zsmalloc.c

/*
 * zsmalloc memory allocator
 *
 * Copyright (C) 2011  Nitin Gupta
 * Copyright (C) 2012, 2013 Minchan Kim
 *
 * This code is released using a dual license strategy: BSD/GPL
 * You can choose the license that better fits your requirements.
 *
 * Released under the terms of 3-clause BSD License
 * Released under the terms of GNU General Public License Version 2.0
 */

/*
 * Following is how we use various fields and flags of underlying
 * struct page(s) to form a zspage.
 *
 * Usage of struct page fields:
 *	page->private: points to zspage
 *	page->freelist(index): links together all component pages of a zspage
 *		For the huge page, this is always 0, so we use this field
 *		to store handle.
 *
 * Usage of struct page flags:
 *	PG_private: identifies the first component page
 *	PG_private2: identifies the last component page
 *	PG_owner_priv_1: indentifies the huge component page
 *
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/highmem.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <asm/tlbflush.h>
#include <asm/pgtable.h>
#include <linux/cpumask.h>
#include <linux/cpu.h>
#include <linux/vmalloc.h>
#include <linux/preempt.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/debugfs.h>
#include <linux/zsmalloc.h>
#include <linux/zpool.h>
#include <linux/mount.h>
#include <linux/migrate.h>
#include <linux/pagemap.h>

#define ZSPAGE_MAGIC	0x58

/*
 * This must be power of 2 and greater than of equal to sizeof(link_free).
 * These two conditions ensure that any 'struct link_free' itself doesn't
 * span more than 1 page which avoids complex case of mapping 2 pages simply
 * to restore link_free pointer values.
 */
#define ZS_ALIGN		8

/*
 * A single 'zspage' is composed of up to 2^N discontiguous 0-order (single)
 * pages. ZS_MAX_ZSPAGE_ORDER defines upper limit on N.
 */
#define ZS_MAX_ZSPAGE_ORDER 2
#define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER)

#define ZS_HANDLE_SIZE (sizeof(unsigned long))

/*
 * Object location (<PFN>, <obj_idx>) is encoded as
 * as single (unsigned long) handle value.
 *
 * Note that object index <obj_idx> starts from 0.
 *
 * This is made more complicated by various memory models and PAE.
 */

#ifndef MAX_PHYSMEM_BITS
#ifdef CONFIG_HIGHMEM64G
#define MAX_PHYSMEM_BITS 36
#else /* !CONFIG_HIGHMEM64G */
/*
 * If this definition of MAX_PHYSMEM_BITS is used, OBJ_INDEX_BITS will just
 * be PAGE_SHIFT
 */
#define MAX_PHYSMEM_BITS BITS_PER_LONG
#endif
#endif
#define _PFN_BITS		(MAX_PHYSMEM_BITS - PAGE_SHIFT)

/*
 * Memory for allocating for handle keeps object position by
 * encoding <page, obj_idx> and the encoded value has a room
 * in least bit(ie, look at obj_to_location).
 * We use the bit to synchronize between object access by
 * user and migration.
 */
#define HANDLE_PIN_BIT	0

/*
 * Head in allocated object should have OBJ_ALLOCATED_TAG
 * to identify the object was allocated or not.
 * It's okay to add the status bit in the least bit because
 * header keeps handle which is 4byte-aligned address so we
 * have room for two bit at least.
 */
#define OBJ_ALLOCATED_TAG 1
#define OBJ_TAG_BITS 1
#define OBJ_INDEX_BITS	(BITS_PER_LONG - _PFN_BITS - OBJ_TAG_BITS)
#define OBJ_INDEX_MASK	((_AC(1, UL) << OBJ_INDEX_BITS) - 1)

#define MAX(a, b) ((a) >= (b) ? (a) : (b))
/* ZS_MIN_ALLOC_SIZE must be multiple of ZS_ALIGN */
#define ZS_MIN_ALLOC_SIZE \
	MAX(32, (ZS_MAX_PAGES_PER_ZSPAGE << PAGE_SHIFT >> OBJ_INDEX_BITS))
/* each chunk includes extra space to keep handle */
#define ZS_MAX_ALLOC_SIZE	PAGE_SIZE

/*
 * On systems with 4K page size, this gives 255 size classes! There is a
 * trader-off here:
 *  - Large number of size classes is potentially wasteful as free page are
 *    spread across these classes
 *  - Small number of size classes causes large internal fragmentation
 *  - Probably its better to use specific size classes (empirically
 *    determined). NOTE: all those class sizes must be set as multiple of
 *    ZS_ALIGN to make sure link_free itself never has to span 2 pages.
 *
 *  ZS_MIN_ALLOC_SIZE and ZS_SIZE_CLASS_DELTA must be multiple of ZS_ALIGN
 *  (reason above)
 */
#define ZS_SIZE_CLASS_DELTA	(PAGE_SIZE >> CLASS_BITS)

/*
 * We do not maintain any list for completely empty or full pages
 */
enum fullness_group {
	ZS_EMPTY,
	ZS_ALMOST_EMPTY,
	ZS_ALMOST_FULL,
	ZS_FULL,
	NR_ZS_FULLNESS,
};

enum zs_stat_type {
	CLASS_EMPTY,
	CLASS_ALMOST_EMPTY,
	CLASS_ALMOST_FULL,
	CLASS_FULL,
	OBJ_ALLOCATED,
	OBJ_USED,
	NR_ZS_STAT_TYPE,
};

struct zs_size_stat {
	unsigned long objs[NR_ZS_STAT_TYPE];
};

#ifdef CONFIG_ZSMALLOC_STAT
static struct dentry *zs_stat_root;
#endif

#ifdef CONFIG_COMPACTION
static struct vfsmount *zsmalloc_mnt;
#endif

/*
 * number of size_classes
 */
static int zs_size_classes;

/*
 * We assign a page to ZS_ALMOST_EMPTY fullness group when:
 *	n <= N / f, where
 * n = number of allocated objects
 * N = total number of objects zspage can store
 * f = fullness_threshold_frac
 *
 * Similarly, we assign zspage to:
 *	ZS_ALMOST_FULL	when n > N / f
 *	ZS_EMPTY	when n == 0
 *	ZS_FULL		when n == N
 *
 * (see: fix_fullness_group())
 */
static const int fullness_threshold_frac = 4;

struct size_class {
	spinlock_t lock;
	struct list_head fullness_list[NR_ZS_FULLNESS];
	/*
	 * Size of objects stored in this class. Must be multiple
	 * of ZS_ALIGN.
	 */
	int size;
	int objs_per_zspage;
	/* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */
	int pages_per_zspage;

	unsigned int index;
	struct zs_size_stat stats;
};

/* huge object: pages_per_zspage == 1 && maxobj_per_zspage == 1 */
static void SetPageHugeObject(struct page *page)
{
	SetPageOwnerPriv1(page);
}

static void ClearPageHugeObject(struct page *page)
{
	ClearPageOwnerPriv1(page);
}

static int PageHugeObject(struct page *page)
{
	return PageOwnerPriv1(page);
}

/*
 * Placed within free objects to form a singly linked list.
 * For every zspage, zspage->freeobj gives head of this list.
 *
 * This must be power of 2 and less than or equal to ZS_ALIGN
 */
struct link_free {
	union {
		/*
		 * Free object index;
		 * It's valid for non-allocated object
		 */
		unsigned long next;
		/*
		 * Handle of allocated object.
		 */
		unsigned long handle;
	};
};

struct zs_pool {
	const char *name;

	struct size_class **size_class;
	struct kmem_cache *handle_cachep;
	struct kmem_cache *zspage_cachep;

	atomic_long_t pages_allocated;

	struct zs_pool_stats stats;

	/* Compact classes */
	struct shrinker shrinker;
	/*
	 * To signify that register_shrinker() was successful
	 * and unregister_shrinker() will not Oops.
	 */
	bool shrinker_enabled;
#ifdef CONFIG_ZSMALLOC_STAT
	struct dentry *stat_dentry;
#endif
#ifdef CONFIG_COMPACTION
	struct inode *inode;
	struct work_struct free_work;
#endif
};

/*
 * A zspage's class index and fullness group
 * are encoded in its (first)page->mapping
 */
#define FULLNESS_BITS	2
#define CLASS_BITS	8
#define ISOLATED_BITS	3
#define MAGIC_VAL_BITS	8

struct zspage {
	struct {
		unsigned int fullness:FULLNESS_BITS;
		unsigned int class:CLASS_BITS;
		unsigned int isolated:ISOLATED_BITS;
		unsigned int magic:MAGIC_VAL_BITS;
	};
	unsigned int inuse;
	unsigned int freeobj;
	struct page *first_page;
	struct list_head list; /* fullness list */
#ifdef CONFIG_COMPACTION
	rwlock_t lock;
#endif
};

struct mapping_area {
#ifdef CONFIG_PGTABLE_MAPPING
	struct vm_struct *vm; /* vm area for mapping object that span pages */
#else
	char *vm_buf; /* copy buffer for objects that span pages */
#endif
	char *vm_addr; /* address of kmap_atomic()'ed pages */
	enum zs_mapmode vm_mm; /* mapping mode */
};

#ifdef CONFIG_COMPACTION
static int zs_register_migration(struct zs_pool *pool);
static void zs_unregister_migration(struct zs_pool *pool);
static void migrate_lock_init(struct zspage *zspage);
static void migrate_read_lock(struct zspage *zspage);
static void migrate_read_unlock(struct zspage *zspage);
static void kick_deferred_free(struct zs_pool *pool);
static void init_deferred_free(struct zs_pool *pool);
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage);
#else
static int zsmalloc_mount(void) { return 0; }
static void zsmalloc_unmount(void) {}
static int zs_register_migration(struct zs_pool *pool) { return 0; }
static void zs_unregister_migration(struct zs_pool *pool) {}
static void migrate_lock_init(struct zspage *zspage) {}
static void migrate_read_lock(struct zspage *zspage) {}
static void migrate_read_unlock(struct zspage *zspage) {}
static void kick_deferred_free(struct zs_pool *pool) {}
static void init_deferred_free(struct zs_pool *pool) {}
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage) {}
#endif

static int create_cache(struct zs_pool *pool)
{
	pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE,
					0, 0, NULL);
	if (!pool->handle_cachep)
		return 1;

	pool->zspage_cachep = kmem_cache_create("zspage", sizeof(struct zspage),
					0, 0, NULL);
	if (!pool->zspage_cachep) {
		kmem_cache_destroy(pool->handle_cachep);
		pool->handle_cachep = NULL;
		return 1;
	}

	return 0;
}

static void destroy_cache(struct zs_pool *pool)
{
	kmem_cache_destroy(pool->handle_cachep);
	kmem_cache_destroy(pool->zspage_cachep);
}

static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp)
{
	return (unsigned long)kmem_cache_alloc(pool->handle_cachep,
			gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
}

static void cache_free_handle(struct zs_pool *pool, unsigned long handle)
{
	kmem_cache_free(pool->handle_cachep, (void *)handle);
}

static struct zspage *cache_alloc_zspage(struct zs_pool *pool, gfp_t flags)
{
	return kmem_cache_alloc(pool->zspage_cachep,
			flags & ~(__GFP_HIGHMEM|__GFP_MOVABLE));
};

static void cache_free_zspage(struct zs_pool *pool, struct zspage *zspage)
{
	kmem_cache_free(pool->zspage_cachep, zspage);
}

static void record_obj(unsigned long handle, unsigned long obj)
{
	/*
	 * lsb of @obj represents handle lock while other bits
	 * represent object value the handle is pointing so
	 * updating shouldn't do store tearing.
	 */
	WRITE_ONCE(*(unsigned long *)handle, obj);
}

/* zpool driver */

#ifdef CONFIG_ZPOOL

static void *zs_zpool_create(const char *name, gfp_t gfp,
			     const struct zpool_ops *zpool_ops,
			     struct zpool *zpool)
{
	/*
	 * Ignore global gfp flags: zs_malloc() may be invoked from
	 * different contexts and its caller must provide a valid
	 * gfp mask.
	 */
	return zs_create_pool(name);
}

static void zs_zpool_destroy(void *pool)
{
	zs_destroy_pool(pool);
}

static int zs_zpool_malloc(void *pool, size_t size, gfp_t gfp,
			unsigned long *handle)
{
	*handle = zs_malloc(pool, size, gfp);
	return *handle ? 0 : -1;
}
static void zs_zpool_free(void *pool, unsigned long handle)
{
	zs_free(pool, handle);
}

