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

Pull scheduler updates from Ingo Molnar:

 - Remove the unused per rq load array and all its infrastructure, by
   Dietmar Eggemann.

 - Add utilization clamping support by Patrick Bellasi. This is a
   refinement of the energy aware scheduling framework with support for
   boosting of interactive and capping of background workloads: to make
   sure critical GUI threads get maximum frequency ASAP, and to make
   sure background processing doesn't unnecessarily move to cpufreq
   governor to higher frequencies and less energy efficient CPU modes.

 - Add the bare minimum of tracepoints required for LISA EAS regression
   testing, by Qais Yousef - which allows automated testing of various
   power management features, including energy aware scheduling.

 - Restructure the former tsk_nr_cpus_allowed() facility that the -rt
   kernel used to modify the scheduler's CPU affinity logic such as
   migrate_disable() - introduce the task->cpus_ptr value instead of
   taking the address of &task->cpus_allowed directly - by Sebastian
   Andrzej Siewior.

 - Misc optimizations, fixes, cleanups and small enhancements - see the
   Git log for details.

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  sched/uclamp: Add uclamp support to energy_compute()
  sched/uclamp: Add uclamp_util_with()
  sched/cpufreq, sched/uclamp: Add clamps for FAIR and RT tasks
  sched/uclamp: Set default clamps for RT tasks
  sched/uclamp: Reset uclamp values on RESET_ON_FORK
  sched/uclamp: Extend sched_setattr() to support utilization clamping
  sched/core: Allow sched_setattr() to use the current policy
  sched/uclamp: Add system default clamps
  sched/uclamp: Enforce last task's UCLAMP_MAX
  sched/uclamp: Add bucket local max tracking
  sched/uclamp: Add CPU's clamp buckets refcounting
  sched/fair: Rename weighted_cpuload() to cpu_runnable_load()
  sched/debug: Export the newly added tracepoints
  sched/debug: Add sched_overutilized tracepoint
  sched/debug: Add new tracepoint to track PELT at se level
  sched/debug: Add new tracepoints to track PELT at rq level
  sched/debug: Add a new sched_trace_*() helper functions
  sched/autogroup: Make autogroup_path() always available
  sched/wait: Deduplicate code with do-while
  sched/topology: Remove unused 'sd' parameter from arch_scale_cpu_capacity()
  ...

kernel/cgroup/cpuset.c

@@ -2829,7 +2829,7 @@ static void cpuset_fork(struct task_struct *task)
 	if (task_css_is_root(task, cpuset_cgrp_id))
 		return;
 
-	set_cpus_allowed_ptr(task, &current->cpus_allowed);
+	set_cpus_allowed_ptr(task, current->cpus_ptr);
 	task->mems_allowed = current->mems_allowed;
 }
 

kernel/fork.c

@@ -898,6 +898,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 #ifdef CONFIG_STACKPROTECTOR
 	tsk->stack_canary = get_random_canary();
 #endif
+	if (orig->cpus_ptr == &orig->cpus_mask)
+		tsk->cpus_ptr = &tsk->cpus_mask;
 
 	/*
 	 * One for us, one for whoever does the "release_task()" (usually

kernel/power/energy_model.c

@@ -223,7 +223,7 @@ int em_register_perf_domain(cpumask_t *span, unsigned int nr_states,
 		 * All CPUs of a domain must have the same micro-architecture
 		 * since they all share the same table.
 		 */
-		cap = arch_scale_cpu_capacity(NULL, cpu);
+		cap = arch_scale_cpu_capacity(cpu);
 		if (prev_cap && prev_cap != cap) {
 			pr_err("CPUs of %*pbl must have the same capacity\n",
 							cpumask_pr_args(span));

kernel/sched/autogroup.c

@@ -259,7 +259,6 @@ out:
 }
 #endif /* CONFIG_PROC_FS */
 
-#ifdef CONFIG_SCHED_DEBUG
 int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
 	if (!task_group_is_autogroup(tg))
@@ -267,4 +266,3 @@ int autogroup_path(struct task_group *tg, char *buf, int buflen)
 
 	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
 }
-#endif

kernel/sched/core.c

@@ -23,6 +23,17 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
+/*
+ * Export tracepoints that act as a bare tracehook (ie: have no trace event
+ * associated with them) to allow external modules to probe them.
+ */
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_cfs_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp);
+EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp);
+
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
 #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_JUMP_LABEL)
@@ -761,6 +772,401 @@ static void set_load_weight(struct task_struct *p, bool update_load)
 	}
 }
 
