slab.c

最新最稳定的Linux内存管理模块源代码

			if (cachep->buffer_size % PAGE_SIZE == 0 &&
					OFF_SLAB(cachep))
				kernel_map_pages(virt_to_page(objp),
					cachep->buffer_size / PAGE_SIZE, 1);
			else
				check_poison_obj(cachep, objp);
#else
			check_poison_obj(cachep, objp);
#endif
		}
		if (cachep->flags & SLAB_RED_ZONE) {
			if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "start of a freed object "
					   "was overwritten");
			if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
				slab_error(cachep, "end of a freed object "
					   "was overwritten");
		}
	}
}
#else
static void slab_destroy_debugcheck(struct kmem_cache *cachep, struct slab *slabp)
{
}
#endif

/**
 * slab_destroy - destroy and release all objects in a slab
 * @cachep: cache pointer being destroyed
 * @slabp: slab pointer being destroyed
 *
 * Destroy all the objs in a slab, and release the mem back to the system.
 * Before calling the slab must have been unlinked from the cache.  The
 * cache-lock is not held/needed.
 */
static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
{
	void *addr = slabp->s_mem - slabp->colouroff;

	slab_destroy_debugcheck(cachep, slabp);
	if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
		struct slab_rcu *slab_rcu;

		slab_rcu = (struct slab_rcu *)slabp;
		slab_rcu->cachep = cachep;
		slab_rcu->addr = addr;
		call_rcu(&slab_rcu->head, kmem_rcu_free);
	} else {
		kmem_freepages(cachep, addr);
		if (OFF_SLAB(cachep))
			kmem_cache_free(cachep->slabp_cache, slabp);
	}
}

static void __kmem_cache_destroy(struct kmem_cache *cachep)
{
	int i;
	struct kmem_list3 *l3;

	for_each_online_cpu(i)
	    kfree(cachep->array[i]);

	/* NUMA: free the list3 structures */
	for_each_online_node(i) {
		l3 = cachep->nodelists[i];
		if (l3) {
			kfree(l3->shared);
			free_alien_cache(l3->alien);
			kfree(l3);
		}
	}
	kmem_cache_free(&cache_cache, cachep);
}


/**
 * calculate_slab_order - calculate size (page order) of slabs
 * @cachep: pointer to the cache that is being created
 * @size: size of objects to be created in this cache.
 * @align: required alignment for the objects.
 * @flags: slab allocation flags
 *
 * Also calculates the number of objects per slab.
 *
 * This could be made much more intelligent.  For now, try to avoid using
 * high order pages for slabs.  When the gfp() functions are more friendly
 * towards high-order requests, this should be changed.
 */
static size_t calculate_slab_order(struct kmem_cache *cachep,
			size_t size, size_t align, unsigned long flags)
{
	unsigned long offslab_limit;
	size_t left_over = 0;
	int gfporder;

	for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
		unsigned int num;
		size_t remainder;

		cache_estimate(gfporder, size, align, flags, &remainder, &num);
		if (!num)
			continue;

		if (flags & CFLGS_OFF_SLAB) {
			/*
			 * Max number of objs-per-slab for caches which
			 * use off-slab slabs. Needed to avoid a possible
			 * looping condition in cache_grow().
			 */
			offslab_limit = size - sizeof(struct slab);
			offslab_limit /= sizeof(kmem_bufctl_t);

 			if (num > offslab_limit)
				break;
		}

		/* Found something acceptable - save it away */
		cachep->num = num;
		cachep->gfporder = gfporder;
		left_over = remainder;

		/*
		 * A VFS-reclaimable slab tends to have most allocations
		 * as GFP_NOFS and we really don't want to have to be allocating
		 * higher-order pages when we are unable to shrink dcache.
		 */
		if (flags & SLAB_RECLAIM_ACCOUNT)
			break;

		/*
		 * Large number of objects is good, but very large slabs are
		 * currently bad for the gfp()s.
		 */
		if (gfporder >= slab_break_gfp_order)
			break;

		/*
		 * Acceptable internal fragmentation?
		 */
		if (left_over * 8 <= (PAGE_SIZE << gfporder))
			break;
	}
	return left_over;
}

static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
{
	if (g_cpucache_up == FULL)
		return enable_cpucache(cachep);

	if (g_cpucache_up == NONE) {
		/*
		 * Note: the first kmem_cache_create must create the cache
		 * that's used by kmalloc(24), otherwise the creation of
		 * further caches will BUG().
		 */
		cachep->array[smp_processor_id()] = &initarray_generic.cache;

