Re: [PATCH mm-unstable v3 2/5] mm: don't hold css->refcnt during traversal

[T.J. Mercier]

On Tue, Aug 27, 2024 at 4:11 PM Kinsey Ho <kinseyho@xxxxxxxxxx> wrote:
>
> To obtain the pointer to the next memcg position, mem_cgroup_iter()
> currently holds css->refcnt during memcg traversal only to put
> css->refcnt at the end of the routine. This isn't necessary as an
> rcu_read_lock is already held throughout the function. The use of
> the RCU read lock with css_next_descendant_pre() guarantees that
> sibling linkage is safe without holding a ref on the passed-in @css.
>
> Remove css->refcnt usage during traversal by leveraging RCU.
>
> Signed-off-by: Kinsey Ho <kinseyho@xxxxxxxxxx>

Reviewed-by: T.J. Mercier <tjmercier@xxxxxxxxxx>

I found a different place where a more trivial css get/put pair than
this could be removed, but I couldn't measure a perf difference. Like
Yosry, I appreciate the simplicity gains here though.

> ---
>  mm/memcontrol.c | 18 +-----------------
>  1 file changed, 1 insertion(+), 17 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 35431035e782..67b1994377b7 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1013,20 +1013,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
>                 else if (reclaim->generation != iter->generation)
>                         goto out_unlock;
>
> -               while (1) {
> -                       pos = READ_ONCE(iter->position);
> -                       if (!pos || css_tryget(&pos->css))
> -                               break;
> -                       /*
> -                        * css reference reached zero, so iter->position will
> -                        * be cleared by ->css_released. However, we should not
> -                        * rely on this happening soon, because ->css_released
> -                        * is called from a work queue, and by busy-waiting we
> -                        * might block it. So we clear iter->position right
> -                        * away.
> -                        */
> -                       (void)cmpxchg(&iter->position, pos, NULL);
> -               }
> +               pos = READ_ONCE(iter->position);
>         } else if (prev) {
>                 pos = prev;
>         }
> @@ -1067,9 +1054,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root,
>                  */
>                 (void)cmpxchg(&iter->position, pos, memcg);
>
> -               if (pos)
> -                       css_put(&pos->css);
> -
>                 if (!memcg)
>                         iter->generation++;
>         }
> --
> 2.46.0.295.g3b9ea8a38a-goog
>
>