sched/deadline: fix try to pull pinned dl tasks in pull algorithm

pull_dl_task can drop (and re-acquire) rq->lock, this means a stop task can slip in, in which case we need to reschedule. This patch add the reschedule when the scenario occurs.

Signed-off-by Wanpeng Li <[email protected]>

---
 kernel/sched/deadline.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

kernel/sched/deadline.c +0 -0

index e49b1e6..7d4c4fc 100644
@@ -1750,7 +1750,13 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
 	if (!task_on_rq_queued(p) || rq->dl.dl_nr_running)
 		return;

Quoted 17 lines · Wanpeng Li

pull_dl_task can drop (and re-acquire) rq->lock, this means a stop task can slip in, in which case we need to reschedule. This patch add the reschedule when the scenario occurs.

Signed-off-by Wanpeng Li <[email protected]>

---
  kernel/sched/deadline.c | 16 +++++++++++++++-
  1 file changed, 15 insertions(+), 1 deletion(-)

kernel/sched/deadline.c +0 -0

index e49b1e6..7d4c4fc 100644
@@ -1750,7 +1750,13 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
  	if (!task_on_rq_queued(p) || rq->dl.dl_nr_running)
  		return;
 

kernel/sched/deadline.c static void switched_from_dl(struct rq *rq, struct task_struct *p) · line 1760

Quoted 9 lines

kernel/sched/deadline.c +7 -1

-	if (pull_dl_task(rq))
+	/*
+	 * pull_dl_task() can drop (and re-acquire) rq->lock; this
+	 * means a stop task can slip in, in which case we need to
+	 * reschedule.
+	 */
+	if (pull_dl_task(rq) ||
+		(rq->stop && task_on_rq_queued(rq->stop)))
  		resched_curr(rq);

But, the waking of the stop task will already have done the preemption check and won (obviously). So the wakeup should already have done the resched_curr().

So why?

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

pull_rt_task() can drop (and re-acquire) rq->lock, this means a dl or stop task can slip in, in which case need to reschedule. This patch add the reschedule when the scenario occurs.

Signed-off-by Wanpeng Li <[email protected]>

---
 kernel/sched/rt.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

kernel/sched/rt.c +0 -1

index 560d2fa..8c948bf 100644
@@ -2136,7 +2136,14 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
 	if (!task_on_rq_queued(p) || rq->rt.rt_nr_running)
 		return;
 
-	if (pull_rt_task(rq))

Quoted 17 lines · Wanpeng Li

pull_rt_task() can drop (and re-acquire) rq->lock, this means a dl or stop task can slip in, in which case need to reschedule. This patch add the reschedule when the scenario occurs.

Signed-off-by Wanpeng Li <[email protected]>

---
  kernel/sched/rt.c | 19 ++++++++++++++++++-
  1 file changed, 18 insertions(+), 1 deletion(-)

kernel/sched/rt.c +0 -0

index 560d2fa..8c948bf 100644
@@ -2136,7 +2136,14 @@ static void switched_from_rt(struct rq *rq, struct task_struct *p)
  	if (!task_on_rq_queued(p) || rq->rt.rt_nr_running)
  		return;
 

kernel/sched/rt.c static void switched_from_rt(struct rq *rq, struct task_struct *p) · line 2148

Quoted 11 lines

kernel/sched/rt.c +8 -1

-	if (pull_rt_task(rq))
+	/*
+	 * pull_rt_task() can drop (and re-acquire) rq->lock; this
+	 * means a dl or stop task can slip in, in which case we need
+	 * to reschedule.
+	 */
+	if (pull_rt_task(rq) ||
+		(unlikely((rq->stop && task_on_rq_queued(rq->stop)) ||
+			rq->dl.dl_nr_running)))
  		resched_curr(rq);
  }

Same as before; why is the normal wakeup preemption check not working?

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Function pick_next_earliest_dl_task is used to pick earliest and pushable dl task from overloaded cpus in pull algorithm, however, it traverses runqueue rbtree instead of pushable task rbtree which is also ordered by tasks' deadlines. This will result in getting no candidates from overloaded cpus if all the dl tasks on the overloaded cpus are pinned. This patch fix it by traversing pushable task rbtree which is also ordered by tasks' deadlines.

Signed-off-by Wanpeng Li <[email protected]>

---
kernel/sched/deadline.c | 29 ++++++++++++++++++++++++++++-

1 file changed, 28 insertions(+), 1 deletion(-)

kernel/sched/deadline.c +28 -1

index 890ce95..f09f3ad 100644
@@ -1230,6 +1230,33 @@ next_node:
 	return NULL;
 }
 
+/*
+ * Return the earliest pushable rq's task, which is suitable to be executed
+ * on the cpu, NULL otherwse
+ */
+static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq,
+									int cpu)
+{
+	struct rb_node *next_node = rq->dl.pushable_dl_tasks_leftmost;
+	struct task_struct *p = NULL;
+
+	if (!has_pushable_dl_tasks(rq))
+		return NULL;
+
+next_node:
+	if (next_node) {
+		p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+
+		if (pick_dl_task(rq, p, cpu))
+			return p;
+
+		next_node = rb_next(next_node);
+		goto next_node;
+	}
+
+	return NULL;
+}
+
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 
 static int find_later_rq(struct task_struct *task)

@@ -1514,7 +1541,7 @@ static int pull_dl_task(struct rq *this_rq)
 		if (src_rq->dl.dl_nr_running <= 1)
 			goto skip;
 
-		p = pick_next_earliest_dl_task(src_rq, this_cpu);
+		p = pick_earliest_pushable_dl_task(src_rq, this_cpu);
 
 		/*
 		 * We found a task to be pulled if:

Signature · 1 line

1.9.1

Ping Peterz for this patchset, :)

Quoted 62 lines · Wanpeng Li

Function pick_next_earliest_dl_task is used to pick earliest and pushable dl task from overloaded cpus in pull algorithm, however, it traverses runqueue rbtree instead of pushable task rbtree which is also ordered by tasks' deadlines. This will result in getting no candidates from overloaded cpus if all the dl tasks on the overloaded cpus are pinned. This patch fix it by traversing pushable task rbtree which is also ordered by tasks' deadlines.

Signed-off-by Wanpeng Li <[email protected]>

---
kernel/sched/deadline.c | 29 ++++++++++++++++++++++++++++-

1 file changed, 28 insertions(+), 1 deletion(-)

kernel/sched/deadline.c +28 -1

index 890ce95..f09f3ad 100644
@@ -1230,6 +1230,33 @@ next_node:
 	return NULL;
 }
 
+/*
+ * Return the earliest pushable rq's task, which is suitable to be executed
+ * on the cpu, NULL otherwse
+ */
+static struct task_struct *pick_earliest_pushable_dl_task(struct rq *rq,
+									int cpu)
+{
+	struct rb_node *next_node = rq->dl.pushable_dl_tasks_leftmost;
+	struct task_struct *p = NULL;
+
+	if (!has_pushable_dl_tasks(rq))
+		return NULL;
+
+next_node:
+	if (next_node) {
+		p = rb_entry(next_node, struct task_struct, pushable_dl_tasks);
+
+		if (pick_dl_task(rq, p, cpu))
+			return p;
+
+		next_node = rb_next(next_node);
+		goto next_node;
+	}
+
+	return NULL;
+}
+
 static DEFINE_PER_CPU(cpumask_var_t, local_cpu_mask_dl);
 
 static int find_later_rq(struct task_struct *task)

@@ -1514,7 +1541,7 @@ static int pull_dl_task(struct rq *this_rq)
 		if (src_rq->dl.dl_nr_running <= 1)
 			goto skip;
 
-		p = pick_next_earliest_dl_task(src_rq, this_cpu);
+		p = pick_earliest_pushable_dl_task(src_rq, this_cpu);
 
 		/*
 		 * We found a task to be pulled if:

Signature · 1 line

1.9.1