1 files changed, 82 insertions, 49 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8a0e6bdba50d..dddaf61378f6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3824,7 +3824,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 		return;
 	}
 
-	rq->misfit_task_load = task_h_load(p);
+	/*
+	 * Make sure that misfit_task_load will not be null even if
+	 * task_h_load() returns 0.
+	 */
+	rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
 }
 
 #else /* CONFIG_SMP */
@@ -4379,16 +4383,16 @@ static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
 }
 
 /* returns 0 on failure to allocate runtime */
-static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+static int __assign_cfs_rq_runtime(struct cfs_bandwidth *cfs_b,
+				   struct cfs_rq *cfs_rq, u64 target_runtime)
 {
-	struct task_group *tg = cfs_rq->tg;
-	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
-	u64 amount = 0, min_amount;
+	u64 min_amount, amount = 0;
+
+	lockdep_assert_held(&cfs_b->lock);
 
 	/* note: this is a positive sum as runtime_remaining <= 0 */
-	min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
+	min_amount = target_runtime - cfs_rq->runtime_remaining;
 
-	raw_spin_lock(&cfs_b->lock);
 	if (cfs_b->quota == RUNTIME_INF)
 		amount = min_amount;
 	else {
@@ -4400,13 +4404,25 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 			cfs_b->idle = 0;
 		}
 	}
-	raw_spin_unlock(&cfs_b->lock);
 
 	cfs_rq->runtime_remaining += amount;
 
 	return cfs_rq->runtime_remaining > 0;
 }
 
+/* returns 0 on failure to allocate runtime */
+static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
+{
+	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
+	int ret;
+
+	raw_spin_lock(&cfs_b->lock);
+	ret = __assign_cfs_rq_runtime(cfs_b, cfs_rq, sched_cfs_bandwidth_slice());
+	raw_spin_unlock(&cfs_b->lock);
+
+	return ret;
+}
+
 static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
 {
 	/* dock delta_exec before expiring quota (as it could span periods) */
@@ -4495,13 +4511,33 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 	return 0;
 }
 
-static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
+static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	struct rq *rq = rq_of(cfs_rq);
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long task_delta, idle_task_delta, dequeue = 1;
-	bool empty;
+
+	raw_spin_lock(&cfs_b->lock);
+	/* This will start the period timer if necessary */
+	if (__assign_cfs_rq_runtime(cfs_b, cfs_rq, 1)) {
+		/*
+		 * We have raced with bandwidth becoming available, and if we
+		 * actually throttled the timer might not unthrottle us for an
+		 * entire period. We additionally needed to make sure that any
+		 * subsequent check_cfs_rq_runtime calls agree not to throttle
+		 * us, as we may commit to do cfs put_prev+pick_next, so we ask
+		 * for 1ns of runtime rather than just check cfs_b.
+		 */
+		dequeue = 0;
+	} else {
+		list_add_tail_rcu(&cfs_rq->throttled_list,
+				  &cfs_b->throttled_cfs_rq);
+	}
+	raw_spin_unlock(&cfs_b->lock);
+
+	if (!dequeue)
+		return false;  /* Throttle no longer required. */
 
 	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
 
@@ -4530,29 +4566,13 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	if (!se)
 		sub_nr_running(rq, task_delta);
 
-	cfs_rq->throttled = 1;
-	cfs_rq->throttled_clock = rq_clock(rq);
-	raw_spin_lock(&cfs_b->lock);
-	empty = list_empty(&cfs_b->throttled_cfs_rq);
-
-	/*
-	 * Add to the _head_ of the list, so that an already-started
-	 * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
-	 * not running add to the tail so that later runqueues don't get starved.
-	 */
-	if (cfs_b->distribute_running)
-		list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-	else
-		list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
-
 	/*
-	 * If we're the first throttled task, make sure the bandwidth
-	 * timer is running.
+	 * Note: distribution will already see us throttled via the
+	 * throttled-list.  rq->lock protects completion.
 	 */
-	if (empty)
-		start_cfs_bandwidth(cfs_b);
-
-	raw_spin_unlock(&cfs_b->lock);
+	cfs_rq->throttled = 1;
+	cfs_rq->throttled_clock = rq_clock(rq);
+	return true;
 }
 
 void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
@@ -4911,8 +4931,7 @@ static bool check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	if (cfs_rq_throttled(cfs_rq))
 		return true;
 
-	throttle_cfs_rq(cfs_rq);
-	return true;
+	return throttle_cfs_rq(cfs_rq);
 }
 
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
@@ -4942,6 +4961,8 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 		if (!overrun)
 			break;
 
+		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
+
 		if (++count > 3) {
 			u64 new, old = ktime_to_ns(cfs_b->period);
 
@@ -4971,8 +4992,6 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
 			/* reset count so we don't come right back in here */
 			count = 0;
 		}
-
-		idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
 	}
 	if (idle)
 		cfs_b->period_active = 0;
@@ -5917,7 +5936,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
 /*
  * Scan the local SMT mask for idle CPUs.
  */
-static int select_idle_smt(struct task_struct *p, int target)
+static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	int cpu, si_cpu = -1;
 
@@ -5925,7 +5944,8 @@ static int select_idle_smt(struct task_struct *p, int target)
 		return -1;
 
 	for_each_cpu(cpu, cpu_smt_mask(target)) {
-		if (!cpumask_test_cpu(cpu, p->cpus_ptr))
+		if (!cpumask_test_cpu(cpu, p->cpus_ptr) ||
+		    !cpumask_test_cpu(cpu, sched_domain_span(sd)))
 			continue;
 		if (available_idle_cpu(cpu))
 			return cpu;
@@ -5943,7 +5963,7 @@ static inline int select_idle_core(struct task_struct *p, struct sched_domain *s
 	return -1;
 }
 
-static inline int select_idle_smt(struct task_struct *p, int target)
+static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
 }
@@ -6053,7 +6073,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
-	i = select_idle_smt(p, target);
+	i = select_idle_smt(p, sd, target);
 	if ((unsigned)i < nr_cpumask_bits)
 		return i;
 
@@ -7407,7 +7427,15 @@ static int detach_tasks(struct lb_env *env)
 		if (!can_migrate_task(p, env))
 			goto next;
 
-		load = task_h_load(p);
+		/*
+		 * Depending of the number of CPUs and tasks and the
+		 * cgroup hierarchy, task_h_load() can return a null
+		 * value. Make sure that env->imbalance decreases
+		 * otherwise detach_tasks() will stop only after
+		 * detaching up to loop_max tasks.
+		 */
+		load = max_t(unsigned long, task_h_load(p), 1);
+
 
 		if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
 			goto next;
@@ -9373,7 +9401,12 @@ static void kick_ilb(unsigned int flags)
 {
 	int ilb_cpu;
 
-	nohz.next_balance++;
+	/*
+	 * Increase nohz.next_balance only when if full ilb is triggered but
+	 * not if we only update stats.
+	 */
+	if (flags & NOHZ_BALANCE_KICK)
+		nohz.next_balance = jiffies+1;
 
 	ilb_cpu = find_new_ilb();
 
@@ -9691,6 +9724,14 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
 		}
 	}
 
+	/*
+	 * next_balance will be updated only when there is a need.
+	 * When the CPU is attached to null domain for ex, it will not be
+	 * updated.
+	 */
+	if (likely(update_next_balance))
+		nohz.next_balance = next_balance;
+
 	/* Newly idle CPU doesn't need an update */
 	if (idle != CPU_NEWLY_IDLE) {
 		update_blocked_averages(this_cpu);
@@ -9711,14 +9752,6 @@ abort:
 	if (has_blocked_load)
 		WRITE_ONCE(nohz.has_blocked, 1);
 
-	/*
-	 * next_balance will be updated only when there is a need.
-	 * When the CPU is attached to null domain for ex, it will not be
-	 * updated.
-	 */
-	if (likely(update_next_balance))
-		nohz.next_balance = next_balance;
-
 	return ret;
 }