| 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
| ||
|
Message-ID: <c91da693-445f-faf4-d69e-d77ab4b5090c@bytedance.com>
Date: Sat, 25 Feb 2023 23:52:43 +0800
From: Qi Zheng <zhengqi.arch@...edance.com>
To: Kirill Tkhai <tkhai@...ru>
Cc: sultan@...neltoast.com, dave@...olabs.net,
penguin-kernel@...ove.SAKURA.ne.jp, paulmck@...nel.org,
linux-mm@...ck.org, linux-kernel@...r.kernel.org,
Andrew Morton <akpm@...ux-foundation.org>,
Johannes Weiner <hannes@...xchg.org>,
Shakeel Butt <shakeelb@...gle.com>,
Michal Hocko <mhocko@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Muchun Song <muchun.song@...ux.dev>,
David Hildenbrand <david@...hat.com>,
Yang Shi <shy828301@...il.com>
Subject: Re: [PATCH v2 1/7] mm: vmscan: add a map_nr_max field to
shrinker_info
On 2023/2/25 23:14, Kirill Tkhai wrote:
> Hi Qi,
>
> On 25.02.2023 11:18, Qi Zheng wrote:
>>
>>
>> On 2023/2/23 21:27, Qi Zheng wrote:
>>> To prepare for the subsequent lockless memcg slab shrink,
>>> add a map_nr_max field to struct shrinker_info to records
>>> its own real shrinker_nr_max.
>>>
>>> No functional changes.
>>>
>>> Signed-off-by: Qi Zheng <zhengqi.arch@...edance.com>
>>
>> I missed Suggested-by here, hi Kirill, can I add it?
>>
>> Suggested-by: Kirill Tkhai <tkhai@...ru>
>
> Yes, feel free to add this tag.
Thanks.
>
> There is a comment below.
>
>>> ---
>>> include/linux/memcontrol.h | 1 +
>>> mm/vmscan.c | 29 ++++++++++++++++++-----------
>>> 2 files changed, 19 insertions(+), 11 deletions(-)
>>>
>>> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
>>> index b6eda2ab205d..aa69ea98e2d8 100644
>>> --- a/include/linux/memcontrol.h
>>> +++ b/include/linux/memcontrol.h
>>> @@ -97,6 +97,7 @@ struct shrinker_info {
>>> struct rcu_head rcu;
>>> atomic_long_t *nr_deferred;
>>> unsigned long *map;
>>> + int map_nr_max;
>>> };
>>> struct lruvec_stats_percpu {
>>> diff --git a/mm/vmscan.c b/mm/vmscan.c
>>> index 9c1c5e8b24b8..9f895ca6216c 100644
>>> --- a/mm/vmscan.c
>>> +++ b/mm/vmscan.c
>>> @@ -224,9 +224,16 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
>>> lockdep_is_held(&shrinker_rwsem));
>>> }
>>> +static inline bool need_expand(int new_nr_max, int old_nr_max)
>>> +{
>>> + return round_up(new_nr_max, BITS_PER_LONG) >
>>> + round_up(old_nr_max, BITS_PER_LONG);
>>> +}
>>> +
>>> static int expand_one_shrinker_info(struct mem_cgroup *memcg,
>>> int map_size, int defer_size,
>>> - int old_map_size, int old_defer_size)
>>> + int old_map_size, int old_defer_size,
>>> + int new_nr_max)
>>> {
>>> struct shrinker_info *new, *old;
>>> struct mem_cgroup_per_node *pn;
>>> @@ -240,12 +247,16 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg,
>>> if (!old)
>>> return 0;
>>> + if (!need_expand(new_nr_max, old->map_nr_max))
>>> + return 0;
>>> +
>>> new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
>>> if (!new)
>>> return -ENOMEM;
>>> new->nr_deferred = (atomic_long_t *)(new + 1);
>>> new->map = (void *)new->nr_deferred + defer_size;
>>> + new->map_nr_max = new_nr_max;
>>> /* map: set all old bits, clear all new bits */
>>> memset(new->map, (int)0xff, old_map_size);
>>> @@ -295,6 +306,7 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
>>> }
>>> info->nr_deferred = (atomic_long_t *)(info + 1);
>>> info->map = (void *)info->nr_deferred + defer_size;
>>> + info->map_nr_max = shrinker_nr_max;
>>> rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_info, info);
>>> }
>>> up_write(&shrinker_rwsem);
>>> @@ -302,12 +314,6 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
>>> return ret;
>>> }
>>> -static inline bool need_expand(int nr_max)
>>> -{
>>> - return round_up(nr_max, BITS_PER_LONG) >
>>> - round_up(shrinker_nr_max, BITS_PER_LONG);
>>> -}
>>> -
>>> static int expand_shrinker_info(int new_id)
>>> {
>>> int ret = 0;
>>> @@ -316,7 +322,7 @@ static int expand_shrinker_info(int new_id)
>>> int old_map_size, old_defer_size = 0;
>>> struct mem_cgroup *memcg;
>>> - if (!need_expand(new_nr_max))
