Merge branch 'pm-cpuidle'

* pm-cpuidle:
  cpuidle: menu: Avoid pointless checks in menu_select()
  sched / idle: Drop default_idle_call() fallback from call_cpuidle()
  cpuidle: Don't enable all governors by default
  cpuidle: Default to ladder governor on ticking systems
  time: nohz: Expose tick_nohz_enabled
  cpuidle: menu: Fix menu_select() for CPUIDLE_DRIVER_STATE_START == 0

drivers/cpuidle/Kconfig

@@ -19,11 +19,9 @@ config CPU_IDLE_MULTIPLE_DRIVERS
 
 config CPU_IDLE_GOV_LADDER
 	bool "Ladder governor (for periodic timer tick)"
-	default y
 
 config CPU_IDLE_GOV_MENU
 	bool "Menu governor (for tickless system)"
-	default y
 
 config DT_IDLE_STATES
 	bool

drivers/cpuidle/cpuidle.c

@@ -79,9 +79,9 @@ static int find_deepest_state(struct cpuidle_driver *drv,
 			      bool freeze)
 {
 	unsigned int latency_req = 0;
-	int i, ret = -ENXIO;
+	int i, ret = 0;
 
-	for (i = 0; i < drv->state_count; i++) {
+	for (i = 1; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
 		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
@@ -243,7 +243,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv,
  * @drv: the cpuidle driver
  * @dev: the cpuidle device
  *
- * Returns the index of the idle state.
+ * Returns the index of the idle state.  The return value must not be negative.
  */
 int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {

drivers/cpuidle/governors/ladder.c

@@ -17,6 +17,7 @@
 #include <linux/pm_qos.h>
 #include <linux/module.h>
 #include <linux/jiffies.h>
+#include <linux/tick.h>
 
 #include <asm/io.h>
 #include <asm/uaccess.h>
@@ -184,6 +185,14 @@ static struct cpuidle_governor ladder_governor = {
  */
 static int __init init_ladder(void)
 {
+	/*
+	 * When NO_HZ is disabled, or when booting with nohz=off, the ladder
+	 * governor is better so give it a higher rating than the menu
+	 * governor.
+	 */
+	if (!tick_nohz_enabled)
+		ladder_governor.rating = 25;
+
 	return cpuidle_register_governor(&ladder_governor);
 }
 

drivers/cpuidle/governors/menu.c

@@ -294,8 +294,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		data->needs_update = 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))
 		return 0;
@@ -326,6 +324,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	if (latency_req > interactivity_req)
 		latency_req = interactivity_req;
 
+	if (CPUIDLE_DRIVER_STATE_START > 0) {
+		data->last_state_idx = CPUIDLE_DRIVER_STATE_START - 1;
 		/*
 		 * We want to default to C1 (hlt), not to busy polling
 		 * unless the timer is happening really really soon.
@@ -334,12 +334,15 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		    !drv->states[CPUIDLE_DRIVER_STATE_START].disabled &&
 			dev->states_usage[CPUIDLE_DRIVER_STATE_START].disable == 0)
 			data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
+	} else {
+		data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
+	}
 
 	/*
 	 * Find the idle state with the lowest power while satisfying
 	 * our constraints.
 	 */
-	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
+	for (i = data->last_state_idx + 1; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
 		struct cpuidle_state_usage *su = &dev->states_usage[i];
 

include/linux/tick.h

@@ -98,6 +98,7 @@ static inline void tick_broadcast_exit(void)
 }
 
 #ifdef CONFIG_NO_HZ_COMMON
+extern int tick_nohz_enabled;
 extern int tick_nohz_tick_stopped(void);
 extern void tick_nohz_idle_enter(void);
 extern void tick_nohz_idle_exit(void);
@@ -106,6 +107,7 @@ extern ktime_t tick_nohz_get_sleep_length(void);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);
 #else /* !CONFIG_NO_HZ_COMMON */
+#define tick_nohz_enabled (0)
 static inline int tick_nohz_tick_stopped(void) { return 0; }
 static inline void tick_nohz_idle_enter(void) { }
 static inline void tick_nohz_idle_exit(void) { }

kernel/sched/idle.c

@@ -97,12 +97,6 @@ void default_idle_call(void)
 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.

kernel/time/tick-sched.c

@@ -387,7 +387,7 @@ void __init tick_nohz_init(void)
 /*
  * NO HZ enabled ?
  */
-static int tick_nohz_enabled __read_mostly  = 1;
+int tick_nohz_enabled __read_mostly = 1;
 unsigned long tick_nohz_active  __read_mostly;
 /*
  * Enable / Disable tickless mode