[PATCH 4.4 88/92] time: Fix CLOCK_MONOTONIC_RAW sub-nanosecond accounting

[Greg Kroah-Hartman]

4.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: John Stultz <john.stultz@xxxxxxxxxx>

commit 3d88d56c5873f6eebe23e05c3da701960146b801 upstream.

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 <john.stultz@xxxxxxxxxx>
Tested-by: Daniel Mentz <danielmentz@xxxxxxxxxx>
Cc: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: Kevin Brodsky <kevin.brodsky@xxxxxxx>
Cc: Richard Cochran <richardcochran@xxxxxxxxx>
Cc: Stephen Boyd <stephen.boyd@xxxxxxxxxx>
Cc: Will Deacon <will.deacon@xxxxxxx>
Cc: "stable #4 . 8+" <stable@xxxxxxxxxxxxxxx>
Cc: Miroslav Lichvar <mlichvar@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/1496965462-20003-3-git-send-email-john.stultz@xxxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
[fabrizio: cherry-pick to 4.4. Kept cycle_t type for function
logarithmic_accumulation local variable "interval". Dropped
casting of "interval" variable]
Signed-off-by: Fabrizio Castro <fabrizio.castro@xxxxxxxxxxxxxx>
Signed-off-by: Biju Das <biju.das@xxxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>

---
 include/linux/timekeeper_internal.h |    4 ++--
 kernel/time/timekeeping.c           |   20 ++++++++++----------
 2 files changed, 12 insertions(+), 12 deletions(-)

--- a/include/linux/timekeeper_internal.h
+++ b/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
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -277,8 +277,7 @@ static void tk_setup_internals(struct ti
 	/* 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) {
@@ -1767,7 +1766,7 @@ static cycle_t logarithmic_accumulation(
 						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)
@@ -1782,14 +1781,15 @@ static cycle_t logarithmic_accumulation(
 	*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;