Re: [PATCH v4 1/8] mm: vmscan: add a map_nr_max field to shrinker_info

[Qi Zheng <zhengqi.arch@bytedance.com>]

On 2023/3/9 06:13, Kirill Tkhai wrote:
> Hi,
> 
> On 07.03.2023 09:55, 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.
>>
>> Suggested-by: Kirill Tkhai <tkhai@ya.ru>
>> Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
>> ---
>>   include/linux/memcontrol.h |  1 +
>>   mm/vmscan.c                | 41 ++++++++++++++++++++++----------------
>>   2 files changed, 25 insertions(+), 17 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 9414226218f0..2dcc01682026 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 +247,17 @@ static int expand_one_shrinker_info(struct mem_cgroup *memcg,
>>   		if (!old)
>>   			return 0;
>>   
>> +		/* Already expanded this shrinker_info */
>> +		if (!need_expand(new_nr_max, old->map_nr_max))
> 
> need_expand() looks confusing here. It's strange that we round_up(old->map_nr_max),
> despite old->map never may exceed old->map_nr_max.
> 
> Won't plain
> 
> 	if (new_nr_max <= old->map_nr_max)
> 
> look clearer here?

Yeah, will change to it.

> 
> The rest in patch looks OK for me.
> 
>> +			continue;
>> +
>>   		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 +307,7 @@ 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);
>> @@ -302,23 +315,14 @@ 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;
>> -	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))
>> -		goto out;
>> -
>>   	if (!root_mem_cgroup)
>>   		goto out;
>>   
>> @@ -332,7 +336,8 @@ 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;
>> @@ -352,9 +357,11 @@ 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();
>>   	}
>>   }
>> @@ -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,
> 

-- 
Thanks,
Qi