aboutsummaryrefslogtreecommitdiff
path: root/kernel/time
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/Kconfig2
-rw-r--r--kernel/time/Makefile5
-rw-r--r--kernel/time/alarmtimer.c20
-rw-r--r--kernel/time/clockevents.c50
-rw-r--r--kernel/time/jiffies.c6
-rw-r--r--kernel/time/ntp.c37
-rw-r--r--kernel/time/sched_clock.c69
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c106
-rw-r--r--kernel/time/tick-broadcast.c92
-rw-r--r--kernel/time/tick-common.c34
-rw-r--r--kernel/time/tick-internal.h16
-rw-r--r--kernel/time/tick-sched.c87
-rw-r--r--kernel/time/timekeeping.c68
-rw-r--r--kernel/time/timekeeping_debug.c2
14 files changed, 421 insertions, 173 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 3ce6e8c5f3f..f448513a45e 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -124,7 +124,7 @@ config NO_HZ_FULL
endchoice
config NO_HZ_FULL_ALL
- bool "Full dynticks system on all CPUs by default"
+ bool "Full dynticks system on all CPUs by default (except CPU 0)"
depends on NO_HZ_FULL
help
If the user doesn't pass the nohz_full boot option to
diff --git a/kernel/time/Makefile b/kernel/time/Makefile
index 9250130646f..57a413fd0eb 100644
--- a/kernel/time/Makefile
+++ b/kernel/time/Makefile
@@ -3,7 +3,10 @@ obj-y += timeconv.o posix-clock.o alarmtimer.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS_BUILD) += clockevents.o
obj-$(CONFIG_GENERIC_CLOCKEVENTS) += tick-common.o
-obj-$(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) += tick-broadcast.o
+ifeq ($(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST),y)
+ obj-y += tick-broadcast.o
+ obj-$(CONFIG_TICK_ONESHOT) += tick-broadcast-hrtimer.o
+endif
obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o
obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o
obj-$(CONFIG_TICK_ONESHOT) += tick-sched.o
diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 88c9c65a430..fe75444ae7e 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -585,9 +585,14 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
struct itimerspec *new_setting,
struct itimerspec *old_setting)
{
+ ktime_t exp;
+
if (!rtcdev)
return -ENOTSUPP;
+ if (flags & ~TIMER_ABSTIME)
+ return -EINVAL;
+
if (old_setting)
alarm_timer_get(timr, old_setting);
@@ -597,8 +602,16 @@ static int alarm_timer_set(struct k_itimer *timr, int flags,
/* start the timer */
timr->it.alarm.interval = timespec_to_ktime(new_setting->it_interval);
- alarm_start(&timr->it.alarm.alarmtimer,
- timespec_to_ktime(new_setting->it_value));
+ exp = timespec_to_ktime(new_setting->it_value);
+ /* Convert (if necessary) to absolute time */
+ if (flags != TIMER_ABSTIME) {
+ ktime_t now;
+
+ now = alarm_bases[timr->it.alarm.alarmtimer.type].gettime();
+ exp = ktime_add(now, exp);
+ }
+
+ alarm_start(&timr->it.alarm.alarmtimer, exp);
return 0;
}
@@ -730,6 +743,9 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
if (!alarmtimer_get_rtcdev())
return -ENOTSUPP;
+ if (flags & ~TIMER_ABSTIME)
+ return -EINVAL;
+
if (!capable(CAP_WAKE_ALARM))
return -EPERM;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 086ad6043bc..9c94c19f130 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -146,7 +146,8 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
{
/* Nothing to do if we already reached the limit */
if (dev->min_delta_ns >= MIN_DELTA_LIMIT) {
- printk(KERN_WARNING "CE: Reprogramming failure. Giving up\n");
+ printk_deferred(KERN_WARNING
+ "CE: Reprogramming failure. Giving up\n");
dev->next_event.tv64 = KTIME_MAX;
return -ETIME;
}
@@ -159,9 +160,10 @@ static int clockevents_increase_min_delta(struct clock_event_device *dev)
if (dev->min_delta_ns > MIN_DELTA_LIMIT)
dev->min_delta_ns = MIN_DELTA_LIMIT;
- printk(KERN_WARNING "CE: %s increased min_delta_ns to %llu nsec\n",
- dev->name ? dev->name : "?",
- (unsigned long long) dev->min_delta_ns);
+ printk_deferred(KERN_WARNING
+ "CE: %s increased min_delta_ns to %llu nsec\n",
+ dev->name ? dev->name : "?",
+ (unsigned long long) dev->min_delta_ns);
return 0;
}
@@ -439,6 +441,19 @@ void clockevents_config_and_register(struct clock_event_device *dev,
}
EXPORT_SYMBOL_GPL(clockevents_config_and_register);
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq)
+{
+ clockevents_config(dev, freq);
+
+ if (dev->mode == CLOCK_EVT_MODE_ONESHOT)
+ return clockevents_program_event(dev, dev->next_event, false);
+
+ if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
+ dev->set_mode(CLOCK_EVT_MODE_PERIODIC, dev);
+
+ return 0;
+}
+
/**
* clockevents_update_freq - Update frequency and reprogram a clock event device.
* @dev: device to modify
@@ -446,17 +461,22 @@ EXPORT_SYMBOL_GPL(clockevents_config_and_register);
*
* Reconfigure and reprogram a clock event device in oneshot
* mode. Must be called on the cpu for which the device delivers per
- * cpu timer events with interrupts disabled! Returns 0 on success,
- * -ETIME when the event is in the past.
+ * cpu timer events. If called for the broadcast device the core takes
+ * care of serialization.
+ *
+ * Returns 0 on success, -ETIME when the event is in the past.
