The commit 0b89e9aa2856 rightfully fixed a regression by letting the couple idle state framework to handle local interrupt enabling when the cpu is exiting an idle state. The current code check if the idle state is a coupled one and, if so, it will let the couple code to enable the interrupt. This way, it can decrement the ready-count before handling the interrupts. This mechanism prevents the other cpus to wait for a cpu which is handling interrupts. But the check is done against the state index returned by the back end driver 'enter' functions which could be different from the initial index passed as parameter to the cpuidle_enter_state() function. entered_state = target_state->enter(dev, drv, index); [ ... ] if (!cpuidle_state_is_coupled(drv, entered_state)) local_irq_enable(); [ ... ] If the 'index' is referring to a coupled idle state but the 'entered_state' is *not* coupled, then the interrupts are enabled again. All cpus blocked on the sync barrier may busy loop longer if the cpu has interrupts to handle before decrementing the ready-count. Thus consuming more energy than saving. Fixes: 0b89e9aa2856 "cpuidle: delay enabling interrupts until all coupled CPUs leave idle" Cc: stable@xxxxxxxxxxxxxxx Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx> --- drivers/cpuidle/cpuidle.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index f996efc..cd021ed 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -214,7 +214,7 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, tick_broadcast_exit(); } - if (!cpuidle_state_is_coupled(drv, entered_state)) + if (!cpuidle_state_is_coupled(drv, index)) local_irq_enable(); diff = ktime_to_us(ktime_sub(time_end, time_start)); -- 1.9.1 -- To unsubscribe from this list: send the line "unsubscribe stable" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html