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

Pull scheduler updates from Ingo Molnar:

 - MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and
   Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann,
   Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers.

   As perf and the scheduler is getting bigger and more complex,
   document the status quo of current responsibilities and interests,
   and spread the review pain^H^H^H^H fun via an increase in the Cc:
   linecount generated by scripts/get_maintainer.pl. :-)

 - Add another series of patches that brings the -rt (PREEMPT_RT) tree
   closer to mainline: split the monolithic CONFIG_PREEMPT dependencies
   into a new CONFIG_PREEMPTION category that will allow the eventual
   introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches
   to go though.

 - Extend the CPU cgroup controller with uclamp.min and uclamp.max to
   allow the finer shaping of CPU bandwidth usage.

 - Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS).

 - Improve the behavior of high CPU count, high thread count
   applications running under cpu.cfs_quota_us constraints.

 - Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present.

 - Improve CPU isolation housekeeping CPU allocation NUMA locality.

 - Fix deadline scheduler bandwidth calculations and logic when cpusets
   rebuilds the topology, or when it gets deadline-throttled while it's
   being offlined.

 - Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from
   setscheduler() system calls without creating global serialization.
   Add new synchronization between cpuset topology-changing events and
   the deadline acceptance tests in setscheduler(), which were broken
   before.

 - Rework the active_mm state machine to be less confusing and more
   optimal.

 - Rework (simplify) the pick_next_task() slowpath.

 - Improve load-balancing on AMD EPYC systems.

 - ... and misc cleanups, smaller fixes and improvements - please see
   the Git log for more details.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits)
  sched/psi: Correct overly pessimistic size calculation
  sched/fair: Speed-up energy-aware wake-ups
  sched/uclamp: Always use 'enum uclamp_id' for clamp_id values
  sched/uclamp: Update CPU's refcount on TG's clamp changes
  sched/uclamp: Use TG's clamps to restrict TASK's clamps
  sched/uclamp: Propagate system defaults to the root group
  sched/uclamp: Propagate parent clamps
  sched/uclamp: Extend CPU's cgroup controller
  sched/topology: Improve load balancing on AMD EPYC systems
  arch, ia64: Make NUMA select SMP
  sched, perf: MAINTAINERS update, add submaintainers and reviewers
  sched/fair: Use rq_lock/unlock in online_fair_sched_group
  cpufreq: schedutil: fix equation in comment
  sched: Rework pick_next_task() slow-path
  sched: Allow put_prev_task() to drop rq->lock
  sched/fair: Expose newidle_balance()
  sched: Add task_struct pointer to sched_class::set_curr_task
  sched: Rework CPU hotplug task selection
  sched/{rt,deadline}: Fix set_next_task vs pick_next_task
  sched: Fix kerneldoc comment for ia64_set_curr_task
  ...

1 files changed, 461 insertions, 100 deletions

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7fa8e74ad2ab..06961b997ed6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -773,6 +773,18 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 }
 
 #ifdef CONFIG_UCLAMP_TASK
+/*
+ * Serializes updates of utilization clamp values
+ *
+ * The (slow-path) user-space triggers utilization clamp value updates which
+ * can require updates on (fast-path) scheduler's data structures used to
+ * support enqueue/dequeue operations.
+ * While the per-CPU rq lock protects fast-path update operations, user-space
+ * requests are serialized using a mutex to reduce the risk of conflicting
+ * updates or API abuses.
+ */
+static DEFINE_MUTEX(uclamp_mutex);
+
 /* Max allowed minimum utilization */
 unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
 
@@ -798,7 +810,7 @@ static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value)
 	return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value);
 }
 
-static inline unsigned int uclamp_none(int clamp_id)
+static inline enum uclamp_id uclamp_none(enum uclamp_id clamp_id)
 {
 	if (clamp_id == UCLAMP_MIN)
 		return 0;
@@ -814,7 +826,7 @@ static inline void uclamp_se_set(struct uclamp_se *uc_se,
 }
 
 static inline unsigned int
-uclamp_idle_value(struct rq *rq, unsigned int clamp_id,
+uclamp_idle_value(struct rq *rq, enum uclamp_id clamp_id,
 		  unsigned int clamp_value)
 {
 	/*
@@ -830,7 +842,7 @@ uclamp_idle_value(struct rq *rq, unsigned int clamp_id,
 	return uclamp_none(UCLAMP_MIN);
 }
 
-static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id,
+static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
 				     unsigned int clamp_value)
 {
 	/* Reset max-clamp retention only on idle exit */
@@ -841,8 +853,8 @@ static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id,
 }
 
 static inline
-unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
-				 unsigned int clamp_value)
+enum uclamp_id uclamp_rq_max_value(struct rq *rq, enum uclamp_id clamp_id,
+				   unsigned int clamp_value)
 {
 	struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
 	int bucket_id = UCLAMP_BUCKETS - 1;
@@ -861,16 +873,42 @@ unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
 	return uclamp_idle_value(rq, clamp_id, clamp_value);
 }
 
+static inline struct uclamp_se
+uclamp_tg_restrict(struct task_struct *p, enum uclamp_id clamp_id)
+{
+	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+	struct uclamp_se uc_max;
+
+	/*
+	 * Tasks in autogroups or root task group will be
+	 * restricted by system defaults.
+	 */
+	if (task_group_is_autogroup(task_group(p)))
+		return uc_req;
+	if (task_group(p) == &root_task_group)
+		return uc_req;
+
+	uc_max = task_group(p)->uclamp[clamp_id];
+	if (uc_req.value > uc_max.value || !uc_req.user_defined)
+		return uc_max;
+#endif
+
+	return uc_req;
+}
+
 /*
  * The effective clamp bucket index of a task depends on, by increasing
  * priority:
  * - the task specific clamp value, when explicitly requested from userspace
+ * - the task group effective clamp value, for tasks not either in the root
+ *   group or in an autogroup
  * - the system default clamp value, defined by the sysadmin
  */
 static inline struct uclamp_se
-uclamp_eff_get(struct task_struct *p, unsigned int clamp_id)
+uclamp_eff_get(struct task_struct *p, enum uclamp_id clamp_id)
 {
-	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+	struct uclamp_se uc_req = uclamp_tg_restrict(p, clamp_id);
 	struct uclamp_se uc_max = uclamp_default[clamp_id];
 
 	/* System default restrictions always apply */
@@ -880,7 +918,7 @@ uclamp_eff_get(struct task_struct *p, unsigned int clamp_id)
 	return uc_req;
 }
 
-unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id)
+enum uclamp_id uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id)
 {
 	struct uclamp_se uc_eff;
 
@@ -904,7 +942,7 @@ unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id)
  * for each bucket when all its RUNNABLE tasks require the same clamp.
  */
 static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
-				    unsigned int clamp_id)
+				    enum uclamp_id clamp_id)
 {
 	struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
 	struct uclamp_se *uc_se = &p->uclamp[clamp_id];
@@ -942,7 +980,7 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
  * enforce the expected state and warn.
  */
 static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
-				    unsigned int clamp_id)
+				    enum uclamp_id clamp_id)
 {
 	struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
 	struct uclamp_se *uc_se = &p->uclamp[clamp_id];
@@ -981,7 +1019,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
 
 static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 {
-	unsigned int clamp_id;
+	enum uclamp_id clamp_id;
 
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
@@ -996,7 +1034,7 @@ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
 
 static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 {
-	unsigned int clamp_id;
+	enum uclamp_id clamp_id;
 
 	if (unlikely(!p->sched_class->uclamp_enabled))
 		return;
@@ -1005,15 +1043,82 @@ static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
 		uclamp_rq_dec_id(rq, p, clamp_id);
 }
 
+static inline void
+uclamp_update_active(struct task_struct *p, enum uclamp_id clamp_id)
+{
+	struct rq_flags rf;
+	struct rq *rq;
+
+	/*
+	 * Lock the task and the rq where the task is (or was) queued.
+	 *
+	 * We might lock the (previous) rq of a !RUNNABLE task, but that's the
+	 * price to pay to safely serialize util_{min,max} updates with
+	 * enqueues, dequeues and migration operations.
+	 * This is the same locking schema used by __set_cpus_allowed_ptr().
+	 */
+	rq = task_rq_lock(p, &rf);
+
+	/*
+	 * Setting the clamp bucket is serialized by task_rq_lock().
+	 * If the task is not yet RUNNABLE and its task_struct is not
+	 * affecting a valid clamp bucket, the next time it's enqueued,
+	 * it will already see the updated clamp bucket value.
+	 */
+	if (!p->uclamp[clamp_id].active) {
+		uclamp_rq_dec_id(rq, p, clamp_id);
+		uclamp_rq_inc_id(rq, p, clamp_id);
+	}
+
+	task_rq_unlock(rq, p, &rf);
+}
+
+static inline void
+uclamp_update_active_tasks(struct cgroup_subsys_state *css,
+			   unsigned int clamps)
+{
+	enum uclamp_id clamp_id;
+	struct css_task_iter it;
+	struct task_struct *p;
+
+	css_task_iter_start(css, 0, &it);
+	while ((p = css_task_iter_next(&it))) {
+		for_each_clamp_id(clamp_id) {
+			if ((0x1 << clamp_id) & clamps)
+				uclamp_update_active(p, clamp_id);
+		}
+	}
+	css_task_iter_end(&it);
+}
+
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+static void cpu_util_update_eff(struct cgroup_subsys_state *css);
+static void uclamp_update_root_tg(void)
+{
+	struct task_group *tg = &root_task_group;
+
+	uclamp_se_set(&tg->uclamp_req[UCLAMP_MIN],
+		      sysctl_sched_uclamp_util_min, false);
+	uclamp_se_set(&tg->uclamp_req[UCLAMP_MAX],
+		      sysctl_sched_uclamp_util_max, false);
+
+	rcu_read_lock();
+	cpu_util_update_eff(&root_task_group.css);
+	rcu_read_unlock();
+}
+#else
+static void uclamp_update_root_tg(void) { }
+#endif
+
 int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp,
 				loff_t *ppos)
 {
+	bool update_root_tg = false;
 	int old_min, old_max;
-	static DEFINE_MUTEX(mutex);
 	int result;
 
-	mutex_lock(&mutex);
+	mutex_lock(&uclamp_mutex);
 	old_min = sysctl_sched_uclamp_util_min;
 	old_max = sysctl_sched_uclamp_util_max;
 
@@ -1032,23 +1137,30 @@ int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
 	if (old_min != sysctl_sched_uclamp_util_min) {
 		uclamp_se_set(&uclamp_default[UCLAMP_MIN],
 			      sysctl_sched_uclamp_util_min, false);
+		update_root_tg = true;
 	}
 	if (old_max != sysctl_sched_uclamp_util_max) {
 		uclamp_se_set(&uclamp_default[UCLAMP_MAX],
 			      sysctl_sched_uclamp_util_max, false);
+		update_root_tg = true;
 	}
 
+	if (update_root_tg)
+		uclamp_update_root_tg();
+
 	/*
-	 * Updating all the RUNNABLE task is expensive, keep it simple and do
-	 * just a lazy update at each next enqueue time.
+	 * We update all RUNNABLE tasks only when task groups are in use.
+	 * Otherwise, keep it simple and do just a lazy update at each next
+	 * task enqueue time.
 	 */
+
 	goto done;
 
 undo:
 	sysctl_sched_uclamp_util_min = old_min;
 	sysctl_sched_uclamp_util_max = old_max;
 done:
-	mutex_unlock(&mutex);
+	mutex_unlock(&uclamp_mutex);
 
 	return result;
 }
@@ -1075,7 +1187,7 @@ static int uclamp_validate(struct task_struct *p,
 static void __setscheduler_uclamp(struct task_struct *p,
 				  const struct sched_attr *attr)
 {
-	unsigned int clamp_id;
+	enum uclamp_id clamp_id;
 
 	/*
 	 * On scheduling class change, reset to default clamps for tasks
@@ -1112,7 +1224,7 @@ static void __setscheduler_uclamp(struct task_struct *p,
 
 static void uclamp_fork(struct task_struct *p)
 {
-	unsigned int clamp_id;
+	enum uclamp_id clamp_id;
 
 	for_each_clamp_id(clamp_id)
 		p->uclamp[clamp_id].active = false;
@@ -1134,9 +1246,11 @@ static void uclamp_fork(struct task_struct *p)
 static void __init init_uclamp(void)
 {
 	struct uclamp_se uc_max = {};
-	unsigned int clamp_id;
+	enum uclamp_id clamp_id;
 	int cpu;
 
+	mutex_init(&uclamp_mutex);
+
 	for_each_possible_cpu(cpu) {
 		memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq));
 		cpu_rq(cpu)->uclamp_flags = 0;
@@ -1149,8 +1263,13 @@ static void __init init_uclamp(void)
 
