Re: [PATCH v4 46/48] mm: shrinker: make memcg slab shrink lockless

[Dave Chinner]

On Mon, Aug 07, 2023 at 07:09:34PM +0800, Qi Zheng wrote:
> Like global slab shrink, this commit also uses refcount+RCU method to make
> memcg slab shrink lockless.

This patch does random code cleanups amongst the actual RCU changes.
Can you please move the cleanups to a spearate patch to reduce the
noise in this one?

> diff --git a/mm/shrinker.c b/mm/shrinker.c
> index d318f5621862..fee6f62904fb 100644
> --- a/mm/shrinker.c
> +++ b/mm/shrinker.c
> @@ -107,6 +107,12 @@ static struct shrinker_info *shrinker_info_protected(struct mem_cgroup *memcg,
>  					 lockdep_is_held(&shrinker_rwsem));
>  }
>  
> +static struct shrinker_info *shrinker_info_rcu(struct mem_cgroup *memcg,
> +					       int nid)
> +{
> +	return rcu_dereference(memcg->nodeinfo[nid]->shrinker_info);
> +}

This helper doesn't add value. It doesn't tell me that
rcu_read_lock() needs to be held when it is called, for one....

>  static int expand_one_shrinker_info(struct mem_cgroup *memcg, int new_size,
>  				    int old_size, int new_nr_max)
>  {
> @@ -198,7 +204,7 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
>  		struct shrinker_info_unit *unit;
>  
>  		rcu_read_lock();
> -		info = rcu_dereference(memcg->nodeinfo[nid]->shrinker_info);
> +		info = shrinker_info_rcu(memcg, nid);

... whilst the original code here was obviously correct.

>  		unit = info->unit[shriner_id_to_index(shrinker_id)];
>  		if (!WARN_ON_ONCE(shrinker_id >= info->map_nr_max)) {
>  			/* Pairs with smp mb in shrink_slab() */
> @@ -211,7 +217,7 @@ void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
>  
>  static DEFINE_IDR(shrinker_idr);
>  
> -static int prealloc_memcg_shrinker(struct shrinker *shrinker)
> +static int shrinker_memcg_alloc(struct shrinker *shrinker)

Cleanups in a separate patch.

> @@ -253,10 +258,15 @@ static long xchg_nr_deferred_memcg(int nid, struct shrinker *shrinker,
>  {
>  	struct shrinker_info *info;
>  	struct shrinker_info_unit *unit;
> +	long nr_deferred;
>  
> -	info = shrinker_info_protected(memcg, nid);
> +	rcu_read_lock();
> +	info = shrinker_info_rcu(memcg, nid);
>  	unit = info->unit[shriner_id_to_index(shrinker->id)];
> -	return atomic_long_xchg(&unit->nr_deferred[shriner_id_to_offset(shrinker->id)], 0);
> +	nr_deferred = atomic_long_xchg(&unit->nr_deferred[shriner_id_to_offset(shrinker->id)], 0);
> +	rcu_read_unlock();
> +
> +	return nr_deferred;
>  }

This adds two rcu_read_lock() sections to every call to
do_shrink_slab(). It's not at all clear ifrom any of the other code
that do_shrink_slab() now has internal rcu_read_lock() sections....

> @@ -464,18 +480,23 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
>  	if (!mem_cgroup_online(memcg))
>  		return 0;
>  
> -	if (!down_read_trylock(&shrinker_rwsem))
> -		return 0;
> -
> -	info = shrinker_info_protected(memcg, nid);
> +again:
> +	rcu_read_lock();
> +	info = shrinker_info_rcu(memcg, nid);
>  	if (unlikely(!info))
>  		goto unlock;
>  
> -	for (; index < shriner_id_to_index(info->map_nr_max); index++) {
> +	if (index < shriner_id_to_index(info->map_nr_max)) {
>  		struct shrinker_info_unit *unit;
>  
>  		unit = info->unit[index];
>  
> +		/*
> +		 * The shrinker_info_unit will not be freed, so we can
> +		 * safely release the RCU lock here.
> +		 */
> +		rcu_read_unlock();

Why - what guarantees that the shrinker_info_unit exists at this
point? We hold no reference to it, we hold no reference to any
shrinker, etc. What provides this existence guarantee?

> +
>  		for_each_set_bit(offset, unit->map, SHRINKER_UNIT_BITS) {
>  			struct shrink_control sc = {
>  				.gfp_mask = gfp_mask,
> @@ -485,12 +506,14 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
>  			struct shrinker *shrinker;
>  			int shrinker_id = calc_shrinker_id(index, offset);
>  
> +			rcu_read_lock();
>  			shrinker = idr_find(&shrinker_idr, shrinker_id);
> -			if (unlikely(!shrinker || !(shrinker->flags & SHRINKER_REGISTERED))) {
> -				if (!shrinker)
> -					clear_bit(offset, unit->map);
> +			if (unlikely(!shrinker || !shrinker_try_get(shrinker))) {
> +				clear_bit(offset, unit->map);
> +				rcu_read_unlock();
>  				continue;
>  			}
> +			rcu_read_unlock();
>  
>  			/* Call non-slab shrinkers even though kmem is disabled */
>  			if (!memcg_kmem_online() &&
> @@ -523,15 +546,20 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
>  					set_shrinker_bit(memcg, nid, shrinker_id);
>  			}
>  			freed += ret;
> -
> -			if (rwsem_is_contended(&shrinker_rwsem)) {
> -				freed = freed ? : 1;
> -				goto unlock;
> -			}
> +			shrinker_put(shrinker);

Ok, so why is this safe to call without holding the rcu read lock?
The global shrinker has to hold the rcu_read_lock() whilst calling
shrinker_put() to guarantee the validity of the list next pointer,
but we don't hold off RCU here so what guarantees a racing global
shrinker walk doesn't trip over this shrinker_put() call dropping
the refcount to zero and freeing occuring in a different context...


> +		/*
> +		 * We have already exited the read-side of rcu critical section
> +		 * before calling do_shrink_slab(), the shrinker_info may be
> +		 * released in expand_one_shrinker_info(), so reacquire the
> +		 * shrinker_info.
> +		 */
> +		index++;
> +		goto again;

With that, what makes the use of shrinker_info in
xchg_nr_deferred_memcg() in do_shrink_slab() coherent and valid?

-Dave.
-- 
Dave Chinner
david@xxxxxxxxxxxxx