linux-kernel - [PATCH v5 11/14] sched/ext: Relinquish DL server reservations when not needed

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20250620203234.3349930-12-joelagnelf@nvidia.com>
Date: Fri, 20 Jun 2025 16:32:26 -0400
From: Joel Fernandes <joelagnelf@...dia.com>
To: linux-kernel@...r.kernel.org,
	Tejun Heo <tj@...nel.org>,
	David Vernet <void@...ifault.com>,
	Andrea Righi <arighi@...dia.com>,
	Changwoo Min <changwoo@...lia.com>,
	Ingo Molnar <mingo@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Juri Lelli <juri.lelli@...hat.com>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	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>
Cc: Joel Fernandes <joelagnelf@...dia.com>,
	sched-ext@...ts.linux.dev
Subject: [PATCH v5 11/14] sched/ext: Relinquish DL server reservations when not needed

I tested loading a test SCX program and verifying the bandwidth both
before and after applying the patch:

Without patch:
Before loading scx:
  .dl_bw->total_bw               : 1887408
After unloading scx:
  .dl_bw->total_bw               : 3774816

After patch:
Before loading scx:
  .dl_bw->total_bw               : 1887408
After unloading scx:
  .dl_bw->total_bw               : 1887408

Co-developed-by: Andrea Righi <arighi@...dia.com>
Signed-off-by: Joel Fernandes <joelagnelf@...dia.com>
---
 kernel/sched/ext.c | 56 ++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 47 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 34c95100fbe5..6bc0ce358238 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4965,6 +4965,31 @@ static void scx_disable_workfn(struct kthread_work *work)
 
 	scx_init_task_enabled = false;
 
+	for_each_possible_cpu(cpu) {
+		struct rq *rq = cpu_rq(cpu);
+		struct rq_flags rf;
+
+		/*
+		 * Invalidate all the rq clocks to prevent getting outdated
+		 * rq clocks from a previous scx scheduler.
+		 */
+		scx_rq_clock_invalidate(rq);
+
+		/*
+		 * We are unloading the sched_ext scheduler, we do not need its
+		 * DL server bandwidth anymore, remove it for all CPUs. Whenever
+		 * the first SCX task is enqueued (when scx is re-loaded), its DL
+		 * server bandwidth will be re-initialized.
+		 */
+		rq_lock_irqsave(rq, &rf);
+		update_rq_clock(rq);
+		if (dl_server_active(&rq->ext_server))
+			dl_server_stop(&rq->ext_server);
+		dl_server_remove_params(&rq->ext_server);
+		rq_unlock_irqrestore(rq, &rf);
+	}
+
+
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
 		const struct sched_class *old_class = p->sched_class;
@@ -4988,15 +5013,6 @@ static void scx_disable_workfn(struct kthread_work *work)
 	scx_task_iter_stop(&sti);
 	percpu_up_write(&scx_fork_rwsem);
 
-	/*
-	 * Invalidate all the rq clocks to prevent getting outdated
-	 * rq clocks from a previous scx scheduler.
-	 */
-	for_each_possible_cpu(cpu) {
-		struct rq *rq = cpu_rq(cpu);
-		scx_rq_clock_invalidate(rq);
-	}
-
 	/* no task is on scx, turn off all the switches and flush in-progress calls */
 	static_branch_disable(&__scx_enabled);
 	bitmap_zero(sch->has_op, SCX_OPI_END);
@@ -5730,6 +5746,28 @@ static int scx_enable(struct sched_ext_ops *ops, struct bpf_link *link)
 		check_class_changed(task_rq(p), p, old_class, p->prio);
 	}
 	scx_task_iter_stop(&sti);
+
+	if (scx_switching_all) {
+		for_each_possible_cpu(cpu) {
+			struct rq *rq = cpu_rq(cpu);
+			struct rq_flags rf;
+
+			/*
+			 * We are switching all fair tasks to the sched_ext scheduler,
+			 * we do not need fair server's DL bandwidth anymore, remove it
+			 * for all CPUs. Whenever the first CFS task is enqueued (when
+			 * scx is unloaded), the fair server's DL bandwidth will be
+			 * re-initialized.
+			 */
+			rq_lock_irqsave(rq, &rf);
+			update_rq_clock(rq);
+			if (dl_server_active(&rq->fair_server))
+				dl_server_stop(&rq->fair_server);
+			dl_server_remove_params(&rq->fair_server);
+			rq_unlock_irqrestore(rq, &rf);
+		}
+	}
+
 	percpu_up_write(&scx_fork_rwsem);
 
 	scx_bypass(false);
-- 
2.43.0