From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752547AbaBYIJp (ORCPT ); Tue, 25 Feb 2014 03:09:45 -0500 Received: from mail-wg0-f51.google.com ([74.125.82.51]:50742 "EHLO mail-wg0-f51.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751500AbaBYII7 (ORCPT ); Tue, 25 Feb 2014 03:08:59 -0500 From: Daniel Lezcano To: mingo@kernel.org, peterz@infradead.org, tglx@linutronix.de, rjw@rjwysocki.net Cc: nicolas.pitre@linaro.org, preeti@linux.vnet.ibm.com, linux-kernel@vger.kernel.org Subject: [PATCH V3 4/5] idle: Move idle conditions in cpuidle_idle main function Date: Tue, 25 Feb 2014 09:08:52 +0100 Message-Id: <1393315733-32321-4-git-send-email-daniel.lezcano@linaro.org> X-Mailer: git-send-email 1.7.9.5 In-Reply-To: <1393315733-32321-1-git-send-email-daniel.lezcano@linaro.org> References: <1393315733-32321-1-git-send-email-daniel.lezcano@linaro.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org This patch moves the condition before entering idle into the cpuidle main function located in idle.c. That simplify the idle mainloop functions and increase the readibility of the conditions to enter truly idle. This patch is code reorganization and does not change the behavior of the function. Signed-off-by: Daniel Lezcano Cc: Peter Zijlstra --- V3: * reorganized cpuidle_idle_call function as Suggested by Peter Zijlstra https://lkml.org/lkml/2014/2/24/492 --- kernel/sched/idle.c | 85 ++++++++++++++++++++++++++++------------------------ 1 file changed, 46 insertions(+), 39 deletions(-) Index: cpuidle-next/kernel/sched/idle.c =================================================================== --- cpuidle-next.orig/kernel/sched/idle.c +++ cpuidle-next/kernel/sched/idle.c @@ -73,46 +73,58 @@ static int cpuidle_idle_call(void) { struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); - int next_state, entered_state, ret; + int next_state, entered_state; bool broadcast; - stop_critical_timings(); - rcu_idle_enter(); - - ret = cpuidle_enabled(drv, dev); - if (ret < 0) { - arch_cpu_idle(); - goto out; - } - - /* ask the governor for the next state */ - next_state = cpuidle_select(drv, dev); - - if (need_resched()) { - dev->last_residency = 0; - /* give the governor an opportunity to reflect on the outcome */ - cpuidle_reflect(dev, next_state); + if (current_clr_polling_and_test()) { local_irq_enable(); - goto out; + __current_set_polling(); + return 0; } - trace_cpu_idle_rcuidle(next_state, dev->cpu); + stop_critical_timings(); + rcu_idle_enter(); - broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP); + if (cpuidle_enabled(drv, dev) == 0) { - if (broadcast) - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu); + /* ask the governor for the next state */ + next_state = cpuidle_select(drv, dev); - entered_state = cpuidle_enter(drv, dev, next_state); + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + entered_state = next_state; + local_irq_enable(); + } else { + trace_cpu_idle_rcuidle(next_state, dev->cpu); + + broadcast = !!(drv->states[next_state].flags & + CPUIDLE_FLAG_TIMER_STOP); + + if (broadcast) + clockevents_notify( + CLOCK_EVT_NOTIFY_BROADCAST_ENTER, + &dev->cpu); + + entered_state = cpuidle_enter(drv, dev, next_state); + + if (broadcast) + clockevents_notify( + CLOCK_EVT_NOTIFY_BROADCAST_EXIT, + &dev->cpu); - if (broadcast) - clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + } - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + /* give the governor an opportunity to reflect on the outcome */ + cpuidle_reflect(dev, next_state); + } else { + if (current_clr_polling_and_test()) + local_irq_enable(); + else + arch_cpu_idle(); + } + __current_set_polling(); - /* give the governor an opportunity to reflect on the outcome */ - cpuidle_reflect(dev, entered_state); -out: if (WARN_ON_ONCE(irqs_disabled())) local_irq_enable(); @@ -139,7 +151,7 @@ static void cpu_idle_loop(void) local_irq_disable(); arch_cpu_idle_enter(); - + /* * In poll mode we reenable interrupts and spin. * @@ -149,16 +161,11 @@ static void cpu_idle_loop(void) * know that the IPI is going to arrive right * away */ - if (cpu_idle_force_poll || tick_check_broadcast_expired()) { + if (cpu_idle_force_poll || tick_check_broadcast_expired()) cpu_idle_poll(); - } else { - if (!current_clr_polling_and_test()) { - cpuidle_idle_call(); - } else { - local_irq_enable(); - } - __current_set_polling(); - } + else + cpuidle_idle_call(); + arch_cpu_idle_exit(); /* * We need to test and propagate the TIF_NEED_RESCHED