diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c index bba9d805dc2b..bd8cb37b4b2e 100644 --- a/kernel/sched/ext.c +++ b/kernel/sched/ext.c @@ -2909,9 +2909,24 @@ static struct task_struct *pick_task_scx(struct rq *rq) * If balance_scx() is telling us to keep running @prev, replenish slice * if necessary and keep running @prev. Otherwise, pop the first one * from the local DSQ. + * + * WORKAROUND: + * + * %SCX_RQ_BAL_KEEP should be set iff $prev is on SCX as it must just + * have gone through balance_scx(). Unfortunately, there currently is a + * bug where fair could say yes on balance() but no on pick_task(), + * which then ends up calling pick_task_scx() without preceding + * balance_scx(). + * + * For now, ignore cases where $prev is not on SCX. This isn't great and + * can theoretically lead to stalls. However, for switch_all cases, this + * happens only while a BPF scheduler is being loaded or unloaded, and, + * for partial cases, fair will likely keep triggering this CPU. + * + * Once fair is fixed, restore WARN_ON_ONCE(). */ if ((rq->scx.flags & SCX_RQ_BAL_KEEP) && - !WARN_ON_ONCE(prev->sched_class != &ext_sched_class)) { + prev->sched_class == &ext_sched_class) { p = prev; if (!p->scx.slice) p->scx.slice = SCX_SLICE_DFL;