timekeeping: Fix possible inconsistencies in _COARSE clockids

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
multiplicator is adjusted forward, so that the non-_COARSE clockids don't
see inconsistencies.

However, the _COARSE clockid getter functions use the adjusted xtime_nsec
value directly and do not compensate the negative offset via the
clocksource delta multiplied with the new multiplicator. In that case the
caller can observe time going backwards in consecutive calls.

By design, this negative adjustment should be fine, because the logic run
from timekeeping_adjust() is done after it accumulated approximately

     multiplicator * interval_cycles

into xtime_nsec.  The accumulated value is always larger then the

     mult_adj * offset

value, which is subtracted from xtime_nsec. Both operations are done
together under the tk_core.lock, so the net change to xtime_nsec is always
always be positive.

However, do_adjtimex() calls into timekeeping_advance() as well, to to
apply the NTP frequency adjustment immediately. In this case,
timekeeping_advance() does not return early when the offset is smaller then
interval_cycles. In that case there is no time accumulated into
xtime_nsec. But the subsequent call into timekeeping_adjust(), which
modifies the multiplicator, subtracts from xtime_nsec to correct
for the new multiplicator.

Here because there was no accumulation, xtime_nsec becomes smaller than
before, which opens a window up to the next accumulation, where the _COARSE
clockid getters, which don't compensate for the offset, can observe the
inconsistency.

To fix this, rework the timekeeping_advance() logic so that when invoked
from do_adjtimex(), the time is immediately forwarded to accumulate also
the sub-interval portion into xtime. That means the remaining offset
becomes zero and the subsequent multiplier adjustment therefore does not
modify xtime_nsec.

There is another related inconsistency. If xtime is forwarded due to the
instantaneous multiplier adjustment, the NTP error, which was accumulated
with the previous setting, becomes meaningless.

Therefore clear the NTP error as well, after forwarding the clock for the
instantaneous multiplier update.

Fixes: da15cfd ("time: Introduce CLOCK_REALTIME_COARSE")
Reported-by: Lei Chen <[email protected]>
Signed-off-by: John Stultz <[email protected]>
Signed-off-by: Thomas Gleixner <[email protected]>
Link: https://lore.kernel.org/all/[email protected]
Closes: https://lore.kernel.org/lkml/[email protected]/

Author: johnstultz-work

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);