linux zram

使用zram的第一步是加载zram模块：modprobe zram（可通过添加num_devices参数指定zram设备的数量，默认一个zram0）。

块设备驱动的一般流程

1、注册块设备 register_blkdev
2、申请gendisk alloc_disk
3、初始化请求队列，并设置请求处理函数blk_alloc_queue
4、将gendisk 添加到内核中 add_disk

zram_init

static int __init zram_init(void)
{
	int ret;

	ret = cpuhp_setup_state_multi(CPUHP_ZCOMP_PREPARE, "block/zram:prepare",
				      zcomp_cpu_up_prepare, zcomp_cpu_dead);
	if (ret < 0)
		return ret;

	ret = class_register(&zram_control_class);//注册zram_control类，sys/class下会生成一个zram-control目录
	if (ret) {
		pr_err("Unable to register zram-control class\n");
		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
		return ret;
	}

	zram_debugfs_create();//在debugfs文件系统中添加zram目录（需要使能CONFIG_ZRAM_MEMORY_TRACKING）
	zram_major = register_blkdev(0, "zram");//申请zram主设备号
	if (zram_major <= 0) {
		pr_err("Unable to get major number\n");
		class_unregister(&zram_control_class);
		cpuhp_remove_multi_state(CPUHP_ZCOMP_PREPARE);
		return -EBUSY;
	}

	while (num_devices != 0) {
		mutex_lock(&zram_index_mutex);
		ret = zram_add(); //创建zram设备
		mutex_unlock(&zram_index_mutex);
		if (ret < 0)
			goto out_error;
		num_devices--;
	}

	return 0;

out_error:
	destroy_devices();
	return ret;
}

zram_add

static int zram_add(void)
{
	struct zram *zram;
	struct request_queue *queue;
	int ret, device_id;

	zram = kzalloc(sizeof(struct zram), GFP_KERNEL);
	if (!zram)
		return -ENOMEM;

	ret = idr_alloc(&zram_index_idr, zram, 0, 0, GFP_KERNEL);
	if (ret < 0)
		goto out_free_dev;
	device_id = ret;

	init_rwsem(&zram->init_lock);

	queue = blk_alloc_queue(GFP_KERNEL);//分配request_queue，并初始化queue->backing_dev_info.
	if (!queue) {
		pr_err("Error allocating disk queue for device %d\n",
			device_id);
		ret = -ENOMEM;
		goto out_free_idr;
	}

	blk_queue_make_request(queue, zram_make_request);//设置request_queue的make_request_fn函数

	/* gendisk structure */
	zram->disk = alloc_disk(1);
	if (!zram->disk) {
		pr_err("Error allocating disk structure for device %d\n",
			device_id);
		ret = -ENOMEM;
		goto out_free_queue;
	}

	zram->disk->major = zram_major;
	zram->disk->first_minor = device_id;
	zram->disk->fops = &zram_devops;//rw_page函数是后序数据流操作的接口
	zram->disk->queue = queue;
	zram->disk->queue->queuedata = zram;
	zram->disk->private_data = zram;
	snprintf(zram->disk->disk_name, 16, "zram%d", device_id);

	/* Actual capacity set using syfs (/sys/block/zram<id>/disksize */
	set_capacity(zram->disk, 0);
	/* zram devices sort of resembles non-rotational disks */
	blk_queue_flag_set(QUEUE_FLAG_NONROT, zram->disk->queue);
	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, zram->disk->queue);

	/*
	 * To ensure that we always get PAGE_SIZE aligned
	 * and n*PAGE_SIZED sized I/O requests.
	 */
	blk_queue_physical_block_size(zram->disk->queue, PAGE_SIZE);
	blk_queue_logical_block_size(zram->disk->queue,
					ZRAM_LOGICAL_BLOCK_SIZE);
	blk_queue_io_min(zram->disk->queue, PAGE_SIZE);
	blk_queue_io_opt(zram->disk->queue, PAGE_SIZE);
	zram->disk->queue->limits.discard_granularity = PAGE_SIZE;
	blk_queue_max_discard_sectors(zram->disk->queue, UINT_MAX);
	blk_queue_flag_set(QUEUE_FLAG_DISCARD, zram->disk->queue);

