summaryrefslogtreecommitdiffstats
path: root/kernel/time
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/clocksource.c48
-rw-r--r--kernel/time/ntp.c2
-rw-r--r--kernel/time/tick-sched.c84
-rw-r--r--kernel/time/timekeeping.c35
-rw-r--r--kernel/time/timer_list.c1
5 files changed, 136 insertions, 34 deletions
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 1f5dde63745..f08e99c1d56 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -625,6 +625,54 @@ static void clocksource_enqueue(struct clocksource *cs)
list_add(&cs->list, entry);
}
+
+/*
+ * Maximum time we expect to go between ticks. This includes idle
+ * tickless time. It provides the trade off between selecting a
+ * mult/shift pair that is very precise but can only handle a short
+ * period of time, vs. a mult/shift pair that can handle long periods
+ * of time but isn't as precise.
+ *
+ * This is a subsystem constant, and actual hardware limitations
+ * may override it (ie: clocksources that wrap every 3 seconds).
+ */
+#define MAX_UPDATE_LENGTH 5 /* Seconds */
+
+/**
+ * __clocksource_register_scale - Used to install new clocksources
+ * @t: 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)
+{
+
+ /*
+ * Ideally we want to use some of the limits used in
+ * clocksource_max_deferment, to provide a more informed
+ * MAX_UPDATE_LENGTH. But for now this just gets the
+ * register interface working properly.
+ */
+ clocks_calc_mult_shift(&cs->mult, &cs->shift, freq,
+ NSEC_PER_SEC/scale,
+ MAX_UPDATE_LENGTH*scale);
+ 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_GPL(__clocksource_register_scale);
+
+
/**
* clocksource_register - Used to install new clocksources
* @t: clocksource to be registered
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 7c0f180d6e9..c63116863a8 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -69,7 +69,7 @@ static s64 time_freq;
/* time at last adjustment (secs): */
static long time_reftime;
-long time_adjust;
+static long time_adjust;
/* constant (boot-param configurable) NTP tick adjustment (upscaled) */
static s64 ntp_tick_adj;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f992762d7f5..1d7b9bc1c03 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -150,14 +150,32 @@ static void tick_nohz_update_jiffies(ktime_t now)
touch_softlockup_watchdog();
}
+/*
+ * Updates the per cpu time idle statistics counters
+ */
+static void
+update_ts_time_stats(struct tick_sched *ts, ktime_t now, u64 *last_update_time)
+{
+ ktime_t delta;
+
+ if (ts->idle_active) {
+ delta = ktime_sub(now, ts->idle_entrytime);
+ ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ if (nr_iowait_cpu() > 0)
+ ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
+ ts->idle_entrytime = now;
+ }
+
+ if (last_update_time)
+ *last_update_time = ktime_to_us(now);
+
+}
+
static void tick_nohz_stop_idle(int cpu, ktime_t now)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
- ktime_t delta;
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_lastupdate = now;
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
+ update_ts_time_stats(ts, now, NULL);
ts->idle_active = 0;
sched_clock_idle_wakeup_event(0);
@@ -165,20 +183,32 @@ static void tick_nohz_stop_idle(int cpu, ktime_t now)
static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
{
- ktime_t now, delta;
+ ktime_t now;
now = ktime_get();
- if (ts->idle_active) {
- delta = ktime_sub(now, ts->idle_entrytime);
- ts->idle_lastupdate = now;
- ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
- }
+
+ update_ts_time_stats(ts, now, NULL);
+
ts->idle_entrytime = now;
ts->idle_active = 1;
sched_clock_idle_sleep_event();
return now;
}
+/**
+ * get_cpu_idle_time_us - get the total idle time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative idle time (since boot) for a given
+ * CPU, in microseconds. The idle time returned includes
+ * the iowait time (unlike what "top" and co report).
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
@@ -186,15 +216,38 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
if (!tick_nohz_enabled)
return -1;
- if (ts->idle_active)
- *last_update_time = ktime_to_us(ts->idle_lastupdate);
- else
- *last_update_time = ktime_to_us(ktime_get());
+ update_ts_time_stats(ts, ktime_get(), last_update_time);
return ktime_to_us(ts->idle_sleeptime);
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
+/*
+ * get_cpu_iowait_time_us - get the total iowait time of a cpu
+ * @cpu: CPU number to query
+ * @last_update_time: variable to store update time in
+ *
+ * Return the cummulative iowait time (since boot) for a given
+ * CPU, in microseconds.
+ *
+ * This time is measured via accounting rather than sampling,
+ * and is as accurate as ktime_get() is.
+ *
+ * This function returns -1 if NOHZ is not enabled.
+ */
+u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
+{
+ struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+
+ if (!tick_nohz_enabled)
+ return -1;
+
+ update_ts_time_stats(ts, ktime_get(), last_update_time);
+
+ return ktime_to_us(ts->iowait_sleeptime);
+}
+EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
+
/**
* tick_nohz_stop_sched_tick - stop the idle tick from the idle task
*
@@ -262,6 +315,9 @@ void tick_nohz_stop_sched_tick(int inidle)
goto end;
}
+ if (nohz_ratelimit(cpu))
+ goto end;
+
ts->idle_calls++;
/* Read jiffies and the time when jiffies were updated last */
do {
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 39f6177fafa..caf8d4d4f5c 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -165,13 +165,6 @@ struct timespec raw_time;
/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;
-static struct timespec xtime_cache __attribute__ ((aligned (16)));
-void update_xtime_cache(u64 nsec)
-{
- xtime_cache = xtime;
- timespec_add_ns(&xtime_cache, nsec);
-}
-
/* must hold xtime_lock */
void timekeeping_leap_insert(int leapsecond)
{
@@ -332,8 +325,6 @@ int do_settimeofday(struct timespec *tv)
xtime = *tv;
- update_xtime_cache(0);
-
timekeeper.ntp_error = 0;
ntp_clear();
@@ -559,7 +550,6 @@ void __init timekeeping_init(void)
}
set_normalized_timespec(&wall_to_monotonic,
-boot.tv_sec, -boot.tv_nsec);
- update_xtime_cache(0);
total_sleep_time.tv_sec = 0;
total_sleep_time.tv_nsec = 0;
write_sequnlock_irqrestore(&xtime_lock, flags);
@@ -593,7 +583,6 @@ static int timekeeping_resume(struct sys_device *dev)
wall_to_monotonic = timespec_sub(wall_to_monotonic, ts);
total_sleep_time = timespec_add_safe(total_sleep_time, ts);
}
- update_xtime_cache(0);
/* re-base the last cycle value */
timekeeper.clock->cycle_last = timekeeper.clock->read(timekeeper.clock);
timekeeper.ntp_error = 0;
@@ -788,7 +777,6 @@ void update_wall_time(void)
{
struct clocksource *clock;
cycle_t offset;
- u64 nsecs;
int shift = 0, maxshift;
/* Make sure we're fully resumed: */
@@ -847,7 +835,9 @@ void update_wall_time(void)
timekeeper.ntp_error += neg << timekeeper.ntp_error_shift;
}
- /* store full nanoseconds into xtime after rounding it up and
+
+ /*
+ * Store full nanoseconds into xtime after rounding it up and
* add the remainder to the error difference.
*/
xtime.tv_nsec = ((s64) timekeeper.xtime_nsec >> timekeeper.shift) + 1;
@@ -855,8 +845,15 @@ void update_wall_time(void)
timekeeper.ntp_error += timekeeper.xtime_nsec <<
timekeeper.ntp_error_shift;
- nsecs = clocksource_cyc2ns(offset, timekeeper.mult, timekeeper.shift);
- update_xtime_cache(nsecs);
+ /*
+ * Finally, make sure that after the rounding
+ * xtime.tv_nsec isn't larger then NSEC_PER_SEC
+ */
+ if (unlikely(xtime.tv_nsec >= NSEC_PER_SEC)) {
+ xtime.tv_nsec -= NSEC_PER_SEC;
+ xtime.tv_sec++;
+ second_overflow();
+ }
/* check to see if there is a new clocksource to use */
update_vsyscall(&xtime, timekeeper.clock, timekeeper.mult);
@@ -896,13 +893,13 @@ EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
unsigned long get_seconds(void)
{
- return xtime_cache.tv_sec;
+ return xtime.tv_sec;
}
EXPORT_SYMBOL(get_seconds);
struct timespec __current_kernel_time(void)
{
- return xtime_cache;
+ return xtime;
}
struct timespec current_kernel_time(void)
@@ -913,7 +910,7 @@ struct timespec current_kernel_time(void)
do {
seq = read_seqbegin(&xtime_lock);
- now = xtime_cache;
+ now = xtime;
} while (read_seqretry(&xtime_lock, seq));
return now;
@@ -928,7 +925,7 @@ struct timespec get_monotonic_coarse(void)
do {
seq = read_seqbegin(&xtime_lock);
- now = xtime_cache;
+ now = xtime;
mono = wall_to_monotonic;
} while (read_seqretry(&xtime_lock, seq));
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 1a4a7dd7877..ab8f5e33fa9 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -176,6 +176,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
P_ns(idle_waketime);
P_ns(idle_exittime);
P_ns(idle_sleeptime);
+ P_ns(iowait_sleeptime);
P(last_jiffies);
P(next_jiffies);
P_ns(idle_expires);