linux-kernel - [PATCH 08/11] sched/deadline: Account ext server bandwidth

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251029191111.167537-9-arighi@nvidia.com>
Date: Wed, 29 Oct 2025 20:08:45 +0100
From: Andrea Righi <arighi@...dia.com>
To: Ingo Molnar <mingo@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Juri Lelli <juri.lelli@...hat.com>,
	Vincent Guittot <vincent.guittot@...aro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@....com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Valentin Schneider <vschneid@...hat.com>,
	Tejun Heo <tj@...nel.org>,
	David Vernet <void@...ifault.com>,
	Changwoo Min <changwoo@...lia.com>,
	Shuah Khan <shuah@...nel.org>,
	Joel Fernandes <joelagnelf@...dia.com>,
	Christian Loehle <christian.loehle@....com>,
	Emil Tsalapatis <emil@...alapatis.com>,
	Luigi De Matteis <ldematteis123@...il.com>,
	sched-ext@...ts.linux.dev,
	bpf@...r.kernel.org,
	linux-kselftest@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: [PATCH 08/11] sched/deadline: Account ext server bandwidth

Always account for both the ext_server and fair_server bandwidth,
especially during CPU hotplug operations.

Ignoring either can lead to imbalances in total_bw when sched_ext
schedulers are active and CPUs are brought online / offline.

Signed-off-by: Andrea Righi <arighi@...dia.com>
---
 kernel/sched/deadline.c | 54 +++++++++++++++++++++++++++++++----------
 kernel/sched/topology.c |  5 ++++
 2 files changed, 46 insertions(+), 13 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 6ecfaaa1f912d..f786174a126c8 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2994,6 +2994,36 @@ void dl_add_task_root_domain(struct task_struct *p)
 	task_rq_unlock(rq, p, &rf);
 }
 
+static void dl_server_add_bw(struct root_domain *rd, int cpu)
+{
+	struct sched_dl_entity *dl_se;
+
+	dl_se = &cpu_rq(cpu)->fair_server;
+	if (dl_server(dl_se))
+		__dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(cpu));
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+	dl_se = &cpu_rq(cpu)->ext_server;
+	if (dl_server(dl_se))
+		__dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(cpu));
+#endif
+}
+
+static u64 dl_server_read_bw(int cpu)
+{
+	u64 dl_bw = 0;
+
+	if (cpu_rq(cpu)->fair_server.dl_server)
+		dl_bw += cpu_rq(cpu)->fair_server.dl_bw;
+
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (cpu_rq(cpu)->ext_server.dl_server)
+		dl_bw += cpu_rq(cpu)->ext_server.dl_bw;
+#endif
+
+	return dl_bw;
+}
+
 void dl_clear_root_domain(struct root_domain *rd)
 {
 	int i;
@@ -3013,10 +3043,9 @@ void dl_clear_root_domain(struct root_domain *rd)
 	 * them, we need to account for them here explicitly.
 	 */
 	for_each_cpu(i, rd->span) {
-		struct sched_dl_entity *dl_se = &cpu_rq(i)->fair_server;
-
-		if (dl_server(dl_se) && cpu_active(i))
-			__dl_add(&rd->dl_bw, dl_se->dl_bw, dl_bw_cpus(i));
+		if (!cpu_active(i))
+			continue;
+		dl_server_add_bw(rd, i);
 	}
 }
 
@@ -3513,7 +3542,7 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 	unsigned long flags, cap;
 	struct dl_bw *dl_b;
 	bool overflow = 0;
-	u64 fair_server_bw = 0;
+	u64 dl_server_bw = 0;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
@@ -3546,27 +3575,26 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 		cap -= arch_scale_cpu_capacity(cpu);
 
 		/*
-		 * cpu is going offline and NORMAL tasks will be moved away
-		 * from it. We can thus discount dl_server bandwidth
-		 * contribution as it won't need to be servicing tasks after
-		 * the cpu is off.
+		 * cpu is going offline and NORMAL and EXT tasks will be
+		 * moved away from it. We can thus discount dl_server
+		 * bandwidth contribution as it won't need to be servicing
+		 * tasks after the cpu is off.
 		 */
-		if (cpu_rq(cpu)->fair_server.dl_server)
-			fair_server_bw = cpu_rq(cpu)->fair_server.dl_bw;
+		dl_server_bw = dl_server_read_bw(cpu);
 
 		/*
 		 * Not much to check if no DEADLINE bandwidth is present.
 		 * dl_servers we can discount, as tasks will be moved out the
 		 * offlined CPUs anyway.
 		 */
-		if (dl_b->total_bw - fair_server_bw > 0) {
+		if (dl_b->total_bw - dl_server_bw > 0) {
 			/*
 			 * Leaving at least one CPU for DEADLINE tasks seems a
 			 * wise thing to do. As said above, cpu is not offline
 			 * yet, so account for that.
 			 */
 			if (dl_bw_cpus(cpu) - 1)
-				overflow = __dl_overflow(dl_b, cap, fair_server_bw, 0);
+				overflow = __dl_overflow(dl_b, cap, dl_server_bw, 0);
 			else
 				overflow = 1;
 		}
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 711076aa49801..1ec8e74b80219 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -508,6 +508,11 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (rq->fair_server.dl_server)
 		__dl_server_attach_root(&rq->fair_server, rq);
 
+#ifdef CONFIG_SCHED_CLASS_EXT
+	if (rq->ext_server.dl_server)
+		__dl_server_attach_root(&rq->ext_server, rq);
+#endif
+
 	rq_unlock_irqrestore(rq, &rf);
 
 	if (old_rd)
-- 
2.51.2