diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-07 18:49:45 +0000 |
commit | 2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch) | |
tree | 848558de17fb3008cdf4d861b01ac7781903ce39 /fs/fat | |
parent | Initial commit. (diff) | |
download | linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip |
Adding upstream version 6.1.76.upstream/6.1.76
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'fs/fat')
-rw-r--r-- | fs/fat/.kunitconfig | 5 | ||||
-rw-r--r-- | fs/fat/Kconfig | 129 | ||||
-rw-r--r-- | fs/fat/Makefile | 14 | ||||
-rw-r--r-- | fs/fat/cache.c | 386 | ||||
-rw-r--r-- | fs/fat/dir.c | 1414 | ||||
-rw-r--r-- | fs/fat/fat.h | 477 | ||||
-rw-r--r-- | fs/fat/fat_test.c | 196 | ||||
-rw-r--r-- | fs/fat/fatent.c | 848 | ||||
-rw-r--r-- | fs/fat/file.c | 578 | ||||
-rw-r--r-- | fs/fat/inode.c | 1975 | ||||
-rw-r--r-- | fs/fat/misc.c | 377 | ||||
-rw-r--r-- | fs/fat/namei_msdos.c | 689 | ||||
-rw-r--r-- | fs/fat/namei_vfat.c | 1234 | ||||
-rw-r--r-- | fs/fat/nfs.c | 292 |
14 files changed, 8614 insertions, 0 deletions
diff --git a/fs/fat/.kunitconfig b/fs/fat/.kunitconfig new file mode 100644 index 000000000..0a6971dbe --- /dev/null +++ b/fs/fat/.kunitconfig @@ -0,0 +1,5 @@ +CONFIG_KUNIT=y +CONFIG_FAT_FS=y +CONFIG_MSDOS_FS=y +CONFIG_VFAT_FS=y +CONFIG_FAT_KUNIT_TEST=y diff --git a/fs/fat/Kconfig b/fs/fat/Kconfig new file mode 100644 index 000000000..238cc55f8 --- /dev/null +++ b/fs/fat/Kconfig @@ -0,0 +1,129 @@ +# SPDX-License-Identifier: GPL-2.0-only +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 + <https://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.rst> 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 FAT_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.rst> 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 - select the next option + instead if you would like to use UTF-8 encoded file names by default. + See <file:Documentation/filesystems/vfat.rst> for more information. + + Enable any character sets you need in File Systems/Native Language + Support. + +config FAT_DEFAULT_UTF8 + bool "Enable FAT UTF-8 option by default" + depends on VFAT_FS + default n + help + Set this if you would like to have "utf8" mount option set + by default when mounting FAT filesystems. + + Even if you say Y here can always disable UTF-8 for + particular mount by adding "utf8=0" to mount options. + + Say Y if you use UTF-8 encoding for file names, N otherwise. + + See <file:Documentation/filesystems/vfat.rst> for more information. + +config FAT_KUNIT_TEST + tristate "Unit Tests for FAT filesystems" if !KUNIT_ALL_TESTS + depends on KUNIT && FAT_FS + default KUNIT_ALL_TESTS + help + This builds the FAT KUnit tests + + For more information on KUnit and unit tests in general, please refer + to the KUnit documentation in Documentation/dev-tools/kunit + + If unsure, say N diff --git a/fs/fat/Makefile b/fs/fat/Makefile new file mode 100644 index 000000000..2b0341126 --- /dev/null +++ b/fs/fat/Makefile @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the Linux fat filesystem support. +# + +obj-$(CONFIG_FAT_FS) += fat.o +obj-$(CONFIG_VFAT_FS) += vfat.o +obj-$(CONFIG_MSDOS_FS) += msdos.o + +fat-y := cache.o dir.o fatent.o file.o inode.o misc.o nfs.o +vfat-y := namei_vfat.o +msdos-y := namei_msdos.o + +obj-$(CONFIG_FAT_KUNIT_TEST) += fat_test.o diff --git a/fs/fat/cache.c b/fs/fat/cache.c new file mode 100644 index 000000000..738e427e2 --- /dev/null +++ b/fs/fat/cache.c @@ -0,0 +1,386 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/fs/fat/cache.c + * + * Written 1992,1993 by Werner Almesberger + * + * Mar 1999. AV. Changed cache, so that it uses the starting cluster instead + * of inode number. + * May 1999. AV. Fixed the bogosity with FAT32 (read "FAT28"). Fscking lusers. + */ + +#include <linux/slab.h> +#include "fat.h" + +/* this must be > 0. */ +#define FAT_MAX_CACHE 8 + +struct fat_cache { + struct list_head cache_list; + int nr_contig; /* number of contiguous clusters */ + int fcluster; /* cluster number in the file. */ + int dcluster; /* cluster number on disk. */ +}; + +struct fat_cache_id { + unsigned int id; + int nr_contig; + int fcluster; + int dcluster; +}; + +static inline int fat_max_cache(struct inode *inode) +{ + return FAT_MAX_CACHE; +} + +static struct kmem_cache *fat_cache_cachep; + +static void init_once(void *foo) +{ + struct fat_cache *cache = (struct fat_cache *)foo; + + INIT_LIST_HEAD(&cache->cache_list); +} + +int __init fat_cache_init(void) +{ + fat_cache_cachep = kmem_cache_create("fat_cache", + sizeof(struct fat_cache), + 0, SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD, + init_once); + if (fat_cache_cachep == NULL) + return -ENOMEM; + return 0; +} + +void fat_cache_destroy(void) +{ + kmem_cache_destroy(fat_cache_cachep); +} + +static inline struct fat_cache *fat_cache_alloc(struct inode *inode) +{ + return kmem_cache_alloc(fat_cache_cachep, GFP_NOFS); +} + +static inline void fat_cache_free(struct fat_cache *cache) +{ + BUG_ON(!list_empty(&cache->cache_list)); + kmem_cache_free(fat_cache_cachep, cache); +} + +static inline void fat_cache_update_lru(struct inode *inode, + struct fat_cache *cache) +{ + if (MSDOS_I(inode)->cache_lru.next != &cache->cache_list) + list_move(&cache->cache_list, &MSDOS_I(inode)->cache_lru); +} + +static int fat_cache_lookup(struct inode *inode, int fclus, + struct fat_cache_id *cid, + int *cached_fclus, int *cached_dclus) +{ + static struct fat_cache nohit = { .fcluster = 0, }; + + struct fat_cache *hit = &nohit, *p; + int offset = -1; + + spin_lock(&MSDOS_I(inode)->cache_lru_lock); + list_for_each_entry(p, &MSDOS_I(inode)->cache_lru, cache_list) { + /* Find the cache of "fclus" or nearest cache. */ + if (p->fcluster <= fclus && hit->fcluster < p->fcluster) { + hit = p; + if ((hit->fcluster + hit->nr_contig) < fclus) { + offset = hit->nr_contig; + } else { + offset = fclus - hit->fcluster; + break; + } + } + } + if (hit != &nohit) { + fat_cache_update_lru(inode, hit); + + cid->id = MSDOS_I(inode)->cache_valid_id; + cid->nr_contig = hit->nr_contig; + cid->fcluster = hit->fcluster; + cid->dcluster = hit->dcluster; + *cached_fclus = cid->fcluster + offset; + *cached_dclus = cid->dcluster + offset; + } + spin_unlock(&MSDOS_I(inode)->cache_lru_lock); + + return offset; +} + +static struct fat_cache *fat_cache_merge(struct inode *inode, + struct fat_cache_id *new) +{ + struct fat_cache *p; + + list_for_each_entry(p, &MSDOS_I(inode)->cache_lru, cache_list) { + /* Find the same part as "new" in cluster-chain. */ + if (p->fcluster == new->fcluster) { + BUG_ON(p->dcluster != new->dcluster); + if (new->nr_contig > p->nr_contig) + p->nr_contig = new->nr_contig; + return p; + } + } + return NULL; +} + +static void fat_cache_add(struct inode *inode, struct fat_cache_id *new) +{ + struct fat_cache *cache, *tmp; + + if (new->fcluster == -1) /* dummy cache */ + return; + + spin_lock(&MSDOS_I(inode)->cache_lru_lock); + if (new->id != FAT_CACHE_VALID && + new->id != MSDOS_I(inode)->cache_valid_id) + goto out; /* this cache was invalidated */ + + cache = fat_cache_merge(inode, new); + if (cache == NULL) { + if (MSDOS_I(inode)->nr_caches < fat_max_cache(inode)) { + MSDOS_I(inode)->nr_caches++; + 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) { + MSDOS_I(inode)->nr_caches--; + fat_cache_free(tmp); + goto out_update_lru; + } + cache = tmp; + } else { + struct list_head *p = MSDOS_I(inode)->cache_lru.prev; + cache = list_entry(p, struct fat_cache, cache_list); + } + cache->fcluster = new->fcluster; + cache->dcluster = new->dcluster; + cache->nr_contig = new->nr_contig; + } +out_update_lru: + fat_cache_update_lru(inode, cache); +out: + spin_unlock(&MSDOS_I(inode)->cache_lru_lock); +} + +/* + * Cache invalidation occurs rarely, thus the LRU chain is not updated. It + * fixes itself after a while. + */ +static void __fat_cache_inval_inode(struct inode *inode) +{ + struct msdos_inode_info *i = MSDOS_I(inode); + struct fat_cache *cache; + + while (!list_empty(&i->cache_lru)) { + 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); + } + /* Update. The copy of caches before this id is discarded. */ + i->cache_valid_id++; + if (i->cache_valid_id == FAT_CACHE_VALID) + i->cache_valid_id++; +} + +void fat_cache_inval_inode(struct inode *inode) +{ + spin_lock(&MSDOS_I(inode)->cache_lru_lock); + __fat_cache_inval_inode(inode); + spin_unlock(&MSDOS_I(inode)->cache_lru_lock); +} + +static inline int cache_contiguous(struct fat_cache_id *cid, int dclus) +{ + cid->nr_contig++; + return ((cid->dcluster + cid->nr_contig) == dclus); +} + +static inline void cache_init(struct fat_cache_id *cid, int fclus, int dclus) +{ + cid->id = FAT_CACHE_VALID; + cid->fcluster = fclus; + cid->dcluster = dclus; + cid->nr_contig = 0; +} + +int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const int limit = sb->s_maxbytes >> sbi->cluster_bits; + struct fat_entry fatent; + struct fat_cache_id cid; + int nr; + + BUG_ON(MSDOS_I(inode)->i_start == 0); + + *fclus = 0; + *dclus = MSDOS_I(inode)->i_start; + if (!fat_valid_entry(sbi, *dclus)) { + fat_fs_error_ratelimit(sb, + "%s: invalid start cluster (i_pos %lld, start %08x)", + __func__, MSDOS_I(inode)->i_pos, *dclus); + return -EIO; + } + if (cluster == 0) + return 0; + + if (fat_cache_lookup(inode, cluster, &cid, fclus, dclus) < 0) { + /* + * dummy, always not contiguous + * This is reinitialized by cache_init(), later. + */ + cache_init(&cid, -1, -1); + } + + fatent_init(&fatent); + while (*fclus < cluster) { + /* prevent the infinite loop of cluster chain */ + if (*fclus > limit) { + fat_fs_error_ratelimit(sb, + "%s: detected the cluster chain loop (i_pos %lld)", + __func__, MSDOS_I(inode)->i_pos); + nr = -EIO; + goto out; + } + + nr = fat_ent_read(inode, &fatent, *dclus); + if (nr < 0) + goto out; + else if (nr == FAT_ENT_FREE) { + 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) { + fat_cache_add(inode, &cid); + goto out; + } + (*fclus)++; + *dclus = nr; + if (!cache_contiguous(&cid, *dclus)) + cache_init(&cid, *fclus, *dclus); + } + nr = 0; + fat_cache_add(inode, &cid); +out: + fatent_brelse(&fatent); + return nr; +} + +static int fat_bmap_cluster(struct inode *inode, int cluster) +{ + struct super_block *sb = inode->i_sb; + int ret, fclus, dclus; + + if (MSDOS_I(inode)->i_start == 0) + return 0; + + ret = fat_get_cluster(inode, cluster, &fclus, &dclus); + if (ret < 0) + return ret; + else if (ret == FAT_ENT_EOF) { + fat_fs_error(sb, "%s: request beyond EOF (i_pos %lld)", + __func__, MSDOS_I(inode)->i_pos); + return -EIO; + } + return dclus; +} + +int fat_get_mapped_cluster(struct inode *inode, sector_t sector, + sector_t last_block, + unsigned long *mapped_blocks, sector_t *bmap) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int cluster, offset; + + cluster = sector >> (sbi->cluster_bits - sb->s_blocksize_bits); + offset = sector & (sbi->sec_per_clus - 1); + cluster = fat_bmap_cluster(inode, cluster); + if (cluster < 0) + return cluster; + else if (cluster) { + *bmap = fat_clus_to_blknr(sbi, cluster) + offset; + *mapped_blocks = sbi->sec_per_clus - offset; + if (*mapped_blocks > last_block - sector) + *mapped_blocks = last_block - sector; + } + + return 0; +} + +static int is_exceed_eof(struct inode *inode, sector_t sector, + sector_t *last_block, int create) +{ + struct super_block *sb = inode->i_sb; + const unsigned long blocksize = sb->s_blocksize; + const unsigned char blocksize_bits = sb->s_blocksize_bits; + + *last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits; + if (sector >= *last_block) { + if (!create) + return 1; + + /* + * ->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 1; + } + + return 0; +} + +int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, + unsigned long *mapped_blocks, int create, bool from_bmap) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + sector_t last_block; + + *phys = 0; + *mapped_blocks = 0; + if (!is_fat32(sbi) && (inode->i_ino == MSDOS_ROOT_INO)) { + if (sector < (sbi->dir_entries >> sbi->dir_per_block_bits)) { + *phys = sector + sbi->dir_start; + *mapped_blocks = 1; + } + return 0; + } + + if (!from_bmap) { + if (is_exceed_eof(inode, sector, &last_block, create)) + return 0; + } else { + last_block = inode->i_blocks >> + (inode->i_sb->s_blocksize_bits - 9); + if (sector >= last_block) + return 0; + } + + return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks, + phys); +} diff --git a/fs/fat/dir.c b/fs/fat/dir.c new file mode 100644 index 000000000..00235b8a1 --- /dev/null +++ b/fs/fat/dir.c @@ -0,0 +1,1414 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/fat/dir.c + * + * directory handling functions for fat-based filesystems + * + * Written 1992,1993 by Werner Almesberger + * + * Hidden files 1995 by Albert Cahalan <albert@ccs.neu.edu> <adc@coe.neu.edu> + * + * VFAT extensions by Gordon Chaffee <chaffee@plateau.cs.berkeley.edu> + * Merged with msdos fs by Henrik Storner <storner@osiris.ping.dk> + * Rewritten for constant inumbers. Plugged buffer overrun in readdir(). AV + * Short name translation 1999, 2001 by Wolfram Pienkoss <wp@bszh.de> + */ + +#include <linux/slab.h> +#include <linux/compat.h> +#include <linux/uaccess.h> +#include <linux/iversion.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, + struct msdos_dir_entry *de) +{ + return ((loff_t)bh->b_blocknr << MSDOS_SB(sb)->dir_per_block_bits) + | (de - (struct msdos_dir_entry *)bh->b_data); +} + +static inline void fat_dir_readahead(struct inode *dir, sector_t iblock, + sector_t phys) +{ + struct super_block *sb = dir->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct buffer_head *bh; + int sec; + + /* This is not a first sector of cluster, or sec_per_clus == 1 */ + if ((iblock & (sbi->sec_per_clus - 1)) || sbi->sec_per_clus == 1) + return; + /* root dir of FAT12/FAT16 */ + if (!is_fat32(sbi) && (dir->i_ino == MSDOS_ROOT_INO)) + return; + + bh = sb_find_get_block(sb, phys); + if (bh == NULL || !buffer_uptodate(bh)) { + for (sec = 0; sec < sbi->sec_per_clus; sec++) + sb_breadahead(sb, phys + sec); + } + brelse(bh); +} + +/* Returns the inode number of the directory entry at offset pos. If bh is + non-NULL, it is brelse'd before. Pos is incremented. The buffer header is + returned in bh. + AV. Most often we do it item-by-item. Makes sense to optimize. + AV. OK, there we go: if both bh and de are non-NULL we assume that we just + AV. want the next entry (took one explicit de=NULL in vfat/namei.c). + AV. It's done in fat_get_entry() (inlined), here the slow case lives. + AV. Additionally, when we return -1 (i.e. reached the end of directory) + AV. we make bh NULL. + */ +static int fat__get_entry(struct inode *dir, loff_t *pos, + struct buffer_head **bh, struct msdos_dir_entry **de) +{ + struct super_block *sb = dir->i_sb; + sector_t phys, iblock; + unsigned long mapped_blocks; + int err, offset; + +next: + brelse(*bh); + *bh = NULL; + iblock = *pos >> sb->s_blocksize_bits; + err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0, false); + if (err || !phys) + return -1; /* beyond EOF or error */ + + fat_dir_readahead(dir, iblock, phys); + + *bh = sb_bread(sb, phys); + if (*bh == NULL) { + 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; + } + + offset = *pos & (sb->s_blocksize - 1); + *pos += sizeof(struct msdos_dir_entry); + *de = (struct msdos_dir_entry *)((*bh)->b_data + offset); + + return 0; +} + +static inline int fat_get_entry(struct inode *dir, loff_t *pos, + struct buffer_head **bh, + struct msdos_dir_entry **de) +{ + /* Fast stuff first */ + if (*bh && *de && + (*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; + } + return fat__get_entry(dir, pos, bh, de); +} + +/* + * Convert Unicode 16 to UTF-8, translated Unicode, or ASCII. + * If uni_xlate is enabled and we can't get a 1:1 conversion, use a + * colon as an escape character since it is normally invalid on the vfat + * filesystem. The following four characters are the hexadecimal digits + * of Unicode value. This lets us do a full dump and restore of Unicode + * filenames. We could get into some trouble with long Unicode names, + * but ignore that right now. + * Ahem... Stack smashing in ring 0 isn't fun. Fixed. + */ +static int uni16_to_x8(struct super_block *sb, unsigned char *ascii, + const wchar_t *uni, int len, struct nls_table *nls) +{ + int uni_xlate = MSDOS_SB(sb)->options.unicode_xlate; + const wchar_t *ip; + wchar_t ec; + unsigned char *op; + int charlen; + + ip = uni; + op = ascii; + + while (*ip && ((len - NLS_MAX_CHARSET_SIZE) > 0)) { + ec = *ip++; + charlen = nls->uni2char(ec, op, NLS_MAX_CHARSET_SIZE); + if (charlen > 0) { + op += charlen; + len -= charlen; + } else { + if (uni_xlate == 1) { + *op++ = ':'; + op = hex_byte_pack(op, ec >> 8); + op = hex_byte_pack(op, ec); + len -= 5; + } else { + *op++ = '?'; + len--; + } + } + } + + if (unlikely(*ip)) { + fat_msg(sb, KERN_WARNING, + "filename was truncated while converting."); + } + + *op = 0; + 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 +fat_short2uni(struct nls_table *t, unsigned char *c, int clen, wchar_t *uni) +{ + int charlen; + + charlen = t->char2uni(c, clen, uni); + if (charlen < 0) { + *uni = 0x003f; /* a question mark */ + charlen = 1; + } + return charlen; +} + +static inline int +fat_short2lower_uni(struct nls_table *t, unsigned char *c, + int clen, wchar_t *uni) +{ + int charlen; + wchar_t wc; + + charlen = t->char2uni(c, clen, &wc); + if (charlen < 0) { + *uni = 0x003f; /* a question mark */ + charlen = 1; + } else if (charlen <= 1) { + unsigned char nc = t->charset2lower[*c]; + + if (!nc) + nc = *c; + + charlen = t->char2uni(&nc, 1, uni); + if (charlen < 0) { + *uni = 0x003f; /* a question mark */ + charlen = 1; + } + } else + *uni = wc; + + return charlen; +} + +static inline int +fat_shortname2uni(struct nls_table *nls, unsigned char *buf, int buf_size, + wchar_t *uni_buf, unsigned short opt, int lower) +{ + int len = 0; + + if (opt & VFAT_SFN_DISPLAY_LOWER) + len = fat_short2lower_uni(nls, buf, buf_size, uni_buf); + else if (opt & VFAT_SFN_DISPLAY_WIN95) + len = fat_short2uni(nls, buf, buf_size, uni_buf); + else if (opt & VFAT_SFN_DISPLAY_WINNT) { + if (lower) + len = fat_short2lower_uni(nls, buf, buf_size, uni_buf); + else + len = fat_short2uni(nls, buf, buf_size, uni_buf); + } else + len = fat_short2uni(nls, buf, buf_size, uni_buf); + + 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, }; + +/** + * fat_parse_long - Parse extended directory entry. + * + * This function returns zero on success, negative value on error, or one of + * the following: + * + * %PARSE_INVALID - Directory entry is invalid. + * %PARSE_NOT_LONGNAME - Directory entry does not contain longname. + * %PARSE_EOF - Directory has no more entries. + */ +static int fat_parse_long(struct inode *dir, loff_t *pos, + struct buffer_head **bh, struct msdos_dir_entry **de, + wchar_t **unicode, unsigned char *nr_slots) +{ + struct msdos_dir_slot *ds; + unsigned char id, slot, slots, alias_checksum; + + if (!