/*
 * Slab allocator functions that are independent of the allocator strategy
 *
 * (C) 2012 Christoph Lameter <cl@linux.com>
 */
#include <linux/slab.h>

#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/interrupt.h>
#include <linux/memory.h>
#include <linux/compiler.h>
#include <linux/module.h>
#include <linux/cpu.h>
#include <linux/uaccess.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <linux/memcontrol.h>

#include "slab.h"

enum slab_state slab_state;
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
struct kmem_cache *kmem_cache;

#ifdef CONFIG_DEBUG_VM
static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
				   size_t size)
{
	struct kmem_cache *s = NULL;

	if (!name || in_interrupt() || size < sizeof(void *) ||
		size > KMALLOC_MAX_SIZE) {
		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
		return -EINVAL;
	}

	list_for_each_entry(s, &slab_caches, list) {
		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(s->name, tmp);
		if (res) {
			pr_err("Slab cache with size %d has lost its name\n",
			       s->object_size);
			continue;
		}

		/*
		 * For simplicity, we won't check this in the list of memcg
		 * caches. We have control over memcg naming, and if there
		 * aren't duplicates in the global list, there won't be any
		 * duplicates in the memcg lists as well.
		 */
		if (!memcg && !strcmp(s->name, name)) {
			pr_err("%s (%s): Cache name already exists.\n",
			       __func__, name);
			dump_stack();
			s = NULL;
			return -EINVAL;
		}
	}

	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
	return 0;
}
#else
static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
					  const char *name, size_t size)
{
	return 0;
}
#endif

#ifdef CONFIG_MEMCG_KMEM
int memcg_update_all_caches(int num_memcgs)
{
	struct kmem_cache *s;
	int ret = 0;
	mutex_lock(&slab_mutex);

	list_for_each_entry(s, &slab_caches, list) {
		if (!is_root_cache(s))
			continue;

		ret = memcg_update_cache_size(s, num_memcgs);
		/*
		 * See comment in memcontrol.c, memcg_update_cache_size:
		 * Instead of freeing the memory, we'll just leave the caches
		 * up to this point in an updated state.
		 */
		if (ret)
			goto out;
	}

	memcg_update_array_size(num_memcgs);
out:
	mutex_unlock(&slab_mutex);
	return ret;
}
#endif

/*
 * Figure out what the alignment of the objects will be given a set of
 * flags, a user specified alignment and the size of the objects.
 */
unsigned long calculate_alignment(unsigned long flags,
		unsigned long align, unsigned long size)
{
	/*
	 * If the user wants hardware cache aligned objects then follow that
	 * suggestion if the object is sufficiently large.
	 *
	 * The hardware cache alignment cannot override the specified
	 * alignment though. If that is greater then use it.
	 */
	if (flags & SLAB_HWCACHE_ALIGN) {
		unsigned long ralign = cache_line_size();
		while (size <= ralign / 2)
			ralign /= 2;
		align = max(align, ralign);
	}

	if (align < ARCH_SLAB_MINALIGN)
		align = ARCH_SLAB_MINALIGN;

	return ALIGN(align, sizeof(void *));
}


/*
 * 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 interrupt, but can be interrupted.
 * The @ctor is run when new pages are allocated by the cache.
 *
 * 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_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
			size_t align, unsigned long flags, void (*ctor)(void *),
			struct kmem_cache *parent_cache)
{
	struct kmem_cache *s = NULL;
	int err = 0;

	get_online_cpus();
	mutex_lock(&slab_mutex);

	if (!kmem_cache_sanity_check(memcg, name, size) == 0)
		goto out_locked;

	/*
	 * Some allocators will constraint the set of valid flags to a subset
	 * of all flags. We expect them to define CACHE_CREATE_MASK in this
	 * case, and we'll just provide them with a sanitized version of the
	 * passed flags.
	 */
	flags &= CACHE_CREATE_MASK;

	s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
	if (s)
		goto out_locked;

	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
	if (s) {
		s->object_size = s->size = size;
		s->align = calculate_alignment(flags, align, size);
		s->ctor = ctor;

		if (memcg_register_cache(memcg, s, parent_cache)) {
			kmem_cache_free(kmem_cache, s);
			err = -ENOMEM;
			goto out_locked;
		}

		s->name = kstrdup(name, GFP_KERNEL);
		if (!s->name) {
			kmem_cache_free(kmem_cache, s);
			err = -ENOMEM;
			goto out_locked;
		}

		err = __kmem_cache_create(s, flags);
		if (!err) {
			s->refcount = 1;
			list_add(&s->list, &slab_caches);
			memcg_cache_list_add(memcg, s);
		} else {
			kfree(s->name);
			kmem_cache_free(kmem_cache, s);
		}
	} else
		err = -ENOMEM;

out_locked:
	mutex_unlock(&slab_mutex);
	put_online_cpus();

	if (err) {

		if (flags & SLAB_PANIC)
			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
				name, err);
		else {
			printk(KERN_WARNING "kmem_cache_create(%s) failed with error %d",
				name, err);
			dump_stack();
		}

		return NULL;
	}

	return s;
}

struct kmem_cache *
kmem_cache_create(const char *name, size_t size, size_t align,
		  unsigned long flags, void (*ctor)(void *))
{
	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
}
EXPORT_SYMBOL(kmem_cache_create);

void kmem_cache_destroy(struct kmem_cache *s)
{
	/* Destroy all the children caches if we aren't a memcg cache */
	kmem_cache_destroy_memcg_children(s);

	get_online_cpus();
	mutex_lock(&slab_mutex);
	s->refcount--;
	if (!s->refcount) {
		list_del(&s->list);

		if (!__kmem_cache_shutdown(s)) {
			mutex_unlock(&slab_mutex);
			if (s->flags & SLAB_DESTROY_BY_RCU)
				rcu_barrier();

			memcg_release_cache(s);
			kfree(s->name);
			kmem_cache_free(kmem_cache, s);
		} else {
			list_add(&s->list, &slab_caches);
			mutex_unlock(&slab_mutex);
			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
				s->name);
			dump_stack();
		}
	} else {
		mutex_unlock(&slab_mutex);
	}
	put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);

int slab_is_available(void)
{
	return slab_state >= UP;
}

#ifndef CONFIG_SLOB
/* Create a cache during boot when no slab services are available yet */
void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size,
		unsigned long flags)
{
	int err;

	s->name = name;
	s->size = s->object_size = size;
	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
	err = __kmem_cache_create(s, flags);

	if (err)
		panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
					name, size, err);

	s->refcount = -1;	/* Exempt from merging for now */
}

struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size,
				unsigned long flags)
{
	struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);

	if (!s)
		panic("Out of memory when creating slab %s\n", name);

	create_boot_cache(s, name, size, flags);
	list_add(&s->list, &slab_caches);
	s->refcount = 1;
	return s;
}

struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
EXPORT_SYMBOL(kmalloc_caches);

#ifdef CONFIG_ZONE_DMA
struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
EXPORT_SYMBOL(kmalloc_dma_caches);
#endif

#endif /* !CONFIG_SLOB */


#ifdef CONFIG_SLABINFO
void print_slabinfo_header(struct seq_file *m)
{
	/*
	 * Output format version, so at least we can change it
	 * without _too_ many complaints.
	 */
#ifdef CONFIG_DEBUG_SLAB
	seq_puts(m, "slabinfo - version: 2.1 (statistics)\n");
#else
	seq_puts(m, "slabinfo - version: 2.1\n");
#endif
	seq_puts(m, "# name            <active_objs> <num_objs> <objsize> "
		 "<objperslab> <pagesperslab>");
	seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
	seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
#ifdef CONFIG_DEBUG_SLAB
	seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
		 "<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
	seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
#endif
	seq_putc(m, '\n');
}

static void *s_start(struct seq_file *m, loff_t *pos)
{
	loff_t n = *pos;

	mutex_lock(&slab_mutex);
	if (!n)
		print_slabinfo_header(m);

	return seq_list_start(&slab_caches, *pos);
}

static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
	return seq_list_next(p, &slab_caches, pos);
}

static void s_stop(struct seq_file *m, void *p)
{
	mutex_unlock(&slab_mutex);
}

static void
memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
{
	struct kmem_cache *c;
	struct slabinfo sinfo;
	int i;

	if (!is_root_cache(s))
		return;

	for_each_memcg_cache_index(i) {
		c = cache_from_memcg(s, i);
		if (!c)
			continue;

		memset(&sinfo, 0, sizeof(sinfo));
		get_slabinfo(c, &sinfo);

		info->active_slabs += sinfo.active_slabs;
		info->num_slabs += sinfo.num_slabs;
		info->shared_avail += sinfo.shared_avail;
		info->active_objs += sinfo.active_objs;
		info->num_objs += sinfo.num_objs;
	}
}

int cache_show(struct kmem_cache *s, struct seq_file *m)
{
	struct slabinfo sinfo;

	memset(&sinfo, 0, sizeof(sinfo));
	get_slabinfo(s, &sinfo);

	memcg_accumulate_slabinfo(s, &sinfo);

	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
		   cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
		   sinfo.objects_per_slab, (1 << sinfo.cache_order));

	seq_printf(m, " : tunables %4u %4u %4u",
		   sinfo.limit, sinfo.batchcount, sinfo.shared);
	seq_printf(m, " : slabdata %6lu %6lu %6lu",
		   sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
	slabinfo_show_stats(m, s);
	seq_putc(m, '\n');
	return 0;
}

static int s_show(struct seq_file *m, void *p)
{
	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);

	if (!is_root_cache(s))
		return 0;
	return cache_show(s, m);
}

/*
 * slabinfo_op - iterator that generates /proc/slabinfo
 *
 * Output layout:
 * cache-name
 * num-active-objs
 * total-objs
 * object size
 * num-active-slabs
 * total-slabs
 * num-pages-per-slab
 * + further values on SMP and with statistics enabled
 */
static const struct seq_operations slabinfo_op = {
	.start = s_start,
	.next = s_next,
	.stop = s_stop,
	.show = s_show,
};

static int slabinfo_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &slabinfo_op);
}

static const struct file_operations proc_slabinfo_operations = {
	.open		= slabinfo_open,
	.read		= seq_read,
	.write          = slabinfo_write,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static int __init slab_proc_init(void)
{
	proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations);
	return 0;
}
module_init(slab_proc_init);
#endif /* CONFIG_SLABINFO */