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

Pull scheduler updates from Ingo Molnar:
 "The biggest change in this cycle is the rewrite of the main SMP load
  balancing metric: the CPU load/utilization.  The main goal was to make
  the metric more precise and more representative - see the changelog of
  this commit for the gory details:

    9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking")

  It is done in a way that significantly reduces complexity of the code:

    5 files changed, 249 insertions(+), 494 deletions(-)

  and the performance testing results are encouraging.  Nevertheless we
  need to keep an eye on potential regressions, since this potentially
  affects every SMP workload in existence.

  This work comes from Yuyang Du.

  Other changes:

   - SCHED_DL updates.  (Andrea Parri)

   - Simplify architecture callbacks by removing finish_arch_switch().
     (Peter Zijlstra et al)

   - cputime accounting: guarantee stime + utime == rtime.  (Peter
     Zijlstra)

   - optimize idle CPU wakeups some more - inspired by Facebook server
     loads.  (Mike Galbraith)

   - stop_machine fixes and updates.  (Oleg Nesterov)

   - Introduce the 'trace_sched_waking' tracepoint.  (Peter Zijlstra)

   - sched/numa tweaks.  (Srikar Dronamraju)

   - misc fixes and small cleanups"

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  sched/deadline: Fix comment in enqueue_task_dl()
  sched/deadline: Fix comment in push_dl_tasks()
  sched: Change the sched_class::set_cpus_allowed() calling context
  sched: Make sched_class::set_cpus_allowed() unconditional
  sched: Fix a race between __kthread_bind() and sched_setaffinity()
  sched: Ensure a task has a non-normalized vruntime when returning back to CFS
  sched/numa: Fix NUMA_DIRECT topology identification
  tile: Reorganize _switch_to()
  sched, sparc32: Update scheduler comments in copy_thread()
  sched: Remove finish_arch_switch()
  sched, tile: Remove finish_arch_switch
  sched, sh: Fold finish_arch_switch() into switch_to()
  sched, score: Remove finish_arch_switch()
  sched, avr32: Remove finish_arch_switch()
  sched, MIPS: Get rid of finish_arch_switch()
  sched, arm: Remove finish_arch_switch()
  sched/fair: Clean up load average references
  sched/fair: Provide runnable_load_avg back to cfs_rq
  sched/fair: Remove task and group entity load when they are dead
  sched/fair: Init cfs_rq's sched_entity load average
  ...

1 files changed, 79 insertions, 22 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5e73c79fadd0..a585c7b2ccf0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1151,15 +1151,45 @@ static int migration_cpu_stop(void *data)
 	return 0;
 }
 
-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+/*
+ * sched_class::set_cpus_allowed must do the below, but is not required to
+ * actually call this function.
+ */
+void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
 {
-	if (p->sched_class->set_cpus_allowed)
-		p->sched_class->set_cpus_allowed(p, new_mask);
-
 	cpumask_copy(&p->cpus_allowed, new_mask);
 	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+	struct rq *rq = task_rq(p);
+	bool queued, running;
+
+	lockdep_assert_held(&p->pi_lock);
+
+	queued = task_on_rq_queued(p);
+	running = task_current(rq, p);
+
+	if (queued) {
+		/*
+		 * Because __kthread_bind() calls this on blocked tasks without
+		 * holding rq->lock.
+		 */
+		lockdep_assert_held(&rq->lock);
+		dequeue_task(rq, p, 0);
+	}
+	if (running)
+		put_prev_task(rq, p);
+
+	p->sched_class->set_cpus_allowed(p, new_mask);
+
+	if (running)
+		p->sched_class->set_curr_task(rq);
+	if (queued)
+		enqueue_task(rq, p, 0);
+}
+
 /*
  * Change a given task's CPU affinity. Migrate the thread to a
  * proper CPU and schedule it away if the CPU it's executing on
@@ -1169,7 +1199,8 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
  * task must not exit() & deallocate itself prematurely. The
  * call is not atomic; no spinlocks may be held.
  */
-int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+static int __set_cpus_allowed_ptr(struct task_struct *p,
+				  const struct cpumask *new_mask, bool check)
 {
 	unsigned long flags;
 	struct rq *rq;
@@ -1178,6 +1209,15 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 
 	rq = task_rq_lock(p, &flags);
 
+	/*
+	 * Must re-check here, to close a race against __kthread_bind(),
+	 * sched_setaffinity() is not guaranteed to observe the flag.
+	 */
+	if (check && (p->flags & PF_NO_SETAFFINITY)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (cpumask_equal(&p->cpus_allowed, new_mask))
 		goto out;
 
@@ -1214,6 +1254,11 @@ out:
 
 	return ret;
 }
+
+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
+{
+	return __set_cpus_allowed_ptr(p, new_mask, false);
+}
 EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
 
