OpenCloudOS-Kernel/kernel/time/timekeeping.c

1781 lines
47 KiB
C
Raw Normal View History

/*
* linux/kernel/time/timekeeping.c
*
* Kernel timekeeping code and accessor functions
*
* This code was moved from linux/kernel/timer.c.
* Please see that file for copyright and history logs.
*
*/
#include <linux/timekeeper_internal.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/percpu.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/syscore_ops.h>
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/time.h>
#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"
#include "timekeeping_internal.h"
#define TK_CLEAR_NTP (1 << 0)
#define TK_MIRROR (1 << 1)
#define TK_CLOCK_WAS_SET (1 << 2)
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;
/* Flag for if there is a persistent clock on this platform */
bool __read_mostly persistent_clock_exist = false;
static inline void tk_normalize_xtime(struct timekeeper *tk)
{
while (tk->xtime_nsec >= ((u64)NSEC_PER_SEC << tk->shift)) {
tk->xtime_nsec -= (u64)NSEC_PER_SEC << tk->shift;
tk->xtime_sec++;
}
}
static inline struct timespec64 tk_xtime(struct timekeeper *tk)
{
struct timespec64 ts;
ts.tv_sec = tk->xtime_sec;
ts.tv_nsec = (long)(tk->xtime_nsec >> tk->shift);
return ts;
}
static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec = ts->tv_sec;
tk->xtime_nsec = (u64)ts->tv_nsec << tk->shift;
}
static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts)
{
tk->xtime_sec += ts->tv_sec;
tk->xtime_nsec += (u64)ts->tv_nsec << tk->shift;
tk_normalize_xtime(tk);
}
static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm)
{
struct timespec64 tmp;
/*
* Verify consistency of: offset_real = -wall_to_monotonic
* before modifying anything
*/
set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec,
-tk->wall_to_monotonic.tv_nsec);
WARN_ON_ONCE(tk->offs_real.tv64 != timespec64_to_ktime(tmp).tv64);
tk->wall_to_monotonic = wtm;
set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec);
tk->offs_real = timespec64_to_ktime(tmp);
tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0));
}
static void tk_set_sleep_time(struct timekeeper *tk, struct timespec64 t)
{
/* Verify consistency before modifying */
WARN_ON_ONCE(tk->offs_boot.tv64 != timespec64_to_ktime(tk->total_sleep_time).tv64);
tk->total_sleep_time = t;
tk->offs_boot = timespec64_to_ktime(t);
}
/**
* 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
* pair and interval request.
*
* Unless you're the timekeeping code, you should not be using this!
*/
static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
{
cycle_t interval;
u64 tmp, ntpinterval;
struct clocksource *old_clock;
old_clock = tk->clock;
tk->clock = clock;
tk->cycle_last = clock->cycle_last = clock->read(clock);
/* Do the ns -> cycle conversion first, using original mult */
tmp = NTP_INTERVAL_LENGTH;
tmp <<= clock->shift;
ntpinterval = tmp;
tmp += clock->mult/2;
do_div(tmp, clock->mult);
if (tmp == 0)
tmp = 1;
interval = (cycle_t) tmp;
tk->cycle_interval = interval;
/* Go back from cycles -> shifted ns */
tk->xtime_interval = (u64) interval * clock->mult;
tk->xtime_remainder = ntpinterval - tk->xtime_interval;
tk->raw_interval =
((u64) interval * clock->mult) >> clock->shift;
/* if changing clocks, convert xtime_nsec shift units */
if (old_clock) {
int shift_change = clock->shift - old_clock->shift;
if (shift_change < 0)
tk->xtime_nsec >>= -shift_change;
else
tk->xtime_nsec <<= shift_change;
}
tk->shift = clock->shift;
tk->ntp_error = 0;
tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift;
/*
* The timekeeper keeps its own mult values for the currently
* active clocksource. These value will be adjusted via NTP
* to counteract clock drifting.
*/
tk->mult = clock->mult;
}
/* Timekeeper helper functions. */
time: convert arch_gettimeoffset to a pointer Currently, whenever CONFIG_ARCH_USES_GETTIMEOFFSET is enabled, each arch core provides a single implementation of arch_gettimeoffset(). In many cases, different sub-architectures, different machines, or different timer providers exist, and so the arch ends up implementing arch_gettimeoffset() as a call-through-pointer anyway. Examples are ARM, Cris, M68K, and it's arguable that the remaining architectures, M32R and Blackfin, should be doing this anyway. Modify arch_gettimeoffset so that it itself is a function pointer, which the arch initializes. This will allow later changes to move the initialization of this function into individual machine support or timer drivers. This is particularly useful for code in drivers/clocksource which should rely on an arch-independant mechanism to register their implementation of arch_gettimeoffset(). This patch also converts the Cris architecture to set arch_gettimeoffset directly to the final implementation in time_init(), because Cris already had separate time_init() functions per sub-architecture. M68K and ARM are converted to set arch_gettimeoffset to the final implementation in later patches, because they already have function pointers in place for this purpose. Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: John Stultz <johnstul@us.ibm.com> Signed-off-by: Stephen Warren <swarren@nvidia.com>
2012-11-08 08:58:54 +08:00
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
static u32 default_arch_gettimeoffset(void) { return 0; }
u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
time: convert arch_gettimeoffset to a pointer Currently, whenever CONFIG_ARCH_USES_GETTIMEOFFSET is enabled, each arch core provides a single implementation of arch_gettimeoffset(). In many cases, different sub-architectures, different machines, or different timer providers exist, and so the arch ends up implementing arch_gettimeoffset() as a call-through-pointer anyway. Examples are ARM, Cris, M68K, and it's arguable that the remaining architectures, M32R and Blackfin, should be doing this anyway. Modify arch_gettimeoffset so that it itself is a function pointer, which the arch initializes. This will allow later changes to move the initialization of this function into individual machine support or timer drivers. This is particularly useful for code in drivers/clocksource which should rely on an arch-independant mechanism to register their implementation of arch_gettimeoffset(). This patch also converts the Cris architecture to set arch_gettimeoffset directly to the final implementation in time_init(), because Cris already had separate time_init() functions per sub-architecture. M68K and ARM are converted to set arch_gettimeoffset to the final implementation in later patches, because they already have function pointers in place for this purpose. Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: John Stultz <johnstul@us.ibm.com> Signed-off-by: Stephen Warren <swarren@nvidia.com>
2012-11-08 08:58:54 +08:00
#else
static inline u32 arch_gettimeoffset(void) { return 0; }
time: convert arch_gettimeoffset to a pointer Currently, whenever CONFIG_ARCH_USES_GETTIMEOFFSET is enabled, each arch core provides a single implementation of arch_gettimeoffset(). In many cases, different sub-architectures, different machines, or different timer providers exist, and so the arch ends up implementing arch_gettimeoffset() as a call-through-pointer anyway. Examples are ARM, Cris, M68K, and it's arguable that the remaining architectures, M32R and Blackfin, should be doing this anyway. Modify arch_gettimeoffset so that it itself is a function pointer, which the arch initializes. This will allow later changes to move the initialization of this function into individual machine support or timer drivers. This is particularly useful for code in drivers/clocksource which should rely on an arch-independant mechanism to register their implementation of arch_gettimeoffset(). This patch also converts the Cris architecture to set arch_gettimeoffset directly to the final implementation in time_init(), because Cris already had separate time_init() functions per sub-architecture. M68K and ARM are converted to set arch_gettimeoffset to the final implementation in later patches, because they already have function pointers in place for this purpose. Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: John Stultz <johnstul@us.ibm.com> Signed-off-by: Stephen Warren <swarren@nvidia.com>
2012-11-08 08:58:54 +08:00
#endif
static inline s64 timekeeping_get_ns(struct timekeeper *tk)
{
cycle_t cycle_now, cycle_delta;
struct clocksource *clock;
s64 nsec;
/* read clocksource: */
clock = tk->clock;
cycle_now = clock->read(clock);
/* calculate the delta since the last update_wall_time: */
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
nsec = cycle_delta * tk->mult + tk->xtime_nsec;
nsec >>= tk->shift;
