timekeeping: Try to catch clocksource delta underflows

In the case where there is a broken clocksource
where there are multiple actual clocks that
aren't perfectly aligned, we may see small "negative"
deltas when we subtract 'now' from 'cycle_last'.

The values are actually negative with respect to the
clocksource mask value, not necessarily negative
if cast to a s64, but we can check by checking the
delta to see if it is a small (relative to the mask)
negative value (again negative relative to the mask).

If so, we assume we jumped backwards somehow and
instead use zero for our delta.

Signed-off-by: John Stultz <john.stultz@linaro.org>
Cc: Dave Jones <davej@codemonkey.org.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Stephen Boyd <sboyd@codeaurora.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1426133800-29329-7-git-send-email-john.stultz@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/time/timekeeping.c

@@ -148,6 +148,13 @@ static inline cycle_t timekeeping_get_delta(struct tk_read_base *tkr)
 	/* calculate the delta since the last update_wall_time */
 	delta = clocksource_delta(cycle_now, tkr->cycle_last, tkr->mask);
 
+	/*
+	 * Try to catch underflows by checking if we are seeing small
+	 * mask-relative negative values.
+	 */
+	if (unlikely((~delta & tkr->mask) < (tkr->mask >> 3)))
+		delta = 0;
+
 	/* Cap delta value to the max_cycles values to avoid mult overflows */
 	if (unlikely(delta > tkr->clock->max_cycles))
 		delta = tkr->clock->max_cycles;