sched: Fix hotplug task migration

Dan Carpenter reported:

> kernel/sched/rt.c:1347 pick_next_task_rt() warn: variable dereferenced before check 'prev' (see line 1338)
> kernel/sched/deadline.c:1011 pick_next_task_dl() warn: variable dereferenced before check 'prev' (see line 1005)

Kirill also spotted that migrate_tasks() will have an instant NULL
deref because pick_next_task() will immediately deref prev.

Instead of fixing all the corner cases because migrate_tasks() can
pass in a NULL prev task in the unlikely case of hot-un-plug, provide
a fake task such that we can remove all the NULL checks from the far
more common paths.

A further problem; not previously spotted; is that because we pushed
pre_schedule() and idle_balance() into pick_next_task() we now need to
avoid those getting called and pulling more tasks on our dying CPU.

We avoid pull_{dl,rt}_task() by setting fake_task.prio to MAX_PRIO+1.
We also note that since we call pick_next_task() exactly the amount of
times we have runnable tasks present, we should never land in
idle_balance().

Fixes: 38033c37fa ("sched: Push down pre_schedule() and idle_balance()")
Cc: Juri Lelli <juri.lelli@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Reported-by: Kirill Tkhai <tkhai@yandex.ru>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20140212094930.GB3545@laptop.programming.kicks-ass.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This commit is contained in:
Peter Zijlstra 2014-02-12 10:49:30 +01:00 committed by Thomas Gleixner
parent 6e83125c6b
commit 3f1d2a3181
7 changed files with 28 additions and 12 deletions

View file

@ -4681,6 +4681,22 @@ static void calc_load_migrate(struct rq *rq)
atomic_long_add(delta, &calc_load_tasks);
}
static void put_prev_task_fake(struct rq *rq, struct task_struct *prev)
{
}
static const struct sched_class fake_sched_class = {
.put_prev_task = put_prev_task_fake,
};
static struct task_struct fake_task = {
/*
* Avoid pull_{rt,dl}_task()
*/
.prio = MAX_PRIO + 1,
.sched_class = &fake_sched_class,
};
/*
* Migrate all tasks from the rq, sleeping tasks will be migrated by
* try_to_wake_up()->select_task_rq().
@ -4721,7 +4737,7 @@ static void migrate_tasks(unsigned int dead_cpu)
if (rq->nr_running == 1)
break;
next = pick_next_task(rq, NULL);
next = pick_next_task(rq, &fake_task);
BUG_ON(!next);
next->sched_class->put_prev_task(rq, next);

View file

@ -1008,8 +1008,7 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev)
if (unlikely(!dl_rq->dl_nr_running))
return NULL;
if (prev)
prev->sched_class->put_prev_task(rq, prev);
put_prev_task(rq, prev);
dl_se = pick_next_dl_entity(rq, dl_rq);
BUG_ON(!dl_se);

View file

@ -4690,7 +4690,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev)
if (!cfs_rq->nr_running)
goto idle;
if (!prev || prev->sched_class != &fair_sched_class)
if (prev->sched_class != &fair_sched_class)
goto simple;
/*
@ -4766,8 +4766,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev)
if (!cfs_rq->nr_running)
goto idle;
if (prev)
prev->sched_class->put_prev_task(rq, prev);
put_prev_task(rq, prev);
do {
se = pick_next_entity(cfs_rq, NULL);

View file

@ -26,8 +26,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
static struct task_struct *
pick_next_task_idle(struct rq *rq, struct task_struct *prev)
{
if (prev)
prev->sched_class->put_prev_task(rq, prev);
put_prev_task(rq, prev);
schedstat_inc(rq, sched_goidle);
#ifdef CONFIG_SMP

View file

@ -1344,8 +1344,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
if (rt_rq_throttled(rt_rq))
return NULL;
if (prev)
prev->sched_class->put_prev_task(rq, prev);
put_prev_task(rq, prev);
p = _pick_next_task_rt(rq);

View file

@ -1147,6 +1147,11 @@ struct sched_class {
#endif
};
static inline void put_prev_task(struct rq *rq, struct task_struct *prev)
{
prev->sched_class->put_prev_task(rq, prev);
}
#define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
for (class = sched_class_highest; class; class = class->next)

View file

@ -31,8 +31,7 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev)
if (!stop || !stop->on_rq)
return NULL;
if (prev)
prev->sched_class->put_prev_task(rq, prev);
put_prev_task(rq, prev);
stop->se.exec_start = rq_clock_task(rq);