[RFC PATCH 04/11] sched: Create a helper function to calculate sched_group stats for fbg()

[Gautham R Shenoy <ego@in.ibm.com>]

Create a helper function named update_sg_lb_stats() which can be invoked to
calculate the individual group's statistics in find_busiest_group().

This reduces the lenght of find_busiest_group() considerably.

Credit: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
---

 kernel/sched.c |  175 ++++++++++++++++++++++++++++++++------------------------
 1 files changed, 100 insertions(+), 75 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 6da9939..d2e9b8a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3133,6 +3133,103 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 
 	return load_idx;
 }
+
+
+/**
+ * update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @group: sched_group whose statistics are to be updated.
+ * @this_cpu: Cpu for which load balance is currently performed.
+ * @idle: Idle status of this_cpu
+ * @load_idx: Load index of sched_domain of this_cpu for load calc.
+ * @sd_idle: Idle status of the sched_domain containing group.
+ * @local_group: Does group contain this_cpu.
+ * @cpus: Set of cpus considered for load balancing.
+ * @balance: Should we balance.
+ * @sgs: variable to hold the statistics for this group.
+ */
+static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu,
+			enum cpu_idle_type idle, int load_idx, int *sd_idle,
+			int local_group, const struct cpumask *cpus,
+			int *balance, struct sg_lb_stats *sgs)
+{
+	unsigned long load, max_cpu_load, min_cpu_load;
+	int i;
+	unsigned int balance_cpu = -1, first_idle_cpu = 0;
+	unsigned long sum_avg_load_per_task;
+	unsigned long avg_load_per_task;
+
+	if (local_group)
+		balance_cpu = group_first_cpu(group);
+
+	/* Tally up the load of all CPUs in the group */
+	sum_avg_load_per_task = avg_load_per_task = 0;
+	max_cpu_load = 0;
+	min_cpu_load = ~0UL;
+
+	for_each_cpu_and(i, sched_group_cpus(group), cpus) {
+		struct rq *rq = cpu_rq(i);
+
+		if (*sd_idle && rq->nr_running)
+			*sd_idle = 0;
+
+		/* Bias balancing toward cpus of our domain */
+		if (local_group) {
+			if (idle_cpu(i) && !first_idle_cpu) {
+				first_idle_cpu = 1;
+				balance_cpu = i;
+			}
+
+			load = target_load(i, load_idx);
+		} else {
+			load = source_load(i, load_idx);
+			if (load > max_cpu_load)
+				max_cpu_load = load;
+			if (min_cpu_load > load)
+				min_cpu_load = load;
+		}
+
+		sgs->group_load += load;
+		sgs->sum_nr_running += rq->nr_running;
+		sgs->sum_weighted_load += weighted_cpuload(i);
+
+		sum_avg_load_per_task += cpu_avg_load_per_task(i);
+	}
+
+	/*
+	 * First idle cpu or the first cpu(busiest) in this sched group
+	 * is eligible for doing load balancing at this and above
+	 * domains. In the newly idle case, we will allow all the cpu's
+	 * to do the newly idle load balance.
+	 */
+	if (idle != CPU_NEWLY_IDLE && local_group &&
+	    balance_cpu != this_cpu && balance) {
+		*balance = 0;
+		return;
+	}
+
+	/* Adjust by relative CPU power of the group */
+	sgs->avg_load = sg_div_cpu_power(group,
+			sgs->group_load * SCHED_LOAD_SCALE);
+
+
+	/*
+	 * Consider the group unbalanced when the imbalance is larger
+	 * than the average weight of two tasks.
+	 *
+	 * APZ: with cgroup the avg task weight can vary wildly and
+	 *      might not be a suitable number - should we keep a
+	 *      normalized nr_running number somewhere that negates
+	 *      the hierarchy?
+	 */
+	avg_load_per_task = sg_div_cpu_power(group,
+			sum_avg_load_per_task * SCHED_LOAD_SCALE);
+
+	if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+		sgs->group_imb = 1;
+
+	sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
+
+}
 /******* find_busiest_group() helpers end here *********************/
 
 /*
@@ -3166,92 +3263,20 @@ find_busiest_group(struct sched_domain *sd, int this_cpu,
 
 	do {
 		struct sg_lb_stats sgs;
-		unsigned long load, max_cpu_load, min_cpu_load;
 		int local_group;
-		int i;
-		unsigned int balance_cpu = -1, first_idle_cpu = 0;
-		unsigned long sum_avg_load_per_task;
-		unsigned long avg_load_per_task;
 
 		local_group = cpumask_test_cpu(this_cpu,
 					       sched_group_cpus(group));
 		memset(&sgs, 0, sizeof(sgs));
+		update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
+				local_group, cpus, balance, &sgs);
 
-		if (local_group)
-			balance_cpu = group_first_cpu(group);
-
-		/* Tally up the load of all CPUs in the group */
-		sum_avg_load_per_task = avg_load_per_task = 0;
-
-		max_cpu_load = 0;
-		min_cpu_load = ~0UL;
-
-		for_each_cpu_and(i, sched_group_cpus(group), cpus) {
-			struct rq *rq = cpu_rq(i);
-
-			if (*sd_idle && rq->nr_running)
-				*sd_idle = 0;
-
-			/* Bias balancing toward cpus of our domain */
-			if (local_group) {
-				if (idle_cpu(i) && !first_idle_cpu) {
-					first_idle_cpu = 1;
-					balance_cpu = i;
-				}
-
-				load = target_load(i, load_idx);
-			} else {
-				load = source_load(i, load_idx);
-				if (load > max_cpu_load)
-					max_cpu_load = load;
-				if (min_cpu_load > load)
-					min_cpu_load = load;
-			}
-
-			sgs.group_load += load;
-			sgs.sum_nr_running += rq->nr_running;
-			sgs.sum_weighted_load += weighted_cpuload(i);
-
-			sum_avg_load_per_task += cpu_avg_load_per_task(i);
-		}
-
-		/*
-		 * First idle cpu or the first cpu(busiest) in this sched group
-		 * is eligible for doing load balancing at this and above
-		 * domains. In the newly idle case, we will allow all the cpu's
-		 * to do the newly idle load balance.
-		 */
-		if (idle != CPU_NEWLY_IDLE && local_group &&
-		    balance_cpu != this_cpu && balance) {
-			*balance = 0;
+		if (balance && !(*balance))
 			goto ret;
-		}
 
 		total_load += sgs.group_load;
 		total_pwr += group->__cpu_power;
 
-		/* Adjust by relative CPU power of the group */
-		sgs.avg_load = sg_div_cpu_power(group,
-				sgs.group_load * SCHED_LOAD_SCALE);
-
-
-		/*
-		 * Consider the group unbalanced when the imbalance is larger
-		 * than the average weight of two tasks.
-		 *
-		 * APZ: with cgroup the avg task weight can vary wildly and
-		 *      might not be a suitable number - should we keep a
-		 *      normalized nr_running number somewhere that negates
-		 *      the hierarchy?
-		 */
-		avg_load_per_task = sg_div_cpu_power(group,
-				sum_avg_load_per_task * SCHED_LOAD_SCALE);
-
-		if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
-			sgs.group_imb = 1;
-
-		sgs.group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
-
 		if (local_group) {
 			this_load = sgs.avg_load;
 			this = group;