 	/* System defaults allow max clamp values for both indexes */
 	uclamp_se_set(&uc_max, uclamp_none(UCLAMP_MAX), false);
-	for_each_clamp_id(clamp_id)
+	for_each_clamp_id(clamp_id) {
 		uclamp_default[clamp_id] = uc_max;
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+		root_task_group.uclamp_req[clamp_id] = uc_max;
+		root_task_group.uclamp[clamp_id] = uc_max;
+#endif
+	}
 }
 
 #else /* CONFIG_UCLAMP_TASK */
@@ -1494,7 +1613,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 	if (running)
-		set_curr_task(rq, p);
+		set_next_task(rq, p);
 }
 
 /*
@@ -3214,12 +3333,8 @@ static __always_inline struct rq *
 context_switch(struct rq *rq, struct task_struct *prev,
 	       struct task_struct *next, struct rq_flags *rf)
 {
-	struct mm_struct *mm, *oldmm;
-
 	prepare_task_switch(rq, prev, next);
 
-	mm = next->mm;
-	oldmm = prev->active_mm;
 	/*
 	 * For paravirt, this is coupled with an exit in switch_to to
 	 * combine the page table reload and the switch backend into
@@ -3228,22 +3343,37 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	arch_start_context_switch(prev);
 
 	/*
-	 * If mm is non-NULL, we pass through switch_mm(). If mm is
-	 * NULL, we will pass through mmdrop() in finish_task_switch().
-	 * Both of these contain the full memory barrier required by
-	 * membarrier after storing to rq->curr, before returning to
-	 * user-space.
+	 * kernel -> kernel   lazy + transfer active
+	 *   user -> kernel   lazy + mmgrab() active
+	 *
+	 * kernel ->   user   switch + mmdrop() active
+	 *   user ->   user   switch
 	 */
-	if (!mm) {
-		next->active_mm = oldmm;
-		mmgrab(oldmm);
-		enter_lazy_tlb(oldmm, next);
-	} else
-		switch_mm_irqs_off(oldmm, mm, next);
+	if (!next->mm) {                                // to kernel
+		enter_lazy_tlb(prev->active_mm, next);
+
+		next->active_mm = prev->active_mm;
+		if (prev->mm)                           // from user
+			mmgrab(prev->active_mm);
+		else
+			prev->active_mm = NULL;
+	} else {                                        // to user
+		/*
+		 * sys_membarrier() requires an smp_mb() between setting
+		 * rq->curr and returning to userspace.
+		 *
+		 * The below provides this either through switch_mm(), or in
+		 * case 'prev->active_mm == next->mm' through
+		 * finish_task_switch()'s mmdrop().
+		 */
+
+		switch_mm_irqs_off(prev->active_mm, next->mm, next);
 
-	if (!prev->mm) {
-		prev->active_mm = NULL;
-		rq->prev_mm = oldmm;
+		if (!prev->mm) {                        // from kernel
+			/* will mmdrop() in finish_task_switch(). */
+			rq->prev_mm = prev->active_mm;
+			prev->active_mm = NULL;
+		}
 	}
 
 	rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
@@ -3622,7 +3752,7 @@ static inline void sched_tick_start(int cpu) { }
 static inline void sched_tick_stop(int cpu) { }
 #endif
 
-#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
+#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
 				defined(CONFIG_TRACE_PREEMPT_TOGGLE))
 /*
  * If the value passed in is equal to the current preempt count
@@ -3780,7 +3910,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
-			goto again;
+			goto restart;
 
 		/* Assumes fair_sched_class->next == idle_sched_class */
 		if (unlikely(!p))
@@ -3789,14 +3919,19 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 		return p;
 	}
 
-again:
+restart:
+	/*
+	 * Ensure that we put DL/RT tasks before the pick loop, such that they
+	 * can PULL higher prio tasks when we lower the RQ 'priority'.
+	 */
+	prev->sched_class->put_prev_task(rq, prev, rf);
+	if (!rq->nr_running)
+		newidle_balance(rq, rf);
+
 	for_each_class(class) {
-		p = class->pick_next_task(rq, prev, rf);
-		if (p) {
-			if (unlikely(p == RETRY_TASK))
-				goto again;
+		p = class->pick_next_task(rq, NULL, NULL);
+		if (p)
 			return p;
-		}
 	}
 
