1 files changed, 34 insertions, 45 deletions

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e5db8c6feebd..a027799ae130 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -350,6 +350,11 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se,
                 dl_se->deadline = rq_clock(rq) + pi_se->dl_deadline;
                 dl_se->runtime = pi_se->dl_runtime;
         }
+
+        if (dl_se->dl_yielded)
+                dl_se->dl_yielded = 0;
+        if (dl_se->dl_throttled)
+                dl_se->dl_throttled = 0;
 }
 
 /*
@@ -536,23 +541,19 @@ again:
 
         sched_clock_tick();
         update_rq_clock(rq);
-        dl_se->dl_throttled = 0;
-        dl_se->dl_yielded = 0;
-        if (task_on_rq_queued(p)) {
-                enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
-                if (dl_task(rq->curr))
-                        check_preempt_curr_dl(rq, p, 0);
-                else
-                        resched_curr(rq);
+        enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
+        if (dl_task(rq->curr))
+                check_preempt_curr_dl(rq, p, 0);
+        else
+                resched_curr(rq);
 #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);
+        /*
+         * 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);
 
@@ -570,24 +571,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
 static
 int dl_runtime_exceeded(struct rq *rq, struct sched_dl_entity *dl_se)
 {
-        int dmiss = dl_time_before(dl_se->deadline, rq_clock(rq));
-        int rorun = dl_se->runtime <= 0;
-
-        if (!rorun && !dmiss)
-                return 0;
-
-        /*
-         * If we are beyond our current deadline and we are still
-         * executing, then we have already used some of the runtime of
-         * the next instance. Thus, if we do not account that, we are
-         * stealing bandwidth from the system at each deadline miss!
-         */
-        if (dmiss) {
-                dl_se->runtime = rorun ? dl_se->runtime : 0;
-                dl_se->runtime -= rq_clock(rq) - dl_se->deadline;
-        }
-
-        return 1;
+        return (dl_se->runtime <= 0);
 }
 
 extern bool sched_rt_bandwidth_account(struct rt_rq *rt_rq);
@@ -630,10 +614,9 @@ static void update_curr_dl(struct rq *rq)
 
         dl_se->runtime -= dl_se->dl_yielded ? 0 : delta_exec;
         if (dl_runtime_exceeded(rq, dl_se)) {
+                dl_se->dl_throttled = 1;
                 __dequeue_task_dl(rq, curr, 0);
-                if (likely(start_dl_timer(dl_se, curr->dl.dl_boosted)))
-                        dl_se->dl_throttled = 1;
-                else
+                if (unlikely(!start_dl_timer(dl_se, curr->dl.dl_boosted)))
                         enqueue_task_dl(rq, curr, ENQUEUE_REPLENISH);
 
                 if (!is_leftmost(curr, &rq->dl))
@@ -826,10 +809,10 @@ enqueue_dl_entity(struct sched_dl_entity *dl_se,
          * parameters of the task might need updating. Otherwise,
          * we want a replenishment of its runtime.
          */
-        if (!dl_se->dl_new && flags & ENQUEUE_REPLENISH)
-                replenish_dl_entity(dl_se, pi_se);
-        else
+        if (dl_se->dl_new || flags & ENQUEUE_WAKEUP)
                 update_dl_entity(dl_se, pi_se);
+        else if (flags & ENQUEUE_REPLENISH)
+                replenish_dl_entity(dl_se, pi_se);
 
         __enqueue_dl_entity(dl_se);
 }
@@ -870,7 +853,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
          * its rq, the bandwidth timer callback (which clearly has not
          * run yet) will take care of this.
          */
-        if (p->dl.dl_throttled)
+        if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH))
                 return;
 
         enqueue_dl_entity(&p->dl, pi_se, flags);
@@ -1090,7 +1073,13 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 {
         update_curr_dl(rq);
 
-        if (hrtick_enabled(rq) && queued && p->dl.runtime > 0)
+        /*
+         * Even when we have runtime, update_curr_dl() might have resulted in us
+         * not being the leftmost task anymore. In that case NEED_RESCHED will
+         * be set and schedule() will start a new hrtick for the next task.
+         */
+        if (hrtick_enabled(rq) && queued && p->dl.runtime > 0 &&
+            is_leftmost(p, &rq->dl))
                 start_hrtick_dl(rq, p);
 }
 
@@ -1111,6 +1100,7 @@ static void task_dead_dl(struct task_struct *p)
          * Since we are TASK_DEAD we won't slip out of the domain!
          */
         raw_spin_lock_irq(&dl_b->lock);
+        /* XXX we should retain the bw until 0-lag */
         dl_b->total_bw -= p->dl.dl_bw;
         raw_spin_unlock_irq(&dl_b->lock);
 
@@ -1182,9 +1172,6 @@ static int find_later_rq(struct task_struct *task)
          * We have to consider system topology and task affinity
          * first, then we can look for a suitable cpu.
          */
-        cpumask_copy(later_mask, task_rq(task)->rd->span);
-        cpumask_and(later_mask, later_mask, cpu_active_mask);
-        cpumask_and(later_mask, later_mask, &task->cpus_allowed);
         best_cpu = cpudl_find(&task_rq(task)->rd->cpudl,
                         task, later_mask);
         if (best_cpu == -1)
@@ -1579,6 +1566,7 @@ static void rq_online_dl(struct rq *rq)
         if (rq->dl.overloaded)
                 dl_set_overload(rq);
 
+        cpudl_set_freecpu(&rq->rd->cpudl, rq->cpu);
         if (rq->dl.dl_nr_running > 0)
                 cpudl_set(&rq->rd->cpudl, rq->cpu, rq->dl.earliest_dl.curr, 1);
 }
@@ -1590,6 +1578,7 @@ static void rq_offline_dl(struct rq *rq)
                 dl_clear_overload(rq);
 
         cpudl_set(&rq->rd->cpudl, rq->cpu, 0, 0);
+        cpudl_clear_freecpu(&rq->rd->cpudl, rq->cpu);
 }
 
 void init_sched_dl_class(void)
@@ -1631,8 +1620,8 @@ static void cancel_dl_timer(struct rq *rq, struct task_struct *p)
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
+        /* XXX we should retain the bw until 0-lag */
         cancel_dl_timer(rq, p);
-
         __dl_clear_params(p);
 
         /*