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

Pull scheduler updates from Ingo Molnar:

 - power-aware scheduling improvements (Patrick Bellasi)

 - NUMA balancing improvements (Mel Gorman)

 - vCPU scheduling fixes (Rohit Jain)

* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/fair: Update util_est before updating schedutil
  sched/cpufreq: Modify aggregate utilization to always include blocked FAIR utilization
  sched/deadline/Documentation: Add overrun signal and GRUB-PA documentation
  sched/core: Distinguish between idle_cpu() calls based on desired effect, introduce available_idle_cpu()
  sched/wait: Include <linux/wait.h> in <linux/swait.h>
  sched/numa: Stagger NUMA balancing scan periods for new threads
  sched/core: Don't schedule threads on pre-empted vCPUs
  sched/fair: Avoid calling sync_entity_load_avg() unnecessarily
  sched/fair: Rearrange select_task_rq_fair() to optimize it

Documentation/scheduler/sched-deadline.txt

@@ -49,7 +49,7 @@ CONTENTS
 2.1 Main algorithm
 ------------------
 
- SCHED_DEADLINE uses three parameters, named "runtime", "period", and
+ SCHED_DEADLINE [18] uses three parameters, named "runtime", "period", and
  "deadline", to schedule tasks. A SCHED_DEADLINE task should receive
  "runtime" microseconds of execution time every "period" microseconds, and
  these "runtime" microseconds are available within "deadline" microseconds
@@ -117,6 +117,10 @@ CONTENTS
          scheduling deadline = scheduling deadline + period
          remaining runtime = remaining runtime + runtime
 
+ The SCHED_FLAG_DL_OVERRUN flag in sched_attr's sched_flags field allows a task
+ to get informed about runtime overruns through the delivery of SIGXCPU
+ signals.
+
 
 2.2 Bandwidth reclaiming
 ------------------------
@@ -279,6 +283,19 @@ CONTENTS
     running_bw is incremented.
 
 
+2.3 Energy-aware scheduling
+------------------------
+
+ When cpufreq's schedutil governor is selected, SCHED_DEADLINE implements the
+ GRUB-PA [19] algorithm, reducing the CPU operating frequency to the minimum
+ value that still allows to meet the deadlines. This behavior is currently
+ implemented only for ARM architectures.
+
+ A particular care must be taken in case the time needed for changing frequency
+ is of the same order of magnitude of the reservation period. In such cases,
+ setting a fixed CPU frequency results in a lower amount of deadline misses.
+
+
 3. Scheduling Real-Time Tasks
 =============================
 
@@ -505,6 +522,12 @@ CONTENTS
   17 - L. Abeni, G. Lipari, A. Parri, Y. Sun, Multicore CPU reclaiming: parallel
        or sequential?. In Proceedings of the 31st Annual ACM Symposium on Applied
        Computing, 2016.
+  18 - J. Lelli, C. Scordino, L. Abeni, D. Faggioli, Deadline scheduling in the
+       Linux kernel, Software: Practice and Experience, 46(6): 821-839, June
+       2016.
+  19 - C. Scordino, L. Abeni, J. Lelli, Energy-Aware Real-Time Scheduling in
+       the Linux Kernel, 33rd ACM/SIGAPP Symposium On Applied Computing (SAC
+       2018), Pau, France, April 2018.
 
 
 4. Bandwidth management

include/linux/sched.h

@@ -1512,6 +1512,7 @@ static inline int task_nice(const struct task_struct *p)
 extern int can_nice(const struct task_struct *p, const int nice);
 extern int task_curr(const struct task_struct *p);
 extern int idle_cpu(int cpu);
+extern int available_idle_cpu(int cpu);
 extern int sched_setscheduler(struct task_struct *, int, const struct sched_param *);
 extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *);
 extern int sched_setattr(struct task_struct *, const struct sched_attr *);

include/linux/swait.h

@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/stddef.h>
 #include <linux/spinlock.h>
+#include <linux/wait.h>
 #include <asm/current.h>
 
 /*

kernel/sched/core.c

@@ -2194,27 +2194,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	INIT_HLIST_HEAD(&p->preempt_notifiers);
 #endif
 
-#ifdef CONFIG_NUMA_BALANCING
-	if (p->mm && atomic_read(&p->mm->mm_users) == 1) {
-		p->mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
-		p->mm->numa_scan_seq = 0;
-	}
-
-	if (clone_flags & CLONE_VM)
-		p->numa_preferred_nid = current->numa_preferred_nid;
-	else
-		p->numa_preferred_nid = -1;
-
-	p->node_stamp = 0ULL;
-	p->numa_scan_seq = p->mm ? p->mm->numa_scan_seq : 0;
-	p->numa_scan_period = sysctl_numa_balancing_scan_delay;
-	p->numa_work.next = &p->numa_work;
-	p->numa_faults = NULL;
-	p->last_task_numa_placement = 0;
-	p->last_sum_exec_runtime = 0;
-
-	p->numa_group = NULL;
-#endif /* CONFIG_NUMA_BALANCING */
+	init_numa_balancing(clone_flags, p);
 }
 
