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 <seanjc@google.com>
Tested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20241010091843.GK33184@noisy.programming.kicks-ass.net

8 files changed, 38 insertions, 7 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index e6ee4258169a..8a9517e6640c 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2133,6 +2133,11 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 #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);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e3589c4287cb..cdd09769e6c5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -9251,7 +9251,7 @@ static void perf_event_switch(struct task_struct *task,
 		},
 	};
 
-	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;
 	}
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 44bbd7dbd2c8..8d530d0949ff 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -109,7 +109,12 @@ static int __set_task_frozen(struct task_struct *p, void *arg)
 {
 	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))
diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
index 6333f4ccf024..4d7ee95df06e 100644
--- a/kernel/rcu/tasks.h
+++ b/kernel/rcu/tasks.h
@@ -986,6 +986,15 @@ static bool rcu_tasks_is_holdout(struct task_struct *t)
 		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.
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 71232f8f9b96..7db711ba6d12 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -548,6 +548,11 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
  *   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
@@ -4317,9 +4322,10 @@ static bool __task_needs_rq_lock(struct task_struct *p)
  * @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
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 753a184c7090..f203f000da1a 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -434,6 +434,12 @@ static void tick_nohz_kick_task(struct task_struct *tsk)
 	 *   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;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index c4ad7cd7e778..1469dd8075fa 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1485,7 +1485,7 @@ trace_selftest_startup_wakeup(struct tracer *trace, struct trace_array *tr)
 	/* 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,
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 05cbb2548d99..0c666f1870af 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -6387,7 +6387,7 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 
 	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);
 	}