From: Florent Carli <fcarli@gmail.com>
To: stable@vger.kernel.org
Cc: Juri Lelli <juri.lelli@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Gabriele Monaco <gmonaco@redhat.com>,
linux-rt-users@vger.kernel.org
Subject: [PATCH 6.12.y 1/4] sched/deadline: Fix dl_server time accounting
Date: Fri, 20 Nov 2026 19:19:46 +0100 [thread overview]
Message-ID: <20261120181949.7528-2-fcarli@gmail.com> (raw)
In-Reply-To: <20261120181949.7528-1-fcarli@gmail.com>
From: Peter Zijlstra <peterz@infradead.org>
commit e636ffb9e31b4f7dde7fef5358669266b9ce02ec upstream.
The dl_server time accounting code is a little odd. The normal scheduler
pattern is to update curr before doing something, such that the old state is
fully accounted before changing state.
Notably, the dl_server_timer() needs to propagate the current time accounting
since the current task could be ran by dl_server and thus this can affect
dl_se->runtime. Similarly for dl_server_start().
And since the (deferred) dl_server wants idle time accounted, rework
sched_idle_class time accounting to be more like all the others.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://patch.msgid.link/20251020141130.GJ3245006@noisy.programming.kicks-ass.net
[ Florent: rq->donor does not exist in 6.12, use rq->curr ]
Signed-off-by: Florent Carli <fcarli@gmail.com>
---
kernel/sched/deadline.c | 40 +++++++++++++++-------------------------
kernel/sched/fair.c | 9 ++-------
kernel/sched/idle.c | 16 +++++++++++++++-
kernel/sched/sched.h | 3 +--
4 files changed, 33 insertions(+), 35 deletions(-)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f5c64d1a0..2e3bd43af 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1216,8 +1216,12 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
sched_clock_tick();
update_rq_clock(rq);
- if (!dl_se->dl_runtime)
- return HRTIMER_NORESTART;
+ /*
+ * Make sure current has propagated its pending runtime into
+ * any relevant server through calling dl_server_update() and
+ * friends.
+ */
+ rq->curr->sched_class->update_curr(rq);
if (dl_se->dl_defer_armed) {
/*
@@ -1594,35 +1598,16 @@ static void update_curr_dl_se(struct rq *rq, struct sched_dl_entity *dl_se, s64
* as time available for the fair server, avoiding a penalty for the
* rt scheduler that did not consumed that time.
*/
-void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
+void dl_server_update_idle(struct sched_dl_entity *dl_se, s64 delta_exec)
{
- s64 delta_exec;
-
- if (!rq->fair_server.dl_defer)
- return;
-
- /* no need to discount more */
- if (rq->fair_server.runtime < 0)
- return;
-
- delta_exec = rq_clock_task(rq) - p->se.exec_start;
- if (delta_exec < 0)
- return;
-
- rq->fair_server.runtime -= delta_exec;
-
- if (rq->fair_server.runtime < 0) {
- rq->fair_server.dl_defer_running = 0;
- rq->fair_server.runtime = 0;
- }
-
- p->se.exec_start = rq_clock_task(rq);
+ if (dl_se->dl_server_active && dl_se->dl_runtime && dl_se->dl_defer)
+ update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
}
void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
{
/* 0 runtime = fair server disabled */
- if (dl_se->dl_runtime)
+ if (dl_se->dl_server_active && dl_se->dl_runtime)
update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
}
@@ -1849,6 +1834,11 @@ void dl_server_start(struct sched_dl_entity *dl_se)
if (!dl_se->dl_runtime || dl_se->dl_server_active)
return;
+ /*
+ * Update the current task to 'now'.
+ */
+ rq->curr->sched_class->update_curr(rq);
+
if (WARN_ON_ONCE(!cpu_online(cpu_of(rq))))
return;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 020a39fe0..7e5179189 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1259,8 +1259,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
* against fair_server such that it can account for this time
* and possibly avoid running this period.
