3 files changed, 27 insertions, 11 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 89e54f3ed571..1a9983da4408 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1447,17 +1447,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 
 #ifdef CONFIG_SMP
 
-static inline bool is_per_cpu_kthread(struct task_struct *p)
-{
-	if (!(p->flags & PF_KTHREAD))
-		return false;
-
-	if (p->nr_cpus_allowed != 1)
-		return false;
-
-	return true;
-}
-
 /*
  * Per-CPU kthreads are allowed to run on !active && online CPUs, see
  * __set_cpus_allowed_ptr() and select_fallback_rq().
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 25dffc03f0f6..94c3b8469cf6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5912,6 +5912,20 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	    (available_idle_cpu(prev) || sched_idle_cpu(prev)))
 		return prev;
 
+	/*
+	 * Allow a per-cpu kthread to stack with the wakee if the
+	 * kworker thread and the tasks previous CPUs are the same.
+	 * The assumption is that the wakee queued work for the
+	 * per-cpu kthread that is now complete and the wakeup is
+	 * essentially a sync wakeup. An obvious example of this
+	 * pattern is IO completions.
+	 */
+	if (is_per_cpu_kthread(current) &&
+	    prev == smp_processor_id() &&
+	    this_rq()->nr_running <= 1) {
+		return prev;
+	}
+
 	/* Check a recently used CPU as a potential idle candidate: */
 	recent_used_cpu = p->recent_used_cpu;
 	if (recent_used_cpu != prev &&
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 1a88dc8ad11b..5876e6ba5903 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2479,3 +2479,16 @@ static inline void membarrier_switch_mm(struct rq *rq,
 {
 }
 #endif
+
+#ifdef CONFIG_SMP
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+	if (!(p->flags & PF_KTHREAD))
+		return false;
+
+	if (p->nr_cpus_allowed != 1)
+		return false;
+
+	return true;
+}
+#endif