The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: mingo@kernel.org
Cc: peterz@infradead.org, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com, mgorman@suse.de,
	vschneid@redhat.com, tj@kernel.org, void@manifault.com,
	linux-kernel@vger.kernel.org
Subject: [RFC][PATCH 6/6] sched: Cleanup sched_delayed handling for class switches
Date: Wed, 30 Oct 2024 16:13:01 +0100	[thread overview]
Message-ID: <20241030152142.928034708@infradead.org> (raw)
In-Reply-To: 20241030151255.300069509@infradead.org

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

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/core.c     |   12 ++++++++----
 kernel/sched/ext.c      |   12 ++++--------
 kernel/sched/fair.c     |    7 +++++++
 kernel/sched/syscalls.c |    3 ---
 4 files changed, 19 insertions(+), 15 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7139,9 +7139,6 @@ void rt_mutex_setprio(struct task_struct
 	if (prev_class != next_class)
 		queue_flag |= DEQUEUE_CLASS;
 
-	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:
@@ -10530,8 +10527,15 @@ struct sched_change_ctx sched_change_beg
 
 	lockdep_assert_rq_held(rq);
 
-	if ((flags & DEQUEUE_CLASS) && p->sched_class->switching_from)
+	if ((flags & DEQUEUE_CLASS) && 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.
+		 */
+		SCHED_WARN_ON(!(flags & DEQUEUE_NOCLOCK));
 		p->sched_class->switching_from(rq, p, flags);
+	}
 
 	struct sched_change_ctx ctx = {
 		.p = p,
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4485,7 +4485,7 @@ static void scx_ops_disable_workfn(struc
 
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
-		unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
+		unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 		const struct sched_class *old_class = p->sched_class;
 		const struct sched_class *new_class =
 			__setscheduler_class(p->policy, p->prio);
@@ -4493,9 +4493,7 @@ static void scx_ops_disable_workfn(struc
 		if (old_class != new_class)
 			queue_flags |= DEQUEUE_CLASS;
 
-		if (old_class != new_class && p->se.sched_delayed)
-			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
-
+		update_rq_clock(task_rq(p));
 		scoped_guard (sched_change, p, queue_flags) {
 			p->sched_class = new_class;
 		}
@@ -5202,7 +5200,7 @@ static int scx_ops_enable(struct sched_e
 	percpu_down_write(&scx_fork_rwsem);
 	scx_task_iter_start(&sti);
 	while ((p = scx_task_iter_next_locked(&sti))) {
-		unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE;
+		unsigned int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 		const struct sched_class *old_class = p->sched_class;
 		const struct sched_class *new_class =
 			__setscheduler_class(p->policy, p->prio);
@@ -5210,9 +5208,7 @@ static int scx_ops_enable(struct sched_e
 		if (old_class != new_class)
 			queue_flags |= DEQUEUE_CLASS;
 
-		if (old_class != new_class && p->se.sched_delayed)
-			dequeue_task(task_rq(p), p, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
-
+		update_rq_clock(task_rq(p));
 		scoped_guard (sched_change, p, DEQUEUE_SAVE | DEQUEUE_MOVE) {
 			p->scx.slice = SCX_SLICE_DFL;
 			p->sched_class = new_class;
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -13175,6 +13175,12 @@ 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, int flags)
+{
+	if ((flags & DEQUEUE_CLASS) && 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, int flags)
 {
 	detach_task_cfs_rq(p);
@@ -13592,6 +13598,7 @@ 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
@@ -701,9 +701,6 @@ int __sched_setscheduler(struct task_str
 	if (prev_class != next_class)
 		queue_flags |= DEQUEUE_CLASS;
 
-	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)) {



  parent reply	other threads:[~2024-10-30 15:25 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-30 15:12 [RFC][PATCH 0/6] clean up class switching Peter Zijlstra
2024-10-30 15:12 ` [PATCH 1/6] sched/ext: Fix scx vs sched_delayed Peter Zijlstra
2024-10-30 15:50   ` Christian Loehle
2024-10-30 15:54     ` Peter Zijlstra
2024-10-30 17:17       ` Christian Loehle
2024-10-30 20:19   ` Tejun Heo
2024-10-30 15:12 ` [RFC][PATCH 2/6] sched: Employ sched_change guards Peter Zijlstra
2024-10-30 20:58   ` Tejun Heo
2024-10-30 21:09     ` Tejun Heo
2024-10-30 21:11       ` Peter Zijlstra
2024-10-30 15:12 ` [RFC][PATCH 3/6] sched: Re-arrange the {EN,DE}QUEUE flags Peter Zijlstra
2024-10-30 15:12 ` [RFC][PATCH 4/6] sched: Fold sched_class::switch{ing,ed}_{to,from}() into the change pattern Peter Zijlstra
2024-10-30 21:12   ` Tejun Heo
2024-10-30 21:15     ` Peter Zijlstra
2024-10-30 21:29       ` Tejun Heo
2024-10-30 21:37         ` Peter Zijlstra
2024-10-30 21:39           ` Tejun Heo
2024-10-30 15:13 ` [RFC][PATCH 5/6] sched: Add flags to the switch{ing,ed}_{to,from}() methods Peter Zijlstra
2024-10-30 15:13 ` Peter Zijlstra [this message]
2024-10-30 15:45   ` [RFC][PATCH 6/6] sched: Cleanup sched_delayed handling for class switches Peter Zijlstra
2024-10-30 21:27     ` Tejun Heo

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20241030152142.928034708@infradead.org \
    --to=peterz@infradead.org \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tj@kernel.org \
    --cc=vincent.guittot@linaro.org \
    --cc=void@manifault.com \
    --cc=vschneid@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox