1 files changed, 136 insertions, 56 deletions

diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index e40e7fe43170..58cf5d18dfdc 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -183,6 +183,25 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
         return ktime_to_ns(rt_rq->tg->rt_bandwidth.rt_period);
 }
 
+typedef struct task_group *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+        for (iter = list_entry_rcu(task_groups.next, typeof(*iter), list); \
+             (&iter->list != &task_groups) && \
+             (rt_rq = iter->rt_rq[cpu_of(rq)]); \
+             iter = list_entry_rcu(iter->list.next, typeof(*iter), list))
+
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+        list_add_rcu(&rt_rq->leaf_rt_rq_list,
+                        &rq_of_rt_rq(rt_rq)->leaf_rt_rq_list);
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+        list_del_rcu(&rt_rq->leaf_rt_rq_list);
+}
+
 #define for_each_leaf_rt_rq(rt_rq, rq) \
         list_for_each_entry_rcu(rt_rq, &rq->leaf_rt_rq_list, leaf_rt_rq_list)
 
@@ -199,11 +218,12 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se);
 
 static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 {
-        int this_cpu = smp_processor_id();
         struct task_struct *curr = rq_of_rt_rq(rt_rq)->curr;
         struct sched_rt_entity *rt_se;
 
-        rt_se = rt_rq->tg->rt_se[this_cpu];
+        int cpu = cpu_of(rq_of_rt_rq(rt_rq));
+
+        rt_se = rt_rq->tg->rt_se[cpu];
 
         if (rt_rq->rt_nr_running) {
                 if (rt_se && !on_rt_rq(rt_se))
@@ -215,10 +235,10 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq)
 
 static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
 {
-        int this_cpu = smp_processor_id();
         struct sched_rt_entity *rt_se;
+        int cpu = cpu_of(rq_of_rt_rq(rt_rq));
 
-        rt_se = rt_rq->tg->rt_se[this_cpu];
+        rt_se = rt_rq->tg->rt_se[cpu];
 
         if (rt_se && on_rt_rq(rt_se))
                 dequeue_rt_entity(rt_se);
@@ -276,6 +296,19 @@ static inline u64 sched_rt_period(struct rt_rq *rt_rq)
         return ktime_to_ns(def_rt_bandwidth.rt_period);
 }
 
+typedef struct rt_rq *rt_rq_iter_t;
+
+#define for_each_rt_rq(rt_rq, iter, rq) \
+        for ((void) iter, rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
+
+static inline void list_add_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
+static inline void list_del_leaf_rt_rq(struct rt_rq *rt_rq)
+{
+}
+
 #define for_each_leaf_rt_rq(rt_rq, rq) \
         for (rt_rq = &rq->rt; rt_rq; rt_rq = NULL)
 
@@ -382,12 +415,13 @@ next:
 static void __disable_runtime(struct rq *rq)
 {
         struct root_domain *rd = rq->rd;
+        rt_rq_iter_t iter;
         struct rt_rq *rt_rq;
 
         if (unlikely(!scheduler_running))
                 return;
 
-        for_each_leaf_rt_rq(rt_rq, rq) {
+        for_each_rt_rq(rt_rq, iter, rq) {
                 struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
                 s64 want;
                 int i;
@@ -467,6 +501,7 @@ static void disable_runtime(struct rq *rq)
 
 static void __enable_runtime(struct rq *rq)
 {
+        rt_rq_iter_t iter;
         struct rt_rq *rt_rq;
 
         if (unlikely(!scheduler_running))
@@ -475,7 +510,7 @@ static void __enable_runtime(struct rq *rq)
         /*
          * Reset each runqueue's bandwidth settings
          */
-        for_each_leaf_rt_rq(rt_rq, rq) {
+        for_each_rt_rq(rt_rq, iter, rq) {
                 struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
 
                 raw_spin_lock(&rt_b->rt_runtime_lock);
@@ -542,12 +577,22 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
                         if (rt_rq->rt_throttled && rt_rq->rt_time < runtime) {
                                 rt_rq->rt_throttled = 0;
                                 enqueue = 1;
+
+                                /*
+                                 * Force a clock update if the CPU was idle,
+                                 * lest wakeup -> unthrottle time accumulate.
+                                 */
+                                if (rt_rq->rt_nr_running && rq->curr == rq->idle)
+                                        rq->skip_clock_update = -1;
                         }
                         if (rt_rq->rt_time || rt_rq->rt_nr_running)
                                 idle = 0;
                         raw_spin_unlock(&rt_rq->rt_runtime_lock);
-                } else if (rt_rq->rt_nr_running)
+                } else if (rt_rq->rt_nr_running) {
                         idle = 0;
+                        if (!rt_rq_throttled(rt_rq))
+                                enqueue = 1;
+                }
 
                 if (enqueue)
                         sched_rt_rq_enqueue(rt_rq);
@@ -606,10 +651,10 @@ static void update_curr_rt(struct rq *rq)
         struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
         u64 delta_exec;
 
