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, 25 insertions, 70 deletions

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0597ba0f85ff..6aaf0a3d6081 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -16,7 +16,7 @@ struct rt_bandwidth def_rt_bandwidth;
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
  */
-unsigned int sysctl_sched_rt_period = 1000000;
+int sysctl_sched_rt_period = 1000000;
 
 /*
  * part of the period that we allow rt tasks to run in us.
@@ -34,9 +34,11 @@ static struct ctl_table sched_rt_sysctls[] = {
 	{
 		.procname       = "sched_rt_period_us",
 		.data           = &sysctl_sched_rt_period,
-		.maxlen         = sizeof(unsigned int),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = sched_rt_handler,
+		.extra1         = SYSCTL_ONE,
+		.extra2         = SYSCTL_INT_MAX,
 	},
 	{
 		.procname       = "sched_rt_runtime_us",
@@ -44,6 +46,8 @@ static struct ctl_table sched_rt_sysctls[] = {
 		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = sched_rt_handler,
+		.extra1         = SYSCTL_NEG_ONE,
+		.extra2         = (void *)&sysctl_sched_rt_period,
 	},
 	{
 		.procname       = "sched_rr_timeslice_ms",
@@ -143,7 +147,6 @@ void init_rt_rq(struct rt_rq *rt_rq)
 #if defined CONFIG_SMP
 	rt_rq->highest_prio.curr = MAX_RT_PRIO-1;
 	rt_rq->highest_prio.next = MAX_RT_PRIO-1;
-	rt_rq->rt_nr_migratory = 0;
 	rt_rq->overloaded = 0;
 	plist_head_init(&rt_rq->pushable_tasks);
 #endif /* CONFIG_SMP */
@@ -358,53 +361,6 @@ static inline void rt_clear_overload(struct rq *rq)
 	cpumask_clear_cpu(rq->cpu, rq->rd->rto_mask);
 }
 
-static void update_rt_migration(struct rt_rq *rt_rq)
-{
-	if (rt_rq->rt_nr_migratory && rt_rq->rt_nr_total > 1) {
-		if (!rt_rq->overloaded) {
-			rt_set_overload(rq_of_rt_rq(rt_rq));
-			rt_rq->overloaded = 1;
-		}
-	} else if (rt_rq->overloaded) {
-		rt_clear_overload(rq_of_rt_rq(rt_rq));
-		rt_rq->overloaded = 0;
-	}
-}
-
-static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-	struct task_struct *p;
-
-	if (!rt_entity_is_task(rt_se))
-		return;
-
-	p = rt_task_of(rt_se);
-	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
-	rt_rq->rt_nr_total++;
-	if (p->nr_cpus_allowed > 1)
-		rt_rq->rt_nr_migratory++;
-
-	update_rt_migration(rt_rq);
-}
-
-static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-	struct task_struct *p;
-
-	if (!rt_entity_is_task(rt_se))
-		return;
-
-	p = rt_task_of(rt_se);
-	rt_rq = &rq_of_rt_rq(rt_rq)->rt;
-
-	rt_rq->rt_nr_total--;
-	if (p->nr_cpus_allowed > 1)
-		rt_rq->rt_nr_migratory--;
-
-	update_rt_migration(rt_rq);
-}
-
 static inline int has_pushable_tasks(struct rq *rq)
 {
 	return !plist_head_empty(&rq->rt.pushable_tasks);
@@ -438,6 +394,11 @@ static void enqueue_pushable_task(struct rq *rq, struct task_struct *p)
 	/* Update the highest prio pushable task */
 	if (p->prio < rq->rt.highest_prio.next)
 		rq->rt.highest_prio.next = p->prio;
+
+	if (!rq->rt.overloaded) {
+		rt_set_overload(rq);
+		rq->rt.overloaded = 1;
+	}
 }
 
 static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
@@ -451,6 +412,11 @@ static void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 		rq->rt.highest_prio.next = p->prio;
 	} else {
 		rq->rt.highest_prio.next = MAX_RT_PRIO-1;
+
+		if (rq->rt.overloaded) {
+			rt_clear_overload(rq);
+			rq->rt.overloaded = 0;
+		}
 	}
 }
 