*unicode) { + *unicode = __getname(); + if (!*unicode) { + brelse(*bh); + return -ENOMEM; + } + } +parse_long: + ds = (struct msdos_dir_slot *)*de; + id = ds->id; + if (!(id & 0x40)) + return PARSE_INVALID; + slots = id & ~0x40; + if (slots > 20 || !slots) /* ceil(256 * 2 / 26) */ + return PARSE_INVALID; + *nr_slots = slots; + alias_checksum = ds->alias_checksum; + + slot = slots; + while (1) { + int offset; + + slot--; + offset = slot * 13; + fat16_towchar(*unicode + offset, ds->name0_4, 5); + fat16_towchar(*unicode + offset + 5, ds->name5_10, 6); + fat16_towchar(*unicode + offset + 11, ds->name11_12, 2); + + if (ds->id & 0x40) + (*unicode)[offset + 13] = 0; + if (fat_get_entry(dir, pos, bh, de) < 0) + return PARSE_EOF; + if (slot == 0) + break; + ds = (struct msdos_dir_slot *)*de; + if (ds->attr != ATTR_EXT) + return PARSE_NOT_LONGNAME; + if ((ds->id & ~0x40) != slot) + goto parse_long; + if (ds->alias_checksum != alias_checksum) + goto parse_long; + } + if ((*de)->name[0] == DELETED_FLAG) + return PARSE_INVALID; + if ((*de)->attr == ATTR_EXT) + goto parse_long; + if (IS_FREE((*de)->name) || ((*de)->attr & ATTR_VOLUME)) + return PARSE_INVALID; + if (fat_checksum((*de)->name) != alias_checksum) + *nr_slots = 0; + + 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)); + /* For an explanation of the special treatment of 0x05 in + * filenames, see msdos_format_name in namei_msdos.c + */ + 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/not found, 0 -> found. + */ +int fat_search_long(struct inode *inode, const unsigned char *name, + int name_len, struct fat_slot_info *sinfo) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct buffer_head *bh = NULL; + struct msdos_dir_entry *de; + unsigned char nr_slots; + wchar_t *unicode = NULL; + unsigned char bufname[FAT_MAX_SHORT_SIZE]; + loff_t cpos = 0; + int err, len; + + err = -ENOENT; + while (1) { + if (fat_get_entry(inode, &cpos, &bh, &de) == -1) + goto end_of_dir; +parse_record: + nr_slots = 0; + if (de->name[0] == DELETED_FLAG) + continue; + if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME)) + continue; + if (de->attr != ATTR_EXT && IS_FREE(de->name)) + continue; + if (de->attr == ATTR_EXT) { + int status = fat_parse_long(inode, &cpos, &bh, &de, + &unicode, &nr_slots); + 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 end_of_dir; + } + + /* 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; + + /* Compare shortname */ + if (fat_name_match(sbi, name, name_len, bufname, len)) + goto found; + + if (nr_slots) { + 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: + nr_slots++; /* include the de */ + sinfo->slot_off = cpos - nr_slots * sizeof(*de); + sinfo->nr_slots = nr_slots; + sinfo->de = de; + sinfo->bh = bh; + sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de); + err = 0; +end_of_dir: + if (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 */ + const char *longname; + int long_len; + const char *shortname; + int short_len; +}; + +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; + unsigned char nr_slots; + wchar_t *unicode = NULL; + unsigned char bufname[FAT_MAX_SHORT_SIZE]; + int isvfat = sbi->options.isvfat; + const char *fill_name = NULL; + int fake_offset = 0; + loff_t cpos; + int short_len = 0, fill_len = 0; + int ret = 0; + + mutex_lock(&sbi->s_lock); + + cpos = ctx->pos; + /* Fake . and .. for the root directory. */ + if (inode->i_ino == MSDOS_ROOT_INO) { + 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)) { + ret = -ENOENT; + goto out; + } + + bh = NULL; +get_new: + if (fat_get_entry(inode, &cpos, &bh, &de) == -1) + goto end_of_dir; +parse_record: + 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 record_end; + if (de->attr != ATTR_EXT && (de->attr & ATTR_VOLUME)) + goto record_end; + if (de->attr != ATTR_EXT && IS_FREE(de->name)) + goto record_end; + } else { + if ((de->attr & ATTR_VOLUME) || IS_FREE(de->name)) + goto record_end; + } + + if (isvfat && de->attr == ATTR_EXT) { + int status = fat_parse_long(inode, &cpos, &bh, &de, + &unicode, &nr_slots); + if (status < 0) { + bh = NULL; + ret = status; + goto end_of_dir; + } else if (status == PARSE_INVALID) + goto record_end; + else if (status == PARSE_NOT_LONGNAME) + goto parse_record; + else if (status == PARSE_EOF) + goto end_of_dir; + + 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); + + 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; + } + } + + short_len = fat_parse_short(sb, de, bufname, sbi->options.dotsOK); + if (short_len == 0) + goto record_end; + + fill_name = bufname; + fill_len = short_len; + +start_filldir: + ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + if (fake_offset && ctx->pos < 2) + ctx->pos = 2; + + 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) { + inum = tmp->i_ino; + 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; + } + +record_end: + fake_offset = 0; + ctx->pos = cpos; + goto get_new; + +end_of_dir: + if (fake_offset && cpos < 2) + ctx->pos = 2; + else + ctx->pos = cpos; +fill_failed: + brelse(bh); + if (unicode) + __putname(unicode); +out: + mutex_unlock(&sbi->s_lock); + + return ret; +} + +static int fat_readdir(struct file *file, struct dir_context *ctx) +{ + return __fat_readdir(file_inode(file), file, ctx, 0, NULL); +} + +#define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type) \ +static bool func(struct dir_context *ctx, const char *name, int name_len, \ + loff_t offset, u64 ino, unsigned int d_type) \ +{ \ + struct fat_ioctl_filldir_callback *buf = \ + container_of(ctx, struct fat_ioctl_filldir_callback, ctx); \ + struct dirent_type __user *d1 = buf->dirent; \ + struct dirent_type __user *d2 = d1 + 1; \ + \ + if (buf->result) \ + return false; \ + buf->result++; \ + \ + if (name != NULL) { \ + /* dirent has only short name */ \ + if (name_len >= sizeof(d1->d_name)) \ + name_len = sizeof(d1->d_name) - 1; \ + \ + if (put_user(0, &d2->d_name[0]) || \ + put_user(0, &d2->d_reclen) || \ + copy_to_user(d1->d_name, name, name_len) || \ + put_user(0, d1->d_name + name_len) || \ + put_user(name_len, &d1->d_reclen)) \ + goto efault; \ + } else { \ + /* dirent has short and long name */ \ + const char *longname = buf->longname; \ + int long_len = buf->long_len; \ + const char *shortname = buf->shortname; \ + int short_len = buf->short_len; \ + \ + if (long_len >= sizeof(d1->d_name)) \ + long_len = sizeof(d1->d_name) - 1; \ + if (short_len >= sizeof(d1->d_name)) \ + short_len = sizeof(d1->d_name) - 1; \ + \ + if (copy_to_user(d2->d_name, longname, long_len) || \ + put_user(0, d2->d_name + long_len) || \ + put_user(long_len, &d2->d_reclen) || \ + put_user(ino, &d2->d_ino) || \ + put_user(offset, &d2->d_off) || \ + copy_to_user(d1->d_name, shortname, short_len) || \ + put_user(0, d1->d_name + short_len) || \ + put_user(short_len, &d1->d_reclen)) \ + goto efault; \ + } \ + return true; \ +efault: \ + buf->result = -EFAULT; \ + return false; \ +} + +FAT_IOCTL_FILLDIR_FUNC(fat_ioctl_filldir, __fat_dirent) + +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 = { + .ctx.actor = filldir, + .dirent = dirent + }; + int ret; + + buf.dirent = dirent; + buf.result = 0; + inode_lock_shared(inode); + buf.ctx.pos = file->f_pos; + ret = -ENOENT; + if (!IS_DEADDIR(inode)) { + ret = __fat_readdir(inode, file, &buf.ctx, + short_only, both ? &buf : NULL); + file->f_pos = buf.ctx.pos; + } + inode_unlock_shared(inode); + if (ret >= 0) + ret = buf.result; + return ret; +} + +static long fat_dir_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct inode *inode = file_inode(filp); + struct __fat_dirent __user *d1 = (struct __fat_dirent __user *)arg; + int short_only, both; + + switch (cmd) { + case VFAT_IOCTL_READDIR_SHORT: + short_only = 1; + both = 0; + break; + case VFAT_IOCTL_READDIR_BOTH: + short_only = 0; + both = 1; + break; + default: + return fat_generic_ioctl(filp, cmd, arg); + } + + /* + * Yes, we don't need this put_user() absolutely. However old + * code didn't return the right value. So, app use this value, + * in order to check whether it is EOF. + */ + if (put_user(0, &d1->d_reclen)) + return -EFAULT; + + return fat_ioctl_readdir(inode, filp, d1, fat_ioctl_filldir, + short_only, both); +} + +#ifdef CONFIG_COMPAT +#define VFAT_IOCTL_READDIR_BOTH32 _IOR('r', 1, struct compat_dirent[2]) +#define VFAT_IOCTL_READDIR_SHORT32 _IOR('r', 2, struct compat_dirent[2]) + +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 = file_inode(filp); + struct compat_dirent __user *d1 = compat_ptr(arg); + int short_only, both; + + switch (cmd) { + case VFAT_IOCTL_READDIR_SHORT32: + short_only = 1; + both = 0; + break; + case VFAT_IOCTL_READDIR_BOTH32: + short_only = 0; + both = 1; + break; + default: + return fat_generic_ioctl(filp, cmd, (unsigned long)arg); + } + + /* + * Yes, we don't need this put_user() absolutely. However old + * code didn't return the right value. So, app use this value, + * in order to check whether it is EOF. + */ + if (put_user(0, &d1->d_reclen)) + return -EFAULT; + + return fat_ioctl_readdir(inode, filp, d1, fat_compat_ioctl_filldir, + short_only, both); +} +#endif /* CONFIG_COMPAT */ + +const struct file_operations fat_dir_operations = { + .llseek = generic_file_llseek, + .read = generic_read_dir, + .iterate_shared = fat_readdir, + .unlocked_ioctl = fat_dir_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = fat_compat_dir_ioctl, +#endif + .fsync = fat_file_fsync, +}; + +static int fat_get_short_entry(struct inode *dir, loff_t *pos, + struct buffer_head **bh, + struct msdos_dir_entry **de) +{ + while (fat_get_entry(dir, pos, bh, de) >= 0) { + /* free entry or long name entry or volume label */ + if (!IS_FREE((*de)->name) && !((*de)->attr & ATTR_VOLUME)) + return 0; + } + return -ENOENT; +} + +/* + * 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 offset = 0; + + *de = NULL; + while (fat_get_short_entry(dir, &offset, bh, de) >= 0) { + if (!strncmp((*de)->name, MSDOS_DOTDOT, MSDOS_NAME)) + return 0; + } + return -ENOENT; +} +EXPORT_SYMBOL_GPL(fat_get_dotdot_entry); + +/* See if directory is empty */ +int fat_dir_empty(struct inode *dir) +{ + struct buffer_head *bh; + struct msdos_dir_entry *de; + loff_t cpos; + int result = 0; + + bh = NULL; + cpos = 0; + while (fat_get_short_entry(dir, &cpos, &bh, &de) >= 0) { + if (strncmp(de->name, MSDOS_DOT , MSDOS_NAME) && + strncmp(de->name, MSDOS_DOTDOT, MSDOS_NAME)) { + result = -ENOTEMPTY; + break; + } + } + brelse(bh); + return result; +} +EXPORT_SYMBOL_GPL(fat_dir_empty); + +/* + * fat_subdirs counts the number of sub-directories of dir. It can be run + * on directories being created. + */ +int fat_subdirs(struct inode *dir) +{ + struct buffer_head *bh; + struct msdos_dir_entry *de; + loff_t cpos; + int count = 0; + + bh = NULL; + cpos = 0; + while (fat_get_short_entry(dir, &cpos, &bh, &de) >= 0) { + if (de->attr & ATTR_DIR) + count++; + } + brelse(bh); + return count; +} + +/* + * Scans a directory for a given file (name points to its formatted name). + * Returns an error code or zero. + */ +int fat_scan(struct inode *dir, const unsigned char *name, + 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 (!strncmp(sinfo->de->name, name, MSDOS_NAME)) { + 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; +} +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; + struct buffer_head *bh; + struct msdos_dir_entry *de, *endp; + int err = 0, orig_slots; + + while (nr_slots) { + bh = NULL; + if (fat_get_entry(dir, &pos, &bh, &de) < 0) { + err = -EIO; + break; + } + + orig_slots = nr_slots; + endp = (struct msdos_dir_entry *)(bh->b_data + sb->s_blocksize); + while (nr_slots && de < endp) { + de->name[0] = DELETED_FLAG; + de++; + nr_slots--; + } + mark_buffer_dirty_inode(bh, dir); + if (IS_DIRSYNC(dir)) + err = sync_dirty_buffer(bh); + brelse(bh); + if (err) + break; + + /* pos is *next* de's position, so this does `- sizeof(de)' */ + pos += ((orig_slots - nr_slots) * sizeof(*de)) - sizeof(*de); + } + + return err; +} + +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; + + /* + * First stage: Remove the shortname. By this, the directory + * entry is removed. + */ + nr_slots = sinfo->nr_slots; + de = sinfo->de; + sinfo->de = NULL; + bh = sinfo->bh; + sinfo->bh = NULL; + while (nr_slots && de >= (struct msdos_dir_entry *)bh->b_data) { + de->name[0] = DELETED_FLAG; + de--; + nr_slots--; + } + mark_buffer_dirty_inode(bh, dir); + if (IS_DIRSYNC(dir)) + err = sync_dirty_buffer(bh); + brelse(bh); + if (err) + return err; + inode_inc_iversion(dir); + + if (nr_slots) { + /* + * Second stage: remove the remaining longname slots. + * (This directory entry is already removed, and so return + * the success) + */ + err = __fat_remove_entries(dir, sinfo->slot_off, nr_slots); + if (err) { + fat_msg(sb, KERN_WARNING, + "Couldn't remove the long name slots"); + } + } + + fat_truncate_time(dir, NULL, S_ATIME|S_MTIME); + if (IS_DIRSYNC(dir)) + (void)fat_sync_inode(dir); + else + mark_inode_dirty(dir); + + return 0; +} +EXPORT_SYMBOL_GPL(fat_remove_entries); + +static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used, + struct buffer_head **bhs, int nr_bhs) +{ + struct super_block *sb = dir->i_sb; + sector_t last_blknr = blknr + MSDOS_SB(sb)->sec_per_clus; + int err, i, n; + + /* Zeroing the unused blocks on this cluster */ + blknr += nr_used; + n = nr_used; + while (blknr < last_blknr) { + bhs[n] = sb_getblk(sb, blknr); + if (!bhs[n]) { + err = -ENOMEM; + goto error; + } + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[n]); + memset(bhs[n]->b_data, 0, sb->s_blocksize); + set_buffer_uptodate(bhs[n]); + unlock_buffer(bhs[n]); + mark_buffer_dirty_inode(bhs[n], dir); + + n++; + blknr++; + if (n == nr_bhs) { + if (IS_DIRSYNC(dir)) { + err = fat_sync_bhs(bhs, n); + if (err) + goto error; + } + for (i = 0; i < n; i++) + brelse(bhs[i]); + n = 0; + } + } + if (IS_DIRSYNC(dir)) { + err = fat_sync_bhs(bhs, n); + if (err) + goto error; + } + for (i = 0; i < n; i++) + brelse(bhs[i]); + + return 0; + +error: + for (i = 0; i < n; i++) + bforget(bhs[i]); + return err; +} + +int fat_alloc_new_dir(struct inode *dir, struct timespec64 *ts) +{ + struct super_block *sb = dir->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct buffer_head *bhs[MAX_BUF_PER_PAGE]; + struct msdos_dir_entry *de; + sector_t blknr; + __le16 