cpuidle: Move dev->last_residency update to driver enter routine; remove dev->last_state

Cpuidle governor only suggests the state to enter using the
governor->select() interface, but allows the low level driver to
override the recommended state. The actual entered state
may be different because of software or hardware demotion. Software
demotion is done by the back-end cpuidle driver and can be accounted
correctly. Current cpuidle code uses last_state field to capture the
actual state entered and based on that updates the statistics for the
state entered.

Ideally the driver enter routine should update the counters,
and it should return the state actually entered rather than the time
spent there. The generic cpuidle code should simply handle where
the counters live in the sysfs namespace, not updating the counters.

Reference:
https://lkml.org/lkml/2011/3/25/52

Signed-off-by: Deepthi Dharwar <deepthi@linux.vnet.ibm.com>
Signed-off-by: Trinabh Gupta <g.trinabh@gmail.com>
Tested-by: Jean Pihet <j-pihet@ti.com>
Reviewed-by: Kevin Hilman <khilman@ti.com>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Kevin Hilman <khilman@ti.com>
Signed-off-by: Len Brown <len.brown@intel.com>

3 files changed, 34 insertions, 18 deletions

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index d4c542372886..88bd12104396 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -62,7 +62,7 @@ int cpuidle_idle_call(void)
 {
         struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices);
         struct cpuidle_state *target_state;
-        int next_state;
+        int next_state, entered_state;
 
         if (off)
                 return -ENODEV;
@@ -102,26 +102,27 @@ int cpuidle_idle_call(void)
 
         target_state = &dev->states[next_state];
 
-        /* enter the state and update stats */
-        dev->last_state = target_state;
-
         trace_power_start(POWER_CSTATE, next_state, dev->cpu);
         trace_cpu_idle(next_state, dev->cpu);
 
-        dev->last_residency = target_state->enter(dev, target_state);
+        entered_state = target_state->enter(dev, next_state);
 
         trace_power_end(dev->cpu);
         trace_cpu_idle(PWR_EVENT_EXIT, dev->cpu);
 
-        if (dev->last_state)
-                target_state = dev->last_state;
-
-        target_state->time += (unsigned long long)dev->last_residency;
-        target_state->usage++;
+        if (entered_state >= 0) {
+                /* Update cpuidle counters */
+                /* This can be moved to within driver enter routine
+                 * but that results in multiple copies of same code.
+                 */
+                dev->states[entered_state].time +=
+                                (unsigned long long)dev->last_residency;
+                dev->states[entered_state].usage++;
+        }
 
         /* give the governor an opportunity to reflect on the outcome */
         if (cpuidle_curr_governor->reflect)
-                cpuidle_curr_governor->reflect(dev);
+                cpuidle_curr_governor->reflect(dev, entered_state);
 
         return 0;
 }
@@ -172,11 +173,10 @@ void cpuidle_resume_and_unlock(void)
 EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock);
 
 #ifdef CONFIG_ARCH_HAS_CPU_RELAX
-static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st)
+static int poll_idle(struct cpuidle_device *dev, int index)
 {
         ktime_t t1, t2;
         s64 diff;
-        int ret;
 
         t1 = ktime_get();
         local_irq_enable();
@@ -188,8 +188,9 @@ static int poll_idle(struct cpuidle_device *dev, struct cpuidle_state *st)
         if (diff > INT_MAX)
                 diff = INT_MAX;
 
-        ret = (int) diff;
-        return ret;
+        dev->last_residency = (int) diff;
+
+        return index;
 }
 
 static void poll_idle_init(struct cpuidle_device *dev)
@@ -248,7 +249,6 @@ int cpuidle_enable_device(struct cpuidle_device *dev)
                 dev->states[i].time = 0;
         }
         dev->last_residency = 0;
-        dev->last_state = NULL;
 
         smp_wmb();
 
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index 12c98900dcf8..6a686a76711f 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -153,11 +153,24 @@ static int ladder_enable_device(struct cpuidle_device *dev)
         return 0;
 }
 
+/**
+ * ladder_reflect - update the correct last_state_idx
+ * @dev: the CPU
+ * @index: the index of actual state entered
+ */
+static void ladder_reflect(struct cpuidle_device *dev, int index)
+{
+        struct ladder_device *ldev = &__get_cpu_var(ladder_devices);
+        if (index > 0)
+                ldev->last_state_idx = index;
+}
+
 static struct cpuidle_governor ladder_governor = {
         .name =         "ladder",
         .rating =       10,
         .enable =       ladder_enable_device,
         .select =       ladder_select_state,
+        .reflect =      ladder_reflect,
         .owner =        THIS_MODULE,
 };
 
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index c47f3d09c1ee..e4b200c5b441 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -310,14 +310,17 @@ static int menu_select(struct cpuidle_device *dev)
 /**
  * menu_reflect - records that data structures need update
  * @dev: the CPU
+ * @index: the index of actual entered state
  *
  * NOTE: it's important to be fast here because this operation will add to
  *       the overall exit latency.
  */
-static void menu_reflect(struct cpuidle_device *dev)
+static void menu_reflect(struct cpuidle_device *dev, int index)
 {
         struct menu_device *data = &__get_cpu_var(menu_devices);
-        data->needs_update = 1;
+        data->last_state_idx = index;
+        if (index >= 0)
+                data->needs_update = 1;
 }
 
 /**