1 files changed, 106 insertions, 69 deletions

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c61a614465c8..f77f9c527449 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -113,6 +113,24 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
 unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
 #endif
 
+static inline void update_load_add(struct load_weight *lw, unsigned long inc)
+{
+	lw->weight += inc;
+	lw->inv_weight = 0;
+}
+
+static inline void update_load_sub(struct load_weight *lw, unsigned long dec)
+{
+	lw->weight -= dec;
+	lw->inv_weight = 0;
+}
+
+static inline void update_load_set(struct load_weight *lw, unsigned long w)
+{
+	lw->weight = w;
+	lw->inv_weight = 0;
+}
+
 /*
  * Increase the granularity value when there are more CPUs,
  * because with more CPUs the 'effective latency' as visible
@@ -662,6 +680,26 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	return calc_delta_fair(sched_slice(cfs_rq, se), se);
 }
 
+#ifdef CONFIG_SMP
+static inline void __update_task_entity_contrib(struct sched_entity *se);
+
+/* Give new task start runnable values to heavy its load in infant time */
+void init_task_runnable_average(struct task_struct *p)
+{
+	u32 slice;
+
+	p->se.avg.decay_count = 0;
+	slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
+	p->se.avg.runnable_avg_sum = slice;
+	p->se.avg.runnable_avg_period = slice;
+	__update_task_entity_contrib(&p->se);
+}
+#else
+void init_task_runnable_average(struct task_struct *p)
+{
+}
+#endif
+
 /*
  * Update the current task's runtime statistics. Skip current tasks that
  * are not in our scheduling class.
@@ -686,7 +724,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
 static void update_curr(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq->curr;
-	u64 now = rq_of(cfs_rq)->clock_task;
+	u64 now = rq_clock_task(rq_of(cfs_rq));
 	unsigned long delta_exec;
 
 	if (unlikely(!curr))
@@ -718,7 +756,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 static inline void
 update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-	schedstat_set(se->statistics.wait_start, rq_of(cfs_rq)->clock);
+	schedstat_set(se->statistics.wait_start, rq_clock(rq_of(cfs_rq)));
 }
 
 /*
@@ -738,14 +776,14 @@ static void
 update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	schedstat_set(se->statistics.wait_max, max(se->statistics.wait_max,
-			rq_of(cfs_rq)->clock - se->statistics.wait_start));
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start));
 	schedstat_set(se->statistics.wait_count, se->statistics.wait_count + 1);
 	schedstat_set(se->statistics.wait_sum, se->statistics.wait_sum +
-			rq_of(cfs_rq)->clock - se->statistics.wait_start);
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
 #ifdef CONFIG_SCHEDSTATS
 	if (entity_is_task(se)) {
 		trace_sched_stat_wait(task_of(se),
-			rq_of(cfs_rq)->clock - se->statistics.wait_start);
+			rq_clock(rq_of(cfs_rq)) - se->statistics.wait_start);
 	}
 #endif
 	schedstat_set(se->statistics.wait_start, 0);
@@ -771,7 +809,7 @@ update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	/*
 	 * We are starting a new run period:
 	 */
-	se->exec_start = rq_of(cfs_rq)->clock_task;
+	se->exec_start = rq_clock_task(rq_of(cfs_rq));
 }
 
 /**************************************************
@@ -1037,7 +1075,7 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
 	 * to gain a more accurate current total weight. See
 	 * update_cfs_rq_load_contribution().
 	 */
-	tg_weight = atomic64_read(&tg->load_avg);
+	tg_weight = atomic_long_read(&tg->load_avg);
 	tg_weight -= cfs_rq->tg_load_contrib;
 	tg_weight += cfs_rq->load.weight;
 
@@ -1110,8 +1148,7 @@ static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
 }
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
-/* Only depends on SMP, FAIR_GROUP_SCHED may be removed when useful in lb */
-#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
+#ifdef CONFIG_SMP
 /*
  * We choose a half-life close to 1 scheduling period.
  * Note: The tables below are dependent on this value.
@@ -1319,13 +1356,13 @@ static inline void __update_cfs_rq_tg_load_contrib(struct cfs_rq *cfs_rq,
 						 int force_update)
 {
 	struct task_group *tg = cfs_rq->tg;
-	s64 tg_contrib;
+	long tg_contrib;
 
 	tg_contrib = cfs_rq->runnable_load_avg + cfs_rq->blocked_load_avg;
 	tg_contrib -= cfs_rq->tg_load_contrib;
 
