Lei Chen raised an issue with CLOCK_MONOTONIC_COARSE seeing time inconsistencies.
Lei tracked down that this was being caused by the adjustment tk->tkr_mono.xtime_nsec -= offset;
which is made to compensate for the unaccumulated cycles in offset when the mult value is adjusted forward, so that the non-_COARSE clockids don't see inconsistencies.
However, the _COARSE clockids don't use the mult*offset value in their calculations, so this subtraction can cause the _COARSE clock ids to jump back a bit.
Now, by design, this negative adjustment should be fine, because the logic run from timekeeping_adjust() is done after we accumulate approx mult*interval_cycles into xtime_nsec. The accumulated (mult*interval_cycles) will be larger then the (mult_adj*offset) value subtracted from xtime_nsec, and both operations are done together under the tk_core.lock, so the net change to xtime_nsec should always be positive.
However, do_adjtimex() calls into timekeeping_advance() as well, since we want to apply the ntp freq adjustment immediately. In this case, we don't return early when the offset is smaller then interval_cycles, so we don't end up accumulating any time into xtime_nsec. But we do go on to call timekeeping_adjust(), which modifies the mult value, and subtracts from xtime_nsec to correct for the new mult value.
Here because we did not accumulate anything, we have a window where the _COARSE clockids that don't utilize the mult*offset value, can see an inconsistency.
So to fix this, rework the timekeeping_advance() logic a bit so that when we are called from do_adjtimex(), we call timekeeping_forward(), to first accumulate the sub-interval time into xtime_nsec. Then with no unaccumulated cycles in offset, we can do the mult adjustment without worry of the subtraction having an impact.
Cc: Thomas Gleixner tglx@linutronix.de Cc: Stephen Boyd sboyd@kernel.org Cc: Anna-Maria Behnsen anna-maria@linutronix.de Cc: Frederic Weisbecker frederic@kernel.org Cc: Shuah Khan shuah@kernel.org Cc: Miroslav Lichvar mlichvar@redhat.com Cc: linux-kselftest@vger.kernel.org Cc: kernel-team@android.com Cc: Lei Chen lei.chen@smartx.com Fixes: da15cfdae033 ("time: Introduce CLOCK_REALTIME_COARSE") Reported-by: Lei Chen lei.chen@smartx.com Closes: https://lore.kernel.org/lkml/20250310030004.3705801-1-lei.chen@smartx.com/ Diagnosed-by: Thomas Gleixner tglx@linutronix.de Additional-fixes-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: John Stultz jstultz@google.com --- v2: Include fixes from Thomas, dropping the unnecessary clock_set setting, and instead clearing ntp_error, along with some other minor tweaks. --- kernel/time/timekeeping.c | 94 ++++++++++++++++++++++++++++----------- 1 file changed, 69 insertions(+), 25 deletions(-)
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 1e67d076f1955..929846b8b45ab 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -682,20 +682,19 @@ static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int act }
/** - * timekeeping_forward_now - update clock to the current time + * timekeeping_forward - update clock to given cycle now value * @tk: Pointer to the timekeeper to update + * @cycle_now: Current clocksource read value * * 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) +static void timekeeping_forward(struct timekeeper *tk, u64 cycle_now) { - u64 cycle_now, delta; + u64 delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, + tk->tkr_mono.clock->max_raw_delta);
- cycle_now = tk_clock_read(&tk->tkr_mono); - delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask, - tk->tkr_mono.clock->max_raw_delta); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now;
@@ -710,6 +709,21 @@ static void timekeeping_forward_now(struct timekeeper *tk) } }
+/** + * timekeeping_forward_now - update clock to the current time + * @tk: Pointer to the timekeeper to update + * + * 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) +{ + u64 cycle_now = tk_clock_read(&tk->tkr_mono); + + timekeeping_forward(tk, cycle_now); +} + /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set @@ -2151,6 +2165,54 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, return offset; }
+static u64 timekeeping_accumulate(struct timekeeper *tk, u64 offset, + enum timekeeping_adv_mode mode, + unsigned int *clock_set) +{ + int shift = 0, maxshift; + + /* + * TK_ADV_FREQ indicates that adjtimex(2) directly set the + * frequency or the tick length. + * + * Accumulate the offset, so that the new multiplier starts from + * now. This is required as otherwise for offsets, which are + * smaller than tk::cycle_interval, timekeeping_adjust() could set + * xtime_nsec backwards, which subsequently causes time going + * backwards in the coarse time getters. But even for the case + * where offset is greater than tk::cycle_interval the periodic + * accumulation does not have much value. + * + * Also reset tk::ntp_error as it does not make sense to keep the + * old accumulated error around in this case. + */ + if (mode == TK_ADV_FREQ) { + timekeeping_forward(tk, tk->tkr_mono.cycle_last + offset); + tk->ntp_error = 0; + return 0; + } + + /* + * 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 + * chunk in one go, and then try to consume the next smaller + * doubled multiple. + */ + shift = ilog2(offset) - ilog2(tk->cycle_interval); + shift = max(0, shift); + /* Bound shift to one less than what overflows tick_length */ + maxshift = (64 - (ilog2(ntp_tick_length()) + 1)) - 1; + shift = min(shift, maxshift); + while (offset >= tk->cycle_interval) { + offset = logarithmic_accumulation(tk, offset, shift, clock_set); + if (offset < tk->cycle_interval << shift) + shift--; + } + return offset; +} + /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length @@ -2160,7 +2222,6 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) struct timekeeper *tk = &tk_core.shadow_timekeeper; struct timekeeper *real_tk = &tk_core.timekeeper; unsigned int clock_set = 0; - int shift = 0, maxshift; u64 offset;
guard(raw_spinlock_irqsave)(&tk_core.lock); @@ -2177,24 +2238,7 @@ static bool timekeeping_advance(enum timekeeping_adv_mode mode) if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) return false;
- /* - * 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 - * chunk in one go, and then try to consume the next smaller - * doubled multiple. - */ - shift = ilog2(offset) - ilog2(tk->cycle_interval); - shift = max(0, shift); - /* Bound shift to one less than what overflows tick_length */ - maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; - shift = min(shift, maxshift); - while (offset >= tk->cycle_interval) { - offset = logarithmic_accumulation(tk, offset, shift, &clock_set); - if (offset < tk->cycle_interval<<shift) - shift--; - } + offset = timekeeping_accumulate(tk, offset, mode, &clock_set);
/* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset);