[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <176060722582.709179.1540483623189425427.tip-bot2@tip-bot2>
Date: Thu, 16 Oct 2025 09:33:45 -0000
From: "tip-bot2 for Doug Berger" <tip-bot2@...utronix.de>
To: linux-tip-commits@...r.kernel.org
Cc: Doug Berger <opendmb@...il.com>,
"Peter Zijlstra (Intel)" <peterz@...radead.org>, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject:
[tip: sched/core] sched/deadline: only set free_cpus for online runqueues
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 382748c05e58a9f1935f5a653c352422375566ea
Gitweb: https://git.kernel.org/tip/382748c05e58a9f1935f5a653c352422375566ea
Author: Doug Berger <opendmb@...il.com>
AuthorDate: Thu, 14 Aug 2025 18:22:36 -07:00
Committer: Peter Zijlstra <peterz@...radead.org>
CommitterDate: Thu, 16 Oct 2025 11:13:49 +02:00
sched/deadline: only set free_cpus for online runqueues
Commit 16b269436b72 ("sched/deadline: Modify cpudl::free_cpus
to reflect rd->online") introduced the cpudl_set/clear_freecpu
functions to allow the cpu_dl::free_cpus mask to be manipulated
by the deadline scheduler class rq_on/offline callbacks so the
mask would also reflect this state.
Commit 9659e1eeee28 ("sched/deadline: Remove cpu_active_mask
from cpudl_find()") removed the check of the cpu_active_mask to
save some processing on the premise that the cpudl::free_cpus
mask already reflected the runqueue online state.
Unfortunately, there are cases where it is possible for the
cpudl_clear function to set the free_cpus bit for a CPU when the
deadline runqueue is offline. When this occurs while a CPU is
connected to the default root domain the flag may retain the bad
state after the CPU has been unplugged. Later, a different CPU
that is transitioning through the default root domain may push a
deadline task to the powered down CPU when cpudl_find sees its
free_cpus bit is set. If this happens the task will not have the
opportunity to run.
One example is outlined here:
https://lore.kernel.org/lkml/20250110233010.2339521-1-opendmb@gmail.com
Another occurs when the last deadline task is migrated from a
CPU that has an offlined runqueue. The dequeue_task member of
the deadline scheduler class will eventually call cpudl_clear
and set the free_cpus bit for the CPU.
This commit modifies the cpudl_clear function to be aware of the
online state of the deadline runqueue so that the free_cpus mask
can be updated appropriately.
It is no longer necessary to manage the mask outside of the
cpudl_set/clear functions so the cpudl_set/clear_freecpu
functions are removed. In addition, since the free_cpus mask is
now only updated under the cpudl lock the code was changed to
use the non-atomic __cpumask functions.
Signed-off-by: Doug Berger <opendmb@...il.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
kernel/sched/cpudeadline.c | 34 +++++++++-------------------------
kernel/sched/cpudeadline.h | 4 +---
kernel/sched/deadline.c | 8 ++++----
3 files changed, 14 insertions(+), 32 deletions(-)
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index cdd740b..37b572c 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -166,12 +166,13 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
* cpudl_clear - remove a CPU from the cpudl max-heap
* @cp: the cpudl max-heap context
* @cpu: the target CPU
+ * @online: the online state of the deadline runqueue
*
* Notes: assumes cpu_rq(cpu)->lock is locked
*
* Returns: (void)
*/
-void cpudl_clear(struct cpudl *cp, int cpu)
+void cpudl_clear(struct cpudl *cp, int cpu, bool online)
{
int old_idx, new_cpu;
unsigned long flags;
@@ -184,7 +185,7 @@ void cpudl_clear(struct cpudl *cp, int cpu)
if (old_idx == IDX_INVALID) {
/*
* Nothing to remove if old_idx was invalid.
- * This could happen if a rq_offline_dl is
+ * This could happen if rq_online_dl or rq_offline_dl is
* called for a CPU without -dl tasks running.
