diff options
Diffstat (limited to 'fs/fat')
| -rw-r--r-- | fs/fat/Kconfig | 100 | ||||
| -rw-r--r-- | fs/fat/Makefile | 6 | ||||
| -rw-r--r-- | fs/fat/cache.c | 58 | ||||
| -rw-r--r-- | fs/fat/dir.c | 698 | ||||
| -rw-r--r-- | fs/fat/fat.h | 422 | ||||
| -rw-r--r-- | fs/fat/fatent.c | 106 | ||||
| -rw-r--r-- | fs/fat/file.c | 492 | ||||
| -rw-r--r-- | fs/fat/inode.c | 1217 | ||||
| -rw-r--r-- | fs/fat/misc.c | 229 | ||||
| -rw-r--r-- | fs/fat/namei_msdos.c | 686 | ||||
| -rw-r--r-- | fs/fat/namei_vfat.c | 1089 | ||||
| -rw-r--r-- | fs/fat/nfs.c | 301 |
12 files changed, 4332 insertions, 1072 deletions
diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig new file mode 100644 index 00000000000..182f9ffe2b5 --- /dev/null +++ b/fs/fat/Kconfig @@ -0,0 +1,100 @@ +config FAT_FS + tristate + select NLS + help + If you want to use one of the FAT-based file systems (the MS-DOS and + VFAT (Windows 95) file systems), then you must say Y or M here + to include FAT support. You will then be able to mount partitions or + diskettes with FAT-based file systems and transparently access the + files on them, i.e. MSDOS files will look and behave just like all + other Unix files. + + This FAT support is not a file system in itself, it only provides + the foundation for the other file systems. You will have to say Y or + M to at least one of "MSDOS fs support" or "VFAT fs support" in + order to make use of it. + + Another way to read and write MSDOS floppies and hard drive + partitions from within Linux (but not transparently) is with the + mtools ("man mtools") program suite. You don't need to say Y here in + order to do that. + + If you need to move large files on floppies between a DOS and a + Linux box, say Y here, mount the floppy under Linux with an MSDOS + file system and use GNU tar's M option. GNU tar is a program + available for Unix and DOS ("man tar" or "info tar"). + + The FAT support will enlarge your kernel by about 37 KB. If unsure, + say Y. + + To compile this as a module, choose M here: the module will be called + fat. Note that if you compile the FAT support as a module, you + cannot compile any of the FAT-based file systems into the kernel + -- they will have to be modules as well. + +config MSDOS_FS + tristate "MSDOS fs support" + select FAT_FS + help + This allows you to mount MSDOS partitions of your hard drive (unless + they are compressed; to access compressed MSDOS partitions under + Linux, you can either use the DOS emulator DOSEMU, described in the + DOSEMU-HOWTO, available from + <http://www.tldp.org/docs.html#howto>, or try dmsdosfs in + <ftp://ibiblio.org/pub/Linux/system/filesystems/dosfs/>. If you + intend to use dosemu with a non-compressed MSDOS partition, say Y + here) and MSDOS floppies. This means that file access becomes + transparent, i.e. the MSDOS files look and behave just like all + other Unix files. + + If you have Windows 95 or Windows NT installed on your MSDOS + partitions, you should use the VFAT file system (say Y to "VFAT fs + support" below), or you will not be able to see the long filenames + generated by Windows 95 / Windows NT. + + This option will enlarge your kernel by about 7 KB. If unsure, + answer Y. This will only work if you said Y to "DOS FAT fs support" + as well. To compile this as a module, choose M here: the module will + be called msdos. + +config VFAT_FS + tristate "VFAT (Windows-95) fs support" + select FAT_FS + help + This option provides support for normal Windows file systems with + long filenames. That includes non-compressed FAT-based file systems + used by Windows 95, Windows 98, Windows NT 4.0, and the Unix + programs from the mtools package. + + The VFAT support enlarges your kernel by about 10 KB and it only + works if you said Y to the "DOS FAT fs support" above. Please read + the file <file:Documentation/filesystems/vfat.txt> for details. If + unsure, say Y. + + To compile this as a module, choose M here: the module will be called + vfat. + +config FAT_DEFAULT_CODEPAGE + int "Default codepage for FAT" + depends on MSDOS_FS || VFAT_FS + default 437 + help + This option should be set to the codepage of your FAT filesystems. + It can be overridden with the "codepage" mount option. + See <file:Documentation/filesystems/vfat.txt> for more information. + +config FAT_DEFAULT_IOCHARSET + string "Default iocharset for FAT" + depends on VFAT_FS + default "iso8859-1" + help + Set this to the default input/output character set you'd + like FAT to use. It should probably match the character set + that most of your FAT filesystems use, and can be overridden + with the "iocharset" mount option for FAT filesystems. + Note that "utf8" is not recommended for FAT filesystems. + If unsure, you shouldn't set "utf8" here. + See <file:Documentation/filesystems/vfat.txt> for more information. + + Enable any character sets you need in File Systems/Native Language + Support. diff --git a/fs/fat/Makefile b/fs/fat/Makefile index bfb5f06cf2c..964b634f666 100644 --- a/fs/fat/Makefile +++ b/fs/fat/Makefile @@ -3,5 +3,9 @@ # obj-$(CONFIG_FAT_FS) += fat.o +obj-$(CONFIG_VFAT_FS) += vfat.o +obj-$(CONFIG_MSDOS_FS) += msdos.o -fat-objs := cache.o dir.o fatent.o file.o inode.o misc.o +fat-y := cache.o dir.o fatent.o file.o inode.o misc.o nfs.o +vfat-y := namei_vfat.o +msdos-y := namei_msdos.o diff --git a/fs/fat/cache.c b/fs/fat/cache.c index 639b3b4f86d..91ad9e1c944 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -9,8 +9,9 @@ */ #include <linux/fs.h> -#include <linux/msdos_fs.h> +#include <linux/slab.h> #include <linux/buffer_head.h> +#include "fat.h" /* this must be > 0. */ #define FAT_MAX_CACHE 8 @@ -36,7 +37,7 @@ static inline int fat_max_cache(struct inode *inode) static struct kmem_cache *fat_cache_cachep; -static void init_once(struct kmem_cache *cachep, void *foo) +static void init_once(void *foo) { struct fat_cache *cache = (struct fat_cache *)foo; @@ -61,7 +62,7 @@ void fat_cache_destroy(void) static inline struct fat_cache *fat_cache_alloc(struct inode *inode) { - return kmem_cache_alloc(fat_cache_cachep, GFP_KERNEL); + return kmem_cache_alloc(fat_cache_cachep, GFP_NOFS); } static inline void fat_cache_free(struct fat_cache *cache) @@ -150,6 +151,13 @@ static void fat_cache_add(struct inode *inode, struct fat_cache_id *new) spin_unlock(&MSDOS_I(inode)->cache_lru_lock); tmp = fat_cache_alloc(inode); + if (!tmp) { + spin_lock(&MSDOS_I(inode)->cache_lru_lock); + MSDOS_I(inode)->nr_caches--; + spin_unlock(&MSDOS_I(inode)->cache_lru_lock); + return; + } + spin_lock(&MSDOS_I(inode)->cache_lru_lock); cache = fat_cache_merge(inode, new); if (cache != NULL) { @@ -182,7 +190,8 @@ static void __fat_cache_inval_inode(struct inode *inode) struct fat_cache *cache; while (!list_empty(&i->cache_lru)) { - cache = list_entry(i->cache_lru.next, struct fat_cache, cache_list); + cache = list_entry(i->cache_lru.next, + struct fat_cache, cache_list); list_del_init(&cache->cache_list); i->nr_caches--; fat_cache_free(cache); @@ -241,9 +250,10 @@ int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) while (*fclus < cluster) { /* prevent the infinite loop of cluster chain */ if (*fclus > limit) { - fat_fs_panic(sb, "%s: detected the cluster chain loop" - " (i_pos %lld)", __FUNCTION__, - MSDOS_I(inode)->i_pos); + fat_fs_error_ratelimit(sb, + "%s: detected the cluster chain loop" + " (i_pos %lld)", __func__, + MSDOS_I(inode)->i_pos); nr = -EIO; goto out; } @@ -252,9 +262,10 @@ int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) if (nr < 0) goto out; else if (nr == FAT_ENT_FREE) { - fat_fs_panic(sb, "%s: invalid cluster chain" - " (i_pos %lld)", __FUNCTION__, - MSDOS_I(inode)->i_pos); + fat_fs_error_ratelimit(sb, + "%s: invalid cluster chain (i_pos %lld)", + __func__, + MSDOS_I(inode)->i_pos); nr = -EIO; goto out; } else if (nr == FAT_ENT_EOF) { @@ -285,18 +296,20 @@ static int fat_bmap_cluster(struct inode *inode, int cluster) if (ret < 0) return ret; else if (ret == FAT_ENT_EOF) { - fat_fs_panic(sb, "%s: request beyond EOF (i_pos %lld)", - __FUNCTION__, MSDOS_I(inode)->i_pos); + fat_fs_error(sb, "%s: request beyond EOF (i_pos %lld)", + __func__, MSDOS_I(inode)->i_pos); return -EIO; } return dclus; } int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, - unsigned long *mapped_blocks) + unsigned long *mapped_blocks, int create) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); + const unsigned long blocksize = sb->s_blocksize; + const unsigned char blocksize_bits = sb->s_blocksize_bits; sector_t last_block; int cluster, offset; @@ -309,10 +322,21 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, } return 0; } - last_block = (MSDOS_I(inode)->mmu_private + (sb->s_blocksize - 1)) - >> sb->s_blocksize_bits; - if (sector >= last_block) - return 0; + + last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits; + if (sector >= last_block) { + if (!create) + return 0; + + /* + * ->mmu_private can access on only allocation path. + * (caller must hold ->i_mutex) + */ + last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1)) + >> blocksize_bits; + if (sector >= last_block) + return 0; + } cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits); offset = sector & (sbi->sec_per_clus - 1); diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 72cbcd61bd9..3963ede84eb 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -16,12 +16,29 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/time.h> -#include <linux/msdos_fs.h> -#include <linux/dirent.h> -#include <linux/smp_lock.h> #include <linux/buffer_head.h> #include <linux/compat.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include "fat.h" + +/* + * Maximum buffer size of short name. + * [(MSDOS_NAME + '.') * max one char + nul] + * For msdos style, ['.' (hidden) + MSDOS_NAME + '.' + nul] + */ +#define FAT_MAX_SHORT_SIZE ((MSDOS_NAME + 1) * NLS_MAX_CHARSET_SIZE + 1) +/* + * Maximum buffer size of unicode chars from slots. + * [(max longname slots * 13 (size in a slot) + nul) * sizeof(wchar_t)] + */ +#define FAT_MAX_UNI_CHARS ((MSDOS_SLOTS - 1) * 13 + 1) +#define FAT_MAX_UNI_SIZE (FAT_MAX_UNI_CHARS * sizeof(wchar_t)) + +static inline unsigned char fat_tolower(unsigned char c) +{ + return ((c >= 'A') && (c <= 'Z')) ? c+32 : c; +} static inline loff_t fat_make_i_pos(struct super_block *sb, struct buffer_head *bh, @@ -78,7 +95,7 @@ next: *bh = NULL; iblock = *pos >> sb->s_blocksize_bits; - err = fat_bmap(dir, iblock, &phys, &mapped_blocks); + err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0); if (err || !phys) return -1; /* beyond EOF or error */ @@ -86,8 +103,8 @@ next: *bh = sb_bread(sb, phys); if (*bh == NULL) { - printk(KERN_ERR "FAT: Directory bread(block %llu) failed\n", - (unsigned long long)phys); + fat_msg_ratelimit(sb, KERN_ERR, + "Directory bread(block %llu) failed", (llu)phys); /* skip this block */ *pos = (iblock + 1) << sb->s_blocksize_bits; goto next; @@ -106,7 +123,8 @@ static inline int fat_get_entry(struct inode *dir, loff_t *pos, { /* Fast stuff first */ if (*bh && *de && - (*de - (struct msdos_dir_entry *)(*bh)->b_data) < MSDOS_SB(dir->i_sb)->dir_per_block - 1) { + (*de - (struct msdos_dir_entry *)(*bh)->b_data) < + MSDOS_SB(dir->i_sb)->dir_per_block - 1) { *pos += sizeof(struct msdos_dir_entry); (*de)++; return 0; @@ -124,43 +142,55 @@ static inline int fat_get_entry(struct inode *dir, loff_t *pos, * but ignore that right now. * Ahem... Stack smashing in ring 0 isn't fun. Fixed. */ -static int uni16_to_x8(unsigned char *ascii, wchar_t *uni, int uni_xlate, - struct nls_table *nls) +static int uni16_to_x8(struct super_block *sb, unsigned char *ascii, + const wchar_t *uni, int len, struct nls_table *nls) { - wchar_t *ip, ec; - unsigned char *op, nc; + int uni_xlate = MSDOS_SB(sb)->options.unicode_xlate; + const wchar_t *ip; + wchar_t ec; + unsigned char *op; int charlen; - int k; ip = uni; op = ascii; - while (*ip) { + while (*ip && ((len - NLS_MAX_CHARSET_SIZE) > 0)) { ec = *ip++; - if ( (charlen = nls->uni2char(ec, op, NLS_MAX_CHARSET_SIZE)) > 0) { + charlen = nls->uni2char(ec, op, NLS_MAX_CHARSET_SIZE); + if (charlen > 0) { op += charlen; + len -= charlen; } else { if (uni_xlate == 1) { - *op = ':'; - for (k = 4; k > 0; k--) { - nc = ec & 0xF; - op[k] = nc > 9 ? nc + ('a' - 10) - : nc + '0'; - ec >>= 4; - } - op += 5; + *op++ = ':'; + op = hex_byte_pack(op, ec >> 8); + op = hex_byte_pack(op, ec); + len -= 5; } else { *op++ = '?'; + len--; } } - /* We have some slack there, so it's OK */ - if (op>ascii+256) { - op = ascii + 256; - break; - } } + + if (unlikely(*ip)) { + fat_msg(sb, KERN_WARNING, + "filename was truncated while converting."); + } + *op = 0; - return (op - ascii); + return op - ascii; +} + +static inline int fat_uni_to_x8(struct super_block *sb, const wchar_t *uni, + unsigned char *buf, int size) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + if (sbi->options.utf8) + return utf16s_to_utf8s(uni, FAT_MAX_UNI_CHARS, + UTF16_HOST_ENDIAN, buf, size); + else + return uni16_to_x8(sb, buf, uni, size, sbi->nls_io); } static inline int @@ -177,7 +207,8 @@ fat_short2uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *uni) } static inline int -fat_short2lower_uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *uni) +fat_short2lower_uni(struct nls_table *t, unsigned char *c, + int clen, wchar_t *uni) { int charlen; wchar_t wc; @@ -192,7 +223,8 @@ fat_short2lower_uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *un if (!nc) nc = *c; - if ( (charlen = t->char2uni(&nc, 1, uni)) < 0) { + charlen = t->char2uni(&nc, 1, uni); + if (charlen < 0) { *uni = 0x003f; /* a question mark */ charlen = 1; } @@ -223,6 +255,19 @@ fat_shortname2uni(struct nls_table *nls, unsigned char *buf, int buf_size, return len; } +static inline int fat_name_match(struct msdos_sb_info *sbi, + const unsigned char *a, int a_len, + const unsigned char *b, int b_len) +{ + if (a_len != b_len) + return 0; + + if (sbi->options.name_check != 's') + return !nls_strnicmp(sbi->nls_io, a, b, a_len); + else + return !memcmp(a, b, a_len); +} + enum { PARSE_INVALID = 1, PARSE_NOT_LONGNAME, PARSE_EOF, }; /** @@ -243,7 +288,7 @@ static int fat_parse_long(struct inode *dir, loff_t *pos, unsigned char id, slot, slots, alias_checksum; if (!*unicode) { - *unicode = (wchar_t *)__get_free_page(GFP_KERNEL); + *unicode = __getname(); if (!*unicode) { brelse(*bh); return -ENOMEM; @@ -297,9 +342,126 @@ parse_long: return 0; } +/** + * fat_parse_short - Parse MS-DOS (short) directory entry. + * @sb: superblock + * @de: directory entry to parse + * @name: FAT_MAX_SHORT_SIZE array in which to place extracted name + * @dot_hidden: Nonzero == prepend '.' to names with ATTR_HIDDEN + * + * Returns the number of characters extracted into 'name'. + */ +static int fat_parse_short(struct super_block *sb, + const struct msdos_dir_entry *de, + unsigned char *name, int dot_hidden) +{ + const struct msdos_sb_info *sbi = MSDOS_SB(sb); + int isvfat = sbi->options.isvfat; + int nocase = sbi->options.nocase; + unsigned short opt_shortname = sbi->options.shortname; + struct nls_table *nls_disk = sbi->nls_disk; + wchar_t uni_name[14]; + unsigned char c, work[MSDOS_NAME]; + unsigned char *ptname = name; + int chi, chl, i, j, k; + int dotoffset = 0; + int name_len = 0, uni_len = 0; + + if (!isvfat && dot_hidden && (de->attr & ATTR_HIDDEN)) { + *ptname++ = '.'; + dotoffset = 1; + } + + memcpy(work, de->name, sizeof(work)); + /* see namei.c, msdos_format_name */ + if (work[0] == 0x05) + work[0] = 0xE5; + + /* Filename */ + for (i = 0, j = 0; i < 8;) { + c = work[i]; + if (!c) + break; + chl = fat_shortname2uni(nls_disk, &work[i], 8 - i, + &uni_name[j++], opt_shortname, + de->lcase & CASE_LOWER_BASE); + if (chl <= 1) { + if (!isvfat) + ptname[i] = nocase ? c : fat_tolower(c); + i++; + if (c != ' ') { + name_len = i; + uni_len = j; + } + } else { + uni_len = j; + if (isvfat) + i += min(chl, 8-i); + else { + for (chi = 0; chi < chl && i < 8; chi++, i++) + ptname[i] = work[i]; + } + if (chl) + name_len = i; + } + } + + i = name_len; + j = uni_len; + fat_short2uni(nls_disk, ".", 1, &uni_name[j++]); + if (!isvfat) + ptname[i] = '.'; + i++; + + /* Extension */ + for (k = 8; k < MSDOS_NAME;) { + c = work[k]; + if (!c) + break; + chl = fat_shortname2uni(nls_disk, &work[k], MSDOS_NAME - k, + &uni_name[j++], opt_shortname, + de->lcase & CASE_LOWER_EXT); + if (chl <= 1) { + k++; + if (!isvfat) + ptname[i] = nocase ? c : fat_tolower(c); + i++; + if (c != ' ') { + name_len = i; + uni_len = j; + } + } else { + uni_len = j; + if (isvfat) { + int offset = min(chl, MSDOS_NAME-k); + k += offset; + i += offset; + } else { + for (chi = 0; chi < chl && k < MSDOS_NAME; + chi++, i++, k++) { + ptname[i] = work[k]; + } + } + if (chl) + name_len = i; + } + } + + if (name_len > 0) { + name_len += dotoffset; + + if (sbi->options.isvfat) { + uni_name[uni_len] = 0x0000; + name_len = fat_uni_to_x8(sb, uni_name, name, + FAT_MAX_SHORT_SIZE); + } + } + + return name_len; +} + /* - * Return values: negative -> error, 0 -> not found, positive -> found, - * value is the total amount of slots, including the shortname entry. + * Return values: negative -> error/not found, 0 -> found. */ int fat_search_long(struct inode *inode, const unsigned char *name, int name_len, struct fat_slot_info *sinfo) @@ -308,23 +470,16 @@ int fat_search_long(struct inode *inode, const unsigned char *name, struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh = NULL; struct msdos_dir_entry *de; - struct nls_table *nls_io = sbi->nls_io; - struct nls_table *nls_disk = sbi->nls_disk; - wchar_t bufuname[14]; - unsigned char xlate_len, nr_slots; + unsigned char nr_slots; wchar_t *unicode = NULL; - unsigned char work[MSDOS_NAME], bufname[260]; /* 256 + 4 */ - int uni_xlate = sbi->options.unicode_xlate; - int utf8 = sbi->options.utf8; - int anycase = (sbi->options.name_check != 's'); - unsigned short opt_shortname = sbi->options.shortname; + unsigned char bufname[FAT_MAX_SHORT_SIZE]; loff_t cpos = 0; - int chl, i, j, last_u, err; + int err, len; err = -ENOENT; - while(1) { + while (1) { if (fat_get_entry(inode, &cpos, &bh, &de) == -1) - goto EODir; + goto end_of_dir; parse_record: nr_slots = 0; if (de->name[0] == DELETED_FLAG) @@ -336,78 +491,42 @@ parse_record: if (de->attr == ATTR_EXT) { int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); - if (status < 0) - return status; - else if (status == PARSE_INVALID) + if (status < 0) { + err = status; + goto end_of_dir; + } else if (status == PARSE_INVALID) continue; else if (status == PARSE_NOT_LONGNAME) goto parse_record; else if (status == PARSE_EOF) - goto EODir; + goto end_of_dir; } - memcpy(work, de->name, sizeof(de->name)); - /* see namei.c, msdos_format_name */ - if (work[0] == 0x05) - work[0] = 0xE5; - for (i = 0, j = 0, last_u = 0; i < 8;) { - if (!work[i]) - break; - chl = fat_shortname2uni(nls_disk, &work[i], 8 - i, - &bufuname[j++], opt_shortname, - de->lcase & CASE_LOWER_BASE); - if (chl <= 1) { - if (work[i] != ' ') - last_u = j; - } else { - last_u = j; - } - i += chl; - } - j = last_u; - fat_short2uni(nls_disk, ".", 1, &bufuname[j++]); - for (i = 8; i < MSDOS_NAME;) { - if (!work[i]) - break; - chl = fat_shortname2uni(nls_disk, &work[i], - MSDOS_NAME - i, - &bufuname[j++], opt_shortname, - de->lcase & CASE_LOWER_EXT); - if (chl <= 1) { - if (work[i] != ' ') - last_u = j; - } else { - last_u = j; - } - i += chl; - } - if (!last_u) + /* Never prepend '.' to hidden files here. + * That is done only for msdos mounts (and only when + * 'dotsOK=yes'); if we are executing here, it is in the + * context of a vfat mount. + */ + len = fat_parse_short(sb, de, bufname, 0); + if (len == 0) continue; - bufuname[last_u] = 0x0000; - xlate_len = utf8 - ?utf8_wcstombs(bufname, bufuname, sizeof(bufname)) - :uni16_to_x8(bufname, bufuname, uni_xlate, nls_io); - if (xlate_len == name_len) - if ((!anycase && !memcmp(name, bufname, xlate_len)) || - (anycase && !nls_strnicmp(nls_io, name, bufname, - xlate_len))) - goto Found; + /* Compare shortname */ + if (fat_name_match(sbi, name, name_len, bufname, len)) + goto found; if (nr_slots) { - xlate_len = utf8 - ?utf8_wcstombs(bufname, unicode, sizeof(bufname)) - :uni16_to_x8(bufname, unicode, uni_xlate, nls_io); - if (xlate_len != name_len) - continue; - if ((!anycase && !memcmp(name, bufname, xlate_len)) || - (anycase && !nls_strnicmp(nls_io, name, bufname, - xlate_len))) - goto Found; + void *longname = unicode + FAT_MAX_UNI_CHARS; + int size = PATH_MAX - FAT_MAX_UNI_SIZE; + + /* Compare longname */ + len = fat_uni_to_x8(sb, unicode, longname, size); + if (fat_name_match(sbi, name, name_len, longname, len)) + goto found; } } -Found: +found: nr_slots++; /* include the de */ sinfo->slot_off = cpos - nr_slots * sizeof(*de); sinfo->nr_slots = nr_slots; @@ -415,16 +534,16 @@ Found: sinfo->bh = bh; sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de); err = 0; -EODir: +end_of_dir: if (unicode) - free_page((unsigned long)unicode); + __putname(unicode); return err; } - EXPORT_SYMBOL_GPL(fat_search_long); struct fat_ioctl_filldir_callback { + struct dir_context ctx; void __user *dirent; int result; /* for dir ioctl */ @@ -434,158 +553,122 @@ struct fat_ioctl_filldir_callback { int short_len; }; -static int __fat_readdir(struct inode *inode, struct file *filp, void *dirent, - filldir_t filldir, int short_only, int both) +static int __fat_readdir(struct inode *inode, struct file *file, + struct dir_context *ctx, int short_only, + struct fat_ioctl_filldir_callback *both) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct msdos_dir_entry *de; - struct nls_table *nls_io = sbi->nls_io; - struct nls_table *nls_disk = sbi->nls_disk; - unsigned char long_slots; - const char *fill_name; - int fill_len; - wchar_t bufuname[14]; + unsigned char nr_slots; wchar_t *unicode = NULL; - unsigned char c, work[MSDOS_NAME], bufname[56], *ptname = bufname; - unsigned long lpos, dummy, *furrfu = &lpos; - int uni_xlate = sbi->options.unicode_xlate; + unsigned char bufname[FAT_MAX_SHORT_SIZE]; int isvfat = sbi->options.isvfat; - int utf8 = sbi->options.utf8; - int nocase = sbi->options.nocase; - unsigned short opt_shortname = sbi->options.shortname; - unsigned long inum; - int chi, chl, i, i2, j, last, last_u, dotoffset = 0; + const char *fill_name = NULL; + int fake_offset = 0; loff_t cpos; + int short_len = 0, fill_len = 0; int ret = 0; - lock_kernel(); + mutex_lock(&sbi->s_lock); - cpos = filp->f_pos; + cpos = ctx->pos; /* Fake . and .. for the root directory. */ if (inode->i_ino == MSDOS_ROOT_INO) { - while (cpos < 2) { - if (filldir(dirent, "..", cpos+1, cpos, MSDOS_ROOT_INO, DT_DIR) < 0) - goto out; - cpos++; - filp->f_pos++; - } - if (cpos == 2) { - dummy = 2; - furrfu = &dummy; + if (!dir_emit_dots(file, ctx)) + goto out; + if (ctx->pos == 2) { + fake_offset = 1; cpos = 0; } } - if (cpos & (sizeof(struct msdos_dir_entry)-1)) { + if (cpos & (sizeof(struct msdos_dir_entry) - 1)) { ret = -ENOENT; goto out; } bh = NULL; -GetNew: +get_new: if (fat_get_entry(inode, &cpos, &bh, &de) == -1) - goto EODir; + goto end_of_dir; parse_record: - long_slots = 0; - /* Check for long filename entry */ - if (isvfat) { + nr_slots = 0; + /* + * Check for long filename entry, but if short_only, we don't + * need to parse long filename. + */ + if (isvfat && !short_only) { if (de->name[0] == DELETED_FLAG) - goto RecEnd; + goto record_end; if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME)) - goto RecEnd; + goto record_end; if (de->attr != ATTR_EXT && IS_FREE(de->name)) - goto RecEnd; + goto record_end; } else { if ((de->attr & ATTR_VOLUME) || IS_FREE(de->name)) - goto RecEnd; + goto record_end; } if (isvfat && de->attr == ATTR_EXT) { int status = fat_parse_long(inode, &cpos, &bh, &de, - &unicode, &long_slots); + &unicode, &nr_slots); if (status < 0) { - filp->f_pos = cpos; + ctx->pos = cpos; ret = status; goto out; } else if (status == PARSE_INVALID) - goto RecEnd; + goto record_end; else if (status == PARSE_NOT_LONGNAME) goto parse_record; else if (status == PARSE_EOF) - goto EODir; - } + goto end_of_dir; - if (sbi->options.dotsOK) { - ptname = bufname; - dotoffset = 0; - if (de->attr & ATTR_HIDDEN) { - *ptname++ = '.'; - dotoffset = 1; - } - } + if (nr_slots) { + void *longname = unicode + FAT_MAX_UNI_CHARS; + int size = PATH_MAX - FAT_MAX_UNI_SIZE; + int len = fat_uni_to_x8(sb, unicode, longname, size); - memcpy(work, de->name, sizeof(de->name)); - /* see namei.c, msdos_format_name */ - if (work[0] == 0x05) - work[0] = 0xE5; - for (i = 0, j = 0, last = 0, last_u = 0; i < 8;) { - if (!