+#ifdef CONFIG_UCLAMP_TASK
+/* Max allowed minimum utilization */
+unsigned int sysctl_sched_uclamp_util_min = SCHED_CAPACITY_SCALE;
+
+/* Max allowed maximum utilization */
+unsigned int sysctl_sched_uclamp_util_max = SCHED_CAPACITY_SCALE;
+
+/* All clamps are required to be less or equal than these values */
+static struct uclamp_se uclamp_default[UCLAMP_CNT];
+
+/* Integer rounded range for each bucket */
+#define UCLAMP_BUCKET_DELTA DIV_ROUND_CLOSEST(SCHED_CAPACITY_SCALE, UCLAMP_BUCKETS)
+
+#define for_each_clamp_id(clamp_id) \
+	for ((clamp_id) = 0; (clamp_id) < UCLAMP_CNT; (clamp_id)++)
+
+static inline unsigned int uclamp_bucket_id(unsigned int clamp_value)
+{
+	return clamp_value / UCLAMP_BUCKET_DELTA;
+}
+
+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)
+{
+	if (clamp_id == UCLAMP_MIN)
+		return 0;
+	return SCHED_CAPACITY_SCALE;
+}
+
+static inline void uclamp_se_set(struct uclamp_se *uc_se,
+				 unsigned int value, bool user_defined)
+{
+	uc_se->value = value;
+	uc_se->bucket_id = uclamp_bucket_id(value);
+	uc_se->user_defined = user_defined;
+}
+
+static inline unsigned int
+uclamp_idle_value(struct rq *rq, unsigned int clamp_id,
+		  unsigned int clamp_value)
+{
+	/*
+	 * Avoid blocked utilization pushing up the frequency when we go
+	 * idle (which drops the max-clamp) by retaining the last known
+	 * max-clamp.
+	 */
+	if (clamp_id == UCLAMP_MAX) {
+		rq->uclamp_flags |= UCLAMP_FLAG_IDLE;
+		return clamp_value;
+	}
+
+	return uclamp_none(UCLAMP_MIN);
+}
+
+static inline void uclamp_idle_reset(struct rq *rq, unsigned int clamp_id,
+				     unsigned int clamp_value)
+{
+	/* Reset max-clamp retention only on idle exit */
+	if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE))
+		return;
+
+	WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value);
+}
+
+static inline
+unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id,
+				 unsigned int clamp_value)
+{
+	struct uclamp_bucket *bucket = rq->uclamp[clamp_id].bucket;
+	int bucket_id = UCLAMP_BUCKETS - 1;
+
+	/*
+	 * Since both min and max clamps are max aggregated, find the
+	 * top most bucket with tasks in.
+	 */
+	for ( ; bucket_id >= 0; bucket_id--) {
+		if (!bucket[bucket_id].tasks)
+			continue;
+		return bucket[bucket_id].value;
+	}
+
+	/* No tasks -- default clamp values */
+	return uclamp_idle_value(rq, clamp_id, clamp_value);
+}
+
+/*
+ * The effective clamp bucket index of a task depends on, by increasing
+ * priority:
+ * - the task specific clamp value, when explicitly requested from userspace
+ * - 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)
+{
+	struct uclamp_se uc_req = p->uclamp_req[clamp_id];
+	struct uclamp_se uc_max = uclamp_default[clamp_id];
+
+	/* System default restrictions always apply */
+	if (unlikely(uc_req.value > uc_max.value))
+		return uc_max;
+
+	return uc_req;
+}
+
+unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id)
+{
+	struct uclamp_se uc_eff;
+
+	/* Task currently refcounted: use back-annotated (effective) value */
+	if (p->uclamp[clamp_id].active)
+		return p->uclamp[clamp_id].value;
+
+	uc_eff = uclamp_eff_get(p, clamp_id);
+
+	return uc_eff.value;
+}
+
+/*
+ * When a task is enqueued on a rq, the clamp bucket currently defined by the
+ * task's uclamp::bucket_id is refcounted on that rq. This also immediately
+ * updates the rq's clamp value if required.
+ *
+ * Tasks can have a task-specific value requested from user-space, track
+ * within each bucket the maximum value for tasks refcounted in it.
+ * This "local max aggregation" allows to track the exact "requested" value
+ * 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)
+{
+	struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
+	struct uclamp_se *uc_se = &p->uclamp[clamp_id];
+	struct uclamp_bucket *bucket;
+
+	lockdep_assert_held(&rq->lock);
+
+	/* Update task effective clamp */
+	p->uclamp[clamp_id] = uclamp_eff_get(p, clamp_id);
+
+	bucket = &uc_rq->bucket[uc_se->bucket_id];
+	bucket->tasks++;
+	uc_se->active = true;
+
+	uclamp_idle_reset(rq, clamp_id, uc_se->value);
+
+	/*
+	 * Local max aggregation: rq buckets always track the max
+	 * "requested" clamp value of its RUNNABLE tasks.
+	 */
+	if (bucket->tasks == 1 || uc_se->value > bucket->value)
+		bucket->value = uc_se->value;
+
+	if (uc_se->value > READ_ONCE(uc_rq->value))
+		WRITE_ONCE(uc_rq->value, uc_se->value);
+}
+
+/*
+ * When a task is dequeued from a rq, the clamp bucket refcounted by the task
+ * is released. If this is the last task reference counting the rq's max
+ * active clamp value, then the rq's clamp value is updated.
+ *
+ * Both refcounted tasks and rq's cached clamp values are expected to be
+ * always valid. If it's detected they are not, as defensive programming,
+ * enforce the expected state and warn.
+ */
+static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
+				    unsigned int clamp_id)
+{
+	struct uclamp_rq *uc_rq = &rq->uclamp[clamp_id];
+	struct uclamp_se *uc_se = &p->uclamp[clamp_id];
+	struct uclamp_bucket *bucket;
+	unsigned int bkt_clamp;
+	unsigned int rq_clamp;
+
+	lockdep_assert_held(&rq->lock);
+
+	bucket = &uc_rq->bucket[uc_se->bucket_id];
+	SCHED_WARN_ON(!bucket->tasks);
+	if (likely(bucket->tasks))
+		bucket->tasks--;
+	uc_se->active = false;
+
+	/*
+	 * Keep "local max aggregation" simple and accept to (possibly)
+	 * overboost some RUNNABLE tasks in the same bucket.
+	 * The rq clamp bucket value is reset to its base value whenever
+	 * there are no more RUNNABLE tasks refcounting it.
+	 */
+	if (likely(bucket->tasks))
+		return;
+
+	rq_clamp = READ_ONCE(uc_rq->value);
+	/*
+	 * Defensive programming: this should never happen. If it happens,
+	 * e.g. due to future modification, warn and fixup the expected value.
+	 */
+	SCHED_WARN_ON(bucket->value > rq_clamp);
+	if (bucket->value >= rq_clamp) {
+		bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
+		WRITE_ONCE(uc_rq->value, bkt_clamp);
+	}
+}
+
+static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p)
+{
+	unsigned int clamp_id;
+
+	if (unlikely(!p->sched_class->uclamp_enabled))
+		return;
+
+	for_each_clamp_id(clamp_id)
+		uclamp_rq_inc_id(rq, p, clamp_id);
+
+	/* Reset clamp idle holding when there is one RUNNABLE task */
+	if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+		rq->uclamp_flags &= ~UCLAMP_FLAG_IDLE;
+}
+
+static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p)
+{
+	unsigned int clamp_id;
+
+	if (unlikely(!p->sched_class->uclamp_enabled))
+		return;
+
+	for_each_clamp_id(clamp_id)
+		uclamp_rq_dec_id(rq, p, clamp_id);
+}
+
+int sysctl_sched_uclamp_handler(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp,
+				loff_t *ppos)
+{
+	int old_min, old_max;
+	static DEFINE_MUTEX(mutex);
+	int result;
+
+	mutex_lock(&mutex);
+	old_min = sysctl_sched_uclamp_util_min;
+	old_max = sysctl_sched_uclamp_util_max;
+
+	result = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (result)
+		goto undo;
+	if (!write)
+		goto done;
+
+	if (sysctl_sched_uclamp_util_min > sysctl_sched_uclamp_util_max ||
+	    sysctl_sched_uclamp_util_max > SCHED_CAPACITY_SCALE) {
+		result = -EINVAL;
+		goto undo;
+	}
+
+	if (old_min != sysctl_sched_uclamp_util_min) {
+		uclamp_se_set(&uclamp_default[UCLAMP_MIN],
+			      sysctl_sched_uclamp_util_min, false);
+	}
+	if (old_max != sysctl_sched_uclamp_util_max) {
+		uclamp_se_set(&uclamp_default[UCLAMP_MAX],
+			      sysctl_sched_uclamp_util_max, false);
+	}
+
+	/*
+	 * Updating all the RUNNABLE task is expensive, keep it simple and do
+	 * just a lazy update at each next enqueue time.
+	 */
+	goto done;
+
+undo:
+	sysctl_sched_uclamp_util_min = old_min;
+	sysctl_sched_uclamp_util_max = old_max;
+done:
+	mutex_unlock(&mutex);
+
+	return result;
+}
+
+static int uclamp_validate(struct task_struct *p,
+			   const struct sched_attr *attr)
+{
+	unsigned int lower_bound = p->uclamp_req[UCLAMP_MIN].value;
+	unsigned int upper_bound = p->uclamp_req[UCLAMP_MAX].value;
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN)
+		lower_bound = attr->sched_util_min;
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX)
+		upper_bound = attr->sched_util_max;
+
+	if (lower_bound > upper_bound)
+		return -EINVAL;
+	if (upper_bound > SCHED_CAPACITY_SCALE)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void __setscheduler_uclamp(struct task_struct *p,
+				  const struct sched_attr *attr)
+{
+	unsigned int clamp_id;
+
+	/*
+	 * On scheduling class change, reset to default clamps for tasks
+	 * without a task-specific value.
+	 */
+	for_each_clamp_id(clamp_id) {
+		struct uclamp_se *uc_se = &p->uclamp_req[clamp_id];
+		unsigned int clamp_value = uclamp_none(clamp_id);
+
+		/* Keep using defined clamps across class changes */
+		if (uc_se->user_defined)
+			continue;
+
+		/* By default, RT tasks always get 100% boost */
+		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
+			clamp_value = uclamp_none(UCLAMP_MAX);
+
+		uclamp_se_set(uc_se, clamp_value, false);
+	}
+
+	if (likely(!(attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)))
+		return;
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MIN) {
+		uclamp_se_set(&p->uclamp_req[UCLAMP_MIN],
+			      attr->sched_util_min, true);
+	}
+
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP_MAX) {
+		uclamp_se_set(&p->uclamp_req[UCLAMP_MAX],
+			      attr->sched_util_max, true);
+	}
+}
+
+static void uclamp_fork(struct task_struct *p)
+{
+	unsigned int clamp_id;
+
+	for_each_clamp_id(clamp_id)
+		p->uclamp[clamp_id].active = false;
+
+	if (likely(!p->sched_reset_on_fork))
+		return;
+
+	for_each_clamp_id(clamp_id) {
+		unsigned int clamp_value = uclamp_none(clamp_id);
+
+		/* By default, RT tasks always get 100% boost */
+		if (unlikely(rt_task(p) && clamp_id == UCLAMP_MIN))
+			clamp_value = uclamp_none(UCLAMP_MAX);
+
+		uclamp_se_set(&p->uclamp_req[clamp_id], clamp_value, false);
+	}
+}
+
+static void __init init_uclamp(void)
+{
+	struct uclamp_se uc_max = {};
+	unsigned int clamp_id;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq));
+		cpu_rq(cpu)->uclamp_flags = 0;
+	}
+
+	for_each_clamp_id(clamp_id) {
+		uclamp_se_set(&init_task.uclamp_req[clamp_id],
+			      uclamp_none(clamp_id), false);
+	}
+
+	/* 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)
+		uclamp_default[clamp_id] = uc_max;
+}
+
+#else /* CONFIG_UCLAMP_TASK */
+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) { }
+static inline int uclamp_validate(struct task_struct *p,
+				  const struct sched_attr *attr)
+{
+	return -EOPNOTSUPP;
+}
+static void __setscheduler_uclamp(struct task_struct *p,
+				  const struct sched_attr *attr) { }
+static inline void uclamp_fork(struct task_struct *p) { }
+static inline void init_uclamp(void) { }
+#endif /* CONFIG_UCLAMP_TASK */
+
 static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 {
 	if (!(flags & ENQUEUE_NOCLOCK))
@@ -771,6 +1177,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
 		psi_enqueue(p, flags & ENQUEUE_WAKEUP);
 	}
 
