Merge tag 'sched_ext-for-6.14-rc4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext

Pull sched_ext fix from Tejun Heo:
 "pick_task_scx() has a workaround to avoid stalling when the fair
  class's balance() says yes but pick_task() says no.

  The workaround was incorrectly deciding to keep the prev taks running
  if the task is on SCX even when the task is in a sleeping state, which
  can lead to several confusing failure modes.

  Fix it by testing the prev task is currently queued on SCX instead"

* tag 'sched_ext-for-6.14-rc4-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/sched_ext:
  sched_ext: Fix pick_task_scx() picking non-queued tasks when it's called without balance()

1 files changed, 7 insertions, 4 deletions

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 5a81d9a1e31f..0f1da199cfc7 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3117,7 +3117,6 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 {
 	struct task_struct *prev = rq->curr;
 	struct task_struct *p;
-	bool prev_on_scx = prev->sched_class == &ext_sched_class;
 	bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
 	bool kick_idle = false;
 
@@ -3137,14 +3136,18 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 	 * if pick_task_scx() is called without preceding balance_scx().
 	 */
 	if (unlikely(rq->scx.flags & SCX_RQ_BAL_PENDING)) {
-		if (prev_on_scx) {
+		if (prev->scx.flags & SCX_TASK_QUEUED) {
 			keep_prev = true;
 		} else {
 			keep_prev = false;
 			kick_idle = true;
 		}
-	} else if (unlikely(keep_prev && !prev_on_scx)) {
-		/* only allowed during transitions */
+	} else if (unlikely(keep_prev &&
+			    prev->sched_class != &ext_sched_class)) {
+		/*
+		 * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is
+		 * conditional on scx_enabled() and may have been skipped.
+		 */
 		WARN_ON_ONCE(scx_ops_enable_state() == SCX_OPS_ENABLED);
 		keep_prev = false;
 	}