@@ -464,16 +430,6 @@ static inline void dequeue_pushable_task(struct rq *rq, struct task_struct *p)
 {
 }
 
-static inline
-void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-}
-
-static inline
-void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
-{
-}
-
 static inline void rt_queue_push_tasks(struct rq *rq)
 {
 }
@@ -515,7 +471,7 @@ static inline bool rt_task_fits_capacity(struct task_struct *p, int cpu)
 	min_cap = uclamp_eff_value(p, UCLAMP_MIN);
 	max_cap = uclamp_eff_value(p, UCLAMP_MAX);
 
-	cpu_cap = capacity_orig_of(cpu);
+	cpu_cap = arch_scale_cpu_capacity(cpu);
 
 	return cpu_cap >= min(min_cap, max_cap);
 }
@@ -953,7 +909,7 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 
 				/*
 				 * When we're idle and a woken (rt) task is
-				 * throttled check_preempt_curr() will set
+				 * throttled wakeup_preempt() will set
 				 * skip_update and the time between the wakeup
 				 * and this unthrottle will get accounted as
 				 * 'runtime'.
@@ -1281,7 +1237,6 @@ void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	rt_rq->rr_nr_running += rt_se_rr_nr_running(rt_se);
 
 	inc_rt_prio(rt_rq, prio);
-	inc_rt_migration(rt_se, rt_rq);
 	inc_rt_group(rt_se, rt_rq);
 }
 
@@ -1294,7 +1249,6 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq)
 	rt_rq->rr_nr_running -= rt_se_rr_nr_running(rt_se);
 
 	dec_rt_prio(rt_rq, rt_se_prio(rt_se));
-	dec_rt_migration(rt_se, rt_rq);
 	dec_rt_group(rt_se, rt_rq);
 }
 
@@ -1715,7 +1669,7 @@ static int balance_rt(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flags)
+static void wakeup_preempt_rt(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (p->prio < rq->curr->prio) {
 		resched_curr(rq);
@@ -2109,9 +2063,11 @@ retry:
 		 */
 		push_task = get_push_task(rq);
 		if (push_task) {
+			preempt_disable();
 			raw_spin_rq_unlock(rq);
 			stop_one_cpu_nowait(rq->cpu, push_cpu_stop,
 					    push_task, &rq->push_work);
+			preempt_enable();
 			raw_spin_rq_lock(rq);
 		}
 
@@ -2448,9 +2404,11 @@ skip:
 		double_unlock_balance(this_rq, src_rq);
 
 		if (push_task) {
+			preempt_disable();
 			raw_spin_rq_unlock(this_rq);
 			stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop,
 					    push_task, &src_rq->push_work);
+			preempt_enable();
 			raw_spin_rq_lock(this_rq);
 		}
 	}
@@ -2702,7 +2660,7 @@ DEFINE_SCHED_CLASS(rt) = {
 	.dequeue_task		= dequeue_task_rt,
 	.yield_task		= yield_task_rt,
 
-	.check_preempt_curr	= check_preempt_curr_rt,
+	.wakeup_preempt		= wakeup_preempt_rt,
 
 	.pick_next_task		= pick_next_task_rt,
 	.put_prev_task		= put_prev_task_rt,
@@ -2985,9 +2943,6 @@ static int sched_rt_global_constraints(void)
 #ifdef CONFIG_SYSCTL
 static int sched_rt_global_validate(void)
 {
-	if (sysctl_sched_rt_period <= 0)
-		return -EINVAL;
-
 	if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
 		((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
 		 ((u64)sysctl_sched_rt_runtime *
@@ -3018,7 +2973,7 @@ static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
 	old_period = sysctl_sched_rt_period;
 	old_runtime = sysctl_sched_rt_runtime;
 
-	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
 	if (!ret && write) {
 		ret = sched_rt_global_validate();