+	uclamp_rq_inc(rq, p);
 	p->sched_class->enqueue_task(rq, p, flags);
 }
 
@@ -784,6 +1191,7 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags)
 		psi_dequeue(p, flags & DEQUEUE_SLEEP);
 	}
 
+	uclamp_rq_dec(rq, p);
 	p->sched_class->dequeue_task(rq, p, flags);
 }
 
@@ -930,7 +1338,7 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
  */
 static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
 {
-	if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+	if (!cpumask_test_cpu(cpu, p->cpus_ptr))
 		return false;
 
 	if (is_per_cpu_kthread(p))
@@ -1025,7 +1433,7 @@ static int migration_cpu_stop(void *data)
 	local_irq_disable();
 	/*
 	 * We need to explicitly wake pending tasks before running
-	 * __migrate_task() such that we will not miss enforcing cpus_allowed
+	 * __migrate_task() such that we will not miss enforcing cpus_ptr
 	 * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
 	 */
 	sched_ttwu_pending();
@@ -1056,7 +1464,7 @@ static int migration_cpu_stop(void *data)
  */
 void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
 {
-	cpumask_copy(&p->cpus_allowed, new_mask);
+	cpumask_copy(&p->cpus_mask, new_mask);
 	p->nr_cpus_allowed = cpumask_weight(new_mask);
 }
 
@@ -1126,7 +1534,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
 		goto out;
 	}
 
-	if (cpumask_equal(&p->cpus_allowed, new_mask))
+	if (cpumask_equal(p->cpus_ptr, new_mask))
 		goto out;
 
 	if (!cpumask_intersects(new_mask, cpu_valid_mask)) {
@@ -1286,10 +1694,10 @@ static int migrate_swap_stop(void *data)
 	if (task_cpu(arg->src_task) != arg->src_cpu)
 		goto unlock;
 
-	if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr))
 		goto unlock;
 
-	if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr))
 		goto unlock;
 
 	__migrate_swap_task(arg->src_task, arg->dst_cpu);
@@ -1331,10 +1739,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p,
 	if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
 		goto out;
 
-	if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr))
 		goto out;
 
-	if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed))
+	if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr))
 		goto out;
 
 	trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
@@ -1479,7 +1887,7 @@ void kick_process(struct task_struct *p)
 EXPORT_SYMBOL_GPL(kick_process);
 
 /*
- * ->cpus_allowed is protected by both rq->lock and p->pi_lock
+ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
  *
  * A few notes on cpu_active vs cpu_online:
  *
@@ -1519,14 +1927,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
 		for_each_cpu(dest_cpu, nodemask) {
 			if (!cpu_active(dest_cpu))
 				continue;
-			if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+			if (cpumask_test_cpu(dest_cpu, p->cpus_ptr))
 				return dest_cpu;
 		}
 	}
 
 	for (;;) {
 		/* Any allowed, online CPU? */
-		for_each_cpu(dest_cpu, &p->cpus_allowed) {
+		for_each_cpu(dest_cpu, p->cpus_ptr) {
 			if (!is_cpu_allowed(p, dest_cpu))
 				continue;
 
