1 files changed, 191 insertions, 201 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index bc0e242e434c..523fd602ea90 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -74,7 +74,11 @@ __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
 
 /*
  * period over which we measure -rt task CPU usage in us.
@@ -1962,6 +1966,25 @@ bool sched_task_on_rq(struct task_struct *p)
 	return task_on_rq_queued(p);
 }
 
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long ip = 0;
+	unsigned int state;
+
+	if (!p || p == current)
+		return 0;
+
+	/* Only get wchan if task is blocked and we can keep it that way. */
+	raw_spin_lock_irq(&p->pi_lock);
+	state = READ_ONCE(p->__state);
+	smp_rmb(); /* see try_to_wake_up() */
+	if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq)
+		ip = __get_wchan(p);
+	raw_spin_unlock_irq(&p->pi_lock);
+
+	return ip;
+}
+
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (!(flags & ENQUEUE_NOCLOCK))
@@ -3251,7 +3274,7 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 			ktime_t to = NSEC_PER_SEC / HZ;
 
 			set_current_state(TASK_UNINTERRUPTIBLE);
-			schedule_hrtimeout(&to, HRTIMER_MODE_REL);
+			schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
 			continue;
 		}
 
@@ -3489,11 +3512,11 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 #ifdef CONFIG_SMP
 	if (cpu == rq->cpu) {
 		__schedstat_inc(rq->ttwu_local);
-		__schedstat_inc(p->se.statistics.nr_wakeups_local);
+		__schedstat_inc(p->stats.nr_wakeups_local);
 	} else {
 		struct sched_domain *sd;
 
-		__schedstat_inc(p->se.statistics.nr_wakeups_remote);
+		__schedstat_inc(p->stats.nr_wakeups_remote);
 		rcu_read_lock();
 		for_each_domain(rq->cpu, sd) {
 			if (cpumask_test_cpu(cpu, sched_domain_span(sd))) {
@@ -3505,14 +3528,14 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 	}
 
 	if (wake_flags & WF_MIGRATED)
-		__schedstat_inc(p->se.statistics.nr_wakeups_migrate);
+		__schedstat_inc(p->stats.nr_wakeups_migrate);
 #endif /* CONFIG_SMP */
 
 	__schedstat_inc(rq->ttwu_count);
-	__schedstat_inc(p->se.statistics.nr_wakeups);
+	__schedstat_inc(p->stats.nr_wakeups);
 
 	if (wake_flags & WF_SYNC)
-		__schedstat_inc(p->se.statistics.nr_wakeups_sync);
+		__schedstat_inc(p->stats.nr_wakeups_sync);
 }
 
 /*
@@ -3691,15 +3714,11 @@ void wake_up_if_idle(int cpu)
 	if (!is_idle_task(rcu_dereference(rq->curr)))
 		goto out;
 
-	if (set_nr_if_polling(rq->idle)) {
-		trace_sched_wake_idle_without_ipi(cpu);
-	} else {
-		rq_lock_irqsave(rq, &rf);
-		if (is_idle_task(rq->curr))
-			smp_send_reschedule(cpu);
-		/* Else CPU is not idle, do nothing here: */
-		rq_unlock_irqrestore(rq, &rf);
-	}
+	rq_lock_irqsave(rq, &rf);
+	if (is_idle_task(rq->curr))
+		resched_curr(rq);
+	/* Else CPU is not idle, do nothing here: */
+	rq_unlock_irqrestore(rq, &rf);
 