*/
int clockevents_update_freq(struct clock_event_device *dev, u32 freq)
{
- clockevents_config(dev, freq);
-
- if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
- return 0;
+ unsigned long flags;
+ int ret;
- return clockevents_program_event(dev, dev->next_event, false);
+ local_irq_save(flags);
+ ret = tick_broadcast_update_freq(dev, freq);
+ if (ret == -ENODEV)
+ ret = __clockevents_update_freq(dev, freq);
+ local_irq_restore(flags);
+ return ret;
}
/*
@@ -524,12 +544,13 @@ void clockevents_resume(void)
#ifdef CONFIG_GENERIC_CLOCKEVENTS
/**
* clockevents_notify - notification about relevant events
+ * Returns 0 on success, any other value on error
*/
-void clockevents_notify(unsigned long reason, void *arg)
+int clockevents_notify(unsigned long reason, void *arg)
{
struct clock_event_device *dev, *tmp;
unsigned long flags;
- int cpu;
+ int cpu, ret = 0;
raw_spin_lock_irqsave(&clockevents_lock, flags);
@@ -542,7 +563,7 @@ void clockevents_notify(unsigned long reason, void *arg)
case CLOCK_EVT_NOTIFY_BROADCAST_ENTER:
case CLOCK_EVT_NOTIFY_BROADCAST_EXIT:
- tick_broadcast_oneshot_control(reason);
+ ret = tick_broadcast_oneshot_control(reason);
break;
case CLOCK_EVT_NOTIFY_CPU_DYING:
@@ -585,6 +606,7 @@ void clockevents_notify(unsigned long reason, void *arg)
break;
}
raw_spin_unlock_irqrestore(&clockevents_lock, flags);
+ return ret;
}
EXPORT_SYMBOL_GPL(clockevents_notify);
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7a925ba456f..a6a5bf53e86 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -51,7 +51,13 @@
* HZ shrinks, so values greater than 8 overflow 32bits when
* HZ=100.
*/
+#if HZ < 34
+#define JIFFIES_SHIFT 6
+#elif HZ < 67
+#define JIFFIES_SHIFT 7
+#else
#define JIFFIES_SHIFT 8
+#endif
static cycle_t jiffies_read(struct clocksource *cs)
{
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index af8d1d4f3d5..33db43a3951 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -165,21 +165,21 @@ static inline void pps_set_freq(s64 freq)
static inline int is_error_status(int status)
{
- return (time_status & (STA_UNSYNC|STA_CLOCKERR))
+ return (status & (STA_UNSYNC|STA_CLOCKERR))
/* PPS signal lost when either PPS time or
* PPS frequency synchronization requested
*/
- || ((time_status & (STA_PPSFREQ|STA_PPSTIME))
- && !(time_status & STA_PPSSIGNAL))
+ || ((status & (STA_PPSFREQ|STA_PPSTIME))
+ && !(status & STA_PPSSIGNAL))
/* PPS jitter exceeded when
* PPS time synchronization requested */
- || ((time_status & (STA_PPSTIME|STA_PPSJITTER))
+ || ((status & (STA_PPSTIME|STA_PPSJITTER))
== (STA_PPSTIME|STA_PPSJITTER))
/* PPS wander exceeded or calibration error when
* PPS frequency synchronization requested
*/
- || ((time_status & STA_PPSFREQ)
- && (time_status & (STA_PPSWANDER|STA_PPSERROR)));
+ || ((status & STA_PPSFREQ)
+ && (status & (STA_PPSWANDER|STA_PPSERROR)));
}
static inline void pps_fill_timex(struct timex *txc)
@@ -514,12 +514,13 @@ static void sync_cmos_clock(struct work_struct *work)
next.tv_sec++;
next.tv_nsec -= NSEC_PER_SEC;
}
- schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
+ queue_delayed_work(system_power_efficient_wq,
+ &sync_cmos_work, timespec_to_jiffies(&next));
}
void ntp_notify_cmos_timer(void)
{
- schedule_delayed_work(&sync_cmos_work, 0);
+ queue_delayed_work(system_power_efficient_wq, &sync_cmos_work, 0);
}
#else
@@ -785,8 +786,9 @@ static long hardpps_update_freq(struct pps_normtime freq_norm)
time_status |= STA_PPSERROR;
pps_errcnt++;
pps_dec_freq_interval();
- pr_err("hardpps: PPSERROR: interval too long - %ld s\n",
- freq_norm.sec);
+ printk_deferred(KERN_ERR
+ "hardpps: PPSERROR: interval too long - %ld s\n",
+ freq_norm.sec);
return 0;
}
@@ -799,7 +801,8 @@ static long hardpps_update_freq(struct pps_normtime freq_norm)
delta = shift_right(ftemp - pps_freq, NTP_SCALE_SHIFT);
pps_freq = ftemp;
if (delta > PPS_MAXWANDER || delta < -PPS_MAXWANDER) {
- pr_warning("hardpps: PPSWANDER: change=%ld\n", delta);
+ printk_deferred(KERN_WARNING
+ "hardpps: PPSWANDER: change=%ld\n", delta);
time_status |= STA_PPSWANDER;
pps_stbcnt++;
pps_dec_freq_interval();
@@ -843,8 +846,9 @@ static void hardpps_update_phase(long error)
* the time offset is updated.
