1 files changed, 163 insertions, 88 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b5743d5b0..4309c8e76 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -715,6 +715,11 @@ void init_entity_runnable_average(struct sched_entity *se)
 	/* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
 }
 
+static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
+static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq);
+static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force);
+static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
 /*
  * With new tasks being created, their initial util_avgs are extrapolated
  * based on the cfs_rq's current util_avg:
@@ -745,6 +750,8 @@ void post_init_entity_util_avg(struct sched_entity *se)
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct sched_avg *sa = &se->avg;
 	long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+	u64 now = cfs_rq_clock_task(cfs_rq);
+	int tg_update;
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
@@ -758,16 +765,42 @@ void post_init_entity_util_avg(struct sched_entity *se)
 		}
 		sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
 	}
+
+	if (entity_is_task(se)) {
+		struct task_struct *p = task_of(se);
+		if (p->sched_class != &fair_sched_class) {
+			/*
+			 * For !fair tasks do:
+			 *
+			update_cfs_rq_load_avg(now, cfs_rq, false);
+			attach_entity_load_avg(cfs_rq, se);
+			switched_from_fair(rq, p);
+			 *
+			 * such that the next switched_to_fair() has the
+			 * expected state.
+			 */
+			se->avg.last_update_time = now;
+			return;
+		}
+	}
+
+	tg_update = update_cfs_rq_load_avg(now, cfs_rq, false);
+	attach_entity_load_avg(cfs_rq, se);
+	if (tg_update)
+		update_tg_load_avg(cfs_rq, false);
 }
 
-#else
+#else /* !CONFIG_SMP */
 void init_entity_runnable_average(struct sched_entity *se)
 {
 }
 void post_init_entity_util_avg(struct sched_entity *se)
 {
 }
-#endif
+static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
+{
+}
+#endif /* CONFIG_SMP */
 
 /*
  * Update the current task's runtime statistics.
@@ -1328,6 +1361,8 @@ static void task_numa_assign(struct task_numa_env *env,
 {
 	if (env->best_task)
 		put_task_struct(env->best_task);
+	if (p)
+		get_task_struct(p);
 
 	env->best_task = p;
 	env->best_imp = imp;
@@ -1395,31 +1430,11 @@ static void task_numa_compare(struct task_numa_env *env,
 	long imp = env->p->numa_group ? groupimp : taskimp;
 	long moveimp = imp;
 	int dist = env->dist;
-	bool assigned = false;
 
 	rcu_read_lock();
-
-	raw_spin_lock_irq(&dst_rq->lock);
-	cur = dst_rq->curr;
-	/*
-	 * No need to move the exiting task or idle task.
-	 */
-	if ((cur->flags & PF_EXITING) || is_idle_task(cur))
+	cur = task_rcu_dereference(&dst_rq->curr);
+	if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
 		cur = NULL;
-	else {
-		/*
-		 * The task_struct must be protected here to protect the
-		 * p->numa_faults access in the task_weight since the
-		 * numa_faults could already be freed in the following path:
-		 * finish_task_switch()
-		 *     --> put_task_struct()
-		 *         --> __put_task_struct()
-		 *             --> task_numa_free()
-		 */
-		get_task_struct(cur);
-	}
-
-	raw_spin_unlock_irq(&dst_rq->lock);
 
 	/*
 	 * Because we have preemption enabled we can get migrated around and
@@ -1502,7 +1517,6 @@ balance:
 		 */
 		if (!load_too_imbalanced(src_load, dst_load, env)) {
 			imp = moveimp - 1;
-			put_task_struct(cur);
 			cur = NULL;
 			goto assign;
 		}
@@ -1528,16 +1542,9 @@ balance:
 		env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
 
 assign:
-	assigned = true;
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
-	/*
-	 * The dst_rq->curr isn't assigned. The protection for task_struct is
-	 * finished.
-	 */
-	if (cur && !assigned)
-		put_task_struct(cur);
 }
 
 static void task_numa_find_cpu(struct task_numa_env *env,
@@ -2891,8 +2898,6 @@ void set_task_rq_fair(struct sched_entity *se,
 static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {}
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq);
-
 static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
@@ -2939,7 +2944,23 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq)
 	WRITE_ONCE(*ptr, res);					\
 } while (0)
 
-/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
+/**
+ * update_cfs_rq_load_avg - update the cfs_rq's load/util averages
+ * @now: current time, as per cfs_rq_clock_task()
+ * @cfs_rq: cfs_rq to update
+ * @update_freq: should we call cfs_rq_util_change() or will the call do so
+ *
+ * The cfs_rq avg is the direct sum of all its entities (blocked and runnable)
+ * avg. The immediate corollary is that all (fair) tasks must be attached, see
+ * post_init_entity_util_avg().
+ *
+ * cfs_rq->avg is used for task_h_load() and update_cfs_share() for example.
+ *
+ * Returns true if the load decayed or we removed utilization. It is expected
+ * that one calls update_tg_load_avg() on this condition, but after you've
+ * modified the cfs_rq avg (attach/detach), such that we propagate the new
+ * avg up.
+ */
 static inline int
 update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
 {
@@ -2994,6 +3015,14 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg)
 		update_tg_load_avg(cfs_rq, 0);
 }
 
+/**
+ * attach_entity_load_avg - attach this entity to its cfs_rq load avg
+ * @cfs_rq: cfs_rq to attach to
+ * @se: sched_entity to attach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
 static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	if (!sched_feat(ATTACH_AGE_LOAD))
@@ -3002,6 +3031,8 @@ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
 	/*
 	 * If we got migrated (either between CPUs or between cgroups) we'll
 	 * have aged the average right before clearing @last_update_time.
+	 *
+	 * Or we're fresh through post_init_entity_util_avg().
 	 */
 	if (se->avg.last_update_time) {
 		__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
@@ -3023,6 +3054,14 @@ skip_aging:
 	cfs_rq_util_change(cfs_rq);
 }
 
+/**
+ * detach_entity_load_avg - detach this entity from its cfs_rq load avg
+ * @cfs_rq: cfs_rq to detach from
+ * @se: sched_entity to detach
+ *
+ * Must call update_cfs_rq_load_avg() before this, since we rely on
+ * cfs_rq->avg.last_update_time being current.
+ */
 static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	__update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)),
@@ -3107,11 +3146,14 @@ void remove_entity_load_avg(struct sched_entity *se)
 	u64 last_update_time;
 
 	/*
-	 * Newly created task or never used group entity should not be removed
-	 * from its (source) cfs_rq
+	 * tasks cannot exit without having gone through wake_up_new_task() ->
+	 * post_init_entity_util_avg() which will have added things to the
+	 * cfs_rq, so we can remove unconditionally.
+	 *
+	 * Similarly for groups, they will have passed through
+	 * post_init_entity_util_avg() before unregister_sched_fair_group()
+	 * calls this.
 	 */
-	if (se->avg.last_update_time == 0)
-		return;
 
 	last_update_time = cfs_rq_last_update_time(cfs_rq);
 
@@ -3134,6 +3176,12 @@ static int idle_balance(struct rq *this_rq);
 
 #else /* CONFIG_SMP */
 
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
+{
+	return 0;
+}
+
 static inline void update_load_avg(struct sched_entity *se, int not_used)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -3723,7 +3771,7 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 {
 	if (unlikely(cfs_rq->throttle_count))
-		return cfs_rq->throttled_clock_task;
+		return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time;
 
 	return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
 }
@@ -3861,13 +3909,11 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 	struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
 
 	cfs_rq->throttle_count--;
-#ifdef CONFIG_SMP
 	if (!cfs_rq->throttle_count) {
 		/* adjust cfs_rq_clock_task() */
 		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
 	}
-#endif
 
 	return 0;
 }
@@ -4220,26 +4266,6 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 	if (!cfs_bandwidth_used())
 		return;
 
-	/* Synchronize hierarchical throttle counter: */
-	if (unlikely(!cfs_rq->throttle_uptodate)) {
-		struct rq *rq = rq_of(cfs_rq);
-		struct cfs_rq *pcfs_rq;
-		struct task_group *tg;
-
-		cfs_rq->throttle_uptodate = 1;
-
-		/* Get closest up-to-date node, because leaves go first: */
-		for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
-			pcfs_rq = tg->cfs_rq[cpu_of(rq)];
-			if (pcfs_rq->throttle_uptodate)
-				break;
-		}
-		if (tg) {
-			cfs_rq->throttle_count = pcfs_rq->throttle_count;
-			cfs_rq->throttled_clock_task = rq_clock_task(rq);
-		}
-	}
-
 	/* an active group must be handled by the update_curr()->put() path */
 	if (!cfs_rq->runtime_enabled || cfs_rq->curr)
 		return;
@@ -4254,6 +4280,23 @@ static void check_enqueue_throttle(struct cfs_rq *cfs_rq)
 		throttle_cfs_rq(cfs_rq);
 }
 
+static void sync_throttle(struct task_group *tg, int cpu)
+{
+	struct cfs_rq *pcfs_rq, *cfs_rq;
+
+	if (!cfs_bandwidth_used())
+		return;
+
+	if (!tg->parent)
+		return;
+
+	cfs_rq = tg->cfs_rq[cpu];
+	pcfs_rq = tg->parent->cfs_rq[cpu];
+
+	cfs_rq->throttle_count = pcfs_rq->throttle_count;
+	cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+}
+
 /* conditionally throttle active cfs_rq's from put_prev_entity() */
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
@@ -4393,6 +4436,7 @@ static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec) {}
 static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq) { return false; }
 static void check_enqueue_throttle(struct cfs_rq *cfs_rq) {}
+static inline void sync_throttle(struct task_group *tg, int cpu) {}
 static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) {}
 
 static inline int cfs_rq_throttled(struct cfs_rq *cfs_rq)
@@ -4501,7 +4545,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		 *
 		 * note: in the case of encountering a throttled cfs_rq we will
 		 * post the final h_nr_running increment below.
-		*/
+		 */
 		if (cfs_rq_throttled(cfs_rq))
 			break;
 		cfs_rq->h_nr_running++;
@@ -8342,31 +8386,17 @@ static void task_fork_fair(struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq;
 	struct sched_entity *se = &p->se, *curr;
-	int this_cpu = smp_processor_id();
 	struct rq *rq = this_rq();
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&rq->lock, flags);
 
+	raw_spin_lock(&rq->lock);
 	update_rq_clock(rq);
 
 	cfs_rq = task_cfs_rq(current);
 	curr = cfs_rq->curr;
-
-	/*
-	 * Not only the cpu but also the task_group of the parent might have
-	 * been changed after parent->se.parent,cfs_rq were copied to
-	 * child->se.parent,cfs_rq. So call __set_task_cpu() to make those
-	 * of child point to valid ones.
-	 */
-	rcu_read_lock();
-	__set_task_cpu(p, this_cpu);
-	rcu_read_unlock();
-
-	update_curr(cfs_rq);
-
-	if (curr)
+	if (curr) {
+		update_curr(cfs_rq);
 		se->vruntime = curr->vruntime;
+	}
 	place_entity(cfs_rq, se, 1);
 
 	if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
@@ -8379,8 +8409,7 @@ static void task_fork_fair(struct task_struct *p)
 	}
 
 	se->vruntime -= cfs_rq->min_vruntime;
-
-	raw_spin_unlock_irqrestore(&rq->lock, flags);
+	raw_spin_unlock(&rq->lock);
 }
 
 /*
@@ -8436,6 +8465,8 @@ static void detach_task_cfs_rq(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 now = cfs_rq_clock_task(cfs_rq);
+	int tg_update;
 
 	if (!vruntime_normalized(p)) {
 		/*
@@ -8447,13 +8478,18 @@ static void detach_task_cfs_rq(struct task_struct *p)
 	}
 
 	/* Catch up with the cfs_rq and remove our load when we leave */
+	tg_update = update_cfs_rq_load_avg(now, cfs_rq, false);
 	detach_entity_load_avg(cfs_rq, se);
+	if (tg_update)
+		update_tg_load_avg(cfs_rq, false);
 }
 
 static void attach_task_cfs_rq(struct task_struct *p)
 {
 	struct sched_entity *se = &p->se;
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
+	u64 now = cfs_rq_clock_task(cfs_rq);
+	int tg_update;
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	/*
@@ -8464,7 +8500,10 @@ static void attach_task_cfs_rq(struct task_struct *p)
 #endif
 
 	/* Synchronize task with its cfs_rq */
+	tg_update = update_cfs_rq_load_avg(now, cfs_rq, false);
 	attach_entity_load_avg(cfs_rq, se);
+	if (tg_update)
+		update_tg_load_avg(cfs_rq, false);
 
 	if (!vruntime_normalized(p))
 		se->vruntime += cfs_rq->min_vruntime;
@@ -8524,6 +8563,14 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
+static void task_set_group_fair(struct task_struct *p)
+{
+	struct sched_entity *se = &p->se;
+
+	set_task_rq(p, task_cpu(p));
+	se->depth = se->parent ? se->parent->depth + 1 : 0;
+}
+
 static void task_move_group_fair(struct task_struct *p)
 {
 	detach_task_cfs_rq(p);
@@ -8536,6 +8583,19 @@ static void task_move_group_fair(struct task_struct *p)
 	attach_task_cfs_rq(p);
 }
 
+static void task_change_group_fair(struct task_struct *p, int type)
+{
+	switch (type) {
+	case TASK_SET_GROUP:
+		task_set_group_fair(p);
+		break;
+
+	case TASK_MOVE_GROUP:
+		task_move_group_fair(p);
+		break;
+	}
+}
+
 void free_fair_sched_group(struct task_group *tg)
 {
 	int i;
@@ -8587,10 +8647,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 		init_cfs_rq(cfs_rq);
 		init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]);
 		init_entity_runnable_average(se);
-
-		raw_spin_lock_irq(&rq->lock);
-		post_init_entity_util_avg(se);
-		raw_spin_unlock_irq(&rq->lock);
 	}
 
 	return 1;
@@ -8601,6 +8657,23 @@ err:
 	return 0;
 }
 
+void online_fair_sched_group(struct task_group *tg)
+{
+	struct sched_entity *se;
+	struct rq *rq;
+	int i;
+
+	for_each_possible_cpu(i) {
+		rq = cpu_rq(i);
+		se = tg->se[i];
+
+		raw_spin_lock_irq(&rq->lock);
+		post_init_entity_util_avg(se);
+		sync_throttle(tg, i);
+		raw_spin_unlock_irq(&rq->lock);
+	}
+}
+
 void unregister_fair_sched_group(struct task_group *tg)
 {
 	unsigned long flags;
@@ -8705,6 +8778,8 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent)
 	return 1;
 }
 
+void online_fair_sched_group(struct task_group *tg) { }
+
 void unregister_fair_sched_group(struct task_group *tg) { }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -8764,7 +8839,7 @@ const struct sched_class fair_sched_class = {
 	.update_curr		= update_curr_fair,
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-	.task_move_group	= task_move_group_fair,
+	.task_change_group	= task_change_group_fair,
 #endif
 };