(c = work[i])) - break; - chl = fat_shortname2uni(nls_disk, &work[i], 8 - i, - &bufuname[j++], opt_shortname, - de->lcase & CASE_LOWER_BASE); - if (chl <= 1) { - ptname[i++] = (!nocase && c>='A' && c<='Z') ? c+32 : c; - if (c != ' ') { - last = i; - last_u = j; - } - } else { - last_u = j; - for (chi = 0; chi < chl && i < 8; chi++) { - ptname[i] = work[i]; - i++; last = i; - } - } - } - i = last; - j = last_u; - fat_short2uni(nls_disk, ".", 1, &bufuname[j++]); - ptname[i++] = '.'; - for (i2 = 8; i2 < MSDOS_NAME;) { - if (!(c = work[i2])) - break; - chl = fat_shortname2uni(nls_disk, &work[i2], MSDOS_NAME - i2, - &bufuname[j++], opt_shortname, - de->lcase & CASE_LOWER_EXT); - if (chl <= 1) { - i2++; - ptname[i++] = (!nocase && c>='A' && c<='Z') ? c+32 : c; - if (c != ' ') { - last = i; - last_u = j; - } - } else { - last_u = j; - for (chi = 0; chi < chl && i2 < MSDOS_NAME; chi++) { - ptname[i++] = work[i2++]; - last = i; - } + fill_name = longname; + fill_len = len; + /* !both && !short_only, so we don't need shortname. */ + if (!both) + goto start_filldir; + + short_len = fat_parse_short(sb, de, bufname, + sbi->options.dotsOK); + if (short_len == 0) + goto record_end; + /* hack for fat_ioctl_filldir() */ + both->longname = fill_name; + both->long_len = fill_len; + both->shortname = bufname; + both->short_len = short_len; + fill_name = NULL; + fill_len = 0; + goto start_filldir; } } - if (!last) - goto RecEnd; - i = last + dotoffset; - j = last_u; + short_len = fat_parse_short(sb, de, bufname, sbi->options.dotsOK); + if (short_len == 0) + goto record_end; - lpos = cpos - (long_slots+1)*sizeof(struct msdos_dir_entry); - if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) - inum = inode->i_ino; - else if (!memcmp(de->name, MSDOS_DOTDOT, MSDOS_NAME)) { - inum = parent_ino(filp->f_path.dentry); + fill_name = bufname; + fill_len = short_len; + +start_filldir: + if (!fake_offset) + ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + + if (!memcmp(de->name, MSDOS_DOT, MSDOS_NAME)) { + if (!dir_emit_dot(file, ctx)) + goto fill_failed; + } else if (!memcmp(de->name, MSDOS_DOTDOT, MSDOS_NAME)) { + if (!dir_emit_dotdot(file, ctx)) + goto fill_failed; } else { + unsigned long inum; loff_t i_pos = fat_make_i_pos(sb, bh, de); struct inode *tmp = fat_iget(sb, i_pos); if (tmp) { @@ -593,63 +676,29 @@ parse_record: iput(tmp); } else inum = iunique(sb, MSDOS_ROOT_INO); + if (!dir_emit(ctx, fill_name, fill_len, inum, + (de->attr & ATTR_DIR) ? DT_DIR : DT_REG)) + goto fill_failed; } - if (isvfat) { - bufuname[j] = 0x0000; - i = utf8 ? utf8_wcstombs(bufname, bufuname, sizeof(bufname)) - : uni16_to_x8(bufname, bufuname, uni_xlate, nls_io); - } - - fill_name = bufname; - fill_len = i; - if (!short_only && long_slots) { - /* convert the unicode long name. 261 is maximum size - * of unicode buffer. (13 * slots + nul) */ - void *longname = unicode + 261; - int buf_size = PAGE_SIZE - (261 * sizeof(unicode[0])); - int long_len = utf8 - ? utf8_wcstombs(longname, unicode, buf_size) - : uni16_to_x8(longname, unicode, uni_xlate, nls_io); - - if (!both) { - fill_name = longname; - fill_len = long_len; - } else { - /* hack for fat_ioctl_filldir() */ - struct fat_ioctl_filldir_callback *p = dirent; - - p->longname = longname; - p->long_len = long_len; - p->shortname = bufname; - p->short_len = i; - fill_name = NULL; - fill_len = 0; - } - } - if (filldir(dirent, fill_name, fill_len, *furrfu, inum, - (de->attr & ATTR_DIR) ? DT_DIR : DT_REG) < 0) - goto FillFailed; - -RecEnd: - furrfu = &lpos; - filp->f_pos = cpos; - goto GetNew; -EODir: - filp->f_pos = cpos; -FillFailed: +record_end: + fake_offset = 0; + ctx->pos = cpos; + goto get_new; +end_of_dir: + ctx->pos = cpos; +fill_failed: brelse(bh); if (unicode) - free_page((unsigned long)unicode); + __putname(unicode); out: - unlock_kernel(); + mutex_unlock(&sbi->s_lock); return ret; } -static int fat_readdir(struct file *filp, void *dirent, filldir_t filldir) +static int fat_readdir(struct file *file, struct dir_context *ctx) { - struct inode *inode = filp->f_path.dentry->d_inode; - return __fat_readdir(inode, filp, dirent, filldir, 0, 0); + return __fat_readdir(file_inode(file), file, ctx, 0, NULL); } #define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type) \ @@ -703,22 +752,27 @@ efault: \ return -EFAULT; \ } -FAT_IOCTL_FILLDIR_FUNC(fat_ioctl_filldir, dirent) +FAT_IOCTL_FILLDIR_FUNC(fat_ioctl_filldir, __fat_dirent) -static int fat_ioctl_readdir(struct inode *inode, struct file *filp, +static int fat_ioctl_readdir(struct inode *inode, struct file *file, void __user *dirent, filldir_t filldir, int short_only, int both) { - struct fat_ioctl_filldir_callback buf; + struct fat_ioctl_filldir_callback buf = { + .ctx.actor = filldir, + .dirent = dirent + }; int ret; buf.dirent = dirent; buf.result = 0; mutex_lock(&inode->i_mutex); + buf.ctx.pos = file->f_pos; ret = -ENOENT; if (!IS_DEADDIR(inode)) { - ret = __fat_readdir(inode, filp, &buf, filldir, - short_only, both); + ret = __fat_readdir(inode, file, &buf.ctx, + short_only, both ? &buf : NULL); + file->f_pos = buf.ctx.pos; } mutex_unlock(&inode->i_mutex); if (ret >= 0) @@ -726,10 +780,11 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *filp, return ret; } -static int fat_dir_ioctl(struct inode *inode, struct file *filp, - unsigned int cmd, unsigned long arg) +static long fat_dir_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) { - struct dirent __user *d1 = (struct dirent __user *)arg; + struct inode *inode = file_inode(filp); + struct __fat_dirent __user *d1 = (struct __fat_dirent __user *)arg; int short_only, both; switch (cmd) { @@ -742,10 +797,10 @@ static int fat_dir_ioctl(struct inode *inode, struct file *filp, both = 1; break; default: - return fat_generic_ioctl(inode, filp, cmd, arg); + return fat_generic_ioctl(filp, cmd, arg); } - if (!access_ok(VERIFY_WRITE, d1, sizeof(struct dirent[2]))) + if (!access_ok(VERIFY_WRITE, d1, sizeof(struct __fat_dirent[2]))) return -EFAULT; /* * Yes, we don't need this put_user() absolutely. However old @@ -768,7 +823,7 @@ FAT_IOCTL_FILLDIR_FUNC(fat_compat_ioctl_filldir, compat_dirent) static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, unsigned long arg) { - struct inode *inode = filp->f_path.dentry->d_inode; + struct inode *inode = file_inode(filp); struct compat_dirent __user *d1 = compat_ptr(arg); int short_only, both; @@ -782,7 +837,7 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, both = 1; break; default: - return -ENOIOCTLCMD; + return fat_generic_ioctl(filp, cmd, (unsigned long)arg); } if (!access_ok(VERIFY_WRITE, d1, sizeof(struct compat_dirent[2]))) @@ -801,13 +856,14 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, #endif /* CONFIG_COMPAT */ const struct file_operations fat_dir_operations = { + .llseek = generic_file_llseek, .read = generic_read_dir, - .readdir = fat_readdir, - .ioctl = fat_dir_ioctl, + .iterate = fat_readdir, + .unlocked_ioctl = fat_dir_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = fat_compat_dir_ioctl, #endif - .fsync = file_fsync, + .fsync = fat_file_fsync, }; static int fat_get_short_entry(struct inode *dir, loff_t *pos, @@ -823,25 +879,26 @@ static int fat_get_short_entry(struct inode *dir, loff_t *pos, } /* - * The ".." entry can not provide the "struct fat_slot_info" informations - * for inode. So, this function provide the some informations only. + * The ".." entry can not provide the "struct fat_slot_info" information + * for inode, nor a usable i_pos. So, this function provides some information + * only. + * + * Since this function walks through the on-disk inodes within a directory, + * callers are responsible for taking any locks necessary to prevent the + * directory from changing. */ int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh, - struct msdos_dir_entry **de, loff_t *i_pos) + struct msdos_dir_entry **de) { - loff_t offset; + loff_t offset = 0; - offset = 0; - *bh = NULL; + *de = NULL; while (fat_get_short_entry(dir, &offset, bh, de) >= 0) { - if (!strncmp((*de)->name, MSDOS_DOTDOT, MSDOS_NAME)) { - *i_pos = fat_make_i_pos(dir->i_sb, *bh, *de); + if (!strncmp((*de)->name, MSDOS_DOTDOT, MSDOS_NAME)) return 0; - } } return -ENOENT; } - EXPORT_SYMBOL_GPL(fat_get_dotdot_entry); /* See if directory is empty */ @@ -864,7 +921,6 @@ int fat_dir_empty(struct inode *dir) brelse(bh); return result; } - EXPORT_SYMBOL_GPL(fat_dir_empty); /* @@ -910,9 +966,31 @@ int fat_scan(struct inode *dir, const unsigned char *name, } return -ENOENT; } - EXPORT_SYMBOL_GPL(fat_scan); +/* + * Scans a directory for a given logstart. + * Returns an error code or zero. + */ +int fat_scan_logstart(struct inode *dir, int i_logstart, + struct fat_slot_info *sinfo) +{ + struct super_block *sb = dir->i_sb; + + sinfo->slot_off = 0; + sinfo->bh = NULL; + while (fat_get_short_entry(dir, &sinfo->slot_off, &sinfo->bh, + &sinfo->de) >= 0) { + if (fat_get_start(MSDOS_SB(sb), sinfo->de) == i_logstart) { + sinfo->slot_off -= sizeof(*sinfo->de); + sinfo->nr_slots = 1; + sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de); + return 0; + } + } + return -ENOENT; +} + static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots) { struct super_block *sb = dir->i_sb; @@ -934,7 +1012,7 @@ static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots) de++; nr_slots--; } - mark_buffer_dirty(bh); + mark_buffer_dirty_inode(bh, dir); if (IS_DIRSYNC(dir)) err = sync_dirty_buffer(bh); brelse(bh); @@ -950,6 +1028,7 @@ static int __fat_remove_entries(struct inode *dir, loff_t pos, int nr_slots) int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo) { + struct super_block *sb = dir->i_sb; struct msdos_dir_entry *de; struct buffer_head *bh; int err = 0, nr_slots; @@ -968,7 +1047,7 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo) de--; nr_slots--; } - mark_buffer_dirty(bh); + mark_buffer_dirty_inode(bh, dir); if (IS_DIRSYNC(dir)) err = sync_dirty_buffer(bh); brelse(bh); @@ -984,8 +1063,8 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo) */ err = __fat_remove_entries(dir, sinfo->slot_off, nr_slots); if (err) { - printk(KERN_WARNING - "FAT: Couldn't remove the long name slots\n"); + fat_msg(sb, KERN_WARNING, + "Couldn't remove the long name slots"); } } @@ -997,7 +1076,6 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo) return 0; } - EXPORT_SYMBOL_GPL(fat_remove_entries); static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used, @@ -1018,7 +1096,7 @@ static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used, } memset(bhs[n]->b_data, 0, sb->s_blocksize); set_buffer_uptodate(bhs[n]); - mark_buffer_dirty(bhs[n]); + mark_buffer_dirty_inode(bhs[n], dir); n++; blknr++; @@ -1057,6 +1135,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) struct msdos_dir_entry *de; sector_t blknr; __le16 date, time; + u8 time_cs; int err, cluster; err = fat_alloc_clusters(dir, &cluster, 1); @@ -1070,7 +1149,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) goto error_free; } - fat_date_unix2dos(ts->tv_sec, &time, &date); + fat_time_unix2fat(sbi, ts, &time, &date, &time_cs); de = (struct msdos_dir_entry *)bhs[0]->b_data; /* filling the new directory slots ("." and ".." entries) */ @@ -1080,23 +1159,22 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) de[0].lcase = de[1].lcase = 0; de[0].time = de[1].time = time; de[0].date = de[1].date = date; - de[0].ctime_cs = de[1].ctime_cs = 0; if (sbi->options.isvfat) { /* extra timestamps */ de[0].ctime = de[1].ctime = time; + de[0].ctime_cs = de[1].ctime_cs = time_cs; de[0].adate = de[0].cdate = de[1].adate = de[1].cdate = date; } else { de[0].ctime = de[1].ctime = 0; + de[0].ctime_cs = de[1].ctime_cs = 0; de[0].adate = de[0].cdate = de[1].adate = de[1].cdate = 0; } - de[0].start = cpu_to_le16(cluster); - de[0].starthi = cpu_to_le16(cluster >> 16); - de[1].start = cpu_to_le16(MSDOS_I(dir)->i_logstart); - de[1].starthi = cpu_to_le16(MSDOS_I(dir)->i_logstart >> 16); + fat_set_start(&de[0], cluster); + fat_set_start(&de[1], MSDOS_I(dir)->i_logstart); de[0].size = de[1].size = 0; memset(de + 2, 0, sb->s_blocksize - 2 * sizeof(*de)); set_buffer_uptodate(bhs[0]); - mark_buffer_dirty(bhs[0]); + mark_buffer_dirty_inode(bhs[0], dir); err = fat_zeroed_cluster(dir, blknr, 1, bhs, MAX_BUF_PER_PAGE); if (err) @@ -1109,7 +1187,6 @@ error_free: error: return err; } - EXPORT_SYMBOL_GPL(fat_alloc_new_dir); static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots, @@ -1158,7 +1235,7 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots, slots += copy; size -= copy; set_buffer_uptodate(bhs[n]); - mark_buffer_dirty(bhs[n]); + mark_buffer_dirty_inode(bhs[n], dir); if (!size) break; n++; @@ -1198,13 +1275,13 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, struct super_block *sb = dir->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */ - struct msdos_dir_entry *de; + struct msdos_dir_entry *uninitialized_var(de); int err, free_slots, i, nr_bhs; loff_t pos, i_pos; sinfo->nr_slots = nr_slots; - /* First stage: search free direcotry entries */ + /* First stage: search free directory entries */ free_slots = nr_bhs = 0; bh = prev = NULL; pos = 0; @@ -1234,7 +1311,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, if (sbi->fat_bits != 32) goto error; } else if (MSDOS_I(dir)->i_start == 0) { - printk(KERN_ERR "FAT: Corrupted directory (i_pos %lld)\n", + fat_msg(sb, KERN_ERR, "Corrupted directory (i_pos %lld)", MSDOS_I(dir)->i_pos); err = -EIO; goto error; @@ -1258,7 +1335,7 @@ found: for (i = 0; i < long_bhs; i++) { int copy = min_t(int, sb->s_blocksize - offset, size); memcpy(bhs[i]->b_data + offset, slots, copy); - mark_buffer_dirty(bhs[i]); + mark_buffer_dirty_inode(bhs[i], dir); offset = 0; slots += copy; size -= copy; @@ -1269,7 +1346,7 @@ found: /* Fill the short name slot. */ int copy = min_t(int, sb->s_blocksize - offset, size); memcpy(bhs[i]->b_data + offset, slots, copy); - mark_buffer_dirty(bhs[i]); + mark_buffer_dirty_inode(bhs[i], dir); if (IS_DIRSYNC(dir)) err = sync_dirty_buffer(bhs[i]); } @@ -1299,7 +1376,7 @@ found: goto error_remove; } if (dir->i_size & (sbi->cluster_size - 1)) { - fat_fs_panic(sb, "Odd directory size"); + fat_fs_error(sb, "Odd directory size"); dir->i_size = (dir->i_size + sbi->cluster_size - 1) & ~((loff_t)sbi->cluster_size - 1); } @@ -1325,5 +1402,4 @@ error_remove: __fat_remove_entries(dir, pos, free_slots); return err; } - EXPORT_SYMBOL_GPL(fat_add_entries); diff --git a/fs/fat/fat.h b/fs/fat/fat.h new file mode 100644 index 00000000000..e0c4ba39a37 --- /dev/null +++ b/fs/fat/fat.h @@ -0,0 +1,422 @@ +#ifndef _FAT_H +#define _FAT_H + +#include <linux/buffer_head.h> +#include <linux/string.h> +#include <linux/nls.h> +#include <linux/fs.h> +#include <linux/hash.h> +#include <linux/mutex.h> +#include <linux/ratelimit.h> +#include <linux/msdos_fs.h> + +/* + * vfat shortname flags + */ +#define VFAT_SFN_DISPLAY_LOWER 0x0001 /* convert to lowercase for display */ +#define VFAT_SFN_DISPLAY_WIN95 0x0002 /* emulate win95 rule for display */ +#define VFAT_SFN_DISPLAY_WINNT 0x0004 /* emulate winnt rule for display */ +#define VFAT_SFN_CREATE_WIN95 0x0100 /* emulate win95 rule for create */ +#define VFAT_SFN_CREATE_WINNT 0x0200 /* emulate winnt rule for create */ + +#define FAT_ERRORS_CONT 1 /* ignore error and continue */ +#define FAT_ERRORS_PANIC 2 /* panic on error */ +#define FAT_ERRORS_RO 3 /* remount r/o on error */ + +#define FAT_NFS_STALE_RW 1 /* NFS RW support, can cause ESTALE */ +#define FAT_NFS_NOSTALE_RO 2 /* NFS RO support, no ESTALE issue */ + +struct fat_mount_options { + kuid_t fs_uid; + kgid_t fs_gid; + unsigned short fs_fmask; + unsigned short fs_dmask; + unsigned short codepage; /* Codepage for shortname conversions */ + int time_offset; /* Offset of timestamps from UTC (in minutes) */ + char *iocharset; /* Charset used for filename input/display */ + unsigned short shortname; /* flags for shortname display/create rule */ + unsigned char name_check; /* r = relaxed, n = normal, s = strict */ + unsigned char errors; /* On error: continue, panic, remount-ro */ + unsigned char nfs; /* NFS support: nostale_ro, stale_rw */ + unsigned short allow_utime;/* permission for setting the [am]time */ + unsigned quiet:1, /* set = fake successful chmods and chowns */ + showexec:1, /* set = only set x bit for com/exe/bat */ + sys_immutable:1, /* set = system files are immutable */ + dotsOK:1, /* set = hidden and system files are named '.filename' */ + isvfat:1, /* 0=no vfat long filename support, 1=vfat support */ + utf8:1, /* Use of UTF-8 character set (Default) */ + unicode_xlate:1, /* create escape sequences for unhandled Unicode */ + numtail:1, /* Does first alias have a numeric '~1' type tail? */ + flush:1, /* write things quickly */ + nocase:1, /* Does this need case conversion? 0=need case conversion*/ + usefree:1, /* Use free_clusters for FAT32 */ + tz_set:1, /* Filesystem timestamps' offset set */ + rodir:1, /* allow ATTR_RO for directory */ + discard:1, /* Issue discard requests on deletions */ + dos1xfloppy:1; /* Assume default BPB for DOS 1.x floppies */ +}; + +#define FAT_HASH_BITS 8 +#define FAT_HASH_SIZE (1UL << FAT_HASH_BITS) + +/* + * MS-DOS file system in-core superblock data + */ +struct msdos_sb_info { + unsigned short sec_per_clus; /* sectors/cluster */ + unsigned short cluster_bits; /* log2(cluster_size) */ + unsigned int cluster_size; /* cluster size */ + unsigned char fats, fat_bits; /* number of FATs, FAT bits (12 or 16) */ + unsigned short fat_start; + unsigned long fat_length; /* FAT start & length (sec.) */ + unsigned long dir_start; + unsigned short dir_entries; /* root dir start & entries */ + unsigned long data_start; /* first data sector */ + unsigned long max_cluster; /* maximum cluster number */ + unsigned long root_cluster; /* first cluster of the root directory */ + unsigned long fsinfo_sector; /* sector number of FAT32 fsinfo */ + struct mutex fat_lock; + struct mutex nfs_build_inode_lock; + struct mutex s_lock; + unsigned int prev_free; /* previously allocated cluster number */ + unsigned int free_clusters; /* -1 if undefined */ + unsigned int free_clus_valid; /* is free_clusters valid? */ + struct fat_mount_options options; + struct nls_table *nls_disk; /* Codepage used on disk */ + struct nls_table *nls_io; /* Charset used for input and display */ + const void *dir_ops; /* Opaque; default directory operations */ + int dir_per_block; /* dir entries per block */ + int dir_per_block_bits; /* log2(dir_per_block) */ + unsigned int vol_id; /*volume ID*/ + + int fatent_shift; + struct fatent_operations *fatent_ops; + struct inode *fat_inode; + struct inode *fsinfo_inode; + + struct ratelimit_state ratelimit; + + spinlock_t inode_hash_lock; + struct hlist_head inode_hashtable[FAT_HASH_SIZE]; + + spinlock_t dir_hash_lock; + struct hlist_head dir_hashtable[FAT_HASH_SIZE]; + + unsigned int dirty; /* fs state before mount */ + struct rcu_head rcu; +}; + +#define FAT_CACHE_VALID 0 /* special case for valid cache */ + +/* + * MS-DOS file system inode data in memory + */ +struct msdos_inode_info { + spinlock_t cache_lru_lock; + struct list_head cache_lru; + int nr_caches; + /* for avoiding the race between fat_free() and fat_get_cluster() */ + unsigned int cache_valid_id; + + /* NOTE: mmu_private is 64bits, so must hold ->i_mutex to access */ + loff_t mmu_private; /* physically allocated size */ + + int i_start; /* first cluster or 0 */ + int i_logstart; /* logical first cluster */ + int i_attrs; /* unused attribute bits */ + loff_t i_pos; /* on-disk position of directory entry or 0 */ + struct hlist_node i_fat_hash; /* hash by i_location */ + struct hlist_node i_dir_hash; /* hash by i_logstart */ + struct rw_semaphore truncate_lock; /* protect bmap against truncate */ + struct inode vfs_inode; +}; + +struct fat_slot_info { + loff_t i_pos; /* on-disk position of directory entry */ + loff_t slot_off; /* offset for slot or de start */ + int nr_slots; /* number of slots + 1(de) in filename */ + struct msdos_dir_entry *de; + struct buffer_head *bh; +}; + +static inline struct msdos_sb_info *MSDOS_SB(struct super_block *sb) +{ + return sb->s_fs_info; +} + +static inline struct msdos_inode_info *MSDOS_I(struct inode *inode) +{ + return container_of(inode, struct msdos_inode_info, vfs_inode); +} + +/* + * If ->i_mode can't hold S_IWUGO (i.e. ATTR_RO), we use ->i_attrs to + * save ATTR_RO instead of ->i_mode. + * + * If it's directory and !sbi->options.rodir, ATTR_RO isn't read-only + * bit, it's just used as flag for app. + */ +static inline int fat_mode_can_hold_ro(struct inode *inode) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + umode_t mask; + + if (S_ISDIR(inode->i_mode)) { + if (!sbi->options.rodir) + return 0; + mask = ~sbi->options.fs_dmask; + } else + mask = ~sbi->options.fs_fmask; + + if (!(mask & S_IWUGO)) + return 0; + return 1; +} + +/* Convert attribute bits and a mask to the UNIX mode. */ +static inline umode_t fat_make_mode(struct msdos_sb_info *sbi, + u8 attrs, umode_t mode) +{ + if (attrs & ATTR_RO && !((attrs & ATTR_DIR) && !sbi->options.rodir)) + mode &= ~S_IWUGO; + + if (attrs & ATTR_DIR) + return (mode & ~sbi->options.fs_dmask) | S_IFDIR; + else + return (mode & ~sbi->options.fs_fmask) | S_IFREG; +} + +/* Return the FAT attribute byte for this inode */ +static inline u8 fat_make_attrs(struct inode *inode) +{ + u8 attrs = MSDOS_I(inode)->i_attrs; + if (S_ISDIR(inode->i_mode)) + attrs |= ATTR_DIR; + if (fat_mode_can_hold_ro(inode) && !