#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 <asm/unaligned.h>
#ifndef CONFIG_FAT_DEFAULT_IOCHARSET
return err;
}
-static int fat_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+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;
+ int err, offset;
- err = fat_bmap(inode, iblock, &phys);
+ err = fat_bmap(inode, iblock, &phys, &mapped_blocks);
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);
+ MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private);
return -EIO;
}
- if (!((unsigned long)iblock & (MSDOS_SB(sb)->sec_per_clus - 1))) {
+
+ 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;
}
- MSDOS_I(inode)->mmu_private += sb->s_blocksize;
- err = fat_bmap(inode, iblock, &phys);
+ /* 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);
if (err)
return err;
- if (!phys)
- BUG();
+
+ 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;
}
return mpage_readpages(mapping, pages, nr_pages, fat_get_block);
}
-static int fat_prepare_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+static int fat_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
{
- return cont_prepare_write(page, from, to, fat_get_block,
- &MSDOS_I(page->mapping->host)->mmu_private);
+ *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_commit_write(struct file *file, struct page *page,
- unsigned from, unsigned to)
+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 = page->mapping->host;
- int err = generic_commit_write(file, page, from, to);
- if (!err && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {
+ 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 ->prepare_write(),
+ * 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)
{
return generic_block_bmap(mapping, block, fat_get_block);
}
-static struct address_space_operations fat_aops = {
+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,
- .prepare_write = fat_prepare_write,
- .commit_write = fat_commit_write,
+ .write_begin = fat_write_begin,
+ .write_end = fat_write_end,
+ .direct_IO = fat_direct_IO,
.bmap = _fat_bmap
};
} else { /* not a directory */
inode->i_generation |= 1;
inode->i_mode = MSDOS_MKMODE(de->attr,
- ((sbi->options.showexec &&
- !is_exec(de->ext))
+ ((sbi->options.showexec && !is_exec(de->name + 8))
? S_IRUGO|S_IWUGO : S_IRWXUGO)
& ~sbi->options.fs_fmask) | S_IFREG;
MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
inode->i_flags |= S_IMMUTABLE;
}
MSDOS_I(inode)->i_attrs = de->attr & ATTR_UNUSED;
- /* this is as close to the truth as we can get ... */
- inode->i_blksize = sbi->cluster_size;
inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
& ~((loff_t)sbi->cluster_size - 1)) >> 9;
inode->i_mtime.tv_sec =
le16_to_cpu(de->cdate)) + secs;
inode->i_ctime.tv_nsec = csecs * 10000000;
inode->i_atime.tv_sec =
- date_dos2unix(le16_to_cpu(0), le16_to_cpu(de->adate));
+ date_dos2unix(0, le16_to_cpu(de->adate));
inode->i_atime.tv_nsec = 0;
} else
inode->i_ctime = inode->i_atime = inode->i_mtime;
kfree(sbi);
}
-static kmem_cache_t *fat_inode_cachep;
+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, SLAB_KERNEL);
+ ei = kmem_cache_alloc(fat_inode_cachep, GFP_KERNEL);
if (!ei)
return NULL;
return &ei->vfs_inode;
kmem_cache_free(fat_inode_cachep, MSDOS_I(inode));
}
-static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags)
+static void init_once(void * foo, struct kmem_cache * cachep, unsigned long flags)
{
struct msdos_inode_info *ei = (struct msdos_inode_info *)foo;
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR) {
- 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);
- }
+ 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,
- init_once, NULL);
+ 0, (SLAB_RECLAIM_ACCOUNT|
+ SLAB_MEM_SPREAD),
+ init_once);
if (fat_inode_cachep == NULL)
return -ENOMEM;
return 0;
static void __exit fat_destroy_inodecache(void)
{
- if (kmem_cache_destroy(fat_inode_cachep))
- printk(KERN_INFO "fat_inode_cache: not all structures were freed\n");
+ kmem_cache_destroy(fat_inode_cachep);
}
static int fat_remount(struct super_block *sb, int *flags, char *data)
return 0;
}
-static int fat_statfs(struct super_block *sb, struct kstatfs *buf)
+static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
{
- struct msdos_sb_info *sbi = MSDOS_SB(sb);
+ struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
/* If the count of free cluster is still unknown, counts it here. */
if (sbi->free_clusters == -1) {
- int err = fat_count_free_clusters(sb);
+ int err = fat_count_free_clusters(dentry->d_sb);
if (err)
return err;
}
- buf->f_type = sb->s_magic;
+ buf->f_type = dentry->d_sb->s_magic;
buf->f_bsize = sbi->cluster_size;
buf->f_blocks = sbi->max_cluster - FAT_START_ENT;
buf->f_bfree = sbi->free_clusters;
EXPORT_SYMBOL_GPL(fat_sync_inode);
static int fat_show_options(struct seq_file *m, struct vfsmount *mnt);
-static struct super_operations fat_sops = {
+static const struct super_operations fat_sops = {
.alloc_inode = fat_alloc_inode,
.destroy_inode = fat_destroy_inode,
.write_inode = fat_write_inode,
}
if (opts->name_check != 'n')
seq_printf(m, ",check=%c", opts->name_check);
+ if (opts->usefree)
+ seq_puts(m, ",usefree");
if (opts->quiet)
seq_puts(m, ",quiet");
if (opts->showexec)
enum {
Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid,
- Opt_umask, Opt_dmask, Opt_fmask, Opt_codepage, Opt_nocase,
+ Opt_umask, Opt_dmask, Opt_fmask, Opt_codepage, Opt_usefree, Opt_nocase,
Opt_quiet, Opt_showexec, Opt_debug, Opt_immutable,
Opt_dots, Opt_nodots,
Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
- Opt_obsolate, Opt_err,
+ Opt_obsolate, Opt_flush, Opt_err,
};
static match_table_t fat_tokens = {
{Opt_dmask, "dmask=%o"},
{Opt_fmask, "fmask=%o"},
{Opt_codepage, "codepage=%u"},
+ {Opt_usefree, "usefree"},
{Opt_nocase, "nocase"},
{Opt_quiet, "quiet"},
{Opt_showexec, "showexec"},
{Opt_obsolate, "cvf_format=%20s"},
{Opt_obsolate, "cvf_options=%100s"},
{Opt_obsolate, "posix"},
- {Opt_err, NULL}
+ {Opt_flush, "flush"},
+ {Opt_err, NULL},
};
static match_table_t msdos_tokens = {
{Opt_nodots, "nodots"},
opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK = 0;
opts->utf8 = opts->unicode_xlate = 0;
opts->numtail = 1;
- opts->nocase = 0;
+ opts->usefree = opts->nocase = 0;
*debug = 0;
if (!options)
case Opt_check_n:
opts->name_check = 'n';
break;
+ case Opt_usefree:
+ opts->usefree = 1;
+ break;
case Opt_nocase:
if (!is_vfat)
opts->nocase = 1;
return 0;
opts->codepage = option;
break;
+ case Opt_flush:
+ opts->flush = 1;
+ break;
/* msdos specific */
case Opt_dots:
return -EINVAL;
}
}
- /* UTF8 doesn't provide FAT semantics */
+ /* UTF-8 doesn't provide FAT semantics */
if (!strcmp(opts->iocharset, "utf8")) {
printk(KERN_ERR "FAT: utf8 is not a recommended IO charset"
" for FAT filesystems, filesystem will be case sensitive!\n");
MSDOS_I(inode)->i_start = 0;
inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry);
}
- inode->i_blksize = sbi->cluster_size;
inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
& ~((loff_t)sbi->cluster_size - 1)) >> 9;
MSDOS_I(inode)->i_logstart = 0;
* Read the super block of an MS-DOS FS.
*/
int fat_fill_super(struct super_block *sb, void *data, int silent,
- struct inode_operations *fs_dir_inode_ops, int isvfat)
+ const struct inode_operations *fs_dir_inode_ops, int isvfat)
{
struct inode *root_inode = NULL;
struct buffer_head *bh;
long error;
char buf[50];
- sbi = kmalloc(sizeof(struct msdos_sb_info), GFP_KERNEL);
+ sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL);
if (!sbi)
return -ENOMEM;
sb->s_fs_info = sbi;
- memset(sbi, 0, sizeof(struct msdos_sb_info));
sb->s_flags |= MS_NODIRATIME;
sb->s_magic = MSDOS_SUPER_MAGIC;
}
logical_sector_size =
le16_to_cpu(get_unaligned((__le16 *)&b->sector_size));
- if (!logical_sector_size
- || (logical_sector_size & (logical_sector_size - 1))
+ if (!is_power_of_2(logical_sector_size)
|| (logical_sector_size < 512)
|| (PAGE_CACHE_SIZE < logical_sector_size)) {
if (!silent)
goto out_invalid;
}
sbi->sec_per_clus = b->sec_per_clus;
- if (!sbi->sec_per_clus
- || (sbi->sec_per_clus & (sbi->sec_per_clus - 1))) {
+ if (!is_power_of_2(sbi->sec_per_clus)) {
if (!silent)
printk(KERN_ERR "FAT: bogus sectors per cluster %u\n",
sbi->sec_per_clus);
le32_to_cpu(fsinfo->signature2),
sbi->fsinfo_sector);
} else {
- sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters);
+ if (sbi->options.usefree)
+ sbi->free_clusters =
+ le32_to_cpu(fsinfo->free_clusters);
sbi->prev_free = le32_to_cpu(fsinfo->next_cluster);
}
EXPORT_SYMBOL_GPL(fat_fill_super);
-int __init fat_cache_init(void);
-void fat_cache_destroy(void);
+/*
+ * helper function for fat_flush_inodes. This writes both the inode
+ * and the file data blocks, waiting for in flight data blocks before
+ * the start of the call. It does not wait for any io started
+ * during the call
+ */
+static int writeback_inode(struct inode *inode)
+{
+
+ int ret;
+ struct address_space *mapping = inode->i_mapping;
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_NONE,
+ .nr_to_write = 0,
+ };
+ /* if we used WB_SYNC_ALL, sync_inode waits for the io for the
+ * inode to finish. So WB_SYNC_NONE is sent down to sync_inode
+ * and filemap_fdatawrite is used for the data blocks
+ */
+ ret = sync_inode(inode, &wbc);
+ if (!ret)
+ ret = filemap_fdatawrite(mapping);
+ return ret;
+}
+
+/*
+ * write data and metadata corresponding to i1 and i2. The io is
+ * started but we do not wait for any of it to finish.
+ *
+ * filemap_flush is used for the block device, so if there is a dirty
+ * page for a block already in flight, we will not wait and start the
+ * io over again
+ */
+int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2)
+{
+ int ret = 0;
+ if (!MSDOS_SB(sb)->options.flush)
+ return 0;
+ if (i1)
+ ret = writeback_inode(i1);
+ if (!ret && i2)
+ ret = writeback_inode(i2);
+ if (!ret) {
+ struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
+ ret = filemap_flush(mapping);
+ }
+ return ret;
+}
+EXPORT_SYMBOL_GPL(fat_flush_inodes);
static int __init init_fat_fs(void)
{