Commit-ID: 477af336ba06ef4c32e97892bb0d2027ce30f466
Gitweb: http://git.kernel.org/tip/477af336ba06ef4c32e97892bb0d2027ce30f466
Author: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate: Fri, 14 Feb 2014 12:25:08 +0100
Committer: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
CommitDate: Fri, 21 Feb 2014 21:43:18 +0100
sched: Guarantee task priority in pick_next_task()
Michael spotted that the idle_balance() push down created a task
priority problem.
Previously, when we called idle_balance() before pick_next_task() it
wasn't a problem when -- because of the rq->lock droppage -- an rt/dl
task slipped in.
Similarly for pre_schedule(), rt pre-schedule could have a dl task
slip in.
But by pulling it into the pick_next_task() loop, we'll not try a
higher task priority again.
Cure this by creating a re-start condition in pick_next_task(); and
triggering this from pick_next_task_{rt,fair}().
Fixes: 38033c37faab ("sched: Push down pre_schedule() and idle_balance()")
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Reported-by: Michael Wang <wangyun@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/n/tip-uuwge7mqn3jk72v4jdkwbixd@xxxxxxxxxxxxxx
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
kernel/sched/core.c | 16 ++++++++++++----
kernel/sched/fair.c | 16 +++++++++++++++-
kernel/sched/rt.c | 10 +++++++++-
3 files changed, 36 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 49db434..4c8aaf0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2574,24 +2574,32 @@ static inline void schedule_debug(struct task_struct *prev)
static inline struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev)
{
- const struct sched_class *class;
+ const struct sched_class *class = &fair_sched_class;
struct task_struct *p;
/*
* Optimization: we know that if all tasks are in
* the fair class we can call that function directly:
*/
- if (likely(prev->sched_class == &fair_sched_class &&
+ if (likely(prev->sched_class == class &&
rq->nr_running == rq->cfs.h_nr_running)) {
p = fair_sched_class.pick_next_task(rq, prev);
- if (likely(p))
+ if (likely(p && p->sched_class == class))
return p;
}
+again:
for_each_class(class) {
p = class->pick_next_task(rq, prev);
- if (p)
+ if (p) {
+ /*
+ * See pick_next_task_{fair,rt}(); they return rq->idle
+ * in case they want to re-start the task selection.
+ */
+ if (unlikely(p->sched_class != class))
+ goto again;
return p;
+ }
}
BUG(); /* the idle class will always have a runnable task */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e884e45..fb6f220 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4684,6 +4684,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev)
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
struct task_struct *p;
+ int new_tasks;
again:
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -4782,7 +4783,20 @@ simple:
return p;
idle:
- if (idle_balance(rq)) /* drops rq->lock */
+ /*
+ * Because idle_balance() releases (and re-acquires) rq->lock, it is
+ * possible for any higher priority task to appear. In that case we
+ * must re-start the pick_next_entity() loop.
+ */
+ new_tasks = idle_balance(rq);
+
+ /*
+ * See pick_next_task(); we return rq->idle to restart task selection.
+ */
+ if (rq->nr_running != rq->cfs.h_nr_running)
+ return rq->idle;
+
+ if (new_tasks)
goto again;
return NULL;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 3e488ca..b22a090 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1360,8 +1360,16 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
struct task_struct *p;
struct rt_rq *rt_rq = &rq->rt;
- if (need_pull_rt_task(rq, prev))
+ if (need_pull_rt_task(rq, prev)) {
pull_rt_task(rq);
+ /*
+ * pull_rt_task() can drop (and re-acquire) rq->lock; this
+ * means a dl task can slip in, in which case we need to
+ * re-start task selection.
+ */
+ if (unlikely(rq->dl.dl_nr_running))
+ return rq->idle;
+ }
if (!rt_rq->rt_nr_running)
return NULL;
--
To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
|