Received-SPF: pass (google.com: domain of linux-kernel+bounces-165427-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
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,
	changwoo@igalia.com,
	himadrics@inria.fr,
	memxor@gmail.com,
	andrea.righi@canonical.com,
	joel@joelfernandes.org
Cc: linux-kernel@vger.kernel.org,
	bpf@vger.kernel.org,
	kernel-team@meta.com,
	Tejun Heo <tj@kernel.org>
Subject: [PATCH 09/39] sched: Add @reason to sched_class->rq_{on|off}line()
Date: Wed,  1 May 2024 05:09:44 -1000
Message-ID: <20240501151312.635565-10-tj@kernel.org>
In-Reply-To: <20240501151312.635565-1-tj@kernel.org>
References: <20240501151312.635565-1-tj@kernel.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

->rq_{on|off}line are called either during CPU hotplug or cpuset partition
updates. A planned BPF extensible sched_class wants to tell the BPF
scheduler progs about CPU hotplug events in a way that's synchronized with
rq state changes.

As the BPF scheduler progs aren't necessarily affected by cpuset partition
updates, we need a way to distinguish the two types of events. Let's add an
argument to tell them apart.

v2: Patch description updated to detail the expected use.

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>
---
 kernel/sched/core.c     | 12 ++++++------
 kernel/sched/deadline.c |  4 ++--
 kernel/sched/fair.c     |  4 ++--
 kernel/sched/rt.c       |  4 ++--
 kernel/sched/sched.h    | 13 +++++++++----
 kernel/sched/topology.c |  4 ++--
 6 files changed, 23 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e48af9fbbd71..90b505fbb488 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9593,7 +9593,7 @@ static inline void balance_hotplug_wait(void)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
-void set_rq_online(struct rq *rq)
+void set_rq_online(struct rq *rq, enum rq_onoff_reason reason)
 {
 	if (!rq->online) {
 		const struct sched_class *class;
@@ -9603,12 +9603,12 @@ void set_rq_online(struct rq *rq)
 
 		for_each_class(class) {
 			if (class->rq_online)
-				class->rq_online(rq);
+				class->rq_online(rq, reason);
 		}
 	}
 }
 
-void set_rq_offline(struct rq *rq)
+void set_rq_offline(struct rq *rq, enum rq_onoff_reason reason)
 {
 	if (rq->online) {
 		const struct sched_class *class;
@@ -9616,7 +9616,7 @@ void set_rq_offline(struct rq *rq)
 		update_rq_clock(rq);
 		for_each_class(class) {
 			if (class->rq_offline)
-				class->rq_offline(rq);
+				class->rq_offline(rq, reason);
 		}
 
 		cpumask_clear_cpu(rq->cpu, rq->rd->online);
@@ -9712,7 +9712,7 @@ int sched_cpu_activate(unsigned int cpu)
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-		set_rq_online(rq);
+		set_rq_online(rq, RQ_ONOFF_HOTPLUG);
 	}
 	rq_unlock_irqrestore(rq, &rf);
 
@@ -9756,7 +9756,7 @@ int sched_cpu_deactivate(unsigned int cpu)
 	rq_lock_irqsave(rq, &rf);
 	if (rq->rd) {
 		BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
-		set_rq_offline(rq);
+		set_rq_offline(rq, RQ_ONOFF_HOTPLUG);
 	}
 	rq_unlock_irqrestore(rq, &rf);
 
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a04a436af8cc..010d1dc5f918 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2607,7 +2607,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
 }
 
 /* Assumes rq->lock is held */
-static void rq_online_dl(struct rq *rq)
+static void rq_online_dl(struct rq *rq, enum rq_onoff_reason reason)
 {
 	if (rq->dl.overloaded)
 		dl_set_overload(rq);
@@ -2618,7 +2618,7 @@ static void rq_online_dl(struct rq *rq)
 }
 
 /* Assumes rq->lock is held */
-static void rq_offline_dl(struct rq *rq)
+static void rq_offline_dl(struct rq *rq, enum rq_onoff_reason reason)
 {
 	if (rq->dl.overloaded)
 		dl_clear_overload(rq);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5d7cffee1a4e..8032256d3972 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12446,14 +12446,14 @@ void trigger_load_balance(struct rq *rq)
 	nohz_balancer_kick(rq);
 }
 
-static void rq_online_fair(struct rq *rq)
+static void rq_online_fair(struct rq *rq, enum rq_onoff_reason reason)
 {
 	update_sysctl();
 
 	update_runtime_enabled(rq);
 }
 
-static void rq_offline_fair(struct rq *rq)
+static void rq_offline_fair(struct rq *rq, enum rq_onoff_reason reason)
 {
 	update_sysctl();
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3261b067b67e..8620474d117d 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2426,7 +2426,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 }
 
 /* Assumes rq->lock is held */
-static void rq_online_rt(struct rq *rq)
+static void rq_online_rt(struct rq *rq, enum rq_onoff_reason reason)
 {
 	if (rq->rt.overloaded)
 		rt_set_overload(rq);
@@ -2437,7 +2437,7 @@ static void rq_online_rt(struct rq *rq)
 }
 
 /* Assumes rq->lock is held */
-static void rq_offline_rt(struct rq *rq)
+static void rq_offline_rt(struct rq *rq, enum rq_onoff_reason reason)
 {
 	if (rq->rt.overloaded)
 		rt_clear_overload(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 0b6a34ba2457..bcc8056acadb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2271,6 +2271,11 @@ extern const u32		sched_prio_to_wmult[40];
 
 #define RETRY_TASK		((void *)-1UL)
 
+enum rq_onoff_reason {
+	RQ_ONOFF_HOTPLUG,		/* CPU is going on/offline */
+	RQ_ONOFF_TOPOLOGY,		/* sched domain topology update */
+};
+
 struct affinity_context {
 	const struct cpumask *new_mask;
 	struct cpumask *user_mask;
@@ -2309,8 +2314,8 @@ struct sched_class {
 
 	void (*set_cpus_allowed)(struct task_struct *p, struct affinity_context *ctx);
 
-	void (*rq_online)(struct rq *rq);
-	void (*rq_offline)(struct rq *rq);
+	void (*rq_online)(struct rq *rq, enum rq_onoff_reason reason);
+	void (*rq_offline)(struct rq *rq, enum rq_onoff_reason reason);
 
 	struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
 #endif
@@ -2853,8 +2858,8 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 	raw_spin_rq_unlock(rq1);
 }
 
-extern void set_rq_online (struct rq *rq);
-extern void set_rq_offline(struct rq *rq);
+extern void set_rq_online (struct rq *rq, enum rq_onoff_reason reason);
+extern void set_rq_offline(struct rq *rq, enum rq_onoff_reason reason);
 extern bool sched_smp_initialized;
 
 #else /* CONFIG_SMP */
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 99ea5986038c..12501543c56d 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -497,7 +497,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 		old_rd = rq->rd;
 
 		if (cpumask_test_cpu(rq->cpu, old_rd->online))
-			set_rq_offline(rq);
+			set_rq_offline(rq, RQ_ONOFF_TOPOLOGY);
 
 		cpumask_clear_cpu(rq->cpu, old_rd->span);
 
@@ -515,7 +515,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 
 	cpumask_set_cpu(rq->cpu, rd->span);
 	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
-		set_rq_online(rq);
+		set_rq_online(rq, RQ_ONOFF_TOPOLOGY);
 
 	rq_unlock_irqrestore(rq, &rf);
 
-- 
2.44.0