PM / sleep: Re-implement suspend-to-idle handling

In preparation for adding support for quiescing timers in the final
stage of suspend-to-idle transitions, rework the freeze_enter()
function making the system wait on a wakeup event, the freeze_wake()
function terminating the suspend-to-idle loop and the mechanism by
which deep idle states are entered during suspend-to-idle.

First of all, introduce a simple state machine for suspend-to-idle
and make the code in question use it.

Second, prevent freeze_enter() from losing wakeup events due to race
conditions and ensure that the number of online CPUs won't change
while it is being executed.  In addition to that, make it force
all of the CPUs re-enter the idle loop in case they are in idle
states already (so they can enter deeper idle states if possible).

Next, drop cpuidle_use_deepest_state() and replace use_deepest_state
checks in cpuidle_select() and cpuidle_reflect() with a single
suspend-to-idle state check in cpuidle_idle_call().

Finally, introduce cpuidle_enter_freeze() that will simply find the
deepest idle state available to the given CPU and enter it using
cpuidle_enter().

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>

1 files changed, 26 insertions, 23 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 125150dc6e81..23a8d6cc8d30 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -19,6 +19,7 @@
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
 #include <linux/module.h>
+#include <linux/suspend.h>
 #include <trace/events/power.h>
 
 #include "cpuidle.h"
@@ -32,7 +33,6 @@ 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)
 {
@@ -66,24 +66,9 @@ int cpuidle_play_dead(void)
 }
 
 /**
- * cpuidle_use_deepest_state - Enable/disable the "deepest idle" mode.
- * @enable: Whether enable or disable the feature.
- *
- * 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.
- */
-void cpuidle_use_deepest_state(bool enable)
-{
-	use_deepest_state = enable;
-}
-
-/**
- * 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.
+ * cpuidle_find_deepest_state - Find deepest state meeting specific conditions.
+ * @drv: cpuidle driver for the given CPU.
+ * @dev: cpuidle device for the given CPU.
  */
 static int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 				      struct cpuidle_device *dev)
@@ -105,6 +90,27 @@ static int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 }
 
 /**
+ * cpuidle_enter_freeze - Enter an idle state suitable for suspend-to-idle.
+ *
+ * Find the deepest state available and enter it.
+ */
+void cpuidle_enter_freeze(void)
+{
+	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
+	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int index;
+
+	index = cpuidle_find_deepest_state(drv, dev);
+	if (index >= 0)
+		cpuidle_enter(drv, dev, index);
+	else
+		arch_cpu_idle();
+
+	/* Interrupts are enabled again here. */
+	local_irq_disable();
+}
+
+/**
  * cpuidle_enter_state - enter the state and update stats
  * @dev: cpuidle device for this cpu
  * @drv: cpuidle driver for this cpu
@@ -166,9 +172,6 @@ int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 	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);
 }
 
@@ -200,7 +203,7 @@ 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 && !unlikely(use_deepest_state))
+	if (cpuidle_curr_governor->reflect)
 		cpuidle_curr_governor->reflect(dev, index);
 }