Re: [PATCH v3 2/7] mm: generalize postponed non-root kmem_cache deactivation

[Shakeel Butt]

From: Roman Gushchin <guro@xxxxxx>
Date: Wed, May 8, 2019 at 1:30 PM
To: Andrew Morton, Shakeel Butt
Cc: <linux-mm@xxxxxxxxx>, <linux-kernel@xxxxxxxxxxxxxxx>,
<kernel-team@xxxxxx>, Johannes Weiner, Michal Hocko, Rik van Riel,
Christoph Lameter, Vladimir Davydov, <cgroups@xxxxxxxxxxxxxxx>, Roman
Gushchin

> Currently SLUB uses a work scheduled after an RCU grace period
> to deactivate a non-root kmem_cache. This mechanism can be reused
> for kmem_caches reparenting, but requires some generalization.
>
> Let's decouple all infrastructure (rcu callback, work callback)
> from the SLUB-specific code, so it can be used with SLAB as well.
>
> Also, let's rename some functions to make the code look simpler.
> All SLAB/SLUB-specific functions start with "__". Remove "deact_"
> prefix from the corresponding struct fields.
>
> Here is the graph of a new calling scheme:
> kmemcg_cache_deactivate()
>   __kmemcg_cache_deactivate()                  SLAB/SLUB-specific
>   kmemcg_schedule_work_after_rcu()             rcu
>     kmemcg_after_rcu_workfn()                  work
>       kmemcg_cache_deactivate_after_rcu()
>         __kmemcg_cache_deactivate_after_rcu()  SLAB/SLUB-specific
>
> instead of:
> __kmemcg_cache_deactivate()                    SLAB/SLUB-specific
>   slab_deactivate_memcg_cache_rcu_sched()      SLUB-only
>     kmemcg_deactivate_rcufn                    SLUB-only, rcu
>       kmemcg_deactivate_workfn                 SLUB-only, work
>         kmemcg_cache_deact_after_rcu()         SLUB-only
>
> Signed-off-by: Roman Gushchin <guro@xxxxxx>

Reviewed-by: Shakeel Butt <shakeelb@xxxxxxxxxx>

> ---
>  include/linux/slab.h |  6 ++---
>  mm/slab.c            |  4 +++
>  mm/slab.h            |  3 ++-
>  mm/slab_common.c     | 62 ++++++++++++++++++++------------------------
>  mm/slub.c            |  8 +-----
>  5 files changed, 38 insertions(+), 45 deletions(-)
>
> diff --git a/include/linux/slab.h b/include/linux/slab.h
> index 9449b19c5f10..47923c173f30 100644
> --- a/include/linux/slab.h
> +++ b/include/linux/slab.h
> @@ -642,10 +642,10 @@ struct memcg_cache_params {
>                         struct list_head children_node;
>                         struct list_head kmem_caches_node;
>
> -                       void (*deact_fn)(struct kmem_cache *);
> +                       void (*work_fn)(struct kmem_cache *);
>                         union {
> -                               struct rcu_head deact_rcu_head;
> -                               struct work_struct deact_work;
> +                               struct rcu_head rcu_head;
> +                               struct work_struct work;
>                         };
>                 };
>         };
> diff --git a/mm/slab.c b/mm/slab.c
> index f6eff59e018e..83000e46b870 100644
> --- a/mm/slab.c
> +++ b/mm/slab.c
> @@ -2281,6 +2281,10 @@ void __kmemcg_cache_deactivate(struct kmem_cache *cachep)
>  {
>         __kmem_cache_shrink(cachep);
>  }
> +
> +void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
> +{
> +}
>  #endif
>
>  int __kmem_cache_shutdown(struct kmem_cache *cachep)
> diff --git a/mm/slab.h b/mm/slab.h
> index 6a562ca72bca..4a261c97c138 100644
> --- a/mm/slab.h
> +++ b/mm/slab.h
> @@ -172,6 +172,7 @@ int __kmem_cache_shutdown(struct kmem_cache *);
>  void __kmem_cache_release(struct kmem_cache *);
>  int __kmem_cache_shrink(struct kmem_cache *);
>  void __kmemcg_cache_deactivate(struct kmem_cache *s);
> +void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s);
>  void slab_kmem_cache_release(struct kmem_cache *);
>
>  struct seq_file;
> @@ -291,7 +292,7 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
>  extern void slab_init_memcg_params(struct kmem_cache *);
>  extern void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg);
>  extern void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
> -                               void (*deact_fn)(struct kmem_cache *));
> +                               void (*work_fn)(struct kmem_cache *));
>
>  #else /* CONFIG_MEMCG_KMEM */
>
> diff --git a/mm/slab_common.c b/mm/slab_common.c
> index 6e00bdf8618d..4e5b4292a763 100644
> --- a/mm/slab_common.c
> +++ b/mm/slab_common.c
> @@ -691,17 +691,18 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
>         put_online_cpus();
>  }
>
> -static void kmemcg_deactivate_workfn(struct work_struct *work)
> +static void kmemcg_after_rcu_workfn(struct work_struct *work)
>  {
>         struct kmem_cache *s = container_of(work, struct kmem_cache,
> -                                           memcg_params.deact_work);
> +                                           memcg_params.work);
>
>         get_online_cpus();
>         get_online_mems();
>
>         mutex_lock(&slab_mutex);
>
> -       s->memcg_params.deact_fn(s);
> +       s->memcg_params.work_fn(s);
> +       s->memcg_params.work_fn = NULL;
>
>         mutex_unlock(&slab_mutex);
>
> @@ -712,37 +713,28 @@ static void kmemcg_deactivate_workfn(struct work_struct *work)
>         css_put(&s->memcg_params.memcg->css);
>  }
>
> -static void kmemcg_deactivate_rcufn(struct rcu_head *head)
> +/*
> + * We need to grab blocking locks.  Bounce to ->work.  The
> + * work item shares the space with the RCU head and can't be
> + * initialized eariler.
> +*/
> +static void kmemcg_schedule_work_after_rcu(struct rcu_head *head)
>  {
>         struct kmem_cache *s = container_of(head, struct kmem_cache,
> -                                           memcg_params.deact_rcu_head);
> +                                           memcg_params.rcu_head);
>
> -       /*
> -        * We need to grab blocking locks.  Bounce to ->deact_work.  The
> -        * work item shares the space with the RCU head and can't be
> -        * initialized eariler.
> -        */
> -       INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn);
> -       queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work);
> +       INIT_WORK(&s->memcg_params.work, kmemcg_after_rcu_workfn);
> +       queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
>  }
>
> -/**
> - * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a
> - *                                        sched RCU grace period
> - * @s: target kmem_cache
> - * @deact_fn: deactivation function to call
> - *
> - * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex
> - * held after a sched RCU grace period.  The slab is guaranteed to stay
> - * alive until @deact_fn is finished.  This is to be used from
> - * __kmemcg_cache_deactivate().
> - */
> -void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
> -                                          void (*deact_fn)(struct kmem_cache *))
> +static void kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
>  {
> -       if (WARN_ON_ONCE(is_root_cache(s)) ||
> -           WARN_ON_ONCE(s->memcg_params.deact_fn))
> -               return;
> +       __kmemcg_cache_deactivate_after_rcu(s);
> +}
> +
> +static void kmemcg_cache_deactivate(struct kmem_cache *s)
> +{
> +       __kmemcg_cache_deactivate(s);
>
>         if (s->memcg_params.root_cache->memcg_params.dying)
>                 return;
> @@ -750,8 +742,9 @@ void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
>         /* pin memcg so that @s doesn't get destroyed in the middle */
>         css_get(&s->memcg_params.memcg->css);
>
> -       s->memcg_params.deact_fn = deact_fn;
> -       call_rcu(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn);
> +       WARN_ON_ONCE(s->memcg_params.work_fn);
> +       s->memcg_params.work_fn = kmemcg_cache_deactivate_after_rcu;
> +       call_rcu(&s->memcg_params.rcu_head, kmemcg_schedule_work_after_rcu);
>  }
>
>  void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
> @@ -773,7 +766,7 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
>                 if (!c)
>                         continue;
>
> -               __kmemcg_cache_deactivate(c);
> +               kmemcg_cache_deactivate(c);
>                 arr->entries[idx] = NULL;
>         }
>         mutex_unlock(&slab_mutex);
> @@ -866,11 +859,12 @@ static void flush_memcg_workqueue(struct kmem_cache *s)
>         mutex_unlock(&slab_mutex);
>
>         /*
> -        * SLUB deactivates the kmem_caches through call_rcu. Make
> +        * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make
>          * sure all registered rcu callbacks have been invoked.
>          */
> -       if (IS_ENABLED(CONFIG_SLUB))
> -               rcu_barrier();
> +#ifndef CONFIG_SLOB
> +       rcu_barrier();
> +#endif
>
>         /*
>          * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
> diff --git a/mm/slub.c b/mm/slub.c
> index 16f7e4f5a141..43c34d54ad86 100644
> --- a/mm/slub.c
> +++ b/mm/slub.c
> @@ -4028,7 +4028,7 @@ int __kmem_cache_shrink(struct kmem_cache *s)
>  }
>
>  #ifdef CONFIG_MEMCG
> -static void kmemcg_cache_deact_after_rcu(struct kmem_cache *s)
> +void __kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
>  {
>         /*
>          * Called with all the locks held after a sched RCU grace period.
> @@ -4054,12 +4054,6 @@ void __kmemcg_cache_deactivate(struct kmem_cache *s)
>          */
>         slub_set_cpu_partial(s, 0);
>         s->min_partial = 0;
> -
> -       /*
> -        * s->cpu_partial is checked locklessly (see put_cpu_partial), so
> -        * we have to make sure the change is visible before shrinking.
> -        */
> -       slab_deactivate_memcg_cache_rcu_sched(s, kmemcg_cache_deact_after_rcu);
>  }
>  #endif /* CONFIG_MEMCG */
>
> --
> 2.20.1
>