@@ -1570,7 +1978,7 @@ out:
 }
 
 /*
- * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
+ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable.
  */
 static inline
 int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
@@ -1580,11 +1988,11 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
 	if (p->nr_cpus_allowed > 1)
 		cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
 	else
-		cpu = cpumask_any(&p->cpus_allowed);
+		cpu = cpumask_any(p->cpus_ptr);
 
 	/*
 	 * In order not to call set_task_cpu() on a blocking task we need
-	 * to rely on ttwu() to place the task on a valid ->cpus_allowed
+	 * to rely on ttwu() to place the task on a valid ->cpus_ptr
 	 * CPU.
 	 *
 	 * Since this is common to all placement strategies, this lives here.
@@ -1991,6 +2399,29 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	unsigned long flags;
 	int cpu, success = 0;
 
+	if (p == current) {
+		/*
+		 * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
+		 * == smp_processor_id()'. Together this means we can special
+		 * case the whole 'p->on_rq && ttwu_remote()' case below
+		 * without taking any locks.
+		 *
+		 * In particular:
+		 *  - we rely on Program-Order guarantees for all the ordering,
+		 *  - we're serialized against set_special_state() by virtue of
+		 *    it disabling IRQs (this allows not taking ->pi_lock).
+		 */
+		if (!(p->state & state))
+			return false;
+
+		success = 1;
+		cpu = task_cpu(p);
+		trace_sched_waking(p);
+		p->state = TASK_RUNNING;
+		trace_sched_wakeup(p);
+		goto out;
+	}
+
 	/*
 	 * If we are going to wake up a thread waiting for CONDITION we
 	 * need to ensure that CONDITION=1 done by the caller can not be
@@ -2000,7 +2431,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
 	smp_mb__after_spinlock();
 	if (!(p->state & state))
-		goto out;
+		goto unlock;
 
 	trace_sched_waking(p);
 
@@ -2030,7 +2461,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
-		goto stat;
+		goto unlock;
 
 #ifdef CONFIG_SMP
 	/*
@@ -2090,10 +2521,11 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu, wake_flags);
-stat:
-	ttwu_stat(p, cpu, wake_flags);
-out:
+unlock:
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+out:
+	if (success)
+		ttwu_stat(p, cpu, wake_flags);
 
 	return success;
 }
@@ -2300,6 +2732,8 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 */
 	p->prio = current->normal_prio;
 
+	uclamp_fork(p);
+
 	/*
 	 * Revert to default priority/policy on fork if requested.
 	 */
@@ -2395,7 +2829,7 @@ void wake_up_new_task(struct task_struct *p)
 #ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
-	 *  - cpus_allowed can change in the fork path
+	 *  - cpus_ptr can change in the fork path
 	 *  - any previously selected CPU might disappear through hotplug
 	 *
 	 * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
@@ -3033,7 +3467,6 @@ void scheduler_tick(void)
 
 	update_rq_clock(rq);
 	curr->sched_class->task_tick(rq, curr, 0);
-	cpu_load_update_active(rq);
 	calc_global_load_tick(rq);
 	psi_task_tick(rq);
 
@@ -4071,6 +4504,13 @@ static void __setscheduler_params(struct task_struct *p,
 static void __setscheduler(struct rq *rq, struct task_struct *p,
 			   const struct sched_attr *attr, bool keep_boost)
 {
+	/*
+	 * If params can't change scheduling class changes aren't allowed
+	 * either.
+	 */
+	if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)
+		return;
+
 	__setscheduler_params(p, attr);
 
 	/*
@@ -4208,6 +4648,13 @@ recheck:
 			return retval;
 	}
 
+	/* Update task specific "requested" clamps */
+	if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) {
+		retval = uclamp_validate(p, attr);
+		if (retval)
+			return retval;
+	}
+
 	/*
 	 * Make sure no PI-waiters arrive (or leave) while we are
 	 * changing the priority of the task:
@@ -4237,6 +4684,8 @@ recheck:
 			goto change;
 		if (dl_policy(policy) && dl_param_changed(p, attr))
 			goto change;
+		if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
+			goto change;
 
 		p->sched_reset_on_fork = reset_on_fork;
 		task_rq_unlock(rq, p, &rf);
@@ -4267,7 +4716,7 @@ change:
 			 * the entire root_domain to become SCHED_DEADLINE. We
 			 * will also fail if there's no bandwidth available.
 			 */
-			if (!cpumask_subset(span, &p->cpus_allowed) ||
+			if (!cpumask_subset(span, p->cpus_ptr) ||
 			    rq->rd->dl_bw.bw == 0) {
 				task_rq_unlock(rq, p, &rf);
 				return -EPERM;
@@ -4317,7 +4766,9 @@ change:
 		put_prev_task(rq, p);
 
 	prev_class = p->sched_class;
+
 	__setscheduler(rq, p, attr, pi);
+	__setscheduler_uclamp(p, attr);
 
 	if (queued) {
 		/*
@@ -4493,6 +4944,10 @@ static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *a
 	if (ret)
 		return -EFAULT;
 
+	if ((attr->sched_flags & SCHED_FLAG_UTIL_CLAMP) &&
+	    size < SCHED_ATTR_SIZE_VER1)
+		return -EINVAL;
+
 	/*
 	 * XXX: Do we want to be lenient like existing syscalls; or do we want
 	 * to be strict and return an error on out-of-bounds values?
@@ -4556,14 +5011,21 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
 
 	if ((int)attr.sched_policy < 0)
 		return -EINVAL;
+	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 (p != NULL)
-		retval = sched_setattr(p, &attr);
+	if (likely(p))
+		get_task_struct(p);
 	rcu_read_unlock();
 
+	if (likely(p)) {
+		retval = sched_setattr(p, &attr);
+		put_task_struct(p);
+	}
+
 	return retval;
 }
 
@@ -4714,6 +5176,11 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	else
 		attr.sched_nice = task_nice(p);
 
+#ifdef CONFIG_UCLAMP_TASK
+	attr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+	attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+#endif
+
 	rcu_read_unlock();
 
 	retval = sched_read_attr(uattr, &attr, size);
@@ -4866,7 +5333,7 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
 		goto out_unlock;
 
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
+	cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 
 out_unlock:
@@ -5123,7 +5590,7 @@ long __sched io_schedule_timeout(long timeout)
 }
 EXPORT_SYMBOL(io_schedule_timeout);
 
-void io_schedule(void)
+void __sched io_schedule(void)
 {
 	int token;
 
@@ -5443,7 +5910,7 @@ int task_can_attach(struct task_struct *p,
 	 * allowed nodes is unnecessary.  Thus, cpusets are not
 	 * applicable for such threads.  This prevents checking for
 	 * success of set_cpus_allowed_ptr() on all attached tasks
-	 * before cpus_allowed may be changed.
+	 * before cpus_mask may be changed.
 	 */
 	if (p->flags & PF_NO_SETAFFINITY) {
 		ret = -EINVAL;
@@ -5470,7 +5937,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (curr_cpu == target_cpu)
 		return 0;
 
