Merge tag 'pm-4.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull more power management updates from Rafael Wysocki:
 "These include one big-ticket item which is the rework of the idle loop
  in order to prevent CPUs from spending too much time in shallow idle
  states. It reduces idle power on some systems by 10% or more and may
  improve performance of workloads in which the idle loop overhead
  matters. This has been in the works for several weeks and it has been
  tested and reviewed quite thoroughly.

  Also included are changes that finalize the cpufreq cleanup moving
  frequency table validation from drivers to the core, a few fixes and
  cleanups of cpufreq drivers, a cpuidle documentation update and a PM
  QoS core update to mark the expected switch fall-throughs in it.

  Specifics:

   - Rework the idle loop in order to prevent CPUs from spending too
     much time in shallow idle states by making it stop the scheduler
     tick before putting the CPU into an idle state only if the idle
     duration predicted by the idle governor is long enough.

     That required the code to be reordered to invoke the idle governor
     before stopping the tick, among other things (Rafael Wysocki,
     Frederic Weisbecker, Arnd Bergmann).

   - Add the missing description of the residency sysfs attribute to the
     cpuidle documentation (Prashanth Prakash).

   - Finalize the cpufreq cleanup moving frequency table validation from
     drivers to the core (Viresh Kumar).

   - Fix a clock leak regression in the armada-37xx cpufreq driver
     (Gregory Clement).

   - Fix the initialization of the CPU performance data structures for
     shared policies in the CPPC cpufreq driver (Shunyong Yang).

   - Clean up the ti-cpufreq, intel_pstate and CPPC cpufreq drivers a
     bit (Viresh Kumar, Rafael Wysocki).

   - Mark the expected switch fall-throughs in the PM QoS core (Gustavo
     Silva)"

* tag 'pm-4.17-rc1-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (23 commits)
  tick-sched: avoid a maybe-uninitialized warning
  cpufreq: Drop cpufreq_table_validate_and_show()
  cpufreq: SCMI: Don't validate the frequency table twice
  cpufreq: CPPC: Initialize shared perf capabilities of CPUs
  cpufreq: armada-37xx: Fix clock leak
  cpufreq: CPPC: Don't set transition_latency
  cpufreq: ti-cpufreq: Use builtin_platform_driver()
  cpufreq: intel_pstate: Do not include debugfs.h
  PM / QoS: mark expected switch fall-throughs
  cpuidle: Add definition of residency to sysfs documentation
  time: hrtimer: Use timerqueue_iterate_next() to get to the next timer
  nohz: Avoid duplication of code related to got_idle_tick
  nohz: Gather tick_sched booleans under a common flag field
  cpuidle: menu: Avoid selecting shallow states with stopped tick
  cpuidle: menu: Refine idle state selection for running tick
  sched: idle: Select idle state before stopping the tick
  time: hrtimer: Introduce hrtimer_next_event_without()
  time: tick-sched: Split tick_nohz_stop_sched_tick()
  cpuidle: Return nohz hint from cpuidle_select()
  jiffies: Introduce USER_TICK_USEC and redefine TICK_USEC
  ...

1 files changed, 93 insertions, 20 deletions

diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index aa390404e85f..1bfe03ceb236 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -123,6 +123,7 @@
 struct menu_device {
 	int		last_state_idx;
 	int             needs_update;
+	int             tick_wakeup;
 
 	unsigned int	next_timer_us;
 	unsigned int	predicted_us;
@@ -279,8 +280,10 @@ again:
  * menu_select - selects the next idle state to enter
  * @drv: cpuidle driver containing state data
  * @dev: the CPU
+ * @stop_tick: indication on whether or not to stop the tick
  */
-static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+		       bool *stop_tick)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 	struct device *device = get_cpu_device(dev->cpu);
@@ -292,6 +295,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
 	int resume_latency = dev_pm_qos_raw_read_value(device);
+	ktime_t delta_next;
 
 	if (data->needs_update) {
 		menu_update(drv, dev);
@@ -303,11 +307,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		latency_req = resume_latency;
 
 	/* Special case when user has set very strict latency requirement */
-	if (unlikely(latency_req == 0))
+	if (unlikely(latency_req == 0)) {
+		*stop_tick = false;
 		return 0;
+	}
 