 out:
 	rcu_read_unlock();
@@ -4106,46 +4125,61 @@ out:
 }
 
 /**
- * try_invoke_on_locked_down_task - Invoke a function on task in fixed state
+ * task_call_func - Invoke a function on task in fixed state
  * @p: Process for which the function is to be invoked, can be @current.
  * @func: Function to invoke.
  * @arg: Argument to function.
  *
- * If the specified task can be quickly locked into a definite state
- * (either sleeping or on a given runqueue), arrange to keep it in that
- * state while invoking @func(@arg).  This function can use ->on_rq and
- * task_curr() to work out what the state is, if required.  Given that
- * @func can be invoked with a runqueue lock held, it had better be quite
- * lightweight.
+ * Fix the task in it's current state by avoiding wakeups and or rq operations
+ * and call @func(@arg) on it.  This function can use ->on_rq and task_curr()
+ * to work out what the state is, if required.  Given that @func can be invoked
+ * with a runqueue lock held, it had better be quite lightweight.
  *
  * Returns:
- *	@false if the task slipped out from under the locks.
- *	@true if the task was locked onto a runqueue or is sleeping.
- *		However, @func can override this by returning @false.
+ *   Whatever @func returns
  */
-bool try_invoke_on_locked_down_task(struct task_struct *p, bool (*func)(struct task_struct *t, void *arg), void *arg)
+int task_call_func(struct task_struct *p, task_call_f func, void *arg)
 {
+	struct rq *rq = NULL;
+	unsigned int state;
 	struct rq_flags rf;
-	bool ret = false;
-	struct rq *rq;
+	int ret;
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
-	if (p->on_rq) {
+
+	state = READ_ONCE(p->__state);
+
+	/*
+	 * Ensure we load p->on_rq after p->__state, otherwise it would be
+	 * possible to, falsely, observe p->on_rq == 0.
+	 *
+	 * See try_to_wake_up() for a longer comment.
+	 */
+	smp_rmb();
+
+	/*
+	 * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
+	 * the task is blocked. Make sure to check @state since ttwu() can drop
+	 * locks at the end, see ttwu_queue_wakelist().
+	 */
+	if (state == TASK_RUNNING || state == TASK_WAKING || p->on_rq)
 		rq = __task_rq_lock(p, &rf);
-		if (task_rq(p) == rq)
-			ret = func(p, arg);
+
+	/*
+	 * At this point the task is pinned; either:
+	 *  - blocked and we're holding off wakeups	 (pi->lock)
+	 *  - woken, and we're holding off enqueue	 (rq->lock)
+	 *  - queued, and we're holding off schedule	 (rq->lock)
+	 *  - running, and we're holding off de-schedule (rq->lock)
+	 *
+	 * The called function (@func) can use: task_curr(), p->on_rq and
+	 * p->__state to differentiate between these states.
+	 */
+	ret = func(p, arg);
+
+	if (rq)
 		rq_unlock(rq, &rf);
-	} else {
-		switch (READ_ONCE(p->__state)) {
-		case TASK_RUNNING:
-		case TASK_WAKING:
-			break;
-		default:
-			smp_rmb(); // See smp_rmb() comment in try_to_wake_up().
-			if (!p->on_rq)
-				ret = func(p, arg);
-		}
-	}
+
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
 	return ret;
 }
@@ -4196,7 +4230,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 #ifdef CONFIG_SCHEDSTATS
 	/* Even if schedstat is disabled, there should not be garbage */
-	memset(&p->se.statistics, 0, sizeof(p->se.statistics));
+	memset(&p->stats, 0, sizeof(p->stats));
 #endif
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
@@ -4328,8 +4362,6 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
  */
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
-	unsigned long flags;
-
 	__sched_fork(clone_flags, p);
 	/*
 	 * We mark the process as NEW here. This guarantees that
@@ -4375,24 +4407,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 
 	init_entity_runnable_average(&p->se);
 
-	/*
-	 * The child is not yet in the pid-hash so no cgroup attach races,
-	 * and the cgroup is pinned to this child due to cgroup_fork()
-	 * is ran before sched_fork().
-	 *
-	 * Silence PROVE_RCU.
-	 */
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	rseq_migrate(p);
-	/*
-	 * We're setting the CPU for the first time, we don't migrate,
-	 * so use __set_task_cpu().
-	 */
-	__set_task_cpu(p, smp_processor_id());
-	if (p->sched_class->task_fork)
-		p->sched_class->task_fork(p);
-	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-
 #ifdef CONFIG_SCHED_INFO
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
@@ -4408,8 +4422,29 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	return 0;
 }
 
-void sched_post_fork(struct task_struct *p)
+void sched_post_fork(struct task_struct *p, struct kernel_clone_args *kargs)
 {
+	unsigned long flags;
+#ifdef CONFIG_CGROUP_SCHED
+	struct task_group *tg;
+#endif
+
+	raw_spin_lock_irqsave(&p->pi_lock, flags);
+#ifdef CONFIG_CGROUP_SCHED
+	tg = container_of(kargs->cset->subsys[cpu_cgrp_id],
+			  struct task_group, css);
+	p->sched_task_group = autogroup_task_group(p, tg);
+#endif
+	rseq_migrate(p);
+	/*
+	 * We're setting the CPU for the first time, we don't migrate,
+	 * so use __set_task_cpu().
+	 */
+	__set_task_cpu(p, smp_processor_id());
+	if (p->sched_class->task_fork)
+		p->sched_class->task_fork(p);
+	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
 	uclamp_post_fork(p);
 }
 