	/*
	 * zram_bio_discard() will clear all logical blocks if logical block
	 * size is identical with physical block size(PAGE_SIZE). But if it is
	 * different, we will skip discarding some parts of logical blocks in
	 * the part of the request range which isn't aligned to physical block
	 * size.  So we can't ensure that all discarded logical blocks are
	 * zeroed.
	 */
	if (ZRAM_LOGICAL_BLOCK_SIZE == PAGE_SIZE)
		blk_queue_max_write_zeroes_sectors(zram->disk->queue, UINT_MAX);

	zram->disk->queue->backing_dev_info->capabilities |=
			(BDI_CAP_STABLE_WRITES | BDI_CAP_SYNCHRONOUS_IO);
	disk_to_dev(zram->disk)->groups = zram_disk_attr_groups; // /sys/block/zramx/目录下的节点
	add_disk(zram->disk);//添加disk信息到内核中
	//为disk分配block_device结构体，打开块设备扫描分区，并将device信息通过netlink广播到用户态从而在dev目录下创建文件

	strlcpy(zram->compressor, default_compressor, sizeof(zram->compressor));

	zram_debugfs_register(zram);
	pr_info("Added device: %s\n", zram->disk->disk_name);
	return device_id;

out_free_queue:
	blk_cleanup_queue(queue);
out_free_idr:
	idr_remove(&zram_index_idr, device_id);
out_free_dev:
	kfree(zram);
	return ret;
}

/dev/zramx文件生成

add_disk之后，udev捕获到内核发送的设备添加信息，会调用mknod创建节点，

static int
shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
{
	struct inode *inode;
	int error = -ENOSPC;

	inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE);//创建inode
	if (inode) {
		error = simple_acl_create(dir, inode);
		if (error)
			goto out_iput;
		error = security_inode_init_security(inode, dir,
						     &dentry->d_name,
						     shmem_initxattrs, NULL);
		if (error && error != -EOPNOTSUPP)
			goto out_iput;

		error = 0;
		dir->i_size += BOGO_DIRENT_SIZE;
		dir->i_ctime = dir->i_mtime = current_time(dir);
		d_instantiate(dentry, inode); //关联  dentry->d_inode = inode;
		dget(dentry); /* Extra count - pin the dentry in core */
	}
	return error;
out_iput:
	iput(inode);
	return error;
}

disksize_store

zram_init中只是初始化了zram作为块设备的一般特性，其内存压缩所需要的相关属性则在写入disksize时完成初始化。

static ssize_t disksize_store(struct device *dev,
		struct device_attribute *attr, const char *buf, size_t len)
{
	u64 disksize;
	struct zcomp *comp;
	struct zram *zram = dev_to_zram(dev);
	int err;

	disksize = memparse(buf, NULL);
	if (!disksize)
		return -EINVAL;

	down_write(&zram->init_lock);
	if (init_done(zram)) {
		pr_info("Cannot change disksize for initialized device\n");
		err = -EBUSY;
		goto out_unlock;
	}

	disksize = PAGE_ALIGN(disksize); //按页大小对齐
	if (!zram_meta_alloc(zram, disksize)) { //初始化table（zram_table_entry数组）和mem_pool（zsmalloc的内存池）字段
		err = -ENOMEM;
		goto out_unlock;
	}

	comp = zcomp_create(zram->compressor); //初始化内存压缩流，数据的压缩解压缩都依赖zcomp的zcom_strm完成,其中包含了缓冲区和压缩算法。
	if (IS_ERR(comp)) {
		pr_err("Cannot initialise %s compressing backend\n",
				zram->compressor);
		err = PTR_ERR(comp);
		goto out_free_meta;
	}

	zram->comp = comp;
	zram->disksize = disksize;
	set_capacity(zram->disk, zram->disksize >> SECTOR_SHIFT);

	revalidate_disk(zram->disk);
	up_write(&zram->init_lock);

	return len;

out_free_meta:
	zram_meta_free(zram, disksize);
out_unlock:
	up_write(&zram->init_lock);
	return err;
}

zram_meta_alloc

static bool zram_meta_alloc(struct zram *zram, u64 disksize)
{
	size_t num_pages;

	num_pages = disksize >> PAGE_SHIFT;
	zram->table = vzalloc(array_size(num_pages, sizeof(*zram->table)));//zram设备中，每个页大小的空间都会分配一个zram_table_entry
	if (!zram->table)
		return false;

	zram->mem_pool = zs_create_pool(zram->disk->disk_name);
	if (!zram->mem_pool) {
		vfree(zram->table);
		return false;
	}

	if (!huge_class_size)
		huge_class_size = zs_huge_class_size(zram->mem_pool);
	return true;
}

zram_table_entry

struct zram_table_entry {
	union {
		unsigned long handle; //对应zsmalloc返回值
		unsigned long element;
	};
	unsigned long value; //低24为表示大小（被压缩后的）、其余位表示zram_page的类型
#ifdef CONFIG_ZRAM_MEMORY_TRACKING
	ktime_t ac_time;
#endif
};

swapon

zram设备初始化之后使用swapon将zram设备挂载为swap设备，内存管理模块与swap_info_struct结构交互，swapon主要就是始化一个swap_info_struct并将其连接到全局的swap_active_node链表。

SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
{
	struct swap_info_struct *p;
	struct filename *name;
	struct file *swap_file = NULL;
	struct address_space *mapping;
	int prio;
	int error;
	union swap_header *swap_header;
	int nr_extents;
	sector_t span;
	unsigned long maxpages;
	unsigned char *swap_map = NULL;
	struct swap_cluster_info *cluster_info = NULL;
	unsigned long *frontswap_map = NULL;
	struct page *page = NULL;
	struct inode *inode = NULL;
	bool inced_nr_rotate_swap = false;

	if (swap_flags & ~SWAP_FLAGS_VALID)
		return -EINVAL;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!swap_avail_heads)
		return -ENOMEM;

	p = alloc_swap_info(); //申请一个swap_info_struct,并加入全局的swap_info数组中，p->type执行其在swap_info数组中的下标
	if (IS_ERR(p))
		return PTR_ERR(p);

	INIT_WORK(&p->discard_work, swap_discard_work);

	name = getname(specialfile);
	if (IS_ERR(name)) {
		error = PTR_ERR(name);
		name = NULL;
		goto bad_swap;
	}
	swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0);
	if (IS_ERR(swap_file)) {
		error = PTR_ERR(swap_file);
		swap_file = NULL;
		goto bad_swap;
	}

	p->swap_file = swap_file;
	mapping = swap_file->f_mapping;
	inode = mapping->host;

	/* If S_ISREG(inode->i_mode) will do inode_lock(inode); */
	error = claim_swapfile(p, inode); //将p的bdev指针指向zram0对应的block_device
	if (unlikely(error))
		goto bad_swap;

	/*
	 * Read the swap header.
	 */
	if (!mapping->a_ops->readpage) {
		error = -EINVAL;
		goto bad_swap;
	}
	page = read_mapping_page(mapping, 0, swap_file);
	if (IS_ERR(page)) {
		error = PTR_ERR(page);
		goto bad_swap;
	}
	swap_header = kmap(page);

	maxpages = read_swap_header(p, swap_header, inode);
	if (unlikely(!maxpages)) {
		error = -EINVAL;
		goto bad_swap;
	}

	/* OK, set up the swap map and apply the bad block list */
	swap_map = vzalloc(maxpages);
	if (!swap_map) {
		error = -ENOMEM;
		goto bad_swap;
	}

	if (bdi_cap_stable_pages_required(inode_to_bdi(inode)))
		p->flags |= SWP_STABLE_WRITES;

	if (bdi_cap_synchronous_io(inode_to_bdi(inode)))
		p->flags |= SWP_SYNCHRONOUS_IO;

	if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) {
		int cpu;
		unsigned long ci, nr_cluster;

		p->flags |= SWP_SOLIDSTATE;
		/*
		 * select a random position to start with to help wear leveling
		 * SSD
		 */
		p->cluster_next = 1 + (prandom_u32() % p->highest_bit);
		nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER);

		cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info),
					GFP_KERNEL);
		if (!cluster_info) {
			error = -ENOMEM;
			goto bad_swap;
		}

		for (ci = 0; ci < nr_cluster; ci++)
			spin_lock_init(&((cluster_info + ci)->lock));

		p->percpu_cluster = alloc_percpu(struct percpu_cluster);
		if (!p->percpu_cluster) {
			error = -ENOMEM;
			goto bad_swap;
		}
		for_each_possible_cpu(cpu) {
			struct percpu_cluster *cluster;
			cluster = per_cpu_ptr(p->percpu_cluster, cpu);
			cluster_set_null(&cluster->index);
		}
	} else {
		atomic_inc(&nr_rotate_swap);
		inced_nr_rotate_swap = true;
	}

