sched/fair: Implement delayed dequeue

Extend / fix 86bfbb7ce4 ("sched/fair: Add lag based placement") by
noting that lag is fundamentally a temporal measure. It should not be
carried around indefinitely.

OTOH it should also not be instantly discarded, doing so will allow a
task to game the system by purposefully (micro) sleeping at the end of
its time quantum.

Since lag is intimately tied to the virtual time base, a wall-time
based decay is also insufficient, notably competition is required for
any of this to make sense.

Instead, delay the dequeue and keep the 'tasks' on the runqueue,
competing until they are eligible.

Strictly speaking, we only care about keeping them until the 0-lag
point, but that is a difficult proposition, instead carry them around
until they get picked again, and dequeue them at that point.

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/20240727105030.226163742@infradead.org

kernel/sched/deadline.c

@@ -2428,7 +2428,6 @@ again:
 		else
 			p = dl_se->server_pick_next(dl_se);
 		if (!p) {
-			WARN_ON_ONCE(1);
 			dl_se->dl_yielded = 1;
 			update_curr_dl_se(rq, dl_se, 0);
 			goto again;

kernel/sched/fair.c

@@ -5379,19 +5379,38 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq);
 
-static void
+static bool
 dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
-	int action = UPDATE_TG;
+	update_curr(cfs_rq);
 
+	if (flags & DEQUEUE_DELAYED) {
+		SCHED_WARN_ON(!se->sched_delayed);
+	} else {
+		bool sleep = flags & DEQUEUE_SLEEP;
+
+		/*
+		 * DELAY_DEQUEUE relies on spurious wakeups, special task
+		 * states must not suffer spurious wakeups, excempt them.
+		 */
+		if (flags & DEQUEUE_SPECIAL)
+			sleep = false;
+
+		SCHED_WARN_ON(sleep && se->sched_delayed);
+
+		if (sched_feat(DELAY_DEQUEUE) && sleep &&
+		    !entity_eligible(cfs_rq, se)) {
+			if (cfs_rq->next == se)
+				cfs_rq->next = NULL;
+			se->sched_delayed = 1;
+			return false;
+		}
+	}
+
+	int action = UPDATE_TG;
 	if (entity_is_task(se) && task_on_rq_migrating(task_of(se)))
 		action |= DO_DETACH;
 
-	/*
-	 * Update run-time statistics of the 'current'.
-	 */
-	update_curr(cfs_rq);
-
 	/*
 	 * When dequeuing a sched_entity, we must:
 	 *   - Update loads to have both entity and cfs_rq synced with now.
@@ -5428,8 +5447,13 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
 		update_min_vruntime(cfs_rq);
 
+	if (flags & DEQUEUE_DELAYED)
+		se->sched_delayed = 0;
+
 	if (cfs_rq->nr_running == 0)
 		update_idle_cfs_rq_clock_pelt(cfs_rq);
+
+	return true;
 }
 
 static void
@@ -5828,11 +5852,21 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	idle_task_delta = cfs_rq->idle_h_nr_running;
 	for_each_sched_entity(se) {
 		struct cfs_rq *qcfs_rq = cfs_rq_of(se);
+		int flags;
+
 		/* throttled entity or throttle-on-deactivate */
 		if (!se->on_rq)
 			goto done;
 
-		dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
+		/*
+		 * Abuse SPECIAL to avoid delayed dequeue in this instance.
+		 * This avoids teaching dequeue_entities() about throttled
+		 * entities and keeps things relatively simple.
+		 */
+		flags = DEQUEUE_SLEEP | DEQUEUE_SPECIAL;
+		if (se->sched_delayed)
+			flags |= DEQUEUE_DELAYED;
+		dequeue_entity(qcfs_rq, se, flags);
 
 		if (cfs_rq_is_idle(group_cfs_rq(se)))
 			idle_task_delta = cfs_rq->h_nr_running;
@@ -6918,6 +6952,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	bool was_sched_idle = sched_idle_rq(rq);
 	int rq_h_nr_running = rq->cfs.h_nr_running;
 	bool task_sleep = flags & DEQUEUE_SLEEP;
+	bool task_delayed = flags & DEQUEUE_DELAYED;
 	struct task_struct *p = NULL;
 	int idle_h_nr_running = 0;
 	int h_nr_running = 0;
@@ -6931,7 +6966,13 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 	for_each_sched_entity(se) {
 		cfs_rq = cfs_rq_of(se);
-		dequeue_entity(cfs_rq, se, flags);
+
+		if (!dequeue_entity(cfs_rq, se, flags)) {
+			if (p && &p->se == se)
+				return -1;
+
+			break;
+		}
 
 		cfs_rq->h_nr_running -= h_nr_running;
 		cfs_rq->idle_h_nr_running -= idle_h_nr_running;
@@ -6956,6 +6997,7 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 			break;
 		}
 		flags |= DEQUEUE_SLEEP;
+		flags &= ~(DEQUEUE_DELAYED | DEQUEUE_SPECIAL);
 	}
 
 	for_each_sched_entity(se) {
@@ -6985,6 +7027,17 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
 
+	if (p && task_delayed) {
+		SCHED_WARN_ON(!task_sleep);
+		SCHED_WARN_ON(p->on_rq != 1);
+
+		/* Fix-up what dequeue_task_fair() skipped */
+		hrtick_update(rq);
+
+		/* Fix-up what block_task() skipped. */
+		__block_task(rq, p);
+	}
+
 	return 1;
 }
 
@@ -6997,8 +7050,10 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
 	util_est_dequeue(&rq->cfs, p);
 
-	if (dequeue_entities(rq, &p->se, flags) < 0)
+	if (dequeue_entities(rq, &p->se, flags) < 0) {
+		util_est_update(&rq->cfs, p, DEQUEUE_SLEEP);
 		return false;
+	}
 
 	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
 	hrtick_update(rq);
@@ -12971,6 +13026,11 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
 		/* ensure bandwidth has been allocated on our new cfs_rq */
 		account_cfs_rq_runtime(cfs_rq, 0);
 	}
+
+	if (!first)
+		return;
+
+	SCHED_WARN_ON(se->sched_delayed);
 }
 
 void init_cfs_rq(struct cfs_rq *cfs_rq)

kernel/sched/features.h

@@ -28,6 +28,15 @@ SCHED_FEAT(NEXT_BUDDY, false)
  */
 SCHED_FEAT(CACHE_HOT_BUDDY, true)
 
+/*
+ * Delay dequeueing tasks until they get selected or woken.
+ *
+ * By delaying the dequeue for non-eligible tasks, they remain in the
+ * competition and can burn off their negative lag. When they get selected
+ * they'll have positive lag by definition.
+ */
+SCHED_FEAT(DELAY_DEQUEUE, true)
+
 /*
  * Allow wakeup-time preemption of the current task:
  */