time: convert arch_gettimeoffset to a pointer Currently, whenever CONFIG_ARCH_USES_GETTIMEOFFSET is enabled, each arch core provides a single implementation of arch_gettimeoffset(). In many cases, different sub-architectures, different machines, or different timer providers exist, and so the arch ends up implementing arch_gettimeoffset() as a call-through-pointer anyway. Examples are ARM, Cris, M68K, and it's arguable that the remaining architectures, M32R and Blackfin, should be doing this anyway. Modify arch_gettimeoffset so that it itself is a function pointer, which the arch initializes. This will allow later changes to move the initialization of this function into individual machine support or timer drivers. This is particularly useful for code in drivers/clocksource which should rely on an arch-independant mechanism to register their implementation of arch_gettimeoffset(). This patch also converts the Cris architecture to set arch_gettimeoffset directly to the final implementation in time_init(), because Cris already had separate time_init() functions per sub-architecture. M68K and ARM are converted to set arch_gettimeoffset to the final implementation in later patches, because they already have function pointers in place for this purpose. Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: John Stultz <johnstul@us.ibm.com> Signed-off-by: Stephen Warren <swarren@nvidia.com>
2012-11-08 08:58:54 +08:00
/* If arch requires, add in get_arch_timeoffset() */
return nsec + arch_gettimeoffset();
}
static inline s64 timekeeping_get_ns_raw(struct timekeeper *tk)
{
cycle_t cycle_now, cycle_delta;
struct clocksource *clock;
s64 nsec;
/* read clocksource: */
clock = tk->clock;
cycle_now = clock->read(clock);
/* calculate the delta since the last update_wall_time: */
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
/* convert delta to nanoseconds. */
nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
time: convert arch_gettimeoffset to a pointer Currently, whenever CONFIG_ARCH_USES_GETTIMEOFFSET is enabled, each arch core provides a single implementation of arch_gettimeoffset(). In many cases, different sub-architectures, different machines, or different timer providers exist, and so the arch ends up implementing arch_gettimeoffset() as a call-through-pointer anyway. Examples are ARM, Cris, M68K, and it's arguable that the remaining architectures, M32R and Blackfin, should be doing this anyway. Modify arch_gettimeoffset so that it itself is a function pointer, which the arch initializes. This will allow later changes to move the initialization of this function into individual machine support or timer drivers. This is particularly useful for code in drivers/clocksource which should rely on an arch-independant mechanism to register their implementation of arch_gettimeoffset(). This patch also converts the Cris architecture to set arch_gettimeoffset directly to the final implementation in time_init(), because Cris already had separate time_init() functions per sub-architecture. M68K and ARM are converted to set arch_gettimeoffset to the final implementation in later patches, because they already have function pointers in place for this purpose. Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: John Stultz <johnstul@us.ibm.com> Signed-off-by: Stephen Warren <swarren@nvidia.com>
2012-11-08 08:58:54 +08:00
/* If arch requires, add in get_arch_timeoffset() */
return nsec + arch_gettimeoffset();
}
#ifdef CONFIG_GENERIC_TIME_VSYSCALL_OLD
static inline void update_vsyscall(struct timekeeper *tk)
{
struct timespec xt;
xt = tk_xtime(tk);
update_vsyscall_old(&xt, &tk->wall_to_monotonic, tk->clock, tk->mult);
}
static inline void old_vsyscall_fixup(struct timekeeper *tk)
{
s64 remainder;
/*
* Store only full nanoseconds into xtime_nsec after rounding
* it up and add the remainder to the error difference.
* XXX - This is necessary to avoid small 1ns inconsistnecies caused
* by truncating the remainder in vsyscalls. However, it causes
* additional work to be done in timekeeping_adjust(). Once
* the vsyscall implementations are converted to use xtime_nsec
* (shifted nanoseconds), and CONFIG_GENERIC_TIME_VSYSCALL_OLD
* users are removed, this can be killed.
*/
remainder = tk->xtime_nsec & ((1ULL << tk->shift) - 1);
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)
#endif
static RAW_NOTIFIER_HEAD(pvclock_gtod_chain);
static void update_pvclock_gtod(struct timekeeper *tk, bool was_set)
{
raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk);
}
/**
* pvclock_gtod_register_notifier - register a pvclock timedata update listener
*/
int pvclock_gtod_register_notifier(struct notifier_block *nb)
{
struct timekeeper *tk = &timekeeper;
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb);
update_pvclock_gtod(tk, true);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier);
/**
* pvclock_gtod_unregister_notifier - unregister a pvclock
* timedata update listener
*/
int pvclock_gtod_unregister_notifier(struct notifier_block *nb)
{
unsigned long flags;
int ret;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
return ret;
}
EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier);
/* must hold timekeeper_lock */
static void timekeeping_update(struct timekeeper *tk, unsigned int action)
{
if (action & TK_CLEAR_NTP) {
tk->ntp_error = 0;
ntp_clear();
}
update_vsyscall(tk);
update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET);
if (action & TK_MIRROR)
memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
}
/**
* timekeeping_forward_now - update clock to the current time
*
* Forward the current clock to update its state since the last call to
* update_wall_time(). This is useful before significant clock changes,
* as it avoids having to deal with this time offset explicitly.
*/
static void timekeeping_forward_now(struct timekeeper *tk)
{
cycle_t cycle_now, cycle_delta;
struct clocksource *clock;
s64 nsec;
clock = tk->clock;
cycle_now = clock->read(clock);
cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
tk->cycle_last = clock->cycle_last = cycle_now;
tk->xtime_nsec += cycle_delta * tk->mult;
time: convert arch_gettimeoffset to a pointer Currently, whenever CONFIG_ARCH_USES_GETTIMEOFFSET is enabled, each arch core provides a single implementation of arch_gettimeoffset(). In many cases, different sub-architectures, different machines, or different timer providers exist, and so the arch ends up implementing arch_gettimeoffset() as a call-through-pointer anyway. Examples are ARM, Cris, M68K, and it's arguable that the remaining architectures, M32R and Blackfin, should be doing this anyway. Modify arch_gettimeoffset so that it itself is a function pointer, which the arch initializes. This will allow later changes to move the initialization of this function into individual machine support or timer drivers. This is particularly useful for code in drivers/clocksource which should rely on an arch-independant mechanism to register their implementation of arch_gettimeoffset(). This patch also converts the Cris architecture to set arch_gettimeoffset directly to the final implementation in time_init(), because Cris already had separate time_init() functions per sub-architecture. M68K and ARM are converted to set arch_gettimeoffset to the final implementation in later patches, because they already have function pointers in place for this purpose. Cc: Russell King <linux@arm.linux.org.uk> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Mikael Starvik <starvik@axis.com> Cc: Hirokazu Takata <takata@linux-m32r.org> Cc: Thomas Gleixner <tglx@linutronix.de> Acked-by: Geert Uytterhoeven <geert@linux-m68k.org> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: John Stultz <johnstul@us.ibm.com> Signed-off-by: Stephen Warren <swarren@nvidia.com>
2012-11-08 08:58:54 +08:00
/* If arch requires, add in get_arch_timeoffset() */
tk->xtime_nsec += (u64)arch_gettimeoffset() << tk->shift;
tk_normalize_xtime(tk);
nsec = clocksource_cyc2ns(cycle_delta, clock->mult, clock->shift);
timespec64_add_ns(&tk->raw_time, nsec);
}
/**
* __getnstimeofday64 - Returns the time of day in a timespec64.
* @ts: pointer to the timespec to be set
*
* Updates the time of day in the timespec.
* Returns 0 on success, or -ve when suspended (timespec will be undefined).
*/
int __getnstimeofday64(struct timespec64 *ts)
{
struct timekeeper *tk = &timekeeper;
unsigned long seq;
s64 nsecs = 0;
do {
seq = read_seqcount_begin(&timekeeper_seq);
ts->tv_sec = tk->xtime_sec;
nsecs = timekeeping_get_ns(tk);
} while (read_seqcount_retry(&timekeeper_seq, seq));
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsecs);
/*
* Do not bail out early, in case there were callers still using
* the value, even in the face of the WARN_ON.
*/
if (unlikely(timekeeping_suspended))
return -EAGAIN;
return 0;
}
EXPORT_SYMBOL(__getnstimeofday64);
/**
* getnstimeofday64 - Returns the time of day in a timespec64.
* @ts: pointer to the timespec to be set
*
* Returns the time of day in a timespec (WARN if suspended).
*/
void getnstimeofday64(struct timespec64 *ts)
{
WARN_ON(__getnstimeofday64(ts));
}
EXPORT_SYMBOL(getnstimeofday64);
ktime_t ktime_get(void)
{
struct timekeeper *tk = &timekeeper;
unsigned int seq;
s64 secs, nsecs;
WARN_ON(timekeeping_suspended);
do {
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_seqcount_retry(&timekeeper_seq, seq));
return ktime_set(secs, nsecs);
}
EXPORT_SYMBOL_GPL(ktime_get);
/**
* ktime_get_ts64 - get the monotonic clock in timespec64 format
* @ts: pointer to timespec variable
*
* The function calculates the monotonic clock from the realtime
* clock and the wall_to_monotonic offset and stores the result
* in normalized timespec format in the variable pointed to by @ts.
*/
void ktime_get_ts64(struct timespec64 *ts)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 tomono;
s64 nsec;
unsigned int seq;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&timekeeper_seq);
ts->tv_sec = tk->xtime_sec;
nsec = timekeeping_get_ns(tk);
tomono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&timekeeper_seq, seq));
ts->tv_sec += tomono.tv_sec;
ts->tv_nsec = 0;
timespec64_add_ns(ts, nsec + tomono.tv_nsec);
}
EXPORT_SYMBOL_GPL(ktime_get_ts64);
/**
* 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;
struct timespec64 ts64;
unsigned long seq;
u64 nsecs;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&timekeeper_seq);
ts64.tv_sec = tk->xtime_sec + tk->tai_offset;
nsecs = timekeeping_get_ns(tk);
} while (read_seqcount_retry(&timekeeper_seq, seq));
ts64.tv_nsec = 0;
timespec64_add_ns(&ts64, nsecs);
*ts = timespec64_to_timespec(ts64);
}
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
/**
* getnstime_raw_and_real - get day and raw monotonic time in timespec format
* @ts_raw: pointer to the timespec to be set to raw monotonic time
* @ts_real: pointer to the timespec to be set to the time of day
*
* This function reads both the time of day and raw monotonic time at the
* same time atomically and stores the resulting timestamps in timespec
* format.
*/
void getnstime_raw_and_real(struct timespec *ts_raw, struct timespec *ts_real)
{
struct timekeeper *tk = &timekeeper;
unsigned long seq;
s64 nsecs_raw, nsecs_real;
WARN_ON_ONCE(timekeeping_suspended);
do {
seq = read_seqcount_begin(&timekeeper_seq);
*ts_raw = timespec64_to_timespec(tk->raw_time);
ts_real->tv_sec = tk->xtime_sec;
ts_real->tv_nsec = 0;
nsecs_raw = timekeeping_get_ns_raw(tk);
nsecs_real = timekeeping_get_ns(tk);
} while (read_seqcount_retry(&timekeeper_seq, seq));
timespec_add_ns(ts_raw, nsecs_raw);
timespec_add_ns(ts_real, nsecs_real);
}
EXPORT_SYMBOL(getnstime_raw_and_real);
#endif /* CONFIG_NTP_PPS */
/**
* do_gettimeofday - Returns the time of day in a timeval
* @tv: pointer to the timeval to be set
*
* NOTE: Users should be converted to using getnstimeofday()
*/
void do_gettimeofday(struct timeval *tv)
{
struct timespec64 now;
getnstimeofday64(&now);
tv->tv_sec = now.tv_sec;
tv->tv_usec = now.tv_nsec/1000;
}
EXPORT_SYMBOL(do_gettimeofday);
/**
* do_settimeofday - Sets the time of day
* @tv: pointer to the timespec variable containing the new time
*
* Sets the time of day to the new time and update NTP and notify hrtimers
*/
int do_settimeofday(const struct timespec *tv)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 ts_delta, xt, tmp;
unsigned long flags;
if (!timespec_valid_strict(tv))
return -EINVAL;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
xt = tk_xtime(tk);
ts_delta.tv_sec = tv->tv_sec - xt.tv_sec;
ts_delta.tv_nsec = tv->tv_nsec - xt.tv_nsec;
tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta));
tmp = timespec_to_timespec64(*tv);
tk_set_xtime(tk, &tmp);
timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
return 0;
}
EXPORT_SYMBOL(do_settimeofday);
/**
* timekeeping_inject_offset - Adds or subtracts from the current time.
* @tv: pointer to the timespec variable containing the offset
*
* Adds or subtracts an offset value from the current time.
*/
int timekeeping_inject_offset(struct timespec *ts)
{
struct timekeeper *tk = &timekeeper;
unsigned long flags;
struct timespec64 ts64, tmp;
int ret = 0;
if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
return -EINVAL;
ts64 = timespec_to_timespec64(*ts);
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
/* Make sure the proposed value is valid */
tmp = timespec64_add(tk_xtime(tk), ts64);
if (!timespec64_valid_strict(&tmp)) {
ret = -EINVAL;
goto error;
}
tk_xtime_add(tk, &ts64);
tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts64));
error: /* even if we error out, we forwarded the time, so call update */
timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
return ret;
}
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_add(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);
timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
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
*
* Accumulates current time interval and initializes new clocksource
*/
static int change_clocksource(void *data)
{
struct timekeeper *tk = &timekeeper;
struct clocksource *new, *old;
unsigned long flags;
new = (struct clocksource *) data;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
/*
* If the cs is in module, get a module reference. Succeeds
* for built-in code (owner == NULL) as well.
*/
if (try_module_get(new->owner)) {
if (!new->enable || new->enable(new) == 0) {
old = tk->clock;
tk_setup_internals(tk, new);
if (old->disable)
old->disable(old);
module_put(old->owner);
} else {
module_put(new->owner);
}
}
timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
return 0;
}
/**
* timekeeping_notify - Install a new clock source
* @clock: pointer to the clock source
*
* This function is called from clocksource.c after a new, better clock
* source has been registered. The caller holds the clocksource_mutex.
*/
int timekeeping_notify(struct clocksource *clock)
{
struct timekeeper *tk = &timekeeper;
if (tk->clock == clock)
return 0;
stop_machine(change_clocksource, clock, NULL);
tick_clock_notify();
return tk->clock == clock ? 0 : -1;
}
/**
* ktime_get_real - get the real (wall-) time in ktime_t format
*
* returns the time in ktime_t format
*/
ktime_t ktime_get_real(void)
{
struct timespec64 now;
getnstimeofday64(&now);
return timespec64_to_ktime(now);
}
EXPORT_SYMBOL_GPL(ktime_get_real);
/**
* getrawmonotonic - Returns the raw monotonic time in a timespec
* @ts: pointer to the timespec to be set
*
* Returns the raw monotonic time (completely un-modified by ntp)
*/
void getrawmonotonic(struct timespec *ts)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 ts64;
unsigned long seq;
s64 nsecs;
do {
seq = read_seqcount_begin(&timekeeper_seq);
nsecs = timekeeping_get_ns_raw(tk);
ts64 = tk->raw_time;
} while (read_seqcount_retry(&timekeeper_seq, seq));
timespec64_add_ns(&ts64, nsecs);
*ts = timespec64_to_timespec(ts64);
}
EXPORT_SYMBOL(getrawmonotonic);
/**
* timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
*/
int timekeeping_valid_for_hres(void)
{
struct timekeeper *tk = &timekeeper;
unsigned long seq;
int ret;
do {
seq = read_seqcount_begin(&timekeeper_seq);
ret = tk->clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
} while (read_seqcount_retry(&timekeeper_seq, seq));
return ret;
}
/**
* timekeeping_max_deferment - Returns max time the clocksource can be deferred
*/
u64 timekeeping_max_deferment(void)
{
struct timekeeper *tk = &timekeeper;
unsigned long seq;
u64 ret;
do {
seq = read_seqcount_begin(&timekeeper_seq);
ret = tk->clock->max_idle_ns;
} while (read_seqcount_retry(&timekeeper_seq, seq));
return ret;
}
/**
* read_persistent_clock - Return time from the persistent clock.
*
* Weak dummy function for arches that do not yet support it.
* Reads the time from the battery backed persistent clock.
* Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
*
* XXX - Do be sure to remove it once all arches implement it.
*/
void __weak read_persistent_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
}
/**
* read_boot_clock - Return time of the system start.
*
* Weak dummy function for arches that do not yet support it.
* Function to read the exact time the system has been started.
* Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported.
*
* XXX - Do be sure to remove it once all arches implement it.
*/
void __weak read_boot_clock(struct timespec *ts)
{
ts->tv_sec = 0;
ts->tv_nsec = 0;
}
/*
* timekeeping_init - Initializes the clocksource and common timekeeping values
*/
void __init timekeeping_init(void)
{
struct timekeeper *tk = &timekeeper;
struct clocksource *clock;
unsigned long flags;
struct timespec64 now, boot, tmp;
struct timespec ts;
read_persistent_clock(&ts);
now = timespec_to_timespec64(ts);
if (!timespec64_valid_strict(&now)) {
pr_warn("WARNING: Persistent clock returned invalid value!\n"
" Check your CMOS/BIOS settings.\n");
now.tv_sec = 0;
now.tv_nsec = 0;
} else if (now.tv_sec || now.tv_nsec)
persistent_clock_exist = true;
read_boot_clock(&ts);
boot = timespec_to_timespec64(ts);
if (!timespec64_valid_strict(&boot)) {
pr_warn("WARNING: Boot clock returned invalid value!\n"
" Check your CMOS/BIOS settings.\n");
boot.tv_sec = 0;
boot.tv_nsec = 0;
}
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
ntp_init();
clock = clocksource_default_clock();
if (clock->enable)
clock->enable(clock);
tk_setup_internals(tk, clock);
tk_set_xtime(tk, &now);
tk->raw_time.tv_sec = 0;
tk->raw_time.tv_nsec = 0;
if (boot.tv_sec == 0 && boot.tv_nsec == 0)
boot = tk_xtime(tk);
set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
tk_set_wall_to_mono(tk, tmp);
tmp.tv_sec = 0;
tmp.tv_nsec = 0;
tk_set_sleep_time(tk, tmp);
memcpy(&shadow_timekeeper, &timekeeper, sizeof(timekeeper));
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
}
/* time in seconds when suspend began */
static struct timespec64 timekeeping_suspend_time;
/**
* __timekeeping_inject_sleeptime - Internal function to add sleep interval
* @delta: pointer to a timespec delta value
*
* Takes a timespec offset measuring a suspend interval and properly
* adds the sleep offset to the timekeeping variables.
*/
static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
struct timespec64 *delta)
{
if (!timespec64_valid_strict(delta)) {
printk_deferred(KERN_WARNING
"__timekeeping_inject_sleeptime: Invalid "
"sleep delta value!\n");
return;
}
tk_xtime_add(tk, delta);
tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta));
tk_set_sleep_time(tk, timespec64_add(tk->total_sleep_time, *delta));
tk_debug_account_sleep_time(delta);
}
/**
* timekeeping_inject_sleeptime - Adds suspend interval to timeekeeping values
* @delta: pointer to a timespec delta value
*
* This hook is for architectures that cannot support read_persistent_clock
* because their RTC/persistent clock is only accessible when irqs are enabled.
*
* This function should only be called by rtc_resume(), and allows
* a suspend offset to be injected into the timekeeping values.
*/
void timekeeping_inject_sleeptime(struct timespec *delta)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 tmp;
unsigned long flags;
/*
* Make sure we don't set the clock twice, as timekeeping_resume()
* already did it
*/
if (has_persistent_clock())
return;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
tmp = timespec_to_timespec64(*delta);
__timekeeping_inject_sleeptime(tk, &tmp);
timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
/* signal hrtimers about time change */
clock_was_set();
}
/**
* timekeeping_resume - Resumes the generic timekeeping subsystem.
*
* This is for the generic clocksource timekeeping.
* xtime/wall_to_monotonic/jiffies/etc are
* still managed by arch specific suspend/resume code.
*/
static void timekeeping_resume(void)
{
struct timekeeper *tk = &timekeeper;
struct clocksource *clock = tk->clock;
unsigned long flags;
struct timespec64 ts_new, ts_delta;
struct timespec tmp;
cycle_t cycle_now, cycle_delta;
bool suspendtime_found = false;
read_persistent_clock(&tmp);
ts_new = timespec_to_timespec64(tmp);
clockevents_resume();
clocksource_resume();
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;
/*
* "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_timespec64(nsec);
suspendtime_found = true;
} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
suspendtime_found = true;
}
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, TK_MIRROR | TK_CLOCK_WAS_SET);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
touch_softlockup_watchdog();
clockevents_notify(CLOCK_EVT_NOTIFY_RESUME, NULL);
/* Resume hrtimers */
hrtimers_resume();
}
static int timekeeping_suspend(void)
{
struct timekeeper *tk = &timekeeper;
unsigned long flags;
struct timespec64 delta, delta_delta;
static struct timespec64 old_delta;
struct timespec tmp;
read_persistent_clock(&tmp);
timekeeping_suspend_time = timespec_to_timespec64(tmp);
/*
* On some systems the persistent_clock can not be detected at
* timekeeping_init by its return value, so if we see a valid
* value returned, update the persistent_clock_exists flag.
*/
if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
persistent_clock_exist = true;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
write_seqcount_begin(&timekeeper_seq);
timekeeping_forward_now(tk);
timekeeping_suspended = 1;
time: Avoid accumulating time drift in suspend/resume Because the read_persistent_clock interface is usually backed by only a second granular interface, each time we read from the persistent clock for suspend/resume, we introduce a half second (on average) of error. In order to avoid this error accumulating as the system is suspended over and over, this patch measures the time delta between the persistent clock and the system CLOCK_REALTIME. If the delta is less then 2 seconds from the last suspend, we compensate by using the previous time delta (keeping it close). If it is larger then 2 seconds, we assume the clock was set or has been changed, so we do no correction and update the delta. Note: If NTP is running, ths could seem to "fight" with the NTP corrected time, where as if the system time was off by 1 second, and NTP slewed the value in, a suspend/resume cycle could undo this correction, by trying to restore the previous offset from the persistent clock. However, without this patch, since each read could cause almost a full second worth of error, its possible to get almost 2 seconds of error just from the suspend/resume cycle alone, so this about equal to any offset added by the compensation. Further on systems that suspend/resume frequently, this should keep time closer then NTP could compensate for if the errors were allowed to accumulate. Credits to Arve Hjønnevåg for suggesting this solution. CC: Arve Hjønnevåg <arve@android.com> CC: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: John Stultz <john.stultz@linaro.org>
2011-06-01 13:53:23 +08:00
/*
* To avoid drift caused by repeated suspend/resumes,
* which each can add ~1 second drift error,
* try to compensate so the difference in system time
* and persistent_clock time stays close to constant.
*/
delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time);
delta_delta = timespec64_sub(delta, old_delta);
time: Avoid accumulating time drift in suspend/resume Because the read_persistent_clock interface is usually backed by only a second granular interface, each time we read from the persistent clock for suspend/resume, we introduce a half second (on average) of error. In order to avoid this error accumulating as the system is suspended over and over, this patch measures the time delta between the persistent clock and the system CLOCK_REALTIME. If the delta is less then 2 seconds from the last suspend, we compensate by using the previous time delta (keeping it close). If it is larger then 2 seconds, we assume the clock was set or has been changed, so we do no correction and update the delta. Note: If NTP is running, ths could seem to "fight" with the NTP corrected time, where as if the system time was off by 1 second, and NTP slewed the value in, a suspend/resume cycle could undo this correction, by trying to restore the previous offset from the persistent clock. However, without this patch, since each read could cause almost a full second worth of error, its possible to get almost 2 seconds of error just from the suspend/resume cycle alone, so this about equal to any offset added by the compensation. Further on systems that suspend/resume frequently, this should keep time closer then NTP could compensate for if the errors were allowed to accumulate. Credits to Arve Hjønnevåg for suggesting this solution. CC: Arve Hjønnevåg <arve@android.com> CC: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: John Stultz <john.stultz@linaro.org>
2011-06-01 13:53:23 +08:00
if (abs(delta_delta.tv_sec) >= 2) {
/*
* if delta_delta is too large, assume time correction
* has occured and set old_delta to the current delta.
*/
old_delta = delta;
} else {
/* Otherwise try to adjust old_system to compensate */
timekeeping_suspend_time =
timespec64_add(timekeeping_suspend_time, delta_delta);
time: Avoid accumulating time drift in suspend/resume Because the read_persistent_clock interface is usually backed by only a second granular interface, each time we read from the persistent clock for suspend/resume, we introduce a half second (on average) of error. In order to avoid this error accumulating as the system is suspended over and over, this patch measures the time delta between the persistent clock and the system CLOCK_REALTIME. If the delta is less then 2 seconds from the last suspend, we compensate by using the previous time delta (keeping it close). If it is larger then 2 seconds, we assume the clock was set or has been changed, so we do no correction and update the delta. Note: If NTP is running, ths could seem to "fight" with the NTP corrected time, where as if the system time was off by 1 second, and NTP slewed the value in, a suspend/resume cycle could undo this correction, by trying to restore the previous offset from the persistent clock. However, without this patch, since each read could cause almost a full second worth of error, its possible to get almost 2 seconds of error just from the suspend/resume cycle alone, so this about equal to any offset added by the compensation. Further on systems that suspend/resume frequently, this should keep time closer then NTP could compensate for if the errors were allowed to accumulate. Credits to Arve Hjønnevåg for suggesting this solution. CC: Arve Hjønnevåg <arve@android.com> CC: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: John Stultz <john.stultz@linaro.org>
2011-06-01 13:53:23 +08:00
}
timekeeping_update(tk, TK_MIRROR);
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
clocksource_suspend();
clockevents_suspend();
return 0;
}
/* sysfs resume/suspend bits for timekeeping */
static struct syscore_ops timekeeping_syscore_ops = {
.resume = timekeeping_resume,
.suspend = timekeeping_suspend,
};
static int __init timekeeping_init_ops(void)
{
register_syscore_ops(&timekeeping_syscore_ops);
return 0;
}
device_initcall(timekeeping_init_ops);
/*
* If the error is already larger, we look ahead even further
* to compensate for late or lost adjustments.
*/
static __always_inline int timekeeping_bigadjust(struct timekeeper *tk,
s64 error, s64 *interval,
s64 *offset)
{
s64 tick_error, i;
u32 look_ahead, adj;
s32 error2, mult;
/*
* Use the current error value to determine how much to look ahead.
* The larger the error the slower we adjust for it to avoid problems
* with losing too many ticks, otherwise we would overadjust and
* produce an even larger error. The smaller the adjustment the
* faster we try to adjust for it, as lost ticks can do less harm
* here. This is tuned so that an error of about 1 msec is adjusted
* within about 1 sec (or 2^20 nsec in 2^SHIFT_HZ ticks).
*/
error2 = tk->ntp_error >> (NTP_SCALE_SHIFT + 22 - 2 * SHIFT_HZ);
error2 = abs(error2);
for (look_ahead = 0; error2 > 0; look_ahead++)
error2 >>= 2;
/*
* Now calculate the error in (1 << look_ahead) ticks, but first
* remove the single look ahead already included in the error.
*/
tick_error = ntp_tick_length() >> (tk->ntp_error_shift + 1);
tick_error -= tk->xtime_interval >> 1;
error = ((error - tick_error) >> look_ahead) + tick_error;
/* Finally calculate the adjustment shift value. */
i = *interval;
mult = 1;
if (error < 0) {
error = -error;
*interval = -*interval;
*offset = -*offset;
mult = -1;
}
for (adj = 0; error > i; adj++)
error >>= 1;
*interval <<= adj;
*offset <<= adj;
return mult << adj;
}
/*
* Adjust the multiplier to reduce the error value,
* this is optimized for the most common adjustments of -1,0,1,
* for other values we can do a bit more work.
*/
static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
{
s64 error, interval = tk->cycle_interval;
int adj;
/*
* The point of this is to check if the error is greater than half
* an interval.
*
* First we shift it down from NTP_SHIFT to clocksource->shifted nsecs.
*
* Note we subtract one in the shift, so that error is really error*2.
* This "saves" dividing(shifting) interval twice, but keeps the
* (error > interval) comparison as still measuring if error is
* larger than half an interval.
*
* Note: It does not "save" on aggravation when reading the code.
*/
error = tk->ntp_error >> (tk->ntp_error_shift - 1);
if (error > interval) {
/*
* We now divide error by 4(via shift), which checks if
* the error is greater than twice the interval.
* If it is greater, we need a bigadjust, if its smaller,
* we can adjust by 1.
*/
error >>= 2;
if (likely(error <= interval))
adj = 1;
else
adj = timekeeping_bigadjust(tk, error, &interval, &offset);
} else {
if (error < -interval) {
/* See comment above, this is just switched for the negative */
error >>= 2;
if (likely(error >= -interval)) {
adj = -1;
interval = -interval;
offset = -offset;
} else {
adj = timekeeping_bigadjust(tk, error, &interval, &offset);
}
} else {
goto out_adjust;
}
}
if (unlikely(tk->clock->maxadj &&
(tk->mult + adj > tk->clock->mult + tk->clock->maxadj))) {
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);
}
/*
* So the following can be confusing.
*
* To keep things simple, lets assume adj == 1 for now.
*
* When adj != 1, remember that the interval and offset values
* have been appropriately scaled so the math is the same.
*
* The basic idea here is that we're increasing the multiplier
* by one, this causes the xtime_interval to be incremented by
* one cycle_interval. This is because:
* xtime_interval = cycle_interval * mult
* So if mult is being incremented by one:
* xtime_interval = cycle_interval * (mult + 1)
* Its the same as:
* xtime_interval = (cycle_interval * mult) + cycle_interval
* Which can be shortened to:
* xtime_interval += cycle_interval
*
* So offset stores the non-accumulated cycles. Thus the current
* time (in shifted nanoseconds) is:
* now = (offset * adj) + xtime_nsec
* Now, even though we're adjusting the clock frequency, we have
* to keep time consistent. In other words, we can't jump back
* in time, and we also want to avoid jumping forward in time.
*
* So given the same offset value, we need the time to be the same
* both before and after the freq adjustment.
* now = (offset * adj_1) + xtime_nsec_1
* now = (offset * adj_2) + xtime_nsec_2
* So:
* (offset * adj_1) + xtime_nsec_1 =
* (offset * adj_2) + xtime_nsec_2
* And we know:
* adj_2 = adj_1 + 1
* So:
* (offset * adj_1) + xtime_nsec_1 =
* (offset * (adj_1+1)) + xtime_nsec_2
* (offset * adj_1) + xtime_nsec_1 =
* (offset * adj_1) + offset + xtime_nsec_2
* Canceling the sides:
* xtime_nsec_1 = offset + xtime_nsec_2
* Which gives us:
* xtime_nsec_2 = xtime_nsec_1 - offset
* Which simplfies to:
* xtime_nsec -= offset
*
* XXX - TODO: Doc ntp_error calculation.
*/
tk->mult += adj;
tk->xtime_interval += interval;
tk->xtime_nsec -= offset;
tk->ntp_error -= (interval - offset) << tk->ntp_error_shift;
out_adjust:
/*
* It may be possible that when we entered this function, xtime_nsec
* was very small. Further, if we're slightly speeding the clocksource
* in the code above, its possible the required corrective factor to
* xtime_nsec could cause it to underflow.
*
* Now, since we already accumulated the second, cannot simply roll
* the accumulated second back, since the NTP subsystem has been
* notified via second_overflow. So instead we push xtime_nsec forward
* by the amount we underflowed, and add that amount into the error.
*
* We'll correct this error next time through this function, when
* xtime_nsec is not as small.
*/
if (unlikely((s64)tk->xtime_nsec < 0)) {
s64 neg = -(s64)tk->xtime_nsec;
tk->xtime_nsec = 0;
tk->ntp_error += neg << tk->ntp_error_shift;
}
}
/**
* accumulate_nsecs_to_secs - Accumulates nsecs into secs
*
* Helper function that accumulates a the nsecs greater then a second
* from the xtime_nsec field to the xtime_secs field.
