Merge branch 'sched-fixes-for-linus' of...

Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (21 commits)
  sched: Remove forced2_migrations stats
  sched: Fix memory leak in two error corner cases
  sched: Fix build warning in get_update_sysctl_factor()
  sched: Update normalized values on user updates via proc
  sched: Make tunable scaling style configurable
  sched: Fix missing sched tunable recalculation on cpu add/remove
  sched: Fix task priority bug
  sched: cgroup: Implement different treatment for idle shares
  sched: Remove unnecessary RCU exclusion
  sched: Discard some old bits
  sched: Clean up check_preempt_wakeup()
  sched: Move update_curr() in check_preempt_wakeup() to avoid redundant call
  sched: Sanitize fork() handling
  sched: Clean up ttwu() rq locking
  sched: Remove rq->clock coupling from set_task_cpu()
  sched: Consolidate select_task_rq() callers
  sched: Remove sysctl.sched_features
  sched: Protect sched_rr_get_param() access to task->sched_class
  sched: Protect task->cpus_allowed access in sched_getaffinity()
  sched: Fix balance vs hotplug race
  ...

Fixed up conflicts in kernel/sysctl.c (due to sysctl cleanup)

include/linux/cpumask.h

@@ -84,6 +84,7 @@ extern const struct cpumask *const cpu_active_mask;
 #define num_online_cpus()	cpumask_weight(cpu_online_mask)
 #define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)
+#define num_active_cpus()	cpumask_weight(cpu_active_mask)
 #define cpu_online(cpu)		cpumask_test_cpu((cpu), cpu_online_mask)
 #define cpu_possible(cpu)	cpumask_test_cpu((cpu), cpu_possible_mask)
 #define cpu_present(cpu)	cpumask_test_cpu((cpu), cpu_present_mask)
@@ -92,6 +93,7 @@ extern const struct cpumask *const cpu_active_mask;
 #define num_online_cpus()	1
 #define num_possible_cpus()	1
 #define num_present_cpus()	1
+#define num_active_cpus()	1
 #define cpu_online(cpu)		((cpu) == 0)
 #define cpu_possible(cpu)	((cpu) == 0)
 #define cpu_present(cpu)	((cpu) == 0)

include/linux/sched.h

@@ -1102,7 +1102,7 @@ struct sched_class {
 
 	void (*set_curr_task) (struct rq *rq);
 	void (*task_tick) (struct rq *rq, struct task_struct *p, int queued);
-	void (*task_new) (struct rq *rq, struct task_struct *p);
+	void (*task_fork) (struct task_struct *p);
 
 	void (*switched_from) (struct rq *this_rq, struct task_struct *task,
 			       int running);
@@ -1111,7 +1111,8 @@ struct sched_class {
 	void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
 			     int oldprio, int running);
 
-	unsigned int (*get_rr_interval) (struct task_struct *task);
+	unsigned int (*get_rr_interval) (struct rq *rq,
+					 struct task_struct *task);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	void (*moved_group) (struct task_struct *p);
@@ -1151,8 +1152,6 @@ struct sched_entity {
 	u64			start_runtime;
 	u64			avg_wakeup;
 
-	u64			avg_running;
-
 #ifdef CONFIG_SCHEDSTATS
 	u64			wait_start;
 	u64			wait_max;
@@ -1175,7 +1174,6 @@ struct sched_entity {
 	u64			nr_failed_migrations_running;
 	u64			nr_failed_migrations_hot;
 	u64			nr_forced_migrations;
-	u64			nr_forced2_migrations;
 
 	u64			nr_wakeups;
 	u64			nr_wakeups_sync;
@@ -1904,14 +1902,22 @@ extern unsigned int sysctl_sched_wakeup_granularity;
 extern unsigned int sysctl_sched_shares_ratelimit;
 extern unsigned int sysctl_sched_shares_thresh;
 extern unsigned int sysctl_sched_child_runs_first;
+
+enum sched_tunable_scaling {
+	SCHED_TUNABLESCALING_NONE,
+	SCHED_TUNABLESCALING_LOG,
+	SCHED_TUNABLESCALING_LINEAR,
+	SCHED_TUNABLESCALING_END,
+};
+extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
+
 #ifdef CONFIG_SCHED_DEBUG
-extern unsigned int sysctl_sched_features;
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
 extern unsigned int sysctl_sched_time_avg;
 extern unsigned int sysctl_timer_migration;
 