	error = swap_cgroup_swapon(p->type, maxpages);
	if (error)
		goto bad_swap;

	nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map,
		cluster_info, maxpages, &span);
	if (unlikely(nr_extents < 0)) {
		error = nr_extents;
		goto bad_swap;
	}
	/* frontswap enabled? set up bit-per-page map for frontswap */
	if (IS_ENABLED(CONFIG_FRONTSWAP))
		frontswap_map = kvcalloc(BITS_TO_LONGS(maxpages),
					 sizeof(long),
					 GFP_KERNEL);

	if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) {
		/*
		 * When discard is enabled for swap with no particular
		 * policy flagged, we set all swap discard flags here in
		 * order to sustain backward compatibility with older
		 * swapon(8) releases.
		 */
		p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD |
			     SWP_PAGE_DISCARD);

		/*
		 * By flagging sys_swapon, a sysadmin can tell us to
		 * either do single-time area discards only, or to just
		 * perform discards for released swap page-clusters.
		 * Now it's time to adjust the p->flags accordingly.
		 */
		if (swap_flags & SWAP_FLAG_DISCARD_ONCE)
			p->flags &= ~SWP_PAGE_DISCARD;
		else if (swap_flags & SWAP_FLAG_DISCARD_PAGES)
			p->flags &= ~SWP_AREA_DISCARD;

		/* issue a swapon-time discard if it's still required */
		if (p->flags & SWP_AREA_DISCARD) {
			int err = discard_swap(p);
			if (unlikely(err))
				pr_err("swapon: discard_swap(%p): %d\n",
					p, err);
		}
	}

	error = init_swap_address_space(p->type, maxpages); //为swap设备分配address_space，其a_ops为swap_aops，每64m分配一个组成链表并加入到全局数组swap_files
	if (error)
		goto bad_swap;

	mutex_lock(&swapon_mutex);
	prio = -1;
	if (swap_flags & SWAP_FLAG_PREFER)
		prio =
		  (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT;
	enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); //将p链接到swap_active_head链表，p->avail_lists连接到swap_avail_head链表

	pr_info("Adding %uk swap on %s.  Priority:%d extents:%d across:%lluk %s%s%s%s%s\n",
		p->pages<<(PAGE_SHIFT-10), name->name, p->prio,
		nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10),
		(p->flags & SWP_SOLIDSTATE) ? "SS" : "",
		(p->flags & SWP_DISCARDABLE) ? "D" : "",
		(p->flags & SWP_AREA_DISCARD) ? "s" : "",
		(p->flags & SWP_PAGE_DISCARD) ? "c" : "",
		(frontswap_map) ? "FS" : "");

	mutex_unlock(&swapon_mutex);
	atomic_inc(&proc_poll_event);
	wake_up_interruptible(&proc_poll_wait);

	if (S_ISREG(inode->i_mode))
		inode->i_flags |= S_SWAPFILE;
	error = 0;
	goto out;
bad_swap:
	free_percpu(p->percpu_cluster);
	p->percpu_cluster = NULL;
	if (inode && S_ISBLK(inode->i_mode) && p->bdev) {
		set_blocksize(p->bdev, p->old_block_size);
		blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
	}
	destroy_swap_extents(p);
	swap_cgroup_swapoff(p->type);
	spin_lock(&swap_lock);
	p->swap_file = NULL;
	p->flags = 0;
	spin_unlock(&swap_lock);
	vfree(swap_map);
	kvfree(cluster_info);
	kvfree(frontswap_map);
	if (inced_nr_rotate_swap)
		atomic_dec(&nr_rotate_swap);
	if (swap_file) {
		if (inode && S_ISREG(inode->i_mode)) {
			inode_unlock(inode);
			inode = NULL;
		}
		filp_close(swap_file, NULL);
	}
out:
	if (page && !IS_ERR(page)) {
		kunmap(page);
		put_page(page);
	}
	if (name)
		putname(name);
	if (inode && S_ISREG(inode->i_mode))
		inode_unlock(inode);
	if (!error)
		enable_swap_slots_cache();
	return error;
}

