sched_ext: TASK_DEAD tasks must be switched out of SCX on ops_disable
scx_ops_disable_workfn() only switches !TASK_DEAD tasks out of SCX while calling scx_ops_exit_task() on all tasks including dead ones. This can leave a dead task on SCX but with SCX_TASK_NONE state, which is inconsistent. If another task was in the process of changing the TASK_DEAD task's scheduling class and grabs the rq lock after scx_ops_disable_workfn() is done with the task, the task ends up calling scx_ops_disable_task() on the dead task which is in an inconsistent state triggering a warning: WARNING: CPU: 6 PID: 3316 at kernel/sched/ext.c:3411 scx_ops_disable_task+0x12c/0x160 ... RIP: 0010:scx_ops_disable_task+0x12c/0x160 ... Call Trace: <TASK> check_class_changed+0x2c/0x70 __sched_setscheduler+0x8a0/0xa50 do_sched_setscheduler+0x104/0x1c0 __x64_sys_sched_setscheduler+0x18/0x30 do_syscall_64+0x7b/0x140 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x7f140d70ea5b There is no reason to leave dead tasks on SCX when unloading the BPF scheduler. Fix by making scx_ops_disable_workfn() eject all tasks including the dead ones from SCX. Signed-off-by: Tejun Heo <tj@kernel.org>
This commit is contained in:
parent
37cb049ef8
commit
61eeb9a905
@ -3998,21 +3998,14 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
|
||||
spin_lock_irq(&scx_tasks_lock);
|
||||
scx_task_iter_init(&sti);
|
||||
/*
|
||||
* Invoke scx_ops_exit_task() on all non-idle tasks, including
|
||||
* TASK_DEAD tasks. Because dead tasks may have a nonzero refcount,
|
||||
* we may not have invoked sched_ext_free() on them by the time a
|
||||
* scheduler is disabled. We must therefore exit the task here, or we'd
|
||||
* fail to invoke ops.exit_task(), as the scheduler will have been
|
||||
* unloaded by the time the task is subsequently exited on the
|
||||
* sched_ext_free() path.
|
||||
* The BPF scheduler is going away. All tasks including %TASK_DEAD ones
|
||||
* must be switched out and exited synchronously.
|
||||
*/
|
||||
while ((p = scx_task_iter_next_locked(&sti, true))) {
|
||||
const struct sched_class *old_class = p->sched_class;
|
||||
struct sched_enq_and_set_ctx ctx;
|
||||
|
||||
if (READ_ONCE(p->__state) != TASK_DEAD) {
|
||||
sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE,
|
||||
&ctx);
|
||||
sched_deq_and_put_task(p, DEQUEUE_SAVE | DEQUEUE_MOVE, &ctx);
|
||||
|
||||
p->scx.slice = min_t(u64, p->scx.slice, SCX_SLICE_DFL);
|
||||
__setscheduler_prio(p, p->prio);
|
||||
@ -4021,7 +4014,6 @@ static void scx_ops_disable_workfn(struct kthread_work *work)
|
||||
sched_enq_and_set_task(&ctx);
|
||||
|
||||
check_class_changed(task_rq(p), p, old_class, p->prio);
|
||||
}
|
||||
scx_ops_exit_task(p);
|
||||
}
|
||||
scx_task_iter_exit(&sti);
|
||||
|
Loading…
Reference in New Issue
Block a user