[deliverable/linux.git] / fs / f2fs / super.c

/*
 * fs/f2fs/super.c
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/module.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/statfs.h>
#include <linux/proc_fs.h>
#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include <linux/kthread.h>
#include <linux/parser.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/random.h>
#include <linux/exportfs.h>
#include <linux/f2fs_fs.h>

#include "f2fs.h"
#include "node.h"
#include "xattr.h"

static struct kmem_cache *f2fs_inode_cachep;

enum {
	Opt_gc_background_off,
	Opt_disable_roll_forward,
	Opt_discard,
	Opt_noheap,
	Opt_nouser_xattr,
	Opt_noacl,
	Opt_active_logs,
	Opt_disable_ext_identify,
	Opt_err,
};

static match_table_t f2fs_tokens = {
	{Opt_gc_background_off, "background_gc_off"},
	{Opt_disable_roll_forward, "disable_roll_forward"},
	{Opt_discard, "discard"},
	{Opt_noheap, "no_heap"},
	{Opt_nouser_xattr, "nouser_xattr"},
	{Opt_noacl, "noacl"},
	{Opt_active_logs, "active_logs=%u"},
	{Opt_disable_ext_identify, "disable_ext_identify"},
	{Opt_err, NULL},
};

static void init_once(void *foo)
{
	struct f2fs_inode_info *fi = (struct f2fs_inode_info *) foo;

	memset(fi, 0, sizeof(*fi));
	inode_init_once(&fi->vfs_inode);
}

static struct inode *f2fs_alloc_inode(struct super_block *sb)
{
	struct f2fs_inode_info *fi;

	fi = kmem_cache_alloc(f2fs_inode_cachep, GFP_NOFS | __GFP_ZERO);
	if (!fi)
		return NULL;

	init_once((void *) fi);

	/* Initilize f2fs-specific inode info */
	fi->vfs_inode.i_version = 1;
	atomic_set(&fi->dirty_dents, 0);
	fi->i_current_depth = 1;
	fi->i_advise = 0;
	rwlock_init(&fi->ext.ext_lock);

	set_inode_flag(fi, FI_NEW_INODE);

	return &fi->vfs_inode;
}

static void f2fs_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode));
}

static void f2fs_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, f2fs_i_callback);
}

static void f2fs_put_super(struct super_block *sb)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);

	f2fs_destroy_stats(sbi);
	stop_gc_thread(sbi);

	write_checkpoint(sbi, false, true);

	iput(sbi->node_inode);
	iput(sbi->meta_inode);

	/* destroy f2fs internal modules */
	destroy_node_manager(sbi);
	destroy_segment_manager(sbi);

	kfree(sbi->ckpt);

	sb->s_fs_info = NULL;
	brelse(sbi->raw_super_buf);
	kfree(sbi);
}

int f2fs_sync_fs(struct super_block *sb, int sync)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	int ret = 0;

	if (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES))
		return 0;

	if (sync)
		write_checkpoint(sbi, false, false);

	return ret;
}

static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
	block_t total_count, user_block_count, start_count, ovp_count;

	total_count = le64_to_cpu(sbi->raw_super->block_count);
	user_block_count = sbi->user_block_count;
	start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
	ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
	buf->f_type = F2FS_SUPER_MAGIC;
	buf->f_bsize = sbi->blocksize;

	buf->f_blocks = total_count - start_count;
	buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
	buf->f_bavail = user_block_count - valid_user_blocks(sbi);

	buf->f_files = valid_inode_count(sbi);
	buf->f_ffree = sbi->total_node_count - valid_node_count(sbi);

	buf->f_namelen = F2FS_MAX_NAME_LEN;
	buf->f_fsid.val[0] = (u32)id;
	buf->f_fsid.val[1] = (u32)(id >> 32);

	return 0;
}

static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
{
	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);

	if (test_opt(sbi, BG_GC))
		seq_puts(seq, ",background_gc_on");
	else
		seq_puts(seq, ",background_gc_off");
	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
		seq_puts(seq, ",disable_roll_forward");
	if (test_opt(sbi, DISCARD))
		seq_puts(seq, ",discard");
	if (test_opt(sbi, NOHEAP))
		seq_puts(seq, ",no_heap_alloc");
#ifdef CONFIG_F2FS_FS_XATTR
	if (test_opt(sbi, XATTR_USER))
		seq_puts(seq, ",user_xattr");
	else
		seq_puts(seq, ",nouser_xattr");
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
	if (test_opt(sbi, POSIX_ACL))
		seq_puts(seq, ",acl");
	else
		seq_puts(seq, ",noacl");
#endif
	if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
		seq_puts(seq, ",disable_ext_indentify");

	seq_printf(seq, ",active_logs=%u", sbi->active_logs);

	return 0;
}

static struct super_operations f2fs_sops = {
	.alloc_inode	= f2fs_alloc_inode,
	.destroy_inode	= f2fs_destroy_inode,
	.write_inode	= f2fs_write_inode,
	.show_options	= f2fs_show_options,
	.evict_inode	= f2fs_evict_inode,
	.put_super	= f2fs_put_super,
	.sync_fs	= f2fs_sync_fs,
	.statfs		= f2fs_statfs,
};

static struct inode *f2fs_nfs_get_inode(struct super_block *sb,
		u64 ino, u32 generation)
{
	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	struct inode *inode;

	if (ino < F2FS_ROOT_INO(sbi))
		return ERR_PTR(-ESTALE);

	/*
	 * f2fs_iget isn't quite right if the inode is currently unallocated!
	 * However f2fs_iget currently does appropriate checks to handle stale
	 * inodes so everything is OK.
	 */
	inode = f2fs_iget(sb, ino);
	if (IS_ERR(inode))
		return ERR_CAST(inode);
	if (generation && inode->i_generation != generation) {
		/* we didn't find the right inode.. */
		iput(inode);
		return ERR_PTR(-ESTALE);
	}
	return inode;
}

static struct dentry *f2fs_fh_to_dentry(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
				    f2fs_nfs_get_inode);
}

static struct dentry *f2fs_fh_to_parent(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
				    f2fs_nfs_get_inode);
}

static const struct export_operations f2fs_export_ops = {
	.fh_to_dentry = f2fs_fh_to_dentry,
	.fh_to_parent = f2fs_fh_to_parent,
	.get_parent = f2fs_get_parent,
};

static int parse_options(struct f2fs_sb_info *sbi, char *options)
{
	substring_t args[MAX_OPT_ARGS];
	char *p;
	int arg = 0;

	if (!options)
		return 0;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;
		/*
		 * Initialize args struct so we know whether arg was
		 * found; some options take optional arguments.
		 */
		args[0].to = args[0].from = NULL;
		token = match_token(p, f2fs_tokens, args);

		switch (token) {
		case Opt_gc_background_off:
			clear_opt(sbi, BG_GC);
			break;
		case Opt_disable_roll_forward:
			set_opt(sbi, DISABLE_ROLL_FORWARD);
			break;
		case Opt_discard:
			set_opt(sbi, DISCARD);
			break;
		case Opt_noheap:
			set_opt(sbi, NOHEAP);
			break;
#ifdef CONFIG_F2FS_FS_XATTR
		case Opt_nouser_xattr:
			clear_opt(sbi, XATTR_USER);
			break;
#else
		case Opt_nouser_xattr:
			pr_info("nouser_xattr options not supported\n");
			break;
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
		case Opt_noacl:
			clear_opt(sbi, POSIX_ACL);
			break;
#else
		case Opt_noacl:
			pr_info("noacl options not supported\n");
			break;
#endif
		case Opt_active_logs:
			if (args->from && match_int(args, &arg))
				return -EINVAL;
			if (arg != 2 && arg != 4 && arg != 6)
				return -EINVAL;
			sbi->active_logs = arg;
			break;
		case Opt_disable_ext_identify:
			set_opt(sbi, DISABLE_EXT_IDENTIFY);
			break;
		default:
			pr_err("Unrecognized mount option \"%s\" or missing value\n",
					p);
			return -EINVAL;
		}
	}
	return 0;
}

static loff_t max_file_size(unsigned bits)
{
	loff_t result = ADDRS_PER_INODE;
	loff_t leaf_count = ADDRS_PER_BLOCK;

	/* two direct node blocks */
	result += (leaf_count * 2);

	/* two indirect node blocks */
	leaf_count *= NIDS_PER_BLOCK;
	result += (leaf_count * 2);

	/* one double indirect node block */
	leaf_count *= NIDS_PER_BLOCK;
	result += leaf_count;

	result <<= bits;
	return result;
}

static int sanity_check_raw_super(struct f2fs_super_block *raw_super)
{
	unsigned int blocksize;

	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic))
		return 1;

	/* Currently, support only 4KB block size */
	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
	if (blocksize != PAGE_CACHE_SIZE)
		return 1;
	if (le32_to_cpu(raw_super->log_sectorsize) !=
					F2FS_LOG_SECTOR_SIZE)
		return 1;
	if (le32_to_cpu(raw_super->log_sectors_per_block) !=
					F2FS_LOG_SECTORS_PER_BLOCK)
		return 1;
	return 0;
}

static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
				struct f2fs_checkpoint *ckpt)
{
	unsigned int total, fsmeta;

	total = le32_to_cpu(raw_super->segment_count);
	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
	fsmeta += le32_to_cpu(raw_super->segment_count_sit);
	fsmeta += le32_to_cpu(raw_super->segment_count_nat);
	fsmeta += le32_to_cpu(ckpt->rsvd_segment_count);
	fsmeta += le32_to_cpu(raw_super->segment_count_ssa);

	if (fsmeta >= total)
		return 1;
	return 0;
}

static void init_sb_info(struct f2fs_sb_info *sbi)
{
	struct f2fs_super_block *raw_super = sbi->raw_super;
	int i;

	sbi->log_sectors_per_block =
		le32_to_cpu(raw_super->log_sectors_per_block);
	sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize);
	sbi->blocksize = 1 << sbi->log_blocksize;
	sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
	sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg;
	sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
	sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
	sbi->total_sections = le32_to_cpu(raw_super->section_count);
	sbi->total_node_count =
		(le32_to_cpu(raw_super->segment_count_nat) / 2)
			* sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
	sbi->root_ino_num = le32_to_cpu(raw_super->root_ino);
	sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
	sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);

	for (i = 0; i < NR_COUNT_TYPE; i++)
		atomic_set(&sbi->nr_pages[i], 0);
}

static int f2fs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct f2fs_sb_info *sbi;
	struct f2fs_super_block *raw_super;
	struct buffer_head *raw_super_buf;
	struct inode *root;
	long err = -EINVAL;
	int i;

	/* allocate memory for f2fs-specific super block info */
	sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

	/* set a temporary block size */
	if (!sb_set_blocksize(sb, F2FS_BLKSIZE))
		goto free_sbi;

	/* read f2fs raw super block */
	raw_super_buf = sb_bread(sb, 0);
	if (!raw_super_buf) {
		err = -EIO;
		goto free_sbi;
	}
	raw_super = (struct f2fs_super_block *)
			((char *)raw_super_buf->b_data + F2FS_SUPER_OFFSET);

	/* init some FS parameters */
	sbi->active_logs = NR_CURSEG_TYPE;

	set_opt(sbi, BG_GC);

#ifdef CONFIG_F2FS_FS_XATTR
	set_opt(sbi, XATTR_USER);
#endif
#ifdef CONFIG_F2FS_FS_POSIX_ACL
	set_opt(sbi, POSIX_ACL);
#endif
	/* parse mount options */
	if (parse_options(sbi, (char *)data))
		goto free_sb_buf;

	/* sanity checking of raw super */
	if (sanity_check_raw_super(raw_super))
		goto free_sb_buf;

	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
	sb->s_max_links = F2FS_LINK_MAX;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));

	sb->s_op = &f2fs_sops;
	sb->s_xattr = f2fs_xattr_handlers;
	sb->s_export_op = &f2fs_export_ops;
	sb->s_magic = F2FS_SUPER_MAGIC;
	sb->s_fs_info = sbi;
	sb->s_time_gran = 1;
	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));

	/* init f2fs-specific super block info */
	sbi->sb = sb;
	sbi->raw_super = raw_super;
	sbi->raw_super_buf = raw_super_buf;
	mutex_init(&sbi->gc_mutex);
	mutex_init(&sbi->write_inode);
	mutex_init(&sbi->writepages);
	mutex_init(&sbi->cp_mutex);
	for (i = 0; i < NR_LOCK_TYPE; i++)
		mutex_init(&sbi->fs_lock[i]);
	sbi->por_doing = 0;
	spin_lock_init(&sbi->stat_lock);
	init_rwsem(&sbi->bio_sem);
	init_sb_info(sbi);

	/* get an inode for meta space */
	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
	if (IS_ERR(sbi->meta_inode)) {
		err = PTR_ERR(sbi->meta_inode);
		goto free_sb_buf;
	}

	err = get_valid_checkpoint(sbi);
	if (err)
		goto free_meta_inode;

	/* sanity checking of checkpoint */
	err = -EINVAL;
	if (sanity_check_ckpt(raw_super, sbi->ckpt))
		goto free_cp;

	sbi->total_valid_node_count =
				le32_to_cpu(sbi->ckpt->valid_node_count);
	sbi->total_valid_inode_count =
				le32_to_cpu(sbi->ckpt->valid_inode_count);
	sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
	sbi->total_valid_block_count =
				le64_to_cpu(sbi->ckpt->valid_block_count);
	sbi->last_valid_block_count = sbi->total_valid_block_count;
	sbi->alloc_valid_block_count = 0;
	INIT_LIST_HEAD(&sbi->dir_inode_list);
	spin_lock_init(&sbi->dir_inode_lock);

	/* init super block */
	if (!sb_set_blocksize(sb, sbi->blocksize))
		goto free_cp;

	init_orphan_info(sbi);

	/* setup f2fs internal modules */
	err = build_segment_manager(sbi);
	if (err)
		goto free_sm;
	err = build_node_manager(sbi);
	if (err)
		goto free_nm;

	build_gc_manager(sbi);

	/* get an inode for node space */
	sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
	if (IS_ERR(sbi->node_inode)) {
		err = PTR_ERR(sbi->node_inode);
		goto free_nm;
	}

	/* if there are nt orphan nodes free them */
	err = -EINVAL;
	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
				recover_orphan_inodes(sbi))
		goto free_node_inode;

	/* read root inode and dentry */
	root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
	if (IS_ERR(root)) {
		err = PTR_ERR(root);
		goto free_node_inode;
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size)
		goto free_root_inode;

	sb->s_root = d_make_root(root); /* allocate root dentry */
	if (!sb->s_root) {
		err = -ENOMEM;
		goto free_root_inode;
	}

	/* recover fsynced data */
	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
				!test_opt(sbi, DISABLE_ROLL_FORWARD))
		recover_fsync_data(sbi);

	/* After POR, we can run background GC thread */
	err = start_gc_thread(sbi);
	if (err)
		goto fail;

	err = f2fs_build_stats(sbi);
	if (err)
		goto fail;

	return 0;
fail:
	stop_gc_thread(sbi);
free_root_inode:
	dput(sb->s_root);
	sb->s_root = NULL;
free_node_inode:
	iput(sbi->node_inode);
free_nm:
	destroy_node_manager(sbi);
free_sm:
	destroy_segment_manager(sbi);
free_cp:
	kfree(sbi->ckpt);
free_meta_inode:
	make_bad_inode(sbi->meta_inode);
	iput(sbi->meta_inode);
free_sb_buf:
	brelse(raw_super_buf);
free_sbi:
	kfree(sbi);
	return err;
}

static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
			const char *dev_name, void *data)
{
	return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
}

static struct file_system_type f2fs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "f2fs",
	.mount		= f2fs_mount,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};

static int init_inodecache(void)
{
	f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
			sizeof(struct f2fs_inode_info), NULL);
	if (f2fs_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(f2fs_inode_cachep);
}

static int __init init_f2fs_fs(void)
{
	int err;

	err = init_inodecache();
	if (err)
		goto fail;
	err = create_node_manager_caches();
	if (err)
		goto fail;
	err = create_gc_caches();
	if (err)
		goto fail;
	err = create_checkpoint_caches();
	if (err)
		goto fail;
	return register_filesystem(&f2fs_fs_type);
fail:
	return err;
}

static void __exit exit_f2fs_fs(void)
{
	destroy_root_stats();
	unregister_filesystem(&f2fs_fs_type);
	destroy_checkpoint_caches();
	destroy_gc_caches();
	destroy_node_manager_caches();
	destroy_inodecache();
}

module_init(init_f2fs_fs)
module_exit(exit_f2fs_fs)

MODULE_AUTHOR("Samsung Electronics's Praesto Team");
MODULE_DESCRIPTION("Flash Friendly File System");
MODULE_LICENSE("GPL");
Commit	Line	Data
0a8165d7	1	/*
aff063e2 JK	2	* fs/f2fs/super.c
	3	*
	4	* Copyright (c) 2012 Samsung Electronics Co., Ltd.
	5	* http://www.samsung.com/
	6	*
	7	* This program is free software; you can redistribute it and/or modify
	8	* it under the terms of the GNU General Public License version 2 as
	9	* published by the Free Software Foundation.
	10	*/
	11	#include <linux/module.h>
	12	#include <linux/init.h>
	13	#include <linux/fs.h>
	14	#include <linux/statfs.h>
	15	#include <linux/proc_fs.h>
	16	#include <linux/buffer_head.h>
	17	#include <linux/backing-dev.h>
	18	#include <linux/kthread.h>
	19	#include <linux/parser.h>
	20	#include <linux/mount.h>
	21	#include <linux/seq_file.h>
	22	#include <linux/random.h>
	23	#include <linux/exportfs.h>
	24	#include <linux/f2fs_fs.h>
	25
	26	#include "f2fs.h"
	27	#include "node.h"
	28	#include "xattr.h"
	29
	30	static struct kmem_cache *f2fs_inode_cachep;
	31
	32	enum {
	33	Opt_gc_background_off,
	34	Opt_disable_roll_forward,
	35	Opt_discard,
	36	Opt_noheap,
	37	Opt_nouser_xattr,
	38	Opt_noacl,
	39	Opt_active_logs,
	40	Opt_disable_ext_identify,
	41	Opt_err,
	42	};
	43
	44	static match_table_t f2fs_tokens = {
	45	{Opt_gc_background_off, "background_gc_off"},
	46	{Opt_disable_roll_forward, "disable_roll_forward"},
	47	{Opt_discard, "discard"},
	48	{Opt_noheap, "no_heap"},
	49	{Opt_nouser_xattr, "nouser_xattr"},
	50	{Opt_noacl, "noacl"},
	51	{Opt_active_logs, "active_logs=%u"},
	52	{Opt_disable_ext_identify, "disable_ext_identify"},
	53	{Opt_err, NULL},
	54	};
	55
	56	static void init_once(void *foo)
	57	{
	58	struct f2fs_inode_info fi = (struct f2fs_inode_info ) foo;
	59
	60	memset(fi, 0, sizeof(*fi));
	61	inode_init_once(&fi->vfs_inode);
	62	}
	63
	64	static struct inode f2fs_alloc_inode(struct super_block sb)
	65	{
66	struct f2fs_inode_info *fi;
67
68	fi = kmem_cache_alloc(f2fs_inode_cachep, GFP_NOFS \| __GFP_ZERO);
69	if (!fi)
70	return NULL;
71
72	init_once((void *) fi);
73
74	/* Initilize f2fs-specific inode info */
75	fi->vfs_inode.i_version = 1;
76	atomic_set(&fi->dirty_dents, 0);
77	fi->i_current_depth = 1;
78	fi->i_advise = 0;
79	rwlock_init(&fi->ext.ext_lock);
80
81	set_inode_flag(fi, FI_NEW_INODE);
82
83	return &fi->vfs_inode;
84	}
85
86	static void f2fs_i_callback(struct rcu_head *head)
87	{
88	struct inode *inode = container_of(head, struct inode, i_rcu);
89	kmem_cache_free(f2fs_inode_cachep, F2FS_I(inode));
90	}
91
25ca923b	92	static void f2fs_destroy_inode(struct inode *inode)
aff063e2 JK	93	{
	94	call_rcu(&inode->i_rcu, f2fs_i_callback);
	95	}
	96
	97	static void f2fs_put_super(struct super_block *sb)
	98	{
	99	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	100
	101	f2fs_destroy_stats(sbi);
	102	stop_gc_thread(sbi);
	103
	104	write_checkpoint(sbi, false, true);
	105
	106	iput(sbi->node_inode);
	107	iput(sbi->meta_inode);
	108
	109	/* destroy f2fs internal modules */
	110	destroy_node_manager(sbi);
	111	destroy_segment_manager(sbi);
	112
	113	kfree(sbi->ckpt);
	114
	115	sb->s_fs_info = NULL;
	116	brelse(sbi->raw_super_buf);
	117	kfree(sbi);
	118	}
	119
	120	int f2fs_sync_fs(struct super_block *sb, int sync)
	121	{
	122	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	123	int ret = 0;
	124
	125	if (!sbi->s_dirty && !get_pages(sbi, F2FS_DIRTY_NODES))
	126	return 0;
	127
	128	if (sync)
	129	write_checkpoint(sbi, false, false);
	130
	131	return ret;
	132	}
	133
	134	static int f2fs_statfs(struct dentry dentry, struct kstatfs buf)
	135	{
	136	struct super_block *sb = dentry->d_sb;
	137	struct f2fs_sb_info *sbi = F2FS_SB(sb);
	138	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
	139	block_t total_count, user_block_count, start_count, ovp_count;
	140
	141	total_count = le64_to_cpu(sbi->raw_super->block_count);
	142	user_block_count = sbi->user_block_count;
	143	start_count = le32_to_cpu(sbi->raw_super->segment0_blkaddr);
	144	ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
	145	buf->f_type = F2FS_SUPER_MAGIC;
	146	buf->f_bsize = sbi->blocksize;
	147
	148	buf->f_blocks = total_count - start_count;
	149	buf->f_bfree = buf->f_blocks - valid_user_blocks(sbi) - ovp_count;
	150	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
	151
	152	buf->f_files = valid_inode_count(sbi);
	153	buf->f_ffree = sbi->total_node_count - valid_node_count(sbi);
	154
	155	buf->f_namelen = F2FS_MAX_NAME_LEN;
	156	buf->f_fsid.val[0] = (u32)id;
157	buf->f_fsid.val[1] = (u32)(id >> 32);
158
159	return 0;
160	}
161
162	static int f2fs_show_options(struct seq_file seq, struct dentry root)
