Merge tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Fair scheduler (SCHED_OTHER) improvements:
   - Remove the old and now unused SIS_PROP code & option
   - Scan cluster before LLC in the wake-up path
   - Use candidate prev/recent_used CPU if scanning failed for cluster
     wakeup

  NUMA scheduling improvements:
   - Improve the VMA access-PID code to better skip/scan VMAs
   - Extend tracing to cover VMA-skipping decisions
   - Improve/fix the recently introduced sched_numa_find_nth_cpu() code
   - Generalize numa_map_to_online_node()

  Energy scheduling improvements:
   - Remove the EM_MAX_COMPLEXITY limit
   - Add tracepoints to track energy computation
   - Make the behavior of the 'sched_energy_aware' sysctl more
     consistent
   - Consolidate and clean up access to a CPU's max compute capacity
   - Fix uclamp code corner cases

  RT scheduling improvements:
   - Drive dl_rq->overloaded with dl_rq->pushable_dl_tasks updates
   - Drive the ->rto_mask with rt_rq->pushable_tasks updates

  Scheduler scalability improvements:
   - Rate-limit updates to tg->load_avg
   - On x86 disable IBRS when CPU is offline to improve single-threaded
     performance
   - Micro-optimize in_task() and in_interrupt()
   - Micro-optimize the PSI code
   - Avoid updating PSI triggers and ->rtpoll_total when there are no
     state changes

  Core scheduler infrastructure improvements:
   - Use saved_state to reduce some spurious freezer wakeups
   - Bring in a handful of fast-headers improvements to scheduler
     headers
   - Make the scheduler UAPI headers more widely usable by user-space
   - Simplify the control flow of scheduler syscalls by using lock
     guards
   - Fix sched_setaffinity() vs. CPU hotplug race

  Scheduler debuggability improvements:
   - Disallow writing invalid values to sched_rt_period_us
   - Fix a race in the rq-clock debugging code triggering warnings
   - Fix a warning in the bandwidth distribution code
   - Micro-optimize in_atomic_preempt_off() checks
   - Enforce that the tasklist_lock is held in for_each_thread()
   - Print the TGID in sched_show_task()
   - Remove the /proc/sys/kernel/sched_child_runs_first sysctl

  ... and misc cleanups & fixes"

* tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
  sched/fair: Remove SIS_PROP
  sched/fair: Use candidate prev/recent_used CPU if scanning failed for cluster wakeup
  sched/fair: Scan cluster before scanning LLC in wake-up path
  sched: Add cpus_share_resources API
  sched/core: Fix RQCF_ACT_SKIP leak
  sched/fair: Remove unused 'curr' argument from pick_next_entity()
  sched/nohz: Update comments about NEWILB_KICK
  sched/fair: Remove duplicate #include
  sched/psi: Update poll => rtpoll in relevant comments
  sched: Make PELT acronym definition searchable
  sched: Fix stop_one_cpu_nowait() vs hotplug
  sched/psi: Bail out early from irq time accounting
  sched/topology: Rename 'DIE' domain to 'PKG'
  sched/psi: Delete the 'update_total' function parameter from update_triggers()
  sched/psi: Avoid updating PSI triggers and ->rtpoll_total when there are no state changes
  sched/headers: Remove comment referring to rq::cpu_load, since this has been removed
  sched/numa: Complete scanning of inactive VMAs when there is no alternative
  sched/numa: Complete scanning of partial VMAs regardless of PID activity
  sched/numa: Move up the access pid reset logic
  sched/numa: Trace decisions related to skipping VMAs
  ...

1 files changed, 274 insertions, 371 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9b075b541865..81885748871d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -85,7 +85,6 @@
 
 #include "sched.h"
 #include "stats.h"
-#include "autogroup.h"
 
 #include "autogroup.h"
 #include "pelt.h"
@@ -114,6 +113,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp);
 EXPORT_TRACEPOINT_SYMBOL_GPL(sched_update_nr_running_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
@@ -919,14 +919,13 @@ static bool set_nr_if_polling(struct task_struct *p)
 	struct thread_info *ti = task_thread_info(p);
 	typeof(ti->flags) val = READ_ONCE(ti->flags);
 
-	for (;;) {
+	do {
 		if (!(val & _TIF_POLLING_NRFLAG))
 			return false;
 		if (val & _TIF_NEED_RESCHED)
 			return true;
-		if (try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED))
-			break;
-	}
+	} while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
+
 	return true;
 }
 
@@ -1480,16 +1479,12 @@ static void __uclamp_update_util_min_rt_default(struct task_struct *p)
 
 static void uclamp_update_util_min_rt_default(struct task_struct *p)
 {
-	struct rq_flags rf;
-	struct rq *rq;
-
 	if (!rt_task(p))
 		return;
 
 	/* Protect updates to p->uclamp_* */
-	rq = task_rq_lock(p, &rf);
+	guard(task_rq_lock)(p);
 	__uclamp_update_util_min_rt_default(p);
-	task_rq_unlock(rq, p, &rf);
 }
 
 static inline struct uclamp_se
@@ -1785,9 +1780,8 @@ static void uclamp_update_root_tg(void)
 	uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX],
 		      sysctl_sched_uclamp_util_max, false);
 
-	rcu_read_lock();
+	guard(rcu)();
 	cpu_util_update_eff(&root_task_group.css);
-	rcu_read_unlock();
 }
 #else
 static void uclamp_update_root_tg(void) { }
@@ -1814,10 +1808,9 @@ static void uclamp_sync_util_min_rt_default(void)
 	smp_mb__after_spinlock();
 	read_unlock(&tasklist_lock);
 
-	rcu_read_lock();
+	guard(rcu)();
 	for_each_process_thread(g, p)
 		uclamp_update_util_min_rt_default(p);
-	rcu_read_unlock();
 }
 
 static int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
@@ -2218,10 +2211,10 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p,
 		p->sched_class->prio_changed(rq, p, oldprio);
 }
 
