diff options
| author | Kees Cook <kees+treewide@kernel.org> | 2026-09-02 15:31:14 -0700 |
|---|---|---|
| committer | Kees Cook <kees@kernel.org> | 2026-09-04 21:37:00 -0700 |
| commit | 3a2c4d55e32ad65efebdb6de44eef3bfa08bb49d (patch) | |
| tree | c65086f9bdcd48c6360fb7cb4598bca084da1f32 /fs/fat/inode.c | |
| download | linux-stable-3a2c4d55e32ad65efebdb6de44eef3bfa08bb49d.tar.gz linux-stable-3a2c4d55e32ad65efebdb6de44eef3bfa08bb49d.zip | |
treewide: refresh kmalloc_obj() conversionsgrafted
This is another run of the Coccinelle script for converting kmalloc()
family of allocations to kmalloc_obj() via the existing rules in
scripts/coccinelle/api/kmalloc_objs.cocci
This catches both the set of kmalloc() uses added since the first
kmalloc_obj() conversions in v7.0 and adds a large group missed in the
first pass due to Coccinelle not interacting well with the cleanup.h
scoped_...() family of macros[1]. I worked around this with spatch's
"--macro-file" argument to a file with all the scoped_...() macros mapped
to Coccinelle's YACFE_ITERATOR[2] as that was the closest viable control
flow indicator I could find.
Build tested allmodconfig on x86, arm64, arm, loongarch, mips, powerpc,
riscv, and s390 with no new warnings.
Link: https://lore.kernel.org/lkml/202609021314.8A9C0B8@keescook/ [1]
Link: https://github.com/coccinelle/coccinelle/blob/master/standard.h [2]
Signed-off-by: Kees Cook <kees+treewide@kernel.org>
Diffstat (limited to 'fs/fat/inode.c')
| -rw-r--r-- | fs/fat/inode.c | 2025 |
1 files changed, 2025 insertions, 0 deletions
diff --git a/fs/fat/inode.c b/fs/fat/inode.c new file mode 100644 index 000000000..f775a004c --- /dev/null +++ b/fs/fat/inode.c @@ -0,0 +1,2025 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/fs/fat/inode.c + * + * Written 1992,1993 by Werner Almesberger + * VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner + * Rewritten for the constant inumbers support by Al Viro + * + * Fixes: + * + * Max Cohan: Fixed invalid FSINFO offset when info_sector is 0 + */ + +#include <linux/module.h> +#include <linux/pagemap.h> +#include <linux/mpage.h> +#include <linux/vfs.h> +#include <linux/seq_file.h> +#include <linux/uio.h> +#include <linux/blkdev.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 +/* if user don't select VFAT, this is undefined. */ +#define CONFIG_FAT_DEFAULT_IOCHARSET "" +#endif + +#define KB_IN_SECTORS 2 + +/* DOS dates from 1980/1/1 through 2107/12/31 */ +#define FAT_DATE_MIN (0<<9 | 1<<5 | 1) +#define FAT_DATE_MAX (127<<9 | 12<<5 | 31) +#define FAT_TIME_MAX (23<<11 | 59<<5 | 29) + +/* + * A deserialized copy of the on-disk structure laid out in struct + * fat_boot_sector. + */ +struct fat_bios_param_block { + u16 fat_sector_size; + u8 fat_sec_per_clus; + u16 fat_reserved; + u8 fat_fats; + u16 fat_dir_entries; + u16 fat_sectors; + u16 fat_fat_length; + u32 fat_total_sect; + + u8 fat16_state; + u32 fat16_vol_id; + + u32 fat32_length; + u32 fat32_root_cluster; + u16 fat32_info_sector; + u8 fat32_state; + u32 fat32_vol_id; +}; + +static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE; +static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET; + +static struct fat_floppy_defaults { + unsigned nr_sectors; + unsigned sec_per_clus; + unsigned dir_entries; + unsigned media; + unsigned fat_length; +} floppy_defaults[] = { +{ + .nr_sectors = 160 * KB_IN_SECTORS, + .sec_per_clus = 1, + .dir_entries = 64, + .media = 0xFE, + .fat_length = 1, +}, +{ + .nr_sectors = 180 * KB_IN_SECTORS, + .sec_per_clus = 1, + .dir_entries = 64, + .media = 0xFC, + .fat_length = 2, +}, +{ + .nr_sectors = 320 * KB_IN_SECTORS, + .sec_per_clus = 2, + .dir_entries = 112, + .media = 0xFF, + .fat_length = 1, +}, +{ + .nr_sectors = 360 * KB_IN_SECTORS, + .sec_per_clus = 2, + .dir_entries = 112, + .media = 0xFD, + .fat_length = 2, +}, +}; + +int fat_add_cluster(struct inode *inode) +{ + int err, cluster; + + err = fat_alloc_clusters(inode, &cluster, 1); + if (err) + return err; + /* FIXME: this cluster should be added after data of this + * cluster is writed */ + err = fat_chain_add(inode, cluster, 1); + if (err) + fat_free_clusters(inode, cluster); + return err; +} + +static inline int __fat_get_block(struct inode *inode, sector_t iblock, + unsigned long *max_blocks, + struct buffer_head *bh_result, int create) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + unsigned long mapped_blocks; + sector_t phys, last_block; + int err, offset; + + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); + if (err) + return err; + if (phys) { + map_bh(bh_result, sb, phys); + *max_blocks = min(mapped_blocks, *max_blocks); + return 0; + } + if (!create) + return 0; + + if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) { + fat_fs_error(sb, "corrupted file size (i_pos %lld, %lld)", + MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private); + return -EIO; + } + + last_block = inode->i_blocks >> (sb->s_blocksize_bits - 9); + offset = (unsigned long)iblock & (sbi->sec_per_clus - 1); + /* + * allocate a cluster according to the following. + * 1) no more available blocks + * 2) not part of fallocate region + */ + if (!offset && !(iblock < last_block)) { + /* TODO: multiple cluster allocation would be desirable. */ + err = fat_add_cluster(inode); + if (err) + return err; + } + /* available blocks on this cluster */ + mapped_blocks = sbi->sec_per_clus - offset; + + *max_blocks = min(mapped_blocks, *max_blocks); + MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits; + + err = fat_bmap(inode, iblock, &phys, &mapped_blocks, create, false); + if (err) + return err; + if (!phys) { + fat_fs_error(sb, + "invalid FAT chain (i_pos %lld, last_block %llu)", + MSDOS_I(inode)->i_pos, + (unsigned long long)last_block); + return -EIO; + } + + BUG_ON(*max_blocks != mapped_blocks); + set_buffer_new(bh_result); + map_bh(bh_result, sb, phys); + + return 0; +} + +static int fat_get_block(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + struct super_block *sb = inode->i_sb; + unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; + int err; + + err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create); + if (err) + return err; + bh_result->b_size = max_blocks << sb->s_blocksize_bits; + return 0; +} + +static int fat_writepages(struct address_space *mapping, + struct writeback_control *wbc) +{ + return mpage_writepages(mapping, wbc, fat_get_block); +} + +static int fat_read_folio(struct file *file, struct folio *folio) +{ + return mpage_read_folio(folio, fat_get_block); +} + +static void fat_readahead(struct readahead_control *rac) +{ + mpage_readahead(rac, fat_get_block); +} + +static void fat_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, inode->i_size); + fat_truncate_blocks(inode, inode->i_size); + } +} + +static int fat_write_begin(const struct kiocb *iocb, + struct address_space *mapping, + loff_t pos, unsigned len, + struct folio **foliop, void **fsdata) +{ + int err; + + 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(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(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)) { + fat_truncate_time(inode, NULL, FAT_UPDATE_CMTIME); + MSDOS_I(inode)->i_attrs |= ATTR_ARCH; + mark_inode_dirty(inode); + } + return err; +} + +static ssize_t fat_direct_IO(struct kiocb *iocb, struct iov_iter *iter) +{ + struct file *file = iocb->ki_filp; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + size_t count = iov_iter_count(iter); + loff_t offset = iocb->ki_pos; + ssize_t ret; + + if (iov_iter_rw(iter) == WRITE) { + /* + * FIXME: blockdev_direct_IO() doesn't use ->write_begin(), + * so we need to update the ->mmu_private to block boundary. + * + * But we must fill the remaining area or hole by nul for + * updating ->mmu_private. + * + * Return 0, and fallback to normal buffered write. + */ + loff_t size = offset + count; + if (MSDOS_I(inode)->mmu_private < size) + return 0; + } + + /* + * FAT need to use the DIO_LOCKING for avoiding the race + * condition of fat_get_block() and ->truncate(). + */ + ret = blockdev_direct_IO(iocb, inode, iter, fat_get_block); + if (ret < 0 && iov_iter_rw(iter) == WRITE) + fat_write_failed(mapping, offset + count); + + return ret; +} + +static int fat_get_block_bmap(struct inode *inode, sector_t iblock, + struct buffer_head *bh_result, int create) +{ + struct super_block *sb = inode->i_sb; + unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits; + int err; + sector_t bmap; + unsigned long mapped_blocks; + + BUG_ON(create != 0); + + err = fat_bmap(inode, iblock, &bmap, &mapped_blocks, create, true); + if (err) + return err; + + if (bmap) { + map_bh(bh_result, sb, bmap); + max_blocks = min(mapped_blocks, max_blocks); + } + + bh_result->b_size = max_blocks << sb->s_blocksize_bits; + + return 0; +} + +static sector_t _fat_bmap(struct address_space *mapping, sector_t block) +{ + sector_t blocknr; + + /* fat_get_cluster() assumes the requested blocknr isn't truncated. */ + down_read(&MSDOS_I(mapping->host)->truncate_lock); + blocknr = generic_block_bmap(mapping, block, fat_get_block_bmap); + up_read(&MSDOS_I(mapping->host)->truncate_lock); + + return blocknr; +} + +/* + * fat_block_truncate_page() zeroes out a mapping from file offset `from' + * up to the end of the block which corresponds to `from'. + * This is required during truncate to physically zeroout the tail end + * of that block so it doesn't yield old data if the file is later grown. + * Also, avoid causing failure from fsx for cases of "data past EOF" + */ +int fat_block_truncate_page(struct inode *inode, loff_t from) +{ + return block_truncate_page(inode->i_mapping, from, fat_get_block); +} + +static const struct address_space_operations fat_aops = { + .dirty_folio = block_dirty_folio, + .invalidate_folio = block_invalidate_folio, + .read_folio = fat_read_folio, + .readahead = fat_readahead, + .writepages = fat_writepages, + .write_begin = fat_write_begin, + .write_end = fat_write_end, + .direct_IO = fat_direct_IO, + .bmap = _fat_bmap, + .migrate_folio = buffer_migrate_folio, +}; + +/* + * New FAT inode stuff. We do the following: + * a) i_ino is constant and has nothing with on-disk location. + * b) FAT manages its own cache of directory entries. + * c) *This* cache is indexed by on-disk location. + * d) inode has an associated directory entry, all right, but + * it may be unhashed. + * e) currently entries are stored within struct inode. That should + * change. + * f) we deal with races in the following way: + * 1. readdir() and lookup() do FAT-dir-cache lookup. + * 2. rename() unhashes the F-d-c entry and rehashes it in + * a new place. + * 3. unlink() and rmdir() unhash F-d-c entry. + * 4. fat_write_inode() checks whether the thing is unhashed. + * If it is we silently return. If it isn't we do bread(), + * check if the location is still valid and retry if it + * isn't. Otherwise we do changes. + * 5. Spinlock is used to protect hash/unhash/location check/lookup + * 6. fat_evict_inode() unhashes the F-d-c entry. + * 7. lookup() and readdir() do igrab() if they find a F-d-c entry + * and consider