date, time; + u8 time_cs; + int err, cluster; + + err = fat_alloc_clusters(dir, &cluster, 1); + if (err) + goto error; + + blknr = fat_clus_to_blknr(sbi, cluster); + bhs[0] = sb_getblk(sb, blknr); + if (!bhs[0]) { + err = -ENOMEM; + goto error_free; + } + + fat_time_unix2fat(sbi, ts, &time, &date, &time_cs); + + de = (struct msdos_dir_entry *)bhs[0]->b_data; + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[0]); + /* filling the new directory slots ("." and ".." entries) */ + memcpy(de[0].name, MSDOS_DOT, MSDOS_NAME); + memcpy(de[1].name, MSDOS_DOTDOT, MSDOS_NAME); + de->attr = de[1].attr = ATTR_DIR; + de[0].lcase = de[1].lcase = 0; + de[0].time = de[1].time = time; + de[0].date = de[1].date = date; + 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; + } + 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]); + unlock_buffer(bhs[0]); + mark_buffer_dirty_inode(bhs[0], dir); + + err = fat_zeroed_cluster(dir, blknr, 1, bhs, MAX_BUF_PER_PAGE); + if (err) + goto error_free; + + return cluster; + +error_free: + fat_free_clusters(dir, cluster); +error: + return err; +} +EXPORT_SYMBOL_GPL(fat_alloc_new_dir); + +static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots, + int *nr_cluster, struct msdos_dir_entry **de, + struct buffer_head **bh, loff_t *i_pos) +{ + struct super_block *sb = dir->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct buffer_head *bhs[MAX_BUF_PER_PAGE]; + sector_t blknr, start_blknr, last_blknr; + unsigned long size, copy; + int err, i, n, offset, cluster[2]; + + /* + * The minimum cluster size is 512bytes, and maximum entry + * size is 32*slots (672bytes). So, iff the cluster size is + * 512bytes, we may need two clusters. + */ + size = nr_slots * sizeof(struct msdos_dir_entry); + *nr_cluster = (size + (sbi->cluster_size - 1)) >> sbi->cluster_bits; + BUG_ON(*nr_cluster > 2); + + err = fat_alloc_clusters(dir, cluster, *nr_cluster); + if (err) + goto error; + + /* + * First stage: Fill the directory entry. NOTE: This cluster + * is not referenced from any inode yet, so updates order is + * not important. + */ + i = n = copy = 0; + do { + start_blknr = blknr = fat_clus_to_blknr(sbi, cluster[i]); + last_blknr = start_blknr + sbi->sec_per_clus; + while (blknr < last_blknr) { + bhs[n] = sb_getblk(sb, blknr); + if (!bhs[n]) { + err = -ENOMEM; + goto error_nomem; + } + + /* fill the directory entry */ + copy = min(size, sb->s_blocksize); + /* Avoid race with userspace read via bdev */ + lock_buffer(bhs[n]); + memcpy(bhs[n]->b_data, slots, copy); + set_buffer_uptodate(bhs[n]); + unlock_buffer(bhs[n]); + mark_buffer_dirty_inode(bhs[n], dir); + slots += copy; + size -= copy; + if (!size) + break; + n++; + blknr++; + } + } while (++i < *nr_cluster); + + memset(bhs[n]->b_data + copy, 0, sb->s_blocksize - copy); + offset = copy - sizeof(struct msdos_dir_entry); + get_bh(bhs[n]); + *bh = bhs[n]; + *de = (struct msdos_dir_entry *)((*bh)->b_data + offset); + *i_pos = fat_make_i_pos(sb, *bh, *de); + + /* Second stage: clear the rest of cluster, and write outs */ + err = fat_zeroed_cluster(dir, start_blknr, ++n, bhs, MAX_BUF_PER_PAGE); + if (err) + goto error_free; + + return cluster[0]; + +error_free: + brelse(*bh); + *bh = NULL; + n = 0; +error_nomem: + for (i = 0; i < n; i++) + bforget(bhs[i]); + fat_free_clusters(dir, cluster[0]); +error: + return err; +} + +int fat_add_entries(struct inode *dir, void *slots, int nr_slots, + struct fat_slot_info *sinfo) +{ + 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; + int err, free_slots, i, nr_bhs; + loff_t pos, i_pos; + + sinfo->nr_slots = nr_slots; + + /* First stage: search free directory entries */ + free_slots = nr_bhs = 0; + bh = prev = NULL; + pos = 0; + err = -ENOSPC; + while (fat_get_entry(dir, &pos, &bh, &de) > -1) { + /* check the maximum size of directory */ + if (pos >= FAT_MAX_DIR_SIZE) + goto error; + + if (IS_FREE(de->name)) { + if (prev != bh) { + get_bh(bh); + bhs[nr_bhs] = prev = bh; + nr_bhs++; + } + free_slots++; + if (free_slots == nr_slots) + goto found; + } else { + for (i = 0; i < nr_bhs; i++) + brelse(bhs[i]); + prev = NULL; + free_slots = nr_bhs = 0; + } + } + if (dir->i_ino == MSDOS_ROOT_INO) { + if (!is_fat32(sbi)) + goto error; + } else if (MSDOS_I(dir)->i_start == 0) { + fat_msg(sb, KERN_ERR, "Corrupted directory (i_pos %lld)", + MSDOS_I(dir)->i_pos); + err = -EIO; + goto error; + } + +found: + err = 0; + pos -= free_slots * sizeof(*de); + nr_slots -= free_slots; + if (free_slots) { + /* + * Second stage: filling the free entries with new entries. + * NOTE: If this slots has shortname, first, we write + * the long name slots, then write the short name. + */ + int size = free_slots * sizeof(*de); + int offset = pos & (sb->s_blocksize - 1); + int long_bhs = nr_bhs - (nr_slots == 0); + + /* Fill the long name slots. */ + 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_inode(bhs[i], dir); + offset = 0; + slots += copy; + size -= copy; + } + if (long_bhs && IS_DIRSYNC(dir)) + err = fat_sync_bhs(bhs, long_bhs); + if (!err && i < nr_bhs) { + /* 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_inode(bhs[i], dir); + if (IS_DIRSYNC(dir)) + err = sync_dirty_buffer(bhs[i]); + } + for (i = 0; i < nr_bhs; i++) + brelse(bhs[i]); + if (err) + goto error_remove; + } + + if (nr_slots) { + int cluster, nr_cluster; + + /* + * Third stage: allocate the cluster for new entries. + * And initialize the cluster with new entries, then + * add the cluster to dir. + */ + cluster = fat_add_new_entries(dir, slots, nr_slots, &nr_cluster, + &de, &bh, &i_pos); + if (cluster < 0) { + err = cluster; + goto error_remove; + } + err = fat_chain_add(dir, cluster, nr_cluster); + if (err) { + fat_free_clusters(dir, cluster); + goto error_remove; + } + if (dir->i_size & (sbi->cluster_size - 1)) { + fat_fs_error(sb, "Odd directory size"); + dir->i_size = (dir->i_size + sbi->cluster_size - 1) + & ~((loff_t)sbi->cluster_size - 1); + } + dir->i_size += nr_cluster << sbi->cluster_bits; + MSDOS_I(dir)->mmu_private += nr_cluster << sbi->cluster_bits; + } + sinfo->slot_off = pos; + sinfo->de = de; + sinfo->bh = bh; + sinfo->i_pos = fat_make_i_pos(sb, sinfo->bh, sinfo->de); + + return 0; + +error: + brelse(bh); + for (i = 0; i < nr_bhs; i++) + brelse(bhs[i]); + return err; + +error_remove: + brelse(bh); + if (free_slots) + __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 000000000..a415c02ed --- /dev/null +++ b/fs/fat/fat.h @@ -0,0 +1,477 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _FAT_H +#define _FAT_H + +#include <linux/buffer_head.h> +#include <linux/nls.h> +#include <linux/hash.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 (12,16 or 32) */ + 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; + const 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 timespec64 i_crtime; /* File creation (birth) time */ + 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; +} + +/* + * Functions that determine the variant of the FAT file system (i.e., + * whether this is FAT12, FAT16 or FAT32. + */ +static inline bool is_fat12(const struct msdos_sb_info *sbi) +{ + return sbi->fat_bits == 12; +} + +static inline bool is_fat16(const struct msdos_sb_info *sbi) +{ + return sbi->fat_bits == 16; +} + +static inline bool is_fat32(const struct msdos_sb_info *sbi) +{ + return sbi->fat_bits == 32; +} + +/* Maximum number of clusters */ +static inline u32 max_fat(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + return is_fat32(sbi) ? MAX_FAT32 : + is_fat16(sbi) ? MAX_FAT16 : MAX_FAT12; +} + +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 (is_fat32(sbi)) + 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_get_mapped_cluster(struct inode *inode, sector_t sector, + sector_t last_block, + unsigned long *mapped_blocks, sector_t *bmap); +extern int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, + unsigned long *mapped_blocks, int create, bool from_bmap); + +/* 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 timespec64 *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; +} + +static inline bool fat_valid_entry(struct msdos_sb_info *sbi, int entry) +{ + return FAT_START_ENT <= entry && entry < sbi->max_cluster; +} + +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); +extern int fat_trim_fs(struct inode *inode, struct fstrim_range *range); + +/* 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 user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr); +extern void fat_truncate_blocks(struct inode *inode, loff_t offset); +extern int fat_getattr(struct user_namespace *mnt_userns, + const struct path *path, struct kstat *stat, + u32 request_mask, unsigned int flags); +extern int fat_file_fsync(struct file *file, loff_t start, loff_t end, + int datasync); + +/* fat/inode.c */ +extern int fat_block_truncate_page(struct inode *inode, loff_t from); +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); +} +extern int fat_add_cluster(struct inode *inode); + +/* 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) + +#define FAT_PRINTK_PREFIX "%sFAT-fs (%s): " +#define fat_msg(sb, level, fmt, args...) \ +do { \ + printk_index_subsys_emit(FAT_PRINTK_PREFIX, level, fmt, ##args);\ + _fat_msg(sb, level, fmt, ##args); \ +} while (0) +__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 timespec64 *ts, + __le16 __time, __le16 __date, u8 time_cs); +extern void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec64 *ts, + __le16 *time, __le16 *date, u8 *time_cs); +extern struct timespec64 fat_truncate_atime(const struct msdos_sb_info *sbi, + const struct timespec64 *ts); +extern struct timespec64 fat_truncate_mtime(const struct msdos_sb_info *sbi, + const struct timespec64 *ts); +extern int fat_truncate_time(struct inode *inode, struct timespec64 *now, + int flags); +extern int fat_update_time(struct inode *inode, struct timespec64 *now, + int flags); +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/fat_test.c b/fs/fat/fat_test.c new file mode 100644 index 000000000..2dab4ca1d --- /dev/null +++ b/fs/fat/fat_test.c @@ -0,0 +1,196 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * KUnit tests for FAT filesystems. + * + * Copyright (C) 2020 Google LLC. + * Author: David Gow <davidgow@google.com> + */ + +#include <kunit/test.h> + +#include "fat.h" + +static void fat_checksum_test(struct kunit *test) +{ + /* With no extension. */ + KUNIT_EXPECT_EQ(test, fat_checksum("VMLINUX "), (u8)44); + /* With 3-letter extension. */ + KUNIT_EXPECT_EQ(test, fat_checksum("README TXT"), (u8)115); + /* With short (1-letter) extension. */ + KUNIT_EXPECT_EQ(test, fat_checksum("ABCDEFGHA "), (u8)98); +} + +struct fat_timestamp_testcase { + const char *name; + struct timespec64 ts; + __le16 time; + __le16 date; + u8 cs; + int time_offset; +}; + +static struct fat_timestamp_testcase time_test_cases[] = { + { + .name = "Earliest possible UTC (1980-01-01 00:00:00)", + .ts = {.tv_sec = 315532800LL, .tv_nsec = 0L}, + .time = cpu_to_le16(0), + .date = cpu_to_le16(33), + .cs = 0, + .time_offset = 0, + }, + { + .name = "Latest possible UTC (2107-12-31 23:59:58)", + .ts = {.tv_sec = 4354819198LL, .tv_nsec = 0L}, + .time = cpu_to_le16(49021), + .date = cpu_to_le16(65439), + .cs = 0, + .time_offset = 0, + }, + { + .name = "Earliest possible (UTC-11) (== 1979-12-31 13:00:00 UTC)", + .ts = {.tv_sec = 315493200LL, .tv_nsec = 0L}, + .time = cpu_to_le16(0), + .date = cpu_to_le16(33), + .cs = 0, + .time_offset = 11 * 60, + }, + { + .name = "Latest possible (UTC+11) (== 2108-01-01 10:59:58 UTC)", + .ts = {.tv_sec = 4354858798LL, .tv_nsec = 0L}, + .time = cpu_to_le16(49021), + .date = cpu_to_le16(65439), + .cs = 0, + .time_offset = -11 * 60, + }, + { + .name = "Leap Day / Year (1996-02-29 00:00:00)", + .ts = {.tv_sec = 825552000LL, .tv_nsec = 0L}, + .time = cpu_to_le16(0), + .date = cpu_to_le16(8285), + .cs = 0, + .time_offset = 0, + }, + { + .name = "Year 2000 is leap year (2000-02-29 00:00:00)", + .ts = {.tv_sec = 951782400LL, .tv_nsec = 0L}, + .time = cpu_to_le16(0), + .date = cpu_to_le16(10333), + .cs = 0, + .time_offset = 0, + }, + { + .name = "Year 2100 not leap year (2100-03-01 00:00:00)", + .ts = {.tv_sec = 4107542400LL, .tv_nsec = 0L}, + .time = cpu_to_le16(0), + .date = cpu_to_le16(61537), + .cs = 0, + .time_offset = 0, + }, + { + .name = "Leap year + timezone UTC+1 (== 2004-02-29 00:30:00 UTC)", + .ts = {.tv_sec = 1078014600LL, .tv_nsec = 0L}, + .time = cpu_to_le16(48064), + .date = cpu_to_le16(12380), + .cs = 0, + .time_offset = -60, + }, + { + .name = "Leap year + timezone UTC-1 (== 2004-02-29 23:30:00 UTC)", + .ts = {.tv_sec = 1078097400LL, .tv_nsec = 0L}, + .time = cpu_to_le16(960), + .date = cpu_to_le16(12385), + .cs = 0, + .time_offset = 60, + }, + { + .name = "VFAT odd-second resolution (1999-12-31 23:59:59)", + .ts = {.tv_sec = 946684799LL, .tv_nsec = 0L}, + .time = cpu_to_le16(49021), + .date = cpu_to_le16(10143), + .cs = 100, + .time_offset = 0, + }, + { + .name = "VFAT 10ms resolution (1980-01-01 00:00:00:0010)", + .ts = {.tv_sec = 315532800LL, .tv_nsec = 10000000L}, + .time = cpu_to_le16(0), + .date = cpu_to_le16(33), + .cs = 1, + .time_offset = 0, + }, +}; + +static void time_testcase_desc(struct fat_timestamp_testcase *t, + char *desc) +{ + strscpy(desc, t->name, KUNIT_PARAM_DESC_SIZE); +} + +KUNIT_ARRAY_PARAM(fat_time, time_test_cases, time_testcase_desc); + +static void fat_time_fat2unix_test(struct kunit *test) +{ + static struct msdos_sb_info fake_sb; + struct timespec64 ts; + struct fat_timestamp_testcase *testcase = + (struct fat_timestamp_testcase *)test->param_value; + + fake_sb.options.tz_set = 1; + fake_sb.options.time_offset = testcase->time_offset; + + fat_time_fat2unix(&fake_sb, &ts, + testcase->time, + testcase->date, + testcase->cs); + KUNIT_EXPECT_EQ_MSG(test, + testcase->ts.tv_sec, + ts.tv_sec, + "Timestamp mismatch (seconds)\n"); + KUNIT_EXPECT_EQ_MSG(test, + testcase->ts.tv_nsec, + ts.tv_nsec, + "Timestamp mismatch (nanoseconds)\n"); +} + +static void fat_time_unix2fat_test(struct kunit *test) +{ + static struct msdos_sb_info fake_sb; + __le16 date, time; + u8 cs; + struct fat_timestamp_testcase *testcase = + (struct fat_timestamp_testcase *)test->param_value; + + fake_sb.options.tz_set = 1; + fake_sb.options.time_offset = testcase->time_offset; + + fat_time_unix2fat(&fake_sb, &testcase->ts, + &time, &date, &cs); + KUNIT_EXPECT_EQ_MSG(test, + le16_to_cpu(testcase->time), + le16_to_cpu(time), + "Time mismatch\n"); + KUNIT_EXPECT_EQ_MSG(test, + le16_to_cpu(testcase->date), + le16_to_cpu(date), + "Date mismatch\n"); + KUNIT_EXPECT_EQ_MSG(test, + testcase->cs, + cs, + "Centisecond mismatch\n"); +} + +static struct kunit_case fat_test_cases[] = { + KUNIT_CASE(fat_checksum_test), + KUNIT_CASE_PARAM(fat_time_fat2unix_test, fat_time_gen_params), + KUNIT_CASE_PARAM(fat_time_unix2fat_test, fat_time_gen_params), + {}, +}; + +static struct kunit_suite fat_test_suite = { + .name = "fat_test", + .test_cases = fat_test_cases, +}; + +kunit_test_suites(&fat_test_suite); + +MODULE_LICENSE("GPL v2"); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c new file mode 100644 index 000000000..1db348f8f --- /dev/null +++ b/fs/fat/fatent.c @@ -0,0 +1,848 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2004, OGAWA Hirofumi + */ + +#include <linux/blkdev.h> +#include <linux/sched/signal.h> +#include <linux/backing-dev-defs.h> +#include "fat.h" + +struct fatent_operations { + void (*ent_blocknr)(struct super_block *, int, int *, sector_t *); + void (*ent_set_ptr)(struct fat_entry *, int); + int (*ent_bread)(struct super_block *, struct fat_entry *, + int, sector_t); + int (*ent_get)(struct fat_entry *); + void (*ent_put)(struct fat_entry *, int); + int (*ent_next)(struct fat_entry *); +}; + +static DEFINE_SPINLOCK(fat12_entry_lock); + +static void fat12_ent_blocknr(struct super_block *sb, int entry, + int *offset, sector_t *blocknr) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int bytes = entry + (entry >> 1); + WARN_ON(!fat_valid_entry(sbi, entry)); + *offset = bytes & (sb->s_blocksize - 1); + *blocknr = sbi->fat_start + (bytes >> sb->s_blocksize_bits); +} + +static void fat_ent_blocknr(struct super_block *sb, int entry, + int *offset, sector_t *blocknr) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int bytes = (entry << sbi->fatent_shift); + WARN_ON(!fat_valid_entry(sbi, entry)); + *offset = bytes & (sb->s_blocksize - 1); + *blocknr = sbi->fat_start + (bytes >> sb->s_blocksize_bits); +} + +static void fat12_ent_set_ptr(struct fat_entry *fatent, int offset) +{ + struct buffer_head **bhs = fatent->bhs; + if (fatent->nr_bhs == 1) { + WARN_ON(offset >= (bhs[0]->b_size - 1)); + fatent->u.ent12_p[0] = bhs[0]->b_data + offset; + fatent->u.ent12_p[1] = bhs[0]->b_data + (offset + 1); + } else { + WARN_ON(offset != (bhs[0]->b_size - 1)); + fatent->u.ent12_p[0] = bhs[0]->b_data + offset; + fatent->u.ent12_p[1] = bhs[1]->b_data; + } +} + +static void fat16_ent_set_ptr(struct fat_entry *fatent, int offset) +{ + WARN_ON(offset & (2 - 1)); + fatent->u.ent16_p = (__le16 *)(fatent->bhs[0]->b_data + offset); +} + +static void fat32_ent_set_ptr(struct fat_entry *fatent, int offset) +{ + WARN_ON(offset & (4 - 1)); + fatent->u.ent32_p = (__le32 *)(fatent->bhs[0]->b_data + offset); +} + +static int fat12_ent_bread(struct super_block *sb, struct fat_entry *fatent, + int offset, sector_t blocknr) +{ + 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; + + if ((offset + 1) < sb->s_blocksize) + fatent->nr_bhs = 1; + else { + /* This entry is block boundary, it needs the next block */ + blocknr++; + bhs[1] = sb_bread(sb, blocknr); + if (!bhs[1]) + goto err_brelse; + fatent->nr_bhs = 2; + } + fat12_ent_set_ptr(fatent, offset); + return 0; + +err_brelse: + brelse(bhs[0]); +err: + fat_msg_ratelimit(sb, KERN_ERR, "FAT read failed (blocknr %llu)", + (llu)blocknr); + return -EIO; +} + +static int fat_ent_bread(struct super_block *sb, struct fat_entry *fatent, + int offset, sector_t blocknr) +{ + const 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]) { + fat_msg_ratelimit(sb, KERN_ERR, "FAT read failed (blocknr %llu)", + (llu)blocknr); + return -EIO; + } + fatent->nr_bhs = 1; + ops->ent_set_ptr(fatent, offset); + return 0; +} + +static int fat12_ent_get(struct fat_entry *fatent) +{ + u8 **ent12_p = fatent->u.ent12_p; + int next; + + spin_lock(&fat12_entry_lock); + if (fatent->entry & 1) + next = (*ent12_p[0] >> 4) | (*ent12_p[1] << 4); + else + next = (*ent12_p[1] << 8) | *ent12_p[0]; + spin_unlock(&fat12_entry_lock); + + next &= 0x0fff; + if (next >= BAD_FAT12) + next = FAT_ENT_EOF; + return next; +} + +static int fat16_ent_get(struct fat_entry *fatent) +{ + int next = le16_to_cpu(*fatent->u.ent16_p); + WARN_ON((unsigned long)fatent->u.ent16_p & (2 - 1)); + if (next >= BAD_FAT16) + next = FAT_ENT_EOF; + return next; +} + +static int fat32_ent_get(struct fat_entry *fatent) +{ + int next = le32_to_cpu(*fatent->u.ent32_p) & 0x0fffffff; + WARN_ON((unsigned long)fatent->u.ent32_p & (4 - 1)); + if (next >= BAD_FAT32) + next = FAT_ENT_EOF; + return next; +} + +static void fat12_ent_put(struct fat_entry *fatent, int new) +{ + u8 **ent12_p = fatent->u.ent12_p; + + if (new == FAT_ENT_EOF) + new = EOF_FAT12; + + spin_lock(&fat12_entry_lock); + if (fatent->entry & 1) { + *ent12_p[0] = (new << 4) | (*ent12_p[0] & 0x0f); + *ent12_p[1] = new >> 4; + } else { + *ent12_p[0] = new & 0xff; + *ent12_p[1] = (*ent12_p[1] & 0xf0) | (new >> 8); + } + spin_unlock(&fat12_entry_lock); + + mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode); + if (fatent->nr_bhs == 2) + mark_buffer_dirty_inode(fatent->bhs[1], fatent->fat_inode); +} + +static void fat16_ent_put(struct fat_entry *fatent, int new) +{ + if (new == FAT_ENT_EOF) + new = EOF_FAT16; + + *fatent->u.ent16_p = cpu_to_le16(new); + mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode); +} + +static void fat32_ent_put(struct fat_entry *fatent, int new) +{ + WARN_ON(new & 0xf0000000); + new |= le32_to_cpu(*fatent->u.ent32_p) & ~0x0fffffff; + *fatent->u.ent32_p = cpu_to_le32(new); + mark_buffer_dirty_inode(fatent->bhs[0], fatent->fat_inode); +} + +static int fat12_ent_next(struct fat_entry *fatent) +{ + u8 **ent12_p = fatent->u.ent12_p; + struct buffer_head **bhs = fatent->bhs; + u8 *nextp = ent12_p[1] + 1 + (fatent->entry & 1); + + 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))); + 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[1] != (u8 *)bhs[1]->b_data); + ent12_p[0] = nextp - 1; + ent12_p[1] = nextp; + brelse(bhs[0]); + bhs[0] = bhs[1]; + fatent->nr_bhs = 1; + return 1; + } + ent12_p[0] = NULL; + ent12_p[1] = NULL; + return 0; +} + +static int fat16_ent_next(struct fat_entry *fatent) +{ + const struct buffer_head *bh = fatent->bhs[0]; + fatent->entry++; + if (fatent->u.ent16_p < (__le16 *)(bh->b_data + (bh->b_size - 2))) { + fatent->u.ent16_p++; + return 1; + } + fatent->u.ent16_p = NULL; + return 0; +} + +static int fat32_ent_next(struct fat_entry *fatent) +{ + const struct buffer_head *bh = fatent->bhs[0]; + fatent->entry++; + if (fatent->u.ent32_p < (__le32 *)(bh->b_data + (bh->b_size - 4))) { + fatent->u.ent32_p++; + return 1; + } + fatent->u.ent32_p = NULL; + return 0; +} + +static const struct fatent_operations fat12_ops = { + .ent_blocknr = fat12_ent_blocknr, + .ent_set_ptr = fat12_ent_set_ptr, + .ent_bread = fat12_ent_bread, + .ent_get = fat12_ent_get, + .ent_put = fat12_ent_put, + .ent_next = fat12_ent_next, +}; + +static const struct fatent_operations fat16_ops = { + .ent_blocknr = fat_ent_blocknr, + .ent_set_ptr = fat16_ent_set_ptr, + .ent_bread = fat_ent_bread, + .ent_get = fat16_ent_get, + .ent_put = fat16_ent_put, + .ent_next = fat16_ent_next, +}; + +static const struct fatent_operations fat32_ops = { + .ent_blocknr = fat_ent_blocknr, + .ent_set_ptr = fat32_ent_set_ptr, + .ent_bread = fat_ent_bread, + .ent_get = fat32_ent_get, + .ent_put = fat32_ent_put, + .ent_next = fat32_ent_next, +}; + +static inline void lock_fat(struct msdos_sb_info *sbi) +{ + mutex_lock(&sbi->fat_lock); +} + +static inline void unlock_fat(struct msdos_sb_info *sbi) +{ + mutex_unlock(&sbi->fat_lock); +} + +void fat_ent_access_init(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + mutex_init(&sbi->fat_lock); + + if (is_fat32(sbi)) { + sbi->fatent_shift = 2; + sbi->fatent_ops = &fat32_ops; + } else if (is_fat16(sbi)) { + sbi->fatent_shift = 1; + sbi->fatent_ops = &fat16_ops; + } else if (is_fat12(sbi)) { + sbi->fatent_shift = -1; + sbi->fatent_ops = &fat12_ops; + } else { + fat_fs_error(sb, "invalid FAT variant, %u bits", sbi->fat_bits); + } +} + +static void mark_fsinfo_dirty(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + if (sb_rdonly(sb) || !is_fat32(sbi)) + 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) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + struct buffer_head **bhs = fatent->bhs; + + /* Is this fatent's blocks including this entry? */ + if (!fatent->nr_bhs || bhs[0]->b_blocknr != blocknr) + return 0; + if (is_fat12(sbi)) { + 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; +} + +int fat_ent_read(struct inode *inode, struct fat_entry *fatent, int entry) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + const struct fatent_operations *ops = sbi->fatent_ops; + int err, offset; + sector_t blocknr; + + if (!fat_valid_entry(sbi, entry)) { + fatent_brelse(fatent); + fat_fs_error(sb, "invalid access to FAT (entry 0x%08x)", entry); + return -EIO; + } + + fatent_set_entry(fatent, entry); + ops->ent_blocknr(sb, entry, &offset, &blocknr); + + if (!fat_ent_update_ptr(sb, fatent, offset, blocknr)) { + fatent_brelse(fatent); + err = ops->ent_bread(sb, fatent, offset, blocknr); + if (err) + return err; + } + return ops->ent_get(fatent); +} + +/* FIXME: We can write the blocks as more big chunk. */ +static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs, + int nr_bhs) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct buffer_head *c_bh; + int err, n, copy; + + err = 0; + for (copy = 1; copy < sbi->fats; copy++) { + sector_t backup_fat = sbi->fat_length * copy; + + for (n = 0; n < nr_bhs; n++) { + c_bh = sb_getblk(sb, backup_fat + bhs[n]->b_blocknr); + if (!c_bh) { + err = -ENOMEM; + goto error; + } + /* Avoid race with userspace read via bdev */ + lock_buffer(c_bh); + memcpy(c_bh->b_data, bhs[n]->b_data, sb->s_blocksize); + set_buffer_uptodate(c_bh); + unlock_buffer(c_bh); + mark_buffer_dirty_inode(c_bh, sbi->fat_inode); + if (sb->s_flags & SB_SYNCHRONOUS) + err = sync_dirty_buffer(c_bh); + brelse(c_bh); + if (err) + goto error; + } + } +error: + return err; +} + +int fat_ent_write(struct inode *inode, struct fat_entry *fatent, + int new, int wait) +{ + struct super_block *sb = inode->i_sb; + const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; + int err; + + ops->ent_put(fatent, new); + if (wait) { + err = fat_sync_bhs(fatent->bhs, fatent->nr_bhs); + if (err) + return err; + } + return fat_mirror_bhs(sb, fatent->bhs, fatent->nr_bhs); +} + +static inline int fat_ent_next(struct msdos_sb_info *sbi, + struct fat_entry *fatent) +{ + if (sbi->fatent_ops->ent_next(fatent)) { + if (fatent->entry < sbi->max_cluster) + return 1; + } + return 0; +} + +static inline int fat_ent_read_block(struct super_block *sb, + struct fat_entry *fatent) +{ + const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; + sector_t blocknr; + int offset; + + fatent_brelse(fatent); + ops->ent_blocknr(sb, fatent->entry, &offset, &blocknr); + return ops->ent_bread(sb, fatent, offset, blocknr); +} + +static void fat_collect_bhs(struct buffer_head **bhs, int *nr_bhs, + struct fat_entry *fatent) +{ + int n, i; + + for (n = 0; n < fatent->nr_bhs; n++) { + for (i = 0; i < *nr_bhs; i++) { + if (fatent->bhs[n] == bhs[i]) + break; + } + if (i == *nr_bhs) { + get_bh(fatent->bhs[n]); + bhs[i] = fatent->bhs[n]; + (*nr_bhs)++; + } + } +} + +int fat_alloc_clusters(struct inode *inode, int *cluster, int nr_cluster) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + struct fat_entry fatent, prev_ent; + struct buffer_head *bhs[MAX_BUF_PER_PAGE]; + int i, count, err, nr_bhs, idx_clus; + + BUG_ON(nr_cluster > (MAX_BUF_PER_PAGE / 2)); /* fixed limit */ + + lock_fat(sbi); + if (sbi->free_clusters != -1 && sbi->free_clus_valid && + sbi->free_clusters < nr_cluster) { + unlock_fat(sbi); + return -ENOSPC; + } + + err = nr_bhs = idx_clus = 0; + count = FAT_START_ENT; + fatent_init(&prev_ent); + fatent_init(&fatent); + fatent_set_entry(&fatent, sbi->prev_free + 1); + while (count < sbi->max_cluster) { + if (fatent.entry >= sbi->max_cluster) + fatent.entry = FAT_START_ENT; + fatent_set_entry(&fatent, fatent.entry); + err = fat_ent_read_block(sb, &fatent); + if (err) + goto out; + + /* Find the free entries in a block */ + do { + if (ops->ent_get(&fatent) == FAT_ENT_FREE) { + int entry = fatent.entry; + + /* make the cluster chain */ + ops->ent_put(&fatent, FAT_ENT_EOF); + if (prev_ent.nr_bhs) + ops->ent_put(&prev_ent, entry); + + fat_collect_bhs(bhs, &nr_bhs, &fatent); + + sbi->prev_free = entry; + if (sbi->free_clusters != -1) + sbi->free_clusters--; + + cluster[idx_clus] = entry; + idx_clus++; + if (idx_clus == nr_cluster) + goto out; + + /* + * fat_collect_bhs() gets ref-count of bhs, + * so we can still use the prev_ent. + */ + prev_ent = fatent; + } + count++; + if (count == sbi->max_cluster) + break; + } while (fat_ent_next(sbi, &fatent)); + } + + /* Couldn't allocate the free entries */ + sbi->free_clusters = 0; + 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)) + err = fat_sync_bhs(bhs, nr_bhs); + if (!err) + err = fat_mirror_bhs(sb, bhs, nr_bhs); + } + for (i = 0; i < nr_bhs; i++) + brelse(bhs[i]); + + if (err && idx_clus) + fat_free_clusters(inode, cluster[0]); + + return err; +} + +int fat_free_clusters(struct inode *inode, int cluster) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + 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); + lock_fat(sbi); + do { + cluster = fat_ent_read(inode, &fatent, cluster); + if (cluster < 0) { + err = cluster; + goto error; + } else if (cluster == FAT_ENT_FREE) { + 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++; + dirty_fsinfo = 1; + } + + if (nr_bhs + fatent.nr_bhs > MAX_BUF_PER_PAGE) { + if (sb->s_flags & SB_SYNCHRONOUS) { + err = fat_sync_bhs(bhs, nr_bhs); + if (err) + goto error; + } + err = fat_mirror_bhs(sb, bhs, nr_bhs); + if (err) + goto error; + for (i = 0; i < nr_bhs; i++) + brelse(bhs[i]); + nr_bhs = 0; + } + fat_collect_bhs(bhs, &nr_bhs, &fatent); + } while (cluster != FAT_ENT_EOF); + + if (sb->s_flags & SB_SYNCHRONOUS) { + err = fat_sync_bhs(bhs, nr_bhs); + if (err) + goto error; + } + err = fat_mirror_bhs(sb, bhs, nr_bhs); +error: + fatent_brelse(&fatent); + for (i = 0; i < nr_bhs; i++) + brelse(bhs[i]); + unlock_fat(sbi); + if (dirty_fsinfo) + mark_fsinfo_dirty(sb); + + return err; +} +EXPORT_SYMBOL_GPL(fat_free_clusters); + +struct fatent_ra { + sector_t cur; + sector_t limit; + + unsigned int ra_blocks; + sector_t ra_advance; + sector_t ra_next; + sector_t ra_limit; +}; + +static void fat_ra_init(struct super_block *sb, struct fatent_ra *ra, + struct fat_entry *fatent, int ent_limit) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + sector_t blocknr, block_end; + int offset; + /* + * This is the sequential read, so ra_pages * 2 (but try to + * align the optimal hardware IO size). + * [BTW, 128kb covers the whole sectors for FAT12 and FAT16] + */ + unsigned long ra_pages = sb->s_bdi->ra_pages; + unsigned int reada_blocks; + + if (fatent->entry >= ent_limit) + return; + + if (ra_pages > sb->s_bdi->io_pages) + ra_pages = rounddown(ra_pages, sb->s_bdi->io_pages); + reada_blocks = ra_pages << (PAGE_SHIFT - sb->s_blocksize_bits + 1); + + /* Initialize the range for sequential read */ + ops->ent_blocknr(sb, fatent->entry, &offset, &blocknr); + ops->ent_blocknr(sb, ent_limit - 1, &offset, &block_end); + ra->cur = 0; + ra->limit = (block_end + 1) - blocknr; + + /* Advancing the window at half size */ + ra->ra_blocks = reada_blocks >> 1; + ra->ra_advance = ra->cur; + ra->ra_next = ra->cur; + ra->ra_limit = ra->cur + min_t(sector_t, reada_blocks, ra->limit); +} + +/* Assuming to be called before reading a new block (increments ->cur). */ +static void fat_ent_reada(struct super_block *sb, struct fatent_ra *ra, + struct fat_entry *fatent) +{ + if (ra->ra_next >= ra->ra_limit) + return; + + if (ra->cur >= ra->ra_advance) { + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + struct blk_plug plug; + sector_t blocknr, diff; + int offset; + + ops->ent_blocknr(sb, fatent->entry, &offset, &blocknr); + + diff = blocknr - ra->cur; + blk_start_plug(&plug); + /* + * FIXME: we would want to directly use the bio with + * pages to reduce the number of segments. + */ + for (; ra->ra_next < ra->ra_limit; ra->ra_next++) + sb_breadahead(sb, ra->ra_next + diff); + blk_finish_plug(&plug); + + /* Advance the readahead window */ + ra->ra_advance += ra->ra_blocks; + ra->ra_limit += min_t(sector_t, + ra->ra_blocks, ra->limit - ra->ra_limit); + } + ra->cur++; +} + +int fat_count_free_clusters(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + struct fat_entry fatent; + struct fatent_ra fatent_ra; + int err = 0, free; + + lock_fat(sbi); + if (sbi->free_clusters != -1 && sbi->free_clus_valid) + goto out; + + free = 0; + fatent_init(&fatent); + fatent_set_entry(&fatent, FAT_START_ENT); + fat_ra_init(sb, &fatent_ra, &fatent, sbi->max_cluster); + while (fatent.entry < sbi->max_cluster) { + /* readahead of fat blocks */ + fat_ent_reada(sb, &fatent_ra, &fatent); + + err = fat_ent_read_block(sb, &fatent); + if (err) + goto out; + + do { + if (ops->ent_get(&fatent) == FAT_ENT_FREE) + free++; + } while (fat_ent_next(sbi, &fatent)); + cond_resched(); + } + sbi->free_clusters = free; + sbi->free_clus_valid = 1; + mark_fsinfo_dirty(sb); + fatent_brelse(&fatent); +out: + unlock_fat(sbi); + return err; +} + +static int fat_trim_clusters(struct super_block *sb, u32 clus, u32 nr_clus) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + return sb_issue_discard(sb, fat_clus_to_blknr(sbi, clus), + nr_clus * sbi->sec_per_clus, GFP_NOFS, 0); +} + +int fat_trim_fs(struct inode *inode, struct fstrim_range *range) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + const struct fatent_operations *ops = sbi->fatent_ops; + struct fat_entry fatent; + struct fatent_ra fatent_ra; + u64 ent_start, ent_end, minlen, trimmed = 0; + u32 free = 0; + int err = 0; + + /* + * FAT data is organized as clusters, trim at the granulary of cluster. + * + * fstrim_range is in byte, convert values to cluster index. + * Treat sectors before data region as all used, not to trim them. + */ + ent_start = max_t(u64, range->start>>sbi->cluster_bits, FAT_START_ENT); + ent_end = ent_start + (range->len >> sbi->cluster_bits) - 1; + minlen = range->minlen >> sbi->cluster_bits; + + if (ent_start >= sbi->max_cluster || range->len < sbi->cluster_size) + return -EINVAL; + if (ent_end >= sbi->max_cluster) + ent_end = sbi->max_cluster - 1; + + fatent_init(&fatent); + lock_fat(sbi); + fatent_set_entry(&fatent, ent_start); + fat_ra_init(sb, &fatent_ra, &fatent, ent_end + 1); + while (fatent.entry <= ent_end) { + /* readahead of fat blocks */ + fat_ent_reada(sb, &fatent_ra, &fatent); + + err = fat_ent_read_block(sb, &fatent); + if (err) + goto error; + do { + if (ops->ent_get(&fatent) == FAT_ENT_FREE) { + free++; + } else if (free) { + if (free >= minlen) { + u32 clus = fatent.entry - free; + + err = fat_trim_clusters(sb, clus, free); + if (err && err != -EOPNOTSUPP) + goto error; + if (!err) + trimmed += free; + err = 0; + } + free = 0; + } + } while (fat_ent_next(sbi, &fatent) && fatent.entry <= ent_end); + + if (fatal_signal_pending(current)) { + err = -ERESTARTSYS; + goto error; + } + + if (need_resched()) { + fatent_brelse(&fatent); + unlock_fat(sbi); + cond_resched(); + lock_fat(sbi); + } + } + /* handle scenario when tail entries are all free */ + if (free && free >= minlen) { + u32 clus = fatent.entry - free; + + err = fat_trim_clusters(sb, clus, free); + if (err && err != -EOPNOTSUPP) + goto error; + if (!err) + trimmed += free; + err = 0; + } + +error: + fatent_brelse(&fatent); + unlock_fat(sbi); + + range->len = trimmed << sbi->cluster_bits; + + return err; +} diff --git a/fs/fat/file.c b/fs/fat/file.c new file mode 100644 index 000000000..8a6b493b5 --- /dev/null +++ b/fs/fat/file.