-	if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed))
+	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
 	/* TODO: This is not properly updating schedstats */
@@ -5608,7 +6075,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
 		put_prev_task(rq, next);
 
 		/*
-		 * Rules for changing task_struct::cpus_allowed are holding
+		 * Rules for changing task_struct::cpus_mask are holding
 		 * both pi_lock and rq->lock, such that holding either
 		 * stabilizes the mask.
 		 *
@@ -5902,8 +6369,8 @@ DECLARE_PER_CPU(cpumask_var_t, select_idle_mask);
 
 void __init sched_init(void)
 {
-	int i, j;
 	unsigned long alloc_size = 0, ptr;
+	int i;
 
 	wait_bit_init();
 
@@ -6005,10 +6472,6 @@ void __init sched_init(void)
 #ifdef CONFIG_RT_GROUP_SCHED
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
-
-		for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
-			rq->cpu_load[j] = 0;
-
 #ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
@@ -6063,6 +6526,8 @@ void __init sched_init(void)
 
 	psi_init();
 
+	init_uclamp();
+
 	scheduler_running = 1;
 }
 

kernel/sched/cpudeadline.c

@@ -120,14 +120,14 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
 	const struct sched_dl_entity *dl_se = &p->dl;
 
 	if (later_mask &&
-	    cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
+	    cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
 		return 1;
 	} else {
 		int best_cpu = cpudl_maximum(cp);
 
 		WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
 
-		if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) &&
+		if (cpumask_test_cpu(best_cpu, p->cpus_ptr) &&
 		    dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
 			if (later_mask)
 				cpumask_set_cpu(best_cpu, later_mask);

kernel/sched/cpufreq_schedutil.c

@@ -196,14 +196,17 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
  * based on the task model parameters and gives the minimal utilization
  * required to meet deadlines.
  */
-unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
-				  unsigned long max, enum schedutil_type type)
+unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum schedutil_type type,
+				 struct task_struct *p)
 {
 	unsigned long dl_util, util, irq;
 	struct rq *rq = cpu_rq(cpu);
 
-	if (type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt))
+	if (!IS_BUILTIN(CONFIG_UCLAMP_TASK) &&
+	    type == FREQUENCY_UTIL && rt_rq_is_runnable(&rq->rt)) {
 		return max;
+	}
 
 	/*
 	 * Early check to see if IRQ/steal time saturates the CPU, can be
@@ -219,9 +222,16 @@ unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
 	 * CFS tasks and we use the same metric to track the effective
 	 * utilization (PELT windows are synchronized) we can directly add them
 	 * to obtain the CPU's actual utilization.
+	 *
+	 * CFS and RT utilization can be boosted or capped, depending on
+	 * utilization clamp constraints requested by currently RUNNABLE
+	 * tasks.
+	 * When there are no CFS RUNNABLE tasks, clamps are released and
+	 * frequency will be gracefully reduced with the utilization decay.
 	 */
-	util = util_cfs;
-	util += cpu_util_rt(rq);
+	util = util_cfs + cpu_util_rt(rq);
+	if (type == FREQUENCY_UTIL)
+		util = uclamp_util_with(rq, util, p);
 
 	dl_util = cpu_util_dl(rq);
 
@@ -276,12 +286,12 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
 	unsigned long util = cpu_util_cfs(rq);
-	unsigned long max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+	unsigned long max = arch_scale_cpu_capacity(sg_cpu->cpu);
 
 	sg_cpu->max = max;
 	sg_cpu->bw_dl = cpu_bw_dl(rq);
 
-	return schedutil_freq_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL);
+	return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
 }
 
 /**

kernel/sched/cpupri.c

@@ -94,11 +94,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
 		if (skip)
 			continue;
 
-		if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
+		if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
 			continue;
 
 		if (lowest_mask) {
-			cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+			cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
 
 			/*
 			 * We have to ensure that we have at least one bit

kernel/sched/deadline.c

@@ -538,7 +538,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 		 * If we cannot preempt any rq, fall back to pick any
 		 * online CPU:
 		 */
-		cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
+		cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr);
 		if (cpu >= nr_cpu_ids) {
 			/*
 			 * Failed to find any suitable CPU.
@@ -1195,7 +1195,7 @@ static void update_curr_dl(struct rq *rq)
 						 &curr->dl);
 	} else {
 		unsigned long scale_freq = arch_scale_freq_capacity(cpu);
-		unsigned long scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+		unsigned long scale_cpu = arch_scale_cpu_capacity(cpu);
 
 		scaled_delta_exec = cap_scale(delta_exec, scale_freq);
 		scaled_delta_exec = cap_scale(scaled_delta_exec, scale_cpu);
@@ -1824,7 +1824,7 @@ static void set_curr_task_dl(struct rq *rq)
 static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, &p->cpus_allowed))
+	    cpumask_test_cpu(cpu, p->cpus_ptr))
 		return 1;
 	return 0;
 }
@@ -1974,7 +1974,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
 		/* Retry if something changed. */
 		if (double_lock_balance(rq, later_rq)) {
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) ||
+				     !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) ||
 				     task_running(rq, task) ||
 				     !dl_task(task) ||
 				     !task_on_rq_queued(task))) {

kernel/sched/debug.c

@@ -233,49 +233,35 @@ static void sd_free_ctl_entry(struct ctl_table **tablep)
 	*tablep = NULL;
 }
 
-static int min_load_idx = 0;
-static int max_load_idx = CPU_LOAD_IDX_MAX-1;
-
 static void
 set_table_entry(struct ctl_table *entry,
 		const char *procname, void *data, int maxlen,
-		umode_t mode, proc_handler *proc_handler,
-		bool load_idx)
+		umode_t mode, proc_handler *proc_handler)
 {
 	entry->procname = procname;
 	entry->data = data;
 	entry->maxlen = maxlen;
 	entry->mode = mode;
 	entry->proc_handler = proc_handler;
-
-	if (load_idx) {
-		entry->extra1 = &min_load_idx;
-		entry->extra2 = &max_load_idx;
-	}
 }
 
 static struct ctl_table *
 sd_alloc_ctl_domain_table(struct sched_domain *sd)
 {
-	struct ctl_table *table = sd_alloc_ctl_entry(14);
+	struct ctl_table *table = sd_alloc_ctl_entry(9);
 
 	if (table == NULL)
 		return NULL;
 
