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

Pull scheduler updates from Ingo Molnar:

 - introduce and use task_rcu_dereference()/try_get_task_struct() to fix
   and generalize task_struct handling (Oleg Nesterov)

 - do various per entity load tracking (PELT) fixes and optimizations
   (Peter Zijlstra)

 - cputime virt-steal time accounting enhancements/fixes (Wanpeng Li)

 - introduce consolidated cputime output file cpuacct.usage_all and
   related refactorings (Zhao Lei)

 - ... plus misc fixes and enhancements

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/core: Panic on scheduling while atomic bugs if kernel.panic_on_warn is set
  sched/cpuacct: Introduce cpuacct.usage_all to show all CPU stats together
  sched/cpuacct: Use loop to consolidate code in cpuacct_stats_show()
  sched/cpuacct: Merge cpuacct_usage_index and cpuacct_stat_index enums
  sched/fair: Rework throttle_count sync
  sched/core: Fix sched_getaffinity() return value kerneldoc comment
  sched/fair: Reorder cgroup creation code
  sched/fair: Apply more PELT fixes
  sched/fair: Fix PELT integrity for new tasks
  sched/cgroup: Fix cpu_cgroup_fork() handling
  sched/fair: Fix PELT integrity for new groups
  sched/fair: Fix and optimize the fork() path
  sched/cputime: Add steal time support to full dynticks CPU time accounting
  sched/cputime: Fix prev steal time accouting during CPU hotplug
  KVM: Fix steal clock warp during guest CPU hotplug
  sched/debug: Always show 'nr_migrations'
  sched/fair: Use task_rcu_dereference()
  sched/api: Introduce task_rcu_dereference() and try_get_task_struct()
  sched/idle: Optimize the generic idle loop
  sched/fair: Fix the wrong throttled clock time for cfs_rq_clock_task()

1 files changed, 81 insertions, 33 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index af0ef74df23c..5c883fe8e440 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2342,11 +2342,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	__sched_fork(clone_flags, p);
 	/*
-	 * We mark the process as running here. This guarantees that
+	 * We mark the process as NEW here. This guarantees that
 	 * nobody will actually run it, and a signal or other external
 	 * event cannot wake it up and insert it on the runqueue either.
 	 */
-	p->state = TASK_RUNNING;
+	p->state = TASK_NEW;
 
 	/*
 	 * Make sure we do not leak PI boosting priority to the child.
@@ -2383,8 +2383,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_class = &fair_sched_class;
 	}
 
-	if (p->sched_class->task_fork)
-		p->sched_class->task_fork(p);
+	init_entity_runnable_average(&p->se);
 
 	/*
 	 * The child is not yet in the pid-hash so no cgroup attach races,
@@ -2394,7 +2393,13 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * Silence PROVE_RCU.
 	 */
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	set_task_cpu(p, cpu);
+	/*
+	 * We're setting the cpu for the first time, we don't migrate,
+	 * so use __set_task_cpu().
+	 */
+	__set_task_cpu(p, cpu);
+	if (p->sched_class->task_fork)
+		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 #ifdef CONFIG_SCHED_INFO
@@ -2526,16 +2531,18 @@ void wake_up_new_task(struct task_struct *p)
 	struct rq_flags rf;
 	struct rq *rq;
 
-	/* Initialize new task's runnable average */
-	init_entity_runnable_average(&p->se);
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
+	p->state = TASK_RUNNING;
 #ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_allowed can change in the fork path
 	 *  - any previously selected cpu might disappear through hotplug
+	 *
+	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
+	 * as we're not fully set-up yet.
 	 */
-	set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
+	__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
 #endif
 	rq = __task_rq_lock(p, &rf);
 	post_init_entity_util_avg(&p->se);
@@ -3161,6 +3168,9 @@ static noinline void __schedule_bug(struct task_struct *prev)
 		pr_cont("\n");
 	}
 #endif
+	if (panic_on_warn)
+		panic("scheduling while atomic\n");
+
 	dump_stack();
 	add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
 }
@@ -4752,7 +4762,8 @@ out_unlock:
  * @len: length in bytes of the bitmask pointed to by user_mask_ptr
  * @user_mask_ptr: user-space pointer to hold the current cpu mask
  *
- * Return: 0 on success. An error code otherwise.
+ * Return: size of CPU mask copied to user_mask_ptr on success. An
+ * error code otherwise.
  */
 SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
 		unsigned long __user *, user_mask_ptr)
@@ -7233,7 +7244,6 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 
 	rq->calc_load_update = calc_load_update;
-	account_reset_rq(rq);
 	update_max_interval();
 }
 
