Merge tag 'sched-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Debuggability:

   - Change most occurances of BUG_ON() to WARN_ON_ONCE()

   - Reorganize & fix TASK_ state comparisons, turn it into a bitmap

   - Update/fix misc scheduler debugging facilities

  Load-balancing & regular scheduling:

   - Improve the behavior of the scheduler in presence of lot of
     SCHED_IDLE tasks - in particular they should not impact other
     scheduling classes.

   - Optimize task load tracking, cleanups & fixes

   - Clean up & simplify misc load-balancing code

  Freezer:

   - Rewrite the core freezer to behave better wrt thawing and be
     simpler in general, by replacing PF_FROZEN with TASK_FROZEN &
     fixing/adjusting all the fallout.

  Deadline scheduler:

   - Fix the DL capacity-aware code

   - Factor out dl_task_is_earliest_deadline() &
     replenish_dl_new_period()

   - Relax/optimize locking in task_non_contending()

  Cleanups:

   - Factor out the update_current_exec_runtime() helper

   - Various cleanups, simplifications"

* tag 'sched-core-2022-10-07' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  sched: Fix more TASK_state comparisons
  sched: Fix TASK_state comparisons
  sched/fair: Move call to list_last_entry() in detach_tasks
  sched/fair: Cleanup loop_max and loop_break
  sched/fair: Make sure to try to detach at least one movable task
  sched: Show PF_flag holes
  freezer,sched: Rewrite core freezer logic
  sched: Widen TAKS_state literals
  sched/wait: Add wait_event_state()
  sched/completion: Add wait_for_completion_state()
  sched: Add TASK_ANY for wait_task_inactive()
  sched: Change wait_task_inactive()s match_state
  freezer,umh: Clean up freezer/initrd interaction
  freezer: Have {,un}lock_system_sleep() save/restore flags
  sched: Rename task_running() to task_on_cpu()
  sched/fair: Cleanup for SIS_PROP
  sched/fair: Default to false in test_idle_cores()
  sched/fair: Remove useless check in select_idle_core()
  sched/fair: Avoid double search on same cpu
  sched/fair: Remove redundant check in select_idle_smt()
  ...

1 files changed, 27 insertions, 76 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 60fdc0faf1c9..8cd1b5a8f613 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -143,11 +143,7 @@ __read_mostly int sysctl_resched_latency_warn_once = 1;
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
  */
-#ifdef CONFIG_PREEMPT_RT
-const_debug unsigned int sysctl_sched_nr_migrate = 8;
-#else
-const_debug unsigned int sysctl_sched_nr_migrate = 32;
-#endif
+const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
 
 __read_mostly int scheduler_running;
 
@@ -482,8 +478,7 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
  *				p->se.load, p->rt_priority,
  *				p->dl.dl_{runtime, deadline, period, flags, bw, density}
  *  - sched_setnuma():		p->numa_preferred_nid
- *  - sched_move_task()/
- *    cpu_cgroup_fork():	p->sched_task_group
+ *  - sched_move_task():	p->sched_task_group
  *  - uclamp_update_active()	p->uclamp*
  *
  * p->state <- TASK_*:
@@ -2329,7 +2324,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 	rq = cpu_rq(new_cpu);
 
 	rq_lock(rq, rf);
-	BUG_ON(task_cpu(p) != new_cpu);
+	WARN_ON_ONCE(task_cpu(p) != new_cpu);
 	activate_task(rq, p, 0);
 	check_preempt_curr(rq, p, 0);
 
@@ -2779,7 +2774,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		return -EINVAL;
 	}
 
-	if (task_running(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) {
+	if (task_on_cpu(rq, p) || READ_ONCE(p->__state) == TASK_WAKING) {
 		/*
 		 * MIGRATE_ENABLE gets here because 'p == current', but for
 		 * anything else we cannot do is_migration_disabled(), punt
@@ -3255,12 +3250,12 @@ out:
 /*
  * wait_task_inactive - wait for a thread to unschedule.
  *
- * If @match_state is nonzero, it's the @p->state value just checked and
- * not expected to change.  If it changes, i.e. @p might have woken up,
- * then return zero.  When we succeed in waiting for @p to be off its CPU,
- * we return a positive number (its total switch count).  If a second call
- * a short while later returns the same number, the caller can be sure that
- * @p has remained unscheduled the whole time.
+ * Wait for the thread to block in any of the states set in @match_state.
+ * If it changes, i.e. @p might have woken up, then return zero.  When we
+ * succeed in waiting for @p to be off its CPU, we return a positive number
+ * (its total switch count).  If a second call a short while later returns the
+ * same number, the caller can be sure that @p has remained unscheduled the
+ * whole time.
  *
  * The caller must ensure that the task *will* unschedule sometime soon,
  * else this function might spin for a *long* time. This function can't
@@ -3291,12 +3286,12 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 		 *
 		 * NOTE! Since we don't hold any locks, it's not
 		 * even sure that "rq" stays as the right runqueue!
-		 * But we don't care, since "task_running()" will
+		 * But we don't care, since "task_on_cpu()" will
 		 * return false if the runqueue has changed and p
 		 * is actually now running somewhere else!
 		 */
-		while (task_running(rq, p)) {
-			if (match_state && unlikely(READ_ONCE(p->__state) != match_state))
+		while (task_on_cpu(rq, p)) {
+			if (!(READ_ONCE(p->__state) & match_state))
 				return 0;
 			cpu_relax();
 		}
@@ -3308,10 +3303,10 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 		 */
 		rq = task_rq_lock(p, &rf);
 		trace_sched_wait_task(p);
-		running = task_running(rq, p);
+		running = task_on_cpu(rq, p);
 		queued = task_on_rq_queued(p);
 		ncsw = 0;
-		if (!match_state || READ_ONCE(p->__state) == match_state)
+		if (READ_ONCE(p->__state) & match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
 		task_rq_unlock(rq, p, &rf);
 