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
@@ -1595,6 +1640,15 @@ static void update_avg(u64 *avg, u64 sample)
 	s64 diff = sample - *avg;
 	*avg += diff >> 3;
 }
+
+#else
+
+static inline int __set_cpus_allowed_ptr(struct task_struct *p,
+					 const struct cpumask *new_mask, bool check)
+{
+	return set_cpus_allowed_ptr(p, new_mask);
+}
+
 #endif /* CONFIG_SMP */
 
 static void
@@ -1654,9 +1708,9 @@ static void
 ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
 	check_preempt_curr(rq, p, wake_flags);
-	trace_sched_wakeup(p, true);
-
 	p->state = TASK_RUNNING;
+	trace_sched_wakeup(p);
+
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
@@ -1874,6 +1928,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	if (!(p->state & state))
 		goto out;
 
+	trace_sched_waking(p);
+
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
 
@@ -1949,6 +2005,8 @@ static void try_to_wake_up_local(struct task_struct *p)
 	if (!(p->state & TASK_NORMAL))
 		goto out;
 
+	trace_sched_waking(p);
+
 	if (!task_on_rq_queued(p))
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
 
@@ -2016,9 +2074,6 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.prev_sum_exec_runtime	= 0;
 	p->se.nr_migrations		= 0;
 	p->se.vruntime			= 0;
-#ifdef CONFIG_SMP
-	p->se.avg.decay_count		= 0;
-#endif
 	INIT_LIST_HEAD(&p->se.group_node);
 
 #ifdef CONFIG_SCHEDSTATS
@@ -2303,11 +2358,11 @@ void wake_up_new_task(struct task_struct *p)
 #endif
 
 	/* Initialize new task's runnable average */
-	init_task_runnable_average(p);
+	init_entity_runnable_average(&p->se);
 	rq = __task_rq_lock(p);
 	activate_task(rq, p, 0);
 	p->on_rq = TASK_ON_RQ_QUEUED;
-	trace_sched_wakeup_new(p, true);
+	trace_sched_wakeup_new(p);
 	check_preempt_curr(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken)
@@ -2469,7 +2524,6 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
-	finish_arch_switch(prev);
 	perf_event_task_sched_in(prev, current);
 	finish_lock_switch(rq, prev);
 	finish_arch_post_lock_switch();
@@ -4340,7 +4394,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	}
 #endif
 again:
-	retval = set_cpus_allowed_ptr(p, new_mask);
+	retval = __set_cpus_allowed_ptr(p, new_mask, true);
 
 	if (!retval) {
 		cpuset_cpus_allowed(p, cpus_allowed);
@@ -4492,7 +4546,7 @@ SYSCALL_DEFINE0(sched_yield)
 
 int __sched _cond_resched(void)
 {
-	if (should_resched()) {
+	if (should_resched(0)) {
 		preempt_schedule_common();
 		return 1;
 	}
@@ -4510,7 +4564,7 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	int resched = should_resched();
+	int resched = should_resched(PREEMPT_LOCK_OFFSET);
 	int ret = 0;
 
 	lockdep_assert_held(lock);
@@ -4532,7 +4586,7 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (should_resched()) {
+	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
 		local_bh_enable();
 		preempt_schedule_common();
 		local_bh_disable();
@@ -4865,7 +4919,8 @@ void init_idle(struct task_struct *idle, int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	raw_spin_lock_irqsave(&idle->pi_lock, flags);
+	raw_spin_lock(&rq->lock);
 
 	__sched_fork(0, idle);
 	idle->state = TASK_RUNNING;
@@ -4891,7 +4946,8 @@ void init_idle(struct task_struct *idle, int cpu)
 #if defined(CONFIG_SMP)
 	idle->on_cpu = 1;
 #endif
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_unlock(&rq->lock);
+	raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
 	init_idle_preempt_count(idle, cpu);
@@ -5311,8 +5367,7 @@ static void register_sched_domain_sysctl(void)
 /* may be called multiple times per register */
 static void unregister_sched_domain_sysctl(void)
 {
-	if (sd_sysctl_header)
-		unregister_sysctl_table(sd_sysctl_header);
+	unregister_sysctl_table(sd_sysctl_header);
 	sd_sysctl_header = NULL;
 	if (sd_ctl_dir[0].child)
 		sd_free_ctl_entry(&sd_ctl_dir[0].child);
@@ -6445,8 +6500,10 @@ static void init_numa_topology_type(void)
 
 	n = sched_max_numa_distance;
 
-	if (n <= 1)
+	if (sched_domains_numa_levels <= 1) {
 		sched_numa_topology_type = NUMA_DIRECT;
+		return;
+	}
 
 	for_each_online_node(a) {
 		for_each_online_node(b) {