From bdb12c26b20775d77caad529caf072d0fe2dc4b4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 30 Sep 2022 18:08:11 +0800
Subject: [PATCH] sched: Wrap rq::lock access

mainline inclusion
from mainline-v5.14-rc1
commit 5cb9eaa3d274f75539077a28cf01e3563195fa53
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I5OOWG
CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=5cb9eaa3d274f75539077a28cf01e3563195fa53

--------------------------------------------------------------------------

In preparation of playing games with rq->lock, abstract the thing
using an accessor.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Don Hiatt <dhiatt@digitalocean.com>
Tested-by: Hongyu Ning <hongyu.ning@linux.intel.com>
Tested-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20210422123308.136465446@infradead.org
Conflicts:
	kernel/sched/core.c
	[Bugfix a7c81556ec4d3("sched: Fix migrate_disable() vs rt/dl balancing")
	 is not applied.
	 Bugfix 565790d28b1e3("sched: Fix balance_callback()") is not applied.
	 Bugfix ae7927023243d("sched: Optimize finish_lock_switch()") is not applied.
	 Bugfix 36c6e17bf1692("sched/core: Print out straggler tasks in sched_cpu_dying()")
	 is not applied.
	 Feature 2558aacff8586("sched/hotplug: Ensure only per-cpu kthreads run
	 during hotplug") is not applied.
	 Feature f2469a1fb43f8("sched/core: Wait for tasks being pushed away on hotplug")
	 is not applied.]

	kernel/sched/deadline.c
	[Bugfix a7c81556ec4d3("sched: Fix migrate_disable() vs rt/dl balancing")
	 is not applied.]

	kernel/sched/fair.c
	[Feature acf66d7048e08("sched/fair: Provide can_migrate_task_llc")
	 Feature 0826530de3cbd("sched/fair: Remove update of blocked load from newidle_balance")
	 s not applied.
	 Feature 6864cf0161bad("sched/fair: Steal work from an overloaded CPU when CPU goes idle")]

	kernel/sched/rt.c
	[Bugfix a7c81556ec4d3("sched: Fix migrate_disable() vs rt/dl balancing")
	 is not applied.]

	kernel/sched/sched.h
	[[Bugfix a7c81556ec4d3("sched: Fix migrate_disable() vs rt/dl balancing")
	 is not applied.]
Signed-off-by: Lin Shengwang <linshengwang1@huawei.com>
Reviewed-by: lihua <hucool.lihua@huawei.com>
Signed-off-by: Zheng Zengkai <zhengzengkai@huawei.com>
---
 kernel/sched/core.c     |  46 +++++++++---------
 kernel/sched/cpuacct.c  |  12 ++---
 kernel/sched/deadline.c |  18 +++----
 kernel/sched/debug.c    |   4 +-
 kernel/sched/fair.c     |  49 ++++++++++---------
 kernel/sched/idle.c     |   4 +-
 kernel/sched/pelt.h     |   2 +-
 kernel/sched/rt.c       |   8 ++--
 kernel/sched/sched.h    | 103 ++++++++++++++++++++--------------------
 kernel/sched/topology.c |   4 +-
 10 files changed, 124 insertions(+), 126 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 32da42297ded..4d69360a3f06 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -202,12 +202,12 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 
 	for (;;) {
 		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
+		raw_spin_rq_lock(rq);
 		if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
 			rq_pin_lock(rq, rf);
 			return rq;
 		}
-		raw_spin_unlock(&rq->lock);
+		raw_spin_rq_unlock(rq);
 
 		while (unlikely(task_on_rq_migrating(p)))
 			cpu_relax();
@@ -226,7 +226,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 	for (;;) {
 		raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
 		rq = task_rq(p);
-		raw_spin_lock(&rq->lock);
+		raw_spin_rq_lock(rq);
 		/*
 		 *	move_queued_task()		task_rq_lock()
 		 *
@@ -248,7 +248,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
 			rq_pin_lock(rq, rf);
 			return rq;
 		}
-		raw_spin_unlock(&rq->lock);
+		raw_spin_rq_unlock(rq);
 		raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 
 		while (unlikely(task_on_rq_migrating(p)))
@@ -318,7 +318,7 @@ void update_rq_clock(struct rq *rq)
 {
 	s64 delta;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (rq->clock_update_flags & RQCF_ACT_SKIP)
 		return;
@@ -617,7 +617,7 @@ void resched_curr(struct rq *rq)
 	struct task_struct *curr = rq->curr;
 	int cpu;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (test_tsk_need_resched(curr))
 		return;
@@ -641,10 +641,10 @@ void resched_cpu(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	raw_spin_rq_lock_irqsave(rq, flags);
 	if (cpu_online(cpu) || cpu == smp_processor_id())
 		resched_curr(rq);
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_rq_unlock_irqrestore(rq, flags);
 }
 