* It also calls into the NTP code to handle leapsecond processing.
*
*/
static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
{
u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
unsigned int clock_set = 0;
while (tk->xtime_nsec >= nsecps) {
int leap;
tk->xtime_nsec -= nsecps;
tk->xtime_sec++;
/* Figure out if its a leap sec and apply if needed */
leap = second_overflow(tk->xtime_sec);
if (unlikely(leap)) {
struct timespec64 ts;
tk->xtime_sec += leap;
ts.tv_sec = leap;
ts.tv_nsec = 0;
tk_set_wall_to_mono(tk,
timespec64_sub(tk->wall_to_monotonic, ts));
__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
clock_set = TK_CLOCK_WAS_SET;
}
}
return clock_set;
}
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
/**
* logarithmic_accumulation - shifted accumulation of cycles
*
* This functions accumulates a shifted interval of cycles into
* into a shifted interval nanoseconds. Allows for O(log) accumulation
* loop.
*
* Returns the unconsumed cycles.
*/
static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
u32 shift,
unsigned int *clock_set)
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
{
cycle_t interval = tk->cycle_interval << shift;
u64 raw_nsecs;
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
/* If the offset is smaller then a shifted interval, do nothing */
if (offset < interval)
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
return offset;
/* Accumulate one shifted interval */
offset -= interval;
tk->cycle_last += interval;
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
tk->xtime_nsec += tk->xtime_interval << shift;
*clock_set |= accumulate_nsecs_to_secs(tk);
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
/* Accumulate raw time */
raw_nsecs = (u64)tk->raw_interval << shift;
raw_nsecs += tk->raw_time.tv_nsec;
if (raw_nsecs >= NSEC_PER_SEC) {
u64 raw_secs = raw_nsecs;
raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
tk->raw_time.tv_sec += raw_secs;
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
}
tk->raw_time.tv_nsec = raw_nsecs;
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
/* Accumulate error between NTP and clock interval */
tk->ntp_error += ntp_tick_length() << shift;
tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) <<
(tk->ntp_error_shift + shift);
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
return offset;
}
/**
* update_wall_time - Uses the current clocksource to increment the wall time
*
*/
void update_wall_time(void)
{
struct clocksource *clock;
struct timekeeper *real_tk = &timekeeper;
struct timekeeper *tk = &shadow_timekeeper;
cycle_t offset;
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
int shift = 0, maxshift;
unsigned int clock_set = 0;
unsigned long flags;
raw_spin_lock_irqsave(&timekeeper_lock, flags);
/* Make sure we're fully resumed: */
if (unlikely(timekeeping_suspended))
goto out;
clock = real_tk->clock;
#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
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 < real_tk->cycle_interval)
goto out;
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
/*
* With NO_HZ we may have to accumulate many cycle_intervals
* (think "ticks") worth of time at once. To do this efficiently,
* we calculate the largest doubling multiple of cycle_intervals
* that is smaller than the offset. We then accumulate that
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
* chunk in one go, and then try to consume the next smaller
* doubled multiple.
*/
shift = ilog2(offset) - ilog2(tk->cycle_interval);
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
shift = max(0, shift);
/* Bound shift to one less than what overflows tick_length */
maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
time: Implement logarithmic time accumulation Accumulating one tick at a time works well unless we're using NOHZ. Then it can be an issue, since we may have to run through the loop a few thousand times, which can increase timer interrupt caused latency. The current solution was to accumulate in half-second intervals with NOHZ. This kept the number of loops down, however it did slightly change how we make NTP adjustments. While not an issue with NTPd users, as NTPd makes adjustments over a longer period of time, other adjtimex() users have noticed the half-second granularity with which we can apply frequency changes to the clock. For instance, if a application tries to apply a 100ppm frequency correction for 20ms to correct a 2us offset, with NOHZ they either get no correction, or a 50us correction. Now, there will always be some granularity error for applying frequency corrections. However with users sensitive to this error have seen a 50-500x increase with NOHZ compared to running without NOHZ. So I figured I'd try another approach then just simply increasing the interval. My approach is to consume the time interval logarithmically. This reduces the number of times through the loop needed keeping latency down, while still preserving the original granularity error for adjtimex() changes. Further, this change allows us to remove the xtime_cache code (patch to follow), as xtime is always within one tick of the current time, instead of the half-second updates it saw before. An earlier version of this patch has been shipping to x86 users in the RedHat MRG releases for awhile without issue, but I've reworked this version to be even more careful about avoiding possible overflows if the shift value gets too large. Signed-off-by: John Stultz <johnstul@us.ibm.com> Acked-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: John Kacur <jkacur@redhat.com> Cc: Clark Williams <williams@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Andrew Morton <akpm@linux-foundation.org> LKML-Reference: <1254525473.7741.88.camel@localhost.localdomain> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-03 07:17:53 +08:00
shift = min(shift, maxshift);
while (offset >= tk->cycle_interval) {
offset = logarithmic_accumulation(tk, offset, shift,
&clock_set);
if (offset < tk->cycle_interval<<shift)
shift--;
}
/* correct the clock when NTP error is too big */
timekeeping_adjust(tk, offset);
/*
* XXX This can be killed once everyone converts
* to the new update_vsyscall.
*/
old_vsyscall_fixup(tk);
/*
* Finally, make sure that after the rounding
* xtime_nsec isn't larger than NSEC_PER_SEC
*/
clock_set |= accumulate_nsecs_to_secs(tk);
Revert "time: Remove xtime_cache" This reverts commit 7bc7d637452383d56ba4368d4336b0dde1bb476d, as requested by John Stultz. Quoting John: "Petr Titěra reported an issue where he saw odd atime regressions with 2.6.33 where there were a full second worth of nanoseconds in the nanoseconds field. He also reviewed the time code and narrowed down the problem: unhandled overflow of the nanosecond field caused by rounding up the sub-nanosecond accumulated time. Details: * At the end of update_wall_time(), we currently round up the sub-nanosecond portion of accumulated time when storing it into xtime. This was added to avoid time inconsistencies caused when the sub-nanosecond portion was truncated when storing into xtime. Unfortunately we don't handle the possible second overflow caused by that rounding. * Previously the xtime_cache code hid this overflow by normalizing the xtime value when storing into the xtime_cache. * We could try to handle the second overflow after the rounding up, but since this affects the timekeeping's internal state, this would further complicate the next accumulation cycle, causing small errors in ntp steering. As much as I'd like to get rid of it, the xtime_cache code is known to work. * The correct fix is really to include the sub-nanosecond portion in the timekeeping accessor function, so we don't need to round up at during accumulation. This would greatly simplify the accumulation code. Unfortunately, we can't do this safely until the last three non-GENERIC_TIME arches (sparc32, arm, cris) are converted (those patches are in -mm) and we kill off the spots where arches set xtime directly. This is all 2.6.34 material, so I think reverting the xtime_cache change is the best approach for now. Many thanks to Petr for both reporting and finding the issue!" Reported-by: Petr Titěra <P.Titera@century.cz> Requested-by: john stultz <johnstul@us.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-23 06:10:37 +08:00
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, 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();
}
/**
* getboottime - Return the real time of system boot.
* @ts: pointer to the timespec to be set
*
* Returns the wall-time of boot in a timespec.
*
* This is based on the wall_to_monotonic offset and the total suspend
* time. Calls to settimeofday will affect the value returned (which
* basically means that however wrong your real time clock is at boot time,
* you get the right time here).
*/
void getboottime(struct timespec *ts)
{
struct timekeeper *tk = &timekeeper;
struct timespec boottime = {
.tv_sec = tk->wall_to_monotonic.tv_sec +
tk->total_sleep_time.tv_sec,
.tv_nsec = tk->wall_to_monotonic.tv_nsec +
tk->total_sleep_time.tv_nsec
};
set_normalized_timespec(ts, -boottime.tv_sec, -boottime.tv_nsec);
}
EXPORT_SYMBOL_GPL(getboottime);
/**
* get_monotonic_boottime - Returns monotonic time since boot
* @ts: pointer to the timespec to be set
*
* Returns the monotonic time since boot in a timespec.
*
* This is similar to CLOCK_MONTONIC/ktime_get_ts, but also
* includes the time spent in suspend.
*/
void get_monotonic_boottime(struct timespec *ts)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 tomono, sleep, ret;
s64 nsec;
unsigned int seq;
WARN_ON(timekeeping_suspended);
do {
seq = read_seqcount_begin(&timekeeper_seq);
ret.tv_sec = tk->xtime_sec;
nsec = timekeeping_get_ns(tk);
tomono = tk->wall_to_monotonic;
sleep = tk->total_sleep_time;
} while (read_seqcount_retry(&timekeeper_seq, seq));
ret.tv_sec += tomono.tv_sec + sleep.tv_sec;
ret.tv_nsec = 0;
timespec64_add_ns(&ret, nsec + tomono.tv_nsec + sleep.tv_nsec);
*ts = timespec64_to_timespec(ret);
}
EXPORT_SYMBOL_GPL(get_monotonic_boottime);
/**
* ktime_get_boottime - Returns monotonic time since boot in a ktime
*
* Returns the monotonic time since boot in a ktime
*
* This is similar to CLOCK_MONTONIC/ktime_get, but also
* includes the time spent in suspend.
*/
ktime_t ktime_get_boottime(void)
{
struct timespec ts;
get_monotonic_boottime(&ts);
return timespec_to_ktime(ts);
}
EXPORT_SYMBOL_GPL(ktime_get_boottime);
/**
* monotonic_to_bootbased - Convert the monotonic time to boot based.
* @ts: pointer to the timespec to be converted
*/
void monotonic_to_bootbased(struct timespec *ts)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 ts64;
ts64 = timespec_to_timespec64(*ts);
ts64 = timespec64_add(ts64, tk->total_sleep_time);
*ts = timespec64_to_timespec(ts64);
}
EXPORT_SYMBOL_GPL(monotonic_to_bootbased);
unsigned long get_seconds(void)
{
struct timekeeper *tk = &timekeeper;
return tk->xtime_sec;
}
EXPORT_SYMBOL(get_seconds);
struct timespec __current_kernel_time(void)
{
struct timekeeper *tk = &timekeeper;
return timespec64_to_timespec(tk_xtime(tk));
}
struct timespec current_kernel_time(void)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 now;
unsigned long seq;
do {
seq = read_seqcount_begin(&timekeeper_seq);
Revert "time: Remove xtime_cache" This reverts commit 7bc7d637452383d56ba4368d4336b0dde1bb476d, as requested by John Stultz. Quoting John: "Petr Titěra reported an issue where he saw odd atime regressions with 2.6.33 where there were a full second worth of nanoseconds in the nanoseconds field. He also reviewed the time code and narrowed down the problem: unhandled overflow of the nanosecond field caused by rounding up the sub-nanosecond accumulated time. Details: * At the end of update_wall_time(), we currently round up the sub-nanosecond portion of accumulated time when storing it into xtime. This was added to avoid time inconsistencies caused when the sub-nanosecond portion was truncated when storing into xtime. Unfortunately we don't handle the possible second overflow caused by that rounding. * Previously the xtime_cache code hid this overflow by normalizing the xtime value when storing into the xtime_cache. * We could try to handle the second overflow after the rounding up, but since this affects the timekeeping's internal state, this would further complicate the next accumulation cycle, causing small errors in ntp steering. As much as I'd like to get rid of it, the xtime_cache code is known to work. * The correct fix is really to include the sub-nanosecond portion in the timekeeping accessor function, so we don't need to round up at during accumulation. This would greatly simplify the accumulation code. Unfortunately, we can't do this safely until the last three non-GENERIC_TIME arches (sparc32, arm, cris) are converted (those patches are in -mm) and we kill off the spots where arches set xtime directly. This is all 2.6.34 material, so I think reverting the xtime_cache change is the best approach for now. Many thanks to Petr for both reporting and finding the issue!" Reported-by: Petr Titěra <P.Titera@century.cz> Requested-by: john stultz <johnstul@us.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-23 06:10:37 +08:00
now = tk_xtime(tk);
} while (read_seqcount_retry(&timekeeper_seq, seq));
return timespec64_to_timespec(now);
}
EXPORT_SYMBOL(current_kernel_time);
struct timespec get_monotonic_coarse(void)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 now, mono;
unsigned long seq;
do {
seq = read_seqcount_begin(&timekeeper_seq);
Revert "time: Remove xtime_cache" This reverts commit 7bc7d637452383d56ba4368d4336b0dde1bb476d, as requested by John Stultz. Quoting John: "Petr Titěra reported an issue where he saw odd atime regressions with 2.6.33 where there were a full second worth of nanoseconds in the nanoseconds field. He also reviewed the time code and narrowed down the problem: unhandled overflow of the nanosecond field caused by rounding up the sub-nanosecond accumulated time. Details: * At the end of update_wall_time(), we currently round up the sub-nanosecond portion of accumulated time when storing it into xtime. This was added to avoid time inconsistencies caused when the sub-nanosecond portion was truncated when storing into xtime. Unfortunately we don't handle the possible second overflow caused by that rounding. * Previously the xtime_cache code hid this overflow by normalizing the xtime value when storing into the xtime_cache. * We could try to handle the second overflow after the rounding up, but since this affects the timekeeping's internal state, this would further complicate the next accumulation cycle, causing small errors in ntp steering. As much as I'd like to get rid of it, the xtime_cache code is known to work. * The correct fix is really to include the sub-nanosecond portion in the timekeeping accessor function, so we don't need to round up at during accumulation. This would greatly simplify the accumulation code. Unfortunately, we can't do this safely until the last three non-GENERIC_TIME arches (sparc32, arm, cris) are converted (those patches are in -mm) and we kill off the spots where arches set xtime directly. This is all 2.6.34 material, so I think reverting the xtime_cache change is the best approach for now. Many thanks to Petr for both reporting and finding the issue!" Reported-by: Petr Titěra <P.Titera@century.cz> Requested-by: john stultz <johnstul@us.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-12-23 06:10:37 +08:00
now = tk_xtime(tk);
mono = tk->wall_to_monotonic;
} while (read_seqcount_retry(&timekeeper_seq, seq));
set_normalized_timespec64(&now, now.tv_sec + mono.tv_sec,
now.tv_nsec + mono.tv_nsec);
return timespec64_to_timespec(now);
}
/*
* Must hold jiffies_lock
*/
void do_timer(unsigned long ticks)
{
jiffies_64 += ticks;
calc_global_load(ticks);
}
/**
* ktime_get_update_offsets_tick - hrtimer helper
* @offs_real: pointer to storage for monotonic -> realtime offset
* @offs_boot: pointer to storage for monotonic -> boottime offset
* @offs_tai: pointer to storage for monotonic -> clock tai offset
*
* Returns monotonic time at last tick and various offsets
*/
ktime_t ktime_get_update_offsets_tick(ktime_t *offs_real, ktime_t *offs_boot,
ktime_t *offs_tai)
{
struct timekeeper *tk = &timekeeper;
struct timespec64 ts;
ktime_t now;
unsigned int seq;
do {
seq = read_seqcount_begin(&timekeeper_seq);
ts = tk_xtime(tk);
*offs_real = tk->offs_real;
*offs_boot = tk->offs_boot;
*offs_tai = tk->offs_tai;
} while (read_seqcount_retry(&timekeeper_seq, seq));
now = ktime_set(ts.tv_sec, ts.tv_nsec);
now = ktime_sub(now, *offs_real);
return now;
}
#ifdef CONFIG_HIGH_RES_TIMERS
/**
* ktime_get_update_offsets_now - hrtimer helper
* @offs_real: pointer to storage for monotonic -> realtime offset
* @offs_boot: pointer to storage for monotonic -> boottime offset
* @offs_tai: pointer to storage for monotonic -> clock tai offset
*
* Returns current monotonic time and updates the offsets
* Called from hrtimer_interrupt() or retrigger_next_event()
*/
