diff options
Diffstat (limited to 'fs/fat')
| -rw-r--r-- | fs/fat/.kunitconfig | 5 | ||||
| -rw-r--r-- | fs/fat/Kconfig | 43 | ||||
| -rw-r--r-- | fs/fat/Makefile | 3 | ||||
| -rw-r--r-- | fs/fat/cache.c | 105 | ||||
| -rw-r--r-- | fs/fat/dir.c | 100 | ||||
| -rw-r--r-- | fs/fat/fat.h | 102 | ||||
| -rw-r--r-- | fs/fat/fat_test.c | 197 | ||||
| -rw-r--r-- | fs/fat/fatent.c | 259 | ||||
| -rw-r--r-- | fs/fat/file.c | 220 | ||||
| -rw-r--r-- | fs/fat/inode.c | 1399 | ||||
| -rw-r--r-- | fs/fat/misc.c | 149 | ||||
| -rw-r--r-- | fs/fat/namei_msdos.c | 123 | ||||
| -rw-r--r-- | fs/fat/namei_vfat.c | 448 | ||||
| -rw-r--r-- | fs/fat/nfs.c | 26 |
14 files changed, 2209 insertions, 970 deletions
diff --git a/fs/fat/.kunitconfig b/fs/fat/.kunitconfig new file mode 100644 index 000000000000..0a6971dbeccb --- /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 index 182f9ffe2b51..25fae1c83725 100644 --- a/fs/fat/Kconfig +++ b/fs/fat/Kconfig @@ -1,6 +1,9 @@ +# SPDX-License-Identifier: GPL-2.0-only config FAT_FS tristate + select BUFFER_HEAD select NLS + select LEGACY_DIRECT_IO 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 @@ -40,7 +43,7 @@ config MSDOS_FS they are compressed; to access compressed MSDOS partitions under Linux, you can either use the DOS emulator DOSEMU, described in the DOSEMU-HOWTO, available from - <http://www.tldp.org/docs.html#howto>, or try dmsdosfs in + <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 @@ -68,7 +71,7 @@ config VFAT_FS The VFAT support enlarges your kernel by about 10 KB and it only works if you said Y to the "DOS FAT fs support" above. Please read - the file <file:Documentation/filesystems/vfat.txt> for details. If + 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 @@ -76,12 +79,12 @@ config VFAT_FS config FAT_DEFAULT_CODEPAGE int "Default codepage for FAT" - depends on MSDOS_FS || VFAT_FS + 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.txt> for more information. + See <file:Documentation/filesystems/vfat.rst> for more information. config FAT_DEFAULT_IOCHARSET string "Default iocharset for FAT" @@ -93,8 +96,36 @@ config FAT_DEFAULT_IOCHARSET that most of your FAT filesystems use, and can be overridden with the "iocharset" mount option for FAT filesystems. Note that "utf8" is not recommended for FAT filesystems. - If unsure, you shouldn't set "utf8" here. - See <file:Documentation/filesystems/vfat.txt> for more information. + 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 index 964b634f6667..2b034112690d 100644 --- a/fs/fat/Makefile +++ b/fs/fat/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 # # Makefile for the Linux fat filesystem support. # @@ -9,3 +10,5 @@ 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 index 91ad9e1c9441..2af424e200b3 100644 --- a/fs/fat/cache.c +++ b/fs/fat/cache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fat/cache.c * @@ -8,9 +9,7 @@ * May 1999. AV. Fixed the bogosity with FAT32 (read "FAT28"). Fscking lusers. */ -#include <linux/fs.h> #include <linux/slab.h> -#include <linux/buffer_head.h> #include "fat.h" /* this must be > 0. */ @@ -48,7 +47,7 @@ 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, + 0, SLAB_RECLAIM_ACCOUNT, init_once); if (fat_cache_cachep == NULL) return -ENOMEM; @@ -226,7 +225,8 @@ static inline void cache_init(struct fat_cache_id *cid, int fclus, int dclus) int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) { struct super_block *sb = inode->i_sb; - const int limit = sb->s_maxbytes >> MSDOS_SB(sb)->cluster_bits; + 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; @@ -235,6 +235,12 @@ int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) *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; @@ -251,9 +257,8 @@ int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) /* 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); + "%s: detected the cluster chain loop (i_pos %lld)", + __func__, MSDOS_I(inode)->i_pos); nr = -EIO; goto out; } @@ -263,9 +268,8 @@ int fat_get_cluster(struct inode *inode, int cluster, int *fclus, int *dclus) 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); + "%s: invalid cluster chain (i_pos %lld)", + __func__, MSDOS_I(inode)->i_pos); nr = -EIO; goto out; } else if (nr == FAT_ENT_EOF) { @@ -303,19 +307,63 @@ static int fat_bmap_cluster(struct inode *inode, int cluster) return dclus; } -int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, - unsigned long *mapped_blocks, int create) +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; - int cluster, offset; *phys = 0; *mapped_blocks = 0; - if ((sbi->fat_bits != 32) && (inode->i_ino == MSDOS_ROOT_INO)) { + 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; @@ -323,31 +371,16 @@ int fat_bmap(struct inode *inode, sector_t sector, sector_t *phys, return 0; } - last_block = (i_size_read(inode) + (blocksize - 1)) >> blocksize_bits; - if (sector >= last_block) { - if (!create) + if (!from_bmap) { + if (is_exceed_eof(inode, sector, &last_block, create)) return 0; - - /* - * ->mmu_private can access on only allocation path. - * (caller must hold ->i_mutex) - */ - last_block = (MSDOS_I(inode)->mmu_private + (blocksize - 1)) - >> blocksize_bits; + } else { + last_block = inode->i_blocks >> + (inode->i_sb->s_blocksize_bits - 9); if (sector >= last_block) return 0; } - 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) { - *phys = 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; + return fat_get_mapped_cluster(inode, sector, last_block, mapped_blocks, + phys); } diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 3963ede84eb0..92b091783966 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/dir.c * @@ -13,13 +14,10 @@ * Short name translation 1999, 2001 by Wolfram Pienkoss <wp@bszh.de> */ -#include <linux/module.h> #include <linux/slab.h> -#include <linux/time.h> -#include <linux/buffer_head.h> #include <linux/compat.h> #include <linux/uaccess.h> -#include <linux/kernel.h> +#include <linux/iversion.h> #include "fat.h" /* @@ -60,7 +58,7 @@ static inline void fat_dir_readahead(struct inode *dir, sector_t iblock, if ((iblock & (sbi->sec_per_clus - 1)) || sbi->sec_per_clus == 1) return; /* root dir of FAT12/FAT16 */ - if ((sbi->fat_bits != 32) && (dir->i_ino == MSDOS_ROOT_INO)) + if (!is_fat32(sbi) && (dir->i_ino == MSDOS_ROOT_INO)) return; bh = sb_find_get_block(sb, phys); @@ -90,12 +88,10 @@ static int fat__get_entry(struct inode *dir, loff_t *pos, int err, offset; next: - if (*bh) - brelse(*bh); - + brelse(*bh); *bh = NULL; iblock = *pos >> sb->s_blocksize_bits; - err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0); + err = fat_bmap(dir, iblock, &phys, &mapped_blocks, 0, false); if (err || !phys) return -1; /* beyond EOF or error */ @@ -273,6 +269,18 @@ enum { PARSE_INVALID = 1, PARSE_NOT_LONGNAME, PARSE_EOF, }; /** * fat_parse_long - Parse extended directory entry. * + * @dir: Pointer to the inode that represents the directory. + * @pos: On input, contains the starting position to read from. + * On output, updated with the new position. + * @bh: Pointer to the buffer head that may be used for reading directory + * entries. May be updated. + * @de: On input, points to the current directory entry. + * On output, points to the next directory entry. + * @unicode: Pointer to a buffer where the parsed Unicode long filename will be + * stored. + * @nr_slots: Pointer to a variable that will store the number of longname + * slots found. + * * This function returns zero on success, negative value on error, or one of * the following: * @@ -295,7 +303,6 @@ static int fat_parse_long(struct inode *dir, loff_t *pos, } } parse_long: - slots = 0; ds = (struct msdos_dir_slot *)*de; id = ds->id; if (!(id & 0x40)) @@ -373,7 +380,9 @@ static int fat_parse_short(struct super_block *sb, } memcpy(work, de->name, sizeof(work)); - /* see namei.c, msdos_format_name */ + /* 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; @@ -614,9 +623,9 @@ parse_record: int status = fat_parse_long(inode, &cpos, &bh, &de, &unicode, &nr_slots); if (status < 0) { - ctx->pos = cpos; + bh = NULL; ret = status; - goto out; + goto end_of_dir; } else if (status == PARSE_INVALID) goto record_end; else if (status == PARSE_NOT_LONGNAME) @@ -658,8 +667,9 @@ parse_record: fill_len = short_len; start_filldir: - if (!fake_offset) - ctx->pos = cpos - (nr_slots + 1) * sizeof(struct msdos_dir_entry); + 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)) @@ -685,14 +695,19 @@ record_end: fake_offset = 0; ctx->pos = cpos; goto get_new; + end_of_dir: - ctx->pos = cpos; + 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; } @@ -702,15 +717,16 @@ static int fat_readdir(struct file *file, struct dir_context *ctx) } #define FAT_IOCTL_FILLDIR_FUNC(func, dirent_type) \ -static int func(void *__buf, const char *name, int name_len, \ +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 = __buf; \ + 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 -EINVAL; \ + return false; \ buf->result++; \ \ if (name != NULL) { \ @@ -718,7 +734,7 @@ static int func(void *__buf, const char *name, int name_len, \ if (name_len >= sizeof(d1->d_name)) \ name_len = sizeof(d1->d_name) - 1; \ \ - if (put_user(0, d2->d_name) || \ + 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) || \ @@ -746,10 +762,10 @@ static int func(void *__buf, const char *name, int name_len, \ put_user(short_len, &d1->d_reclen)) \ goto efault; \ } \ - return 0; \ + return true; \ efault: \ buf->result = -EFAULT; \ - return -EFAULT; \ + return false; \ } FAT_IOCTL_FILLDIR_FUNC(fat_ioctl_filldir, __fat_dirent) @@ -766,7 +782,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file, buf.dirent = dirent; buf.result = 0; - mutex_lock(&inode->i_mutex); + inode_lock_shared(inode); buf.ctx.pos = file->f_pos; ret = -ENOENT; if (!IS_DEADDIR(inode)) { @@ -774,7 +790,7 @@ static int fat_ioctl_readdir(struct inode *inode, struct file *file, short_only, both ? &buf : NULL); file->f_pos = buf.ctx.pos; } - mutex_unlock(&inode->i_mutex); + inode_unlock_shared(inode); if (ret >= 0) ret = buf.result; return ret; @@ -800,8 +816,6 @@ static long fat_dir_ioctl(struct file *filp, unsigned int cmd, return fat_generic_ioctl(filp, cmd, arg); } - if (!access_ok(VERIFY_WRITE, d1, sizeof(struct __fat_dirent[2]))) - return -EFAULT; /* * Yes, we don't need this put_user() absolutely. However old * code didn't return the right value. So, app use this value, @@ -840,8 +854,6 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, return fat_generic_ioctl(filp, cmd, (unsigned long)arg); } - if (!access_ok(VERIFY_WRITE, d1, sizeof(struct compat_dirent[2]))) - return -EFAULT; /* * Yes, we don't need this put_user() absolutely. However old * code didn't return the right value. So, app use this value, @@ -858,7 +870,7 @@ static long fat_compat_dir_ioctl(struct file *filp, unsigned cmd, const struct file_operations fat_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, - .iterate = fat_readdir, + .iterate_shared = fat_readdir, .unlocked_ioctl = fat_dir_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = fat_compat_dir_ioctl, @@ -1053,7 +1065,7 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo) brelse(bh); if (err) return err; - dir->i_version++; + inode_inc_iversion(dir); if (nr_slots) { /* @@ -1068,7 +1080,7 @@ int fat_remove_entries(struct inode *dir, struct fat_slot_info *sinfo) } } - dir->i_mtime = dir->i_atime = CURRENT_TIME_SEC; + fat_truncate_time(dir, NULL, S_ATIME|S_MTIME); if (IS_DIRSYNC(dir)) (void)fat_sync_inode(dir); else @@ -1094,8 +1106,11 @@ static int fat_zeroed_cluster(struct inode *dir, sector_t blknr, int nr_used, 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++; @@ -1127,7 +1142,7 @@ error: return err; } -int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) +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); @@ -1152,6 +1167,8 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) 