 #ifdef CONFIG_SMP
@@ -1146,7 +1146,7 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
 	struct uclamp_se *uc_se = &p->uclamp[clamp_id];
 	struct uclamp_bucket *bucket;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	/* Update task effective clamp */
 	p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id);
@@ -1186,7 +1186,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 	unsigned int bkt_clamp;
 	unsigned int rq_clamp;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	/*
 	 * If sched_uclamp_used was enabled after task @p was enqueued,
@@ -1755,7 +1755,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 				   struct task_struct *p, int new_cpu)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	deactivate_task(rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, new_cpu);
@@ -1867,7 +1867,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 		 * Because __kthread_bind() calls this on blocked tasks without
 		 * holding rq->lock.
 		 */
-		lockdep_assert_held(&rq->lock);
+		lockdep_assert_rq_held(rq);
 		dequeue_task(rq, p, DEQUEUE_SAVE | DEQUEUE_NOCLOCK);
 	}
 	if (running)
@@ -2004,7 +2004,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	 * task_rq_lock().
 	 */
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
-				      lockdep_is_held(&task_rq(p)->lock)));
+				      lockdep_is_held(rq_lockp(task_rq(p)))));
 #endif
 	/*
 	 * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
@@ -2515,7 +2515,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 {
 	int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
@@ -3565,10 +3565,10 @@ prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf
 	 * do an early lockdep release here:
 	 */
 	rq_unpin_lock(rq, rf);
-	spin_release(&rq->lock.dep_map, _THIS_IP_);
+	spin_release(&rq_lockp(rq)->dep_map, _THIS_IP_);
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
-	rq->lock.owner = next;
+	rq_lockp(rq)->owner = next;
 #endif
 }
 
@@ -3579,8 +3579,8 @@ static inline void finish_lock_switch(struct rq *rq)
 	 * fix up the runqueue lock - which gets 'carried over' from
 	 * prev into current:
 	 */
-	spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
-	raw_spin_unlock_irq(&rq->lock);
+	spin_acquire(&rq_lockp(rq)->dep_map, 0, 0, _THIS_IP_);
+	raw_spin_rq_unlock_irq(rq);
 }
 
 /*
@@ -3730,7 +3730,7 @@ static void __balance_callback(struct rq *rq)
 	void (*func)(struct rq *rq);
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	raw_spin_rq_lock_irqsave(rq, flags);
 	head = rq->balance_callback;
 	rq->balance_callback = NULL;
 	while (head) {
@@ -3741,7 +3741,7 @@ static void __balance_callback(struct rq *rq)
 
 		func(rq);
 	}
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_rq_unlock_irqrestore(rq, flags);
 }
 
 static inline void balance_callback(struct rq *rq)
@@ -6786,7 +6786,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	__sched_fork(0, idle);
 
 	raw_spin_lock_irqsave(&idle->pi_lock, flags);
-	raw_spin_lock(&rq->lock);
+	raw_spin_rq_lock(rq);
 
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
@@ -6821,7 +6821,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
 #ifdef CONFIG_SMP
 	idle->on_cpu = 1;
 #endif
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
 
 	/* Set the preempt count _outside_ the spinlocks! */
@@ -7393,7 +7393,7 @@ void __init sched_init(void)
 		struct rq *rq;
 
 		rq = cpu_rq(i);
-		raw_spin_lock_init(&rq->lock);
+		raw_spin_lock_init(&rq->__lock);
 		rq->nr_running = 0;
 		rq->calc_load_active = 0;
 		rq->calc_load_update = jiffies + LOAD_FREQ;
diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c
index e51c1f524b8c..5c00d3dcee8d 100644
--- a/kernel/sched/cpuacct.c
+++ b/kernel/sched/cpuacct.c
@@ -112,7 +112,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu,
 	/*
 	 * Take rq->lock to make 64-bit read safe on 32-bit platforms.
 	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	raw_spin_rq_lock_irq(cpu_rq(cpu));
 #endif
 
 	if (index == CPUACCT_STAT_NSTATS) {
@@ -126,7 +126,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu,
 	}
 
 #ifndef CONFIG_64BIT
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+	raw_spin_rq_unlock_irq(cpu_rq(cpu));
 #endif
 
 	return data;
@@ -141,14 +141,14 @@ static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val)
 	/*
 	 * Take rq->lock to make 64-bit write safe on 32-bit platforms.
 	 */
-	raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+	raw_spin_rq_lock_irq(cpu_rq(cpu));
 #endif
 
 	for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
 		cpuusage->usages[i] = val;
 
 #ifndef CONFIG_64BIT
-	raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+	raw_spin_rq_unlock_irq(cpu_rq(cpu));
 #endif
 }
 
@@ -253,13 +253,13 @@ static int cpuacct_all_seq_show(struct seq_file *m, void *V)
 			 * Take rq->lock to make 64-bit read safe on 32-bit
 			 * platforms.
 			 */
-			raw_spin_lock_irq(&cpu_rq(cpu)->lock);
+			raw_spin_rq_lock_irq(cpu_rq(cpu));
 #endif
 
 			seq_printf(m, " %llu", cpuusage->usages[index]);
 
 #ifndef CONFIG_64BIT
-			raw_spin_unlock_irq(&cpu_rq(cpu)->lock);
+			raw_spin_rq_unlock_irq(cpu_rq(cpu));
 #endif
 		}
 		seq_puts(m, "\n");
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 8255267ce323..990bffb1443d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -141,7 +141,7 @@ void __add_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
 {
 	u64 old = dl_rq->running_bw;
 
-	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->running_bw += dl_bw;
 	SCHED_WARN_ON(dl_rq->running_bw < old); /* overflow */
 	SCHED_WARN_ON(dl_rq->running_bw > dl_rq->this_bw);
@@ -154,7 +154,7 @@ void __sub_running_bw(u64 dl_bw, struct dl_rq *dl_rq)
 {
 	u64 old = dl_rq->running_bw;
 
-	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->running_bw -= dl_bw;
 	SCHED_WARN_ON(dl_rq->running_bw > old); /* underflow */
 	if (dl_rq->running_bw > old)
@@ -168,7 +168,7 @@ void __add_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
 {
 	u64 old = dl_rq->this_bw;
 
-	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->this_bw += dl_bw;
 	SCHED_WARN_ON(dl_rq->this_bw < old); /* overflow */
 }
@@ -178,7 +178,7 @@ void __sub_rq_bw(u64 dl_bw, struct dl_rq *dl_rq)
 {
 	u64 old = dl_rq->this_bw;
 
-	lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock);
+	lockdep_assert_rq_held(rq_of_dl_rq(dl_rq));
 	dl_rq->this_bw -= dl_bw;
 	SCHED_WARN_ON(dl_rq->this_bw > old); /* underflow */
 	if (dl_rq->this_bw > old)
@@ -985,7 +985,7 @@ static int start_dl_timer(struct task_struct *p)
 	ktime_t now, act;
 	s64 delta;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	/*
 	 * We want the timer to fire at the deadline, but considering
@@ -1095,9 +1095,9 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		 * If the runqueue is no longer available, migrate the
 		 * task elsewhere. This necessarily changes rq.
 		 */
-		lockdep_unpin_lock(&rq->lock, rf.cookie);
+		lockdep_unpin_lock(rq_lockp(rq), rf.cookie);
 		rq = dl_task_offline_migration(rq, p);
-		rf.cookie = lockdep_pin_lock(&rq->lock);
+		rf.cookie = lockdep_pin_lock(rq_lockp(rq));
 		update_rq_clock(rq);
 
 		/*
@@ -1733,7 +1733,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 	 * from try_to_wake_up(). Hence, p->pi_lock is locked, but
 	 * rq->lock is not... So, lock it
 	 */
-	raw_spin_lock(&rq->lock);
+	raw_spin_rq_lock(rq);
 	if (p->dl.dl_non_contending) {
 		update_rq_clock(rq);
 		sub_running_bw(&p->dl, &rq->dl);
@@ -1749,7 +1749,7 @@ static void migrate_task_rq_dl(struct task_struct *p, int new_cpu __maybe_unused
 			put_task_struct(p);
 	}
 	sub_rq_bw(&p->dl, &rq->dl);
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 }
 
 static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index a260ff7800db..dda6e77accc2 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -570,7 +570,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "exec_clock",
 			SPLIT_NS(cfs_rq->exec_clock));
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	raw_spin_rq_lock_irqsave(rq, flags);
 	if (rb_first_cached(&cfs_rq->tasks_timeline))
 		MIN_vruntime = (__pick_first_entity(cfs_rq))->vruntime;
 	last = __pick_last_entity(cfs_rq);
@@ -578,7 +578,7 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
 		max_vruntime = last->vruntime;
 	min_vruntime = cfs_rq->min_vruntime;
 	rq0_min_vruntime = cpu_rq(0)->cfs.min_vruntime;
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_rq_unlock_irqrestore(rq, flags);
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "MIN_vruntime",
 			SPLIT_NS(MIN_vruntime));
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", "min_vruntime",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 49aeab435237..5aa269fbb068 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1131,7 +1131,7 @@ struct numa_group {
 static struct numa_group *deref_task_numa_group(struct task_struct *p)
 {
 	return rcu_dereference_check(p->numa_group, p == current ||
-		(lockdep_is_held(&task_rq(p)->lock) && !READ_ONCE(p->on_cpu)));
+		(lockdep_is_held(rq_lockp(task_rq(p))) && !READ_ONCE(p->on_cpu)));
 }
 
 static struct numa_group *deref_curr_numa_group(struct task_struct *p)
@@ -5454,7 +5454,7 @@ static void __maybe_unused update_runtime_enabled(struct rq *rq)
 {
 	struct task_group *tg;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tg, &task_groups, list) {
@@ -5473,7 +5473,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 {
 	struct task_group *tg;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 #ifdef CONFIG_QOS_SCHED
 	unthrottle_qos_cfs_rqs(cpu_of(rq));
@@ -6996,7 +6996,7 @@ static void migrate_task_rq_fair(struct task_struct *p, int new_cpu)
 		 * In case of TASK_ON_RQ_MIGRATING we in fact hold the 'old'
 		 * rq->lock and can modify state directly.
 		 */
-		lockdep_assert_held(&task_rq(p)->lock);
+		lockdep_assert_rq_held(task_rq(p));
 		detach_entity_cfs_rq(&p->se);
 
 	} else {
@@ -8093,7 +8093,7 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 {
 	s64 delta;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	if (p->sched_class != &fair_sched_class)
 		return 0;
@@ -8191,7 +8191,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 {
 	int tsk_cache_hot;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	/*
 	 * We do not migrate tasks that are:
@@ -8279,7 +8279,7 @@ can_migrate_task_llc(struct task_struct *p, struct rq *rq, struct rq *dst_rq)
 {
 	int dst_cpu = dst_rq->cpu;
 
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (throttled_lb_pair(task_group(p), cpu_of(rq), dst_cpu))
 		return false;
@@ -8303,7 +8303,7 @@ can_migrate_task_llc(struct task_struct *p, struct rq *rq, struct rq *dst_rq)
  */
 static void detach_task(struct task_struct *p, struct rq *src_rq, int dst_cpu)
 {
-	lockdep_assert_held(&src_rq->lock);
+	lockdep_assert_rq_held(src_rq);
 
 	deactivate_task(src_rq, p, DEQUEUE_NOCLOCK);
 	set_task_cpu(p, dst_cpu);
@@ -8319,7 +8319,7 @@ static struct task_struct *detach_one_task(struct lb_env *env)
 {
 	struct task_struct *p;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	list_for_each_entry_reverse(p,
 			&env->src_rq->cfs_tasks, se.group_node) {
@@ -8355,7 +8355,7 @@ static int detach_tasks(struct lb_env *env)
 	struct task_struct *p;
 	int detached = 0;
 
-	lockdep_assert_held(&env->src_rq->lock);
+	lockdep_assert_rq_held(env->src_rq);
 
 	if (env->imbalance <= 0)
 		return 0;
@@ -8476,7 +8476,7 @@ static int detach_tasks(struct lb_env *env)
  */
 static void attach_task(struct rq *rq, struct task_struct *p)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	BUG_ON(task_rq(p) != rq);
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
@@ -10427,7 +10427,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 		if (need_active_balance(&env)) {
 			unsigned long flags;
 
-			raw_spin_lock_irqsave(&busiest->lock, flags);
+			raw_spin_rq_lock_irqsave(busiest, flags);
 
 			/*
 			 * Don't kick the active_load_balance_cpu_stop,
@@ -10435,8 +10435,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 			 * moved to this_cpu:
 			 */
 			if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
-				raw_spin_unlock_irqrestore(&busiest->lock,
-							    flags);
+				raw_spin_rq_unlock_irqrestore(busiest, flags);
 				env.flags |= LBF_ALL_PINNED;
 				goto out_one_pinned;
 			}
@@ -10451,7 +10450,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
 				busiest->push_cpu = this_cpu;
 				active_balance = 1;
 			}
-			raw_spin_unlock_irqrestore(&busiest->lock, flags);
+			raw_spin_rq_unlock_irqrestore(busiest, flags);
 
 			if (active_balance) {
 				stop_one_cpu_nowait(cpu_of(busiest),
@@ -11203,7 +11202,7 @@ static void nohz_newidle_balance(struct rq *this_rq)
 	    time_before(jiffies, READ_ONCE(nohz.next_blocked)))
 		return;
 
-	raw_spin_unlock(&this_rq->lock);
+	raw_spin_rq_unlock(this_rq);
 	/*
 	 * This CPU is going to be idle and blocked load of idle CPUs
 	 * need to be updated. Run the ilb locally as it is a good
@@ -11212,7 +11211,7 @@ static void nohz_newidle_balance(struct rq *this_rq)
 	 */
 	if (!_nohz_idle_balance(this_rq, NOHZ_STATS_KICK, CPU_NEWLY_IDLE))
 		kick_ilb(NOHZ_STATS_KICK);
-	raw_spin_lock(&this_rq->lock);
+	raw_spin_rq_lock(this_rq);
 }
 
 #else /* !CONFIG_NO_HZ_COMMON */
@@ -11273,7 +11272,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 		goto out;
 	}
 
-	raw_spin_unlock(&this_rq->lock);
+	raw_spin_rq_unlock(this_rq);
 
 	update_blocked_averages(this_cpu);
 	rcu_read_lock();
@@ -11311,7 +11310,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf)
 	}
 	rcu_read_unlock();
 
-	raw_spin_lock(&this_rq->lock);
+	raw_spin_rq_lock(this_rq);
 
 	if (curr_cost > this_rq->max_idle_balance_cost)
 		this_rq->max_idle_balance_cost = curr_cost;
@@ -11392,7 +11391,7 @@ detach_next_task(struct cfs_rq *cfs_rq, struct rq *dst_rq)
 	struct task_struct *p;
 	struct rq *rq = rq_of(cfs_rq);
 
-	lockdep_assert_held(&rq_of(cfs_rq)->lock);
+	lockdep_assert_rq_held(rq_of(cfs_rq));
 
 	list_for_each_entry_reverse(p, &rq->cfs_tasks, se.group_node) {
 		if (can_migrate_task_llc(p, rq, dst_rq)) {
@@ -11424,7 +11423,7 @@ static int steal_from(struct rq *dst_rq, struct rq_flags *dst_rf, bool *locked,
 
 	if (*locked) {
 		rq_unpin_lock(dst_rq, dst_rf);
-		raw_spin_unlock(&dst_rq->lock);
+		raw_spin_rq_unlock(dst_rq);
 		*locked = false;
 	}
 	rq_lock_irqsave(src_rq, &rf);
@@ -11438,7 +11437,7 @@ static int steal_from(struct rq *dst_rq, struct rq_flags *dst_rf, bool *locked,
 	rq_unlock(src_rq, &rf);
 
 	if (p) {
-		raw_spin_lock(&dst_rq->lock);
+		raw_spin_rq_lock(dst_rq);
 		rq_repin_lock(dst_rq, dst_rf);
 		*locked = true;
 		update_rq_clock(dst_rq);
@@ -11518,7 +11517,7 @@ static int try_steal(struct rq *dst_rq, struct rq_flags *dst_rf)
 out:
 	rcu_read_unlock();
 	if (!locked) {
-		raw_spin_lock(&dst_rq->lock);
+		raw_spin_rq_lock(dst_rq);
 		rq_repin_lock(dst_rq, dst_rf);
 	}
 	stolen |= (dst_rq->cfs.h_nr_running > 0);
@@ -11945,9 +11944,9 @@ void unregister_fair_sched_group(struct task_group *tg)
 
 		rq = cpu_rq(cpu);
 
-		raw_spin_lock_irqsave(&rq->lock, flags);
+		raw_spin_rq_lock_irqsave(rq, flags);
 		list_del_leaf_cfs_rq(tg->cfs_rq[cpu]);
-		raw_spin_unlock_irqrestore(&rq->lock, flags);
+		raw_spin_rq_unlock_irqrestore(rq, flags);
 	}
 }
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 2593a733c084..c781dc136a5b 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -448,10 +448,10 @@ struct task_struct *pick_next_task_idle(struct rq *rq)
 static void
 dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
 {
-	raw_spin_unlock_irq(&rq->lock);
+	raw_spin_rq_unlock_irq(rq);
 	printk(KERN_ERR "bad: scheduling from the idle thread!\n");
 	dump_stack();
-	raw_spin_lock_irq(&rq->lock);
+	raw_spin_rq_lock_irq(rq);
 }
 
 /*
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 89150ced09cf..dc3a730e0d04 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -134,7 +134,7 @@ static inline void update_idle_rq_clock_pelt(struct rq *rq)
 
 static inline u64 rq_clock_pelt(struct rq *rq)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 	assert_clock_updated(rq);
 
 	return rq->clock_pelt - rq->lost_idle_time;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 59c3e20943ac..4e971b5cea19 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -890,7 +890,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 		if (skip)
 			continue;
 
-		raw_spin_lock(&rq->lock);
+		raw_spin_rq_lock(rq);
 		update_rq_clock(rq);
 
 		if (rt_rq->rt_time) {
@@ -928,7 +928,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
-		raw_spin_unlock(&rq->lock);
+		raw_spin_rq_unlock(rq);
 	}
 
 	if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
@@ -2097,9 +2097,9 @@ void rto_push_irq_work_func(struct irq_work *work)
 	 * When it gets updated, a check is made if a push is possible.
 	 */
 	if (has_pushable_tasks(rq)) {
-		raw_spin_lock(&rq->lock);
+		raw_spin_rq_lock(rq);
 		push_rt_tasks(rq);
-		raw_spin_unlock(&rq->lock);
+		raw_spin_rq_unlock(rq);
 	}
 
 	raw_spin_lock(&rd->rto_lock);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b71627aacc30..4aed3a7923a2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -937,7 +937,7 @@ DECLARE_STATIC_KEY_FALSE(sched_uclamp_used);
  */
 struct rq {
 	/* runqueue lock: */
-	raw_spinlock_t		lock;
+	raw_spinlock_t		__lock;
 
 	/*
 	 * nr_running and cpu_load should be in the same cacheline because
@@ -1153,7 +1153,7 @@ void init_qos_hrtimer(int cpu);
 
 static inline raw_spinlock_t *rq_lockp(struct rq *rq)
 {
-	return &rq->lock;
+	return &rq->__lock;
 }
 
 static inline void lockdep_assert_rq_held(struct rq *rq)
@@ -1267,7 +1267,7 @@ static inline void assert_clock_updated(struct rq *rq)
 
 static inline u64 rq_clock(struct rq *rq)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 	assert_clock_updated(rq);
 
 	return rq->clock;
@@ -1275,7 +1275,7 @@ static inline u64 rq_clock(struct rq *rq)
 
 static inline u64 rq_clock_task(struct rq *rq)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 	assert_clock_updated(rq);
 
 	return rq->clock_task;
@@ -1301,7 +1301,7 @@ static inline u64 rq_clock_thermal(struct rq *rq)
 
 static inline void rq_clock_skip_update(struct rq *rq)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 	rq->clock_update_flags |= RQCF_REQ_SKIP;
 }
 
@@ -1311,7 +1311,7 @@ static inline void rq_clock_skip_update(struct rq *rq)
  */
 static inline void rq_clock_cancel_skipupdate(struct rq *rq)
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 	rq->clock_update_flags &= ~RQCF_REQ_SKIP;
 }
 
@@ -1340,7 +1340,7 @@ struct rq_flags {
  */
 static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf)
 {
-	rf->cookie = lockdep_pin_lock(&rq->lock);
+	rf->cookie = lockdep_pin_lock(rq_lockp(rq));
 
 #ifdef CONFIG_SCHED_DEBUG
 	rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP);
@@ -1355,12 +1355,12 @@ static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf)
 		rf->clock_update_flags = RQCF_UPDATED;
 #endif
 
-	lockdep_unpin_lock(&rq->lock, rf->cookie);
+	lockdep_unpin_lock(rq_lockp(rq), rf->cookie);
 }
 
 static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf)
 {
-	lockdep_repin_lock(&rq->lock, rf->cookie);
+	lockdep_repin_lock(rq_lockp(rq), rf->cookie);
 
 #ifdef CONFIG_SCHED_DEBUG
 	/*
@@ -1381,7 +1381,7 @@ static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
 	rq_unpin_lock(rq, rf);
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 }
 
 static inline void
@@ -1390,7 +1390,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	__releases(p->pi_lock)
 {
 	rq_unpin_lock(rq, rf);
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
@@ -1398,7 +1398,7 @@ static inline void
 rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
-	raw_spin_lock_irqsave(&rq->lock, rf->flags);
+	raw_spin_rq_lock_irqsave(rq, rf->flags);
 	rq_pin_lock(rq, rf);
 }
 
@@ -1406,7 +1406,7 @@ static inline void
 rq_lock_irq(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
-	raw_spin_lock_irq(&rq->lock);
+	raw_spin_rq_lock_irq(rq);
 	rq_pin_lock(rq, rf);
 }
 
@@ -1414,7 +1414,7 @@ static inline void
 rq_lock(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
-	raw_spin_lock(&rq->lock);
+	raw_spin_rq_lock(rq);
 	rq_pin_lock(rq, rf);
 }
 
@@ -1422,7 +1422,7 @@ static inline void
 rq_relock(struct rq *rq, struct rq_flags *rf)
 	__acquires(rq->lock)
 {
-	raw_spin_lock(&rq->lock);
+	raw_spin_rq_lock(rq);
 	rq_repin_lock(rq, rf);
 }
 
@@ -1431,7 +1431,7 @@ rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
 	rq_unpin_lock(rq, rf);
-	raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
+	raw_spin_rq_unlock_irqrestore(rq, rf->flags);
 }
 
 static inline void
@@ -1439,7 +1439,7 @@ rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
 	rq_unpin_lock(rq, rf);
-	raw_spin_unlock_irq(&rq->lock);
+	raw_spin_rq_unlock_irq(rq);
 }
 
 static inline void
@@ -1447,7 +1447,7 @@ rq_unlock(struct rq *rq, struct rq_flags *rf)
 	__releases(rq->lock)
 {
 	rq_unpin_lock(rq, rf);
-	raw_spin_unlock(&rq->lock);
+	raw_spin_rq_unlock(rq);
 }
 
 static inline struct rq *
@@ -1516,7 +1516,7 @@ queue_balance_callback(struct rq *rq,
 		       struct callback_head *head,
 		       void (*func)(struct rq *rq))
 {
-	lockdep_assert_held(&rq->lock);
+	lockdep_assert_rq_held(rq);
 
 	if (unlikely(head->next))
 		return;
@@ -2221,7 +2221,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
-	raw_spin_unlock(&this_rq->lock);
+	raw_spin_rq_unlock(this_rq);
 	double_rq_lock(this_rq, busiest);
 
 	return 1;
@@ -2240,20 +2240,22 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
 	__acquires(busiest->lock)
 	__acquires(this_rq->lock)
 {
-	int ret = 0;
-
-	if (unlikely(!raw_spin_trylock(&busiest->lock))) {
-		if (busiest < this_rq) {
-			raw_spin_unlock(&this_rq->lock);
-			raw_spin_lock(&busiest->lock);
-			raw_spin_lock_nested(&this_rq->lock,
-					      SINGLE_DEPTH_NESTING);
-			ret = 1;
-		} else
-			raw_spin_lock_nested(&busiest->lock,
-					      SINGLE_DEPTH_NESTING);
+	if (rq_lockp(this_rq) == rq_lockp(busiest))
+		return 0;
+
+	if (likely(raw_spin_rq_trylock(busiest)))
+		return 0;
+
+	if (rq_lockp(busiest) >= rq_lockp(this_rq)) {
+		raw_spin_rq_lock_nested(busiest, SINGLE_DEPTH_NESTING);
+		return 0;
 	}
-	return ret;
+
+	raw_spin_rq_unlock(this_rq);
+	raw_spin_rq_lock(busiest);
+	raw_spin_rq_lock_nested(this_rq, SINGLE_DEPTH_NESTING);
+
+	return 1;
 }
 
 #endif /* CONFIG_PREEMPTION */
@@ -2263,11 +2265,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest)
  */
 static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
 {
-	if (unlikely(!irqs_disabled())) {
-		/* printk() doesn't work well under rq->lock */
-		raw_spin_unlock(&this_rq->lock);
-		BUG_ON(1);
-	}
+	lockdep_assert_irqs_disabled();
 
 	return _double_lock_balance(this_rq, busiest);
 }
@@ -2275,8 +2273,9 @@ static inline int double_lock_balance(struct rq *this_rq, struct rq *busiest)
 static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest)
 	__releases(busiest->lock)
 {
-	raw_spin_unlock(&busiest->lock);
-	lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_);
+	if (rq_lockp(this_rq) != rq_lockp(busiest))
+		raw_spin_rq_unlock(busiest);
+	lock_set_subclass(&rq_lockp(this_rq)->dep_map, 0, _RET_IP_);
 }
 
 static inline void double_lock(spinlock_t *l1, spinlock_t *l2)
@@ -2317,16 +2316,16 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
 	__acquires(rq2->lock)
 {
 	BUG_ON(!irqs_disabled());
-	if (rq1 == rq2) {
-		raw_spin_lock(&rq1->lock);
+	if (rq_lockp(rq1) == rq_lockp(rq2)) {
+		raw_spin_rq_lock(rq1);
 		__acquire(rq2->lock);	/* Fake it out ;) */
 	} else {
-		if (rq1 < rq2) {
-			raw_spin_lock(&rq1->lock);
-			raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING);
+		if (rq_lockp(rq1) < rq_lockp(rq2)) {
+			raw_spin_rq_lock(rq1);
+			raw_spin_rq_lock_nested(rq2, SINGLE_DEPTH_NESTING);
 		} else {
-			raw_spin_lock(&rq2->lock);
-			raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING);
+			raw_spin_rq_lock(rq2);
+			raw_spin_rq_lock_nested(rq1, SINGLE_DEPTH_NESTING);
 		}
 	}
 }
@@ -2341,9 +2340,9 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 	__releases(rq1->lock)
 	__releases(rq2->lock)
 {
-	raw_spin_unlock(&rq1->lock);
-	if (rq1 != rq2)
-		raw_spin_unlock(&rq2->lock);
+	raw_spin_rq_unlock(rq1);
+	if (rq_lockp(rq1) != rq_lockp(rq2))
+		raw_spin_rq_unlock(rq2);
 	else
 		__release(rq2->lock);
 }
@@ -2366,7 +2365,7 @@ static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
 {
 	BUG_ON(!irqs_disabled());
 	BUG_ON(rq1 != rq2);
-	raw_spin_lock(&rq1->lock);
+	raw_spin_rq_lock(rq1);
 	__acquire(rq2->lock);	/* Fake it out ;) */
 }
 
@@ -2381,7 +2380,7 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
 	__releases(rq2->lock)
 {
 	BUG_ON(rq1 != rq2);
-	raw_spin_unlock(&rq1->lock);
+	raw_spin_rq_unlock(rq1);
 	__release(rq2->lock);
 }
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 9b4e3b25ddff..2678e7590cfc 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -469,7 +469,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	struct root_domain *old_rd = NULL;
 	unsigned long flags;
 
-	raw_spin_lock_irqsave(&rq->lock, flags);
+	raw_spin_rq_lock_irqsave(rq, flags);
 
 	if (rq->rd) {
 		old_rd = rq->rd;
@@ -495,7 +495,7 @@ void rq_attach_root(struct rq *rq, struct root_domain *rd)
 	if (cpumask_test_cpu(rq->cpu, cpu_active_mask))
 		set_rq_online(rq);
 
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_rq_unlock_irqrestore(rq, flags);
 
 	if (old_rd)
 		call_rcu(&old_rd->rcu, free_rootdomain);
-- 
GitLab