Merge branch 'pm-cpuidle'

* pm-cpuidle:
  cpuidle: Do not use CPUIDLE_DRIVER_STATE_START in cpuidle.c
  cpuidle: Select a different state on tick_broadcast_enter() failures
  sched / idle: Call default_idle_call() from cpuidle_enter_state()
  sched / idle: Call idle_set_state() from cpuidle_enter_state()
  cpuidle: Fix the kerneldoc comment for cpuidle_enter_state()
  sched / idle: Eliminate the "reflect" check from cpuidle_idle_call()
  cpuidle: Check the sign of index in cpuidle_reflect()
  sched / idle: Move the default idle call code to a separate function

drivers/cpuidle/cpuidle.c

@@ -65,7 +65,7 @@ int cpuidle_play_dead(void)
 		return -ENODEV;
 
 	/* Find lowest-power state that supports long-term idle */
-	for (i = drv->state_count - 1; i >= CPUIDLE_DRIVER_STATE_START; i--)
+	for (i = drv->state_count - 1; i >= 0; i--)
 		if (drv->states[i].enter_dead)
 			return drv->states[i].enter_dead(dev, i);
 
@@ -73,16 +73,21 @@ int cpuidle_play_dead(void)
 }
 
 static int find_deepest_state(struct cpuidle_driver *drv,
-			      struct cpuidle_device *dev, bool freeze)
+			      struct cpuidle_device *dev,
+			      unsigned int max_latency,
+			      unsigned int forbidden_flags,
+			      bool freeze)
 {
 	unsigned int latency_req = 0;
-	int i, ret = freeze ? -1 : CPUIDLE_DRIVER_STATE_START - 1;
+	int i, ret = -ENXIO;
 
-	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+	for (i = 0; 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
+		    || s->exit_latency > max_latency
+		    || (s->flags & forbidden_flags)
 		    || (freeze && !s->enter_freeze))
 			continue;
 
@@ -100,7 +105,7 @@ static int find_deepest_state(struct cpuidle_driver *drv,
 int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 			       struct cpuidle_device *dev)
 {
-	return find_deepest_state(drv, dev, false);
+	return find_deepest_state(drv, dev, UINT_MAX, 0, false);
 }
 
 static void enter_freeze_proper(struct cpuidle_driver *drv,
@@ -139,7 +144,7 @@ int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	 * that interrupts won't be enabled when it exits and allows the tick to
 	 * be frozen safely.
 	 */
-	index = find_deepest_state(drv, dev, true);
+	index = find_deepest_state(drv, dev, UINT_MAX, 0, true);
 	if (index >= 0)
 		enter_freeze_proper(drv, dev, index);
 
@@ -150,7 +155,7 @@ int cpuidle_enter_freeze(struct cpuidle_driver *drv, struct cpuidle_device *dev)
  * cpuidle_enter_state - enter the state and update stats
  * @dev: cpuidle device for this cpu
  * @drv: cpuidle driver for this cpu
- * @next_state: index into drv->states of the state to enter
+ * @index: index into the states table in @drv of the state to enter
  */
 int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 			int index)
@@ -167,8 +172,18 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	 * local timer will be shut down.  If a local timer is used from another
 	 * CPU as a broadcast timer, this call may fail if it is not available.
 	 */
-	if (broadcast && tick_broadcast_enter())
-		return -EBUSY;
+	if (broadcast && tick_broadcast_enter()) {
+		index = find_deepest_state(drv, dev, target_state->exit_latency,
+					   CPUIDLE_FLAG_TIMER_STOP, false);
+		if (index < 0) {
+			default_idle_call();
+			return -EBUSY;
+		}
+		target_state = &drv->states[index];
+	}
+
+	/* Take note of the planned idle state. */
+	sched_idle_set_state(target_state);
 
 	trace_cpu_idle_rcuidle(index, dev->cpu);
 	time_start = ktime_get();
@@ -178,6 +193,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
 	time_end = ktime_get();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
 
+	/* The cpu is no longer idle or about to enter idle. */
+	sched_idle_set_state(NULL);
+
 	if (broadcast) {
 		if (WARN_ON_ONCE(!irqs_disabled()))
 			local_irq_disable();
@@ -249,7 +267,7 @@ 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 && index >= 0)
 		cpuidle_curr_governor->reflect(dev, index);
 }
 

drivers/cpuidle/governors/menu.c

@@ -367,9 +367,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 static void menu_reflect(struct cpuidle_device *dev, int index)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
+
 	data->last_state_idx = index;
-	if (index >= 0)
-		data->needs_update = 1;
+	data->needs_update = 1;
 }
 
 /**

include/linux/cpuidle.h

@@ -200,6 +200,10 @@ static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
 	struct cpuidle_device *dev) {return NULL; }
 #endif
 
+/* kernel/sched/idle.c */
+extern void sched_idle_set_state(struct cpuidle_state *idle_state);
+extern void default_idle_call(void);
+
 #ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED
 void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a);
 #else

kernel/sched/idle.c

@@ -15,6 +15,15 @@
 
 #include "sched.h"
 
+/**
+ * sched_idle_set_state - Record idle state for the current CPU.
+ * @idle_state: State to record.
+ */
+void sched_idle_set_state(struct cpuidle_state *idle_state)
+{
+	idle_set_state(this_rq(), idle_state);
+}
+
 static int __read_mostly cpu_idle_force_poll;
 
 void cpu_idle_poll_ctrl(bool enable)
@@ -67,6 +76,46 @@ void __weak arch_cpu_idle(void)
 	local_irq_enable();
 }
 
+/**
+ * default_idle_call - Default CPU idle routine.
+ *
+ * To use when the cpuidle framework cannot be used.
+ */
+void default_idle_call(void)
+{
+	if (current_clr_polling_and_test())
+		local_irq_enable();
+	else
+		arch_cpu_idle();
+}
+
+static int call_cpuidle(struct cpuidle_driver *drv, struct cpuidle_device *dev,
+		      int next_state)
+{
+	/* Fall back to the default arch idle method on errors. */
+	if (next_state < 0) {
+		default_idle_call();
+		return next_state;
+	}
+
+	/*
+	 * The idle task must be scheduled, it is pointless to go to idle, just
+	 * update no idle residency and return.
+	 */
+	if (current_clr_polling_and_test()) {
+		dev->last_residency = 0;
+		local_irq_enable();
+		return -EBUSY;
+	}
+
+	/*
+	 * Enter the idle state previously returned by the governor decision.
+	 * This function will block until an interrupt occurs and will take
+	 * care of re-enabling the local interrupts
+	 */
+	return cpuidle_enter(drv, dev, next_state);
+}
+
 /**
  * cpuidle_idle_call - the main idle function
  *
@@ -81,7 +130,6 @@ static void cpuidle_idle_call(void)
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
 	int next_state, entered_state;
-	bool reflect;
 
 	/*
 	 * Check if the idle task must be rescheduled. If it is the
@@ -105,8 +153,10 @@ static void cpuidle_idle_call(void)
 	 */
 	rcu_idle_enter();
 
-	if (cpuidle_not_available(drv, dev))
-		goto use_default;
+	if (cpuidle_not_available(drv, dev)) {
+		default_idle_call();
+		goto exit_idle;
+	}
 
 	/*
 	 * Suspend-to-idle ("freeze") is a system state in which all user space
@@ -124,52 +174,19 @@ static void cpuidle_idle_call(void)
 			goto exit_idle;
 		}
 
-		reflect = false;
 		next_state = cpuidle_find_deepest_state(drv, dev);
+		call_cpuidle(drv, dev, next_state);
 	} else {
-		reflect = true;
 		/*
 		 * Ask the cpuidle framework to choose a convenient idle state.
 		 */
 		next_state = cpuidle_select(drv, dev);
-	}
-	/* Fall back to the default arch idle method on errors. */
-	if (next_state < 0)
-		goto use_default;
-
-	/*
-	 * The idle task must be scheduled, it is pointless to
-	 * go to idle, just update no idle residency and get
-	 * out of this function
-	 */
-	if (current_clr_polling_and_test()) {
-		dev->last_residency = 0;
-		entered_state = next_state;
-		local_irq_enable();
-		goto exit_idle;
-	}
-
-	/* Take note of the planned idle state. */
-	idle_set_state(this_rq(), &drv->states[next_state]);
-
-	/*
-	 * Enter the idle state previously returned by the governor decision.
-	 * This function will block until an interrupt occurs and will take
-	 * care of re-enabling the local interrupts
-	 */
-	entered_state = cpuidle_enter(drv, dev, next_state);
-
-	/* The cpu is no longer idle or about to enter idle. */
-	idle_set_state(this_rq(), NULL);
-
-	if (entered_state == -EBUSY)
-		goto use_default;
-
-	/*
-	 * Give the governor an opportunity to reflect on the outcome
-	 */
-	if (reflect)
+		entered_state = call_cpuidle(drv, dev, next_state);
+		/*
+		 * Give the governor an opportunity to reflect on the outcome
+		 */
 		cpuidle_reflect(dev, entered_state);
+	}
 
 exit_idle:
 	__current_set_polling();
@@ -182,19 +199,6 @@ exit_idle:
 
 	rcu_idle_exit();
 	start_critical_timings();
-	return;
-
-use_default:
-	/*
-	 * We can't use the cpuidle framework, let's use the default
-	 * idle routine.
-	 */
-	if (current_clr_polling_and_test())
-		local_irq_enable();
-	else
-		arch_cpu_idle();
-
-	goto exit_idle;
 }
 
 DEFINE_PER_CPU(bool, cpu_dead_idle);