 	/* determine the expected residency time, round up */
-	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length());
+	data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next));
 
 	get_iowait_load(&nr_iowaiters, &cpu_load);
 	data->bucket = which_bucket(data->next_timer_us, nr_iowaiters);
@@ -346,14 +352,30 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 */
 	data->predicted_us = min(data->predicted_us, expected_interval);
 
-	/*
-	 * Use the performance multiplier and the user-configurable
-	 * latency_req to determine the maximum exit latency.
-	 */
-	interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
-	if (latency_req > interactivity_req)
-		latency_req = interactivity_req;
+	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 try
+		 * to force the CPU into a state for which we would have stopped
+		 * the tick, unless a timer is going to expire really soon
+		 * anyway.
+		 */
+		if (data->predicted_us < TICK_USEC)
+			data->predicted_us = min_t(unsigned int, TICK_USEC,
+						   ktime_to_us(delta_next));
+	} else {
+		/*
+		 * Use the performance multiplier and the user-configurable
+		 * latency_req to determine the maximum exit latency.
+		 */
+		interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load);
+		if (latency_req > interactivity_req)
+			latency_req = interactivity_req;
+	}
 
+	expected_interval = data->predicted_us;
 	/*
 	 * Find the idle state with the lowest power while satisfying
 	 * our constraints.
@@ -369,15 +391,52 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 			idx = i; /* first enabled state */
 		if (s->target_residency > data->predicted_us)
 			break;
-		if (s->exit_latency > latency_req)
+		if (s->exit_latency > latency_req) {
+			/*
+			 * If we break out of the loop for latency reasons, use
+			 * the target residency of the selected state as the
+			 * expected idle duration so that the tick is retained
+			 * as long as that target residency is low enough.
+			 */
+			expected_interval = drv->states[idx].target_residency;
 			break;
-
+		}
 		idx = i;
 	}
 
 	if (idx == -1)
 		idx = 0; /* No states enabled. Must use 0. */
 
+	/*
+	 * Don't stop the tick if the selected state is a polling one or if the
+	 * expected idle duration is shorter than the tick period length.
+	 */
+	if ((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) ||
+	    expected_interval < TICK_USEC) {
+		unsigned int delta_next_us = ktime_to_us(delta_next);
+
+		*stop_tick = false;
+
+		if (!tick_nohz_tick_stopped() && idx > 0 &&
+		    drv->states[idx].target_residency > delta_next_us) {
+			/*
+			 * The tick is not going to be stopped and the target
+			 * residency of the state to be returned is not within
+			 * the time until the next timer event including the
+			 * tick, so try to correct that.
+			 */
+			for (i = idx - 1; i >= 0; i--) {
+			    if (drv->states[i].disabled ||
+			        dev->states_usage[i].disable)
+					continue;
+
+				idx = i;
+				if (drv->states[i].target_residency <= delta_next_us)
+					break;
+			}
+		}
+	}
+
 	data->last_state_idx = idx;
 
 	return data->last_state_idx;
@@ -397,6 +456,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
 
 	data->last_state_idx = index;
 	data->needs_update = 1;
+	data->tick_wakeup = tick_nohz_idle_got_tick();
 }
 
 /**
@@ -427,14 +487,27 @@ static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * assume the state was never reached and the exit latency is 0.
 	 */
 
-	/* measured value */
-	measured_us = cpuidle_get_last_residency(dev);
-
-	/* Deduct exit latency */
-	if (measured_us > 2 * target->exit_latency)
-		measured_us -= target->exit_latency;
-	else
-		measured_us /= 2;
+	if (data->tick_wakeup && data->next_timer_us > TICK_USEC) {
+		/*
+		 * The nohz code said that there wouldn't be any events within
+		 * the tick boundary (if the tick was stopped), but the idle
+		 * duration predictor had a differing opinion.  Since the CPU
+		 * was woken up by a tick (that wasn't stopped after all), the
+		 * predictor was not quite right, so assume that the CPU could
+		 * have been idle long (but not forever) to help the idle
+		 * duration predictor do a better job next time.
+		 */
+		measured_us = 9 * MAX_INTERESTING / 10;
+	} else {
+		/* measured value */
+		measured_us = cpuidle_get_last_residency(dev);
+
+		/* Deduct exit latency */
+		if (measured_us > 2 * target->exit_latency)
+			measured_us -= target->exit_latency;
+		else
+			measured_us /= 2;
+	}
 
 	/* Make sure our coefficients do not exceed unity */
 	if (measured_us > data->next_timer_us)