ktime_t ktime_get_update_offsets_now(ktime_t *offs_real, ktime_t *offs_boot,
ktime_t *offs_tai)
{
struct timekeeper *tk = &timekeeper;
ktime_t now;
unsigned int seq;
u64 secs, nsecs;
do {
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;
*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);
return now;
}
#endif
2011-04-27 20:16:42 +08:00
/**
* ktime_get_monotonic_offset() - get wall_to_monotonic in ktime_t format
*/
ktime_t ktime_get_monotonic_offset(void)
{
struct timekeeper *tk = &timekeeper;
2011-04-27 20:16:42 +08:00
unsigned long seq;
struct timespec64 wtom;
2011-04-27 20:16:42 +08:00
do {
seq = read_seqcount_begin(&timekeeper_seq);
wtom = tk->wall_to_monotonic;
} while (read_seqcount_retry(&timekeeper_seq, seq));
return timespec64_to_ktime(wtom);
2011-04-27 20:16:42 +08:00
}
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 timespec64 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;
}
getnstimeofday64(&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);
timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
}
write_seqcount_end(&timekeeper_seq);
raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
timekeeping: Avoid possible deadlock from clock_was_set_delayed As part of normal operaions, the hrtimer subsystem frequently calls into the timekeeping code, creating a locking order of hrtimer locks -> timekeeping locks clock_was_set_delayed() was suppoed to allow us to avoid deadlocks between the timekeeping the hrtimer subsystem, so that we could notify the hrtimer subsytem the time had changed while holding the timekeeping locks. This was done by scheduling delayed work that would run later once we were out of the timekeeing code. But unfortunately the lock chains are complex enoguh that in scheduling delayed work, we end up eventually trying to grab an hrtimer lock. Sasha Levin noticed this in testing when the new seqlock lockdep enablement triggered the following (somewhat abrieviated) message: [ 251.100221] ====================================================== [ 251.100221] [ INFO: possible circular locking dependency detected ] [ 251.100221] 3.13.0-rc2-next-20131206-sasha-00005-g8be2375-dirty #4053 Not tainted [ 251.101967] ------------------------------------------------------- [ 251.101967] kworker/10:1/4506 is trying to acquire lock: [ 251.101967] (timekeeper_seq){----..}, at: [<ffffffff81160e96>] retrigger_next_event+0x56/0x70 [ 251.101967] [ 251.101967] but task is already holding lock: [ 251.101967] (hrtimer_bases.lock#11){-.-...}, at: [<ffffffff81160e7c>] retrigger_next_event+0x3c/0x70 [ 251.101967] [ 251.101967] which lock already depends on the new lock. [ 251.101967] [ 251.101967] [ 251.101967] the existing dependency chain (in reverse order) is: [ 251.101967] -> #5 (hrtimer_bases.lock#11){-.-...}: [snipped] -> #4 (&rt_b->rt_runtime_lock){-.-...}: [snipped] -> #3 (&rq->lock){-.-.-.}: [snipped] -> #2 (&p->pi_lock){-.-.-.}: [snipped] -> #1 (&(&pool->lock)->rlock){-.-...}: [ 251.101967] [<ffffffff81194803>] validate_chain+0x6c3/0x7b0 [ 251.101967] [<ffffffff81194d9d>] __lock_acquire+0x4ad/0x580 [ 251.101967] [<ffffffff81194ff2>] lock_acquire+0x182/0x1d0 [ 251.101967] [<ffffffff84398500>] _raw_spin_lock+0x40/0x80 [ 251.101967] [<ffffffff81153e69>] __queue_work+0x1a9/0x3f0 [ 251.101967] [<ffffffff81154168>] queue_work_on+0x98/0x120 [ 251.101967] [<ffffffff81161351>] clock_was_set_delayed+0x21/0x30 [ 251.101967] [<ffffffff811c4bd1>] do_adjtimex+0x111/0x160 [ 251.101967] [<ffffffff811e2711>] compat_sys_adjtimex+0x41/0x70 [ 251.101967] [<ffffffff843a4b49>] ia32_sysret+0x0/0x5 [ 251.101967] -> #0 (timekeeper_seq){----..}: [snipped] [ 251.101967] other info that might help us debug this: [ 251.101967] [ 251.101967] Chain exists of: timekeeper_seq --> &rt_b->rt_runtime_lock --> hrtimer_bases.lock#11 [ 251.101967] Possible unsafe locking scenario: [ 251.101967] [ 251.101967] CPU0 CPU1 [ 251.101967] ---- ---- [ 251.101967] lock(hrtimer_bases.lock#11); [ 251.101967] lock(&rt_b->rt_runtime_lock); [ 251.101967] lock(hrtimer_bases.lock#11); [ 251.101967] lock(timekeeper_seq); [ 251.101967] [ 251.101967] *** DEADLOCK *** [ 251.101967] [ 251.101967] 3 locks held by kworker/10:1/4506: [ 251.101967] #0: (events){.+.+.+}, at: [<ffffffff81154960>] process_one_work+0x200/0x530 [ 251.101967] #1: (hrtimer_work){+.+...}, at: [<ffffffff81154960>] process_one_work+0x200/0x530 [ 251.101967] #2: (hrtimer_bases.lock#11){-.-...}, at: [<ffffffff81160e7c>] retrigger_next_event+0x3c/0x70 [ 251.101967] [ 251.101967] stack backtrace: [ 251.101967] CPU: 10 PID: 4506 Comm: kworker/10:1 Not tainted 3.13.0-rc2-next-20131206-sasha-00005-g8be2375-dirty #4053 [ 251.101967] Workqueue: events clock_was_set_work So the best solution is to avoid calling clock_was_set_delayed() while holding the timekeeping lock, and instead using a flag variable to decide if we should call clock_was_set() once we've released the locks. This works for the case here, where the do_adjtimex() was the deadlock trigger point. Unfortuantely, in update_wall_time() we still hold the jiffies lock, which would deadlock with the ipi triggered by clock_was_set(), preventing us from calling it even after we drop the timekeeping lock. So instead call clock_was_set_delayed() at that point. Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Sasha Levin <sasha.levin@oracle.com> Cc: stable <stable@vger.kernel.org> #3.10+ Reported-by: Sasha Levin <sasha.levin@oracle.com> Tested-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: John Stultz <john.stultz@linaro.org>
2013-12-11 09:18:18 +08:00
if (tai != orig_tai)
clock_was_set();
timekeeping: Fix HRTICK related deadlock from ntp lock changes Gerlando Falauto reported that when HRTICK is enabled, it is possible to trigger system deadlocks. These were hard to reproduce, as HRTICK has been broken in the past, but seemed to be connected to the timekeeping_seq lock. Since seqlock/seqcount's aren't supported w/ lockdep, I added some extra spinlock based locking and triggered the following lockdep output: [ 15.849182] ntpd/4062 is trying to acquire lock: [ 15.849765] (&(&pool->lock)->rlock){..-...}, at: [<ffffffff810aa9b5>] __queue_work+0x145/0x480 [ 15.850051] [ 15.850051] but task is already holding lock: [ 15.850051] (timekeeper_lock){-.-.-.}, at: [<ffffffff810df6df>] do_adjtimex+0x7f/0x100 <snip> [ 15.850051] Chain exists of: &(&pool->lock)->rlock --> &p->pi_lock --> timekeeper_lock [ 15.850051] Possible unsafe locking scenario: [ 15.850051] [ 15.850051] CPU0 CPU1 [ 15.850051] ---- ---- [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&p->pi_lock); [ 15.850051] lock(timekeeper_lock); [ 15.850051] lock(&(&pool->lock)->rlock); [ 15.850051] [ 15.850051] *** DEADLOCK *** The deadlock was introduced by 06c017fdd4dc48451a ("timekeeping: Hold timekeepering locks in do_adjtimex and hardpps") in 3.10 This patch avoids this deadlock, by moving the call to schedule_delayed_work() outside of the timekeeper lock critical section. Reported-by: Gerlando Falauto <gerlando.falauto@keymile.com> Tested-by: Lin Ming <minggr@gmail.com> Signed-off-by: John Stultz <john.stultz@linaro.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: stable <stable@vger.kernel.org> #3.11, 3.10 Link: http://lkml.kernel.org/r/1378943457-27314-1-git-send-email-john.stultz@linaro.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
2013-09-12 07:50:56 +08:00
ntp_notify_cmos_timer();
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.
*
* Must be called with interrupts disabled.
*/
void xtime_update(unsigned long ticks)
{
write_seqlock(&jiffies_lock);
do_timer(ticks);
write_sequnlock(&jiffies_lock);
update_wall_time();
}