sched/fair: Fix external p->on_rq users

Sean noted that ever since commit 152e11f6df29 ("sched/fair: Implement
delayed dequeue") KVM's preemption notifiers have started
mis-classifying preemption vs blocking.

Notably p->on_rq is no longer sufficient to determine if a task is
runnable or blocked -- the aforementioned commit introduces tasks that
remain on the runqueue even through they will not run again, and
should be considered blocked for many cases.

Add the task_is_runnable() helper to classify things and audit all
external users of the p->on_rq state. Also add a few comments.

Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue")
Reported-by: Sean Christopherson <[e-mail]>
Tested-by: Sean Christopherson <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>
Link: https://lkml.kernel.org/r/[e-mail]

include/linux/sched.h

···
 
 #endif /* CONFIG_SMP */
 
+static inline bool task_is_runnable(struct task_struct *p)
+{
+	return p->on_rq && !p->se.sched_delayed;
+}
+
 extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_curr_snapshot(int cpu);

kernel/events/core.c

···
 		},
 	};
 
-	if (!sched_in && task->on_rq) {
+	if (!sched_in && task_is_runnable(task)) {
 		switch_event.event_id.header.misc |=
 				PERF_RECORD_MISC_SWITCH_OUT_PREEMPT;
 	}

kernel/freezer.c

···
 {
 	unsigned int state = READ_ONCE(p->__state);
 
-	if (p->on_rq)
+	/*
+	 * Allow freezing the sched_delayed tasks; they will not execute until
+	 * ttwu() fixes them up, so it is safe to swap their state now, instead
+	 * of waiting for them to get fully dequeued.
+	 */
+	if (task_is_runnable(p))
 		return 0;
 
 	if (p != current && task_curr(p))

kernel/rcu/tasks.h

···
 		return false;
 
 	/*
+	 * t->on_rq && !t->se.sched_delayed *could* be considered sleeping but
+	 * since it is a spurious state (it will transition into the
+	 * traditional blocked state or get woken up without outside
+	 * dependencies), not considering it such should only affect timing.
+	 *
+	 * Be conservative for now and not include it.
+	 */
+
+	/*
 	 * Idle tasks (or idle injection) within the idle loop are RCU-tasks
 	 * quiescent states. But CPU boot code performed by the idle task
 	 * isn't a quiescent state.

kernel/sched/core.c

···
  *   ON_RQ_MIGRATING state is used for migration without holding both
  *   rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
  *
+ *   Additionally it is possible to be ->on_rq but still be considered not
+ *   runnable when p->se.sched_delayed is true. These tasks are on the runqueue
+ *   but will be dequeued as soon as they get picked again. See the
+ *   task_is_runnable() helper.
+ *
  * p->on_cpu <- { 0, 1 }:
  *
  *   is set by prepare_task() and cleared by finish_task() such that it will be
···
  * @arg: Argument to function.
  *
  * 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.
+ * and call @func(@arg) on it.  This function can use task_is_runnable() 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:
  *   Whatever @func returns

kernel/time/tick-sched.c

···
 	 *   smp_mb__after_spin_lock()
 	 *   tick_nohz_task_switch()
 	 *     LOAD p->tick_dep_mask
+	 *
+	 * XXX given a task picks up the dependency on schedule(), should we
+	 * only care about tasks that are currently on the CPU instead of all
+	 * that are on the runqueue?
+	 *
+	 * That is, does this want to be: task_on_cpu() / task_curr()?
 	 */
 	if (!sched_task_on_rq(tsk))
 		return;

kernel/trace/trace_selftest.c

···
 	/* reset the max latency */
 	tr->max_latency = 0;
 
-	while (p->on_rq) {
+	while (task_is_runnable(p)) {
 		/*
 		 * Sleep to make sure the -deadline thread is asleep too.
 		 * On virtual machines we can't rely on timings,

virt/kvm/kvm_main.c

···
 
 	WRITE_ONCE(vcpu->scheduled_out, true);
 
-	if (current->on_rq && vcpu->wants_to_run) {
+	if (task_is_runnable(current) && vcpu->wants_to_run) {
 		WRITE_ONCE(vcpu->preempted, true);
 		WRITE_ONCE(vcpu->ready, true);
 	}