[tip: sched/core] sched: Restart fair hrtick after same-task repicks
From: tip-bot2 for Shubhang Kaushik (Ampere)
Date: Fri Sep 25 2026 - 06:56:12 EST
The following commit has been merged into the sched/core branch of tip:
Commit-ID: c72945693b90423f1b46ac2dbc8749c2b7804fc8
Gitweb: https://git.kernel.org/tip/c72945693b90423f1b46ac2dbc8749c2b7804fc8
Author: Shubhang Kaushik (Ampere) <sh@xxxxxxxxxx>
AuthorDate: Thu, 17 Sep 2026 16:06:59 -07:00
Committer: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Fri, 25 Sep 2026 12:45:57 +02:00
sched: Restart fair hrtick after same-task repicks
Fair hrticks are one-shot timers. A same-task repick after hrtick expiry
skips set_next_task_fair() and leaves no hrtick armed for the next fair
preemption point:
hrtick()
-> task_tick_fair(..., queued=1)
-> entity_tick()
-> resched_curr()
-> schedule()
-> pick_task_fair() selects current
-> put_prev_set_next_task(rq, prev, next)
-> next == prev
-> return
Introduce SNT_REPICK for the next == prev path:
put_prev_set_next_task(rq, prev, next)
-> next == prev
-> next->sched_class->set_next_task(rq, next, SNT_REPICK)
-> set_next_task_fair()
-> hrtick_start_fair()
set_next_task_fair() skips task-transition work for SNT_REPICK and
restarts the fair hrtick. hrtick_start() records the delay during
schedule(), and hrtick_schedule_exit() rearms the timer.
Do not restart the SCHED_DEADLINE hrtick for SNT_REPICK. Same-task
repicks skip put_prev_task() for both fair and SCHED_DEADLINE, but
pick_task_fair() refreshes the selected fair entity before selecting it
again. hrtick_start_fair() reads that refreshed entity, including with
group scheduling.
The SCHED_DEADLINE picker has no corresponding current-runtime update.
Restarting its hrtick on SNT_REPICK could therefore use stale
dl_se->runtime and delay the next runtime enforcement point.
Suggested-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Shubhang Kaushik (Ampere) <sh@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Zhan Xusheng <zhanxusheng@xxxxxxxxxx>
Link: https://patch.msgid.link/20260917-sched-fair-hrtick-restart-v4-1-4dd1414da81a@xxxxxxxxxx
---
kernel/sched/core.c | 2 +-
kernel/sched/deadline.c | 7 +++++--
kernel/sched/ext/ext.c | 5 ++++-
kernel/sched/fair.c | 21 ++++++++++++++++-----
kernel/sched/idle.c | 5 ++++-
kernel/sched/rt.c | 7 +++++--
kernel/sched/sched.h | 16 ++++++++++++----
kernel/sched/stop_task.c | 5 ++++-
8 files changed, 51 insertions(+), 17 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5a61650..d368aaf 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7240,7 +7240,7 @@ pick_again:
* on_cpu.
*/
donor->sched_class->put_prev_task(rq, donor, donor);
- donor->sched_class->set_next_task(rq, donor, true);
+ donor->sched_class->set_next_task(rq, donor, SNT_PICK);
}
} else {
rq_set_donor(rq, next);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index de6a361..c0ebdcd 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2773,11 +2773,14 @@ static void start_hrtick_dl(struct rq *rq, struct sched_dl_entity *dl_se)
* DL keeps current in tree, because ->deadline is not typically changed while
* a task is runnable.
