From: Valentin Schneider <vschneid@redhat.com>
Date: Fri, 29 Aug 2025 08:11:17 +0000 (+0800)
Subject: sched/fair: Implement throttle task work and related helpers
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=7fc2d14392475e368a2a7be458aba4eecdf2439b;p=users%2Fhch%2Fmisc.git

sched/fair: Implement throttle task work and related helpers

Implement throttle_cfs_rq_work() task work which gets executed on task's
ret2user path where the task is dequeued and marked as throttled.

Signed-off-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Aaron Lu <ziqianlu@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Tested-by: Valentin Schneider <vschneid@redhat.com>
Tested-by: Matteo Martelli <matteo.martelli@codethink.co.uk>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20250829081120.806-3-ziqianlu@bytedance.com
---

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8fff40fcbc42..dab4ed86d0c8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5748,8 +5748,51 @@ static inline int throttled_lb_pair(struct task_group *tg,
 	       throttled_hierarchy(dest_cfs_rq);
 }
 
+static inline bool task_is_throttled(struct task_struct *p)
+{
+	return cfs_bandwidth_used() && p->throttled;
+}
+
+static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags);
 static void throttle_cfs_rq_work(struct callback_head *work)
 {
+	struct task_struct *p = container_of(work, struct task_struct, sched_throttle_work);
+	struct sched_entity *se;
+	struct cfs_rq *cfs_rq;
+	struct rq *rq;
+
+	WARN_ON_ONCE(p != current);
+	p->sched_throttle_work.next = &p->sched_throttle_work;
+
+	/*
+	 * If task is exiting, then there won't be a return to userspace, so we
+	 * don't have to bother with any of this.
+	 */
+	if ((p->flags & PF_EXITING))
+		return;
+
+	scoped_guard(task_rq_lock, p) {
+		se = &p->se;
+		cfs_rq = cfs_rq_of(se);
+
+		/* Raced, forget */
+		if (p->sched_class != &fair_sched_class)
+			return;
+
+		/*
+		 * If not in limbo, then either replenish has happened or this
+		 * task got migrated out of the throttled cfs_rq, move along.
+		 */
+		if (!cfs_rq->throttle_count)
+			return;
+		rq = scope.rq;
+		update_rq_clock(rq);
+		WARN_ON_ONCE(p->throttled || !list_empty(&p->throttle_node));
+		dequeue_task_fair(rq, p, DEQUEUE_SLEEP | DEQUEUE_SPECIAL);
+		list_add(&p->throttle_node, &cfs_rq->throttled_limbo_list);
+		p->throttled = true;
+		resched_curr(rq);
+	}
 }
 
 void init_cfs_throttle_work(struct task_struct *p)
@@ -5789,6 +5832,26 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 	return 0;
 }
 
+static inline bool task_has_throttle_work(struct task_struct *p)
+{
+	return p->sched_throttle_work.next != &p->sched_throttle_work;
+}
+
+static inline void task_throttle_setup_work(struct task_struct *p)
+{
+	if (task_has_throttle_work(p))
+		return;
+
+	/*
+	 * Kthreads and exiting tasks don't return to userspace, so adding the
+	 * work is pointless
+	 */
+	if ((p->flags & (PF_EXITING | PF_KTHREAD)))
+		return;
+
+	task_work_add(p, &p->sched_throttle_work, TWA_RESUME);
+}
+
 static int tg_throttle_down(struct task_group *tg, void *data)
 {
 	struct rq *rq = data;
@@ -6652,6 +6715,8 @@ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
 static inline void sync_throttle(struct task_group *tg, int cpu) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
+static void task_throttle_setup_work(struct task_struct *p) {}
+static bool task_is_throttled(struct task_struct *p) { return false; }
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
 {