![Peter Zijlstra](/assets/img/avatar_default.png)
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>
132 lines
2.8 KiB
C
132 lines
2.8 KiB
C
#include "sched.h"
|
|
|
|
/*
|
|
* stop-task scheduling class.
|
|
*
|
|
* The stop task is the highest priority task in the system, it preempts
|
|
* everything and will be preempted by nothing.
|
|
*
|
|
* See kernel/stop_machine.c
|
|
*/
|
|
|
|
#ifdef CONFIG_SMP
|
|
static int
|
|
select_task_rq_stop(struct task_struct *p, int cpu, int sd_flag, int flags)
|
|
{
|
|
return task_cpu(p); /* stop tasks as never migrate */
|
|
}
|
|
#endif /* CONFIG_SMP */
|
|
|
|
static void
|
|
check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
/* we're never preempted */
|
|
}
|
|
|
|
static struct task_struct *
|
|
pick_next_task_stop(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
struct task_struct *stop = rq->stop;
|
|
|
|
if (!stop || !stop->on_rq)
|
|
return NULL;
|
|
|
|
put_prev_task(rq, prev);
|
|
|
|
stop->se.exec_start = rq_clock_task(rq);
|
|
|
|
return stop;
|
|
}
|
|
|
|
static void
|
|
enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
inc_nr_running(rq);
|
|
}
|
|
|
|
static void
|
|
dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
dec_nr_running(rq);
|
|
}
|
|
|
|
static void yield_task_stop(struct rq *rq)
|
|
{
|
|
BUG(); /* the stop task should never yield, its pointless. */
|
|
}
|
|
|
|
static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)
|
|
{
|
|
struct task_struct *curr = rq->curr;
|
|
u64 delta_exec;
|
|
|
|
delta_exec = rq_clock_task(rq) - curr->se.exec_start;
|
|
if (unlikely((s64)delta_exec < 0))
|
|
delta_exec = 0;
|
|
|
|
schedstat_set(curr->se.statistics.exec_max,
|
|
max(curr->se.statistics.exec_max, delta_exec));
|
|
|
|
curr->se.sum_exec_runtime += delta_exec;
|
|
account_group_exec_runtime(curr, delta_exec);
|
|
|
|
curr->se.exec_start = rq_clock_task(rq);
|
|
cpuacct_charge(curr, delta_exec);
|
|
}
|
|
|
|
static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
|
|
{
|
|
}
|
|
|
|
static void set_curr_task_stop(struct rq *rq)
|
|
{
|
|
struct task_struct *stop = rq->stop;
|
|
|
|
stop->se.exec_start = rq_clock_task(rq);
|
|
}
|
|
|
|
static void switched_to_stop(struct rq *rq, struct task_struct *p)
|
|
{
|
|
BUG(); /* its impossible to change to this class */
|
|
}
|
|
|
|
static void
|
|
prio_changed_stop(struct rq *rq, struct task_struct *p, int oldprio)
|
|
{
|
|
BUG(); /* how!?, what priority? */
|
|
}
|
|
|
|
static unsigned int
|
|
get_rr_interval_stop(struct rq *rq, struct task_struct *task)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Simple, special scheduling class for the per-CPU stop tasks:
|
|
*/
|
|
const struct sched_class stop_sched_class = {
|
|
.next = &dl_sched_class,
|
|
|
|
.enqueue_task = enqueue_task_stop,
|
|
.dequeue_task = dequeue_task_stop,
|
|
.yield_task = yield_task_stop,
|
|
|
|
.check_preempt_curr = check_preempt_curr_stop,
|
|
|
|
.pick_next_task = pick_next_task_stop,
|
|
.put_prev_task = put_prev_task_stop,
|
|
|
|
#ifdef CONFIG_SMP
|
|
.select_task_rq = select_task_rq_stop,
|
|
#endif
|
|
|
|
.set_curr_task = set_curr_task_stop,
|
|
.task_tick = task_tick_stop,
|
|
|
|
.get_rr_interval = get_rr_interval_stop,
|
|
|
|
.prio_changed = prio_changed_stop,
|
|
.switched_to = switched_to_stop,
|
|
};
|