(inode->i_mode & S_IWUGO)) + attrs |= ATTR_RO; + return attrs; +} + +static inline void fat_save_attrs(struct inode *inode, u8 attrs) +{ + if (fat_mode_can_hold_ro(inode)) + MSDOS_I(inode)->i_attrs = attrs & ATTR_UNUSED; + else + MSDOS_I(inode)->i_attrs = attrs & (ATTR_UNUSED | ATTR_RO); +} + +static inline unsigned char fat_checksum(const __u8 *name) +{ + unsigned char s = name[0]; + s = (s<<7) + (s>>1) + name[1]; s = (s<<7) + (s>>1) + name[2]; + s = (s<<7) + (s>>1) + name[3]; s = (s<<7) + (s>>1) + name[4]; + s = (s<<7) + (s>>1) + name[5]; s = (s<<7) + (s>>1) + name[6]; + s = (s<<7) + (s>>1) + name[7]; s = (s<<7) + (s>>1) + name[8]; + s = (s<<7) + (s>>1) + name[9]; s = (s<<7) + (s>>1) + name[10]; + return s; +} + +static inline sector_t fat_clus_to_blknr(struct msdos_sb_info *sbi, int clus) +{ + return ((sector_t)clus - FAT_START_ENT) * sbi->sec_per_clus + + sbi->data_start; +} + +static inline void fat_get_blknr_offset(struct msdos_sb_info *sbi, + loff_t i_pos, sector_t *blknr, int *offset) +{ + *blknr = i_pos >> sbi->dir_per_block_bits; + *offset = i_pos & (sbi->dir_per_block - 1); +} + +static inline loff_t fat_i_pos_read(struct msdos_sb_info *sbi, + struct inode *inode) +{ + loff_t i_pos; +#if BITS_PER_LONG == 32 + spin_lock(&sbi->inode_hash_lock); +#endif + i_pos = MSDOS_I(inode)->i_pos; +#if BITS_PER_LONG == 32 + spin_unlock(&sbi->inode_hash_lock); +#endif + return i_pos; +} + +static inline void fat16_towchar(wchar_t *dst, const __u8 *src, size_t len) +{ +#ifdef __BIG_ENDIAN + while (len--) { + *dst++ = src[0] | (src[1] << 8); + src += 2; + } +#else + memcpy(dst, src, len * 2); +#endif +} + +static inline int fat_get_start(const struct msdos_sb_info *sbi, + const struct msdos_dir_entry *de) +{ + int cluster = le16_to_cpu(de->start); + if (sbi->fat_bits == 32) + cluster |= (le16_to_cpu(de->starthi) << 16); + return cluster; +} + +static inline void fat_set_start(struct msdos_dir_entry *de, int cluster) +{ + de->start = cpu_to_le16(cluster); + de->starthi = cpu_to_le16(cluster >> 16); +} + +static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len) +{ +#ifdef __BIG_ENDIAN + while (len--) { + dst[0] = *src & 0x00FF; + dst[1] = (*src & 0xFF00) >> 8; + dst += 2; + src++; + } +#else + memcpy(dst, src, len * 2); +#endif +} + +/* fat/cache.c */ +extern void fat_cache_inval_inode(struct inode *inode); +extern int fat_get_cluster(struct inode *inode, int cluster, + int *fclus, int *dclus); +extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, + unsigned long *mapped_blocks, int create); + +/* fat/dir.c */ +extern const struct file_operations fat_dir_operations; +extern int fat_search_long(struct inode *inode, const unsigned char *name, + int name_len, struct fat_slot_info *sinfo); +extern int fat_dir_empty(struct inode *dir); +extern int fat_subdirs(struct inode *dir); +extern int fat_scan(struct inode *dir, const unsigned char *name, + struct fat_slot_info *sinfo); +extern int fat_scan_logstart(struct inode *dir, int i_logstart, + struct fat_slot_info *sinfo); +extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh, + struct msdos_dir_entry **de); +extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts); +extern int fat_add_entries(struct inode *dir, void *slots, int nr_slots, + struct fat_slot_info *sinfo); +extern int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo); + +/* fat/fatent.c */ +struct fat_entry { + int entry; + union { + u8 *ent12_p[2]; + __le16 *ent16_p; + __le32 *ent32_p; + } u; + int nr_bhs; + struct buffer_head *bhs[2]; + struct inode *fat_inode; +}; + +static inline void fatent_init(struct fat_entry *fatent) +{ + fatent->nr_bhs = 0; + fatent->entry = 0; + fatent->u.ent32_p = NULL; + fatent->bhs[0] = fatent->bhs[1] = NULL; + fatent->fat_inode = NULL; +} + +static inline void fatent_set_entry(struct fat_entry *fatent, int entry) +{ + fatent->entry = entry; + fatent->u.ent32_p = NULL; +} + +static inline void fatent_brelse(struct fat_entry *fatent) +{ + int i; + fatent->u.ent32_p = NULL; + for (i = 0; i < fatent->nr_bhs; i++) + brelse(fatent->bhs[i]); + fatent->nr_bhs = 0; + fatent->bhs[0] = fatent->bhs[1] = NULL; + fatent->fat_inode = NULL; +} + +extern void fat_ent_access_init(struct super_block *sb); +extern int fat_ent_read(struct inode *inode, struct fat_entry *fatent, + int entry); +extern int fat_ent_write(struct inode *inode, struct fat_entry *fatent, + int new, int wait); +extern int fat_alloc_clusters(struct inode *inode, int *cluster, + int nr_cluster); +extern int fat_free_clusters(struct inode *inode, int cluster); +extern int fat_count_free_clusters(struct super_block *sb); + +/* fat/file.c */ +extern long fat_generic_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg); +extern const struct file_operations fat_file_operations; +extern const struct inode_operations fat_file_inode_operations; +extern int fat_setattr(struct dentry *dentry, struct iattr *attr); +extern void fat_truncate_blocks(struct inode *inode, loff_t offset); +extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, + struct kstat *stat); +extern int fat_file_fsync(struct file *file, loff_t start, loff_t end, + int datasync); + +/* fat/inode.c */ +extern void fat_attach(struct inode *inode, loff_t i_pos); +extern void fat_detach(struct inode *inode); +extern struct inode *fat_iget(struct super_block *sb, loff_t i_pos); +extern struct inode *fat_build_inode(struct super_block *sb, + struct msdos_dir_entry *de, loff_t i_pos); +extern int fat_sync_inode(struct inode *inode); +extern int fat_fill_super(struct super_block *sb, void *data, int silent, + int isvfat, void (*setup)(struct super_block *)); +extern int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de); + +extern int fat_flush_inodes(struct super_block *sb, struct inode *i1, + struct inode *i2); +static inline unsigned long fat_dir_hash(int logstart) +{ + return hash_32(logstart, FAT_HASH_BITS); +} + +/* fat/misc.c */ +extern __printf(3, 4) __cold +void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...); +#define fat_fs_error(sb, fmt, args...) \ + __fat_fs_error(sb, 1, fmt , ## args) +#define fat_fs_error_ratelimit(sb, fmt, args...) \ + __fat_fs_error(sb, __ratelimit(&MSDOS_SB(sb)->ratelimit), fmt , ## args) +__printf(3, 4) __cold +void fat_msg(struct super_block *sb, const char *level, const char *fmt, ...); +#define fat_msg_ratelimit(sb, level, fmt, args...) \ + do { \ + if (__ratelimit(&MSDOS_SB(sb)->ratelimit)) \ + fat_msg(sb, level, fmt, ## args); \ + } while (0) +extern int fat_clusters_flush(struct super_block *sb); +extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster); +extern void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts, + __le16 __time, __le16 __date, u8 time_cs); +extern void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec *ts, + __le16 *time, __le16 *date, u8 *time_cs); +extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs); + +int fat_cache_init(void); +void fat_cache_destroy(void); + +/* fat/nfs.c */ +extern const struct export_operations fat_export_ops; +extern const struct export_operations fat_export_ops_nostale; + +/* helper for printk */ +typedef unsigned long long llu; + +#endif /* !_FAT_H */ diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 5fb366992b7..260705c5806 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -6,6 +6,8 @@ #include <linux/module.h> #include <linux/fs.h> #include <linux/msdos_fs.h> +#include <linux/blkdev.h> +#include "fat.h" struct fatent_operations { void (*ent_blocknr)(struct super_block *, int, int *, sector_t *); @@ -71,6 +73,8 @@ static int fat12_ent_bread(struct super_block *sb, struct fat_entry *fatent, struct buffer_head **bhs = fatent->bhs; WARN_ON(blocknr < MSDOS_SB(sb)->fat_start); + fatent->fat_inode = MSDOS_SB(sb)->fat_inode; + bhs[0] = sb_bread(sb, blocknr); if (!bhs[0]) goto err; @@ -91,8 +95,7 @@ static int fat12_ent_bread(struct super_block *sb, struct fat_entry *fatent, err_brelse: brelse(bhs[0]); err: - printk(KERN_ERR "FAT: FAT read failed (blocknr %llu)\n", - (unsigned long long)blocknr); + fat_msg(sb, KERN_ERR, "FAT read failed (blocknr %llu)", (llu)blocknr); return -EIO; } @@ -102,10 +105,11 @@ static int fat_ent_bread(struct super_block *sb, struct fat_entry *fatent, struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; WARN_ON(blocknr < MSDOS_SB(sb)->fat_start); + fatent->fat_inode = MSDOS_SB(sb)->fat_inode; fatent->bhs[0] = sb_bread(sb, blocknr); if (!fatent->bhs[0]) { - printk(KERN_ERR "FAT: FAT read failed (blocknr %llu)\n", - (unsigned long long)blocknr); + fat_msg(sb, KERN_ERR, "FAT read failed (blocknr %llu)", + (llu)blocknr); return -EIO; } fatent->nr_bhs = 1; @@ -166,9 +170,9 @@ static void fat12_ent_put(struct fat_entry *fatent, int new) } spin_unlock(&fat12_entry_lock); - mark_buffer_dirty(fatent->bhs[0]); + mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode); if (fatent->nr_bhs == 2) - mark_buffer_dirty(fatent->bhs[1]); + mark_buffer_dirty_inode(fatent->bhs[1], fatent->fat_inode); } static void fat16_ent_put(struct fat_entry *fatent, int new) @@ -177,18 +181,15 @@ static void fat16_ent_put(struct fat_entry *fatent, int new) new = EOF_FAT16; *fatent->u.ent16_p = cpu_to_le16(new); - mark_buffer_dirty(fatent->bhs[0]); + mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode); } static void fat32_ent_put(struct fat_entry *fatent, int new) { - if (new == FAT_ENT_EOF) - new = EOF_FAT32; - WARN_ON(new & 0xf0000000); new |= le32_to_cpu(*fatent->u.ent32_p) & ~0x0fffffff; *fatent->u.ent32_p = cpu_to_le32(new); - mark_buffer_dirty(fatent->bhs[0]); + mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode); } static int fat12_ent_next(struct fat_entry *fatent) @@ -199,15 +200,18 @@ static int fat12_ent_next(struct fat_entry *fatent) fatent->entry++; if (fatent->nr_bhs == 1) { - WARN_ON(ent12_p[0] > (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 2))); - WARN_ON(ent12_p[1] > (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 1))); + WARN_ON(ent12_p[0] > (u8 *)(bhs[0]->b_data + + (bhs[0]->b_size - 2))); + WARN_ON(ent12_p[1] > (u8 *)(bhs[0]->b_data + + (bhs[0]->b_size - 1))); if (nextp < (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 1))) { ent12_p[0] = nextp - 1; ent12_p[1] = nextp; return 1; } } else { - WARN_ON(ent12_p[0] != (u8 *)(bhs[0]->b_data + (bhs[0]->b_size - 1))); + WARN_ON(ent12_p[0] != (u8 *)(bhs[0]->b_data + + (bhs[0]->b_size - 1))); WARN_ON(ent12_p[1] != (u8 *)bhs[1]->b_data); ent12_p[0] = nextp - 1; ent12_p[1] = nextp; @@ -304,6 +308,16 @@ void fat_ent_access_init(struct super_block *sb) } } +static void mark_fsinfo_dirty(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + if (sb->s_flags & MS_RDONLY || sbi->fat_bits != 32) + return; + + __mark_inode_dirty(sbi->fsinfo_inode, I_DIRTY_SYNC); +} + static inline int fat_ent_update_ptr(struct super_block *sb, struct fat_entry *fatent, int offset, sector_t blocknr) @@ -315,10 +329,20 @@ static inline int fat_ent_update_ptr(struct super_block *sb, /* Is this fatent's blocks including this entry? */ if (!fatent->nr_bhs || bhs[0]->b_blocknr != blocknr) return 0; - /* Does this entry need the next block? */ - if (sbi->fat_bits == 12 && (offset + 1) >= sb->s_blocksize) { - if (fatent->nr_bhs != 2 || bhs[1]->b_blocknr != (blocknr + 1)) - return 0; + if (sbi->fat_bits == 12) { + if ((offset + 1) < sb->s_blocksize) { + /* This entry is on bhs[0]. */ + if (fatent->nr_bhs == 2) { + brelse(bhs[1]); + fatent->nr_bhs = 1; + } + } else { + /* This entry needs the next block. */ + if (fatent->nr_bhs != 2) + return 0; + if (bhs[1]->b_blocknr != (blocknr + 1)) + return 0; + } } ops->ent_set_ptr(fatent, offset); return 1; @@ -334,7 +358,7 @@ int fat_ent_read(struct inode *inode, struct fat_entry *fatent, int entry) if (entry < FAT_START_ENT || sbi->max_cluster <= entry) { fatent_brelse(fatent); - fat_fs_panic(sb, "invalid access to FAT (entry 0x%08x)", entry); + fat_fs_error(sb, "invalid access to FAT (entry 0x%08x)", entry); return -EIO; } @@ -370,7 +394,7 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs, } memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize); set_buffer_uptodate(c_bh); - mark_buffer_dirty(c_bh); + mark_buffer_dirty_inode(c_bh, sbi->fat_inode); if (sb->s_flags & MS_SYNCHRONOUS) err = sync_dirty_buffer(c_bh); brelse(c_bh); @@ -450,7 +474,8 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster) BUG_ON(nr_cluster > (MAX_BUF_PER_PAGE / 2)); /* fixed limit */ lock_fat(sbi); - if (sbi->free_clusters != -1 && sbi->free_clusters < nr_cluster) { + if (sbi->free_clusters != -1 && sbi->free_clus_valid && + sbi->free_clusters < nr_cluster) { unlock_fat(sbi); return -ENOSPC; } @@ -483,7 +508,6 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster) sbi->prev_free = entry; if (sbi->free_clusters != -1) sbi->free_clusters--; - sb->s_dirt = 1; cluster[idx_clus] = entry; idx_clus++; @@ -504,11 +528,12 @@ int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster) /* Couldn't allocate the free entries */ sbi->free_clusters = 0; - sb->s_dirt = 1; + sbi->free_clus_valid = 1; err = -ENOSPC; out: unlock_fat(sbi); + mark_fsinfo_dirty(sb); fatent_brelse(&fatent); if (!err) { if (inode_needs_sync(inode)) @@ -533,6 +558,7 @@ int fat_free_clusters(struct inode *inode, int cluster) struct fat_entry fatent; struct buffer_head *bhs[MAX_BUF_PER_PAGE]; int i, err, nr_bhs; + int first_cl = cluster, dirty_fsinfo = 0; nr_bhs = 0; fatent_init(&fatent); @@ -543,16 +569,34 @@ int fat_free_clusters(struct inode *inode, int cluster) err = cluster; goto error; } else if (cluster == FAT_ENT_FREE) { - fat_fs_panic(sb, "%s: deleting FAT entry beyond EOF", - __FUNCTION__); + fat_fs_error(sb, "%s: deleting FAT entry beyond EOF", + __func__); err = -EIO; goto error; } + if (sbi->options.discard) { + /* + * Issue discard for the sectors we no longer + * care about, batching contiguous clusters + * into one request + */ + if (cluster != fatent.entry + 1) { + int nr_clus = fatent.entry - first_cl + 1; + + sb_issue_discard(sb, + fat_clus_to_blknr(sbi, first_cl), + nr_clus * sbi->sec_per_clus, + GFP_NOFS, 0); + + first_cl = cluster; + } + } + ops->ent_put(&fatent, FAT_ENT_FREE); if (sbi->free_clusters != -1) { sbi->free_clusters++; - sb->s_dirt = 1; + dirty_fsinfo = 1; } if (nr_bhs + fatent.nr_bhs > MAX_BUF_PER_PAGE) { @@ -582,12 +626,11 @@ error: for (i = 0; i < nr_bhs; i++) brelse(bhs[i]); unlock_fat(sbi); - - fat_clusters_flush(sb); + if (dirty_fsinfo) + mark_fsinfo_dirty(sb); return err; } - EXPORT_SYMBOL_GPL(fat_free_clusters); /* 128kb is the whole sectors for FAT12 and FAT16 */ @@ -615,7 +658,7 @@ int fat_count_free_clusters(struct super_block *sb) int err = 0, free; lock_fat(sbi); - if (sbi->free_clusters != -1) + if (sbi->free_clusters != -1 && sbi->free_clus_valid) goto out; reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits; @@ -643,7 +686,8 @@ int fat_count_free_clusters(struct super_block *sb) } while (fat_ent_next(sbi, &fatent)); } sbi->free_clusters = free; - sb->s_dirt = 1; + sbi->free_clus_valid = 1; + mark_fsinfo_dirty(sb); fatent_brelse(&fatent); out: unlock_fat(sbi); diff --git a/fs/fat/file.c b/fs/fat/file.c index c614175876e..85f79a89e74 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -8,132 +8,179 @@ #include <linux/capability.h> #include <linux/module.h> +#include <linux/compat.h> +#include <linux/mount.h> #include <linux/time.h> -#include <linux/msdos_fs.h> -#include <linux/smp_lock.h> #include <linux/buffer_head.h> #include <linux/writeback.h> #include <linux/backing-dev.h> #include <linux/blkdev.h> +#include <linux/fsnotify.h> +#include <linux/security.h> +#include "fat.h" -int fat_generic_ioctl(struct inode *inode, struct file *filp, - unsigned int cmd, unsigned long arg) +static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr) { + u32 attr; + + mutex_lock(&inode->i_mutex); + attr = fat_make_attrs(inode); + mutex_unlock(&inode->i_mutex); + + return put_user(attr, user_attr); +} + +static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) +{ + struct inode *inode = file_inode(file); struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); - u32 __user *user_attr = (u32 __user *)arg; + int is_dir = S_ISDIR(inode->i_mode); + u32 attr, oldattr; + struct iattr ia; + int err; - switch (cmd) { - case FAT_IOCTL_GET_ATTRIBUTES: - { - u32 attr; + err = get_user(attr, user_attr); + if (err) + goto out; - if (inode->i_ino == MSDOS_ROOT_INO) - attr = ATTR_DIR; - else - attr = fat_attr(inode); + err = mnt_want_write_file(file); + if (err) + goto out; + mutex_lock(&inode->i_mutex); - return put_user(attr, user_attr); + /* + * ATTR_VOLUME and ATTR_DIR cannot be changed; this also + * prevents the user from turning us into a VFAT + * longname entry. Also, we obviously can't set + * any of the NTFS attributes in the high 24 bits. + */ + attr &= 0xff & ~(ATTR_VOLUME | ATTR_DIR); + /* Merge in ATTR_VOLUME and ATTR_DIR */ + attr |= (MSDOS_I(inode)->i_attrs & ATTR_VOLUME) | + (is_dir ? ATTR_DIR : 0); + oldattr = fat_make_attrs(inode); + + /* Equivalent to a chmod() */ + ia.ia_valid = ATTR_MODE | ATTR_CTIME; + ia.ia_ctime = current_fs_time(inode->i_sb); + if (is_dir) + ia.ia_mode = fat_make_mode(sbi, attr, S_IRWXUGO); + else { + ia.ia_mode = fat_make_mode(sbi, attr, + S_IRUGO | S_IWUGO | (inode->i_mode & S_IXUGO)); } - case FAT_IOCTL_SET_ATTRIBUTES: - { - u32 attr, oldattr; - int err, is_dir = S_ISDIR(inode->i_mode); - struct iattr ia; - err = get_user(attr, user_attr); - if (err) - return err; + /* The root directory has no attributes */ + if (inode->i_ino == MSDOS_ROOT_INO && attr != ATTR_DIR) { + err = -EINVAL; + goto out_unlock_inode; + } - mutex_lock(&inode->i_mutex); + if (sbi->options.sys_immutable && + ((attr | oldattr) & ATTR_SYS) && + !capable(CAP_LINUX_IMMUTABLE)) { + err = -EPERM; + goto out_unlock_inode; + } - if (IS_RDONLY(inode)) { - err = -EROFS; - goto up; - } + /* + * The security check is questionable... We single + * out the RO attribute for checking by the security + * module, just because it maps to a file mode. + */ + err = security_inode_setattr(file->f_path.dentry, &ia); + if (err) + goto out_unlock_inode; - /* - * ATTR_VOLUME and ATTR_DIR cannot be changed; this also - * prevents the user from turning us into a VFAT - * longname entry. Also, we obviously can't set - * any of the NTFS attributes in the high 24 bits. - */ - attr &= 0xff & ~(ATTR_VOLUME | ATTR_DIR); - /* Merge in ATTR_VOLUME and ATTR_DIR */ - attr |= (MSDOS_I(inode)->i_attrs & ATTR_VOLUME) | - (is_dir ? ATTR_DIR : 0); - oldattr = fat_attr(inode); - - /* Equivalent to a chmod() */ - ia.ia_valid = ATTR_MODE | ATTR_CTIME; - if (is_dir) { - ia.ia_mode = MSDOS_MKMODE(attr, - S_IRWXUGO & ~sbi->options.fs_dmask) - | S_IFDIR; - } else { - ia.ia_mode = MSDOS_MKMODE(attr, - (S_IRUGO | S_IWUGO | (inode->i_mode & S_IXUGO)) - & ~sbi->options.fs_fmask) - | S_IFREG; - } + /* This MUST be done before doing anything irreversible... */ + err = fat_setattr(file->f_path.dentry, &ia); + if (err) + goto out_unlock_inode; - /* The root directory has no attributes */ - if (inode->i_ino == MSDOS_ROOT_INO && attr != ATTR_DIR) { - err = -EINVAL; - goto up; - } + fsnotify_change(file->f_path.dentry, ia.ia_valid); + if (sbi->options.sys_immutable) { + if (attr & ATTR_SYS) + inode->i_flags |= S_IMMUTABLE; + else + inode->i_flags &= ~S_IMMUTABLE; + } - if (sbi->options.sys_immutable) { - if ((attr | oldattr) & ATTR_SYS) { - if (!capable(CAP_LINUX_IMMUTABLE)) { - err = -EPERM; - goto up; - } - } - } + fat_save_attrs(inode, attr); + mark_inode_dirty(inode); +out_unlock_inode: + mutex_unlock(&inode->i_mutex); + mnt_drop_write_file(file); +out: + return err; +} - /* This MUST be done before doing anything irreversible... */ - err = notify_change(filp->f_path.dentry, &ia); - if (err) - goto up; +static int fat_ioctl_get_volume_id(struct inode *inode, u32 __user *user_attr) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + return put_user(sbi->vol_id, user_attr); +} - if (sbi->options.sys_immutable) { - if (attr & ATTR_SYS) - inode->i_flags |= S_IMMUTABLE; - else - inode->i_flags &= S_IMMUTABLE; - } +long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) +{ + struct inode *inode = file_inode(filp); + u32 __user *user_attr = (u32 __user *)arg; - MSDOS_I(inode)->i_attrs = attr & ATTR_UNUSED; - mark_inode_dirty(inode); - up: - mutex_unlock(&inode->i_mutex); - return err; - } + switch (cmd) { + case FAT_IOCTL_GET_ATTRIBUTES: + return fat_ioctl_get_attributes(inode, user_attr); + case FAT_IOCTL_SET_ATTRIBUTES: + return fat_ioctl_set_attributes(filp, user_attr); + case FAT_IOCTL_GET_VOLUME_ID: + return fat_ioctl_get_volume_id(inode, user_attr); default: return -ENOTTY; /* Inappropriate ioctl for device */ } } +#ifdef CONFIG_COMPAT +static long fat_generic_compat_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) + +{ + return fat_generic_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + static int fat_file_release(struct inode *inode, struct file *filp) { if ((filp->f_mode & FMODE_WRITE) && MSDOS_SB(inode->i_sb)->options.flush) { fat_flush_inodes(inode->i_sb, inode, NULL); - congestion_wait(WRITE, HZ/10); + congestion_wait(BLK_RW_ASYNC, HZ/10); } return 0; } +int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) +{ + struct inode *inode = filp->f_mapping->host; + int res, err; + + res = generic_file_fsync(filp, start, end, datasync); + err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); + + return res ? res : err; +} + + const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, + .read = new_sync_read, + .write = new_sync_write, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, .mmap = generic_file_mmap, .release = fat_file_release, - .ioctl = fat_generic_ioctl, - .fsync = file_fsync, + .unlocked_ioctl = fat_generic_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = fat_generic_compat_ioctl, +#endif + .fsync = fat_file_fsync, .splice_read = generic_file_splice_read, }; @@ -149,110 +196,30 @@ static int fat_cont_expand(struct inode *inode, loff_t size) inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; mark_inode_dirty(inode); - if (IS_SYNC(inode)) - err = sync_page_range_nolock(inode, mapping, start, count); -out: - return err; -} - -static int check_mode(const struct msdos_sb_info *sbi, mode_t mode) -{ - mode_t req = mode & ~S_IFMT; - - /* - * Of the r and x bits, all (subject to umask) must be present. Of the - * w bits, either all (subject to umask) or none must be present. - */ - - if (S_ISREG(mode)) { - req &= ~sbi->options.fs_fmask; - - if ((req & (S_IRUGO | S_IXUGO)) != - ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_fmask)) - return -EPERM; - - if ((req & S_IWUGO) != 0 && - (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_fmask)) - return -EPERM; - } else if (S_ISDIR(mode)) { - req &= ~sbi->options.fs_dmask; - - if ((req & (S_IRUGO | S_IXUGO)) != - ((S_IRUGO | S_IXUGO) & ~sbi->options.fs_dmask)) - return -EPERM; - - if ((req & S_IWUGO) != 0 && - (req & S_IWUGO) != (S_IWUGO & ~sbi->options.fs_dmask)) - return -EPERM; - } else { - return -EPERM; - } + if (IS_SYNC(inode)) { + int err2; - return 0; -} - -int fat_notify_change(struct dentry *dentry, struct iattr *attr) -{ - struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); - struct inode *inode = dentry->d_inode; - int mask, error = 0; - - lock_kernel(); - - /* - * Expand the file. Since inode_setattr() updates ->i_size - * before calling the ->truncate(), but FAT needs to fill the - * hole before it. - */ - if (attr->ia_valid & ATTR_SIZE) { - if (attr->ia_size > inode->i_size) { - error = fat_cont_expand(inode, attr->ia_size); - if (error || attr->ia_valid == ATTR_SIZE) - goto out; - attr->ia_valid &= ~ATTR_SIZE; + /* + * Opencode syncing since we don't have a file open to use + * standard fsync