diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f0d68a636da1..e2ab638162b9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4947,7 +4947,13 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 	s64 delta;
 	bool skip_preempt = false;
 
-	ideal_runtime = sched_slice(cfs_rq, curr);
+	/*
+	 * When many tasks blow up the sched_period; it is possible that
+	 * sched_slice() reports unusually large results (when many tasks are
+	 * very light for example). Therefore impose a maximum.
+	 */
+	ideal_runtime = min_t(u64, sched_slice(cfs_rq, curr), sysctl_sched_latency);
+
 	delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
 	trace_android_rvh_check_preempt_tick(current, &ideal_runtime, &skip_preempt,
 			delta_exec, cfs_rq, curr, sysctl_sched_min_granularity);