-        if (!task_has_rt_policy(curr))
+        if (curr->sched_class != &rt_sched_class)
                 return;
 
-        delta_exec = rq->clock - curr->se.exec_start;
+        delta_exec = rq->clock_task - curr->se.exec_start;
         if (unlikely((s64)delta_exec < 0))
                 delta_exec = 0;
 
@@ -618,7 +663,7 @@ static void update_curr_rt(struct rq *rq)
         curr->se.sum_exec_runtime += delta_exec;
         account_group_exec_runtime(curr, delta_exec);
 
-        curr->se.exec_start = rq->clock;
+        curr->se.exec_start = rq->clock_task;
         cpuacct_charge(curr, delta_exec);
 
         sched_rt_avg_update(rq, delta_exec);
@@ -825,6 +870,9 @@ static void __enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head)
         if (group_rq && (rt_rq_throttled(group_rq) || !group_rq->rt_nr_running))
                 return;
 
+        if (!rt_rq->rt_nr_running)
+                list_add_leaf_rt_rq(rt_rq);
+
         if (head)
                 list_add(&rt_se->run_list, queue);
         else
@@ -844,6 +892,8 @@ static void __dequeue_rt_entity(struct sched_rt_entity *rt_se)
                 __clear_bit(rt_se_prio(rt_se), array->bitmap);
 
         dec_rt_tasks(rt_se, rt_rq);
+        if (!rt_rq->rt_nr_running)
+                list_del_leaf_rt_rq(rt_rq);
 }
 
 /*
@@ -949,40 +999,55 @@ static void yield_task_rt(struct rq *rq)
 static int find_lowest_rq(struct task_struct *task);
 
 static int
-select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags)
+select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 {
+        struct task_struct *curr;
+        struct rq *rq;
+        int cpu;
+
         if (sd_flag != SD_BALANCE_WAKE)
                 return smp_processor_id();
 
+        cpu = task_cpu(p);
+        rq = cpu_rq(cpu);
+
+        rcu_read_lock();
+        curr = ACCESS_ONCE(rq->curr); /* unlocked access */
+
         /*
-         * If the current task is an RT task, then
+         * If the current task on @p's runqueue is an RT task, then
          * try to see if we can wake this RT task up on another
          * runqueue. Otherwise simply start this RT task
          * on its current runqueue.
          *
-         * We want to avoid overloading runqueues. Even if
-         * the RT task is of higher priority than the current RT task.
-         * RT tasks behave differently than other tasks. If
-         * one gets preempted, we try to push it off to another queue.
-         * So trying to keep a preempting RT task on the same
-         * cache hot CPU will force the running RT task to
-         * a cold CPU. So we waste all the cache for the lower
-         * RT task in hopes of saving some of a RT task
-         * that is just being woken and probably will have
-         * cold cache anyway.
+         * We want to avoid overloading runqueues. If the woken
+         * task is a higher priority, then it will stay on this CPU
+         * and the lower prio task should be moved to another CPU.
+         * Even though this will probably make the lower prio task
+         * lose its cache, we do not want to bounce a higher task
+         * around just because it gave up its CPU, perhaps for a
+         * lock?
+         *
+         * For equal prio tasks, we just let the scheduler sort it out.
+         *
+         * Otherwise, just let it ride on the affined RQ and the
+         * post-schedule router will push the preempted task away
+         *
+         * This test is optimistic, if we get it wrong the load-balancer
+         * will have to sort it out.
          */
-        if (unlikely(rt_task(rq->curr)) &&
+        if (curr && unlikely(rt_task(curr)) &&
+            (curr->rt.nr_cpus_allowed < 2 ||
+             curr->prio < p->prio) &&
             (p->rt.nr_cpus_allowed > 1)) {
-                int cpu = find_lowest_rq(p);
+                int target = find_lowest_rq(p);
 
-                return (cpu == -1) ? task_cpu(p) : cpu;
+                if (target != -1)
+                        cpu = target;
         }
+        rcu_read_unlock();
 