path. + */ + err = filemap_fdatawrite_range(mapping, start, + start + count - 1); + err2 = sync_mapping_buffers(mapping); + if (!err) + err = err2; + err2 = write_inode_now(inode, 1); + if (!err) + err = err2; + if (!err) { + err = filemap_fdatawait_range(mapping, start, + start + count - 1); } } - - error = inode_change_ok(inode, attr); - if (error) { - if (sbi->options.quiet) - error = 0; - goto out; - } - if (((attr->ia_valid & ATTR_UID) && - (attr->ia_uid != sbi->options.fs_uid)) || - ((attr->ia_valid & ATTR_GID) && - (attr->ia_gid != sbi->options.fs_gid))) - error = -EPERM; - - if (error) { - if (sbi->options.quiet) - error = 0; - goto out; - } - - if (attr->ia_valid & ATTR_MODE) { - error = check_mode(sbi, attr->ia_mode); - if (error != 0 && !sbi->options.quiet) - goto out; - } - - error = inode_setattr(inode, attr); - if (error) - goto out; - - if (S_ISDIR(inode->i_mode)) - mask = sbi->options.fs_dmask; - else - mask = sbi->options.fs_fmask; - inode->i_mode &= S_IFMT | (S_IRWXUGO & ~mask); out: - unlock_kernel(); - return error; + return err; } -EXPORT_SYMBOL_GPL(fat_notify_change); - /* Free all clusters after the skip'th cluster. */ static int fat_free(struct inode *inode, int skip) { @@ -302,9 +269,9 @@ static int fat_free(struct inode *inode, int skip) fatent_brelse(&fatent); return 0; } else if (ret == FAT_ENT_FREE) { - fat_fs_panic(sb, + fat_fs_error(sb, "%s: invalid cluster chain (i_pos %lld)", - __FUNCTION__, MSDOS_I(inode)->i_pos); + __func__, MSDOS_I(inode)->i_pos); ret = -EIO; } else if (ret > 0) { err = fat_ent_write(inode, &fatent, FAT_ENT_EOF, wait); @@ -323,7 +290,7 @@ static int fat_free(struct inode *inode, int skip) return fat_free_clusters(inode, free_start); } -void fat_truncate(struct inode *inode) +void fat_truncate_blocks(struct inode *inode, loff_t offset) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); const unsigned int cluster_size = sbi->cluster_size; @@ -333,14 +300,12 @@ void fat_truncate(struct inode *inode) * This protects against truncating a file bigger than it was then * trying to write into the hole. */ - if (MSDOS_I(inode)->mmu_private > inode->i_size) - MSDOS_I(inode)->mmu_private = inode->i_size; + if (MSDOS_I(inode)->mmu_private > offset) + MSDOS_I(inode)->mmu_private = offset; - nr_clusters = (inode->i_size + (cluster_size - 1)) >> sbi->cluster_bits; + nr_clusters = (offset + (cluster_size - 1)) >> sbi->cluster_bits; - lock_kernel(); fat_free(inode, nr_clusters); - unlock_kernel(); fat_flush_inodes(inode->i_sb, inode, NULL); } @@ -349,12 +314,149 @@ int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) struct inode *inode = dentry->d_inode; generic_fillattr(inode, stat); stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size; + + if (MSDOS_SB(inode->i_sb)->options.nfs == FAT_NFS_NOSTALE_RO) { + /* Use i_pos for ino. This is used as fileid of nfs. */ + stat->ino = fat_i_pos_read(MSDOS_SB(inode->i_sb), inode); + } return 0; } EXPORT_SYMBOL_GPL(fat_getattr); +static int fat_sanitize_mode(const struct msdos_sb_info *sbi, + struct inode *inode, umode_t *mode_ptr) +{ + umode_t mask, perm; + + /* + * Note, the basic check is already done by a caller of + * (attr->ia_mode & ~FAT_VALID_MODE) + */ + + if (S_ISREG(inode->i_mode)) + mask = sbi->options.fs_fmask; + else + mask = sbi->options.fs_dmask; + + perm = *mode_ptr & ~(S_IFMT | mask); + + /* + * Of the r and x bits, all (subject to umask) must be present. Of the + * w bits, either all (subject to umask) or none must be present. + * + * If fat_mode_can_hold_ro(inode) is false, can't change w bits. + */ + if ((perm & (S_IRUGO | S_IXUGO)) != (inode->i_mode & (S_IRUGO|S_IXUGO))) + return -EPERM; + if (fat_mode_can_hold_ro(inode)) { + if ((perm & S_IWUGO) && ((perm & S_IWUGO) != (S_IWUGO & ~mask))) + return -EPERM; + } else { + if ((perm & S_IWUGO) != (S_IWUGO & ~mask)) + return -EPERM; + } + + *mode_ptr &= S_IFMT | perm; + + return 0; +} + +static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode) +{ + umode_t allow_utime = sbi->options.allow_utime; + + if (!uid_eq(current_fsuid(), inode->i_uid)) { + if (in_group_p(inode->i_gid)) + allow_utime >>= 3; + if (allow_utime & MAY_WRITE) + return 1; + } + + /* use a default check */ + return 0; +} + +#define TIMES_SET_FLAGS (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET) +/* valid file mode bits */ +#define FAT_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXUGO) + +int fat_setattr(struct dentry *dentry, struct iattr *attr) +{ + struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); + struct inode *inode = dentry->d_inode; + unsigned int ia_valid; + int error; + + /* Check for setting the inode time. */ + ia_valid = attr->ia_valid; + if (ia_valid & TIMES_SET_FLAGS) { + if (fat_allow_set_time(sbi, inode)) + attr->ia_valid &= ~TIMES_SET_FLAGS; + } + + error = inode_change_ok(inode, attr); + attr->ia_valid = ia_valid; + if (error) { + if (sbi->options.quiet) + error = 0; + goto out; + } + + /* + * Expand the file. Since inode_setattr() updates ->i_size + * before calling the ->truncate(), but FAT needs to fill the + * hole before it. XXX: this is no longer true with new truncate + * sequence. + */ + if (attr->ia_valid & ATTR_SIZE) { + inode_dio_wait(inode); + + if (attr->ia_size > inode->i_size) { + error = fat_cont_expand(inode, attr->ia_size); + if (error || attr->ia_valid == ATTR_SIZE) + goto out; + attr->ia_valid &= ~ATTR_SIZE; + } + } + + if (((attr->ia_valid & ATTR_UID) && + (!uid_eq(attr->ia_uid, sbi->options.fs_uid))) || + ((attr->ia_valid & ATTR_GID) && + (!gid_eq(attr->ia_gid, sbi->options.fs_gid))) || + ((attr->ia_valid & ATTR_MODE) && + (attr->ia_mode & ~FAT_VALID_MODE))) + error = -EPERM; + + if (error) { + if (sbi->options.quiet) + error = 0; + goto out; + } + + /* + * We don't return -EPERM here. Yes, strange, but this is too + * old behavior. + */ + if (attr->ia_valid & ATTR_MODE) { + if (fat_sanitize_mode(sbi, inode, &attr->ia_mode) < 0) + attr->ia_valid &= ~ATTR_MODE; + } + + if (attr->ia_valid & ATTR_SIZE) { + down_write(&MSDOS_I(inode)->truncate_lock); + truncate_setsize(inode, attr->ia_size); + fat_truncate_blocks(inode, attr->ia_size); + up_write(&MSDOS_I(inode)->truncate_lock); + } + + setattr_copy(inode, attr); + mark_inode_dirty(inode); +out: + return error; +} +EXPORT_SYMBOL_GPL(fat_setattr); + const struct inode_operations fat_file_inode_operations = { - .truncate = fat_truncate, - .setattr = fat_notify_change, + .setattr = fat_setattr, .getattr = fat_getattr, }; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 53f3cf62b7c..756aead10d9 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -14,29 +14,92 @@ #include <linux/init.h> #include <linux/time.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/seq_file.h> -#include <linux/msdos_fs.h> #include <linux/pagemap.h> #include <linux/mpage.h> #include <linux/buffer_head.h> -#include <linux/exportfs.h> #include <linux/mount.h> +#include <linux/aio.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 <linux/blkdev.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 +#define KB_IN_SECTORS 2 + +/* + * A deserialized copy of the on-disk structure laid out in struct + * fat_boot_sector. + */ +struct fat_bios_param_block { + u16 fat_sector_size; + u8 fat_sec_per_clus; + u16 fat_reserved; + u8 fat_fats; + u16 fat_dir_entries; + u16 fat_sectors; + u16 fat_fat_length; + u32 fat_total_sect; + + u8 fat16_state; + u32 fat16_vol_id; + + u32 fat32_length; + u32 fat32_root_cluster; + u16 fat32_info_sector; + u8 fat32_state; + u32 fat32_vol_id; +}; + static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE; static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET; +static struct fat_floppy_defaults { + unsigned nr_sectors; + unsigned sec_per_clus; + unsigned dir_entries; + unsigned media; + unsigned fat_length; +} floppy_defaults[] = { +{ + .nr_sectors = 160 * KB_IN_SECTORS, + .sec_per_clus = 1, + .dir_entries = 64, + .media = 0xFE, + .fat_length = 1, +}, +{ + .nr_sectors = 180 * KB_IN_SECTORS, + .sec_per_clus = 1, + .dir_entries = 64, + .media = 0xFC, + .fat_length = 2, +}, +{ + .nr_sectors = 320 * KB_IN_SECTORS, + .sec_per_clus = 2, + .dir_entries = 112, + .media = 0xFF, + .fat_length = 1, +}, +{ + .nr_sectors = 360 * KB_IN_SECTORS, + .sec_per_clus = 2, + .dir_entries = 112, + .media = 0xFD, + .fat_length = 2, +}, +}; static int fat_add_cluster(struct inode *inode) { @@ -63,7 +126,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, sector_t phys; int err, offset; - err = fat_bmap(inode, iblock, &phys, &mapped_blocks); + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create); if (err) return err; if (phys) { @@ -75,7 +138,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, return 0; if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) { - fat_fs_panic(sb, "corrupted file size (i_pos %lld, %lld)", + fat_fs_error(sb, "corrupted file size (i_pos %lld, %lld)", MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); return -EIO; } @@ -93,7 +156,7 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, *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); + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create); if (err) return err; @@ -141,14 +204,29 @@ static int fat_readpages(struct file *file, struct address_space *mapping, return mpage_readpages(mapping, pages, nr_pages, fat_get_block); } +static void fat_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, inode->i_size); + fat_truncate_blocks(inode, inode->i_size); + } +} + static int fat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int err; + *pagep = NULL; - return cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - fat_get_block, + err = cont_write_begin(file, mapping, pos, len, flags, + pagep, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); + if (err < 0) + fat_write_failed(mapping, pos + len); + return err; } static int fat_write_end(struct file *file, struct address_space *mapping, @@ -158,6 +236,8 @@ static int fat_write_end(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; int err; err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + if (err < len) + fat_write_failed(mapping, pos + len); 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; @@ -167,15 +247,18 @@ static int fat_write_end(struct file *file, struct address_space *mapping, } static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) + struct iov_iter *iter, + loff_t offset) { struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); + ssize_t ret; if (rw == WRITE) { /* - * FIXME: blockdev_direct_IO() doesn't use ->prepare_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 @@ -183,7 +266,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * * Return 0, and fallback to normal buffered write. */ - loff_t size = offset + iov_length(iov, nr_segs); + loff_t size = offset + count; if (MSDOS_I(inode)->mmu_private < size) return 0; } @@ -192,13 +275,23 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * 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); + ret = blockdev_direct_IO(rw, iocb, inode, iter, offset, fat_get_block); + if (ret < 0 && (rw & WRITE)) + fat_write_failed(mapping, offset + count); + + return ret; } static sector_t _fat_bmap(struct address_space *mapping, sector_t block) { - return generic_block_bmap(mapping, block, fat_get_block); + sector_t blocknr; + + /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ + down_read(&MSDOS_I(mapping->host)->truncate_lock); + blocknr = generic_block_bmap(mapping, block, fat_get_block); + up_read(&MSDOS_I(mapping->host)->truncate_lock); + + return blocknr; } static const struct address_space_operations fat_aops = { @@ -206,7 +299,6 @@ static const struct address_space_operations fat_aops = { .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, @@ -232,7 +324,7 @@ static const struct address_space_operations fat_aops = { * 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. + * 6. fat_evict_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. */ @@ -247,25 +339,48 @@ static void fat_hash_init(struct super_block *sb) INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); } -static inline unsigned long fat_hash(struct super_block *sb, loff_t i_pos) +static inline unsigned long fat_hash(loff_t i_pos) { - unsigned long tmp = (unsigned long)i_pos | (unsigned long) sb; - tmp = tmp + (tmp >> FAT_HASH_BITS) + (tmp >> FAT_HASH_BITS * 2); - return tmp & FAT_HASH_MASK; + return hash_32(i_pos, FAT_HASH_BITS); } -void fat_attach(struct inode *inode, loff_t i_pos) +static void dir_hash_init(struct super_block *sb) { - struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); + int i; - spin_lock(&sbi->inode_hash_lock); - MSDOS_I(inode)->i_pos = i_pos; - hlist_add_head(&MSDOS_I(inode)->i_fat_hash, - sbi->inode_hashtable + fat_hash(sb, i_pos)); - spin_unlock(&sbi->inode_hash_lock); + spin_lock_init(&sbi->dir_hash_lock); + for (i = 0; i < FAT_HASH_SIZE; i++) + INIT_HLIST_HEAD(&sbi->dir_hashtable[i]); } +void fat_attach(struct inode *inode, loff_t i_pos) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + + if (inode->i_ino != MSDOS_ROOT_INO) { + 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); + } + + /* If NFS support is enabled, cache the mapping of start cluster + * to directory inode. This is used during reconnection of + * dentries to the filesystem root. + */ + if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { + struct hlist_head *d_head = sbi->dir_hashtable; + d_head += fat_dir_hash(MSDOS_I(inode)->i_logstart); + + spin_lock(&sbi->dir_hash_lock); + hlist_add_head(&MSDOS_I(inode)->i_dir_hash, d_head); + spin_unlock(&sbi->dir_hash_lock); + } +} EXPORT_SYMBOL_GPL(fat_attach); void fat_detach(struct inode *inode) @@ -275,20 +390,24 @@ void fat_detach(struct inode *inode) MSDOS_I(inode)->i_pos = 0; hlist_del_init(&MSDOS_I(inode)->i_fat_hash); spin_unlock(&sbi->inode_hash_lock); -} + if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { + spin_lock(&sbi->dir_hash_lock); + hlist_del_init(&MSDOS_I(inode)->i_dir_hash); + spin_unlock(&sbi->dir_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(sb, i_pos); - struct hlist_node *_p; + struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); 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) { + hlist_for_each_entry(i, head, i_fat_hash) { BUG_ON(i->vfs_inode.i_sb != sb); if (i->i_pos != i_pos) continue; @@ -302,7 +421,7 @@ struct inode *fat_iget(struct super_block *sb, loff_t i_pos) static int is_exec(unsigned char *extension) { - unsigned char *exe_extensions = "EXECOMBAT", *walk; + unsigned char exe_extensions[] = "EXECOMBAT", *walk; for (walk = exe_extensions; *walk; walk += 3) if (!strncmp(extension, walk, 3)) @@ -328,7 +447,7 @@ static int fat_calc_dir_size(struct inode *inode) } /* doesn't deal with root inode */ -static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) +int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); int error; @@ -341,31 +460,24 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { inode->i_generation &= ~1; - inode->i_mode = MSDOS_MKMODE(de->attr, - S_IRWXUGO & ~sbi->options.fs_dmask) | S_IFDIR; + 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_start = fat_get_start(sbi, de); 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); + set_nlink(inode, fat_subdirs(inode)); } else { /* not a directory */ inode->i_generation |= 1; - inode->i_mode = MSDOS_MKMODE(de->attr, - ((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); - if (sbi->fat_bits == 32) - MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16); + 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 = fat_get_start(sbi, de); MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; inode->i_size = le32_to_cpu(de->size); @@ -378,34 +490,41 @@ static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) if (sbi->options.sys_immutable) inode->i_flags |= S_IMMUTABLE; } - MSDOS_I(inode)->i_attrs = de->attr & ATTR_UNUSED; + fat_save_attrs(inode, de->attr); + inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) & ~((loff_t)sbi->cluster_size - 1)) >> 9; - inode->i_mtime.tv_sec = - date_dos2unix(le16_to_cpu(de->time), le16_to_cpu(de->date)); - inode->i_mtime.tv_nsec = 0; + + fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0); if (sbi->options.isvfat) { - int secs = de->ctime_cs / 100; - int csecs = de->ctime_cs % 100; - inode->i_ctime.tv_sec = - date_dos2unix(le16_to_cpu(de->ctime), - le16_to_cpu(de->cdate)) + secs; - inode->i_ctime.tv_nsec = csecs * 10000000; - inode->i_atime.tv_sec = - date_dos2unix(0, le16_to_cpu(de->adate)); - inode->i_atime.tv_nsec = 0; + 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; } +static inline void fat_lock_build_inode(struct msdos_sb_info *sbi) +{ + if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) + mutex_lock(&sbi->nfs_build_inode_lock); +} + +static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi) +{ + if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) + mutex_unlock(&sbi->nfs_build_inode_lock); +} + struct inode *fat_build_inode(struct super_block *sb, struct msdos_dir_entry *de, loff_t i_pos) { struct inode *inode; int err; + fat_lock_build_inode(MSDOS_SB(sb)); inode = fat_iget(sb, i_pos); if (inode) goto out; @@ -425,64 +544,92 @@ struct inode *fat_build_inode(struct super_block *sb, fat_attach(inode, i_pos); insert_inode_hash(inode); out: + fat_unlock_build_inode(MSDOS_SB(sb)); return inode; } EXPORT_SYMBOL_GPL(fat_build_inode); -static void fat_delete_inode(struct inode *inode) +static void fat_evict_inode(struct inode *inode) { - truncate_inode_pages(&inode->i_data, 0); - - if (!is_bad_inode(inode)) { + truncate_inode_pages_final(&inode->i_data); + if (!inode->i_nlink) { inode->i_size = 0; - fat_truncate(inode); + fat_truncate_blocks(inode, 0); } + invalidate_inode_buffers(inode); clear_inode(inode); + fat_cache_inval_inode(inode); + fat_detach(inode); } -static void fat_clear_inode(struct inode *inode) +static void fat_set_state(struct super_block *sb, + unsigned int set, unsigned int force) { - struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + struct buffer_head *bh; + struct fat_boot_sector *b; + struct msdos_sb_info *sbi = sb->s_fs_info; - if (is_bad_inode(inode)) + /* do not change any thing if mounted read only */ + if ((sb->s_flags & MS_RDONLY) && !force) return; - lock_kernel(); - spin_lock(&sbi->inode_hash_lock); - fat_cache_inval_inode(inode); - hlist_del_init(&MSDOS_I(inode)->i_fat_hash); - spin_unlock(&sbi->inode_hash_lock); - unlock_kernel(); + + /* do not change state if fs was dirty */ + if (sbi->dirty) { + /* warn only on set (mount). */ + if (set) + fat_msg(sb, KERN_WARNING, "Volume was not properly " + "unmounted. Some data may be corrupt. " + "Please run fsck."); + return; + } + + bh = sb_bread(sb, 0); + if (bh == NULL) { + fat_msg(sb, KERN_ERR, "unable to read boot sector " + "to mark fs as dirty"); + return; + } + + b = (struct fat_boot_sector *) bh->b_data; + + if (sbi->fat_bits == 32) { + if (set) + b->fat32.state |= FAT_STATE_DIRTY; + else + b->fat32.state &= ~FAT_STATE_DIRTY; + } else /* fat 16 and 12 */ { + if (set) + b->fat16.state |= FAT_STATE_DIRTY; + else + b->fat16.state &= ~FAT_STATE_DIRTY; + } + + mark_buffer_dirty(bh); + sync_dirty_buffer(bh); + brelse(bh); } -static void fat_write_super(struct super_block *sb) +static void delayed_free(struct rcu_head *p) { - sb->s_dirt = 0; - - if (!(sb->s_flags & MS_RDONLY)) - fat_clusters_flush(sb); + struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); + unload_nls(sbi->nls_disk); + unload_nls(sbi->nls_io); + if (sbi->options.iocharset != fat_default_iocharset) + kfree(sbi->options.iocharset); + kfree(sbi); } 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; - } + fat_set_state(sb, 0, 0); - sb->s_fs_info = NULL; - kfree(sbi); + iput(sbi->fsinfo_inode); + iput(sbi->fat_inode); + + call_rcu(&sbi->rcu, delayed_free); } static struct kmem_cache *fat_inode_cachep; @@ -490,18 +637,26 @@ 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_KERNEL); + ei = kmem_cache_alloc(fat_inode_cachep, GFP_NOFS); if (!ei) return NULL; + + init_rwsem(&ei->truncate_lock); return &ei->vfs_inode; } -static void fat_destroy_inode(struct inode *inode) +static void fat_i_callback(struct rcu_head *head) { + struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); } -static void init_once(struct kmem_cache *cachep, void *foo) +static void fat_destroy_inode(struct inode *inode) +{ + call_rcu(&inode->i_rcu, fat_i_callback); +} + +static void init_once(void *foo) { struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; @@ -510,6 +665,7 @@ static void init_once(struct kmem_cache *cachep, void *foo) ei->cache_valid_id = FAT_CACHE_VALID + 1; INIT_LIST_HEAD(&ei->cache_lru); INIT_HLIST_NODE(&ei->i_fat_hash); + INIT_HLIST_NODE(&ei->i_dir_hash); inode_init_once(&ei->vfs_inode); } @@ -527,22 +683,41 @@ static int __init fat_init_inodecache(void) static void __exit fat_destroy_inodecache(void) { + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); kmem_cache_destroy(fat_inode_cachep); } static int fat_remount(struct super_block *sb, int *flags, char *data) { + int new_rdonly; struct msdos_sb_info *sbi = MSDOS_SB(sb); *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME); + + sync_filesystem(sb); + + /* make sure we update state on remount. */ + new_rdonly = *flags & MS_RDONLY; + if (new_rdonly != (sb->s_flags & MS_RDONLY)) { + if (new_rdonly) + fat_set_state(sb, 0, 0); + else + fat_set_state(sb, 1, 1); + } return 0; } static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) { - struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); + struct super_block *sb = dentry->d_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); /* If the count of free cluster is still unknown, counts it here. */ - if (sbi->free_clusters == -1) { + if (sbi->free_clusters == -1 || !sbi->free_clus_valid) { int err = fat_count_free_clusters(dentry->d_sb); if (err) return err; @@ -553,245 +728,126 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = sbi->max_cluster - FAT_START_ENT; buf->f_bfree = sbi->free_clusters; buf->f_bavail = sbi->free_clusters; - buf->f_namelen = sbi->options.isvfat ? 260 : 12; + buf->f_fsid.val[0] = (u32)id; + buf->f_fsid.val[1] = (u32)(id >> 32); + buf->f_namelen = + (sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE; return 0; } -static int fat_write_inode(struct inode *inode, int wait) +static int __fat_write_inode(struct inode *inode, int wait) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct msdos_dir_entry *raw_entry; loff_t i_pos; - int err = 0; + sector_t blocknr; + int err, offset; + + if (inode->i_ino == MSDOS_ROOT_INO) + return 0; retry: - i_pos = MSDOS_I(inode)->i_pos; - if (inode->i_ino == MSDOS_ROOT_INO || !i_pos) + i_pos = fat_i_pos_read(sbi, inode); + if (!i_pos) return 0; - lock_kernel(); - bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits); + fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); + bh = sb_bread(sb, blocknr); if (!bh) { - printk(KERN_ERR "FAT: unable to read inode block " - "for updating (i_pos %lld)\n", i_pos); - err = -EIO; - goto out; + fat_msg(sb, KERN_ERR, "unable to read inode block " + "for updating (i_pos %lld)", i_pos); + return -EIO; } spin_lock(&sbi->inode_hash_lock); if (i_pos != MSDOS_I(inode)->i_pos) { spin_unlock(&sbi->inode_hash_lock); brelse(bh); - unlock_kernel(); goto retry; } - raw_entry = &((struct msdos_dir_entry *) (bh->b_data)) - [i_pos & (sbi->dir_per_block - 1)]; + raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset]; if (S_ISDIR(inode->i_mode)) raw_entry->size = 0; else raw_entry->size = cpu_to_le32(inode->i_size); - raw_entry->attr = fat_attr(inode); - raw_entry->start = cpu_to_le16(MSDOS_I(inode)->i_logstart); - raw_entry->starthi = cpu_to_le16(MSDOS_I(inode)->i_logstart >> 16); - fat_date_unix2dos(inode->i_mtime.tv_sec, &raw_entry->time, &raw_entry->date); + raw_entry->attr = fat_make_attrs(inode); + fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart); + fat_time_unix2fat(sbi, &inode->i_mtime, &raw_entry->time, + &raw_entry->date, NULL); if (sbi->options.isvfat) { __le16 atime; - fat_date_unix2dos(inode->i_ctime.tv_sec,&raw_entry->ctime,&raw_entry->cdate); - fat_date_unix2dos(inode->i_atime.tv_sec,&atime,&raw_entry->adate); - raw_entry->ctime_cs = (inode->i_ctime.tv_sec & 1) * 100 + - inode->i_ctime.tv_nsec / 10000000; + fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime, + &raw_entry->cdate, &raw_entry->ctime_cs); + fat_time_unix2fat(sbi, &inode->i_atime, &atime, + &raw_entry->adate, NULL); } spin_unlock(&sbi->inode_hash_lock); mark_buffer_dirty(bh); + err = 0; if (wait) err = sync_dirty_buffer(bh); brelse(bh); -out: - unlock_kernel(); + return err; +} + +static int fat_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + int err; + + if (inode->i_ino == MSDOS_FSINFO_INO) { + struct super_block *sb = inode->i_sb; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + err = fat_clusters_flush(sb); + mutex_unlock(&MSDOS_SB(sb)->s_lock); + } else + err = __fat_write_inode(inode, wbc->sync_mode == WB_SYNC_ALL); + return err; } int fat_sync_inode(struct inode *inode) { - return fat_write_inode(inode, 1); + return __fat_write_inode(inode, 1); } EXPORT_SYMBOL_GPL(fat_sync_inode); -static int fat_show_options(struct seq_file *m, struct vfsmount *mnt); +static int fat_show_options(struct seq_file *m, struct dentry *root); static const struct super_operations fat_sops = { .alloc_inode = fat_alloc_inode, .destroy_inode = fat_destroy_inode, .write_inode = fat_write_inode, - .delete_inode = fat_delete_inode, + .evict_inode = fat_evict_inode, .put_super = fat_put_super, - .write_super = fat_write_super, .statfs = fat_statfs, - .clear_inode = fat_clear_inode, .remount_fs = fat_remount, .show_options = fat_show_options, }; -/* - * a FAT file handle with fhtype 3 is - * 0/ i_ino - for fast, reliable lookup if still in the cache - * 1/ i_generation - to see if i_ino is still valid - * bit 0 == 0 iff directory - * 2/ i_pos(8-39) - if ino has changed, but still in cache - * 3/ i_pos(4-7)|i_logstart - to semi-verify inode found at i_pos - * 4/ i_pos(0-3)|parent->i_logstart - maybe used to hunt for the file on disc - * - * Hack for NFSv2: Maximum FAT entry number is 28bits and maximum - * i_pos is 40bits (blocknr(32) + dir offset(8)), so two 4bits - * of i_logstart is used to store the directory entry offset. - */ - -static struct dentry *fat_fh_to_dentry(struct super_block *sb, - struct fid *fid, int fh_len, int fh_type) -{ - struct inode *inode = NULL; - struct dentry *result; - u32 *fh = fid->raw; - - if (fh_len < 5 || fh_type != 3) - return NULL; - - inode = ilookup(sb, fh[0]); - if (!inode || inode->i_generation != fh[1]) { - if (inode) - iput(inode); - inode = NULL; - } - if (!inode) { - loff_t i_pos; - int i_logstart = fh[3] & 0x0fffffff; - - i_pos = (loff_t)fh[2] << 8; - i_pos |= ((fh[3] >> 24) & 0xf0) | (fh[4] >> 28); - - /* try 2 - see if i_pos is in F-d-c - * require i_logstart to be the same - * Will fail if you truncate and then re-write - */ - - inode = fat_iget(sb, i_pos); - if (inode && MSDOS_I(inode)->i_logstart != i_logstart) { - iput(inode); - inode = NULL; - } - } - if (!inode) { - /* For now, do nothing - * What we could do is: - * follow the file starting at fh[4], and record - * the ".." entry, and the name of the fh[2] entry. - * The follow the ".." file finding the next step up. - * This way we build a path to the root of - * the tree. If this works, we lookup the path and so - * get this inode into the cache. - * Finally try the fat_iget lookup again - * If that fails, then weare totally out of luck - * But all that is for another day - */ - } - if (!inode) - return ERR_PTR(-ESTALE); - - - /* now to find a dentry. - * If possible, get a well-connected one - */ - result = d_alloc_anon(inode); - if (result == NULL) { - iput(inode); - return ERR_PTR(-ENOMEM); - } - result->d_op = sb->s_root->d_op; - return result; -} - -static int -fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable) +static int fat_show_options(struct seq_file *m, struct dentry *root) { - int len = *lenp; - struct inode *inode = de->d_inode; - u32 ipos_h, ipos_m, ipos_l; - - if (len < 5) - return 255; /* no room */ - - ipos_h = MSDOS_I(inode)->i_pos >> 8; - ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24; - ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28; - *lenp = 5; - fh[0] = inode->i_ino; - fh[1] = inode->i_generation; - fh[2] = ipos_h; - fh[3] = ipos_m | MSDOS_I(inode)->i_logstart; - spin_lock(&de->d_lock); - fh[4] = ipos_l | MSDOS_I(de->d_parent->d_inode)->i_logstart; - spin_unlock(&de->d_lock); - return 3; -} - -static struct dentry *fat_get_parent(struct dentry *child) -{ - struct buffer_head *bh; - struct msdos_dir_entry *de; - loff_t i_pos; - struct dentry *parent; - struct inode *inode; - int err; - - lock_kernel(); - - err = fat_get_dotdot_entry(child->d_inode, &bh, &de, &i_pos); - if (err) { - parent = ERR_PTR(err); - goto out; - } - inode = fat_build_inode(child->d_sb, de, i_pos); - brelse(bh); - if (IS_ERR(inode)) { - parent = ERR_CAST(inode); - goto out; - } - parent = d_alloc_anon(inode); - if (!parent) { - iput(inode); - parent = ERR_PTR(-ENOMEM); - } -out: - unlock_kernel(); - - return parent; -} - -static const struct export_operations fat_export_ops = { - .encode_fh = fat_encode_fh, - .fh_to_dentry = fat_fh_to_dentry, - .get_parent = fat_get_parent, -}; - -static int fat_show_options(struct seq_file *m, struct vfsmount *mnt) -{ - struct msdos_sb_info *sbi = MSDOS_SB(mnt->mnt_sb); + struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb); struct fat_mount_options *opts = &sbi->options; int isvfat = opts->isvfat; - if (opts->fs_uid != 0) - seq_printf(m, ",uid=%u", opts->fs_uid); - if (opts->fs_gid != 0) - seq_printf(m, ",gid=%u", opts->fs_gid); + if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->fs_uid)); + if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->fs_gid)); seq_printf(m, ",fmask=%04o", opts->fs_fmask); seq_printf(m, ",dmask=%04o", opts->fs_dmask); + if (opts->allow_utime) + seq_printf(m, ",allow_utime=%04o", opts->allow_utime); if (sbi->nls_disk) - seq_printf(m, ",codepage=%s", sbi->nls_disk->charset); + /* strip "cp" prefix from displayed option */ + seq_printf(m, ",codepage=%s", &sbi->nls_disk->charset[2]); if (isvfat) { if (sbi->nls_io) seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); @@ -807,7 +863,7 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt) seq_puts(m, ",shortname=mixed"); break; case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95: - /* seq_puts(m, ",shortname=lower"); */ + seq_puts(m, ",shortname=lower"); break; default: seq_puts(m, ",shortname=unknown"); @@ -836,25 +892,49 @@ static int fat_show_options(struct seq_file *m, struct vfsmount *mnt) seq_puts(m, ",uni_xlate"); if (!opts->numtail) seq_puts(m, ",nonumtail"); + if (opts->rodir) + seq_puts(m, ",rodir"); } - if (sbi->options.flush) + if (opts->flush) seq_puts(m, ",flush"); + if (opts->tz_set) { + if (opts->time_offset) + seq_printf(m, ",time_offset=%d", opts->time_offset); + else + seq_puts(m, ",tz=UTC"); + } + if (opts->errors == FAT_ERRORS_CONT) + seq_puts(m, ",errors=continue"); + else if (opts->errors == FAT_ERRORS_PANIC) + seq_puts(m, ",errors=panic"); + else + seq_puts(m, ",errors=remount-ro"); + if (opts->nfs == FAT_NFS_NOSTALE_RO) + seq_puts(m, ",nfs=nostale_ro"); + else if (opts->nfs) + seq_puts(m, ",nfs=stale_rw"); + if (opts->discard) + seq_puts(m, ",discard"); + if (opts->dos1xfloppy) + seq_puts(m, ",dos1xfloppy"); return 0; } enum { Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid, - 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_umask, Opt_dmask, Opt_fmask, Opt_allow_utime, 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_flush, Opt_err, + Opt_obsolete, Opt_flush, Opt_tz_utc, Opt_rodir, Opt_err_cont, + Opt_err_panic, Opt_err_ro, Opt_discard, Opt_nfs, Opt_time_offset, + Opt_nfs_stale_rw, Opt_nfs_nostale_ro, Opt_err, Opt_dos1xfloppy, }; -static match_table_t fat_tokens = { +static const match_table_t fat_tokens = { {Opt_check_r, "check=relaxed"}, {Opt_check_s, "check=strict"}, {Opt_check_n, "check=normal"}, @@ -866,6 +946,7 @@ static match_table_t fat_tokens = { {Opt_umask, "umask=%o"}, {Opt_dmask, "dmask=%o"}, {Opt_fmask, "fmask=%o"}, + {Opt_allow_utime, "allow_utime=%o"}, {Opt_codepage, "codepage=%u"}, {Opt_usefree, "usefree"}, {Opt_nocase, "nocase"}, @@ -873,28 +954,38 @@ static match_table_t fat_tokens = { {Opt_showexec, "showexec"}, {Opt_debug, "debug"}, {Opt_immutable, "sys_immutable"}, - {Opt_obsolate, "conv=binary"}, - {Opt_obsolate, "conv=text"}, - {Opt_obsolate, "conv=auto"}, - {Opt_obsolate, "conv=b"}, - {Opt_obsolate, "conv=t"}, - {Opt_obsolate, "conv=a"}, - {Opt_obsolate, "fat=%u"}, - {Opt_obsolate, "blocksize=%u"}, - {Opt_obsolate, "cvf_format=%20s"}, - {Opt_obsolate, "cvf_options=%100s"}, - {Opt_obsolate, "posix"}, {Opt_flush, "flush"}, + {Opt_tz_utc, "tz=UTC"}, + {Opt_time_offset, "time_offset=%d"}, + {Opt_err_cont, "errors=continue"}, + {Opt_err_panic, "errors=panic"}, + {Opt_err_ro, "errors=remount-ro"}, + {Opt_discard, "discard"}, + {Opt_nfs_stale_rw, "nfs"}, + {Opt_nfs_stale_rw, "nfs=stale_rw"}, + {Opt_nfs_nostale_ro, "nfs=nostale_ro"}, + {Opt_dos1xfloppy, "dos1xfloppy"}, + {Opt_obsolete, "conv=binary"}, + {Opt_obsolete, "conv=text"}, + {Opt_obsolete, "conv=auto"}, + {Opt_obsolete, "conv=b"}, + {Opt_obsolete, "conv=t"}, + {Opt_obsolete, "conv=a"}, + {Opt_obsolete, "fat=%u"}, + {Opt_obsolete, "blocksize=%u"}, + {Opt_obsolete, "cvf_format=%20s"}, + {Opt_obsolete, "cvf_options=%100s"}, + {Opt_obsolete, "posix"}, {Opt_err, NULL}, }; -static match_table_t msdos_tokens = { +static const match_table_t msdos_tokens = { {Opt_nodots, "nodots"}, {Opt_nodots, "dotsOK=no"}, {Opt_dots, "dots"}, {Opt_dots, "dotsOK=yes"}, {Opt_err, NULL} }; -static match_table_t vfat_tokens = { +static const match_table_t vfat_tokens = { {Opt_charset, "iocharset=%s"}, {Opt_shortname_lower, "shortname=lower"}, {Opt_shortname_win95, "shortname=win95"}, @@ -921,11 +1012,12 @@ static match_table_t vfat_tokens = { {Opt_nonumtail_yes, "nonumtail=yes"}, {Opt_nonumtail_yes, "nonumtail=true"}, {Opt_nonumtail_yes, "nonumtail"}, + {Opt_rodir, "rodir"}, {Opt_err, NULL} }; -static int parse_options(char *options, int is_vfat, int silent, int *debug, - struct fat_mount_options *opts) +static int parse_options(struct super_block *sb, char *options, int is_vfat, + int silent, int *debug, struct fat_mount_options *opts) { char *p; substring_t args[MAX_OPT_ARGS]; @@ -934,24 +1026,31 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug, opts->isvfat = is_vfat; - opts->fs_uid = current->uid; - opts->fs_gid = current->gid; - opts->fs_fmask = opts->fs_dmask = current->fs->umask; + opts->fs_uid = current_uid(); + opts->fs_gid = current_gid(); + opts->fs_fmask = opts->fs_dmask = current_umask(); + opts->allow_utime = -1; opts->codepage = fat_default_codepage; opts->iocharset = fat_default_iocharset; - if (is_vfat) - opts->shortname = VFAT_SFN_DISPLAY_LOWER|VFAT_SFN_CREATE_WIN95; - else + if (is_vfat) { + opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; + opts->rodir = 0; + } else { opts->shortname = 0; + opts->rodir = 1; + } opts->name_check = 'n'; opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK = 0; opts->utf8 = opts->unicode_xlate = 0; opts->numtail = 1; opts->usefree = opts->nocase = 0; + opts->tz_set = 0; + opts->nfs = 0; + opts->errors = FAT_ERRORS_RO; *debug = 0; if (!options) - return 0; + goto out; while ((p = strsep(&options, ",")) != NULL) { int token; @@ -1001,37 +1100,76 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug, break; case Opt_uid: if (match_int(&args[0], &option)) - return 0; - opts->fs_uid = option; + return -EINVAL; + opts->fs_uid = make_kuid(current_user_ns(), option); + if (!uid_valid(opts->fs_uid)) + return -EINVAL; break; case Opt_gid: if (match_int(&args[0], &option)) - return 0; - opts->fs_gid = option; + return -EINVAL; + opts->fs_gid = make_kgid(current_user_ns(), option); + if (!gid_valid(opts->fs_gid)) + return -EINVAL; break; case Opt_umask: if (match_octal(&args[0], &option)) - return 0; + return -EINVAL; opts->fs_fmask = opts->fs_dmask = option; break; case Opt_dmask: if (match_octal(&args[0], &option)) - return 0; + return -EINVAL; opts->fs_dmask = option; break; case Opt_fmask: if (match_octal(&args[0], &option)) - return 0; + return -EINVAL; opts->fs_fmask = option; break; + case Opt_allow_utime: + if (match_octal(&args[0], &option)) + return -EINVAL; + opts->allow_utime = option & (S_IWGRP | S_IWOTH); + break; case Opt_codepage: if (match_int(&args[0], &option)) - return 0; + return -EINVAL; opts->codepage = option; break; case Opt_flush: opts->flush = 1; break; + case Opt_time_offset: + if (match_int(&args[0], &option)) + return -EINVAL; + if (option < -12 * 60 || option > 12 * 60) + return -EINVAL; + opts->tz_set = 1; + opts->time_offset = option; + break; + case Opt_tz_utc: + opts->tz_set = 1; + opts->time_offset = 0; + break; + case Opt_err_cont: + opts->errors = FAT_ERRORS_CONT; + break; + case Opt_err_panic: + opts->errors = FAT_ERRORS_PANIC; + break; + case Opt_err_ro: + opts->errors = FAT_ERRORS_RO; + break; + case Opt_nfs_stale_rw: + opts->nfs = FAT_NFS_STALE_RW; + break; + case Opt_nfs_nostale_ro: + opts->nfs = FAT_NFS_NOSTALE_RO; + break; + case Opt_dos1xfloppy: + opts->dos1xfloppy = 1; + break; /* msdos specific */ case Opt_dots: @@ -1084,30 +1222,46 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug, case Opt_nonumtail_yes: /* empty or 1 or yes or true */ opts->numtail = 0; /* negated option */ break; + case Opt_rodir: + opts->rodir = 1; + break; + case Opt_discard: + opts->discard = 1; + break; /* obsolete mount options */ - case Opt_obsolate: - printk(KERN_INFO "FAT: \"%s\" option is obsolete, " - "not supported now\n", p); + case Opt_obsolete: + fat_msg(sb, KERN_INFO, "\"%s\" option is obsolete, " + "not supported now", p); break; /* unknown option */ default: if (!silent) { - printk(KERN_ERR - "FAT: Unrecognized mount option \"%s\" " - "or missing value\n", p); + fat_msg(sb, KERN_ERR, + "Unrecognized mount option \"%s\" " + "or missing value", p); } return -EINVAL; } } + +out: /* 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"); + fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset" + " for FAT filesystems, filesystem will be " + "case sensitive!"); } + /* If user doesn't specify allow_utime, it's initialized from dmask. */ + if (opts->allow_utime == (unsigned short)-1) + opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH); if (opts->unicode_xlate) opts->utf8 = 0; + if (opts->nfs == FAT_NFS_NOSTALE_RO) { + sb->s_flags |= MS_RDONLY; + sb->s_export_op = &fat_export_ops_nostale; + } return 0; } @@ -1118,12 +1272,12 @@ static int fat_read_root(struct inode *inode) struct msdos_sb_info *sbi = MSDOS_SB(sb); int error; - MSDOS_I(inode)->i_pos = 0; + MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; inode->i_version++; inode->i_generation = 0; - inode->i_mode = (S_IRWXUGO & ~sbi->options.fs_dmask) | S_IFDIR; + inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO); inode->i_op = sbi->dir_ops; inode->i_fop = &fat_dir_operations; if (sbi->fat_bits == 32) { @@ -1140,31 +1294,213 @@ static int fat_read_root(struct inode *inode) MSDOS_I(inode)->i_logstart = 0; MSDOS_I(inode)->mmu_private = inode->i_size; - MSDOS_I(inode)->i_attrs = ATTR_NONE; + fat_save_attrs(inode, ATTR_DIR); inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0; inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0; - inode->i_nlink = fat_subdirs(inode)+2; + set_nlink(inode, fat_subdirs(inode)+2); return 0; } +static unsigned long calc_fat_clusters(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + /* Divide first to avoid overflow */ + if (sbi->fat_bits != 12) { + unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; + return ent_per_sec * sbi->fat_length; + } + + return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; +} + +static bool fat_bpb_is_zero(struct fat_boot_sector *b) +{ + if (get_unaligned_le16(&b->sector_size)) + return false; + if (b->sec_per_clus) + return false; + if (b->reserved) + return false; + if (b->fats) + return false; + if (get_unaligned_le16(&b->dir_entries)) + return false; + if (get_unaligned_le16(&b->sectors)) + return false; + if (b->media) + return false; + if (b->fat_length) + return false; + if (b->secs_track) + return false; + if (b->heads) + return false; + return true; +} + +static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b, + int silent, struct fat_bios_param_block *bpb) +{ + int error = -EINVAL; + + /* Read in BPB ... */ + memset(bpb, 0, sizeof(*bpb)); + bpb->fat_sector_size = get_unaligned_le16(&b->sector_size); + bpb->fat_sec_per_clus = b->sec_per_clus; + bpb->fat_reserved = le16_to_cpu(b->reserved); + bpb->fat_fats = b->fats; + bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries); + bpb->fat_sectors = get_unaligned_le16(&b->sectors); + bpb->fat_fat_length = le16_to_cpu(b->fat_length); + bpb->fat_total_sect = le32_to_cpu(b->total_sect); + + bpb->fat16_state = b->fat16.state; + bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id); + + bpb->fat32_length = le32_to_cpu(b->fat32.length); + bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster); + bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector); + bpb->fat32_state = b->fat32.state; + bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id); + + /* Validate this looks like a FAT filesystem BPB */ + if (!bpb->fat_reserved) { + if (!silent) + fat_msg(sb, KERN_ERR, + "bogus number of reserved sectors"); + goto out; + } + if (!bpb->fat_fats) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); + goto out; + } + + /* + * Earlier we checked here that b->secs_track and b->head are nonzero, + * but it turns out valid FAT filesystems can have zero there. + */ + + if (!fat_valid_media(b->media)) { + if (!silent) + fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", + (unsigned)b->media); + goto out; + } + + if (!is_power_of_2(bpb->fat_sector_size) + || (bpb->fat_sector_size < 512) + || (bpb->fat_sector_size > 4096)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus logical sector size %u", + (unsigned)bpb->fat_sector_size); + goto out; + } + + if (!is_power_of_2(bpb->fat_sec_per_clus)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", + (unsigned)bpb->fat_sec_per_clus); + goto out; + } + + error = 0; + +out: + return error; +} + +static int fat_read_static_bpb(struct super_block *sb, + struct fat_boot_sector *b, int silent, + struct fat_bios_param_block *bpb) +{ + static const char *notdos1x = "This doesn't look like a DOS 1.x volume"; + + struct fat_floppy_defaults *fdefaults = NULL; + int error = -EINVAL; + sector_t bd_sects; + unsigned i; + + bd_sects = i_size_read(sb->s_bdev->bd_inode) / SECTOR_SIZE; + + /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp code */ + if (b->ignored[0] != 0xeb || b->ignored[2] != 0x90) { + if (!silent) + fat_msg(sb, KERN_ERR, + "%s; no bootstrapping code", notdos1x); + goto out; + } + + /* + * If any value in this region is non-zero, it isn't archaic + * DOS. + */ + if (!fat_bpb_is_zero(b)) { + if (!silent) + fat_msg(sb, KERN_ERR, + "%s; DOS 2.x BPB is non-zero", notdos1x); + goto out; + } + + for (i = 0; i < ARRAY_SIZE(floppy_defaults); i++) { + if (floppy_defaults[i].nr_sectors == bd_sects) { + fdefaults = &floppy_defaults[i]; + break; + } + } + + if (fdefaults == NULL) { + if (!silent) + fat_msg(sb, KERN_WARNING, + "This looks like a DOS 1.x volume, but isn't a recognized floppy size (%llu sectors)", + (u64)bd_sects); + goto out; + } + + if (!silent) + fat_msg(sb, KERN_INFO, + "This looks like a DOS 1.x volume; assuming default BPB values"); + + memset(bpb, 0, sizeof(*bpb)); + bpb->fat_sector_size = SECTOR_SIZE; + bpb->fat_sec_per_clus = fdefaults->sec_per_clus; + bpb->fat_reserved = 1; + bpb->fat_fats = 2; + bpb->fat_dir_entries = fdefaults->dir_entries; + bpb->fat_sectors = fdefaults->nr_sectors; + bpb->fat_fat_length = fdefaults->fat_length; + + error = 0; + +out: + return error; +} + /* * Read the super block of an MS-DOS FS. */ -int fat_fill_super(struct super_block *sb, void *data, int silent, - const struct inode_operations *fs_dir_inode_ops, int isvfat) +int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, + void (*setup)(struct super_block *)) { - struct inode *root_inode = NULL; + struct inode *root_inode = NULL, *fat_inode = NULL; + struct inode *fsinfo_inode = NULL; struct buffer_head *bh; - struct fat_boot_sector *b; + struct fat_bios_param_block bpb; struct msdos_sb_info *sbi; u16 logical_sector_size; u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; int debug; - unsigned int media; long error; char buf[50]; + /* + * GFP_KERNEL is ok here, because while we do hold the + * supeblock lock, memory pressure can't call back into + * the filesystem, since we're only just about to mount + * it and have no inodes etc active! + */ sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL); if (!sbi) return -ENOMEM; @@ -1174,176 +1510,160 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, sb->s_magic = MSDOS_SUPER_MAGIC; sb->s_op = &fat_sops; sb->s_export_op = &fat_export_ops; - sbi->dir_ops = fs_dir_inode_ops; + mutex_init(&sbi->nfs_build_inode_lock); + ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); - error = parse_options(data, isvfat, silent, &debug, &sbi->options); + error = parse_options(sb, data, isvfat, silent, &debug, &sbi->options); if (error) goto out_fail; + setup(sb); /* flavour-specific stuff that needs options */ + error = -EIO; sb_min_blocksize(sb, 512); bh = sb_bread(sb, 0); if (bh == NULL) { - printk(KERN_ERR "FAT: unable to read boot sector\n"); + fat_msg(sb, KERN_ERR, "unable to read boot sector"); goto out_fail; } - b = (struct fat_boot_sector *) bh->b_data; - if (!b->reserved) { - if (!silent) - printk(KERN_ERR "FAT: bogus number of reserved sectors\n"); - brelse(bh); - goto out_invalid; - } - if (!b->fats) { - if (!silent) - printk(KERN_ERR "FAT: bogus number of FAT structure\n"); - brelse(bh); - goto out_invalid; - } - - /* - * Earlier we checked here that b->secs_track and b->head are nonzero, - * but it turns out valid FAT filesystems can have zero there. - */ + error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, + &bpb); + if (error == -EINVAL && sbi->options.dos1xfloppy) + error = fat_read_static_bpb(sb, + (struct fat_boot_sector *)bh->b_data, silent, &bpb); + brelse(bh); - media = b->media; - if (!FAT_VALID_MEDIA(media)) { - if (!silent) - printk(KERN_ERR "FAT: invalid media value (0x%02x)\n", - media); - brelse(bh); - goto out_invalid; - } - logical_sector_size = - le16_to_cpu(get_unaligned((__le16 *)&b->sector_size)); - if (!is_power_of_2(logical_sector_size) - || (logical_sector_size < 512) - || (PAGE_CACHE_SIZE < logical_sector_size)) { - if (!silent) - printk(KERN_ERR "FAT: bogus logical sector size %u\n", - logical_sector_size); - brelse(bh); - goto out_invalid; - } - sbi->sec_per_clus = b->sec_per_clus; - 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); - brelse(bh); + if (error == -EINVAL) goto out_invalid; - } + else if (error) + goto out_fail; + logical_sector_size = bpb.fat_sector_size; + sbi->sec_per_clus = bpb.fat_sec_per_clus; + + error = -EIO; if (logical_sector_size < sb->s_blocksize) { - printk(KERN_ERR "FAT: logical sector size too small for device" - " (logical sector size = %u)\n", logical_sector_size); - brelse(bh); + fat_msg(sb, KERN_ERR, "logical sector size too small for device" + " (logical sector size = %u)", logical_sector_size); goto out_fail; } + if (logical_sector_size > sb->s_blocksize) { - brelse(bh); + struct buffer_head *bh_resize; if (!sb_set_blocksize(sb, logical_sector_size)) { - printk(KERN_ERR "FAT: unable to set blocksize %u\n", + fat_msg(sb, KERN_ERR, "unable to set blocksize %u", logical_sector_size); goto out_fail; } - bh = sb_bread(sb, 0); - if (bh == NULL) { - printk(KERN_ERR "FAT: unable to read boot sector" - " (logical sector size = %lu)\n", + + /* Verify that the larger boot sector is fully readable */ + bh_resize = sb_bread(sb, 0); + if (bh_resize == NULL) { + fat_msg(sb, KERN_ERR, "unable to read boot sector" + " (logical sector size = %lu)", sb->s_blocksize); goto out_fail; } - b = (struct fat_boot_sector *) bh->b_data; + brelse(bh_resize); } + mutex_init(&sbi->s_lock); sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus; sbi->cluster_bits = ffs(sbi->cluster_size) - 1; - sbi->fats = b->fats; + sbi->fats = bpb.fat_fats; sbi->fat_bits = 0; /* Don't know yet */ - sbi->fat_start = le16_to_cpu(b->reserved); - sbi->fat_length = le16_to_cpu(b->fat_length); + sbi->fat_start = bpb.fat_reserved; + sbi->fat_length = bpb.fat_fat_length; sbi->root_cluster = 0; sbi->free_clusters = -1; /* Don't know yet */ + sbi->free_clus_valid = 0; sbi->prev_free = FAT_START_ENT; + sb->s_maxbytes = 0xffffffff; - if (!sbi->fat_length && b->fat32_length) { + if (!sbi->fat_length && bpb.fat32_length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; - sbi->fat_length = le32_to_cpu(b->fat32_length); - sbi->root_cluster = le32_to_cpu(b->root_cluster); - - sb->s_maxbytes = 0xffffffff; + sbi->fat_length = bpb.fat32_length; + sbi->root_cluster = bpb.fat32_root_cluster; /* MC - if info_sector is 0, don't multiply by 0 */ - sbi->fsinfo_sector = le16_to_cpu(b->info_sector); + sbi->fsinfo_sector = bpb.fat32_info_sector; if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; fsinfo_bh = sb_bread(sb, sbi->fsinfo_sector); if (fsinfo_bh == NULL) { - printk(KERN_ERR "FAT: bread failed, FSINFO block" - " (sector = %lu)\n", sbi->fsinfo_sector); - brelse(bh); + fat_msg(sb, KERN_ERR, "bread failed, FSINFO block" + " (sector = %lu)", sbi->fsinfo_sector); goto out_fail; } fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; if (!IS_FSINFO(fsinfo)) { - printk(KERN_WARNING "FAT: Invalid FSINFO signature: " - "0x%08x, 0x%08x (sector = %lu)\n", + fat_msg(sb, KERN_WARNING, "Invalid FSINFO signature: " + "0x%08x, 0x%08x (sector = %lu)", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); } else { if (sbi->options.usefree) - sbi->free_clusters = - le32_to_cpu(fsinfo->free_clusters); + sbi->free_clus_valid = 1; + sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters); sbi->prev_free = le32_to_cpu(fsinfo->next_cluster); } brelse(fsinfo_bh); } + /* interpret volume ID as a little endian 32 bit integer */ + if (sbi->fat_bits == 32) + sbi->vol_id = bpb.fat32_vol_id; + else /* fat 16 or 12 */ + sbi->vol_id = bpb.fat16_vol_id; + sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry); sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1; sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length; - sbi->dir_entries = - le16_to_cpu(get_unaligned((__le16 *)&b->dir_entries)); + sbi->dir_entries = bpb.fat_dir_entries; if (sbi->dir_entries & (sbi->dir_per_block - 1)) { if (!silent) - printk(KERN_ERR "FAT: bogus directroy-entries per block" - " (%u)\n", sbi->dir_entries); - brelse(bh); + fat_msg(sb, KERN_ERR, "bogus directory-entries per block" + " (%u)", sbi->dir_entries); goto out_invalid; } rootdir_sectors = sbi->dir_entries * sizeof(struct msdos_dir_entry) / sb->s_blocksize; sbi->data_start = sbi->dir_start + rootdir_sectors; - total_sectors = le16_to_cpu(get_unaligned((__le16 *)&b->sectors)); + total_sectors = bpb.fat_sectors; if (total_sectors == 0) - total_sectors = le32_to_cpu(b->total_sect); + total_sectors = bpb.fat_total_sect; total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; if (sbi->fat_bits != 32) sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; + /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ + if (sbi->fat_bits == 32) + sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; + else /* fat 16 or 12 */ + sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY; + /* check that FAT table does not overflow */ - fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; + fat_clusters = calc_fat_clusters(sb); total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); if (total_clusters > MAX_FAT(sb)) { if (!silent) - printk(KERN_ERR "FAT: count of clusters too big (%u)\n", + fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", total_clusters); - brelse(bh); goto out_invalid; } @@ -1356,10 +1676,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, if (sbi->prev_free < FAT_START_ENT) sbi->prev_free = FAT_START_ENT; - brelse(bh); - /* set up enough so that it can read an inode */ fat_hash_init(sb); + dir_hash_init(sb); fat_ent_access_init(sb); /* @@ -1374,7 +1693,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, sprintf(buf, "cp%d", sbi->options.codepage); sbi->nls_disk = load_nls(buf); if (!sbi->nls_disk) { - printk(KERN_ERR "FAT: codepage %s not found\n", buf); + fat_msg(sb, KERN_ERR, "codepage %s not found", buf); goto out_fail; } @@ -1382,44 +1701,68 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, if (sbi->options.isvfat) { sbi->nls_io = load_nls(sbi->options.iocharset); if (!sbi->nls_io) { - printk(KERN_ERR "FAT: IO charset %s not found\n", + fat_msg(sb, KERN_ERR, "IO charset %s not found", sbi->options.iocharset); goto out_fail; } } error = -ENOMEM; + fat_inode = new_inode(sb); + if (!fat_inode) + goto out_fail; + MSDOS_I(fat_inode)->i_pos = 0; + sbi->fat_inode = fat_inode; + + fsinfo_inode = new_inode(sb); + if (!fsinfo_inode) + goto out_fail; + fsinfo_inode->i_ino = MSDOS_FSINFO_INO; + sbi->fsinfo_inode = fsinfo_inode; + insert_inode_hash(fsinfo_inode); + root_inode = new_inode(sb); if (!root_inode) goto out_fail; root_inode->i_ino = MSDOS_ROOT_INO; root_inode->i_version = 1; error = fat_read_root(root_inode); - if (error < 0) + if (error < 0) { + iput(root_inode); goto out_fail; + } error = -ENOMEM; insert_inode_hash(root_inode); - sb->s_root = d_alloc_root(root_inode); + fat_attach(root_inode, 0); + sb->s_root = d_make_root(root_inode); if (!sb->s_root) { - printk(KERN_ERR "FAT: get root inode failed\n"); + fat_msg(sb, KERN_ERR, "get root inode failed"); goto out_fail; } + if (sbi->options.discard) { + struct request_queue *q = bdev_get_queue(sb->s_bdev); + if (!blk_queue_discard(q)) + fat_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but " + "the device does not support discard"); + } + + fat_set_state(sb, 1, 0); return 0; out_invalid: error = -EINVAL; if (!silent) - printk(KERN_INFO "VFS: Can't find a valid FAT filesystem" - " on dev %s.\n", sb->s_id); + fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); out_fail: - if (root_inode) - iput(root_inode); - if (sbi->nls_io) - unload_nls(sbi->nls_io); - if (sbi->nls_disk) - unload_nls(sbi->nls_disk); + if (fsinfo_inode) + iput(fsinfo_inode); + if (fat_inode) + iput(fat_inode); + unload_nls(sbi->nls_io); + unload_nls(sbi->nls_disk); if (sbi->options.iocharset != fat_default_iocharset) kfree(sbi->options.iocharset); sb->s_fs_info = NULL; @@ -1439,18 +1782,14 @@ 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 + + /* if we used wait=1, sync_inode_metadata waits for the io for the + * inode to finish. So wait=0 is sent down to sync_inode_metadata * and filemap_fdatawrite is used for the data blocks */ - ret = sync_inode(inode, &wbc); + ret = sync_inode_metadata(inode, 0); if (!ret) - ret = filemap_fdatawrite(mapping); + ret = filemap_fdatawrite(inode->i_mapping); return ret; } diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 61f23511eac..628e22a5a54 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -8,55 +8,79 @@ #include <linux/module.h> #include <linux/fs.h> -#include <linux/msdos_fs.h> #include <linux/buffer_head.h> +#include <linux/time.h> +#include "fat.h" /* - * fat_fs_panic reports a severe file system problem and sets the file system - * read-only. The file system can be made writable again by remounting it. + * fat_fs_error reports a file system problem that might indicate fa data + * corruption/inconsistency. Depending on 'errors' mount option the + * panic() is called, or error message is printed FAT and nothing is done, + * or filesystem is remounted read-only (default behavior). + * In case the file system is remounted read-only, it can be made writable + * again by remounting it. */ -void fat_fs_panic(struct super_block *s, const char *fmt, ...) +void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...) { + struct fat_mount_options *opts = &MSDOS_SB(sb)->options; va_list args; + struct va_format vaf; - printk(KERN_ERR "FAT: Filesystem panic (dev %s)\n", s->s_id); - - printk(KERN_ERR " "); - va_start(args, fmt); - vprintk(fmt, args); - va_end(args); - printk("\n"); + if (report) { + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + fat_msg(sb, KERN_ERR, "error, %pV", &vaf); + va_end(args); + } - if (!(s->s_flags & MS_RDONLY)) { - s->s_flags |= MS_RDONLY; - printk(KERN_ERR " File system has been set read-only\n"); + if (opts->errors == FAT_ERRORS_PANIC) + panic("FAT-fs (%s): fs panic from previous error\n", sb->s_id); + else if (opts->errors == FAT_ERRORS_RO && !(sb->s_flags & MS_RDONLY)) { + sb->s_flags |= MS_RDONLY; + fat_msg(sb, KERN_ERR, "Filesystem has been set read-only"); } } +EXPORT_SYMBOL_GPL(__fat_fs_error); + +/** + * fat_msg() - print preformated FAT specific messages. Every thing what is + * not fat_fs_error() should be fat_msg(). + */ +void fat_msg(struct super_block *sb, const char *level, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; -EXPORT_SYMBOL_GPL(fat_fs_panic); + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + printk("%sFAT-fs (%s): %pV\n", level, sb->s_id, &vaf); + va_end(args); +} /* Flushes the number of free clusters on FAT32 */ /* XXX: Need to write one per FSINFO block. Currently only writes 1 */ -void fat_clusters_flush(struct super_block *sb) +int fat_clusters_flush(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct fat_boot_fsinfo *fsinfo; if (sbi->fat_bits != 32) - return; + return 0; bh = sb_bread(sb, sbi->fsinfo_sector); if (bh == NULL) { - printk(KERN_ERR "FAT: bread failed in fat_clusters_flush\n"); - return; + fat_msg(sb, KERN_ERR, "bread failed in fat_clusters_flush"); + return -EIO; } fsinfo = (struct fat_boot_fsinfo *)bh->b_data; /* Sanity check */ if (!IS_FSINFO(fsinfo)) { - printk(KERN_ERR "FAT: Invalid FSINFO signature: " - "0x%08x, 0x%08x (sector = %lu)\n", + fat_msg(sb, KERN_ERR, "Invalid FSINFO signature: " + "0x%08x, 0x%08x (sector = %lu)", le32_to_cpu(fsinfo->signature1), le32_to_cpu(fsinfo->signature2), sbi->fsinfo_sector); @@ -68,6 +92,8 @@ void fat_clusters_flush(struct super_block *sb) mark_buffer_dirty(bh); } brelse(bh); + + return 0; } /* @@ -108,13 +134,17 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) } if (ret < 0) return ret; + /* + * FIXME:Although we can add this cache, fat_cache_add() is + * assuming to be called after linear search with fat_cache_id. + */ // fat_cache_add(inode, new_fclus, new_dclus); } else { MSDOS_I(inode)->i_start = new_dclus; MSDOS_I(inode)->i_logstart = new_dclus; /* - * Since generic_osync_inode() synchronize later if - * this is not directory, we don't here. + * Since generic_write_sync() synchronizes regular files later, + * we sync here only directories. */ if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) { ret = fat_sync_inode(inode); @@ -124,8 +154,9 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) mark_inode_dirty(inode); } if (new_fclus != (inode->i_blocks >> (sbi->cluster_bits - 9))) { - fat_fs_panic(sb, "clusters badly computed (%d != %lu)", - new_fclus, inode->i_blocks >> (sbi->cluster_bits - 9)); + fat_fs_error(sb, "clusters badly computed (%d != %llu)", + new_fclus, + (llu)(inode->i_blocks >> (sbi->cluster_bits - 9))); fat_cache_inval_inode(inode); } inode->i_blocks += nr_cluster << (sbi->cluster_bits - 9); @@ -135,77 +166,119 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) extern struct timezone sys_tz; +/* + * The epoch of FAT timestamp is 1980. + * : bits : value + * date: 0 - 4: day (1 - 31) + * date: 5 - 8: month (1 - 12) + * date: 9 - 15: year (0 - 127) from 1980 + * time: 0 - 4: sec (0 - 29) 2sec counts + * time: 5 - 10: min (0 - 59) + * time: 11 - 15: hour (0 - 23) + */ +#define SECS_PER_MIN 60 +#define SECS_PER_HOUR (60 * 60) +#define SECS_PER_DAY (SECS_PER_HOUR * 24) +/* days between 1.1.70 and 1.1.80 (2 leap days) */ +#define DAYS_DELTA (365 * 10 + 2) +/* 120 (2100 - 1980) isn't leap year */ +#define YEAR_2100 120 +#define IS_LEAP_YEAR(y) (!((y) & 3) && (y) != YEAR_2100) + /* Linear day numbers of the respective 1sts in non-leap years. */ -static int day_n[] = { - /* Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec */ - 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 0, 0, 0, 0 +static time_t days_in_year[] = { + /* Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec */ + 0, 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 0, 0, 0, }; -/* Convert a MS-DOS time/date pair to a UNIX date (seconds since 1 1 70). */ -int date_dos2unix(unsigned short time, unsigned short date) +/* Convert a FAT time/date pair to a UNIX date (seconds since 1 1 70). */ +void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts, + __le16 __time, __le16 __date, u8 time_cs) { - int month, year, secs; + u16 time = le16_to_cpu(__time), date = le16_to_cpu(__date); + time_t second, day, leap_day, month, year; - /* - * first subtract and mask after that... Otherwise, if - * date == 0, bad things happen - */ - month = ((date >> 5) - 1) & 15; - year = date >> 9; - secs = (time & 31)*2+60*((time >> 5) & 63)+(time >> 11)*3600+86400* - ((date & 31)-1+day_n[month]+(year/4)+year*365-((year & 3) == 0 && - month < 2 ? 1 : 0)+3653); - /* days since 1.1.70 plus 80's leap day */ - secs += sys_tz.tz_minuteswest*60; - return secs; -} + year = date >> 9; + month = max(1, (date >> 5) & 0xf); + day = max(1, date & 0x1f) - 1; -/* Convert linear UNIX date to a MS-DOS time/date pair. */ -void fat_date_unix2dos(int unix_date, __le16 *time, __le16 *date) -{ - int day, year, nl_day, month; - - unix_date -= sys_tz.tz_minuteswest*60; - - /* Jan 1 GMT 00:00:00 1980. But what about another time zone? */ - if (unix_date < 315532800) - unix_date = 315532800; - - *time = cpu_to_le16((unix_date % 60)/2+(((unix_date/60) % 60) << 5)+ - (((unix_date/3600) % 24) << 11)); - day = unix_date/86400-3652; - year = day/365; - if ((year+3)/4+365*year > day) - year--; - day -= (year+3)/4+365*year; - if (day == 59 && !(year & 3)) { - nl_day = day; - month = 2; + leap_day = (year + 3) / 4; + if (year > YEAR_2100) /* 2100 isn't leap year */ + leap_day--; + if (IS_LEAP_YEAR(year) && month > 2) + leap_day++; + + second = (time & 0x1f) << 1; + second += ((time >> 5) & 0x3f) * SECS_PER_MIN; + second += (time >> 11) * SECS_PER_HOUR; + second += (year * 365 + leap_day + + days_in_year[month] + day + + DAYS_DELTA) * SECS_PER_DAY; + + if (!sbi->options.tz_set) + second += sys_tz.tz_minuteswest * SECS_PER_MIN; + else + second -= sbi->options.time_offset * SECS_PER_MIN; + + if (time_cs) { + ts->tv_sec = second + (time_cs / 100); + ts->tv_nsec = (time_cs % 100) * 10000000; } else { - nl_day = (year & 3) || day <= 59 ? day : day-1; - for (month = 0; month < 12; month++) { - if (day_n[month] > nl_day) - break; - } + ts->tv_sec = second; + ts->tv_nsec = 0; } - *date = cpu_to_le16(nl_day-day_n[month-1]+1+(month << 5)+(year << 9)); } -EXPORT_SYMBOL_GPL(fat_date_unix2dos); +/* Convert linear UNIX date to a FAT time/date pair. */ +void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec *ts, + __le16 *time, __le16 *date, u8 *time_cs) +{ + struct tm tm; + time_to_tm(ts->tv_sec, + (sbi->options.tz_set ? sbi->options.time_offset : + -sys_tz.tz_minuteswest) * SECS_PER_MIN, &tm); + + /* FAT can only support year between 1980 to 2107 */ + if (tm.tm_year < 1980 - 1900) { + *time = 0; + *date = cpu_to_le16((0 << 9) | (1 << 5) | 1); + if (time_cs) + *time_cs = 0; + return; + } + if (tm.tm_year > 2107 - 1900) { + *time = cpu_to_le16((23 << 11) | (59 << 5) | 29); + *date = cpu_to_le16((127 << 9) | (12 << 5) | 31); + if (time_cs) + *time_cs = 199; + return; + } + + /* from 1900 -> from 1980 */ + tm.tm_year -= 80; + /* 0~11 -> 1~12 */ + tm.tm_mon++; + /* 0~59 -> 0~29(2sec counts) */ + tm.tm_sec >>= 1; + + *time = cpu_to_le16(tm.tm_hour << 11 | tm.tm_min << 5 | tm.tm_sec); + *date = cpu_to_le16(tm.tm_year << 9 | tm.tm_mon << 5 | tm.tm_mday); + if (time_cs) + *time_cs = (ts->tv_sec & 1) * 100 + ts->tv_nsec / 10000000; +} +EXPORT_SYMBOL_GPL(fat_time_unix2fat); int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs) { int i, err = 0; - ll_rw_block(SWRITE, nr_bhs, bhs); + for (i = 0; i < nr_bhs; i++) + write_dirty_buffer(bhs[i], WRITE); + for (i = 0; i < nr_bhs; i++) { wait_on_buffer(bhs[i]); - if (buffer_eopnotsupp(bhs[i])) { - clear_buffer_eopnotsupp(bhs[i]); - err = -EOPNOTSUPP; - } else if (!err && !buffer_uptodate(bhs[i])) + if (!err && !buffer_uptodate(bhs[i])) err = -EIO; } return err; } - diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c new file mode 100644 index 00000000000..a783b0e1272 --- /dev/null +++ b/fs/fat/namei_msdos.c @@ -0,0 +1,686 @@ +/* + * linux/fs/msdos/namei.c + * + * Written 1992,1993 by Werner Almesberger + * Hidden files 1995 by Albert Cahalan <albert@ccs.neu.edu> <adc@coe.neu.edu> + * Rewritten for constant inumbers 1999 by Al Viro + */ + +#include <linux/module.h> +#include <linux/time.h> +#include <linux/buffer_head.h> +#include "fat.h" + +/* Characters that are undesirable in an MS-DOS file name */ +static unsigned char bad_chars[] = "*?<>|\""; +static unsigned char bad_if_strict[] = "+=,; "; + +/***** Formats an MS-DOS file name. Rejects invalid names. */ +static int msdos_format_name(const unsigned char *name, int len, + unsigned char *res, struct fat_mount_options *opts) + /* + * name is the proposed name, len is its length, res is + * the resulting name, opts->name_check is either (r)elaxed, + * (n)ormal or (s)trict, opts->dotsOK allows dots at the + * beginning of name (for hidden files) + */ +{ + unsigned char *walk; + unsigned char c; + int space; + + if (name[0] == '.') { /* dotfile because . and .. already done */ + if (opts->dotsOK) { + /* Get rid of dot - test for it elsewhere */ + name++; + len--; + } else + return -EINVAL; + } + /* + * disallow names that _really_ start with a dot + */ + space = 1; + c = 0; + for (walk = res; len && walk - res < 8; walk++) { + c = *name++; + len--; + if (opts->name_check != 'r' && strchr(bad_chars, c)) + return -EINVAL; + if (opts->name_check == 's' && strchr(bad_if_strict, c)) + return -EINVAL; + if (c >= 'A' && c <= 'Z' && opts->name_check == 's') + return -EINVAL; + if (c < ' ' || c == ':' || c == '\\') + return -EINVAL; + /* + * 0xE5 is legal as a first character, but we must substitute + * 0x05 because 0xE5 marks deleted files. Yes, DOS really + * does this. + * It seems that Microsoft hacked DOS to support non-US + * characters after the 0xE5 character was already in use to + * mark deleted files. + */ + if ((res == walk) && (c == 0xE5)) + c = 0x05; + if (c == '.') + break; + space = (c == ' '); + *walk = (!opts->nocase && c >= 'a' && c <= 'z') ? c - 32 : c; + } + if (space) + return -EINVAL; + if (opts->name_check == 's' && len && c != '.') { + c = *name++; + len--; + if (c != '.') + return -EINVAL; + } + while (c != '.' && len--) + c = *name++; + if (c == '.') { + while (walk - res < 8) + *walk++ = ' '; + while (len > 0 && walk - res < MSDOS_NAME) { + c = *name++; + len--; + if (opts->name_check != 'r' && strchr(bad_chars, c)) + return -EINVAL; + if (opts->name_check == 's' && + strchr(bad_if_strict, c)) + return -EINVAL; + if (c < ' ' || c == ':' || c == '\\') + return -EINVAL; + if (c == '.') { + if (opts->name_check == 's') + return -EINVAL; + break; + } + if (c >= 'A' && c <= 'Z' && opts->name_check == 's') + return -EINVAL; + space = c == ' '; + if (!opts->nocase && c >= 'a' && c <= 'z') + *walk++ = c - 32; + else + *walk++ = c; + } + if (space) + return -EINVAL; + if (opts->name_check == 's' && len) + return -EINVAL; + } + while (walk - res < MSDOS_NAME) + *walk++ = ' '; + + return 0; +} + +/***** Locates a directory entry. Uses unformatted name. */ +static int msdos_find(struct inode *dir, const unsigned char *name, int len, + struct fat_slot_info *sinfo) +{ + struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb); + unsigned char msdos_name[MSDOS_NAME]; + int err; + + err = msdos_format_name(name, len, msdos_name, &sbi->options); + if (err) + return -ENOENT; + + err = fat_scan(dir, msdos_name, sinfo); + if (!err && sbi->options.dotsOK) { + if (name[0] == '.') { + if (!