 DEFINE_STATIC_KEY_FALSE(sched_numa_balancing);
@@ -4049,6 +4029,23 @@ int idle_cpu(int cpu)
 	return 1;
 }
 
+/**
+ * available_idle_cpu - is a given CPU idle for enqueuing work.
+ * @cpu: the CPU in question.
+ *
+ * Return: 1 if the CPU is currently idle. 0 otherwise.
+ */
+int available_idle_cpu(int cpu)
+{
+	if (!idle_cpu(cpu))
+		return 0;
+
+	if (vcpu_is_preempted(cpu))
+		return 0;
+
+	return 1;
+}
+
 /**
  * idle_task - return the idle task for a given CPU.
  * @cpu: the processor in question.

kernel/sched/cpufreq_schedutil.c

@@ -183,22 +183,21 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util;
 
-	if (rq->rt.rt_nr_running) {
-		util = sg_cpu->max;
-	} else {
-		util = sg_cpu->util_dl;
-		if (rq->cfs.h_nr_running)
-			util += sg_cpu->util_cfs;
-	}
+	if (rq->rt.rt_nr_running)
+		return sg_cpu->max;
 
 	/*
+	 * Utilization required by DEADLINE must always be granted while, for
+	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
+	 * gracefully reduce the frequency when no tasks show up for longer
+	 * periods of time.
+	 *
 	 * Ideally we would like to set util_dl as min/guaranteed freq and
 	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
 	 * ready for such an interface. So, we only do the latter for now.
 	 */
-	return min(util, sg_cpu->max);
+	return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
 }
 
 static void sugov_set_iowait_boost(struct sugov_cpu *sg_cpu, u64 time, unsigned int flags)

kernel/sched/fair.c

@@ -1139,6 +1139,47 @@ static unsigned int task_scan_max(struct task_struct *p)
 	return max(smin, smax);
 }
 
+void init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+	int mm_users = 0;
+	struct mm_struct *mm = p->mm;
+
+	if (mm) {
+		mm_users = atomic_read(&mm->mm_users);
+		if (mm_users == 1) {
+			mm->numa_next_scan = jiffies + msecs_to_jiffies(sysctl_numa_balancing_scan_delay);
+			mm->numa_scan_seq = 0;
+		}
+	}
+	p->node_stamp			= 0;
+	p->numa_scan_seq		= mm ? mm->numa_scan_seq : 0;
+	p->numa_scan_period		= sysctl_numa_balancing_scan_delay;
+	p->numa_work.next		= &p->numa_work;
+	p->numa_faults			= NULL;
+	p->numa_group			= NULL;
+	p->last_task_numa_placement	= 0;
+	p->last_sum_exec_runtime	= 0;
+
+	/* New address space, reset the preferred nid */
+	if (!(clone_flags & CLONE_VM)) {
+		p->numa_preferred_nid = -1;
+		return;
+	}
+
+	/*
+	 * New thread, keep existing numa_preferred_nid which should be copied
+	 * already by arch_dup_task_struct but stagger when scans start.
+	 */
+	if (mm) {
+		unsigned int delay;
+
+		delay = min_t(unsigned int, task_scan_max(current),
+			current->numa_scan_period * mm_users * NSEC_PER_MSEC);
+		delay += 2 * TICK_NSEC;
+		p->node_stamp = delay;
+	}
+}
+
 static void account_numa_enqueue(struct rq *rq, struct task_struct *p)
 {
 	rq->nr_numa_running += (p->numa_preferred_nid != -1);
@@ -5344,6 +5385,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se;
 
+	/*
+	 * The code below (indirectly) updates schedutil which looks at
+	 * the cfs_rq utilization to select a frequency.
+	 * Let's add the task's estimated utilization to the cfs_rq's
+	 * estimated utilization, before we update schedutil.
+	 */
+	util_est_enqueue(&rq->cfs, p);
+
 	/*
 	 * If in_iowait is set, the code below may not trigger any cpufreq
 	 * utilization updates, so do it here explicitly with the IOWAIT flag
@@ -5385,7 +5434,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!se)
 		add_nr_running(rq, 1);
 
-	util_est_enqueue(&rq->cfs, p);
 	hrtick_update(rq);
 }
 
@@ -5858,8 +5906,8 @@ wake_affine_idle(int this_cpu, int prev_cpu, int sync)
 	 * a cpufreq perspective, it's better to have higher utilisation
 	 * on one CPU.
 	 */
-	if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
-		return idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
+	if (available_idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu))
+		return available_idle_cpu(prev_cpu) ? prev_cpu : this_cpu;
 
 	if (sync && cpu_rq(this_cpu)->nr_running == 1)
 		return this_cpu;
@@ -6102,7 +6150,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
 
