dx_countlimit's count field was read from disk and used directly to compute the checksummed range (count_offset + count * sizeof(dx_entry)) without ever being checked against limit -- only limit itself was bounds-checked against the block size. A corrupted or maliciously crafted filesystem image that sets count to a large value (e.g. 65535) makes ext4_chksum() read far past the end of the directory block buffer, hitting adjacent slab objects. Reported-by: xiaowu.417@qq.com Signed-off-by: Artem Blagodarenko --- fs/ext4/namei.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index cc49ae04a6f6..a283e285937a 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -477,6 +477,10 @@ static int ext4_dx_csum_verify(struct inode *inode, warn_no_space_for_csum(inode); return 0; } + if (count > limit) { + EXT4_ERROR_INODE(inode, "dir seems corrupt? Run e2fsck -D."); + return 0; + } t = (struct dx_tail *)(((struct dx_entry *)c) + limit); if (t->dt_checksum != ext4_dx_csum(inode, dirent, count_offset, @@ -506,6 +510,10 @@ static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) warn_no_space_for_csum(inode); return; } + if (count > limit) { + EXT4_ERROR_INODE(inode, "dir seems corrupt? Run e2fsck -D."); + return; + } t = (struct dx_tail *)(((struct dx_entry *)c) + limit); t->dt_checksum = ext4_dx_csum(inode, dirent, count_offset, count, t); -- 2.43.7 From: Artem Blagodarenko Replace remaining uses of struct ext4_dir_entry in namei.c with struct ext4_dir_entry_2. The code paths affected by this change already depend on the filetype feature, so using struct ext4_dir_entry_2 is appropriate and avoids mixing the two directory entry types unnecessarily. This change does not affect support for 16-bit rec_len. Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/namei.c | 38 +++++++++++++++++++------------------- 1 file changed, 19 insertions(+), 19 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index a283e285937a..c2f330c75c81 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -102,7 +102,7 @@ static struct buffer_head *ext4_append(handle_t *handle, } static int ext4_dx_csum_verify(struct inode *inode, - struct ext4_dir_entry *dirent); + struct ext4_dir_entry_2 *dirent); /* * Hints to ext4_read_dirblock regarding whether we expect a directory @@ -128,7 +128,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, unsigned int line) { struct buffer_head *bh; - struct ext4_dir_entry *dirent; + struct ext4_dir_entry_2 *dirent; int is_dx_block = 0; if (block >= inode->i_size >> inode->i_blkbits) { @@ -160,7 +160,7 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode, } if (!bh) return NULL; - dirent = (struct ext4_dir_entry *) bh->b_data; + dirent = (struct ext4_dir_entry_2 *) bh->b_data; /* Determine whether or not we have an index block */ if (is_dx(inode)) { if (block == 0) @@ -317,13 +317,13 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); #ifdef PARANOID - struct ext4_dir_entry *d, *top; + struct ext4_dir_entry_2 *d, *top; - d = (struct ext4_dir_entry *)bh->b_data; - top = (struct ext4_dir_entry *)(bh->b_data + + d = (struct ext4_dir_entry_2 *)bh->b_data; + top = (struct ext4_dir_entry_2 *)(bh->b_data + (blocksize - sizeof(struct ext4_dir_entry_tail))); while (d < top && ext4_rec_len_from_disk(d->rec_len, blocksize)) - d = (struct ext4_dir_entry *)(((void *)d) + + d = (struct ext4_dir_entry_2 *)(((void *)d) + ext4_rec_len_from_disk(d->rec_len, blocksize)); if (d != top) @@ -410,22 +410,22 @@ int ext4_handle_dirty_dirblock(handle_t *handle, } static struct dx_countlimit *get_dx_countlimit(struct inode *inode, - struct ext4_dir_entry *dirent, + struct ext4_dir_entry_2 *dirent, int *offset) { - struct ext4_dir_entry *dp; + struct ext4_dir_entry_2 *de; struct dx_root_info *root; int count_offset; int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize); if (rlen == blocksize) - count_offset = 8; + count_offset = sizeof(struct dx_node); else if (rlen == 12) { - dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); - if (ext4_rec_len_from_disk(dp->rec_len, blocksize) != blocksize - 12) + de = (struct ext4_dir_entry_2 *)(((void *)dirent) + 12); + if (ext4_rec_len_from_disk(de->rec_len, blocksize) != blocksize - 12) return NULL; - root = (struct dx_root_info *)(((void *)dp + 12)); + root = (struct dx_root_info *)(((void *)de + 12)); if (root->reserved_zero || root->info_length != sizeof(struct dx_root_info)) return NULL; @@ -438,7 +438,7 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode, return (struct dx_countlimit *)(((void *)dirent) + count_offset); } -static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent, +static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry_2 *dirent, int count_offset, int count, struct dx_tail *t) { struct ext4_inode_info *ei = EXT4_I(inode); @@ -456,7 +456,7 @@ static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent, } static int ext4_dx_csum_verify(struct inode *inode, - struct ext4_dir_entry *dirent) + struct ext4_dir_entry_2 *dirent) { struct dx_countlimit *c; struct dx_tail *t; @@ -489,7 +489,7 @@ static int ext4_dx_csum_verify(struct inode *inode, return 1; } -static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent) +static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry_2 *dirent) { struct dx_countlimit *c; struct dx_tail *t; @@ -523,7 +523,7 @@ static inline int ext4_handle_dirty_dx_node(handle_t *handle, struct inode *inode, struct buffer_head *bh) { - ext4_dx_csum_set(inode, (struct ext4_dir_entry *)bh->b_data); + ext4_dx_csum_set(inode, (struct ext4_dir_entry_2 *)bh->b_data); return ext4_handle_dirty_metadata(handle, inode, bh); } @@ -1496,7 +1496,7 @@ int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size, } static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block, - struct ext4_dir_entry *de) + struct ext4_dir_entry_2 *de) { struct super_block *sb = dir->i_sb; @@ -1627,7 +1627,7 @@ static struct buffer_head *__ext4_find_entry(struct inode *dir, } if (!buffer_verified(bh) && !is_dx_internal_node(dir, block, - (struct ext4_dir_entry *)bh->b_data) && + (struct ext4_dir_entry_2 *)bh->b_data) && !ext4_dirblock_csum_verify(dir, bh)) { EXT4_ERROR_INODE_ERR(dir, EFSBADCRC, "checksumming directory " -- 2.43.7 From: Artem Blagodarenko Replace open-coded checks for directory tail entries with a call to ext4_dir_entry_is_tail(). This helper will also be used by upcoming changes. Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/ext4.h | 16 ++++++++++++++++ fs/ext4/namei.c | 7 +------ 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index b37c136ea3ab..9400bc2858a5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -4004,6 +4004,22 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) io_end->flag &= ~EXT4_IO_END_UNWRITTEN; } +/* + * ext4_dir_entry_is_tail() - Check if a directory entry is a tail entry. + * @de: directory entry to check + * + * Returns true if @de is a directory block tail entry (checksum record). + */ +static inline bool ext4_dir_entry_is_tail(struct ext4_dir_entry_2 *de) +{ + struct ext4_dir_entry_tail *t = (struct ext4_dir_entry_tail *)de; + + return !t->det_reserved_zero1 && + le16_to_cpu(t->det_rec_len) == sizeof(*t) && + !t->det_reserved_zero2 && + t->det_reserved_ft == EXT4_FT_DIR_CSUM; +} + extern const struct iomap_ops ext4_iomap_ops; extern const struct iomap_ops ext4_iomap_report_ops; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index c2f330c75c81..2fc14332fab7 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -314,7 +314,6 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, struct buffer_head *bh) { struct ext4_dir_entry_tail *t; - int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); #ifdef PARANOID struct ext4_dir_entry_2 *d, *top; @@ -334,11 +333,7 @@ static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode, t = EXT4_DIRENT_TAIL(bh->b_data, EXT4_BLOCK_SIZE(inode->i_sb)); #endif - if (t->det_reserved_zero1 || - (ext4_rec_len_from_disk(t->det_rec_len, blocksize) != - sizeof(struct ext4_dir_entry_tail)) || - t->det_reserved_zero2 || - t->det_reserved_ft != EXT4_FT_DIR_CSUM) + if (!ext4_dir_entry_is_tail((struct ext4_dir_entry_2 *)t)) return NULL; return t; -- 2.43.7 From: Artem Blagodarenko Split monolithic definition of dx_root struct to separate dx_root_info from fake struct ext4_dir_entry2 for improved code readability. This allows "." and ".." dirents to have different sizes if necessary, since we can't assume the rec_len 12 if dx_root dirents have dirdata. Adds dx_get_dx_info() accessor instead of complex typecast at callers. Does not change any functionality. Signed-off-by: Pravin Shelar Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/namei.c | 145 +++++++++++++++++++++++------------------------- 1 file changed, 70 insertions(+), 75 deletions(-) diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 2fc14332fab7..61410fa0effa 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -244,22 +244,13 @@ struct dx_entry * hash version mod 4 should never be 0. Sincerely, the paranoia department. */ -struct dx_root +struct dx_root_info { - struct fake_dirent dot; - char dot_name[4]; - struct fake_dirent dotdot; - char dotdot_name[4]; - struct dx_root_info - { - __le32 reserved_zero; - u8 hash_version; - u8 info_length; /* 8 */ - u8 indirect_levels; - u8 unused_flags; - } - info; - struct dx_entry entries[]; + __le32 reserved_zero; + u8 hash_version; + u8 info_length; /* 8 */ + u8 indirect_levels; + u8 unused_flags; }; struct dx_node @@ -536,6 +527,16 @@ ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize) * Future: use high four bits of block for coalesce-on-delete flags * Mask them off for now. */ +static struct dx_root_info *dx_get_dx_info(void *de_buf) +{ + /* get dotdot first */ + de_buf = de_buf + ext4_dir_rec_len(1, NULL); + + /* dx root info is after dotdot entry */ + de_buf = de_buf + ext4_dir_rec_len(2, NULL); + + return (struct dx_root_info *)de_buf; +} static inline ext4_lblk_t dx_get_block(struct dx_entry *entry) { @@ -783,7 +784,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, { unsigned count, indirect, level, i; struct dx_entry *at, *entries, *p, *q, *m; - struct dx_root *root; + struct dx_root_info *info; struct dx_frame *frame = frame_in; struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR); u32 hash; @@ -795,23 +796,24 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, if (IS_ERR(frame->bh)) return (struct dx_frame *) frame->bh; - root = (struct dx_root *) frame->bh->b_data; - if (root->info.hash_version != DX_HASH_TEA && - root->info.hash_version != DX_HASH_HALF_MD4 && - root->info.hash_version != DX_HASH_LEGACY && - root->info.hash_version != DX_HASH_SIPHASH) { - ext4_warning_inode(dir, "Unrecognised inode hash code %u", - root->info.hash_version); + info = dx_get_dx_info((struct ext4_dir_entry_2 *)frame->bh->b_data); + if (info->hash_version != DX_HASH_TEA && + info->hash_version != DX_HASH_HALF_MD4 && + info->hash_version != DX_HASH_LEGACY && + info->hash_version != DX_HASH_SIPHASH) { + ext4_warning(dir->i_sb, + "Unrecognised inode hash code %d for directory #%llu", + info->hash_version, dir->i_ino); goto fail; } if (ext4_hash_in_dirent(dir)) { - if (root->info.hash_version != DX_HASH_SIPHASH) { + if (info->hash_version != DX_HASH_SIPHASH) { ext4_warning_inode(dir, "Hash in dirent, but hash is not SIPHASH"); goto fail; } } else { - if (root->info.hash_version == DX_HASH_SIPHASH) { + if (info->hash_version == DX_HASH_SIPHASH) { ext4_warning_inode(dir, "Hash code is SIPHASH, but hash not in dirent"); goto fail; @@ -819,7 +821,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } if (fname) hinfo = &fname->hinfo; - hinfo->hash_version = root->info.hash_version; + hinfo->hash_version = info->hash_version; if (hinfo->hash_version <= DX_HASH_TEA) hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed; @@ -835,13 +837,13 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, } hash = hinfo->hash; - if (root->info.unused_flags & 1) { + if (info->unused_flags & 1) { ext4_warning_inode(dir, "Unimplemented hash flags: %#06x", - root->info.unused_flags); + info->unused_flags); goto fail; } - indirect = root->info.indirect_levels; + indirect = info->indirect_levels; if (indirect >= ext4_dir_htree_level(dir->i_sb)) { ext4_warning(dir->i_sb, "Directory (ino: %llu) htree depth %#06x exceed" @@ -854,14 +856,12 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, goto fail; } - entries = (struct dx_entry *)(((char *)&root->info) + - root->info.info_length); + entries = (struct dx_entry *)(((char *)info) + info->info_length); - if (dx_get_limit(entries) != dx_root_limit(dir, - root->info.info_length)) { + if (dx_get_limit(entries) != dx_root_limit(dir, info->info_length)) { ext4_warning_inode(dir, "dx entry: limit %u != root limit %u", dx_get_limit(entries), - dx_root_limit(dir, root->info.info_length)); + dx_root_limit(dir, info->info_length)); goto fail; } @@ -947,7 +947,7 @@ static void dx_release(struct dx_frame *frames) if (frames[0].bh == NULL) return; - info = &((struct dx_root *)frames[0].bh->b_data)->info; + info = dx_get_dx_info((struct ext4_dir_entry_2 *)frames[0].bh->b_data); /* save local copy, "info" may be freed after brelse() */ indirect_levels = info->indirect_levels; for (i = 0; i <= indirect_levels; i++) { @@ -2159,44 +2159,38 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, return err ? err : err2; } -static bool ext4_check_dx_root(struct inode *dir, struct dx_root *root) +static bool ext4_check_dx_root(struct inode *dir, + struct ext4_dir_entry_2 *dot_de, + struct ext4_dir_entry_2 *dotdot_de, + struct ext4_dir_entry_2 **entry) { - struct fake_dirent *fde; const char *error_msg; - unsigned int rlen; unsigned int blocksize = dir->i_sb->s_blocksize; - char *blockend = (char *)root + dir->i_sb->s_blocksize; + struct ext4_dir_entry_2 *de = NULL; - fde = &root->dot; - if (unlikely(fde->name_len != 1)) { + if (unlikely(dot_de->name_len != 1)) { error_msg = "invalid name_len for '.'"; goto corrupted; } - if (unlikely(strncmp(root->dot_name, ".", fde->name_len))) { + if (unlikely(strncmp(dot_de->name, ".", dot_de->name_len))) { error_msg = "invalid name for '.'"; goto corrupted; } - rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize); - if (unlikely((char *)fde + rlen >= blockend)) { - error_msg = "invalid rec_len for '.'"; - goto corrupted; - } - fde = &root->dotdot; - if (unlikely(fde->name_len != 2)) { + if (unlikely(dotdot_de->name_len != 2)) { error_msg = "invalid name_len for '..'"; goto corrupted; } - if (unlikely(strncmp(root->dotdot_name, "..", fde->name_len))) { + if (unlikely(strncmp(dotdot_de->name, "..", dotdot_de->name_len))) { error_msg = "invalid name for '..'"; goto corrupted; } - rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize); - if (unlikely((char *)fde + rlen >= blockend)) { + de = ext4_next_entry(dotdot_de, blocksize); + if ((char *)de >= (((char *)dot_de) + blocksize)) { error_msg = "invalid rec_len for '..'"; goto corrupted; } - + *entry = de; return true; corrupted: @@ -2214,16 +2208,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, struct inode *inode, struct buffer_head *bh) { struct buffer_head *bh2; - struct dx_root *root; struct dx_frame frames[EXT4_HTREE_LEVEL], *frame; struct dx_entry *entries; - struct ext4_dir_entry_2 *de, *de2; + struct ext4_dir_entry_2 *de, *de2, *dot_de, *dotdot_de; char *data2, *top; unsigned len; int retval; unsigned blocksize; ext4_lblk_t block; - struct fake_dirent *fde; + struct dx_root_info *dx_info; int csum_size = 0; if (ext4_has_feature_metadata_csum(inode->i_sb)) @@ -2240,17 +2233,15 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, return retval; } - root = (struct dx_root *) bh->b_data; - if (!ext4_check_dx_root(dir, root)) { + dot_de = (struct ext4_dir_entry_2 *)bh->b_data; + dotdot_de = ext4_next_entry(dot_de, blocksize); + if (!ext4_check_dx_root(dir, dot_de, dotdot_de, &de)) { brelse(bh); return -EFSCORRUPTED; } /* The 0th block becomes the root, move the dirents out */ - fde = &root->dotdot; - de = (struct ext4_dir_entry_2 *)((char *)fde + - ext4_rec_len_from_disk(fde->rec_len, blocksize)); - len = ((char *) root) + (blocksize - csum_size) - (char *) de; + len = ((char *)dot_de) + (blocksize - csum_size) - (char *)de; /* Allocate new block for the 0th block's dirents */ bh2 = ext4_append(handle, dir, &block); @@ -2281,24 +2272,27 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, ext4_initialize_dirent_tail(bh2, blocksize); /* Initialize the root; the dot dirents already exist */ - de = (struct ext4_dir_entry_2 *) (&root->dotdot); - de->rec_len = ext4_rec_len_to_disk( - blocksize - ext4_dir_rec_len(2, NULL), blocksize); - memset (&root->info, 0, sizeof(root->info)); - root->info.info_length = sizeof(root->info); + dotdot_de->rec_len = + ext4_rec_len_to_disk(blocksize - le16_to_cpu(dot_de->rec_len), + blocksize); + + /* initialize hashing info */ + dx_info = dx_get_dx_info(dot_de); + memset(dx_info, 0, sizeof(*dx_info)); + dx_info->info_length = sizeof(*dx_info); if (ext4_hash_in_dirent(dir)) - root->info.hash_version = DX_HASH_SIPHASH; + dx_info->hash_version = DX_HASH_SIPHASH; else - root->info.hash_version = + dx_info->hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; - entries = root->entries; + entries = (void *)dx_info + sizeof(*dx_info); dx_set_block(entries, 1); dx_set_count(entries, 1); - dx_set_limit(entries, dx_root_limit(dir, sizeof(root->info))); + dx_set_limit(entries, dx_root_limit(dir, sizeof(*dx_info))); /* Initialize as for dx_probe */ - fname->hinfo.hash_version = root->info.hash_version; + fname->hinfo.hash_version = dx_info->hash_version; if (fname->hinfo.hash_version <= DX_HASH_TEA) fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned; fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed; @@ -2608,7 +2602,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, if (restart || err) goto journal_error; } else { - struct dx_root *dxroot; + struct dx_root_info *info; memcpy((char *) entries2, (char *) entries, icount * sizeof(struct dx_entry)); dx_set_limit(entries2, dx_node_limit(dir)); @@ -2616,8 +2610,9 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, /* Set up root */ dx_set_count(entries, 1); dx_set_block(entries + 0, newblock); - dxroot = (struct dx_root *)frames[0].bh->b_data; - dxroot->info.indirect_levels += 1; + info = dx_get_dx_info((struct ext4_dir_entry_2 *) + frames[0].bh->b_data); + info->indirect_levels += 1; dxtrace(printk(KERN_DEBUG "Creating %d level index...\n", dxroot->info.indirect_levels)); -- 2.43.7 From: Artem Blagodarenko Define the on-disk format for ext4 directory entry extension data. The upper four bits of de->file_type indicate the presence of optional data stored after the filename NUL terminator. This patch defines flags for LUFID, 64-bit inode numbers, and casefold hash data stored in that area. Add struct ext4_dirent_data_header to describe variable-length extension records and struct ext4_dirent_hash for hash storage used by casefold and fscrypt. Provide ext4_dirdata_next() to advance to the next extension record and ext4_dirent_get_data_len() to compute the total extension data length associated with a directory entry. No functional changes. Signed-off-by: Pravin Shelar Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/ext4.h | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 83 insertions(+) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 9400bc2858a5..98603aa44693 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2556,6 +2556,49 @@ struct ext4_dir_entry_tail { #define EXT4_FT_SYMLINK 7 #define EXT4_FT_MAX 8 +#define EXT4_FT_MASK 0xf + +#if EXT4_FT_MAX > EXT4_FT_MASK +#error "conflicting EXT4_FT_MAX and EXT4_FT_MASK" +#endif + +/* + * d_type has 4 unused bits, so it can hold four types of data. These different + * types of data (e.g. fscypt hash, high 32 bits of 64-bit inode number) can be + * stored, in flag order, after file-name in ext4 dirent. + * + * These flags are added to d_type if ext4 dirent has extra data after + * filename. This data length is variable and length is stored in first byte + * of data. Data starts after filename NUL byte. + */ +#define EXT4_DIRENT_LUFID 0x10 +#define EXT4_DIRENT_INO64 0x20 +#define EXT4_DIRENT_CFHASH 0x40 + +struct ext4_fid { + char fid[16]; /* 128-bit unique file identifier */ +}; + +struct ext4_dirent_data_header { + /* length of this header + the whole data blob */ + __u8 ddh_length; +} __packed; + +struct