negative result as cache miss. + */ + +static void fat_hash_init(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int i; + + spin_lock_init(&sbi->inode_hash_lock); + for (i = 0; i < FAT_HASH_SIZE; i++) + INIT_HLIST_HEAD(&sbi->inode_hashtable[i]); +} + +static inline unsigned long fat_hash(loff_t i_pos) +{ + return hash_32(i_pos, FAT_HASH_BITS); +} + +static void dir_hash_init(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + int i; + + spin_lock_init(&sbi->dir_hash_lock); + for (i = 0; i < FAT_HASH_SIZE; i++) + INIT_HLIST_HEAD(&sbi->dir_hashtable[i]); +} + +void fat_attach(struct inode *inode, loff_t i_pos) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + + if (inode->i_ino != MSDOS_ROOT_INO) { + struct hlist_head *head = sbi->inode_hashtable + + fat_hash(i_pos); + + spin_lock(&sbi->inode_hash_lock); + MSDOS_I(inode)->i_pos = i_pos; + hlist_add_head(&MSDOS_I(inode)->i_fat_hash, head); + spin_unlock(&sbi->inode_hash_lock); + } + + /* If NFS support is enabled, cache the mapping of start cluster + * to directory inode. This is used during reconnection of + * dentries to the filesystem root. + */ + if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { + struct hlist_head *d_head = sbi->dir_hashtable; + d_head += fat_dir_hash(MSDOS_I(inode)->i_logstart); + + spin_lock(&sbi->dir_hash_lock); + hlist_add_head(&MSDOS_I(inode)->i_dir_hash, d_head); + spin_unlock(&sbi->dir_hash_lock); + } +} +EXPORT_SYMBOL_GPL(fat_attach); + +void fat_detach(struct inode *inode) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + spin_lock(&sbi->inode_hash_lock); + MSDOS_I(inode)->i_pos = 0; + hlist_del_init(&MSDOS_I(inode)->i_fat_hash); + spin_unlock(&sbi->inode_hash_lock); + + if (S_ISDIR(inode->i_mode) && sbi->options.nfs) { + spin_lock(&sbi->dir_hash_lock); + hlist_del_init(&MSDOS_I(inode)->i_dir_hash); + spin_unlock(&sbi->dir_hash_lock); + } +} +EXPORT_SYMBOL_GPL(fat_detach); + +struct inode *fat_iget(struct super_block *sb, loff_t i_pos) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct hlist_head *head = sbi->inode_hashtable + fat_hash(i_pos); + struct msdos_inode_info *i; + struct inode *inode = NULL; + + spin_lock(&sbi->inode_hash_lock); + hlist_for_each_entry(i, head, i_fat_hash) { + BUG_ON(i->vfs_inode.i_sb != sb); + if (i->i_pos != i_pos) + continue; + inode = igrab(&i->vfs_inode); + if (inode) + break; + } + spin_unlock(&sbi->inode_hash_lock); + return inode; +} + +static int is_exec(unsigned char *extension) +{ + unsigned char exe_extensions[] = "EXECOMBAT", *walk; + + for (walk = exe_extensions; *walk; walk += 3) + if (!strncmp(extension, walk, 3)) + return 1; + return 0; +} + +static int fat_calc_dir_size(struct inode *inode) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + int ret, fclus, dclus; + + inode->i_size = 0; + if (MSDOS_I(inode)->i_start == 0) + return 0; + + ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus); + if (ret < 0) + return ret; + inode->i_size = (fclus + 1) << sbi->cluster_bits; + + return 0; +} + +static int fat_validate_dir(struct inode *dir) +{ + struct super_block *sb = dir->i_sb; + + if (dir->i_nlink < 2) { + /* Directory should have "."/".." entries at least. */ + fat_fs_error(sb, "corrupted directory (invalid entries)"); + return -EIO; + } + if (MSDOS_I(dir)->i_start == 0 || + MSDOS_I(dir)->i_start == MSDOS_SB(sb)->root_cluster) { + /* Directory should point valid cluster. */ + fat_fs_error(sb, "corrupted directory (invalid i_start)"); + return -EIO; + } + return 0; +} + +/* doesn't deal with root inode */ +int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + 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_inc_iversion(inode); + inode->i_generation = get_random_u32(); + + if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) { + inode->i_generation &= ~1; + inode->i_mode = fat_make_mode(sbi, de->attr, S_IRWXUGO); + inode->i_op = sbi->dir_ops; + inode->i_fop = &fat_dir_operations; + + MSDOS_I(inode)->i_start = fat_get_start(sbi, de); + MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; + error = fat_calc_dir_size(inode); + if (error < 0) + return error; + MSDOS_I(inode)->mmu_private = inode->i_size; + + set_nlink(inode, fat_subdirs(inode)); + + error = fat_validate_dir(inode); + if (error < 0) + return error; + } else { /* not a directory */ + inode->i_generation |= 1; + inode->i_mode = fat_make_mode(sbi, de->attr, + ((sbi->options.showexec && !is_exec(de->name + 8)) + ? S_IRUGO|S_IWUGO : S_IRWXUGO)); + MSDOS_I(inode)->i_start = fat_get_start(sbi, de); + + MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start; + inode->i_size = le32_to_cpu(de->size); + inode->i_op = &fat_file_inode_operations; + inode->i_fop = &fat_file_operations; + inode->i_mapping->a_ops = &fat_aops; + MSDOS_I(inode)->mmu_private = inode->i_size; + } + if (de->attr & ATTR_SYS) { + if (sbi->options.sys_immutable) + inode->i_flags |= S_IMMUTABLE; + } + fat_save_attrs(inode, de->attr); + + inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) + & ~((loff_t)sbi->cluster_size - 1)) >> 9; + + fat_time_fat2unix(sbi, &mtime, de->time, de->date, 0); + inode_set_mtime_to_ts(inode, mtime); + inode_set_ctime_to_ts(inode, mtime); + if (sbi->options.isvfat) { + 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); + } else + inode_set_atime_to_ts(inode, fat_truncate_atime(sbi, &mtime)); + + return 0; +} + +static inline void fat_lock_build_inode(struct msdos_sb_info *sbi) +{ + if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) + mutex_lock(&sbi->nfs_build_inode_lock); +} + +static inline void