@@ -6430,7 +6425,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 			prev->sched_contributes_to_load =
 				(prev_state & TASK_UNINTERRUPTIBLE) &&
 				!(prev_state & TASK_NOLOAD) &&
-				!(prev->flags & PF_FROZEN);
+				!(prev_state & TASK_FROZEN);
 
 			if (prev->sched_contributes_to_load)
 				rq->nr_uninterruptible++;
@@ -8650,7 +8645,7 @@ again:
 	if (curr->sched_class != p->sched_class)
 		goto out_unlock;
 
-	if (task_running(p_rq, p) || !task_is_running(p))
+	if (task_on_cpu(p_rq, p) || !task_is_running(p))
 		goto out_unlock;
 
 	yielded = curr->sched_class->yield_to_task(rq, p);
@@ -8862,7 +8857,7 @@ void sched_show_task(struct task_struct *p)
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	pr_cont(" stack:%5lu pid:%5d ppid:%6d flags:0x%08lx\n",
+	pr_cont(" stack:%-5lu pid:%-5d ppid:%-6d flags:0x%08lx\n",
 		free, task_pid_nr(p), ppid,
 		read_task_thread_flags(p));
 
@@ -8890,7 +8885,7 @@ state_filter_match(unsigned long state_filter, struct task_struct *p)
 	 * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
 	 * TASK_KILLABLE).
 	 */
-	if (state_filter == TASK_UNINTERRUPTIBLE && state == TASK_IDLE)
+	if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD))
 		return false;
 
 	return true;
@@ -9602,9 +9597,6 @@ LIST_HEAD(task_groups);
 static struct kmem_cache *task_group_cache __read_mostly;
 #endif
 
-DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
-DECLARE_PER_CPU(cpumask_var_t, select_rq_mask);
-
 void __init sched_init(void)
 {
 	unsigned long ptr = 0;
@@ -9648,14 +9640,6 @@ void __init sched_init(void)
 
 #endif /* CONFIG_RT_GROUP_SCHED */
 	}
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	for_each_possible_cpu(i) {
-		per_cpu(load_balance_mask, i) = (cpumask_var_t)kzalloc_node(
-			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
-		per_cpu(select_rq_mask, i) = (cpumask_var_t)kzalloc_node(
-			cpumask_size(), GFP_KERNEL, cpu_to_node(i));
-	}
-#endif /* CONFIG_CPUMASK_OFFSTACK */
 
 	init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
 
@@ -10164,7 +10148,7 @@ void sched_release_group(struct task_group *tg)
 	spin_unlock_irqrestore(&task_group_lock, flags);
 }
 
-static void sched_change_group(struct task_struct *tsk, int type)
+static void sched_change_group(struct task_struct *tsk)
 {
 	struct task_group *tg;
 
@@ -10180,7 +10164,7 @@ static void sched_change_group(struct task_struct *tsk, int type)
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (tsk->sched_class->task_change_group)
-		tsk->sched_class->task_change_group(tsk, type);
+		tsk->sched_class->task_change_group(tsk);
 	else
 #endif
 		set_task_rq(tsk, task_cpu(tsk));
@@ -10211,7 +10195,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (running)
 		put_prev_task(rq, tsk);
 
-	sched_change_group(tsk, TASK_MOVE_GROUP);
+	sched_change_group(tsk);
 
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
@@ -10289,53 +10273,19 @@ static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
 	sched_unregister_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)
-{
-	struct rq_flags rf;
-	struct rq *rq;
-
-	rq = task_rq_lock(task, &rf);
-
-	update_rq_clock(rq);
-	sched_change_group(task, TASK_SET_GROUP);
-
-	task_rq_unlock(rq, task, &rf);
-}
-
+#ifdef CONFIG_RT_GROUP_SCHED
 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
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
-#endif
-		/*
-		 * Serialize against wake_up_new_task() such that if it's
-		 * 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 (READ_ONCE(task->__state) == TASK_NEW)
-			ret = -EINVAL;
-		raw_spin_unlock_irq(&task->pi_lock);
-
-		if (ret)
-			break;
 	}
-	return ret;
+	return 0;
 }
+#endif
 
 static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 {
@@ -11171,8 +11121,9 @@ struct cgroup_subsys cpu_cgrp_subsys = {
 	.css_released	= cpu_cgroup_css_released,
 	.css_free	= cpu_cgroup_css_free,
 	.css_extra_stat_show = cpu_extra_stat_show,
-	.fork		= cpu_cgroup_fork,
+#ifdef CONFIG_RT_GROUP_SCHED
 	.can_attach	= cpu_cgroup_can_attach,
+#endif
 	.attach		= cpu_cgroup_attach,
 	.legacy_cftypes	= cpu_legacy_files,
 	.dfl_cftypes	= cpu_files,