1 files changed, 261 insertions, 153 deletions

diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index aa7f84121016..10d218ab69f2 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -711,7 +711,7 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
 
         if (!initial) {
                 /* sleeps upto a single latency don't count. */
-                if (sched_feat(NEW_FAIR_SLEEPERS)) {
+                if (sched_feat(FAIR_SLEEPERS)) {
                         unsigned long thresh = sysctl_sched_latency;
 
                         /*
@@ -725,6 +725,13 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
                                          task_of(se)->policy != SCHED_IDLE))
                                 thresh = calc_delta_fair(thresh, se);
 
+                        /*
+                         * Halve their sleep time's effect, to allow
+                         * for a gentler effect of sleepers:
+                         */
+                        if (sched_feat(GENTLE_FAIR_SLEEPERS))
+                                thresh >>= 1;
+
                         vruntime -= thresh;
                 }
         }
@@ -757,10 +764,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
 
 static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
-        if (cfs_rq->last == se)
+        if (!se || cfs_rq->last == se)
                 cfs_rq->last = NULL;
 
-        if (cfs_rq->next == se)
+        if (!se || cfs_rq->next == se)
                 cfs_rq->next = NULL;
 }
 
@@ -1062,83 +1069,6 @@ static void yield_task_fair(struct rq *rq)
         se->vruntime = rightmost->vruntime + 1;
 }
 
-/*
- * 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 (rq->rd->online)
- *
- * Returns the CPU we should wake onto.
- */
-#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
-
-#define cpu_rd_active(cpu, rq) cpumask_test_cpu(cpu, rq->rd->online)
-
-static int wake_idle(int cpu, struct task_struct *p)
-{
-        struct sched_domain *sd;
-        int i;
-        unsigned int chosen_wakeup_cpu;
-        int this_cpu;
-        struct rq *task_rq = task_rq(p);
-
-        /*
-         * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
-         * are idle and this is not a kernel thread and this task's affinity
-         * allows it to be moved to preferred cpu, then just move!
-         */
-
-        this_cpu = smp_processor_id();
-        chosen_wakeup_cpu =
-                cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
-
-        if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
-                idle_cpu(cpu) && idle_cpu(this_cpu) &&
-                p->mm && !(p->flags & PF_KTHREAD) &&
-                cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))
-                return chosen_wakeup_cpu;
-
-        /*
-         * 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->clock, sd))) {
-                        for_each_cpu_and(i, sched_domain_span(sd),
-                                         &p->cpus_allowed) {
-                                if (cpu_rd_active(i, task_rq) && 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
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1225,25 +1155,34 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 #endif
 
-static int
-wake_affine(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)
+static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-        struct task_struct *curr = this_rq->curr;
-        struct task_group *tg;
-        unsigned long tl = this_load;
+        struct task_struct *curr = current;
+        unsigned long this_load, load;
+        int idx, this_cpu, prev_cpu;
         unsigned long tl_per_task;
+        unsigned int imbalance;
+        struct task_group *tg;
         unsigned long weight;
         int balanced;
 
-        if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
-                return 0;
+        idx       = sd->wake_idx;
+        this_cpu  = smp_processor_id();
+        prev_cpu  = task_cpu(p);
+        load      = source_load(prev_cpu, idx);
+        this_load = target_load(this_cpu, idx);
 
-        if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
-                        p->se.avg_overlap > sysctl_sched_migration_cost))
-                sync = 0;
+        if (sync) {
+               if (sched_feat(SYNC_LESS) &&
+                   (curr->se.avg_overlap > sysctl_sched_migration_cost ||
+                    p->se.avg_overlap > sysctl_sched_migration_cost))
+                       sync = 0;
+        } else {
+                if (sched_feat(SYNC_MORE) &&
+                    (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+                     p->se.avg_overlap < sysctl_sched_migration_cost))
+                        sync = 1;
+        }
 
         /*
          * If sync wakeup then subtract the (maximum possible)
@@ -1254,24 +1193,26 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
                 tg = task_group(current);
                 weight = current->se.load.weight;
 
-                tl += effective_load(tg, this_cpu, -weight, -weight);
+                this_load += effective_load(tg, this_cpu, -weight, -weight);
                 load += effective_load(tg, prev_cpu, 0, -weight);
         }
 
         tg = task_group(p);
         weight = p->se.load.weight;
 
+        imbalance = 100 + (sd->imbalance_pct - 100) / 2;
+
         /*
          * In low-load situations, where prev_cpu is idle and this_cpu is idle
-         * due to the sync cause above having dropped tl to 0, we'll always have
-         * an imbalance, but there's really nothing you can do about that, so
-         * that's good too.
+         * due to the sync cause above having dropped this_load to 0, we'll
+         * always have an imbalance, but there's really nothing you can do
+         * about that, so that's good too.
          *
          * Otherwise check if either cpus are near enough in load to allow this
          * task to be woken on this_cpu.
          */
-        balanced = !tl ||
-                100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+        balanced = !this_load ||
+                100*(this_load + effective_load(tg, this_cpu, weight, weight)) <=
                 imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
 
         /*
@@ -1285,14 +1226,15 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
         schedstat_inc(p, se.nr_wakeups_affine_attempts);
         tl_per_task = cpu_avg_load_per_task(this_cpu);
 
-        if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <=
-                        tl_per_task)) {
+        if (balanced ||
+            (this_load <= load &&
+             this_load + target_load(prev_cpu, idx) <= tl_per_task)) {
                 /*
                  * 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(sd, ttwu_move_affine);
                 schedstat_inc(p, se.nr_wakeups_affine);
 
                 return 1;
@@ -1300,65 +1242,215 @@ wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
         return 0;
 }
 
-static int select_task_rq_fair(struct task_struct *p, int sync)
+/*
+ * find_idlest_group finds and returns the least busy CPU group within the
+ * domain.
+ */
+static struct sched_group *
+find_idlest_group(struct sched_domain *sd, struct task_struct *p,
+                  int this_cpu, int load_idx)
 {
-        struct sched_domain *sd, *this_sd = NULL;
-        int prev_cpu, this_cpu, new_cpu;
-        unsigned long load, this_load;
-        struct rq *this_rq;
-        unsigned int imbalance;
-        int idx;
+        struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
+        unsigned long min_load = ULONG_MAX, this_load = 0;
+        int imbalance = 100 + (sd->imbalance_pct-100)/2;
 
-        prev_cpu        = task_cpu(p);
-        this_cpu        = smp_processor_id();
-        this_rq         = cpu_rq(this_cpu);
-        new_cpu         = prev_cpu;
+        do {
+                unsigned long load, avg_load;
+                int local_group;
+                int i;
 
-        /*
-         * 'this_sd' is the first domain that both
-         * this_cpu and prev_cpu are present in:
-         */
-        for_each_domain(this_cpu, sd) {
-                if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) {
-                        this_sd = sd;
-                        break;
+                /* Skip over this group if it has no CPUs allowed */
+                if (!cpumask_intersects(sched_group_cpus(group),
+                                        &p->cpus_allowed))
+                        continue;
+
+                local_group = cpumask_test_cpu(this_cpu,
+                                               sched_group_cpus(group));
+
+                /* Tally up the load of all CPUs in the group */
+                avg_load = 0;
+
+                for_each_cpu(i, sched_group_cpus(group)) {
+                        /* Bias balancing toward cpus of our domain */
+                        if (local_group)
+                                load = source_load(i, load_idx);
+                        else
+                                load = target_load(i, load_idx);
+
+                        avg_load += load;
+                }
+
+                /* Adjust by relative CPU power of the group */
+                avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
+
+                if (local_group) {
+                        this_load = avg_load;
+                        this = group;
+                } else if (avg_load < min_load) {
+                        min_load = avg_load;
+                        idlest = group;
+                }
+        } while (group = group->next, group != sd->groups);
+
+        if (!idlest || 100*this_load < imbalance*min_load)
+                return NULL;
+        return idlest;
+}
+
+/*
+ * find_idlest_cpu - find the idlest cpu among the cpus in group.
+ */
+static int
+find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
+{
+        unsigned long load, min_load = ULONG_MAX;
+        int idlest = -1;
+        int i;
+
+        /* Traverse only the allowed CPUs */
+        for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
+                load = weighted_cpuload(i);
+
+                if (load < min_load || (load == min_load && i == this_cpu)) {
+                        min_load = load;
+                        idlest = i;
                 }
         }
 
-        if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed)))
-                goto out;
+        return idlest;
+}
 
-        /*
-         * Check for affine wakeup and passive balancing possibilities.
-         */
-        if (!this_sd)
+/*
+ * sched_balance_self: balance the current task (running on cpu) in domains
+ * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
+ * SD_BALANCE_EXEC.
+ *
+ * Balance, ie. select the least loaded group.
+ *
+ * Returns the target CPU number, or the same CPU if no balancing is needed.
+ *
+ * preempt must be disabled.
+ */
+static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
+{
+        struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
+        int cpu = smp_processor_id();
+        int prev_cpu = task_cpu(p);
+        int new_cpu = cpu;
+        int want_affine = 0;
+        int want_sd = 1;
+        int sync = wake_flags & WF_SYNC;
+
+        if (sd_flag & SD_BALANCE_WAKE) {
+                if (sched_feat(AFFINE_WAKEUPS))
+                        want_affine = 1;
+                new_cpu = prev_cpu;
+        }
+
+        rcu_read_lock();
+        for_each_domain(cpu, tmp) {
+                /*
+                 * If power savings logic is enabled for a domain, see if we
+                 * are not overloaded, if so, don't balance wider.
+                 */
+                if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) {
+                        unsigned long power = 0;
+                        unsigned long nr_running = 0;
+                        unsigned long capacity;
+                        int i;
+
+                        for_each_cpu(i, sched_domain_span(tmp)) {
+                                power += power_of(i);
+                                nr_running += cpu_rq(i)->cfs.nr_running;
+                        }
+
+                        capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
+
+                        if (tmp->flags & SD_POWERSAVINGS_BALANCE)
+                                nr_running /= 2;
+
+                        if (nr_running < capacity)
+                                want_sd = 0;
+                }
+
+                if (want_affine && (tmp->flags & SD_WAKE_AFFINE) &&
+                    cpumask_test_cpu(prev_cpu, sched_domain_span(tmp))) {
+
+                        affine_sd = tmp;
+                        want_affine = 0;
+                }
+
+                if (!want_sd && !want_affine)
+                        break;
+
+                if (!(tmp->flags & sd_flag))
+                        continue;
+
+                if (want_sd)
+                        sd = tmp;
+        }
+
+        if (sched_feat(LB_SHARES_UPDATE)) {
+                /*
+                 * Pick the largest domain to update shares over
+                 */
+                tmp = sd;
+                if (affine_sd && (!tmp ||
+                                  cpumask_weight(sched_domain_span(affine_sd)) >
+                                  cpumask_weight(sched_domain_span(sd))))
+                        tmp = affine_sd;
+
+                if (tmp)
+                        update_shares(tmp);
+        }
+
+        if (affine_sd && wake_affine(affine_sd, p, sync)) {
+                new_cpu = cpu;
                 goto out;
+        }
 
-        idx = this_sd->wake_idx;
+        while (sd) {
+                int load_idx = sd->forkexec_idx;
+                struct sched_group *group;
+                int weight;
 
-        imbalance = 100 + (this_sd->imbalance_pct - 100) / 2;
+                if (!(sd->flags & sd_flag)) {
+                        sd = sd->child;
+                        continue;
+                }
 
-        load = source_load(prev_cpu, idx);
-        this_load = target_load(this_cpu, idx);
+                if (sd_flag & SD_BALANCE_WAKE)
+                        load_idx = sd->wake_idx;
 
-        if (wake_affine(this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
-                                     load, this_load, imbalance))
-                return this_cpu;
+                group = find_idlest_group(sd, p, cpu, load_idx);
+                if (!group) {
+                        sd = sd->child;
+                        continue;
+                }
 
-        /*
-         * 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;
+                new_cpu = find_idlest_cpu(group, p, cpu);
+                if (new_cpu == -1 || new_cpu == cpu) {
+                        /* Now try balancing at a lower domain level of cpu */
+                        sd = sd->child;
+                        continue;
                 }
+
+                /* Now try balancing at a lower domain level of new_cpu */
+                cpu = new_cpu;
+                weight = cpumask_weight(sched_domain_span(sd));
+                sd = NULL;
+                for_each_domain(cpu, tmp) {
+                        if (weight <= cpumask_weight(sched_domain_span(tmp)))
+                                break;
+                        if (tmp->flags & sd_flag)
+                                sd = tmp;
+                }
+                /* while loop will break here if sd == NULL */
         }
 
 out:
-        return wake_idle(new_cpu, p);
+        rcu_read_unlock();
+        return new_cpu;
 }
 #endif /* CONFIG_SMP */
 
@@ -1471,11 +1563,12 @@ static void set_next_buddy(struct sched_entity *se)
 /*
  * Preempt the current task with a newly woken task if needed:
  */
-static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
+static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
 {
         struct task_struct *curr = rq->curr;
         struct sched_entity *se = &curr->se, *pse = &p->se;
         struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+        int sync = wake_flags & WF_SYNC;
 
         update_curr(cfs_rq);
 
@@ -1501,7 +1594,8 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
          */
         if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
                 set_last_buddy(se);
-        set_next_buddy(pse);
+        if (sched_feat(NEXT_BUDDY) && !(wake_flags & WF_FORK))
+                set_next_buddy(pse);
 
         /*
          * We can come here with TIF_NEED_RESCHED already set from new task
@@ -1523,16 +1617,25 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
                 return;
         }
 
-        if (!sched_feat(WAKEUP_PREEMPT))
-                return;
-
-        if (sched_feat(WAKEUP_OVERLAP) && (sync ||
-                        (se->avg_overlap < sysctl_sched_migration_cost &&
-                         pse->avg_overlap < sysctl_sched_migration_cost))) {
+        if ((sched_feat(WAKEUP_SYNC) && sync) ||
+            (sched_feat(WAKEUP_OVERLAP) &&
+             (se->avg_overlap < sysctl_sched_migration_cost &&
+              pse->avg_overlap < sysctl_sched_migration_cost))) {
                 resched_task(curr);
                 return;
         }
 
+        if (sched_feat(WAKEUP_RUNNING)) {
+                if (pse->avg_running < se->avg_running) {
+                        set_next_buddy(pse);
+                        resched_task(curr);
+                        return;
+                }
+        }
+
+        if (!sched_feat(WAKEUP_PREEMPT))
+                return;
+
         find_matching_se(&se, &pse);
 
         BUG_ON(!pse);
@@ -1555,8 +1658,13 @@ static struct task_struct *pick_next_task_fair(struct rq *rq)
                 /*
                  * If se was a buddy, clear it so that it will have to earn
                  * the favour again.
+                 *
+                 * If se was not a buddy, clear the buddies because neither
+                 * was elegible to run, let them earn it again.
+                 *
+                 * IOW. unconditionally clear buddies.
                  */
-                __clear_buddies(cfs_rq, se);
+                __clear_buddies(cfs_rq, NULL);
                 set_next_entity(cfs_rq, se);
                 cfs_rq = group_cfs_rq(se);
         } while (cfs_rq);