-int sched_nr_latency_handler(struct ctl_table *table, int write,
+int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
 		loff_t *ppos);
 #endif

kernel/cpu.c

@@ -212,6 +212,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
 					hcpu, -1, &nr_calls);
 	if (err == NOTIFY_BAD) {
+		set_cpu_active(cpu, true);
+
 		nr_calls--;
 		__raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
 					  hcpu, nr_calls, NULL);
@@ -223,11 +225,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
 	/* Ensure that we are not runnable on dying cpu */
 	cpumask_copy(old_allowed, &current->cpus_allowed);
-	set_cpus_allowed_ptr(current,
-			     cpumask_of(cpumask_any_but(cpu_online_mask, cpu)));
+	set_cpus_allowed_ptr(current, cpu_active_mask);
 
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
+		set_cpu_active(cpu, true);
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
 					    hcpu) == NOTIFY_BAD)
@@ -292,9 +294,6 @@ int __ref cpu_down(unsigned int cpu)
 
 	err = _cpu_down(cpu, 0);
 
-	if (cpu_online(cpu))
-		set_cpu_active(cpu, true);
-
 out:
 	cpu_maps_update_done();
 	stop_machine_destroy();
@@ -387,6 +386,15 @@ int disable_nonboot_cpus(void)
 	 * with the userspace trying to use the CPU hotplug at the same time
 	 */
 	cpumask_clear(frozen_cpus);
+
+	for_each_online_cpu(cpu) {
+		if (cpu == first_cpu)
+			continue;
+		set_cpu_active(cpu, false);
+	}
+
+	synchronize_sched();
+
 	printk("Disabling non-boot CPUs ...\n");
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)

kernel/cpuset.c

@@ -737,7 +737,7 @@ static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 }
 
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
 			struct sched_domain_attr **attributes)
 {
 	*domains = NULL;
@@ -872,7 +872,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 		if (retval < 0)
 			return retval;
 
-		if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask))
+		if (!cpumask_subset(trialcs->cpus_allowed, cpu_active_mask))
 			return -EINVAL;
 	}
 	retval = validate_change(cs, trialcs);
@@ -2010,7 +2010,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 		}
 
 		/* Continue past cpusets with all cpus, mems online */
-		if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) &&
+		if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) &&
 		    nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
 			continue;
 
@@ -2019,7 +2019,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 		/* Remove offline cpus and mems from this cpuset. */
 		mutex_lock(&callback_mutex);
 		cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
-			    cpu_online_mask);
+			    cpu_active_mask);
 		nodes_and(cp->mems_allowed, cp->mems_allowed,
 						node_states[N_HIGH_MEMORY]);
 		mutex_unlock(&callback_mutex);
@@ -2057,8 +2057,10 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 	switch (phase) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
 		break;
 
 	default:
@@ -2067,7 +2069,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 
 	cgroup_lock();
 	mutex_lock(&callback_mutex);
-	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	mutex_unlock(&callback_mutex);
 	scan_for_empty_cpusets(&top_cpuset);
 	ndoms = generate_sched_domains(&doms, &attr);
@@ -2114,7 +2116,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 
 void __init cpuset_init_smp(void)
 {
-	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+	cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
 	top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
 	hotcpu_notifier(cpuset_track_online_cpus, 0);

kernel/sched_debug.c

@@ -309,6 +309,12 @@ static void print_cpu(struct seq_file *m, int cpu)
 	print_rq(m, rq, cpu);
 }
 
+static const char *sched_tunable_scaling_names[] = {
+	"none",
+	"logaritmic",
+	"linear"
+};
+
 static int sched_debug_show(struct seq_file *m, void *v)
 {
 	u64 now = ktime_to_ns(ktime_get());
@@ -334,6 +340,10 @@ static int sched_debug_show(struct seq_file *m, void *v)
 #undef PN
 #undef P
 
+	SEQ_printf(m, "  .%-40s: %d (%s)\n", "sysctl_sched_tunable_scaling",
+		sysctl_sched_tunable_scaling,
+		sched_tunable_scaling_names[sysctl_sched_tunable_scaling]);
+
 	for_each_online_cpu(cpu)
 		print_cpu(m, cpu);
 
@@ -399,7 +409,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	PN(se.sum_exec_runtime);
 	PN(se.avg_overlap);
 	PN(se.avg_wakeup);
-	PN(se.avg_running);
 
 	nr_switches = p->nvcsw + p->nivcsw;
 
