Commit 31e0886f authored by Vlastimil Babka's avatar Vlastimil Babka
Browse files

slub: remove CONFIG_SLUB_TINY specific code paths 

CONFIG_SLUB_TINY minimizes the SLUB's memory overhead in multiple ways,
mainly by avoiding percpu caching of slabs and objects. It also reduces
code size by replacing some code paths with simplified ones through
ifdefs, but the benefits of that are smaller and would complicate the
upcoming changes.

Thus remove these code paths and associated ifdefs and simplify the code
base.

Link: https://patch.msgid.link/20251105-sheaves-cleanups-v1-4-b8218e1ac7ef@suse.cz


Reviewed-by: default avatarHarry Yoo <harry.yoo@oracle.com>
Signed-off-by: default avatarVlastimil Babka <vbabka@suse.cz>
parent 1ce20c28

mm/slab.h

+0 −2
Original line number Diff line number Diff line
@@ -236,10 +236,8 @@ struct kmem_cache_order_objects { 
 * Slab cache management.

 */

struct kmem_cache {

#ifndef CONFIG_SLUB_TINY

	struct kmem_cache_cpu __percpu *cpu_slab;

	struct lock_class_key lock_key;

#endif

	struct slub_percpu_sheaves __percpu *cpu_sheaves;

	/* Used for retrieving partial slabs, etc. */

	slab_flags_t flags;

mm/slub.c

+4 −103
Original line number Diff line number Diff line
@@ -410,7 +410,6 @@ enum stat_item { 
	NR_SLUB_STAT_ITEMS

};



#ifndef CONFIG_SLUB_TINY

/*

 * When changing the layout, make sure freelist and tid are still compatible

 * with this_cpu_cmpxchg_double() alignment requirements.
@@ -432,7 +431,6 @@ struct kmem_cache_cpu { 
	unsigned int stat[NR_SLUB_STAT_ITEMS];

#endif

};

#endif /* CONFIG_SLUB_TINY */



static inline void stat(const struct kmem_cache *s, enum stat_item si)

{
@@ -597,12 +595,10 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object) 
	return freelist_ptr_decode(s, p, ptr_addr);

}



#ifndef CONFIG_SLUB_TINY

static void prefetch_freepointer(const struct kmem_cache *s, void *object)

{

	prefetchw(object + s->offset);

}

#endif



/*

 * When running under KMSAN, get_freepointer_safe() may return an uninitialized
@@ -714,10 +710,12 @@ static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s) 
	return s->cpu_partial_slabs;

}

#else

#ifdef SLAB_SUPPORTS_SYSFS

static inline void

slub_set_cpu_partial(struct kmem_cache *s, unsigned int nr_objects)

{

}

#endif



static inline unsigned int slub_get_cpu_partial(struct kmem_cache *s)

{
@@ -2026,13 +2024,11 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, 
							int objects) {}

static inline void dec_slabs_node(struct kmem_cache *s, int node,

							int objects) {}

#ifndef CONFIG_SLUB_TINY

static bool freelist_corrupted(struct kmem_cache *s, struct slab *slab,

			       void **freelist, void *nextfree)

{

	return false;

}

#endif

#endif /* CONFIG_SLUB_DEBUG */



#ifdef CONFIG_SLAB_OBJ_EXT
@@ -3623,8 +3619,6 @@ static struct slab *get_partial(struct kmem_cache *s, int node, 
	return get_any_partial(s, pc);

}



#ifndef CONFIG_SLUB_TINY



#ifdef CONFIG_PREEMPTION

/*

 * Calculate the next globally unique transaction for disambiguation
@@ -4024,12 +4018,6 @@ static bool has_cpu_slab(int cpu, struct kmem_cache *s) 
	return c->slab || slub_percpu_partial(c);

}



#else /* CONFIG_SLUB_TINY */

static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu) { }

static inline bool has_cpu_slab(int cpu, struct kmem_cache *s) { return false; }

static inline void flush_this_cpu_slab(struct kmem_cache *s) { }

#endif /* CONFIG_SLUB_TINY */



static bool has_pcs_used(int cpu, struct kmem_cache *s)

{

	struct slub_percpu_sheaves *pcs;
@@ -4370,7 +4358,6 @@ static inline bool pfmemalloc_match(struct slab *slab, gfp_t gfpflags) 
	return true;

}



#ifndef CONFIG_SLUB_TINY

static inline bool

__update_cpu_freelist_fast(struct kmem_cache *s,

			   void *freelist_old, void *freelist_new,
@@ -4634,7 +4621,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, 
	pc.orig_size = orig_size;

	slab = get_partial(s, node, &pc);

	if (slab) {

		if (kmem_cache_debug(s)) {

		if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {

			freelist = pc.object;

			/*

			 * For debug caches here we had to go through
@@ -4672,7 +4659,7 @@ static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, 


	stat(s, ALLOC_SLAB);



	if (kmem_cache_debug(s)) {

	if (IS_ENABLED(CONFIG_SLUB_TINY) || kmem_cache_debug(s)) {

		freelist = alloc_single_from_new_slab(s, slab, orig_size, gfpflags);



		if (unlikely(!freelist)) {
@@ -4884,32 +4871,6 @@ static __always_inline void *__slab_alloc_node(struct kmem_cache *s, 


	return object;

}

#else /* CONFIG_SLUB_TINY */

static void *__slab_alloc_node(struct kmem_cache *s,

		gfp_t gfpflags, int node, unsigned long addr, size_t orig_size)

{

	struct partial_context pc;

	struct slab *slab;

	void *object;



	pc.flags = gfpflags;

	pc.orig_size = orig_size;

	slab = get_partial(s, node, &pc);



	if (slab)

		return pc.object;



	slab = new_slab(s, gfpflags, node);

	if (unlikely(!slab)) {

		slab_out_of_memory(s, gfpflags, node);

		return NULL;

	}



	object = alloc_single_from_new_slab(s, slab, orig_size, gfpflags);



	return object;

}

#endif /* CONFIG_SLUB_TINY */



/*

 * If the object has been wiped upon free, make sure it's fully initialized by
@@ -5760,9 +5721,7 @@ void *kmalloc_nolock_noprof(size_t size, gfp_t gfp_flags, int node) 
	 * it did local_lock_irqsave(&s->cpu_slab->lock, flags).