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/fat/file.c + * + * Written 1992,1993 by Werner Almesberger + * + * regular file handling primitives for fat-based filesystems + */ + +#include <linux/capability.h> +#include <linux/module.h> +#include <linux/compat.h> +#include <linux/mount.h> +#include <linux/blkdev.h> +#include <linux/backing-dev.h> +#include <linux/fsnotify.h> +#include <linux/security.h> +#include <linux/falloc.h> +#include "fat.h" + +static long fat_fallocate(struct file *file, int mode, + loff_t offset, loff_t len); + +static int fat_ioctl_get_attributes(struct inode *inode, u32 __user *user_attr) +{ + u32 attr; + + inode_lock_shared(inode); + attr = fat_make_attrs(inode); + inode_unlock_shared(inode); + + 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); + int is_dir = S_ISDIR(inode->i_mode); + u32 attr, oldattr; + struct iattr ia; + int err; + + err = get_user(attr, user_attr); + if (err) + goto out; + + err = mnt_want_write_file(file); + if (err) + goto out; + inode_lock(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_make_attrs(inode); + + /* Equivalent to a chmod() */ + ia.ia_valid = ATTR_MODE | ATTR_CTIME; + ia.ia_ctime = current_time(inode); + 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)); + } + + /* The root directory has no attributes */ + if (inode->i_ino == MSDOS_ROOT_INO && attr != ATTR_DIR) { + err = -EINVAL; + goto out_unlock_inode; + } + + if (sbi->options.sys_immutable && + ((attr | oldattr) & ATTR_SYS) && + !capable(CAP_LINUX_IMMUTABLE)) { + err = -EPERM; + goto out_unlock_inode; + } + + /* + * 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_mnt_user_ns(file), + file->f_path.dentry, &ia); + if (err) + goto out_unlock_inode; + + /* This MUST be done before doing anything irreversible... */ + err = fat_setattr(file_mnt_user_ns(file), file->f_path.dentry, &ia); + if (err) + goto out_unlock_inode; + + 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; + } + + fat_save_attrs(inode, attr); + mark_inode_dirty(inode); +out_unlock_inode: + inode_unlock(inode); + mnt_drop_write_file(file); +out: + return err; +} + +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); +} + +static int fat_ioctl_fitrim(struct inode *inode, unsigned long arg) +{ + struct super_block *sb = inode->i_sb; + struct fstrim_range __user *user_range; + struct fstrim_range range; + int err; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (!bdev_max_discard_sectors(sb->s_bdev)) + return -EOPNOTSUPP; + + user_range = (struct fstrim_range __user *)arg; + if (copy_from_user(&range, user_range, sizeof(range))) + return -EFAULT; + + range.minlen = max_t(unsigned int, range.minlen, + bdev_discard_granularity(sb->s_bdev)); + + err = fat_trim_fs(inode, &range); + if (err < 0) + return err; + + if (copy_to_user(user_range, &range, sizeof(range))) + return -EFAULT; + + return 0; +} + +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; + + 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); + case FITRIM: + return fat_ioctl_fitrim(inode, arg); + default: + return -ENOTTY; /* Inappropriate ioctl for device */ + } +} + +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); + set_current_state(TASK_UNINTERRUPTIBLE); + io_schedule_timeout(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 err; + + err = __generic_file_fsync(filp, start, end, datasync); + if (err) + return err; + + err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); + if (err) + return err; + + return blkdev_issue_flush(inode->i_sb->s_bdev); +} + + +const struct file_operations fat_file_operations = { + .llseek = generic_file_llseek, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .mmap = generic_file_mmap, + .release = fat_file_release, + .unlocked_ioctl = fat_generic_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .fsync = fat_file_fsync, + .splice_read = generic_file_splice_read, + .splice_write = iter_file_splice_write, + .fallocate = fat_fallocate, +}; + +static int fat_cont_expand(struct inode *inode, loff_t size) +{ + struct address_space *mapping = inode->i_mapping; + loff_t start = inode->i_size, count = size - inode->i_size; + int err; + + err = generic_cont_expand_simple(inode, size); + if (err) + goto out; + + fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); + mark_inode_dirty(inode); + if (IS_SYNC(inode)) { + int err2; + + /* + * 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); + } + } +out: + return err; +} + +/* + * Preallocate space for a file. This implements fat's fallocate file + * operation, which gets called from sys_fallocate system call. User + * space requests len bytes at offset. If FALLOC_FL_KEEP_SIZE is set + * we just allocate clusters without zeroing them out. Otherwise we + * allocate and zero out clusters via an expanding truncate. + */ +static long fat_fallocate(struct file *file, int mode, + loff_t offset, loff_t len) +{ + int nr_cluster; /* Number of clusters to be allocated */ + loff_t mm_bytes; /* Number of bytes to be allocated for file */ + loff_t ondisksize; /* block aligned on-disk size in bytes*/ + struct inode *inode = file->f_mapping->host; + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int err = 0; + + /* No support for hole punch or other fallocate flags. */ + if (mode & ~FALLOC_FL_KEEP_SIZE) + return -EOPNOTSUPP; + + /* No support for dir */ + if (!S_ISREG(inode->i_mode)) + return -EOPNOTSUPP; + + inode_lock(inode); + if (mode & FALLOC_FL_KEEP_SIZE) { + ondisksize = inode->i_blocks << 9; + if ((offset + len) <= ondisksize) + goto error; + + /* First compute the number of clusters to be allocated */ + mm_bytes = offset + len - ondisksize; + nr_cluster = (mm_bytes + (sbi->cluster_size - 1)) >> + sbi->cluster_bits; + + /* Start the allocation.We are not zeroing out the clusters */ + while (nr_cluster-- > 0) { + err = fat_add_cluster(inode); + if (err) + goto error; + } + } else { + if ((offset + len) <= i_size_read(inode)) + goto error; + + /* This is just an expanding truncate */ + err = fat_cont_expand(inode, (offset + len)); + } + +error: + inode_unlock(inode); + return err; +} + +/* Free all clusters after the skip'th cluster. */ +static int fat_free(struct inode *inode, int skip) +{ + struct super_block *sb = inode->i_sb; + int err, wait, free_start, i_start, i_logstart; + + if (MSDOS_I(inode)->i_start == 0) + return 0; + + fat_cache_inval_inode(inode); + + wait = IS_DIRSYNC(inode); + i_start = free_start = MSDOS_I(inode)->i_start; + i_logstart = MSDOS_I(inode)->i_logstart; + + /* First, we write the new file size. */ + if (!skip) { + MSDOS_I(inode)->i_start = 0; + MSDOS_I(inode)->i_logstart = 0; + } + MSDOS_I(inode)->i_attrs |= ATTR_ARCH; + fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); + if (wait) { + err = fat_sync_inode(inode); + if (err) { + MSDOS_I(inode)->i_start = i_start; + MSDOS_I(inode)->i_logstart = i_logstart; + return err; + } + } else + mark_inode_dirty(inode); + + /* Write a new EOF, and get the remaining cluster chain for freeing. */ + if (skip) { + struct fat_entry fatent; + int ret, fclus, dclus; + + ret = fat_get_cluster(inode, skip - 1, &fclus, &dclus); + if (ret < 0) + return ret; + else if (ret == FAT_ENT_EOF) + return 0; + + fatent_init(&fatent); + ret = fat_ent_read(inode, &fatent, dclus); + if (ret == FAT_ENT_EOF) { + fatent_brelse(&fatent); + return 0; + } else if (ret == FAT_ENT_FREE) { + fat_fs_error(sb, + "%s: invalid cluster chain (i_pos %lld)", + __func__, MSDOS_I(inode)->i_pos); + ret = -EIO; + } else if (ret > 0) { + err = fat_ent_write(inode, &fatent, FAT_ENT_EOF, wait); + if (err) + ret = err; + } + fatent_brelse(&fatent); + if (ret < 0) + return ret; + + free_start = ret; + } + inode->i_blocks = skip << (MSDOS_SB(sb)->cluster_bits - 9); + + /* Freeing the remained cluster chain */ + return fat_free_clusters(inode, free_start); +} + +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; + int nr_clusters; + + /* + * This protects against truncating a file bigger than it was then + * trying to write into the hole. + */ + if (MSDOS_I(inode)->mmu_private > offset) + MSDOS_I(inode)->mmu_private = offset; + + nr_clusters = (offset + (cluster_size - 1)) >> sbi->cluster_bits; + + fat_free(inode, nr_clusters); + fat_flush_inodes(inode->i_sb, inode, NULL); +} + +int fat_getattr(struct user_namespace *mnt_userns, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) +{ + struct inode *inode = d_inode(path->dentry); + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + + generic_fillattr(mnt_userns, inode, stat); + stat->blksize = sbi->cluster_size; + + if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) { + /* Use i_pos for ino. This is used as fileid of nfs. */ + stat->ino = fat_i_pos_read(sbi, inode); + } + + if (sbi->options.isvfat && request_mask & STATX_BTIME) { + stat->result_mask |= STATX_BTIME; + stat->btime = MSDOS_I(inode)->i_crtime; + } + + 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 user_namespace *mnt_userns, + struct msdos_sb_info *sbi, struct inode *inode) +{ + umode_t allow_utime = sbi->options.allow_utime; + + if (!vfsuid_eq_kuid(i_uid_into_vfsuid(mnt_userns, inode), + current_fsuid())) { + if (vfsgid_in_group_p(i_gid_into_vfsgid(mnt_userns, inode))) + 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 user_namespace *mnt_userns, struct dentry *dentry, + struct iattr *attr) +{ + struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); + struct inode *inode = d_inode(dentry); + 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(mnt_userns, sbi, inode)) + attr->ia_valid &= ~TIMES_SET_FLAGS; + } + + error = setattr_prepare(mnt_userns, dentry, 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(from_vfsuid(mnt_userns, i_user_ns(inode), attr->ia_vfsuid), + sbi->options.fs_uid))) || + ((attr->ia_valid & ATTR_GID) && + (!gid_eq(from_vfsgid(mnt_userns, i_user_ns(inode), attr->ia_vfsgid), + 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) { + error = fat_block_truncate_page(inode, attr->ia_size); + if (error) + goto out; + 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 can't truncate these appropriately, so we'll + * copy them ourselves + */ + if (attr->ia_valid & ATTR_ATIME) + fat_truncate_time(inode, &attr->ia_atime, S_ATIME); + if (attr->ia_valid & ATTR_CTIME) + fat_truncate_time(inode, &attr->ia_ctime, S_CTIME); + if (attr->ia_valid & ATTR_MTIME) + fat_truncate_time(inode, &attr->ia_mtime, S_MTIME); + attr->ia_valid &= ~(ATTR_ATIME|ATTR_CTIME|ATTR_MTIME); + + setattr_copy(mnt_userns, inode, attr); + mark_inode_dirty(inode); +out: + return error; +} +EXPORT_SYMBOL_GPL(fat_setattr); + +const struct inode_operations fat_file_inode_operations = { + .setattr = fat_setattr, + .getattr = fat_getattr, + .update_time = fat_update_time, +}; diff --git a/fs/fat/inode.c b/fs/fat/inode.c new file mode 100644 index 000000000..1cbcc4608 --- /dev/null +++ b/fs/fat/inode.c @@ -0,0 +1,1975 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/fat/inode.c + * + * Written 1992,1993 by Werner Almesberger + * VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner + * Rewritten for the constant inumbers support by Al Viro + * + * Fixes: + * + * Max Cohan: Fixed invalid FSINFO offset when info_sector is 0 + */ + +#include <linux/module.h> +#include <linux/pagemap.h> +#include <linux/mpage.h> +#include <linux/vfs.h> +#include <linux/seq_file.h> +#include <linux/parser.h> +#include <linux/uio.h> +#include <linux/blkdev.h> +#include <linux/backing-dev.h> +#include <asm/unaligned.h> +#include <linux/random.h> +#include <linux/iversion.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 + +/* DOS dates from 1980/1/1 through 2107/12/31 */ +#define FAT_DATE_MIN (0<<9 | 1<<5 | 1) +#define FAT_DATE_MAX (127<<9 | 12<<5 | 31) +#define FAT_TIME_MAX (23<<11 | 59<<5 | 29) + +/* + * 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, +}, +}; + +int fat_add_cluster(struct inode *inode) +{ + int err, cluster; + + err = fat_alloc_clusters(inode, &cluster, 1); + if (err) + return err; + /* FIXME: this cluster should be added after data of this + * cluster is writed */ + err = fat_chain_add(inode, cluster, 1); + if (err) + fat_free_clusters(inode, cluster); + return err; +} + +static inline int __fat_get_block(struct inode *inode, sector_t iblock, + unsigned long *max_blocks, + struct buffer_head *bh_result, int create) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + unsigned long mapped_blocks; + sector_t phys, last_block; + int err, offset; + + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); + if (err) + return err; + if (phys) { + map_bh(bh_result, sb, phys); + *max_blocks = min(mapped_blocks, *max_blocks); + return 0; + } + if (!create) + return 0; + + if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) { + fat_fs_error(sb, "corrupted file size (i_pos %lld, %lld)", + MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); + return -EIO; + } + + last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9); + offset = (unsigned long)iblock & (sbi->sec_per_clus - 1); + /* + * allocate a cluster according to the following. + * 1) no more available blocks + * 2) not part of fallocate region + */ + if (!offset && !