slab.c

最新最稳定的Linux内存管理模块源代码

	nc = kmalloc_node(memsize, GFP_KERNEL, node);
	if (nc) {
		nc->avail = 0;
		nc->limit = entries;
		nc->batchcount = batchcount;
		nc->touched = 0;
		spin_lock_init(&nc->lock);
	}
	return nc;
}

/*
 * Transfer objects in one arraycache to another.
 * Locking must be handled by the caller.
 *
 * Return the number of entries transferred.
 */
static int transfer_objects(struct array_cache *to,
		struct array_cache *from, unsigned int max)
{
	/* Figure out how many entries to transfer */
	int nr = min(min(from->avail, max), to->limit - to->avail);

	if (!nr)
		return 0;

	memcpy(to->entry + to->avail, from->entry + from->avail -nr,
			sizeof(void *) *nr);

	from->avail -= nr;
	to->avail += nr;
	to->touched = 1;
	return nr;
}

#ifndef CONFIG_NUMA

#define drain_alien_cache(cachep, alien) do { } while (0)
#define reap_alien(cachep, l3) do { } while (0)

static inline struct array_cache **alloc_alien_cache(int node, int limit)
{
	return (struct array_cache **)BAD_ALIEN_MAGIC;
}

static inline void free_alien_cache(struct array_cache **ac_ptr)
{
}

static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
	return 0;
}

static inline void *alternate_node_alloc(struct kmem_cache *cachep,
		gfp_t flags)
{
	return NULL;
}

static inline void *____cache_alloc_node(struct kmem_cache *cachep,
		 gfp_t flags, int nodeid)
{
	return NULL;
}

#else	/* CONFIG_NUMA */

static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
static void *alternate_node_alloc(struct kmem_cache *, gfp_t);

static struct array_cache **alloc_alien_cache(int node, int limit)
{
	struct array_cache **ac_ptr;
	int memsize = sizeof(void *) * nr_node_ids;
	int i;

	if (limit > 1)
		limit = 12;
	ac_ptr = kmalloc_node(memsize, GFP_KERNEL, node);
	if (ac_ptr) {
		for_each_node(i) {
			if (i == node || !node_online(i)) {
				ac_ptr[i] = NULL;
				continue;
			}
			ac_ptr[i] = alloc_arraycache(node, limit, 0xbaadf00d);
			if (!ac_ptr[i]) {
				for (i--; i >= 0; i--)
					kfree(ac_ptr[i]);
				kfree(ac_ptr);
				return NULL;
			}
		}
	}
	return ac_ptr;
}

static void free_alien_cache(struct array_cache **ac_ptr)
{
	int i;

	if (!ac_ptr)
		return;
	for_each_node(i)
	    kfree(ac_ptr[i]);
	kfree(ac_ptr);
}

static void __drain_alien_cache(struct kmem_cache *cachep,
				struct array_cache *ac, int node)
{
	struct kmem_list3 *rl3 = cachep->nodelists[node];

	if (ac->avail) {
		spin_lock(&rl3->list_lock);
		/*
		 * Stuff objects into the remote nodes shared array first.
		 * That way we could avoid the overhead of putting the objects
		 * into the free lists and getting them back later.
		 */
		if (rl3->shared)
			transfer_objects(rl3->shared, ac, ac->limit);

		free_block(cachep, ac->entry, ac->avail, node);
		ac->avail = 0;
		spin_unlock(&rl3->list_lock);
	}
}

/*
 * Called from cache_reap() to regularly drain alien caches round robin.
 */
static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
{
	int node = __get_cpu_var(reap_node);

	if (l3->alien) {
		struct array_cache *ac = l3->alien[node];

		if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
			__drain_alien_cache(cachep, ac, node);
			spin_unlock_irq(&ac->lock);
		}
	}
}

static void drain_alien_cache(struct kmem_cache *cachep,
				struct array_cache **alien)
{
	int i = 0;
	struct array_cache *ac;
	unsigned long flags;

	for_each_online_node(i) {
		ac = alien[i];
		if (ac) {
			spin_lock_irqsave(&ac->lock, flags);
			__drain_alien_cache(cachep, ac, i);
			spin_unlock_irqrestore(&ac->lock, flags);
		}
	}
}

static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
	struct slab *slabp = virt_to_slab(objp);
	int nodeid = slabp->nodeid;
	struct kmem_list3 *l3;
	struct array_cache *alien = NULL;
	int node;

	node = numa_node_id();