-void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
+void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->sched_class == rq->curr->sched_class)
-		rq->curr->sched_class->check_preempt_curr(rq, p, flags);
+		rq->curr->sched_class->wakeup_preempt(rq, p, flags);
 	else if (sched_class_above(p->sched_class, rq->curr->sched_class))
 		resched_curr(rq);
 
@@ -2239,31 +2232,21 @@ int __task_state_match(struct task_struct *p, unsigned int state)
 	if (READ_ONCE(p->__state) & state)
 		return 1;
 
-#ifdef CONFIG_PREEMPT_RT
 	if (READ_ONCE(p->saved_state) & state)
 		return -1;
-#endif
+
 	return 0;
 }
 
 static __always_inline
 int task_state_match(struct task_struct *p, unsigned int state)
 {
-#ifdef CONFIG_PREEMPT_RT
-	int match;
-
 	/*
-	 * Serialize against current_save_and_set_rtlock_wait_state() and
-	 * current_restore_rtlock_saved_state().
+	 * Serialize against current_save_and_set_rtlock_wait_state(),
+	 * current_restore_rtlock_saved_state(), and __refrigerator().
 	 */
-	raw_spin_lock_irq(&p->pi_lock);
-	match = __task_state_match(p, state);
-	raw_spin_unlock_irq(&p->pi_lock);
-
-	return match;
-#else
+	guard(raw_spinlock_irq)(&p->pi_lock);
 	return __task_state_match(p, state);
-#endif
 }
 
 /*
@@ -2417,10 +2400,9 @@ void migrate_disable(void)
 		return;
 	}
 
-	preempt_disable();
+	guard(preempt)();
 	this_rq()->nr_pinned++;
 	p->migration_disabled = 1;
-	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(migrate_disable);
 
@@ -2444,7 +2426,7 @@ void migrate_enable(void)
 	 * Ensure stop_task runs either before or after this, and that
 	 * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
 	 */
-	preempt_disable();
+	guard(preempt)();
 	if (p->cpus_ptr != &p->cpus_mask)
 		__set_cpus_allowed_ptr(p, &ac);
 	/*
@@ -2455,7 +2437,6 @@ void migrate_enable(void)
 	barrier();
 	p->migration_disabled = 0;
 	this_rq()->nr_pinned--;
-	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(migrate_enable);
 
@@ -2527,7 +2508,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
 	rq_lock(rq, rf);
 	WARN_ON_ONCE(task_cpu(p) != new_cpu);
 	activate_task(rq, p, 0);
-	check_preempt_curr(rq, p, 0);
+	wakeup_preempt(rq, p, 0);
 
 	return rq;
 }
@@ -2664,9 +2645,11 @@ static int migration_cpu_stop(void *data)
 		 * it.
 		 */
 		WARN_ON_ONCE(!pending->stop_pending);
+		preempt_disable();
 		task_rq_unlock(rq, p, &rf);
 		stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
 				    &pending->arg, &pending->stop_work);
+		preempt_enable();
 		return 0;
 	}
 out:
@@ -2986,12 +2969,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 			complete = true;
 		}
 
+		preempt_disable();
 		task_rq_unlock(rq, p, rf);
-
 		if (push_task) {
 			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
 					    p, &rq->push_work);
 		}
+		preempt_enable();
 
 		if (complete)
 			complete_all(&pending->done);
@@ -3057,12 +3041,13 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 		if (flags & SCA_MIGRATE_ENABLE)
 			p->migration_flags &= ~MDF_PUSH;
 
+		preempt_disable();
 		task_rq_unlock(rq, p, rf);
-
 		if (!stop_pending) {
 			stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop,
 					    &pending->arg, &pending->stop_work);
 		}
+		preempt_enable();
 
 		if (flags & SCA_MIGRATE_ENABLE)
 			return 0;
@@ -3409,7 +3394,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu)
 		deactivate_task(src_rq, p, 0);
 		set_task_cpu(p, cpu);
 		activate_task(dst_rq, p, 0);
-		check_preempt_curr(dst_rq, p, 0);
+		wakeup_preempt(dst_rq, p, 0);
 
 		rq_unpin_lock(dst_rq, &drf);
 		rq_unpin_lock(src_rq, &srf);
@@ -3516,13 +3501,11 @@ out:
  */
 void kick_process(struct task_struct *p)
 {
-	int cpu;
+	guard(preempt)();
+	int cpu = task_cpu(p);
 
-	preempt_disable();
-	cpu = task_cpu(p);
 	if ((cpu != smp_processor_id()) && task_curr(p))
 		smp_send_reschedule(cpu);
-	preempt_enable();
 }
 EXPORT_SYMBOL_GPL(kick_process);
 
@@ -3785,7 +3768,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 	}
 
 	activate_task(rq, p, en_flags);
-	check_preempt_curr(rq, p, wake_flags);
+	wakeup_preempt(rq, p, wake_flags);
 
 	ttwu_do_wakeup(p);
 
@@ -3809,9 +3792,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 		if (rq->avg_idle > max)
 			rq->avg_idle = max;
 
-		rq->wake_stamp = jiffies;
-		rq->wake_avg_idle = rq->avg_idle / 2;
-
 		rq->idle_stamp = 0;
 	}
 #endif
@@ -3856,7 +3836,7 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 			 * it should preempt the task that is current now.
 			 */
 			update_rq_clock(rq);
-			check_preempt_curr(rq, p, wake_flags);
+			wakeup_preempt(rq, p, wake_flags);
 		}
 		ttwu_do_wakeup(p);
 		ret = 1;
@@ -3956,6 +3936,18 @@ bool cpus_share_cache(int this_cpu, int that_cpu)
 	return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
 }
 