(sinfo->de->attr & ATTR_HIDDEN)) + err = -ENOENT; + } else { + if (sinfo->de->attr & ATTR_HIDDEN) + err = -ENOENT; + } + if (err) + brelse(sinfo->bh); + } + return err; +} + +/* + * Compute the hash for the msdos name corresponding to the dentry. + * Note: if the name is invalid, we leave the hash code unchanged so + * that the existing dentry can be used. The msdos fs routines will + * return ENOENT or EINVAL as appropriate. + */ +static int msdos_hash(const struct dentry *dentry, struct qstr *qstr) +{ + struct fat_mount_options *options = &MSDOS_SB(dentry->d_sb)->options; + unsigned char msdos_name[MSDOS_NAME]; + int error; + + error = msdos_format_name(qstr->name, qstr->len, msdos_name, options); + if (!error) + qstr->hash = full_name_hash(msdos_name, MSDOS_NAME); + return 0; +} + +/* + * Compare two msdos names. If either of the names are invalid, + * we fall back to doing the standard name comparison. + */ +static int msdos_cmp(const struct dentry *parent, const struct dentry *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + struct fat_mount_options *options = &MSDOS_SB(parent->d_sb)->options; + unsigned char a_msdos_name[MSDOS_NAME], b_msdos_name[MSDOS_NAME]; + int error; + + error = msdos_format_name(name->name, name->len, a_msdos_name, options); + if (error) + goto old_compare; + error = msdos_format_name(str, len, b_msdos_name, options); + if (error) + goto old_compare; + error = memcmp(a_msdos_name, b_msdos_name, MSDOS_NAME); +out: + return error; + +old_compare: + error = 1; + if (name->len == len) + error = memcmp(name->name, str, len); + goto out; +} + +static const struct dentry_operations msdos_dentry_operations = { + .d_hash = msdos_hash, + .d_compare = msdos_cmp, +}; + +/* + * AV. Wrappers for FAT sb operations. Is it wise? + */ + +/***** Get inode using directory and name */ +static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct super_block *sb = dir->i_sb; + struct fat_slot_info sinfo; + struct inode *inode; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo); + switch (err) { + case -ENOENT: + inode = NULL; + break; + case 0: + inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + brelse(sinfo.bh); + break; + default: + inode = ERR_PTR(err); + } + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return d_splice_alias(inode, dentry); +} + +/***** Creates a directory entry (name is already formatted). */ +static int msdos_add_entry(struct inode *dir, const unsigned char *name, + int is_dir, int is_hid, int cluster, + struct timespec *ts, struct fat_slot_info *sinfo) +{ + struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb); + struct msdos_dir_entry de; + __le16 time, date; + int err; + + memcpy(de.name, name, MSDOS_NAME); + de.attr = is_dir ? ATTR_DIR : ATTR_ARCH; + if (is_hid) + de.attr |= ATTR_HIDDEN; + de.lcase = 0; + fat_time_unix2fat(sbi, ts, &time, &date, NULL); + de.cdate = de.adate = 0; + de.ctime = 0; + de.ctime_cs = 0; + de.time = time; + de.date = date; + fat_set_start(&de, cluster); + de.size = 0; + + err = fat_add_entries(dir, &de, 1, sinfo); + if (err) + return err; + + dir->i_ctime = dir->i_mtime = *ts; + if (IS_DIRSYNC(dir)) + (void)fat_sync_inode(dir); + else + mark_inode_dirty(dir); + + return 0; +} + +/***** Create a file */ +static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + struct super_block *sb = dir->i_sb; + struct inode *inode = NULL; + struct fat_slot_info sinfo; + struct timespec ts; + unsigned char msdos_name[MSDOS_NAME]; + int err, is_hid; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + err = msdos_format_name(dentry->d_name.name, dentry->d_name.len, + msdos_name, &MSDOS_SB(sb)->options); + if (err) + goto out; + is_hid = (dentry->d_name.name[0] == '.') && (msdos_name[0] != '.'); + /* Have to do it due to foo vs. .foo conflicts */ + if (!fat_scan(dir, msdos_name, &sinfo)) { + brelse(sinfo.bh); + err = -EINVAL; + goto out; + } + + ts = CURRENT_TIME_SEC; + err = msdos_add_entry(dir, msdos_name, 0, is_hid, 0, &ts, &sinfo); + if (err) + goto out; + inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + brelse(sinfo.bh); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out; + } + inode->i_mtime = inode->i_atime = inode->i_ctime = ts; + /* timestamp is already written, so mark_inode_dirty() is unneeded. */ + + d_instantiate(dentry, inode); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + if (!err) + err = fat_flush_inodes(sb, dir, inode); + return err; +} + +/***** Remove a directory */ +static int msdos_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct super_block *sb = dir->i_sb; + struct inode *inode = dentry->d_inode; + struct fat_slot_info sinfo; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + /* + * Check whether the directory is not in use, then check + * whether it is empty. + */ + err = fat_dir_empty(inode); + if (err) + goto out; + err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo); + if (err) + goto out; + + err = fat_remove_entries(dir, &sinfo); /* and releases bh */ + if (err) + goto out; + drop_nlink(dir); + + clear_nlink(inode); + inode->i_ctime = CURRENT_TIME_SEC; + fat_detach(inode); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + if (!err) + err = fat_flush_inodes(sb, dir, inode); + + return err; +} + +/***** Make a directory */ +static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct super_block *sb = dir->i_sb; + struct fat_slot_info sinfo; + struct inode *inode; + unsigned char msdos_name[MSDOS_NAME]; + struct timespec ts; + int err, is_hid, cluster; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + err = msdos_format_name(dentry->d_name.name, dentry->d_name.len, + msdos_name, &MSDOS_SB(sb)->options); + if (err) + goto out; + is_hid = (dentry->d_name.name[0] == '.') && (msdos_name[0] != '.'); + /* foo vs .foo situation */ + if (!fat_scan(dir, msdos_name, &sinfo)) { + brelse(sinfo.bh); + err = -EINVAL; + goto out; + } + + ts = CURRENT_TIME_SEC; + cluster = fat_alloc_new_dir(dir, &ts); + if (cluster < 0) { + err = cluster; + goto out; + } + err = msdos_add_entry(dir, msdos_name, 1, is_hid, cluster, &ts, &sinfo); + if (err) + goto out_free; + inc_nlink(dir); + + inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + brelse(sinfo.bh); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + /* the directory was completed, just return a error */ + goto out; + } + set_nlink(inode, 2); + inode->i_mtime = inode->i_atime = inode->i_ctime = ts; + /* timestamp is already written, so mark_inode_dirty() is unneeded. */ + + d_instantiate(dentry, inode); + + mutex_unlock(&MSDOS_SB(sb)->s_lock); + fat_flush_inodes(sb, dir, inode); + return 0; + +out_free: + fat_free_clusters(dir, cluster); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return err; +} + +/***** Unlink a file */ +static int msdos_unlink(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct super_block *sb = inode->i_sb; + struct fat_slot_info sinfo; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + err = msdos_find(dir, dentry->d_name.name, dentry->d_name.len, &sinfo); + if (err) + goto out; + + err = fat_remove_entries(dir, &sinfo); /* and releases bh */ + if (err) + goto out; + clear_nlink(inode); + inode->i_ctime = CURRENT_TIME_SEC; + fat_detach(inode); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + if (!err) + err = fat_flush_inodes(sb, dir, inode); + + return err; +} + +static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, + struct dentry *old_dentry, + struct inode *new_dir, unsigned char *new_name, + struct dentry *new_dentry, int is_hid) +{ + struct buffer_head *dotdot_bh; + struct msdos_dir_entry *dotdot_de; + struct inode *old_inode, *new_inode; + struct fat_slot_info old_sinfo, sinfo; + struct timespec ts; + loff_t new_i_pos; + int err, old_attrs, is_dir, update_dotdot, corrupt = 0; + + old_sinfo.bh = sinfo.bh = dotdot_bh = NULL; + old_inode = old_dentry->d_inode; + new_inode = new_dentry->d_inode; + + err = fat_scan(old_dir, old_name, &old_sinfo); + if (err) { + err = -EIO; + goto out; + } + + is_dir = S_ISDIR(old_inode->i_mode); + update_dotdot = (is_dir && old_dir != new_dir); + if (update_dotdot) { + if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de)) { + err = -EIO; + goto out; + } + } + + old_attrs = MSDOS_I(old_inode)->i_attrs; + err = fat_scan(new_dir, new_name, &sinfo); + if (!err) { + if (!new_inode) { + /* "foo" -> ".foo" case. just change the ATTR_HIDDEN */ + if (sinfo.de != old_sinfo.de) { + err = -EINVAL; + goto out; + } + if (is_hid) + MSDOS_I(old_inode)->i_attrs |= ATTR_HIDDEN; + else + MSDOS_I(old_inode)->i_attrs &= ~ATTR_HIDDEN; + if (IS_DIRSYNC(old_dir)) { + err = fat_sync_inode(old_inode); + if (err) { + MSDOS_I(old_inode)->i_attrs = old_attrs; + goto out; + } + } else + mark_inode_dirty(old_inode); + + old_dir->i_version++; + old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; + if (IS_DIRSYNC(old_dir)) + (void)fat_sync_inode(old_dir); + else + mark_inode_dirty(old_dir); + goto out; + } + } + + ts = CURRENT_TIME_SEC; + if (new_inode) { + if (err) + goto out; + if (is_dir) { + err = fat_dir_empty(new_inode); + if (err) + goto out; + } + new_i_pos = MSDOS_I(new_inode)->i_pos; + fat_detach(new_inode); + } else { + err = msdos_add_entry(new_dir, new_name, is_dir, is_hid, 0, + &ts, &sinfo); + if (err) + goto out; + new_i_pos = sinfo.i_pos; + } + new_dir->i_version++; + + fat_detach(old_inode); + fat_attach(old_inode, new_i_pos); + if (is_hid) + MSDOS_I(old_inode)->i_attrs |= ATTR_HIDDEN; + else + MSDOS_I(old_inode)->i_attrs &= ~ATTR_HIDDEN; + if (IS_DIRSYNC(new_dir)) { + err = fat_sync_inode(old_inode); + if (err) + goto error_inode; + } else + mark_inode_dirty(old_inode); + + if (update_dotdot) { + fat_set_start(dotdot_de, MSDOS_I(new_dir)->i_logstart); + mark_buffer_dirty_inode(dotdot_bh, old_inode); + if (IS_DIRSYNC(new_dir)) { + err = sync_dirty_buffer(dotdot_bh); + if (err) + goto error_dotdot; + } + drop_nlink(old_dir); + if (!new_inode) + inc_nlink(new_dir); + } + + err = fat_remove_entries(old_dir, &old_sinfo); /* and releases bh */ + old_sinfo.bh = NULL; + if (err) + goto error_dotdot; + old_dir->i_version++; + old_dir->i_ctime = old_dir->i_mtime = ts; + if (IS_DIRSYNC(old_dir)) + (void)fat_sync_inode(old_dir); + else + mark_inode_dirty(old_dir); + + if (new_inode) { + drop_nlink(new_inode); + if (is_dir) + drop_nlink(new_inode); + new_inode->i_ctime = ts; + } +out: + brelse(sinfo.bh); + brelse(dotdot_bh); + brelse(old_sinfo.bh); + return err; + +error_dotdot: + /* data cluster is shared, serious corruption */ + corrupt = 1; + + if (update_dotdot) { + fat_set_start(dotdot_de, MSDOS_I(old_dir)->i_logstart); + mark_buffer_dirty_inode(dotdot_bh, old_inode); + corrupt |= sync_dirty_buffer(dotdot_bh); + } +error_inode: + fat_detach(old_inode); + fat_attach(old_inode, old_sinfo.i_pos); + MSDOS_I(old_inode)->i_attrs = old_attrs; + if (new_inode) { + fat_attach(new_inode, new_i_pos); + if (corrupt) + corrupt |= fat_sync_inode(new_inode); + } else { + /* + * If new entry was not sharing the data cluster, it + * shouldn't be serious corruption. + */ + int err2 = fat_remove_entries(new_dir, &sinfo); + if (corrupt) + corrupt |= err2; + sinfo.bh = NULL; + } + if (corrupt < 0) { + fat_fs_error(new_dir->i_sb, + "%s: Filesystem corrupted (i_pos %lld)", + __func__, sinfo.i_pos); + } + goto out; +} + +/***** Rename, a wrapper for rename_same_dir & rename_diff_dir */ +static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct super_block *sb = old_dir->i_sb; + unsigned char old_msdos_name[MSDOS_NAME], new_msdos_name[MSDOS_NAME]; + int err, is_hid; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + err = msdos_format_name(old_dentry->d_name.name, + old_dentry->d_name.len, old_msdos_name, + &MSDOS_SB(old_dir->i_sb)->options); + if (err) + goto out; + err = msdos_format_name(new_dentry->d_name.name, + new_dentry->d_name.len, new_msdos_name, + &MSDOS_SB(new_dir->i_sb)->options); + if (err) + goto out; + + is_hid = + (new_dentry->d_name.name[0] == '.') && (new_msdos_name[0] != '.'); + + err = do_msdos_rename(old_dir, old_msdos_name, old_dentry, + new_dir, new_msdos_name, new_dentry, is_hid); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + if (!err) + err = fat_flush_inodes(sb, old_dir, new_dir); + return err; +} + +static const struct inode_operations msdos_dir_inode_operations = { + .create = msdos_create, + .lookup = msdos_lookup, + .unlink = msdos_unlink, + .mkdir = msdos_mkdir, + .rmdir = msdos_rmdir, + .rename = msdos_rename, + .setattr = fat_setattr, + .getattr = fat_getattr, +}; + +static void setup(struct super_block *sb) +{ + MSDOS_SB(sb)->dir_ops = &msdos_dir_inode_operations; + sb->s_d_op = &msdos_dentry_operations; + sb->s_flags |= MS_NOATIME; +} + +static int msdos_fill_super(struct super_block *sb, void *data, int silent) +{ + return fat_fill_super(sb, data, silent, 0, setup); +} + +static struct dentry *msdos_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, msdos_fill_super); +} + +static struct file_system_type msdos_fs_type = { + .owner = THIS_MODULE, + .name = "msdos", + .mount = msdos_mount, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; +MODULE_ALIAS_FS("msdos"); + +static int __init init_msdos_fs(void) +{ + return register_filesystem(&msdos_fs_type); +} + +static void __exit exit_msdos_fs(void) +{ + unregister_filesystem(&msdos_fs_type); +} + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Werner Almesberger"); +MODULE_DESCRIPTION("MS-DOS filesystem support"); + +module_init(init_msdos_fs) +module_exit(exit_msdos_fs) diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c new file mode 100644 index 00000000000..6df8d3d885e --- /dev/null +++ b/fs/fat/namei_vfat.c @@ -0,0 +1,1089 @@ +/* + * linux/fs/vfat/namei.c + * + * Written 1992,1993 by Werner Almesberger + * + * Windows95/Windows NT compatible extended MSDOS filesystem + * by Gordon Chaffee Copyright (C) 1995. Send bug reports for the + * VFAT filesystem to <chaffee@cs.berkeley.edu>. Specify + * what file operation caused you trouble and if you can duplicate + * the problem, send a script that demonstrates it. + * + * Short name translation 1999, 2001 by Wolfram Pienkoss <wp@bszh.de> + * + * Support Multibyte characters and cleanup by + * OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> + */ + +#include <linux/module.h> +#include <linux/jiffies.h> +#include <linux/ctype.h> +#include <linux/slab.h> +#include <linux/buffer_head.h> +#include <linux/namei.h> +#include "fat.h" + +/* + * If new entry was created in the parent, it could create the 8.3 + * alias (the shortname of logname). So, the parent may have the + * negative-dentry which matches the created 8.3 alias. + * + * If it happened, the negative dentry isn't actually negative + * anymore. So, drop it. + */ +static int vfat_revalidate_shortname(struct dentry *dentry) +{ + int ret = 1; + spin_lock(&dentry->d_lock); + if (dentry->d_time != dentry->d_parent->d_inode->i_version) + ret = 0; + spin_unlock(&dentry->d_lock); + return ret; +} + +static int vfat_revalidate(struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + + /* This is not negative dentry. Always valid. */ + if (dentry->d_inode) + return 1; + return vfat_revalidate_shortname(dentry); +} + +static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) +{ + if (flags & LOOKUP_RCU) + return -ECHILD; + + /* + * This is not negative dentry. Always valid. + * + * Note, rename() to existing directory entry will have ->d_inode, + * and will use existing name which isn't specified name by user. + * + * We may be able to drop this positive dentry here. But dropping + * positive dentry isn't good idea. So it's unsupported like + * rename("filename", "FILENAME") for now. + */ + if (dentry->d_inode) + return 1; + + /* + * This may be nfsd (or something), anyway, we can't see the + * intent of this. So, since this can be for creation, drop it. + */ + if (!flags) + return 0; + + /* + * Drop the negative dentry, in order to make sure to use the + * case sensitive name which is specified by user if this is + * for creation. + */ + if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) + return 0; + + return vfat_revalidate_shortname(dentry); +} + +/* returns the length of a struct qstr, ignoring trailing dots */ +static unsigned int __vfat_striptail_len(unsigned int len, const char *name) +{ + while (len && name[len - 1] == '.') + len--; + return len; +} + +static unsigned int vfat_striptail_len(const struct qstr *qstr) +{ + return __vfat_striptail_len(qstr->len, qstr->name); +} + +/* + * Compute the hash for the vfat name corresponding to the dentry. + * Note: if the name is invalid, we leave the hash code unchanged so + * that the existing dentry can be used. The vfat fs routines will + * return ENOENT or EINVAL as appropriate. + */ +static int vfat_hash(const struct dentry *dentry, struct qstr *qstr) +{ + qstr->hash = full_name_hash(qstr->name, vfat_striptail_len(qstr)); + return 0; +} + +/* + * Compute the hash for the vfat name corresponding to the dentry. + * Note: if the name is invalid, we leave the hash code unchanged so + * that the existing dentry can be used. The vfat fs routines will + * return ENOENT or EINVAL as appropriate. + */ +static int vfat_hashi(const struct dentry *dentry, struct qstr *qstr) +{ + struct nls_table *t = MSDOS_SB(dentry->d_sb)->nls_io; + const unsigned char *name; + unsigned int len; + unsigned long hash; + + name = qstr->name; + len = vfat_striptail_len(qstr); + + hash = init_name_hash(); + while (len--) + hash = partial_name_hash(nls_tolower(t, *name++), hash); + qstr->hash = end_name_hash(hash); + + return 0; +} + +/* + * Case insensitive compare of two vfat names. + */ +static int vfat_cmpi(const struct dentry *parent, const struct dentry *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + struct nls_table *t = MSDOS_SB(parent->d_sb)->nls_io; + unsigned int alen, blen; + + /* A filename cannot end in '.' or we treat it like it has none */ + alen = vfat_striptail_len(name); + blen = __vfat_striptail_len(len, str); + if (alen == blen) { + if (nls_strnicmp(t, name->name, str, alen) == 0) + return 0; + } + return 1; +} + +/* + * Case sensitive compare of two vfat names. + */ +static int vfat_cmp(const struct dentry *parent, const struct dentry *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + unsigned int alen, blen; + + /* A filename cannot end in '.' or we treat it like it has none */ + alen = vfat_striptail_len(name); + blen = __vfat_striptail_len(len, str); + if (alen == blen) { + if (strncmp(name->name, str, alen) == 0) + return 0; + } + return 1; +} + +static const struct dentry_operations vfat_ci_dentry_ops = { + .d_revalidate = vfat_revalidate_ci, + .d_hash = vfat_hashi, + .d_compare = vfat_cmpi, +}; + +static const struct dentry_operations vfat_dentry_ops = { + .d_revalidate = vfat_revalidate, + .d_hash = vfat_hash, + .d_compare = vfat_cmp, +}; + +/* Characters that are undesirable in an MS-DOS file name */ + +static inline wchar_t vfat_bad_char(wchar_t w) +{ + return (w < 0x0020) + || (w == '*') || (w == '?') || (w == '<') || (w == '>') + || (w == '|') || (w == '"') || (w == ':') || (w == '/') + || (w == '\\'); +} + +static inline wchar_t vfat_replace_char(wchar_t w) +{ + return (w == '[') || (w == ']') || (w == ';') || (w == ',') + || (w == '+') || (w == '='); +} + +static wchar_t vfat_skip_char(wchar_t w) +{ + return (w == '.') || (w == ' '); +} + +static inline int vfat_is_used_badchars(const wchar_t *s, int len) +{ + int i; + + for (i = 0; i < len; i++) + if (vfat_bad_char(s[i])) + return -EINVAL; + + if (s[i - 1] == ' ') /* last character cannot be space */ + return -EINVAL; + + return 0; +} + +static int vfat_find_form(struct inode *dir, unsigned char *name) +{ + struct fat_slot_info sinfo; + int err = fat_scan(dir, name, &sinfo); + if (err) + return -ENOENT; + brelse(sinfo.bh); + return 0; +} + +/* + * 1) Valid characters for the 8.3 format alias are any combination of + * letters, uppercase alphabets, digits, any of the + * following special characters: + * $ % ' ` - @ { } ~ ! # ( ) & _ ^ + * In this case Longfilename is not stored in disk. + * + * WinNT's Extension: + * File name and extension name is contain uppercase/lowercase + * only. And it is expressed by CASE_LOWER_BASE and CASE_LOWER_EXT. + * + * 2) File name is 8.3 format, but it contain the uppercase and + * lowercase char, muliti bytes char, etc. In this case numtail is not + * added, but Longfilename is stored. + * + * 3) When the one except for the above, or the following special + * character are contained: + * . [ ] ; , + = + * numtail is added, and Longfilename must be stored in disk . + */ +struct shortname_info { + unsigned char lower:1, + upper:1, + valid:1; +}; +#define INIT_SHORTNAME_INFO(x) do { \ + (x)->lower = 1; \ + (x)->upper = 1; \ + (x)->valid = 1; \ +} while (0) + +static inline int to_shortname_char(struct nls_table *nls, + unsigned char *buf, int buf_size, + wchar_t *src, struct shortname_info *info) +{ + int len; + + if (vfat_skip_char(*src)) { + info->valid = 0; + return 0; + } + if (vfat_replace_char(*src)) { + info->valid = 0; + buf[0] = '_'; + return 1; + } + + len = nls->uni2char(*src, buf, buf_size); + if (len <= 0) { + info->valid = 0; + buf[0] = '_'; + len = 1; + } else if (len == 1) { + unsigned char prev = buf[0]; + + if (buf[0] >= 0x7F) { + info->lower = 0; + info->upper = 0; + } + + buf[0] = nls_toupper(nls, buf[0]); + if (isalpha(buf[0])) { + if (buf[0] == prev) + info->lower = 0; + else + info->upper = 0; + } + } else { + info->lower = 0; + info->upper = 0; + } + + return len; +} + +/* + * Given a valid longname, create a unique shortname. Make sure the + * shortname does not exist + * Returns negative number on error, 0 for a normal + * return, and 1 for valid shortname + */ +static int vfat_create_shortname(struct inode *dir, struct nls_table *nls, + wchar_t *uname, int ulen, + unsigned char *name_res, unsigned char *lcase) +{ + struct fat_mount_options *opts = &MSDOS_SB(dir->i_sb)->options; + wchar_t *ip, *ext_start, *end, *name_start; + unsigned char base[9], ext[4], buf[5], *p; + unsigned char charbuf[NLS_MAX_CHARSET_SIZE]; + int chl, chi; + int sz = 0, extlen, baselen, i, numtail_baselen, numtail2_baselen; + int is_shortname; + struct shortname_info base_info, ext_info; + + is_shortname = 1; + INIT_SHORTNAME_INFO(&base_info); + INIT_SHORTNAME_INFO(&ext_info); + + /* Now, we need to create a shortname from the long name */ + ext_start = end = &uname[ulen]; + while (--ext_start >= uname) { + if (*ext_start == 0x002E) { /* is `.' */ + if (ext_start == end - 1) { + sz = ulen; + ext_start = NULL; + } + break; + } + } + + if (ext_start == uname - 1) { + sz = ulen; + ext_start = NULL; + } else if (ext_start) { + /* + * Names which start with a dot could be just + * an extension eg. "...test". In this case Win95 + * uses the extension as the name and sets no extension. + */ + name_start = &uname[0]; + while (name_start < ext_start) { + if (!vfat_skip_char(*name_start)) + break; + name_start++; + } + if (name_start != ext_start) { + sz = ext_start - uname; + ext_start++; + } else { + sz = ulen; + ext_start = NULL; + } + } + + numtail_baselen = 6; + numtail2_baselen = 2; + for (baselen = i = 0, p = base, ip = uname; i < sz; i++, ip++) { + chl = to_shortname_char(nls, charbuf, sizeof(charbuf), + ip, &base_info); + if (chl == 0) + continue; + + if (baselen < 2 && (baselen + chl) > 2) + numtail2_baselen = baselen; + if (baselen < 6 && (baselen + chl) > 6) + numtail_baselen = baselen; + for (chi = 0; chi < chl; chi++) { + *p++ = charbuf[chi]; + baselen++; + if (baselen >= 8) + break; + } + if (baselen >= 8) { + if ((chi < chl - 1) || (ip + 1) - uname < sz) + is_shortname = 0; + break; + } + } + if (baselen == 0) { + return -EINVAL; + } + + extlen = 0; + if (ext_start) { + for (p = ext, ip = ext_start; extlen < 3 && ip < end; ip++) { + chl = to_shortname_char(nls, charbuf, sizeof(charbuf), + ip, &ext_info); + if (chl == 0) + continue; + + if ((extlen + chl) > 3) { + is_shortname = 0; + break; + } + for (chi = 0; chi < chl; chi++) { + *p++ = charbuf[chi]; + extlen++; + } + if (extlen >= 3) { + if (ip + 1 != end) + is_shortname = 0; + break; + } + } + } + ext[extlen] = '\0'; + base[baselen] = '\0'; + + /* Yes, it can happen. ".