Merge branch 'sched/core' into auto-latest

5 files changed, 51 insertions, 36 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 850bdb53589a..36e936da9969 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3666,6 +3666,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	__account_system_time(p, cputime, cputime_scaled, target_cputime64);
 }
 
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 /*
  * Account a tick to a process and cpustat
@@ -3732,6 +3733,7 @@ static void irqtime_account_idle_ticks(int ticks) {}
 static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 						struct rq *rq) {}
 #endif
+#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 /*
  * Account for involuntary wait time.
diff --git a/kernel/sched_autogroup.c b/kernel/sched_autogroup.c
index 9fb656283157..5946ac515602 100644
--- a/kernel/sched_autogroup.c
+++ b/kernel/sched_autogroup.c
@@ -12,7 +12,6 @@ static atomic_t autogroup_seq_nr;
 static void __init autogroup_init(struct task_struct *init_task)
 {
 	autogroup_default.tg = &root_task_group;
-	root_task_group.autogroup = &autogroup_default;
 	kref_init(&autogroup_default.kref);
 	init_rwsem(&autogroup_default.lock);
 	init_task->signal->autogroup = &autogroup_default;
@@ -130,7 +129,7 @@ task_wants_autogroup(struct task_struct *p, struct task_group *tg)
 
 static inline bool task_group_is_autogroup(struct task_group *tg)
 {
-	return tg != &root_task_group && tg->autogroup;
+	return !!tg->autogroup;
 }
 
 static inline struct task_group *
@@ -161,11 +160,15 @@ autogroup_move_group(struct task_struct *p, struct autogroup *ag)
 
 	p->signal->autogroup = autogroup_kref_get(ag);
 
+	if (!ACCESS_ONCE(sysctl_sched_autogroup_enabled))
+		goto out;
+
 	t = p;
 	do {
 		sched_move_task(t);
 	} while_each_thread(p, t);
 
+out:
 	unlock_task_sighand(p, &flags);
 	autogroup_kref_put(prev);
 }
@@ -247,10 +250,14 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 {
 	struct autogroup *ag = autogroup_task_get(p);
 
+	if (!task_group_is_autogroup(ag->tg))
+		goto out;
+
 	down_read(&ag->lock);
 	seq_printf(m, "/autogroup-%ld nice %d\n", ag->id, ag->nice);
 	up_read(&ag->lock);
 
+out:
 	autogroup_kref_put(ag);
 }
 #endif /* CONFIG_PROC_FS */
@@ -258,9 +265,7 @@ void proc_sched_autogroup_show_task(struct task_struct *p, struct seq_file *m)
 #ifdef CONFIG_SCHED_DEBUG
 static inline int autogroup_path(struct task_group *tg, char *buf, int buflen)
 {
-	int enabled = ACCESS_ONCE(sysctl_sched_autogroup_enabled);
-
-	if (!enabled || !tg->autogroup)
+	if (!task_group_is_autogroup(tg))
 		return 0;
 
 	return snprintf(buf, buflen, "%s-%ld", "/autogroup", tg->autogroup->id);
diff --git a/kernel/sched_autogroup.h b/kernel/sched_autogroup.h
index 7b859ffe5dad..05577055cfca 100644
--- a/kernel/sched_autogroup.h
+++ b/kernel/sched_autogroup.h
@@ -1,6 +1,11 @@
 #ifdef CONFIG_SCHED_AUTOGROUP
 
 struct autogroup {
+	/*
+	 * reference doesn't mean how many thread attach to this
+	 * autogroup now. It just stands for the number of task
+	 * could use this autogroup.
+	 */
 	struct kref		kref;
 	struct task_group	*tg;
 	struct rw_semaphore	lock;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index d384e739ea95..3a88dee165c0 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2743,7 +2743,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 
 	/*
 	 * Consider the group unbalanced when the imbalance is larger
-	 * than the average weight of two tasks.
+	 * than the average weight of a task.
 	 *
 	 * APZ: with cgroup the avg task weight can vary wildly and
 	 *      might not be a suitable number - should we keep a
@@ -2753,7 +2753,7 @@ static inline void update_sg_lb_stats(struct sched_domain *sd,
 	if (sgs->sum_nr_running)
 		avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
 
-	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
+	if ((max_cpu_load - min_cpu_load) >= avg_load_per_task && max_nr_running > 1)
 		sgs->group_imb = 1;
 
 	sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
@@ -3113,19 +3113,9 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	 */
 	update_sd_lb_stats(sd, this_cpu, idle, cpus, balance, &sds);
 
-	/* Cases where imbalance does not exist from POV of this_cpu */
-	/* 1) this_cpu is not the appropriate cpu to perform load balancing
-	 *    at this level.
-	 * 2) There is no busy sibling group to pull from.
-	 * 3) This group is the busiest group.
-	 * 4) This group is more busy than the avg busieness at this
-	 *    sched_domain.
-	 * 5) The imbalance is within the specified limit.
-	 *
-	 * Note: when doing newidle balance, if the local group has excess
-	 * capacity (i.e. nr_running < group_capacity) and the busiest group
-	 * does not have any capacity, we force a load balance to pull tasks
-	 * to the local group. In this case, we skip past checks 3, 4 and 5.
+	/*
+	 * this_cpu is not the appropriate cpu to perform load balancing at
+	 * this level.
 	 */
 	if (!(*balance))
 		goto ret;
@@ -3134,41 +3124,55 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 	    check_asym_packing(sd, &sds, this_cpu, imbalance))
 		return sds.busiest;
 
+	/* There is no busy sibling group to pull tasks from */
 	if (!sds.busiest || sds.busiest_nr_running == 0)
 		goto out_balanced;
 
-	/*  SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+	/*
+	 * If the busiest group is imbalanced the below checks don't
+	 * work because they assumes all things are equal, which typically
+	 * isn't true due to cpus_allowed constraints and the like.
+	 */
+	if (sds.group_imb)
+		goto force_balance;
+
+	/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
 	if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
 			!sds.busiest_has_capacity)
 		goto force_balance;
 
+	/*
+	 * If the local group is more busy than the selected busiest group
+	 * don't try and pull any tasks.
+	 */
 	if (sds.this_load >= sds.max_load)
 		goto out_balanced;
 
+	/*
+	 * Don't pull any tasks if this group is already above the domain
+	 * average load.
+	 */
 	sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr;
-
 	if (sds.this_load >= sds.avg_load)
 		goto out_balanced;
 
-	/*
-	 * In the CPU_NEWLY_IDLE, use imbalance_pct to be conservative.
-	 * And to check for busy balance use !idle_cpu instead of
-	 * CPU_NOT_IDLE. This is because HT siblings will use CPU_NOT_IDLE
-	 * even when they are idle.
-	 */
-	if (idle == CPU_NEWLY_IDLE || !idle_cpu(this_cpu)) {
-		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
-			goto out_balanced;
-	} else {
+	if (idle == CPU_IDLE) {
 		/*
 		 * This cpu is idle. If the busiest group load doesn't
 		 * have more tasks than the number of available cpu's and
 		 * there is no imbalance between this and busiest group
 		 * wrt to idle cpu's, it is balanced.
 		 */
-		if ((sds.this_idle_cpus  <= sds.busiest_idle_cpus + 1) &&
+		if ((sds.this_idle_cpus <= sds.busiest_idle_cpus + 1) &&
 		    sds.busiest_nr_running <= sds.busiest_group_weight)
 			goto out_balanced;
+	} else {
+		/*
+		 * In the CPU_NEWLY_IDLE, CPU_NOT_IDLE cases, use
+		 * imbalance_pct to be conservative.
+		 */
+		if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
+			goto out_balanced;
 	}
 
 force_balance:
@@ -3862,8 +3866,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
 				 * We've pulled tasks over so either we're no
-				 * longer idle, or one of our SMT siblings is
-				 * not idle.
+				 * longer idle.
 				 */
 				idle = CPU_NOT_IDLE;
 			}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 40eb4bf48ca4..f76aeae389ce 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -367,7 +367,7 @@ static struct ctl_table kern_table[] = {
 		.data		= &sysctl_sched_autogroup_enabled,
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},