static int zs_zpool_shrink(void *pool, unsigned int pages,
			unsigned int *reclaimed)
{
	return -EINVAL;
}

static void *zs_zpool_map(void *pool, unsigned long handle,
			enum zpool_mapmode mm)
{
	enum zs_mapmode zs_mm;

	switch (mm) {
	case ZPOOL_MM_RO:
		zs_mm = ZS_MM_RO;
		break;
	case ZPOOL_MM_WO:
		zs_mm = ZS_MM_WO;
		break;
	case ZPOOL_MM_RW: /* fallthru */
	default:
		zs_mm = ZS_MM_RW;
		break;
	}

	return zs_map_object(pool, handle, zs_mm);
}
static void zs_zpool_unmap(void *pool, unsigned long handle)
{
	zs_unmap_object(pool, handle);
}

static u64 zs_zpool_total_size(void *pool)
{
	return zs_get_total_pages(pool) << PAGE_SHIFT;
}

static struct zpool_driver zs_zpool_driver = {
	.type =		"zsmalloc",
	.owner =	THIS_MODULE,
	.create =	zs_zpool_create,
	.destroy =	zs_zpool_destroy,
	.malloc =	zs_zpool_malloc,
	.free =		zs_zpool_free,
	.shrink =	zs_zpool_shrink,
	.map =		zs_zpool_map,
	.unmap =	zs_zpool_unmap,
	.total_size =	zs_zpool_total_size,
};

MODULE_ALIAS("zpool-zsmalloc");
#endif /* CONFIG_ZPOOL */

/* per-cpu VM mapping areas for zspage accesses that cross page boundaries */
static DEFINE_PER_CPU(struct mapping_area, zs_map_area);

static bool is_zspage_isolated(struct zspage *zspage)
{
	return zspage->isolated;
}

static int is_first_page(struct page *page)
{
	return PagePrivate(page);
}

/* Protected by class->lock */
static inline int get_zspage_inuse(struct zspage *zspage)
{
	return zspage->inuse;
}

static inline void set_zspage_inuse(struct zspage *zspage, int val)
{
	zspage->inuse = val;
}

static inline void mod_zspage_inuse(struct zspage *zspage, int val)
{
	zspage->inuse += val;
}

static inline struct page *get_first_page(struct zspage *zspage)
{
	struct page *first_page = zspage->first_page;

	VM_BUG_ON_PAGE(!is_first_page(first_page), first_page);
	return first_page;
}

static inline int get_first_obj_offset(struct page *page)
{
	return page->units;
}

static inline void set_first_obj_offset(struct page *page, int offset)
{
	page->units = offset;
}

static inline unsigned int get_freeobj(struct zspage *zspage)
{
	return zspage->freeobj;
}

static inline void set_freeobj(struct zspage *zspage, unsigned int obj)
{
	zspage->freeobj = obj;
}

static void get_zspage_mapping(struct zspage *zspage,
				unsigned int *class_idx,
				enum fullness_group *fullness)
{
	BUG_ON(zspage->magic != ZSPAGE_MAGIC);

	*fullness = zspage->fullness;
	*class_idx = zspage->class;
}

static void set_zspage_mapping(struct zspage *zspage,
				unsigned int class_idx,
				enum fullness_group fullness)
{
	zspage->class = class_idx;
	zspage->fullness = fullness;
}

/*
 * zsmalloc divides the pool into various size classes where each
 * class maintains a list of zspages where each zspage is divided
 * into equal sized chunks. Each allocation falls into one of these
 * classes depending on its size. This function returns index of the
 * size class which has chunk size big enough to hold the give size.
 */
static int get_size_class_index(int size)
{
	int idx = 0;

	if (likely(size > ZS_MIN_ALLOC_SIZE))
		idx = DIV_ROUND_UP(size - ZS_MIN_ALLOC_SIZE,
				ZS_SIZE_CLASS_DELTA);

	return min(zs_size_classes - 1, idx);
}

static inline void zs_stat_inc(struct size_class *class,
				enum zs_stat_type type, unsigned long cnt)
{
	class->stats.objs[type] += cnt;
}

static inline void zs_stat_dec(struct size_class *class,
				enum zs_stat_type type, unsigned long cnt)
{
	class->stats.objs[type] -= cnt;
}

static inline unsigned long zs_stat_get(struct size_class *class,
				enum zs_stat_type type)
{
	return class->stats.objs[type];
}

#ifdef CONFIG_ZSMALLOC_STAT

static void __init zs_stat_init(void)
{
	if (!debugfs_initialized()) {
		pr_warn("debugfs not available, stat dir not created\n");
		return;
	}

	zs_stat_root = debugfs_create_dir("zsmalloc", NULL);
	if (!zs_stat_root)
		pr_warn("debugfs 'zsmalloc' stat dir creation failed\n");
}

static void __exit zs_stat_exit(void)
{
	debugfs_remove_recursive(zs_stat_root);
}

static unsigned long zs_can_compact(struct size_class *class);

static int zs_stats_size_show(struct seq_file *s, void *v)
{
	int i;
	struct zs_pool *pool = s->private;
	struct size_class *class;
	int objs_per_zspage;
	unsigned long class_almost_full, class_almost_empty;
	unsigned long obj_allocated, obj_used, pages_used, freeable;
	unsigned long total_class_almost_full = 0, total_class_almost_empty = 0;
	unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0;
	unsigned long total_freeable = 0;

	seq_printf(s, " %5s %5s %11s %12s %13s %10s %10s %16s %8s\n",
			"class", "size", "almost_full", "almost_empty",
			"obj_allocated", "obj_used", "pages_used",
			"pages_per_zspage", "freeable");

	for (i = 0; i < zs_size_classes; i++) {
		class = pool->size_class[i];

		if (class->index != i)
			continue;

		spin_lock(&class->lock);
		class_almost_full = zs_stat_get(class, CLASS_ALMOST_FULL);
		class_almost_empty = zs_stat_get(class, CLASS_ALMOST_EMPTY);
		obj_allocated = zs_stat_get(class, OBJ_ALLOCATED);
		obj_used = zs_stat_get(class, OBJ_USED);
		freeable = zs_can_compact(class);
		spin_unlock(&class->lock);

		objs_per_zspage = class->objs_per_zspage;
		pages_used = obj_allocated / objs_per_zspage *
				class->pages_per_zspage;

		seq_printf(s, " %5u %5u %11lu %12lu %13lu"
				" %10lu %10lu %16d %8lu\n",
			i, class->size, class_almost_full, class_almost_empty,
			obj_allocated, obj_used, pages_used,
			class->pages_per_zspage, freeable);

		total_class_almost_full += class_almost_full;
		total_class_almost_empty += class_almost_empty;
		total_objs += obj_allocated;
		total_used_objs += obj_used;
		total_pages += pages_used;
		total_freeable += freeable;
	}

	seq_puts(s, "\n");
	seq_printf(s, " %5s %5s %11lu %12lu %13lu %10lu %10lu %16s %8lu\n",
			"Total", "", total_class_almost_full,
			total_class_almost_empty, total_objs,
			total_used_objs, total_pages, "", total_freeable);

	return 0;
}

static int zs_stats_size_open(struct inode *inode, struct file *file)
{
	return single_open(file, zs_stats_size_show, inode->i_private);
}

static const struct file_operations zs_stat_size_ops = {
	.open           = zs_stats_size_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = single_release,
};

static void zs_pool_stat_create(struct zs_pool *pool, const char *name)
{
	struct dentry *entry;

	if (!zs_stat_root) {
		pr_warn("no root stat dir, not creating <%s> stat dir\n", name);
		return;
	}

	entry = debugfs_create_dir(name, zs_stat_root);
	if (!entry) {
		pr_warn("debugfs dir <%s> creation failed\n", name);
		return;
	}
	pool->stat_dentry = entry;

	entry = debugfs_create_file("classes", S_IFREG | S_IRUGO,
			pool->stat_dentry, pool, &zs_stat_size_ops);
	if (!entry) {
		pr_warn("%s: debugfs file entry <%s> creation failed\n",
				name, "classes");
		debugfs_remove_recursive(pool->stat_dentry);
		pool->stat_dentry = NULL;
	}
}

static void zs_pool_stat_destroy(struct zs_pool *pool)
{
	debugfs_remove_recursive(pool->stat_dentry);
}

#else /* CONFIG_ZSMALLOC_STAT */
static void __init zs_stat_init(void)
{
}

static void __exit zs_stat_exit(void)
{
}

static inline void zs_pool_stat_create(struct zs_pool *pool, const char *name)
{
}

static inline void zs_pool_stat_destroy(struct zs_pool *pool)
{
}
#endif


/*
 * For each size class, zspages are divided into different groups
 * depending on how "full" they are. This was done so that we could
 * easily find empty or nearly empty zspages when we try to shrink
 * the pool (not yet implemented). This function returns fullness
 * status of the given page.
 */
static enum fullness_group get_fullness_group(struct size_class *class,
						struct zspage *zspage)
{
	int inuse, objs_per_zspage;
	enum fullness_group fg;

	inuse = get_zspage_inuse(zspage);
	objs_per_zspage = class->objs_per_zspage;

	if (inuse == 0)
		fg = ZS_EMPTY;
	else if (inuse == objs_per_zspage)
		fg = ZS_FULL;
	else if (inuse <= 3 * objs_per_zspage / fullness_threshold_frac)
		fg = ZS_ALMOST_EMPTY;
	else
		fg = ZS_ALMOST_FULL;

	return fg;
}

/*
 * Each size class maintains various freelists and zspages are assigned
 * to one of these freelists based on the number of live objects they
 * have. This functions inserts the given zspage into the freelist
 * identified by <class, fullness_group>.
 */
static void insert_zspage(struct size_class *class,
				struct zspage *zspage,
				enum fullness_group fullness)
{
	struct zspage *head;

	zs_stat_inc(class, fullness, 1);
	head = list_first_entry_or_null(&class->fullness_list[fullness],
					struct zspage, list);
	/*
	 * We want to see more ZS_FULL pages and less almost empty/full.
	 * Put pages with higher ->inuse first.
	 */
	if (head) {
		if (get_zspage_inuse(zspage) < get_zspage_inuse(head)) {
			list_add(&zspage->list, &head->list);
			return;
		}
	}
	list_add(&zspage->list, &class->fullness_list[fullness]);
}

/*
 * This function removes the given zspage from the freelist identified
 * by <class, fullness_group>.
 */
static void remove_zspage(struct size_class *class,
				struct zspage *zspage,
				enum fullness_group fullness)
{
	VM_BUG_ON(list_empty(&class->fullness_list[fullness]));
	VM_BUG_ON(is_zspage_isolated(zspage));

	list_del_init(&zspage->list);
	zs_stat_dec(class, fullness, 1);
}

/*
 * Each size class maintains zspages in different fullness groups depending
 * on the number of live objects they contain. When allocating or freeing
 * objects, the fullness status of the page can change, say, from ALMOST_FULL
 * to ALMOST_EMPTY when freeing an object. This function checks if such
 * a status change has occurred for the given page and accordingly moves the
 * page from the freelist of the old fullness group to that of the new
 * fullness group.
 */
static enum fullness_group fix_fullness_group(struct size_class *class,
						struct zspage *zspage)
{
	int class_idx;
	enum fullness_group currfg, newfg;

	get_zspage_mapping(zspage, &class_idx, &currfg);
	newfg = get_fullness_group(class, zspage);
	if (newfg == currfg)
		goto out;

	if (!is_zspage_isolated(zspage)) {
		remove_zspage(class, zspage, currfg);
		insert_zspage(class, zspage, newfg);
	}

	set_zspage_mapping(zspage, class_idx, newfg);

out:
	return newfg;
}

/*
 * We have to decide on how many pages to link together
 * to form a zspage for each size class. This is important
 * to reduce wastage due to unusable space left at end of
 * each zspage which is given as:
 *     wastage = Zp % class_size
 *     usage = Zp - wastage
 * where Zp = zspage size = k * PAGE_SIZE where k = 1, 2, ...
 *
 * For example, for size class of 3/8 * PAGE_SIZE, we should
 * link together 3 PAGE_SIZE sized pages to form a zspage
 * since then we can perfectly fit in 8 such objects.
 */
static int get_pages_per_zspage(int class_size)
{
	int i, max_usedpc = 0;
	/* zspage order which gives maximum used size per KB */
	int max_usedpc_order = 1;

	for (i = 1; i <= ZS_MAX_PAGES_PER_ZSPAGE; i++) {
		int zspage_size;
		int waste, usedpc;

		zspage_size = i * PAGE_SIZE;
		waste = zspage_size % class_size;
		usedpc = (zspage_size - waste) * 100 / zspage_size;

		if (usedpc > max_usedpc) {
			max_usedpc = usedpc;
			max_usedpc_order = i;
		}
	}

	return max_usedpc_order;
}

static struct zspage *get_zspage(struct page *page)
{
	struct zspage *zspage = (struct zspage *)page->private;

	BUG_ON(zspage->magic != ZSPAGE_MAGIC);
	return zspage;
}

static struct page *get_next_page(struct page *page)
{
	if (unlikely(PageHugeObject(page)))
		return NULL;

	return page->freelist;
}

/**
 * obj_to_location - get (<page>, <obj_idx>) from encoded object value
 * @page: page object resides in zspage
 * @obj_idx: object index
 */
static void obj_to_location(unsigned long obj, struct page **page,
				unsigned int *obj_idx)
{
	obj >>= OBJ_TAG_BITS;
	*page = pfn_to_page(obj >> OBJ_INDEX_BITS);
	*obj_idx = (obj & OBJ_INDEX_MASK);
}

/**
 * location_to_obj - get obj value encoded from (<page>, <obj_idx>)
 * @page: page object resides in zspage
 * @obj_idx: object index
 */
static unsigned long location_to_obj(struct page *page, unsigned int obj_idx)
{
	unsigned long obj;

	obj = page_to_pfn(page) << OBJ_INDEX_BITS;
	obj |= obj_idx & OBJ_INDEX_MASK;
	obj <<= OBJ_TAG_BITS;

	return obj;
}

static unsigned long handle_to_obj(unsigned long handle)
{
	return *(unsigned long *)handle;
}

static unsigned long obj_to_head(struct page *page, void *obj)
{
	if (unlikely(PageHugeObject(page))) {
		VM_BUG_ON_PAGE(!is_first_page(page), page);
		return page->index;
	} else
		return *(unsigned long *)obj;
}

static inline int testpin_tag(unsigned long handle)
{
	return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle);
}

static inline int trypin_tag(unsigned long handle)
{
	return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle);
}

static void pin_tag(unsigned long handle)
{
	bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle);
}

static void unpin_tag(unsigned long handle)
{
	bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle);
}

static void reset_page(struct page *page)
{
	__ClearPageMovable(page);
	clear_bit(PG_private, &page->flags);
	clear_bit(PG_private_2, &page->flags);
	set_page_private(page, 0);
	page_mapcount_reset(page);
	ClearPageHugeObject(page);
	page->freelist = NULL;
}

/*
 * To prevent zspage destroy during migration, zspage freeing should
 * hold locks of all pages in the zspage.
 */
void lock_zspage(struct zspage *zspage)
{
	struct page *page = get_first_page(zspage);

	do {
		lock_page(page);
	} while ((page = get_next_page(page)) != NULL);
}

int trylock_zspage(struct zspage *zspage)
{
	struct page *cursor, *fail;

	for (cursor = get_first_page(zspage); cursor != NULL; cursor =
					get_next_page(cursor)) {
		if (!trylock_page(cursor)) {
			fail = cursor;
			goto unlock;
		}
	}

	return 1;
unlock:
	for (cursor = get_first_page(zspage); cursor != fail; cursor =
					get_next_page(cursor))
		unlock_page(cursor);

	return 0;
}

static void __free_zspage(struct zs_pool *pool, struct size_class *class,
				struct zspage *zspage)
{
	struct page *page, *next;
	enum fullness_group fg;
	unsigned int class_idx;

	get_zspage_mapping(zspage, &class_idx, &fg);

	assert_spin_locked(&class->lock);

	VM_BUG_ON(get_zspage_inuse(zspage));
	VM_BUG_ON(fg != ZS_EMPTY);

	next = page = get_first_page(zspage);
	do {
		VM_BUG_ON_PAGE(!PageLocked(page), page);