diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 5efc97437c0a..5418e6357249 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -2307,6 +2307,7 @@ static void move_remote_task_to_local_dsq(struct task_struct *p, u64 enq_flags,
  *   no to the BPF scheduler initiated migrations while offline.
  *
  * The caller must ensure that @p and @rq are on different CPUs.
+ * If enforce == true, caller must hold @p's rq lock.
  */
 static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 				      struct task_struct *p, struct rq *rq,
@@ -2314,6 +2315,14 @@ static bool task_can_run_on_remote_rq(struct scx_sched *sch,
 {
 	s32 cpu = cpu_of(rq);
 
+	/*
+	 * To prevent races with @p still running on its old CPU while switching
+	 * out, make sure we're holding @p's rq lock so as not to risk
+	 * erroneously killing the BPF scheduler.
+	 */
+	if (enforce)
+		lockdep_assert_rq_held(task_rq(p));
+
 	WARN_ON_ONCE(task_cpu(p) == cpu);
 
 	/*
@@ -2581,13 +2590,6 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 		return;
 	}
 
-	if (src_rq != dst_rq &&
-	    unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
-		dispatch_enqueue(sch, rq, find_global_dsq(sch, task_cpu(p)), p,
-				 enq_flags | SCX_ENQ_CLEAR_OPSS | SCX_ENQ_GDSQ_FALLBACK);
-		return;
-	}
-
 	/*
 	 * @p is on a possibly remote @src_rq which we need to lock to move the
 	 * task. If dequeue is in progress, it'd be locking @src_rq and waiting
@@ -2614,6 +2616,7 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 	/* task_rq couldn't have changed if we're still the holding cpu */
 	if (likely(p->scx.holding_cpu == raw_smp_processor_id()) &&
 	    !WARN_ON_ONCE(src_rq != task_rq(p))) {
+		bool fallback = false;
 		/*
 		 * If @p is staying on the same rq, there's no need to go
 		 * through the full deactivate/activate cycle. Optimize by
@@ -2623,6 +2626,11 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 			p->scx.holding_cpu = -1;
 			dispatch_enqueue(sch, dst_rq, &dst_rq->scx.local_dsq, p,
 					 enq_flags);
+		} else if (unlikely(!task_can_run_on_remote_rq(sch, p, dst_rq, true))) {
+			p->scx.holding_cpu = -1;
+			fallback = true;
+			dispatch_enqueue(sch, src_rq, find_global_dsq(sch, task_cpu(p)),
+					 p, enq_flags | SCX_ENQ_GDSQ_FALLBACK);
 		} else {
 			move_remote_task_to_local_dsq(p, enq_flags,
 						      src_rq, dst_rq);
@@ -2631,7 +2639,7 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq,
 		}
 
 		/* if the destination CPU is idle, wake it up */
-		if (sched_class_above(p->sched_class, dst_rq->curr->sched_class))
+		if (!fallback && sched_class_above(p->sched_class, dst_rq->curr->sched_class))
 			resched_curr(dst_rq);
 	}
 
diff --git a/kernel/sched/ext/internal.h b/kernel/sched/ext/internal.h
index 145272cb4d8a..673059fa9d72 100644
--- a/kernel/sched/ext/internal.h
+++ b/kernel/sched/ext/internal.h
@@ -1469,21 +1469,24 @@ static const char *scx_enable_state_str[] = {
  * The sched_ext core uses a "lock dancing" protocol coordinated by
  * p->scx.holding_cpu. When moving a task to a different rq:
  *
- *   1. Verify task can be moved (CPU affinity, migration_disabled, etc.)
- *   2. Set p->scx.holding_cpu to the current CPU
- *   3. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING
+ *   1. Set p->scx.holding_cpu to the current CPU
+ *   2. Set task state to %SCX_OPSS_NONE; dequeue waits while DISPATCHING
  *      is set, so clearing DISPATCHING first prevents the circular wait
  *      (safe to lock the rq we need)
- *   4. Unlock the current CPU's rq
- *   5. Lock src_rq (where the task currently lives)
- *   6. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the
+ *   3. Unlock the current CPU's rq
+ *   4. Lock src_rq (where the task currently lives)
+ *   5. Verify p->scx.holding_cpu == current CPU, if not, dequeue won the
  *      race (dequeue clears holding_cpu to -1 when it takes the task), in
  *      this case migration is aborted
- *   7. If src_rq == dst_rq: clear holding_cpu and enqueue directly
+ *   6. If src_rq == dst_rq: clear holding_cpu and enqueue directly
  *      into dst_rq's local DSQ (no lock swap needed)
- *   8. Otherwise: call move_remote_task_to_local_dsq(), which releases
- *      src_rq, locks dst_rq, and performs the deactivate/activate
- *      migration cycle (dst_rq is held on return)
+ *   7. Otherwise, verify under src_rq lock that the task can be moved to dst_rq
+ *      (CPU affinity, migration_disabled, etc.). If not, clear holding_cpu,
+ *      leave the task on src_rq, and enqueue it on the fallback DSQ.
+ *   8. Otherwise (i.e. if the task can be moved to dst_rq), call
+ *      move_remote_task_to_local_dsq(), which releases src_rq, locks dst_rq,
+ *      and performs the deactivate/activate migration cycle
+ *      (dst_rq is held on return)
  *   9. Unlock dst_rq and re-lock the current CPU's rq to restore
  *      the lock state expected by the caller
  *