*/
- if (dl_server_active(&rq->fair_server))
- dl_server_update(&rq->fair_server, delta_exec);
+ dl_server_update(&rq->fair_server, delta_exec);
}
account_cfs_rq_runtime(cfs_rq, delta_exec);
@@ -7114,12 +7113,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
goto enqueue_throttle;
}
- if (!rq_h_nr_queued && rq->cfs.h_nr_queued) {
- /* Account for idle runtime */
- if (!rq->nr_running)
- dl_server_update_idle_time(rq, rq->curr);
+ if (!rq_h_nr_queued && rq->cfs.h_nr_queued)
dl_server_start(&rq->fair_server);
- }
/* At this point se is NULL and we are at root level*/
add_nr_running(rq, 1);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 1f0f0d9a5..a2ab252e7 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -471,9 +471,11 @@ static void wakeup_preempt_idle(struct rq *rq, struct task_struct *p, int flags)
resched_curr(rq);
}
+static void update_curr_idle(struct rq *rq);
+
static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct task_struct *next)
{
- dl_server_update_idle_time(rq, prev);
+ update_curr_idle(rq);
scx_update_idle(rq, false, true);
}
@@ -521,6 +523,7 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
*/
static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
{
+ update_curr_idle(rq);
}
static void switched_to_idle(struct rq *rq, struct task_struct *p)
@@ -536,6 +539,17 @@ prio_changed_idle(struct rq *rq, struct task_struct *p, int oldprio)
static void update_curr_idle(struct rq *rq)
{
+ struct sched_entity *se = &rq->idle->se;
+ u64 now = rq_clock_task(rq);
+ s64 delta_exec;
+
+ delta_exec = now - se->exec_start;
+ if (unlikely(delta_exec <= 0))
+ return;
+
+ se->exec_start = now;
+
+ dl_server_update_idle(&rq->fair_server, delta_exec);
}
/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 5e788dc39..598dd26fe 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -411,14 +411,13 @@ extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s6
* naturally thottled to once per period, avoiding high context switch
* workloads from spamming the hrtimer program/cancel paths.
*/
+extern void dl_server_update_idle(struct sched_dl_entity *dl_se, s64 delta_exec);
extern void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec);
extern void dl_server_start(struct sched_dl_entity *dl_se);
extern void dl_server_stop(struct sched_dl_entity *dl_se);
extern void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
dl_server_pick_f pick_task);
-extern void dl_server_update_idle_time(struct rq *rq,
- struct task_struct *p);
extern void fair_server_init(struct rq *rq);
extern void __dl_server_attach_root(struct sched_dl_entity *dl_se, struct rq *rq);
extern int dl_server_apply_params(struct sched_dl_entity *dl_se,
--
2.39.3 (Apple Git-146)
next prev parent reply other threads:[~2026-11-20 18:20 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-20 15:09 [REGRESSION] 6.12.y, 6.18.y: fair server runs SCHED_OTHER ahead of SCHED_FIFO on an idle CPU (fixed in 6.19) Florent Carli
2026-11-20 17:09 ` Juri Lelli
2026-11-20 18:19 ` Florent Carli
2026-11-21 15:27 ` Sasha Levin
2026-11-20 18:19 ` [PATCH 6.12.y 0/4] sched/deadline: dl_server fixes from 6.19 Florent Carli
2026-11-20 18:19 ` Florent Carli [this message]
2026-11-20 18:19 ` [PATCH 6.12.y 2/4] sched/deadline: Fix dl_server stop condition Florent Carli
2026-11-20 18:19 ` [PATCH 6.12.y 3/4] sched: Provide idle_rq() helper Florent Carli
2026-11-20 18:19 ` [PATCH 6.12.y 4/4] sched/deadline: Fix server stopping with runnable tasks Florent Carli
2026-11-21 15:27 ` [PATCH 6.12.y 0/4] sched/deadline: dl_server fixes from 6.19 Sasha Levin
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=20261120181949.7528-2-fcarli@gmail.com \
--to=fcarli@gmail.com \
--cc=gmonaco@redhat.com \
--cc=juri.lelli@redhat.com \
--cc=linux-rt-users@vger.kernel.org \
--cc=peterz@infradead.org \
--cc=stable@vger.kernel.org \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.