aboutsummaryrefslogtreecommitdiff
path: root/kernel/time
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/time')
-rw-r--r--kernel/time/Kconfig80
-rw-r--r--kernel/time/ntp.c105
-rw-r--r--kernel/time/ntp_internal.h12
-rw-r--r--kernel/time/tick-broadcast.c242
-rw-r--r--kernel/time/tick-common.c7
-rw-r--r--kernel/time/tick-internal.h5
-rw-r--r--kernel/time/tick-sched.c300
-rw-r--r--kernel/time/timekeeping.c396
-rw-r--r--kernel/time/timer_list.c104
9 files changed, 994 insertions, 257 deletions
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index 24510d84efd..e4c07b0692b 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -64,20 +64,88 @@ config GENERIC_CMOS_UPDATE
if GENERIC_CLOCKEVENTS
menu "Timers subsystem"
-# Core internal switch. Selected by NO_HZ / HIGH_RES_TIMERS. This is
+# Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is
# only related to the tick functionality. Oneshot clockevent devices
# are supported independ of this.
config TICK_ONESHOT
bool
-config NO_HZ
- bool "Tickless System (Dynamic Ticks)"
+config NO_HZ_COMMON
+ bool
depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
select TICK_ONESHOT
+
+choice
+ prompt "Timer tick handling"
+ default NO_HZ_IDLE if NO_HZ
+
+config HZ_PERIODIC
+ bool "Periodic timer ticks (constant rate, no dynticks)"
+ help
+ This option keeps the tick running periodically at a constant
+ rate, even when the CPU doesn't need it.
+
+config NO_HZ_IDLE
+ bool "Idle dynticks system (tickless idle)"
+ depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
+ select NO_HZ_COMMON
+ help
+ This option enables a tickless idle system: timer interrupts
+ will only trigger on an as-needed basis when the system is idle.
+ This is usually interesting for energy saving.
+
+ Most of the time you want to say Y here.
+
+config NO_HZ_FULL
+ bool "Full dynticks system (tickless)"
+ # NO_HZ_COMMON dependency
+ depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
+ # We need at least one periodic CPU for timekeeping
+ depends on SMP
+ # RCU_USER_QS dependency
+ depends on HAVE_CONTEXT_TRACKING
+ # VIRT_CPU_ACCOUNTING_GEN dependency
+ depends on 64BIT
+ select NO_HZ_COMMON
+ select RCU_USER_QS
+ select RCU_NOCB_CPU
+ select VIRT_CPU_ACCOUNTING_GEN
+ select CONTEXT_TRACKING_FORCE
+ select IRQ_WORK
+ help
+ Adaptively try to shutdown the tick whenever possible, even when
+ the CPU is running tasks. Typically this requires running a single
+ task on the CPU. Chances for running tickless are maximized when
+ the task mostly runs in userspace and has few kernel activity.
+
+ You need to fill up the nohz_full boot parameter with the
+ desired range of dynticks CPUs.
+
+ This is implemented at the expense of some overhead in user <-> kernel
+ transitions: syscalls, exceptions and interrupts. Even when it's
+ dynamically off.
+
+ Say N.
+
+endchoice
+
+config NO_HZ_FULL_ALL
+ bool "Full dynticks system on all CPUs by default"
+ depends on NO_HZ_FULL
+ help
+ If the user doesn't pass the nohz_full boot option to
+ define the range of full dynticks CPUs, consider that all
+ CPUs in the system are full dynticks by default.
+ Note the boot CPU will still be kept outside the range to
+ handle the timekeeping duty.
+
+config NO_HZ
+ bool "Old Idle dynticks config"
+ depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS
help
- This option enables a tickless system: timer interrupts will
- only trigger on an as-needed basis both when the system is
- busy and when the system is idle.
+ This is the old config entry that enables dynticks idle.
+ We keep it around for a little while to enforce backward
+ compatibility with older config files.
config HIGH_RES_TIMERS
bool "High Resolution Timer Support"
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 072bb066bb7..12ff13a838c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -18,13 +18,14 @@
#include <linux/rtc.h>
#include "tick-internal.h"
+#include "ntp_internal.h"
/*
* NTP timekeeping variables:
+ *
+ * Note: All of the NTP state is protected by the timekeeping locks.
*/
-DEFINE_RAW_SPINLOCK(ntp_lock);
-
/* USER_HZ period (usecs): */
unsigned long tick_usec = TICK_USEC;
@@ -53,9 +54,6 @@ static int time_state = TIME_OK;
/* clock status bits: */
static int time_status = STA_UNSYNC;
-/* TAI offset (secs): */
-static long time_tai;
-
/* time adjustment (nsecs): */
static s64 time_offset;
@@ -134,8 +132,6 @@ static inline void pps_reset_freq_interval(void)
/**
* pps_clear - Clears the PPS state variables
- *
- * Must be called while holding a write on the ntp_lock
*/
static inline void pps_clear(void)
{
@@ -150,8 +146,6 @@ static inline void pps_clear(void)
/* Decrease pps_valid to indicate that another second has passed since
* the last PPS signal. When it reaches 0, indicate that PPS signal is
* missing.
- *
- * Must be called while holding a write on the ntp_lock
*/
static inline void pps_dec_valid(void)
{
@@ -346,10 +340,6 @@ static void ntp_update_offset(long offset)
*/
void ntp_clear(void)
{
- unsigned long flags;
-
- raw_spin_lock_irqsave(&ntp_lock, flags);
-
time_adjust = 0; /* stop active adjtime() */
time_status |= STA_UNSYNC;
time_maxerror = NTP_PHASE_LIMIT;
@@ -362,20 +352,12 @@ void ntp_clear(void)
/* Clear PPS state variables */
pps_clear();
- raw_spin_unlock_irqrestore(&ntp_lock, flags);
-
}
u64 ntp_tick_length(void)
{
- unsigned long flags;
- s64 ret;
-
- raw_spin_lock_irqsave(&ntp_lock, flags);
- ret = tick_length;
- raw_spin_unlock_irqrestore(&ntp_lock, flags);
- return ret;
+ return tick_length;
}
@@ -393,9 +375,6 @@ int second_overflow(unsigned long secs)
{
s64 delta;
int leap = 0;
- unsigned long flags;
-
- raw_spin_lock_irqsave(&ntp_lock, flags);
/*
* Leap second processing. If in leap-insert state at the end of the
@@ -415,7 +394,6 @@ int second_overflow(unsigned long secs)
else if (secs % 86400 == 0) {
leap = -1;
time_state = TIME_OOP;
- time_tai++;
printk(KERN_NOTICE
"Clock: inserting leap second 23:59:60 UTC\n");
}
@@ -425,7 +403,6 @@ int second_overflow(unsigned long secs)
time_state = TIME_OK;
else if ((secs + 1) % 86400 == 0) {
leap = 1;
- time_tai--;
time_state = TIME_WAIT;
printk(KERN_NOTICE
"Clock: deleting leap second 23:59:59 UTC\n");
@@ -479,8 +456,6 @@ int second_overflow(unsigned long secs)
time_adjust = 0;
out:
- raw_spin_unlock_irqrestore(&ntp_lock, flags);
-
return leap;
}
@@ -575,11 +550,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec *ts)
time_status |= txc->status & ~STA_RONLY;
}
-/*
- * Called with ntp_lock held, so we can access and modify
- * all the global NTP state:
- */
-static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts)
+
+static inline void process_adjtimex_modes(struct timex *txc,
+ struct timespec *ts,
+ s32 *time_tai)
{
if (txc->modes & ADJ_STATUS)
process_adj_status(txc, ts);
@@ -613,7 +587,7 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
}
if (txc->modes & ADJ_TAI && txc->constant > 0)
- time_tai = txc->constant;
+ *time_tai = txc->constant;
if (txc->modes & ADJ_OFFSET)
ntp_update_offset(txc->offset);
@@ -625,16 +599,13 @@ static inline void process_adjtimex_modes(struct timex *txc, struct timespec *ts
ntp_update_frequency();
}
-/*
- * adjtimex mainly allows reading (and writing, if superuser) of
- * kernel time-keeping variables. used by xntpd.
+
+
+/**
+ * ntp_validate_timex - Ensures the timex is ok for use in do_adjtimex
*/
-int do_adjtimex(struct timex *txc)
+int ntp_validate_timex(struct timex *txc)
{
- struct timespec ts;
- int result;
-
- /* Validate the data before disabling interrupts */
if (txc->modes & ADJ_ADJTIME) {
/* singleshot must not be used with any other mode bits */
if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
@@ -646,7 +617,6 @@ int do_adjtimex(struct timex *txc)
/* In order to modify anything, you gotta be super-user! */
if (txc->modes && !capable(CAP_SYS_TIME))
return -EPERM;
-
/*
* if the quartz is off by more than 10% then
* something is VERY wrong!
@@ -657,22 +627,20 @@ int do_adjtimex(struct timex *txc)
return -EINVAL;
}
- if (txc->modes & ADJ_SETOFFSET) {
- struct timespec delta;
- delta.tv_sec = txc->time.tv_sec;
- delta.tv_nsec = txc->time.tv_usec;
- if (!capable(CAP_SYS_TIME))
- return -EPERM;
- if (!(txc->modes & ADJ_NANO))
- delta.tv_nsec *= 1000;
- result = timekeeping_inject_offset(&delta);
- if (result)
- return result;
- }
+ if ((txc->modes & ADJ_SETOFFSET) && (!capable(CAP_SYS_TIME)))
+ return -EPERM;
- getnstimeofday(&ts);
+ return 0;
+}
- raw_spin_lock_irq(&ntp_lock);
+
+/*
+ * adjtimex mainly allows reading (and writing, if superuser) of
+ * kernel time-keeping variables. used by xntpd.
+ */
+int __do_adjtimex(struct timex *txc, struct timespec *ts, s32 *time_tai)
+{
+ int result;
if (txc->modes & ADJ_ADJTIME) {
long save_adjust = time_adjust;
@@ -687,7 +655,7 @@ int do_adjtimex(struct timex *txc)
/* If there are input parameters, then process them: */
if (txc->modes)
- process_adjtimex_modes(txc, &ts);
+ process_adjtimex_modes(txc, ts, time_tai);
txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
NTP_SCALE_SHIFT);
@@ -709,15 +677,13 @@ int do_adjtimex(struct timex *txc)
txc->precision = 1;
txc->tolerance = MAXFREQ_SCALED / PPM_SCALE;
txc->tick = tick_usec;
- txc->tai = time_tai;
+ txc->tai = *time_tai;
/* fill PPS status fields */
pps_fill_timex(txc);
- raw_spin_unlock_irq(&ntp_lock);
-
- txc->time.tv_sec = ts.tv_sec;
- txc->time.tv_usec = ts.tv_nsec;
+ txc->time.tv_sec = ts->tv_sec;
+ txc->time.tv_usec = ts->tv_nsec;
if (!(time_status & STA_NANO))
txc->time.tv_usec /= NSEC_PER_USEC;
@@ -894,7 +860,7 @@ static void hardpps_update_phase(long error)
}
/*
- * hardpps() - discipline CPU clock oscillator to external PPS signal
+ * __hardpps() - discipline CPU clock oscillator to external PPS signal
*
* This routine is called at each PPS signal arrival in order to
* discipline the CPU clock oscillator to the PPS signal. It takes two
@@ -905,15 +871,13 @@ static void hardpps_update_phase(long error)
* This code is based on David Mills's reference nanokernel
* implementation. It was mostly rewritten but keeps the same idea.
*/
-void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
+void __hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
{
struct pps_normtime pts_norm, freq_norm;
unsigned long flags;
pts_norm = pps_normalize_ts(*phase_ts);
- raw_spin_lock_irqsave(&ntp_lock, flags);
-
/* clear the error bits, they will be set again if needed */
time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR);
@@ -925,7 +889,6 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
* just start the frequency interval */
if (unlikely(pps_fbase.tv_sec == 0)) {
pps_fbase = *raw_ts;
- raw_spin_unlock_irqrestore(&ntp_lock, flags);
return;
}
@@ -940,7 +903,6 @@ 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;
- raw_spin_unlock_irqrestore(&ntp_lock, flags);
pr_err("hardpps: PPSJITTER: bad pulse\n");
return;
}
@@ -957,10 +919,7 @@ void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
hardpps_update_phase(pts_norm.nsec);
- raw_spin_unlock_irqrestore(&ntp_lock, flags);
}
-EXPORT_SYMBOL(hardpps);
-
#endif /* CONFIG_NTP_PPS */
static int __init ntp_tick_adj_setup(char *str)
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
new file mode 100644
index 00000000000..1950cb4ca2a
--- /dev/null
+++ b/kernel/time/ntp_internal.h
@@ -0,0 +1,12 @@
+#ifndef _LINUX_NTP_INTERNAL_H
+#define _LINUX_NTP_INTERNAL_H
+
+extern void ntp_init(void);
+extern void ntp_clear(void);
+/* Returns how long ticks are at present, in ns / 2^NTP_SCALE_SHIFT. */
+extern u64 ntp_tick_length(void);
+extern int second_overflow(unsigned long secs);
+extern int ntp_validate_timex(struct timex *);
+extern int __do_adjtimex(struct timex *, struct timespec *, s32 *);
+extern void __hardpps(const struct timespec *, const struct timespec *);
+#endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 7f32fe0e52c..206bbfb34e0 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -28,9 +28,8 @@
*/
static struct tick_device tick_broadcast_device;
-/* FIXME: Use cpumask_var_t. */
-static DECLARE_BITMAP(tick_broadcast_mask, NR_CPUS);
-static DECLARE_BITMAP(tmpmask, NR_CPUS);
+static cpumask_var_t tick_broadcast_mask;
+static cpumask_var_t tmpmask;
static DEFINE_RAW_SPINLOCK(tick_broadcast_lock);
static int tick_broadcast_force;
@@ -50,7 +49,7 @@ struct tick_device *tick_get_broadcast_device(void)
struct cpumask *tick_get_broadcast_mask(void)
{
- return to_cpumask(tick_broadcast_mask);
+ return tick_broadcast_mask;
}
/*
@@ -67,6 +66,8 @@ static void tick_broadcast_start_periodic(struct clock_event_device *bc)
*/
int tick_check_broadcast_device(struct clock_event_device *dev)
{
+ struct clock_event_device *cur = tick_broadcast_device.evtdev;
+
if ((dev->features & CLOCK_EVT_FEAT_DUMMY) ||
(tick_broadcast_device.evtdev &&
tick_broadcast_device.evtdev->rating >= dev->rating) ||
@@ -74,9 +75,21 @@ int tick_check_broadcast_device(struct clock_event_device *dev)
return 0;
clockevents_exchange_device(tick_broadcast_device.evtdev, dev);
+ if (cur)
+ cur->event_handler = clockevents_handle_noop;
tick_broadcast_device.evtdev = dev;
- if (!cpumask_empty(tick_get_broadcast_mask()))
+ if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(dev);
+ /*
+ * Inform all cpus about this. We might be in a situation
+ * where we did not switch to oneshot mode because the per cpu
+ * devices are affected by CLOCK_EVT_FEAT_C3STOP and the lack
+ * of a oneshot capable broadcast device. Without that
+ * notification the systems stays stuck in periodic mode
+ * forever.
+ */
+ if (dev->features & CLOCK_EVT_FEAT_ONESHOT)
+ tick_clock_notify();
return 1;
}
@@ -124,7 +137,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
if (!tick_device_is_functional(dev)) {
dev->event_handler = tick_handle_periodic;
tick_device_setup_broadcast_func(dev);
- cpumask_set_cpu(cpu, tick_get_broadcast_mask());
+ cpumask_set_cpu(cpu, tick_broadcast_mask);
tick_broadcast_start_periodic(tick_broadcast_device.evtdev);
ret = 1;
} else {
@@ -135,7 +148,7 @@ int tick_device_uses_broadcast(struct clock_event_device *dev, int cpu)
*/
if (!(dev->features & CLOCK_EVT_FEAT_C3STOP)) {
int cpu = smp_processor_id();
- cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+ cpumask_clear_cpu(cpu, tick_broadcast_mask);
tick_broadcast_clear_oneshot(cpu);
} else {
tick_device_setup_broadcast_func(dev);
@@ -199,9 +212,8 @@ static void tick_do_periodic_broadcast(void)
{
raw_spin_lock(&tick_broadcast_lock);
- cpumask_and(to_cpumask(tmpmask),
- cpu_online_mask, tick_get_broadcast_mask());
- tick_do_broadcast(to_cpumask(tmpmask));
+ cpumask_and(tmpmask, cpu_online_mask, tick_broadcast_mask);
+ tick_do_broadcast(tmpmask);
raw_spin_unlock(&tick_broadcast_lock);
}
@@ -264,13 +276,12 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
if (!tick_device_is_functional(dev))
goto out;
- bc_stopped = cpumask_empty(tick_get_broadcast_mask());
+ bc_stopped = cpumask_empty(tick_broadcast_mask);
switch (*reason) {
case CLOCK_EVT_NOTIFY_BROADCAST_ON:
case CLOCK_EVT_NOTIFY_BROADCAST_FORCE:
- if (!cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
- cpumask_set_cpu(cpu, tick_get_broadcast_mask());
+ if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
clockevents_shutdown(dev);
@@ -280,8 +291,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
break;
case CLOCK_EVT_NOTIFY_BROADCAST_OFF:
if (!tick_broadcast_force &&
- cpumask_test_cpu(cpu, tick_get_broadcast_mask())) {
- cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+ cpumask_test_and_clear_cpu(cpu, tick_broadcast_mask)) {
if (tick_broadcast_device.mode ==
TICKDEV_MODE_PERIODIC)
tick_setup_periodic(dev, 0);
@@ -289,7 +299,7 @@ static void tick_do_broadcast_on_off(unsigned long *reason)
break;
}
- if (cpumask_empty(tick_get_broadcast_mask())) {
+ if (cpumask_empty(tick_broadcast_mask)) {
if (!bc_stopped)
clockevents_shutdown(bc);
} else if (bc_stopped) {
@@ -338,10 +348,10 @@ void tick_shutdown_broadcast(unsigned int *cpup)
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
bc = tick_broadcast_device.evtdev;
- cpumask_clear_cpu(cpu, tick_get_broadcast_mask());
+ cpumask_clear_cpu(cpu, tick_broadcast_mask);
if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
- if (bc && cpumask_empty(tick_get_broadcast_mask()))
+ if (bc && cpumask_empty(tick_broadcast_mask))
clockevents_shutdown(bc);
}
@@ -377,13 +387,13 @@ int tick_resume_broadcast(void)
switch (tick_broadcast_device.mode) {
case TICKDEV_MODE_PERIODIC:
- if (!cpumask_empty(tick_get_broadcast_mask()))
+ if (!cpumask_empty(tick_broadcast_mask))
tick_broadcast_start_periodic(bc);
broadcast = cpumask_test_cpu(smp_processor_id(),
- tick_get_broadcast_mask());
+ tick_broadcast_mask);
break;
case TICKDEV_MODE_ONESHOT:
- if (!cpumask_empty(tick_get_broadcast_mask()))
+ if (!cpumask_empty(tick_broadcast_mask))
broadcast = tick_resume_broadcast_oneshot(bc);
break;
}
@@ -396,25 +406,58 @@ int tick_resume_broadcast(void)
#ifdef CONFIG_TICK_ONESHOT
-/* FIXME: use cpumask_var_t. */
-static DECLARE_BITMAP(tick_broadcast_oneshot_mask, NR_CPUS);
+static cpumask_var_t tick_broadcast_oneshot_mask;
+static cpumask_var_t tick_broadcast_pending_mask;
+static cpumask_var_t tick_broadcast_force_mask;
/*
* Exposed for debugging: see timer_list.c
*/
struct cpumask *tick_get_broadcast_oneshot_mask(void)
{
- return to_cpumask(tick_broadcast_oneshot_mask);
+ return tick_broadcast_oneshot_mask;
}
-static int tick_broadcast_set_event(ktime_t expires, int force)
+/*
+ * Called before going idle with interrupts disabled. Checks whether a
+ * broadcast event from the other core is about to happen. We detected
+ * that in tick_broadcast_oneshot_control(). The callsite can use this
+ * to avoid a deep idle transition as we are about to get the
+ * broadcast IPI right away.
+ */
+int tick_check_broadcast_expired(void)
{
- struct clock_event_device *bc = tick_broadcast_device.evtdev;
+ return cpumask_test_cpu(smp_processor_id(), tick_broadcast_force_mask);
+}
+
+/*
+ * Set broadcast interrupt affinity
+ */
+static void tick_broadcast_set_affinity(struct clock_event_device *bc,
+ const struct cpumask *cpumask)
+{
+ if (!(bc->features & CLOCK_EVT_FEAT_DYNIRQ))
+ return;
+
+ if (cpumask_equal(bc->cpumask, cpumask))
+ return;
+
+ bc->cpumask = cpumask;
+ irq_set_affinity(bc->irq, bc->cpumask);
+}
+
+static int tick_broadcast_set_event(struct clock_event_device *bc, int cpu,
+ ktime_t expires, int force)
+{
+ int ret;
if (bc->mode != CLOCK_EVT_MODE_ONESHOT)
clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
- return clockevents_program_event(bc, expires, force);
+ ret = clockevents_program_event(bc, expires, force);
+ if (!ret)
+ tick_broadcast_set_affinity(bc, cpumask_of(cpu));
+ return ret;
}
int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
@@ -429,7 +472,7 @@ int tick_resume_broadcast_oneshot(struct clock_event_device *bc)
*/
void tick_check_oneshot_broadcast(int cpu)
{
- if (cpumask_test_cpu(cpu, to_cpumask(tick_broadcast_oneshot_mask))) {
+ if (cpumask_test_cpu(cpu, tick_broadcast_oneshot_mask)) {
struct tick_device *td = &per_cpu(tick_cpu_device, cpu);
clockevents_set_mode(td->evtdev, CLOCK_EVT_MODE_ONESHOT);
@@ -443,27 +486,39 @@ static void tick_handle_oneshot_broadcast(struct clock_event_device *dev)
{
struct tick_device *td;
ktime_t now, next_event;
- int cpu;
+ int cpu, next_cpu = 0;
raw_spin_lock(&tick_broadcast_lock);
again:
dev->next_event.tv64 = KTIME_MAX;
next_event.tv64 = KTIME_MAX;
- cpumask_clear(to_cpumask(tmpmask));
+ cpumask_clear(tmpmask);
now = ktime_get();
/* Find all expired events */
- for_each_cpu(cpu, tick_get_broadcast_oneshot_mask()) {
+ for_each_cpu(cpu, tick_broadcast_oneshot_mask) {
td = &per_cpu(tick_cpu_device, cpu);
- if (td->evtdev->next_event.tv64 <= now.tv64)
- cpumask_set_cpu(cpu, to_cpumask(tmpmask));
- else if (td->evtdev->next_event.tv64 < next_event.tv64)
+ if (td->evtdev->next_event.tv64 <= now.tv64) {
+ cpumask_set_cpu(cpu, tmpmask);
+ /*
+ * Mark the remote cpu in the pending mask, so
+ * it can avoid reprogramming the cpu local
+ * timer in tick_broadcast_oneshot_control().
+ */
+ cpumask_set_cpu(cpu, tick_broadcast_pending_mask);
+ } else if (td->evtdev->next_event.tv64 < next_event.tv64) {
next_event.tv64 = td->evtdev->next_event.tv64;
+ next_cpu = cpu;
+ }
}
+ /* Take care of enforced broadcast requests */
+ cpumask_or(tmpmask, tmpmask, tick_broadcast_force_mask);
+ cpumask_clear(tick_broadcast_force_mask);
+
/*
* Wakeup the cpus which have an expired event.
*/
- tick_do_broadcast(to_cpumask(tmpmask));
+ tick_do_broadcast(tmpmask);
/*
* Two reasons for reprogram:
@@ -480,7 +535,7 @@ again:
* Rearm the broadcast device. If event expired,
* repeat the above
*/
- if (tick_broadcast_set_event(next_event, 0))
+ if (tick_broadcast_set_event(dev, next_cpu, next_event, 0))
goto again;
}
raw_spin_unlock(&tick_broadcast_lock);
@@ -495,6 +550,7 @@ void 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;
/*
@@ -519,21 +575,84 @@ void tick_broadcast_oneshot_control(unsigned long reason)
raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
if (reason == CLOCK_EVT_NOTIFY_BROADCAST_ENTER) {
- if (!cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
- cpumask_set_cpu(cpu, tick_get_broadcast_oneshot_mask());
+ WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
+ if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_SHUTDOWN);
- if (dev->next_event.tv64 < bc->next_event.tv64)
- tick_broadcast_set_event(dev->next_event, 1);
+ /*
+ * We only reprogram the broadcast timer if we
+ * did not mark ourself in the force mask and
+ * if the cpu local event is earlier than the
+ * broadcast event. If the current CPU is in
+ * the force mask, then we are going to be
+ * woken by the IPI right away.
+ */
+ if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
+ dev->next_event.tv64 < bc->next_event.tv64)
+ tick_broadcast_set_event(bc, cpu, dev->next_event, 1);
}
} else {
- if (cpumask_test_cpu(cpu, tick_get_broadcast_oneshot_mask())) {
- cpumask_clear_cpu(cpu,
- tick_get_broadcast_oneshot_mask());
+ if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
- if (dev->next_event.tv64 != KTIME_MAX)
- tick_program_event(dev->next_event, 1);
+ if (dev->next_event.tv64 == KTIME_MAX)
+ goto out;
+ /*
+ * The cpu which was handling the broadcast
+ * timer marked this cpu in the broadcast
+ * pending mask and fired the broadcast
+ * IPI. So we are going to handle the expired
+ * event anyway via the broadcast IPI
+ * handler. No need to reprogram the timer
+ * with an already expired event.
