource_select(true); +} - if (clocksource_override) - next = clocksource_override; - else - next = list_entry(clocksource_list.next, struct clocksource, - list); +#else /* !CONFIG_ARCH_USES_GETTIMEOFFSET */ - if (next == curr_clocksource) - return NULL; +static inline void clocksource_select(void) { } +static inline void clocksource_select_fallback(void) { } + +#endif - return next; +/* + * 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(); + finished_booting = 1; + /* + * Run the watchdog first to eliminate unstable clock sources + */ + __clocksource_watchdog_kthread(); + clocksource_select(); + mutex_unlock(&clocksource_mutex); + return 0; } +fs_initcall(clocksource_done_booting); /* * Enqueue the clocksource sorted by rating */ -static int clocksource_enqueue(struct clocksource *c) +static void clocksource_enqueue(struct clocksource *cs) { - struct list_head *tmp, *entry = &clocksource_list; - - list_for_each(tmp, &clocksource_list) { - struct clocksource *cs; + struct list_head *entry = &clocksource_list; + struct clocksource *tmp; - cs = list_entry(tmp, struct clocksource, list); - if (cs == c) - return -EBUSY; + list_for_each_entry(tmp, &clocksource_list, list) /* Keep track of the place, where to insert */ - if (cs->rating >= c->rating) - entry = tmp; + if (tmp->rating >= cs->rating) + entry = &tmp->list; + list_add(&cs->list, entry); +} + +/** + * __clocksource_updatefreq_scale - Used update clocksource with new freq + * @cs: clocksource to be registered + * @scale: Scale factor multiplied against freq to get clocksource hz + * @freq: clocksource frequency (cycles per second) divided by scale + * + * This should only be called from the clocksource->enable() method. + * + * This *SHOULD NOT* be called directly! Please use the + * clocksource_updatefreq_hz() or clocksource_updatefreq_khz helper functions. + */ +void __clocksource_updatefreq_scale(struct clocksource *cs, u32 scale, u32 freq) +{ + u64 sec; + /* + * Calc the maximum number of seconds which we can run before + * wrapping around. For clocksources which have a mask > 32bit + * we need to limit the max sleep time to have a good + * conversion precision. 10 minutes is still a reasonable + * amount. That results in a shift value of 24 for a + * clocksource with mask >= 40bit and f >= 4GHz. That maps to + * ~ 0.06ppm granularity for NTP. We apply the same 12.5% + * margin as we do in clocksource_max_deferment() + */ + sec = (cs->mask - (cs->mask >> 3)); + do_div(sec, freq); + do_div(sec, scale); + if (!sec) + sec = 1; + else if (sec > 600 && cs->mask > UINT_MAX) + sec = 600; + + clocks_calc_mult_shift(&cs->mult, &cs->shift, freq, + NSEC_PER_SEC / scale, sec * scale); + + /* + * for clocksources that have large mults, to avoid overflow. + * Since mult may be adjusted by ntp, add an safety extra margin + * + */ + cs->maxadj = clocksource_max_adjustment(cs); + while ((cs->mult + cs->maxadj < cs->mult) + || (cs->mult - cs->maxadj > cs->mult)) { + cs->mult >>= 1; + cs->shift--; + cs->maxadj = clocksource_max_adjustment(cs); } - list_add(&c->list, entry); - if (strlen(c->name) == strlen(override_name) && - !strcmp(c->name, override_name)) - clocksource_override = c; + cs->max_idle_ns = clocksource_max_deferment(cs); +} +EXPORT_SYMBOL_GPL(__clocksource_updatefreq_scale); + +/** + * __clocksource_register_scale - Used to install new clocksources + * @cs: clocksource to be registered + * @scale: Scale factor multiplied against freq to get clocksource hz + * @freq: clocksource frequency (cycles per second) divided by scale + * + * Returns -EBUSY if registration fails, zero otherwise. + * + * This *SHOULD NOT* be called directly! Please use the + * clocksource_register_hz() or clocksource_register_khz helper functions. + */ +int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq) +{ + + /* Initialize mult/shift and max_idle_ns */ + __clocksource_updatefreq_scale(cs, scale, freq); + /* Add clocksource to the clcoksource list */ + mutex_lock(&clocksource_mutex); + clocksource_enqueue(cs); + clocksource_enqueue_watchdog(cs); + clocksource_select(); + mutex_unlock(&clocksource_mutex); return 0; } +EXPORT_SYMBOL_GPL(__clocksource_register_scale); + /** * clocksource_register - Used to install new clocksources - * @t: clocksource to be registered + * @cs: clocksource to be registered * * Returns -EBUSY if registration fails, zero otherwise. */ -int clocksource_register(struct clocksource *c) +int clocksource_register(struct clocksource *cs) { - unsigned long flags; - int ret; - - spin_lock_irqsave(&clocksource_lock, flags); - ret = clocksource_enqueue(c); - if (!ret) - next_clocksource = select_clocksource(); - spin_unlock_irqrestore(&clocksource_lock, flags); - if (!ret) - clocksource_check_watchdog(c); - return ret; + /* calculate max adjustment for given mult/shift */ + cs->maxadj = clocksource_max_adjustment(cs); + WARN_ONCE(cs->mult + cs->maxadj < cs->mult, + "Clocksource %s might overflow on 11%% adjustment\n", + cs->name); + + /* calculate max idle time permitted for this clocksource */ + cs->max_idle_ns = clocksource_max_deferment(cs); + + mutex_lock(&clocksource_mutex); + clocksource_enqueue(cs); + clocksource_enqueue_watchdog(cs); + clocksource_select(); + mutex_unlock(&clocksource_mutex); + return 0; } EXPORT_SYMBOL(clocksource_register); +static void __clocksource_change_rating(struct clocksource *cs, int rating) +{ + list_del(&cs->list); + cs->rating = rating; + clocksource_enqueue(cs); +} + /** * clocksource_change_rating - Change the rating of a registered clocksource - * + * @cs: clocksource to be changed + * @rating: new rating */ void clocksource_change_rating(struct clocksource *cs, int rating) { - unsigned long flags; + mutex_lock(&clocksource_mutex); + __clocksource_change_rating(cs, rating); + clocksource_select(); + mutex_unlock(&clocksource_mutex); +} +EXPORT_SYMBOL(clocksource_change_rating); - spin_lock_irqsave(&clocksource_lock, flags); - list_del(&cs->list); - cs->rating = rating; - clocksource_enqueue(cs); - next_clocksource = select_clocksource(); - spin_unlock_irqrestore(&clocksource_lock, flags); +/* + * Unbind clocksource @cs. Called with clocksource_mutex held + */ +static int clocksource_unbind(struct clocksource *cs) +{ + /* + * I really can't convince myself to support this on hardware + * designed by lobotomized monkeys. + */ + if (clocksource_is_watchdog(cs)) + return -EBUSY; + + if (cs == curr_clocksource) { + /* Select and try to install a replacement clock source */ + clocksource_select_fallback(); + if (curr_clocksource == cs) + return -EBUSY; + } + clocksource_dequeue_watchdog(cs); + list_del_init(&cs->list); + return 0; } /** * clocksource_unregister - remove a registered clocksource + * @cs: clocksource to be unregistered */ -void clocksource_unregister(struct clocksource *cs) +int clocksource_unregister(struct clocksource *cs) { - unsigned long flags; + int ret = 0; - spin_lock_irqsave(&clocksource_lock, flags); - list_del(&cs->list); - if (clocksource_override == cs) - clocksource_override = NULL; - next_clocksource = select_clocksource(); - spin_unlock_irqrestore(&clocksource_lock, flags); + mutex_lock(&clocksource_mutex); + if (!list_empty(&cs->list)) + ret = clocksource_unbind(cs); + mutex_unlock(&clocksource_mutex); + return ret; } +EXPORT_SYMBOL(clocksource_unregister); #ifdef CONFIG_SYSFS /** * sysfs_show_current_clocksources - sysfs interface for current clocksource * @dev: unused + * @attr: unused * @buf: char buffer to be filled with clocksource list * * Provides sysfs interface for listing current clocksource. */ static ssize_t -sysfs_show_current_clocksources(struct sys_device *dev, - struct sysdev_attribute *attr, char *buf) +sysfs_show_current_clocksources(struct device *dev, + struct device_attribute *attr, char *buf) { ssize_t count = 0; - spin_lock_irq(&clocksource_lock); + mutex_lock(&clocksource_mutex); count = snprintf(buf, PAGE_SIZE, "%s\n", curr_clocksource->name); - spin_unlock_irq(&clocksource_lock); + mutex_unlock(&clocksource_mutex); return count; } +ssize_t sysfs_get_uname(const char *buf, char *dst, size_t cnt) +{ + size_t ret = cnt; + + /* strings from sysfs write are not 0 terminated! */ + if (!cnt || cnt >= CS_NAME_LEN) + return -EINVAL; + + /* strip of \n: */ + if (buf[cnt-1] == '\n') + cnt--; + if (cnt > 0) + memcpy(dst, buf, cnt); + dst[cnt] = 0; + return ret; +} + /** * sysfs_override_clocksource - interface for manually overriding clocksource * @dev: unused + * @attr: unused * @buf: name of override clocksource * @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, +static ssize_t