-	if (force_update || abs64(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
-		atomic64_add(tg_contrib, &tg->load_avg);
+	if (force_update || abs(tg_contrib) > cfs_rq->tg_load_contrib / 8) {
+		atomic_long_add(tg_contrib, &tg->load_avg);
 		cfs_rq->tg_load_contrib += tg_contrib;
 	}
 }
@@ -1360,8 +1397,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 	u64 contrib;
 
 	contrib = cfs_rq->tg_load_contrib * tg->shares;
-	se->avg.load_avg_contrib = div64_u64(contrib,
-					     atomic64_read(&tg->load_avg) + 1);
+	se->avg.load_avg_contrib = div_u64(contrib,
+				     atomic_long_read(&tg->load_avg) + 1);
 
 	/*
 	 * For group entities we need to compute a correction term in the case
@@ -1480,8 +1517,9 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 	if (!decays && !force_update)
 		return;
 
-	if (atomic64_read(&cfs_rq->removed_load)) {
-		u64 removed_load = atomic64_xchg(&cfs_rq->removed_load, 0);
+	if (atomic_long_read(&cfs_rq->removed_load)) {
+		unsigned long removed_load;
+		removed_load = atomic_long_xchg(&cfs_rq->removed_load, 0);
 		subtract_blocked_load_contrib(cfs_rq, removed_load);
 	}
 
@@ -1497,7 +1535,7 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-	__update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
+	__update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
 	__update_tg_runnable_avg(&rq->avg, &rq->cfs);
 }
 
@@ -1510,9 +1548,13 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 	 * We track migrations using entity decay_count <= 0, on a wake-up
 	 * migration we use a negative decay count to track the remote decays
 	 * accumulated while sleeping.
+	 *
+	 * Newly forked tasks are enqueued with se->avg.decay_count == 0, they
+	 * are seen by enqueue_entity_load_avg() as a migration with an already
+	 * constructed load_avg_contrib.
 	 */
 	if (unlikely(se->avg.decay_count <= 0)) {
-		se->avg.last_runnable_update = rq_of(cfs_rq)->clock_task;
+		se->avg.last_runnable_update = rq_clock_task(rq_of(cfs_rq));
 		if (se->avg.decay_count) {
 			/*
 			 * In a wake-up migration we have to approximate the
@@ -1530,7 +1572,13 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
 		}
 		wakeup = 0;
 	} else {
-		__synchronize_entity_decay(se);
+		/*
+		 * Task re-woke on same cpu (or else migrate_task_rq_fair()
+		 * would have made count negative); we must be careful to avoid
+		 * double-accounting blocked time after synchronizing decays.
+		 */
+		se->avg.last_runnable_update += __synchronize_entity_decay(se)
+							<< 20;
 	}
 
 	/* migrated tasks did not contribute to our blocked load */
@@ -1607,7 +1655,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		tsk = task_of(se);
 
 	if (se->statistics.sleep_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->statistics.sleep_start;
+		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.sleep_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -1624,7 +1672,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 		}
 	}
 	if (se->statistics.block_start) {
-		u64 delta = rq_of(cfs_rq)->clock - se->statistics.block_start;
+		u64 delta = rq_clock(rq_of(cfs_rq)) - se->statistics.block_start;
 
 		if ((s64)delta < 0)
 			delta = 0;
@@ -1712,7 +1760,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 {
 	/*
 	 * Update the normalized vruntime before updating min_vruntime
-	 * through callig update_curr().
+	 * through calling update_curr().
 	 */
 	if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING))
 		se->vruntime += cfs_rq->min_vruntime;
@@ -1805,9 +1853,9 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
 			struct task_struct *tsk = task_of(se);
 
 			if (tsk->state & TASK_INTERRUPTIBLE)
-				se->statistics.sleep_start = rq_of(cfs_rq)->clock;
+				se->statistics.sleep_start = rq_clock(rq_of(cfs_rq));
 			if (tsk->state & TASK_UNINTERRUPTIBLE)
-				se->statistics.block_start = rq_of(cfs_rq)->clock;
+				se->statistics.block_start = rq_clock(rq_of(cfs_rq));
 		}
 #endif
 	}
@@ -2082,7 +2130,7 @@ 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 rq_of(cfs_rq)->clock_task - cfs_rq->throttled_clock_task_time;
+	return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
 }
 
 /* returns 0 on failure to allocate runtime */
@@ -2138,10 +2186,9 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 {
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
-	struct rq *rq = rq_of(cfs_rq);
 
 	/* if the deadline is ahead of our clock, nothing to do */
-	if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0))
+	if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
 		return;
 
 	if (cfs_rq->runtime_remaining < 0)
@@ -2230,7 +2277,7 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
 #ifdef CONFIG_SMP
 	if (!cfs_rq->throttle_count) {
 		/* adjust cfs_rq_clock_task() */
-		cfs_rq->throttled_clock_task_time += rq->clock_task -
+		cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
 					     cfs_rq->throttled_clock_task;
 	}
 #endif
@@ -2245,7 +2292,7 @@ static int tg_throttle_down(struct task_group *tg, void *data)
 
 	/* group is entering throttled state, stop time */
 	if (!cfs_rq->throttle_count)
-		cfs_rq->throttled_clock_task = rq->clock_task;
+		cfs_rq->throttled_clock_task = rq_clock_task(rq);
 	cfs_rq->throttle_count++;
 
 	return 0;
@@ -2284,7 +2331,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
 		rq->nr_running -= task_delta;
 
 	cfs_rq->throttled = 1;
-	cfs_rq->throttled_clock = rq->clock;
+	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
 	list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
 	raw_spin_unlock(&cfs_b->lock);
@@ -2298,15 +2345,17 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
 	int enqueue = 1;
 	long task_delta;
 
-	se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
+	se = cfs_rq->tg->se[cpu_of(rq)];
 
 	cfs_rq->throttled = 0;
+
+	update_rq_clock(rq);
+
 	raw_spin_lock(&cfs_b->lock);
-	cfs_b->throttled_time += rq->clock - cfs_rq->throttled_clock;
+	cfs_b->throttled_time += rq_clock(rq) - cfs_rq->throttled_clock;
 	list_del_rcu(&cfs_rq->throttled_list);
 	raw_spin_unlock(&cfs_b->lock);
 
-	update_rq_clock(rq);
 	/* update hierarchical throttle state */
 	walk_tg_tree_from(cfs_rq->tg, tg_nop, tg_unthrottle_up, (void *)rq);
 
@@ -2599,10 +2648,6 @@ static void check_cfs_rq_runtime(struct cfs_rq *cfs_rq)
 	throttle_cfs_rq(cfs_rq);
 }
 
-static inline u64 default_cfs_period(void);
-static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun);
-static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b);
-
 static enum hrtimer_restart sched_cfs_slack_timer(struct hrtimer *timer)
 {
 	struct cfs_bandwidth *cfs_b =
@@ -2706,7 +2751,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq)
 #else /* CONFIG_CFS_BANDWIDTH */
 static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
 {
-	return rq_of(cfs_rq)->clock_task;
+	return rq_clock_task(rq_of(cfs_rq));
 }
 
 static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
@@ -2919,7 +2964,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 /* Used instead of source_load when we know the type == 0 */
 static unsigned long weighted_cpuload(const int cpu)
 {
-	return cpu_rq(cpu)->load.weight;
+	return cpu_rq(cpu)->cfs.runnable_load_avg;
 }
 
 /*
@@ -2964,9 +3009,10 @@ static unsigned long cpu_avg_load_per_task(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long nr_running = ACCESS_ONCE(rq->nr_running);
+	unsigned long load_avg = rq->cfs.runnable_load_avg;
 
 	if (nr_running)
-		return rq->load.weight / nr_running;
+		return load_avg / nr_running;
 
 	return 0;
 }
@@ -3416,12 +3462,6 @@ unlock:
 }
 
 /*
- * Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
- * removed when useful for applications beyond shares distribution (e.g.
- * load-balance).
- */
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/*
  * Called immediately before a task is migrated to a new cpu; task_cpu(p) and
  * cfs_rq_of(p) references at time of call are still valid and identify the
  * previous cpu.  However, the caller only guarantees p->pi_lock is held; no
@@ -3441,10 +3481,10 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu)
 	 */
 	if (se->avg.decay_count) {
 		se->avg.decay_count = -__synchronize_entity_decay(se);
-		atomic64_add(se->avg.load_avg_contrib, &cfs_rq->removed_load);
+		atomic_long_add(se->avg.load_avg_contrib,
+						&cfs_rq->removed_load);
 	}
 }
-#endif
 #endif /* CONFIG_SMP */
 
 static unsigned long
@@ -3946,7 +3986,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
 	 * 2) too many balance attempts have failed.
 	 */
 
-	tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd);
+	tsk_cache_hot = task_hot(p, rq_clock_task(env->src_rq), env->sd);
 	if (!tsk_cache_hot ||
 		env->sd->nr_balance_failed > env->sd->cache_nice_tries) {
 
@@ -4141,11 +4181,11 @@ static int tg_load_down(struct task_group *tg, void *data)
 	long cpu = (long)data;
 
 	if (!tg->parent) {
-		load = cpu_rq(cpu)->load.weight;
+		load = cpu_rq(cpu)->avg.load_avg_contrib;
 	} else {
 		load = tg->parent->cfs_rq[cpu]->h_load;
-		load *= tg->se[cpu]->load.weight;
-		load /= tg->parent->cfs_rq[cpu]->load.weight + 1;
+		load = div64_ul(load * tg->se[cpu]->avg.load_avg_contrib,
+				tg->parent->cfs_rq[cpu]->runnable_load_avg + 1);
 	}
 
 	tg->cfs_rq[cpu]->h_load = load;
@@ -4171,12 +4211,9 @@ static void update_h_load(long cpu)
 static unsigned long task_h_load(struct task_struct *p)
 {
 	struct cfs_rq *cfs_rq = task_cfs_rq(p);
-	unsigned long load;
-
-	load = p->se.load.weight;
-	load = div_u64(load * cfs_rq->h_load, cfs_rq->load.weight + 1);
 
-	return load;
+	return div64_ul(p->se.avg.load_avg_contrib * cfs_rq->h_load,
+			cfs_rq->runnable_load_avg + 1);
 }
 #else
 static inline void update_blocked_averages(int cpu)
@@ -4189,7 +4226,7 @@ static inline void update_h_load(long cpu)
 
 static unsigned long task_h_load(struct task_struct *p)
 {
-	return p->se.load.weight;
+	return p->se.avg.load_avg_contrib;
 }
 #endif
 
@@ -4302,7 +4339,7 @@ static unsigned long scale_rt_power(int cpu)
 	age_stamp = ACCESS_ONCE(rq->age_stamp);
 	avg = ACCESS_ONCE(rq->rt_avg);
 
-	total = sched_avg_period() + (rq->clock - age_stamp);
+	total = sched_avg_period() + (rq_clock(rq) - age_stamp);
 
 	if (unlikely(total < avg)) {
 		/* Ensures that power won't end up being negative */
@@ -5241,7 +5278,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
 
-	this_rq->idle_stamp = this_rq->clock;
+	this_rq->idle_stamp = rq_clock(this_rq);
 
 	if (this_rq->avg_idle < sysctl_sched_migration_cost)
 		return;
@@ -5418,10 +5455,9 @@ static inline void nohz_balance_exit_idle(int cpu)
 static inline void set_cpu_sd_state_busy(void)
 {
 	struct sched_domain *sd;
-	int cpu = smp_processor_id();
 
 	rcu_read_lock();
-	sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+	sd = rcu_dereference_check_sched_domain(this_rq()->sd);
 
 	if (!sd || !sd->nohz_idle)
 		goto unlock;
@@ -5436,10 +5472,9 @@ unlock:
 void set_cpu_sd_state_idle(void)
 {
 	struct sched_domain *sd;
-	int cpu = smp_processor_id();
 
 	rcu_read_lock();
-	sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd);
+	sd = rcu_dereference_check_sched_domain(this_rq()->sd);
 
 	if (!sd || sd->nohz_idle)
 		goto unlock;
@@ -5848,7 +5883,7 @@ static void switched_from_fair(struct rq *rq, struct task_struct *p)
 		se->vruntime -= cfs_rq->min_vruntime;
 	}
 
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	/*
 	* Remove our load from contribution when we leave sched_fair
 	* and ensure we don't carry in an old decay_count if we
@@ -5907,9 +5942,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 #ifndef CONFIG_64BIT
 	cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime;
 #endif
-#if defined(CONFIG_FAIR_GROUP_SCHED) && defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	atomic64_set(&cfs_rq->decay_counter, 1);
-	atomic64_set(&cfs_rq->removed_load, 0);
+	atomic_long_set(&cfs_rq->removed_load, 0);
 #endif
 }
 
@@ -6091,6 +6126,9 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares)
 		se = tg->se[i];
 		/* Propagate contribution to hierarchy */
 		raw_spin_lock_irqsave(&rq->lock, flags);
+
+		/* Possible calls to update_curr() need rq clock */
+		update_rq_clock(rq);
 		for_each_sched_entity(se)
 			update_cfs_shares(group_cfs_rq(se));
 		raw_spin_unlock_irqrestore(&rq->lock, flags);
@@ -6146,9 +6184,8 @@ const struct sched_class fair_sched_class = {
 
 #ifdef CONFIG_SMP
 	.select_task_rq		= select_task_rq_fair,
-#ifdef CONFIG_FAIR_GROUP_SCHED
 	.migrate_task_rq	= migrate_task_rq_fair,
-#endif
+
 	.rq_online		= rq_online_fair,
 	.rq_offline		= rq_offline_fair,