163	{
164	struct f2fs_sb_info *sbi = F2FS_SB(root->d_sb);
165
166	if (test_opt(sbi, BG_GC))
167	seq_puts(seq, ",background_gc_on");
168	else
169	seq_puts(seq, ",background_gc_off");
170	if (test_opt(sbi, DISABLE_ROLL_FORWARD))
171	seq_puts(seq, ",disable_roll_forward");
172	if (test_opt(sbi, DISCARD))
173	seq_puts(seq, ",discard");
174	if (test_opt(sbi, NOHEAP))
175	seq_puts(seq, ",no_heap_alloc");
176	#ifdef CONFIG_F2FS_FS_XATTR
177	if (test_opt(sbi, XATTR_USER))
178	seq_puts(seq, ",user_xattr");
179	else
180	seq_puts(seq, ",nouser_xattr");
181	#endif
182	#ifdef CONFIG_F2FS_FS_POSIX_ACL
183	if (test_opt(sbi, POSIX_ACL))
184	seq_puts(seq, ",acl");
185	else
186	seq_puts(seq, ",noacl");
187	#endif
188	if (test_opt(sbi, DISABLE_EXT_IDENTIFY))
189	seq_puts(seq, ",disable_ext_indentify");
190
191	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
192
193	return 0;
194	}
195
196	static struct super_operations f2fs_sops = {
197	.alloc_inode = f2fs_alloc_inode,
198	.destroy_inode = f2fs_destroy_inode,
199	.write_inode = f2fs_write_inode,
200	.show_options = f2fs_show_options,
201	.evict_inode = f2fs_evict_inode,
202	.put_super = f2fs_put_super,
203	.sync_fs = f2fs_sync_fs,
204	.statfs = f2fs_statfs,
205	};
206
207	static struct inode f2fs_nfs_get_inode(struct super_block sb,
208	u64 ino, u32 generation)
209	{
210	struct f2fs_sb_info *sbi = F2FS_SB(sb);
211	struct inode *inode;
212
213	if (ino < F2FS_ROOT_INO(sbi))
214	return ERR_PTR(-ESTALE);
215
216	/*
217	* f2fs_iget isn't quite right if the inode is currently unallocated!
218	* However f2fs_iget currently does appropriate checks to handle stale
219	* inodes so everything is OK.
220	*/
221	inode = f2fs_iget(sb, ino);
222	if (IS_ERR(inode))
223	return ERR_CAST(inode);
224	if (generation && inode->i_generation != generation) {
225	/* we didn't find the right inode.. */
226	iput(inode);
227	return ERR_PTR(-ESTALE);
228	}
229	return inode;
230	}
231
232	static struct dentry f2fs_fh_to_dentry(struct super_block sb, struct fid *fid,
233	int fh_len, int fh_type)
234	{
235	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
236	f2fs_nfs_get_inode);
237	}
238
239	static struct dentry f2fs_fh_to_parent(struct super_block sb, struct fid *fid,
240	int fh_len, int fh_type)
241	{
242	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
243	f2fs_nfs_get_inode);
244	}
245
246	static const struct export_operations f2fs_export_ops = {
247	.fh_to_dentry = f2fs_fh_to_dentry,
248	.fh_to_parent = f2fs_fh_to_parent,
249	.get_parent = f2fs_get_parent,
250	};
251
252	static int parse_options(struct f2fs_sb_info sbi, char options)
253	{
254	substring_t args[MAX_OPT_ARGS];
255	char *p;
256	int arg = 0;
257
258	if (!options)
259	return 0;
260
261	while ((p = strsep(&options, ",")) != NULL) {
262	int token;
263	if (!*p)
264	continue;
265	/*
266	* Initialize args struct so we know whether arg was
267	* found; some options take optional arguments.
268	*/
269	args[0].to = args[0].from = NULL;
270	token = match_token(p, f2fs_tokens, args);
271
272	switch (token) {
273	case Opt_gc_background_off:
274	clear_opt(sbi, BG_GC);
275	break;
276	case Opt_disable_roll_forward:
277	set_opt(sbi, DISABLE_ROLL_FORWARD);
278	break;
279	case Opt_discard:
280	set_opt(sbi, DISCARD);
281	break;
282	case Opt_noheap:
283	set_opt(sbi, NOHEAP);
284	break;
285	#ifdef CONFIG_F2FS_FS_XATTR
286	case Opt_nouser_xattr:
287	clear_opt(sbi, XATTR_USER);
288	break;
289	#else
290	case Opt_nouser_xattr:
291	pr_info("nouser_xattr options not supported\n");
292	break;
293	#endif
294	#ifdef CONFIG_F2FS_FS_POSIX_ACL
295	case Opt_noacl:
296	clear_opt(sbi, POSIX_ACL);
297	break;
298	#else
299	case Opt_noacl:
300	pr_info("noacl options not supported\n");
301	break;
302	#endif
303	case Opt_active_logs:
304	if (args->from && match_int(args, &arg))
305	return -EINVAL;
306	if (arg != 2 && arg != 4 && arg != 6)
307	return -EINVAL;
308	sbi->active_logs = arg;
309	break;
310	case Opt_disable_ext_identify:
311	set_opt(sbi, DISABLE_EXT_IDENTIFY);
312	break;
313	default:
72ce6094 NJ	314	pr_err("Unrecognized mount option \"%s\" or missing value\n",
72ce6094 NJ	315	p);
aff063e2 JK	316	return -EINVAL;
	317	}
	318	}
	319	return 0;
	320	}
	321
	322	static loff_t max_file_size(unsigned bits)
	323	{
	324	loff_t result = ADDRS_PER_INODE;
	325	loff_t leaf_count = ADDRS_PER_BLOCK;
	326
	327	/* two direct node blocks */
	328	result += (leaf_count * 2);
	329
	330	/* two indirect node blocks */
	331	leaf_count *= NIDS_PER_BLOCK;
	332	result += (leaf_count * 2);
	333
	334	/* one double indirect node block */
	335	leaf_count *= NIDS_PER_BLOCK;
	336	result += leaf_count;
	337