@@ -7713,6 +7723,8 @@ void sched_online_group(struct task_group *tg, struct task_group *parent)
 	INIT_LIST_HEAD(&tg->children);
 	list_add_rcu(&tg->siblings, &parent->children);
 	spin_unlock_irqrestore(&task_group_lock, flags);
+
+	online_fair_sched_group(tg);
 }
 
 /* rcu callback to free various structures associated with a task group */
@@ -7741,27 +7753,9 @@ void sched_offline_group(struct task_group *tg)
 	spin_unlock_irqrestore(&task_group_lock, flags);
 }
 
-/* change task's runqueue when it moves between groups.
- *	The caller of this function should have put the task in its new group
- *	by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to
- *	reflect its new group.
- */
-void sched_move_task(struct task_struct *tsk)
+static void sched_change_group(struct task_struct *tsk, int type)
 {
 	struct task_group *tg;
-	int queued, running;
-	struct rq_flags rf;
-	struct rq *rq;
-
-	rq = task_rq_lock(tsk, &rf);
-
-	running = task_current(rq, tsk);
-	queued = task_on_rq_queued(tsk);
-
-	if (queued)
-		dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
-	if (unlikely(running))
-		put_prev_task(rq, tsk);
 
 	/*
 	 * All callers are synchronized by task_rq_lock(); we do not use RCU
@@ -7774,11 +7768,37 @@ void sched_move_task(struct task_struct *tsk)
 	tsk->sched_task_group = tg;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	if (tsk->sched_class->task_move_group)
-		tsk->sched_class->task_move_group(tsk);
+	if (tsk->sched_class->task_change_group)
+		tsk->sched_class->task_change_group(tsk, type);
 	else
 #endif
 		set_task_rq(tsk, task_cpu(tsk));
+}
+
+/*
+ * Change task's runqueue when it moves between groups.
+ *
+ * The caller of this function should have put the task in its new group by
+ * now. This function just updates tsk->se.cfs_rq and tsk->se.parent to reflect
+ * its new group.
+ */
+void sched_move_task(struct task_struct *tsk)
+{
+	int queued, running;
+	struct rq_flags rf;
+	struct rq *rq;
+
+	rq = task_rq_lock(tsk, &rf);
+
+	running = task_current(rq, tsk);
+	queued = task_on_rq_queued(tsk);
+
+	if (queued)
+		dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE);
+	if (unlikely(running))
+		put_prev_task(rq, tsk);
+
+	sched_change_group(tsk, TASK_MOVE_GROUP);
 
 	if (unlikely(running))
 		tsk->sched_class->set_curr_task(rq);
@@ -8206,15 +8226,27 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 	sched_free_group(tg);
 }
 
+/*
+ * This is called before wake_up_new_task(), therefore we really only
+ * have to set its group bits, all the other stuff does not apply.
+ */
 static void cpu_cgroup_fork(struct task_struct *task)
 {
-	sched_move_task(task);
+	struct rq_flags rf;
+	struct rq *rq;
+
+	rq = task_rq_lock(task, &rf);
+
+	sched_change_group(task, TASK_SET_GROUP);
+
+	task_rq_unlock(rq, task, &rf);
 }
 
 static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 {
 	struct task_struct *task;
 	struct cgroup_subsys_state *css;
+	int ret = 0;
 
 	cgroup_taskset_for_each(task, css, tset) {
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -8225,8 +8257,24 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 		if (task->sched_class != &fair_sched_class)
 			return -EINVAL;
 #endif
+		/*
+		 * Serialize against wake_up_new_task() such that if its
+		 * running, we're sure to observe its full state.
+		 */
+		raw_spin_lock_irq(&task->pi_lock);
+		/*
+		 * Avoid calling sched_move_task() before wake_up_new_task()
+		 * has happened. This would lead to problems with PELT, due to
+		 * move wanting to detach+attach while we're not attached yet.
+		 */
+		if (task->state == TASK_NEW)
+			ret = -EINVAL;
+		raw_spin_unlock_irq(&task->pi_lock);
+
+		if (ret)
+			break;
 	}
-	return 0;
+	return ret;
 }
 
 static void cpu_cgroup_attach(struct cgroup_taskset *tset)