+ */
+ if (cpumask_test_and_clear_cpu(cpu,
+ tick_broadcast_pending_mask))
+ goto out;
+
+ /*
+ * If the pending bit is not set, then we are
+ * either the CPU handling the broadcast
+ * interrupt or we got woken by something else.
+ *
+ * We are not longer in the broadcast mask, so
+ * if the cpu local expiry time is already
+ * reached, we would reprogram the cpu local
+ * timer with an already expired event.
+ *
+ * This can lead to a ping-pong when we return
+ * to idle and therefor rearm the broadcast
+ * timer before the cpu local timer was able
+ * to fire. This happens because the forced
+ * reprogramming makes sure that the event
+ * will happen in the future and depending on
+ * the min_delta setting this might be far
+ * enough out that the ping-pong starts.
+ *
+ * If the cpu local next_event has expired
+ * then we know that the broadcast timer
+ * next_event has expired as well and
+ * broadcast is about to be handled. So we
+ * avoid reprogramming and enforce that the
+ * broadcast handler, which did not run yet,
+ * will invoke the cpu local handler.
+ *
+ * We cannot call the handler directly from
+ * here, because we might be in a NOHZ phase
+ * and we did not go through the irq_enter()
+ * nohz fixups.
+ */
+ now = ktime_get();
+ if (dev->next_event.tv64 <= now.tv64) {
+ cpumask_set_cpu(cpu, tick_broadcast_force_mask);
+ goto out;
+ }
+ /*
+ * We got woken by something else. Reprogram
+ * the cpu local timer device.
+ */
+ tick_program_event(dev->next_event, 1);
}
}
+out:
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
@@ -544,7 +663,7 @@ void tick_broadcast_oneshot_control(unsigned long reason)
*/
static void tick_broadcast_clear_oneshot(int cpu)
{
- cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
}
static void tick_broadcast_init_next_event(struct cpumask *mask,
@@ -574,7 +693,8 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
bc->event_handler = tick_handle_oneshot_broadcast;
/* Take the do_timer update */
- tick_do_timer_cpu = cpu;
+ if (!tick_nohz_full_cpu(cpu))
+ tick_do_timer_cpu = cpu;
/*
* We must be careful here. There might be other CPUs
@@ -582,17 +702,16 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
* oneshot_mask bits for those and program the
* broadcast device to fire.
*/
- cpumask_copy(to_cpumask(tmpmask), tick_get_broadcast_mask());
- cpumask_clear_cpu(cpu, to_cpumask(tmpmask));
- cpumask_or(tick_get_broadcast_oneshot_mask(),
- tick_get_broadcast_oneshot_mask(),
- to_cpumask(tmpmask));
+ cpumask_copy(tmpmask, tick_broadcast_mask);
+ cpumask_clear_cpu(cpu, tmpmask);
+ cpumask_or(tick_broadcast_oneshot_mask,
+ tick_broadcast_oneshot_mask, tmpmask);
- if (was_periodic && !cpumask_empty(to_cpumask(tmpmask))) {
+ if (was_periodic && !cpumask_empty(tmpmask)) {
clockevents_set_mode(bc, CLOCK_EVT_MODE_ONESHOT);
- tick_broadcast_init_next_event(to_cpumask(tmpmask),
+ tick_broadcast_init_next_event(tmpmask,
tick_next_period);
- tick_broadcast_set_event(tick_next_period, 1);
+ tick_broadcast_set_event(bc, cpu, tick_next_period, 1);
} else
bc->next_event.tv64 = KTIME_MAX;
} else {
@@ -640,7 +759,7 @@ void tick_shutdown_broadcast_oneshot(unsigned int *cpup)
* Clear the broadcast mask flag for the dead cpu, but do not
* stop the broadcast device!
*/
- cpumask_clear_cpu(cpu, tick_get_broadcast_oneshot_mask());
+ cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
raw_spin_unlock_irqrestore(&tick_broadcast_lock, flags);
}
@@ -664,3 +783,14 @@ bool tick_broadcast_oneshot_available(void)
}
#endif
+
+void __init tick_broadcast_init(void)
+{
+ alloc_cpumask_var(&tick_broadcast_mask, GFP_NOWAIT);
+ alloc_cpumask_var(&tmpmask, GFP_NOWAIT);
+#ifdef CONFIG_TICK_ONESHOT
+ alloc_cpumask_var(&tick_broadcast_oneshot_mask, GFP_NOWAIT);
+ alloc_cpumask_var(&tick_broadcast_pending_mask, GFP_NOWAIT);
+ alloc_cpumask_var(&tick_broadcast_force_mask, GFP_NOWAIT);
+#endif
+}
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index b1600a6973f..5d3fb100bc0 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -163,7 +163,10 @@ static void tick_setup_device(struct tick_device *td,
* this cpu:
*/
if (tick_do_timer_cpu == TICK_DO_TIMER_BOOT) {
- tick_do_timer_cpu = cpu;
+ if (!tick_nohz_full_cpu(cpu))
+ tick_do_timer_cpu = cpu;
+ else
+ tick_do_timer_cpu = TICK_DO_TIMER_NONE;
tick_next_period = ktime_get();
tick_period = ktime_set(0, NSEC_PER_SEC / HZ);
}
@@ -323,6 +326,7 @@ static void tick_shutdown(unsigned int *cpup)
*/
dev->mode = CLOCK_EVT_MODE_UNUSED;
clockevents_exchange_device(dev, NULL);
+ dev->event_handler = clockevents_handle_noop;
td->evtdev = NULL;
}
raw_spin_unlock_irqrestore(&tick_device_lock, flags);
@@ -416,4 +420,5 @@ static struct notifier_block tick_notifier = {
void __init tick_init(void)
{
clockevents_register_notifier(&tick_notifier);
+ tick_broadcast_init();
}
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index cf3e59ed6dc..f0299eae460 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -4,6 +4,8 @@
#include <linux/hrtimer.h>
#include <linux/tick.h>
+extern seqlock_t jiffies_lock;
+
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BUILD
#define TICK_DO_TIMER_NONE -1
@@ -94,7 +96,7 @@ extern void tick_broadcast_on_off(unsigned long reason, int *oncpu);
extern void tick_shutdown_broadcast(unsigned int *cpup);
extern void tick_suspend_broadcast(void);
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);
@@ -119,6 +121,7 @@ static inline void tick_broadcast_on_off(unsigned long reason, int *oncpu) { }
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) { }
/*
* Set the periodic handler in non broadcast mode
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index a19a39952c1..bc67d4245e1 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -21,11 +21,15 @@
#include <linux/sched.h>
#include <linux/module.h>
#include <linux/irq_work.h>
+#include <linux/posix-timers.h>
+#include <linux/perf_event.h>
#include <asm/irq_regs.h>
#include "tick-internal.h"
+#include <trace/events/timer.h>
+
/*
* Per cpu nohz control structure
*/
@@ -104,7 +108,7 @@ static void tick_sched_do_timer(ktime_t now)
{
int cpu = smp_processor_id();
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
/*
* Check if the do_timer duty was dropped. We don't care about
* concurrency: This happens only when the cpu in charge went
@@ -112,7 +116,8 @@ static void tick_sched_do_timer(ktime_t now)
* this duty, then the jiffies update is still serialized by
* jiffies_lock.
*/
- if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE))
+ if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+ && !tick_nohz_full_cpu(cpu))
tick_do_timer_cpu = cpu;
#endif
@@ -123,7 +128,7 @@ static void tick_sched_do_timer(ktime_t now)
static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
{
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
/*
* When we are idle and the tick is stopped, we have to touch
* the watchdog as we might not schedule for a really long
@@ -142,10 +147,226 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs)
profile_tick(CPU_PROFILING);
}
+#ifdef CONFIG_NO_HZ_FULL
+static cpumask_var_t nohz_full_mask;
+bool have_nohz_full_mask;
+
+static bool can_stop_full_tick(void)
+{
+ WARN_ON_ONCE(!irqs_disabled());
+
+ if (!sched_can_stop_tick()) {
+ trace_tick_stop(0, "more than 1 task in runqueue\n");
+ return false;
+ }
+
+ if (!posix_cpu_timers_can_stop_tick(current)) {
+ trace_tick_stop(0, "posix timers running\n");
+ return false;
+ }
+
+ if (!perf_event_can_stop_tick()) {
+ trace_tick_stop(0, "perf events running\n");
+ return false;
+ }
+
+ /* sched_clock_tick() needs us? */
+#ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
+ /*
+ * TODO: kick full dynticks CPUs when
+ * sched_clock_stable is set.
