Merge tag 'sched-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Improve uclamp performance by using a static key for the fast path

 - Add the "sched_util_clamp_min_rt_default" sysctl, to optimize for
   better power efficiency of RT tasks on battery powered devices.
   (The default is to maximize performance & reduce RT latencies.)

 - Improve utime and stime tracking accuracy, which had a fixed boundary
   of error, which created larger and larger relative errors as the
   values become larger. This is now replaced with more precise
   arithmetics, using the new mul_u64_u64_div_u64() helper in math64.h.

 - Improve the deadline scheduler, such as making it capacity aware

 - Improve frequency-invariant scheduling

 - Misc cleanups in energy/power aware scheduling

 - Add sched_update_nr_running tracepoint to track changes to nr_running

 - Documentation additions and updates

 - Misc cleanups and smaller fixes

* tag 'sched-core-2020-08-03' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  sched/doc: Factorize bits between sched-energy.rst & sched-capacity.rst
  sched/doc: Document capacity aware scheduling
  sched: Document arch_scale_*_capacity()
  arm, arm64: Fix selection of CONFIG_SCHED_THERMAL_PRESSURE
  Documentation/sysctl: Document uclamp sysctl knobs
  sched/uclamp: Add a new sysctl to control RT default boost value
  sched/uclamp: Fix a deadlock when enabling uclamp static key
  sched: Remove duplicated tick_nohz_full_enabled() check
  sched: Fix a typo in a comment
  sched/uclamp: Remove unnecessary mutex_init()
  arm, arm64: Select CONFIG_SCHED_THERMAL_PRESSURE
  sched: Cleanup SCHED_THERMAL_PRESSURE kconfig entry
  arch_topology, sched/core: Cleanup thermal pressure definition
  trace/events/sched.h: fix duplicated word
  linux/sched/mm.h: drop duplicated words in comments
  smp: Fix a potential usage of stale nr_cpus
  sched/fair: update_pick_idlest() Select group with lowest group_util when idle_cpus are equal
  sched: nohz: stop passing around unused "ticks" parameter.
  sched: Better document ttwu()
  sched: Add a tracepoint to track rq->nr_running
  ...

1 files changed, 95 insertions, 23 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f63f337c7147..3862a28cd05d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -54,15 +54,49 @@ static inline struct dl_bw *dl_bw_of(int i)
 static inline int dl_bw_cpus(int i)
 {
 	struct root_domain *rd = cpu_rq(i)->rd;
-	int cpus = 0;
+	int cpus;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
 			 "sched RCU must be held");
+
+	if (cpumask_subset(rd->span, cpu_active_mask))
+		return cpumask_weight(rd->span);
+
+	cpus = 0;
+
 	for_each_cpu_and(i, rd->span, cpu_active_mask)
 		cpus++;
 
 	return cpus;
 }
+
+static inline unsigned long __dl_bw_capacity(int i)
+{
+	struct root_domain *rd = cpu_rq(i)->rd;
+	unsigned long cap = 0;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
+			 "sched RCU must be held");
+
+	for_each_cpu_and(i, rd->span, cpu_active_mask)
+		cap += capacity_orig_of(i);
+
+	return cap;
+}
+
+/*
+ * XXX Fix: If 'rq->rd == def_root_domain' perform AC against capacity
+ * of the CPU the task is running on rather rd's \Sum CPU capacity.
+ */
+static inline unsigned long dl_bw_capacity(int i)
+{
+	if (!static_branch_unlikely(&sched_asym_cpucapacity) &&
+	    capacity_orig_of(i) == SCHED_CAPACITY_SCALE) {
+		return dl_bw_cpus(i) << SCHED_CAPACITY_SHIFT;
+	} else {
+		return __dl_bw_capacity(i);
+	}
+}
 #else
 static inline struct dl_bw *dl_bw_of(int i)
 {
@@ -73,6 +107,11 @@ static inline int dl_bw_cpus(int i)
 {
 	return 1;
 }
+
+static inline unsigned long dl_bw_capacity(int i)
+{
+	return SCHED_CAPACITY_SCALE;
+}
 #endif
 
