3 files changed, 51 insertions, 7 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index dbefe15bd582..a50710843378 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -74,6 +74,17 @@ static void cpuidle_idle_call(void)
          */
         hrtimer_peek_ahead_timers();
 #endif
+
+        /*
+         * Call the device's prepare function before calling the
+         * governor's select function.  ->prepare gives the device's
+         * cpuidle driver a chance to update any dynamic information
+         * of its cpuidle states for the current idle period, e.g.
+         * state availability, latencies, residencies, etc.
+         */
+        if (dev->prepare)
+                dev->prepare(dev);
+
         /* ask the governor for the next state */
         next_state = cpuidle_curr_governor->select(dev);
         if (need_resched()) {
@@ -282,6 +293,26 @@ static int __cpuidle_register_device(struct cpuidle_device *dev)
 
         poll_idle_init(dev);
 
+        /*
+         * cpuidle driver should set the dev->power_specified bit
+         * before registering the device if the driver provides
+         * power_usage numbers.
+         *
+         * For those devices whose ->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.
+         */
+        if (!dev->power_specified) {
+                int i;
+                for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++)
+                        dev->states[i].power_usage = -1 - i;
+        }
+
         per_cpu(cpuidle_devices, dev->cpu) = dev;
         list_add(&dev->device_list, &cpuidle_detected_devices);
         if ((ret = cpuidle_add_sysfs(sys_dev))) {
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 1b128702d300..c2408bbe9c2e 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -234,6 +234,7 @@ static int menu_select(struct cpuidle_device *dev)
 {
         struct menu_device *data = &__get_cpu_var(menu_devices);
         int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+        unsigned int power_usage = -1;
         int i;
         int multiplier;
 
@@ -278,19 +279,27 @@ static int menu_select(struct cpuidle_device *dev)
         if (data->expected_us > 5)
                 data->last_state_idx = CPUIDLE_DRIVER_STATE_START;
 
-
-        /* find the deepest idle state that satisfies our constraints */
+        /*
+         * Find the idle state with the lowest power while satisfying
+         * our constraints.
+         */
         for (i = CPUIDLE_DRIVER_STATE_START; i < dev->state_count; i++) {
                 struct cpuidle_state *s = &dev->states[i];
 
+                if (s->flags & CPUIDLE_FLAG_IGNORE)
+                        continue;
                 if (s->target_residency > data->predicted_us)
-                        break;
+                        continue;
                 if (s->exit_latency > latency_req)
-                        break;
+                        continue;
                 if (s->exit_latency * multiplier > data->predicted_us)
-                        break;
-                data->exit_us = s->exit_latency;
-                data->last_state_idx = i;
+                        continue;
+
+                if (s->power_usage < power_usage) {
+                        power_usage = s->power_usage;
+                        data->last_state_idx = i;
+                        data->exit_us = s->exit_latency;
+                }
         }
 
         return data->last_state_idx;
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 55215cce5005..36ca9721a0c2 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -52,6 +52,7 @@ struct cpuidle_state {
 #define CPUIDLE_FLAG_SHALLOW    (0x20) /* low latency, minimal savings */
 #define CPUIDLE_FLAG_BALANCED   (0x40) /* medium latency, moderate savings */
 #define CPUIDLE_FLAG_DEEP       (0x80) /* high latency, large savings */
+#define CPUIDLE_FLAG_IGNORE     (0x100) /* ignore during this idle period */
 
 #define CPUIDLE_DRIVER_FLAGS_MASK (0xFFFF0000)
 
@@ -84,6 +85,7 @@ struct cpuidle_state_kobj {
 struct cpuidle_device {
         unsigned int            registered:1;
         unsigned int            enabled:1;
+        unsigned int            power_specified:1;
         unsigned int            cpu;
 
         int                     last_residency;
@@ -97,6 +99,8 @@ struct cpuidle_device {
         struct completion       kobj_unregister;
         void                    *governor_data;
         struct cpuidle_state    *safe_state;
+
+        int (*prepare)          (struct cpuidle_device *dev);
 };
 
 DECLARE_PER_CPU(struct cpuidle_device *, cpuidle_devices);