@@ -131,7 +131,7 @@ int cpuidle_idle_call(void)
/* ask the governor for the next state */
next_state = cpuidle_curr_governor->select(drv, dev);
- if (need_resched()) {
+ if (need_resched() || (next_state < 0)) {
dev->last_residency = 0;
/* give the governor an opportunity to reflect on the outcome */
if (cpuidle_curr_governor->reflect)
@@ -58,6 +58,36 @@ static inline void ladder_do_selection(struct ladder_device *ldev,
ldev->last_state_idx = new_idx;
}
+static int can_promote(struct ladder_device *ldev, int last_idx,
+ int last_residency)
+{
+ struct ladder_device_state *last_state;
+
+ last_state = &ldev->states[last_idx];
+ if (last_residency > last_state->threshold.promotion_time) {
+ last_state->stats.promotion_count++;
+ last_state->stats.demotion_count = 0;
+ if (last_state->stats.promotion_count >= last_state->threshold.promotion_count)
+ return 1;
+ }
+ return 0;
+}
+
+static int can_demote(struct ladder_device *ldev, int last_idx,
+ int last_residency)
+{
+ struct ladder_device_state *last_state;
+
+ last_state = &ldev->states[last_idx];
+ if (last_residency < last_state->threshold.demotion_time) {
+ last_state->stats.demotion_count++;
+ last_state->stats.promotion_count = 0;
+ if (last_state->stats.demotion_count >= last_state->threshold.demotion_count)
+ return 1;
+ }
+ return 0;
+}
+
/**
* ladder_select_state - selects the next state to enter
* @drv: cpuidle driver
@@ -73,29 +103,33 @@ static int ladder_select_state(struct cpuidle_driver *drv,
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0)) {
- ladder_do_selection(ldev, last_idx, 0);
- return 0;
+ if (last_idx >= 0)
+ ladder_do_selection(ldev, last_idx, -1);
+ goto out;
}
- last_state = &ldev->states[last_idx];
-
- if (drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) {
- last_residency = cpuidle_get_last_residency(dev) - \
- drv->states[last_idx].exit_latency;
+ if (last_idx >= 0) {
+ if (drv->states[last_idx].flags & CPUIDLE_FLAG_TIME_VALID) {
+ last_residency = cpuidle_get_last_residency(dev) - \
+ drv->states[last_idx].exit_latency;
+ } else {
+ last_state = &ldev->states[last_idx];
+ last_residency = last_state->threshold.promotion_time + 1;
+ }
}
- else
- last_residency = last_state->threshold.promotion_time + 1;
/* consider promotion */
if (last_idx < drv->state_count - 1 &&
!drv->states[last_idx + 1].disabled &&
!dev->states_usage[last_idx + 1].disable &&
- last_residency > last_state->threshold.promotion_time &&
drv->states[last_idx + 1].exit_latency <= latency_req) {
- last_state->stats.promotion_count++;
- last_state->stats.demotion_count = 0;
- if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
- ladder_do_selection(ldev, last_idx, last_idx + 1);
+ if (last_idx >= 0) {
+ if (can_promote(ldev, last_idx, last_residency)) {
+ ladder_do_selection(ldev, last_idx, last_idx + 1);
+ return last_idx + 1;
+ }
+ } else {
+ ldev->last_state_idx = last_idx + 1;
return last_idx + 1;
}
}
@@ -107,26 +141,36 @@ static int ladder_select_state(struct cpuidle_driver *drv,
drv->states[last_idx].exit_latency > latency_req)) {
int i;
- for (i = last_idx - 1; i > CPUIDLE_DRIVER_STATE_START; i--) {
- if (drv->states[i].exit_latency <= latency_req)
+ for (i = last_idx - 1; i >= CPUIDLE_DRIVER_STATE_START; i--) {
+ if (drv->states[i].exit_latency <= latency_req &&
+ !(drv->states[i].disabled || dev->states_usage[i].disable))
break;
}
- ladder_do_selection(ldev, last_idx, i);
- return i;
+ if (i >= 0) {
+ ladder_do_selection(ldev, last_idx, i);
+ return i;
+ }
+ goto out;
}
- if (last_idx > CPUIDLE_DRIVER_STATE_START &&
- last_residency < last_state->threshold.demotion_time) {
- last_state->stats.demotion_count++;
- last_state->stats.promotion_count = 0;
- if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) {
- ladder_do_selection(ldev, last_idx, last_idx - 1);
- return last_idx - 1;
+ if (last_idx > CPUIDLE_DRIVER_STATE_START) {
+ int i = last_idx - 1;
+
+ if (can_demote(ldev, last_idx, last_residency) &&
+ !(drv->states[i].disabled || dev->states_usage[i].disable)) {
+ ladder_do_selection(ldev, last_idx, i);
+ return i;
}
+ /* We come here when the last_idx is still a suitable idle state,
+ * just that promotion or demotion is not ideal.