-        /*
-         * Otherwise, just let it ride on the affined RQ and the
-         * post-schedule router will push the preempted task away
-         */
-        return task_cpu(p);
+        return cpu;
 }
 
 static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p)
@@ -1031,7 +1096,7 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
          * to move current somewhere else, making room for our non-migratable
          * task.
          */
-        if (p->prio == rq->curr->prio && !need_resched())
+        if (p->prio == rq->curr->prio && !test_tsk_need_resched(rq->curr))
                 check_preempt_equal_prio(rq, p);
 #endif
 }
@@ -1074,7 +1139,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
         } while (rt_rq);
 
         p = rt_task_of(rt_se);
-        p->se.exec_start = rq->clock;
+        p->se.exec_start = rq->clock_task;
 
         return p;
 }
@@ -1107,7 +1172,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
          * The previous task needs to be made eligible for pushing
          * if it is still active
          */
-        if (p->se.on_rq && p->rt.nr_cpus_allowed > 1)
+        if (on_rt_rq(&p->rt) && p->rt.nr_cpus_allowed > 1)
                 enqueue_pushable_task(rq, p);
 }
 
@@ -1139,7 +1204,7 @@ static struct task_struct *pick_next_highest_task_rt(struct rq *rq, int cpu)
         for_each_leaf_rt_rq(rt_rq, rq) {
                 array = &rt_rq->active;
                 idx = sched_find_first_bit(array->bitmap);
- next_idx:
+next_idx:
                 if (idx >= MAX_RT_PRIO)
                         continue;
                 if (next && next->prio < idx)
@@ -1174,6 +1239,10 @@ static int find_lowest_rq(struct task_struct *task)
         int this_cpu = smp_processor_id();
         int cpu      = task_cpu(task);
 
+        /* Make sure the mask is initialized first */
+        if (unlikely(!lowest_mask))
+                return -1;
+
         if (task->rt.nr_cpus_allowed == 1)
                 return -1; /* No other targets possible */
 
@@ -1198,6 +1267,7 @@ static int find_lowest_rq(struct task_struct *task)
         if (!cpumask_test_cpu(this_cpu, lowest_mask))
                 this_cpu = -1; /* Skip this_cpu opt if not among lowest */
 
+        rcu_read_lock();
         for_each_domain(cpu, sd) {
                 if (sd->flags & SD_WAKE_AFFINE) {
                         int best_cpu;
@@ -1207,15 +1277,20 @@ static int find_lowest_rq(struct task_struct *task)
                          * remote processor.
                          */
                         if (this_cpu != -1 &&
-                            cpumask_test_cpu(this_cpu, sched_domain_span(sd)))
+                            cpumask_test_cpu(this_cpu, sched_domain_span(sd))) {
+                                rcu_read_unlock();
                                 return this_cpu;
+                        }
 
                         best_cpu = cpumask_first_and(lowest_mask,
                                                      sched_domain_span(sd));
-                        if (best_cpu < nr_cpu_ids)
+                        if (best_cpu < nr_cpu_ids) {
+                                rcu_read_unlock();
                                 return best_cpu;
+                        }
                 }
         }
+        rcu_read_unlock();
 
         /*
          * And finally, if there were no matches within the domains
@@ -1258,7 +1333,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
                                      !cpumask_test_cpu(lowest_rq->cpu,
                                                        &task->cpus_allowed) ||
                                      task_running(rq, task) ||
-                                     !task->se.on_rq)) {
+                                     !task->on_rq)) {
 
                                 raw_spin_unlock(&lowest_rq->lock);
                                 lowest_rq = NULL;
@@ -1292,7 +1367,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq)
         BUG_ON(task_current(rq, p));
         BUG_ON(p->rt.nr_cpus_allowed <= 1);
 
-        BUG_ON(!p->se.on_rq);
+        BUG_ON(!p->on_rq);
         BUG_ON(!rt_task(p));
 
         return p;
@@ -1315,7 +1390,7 @@ static int push_rt_task(struct rq *rq)
         if (!next_task)
                 return 0;
 
- retry:
+retry:
         if (unlikely(next_task == rq->curr)) {
                 WARN_ON(1);
                 return 0;
@@ -1349,7 +1424,7 @@ static int push_rt_task(struct rq *rq)
                 task = pick_next_pushable_task(rq);
                 if (task_cpu(next_task) == rq->cpu && task == next_task) {
                         /*
-                         * If we get here, the task hasnt moved at all, but
+                         * If we get here, the task hasn't moved at all, but
                          * it has failed to push.  We will not try again,
                          * since the other cpus will pull from us when they
                          * are ready.
@@ -1438,7 +1513,7 @@ static int pull_rt_task(struct rq *this_rq)
                  */
                 if (p && (p->prio < this_rq->rt.highest_prio.curr)) {
                         WARN_ON(p == src_rq->curr);
-                        WARN_ON(!p->se.on_rq);
+                        WARN_ON(!p->on_rq);
 
                         /*
                          * There's a chance that p is higher in priority
@@ -1459,11 +1534,11 @@ static int pull_rt_task(struct rq *this_rq)
                         /*
                          * We continue with the search, just in
                          * case there's an even higher prio task
-                         * in another runqueue. (low likelyhood
+                         * in another runqueue. (low likelihood
                          * but possible)
                          */
                 }
- skip:
+skip:
                 double_unlock_balance(this_rq, src_rq);
         }
 
@@ -1491,7 +1566,10 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
         if (!task_running(rq, p) &&
             !test_tsk_need_resched(rq->curr) &&
             has_pushable_tasks(rq) &&
-            p->rt.nr_cpus_allowed > 1)
+            p->rt.nr_cpus_allowed > 1 &&
+            rt_task(rq->curr) &&
+            (rq->curr->rt.nr_cpus_allowed < 2 ||
+             rq->curr->prio < p->prio))
                 push_rt_tasks(rq);
 }
 
@@ -1506,7 +1584,7 @@ static void set_cpus_allowed_rt(struct task_struct *p,
          * Update the migration status of the RQ if we have an RT task
          * which is running AND changing its weight value.
          */
-        if (p->se.on_rq && (weight != p->rt.nr_cpus_allowed)) {
+        if (p->on_rq && (weight != p->rt.nr_cpus_allowed)) {
                 struct rq *rq = task_rq(p);
 
                 if (!task_current(rq, p)) {
@@ -1567,8 +1645,7 @@ static void rq_offline_rt(struct rq *rq)
  * When switch from the rt queue, we bring ourselves to a position
  * that we might want to pull RT tasks from other runqueues.
  */
-static void switched_from_rt(struct rq *rq, struct task_struct *p,
-                           int running)
+static void switched_from_rt(struct rq *rq, struct task_struct *p)
 {
         /*
          * If there are other RT tasks then we will reschedule
@@ -1577,7 +1654,7 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p,
          * we may need to handle the pulling of RT tasks
          * now.
          */
-        if (!rq->rt.rt_nr_running)
+        if (p->on_rq && !rq->rt.rt_nr_running)
                 pull_rt_task(rq);
 }
 
@@ -1596,8 +1673,7 @@ static inline void init_sched_rt_class(void)
  * with RT tasks. In this case we try to push them off to
  * other runqueues.
  */
-static void switched_to_rt(struct rq *rq, struct task_struct *p,
-                           int running)
+static void switched_to_rt(struct rq *rq, struct task_struct *p)
 {
         int check_resched = 1;
 
@@ -1608,7 +1684,7 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
          * If that current running task is also an RT task
          * then see if we can move to another run queue.
          */
-        if (!running) {
+        if (p->on_rq && rq->curr != p) {
 #ifdef CONFIG_SMP
                 if (rq->rt.overloaded && push_rt_task(rq) &&
                     /* Don't resched if we changed runqueues */
@@ -1624,10 +1700,13 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p,
  * Priority of the task has changed. This may cause
  * us to initiate a push or pull.
  */
-static void prio_changed_rt(struct rq *rq, struct task_struct *p,
-                            int oldprio, int running)
+static void
+prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio)
 {
-        if (running) {
+        if (!p->on_rq)
+                return;
+
+        if (rq->curr == p) {
 #ifdef CONFIG_SMP
                 /*
                  * If our priority decreases while running, we
@@ -1709,7 +1788,7 @@ static void set_curr_task_rt(struct rq *rq)
 {
         struct task_struct *p = rq->curr;
 
-        p->se.exec_start = rq->clock;
+        p->se.exec_start = rq->clock_task;
 
         /* The running task is never eligible for pushing */
         dequeue_pushable_task(rq, p);
@@ -1763,10 +1842,11 @@ extern void print_rt_rq(struct seq_file *m, int cpu, struct rt_rq *rt_rq);
 
 static void print_rt_stats(struct seq_file *m, int cpu)
 {
+        rt_rq_iter_t iter;
         struct rt_rq *rt_rq;
 
         rcu_read_lock();
-        for_each_leaf_rt_rq(rt_rq, cpu_rq(cpu))
+        for_each_rt_rq(rt_rq, iter, cpu_rq(cpu))
                 print_rt_rq(m, cpu, rt_rq);
         rcu_read_unlock();
 }