+ * wake_idle() will wake a task on an idle cpu if task->cpu is
+ * not idle and an idle cpu is available. The span of cpus to
+ * search starts with cpus closest then further out as needed,
+ * so we always favor a closer, idle cpu.
+ * Domains may include CPUs that are not usable for migration,
+ * hence we need to mask them out (cpu_active_map)
+ *
+ * Returns the CPU we should wake onto.
+ */
+#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
+static int wake_idle(int cpu, struct task_struct *p)
+{
+ cpumask_t tmp;
+ struct sched_domain *sd;
+ int i;
+
+ /*
+ * If it is idle, then it is the best cpu to run this task.
+ *
+ * This cpu is also the best, if it has more than one task already.
+ * Siblings must be also busy(in most cases) as they didn't already
+ * pickup the extra load from this cpu and hence we need not check
+ * sibling runqueue info. This will avoid the checks and cache miss
+ * penalities associated with that.
+ */
+ if (idle_cpu(cpu) || cpu_rq(cpu)->cfs.nr_running > 1)
+ return cpu;
+
+ for_each_domain(cpu, sd) {
+ if ((sd->flags & SD_WAKE_IDLE)
+ || ((sd->flags & SD_WAKE_IDLE_FAR)
+ && !task_hot(p, task_rq(p)->clock, sd))) {
+ cpus_and(tmp, sd->span, p->cpus_allowed);
+ cpus_and(tmp, tmp, cpu_active_map);
+ for_each_cpu_mask_nr(i, tmp) {
+ if (idle_cpu(i)) {
+ if (i != task_cpu(p)) {
+ schedstat_inc(p,
+ se.nr_wakeups_idle);
+ }
+ return i;
+ }
+ }
+ } else {
+ break;
+ }
+ }
+ return cpu;
+}
+#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
+static inline int wake_idle(int cpu, struct task_struct *p)
+{
+ return cpu;
+}
+#endif
+
+#ifdef CONFIG_SMP
+
+static const struct sched_class fair_sched_class;
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * effective_load() calculates the load change as seen from the root_task_group
+ *
+ * Adding load to a group doesn't make a group heavier, but can cause movement
+ * of group shares between cpus. Assuming the shares were perfectly aligned one
+ * can calculate the shift in shares.
+ *
+ * The problem is that perfectly aligning the shares is rather expensive, hence
+ * we try to avoid doing that too often - see update_shares(), which ratelimits
+ * this change.
+ *
+ * We compensate this by not only taking the current delta into account, but
+ * also considering the delta between when the shares were last adjusted and
+ * now.
+ *
+ * We still saw a performance dip, some tracing learned us that between
+ * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
+ * significantly. Therefore try to bias the error in direction of failing
+ * the affine wakeup.
+ *
+ */
+static long effective_load(struct task_group *tg, int cpu,
+ long wl, long wg)
+{
+ struct sched_entity *se = tg->se[cpu];
+ long more_w;
+
+ if (!tg->parent)
+ return wl;
+
+ /*
+ * By not taking the decrease of shares on the other cpu into
+ * account our error leans towards reducing the affine wakeups.
+ */
+ if (!wl && sched_feat(ASYM_EFF_LOAD))
+ return wl;
+
+ /*
+ * Instead of using this increment, also add the difference
+ * between when the shares were last updated and now.
+ */
+ more_w = se->my_q->load.weight - se->my_q->rq_weight;
+ wl += more_w;
+ wg += more_w;
+
+ for_each_sched_entity(se) {
+#define D(n) (likely(n) ? (n) : 1)
+
+ long S, rw, s, a, b;
+
+ S = se->my_q->tg->shares;
+ s = se->my_q->shares;
+ rw = se->my_q->rq_weight;
+
+ a = S*(rw + wl);
+ b = S*rw + s*wg;
+
+ wl = s*(a-b)/D(b);
+ /*
+ * Assume the group is already running and will
+ * thus already be accounted for in the weight.
+ *
+ * That is, moving shares between CPUs, does not
+ * alter the group weight.
+ */
+ wg = 0;
+#undef D
+ }
+
+ return wl;
+}
+
+#else
+
+static inline unsigned long effective_load(struct task_group *tg, int cpu,
+ unsigned long wl, unsigned long wg)
+{
+ return wl;
+}
+
+#endif
+
+static int
+wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+ struct task_struct *p, int prev_cpu, int this_cpu, int sync,
+ int idx, unsigned long load, unsigned long this_load,
+ unsigned int imbalance)
+{
+ struct task_struct *curr = this_rq->curr;
+ struct task_group *tg;
+ unsigned long tl = this_load;
+ unsigned long tl_per_task;
+ unsigned long weight;
+ int balanced;
+
+ if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
+ return 0;
+
+ /*
+ * If sync wakeup then subtract the (maximum possible)
+ * effect of the currently running task from the load
+ * of the current CPU:
+ */
+ if (sync) {
+ tg = task_group(current);
+ weight = current->se.load.weight;
+
+ tl += effective_load(tg, this_cpu, -weight, -weight);
+ load += effective_load(tg, prev_cpu, 0, -weight);
+ }
+
+ tg = task_group(p);
+ weight = p->se.load.weight;
+
+ balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+ imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
+
+ /*
+ * If the currently running task will sleep within
+ * a reasonable amount of time then attract this newly
+ * woken task:
+ */
+ if (sync && balanced) {
+ if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+ p->se.avg_overlap < sysctl_sched_migration_cost)
+ return 1;
+ }
+
+ schedstat_inc(p, se.nr_wakeups_affine_attempts);
+ tl_per_task = cpu_avg_load_per_task(this_cpu);
+
+ if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
+ balanced) {
+ /*
+ * This domain has SD_WAKE_AFFINE and
+ * p is cache cold in this domain, and
+ * there is no bad imbalance.
+ */
+ schedstat_inc(this_sd, ttwu_move_affine);
+ schedstat_inc(p, se.nr_wakeups_affine);
+
+ return 1;
+ }
+ return 0;
+}
+
+static int select_task_rq_fair(struct task_struct *p, int sync)
+{
+ struct sched_domain *sd, *this_sd = NULL;
+ int prev_cpu, this_cpu, new_cpu;
+ unsigned long load, this_load;
+ struct rq *rq, *this_rq;
+ unsigned int imbalance;
+ int idx;
+
+ prev_cpu = task_cpu(p);
+ rq = task_rq(p);
+ this_cpu = smp_processor_id();
+ this_rq = cpu_rq(this_cpu);
+ new_cpu = prev_cpu;
+
+ /*
+ * 'this_sd' is the first domain that both
+ * this_cpu and prev_cpu are present in:
+ */
+ for_each_domain(this_cpu, sd) {
+ if (cpu_isset(prev_cpu, sd->span)) {
+ this_sd = sd;
+ break;
+ }
+ }
+
+ if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+ goto out;
+
+ /*
+ * Check for affine wakeup and passive balancing possibilities.
+ */
+ if (!this_sd)
+ goto out;
+
+ idx = this_sd->wake_idx;
+
+ imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+
+ load = source_load(prev_cpu, idx);
+ this_load = target_load(this_cpu, idx);
+
+ if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+ load, this_load, imbalance))
+ return this_cpu;
+
+ if (prev_cpu == this_cpu)
+ goto out;
+
+ /*
+ * Start passive balancing when half the imbalance_pct
+ * limit is reached.
+ */
+ if (this_sd->flags & SD_WAKE_BALANCE) {
+ if (imbalance*this_load <= 100*load) {
+ schedstat_inc(this_sd, ttwu_move_balance);
+ schedstat_inc(p, se.nr_wakeups_passive);
+ return this_cpu;
+ }
+ }
+
+out:
+ return wake_idle(new_cpu, p);
+}
+#endif /* CONFIG_SMP */
+
+static unsigned long wakeup_gran(struct sched_entity *se)
+{
+ unsigned long gran = sysctl_sched_wakeup_granularity;
+
+ /*
+ * More easily preempt - nice tasks, while not making it harder for
+ * + nice tasks.
+ */
+ if (sched_feat(ASYM_GRAN))
+ gran = calc_delta_asym(sysctl_sched_wakeup_granularity, se);
+ else
+ gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
+
+ return gran;
+}
+
+/*
+ * Should 'se' preempt 'curr'.
+ *
+ * |s1
+ * |s2
+ * |s3
+ * g
+ * |<--->|c
+ *
+ * w(c, s1) = -1
+ * w(c, s2) = 0
+ * w(c, s3) = 1
+ *
+ */
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
+{
+ s64 gran, vdiff = curr->vruntime - se->vruntime;
+
+ if (vdiff < 0)
+ return -1;
+
+ gran = wakeup_gran(curr);
+ if (vdiff > gran)
+ return 1;
+
+ return 0;
+}
+
+/* return depth at which a sched entity is present in the hierarchy */
+static inline int depth_se(struct sched_entity *se)
+{
+ int depth = 0;
+
+ for_each_sched_entity(se)
+ depth++;
+
+ return depth;
+}
+
+/*