	338	result <<= bits;
	339	return result;
	340	}
	341
	342	static int sanity_check_raw_super(struct f2fs_super_block *raw_super)
	343	{
	344	unsigned int blocksize;
	345
	346	if (F2FS_SUPER_MAGIC != le32_to_cpu(raw_super->magic))
	347	return 1;
	348
	349	/* Currently, support only 4KB block size */
	350	blocksize = 1 << le32_to_cpu(raw_super->log_blocksize);
	351	if (blocksize != PAGE_CACHE_SIZE)
	352	return 1;
	353	if (le32_to_cpu(raw_super->log_sectorsize) !=
	354	F2FS_LOG_SECTOR_SIZE)
	355	return 1;
	356	if (le32_to_cpu(raw_super->log_sectors_per_block) !=
	357	F2FS_LOG_SECTORS_PER_BLOCK)
	358	return 1;
	359	return 0;
	360	}
	361
	362	static int sanity_check_ckpt(struct f2fs_super_block *raw_super,
	363	struct f2fs_checkpoint *ckpt)
	364	{
	365	unsigned int total, fsmeta;
	366
	367	total = le32_to_cpu(raw_super->segment_count);
	368	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
	369	fsmeta += le32_to_cpu(raw_super->segment_count_sit);
	370	fsmeta += le32_to_cpu(raw_super->segment_count_nat);
	371	fsmeta += le32_to_cpu(ckpt->rsvd_segment_count);
	372	fsmeta += le32_to_cpu(raw_super->segment_count_ssa);
	373
	374	if (fsmeta >= total)
	375	return 1;
	376	return 0;
	377	}
	378
	379	static void init_sb_info(struct f2fs_sb_info *sbi)
380	{
381	struct f2fs_super_block *raw_super = sbi->raw_super;
382	int i;
383
384	sbi->log_sectors_per_block =
385	le32_to_cpu(raw_super->log_sectors_per_block);
386	sbi->log_blocksize = le32_to_cpu(raw_super->log_blocksize);
387	sbi->blocksize = 1 << sbi->log_blocksize;
388	sbi->log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
389	sbi->blocks_per_seg = 1 << sbi->log_blocks_per_seg;
390	sbi->segs_per_sec = le32_to_cpu(raw_super->segs_per_sec);
391	sbi->secs_per_zone = le32_to_cpu(raw_super->secs_per_zone);
392	sbi->total_sections = le32_to_cpu(raw_super->section_count);
393	sbi->total_node_count =
394	(le32_to_cpu(raw_super->segment_count_nat) / 2)
395	* sbi->blocks_per_seg * NAT_ENTRY_PER_BLOCK;
396	sbi->root_ino_num = le32_to_cpu(raw_super->root_ino);
397	sbi->node_ino_num = le32_to_cpu(raw_super->node_ino);
398	sbi->meta_ino_num = le32_to_cpu(raw_super->meta_ino);
399
400	for (i = 0; i < NR_COUNT_TYPE; i++)
401	atomic_set(&sbi->nr_pages[i], 0);
402	}
403
404	static int f2fs_fill_super(struct super_block sb, void data, int silent)
405	{
406	struct f2fs_sb_info *sbi;
407	struct f2fs_super_block *raw_super;
408	struct buffer_head *raw_super_buf;
409	struct inode *root;
410	long err = -EINVAL;
411	int i;
412
413	/* allocate memory for f2fs-specific super block info */
414	sbi = kzalloc(sizeof(struct f2fs_sb_info), GFP_KERNEL);
415	if (!sbi)
416	return -ENOMEM;
417
418	/* set a temporary block size */
419	if (!sb_set_blocksize(sb, F2FS_BLKSIZE))
420	goto free_sbi;
421
422	/* read f2fs raw super block */
423	raw_super_buf = sb_bread(sb, 0);
424	if (!raw_super_buf) {
425	err = -EIO;
426	goto free_sbi;
427	}
428	raw_super = (struct f2fs_super_block *)
429	((char *)raw_super_buf->b_data + F2FS_SUPER_OFFSET);
430
431	/* init some FS parameters */
432	sbi->active_logs = NR_CURSEG_TYPE;
433
434	set_opt(sbi, BG_GC);
435
436	#ifdef CONFIG_F2FS_FS_XATTR
437	set_opt(sbi, XATTR_USER);
438	#endif
439	#ifdef CONFIG_F2FS_FS_POSIX_ACL
440	set_opt(sbi, POSIX_ACL);
441	#endif
442	/* parse mount options */
443	if (parse_options(sbi, (char *)data))
444	goto free_sb_buf;
445
446	/* sanity checking of raw super */
447	if (sanity_check_raw_super(raw_super))
448	goto free_sb_buf;
449
25ca923b	450	sb->s_maxbytes = max_file_size(le32_to_cpu(raw_super->log_blocksize));
aff063e2 JK	451	sb->s_max_links = F2FS_LINK_MAX;
	452	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
	453
	454	sb->s_op = &f2fs_sops;
	455	sb->s_xattr = f2fs_xattr_handlers;
	456	sb->s_export_op = &f2fs_export_ops;
	457	sb->s_magic = F2FS_SUPER_MAGIC;
	458	sb->s_fs_info = sbi;
	459	sb->s_time_gran = 1;
	460	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) \|
	461	(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
	462	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
	463
	464	/* init f2fs-specific super block info */
	465	sbi->sb = sb;
	466	sbi->raw_super = raw_super;
	467	sbi->raw_super_buf = raw_super_buf;
	468	mutex_init(&sbi->gc_mutex);
	469	mutex_init(&sbi->write_inode);
	470	mutex_init(&sbi->writepages);
	471	mutex_init(&sbi->cp_mutex);
	472	for (i = 0; i < NR_LOCK_TYPE; i++)
	473	mutex_init(&sbi->fs_lock[i]);
	474	sbi->por_doing = 0;
	475	spin_lock_init(&sbi->stat_lock);
	476	init_rwsem(&sbi->bio_sem);
	477	init_sb_info(sbi);
	478
	479	/* get an inode for meta space */
	480	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