sysfs_override_clocksource(struct device *dev, + struct device_attribute *attr, const char *buf, size_t count) { - struct clocksource *ovr = NULL; - size_t ret = count; - int len; + ssize_t ret; - /* strings from sysfs write are not 0 terminated! */ - if (count >= sizeof(override_name)) - return -EINVAL; + mutex_lock(&clocksource_mutex); - /* strip of \n: */ - if (buf[count-1] == '\n') - count--; + ret = sysfs_get_uname(buf, override_name, count); + if (ret >= 0) + clocksource_select(); - spin_lock_irq(&clocksource_lock); + mutex_unlock(&clocksource_mutex); - if (count > 0) - memcpy(override_name, buf, count); - override_name[count] = 0; + return ret; +} - len = strlen(override_name); - if (len) { - struct clocksource *cs; +/** + * sysfs_unbind_current_clocksource - interface for manually unbinding clocksource + * @dev: unused + * @attr: unused + * @buf: unused + * @count: length of buffer + * + * Takes input from sysfs interface for manually unbinding a clocksource. + */ +static ssize_t sysfs_unbind_clocksource(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct clocksource *cs; + char name[CS_NAME_LEN]; + ssize_t ret; - ovr = clocksource_override; - /* try to select it: */ - list_for_each_entry(cs, &clocksource_list, list) { - if (strlen(cs->name) == len && - !strcmp(cs->name, override_name)) - ovr = cs; - } - } + ret = sysfs_get_uname(buf, name, count); + if (ret < 0) + return ret; - /* Reselect, when the override name has changed */ - if (ovr != clocksource_override) { - clocksource_override = ovr; - next_clocksource = select_clocksource(); + ret = -ENODEV; + mutex_lock(&clocksource_mutex); + list_for_each_entry(cs, &clocksource_list, list) { + if (strcmp(cs->name, name)) + continue; + ret = clocksource_unbind(cs); + break; } + mutex_unlock(&clocksource_mutex); - spin_unlock_irq(&clocksource_lock); - - return ret; + return ret ? ret : count; } /** * sysfs_show_available_clocksources - sysfs interface for listing clocksource * @dev: unused + * @attr: unused * @buf: char buffer to be filled with clocksource list * * Provides sysfs interface for listing registered clocksources */ static ssize_t -sysfs_show_available_clocksources(struct sys_device *dev, - struct sysdev_attribute *attr, +sysfs_show_available_clocksources(struct device *dev, + struct device_attribute *attr, char *buf) { struct clocksource *src; ssize_t count = 0; - spin_lock_irq(&clocksource_lock); + mutex_lock(&clocksource_mutex); list_for_each_entry(src, &clocksource_list, list) { - count += snprintf(buf + count, + /* + * 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); count += snprintf(buf + count, max((ssize_t)PAGE_SIZE - count, (ssize_t)0), "\n"); @@ -475,35 +1026,41 @@ sysfs_show_available_clocksources(struct sys_device *dev, /* * Sysfs setup bits: */ -static SYSDEV_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, +static DEVICE_ATTR(current_clocksource, 0644, sysfs_show_current_clocksources, sysfs_override_clocksource); -static SYSDEV_ATTR(available_clocksource, 0444, +static DEVICE_ATTR(unbind_clocksource, 0200, NULL, sysfs_unbind_clocksource); + +static DEVICE_ATTR(available_clocksource, 0444, sysfs_show_available_clocksources, NULL); -static struct sysdev_class clocksource_sysclass = { +static struct bus_type clocksource_subsys = { .name = "clocksource", + .dev_name = "clocksource", }; -static struct sys_device device_clocksource = { +static struct device device_clocksource = { .id = 0, - .cls = &clocksource_sysclass, + .bus = &clocksource_subsys, }; static int __init init_clocksource_sysfs(void) { - int error = sysdev_class_register(&clocksource_sysclass); + int error = subsys_system_register(&clocksource_subsys, NULL); if (!error) - error = sysdev_register(&device_clocksource); + error = device_register(&device_clocksource); if (!error) - error = sysdev_create_file( + error = device_create_file( &device_clocksource, - &attr_current_clocksource); + &dev_attr_current_clocksource); if (!error) - error = sysdev_create_file( + error = device_create_file(&device_clocksource, + &dev_attr_unbind_clocksource); + if (!error) + error = device_create_file( &device_clocksource, - &attr_available_clocksource); + &dev_attr_available_clocksource); return error; } @@ -519,11 +1076,10 @@ 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; } |