slab.c

最新最稳定的Linux内存管理模块源代码

	int node;

	if (num_possible_nodes() == 1) {
		use_alien_caches = 0;
		numa_platform = 0;
	}

	for (i = 0; i < NUM_INIT_LISTS; i++) {
		kmem_list3_init(&initkmem_list3[i]);
		if (i < MAX_NUMNODES)
			cache_cache.nodelists[i] = NULL;
	}
	set_up_list3s(&cache_cache, CACHE_CACHE);

	/*
	 * Fragmentation resistance on low memory - only use bigger
	 * page orders on machines with more than 32MB of memory.
	 */
	if (num_physpages > (32 << 20) >> PAGE_SHIFT)
		slab_break_gfp_order = BREAK_GFP_ORDER_HI;

	/* Bootstrap is tricky, because several objects are allocated
	 * from caches that do not exist yet:
	 * 1) initialize the cache_cache cache: it contains the struct
	 *    kmem_cache structures of all caches, except cache_cache itself:
	 *    cache_cache is statically allocated.
	 *    Initially an __init data area is used for the head array and the
	 *    kmem_list3 structures, it's replaced with a kmalloc allocated
	 *    array at the end of the bootstrap.
	 * 2) Create the first kmalloc cache.
	 *    The struct kmem_cache for the new cache is allocated normally.
	 *    An __init data area is used for the head array.
	 * 3) Create the remaining kmalloc caches, with minimally sized
	 *    head arrays.
	 * 4) Replace the __init data head arrays for cache_cache and the first
	 *    kmalloc cache with kmalloc allocated arrays.
	 * 5) Replace the __init data for kmem_list3 for cache_cache and
	 *    the other cache's with kmalloc allocated memory.
	 * 6) Resize the head arrays of the kmalloc caches to their final sizes.
	 */

	node = numa_node_id();

	/* 1) create the cache_cache */
	INIT_LIST_HEAD(&cache_chain);
	list_add(&cache_cache.next, &cache_chain);
	cache_cache.colour_off = cache_line_size();
	cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
	cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];

	/*
	 * struct kmem_cache size depends on nr_node_ids, which
	 * can be less than MAX_NUMNODES.
	 */
	cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) +
				 nr_node_ids * sizeof(struct kmem_list3 *);
#if DEBUG
	cache_cache.obj_size = cache_cache.buffer_size;
#endif
	cache_cache.buffer_size = ALIGN(cache_cache.buffer_size,
					cache_line_size());
	cache_cache.reciprocal_buffer_size =
		reciprocal_value(cache_cache.buffer_size);

	for (order = 0; order < MAX_ORDER; order++) {
		cache_estimate(order, cache_cache.buffer_size,
			cache_line_size(), 0, &left_over, &cache_cache.num);
		if (cache_cache.num)
			break;
	}
	BUG_ON(!cache_cache.num);
	cache_cache.gfporder = order;
	cache_cache.colour = left_over / cache_cache.colour_off;
	cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
				      sizeof(struct slab), cache_line_size());

	/* 2+3) create the kmalloc caches */
	sizes = malloc_sizes;
	names = cache_names;

	/*
	 * Initialize the caches that provide memory for the array cache and the
	 * kmem_list3 structures first.  Without this, further allocations will
	 * bug.
	 */

	sizes[INDEX_AC].cs_cachep = kmem_cache_create(names[INDEX_AC].name,
					sizes[INDEX_AC].cs_size,
					ARCH_KMALLOC_MINALIGN,
					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
					NULL);

	if (INDEX_AC != INDEX_L3) {
		sizes[INDEX_L3].cs_cachep =
			kmem_cache_create(names[INDEX_L3].name,
				sizes[INDEX_L3].cs_size,
				ARCH_KMALLOC_MINALIGN,
				ARCH_KMALLOC_FLAGS|SLAB_PANIC,
				NULL);
	}

	slab_early_init = 0;

	while (sizes->cs_size != ULONG_MAX) {
		/*
		 * For performance, all the general caches are L1 aligned.
		 * This should be particularly beneficial on SMP boxes, as it
		 * eliminates "false sharing".
		 * Note for systems short on memory removing the alignment will
		 * allow tighter packing of the smaller caches.
		 */
		if (!sizes->cs_cachep) {
			sizes->cs_cachep = kmem_cache_create(names->name,
					sizes->cs_size,
					ARCH_KMALLOC_MINALIGN,
					ARCH_KMALLOC_FLAGS|SLAB_PANIC,
					NULL);
		}
#ifdef CONFIG_ZONE_DMA
		sizes->cs_dmacachep = kmem_cache_create(
					names->name_dma,
					sizes->cs_size,
					ARCH_KMALLOC_MINALIGN,
					ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA|
						SLAB_PANIC,
					NULL);
#endif
		sizes++;
		names++;
	}
	/* 4) Replace the bootstrap head arrays */
	{
		struct array_cache *ptr;

