slub.c

最新最稳定的Linux内存管理模块源代码

	void (*ctor)(void *))
{
	return flags;
}
#define slub_debug 0

static inline unsigned long slabs_node(struct kmem_cache *s, int node)
							{ return 0; }
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) {}
#endif

/*
 * Slab allocation and freeing
 */
static inline struct page *alloc_slab_page(gfp_t flags, int node,
					struct kmem_cache_order_objects oo)
{
	int order = oo_order(oo);

	if (node == -1)
		return alloc_pages(flags, order);
	else
		return alloc_pages_node(node, flags, order);
}

static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
	struct page *page;
	struct kmem_cache_order_objects oo = s->oo;

	flags |= s->allocflags;

	page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node,
									oo);
	if (unlikely(!page)) {
		oo = s->min;
		/*
		 * Allocation may have failed due to fragmentation.
		 * Try a lower order alloc if possible
		 */
		page = alloc_slab_page(flags, node, oo);
		if (!page)
			return NULL;

		stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
	}
	page->objects = oo_objects(oo);
	mod_zone_page_state(page_zone(page),
		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
		1 << oo_order(oo));

	return page;
}

static void setup_object(struct kmem_cache *s, struct page *page,
				void *object)
{
	setup_object_debug(s, page, object);
	if (unlikely(s->ctor))
		s->ctor(object);
}

static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
{
	struct page *page;
	void *start;
	void *last;
	void *p;

	BUG_ON(flags & GFP_SLAB_BUG_MASK);

	page = allocate_slab(s,
		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
	if (!page)
		goto out;

	inc_slabs_node(s, page_to_nid(page), page->objects);
	page->slab = s;
	page->flags |= 1 << PG_slab;
	if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
			SLAB_STORE_USER | SLAB_TRACE))
		__SetPageSlubDebug(page);

	start = page_address(page);

	if (unlikely(s->flags & SLAB_POISON))
		memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));

	last = start;
	for_each_object(p, s, start, page->objects) {
		setup_object(s, page, last);
		set_freepointer(s, last, p);
		last = p;
	}
	setup_object(s, page, last);
	set_freepointer(s, last, NULL);

	page->freelist = start;
	page->inuse = 0;
out:
	return page;
}

static void __free_slab(struct kmem_cache *s, struct page *page)
{
	int order = compound_order(page);
	int pages = 1 << order;

	if (unlikely(SLABDEBUG && PageSlubDebug(page))) {
		void *p;

		slab_pad_check(s, page);
		for_each_object(p, s, page_address(page),
						page->objects)
			check_object(s, page, p, 0);
		__ClearPageSlubDebug(page);
	}

	mod_zone_page_state(page_zone(page),
		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
		-pages);

	__ClearPageSlab(page);
	reset_page_mapcount(page);
	__free_pages(page, order);
}

static void rcu_free_slab(struct rcu_head *h)
{
	struct page *page;

	page = container_of((struct list_head *)h, struct page, lru);
	__free_slab(page->slab, page);
}

static void free_slab(struct kmem_cache *s, struct page *page)
{
	if (unlikely(s->flags & SLAB_DESTROY_BY_RCU)) {
		/*
		 * RCU free overloads the RCU head over the LRU
		 */
		struct rcu_head *head = (void *)&page->lru;

		call_rcu(head, rcu_free_slab);
	} else
		__free_slab(s, page);
}

static void discard_slab(struct kmem_cache *s, struct page *page)
{
	dec_slabs_node(s, page_to_nid(page), page->objects);
	free_slab(s, page);
}

/*
 * Per slab locking using the pagelock
 */
static __always_inline void slab_lock(struct page *page)
{
	bit_spin_lock(PG_locked, &page->flags);
}

static __always_inline void slab_unlock(struct page *page)
{
	__bit_spin_unlock(PG_locked, &page->flags);
}

static __always_inline int slab_trylock(struct page *page)
{
	int rc = 1;

	rc = bit_spin_trylock(PG_locked, &page->flags);
	return rc;
}

/*
 * Management of partially allocated slabs
 */
static void add_partial(struct kmem_cache_node *n,
				struct page *page, int tail)
{
	spin_lock(&n->list_lock);
	n->nr_partial++;
	if (tail)
		list_add_tail(&page->lru, &n->partial);
	else
		list_add(&page->lru, &n->partial);
	spin_unlock(&n->list_lock);
}

static void remove_partial(struct kmem_cache *s, struct page *page)
{
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));

	spin_lock(&n->list_lock);
	list_del(&page->lru);
	n->nr_partial--;
	spin_unlock(&n->list_lock);
}