*/
if (jitter > (pps_jitter << PPS_POPCORN)) {
- pr_warning("hardpps: PPSJITTER: jitter=%ld, limit=%ld\n",
- jitter, (pps_jitter << PPS_POPCORN));
+ printk_deferred(KERN_WARNING
+ "hardpps: PPSJITTER: jitter=%ld, limit=%ld\n",
+ jitter, (pps_jitter << PPS_POPCORN));
time_status |= STA_PPSJITTER;
pps_jitcnt++;
} else if (time_status & STA_PPSTIME) {
@@ -901,7 +905,7 @@ void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
time_status |= STA_PPSJITTER;
/* restart the frequency calibration interval */
pps_fbase = *raw_ts;
- pr_err("hardpps: PPSJITTER: bad pulse\n");
+ printk_deferred(KERN_ERR "hardpps: PPSJITTER: bad pulse\n");
return;
}
@@ -922,7 +926,10 @@ void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
static int __init ntp_tick_adj_setup(char *str)
{
- ntp_tick_adj = simple_strtol(str, NULL, 0);
+ int rc = kstrtol(str, 0, (long *)&ntp_tick_adj);
+
+ if (rc)
+ return rc;
ntp_tick_adj <<= NTP_SCALE_SHIFT;
return 1;
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 68b79937598..01d2d15aa66 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -49,13 +49,6 @@ static u64 notrace jiffy_sched_clock_read(void)
return (u64)(jiffies - INITIAL_JIFFIES);
}
-static u32 __read_mostly (*read_sched_clock_32)(void);
-
-static u64 notrace read_sched_clock_32_wrapper(void)
-{
- return read_sched_clock_32();
-}
-
static u64 __read_mostly (*read_sched_clock)(void) = jiffy_sched_clock_read;
static inline u64 notrace cyc_to_ns(u64 cyc, u32 mult, u32 shift)
@@ -74,7 +67,7 @@ unsigned long long notrace sched_clock(void)
return cd.epoch_ns;
do {
- seq = read_seqcount_begin(&cd.seq);
+ seq = raw_read_seqcount_begin(&cd.seq);
epoch_cyc = cd.epoch_cyc;
epoch_ns = cd.epoch_ns;
} while (read_seqcount_retry(&cd.seq, seq));
@@ -99,10 +92,10 @@ static void notrace update_sched_clock(void)
cd.mult, cd.shift);
raw_local_irq_save(flags);
- write_seqcount_begin(&cd.seq);
+ raw_write_seqcount_begin(&cd.seq);
cd.epoch_ns = ns;
cd.epoch_cyc = cyc;
- write_seqcount_end(&cd.seq);
+ raw_write_seqcount_end(&cd.seq);
raw_local_irq_restore(flags);
}
@@ -116,20 +109,42 @@ static enum hrtimer_restart sched_clock_poll(struct hrtimer *hrt)
void __init sched_clock_register(u64 (*read)(void), int bits,
unsigned long rate)
{
+ u64 res, wrap, new_mask, new_epoch, cyc, ns;
+ u32 new_mult, new_shift;
+ ktime_t new_wrap_kt;
unsigned long r;
- u64 res, wrap;
char r_unit;
if (cd.rate > rate)
return;
WARN_ON(!irqs_disabled());
- read_sched_clock = read;
- sched_clock_mask = CLOCKSOURCE_MASK(bits);
- cd.rate = rate;
/* calculate the mult/shift to convert counter ticks to ns. */
- clocks_calc_mult_shift(&cd.mult, &cd.shift, rate, NSEC_PER_SEC, 3600);
+ clocks_calc_mult_shift(&new_mult, &new_shift, rate, NSEC_PER_SEC, 3600);
+
+ new_mask = CLOCKSOURCE_MASK(bits);
+
+ /* calculate how many ns until we wrap */
+ wrap = clocks_calc_max_nsecs(new_mult, new_shift, 0, new_mask);
+ new_wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
+
+ /* update epoch for new counter and update epoch_ns from old counter*/
+ new_epoch = read();
+ cyc = read_sched_clock();
+ ns = cd.epoch_ns + cyc_to_ns((cyc - cd.epoch_cyc) & sched_clock_mask,
+ cd.mult, cd.shift);
+
+ raw_write_seqcount_begin(&cd.seq);
+ read_sched_clock = read;
+ sched_clock_mask = new_mask;
+ cd.rate = rate;
+ cd.wrap_kt = new_wrap_kt;
+ cd.mult = new_mult;
+ cd.shift = new_shift;
+ cd.epoch_cyc = new_epoch;
+ cd.epoch_ns = ns;
+ raw_write_seqcount_end(&cd.seq);
r = rate;
if (r >= 4000000) {
@@ -141,22 +156,12 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
} else
r_unit = ' ';
- /* calculate how many ns until we wrap */
- wrap = clocks_calc_max_nsecs(cd.mult, cd.shift, 0, sched_clock_mask);
- cd.wrap_kt = ns_to_ktime(wrap - (wrap >> 3));
-
/* calculate the ns resolution of this counter */
- res = cyc_to_ns(1ULL, cd.mult, cd.shift);
+ res = cyc_to_ns(1ULL, new_mult, new_shift);
+
pr_info("sched_clock: %u bits at %lu%cHz, resolution %lluns, wraps every %lluns\n",
bits, r, r_unit, res, wrap);
- update_sched_clock();
-
- /*
- * Ensure that sched_clock() starts off at 0ns
- */
- cd.epoch_ns = 0;
-
/* Enable IRQ time accounting if we have a fast enough sched_clock */
if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
enable_sched_clock_irqtime();
@@ -164,12 +169,6 @@ void __init sched_clock_register(u64 (*read)(void), int bits,
pr_debug("Registered %pF as sched_clock source\n", read);
}
-void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
-{
- read_sched_clock_32 = read;
- sched_clock_register(read_sched_clock_32_wrapper, bits, rate);
-}
-
void __init sched_clock_postinit(void)
{
/*
@@ -192,7 +191,8 @@ void __init sched_clock_postinit(void)
static int sched_clock_suspend(void)
{
- sched_clock_poll(&sched_clock_timer);
+ update_sched_clock();
+ hrtimer_cancel(&sched_clock_timer);
cd.suspended = true;
return 0;
}
@@ -200,6 +200,7 @@ static int sched_clock_suspend(void)
static void sched_clock_resume(void)
{
cd.epoch_cyc = read_sched_clock();
+ hrtimer_start(&sched_clock_timer, cd.wrap_kt, HRTIMER_MODE_REL);
cd.suspended = false;
}
diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
new file mode 100644
index 00000000000..eb682d5c697
--- /dev/null
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -0,0 +1,106 @@
+/*
+ * linux/kernel/time/tick-broadcast-hrtimer.c
+ * This file emulates a local clock event device
+ * via a pseudo clock device.
+ */
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/clockchips.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+
+#include "tick-internal.h"
+
+static struct hrtimer bctimer;
+
+static void bc_set_mode(enum clock_event_mode mode,
+ struct clock_event_device *bc)
+{
+ switch (mode) {
+ case CLOCK_EVT_MODE_SHUTDOWN:
+ /*
+ * Note, we cannot cancel the timer here as we might
+ * run into the following live lock scenario:
+ *
+ * cpu 0 cpu1
+ * lock(broadcast_lock);
+ * hrtimer_interrupt()
+ * bc_handler()
+ * tick_handle_oneshot_broadcast();
+ * lock(broadcast_lock);
+ * hrtimer_cancel()
+ * wait_for_callback()
+ */
+ hrtimer_try_to_cancel(&bctimer);
+ break;
+ default:
+ break;
+ }
+}
+
+/*
+ * This is called from the guts of the broadcast code when the cpu
+ * which is about to enter idle has the earliest broadcast timer event.
+ */
+static int bc_set_next(ktime_t expires, struct clock_event_device *bc)
+{
+ /*
+ * We try to cancel the timer first. If the callback is on
+ * flight on some other cpu then we let it handle it. If we
+ * were able to cancel the timer nothing can rearm it as we
+ * own broadcast_lock.
+ *
+ * However we can also be called from the event handler of
+ * ce_broadcast_hrtimer itself when it expires. We cannot
+ * restart the timer because we are in the callback, but we
+ * can set the expiry time and let the callback return
+ * HRTIMER_RESTART.
+ */
+ if (hrtimer_try_to_cancel(&bctimer) >= 0) {
+ hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED);
+ /* Bind the "device" to the cpu */
+ bc->bound_on = smp_processor_id();
+ } else if (bc->bound_on == smp_processor_id()) {
+ hrtimer_set_expires(&bctimer, expires);
+ }
+ return 0;
+}
+
+static struct clock_event_device ce_broadcast_hrtimer = {
+ .set_mode = bc_set_mode,
+ .set_next_ktime = bc_set_next,
+ .features = CLOCK_EVT_FEAT_ONESHOT |
+ CLOCK_EVT_FEAT_KTIME |
+ CLOCK_EVT_FEAT_HRTIMER,
+ .rating = 0,
+ .bound_on = -1,
+ .min_delta_ns = 1,
+ .max_delta_ns = KTIME_MAX,
+ .min_delta_ticks = 1,
+ .max_delta_ticks = ULONG_MAX,
+ .mult = 1,
+ .shift = 0,
+ .cpumask = cpu_all_mask,
+};
+
+static enum hrtimer_restart bc_handler(struct hrtimer *t)
+{
+ ce_broadcast_hrtimer.event_handler(&ce_broadcast_hrtimer);
+
+ if (ce_broadcast_hrtimer.next_event.tv64 == KTIME_MAX)
+ return HRTIMER_NORESTART;
+
+ return HRTIMER_RESTART;
+}
+
+void tick_setup_hrtimer_broadcast(void)
+{
+ hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ bctimer.function = bc_handler;
+ clockevents_register_device(&ce_broadcast_hrtimer);
+}
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 9532690daaa..64c5990fd50 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -120,6 +120,19 @@ int tick_is_broadcast_device(struct clock_event_device *dev)
return (dev && tick_broadcast_device.evtdev == dev);
}
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq)
+{
+ int ret = -ENODEV;
+
+ if (tick_is_broadcast_device(dev)) {
+ raw_spin_lock(&tick_broadcast_lock);
+ ret = __clockevents_update_freq(dev, freq);
+ raw_spin_unlock(&tick_broadcast_lock);
+ }
+ return ret;
+}
+
+
static void err_broadcast(const struct cpumask *mask)
{
pr_crit_once("Failed to broadcast timer tick. Some CPUs may be unresponsive.\n");
@@ -272,12 +285,8 @@ static void tick_do_broadcast(struct cpumask *mask)
*/
static void tick_do_periodic_broadcast(void)
{
- raw_spin_lock(&tick_broadcast_lock);
-
cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
tick_do_broadcast(tmpmask);
-
- raw_spin_unlock(&tick_broadcast_lock);
}
/*
@@ -287,13 +296,15 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
{
ktime_t next;
+ raw_spin_lock(&tick_broadcast_lock);
+
tick_do_periodic_broadcast();
/*
* The device is in periodic mode. No reprogramming necessary:
*/
if (dev->mode == CLOCK_EVT_MODE_PERIODIC)
- return;
+ goto unlock;
/*
* Setup the next period for devices, which do not have
@@ -306,9 +317,11 @@ static void tick_handle_periodic_broadcast(struct clock_event_device *dev)
next = ktime_add(next, tick_period);
if (!clockevents_program_event(dev, next, false))
- return;
+ goto unlock;
tick_do_periodic_broadcast();
}
+unlock:
+ raw_spin_unlock(&tick_broadcast_lock);
}
/*
@@ -538,10 +551,10 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
* Called from irq_enter() when idle was interrupted to reenable the
* per cpu device.
*/
-void tick_check_oneshot_broadcast(int cpu)
+void tick_check_oneshot_broadcast_this_cpu(void)
{
- if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
- struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
+ if (cpumask_test_cpu(smp_processor_id(), tick_broadcast_oneshot_mask)) {
+ struct tick_device *td = &__get_cpu_var(tick_cpu_device);
/*
* We might be in the middle of switching over from
@@ -630,24 +643,61 @@ again:
raw_spin_unlock(&tick_broadcast_lock);
}
+static int broadcast_needs_cpu(struct clock_event_device *bc, int cpu)
+{
+ if (!(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+ return 0;
+ if (bc->next_event.tv64 == KTIME_MAX)
+ return 0;
+ return bc->bound_on == cpu ? -EBUSY : 0;
+}
+
+static void broadcast_shutdown_local(struct clock_event_device *bc,
+ struct clock_event_device *dev)
+{
+ /*
+ * For hrtimer based broadcasting we cannot shutdown the cpu
+ * local device if our own event is the first one to expire or
+ * if we own the broadcast timer.
+ */
+ if (bc->features & CLOCK_EVT_FEAT_HRTIMER) {
+ if (broadcast_needs_cpu(bc, smp_processor_id()))
+ return;
+ if (dev->next_event.tv64 < bc->next_event.tv64)
+ return;
+ }
+ clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+}
+
+static void broadcast_move_bc(int deadcpu)
+{
+ struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+ if (!bc || !broadcast_needs_cpu(bc, deadcpu))
+ return;
+ /* This moves the broadcast assignment to this cpu */
+ clockevents_program_event(bc, bc->next_event, 1);
+}
+
/*
* Powerstate information: The system enters/leaves a state, where
* affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
*/
-void tick_broadcast_oneshot_control(unsigned long reason)
+int tick_broadcast_oneshot_control(unsigned long reason)
{
struct clock_event_device *bc, *dev;
struct tick_device *td;
unsigned long flags;
ktime_t now;
- int cpu;
+ int cpu, ret = 0;
/*
* Periodic mode does not care about the enter/exit of power
* states
*/
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
- return;
+ return 0;
/*
* We are called with preemtion disabled from the depth of the
@@ -658,7 +708,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
dev = td->evtdev;
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
- return;
+ return 0;
bc = tick_broadcast_device.evtdev;
@@ -666,7 +716,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
- clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
+ broadcast_shutdown_local(bc, dev);
/*
* We only reprogram the broadcast timer if we
* did not mark ourself in the force mask and
@@ -679,6 +729,16 @@ void tick_broadcast_oneshot_control(unsigned long reason)
dev->next_event.tv64 < bc->next_event.tv64)
tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
}
+ /*
+ * If the current CPU owns the hrtimer broadcast
+ * mechanism, it cannot go deep idle and we remove the
+ * CPU from the broadcast mask. We don't have to go
+ * through the EXIT path as the local timer is not
+ * shutdown.
+ */
+ ret = broadcast_needs_cpu(bc, cpu);
+ if (ret)
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
} else {
if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
@@ -746,6 +806,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
}
out:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
+ return ret;
}
/*
@@ -756,6 +817,7 @@ out:
static void tick_broadcast_clear_oneshot(int cpu)
{
cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
+ cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
}
static void tick_broadcast_init_next_event(struct cpumask *mask,
@@ -851,6 +913,8 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
cpumask_clear_cpu(cpu, tick_broadcast_pending_mask);
cpumask_clear_cpu(cpu, tick_broadcast_force_mask);
+ broadcast_move_bc(cpu);
+
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 64522ecdfe0..0a0608edeb2 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -33,6 +33,21 @@ DEFINE_PER_CPU(struct tick_device, tick_cpu_device);
*/
ktime_t tick_next_period;
ktime_t tick_period;
+
+/*
+ * tick_do_timer_cpu is a timer core internal variable which holds the CPU NR
+ * which is responsible for calling do_timer(), i.e. the timekeeping stuff. This
+ * variable has two functions:
+ *
+ * 1) Prevent a thundering herd issue of a gazillion of CPUs trying to grab the
+ * timekeeping lock all at once. Only the CPU which is assigned to do the
+ * update is handling it.
+ *
+ * 2) Hand off the duty in the NOHZ idle case by setting the value to
+ * TICK_DO_TIMER_NONE, i.e. a non existing CPU. So the next cpu which looks
+ * at it will take over and keep the time keeping alive. The handover
+ * procedure also covers cpu hotplug.
+ */
int tick_do_timer_cpu __read_mostly = TICK_DO_TIMER_BOOT;
/*
@@ -70,6 +85,7 @@ static void tick_periodic(int cpu)
do_timer(1);
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
update_process_times(user_mode(get_irq_regs()));
@@ -82,18 +98,19 @@ static void tick_periodic(int cpu)
void tick_handle_periodic(struct clock_event_device *dev)
{
int cpu = smp_processor_id();
- ktime_t next;
+ ktime_t next = dev->next_event;
tick_periodic(cpu);
if (dev->mode != CLOCK_EVT_MODE_ONESHOT)
return;
- /*
- * Setup the next period for devices, which do not have
- * periodic mode:
- */
- next = ktime_add(dev->next_event, tick_period);
for (;;) {
+ /*
+ * Setup the next period for devices, which do not have
+ * periodic mode:
+ */
+ next = ktime_add(next, tick_period);
+
if (!clockevents_program_event(dev, next, false))
return;
/*
@@ -102,12 +119,11 @@ void tick_handle_periodic(struct clock_event_device *dev)
* to be sure we're using a real hardware clocksource.
* Otherwise we could get trapped in an infinite
* loop, as the tick_periodic() increments jiffies,
- * when then will increment time, posibly causing
+ * which then will increment time, possibly causing
* the loop to trigger again and again.