	 * In this case fast path with __update_cpu_freelist_fast() is not safe.

	 */

#ifndef CONFIG_SLUB_TINY

	if (!in_nmi() || !local_lock_is_locked(&s->cpu_slab->lock))

#endif

		ret = __slab_alloc_node(s, alloc_gfp, node, _RET_IP_, size);



	if (PTR_ERR(ret) == -EBUSY) {
@@ -6553,14 +6512,10 @@ static void free_deferred_objects(struct irq_work *work) 
	llist_for_each_safe(pos, t, llnode) {

		struct slab *slab = container_of(pos, struct slab, llnode);



#ifdef CONFIG_SLUB_TINY

		free_slab(slab->slab_cache, slab);

#else

		if (slab->frozen)

			deactivate_slab(slab->slab_cache, slab, slab->flush_freelist);

		else

			free_slab(slab->slab_cache, slab);

#endif

	}

}
@@ -6596,7 +6551,6 @@ void defer_free_barrier(void) 
		irq_work_sync(&per_cpu_ptr(&defer_free_objects, cpu)->work);

}



#ifndef CONFIG_SLUB_TINY

/*

 * Fastpath with forced inlining to produce a kfree and kmem_cache_free that

 * can perform fastpath freeing without additional function calls.
@@ -6689,14 +6643,6 @@ static __always_inline void do_slab_free(struct kmem_cache *s, 
	}

	stat_add(s, FREE_FASTPATH, cnt);

}

#else /* CONFIG_SLUB_TINY */

static void do_slab_free(struct kmem_cache *s,

				struct slab *slab, void *head, void *tail,

				int cnt, unsigned long addr)

{

	__slab_free(s, slab, head, tail, cnt, addr);

}

#endif /* CONFIG_SLUB_TINY */



static __fastpath_inline

void slab_free(struct kmem_cache *s, struct slab *slab, void *object,
@@ -6974,11 +6920,7 @@ void kfree_nolock(const void *object) 
	 * since kasan quarantine takes locks and not supported from NMI.

	 */

	kasan_slab_free(s, x, false, false, /* skip quarantine */true);

#ifndef CONFIG_SLUB_TINY

	do_slab_free(s, slab, x, x, 0, _RET_IP_);

#else

	defer_free(s, x);

#endif

}

EXPORT_SYMBOL_GPL(kfree_nolock);
@@ -7428,7 +7370,6 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) 
}

EXPORT_SYMBOL(kmem_cache_free_bulk);



#ifndef CONFIG_SLUB_TINY

static inline

int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,

			    void **p)
@@ -7493,35 +7434,6 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, 
	return 0;



}

#else /* CONFIG_SLUB_TINY */

static int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags,

				   size_t size, void **p)

{

	int i;



	for (i = 0; i < size; i++) {

		void *object = kfence_alloc(s, s->object_size, flags);



		if (unlikely(object)) {

			p[i] = object;

			continue;

		}



		p[i] = __slab_alloc_node(s, flags, NUMA_NO_NODE,

					 _RET_IP_, s->object_size);

		if (unlikely(!p[i]))

			goto error;



		maybe_wipe_obj_freeptr(s, p[i]);

	}



	return i;



error:

	__kmem_cache_free_bulk(s, i, p);

	return 0;

}

#endif /* CONFIG_SLUB_TINY */



/* Note that interrupts must be enabled when calling this function. */

int kmem_cache_alloc_bulk_noprof(struct kmem_cache *s, gfp_t flags, size_t size,
@@ -7740,7 +7652,6 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct node_barn *barn) 
		barn_init(barn);

}



#ifndef CONFIG_SLUB_TINY

static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)

{

	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
@@ -7761,12 +7672,6 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s) 


	return 1;

}

#else

static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)

{

	return 1;

}

#endif /* CONFIG_SLUB_TINY */



static int init_percpu_sheaves(struct kmem_cache *s)

{
@@ -7856,13 +7761,11 @@ void __kmem_cache_release(struct kmem_cache *s) 
	cache_random_seq_destroy(s);

	if (s->cpu_sheaves)

		pcs_destroy(s);

#ifndef CONFIG_SLUB_TINY

#ifdef CONFIG_PREEMPT_RT

	if (s->cpu_slab)

		lockdep_unregister_key(&s->lock_key);

#endif

	free_percpu(s->cpu_slab);

#endif

	free_kmem_cache_nodes(s);

}
@@ -8605,10 +8508,8 @@ void __init kmem_cache_init(void) 


void __init kmem_cache_init_late(void)

{

#ifndef CONFIG_SLUB_TINY

	flushwq = alloc_workqueue("slub_flushwq", WQ_MEM_RECLAIM, 0);

	WARN_ON(!flushwq);

#endif

}



struct kmem_cache *