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); @@ -1174,6 +1191,7 @@ int fat_alloc_new_dir(struct inode *dir, struct timespec *ts) 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); @@ -1191,7 +1209,7 @@ 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 buffer_head **bh) { struct super_block *sb = dir->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); @@ -1231,11 +1249,14 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots, /* 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); - slots += copy; - size -= 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++; @@ -1248,7 +1269,6 @@ static int fat_add_new_entries(struct inode *dir, void *slots, int nr_slots, 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); @@ -1275,9 +1295,9 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, struct super_block *sb = dir->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */ - struct msdos_dir_entry *uninitialized_var(de); + struct msdos_dir_entry *de; int err, free_slots, i, nr_bhs; - loff_t pos, i_pos; + loff_t pos; sinfo->nr_slots = nr_slots; @@ -1308,7 +1328,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, } } if (dir->i_ino == MSDOS_ROOT_INO) { - if (sbi->fat_bits != 32) + if (!is_fat32(sbi)) goto error; } else if (MSDOS_I(dir)->i_start == 0) { fat_msg(sb, KERN_ERR, "Corrupted directory (i_pos %lld)", @@ -1365,7 +1385,7 @@ found: * add the cluster to dir. */ cluster = fat_add_new_entries(dir, slots, nr_slots, &nr_cluster, - &de, &bh, &i_pos); + &de, &bh); if (cluster < 0) { err = cluster; goto error_remove; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 4241e6f39e86..d3e426de5f01 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -1,14 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _FAT_H #define _FAT_H #include <linux/buffer_head.h> -#include <linux/string.h> #include <linux/nls.h> -#include <linux/fs.h> #include <linux/hash.h> -#include <linux/mutex.h> #include <linux/ratelimit.h> #include <linux/msdos_fs.h> +#include <linux/fs_context.h> +#include <linux/fs_parser.h> /* * vfat shortname flags @@ -52,7 +52,9 @@ struct fat_mount_options { 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 */ + discard:1, /* Issue discard requests on deletions */ + dos1xfloppy:1, /* Assume default BPB for DOS 1.x floppies */ + debug:1; /* Not currently used */ }; #define FAT_HASH_BITS 8 @@ -65,7 +67,7 @@ struct msdos_sb_info { unsigned short sec_per_clus; /* sectors/cluster */ unsigned short cluster_bits; /* log2(cluster_size) */ unsigned int cluster_size; /* cluster size */ - unsigned char fats, fat_bits; /* number of FATs, FAT bits (12 or 16) */ + unsigned 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; @@ -89,7 +91,7 @@ struct msdos_sb_info { unsigned int vol_id; /*volume ID*/ int fatent_shift; - struct fatent_operations *fatent_ops; + const struct fatent_operations *fatent_ops; struct inode *fat_inode; struct inode *fsinfo_inode; @@ -102,6 +104,7 @@ struct msdos_sb_info { 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 */ @@ -126,6 +129,7 @@ struct msdos_inode_info { 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; }; @@ -142,6 +146,34 @@ 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); @@ -257,7 +289,7 @@ static inline int fat_get_start(const struct msdos_sb_info *sbi, const struct msdos_dir_entry *de) { int cluster = le16_to_cpu(de->start); - if (sbi->fat_bits == 32) + if (is_fat32(sbi)) cluster |= (le16_to_cpu(de->starthi) << 16); return cluster; } @@ -286,8 +318,11 @@ static inline void fatwchar_to16(__u8 *dst, const wchar_t *src, size_t len) 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); + unsigned long *mapped_blocks, int create, bool from_bmap); /* fat/dir.c */ extern const struct file_operations fat_dir_operations; @@ -301,7 +336,7 @@ extern int fat_scan_logstart(struct inode *dir, int i_logstart, struct fat_slot_info *sinfo); extern int fat_get_dotdot_entry(struct inode *dir, struct buffer_head **bh, struct msdos_dir_entry **de); -extern int fat_alloc_new_dir(struct inode *dir, struct timespec *ts); +extern int fat_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); @@ -345,6 +380,11 @@ static inline void fatent_brelse(struct fat_entry *fatent) 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); @@ -354,36 +394,50 @@ 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 dentry *dentry, struct iattr *attr); +extern int fat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr); extern void fat_truncate_blocks(struct inode *inode, loff_t offset); -extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, - struct kstat *stat); +extern int fat_getattr(struct mnt_idmap *idmap, + 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_super(struct super_block *sb, struct fs_context *fc, + 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); + +extern const struct fs_parameter_spec fat_param_spec[]; +int fat_init_fs_context(struct fs_context *fc, bool is_vfat); +void fat_free_fc(struct fs_context *fc); + +int fat_parse_param(struct fs_context *fc, struct fs_parameter *param, + bool is_vfat); +int fat_reconfigure(struct fs_context *fc); + 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 @@ -392,8 +446,15 @@ void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...); __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, ...); +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)) \ @@ -401,10 +462,17 @@ void fat_msg(struct super_block *sb, const char *level, const char *fmt, ...); } while (0) extern int fat_clusters_flush(struct super_block *sb); extern int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster); -extern void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts, +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 timespec *ts, +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, int flags); extern int fat_sync_bhs(struct buffer_head **bhs, int nr_bhs); int fat_cache_init(void); diff --git a/fs/fat/fat_test.c b/fs/fat/fat_test.c new file mode 100644 index 000000000000..1f0062659067 --- /dev/null +++ b/fs/fat/fat_test.c @@ -0,0 +1,197 @@ +// 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_DESCRIPTION("KUnit tests for FAT filesystems"); +MODULE_LICENSE("GPL v2"); diff --git a/fs/fat/fatent.c b/fs/fat/fatent.c index 260705c58062..a7061c2ad8e4 100644 --- a/fs/fat/fatent.c +++ b/fs/fat/fatent.c @@ -1,12 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2004, OGAWA Hirofumi - * Released under GPL v2. */ -#include <linux/module.h> -#include <linux/fs.h> -#include <linux/msdos_fs.h> #include <linux/blkdev.h> +#include <linux/sched/signal.h> +#include <linux/backing-dev-defs.h> #include "fat.h" struct fatent_operations { @@ -26,7 +25,7 @@ static void fat12_ent_blocknr(struct super_block *sb, int entry, { struct msdos_sb_info *sbi = MSDOS_SB(sb); int bytes = entry + (entry >> 1); - WARN_ON(entry < FAT_START_ENT || sbi->max_cluster <= entry); + WARN_ON(!fat_valid_entry(sbi, entry)); *offset = bytes & (sb->s_blocksize - 1); *blocknr = sbi->fat_start + (bytes >> sb->s_blocksize_bits); } @@ -36,7 +35,7 @@ static void fat_ent_blocknr(struct super_block *sb, int entry, { struct msdos_sb_info *sbi = MSDOS_SB(sb); int bytes = (entry << sbi->fatent_shift); - WARN_ON(entry < FAT_START_ENT || sbi->max_cluster <= entry); + WARN_ON(!fat_valid_entry(sbi, entry)); *offset = bytes & (sb->s_blocksize - 1); *blocknr = sbi->fat_start + (bytes >> sb->s_blocksize_bits); } @@ -95,21 +94,22 @@ static int fat12_ent_bread(struct super_block *sb, struct fat_entry *fatent, err_brelse: brelse(bhs[0]); err: - fat_msg(sb, KERN_ERR, "FAT read failed (blocknr %llu)", (llu)blocknr); + 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) { - struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; + 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(sb, KERN_ERR, "FAT read failed (blocknr %llu)", - (llu)blocknr); + fat_msg_ratelimit(sb, KERN_ERR, "FAT read failed (blocknr %llu)", + (llu)blocknr); return -EIO; } fatent->nr_bhs = 1; @@ -249,7 +249,7 @@ static int fat32_ent_next(struct fat_entry *fatent) return 0; } -static struct fatent_operations fat12_ops = { +static const struct fatent_operations fat12_ops = { .ent_blocknr = fat12_ent_blocknr, .ent_set_ptr = fat12_ent_set_ptr, .ent_bread = fat12_ent_bread, @@ -258,7 +258,7 @@ static struct fatent_operations fat12_ops = { .ent_next = fat12_ent_next, }; -static struct fatent_operations fat16_ops = { +static const struct fatent_operations fat16_ops = { .ent_blocknr = fat_ent_blocknr, .ent_set_ptr = fat16_ent_set_ptr, .ent_bread = fat_ent_bread, @@ -267,7 +267,7 @@ static struct fatent_operations fat16_ops = { .ent_next = fat16_ent_next, }; -static struct fatent_operations fat32_ops = { +static const struct fatent_operations fat32_ops = { .ent_blocknr = fat_ent_blocknr, .ent_set_ptr = fat32_ent_set_ptr, .ent_bread = fat_ent_bread, @@ -292,19 +292,17 @@ void fat_ent_access_init(struct super_block *sb) mutex_init(&sbi->fat_lock); - switch (sbi->fat_bits) { - case 32: + if (is_fat32(sbi)) { sbi->fatent_shift = 2; sbi->fatent_ops = &fat32_ops; - break; - case 16: + } else if (is_fat16(sbi)) { sbi->fatent_shift = 1; sbi->fatent_ops = &fat16_ops; - break; - case 12: + } else if (is_fat12(sbi)) { sbi->fatent_shift = -1; sbi->fatent_ops = &fat12_ops; - break; + } else { + fat_fs_error(sb, "invalid FAT variant, %u bits", sbi->fat_bits); } } @@ -312,7 +310,7 @@ static void mark_fsinfo_dirty(struct super_block *sb) { struct msdos_sb_info *sbi = MSDOS_SB(sb); - if (sb->s_flags & MS_RDONLY || sbi->fat_bits != 32) + if (sb_rdonly(sb) || !is_fat32(sbi)) return; __mark_inode_dirty(sbi->fsinfo_inode, I_DIRTY_SYNC); @@ -323,13 +321,13 @@ static inline int fat_ent_update_ptr(struct super_block *sb, int offset, sector_t blocknr) { struct msdos_sb_info *sbi = MSDOS_SB(sb); - struct fatent_operations *ops = sbi->fatent_ops; + 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 (sbi->fat_bits == 12) { + if (is_fat12(sbi)) { if ((offset + 1) < sb->s_blocksize) { /* This entry is on bhs[0]. */ if (fatent->nr_bhs == 2) { @@ -352,13 +350,13 @@ 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); - struct fatent_operations *ops = sbi->fatent_ops; + const struct fatent_operations *ops = sbi->fatent_ops; int err, offset; sector_t blocknr; - if (entry < FAT_START_ENT || sbi->max_cluster <= entry) { + if (!fat_valid_entry(sbi, entry)) { fatent_brelse(fatent); - fat_fs_error(sb, "invalid access to FAT (entry 0x%08x)", entry); + fat_fs_error_ratelimit(sb, "invalid access to FAT (entry 0x%08x)", entry); return -EIO; } @@ -392,10 +390,13 @@ static int fat_mirror_bhs(struct super_block *sb, struct buffer_head **bhs, 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 & MS_SYNCHRONOUS) + if (sb->s_flags & SB_SYNCHRONOUS) err = sync_dirty_buffer(c_bh); brelse(c_bh); if (err) @@ -410,7 +411,7 @@ int fat_ent_write(struct inode *inode, struct fat_entry *fatent, int new, int wait) { struct super_block *sb = inode->i_sb; - struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; + const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; int err; ops->ent_put(fatent, new); @@ -435,7 +436,7 @@ static inline int fat_ent_next(struct msdos_sb_info *sbi, static inline int fat_ent_read_block(struct super_block *sb, struct fat_entry *fatent) { - struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; + const struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; sector_t blocknr; int offset; @@ -466,7 +467,7 @@ 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); - struct fatent_operations *ops = sbi->fatent_ops; + 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; @@ -554,7 +555,7 @@ int fat_free_clusters(struct inode *inode, int cluster) { struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); - struct fatent_operations *ops = sbi->fatent_ops; + 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; @@ -600,7 +601,7 @@ int fat_free_clusters(struct inode *inode, int