 	/* The idle class should always have a runnable task: */
@@ -3823,7 +3958,7 @@ again:
  *      task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
  *      called on the nearest possible occasion:
  *
- *       - If the kernel is preemptible (CONFIG_PREEMPT=y):
+ *       - If the kernel is preemptible (CONFIG_PREEMPTION=y):
  *
  *         - in syscall or exception context, at the next outmost
  *           preempt_enable(). (this might be as soon as the wake_up()'s
@@ -3832,7 +3967,7 @@ again:
  *         - in IRQ context, return from interrupt-handler to
  *           preemptible context
  *
- *       - If the kernel is not preemptible (CONFIG_PREEMPT is not set)
+ *       - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
  *         then at the next:
  *
  *          - cond_resched() call
@@ -4077,7 +4212,7 @@ static void __sched notrace preempt_schedule_common(void)
 	} while (need_resched());
 }
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 /*
  * this is the entry point to schedule() from in-kernel preemption
  * off of preempt_enable. Kernel preemptions off return from interrupt
@@ -4149,7 +4284,7 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
 }
 EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
 
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 /*
  * this is the entry point to schedule() from kernel preemption
@@ -4317,7 +4452,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 	if (queued)
 		enqueue_task(rq, p, queue_flag);
 	if (running)
-		set_curr_task(rq, p);
+		set_next_task(rq, p);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 out_unlock:
@@ -4384,7 +4519,7 @@ void set_user_nice(struct task_struct *p, long nice)
 			resched_curr(rq);
 	}
 	if (running)
-		set_curr_task(rq, p);
+		set_next_task(rq, p);
 out_unlock:
 	task_rq_unlock(rq, p, &rf);
 }
@@ -4701,6 +4836,9 @@ recheck:
 			return retval;
 	}
 
+	if (pi)
+		cpuset_read_lock();
+
 	/*
 	 * Make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
@@ -4715,8 +4853,8 @@ recheck:
 	 * Changing the policy of the stop threads its a very bad idea:
 	 */
 	if (p == rq->stop) {
-		task_rq_unlock(rq, p, &rf);
-		return -EINVAL;
+		retval = -EINVAL;
+		goto unlock;
 	}
 
 	/*
@@ -4734,8 +4872,8 @@ recheck:
 			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
-		task_rq_unlock(rq, p, &rf);
-		return 0;
+		retval = 0;
+		goto unlock;
 	}
 change:
 
@@ -4748,8 +4886,8 @@ change:
 		if (rt_bandwidth_enabled() && rt_policy(policy) &&
 				task_group(p)->rt_bandwidth.rt_runtime == 0 &&
 				!task_group_is_autogroup(task_group(p))) {
-			task_rq_unlock(rq, p, &rf);
-			return -EPERM;
+			retval = -EPERM;
+			goto unlock;
 		}
 #endif
 #ifdef CONFIG_SMP
@@ -4764,8 +4902,8 @@ change:
 			 */
 			if (!cpumask_subset(span, p->cpus_ptr) ||
 			    rq->rd->dl_bw.bw == 0) {
-				task_rq_unlock(rq, p, &rf);
-				return -EPERM;
+				retval = -EPERM;
+				goto unlock;
 			}
 		}
 #endif
@@ -4775,6 +4913,8 @@ change:
 	if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
 		policy = oldpolicy = -1;
 		task_rq_unlock(rq, p, &rf);
+		if (pi)
+			cpuset_read_unlock();
 		goto recheck;
 	}
 
@@ -4784,8 +4924,8 @@ change:
 	 * is available.
 	 */
 	if ((dl_policy(policy) || dl_task(p)) && sched_dl_overflow(p, policy, attr)) {
-		task_rq_unlock(rq, p, &rf);
-		return -EBUSY;
+		retval = -EBUSY;
+		goto unlock;
 	}
 
 	p->sched_reset_on_fork = reset_on_fork;
@@ -4827,7 +4967,7 @@ change:
 		enqueue_task(rq, p, queue_flags);
 	}
 	if (running)
-		set_curr_task(rq, p);
+		set_next_task(rq, p);
 
 	check_class_changed(rq, p, prev_class, oldprio);
 
@@ -4835,14 +4975,22 @@ change:
 	preempt_disable();
 	task_rq_unlock(rq, p, &rf);
 
