linux_old1/kernel/time/ntp.c

521 lines
12 KiB
C
Raw Normal View History

/*
* NTP state machine interfaces and logic.
*
* This code was mainly moved from kernel/timer.c and kernel/time.c
* Please see those files for relevant copyright info and historical
* changelogs.
*/
#include <linux/capability.h>
#include <linux/clocksource.h>
#include <linux/workqueue.h>
#include <linux/hrtimer.h>
#include <linux/jiffies.h>
#include <linux/math64.h>
#include <linux/timex.h>
#include <linux/time.h>
#include <linux/mm.h>
/*
* NTP timekeeping variables:
*/
/* USER_HZ period (usecs): */
unsigned long tick_usec = TICK_USEC;
/* ACTHZ period (nsecs): */
unsigned long tick_nsec;
u64 tick_length;
static u64 tick_length_base;
static struct hrtimer leap_timer;
#define MAX_TICKADJ 500LL /* usecs */
#define MAX_TICKADJ_SCALED \
(((MAX_TICKADJ * NSEC_PER_USEC) << NTP_SCALE_SHIFT) / NTP_INTERVAL_FREQ)
/*
* phase-lock loop variables
*/
/*
* clock synchronization status
*
* (TIME_ERROR prevents overwriting the CMOS clock)
*/
static int time_state = TIME_OK;
/* clock status bits: */
int time_status = STA_UNSYNC;
/* TAI offset (secs): */
static long time_tai;
/* time adjustment (nsecs): */
static s64 time_offset;
/* pll time constant: */
static long time_constant = 2;
/* maximum error (usecs): */
long time_maxerror = NTP_PHASE_LIMIT;
/* estimated error (usecs): */
long time_esterror = NTP_PHASE_LIMIT;
/* frequency offset (scaled nsecs/secs): */
static s64 time_freq;
/* time at last adjustment (secs): */
static long time_reftime;
long time_adjust;
static long ntp_tick_adj;
/*
* NTP methods:
*/
/*
* Update (tick_length, tick_length_base, tick_nsec), based
* on (tick_usec, ntp_tick_adj, time_freq):
*/
static void ntp_update_frequency(void)
{
u64 second_length;
u64 new_base;
second_length = (u64)(tick_usec * NSEC_PER_USEC * USER_HZ)
<< NTP_SCALE_SHIFT;
second_length += (s64)ntp_tick_adj << NTP_SCALE_SHIFT;
second_length += time_freq;
tick_nsec = div_u64(second_length, HZ) >> NTP_SCALE_SHIFT;
new_base = div_u64(second_length, NTP_INTERVAL_FREQ);
/*
* Don't wait for the next second_overflow, apply
* the change to the tick length immediately:
*/
tick_length += new_base - tick_length_base;
tick_length_base = new_base;
}
static inline s64 ntp_update_offset_fll(s64 freq_adj, s64 offset64, long secs)
{
time_status &= ~STA_MODE;
if (secs < MINSEC)
return freq_adj;
if (!(time_status & STA_FLL) && (secs <= MAXSEC))
return freq_adj;
freq_adj += div_s64(offset64 << (NTP_SCALE_SHIFT - SHIFT_FLL), secs);
time_status |= STA_MODE;
return freq_adj;
}
static void ntp_update_offset(long offset)
{
s64 freq_adj;
s64 offset64;
long secs;
if (!(time_status & STA_PLL))
return;
if (!(time_status & STA_NANO))
offset *= NSEC_PER_USEC;
/*
* Scale the phase adjustment and
* clamp to the operating range.
*/
offset = min(offset, MAXPHASE);
offset = max(offset, -MAXPHASE);
/*
* Select how the frequency is to be controlled
* and in which mode (PLL or FLL).
*/
if (time_status & STA_FREQHOLD || time_reftime == 0)
time_reftime = xtime.tv_sec;
secs = xtime.tv_sec - time_reftime;
time_reftime = xtime.tv_sec;
offset64 = offset;
freq_adj = (offset64 * secs) <<
(NTP_SCALE_SHIFT - 2 * (SHIFT_PLL + 2 + time_constant));
freq_adj = ntp_update_offset_fll(freq_adj, offset64, secs);
freq_adj = min(freq_adj + time_freq, MAXFREQ_SCALED);
time_freq = max(freq_adj, -MAXFREQ_SCALED);
time_offset = div_s64(offset64 << NTP_SCALE_SHIFT, NTP_INTERVAL_FREQ);
}
/**
* ntp_clear - Clears the NTP state variables
*
* Must be called while holding a write on the xtime_lock
*/
void ntp_clear(void)
{
time_adjust = 0; /* stop active adjtime() */
time_status |= STA_UNSYNC;
time_maxerror = NTP_PHASE_LIMIT;
time_esterror = NTP_PHASE_LIMIT;
ntp_update_frequency();
tick_length = tick_length_base;
time_offset = 0;
}
/*
* Leap second processing. If in leap-insert state at the end of the
* day, the system clock is set back one second; if in leap-delete
* state, the system clock is set ahead one second.
