Re: [PATCH 3/3] introduce task_rcu_dereference()

From: Oleg Nesterov
Date: Wed May 18 2016 - 15:57:41 EST


On 05/18, Peter Zijlstra wrote:
>
> OK, something like so then?

Yes thanks!

Just one note,

> +struct task_struct *task_rcu_dereference(struct task_struct **ptask)
> +{
> + struct sighand_struct *sighand;
> + struct task_struct *task;
> +
> + /*
> + * We need to verify that release_task() was not called and thus
> + * delayed_put_task_struct() can't run and drop the last reference
> + * before rcu_read_unlock(). We check task->sighand != NULL,
> + * but we can read the already freed and reused memory.
> + */
> +retry:
> + task = rcu_dereference(*ptask);
> + if (!task)
> + return NULL;
> +
> + probe_kernel_address(&task->sighand, sighand);

OK. Then I'll re-send the patch which adds the probe_slab_address() helper
on top of this change. We do not want __probe_kernel_read() if
if CONFIG_DEBUG_PAGEALLOC=n.

> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1374,30 +1374,15 @@ static void task_numa_compare(struct task_numa_env *env,
> int dist = env->dist;
> bool assigned = false;
>
> - rcu_read_lock();
> -
> - raw_spin_lock_irq(&dst_rq->lock);
> - cur = dst_rq->curr;
> - /*
> - * No need to move the exiting task or idle task.
> - */
> - if ((cur->flags & PF_EXITING) || is_idle_task(cur))
> - cur = NULL;
> - else {
> - /*
> - * The task_struct must be protected here to protect the
> - * p->numa_faults access in the task_weight since the
> - * numa_faults could already be freed in the following path:
> - * finish_task_switch()
> - * --> put_task_struct()
> - * --> __put_task_struct()
> - * --> task_numa_free()
> - */
> - get_task_struct(cur);
> + cur = try_get_task_struct(&dst_rq->curr);

Do we really want try_get_task_struct() here? How about the change below?

To me it would be more clean to do get_task_struct() in task_numa_assign(),
it clearly pairs with put_task_struct(best_task) and task_numa_compare()
looks a bit simpler this way, no need to put_task_struct() if we nullify
cur.

What do you think? In any case I think the change in sched/fair.c should
probably come as a separate patch, but this is up to you.

Oleg.

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 40748dc..8e7083e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1254,6 +1254,8 @@ static void task_numa_assign(struct task_numa_env *env,
{
if (env->best_task)
put_task_struct(env->best_task);
+ if (p)
+ get_task_struct(p);

env->best_task = p;
env->best_imp = imp;
@@ -1321,31 +1323,11 @@ static void task_numa_compare(struct task_numa_env *env,
long imp = env->p->numa_group ? groupimp : taskimp;
long moveimp = imp;
int dist = env->dist;
- bool assigned = false;

rcu_read_lock();
-
- raw_spin_lock_irq(&dst_rq->lock);
- cur = dst_rq->curr;
- /*
- * No need to move the exiting task or idle task.
- */
- if ((cur->flags & PF_EXITING) || is_idle_task(cur))
+ cur = task_rcu_dereference(&dst_rq->curr);
+ if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
cur = NULL;
- else {
- /*
- * The task_struct must be protected here to protect the
- * p->numa_faults access in the task_weight since the
- * numa_faults could already be freed in the following path:
- * finish_task_switch()
- * --> put_task_struct()
- * --> __put_task_struct()
- * --> task_numa_free()
- */
- get_task_struct(cur);
- }
-
- raw_spin_unlock_irq(&dst_rq->lock);

/*
* Because we have preemption enabled we can get migrated around and
@@ -1428,7 +1410,6 @@ balance:
*/
if (!load_too_imbalanced(src_load, dst_load, env)) {
imp = moveimp - 1;
- put_task_struct(cur);
cur = NULL;
goto assign;
}
@@ -1454,16 +1435,9 @@ balance:
env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);

assign:
- assigned = true;
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
- /*
- * The dst_rq->curr isn't assigned. The protection for task_struct is
- * finished.
- */
- if (cur && !assigned)
- put_task_struct(cur);
}

static void task_numa_find_cpu(struct task_numa_env *env,