Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next

Pull scheduler updates from Ingo Molnar:
 "The main scheduling related changes in this cycle were:

   - various sched/numa updates, for better performance

   - tree wide cleanup of open coded nice levels

   - nohz fix related to rq->nr_running use

   - cpuidle changes and continued consolidation to improve the
     kernel/sched/idle.c high level idle scheduling logic.  As part of
     this effort I pulled cpuidle driver changes from Rafael as well.

   - standardized idle polling amongst architectures

   - continued work on preparing better power/energy aware scheduling

   - sched/rt updates

   - misc fixlets and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  sched/numa: Decay ->wakee_flips instead of zeroing
  sched/numa: Update migrate_improves/degrades_locality()
  sched/numa: Allow task switch if load imbalance improves
  sched/rt: Fix 'struct sched_dl_entity' and dl_task_time() comments, to match the current upstream code
  sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice()
  sched: Initialize rq->age_stamp on processor start
  sched, nohz: Change rq->nr_running to always use wrappers
  sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance()
  sched: Use clamp() and clamp_val() to make sys_nice() more readable
  sched: Do not zero sg->cpumask and sg->sgp->power in build_sched_groups()
  sched/numa: Fix initialization of sched_domain_topology for NUMA
  sched: Call select_idle_sibling() when not affine_sd
  sched: Simplify return logic in sched_read_attr()
  sched: Simplify return logic in sched_copy_attr()
  sched: Fix exec_start/task_hot on migrated tasks
  arm64: Remove TIF_POLLING_NRFLAG
  metag: Remove TIF_POLLING_NRFLAG
  sched/idle: Make cpuidle_idle_call() void
  sched/idle: Reflow cpuidle_idle_call()
  sched/idle: Delay clearing the polling bit
  ...

drivers/cpuidle/cpuidle.c

@@ -32,6 +32,7 @@ LIST_HEAD(cpuidle_detected_devices);
 static int enabled_devices;
 static int off __read_mostly;
 static int initialized __read_mostly;
+static bool use_deepest_state __read_mostly;
 
 int cpuidle_disabled(void)
 {
@@ -65,23 +66,42 @@ int cpuidle_play_dead(void)
 }
 
 /**
- * cpuidle_enabled - check if the cpuidle framework is ready
- * @dev: cpuidle device for this cpu
- * @drv: cpuidle driver for this cpu
+ * cpuidle_use_deepest_state - Enable/disable the "deepest idle" mode.
+ * @enable: Whether enable or disable the feature.
  *
- * Return 0 on success, otherwise:
- * -NODEV : the cpuidle framework is not available
- * -EBUSY : the cpuidle framework is not initialized
+ * If the "deepest idle" mode is enabled, cpuidle will ignore the governor and
+ * always use the state with the greatest exit latency (out of the states that
+ * are not disabled).
+ *
+ * This function can only be called after cpuidle_pause() to avoid races.
  */
-int cpuidle_enabled(struct cpuidle_driver *drv, struct cpuidle_device *dev)
+void cpuidle_use_deepest_state(bool enable)
 {
-	if (off || !initialized)
-		return -ENODEV;
+	use_deepest_state = enable;
+}
 
-	if (!drv || !dev || !dev->enabled)
-		return -EBUSY;
+/**
+ * cpuidle_find_deepest_state - Find the state of the greatest exit latency.
+ * @drv: cpuidle driver for a given CPU.
+ * @dev: cpuidle device for a given CPU.
+ */
+static int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
+				      struct cpuidle_device *dev)
+{
+	unsigned int latency_req = 0;
+	int i, ret = CPUIDLE_DRIVER_STATE_START - 1;
 
-	return 0;
+	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+		struct cpuidle_state *s = &drv->states[i];
+		struct cpuidle_state_usage *su = &dev->states_usage[i];
+
+		if (s->disabled || su->disable || s->exit_latency <= latency_req)
+			continue;
+
+		latency_req = s->exit_latency;
+		ret = i;
+	}
+	return ret;
 }
 
 /**
@@ -138,6 +158,15 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
  */
 int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
+	if (off || !initialized)
+		return -ENODEV;
+
+	if (!drv || !dev || !dev->enabled)
+		return -EBUSY;
+
+	if (unlikely(use_deepest_state))
+		return cpuidle_find_deepest_state(drv, dev);
+
 	return cpuidle_curr_governor->select(drv, dev);
 }
 
@@ -169,7 +198,7 @@ int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev,
  */
 void cpuidle_reflect(struct cpuidle_device *dev, int index)
 {
-	if (cpuidle_curr_governor->reflect)
+	if (cpuidle_curr_governor->reflect && !unlikely(use_deepest_state))
 		cpuidle_curr_governor->reflect(dev, index);
 }
 

drivers/cpuidle/governors/menu.c

@@ -296,7 +296,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		data->needs_update = 0;
 	}
 
-	data->last_state_idx = 0;
+	data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1;
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0))
@@ -310,13 +310,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 	data->bucket = which_bucket(data->next_timer_us);
 
-	/*
-	 * if the correction factor is 0 (eg first time init or cpu hotplug
-	 * etc), we actually want to start out with a unity factor.
-	 */
-	if (data->correction_factor[data->bucket] == 0)
-		data->correction_factor[data->bucket] = RESOLUTION * DECAY;
-
 	/*
 	 * Force the result of multiplication to be 64 bits even if both
 	 * operands are 32 bits.
@@ -466,9 +459,17 @@ static int menu_enable_device(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev)
 {
 	struct menu_device *data = &per_cpu(menu_devices, dev->cpu);
+	int i;
 
 	memset(data, 0, sizeof(struct menu_device));
 
+	/*
+	 * if the correction factor is 0 (eg first time init or cpu hotplug
+	 * etc), we actually want to start out with a unity factor.
+	 */
+	for(i = 0; i < BUCKETS; i++)
+		data->correction_factor[i] = RESOLUTION * DECAY;
+
 	return 0;
 }