Re: [PATCH RFC v2 08/20] slab: add optimized sheaf refill from partial list

[Vlastimil Babka <vbabka@suse.cz>]

On 1/12/26 16:17, Vlastimil Babka wrote:
> At this point we have sheaves enabled for all caches, but their refill
> is done via __kmem_cache_alloc_bulk() which relies on cpu (partial)
> slabs - now a redundant caching layer that we are about to remove.
> 
> The refill will thus be done from slabs on the node partial list.
> Introduce new functions that can do that in an optimized way as it's
> easier than modifying the __kmem_cache_alloc_bulk() call chain.
> 
> Extend struct partial_context so it can return a list of slabs from the
> partial list with the sum of free objects in them within the requested
> min and max.
> 
> Introduce get_partial_node_bulk() that removes the slabs from freelist
> and returns them in the list.
> 
> Introduce get_freelist_nofreeze() which grabs the freelist without
> freezing the slab.
> 
> Introduce alloc_from_new_slab() which can allocate multiple objects from
> a newly allocated slab where we don't need to synchronize with freeing.
> In some aspects it's similar to alloc_single_from_new_slab() but assumes
> the cache is a non-debug one so it can avoid some actions.
> 
> Introduce __refill_objects() that uses the functions above to fill an
> array of objects. It has to handle the possibility that the slabs will
> contain more objects that were requested, due to concurrent freeing of
> objects to those slabs. When no more slabs on partial lists are
> available, it will allocate new slabs. It is intended to be only used
> in context where spinning is allowed, so add a WARN_ON_ONCE check there.
> 
> Finally, switch refill_sheaf() to use __refill_objects(). Sheaves are
> only refilled from contexts that allow spinning, or even blocking.
> 
> Signed-off-by: Vlastimil Babka <vbabka@suse.cz>

...

> +static unsigned int alloc_from_new_slab(struct kmem_cache *s, struct slab *slab,
> +		void **p, unsigned int count, bool allow_spin)
> +{
> +	unsigned int allocated = 0;
> +	struct kmem_cache_node *n;
> +	unsigned long flags;
> +	void *object;
> +
> +	if (!allow_spin && (slab->objects - slab->inuse) > count) {
> +
> +		n = get_node(s, slab_nid(slab));
> +
> +		if (!spin_trylock_irqsave(&n->list_lock, flags)) {
> +			/* Unlucky, discard newly allocated slab */
> +			defer_deactivate_slab(slab, NULL);

This actually does dec_slabs_node() only with slab->frozen which we don't set.

> +			return 0;
> +		}
> +	}
> +
> +	object = slab->freelist;
> +	while (object && allocated < count) {
> +		p[allocated] = object;
> +		object = get_freepointer(s, object);
> +		maybe_wipe_obj_freeptr(s, p[allocated]);
> +
> +		slab->inuse++;
> +		allocated++;
> +	}
> +	slab->freelist = object;
> +
> +	if (slab->freelist) {
> +
> +		if (allow_spin) {
> +			n = get_node(s, slab_nid(slab));
> +			spin_lock_irqsave(&n->list_lock, flags);
> +		}
> +		add_partial(n, slab, DEACTIVATE_TO_HEAD);
> +		spin_unlock_irqrestore(&n->list_lock, flags);
> +	}

So we should only do inc_slabs_node() here.
This also addresses the problem in 9/20 that Hao Li pointed out...

> +	return allocated;
> +}
> +

...

> +static unsigned int
> +__refill_objects(struct kmem_cache *s, void **p, gfp_t gfp, unsigned int min,
> +		 unsigned int max)
> +{
> +	struct slab *slab, *slab2;
> +	struct partial_context pc;
> +	unsigned int refilled = 0;
> +	unsigned long flags;
> +	void *object;
> +	int node;
> +
> +	pc.flags = gfp;
> +	pc.min_objects = min;
> +	pc.max_objects = max;
> +
> +	node = numa_mem_id();
> +
> +	if (WARN_ON_ONCE(!gfpflags_allow_spinning(gfp)))
> +		return 0;
> +
> +	/* TODO: consider also other nodes? */
> +	if (!get_partial_node_bulk(s, get_node(s, node), &pc))
> +		goto new_slab;
> +
> +	list_for_each_entry_safe(slab, slab2, &pc.slabs, slab_list) {
> +
> +		list_del(&slab->slab_list);
> +
> +		object = get_freelist_nofreeze(s, slab);
> +
> +		while (object && refilled < max) {
> +			p[refilled] = object;
> +			object = get_freepointer(s, object);
> +			maybe_wipe_obj_freeptr(s, p[refilled]);
> +
> +			refilled++;
> +		}
> +
> +		/*
> +		 * Freelist had more objects than we can accomodate, we need to
> +		 * free them back. We can treat it like a detached freelist, just
> +		 * need to find the tail object.
> +		 */
> +		if (unlikely(object)) {
> +			void *head = object;
> +			void *tail;
> +			int cnt = 0;
> +
> +			do {
> +				tail = object;
> +				cnt++;
> +				object = get_freepointer(s, object);
> +			} while (object);
> +			do_slab_free(s, slab, head, tail, cnt, _RET_IP_);
> +		}
> +
> +		if (refilled >= max)
> +			break;
> +	}
> +
> +	if (unlikely(!list_empty(&pc.slabs))) {
> +		struct kmem_cache_node *n = get_node(s, node);
> +
> +		spin_lock_irqsave(&n->list_lock, flags);
> +
> +		list_for_each_entry_safe(slab, slab2, &pc.slabs, slab_list) {
> +
> +			if (unlikely(!slab->inuse && n->nr_partial >= s->min_partial))
> +				continue;
> +
> +			list_del(&slab->slab_list);
> +			add_partial(n, slab, DEACTIVATE_TO_HEAD);
> +		}
> +
> +		spin_unlock_irqrestore(&n->list_lock, flags);
> +
> +		/* any slabs left are completely free and for discard */
> +		list_for_each_entry_safe(slab, slab2, &pc.slabs, slab_list) {
> +
> +			list_del(&slab->slab_list);
> +			discard_slab(s, slab);
> +		}
> +	}
> +
> +
> +	if (likely(refilled >= min))
> +		goto out;
> +
> +new_slab:
> +
> +	slab = new_slab(s, pc.flags, node);
> +	if (!slab)
> +		goto out;
> +
> +	stat(s, ALLOC_SLAB);
> +	inc_slabs_node(s, slab_nid(slab), slab->objects);

And remove it from here.

> +
> +	/*
> +	 * TODO: possible optimization - if we know we will consume the whole
> +	 * slab we might skip creating the freelist?
> +	 */
> +	refilled += alloc_from_new_slab(s, slab, p + refilled, max - refilled,
> +					/* allow_spin = */ true);
> +
> +	if (refilled < min)
> +		goto new_slab;
> +out:
> +
> +	return refilled;
> +}
> +
>  static inline
>  int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
>  			    void **p)
>