*/
if (timekeeping_valid_for_hres())
tick_periodic(cpu);
- next = ktime_add(next, tick_period);
}
}
@@ -260,7 +276,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
bool tick_check_replacement(struct clock_event_device *curdev,
struct clock_event_device *newdev)
{
- if (tick_check_percpu(curdev, newdev, smp_processor_id()))
+ if (!tick_check_percpu(curdev, newdev, smp_processor_id()))
return false;
return tick_check_preferred(curdev, newdev);
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 18e71f7fbc2..7ab92b19965 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -46,23 +46,23 @@ extern int tick_switch_to_oneshot(void (*handler)(struct clock_event_device *));
extern void tick_resume_oneshot(void);
# ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
extern void tick_broadcast_setup_oneshot(struct clock_event_device *bc);
-extern void tick_broadcast_oneshot_control(unsigned long reason);
+extern int tick_broadcast_oneshot_control(unsigned long reason);
extern void tick_broadcast_switch_to_oneshot(void);
extern void tick_shutdown_broadcast_oneshot(unsigned int *cpup);
extern int tick_resume_broadcast_oneshot(struct clock_event_device *bc);
extern int tick_broadcast_oneshot_active(void);
-extern void tick_check_oneshot_broadcast(int cpu);
+extern void tick_check_oneshot_broadcast_this_cpu(void);
bool tick_broadcast_oneshot_available(void);
# else /* BROADCAST */
static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
static inline void tick_broadcast_switch_to_oneshot(void) { }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_broadcast_oneshot_active(void) { return 0; }
-static inline void tick_check_oneshot_broadcast(int cpu) { }
+static inline void tick_check_oneshot_broadcast_this_cpu(void) { }
static inline bool tick_broadcast_oneshot_available(void) { return true; }
# endif /* !BROADCAST */
@@ -87,7 +87,7 @@ static inline void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
{
BUG();
}
-static inline void tick_broadcast_oneshot_control(unsigned long reason) { }
+static inline int tick_broadcast_oneshot_control(unsigned long reason) { return 0; }
static inline void tick_shutdown_broadcast_oneshot(unsigned int *cpup) { }
static inline int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
{
@@ -111,6 +111,7 @@ extern int tick_resume_broadcast(void);
extern void tick_broadcast_init(void);
extern void
tick_set_periodic_handler(struct clock_event_device *dev, int broadcast);
+int tick_broadcast_update_freq(struct clock_event_device *dev, u32 freq);
#else /* !BROADCAST */
@@ -133,6 +134,8 @@ static inline void tick_shutdown_broadcast(unsigned int *cpup) { }
static inline void tick_suspend_broadcast(void) { }
static inline int tick_resume_broadcast(void) { return 0; }
static inline void tick_broadcast_init(void) { }
+static inline int tick_broadcast_update_freq(struct clock_event_device *dev,
+ u32 freq) { return -ENODEV; }
/*
* Set the periodic handler in non broadcast mode
@@ -152,6 +155,9 @@ static inline int tick_device_is_functional(struct clock_event_device *dev)
return !(dev->features & CLOCK_EVT_FEAT_DUMMY);
}
+int __clockevents_update_freq(struct clock_event_device *dev, u32 freq);
+
#endif
extern void do_timer(unsigned long ticks);
+extern void update_wall_time(void);
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3612fc77f83..6558b7ac112 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -84,8 +84,12 @@ static void tick_do_update_jiffies64(ktime_t now)
/* Keep the tick_next_period variable up to date */
tick_next_period = ktime_add(last_jiffies_update, tick_period);
+ } else {
+ write_sequnlock(&jiffies_lock);
+ return;
}
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
/*
@@ -177,7 +181,7 @@ static bool can_stop_full_tick(void)
* TODO: kick full dynticks CPUs when
* sched_clock_stable is set.
*/
- if (!sched_clock_stable) {
+ if (!sched_clock_stable()) {
trace_tick_stop(0, "unstable sched clock\n");
/*
* Don't allow the user to think they can get
@@ -361,8 +365,8 @@ void __init tick_nohz_init(void)
/*
* NO HZ enabled ?
*/
-int tick_nohz_enabled __read_mostly = 1;
-
+static int tick_nohz_enabled __read_mostly = 1;
+int tick_nohz_active __read_mostly;
/*
* Enable / Disable tickless mode
*/
@@ -391,11 +395,9 @@ __setup("nohz=", setup_tick_nohz);
*/
static void tick_nohz_update_jiffies(ktime_t now)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
unsigned long flags;
- ts->idle_waketime = now;
+ __this_cpu_write(tick_cpu_sched.idle_waketime, now);
local_irq_save(flags);
tick_do_update_jiffies64(now);
@@ -426,17 +428,15 @@ update_ts_time_stats(int cpu, struct tick_sched *ts, ktime_t now, u64 *last_upda
}
-static void tick_nohz_stop_idle(int cpu, ktime_t now)
+static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
-
- update_ts_time_stats(cpu, ts, now, NULL);
+ update_ts_time_stats(smp_processor_id(), ts, now, NULL);
ts->idle_active = 0;
sched_clock_idle_wakeup_event(0);
}
-static ktime_t tick_nohz_start_idle(int cpu, struct tick_sched *ts)
+static ktime_t tick_nohz_start_idle(struct tick_sched *ts)
{
ktime_t now = ktime_get();
@@ -465,7 +465,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, idle;
- if (!tick_nohz_enabled)
+ if (!tick_nohz_active)
return -1;
now = ktime_get();
@@ -506,7 +506,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t now, iowait;
- if (!tick_nohz_enabled)
+ if (!tick_nohz_active)
return -1;
now = ktime_get();
@@ -536,12 +536,13 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
u64 time_delta;
+ time_delta = timekeeping_max_deferment();
+
/* Read jiffies and the time when jiffies were updated last */
do {
seq = read_seqbegin(&jiffies_lock);
last_update = last_jiffies_update;
last_jiffies = jiffies;
- time_delta = timekeeping_max_deferment();
} while (read_seqretry(&jiffies_lock, seq));
if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) ||
@@ -681,18 +682,18 @@ out:
static void tick_nohz_full_stop_tick(struct tick_sched *ts)
{
#ifdef CONFIG_NO_HZ_FULL
- int cpu = smp_processor_id();
+ int cpu = smp_processor_id();
- if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
- return;
+ if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
+ return;
- if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
- return;
+ if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
+ return;
- if (!can_stop_full_tick())
- return;
+ if (!can_stop_full_tick())
+ return;
- tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
+ tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
#endif
}
@@ -711,8 +712,10 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
return false;
}
- if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
+ if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) {
+ ts->sleep_length = (ktime_t) { .tv64 = NSEC_PER_SEC/HZ };
return false;
+ }
if (need_resched())
return false;
@@ -752,7 +755,7 @@ static void __tick_nohz_idle_enter(struct tick_sched *ts)
ktime_t now, expires;
int cpu = smp_processor_id();
- now = tick_nohz_start_idle(cpu, ts);
+ now = tick_nohz_start_idle(ts);
if (can_stop_idle_tick(cpu, ts)) {
int was_stopped = ts->tick_stopped;
@@ -799,11 +802,6 @@ void tick_nohz_idle_enter(void)
local_irq_disable();
ts = &__get_cpu_var(tick_cpu_sched);
- /*
- * set ts->inidle unconditionally. even if the system did not
- * switch to nohz mode the cpu frequency governers rely on the
- * update of the idle time accounting in tick_nohz_start_idle().
