cpuidle: remove the power_specified field in the driver

We realized that the power usage field is never filled and when it
is filled for tegra, the power_specified flag is not set causing all
of these values to be reset when the driver is initialized with
set_power_state().

However, the power_specified flag can be simply removed under the
assumption that the states are always backward sorted, which is the
case with the current code.

This change allows the menu governor select function and the
cpuidle_play_dead() to be simplified.  Moreover, the
set_power_states() function can removed as it does not make sense
any more.

Drop the power_specified flag from struct cpuidle_driver and make
the related changes as described above.

As a consequence, this also fixes the bug where on the dynamic
C-states system, the power fields are not initialized.

[rjw: Changelog]
References: https://bugzilla.kernel.org/show_bug.cgi?id=42870
References: https://bugzilla.kernel.org/show_bug.cgi?id=43349
References: https://lkml.org/lkml/2012/10/16/518
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

4 files changed, 7 insertions, 45 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index fb4a7dd57f94..e1f6860e069c 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -69,24 +69,15 @@ int cpuidle_play_dead(void)
 {
 	struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
-	int i, dead_state = -1;
-	int power_usage = INT_MAX;
+	int i;
 
 	if (!drv)
 		return -ENODEV;
 
 	/* Find lowest-power state that supports long-term idle */
-	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {
-		struct cpuidle_state *s = &drv->states[i];
-
-		if (s->power_usage < power_usage && s->enter_dead) {
-			power_usage = s->power_usage;
-			dead_state = i;
-		}
-	}
-
-	if (dead_state != -1)
-		return drv->states[dead_state].enter_dead(dev, dead_state);
+	for (i = drv->state_count - 1; i >= CPUIDLE_DRIVER_STATE_START; i--)
+		if (drv->states[i].enter_dead)
+			return drv->states[i].enter_dead(dev, i);
 
 	return -ENODEV;
 }
diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c
index c2b281afe0ed..422c7b69ba7c 100644
--- a/drivers/cpuidle/driver.c
+++ b/drivers/cpuidle/driver.c
@@ -19,34 +19,9 @@ DEFINE_SPINLOCK(cpuidle_driver_lock);
 static void __cpuidle_set_cpu_driver(struct cpuidle_driver *drv, int cpu);
 static struct cpuidle_driver * __cpuidle_get_cpu_driver(int cpu);
 
-static void set_power_states(struct cpuidle_driver *drv)
-{
-	int i;
-
-	/*
-	 * cpuidle driver should set the drv->power_specified bit
-	 * before registering if the driver provides
-	 * power_usage numbers.
-	 *
-	 * If power_specified is not set,
-	 * we fill in power_usage with decreasing values as the
-	 * cpuidle code has an implicit assumption that state Cn
-	 * uses less power than C(n-1).
-	 *
-	 * With CONFIG_ARCH_HAS_CPU_RELAX, C0 is already assigned
-	 * an power value of -1.  So we use -2, -3, etc, for other
-	 * c-states.
-	 */
-	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++)
-		drv->states[i].power_usage = -1 - i;
-}
-
 static void __cpuidle_driver_init(struct cpuidle_driver *drv)
 {
 	drv->refcnt = 0;
-
-	if (!drv->power_specified)
-		set_power_states(drv);
 }
 
 static int __cpuidle_register_driver(struct cpuidle_driver *drv, int cpu)
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 20ea33afdda1..fe343a06b7da 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -312,7 +312,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = &__get_cpu_var(menu_devices);
 	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
-	int power_usage = INT_MAX;
 	int i;
 	int multiplier;
 	struct timespec t;
@@ -383,11 +382,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		if (s->exit_latency * multiplier > data->predicted_us)
 			continue;
 
-		if (s->power_usage < power_usage) {
-			power_usage = s->power_usage;
-			data->last_state_idx = i;
-			data->exit_us = s->exit_latency;
-		}
+		data->last_state_idx = i;
+		data->exit_us = s->exit_latency;
 	}
 
 	/* not deepest C-state chosen for low predicted residency */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3711b34dc4f9..24cd1037b6d6 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -126,9 +126,9 @@ struct cpuidle_driver {
 	struct module 		*owner;
 	int                     refcnt;
 
-	unsigned int		power_specified:1;
 	/* set to 1 to use the core cpuidle time keeping (for all states). */
 	unsigned int		en_core_tk_irqen:1;
+	/* states array must be ordered in decreasing power consumption */
 	struct cpuidle_state	states[CPUIDLE_STATE_MAX];
 	int			state_count;
 	int			safe_state_index;