Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Sender: Tejun Heo <htejun@gmail.com>
From:   Tejun Heo <tj@kernel.org>
To:     torvalds@linux-foundation.org, mingo@redhat.com,
        peterz@infradead.org, juri.lelli@redhat.com,
        vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
        rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
        bristot@redhat.com, vschneid@redhat.com, ast@kernel.org,
        daniel@iogearbox.net, andrii@kernel.org, martin.lau@kernel.org,
        joshdon@google.com, brho@google.com, pjt@google.com,
        derkling@google.com, haoluo@google.com, dvernet@meta.com,
        dschatzberg@meta.com, dskarlat@cs.cmu.edu, riel@surriel.com
Cc:     linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
        kernel-team@meta.com, Tejun Heo <tj@kernel.org>
Subject: [PATCH 29/34] sched_ext: Implement sched_ext_ops.cpu_online/offline()
Date:   Mon, 10 Jul 2023 15:13:47 -1000
Message-ID: <20230711011412.100319-30-tj@kernel.org>
In-Reply-To: <20230711011412.100319-1-tj@kernel.org>
References: <20230711011412.100319-1-tj@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Add ops.cpu_online/offline() which are invoked when CPUs come online and
offline respectively. As the enqueue path already automatically bypasses
tasks to the local dsq on a deactivated CPU, BPF schedulers are guaranteed
to see tasks only on CPUs which are between online() and offline().

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: David Vernet <dvernet@meta.com>
Acked-by: Josh Don <joshdon@google.com>
Acked-by: Hao Luo <haoluo@google.com>
Acked-by: Barret Rhoden <brho@google.com>
---
 include/linux/sched/ext.h | 18 ++++++++++++++++++
 kernel/sched/ext.c        | 18 +++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 8a275ec05ee1..c17957bd75df 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -377,6 +377,24 @@ struct sched_ext_ops {
 	 */
 	void (*cpu_release)(s32 cpu, struct scx_cpu_release_args *args);
 
+	/**
+	 * cpu_online - A CPU became online
+	 * @cpu: CPU which just came up
+	 *
+	 * @cpu just came online. @cpu doesn't call ops.enqueue() or run tasks
+	 * associated with other CPUs beforehand.
+	 */
+	void (*cpu_online)(s32 cpu);
+
+	/**
+	 * cpu_offline - A CPU is going offline
+	 * @cpu: CPU which is going offline
+	 *
+	 * @cpu is going offline. @cpu doesn't call ops.enqueue() or run tasks
+	 * associated with other CPUs afterwards.
+	 */
+	void (*cpu_offline)(s32 cpu);
+
 	/**
 	 * prep_enable - Prepare to enable BPF scheduling for a task
 	 * @p: task to prepare BPF scheduling for
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 1b83dddbdf10..e54d8c7d19a9 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1392,7 +1392,8 @@ static int balance_scx(struct rq *rq, struct task_struct *prev,
 		 * emitted in scx_notify_pick_next_task().
 		 */
 		if (SCX_HAS_OP(cpu_acquire))
-			SCX_CALL_OP(0, cpu_acquire, cpu_of(rq), NULL);
+			SCX_CALL_OP(SCX_KF_UNLOCKED, cpu_acquire, cpu_of(rq),
+				    NULL);
 		rq->scx.cpu_released = false;
 	}
 
@@ -1852,6 +1853,18 @@ void __scx_update_idle(struct rq *rq, bool idle)
 #endif
 }
 
+static void rq_online_scx(struct rq *rq, enum rq_onoff_reason reason)
+{
+	if (SCX_HAS_OP(cpu_online) && reason == RQ_ONOFF_HOTPLUG)
+		SCX_CALL_OP(SCX_KF_REST, cpu_online, cpu_of(rq));
+}
+
+static void rq_offline_scx(struct rq *rq, enum rq_onoff_reason reason)
+{
+	if (SCX_HAS_OP(cpu_offline) && reason == RQ_ONOFF_HOTPLUG)
+		SCX_CALL_OP(SCX_KF_REST, cpu_offline, cpu_of(rq));
+}
+
 #else /* !CONFIG_SMP */
 
 static bool test_and_clear_cpu_idle(int cpu) { return false; }
@@ -2370,6 +2383,9 @@ DEFINE_SCHED_CLASS(ext) = {
 	.balance		= balance_scx,
 	.select_task_rq		= select_task_rq_scx,
 	.set_cpus_allowed	= set_cpus_allowed_scx,
+
+	.rq_online		= rq_online_scx,
+	.rq_offline		= rq_offline_scx,
 #endif
 
 	.task_tick		= task_tick_scx,
-- 
2.41.0