/*
 * Lock slab and remove from the partial list.
 *
 * Must hold list_lock.
 */
static inline int lock_and_freeze_slab(struct kmem_cache_node *n,
							struct page *page)
{
	if (slab_trylock(page)) {
		list_del(&page->lru);
		n->nr_partial--;
		__SetPageSlubFrozen(page);
		return 1;
	}
	return 0;
}

/*
 * Try to allocate a partial slab from a specific node.
 */
static struct page *get_partial_node(struct kmem_cache_node *n)
{
	struct page *page;

	/*
	 * Racy check. If we mistakenly see no partial slabs then we
	 * just allocate an empty slab. If we mistakenly try to get a
	 * partial slab and there is none available then get_partials()
	 * will return NULL.
	 */
	if (!n || !n->nr_partial)
		return NULL;

	spin_lock(&n->list_lock);
	list_for_each_entry(page, &n->partial, lru)
		if (lock_and_freeze_slab(n, page))
			goto out;
	page = NULL;
out:
	spin_unlock(&n->list_lock);
	return page;
}

/*
 * Get a page from somewhere. Search in increasing NUMA distances.
 */
static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
{
#ifdef CONFIG_NUMA
	struct zonelist *zonelist;
	struct zoneref *z;
	struct zone *zone;
	enum zone_type high_zoneidx = gfp_zone(flags);
	struct page *page;

	/*
	 * The defrag ratio allows a configuration of the tradeoffs between
	 * inter node defragmentation and node local allocations. A lower
	 * defrag_ratio increases the tendency to do local allocations
	 * instead of attempting to obtain partial slabs from other nodes.
	 *
	 * If the defrag_ratio is set to 0 then kmalloc() always
	 * returns node local objects. If the ratio is higher then kmalloc()
	 * may return off node objects because partial slabs are obtained
	 * from other nodes and filled up.
	 *
	 * If /sys/kernel/slab/xx/defrag_ratio is set to 100 (which makes
	 * defrag_ratio = 1000) then every (well almost) allocation will
	 * first attempt to defrag slab caches on other nodes. This means
	 * scanning over all nodes to look for partial slabs which may be
	 * expensive if we do it every time we are trying to find a slab
	 * with available objects.
	 */
	if (!s->remote_node_defrag_ratio ||
			get_cycles() % 1024 > s->remote_node_defrag_ratio)
		return NULL;

	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
		struct kmem_cache_node *n;

		n = get_node(s, zone_to_nid(zone));

		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
				n->nr_partial > n->min_partial) {
			page = get_partial_node(n);
			if (page)
				return page;
		}
	}
#endif
	return NULL;
}

/*
 * Get a partial page, lock it and return it.
 */
static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
{
	struct page *page;
	int searchnode = (node == -1) ? numa_node_id() : node;

	page = get_partial_node(get_node(s, searchnode));
	if (page || (flags & __GFP_THISNODE))
		return page;

	return get_any_partial(s, flags);
}

/*
 * Move a page back to the lists.
 *
 * Must be called with the slab lock held.
 *
 * On exit the slab lock will have been dropped.
 */
static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
{
	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
	struct kmem_cache_cpu *c = get_cpu_slab(s, smp_processor_id());

	__ClearPageSlubFrozen(page);
	if (page->inuse) {

		if (page->freelist) {
			add_partial(n, page, tail);
			stat(c, tail ? DEACTIVATE_TO_TAIL : DEACTIVATE_TO_HEAD);
		} else {
			stat(c, DEACTIVATE_FULL);
			if (SLABDEBUG && PageSlubDebug(page) &&
						(s->flags & SLAB_STORE_USER))
				add_full(n, page);
		}
		slab_unlock(page);
	} else {
		stat(c, DEACTIVATE_EMPTY);
		if (n->nr_partial < n->min_partial) {
			/*
			 * Adding an empty slab to the partial slabs in order
			 * to avoid page allocator overhead. This slab needs
			 * to come after the other slabs with objects in
			 * so that the others get filled first. That way the
			 * size of the partial list stays small.
			 *
			 * kmem_cache_shrink can reclaim any empty slabs from
			 * the partial list.
			 */
			add_partial(n, page, 1);
			slab_unlock(page);
		} else {
			slab_unlock(page);
			stat(get_cpu_slab(s, raw_smp_processor_id()), FREE_SLAB);
			discard_slab(s, page);
		}
	}
}