		/*
		 * If the cache that's used by kmalloc(sizeof(kmem_list3)) is
		 * the first cache, then we need to set up all its list3s,
		 * otherwise the creation of further caches will BUG().
		 */
		set_up_list3s(cachep, SIZE_AC);
		if (INDEX_AC == INDEX_L3)
			g_cpucache_up = PARTIAL_L3;
		else
			g_cpucache_up = PARTIAL_AC;
	} else {
		cachep->array[smp_processor_id()] =
			kmalloc(sizeof(struct arraycache_init), GFP_KERNEL);

		if (g_cpucache_up == PARTIAL_AC) {
			set_up_list3s(cachep, SIZE_L3);
			g_cpucache_up = PARTIAL_L3;
		} else {
			int node;
			for_each_online_node(node) {
				cachep->nodelists[node] =
				    kmalloc_node(sizeof(struct kmem_list3),
						GFP_KERNEL, node);
				BUG_ON(!cachep->nodelists[node]);
				kmem_list3_init(cachep->nodelists[node]);
			}
		}
	}
	cachep->nodelists[numa_node_id()]->next_reap =
			jiffies + REAPTIMEOUT_LIST3 +
			((unsigned long)cachep) % REAPTIMEOUT_LIST3;

	cpu_cache_get(cachep)->avail = 0;
	cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
	cpu_cache_get(cachep)->batchcount = 1;
	cpu_cache_get(cachep)->touched = 0;
	cachep->batchcount = 1;
	cachep->limit = BOOT_CPUCACHE_ENTRIES;
	return 0;
}

/**
 * kmem_cache_create - Create a cache.
 * @name: A string which is used in /proc/slabinfo to identify this cache.
 * @size: The size of objects to be created in this cache.
 * @align: The required alignment for the objects.
 * @flags: SLAB flags
 * @ctor: A constructor for the objects.
 *
 * Returns a ptr to the cache on success, NULL on failure.
 * Cannot be called within a int, but can be interrupted.
 * The @ctor is run when new pages are allocated by the cache.
 *
 * @name must be valid until the cache is destroyed. This implies that
 * the module calling this has to destroy the cache before getting unloaded.
 * Note that kmem_cache_name() is not guaranteed to return the same pointer,
 * therefore applications must manage it themselves.
 *
 * The flags are
 *
 * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
 * to catch references to uninitialised memory.
 *
 * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
 * for buffer overruns.
 *
 * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
 * cacheline.  This can be beneficial if you're counting cycles as closely
 * as davem.
 */
struct kmem_cache *
kmem_cache_create (const char *name, size_t size, size_t align,
	unsigned long flags, void (*ctor)(void *))
{
	size_t left_over, slab_size, ralign;
	struct kmem_cache *cachep = NULL, *pc;

	/*
	 * Sanity checks... these are all serious usage bugs.
	 */
	if (!name || in_interrupt() || (size < BYTES_PER_WORD) ||
	    size > KMALLOC_MAX_SIZE) {
		printk(KERN_ERR "%s: Early error in slab %s\n", __func__,
				name);
		BUG();
	}

	/*
	 * We use cache_chain_mutex to ensure a consistent view of
	 * cpu_online_mask as well.  Please see cpuup_callback
	 */
	get_online_cpus();
	mutex_lock(&cache_chain_mutex);

	list_for_each_entry(pc, &cache_chain, next) {
		char tmp;
		int res;

		/*
		 * This happens when the module gets unloaded and doesn't
		 * destroy its slab cache and no-one else reuses the vmalloc
		 * area of the module.  Print a warning.
		 */
		res = probe_kernel_address(pc->name, tmp);
		if (res) {
			printk(KERN_ERR
			       "SLAB: cache with size %d has lost its name\n",
			       pc->buffer_size);
			continue;
		}

		if (!strcmp(pc->name, name)) {
			printk(KERN_ERR
			       "kmem_cache_create: duplicate cache %s\n", name);
			dump_stack();
			goto oops;
		}
	}

#if DEBUG
	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
#if FORCED_DEBUG
	/*
	 * Enable redzoning and last user accounting, except for caches with
	 * large objects, if the increased size would increase the object size
	 * above the next power of two: caches with object sizes just above a
	 * power of two have a significant amount of internal fragmentation.
	 */
	if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
						2 * sizeof(unsigned long long)))
		flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
	if (!(flags & SLAB_DESTROY_BY_RCU))
		flags |= SLAB_POISON;
#endif
	if (flags & SLAB_DESTROY_BY_RCU)
		BUG_ON(flags & SLAB_POISON);
#endif
	/*
	 * Always checks flags, a caller might be expecting debug support which
	 * isn't available.
	 */
	BUG_ON(flags & ~CREATE_MASK);

	/*
	 * Check that size is in terms of words.  This is needed to avoid
	 * unaligned accesses for some archs when redzoning is used, and makes
	 * sure any on-slab bufctl's are also correctly aligned.
	 */
	if (size & (BYTES_PER_WORD - 1)) {
		size += (BYTES_PER_WORD - 1);
		size &= ~(BYTES_PER_WORD - 1);
	}

	/* calculate the final buffer alignment: */

	/* 1) arch recommendation: can be overridden for debug */
	if (flags & SLAB_HWCACHE_ALIGN) {
		/*
		 * Default alignment: as specified by the arch code.  Except if
		 * an object is really small, then squeeze multiple objects into
		 * one cacheline.
		 */
		ralign = cache_line_size();
		while (size <= ralign / 2)
			ralign /= 2;
	} else {
		ralign = BYTES_PER_WORD;
	}

	/*
	 * Redzoning and user store require word alignment or possibly larger.
	 * Note this will be overridden by architecture or caller mandated
	 * alignment if either is greater than BYTES_PER_WORD.
	 */
	if (flags & SLAB_STORE_USER)
		ralign = BYTES_PER_WORD;

	if (flags & SLAB_RED_ZONE) {
		ralign = REDZONE_ALIGN;
		/* If redzoning, ensure that the second redzone is suitably
		 * aligned, by adjusting the object size accordingly. */
		size += REDZONE_ALIGN - 1;
		size &= ~(REDZONE_ALIGN - 1);
	}

	/* 2) arch mandated alignment */
	if (ralign < ARCH_SLAB_MINALIGN) {
		ralign = ARCH_SLAB_MINALIGN;
	}
	/* 3) caller mandated alignment */
	if (ralign < align) {
		ralign = align;
	}
	/* disable debug if necessary */
	if (ralign > __alignof__(unsigned long long))
		flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
	/*
	 * 4) Store it.
	 */
	align = ralign;

	/* Get cache's description obj. */
	cachep = kmem_cache_zalloc(&cache_cache, GFP_KERNEL);
	if (!cachep)
		goto oops;

#if DEBUG
	cachep->obj_size = size;

	/*
	 * Both debugging options require word-alignment which is calculated
	 * into align above.
	 */
	if (flags & SLAB_RED_ZONE) {
		/* add space for red zone words */
		cachep->obj_offset += sizeof(unsigned long long);
		size += 2 * sizeof(unsigned long long);
	}
	if (flags & SLAB_STORE_USER) {
		/* user store requires one word storage behind the end of
		 * the real object. But if the second red zone needs to be
		 * aligned to 64 bits, we must allow that much space.
		 */
		if (flags & SLAB_RED_ZONE)
			size += REDZONE_ALIGN;
		else
			size += BYTES_PER_WORD;
	}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
	if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
	    && cachep->obj_size > cache_line_size() && size < PAGE_SIZE) {
		cachep->obj_offset += PAGE_SIZE - size;
		size = PAGE_SIZE;
	}
#endif
#endif

	/*
	 * Determine if the slab management is 'on' or 'off' slab.
	 * (bootstrapping cannot cope with offslab caches so don't do
	 * it too early on.)
	 */
	if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init)
		/*
		 * Size is large, assume best to place the slab management obj
		 * off-slab (should allow better packing of objs).
		 */
		flags |= CFLGS_OFF_SLAB;

	size = ALIGN(size, align);

	left_over = calculate_slab_order(cachep, size, align, flags);

	if (!cachep->num) {
		printk(KERN_ERR
		       "kmem_cache_create: couldn't create cache %s.\n", name);
		kmem_cache_free(&cache_cache, cachep);
		cachep = NULL;
		goto oops;
	}
	slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
			  + sizeof(struct slab), align);

	/*
	 * If the slab has been placed off-slab, and we have enough space then
	 * move it on-slab. This is at the expense of any extra colouring.
	 */
	if (flags & CFLGS_OFF_SLAB && left_over >= slab_size) {
		flags &= ~CFLGS_OFF_SLAB;
		left_over -= slab_size;
	}

	if (flags & CFLGS_OFF_SLAB) {
		/* really off slab. No need for manual alignment */
		slab_size =
		    cachep->num * sizeof(kmem_bufctl_t) + sizeof(struct slab);
	}

	cachep->colour_off = cache_line_size();
	/* Offset must be a multiple of the alignment. */
	if (cachep->colour_off < align)
		cachep->colour_off = align;
	cachep->colour = left_over / cachep->colour_off;
	cachep->slab_size = slab_size;
	cachep->flags = flags;
	cachep->gfpflags = 0;
	if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
		cachep->gfpflags |= GFP_DMA;
	cachep->buffer_size = size;
	cachep->reciprocal_buffer_size = reciprocal_value(size);

	if (flags & CFLGS_OFF_SLAB) {
		cachep->slabp_cache = kmem_find_general_cachep(slab_size, 0u);
		/*
		 * This is a possibility for one of the malloc_sizes caches.
		 * But since we go off slab only for object size greater than
		 * PAGE_SIZE/8, and malloc_sizes gets created in ascending order,
		 * this should not happen at all.
		 * But leave a BUG_ON for some lucky dude.
		 */
		BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
	}
	cachep->ctor = ctor;
	cachep->name = name;

	if (setup_cpu_cache(cachep)) {
		__kmem_cache_destroy(cachep);
		cachep = NULL;
		goto oops;
	}

	/* cache setup completed, link it into the list */
	list_add(&cachep->next, &cache_chain);
oops:
	if (!cachep && (flags & SLAB_PANIC))
		panic("kmem_cache_create():