sched: Factor out code to should_we_balance()

Now checking whether this cpu is appropriate to balance or not
is embedded into update_sg_lb_stats() and this checking has no direct
relationship to this function. There is not enough reason to place
this checking at update_sg_lb_stats(), except saving one iteration
for sched_group_cpus.

In this patch, I factor out this checking to should_we_balance() function.
And before doing actual work for load_balancing, check whether this cpu is
appropriate to balance via should_we_balance(). If this cpu is not
a candidate for balancing, it quit the work immediately.

With this change, we can save two memset cost and can expect better
compiler optimization.

Below is result of this patch.

 * Vanilla *
   text	   data	    bss	    dec	    hex	filename
  34499	   1136	    116	  35751	   8ba7	kernel/sched/fair.o

 * Patched *
   text	   data	    bss	    dec	    hex	filename
  34243	   1136	    116	  35495	   8aa7	kernel/sched/fair.o

In addition, rename @balance to @continue_balancing in order to represent
its purpose more clearly.

Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@lge.com>
[ s/should_balance/continue_balancing/g ]
Reviewed-by: Paul Turner <pjt@google.com>
[ Made style changes and a fix in should_we_balance(). ]
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1375778203-31343-3-git-send-email-iamjoonsoo.kim@lge.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8aa217f..9a6daf8 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4463,22 +4463,17 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
  * @group: sched_group whose statistics are to be updated.
  * @load_idx: Load index of sched_domain of this_cpu for load calc.
  * @local_group: Does group contain this_cpu.
- * @balance: Should we balance.
  * @sgs: variable to hold the statistics for this group.
  */
 static inline void update_sg_lb_stats(struct lb_env *env,
                        struct sched_group *group, int load_idx,
-                       int local_group, int *balance, struct sg_lb_stats *sgs)
+                       int local_group, struct sg_lb_stats *sgs)
 {
        unsigned long nr_running, max_nr_running, min_nr_running;
        unsigned long load, max_cpu_load, min_cpu_load;
-       unsigned int balance_cpu = -1, first_idle_cpu = 0;
        unsigned long avg_load_per_task = 0;
        int i;
 
-       if (local_group)
-               balance_cpu = group_balance_cpu(group);
-
        /* Tally up the load of all CPUs in the group */
        max_cpu_load = 0;
        min_cpu_load = ~0UL;
@@ -4492,12 +4487,6 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 
                /* Bias balancing toward cpus of our domain */
                if (local_group) {
-                       if (idle_cpu(i) && !first_idle_cpu &&
-                                       cpumask_test_cpu(i, sched_group_mask(group))) {
-                               first_idle_cpu = 1;
-                               balance_cpu = i;
-                       }
-
                        load = target_load(i, load_idx);
                } else {
                        load = source_load(i, load_idx);
@@ -4519,22 +4508,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
                        sgs->idle_cpus++;
        }
 
-       /*
-        * 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 (local_group) {
-               if (env->idle != CPU_NEWLY_IDLE) {
-                       if (balance_cpu != env->dst_cpu) {
-                               *balance = 0;
-                               return;
-                       }
-                       update_group_power(env->sd, env->dst_cpu);
-               } else if (time_after_eq(jiffies, group->sgp->next_update))
-                       update_group_power(env->sd, env->dst_cpu);
-       }
+       if (local_group && (env->idle != CPU_NEWLY_IDLE ||
+                       time_after_eq(jiffies, group->sgp->next_update)))
+               update_group_power(env->sd, env->dst_cpu);
 
        /* Adjust by relative CPU power of the group */
        sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / group->sgp->power;
@@ -4613,7 +4589,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
  * @sds: variable to hold the statistics for this sched_domain.
  */
 static inline void update_sd_lb_stats(struct lb_env *env,
-                                       int *balance, struct sd_lb_stats *sds)
+                                       struct sd_lb_stats *sds)
 {
        struct sched_domain *child = env->sd->child;
        struct sched_group *sg = env->sd->groups;
@@ -4630,10 +4606,7 @@ static inline void update_sd_lb_stats(struct lb_env *env,
 
                local_group = cpumask_test_cpu(env->dst_cpu, sched_group_cpus(sg));
                memset(&sgs, 0, sizeof(sgs));
-               update_sg_lb_stats(env, sg, load_idx, local_group, balance, &sgs);
-
-               if (local_group && !(*balance))
-                       return;
+               update_sg_lb_stats(env, sg, load_idx, local_group, &sgs);
 
                sds->total_load += sgs.group_load;
                sds->total_pwr += sg->sgp->power;
@@ -4866,8 +4839,6 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  * to restore balance.
  *
  * @env: The load balancing environment.
- * @balance: Pointer to a variable indicating if this_cpu
- *     is the appropriate cpu to perform load balancing at this_level.
  *
  * Returns:    - the busiest group if imbalance exists.
  *             - If no imbalance and user has opted for power-savings balance,
@@ -4875,7 +4846,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
  *                put to idle by rebalancing its tasks onto our group.
  */
 static struct sched_group *
-find_busiest_group(struct lb_env *env, int *balance)
+find_busiest_group(struct lb_env *env)
 {
        struct sd_lb_stats sds;
 
@@ -4885,14 +4856,7 @@ find_busiest_group(struct lb_env *env, int *balance)
         * Compute the various statistics relavent for load balancing at
         * this level.
         */
-       update_sd_lb_stats(env, balance, &sds);
-
-       /*
-        * this_cpu is not the appropriate cpu to perform load balancing at
-        * this level.
-        */
-       if (!(*balance))
-               goto ret;
+       update_sd_lb_stats(env, &sds);
 
        if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) &&
            check_asym_packing(env, &sds))
@@ -4956,7 +4920,6 @@ force_balance:
        return sds.busiest;
 
 out_balanced:
-ret:
        env->imbalance = 0;
        return NULL;
 }
@@ -5043,13 +5006,47 @@ static int need_active_balance(struct lb_env *env)
 
 static int active_load_balance_cpu_stop(void *data);
 
+static int should_we_balance(struct lb_env *env)
+{
+       struct sched_group *sg = env->sd->groups;
+       struct cpumask *sg_cpus, *sg_mask;
+       int cpu, balance_cpu = -1;
+
+       /*
+        * In the newly idle case, we will allow all the cpu's
+        * to do the newly idle load balance.
+        */
+       if (env->idle == CPU_NEWLY_IDLE)
+               return 1;
+
+       sg_cpus = sched_group_cpus(sg);
+       sg_mask = sched_group_mask(sg);
+       /* Try to find first idle cpu */
+       for_each_cpu_and(cpu, sg_cpus, env->cpus) {
+               if (!cpumask_test_cpu(cpu, sg_mask) || !idle_cpu(cpu))
+                       continue;
+
+               balance_cpu = cpu;
+               break;
+       }
+
+       if (balance_cpu == -1)
+               balance_cpu = group_balance_cpu(sg);
+
+       /*
+        * First idle cpu or the first cpu(busiest) in this sched group
+        * is eligible for doing load balancing at this and above domains.
+        */
+       return balance_cpu != env->dst_cpu;
+}
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
  */
 static int load_balance(int this_cpu, struct rq *this_rq,
                        struct sched_domain *sd, enum cpu_idle_type idle,
-                       int *balance)
+                       int *continue_balancing)
 {
        int ld_moved, cur_ld_moved, active_balance = 0;
        struct sched_group *group;
@@ -5079,11 +5076,12 @@ static int load_balance(int this_cpu, struct rq *this_rq,
        schedstat_inc(sd, lb_count[idle]);
 
 redo:
-       group = find_busiest_group(&env, balance);
-
-       if (*balance == 0)
+       if (!should_we_balance(&env)) {
+               *continue_balancing = 0;
                goto out_balanced;
+       }
 
+       group = find_busiest_group(&env);
        if (!group) {
                schedstat_inc(sd, lb_nobusyg[idle]);
                goto out_balanced;
@@ -5296,7 +5294,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
        rcu_read_lock();
        for_each_domain(this_cpu, sd) {
                unsigned long interval;
-               int balance = 1;
+               int continue_balancing = 1;
 
                if (!(sd->flags & SD_LOAD_BALANCE))
                        continue;
@@ -5304,7 +5302,8 @@ void idle_balance(int this_cpu, struct rq *this_rq)
                if (sd->flags & SD_BALANCE_NEWIDLE) {
                        /* If we've pulled tasks over stop searching: */
                        pulled_task = load_balance(this_cpu, this_rq,
-                                                  sd, CPU_NEWLY_IDLE, &balance);
+                                                  sd, CPU_NEWLY_IDLE,
+                                                  &continue_balancing);
                }
 
                interval = msecs_to_jiffies(sd->balance_interval);
@@ -5542,7 +5541,7 @@ void update_max_interval(void)
  */
 static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 {
-       int balance = 1;
+       int continue_balancing = 1;
        struct rq *rq = cpu_rq(cpu);
        unsigned long interval;
        struct sched_domain *sd;
@@ -5574,7 +5573,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
                }
 
                if (time_after_eq(jiffies, sd->last_balance + interval)) {
-                       if (load_balance(cpu, rq, sd, idle, &balance)) {
+                       if (load_balance(cpu, rq, sd, idle, &continue_balancing)) {
                                /*
                                 * The LBF_SOME_PINNED logic could have changed
                                 * env->dst_cpu, so we can't know our idle
@@ -5597,7 +5596,7 @@ out:
                 * CPU in our sched group which is doing load balancing more
                 * actively.
                 */
-               if (!balance)
+               if (!continue_balancing)
                        break;
        }
        rcu_read_unlock();