@@ -4836,18 +4871,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 */
 	if (mm) {
 		membarrier_mm_sync_core_before_usermode(mm);
-		mmdrop(mm);
+		mmdrop_sched(mm);
 	}
 	if (unlikely(prev_state == TASK_DEAD)) {
 		if (prev->sched_class->task_dead)
 			prev->sched_class->task_dead(prev);
 
-		/*
-		 * Remove function-return probe instances associated with this
-		 * task and put them back on the free list.
-		 */
-		kprobe_flush_task(prev);
-
 		/* Task is done with its stack. */
 		put_task_stack(prev);
 
@@ -5580,8 +5609,7 @@ restart:
 			return p;
 	}
 
-	/* The idle class should always have a runnable task: */
-	BUG();
+	BUG(); /* The idle class should always have a runnable task. */
 }
 
 #ifdef CONFIG_SCHED_CORE
@@ -5603,54 +5631,18 @@ static inline bool cookie_match(struct task_struct *a, struct task_struct *b)
 	return a->core_cookie == b->core_cookie;
 }
 
-// XXX fairness/fwd progress conditions
-/*
- * Returns
- * - NULL if there is no runnable task for this class.
- * - the highest priority task for this runqueue if it matches
- *   rq->core->core_cookie or its priority is greater than max.
- * - Else returns idle_task.
- */
-static struct task_struct *
-pick_task(struct rq *rq, const struct sched_class *class, struct task_struct *max, bool in_fi)
+static inline struct task_struct *pick_task(struct rq *rq)
 {
-	struct task_struct *class_pick, *cookie_pick;
-	unsigned long cookie = rq->core->core_cookie;
-
-	class_pick = class->pick_task(rq);
-	if (!class_pick)
-		return NULL;
-
-	if (!cookie) {
-		/*
-		 * If class_pick is tagged, return it only if it has
-		 * higher priority than max.
-		 */
-		if (max && class_pick->core_cookie &&
-		    prio_less(class_pick, max, in_fi))
-			return idle_sched_class.pick_task(rq);
+	const struct sched_class *class;
+	struct task_struct *p;
 
-		return class_pick;
+	for_each_class(class) {
+		p = class->pick_task(rq);
+		if (p)
+			return p;
 	}
 
-	/*
-	 * If class_pick is idle or matches cookie, return early.
-	 */
-	if (cookie_equals(class_pick, cookie))
-		return class_pick;
-
-	cookie_pick = sched_core_find(rq, cookie);
-
-	/*
-	 * If class > max && class > cookie, it is the highest priority task on
-	 * the core (so far) and it must be selected, otherwise we must go with
-	 * the cookie pick in order to satisfy the constraint.
-	 */
-	if (prio_less(cookie_pick, class_pick, in_fi) &&
-	    (!max || prio_less(max, class_pick, in_fi)))
-		return class_pick;
-
-	return cookie_pick;
+	BUG(); /* The idle class should always have a runnable task. */
 }
 
 extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
@@ -5658,11 +5650,12 @@ extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_f
 static struct task_struct *
 pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct task_struct *next, *max = NULL;
-	const struct sched_class *class;
+	struct task_struct *next, *p, *max = NULL;
 	const struct cpumask *smt_mask;
 	bool fi_before = false;
-	int i, j, cpu, occ = 0;
+	unsigned long cookie;
+	int i, cpu, occ = 0;
+	struct rq *rq_i;
 	bool need_sync;
 
 	if (!sched_core_enabled(rq))
@@ -5735,12 +5728,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	 * and there are no cookied tasks running on siblings.
 	 */
 	if (!need_sync) {
-		for_each_class(class) {
-			next = class->pick_task(rq);
-			if (next)
-				break;
-		}
-
+		next = pick_task(rq);
 		if (!next->core_cookie) {
 			rq->core_pick = NULL;
 			/*
@@ -5753,76 +5741,51 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		}
 	}
 
