linux-kernel - [PATCH 04/14] sched: Cleanup sched_delayed handling for class switches

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: <20250910155808.764084708@infradead.org>
Date: Wed, 10 Sep 2025 17:44:13 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: tj@...nel.org
Cc: linux-kernel@...r.kernel.org,
 peterz@...radead.org,
 mingo@...hat.com,
 juri.lelli@...hat.com,
 vincent.guittot@...aro.org,
 dietmar.eggemann@....com,
 rostedt@...dmis.org,
 bsegall@...gle.com,
 mgorman@...e.de,
 vschneid@...hat.com,
 longman@...hat.com,
 hannes@...xchg.org,
 mkoutny@...e.com,
 void@...ifault.com,
 arighi@...dia.com,
 changwoo@...lia.com,
 cgroups@...r.kernel.org,
 sched-ext@...ts.linux.dev,
 liuwenfang@...or.com,
 tglx@...utronix.de
Subject: [PATCH 04/14] sched: Cleanup sched_delayed handling for class switches

Use the new sched_class::switching_from() method to dequeue delayed
tasks before switching to another class.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 kernel/sched/core.c     |   12 ++++++++----
 kernel/sched/ext.c      |    6 ------
 kernel/sched/fair.c     |    7 +++++++
 kernel/sched/syscalls.c |    3 ---
 4 files changed, 15 insertions(+), 13 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7403,9 +7403,6 @@ void rt_mutex_setprio(struct task_struct
 		queue_flag &= ~(DEQUEUE_SAVE | DEQUEUE_MOVE);
 	}
 
-	if (prev_class != next_class && p->se.sched_delayed)
-		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
-
 	scoped_guard (sched_change, p, queue_flag) {
 		/*
 		 * Boosting condition are:
@@ -10879,8 +10876,15 @@ struct sched_change_ctx *sched_change_be
 		if (WARN_ON_ONCE(flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)))
 			flags &= ~(DEQUEUE_SAVE | DEQUEUE_MOVE);
 
-		if (p->sched_class->switching_from)
+		if (p->sched_class->switching_from) {
+			/*
+			 * switching_from_fair() assumes CLASS implies NOCLOCK;
+			 * fixing this assumption would mean switching_from()
+			 * would need to be able to change flags.
+			 */
+			WARN_ON(!(flags & DEQUEUE_NOCLOCK));
 			p->sched_class->switching_from(rq, p);
+		}
 	}
 
 	*ctx = (struct sched_change_ctx){
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5011,9 +5011,6 @@ static void scx_disable_workfn(struct kt
 			queue_flags &= ~(DEQUEUE_SAVE | DEQUEUE_MOVE);
 		}
 
-		if (old_class != new_class && p->se.sched_delayed)
-			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
-
 		scoped_guard (sched_change, p, queue_flags) {
 			p->sched_class = new_class;
 		}
@@ -5764,9 +5761,6 @@ static int scx_enable(struct sched_ext_o
 			queue_flags &= ~(DEQUEUE_SAVE | DEQUEUE_MOVE);
 		}
 
-		if (old_class != new_class && p->se.sched_delayed)
-			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
-
 		scoped_guard (sched_change, p, queue_flags) {
 			p->scx.slice = SCX_SLICE_DFL;
 			p->sched_class = new_class;
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -13221,6 +13221,12 @@ static void attach_task_cfs_rq(struct ta
 	attach_entity_cfs_rq(se);
 }
 
+static void switching_from_fair(struct rq *rq, struct task_struct *p)
+{
+	if (p->se.sched_delayed)
+		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
+}
+
 static void switched_from_fair(struct rq *rq, struct task_struct *p)
 {
 	detach_task_cfs_rq(p);
@@ -13622,6 +13628,7 @@ DEFINE_SCHED_CLASS(fair) = {
 
 	.reweight_task		= reweight_task_fair,
 	.prio_changed		= prio_changed_fair,
+	.switching_from		= switching_from_fair,
 	.switched_from		= switched_from_fair,
 	.switched_to		= switched_to_fair,
 
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -689,9 +689,6 @@ int __sched_setscheduler(struct task_str
 		queue_flags &= ~(DEQUEUE_SAVE | DEQUEUE_MOVE);
 	}
 
-	if (prev_class != next_class && p->se.sched_delayed)
-		dequeue_task(rq, p, DEQUEUE_SLEEP | DEQUEUE_DELAYED | DEQUEUE_NOCLOCK);
-
 	scoped_guard (sched_change, p, queue_flags) {
 
 		if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {