Merge tag 'sysctl-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux

Pull sysctl updates from Luis Chamberlain:
 "For two kernel releases now kernel/sysctl.c has been being cleaned up
  slowly, since the tables were grossly long, sprinkled with tons of
  #ifdefs and all this caused merge conflicts with one susbystem or
  another.

  This tree was put together to help try to avoid conflicts with these
  cleanups going on different trees at time. So nothing exciting on this
  pull request, just cleanups.

  Thanks a lot to the Uniontech and Huawei folks for doing some of this
  nasty work"

* tag 'sysctl-5.19-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/mcgrof/linux: (28 commits)
  sched: Fix build warning without CONFIG_SYSCTL
  reboot: Fix build warning without CONFIG_SYSCTL
  kernel/kexec_core: move kexec_core sysctls into its own file
  sysctl: minor cleanup in new_dir()
  ftrace: fix building with SYSCTL=y but DYNAMIC_FTRACE=n
  fs/proc: Introduce list_for_each_table_entry for proc sysctl
  mm: fix unused variable kernel warning when SYSCTL=n
  latencytop: move sysctl to its own file
  ftrace: fix building with SYSCTL=n but DYNAMIC_FTRACE=y
  ftrace: Fix build warning
  ftrace: move sysctl_ftrace_enabled to ftrace.c
  kernel/do_mount_initrd: move real_root_dev sysctls to its own file
  kernel/delayacct: move delayacct sysctls to its own file
  kernel/acct: move acct sysctls to its own file
  kernel/panic: move panic sysctls to its own file
  kernel/lockdep: move lockdep sysctls to its own file
  mm: move page-writeback sysctls to their own file
  mm: move oom_kill sysctls to their own file
  kernel/reboot: move reboot sysctls to its own file
  sched: Move energy_aware sysctls to topology.c
  ...

6 files changed, 240 insertions, 59 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a247f8d9d417..696c6490bd5b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -148,12 +148,6 @@ const_debug unsigned int sysctl_sched_nr_migrate = 8;
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 #endif
 
-/*
- * period over which we measure -rt task CPU usage in us.
- * default: 1s
- */
-unsigned int sysctl_sched_rt_period = 1000000;
-
 __read_mostly int scheduler_running;
 
 #ifdef CONFIG_SCHED_CORE
@@ -448,13 +442,6 @@ sched_core_dequeue(struct rq *rq, struct task_struct *p, int flags) { }
 #endif /* CONFIG_SCHED_CORE */
 
 /*
- * part of the period that we allow rt tasks to run in us.
- * default: 0.95s
- */
-int sysctl_sched_rt_runtime = 950000;
-
-
-/*
  * Serialization rules:
  *
  * Lock order:
@@ -1322,10 +1309,10 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 static DEFINE_MUTEX(uclamp_mutex);
 
 /* Max allowed minimum utilization */
-unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
+static unsigned int __maybe_unused sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 
 /* Max allowed maximum utilization */
-unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
+static unsigned int __maybe_unused sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
 
 /*
  * By default RT tasks run at the maximum performance point/capacity of the
@@ -1342,7 +1329,7 @@ unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
  * This knob will not override the system default sched_util_clamp_min defined
  * above.
  */
-unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
+static unsigned int sysctl_sched_uclamp_util_min_rt_default = SCHED_CAPACITY_SCALE;
 
 /* All clamps are required to be less or equal than these values */
 static struct uclamp_se uclamp_default[UCLAMP_CNT];
@@ -1472,33 +1459,6 @@ static void uclamp_update_util_min_rt_default(struct task_struct *p)
 	task_rq_unlock(rq, p, &rf);
 }
 
-static void uclamp_sync_util_min_rt_default(void)
-{
-	struct task_struct *g, *p;
-
-	/*
-	 * copy_process()			sysctl_uclamp
-	 *					  uclamp_min_rt = X;
-	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
-	 *   // link thread			  smp_mb__after_spinlock()
-	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
-	 *   sched_post_fork()			  for_each_process_thread()
-	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
-	 *
-	 * Ensures that either sched_post_fork() will observe the new
-	 * uclamp_min_rt or for_each_process_thread() will observe the new
-	 * task.
-	 */
-	read_lock(&tasklist_lock);
-	smp_mb__after_spinlock();
-	read_unlock(&tasklist_lock);
-
-	rcu_read_lock();
-	for_each_process_thread(g, p)
-		uclamp_update_util_min_rt_default(p);
-	rcu_read_unlock();
-}
-
 static inline struct uclamp_se
 uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
 {
@@ -1778,6 +1738,11 @@ uclamp_update_active_tasks(struct cgroup_subsys_state *css)
 }
 
 static void cpu_util_update_eff(struct cgroup_subsys_state *css);
+#endif
+
+#ifdef CONFIG_SYSCTL
+#ifdef CONFIG_UCLAMP_TASK
+#ifdef CONFIG_UCLAMP_TASK_GROUP
 static void uclamp_update_root_tg(void)
 {
 	struct task_group *tg = &root_task_group;
@@ -1795,7 +1760,34 @@ static void uclamp_update_root_tg(void)
 static void uclamp_update_root_tg(void) { }
 #endif
 
-int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+static void uclamp_sync_util_min_rt_default(void)
+{
+	struct task_struct *g, *p;
+
+	/*
+	 * copy_process()			sysctl_uclamp
+	 *					  uclamp_min_rt = X;
+	 *   write_lock(&tasklist_lock)		  read_lock(&tasklist_lock)
+	 *   // link thread			  smp_mb__after_spinlock()
+	 *   write_unlock(&tasklist_lock)	  read_unlock(&tasklist_lock);
+	 *   sched_post_fork()			  for_each_process_thread()
+	 *     __uclamp_sync_rt()		    __uclamp_sync_rt()
+	 *
+	 * Ensures that either sched_post_fork() will observe the new
+	 * uclamp_min_rt or for_each_process_thread() will observe the new
+	 * task.
+	 */
+	read_lock(&tasklist_lock);
+	smp_mb__after_spinlock();
+	read_unlock(&tasklist_lock);
+
+	rcu_read_lock();
+	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,
 				void *buffer, size_t *lenp, loff_t *ppos)
 {
 	bool update_root_tg = false;
@@ -1859,6 +1851,8 @@ done:
 
 	return result;
 }
+#endif
+#endif
 
 static int uclamp_validate(struct task_struct *p,
 			   const struct sched_attr *attr)
@@ -4433,7 +4427,7 @@ out:
 __setup("schedstats=", setup_schedstats);
 
 #ifdef CONFIG_PROC_SYSCTL
-int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
+static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -4455,6 +4449,52 @@ int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
 #endif /* CONFIG_PROC_SYSCTL */
 #endif /* CONFIG_SCHEDSTATS */
 
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_core_sysctls[] = {
+#ifdef CONFIG_SCHEDSTATS
+	{
+		.procname       = "sched_schedstats",
+		.data           = NULL,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_schedstats,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+#endif /* CONFIG_SCHEDSTATS */
+#ifdef CONFIG_UCLAMP_TASK
+	{
+		.procname       = "sched_util_clamp_min",
+		.data           = &sysctl_sched_uclamp_util_min,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+	{
+		.procname       = "sched_util_clamp_max",
+		.data           = &sysctl_sched_uclamp_util_max,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+	{
+		.procname       = "sched_util_clamp_min_rt_default",
+		.data           = &sysctl_sched_uclamp_util_min_rt_default,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sysctl_sched_uclamp_handler,
+	},
+#endif /* CONFIG_UCLAMP_TASK */
+	{}
+};
+static int __init sched_core_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_core_sysctls);
+	return 0;
+}
+late_initcall(sched_core_sysctl_init);
+#endif /* CONFIG_SYSCTL */
+
 /*
  * fork()/clone()-time setup:
  */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 936817ae142f..b5152961b743 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,40 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 
+/*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting ridiculously long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+static unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+static unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_dl_sysctls[] = {
+	{
+		.procname       = "sched_deadline_period_max_us",
+		.data           = &sysctl_sched_dl_period_max,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{
+		.procname       = "sched_deadline_period_min_us",
+		.data           = &sysctl_sched_dl_period_min,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+	{}
+};
+
+static int __init sched_dl_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_dl_sysctls);
+	return 0;
+}
+late_initcall(sched_dl_sysctl_init);
+#endif
+
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
 	return container_of(dl_se, struct task_struct, dl);
@@ -2873,14 +2907,6 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 }
 
 /*
- * Default limits for DL period; on the top end we guard against small util
- * tasks still getting ridiculously long effective runtimes, on the bottom end we
- * guard against timer DoS.
- */
-unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
-unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
-
-/*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 906b2c7c48d1..8c5b74f66bd3 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -174,7 +174,37 @@ int __weak arch_asym_cpu_priority(int cpu)
  *
  * (default: 5 msec, units: microseconds)
  */
-unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
+static unsigned int sysctl_sched_cfs_bandwidth_slice		= 5000UL;
+#endif
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table sched_fair_sysctls[] = {
+	{
+		.procname       = "sched_child_runs_first",
+		.data           = &sysctl_sched_child_runs_first,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec,
+	},
+#ifdef CONFIG_CFS_BANDWIDTH
+	{
+		.procname       = "sched_cfs_bandwidth_slice_us",
+		.data           = &sysctl_sched_cfs_bandwidth_slice,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1         = SYSCTL_ONE,
+	},
+#endif
+	{}
+};
+
+static int __init sched_fair_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_fair_sysctls);
+	return 0;
+}
+late_initcall(sched_fair_sysctl_init);
 #endif
 
 static inline void update_load_add(struct load_weight *lw, unsigned long inc)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7891c0f0e1ff..8c9ed9664840 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -5,7 +5,6 @@
  */
 
 int sched_rr_timeslice = RR_TIMESLICE;
-int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 /* More than 4 hours if BW_SHIFT equals 20. */
 static const u64 max_rt_runtime = MAX_BW;
 