	/*
	 * Make sure we are not freeing a object from another node to the array
	 * cache on this cpu.
	 */
	if (likely(slabp->nodeid == node))
		return 0;

	l3 = cachep->nodelists[node];
	STATS_INC_NODEFREES(cachep);
	if (l3->alien && l3->alien[nodeid]) {
		alien = l3->alien[nodeid];
		spin_lock(&alien->lock);
		if (unlikely(alien->avail == alien->limit)) {
			STATS_INC_ACOVERFLOW(cachep);
			__drain_alien_cache(cachep, alien, nodeid);
		}
		alien->entry[alien->avail++] = objp;
		spin_unlock(&alien->lock);
	} else {
		spin_lock(&(cachep->nodelists[nodeid])->list_lock);
		free_block(cachep, &objp, 1, nodeid);
		spin_unlock(&(cachep->nodelists[nodeid])->list_lock);
	}
	return 1;
}
#endif

static void __cpuinit cpuup_canceled(long cpu)
{
	struct kmem_cache *cachep;
	struct kmem_list3 *l3 = NULL;
	int node = cpu_to_node(cpu);
	node_to_cpumask_ptr(mask, node);

	list_for_each_entry(cachep, &cache_chain, next) {
		struct array_cache *nc;
		struct array_cache *shared;
		struct array_cache **alien;

		/* cpu is dead; no one can alloc from it. */
		nc = cachep->array[cpu];
		cachep->array[cpu] = NULL;
		l3 = cachep->nodelists[node];

		if (!l3)
			goto free_array_cache;

		spin_lock_irq(&l3->list_lock);

		/* Free limit for this kmem_list3 */
		l3->free_limit -= cachep->batchcount;
		if (nc)
			free_block(cachep, nc->entry, nc->avail, node);

		if (!cpus_empty(*mask)) {
			spin_unlock_irq(&l3->list_lock);
			goto free_array_cache;
		}

		shared = l3->shared;
		if (shared) {
			free_block(cachep, shared->entry,
				   shared->avail, node);
			l3->shared = NULL;
		}

		alien = l3->alien;
		l3->alien = NULL;

		spin_unlock_irq(&l3->list_lock);

		kfree(shared);
		if (alien) {
			drain_alien_cache(cachep, alien);
			free_alien_cache(alien);
		}
free_array_cache:
		kfree(nc);
	}
	/*
	 * In the previous loop, all the objects were freed to
	 * the respective cache's slabs,  now we can go ahead and
	 * shrink each nodelist to its limit.
	 */
	list_for_each_entry(cachep, &cache_chain, next) {
		l3 = cachep->nodelists[node];
		if (!l3)
			continue;
		drain_freelist(cachep, l3, l3->free_objects);
	}
}

static int __cpuinit cpuup_prepare(long cpu)
{
	struct kmem_cache *cachep;
	struct kmem_list3 *l3 = NULL;
	int node = cpu_to_node(cpu);
	const int memsize = sizeof(struct kmem_list3);

	/*
	 * We need to do this right in the beginning since
	 * alloc_arraycache's are going to use this list.
	 * kmalloc_node allows us to add the slab to the right
	 * kmem_list3 and not this cpu's kmem_list3
	 */

	list_for_each_entry(cachep, &cache_chain, next) {
		/*
		 * Set up the size64 kmemlist for cpu before we can
		 * begin anything. Make sure some other cpu on this
		 * node has not already allocated this
		 */
		if (!cachep->nodelists[node]) {
			l3 = kmalloc_node(memsize, GFP_KERNEL, node);
			if (!l3)
				goto bad;
			kmem_list3_init(l3);
			l3->next_reap = jiffies + REAPTIMEOUT_LIST3 +
			    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;

			/*
			 * The l3s don't come and go as CPUs come and
			 * go.  cache_chain_mutex is sufficient
			 * protection here.
			 */
			cachep->nodelists[node] = l3;
		}

		spin_lock_irq(&cachep->nodelists[node]->list_lock);
		cachep->nodelists[node]->free_limit =
			(1 + nr_cpus_node(node)) *
			cachep->batchcount + cachep->num;
		spin_unlock_irq(&cachep->nodelists[node]->list_lock);
	}