-	if (pi)
+	if (pi) {
+		cpuset_read_unlock();
 		rt_mutex_adjust_pi(p);
+	}
 
 	/* Run balance callbacks after we've adjusted the PI chain: */
 	balance_callback(rq);
 	preempt_enable();
 
 	return 0;
+
+unlock:
+	task_rq_unlock(rq, p, &rf);
+	if (pi)
+		cpuset_read_unlock();
+	return retval;
 }
 
 static int _sched_setscheduler(struct task_struct *p, int policy,
@@ -4926,10 +5074,15 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
 	rcu_read_lock();
 	retval = -ESRCH;
 	p = find_process_by_pid(pid);
-	if (p != NULL)
-		retval = sched_setscheduler(p, policy, &lparam);
+	if (likely(p))
+		get_task_struct(p);
 	rcu_read_unlock();
 
+	if (likely(p)) {
+		retval = sched_setscheduler(p, policy, &lparam);
+		put_task_struct(p);
+	}
+
 	return retval;
 }
 
@@ -5460,7 +5613,7 @@ SYSCALL_DEFINE0(sched_yield)
 	return 0;
 }
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 int __sched _cond_resched(void)
 {
 	if (should_resched(0)) {
@@ -5477,7 +5630,7 @@ EXPORT_SYMBOL(_cond_resched);
  * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
  * call schedule, and on return reacquire the lock.
  *
- * This works OK both with and without CONFIG_PREEMPT. We do strange low-level
+ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
  * operations here to prevent schedule() from being called twice (once via
  * spin_unlock(), once by hand).
  */
@@ -6016,7 +6169,7 @@ void sched_setnuma(struct task_struct *p, int nid)
 	if (queued)
 		enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
 	if (running)
-		set_curr_task(rq, p);
+		set_next_task(rq, p);
 	task_rq_unlock(rq, p, &rf);
 }
 #endif /* CONFIG_NUMA_BALANCING */
@@ -6056,21 +6209,22 @@ static void calc_load_migrate(struct rq *rq)
 		atomic_long_add(delta, &calc_load_tasks);
 }
 
-static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
+static struct task_struct *__pick_migrate_task(struct rq *rq)
 {
-}
+	const struct sched_class *class;
+	struct task_struct *next;
 
-static const struct sched_class fake_sched_class = {
-	.put_prev_task = put_prev_task_fake,
-};
+	for_each_class(class) {
+		next = class->pick_next_task(rq, NULL, NULL);
+		if (next) {
+			next->sched_class->put_prev_task(rq, next, NULL);
+			return next;
+		}
+	}
 
-static struct task_struct fake_task = {
-	/*
-	 * Avoid pull_{rt,dl}_task()
-	 */
-	.prio = MAX_PRIO + 1,
-	.sched_class = &fake_sched_class,
-};
+	/* The idle class should always have a runnable task */
+	BUG();
+}
 
 /*
  * Migrate all tasks from the rq, sleeping tasks will be migrated by
@@ -6113,12 +6267,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
 		if (rq->nr_running == 1)
 			break;
 
-		/*
-		 * pick_next_task() assumes pinned rq->lock:
-		 */
-		next = pick_next_task(rq, &fake_task, rf);
-		BUG_ON(!next);
-		put_prev_task(rq, next);
+		next = __pick_migrate_task(rq);
 
 		/*
 		 * Rules for changing task_struct::cpus_mask are holding
@@ -6415,19 +6564,19 @@ DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
 void __init sched_init(void)
 {
-	unsigned long alloc_size = 0, ptr;
+	unsigned long ptr = 0;
 	int i;
 
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+	ptr += 2 * nr_cpu_ids * sizeof(void **);
 #endif
 #ifdef CONFIG_RT_GROUP_SCHED
-	alloc_size += 2 * nr_cpu_ids * sizeof(void **);
+	ptr += 2 * nr_cpu_ids * sizeof(void **);
 #endif
-	if (alloc_size) {
-		ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
+	if (ptr) {
+		ptr = (unsigned long)kzalloc(ptr, GFP_NOWAIT);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 		root_task_group.se = (struct sched_entity **)ptr;
@@ -6746,7 +6895,7 @@ struct task_struct *curr_task(int cpu)
 
 #ifdef CONFIG_IA64
 /**
- * set_curr_task - set the current task for a given CPU.
+ * ia64_set_curr_task - set the current task for a given CPU.
  * @cpu: the processor in question.
  * @p: the task pointer to set.
  *
@@ -6771,6 +6920,20 @@ void ia64_set_curr_task(int cpu, struct task_struct *p)
 /* task_group_lock serializes the addition/removal of task groups */
 static DEFINE_SPINLOCK(task_group_lock);
 
+static inline void alloc_uclamp_sched_group(struct task_group *tg,
+					    struct task_group *parent)
+{
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+	enum uclamp_id clamp_id;
+
+	for_each_clamp_id(clamp_id) {
+		uclamp_se_set(&tg->uclamp_req[clamp_id],
+			      uclamp_none(clamp_id), false);
+		tg->uclamp[clamp_id] = parent->uclamp[clamp_id];
+	}
+#endif
+}
+
 static void sched_free_group(struct task_group *tg)
 {
 	free_fair_sched_group(tg);
@@ -6794,6 +6957,8 @@ struct task_group *sched_create_group(struct task_group *parent)
 	if (!alloc_rt_sched_group(tg, parent))
 		goto err;
 
+	alloc_uclamp_sched_group(tg, parent);
+
 	return tg;
 
 err:
@@ -6897,7 +7062,7 @@ void sched_move_task(struct task_struct *tsk)
 	if (queued)
 		enqueue_task(rq, tsk, queue_flags);
 	if (running)
-		set_curr_task(rq, tsk);
+		set_next_task(rq, tsk);
 
 	task_rq_unlock(rq, tsk, &rf);
 }
@@ -6980,10 +7145,6 @@ static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
 #ifdef CONFIG_RT_GROUP_SCHED
 		if (!sched_rt_can_attach(css_tg(css), task))
 			return -EINVAL;
-#else
-		/* We don't support RT-tasks being in separate groups */
-		if (task->sched_class != &fair_sched_class)
-			return -EINVAL;
 #endif
 		/*
 		 * Serialize against wake_up_new_task() such that if its
@@ -7014,6 +7175,178 @@ static void cpu_cgroup_attach(struct cgroup_taskset *tset)
 		sched_move_task(task);
 }
 