-	set_table_entry(&table[0] , "min_interval",	   &sd->min_interval,	     sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[1] , "max_interval",	   &sd->max_interval,	     sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[2] , "busy_idx",		   &sd->busy_idx,	     sizeof(int) , 0644, proc_dointvec_minmax,   true );
-	set_table_entry(&table[3] , "idle_idx",		   &sd->idle_idx,	     sizeof(int) , 0644, proc_dointvec_minmax,   true );
-	set_table_entry(&table[4] , "newidle_idx",	   &sd->newidle_idx,	     sizeof(int) , 0644, proc_dointvec_minmax,   true );
-	set_table_entry(&table[5] , "wake_idx",		   &sd->wake_idx,	     sizeof(int) , 0644, proc_dointvec_minmax,   true );
-	set_table_entry(&table[6] , "forkexec_idx",	   &sd->forkexec_idx,	     sizeof(int) , 0644, proc_dointvec_minmax,   true );
-	set_table_entry(&table[7] , "busy_factor",	   &sd->busy_factor,	     sizeof(int) , 0644, proc_dointvec_minmax,   false);
-	set_table_entry(&table[8] , "imbalance_pct",	   &sd->imbalance_pct,	     sizeof(int) , 0644, proc_dointvec_minmax,   false);
-	set_table_entry(&table[9] , "cache_nice_tries",	   &sd->cache_nice_tries,    sizeof(int) , 0644, proc_dointvec_minmax,   false);
-	set_table_entry(&table[10], "flags",		   &sd->flags,		     sizeof(int) , 0644, proc_dointvec_minmax,   false);
-	set_table_entry(&table[11], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax, false);
-	set_table_entry(&table[12], "name",		   sd->name,		CORENAME_MAX_SIZE, 0444, proc_dostring,		 false);
-	/* &table[13] is terminator */
+	set_table_entry(&table[0], "min_interval",	  &sd->min_interval,	    sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[1], "max_interval",	  &sd->max_interval,	    sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[2], "busy_factor",	  &sd->busy_factor,	    sizeof(int),  0644, proc_dointvec_minmax);
+	set_table_entry(&table[3], "imbalance_pct",	  &sd->imbalance_pct,	    sizeof(int),  0644, proc_dointvec_minmax);
+	set_table_entry(&table[4], "cache_nice_tries",	  &sd->cache_nice_tries,    sizeof(int),  0644, proc_dointvec_minmax);
+	set_table_entry(&table[5], "flags",		  &sd->flags,		    sizeof(int),  0644, proc_dointvec_minmax);
+	set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax);
+	set_table_entry(&table[7], "name",		  sd->name,	       CORENAME_MAX_SIZE, 0444, proc_dostring);
+	/* &table[8] is terminator */
 
 	return table;
 }
@@ -653,8 +639,6 @@ do {									\
 	SEQ_printf(m, "  .%-30s: %Ld.%06ld\n", #x, SPLIT_NS(rq->x))
 
 	P(nr_running);
-	SEQ_printf(m, "  .%-30s: %lu\n", "load",
-		   rq->load.weight);
 	P(nr_switches);
 	P(nr_load_updates);
 	P(nr_uninterruptible);
@@ -662,11 +646,6 @@ do {									\
 	SEQ_printf(m, "  .%-30s: %ld\n", "curr->pid", (long)(task_pid_nr(rq->curr)));
 	PN(clock);
 	PN(clock_task);
-	P(cpu_load[0]);
-	P(cpu_load[1]);
-	P(cpu_load[2]);
-	P(cpu_load[3]);
-	P(cpu_load[4]);
 #undef P
 #undef PN
 

kernel/sched/features.h

@@ -39,7 +39,6 @@ SCHED_FEAT(WAKEUP_PREEMPTION, true)
 
 SCHED_FEAT(HRTICK, false)
 SCHED_FEAT(DOUBLE_TICK, false)
-SCHED_FEAT(LB_BIAS, false)
 
 /*
  * Decrement CPU capacity based on time not spent running tasks

kernel/sched/pelt.c

@@ -28,6 +28,8 @@
 #include "sched.h"
 #include "pelt.h"
 
+#include <trace/events/sched.h>
+
 /*
  * Approximate:
  *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
@@ -265,6 +267,7 @@ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se)
 {
 	if (___update_load_sum(now, &se->avg, 0, 0, 0)) {
 		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		trace_pelt_se_tp(se);
 		return 1;
 	}
 
@@ -278,6 +281,7 @@ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se
 
 		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
 		cfs_se_util_change(&se->avg);
+		trace_pelt_se_tp(se);
 		return 1;
 	}
 
@@ -292,6 +296,7 @@ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq)
 				cfs_rq->curr != NULL)) {
 
 		___update_load_avg(&cfs_rq->avg, 1, 1);
+		trace_pelt_cfs_tp(cfs_rq);
 		return 1;
 	}
 
@@ -317,6 +322,7 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
 				running)) {
 
 		___update_load_avg(&rq->avg_rt, 1, 1);
+		trace_pelt_rt_tp(rq);
 		return 1;
 	}
 
@@ -340,6 +346,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 				running)) {
 
 		___update_load_avg(&rq->avg_dl, 1, 1);
+		trace_pelt_dl_tp(rq);
 		return 1;
 	}
 
@@ -366,7 +373,7 @@ int update_irq_load_avg(struct rq *rq, u64 running)
 	 * reflect the real amount of computation
 	 */
 	running = cap_scale(running, arch_scale_freq_capacity(cpu_of(rq)));
-	running = cap_scale(running, arch_scale_cpu_capacity(NULL, cpu_of(rq)));
+	running = cap_scale(running, arch_scale_cpu_capacity(cpu_of(rq)));
 
 	/*
 	 * We know the time that has been used by interrupt since last update
@@ -388,8 +395,10 @@ int update_irq_load_avg(struct rq *rq, u64 running)
 				1,
 				1);
 
-	if (ret)
+	if (ret) {
 		___update_load_avg(&rq->avg_irq, 1, 1);
+		trace_pelt_irq_tp(rq);
+	}
 
 	return ret;
 }

kernel/sched/pelt.h

@@ -79,7 +79,7 @@ static inline void update_rq_clock_pelt(struct rq *rq, s64 delta)
 	 * Scale the elapsed time to reflect the real amount of
 	 * computation
 	 */
-	delta = cap_scale(delta, arch_scale_cpu_capacity(NULL, cpu_of(rq)));
+	delta = cap_scale(delta, arch_scale_cpu_capacity(cpu_of(rq)));
 	delta = cap_scale(delta, arch_scale_freq_capacity(cpu_of(rq)));
 
 	rq->clock_pelt += delta;

kernel/sched/rt.c

@@ -1614,7 +1614,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
 {
 	if (!task_running(rq, p) &&
-	    cpumask_test_cpu(cpu, &p->cpus_allowed))
+	    cpumask_test_cpu(cpu, p->cpus_ptr))
 		return 1;
 
 	return 0;
@@ -1751,7 +1751,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
 			 * Also make sure that it wasn't scheduled on its rq.
 			 */
 			if (unlikely(task_rq(task) != rq ||
-				     !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) ||
+				     !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) ||
 				     task_running(rq, task) ||
 				     !rt_task(task) ||
 				     !task_on_rq_queued(task))) {
@@ -2400,6 +2400,10 @@ const struct sched_class rt_sched_class = {
 	.switched_to		= switched_to_rt,
 
 	.update_curr		= update_curr_rt,
+
+#ifdef CONFIG_UCLAMP_TASK
+	.uclamp_enabled		= 1,
+#endif
 };
 
 #ifdef CONFIG_RT_GROUP_SCHED

kernel/sched/sched-pelt.h

@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Generated by Documentation/scheduler/sched-pelt; do not modify. */
 
-static const u32 runnable_avg_yN_inv[] = {
+static const u32 runnable_avg_yN_inv[] __maybe_unused = {
 	0xffffffff, 0xfa83b2da, 0xf5257d14, 0xefe4b99a, 0xeac0c6e6, 0xe5b906e6,
 	0xe0ccdeeb, 0xdbfbb796, 0xd744fcc9, 0xd2a81d91, 0xce248c14, 0xc9b9bd85,
 	0xc5672a10, 0xc12c4cc9, 0xbd08a39e, 0xb8fbaf46, 0xb504f333, 0xb123f581,

kernel/sched/sched.h

@@ -96,12 +96,6 @@ extern atomic_long_t calc_load_tasks;
 extern void calc_global_load_tick(struct rq *this_rq);
 extern long calc_load_fold_active(struct rq *this_rq, long adjust);
 
-#ifdef CONFIG_SMP
-extern void cpu_load_update_active(struct rq *this_rq);
-#else
-static inline void cpu_load_update_active(struct rq *this_rq) { }
-#endif
-
 /*
  * Helpers for converting nanosecond timing to jiffy resolution
  */
@@ -344,8 +338,10 @@ struct cfs_bandwidth {
 	u64			runtime_expires;
 	int			expires_seq;
 
-	short			idle;
-	short			period_active;
+	u8			idle;
+	u8			period_active;
+	u8			distribute_running;
+	u8			slack_started;
 	struct hrtimer		period_timer;
 	struct hrtimer		slack_timer;
 	struct list_head	throttled_cfs_rq;
@@ -354,8 +350,6 @@ struct cfs_bandwidth {
 	int			nr_periods;
 	int			nr_throttled;
 	u64			throttled_time;
-
-	bool                    distribute_running;
 #endif
 };
 
@@ -797,6 +791,48 @@ extern void rto_push_irq_work_func(struct irq_work *work);
 #endif
 #endif /* CONFIG_SMP */
 
+#ifdef CONFIG_UCLAMP_TASK
+/*
+ * struct uclamp_bucket - Utilization clamp bucket
+ * @value: utilization clamp value for tasks on this clamp bucket
+ * @tasks: number of RUNNABLE tasks on this clamp bucket
+ *
+ * Keep track of how many tasks are RUNNABLE for a given utilization
+ * clamp value.
+ */
+struct uclamp_bucket {
+	unsigned long value : bits_per(SCHED_CAPACITY_SCALE);
+	unsigned long tasks : BITS_PER_LONG - bits_per(SCHED_CAPACITY_SCALE);
+};
+
+/*
+ * struct uclamp_rq - rq's utilization clamp
+ * @value: currently active clamp values for a rq
+ * @bucket: utilization clamp buckets affecting a rq
+ *
+ * Keep track of RUNNABLE tasks on a rq to aggregate their clamp values.
+ * A clamp value is affecting a rq when there is at least one task RUNNABLE
+ * (or actually running) with that value.
+ *
+ * There are up to UCLAMP_CNT possible different clamp values, currently there
+ * are only two: minimum utilization and maximum utilization.
+ *
+ * All utilization clamping values are MAX aggregated, since:
+ * - for util_min: we want to run the CPU at least at the max of the minimum
+ *   utilization required by its currently RUNNABLE tasks.
+ * - for util_max: we want to allow the CPU to run up to the max of the
+ *   maximum utilization allowed by its currently RUNNABLE tasks.
+ *
+ * Since on each system we expect only a limited number of different
+ * utilization clamp values (UCLAMP_BUCKETS), use a simple array to track
+ * the metrics required to compute all the per-rq utilization clamp values.
+ */
+struct uclamp_rq {
+	unsigned int value;
+	struct uclamp_bucket bucket[UCLAMP_BUCKETS];
+};
+#endif /* CONFIG_UCLAMP_TASK */
+
 /*
  * This is the main, per-CPU runqueue data structure.
  *
@@ -818,8 +854,6 @@ struct rq {
 	unsigned int		nr_preferred_running;
 	unsigned int		numa_migrate_on;
 #endif
-	#define CPU_LOAD_IDX_MAX 5
-	unsigned long		cpu_load[CPU_LOAD_IDX_MAX];
 #ifdef CONFIG_NO_HZ_COMMON
 #ifdef CONFIG_SMP
 	unsigned long		last_load_update_tick;
@@ -830,11 +864,16 @@ struct rq {
 	atomic_t nohz_flags;
 #endif /* CONFIG_NO_HZ_COMMON */
 
-	/* capture load from *all* tasks on this CPU: */
-	struct load_weight	load;
 	unsigned long		nr_load_updates;
 	u64			nr_switches;
 
+#ifdef CONFIG_UCLAMP_TASK
+	/* Utilization clamp values based on CPU's RUNNABLE tasks */
+	struct uclamp_rq	uclamp[UCLAMP_CNT] ____cacheline_aligned;
+	unsigned int		uclamp_flags;
+#define UCLAMP_FLAG_IDLE 0x01
+#endif
+
 	struct cfs_rq		cfs;
 	struct rt_rq		rt;
 	struct dl_rq		dl;
@@ -1649,6 +1688,10 @@ extern const u32		sched_prio_to_wmult[40];
 struct sched_class {
 	const struct sched_class *next;
 
+#ifdef CONFIG_UCLAMP_TASK
+	int uclamp_enabled;
+#endif
+
 	void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags);
 	void (*yield_task)   (struct rq *rq);
@@ -2222,6 +2265,48 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
 static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif /* CONFIG_CPU_FREQ */
 