+ */
+ if (!sched_clock_stable) {
+ trace_tick_stop(0, "unstable sched clock\n");
+ return false;
+ }
+#endif
+
+ return true;
+}
+
+static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now);
+
+/*
+ * Re-evaluate the need for the tick on the current CPU
+ * and restart it if necessary.
+ */
+void tick_nohz_full_check(void)
+{
+ struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
+
+ if (tick_nohz_full_cpu(smp_processor_id())) {
+ if (ts->tick_stopped && !is_idle_task(current)) {
+ if (!can_stop_full_tick())
+ tick_nohz_restart_sched_tick(ts, ktime_get());
+ }
+ }
+}
+
+static void nohz_full_kick_work_func(struct irq_work *work)
+{
+ tick_nohz_full_check();
+}
+
+static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = {
+ .func = nohz_full_kick_work_func,
+};
+
+/*
+ * Kick the current CPU if it's full dynticks in order to force it to
+ * re-evaluate its dependency on the tick and restart it if necessary.
+ */
+void tick_nohz_full_kick(void)
+{
+ if (tick_nohz_full_cpu(smp_processor_id()))
+ irq_work_queue(&__get_cpu_var(nohz_full_kick_work));
+}
+
+static void nohz_full_kick_ipi(void *info)
+{
+ tick_nohz_full_check();
+}
+
+/*
+ * Kick all full dynticks CPUs in order to force these to re-evaluate
+ * their dependency on the tick and restart it if necessary.
+ */
+void tick_nohz_full_kick_all(void)
+{
+ if (!have_nohz_full_mask)
+ return;
+
+ preempt_disable();
+ smp_call_function_many(nohz_full_mask,
+ nohz_full_kick_ipi, NULL, false);
+ preempt_enable();
+}
+
+/*
+ * Re-evaluate the need for the tick as we switch the current task.
+ * It might need the tick due to per task/process properties:
+ * perf events, posix cpu timers, ...
+ */
+void tick_nohz_task_switch(struct task_struct *tsk)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ if (!tick_nohz_full_cpu(smp_processor_id()))
+ goto out;
+
+ if (tick_nohz_tick_stopped() && !can_stop_full_tick())
+ tick_nohz_full_kick();
+
+out:
+ local_irq_restore(flags);
+}
+
+int tick_nohz_full_cpu(int cpu)
+{
+ if (!have_nohz_full_mask)
+ return 0;
+
+ return cpumask_test_cpu(cpu, nohz_full_mask);
+}
+
+/* Parse the boot-time nohz CPU list from the kernel parameters. */
+static int __init tick_nohz_full_setup(char *str)
+{
+ int cpu;
+
+ alloc_bootmem_cpumask_var(&nohz_full_mask);
+ if (cpulist_parse(str, nohz_full_mask) < 0) {
+ pr_warning("NOHZ: Incorrect nohz_full cpumask\n");
+ return 1;
+ }
+
+ cpu = smp_processor_id();
+ if (cpumask_test_cpu(cpu, nohz_full_mask)) {
+ pr_warning("NO_HZ: Clearing %d from nohz_full range for timekeeping\n", cpu);
+ cpumask_clear_cpu(cpu, nohz_full_mask);
+ }
+ have_nohz_full_mask = true;
+
+ return 1;
+}
+__setup("nohz_full=", tick_nohz_full_setup);
+
+static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb,
+ unsigned long action,
+ void *hcpu)
+{
+ unsigned int cpu = (unsigned long)hcpu;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+ case CPU_DOWN_PREPARE:
+ /*
+ * If we handle the timekeeping duty for full dynticks CPUs,
+ * we can't safely shutdown that CPU.
+ */
+ if (have_nohz_full_mask && tick_do_timer_cpu == cpu)
+ return -EINVAL;
+ break;
+ }
+ return NOTIFY_OK;
+}
+
+/*
+ * Worst case string length in chunks of CPU range seems 2 steps
+ * separations: 0,2,4,6,...
+ * This is NR_CPUS + sizeof('\0')
+ */
+static char __initdata nohz_full_buf[NR_CPUS + 1];
+
+static int tick_nohz_init_all(void)
+{
+ int err = -1;
+
+#ifdef CONFIG_NO_HZ_FULL_ALL
+ if (!alloc_cpumask_var(&nohz_full_mask, GFP_KERNEL)) {
+ pr_err("NO_HZ: Can't allocate full dynticks cpumask\n");
+ return err;
+ }
+ err = 0;
+ cpumask_setall(nohz_full_mask);
+ cpumask_clear_cpu(smp_processor_id(), nohz_full_mask);
+ have_nohz_full_mask = true;
+#endif
+ return err;
+}
+
+void __init tick_nohz_init(void)
+{
+ int cpu;
+
+ if (!have_nohz_full_mask) {
+ if (tick_nohz_init_all() < 0)
+ return;
+ }
+
+ cpu_notifier(tick_nohz_cpu_down_callback, 0);
+
+ /* Make sure full dynticks CPU are also RCU nocbs */
+ for_each_cpu(cpu, nohz_full_mask) {
+ if (!rcu_is_nocb_cpu(cpu)) {
+ pr_warning("NO_HZ: CPU %d is not RCU nocb: "
+ "cleared from nohz_full range", cpu);
+ cpumask_clear_cpu(cpu, nohz_full_mask);
+ }
+ }
+
+ cpulist_scnprintf(nohz_full_buf, sizeof(nohz_full_buf), nohz_full_mask);
+ pr_info("NO_HZ: Full dynticks CPUs: %s.\n", nohz_full_buf);
+}
+#else
+#define have_nohz_full_mask (0)
+#endif
+
/*
* NOHZ - aka dynamic tick functionality
*/
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
/*
* NO HZ enabled ?
*/
@@ -345,11 +566,12 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
delta_jiffies = rcu_delta_jiffies;
}
}
+
/*
- * Do not stop the tick, if we are only one off
- * or if the cpu is required for rcu
+ * Do not stop the tick, if we are only one off (or less)
+ * or if the cpu is required for RCU:
*/
- if (!ts->tick_stopped && delta_jiffies == 1)
+ if (!ts->tick_stopped && delta_jiffies <= 1)
goto out;
/* Schedule the tick, if we are at least one jiffie off */
@@ -378,6 +600,13 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
time_delta = KTIME_MAX;
}
+#ifdef CONFIG_NO_HZ_FULL
+ if (!ts->inidle) {
+ time_delta = min(time_delta,
+ scheduler_tick_max_deferment());
+ }
+#endif
+
/*
* calculate the expiry time for the next timer wheel
* timer. delta_jiffies >= NEXT_TIMER_MAX_DELTA signals
@@ -421,6 +650,7 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts,
ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
ts->tick_stopped = 1;
+ trace_tick_stop(1, " ");
}
/*
@@ -457,6 +687,24 @@ out:
return ret;
}
+static void tick_nohz_full_stop_tick(struct tick_sched *ts)
+{
+#ifdef CONFIG_NO_HZ_FULL
+ int cpu = smp_processor_id();
+
+ if (!tick_nohz_full_cpu(cpu) || is_idle_task(current))
+ return;
+
+ if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE)
+ return;
+
+ if (!can_stop_full_tick())
+ return;
+
+ tick_nohz_stop_sched_tick(ts, ktime_get(), cpu);
+#endif
+}
+
static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
{
/*
@@ -482,13 +730,28 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts)
if (ratelimit < 10 &&
(local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) {
- printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
- (unsigned int) local_softirq_pending());
+ pr_warn("NOHZ: local_softirq_pending %02x\n",
+ (unsigned int) local_softirq_pending());
ratelimit++;
}
return false;
}
+ if (have_nohz_full_mask) {
+ /*
+ * Keep the tick alive to guarantee timekeeping progression
+ * if there are full dynticks CPUs around
+ */
+ if (tick_do_timer_cpu == cpu)
+ return false;
+ /*
+ * Boot safety: make sure the timekeeping duty has been
+ * assigned before entering dyntick-idle mode,
+ */
+ if (tick_do_timer_cpu == TICK_DO_TIMER_NONE)
+ return false;
+ }
+
return true;
}
@@ -568,12 +831,13 @@ void tick_nohz_irq_exit(void)
{
struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched);
- if (!ts->inidle)
- return;
-
- /* Cancel the timer because CPU already waken up from the C-states*/
- menu_hrtimer_cancel();
- __tick_nohz_idle_enter(ts);
+ if (ts->inidle) {
+ /* Cancel the timer because CPU already waken up from the C-states*/
+ menu_hrtimer_cancel();
+ __tick_nohz_idle_enter(ts);
+ } else {
+ tick_nohz_full_stop_tick(ts);
+ }
}
/**
@@ -802,7 +1066,7 @@ static inline void tick_check_nohz(int cpu)
static inline void tick_nohz_switch_to_nohz(void) { }
static inline void tick_check_nohz(int cpu) { }
-#endif /* NO_HZ */
+#endif /* CONFIG_NO_HZ_COMMON */
/*
* Called from irq_enter to notify about the possible interruption of idle()
@@ -887,14 +1151,14 @@ void tick_setup_sched_timer(void)
now = ktime_get();
}
-#ifdef CONFIG_NO_HZ
+#ifdef CONFIG_NO_HZ_COMMON
if (tick_nohz_enabled)
ts->nohz_mode = NOHZ_MODE_HIGHRES;
#endif
}
#endif /* HIGH_RES_TIMERS */
-#if defined CONFIG_NO_HZ || defined CONFIG_HIGH_RES_TIMERS
+#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS
void tick_cancel_sched_timer(int cpu)
{
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 9a0bc98fbe1..98cd470bbe4 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -23,8 +23,13 @@
#include <linux/stop_machine.h>
#include <linux/pvclock_gtod.h>
+#include "tick-internal.h"
+#include "ntp_internal.h"
static struct timekeeper timekeeper;
+static DEFINE_RAW_SPINLOCK(timekeeper_lock);
+static seqcount_t timekeeper_seq;
+static struct timekeeper shadow_timekeeper;
/* flag for if timekeeping is suspended */
int __read_mostly timekeeping_suspended;
@@ -67,6 +72,7 @@ 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));
}
static void tk_set_sleep_time(struct timekeeper *tk, struct timespec t)
@@ -96,7 +102,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
old_clock = tk->clock;
tk->clock = clock;
- clock->cycle_last = clock->read(clock);
+ tk->cycle_last = clock->cycle_last = clock->read(clock);
/* Do the ns -> cycle conversion first, using original mult */
tmp = NTP_INTERVAL_LENGTH;