+ */
+ ldev->last_state_idx = last_idx;
+ return last_idx;
}
- /* otherwise remain at the current state */
- return last_idx;
+ /* we come here if no idle state is suitable */
+out: ldev->last_state_idx = -1;
+ return ldev->last_state_idx;
}
/**
@@ -166,7 +210,8 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
/**
* ladder_reflect - update the correct last_state_idx
* @dev: the CPU
- * @index: the index of actual state entered
+ * @index: the index of actual state entered or -1 if no idle state is
+ * suitable.
*/
static void ladder_reflect(struct cpuidle_device *dev, int index)
{
@@ -297,12 +297,12 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
data->needs_update = 0;
}
- data->last_state_idx = 0;
+ data->last_state_idx = -1;
data->exit_us = 0;
/* Special case when user has set very strict latency requirement */
if (unlikely(latency_req == 0))
- return 0;
+ return data->last_state_idx;
/* determine the expected residency time, round up */
t = ktime_to_timespec(tick_nohz_get_sleep_length());
@@ -368,7 +368,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev)
/**
* menu_reflect - records that data structures need update
* @dev: the CPU
- * @index: the index of actual entered state
+ * @index: the index of actual entered state or -1 if no idle state is
+ * suitable.
*
* NOTE: it's important to be fast here because this operation will add to
* the overall exit latency.
The cpuidle governors today are not handling scenarios where no idle state can be chosen. Such scenarios coud arise if the user has disabled all the idle states at runtime or the latency requirement from the cpus is very strict. The menu governor returns 0th index of the idle state table when no other idle state is suitable. This is even when the idle state corresponding to this index is disabled or the latency requirement is strict and the exit_latency of the lowest idle state is also not acceptable. Hence this patch fixes this logic in the menu governor by defaulting to an idle state index of -1 unless any other state is suitable. The ladder governor needs a few more fixes in addition to that required in the menu governor. When the ladder governor decides to demote the idle state of a CPU, it does not check if the lower idle states are enabled. Add this logic in addition to the logic where it chooses an index of -1 if it can neither promote or demote the idle state of a cpu nor can it choose the current idle state. The cpuidle_idle_call() will return back if the governor decides upon not entering any idle state. However it cannot return an error code because all archs have the logic today that if the call to cpuidle_idle_call() fails, it means that the cpuidle driver failed to *function*; for instance due to errors during registration. As a result they end up deciding upon a default idle state on their own, which could very well be a deep idle state. This is incorrect in cases where no idle state is suitable. Besides for the scenario that this patch is addressing, the call actually succeeds. Its just that no idle state is thought to be suitable by the governors. Under such a circumstance return success code without entering any idle state. The consequence of this patch, on the menu governor is that as long as a valid idle state cannot be chosen, the cpuidle statistics that this governor uses to predict the next idle state remain untouched from the last valid idle state. This is because an idle state is not even being predicted in this path, hence there is no point correcting the prediction either. Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com> Changes from V1:https://lkml.org/lkml/2014/1/14/26 1. Change the return code to success from -EINVAL due to the reason mentioned in the changelog. 2. Add logic that the patch is addressing in the ladder governor as well. 3. Added relevant comments and removed redundant logic as suggested in the above thread. Changes from V2:lkml.org/lkml/2014/1/16/617 1. Enable interrupts when exiting from cpuidle_idle_call() in the case when no idle state was deemed suitable by the governor. --- drivers/cpuidle/cpuidle.c | 2 - drivers/cpuidle/governors/ladder.c | 101 ++++++++++++++++++++++++++---------- drivers/cpuidle/governors/menu.c | 7 +- 3 files changed, 78 insertions(+), 32 deletions(-) -- To unsubscribe from this list: send the line "unsubscribe linux-pm" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html