inode.c

linux环境下基于FAT的文件系统的通用代码

/*
 *  linux/fs/fat/inode.c
 *
 *  Written 1992,1993 by Werner Almesberger
 *  VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner
 *  Rewritten for the constant inumbers support by Al Viro
 *
 *  Fixes:
 *
 *	Max Cohan: Fixed invalid FSINFO offset when info_sector is 0
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/pagemap.h>
#include <linux/mpage.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/parser.h>
#include <linux/uio.h>
#include <linux/writeback.h>
#include <linux/log2.h>
#include <linux/hash.h>
#include <asm/unaligned.h>
#include "fat.h"

#ifndef CONFIG_FAT_DEFAULT_IOCHARSET
/* if user don't select VFAT, this is undefined. */
#define CONFIG_FAT_DEFAULT_IOCHARSET	""
#endif

static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE;
static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET;


static int fat_add_cluster(struct inode *inode)
{
	int err, cluster;

	err = fat_alloc_clusters(inode, &cluster, 1);
	if (err)
		return err;
	/* FIXME: this cluster should be added after data of this
	 * cluster is writed */
	err = fat_chain_add(inode, cluster, 1);
	if (err)
		fat_free_clusters(inode, cluster);
	return err;
}

static inline int __fat_get_block(struct inode *inode, sector_t iblock,
				  unsigned long *max_blocks,
				  struct buffer_head *bh_result, int create)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	unsigned long mapped_blocks;
	sector_t phys;
	int err, offset;

	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
	if (err)
		return err;
	if (phys) {
		map_bh(bh_result, sb, phys);
		*max_blocks = min(mapped_blocks, *max_blocks);
		return 0;
	}
	if (!create)
		return 0;

	if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) {
		fat_fs_panic(sb, "corrupted file size (i_pos %lld, %lld)",
			MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private);
		return -EIO;
	}

	offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
	if (!offset) {
		/* TODO: multiple cluster allocation would be desirable. */
		err = fat_add_cluster(inode);
		if (err)
			return err;
	}
	/* available blocks on this cluster */
	mapped_blocks = sbi->sec_per_clus - offset;

	*max_blocks = min(mapped_blocks, *max_blocks);
	MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;

	err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create);
	if (err)
		return err;

	BUG_ON(!phys);
	BUG_ON(*max_blocks != mapped_blocks);
	set_buffer_new(bh_result);
	map_bh(bh_result, sb, phys);

	return 0;
}

static int fat_get_block(struct inode *inode, sector_t iblock,
			 struct buffer_head *bh_result, int create)
{
	struct super_block *sb = inode->i_sb;
	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
	int err;

	err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create);
	if (err)
		return err;
	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
	return 0;
}

static int fat_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page, fat_get_block, wbc);
}

static int fat_writepages(struct address_space *mapping,
			  struct writeback_control *wbc)
{
	return mpage_writepages(mapping, wbc, fat_get_block);
}

static int fat_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, fat_get_block);
}

static int fat_readpages(struct file *file, struct address_space *mapping,
			 struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, fat_get_block);
}

static int fat_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	*pagep = NULL;
	return cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
				fat_get_block,
				&MSDOS_I(mapping->host)->mmu_private);
}

static int fat_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *pagep, void *fsdata)
{
	struct inode *inode = mapping->host;
	int err;
	err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata);
	if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {
		inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
		MSDOS_I(inode)->i_attrs |= ATTR_ARCH;
		mark_inode_dirty(inode);
	}
	return err;
}

static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
			     const struct iovec *iov,
			     loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;

	if (rw == WRITE) {
		/*
		 * FIXME: blockdev_direct_IO() doesn't use ->write_begin(),
		 * so we need to update the ->mmu_private to block boundary.
		 *
		 * But we must fill the remaining area or hole by nul for
		 * updating ->mmu_private.
		 *
		 * Return 0, and fallback to normal buffered write.
		 */
		loff_t size = offset + iov_length(iov, nr_segs);
		if (MSDOS_I(inode)->mmu_private < size)
			return 0;
	}

	/*
	 * FAT need to use the DIO_LOCKING for avoiding the race
	 * condition of fat_get_block() and ->truncate().
	 */
	return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				  offset, nr_segs, fat_get_block, NULL);
}

static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
{
	sector_t blocknr;

	/* fat_get_cluster() assumes the requested blocknr isn't truncated. */
	down_read(&mapping->host->i_alloc_sem);
	blocknr = generic_block_bmap(mapping, block, fat_get_block);
	up_read(&mapping->host->i_alloc_sem);

	return blocknr;
}

static const struct address_space_operations fat_aops = {
	.readpage	= fat_readpage,
	.readpages	= fat_readpages,
	.writepage	= fat_writepage,
	.writepages	= fat_writepages,
	.sync_page	= block_sync_page,
	.write_begin	= fat_write_begin,
	.write_end	= fat_write_end,
	.direct_IO	= fat_direct_IO,
	.bmap		= _fat_bmap
};

/*
 * New FAT inode stuff. We do the following:
 *	a) i_ino is constant and has nothing with on-disk location.
 *	b) FAT manages its own cache of directory entries.
 *	c) *This* cache is indexed by on-disk location.
 *	d) inode has an associated directory entry, all right, but
 *		it may be unhashed.
 *	e) currently entries are stored within struct inode. That should
 *		change.
 *	f) we deal with races in the following way:
 *		1. readdir() and lookup() do FAT-dir-cache lookup.
 *		2. rename() unhashes the F-d-c entry and rehashes it in
 *			a new place.
 *		3. unlink() and rmdir() unhash F-d-c entry.
 *		4. fat_write_inode() checks whether the thing is unhashed.
 *			If it is we silently return. If it isn't we do bread(),
 *			check if the location is still valid and retry if it
 *			isn't. Otherwise we do changes.
 *		5. Spinlock is used to protect hash/unhash/location check/lookup
 *		6. fat_clear_inode() unhashes the F-d-c entry.
 *		7. lookup() and readdir() do igrab() if they find a F-d-c entry
 *			and consider negative result as cache miss.
 */

static void fat_hash_init(struct super_block *sb)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	int i;

	spin_lock_init(&sbi->inode_hash_lock);
	for (i = 0; i < FAT_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&sbi->inode_hashtable[i]);
}

static inline unsigned long fat_hash(loff_t i_pos)
{
	return hash_32(i_pos, FAT_HASH_BITS);
}

void fat_attach(struct inode *inode, loff_t i_pos)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);

	spin_lock(&sbi->inode_hash_lock);
	MSDOS_I(inode)->i_pos = i_pos;
	hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head);
	spin_unlock(&sbi->inode_hash_lock);
}
EXPORT_SYMBOL_GPL(fat_attach);

void fat_detach(struct inode *inode)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	spin_lock(&sbi->inode_hash_lock);
	MSDOS_I(inode)->i_pos = 0;
	hlist_del_init(&MSDOS_I(inode)->i_fat_hash);
	spin_unlock(&sbi->inode_hash_lock);
}
EXPORT_SYMBOL_GPL(fat_detach);

struct inode *fat_iget(struct super_block *sb, loff_t i_pos)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos);
	struct hlist_node *_p;
	struct msdos_inode_info *i;
	struct inode *inode = NULL;

	spin_lock(&sbi->inode_hash_lock);
	hlist_for_each_entry(i, _p, head, i_fat_hash) {
		BUG_ON(i->vfs_inode.i_sb != sb);
		if (i->i_pos != i_pos)
			continue;
		inode = igrab(&i->vfs_inode);
		if (inode)
			break;
	}
	spin_unlock(&sbi->inode_hash_lock);
	return inode;
}

static int is_exec(unsigned char *extension)
{
	unsigned char *exe_extensions = "EXECOMBAT", *walk;

	for (walk = exe_extensions; *walk; walk += 3)
		if (!strncmp(extension, walk, 3))
			return 1;
	return 0;
}

static int fat_calc_dir_size(struct inode *inode)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	int ret, fclus, dclus;

	inode->i_size = 0;
	if (MSDOS_I(inode)->i_start == 0)
		return 0;

	ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus);
	if (ret < 0)
		return ret;
	inode->i_size = (fclus + 1) << sbi->cluster_bits;

	return 0;
}

/* doesn't deal with root inode */
static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	int error;

	MSDOS_I(inode)->i_pos = 0;
	inode->i_uid = sbi->options.fs_uid;
	inode->i_gid = sbi->options.fs_gid;
	inode->i_version++;
	inode->i_generation = get_seconds();

	if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) {
		inode->i_generation &= ~1;
		inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO);
		inode->i_op = sbi->dir_ops;
		inode->i_fop = &fat_dir_operations;

		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
		if (sbi->fat_bits == 32)
			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);

		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
		error = fat_calc_dir_size(inode);
		if (error < 0)
			return error;
		MSDOS_I(inode)->mmu_private = inode->i_size;

		inode->i_nlink = fat_subdirs(inode);
	} else { /* not a directory */
		inode->i_generation |= 1;
		inode->i_mode = fat_make_mode(sbi, de->attr,
			((sbi->options.showexec && !is_exec(de->name + 8))
			 ? S_IRUGO|S_IWUGO : S_IRWXUGO));
		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
		if (sbi->fat_bits == 32)
			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);

		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
		inode->i_size = le32_to_cpu(de->size);
		inode->i_op = &fat_file_inode_operations;
		inode->i_fop = &fat_file_operations;
		inode->i_mapping->a_ops = &fat_aops;
		MSDOS_I(inode)->mmu_private = inode->i_size;
	}
	if (de->attr & ATTR_SYS) {
		if (sbi->options.sys_immutable)
			inode->i_flags |= S_IMMUTABLE;
	}
	fat_save_attrs(inode, de->attr);

	inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
			   & ~((loff_t)sbi->cluster_size - 1)) >> 9;

	fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0);
	if (sbi->options.isvfat) {
		fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime,
				  de->cdate, de->ctime_cs);
		fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0);
	} else
		inode->i_ctime = inode->i_atime = inode->i_mtime;

	return 0;
}

struct inode *fat_build_inode(struct super_block *sb,
			struct msdos_dir_entry *de, loff_t i_pos)
{
	struct inode *inode;
	int err;

	inode = fat_iget(sb, i_pos);
	if (inode)
		goto out;
	inode = new_inode(sb);
	if (!inode) {
		inode = ERR_PTR(-ENOMEM);
		goto out;
	}
	inode->i_ino = iunique(sb, MSDOS_ROOT_INO);
	inode->i_version = 1;
	err = fat_fill_inode(inode, de);
	if (err) {
		iput(inode);
		inode = ERR_PTR(err);
		goto out;
	}
	fat_attach(inode, i_pos);
	insert_inode_hash(inode);
out:
	return inode;
}

EXPORT_SYMBOL_GPL(fat_build_inode);

static void fat_delete_inode(struct inode *inode)
{
	truncate_inode_pages(&inode->i_data, 0);
	inode->i_size = 0;
	fat_truncate(inode);
	clear_inode(inode);
}

static void fat_clear_inode(struct inode *inode)
{
	fat_cache_inval_inode(inode);
	fat_detach(inode);
}

static void fat_write_super(struct super_block *sb)
{
	sb->s_dirt = 0;

	if (!(sb->s_flags & MS_RDONLY))
		fat_clusters_flush(sb);
}

static void fat_put_super(struct super_block *sb)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);

	if (sbi->nls_disk) {
		unload_nls(sbi->nls_disk);
		sbi->nls_disk = NULL;
		sbi->options.codepage = fat_default_codepage;
	}
	if (sbi->nls_io) {
		unload_nls(sbi->nls_io);
		sbi->nls_io = NULL;
	}
	if (sbi->options.iocharset != fat_default_iocharset) {
		kfree(sbi->options.iocharset);
		sbi->options.iocharset = fat_default_iocharset;
	}

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

static struct kmem_cache *fat_inode_cachep;

static struct inode *fat_alloc_inode(struct super_block *sb)
{
	struct msdos_inode_info *ei;
	ei = kmem_cache_alloc(fat_inode_cachep, GFP_NOFS);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void fat_destroy_inode(struct inode *inode)
{
	kmem_cache_free(fat_inode_cachep, MSDOS_I(inode));
}

static void init_once(void *foo)
{
	struct msdos_inode_info *ei = (struct msdos_inode_info *)foo;

	spin_lock_init(&ei->cache_lru_lock);
	ei->nr_caches = 0;
	ei->cache_valid_id = FAT_CACHE_VALID + 1;
	INIT_LIST_HEAD(&ei->cache_lru);
	INIT_HLIST_NODE(&ei->i_fat_hash);
	inode_init_once(&ei->vfs_inode);
}

static int __init fat_init_inodecache(void)
{
	fat_inode_cachep = kmem_cache_create("fat_inode_cache",
					     sizeof(struct msdos_inode_info),
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
					     init_once);
	if (fat_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}