@@ -423,7 +432,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
 	P(se.nr_failed_migrations_running);
 	P(se.nr_failed_migrations_hot);
 	P(se.nr_forced_migrations);
-	P(se.nr_forced2_migrations);
 	P(se.nr_wakeups);
 	P(se.nr_wakeups_sync);
 	P(se.nr_wakeups_migrate);
@@ -499,7 +507,6 @@ void proc_sched_set_task(struct task_struct *p)
 	p->se.nr_failed_migrations_running	= 0;
 	p->se.nr_failed_migrations_hot		= 0;
 	p->se.nr_forced_migrations		= 0;
-	p->se.nr_forced2_migrations		= 0;
 	p->se.nr_wakeups			= 0;
 	p->se.nr_wakeups_sync			= 0;
 	p->se.nr_wakeups_migrate		= 0;

kernel/sched_fair.c

@@ -21,6 +21,7 @@
  */
 
 #include <linux/latencytop.h>
+#include <linux/sched.h>
 
 /*
  * Targeted preemption latency for CPU-bound tasks:
@@ -35,12 +36,26 @@
  *  run vmstat and monitor the context-switches (cs) field)
  */
 unsigned int sysctl_sched_latency = 5000000ULL;
+unsigned int normalized_sysctl_sched_latency = 5000000ULL;
+
+/*
+ * The initial- and re-scaling of tunables is configurable
+ * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
+ *
+ * Options are:
+ * SCHED_TUNABLESCALING_NONE - unscaled, always *1
+ * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
+ * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
+ */
+enum sched_tunable_scaling sysctl_sched_tunable_scaling
+	= SCHED_TUNABLESCALING_LOG;
 
 /*
  * Minimal preemption granularity for CPU-bound tasks:
  * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
 unsigned int sysctl_sched_min_granularity = 1000000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
@@ -70,6 +85,7 @@ unsigned int __read_mostly sysctl_sched_compat_yield;
  * have immediate wakeup/sleep latencies.
  */
 unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
+unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
 
 const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
 
@@ -383,11 +399,12 @@ static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
  */
 
 #ifdef CONFIG_SCHED_DEBUG
-int sched_nr_latency_handler(struct ctl_table *table, int write,
+int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp,
 		loff_t *ppos)
 {
 	int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	int factor = get_update_sysctl_factor();
 
 	if (ret || !write)
 		return ret;
@@ -395,6 +412,14 @@ int sched_nr_latency_handler(struct ctl_table *table, int write,
 	sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
 					sysctl_sched_min_granularity);
 
+#define WRT_SYSCTL(name) \
+	(normalized_sysctl_##name = sysctl_##name / (factor))
+	WRT_SYSCTL(sched_min_granularity);
+	WRT_SYSCTL(sched_latency);
+	WRT_SYSCTL(sched_wakeup_granularity);
+	WRT_SYSCTL(sched_shares_ratelimit);
+#undef WRT_SYSCTL
+
 	return 0;
 }
 #endif
@@ -1403,7 +1428,6 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 		new_cpu = prev_cpu;
 	}
 
-	rcu_read_lock();
 	for_each_domain(cpu, tmp) {
 		/*
 		 * If power savings logic is enabled for a domain, see if we
@@ -1484,10 +1508,8 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 			update_shares(tmp);
 	}
 
-	if (affine_sd && wake_affine(affine_sd, p, sync)) {
-		new_cpu = cpu;
-		goto out;
-	}
+	if (affine_sd && wake_affine(affine_sd, p, sync))
+		return cpu;
 
 	while (sd) {
 		int load_idx = sd->forkexec_idx;
@@ -1528,8 +1550,6 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag
 		/* while loop will break here if sd == NULL */
 	}
 
-out:
-	rcu_read_unlock();
 	return new_cpu;
 }
 #endif /* CONFIG_SMP */
@@ -1651,12 +1671,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	int sync = wake_flags & WF_SYNC;
 	int scale = cfs_rq->nr_running >= sched_nr_latency;
 
-	update_curr(cfs_rq);
-
-	if (unlikely(rt_prio(p->prio))) {
-		resched_task(curr);
-		return;
-	}
+	if (unlikely(rt_prio(p->prio)))
+		goto preempt;
 
 	if (unlikely(p->sched_class != &fair_sched_class))
 		return;
@@ -1682,35 +1698,29 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 		return;
 
 	/* Idle tasks are by definition preempted by everybody. */
-	if (unlikely(curr->policy == SCHED_IDLE)) {
-		resched_task(curr);
-		return;
-	}
+	if (unlikely(curr->policy == SCHED_IDLE))
+		goto preempt;
 