(iblock < last_block)) { + /* TODO: multiple cluster allocation would be desirable. */ + err = fat_add_cluster(inode); + if (err) + return err; + } + /* available blocks on this cluster */ + mapped_blocks = sbi->sec_per_clus - offset; + + *max_blocks = min(mapped_blocks, *max_blocks); + MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits; + + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); + if (err) + return err; + if (!phys) { + fat_fs_error(sb, + "invalid FAT chain (i_pos %lld, last_block %llu)", + MSDOS_I(inode)->i_pos, + (unsigned long long)last_block); + return -EIO; + } + + BUG_ON(*max_blocks != mapped_blocks); + set_buffer_new(bh_result); + map_bh(bh_result, sb, phys); + + return 0; +} + +static int fat_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + struct super_block *sb = inode->i_sb; + unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; + int err; + + err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create); + if (err) + return err; + bh_result->b_size = max_blocks << sb->s_blocksize_bits; + return 0; +} + +static int fat_writepage(struct page *page, struct writeback_control *wbc) +{ + return block_write_full_page(page, fat_get_block, wbc); +} + +static int fat_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + return mpage_writepages(mapping, wbc, fat_get_block); +} + +static int fat_read_folio(struct file *file, struct folio *folio) +{ + return mpage_read_folio(folio, fat_get_block); +} + +static void fat_readahead(struct readahead_control *rac) +{ + mpage_readahead(rac, 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, + struct page **pagep, void **fsdata) +{ + int err; + + *pagep = NULL; + err = cont_write_begin(file, mapping, pos, len, + 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, + loff_t pos, unsigned len, unsigned copied, + struct page *pagep, void *fsdata) +{ + struct inode *inode = mapping->host; + int err; + err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + if (err < len) + fat_write_failed(mapping, pos + len); + if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { + fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); + MSDOS_I(inode)->i_attrs |= ATTR_ARCH; + mark_inode_dirty(inode); + } + return err; +} + +static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; + ssize_t ret; + + if (iov_iter_rw(iter) == WRITE) { + /* + * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), + * so we need to update the ->mmu_private to block boundary. + * + * But we must fill the remaining area or hole by nul for + * updating ->mmu_private. + * + * Return 0, and fallback to normal buffered write. + */ + loff_t size = offset + count; + if (MSDOS_I(inode)->mmu_private < size) + return 0; + } + + /* + * FAT need to use the DIO_LOCKING for avoiding the race + * condition of fat_get_block() and ->truncate(). + */ + ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block); + if (ret < 0 && iov_iter_rw(iter) == WRITE) + fat_write_failed(mapping, offset + count); + + return ret; +} + +static int fat_get_block_bmap(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + struct super_block *sb = inode->i_sb; + unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; + int err; + sector_t bmap; + unsigned long mapped_blocks; + + BUG_ON(create != 0); + + err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true); + if (err) + return err; + + if (bmap) { + map_bh(bh_result, sb, bmap); + max_blocks = min(mapped_blocks, max_blocks); + } + + bh_result->b_size = max_blocks << sb->s_blocksize_bits; + + return 0; +} + +static sector_t _fat_bmap(struct address_space *mapping, sector_t block) +{ + sector_t blocknr; + + /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ + down_read(&MSDOS_I(mapping->host)->truncate_lock); + blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap); + up_read(&MSDOS_I(mapping->host)->truncate_lock); + + return blocknr; +} + +/* + * fat_block_truncate_page() zeroes out a mapping from file offset `from' + * up to the end of the block which corresponds to `from'. + * This is required during truncate to physically zeroout the tail end + * of that block so it doesn't yield old data if the file is later grown. + * Also, avoid causing failure from fsx for cases of "data past EOF" + */ +int fat_block_truncate_page(struct inode *inode, loff_t from) +{ + return block_truncate_page(inode->i_mapping, from, fat_get_block); +} + +static const struct address_space_operations fat_aops = { + .dirty_folio = block_dirty_folio, + .invalidate_folio = block_invalidate_folio, + .read_folio = fat_read_folio, + .readahead = fat_readahead, + .writepage = fat_writepage, + .writepages = fat_writepages, + .write_begin = fat_write_begin, + .write_end = fat_write_end, + .direct_IO = fat_direct_IO, + .bmap = _fat_bmap +}; + +/* + * New FAT inode stuff. We do the following: + * a) i_ino is constant and has nothing with on-disk location. + * b) FAT manages its own cache of directory entries. + * c) *This* cache is indexed by on-disk location. + * d) inode has an associated directory entry, all right, but + * it may be unhashed. + * e) currently entries are stored within struct inode. That should + * change. + * f) we deal with races in the following way: + * 1. readdir() and lookup() do FAT-dir-cache lookup. + * 2. rename() unhashes the F-d-c entry and rehashes it in + * a new place. + * 3. unlink() and rmdir() unhash F-d-c entry. + * 4. fat_write_inode() checks whether the thing is unhashed. + * If it is we silently return. If it isn't we do bread(), + * check if the location is still valid and retry if it + * isn't. Otherwise we do changes. + * 5. Spinlock is used to protect hash/unhash/location check/lookup + * 6. fat_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. + */ + +static void fat_hash_init(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int i; + + spin_lock_init(&sbi->inode_hash_lock); + for (i = 0; i < FAT_HASH_SIZE; i++) + INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); +} + +static inline unsigned long fat_hash(loff_t i_pos) +{ + return hash_32(i_pos, FAT_HASH_BITS); +} + +static void dir_hash_init(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int i; + + 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) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + spin_lock(&sbi->inode_hash_lock); + MSDOS_I(inode)->i_pos = 0; + hlist_del_init(&MSDOS_I(inode)->i_fat_hash); + spin_unlock(&sbi->inode_hash_lock); + + 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(i_pos); + struct msdos_inode_info *i; + struct inode *inode = NULL; + + spin_lock(&sbi->inode_hash_lock); + hlist_for_each_entry(i, head, i_fat_hash) { + BUG_ON(i->vfs_inode.i_sb != sb); + if (i->i_pos != i_pos) + continue; + inode = igrab(&i->vfs_inode); + if (inode) + break; + } + spin_unlock(&sbi->inode_hash_lock); + return inode; +} + +static int is_exec(unsigned char *extension) +{ + unsigned char exe_extensions[] = "EXECOMBAT", *walk; + + for (walk = exe_extensions; *walk; walk += 3) + if (!strncmp(extension, walk, 3)) + return 1; + return 0; +} + +static int fat_calc_dir_size(struct inode *inode) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + int ret, fclus, dclus; + + inode->i_size = 0; + if (MSDOS_I(inode)->i_start == 0) + return 0; + + ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus); + if (ret < 0) + return ret; + inode->i_size = (fclus + 1) << sbi->cluster_bits; + + return 0; +} + +static int fat_validate_dir(struct inode *dir) +{ + struct super_block *sb = dir->i_sb; + + if (dir->i_nlink < 2) { + /* Directory should have "."/".." entries at least. */ + fat_fs_error(sb, "corrupted directory (invalid entries)"); + return -EIO; + } + if (MSDOS_I(dir)->i_start == 0 || + MSDOS_I(dir)->i_start == MSDOS_SB(sb)->root_cluster) { + /* Directory should point valid cluster. */ + fat_fs_error(sb, "corrupted directory (invalid i_start)"); + return -EIO; + } + return 0; +} + +/* doesn't deal with root inode */ +int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + int error; + + MSDOS_I(inode)->i_pos = 0; + inode->i_uid = sbi->options.fs_uid; + inode->i_gid = sbi->options.fs_gid; + inode_inc_iversion(inode); + inode->i_generation = get_random_u32(); + + if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { + inode->i_generation &= ~1; + inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO); + inode->i_op = sbi->dir_ops; + inode->i_fop = &fat_dir_operations; + + MSDOS_I(inode)->i_start = 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; + + set_nlink(inode, fat_subdirs(inode)); + + error = fat_validate_dir(inode); + if (error < 0) + return error; + } else { /* not a directory */ + inode->i_generation |= 1; + inode->i_mode = fat_make_mode(sbi, de->attr, + ((sbi->options.showexec && !is_exec(de->name + 8)) + ? S_IRUGO|S_IWUGO : S_IRWXUGO)); + MSDOS_I(inode)->i_start = fat_get_start(sbi, de); + + MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; + inode->i_size = le32_to_cpu(de->size); + inode->i_op = &fat_file_inode_operations; + inode->i_fop = &fat_file_operations; + inode->i_mapping->a_ops = &fat_aops; + MSDOS_I(inode)->mmu_private = inode->i_size; + } + if (de->attr & ATTR_SYS) { + if (sbi->options.sys_immutable) + inode->i_flags |= S_IMMUTABLE; + } + fat_save_attrs(inode, de->attr); + + inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) + & ~((loff_t)sbi->cluster_size - 1)) >> 9; + + fat_time_fat2unix(sbi, &inode->i_mtime, de->time, de->date, 0); + inode->i_ctime = inode->i_mtime; + if (sbi->options.isvfat) { + fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0); + fat_time_fat2unix(sbi, &MSDOS_I(inode)->i_crtime, de->ctime, + de->cdate, de->ctime_cs); + } else + inode->i_atime = fat_truncate_atime(sbi, &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; + inode = new_inode(sb); + if (!inode) { + inode = ERR_PTR(-ENOMEM); + goto out; + } + inode->i_ino = iunique(sb, MSDOS_ROOT_INO); + inode_set_iversion(inode, 1); + err = fat_fill_inode(inode, de); + if (err) { + iput(inode); + inode = ERR_PTR(err); + goto out; + } + fat_attach(inode, i_pos); + insert_inode_hash(inode); +out: + fat_unlock_build_inode(MSDOS_SB(sb)); + return inode; +} + +EXPORT_SYMBOL_GPL(fat_build_inode); + +static int __fat_write_inode(struct inode *inode, int wait); + +static void fat_free_eofblocks(struct inode *inode) +{ + /* Release unwritten fallocated blocks on inode eviction. */ + if ((inode->i_blocks << 9) > + round_up(MSDOS_I(inode)->mmu_private, + MSDOS_SB(inode->i_sb)->cluster_size)) { + int err; + + fat_truncate_blocks(inode, MSDOS_I(inode)->mmu_private); + /* Fallocate results in updating the i_start/iogstart + * for the zero byte file. So, make it return to + * original state during evict and commit it to avoid + * any corruption on the next access to the cluster + * chain for the file. + */ + err = __fat_write_inode(inode, inode_needs_sync(inode)); + if (err) { + fat_msg(inode->i_sb, KERN_WARNING, "Failed to " + "update on disk inode for unused " + "fallocated blocks, inode could be " + "corrupted. Please run fsck"); + } + + } +} + +static void fat_evict_inode(struct inode *inode) +{ + truncate_inode_pages_final(&inode->i_data); + if (!inode->i_nlink) { + inode->i_size = 0; + fat_truncate_blocks(inode, 0); + } else + fat_free_eofblocks(inode); + + invalidate_inode_buffers(inode); + clear_inode(inode); + fat_cache_inval_inode(inode); + fat_detach(inode); +} + +static void fat_set_state(struct super_block *sb, + unsigned int set, unsigned int force) +{ + struct buffer_head *bh; + struct fat_boot_sector *b; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + /* do not change any thing if mounted read only */ + if (sb_rdonly(sb) && !force) + return; + + /* 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 (is_fat32(sbi)) { + 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_reset_iocharset(struct fat_mount_options *opts) +{ + if (opts->iocharset != fat_default_iocharset) { + /* Note: opts->iocharset can be NULL here */ + kfree(opts->iocharset); + opts->iocharset = fat_default_iocharset; + } +} + +static void delayed_free(struct rcu_head *p) +{ + struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); + unload_nls(sbi->nls_disk); + unload_nls(sbi->nls_io); + fat_reset_iocharset(&sbi->options); + kfree(sbi); +} + +static void fat_put_super(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + fat_set_state(sb, 0, 0); + + iput(sbi->fsinfo_inode); + iput(sbi->fat_inode); + + call_rcu(&sbi->rcu, delayed_free); +} + +static struct kmem_cache *fat_inode_cachep; + +static struct inode *fat_alloc_inode(struct super_block *sb) +{ + struct msdos_inode_info *ei; + ei = alloc_inode_sb(sb, fat_inode_cachep, GFP_NOFS); + if (!ei) + return NULL; + + init_rwsem(&ei->truncate_lock); + /* Zeroing to allow iput() even if partial initialized inode. */ + ei->mmu_private = 0; + ei->i_start = 0; + ei->i_logstart = 0; + ei->i_attrs = 0; + ei->i_pos = 0; + ei->i_crtime.tv_sec = 0; + ei->i_crtime.tv_nsec = 0; + + return &ei->vfs_inode; +} + +static void fat_free_inode(struct inode *inode) +{ + kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); +} + +static void init_once(void *foo) +{ + struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; + + spin_lock_init(&ei->cache_lru_lock); + ei->nr_caches = 0; + ei->cache_valid_id = FAT_CACHE_VALID + 1; + INIT_LIST_HEAD(&ei->cache_lru); + INIT_HLIST_NODE(&ei->i_fat_hash); + INIT_HLIST_NODE(&ei->i_dir_hash); + inode_init_once(&ei->vfs_inode); +} + +static int __init fat_init_inodecache(void) +{ + fat_inode_cachep = kmem_cache_create("fat_inode_cache", + sizeof(struct msdos_inode_info), + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_MEM_SPREAD|SLAB_ACCOUNT), + init_once); + if (fat_inode_cachep == NULL) + return -ENOMEM; + return 0; +} + +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) +{ + bool new_rdonly; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + *flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME); + + sync_filesystem(sb); + + /* make sure we update state on remount. */ + new_rdonly = *flags & SB_RDONLY; + if (new_rdonly != sb_rdonly(sb)) { + 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 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 || !sbi->free_clus_valid) { + int err = fat_count_free_clusters(dentry->d_sb); + if (err) + return err; + } + + buf->f_type = dentry->d_sb->s_magic; + buf->f_bsize = sbi->cluster_size; + buf->f_blocks = sbi->max_cluster - FAT_START_ENT; + buf->f_bfree = sbi->free_clusters; + buf->f_bavail = sbi->free_clusters; + buf->f_fsid = u64_to_fsid(id); + 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) +{ + 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; + sector_t blocknr; + int err, offset; + + if (inode->i_ino == MSDOS_ROOT_INO) + return 0; + +retry: + i_pos = fat_i_pos_read(sbi, inode); + if (!i_pos) + return 0; + + fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); + bh = sb_bread(sb, blocknr); + if (!bh) { + 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); + goto retry; + } + + 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_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_time_unix2fat(sbi, &inode->i_atime, &atime, + &raw_entry->adate, NULL); + fat_time_unix2fat(sbi, &MSDOS_I(inode)->i_crtime, &raw_entry->ctime, + &raw_entry->cdate, &raw_entry->ctime_cs); + } + spin_unlock(&sbi->inode_hash_lock); + mark_buffer_dirty(bh); + err = 0; + if (wait) + err = sync_dirty_buffer(bh); + brelse(bh); + 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); +} + +EXPORT_SYMBOL_GPL(fat_sync_inode); + +static int fat_show_options(struct seq_file *m, struct dentry *root); +static const struct super_operations fat_sops = { + .alloc_inode = fat_alloc_inode, + .free_inode = fat_free_inode, + .write_inode = fat_write_inode, + .evict_inode = fat_evict_inode, + .put_super = fat_put_super, + .statfs = fat_statfs, + .remount_fs = fat_remount, + + .show_options = fat_show_options, +}; + +static int fat_show_options(struct seq_file *m, struct dentry *root) +{ + struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb); + struct fat_mount_options *opts = &sbi->options; + int isvfat = opts->isvfat; + + 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) + /* 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); + + switch (opts->shortname) { + case VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95: + seq_puts(m, ",shortname=win95"); + break; + case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT: + seq_puts(m, ",shortname=winnt"); + break; + case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95: + seq_puts(m, ",shortname=mixed"); + break; + case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95: + seq_puts(m, ",shortname=lower"); + break; + default: + seq_puts(m, ",shortname=unknown"); + break; + } + } + if (opts->name_check != 'n') + seq_printf(m, ",check=%c", opts->name_check); + if (opts->usefree) + seq_puts(m, ",usefree"); + if (opts->quiet) + seq_puts(m, ",quiet"); + if (opts->showexec) + seq_puts(m, ",showexec"); + if (opts->sys_immutable) + seq_puts(m, ",sys_immutable"); + if (!isvfat) { + if (opts->dotsOK) + seq_puts(m, ",dotsOK=yes"); + if (opts->nocase) + seq_puts(m, ",nocase"); + } else { + if (opts->utf8) + seq_puts(m, ",utf8"); + if (opts->unicode_xlate) + seq_puts(m, ",uni_xlate"); + if (!opts->numtail) + seq_puts(m, ",nonumtail"); + if (opts->rodir) + seq_puts(m, ",rodir"); + } + 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_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_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 const match_table_t fat_tokens = { + {Opt_check_r, "check=relaxed"}, + {Opt_check_s, "check=strict"}, + {Opt_check_n, "check=normal"}, + {Opt_check_r, "check=r"}, + {Opt_check_s, "check=s"}, + {Opt_check_n, "check=n"}, + {Opt_uid, "uid=%u"}, + {Opt_gid, "gid=%u"}, + {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"}, + {Opt_quiet, "quiet"}, + {Opt_showexec, "showexec"}, + {Opt_debug, "debug"}, + {Opt_immutable, "sys_immutable"}, + {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 const match_table_t msdos_tokens = { + {Opt_nodots, "nodots"}, + {Opt_nodots, "dotsOK=no"}, + {Opt_dots, "dots"}, + {Opt_dots, "dotsOK=yes"}, + {Opt_err, NULL} +}; +static const match_table_t vfat_tokens = { + {Opt_charset, "iocharset=%s"}, + {Opt_shortname_lower, "shortname=lower"}, + {Opt_shortname_win95, "shortname=win95"}, + {Opt_shortname_winnt, "shortname=winnt"}, + {Opt_shortname_mixed, "shortname=mixed"}, + {Opt_utf8_no, "utf8=0"}, /* 0 or no or false */ + {Opt_utf8_no, "utf8=no"}, + {Opt_utf8_no, "utf8=false"}, + {Opt_utf8_yes, "utf8=1"}, /* empty or 1 or yes or true */ + {Opt_utf8_yes, "utf8=yes"}, + {Opt_utf8_yes, "utf8=true"}, + {Opt_utf8_yes, "utf8"}, + {Opt_uni_xl_no, "uni_xlate=0"}, /* 0 or no or false */ + {Opt_uni_xl_no, "uni_xlate=no"}, + {Opt_uni_xl_no, "uni_xlate=false"}, + {Opt_uni_xl_yes, "uni_xlate=1"}, /* empty or 1 or yes or true */ + {Opt_uni_xl_yes, "uni_xlate=yes"}, + {Opt_uni_xl_yes, "uni_xlate=true"}, + {Opt_uni_xl_yes, "uni_xlate"}, + {Opt_nonumtail_no, "nonumtail=0"}, /* 0 or no or false */ + {Opt_nonumtail_no, "nonumtail=no"}, + {Opt_nonumtail_no, "nonumtail=false"}, + {Opt_nonumtail_yes, "nonumtail=1"}, /* empty or 1 or yes or true */ + {Opt_nonumtail_yes, "nonumtail=yes"}, + {Opt_nonumtail_yes, "nonumtail=true"}, + {Opt_nonumtail_yes, "nonumtail"}, + {Opt_rodir, "rodir"}, + {Opt_err, NULL} +}; + +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]; + int option; + char *iocharset; + + opts->isvfat = is_vfat; + + 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; + fat_reset_iocharset(opts); + 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->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; + + opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat; + + if (!options) + goto out; + + while ((p = strsep(&options, ",")) != NULL) { + int token; + if (!*p) + continue; + + token = match_token(p, fat_tokens, args); + if (token == Opt_err) { + if (is_vfat) + token = match_token(p, vfat_tokens, args); + else + token = match_token(p, msdos_tokens, args); + } + switch (token) { + case Opt_check_s: + opts->name_check = 's'; + break; + case Opt_check_r: + opts->name_check = 'r'; + break; + case Opt_check_n: + opts->name_check = 'n'; + break; + case Opt_usefree: + opts->usefree = 1; + break; + case Opt_nocase: + if (!is_vfat) + opts->nocase = 1; + else { + /* for backward compatibility */ + opts->shortname = VFAT_SFN_DISPLAY_WIN95 + | VFAT_SFN_CREATE_WIN95; + } + break; + case Opt_quiet: + opts->quiet = 1; + break; + case Opt_showexec: + opts->showexec = 1; + break; + case Opt_debug: + *debug = 1; + break; + case Opt_immutable: + opts->sys_immutable = 1; + break; + case Opt_uid: + if (match_int(&args[0], &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 -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 -EINVAL; + opts->fs_fmask = opts->fs_dmask = option; + break; + case Opt_dmask: + if (match_octal(&args[0], &option)) + return -EINVAL; + opts->fs_dmask = option; + break; + case Opt_fmask: + if (match_octal(&args[0], &option)) + 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 -EINVAL; + opts->codepage = option; + break; + case Opt_flush: + opts->flush = 1; + break; + case Opt_time_offset: + if (match_int(&args[0], &option)) + return -EINVAL; + /* + * GMT+-12 zones may have DST corrections so at least + * 13 hours difference is needed. Make the limit 24 + * just in case someone invents something unusual. + */ + if (option < -24 * 60 || option > 24 * 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: + opts->dotsOK = 1; + break; + case Opt_nodots: + opts->dotsOK = 0; + break; + + /* vfat specific */ + case Opt_charset: + fat_reset_iocharset(opts); + iocharset = match_strdup(&args[0]); + if (!iocharset) + return -ENOMEM; + opts->iocharset = iocharset; + break; + case Opt_shortname_lower: + opts->shortname = VFAT_SFN_DISPLAY_LOWER + | VFAT_SFN_CREATE_WIN95; + break; + case Opt_shortname_win95: + opts->shortname = VFAT_SFN_DISPLAY_WIN95 + | VFAT_SFN_CREATE_WIN95; + break; + case Opt_shortname_winnt: + opts->shortname = VFAT_SFN_DISPLAY_WINNT + | VFAT_SFN_CREATE_WINNT; + break; + case Opt_shortname_mixed: + opts->shortname = VFAT_SFN_DISPLAY_WINNT + | VFAT_SFN_CREATE_WIN95; + break; + case Opt_utf8_no: /* 0 or no or false */ + opts->utf8 = 0; + break; + case Opt_utf8_yes: /* empty or 1 or yes or true */ + opts->utf8 = 1; + break; + case Opt_uni_xl_no: /* 0 or no or false */ + opts->unicode_xlate = 0; + break; + case Opt_uni_xl_yes: /* empty or 1 or yes or true */ + opts->unicode_xlate = 1; + break; + case Opt_nonumtail_no: /* 0 or no or false */ + opts->numtail = 1; /* negated option */ + break; + 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_obsolete: + fat_msg(sb, KERN_INFO, "\"%s\" option is obsolete, " + "not supported now", p); + break; + /* unknown option */ + default: + if (!silent) { + 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")) { + 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 |= SB_RDONLY; + sb->s_export_op = &fat_export_ops_nostale; + } + + return 0; +} + +static int fat_read_root(struct inode *inode) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + int error; + + MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; + inode->i_uid = sbi->options.fs_uid; + inode->i_gid = sbi->options.fs_gid; + inode_inc_iversion(inode); + inode->i_generation = 0; + inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO); + inode->i_op = sbi->dir_ops; + inode->i_fop = &fat_dir_operations; + if (is_fat32(sbi)) { + MSDOS_I(inode)->i_start = sbi->root_cluster; + error = fat_calc_dir_size(inode); + if (error < 0) + return error; + } else { + MSDOS_I(inode)->i_start = 0; + inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry); + } + inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) + & ~((loff_t)sbi->cluster_size - 1)) >> 9; + MSDOS_I(inode)->i_logstart = 0; + MSDOS_I(inode)->mmu_private = inode->i_size; + + 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; + 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 (!is_fat12(sbi)) { + 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; + } + + if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of FAT sectors"); + 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"; + sector_t bd_sects = bdev_nr_sectors(sb->s_bdev); + struct fat_floppy_defaults *fdefaults = NULL; + int error = -EINVAL; + unsigned i; + + /* 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, int isvfat, + void (*setup)(struct super_block *)) +{ + struct inode *root_inode = NULL, *fat_inode = NULL; + struct inode *fsinfo_inode = NULL; + struct buffer_head *bh; + 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; + long error; + char buf[50]; + struct timespec64 ts; + + /* + * GFP_KERNEL is ok here, because while we do hold the + * superblock 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; + sb->s_fs_info = sbi; + + sb->s_flags |= SB_NODIRATIME; + sb->s_magic = MSDOS_SUPER_MAGIC; + sb->s_op = &fat_sops; + sb->s_export_op = &fat_export_ops; + /* + * fat timestamps are complex and truncated by fat itself, so + * we set 1 here to be fast + */ + sb->s_time_gran = 1; + mutex_init(&sbi->nfs_build_inode_lock); + ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + 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) { + fat_msg(sb, KERN_ERR, "unable to read boot sector"); + goto out_fail; + } + + 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); + + 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) { + 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) { + struct buffer_head *bh_resize; + + if (!sb_set_blocksize(sb, logical_sector_size)) { + fat_msg(sb, KERN_ERR, "unable to set blocksize %u", + logical_sector_size); + goto out_fail; + } + + /* 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; + } + 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 = bpb.fat_fats; + sbi->fat_bits = 0; /* Don't know yet */ + 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; + fat_time_fat2unix(sbi, &ts, 0, cpu_to_le16(FAT_DATE_MIN), 0); + sb->s_time_min = ts.tv_sec; + + fat_time_fat2unix(sbi, &ts, cpu_to_le16(FAT_TIME_MAX), + cpu_to_le16(FAT_DATE_MAX), 0); + sb->s_time_max = ts.tv_sec; + + 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 = bpb.fat32_length; + sbi->root_cluster = bpb.fat32_root_cluster; + + /* MC - if info_sector is 0, don't multiply by 0 */ + 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) { + 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)) { + 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_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 (is_fat32(sbi)) + 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 = bpb.fat_dir_entries; + if (sbi->dir_entries & (sbi->dir_per_block - 1)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of directory entries" + " (%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 = bpb.fat_sectors; + if (total_sectors == 0) + total_sectors = bpb.fat_total_sect; + + total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; + + if (!is_fat32(sbi)) + sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; + + /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ + if (is_fat32(sbi)) + 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 = calc_fat_clusters(sb); + total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); + if (total_clusters > max_fat(sb)) { + if (!silent) + fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", + total_clusters); + goto out_invalid; + } + + sbi->max_cluster = total_clusters + FAT_START_ENT; + /* check the free_clusters, it's not necessarily correct */ + if (sbi->free_clusters != -1 && sbi->free_clusters > total_clusters) + sbi->free_clusters = -1; + /* check the prev_free, it's not necessarily correct */ + sbi->prev_free %= sbi->max_cluster; + if (sbi->prev_free < FAT_START_ENT) + sbi->prev_free = FAT_START_ENT; + + /* set up enough so that it can read an inode */ + fat_hash_init(sb); + dir_hash_init(sb); + fat_ent_access_init(sb); + + /* + * The low byte of the first FAT entry must have the same value as + * the media field of the boot sector. But in real world, too many + * devices are writing wrong values. So, removed that validity check. + * + * The removed check compared the first FAT entry to a value dependent + * on the media field like this: + * == (0x0F00 | media), for FAT12 + * == (0XFF00 | media), for FAT16 + * == (0x0FFFFF | media), for FAT32 + */ + + error = -EINVAL; + sprintf(buf, "cp%d", sbi->options.codepage); + sbi->nls_disk = load_nls(buf); + if (!sbi->nls_disk) { + fat_msg(sb, KERN_ERR, "codepage %s not found", buf); + goto out_fail; + } + + /* FIXME: utf8 is using iocharset for upper/lower conversion */ + if (sbi->options.isvfat) { + sbi->nls_io = load_nls(sbi->options.iocharset); + if (!sbi->nls_io) { + 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; + 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; + inode_set_iversion(root_inode, 1); + error = fat_read_root(root_inode); + if (error < 0) { + iput(root_inode); + goto out_fail; + } + error = -ENOMEM; + insert_inode_hash(root_inode); + fat_attach(root_inode, 0); + sb->s_root = d_make_root(root_inode); + if (!sb->s_root) { + fat_msg(sb, KERN_ERR, "get root inode failed"); + goto out_fail; + } + + if (sbi->options.discard && !bdev_max_discard_sectors(sb->s_bdev)) + 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) + fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); + +out_fail: + iput(fsinfo_inode); + iput(fat_inode); + unload_nls(sbi->nls_io); + unload_nls(sbi->nls_disk); + fat_reset_iocharset(&sbi->options); + sb->s_fs_info = NULL; + kfree(sbi); + return error; +} + +EXPORT_SYMBOL_GPL(fat_fill_super); + +/* + * helper function for fat_flush_inodes. This writes both the inode + * and the file data blocks, waiting for in flight data blocks before + * the start of the call. It does not wait for any io started + * during the call + */ +static int writeback_inode(struct inode *inode) +{ + + int ret; + + /* 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_metadata(inode, 0); + if (!ret) + ret = filemap_fdatawrite(inode->i_mapping); + return ret; +} + +/* + * write data and metadata corresponding to i1 and i2. The io is + * started but we do not wait for any of it to finish. + * + * filemap_flush is used for the block device, so if there is a dirty + * page for a block already in flight, we will not wait and start the + * io over again + */ +int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2) +{ + int ret = 0; + if (!MSDOS_SB(sb)->options.flush) + return 0; + if (i1) + ret = writeback_inode(i1); + if (!ret && i2) + ret = writeback_inode(i2); + if (!ret) + ret = sync_blockdev_nowait(sb->s_bdev); + return ret; +} +EXPORT_SYMBOL_GPL(fat_flush_inodes); + +static int __init init_fat_fs(void) +{ + int err; + + err = fat_cache_init(); + if (err) + return err; + + err = fat_init_inodecache(); + if (err) + goto failed; + + return 0; + +failed: + fat_cache_destroy(); + return err; +} + +static void __exit exit_fat_fs(void) +{ + fat_cache_destroy(); + fat_destroy_inodecache(); +} + +module_init(init_fat_fs) +module_exit(exit_fat_fs) + +MODULE_LICENSE("GPL"); diff --git a/fs/fat/misc.c b/fs/fat/misc.c new file mode 100644 index 000000000..7e5d6ae30 --- /dev/null +++ b/fs/fat/misc.c @@ -0,0 +1,377 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/fat/misc.c + * + * Written 1992,1993 by Werner Almesberger + * 22/11/2000 - Fixed fat_date_unix2dos for dates earlier than 01/01/1980 + * and date_dos2unix for date==0 by Igor Zhbanov(bsg@uniyar.ac.ru) + */ + +#include "fat.h" +#include <linux/iversion.h> + +/* + * 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_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; + + if (report) { + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + fat_msg(sb, KERN_ERR, "error, %pV", &vaf); + va_end(args); + } + + 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_rdonly(sb)) { + sb->s_flags |= SB_RDONLY; + fat_msg(sb, KERN_ERR, "Filesystem has been set read-only"); + } +} +EXPORT_SYMBOL_GPL(__fat_fs_error); + +/** + * _fat_msg() - Print a preformatted FAT message based on a superblock. + * @sb: A pointer to a &struct super_block + * @level: A Kernel printk level constant + * @fmt: The printf-style format string to print. + * + * Everything that is not fat_fs_error() should be fat_msg(). + * + * fat_msg() wraps _fat_msg() for printk indexing. + */ +void _fat_msg(struct super_block *sb, const char *level, const char *fmt, ...) +{ + struct va_format vaf; + va_list args; + + va_start(args, fmt); + vaf.fmt = fmt; + vaf.va = &args; + _printk(FAT_PRINTK_PREFIX "%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 */ +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 (!is_fat32(sbi)) + return 0; + + bh = sb_bread(sb, sbi->fsinfo_sector); + if (bh == NULL) { + 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)) { + 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); + } else { + if (sbi->free_clusters != -1) + fsinfo->free_clusters = cpu_to_le32(sbi->free_clusters); + if (sbi->prev_free != -1) + fsinfo->next_cluster = cpu_to_le32(sbi->prev_free); + mark_buffer_dirty(bh); + } + brelse(bh); + + return 0; +} + +/* + * fat_chain_add() adds a new cluster to the chain of clusters represented + * by inode. + */ +int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int ret, new_fclus, last; + + /* + * We must locate the last cluster of the file to add this new + * one (new_dclus) to the end of the link list (the FAT). + */ + last = new_fclus = 0; + if (MSDOS_I(inode)->i_start) { + int fclus, dclus; + + ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus); + if (ret < 0) + return ret; + new_fclus = fclus + 1; + last = dclus; + } + + /* add new one to the last of the cluster chain */ + if (last) { + struct fat_entry fatent; + + fatent_init(&fatent); + ret = fat_ent_read(inode, &fatent, last); + if (ret >= 0) { + int wait = inode_needs_sync(inode); + ret = fat_ent_write(inode, &fatent, new_dclus, wait); + fatent_brelse(&fatent); + } + 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_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); + if (ret) + return ret; + } else + mark_inode_dirty(inode); + } + if (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); + + return 0; +} + +/* + * 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 long 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, +}; + +static inline int fat_tz_offset(const struct msdos_sb_info *sbi) +{ + return (sbi->options.tz_set ? + -sbi->options.time_offset : + sys_tz.tz_minuteswest) * SECS_PER_MIN; +} + +/* 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 timespec64 *ts, + __le16 __time, __le16 __date, u8 time_cs) +{ + u16 time = le16_to_cpu(__time), date = le16_to_cpu(__date); + time64_t second; + long day, leap_day, month, year; + + year = date >> 9; + month = max(1, (date >> 5) & 0xf); + day = max(1, date & 0x1f) - 1; + + 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 += (time64_t)(year * 365 + leap_day + + days_in_year[month] + day + + DAYS_DELTA) * SECS_PER_DAY; + + second += fat_tz_offset(sbi); + + if (time_cs) { + ts->tv_sec = second + (time_cs / 100); + ts->tv_nsec = (time_cs % 100) * 10000000; + } else { + ts->tv_sec = second; + ts->tv_nsec = 0; + } +} + +/* Export fat_time_fat2unix() for the fat_test KUnit tests. */ +EXPORT_SYMBOL_GPL(fat_time_fat2unix); + +/* Convert linear UNIX date to a FAT time/date pair. */ +void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec64 *ts, + __le16 *time, __le16 *date, u8 *time_cs) +{ + struct tm tm; + time64_to_tm(ts->tv_sec, -fat_tz_offset(sbi), &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); + +static inline struct timespec64 fat_timespec64_trunc_2secs(struct timespec64 ts) +{ + return (struct timespec64){ ts.tv_sec & ~1ULL, 0 }; +} + +/* + * truncate atime to 24 hour granularity (00:00:00 in local timezone) + */ +struct timespec64 fat_truncate_atime(const struct msdos_sb_info *sbi, + const struct timespec64 *ts) +{ + /* to localtime */ + time64_t seconds = ts->tv_sec - fat_tz_offset(sbi); + s32 remainder; + + div_s64_rem(seconds, SECS_PER_DAY, &remainder); + /* to day boundary, and back to unix time */ + seconds = seconds + fat_tz_offset(sbi) - remainder; + + return (struct timespec64){ seconds, 0 }; +} + +/* + * truncate mtime to 2 second granularity + */ +struct timespec64 fat_truncate_mtime(const struct msdos_sb_info *sbi, + const struct timespec64 *ts) +{ + return fat_timespec64_trunc_2secs(*ts); +} + +/* + * truncate the various times with appropriate granularity: + * all times in root node are always 0 + */ +int fat_truncate_time(struct inode *inode, struct timespec64 *now, int flags) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + struct timespec64 ts; + + if (inode->i_ino == MSDOS_ROOT_INO) + return 0; + + if (now == NULL) { + now = &ts; + ts = current_time(inode); + } + + if (flags & S_ATIME) + inode->i_atime = fat_truncate_atime(sbi, now); + /* + * ctime and mtime share the same on-disk field, and should be + * identical in memory. all mtime updates will be applied to ctime, + * but ctime updates are ignored. + */ + if (flags & S_MTIME) + inode->i_mtime = inode->i_ctime = fat_truncate_mtime(sbi, now); + + return 0; +} +EXPORT_SYMBOL_GPL(fat_truncate_time); + +int fat_update_time(struct inode *inode, struct timespec64 *now, int flags) +{ + int dirty_flags = 0; + + if (inode->i_ino == MSDOS_ROOT_INO) + return 0; + + if (flags & (S_ATIME | S_CTIME | S_MTIME)) { + fat_truncate_time(inode, now, flags); + if (inode->i_sb->s_flags & SB_LAZYTIME) + dirty_flags |= I_DIRTY_TIME; + else + dirty_flags |= I_DIRTY_SYNC; + } + + if ((flags & S_VERSION) && inode_maybe_inc_iversion(inode, false)) + dirty_flags |= I_DIRTY_SYNC; + + __mark_inode_dirty(inode, dirty_flags); + return 0; +} +EXPORT_SYMBOL_GPL(fat_update_time); + +int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs) +{ + int i, err = 0; + + for (i = 0; i < nr_bhs; i++) + write_dirty_buffer(bhs[i], 0); + + for (i = 0; i < nr_bhs; i++) { + wait_on_buffer(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 000000000..efba301d6 --- /dev/null +++ b/fs/fat/namei_msdos.c @@ -0,0 +1,689 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * 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/iversion.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(dentry, 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 *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + struct fat_mount_options *options = &MSDOS_SB(dentry->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 timespec64 *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; + + fat_truncate_time(dir, ts, S_CTIME|S_MTIME); + if (IS_DIRSYNC(dir)) + (void)fat_sync_inode(dir); + else + mark_inode_dirty(dir); + + return 0; +} + +/***** Create a file */ +static int msdos_create(struct user_namespace *mnt_userns, 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 timespec64 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(dir); + 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; + } + fat_truncate_time(inode, &ts, S_ATIME|S_CTIME|S_MTIME); + /* 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 = d_inode(dentry); + struct fat_slot_info sinfo; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + 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); + fat_truncate_time(inode, NULL, S_CTIME); + 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 user_namespace *mnt_userns, 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 timespec64 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(dir); + 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); + fat_truncate_time(inode, &ts, S_ATIME|S_CTIME|S_MTIME); + /* 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 = d_inode(dentry); + 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); + fat_truncate_time(inode, NULL, S_CTIME); + 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 timespec64 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 = d_inode(old_dentry); + new_inode = d_inode(new_dentry); + + 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); + + inode_inc_iversion(old_dir); + fat_truncate_time(old_dir, NULL, S_CTIME|S_MTIME); + if (IS_DIRSYNC(old_dir)) + (void)fat_sync_inode(old_dir); + else + mark_inode_dirty(old_dir); + goto out; + } + } + + ts = current_time(old_inode); + 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; + } + inode_inc_iversion(new_dir); + + 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; + inode_inc_iversion(old_dir); + fat_truncate_time(old_dir, &ts, S_CTIME|S_MTIME); + 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); + fat_truncate_time(new_inode, &ts, S_CTIME); + } +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 user_namespace *mnt_userns, + struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry, + unsigned int flags) +{ + struct super_block *sb = old_dir->i_sb; + unsigned char old_msdos_name[MSDOS_NAME], new_msdos_name[MSDOS_NAME]; + int err, is_hid; + + if (flags & ~RENAME_NOREPLACE) + return -EINVAL; + + 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, + .update_time = fat_update_time, +}; + +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 |= SB_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 | FS_ALLOW_IDMAP, +}; +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 000000000..21620054e --- /dev/null +++ b/fs/fat/namei_vfat.c @@ -0,0 +1,1234 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * 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/ctype.h> +#include <linux/slab.h> +#include <linux/namei.h> +#include <linux/kernel.h> +#include <linux/iversion.h> +#include "fat.h" + +static inline unsigned long vfat_d_version(struct dentry *dentry) +{ + return (unsigned long) dentry->d_fsdata; +} + +static inline void vfat_d_version_set(struct dentry *dentry, + unsigned long version) +{ + dentry->d_fsdata = (void *) version; +} + +/* + * 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 (!inode_eq_iversion(d_inode(dentry->d_parent), vfat_d_version(dentry))) + 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 (d_really_is_positive(dentry)) + 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 (d_really_is_positive(dentry)) + 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(dentry, 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(dentry); + 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 *dentry, + unsigned int len, const char *str, const struct qstr *name) +{ + struct nls_table *t = MSDOS_SB(dentry->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 *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 *op; + int i, 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 == ':')) { + u8 uc[2]; + + if (i > len - 5) + return -EINVAL; + + if (hex2bin(uc, ip + 1, 2) < 0) + return -EINVAL; + + *(wchar_t *)op = uc[0] << 8 | uc[1]; + + op += 2; + 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 timespec64 *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, const struct qstr *qname, + int is_dir, int cluster, struct timespec64 *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_array(MSDOS_SLOTS, sizeof(*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 */ + fat_truncate_time(dir, ts, S_CTIME|S_MTIME); + 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, const 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); +} + +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); + /* + * Checking "alias->d_parent == dentry->d_parent" to make sure + * FS is not corrupted (especially double linked dir). + */ + if (alias && alias->d_parent == dentry->d_parent) { + /* + * 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. + */ + 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); + if (!inode) + vfat_d_version_set(dentry, inode_query_iversion(dir)); + return d_splice_alias(inode, dentry); +error: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + return ERR_PTR(err); +} + +static int vfat_create(struct user_namespace *mnt_userns, 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 timespec64 ts; + int err; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + ts = current_time(dir); + err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo); + if (err) + goto out; + inode_inc_iversion(dir); + + inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); + brelse(sinfo.bh); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out; + } + inode_inc_iversion(inode); + + 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 = d_inode(dentry); + 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); + fat_truncate_time(inode, NULL, S_ATIME|S_MTIME); + fat_detach(inode); + vfat_d_version_set(dentry, inode_query_iversion(dir)); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + + return err; +} + +static int vfat_unlink(struct inode *dir, struct dentry *dentry) +{ + struct inode *inode = d_inode(dentry); + 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); + fat_truncate_time(inode, NULL, S_ATIME|S_MTIME); + fat_detach(inode); + vfat_d_version_set(dentry, inode_query_iversion(dir)); +out: + mutex_unlock(&MSDOS_SB(sb)->s_lock); + + return err; +} + +static int vfat_mkdir(struct user_namespace *mnt_userns, 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 timespec64 ts; + int err, cluster; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + + ts = current_time(dir); + 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; + inode_inc_iversion(dir); + 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_inc_iversion(inode); + set_nlink(inode, 2); + + 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_get_dotdot_de(struct inode *inode, struct buffer_head **bh, + struct msdos_dir_entry **de) +{ + if (S_ISDIR(inode->i_mode)) { + if (fat_get_dotdot_entry(inode, bh, de)) + return -EIO; + } + return 0; +} + +static int vfat_sync_ipos(struct inode *dir, struct inode *inode) +{ + if (IS_DIRSYNC(dir)) + return fat_sync_inode(inode); + mark_inode_dirty(inode); + return 0; +} + +static int vfat_update_dotdot_de(struct inode *dir, struct inode *inode, + struct buffer_head *dotdot_bh, + struct msdos_dir_entry *dotdot_de) +{ + fat_set_start(dotdot_de, MSDOS_I(dir)->i_logstart); + mark_buffer_dirty_inode(dotdot_bh, inode); + if (IS_DIRSYNC(dir)) + return sync_dirty_buffer(dotdot_bh); + return 0; +} + +static void vfat_update_dir_metadata(struct inode *dir, struct timespec64 *ts) +{ + inode_inc_iversion(dir); + fat_truncate_time(dir, ts, S_CTIME | S_MTIME); + if (IS_DIRSYNC(dir)) + (void)fat_sync_inode(dir); + else + mark_inode_dirty(dir); +} + +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 = NULL; + struct inode *old_inode, *new_inode; + struct fat_slot_info old_sinfo, sinfo; + struct timespec64 ts; + loff_t new_i_pos; + int err, is_dir, corrupt = 0; + struct super_block *sb = old_dir->i_sb; + + old_sinfo.bh = sinfo.bh = dotdot_bh = NULL; + old_inode = d_inode(old_dentry); + new_inode = d_inode(new_dentry); + mutex_lock(&MSDOS_SB(sb)->s_lock); + err = vfat_find(old_dir, &old_dentry->d_name, &old_sinfo); + if (err) + goto out; + + if (old_dir != new_dir) { + err = vfat_get_dotdot_de(old_inode, &dotdot_bh, &dotdot_de); + if (err) + goto out; + } + + is_dir = S_ISDIR(old_inode->i_mode); + ts = current_time(old_dir); + 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; + } + inode_inc_iversion(new_dir); + + fat_detach(old_inode); + fat_attach(old_inode, new_i_pos); + err = vfat_sync_ipos(new_dir, old_inode); + if (err) + goto error_inode; + + if (dotdot_de) { + err = vfat_update_dotdot_de(new_dir, old_inode, dotdot_bh, + dotdot_de); + 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; + vfat_update_dir_metadata(old_dir, &ts); + + if (new_inode) { + drop_nlink(new_inode); + if (is_dir) + drop_nlink(new_inode); + fat_truncate_time(new_inode, &ts, S_CTIME); + } +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 (dotdot_de) { + corrupt |= vfat_update_dotdot_de(old_dir, old_inode, dotdot_bh, + dotdot_de); + } +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 void vfat_exchange_ipos(struct inode *old_inode, struct inode *new_inode, + loff_t old_i_pos, loff_t new_i_pos) +{ + fat_detach(old_inode); + fat_detach(new_inode); + fat_attach(old_inode, new_i_pos); + fat_attach(new_inode, old_i_pos); +} + +static void vfat_move_nlink(struct inode *src, struct inode *dst) +{ + drop_nlink(src); + inc_nlink(dst); +} + +static int vfat_rename_exchange(struct inode *old_dir, struct dentry *old_dentry, + struct inode *new_dir, struct dentry *new_dentry) +{ + struct buffer_head *old_dotdot_bh = NULL, *new_dotdot_bh = NULL; + struct msdos_dir_entry *old_dotdot_de = NULL, *new_dotdot_de = NULL; + struct inode *old_inode, *new_inode; + struct timespec64 ts = current_time(old_dir); + loff_t old_i_pos, new_i_pos; + int err, corrupt = 0; + struct super_block *sb = old_dir->i_sb; + + old_inode = d_inode(old_dentry); + new_inode = d_inode(new_dentry); + + /* Acquire super block lock for the operation to be atomic */ + mutex_lock(&MSDOS_SB(sb)->s_lock); + + /* if directories are not the same, get ".." info to update */ + if (old_dir != new_dir) { + err = vfat_get_dotdot_de(old_inode, &old_dotdot_bh, + &old_dotdot_de); + if (err) + goto out; + + err = vfat_get_dotdot_de(new_inode, &new_dotdot_bh, + &new_dotdot_de); + if (err) + goto out; + } + + old_i_pos = MSDOS_I(old_inode)->i_pos; + new_i_pos = MSDOS_I(new_inode)->i_pos; + + vfat_exchange_ipos(old_inode, new_inode, old_i_pos, new_i_pos); + + err = vfat_sync_ipos(old_dir, new_inode); + if (err) + goto error_exchange; + err = vfat_sync_ipos(new_dir, old_inode); + if (err) + goto error_exchange; + + /* update ".." directory entry info */ + if (old_dotdot_de) { + err = vfat_update_dotdot_de(new_dir, old_inode, old_dotdot_bh, + old_dotdot_de); + if (err) + goto error_old_dotdot; + } + if (new_dotdot_de) { + err = vfat_update_dotdot_de(old_dir, new_inode, new_dotdot_bh, + new_dotdot_de); + if (err) + goto error_new_dotdot; + } + + /* if cross directory and only one is a directory, adjust nlink */ + if (!old_dotdot_de != !new_dotdot_de) { + if (old_dotdot_de) + vfat_move_nlink(old_dir, new_dir); + else + vfat_move_nlink(new_dir, old_dir); + } + + vfat_update_dir_metadata(old_dir, &ts); + /* if directories are not the same, update new_dir as well */ + if (old_dir != new_dir) + vfat_update_dir_metadata(new_dir, &ts); + +out: + brelse(old_dotdot_bh); + brelse(new_dotdot_bh); + mutex_unlock(&MSDOS_SB(sb)->s_lock); + + return err; + +error_new_dotdot: + if (new_dotdot_de) { + corrupt |= vfat_update_dotdot_de(new_dir, new_inode, + new_dotdot_bh, new_dotdot_de); + } + +error_old_dotdot: + if (old_dotdot_de) { + corrupt |= vfat_update_dotdot_de(old_dir, old_inode, + old_dotdot_bh, old_dotdot_de); + } + +error_exchange: + vfat_exchange_ipos(old_inode, new_inode, new_i_pos, old_i_pos); + corrupt |= vfat_sync_ipos(new_dir, new_inode); + corrupt |= vfat_sync_ipos(old_dir, old_inode); + + if (corrupt < 0) { + fat_fs_error(new_dir->i_sb, + "%s: Filesystem corrupted (i_pos %lld, %lld)", + __func__, old_i_pos, new_i_pos); + } + goto out; +} + +static int vfat_rename2(struct user_namespace *mnt_userns, struct inode *old_dir, + struct dentry *old_dentry, struct inode *new_dir, + struct dentry *new_dentry, unsigned int flags) +{ + if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE)) + return -EINVAL; + + if (flags & RENAME_EXCHANGE) { + return vfat_rename_exchange(old_dir, old_dentry, + new_dir, new_dentry); + } + + /* VFS already handled RENAME_NOREPLACE, handle it as a normal rename */ + return vfat_rename(old_dir, old_dentry, new_dir, new_dentry); +} + +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_rename2, + .setattr = fat_setattr, + .getattr = fat_getattr, + .update_time = fat_update_time, +}; + +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 | FS_ALLOW_IDMAP, +}; +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 000000000..af191371c --- /dev/null +++ b/fs/fat/nfs.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* fs/fat/nfs.c + */ + +#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 d_inode(child_dir)->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(d_inode(child_dir), &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, +}; |