/*
 * Remove the cpu slab
 */
static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
	struct page *page = c->page;
	int tail = 1;

	if (page->freelist)
		stat(c, DEACTIVATE_REMOTE_FREES);
	/*
	 * Merge cpu freelist into slab freelist. Typically we get here
	 * because both freelists are empty. So this is unlikely
	 * to occur.
	 */
	while (unlikely(c->freelist)) {
		void **object;

		tail = 0;	/* Hot objects. Put the slab first */

		/* Retrieve object from cpu_freelist */
		object = c->freelist;
		c->freelist = c->freelist[c->offset];

		/* And put onto the regular freelist */
		object[c->offset] = page->freelist;
		page->freelist = object;
		page->inuse--;
	}
	c->page = NULL;
	unfreeze_slab(s, page, tail);
}

static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
{
	stat(c, CPUSLAB_FLUSH);
	slab_lock(c->page);
	deactivate_slab(s, c);
}

/*
 * Flush cpu slab.
 *
 * Called from IPI handler with interrupts disabled.
 */
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
{
	struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);

	if (likely(c && c->page))
		flush_slab(s, c);
}

static void flush_cpu_slab(void *d)
{
	struct kmem_cache *s = d;

	__flush_cpu_slab(s, smp_processor_id());
}

static void flush_all(struct kmem_cache *s)
{
	on_each_cpu(flush_cpu_slab, s, 1);
}

/*
 * Check if the objects in a per cpu structure fit numa
 * locality expectations.
 */
static inline int node_match(struct kmem_cache_cpu *c, int node)
{
#ifdef CONFIG_NUMA
	if (node != -1 && c->node != node)
		return 0;
#endif
	return 1;
}

/*
 * Slow path. The lockless freelist is empty or we need to perform
 * debugging duties.
 *
 * Interrupts are disabled.
 *
 * Processing is still very fast if new objects have been freed to the
 * regular freelist. In that case we simply take over the regular freelist
 * as the lockless freelist and zap the regular freelist.
 *
 * If that is not working then we fall back to the partial lists. We take the
 * first element of the freelist as the object to allocate now and move the
 * rest of the freelist to the lockless freelist.
 *
 * And if we were unable to get a new slab from the partial slab lists then
 * we need to allocate a new slab. This is the slowest path since it involves
 * a call to the page allocator and the setup of a new slab.
 */
static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
			  unsigned long addr, struct kmem_cache_cpu *c)
{
	void **object;
	struct page *new;

	/* We handle __GFP_ZERO in the caller */
	gfpflags &= ~__GFP_ZERO;

	if (!c->page)
		goto new_slab;

	slab_lock(c->page);
	if (unlikely(!node_match(c, node)))
		goto another_slab;

	stat(c, ALLOC_REFILL);

load_freelist:
	object = c->page->freelist;
	if (unlikely(!object))
		goto another_slab;
	if (unlikely(SLABDEBUG && PageSlubDebug(c->page)))
		goto debug;

	c->freelist = object[c->offset];
	c->page->inuse = c->page->objects;
	c->page->freelist = NULL;
	c->node = page_to_nid(c->page);
unlock_out:
	slab_unlock(c->page);
	stat(c, ALLOC_SLOWPATH);
	return object;

another_slab:
	deactivate_slab(s, c);

new_slab:
	new = get_partial(s, gfpflags, node);
	if (new) {
		c->page = new;
		stat(c, ALLOC_FROM_PARTIAL);
		goto load_freelist;
	}

	if (gfpflags & __GFP_WAIT)
		local_irq_enable();

	new = new_slab(s, gfpflags, node);

	if (gfpflags & __GFP_WAIT)
		local_irq_disable();

	if (new) {
		c = get_cpu_slab(s, smp_processor_id());
		stat(c, ALLOC_SLAB);
		if (c->page)
			flush_slab(s, c);
		slab_lock(new);
		__SetPageSlubFrozen(new);
		c->page = new;
		goto load_freelist;
	}
	return NULL;
debug:
	if (!alloc_debug_processing(s, c->page, object, addr))