+/*
+ * Whether CPUs are share cache resources, which means LLC on non-cluster
+ * machines and LLC tag or L2 on machines with clusters.
+ */
+bool cpus_share_resources(int this_cpu, int that_cpu)
+{
+	if (this_cpu == that_cpu)
+		return true;
+
+	return per_cpu(sd_share_id, this_cpu) == per_cpu(sd_share_id, that_cpu);
+}
+
 static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
 {
 	/*
@@ -4036,13 +4028,17 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * The caller holds p::pi_lock if p != current or has preemption
  * disabled when p == current.
  *
- * The rules of PREEMPT_RT saved_state:
+ * The rules of saved_state:
  *
  *   The related locking code always holds p::pi_lock when updating
  *   p::saved_state, which means the code is fully serialized in both cases.
  *
- *   The lock wait and lock wakeups happen via TASK_RTLOCK_WAIT. No other
- *   bits set. This allows to distinguish all wakeup scenarios.
+ *   For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
+ *   No other bits set. This allows to distinguish all wakeup scenarios.
+ *
+ *   For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
+ *   allows us to prevent early wakeup of tasks before they can be run on
+ *   asymmetric ISA architectures (eg ARMv9).
  */
 static __always_inline
 bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
@@ -4056,13 +4052,13 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
 
 	*success = !!(match = __task_state_match(p, state));
 
-#ifdef CONFIG_PREEMPT_RT
 	/*
 	 * Saved state preserves the task state across blocking on
-	 * an RT lock.  If the state matches, set p::saved_state to
-	 * TASK_RUNNING, but do not wake the task because it waits
-	 * for a lock wakeup. Also indicate success because from
-	 * the regular waker's point of view this has succeeded.
+	 * an RT lock or TASK_FREEZABLE tasks.  If the state matches,
+	 * set p::saved_state to TASK_RUNNING, but do not wake the task
+	 * because it waits for a lock wakeup or __thaw_task(). Also
+	 * indicate success because from the regular waker's point of
+	 * view this has succeeded.
 	 *
 	 * After acquiring the lock the task will restore p::__state
 	 * from p::saved_state which ensures that the regular
@@ -4072,7 +4068,7 @@ bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
 	 */
 	if (match < 0)
 		p->saved_state = TASK_RUNNING;
-#endif
+
 	return match > 0;
 }
 
@@ -4254,7 +4250,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
 		 * __schedule().  See the comment for smp_mb__after_spinlock().
 		 *
-		 * A similar smb_rmb() lives in try_invoke_on_locked_down_task().
+		 * A similar smp_rmb() lives in __task_needs_rq_lock().
 		 */
 		smp_rmb();
 		if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
@@ -4871,7 +4867,7 @@ void wake_up_new_task(struct task_struct *p)
 
 	activate_task(rq, p, ENQUEUE_NOCLOCK);
 	trace_sched_wakeup_new(p);
-	check_preempt_curr(rq, p, WF_FORK);
+	wakeup_preempt(rq, p, WF_FORK);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
@@ -5374,8 +5370,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	/* switch_mm_cid() requires the memory barriers above. */
 	switch_mm_cid(rq, prev, next);
 
-	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
-
 	prepare_lock_switch(rq, next, rf);
 
 	/* Here we just switch the register state and the stack. */
@@ -5916,8 +5910,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
 	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
-	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
-	    && in_atomic_preempt_off()) {
+	if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
 		pr_err("Preemption disabled at:");
 		print_ip_sym(KERN_ERR, preempt_disable_ip);
 	}
@@ -6368,8 +6361,9 @@ static void sched_core_balance(struct rq *rq)
 	struct sched_domain *sd;
 	int cpu = cpu_of(rq);
 
-	preempt_disable();
-	rcu_read_lock();
+	guard(preempt)();
+	guard(rcu)();
+
 	raw_spin_rq_unlock_irq(rq);
 	for_each_domain(cpu, sd) {
 		if (need_resched())
@@ -6379,8 +6373,6 @@ static void sched_core_balance(struct rq *rq)
 			break;
 	}
 	raw_spin_rq_lock_irq(rq);
-	rcu_read_unlock();
-	preempt_enable();
 }
 
 static DEFINE_PER_CPU(struct balance_callback, core_balance_head);
@@ -6615,6 +6607,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 	/* Promote REQ to ACT */
 	rq->clock_update_flags <<= 1;
 	update_rq_clock(rq);
+	rq->clock_update_flags = RQCF_UPDATED;
 
 	switch_count = &prev->nivcsw;
 
@@ -6694,8 +6687,6 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		/* Also unlocks the rq: */
 		rq = context_switch(rq, prev, next, &rf);
 	} else {
-		rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
-
 		rq_unpin_lock(rq, &rf);
 		__balance_callbacks(rq);
 		raw_spin_rq_unlock_irq(rq);
@@ -6734,12 +6725,10 @@ static inline void sched_submit_work(struct task_struct *tsk)
 	 * If a worker goes to sleep, notify and ask workqueue whether it
 	 * wants to wake up a task to maintain concurrency.
 	 */
-	if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) {
-		if (task_flags & PF_WQ_WORKER)
-			wq_worker_sleeping(tsk);
-		else
-			io_wq_worker_sleeping(tsk);
-	}
+	if (task_flags & PF_WQ_WORKER)
+		wq_worker_sleeping(tsk);
+	else if (task_flags & PF_IO_WORKER)
+		io_wq_worker_sleeping(tsk);
 
 	/*
 	 * spinlock and rwlock must not flush block requests.  This will
@@ -7225,9 +7214,8 @@ static inline int rt_effective_prio(struct task_struct *p, int prio)
 void set_user_nice(struct task_struct *p, long nice)
 {
 	bool queued, running;
-	int old_prio;
-	struct rq_flags rf;
 	struct rq *rq;
+	int old_prio;
 
 	if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
 		return;
@@ -7235,7 +7223,9 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * We have to be careful, if called from sys_setpriority(),
 	 * the task might be in the middle of scheduling on another CPU.
 	 */
-	rq = task_rq_lock(p, &rf);
+	CLASS(task_rq_lock, rq_guard)(p);
+	rq = rq_guard.rq;
+
 	update_rq_clock(rq);
 