>>> + if (!need_expand(new_nr_max, shrinker_nr_max))
>>> goto out;
>>> if (!root_mem_cgroup)
>>> @@ -332,7 +338,8 @@ static int expand_shrinker_info(int new_id)
>>> memcg = mem_cgroup_iter(NULL, NULL, NULL);
>>> do {
>>> ret = expand_one_shrinker_info(memcg, map_size, defer_size,
>>> - old_map_size, old_defer_size);
>>> + old_map_size, old_defer_size,
>>> + new_nr_max);
>>> if (ret) {
>>> mem_cgroup_iter_break(NULL, memcg);
>>> goto out;
>>> @@ -432,7 +439,7 @@ void reparent_shrinker_deferred(struct mem_cgroup *memcg)
>>> for_each_node(nid) {
>>> child_info = shrinker_info_protected(memcg, nid);
>>> parent_info = shrinker_info_protected(parent, nid);
>>> - for (i = 0; i < shrinker_nr_max; i++) {
>>> + for (i = 0; i < child_info->map_nr_max; i++) {
>>> nr = atomic_long_read(&child_info->nr_deferred[i]);
>>> atomic_long_add(nr, &parent_info->nr_deferred[i]);
>>> }
>>> @@ -899,7 +906,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
>>> if (unlikely(!info))
>>> goto unlock;
>>> - for_each_set_bit(i, info->map, shrinker_nr_max) {
>>> + for_each_set_bit(i, info->map, info->map_nr_max) {
>>> struct shrink_control sc = {
>>> .gfp_mask = gfp_mask,
>>> .nid = nid,
>
> The patch as whole thing won't work as expected. It won't ever call shrinker with ids from [round_down(shrinker_nr_max, sizeof(unsigned long)) + 1, shrinker_nr_max - 1]
>
> Just replay the sequence we add new shrinkers:
>
> 1)We add shrinker #0:
> shrinker_nr_max = 0;
>
> prealloc_memcg_shrinker()
> id = 0;
> expand_shrinker_info(0)
> new_nr_max = 1;
> expand_one_shrinker_info(new_nr_max = 1)
> new->map_nr_max = 1;
> shrinker_nr_max = 1;
>
> 2)We add shrinker #1:
> prealloc_memcg_shrinker()
> id = 1;
> expand_shrinker_info(1)
> new_nr_max = 2;
> need_expand(2, 1) => false => ignore expand
> shrinker_nr_max = 2;
>
> 3)Then we call shrinker:
> shrink_slab_memcg()
> for_each_set_bit(i, info->map, 1/* info->map_nr_max */ ) {
> } => ignore shrinker #1
Oh, I got it.
>
> I'd fixed this patch by something like the below:
The fix below looks good to me, will add them to the next version. :)
Thanks,
Qi
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 9f895ca6216c..bb617a3871f1 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -224,12 +224,6 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
> lockdep_is_held(&shrinker_rwsem));
> }
>
> -static inline bool need_expand(int new_nr_max, int old_nr_max)
> -{
> - return round_up(new_nr_max, BITS_PER_LONG) >
> - round_up(old_nr_max, BITS_PER_LONG);
> -}
> -
> static int expand_one_shrinker_info(struct mem_cgroup *memcg,
> int map_size, int defer_size,
> int old_map_size, int old_defer_size,
> @@ -247,9 +241,6 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg,
> if (!old)
> return 0;
>
> - if (!need_expand(new_nr_max, old->map_nr_max))
> - return 0;
> -
> new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
> if (!new)
> return -ENOMEM;
> @@ -317,14 +308,11 @@ int alloc_shrinker_info(struct mem_cgroup *memcg)
> static int expand_shrinker_info(int new_id)
> {
> int ret = 0;
> - int new_nr_max = new_id + 1;
> + int new_nr_max = round_up(new_id + 1, BITS_PER_LONG);
> int map_size, defer_size = 0;
> int old_map_size, old_defer_size = 0;
> struct mem_cgroup *memcg;
>
> - if (!need_expand(new_nr_max, shrinker_nr_max))
> - goto out;
> -
> if (!root_mem_cgroup)
> goto out;
>
> @@ -359,9 +347,11 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
>
> rcu_read_lock();
> info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info);
> - /* Pairs with smp mb in shrink_slab() */
> - smp_mb__before_atomic();
> - set_bit(shrinker_id, info->map);
> + if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) {
> + /* Pairs with smp mb in shrink_slab() */
> + smp_mb__before_atomic();
> + set_bit(shrinker_id, info->map);
> + }
> rcu_read_unlock();
> }
> }
>
> (I also added a new check into set_shrinker_bit() for safety).
>
> Kirill
--
Thanks,
Qi
Powered by blists - more mailing lists