Re: [PATCH] sched/numa: fix unsafe get_task_struct() in task_numa_assign()

[Kirill Tkhai <tkhai@yandex.ru>]

18.10.2014, 12:15, "Kirill Tkhai" <tkhai@yandex.ru>:
> 18.10.2014, 01:40, "Oleg Nesterov" <oleg@redhat.com>:
>>  The lockless get_task_struct(tsk) is only safe if tsk == current
>>  and didn't pass exit_notify(), or if this tsk was found on a rcu
>>  protected list (say, for_each_process() or find_task_by_vpid()).
>>  IOW, it is only safe if release_task() was not called before we
>>  take rcu_read_lock(), in this case we can rely on the fact that
>>  delayed_put_pid() can not drop the (potentially) last reference
>>  until rcu_read_unlock().
>>
>>  And as Kirill pointed out task_numa_compare()->task_numa_assign()
>>  path does get_task_struct(dst_rq->curr) and this is not safe. The
>>  task_struct itself can't go away, but rcu_read_lock() can't save
>>  us from the final put_task_struct() in finish_task_switch(); this
>>  reference goes away without rcu gp.
>>
>>  Reported-by: Kirill Tkhai <ktkhai@parallels.com>
>>  Signed-off-by: Oleg Nesterov <oleg@redhat.com>
>>  ---
>>   kernel/sched/fair.c |    8 +++++++-
>>   1 files changed, 7 insertions(+), 1 deletions(-)
>>
>>  diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>>  index 0090e8c..52049b9 100644
>>  --- a/kernel/sched/fair.c
>>  +++ b/kernel/sched/fair.c
>>  @@ -1158,7 +1158,13 @@ static void task_numa_compare(struct task_numa_env *env,
>>
>>           rcu_read_lock();
>>           cur = ACCESS_ONCE(dst_rq->curr);
>>  - if (cur->pid == 0) /* idle */
>>  + /*
>>  + * No need to move the exiting task, and this ensures that ->curr
>>  + * wasn't reaped and thus get_task_struct() in task_numa_assign()
>>  + * is safe; note that rcu_read_lock() can't protect from the final
>>  + * put_task_struct() after the last schedule().
>>  + */
>>  + if (is_idle_task(cur) || (cur->flags & PF_EXITING))
>>                   cur = NULL;
>>
>>           /*
>
> Oleg, I've looked once again, and now it's not good for me.
> Where is the guarantee this memory hasn't been allocated again?
> If so, PF_EXITING is not of the task we are interesting, but it's
> not a task's even.
>
> rcu_read_lock()                   ...                           ...
> cur = ACCESS_ONCE(dst_rq->curr);  ...                           ...
> <interrupt>                       rq->curr = next;              ...
> <interrupt>                           put_prev_task()           ...
> <interrupt>                               __put_prev_task       ...
> <interrupt>                                  kmem_cache_free()  ...
> <interrupt>                                  ...                <alocated again>
> <interrupt>                                  ...                memset(, 0, )
> <interrupt>                                  ...                ...
> if (cur->flags & PF_EXITING)                 ...                ...
>     <no>                                     ...                ...
> get_task_struct()                            ...                ...

How about this?

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b78280c..d46427e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1165,7 +1165,21 @@ static void task_numa_compare(struct task_numa_env *env,
 
 	rcu_read_lock();
 	cur = ACCESS_ONCE(dst_rq->curr);
-	if (cur->pid == 0) /* idle */
+	/*
+	 * No need to move the exiting task, and this ensures that ->curr
+	 * wasn't reaped and thus get_task_struct() in task_numa_assign()
+	 * is safe; note that rcu_read_lock() can't protect from the final
+	 * put_task_struct() after the last schedule().
+	 */
+	if (is_idle_task(cur) || (cur->flags & PF_EXITING))
+		cur = NULL;
+	/*
+	 * Check once again to be sure curr is still on dst_rq. Even if
+	 * it points on a new task, which is using the memory of freed
+	 * cur, it's OK, because we've locked RCU before
+	 * delayed_put_task_struct() callback is called to put its struct.
+	 */
+	if (cur != ACCESS_ONCE(dst_rq->curr))
 		cur = NULL;
 
 	/*