fat_unlock_build_inode(struct msdos_sb_info *sbi) +{ + if (sbi->options.nfs == FAT_NFS_NOSTALE_RO) + mutex_unlock(&sbi->nfs_build_inode_lock); +} + +struct inode *fat_build_inode(struct super_block *sb, + struct msdos_dir_entry *de, loff_t i_pos) +{ + struct inode *inode; + int err; + + fat_lock_build_inode(MSDOS_SB(sb)); + inode = fat_iget(sb, i_pos); + if (inode) + goto out; + inode = new_inode(sb); + if (!inode) { + inode = ERR_PTR(-ENOMEM); + goto out; + } + inode->i_ino = iunique(sb, MSDOS_ROOT_INO); + inode_set_iversion(inode, 1); + err = fat_fill_inode(inode, de); + if (err) { + iput(inode); + inode = ERR_PTR(err); + goto out; + } + fat_attach(inode, i_pos); + insert_inode_hash(inode); +out: + fat_unlock_build_inode(MSDOS_SB(sb)); + return inode; +} + +EXPORT_SYMBOL_GPL(fat_build_inode); + +static int __fat_write_inode(struct inode *inode); + +static int fat_sync_inode_metadata(struct inode *inode, + struct writeback_control *wbc) +{ + struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + struct buffer_head *bh; + loff_t i_pos; + sector_t blocknr; + int offset; + + /* The root directory has no directory entry of its own. */ + if (inode->i_ino == MSDOS_ROOT_INO) + goto sync_bhs; + i_pos = fat_i_pos_read(sbi, inode); + if (!i_pos) + goto sync_bhs; + + fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); + bh = sb_find_get_block_nonatomic(inode->i_sb, blocknr); + /* + * Buffer present? We leave buffer_dirty check for sync_dirty_buffer() + * for proper synchronization with ongoing IO. + */ + if (bh && buffer_uptodate(bh)) { + sync_dirty_buffer(bh); + if (buffer_write_io_error(bh)) { + brelse(bh); + return -EIO; + } + } + brelse(bh); +sync_bhs: + return mmb_sync(&MSDOS_I(inode)->i_metadata_bhs); +} + +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 = sync_inode_metadata(inode, inode_needs_sync(inode)); + if (err) { + fat_msg(inode->i_sb, KERN_WARNING, "Failed to " + "update on disk inode for unused " + "fallocated blocks, inode could be " + "corrupted. Please run fsck"); + } + + } +} + +static void fat_evict_inode(struct inode *inode) +{ + truncate_inode_pages_final(&inode->i_data); + if (!inode->i_nlink) { + inode->i_size = 0; + fat_truncate_blocks(inode, 0); + } else { + mmb_sync(&MSDOS_I(inode)->i_metadata_bhs); + fat_free_eofblocks(inode); + } + + mmb_invalidate(&MSDOS_I(inode)->i_metadata_bhs); + clear_inode(inode); + fat_cache_inval_inode(inode); + fat_detach(inode); +} + +static void fat_set_state(struct super_block *sb, + unsigned int set, unsigned int force) +{ + struct buffer_head *bh; + struct fat_boot_sector *b; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + /* do not change any thing if mounted read only */ + if (sb_rdonly(sb) && !force) + return; + + /* do not change state if fs was dirty */ + if (sbi->dirty) { + /* warn only on set (mount). */ + if (set) + fat_msg(sb, KERN_WARNING, "Volume was not properly " + "unmounted. Some data may be corrupt. " + "Please run fsck."); + return; + } + + bh = sb_bread(sb, 0); + if (bh == NULL) { + fat_msg(sb, KERN_ERR, "unable to read boot sector " + "to mark fs as dirty"); + return; + } + + b = (struct fat_boot_sector *) bh->b_data; + + if (is_fat32(sbi)) { + if (set) + b->fat32.state |= FAT_STATE_DIRTY; + else + b->fat32.state &= ~FAT_STATE_DIRTY; + } else /* fat 16 and 12 */ { + if (set) + b->fat16.state |= FAT_STATE_DIRTY; + else + b->fat16.state &= ~FAT_STATE_DIRTY; + } + + mark_buffer_dirty(bh); + sync_dirty_buffer(bh); + brelse(bh); +} + +static void fat_reset_iocharset(struct fat_mount_options *opts) +{ + if (opts->iocharset != fat_default_iocharset) { + /* Note: opts->iocharset can be NULL here */ + kfree(opts->iocharset); + opts->iocharset = fat_default_iocharset; + } +} + +static void delayed_free(struct rcu_head *p) +{ + struct msdos_sb_info *sbi = container_of(p, struct msdos_sb_info, rcu); + unload_nls(sbi->nls_disk); + unload_nls(sbi->nls_io); + fat_reset_iocharset(&sbi->options); + kfree(sbi); +} + +static void fat_put_super(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + fat_set_state(sb, 0, 0); + + iput(sbi->fsinfo_inode); + iput(sbi->fat_inode); + + call_rcu(&sbi->rcu, delayed_free); +} + +static struct kmem_cache *fat_inode_cachep; + +static struct inode *fat_alloc_inode(struct super_block *sb) +{ + struct msdos_inode_info *ei; + ei = alloc_inode_sb(sb, fat_inode_cachep, GFP_NOFS); + if (!ei) + return NULL; + + init_rwsem(&ei->truncate_lock); + /* Zeroing to allow iput() even if partial initialized inode. */ + ei->mmu_private = 0; + ei->i_start = 0; + ei->i_logstart = 0; + ei->i_attrs = 0; + ei->i_pos = 0; + ei->i_crtime.tv_sec = 0; + ei->i_crtime.tv_nsec = 0; + mmb_init(&ei->i_metadata_bhs, &ei->vfs_inode.i_data); + + return &ei->vfs_inode; +} + +static void fat_free_inode(struct inode *inode) +{ + kmem_cache_free(fat_inode_cachep, MSDOS_I(inode)); +} + +static void init_once(void *foo) +{ + struct msdos_inode_info *ei = (struct msdos_inode_info *)foo; + + spin_lock_init(&ei->cache_lru_lock); + ei->nr_caches = 0; + ei->cache_valid_id = FAT_CACHE_VALID + 1; + INIT_LIST_HEAD(&ei->cache_lru); + INIT_HLIST_NODE(&ei->i_fat_hash); + INIT_HLIST_NODE(&ei->i_dir_hash); + inode_init_once(&ei->vfs_inode); +} + +static int __init fat_init_inodecache(void) +{ + fat_inode_cachep = kmem_cache_create("fat_inode_cache", + sizeof(struct msdos_inode_info), + 0, (SLAB_RECLAIM_ACCOUNT| + SLAB_ACCOUNT), + init_once); + if (fat_inode_cachep == NULL) + return -ENOMEM; + return 0; +} + +static void __exit fat_destroy_inodecache(void) +{ + /* + * Make sure all delayed rcu free inodes are flushed before we + * destroy cache. + */ + rcu_barrier(); + kmem_cache_destroy(fat_inode_cachep); +} + +int fat_reconfigure(struct fs_context *fc) +{ + bool new_rdonly; + struct super_block *sb = fc->root->d_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + fc->sb_flags |= SB_NODIRATIME | (sbi->options.isvfat ? 