 	/* Traverse only the allowed CPUs */
 	for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
-		if (idle_cpu(i)) {
+		if (available_idle_cpu(i)) {
 			struct rq *rq = cpu_rq(i);
 			struct cpuidle_state *idle = idle_get_state(rq);
 			if (idle && idle->exit_latency < min_exit_latency) {
@@ -6144,6 +6192,13 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 	if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
 		return prev_cpu;
 
+	/*
+	 * We need task's util for capacity_spare_wake, sync it up to prev_cpu's
+	 * last_update_time.
+	 */
+	if (!(sd_flag & SD_BALANCE_FORK))
+		sync_entity_load_avg(&p->se);
+
 	while (sd) {
 		struct sched_group *group;
 		struct sched_domain *tmp;
@@ -6224,7 +6279,7 @@ void __update_idle_core(struct rq *rq)
 		if (cpu == core)
 			continue;
 
-		if (!idle_cpu(cpu))
+		if (!available_idle_cpu(cpu))
 			goto unlock;
 	}
 
@@ -6256,7 +6311,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 
 		for_each_cpu(cpu, cpu_smt_mask(core)) {
 			cpumask_clear_cpu(cpu, cpus);
-			if (!idle_cpu(cpu))
+			if (!available_idle_cpu(cpu))
 				idle = false;
 		}
 
@@ -6285,7 +6340,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
-		if (idle_cpu(cpu))
+		if (available_idle_cpu(cpu))
 			return cpu;
 	}
 
@@ -6348,7 +6403,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 			return -1;
 		if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
 			continue;
-		if (idle_cpu(cpu))
+		if (available_idle_cpu(cpu))
 			break;
 	}
 
@@ -6368,13 +6423,13 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	struct sched_domain *sd;
 	int i, recent_used_cpu;
 
-	if (idle_cpu(target))
+	if (available_idle_cpu(target))
 		return target;
 
 	/*
 	 * If the previous CPU is cache affine and idle, don't be stupid:
 	 */
-	if (prev != target && cpus_share_cache(prev, target) && idle_cpu(prev))
+	if (prev != target && cpus_share_cache(prev, target) && available_idle_cpu(prev))
 		return prev;
 
 	/* Check a recently used CPU as a potential idle candidate: */
@@ -6382,7 +6437,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	if (recent_used_cpu != prev &&
 	    recent_used_cpu != target &&
 	    cpus_share_cache(recent_used_cpu, target) &&
-	    idle_cpu(recent_used_cpu) &&
+	    available_idle_cpu(recent_used_cpu) &&
 	    cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) {
 		/*
 		 * Replace recent_used_cpu with prev as it is a potential
@@ -6558,7 +6613,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
 static int
 select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
 {
-	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
+	struct sched_domain *tmp, *sd = NULL;
 	int cpu = smp_processor_id();
 	int new_cpu = prev_cpu;
 	int want_affine = 0;
@@ -6581,7 +6636,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 		 */
 		if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
 		    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
-			affine_sd = tmp;
+			if (cpu != prev_cpu)
+				new_cpu = wake_affine(tmp, p, cpu, prev_cpu, sync);
+
+			sd = NULL; /* Prefer wake_affine over balance flags */
 			break;
 		}
 
@@ -6591,34 +6649,17 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
 			break;
 	}
 
-	if (affine_sd) {
-		sd = NULL; /* Prefer wake_affine over balance flags */
-		if (cpu == prev_cpu)
-			goto pick_cpu;
-
-		new_cpu = wake_affine(affine_sd, p, cpu, prev_cpu, sync);
-	}
-
-	if (sd && !(sd_flag & SD_BALANCE_FORK)) {
-		/*
-		 * We're going to need the task's util for capacity_spare_wake
-		 * in find_idlest_group. Sync it up to prev_cpu's
-		 * last_update_time.
-		 */
-		sync_entity_load_avg(&p->se);
-	}
+	if (unlikely(sd)) {
+		/* Slow path */
+		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
+	} else if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
+		/* Fast path */
 
-	if (!sd) {
-pick_cpu:
-		if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
 		new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
 
 		if (want_affine)
 			current->recent_used_cpu = cpu;
 	}
-	} else {
-		new_cpu = find_idlest_cpu(sd, p, cpu, prev_cpu, sd_flag);
-	}
 	rcu_read_unlock();
 
 	return new_cpu;

kernel/sched/sched.h

@@ -1069,6 +1069,12 @@ enum numa_faults_stats {
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
 extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
+#else
+static inline void
+init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
+{
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #ifdef CONFIG_SMP