zram读写

__zram_bvec_write

static int __zram_bvec_write(struct zram *zram, struct bio_vec *bvec,
				u32 index, struct bio *bio)
{
	int ret = 0;
	unsigned long alloced_pages;
	unsigned long handle = 0;
	unsigned int comp_len = 0;
	void *src, *dst, *mem;
	struct zcomp_strm *zstrm;
	struct page *page = bvec->bv_page;
	unsigned long element = 0;
	enum zram_pageflags flags = 0;
	bool allow_wb = true;

	mem = kmap_atomic(page);
	if (page_same_filled(mem, &element)) {
		kunmap_atomic(mem);
		/* Free memory associated with this sector now. */
		flags = ZRAM_SAME;
		atomic64_inc(&zram->stats.same_pages);
		goto out;
	}
	kunmap_atomic(mem);

compress_again:
	zstrm = zcomp_stream_get(zram->comp);
	src = kmap_atomic(page);
	ret = zcomp_compress(zstrm, src, &comp_len);
	kunmap_atomic(src);

	if (unlikely(ret)) {
		zcomp_stream_put(zram->comp);
		pr_err("Compression failed! err=%d\n", ret);
		zs_free(zram->mem_pool, handle);
		return ret;
	}

	if (unlikely(comp_len >= huge_class_size)) {
		comp_len = PAGE_SIZE;
		if (zram_wb_enabled(zram) && allow_wb) {
			zcomp_stream_put(zram->comp);
			ret = write_to_bdev(zram, bvec, index, bio, &element);
			if (!ret) {
				flags = ZRAM_WB;
				ret = 1;
				goto out;
			}
			allow_wb = false;
			goto compress_again;
		}
	}

	/*
	 * handle allocation has 2 paths:
	 * a) fast path is executed with preemption disabled (for
	 *  per-cpu streams) and has __GFP_DIRECT_RECLAIM bit clear,
	 *  since we can't sleep;
	 * b) slow path enables preemption and attempts to allocate
	 *  the page with __GFP_DIRECT_RECLAIM bit set. we have to
	 *  put per-cpu compression stream and, thus, to re-do
	 *  the compression once handle is allocated.
	 *
	 * if we have a 'non-null' handle here then we are coming
	 * from the slow path and handle has already been allocated.
	 */
	if (!handle)
		handle = zs_malloc(zram->mem_pool, comp_len,
				__GFP_KSWAPD_RECLAIM |
				__GFP_NOWARN |
				__GFP_HIGHMEM |
				__GFP_MOVABLE);
	if (!handle) {
		zcomp_stream_put(zram->comp);
		atomic64_inc(&zram->stats.writestall);
		handle = zs_malloc(zram->mem_pool, comp_len,
				GFP_NOIO | __GFP_HIGHMEM |
				__GFP_MOVABLE);
		if (handle)
			goto compress_again;
		return -ENOMEM;
	}

	alloced_pages = zs_get_total_pages(zram->mem_pool);
	update_used_max(zram, alloced_pages);

	if (zram->limit_pages && alloced_pages > zram->limit_pages) {
		zcomp_stream_put(zram->comp);
		zs_free(zram->mem_pool, handle);
		return -ENOMEM;
	}

	dst = zs_map_object(zram->mem_pool, handle, ZS_MM_WO);

	src = zstrm->buffer;
	if (comp_len == PAGE_SIZE)
		src = kmap_atomic(page);
	memcpy(dst, src, comp_len);
	if (comp_len == PAGE_SIZE)
		kunmap_atomic(src);

	zcomp_stream_put(zram->comp);
	zs_unmap_object(zram->mem_pool, handle);
	atomic64_add(comp_len, &zram->stats.compr_data_size);
out:
	/*
	 * Free memory associated with this sector
	 * before overwriting unused sectors.
	 */
	zram_slot_lock(zram, index);
	zram_free_page(zram, index);

	if (comp_len == PAGE_SIZE) {
		zram_set_flag(zram, index, ZRAM_HUGE);
		atomic64_inc(&zram->stats.huge_pages);
	}

	if (flags) {
		zram_set_flag(zram, index, flags);
		zram_set_element(zram, index, element);
	}  else {
		zram_set_handle(zram, index, handle);
		zram_set_obj_size(zram, index, comp_len);
	}
	zram_slot_unlock(zram, index);