*/
static enum hrtimer_restart ntp_leap_second(struct hrtimer *timer)
{
enum hrtimer_restart res = HRTIMER_NORESTART;
write_seqlock(&xtime_lock);
switch (time_state) {
case TIME_OK:
break;
case TIME_INS:
xtime.tv_sec--;
wall_to_monotonic.tv_sec++;
time_state = TIME_OOP;
printk(KERN_NOTICE
"Clock: inserting leap second 23:59:60 UTC\n");
hrtimer_add_expires_ns(&leap_timer, NSEC_PER_SEC);
res = HRTIMER_RESTART;
break;
case TIME_DEL:
xtime.tv_sec++;
time_tai--;
wall_to_monotonic.tv_sec--;
time_state = TIME_WAIT;
printk(KERN_NOTICE
"Clock: deleting leap second 23:59:59 UTC\n");
break;
case TIME_OOP:
time_tai++;
time_state = TIME_WAIT;
/* fall through */
case TIME_WAIT:
if (!(time_status & (STA_INS | STA_DEL)))
time_state = TIME_OK;
break;
}
update_vsyscall(&xtime, clock);
write_sequnlock(&xtime_lock);
return res;
}
/*
* this routine handles the overflow of the microsecond field
*
* The tricky bits of code to handle the accurate clock support
* were provided by Dave Mills (Mills@UDEL.EDU) of NTP fame.
* They were originally developed for SUN and DEC kernels.
* All the kudos should go to Dave for this stuff.
*/
void second_overflow(void)
{
s64 time_adj;
/* Bump the maxerror field */
time_maxerror += MAXFREQ / NSEC_PER_USEC;
if (time_maxerror > NTP_PHASE_LIMIT) {
time_maxerror = NTP_PHASE_LIMIT;
time_status |= STA_UNSYNC;
}
/*
* Compute the phase adjustment for the next second. The offset is
* reduced by a fixed factor times the time constant.
*/
tick_length = tick_length_base;
time_adj = shift_right(time_offset, SHIFT_PLL + time_constant);
time_offset -= time_adj;
tick_length += time_adj;
if (!time_adjust)
return;
if (time_adjust > MAX_TICKADJ) {
time_adjust -= MAX_TICKADJ;
tick_length += MAX_TICKADJ_SCALED;
return;
}
if (time_adjust < -MAX_TICKADJ) {
time_adjust += MAX_TICKADJ;
tick_length -= MAX_TICKADJ_SCALED;
return;
}
tick_length += (s64)(time_adjust * NSEC_PER_USEC / NTP_INTERVAL_FREQ)
<< NTP_SCALE_SHIFT;
time_adjust = 0;
}
#ifdef CONFIG_GENERIC_CMOS_UPDATE
/* Disable the cmos update - used by virtualization and embedded */
int no_sync_cmos_clock __read_mostly;
static void sync_cmos_clock(struct work_struct *work);
static DECLARE_DELAYED_WORK(sync_cmos_work, sync_cmos_clock);
static void sync_cmos_clock(struct work_struct *work)
{
struct timespec now, next;
int fail = 1;
/*
* If we have an externally synchronized Linux clock, then update
* CMOS clock accordingly every ~11 minutes. Set_rtc_mmss() has to be
* called as close as possible to 500 ms before the new second starts.
* This code is run on a timer. If the clock is set, that timer
* may not expire at the correct time. Thus, we adjust...
*/
if (!ntp_synced()) {
/*
* Not synced, exit, do not restart a timer (if one is
* running, let it run out).