-	if ((sched_feat(WAKEUP_SYNC) && sync) ||
-	    (sched_feat(WAKEUP_OVERLAP) &&
-	     (se->avg_overlap < sysctl_sched_migration_cost &&
-	      pse->avg_overlap < sysctl_sched_migration_cost))) {
-		resched_task(curr);
-		return;
-	}
+	if (sched_feat(WAKEUP_SYNC) && sync)
+		goto preempt;
 
-	if (sched_feat(WAKEUP_RUNNING)) {
-		if (pse->avg_running < se->avg_running) {
-			set_next_buddy(pse);
-			resched_task(curr);
-			return;
-		}
-	}
+	if (sched_feat(WAKEUP_OVERLAP) &&
+			se->avg_overlap < sysctl_sched_migration_cost &&
+			pse->avg_overlap < sysctl_sched_migration_cost)
+		goto preempt;
 
 	if (!sched_feat(WAKEUP_PREEMPT))
 		return;
 
+	update_curr(cfs_rq);
 	find_matching_se(&se, &pse);
-
 	BUG_ON(!pse);
+	if (wakeup_preempt_entity(se, pse) == 1)
+		goto preempt;
 
-	if (wakeup_preempt_entity(se, pse) == 1) {
+	return;
+
+preempt:
 	resched_task(curr);
 	/*
 	 * Only set the backward buddy when the current task is still
@@ -1723,9 +1733,9 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
 	 */
 	if (unlikely(!se->on_rq || curr == rq->idle))
 		return;
+
 	if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
 		set_last_buddy(se);
-	}
 }
 
 static struct task_struct *pick_next_task_fair(struct rq *rq)
@@ -1905,6 +1915,17 @@ move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
 
 	return 0;
 }
+
+static void rq_online_fair(struct rq *rq)
+{
+	update_sysctl();
+}
+
+static void rq_offline_fair(struct rq *rq)
+{
+	update_sysctl();
+}
+
 #endif /* CONFIG_SMP */
 
 /*
@@ -1922,28 +1943,30 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 }
 
 /*
- * Share the fairness runtime between parent and child, thus the
- * total amount of pressure for CPU stays equal - new tasks
- * get a chance to run but frequent forkers are not allowed to
- * monopolize the CPU. Note: the parent runqueue is locked,
- * the child is not running yet.
+ * called on fork with the child task as argument from the parent's context
+ *  - child not yet on the tasklist
+ *  - preemption disabled
  */
-static void task_new_fair(struct rq *rq, struct task_struct *p)
+static void task_fork_fair(struct task_struct *p)
 {
-	struct cfs_rq *cfs_rq = task_cfs_rq(p);
+	struct cfs_rq *cfs_rq = task_cfs_rq(current);
 	struct sched_entity *se = &p->se, *curr = cfs_rq->curr;
 	int this_cpu = smp_processor_id();
+	struct rq *rq = this_rq();
+	unsigned long flags;
+
+	spin_lock_irqsave(&rq->lock, flags);
 
-	sched_info_queued(p);
+	if (unlikely(task_cpu(p) != this_cpu))
+		__set_task_cpu(p, this_cpu);
 
 	update_curr(cfs_rq);
+
 	if (curr)
 		se->vruntime = curr->vruntime;
 	place_entity(cfs_rq, se, 1);
 
-	/* 'curr' will be NULL if the child belongs to a different group */
-	if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
-			curr && entity_before(curr, se)) {
+	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
 		/*
 		 * Upon rescheduling, sched_class::put_prev_task() will place
 		 * 'current' within the tree based on its new key value.
@@ -1952,7 +1975,7 @@ static void task_new_fair(struct rq *rq, struct task_struct *p)
 		resched_task(rq->curr);
 	}
 
-	enqueue_task_fair(rq, p, 0);
+	spin_unlock_irqrestore(&rq->lock, flags);
 }
 
 /*
@@ -2014,21 +2037,17 @@ static void moved_group_fair(struct task_struct *p)
 }
 #endif
 
-unsigned int get_rr_interval_fair(struct task_struct *task)
+unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
 {
 	struct sched_entity *se = &task->se;
-	unsigned long flags;
-	struct rq *rq;
 	unsigned int rr_interval = 0;
 