	/* Update stats */
	atomic64_inc(&zram->stats.pages_stored);
	return ret;
}

__zram_bvec_read

static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
				struct bio *bio, bool partial_io)
{
	int ret;
	unsigned long handle;
	unsigned int size;
	void *src, *dst;

	if (zram_wb_enabled(zram)) {
		zram_slot_lock(zram, index);
		if (zram_test_flag(zram, index, ZRAM_WB)) {
			struct bio_vec bvec;

			zram_slot_unlock(zram, index);

			bvec.bv_page = page;
			bvec.bv_len = PAGE_SIZE;
			bvec.bv_offset = 0;
			return read_from_bdev(zram, &bvec,
					zram_get_element(zram, index),
					bio, partial_io);
		}
		zram_slot_unlock(zram, index);
	}

	zram_slot_lock(zram, index);
	handle = zram_get_handle(zram, index);
	if (!handle || zram_test_flag(zram, index, ZRAM_SAME)) {
		unsigned long value;
		void *mem;

		value = handle ? zram_get_element(zram, index) : 0;
		mem = kmap_atomic(page);
		zram_fill_page(mem, PAGE_SIZE, value);
		kunmap_atomic(mem);
		zram_slot_unlock(zram, index);
		return 0;
	}

	size = zram_get_obj_size(zram, index);

	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
	if (size == PAGE_SIZE) {
		dst = kmap_atomic(page);
		memcpy(dst, src, PAGE_SIZE);
		kunmap_atomic(dst);
		ret = 0;
	} else {
		struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);

		dst = kmap_atomic(page);
		ret = zcomp_decompress(zstrm, src, size, dst);
		kunmap_atomic(dst);
		zcomp_stream_put(zram->comp);
	}
	zs_unmap_object(zram->mem_pool, handle);
	zram_slot_unlock(zram, index);

	/* Should NEVER happen. Return bio error if it does. */
	if (unlikely(ret))
		pr_err("Decompression failed! err=%d, page=%u\n", ret, index);

	return ret;
}

zram_stats

可通过 /sys/block/zramx/下的mm_stat、io_stat或是debugfs下的zram节点获取zram的使用信息，其主要通过zram的zram_stats成员获取。

struct zram_stats {
	atomic64_t compr_data_size;	/* compressed size of pages stored */
	atomic64_t num_reads;	/* failed + successful */
	atomic64_t num_writes;	/* --do-- */
	atomic64_t failed_reads;	/* can happen when memory is too low */
	atomic64_t failed_writes;	/* can happen when memory is too low */
	atomic64_t invalid_io;	/* non-page-aligned I/O requests */
	atomic64_t notify_free;	/* no. of swap slot free notifications */
	atomic64_t same_pages;		/* no. of same element filled pages */
	atomic64_t huge_pages;		/* no. of huge pages，压缩后大小超过huge_class_size的页 */
	atomic64_t pages_stored;	/* no. of pages currently stored */
	atomic_long_t max_used_pages;	/* no. of maximum pages stored */
	atomic64_t writestall;		/* no. of write slow paths */
	atomic64_t miss_free;		/* no. of missed free */
};

static ssize_t mm_stat_show(struct device *dev,
		struct device_attribute *attr, char *buf)
{
	struct zram *zram = dev_to_zram(dev);
	struct zs_pool_stats pool_stats;
	u64 orig_size, mem_used = 0;
	long max_used;
	ssize_t ret;

	memset(&pool_stats, 0x00, sizeof(struct zs_pool_stats));

	down_read(&zram->init_lock);
	if (init_done(zram)) {
		mem_used = zs_get_total_pages(zram->mem_pool);
		zs_pool_stats(zram->mem_pool, &pool_stats);
	}

	orig_size = atomic64_read(&zram->stats.pages_stored);
	max_used = atomic_long_read(&zram->stats.max_used_pages);

	ret = scnprintf(buf, PAGE_SIZE,
			"%8llu %8llu %8llu %8lu %8ld %8llu %8lu %8llu\n",
			orig_size << PAGE_SHIFT,
			(u64)atomic64_read(&zram->stats.compr_data_size),
			mem_used << PAGE_SHIFT,
			zram->limit_pages << PAGE_SHIFT,
			max_used << PAGE_SHIFT,
			(u64)atomic64_read(&zram->stats.same_pages),
			pool_stats.pages_compacted,
			(u64)atomic64_read(&zram->stats.huge_pages));
	up_read(&zram->init_lock);

	return ret;
}