sched/fair: Unify pick_{,next_}_task_fair()

Implement pick_next_task_fair() in terms of pick_task_fair() to
de-duplicate the pick loop.

More importantly, this makes all the pick loops use the
state-invariant form, which is useful to introduce further re-try
conditions in later patches.

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/20240727105028.725062368@infradead.org

1 files changed, 8 insertions, 52 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 175ccec8c53f..1452c536b578 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8451,7 +8451,6 @@ preempt:
 	resched_curr(rq);
 }
 
-#ifdef CONFIG_SMP
 static struct task_struct *pick_task_fair(struct rq *rq)
 {
 	struct sched_entity *se;
@@ -8463,7 +8462,7 @@ again:
 		return NULL;
 
 	do {
-		/* When we pick for a remote RQ, we'll not have done put_prev_entity() */
+		/* Might not have done put_prev_entity() */
 		if (cfs_rq->curr && cfs_rq->curr->on_rq)
 			update_curr(cfs_rq);
 
@@ -8484,19 +8483,19 @@ again:
 
 	return task_of(se);
 }
-#endif
 
 struct task_struct *
 pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 {
-	struct cfs_rq *cfs_rq = &rq->cfs;
 	struct sched_entity *se;
 	struct task_struct *p;
 	int new_tasks;
 
 again:
-	if (!sched_fair_runnable(rq))
+	p = pick_task_fair(rq);
+	if (!p)
 		goto idle;
+	se = &p->se;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	if (!prev || prev->sched_class != &fair_sched_class)
@@ -8508,52 +8507,14 @@ again:
 	 *
 	 * Therefore attempt to avoid putting and setting the entire cgroup
 	 * hierarchy, only change the part that actually changes.
-	 */
-
-	do {
-		struct sched_entity *curr = cfs_rq->curr;
-
-		/*
-		 * Since we got here without doing put_prev_entity() we also
-		 * have to consider cfs_rq->curr. If it is still a runnable
-		 * entity, update_curr() will update its vruntime, otherwise
-		 * forget we've ever seen it.
-		 */
-		if (curr) {
-			if (curr->on_rq)
-				update_curr(cfs_rq);
-			else
-				curr = NULL;
-
-			/*
-			 * This call to check_cfs_rq_runtime() will do the
-			 * throttle and dequeue its entity in the parent(s).
-			 * Therefore the nr_running test will indeed
-			 * be correct.
-			 */
-			if (unlikely(check_cfs_rq_runtime(cfs_rq))) {
-				cfs_rq = &rq->cfs;
-
-				if (!cfs_rq->nr_running)
-					goto idle;
-
-				goto simple;
-			}
-		}
-
-		se = pick_next_entity(cfs_rq);
-		cfs_rq = group_cfs_rq(se);
-	} while (cfs_rq);
-
-	p = task_of(se);
-
-	/*
+	 *
 	 * Since we haven't yet done put_prev_entity and if the selected task
 	 * is a different task than we started out with, try and touch the
 	 * least amount of cfs_rqs.
 	 */
 	if (prev != p) {
 		struct sched_entity *pse = &prev->se;
+		struct cfs_rq *cfs_rq;
 
 		while (!(cfs_rq = is_same_group(se, pse))) {
 			int se_depth = se->depth;
@@ -8579,13 +8540,8 @@ simple:
 	if (prev)
 		put_prev_task(rq, prev);
 
-	do {
-		se = pick_next_entity(cfs_rq);
-		set_next_entity(cfs_rq, se);
-		cfs_rq = group_cfs_rq(se);
-	} while (cfs_rq);
-
-	p = task_of(se);
+	for_each_sched_entity(se)
+		set_next_entity(cfs_rq_of(se), se);
 
 done: __maybe_unused;
 #ifdef CONFIG_SMP