From: zhidao su <suzhidao@xiaomi.com>
Date: Sat, 11 Oct 2025 07:16:51 +0000 (+0800)
Subject: sched/ext: Implement cgroup_set_idle() callback
X-Git-Tag: v6.19-rc1~177^2~41
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=347ed2d566dabb06c7970fff01129c4f59995ed6;p=thirdparty%2Fkernel%2Flinux.git

sched/ext: Implement cgroup_set_idle() callback

Implement the missing cgroup_set_idle() callback that was marked as a
TODO. This allows BPF schedulers to be notified when a cgroup's idle
state changes, enabling them to adjust their scheduling behavior
accordingly.

The implementation follows the same pattern as other cgroup callbacks
like cgroup_set_weight() and cgroup_set_bandwidth(). It checks if the
BPF scheduler has implemented the callback and invokes it with the
appropriate parameters.

Fixes a spelling error in the cgroup_set_bandwidth() documentation.

tj: s/scx_cgroup_rwsem/scx_cgroup_ops_rwsem/ to fix build breakage.

Signed-off-by: zhidao su <soolaugust@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index d82b7a9b0658b..9848aeab27864 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -228,6 +228,7 @@ struct scx_task_group {
 	u64			bw_period_us;
 	u64			bw_quota_us;
 	u64			bw_burst_us;
+	bool			idle;
 #endif
 };
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 4b1467d3541a4..430749ce46ab3 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3066,6 +3066,7 @@ void scx_tg_init(struct task_group *tg)
 	tg->scx.weight = CGROUP_WEIGHT_DFL;
 	tg->scx.bw_period_us = default_bw_period_us();
 	tg->scx.bw_quota_us = RUNTIME_INF;
+	tg->scx.idle = false;
 }
 
 int scx_tg_online(struct task_group *tg)
@@ -3214,7 +3215,18 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 
 void scx_group_set_idle(struct task_group *tg, bool idle)
 {
-	/* TODO: Implement ops->cgroup_set_idle() */
+	struct scx_sched *sch = scx_root;
+
+	percpu_down_read(&scx_cgroup_ops_rwsem);
+
+	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_idle))
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_idle, NULL,
+			    tg_cgrp(tg), idle);
+
+	/* Update the task group's idle state */
+	tg->scx.idle = idle;
+
+	percpu_up_read(&scx_cgroup_ops_rwsem);
 }
 
 void scx_group_set_bandwidth(struct task_group *tg,
@@ -5017,6 +5029,7 @@ static void sched_ext_ops__cgroup_move(struct task_struct *p, struct cgroup *fro
 static void sched_ext_ops__cgroup_cancel_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
 static void sched_ext_ops__cgroup_set_weight(struct cgroup *cgrp, u32 weight) {}
 static void sched_ext_ops__cgroup_set_bandwidth(struct cgroup *cgrp, u64 period_us, u64 quota_us, u64 burst_us) {}
+static void sched_ext_ops__cgroup_set_idle(struct cgroup *cgrp, bool idle) {}
 #endif
 static void sched_ext_ops__cpu_online(s32 cpu) {}
 static void sched_ext_ops__cpu_offline(s32 cpu) {}
@@ -5055,6 +5068,7 @@ static struct sched_ext_ops __bpf_ops_sched_ext_ops = {
 	.cgroup_cancel_move	= sched_ext_ops__cgroup_cancel_move,
 	.cgroup_set_weight	= sched_ext_ops__cgroup_set_weight,
 	.cgroup_set_bandwidth	= sched_ext_ops__cgroup_set_bandwidth,
+	.cgroup_set_idle	= sched_ext_ops__cgroup_set_idle,
 #endif
 	.cpu_online		= sched_ext_ops__cpu_online,
 	.cpu_offline		= sched_ext_ops__cpu_offline,
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index b3617abed5108..7d00a0a2456e2 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -697,12 +697,23 @@ struct sched_ext_ops {
 	 * 2_500_000. @cgrp is entitled to 2.5 CPUs. @burst_us can be
 	 * interpreted in the same fashion and specifies how much @cgrp can
 	 * burst temporarily. The specific control mechanism and thus the
-	 * interpretation of @period_us and burstiness is upto to the BPF
+	 * interpretation of @period_us and burstiness is up to the BPF
 	 * scheduler.
 	 */
 	void (*cgroup_set_bandwidth)(struct cgroup *cgrp,
 				     u64 period_us, u64 quota_us, u64 burst_us);
 
+	/**
+	 * @cgroup_set_idle: A cgroup's idle state is being changed
+	 * @cgrp: cgroup whose idle state is being updated
+	 * @idle: whether the cgroup is entering or exiting idle state
+	 *
+	 * Update @cgrp's idle state to @idle. This callback is invoked when
+	 * a cgroup transitions between idle and non-idle states, allowing the
+	 * BPF scheduler to adjust its behavior accordingly.
+	 */
+	void (*cgroup_set_idle)(struct cgroup *cgrp, bool idle);
+
 #endif	/* CONFIG_EXT_GROUP_SCHED */
 
 	/*