	481	if (IS_ERR(sbi->meta_inode)) {
	482	err = PTR_ERR(sbi->meta_inode);
	483	goto free_sb_buf;
	484	}
	485
	486	err = get_valid_checkpoint(sbi);
	487	if (err)
	488	goto free_meta_inode;
	489
	490	/* sanity checking of checkpoint */
	491	err = -EINVAL;
	492	if (sanity_check_ckpt(raw_super, sbi->ckpt))
	493	goto free_cp;
	494
	495	sbi->total_valid_node_count =
	496	le32_to_cpu(sbi->ckpt->valid_node_count);
	497	sbi->total_valid_inode_count =
	498	le32_to_cpu(sbi->ckpt->valid_inode_count);
	499	sbi->user_block_count = le64_to_cpu(sbi->ckpt->user_block_count);
	500	sbi->total_valid_block_count =
	501	le64_to_cpu(sbi->ckpt->valid_block_count);
	502	sbi->last_valid_block_count = sbi->total_valid_block_count;
	503	sbi->alloc_valid_block_count = 0;
	504	INIT_LIST_HEAD(&sbi->dir_inode_list);
	505	spin_lock_init(&sbi->dir_inode_lock);
	506
	507	/* init super block */
	508	if (!sb_set_blocksize(sb, sbi->blocksize))
	509	goto free_cp;
	510
	511	init_orphan_info(sbi);
	512
	513	/* setup f2fs internal modules */
	514	err = build_segment_manager(sbi);
515	if (err)
516	goto free_sm;
517	err = build_node_manager(sbi);
518	if (err)
519	goto free_nm;
520
521	build_gc_manager(sbi);
522
523	/* get an inode for node space */
524	sbi->node_inode = f2fs_iget(sb, F2FS_NODE_INO(sbi));
525	if (IS_ERR(sbi->node_inode)) {
526	err = PTR_ERR(sbi->node_inode);
527	goto free_nm;
528	}
529
530	/* if there are nt orphan nodes free them */
531	err = -EINVAL;
25ca923b	532	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
aff063e2 JK	533	recover_orphan_inodes(sbi))
	534	goto free_node_inode;
	535
	536	/* read root inode and dentry */
	537	root = f2fs_iget(sb, F2FS_ROOT_INO(sbi));
	538	if (IS_ERR(root)) {
	539	err = PTR_ERR(root);
	540	goto free_node_inode;
	541	}
	542	if (!S_ISDIR(root->i_mode) \|\| !root->i_blocks \|\| !root->i_size)
	543	goto free_root_inode;
	544
	545	sb->s_root = d_make_root(root); /* allocate root dentry */
	546	if (!sb->s_root) {
	547	err = -ENOMEM;
	548	goto free_root_inode;
	549	}
	550
	551	/* recover fsynced data */
25ca923b	552	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_UMOUNT_FLAG) &&
aff063e2 JK	553	!test_opt(sbi, DISABLE_ROLL_FORWARD))
	554	recover_fsync_data(sbi);
	555
	556	/* After POR, we can run background GC thread */
	557	err = start_gc_thread(sbi);
	558	if (err)
	559	goto fail;
	560
	561	err = f2fs_build_stats(sbi);
	562	if (err)
	563	goto fail;
	564
	565	return 0;
	566	fail:
	567	stop_gc_thread(sbi);
	568	free_root_inode:
	569	dput(sb->s_root);
	570	sb->s_root = NULL;
	571	free_node_inode:
	572	iput(sbi->node_inode);
	573	free_nm:
	574	destroy_node_manager(sbi);
	575	free_sm:
	576	destroy_segment_manager(sbi);
	577	free_cp:
	578	kfree(sbi->ckpt);
	579	free_meta_inode:
	580	make_bad_inode(sbi->meta_inode);
	581	iput(sbi->meta_inode);
	582	free_sb_buf:
	583	brelse(raw_super_buf);
	584	free_sbi:
	585	kfree(sbi);
	586	return err;
	587	}
	588
	589	static struct dentry f2fs_mount(struct file_system_type fs_type, int flags,
	590	const char dev_name, void data)
	591	{
	592	return mount_bdev(fs_type, flags, dev_name, data, f2fs_fill_super);
	593	}
	594
	595	static struct file_system_type f2fs_fs_type = {
	596	.owner = THIS_MODULE,
	597	.name = "f2fs",
	598	.mount = f2fs_mount,
	599	.kill_sb = kill_block_super,
	600	.fs_flags = FS_REQUIRES_DEV,
	601	};
	602
	603	static int init_inodecache(void)
	604	{
	605	f2fs_inode_cachep = f2fs_kmem_cache_create("f2fs_inode_cache",
	606	sizeof(struct f2fs_inode_info), NULL);
	607	if (f2fs_inode_cachep == NULL)
	608	return -ENOMEM;
	609	return 0;
	610	}
	611
	612	static void destroy_inodecache(void)
	613	{
	614	/*
	615	* Make sure all delayed rcu free inodes are flushed before we
	616	* destroy cache.
617	*/
618	rcu_barrier();
619	kmem_cache_destroy(f2fs_inode_cachep);
620	}
621
622	static int __init init_f2fs_fs(void)
623	{
624	int err;
625
626	err = init_inodecache();
627	if (err)
628	goto fail;
629	err = create_node_manager_caches();
630	if (err)
631	goto fail;
632	err = create_gc_caches();
633	if (err)
634	goto fail;
635	err = create_checkpoint_caches();
636	if (err)
637	goto fail;
638	return register_filesystem(&f2fs_fs_type);
639	fail:
640	return err;
641	}
642
643	static void __exit exit_f2fs_fs(void)
644	{
645	destroy_root_stats();
646	unregister_filesystem(&f2fs_fs_type);
647	destroy_checkpoint_caches();
648	destroy_gc_caches();
649	destroy_node_manager_caches();
650	destroy_inodecache();
651	}
652
653	module_init(init_f2fs_fs)
654	module_exit(exit_f2fs_fs)
655
656	MODULE_AUTHOR("Samsung Electronics's Praesto Team");
657	MODULE_DESCRIPTION("Flash Friendly File System");
658	MODULE_LICENSE("GPL");