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+static void cpu_util_update_eff(struct cgroup_subsys_state *css)
+{
+	struct cgroup_subsys_state *top_css = css;
+	struct uclamp_se *uc_parent = NULL;
+	struct uclamp_se *uc_se = NULL;
+	unsigned int eff[UCLAMP_CNT];
+	enum uclamp_id clamp_id;
+	unsigned int clamps;
+
+	css_for_each_descendant_pre(css, top_css) {
+		uc_parent = css_tg(css)->parent
+			? css_tg(css)->parent->uclamp : NULL;
+
+		for_each_clamp_id(clamp_id) {
+			/* Assume effective clamps matches requested clamps */
+			eff[clamp_id] = css_tg(css)->uclamp_req[clamp_id].value;
+			/* Cap effective clamps with parent's effective clamps */
+			if (uc_parent &&
+			    eff[clamp_id] > uc_parent[clamp_id].value) {
+				eff[clamp_id] = uc_parent[clamp_id].value;
+			}
+		}
+		/* Ensure protection is always capped by limit */
+		eff[UCLAMP_MIN] = min(eff[UCLAMP_MIN], eff[UCLAMP_MAX]);
+
+		/* Propagate most restrictive effective clamps */
+		clamps = 0x0;
+		uc_se = css_tg(css)->uclamp;
+		for_each_clamp_id(clamp_id) {
+			if (eff[clamp_id] == uc_se[clamp_id].value)
+				continue;
+			uc_se[clamp_id].value = eff[clamp_id];
+			uc_se[clamp_id].bucket_id = uclamp_bucket_id(eff[clamp_id]);
+			clamps |= (0x1 << clamp_id);
+		}
+		if (!clamps) {
+			css = css_rightmost_descendant(css);
+			continue;
+		}
+
+		/* Immediately update descendants RUNNABLE tasks */
+		uclamp_update_active_tasks(css, clamps);
+	}
+}
+
+/*
+ * Integer 10^N with a given N exponent by casting to integer the literal "1eN"
+ * C expression. Since there is no way to convert a macro argument (N) into a
+ * character constant, use two levels of macros.
+ */
+#define _POW10(exp) ((unsigned int)1e##exp)
+#define POW10(exp) _POW10(exp)
+
+struct uclamp_request {
+#define UCLAMP_PERCENT_SHIFT	2
+#define UCLAMP_PERCENT_SCALE	(100 * POW10(UCLAMP_PERCENT_SHIFT))
+	s64 percent;
+	u64 util;
+	int ret;
+};
+
+static inline struct uclamp_request
+capacity_from_percent(char *buf)
+{
+	struct uclamp_request req = {
+		.percent = UCLAMP_PERCENT_SCALE,
+		.util = SCHED_CAPACITY_SCALE,
+		.ret = 0,
+	};
+
+	buf = strim(buf);
+	if (strcmp(buf, "max")) {
+		req.ret = cgroup_parse_float(buf, UCLAMP_PERCENT_SHIFT,
+					     &req.percent);
+		if (req.ret)
+			return req;
+		if (req.percent > UCLAMP_PERCENT_SCALE) {
+			req.ret = -ERANGE;
+			return req;
+		}
+
+		req.util = req.percent << SCHED_CAPACITY_SHIFT;
+		req.util = DIV_ROUND_CLOSEST_ULL(req.util, UCLAMP_PERCENT_SCALE);
+	}
+
+	return req;
+}
+
+static ssize_t cpu_uclamp_write(struct kernfs_open_file *of, char *buf,
+				size_t nbytes, loff_t off,
+				enum uclamp_id clamp_id)
+{
+	struct uclamp_request req;
+	struct task_group *tg;
+
+	req = capacity_from_percent(buf);
+	if (req.ret)
+		return req.ret;
+
+	mutex_lock(&uclamp_mutex);
+	rcu_read_lock();
+
+	tg = css_tg(of_css(of));
+	if (tg->uclamp_req[clamp_id].value != req.util)
+		uclamp_se_set(&tg->uclamp_req[clamp_id], req.util, false);
+
+	/*
+	 * Because of not recoverable conversion rounding we keep track of the
+	 * exact requested value
+	 */
+	tg->uclamp_pct[clamp_id] = req.percent;
+
+	/* 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;
+}
+
+static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes,
+				    loff_t off)
+{
+	return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MIN);
+}
+
+static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
+				    char *buf, size_t nbytes,
+				    loff_t off)
+{
+	return cpu_uclamp_write(of, buf, nbytes, off, UCLAMP_MAX);
+}
+
+static inline void cpu_uclamp_print(struct seq_file *sf,
+				    enum uclamp_id clamp_id)
+{
+	struct task_group *tg;
+	u64 util_clamp;
+	u64 percent;
+	u32 rem;
+
+	rcu_read_lock();
+	tg = css_tg(seq_css(sf));
+	util_clamp = tg->uclamp_req[clamp_id].value;
+	rcu_read_unlock();
+
+	if (util_clamp == SCHED_CAPACITY_SCALE) {
+		seq_puts(sf, "max\n");
+		return;
+	}
+
+	percent = tg->uclamp_pct[clamp_id];
+	percent = div_u64_rem(percent, POW10(UCLAMP_PERCENT_SHIFT), &rem);
+	seq_printf(sf, "%llu.%0*u\n", percent, UCLAMP_PERCENT_SHIFT, rem);
+}
+
+static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
+{
+	cpu_uclamp_print(sf, UCLAMP_MIN);
+	return 0;
+}
+
+static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
+{
+	cpu_uclamp_print(sf, UCLAMP_MAX);
+	return 0;
+}
+#endif /* CONFIG_UCLAMP_TASK_GROUP */
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
 				struct cftype *cftype, u64 shareval)
@@ -7359,6 +7692,20 @@ static struct cftype cpu_legacy_files[] = {
 		.write_u64 = cpu_rt_period_write_uint,
 	},
 #endif
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+	{
+		.name = "uclamp.min",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cpu_uclamp_min_show,
+		.write = cpu_uclamp_min_write,
+	},
+	{
+		.name = "uclamp.max",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cpu_uclamp_max_show,
+		.write = cpu_uclamp_max_write,
+	},
+#endif
 	{ }	/* Terminate */
 };
 
@@ -7526,6 +7873,20 @@ static struct cftype cpu_files[] = {
 		.write = cpu_max_write,
 	},
 #endif
+#ifdef CONFIG_UCLAMP_TASK_GROUP
+	{
+		.name = "uclamp.min",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cpu_uclamp_min_show,
+		.write = cpu_uclamp_min_write,
+	},
+	{
+		.name = "uclamp.max",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = cpu_uclamp_max_show,
+		.write = cpu_uclamp_max_write,
+	},
+#endif
 	{ }	/* terminate */
 };