	/*
	 * Now we can go ahead with allocating the shared arrays and
	 * array caches
	 */
	list_for_each_entry(cachep, &cache_chain, next) {
		struct array_cache *nc;
		struct array_cache *shared = NULL;
		struct array_cache **alien = NULL;

		nc = alloc_arraycache(node, cachep->limit,
					cachep->batchcount);
		if (!nc)
			goto bad;
		if (cachep->shared) {
			shared = alloc_arraycache(node,
				cachep->shared * cachep->batchcount,
				0xbaadf00d);
			if (!shared) {
				kfree(nc);
				goto bad;
			}
		}
		if (use_alien_caches) {
			alien = alloc_alien_cache(node, cachep->limit);
			if (!alien) {
				kfree(shared);
				kfree(nc);
				goto bad;
			}
		}
		cachep->array[cpu] = nc;
		l3 = cachep->nodelists[node];
		BUG_ON(!l3);

		spin_lock_irq(&l3->list_lock);
		if (!l3->shared) {
			/*
			 * We are serialised from CPU_DEAD or
			 * CPU_UP_CANCELLED by the cpucontrol lock
			 */
			l3->shared = shared;
			shared = NULL;
		}
#ifdef CONFIG_NUMA
		if (!l3->alien) {
			l3->alien = alien;
			alien = NULL;
		}
#endif
		spin_unlock_irq(&l3->list_lock);
		kfree(shared);
		free_alien_cache(alien);
	}
	return 0;
bad:
	cpuup_canceled(cpu);
	return -ENOMEM;
}

static int __cpuinit cpuup_callback(struct notifier_block *nfb,
				    unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	int err = 0;

	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		mutex_lock(&cache_chain_mutex);
		err = cpuup_prepare(cpu);
		mutex_unlock(&cache_chain_mutex);
		break;
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		start_cpu_timer(cpu);
		break;
#ifdef CONFIG_HOTPLUG_CPU
  	case CPU_DOWN_PREPARE:
  	case CPU_DOWN_PREPARE_FROZEN:
		/*
		 * Shutdown cache reaper. Note that the cache_chain_mutex is
		 * held so that if cache_reap() is invoked it cannot do
		 * anything expensive but will only modify reap_work
		 * and reschedule the timer.
		*/
		cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
		/* Now the cache_reaper is guaranteed to be not running. */
		per_cpu(reap_work, cpu).work.func = NULL;
  		break;
  	case CPU_DOWN_FAILED:
  	case CPU_DOWN_FAILED_FROZEN:
		start_cpu_timer(cpu);
  		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		/*
		 * Even if all the cpus of a node are down, we don't free the
		 * kmem_list3 of any cache. This to avoid a race between
		 * cpu_down, and a kmalloc allocation from another cpu for
		 * memory from the node of the cpu going down.  The list3
		 * structure is usually allocated from kmem_cache_create() and
		 * gets destroyed at kmem_cache_destroy().
		 */
		/* fall through */
#endif
	case CPU_UP_CANCELED:
	case CPU_UP_CANCELED_FROZEN:
		mutex_lock(&cache_chain_mutex);
		cpuup_canceled(cpu);
		mutex_unlock(&cache_chain_mutex);
		break;
	}
	return err ? NOTIFY_BAD : NOTIFY_OK;
}

static struct notifier_block __cpuinitdata cpucache_notifier = {
	&cpuup_callback, NULL, 0
};

/*
 * swap the static kmem_list3 with kmalloced memory
 */
static void init_list(struct kmem_cache *cachep, struct kmem_list3 *list,
			int nodeid)
{
	struct kmem_list3 *ptr;

	ptr = kmalloc_node(sizeof(struct kmem_list3), GFP_KERNEL, nodeid);
	BUG_ON(!ptr);

	local_irq_disable();
	memcpy(ptr, list, sizeof(struct kmem_list3));
	/*
	 * Do not assume that spinlocks can be initialized via memcpy:
	 */
	spin_lock_init(&ptr->list_lock);

	MAKE_ALL_LISTS(cachep, ptr, nodeid);
	cachep->nodelists[nodeid] = ptr;
	local_irq_enable();
}

/*
 * For setting up all the kmem_list3s for cache whose buffer_size is same as
 * size of kmem_list3.
 */
static void __init set_up_list3s(struct kmem_cache *cachep, int index)
{
	int node;

	for_each_online_node(node) {
		cachep->nodelists[node] = &initkmem_list3[index + node];
		cachep->nodelists[node]->next_reap = jiffies +
		    REAPTIMEOUT_LIST3 +
		    ((unsigned long)cachep) % REAPTIMEOUT_LIST3;
	}
}

/*
 * Initialisation.  Called after the page allocator have been initialised and
 * before smp_init().
 */
void __init kmem_cache_init(void)
{
	size_t left_over;
	struct cache_sizes *sizes;
	struct cache_names *names;
	int i;
	int order;