		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);

		local_irq_disable();
		BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache);
		memcpy(ptr, cpu_cache_get(&cache_cache),
		       sizeof(struct arraycache_init));
		/*
		 * Do not assume that spinlocks can be initialized via memcpy:
		 */
		spin_lock_init(&ptr->lock);

		cache_cache.array[smp_processor_id()] = ptr;
		local_irq_enable();

		ptr = kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);

		local_irq_disable();
		BUG_ON(cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep)
		       != &initarray_generic.cache);
		memcpy(ptr, cpu_cache_get(malloc_sizes[INDEX_AC].cs_cachep),
		       sizeof(struct arraycache_init));
		/*
		 * Do not assume that spinlocks can be initialized via memcpy:
		 */
		spin_lock_init(&ptr->lock);

		malloc_sizes[INDEX_AC].cs_cachep->array[smp_processor_id()] =
		    ptr;
		local_irq_enable();
	}
	/* 5) Replace the bootstrap kmem_list3's */
	{
		int nid;

		for_each_online_node(nid) {
			init_list(&cache_cache, &initkmem_list3[CACHE_CACHE + nid], nid);

			init_list(malloc_sizes[INDEX_AC].cs_cachep,
				  &initkmem_list3[SIZE_AC + nid], nid);

			if (INDEX_AC != INDEX_L3) {
				init_list(malloc_sizes[INDEX_L3].cs_cachep,
					  &initkmem_list3[SIZE_L3 + nid], nid);
			}
		}
	}

	/* 6) resize the head arrays to their final sizes */
	{
		struct kmem_cache *cachep;
		mutex_lock(&cache_chain_mutex);
		list_for_each_entry(cachep, &cache_chain, next)
			if (enable_cpucache(cachep))
				BUG();
		mutex_unlock(&cache_chain_mutex);
	}

	/* Annotate slab for lockdep -- annotate the malloc caches */
	init_lock_keys();


	/* Done! */
	g_cpucache_up = FULL;

	/*
	 * Register a cpu startup notifier callback that initializes
	 * cpu_cache_get for all new cpus
	 */
	register_cpu_notifier(&cpucache_notifier);

	/*
	 * The reap timers are started later, with a module init call: That part
	 * of the kernel is not yet operational.
	 */
}

static int __init cpucache_init(void)
{
	int cpu;

	/*
	 * Register the timers that return unneeded pages to the page allocator
	 */
	for_each_online_cpu(cpu)
		start_cpu_timer(cpu);
	return 0;
}
__initcall(cpucache_init);

/*
 * Interface to system's page allocator. No need to hold the cache-lock.
 *
 * If we requested dmaable memory, we will get it. Even if we
 * did not request dmaable memory, we might get it, but that
 * would be relatively rare and ignorable.
 */
static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
	struct page *page;
	int nr_pages;
	int i;

#ifndef CONFIG_MMU
	/*
	 * Nommu uses slab's for process anonymous memory allocations, and thus
	 * requires __GFP_COMP to properly refcount higher order allocations
	 */
	flags |= __GFP_COMP;
#endif

	flags |= cachep->gfpflags;
	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
		flags |= __GFP_RECLAIMABLE;

	page = alloc_pages_node(nodeid, flags, cachep->gfporder);
	if (!page)
		return NULL;

	nr_pages = (1 << cachep->gfporder);
	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
		add_zone_page_state(page_zone(page),
			NR_SLAB_RECLAIMABLE, nr_pages);
	else
		add_zone_page_state(page_zone(page),
			NR_SLAB_UNRECLAIMABLE, nr_pages);
	for (i = 0; i < nr_pages; i++)
		__SetPageSlab(page + i);
	return page_address(page);
}

/*
 * Interface to system's page release.
 */
static void kmem_freepages(struct kmem_cache *cachep, void *addr)
{
	unsigned long i = (1 << cachep->gfporder);
	struct page *page = virt_to_page(addr);
	const unsigned long nr_freed = i;

	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
		sub_zone_page_state(page_zone(page),
				NR_SLAB_RECLAIMABLE, nr_freed);
	else
		sub_zone_page_state(page_zone(page),
				NR_SLAB_UNRECLAIMABLE, nr_freed);
	while (i--) {
		BUG_ON(!PageSlab(page));
		__ClearPageSlab(page);
		page++;
	}
	if (current->reclaim_state)
		current->reclaim_state->reclaimed_slab += nr_freed;
	free_pages((unsigned long)addr, cachep->gfporder);
}

static void kmem_rcu_free(struct rcu_head *head)
{
	struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
	struct kmem_cache *cachep = slab_rcu->cachep;

	kmem_freepages(cachep, slab_rcu->addr);
	if (OFF_SLAB(cachep))
		kmem_cache_free(cachep->slabp_cache, slab_rcu);
}