*/
return;
}
getnstimeofday(&now);
if (abs(now.tv_nsec - (NSEC_PER_SEC / 2)) <= tick_nsec / 2)
fail = update_persistent_clock(now);
ntp: fix calculation of the next jiffie to trigger RTC sync We have a bug in the calculation of the next jiffie to trigger the RTC synchronisation. The aim here is to run sync_cmos_clock() as close as possible to the middle of a second. Which means we want this function to be called less than or equal to half a jiffie away from when now.tv_nsec equals 5e8 (500000000). If this is not the case for a given call to the function, for this purpose instead of updating the RTC we calculate the offset in nanoseconds to the next point in time where now.tv_nsec will be equal 5e8. The calculated offset is then converted to jiffies as these are the unit used by the timer. Hovewer timespec_to_jiffies() used here uses a ceil()-type rounding mode, where the resulting value is rounded up. As a result the range of now.tv_nsec when the timer will trigger is from 5e8 to 5e8 + TICK_NSEC rather than the desired 5e8 - TICK_NSEC / 2 to 5e8 + TICK_NSEC / 2. As a result if for example sync_cmos_clock() happens to be called at the time when now.tv_nsec is between 5e8 + TICK_NSEC / 2 and 5e8 to 5e8 + TICK_NSEC, it will simply be rescheduled HZ jiffies later, falling in the same range of now.tv_nsec again. Similarly for cases offsetted by an integer multiple of TICK_NSEC. This change addresses the problem by subtracting TICK_NSEC / 2 from the nanosecond offset to the next point in time where now.tv_nsec will be equal 5e8, effectively shifting the following rounding in timespec_to_jiffies() so that it produces a rounded-to-nearest result. Signed-off-by: Maciej W. Rozycki <macro@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-06 05:05:31 +08:00
next.tv_nsec = (NSEC_PER_SEC / 2) - now.tv_nsec - (TICK_NSEC / 2);
if (next.tv_nsec <= 0)
next.tv_nsec += NSEC_PER_SEC;
if (!fail)
next.tv_sec = 659;
else
next.tv_sec = 0;
if (next.tv_nsec >= NSEC_PER_SEC) {
next.tv_sec++;
next.tv_nsec -= NSEC_PER_SEC;
}
schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
}
static void notify_cmos_timer(void)
{
if (!no_sync_cmos_clock)
schedule_delayed_work(&sync_cmos_work, 0);
}
#else
static inline void notify_cmos_timer(void) { }
#endif
/*
* adjtimex mainly allows reading (and writing, if superuser) of
* kernel time-keeping variables. used by xntpd.
*/
int do_adjtimex(struct timex *txc)
{
struct timespec ts;
int result;
/* Validate the data before disabling interrupts */
if (txc->modes & ADJ_ADJTIME) {
/* singleshot must not be used with any other mode bits */
if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
return -EINVAL;
if (!(txc->modes & ADJ_OFFSET_READONLY) &&
!capable(CAP_SYS_TIME))
return -EPERM;
} else {
/* In order to modify anything, you gotta be super-user! */
if (txc->modes && !capable(CAP_SYS_TIME))
return -EPERM;
/*
* if the quartz is off by more than 10% then
* something is VERY wrong!
*/
if (txc->modes & ADJ_TICK &&
(txc->tick < 900000/USER_HZ ||
txc->tick > 1100000/USER_HZ))
return -EINVAL;
if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
hrtimer_cancel(&leap_timer);
}
getnstimeofday(&ts);
write_seqlock_irq(&xtime_lock);
/* If there are input parameters, then process them */
if (txc->modes & ADJ_ADJTIME) {
long save_adjust = time_adjust;
if (!(txc->modes & ADJ_OFFSET_READONLY)) {
/* adjtime() is independent from ntp_adjtime() */
time_adjust = txc->offset;
ntp_update_frequency();
}
txc->offset = save_adjust;
goto adj_done;
}
if (txc->modes) {
long sec;
if (txc->modes & ADJ_STATUS) {
if ((time_status & STA_PLL) &&
!(txc->status & STA_PLL)) {
time_state = TIME_OK;
time_status = STA_UNSYNC;
}
/* only set allowed bits */
time_status &= STA_RONLY;
time_status |= txc->status & ~STA_RONLY;
switch (time_state) {
case TIME_OK:
start_timer:
sec = ts.tv_sec;
if (time_status & STA_INS) {
time_state = TIME_INS;
sec += 86400 - sec % 86400;
hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS);
} else if (time_status & STA_DEL) {
time_state = TIME_DEL;
sec += 86400 - (sec + 1) % 86400;
hrtimer_start(&leap_timer, ktime_set(sec, 0), HRTIMER_MODE_ABS);
}
break;
case TIME_INS:
case TIME_DEL:
time_state = TIME_OK;
goto start_timer;
break;
