linux-kernel - [RFC][PATCH 1/3] sched: Detect per-class runqueue changes

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: <20251006105453.522934521@infradead.org>
Date: Mon, 06 Oct 2025 12:46:53 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: tj@...nel.org
Cc: linux-kernel@...r.kernel.org,
 peterz@...radead.org,
 mingo@...nel.org,
 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: [RFC][PATCH 1/3] sched: Detect per-class runqueue changes

Have enqueue/dequeue set a per-class bit in rq->queue_mask. This then
enables easy tracking of which runqueues are modified over a
lock-break.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 kernel/sched/core.c      |    2 ++
 kernel/sched/deadline.c  |    2 ++
 kernel/sched/ext.c       |    2 ++
 kernel/sched/fair.c      |    7 +++++--
 kernel/sched/idle.c      |    2 ++
 kernel/sched/rt.c        |    2 ++
 kernel/sched/sched.h     |   10 ++++++++++
 kernel/sched/stop_task.c |    2 ++
 8 files changed, 27 insertions(+), 2 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2089,6 +2089,7 @@ void enqueue_task(struct rq *rq, struct
 	 */
 	uclamp_rq_inc(rq, p, flags);
 
+	rq->queue_mask |= p->sched_class->queue_mask;
 	p->sched_class->enqueue_task(rq, p, flags);
 
 	psi_enqueue(p, flags);
@@ -2121,6 +2122,7 @@ inline bool dequeue_task(struct rq *rq,
 	 * and mark the task ->sched_delayed.
 	 */
 	uclamp_rq_dec(rq, p);
+	rq->queue_mask |= p->sched_class->queue_mask;
 	return p->sched_class->dequeue_task(rq, p, flags);
 }
 
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3094,6 +3094,8 @@ static int task_is_throttled_dl(struct t
 
 DEFINE_SCHED_CLASS(dl) = {
 
+	.queue_mask		= 8,
+
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3234,6 +3234,8 @@ static void scx_cgroup_unlock(void) {}
  *   their current sched_class. Call them directly from sched core instead.
  */
 DEFINE_SCHED_CLASS(ext) = {
+	.queue_mask		= 1,
+
 	.enqueue_task		= enqueue_task_scx,
 	.dequeue_task		= dequeue_task_scx,
 	.yield_task		= yield_task_scx,
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -12830,6 +12830,7 @@ static int sched_balance_newidle(struct
 	}
 	rcu_read_unlock();
 
+	this_rq->queue_mask = 0;
 	raw_spin_rq_unlock(this_rq);
 
 	t0 = sched_clock_cpu(this_cpu);
@@ -12887,8 +12888,8 @@ static int sched_balance_newidle(struct
 	if (this_rq->cfs.h_nr_queued && !pulled_task)
 		pulled_task = 1;
 
-	/* Is there a task of a high priority class? */
-	if (this_rq->nr_running != this_rq->cfs.h_nr_queued)
+	/* If a higher prio class was modified, restart the pick */
+	if (this_rq->queue_mask & ~((fair_sched_class.queue_mask << 1)-1))
 		pulled_task = -1;
 
 out:
@@ -13623,6 +13624,8 @@ static unsigned int get_rr_interval_fair
  */
 DEFINE_SCHED_CLASS(fair) = {
 
+	.queue_mask		= 2,
+
 	.enqueue_task		= enqueue_task_fair,
 	.dequeue_task		= dequeue_task_fair,
 	.yield_task		= yield_task_fair,
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -522,6 +522,8 @@ static void update_curr_idle(struct rq *
  */
 DEFINE_SCHED_CLASS(idle) = {
 
+	.queue_mask		= 0,
+
 	/* no enqueue/yield_task for idle tasks */
 
 	/* dequeue is not valid, we print a debug message there: */
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2571,6 +2571,8 @@ static int task_is_throttled_rt(struct t
 
 DEFINE_SCHED_CLASS(rt) = {
 
+	.queue_mask		= 4,
+
 	.enqueue_task		= enqueue_task_rt,
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1118,6 +1118,7 @@ struct rq {
 	/* runqueue lock: */
 	raw_spinlock_t		__lock;
 
+	unsigned int		queue_mask;
 	unsigned int		nr_running;
 #ifdef CONFIG_NUMA_BALANCING
 	unsigned int		nr_numa_running;
@@ -2414,6 +2415,15 @@ struct sched_class {
 #ifdef CONFIG_UCLAMP_TASK
 	int uclamp_enabled;
 #endif
+	/*
+	 * idle:  0
+	 * ext:   1
+	 * fair:  2
+	 * rt:    4
+	 * dl:    8
+	 * stop: 16
+	 */
+	unsigned int queue_mask;
 
 	/*
 	 * move_queued_task/activate_task/enqueue_task: rq->lock
--- a/kernel/sched/stop_task.c
+++ b/kernel/sched/stop_task.c
@@ -99,6 +99,8 @@ static void update_curr_stop(struct rq *
  */
 DEFINE_SCHED_CLASS(stop) = {
 
+	.queue_mask		= 16,
+
 	.enqueue_task		= enqueue_task_stop,
 	.dequeue_task		= dequeue_task_stop,
 	.yield_task		= yield_task_stop,