/*
 * SLOB Allocator: Simple List Of Blocks
 *
 * Matt Mackall <mpm@selenic.com> 12/30/03
 *
 * How SLOB works:
 *
 * The core of SLOB is a traditional K&R style heap allocator, with
 * support for returning aligned objects. The granularity of this
 * allocator is 8 bytes on x86, though it's perhaps possible to reduce
 * this to 4 if it's deemed worth the effort. The slob heap is a
 * singly-linked list of pages from __get_free_page, grown on demand
 * and allocation from the heap is currently first-fit.
 *
 * Above this is an implementation of kmalloc/kfree. Blocks returned
 * from kmalloc are 8-byte aligned and prepended with a 8-byte header.
 * If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
 * __get_free_pages directly so that it can return page-aligned blocks
 * and keeps a linked list of such pages and their orders. These
 * objects are detected in kfree() by their page alignment.
 *
 * SLAB is emulated on top of SLOB by simply calling constructors and
 * destructors for every SLAB allocation. Objects are returned with
 * the 8-byte alignment unless the SLAB_HWCACHE_ALIGN flag is
 * set, in which case the low-level allocator will fragment blocks to
 * create the proper alignment. Again, objects of page-size or greater
 * are allocated by calling __get_free_pages. As SLAB objects know
 * their size, no separate size bookkeeping is necessary and there is
 * essentially no allocation space overhead.
 */

#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/rcupdate.h>

struct slob_block {
        int units;
        struct slob_block *next;
};
typedef struct slob_block slob_t;

#define SLOB_UNIT sizeof(slob_t)
#define SLOB_UNITS(size) (((size) + SLOB_UNIT - 1)/SLOB_UNIT)
#define SLOB_ALIGN L1_CACHE_BYTES

struct bigblock {
        int order;
        void *pages;
        struct bigblock *next;
};
typedef struct bigblock bigblock_t;

/*
 * struct slob_rcu is inserted at the tail of allocated slob blocks, which
 * were created with a SLAB_DESTROY_BY_RCU slab. slob_rcu is used to free
 * the block using call_rcu.
 */
struct slob_rcu {
        struct rcu_head head;
        int size;
};

static slob_t arena = { .next = &arena, .units = 1 };
static slob_t *slobfree = &arena;
static bigblock_t *bigblocks;
static DEFINE_SPINLOCK(slob_lock);
static DEFINE_SPINLOCK(block_lock);

static void slob_free(void *b, int size);
static void slob_timer_cbk(void);


static void *slob_alloc(size_t size, gfp_t gfp, int align)
{
        slob_t *prev, *cur, *aligned = 0;
        int delta = 0, units = SLOB_UNITS(size);
        unsigned long flags;

        spin_lock_irqsave(&slob_lock, flags);
        prev = slobfree;
        for (cur = prev->next; ; prev = cur, cur = cur->next) {
                if (align) {
                        aligned = (slob_t *)ALIGN((unsigned long)cur, align);
                        delta = aligned - cur;
                }
                if (cur->units >= units + delta) { /* room enough? */
                        if (delta) { /* need to fragment head to align? */
                                aligned->units = cur->units - delta;
                                aligned->next = cur->next;
                                cur->next = aligned;
                                cur->units = delta;
                                prev = cur;
                                cur = aligned;
                        }

                        if (cur->units == units) /* exact fit? */
                                prev->next = cur->next; /* unlink */
                        else { /* fragment */
                                prev->next = cur + units;
                                prev->next->units = cur->units - units;
                                prev->next->next = cur->next;
                                cur->units = units;
                        }

                        slobfree = prev;
                        spin_unlock_irqrestore(&slob_lock, flags);
                        return cur;
                }
                if (cur == slobfree) {
                        spin_unlock_irqrestore(&slob_lock, flags);

                        if (size == PAGE_SIZE) /* trying to shrink arena? */
                                return 0;

                        cur = (slob_t *)__get_free_page(gfp);
                        if (!cur)
                                return 0;

                        slob_free(cur, PAGE_SIZE);
                        spin_lock_irqsave(&slob_lock, flags);
                        cur = slobfree;
                }
        }
}

static void slob_free(void *block, int size)
{
        slob_t *cur, *b = (slob_t *)block;
        unsigned long flags;

        if (!block)
                return;

        if (size)
                b->units = SLOB_UNITS(size);

        /* Find reinsertion point */
        spin_lock_irqsave(&slob_lock, flags);
        for (cur = slobfree; !(b > cur && b < cur->next); cur = cur->next)
                if (cur >= cur->next && (b > cur || b < cur->next))
                        break;

        if (b + b->units == cur->next) {
                b->units += cur->next->units;
                b->next = cur->next->next;
        } else
                b->next = cur->next;

        if (cur + cur->units == b) {
                cur->units += b->units;
                cur->next = b->next;
        } else
                cur->next = b;

        slobfree = cur;

        spin_unlock_irqrestore(&slob_lock, flags);
}

void *__kmalloc(size_t size, gfp_t gfp)
{
        slob_t *m;
        bigblock_t *bb;
        unsigned long flags;

        if (size < PAGE_SIZE - SLOB_UNIT) {
                m = slob_alloc(size + SLOB_UNIT, gfp, 0);
                return m ? (void *)(m + 1) : 0;
        }

        bb = slob_alloc(sizeof(bigblock_t), gfp, 0);
        if (!bb)
                return 0;

        bb->order = get_order(size);
        bb->pages = (void *)__get_free_pages(gfp, bb->order);

        if (bb->pages) {
                spin_lock_irqsave(&block_lock, flags);
                bb->next = bigblocks;
                bigblocks = bb;
                spin_unlock_irqrestore(&block_lock, flags);
                return bb->pages;
        }

        slob_free(bb, sizeof(bigblock_t));
        return 0;
}
EXPORT_SYMBOL(__kmalloc);

/**
 * krealloc - reallocate memory. The contents will remain unchanged.
 *
 * @p: object to reallocate memory for.
 * @new_size: how many bytes of memory are required.
 * @flags: the type of memory to allocate.
 *
 * The contents of the object pointed to are preserved up to the
 * lesser of the new and old sizes.  If @p is %NULL, krealloc()
 * behaves exactly like kmalloc().  If @size is 0 and @p is not a
 * %NULL pointer, the object pointed to is freed.
 */
void *krealloc(const void *p, size_t new_size, gfp_t flags)
{
        void *ret;

        if (unlikely(!p))
                return kmalloc_track_caller(new_size, flags);

        if (unlikely(!new_size)) {
                kfree(p);
                return NULL;
        }

        ret = kmalloc_track_caller(new_size, flags);
        if (ret) {
                memcpy(ret, p, min(new_size, ksize(p)));
                kfree(p);
        }
        return ret;
}
EXPORT_SYMBOL(krealloc);

void kfree(const void *block)
{
        bigblock_t *bb, **last = &bigblocks;
        unsigned long flags;

        if (!block)
                return;

        if (!((unsigned long)block & (PAGE_SIZE-1))) {
                /* might be on the big block list */
                spin_lock_irqsave(&block_lock, flags);
                for (bb = bigblocks; bb; last = &bb->next, bb = bb->next) {
                        if (bb->pages == block) {
                                *last = bb->next;
                                spin_unlock_irqrestore(&block_lock, flags);
                                free_pages((unsigned long)block, bb->order);
                                slob_free(bb, sizeof(bigblock_t));
                                return;
                        }
                }
                spin_unlock_irqrestore(&block_lock, flags);
        }

        slob_free((slob_t *)block - 1, 0);
        return;
}

EXPORT_SYMBOL(kfree);

size_t ksize(const void *block)
{
        bigblock_t *bb;
        unsigned long flags;

        if (!block)
                return 0;

        if (!((unsigned long)block & (PAGE_SIZE-1))) {
                spin_lock_irqsave(&block_lock, flags);
                for (bb = bigblocks; bb; bb = bb->next)
                        if (bb->pages == block) {
                                spin_unlock_irqrestore(&slob_lock, flags);
                                return PAGE_SIZE << bb->order;
                        }
                spin_unlock_irqrestore(&block_lock, flags);
        }

        return ((slob_t *)block - 1)->units * SLOB_UNIT;
}

struct kmem_cache {
        unsigned int size, align;
        unsigned long flags;
        const char *name;
        void (*ctor)(void *, struct kmem_cache *, unsigned long);
};

struct kmem_cache *kmem_cache_create(const char *name, size_t size,
        size_t align, unsigned long flags,
        void (*ctor)(void*, struct kmem_cache *, unsigned long),
        void (*dtor)(void*, struct kmem_cache *, unsigned long))
{
        struct kmem_cache *c;

        c = slob_alloc(sizeof(struct kmem_cache), flags, 0);

        if (c) {
                c->name = name;
                c->size = size;
                if (flags & SLAB_DESTROY_BY_RCU) {
                        /* leave room for rcu footer at the end of object */
                        c->size += sizeof(struct slob_rcu);
                }
                c->flags = flags;
                c->ctor = ctor;
                /* ignore alignment unless it's forced */
                c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
                if (c->align < align)
                        c->align = align;
        } else if (flags & SLAB_PANIC)
                panic("Cannot create slab cache %s\n", name);

        return c;
}
EXPORT_SYMBOL(kmem_cache_create);

void kmem_cache_destroy(struct kmem_cache *c)
{
        slob_free(c, sizeof(struct kmem_cache));
}
EXPORT_SYMBOL(kmem_cache_destroy);

void *kmem_cache_alloc(struct kmem_cache *c, gfp_t flags)
{
        void *b;

        if (c->size < PAGE_SIZE)
                b = slob_alloc(c->size, flags, c->align);
        else
                b = (void *)__get_free_pages(flags, get_order(c->size));

        if (c->ctor)
                c->ctor(b, c, 0);

        return b;
}
EXPORT_SYMBOL(kmem_cache_alloc);

void *kmem_cache_zalloc(struct kmem_cache *c, gfp_t flags)
{
        void *ret = kmem_cache_alloc(c, flags);
        if (ret)
                memset(ret, 0, c->size);

        return ret;
}
EXPORT_SYMBOL(kmem_cache_zalloc);

static void __kmem_cache_free(void *b, int size)
{
        if (size < PAGE_SIZE)
                slob_free(b, size);
        else
                free_pages((unsigned long)b, get_order(size));
}

static void kmem_rcu_free(struct rcu_head *head)
{
        struct slob_rcu *slob_rcu = (struct slob_rcu *)head;
        void *b = (void *)slob_rcu - (slob_rcu->size - sizeof(struct slob_rcu));

        __kmem_cache_free(b, slob_rcu->size);
}

void kmem_cache_free(struct kmem_cache *c, void *b)
{
        if (unlikely(c->flags & SLAB_DESTROY_BY_RCU)) {
                struct slob_rcu *slob_rcu;
                slob_rcu = b + (c->size - sizeof(struct slob_rcu));
                INIT_RCU_HEAD(&slob_rcu->head);
                slob_rcu->size = c->size;
                call_rcu(&slob_rcu->head, kmem_rcu_free);
        } else {
                __kmem_cache_free(b, c->size);
        }
}
EXPORT_SYMBOL(kmem_cache_free);

unsigned int kmem_cache_size(struct kmem_cache *c)
{
        return c->size;
}
EXPORT_SYMBOL(kmem_cache_size);

const char *kmem_cache_name(struct kmem_cache *c)
{
        return c->name;
}
EXPORT_SYMBOL(kmem_cache_name);

static struct timer_list slob_timer = TIMER_INITIALIZER(
        (void (*)(unsigned long))slob_timer_cbk, 0, 0);

int kmem_cache_shrink(struct kmem_cache *d)
{
        return 0;
}
EXPORT_SYMBOL(kmem_cache_shrink);

int kmem_ptr_validate(struct kmem_cache *a, const void *b)
{
        return 0;
}

void __init kmem_cache_init(void)
{
        slob_timer_cbk();
}

static void slob_timer_cbk(void)
{
        void *p = slob_alloc(PAGE_SIZE, 0, PAGE_SIZE-1);

        if (p)
                free_page((unsigned long)p);

        mod_timer(&slob_timer, jiffies + HZ);
}