@@ -13,6 +12,57 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
 
 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;
+
+/*
+ * part of the period that we allow rt tasks to run in us.
+ * default: 0.95s
+ */
+int sysctl_sched_rt_runtime = 950000;
+
+#ifdef CONFIG_SYSCTL
+static int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+		size_t *lenp, loff_t *ppos);
+static struct ctl_table sched_rt_sysctls[] = {
+	{
+		.procname       = "sched_rt_period_us",
+		.data           = &sysctl_sched_rt_period,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sched_rt_handler,
+	},
+	{
+		.procname       = "sched_rt_runtime_us",
+		.data           = &sysctl_sched_rt_runtime,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = sched_rt_handler,
+	},
+	{
+		.procname       = "sched_rr_timeslice_ms",
+		.data           = &sysctl_sched_rr_timeslice,
+		.maxlen         = sizeof(int),
+		.mode           = 0644,
+		.proc_handler   = sched_rr_handler,
+	},
+	{}
+};
+
+static int __init sched_rt_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_rt_sysctls);
+	return 0;
+}
+late_initcall(sched_rt_sysctl_init);
+#endif
+
 static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer)
 {
 	struct rt_bandwidth *rt_b =
@@ -2862,6 +2912,7 @@ long sched_group_rt_period(struct task_group *tg)
 	return rt_period_us;
 }
 
+#ifdef CONFIG_SYSCTL
 static int sched_rt_global_constraints(void)
 {
 	int ret = 0;
@@ -2872,6 +2923,7 @@ static int sched_rt_global_constraints(void)
 
 	return ret;
 }
+#endif /* CONFIG_SYSCTL */
 
 int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 {
@@ -2883,6 +2935,8 @@ int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk)
 }
 
 #else /* !CONFIG_RT_GROUP_SCHED */
+
+#ifdef CONFIG_SYSCTL
 static int sched_rt_global_constraints(void)
 {
 	unsigned long flags;
@@ -2900,8 +2954,10 @@ static int sched_rt_global_constraints(void)
 
 	return 0;
 }
+#endif /* CONFIG_SYSCTL */
 #endif /* CONFIG_RT_GROUP_SCHED */
 
+#ifdef CONFIG_SYSCTL
 static int sched_rt_global_validate(void)
 {
 	if (sysctl_sched_rt_period <= 0)
@@ -2926,7 +2982,7 @@ static void sched_rt_do_global(void)
 	raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags);
 }
 
-int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rt_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int old_period, old_runtime;
@@ -2965,7 +3021,7 @@ undo:
 	return ret;
 }
 
-int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
+static int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
 		size_t *lenp, loff_t *ppos)
 {
 	int ret;
@@ -2986,6 +3042,7 @@ int sched_rr_handler(struct ctl_table *table, int write, void *buffer,
 
 	return ret;
 }
+#endif /* CONFIG_SYSCTL */
 
 #ifdef CONFIG_SCHED_DEBUG
 void print_rt_stats(struct seq_file *m, int cpu)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2ce18584dca3..01259611beb9 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -108,10 +108,17 @@ extern __read_mostly int scheduler_running;
 extern unsigned long calc_load_update;
 extern atomic_long_t calc_load_tasks;
 
+extern unsigned int sysctl_sched_child_runs_first;
+
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
 extern void call_trace_sched_update_nr_running(struct rq *rq, int count);
+
+extern unsigned int sysctl_sched_rt_period;
+extern int sysctl_sched_rt_runtime;
+extern int sched_rr_timeslice;
+
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 810750e62118..05b6c2ad90b9 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -206,7 +206,7 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent)
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 DEFINE_STATIC_KEY_FALSE(sched_energy_present);
-unsigned int sysctl_sched_energy_aware = 1;
+static unsigned int sysctl_sched_energy_aware = 1;
 DEFINE_MUTEX(sched_energy_mutex);
 bool sched_energy_update;
 
@@ -220,7 +220,7 @@ void rebuild_sched_domains_energy(void)
 }
 
 #ifdef CONFIG_PROC_SYSCTL
-int sched_energy_aware_handler(struct ctl_table *table, int write,
+static int sched_energy_aware_handler(struct ctl_table *table, int write,
 		void *buffer, size_t *lenp, loff_t *ppos)
 {
 	int ret, state;
@@ -237,6 +237,27 @@ int sched_energy_aware_handler(struct ctl_table *table, int write,
 
 	return ret;
 }
+
+static struct ctl_table sched_energy_aware_sysctls[] = {
+	{
+		.procname       = "sched_energy_aware",
+		.data           = &sysctl_sched_energy_aware,
+		.maxlen         = sizeof(unsigned int),
+		.mode           = 0644,
+		.proc_handler   = sched_energy_aware_handler,
+		.extra1         = SYSCTL_ZERO,
+		.extra2         = SYSCTL_ONE,
+	},
+	{}
+};
+
+static int __init sched_energy_aware_sysctl_init(void)
+{
+	register_sysctl_init("kernel", sched_energy_aware_sysctls);
+	return 0;
+}
+
+late_initcall(sched_energy_aware_sysctl_init);
 #endif
 
 static void free_pd(struct perf_domain *pd)