*/
} else {
@@ -195,9 +196,12 @@ void cpudl_clear(struct cpudl *cp, int cpu)
cp->elements[new_cpu].idx = old_idx;
cp->elements[cpu].idx = IDX_INVALID;
cpudl_heapify(cp, old_idx);
-
- cpumask_set_cpu(cpu, cp->free_cpus);
}
+ if (likely(online))
+ __cpumask_set_cpu(cpu, cp->free_cpus);
+ else
+ __cpumask_clear_cpu(cpu, cp->free_cpus);
+
raw_spin_unlock_irqrestore(&cp->lock, flags);
}
@@ -228,7 +232,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl)
cp->elements[new_idx].cpu = cpu;
cp->elements[cpu].idx = new_idx;
cpudl_heapify_up(cp, new_idx);
- cpumask_clear_cpu(cpu, cp->free_cpus);
+ __cpumask_clear_cpu(cpu, cp->free_cpus);
} else {
cp->elements[old_idx].dl = dl;
cpudl_heapify(cp, old_idx);
@@ -238,26 +242,6 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl)
}
/*
- * cpudl_set_freecpu - Set the cpudl.free_cpus
- * @cp: the cpudl max-heap context
- * @cpu: rd attached CPU
- */
-void cpudl_set_freecpu(struct cpudl *cp, int cpu)
-{
- cpumask_set_cpu(cpu, cp->free_cpus);
-}
-
-/*
- * cpudl_clear_freecpu - Clear the cpudl.free_cpus
- * @cp: the cpudl max-heap context
- * @cpu: rd attached CPU
- */
-void cpudl_clear_freecpu(struct cpudl *cp, int cpu)
-{
- cpumask_clear_cpu(cpu, cp->free_cpus);
-}
-
-/*
* cpudl_init - initialize the cpudl structure
* @cp: the cpudl max-heap context
*/
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index 11c0f1f..d769946 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -19,8 +19,6 @@ struct cpudl {
int cpudl_find(struct cpudl *cp, struct task_struct *p, struct cpumask *later_mask);
void cpudl_set(struct cpudl *cp, int cpu, u64 dl);
-void cpudl_clear(struct cpudl *cp, int cpu);
+void cpudl_clear(struct cpudl *cp, int cpu, bool online);
int cpudl_init(struct cpudl *cp);
-void cpudl_set_freecpu(struct cpudl *cp, int cpu);
-void cpudl_clear_freecpu(struct cpudl *cp, int cpu);
void cpudl_cleanup(struct cpudl *cp);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 615411a..933bd1f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1808,7 +1808,7 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
if (!dl_rq->dl_nr_running) {
dl_rq->earliest_dl.curr = 0;
dl_rq->earliest_dl.next = 0;
- cpudl_clear(&rq->rd->cpudl, rq->cpu);
+ cpudl_clear(&rq->rd->cpudl, rq->cpu, rq->online);
cpupri_set(&rq->rd->cpupri, rq->cpu, rq->rt.highest_prio.curr);
} else {
struct rb_node *leftmost = rb_first_cached(&dl_rq->root);
@@ -2880,9 +2880,10 @@ static void rq_online_dl(struct rq *rq)
if (rq->dl.overloaded)
dl_set_overload(rq);
- cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu);
if (rq->dl.dl_nr_running > 0)
cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr);
+ else
+ cpudl_clear(&rq->rd->cpudl, rq->cpu, true);
}
/* Assumes rq->lock is held */
@@ -2891,8 +2892,7 @@ static void rq_offline_dl(struct rq *rq)
if (rq->dl.overloaded)
dl_clear_overload(rq);
- cpudl_clear(&rq->rd->cpudl, rq->cpu);
- cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
+ cpudl_clear(&rq->rd->cpudl, rq->cpu, false);
}
void __init init_sched_dl_class(void)
Powered by blists - more mailing lists