sched: fix race in schedule()
Fix a hard to trigger crash seen in the -rt kernel that also affects
the vanilla scheduler.
There is a race condition between schedule() and some dequeue/enqueue
functions; rt_mutex_setprio(), __setscheduler() and sched_move_task().
When scheduling to idle, idle_balance() is called to pull tasks from
other busy processor. It might drop the rq lock. It means that those 3
functions encounter on_rq=0 and running=1. The current task should be
put when running.
Here is a possible scenario:
CPU0 CPU1
| schedule()
| ->deactivate_task()
| ->idle_balance()
| -->load_balance_newidle()
rt_mutex_setprio() |
| --->double_lock_balance()
*get lock *rel lock
* on_rq=0, ruuning=1 |
* sched_class is changed |
*rel lock *get lock
: |
:
->put_prev_task_rt()
->pick_next_task_fair()
=> panic
The current process of CPU1(P1) is scheduling. Deactivated P1, and the
scheduler looks for another process on other CPU's runqueue because CPU1
will be idle. idle_balance(), load_balance_newidle() and
double_lock_balance() are called and double_lock_balance() could drop
the rq lock. On the other hand, CPU0 is trying to boost the priority of
P1. The result of boosting only P1's prio and sched_class are changed to
RT. The sched entities of P1 and P1's group are never put. It makes
cfs_rq invalid, because the cfs_rq has curr and no leaf, but
pick_next_task_fair() is called, then the kernel panics.
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
committed by
Ingo Molnar
parent
4faa849665
commit
0e1f34833b
@@ -4268,11 +4268,10 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
|
||||
oldprio = p->prio;
|
||||
on_rq = p->se.on_rq;
|
||||
running = task_current(rq, p);
|
||||
if (on_rq) {
|
||||
if (on_rq)
|
||||
dequeue_task(rq, p, 0);
|
||||
if (running)
|
||||
p->sched_class->put_prev_task(rq, p);
|
||||
}
|
||||
if (running)
|
||||
p->sched_class->put_prev_task(rq, p);
|
||||
|
||||
if (rt_prio(prio))
|
||||
p->sched_class = &rt_sched_class;
|
||||
@@ -4281,10 +4280,9 @@ void rt_mutex_setprio(struct task_struct *p, int prio)
|
||||
|
||||
p->prio = prio;
|
||||
|
||||
if (running)
|
||||
p->sched_class->set_curr_task(rq);
|
||||
if (on_rq) {
|
||||
if (running)
|
||||
p->sched_class->set_curr_task(rq);
|
||||
|
||||
enqueue_task(rq, p, 0);
|
||||
|
||||
check_class_changed(rq, p, prev_class, oldprio, running);
|
||||
@@ -4581,19 +4579,17 @@ recheck:
|
||||
update_rq_clock(rq);
|
||||
on_rq = p->se.on_rq;
|
||||
running = task_current(rq, p);
|
||||
if (on_rq) {
|
||||
if (on_rq)
|
||||
deactivate_task(rq, p, 0);
|
||||
if (running)
|
||||
p->sched_class->put_prev_task(rq, p);
|
||||
}
|
||||
if (running)
|
||||
p->sched_class->put_prev_task(rq, p);
|
||||
|
||||
oldprio = p->prio;
|
||||
__setscheduler(rq, p, policy, param->sched_priority);
|
||||
|
||||
if (running)
|
||||
p->sched_class->set_curr_task(rq);
|
||||
if (on_rq) {
|
||||
if (running)
|
||||
p->sched_class->set_curr_task(rq);
|
||||
|
||||
activate_task(rq, p, 0);
|
||||
|
||||
check_class_changed(rq, p, prev_class, oldprio, running);
|
||||
@@ -7618,11 +7614,10 @@ void sched_move_task(struct task_struct *tsk)
|
||||
running = task_current(rq, tsk);
|
||||
on_rq = tsk->se.on_rq;
|
||||
|
||||
if (on_rq) {
|
||||
if (on_rq)
|
||||
dequeue_task(rq, tsk, 0);
|
||||
if (unlikely(running))
|
||||
tsk->sched_class->put_prev_task(rq, tsk);
|
||||
}
|
||||
if (unlikely(running))
|
||||
tsk->sched_class->put_prev_task(rq, tsk);
|
||||
|
||||
set_task_rq(tsk, task_cpu(tsk));
|
||||
|
||||
@@ -7631,11 +7626,10 @@ void sched_move_task(struct task_struct *tsk)
|
||||
tsk->sched_class->moved_group(tsk);
|
||||
#endif
|
||||
|
||||
if (on_rq) {
|
||||
if (unlikely(running))
|
||||
tsk->sched_class->set_curr_task(rq);
|
||||
if (unlikely(running))
|
||||
tsk->sched_class->set_curr_task(rq);
|
||||
if (on_rq)
|
||||
enqueue_task(rq, tsk, 0);
|
||||
}
|
||||
|
||||
task_rq_unlock(rq, &flags);
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user