From: Kirill Tkhai <tkhai@ya.ru>
To: Qi Zheng <zhengqi.arch@bytedance.com>,
Sultan Alsawaf <sultan@kerneltoast.com>
Cc: akpm@linux-foundation.org, hannes@cmpxchg.org,
shakeelb@google.com, mhocko@kernel.org, roman.gushchin@linux.dev,
muchun.song@linux.dev, david@redhat.com, shy828301@gmail.com,
dave@stgolabs.net, penguin-kernel@i-love.sakura.ne.jp,
paulmck@kernel.org, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2 2/7] mm: vmscan: make global slab shrink lockless
Date: Sun, 26 Feb 2023 00:28:31 +0300 [thread overview]
Message-ID: <8dab3b27-7282-f8bc-7d04-ca63c9b872cf@ya.ru> (raw)
In-Reply-To: <2ba86f45-f0a5-3a85-4aa6-f8beb50491b3@bytedance.com>
On 25.02.2023 19:37, Qi Zheng wrote:
>
>
> On 2023/2/26 00:17, Kirill Tkhai wrote:
>> On 25.02.2023 18:57, Qi Zheng wrote:
>>>
> <...>
>>> How about this?
>>>>>
>>>>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>>>>> index ffddbd204259..9d8c53075298 100644
>>>>> --- a/mm/vmscan.c
>>>>> +++ b/mm/vmscan.c
>>>>> @@ -1012,7 +1012,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>>>>> int priority)
>>>>> {
>>>>> unsigned long ret, freed = 0;
>>>>> - struct shrinker *shrinker;
>>>>> + struct shrinker *shrinker = NULL;
>>>>> int srcu_idx, generation;
>>>>>
>>>>> /*
>>>>> @@ -1025,11 +1025,15 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>>>>> if (!mem_cgroup_disabled() && !mem_cgroup_is_root(memcg))
>>>>> return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
>>>>>
>>>>> +again:
>>>>> srcu_idx = srcu_read_lock(&shrinker_srcu);
>>>>>
>>>>> generation = atomic_read(&shrinker_srcu_generation);
>>>>> - list_for_each_entry_srcu(shrinker, &shrinker_list, list,
>>>>> - srcu_read_lock_held(&shrinker_srcu)) {
>>>>> + if (!shrinker)
>>>>> + shrinker = list_entry_rcu(shrinker_list.next, struct shrinker, list);
>>>>> + else
>>>>> + shrinker = list_entry_rcu(shrinker->list.next, struct shrinker, list);
>>>>> + list_for_each_entry_from_rcu(shrinker, &shrinker_list, list) {
>>>>> struct shrink_control sc = {
>>>>> .gfp_mask = gfp_mask,
>>>>> .nid = nid,
>>>>> @@ -1042,8 +1046,9 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>>>>> freed += ret;
>>>>>
>>>>> if (atomic_read(&shrinker_srcu_generation) != generation) {
>>>>> - freed = freed ? : 1;
>>>>> - break;
>>>>> + srcu_read_unlock(&shrinker_srcu, srcu_idx);
>>
>> After SRCU in unlocked we can't believe @shrinker anymore. So, above list_entry_rcu(shrinker->list.next)
>> dereferences some random memory.
>
> Indeed.