 	/*
@@ -7246,8 +7236,9 @@ void set_user_nice(struct task_struct *p, long nice)
 	 */
 	if (task_has_dl_policy(p) || task_has_rt_policy(p)) {
 		p->static_prio = NICE_TO_PRIO(nice);
-		goto out_unlock;
+		return;
 	}
+
 	queued = task_on_rq_queued(p);
 	running = task_current(rq, p);
 	if (queued)
@@ -7270,9 +7261,6 @@ void set_user_nice(struct task_struct *p, long nice)
 	 * lowered its priority, then reschedule its CPU:
 	 */
 	p->sched_class->prio_changed(rq, p, old_prio);
-
-out_unlock:
-	task_rq_unlock(rq, p, &rf);
 }
 EXPORT_SYMBOL(set_user_nice);
 
@@ -7545,6 +7533,21 @@ static struct task_struct *find_process_by_pid(pid_t pid)
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
+static struct task_struct *find_get_task(pid_t pid)
+{
+	struct task_struct *p;
+	guard(rcu)();
+
+	p = find_process_by_pid(pid);
+	if (likely(p))
+		get_task_struct(p);
+
+	return p;
+}
+
+DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
+	     find_get_task(pid), pid_t pid)
+
 /*
  * sched_setparam() passes in -1 for its policy, to let the functions
  * it calls know not to change it.
@@ -7582,14 +7585,11 @@ static void __setscheduler_params(struct task_struct *p,
 static bool check_same_owner(struct task_struct *p)
 {
 	const struct cred *cred = current_cred(), *pcred;
-	bool match;
+	guard(rcu)();
 
-	rcu_read_lock();
 	pcred = __task_cred(p);
-	match = (uid_eq(cred->euid, pcred->euid) ||
-		 uid_eq(cred->euid, pcred->uid));
-	rcu_read_unlock();
-	return match;
+	return (uid_eq(cred->euid, pcred->euid) ||
+		uid_eq(cred->euid, pcred->uid));
 }
 
 /*
@@ -8001,27 +8001,17 @@ static int
 do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 {
 	struct sched_param lparam;
-	struct task_struct *p;
-	int retval;
 
 	if (!param || pid < 0)
 		return -EINVAL;
 	if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
 		return -EFAULT;
 
-	rcu_read_lock();
-	retval = -ESRCH;
-	p = find_process_by_pid(pid);
-	if (likely(p))
-		get_task_struct(p);
-	rcu_read_unlock();
-
-	if (likely(p)) {
-		retval = sched_setscheduler(p, policy, &lparam);
-		put_task_struct(p);
-	}
+	CLASS(find_get_task, p)(pid);
+	if (!p)
+		return -ESRCH;
 
-	return retval;
+	return sched_setscheduler(p, policy, &lparam);
 }
 
 /*
@@ -8117,7 +8107,6 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 			       unsigned int, flags)
 {
 	struct sched_attr attr;
-	struct task_struct *p;
 	int retval;
 
 	if (!uattr || pid < 0 || flags)
@@ -8132,21 +8121,14 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 	if (attr.sched_flags & SCHED_FLAG_KEEP_POLICY)
 		attr.sched_policy = SETPARAM_POLICY;
 
-	rcu_read_lock();
-	retval = -ESRCH;
-	p = find_process_by_pid(pid);
-	if (likely(p))
-		get_task_struct(p);
-	rcu_read_unlock();
+	CLASS(find_get_task, p)(pid);
+	if (!p)
+		return -ESRCH;
 
-	if (likely(p)) {
-		if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
-			get_params(p, &attr);
-		retval = sched_setattr(p, &attr);
-		put_task_struct(p);
-	}
+	if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
+		get_params(p, &attr);
 
-	return retval;
+	return sched_setattr(p, &attr);
 }
 
 /**
@@ -8164,16 +8146,17 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
 	if (pid < 0)
 		return -EINVAL;
 
-	retval = -ESRCH;
-	rcu_read_lock();
+	guard(rcu)();
 	p = find_process_by_pid(pid);
-	if (p) {
-		retval = security_task_getscheduler(p);
-		if (!retval)
-			retval = p->policy
-				| (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0);
+	if (!p)
+		return -ESRCH;
+
+	retval = security_task_getscheduler(p);
+	if (!retval) {
+		retval = p->policy;
+		if (p->sched_reset_on_fork)
+			retval |= SCHED_RESET_ON_FORK;
 	}
-	rcu_read_unlock();
 	return retval;
 }
 
@@ -8194,30 +8177,23 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
 	if (!param || pid < 0)
 		return -EINVAL;
 
-	rcu_read_lock();
-	p = find_process_by_pid(pid);
-	retval = -ESRCH;
-	if (!p)
-		goto out_unlock;
+	scoped_guard (rcu) {
+		p = find_process_by_pid(pid);
+		if (!p)
+			return -ESRCH;
 
-	retval = security_task_getscheduler(p);
-	if (retval)
-		goto out_unlock;
+		retval = security_task_getscheduler(p);
+		if (retval)
+			return retval;
 
-	if (task_has_rt_policy(p))
-		lp.sched_priority = p->rt_priority;
-	rcu_read_unlock();
+		if (task_has_rt_policy(p))
+			lp.sched_priority = p->rt_priority;
+	}
 
 	/*
 	 * This one might sleep, we cannot do it with a spinlock held ...
 	 */
-	retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
-
-	return retval;
-
-out_unlock:
-	rcu_read_unlock();
-	return retval;
+	return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
 }
 
 /*
@@ -8277,46 +8253,38 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	    usize < SCHED_ATTR_SIZE_VER0 || flags)
 		return -EINVAL;
 
-	rcu_read_lock();
-	p = find_process_by_pid(pid);
-	retval = -ESRCH;
-	if (!p)
-		goto out_unlock;
+	scoped_guard (rcu) {
+		p = find_process_by_pid(pid);
+		if (!p)
+			return -ESRCH;
 
-	retval = security_task_getscheduler(p);
-	if (retval)
-		goto out_unlock;
+		retval = security_task_getscheduler(p);
+		if (retval)
+			return retval;
 
-	kattr.sched_policy = p->policy;
-	if (p->sched_reset_on_fork)
-		kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-	get_params(p, &kattr);
-	kattr.sched_flags &= SCHED_FLAG_ALL;
+		kattr.sched_policy = p->policy;
+		if (p->sched_reset_on_fork)
+			kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+		get_params(p, &kattr);
+		kattr.sched_flags &= SCHED_FLAG_ALL;
 
 #ifdef CONFIG_UCLAMP_TASK
-	/*
-	 * This could race with another potential updater, but this is fine
-	 * because it'll correctly read the old or the new value. We don't need
-	 * to guarantee who wins the race as long as it doesn't return garbage.
-	 */
-	kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
-	kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+		/*
+		 * This could race with another potential updater, but this is fine
+		 * because it'll correctly read the old or the new value. We don't need
+		 * to guarantee who wins the race as long as it doesn't return garbage.
+		 */
+		kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+		kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
 #endif
-
-	rcu_read_unlock();
+	}
 
 	return sched_attr_copy_to_user(uattr, &kattr, usize);
-
-out_unlock:
-	rcu_read_unlock();
-	return retval;
 }
 
 #ifdef CONFIG_SMP
 int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 {
-	int ret = 0;
-
 	/*
 	 * If the task isn't a deadline task or admission control is
 	 * disabled then we don't care about affinity changes.
@@ -8330,11 +8298,11 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 	 * tasks allowed to run on all the CPUs in the task's
 	 * root_domain.
 	 */
-	rcu_read_lock();
+	guard(rcu)();
 	if (!cpumask_subset(task_rq(p)->rd->span, mask))
-		ret = -EBUSY;
-	rcu_read_unlock();
-	return ret;
+		return -EBUSY;
+
+	return 0;
 }
 #endif
 
@@ -8404,39 +8372,24 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 {
 	struct affinity_context ac;
 	struct cpumask *user_mask;
-	struct task_struct *p;
 	int retval;
 
-	rcu_read_lock();
-
-	p = find_process_by_pid(pid);
-	if (!p) {
-		rcu_read_unlock();
+	CLASS(find_get_task, p)(pid);
+	if (!p)
 		return -ESRCH;
-	}
-
-	/* Prevent p going away */
-	get_task_struct(p);
-	rcu_read_unlock();
 
-	if (p->flags & PF_NO_SETAFFINITY) {
-		retval = -EINVAL;
-		goto out_put_task;
-	}
+	if (p->flags & PF_NO_SETAFFINITY)
+		return -EINVAL;
 
 	if (!check_same_owner(p)) {
-		rcu_read_lock();
-		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {
-			rcu_read_unlock();
-			retval = -EPERM;
-			goto out_put_task;
-		}
-		rcu_read_unlock();
+		guard(rcu)();
+		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
+			return -EPERM;
 	}
 
 	retval = security_task_setscheduler(p);
 	if (retval)
-		goto out_put_task;
+		return retval;
 
 	/*
 	 * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
@@ -8446,8 +8399,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	if (user_mask) {
 		cpumask_copy(user_mask, in_mask);
 	} else if (IS_ENABLED(CONFIG_SMP)) {
-		retval = -ENOMEM;
-		goto out_put_task;
+		return -ENOMEM;
 	}
 
 	ac = (struct affinity_context){
@@ -8459,8 +8411,6 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	retval = __sched_setaffinity(p, &ac);
 	kfree(ac.user_mask);
 
-out_put_task:
-	put_task_struct(p);
 	return retval;
 }
 
@@ -8502,28 +8452,21 @@ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
 long sched_getaffinity(pid_t pid, struct cpumask *mask)
 {
 	struct task_struct *p;
-	unsigned long flags;
 	int retval;
 
-	rcu_read_lock();
-
-	retval = -ESRCH;
+	guard(rcu)();
 	p = find_process_by_pid(pid);
 	if (!p)
-		goto out_unlock;
+		return -ESRCH;
 
 	retval = security_task_getscheduler(p);
 	if (retval)
-		goto out_unlock;
+		return retval;
 
-	raw_spin_lock_irqsave(&p->pi_lock, flags);
+	guard(raw_spinlock_irqsave)(&p->pi_lock);
 	cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
-	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
-out_unlock:
-	rcu_read_unlock();
-
-	return retval;
+	return 0;
 }
 
 /**
@@ -8970,55 +8913,46 @@ int __sched yield_to(struct task_struct *p, bool preempt)
 {
 	struct task_struct *curr = current;
 	struct rq *rq, *p_rq;
-	unsigned long flags;
 	int yielded = 0;
 
-	local_irq_save(flags);
-	rq = this_rq();
+	scoped_guard (irqsave) {
+		rq = this_rq();
 
 again:
-	p_rq = task_rq(p);
-	/*
-	 * If we're the only runnable task on the rq and target rq also
-	 * has only one task, there's absolutely no point in yielding.
-	 */
-	if (rq->nr_running == 1 && p_rq->nr_running == 1) {
-		yielded = -ESRCH;
-		goto out_irq;
-	}
+		p_rq = task_rq(p);
+		/*
+		 * If we're the only runnable task on the rq and target rq also
+		 * has only one task, there's absolutely no point in yielding.
+		 */
+		if (rq->nr_running == 1 && p_rq->nr_running == 1)
+			return -ESRCH;
 
-	double_rq_lock(rq, p_rq);
-	if (task_rq(p) != p_rq) {
-		double_rq_unlock(rq, p_rq);
-		goto again;
-	}
+		guard(double_rq_lock)(rq, p_rq);
+		if (task_rq(p) != p_rq)
+			goto again;
 
-	if (!curr->sched_class->yield_to_task)
-		goto out_unlock;
+		if (!curr->sched_class->yield_to_task)
+			return 0;
 
-	if (curr->sched_class != p->sched_class)
-		goto out_unlock;
+		if (curr->sched_class != p->sched_class)
+			return 0;
 
-	if (task_on_cpu(p_rq, p) || !task_is_running(p))
-		goto out_unlock;
+		if (task_on_cpu(p_rq, p) || !task_is_running(p))
+			return 0;
 
-	yielded = curr->sched_class->yield_to_task(rq, p);
-	if (yielded) {
-		schedstat_inc(rq->yld_count);
-		/*
-		 * Make p's CPU reschedule; pick_next_entity takes care of
-		 * fairness.
-		 */
-		if (preempt && rq != p_rq)
-			resched_curr(p_rq);
+		yielded = curr->sched_class->yield_to_task(rq, p);
+		if (yielded) {
+			schedstat_inc(rq->yld_count);
+			/*
+			 * Make p's CPU reschedule; pick_next_entity
+			 * takes care of fairness.
+			 */
+			if (preempt && rq != p_rq)
+				resched_curr(p_rq);
+		}
 	}
 
-out_unlock:
-	double_rq_unlock(rq, p_rq);
-out_irq:
-	local_irq_restore(flags);
-
-	if (yielded > 0)
+	if (yielded)
 		schedule();
 
 	return yielded;
@@ -9121,38 +9055,30 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
 
 static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
 {
-	struct task_struct *p;
-	unsigned int time_slice;
-	struct rq_flags rf;
-	struct rq *rq;
+	unsigned int time_slice = 0;
 	int retval;
 
 	if (pid < 0)
 		return -EINVAL;
 
-	retval = -ESRCH;
-	rcu_read_lock();
-	p = find_process_by_pid(pid);
-	if (!p)
-		goto out_unlock;
+	scoped_guard (rcu) {
+		struct task_struct *p = find_process_by_pid(pid);
+		if (!p)
+			return -ESRCH;
 
-	retval = security_task_getscheduler(p);
-	if (retval)
-		goto out_unlock;
+		retval = security_task_getscheduler(p);
+		if (retval)
+			return retval;
 
-	rq = task_rq_lock(p, &rf);
-	time_slice = 0;
-	if (p->sched_class->get_rr_interval)
-		time_slice = p->sched_class->get_rr_interval(rq, p);
-	task_rq_unlock(rq, p, &rf);
+		scoped_guard (task_rq_lock, p) {
+			struct rq *rq = scope.rq;
+			if (p->sched_class->get_rr_interval)
+				time_slice = p->sched_class->get_rr_interval(rq, p);
+		}
+	}
 
-	rcu_read_unlock();
 	jiffies_to_timespec64(time_slice, t);
 	return 0;
-
-out_unlock:
-	rcu_read_unlock();
-	return retval;
 }
 
 /**
@@ -9211,9 +9137,9 @@ void sched_show_task(struct task_struct *p)
 	if (pid_alive(p))
 		ppid = task_pid_nr(rcu_dereference(p->real_parent));
 	rcu_read_unlock();
-	pr_cont(" stack:%-5lu pid:%-5d ppid:%-6d flags:0x%08lx\n",
-		free, task_pid_nr(p), ppid,
-		read_task_thread_flags(p));
+	pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
+		free, task_pid_nr(p), task_tgid_nr(p),
+		ppid, read_task_thread_flags(p));
 
 	print_worker_info(KERN_INFO, p);
 	print_stop_info(KERN_INFO, p);
@@ -9543,9 +9469,11 @@ static void balance_push(struct rq *rq)
 	 * Temporarily drop rq->lock such that we can wake-up the stop task.
 	 * Both preemption and IRQs are still disabled.
 	 */
+	preempt_disable();
 	raw_spin_rq_unlock(rq);
 	stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
 			    this_cpu_ptr(&push_work));
+	preempt_enable();
 	/*
 	 * At this point need_resched() is true and we'll take the loop in
 	 * schedule(). The next pick is obviously going to be the stop task
@@ -10051,7 +9979,7 @@ void __init sched_init(void)
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
-		rq->cpu_capacity = rq->cpu_capacity_orig = SCHED_CAPACITY_SCALE;
+		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
 		rq->balance_callback = &balance_push_callback;
 		rq->active_balance = 0;
 		rq->next_balance = jiffies;
@@ -10060,8 +9988,6 @@ void __init sched_init(void)
 		rq->online = 0;
 		rq->idle_stamp = 0;
 		rq->avg_idle = 2*sysctl_sched_migration_cost;
-		rq->wake_stamp = jiffies;
-		rq->wake_avg_idle = rq->avg_idle;
 		rq->max_idle_balance_cost = sysctl_sched_migration_cost;
 
 		INIT_LIST_HEAD(&rq->cfs_tasks);
@@ -10536,17 +10462,18 @@ void sched_move_task(struct task_struct *tsk)
 	int queued, running, queue_flags =
 		DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
 	struct task_group *group;
-	struct rq_flags rf;
 	struct rq *rq;
 
-	rq = task_rq_lock(tsk, &rf);
+	CLASS(task_rq_lock, rq_guard)(tsk);
+	rq = rq_guard.rq;
+
 	/*
 	 * Esp. with SCHED_AUTOGROUP enabled it is possible to get superfluous
 	 * group changes.
 	 */
 	group = sched_get_task_group(tsk);
 	if (group == tsk->sched_task_group)
-		goto unlock;
+		return;
 
 	update_rq_clock(rq);
 
@@ -10571,9 +10498,6 @@ void sched_move_task(struct task_struct *tsk)
 		 */
 		resched_curr(rq);
 	}
-
-unlock:
-	task_rq_unlock(rq, tsk, &rf);
 }
 
 static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
@@ -10610,11 +10534,9 @@ static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
 
 #ifdef CONFIG_UCLAMP_TASK_GROUP
 	/* Propagate the effective uclamp value for the new group */
-	mutex_lock(&uclamp_mutex);
-	rcu_read_lock();
+	guard(mutex)(&uclamp_mutex);
+	guard(rcu)();
 	cpu_util_update_eff(css);
-	rcu_read_unlock();
-	mutex_unlock(&uclamp_mutex);
 #endif
 
 	return 0;
@@ -10765,8 +10687,8 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 
 	static_branch_enable(&sched_uclamp_used);
 
-	mutex_lock(&uclamp_mutex);
-	rcu_read_lock();
+	guard(mutex)(&uclamp_mutex);
+	guard(rcu)();
 
 	tg = css_tg(of_css(of));
 	if (tg->uclamp_req[clamp_id].value != req.util)
@@ -10781,9 +10703,6 @@ static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
 	/* Update effective clamps to track the most restrictive value */
 	cpu_util_update_eff(of_css(of));
 
-	rcu_read_unlock();
-	mutex_unlock(&uclamp_mutex);
-
 	return nbytes;
 }
 
@@ -10809,10 +10728,10 @@ static inline void cpu_uclamp_print(struct seq_file *sf,
 	u64 percent;
 	u32 rem;
 
-	rcu_read_lock();
-	tg = css_tg(seq_css(sf));
-	util_clamp = tg->uclamp_req[clamp_id].value;
-	rcu_read_unlock();
+	scoped_guard (rcu) {
+		tg = css_tg(seq_css(sf));
+		util_clamp = tg->uclamp_req[clamp_id].value;
+	}
 
 	if (util_clamp == SCHED_CAPACITY_SCALE) {
 		seq_puts(sf, "max\n");
@@ -10903,11 +10822,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 	 * Prevent race between setting of cfs_rq->runtime_enabled and
 	 * unthrottle_offline_cfs_rqs().
 	 */
-	cpus_read_lock();
-	mutex_lock(&cfs_constraints_mutex);
+	guard(cpus_read_lock)();
+	guard(mutex)(&cfs_constraints_mutex);
+
 	ret = __cfs_schedulable(tg, period, quota);
 	if (ret)
-		goto out_unlock;
+		return ret;
 
 	runtime_enabled = quota != RUNTIME_INF;
 	runtime_was_enabled = cfs_b->quota != RUNTIME_INF;
@@ -10917,39 +10837,38 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota,
 	 */
 	if (runtime_enabled && !runtime_was_enabled)
 		cfs_bandwidth_usage_inc();
-	raw_spin_lock_irq(&cfs_b->lock);
-	cfs_b->period = ns_to_ktime(period);
-	cfs_b->quota = quota;
-	cfs_b->burst = burst;
 
-	__refill_cfs_bandwidth_runtime(cfs_b);
+	scoped_guard (raw_spinlock_irq, &cfs_b->lock) {
+		cfs_b->period = ns_to_ktime(period);
+		cfs_b->quota = quota;
+		cfs_b->burst = burst;
 
-	/* Restart the period timer (if active) to handle new period expiry: */
-	if (runtime_enabled)
-		start_cfs_bandwidth(cfs_b);
+		__refill_cfs_bandwidth_runtime(cfs_b);
 
-	raw_spin_unlock_irq(&cfs_b->lock);
+		/*
+		 * Restart the period timer (if active) to handle new
+		 * period expiry:
+		 */
+		if (runtime_enabled)
+			start_cfs_bandwidth(cfs_b);
+	}
 
 	for_each_online_cpu(i) {
 		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
 		struct rq *rq = cfs_rq->rq;
-		struct rq_flags rf;
 
-		rq_lock_irq(rq, &rf);
+		guard(rq_lock_irq)(rq);
 		cfs_rq->runtime_enabled = runtime_enabled;
 		cfs_rq->runtime_remaining = 0;
 
 		if (cfs_rq->throttled)
 			unthrottle_cfs_rq(cfs_rq);
-		rq_unlock_irq(rq, &rf);
 	}
+
 	if (runtime_was_enabled && !runtime_enabled)
 		cfs_bandwidth_usage_dec();
-out_unlock:
-	mutex_unlock(&cfs_constraints_mutex);
-	cpus_read_unlock();
 
-	return ret;
+	return 0;
 }
 
 static int tg_set_cfs_quota(struct task_group *tg, long cfs_quota_us)
@@ -11134,7 +11053,6 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data)
 
 static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
 {
-	int ret;
 	struct cfs_schedulable_data data = {
 		.tg = tg,
 		.period = period,
@@ -11146,11 +11064,8 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota)
 		do_div(data.quota, NSEC_PER_USEC);
 	}
 
-	rcu_read_lock();
-	ret = walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
-	rcu_read_unlock();
-
-	return ret;
+	guard(rcu)();
+	return walk_tg_tree(tg_cfs_schedulable_down, tg_nop, &data);
 }
 
 static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
@@ -11755,14 +11670,12 @@ int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
 	 * are not the last task to be migrated from this cpu for this mm, so
 	 * there is no need to move src_cid to the destination cpu.
 	 */
-	rcu_read_lock();
+	guard(rcu)();
 	src_task = rcu_dereference(src_rq->curr);
 	if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-		rcu_read_unlock();
 		t->last_mm_cid = -1;
 		return -1;
 	}
-	rcu_read_unlock();
 
 	return src_cid;
 }
@@ -11806,18 +11719,17 @@ int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
 	 * the lazy-put flag, this task will be responsible for transitioning
 	 * from lazy-put flag set to MM_CID_UNSET.
 	 */
-	rcu_read_lock();
-	src_task = rcu_dereference(src_rq->curr);
-	if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-		rcu_read_unlock();
-		/*
-		 * We observed an active task for this mm, there is therefore
-		 * no point in moving this cid to the destination cpu.
-		 */
-		t->last_mm_cid = -1;
-		return -1;
+	scoped_guard (rcu) {
+		src_task = rcu_dereference(src_rq->curr);
+		if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
+			/*
+			 * We observed an active task for this mm, there is therefore
+			 * no point in moving this cid to the destination cpu.
+			 */
+			t->last_mm_cid = -1;
+			return -1;
+		}
 	}
-	rcu_read_unlock();
 
 	/*
 	 * The src_cid is unused, so it can be unset.
@@ -11890,7 +11802,6 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_
 {
 	struct rq *rq = cpu_rq(cpu);
 	struct task_struct *t;
-	unsigned long flags;
 	int cid, lazy_cid;
 
 	cid = READ_ONCE(pcpu_cid->cid);
@@ -11925,23 +11836,21 @@ static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_
 	 * the lazy-put flag, that task will be responsible for transitioning
 	 * from lazy-put flag set to MM_CID_UNSET.
 	 */
-	rcu_read_lock();
-	t = rcu_dereference(rq->curr);
-	if (READ_ONCE(t->mm_cid_active) && t->mm == mm) {
-		rcu_read_unlock();
-		return;
+	scoped_guard (rcu) {
+		t = rcu_dereference(rq->curr);
+		if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
+			return;
 	}
-	rcu_read_unlock();
 
 	/*
 	 * The cid is unused, so it can be unset.
 	 * Disable interrupts to keep the window of cid ownership without rq
 	 * lock small.
 	 */
-	local_irq_save(flags);
-	if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
-		__mm_cid_put(mm, cid);
-	local_irq_restore(flags);
+	scoped_guard (irqsave) {
+		if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
+			__mm_cid_put(mm, cid);
+	}
 }
 
 static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
@@ -11963,14 +11872,13 @@ static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
 	 * snapshot associated with this cid if an active task using the mm is
 	 * observed on this rq.
 	 */
-	rcu_read_lock();
-	curr = rcu_dereference(rq->curr);
-	if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
-		WRITE_ONCE(pcpu_cid->time, rq_clock);
-		rcu_read_unlock();
-		return;
+	scoped_guard (rcu) {
+		curr = rcu_dereference(rq->curr);
+		if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
+			WRITE_ONCE(pcpu_cid->time, rq_clock);
+			return;
+		}
 	}
-	rcu_read_unlock();
 
 	if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
 		return;
@@ -12064,7 +11972,6 @@ void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
 void sched_mm_cid_exit_signals(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
-	struct rq_flags rf;
 	struct rq *rq;
 
 	if (!mm)
@@ -12072,7 +11979,7 @@ void sched_mm_cid_exit_signals(struct task_struct *t)
 
 	preempt_disable();
 	rq = this_rq();
-	rq_lock_irqsave(rq, &rf);
+	guard(rq_lock_irqsave)(rq);
 	preempt_enable_no_resched();	/* holding spinlock */
 	WRITE_ONCE(t->mm_cid_active, 0);
 	/*
@@ -12082,13 +11989,11 @@ void sched_mm_cid_exit_signals(struct task_struct *t)
 	smp_mb();
 	mm_cid_put(mm);
 	t->last_mm_cid = t->mm_cid = -1;
-	rq_unlock_irqrestore(rq, &rf);
 }
 
 void sched_mm_cid_before_execve(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
-	struct rq_flags rf;
 	struct rq *rq;
 
 	if (!mm)
@@ -12096,7 +12001,7 @@ void sched_mm_cid_before_execve(struct task_struct *t)
 
 	preempt_disable();
 	rq = this_rq();
-	rq_lock_irqsave(rq, &rf);
+	guard(rq_lock_irqsave)(rq);
 	preempt_enable_no_resched();	/* holding spinlock */
 	WRITE_ONCE(t->mm_cid_active, 0);
 	/*
@@ -12106,13 +12011,11 @@ void sched_mm_cid_before_execve(struct task_struct *t)
 	smp_mb();
 	mm_cid_put(mm);
 	t->last_mm_cid = t->mm_cid = -1;
-	rq_unlock_irqrestore(rq, &rf);
 }
 
 void sched_mm_cid_after_execve(struct task_struct *t)
 {
 	struct mm_struct *mm = t->mm;
-	struct rq_flags rf;
 	struct rq *rq;
 
 	if (!mm)
@@ -12120,16 +12023,16 @@ void sched_mm_cid_after_execve(struct task_struct *t)
 
 	preempt_disable();
 	rq = this_rq();
-	rq_lock_irqsave(rq, &rf);
-	preempt_enable_no_resched();	/* holding spinlock */
-	WRITE_ONCE(t->mm_cid_active, 1);
-	/*
-	 * Store t->mm_cid_active before loading per-mm/cpu cid.
-	 * Matches barrier in sched_mm_cid_remote_clear_old().
-	 */
-	smp_mb();
-	t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
-	rq_unlock_irqrestore(rq, &rf);
+	scoped_guard (rq_lock_irqsave, rq) {
+		preempt_enable_no_resched();	/* holding spinlock */
+		WRITE_ONCE(t->mm_cid_active, 1);
+		/*
+		 * Store t->mm_cid_active before loading per-mm/cpu cid.
+		 * Matches barrier in sched_mm_cid_remote_clear_old().
+		 */
+		smp_mb();
+		t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
+	}
 	rseq_set_notify_resume(t);
 }