public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Yuri Andriaccio <yurand2000@gmail.com>
To: Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
	Valentin Schneider <vschneid@redhat.com>
Cc: linux-kernel@vger.kernel.org,
	Luca Abeni <luca.abeni@santannapisa.it>,
	Yuri Andriaccio <yuri.andriaccio@santannapisa.it>
Subject: [RFC PATCH v5 04/29] sched/rt: Pass an rt_rq instead of an rq where needed
Date: Thu, 30 Apr 2026 23:38:08 +0200	[thread overview]
Message-ID: <20260430213835.62217-5-yurand2000@gmail.com> (raw)
In-Reply-To: <20260430213835.62217-1-yurand2000@gmail.com>

From: luca abeni <luca.abeni@santannapisa.it>

Make rt.c code access the runqueue through the rt_rq data structure rather
than passing an rq pointer directly. This allows future patches to define
rt_rq data structures which do not refer only to the global runqueue, but
also to local cgroup runqueues (as rt_rq will not be always equal to
&rq->rt).

Add checks in rt_queue_{push/pull}_tasks to make sure that the given rt_rq
object refers to a global runqueue and not any local one.

Signed-off-by: luca abeni <luca.abeni@santannapisa.it>
Signed-off-by: Yuri Andriaccio <yurand2000@gmail.com>
---
 kernel/sched/rt.c | 99 ++++++++++++++++++++++++++---------------------
 1 file changed, 54 insertions(+), 45 deletions(-)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index f69e1f16d923..597eaba00a20 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -370,9 +370,9 @@ static inline void rt_clear_overload(struct rq *rq)
 	cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
 }

-static inline int has_pushable_tasks(struct rq *rq)
+static inline int has_pushable_tasks(struct rt_rq *rt_rq)
 {
-	return !plist_head_empty(&rq->rt.pushable_tasks);
+	return !plist_head_empty(&rt_rq->pushable_tasks);
 }

 static DEFINE_PER_CPU(struct balance_callback, rt_push_head);
@@ -381,50 +381,54 @@ static DEFINE_PER_CPU(struct balance_callback, rt_pull_head);
 static void push_rt_tasks(struct rq *);
 static void pull_rt_task(struct rq *);

-static inline void rt_queue_push_tasks(struct rq *rq)
+static inline void rt_queue_push_tasks(struct rt_rq *rt_rq)
 {
-	if (!has_pushable_tasks(rq))
+	struct rq *rq = container_of_const(rt_rq, struct rq, rt);
+
+	if (!has_pushable_tasks(rt_rq))
 		return;

 	queue_balance_callback(rq, &per_cpu(rt_push_head, rq->cpu), push_rt_tasks);
 }

-static inline void rt_queue_pull_task(struct rq *rq)
+static inline void rt_queue_pull_task(struct rt_rq *rt_rq)
 {
+	struct rq *rq = container_of_const(rt_rq, struct rq, rt);
+
 	queue_balance_callback(rq, &per_cpu(rt_pull_head, rq->cpu), pull_rt_task);
 }

-static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
+static void enqueue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
 {
-	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+	plist_del(&p->pushable_tasks, &rt_rq->pushable_tasks);
 	plist_node_init(&p->pushable_tasks, p->prio);
-	plist_add(&p->pushable_tasks, &rq->rt.pushable_tasks);
+	plist_add(&p->pushable_tasks, &rt_rq->pushable_tasks);

 	/* Update the highest prio pushable task */
-	if (p->prio < rq->rt.highest_prio.next)
-		rq->rt.highest_prio.next = p->prio;
+	if (p->prio < rt_rq->highest_prio.next)
+		rt_rq->highest_prio.next = p->prio;

-	if (!rq->rt.overloaded) {
-		rt_set_overload(rq);
-		rq->rt.overloaded = 1;
+	if (!rt_rq->overloaded) {
+		rt_set_overload(rq_of_rt_rq(rt_rq));
+		rt_rq->overloaded = 1;
 	}
 }

-static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
+static void dequeue_pushable_task(struct rt_rq *rt_rq, struct task_struct *p)
 {
-	plist_del(&p->pushable_tasks, &rq->rt.pushable_tasks);
+	plist_del(&p->pushable_tasks, &rt_rq->pushable_tasks);

 	/* Update the new highest prio pushable task */
-	if (has_pushable_tasks(rq)) {
-		p = plist_first_entry(&rq->rt.pushable_tasks,
+	if (has_pushable_tasks(rt_rq)) {
+		p = plist_first_entry(&rt_rq->pushable_tasks,
 				      struct task_struct, pushable_tasks);
-		rq->rt.highest_prio.next = p->prio;
+		rt_rq->highest_prio.next = p->prio;
 	} else {
-		rq->rt.highest_prio.next = MAX_RT_PRIO-1;
+		rt_rq->highest_prio.next = MAX_RT_PRIO-1;

-		if (rq->rt.overloaded) {
-			rt_clear_overload(rq);
-			rq->rt.overloaded = 0;
+		if (rt_rq->overloaded) {
+			rt_clear_overload(rq_of_rt_rq(rt_rq));
+			rt_rq->overloaded = 0;
 		}
 	}
 }
@@ -1431,6 +1435,7 @@ static void
 enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
+	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);

 	if (flags & ENQUEUE_WAKEUP)
 		rt_se->timeout = 0;
@@ -1444,17 +1449,18 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 		return;

 	if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
-		enqueue_pushable_task(rq, p);
+		enqueue_pushable_task(rt_rq, p);
 }

 static bool dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
+	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);

 	update_curr_rt(rq);
 	dequeue_rt_entity(rt_se, flags);

-	dequeue_pushable_task(rq, p);
+	dequeue_pushable_task(rt_rq, p);

 	return true;
 }
@@ -1645,14 +1651,14 @@ static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
 static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool first)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
-	struct rt_rq *rt_rq = &rq->rt;
+	struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);

 	p->se.exec_start = rq_clock_task(rq);
 	if (on_rt_rq(&p->rt))
 		update_stats_wait_end_rt(rt_rq, rt_se);

 	/* The running task is never eligible for pushing */
-	dequeue_pushable_task(rq, p);
+	dequeue_pushable_task(rt_rq, p);

 	if (!first)
 		return;
@@ -1665,7 +1671,7 @@ static inline void set_next_task_rt(struct rq *rq, struct task_struct *p, bool f
 	if (rq->donor->sched_class != &rt_sched_class)
 		update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 0);

-	rt_queue_push_tasks(rq);
+	rt_queue_push_tasks(rt_rq);
 }

 static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
@@ -1716,7 +1722,7 @@ static struct task_struct *pick_task_rt(struct rq *rq, struct rq_flags *rf)
 static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_struct *next)
 {
 	struct sched_rt_entity *rt_se = &p->rt;
-	struct rt_rq *rt_rq = &rq->rt;
+	struct rt_rq *rt_rq = rt_rq_of_se(&p->rt);

 	if (on_rt_rq(&p->rt))
 		update_stats_wait_start_rt(rt_rq, rt_se);
@@ -1732,7 +1738,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_s
 	 * if it is still active
 	 */
 	if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1)
-		enqueue_pushable_task(rq, p);
+		enqueue_pushable_task(rt_rq, p);
 }

 /* Only try algorithms three times */
@@ -1742,16 +1748,16 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p, struct task_s
  * Return the highest pushable rq's task, which is suitable to be executed
  * on the CPU, NULL otherwise
  */
-static struct task_struct *pick_highest_pushable_task(struct rq *rq, int cpu)
+static struct task_struct *pick_highest_pushable_task(struct rt_rq *rt_rq, int cpu)
 {
-	struct plist_head *head = &rq->rt.pushable_tasks;
+	struct plist_head *head = &rt_rq->pushable_tasks;
 	struct task_struct *p;

-	if (!has_pushable_tasks(rq))
+	if (!has_pushable_tasks(rt_rq))
 		return NULL;

 	plist_for_each_entry(p, head, pushable_tasks) {
-		if (task_is_pushable(rq, p, cpu))
+		if (task_is_pushable(rq_of_rt_rq(rt_rq), p, cpu))
 			return p;
 	}

@@ -1851,14 +1857,15 @@ static int find_lowest_rq(struct task_struct *task)
 	return -1;
 }

-static struct task_struct *pick_next_pushable_task(struct rq *rq)
+static struct task_struct *pick_next_pushable_task(struct rt_rq *rt_rq)
 {
+	struct rq *rq = rq_of_rt_rq(rt_rq);
 	struct task_struct *p;

-	if (!has_pushable_tasks(rq))
+	if (!has_pushable_tasks(rt_rq))
 		return NULL;

-	p = plist_first_entry(&rq->rt.pushable_tasks,
+	p = plist_first_entry(&rt_rq->pushable_tasks,
 			      struct task_struct, pushable_tasks);

 	BUG_ON(rq->cpu != task_cpu(p));
@@ -1911,7 +1918,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 */
 			if (unlikely(is_migration_disabled(task) ||
 				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) ||
-				     task != pick_next_pushable_task(rq))) {
+				     task != pick_next_pushable_task(&rq->rt))) {

 				double_unlock_balance(rq, lowest_rq);
 				lowest_rq = NULL;
@@ -1945,7 +1952,7 @@ static int push_rt_task(struct rq *rq, bool pull)
 	if (!rq->rt.overloaded)
 		return 0;

-	next_task = pick_next_pushable_task(rq);
+	next_task = pick_next_pushable_task(&rq->rt);
 	if (!next_task)
 		return 0;

@@ -2020,7 +2027,7 @@ static int push_rt_task(struct rq *rq, bool pull)
 		 * run-queue and is also still the next task eligible for
 		 * pushing.
 		 */
-		task = pick_next_pushable_task(rq);
+		task = pick_next_pushable_task(&rq->rt);
 		if (task == next_task) {
 			/*
 			 * The task hasn't migrated, and is still the next
@@ -2213,7 +2220,7 @@ void rto_push_irq_work_func(struct irq_work *work)
 	 * We do not need to grab the lock to check for has_pushable_tasks.
 	 * When it gets updated, a check is made if a push is possible.
 	 */
-	if (has_pushable_tasks(rq)) {
+	if (has_pushable_tasks(&rq->rt)) {
 		raw_spin_rq_lock(rq);
 		while (push_rt_task(rq, true))
 			;
@@ -2242,6 +2249,7 @@ static void pull_rt_task(struct rq *this_rq)
 	int this_cpu = this_rq->cpu, cpu;
 	bool resched = false;
 	struct task_struct *p, *push_task;
+	struct rt_rq *src_rt_rq;
 	struct rq *src_rq;
 	int rt_overload_count = rt_overloaded(this_rq);

@@ -2271,6 +2279,7 @@ static void pull_rt_task(struct rq *this_rq)
 			continue;

 		src_rq = cpu_rq(cpu);
+		src_rt_rq = &src_rq->rt;

 		/*
 		 * Don't bother taking the src_rq->lock if the next highest
@@ -2279,7 +2288,7 @@ static void pull_rt_task(struct rq *this_rq)
 		 * logically higher, the src_rq will push this task away.
 		 * And if its going logically lower, we do not care
 		 */
-		if (src_rq->rt.highest_prio.next >=
+		if (src_rt_rq->highest_prio.next >=
 		    this_rq->rt.highest_prio.curr)
 			continue;

@@ -2295,7 +2304,7 @@ static void pull_rt_task(struct rq *this_rq)
 		 * We can pull only a task, which is pushable
 		 * on its rq, and no others.
 		 */
-		p = pick_highest_pushable_task(src_rq, this_cpu);
+		p = pick_highest_pushable_task(src_rt_rq, this_cpu);

 		/*
 		 * Do we have an RT task that preempts
@@ -2401,7 +2410,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 	if (!task_on_rq_queued(p) || rq->rt.rt_nr_running)
 		return;

-	rt_queue_pull_task(rq);
+	rt_queue_pull_task(rt_rq_of_se(&p->rt));
 }

 void __init init_sched_rt_class(void)
@@ -2437,7 +2446,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p)
 	 */
 	if (task_on_rq_queued(p)) {
 		if (p->nr_cpus_allowed > 1 && rq->rt.overloaded)
-			rt_queue_push_tasks(rq);
+			rt_queue_push_tasks(rt_rq_of_se(&p->rt));
 		if (p->prio < rq->donor->prio && cpu_online(cpu_of(rq)))
 			resched_curr(rq);
 	}
@@ -2462,7 +2471,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, u64 oldprio)
 		 * may need to pull tasks to this runqueue.
 		 */
 		if (oldprio < p->prio)
-			rt_queue_pull_task(rq);
+			rt_queue_pull_task(rt_rq_of_se(&p->rt));

 		/*
 		 * If there's a higher priority task waiting to run
--
2.53.0


  parent reply	other threads:[~2026-04-30 21:38 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-30 21:38 [RFC PATCH v5 00/29] Hierarchical Constant Bandwidth Server Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 01/29] sched/deadline: Fix replenishment logic for non-deferred servers Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 02/29] sched/deadline: Do not access dl_se->rq directly Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 03/29] sched/deadline: Distinguish between dl_rq and my_q Yuri Andriaccio
2026-04-30 21:38 ` Yuri Andriaccio [this message]
2026-04-30 21:38 ` [RFC PATCH v5 05/29] sched/rt: Move functions from rt.c to sched.h Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 06/29] sched/rt: Disable RT_GROUP_SCHED Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 07/29] sched/rt: Remove unnecessary runqueue pointer in struct rt_rq Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 08/29] sched/rt: Introduce HCBS specific structs in task_group Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 09/29] sched/core: Initialize HCBS specific structures Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 10/29] sched/deadline: Add dl_init_tg Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 11/29] sched/rt: Add {alloc/unregister/free}_rt_sched_group Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 12/29] sched/deadline: Account rt-cgroups bandwidth in deadline tasks schedulability tests Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 13/29] sched/rt: Implement dl-server operations for rt-cgroups Yuri Andriaccio
2026-05-05 13:04   ` Peter Zijlstra
2026-04-30 21:38 ` [RFC PATCH v5 14/29] sched/rt: Update task event callbacks for HCBS scheduling Yuri Andriaccio
2026-05-05 13:16   ` Peter Zijlstra
2026-04-30 21:38 ` [RFC PATCH v5 15/29] sched/rt: Update rt-cgroup schedulability checks Yuri Andriaccio
2026-05-05 14:36   ` Peter Zijlstra
2026-04-30 21:38 ` [RFC PATCH v5 16/29] sched/rt: Allow zeroing the runtime of the root control group Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 17/29] sched/rt: Remove old RT_GROUP_SCHED data structures Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 18/29] sched/core: Cgroup v2 support Yuri Andriaccio
2026-05-05 14:59   ` Peter Zijlstra
2026-04-30 21:38 ` [RFC PATCH v5 19/29] sched/rt: Remove support for cgroups-v1 Yuri Andriaccio
2026-05-05 15:01   ` Peter Zijlstra
2026-04-30 21:38 ` [RFC PATCH v5 20/29] sched/deadline: Allow deeper hierarchies of RT cgroups Yuri Andriaccio
2026-05-05 15:15   ` Peter Zijlstra
2026-05-05 19:56     ` Tejun Heo
2026-04-30 21:38 ` [RFC PATCH v5 21/29] sched/rt: Update default bandwidth for real-time tasks to ONE Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 22/29] sched/rt: Add rt-cgroup migration functions Yuri Andriaccio
2026-05-05 15:20   ` Peter Zijlstra
2026-05-05 15:24   ` Peter Zijlstra
2026-04-30 21:38 ` [RFC PATCH v5 23/29] sched/rt: Hook HCBS " Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 24/29] sched/core: Execute enqueued balance callbacks when changing allowed CPUs Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 25/29] sched/rt: Try pull task on empty server pick Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 26/29] sched/core: Execute enqueued balance callbacks after migrate_disable_switch Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 27/29] Documentation: Update documentation for real-time cgroups Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 28/29] sched/rt: Add debug BUG_ONs for pre-migration code Yuri Andriaccio
2026-04-30 21:38 ` [RFC PATCH v5 29/29] sched/rt: Add debug BUG_ONs in migration code Yuri Andriaccio

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=20260430213835.62217-5-yurand2000@gmail.com \
    --to=yurand2000@gmail.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luca.abeni@santannapisa.it \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    --cc=yuri.andriaccio@santannapisa.it \
    /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