 	/*
 	 * Time slice is 0 for SCHED_OTHER tasks that are on an otherwise
 	 * idle runqueue:
 	 */
-	rq = task_rq_lock(task, &flags);
 	if (rq->cfs.load.weight)
 		rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
-	task_rq_unlock(rq, &flags);
 
 	return rr_interval;
 }
@@ -2052,11 +2071,13 @@ static const struct sched_class fair_sched_class = {
 
 	.load_balance		= load_balance_fair,
 	.move_one_task		= move_one_task_fair,
+	.rq_online		= rq_online_fair,
+	.rq_offline		= rq_offline_fair,
 #endif
 
 	.set_curr_task          = set_curr_task_fair,
 	.task_tick		= task_tick_fair,
-	.task_new		= task_new_fair,
+	.task_fork		= task_fork_fair,
 
 	.prio_changed		= prio_changed_fair,
 	.switched_to		= switched_to_fair,

kernel/sched_features.h

@@ -53,11 +53,6 @@ SCHED_FEAT(WAKEUP_SYNC, 0)
  */
 SCHED_FEAT(WAKEUP_OVERLAP, 0)
 
-/*
- * Wakeup preemption towards tasks that run short
- */
-SCHED_FEAT(WAKEUP_RUNNING, 0)
-
 /*
  * Use the SYNC wakeup hint, pipes and the likes use this to indicate
  * the remote end is likely to consume the data we just wrote, and

kernel/sched_idletask.c

@@ -97,7 +97,7 @@ static void prio_changed_idle(struct rq *rq, struct task_struct *p,
 		check_preempt_curr(rq, p, 0);
 }
 
-unsigned int get_rr_interval_idle(struct task_struct *task)
+unsigned int get_rr_interval_idle(struct rq *rq, struct task_struct *task)
 {
 	return 0;
 }

kernel/sched_rt.c

@@ -1721,7 +1721,7 @@ static void set_curr_task_rt(struct rq *rq)
 	dequeue_pushable_task(rq, p);
 }
 
-unsigned int get_rr_interval_rt(struct task_struct *task)
+unsigned int get_rr_interval_rt(struct rq *rq, struct task_struct *task)
 {
 	/*
 	 * Time slice is 0 for SCHED_FIFO tasks

kernel/sysctl.c

@@ -244,6 +244,10 @@ static int min_sched_granularity_ns = 100000;		/* 100 usecs */
 static int max_sched_granularity_ns = NSEC_PER_SEC;	/* 1 second */
 static int min_wakeup_granularity_ns;			/* 0 usecs */
 static int max_wakeup_granularity_ns = NSEC_PER_SEC;	/* 1 second */
+static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE;
+static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1;
+static int min_sched_shares_ratelimit = 100000; /* 100 usec */
+static int max_sched_shares_ratelimit = NSEC_PER_SEC; /* 1 second */
 #endif
 
 static struct ctl_table kern_table[] = {
@@ -260,7 +264,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_sched_min_granularity,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= sched_nr_latency_handler,
+		.proc_handler	= sched_proc_update_handler,
 		.extra1		= &min_sched_granularity_ns,
 		.extra2		= &max_sched_granularity_ns,
 	},
@@ -269,7 +273,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_sched_latency,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= sched_nr_latency_handler,
+		.proc_handler	= sched_proc_update_handler,
 		.extra1		= &min_sched_granularity_ns,
 		.extra2		= &max_sched_granularity_ns,
 	},
@@ -278,7 +282,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_sched_wakeup_granularity,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= sched_proc_update_handler,
 		.extra1		= &min_wakeup_granularity_ns,
 		.extra2		= &max_wakeup_granularity_ns,
 	},
@@ -287,7 +291,18 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_sched_shares_ratelimit,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= sched_proc_update_handler,
+		.extra1		= &min_sched_shares_ratelimit,
+		.extra2		= &max_sched_shares_ratelimit,
+	},
+	{
+		.procname	= "sched_tunable_scaling",
+		.data		= &sysctl_sched_tunable_scaling,
+		.maxlen		= sizeof(enum sched_tunable_scaling),
+		.mode		= 0644,
+		.proc_handler	= sched_proc_update_handler,
+		.extra1		= &min_sched_tunable_scaling,
+		.extra2		= &max_sched_tunable_scaling,
 	},
 	{
 		.procname	= "sched_shares_thresh",
@@ -297,13 +312,6 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 	},
-	{
-		.procname	= "sched_features",
-		.data		= &sysctl_sched_features,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
 	{
 		.procname	= "sched_migration_cost",
 		.data		= &sysctl_sched_migration_cost,