cluster) } if (nr_bhs + fatent.nr_bhs > MAX_BUF_PER_PAGE) { - if (sb->s_flags & MS_SYNCHRONOUS) { + if (sb->s_flags & SB_SYNCHRONOUS) { err = fat_sync_bhs(bhs, nr_bhs); if (err) goto error; @@ -615,7 +616,7 @@ int fat_free_clusters(struct inode *inode, int cluster) fat_collect_bhs(bhs, &nr_bhs, &fatent); } while (cluster != FAT_ENT_EOF); - if (sb->s_flags & MS_SYNCHRONOUS) { + if (sb->s_flags & SB_SYNCHRONOUS) { err = fat_sync_bhs(bhs, nr_bhs); if (err) goto error; @@ -633,48 +634,104 @@ error: } EXPORT_SYMBOL_GPL(fat_free_clusters); -/* 128kb is the whole sectors for FAT12 and FAT16 */ -#define FAT_READA_SIZE (128 * 1024) +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_ent_reada(struct super_block *sb, struct fat_entry *fatent, - unsigned long reada_blocks) +static void fat_ra_init(struct super_block *sb, struct fatent_ra *ra, + struct fat_entry *fatent, int ent_limit) { - struct fatent_operations *ops = MSDOS_SB(sb)->fatent_ops; - sector_t blocknr; - int i, offset; + 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); +} - for (i = 0; i < reada_blocks; i++) - sb_breadahead(sb, blocknr + i); +/* 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); - struct fatent_operations *ops = sbi->fatent_ops; + const struct fatent_operations *ops = sbi->fatent_ops; struct fat_entry fatent; - unsigned long reada_blocks, reada_mask, cur_block; + struct fatent_ra fatent_ra; int err = 0, free; lock_fat(sbi); if (sbi->free_clusters != -1 && sbi->free_clus_valid) goto out; - reada_blocks = FAT_READA_SIZE >> sb->s_blocksize_bits; - reada_mask = reada_blocks - 1; - cur_block = 0; - 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 */ - if ((cur_block & reada_mask) == 0) { - unsigned long rest = sbi->fat_length - cur_block; - fat_ent_reada(sb, &fatent, min(reada_blocks, rest)); - } - cur_block++; + fat_ent_reada(sb, &fatent_ra, &fatent); err = fat_ent_read_block(sb, &fatent); if (err) @@ -684,6 +741,7 @@ int fat_count_free_clusters(struct super_block *sb) 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; @@ -693,3 +751,98 @@ 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 index 9b104f543056..4fc49a614fb8 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/file.c * @@ -10,22 +11,23 @@ #include <linux/module.h> #include <linux/compat.h> #include <linux/mount.h> -#include <linux/time.h> -#include <linux/buffer_head.h> -#include <linux/writeback.h> -#include <linux/backing-dev.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; - mutex_lock(&inode->i_mutex); + inode_lock_shared(inode); attr = fat_make_attrs(inode); - mutex_unlock(&inode->i_mutex); + inode_unlock_shared(inode); return put_user(attr, user_attr); } @@ -46,7 +48,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) err = mnt_want_write_file(file); if (err) goto out; - mutex_lock(&inode->i_mutex); + inode_lock(inode); /* * ATTR_VOLUME and ATTR_DIR cannot be changed; this also @@ -62,7 +64,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) /* Equivalent to a chmod() */ ia.ia_valid = ATTR_MODE | ATTR_CTIME; - ia.ia_ctime = current_fs_time(inode->i_sb); + ia.ia_ctime = current_time(inode); if (is_dir) ia.ia_mode = fat_make_mode(sbi, attr, S_IRWXUGO); else { @@ -88,12 +90,13 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) * out the RO attribute for checking by the security * module, just because it maps to a file mode. */ - err = security_inode_setattr(file->f_path.dentry, &ia); + err = security_inode_setattr(file_mnt_idmap(file), + file->f_path.dentry, &ia); if (err) goto out_unlock_inode; /* This MUST be done before doing anything irreversible... */ - err = fat_setattr(file->f_path.dentry, &ia); + err = fat_setattr(file_mnt_idmap(file), file->f_path.dentry, &ia); if (err) goto out_unlock_inode; @@ -108,7 +111,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr) fat_save_attrs(inode, attr); mark_inode_dirty(inode); out_unlock_inode: - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); mnt_drop_write_file(file); out: return err; @@ -120,6 +123,36 @@ static int fat_ioctl_get_volume_id(struct inode *inode, u32 __user *user_attr) 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); @@ -132,26 +165,20 @@ long fat_generic_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) 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 */ } } -#ifdef CONFIG_COMPAT -static long fat_generic_compat_ioctl(struct file *filp, unsigned int cmd, - unsigned long arg) - -{ - return fat_generic_ioctl(filp, cmd, (unsigned long)compat_ptr(arg)); -} -#endif - static int fat_file_release(struct inode *inode, struct file *filp) { if ((filp->f_mode & FMODE_WRITE) && - MSDOS_SB(inode->i_sb)->options.flush) { + MSDOS_SB(inode->i_sb)->options.flush) { fat_flush_inodes(inode->i_sb, inode, NULL); - congestion_wait(BLK_RW_ASYNC, HZ/10); + set_current_state(TASK_UNINTERRUPTIBLE); + io_schedule_timeout(HZ/10); } return 0; } @@ -159,29 +186,32 @@ static int fat_file_release(struct inode *inode, struct file *filp) int fat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync) { struct inode *inode = filp->f_mapping->host; - int res, err; + int err; + + err = __generic_file_fsync(filp, start, end, datasync); + if (err) + return err; - res = generic_file_fsync(filp, start, end, datasync); err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); + if (err) + return err; - return res ? res : err; + return blkdev_issue_flush(inode->i_sb->s_bdev); } const struct file_operations fat_file_operations = { .llseek = generic_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = generic_file_aio_read, - .aio_write = generic_file_aio_write, - .mmap = generic_file_mmap, + .read_iter = generic_file_read_iter, + .write_iter = generic_file_write_iter, + .mmap_prepare = generic_file_mmap_prepare, .release = fat_file_release, .unlocked_ioctl = fat_generic_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = fat_generic_compat_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, .fsync = fat_file_fsync, - .splice_read = generic_file_splice_read, + .splice_read = filemap_splice_read, + .splice_write = iter_file_splice_write, + .fallocate = fat_fallocate, }; static int fat_cont_expand(struct inode *inode, loff_t size) @@ -194,7 +224,7 @@ static int fat_cont_expand(struct inode *inode, loff_t size) if (err) goto out; - inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; + fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); mark_inode_dirty(inode); if (IS_SYNC(inode)) { int err2; @@ -220,6 +250,62 @@ 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) { @@ -241,7 +327,7 @@ static int fat_free(struct inode *inode, int skip) MSDOS_I(inode)->i_logstart = 0; } MSDOS_I(inode)->i_attrs |= ATTR_ARCH; - inode->i_ctime = inode->i_mtime = CURRENT_TIME_SEC; + fat_truncate_time(inode, NULL, S_CTIME|S_MTIME); if (wait) { err = fat_sync_inode(inode); if (err) { @@ -309,16 +395,25 @@ void fat_truncate_blocks(struct inode *inode, loff_t offset) fat_flush_inodes(inode->i_sb, inode, NULL); } -int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) +int fat_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, unsigned int flags) { - struct inode *inode = dentry->d_inode; - generic_fillattr(inode, stat); - stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size; + struct inode *inode = d_inode(path->dentry); + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + + generic_fillattr(idmap, request_mask, inode, stat); + stat->blksize = sbi->cluster_size; - if (MSDOS_SB(inode->i_sb)->options.nfs == FAT_NFS_NOSTALE_RO) { + 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(MSDOS_SB(inode->i_sb), inode); + 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); @@ -361,12 +456,14 @@ static int fat_sanitize_mode(const struct msdos_sb_info *sbi, return 0; } -static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode) +static int fat_allow_set_time(struct mnt_idmap *idmap, + struct msdos_sb_info *sbi, struct inode *inode) { umode_t allow_utime = sbi->options.allow_utime; - if (!uid_eq(current_fsuid(), inode->i_uid)) { - if (in_group_p(inode->i_gid)) + if (!vfsuid_eq_kuid(i_uid_into_vfsuid(idmap, inode), + current_fsuid())) { + if (vfsgid_in_group_p(i_gid_into_vfsgid(idmap, inode))) allow_utime >>= 3; if (allow_utime & MAY_WRITE) return 1; @@ -380,21 +477,22 @@ static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode) /* valid file mode bits */ #define FAT_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXUGO) -int fat_setattr(struct dentry *dentry, struct iattr *attr) +int fat_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) { struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb); - struct inode *inode = dentry->d_inode; + 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(sbi, inode)) + if (fat_allow_set_time(idmap, sbi, inode)) attr->ia_valid &= ~TIMES_SET_FLAGS; } - error = inode_change_ok(inode, attr); + error = setattr_prepare(idmap, dentry, attr); attr->ia_valid = ia_valid; if (error) { if (sbi->options.quiet) @@ -420,9 +518,11 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) } if (((attr->ia_valid & ATTR_UID) && - (!uid_eq(attr->ia_uid, sbi->options.fs_uid))) || + (!uid_eq(from_vfsuid(idmap, i_user_ns(inode), attr->ia_vfsuid), + sbi->options.fs_uid))) || ((attr->ia_valid & ATTR_GID) && - (!gid_eq(attr->ia_gid, sbi->options.fs_gid))) || + (!gid_eq(from_vfsgid(idmap, i_user_ns(inode), attr->ia_vfsgid), + sbi->options.fs_gid))) || ((attr->ia_valid & ATTR_MODE) && (attr->ia_mode & ~FAT_VALID_MODE))) error = -EPERM; @@ -443,13 +543,28 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) } 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(inode, attr); + /* + * 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(idmap, inode, attr); mark_inode_dirty(inode); out: return error; @@ -459,4 +574,5 @@ 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 index 11b51bb55b42..0b6009cd1844 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/inode.c * @@ -11,23 +12,17 @@ */ #include <linux/module.h> -#include <linux/init.h> -#include <linux/time.h> -#include <linux/slab.h> -#include <linux/seq_file.h> #include <linux/pagemap.h> #include <linux/mpage.h> -#include <linux/buffer_head.h> -#include <linux/mount.h> -#include <linux/aio.h> #include <linux/vfs.h> -#include <linux/parser.h> +#include <linux/seq_file.h> #include <linux/uio.h> -#include <linux/writeback.h> -#include <linux/log2.h> -#include <linux/hash.h> #include <linux/blkdev.h> -#include <asm/unaligned.h> +#include <linux/backing-dev.h> +#include <linux/unaligned.h> +#include <linux/random.h> +#include <linux/iversion.h> +#include <linux/fs_struct.h> #include "fat.h" #ifndef CONFIG_FAT_DEFAULT_IOCHARSET @@ -35,11 +30,78 @@ #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, +}, +}; -static int fat_add_cluster(struct inode *inode) +int fat_add_cluster(struct inode *inode) { int err, cluster; @@ -61,10 +123,10 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, struct super_block *sb = inode->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); unsigned long mapped_blocks; - sector_t phys; + sector_t phys, last_block; int err, offset; - err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create); + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); if (err) return err; if (phys) { @@ -81,8 +143,14 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, return -EIO; } + last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9); offset = (unsigned long)iblock & (sbi->sec_per_clus - 1); - if (!offset) { + /* + * 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) @@ -94,11 +162,17 @@ static inline int __fat_get_block(struct inode *inode, sector_t iblock, *max_blocks = min(mapped_blocks, *max_blocks); MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits; - err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create); + 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(!phys); BUG_ON(*max_blocks != mapped_blocks); set_buffer_new(bh_result); map_bh(bh_result, sb, phys); @@ -120,26 +194,20 @@ static int fat_get_block(struct inode *inode, sector_t iblock, return 0; } -static int fat_writepage(struct page *page, struct writeback_control *wbc) -{ - return block_write_full_page(page, fat_get_block, wbc); -} - static int fat_writepages(struct address_space *mapping, struct writeback_control *wbc) { return mpage_writepages(mapping, wbc, fat_get_block); } -static int fat_readpage(struct file *file, struct page *page) +static int fat_read_folio(struct file *file, struct folio *folio) { - return mpage_readpage(page, fat_get_block); + return mpage_read_folio(folio, fat_get_block); } -static int fat_readpages(struct file *file, struct address_space *mapping, - struct list_head *pages, unsigned nr_pages) +static void fat_readahead(struct readahead_control *rac) { - return mpage_readpages(mapping, pages, nr_pages, fat_get_block); + mpage_readahead(rac, fat_get_block); } static void fat_write_failed(struct address_space *mapping, loff_t to) @@ -147,53 +215,54 @@ 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, to, inode->i_size); + truncate_pagecache(inode, inode->i_size); fat_truncate_blocks(inode, inode->i_size); } } -static int fat_write_begin(struct file *file, struct address_space *mapping, - loff_t pos, unsigned len, unsigned flags, - struct page **pagep, void **fsdata) +static int fat_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata) { int err; - *pagep = NULL; - err = cont_write_begin(file, mapping, pos, len, flags, - pagep, fsdata, fat_get_block, + err = cont_write_begin(iocb, mapping, pos, len, + foliop, 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) +static int fat_write_end(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct folio *folio, void *fsdata) { struct inode *inode = mapping->host; int err; - err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata); if (err < len) fat_write_failed(mapping, pos + len); if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { - inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; + 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(int rw, struct kiocb *iocb, - const struct iovec *iov, - loff_t offset, unsigned long nr_segs) +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 (rw == WRITE) { + 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. @@ -203,7 +272,7 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * * Return 0, and fallback to normal buffered write. */ - loff_t size = offset + iov_length(iov, nr_segs); + loff_t size = offset + count; if (MSDOS_I(inode)->mmu_private < size) return 0; } @@ -212,35 +281,73 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, - fat_get_block); - if (ret < 0 && (rw & WRITE)) - fat_write_failed(mapping, offset + iov_length(iov, nr_segs)); + 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); + 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 = { - .readpage = fat_readpage, - .readpages = fat_readpages, - .writepage = fat_writepage, + .dirty_folio = block_dirty_folio, + .invalidate_folio = block_invalidate_folio, + .read_folio = fat_read_folio, + .readahead = fat_readahead, .writepages = fat_writepages, .write_begin = fat_write_begin, .write_end = fat_write_end, .direct_IO = fat_direct_IO, - .bmap = _fat_bmap + .bmap = _fat_bmap, + .migrate_folio = buffer_migrate_folio, }; /* @@ -359,7 +466,7 @@ struct inode *fat_iget(struct super_block *sb, loff_t i_pos) static int is_exec(unsigned char *extension) { - unsigned char *exe_extensions = "EXECOMBAT", *walk; + unsigned char exe_extensions[] = "EXECOMBAT", *walk; for (walk = exe_extensions; *walk; walk += 3) if (!strncmp(extension, walk, 3)) @@ -384,17 +491,36 @@ static int fat_calc_dir_size(struct inode *inode) 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); + struct timespec64 mtime; int error; MSDOS_I(inode)->i_pos = 0; inode->i_uid = sbi->options.fs_uid; inode->i_gid = sbi->options.fs_gid; - inode->i_version++; - inode->i_generation = get_seconds(); + inode_inc_iversion(inode); + inode->i_generation = get_random_u32(); if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { inode->i_generation &= ~1; @@ -410,6 +536,10 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) 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, @@ -433,13 +563,18 @@ int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) 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); + fat_time_fat2unix(sbi, &mtime, de->time, de->date, 0); + inode_set_mtime_to_ts(inode, mtime); + inode_set_ctime_to_ts(inode, mtime); if (sbi->options.isvfat) { - fat_time_fat2unix(sbi, &inode->i_ctime, de->ctime, + struct timespec64 atime; + + fat_time_fat2unix(sbi, &atime, 0, de->adate, 0); + inode_set_atime_to_ts(inode, atime); + fat_time_fat2unix(sbi, &MSDOS_I(inode)->i_crtime, de->ctime, de->cdate, de->ctime_cs); - fat_time_fat2unix(sbi, &inode->i_atime, 0, de->adate, 0); } else - inode->i_ctime = inode->i_atime = inode->i_mtime; + inode_set_atime_to_ts(inode, fat_truncate_atime(sbi, &mtime)); return 0; } @@ -472,7 +607,7 @@ struct inode *fat_build_inode(struct super_block *sb, goto out; } inode->i_ino = iunique(sb, MSDOS_ROOT_INO); - inode->i_version = 1; + inode_set_iversion(inode, 1); err = fat_fill_inode(inode, de); if (err) { iput(inode); @@ -488,13 +623,43 @@ out: 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(&inode->i_data, 0); + 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); @@ -506,10 +671,10 @@ static void fat_set_state(struct super_block *sb, { struct buffer_head *bh; struct fat_boot_sector *b; - struct msdos_sb_info *sbi = sb->s_fs_info; + struct msdos_sb_info *sbi = MSDOS_SB(sb); /* do not change any thing if mounted read only */ - if ((sb->s_flags & MS_RDONLY) && !force) + if (sb_rdonly(sb) && !force) return; /* do not change state if fs was dirty */ @@ -531,7 +696,7 @@ static void fat_set_state(struct super_block *sb, b = (struct fat_boot_sector *) bh->b_data; - if (sbi->fat_bits == 32) { + if (is_fat32(sbi)) { if (set) b->fat32.state |= FAT_STATE_DIRTY; else @@ -548,6 +713,24 @@ static void fat_set_state(struct super_block *sb, 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); @@ -557,14 +740,7 @@ static void fat_put_super(struct super_block *sb) iput(sbi->fsinfo_inode); iput(sbi->fat_inode); - unload_nls(sbi->nls_disk); - unload_nls(sbi->nls_io); - - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); - - sb->s_fs_info = NULL; - kfree(sbi); + call_rcu(&sbi->rcu, delayed_free); } static struct kmem_cache *fat_inode_cachep; @@ -572,25 +748,28 @@ static struct kmem_cache *fat_inode_cachep; static struct inode *fat_alloc_inode(struct super_block *sb) { struct msdos_inode_info *ei; - ei = kmem_cache_alloc(fat_inode_cachep, GFP_NOFS); + 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_i_callback(struct rcu_head *head) +static void fat_free_inode(struct inode *inode) { - struct inode *inode = container_of(head, struct inode, i_rcu); kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); } -static void fat_destroy_inode(struct inode *inode) -{ - call_rcu(&inode->i_rcu, fat_i_callback); -} - static void init_once(void *foo) { struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; @@ -609,7 +788,7 @@ 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; @@ -626,15 +805,18 @@ static void __exit fat_destroy_inodecache(void) kmem_cache_destroy(fat_inode_cachep); } -static int fat_remount(struct super_block *sb, int *flags, char *data) +int fat_reconfigure(struct fs_context *fc) { - int new_rdonly; + bool new_rdonly; + struct super_block *sb = fc->root->d_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); - *flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME); + fc->sb_flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME); + + sync_filesystem(sb); /* make sure we update state on remount. */ - new_rdonly = *flags & MS_RDONLY; - if (new_rdonly != (sb->s_flags & MS_RDONLY)) { + new_rdonly = fc->sb_flags & SB_RDONLY; + if (new_rdonly != sb_rdonly(sb)) { if (new_rdonly) fat_set_state(sb, 0, 0); else @@ -642,6 +824,7 @@ static int fat_remount(struct super_block *sb, int *flags, char *data) } return 0; } +EXPORT_SYMBOL_GPL(fat_reconfigure); static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) { @@ -661,8 +844,7 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) buf->f_blocks = sbi->max_cluster - FAT_START_ENT; buf->f_bfree = sbi->free_clusters; buf->f_bavail = sbi->free_clusters; - buf->f_fsid.val[0] = (u32)id; - buf->f_fsid.val[1] = (u32)(id >> 32); + buf->f_fsid = u64_to_fsid(id); buf->f_namelen = (sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE; @@ -675,6 +857,7 @@ static int __fat_write_inode(struct inode *inode, int wait) struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh; struct msdos_dir_entry *raw_entry; + struct timespec64 mtime; loff_t i_pos; sector_t blocknr; int err, offset; @@ -708,14 +891,16 @@ retry: 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, + mtime = inode_get_mtime(inode); + fat_time_unix2fat(sbi, &mtime, &raw_entry->time, &raw_entry->date, NULL); if (sbi->options.isvfat) { + struct timespec64 ts = inode_get_atime(inode); __le16 atime; - fat_time_unix2fat(sbi, &inode->i_ctime, &raw_entry->ctime, + + fat_time_unix2fat(sbi, &ts, &atime, &raw_entry->adate, NULL); + fat_time_unix2fat(sbi, &MSDOS_I(inode)->i_crtime, &raw_entry->ctime, &raw_entry->cdate, &raw_entry->ctime_cs); - fat_time_unix2fat(sbi, &inode->i_atime, &atime, - &raw_entry->adate, NULL); } spin_unlock(&sbi->inode_hash_lock); mark_buffer_dirty(bh); @@ -752,13 +937,11 @@ 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, - .destroy_inode = fat_destroy_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, }; @@ -848,366 +1031,304 @@ static int fat_show_options(struct seq_file *m, struct dentry *root) 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_check, 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_dotsOK, + Opt_charset, Opt_shortname, Opt_utf8, Opt_utf8_bool, + Opt_uni_xl, Opt_uni_xl_bool, Opt_nonumtail, Opt_nonumtail_bool, + Opt_obsolete, Opt_flush, Opt_tz, Opt_rodir, Opt_errors, Opt_discard, + Opt_nfs, Opt_nfs_enum, Opt_time_offset, 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_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 struct constant_table fat_param_check[] = { + {"relaxed", 'r'}, + {"r", 'r'}, + {"strict", 's'}, + {"s", 's'}, + {"normal", 'n'}, + {"n", 'n'}, + {} }; -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 struct constant_table fat_param_tz[] = { + {"UTC", 0}, + {} }; -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 const struct constant_table fat_param_errors[] = { + {"continue", FAT_ERRORS_CONT}, + {"panic", FAT_ERRORS_PANIC}, + {"remount-ro", FAT_ERRORS_RO}, + {} }; -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; +static const struct constant_table fat_param_nfs[] = { + {"stale_rw", FAT_NFS_STALE_RW}, + {"nostale_ro", FAT_NFS_NOSTALE_RO}, + {} +}; - opts->fs_uid = current_uid(); - opts->fs_gid = current_gid(); - opts->fs_fmask = opts->fs_dmask = current_umask(); - opts->allow_utime = -1; - opts->codepage = fat_default_codepage; - opts->iocharset = fat_default_iocharset; - if (is_vfat) { - opts->shortname = VFAT_SFN_DISPLAY_WINNT|VFAT_SFN_CREATE_WIN95; - opts->rodir = 0; - } else { - opts->shortname = 0; - opts->rodir = 1; - } - opts->name_check = 'n'; - opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK = 0; - opts->utf8 = opts->unicode_xlate = 0; - opts->numtail = 1; - opts->usefree = opts->nocase = 0; - opts->tz_set = 0; - opts->nfs = 0; - opts->errors = FAT_ERRORS_RO; - *debug = 0; +/* + * These are all obsolete but we still reject invalid options. + * The corresponding values are therefore meaningless. + */ +static const struct constant_table fat_param_conv[] = { + {"binary", 0}, + {"text", 0}, + {"auto", 0}, + {"b", 0}, + {"t", 0}, + {"a", 0}, + {} +}; - if (!options) - goto out; +/* Core options. See below for vfat and msdos extras */ +const struct fs_parameter_spec fat_param_spec[] = { + fsparam_enum ("check", Opt_check, fat_param_check), + fsparam_uid ("uid", Opt_uid), + fsparam_gid ("gid", Opt_gid), + fsparam_u32oct ("umask", Opt_umask), + fsparam_u32oct ("dmask", Opt_dmask), + fsparam_u32oct ("fmask", Opt_fmask), + fsparam_u32oct ("allow_utime", Opt_allow_utime), + fsparam_u32 ("codepage", Opt_codepage), + fsparam_flag ("usefree", Opt_usefree), + fsparam_flag ("nocase", Opt_nocase), + fsparam_flag ("quiet", Opt_quiet), + fsparam_flag ("showexec", Opt_showexec), + fsparam_flag ("debug", Opt_debug), + fsparam_flag ("sys_immutable", Opt_immutable), + fsparam_flag ("flush", Opt_flush), + fsparam_enum ("tz", Opt_tz, fat_param_tz), + fsparam_s32 ("time_offset", Opt_time_offset), + fsparam_enum ("errors", Opt_errors, fat_param_errors), + fsparam_flag ("discard", Opt_discard), + fsparam_flag ("nfs", Opt_nfs), + fsparam_enum ("nfs", Opt_nfs_enum, fat_param_nfs), + fsparam_flag ("dos1xfloppy", Opt_dos1xfloppy), + __fsparam(fs_param_is_enum, "conv", + Opt_obsolete, fs_param_deprecated, fat_param_conv), + __fsparam(fs_param_is_u32, "fat", + Opt_obsolete, fs_param_deprecated, NULL), + __fsparam(fs_param_is_u32, "blocksize", + Opt_obsolete, fs_param_deprecated, NULL), + __fsparam(fs_param_is_string, "cvf_format", + Opt_obsolete, fs_param_deprecated, NULL), + __fsparam(fs_param_is_string, "cvf_options", + Opt_obsolete, fs_param_deprecated, NULL), + __fsparam(NULL, "posix", + Opt_obsolete, fs_param_deprecated, NULL), + {} +}; +EXPORT_SYMBOL_GPL(fat_param_spec); - while ((p = strsep(&options, ",")) != NULL) { - int token; - if (!