>
>>
>>>>> + cond_resched();
>>>>> + goto again;
>>>>> }
>>>>> }
>>>>>
>>>>>>
>>>>>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>>>>>> index 27ef9946ae8a..0b197bba1257 100644
>>>>>> --- a/mm/vmscan.c
>>>>>> +++ b/mm/vmscan.c
>>>>>> @@ -204,6 +204,7 @@ static void set_task_reclaim_state(struct task_struct *task,
>>>>>> LIST_HEAD(shrinker_list);
>>>>>> DEFINE_MUTEX(shrinker_mutex);
>>>>>> DEFINE_SRCU(shrinker_srcu);
>>>>>> +static atomic_t shrinker_srcu_generation = ATOMIC_INIT(0);
>>>>>> #ifdef CONFIG_MEMCG
>>>>>> static int shrinker_nr_max;
>>>>>> @@ -782,6 +783,7 @@ void unregister_shrinker(struct shrinker *shrinker)
>>>>>> debugfs_entry = shrinker_debugfs_remove(shrinker);
>>>>>> mutex_unlock(&shrinker_mutex);
>>>>>> + atomic_inc(&shrinker_srcu_generation);
>>>>>> synchronize_srcu(&shrinker_srcu);
>>>>>> debugfs_remove_recursive(debugfs_entry);
>>>>>> @@ -799,6 +801,7 @@ EXPORT_SYMBOL(unregister_shrinker);
>>>>>> */
>>>>>> void synchronize_shrinkers(void)
>>>>>> {
>>>>>> + atomic_inc(&shrinker_srcu_generation);
>>>>>> synchronize_srcu(&shrinker_srcu);
>>>>>> }
>>>>>> EXPORT_SYMBOL(synchronize_shrinkers);
>>>>>> @@ -908,18 +911,19 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
>>>>>> {
>>>>>> struct shrinker_info *info;
>>>>>> unsigned long ret, freed = 0;
>>>>>> - int srcu_idx;
>>>>>> - int i;
>>>>>> + int srcu_idx, generation;
>>>>>> + int i = 0;
>>>>>> if (!mem_cgroup_online(memcg))
>>>>>> return 0;
>>>>>> -
>>>>>> +again:
>>>>>> srcu_idx = srcu_read_lock(&shrinker_srcu);
>>>>>> info = shrinker_info_srcu(memcg, nid);
>>>>>> if (unlikely(!info))
>>>>>> goto unlock;
>>>>>> - for_each_set_bit(i, info->map, info->map_nr_max) {
>>>>>> + generation = atomic_read(&shrinker_srcu_generation);
>>>>>> + for_each_set_bit_from(i, info->map, info->map_nr_max) {
>>>>>> struct shrink_control sc = {
>>>>>> .gfp_mask = gfp_mask,
>>>>>> .nid = nid,
>>>>>> @@ -965,6 +969,11 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
>>>>>> set_shrinker_bit(memcg, nid, i);
>>>>>> }
>>>>>> freed += ret;
>>>>>> +
>>>>>> + if (atomic_read(&shrinker_srcu_generation) != generation) {
>>>>>> + srcu_read_unlock(&shrinker_srcu, srcu_idx);
>>>>>
>>>>> Maybe we can add the following code here, so as to avoid repeating the
>>>>> current id and avoid triggering softlockup:
>>>>>
>>>>> i++;
>>
>> This is OK.
>>
>>>>> cond_resched();
>>
>> Possible, existing cond_resched() in do_shrink_slab() is enough.
>
> Yeah.
>
> I will add this patch in the next version. May I mark you as the author
> of this patch?
