linux-kernel - Re: [v3 PATCH 09/11] mm: vmscan: don't need allocate shrinker->nr

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ed883db6-5f52-a41b-d759-f4fb61d5b4e5@virtuozzo.com>
Date:   Tue, 12 Jan 2021 00:57:02 +0300
From:   Kirill Tkhai <ktkhai@...tuozzo.com>
To:     Yang Shi <shy828301@...il.com>
Cc:     Roman Gushchin <guro@...com>, Shakeel Butt <shakeelb@...gle.com>,
        Dave Chinner <david@...morbit.com>,
        Johannes Weiner <hannes@...xchg.org>,
        Michal Hocko <mhocko@...e.com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        Linux MM <linux-mm@...ck.org>,
        Linux FS-devel Mailing List <linux-fsdevel@...r.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [v3 PATCH 09/11] mm: vmscan: don't need allocate
 shrinker->nr_deferred for memcg aware shrinkers

On 11.01.2021 21:40, Yang Shi wrote:
> On Wed, Jan 6, 2021 at 3:16 AM Kirill Tkhai <ktkhai@...tuozzo.com> wrote:
>>
>> On 06.01.2021 01:58, Yang Shi wrote:
>>> Now nr_deferred is available on per memcg level for memcg aware shrinkers, so don't need
>>> allocate shrinker->nr_deferred for such shrinkers anymore.
>>>
>>> The prealloc_memcg_shrinker() would return -ENOSYS if !CONFIG_MEMCG or memcg is disabled
>>> by kernel command line, then shrinker's SHRINKER_MEMCG_AWARE flag would be cleared.
>>> This makes the implementation of this patch simpler.
>>>
>>> Signed-off-by: Yang Shi <shy828301@...il.com>
>>> ---
>>>  mm/vmscan.c | 33 ++++++++++++++++++---------------
>>>  1 file changed, 18 insertions(+), 15 deletions(-)
>>>
>>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>>> index f20ed8e928c2..d9795fb0f1c5 100644
>>> --- a/mm/vmscan.c
>>> +++ b/mm/vmscan.c
>>> @@ -340,6 +340,9 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker)
>>>  {
>>>       int id, ret = -ENOMEM;
>>>
>>> +     if (mem_cgroup_disabled())
>>> +             return -ENOSYS;
>>> +
>>>       down_write(&shrinker_rwsem);
>>>       /* This may call shrinker, so it must use down_read_trylock() */
>>>       id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL);
>>> @@ -424,7 +427,7 @@ static bool writeback_throttling_sane(struct scan_control *sc)
>>>  #else
>>>  static int prealloc_memcg_shrinker(struct shrinker *shrinker)
>>>  {
>>> -     return 0;
>>> +     return -ENOSYS;
>>>  }
>>>
>>>  static void unregister_memcg_shrinker(struct shrinker *shrinker)
>>> @@ -535,8 +538,20 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
>>>   */
>>>  int prealloc_shrinker(struct shrinker *shrinker)
>>>  {
>>> -     unsigned int size = sizeof(*shrinker->nr_deferred);
>>> +     unsigned int size;
>>> +     int err;
>>> +
>>> +     if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
>>> +             err = prealloc_memcg_shrinker(shrinker);
>>> +             if (!err)
>>> +                     return 0;
>>> +             if (err != -ENOSYS)
>>> +                     return err;
>>> +
>>> +             shrinker->flags &= ~SHRINKER_MEMCG_AWARE;
>>
>> This looks very confusing.
>>
>> In case of you want to disable preallocation branch for !MEMCG case,
>> you should firstly consider something like the below:
> 
> Not only !CONFIG_MEMCG, but also "cgroup_disable=memory" case.
> 
>>
>> #ifdef CONFIG_MEMCG
>> #define SHRINKER_MEMCG_AWARE    (1 << 2)
>> #else
>> #define SHRINKER_MEMCG_AWARE    0
>> #endif
> 
> This could handle !CONFIG_MEMCG case, but can't deal with
> "cgroup_disable=memory" case. We could consider check
> mem_cgroup_disabled() when initializing shrinker, but this may result
> in touching fs codes like below:
> 
> --- a/fs/super.c
> +++ b/fs/super.c
> @@ -266,7 +266,9 @@ static struct super_block *alloc_super(struct
> file_system_type *type, int flags,
>         s->s_shrink.scan_objects = super_cache_scan;
>         s->s_shrink.count_objects = super_cache_count;
>         s->s_shrink.batch = 1024;
> -       s->s_shrink.flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE;
> +       s->s_shrink.flags = SHRINKER_NUMA_AWARE;
> +       if (!mem_cgroup_disabled())
> +               s->s_shrink.flags |= SHRINKER_MEMCG_AWARE;
>         if (prealloc_shrinker(&s->s_shrink))
>                 goto fail;
>         if (list_lru_init_memcg(&s->s_dentry_lru, &s->s_shrink))

Oh. If so, then initial variant was better.

>>
>>> +     }
>>>
>>> +     size = sizeof(*shrinker->nr_deferred);
>>>       if (shrinker->flags & SHRINKER_NUMA_AWARE)
>>>               size *= nr_node_ids;
>>>
>>> @@ -544,26 +559,14 @@ int prealloc_shrinker(struct shrinker *shrinker)
>>>       if (!shrinker->nr_deferred)
>>>               return -ENOMEM;
>>>
>>> -     if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
>>> -             if (prealloc_memcg_shrinker(shrinker))
>>> -                     goto free_deferred;
>>> -     }
>>>
>>>       return 0;
>>> -
>>> -free_deferred:
>>> -     kfree(shrinker->nr_deferred);
>>> -     shrinker->nr_deferred = NULL;
>>> -     return -ENOMEM;
>>>  }
>>>
>>>  void free_prealloced_shrinker(struct shrinker *shrinker)
>>>  {
>>> -     if (!shrinker->nr_deferred)
>>> -             return;
>>> -
>>>       if (shrinker->flags & SHRINKER_MEMCG_AWARE)
>>> -             unregister_memcg_shrinker(shrinker);
>>> +             return unregister_memcg_shrinker(shrinker);
>>>
>>>       kfree(shrinker->nr_deferred);
>>>       shrinker->nr_deferred = NULL;
>>>
>>
>>