timekeeping: Fix potential lost pv notification of time change

johnstultz-work · johnstultz-work · commit 5258d3f25c76 · 2013-12-23T11:53:26.000-08:00
In 780427f (Indicate that clock was set in the pvclock gtod notifier), logic was added to pass a CLOCK_WAS_SET notification to the pvclock notifier chain. While that patch added a action flag returned from accumulate_nsecs_to_secs(), it only uses the returned value in one location, and not in the logarithmic accumulation. This means if a leap second triggered during the logarithmic accumulation (which is most likely where it would happen), the notification that the clock was set would not make it to the pv notifiers. This patch extends the logarithmic_accumulation pass down that action flag so proper notification will occur. This patch also changes the varialbe action -> clock_set per Ingo's suggestion. Cc: Sasha Levin <sasha.levin@oracle.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@kernel.org> Cc: David Vrabel <david.vrabel@citrix.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Richard Cochran <richardcochran@gmail.com> Cc: <xen-devel@lists.xen.org> Cc: stable <stable@vger.kernel.org> #3.11+ Signed-off-by: John Stultz <john.stultz@linaro.org>
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
@@ -1256,7 +1256,7 @@ static void timekeeping_adjust(struct timekeeper *tk, s64 offset)
 static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 {
 	u64 nsecps = (u64)NSEC_PER_SEC << tk->shift;
-	unsigned int action = 0;
+	unsigned int clock_set = 0;
 
 	while (tk->xtime_nsec >= nsecps) {
 		int leap;
@@ -1279,10 +1279,10 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
 			__timekeeping_set_tai_offset(tk, tk->tai_offset - leap);
 
 			clock_was_set_delayed();
-			action = TK_CLOCK_WAS_SET;
+			clock_set = TK_CLOCK_WAS_SET;
 		}
 	}
-	return action;
+	return clock_set;
 }
 
 /**
@@ -1295,7 +1295,8 @@ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk)
  * Returns the unconsumed cycles.
  */
 static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
-						u32 shift)
+						u32 shift,
+						unsigned int *clock_set)
 {
 	cycle_t interval = tk->cycle_interval << shift;
 	u64 raw_nsecs;
@@ -1309,7 +1310,7 @@ static cycle_t logarithmic_accumulation(struct timekeeper *tk, cycle_t offset,
 	tk->cycle_last += interval;
 
 	tk->xtime_nsec += tk->xtime_interval << shift;
-	accumulate_nsecs_to_secs(tk);
+	*clock_set |= accumulate_nsecs_to_secs(tk);
 
 	/* Accumulate raw time */
 	raw_nsecs = (u64)tk->raw_interval << shift;
@@ -1367,7 +1368,7 @@ static void update_wall_time(void)
 	struct timekeeper *tk = &shadow_timekeeper;
 	cycle_t offset;
 	int shift = 0, maxshift;
-	unsigned int action;
+	unsigned int clock_set = 0;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
@@ -1402,7 +1403,8 @@ static void update_wall_time(void)
 	maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1;
 	shift = min(shift, maxshift);
 	while (offset >= tk->cycle_interval) {
-		offset = logarithmic_accumulation(tk, offset, shift);
+		offset = logarithmic_accumulation(tk, offset, shift,
+							&clock_set);
 		if (offset < tk->cycle_interval<<shift)
 			shift--;
 	}
@@ -1420,7 +1422,7 @@ static void update_wall_time(void)
 	 * Finally, make sure that after the rounding
 	 * xtime_nsec isn't larger than NSEC_PER_SEC
 	 */
-	action = accumulate_nsecs_to_secs(tk);
+	clock_set |= accumulate_nsecs_to_secs(tk);
 
 	write_seqcount_begin(&timekeeper_seq);
 	/* Update clock->cycle_last with the new value */
@@ -1436,7 +1438,7 @@ static void update_wall_time(void)
 	 * updating.
 	 */
 	memcpy(real_tk, tk, sizeof(*tk));
-	timekeeping_update(real_tk, action);
+	timekeeping_update(real_tk, clock_set);
 	write_seqcount_end(&timekeeper_seq);
 out:
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
