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>

1 files changed, 49 insertions, 26 deletions

diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c
index 431ab11..9cd08ce 100644
--- a/drivers/acpi/processor_idle.c
+++ b/drivers/acpi/processor_idle.c
@@ -741,22 +741,24 @@ static inline void acpi_idle_do_entry(struct acpi_processor_cx *cx)
 /**
  * acpi_idle_enter_c1 - enters an ACPI C1 state-type
  * @dev: the target CPU
- * @state: the state data
+ * @index: index of target state
  *
  * This is equivalent to the HALT instruction.
  */
 static int acpi_idle_enter_c1(struct cpuidle_device *dev,
-			      struct cpuidle_state *state)
+				int index)
 {
 	ktime_t  kt1, kt2;
 	s64 idle_time;
 	struct acpi_processor *pr;
+	struct cpuidle_state *state = &dev->states[index];
 	struct acpi_processor_cx *cx = cpuidle_get_statedata(state);
 
 	pr = __this_cpu_read(processors);
+	dev->last_residency = 0;
 
 	if (unlikely(!pr))
-		return 0;
+		return -EINVAL;
 
 	local_irq_disable();
 
@@ -764,7 +766,7 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	if (acpi_idle_suspend) {
 		local_irq_enable();
 		cpu_relax();
-		return 0;
+		return -EINVAL;
 	}
 
 	lapic_timer_state_broadcast(pr, cx, 1);
@@ -773,37 +775,46 @@ static int acpi_idle_enter_c1(struct cpuidle_device *dev,
 	kt2 = ktime_get_real();
 	idle_time =  ktime_to_us(ktime_sub(kt2, kt1));
 
+	/* Update device last_residency*/
+	dev->last_residency = (int)idle_time;
+
 	local_irq_enable();
 	cx->usage++;
 	lapic_timer_state_broadcast(pr, cx, 0);
 
-	return idle_time;
+	return index;
 }
 
 /**
  * acpi_idle_enter_simple - enters an ACPI state without BM handling
  * @dev: the target CPU
- * @state: the state data
+ * @index: the index of suggested state
  */
 static int acpi_idle_enter_simple(struct cpuidle_device *dev,
-				  struct cpuidle_state *state)
+				int index)
 {
 	struct acpi_processor *pr;
+	struct cpuidle_state *state = &dev->states[index];
 	struct acpi_processor_cx *cx = cpuidle_get_statedata(state);
 	ktime_t  kt1, kt2;
 	s64 idle_time_ns;
 	s64 idle_time;
 
 	pr = __this_cpu_read(processors);
+	dev->last_residency = 0;
 
 	if (unlikely(!pr))
-		return 0;
-
-	if (acpi_idle_suspend)
-		return(acpi_idle_enter_c1(dev, state));
+		return -EINVAL;
 
 	local_irq_disable();
 
+	if (acpi_idle_suspend) {
+		local_irq_enable();
+		cpu_relax();
+		return -EINVAL;
+	}
+
+
 	if (cx->entry_method != ACPI_CSTATE_FFH) {
 		current_thread_info()->status &= ~TS_POLLING;
 		/*
@@ -815,7 +826,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 		if (unlikely(need_resched())) {
 			current_thread_info()->status |= TS_POLLING;
 			local_irq_enable();
-			return 0;
+			return -EINVAL;
 		}
 	}
 
@@ -837,6 +848,9 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 	idle_time = idle_time_ns;
 	do_div(idle_time, NSEC_PER_USEC);
 
+	/* Update device last_residency*/
+	dev->last_residency = (int)idle_time;
+
 	/* Tell the scheduler how much we idled: */
 	sched_clock_idle_wakeup_event(idle_time_ns);
 
@@ -848,7 +862,7 @@ static int acpi_idle_enter_simple(struct cpuidle_device *dev,
 
 	lapic_timer_state_broadcast(pr, cx, 0);
 	cx->time += idle_time;
-	return idle_time;
+	return index;
 }
 
 static int c3_cpu_count;
@@ -857,14 +871,15 @@ static DEFINE_SPINLOCK(c3_lock);
 /**
  * acpi_idle_enter_bm - enters C3 with proper BM handling
  * @dev: the target CPU
- * @state: the state data
+ * @index: the index of suggested state
  *
  * If BM is detected, the deepest non-C3 idle state is entered instead.
  */
 static int acpi_idle_enter_bm(struct cpuidle_device *dev,
-			      struct cpuidle_state *state)
+				int index)
 {
 	struct acpi_processor *pr;
+	struct cpuidle_state *state = &dev->states[index];
 	struct acpi_processor_cx *cx = cpuidle_get_statedata(state);
 	ktime_t  kt1, kt2;
 	s64 idle_time_ns;
@@ -872,22 +887,26 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 
 
 	pr = __this_cpu_read(processors);
+	dev->last_residency = 0;
 
 	if (unlikely(!pr))
-		return 0;
+		return -EINVAL;
 
-	if (acpi_idle_suspend)
-		return(acpi_idle_enter_c1(dev, state));
+
+	if (acpi_idle_suspend) {
+		cpu_relax();
+		return -EINVAL;
+	}
 
 	if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
-		if (dev->safe_state) {
-			dev->last_state = dev->safe_state;
-			return dev->safe_state->enter(dev, dev->safe_state);
+		if (dev->safe_state_index >= 0) {
+			return dev->states[dev->safe_state_index].enter(dev,
+						dev->safe_state_index);
 		} else {
 			local_irq_disable();
 			acpi_safe_halt();
 			local_irq_enable();
-			return 0;
+			return -EINVAL;
 		}
 	}
 
@@ -904,7 +923,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 		if (unlikely(need_resched())) {
 			current_thread_info()->status |= TS_POLLING;
 			local_irq_enable();
-			return 0;
+			return -EINVAL;
 		}
 	}
 
@@ -954,6 +973,9 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 	idle_time = idle_time_ns;
 	do_div(idle_time, NSEC_PER_USEC);
 
+	/* Update device last_residency*/
+	dev->last_residency = (int)idle_time;
+
 	/* Tell the scheduler how much we idled: */
 	sched_clock_idle_wakeup_event(idle_time_ns);
 
@@ -965,7 +987,7 @@ static int acpi_idle_enter_bm(struct cpuidle_device *dev,
 
 	lapic_timer_state_broadcast(pr, cx, 0);
 	cx->time += idle_time;
-	return idle_time;
+	return index;
 }
 
 struct cpuidle_driver acpi_idle_driver = {
@@ -992,6 +1014,7 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
 	}
 
 	dev->cpu = pr->id;
+	dev->safe_state_index = -1;
 	for (i = 0; i < CPUIDLE_STATE_MAX; i++) {
 		dev->states[i].name[0] = '\0';
 		dev->states[i].desc[0] = '\0';
@@ -1027,13 +1050,13 @@ static int acpi_processor_setup_cpuidle(struct acpi_processor *pr)
 				state->flags |= CPUIDLE_FLAG_TIME_VALID;
 
 			state->enter = acpi_idle_enter_c1;
-			dev->safe_state = state;
+			dev->safe_state_index = count;
 			break;
 
 			case ACPI_STATE_C2:
 			state->flags |= CPUIDLE_FLAG_TIME_VALID;
 			state->enter = acpi_idle_enter_simple;
-			dev->safe_state = state;
+			dev->safe_state_index = count;
 			break;
 
 			case ACPI_STATE_C3: