1 files changed, 77 insertions, 94 deletions
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 3d128825d343..929846b8b45a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -485,91 +485,30 @@ u64 notrace ktime_get_tai_fast_ns(void)
 }
 EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns);
 
-static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono)
+/**
+ * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime.
+ *
+ * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering.
+ */
+u64 ktime_get_real_fast_ns(void)
 {
+	struct tk_fast *tkf = &tk_fast_mono;
 	struct tk_read_base *tkr;
-	u64 basem, baser, delta;
+	u64 baser, delta;
 	unsigned int seq;
 
 	do {
 		seq = raw_read_seqcount_latch(&tkf->seq);
 		tkr = tkf->base + (seq & 0x01);
-		basem = ktime_to_ns(tkr->base);
 		baser = ktime_to_ns(tkr->base_real);
 		delta = timekeeping_get_ns(tkr);
 	} while (raw_read_seqcount_latch_retry(&tkf->seq, seq));
 
-	if (mono)
-		*mono = basem + delta;
 	return baser + delta;
 }
-
-/**
- * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime.
- *
- * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering.
- */
-u64 ktime_get_real_fast_ns(void)
-{
-	return __ktime_get_real_fast(&tk_fast_mono, NULL);
-}
 EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
 
 /**
- * ktime_get_fast_timestamps: - NMI safe timestamps
- * @snapshot:	Pointer to timestamp storage
- *
- * Stores clock monotonic, boottime and realtime timestamps.
- *
- * Boot time is a racy access on 32bit systems if the sleep time injection
- * happens late during resume and not in timekeeping_resume(). That could
- * be avoided by expanding struct tk_read_base with boot offset for 32bit
- * and adding more overhead to the update. As this is a hard to observe
- * once per resume event which can be filtered with reasonable effort using
- * the accurate mono/real timestamps, it's probably not worth the trouble.
- *
- * Aside of that it might be possible on 32 and 64 bit to observe the
- * following when the sleep time injection happens late:
- *
- * CPU 0				CPU 1
- * timekeeping_resume()
- * ktime_get_fast_timestamps()
- *	mono, real = __ktime_get_real_fast()
- *					inject_sleep_time()
- *					   update boot offset
- *	boot = mono + bootoffset;
- *
- * That means that boot time already has the sleep time adjustment, but
- * real time does not. On the next readout both are in sync again.
- *
- * Preventing this for 64bit is not really feasible without destroying the
- * careful cache layout of the timekeeper because the sequence count and
- * struct tk_read_base would then need two cache lines instead of one.
- *
- * Access to the time keeper clock source is disabled across the innermost
- * steps of suspend/resume. The accessors still work, but the timestamps
- * are frozen until time keeping is resumed which happens very early.
- *
- * For regular suspend/resume there is no observable difference vs. sched
- * clock, but it might affect some of the nasty low level debug printks.
- *
- * OTOH, access to sched clock is not guaranteed across suspend/resume on
- * all systems either so it depends on the hardware in use.
- *
- * If that turns out to be a real problem then this could be mitigated by
- * using sched clock in a similar way as during early boot. But it's not as
- * trivial as on early boot because it needs some careful protection
- * against the clock monotonic timestamp jumping backwards on resume.
- */
-void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot)
-{
-	struct timekeeper *tk = &tk_core.timekeeper;
-
-	snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono);
-	snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot));
-}
-
-/**
  * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource.
  * @tk: Timekeeper to snapshot.
  *
@@ -743,20 +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;
 
@@ -772,6 +710,21 @@ 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
  *
@@ -2212,6 +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
@@ -2221,7 +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);
@@ -2238,24 +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);