1 files changed, 103 insertions, 63 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 79f574dba096..2f0a0be4d344 100644
--- a/kernel/sched/fair.c
+++ b/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);
@@ -3941,18 +3982,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 	if (!sched_feat(UTIL_EST))
 		return;
 
-	/*
-	 * Update root cfs_rq's estimated utilization
-	 *
-	 * If *p is the last task then the root cfs_rq's estimated utilization
-	 * of a CPU is 0 by definition.
-	 */
-	ue.enqueued = 0;
-	if (cfs_rq->nr_running) {
-		ue.enqueued  = cfs_rq->avg.util_est.enqueued;
-		ue.enqueued -= min_t(unsigned int, ue.enqueued,
-				     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
-	}
+	/* Update root cfs_rq's estimated utilization */
+	ue.enqueued  = cfs_rq->avg.util_est.enqueued;
+	ue.enqueued -= min_t(unsigned int, ue.enqueued,
+			     (_task_util_est(p) | UTIL_AVG_UNCHANGED));
 	WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
 
 	/*
@@ -4549,6 +4582,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
 	now = sched_clock_cpu(smp_processor_id());
 	cfs_b->runtime = cfs_b->quota;
 	cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
+	cfs_b->expires_seq++;
 }
 
 static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4571,6 +4605,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	struct task_group *tg = cfs_rq->tg;
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
 	u64 amount = 0, min_amount, expires;
+	int expires_seq;
 
 	/* note: this is a positive sum as runtime_remaining <= 0 */
 	min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4587,6 +4622,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 			cfs_b->idle = 0;
 		}
 	}
+	expires_seq = cfs_b->expires_seq;
 	expires = cfs_b->runtime_expires;
 	raw_spin_unlock(&cfs_b->lock);
 
@@ -4596,8 +4632,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	 * spread between our sched_clock and the one on which runtime was
 	 * issued.
 	 */
-	if ((s64)(expires - cfs_rq->runtime_expires) > 0)
+	if (cfs_rq->expires_seq != expires_seq) {
+		cfs_rq->expires_seq = expires_seq;
 		cfs_rq->runtime_expires = expires;
+	}
 
 	return cfs_rq->runtime_remaining > 0;
 }
@@ -4623,12 +4661,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	 * has not truly expired.
 	 *
 	 * Fortunately we can check determine whether this the case by checking
-	 * whether the global deadline has advanced. It is valid to compare
-	 * cfs_b->runtime_expires without any locks since we only care about
-	 * exact equality, so a partial write will still work.
+	 * whether the global deadline(cfs_b->expires_seq) has advanced.
 	 */
-
-	if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
+	if (cfs_rq->expires_seq == cfs_b->expires_seq) {
 		/* extend local deadline, drift is bounded above by 2 ticks */
 		cfs_rq->runtime_expires += TICK_NSEC;
 	} else {
@@ -5161,13 +5196,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 
 void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 {
+	u64 overrun;
+
 	lockdep_assert_held(&cfs_b->lock);
 
-	if (!cfs_b->period_active) {
-		cfs_b->period_active = 1;
-		hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
-		hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
-	}
+	if (cfs_b->period_active)
+		return;
+
+	cfs_b->period_active = 1;
+	overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+	cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
+	cfs_b->expires_seq++;
+	hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
@@ -5345,6 +5385,14 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	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
 	 * passed.
@@ -5385,7 +5433,6 @@ 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 +5905,8 @@ 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 +6149,7 @@ 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 +6191,13 @@ 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 +6278,7 @@ void __update_idle_core(struct rq *rq)
 		if (cpu == core)
 			continue;
 
-		if (!idle_cpu(cpu))
+		if (!available_idle_cpu(cpu))
 			goto unlock;
 	}
 
@@ -6256,7 +6310,7 @@ 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 +6339,7 @@ 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 +6402,7 @@ 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 +6422,13 @@ 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 +6436,7 @@ 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 +6612,7 @@ 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 +6635,10 @@ 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;
 		}
 
@@ -6591,33 +6648,16 @@ 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);
+		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);
+		if (want_affine)
+			current->recent_used_cpu = cpu;
 	}
 	rcu_read_unlock();
 
@@ -10174,10 +10214,10 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	struct cfs_rq *cfs_rq;
 	int i;
 
-	tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL);
+	tg->cfs_rq = kcalloc(nr_cpu_ids, sizeof(cfs_rq), GFP_KERNEL);
 	if (!tg->cfs_rq)
 		goto err;
-	tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL);
+	tg->se = kcalloc(nr_cpu_ids, sizeof(se), GFP_KERNEL);
 	if (!tg->se)
 		goto err;