\xe5" would do it. */ + if (base[0] == DELETED_FLAG) + base[0] = 0x05; + + /* OK, at this point we know that base is not longer than 8 symbols, + * ext is not longer than 3, base is nonempty, both don't contain + * any bad symbols (lowercase transformed to uppercase). + */ + + memset(name_res, ' ', MSDOS_NAME); + memcpy(name_res, base, baselen); + memcpy(name_res + 8, ext, extlen); + *lcase = 0; + if (is_shortname && base_info.valid && ext_info.valid) { + if (vfat_find_form(dir, name_res) == 0) + return -EEXIST; + + if (opts->shortname & VFAT_SFN_CREATE_WIN95) { + return (base_info.upper && ext_info.upper); + } else if (opts->shortname & VFAT_SFN_CREATE_WINNT) { + if ((base_info.upper || base_info.lower) && + (ext_info.upper || ext_info.lower)) { + if (!base_info.upper && base_info.lower) + *lcase |= CASE_LOWER_BASE; + if (!ext_info.upper && ext_info.lower) + *lcase |= CASE_LOWER_EXT; + return 1; + } + return 0; + } else { + BUG(); + } + } + + if (opts->numtail == 0) + if (vfat_find_form(dir, name_res) < 0) + return 0; + + /* + * Try to find a unique extension. This used to + * iterate through all possibilities sequentially, + * but that gave extremely bad performance. Windows + * only tries a few cases before using random + * values for part of the base. + */ + + if (baselen > 6) { + baselen = numtail_baselen; + name_res[7] = ' '; + } + name_res[baselen] = '~'; + for (i = 1; i < 10; i++) { + name_res[baselen + 1] = i + '0'; + if (vfat_find_form(dir, name_res) < 0) + return 0; + } + + i = jiffies; + sz = (jiffies >> 16) & 0x7; + if (baselen > 2) { + baselen = numtail2_baselen; + name_res[7] = ' '; + } + name_res[baselen + 4] = '~'; + name_res[baselen + 5] = '1' + sz; + while (1) { + snprintf(buf, sizeof(buf), "%04X", i & 0xffff); + memcpy(&name_res[baselen], buf, 4); + if (vfat_find_form(dir, name_res) < 0) + break; + i -= 11; + } + return 0; +} + +/* Translate a string, including coded sequences into Unicode */ +static int +xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, + int *longlen, int *outlen, int escape, int utf8, + struct nls_table *nls) +{ + const unsigned char *ip; + unsigned char nc; + unsigned char *op; + unsigned int ec; + int i, k, fill; + int charlen; + + if (utf8) { + *outlen = utf8s_to_utf16s(name, len, UTF16_HOST_ENDIAN, + (wchar_t *) outname, FAT_LFN_LEN + 2); + if (*outlen < 0) + return *outlen; + else if (*outlen > FAT_LFN_LEN) + return -ENAMETOOLONG; + + op = &outname[*outlen * sizeof(wchar_t)]; + } else { + for (i = 0, ip = name, op = outname, *outlen = 0; + i < len && *outlen < FAT_LFN_LEN; + *outlen += 1) { + if (escape && (*ip == ':')) { + if (i > len - 5) + return -EINVAL; + ec = 0; + for (k = 1; k < 5; k++) { + nc = ip[k]; + ec <<= 4; + if (nc >= '0' && nc <= '9') { + ec |= nc - '0'; + continue; + } + if (nc >= 'a' && nc <= 'f') { + ec |= nc - ('a' - 10); + continue; + } + if (nc >= 'A' && nc <= 'F') { + ec |= nc - ('A' - 10); + continue; + } + return -EINVAL; + } + *op++ = ec & 0xFF; + *op++ = ec >> 8; + ip += 5; + i += 5; + } else { + charlen = nls->char2uni(ip, len - i, + (wchar_t *)op); + if (charlen < 0) + return -EINVAL; + ip += charlen; + i += charlen; + op += 2; + } + } + if (i < len) + return -ENAMETOOLONG; + } + + *longlen = *outlen; + if (*outlen % 13) { + *op++ = 0; + *op++ = 0; + *outlen += 1; + if (*outlen % 13) { + fill = 13 - (*outlen % 13); + for (i = 0; i < fill; i++) { + *op++ = 0xff; + *op++ = 0xff; + } + *outlen += fill; + } + } + + return 0; +} + +static int vfat_build_slots(struct inode *dir, const unsigned char *name, + int len, int is_dir, int cluster, + struct timespec *ts, + struct msdos_dir_slot *slots, int *nr_slots) +{ + struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb); + struct fat_mount_options *opts = &sbi->options; + struct msdos_dir_slot *ps; + struct msdos_dir_entry *de; + unsigned char cksum, lcase; + unsigned char msdos_name[MSDOS_NAME]; + wchar_t *uname; + __le16 time, date; + u8 time_cs; + int err, ulen, usize, i; + loff_t offset; + + *nr_slots = 0; + + uname = __getname(); + if (!uname) + return -ENOMEM; + + err = xlate_to_uni(name, len, (unsigned char *)uname, &ulen, &usize, + opts->unicode_xlate, opts->utf8, sbi->nls_io); + if (err) + goto out_free; + + err = vfat_is_used_badchars(uname, ulen); + if (err) + goto out_free; + + err = vfat_create_shortname(dir, sbi->nls_disk, uname, ulen, + msdos_name, &lcase); + if (err < 0) + goto out_free; + else if (err == 1) { + de = (struct msdos_dir_entry *)slots; + err = 0; + goto shortname; + } + + /* build the entry of long file name */ + cksum = fat_checksum(msdos_name); + + *nr_slots = usize / 13; + for (ps = slots, i = *nr_slots; i > 0; i--, ps++) { + ps->id = i; + ps->attr = ATTR_EXT; + ps->reserved = 0; + ps->alias_checksum = cksum; + ps->start = 0; + offset = (i - 1) * 13; + fatwchar_to16(ps->name0_4, uname + offset, 5); + fatwchar_to16(ps->name5_10, uname + offset + 5, 6); + fatwchar_to16(ps->name11_12, uname + offset + 11, 2); + } + slots[0].id |= 0x40; + de = (struct msdos_dir_entry *)ps; + +shortname: + /* build the entry of 8.3 alias name */ + (*nr_slots)++; + memcpy(de->name, msdos_name, MSDOS_NAME); + de->attr = is_dir ? ATTR_DIR : ATTR_ARCH; + de->lcase = lcase; + fat_time_unix2fat(sbi, ts, &time, &date, &time_cs); + de->time = de->ctime = time; + de->date = de->cdate = de->adate = date; + de->ctime_cs = time_cs; + fat_set_start(de, cluster); + de->size = 0; +out_free: + __putname(uname); + return err; +} + +static int vfat_add_entry(struct inode *dir, struct qstr *qname, int is_dir, + int cluster, struct timespec *ts, + struct fat_slot_info *sinfo) +{ + struct msdos_dir_slot *slots; + unsigned int len; + int err, nr_slots; + + len = vfat_striptail_len(qname); + if (len == 0) + return -ENOENT; + + slots = kmalloc(sizeof(*slots) * MSDOS_SLOTS, GFP_NOFS); + if (slots == NULL) + return -ENOMEM; + + err = vfat_build_slots(dir, qname->name, len, is_dir, cluster, ts, + slots, &nr_slots); + if (err) + goto cleanup; + + err = fat_add_entries(dir, slots, nr_slots, sinfo); + if (err) + goto cleanup; + + /* update timestamp */ + dir->i_ctime = dir->i_mtime = dir->i_atime = *ts; + if (IS_DIRSYNC(dir)) + (void)fat_sync_inode(dir); + else + mark_inode_dirty(dir); +cleanup: + kfree(slots); + return err; +} + +static int vfat_find(struct inode *dir, struct qstr *qname, + struct fat_slot_info *sinfo) +{ + unsigned int len = vfat_striptail_len(qname); + if (len == 0) + return -ENOENT; + return fat_search_long(dir, qname->name, len, sinfo); +} + +/* + * (nfsd's) anonymous disconnected dentry? + * NOTE: !IS_ROOT() is not anonymous (I.e. d_splice_alias() did the job). + */ +static int vfat_d_anon_disconn(struct dentry *dentry) +{ + return IS_ROOT(dentry) && (dentry->d_flags & DCACHE_DISCONNECTED); +} + +static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, + unsigned int flags) +{ + struct super_block *sb = dir->i_sb; + struct fat_slot_info sinfo; + struct inode *inode; + struct dentry *alias; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + err = vfat_find(dir, &dentry->d_name, &sinfo); + if (err) { + if (err == -ENOENT) { + inode = NULL; + goto out; + } + goto error; + } + + inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + brelse(sinfo.bh); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto error; + } + + alias = d_find_alias(inode); + if (alias && !vfat_d_anon_disconn(alias)) { + /* + * This inode has non anonymous-DCACHE_DISCONNECTED + * dentry. This means, the user did ->lookup() by an + * another name (longname vs 8.3 alias of it) in past. + * + * Switch to new one for reason of locality if possible. + */ + BUG_ON(d_unhashed(alias)); + if (!S_ISDIR(inode->i_mode)) + d_move(alias, dentry); + iput(inode); + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return alias; + } else + dput(alias); + +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + dentry->d_time = dentry->d_parent->d_inode->i_version; + dentry = d_splice_alias(inode, dentry); + if (dentry) + dentry->d_time = dentry->d_parent->d_inode->i_version; + return dentry; + +error: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return ERR_PTR(err); +} + +static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, + bool excl) +{ + struct super_block *sb = dir->i_sb; + struct inode *inode; + struct fat_slot_info sinfo; + struct timespec ts; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + ts = CURRENT_TIME_SEC; + err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo); + if (err) + goto out; + dir->i_version++; + + inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + brelse(sinfo.bh); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out; + } + inode->i_version++; + inode->i_mtime = inode->i_atime = inode->i_ctime = ts; + /* timestamp is already written, so mark_inode_dirty() is unneeded. */ + + dentry->d_time = dentry->d_parent->d_inode->i_version; + d_instantiate(dentry, inode); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return err; +} + +static int vfat_rmdir(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct super_block *sb = dir->i_sb; + struct fat_slot_info sinfo; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + err = fat_dir_empty(inode); + if (err) + goto out; + err = vfat_find(dir, &dentry->d_name, &sinfo); + if (err) + goto out; + + err = fat_remove_entries(dir, &sinfo); /* and releases bh */ + if (err) + goto out; + drop_nlink(dir); + + clear_nlink(inode); + inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; + fat_detach(inode); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + + return err; +} + +static int vfat_unlink(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = dentry->d_inode; + struct super_block *sb = dir->i_sb; + struct fat_slot_info sinfo; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + err = vfat_find(dir, &dentry->d_name, &sinfo); + if (err) + goto out; + + err = fat_remove_entries(dir, &sinfo); /* and releases bh */ + if (err) + goto out; + clear_nlink(inode); + inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; + fat_detach(inode); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + + return err; +} + +static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct super_block *sb = dir->i_sb; + struct inode *inode; + struct fat_slot_info sinfo; + struct timespec ts; + int err, cluster; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + ts = CURRENT_TIME_SEC; + cluster = fat_alloc_new_dir(dir, &ts); + if (cluster < 0) { + err = cluster; + goto out; + } + err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &ts, &sinfo); + if (err) + goto out_free; + dir->i_version++; + inc_nlink(dir); + + inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + brelse(sinfo.bh); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + /* the directory was completed, just return a error */ + goto out; + } + inode->i_version++; + set_nlink(inode, 2); + inode->i_mtime = inode->i_atime = inode->i_ctime = ts; + /* timestamp is already written, so mark_inode_dirty() is unneeded. */ + + dentry->d_time = dentry->d_parent->d_inode->i_version; + d_instantiate(dentry, inode); + + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return 0; + +out_free: + fat_free_clusters(dir, cluster); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return err; +} + +static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct buffer_head *dotdot_bh; + struct msdos_dir_entry *dotdot_de; + struct inode *old_inode, *new_inode; + struct fat_slot_info old_sinfo, sinfo; + struct timespec ts; + loff_t new_i_pos; + int err, is_dir, update_dotdot, corrupt = 0; + struct super_block *sb = old_dir->i_sb; + + old_sinfo.bh = sinfo.bh = dotdot_bh = NULL; + old_inode = old_dentry->d_inode; + new_inode = new_dentry->d_inode; + mutex_lock(&MSDOS_SB(sb)->s_lock); + err = vfat_find(old_dir, &old_dentry->d_name, &old_sinfo); + if (err) + goto out; + + is_dir = S_ISDIR(old_inode->i_mode); + update_dotdot = (is_dir && old_dir != new_dir); + if (update_dotdot) { + if (fat_get_dotdot_entry(old_inode, &dotdot_bh, &dotdot_de)) { + err = -EIO; + goto out; + } + } + + ts = CURRENT_TIME_SEC; + if (new_inode) { + if (is_dir) { + err = fat_dir_empty(new_inode); + if (err) + goto out; + } + new_i_pos = MSDOS_I(new_inode)->i_pos; + fat_detach(new_inode); + } else { + err = vfat_add_entry(new_dir, &new_dentry->d_name, is_dir, 0, + &ts, &sinfo); + if (err) + goto out; + new_i_pos = sinfo.i_pos; + } + new_dir->i_version++; + + fat_detach(old_inode); + fat_attach(old_inode, new_i_pos); + if (IS_DIRSYNC(new_dir)) { + err = fat_sync_inode(old_inode); + if (err) + goto error_inode; + } else + mark_inode_dirty(old_inode); + + if (update_dotdot) { + fat_set_start(dotdot_de, MSDOS_I(new_dir)->i_logstart); + mark_buffer_dirty_inode(dotdot_bh, old_inode); + if (IS_DIRSYNC(new_dir)) { + err = sync_dirty_buffer(dotdot_bh); + if (err) + goto error_dotdot; + } + drop_nlink(old_dir); + if (!new_inode) + inc_nlink(new_dir); + } + + err = fat_remove_entries(old_dir, &old_sinfo); /* and releases bh */ + old_sinfo.bh = NULL; + if (err) + goto error_dotdot; + old_dir->i_version++; + old_dir->i_ctime = old_dir->i_mtime = ts; + if (IS_DIRSYNC(old_dir)) + (void)fat_sync_inode(old_dir); + else + mark_inode_dirty(old_dir); + + if (new_inode) { + drop_nlink(new_inode); + if (is_dir) + drop_nlink(new_inode); + new_inode->i_ctime = ts; + } +out: + brelse(sinfo.bh); + brelse(dotdot_bh); + brelse(old_sinfo.bh); + mutex_unlock(&MSDOS_SB(sb)->s_lock); + + return err; + +error_dotdot: + /* data cluster is shared, serious corruption */ + corrupt = 1; + + if (update_dotdot) { + fat_set_start(dotdot_de, MSDOS_I(old_dir)->i_logstart); + mark_buffer_dirty_inode(dotdot_bh, old_inode); + corrupt |= sync_dirty_buffer(dotdot_bh); + } +error_inode: + fat_detach(old_inode); + fat_attach(old_inode, old_sinfo.i_pos); + if (new_inode) { + fat_attach(new_inode, new_i_pos); + if (corrupt) + corrupt |= fat_sync_inode(new_inode); + } else { + /* + * If new entry was not sharing the data cluster, it + * shouldn't be serious corruption. + */ + int err2 = fat_remove_entries(new_dir, &sinfo); + if (corrupt) + corrupt |= err2; + sinfo.bh = NULL; + } + if (corrupt < 0) { + fat_fs_error(new_dir->i_sb, + "%s: Filesystem corrupted (i_pos %lld)", + __func__, sinfo.i_pos); + } + goto out; +} + +static const struct inode_operations vfat_dir_inode_operations = { + .create = vfat_create, + .lookup = vfat_lookup, + .unlink = vfat_unlink, + .mkdir = vfat_mkdir, + .rmdir = vfat_rmdir, + .rename = vfat_rename, + .setattr = fat_setattr, + .getattr = fat_getattr, +}; + +static void setup(struct super_block *sb) +{ + MSDOS_SB(sb)->dir_ops = &vfat_dir_inode_operations; + if (MSDOS_SB(sb)->options.name_check != 's') + sb->s_d_op = &vfat_ci_dentry_ops; + else + sb->s_d_op = &vfat_dentry_ops; +} + +static int vfat_fill_super(struct super_block *sb, void *data, int silent) +{ + return fat_fill_super(sb, data, silent, 1, setup); +} + +static struct dentry *vfat_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data) +{ + return mount_bdev(fs_type, flags, dev_name, data, vfat_fill_super); +} + +static struct file_system_type vfat_fs_type = { + .owner = THIS_MODULE, + .name = "vfat", + .mount = vfat_mount, + .kill_sb = kill_block_super, + .fs_flags = FS_REQUIRES_DEV, +}; +MODULE_ALIAS_FS("vfat"); + +static int __init init_vfat_fs(void) +{ + return register_filesystem(&vfat_fs_type); +} + +static void __exit exit_vfat_fs(void) +{ + unregister_filesystem(&vfat_fs_type); +} + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("VFAT filesystem support"); +MODULE_AUTHOR("Gordon Chaffee"); + +module_init(init_vfat_fs) +module_exit(exit_vfat_fs) diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c new file mode 100644 index 00000000000..93e14933dcb --- /dev/null +++ b/fs/fat/nfs.c @@ -0,0 +1,301 @@ +/* fs/fat/nfs.c + * + * This software is licensed under the terms of the GNU General Public + * License version 2, as published by the Free Software Foundation, and + * may be copied, distributed, and modified under those terms. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + */ + +#include <linux/exportfs.h> +#include "fat.h" + +struct fat_fid { + u32 i_gen; + u32 i_pos_low; + u16 i_pos_hi; + u16 parent_i_pos_hi; + u32 parent_i_pos_low; + u32 parent_i_gen; +}; + +#define FAT_FID_SIZE_WITHOUT_PARENT 3 +#define FAT_FID_SIZE_WITH_PARENT (sizeof(struct fat_fid)/sizeof(u32)) + +/** + * Look up a directory inode given its starting cluster. + */ +static struct inode *fat_dget(struct super_block *sb, int i_logstart) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct hlist_head *head; + struct msdos_inode_info *i; + struct inode *inode = NULL; + + head = sbi->dir_hashtable + fat_dir_hash(i_logstart); + spin_lock(&sbi->dir_hash_lock); + hlist_for_each_entry(i, head, i_dir_hash) { + BUG_ON(i->vfs_inode.i_sb != sb); + if (i->i_logstart != i_logstart) + continue; + inode = igrab(&i->vfs_inode); + if (inode) + break; + } + spin_unlock(&sbi->dir_hash_lock); + return inode; +} + +static struct inode *fat_ilookup(struct super_block *sb, u64 ino, loff_t i_pos) +{ + if (MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO) + return fat_iget(sb, i_pos); + + else { + if ((ino < MSDOS_ROOT_INO) || (ino == MSDOS_FSINFO_INO)) + return NULL; + return ilookup(sb, ino); + } +} + +static struct inode *__fat_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation, loff_t i_pos) +{ + struct inode *inode = fat_ilookup(sb, ino, i_pos); + + if (inode && generation && (inode->i_generation != generation)) { + iput(inode); + inode = NULL; + } + if (inode == NULL && MSDOS_SB(sb)->options.nfs == FAT_NFS_NOSTALE_RO) { + struct buffer_head *bh = NULL; + struct msdos_dir_entry *de ; + sector_t blocknr; + int offset; + fat_get_blknr_offset(MSDOS_SB(sb), i_pos, &blocknr, &offset); + bh = sb_bread(sb, blocknr); + if (!bh) { + fat_msg(sb, KERN_ERR, + "unable to read block(%llu) for building NFS inode", + (llu)blocknr); + return inode; + } + de = (struct msdos_dir_entry *)bh->b_data; + /* If a file is deleted on server and client is not updated + * yet, we must not build the inode upon a lookup call. + */ + if (IS_FREE(de[offset].name)) + inode = NULL; + else + inode = fat_build_inode(sb, &de[offset], i_pos); + brelse(bh); + } + + return inode; +} + +static struct inode *fat_nfs_get_inode(struct super_block *sb, + u64 ino, u32 generation) +{ + + return __fat_nfs_get_inode(sb, ino, generation, 0); +} + +static int +fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, + struct inode *parent) +{ + int len = *lenp; + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + struct fat_fid *fid = (struct fat_fid *) fh; + loff_t i_pos; + int type = FILEID_FAT_WITHOUT_PARENT; + + if (parent) { + if (len < FAT_FID_SIZE_WITH_PARENT) { + *lenp = FAT_FID_SIZE_WITH_PARENT; + return FILEID_INVALID; + } + } else { + if (len < FAT_FID_SIZE_WITHOUT_PARENT) { + *lenp = FAT_FID_SIZE_WITHOUT_PARENT; + return FILEID_INVALID; + } + } + + i_pos = fat_i_pos_read(sbi, inode); + *lenp = FAT_FID_SIZE_WITHOUT_PARENT; + fid->i_gen = inode->i_generation; + fid->i_pos_low = i_pos & 0xFFFFFFFF; + fid->i_pos_hi = (i_pos >> 32) & 0xFFFF; + if (parent) { + i_pos = fat_i_pos_read(sbi, parent); + fid->parent_i_pos_hi = (i_pos >> 32) & 0xFFFF; + fid->parent_i_pos_low = i_pos & 0xFFFFFFFF; + fid->parent_i_gen = parent->i_generation; + type = FILEID_FAT_WITH_PARENT; + *lenp = FAT_FID_SIZE_WITH_PARENT; + } + + return type; +} + +/** + * Map a NFS file handle to a corresponding dentry. + * The dentry may or may not be connected to the filesystem root. + */ +static struct dentry *fat_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, + fat_nfs_get_inode); +} + +static struct dentry *fat_fh_to_dentry_nostale(struct super_block *sb, + struct fid *fh, int fh_len, + int fh_type) +{ + struct inode *inode = NULL; + struct fat_fid *fid = (struct fat_fid *)fh; + loff_t i_pos; + + switch (fh_type) { + case FILEID_FAT_WITHOUT_PARENT: + if (fh_len < FAT_FID_SIZE_WITHOUT_PARENT) + return NULL; + break; + case FILEID_FAT_WITH_PARENT: + if (fh_len < FAT_FID_SIZE_WITH_PARENT) + return NULL; + break; + default: + return NULL; + } + i_pos = fid->i_pos_hi; + i_pos = (i_pos << 32) | (fid->i_pos_low); + inode = __fat_nfs_get_inode(sb, 0, fid->i_gen, i_pos); + + return d_obtain_alias(inode); +} + +/* + * Find the parent for a file specified by NFS handle. + * This requires that the handle contain the i_ino of the parent. + */ +static struct dentry *fat_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, + fat_nfs_get_inode); +} + +static struct dentry *fat_fh_to_parent_nostale(struct super_block *sb, + struct fid *fh, int fh_len, + int fh_type) +{ + struct inode *inode = NULL; + struct fat_fid *fid = (struct fat_fid *)fh; + loff_t i_pos; + + if (fh_len < FAT_FID_SIZE_WITH_PARENT) + return NULL; + + switch (fh_type) { + case FILEID_FAT_WITH_PARENT: + i_pos = fid->parent_i_pos_hi; + i_pos = (i_pos << 32) | (fid->parent_i_pos_low); + inode = __fat_nfs_get_inode(sb, 0, fid->parent_i_gen, i_pos); + break; + } + + return d_obtain_alias(inode); +} + +/* + * Rebuild the parent for a directory that is not connected + * to the filesystem root + */ +static +struct inode *fat_rebuild_parent(struct super_block *sb, int parent_logstart) +{ + int search_clus, clus_to_match; + struct msdos_dir_entry *de; + struct inode *parent = NULL; + struct inode *dummy_grand_parent = NULL; + struct fat_slot_info sinfo; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + sector_t blknr = fat_clus_to_blknr(sbi, parent_logstart); + struct buffer_head *parent_bh = sb_bread(sb, blknr); + if (!parent_bh) { + fat_msg(sb, KERN_ERR, + "unable to read cluster of parent directory"); + return NULL; + } + + de = (struct msdos_dir_entry *) parent_bh->b_data; + clus_to_match = fat_get_start(sbi, &de[0]); + search_clus = fat_get_start(sbi, &de[1]); + + dummy_grand_parent = fat_dget(sb, search_clus); + if (!dummy_grand_parent) { + dummy_grand_parent = new_inode(sb); + if (!dummy_grand_parent) { + brelse(parent_bh); + return parent; + } + + dummy_grand_parent->i_ino = iunique(sb, MSDOS_ROOT_INO); + fat_fill_inode(dummy_grand_parent, &de[1]); + MSDOS_I(dummy_grand_parent)->i_pos = -1; + } + + if (!fat_scan_logstart(dummy_grand_parent, clus_to_match, &sinfo)) + parent = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + + brelse(parent_bh); + iput(dummy_grand_parent); + + return parent; +} + +/* + * Find the parent for a directory that is not currently connected to + * the filesystem root. + * + * On entry, the caller holds child_dir->d_inode->i_mutex. + */ +static struct dentry *fat_get_parent(struct dentry *child_dir) +{ + struct super_block *sb = child_dir->d_sb; + struct buffer_head *bh = NULL; + struct msdos_dir_entry *de; + struct inode *parent_inode = NULL; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + if (!fat_get_dotdot_entry(child_dir->d_inode, &bh, &de)) { + int parent_logstart = fat_get_start(sbi, de); + parent_inode = fat_dget(sb, parent_logstart); + if (!parent_inode && sbi->options.nfs == FAT_NFS_NOSTALE_RO) + parent_inode = fat_rebuild_parent(sb, parent_logstart); + } + brelse(bh); + + return d_obtain_alias(parent_inode); +} + +const struct export_operations fat_export_ops = { + .fh_to_dentry = fat_fh_to_dentry, + .fh_to_parent = fat_fh_to_parent, + .get_parent = fat_get_parent, +}; + +const struct export_operations fat_export_ops_nostale = { + .encode_fh = fat_encode_fh_nostale, + .fh_to_dentry = fat_fh_to_dentry_nostale, + .fh_to_parent = fat_fh_to_parent_nostale, + .get_parent = fat_get_parent, +}; |
