Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next

Pull scheduler updates from Ingo Molnar:
 "The main scheduling related changes in this cycle were:

   - various sched/numa updates, for better performance

   - tree wide cleanup of open coded nice levels

   - nohz fix related to rq->nr_running use

   - cpuidle changes and continued consolidation to improve the
     kernel/sched/idle.c high level idle scheduling logic.  As part of
     this effort I pulled cpuidle driver changes from Rafael as well.

   - standardized idle polling amongst architectures

   - continued work on preparing better power/energy aware scheduling

   - sched/rt updates

   - misc fixlets and cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
  sched/numa: Decay ->wakee_flips instead of zeroing
  sched/numa: Update migrate_improves/degrades_locality()
  sched/numa: Allow task switch if load imbalance improves
  sched/rt: Fix 'struct sched_dl_entity' and dl_task_time() comments, to match the current upstream code
  sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice()
  sched: Initialize rq->age_stamp on processor start
  sched, nohz: Change rq->nr_running to always use wrappers
  sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance()
  sched: Use clamp() and clamp_val() to make sys_nice() more readable
  sched: Do not zero sg->cpumask and sg->sgp->power in build_sched_groups()
  sched/numa: Fix initialization of sched_domain_topology for NUMA
  sched: Call select_idle_sibling() when not affine_sd
  sched: Simplify return logic in sched_read_attr()
  sched: Simplify return logic in sched_copy_attr()
  sched: Fix exec_start/task_hot on migrated tasks
  arm64: Remove TIF_POLLING_NRFLAG
  metag: Remove TIF_POLLING_NRFLAG
  sched/idle: Make cpuidle_idle_call() void
  sched/idle: Reflow cpuidle_idle_call()
  sched/idle: Delay clearing the polling bit
  ...

1 files changed, 60 insertions, 80 deletions

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f4390a079c7..25b9423abce9 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -67,24 +67,21 @@ void __weak arch_cpu_idle(void)
  * cpuidle_idle_call - the main idle function
  *
  * NOTE: no locks or semaphores should be used here
- * return non-zero on failure
  */
-static int cpuidle_idle_call(void)
+static void 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;
 
 	/*
 	 * Check if the idle task must be rescheduled. If it is the
-	 * case, exit the function after re-enabling the local irq and
-	 * set again the polling flag
+	 * case, exit the function after re-enabling the local irq.
 	 */
-	if (current_clr_polling_and_test()) {
+	if (need_resched()) {
 		local_irq_enable();
-		__current_set_polling();
-		return 0;
+		return;
 	}
 
 	/*
@@ -101,96 +98,79 @@ static int cpuidle_idle_call(void)
 	rcu_idle_enter();
 
 	/*
-	 * Check if the cpuidle framework is ready, otherwise fallback
-	 * to the default arch specific idle method
+	 * Ask the cpuidle framework to choose a convenient idle state.
+	 * Fall back to the default arch idle method on errors.
 	 */
-	ret = cpuidle_enabled(drv, dev);
-
-	if (!ret) {
+	next_state = cpuidle_select(drv, dev);
+	if (next_state < 0) {
+use_default:
 		/*
-		 * Ask the governor to choose an idle state it thinks
-		 * it is convenient to go to. There is *always* a
-		 * convenient idle state
+		 * We can't use the cpuidle framework, let's use the default
+		 * idle routine.
 		 */
-		next_state = cpuidle_select(drv, dev);
-
-		/*
-		 * The idle task must be scheduled, it is pointless to
-		 * go to idle, just update no idle residency and get
-		 * out of this function
-		 */
-		if (current_clr_polling_and_test()) {
-			dev->last_residency = 0;
-			entered_state = next_state;
+		if (current_clr_polling_and_test())
 			local_irq_enable();
-		} else {
-			broadcast = !!(drv->states[next_state].flags &
-				       CPUIDLE_FLAG_TIMER_STOP);
-
-			if (broadcast)
-				/*
-				 * Tell the time framework to switch
-				 * to a broadcast timer because our
-				 * local timer will be shutdown. If a
-				 * local timer is used from another
-				 * cpu as a broadcast timer, this call
-				 * may fail if it is not available
-				 */
-				ret = clockevents_notify(
-					CLOCK_EVT_NOTIFY_BROADCAST_ENTER,
-					&dev->cpu);
-
-			if (!ret) {
-				trace_cpu_idle_rcuidle(next_state, dev->cpu);
-
-				/*
-				 * Enter the idle state previously
-				 * returned by the governor
-				 * decision. This function will block
-				 * until an interrupt occurs and will
-				 * take care of re-enabling the local
-				 * interrupts
-				 */
-				entered_state = cpuidle_enter(drv, dev,
-							      next_state);
-
-				trace_cpu_idle_rcuidle(PWR_EVENT_EXIT,
-						       dev->cpu);
-
-				if (broadcast)
-					clockevents_notify(
-						CLOCK_EVT_NOTIFY_BROADCAST_EXIT,
-						&dev->cpu);
-
-				/*
-				 * Give the governor an opportunity to reflect on the
-				 * outcome
-				 */
-				cpuidle_reflect(dev, entered_state);
-			}
-		}
+		else
+			arch_cpu_idle();
+
+		goto exit_idle;
 	}
 
+
 	/*
-	 * We can't use the cpuidle framework, let's use the default
-	 * idle routine
+	 * The idle task must be scheduled, it is pointless to
+	 * go to idle, just update no idle residency and get
+	 * out of this function
 	 */
-	if (ret)
-		arch_cpu_idle();
+	if (current_clr_polling_and_test()) {
+		dev->last_residency = 0;
+		entered_state = next_state;
+		local_irq_enable();
+		goto exit_idle;
+	}
+
+	broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP);
 
+	/*
+	 * Tell the time framework to switch to a broadcast timer
+	 * because our local timer will be shutdown. If a local timer
+	 * is used from another cpu as a broadcast timer, this call may
+	 * fail if it is not available
+	 */
+	if (broadcast &&
+	    clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu))
+		goto use_default;
+
+	trace_cpu_idle_rcuidle(next_state, dev->cpu);
+
+	/*
+	 * Enter the idle state previously returned by the governor decision.
+	 * This function will block until an interrupt occurs and will take
+	 * care of re-enabling the local interrupts
+	 */
+	entered_state = cpuidle_enter(drv, dev, next_state);
+
+	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu);
+
+	if (broadcast)
+		clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu);
+
+	/*
+	 * Give the governor an opportunity to reflect on the outcome
+	 */
+	cpuidle_reflect(dev, entered_state);
+
+exit_idle:
 	__current_set_polling();
 
 	/*
-	 * It is up to the idle functions to enable back the local
-	 * interrupt
+	 * It is up to the idle functions to reenable local interrupts
 	 */
 	if (WARN_ON_ONCE(irqs_disabled()))
 		local_irq_enable();
 
 	rcu_idle_exit();
 	start_critical_timings();
-
-	return 0;
 }
 
 /*