0 : SB_NOATIME); + + sync_filesystem(sb); + + /* make sure we update state on remount. */ + new_rdonly = fc->sb_flags & SB_RDONLY; + if (new_rdonly != sb_rdonly(sb)) { + if (new_rdonly) + fat_set_state(sb, 0, 0); + else + fat_set_state(sb, 1, 1); + } + return 0; +} +EXPORT_SYMBOL_GPL(fat_reconfigure); + +static int fat_statfs(struct dentry *dentry, struct kstatfs *buf) +{ + struct super_block *sb = dentry->d_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + u64 id = huge_encode_dev(sb->s_bdev->bd_dev); + + /* If the count of free cluster is still unknown, counts it here. */ + if (sbi->free_clusters == -1 || !sbi->free_clus_valid) { + int err = fat_count_free_clusters(dentry->d_sb); + if (err) + return err; + } + + buf->f_type = dentry->d_sb->s_magic; + buf->f_bsize = sbi->cluster_size; + buf->f_blocks = sbi->max_cluster - FAT_START_ENT; + buf->f_bfree = sbi->free_clusters; + buf->f_bavail = sbi->free_clusters; + buf->f_fsid = u64_to_fsid(id); + buf->f_namelen = + (sbi->options.isvfat ? FAT_LFN_LEN : 12) * NLS_MAX_CHARSET_SIZE; + + return 0; +} + +static int __fat_write_inode(struct inode *inode) +{ + struct super_block *sb = inode->i_sb; + struct msdos_sb_info *sbi = MSDOS_SB(sb); + struct buffer_head *bh; + struct msdos_dir_entry *raw_entry; + struct timespec64 mtime; + loff_t i_pos; + sector_t blocknr; + int offset; + + if (inode->i_ino == MSDOS_ROOT_INO) { + /* No entry to update but the metadata bh list may need syncing. */ + set_inode_metadata_writeback(inode); + return 0; + } + +retry: + i_pos = fat_i_pos_read(sbi, inode); + if (!i_pos) + return 0; + + fat_get_blknr_offset(sbi, i_pos, &blocknr, &offset); + bh = sb_bread(sb, blocknr); + if (!bh) { + fat_msg(sb, KERN_ERR, "unable to read inode block " + "for updating (i_pos %lld)", i_pos); + return -EIO; + } + spin_lock(&sbi->inode_hash_lock); + if (i_pos != MSDOS_I(inode)->i_pos) { + spin_unlock(&sbi->inode_hash_lock); + brelse(bh); + goto retry; + } + + raw_entry = &((struct msdos_dir_entry *) (bh->b_data))[offset]; + if (S_ISDIR(inode->i_mode)) + raw_entry->size = 0; + else + raw_entry->size = cpu_to_le32(inode->i_size); + raw_entry->attr = fat_make_attrs(inode); + fat_set_start(raw_entry, MSDOS_I(inode)->i_logstart); + 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, &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); + } + spin_unlock(&sbi->inode_hash_lock); + mark_buffer_dirty(bh); + brelse(bh); + set_inode_metadata_writeback(inode); + return 0; +} + +static int fat_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + int err; + + if (inode->i_ino == MSDOS_FSINFO_INO) { + struct super_block *sb = inode->i_sb; + + mutex_lock(&MSDOS_SB(sb)->s_lock); + err = fat_clusters_flush(sb); + mutex_unlock(&MSDOS_SB(sb)->s_lock); + } else + err = __fat_write_inode(inode); + + return err; +} + +static int fat_show_options(struct seq_file *m, struct dentry *root); +static const struct super_operations fat_sops = { + .alloc_inode = fat_alloc_inode, + .free_inode = fat_free_inode, + .write_inode = fat_write_inode, + .sync_inode_metadata = fat_sync_inode_metadata, + .evict_inode = fat_evict_inode, + .put_super = fat_put_super, + .statfs = fat_statfs, + .show_options = fat_show_options, +}; + +static int fat_show_options(struct seq_file *m, struct dentry *root) +{ + struct msdos_sb_info *sbi = MSDOS_SB(root->d_sb); + struct fat_mount_options *opts = &sbi->options; + int isvfat = opts->isvfat; + + if (!uid_eq(opts->fs_uid, GLOBAL_ROOT_UID)) + seq_printf(m, ",uid=%u", + from_kuid_munged(&init_user_ns, opts->fs_uid)); + if (!gid_eq(opts->fs_gid, GLOBAL_ROOT_GID)) + seq_printf(m, ",gid=%u", + from_kgid_munged(&init_user_ns, opts->fs_gid)); + seq_printf(m, ",fmask=%04o", opts->fs_fmask); + seq_printf(m, ",dmask=%04o", opts->fs_dmask); + if (opts->allow_utime) + seq_printf(m, ",allow_utime=%04o", opts->allow_utime); + if (sbi->nls_disk) + /* strip "cp" prefix from displayed option */ + seq_printf(m, ",codepage=%s", &sbi->nls_disk->charset[2]); + if (isvfat) { + if (sbi->nls_io) + seq_printf(m, ",iocharset=%s", sbi->nls_io->charset); + + switch (opts->shortname) { + case VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95: + seq_puts(m, ",shortname=win95"); + break; + case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT: + seq_puts(m, ",shortname=winnt"); + break; + case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95: + seq_puts(m, ",shortname=mixed"); + break; + case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95: + seq_puts(m, ",shortname=lower"); + break; + default: + seq_puts(m, ",shortname=unknown"); + break; + } + } + if (opts->name_check != 'n') + seq_printf(m, ",check=%c", opts->name_check); + if (opts->usefree) + seq_puts(m, ",usefree"); + if (opts->quiet) + seq_puts(m, ",quiet"); + if (opts->showexec) + seq_puts(m, ",showexec"); + if (opts->sys_immutable) + seq_puts(m, ",sys_immutable"); + if (!isvfat) { + if (opts->dotsOK) + seq_puts(m, ",dotsOK=yes"); + if (opts->nocase) + seq_puts(m, ",nocase"); + } else { + if (opts->utf8) + seq_puts(m, ",utf8"); + if (opts->unicode_xlate) + seq_puts(m, ",uni_xlate"); + if (!opts->numtail) + seq_puts(m, ",nonumtail"); + if (opts->rodir) + seq_puts(m, ",rodir"); + } + if (opts->flush) + seq_puts(m, ",flush"); + if (opts->tz_set) { + if (opts->time_offset) + seq_printf(m, ",time_offset=%d", opts->time_offset); + else + seq_puts(m, ",tz=UTC"); + } + if (opts->errors == FAT_ERRORS_CONT) + seq_puts(m, ",errors=continue"); + else if (opts->errors == FAT_ERRORS_PANIC) + seq_puts(m, ",errors=panic"); + else + seq_puts(m, ",errors=remount-ro"); + if (opts->nfs == FAT_NFS_NOSTALE_RO) + seq_puts(m, ",nfs=nostale_ro"); + else if (opts->nfs) + seq_puts(m, ",nfs=stale_rw"); + if (opts->discard) + seq_puts(m, ",discard"); + if (opts->dos1xfloppy) + seq_puts(m, ",dos1xfloppy"); + + return 0; +} + +enum { + Opt_check, 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 struct constant_table fat_param_check[] = { + {"relaxed", 'r'}, + {"r", 'r'}, + {"strict", 's'}, + {"s", 's'}, + {"normal", 'n'}, + {"n", 'n'}, + {} +}; + +static const struct constant_table fat_param_tz[] = { + {"UTC", 0}, + {} +}; + +static const struct constant_table fat_param_errors[] = { + {"continue", FAT_ERRORS_CONT}, + {"panic", FAT_ERRORS_PANIC}, + {"remount-ro", FAT_ERRORS_RO}, + {} +}; + + +static const struct constant_table fat_param_nfs[] = { + {"stale_rw", FAT_NFS_STALE_RW}, + {"nostale_ro", FAT_NFS_NOSTALE_RO}, + {} +}; + +/* + * 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}, + {} +}; + +/* 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); + +static const struct fs_parameter_spec msdos_param_spec[] = { + fsparam_flag_no ("dots", Opt_dots), + fsparam_bool ("dotsOK", Opt_dotsOK), + {} +}; + +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}, + {} +}; + +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), + {} +}; + +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; + + /* remount options have traditionally been ignored */ + if (fc->purpose == FS_CONTEXT_FOR_RECONFIGURE) + return 0; + + 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 (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 msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); + int error; + + MSDOS_I(inode)->i_pos = MSDOS_ROOT_INO; + inode->i_uid = sbi->options.fs_uid; + inode->i_gid = sbi->options.fs_gid; + inode_inc_iversion(inode); + inode->i_generation = 0; + inode->i_mode = fat_make_mode(sbi, ATTR_DIR, S_IRWXUGO); + inode->i_op = sbi->dir_ops; + inode->i_fop = &fat_dir_operations; + if (is_fat32(sbi)) { + MSDOS_I(inode)->i_start = sbi->root_cluster; + error = fat_calc_dir_size(inode); + if (error < 0) + return error; + } else { + MSDOS_I(inode)->i_start = 0; + inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry); + } + inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1)) + & ~((loff_t)sbi->cluster_size - 1)) >> 9; + MSDOS_I(inode)->i_logstart = 0; + MSDOS_I(inode)->mmu_private = inode->i_size; + + fat_save_attrs(inode, ATTR_DIR); + inode_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; +} + +static unsigned long calc_fat_clusters(struct super_block *sb) +{ + struct msdos_sb_info *sbi = MSDOS_SB(sb); + + /* Divide first to avoid overflow */ + if (!is_fat12(sbi)) { + unsigned long ent_per_sec = sb->s_blocksize * 8 / sbi->fat_bits; + return ent_per_sec * sbi->fat_length; + } + + return sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits; +} + +static bool fat_bpb_is_zero(struct fat_boot_sector *b) +{ + if (get_unaligned_le16(&b->sector_size)) + return false; + if (b->sec_per_clus) + return false; + if (b->reserved) + return false; + if (b->fats) + return false; + if (get_unaligned_le16(&b->dir_entries)) + return false; + if (get_unaligned_le16(&b->sectors)) + return false; + if (b->media) + return false; + if (b->fat_length) + return false; + if (b->secs_track) + return false; + if (b->heads) + return false; + return true; +} + +static int fat_read_bpb(struct super_block *sb, struct fat_boot_sector *b, + int silent, struct fat_bios_param_block *bpb) +{ + int error = -EINVAL; + + /* Read in BPB ... */ + memset(bpb, 0, sizeof(*bpb)); + bpb->fat_sector_size = get_unaligned_le16(&b->sector_size); + bpb->fat_sec_per_clus = b->sec_per_clus; + bpb->fat_reserved = le16_to_cpu(b->reserved); + bpb->fat_fats = b->fats; + bpb->fat_dir_entries = get_unaligned_le16(&b->dir_entries); + bpb->fat_sectors = get_unaligned_le16(&b->sectors); + bpb->fat_fat_length = le16_to_cpu(b->fat_length); + bpb->fat_total_sect = le32_to_cpu(b->total_sect); + + bpb->fat16_state = b->fat16.state; + bpb->fat16_vol_id = get_unaligned_le32(b->fat16.vol_id); + + bpb->fat32_length = le32_to_cpu(b->fat32.length); + bpb->fat32_root_cluster = le32_to_cpu(b->fat32.root_cluster); + bpb->fat32_info_sector = le16_to_cpu(b->fat32.info_sector); + bpb->fat32_state = b->fat32.state; + bpb->fat32_vol_id = get_unaligned_le32(b->fat32.vol_id); + + /* Validate this looks like a FAT filesystem BPB */ + if (!bpb->fat_reserved) { + if (!silent) + fat_msg(sb, KERN_ERR, + "bogus number of reserved sectors"); + goto out; + } + if (!bpb->fat_fats) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of FAT structure"); + goto out; + } + + /* + * Earlier we checked here that b->secs_track and b->head are nonzero, + * but it turns out valid FAT filesystems can have zero there. + */ + + if (!fat_valid_media(b->media)) { + if (!silent) + fat_msg(sb, KERN_ERR, "invalid media value (0x%02x)", + (unsigned)b->media); + goto out; + } + + if (!is_power_of_2(bpb->fat_sector_size) + || (bpb->fat_sector_size < 512) + || (bpb->fat_sector_size > 4096)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus logical sector size %u", + (unsigned)bpb->fat_sector_size); + goto out; + } + + if (!is_power_of_2(bpb->fat_sec_per_clus)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus sectors per cluster %u", + (unsigned)bpb->fat_sec_per_clus); + goto out; + } + + if (bpb->fat_fat_length == 0 && bpb->fat32_length == 0) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of FAT sectors"); + goto out; + } + + error = 0; + +out: + return error; +} + +static int fat_read_static_bpb(struct super_block *sb, + struct fat_boot_sector *b, int silent, + struct fat_bios_param_block *bpb) +{ + static const char *notdos1x = "This doesn't look like a DOS 1.x volume"; + sector_t bd_sects = bdev_nr_sectors(sb->s_bdev); + struct fat_floppy_defaults *fdefaults = NULL; + int error = -EINVAL; + unsigned i; + + /* 16-bit DOS 1.x reliably wrote bootstrap short-jmp or near-jmp code */ + if ((b->ignored[0] != 0xeb || b->ignored[2] != 0x90) && + (b->ignored[0] != 0xe9)) { + 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, 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_bios_param_block bpb; + struct msdos_sb_info *sbi; + u16 logical_sector_size; + u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors; + long error; + char buf[50]; + struct timespec64 ts; + + /* + * GFP_KERNEL is ok here, because while we do hold the + * superblock lock, memory pressure can't call back into + * the filesystem, since we're only just about to mount + * it and have no inodes etc active! + */ + sbi = kzalloc_obj(struct msdos_sb_info); + if (!sbi) + return -ENOMEM; + sb->s_fs_info = sbi; + + sb->s_flags |= SB_NODIRATIME; + sb->s_magic = MSDOS_SUPER_MAGIC; + sb->s_op = &fat_sops; + sb->s_export_op = &fat_export_ops; + /* + * fat timestamps are complex and truncated by fat itself, so + * we set 1 here to be fast + */ + sb->s_time_gran = 1; + mutex_init(&sbi->nfs_build_inode_lock); + ratelimit_state_init(&sbi->ratelimit, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); + + /* 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; + bh = sb_bread(sb, 0); + if (bh == NULL) { + fat_msg(sb, KERN_ERR, "unable to read boot sector"); + goto out_fail; + } + + error = fat_read_bpb(sb, (struct fat_boot_sector *)bh->b_data, silent, + &bpb); + if (error == -EINVAL && sbi->options.dos1xfloppy) + error = fat_read_static_bpb(sb, + (struct fat_boot_sector *)bh->b_data, silent, &bpb); + brelse(bh); + + if (error == -EINVAL) + goto out_invalid; + else if (error) + goto out_fail; + + logical_sector_size = bpb.fat_sector_size; + sbi->sec_per_clus = bpb.fat_sec_per_clus; + + error = -EIO; + if (logical_sector_size < sb->s_blocksize) { + fat_msg(sb, KERN_ERR, "logical sector size too small for device" + " (logical sector size = %u)", logical_sector_size); + goto out_fail; + } + + if (logical_sector_size > sb->s_blocksize) { + struct buffer_head *bh_resize; + + if (!sb_set_blocksize(sb, logical_sector_size)) { + fat_msg(sb, KERN_ERR, "unable to set blocksize %u", + logical_sector_size); + goto out_fail; + } + + /* Verify that the larger boot sector is fully readable */ + bh_resize = sb_bread(sb, 0); + if (bh_resize == NULL) { + fat_msg(sb, KERN_ERR, "unable to read boot sector" + " (logical sector size = %lu)", + sb->s_blocksize); + goto out_fail; + } + brelse(bh_resize); + } + + mutex_init(&sbi->s_lock); + sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus; + sbi->cluster_bits = ffs(sbi->cluster_size) - 1; + sbi->fats = bpb.fat_fats; + sbi->fat_bits = 0; /* Don't know yet */ + sbi->fat_start = bpb.fat_reserved; + sbi->fat_length = bpb.fat_fat_length; + sbi->root_cluster = 0; + sbi->free_clusters = -1; /* Don't know yet */ + sbi->free_clus_valid = 0; + sbi->prev_free = FAT_START_ENT; + sb->s_maxbytes = 0xffffffff; + fat_time_fat2unix(sbi, &ts, 0, cpu_to_le16(FAT_DATE_MIN), 0); + sb->s_time_min = ts.tv_sec; + + fat_time_fat2unix(sbi, &ts, cpu_to_le16(FAT_TIME_MAX), + cpu_to_le16(FAT_DATE_MAX), 0); + sb->s_time_max = ts.tv_sec; + + if (!sbi->fat_length && bpb.fat32_length) { + struct fat_boot_fsinfo *fsinfo; + struct buffer_head *fsinfo_bh; + + /* Must be FAT32 */ + sbi->fat_bits = 32; + sbi->fat_length = bpb.fat32_length; + sbi->root_cluster = bpb.fat32_root_cluster; + + /* MC - if info_sector is 0, don't multiply by 0 */ + sbi->fsinfo_sector = bpb.fat32_info_sector; + if (sbi->fsinfo_sector == 0) + sbi->fsinfo_sector = 1; + + fsinfo_bh = sb_bread(sb, sbi->fsinfo_sector); + if (fsinfo_bh == NULL) { + fat_msg(sb, KERN_ERR, "bread failed, FSINFO block" + " (sector = %lu)", sbi->fsinfo_sector); + goto out_fail; + } + + fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data; + if (!IS_FSINFO(fsinfo)) { + fat_msg(sb, KERN_WARNING, "Invalid FSINFO signature: " + "0x%08x, 0x%08x (sector = %lu)", + le32_to_cpu(fsinfo->signature1), + le32_to_cpu(fsinfo->signature2), + sbi->fsinfo_sector); + } else { + if (sbi->options.usefree) + sbi->free_clus_valid = 1; + sbi->free_clusters = le32_to_cpu(fsinfo->free_clusters); + sbi->prev_free = le32_to_cpu(fsinfo->next_cluster); + } + + brelse(fsinfo_bh); + } + + /* interpret volume ID as a little endian 32 bit integer */ + if (is_fat32(sbi)) + sbi->vol_id = bpb.fat32_vol_id; + else /* fat 16 or 12 */ + sbi->vol_id = bpb.fat16_vol_id; + + __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 = bpb.fat_dir_entries; + if (sbi->dir_entries & (sbi->dir_per_block - 1)) { + if (!silent) + fat_msg(sb, KERN_ERR, "bogus number of directory entries" + " (%u)", sbi->dir_entries); + goto out_invalid; + } + + rootdir_sectors = sbi->dir_entries + * sizeof(struct msdos_dir_entry) / sb->s_blocksize; + sbi->data_start = sbi->dir_start + rootdir_sectors; + total_sectors = bpb.fat_sectors; + if (total_sectors == 0) + total_sectors = bpb.fat_total_sect; + + if (total_sectors < sbi->data_start) { + if (!silent) + fat_msg(sb, KERN_ERR, + "data area starts beyond volume (%lu > %u)", + sbi->data_start, total_sectors); + goto out_invalid; + } + + total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus; + + if (!is_fat32(sbi)) + sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12; + + /* some OSes set FAT_STATE_DIRTY and clean it on unmount. */ + if (is_fat32(sbi)) + sbi->dirty = bpb.fat32_state & FAT_STATE_DIRTY; + else /* fat 16 or 12 */ + sbi->dirty = bpb.fat16_state & FAT_STATE_DIRTY; + + /* check that FAT table does not overflow */ + fat_clusters = calc_fat_clusters(sb); + total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT); + if (total_clusters > max_fat(sb)) { + if (!silent) + fat_msg(sb, KERN_ERR, "count of clusters too big (%u)", + total_clusters); + goto out_invalid; + } + + sbi->max_cluster = total_clusters + FAT_START_ENT; + /* check the free_clusters, it's not necessarily correct */ + if (sbi->free_clusters != -1 && sbi->free_clusters > total_clusters) + sbi->free_clusters = -1; + /* check the prev_free, it's not necessarily correct */ + sbi->prev_free %= sbi->max_cluster; + if (sbi->prev_free < FAT_START_ENT) + sbi->prev_free = FAT_START_ENT; + + /* set up enough so that it can read an inode */ + fat_hash_init(sb); + dir_hash_init(sb); + fat_ent_access_init(sb); + + /* + * The low byte of the first FAT entry must have the same value as + * the media field of the boot sector. But in real world, too many + * devices are writing wrong values. So, removed that validity check. + * + * The removed check compared the first FAT entry to a value dependent + * on the media field like this: + * == (0x0F00 | media), for FAT12 + * == (0XFF00 | media), for FAT16 + * == (0x0FFFFF | media), for FAT32 + */ + + error = -EINVAL; + scnprintf(buf, sizeof(buf), "cp%d", sbi->options.codepage); + sbi->nls_disk = load_nls(buf); + if (!sbi->nls_disk) { + fat_msg(sb, KERN_ERR, "codepage %s not found", buf); + goto out_fail; + } + + /* FIXME: utf8 is using iocharset for upper/lower conversion */ + if (sbi->options.isvfat) { + sbi->nls_io = load_nls(sbi->options.iocharset); + if (!sbi->nls_io) { + fat_msg(sb, KERN_ERR, "IO charset %s not found", + sbi->options.iocharset); + goto out_fail; + } + } + + error = -ENOMEM; + fat_inode = new_inode(sb); + if (!fat_inode) + goto out_fail; + sbi->fat_inode = fat_inode; + + fsinfo_inode = new_inode(sb); + if (!fsinfo_inode) + goto out_fail; + fsinfo_inode->i_ino = MSDOS_FSINFO_INO; + sbi->fsinfo_inode = fsinfo_inode; + insert_inode_hash(fsinfo_inode); + + root_inode = new_inode(sb); + if (!root_inode) + goto out_fail; + root_inode->i_ino = MSDOS_ROOT_INO; + inode_set_iversion(root_inode, 1); + error = fat_read_root(root_inode); + if (error < 0) { + iput(root_inode); + goto out_fail; + } + error = -ENOMEM; + insert_inode_hash(root_inode); + fat_attach(root_inode, 0); + sb->s_root = d_make_root(root_inode); + if (!sb->s_root) { + fat_msg(sb, KERN_ERR, "get root inode failed"); + goto out_fail; + } + + if (sbi->options.discard && !bdev_max_discard_sectors(sb->s_bdev)) + fat_msg(sb, KERN_WARNING, + "mounting with \"discard\" option, but the device does not support discard"); + + fat_set_state(sb, 1, 0); + return 0; + +out_invalid: + error = -EINVAL; + if (!silent) + fat_msg(sb, KERN_INFO, "Can't find a valid FAT filesystem"); + +out_fail: + iput(fsinfo_inode); + iput(fat_inode); + unload_nls(sbi->nls_io); + unload_nls(sbi->nls_disk); + fat_reset_iocharset(&sbi->options); + sb->s_fs_info = NULL; + kfree(sbi); + return error; +} + +EXPORT_SYMBOL_GPL(fat_fill_super); + +/* + * helper function for fat_flush_inodes. This writes both the inode + * and the file data blocks, waiting for in flight data blocks before + * the start of the call. It does not wait for any io started + * during the call + */ +static int writeback_inode(struct inode *inode) +{ + + int ret; + + /* if we used wait=1, sync_inode_metadata waits for the io for the + * inode to finish. So wait=0 is sent down to sync_inode_metadata + * and filemap_fdatawrite is used for the data blocks + */ + ret = sync_inode_metadata(inode, 0); + if (!ret) + ret = filemap_fdatawrite(inode->i_mapping); + return ret; +} + +/* + * write data and metadata corresponding to i1 and i2. The io is + * started but we do not wait for any of it to finish. + * + * filemap_flush is used for the block device, so if there is a dirty + * page for a block already in flight, we will not wait and start the + * io over again + */ +int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2) +{ + int ret = 0; + if (!MSDOS_SB(sb)->options.flush) + return 0; + if (i1) + ret = writeback_inode(i1); + if (!ret && i2) + ret = writeback_inode(i2); + if (!ret) + ret = sync_blockdev_nowait(sb->s_bdev); + return ret; +} +EXPORT_SYMBOL_GPL(fat_flush_inodes); + +int fat_init_fs_context(struct fs_context *fc, bool is_vfat) +{ + struct fat_mount_options *opts; + + opts = kzalloc_obj(*opts); + 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; + + err = fat_cache_init(); + if (err) + return err; + + err = fat_init_inodecache(); + if (err) + goto failed; + + return 0; + +failed: + fat_cache_destroy(); + return err; +} + +static void __exit exit_fat_fs(void) +{ + fat_cache_destroy(); + fat_destroy_inodecache(); +} + +module_init(init_fat_fs) +module_exit(exit_fat_fs) + +MODULE_DESCRIPTION("Core FAT filesystem support"); +MODULE_LICENSE("GPL"); |
