sched_ext: Replay ecaps notifications suppressed by bypass

scx_process_sync_ecaps() consumes ecaps syncs while the sched is bypassing
without delivering ops.sub_ecaps_updated(), leaving reported_ecaps stale.
Nothing re-queued a sync when bypass lifted, so a cid whose caps never
change again would never be notified. Attach-time initial grants hit this
every time: they are consumed during the enable bypass window, so a sched
never learned its initial effective caps through the callback.

Re-queue a sync for every (sched, cpu) with an undelivered delta at the
per-cpu bypass exit in scx_bypass(), next to the idle renotify catch-up. The
next balance on the cpu then delivers the pending delta with proper dispatch
context.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

kernel/sched/ext/ext.c

@@ -5662,8 +5662,10 @@ void scx_bypass(struct scx_sched *sch, bool bypass)
 				pcpu->flags |= SCX_SCHED_PCPU_BYPASSING;
 			} else {
 				pcpu->flags &= ~SCX_SCHED_PCPU_BYPASSING;
-				if (was_bypassing)
+				if (was_bypassing) {
 					unbypass_renotify_idle(rq, pos, pcpu);
+					scx_unbypass_replay_ecaps(rq, pos);
+				}
 			}
 		}
 

kernel/sched/ext/sub.c

@@ -575,6 +575,41 @@ void scx_process_sync_ecaps(struct rq *rq, struct task_struct *prev)
 		scx_schedule_reenq_local(rq, SCX_REENQ_CAP_REVOKE);
 }
 
+/**
+ * scx_unbypass_replay_ecaps - Replay a bypass-suppressed ecaps notification
+ * @rq: rq of the cpu leaving bypass
+ * @sch: scheduler that just left bypass on @rq's cpu
+ *
+ * scx_process_sync_ecaps() consumes syncs while bypassing without delivering
+ * ops.sub_ecaps_updated(), leaving reported_ecaps stale. Nothing re-queues a
+ * sync when bypass lifts, so without a replay a cid that never changes again
+ * would never be notified. The attach-time initial grants are the acute case
+ * as they are consumed during the enable bypass window. Re-queue a sync for
+ * any undelivered delta so the next balance delivers it.
+ */
+void scx_unbypass_replay_ecaps(struct rq *rq, struct scx_sched *sch)
+{
+	s32 cpu = cpu_of(rq);
+	struct scx_sched_pcpu *pcpu = per_cpu_ptr(sch->pcpu, cpu);
+	struct scx_pshard *ps;
+	s32 cid;
+
+	lockdep_assert_rq_held(rq);
+
+	/* root holds every cap and never uses ecaps */
+	if (!sch->level)
+		return;
+
+	if (READ_ONCE(pcpu->ecaps) == pcpu->reported_ecaps)
+		return;
+
+	cid = __scx_cpu_to_cid(cpu);
+	ps = sch->pshard[scx_cid_to_shard[cid]];
+
+	guard(raw_spinlock)(&ps->lock);
+	queue_sync_ecaps(sch, cid);
+}
+
 /*
  * A cpu came back. Re-seed each sub-sched's ecaps on the cpu's cid. The sync
  * recomputes effective caps from the pshard and fires ops.sub_ecaps_updated()

kernel/sched/ext/sub.h

@@ -30,6 +30,7 @@ void scx_free_pshards(struct scx_sched *sch);
 s32 scx_alloc_pshards(struct scx_sched *sch);
 void scx_init_root_caps(struct scx_sched *sch);
 void scx_process_sync_ecaps(struct rq *rq, struct task_struct *prev);
+void scx_unbypass_replay_ecaps(struct rq *rq, struct scx_sched *sch);
 void scx_online_ecaps(struct rq *rq);
 void scx_offline_ecaps(struct rq *rq);
 void scx_discard_ecaps_to_sync(s32 cpu, struct scx_sched_pcpu *pcpu);
@@ -58,6 +59,7 @@ static inline void scx_free_pshards(struct scx_sched *sch) {}
 static inline s32 scx_alloc_pshards(struct scx_sched *sch) { return 0; }
 static inline void scx_init_root_caps(struct scx_sched *sch) {}
 static inline void scx_process_sync_ecaps(struct rq *rq, struct task_struct *prev) {}
+static inline void scx_unbypass_replay_ecaps(struct rq *rq, struct scx_sched *sch) {}
 static inline void scx_online_ecaps(struct rq *rq) {}
 static inline void scx_offline_ecaps(struct rq *rq) {}
 static inline void scx_discard_ecaps_to_sync(s32 cpu, struct scx_sched_pcpu *pcpu) {}