@@ -201,8 +207,6 @@ static void update_pvclock_gtod(struct timekeeper *tk)
/**
* pvclock_gtod_register_notifier - register a pvclock timedata update listener
- *
- * Must hold write on timekeeper.lock
*/
int pvclock_gtod_register_notifier(struct notifier_block *nb)
{
@@ -210,11 +214,10 @@ int pvclock_gtod_register_notifier(struct notifier_block *nb)
unsigned long flags;
int ret;
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
- /* update timekeeping data */
update_pvclock_gtod(tk);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
return ret;
}
@@ -223,25 +226,22 @@ EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
/**
* pvclock_gtod_unregister_notifier - unregister a pvclock
* timedata update listener
- *
- * Must hold write on timekeeper.lock
*/
int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
{
- struct timekeeper *tk = &timekeeper;
unsigned long flags;
int ret;
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
-/* must hold write on timekeeper.lock */
-static void timekeeping_update(struct timekeeper *tk, bool clearntp)
+/* must hold timekeeper_lock */
+static void timekeeping_update(struct timekeeper *tk, bool clearntp, bool mirror)
{
if (clearntp) {
tk->ntp_error = 0;
@@ -249,6 +249,9 @@ static void timekeeping_update(struct timekeeper *tk, bool clearntp)
}
update_vsyscall(tk);
update_pvclock_gtod(tk);
+
+ if (mirror)
+ memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
}
/**
@@ -267,7 +270,7 @@ static void timekeeping_forward_now(struct timekeeper *tk)
clock = tk->clock;
cycle_now = clock->read(clock);
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
- clock->cycle_last = cycle_now;
+ tk->cycle_last = clock->cycle_last = cycle_now;
tk->xtime_nsec += cycle_delta * tk->mult;
@@ -294,12 +297,12 @@ int __getnstimeofday(struct timespec *ts)
s64 nsecs = 0;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
ts->tv_sec = tk->xtime_sec;
nsecs = timekeeping_get_ns(tk);
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
ts->tv_nsec = 0;
timespec_add_ns(ts, nsecs);
@@ -335,11 +338,11 @@ ktime_t ktime_get(void)
WARN_ON(timekeeping_suspended);
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
secs = tk->xtime_sec + tk->wall_to_monotonic.tv_sec;
nsecs = timekeeping_get_ns(tk) + tk->wall_to_monotonic.tv_nsec;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
/*
* Use ktime_set/ktime_add_ns to create a proper ktime on
* 32-bit architectures without CONFIG_KTIME_SCALAR.
@@ -366,12 +369,12 @@ void ktime_get_ts(struct timespec *ts)
WARN_ON(timekeeping_suspended);
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
ts->tv_sec = tk->xtime_sec;
nsec = timekeeping_get_ns(tk);
tomono = tk->wall_to_monotonic;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
ts->tv_sec += tomono.tv_sec;
ts->tv_nsec = 0;
@@ -379,6 +382,50 @@ void ktime_get_ts(struct timespec *ts)
}
EXPORT_SYMBOL_GPL(ktime_get_ts);
+
+/**
+ * timekeeping_clocktai - Returns the TAI time of day in a timespec
+ * @ts: pointer to the timespec to be set
+ *
+ * Returns the time of day in a timespec.
+ */
+void timekeeping_clocktai(struct timespec *ts)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long seq;
+ u64 nsecs;
+
+ WARN_ON(timekeeping_suspended);
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+
+ ts->tv_sec = tk->xtime_sec + tk->tai_offset;
+ nsecs = timekeeping_get_ns(tk);
+
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ ts->tv_nsec = 0;
+ timespec_add_ns(ts, nsecs);
+
+}
+EXPORT_SYMBOL(timekeeping_clocktai);
+
+
+/**
+ * ktime_get_clocktai - Returns the TAI time of day in a ktime
+ *
+ * Returns the time of day in a ktime.
+ */
+ktime_t ktime_get_clocktai(void)
+{
+ struct timespec ts;
+
+ timekeeping_clocktai(&ts);
+ return timespec_to_ktime(ts);
+}
+EXPORT_SYMBOL(ktime_get_clocktai);
+
#ifdef CONFIG_NTP_PPS
/**
@@ -399,7 +446,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
WARN_ON_ONCE(timekeeping_suspended);
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
*ts_raw = tk->raw_time;
ts_real->tv_sec = tk->xtime_sec;
@@ -408,7 +455,7 @@ void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
nsecs_raw = timekeeping_get_ns_raw(tk);
nsecs_real = timekeeping_get_ns(tk);
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
timespec_add_ns(ts_raw, nsecs_raw);
timespec_add_ns(ts_real, nsecs_real);
@@ -448,7 +495,8 @@ int do_settimeofday(const struct timespec *tv)
if (!timespec_valid_strict(tv))
return -EINVAL;
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
@@ -460,9 +508,10 @@ int do_settimeofday(const struct timespec *tv)
tk_set_xtime(tk, tv);
- timekeeping_update(tk, true);
+ timekeeping_update(tk, true, true);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
@@ -487,7 +536,8 @@ int timekeeping_inject_offset(struct timespec *ts)
if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
return -EINVAL;
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
@@ -502,9 +552,10 @@ int timekeeping_inject_offset(struct timespec *ts)
tk_set_wall_to_mono(tk, timespec_sub(tk->wall_to_monotonic, *ts));
error: /* even if we error out, we forwarded the time, so call update */
- timekeeping_update(tk, true);
+ timekeeping_update(tk, true, true);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
@@ -513,6 +564,52 @@ error: /* even if we error out, we forwarded the time, so call update */
}
EXPORT_SYMBOL(timekeeping_inject_offset);
+
+/**
+ * timekeeping_get_tai_offset - Returns current TAI offset from UTC
+ *
+ */
+s32 timekeeping_get_tai_offset(void)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned int seq;
+ s32 ret;
+
+ do {
+ seq = read_seqcount_begin(&timekeeper_seq);
+ ret = tk->tai_offset;
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
+
+ return ret;
+}
+
+/**
+ * __timekeeping_set_tai_offset - Lock free worker function
+ *
+ */
+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));
+}
+
+/**
+ * timekeeping_set_tai_offset - Sets the current TAI offset from UTC
+ *
+ */
+void timekeeping_set_tai_offset(s32 tai_offset)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+ __timekeeping_set_tai_offset(tk, tai_offset);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+ clock_was_set();
+}
+
/**
* change_clocksource - Swaps clocksources if a new one is available
*
@@ -526,7 +623,8 @@ static int change_clocksource(void *data)
new = (struct clocksource *) data;
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
if (!new->enable || new->enable(new) == 0) {
@@ -535,9 +633,10 @@ static int change_clocksource(void *data)
if (old->disable)
old->disable(old);
}
- timekeeping_update(tk, true);
+ timekeeping_update(tk, true, true);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
return 0;
}
@@ -587,11 +686,11 @@ void getrawmonotonic(struct timespec *ts)
s64 nsecs;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
nsecs = timekeeping_get_ns_raw(tk);
*ts = tk->raw_time;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
timespec_add_ns(ts, nsecs);
}
@@ -607,11 +706,11 @@ int timekeeping_valid_for_hres(void)
int ret;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
return ret;
}
@@ -626,11 +725,11 @@ u64 timekeeping_max_deferment(void)
u64 ret;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
ret = tk->clock->max_idle_ns;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
return ret;
}
@@ -693,11 +792,10 @@ void __init timekeeping_init(void)
boot.tv_nsec = 0;
}
- seqlock_init(&tk->lock);
-
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
ntp_init();
- write_seqlock_irqsave(&tk->lock, flags);
clock = clocksource_default_clock();
if (clock->enable)
clock->enable(clock);
@@ -716,7 +814,10 @@ void __init timekeeping_init(void)
tmp.tv_nsec = 0;
tk_set_sleep_time(tk, tmp);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
+
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}
/* time in seconds when suspend began */
@@ -764,15 +865,17 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
if (has_persistent_clock())
return;
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
__timekeeping_inject_sleeptime(tk, delta);
- timekeeping_update(tk, true);
+ timekeeping_update(tk, true, true);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
@@ -788,26 +891,72 @@ void timekeeping_inject_sleeptime(struct timespec *delta)
static void timekeeping_resume(void)
{
struct timekeeper *tk = &timekeeper;
+ struct clocksource *clock = tk->clock;
unsigned long flags;
- struct timespec ts;
+ struct timespec ts_new, ts_delta;
+ cycle_t cycle_now, cycle_delta;
+ bool suspendtime_found = false;
- read_persistent_clock(&ts);
+ read_persistent_clock(&ts_new);
clockevents_resume();
clocksource_resume();
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ /*
+ * After system resumes, we need to calculate the suspended time and
+ * compensate it for the OS time. There are 3 sources that could be
+ * used: Nonstop clocksource during suspend, persistent clock and rtc
+ * device.
