---
 drivers/cpufreq/cpufreq_governor.c |   80 ++++++++++++++++++++-----------------
 1 file changed, 45 insertions(+), 35 deletions(-)

Index: linux-pm/drivers/cpufreq/cpufreq_governor.c
===================================================================
--- linux-pm.orig/drivers/cpufreq/cpufreq_governor.c
+++ linux-pm/drivers/cpufreq/cpufreq_governor.c
@@ -156,44 +156,54 @@ unsigned int dbs_update(struct cpufreq_p
 			j_cdbs->prev_cpu_nice = cur_nice;
 		}
 
-		if (unlikely(!time_elapsed || time_elapsed < idle_time))
-			continue;
-
-		/*
-		 * If the CPU had gone completely idle, and a task just woke up
-		 * on this CPU now, it would be unfair to calculate 'load' the
-		 * usual way for this elapsed time-window, because it will show
-		 * near-zero load, irrespective of how CPU intensive that task
-		 * actually is. This is undesirable for latency-sensitive bursty
-		 * workloads.
-		 *
-		 * To avoid this, we reuse the 'load' from the previous
-		 * time-window and give this task a chance to start with a
-		 * reasonably high CPU frequency. (However, we shouldn't over-do
-		 * this copy, lest we get stuck at a high load (high frequency)
-		 * for too long, even when the current system load has actually
-		 * dropped down. So we perform the copy only once, upon the
-		 * first wake-up from idle.)
-		 *
-		 * Detecting this situation is easy: the governor's utilization
-		 * update handler would not have run during CPU-idle periods.
-		 * Hence, an unusually large 'time_elapsed' (as compared to the
-		 * sampling rate) indicates this scenario.
-		 *
-		 * prev_load can be zero in two cases and we must recalculate it
-		 * for both cases:
-		 * - during long idle intervals
-		 * - explicitly set to zero
-		 */
-		if (unlikely(time_elapsed > 2 * sampling_rate &&
-			     j_cdbs->prev_load)) {
+		if (unlikely(!time_elapsed)) {
+			/*
+			 * That can only happen when this function is called
+			 * twice in a row with a very short interval between the
+			 * calls, so the previous load value can be used then.
+			 */
 			load = j_cdbs->prev_load;
-
+		} else if (time_elapsed < idle_time) {
 			/*
-			 * Perform a destructive copy, to ensure that we copy
-			 * the previous load only once, upon the first wake-up
-			 * from idle.
+			 * That can happen if idle_time is returned by
+			 * get_cpu_idle_time_jiffy().  In that case idle_time is
+			 * roughly equal to the difference between time_elapsed
+			 * and "busy time" obtained from CPU statistics.  In
+			 * that case the "busy time" can end up being greater
+			 * than time_elapsed (for example, if jiffies_64 and
+			 * the CPU statistics are updated by different CPUs),
+			 * so idle_time may in fact be negative.  That means,
+			 * though, that the CPU was busy all the time (on the
+			 * rough average), 100 can be returned as the load.
 			 */
+			load = (int)idle_time < 0 ? 100 : 0;
+		} else if (unlikely(time_elapsed > 2 * sampling_rate &&
+				    j_cdbs->prev_load)) {
+			/*
+			 * If the CPU had gone completely idle and a task has
+			 * just woken up on this CPU now, it would be unfair to
+			 * calculate 'load' the usual way for this elapsed
+			 * time-window, because it would show near-zero load,
+			 * irrespective of how CPU intensive that task actually
+			 * was. This is undesirable for latency-sensitive bursty
+			 * workloads.
+			 *
+			 * To avoid this, reuse the 'load' from the previous
+			 * time-window and give this task a chance to start with
+			 * a reasonably high CPU frequency. However, that
+			 * shouldn't be over-done, lest we get stuck at a high
+			 * load (high frequency) for too long, even when the
+			 * current system load has actually dropped down, so
+			 * clear prev_load to guarantee that the load will be
+			 * computed again next time.
+			 *
+			 * Detecting this situation is easy: the governor's
+			 * utilization update handler would not have run during
+			 * CPU-idle periods.  Hence, an unusually large
+			 * 'time_elapsed' (as compared to the sampling rate)
+			 * indicates this scenario.
+			 */
+			load = j_cdbs->prev_load;
 			j_cdbs->prev_load = 0;
 		} else {
 			load = 100 * (time_elapsed - idle_time) / time_elapsed;