On Sat, May 3, 2008 at 2:38 PM, Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
quoted text
>  +
>  +int rlimit_cgroup_charge_as(struct mm_struct *mm, unsigned long nr_pages)
>  +{
>  +       int ret;
>  +       struct rlimit_cgroup *rcg;
>  +
>  +       rcu_read_lock();
>  +       rcg = rlimit_cgroup_from_task(rcu_dereference(mm->owner));
>  +       css_get(&rcg->css);
>  +       rcu_read_unlock();
>  +
>  +       ret = res_counter_charge(&rcg->as_res, (nr_pages << PAGE_SHIFT));
>  +       css_put(&rcg->css);
>  +       return ret;
>  +}

You need to synchronize against mm->owner changing, or
mm->owner->cgroups changing. How about:

int rlimit_cgroup_charge_as(struct mm_struct *mm, unsigned long nr_pages)
{
  int ret;
  struct rlimit_cgroup *rcg;
  struct task_struct *owner;

  rcu_read_lock();
 again:

  /* Find and lock the owner of the mm */
  owner = rcu_dereference(mm->owner);
  task_lock(owner);
  if (mm->owner != owner) {
    task_unlock(owner);
    goto again;
  }

  /* Charge the owner's cgroup with the new memory */
  rcg = rlimit_cgroup_from_task(owner);
  ret = res_counter_charge(&rcg->as_res, (nr_pages << PAGE_SHIFT));
  task_unlock(owner);
  rcu_read_unlock();
  return ret;
}

quoted text
>  +
>  +void rlimit_cgroup_uncharge_as(struct mm_struct *mm, unsigned long nr_pages)
>  +{
>  +       struct rlimit_cgroup *rcg;
>  +
>  +       rcu_read_lock();
>  +       rcg = rlimit_cgroup_from_task(rcu_dereference(mm->owner));
>  +       css_get(&rcg->css);
>  +       rcu_read_unlock();
>  +
>  +       res_counter_uncharge(&rcg->as_res, (nr_pages << PAGE_SHIFT));
>  +       css_put(&rcg->css);
>  +}

Can't this be implemented as just a call to charge() with a negative
value? (Possibly fixing res_counter_charge() to handle negative values
if necessary) Seems simpler.

quoted text
>
>  +/*
>  + * TODO: get the attach callbacks to fail and disallow task movement.
>  + */

You mean disallow all movement within a hierarchy that has this cgroup
mounted? Doesn't that make it rather hard to use?

quoted text
>  +static void rlimit_cgroup_move_task(struct cgroup_subsys *ss,
>  +                                       struct cgroup *cgrp,
>  +                                       struct cgroup *old_cgrp,
>  +                                       struct task_struct *p)
>  +{
>  +       struct mm_struct *mm;
>  +       struct rlimit_cgroup *rcg, *old_rcg;
>  +
>  +       mm = get_task_mm(p);
>  +       if (mm == NULL)
>  +               return;
>  +
>  +       rcu_read_lock();
>  +       if (p != rcu_dereference(mm->owner))
>  +               goto out;
>  +
>  +       rcg = rlimit_cgroup_from_cgrp(cgrp);
>  +       old_rcg = rlimit_cgroup_from_cgrp(old_cgrp);
>  +
>  +       if (rcg == old_rcg)
>  +               goto out;
>  +
>  +       if (res_counter_charge(&rcg->as_res, (mm->total_vm << PAGE_SHIFT)))
>  +               goto out;
>  +       res_counter_uncharge(&old_rcg->as_res, (mm->total_vm << PAGE_SHIFT));
>  +out:
>  +       rcu_read_unlock();
>  +       mmput(mm);
>  +}
>  +

Since you need to protect against concurrent charges, and against
concurrent mm ownership changes, I think you should just do this under
task_lock(p).

quoted text
>  +static void rlimit_cgroup_mm_owner_changed(struct cgroup_subsys *ss,
>  +                                               struct cgroup *cgrp,
>  +                                               struct cgroup *old_cgrp,
>  +                                               struct task_struct *p)
>  +{
>  +       struct rlimit_cgroup *rcg, *old_rcg;
>  +       struct mm_struct *mm = get_task_mm(p);
>  +
>  +       BUG_ON(!mm);
>  +       rcg = rlimit_cgroup_from_cgrp(cgrp);
>  +       old_rcg = rlimit_cgroup_from_cgrp(old_cgrp);
>  +       if (res_counter_charge(&rcg->as_res, (mm->total_vm << PAGE_SHIFT)))
>  +               goto out;
>  +       res_counter_uncharge(&old_rcg->as_res, (mm->total_vm << PAGE_SHIFT));
>  +out:
>  +       mmput(mm);
>  +}
>  +

Also needs to task_lock(p) to prevent concurrent charges or cgroup
reassignments?

Paul
--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/