kmem_cache_create函数的源码分析

kmem_cache_create函数的源码如下：

/**
 * 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.
 *
 * 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;
	gfp_t gfp;

	/*
	 * 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
	 */
	if (slab_is_available()) {
		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;

	if (slab_is_available())
		gfp = GFP_KERNEL;
	else
		gfp = GFP_NOWAIT;

	/* Get cache's description obj. */
	cachep = kmem_cache_zalloc(&cache_cache, gfp);
	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() && ALIGN(size, align) < PAGE_SIZE) {
		cachep->obj_offset += PAGE_SIZE - ALIGN(size, align);
		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. Always use on-slab management when
	 * SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
	 */
	if ((size >= (PAGE_SIZE >> 3)) && !slab_early_init &&
	    !(flags & SLAB_NOLEAKTRACE))
		/*
		 * 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);

#ifdef CONFIG_PAGE_POISONING
		/* If we're going to use the generic kernel_map_pages()
		 * poisoning, then it's going to smash the contents of
		 * the redzone and userword anyhow, so switch them off.
		 */
		if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
			flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
#endif
	}

	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, gfp)) {
		__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(): failed to create slab `%s'\n",
		      name);
	if (slab_is_available()) {
		mutex_unlock(&cache_chain_mutex);
		put_online_cpus();
	}
	return cachep;
}