cpuidle: Add 'above' and 'below' idle state metrics

Add two new metrics for CPU idle states, "above" and "below", to count
the number of times the given state had been asked for (or entered
from the kernel's perspective), but the observed idle duration turned
out to be too short or too long for it (respectively).

These metrics help to estimate the quality of the CPU idle governor
in use.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

2 files changed, 36 insertions, 1 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index f7c58043e50f..7f108309e871 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -202,7 +202,6 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	struct cpuidle_state *target_state = &drv->states[index];
 	bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP);
 	ktime_t time_start, time_end;
-	s64 diff;
 
 	/*
 	 * Tell the time framework to switch to a broadcast timer because our
@@ -248,6 +247,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		local_irq_enable();
 
 	if (entered_state >= 0) {
+		s64 diff, delay = drv->states[entered_state].exit_latency;
+		int i;
+
 		/*
 		 * Update cpuidle counters
 		 * This can be moved to within driver enter routine,
@@ -260,6 +262,33 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 		dev->last_residency = (int)diff;
 		dev->states_usage[entered_state].time += dev->last_residency;
 		dev->states_usage[entered_state].usage++;
+
+		if (diff < drv->states[entered_state].target_residency) {
+			for (i = entered_state - 1; i >= 0; i--) {
+				if (drv->states[i].disabled ||
+				    dev->states_usage[i].disable)
+					continue;
+
+				/* Shallower states are enabled, so update. */
+				dev->states_usage[entered_state].above++;
+				break;
+			}
+		} else if (diff > delay) {
+			for (i = entered_state + 1; i < drv->state_count; i++) {
+				if (drv->states[i].disabled ||
+				    dev->states_usage[i].disable)
+					continue;
+
+				/*
+				 * Update if a deeper state would have been a
+				 * better match for the observed idle duration.
+				 */
+				if (diff - delay >= drv->states[i].target_residency)
+					dev->states_usage[entered_state].below++;
+
+				break;
+			}
+		}
 	} else {
 		dev->last_residency = 0;
 	}
diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c
index e754c7aae7f7..eb20adb5de23 100644
--- a/drivers/cpuidle/sysfs.c
+++ b/drivers/cpuidle/sysfs.c
@@ -301,6 +301,8 @@ define_show_state_str_function(name)
 define_show_state_str_function(desc)
 define_show_state_ull_function(disable)
 define_store_state_ull_function(disable)
+define_show_state_ull_function(above)
+define_show_state_ull_function(below)
 
 define_one_state_ro(name, show_state_name);
 define_one_state_ro(desc, show_state_desc);
@@ -310,6 +312,8 @@ define_one_state_ro(power, show_state_power_usage);
 define_one_state_ro(usage, show_state_usage);
 define_one_state_ro(time, show_state_time);
 define_one_state_rw(disable, show_state_disable, store_state_disable);
+define_one_state_ro(above, show_state_above);
+define_one_state_ro(below, show_state_below);
 
 static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_name.attr,
@@ -320,6 +324,8 @@ static struct attribute *cpuidle_state_default_attrs[] = {
 	&attr_usage.attr,
 	&attr_time.attr,
 	&attr_disable.attr,
+	&attr_above.attr,
+	&attr_below.attr,
 	NULL
 };