I think, yes
>>
>>> And this. :)
>>>
>>> Thanks,
>>> Qi
>>>
>>>>>
>>>>> Thanks,
>>>>> Qi
>>>>>
>>>>>> + goto again;
>>>>>> + }
>>>>>> }
>>>>>> unlock:
>>>>>> srcu_read_unlock(&shrinker_srcu, srcu_idx);
>>>>>> @@ -1004,7 +1013,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>>>>>> {
>>>>>> unsigned long ret, freed = 0;
>>>>>> struct shrinker *shrinker;
>>>>>> - int srcu_idx;
>>>>>> + int srcu_idx, generation;
>>>>>> /*
>>>>>> * The root memcg might be allocated even though memcg is disabled
>>>>>> @@ -1017,6 +1026,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>>>>>> return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
>>>>>> srcu_idx = srcu_read_lock(&shrinker_srcu);
>>>>>> + generation = atomic_read(&shrinker_srcu_generation);
>>>>>> list_for_each_entry_srcu(shrinker, &shrinker_list, list,
>>>>>> srcu_read_lock_held(&shrinker_srcu)) {
>>>>>> @@ -1030,6 +1040,11 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
>>>>>> if (ret == SHRINK_EMPTY)
>>>>>> ret = 0;
>>>>>> freed += ret;
>>>>>> +
>>>>>> + if (atomic_read(&shrinker_srcu_generation) != generation) {
>>>>>> + freed = freed ? : 1;
>>>>>> + break;
>>>>>> + }
>>>>>> }
>>>>>> srcu_read_unlock(&shrinker_srcu, srcu_idx);
>>>>>>
>>>>>>
>>>>>
>>>>
>>>
>>
>
next prev parent reply other threads:[~2023-02-25 21:28 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-23 13:27 [PATCH v2 0/7] make " Qi Zheng
2023-02-23 13:27 ` [PATCH v2 1/7] mm: vmscan: add a map_nr_max field to shrinker_info Qi Zheng
2023-02-25 8:18 ` Qi Zheng
2023-02-25 15:14 ` Kirill Tkhai
2023-02-25 15:52 ` Qi Zheng
2023-02-26 13:54 ` Qi Zheng
2023-02-23 13:27 ` [PATCH v2 2/7] mm: vmscan: make global slab shrink lockless Qi Zheng
2023-02-23 15:26 ` Rafael Aquini
2023-02-23 15:37 ` Rafael Aquini
2023-02-24 4:09 ` Qi Zheng
2023-02-23 18:24 ` Sultan Alsawaf
2023-02-23 18:39 ` Paul E. McKenney
2023-02-23 19:18 ` Sultan Alsawaf
2023-02-24 4:00 ` Qi Zheng
2023-02-24 4:16 ` Qi Zheng
2023-02-24 8:20 ` Sultan Alsawaf
2023-02-24 10:12 ` Qi Zheng
2023-02-24 21:02 ` Kirill Tkhai
2023-02-24 21:14 ` Kirill Tkhai
2023-02-25 8:08 ` Qi Zheng
2023-02-25 15:30 ` Kirill Tkhai
2023-02-25 15:57 ` Qi Zheng
2023-02-25 16:17 ` Kirill Tkhai
2023-02-25 16:37 ` Qi Zheng
2023-02-25 21:28 ` Kirill Tkhai [this message]
2023-02-26 13:56 ` Qi Zheng
2023-02-23 13:27 ` [PATCH v2 3/7] mm: vmscan: make memcg " Qi Zheng
2023-02-23 13:27 ` [PATCH v2 4/7] mm: shrinkers: make count and scan in shrinker debugfs lockless Qi Zheng
2023-02-23 13:27 ` [PATCH v2 5/7] mm: vmscan: hold write lock to reparent shrinker nr_deferred Qi Zheng
2023-02-23 13:27 ` [PATCH v2 6/7] mm: vmscan: remove shrinker_rwsem from synchronize_shrinkers() Qi Zheng
2023-02-23 13:27 ` [PATCH v2 7/7] mm: shrinkers: convert shrinker_rwsem to mutex Qi Zheng
2023-02-23 18:19 ` [PATCH v2 0/7] make slab shrink lockless Paul E. McKenney
2023-02-24 4:08 ` Qi Zheng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=8dab3b27-7282-f8bc-7d04-ca63c9b872cf@ya.ru \
--to=tkhai@ya.ru \
--cc=akpm@linux-foundation.org \
--cc=dave@stgolabs.net \
--cc=david@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@kernel.org \
--cc=muchun.song@linux.dev \
--cc=paulmck@kernel.org \
--cc=penguin-kernel@i-love.sakura.ne.jp \
--cc=roman.gushchin@linux.dev \
--cc=shakeelb@google.com \
--cc=shy828301@gmail.com \
--cc=sultan@kerneltoast.com \
--cc=zhengqi.arch@bytedance.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox