cpuidle: Allow enforcing deepest idle state selection

When idle injection is used to cap power, we need to override the
governor's choice of idle states.

For this reason, make it possible the deepest idle state selection to
be enforced by setting a flag on a given CPU to achieve the maximum
potential power draw reduction.

Signed-off-by: Jacob Pan <jacob.jun.pan@linux.intel.com>
[ rjw: Subject & changelog ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

drivers/cpuidle/cpuidle.c

@@ -97,7 +97,17 @@ static int find_deepest_state(struct cpuidle_driver *drv,
 	return ret;
 }
 
-#ifdef CONFIG_SUSPEND
+/* Set the current cpu to use the deepest idle state, override governors */
+void cpuidle_use_deepest_state(bool enable)
+{
+	struct cpuidle_device *dev;
+
+	preempt_disable();
+	dev = cpuidle_get_device();
+	dev->use_deepest_state = enable;
+	preempt_enable();
+}
+
 /**
  * cpuidle_find_deepest_state - Find the deepest available idle state.
  * @drv: cpuidle driver for the given CPU.
@@ -109,6 +119,7 @@ int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 	return find_deepest_state(drv, dev, UINT_MAX, 0, false);
 }
 
+#ifdef CONFIG_SUSPEND
 static void enter_freeze_proper(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {

include/linux/cpuidle.h

@@ -74,6 +74,7 @@ struct cpuidle_driver_kobj;
 struct cpuidle_device {
 	unsigned int		registered:1;
 	unsigned int		enabled:1;
+	unsigned int		use_deepest_state:1;
 	unsigned int		cpu;
 
 	int			last_residency;
@@ -192,11 +193,12 @@ static inline struct cpuidle_driver *cpuidle_get_cpu_driver(
 static inline struct cpuidle_device *cpuidle_get_device(void) {return NULL; }
 #endif
 
-#if defined(CONFIG_CPU_IDLE) && defined(CONFIG_SUSPEND)
+#ifdef CONFIG_CPU_IDLE
 extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 				      struct cpuidle_device *dev);
 extern int cpuidle_enter_freeze(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev);
+extern void cpuidle_use_deepest_state(bool enable);
 #else
 static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 					     struct cpuidle_device *dev)
@@ -204,6 +206,9 @@ static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 static inline int cpuidle_enter_freeze(struct cpuidle_driver *drv,
 				       struct cpuidle_device *dev)
 {return -ENODEV; }
+static inline void cpuidle_use_deepest_state(bool enable)
+{
+}
 #endif
 
 /* kernel/sched/idle.c */

kernel/sched/idle.c

@@ -164,11 +164,14 @@ static void cpuidle_idle_call(void)
 	 * timekeeping to prevent timer interrupts from kicking us out of idle
 	 * until a proper wakeup interrupt happens.
 	 */
-	if (idle_should_freeze()) {
-		entered_state = cpuidle_enter_freeze(drv, dev);
-		if (entered_state > 0) {
-			local_irq_enable();
-			goto exit_idle;
+
+	if (idle_should_freeze() || dev->use_deepest_state) {
+		if (idle_should_freeze()) {
+			entered_state = cpuidle_enter_freeze(drv, dev);
+			if (entered_state > 0) {
+				local_irq_enable();
+				goto exit_idle;
+			}
 		}
 
 		next_state = cpuidle_find_deepest_state(drv, dev);