 static inline
@@ -1098,7 +1137,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
  * cannot use the runtime, and so it replenishes the task. This rule
  * works fine for implicit deadline tasks (deadline == period), and the
  * CBS was designed for implicit deadline tasks. However, a task with
- * constrained deadline (deadine < period) might be awakened after the
+ * constrained deadline (deadline < period) might be awakened after the
  * deadline, but before the next period. In this case, replenishing the
  * task would allow it to run for runtime / deadline. As in this case
  * deadline < period, CBS enables a task to run for more than the
@@ -1604,6 +1643,7 @@ static int
 select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 {
 	struct task_struct *curr;
+	bool select_rq;
 	struct rq *rq;
 
 	if (sd_flag != SD_BALANCE_WAKE)
@@ -1623,10 +1663,19 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
 	 * other hand, if it has a shorter deadline, we
 	 * try to make it stay here, it might be important.
 	 */
-	if (unlikely(dl_task(curr)) &&
-	    (curr->nr_cpus_allowed < 2 ||
-	     !dl_entity_preempt(&p->dl, &curr->dl)) &&
-	    (p->nr_cpus_allowed > 1)) {
+	select_rq = unlikely(dl_task(curr)) &&
+		    (curr->nr_cpus_allowed < 2 ||
+		     !dl_entity_preempt(&p->dl, &curr->dl)) &&
+		    p->nr_cpus_allowed > 1;
+
+	/*
+	 * Take the capacity of the CPU into account to
+	 * ensure it fits the requirement of the task.
+	 */
+	if (static_branch_unlikely(&sched_asym_cpucapacity))
+		select_rq |= !dl_task_fits_capacity(p, cpu);
+
+	if (select_rq) {
 		int target = find_later_rq(p);
 
 		if (target != -1 &&
@@ -2430,8 +2479,8 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
 	}
 }
 
-const struct sched_class dl_sched_class = {
-	.next			= &rt_sched_class,
+const struct sched_class dl_sched_class
+	__attribute__((section("__dl_sched_class"))) = {
 	.enqueue_task		= enqueue_task_dl,
 	.dequeue_task		= dequeue_task_dl,
 	.yield_task		= yield_task_dl,
@@ -2551,11 +2600,12 @@ void sched_dl_do_global(void)
 int sched_dl_overflow(struct task_struct *p, int policy,
 		      const struct sched_attr *attr)
 {
-	struct dl_bw *dl_b = dl_bw_of(task_cpu(p));
 	u64 period = attr->sched_period ?: attr->sched_deadline;
 	u64 runtime = attr->sched_runtime;
 	u64 new_bw = dl_policy(policy) ? to_ratio(period, runtime) : 0;
-	int cpus, err = -1;
+	int cpus, err = -1, cpu = task_cpu(p);
+	struct dl_bw *dl_b = dl_bw_of(cpu);
+	unsigned long cap;
 
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return 0;
@@ -2570,15 +2620,17 @@ int sched_dl_overflow(struct task_struct *p, int policy,
 	 * allocated bandwidth of the container.
 	 */
 	raw_spin_lock(&dl_b->lock);
-	cpus = dl_bw_cpus(task_cpu(p));
+	cpus = dl_bw_cpus(cpu);
+	cap = dl_bw_capacity(cpu);
+
 	if (dl_policy(policy) && !task_has_dl_policy(p) &&
-	    !__dl_overflow(dl_b, cpus, 0, new_bw)) {
+	    !__dl_overflow(dl_b, cap, 0, new_bw)) {
 		if (hrtimer_active(&p->dl.inactive_timer))
 			__dl_sub(dl_b, p->dl.dl_bw, cpus);
 		__dl_add(dl_b, new_bw, cpus);
 		err = 0;
 	} else if (dl_policy(policy) && task_has_dl_policy(p) &&
-		   !__dl_overflow(dl_b, cpus, p->dl.dl_bw, new_bw)) {
+		   !__dl_overflow(dl_b, cap, p->dl.dl_bw, new_bw)) {
 		/*
 		 * XXX this is slightly incorrect: when the task
 		 * utilization decreases, we should delay the total
@@ -2635,6 +2687,14 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
 }
 
