Merge pull request #744 from angolini/lf-6.12.20-2.0.0_up_6.12.49toradex_6.12-2.0.x-imx

Lf 6.12.20 2.0.0 up 6.12.49

1 files changed, 47 insertions, 86 deletions

diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index f3c9d49f0f2a..3eb543b1644d 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -19,7 +19,7 @@
 
 #include "gov.h"
 
-#define BUCKETS 12
+#define BUCKETS 6
 #define INTERVAL_SHIFT 3
 #define INTERVALS (1UL << INTERVAL_SHIFT)
 #define RESOLUTION 1024
@@ -29,12 +29,11 @@
 /*
  * Concepts and ideas behind the menu governor
  *
- * For the menu governor, there are 3 decision factors for picking a C
+ * For the menu governor, there are 2 decision factors for picking a C
  * state:
  * 1) Energy break even point
- * 2) Performance impact
- * 3) Latency tolerance (from pmqos infrastructure)
- * These three factors are treated independently.
+ * 2) Latency tolerance (from pmqos infrastructure)
+ * These two factors are treated independently.
  *
  * Energy break even point
  * -----------------------
@@ -75,30 +74,6 @@
  * intervals and if the stand deviation of these 8 intervals is below a
  * threshold value, we use the average of these intervals as prediction.
  *
- * Limiting Performance Impact
- * ---------------------------
- * C states, especially those with large exit latencies, can have a real
- * noticeable impact on workloads, which is not acceptable for most sysadmins,
- * and in addition, less performance has a power price of its own.
- *
- * As a general rule of thumb, menu assumes that the following heuristic
- * holds:
- *     The busier the system, the less impact of C states is acceptable
- *
- * This rule-of-thumb is implemented using a performance-multiplier:
- * If the exit latency times the performance multiplier is longer than
- * the predicted duration, the C state is not considered a candidate
- * for selection due to a too high performance impact. So the higher
- * this multiplier is, the longer we need to be idle to pick a deep C
- * state, and thus the less likely a busy CPU will hit such a deep
- * C state.
- *
- * Currently there is only one value determining the factor:
- * 10 points are added for each process that is waiting for IO on this CPU.
- * (This value was experimentally determined.)
- * Utilization is no longer a factor as it was shown that it never contributed
- * significantly to the performance multiplier in the first place.
- *
  */
 
 struct menu_device {
@@ -112,19 +87,10 @@ struct menu_device {
 	int		interval_ptr;
 };
 
-static inline int which_bucket(u64 duration_ns, unsigned int nr_iowaiters)
+static inline int which_bucket(u64 duration_ns)
 {
 	int bucket = 0;
 
-	/*
-	 * We keep two groups of stats; one with no
-	 * IO pending, one without.
-	 * This allows us to calculate
-	 * E(duration)|iowait
-	 */
-	if (nr_iowaiters)
-		bucket = BUCKETS/2;
-
 	if (duration_ns < 10ULL * NSEC_PER_USEC)
 		return bucket;
 	if (duration_ns < 100ULL * NSEC_PER_USEC)
@@ -138,21 +104,16 @@ static inline int which_bucket(u64 duration_ns, unsigned int nr_iowaiters)
 	return bucket + 5;
 }
 
-/*
- * Return a multiplier for the exit latency that is intended
- * to take performance requirements into account.
- * The more performance critical we estimate the system
- * to be, the higher this multiplier, and thus the higher
- * the barrier to go to an expensive C state.
- */
-static inline int performance_multiplier(unsigned int nr_iowaiters)
+static DEFINE_PER_CPU(struct menu_device, menu_devices);
+
+static void menu_update_intervals(struct menu_device *data, unsigned int interval_us)
 {
-	/* for IO wait tasks (per cpu!) we add 10x each */
-	return 1 + 10 * nr_iowaiters;
+	/* Update the repeating-pattern data. */
+	data->intervals[data->interval_ptr++] = interval_us;
+	if (data->interval_ptr >= INTERVALS)
+		data->interval_ptr = 0;
 }
 
-static DEFINE_PER_CPU(struct menu_device, menu_devices);
-
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev);
 
 /*
@@ -239,8 +200,19 @@ again:
 	 * This can deal with workloads that have long pauses interspersed
 	 * with sporadic activity with a bunch of short pauses.
 	 */
-	if ((divisor * 4) <= INTERVALS * 3)
+	if (divisor * 4 <= INTERVALS * 3) {
+		/*
+		 * If there are sufficiently many data points still under
+		 * consideration after the outliers have been eliminated,
+		 * returning without a prediction would be a mistake because it
+		 * is likely that the next interval will not exceed the current
+		 * maximum, so return the latter in that case.
+		 */
+		if (divisor >= INTERVALS / 2)
+			return max;
+
 		return UINT_MAX;
+	}
 
 	thresh = max - 1;
 	goto again;
@@ -258,18 +230,22 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	s64 latency_req = cpuidle_governor_latency_req(dev->cpu);
 	u64 predicted_ns;
-	u64 interactivity_req;
-	unsigned int nr_iowaiters;
 	ktime_t delta, delta_tick;
 	int i, idx;
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
 		data->needs_update = 0;
+	} else if (!dev->last_residency_ns) {
+		/*
+		 * This happens when the driver rejects the previously selected
+		 * idle state and returns an error, so update the recent
+		 * intervals table to prevent invalid information from being
+		 * used going forward.
+		 */
+		menu_update_intervals(data, UINT_MAX);
 	}
 
-	nr_iowaiters = nr_iowait_cpu(dev->cpu);
-
 	/* Find the shortest expected idle interval. */
 	predicted_ns = get_typical_interval(data) * NSEC_PER_USEC;
 	if (predicted_ns > RESIDENCY_THRESHOLD_NS) {
@@ -283,7 +259,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		}
 
 		data->next_timer_ns = delta;
-		data->bucket = which_bucket(data->next_timer_ns, nr_iowaiters);
+		data->bucket = which_bucket(data->next_timer_ns);
 
 		/* Round up the result for half microseconds. */
 		timer_us = div_u64((RESOLUTION * DECAY * NSEC_PER_USEC) / 2 +
@@ -301,7 +277,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		 */
 		data->next_timer_ns = KTIME_MAX;
 		delta_tick = TICK_NSEC / 2;
-		data->bucket = which_bucket(KTIME_MAX, nr_iowaiters);
+		data->bucket = which_bucket(KTIME_MAX);
 	}
 
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
@@ -317,27 +293,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		return 0;
 	}
 
-	if (tick_nohz_tick_stopped()) {
-		/*
-		 * If the tick is already stopped, the cost of possible short
-		 * idle duration misprediction is much higher, because the CPU
-		 * may be stuck in a shallow idle state for a long time as a
-		 * result of it.  In that case say we might mispredict and use
-		 * the known time till the closest timer event for the idle
-		 * state selection.
-		 */
-		if (predicted_ns < TICK_NSEC)
-			predicted_ns = data->next_timer_ns;
-	} else {
-		/*
-		 * Use the performance multiplier and the user-configurable
-		 * latency_req to determine the maximum exit latency.
-		 */
-		interactivity_req = div64_u64(predicted_ns,
-					      performance_multiplier(nr_iowaiters));
-		if (latency_req > interactivity_req)
-			latency_req = interactivity_req;
-	}
+	/*
+	 * If the tick is already stopped, the cost of possible short idle
+	 * duration misprediction is much higher, because the CPU may be stuck
+	 * in a shallow idle state for a long time as a result of it.  In that
+	 * case, say we might mispredict and use the known time till the closest
+	 * timer event for the idle state selection.
+	 */
+	if (tick_nohz_tick_stopped() && predicted_ns < TICK_NSEC)
+		predicted_ns = data->next_timer_ns;
 
 	/*
 	 * Find the idle state with the lowest power while satisfying
@@ -353,13 +317,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		if (idx == -1)
 			idx = i; /* first enabled state */
 
+		if (s->exit_latency_ns > latency_req)
+			break;
+
 		if (s->target_residency_ns > predicted_ns) {
 			/*
 			 * Use a physical idle state, not busy polling, unless
 			 * a timer is going to trigger soon enough.
 			 */
 			if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) &&
-			    s->exit_latency_ns <= latency_req &&
 			    s->target_residency_ns <= data->next_timer_ns) {
 				predicted_ns = s->target_residency_ns;
 				idx = i;
@@ -391,8 +357,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 			return idx;
 		}
-		if (s->exit_latency_ns > latency_req)
-			break;
 
 		idx = i;
 	}
@@ -535,10 +499,7 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 	data->correction_factor[data->bucket] = new_factor;
 
-	/* update the repeating-pattern data */
-	data->intervals[data->interval_ptr++] = ktime_to_us(measured_ns);
-	if (data->interval_ptr >= INTERVALS)
-		data->interval_ptr = 0;
+	menu_update_intervals(data, ktime_to_us(measured_ns));
 }
 
 /**