- */
ts->inidle = 1;
__tick_nohz_idle_enter(ts);
@@ -914,8 +912,7 @@ static void tick_nohz_account_idle_ticks(struct tick_sched *ts)
*/
void tick_nohz_idle_exit(void)
{
- int cpu = smp_processor_id();
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now;
local_irq_disable();
@@ -928,7 +925,7 @@ void tick_nohz_idle_exit(void)
now = ktime_get();
if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
+ tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
tick_nohz_restart_sched_tick(ts, now);
@@ -981,7 +978,7 @@ static void tick_nohz_switch_to_nohz(void)
local_irq_enable();
return;
}
-
+ tick_nohz_active = 1;
ts->nohz_mode = NOHZ_MODE_LOWRES;
/*
@@ -1012,12 +1009,10 @@ static void tick_nohz_switch_to_nohz(void)
* timer and do not touch the other magic bits which need to be done
* when idle is left.
*/
-static void tick_nohz_kick_tick(int cpu, ktime_t now)
+static void tick_nohz_kick_tick(struct tick_sched *ts, ktime_t now)
{
#if 0
/* Switch back to 2.6.27 behaviour */
-
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
ktime_t delta;
/*
@@ -1032,36 +1027,36 @@ static void tick_nohz_kick_tick(int cpu, ktime_t now)
#endif
}
-static inline void tick_check_nohz(int cpu)
+static inline void tick_nohz_irq_enter(void)
{
- struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
ktime_t now;
if (!ts->idle_active && !ts->tick_stopped)
return;
now = ktime_get();
if (ts->idle_active)
- tick_nohz_stop_idle(cpu, now);
+ tick_nohz_stop_idle(ts, now);
if (ts->tick_stopped) {
tick_nohz_update_jiffies(now);
- tick_nohz_kick_tick(cpu, now);
+ tick_nohz_kick_tick(ts, now);
}
}
#else
static inline void tick_nohz_switch_to_nohz(void) { }
-static inline void tick_check_nohz(int cpu) { }
+static inline void tick_nohz_irq_enter(void) { }
#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from irq_enter to notify about the possible interruption of idle()
*/
-void tick_check_idle(int cpu)
+void tick_irq_enter(void)
{
- tick_check_oneshot_broadcast(cpu);
- tick_check_nohz(cpu);
+ tick_check_oneshot_broadcast_this_cpu();
+ tick_nohz_irq_enter();
}
/*
@@ -1139,8 +1134,10 @@ void tick_setup_sched_timer(void)
}
#ifdef CONFIG_NO_HZ_COMMON
- if (tick_nohz_enabled)
+ if (tick_nohz_enabled) {
ts->nohz_mode = NOHZ_MODE_HIGHRES;
+ tick_nohz_active = 1;
+ }
#endif
}
#endif /* HIGH_RES_TIMERS */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3abf53418b6..32d8d6aaedb 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -22,6 +22,7 @@
#include <linux/tick.h>
#include <linux/stop_machine.h>
#include <linux/pvclock_gtod.h>
+#include <linux/compiler.h>
#include "tick-internal.h"
#include "ntp_internal.h"
@@ -77,7 +78,7 @@ static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec wtm)
tk->wall_to_monotonic = wtm;
set_normalized_timespec(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
tk->offs_real = timespec_to_ktime(tmp);
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tk->tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
}
static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -90,8 +91,9 @@ static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
}
/**
- * timekeeper_setup_internals - Set up internals to use clocksource clock.
+ * tk_setup_internals - Set up internals to use clocksource clock.
*
+ * @tk: The target timekeeper to setup.
* @clock: Pointer to clocksource.
*
* Calculates a fixed cycle/nsec interval for a given clocksource/adjustment
@@ -595,7 +597,7 @@ s32 timekeeping_get_tai_offset(void)
static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset)
{
tk->tai_offset = tai_offset;
- tk->offs_tai = ktime_sub(tk->offs_real, ktime_set(tai_offset, 0));
+ tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0));
}
/**
@@ -610,6 +612,7 @@ void timekeeping_set_tai_offset(s32 tai_offset)
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
__timekeeping_set_tai_offset(tk, tai_offset);
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
clock_was_set();
@@ -758,7 +761,7 @@ u64 timekeeping_max_deferment(void)
*
* XXX - Do be sure to remove it once all arches implement it.
*/
-void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
+void __weak read_persistent_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
@@ -773,7 +776,7 @@ void __attribute__((weak)) read_persistent_clock(struct timespec *ts)
*
* XXX - Do be sure to remove it once all arches implement it.
*/
-void __attribute__((weak)) read_boot_clock(struct timespec *ts)
+void __weak read_boot_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
@@ -849,8 +852,9 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
struct timespec *delta)
{
if (!timespec_valid_strict(delta)) {
- printk(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid "
- "sleep delta value!\n");
+ printk_deferred(KERN_WARNING
+ "__timekeeping_inject_sleeptime: Invalid "
+ "sleep delta value!\n");
return;
}
tk_xtime_add(tk, delta);
@@ -1023,6 +1027,8 @@ static int timekeeping_suspend(void)
timekeeping_suspend_time =
timespec_add(timekeeping_suspend_time, delta_delta);
}
+
+ timekeeping_update(tk, TK_MIRROR);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
@@ -1130,16 +1136,6 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
* we can adjust by 1.
*/
error >>= 2;
- /*
- * XXX - In update_wall_time, we round up to the next
- * nanosecond, and store the amount rounded up into
- * the error. This causes the likely below to be unlikely.
- *
- * The proper fix is to avoid rounding up by using
- * the high precision tk->xtime_nsec instead of
- * xtime.tv_nsec everywhere. Fixing this will take some
- * time.
- */
if (likely(error <= interval))
adj = 1;
else
@@ -1162,7 +1158,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
if (unlikely(tk->clock->maxadj &&
(tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) {
- printk_once(KERN_WARNING
+ printk_deferred_once(KERN_WARNING
"Adjusting %s more than 11%% (%ld vs %ld)\n",
tk->clock->name, (long)tk->mult + adj,
(long)tk->clock->mult + tk->clock->maxadj);
@@ -1255,7 +1251,7 @@ out_adjust:
static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
- unsigned int action = 0;
+ unsigned int clock_set = 0;
while (tk->xtime_nsec >= nsecps) {
int leap;
@@ -1277,11 +1273,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
- clock_was_set_delayed();
- action = TK_CLOCK_WAS_SET;
+ clock_set = TK_CLOCK_WAS_SET;
}
}
- return action;
+ return clock_set;
}
/**
@@ -1294,7 +1289,8 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
* Returns the unconsumed cycles.
*/
static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
- u32 shift)
+ u32 shift,
+ unsigned int *clock_set)
{
cycle_t interval = tk->cycle_interval << shift;
u64 raw_nsecs;
@@ -1308,7 +1304,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
tk->cycle_last += interval;
tk->xtime_nsec += tk->xtime_interval << shift;
- accumulate_nsecs_to_secs(tk);
+ *clock_set |= accumulate_nsecs_to_secs(tk);
/* Accumulate raw time */
raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1347,7 +1343,7 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
tk->xtime_nsec -= remainder;
tk->xtime_nsec += 1ULL << tk->shift;
tk->ntp_error += remainder << tk->ntp_error_shift;
-
+ tk->ntp_error -= (1ULL << tk->shift) << tk->ntp_error_shift;
}
#else
#define old_vsyscall_fixup(tk)
@@ -1359,14 +1355,14 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
* update_wall_time - Uses the current clocksource to increment the wall time
*
*/
-static void update_wall_time(void)
+void update_wall_time(void)
{
struct clocksource *clock;
struct timekeeper *real_tk = &timekeeper;
struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
int shift = 0, maxshift;
- unsigned int action;
+ unsigned int clock_set = 0;
unsigned long flags;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1401,7 +1397,8 @@ static void update_wall_time(void)
maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
shift = min(shift, maxshift);
while (offset >= tk->cycle_interval) {
- offset = logarithmic_accumulation(tk, offset, shift);
+ offset = logarithmic_accumulation(tk, offset, shift,
+ &clock_set);
if (offset < tk->cycle_interval<<shift)
shift--;
}
@@ -1419,7 +1416,7 @@ static void update_wall_time(void)
* Finally, make sure that after the rounding
* xtime_nsec isn't larger than NSEC_PER_SEC
*/
- action = accumulate_nsecs_to_secs(tk);
+ clock_set |= accumulate_nsecs_to_secs(tk);
write_seqcount_begin(&timekeeper_seq);
/* Update clock->cycle_last with the new value */
@@ -1435,10 +1432,13 @@ static void update_wall_time(void)
* updating.
*/
memcpy(real_tk, tk, sizeof(*tk));
- timekeeping_update(real_tk, action);
+ timekeeping_update(real_tk, clock_set);
write_seqcount_end(&timekeeper_seq);
out:
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (clock_set)
+ /* Have to call _delayed version, since in irq context*/
+ clock_was_set_delayed();
}
/**
@@ -1583,7 +1583,6 @@ struct timespec get_monotonic_coarse(void)
void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
- update_wall_time();
calc_global_load(ticks);
}
@@ -1698,12 +1697,14 @@ int do_adjtimex(struct timex *txc)
if (tai != orig_tai) {
__timekeeping_set_tai_offset(tk, tai);
- update_pvclock_gtod(tk, true);
- clock_was_set_delayed();
+ timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
}
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ if (tai != orig_tai)
+ clock_was_set();
+
ntp_notify_cmos_timer();
return ret;
@@ -1739,4 +1740,5 @@ void xtime_update(unsigned long ticks)
write_seqlock(&jiffies_lock);
do_timer(ticks);
write_sequnlock(&jiffies_lock);
+ update_wall_time();
}
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 802433a4f5e..4d54f97558d 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -21,6 +21,8 @@
#include <linux/seq_file.h>
#include <linux/time.h>
+#include "timekeeping_internal.h"
+
static unsigned int sleep_time_bin[32] = {0};
static int tk_debug_show_sleep_time(struct seq_file *s, void *data)
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-14 04:23:53 +0000