-	for_each_cpu(i, smt_mask) {
-		struct rq *rq_i = cpu_rq(i);
-
-		rq_i->core_pick = NULL;
+	/*
+	 * For each thread: do the regular task pick and find the max prio task
+	 * amongst them.
+	 *
+	 * Tie-break prio towards the current CPU
+	 */
+	for_each_cpu_wrap(i, smt_mask, cpu) {
+		rq_i = cpu_rq(i);
 
 		if (i != cpu)
 			update_rq_clock(rq_i);
+
+		p = rq_i->core_pick = pick_task(rq_i);
+		if (!max || prio_less(max, p, fi_before))
+			max = p;
 	}
 
+	cookie = rq->core->core_cookie = max->core_cookie;
+
 	/*
-	 * Try and select tasks for each sibling in descending sched_class
-	 * order.
+	 * For each thread: try and find a runnable task that matches @max or
+	 * force idle.
 	 */
-	for_each_class(class) {
-again:
-		for_each_cpu_wrap(i, smt_mask, cpu) {
-			struct rq *rq_i = cpu_rq(i);
-			struct task_struct *p;
-
-			if (rq_i->core_pick)
-				continue;
+	for_each_cpu(i, smt_mask) {
+		rq_i = cpu_rq(i);
+		p = rq_i->core_pick;
 
-			/*
-			 * If this sibling doesn't yet have a suitable task to
-			 * run; ask for the most eligible task, given the
-			 * highest priority task already selected for this
-			 * core.
-			 */
-			p = pick_task(rq_i, class, max, fi_before);
+		if (!cookie_equals(p, cookie)) {
+			p = NULL;
+			if (cookie)
+				p = sched_core_find(rq_i, cookie);
 			if (!p)
-				continue;
+				p = idle_sched_class.pick_task(rq_i);
+		}
 
-			if (!is_task_rq_idle(p))
-				occ++;
+		rq_i->core_pick = p;
 
-			rq_i->core_pick = p;
-			if (rq_i->idle == p && rq_i->nr_running) {
+		if (p == rq_i->idle) {
+			if (rq_i->nr_running) {
 				rq->core->core_forceidle = true;
 				if (!fi_before)
 					rq->core->core_forceidle_seq++;
 			}
-
-			/*
-			 * If this new candidate is of higher priority than the
-			 * previous; and they're incompatible; we need to wipe
-			 * the slate and start over. pick_task makes sure that
-			 * p's priority is more than max if it doesn't match
-			 * max's cookie.
-			 *
-			 * NOTE: this is a linear max-filter and is thus bounded
-			 * in execution time.
-			 */
-			if (!max || !cookie_match(max, p)) {
-				struct task_struct *old_max = max;
-
-				rq->core->core_cookie = p->core_cookie;
-				max = p;
-
-				if (old_max) {
-					rq->core->core_forceidle = false;
-					for_each_cpu(j, smt_mask) {
-						if (j == i)
-							continue;
-
-						cpu_rq(j)->core_pick = NULL;
-					}
-					occ = 1;
-					goto again;
-				}
-			}
+		} else {
+			occ++;
 		}
 	}
 
@@ -5842,7 +5805,7 @@ again:
 	 * non-matching user state.
 	 */
 	for_each_cpu(i, smt_mask) {
-		struct rq *rq_i = cpu_rq(i);
+		rq_i = cpu_rq(i);
 
 		/*
 		 * An online sibling might have gone offline before a task
@@ -6319,20 +6282,14 @@ static inline void sched_submit_work(struct task_struct *tsk)
 
 	task_flags = tsk->flags;
 	/*
-	 * If a worker went to sleep, notify and ask workqueue whether
-	 * it wants to wake up a task to maintain concurrency.
-	 * As this function is called inside the schedule() context,
-	 * we disable preemption to avoid it calling schedule() again
-	 * in the possible wakeup of a kworker and because wq_worker_sleeping()
-	 * requires it.
+	 * If a worker goes to sleep, notify and ask workqueue whether it
+	 * wants to wake up a task to maintain concurrency.
 	 */
 	if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
-		preempt_disable();
 		if (task_flags & PF_WQ_WORKER)
 			wq_worker_sleeping(tsk);
 		else
 			io_wq_worker_sleeping(tsk);
-		preempt_enable_no_resched();
 	}
 
 	if (tsk_is_pi_blocked(tsk))
@@ -6586,12 +6543,13 @@ EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
  */
 
 enum {
-	preempt_dynamic_none = 0,
+	preempt_dynamic_undefined = -1,
+	preempt_dynamic_none,
 	preempt_dynamic_voluntary,
 	preempt_dynamic_full,
 };
 