case TIME_WAIT:
if (!(time_status & (STA_INS | STA_DEL)))
time_state = TIME_OK;
break;
case TIME_OOP:
hrtimer_restart(&leap_timer);
break;
}
}
if (txc->modes & ADJ_NANO)
time_status |= STA_NANO;
if (txc->modes & ADJ_MICRO)
time_status &= ~STA_NANO;
if (txc->modes & ADJ_FREQUENCY) {
time_freq = (s64)txc->freq * PPM_SCALE;
time_freq = min(time_freq, MAXFREQ_SCALED);
time_freq = max(time_freq, -MAXFREQ_SCALED);
}
if (txc->modes & ADJ_MAXERROR)
time_maxerror = txc->maxerror;
if (txc->modes & ADJ_ESTERROR)
time_esterror = txc->esterror;
if (txc->modes & ADJ_TIMECONST) {
time_constant = txc->constant;
if (!(time_status & STA_NANO))
time_constant += 4;
time_constant = min(time_constant, (long)MAXTC);
time_constant = max(time_constant, 0l);
}
if (txc->modes & ADJ_TAI && txc->constant > 0)
time_tai = txc->constant;
if (txc->modes & ADJ_OFFSET)
ntp_update_offset(txc->offset);
if (txc->modes & ADJ_TICK)
tick_usec = txc->tick;
if (txc->modes & (ADJ_TICK|ADJ_FREQUENCY|ADJ_OFFSET))
ntp_update_frequency();
}
txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
NTP_SCALE_SHIFT);
if (!(time_status & STA_NANO))
txc->offset /= NSEC_PER_USEC;
adj_done:
result = time_state; /* mostly `TIME_OK' */
if (time_status & (STA_UNSYNC|STA_CLOCKERR))
result = TIME_ERROR;
txc->freq = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) *
(s64)PPM_SCALE_INV, NTP_SCALE_SHIFT);
txc->maxerror = time_maxerror;
txc->esterror = time_esterror;
txc->status = time_status;
txc->constant = time_constant;
txc->precision = 1;
txc->tolerance = MAXFREQ_SCALED / PPM_SCALE;
txc->tick = tick_usec;
txc->tai = time_tai;
/* PPS is not implemented, so these are zero */
txc->ppsfreq = 0;
txc->jitter = 0;
txc->shift = 0;
txc->stabil = 0;
txc->jitcnt = 0;
txc->calcnt = 0;
txc->errcnt = 0;
txc->stbcnt = 0;
write_sequnlock_irq(&xtime_lock);
txc->time.tv_sec = ts.tv_sec;
txc->time.tv_usec = ts.tv_nsec;
if (!(time_status & STA_NANO))
txc->time.tv_usec /= NSEC_PER_USEC;
notify_cmos_timer();
return result;
}
time: remove obsolete CLOCK_TICK_ADJUST The first version of the ntp_interval/tick_length inconsistent usage patch was recently merged as bbe4d18ac2e058c56adb0cd71f49d9ed3216a405 http://git.kernel.org/gitweb.cgi?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=bbe4d18ac2e058c56adb0cd71f49d9ed3216a405 While the fix did greatly improve the situation, it was correctly pointed out by Roman that it does have a small bug: If the users change clocksources after the system has been running and NTP has made corrections, the correctoins made against the old clocksource will be applied against the new clocksource, causing error. The second attempt, which corrects the issue in the NTP_INTERVAL_LENGTH definition has also made it up-stream as commit e13a2e61dd5152f5499d2003470acf9c838eab84 http://git.kernel.org/gitweb.cgi?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=e13a2e61dd5152f5499d2003470acf9c838eab84 Roman has correctly pointed out that CLOCK_TICK_ADJUST is calculated based on the PIT's frequency, and isn't really relevant to non-PIT driven clocksources (that is, clocksources other then jiffies and pit). This patch reverts both of those changes, and simply removes CLOCK_TICK_ADJUST. This does remove the granularity error correction for users of PIT and Jiffies clocksource users, but the granularity error but for the majority of users, it should be within the 500ppm range NTP can accommodate for. For systems that have granularity errors greater then 500ppm, the "ntp_tick_adj=" boot option can be used to compensate. [johnstul@us.ibm.com: provided changelog] [mattilinnanvuori@yahoo.com: maek ntp_tick_adj static] Signed-off-by: Roman Zippel <zippel@linux-m68k.org> Acked-by: john stultz <johnstul@us.ibm.com> Signed-off-by: Matti Linnanvuori <mattilinnanvuori@yahoo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Cc: mingo@elte.hu Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-03-05 07:14:26 +08:00
static int __init ntp_tick_adj_setup(char *str)
{
ntp_tick_adj = simple_strtol(str, NULL, 0);
return 1;
}
__setup("ntp_tick_adj=", ntp_tick_adj_setup);
void __init ntp_init(void)
{
ntp_clear();
hrtimer_init(&leap_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
leap_timer.function = ntp_leap_second;
}