BACKPORT: time: Fix CLOCK_MONOTONIC_RAW sub-nanosecond accounting

(cherry pick from commit 3d88d56)

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 <[email protected]>
Tested-by: Daniel Mentz <[email protected]>
Cc: Prarit Bhargava <[email protected]>
Cc: Kevin Brodsky <[email protected]>
Cc: Richard Cochran <[email protected]>
Cc: Stephen Boyd <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: "stable #4 . 8+" <[email protected]>
Cc: Miroslav Lichvar <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: Thomas Gleixner <[email protected]>
Bug: 20045882
Bug: 63737556
Change-Id: I6c55dd7685f6bd212c6af9d09c527528e1dd5fa1

include/linux/timekeeper_internal.h

@@ -56,7 +56,7 @@ struct tk_read_base {
  *			interval.
  * @xtime_remainder:	Shifted nano seconds left over when rounding
  *			@cycle_interval
- * @raw_interval:	Raw nano seconds accumulated per NTP 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
@@ -97,7 +97,7 @@ struct timekeeper {
 	cycle_t			cycle_interval;
 	u64			xtime_interval;
 	s64			xtime_remainder;
-	u32			raw_interval;
+	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

kernel/time/timekeeping.c

@@ -277,8 +277,7 @@ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock)
 	/* Go back from cycles -> shifted ns */
 	tk->xtime_interval = (u64) interval * clock->mult;
 	tk->xtime_remainder = ntpinterval - tk->xtime_interval;
-	tk->raw_interval =
-		((u64) interval * clock->mult) >> clock->shift;
+	tk->raw_interval = interval * clock->mult;
 
 	 /* if changing clocks, convert xtime_nsec shift units */
 	if (old_clock) {
@@ -1796,7 +1795,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 						unsigned int *clock_set)
 {
 	cycle_t interval = tk->cycle_interval << shift;
-	u64 raw_nsecs;
+	u64 snsec_per_sec;
 
 	/* If the offset is smaller than a shifted interval, do nothing */
 	if (offset < interval)
@@ -1811,14 +1810,15 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
-	raw_nsecs = (u64)tk->raw_interval << shift;
-	raw_nsecs += tk->raw_time.tv_nsec;
-	if (raw_nsecs >= NSEC_PER_SEC) {
-		u64 raw_secs = raw_nsecs;
-		raw_nsecs = do_div(raw_secs, NSEC_PER_SEC);
-		tk->raw_time.tv_sec += raw_secs;
+	tk->tkr_raw.xtime_nsec += (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift;
+	tk->tkr_raw.xtime_nsec += tk->raw_interval << shift;
+	snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift;
+	while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) {
+		tk->tkr_raw.xtime_nsec -= snsec_per_sec;
+		tk->raw_time.tv_sec++;
 	}
-	tk->raw_time.tv_nsec = raw_nsecs;
+	tk->raw_time.tv_nsec = tk->tkr_raw.xtime_nsec >> tk->tkr_raw.shift;
+	tk->tkr_raw.xtime_nsec -= (u64)tk->raw_time.tv_nsec << tk->tkr_raw.shift;
 
 	/* Accumulate error between NTP and clock interval */
 	tk->ntp_error += tk->ntp_tick << shift;