commit 3d88d56c5873f6eebe23e05c3da701960146b801 upstream. Due to how the MONOTONIC_RAW accumulation logic was handled, there is the potential for a 1ns discontinuity when we do accumulations. This small discontinuity has for the most part gone un-noticed, but since ARM64 enabled CLOCK_MONOTONIC_RAW in their vDSO clock_gettime implementation, we've seen failures with the inconsistency-check test in kselftest. This patch addresses the issue by using the same sub-ns accumulation handling that CLOCK_MONOTONIC uses, which avoids the issue for in-kernel users. Since the ARM64 vDSO implementation has its own clock_gettime calculation logic, this patch reduces the frequency of errors, but failures are still seen. The ARM64 vDSO will need to be updated to include the sub-nanosecond xtime_nsec values in its calculation for this issue to be completely fixed. Signed-off-by: John Stultz <john.stultz@linaro.org> Tested-by: Daniel Mentz <danielmentz@google.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Kevin Brodsky <kevin.brodsky@arm.com> Cc: Richard Cochran <richardcochran@gmail.com> Cc: Stephen Boyd <stephen.boyd@linaro.org> Cc: Will Deacon <will.deacon@arm.com> Cc: "stable #4 . 8+" <stable@vger.kernel.org> Cc: Miroslav Lichvar <mlichvar@redhat.com> Link: http://lkml.kernel.org/r/1496965462-20003-3-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de> [fabrizio: cherry-pick to 4.4. Kept cycle_t type for function logarithmic_accumulation local variable "interval". Dropped casting of "interval" variable] Signed-off-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com> Signed-off-by: Biju Das <biju.das@bp.renesas.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
149 lines
5 KiB
C
149 lines
5 KiB
C
/*
|
|
* 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.
|
|
* @read: Read function of @clock
|
|
* @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
|
|
*
|
|
* 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.
|
|
*/
|
|
struct tk_read_base {
|
|
struct clocksource *clock;
|
|
cycle_t mask;
|
|
cycle_t cycle_last;
|
|
u32 mult;
|
|
u32 shift;
|
|
u64 xtime_nsec;
|
|
ktime_t base;
|
|
};
|
|
|
|
/**
|
|
* 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
|
|
* @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;
|
|
ktime_t next_leap_ktime;
|
|
u64 raw_sec;
|
|
|
|
/* The following members are for timekeeping internal use */
|
|
cycle_t 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;
|
|
#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);
|
|
|
|
#elif defined(CONFIG_GENERIC_TIME_VSYSCALL_OLD)
|
|
|
|
extern void update_vsyscall_old(struct timespec *ts, struct timespec *wtm,
|
|
struct clocksource *c, u32 mult,
|
|
cycle_t cycle_last);
|
|
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 */
|