sched: Prepare generic code for delayed dequeue

While most of the delayed dequeue code can be done inside the
sched_class itself, there is one location where we do not have an
appropriate hook, namely ttwu_runnable().

Add an ENQUEUE_DELAYED call to the on_rq path to deal with waking
delayed dequeue tasks.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: Valentin Schneider <vschneid@redhat.com>
Link: https://lkml.kernel.org/r/20240727105029.200000445@infradead.org

Author: Peter Zijlstra

include/linux/sched.h

@@ -544,6 +544,7 @@ struct sched_entity {
 
 	struct list_head		group_node;
 	unsigned int			on_rq;
+	unsigned int			sched_delayed;
 
 	u64				exec_start;
 	u64				sum_exec_runtime;

kernel/sched/core.c

@@ -2036,6 +2036,8 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 
 void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
 {
+	SCHED_WARN_ON(flags & DEQUEUE_SLEEP);
+
 	WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
 	ASSERT_EXCLUSIVE_WRITER(p->on_rq);
 
@@ -3689,12 +3691,14 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 
 	rq = __task_rq_lock(p, &rf);
 	if (task_on_rq_queued(p)) {
+		update_rq_clock(rq);
+		if (p->se.sched_delayed)
+			enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
 		if (!task_on_cpu(rq, p)) {
 			/*
 			 * When on_rq && !on_cpu the task is preempted, see if
 			 * it should preempt the task that is current now.
 			 */
-			update_rq_clock(rq);
 			wakeup_preempt(rq, p, wake_flags);
 		}
 		ttwu_do_wakeup(p);
@@ -4074,11 +4078,16 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 * case the whole 'p->on_rq && ttwu_runnable()' case below
 		 * without taking any locks.
 		 *
+		 * Specifically, given current runs ttwu() we must be before
+		 * schedule()'s block_task(), as such this must not observe
+		 * sched_delayed.
+		 *
 		 * In particular:
 		 *  - we rely on Program-Order guarantees for all the ordering,
 		 *  - we're serialized against set_special_state() by virtue of
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
+		SCHED_WARN_ON(p->se.sched_delayed);
 		if (!ttwu_state_match(p, state, &success))
 			goto out;
 
@@ -4370,6 +4379,9 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->se.slice			= sysctl_sched_base_slice;
 	INIT_LIST_HEAD(&p->se.group_node);
 
+	/* A delayed task cannot be in clone(). */
+	SCHED_WARN_ON(p->se.sched_delayed);
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq			= NULL;
 #endif

kernel/sched/sched.h

@@ -2253,6 +2253,7 @@ extern const u32		sched_prio_to_wmult[40];
 #define DEQUEUE_MOVE		0x04 /* Matches ENQUEUE_MOVE */
 #define DEQUEUE_NOCLOCK		0x08 /* Matches ENQUEUE_NOCLOCK */
 #define DEQUEUE_MIGRATING	0x100 /* Matches ENQUEUE_MIGRATING */
+#define DEQUEUE_DELAYED		0x200 /* Matches ENQUEUE_DELAYED */
 
 #define ENQUEUE_WAKEUP		0x01
 #define ENQUEUE_RESTORE		0x02
@@ -2268,6 +2269,7 @@ extern const u32		sched_prio_to_wmult[40];
 #endif
 #define ENQUEUE_INITIAL		0x80
 #define ENQUEUE_MIGRATING	0x100
+#define ENQUEUE_DELAYED		0x200
 
 #define RETRY_TASK		((void *)-1UL)