 /*
+ * Default limits for DL period; on the top end we guard against small util
+ * tasks still getting rediculous long effective runtimes, on the bottom end we
+ * guard against timer DoS.
+ */
+unsigned int sysctl_sched_dl_period_max = 1 << 22; /* ~4 seconds */
+unsigned int sysctl_sched_dl_period_min = 100;     /* 100 us */
+
+/*
  * This function validates the new parameters of a -deadline task.
  * We ask for the deadline not being zero, and greater or equal
  * than the runtime, as well as the period of being zero or
@@ -2646,6 +2706,8 @@ void __getparam_dl(struct task_struct *p, struct sched_attr *attr)
  */
 bool __checkparam_dl(const struct sched_attr *attr)
 {
+	u64 period, max, min;
+
 	/* special dl tasks don't actually use any parameter */
 	if (attr->sched_flags & SCHED_FLAG_SUGOV)
 		return true;
@@ -2669,12 +2731,21 @@ bool __checkparam_dl(const struct sched_attr *attr)
 	    attr->sched_period & (1ULL << 63))
 		return false;
 
+	period = attr->sched_period;
+	if (!period)
+		period = attr->sched_deadline;
+
 	/* runtime <= deadline <= period (if period != 0) */
-	if ((attr->sched_period != 0 &&
-	     attr->sched_period < attr->sched_deadline) ||
+	if (period < attr->sched_deadline ||
 	    attr->sched_deadline < attr->sched_runtime)
 		return false;
 
+	max = (u64)READ_ONCE(sysctl_sched_dl_period_max) * NSEC_PER_USEC;
+	min = (u64)READ_ONCE(sysctl_sched_dl_period_min) * NSEC_PER_USEC;
+
+	if (period < min || period > max)
+		return false;
+
 	return true;
 }
 
@@ -2715,19 +2786,19 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 #ifdef CONFIG_SMP
 int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed)
 {
+	unsigned long flags, cap;
 	unsigned int dest_cpu;
 	struct dl_bw *dl_b;
 	bool overflow;
-	int cpus, ret;
-	unsigned long flags;
+	int ret;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, cs_cpus_allowed);
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(dest_cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cpus = dl_bw_cpus(dest_cpu);
-	overflow = __dl_overflow(dl_b, cpus, 0, p->dl.dl_bw);
+	cap = dl_bw_capacity(dest_cpu);
+	overflow = __dl_overflow(dl_b, cap, 0, p->dl.dl_bw);
 	if (overflow) {
 		ret = -EBUSY;
 	} else {
@@ -2737,6 +2808,8 @@ int dl_task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allo
 		 * We will free resources in the source root_domain
 		 * later on (see set_cpus_allowed_dl()).
 		 */
+		int cpus = dl_bw_cpus(dest_cpu);
+
 		__dl_add(dl_b, p->dl.dl_bw, cpus);
 		ret = 0;
 	}
@@ -2769,16 +2842,15 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 
 bool dl_cpu_busy(unsigned int cpu)
 {
-	unsigned long flags;
+	unsigned long flags, cap;
 	struct dl_bw *dl_b;
 	bool overflow;
-	int cpus;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
-	cpus = dl_bw_cpus(cpu);
-	overflow = __dl_overflow(dl_b, cpus, 0, 0);
+	cap = dl_bw_capacity(cpu);
+	overflow = __dl_overflow(dl_b, cap, 0, 0);
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
 	rcu_read_unlock_sched();