-int preempt_dynamic_mode = preempt_dynamic_full;
+int preempt_dynamic_mode = preempt_dynamic_undefined;
 
 int sched_dynamic_mode(const char *str)
 {
@@ -6664,7 +6622,27 @@ static int __init setup_preempt_mode(char *str)
 }
 __setup("preempt=", setup_preempt_mode);
 
-#endif /* CONFIG_PREEMPT_DYNAMIC */
+static void __init preempt_dynamic_init(void)
+{
+	if (preempt_dynamic_mode == preempt_dynamic_undefined) {
+		if (IS_ENABLED(CONFIG_PREEMPT_NONE_BEHAVIOUR)) {
+			sched_dynamic_update(preempt_dynamic_none);
+		} else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY_BEHAVIOUR)) {
+			sched_dynamic_update(preempt_dynamic_voluntary);
+		} else {
+			/* Default static call setting, nothing to do */
+			WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT_BEHAVIOUR));
+			preempt_dynamic_mode = preempt_dynamic_full;
+			pr_info("Dynamic Preempt: full\n");
+		}
+	}
+}
+
+#else /* !CONFIG_PREEMPT_DYNAMIC */
+
+static inline void preempt_dynamic_init(void) { }
+
+#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
 
 /*
  * This is the entry point to schedule() from kernel preemption
@@ -9466,6 +9444,8 @@ void __init sched_init(void)
 
 	init_uclamp();
 
+	preempt_dynamic_init();
+
 	scheduler_running = 1;
 }
 
@@ -9640,9 +9620,9 @@ void normalize_rt_tasks(void)
 			continue;
 
 		p->se.exec_start = 0;
-		schedstat_set(p->se.statistics.wait_start,  0);
-		schedstat_set(p->se.statistics.sleep_start, 0);
-		schedstat_set(p->se.statistics.block_start, 0);
+		schedstat_set(p->stats.wait_start,  0);
+		schedstat_set(p->stats.sleep_start, 0);
+		schedstat_set(p->stats.block_start, 0);
 
 		if (!dl_task(p) && !rt_task(p)) {
 			/*
@@ -10484,15 +10464,21 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
 	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
 
 	if (schedstat_enabled() && tg != &root_task_group) {
+		struct sched_statistics *stats;
 		u64 ws = 0;
 		int i;
 
-		for_each_possible_cpu(i)
-			ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+		for_each_possible_cpu(i) {
+			stats = __schedstats_from_se(tg->se[i]);
+			ws += schedstat_val(stats->wait_sum);
+		}
 
 		seq_printf(sf, "wait_sum %llu\n", ws);
 	}
 
+	seq_printf(sf, "nr_bursts %d\n", cfs_b->nr_burst);
+	seq_printf(sf, "burst_time %llu\n", cfs_b->burst_time);
+
 	return 0;
 }
 #endif /* CONFIG_CFS_BANDWIDTH */
@@ -10608,16 +10594,20 @@ static int cpu_extra_stat_show(struct seq_file *sf,
 	{
 		struct task_group *tg = css_tg(css);
 		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
-		u64 throttled_usec;
+		u64 throttled_usec, burst_usec;
 
 		throttled_usec = cfs_b->throttled_time;
 		do_div(throttled_usec, NSEC_PER_USEC);
+		burst_usec = cfs_b->burst_time;
+		do_div(burst_usec, NSEC_PER_USEC);
 
 		seq_printf(sf, "nr_periods %d\n"
 			   "nr_throttled %d\n"
-			   "throttled_usec %llu\n",
+			   "throttled_usec %llu\n"
+			   "nr_bursts %d\n"
+			   "burst_usec %llu\n",
 			   cfs_b->nr_periods, cfs_b->nr_throttled,
-			   throttled_usec);
+			   throttled_usec, cfs_b->nr_burst, burst_usec);
 	}
 #endif
 	return 0;