*p) - continue; +static const struct fs_parameter_spec msdos_param_spec[] = { + fsparam_flag_no ("dots", Opt_dots), + fsparam_bool ("dotsOK", Opt_dotsOK), + {} +}; - 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; - if (option < -12 * 60 || option > 12 * 60) - return -EINVAL; - opts->tz_set = 1; - opts->time_offset = option; - break; - case Opt_tz_utc: - opts->tz_set = 1; - opts->time_offset = 0; - break; - case Opt_err_cont: - opts->errors = FAT_ERRORS_CONT; - break; - case Opt_err_panic: - opts->errors = FAT_ERRORS_PANIC; - break; - case Opt_err_ro: - opts->errors = FAT_ERRORS_RO; - break; - case Opt_nfs_stale_rw: - opts->nfs = FAT_NFS_STALE_RW; - break; - case Opt_nfs_nostale_ro: - opts->nfs = FAT_NFS_NOSTALE_RO; - break; +static const struct constant_table fat_param_shortname[] = { + {"lower", VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95}, + {"win95", VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95}, + {"winnt", VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT}, + {"mixed", VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95}, + {} +}; - /* msdos specific */ - case Opt_dots: - opts->dotsOK = 1; - break; - case Opt_nodots: - opts->dotsOK = 0; - break; +static const struct fs_parameter_spec vfat_param_spec[] = { + fsparam_string ("iocharset", Opt_charset), + fsparam_enum ("shortname", Opt_shortname, fat_param_shortname), + fsparam_flag ("utf8", Opt_utf8), + fsparam_bool ("utf8", Opt_utf8_bool), + fsparam_flag ("uni_xlate", Opt_uni_xl), + fsparam_bool ("uni_xlate", Opt_uni_xl_bool), + fsparam_flag ("nonumtail", Opt_nonumtail), + fsparam_bool ("nonumtail", Opt_nonumtail_bool), + fsparam_flag ("rodir", Opt_rodir), + {} +}; - /* vfat specific */ - case Opt_charset: - if (opts->iocharset != fat_default_iocharset) - kfree(opts->iocharset); - 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; +int fat_parse_param(struct fs_context *fc, struct fs_parameter *param, + bool is_vfat) +{ + struct fat_mount_options *opts = fc->fs_private; + struct fs_parse_result result; + int opt; - /* 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; - } - } + /* remount options have traditionally been ignored */ + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) + return 0; -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!"); + opt = fs_parse(fc, fat_param_spec, param, &result); + /* If option not found in fat_param_spec, try vfat/msdos options */ + if (opt == -ENOPARAM) { + if (is_vfat) + opt = fs_parse(fc, vfat_param_spec, param, &result); + else + opt = fs_parse(fc, msdos_param_spec, param, &result); } - /* If user doesn't specify allow_utime, it's initialized from dmask. */ - if (opts->allow_utime == (unsigned short)-1) - opts->allow_utime = ~opts->fs_dmask & (S_IWGRP | S_IWOTH); - if (opts->unicode_xlate) - opts->utf8 = 0; - if (opts->nfs == FAT_NFS_NOSTALE_RO) { - sb->s_flags |= MS_RDONLY; - sb->s_export_op = &fat_export_ops_nostale; + if (opt < 0) + return opt; + + switch (opt) { + case Opt_check: + opts->name_check = result.uint_32; + 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: + opts->debug = 1; + break; + case Opt_immutable: + opts->sys_immutable = 1; + break; + case Opt_uid: + opts->fs_uid = result.uid; + break; + case Opt_gid: + opts->fs_gid = result.gid; + break; + case Opt_umask: + opts->fs_fmask = opts->fs_dmask = result.uint_32; + break; + case Opt_dmask: + opts->fs_dmask = result.uint_32; + break; + case Opt_fmask: + opts->fs_fmask = result.uint_32; + break; + case Opt_allow_utime: + opts->allow_utime = result.uint_32 & (S_IWGRP | S_IWOTH); + break; + case Opt_codepage: + opts->codepage = result.uint_32; + break; + case Opt_flush: + opts->flush = 1; + break; + case Opt_time_offset: + /* + * 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 (result.int_32 < -24 * 60 || result.int_32 > 24 * 60) + return -EINVAL; + opts->tz_set = 1; + opts->time_offset = result.int_32; + break; + case Opt_tz: + opts->tz_set = 1; + opts->time_offset = result.uint_32; + break; + case Opt_errors: + opts->errors = result.uint_32; + break; + case Opt_nfs: + opts->nfs = FAT_NFS_STALE_RW; + break; + case Opt_nfs_enum: + opts->nfs = result.uint_32; + break; + case Opt_dos1xfloppy: + opts->dos1xfloppy = 1; + break; + + /* msdos specific */ + case Opt_dots: /* dots / nodots */ + opts->dotsOK = !result.negated; + break; + case Opt_dotsOK: /* dotsOK = yes/no */ + opts->dotsOK = result.boolean; + break; + + /* vfat specific */ + case Opt_charset: + fat_reset_iocharset(opts); + opts->iocharset = param->string; + param->string = NULL; /* Steal string */ + break; + case Opt_shortname: + opts->shortname = result.uint_32; + break; + case Opt_utf8: + opts->utf8 = 1; + break; + case Opt_utf8_bool: + opts->utf8 = result.boolean; + break; + case Opt_uni_xl: + opts->unicode_xlate = 1; + break; + case Opt_uni_xl_bool: + opts->unicode_xlate = result.boolean; + break; + case Opt_nonumtail: + opts->numtail = 0; /* negated option */ + break; + case Opt_nonumtail_bool: + opts->numtail = !result.boolean; /* negated option */ + break; + case Opt_rodir: + opts->rodir = 1; + break; + case Opt_discard: + opts->discard = 1; + break; + + /* obsolete mount options */ + case Opt_obsolete: + printk(KERN_INFO "FAT-fs: \"%s\" option is obsolete, " + "not supported now", param->key); + break; + default: + return -EINVAL; } return 0; } +EXPORT_SYMBOL_GPL(fat_parse_param); static int fat_read_root(struct inode *inode) { - struct super_block *sb = inode->i_sb; - struct msdos_sb_info *sbi = MSDOS_SB(sb); + 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->i_version++; + 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 (sbi->fat_bits == 32) { + if (is_fat32(sbi)) { MSDOS_I(inode)->i_start = sbi->root_cluster; error = fat_calc_dir_size(inode); if (error < 0) @@ -1222,8 +1343,8 @@ static int fat_read_root(struct inode *inode) 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; + inode_set_mtime_to_ts(inode, + inode_set_atime_to_ts(inode, inode_set_ctime(inode, 0, 0))); set_nlink(inode, fat_subdirs(inode)+2); return 0; @@ -1234,7 +1355,7 @@ static unsigned long calc_fat_clusters(struct super_block *sb) struct msdos_sb_info *sbi = MSDOS_SB(sb); /* Divide first to avoid overflow */ - if (sbi->fat_bits != 12) { + if (!is_fat12(sbi)) { unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; return ent_per_sec * sbi->fat_length; } @@ -1242,27 +1363,194 @@ static unsigned long calc_fat_clusters(struct super_block *sb) 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, +int fat_fill_super(struct super_block *sb, struct fs_context *fc, void (*setup)(struct super_block *)) { + struct fat_mount_options *opts = fc->fs_private; + int silent = fc->sb_flags & SB_SILENT; struct inode *root_inode = NULL, *fat_inode = NULL; struct inode *fsinfo_inode = NULL; struct buffer_head *bh; - struct fat_boot_sector *b; + struct fat_bios_param_block bpb; struct msdos_sb_info *sbi; u16 logical_sector_size; u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; - int debug; - unsigned int media; long error; char buf[50]; + struct timespec64 ts; /* * GFP_KERNEL is ok here, because while we do hold the - * supeblock lock, memory pressure can't call back into + * 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! */ @@ -1271,122 +1559,127 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, return -ENOMEM; sb->s_fs_info = sbi; - sb->s_flags |= MS_NODIRATIME; + 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; + /* 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; + } + + /* Apply parsed options to sbi (structure copy) */ + sbi->options = *opts; + /* Transfer ownership of iocharset to sbi->options */ + opts->iocharset = NULL; setup(sb); /* flavour-specific stuff that needs options */ + error = -EINVAL; + if (!sb_min_blocksize(sb, 512)) { + fat_msg(sb, KERN_ERR, "unable to set blocksize"); + goto out_fail; + } 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; } - b = (struct fat_boot_sector *) bh->b_data; - if (!b->reserved) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus number of reserved sectors"); - brelse(bh); - goto out_invalid; - } - if (!b->fats) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); - brelse(bh); - goto out_invalid; - } - - /* - * Earlier we checked here that b->secs_track and b->head are nonzero, - * but it turns out valid FAT filesystems can have zero there. - */ + error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, + &bpb); + if (error == -EINVAL && sbi->options.dos1xfloppy) + error = fat_read_static_bpb(sb, + (struct fat_boot_sector *)bh->b_data, silent, &bpb); + brelse(bh); - media = b->media; - if (!fat_valid_media(media)) { - if (!silent) - fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", - media); - brelse(bh); - goto out_invalid; - } - logical_sector_size = get_unaligned_le16(&b->sector_size); - if (!is_power_of_2(logical_sector_size) - || (logical_sector_size < 512) - || (logical_sector_size > 4096)) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus logical sector size %u", - logical_sector_size); - brelse(bh); + if (error == -EINVAL) goto out_invalid; - } - sbi->sec_per_clus = b->sec_per_clus; - if (!is_power_of_2(sbi->sec_per_clus)) { - if (!silent) - fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", - sbi->sec_per_clus); - brelse(bh); - 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); - brelse(bh); goto out_fail; } + if (logical_sector_size > sb->s_blocksize) { - brelse(bh); + struct buffer_head *bh_resize; if (!sb_set_blocksize(sb, logical_sector_size)) { fat_msg(sb, KERN_ERR, "unable to set blocksize %u", logical_sector_size); goto out_fail; } - bh = sb_bread(sb, 0); - if (bh == NULL) { + + /* Verify that the larger boot sector is fully readable */ + bh_resize = sb_bread(sb, 0); + if (bh_resize == NULL) { fat_msg(sb, KERN_ERR, "unable to read boot sector" " (logical sector size = %lu)", sb->s_blocksize); goto out_fail; } - b = (struct fat_boot_sector *) bh->b_data; + brelse(bh_resize); } mutex_init(&sbi->s_lock); sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus; sbi->cluster_bits = ffs(sbi->cluster_size) - 1; - sbi->fats = b->fats; + sbi->fats = bpb.fat_fats; sbi->fat_bits = 0; /* Don't know yet */ - sbi->fat_start = le16_to_cpu(b->reserved); - sbi->fat_length = le16_to_cpu(b->fat_length); + sbi->fat_start = bpb.fat_reserved; + sbi->fat_length = bpb.fat_fat_length; sbi->root_cluster = 0; sbi->free_clusters = -1; /* Don't know yet */ sbi->free_clus_valid = 0; sbi->prev_free = FAT_START_ENT; sb->s_maxbytes = 0xffffffff; + 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 && b->fat32.length) { + if (!sbi->fat_length && bpb.fat32_length) { struct fat_boot_fsinfo *fsinfo; struct buffer_head *fsinfo_bh; /* Must be FAT32 */ sbi->fat_bits = 32; - sbi->fat_length = le32_to_cpu(b->fat32.length); - sbi->root_cluster = le32_to_cpu(b->fat32.root_cluster); + sbi->fat_length = bpb.fat32_length; + sbi->root_cluster = bpb.fat32_root_cluster; /* MC - if info_sector is 0, don't multiply by 0 */ - sbi->fsinfo_sector = le16_to_cpu(b->fat32.info_sector); + sbi->fsinfo_sector = bpb.fat32_info_sector; if (sbi->fsinfo_sector == 0) sbi->fsinfo_sector = 1; @@ -1394,7 +1687,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (fsinfo_bh == NULL) { fat_msg(sb, KERN_ERR, "bread failed, FSINFO block" " (sector = %lu)", sbi->fsinfo_sector); - brelse(bh); goto out_fail; } @@ -1416,56 +1708,51 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, } /* interpret volume ID as a little endian 32 bit integer */ - if (sbi->fat_bits == 32) - sbi->vol_id = (((u32)b->fat32.vol_id[0]) | - ((u32)b->fat32.vol_id[1] << 8) | - ((u32)b->fat32.vol_id[2] << 16) | - ((u32)b->fat32.vol_id[3] << 24)); + if (is_fat32(sbi)) + sbi->vol_id = bpb.fat32_vol_id; else /* fat 16 or 12 */ - sbi->vol_id = (((u32)b->fat16.vol_id[0]) | - ((u32)b->fat16.vol_id[1] << 8) | - ((u32)b->fat16.vol_id[2] << 16) | - ((u32)b->fat16.vol_id[3] << 24)); + sbi->vol_id = bpb.fat16_vol_id; + + __le32 vol_id_le = cpu_to_le32(sbi->vol_id); + super_set_uuid(sb, (void *) &vol_id_le, sizeof(vol_id_le)); 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 = get_unaligned_le16(&b->dir_entries); + sbi->dir_entries = bpb.fat_dir_entries; if (sbi->dir_entries & (sbi->dir_per_block - 1)) { if (!silent) - fat_msg(sb, KERN_ERR, "bogus directory-entries per block" + fat_msg(sb, KERN_ERR, "bogus number of directory entries" " (%u)", sbi->dir_entries); - brelse(bh); 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 = get_unaligned_le16(&b->sectors); + total_sectors = bpb.fat_sectors; if (total_sectors == 0) - total_sectors = le32_to_cpu(b->total_sect); + total_sectors = bpb.fat_total_sect; total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; - if (sbi->fat_bits != 32) + 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 (sbi->fat_bits == 32) - sbi->dirty = b->fat32.state & FAT_STATE_DIRTY; + if (is_fat32(sbi)) + sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; else /* fat 16 or 12 */ - sbi->dirty = b->fat16.state & FAT_STATE_DIRTY; + 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 (total_clusters > max_fat(sb)) { if (!silent) fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", total_clusters); - brelse(bh); goto out_invalid; } @@ -1478,19 +1765,21 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (sbi->prev_free < FAT_START_ENT) sbi->prev_free = FAT_START_ENT; - brelse(bh); - /* set up enough so that it can read an inode */ fat_hash_init(sb); dir_hash_init(sb); fat_ent_access_init(sb); /* - * The low byte of FAT's first entry must have same value with - * media-field. But in real world, too many devices is - * writing wrong value. So, removed that validity check. + * 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. * - * if (FAT_FIRST_ENT(sb, media) != first) + * 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; @@ -1515,7 +1804,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, fat_inode = new_inode(sb); if (!fat_inode) goto out_fail; - MSDOS_I(fat_inode)->i_pos = 0; sbi->fat_inode = fat_inode; fsinfo_inode = new_inode(sb); @@ -1529,7 +1817,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, if (!root_inode) goto out_fail; root_inode->i_ino = MSDOS_ROOT_INO; - root_inode->i_version = 1; + inode_set_iversion(root_inode, 1); error = fat_read_root(root_inode); if (error < 0) { iput(root_inode); @@ -1544,13 +1832,9 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, goto out_fail; } - if (sbi->options.discard) { - struct request_queue *q = bdev_get_queue(sb->s_bdev); - if (!blk_queue_discard(q)) - fat_msg(sb, KERN_WARNING, - "mounting with \"discard\" option, but " - "the device does not support discard"); - } + 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; @@ -1561,14 +1845,11 @@ out_invalid: fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); out_fail: - if (fsinfo_inode) - iput(fsinfo_inode); - if (fat_inode) - iput(fat_inode); + iput(fsinfo_inode); + iput(fat_inode); unload_nls(sbi->nls_io); unload_nls(sbi->nls_disk); - if (sbi->options.iocharset != fat_default_iocharset) - kfree(sbi->options.iocharset); + fat_reset_iocharset(&sbi->options); sb->s_fs_info = NULL; kfree(sbi); return error; @@ -1614,14 +1895,63 @@ int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2) ret = writeback_inode(i1); if (!ret && i2) ret = writeback_inode(i2); - if (!ret) { - struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; - ret = filemap_flush(mapping); - } + if (!ret) + ret = sync_blockdev_nowait(sb->s_bdev); return ret; } EXPORT_SYMBOL_GPL(fat_flush_inodes); +int fat_init_fs_context(struct fs_context *fc, bool is_vfat) +{ + struct fat_mount_options *opts; + + opts = kzalloc(sizeof(*opts), GFP_KERNEL); + if (!opts) + return -ENOMEM; + + 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; + opts->debug = 0; + + opts->utf8 = IS_ENABLED(CONFIG_FAT_DEFAULT_UTF8) && is_vfat; + + fc->fs_private = opts; + /* fc->ops assigned by caller */ + + return 0; +} +EXPORT_SYMBOL_GPL(fat_init_fs_context); + +void fat_free_fc(struct fs_context *fc) +{ + struct fat_mount_options *opts = fc->fs_private; + + if (opts->iocharset != fat_default_iocharset) + kfree(opts->iocharset); + kfree(fc->fs_private); +} +EXPORT_SYMBOL_GPL(fat_free_fc); + static int __init init_fat_fs(void) { int err; @@ -1650,4 +1980,5 @@ static void __exit exit_fat_fs(void) module_init(init_fat_fs) module_exit(exit_fat_fs) +MODULE_DESCRIPTION("Core FAT filesystem support"); MODULE_LICENSE("GPL"); diff --git a/fs/fat/misc.c b/fs/fat/misc.c index 628e22a5a543..950da09f0961 100644 --- a/fs/fat/misc.c +++ b/fs/fat/misc.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/fat/misc.c * @@ -6,11 +7,8 @@ * and date_dos2unix for date==0 by Igor Zhbanov(bsg@uniyar.ac.ru) */ -#include <linux/module.h> -#include <linux/fs.h> -#include <linux/buffer_head.h> -#include <linux/time.h> #include "fat.h" +#include <linux/iversion.h> /* * fat_fs_error reports a file system problem that might indicate fa data @@ -36,18 +34,24 @@ void __fat_fs_error(struct super_block *sb, int report, const char *fmt, ...) if (opts->errors == FAT_ERRORS_PANIC) panic("FAT-fs (%s): fs panic from previous error\n", sb->s_id); - else if (opts->errors == FAT_ERRORS_RO && !(sb->s_flags & MS_RDONLY)) { - sb->s_flags |= MS_RDONLY; + 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 preformated FAT specific messages. Every thing what is - * not fat_fs_error() should be fat_msg(). + * _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, ...) +void _fat_msg(struct super_block *sb, const char *level, const char *fmt, ...) { struct va_format vaf; va_list args; @@ -55,7 +59,7 @@ void fat_msg(struct super_block *sb, const char *level, const char *fmt, ...) va_start(args, fmt); vaf.fmt = fmt; vaf.va = &args; - printk("%sFAT-fs (%s): %pV\n", level, sb->s_id, &vaf); + _printk(FAT_PRINTK_PREFIX "%pV\n", level, sb->s_id, &vaf); va_end(args); } @@ -67,7 +71,7 @@ int fat_clusters_flush(struct super_block *sb) struct buffer_head *bh; struct fat_boot_fsinfo *fsinfo; - if (sbi->fat_bits != 32) + if (!is_fat32(sbi)) return 0; bh = sb_bread(sb, sbi->fsinfo_sector); @@ -154,9 +158,9 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) mark_inode_dirty(inode); } if (new_fclus != (inode->i_blocks >> (sbi->cluster_bits - 9))) { - fat_fs_error(sb, "clusters badly computed (%d != %llu)", - new_fclus, - (llu)(inode->i_blocks >> (sbi->cluster_bits - 9))); + fat_fs_error_ratelimit( + 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); @@ -164,8 +168,6 @@ int fat_chain_add(struct inode *inode, int new_dclus, int nr_cluster) return 0; } -extern struct timezone sys_tz; - /* * The epoch of FAT timestamp is 1980. * : bits : value @@ -186,17 +188,25 @@ extern struct timezone sys_tz; #define IS_LEAP_YEAR(y) (!((y) & 3) && (y) != YEAR_2100) /* Linear day numbers of the respective 1sts in non-leap years. */ -static time_t days_in_year[] = { +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 timespec *ts, +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); - time_t second, day, leap_day, month, year; + time64_t second; + long day, leap_day, month, year; year = date >> 9; month = max(1, (date >> 5) & 0xf); @@ -211,14 +221,11 @@ void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts, second = (time & 0x1f) << 1; second += ((time >> 5) & 0x3f) * SECS_PER_MIN; second += (time >> 11) * SECS_PER_HOUR; - second += (year * 365 + leap_day + second += (time64_t)(year * 365 + leap_day + days_in_year[month] + day + DAYS_DELTA) * SECS_PER_DAY; - if (!sbi->options.tz_set) - second += sys_tz.tz_minuteswest * SECS_PER_MIN; - else - second -= sbi->options.time_offset * SECS_PER_MIN; + second += fat_tz_offset(sbi); if (time_cs) { ts->tv_sec = second + (time_cs / 100); @@ -229,14 +236,15 @@ void fat_time_fat2unix(struct msdos_sb_info *sbi, struct timespec *ts, } } +/* 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 timespec *ts, +void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec64 *ts, __le16 *time, __le16 *date, u8 *time_cs) { struct tm tm; - time_to_tm(ts->tv_sec, - (sbi->options.tz_set ? sbi->options.time_offset : - -sys_tz.tz_minuteswest) * SECS_PER_MIN, &tm); + 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) { @@ -268,12 +276,95 @@ void fat_time_unix2fat(struct msdos_sb_info *sbi, struct timespec *ts, } 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_set_atime_to_ts(inode, 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_set_mtime_to_ts(inode, + inode_set_ctime_to_ts(inode, fat_truncate_mtime(sbi, now))); + + return 0; +} +EXPORT_SYMBOL_GPL(fat_truncate_time); + +int fat_update_time(struct inode *inode, 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, NULL, flags); + if (inode->i_sb->s_flags & SB_LAZYTIME) + dirty_flags |= I_DIRTY_TIME; + else + 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], WRITE); + write_dirty_buffer(bhs[i], 0); for (i = 0; i < nr_bhs; i++) { wait_on_buffer(bhs[i]); diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c index a783b0e1272a..0b920ee40a7f 100644 --- a/fs/fat/namei_msdos.c +++ b/fs/fat/namei_msdos.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/msdos/namei.c * @@ -7,8 +8,7 @@ */ #include <linux/module.h> -#include <linux/time.h> -#include <linux/buffer_head.h> +#include <linux/iversion.h> #include "fat.h" /* Characters that are undesirable in an MS-DOS file name */ @@ -156,7 +156,7 @@ static int msdos_hash(const struct dentry *dentry, struct qstr *qstr) error = msdos_format_name(qstr->name, qstr->len, msdos_name, options); if (!error) - qstr->hash = full_name_hash(msdos_name, MSDOS_NAME); + qstr->hash = full_name_hash(dentry, msdos_name, MSDOS_NAME); return 0; } @@ -164,10 +164,10 @@ static int msdos_hash(const struct dentry *dentry, struct qstr *qstr) * Compare two msdos names. If either of the names are invalid, * we fall back to doing the standard name comparison. */ -static int msdos_cmp(const struct dentry *parent, const struct dentry *dentry, +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(parent->d_sb)->options; + 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; @@ -226,7 +226,7 @@ static struct dentry *msdos_lookup(struct inode *dir, struct dentry *dentry, /***** Creates a directory entry (name is already formatted). */ static int msdos_add_entry(struct inode *dir, const unsigned char *name, int is_dir, int is_hid, int cluster, - struct timespec *ts, struct fat_slot_info *sinfo) + struct timespec64 *ts, struct fat_slot_info *sinfo) { struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb); struct msdos_dir_entry de; @@ -251,7 +251,7 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, if (err) return err; - dir->i_ctime = dir->i_mtime = *ts; + fat_truncate_time(dir, ts, S_CTIME|S_MTIME); if (IS_DIRSYNC(dir)) (void)fat_sync_inode(dir); else @@ -261,13 +261,13 @@ static int msdos_add_entry(struct inode *dir, const unsigned char *name, } /***** Create a file */ -static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int msdos_create(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode = NULL; struct fat_slot_info sinfo; - struct timespec ts; + struct timespec64 ts; unsigned char msdos_name[MSDOS_NAME]; int err, is_hid; @@ -285,7 +285,7 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, goto out; } - ts = CURRENT_TIME_SEC; + ts = current_time(dir); err = msdos_add_entry(dir, msdos_name, 0, is_hid, 0, &ts, &sinfo); if (err) goto out; @@ -295,7 +295,7 @@ static int msdos_create(struct inode *dir, struct dentry *dentry, umode_t mode, err = PTR_ERR(inode); goto out; } - inode->i_mtime = inode->i_atime = inode->i_ctime = ts; + 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); @@ -310,15 +310,11 @@ out: static int msdos_rmdir(struct inode *dir, struct dentry *dentry) { struct super_block *sb = dir->i_sb; - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct fat_slot_info sinfo; int err; mutex_lock(&MSDOS_SB(sb)->s_lock); - /* - * Check whether the directory is not in use, then check - * whether it is empty. - */ err = fat_dir_empty(inode); if (err) goto out; @@ -332,7 +328,7 @@ static int msdos_rmdir(struct inode *dir, struct dentry *dentry) drop_nlink(dir); clear_nlink(inode); - inode->i_ctime = CURRENT_TIME_SEC; + fat_truncate_time(inode, NULL, S_CTIME); fat_detach(inode); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); @@ -343,13 +339,14 @@ out: } /***** Make a directory */ -static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +static struct dentry *msdos_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; struct inode *inode; unsigned char msdos_name[MSDOS_NAME]; - struct timespec ts; + struct timespec64 ts; int err, is_hid, cluster; mutex_lock(&MSDOS_SB(sb)->s_lock); @@ -366,7 +363,7 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out; } - ts = CURRENT_TIME_SEC; + ts = current_time(dir); cluster = fat_alloc_new_dir(dir, &ts); if (cluster < 0) { err = cluster; @@ -385,26 +382,26 @@ static int msdos_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) goto out; } set_nlink(inode, 2); - inode->i_mtime = inode->i_atime = inode->i_ctime = ts; + 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; + return NULL; out_free: fat_free_clusters(dir, cluster); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); - return err; + return ERR_PTR(err); } /***** Unlink a file */ static int msdos_unlink(struct inode *dir, struct dentry *dentry) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct super_block *sb = inode->i_sb; struct fat_slot_info sinfo; int err; @@ -418,7 +415,7 @@ static int msdos_unlink(struct inode *dir, struct dentry *dentry) if (err) goto out; clear_nlink(inode); - inode->i_ctime = CURRENT_TIME_SEC; + fat_truncate_time(inode, NULL, S_CTIME); fat_detach(inode); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); @@ -437,13 +434,13 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, struct msdos_dir_entry *dotdot_de; struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; - struct timespec ts; + 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 = old_dentry->d_inode; - new_inode = new_dentry->d_inode; + old_inode = d_inode(old_dentry); + new_inode = d_inode(new_dentry); err = fat_scan(old_dir, old_name, &old_sinfo); if (err) { @@ -482,8 +479,8 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, } else mark_inode_dirty(old_inode); - old_dir->i_version++; - old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME_SEC; + 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 @@ -492,7 +489,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, } } - ts = CURRENT_TIME_SEC; + ts = current_time(old_inode); if (new_inode) { if (err) goto out; @@ -510,7 +507,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, goto out; new_i_pos = sinfo.i_pos; } - new_dir->i_version++; + inode_inc_iversion(new_dir); fat_detach(old_inode); fat_attach(old_inode, new_i_pos); @@ -542,8 +539,8 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, old_sinfo.bh = NULL; if (err) goto error_dotdot; - old_dir->i_version++; - old_dir->i_ctime = old_dir->i_mtime = ts; + 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 @@ -553,7 +550,7 @@ static int do_msdos_rename(struct inode *old_dir, unsigned char *old_name, drop_nlink(new_inode); if (is_dir) drop_nlink(new_inode); - new_inode->i_ctime = ts; + fat_truncate_time(new_inode, &ts, S_CTIME); } out: brelse(sinfo.bh); @@ -597,13 +594,18 @@ error_inode: } /***** Rename, a wrapper for rename_same_dir & rename_diff_dir */ -static int msdos_rename(struct inode *old_dir, struct dentry *old_dentry, - struct inode *new_dir, struct dentry *new_dentry) +static int msdos_rename(struct mnt_idmap *idmap, + 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, @@ -638,33 +640,58 @@ static const struct inode_operations msdos_dir_inode_operations = { .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 |= MS_NOATIME; + set_default_d_op(sb, &msdos_dentry_operations); + sb->s_flags |= SB_NOATIME; } -static int msdos_fill_super(struct super_block *sb, void *data, int silent) +static int msdos_fill_super(struct super_block *sb, struct fs_context *fc) { - return fat_fill_super(sb, data, silent, 0, setup); + return fat_fill_super(sb, fc, setup); } -static struct dentry *msdos_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data) +static int msdos_get_tree(struct fs_context *fc) { - return mount_bdev(fs_type, flags, dev_name, data, msdos_fill_super); + return get_tree_bdev(fc, msdos_fill_super); +} + +static int msdos_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + return fat_parse_param(fc, param, false); +} + +static const struct fs_context_operations msdos_context_ops = { + .parse_param = msdos_parse_param, + .get_tree = msdos_get_tree, + .reconfigure = fat_reconfigure, + .free = fat_free_fc, +}; + +static int msdos_init_fs_context(struct fs_context *fc) +{ + int err; + + /* Initialize with is_vfat == false */ + err = fat_init_fs_context(fc, false); + if (err) + return err; + + fc->ops = &msdos_context_ops; + return 0; } 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_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, + .init_fs_context = msdos_init_fs_context, + .parameters = fat_param_spec, }; MODULE_ALIAS_FS("msdos"); diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index 6df8d3d885e5..5dbc4cbb8fce 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/vfat/namei.c * @@ -16,13 +17,24 @@ */ #include <linux/module.h> -#include <linux/jiffies.h> #include <linux/ctype.h> #include <linux/slab.h> -#include <linux/buffer_head.h> #include <linux/namei.h> +#include <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 @@ -31,28 +43,25 @@ * If it happened, the negative dentry isn't actually negative * anymore. So, drop it. */ -static int vfat_revalidate_shortname(struct dentry *dentry) +static bool vfat_revalidate_shortname(struct dentry *dentry, struct inode *dir) { - int ret = 1; - spin_lock(&dentry->d_lock); - if (dentry->d_time != dentry->d_parent->d_inode->i_version) - ret = 0; - spin_unlock(&dentry->d_lock); - return ret; + return inode_eq_iversion(dir, vfat_d_version(dentry)); } -static int vfat_revalidate(struct dentry *dentry, unsigned int flags) +static int vfat_revalidate(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; /* This is not negative dentry. Always valid. */ - if (dentry->d_inode) + if (d_really_is_positive(dentry)) return 1; - return vfat_revalidate_shortname(dentry); + return vfat_revalidate_shortname(dentry, dir); } -static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) +static int vfat_revalidate_ci(struct inode *dir, const struct qstr *name, + struct dentry *dentry, unsigned int flags) { if (flags & LOOKUP_RCU) return -ECHILD; @@ -67,7 +76,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) * positive dentry isn't good idea. So it's unsupported like * rename("filename", "FILENAME") for now. */ - if (dentry->d_inode) + if (d_really_is_positive(dentry)) return 1; /* @@ -85,7 +94,7 @@ static int vfat_revalidate_ci(struct dentry *dentry, unsigned int flags) if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET)) return 0; - return vfat_revalidate_shortname(dentry); + return vfat_revalidate_shortname(dentry, dir); } /* returns the length of a struct qstr, ignoring trailing dots */ @@ -109,7 +118,7 @@ static unsigned int vfat_striptail_len(const struct qstr *qstr) */ static int vfat_hash(const struct dentry *dentry, struct qstr *qstr) { - qstr->hash = full_name_hash(qstr->name, vfat_striptail_len(qstr)); + qstr->hash = full_name_hash(dentry, qstr->name, vfat_striptail_len(qstr)); return 0; } @@ -129,7 +138,7 @@ static int vfat_hashi(const struct dentry *dentry, struct qstr *qstr) name = qstr->name; len = vfat_striptail_len(qstr); - hash = init_name_hash(); + hash = init_name_hash(dentry); while (len--) hash = partial_name_hash(nls_tolower(t, *name++), hash); qstr->hash = end_name_hash(hash); @@ -140,10 +149,10 @@ static int vfat_hashi(const struct dentry *dentry, struct qstr *qstr) /* * Case insensitive compare of two vfat names. */ -static int vfat_cmpi(const struct dentry *parent, const struct dentry *dentry, +static int vfat_cmpi(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { - struct nls_table *t = MSDOS_SB(parent->d_sb)->nls_io; + 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 */ @@ -159,7 +168,7 @@ static int vfat_cmpi(const struct dentry *parent, const struct dentry *dentry, /* * Case sensitive compare of two vfat names. */ -static int vfat_cmp(const struct dentry *parent, const struct dentry *dentry, +static int vfat_cmp(const struct dentry *dentry, unsigned int len, const char *str, const struct qstr *name) { unsigned int alen, blen; @@ -188,7 +197,7 @@ static const struct dentry_operations vfat_dentry_ops = { /* Characters that are undesirable in an MS-DOS file name */ -static inline wchar_t vfat_bad_char(wchar_t w) +static inline bool vfat_bad_char(wchar_t w) { return (w < 0x0020) || (w == '*') || (w == '?') || (w == '<') || (w == '>') @@ -196,7 +205,7 @@ static inline wchar_t vfat_bad_char(wchar_t w) || (w == '\\'); } -static inline wchar_t vfat_replace_char(wchar_t w) +static inline bool vfat_replace_char(wchar_t w) { return (w == '[') || (w == ']') || (w == ';') || (w == ',') || (w == '+') || (w == '='); @@ -501,10 +510,8 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, struct nls_table *nls) { const unsigned char *ip; - unsigned char nc; unsigned char *op; - unsigned int ec; - int i, k, fill; + int i, fill; int charlen; if (utf8) { @@ -521,33 +528,22 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, i < len && *outlen < FAT_LFN_LEN; *outlen += 1) { if (escape && (*ip == ':')) { + u8 uc[2]; + if (i > len - 5) return -EINVAL; - ec = 0; - for (k = 1; k < 5; k++) { - nc = ip[k]; - ec <<= 4; - if (nc >= '0' && nc <= '9') { - ec |= nc - '0'; - continue; - } - if (nc >= 'a' && nc <= 'f') { - ec |= nc - ('a' - 10); - continue; - } - if (nc >= 'A' && nc <= 'F') { - ec |= nc - ('A' - 10); - continue; - } + + if (hex2bin(uc, ip + 1, 2) < 0) return -EINVAL; - } - *op++ = ec & 0xFF; - *op++ = ec >> 8; + + *(wchar_t *)op = uc[0] << 8 | uc[1]; + + op += 2; ip += 5; i += 5; } else { charlen = nls->char2uni(ip, len - i, - (wchar_t *)op); + (wchar_t *)op); if (charlen < 0) return -EINVAL; ip += charlen; @@ -579,7 +575,7 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, static int vfat_build_slots(struct inode *dir, const unsigned char *name, int len, int is_dir, int cluster, - struct timespec *ts, + struct timespec64 *ts, struct msdos_dir_slot *slots, int *nr_slots) { struct msdos_sb_info *sbi = MSDOS_SB(dir->i_sb); @@ -654,8 +650,8 @@ out_free: return err; } -static int vfat_add_entry(struct inode *dir, struct qstr *qname, int is_dir, - int cluster, struct timespec *ts, +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; @@ -666,7 +662,7 @@ static int vfat_add_entry(struct inode *dir, struct qstr *qname, int is_dir, if (len == 0) return -ENOENT; - slots = kmalloc(sizeof(*slots) * MSDOS_SLOTS, GFP_NOFS); + slots = kmalloc_array(MSDOS_SLOTS, sizeof(*slots), GFP_NOFS); if (slots == NULL) return -ENOMEM; @@ -680,7 +676,7 @@ static int vfat_add_entry(struct inode *dir, struct qstr *qname, int is_dir, goto cleanup; /* update timestamp */ - dir->i_ctime = dir->i_mtime = dir->i_atime = *ts; + fat_truncate_time(dir, ts, S_CTIME|S_MTIME); if (IS_DIRSYNC(dir)) (void)fat_sync_inode(dir); else @@ -690,7 +686,7 @@ cleanup: return err; } -static int vfat_find(struct inode *dir, struct qstr *qname, +static int vfat_find(struct inode *dir, const struct qstr *qname, struct fat_slot_info *sinfo) { unsigned int len = vfat_striptail_len(qname); @@ -699,15 +695,6 @@ static int vfat_find(struct inode *dir, struct qstr *qname, return fat_search_long(dir, qname->name, len, sinfo); } -/* - * (nfsd's) anonymous disconnected dentry? - * NOTE: !IS_ROOT() is not anonymous (I.e. d_splice_alias() did the job). - */ -static int vfat_d_anon_disconn(struct dentry *dentry) -{ - return IS_ROOT(dentry) && (dentry->d_flags & DCACHE_DISCONNECTED); -} - static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags) { @@ -736,7 +723,11 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, } alias = d_find_alias(inode); - if (alias && !vfat_d_anon_disconn(alias)) { + /* + * 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 @@ -744,7 +735,6 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, * * Switch to new one for reason of locality if possible. */ - BUG_ON(d_unhashed(alias)); if (!S_ISDIR(inode->i_mode)) d_move(alias, dentry); iput(inode); @@ -755,33 +745,30 @@ static struct dentry *vfat_lookup(struct inode *dir, struct dentry *dentry, out: mutex_unlock(&MSDOS_SB(sb)->s_lock); - dentry->d_time = dentry->d_parent->d_inode->i_version; - dentry = d_splice_alias(inode, dentry); - if (dentry) - dentry->d_time = dentry->d_parent->d_inode->i_version; - return dentry; - + 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 inode *dir, struct dentry *dentry, umode_t mode, - bool excl) +static int vfat_create(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode, bool excl) { struct super_block *sb = dir->i_sb; struct inode *inode; struct fat_slot_info sinfo; - struct timespec ts; + struct timespec64 ts; int err; mutex_lock(&MSDOS_SB(sb)->s_lock); - ts = CURRENT_TIME_SEC; + ts = current_time(dir); err = vfat_add_entry(dir, &dentry->d_name, 0, 0, &ts, &sinfo); if (err) goto out; - dir->i_version++; + inode_inc_iversion(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); brelse(sinfo.bh); @@ -789,11 +776,8 @@ static int vfat_create(struct inode *dir, struct dentry *dentry, umode_t mode, err = PTR_ERR(inode); goto out; } - inode->i_version++; - inode->i_mtime = inode->i_atime = inode->i_ctime = ts; - /* timestamp is already written, so mark_inode_dirty() is unneeded. */ + inode_inc_iversion(inode); - dentry->d_time = dentry->d_parent->d_inode->i_version; d_instantiate(dentry, inode); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); @@ -802,7 +786,7 @@ out: static int vfat_rmdir(struct inode *dir, struct dentry *dentry) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; int err; @@ -822,8 +806,9 @@ static int vfat_rmdir(struct inode *dir, struct dentry *dentry) drop_nlink(dir); clear_nlink(inode); - inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; + 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); @@ -832,7 +817,7 @@ out: static int vfat_unlink(struct inode *dir, struct dentry *dentry) { - struct inode *inode = dentry->d_inode; + struct inode *inode = d_inode(dentry); struct super_block *sb = dir->i_sb; struct fat_slot_info sinfo; int err; @@ -847,25 +832,27 @@ static int vfat_unlink(struct inode *dir, struct dentry *dentry) if (err) goto out; clear_nlink(inode); - inode->i_mtime = inode->i_atime = CURRENT_TIME_SEC; + 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 inode *dir, struct dentry *dentry, umode_t mode) +static struct dentry *vfat_mkdir(struct mnt_idmap *idmap, struct inode *dir, + struct dentry *dentry, umode_t mode) { struct super_block *sb = dir->i_sb; struct inode *inode; struct fat_slot_info sinfo; - struct timespec ts; + struct timespec64 ts; int err, cluster; mutex_lock(&MSDOS_SB(sb)->s_lock); - ts = CURRENT_TIME_SEC; + ts = current_time(dir); cluster = fat_alloc_new_dir(dir, &ts); if (cluster < 0) { err = cluster; @@ -874,7 +861,7 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) err = vfat_add_entry(dir, &dentry->d_name, 1, cluster, &ts, &sinfo); if (err) goto out_free; - dir->i_version++; + inode_inc_iversion(dir); inc_nlink(dir); inode = fat_build_inode(sb, sinfo.de, sinfo.i_pos); @@ -884,54 +871,88 @@ static int vfat_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) /* the directory was completed, just return a error */ goto out; } - inode->i_version++; + inode_inc_iversion(inode); set_nlink(inode, 2); - inode->i_mtime = inode->i_atime = inode->i_ctime = ts; - /* timestamp is already written, so mark_inode_dirty() is unneeded. */ - dentry->d_time = dentry->d_parent->d_inode->i_version; d_instantiate(dentry, inode); mutex_unlock(&MSDOS_SB(sb)->s_lock); - return 0; + return NULL; out_free: fat_free_clusters(dir, cluster); out: mutex_unlock(&MSDOS_SB(sb)->s_lock); - return err; + return ERR_PTR(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; + struct msdos_dir_entry *dotdot_de = NULL; struct inode *old_inode, *new_inode; struct fat_slot_info old_sinfo, sinfo; - struct timespec ts; + struct timespec64 ts; loff_t new_i_pos; - int err, is_dir, update_dotdot, corrupt = 0; + int err, is_dir, corrupt = 0; struct super_block *sb = old_dir->i_sb; old_sinfo.bh = sinfo.bh = dotdot_bh = NULL; - old_inode = old_dentry->d_inode; - new_inode = new_dentry->d_inode; + 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; - 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; + if (old_dir != new_dir) { + err = vfat_get_dotdot_de(old_inode, &dotdot_bh, &dotdot_de); + if (err) goto out; - } } - ts = CURRENT_TIME_SEC; + 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); @@ -947,25 +968,19 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, goto out; new_i_pos = sinfo.i_pos; } - new_dir->i_version++; + inode_inc_iversion(new_dir); fat_detach(old_inode); fat_attach(old_inode, new_i_pos); - if (IS_DIRSYNC(new_dir)) { - err = fat_sync_inode(old_inode); - if (err) - goto error_inode; - } else - mark_inode_dirty(old_inode); + err = vfat_sync_ipos(new_dir, old_inode); + if (err) + goto error_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; - } + 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); @@ -975,18 +990,13 @@ static int vfat_rename(struct inode *old_dir, struct dentry *old_dentry, old_sinfo.bh = NULL; if (err) goto error_dotdot; - old_dir->i_version++; - old_dir->i_ctime = old_dir->i_mtime = ts; - if (IS_DIRSYNC(old_dir)) - (void)fat_sync_inode(old_dir); - else - mark_inode_dirty(old_dir); + vfat_update_dir_metadata(old_dir, &ts); if (new_inode) { drop_nlink(new_inode); if (is_dir) drop_nlink(new_inode); - new_inode->i_ctime = ts; + fat_truncate_time(new_inode, &ts, S_CTIME); } out: brelse(sinfo.bh); @@ -1000,10 +1010,9 @@ 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); + if (dotdot_de) { + corrupt |= vfat_update_dotdot_de(old_dir, old_inode, dotdot_bh, + dotdot_de); } error_inode: fat_detach(old_inode); @@ -1025,49 +1034,206 @@ error_inode: if (corrupt < 0) { fat_fs_error(new_dir->i_sb, "%s: Filesystem corrupted (i_pos %lld)", - __func__, sinfo.i_pos); + __func__, new_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 mnt_idmap *idmap, 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_rename, + .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; + set_default_d_op(sb, &vfat_ci_dentry_ops); else - sb->s_d_op = &vfat_dentry_ops; + set_default_d_op(sb, &vfat_dentry_ops); +} + +static int vfat_fill_super(struct super_block *sb, struct fs_context *fc) +{ + return fat_fill_super(sb, fc, setup); } -static int vfat_fill_super(struct super_block *sb, void *data, int silent) +static int vfat_get_tree(struct fs_context *fc) { - return fat_fill_super(sb, data, silent, 1, setup); + return get_tree_bdev(fc, vfat_fill_super); } -static struct dentry *vfat_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data) +static int vfat_parse_param(struct fs_context *fc, struct fs_parameter *param) { - return mount_bdev(fs_type, flags, dev_name, data, vfat_fill_super); + return fat_parse_param(fc, param, true); +} + +static const struct fs_context_operations vfat_context_ops = { + .parse_param = vfat_parse_param, + .get_tree = vfat_get_tree, + .reconfigure = fat_reconfigure, + .free = fat_free_fc, +}; + +static int vfat_init_fs_context(struct fs_context *fc) +{ + int err; + + /* Initialize with is_vfat == true */ + err = fat_init_fs_context(fc, true); + if (err) + return err; + + fc->ops = &vfat_context_ops; + return 0; } 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_flags = FS_REQUIRES_DEV | FS_ALLOW_IDMAP, + .init_fs_context = vfat_init_fs_context, + .parameters = fat_param_spec, }; MODULE_ALIAS_FS("vfat"); diff --git a/fs/fat/nfs.c b/fs/fat/nfs.c index 93e14933dcb6..509eea96a457 100644 --- a/fs/fat/nfs.c +++ b/fs/fat/nfs.c @@ -1,14 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only /* fs/fat/nfs.c - * - * This software is licensed under the terms of the GNU General Public - * License version 2, as published by the Free Software Foundation, and - * may be copied, distributed, and modified under those terms. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * */ #include <linux/exportfs.h> @@ -26,7 +17,7 @@ struct fat_fid { #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) @@ -139,12 +130,18 @@ fat_encode_fh_nostale(struct inode *inode, __u32 *fh, int *lenp, fid->parent_i_gen = parent->i_generation; type = FILEID_FAT_WITH_PARENT; *lenp = FAT_FID_SIZE_WITH_PARENT; + } else { + /* + * We need to initialize this field because the fh is actually + * 12 bytes long + */ + fid->parent_i_pos_hi = 0; } return type; } -/** +/* * Map a NFS file handle to a corresponding dentry. * The dentry may or may not be connected to the filesystem root. */ @@ -266,7 +263,7 @@ struct inode *fat_rebuild_parent(struct super_block *sb, int parent_logstart) * Find the parent for a directory that is not currently connected to * the filesystem root. * - * On entry, the caller holds child_dir->d_inode->i_mutex. + * On entry, the caller holds d_inode(child_dir)->i_mutex. */ static struct dentry *fat_get_parent(struct dentry *child_dir) { @@ -276,7 +273,7 @@ static struct dentry *fat_get_parent(struct dentry *child_dir) struct inode *parent_inode = NULL; struct msdos_sb_info *sbi = MSDOS_SB(sb); - if (!fat_get_dotdot_entry(child_dir->d_inode, &bh, &de)) { + 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) @@ -288,6 +285,7 @@ static struct dentry *fat_get_parent(struct dentry *child_dir) } const struct export_operations fat_export_ops = { + .encode_fh = generic_encode_ino32_fh, .fh_to_dentry = fat_fh_to_dentry, .fh_to_parent = fat_fh_to_parent, .get_parent = fat_get_parent, |