*/
-static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
+static void set_next_task_dl(struct rq *rq, struct task_struct *p, enum snt_e type)
{
struct sched_dl_entity *dl_se = &p->dl;
struct dl_rq *dl_rq = &rq->dl;
+ if (type == SNT_REPICK)
+ return;
+
p->se.exec_start = rq_clock_task(rq);
if (on_dl_rq(&p->dl))
update_stats_wait_end_dl(dl_rq, dl_se);
@@ -2788,7 +2791,7 @@ static void set_next_task_dl(struct rq *rq, struct task_struct *p, bool first)
WARN_ON_ONCE(dl_rq->curr);
dl_rq->curr = dl_se;
- if (!first)
+ if (type != SNT_PICK)
return;
if (rq->donor->sched_class != &dl_sched_class)
diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c
index 10af28a..53275bc 100644
--- a/kernel/sched/ext/ext.c
+++ b/kernel/sched/ext/ext.c
@@ -3001,10 +3001,13 @@ has_tasks:
return verdict;
}
-static void set_next_task_scx(struct rq *rq, struct task_struct *p, bool first)
+static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e type)
{
struct scx_sched *sch = scx_task_sched(p);
+ if (type == SNT_REPICK)
+ return;
+
if (p->scx.flags & SCX_TASK_QUEUED) {
/*
* Core-sched might decide to execute @p before it is
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a42360c..36861f4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -15234,14 +15234,18 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p)
}
}
-static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
+static void set_next_task_fair(struct rq *rq, struct task_struct *p, enum snt_e type)
{
struct sched_entity *se = &p->se;
- bool throttled = false;
struct cfs_rq *cfs_rq = &rq->cfs;
unsigned long weight = NICE_0_LOAD;
+ bool first = type == SNT_PICK;
+ bool throttled = false;
bool on_rq = se->on_rq;
+ if (type == SNT_REPICK)
+ goto repick;
+
clear_buddies(cfs_rq, se);
if (on_rq)
@@ -15285,11 +15289,18 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
WARN_ON_ONCE(se->sched_delayed);
- if (hrtick_enabled_fair(rq))
- hrtick_start_fair(rq, p);
-
update_misfit_status(p, rq);
sched_fair_update_stop_tick(rq, p);
+
+repick:
+ /*
+ * A same-task repick skips put_prev_task_fair(), but
+ * pick_task_fair() refreshed the entity hrtick_start_fair() reads
+ * before selecting it again. rq->cfs.curr identifies that entity,
+ * including with group scheduling.
+ */
+ if (hrtick_enabled_fair(rq))
+ hrtick_start_fair(rq, p);
}
void init_cfs_rq(struct cfs_rq *cfs_rq)
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index eb73b65..76f3c84 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -487,8 +487,11 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev, struct t
update_rq_avg_idle(rq);
}
-static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool first)
+static void set_next_task_idle(struct rq *rq, struct task_struct *next, enum snt_e type)
{
+ if (type == SNT_REPICK)
+ return;
+
update_idle_core(rq);
scx_update_idle(rq, true, true);
schedstat_inc(rq->sched_goidle);
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 85303ad..1535046 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1654,11 +1654,14 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
check_preempt_equal_prio(rq, p);
}
-static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
+static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, enum snt_e type)
{
struct sched_rt_entity *rt_se = &p->rt;
struct rt_rq *rt_rq = &rq->rt;
+ if (type == SNT_REPICK)
+ return;
+
p->se.exec_start = rq_clock_task(rq);
if (on_rt_rq(&p->rt))
update_stats_wait_end_rt(rt_rq, rt_se);
@@ -1666,7 +1669,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f
/* The running task is never eligible for pushing */
dequeue_pushable_task(rq, p);
- if (!first)
+ if (type != SNT_PICK)
return;
/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6c3ad70..1b64be5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2630,6 +2630,12 @@ struct affinity_context {
extern s64 update_curr_common(struct rq *rq);
+enum snt_e {
+ SNT_NORMAL, /* set_next_task() */
+ SNT_PICK, /* put_prev_set_next_task(): prev != next */
+ SNT_REPICK, /* put_prev_set_next_task(): prev == next */
+};
+
struct sched_class {
#ifdef CONFIG_UCLAMP_TASK
@@ -2687,7 +2693,7 @@ struct sched_class {
* __schedule: rq->lock
*/
void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
- void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
+ void (*set_next_task)(struct rq *rq, struct task_struct *p, enum snt_e type);
/*
* select_task_rq: p->pi_lock
@@ -2790,7 +2796,7 @@ static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
static inline void set_next_task(struct rq *rq, struct task_struct *next)
{
- next->sched_class->set_next_task(rq, next, false);
+ next->sched_class->set_next_task(rq, next, SNT_NORMAL);
}
static inline void
@@ -2811,11 +2817,13 @@ static inline void put_prev_set_next_task(struct rq *rq,
__put_prev_set_next_dl_server(rq, prev, next);
- if (next == prev)
+ if (next == prev) {
+ next->sched_class->set_next_task(rq, next, SNT_REPICK);
return;
+ }
prev->sched_class->put_prev_task(rq, prev, next);
- next->sched_class->set_next_task(rq, next, true);
+ next->sched_class->set_next_task(rq, next, SNT_PICK);
}
/*
diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c
index c909ca0..1e0109e 100644
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -27,8 +27,11 @@ wakeup_preempt_stop(struct rq *rq, struct task_struct *p, int flags)
/* we're never preempted */
}
-static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool first)
+static void set_next_task_stop(struct rq *rq, struct task_struct *stop, enum snt_e type)
{
+ if (type == SNT_REPICK)
+ return;
+
stop->se.exec_start = rq_clock_task(rq);
}