+ *
+ * One specific platform may have 1 or 2 or all of them, and the
+ * preference will be:
+ * suspend-nonstop clocksource -> persistent clock -> rtc
+ * The less preferred source will only be tried if there is no better
+ * usable source. The rtc part is handled separately in rtc core code.
+ */
+ cycle_now = clock->read(clock);
+ if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
+ cycle_now > clock->cycle_last) {
+ u64 num, max = ULLONG_MAX;
+ u32 mult = clock->mult;
+ u32 shift = clock->shift;
+ s64 nsec = 0;
+
+ cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
- if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
- ts = timespec_sub(ts, timekeeping_suspend_time);
- __timekeeping_inject_sleeptime(tk, &ts);
+ /*
+ * "cycle_delta * mutl" may cause 64 bits overflow, if the
+ * suspended time is too long. In that case we need do the
+ * 64 bits math carefully
+ */
+ do_div(max, mult);
+ if (cycle_delta > max) {
+ num = div64_u64(cycle_delta, max);
+ nsec = (((u64) max * mult) >> shift) * num;
+ cycle_delta -= num * max;
+ }
+ nsec += ((u64) cycle_delta * mult) >> shift;
+
+ ts_delta = ns_to_timespec(nsec);
+ suspendtime_found = true;
+ } else if (timespec_compare(&ts_new, &timekeeping_suspend_time) > 0) {
+ ts_delta = timespec_sub(ts_new, timekeeping_suspend_time);
+ suspendtime_found = true;
}
- /* re-base the last cycle value */
- tk->clock->cycle_last = tk->clock->read(tk->clock);
+
+ if (suspendtime_found)
+ __timekeeping_inject_sleeptime(tk, &ts_delta);
+
+ /* Re-base the last cycle value */
+ tk->cycle_last = clock->cycle_last = cycle_now;
tk->ntp_error = 0;
timekeeping_suspended = 0;
- timekeeping_update(tk, false);
- write_sequnlock_irqrestore(&tk->lock, flags);
+ timekeeping_update(tk, false, true);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
touch_softlockup_watchdog();
@@ -826,7 +975,8 @@ static int timekeeping_suspend(void)
read_persistent_clock(&timekeeping_suspend_time);
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
timekeeping_suspended = 1;
@@ -849,7 +999,8 @@ static int timekeeping_suspend(void)
timekeeping_suspend_time =
timespec_add(timekeeping_suspend_time, delta_delta);
}
- write_sequnlock_irqrestore(&tk->lock, flags);
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
clocksource_suspend();
@@ -1099,6 +1250,8 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
tk_set_wall_to_mono(tk,
timespec_sub(tk->wall_to_monotonic, ts));
+ __timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
+
clock_was_set_delayed();
}
}
@@ -1116,15 +1269,16 @@ static inline void accumulate_nsecs_to_secs(struct timekeeper *tk)
static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
u32 shift)
{
+ cycle_t interval = tk->cycle_interval << shift;
u64 raw_nsecs;
/* If the offset is smaller then a shifted interval, do nothing */
- if (offset < tk->cycle_interval<<shift)
+ if (offset < interval)
return offset;
/* Accumulate one shifted interval */
- offset -= tk->cycle_interval << shift;
- tk->clock->cycle_last += tk->cycle_interval << shift;
+ offset -= interval;
+ tk->cycle_last += interval;
tk->xtime_nsec += tk->xtime_interval << shift;
accumulate_nsecs_to_secs(tk);
@@ -1181,27 +1335,28 @@ static inline void old_vsyscall_fixup(struct timekeeper *tk)
static void update_wall_time(void)
{
struct clocksource *clock;
- struct timekeeper *tk = &timekeeper;
+ struct timekeeper *real_tk = &timekeeper;
+ struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
int shift = 0, maxshift;
unsigned long flags;
- write_seqlock_irqsave(&tk->lock, flags);
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
/* Make sure we're fully resumed: */
if (unlikely(timekeeping_suspended))
goto out;
- clock = tk->clock;
+ clock = real_tk->clock;
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
- offset = tk->cycle_interval;
+ offset = real_tk->cycle_interval;
#else
offset = (clock->read(clock) - clock->cycle_last) & clock->mask;
#endif
/* Check if there's really nothing to do */
- if (offset < tk->cycle_interval)
+ if (offset < real_tk->cycle_interval)
goto out;
/*
@@ -1238,11 +1393,24 @@ static void update_wall_time(void)
*/
accumulate_nsecs_to_secs(tk);
- timekeeping_update(tk, false);
-
+ write_seqcount_begin(&timekeeper_seq);
+ /* Update clock->cycle_last with the new value */
+ clock->cycle_last = tk->cycle_last;
+ /*
+ * Update the real timekeeper.
+ *
+ * We could avoid this memcpy by switching pointers, but that
+ * requires changes to all other timekeeper usage sites as
+ * well, i.e. move the timekeeper pointer getter into the
+ * spinlocked/seqcount protected sections. And we trade this
+ * memcpy under the timekeeper_seq against one before we start
+ * updating.
+ */
+ memcpy(real_tk, tk, sizeof(*tk));
+ timekeeping_update(real_tk, false, false);
+ write_seqcount_end(&timekeeper_seq);
out:
- write_sequnlock_irqrestore(&tk->lock, flags);
-
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}
/**
@@ -1289,13 +1457,13 @@ void get_monotonic_boottime(struct timespec *ts)
WARN_ON(timekeeping_suspended);
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
ts->tv_sec = tk->xtime_sec;
nsec = timekeeping_get_ns(tk);
tomono = tk->wall_to_monotonic;
sleep = tk->total_sleep_time;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
ts->tv_sec += tomono.tv_sec + sleep.tv_sec;
ts->tv_nsec = 0;
@@ -1354,10 +1522,10 @@ struct timespec current_kernel_time(void)
unsigned long seq;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
now = tk_xtime(tk);
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
return now;
}
@@ -1370,11 +1538,11 @@ struct timespec get_monotonic_coarse(void)
unsigned long seq;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
now = tk_xtime(tk);
mono = tk->wall_to_monotonic;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
set_normalized_timespec(&now, now.tv_sec + mono.tv_sec,
now.tv_nsec + mono.tv_nsec);
@@ -1405,11 +1573,11 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
unsigned long seq;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
*xtim = tk_xtime(tk);
*wtom = tk->wall_to_monotonic;
*sleep = tk->total_sleep_time;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
}
#ifdef CONFIG_HIGH_RES_TIMERS
@@ -1421,7 +1589,8 @@ void get_xtime_and_monotonic_and_sleep_offset(struct timespec *xtim,
* Returns current monotonic time and updates the offsets
* Called from hrtimer_interupt() or retrigger_next_event()
*/
-ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
+ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot,
+ ktime_t *offs_tai)
{
struct timekeeper *tk = &timekeeper;
ktime_t now;
@@ -1429,14 +1598,15 @@ ktime_t ktime_get_update_offsets(ktime_t *offs_real, ktime_t *offs_boot)
u64 secs, nsecs;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
secs = tk->xtime_sec;
nsecs = timekeeping_get_ns(tk);
*offs_real = tk->offs_real;
*offs_boot = tk->offs_boot;
- } while (read_seqretry(&tk->lock, seq));
+ *offs_tai = tk->offs_tai;
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
now = ktime_add_ns(ktime_set(secs, 0), nsecs);
now = ktime_sub(now, *offs_real);
@@ -1454,15 +1624,79 @@ ktime_t ktime_get_monotonic_offset(void)
struct timespec wtom;
do {
- seq = read_seqbegin(&tk->lock);
+ seq = read_seqcount_begin(&timekeeper_seq);
wtom = tk->wall_to_monotonic;
- } while (read_seqretry(&tk->lock, seq));
+ } while (read_seqcount_retry(&timekeeper_seq, seq));
return timespec_to_ktime(wtom);
}
EXPORT_SYMBOL_GPL(ktime_get_monotonic_offset);
/**
+ * do_adjtimex() - Accessor function to NTP __do_adjtimex function
+ */
+int do_adjtimex(struct timex *txc)
+{
+ struct timekeeper *tk = &timekeeper;
+ unsigned long flags;
+ struct timespec ts;
+ s32 orig_tai, tai;
+ int ret;
+
+ /* Validate the data before disabling interrupts */
+ ret = ntp_validate_timex(txc);
+ if (ret)
+ return ret;
+
+ if (txc->modes & ADJ_SETOFFSET) {
+ struct timespec delta;
+ delta.tv_sec = txc->time.tv_sec;
+ delta.tv_nsec = txc->time.tv_usec;
+ if (!(txc->modes & ADJ_NANO))
+ delta.tv_nsec *= 1000;
+ ret = timekeeping_inject_offset(&delta);
+ if (ret)
+ return ret;
+ }
+
+ getnstimeofday(&ts);
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ orig_tai = tai = tk->tai_offset;
+ ret = __do_adjtimex(txc, &ts, &tai);
+
+ if (tai != orig_tai) {
+ __timekeeping_set_tai_offset(tk, tai);
+ clock_was_set_delayed();
+ }
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+
+ return ret;
+}
+
+#ifdef CONFIG_NTP_PPS
+/**
+ * hardpps() - Accessor function to NTP __hardpps function
+ */
+void hardpps(const struct timespec *phase_ts, const struct timespec *raw_ts)
+{
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&timekeeper_lock, flags);
+ write_seqcount_begin(&timekeeper_seq);
+
+ __hardpps(phase_ts, raw_ts);
+
+ write_seqcount_end(&timekeeper_seq);
+ raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
+}
+EXPORT_SYMBOL(hardpps);
+#endif
+
+/**
* xtime_update() - advances the timekeeping infrastructure
* @ticks: number of ticks, that have elapsed since the last call.
*
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index af5a7e9f164..3bdf2832301 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -20,6 +20,13 @@
#include <asm/uaccess.h>
+
+struct timer_list_iter {
+ int cpu;
+ bool second_pass;
+ u64 now;
+};
+
typedef void (*print_fn_t)(struct seq_file *m, unsigned int *classes);
DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases);
@@ -133,7 +140,6 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
struct hrtimer_cpu_base *cpu_base = &per_cpu(hrtimer_bases, cpu);
int i;
- SEQ_printf(m, "\n");
SEQ_printf(m, "cpu: %d\n", cpu);
for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
SEQ_printf(m, " clock %d:\n", i);
@@ -187,6 +193,7 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now)
#undef P
#undef P_ns
+ SEQ_printf(m, "\n");
}
#ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -195,7 +202,6 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
{
struct clock_event_device *dev = td->evtdev;
- SEQ_printf(m, "\n");
SEQ_printf(m, "Tick Device: mode: %d\n", td->mode);
if (cpu < 0)
SEQ_printf(m, "Broadcast device\n");
@@ -230,12 +236,11 @@ print_tickdevice(struct seq_file *m, struct tick_device *td, int cpu)
print_name_offset(m, dev->event_handler);
SEQ_printf(m, "\n");
SEQ_printf(m, " retries: %lu\n", dev->retries);
+ SEQ_printf(m, "\n");
}
-static void timer_list_show_tickdevices(struct seq_file *m)
+static void timer_list_show_tickdevices_header(struct seq_file *m)
{
- int cpu;
-
#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
print_tickdevice(m, tick_get_broadcast_device(), -1);
SEQ_printf(m, "tick_broadcast_mask: %08lx\n",
@@ -246,47 +251,104 @@ static void timer_list_show_tickdevices(struct seq_file *m)
#endif
SEQ_printf(m, "\n");
#endif
- for_each_online_cpu(cpu)
- print_tickdevice(m, tick_get_device(cpu), cpu);
- SEQ_printf(m, "\n");
}
-#else
-static void timer_list_show_tickdevices(struct seq_file *m) { }
#endif
+static inline void timer_list_header(struct seq_file *m, u64 now)
+{
+ SEQ_printf(m, "Timer List Version: v0.7\n");
+ SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
+ SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
+ SEQ_printf(m, "\n");
+}
+
static int timer_list_show(struct seq_file *m, void *v)
{
+ struct timer_list_iter *iter = v;
+ u64 now = ktime_to_ns(ktime_get());
+
+ if (iter->cpu == -1 && !iter->second_pass)
+ timer_list_header(m, now);
+ else if (!iter->second_pass)
+ print_cpu(m, iter->cpu, iter->now);
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+ else if (iter->cpu == -1 && iter->second_pass)
+ timer_list_show_tickdevices_header(m);
+ else
+ print_tickdevice(m, tick_get_device(iter->cpu), iter->cpu);
+#endif
+ return 0;
+}
+
+void sysrq_timer_list_show(void)
+{
u64 now = ktime_to_ns(ktime_get());
int cpu;
- SEQ_printf(m, "Timer List Version: v0.7\n");
- SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES);
- SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now);
+ timer_list_header(NULL, now);
for_each_online_cpu(cpu)
- print_cpu(m, cpu, now);
+ print_cpu(NULL, cpu, now);
- SEQ_printf(m, "\n");
- timer_list_show_tickdevices(m);
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+ timer_list_show_tickdevices_header(NULL);
+ for_each_online_cpu(cpu)
+ print_tickdevice(NULL, tick_get_device(cpu), cpu);
+#endif
+ return;
+}
- return 0;
+static void *timer_list_start(struct seq_file *file, loff_t *offset)
+{
+ struct timer_list_iter *iter = file->private;
+
+ if (!*offset) {
+ iter->cpu = -1;
+ iter->now = ktime_to_ns(ktime_get());
+ } else if (iter->cpu >= nr_cpu_ids) {
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
+ if (!iter->second_pass) {
+ iter->cpu = -1;
+ iter->second_pass = true;
+ } else
+ return NULL;
+#else
+ return NULL;
+#endif
+ }
+ return iter;
}
-void sysrq_timer_list_show(void)
+static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset)
+{
+ struct timer_list_iter *iter = file->private;
+ iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
+ ++*offset;
+ return timer_list_start(file, offset);
+}
+
+static void timer_list_stop(struct seq_file *seq, void *v)
{
- timer_list_show(NULL, NULL);
}
+static const struct seq_operations timer_list_sops = {
+ .start = timer_list_start,
+ .next = timer_list_next,
+ .stop = timer_list_stop,
+ .show = timer_list_show,
+};
+
static int timer_list_open(struct inode *inode, struct file *filp)
{
- return single_open(filp, timer_list_show, NULL);
+ return seq_open_private(filp, &timer_list_sops,
+ sizeof(struct timer_list_iter));
}
static const struct file_operations timer_list_fops = {
.open = timer_list_open,
.read = seq_read,
.llseek = seq_lseek,
- .release = single_release,
+ .release = seq_release_private,
};
static int __init init_timer_list_procfs(void)
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-10-31 09:33:45 +0000