linux-stable/include/linux/timekeeper_internal.h
Miroslav Lichvar 78b98e3c5a timekeeping/ntp: Determine the multiplier directly from NTP tick length
When the length of the NTP tick changes significantly, e.g. when an
NTP/PTP application is correcting the initial offset of the clock, a
large value may accumulate in the NTP error before the multiplier
converges to the correct value. It may then take a very long time (hours
or even days) before the error is corrected. This causes the clock to
have an unstable frequency offset, which has a negative impact on the
stability of synchronization with precise time sources (e.g. NTP/PTP
using hardware timestamping or the PTP KVM clock).

Use division to determine the correct multiplier directly from the NTP
tick length and replace the iterative approach. This removes the last
major source of the NTP error. The only remaining source is now limited
resolution of the multiplier, which is corrected by adding 1 to the
multiplier when the system clock is behind the NTP time.

Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Stephen Boyd <stephen.boyd@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1520620971-9567-3-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2018-03-10 09:12:41 +01:00

151 lines
5.1 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* You SHOULD NOT be including this unless you're vsyscall
* handling code or timekeeping internal code!
*/
#ifndef _LINUX_TIMEKEEPER_INTERNAL_H
#define _LINUX_TIMEKEEPER_INTERNAL_H
#include <linux/clocksource.h>
#include <linux/jiffies.h>
#include <linux/time.h>
/**
* struct tk_read_base - base structure for timekeeping readout
* @clock: Current clocksource used for timekeeping.
* @mask: Bitmask for two's complement subtraction of non 64bit clocks
* @cycle_last: @clock cycle value at last update
* @mult: (NTP adjusted) multiplier for scaled math conversion
* @shift: Shift value for scaled math conversion
* @xtime_nsec: Shifted (fractional) nano seconds offset for readout
* @base: ktime_t (nanoseconds) base time for readout
* @base_real: Nanoseconds base value for clock REALTIME readout
*
* This struct has size 56 byte on 64 bit. Together with a seqcount it
* occupies a single 64byte cache line.
*
* The struct is separate from struct timekeeper as it is also used
* for a fast NMI safe accessors.
*
* @base_real is for the fast NMI safe accessor to allow reading clock
* realtime from any context.
*/
struct tk_read_base {
struct clocksource *clock;
u64 mask;
u64 cycle_last;
u32 mult;
u32 shift;
u64 xtime_nsec;
ktime_t base;
u64 base_real;
};
/**
* struct timekeeper - Structure holding internal timekeeping values.
* @tkr_mono: The readout base structure for CLOCK_MONOTONIC
* @tkr_raw: The readout base structure for CLOCK_MONOTONIC_RAW
* @xtime_sec: Current CLOCK_REALTIME time in seconds
* @ktime_sec: Current CLOCK_MONOTONIC time in seconds
* @wall_to_monotonic: CLOCK_REALTIME to CLOCK_MONOTONIC offset
* @offs_real: Offset clock monotonic -> clock realtime
* @offs_boot: Offset clock monotonic -> clock boottime
* @offs_tai: Offset clock monotonic -> clock tai
* @tai_offset: The current UTC to TAI offset in seconds
* @clock_was_set_seq: The sequence number of clock was set events
* @cs_was_changed_seq: The sequence number of clocksource change events
* @next_leap_ktime: CLOCK_MONOTONIC time value of a pending leap-second
* @raw_sec: CLOCK_MONOTONIC_RAW time in seconds
* @cycle_interval: Number of clock cycles in one NTP interval
* @xtime_interval: Number of clock shifted nano seconds in one NTP
* interval.
* @xtime_remainder: Shifted nano seconds left over when rounding
* @cycle_interval
* @raw_interval: Shifted raw nano seconds accumulated per NTP interval.
* @ntp_error: Difference between accumulated time and NTP time in ntp
* shifted nano seconds.
* @ntp_error_shift: Shift conversion between clock shifted nano seconds and
* ntp shifted nano seconds.
* @last_warning: Warning ratelimiter (DEBUG_TIMEKEEPING)
* @underflow_seen: Underflow warning flag (DEBUG_TIMEKEEPING)
* @overflow_seen: Overflow warning flag (DEBUG_TIMEKEEPING)
*
* Note: For timespec(64) based interfaces wall_to_monotonic is what
* we need to add to xtime (or xtime corrected for sub jiffie times)
* to get to monotonic time. Monotonic is pegged at zero at system
* boot time, so wall_to_monotonic will be negative, however, we will
* ALWAYS keep the tv_nsec part positive so we can use the usual
* normalization.
*
* wall_to_monotonic is moved after resume from suspend for the
* monotonic time not to jump. We need to add total_sleep_time to
* wall_to_monotonic to get the real boot based time offset.
*
* wall_to_monotonic is no longer the boot time, getboottime must be
* used instead.
*/
struct timekeeper {
struct tk_read_base tkr_mono;
struct tk_read_base tkr_raw;
u64 xtime_sec;
unsigned long ktime_sec;
struct timespec64 wall_to_monotonic;
ktime_t offs_real;
ktime_t offs_boot;
ktime_t offs_tai;
s32 tai_offset;
unsigned int clock_was_set_seq;
u8 cs_was_changed_seq;
ktime_t next_leap_ktime;
u64 raw_sec;
/* The following members are for timekeeping internal use */
u64 cycle_interval;
u64 xtime_interval;
s64 xtime_remainder;
u64 raw_interval;
/* The ntp_tick_length() value currently being used.
* This cached copy ensures we consistently apply the tick
* length for an entire tick, as ntp_tick_length may change
* mid-tick, and we don't want to apply that new value to
* the tick in progress.
*/
u64 ntp_tick;
/* Difference between accumulated time and NTP time in ntp
* shifted nano seconds. */
s64 ntp_error;
u32 ntp_error_shift;
u32 ntp_err_mult;
/* Flag used to avoid updating NTP twice with same second */
u32 skip_second_overflow;
#ifdef CONFIG_DEBUG_TIMEKEEPING
long last_warning;
/*
* These simple flag variables are managed
* without locks, which is racy, but they are
* ok since we don't really care about being
* super precise about how many events were
* seen, just that a problem was observed.
*/
int underflow_seen;
int overflow_seen;
#endif
};
#ifdef CONFIG_GENERIC_TIME_VSYSCALL
extern void update_vsyscall(struct timekeeper *tk);
extern void update_vsyscall_tz(void);
#else
static inline void update_vsyscall(struct timekeeper *tk)
{
}
static inline void update_vsyscall_tz(void)
{
}
#endif
#endif /* _LINUX_TIMEKEEPER_INTERNAL_H */