#if DEBUG

#ifdef CONFIG_DEBUG_PAGEALLOC
static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
			    unsigned long caller)
{
	int size = obj_size(cachep);

	addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];

	if (size < 5 * sizeof(unsigned long))
		return;

	*addr++ = 0x12345678;
	*addr++ = caller;
	*addr++ = smp_processor_id();
	size -= 3 * sizeof(unsigned long);
	{
		unsigned long *sptr = &caller;
		unsigned long svalue;

		while (!kstack_end(sptr)) {
			svalue = *sptr++;
			if (kernel_text_address(svalue)) {
				*addr++ = svalue;
				size -= sizeof(unsigned long);
				if (size <= sizeof(unsigned long))
					break;
			}
		}

	}
	*addr++ = 0x87654321;
}
#endif

static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
{
	int size = obj_size(cachep);
	addr = &((char *)addr)[obj_offset(cachep)];

	memset(addr, val, size);
	*(unsigned char *)(addr + size - 1) = POISON_END;
}

static void dump_line(char *data, int offset, int limit)
{
	int i;
	unsigned char error = 0;
	int bad_count = 0;

	printk(KERN_ERR "%03x:", offset);
	for (i = 0; i < limit; i++) {
		if (data[offset + i] != POISON_FREE) {
			error = data[offset + i];
			bad_count++;
		}
		printk(" %02x", (unsigned char)data[offset + i]);
	}
	printk("\n");

	if (bad_count == 1) {
		error ^= POISON_FREE;
		if (!(error & (error - 1))) {
			printk(KERN_ERR "Single bit error detected. Probably "
					"bad RAM.\n");
#ifdef CONFIG_X86
			printk(KERN_ERR "Run memtest86+ or a similar memory "
					"test tool.\n");
#else
			printk(KERN_ERR "Run a memory test tool.\n");
#endif
		}
	}
}
#endif

#if DEBUG

static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
{
	int i, size;
	char *realobj;

	if (cachep->flags & SLAB_RED_ZONE) {
		printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n",
			*dbg_redzone1(cachep, objp),
			*dbg_redzone2(cachep, objp));
	}

	if (cachep->flags & SLAB_STORE_USER) {
		printk(KERN_ERR "Last user: [<%p>]",
			*dbg_userword(cachep, objp));
		print_symbol("(%s)",
				(unsigned long)*dbg_userword(cachep, objp));
		printk("\n");
	}
	realobj = (char *)objp + obj_offset(cachep);
	size = obj_size(cachep);
	for (i = 0; i < size && lines; i += 16, lines--) {
		int limit;
		limit = 16;
		if (i + limit > size)
			limit = size - i;
		dump_line(realobj, i, limit);
	}
}

static void check_poison_obj(struct kmem_cache *cachep, void *objp)
{
	char *realobj;
	int size, i;
	int lines = 0;

	realobj = (char *)objp + obj_offset(cachep);
	size = obj_size(cachep);

	for (i = 0; i < size; i++) {
		char exp = POISON_FREE;
		if (i == size - 1)
			exp = POISON_END;
		if (realobj[i] != exp) {
			int limit;
			/* Mismatch ! */
			/* Print header */
			if (lines == 0) {
				printk(KERN_ERR
					"Slab corruption: %s start=%p, len=%d\n",
					cachep->name, realobj, size);
				print_objinfo(cachep, objp, 0);
			}
			/* Hexdump the affected line */
			i = (i / 16) * 16;
			limit = 16;
			if (i + limit > size)
				limit = size - i;
			dump_line(realobj, i, limit);
			i += 16;
			lines++;
			/* Limit to 5 lines */
			if (lines > 5)
				break;
		}
	}
	if (lines != 0) {
		/* Print some data about the neighboring objects, if they
		 * exist:
		 */
		struct slab *slabp = virt_to_slab(objp);
		unsigned int objnr;

		objnr = obj_to_index(cachep, slabp, objp);
		if (objnr) {
			objp = index_to_obj(cachep, slabp, objnr - 1);
			realobj = (char *)objp + obj_offset(cachep);
			printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
			       realobj, size);
			print_objinfo(cachep, objp, 2);
		}
		if (objnr + 1 < cachep->num) {
			objp = index_to_obj(cachep, slabp, objnr + 1);
			realobj = (char *)objp + obj_offset(cachep);
			printk(KERN_ERR "Next obj: start=%p, len=%d\n",
			       realobj, size);
			print_objinfo(cachep, objp, 2);
		}
	}
}
#endif

#if DEBUG
static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
{
	int i;
	for (i = 0; i < cachep->num; i++) {
		void *objp = index_to_obj(cachep, slabp, i);

		if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC