5 files changed, 963 insertions, 17 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6c196794fc12..cc66f2615a6d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1201,6 +1201,7 @@ struct task_struct {
         struct list_head tasks;
 #ifdef CONFIG_SMP
         struct plist_node pushable_tasks;
+        struct rb_node pushable_dl_tasks;
 #endif
 
         struct mm_struct *mm, *active_mm;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 203aecdcfccb..548cc04aee45 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1848,6 +1848,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
         init_task_preempt_count(p);
 #ifdef CONFIG_SMP
         plist_node_init(&p->pushable_tasks, MAX_PRIO);
+        RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
 
         put_cpu();
@@ -5040,6 +5041,7 @@ static void free_rootdomain(struct rcu_head *rcu)
         struct root_domain *rd = container_of(rcu, struct root_domain, rcu);
 
         cpupri_cleanup(&rd->cpupri);
+        free_cpumask_var(rd->dlo_mask);
         free_cpumask_var(rd->rto_mask);
         free_cpumask_var(rd->online);
         free_cpumask_var(rd->span);
@@ -5091,8 +5093,10 @@ static int init_rootdomain(struct root_domain *rd)
                 goto out;
         if (!alloc_cpumask_var(&rd->online, GFP_KERNEL))
                 goto free_span;
-        if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+        if (!alloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL))
                 goto free_online;
+        if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL))
+                goto free_dlo_mask;
 
         if (cpupri_init(&rd->cpupri) != 0)
                 goto free_rto_mask;
@@ -5100,6 +5104,8 @@ static int init_rootdomain(struct root_domain *rd)
 
 free_rto_mask:
         free_cpumask_var(rd->rto_mask);
+free_dlo_mask:
+        free_cpumask_var(rd->dlo_mask);
 free_online:
         free_cpumask_var(rd->online);
 free_span:
@@ -6451,6 +6457,7 @@ void __init sched_init_smp(void)
         free_cpumask_var(non_isolated_cpus);
 
         init_sched_rt_class();
+        init_sched_dl_class();
 }
 #else
 void __init sched_init_smp(void)
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 93d82b2a88bd..fcc02c9ca16b 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -10,6 +10,7 @@
  * miss some of their deadlines), and won't affect any other task.
  *
  * Copyright (C) 2012 Dario Faggioli <raistlin@linux.it>,
+ *                    Juri Lelli <juri.lelli@gmail.com>,
  *                    Michael Trimarchi <michael@amarulasolutions.com>,
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
@@ -20,6 +21,15 @@ static inline int dl_time_before(u64 a, u64 b)
         return (s64)(a - b) < 0;
 }
 
+/*
+ * Tells if entity @a should preempt entity @b.
+ */
+static inline
+int dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+{
+        return dl_time_before(a->deadline, b->deadline);
+}
+
 static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se)
 {
         return container_of(dl_se, struct task_struct, dl);
@@ -53,8 +63,168 @@ static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq)
 void init_dl_rq(struct dl_rq *dl_rq, struct rq *rq)
 {
         dl_rq->rb_root = RB_ROOT;
+
+#ifdef CONFIG_SMP
+        /* zero means no -deadline tasks */
+        dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
+
+        dl_rq->dl_nr_migratory = 0;
+        dl_rq->overloaded = 0;
+        dl_rq->pushable_dl_tasks_root = RB_ROOT;
+#endif
+}
+
+#ifdef CONFIG_SMP
+
+static inline int dl_overloaded(struct rq *rq)
+{
+        return atomic_read(&rq->rd->dlo_count);
+}
+
+static inline void dl_set_overload(struct rq *rq)
+{
+        if (!rq->online)
+                return;
+
+        cpumask_set_cpu(rq->cpu, rq->rd->dlo_mask);
+        /*
+         * Must be visible before the overload count is
+         * set (as in sched_rt.c).
+         *
+         * Matched by the barrier in pull_dl_task().
+         */
+        smp_wmb();
+        atomic_inc(&rq->rd->dlo_count);
+}
+
+static inline void dl_clear_overload(struct rq *rq)
+{
+        if (!rq->online)
+                return;
+
+        atomic_dec(&rq->rd->dlo_count);
+        cpumask_clear_cpu(rq->cpu, rq->rd->dlo_mask);
+}
+
+static void update_dl_migration(struct dl_rq *dl_rq)
+{
+        if (dl_rq->dl_nr_migratory && dl_rq->dl_nr_total > 1) {
+                if (!dl_rq->overloaded) {
+                        dl_set_overload(rq_of_dl_rq(dl_rq));
+                        dl_rq->overloaded = 1;
+                }
+        } else if (dl_rq->overloaded) {
+                dl_clear_overload(rq_of_dl_rq(dl_rq));
+                dl_rq->overloaded = 0;
+        }
+}
+
+static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+        struct task_struct *p = dl_task_of(dl_se);
+        dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+        dl_rq->dl_nr_total++;
+        if (p->nr_cpus_allowed > 1)
+                dl_rq->dl_nr_migratory++;
+
+        update_dl_migration(dl_rq);
+}
+
+static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+        struct task_struct *p = dl_task_of(dl_se);
+        dl_rq = &rq_of_dl_rq(dl_rq)->dl;
+
+        dl_rq->dl_nr_total--;
+        if (p->nr_cpus_allowed > 1)
+                dl_rq->dl_nr_migratory--;
+
+        update_dl_migration(dl_rq);
+}
+
+/*
+ * The list of pushable -deadline task is not a plist, like in
+ * sched_rt.c, it is an rb-tree with tasks ordered by deadline.
+ */
+static void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+        struct dl_rq *dl_rq = &rq->dl;
+        struct rb_node **link = &dl_rq->pushable_dl_tasks_root.rb_node;
+        struct rb_node *parent = NULL;
+        struct task_struct *entry;
+        int leftmost = 1;
+
+        BUG_ON(!RB_EMPTY_NODE(&p->pushable_dl_tasks));
+
+        while (*link) {
+                parent = *link;
+                entry = rb_entry(parent, struct task_struct,
+                                 pushable_dl_tasks);
+                if (dl_entity_preempt(&p->dl, &entry->dl))
+                        link = &parent->rb_left;
+                else {
+                        link = &parent->rb_right;
+                        leftmost = 0;
+                }
+        }
+
+        if (leftmost)
+                dl_rq->pushable_dl_tasks_leftmost = &p->pushable_dl_tasks;
+
+        rb_link_node(&p->pushable_dl_tasks, parent, link);
+        rb_insert_color(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
 }
 
+static void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+        struct dl_rq *dl_rq = &rq->dl;
+
+        if (RB_EMPTY_NODE(&p->pushable_dl_tasks))
+                return;
+
+        if (dl_rq->pushable_dl_tasks_leftmost == &p->pushable_dl_tasks) {
+                struct rb_node *next_node;
+
+                next_node = rb_next(&p->pushable_dl_tasks);
+                dl_rq->pushable_dl_tasks_leftmost = next_node;
+        }
+
+        rb_erase(&p->pushable_dl_tasks, &dl_rq->pushable_dl_tasks_root);
+        RB_CLEAR_NODE(&p->pushable_dl_tasks);
+}
+
+static inline int has_pushable_dl_tasks(struct rq *rq)
+{
+        return !RB_EMPTY_ROOT(&rq->dl.pushable_dl_tasks_root);
+}
+
+static int push_dl_task(struct rq *rq);
+
+#else
+
+static inline
+void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
+{
+}
+
+static inline
+void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+static inline
+void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+}
+
+#endif /* CONFIG_SMP */
+
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags);
 static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
@@ -309,6 +479,14 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
                         check_preempt_curr_dl(rq, p, 0);
                 else
                         resched_task(rq->curr);
+#ifdef CONFIG_SMP
+                /*
+                 * Queueing this task back might have overloaded rq,
+                 * check if we need to kick someone away.
+                 */
+                if (has_pushable_dl_tasks(rq))
+                        push_dl_task(rq);
+#endif
         }
 unlock:
         raw_spin_unlock(&rq->lock);
@@ -399,6 +577,100 @@ static void update_curr_dl(struct rq *rq)
         }
 }
 
+#ifdef CONFIG_SMP
+
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu);
+
+static inline u64 next_deadline(struct rq *rq)
+{
+        struct task_struct *next = pick_next_earliest_dl_task(rq, rq->cpu);
+
+        if (next && dl_prio(next->prio))
+                return next->dl.deadline;
+        else
+                return 0;
+}
+
+static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+        struct rq *rq = rq_of_dl_rq(dl_rq);
+
+        if (dl_rq->earliest_dl.curr == 0 ||
+            dl_time_before(deadline, dl_rq->earliest_dl.curr)) {
+                /*
+                 * If the dl_rq had no -deadline tasks, or if the new task
+                 * has shorter deadline than the current one on dl_rq, we
+                 * know that the previous earliest becomes our next earliest,
+                 * as the new task becomes the earliest itself.
+                 */
+                dl_rq->earliest_dl.next = dl_rq->earliest_dl.curr;
+                dl_rq->earliest_dl.curr = deadline;
+        } else if (dl_rq->earliest_dl.next == 0 ||
+                   dl_time_before(deadline, dl_rq->earliest_dl.next)) {
+                /*
+                 * On the other hand, if the new -deadline task has a
+                 * a later deadline than the earliest one on dl_rq, but
+                 * it is earlier than the next (if any), we must
+                 * recompute the next-earliest.
+                 */
+                dl_rq->earliest_dl.next = next_deadline(rq);
+        }
+}
+
+static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
+{
+        struct rq *rq = rq_of_dl_rq(dl_rq);
+
+        /*
+         * Since we may have removed our earliest (and/or next earliest)
+         * task we must recompute them.
+         */
+        if (!dl_rq->dl_nr_running) {
+                dl_rq->earliest_dl.curr = 0;
+                dl_rq->earliest_dl.next = 0;
+        } else {
+                struct rb_node *leftmost = dl_rq->rb_leftmost;
+                struct sched_dl_entity *entry;
+
+                entry = rb_entry(leftmost, struct sched_dl_entity, rb_node);
+                dl_rq->earliest_dl.curr = entry->deadline;
+                dl_rq->earliest_dl.next = next_deadline(rq);
+        }
+}
+
+#else
+
+static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
+
+#endif /* CONFIG_SMP */
+
+static inline
+void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+        int prio = dl_task_of(dl_se)->prio;
+        u64 deadline = dl_se->deadline;
+
+        WARN_ON(!dl_prio(prio));
+        dl_rq->dl_nr_running++;
+
+        inc_dl_deadline(dl_rq, deadline);
+        inc_dl_migration(dl_se, dl_rq);
+}
+
+static inline
+void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
+{
+        int prio = dl_task_of(dl_se)->prio;
+
+        WARN_ON(!dl_prio(prio));
+        WARN_ON(!dl_rq->dl_nr_running);
+        dl_rq->dl_nr_running--;
+
+        dec_dl_deadline(dl_rq, dl_se->deadline);
+        dec_dl_migration(dl_se, dl_rq);
+}
+
 static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
 {
         struct dl_rq *dl_rq = dl_rq_of_se(dl_se);
@@ -426,7 +698,7 @@ static void __enqueue_dl_entity(struct sched_dl_entity *dl_se)
         rb_link_node(&dl_se->rb_node, parent, link);
         rb_insert_color(&dl_se->rb_node, &dl_rq->rb_root);
 
-        dl_rq->dl_nr_running++;
+        inc_dl_tasks(dl_se, dl_rq);
 }
 
 static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
@@ -446,7 +718,7 @@ static void __dequeue_dl_entity(struct sched_dl_entity *dl_se)
         rb_erase(&dl_se->rb_node, &dl_rq->rb_root);
         RB_CLEAR_NODE(&dl_se->rb_node);
 
-        dl_rq->dl_nr_running--;
+        dec_dl_tasks(dl_se, dl_rq);
 }
 
 static void
@@ -484,12 +756,17 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
                 return;
 
         enqueue_dl_entity(&p->dl, flags);
+
+        if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
+                enqueue_pushable_dl_task(rq, p);
+
         inc_nr_running(rq);
 }
 
 static void __dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 {
         dequeue_dl_entity(&p->dl);
+        dequeue_pushable_dl_task(rq, p);
 }
 
 static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags)
@@ -527,6 +804,74 @@ static void yield_task_dl(struct rq *rq)
         update_curr_dl(rq);
 }
 
+#ifdef CONFIG_SMP
+
+static int find_later_rq(struct task_struct *task);
+static int latest_cpu_find(struct cpumask *span,
+                           struct task_struct *task,
+                           struct cpumask *later_mask);
+
+static int
+select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags)
+{
+        struct task_struct *curr;
+        struct rq *rq;
+
+        if (sd_flag != SD_BALANCE_WAKE && sd_flag != SD_BALANCE_FORK)
+                goto out;
+
+        rq = cpu_rq(cpu);
+
+        rcu_read_lock();
+        curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
+        /*
+         * If we are dealing with a -deadline task, we must
+         * decide where to wake it up.
+         * If it has a later deadline and the current task
+         * on this rq can't move (provided the waking task
+         * can!) we prefer to send it somewhere else. On the
+         * other hand, if it has a shorter deadline, we
+         * try to make it stay here, it might be important.
+         */
+        if (unlikely(dl_task(curr)) &&
+            (curr->nr_cpus_allowed < 2 ||
+             !dl_entity_preempt(&p->dl, &curr->dl)) &&
+            (p->nr_cpus_allowed > 1)) {
+                int target = find_later_rq(p);
+
+                if (target != -1)
+                        cpu = target;
+        }
+        rcu_read_unlock();
+
+out:
+        return cpu;
+}
+
+static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p)
+{
+        /*
+         * Current can't be migrated, useless to reschedule,
+         * let's hope p can move out.
+         */
+        if (rq->curr->nr_cpus_allowed == 1 ||
+            latest_cpu_find(rq->rd->span, rq->curr, NULL) == -1)
+                return;
+
+        /*
+         * p is migratable, so let's not schedule it and
+         * see if it is pushed or pulled somewhere else.
+         */
+        if (p->nr_cpus_allowed != 1 &&
+            latest_cpu_find(rq->rd->span, p, NULL) != -1)
+                return;
+
+        resched_task(rq->curr);
+}
+
+#endif /* CONFIG_SMP */
+
 /*
  * Only called when both the current and waking task are -deadline
  * tasks.
@@ -534,8 +879,20 @@ static void yield_task_dl(struct rq *rq)
 static void check_preempt_curr_dl(struct rq *rq, struct task_struct *p,
                                   int flags)
 {
-        if (dl_time_before(p->dl.deadline, rq->curr->dl.deadline))
+        if (dl_entity_preempt(&p->dl, &rq->curr->dl)) {
                 resched_task(rq->curr);
+                return;
+        }
+
+#ifdef CONFIG_SMP
+        /*
+         * In the unlikely case current and p have the same deadline
+         * let us try to decide what's the best thing to do...
+         */
+        if ((s64)(p->dl.deadline - rq->curr->dl.deadline) == 0 &&
+            !need_resched())
+                check_preempt_equal_dl(rq, p);
+#endif /* CONFIG_SMP */
 }
 
 #ifdef CONFIG_SCHED_HRTICK
@@ -575,16 +932,29 @@ struct task_struct *pick_next_task_dl(struct rq *rq)
 
         p = dl_task_of(dl_se);
         p->se.exec_start = rq_clock_task(rq);
+
+        /* Running task will never be pushed. */
+        if (p)
+                dequeue_pushable_dl_task(rq, p);
+
 #ifdef CONFIG_SCHED_HRTICK
         if (hrtick_enabled(rq))
                 start_hrtick_dl(rq, p);
 #endif
+
+#ifdef CONFIG_SMP
+        rq->post_schedule = has_pushable_dl_tasks(rq);
+#endif /* CONFIG_SMP */
+
         return p;
 }
 
 static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
         update_curr_dl(rq);
+
+        if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
+                enqueue_pushable_dl_task(rq, p);
 }
 
 static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
@@ -618,16 +988,517 @@ static void set_curr_task_dl(struct rq *rq)
         struct task_struct *p = rq->curr;
 
         p->se.exec_start = rq_clock_task(rq);
+
+        /* You can't push away the running task */
+        dequeue_pushable_dl_task(rq, p);
+}
+
+#ifdef CONFIG_SMP
+
+/* Only try algorithms three times */
+#define DL_MAX_TRIES 3
+
+static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
+{
+        if (!task_running(rq, p) &&
+            (cpu < 0 || cpumask_test_cpu(cpu, &p->cpus_allowed)) &&
+            (p->nr_cpus_allowed > 1))
+                return 1;
+
+        return 0;
+}
+
+/* Returns the second earliest -deadline task, NULL otherwise */
+static struct task_struct *pick_next_earliest_dl_task(struct rq *rq, int cpu)
+{
+        struct rb_node *next_node = rq->dl.rb_leftmost;
+        struct sched_dl_entity *dl_se;
+        struct task_struct *p = NULL;
+
+next_node:
+        next_node = rb_next(next_node);
+        if (next_node) {
+                dl_se = rb_entry(next_node, struct sched_dl_entity, rb_node);
+                p = dl_task_of(dl_se);
+
+                if (pick_dl_task(rq, p, cpu))
+                        return p;
+
+                goto next_node;
+        }
+
+        return NULL;
+}
+
+static int latest_cpu_find(struct cpumask *span,
+                           struct task_struct *task,
+                           struct cpumask *later_mask)
+{
+        const struct sched_dl_entity *dl_se = &task->dl;
+        int cpu, found = -1, best = 0;
+        u64 max_dl = 0;
+
+        for_each_cpu(cpu, span) {
+                struct rq *rq = cpu_rq(cpu);
+                struct dl_rq *dl_rq = &rq->dl;
+
+                if (cpumask_test_cpu(cpu, &task->cpus_allowed) &&
+                    (!dl_rq->dl_nr_running || dl_time_before(dl_se->deadline,
+                     dl_rq->earliest_dl.curr))) {
+                        if (later_mask)
+                                cpumask_set_cpu(cpu, later_mask);
+                        if (!best && !dl_rq->dl_nr_running) {
+                                best = 1;
+                                found = cpu;
+                        } else if (!best &&
+                                   dl_time_before(max_dl,
+                                                  dl_rq->earliest_dl.curr)) {
+                                max_dl = dl_rq->earliest_dl.curr;
+                                found = cpu;
+                        }
+                } else if (later_mask)
+                        cpumask_clear_cpu(cpu, later_mask);
+        }
+
+        return found;
+}
+
+static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
+
+static int find_later_rq(struct task_struct *task)
+{
+        struct sched_domain *sd;
+        struct cpumask *later_mask = __get_cpu_var(local_cpu_mask_dl);
+        int this_cpu = smp_processor_id();
+        int best_cpu, cpu = task_cpu(task);
+
+        /* Make sure the mask is initialized first */
+        if (unlikely(!later_mask))
+                return -1;
+
+        if (task->nr_cpus_allowed == 1)
+                return -1;
+
+        best_cpu = latest_cpu_find(task_rq(task)->rd->span, task, later_mask);
+        if (best_cpu == -1)
+                return -1;
+
+        /*
+         * If we are here, some target has been found,
+         * the most suitable of which is cached in best_cpu.
+         * This is, among the runqueues where the current tasks
+         * have later deadlines than the task's one, the rq
+         * with the latest possible one.
+         *
+         * Now we check how well this matches with task's
+         * affinity and system topology.
+         *
+         * The last cpu where the task run is our first
+         * guess, since it is most likely cache-hot there.
+         */
+        if (cpumask_test_cpu(cpu, later_mask))
+                return cpu;
+        /*
+         * Check if this_cpu is to be skipped (i.e., it is
+         * not in the mask) or not.
+         */
+        if (!cpumask_test_cpu(this_cpu, later_mask))
+                this_cpu = -1;
+
+        rcu_read_lock();
+        for_each_domain(cpu, sd) {
+                if (sd->flags & SD_WAKE_AFFINE) {
+
+                        /*
+                         * If possible, preempting this_cpu is
+                         * cheaper than migrating.
+                         */
+                        if (this_cpu != -1 &&
+                            cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+                                rcu_read_unlock();
+                                return this_cpu;
+                        }
+
+                        /*
+                         * Last chance: if best_cpu is valid and is
+                         * in the mask, that becomes our choice.
+                         */
+                        if (best_cpu < nr_cpu_ids &&
+                            cpumask_test_cpu(best_cpu, sched_domain_span(sd))) {
+                                rcu_read_unlock();
+                                return best_cpu;
+                        }
+                }
+        }
+        rcu_read_unlock();
+
+        /*
+         * At this point, all our guesses failed, we just return
+         * 'something', and let the caller sort the things out.
+         */
+        if (this_cpu != -1)
+                return this_cpu;
+
+        cpu = cpumask_any(later_mask);
+        if (cpu < nr_cpu_ids)
+                return cpu;
+
+        return -1;
+}
+
+/* Locks the rq it finds */
+static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
+{
+        struct rq *later_rq = NULL;
+        int tries;
+        int cpu;
+
+        for (tries = 0; tries < DL_MAX_TRIES; tries++) {
+                cpu = find_later_rq(task);
+
+                if ((cpu == -1) || (cpu == rq->cpu))
+                        break;
+
+                later_rq = cpu_rq(cpu);
+
+                /* Retry if something changed. */
+                if (double_lock_balance(rq, later_rq)) {
+                        if (unlikely(task_rq(task) != rq ||
+                                     !cpumask_test_cpu(later_rq->cpu,
+                                                       &task->cpus_allowed) ||
+                                     task_running(rq, task) || !task->on_rq)) {
+                                double_unlock_balance(rq, later_rq);
+                                later_rq = NULL;
+                                break;
+                        }
+                }
+
+                /*
+                 * If the rq we found has no -deadline task, or
+                 * its earliest one has a later deadline than our
+                 * task, the rq is a good one.
+                 */
+                if (!later_rq->dl.dl_nr_running ||
+                    dl_time_before(task->dl.deadline,
+                                   later_rq->dl.earliest_dl.curr))
+                        break;
+
+                /* Otherwise we try again. */
+                double_unlock_balance(rq, later_rq);
+                later_rq = NULL;
+        }
+
+        return later_rq;
+}
+
+static struct task_struct *pick_next_pushable_dl_task(struct rq *rq)
+{
+        struct task_struct *p;
+
+        if (!has_pushable_dl_tasks(rq))
+                return NULL;
+
+        p = rb_entry(rq->dl.pushable_dl_tasks_leftmost,
+                     struct task_struct, pushable_dl_tasks);
+
+        BUG_ON(rq->cpu != task_cpu(p));
+        BUG_ON(task_current(rq, p));
+        BUG_ON(p->nr_cpus_allowed <= 1);
+
+        BUG_ON(!p->se.on_rq);
+        BUG_ON(!dl_task(p));
+
+        return p;
+}
+
+/*
+ * See if the non running -deadline tasks on this rq
+ * can be sent to some other CPU where they can preempt
+ * and start executing.
+ */
+static int push_dl_task(struct rq *rq)
+{
+        struct task_struct *next_task;
+        struct rq *later_rq;
+
+        if (!rq->dl.overloaded)
+                return 0;
+
+        next_task = pick_next_pushable_dl_task(rq);
+        if (!next_task)
+                return 0;
+
+retry:
+        if (unlikely(next_task == rq->curr)) {
+                WARN_ON(1);
+                return 0;
+        }
+
+        /*
+         * If next_task preempts rq->curr, and rq->curr
+         * can move away, it makes sense to just reschedule
+         * without going further in pushing next_task.
+         */
+        if (dl_task(rq->curr) &&
+            dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) &&
+            rq->curr->nr_cpus_allowed > 1) {
+                resched_task(rq->curr);
+                return 0;
+        }
+
+        /* We might release rq lock */
+        get_task_struct(next_task);
+
+        /* Will lock the rq it'll find */
+        later_rq = find_lock_later_rq(next_task, rq);
+        if (!later_rq) {
+                struct task_struct *task;
+
+                /*
+                 * We must check all this again, since
+                 * find_lock_later_rq releases rq->lock and it is
+                 * then possible that next_task has migrated.
+                 */
+                task = pick_next_pushable_dl_task(rq);
+                if (task_cpu(next_task) == rq->cpu && task == next_task) {
+                        /*
+                         * The task is still there. We don't try
+                         * again, some other cpu will pull it when ready.
+                         */
+                        dequeue_pushable_dl_task(rq, next_task);
+                        goto out;
+                }
+
+                if (!task)
+                        /* No more tasks */
+                        goto out;
+
+                put_task_struct(next_task);
+                next_task = task;
+                goto retry;
+        }
+
+        deactivate_task(rq, next_task, 0);
+        set_task_cpu(next_task, later_rq->cpu);
+        activate_task(later_rq, next_task, 0);
+
+        resched_task(later_rq->curr);
+
+        double_unlock_balance(rq, later_rq);
+
+out:
+        put_task_struct(next_task);
+
+        return 1;
+}
+
+static void push_dl_tasks(struct rq *rq)
+{
+        /* Terminates as it moves a -deadline task */
+        while (push_dl_task(rq))
+                ;
 }
 
+static int pull_dl_task(struct rq *this_rq)
+{
+        int this_cpu = this_rq->cpu, ret = 0, cpu;
+        struct task_struct *p;
+        struct rq *src_rq;
+        u64 dmin = LONG_MAX;
+
+        if (likely(!dl_overloaded(this_rq)))
+                return 0;
+
+        /*
+         * Match the barrier from dl_set_overloaded; this guarantees that if we
+         * see overloaded we must also see the dlo_mask bit.
+         */
+        smp_rmb();
+
+        for_each_cpu(cpu, this_rq->rd->dlo_mask) {
+                if (this_cpu == cpu)
+                        continue;
+
+                src_rq = cpu_rq(cpu);
+
+                /*
+                 * It looks racy, abd it is! However, as in sched_rt.c,
+                 * we are fine with this.
+                 */
+                if (this_rq->dl.dl_nr_running &&
+                    dl_time_before(this_rq->dl.earliest_dl.curr,
+                                   src_rq->dl.earliest_dl.next))
+                        continue;
+
+                /* Might drop this_rq->lock */
+                double_lock_balance(this_rq, src_rq);
+
+                /*
+                 * If there are no more pullable tasks on the
+                 * rq, we're done with it.
+                 */
+                if (src_rq->dl.dl_nr_running <= 1)
+                        goto skip;
+
+                p = pick_next_earliest_dl_task(src_rq, this_cpu);
+
+                /*
+                 * We found a task to be pulled if:
+                 *  - it preempts our current (if there's one),
+                 *  - it will preempt the last one we pulled (if any).
+                 */
+                if (p && dl_time_before(p->dl.deadline, dmin) &&
+                    (!this_rq->dl.dl_nr_running ||
+                     dl_time_before(p->dl.deadline,
+                                    this_rq->dl.earliest_dl.curr))) {
+                        WARN_ON(p == src_rq->curr);
+                        WARN_ON(!p->se.on_rq);
+
+                        /*
+                         * Then we pull iff p has actually an earlier
+                         * deadline than the current task of its runqueue.
+                         */
+                        if (dl_time_before(p->dl.deadline,
+                                           src_rq->curr->dl.deadline))
+                                goto skip;
+
+                        ret = 1;
+
+                        deactivate_task(src_rq, p, 0);
+                        set_task_cpu(p, this_cpu);
+                        activate_task(this_rq, p, 0);
+                        dmin = p->dl.deadline;
+
+                        /* Is there any other task even earlier? */
+                }
+skip:
+                double_unlock_balance(this_rq, src_rq);
+        }
+
+        return ret;
+}
+
+static void pre_schedule_dl(struct rq *rq, struct task_struct *prev)
+{
+        /* Try to pull other tasks here */
+        if (dl_task(prev))
+                pull_dl_task(rq);
+}
+
+static void post_schedule_dl(struct rq *rq)
+{
+        push_dl_tasks(rq);
+}
+
+/*
+ * Since the task is not running and a reschedule is not going to happen
+ * anytime soon on its runqueue, we try pushing it away now.
+ */
+static void task_woken_dl(struct rq *rq, struct task_struct *p)
+{
+        if (!task_running(rq, p) &&
+            !test_tsk_need_resched(rq->curr) &&
+            has_pushable_dl_tasks(rq) &&
+            p->nr_cpus_allowed > 1 &&
+            dl_task(rq->curr) &&
+            (rq->curr->nr_cpus_allowed < 2 ||
+             dl_entity_preempt(&rq->curr->dl, &p->dl))) {
+                push_dl_tasks(rq);
+        }
+}
+
+static void set_cpus_allowed_dl(struct task_struct *p,
+                                const struct cpumask *new_mask)
+{
+        struct rq *rq;
+        int weight;
+
+        BUG_ON(!dl_task(p));
+
+        /*
+         * Update only if the task is actually running (i.e.,
+         * it is on the rq AND it is not throttled).
+         */
+        if (!on_dl_rq(&p->dl))
+                return;
+
+        weight = cpumask_weight(new_mask);
+
+        /*
+         * Only update if the process changes its state from whether it
+         * can migrate or not.
+         */
+        if ((p->nr_cpus_allowed > 1) == (weight > 1))
+                return;
+
+        rq = task_rq(p);
+
+        /*
+         * The process used to be able to migrate OR it can now migrate
+         */
+        if (weight <= 1) {
+                if (!task_current(rq, p))
+                        dequeue_pushable_dl_task(rq, p);
+                BUG_ON(!rq->dl.dl_nr_migratory);
+                rq->dl.dl_nr_migratory--;
+        } else {
+                if (!task_current(rq, p))
+                        enqueue_pushable_dl_task(rq, p);
+                rq->dl.dl_nr_migratory++;
+        }
+
+        update_dl_migration(&rq->dl);
+}
+
+/* Assumes rq->lock is held */
+static void rq_online_dl(struct rq *rq)
+{
+        if (rq->dl.overloaded)
+                dl_set_overload(rq);
+}
+
+/* Assumes rq->lock is held */
+static void rq_offline_dl(struct rq *rq)
+{
+        if (rq->dl.overloaded)
+                dl_clear_overload(rq);
+}
+
+void init_sched_dl_class(void)
+{
+        unsigned int i;
+
+        for_each_possible_cpu(i)
+                zalloc_cpumask_var_node(&per_cpu(local_cpu_mask_dl, i),
+                                        GFP_KERNEL, cpu_to_node(i));
+}
+
+#endif /* CONFIG_SMP */
+
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
-        if (hrtimer_active(&p->dl.dl_timer))
+        if (hrtimer_active(&p->dl.dl_timer) && !dl_policy(p->policy))
                 hrtimer_try_to_cancel(&p->dl.dl_timer);
+
+#ifdef CONFIG_SMP
+        /*
+         * Since this might be the only -deadline task on the rq,
+         * this is the right place to try to pull some other one
+         * from an overloaded cpu, if any.
+         */
+        if (!rq->dl.dl_nr_running)
+                pull_dl_task(rq);
+#endif
 }
 
+/*
+ * When switching to -deadline, we may overload the rq, then
+ * we try to push someone off, if possible.
+ */
 static void switched_to_dl(struct rq *rq, struct task_struct *p)
 {
+        int check_resched = 1;
+
         /*
          * If p is throttled, don't consider the possibility
          * of preempting rq->curr, the check will be done right
@@ -637,26 +1508,53 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
                 return;
 
         if (p->on_rq || rq->curr != p) {
-                if (task_has_dl_policy(rq->curr))
+#ifdef CONFIG_SMP
+                if (rq->dl.overloaded && push_dl_task(rq) && rq != task_rq(p))
+                        /* Only reschedule if pushing failed */
+                        check_resched = 0;
+#endif /* CONFIG_SMP */
+                if (check_resched && task_has_dl_policy(rq->curr))
                         check_preempt_curr_dl(rq, p, 0);
-                else
-                        resched_task(rq->curr);
         }
 }
 
+/*
+ * If the scheduling parameters of a -deadline task changed,
+ * a push or pull operation might be needed.
+ */
 static void prio_changed_dl(struct rq *rq, struct task_struct *p,
                             int oldprio)
 {
-        switched_to_dl(rq, p);
-}
-
+        if (p->on_rq || rq->curr == p) {
 #ifdef CONFIG_SMP
-static int
-select_task_rq_dl(struct task_struct *p, int prev_cpu, int sd_flag, int flags)
-{
-        return task_cpu(p);
+                /*
+                 * This might be too much, but unfortunately
+                 * we don't have the old deadline value, and
+                 * we can't argue if the task is increasing
+                 * or lowering its prio, so...
+                 */
+                if (!rq->dl.overloaded)
+                        pull_dl_task(rq);
+
+                /*
+                 * If we now have a earlier deadline task than p,
+                 * then reschedule, provided p is still on this
+                 * runqueue.
+                 */
+                if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline) &&
+                    rq->curr == p)
+                        resched_task(p);
+#else
+                /*
+                 * Again, we don't know if p has a earlier
+                 * or later deadline, so let's blindly set a
+                 * (maybe not needed) rescheduling point.
+                 */
+                resched_task(p);
+#endif /* CONFIG_SMP */
+        } else
+                switched_to_dl(rq, p);
 }
-#endif
 
 const struct sched_class dl_sched_class = {
         .next                   = &rt_sched_class,
@@ -671,6 +1569,12 @@ const struct sched_class dl_sched_class = {
 
 #ifdef CONFIG_SMP
         .select_task_rq         = select_task_rq_dl,
+        .set_cpus_allowed       = set_cpus_allowed_dl,
+        .rq_online              = rq_online_dl,
+        .rq_offline             = rq_offline_dl,
+        .pre_schedule           = pre_schedule_dl,
+        .post_schedule          = post_schedule_dl,
+        .task_woken             = task_woken_dl,
 #endif
 
         .set_curr_task          = set_curr_task_dl,
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1c4065575fa2..a2740b775b45 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1738,7 +1738,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
             !test_tsk_need_resched(rq->curr) &&
             has_pushable_tasks(rq) &&
             p->nr_cpus_allowed > 1 &&
-            rt_task(rq->curr) &&
+            (dl_task(rq->curr) || rt_task(rq->curr)) &&
             (rq->curr->nr_cpus_allowed < 2 ||
              rq->curr->prio <= p->prio))
                 push_rt_tasks(rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 83eb5390f753..93ea62754f11 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -385,6 +385,31 @@ struct dl_rq {
         struct rb_node *rb_leftmost;
 
         unsigned long dl_nr_running;
+
+#ifdef CONFIG_SMP
+        /*
+         * Deadline values of the currently executing and the
+         * earliest ready task on this rq. Caching these facilitates
+         * the decision wether or not a ready but not running task
+         * should migrate somewhere else.
+         */
+        struct {
+                u64 curr;
+                u64 next;
+        } earliest_dl;
+
+        unsigned long dl_nr_migratory;
+        unsigned long dl_nr_total;
+        int overloaded;
+
+        /*
+         * Tasks on this rq that can be pushed away. They are kept in
+         * an rb-tree, ordered by tasks' deadlines, with caching
+         * of the leftmost (earliest deadline) element.
+         */
+        struct rb_root pushable_dl_tasks_root;
+        struct rb_node *pushable_dl_tasks_leftmost;
+#endif
 };
 
 #ifdef CONFIG_SMP
@@ -405,6 +430,13 @@ struct root_domain {
         cpumask_var_t online;
 
         /*
+         * The bit corresponding to a CPU gets set here if such CPU has more
+         * than one runnable -deadline task (as it is below for RT tasks).
+         */
+        cpumask_var_t dlo_mask;
+        atomic_t dlo_count;
+
+        /*
          * The "RT overload" flag: it gets set if a CPU has more than
          * one runnable RT task.
          */
@@ -1095,6 +1127,8 @@ static inline void idle_balance(int cpu, struct rq *rq)
 extern void sysrq_sched_debug_show(void);
 extern void sched_init_granularity(void);
 extern void update_max_interval(void);
+
+extern void init_sched_dl_class(void);
 extern void init_sched_rt_class(void);
 extern void init_sched_fair_class(void);