+#ifdef CONFIG_UCLAMP_TASK
+unsigned int uclamp_eff_value(struct task_struct *p, unsigned int clamp_id);
+
+static __always_inline
+unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
+			      struct task_struct *p)
+{
+	unsigned int min_util = READ_ONCE(rq->uclamp[UCLAMP_MIN].value);
+	unsigned int max_util = READ_ONCE(rq->uclamp[UCLAMP_MAX].value);
+
+	if (p) {
+		min_util = max(min_util, uclamp_eff_value(p, UCLAMP_MIN));
+		max_util = max(max_util, uclamp_eff_value(p, UCLAMP_MAX));
+	}
+
+	/*
+	 * Since CPU's {min,max}_util clamps are MAX aggregated considering
+	 * RUNNABLE tasks with _different_ clamps, we can end up with an
+	 * inversion. Fix it now when the clamps are applied.
+	 */
+	if (unlikely(min_util >= max_util))
+		return min_util;
+
+	return clamp(util, min_util, max_util);
+}
+
+static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
+{
+	return uclamp_util_with(rq, util, NULL);
+}
+#else /* CONFIG_UCLAMP_TASK */
+static inline unsigned int uclamp_util_with(struct rq *rq, unsigned int util,
+					    struct task_struct *p)
+{
+	return util;
+}
+static inline unsigned int uclamp_util(struct rq *rq, unsigned int util)
+{
+	return util;
+}
+#endif /* CONFIG_UCLAMP_TASK */
+
 #ifdef arch_scale_freq_capacity
 # ifndef arch_scale_freq_invariant
 #  define arch_scale_freq_invariant()	true
@@ -2237,7 +2322,6 @@ static inline unsigned long capacity_orig_of(int cpu)
 }
 #endif
 
-#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
 /**
  * enum schedutil_type - CPU utilization type
  * @FREQUENCY_UTIL:	Utilization used to select frequency
@@ -2253,15 +2337,11 @@ enum schedutil_type {
 	ENERGY_UTIL,
 };
 
-unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
-				  unsigned long max, enum schedutil_type type);
+#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
 
-static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
-{
-	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
-
-	return schedutil_freq_util(cpu, cfs, max, ENERGY_UTIL);
-}
+unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum schedutil_type type,
+				 struct task_struct *p);
 
 static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
@@ -2290,11 +2370,13 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 	return READ_ONCE(rq->avg_rt.util_avg);
 }
 #else /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
-static inline unsigned long schedutil_energy_util(int cpu, unsigned long cfs)
+static inline unsigned long schedutil_cpu_util(int cpu, unsigned long util_cfs,
+				 unsigned long max, enum schedutil_type type,
+				 struct task_struct *p)
 {
-	return cfs;
+	return 0;
 }
-#endif
+#endif /* CONFIG_CPU_FREQ_GOV_SCHEDUTIL */
 
 #ifdef CONFIG_HAVE_SCHED_AVG_IRQ
 static inline unsigned long cpu_util_irq(struct rq *rq)

kernel/sched/topology.c

@@ -1344,11 +1344,6 @@ sd_init(struct sched_domain_topology_level *tl,
 		.imbalance_pct		= 125,
 
 		.cache_nice_tries	= 0,
-		.busy_idx		= 0,
-		.idle_idx		= 0,
-		.newidle_idx		= 0,
-		.wake_idx		= 0,
-		.forkexec_idx		= 0,
 
 		.flags			= 1*SD_LOAD_BALANCE
 					| 1*SD_BALANCE_NEWIDLE
@@ -1400,13 +1395,10 @@ sd_init(struct sched_domain_topology_level *tl,
 	} else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
 		sd->imbalance_pct = 117;
 		sd->cache_nice_tries = 1;
-		sd->busy_idx = 2;
 
 #ifdef CONFIG_NUMA
 	} else if (sd->flags & SD_NUMA) {
 		sd->cache_nice_tries = 2;
-		sd->busy_idx = 3;
-		sd->idle_idx = 2;
 
 		sd->flags &= ~SD_PREFER_SIBLING;
 		sd->flags |= SD_SERIALIZE;
@@ -1419,8 +1411,6 @@ sd_init(struct sched_domain_topology_level *tl,
 #endif
 	} else {
 		sd->cache_nice_tries = 1;
-		sd->busy_idx = 2;
-		sd->idle_idx = 1;
 	}
 
 	/*
@@ -1884,10 +1874,10 @@ static struct sched_domain_topology_level
 	unsigned long cap;
 
 	/* Is there any asymmetry? */
-	cap = arch_scale_cpu_capacity(NULL, cpumask_first(cpu_map));
+	cap = arch_scale_cpu_capacity(cpumask_first(cpu_map));
 
 	for_each_cpu(i, cpu_map) {
-		if (arch_scale_cpu_capacity(NULL, i) != cap) {
+		if (arch_scale_cpu_capacity(i) != cap) {
 			asym = true;
 			break;
 		}
@@ -1902,7 +1892,7 @@ static struct sched_domain_topology_level
 	 * to everyone.
 	 */
 	for_each_cpu(i, cpu_map) {
-		unsigned long max_capacity = arch_scale_cpu_capacity(NULL, i);
+		unsigned long max_capacity = arch_scale_cpu_capacity(i);
 		int tl_id = 0;
 
 		for_each_sd_topology(tl) {
@@ -1912,7 +1902,7 @@ static struct sched_domain_topology_level
 			for_each_cpu_and(j, tl->mask(i), cpu_map) {
 				unsigned long capacity;
 
-				capacity = arch_scale_cpu_capacity(NULL, j);
+				capacity = arch_scale_cpu_capacity(j);
 
 				if (capacity <= max_capacity)
 					continue;

kernel/sched/wait.c

@@ -118,16 +118,12 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
 	bookmark.func = NULL;
 	INIT_LIST_HEAD(&bookmark.entry);
 
-	spin_lock_irqsave(&wq_head->lock, flags);
-	nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key, &bookmark);
-	spin_unlock_irqrestore(&wq_head->lock, flags);
-
-	while (bookmark.flags & WQ_FLAG_BOOKMARK) {
+	do {
 		spin_lock_irqsave(&wq_head->lock, flags);
 		nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive,
 						wake_flags, key, &bookmark);
 		spin_unlock_irqrestore(&wq_head->lock, flags);
-	}
+	} while (bookmark.flags & WQ_FLAG_BOOKMARK);
 }
 
 /**

kernel/sysctl.c

@@ -452,6 +452,22 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= sched_rr_handler,
 	},
+#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,
+	},
+#endif
 #ifdef CONFIG_SCHED_AUTOGROUP
 	{
 		.procname	= "sched_autogroup_enabled",

kernel/time/tick-sched.c

@@ -782,7 +782,6 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu)
 	 */
 	if (!ts->tick_stopped) {
 		calc_load_nohz_start();
-		cpu_load_update_nohz_start();
 		quiet_vmstat();
 
 		ts->last_tick = hrtimer_get_expires(&ts->sched_timer);
@@ -829,7 +828,6 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now)
 {
 	/* Update jiffies first */
 	tick_do_update_jiffies64(now);
-	cpu_load_update_nohz_stop();
 
 	/*
 	 * Clear the timer idle flag, so we avoid IPIs on remote queueing and

kernel/trace/trace_hwlat.c

@@ -277,7 +277,7 @@ static void move_to_next_cpu(void)
 	 * of this thread, than stop migrating for the duration
 	 * of the current test.
 	 */
-	if (!cpumask_equal(current_mask, &current->cpus_allowed))
+	if (!cpumask_equal(current_mask, current->cpus_ptr))
 		goto disable;
 
 	get_online_cpus();