On Fri, Oct 1, 2021 at 12:10 PM Waiman Long <longman@xxxxxxxxxx> wrote:
>
> To ensure that a to-be-offlined memcg fetched from objcg remains
> valid (has non-zero reference count) within a RCU critical section,
> a synchronize_rcu() call is inserted at the end of memcg_offline_kmem().
>
> With that change, we no longer need to use css_tryget()
> in get_mem_cgroup_from_objcg() as the final css_put() in
> css_killed_work_fn() would not have been called yet.
>
> The obj_cgroup_uncharge_pages() function is simplifed to perform
> the whole uncharge operation within a RCU critical section saving a
> css_get()/css_put() pair.
>
> Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
> ---
> mm/memcontrol.c | 16 +++++++++++-----
> 1 file changed, 11 insertions(+), 5 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 8177f253a127..1dbb37d96e49 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -2769,10 +2769,8 @@ static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
> struct mem_cgroup *memcg;
>
> rcu_read_lock();
> -retry:
> memcg = obj_cgroup_memcg(objcg);
> - if (unlikely(!css_tryget(&memcg->css)))
> - goto retry;
> + css_get(&memcg->css);
> rcu_read_unlock();
>
> return memcg;
> @@ -2947,13 +2945,14 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg,
> {
> struct mem_cgroup *memcg;
>
> - memcg = get_mem_cgroup_from_objcg(objcg);
> + rcu_read_lock();
> + memcg = obj_cgroup_memcg(objcg);
>
> if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
> page_counter_uncharge(&memcg->kmem, nr_pages);
> refill_stock(memcg, nr_pages);
>
> - css_put(&memcg->css);
> + rcu_read_unlock();
> }
>
> /*
> @@ -3672,6 +3671,13 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg)
> memcg_drain_all_list_lrus(kmemcg_id, parent);
>
> memcg_free_cache_id(kmemcg_id);
> +
> + /*
> + * To ensure that a to-be-offlined memcg fetched from objcg remains
> + * valid within a RCU critical section, we need to wait here until
> + * the a grace period has elapsed.
> + */
> + synchronize_rcu();
This is called with cgroup_mutex held from css_offline path and
synchronize_rcu() can be very expensive on a busy system, so, this
will indirectly impact all the code paths which take cgroup_mutex.
> }
> #else
> static int memcg_online_kmem(struct mem_cgroup *memcg)
> --
> 2.18.1
>