ext4_dirent_fid { + struct ext4_dirent_data_header df_header; + struct ext4_fid df_fid[]; +}; + +#define EXT4_LUFID_MAGIC 0xAD200907UL +struct ext4_dentry_param { + __u32 edp_magic; /* EXT4_LUFID_MAGIC */ + struct ext4_dirent_fid edp_dfid; +}; + +struct ext4_dirent_hash { + struct ext4_dirent_data_header dh_header; + struct ext4_dir_entry_hash dh_hash; +} __packed; #define EXT4_FT_DIR_CSUM 0xDE @@ -4004,6 +4047,12 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end) io_end->flag &= ~EXT4_IO_END_UNWRITTEN; } +/* + * Advance to the next dirdata record header starting from @ddh. + */ +#define ext4_dirdata_next(ddh) \ + ((struct ext4_dirent_data_header *)((char *)(ddh) + (ddh)->ddh_length)) + /* * ext4_dir_entry_is_tail() - Check if a directory entry is a tail entry. * @de: directory entry to check @@ -4020,6 +4069,40 @@ static inline bool ext4_dir_entry_is_tail(struct ext4_dir_entry_2 *de) t->det_reserved_ft == EXT4_FT_DIR_CSUM; } +/* + * ext4_dirent_get_data_len() - Compute the total dirdata length for an entry. + * @de: directory entry + * + * Computes the length of optional data stored after the filename (and its + * implicit NUL terminator). Each extension is indicated by a bit in the + * high 4 bits of de->file_type; the first byte of each extension is its + * length (including that length byte itself). + * + * Returns 0 for tail entries and for entries with no dirdata. + */ +static inline int ext4_dirent_get_data_len(struct ext4_dir_entry_2 *de) +{ + __u8 extra_data_flags; + struct ext4_dirent_data_header *ddh; + int dlen = 0; + + if (ext4_dir_entry_is_tail(de)) + return 0; + + extra_data_flags = (de->file_type & ~EXT4_FT_MASK) >> 4; + ddh = (struct ext4_dirent_data_header *)(de->name + de->name_len + + 1 /* NUL terminator */); + + while (extra_data_flags) { + if (extra_data_flags & 1) { + dlen += ddh->ddh_length + (dlen == 0); + ddh = ext4_dirdata_next(ddh); + } + extra_data_flags >>= 1; + } + return dlen; +} + extern const struct iomap_ops ext4_iomap_ops; extern const struct iomap_ops ext4_iomap_report_ops; -- 2.43.7 From: Artem Blagodarenko Mask the filetype with EXT4_FT_MASK when indexing ext4_filetype_table[] to avoid using dirdata bits as an index. Preserve the extra bits stored in the upper part of filetype and propagate them to the returned dtype value. Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/ext4.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 98603aa44693..2f29f50a12ac 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3046,12 +3046,15 @@ static const unsigned char ext4_filetype_table[] = { DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK }; -static inline unsigned char get_dtype(struct super_block *sb, int filetype) +static inline unsigned char get_dtype(struct super_block *sb, int filetype) { - if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX) + unsigned char fl_index = filetype & EXT4_FT_MASK; + + if (!ext4_has_feature_filetype(sb) || fl_index >= EXT4_FT_MAX) return DT_UNKNOWN; - return ext4_filetype_table[filetype]; + return (ext4_filetype_table[fl_index]) | + (filetype & ~EXT4_FT_MASK); } extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size); -- 2.43.7 From: Artem Blagodarenko Introduce ext4_dir_entry_len() helper to compute the required rec_len for a directory entry, taking into account dirdata and casefold+fscrypt hash space. Convert ext4_dirent_get_data_len() to take the decoded rec_len as an argument and add bounds checking when walking dirdata extensions to avoid overruns on malformed entries. Update dx_root_limit() to use ext4_dir_entry_len() instead of open-coded ext4_dir_rec_len() for '.' and '..' entries. Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/ext4.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++--- fs/ext4/namei.c | 23 ++++++++++++++-------- 2 files changed, 63 insertions(+), 11 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2f29f50a12ac..a369a0cd04bc 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -4075,6 +4075,7 @@ static inline bool ext4_dir_entry_is_tail(struct ext4_dir_entry_2 *de) /* * ext4_dirent_get_data_len() - Compute the total dirdata length for an entry. * @de: directory entry + * @rec_len: the record length of the directory entry (decoded) * * Computes the length of optional data stored after the filename (and its * implicit NUL terminator). Each extension is indicated by a bit in the @@ -4083,22 +4084,41 @@ static inline bool ext4_dir_entry_is_tail(struct ext4_dir_entry_2 *de) * * Returns 0 for tail entries and for entries with no dirdata. */ -static inline int ext4_dirent_get_data_len(struct ext4_dir_entry_2 *de) +static inline int ext4_dirent_get_data_len(struct ext4_dir_entry_2 *de, + unsigned int rec_len) { __u8 extra_data_flags; struct ext4_dirent_data_header *ddh; int dlen = 0; + unsigned int offset; if (ext4_dir_entry_is_tail(de)) return 0; extra_data_flags = (de->file_type & ~EXT4_FT_MASK) >> 4; - ddh = (struct ext4_dirent_data_header *)(de->name + de->name_len + - 1 /* NUL terminator */); + /* offset from start of entry to after filename + NUL */ + offset = EXT4_BASE_DIR_LEN + de->name_len + 1; + /* bounds check: ensure we start reading within the entry */ + if (offset >= rec_len) + return 0; + + ddh = (struct ext4_dirent_data_header *)((char *)de + offset); + while (extra_data_flags) { if (extra_data_flags & 1) { + /* bounds check before reading ddh_length */ + if (offset + sizeof(*ddh) > + rec_len) + return dlen; + + /* validate ddh_length is reasonable */ + if (ddh->ddh_length == 0 || ddh->ddh_length > + rec_len - offset) + return dlen; + dlen += ddh->ddh_length + (dlen == 0); + offset += ddh->ddh_length; ddh = ext4_dirdata_next(ddh); } extra_data_flags >>= 1; @@ -4106,6 +4126,31 @@ static inline int ext4_dirent_get_data_len(struct ext4_dir_entry_2 *de) return dlen; } +/* + * ext4_dir_entry_len() - Compute the required rec_len for a directory entry. + * @de: directory entry (used to read name_len and any dirdata length) + * @blocksize: size of the buffer @de lives in (the real directory block + * size, or the smaller inline-data buffer size for inline + * directories) -- used only to decode @de->rec_len's "0/65535 + * means rest of buffer" sentinel correctly. + * @dir: directory inode (may be NULL for '.' and '..' entries, which + * never carry the casefold+fscrypt hash regardless of the + * directory's feature flags) + * + * Returns the minimum record length needed to hold @de, rounded up to the + * directory alignment and including room for the casefold+fscrypt hash if + * the directory requires it. + */ +static inline unsigned int ext4_dir_entry_len(struct ext4_dir_entry_2 *de, + unsigned int blocksize, + const struct inode *dir) +{ + unsigned int rec_len = ext4_rec_len_from_disk(de->rec_len, blocksize); + unsigned int dirdata = ext4_dirent_get_data_len(de, rec_len); + + return ext4_dir_rec_len(de->name_len + dirdata, dir); +} + extern const struct iomap_ops ext4_iomap_ops; extern const struct iomap_ops ext4_iomap_report_ops; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 61410fa0effa..e2dda8dee77c 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -578,11 +578,15 @@ static inline void dx_set_limit(struct dx_entry *entries, unsigned value) ((struct dx_countlimit *) entries)->limit = cpu_to_le16(value); } -static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize) +static inline unsigned dx_root_limit(struct inode *dir, + struct ext4_dir_entry_2 *dot_de) { - unsigned int entry_space = dir->i_sb->s_blocksize - - ext4_dir_rec_len(1, NULL) - - ext4_dir_rec_len(2, NULL) - infosize; + struct dx_root_info *info; + unsigned int entry_space; + + info = dx_get_dx_info(dot_de); + entry_space = dir->i_sb->s_blocksize - ((char *)info - (char *)dot_de) - + info->info_length; if (ext4_has_feature_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -858,10 +862,13 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, entries = (struct dx_entry *)(((char *)info) + info->info_length); - if (dx_get_limit(entries) != dx_root_limit(dir, info->info_length)) { + if (dx_get_limit(entries) != + dx_root_limit(dir, (struct ext4_dir_entry_2 *)frame->bh->b_data)) { ext4_warning_inode(dir, "dx entry: limit %u != root limit %u", dx_get_limit(entries), - dx_root_limit(dir, info->info_length)); + dx_root_limit(dir, + (struct ext4_dir_entry_2 *)frame->bh->b_data + )); goto fail; } @@ -2286,10 +2293,10 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, dx_info->hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version; - entries = (void *)dx_info + sizeof(*dx_info); + entries = (void *)dx_info + dx_info->info_length; dx_set_block(entries, 1); dx_set_count(entries, 1); - dx_set_limit(entries, dx_root_limit(dir, sizeof(*dx_info))); + dx_set_limit(entries, dx_root_limit(dir, dot_de)); /* Initialize as for dx_probe */ fname->hinfo.hash_version = dx_info->hash_version; -- 2.43.7 From: Artem Blagodarenko Rename ext4_dir_rec_len() to ext4_dirent_rec_len() to better reflect that it computes the record length for a directory entry based on the provided name length. Update the comment to clarify handling of dirdata-enabled directories and document the use of ext4_dir_entry_len() when dirdata is present. No functional changes. Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/dir.c | 9 +++-- fs/ext4/ext4.h | 14 +++++--- fs/ext4/inline.c | 14 ++++---- fs/ext4/namei.c | 89 ++++++++++++++++++++++++++++++++---------------- 4 files changed, 80 insertions(+), 46 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 17edd678fa87..d22b09f86365 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -89,16 +89,15 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, bool fake = is_fake_dir_entry(de); bool has_csum = ext4_has_feature_metadata_csum(dir->i_sb); - if (unlikely(rlen < ext4_dir_rec_len(1, fake ? NULL : dir))) + if (unlikely(rlen < ext4_dirent_rec_len(1, fake ? NULL : dir))) error_msg = "rec_len is smaller than minimal"; else if (unlikely(rlen % 4 != 0)) error_msg = "rec_len % 4 != 0"; - else if (unlikely(rlen < ext4_dir_rec_len(de->name_len, - fake ? NULL : dir))) + else if (unlikely(rlen < ext4_dir_entry_len(de, size, fake ? NULL : dir))) error_msg = "rec_len is too small for name_len"; else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; - else if (unlikely(next_offset > size - ext4_dir_rec_len(1, + else if (unlikely(next_offset > size - ext4_dirent_rec_len(1, has_csum ? NULL : dir) && next_offset != size)) error_msg = "directory entry too close to block end"; @@ -245,7 +244,7 @@ static int ext4_readdir(struct file *file, struct dir_context *ctx) * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, - sb->s_blocksize) < ext4_dir_rec_len(1, + sb->s_blocksize) < ext4_dirent_rec_len(1, inode)) break; i += ext4_rec_len_from_disk(de->rec_len, diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index a369a0cd04bc..2fc9fa6d3021 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2616,11 +2616,16 @@ struct ext4_dirent_hash { * casefolded and encrypted need to store the hash as well, so we add room for * ext4_extended_dir_entry_2. For all entries related to '.' or '..' you should * pass NULL for dir, as those entries do not use the extra fields. + * + * For directories with the dirdata feature, extra data may follow the filename. + * Use ext4_dir_entry_len() to compute the length of a directory entry + * including any dirdata, or ext4_dirent_rec_len() directly when the total + * name_len (including dirdata length) is already known. */ -static inline unsigned int ext4_dir_rec_len(__u8 name_len, +static inline unsigned int ext4_dirent_rec_len(unsigned int name_len, const struct inode *dir) { - int rec_len = (name_len + 8 + EXT4_DIR_ROUND); + unsigned int rec_len = (name_len + 8 + EXT4_DIR_ROUND); if (dir && ext4_hash_in_dirent(dir)) rec_len += sizeof(struct ext4_dir_entry_hash); @@ -3028,7 +3033,8 @@ extern void ext4_htree_free_dir_info(struct dir_private_info *p); extern int ext4_find_dest_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size, struct ext4_filename *fname, - struct ext4_dir_entry_2 **dest_de); + struct ext4_dir_entry_2 **dest_de, + int dlen); void ext4_insert_dentry(struct inode *dir, struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, @@ -4148,7 +4154,7 @@ static inline unsigned int ext4_dir_entry_len(struct ext4_dir_entry_2 *de, unsigned int rec_len = ext4_rec_len_from_disk(de->rec_len, blocksize); unsigned int dirdata = ext4_dirent_get_data_len(de, rec_len); - return ext4_dir_rec_len(de->name_len + dirdata, dir); + return ext4_dirent_rec_len(de->name_len + dirdata, dir); } extern const struct iomap_ops ext4_iomap_ops; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 8045e4ff270c..5b3faacdf143 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -977,7 +977,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_dir_entry_2 *de; err = ext4_find_dest_de(dir, iloc->bh, inline_start, - inline_size, fname, &de); + inline_size, fname, &de, 0); if (err) return err; @@ -1055,7 +1055,7 @@ static int ext4_update_inline_dir(handle_t *handle, struct inode *dir, int old_size = EXT4_I(dir)->i_inline_size - EXT4_MIN_INLINE_DATA_SIZE; int new_size = get_max_inline_xattr_value_size(dir, iloc); - if (new_size - old_size <= ext4_dir_rec_len(1, NULL)) + if (new_size - old_size <= ext4_dirent_rec_len(1, NULL)) return -ENOSPC; ret = ext4_update_inline_data(handle, dir, @@ -1309,7 +1309,7 @@ int ext4_inlinedir_to_tree(struct file *dir_file, fake.name_len = 1; memcpy(fake.name, ".", 2); fake.rec_len = ext4_rec_len_to_disk( - ext4_dir_rec_len(fake.name_len, NULL), + ext4_dirent_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; @@ -1319,7 +1319,7 @@ int ext4_inlinedir_to_tree(struct file *dir_file, fake.name_len = 2; memcpy(fake.name, "..", 3); fake.rec_len = ext4_rec_len_to_disk( - ext4_dir_rec_len(fake.name_len, NULL), + ext4_dirent_rec_len(fake.name_len, NULL), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; @@ -1427,8 +1427,8 @@ int ext4_read_inline_dir(struct file *file, * So we will use extra_offset and extra_size to indicate them * during the inline dir iteration. */ - dotdot_offset = ext4_dir_rec_len(1, NULL); - dotdot_size = dotdot_offset + ext4_dir_rec_len(2, NULL); + dotdot_offset = ext4_dirent_rec_len(1, NULL); + dotdot_size = dotdot_offset + ext4_dirent_rec_len(2, NULL); extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE; extra_size = extra_offset + inline_size; @@ -1463,7 +1463,7 @@ int ext4_read_inline_dir(struct file *file, * failure will be detected in the * dirent test below. */ if (ext4_rec_len_from_disk(de->rec_len, extra_size) - < ext4_dir_rec_len(1, NULL)) + < ext4_dirent_rec_len(1, NULL)) break; i += ext4_rec_len_from_disk(de->rec_len, extra_size); diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index e2dda8dee77c..73c8f1b399ef 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -527,13 +527,21 @@ ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize) * Future: use high four bits of block for coalesce-on-delete flags * Mask them off for now. */ -static struct dx_root_info *dx_get_dx_info(void *de_buf) +static struct dx_root_info *dx_get_dx_info(struct inode *dir, void *de_buf) { - /* get dotdot first */ - de_buf = de_buf + ext4_dir_rec_len(1, NULL); + unsigned int blocksize = dir->i_sb->s_blocksize; + void *base = de_buf; + + /* get dotdot first; '.' and '..' never carry the casefold+fscrypt + * hash, so pass NULL for dir regardless of the directory's flags */ + de_buf += ext4_dir_entry_len(de_buf, blocksize, NULL); /* dx root info is after dotdot entry */ - de_buf = de_buf + ext4_dir_rec_len(2, NULL); + de_buf += ext4_dir_entry_len(de_buf, blocksize, NULL); + + if (de_buf < base || (char *)de_buf - (char *)base + + sizeof(struct dx_root_info) > blocksize) + return ERR_PTR(-EFSCORRUPTED); return (struct dx_root_info *)de_buf; } @@ -584,7 +592,9 @@ static inline unsigned dx_root_limit(struct inode *dir, struct dx_root_info *info; unsigned int entry_space; - info = dx_get_dx_info(dot_de); + info = dx_get_dx_info(dir, dot_de); + if (IS_ERR(info)) + return 0; entry_space = dir->i_sb->s_blocksize - ((char *)info - (char *)dot_de) - info->info_length; @@ -596,7 +606,7 @@ static inline unsigned dx_root_limit(struct inode *dir, static inline unsigned dx_node_limit(struct inode *dir) { unsigned int entry_space = dir->i_sb->s_blocksize - - ext4_dir_rec_len(0, dir); + ext4_dirent_rec_len(0, dir); if (ext4_has_feature_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -800,7 +810,9 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, if (IS_ERR(frame->bh)) return (struct dx_frame *) frame->bh; - info = dx_get_dx_info((struct ext4_dir_entry_2 *)frame->bh->b_data); + info = dx_get_dx_info(dir, (struct ext4_dir_entry_2 *)frame->bh->b_data); + if (IS_ERR(info)) + goto fail; if (info->hash_version != DX_HASH_TEA && info->hash_version != DX_HASH_HALF_MD4 && info->hash_version != DX_HASH_LEGACY && @@ -945,7 +957,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir, return ret_err; } -static void dx_release(struct dx_frame *frames) +static void dx_release(struct inode *dir, struct dx_frame *frames) { struct dx_root_info *info; int i; @@ -954,7 +966,9 @@ static void dx_release(struct dx_frame *frames) if (frames[0].bh == NULL) return; - info = dx_get_dx_info((struct ext4_dir_entry_2 *)frames[0].bh->b_data); + info = dx_get_dx_info(dir, (struct ext4_dir_entry_2 *)frames[0].bh->b_data); + if (IS_ERR(info)) + return; /* save local copy, "info" may be freed after brelse() */ indirect_levels = info->indirect_levels; for (i = 0; i <= indirect_levels; i++) { @@ -1066,7 +1080,7 @@ static int htree_dirblock_to_tree(struct file *dir_file, /* csum entries are not larger in the casefolded encrypted case */ top = (struct ext4_dir_entry_2 *) ((char *) de + dir->i_sb->s_blocksize - - ext4_dir_rec_len(0, + ext4_dirent_rec_len(0, csum ? NULL : dir)); /* Check if the directory is encrypted */ if (IS_ENCRYPTED(dir)) { @@ -1260,12 +1274,12 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, (count && ((hashval & 1) == 0))) break; } - dx_release(frames); + dx_release(dir, frames); dxtrace(printk(KERN_DEBUG "Fill tree: returned %d entries, " "next hash: %x\n", count, *next_hash)); return count; errout: - dx_release(frames); + dx_release(dir, frames); return (err); } @@ -1763,7 +1777,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir, errout: dxtrace(printk(KERN_DEBUG "%s not found\n", fname->usr_fname->name)); success: - dx_release(frames); + dx_release(dir, frames); return bh; } @@ -1860,7 +1874,7 @@ dx_move_dirents(struct inode *dir, char *from, char *to, while (count--) { struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *) (from + (map->offs<<2)); - rec_len = ext4_dir_rec_len(de->name_len, dir); + rec_len = ext4_dir_entry_len(de, blocksize, dir); memcpy (to, de, rec_len); ((struct ext4_dir_entry_2 *) to)->rec_len = @@ -1893,7 +1907,7 @@ static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base, while ((char*)de < base + blocksize) { next = ext4_next_entry(de, blocksize); if (de->inode && de->name_len) { - rec_len = ext4_dir_rec_len(de->name_len, dir); + rec_len = ext4_dir_entry_len(de, blocksize, dir); if (de > to) memmove(to, de, rec_len); to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); @@ -2045,10 +2059,11 @@ static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir, int ext4_find_dest_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size, struct ext4_filename *fname, - struct ext4_dir_entry_2 **dest_de) + struct ext4_dir_entry_2 **dest_de, + int dlen) { struct ext4_dir_entry_2 *de; - unsigned short reclen = ext4_dir_rec_len(fname_len(fname), dir); + unsigned short reclen = ext4_dirent_rec_len(fname_len(fname) + dlen, dir); int nlen, rlen; unsigned int offset = 0; char *top; @@ -2061,7 +2076,7 @@ int ext4_find_dest_de(struct inode *dir, struct buffer_head *bh, return -EFSCORRUPTED; if (ext4_match(dir, fname, de)) return -EEXIST; - nlen = ext4_dir_rec_len(de->name_len, dir); + nlen = ext4_dir_entry_len(de, buf_size, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if ((de->inode ? rlen - nlen : rlen) >= reclen) break; @@ -2084,7 +2099,7 @@ void ext4_insert_dentry(struct inode *dir, int nlen, rlen; - nlen = ext4_dir_rec_len(de->name_len, dir); + nlen = ext4_dir_entry_len(de, buf_size, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if (de->inode) { struct ext4_dir_entry_2 *de1 = @@ -2122,14 +2137,18 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, { unsigned int blocksize = dir->i_sb->s_blocksize; int csum_size = 0; - int err, err2; + int err, err2, dlen = 0; + unsigned char *data = NULL; + /* Deliver data in any appropriate way here. Now it is NULL */ if (ext4_has_feature_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (!de) { + if (data) + dlen = (*data) + 1; err = ext4_find_dest_de(dir, bh, bh->b_data, - blocksize - csum_size, fname, &de); + blocksize - csum_size, fname, &de, dlen); if (err) return err; } @@ -2284,7 +2303,12 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, blocksize); /* initialize hashing info */ - dx_info = dx_get_dx_info(dot_de); + dx_info = dx_get_dx_info(dir, dot_de); + if (IS_ERR(dx_info)) { + brelse(bh2); + brelse(bh); + return PTR_ERR(dx_info); + } memset(dx_info, 0, sizeof(*dx_info)); dx_info->info_length = sizeof(*dx_info); if (ext4_hash_in_dirent(dir)) @@ -2342,7 +2366,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, */ if (retval) ext4_mark_inode_dirty(handle, dir); - dx_release(frames); + dx_release(dir, frames); brelse(bh2); return retval; } @@ -2617,8 +2641,13 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, /* Set up root */ dx_set_count(entries, 1); dx_set_block(entries + 0, newblock); - info = dx_get_dx_info((struct ext4_dir_entry_2 *) + info = dx_get_dx_info(dir, (struct ext4_dir_entry_2 *) frames[0].bh->b_data); + if (IS_ERR(info)) { + err = PTR_ERR(info); + brelse(bh2); + goto journal_error; + } info->indirect_levels += 1; dxtrace(printk(KERN_DEBUG "Creating %d level index...\n", @@ -2646,7 +2675,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname, ext4_std_error(dir->i_sb, err); /* this is a no-op if err == 0 */ cleanup: brelse(bh); - dx_release(frames); + dx_release(dir, frames); /* @restart is true means htree-path has been changed, we need to * repeat dx_probe() to find out valid htree-path */ @@ -2938,7 +2967,7 @@ int ext4_init_dirblock(handle_t *handle, struct inode *inode, de->inode = cpu_to_le32(inode->i_ino); de->name_len = 1; - de->rec_len = ext4_rec_len_to_disk(ext4_dir_rec_len(de->name_len, NULL), + de->rec_len = ext4_rec_len_to_disk(ext4_dirent_rec_len(de->name_len, NULL), blocksize); memcpy(de->name, ".", 2); ext4_set_de_type(inode->i_sb, de, S_IFDIR); @@ -2950,7 +2979,7 @@ int ext4_init_dirblock(handle_t *handle, struct inode *inode, ext4_set_de_type(inode->i_sb, de, S_IFDIR); if (inline_buf) { de->rec_len = ext4_rec_len_to_disk( - ext4_dir_rec_len(de->name_len, NULL), + ext4_dirent_rec_len(de->name_len, NULL), blocksize); de = ext4_next_entry(de, blocksize); header_size = (char *)de - bh->b_data; @@ -2959,7 +2988,7 @@ int ext4_init_dirblock(handle_t *handle, struct inode *inode, blocksize - csum_size); } else { de->rec_len = ext4_rec_len_to_disk(blocksize - - (csum_size + ext4_dir_rec_len(1, NULL)), + (csum_size + ext4_dirent_rec_len(1, NULL)), blocksize); } @@ -3082,8 +3111,8 @@ bool ext4_empty_dir(struct inode *inode) } sb = inode->i_sb; - if (inode->i_size < ext4_dir_rec_len(1, NULL) + - ext4_dir_rec_len(2, NULL)) { + if (inode->i_size < ext4_dirent_rec_len(1, NULL) + + ext4_dirent_rec_len(2, NULL)) { EXT4_ERROR_INODE(inode, "invalid size"); return false; } -- 2.43.7 From: Artem Blagodarenko When fscrypt and casefold are enabled together for a directory, all ext4_dir_entry[_2] in that directory store a n 8-byte hash of the filename after 'name' between 'name_len' and 'rec_len'. However, there is no clear indication there is important data stored in these bytes, which are only for padding and alignment in other directory entries. This adds complexity to code handling the on-disk directory entries, and there is no provision for other metadata to be stored in each dir entry after 'name'. The dirdata feature adds a mechanism to store multiple metadata entries in each dir entry after 'name' (including the fchash). The unused high 4 bits of 'file_type' are used to indicate whether additional data fields are stored after 'name'. If a bit is set, the corresponding dirdata record is present, starting after a NUL filename terminator. If present, a record starts with a 1-byte length (including the length byte itself) and the data immediately follows the length byte without any alignment. This allows up to four different dirdata records to be stored in each entry, and allows unhandled record bytes to be skipped without having to process the contents, providing forward compatibility. If and when the fourth and last dirdata record is needed, it is recommended to further subdivide it into sub-records, with the first byte being the total length, and then there being a second byte that gives the sub-record length, etc. as long as the total record length is less than 255 bytes. However, this would not affect compatibility with the current code since the record length would allow it to be skipped without processing. Signed-off-by: Pravin Shelar Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- fs/ext4/ext4.h | 27 +++++++++++++++++++++------ fs/ext4/inline.c | 23 +++++++++++++++++++---- fs/ext4/namei.c | 45 +++++++++++++++++++++++---------------------- fs/ext4/sysfs.c | 2 ++ 4 files changed, 65 insertions(+), 32 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 2fc9fa6d3021..1e61ce13ed07 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2334,6 +2334,7 @@ EXT4_FEATURE_INCOMPAT_FUNCS(casefold, CASEFOLD) EXT4_FEATURE_INCOMPAT_FLEX_BG| \ EXT4_FEATURE_INCOMPAT_EA_INODE| \ EXT4_FEATURE_INCOMPAT_MMP | \ + EXT4_FEATURE_INCOMPAT_DIRDATA | \ EXT4_FEATURE_INCOMPAT_INLINE_DATA | \ EXT4_FEATURE_INCOMPAT_ENCRYPT | \ EXT4_FEATURE_INCOMPAT_CASEFOLD | \ @@ -3035,10 +3036,18 @@ extern int ext4_find_dest_de(struct inode *dir, struct buffer_head *bh, struct ext4_filename *fname, struct ext4_dir_entry_2 **dest_de, int dlen); -void ext4_insert_dentry(struct inode *dir, struct inode *inode, - struct ext4_dir_entry_2 *de, - int buf_size, - struct ext4_filename *fname); +void ext4_insert_dentry_data(struct inode *dir, struct inode *inode, + struct ext4_dir_entry_2 *de, + int buf_size, + struct ext4_filename *fname, + void *data); +static inline void ext4_insert_dentry(struct inode *dir, struct inode *inode, + struct ext4_dir_entry_2 *de, + int buf_size, + struct ext4_filename *fname) +{ + ext4_insert_dentry_data(dir, inode, de, buf_size, fname, NULL); +} static inline void ext4_update_dx_flag(struct inode *inode) { if (!ext4_has_feature_dir_index(inode->i_sb) && @@ -3283,8 +3292,14 @@ extern int ext4_ext_migrate(struct inode *); extern int ext4_ind_migrate(struct inode *inode); /* namei.c */ -extern int ext4_init_new_dir(handle_t *handle, struct inode *dir, - struct inode *inode); +extern int ext4_init_new_dir_data(handle_t *handle, struct inode *dir, + struct inode *inode, + const void *data1, const void *data2); +static inline int ext4_init_new_dir(handle_t *handle, struct inode *dir, + struct inode *inode) +{ + return ext4_init_new_dir_data(handle, dir, inode, NULL, NULL); +} extern int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 5b3faacdf143..1fff4defd45b 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -973,11 +973,16 @@ static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_iloc *iloc, void *inline_start, int inline_size) { - int err; + int err, dlen = 0; struct ext4_dir_entry_2 *de; + unsigned char *data = NULL; + + /* Deliver data in any appropriate way here. Now it is NULL */ + if (data) + dlen = (*data) + 1; err = ext4_find_dest_de(dir, iloc->bh, inline_start, - inline_size, fname, &de, 0); + inline_size, fname, &de, dlen); if (err) return err; @@ -986,7 +991,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, EXT4_JTR_NONE); if (err) return err; - ext4_insert_dentry(dir, inode, de, inline_size, fname); + ext4_insert_dentry_data(dir, inode, de, inline_size, fname, NULL); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); @@ -1326,7 +1331,17 @@ int ext4_inlinedir_to_tree(struct file *dir_file, pos = EXT4_INLINE_DOTDOT_SIZE; } else { de = (struct ext4_dir_entry_2 *)(dir_buf + pos); - pos += ext4_rec_len_from_disk(de->rec_len, inline_size); + /* Use ext4_dir_entry_len to account for dirdata extensions. + * This buffer is the inline-data buffer (inline_size bytes), + * not a full directory block -- pass the real buffer size so + * a corrupted/sentinel on-disk rec_len doesn't get decoded as + * a full block's worth of bytes. */ + pos += ext4_dir_entry_len(de, inline_size, dir); + /* Validate pos doesn't exceed buffer to prevent use-after-free */ + if (pos > inline_size) { + ret = count; + goto out; + } if (ext4_check_dir_entry(inode, dir_file, de, iloc.bh, dir_buf, inline_size, pos)) { diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 73c8f1b399ef..91def9e0f84d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -401,23 +401,26 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode, { struct ext4_dir_entry_2 *de; struct dx_root_info *root; - int count_offset; + int count_offset, dotdot_rec_len; int blocksize = EXT4_BLOCK_SIZE(inode->i_sb); unsigned int rlen = ext4_rec_len_from_disk(dirent->rec_len, blocksize); - if (rlen == blocksize) + if (rlen == blocksize) { count_offset = sizeof(struct dx_node); - else if (rlen == 12) { - de = (struct ext4_dir_entry_2 *)(((void *)dirent) + 12); - if (ext4_rec_len_from_disk(de->rec_len, blocksize) != blocksize - 12) + } else { + de = (struct ext4_dir_entry_2 *)(((char *)dirent) + rlen); + if (le16_to_cpu(de->rec_len) != (blocksize - rlen)) return NULL; - root = (struct dx_root_info *)(((void *)de + 12)); + /* de->rec_len covers whole dx_root block, calculate actual length. + * This is the '..' entry, which never carries the casefold+fscrypt + * hash, so pass NULL for dir regardless of the directory's flags */ + dotdot_rec_len = ext4_dir_entry_len(de, blocksize, NULL); + root = (struct dx_root_info *)(((char *)de + dotdot_rec_len)); if (root->reserved_zero || root->info_length != sizeof(struct dx_root_info)) return NULL; - count_offset = 32; - } else - return NULL; + count_offset = root->info_length + rlen + dotdot_rec_len; + } if (offset) *offset = count_offset; @@ -716,7 +719,7 @@ static struct stats dx_show_leaf(struct inode *dir, (unsigned) ((char *) de - base)); #endif } - space += ext4_dir_rec_len(de->name_len, dir); + space += ext4_dir_entry_len(de, size, dir); names++; } de = ext4_next_entry(de, size); @@ -2090,13 +2093,10 @@ int ext4_find_dest_de(struct inode *dir, struct buffer_head *bh, return 0; } -void ext4_insert_dentry(struct inode *dir, - struct inode *inode, - struct ext4_dir_entry_2 *de, - int buf_size, - struct ext4_filename *fname) +void ext4_insert_dentry_data(struct inode *dir, struct inode *inode, + struct ext4_dir_entry_2 *de, int buf_size, + struct ext4_filename *fname, void *data) { - int nlen, rlen; nlen = ext4_dir_entry_len(de, buf_size, dir); @@ -2138,15 +2138,15 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, unsigned int blocksize = dir->i_sb->s_blocksize; int csum_size = 0; int err, err2, dlen = 0; - unsigned char *data = NULL; + struct ext4_dirent_fid *dfid = NULL; /* Deliver data in any appropriate way here. Now it is NULL */ if (ext4_has_feature_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); if (!de) { - if (data) - dlen = (*data) + 1; + if (dfid) + dlen = dfid->df_header.ddh_length; err = ext4_find_dest_de(dir, bh, bh->b_data, blocksize - csum_size, fname, &de, dlen); if (err) @@ -2161,7 +2161,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, } /* By now the buffer is marked for journaling */ - ext4_insert_dentry(dir, inode, de, blocksize, fname); + ext4_insert_dentry_data(dir, inode, de, blocksize, fname, dfid); /* * XXX shouldn't update any times until successful @@ -3000,8 +3000,9 @@ int ext4_init_dirblock(handle_t *handle, struct inode *inode, return ext4_handle_dirty_dirblock(handle, inode, bh); } -int ext4_init_new_dir(handle_t *handle, struct inode *dir, - struct inode *inode) +int ext4_init_new_dir_data(handle_t *handle, struct inode *dir, + struct inode *inode, + const void *data1, const void *data2) { struct buffer_head *dir_block = NULL; ext4_lblk_t block = 0; diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c index 923b375e017f..80074fb15ee9 100644 --- a/fs/ext4/sysfs.c +++ b/fs/ext4/sysfs.c @@ -362,6 +362,7 @@ EXT4_ATTR_FEATURE(verity); #endif EXT4_ATTR_FEATURE(metadata_csum_seed); EXT4_ATTR_FEATURE(fast_commit); +EXT4_ATTR_FEATURE(dirdata); #if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) EXT4_ATTR_FEATURE(encrypted_casefold); #endif @@ -385,6 +386,7 @@ static struct attribute *ext4_feat_attrs[] = { #endif ATTR_LIST(metadata_csum_seed), ATTR_LIST(fast_commit), + ATTR_LIST(dirdata), #if IS_ENABLED(CONFIG_UNICODE) && defined(CONFIG_FS_ENCRYPTION) ATTR_LIST(encrypted_casefold), #endif -- 2.43.7 From: Artem Blagodarenko Add helpers to set and retrieve dirdata payload and hook them up at the appropriate call sites. Enable dirdata for casefold+encryption hashes and storing unique 128-bit file identifier in the directory entry for testing. Signed-off-by: Artem Blagodarenko Reviewed-by: Andreas Dilger --- foofile.txt | 0 fs/ext4/ext4.h | 4 + fs/ext4/inline.c | 6 +- fs/ext4/namei.c | 227 +++++++++++++++++++++++++++++++++++++++++------ 4 files changed, 207 insertions(+), 30 deletions(-) diff --git a/foofile.txt b/foofile.txt new file mode 100644 index 000000000000..e69de29bb2d1 diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1e61ce13ed07..5674a64f830f 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -3874,6 +3874,10 @@ extern int __ext4_unlink(struct inode *dir, const struct qstr *d_name, struct inode *inode, struct dentry *dentry); extern int __ext4_link(struct inode *dir, struct inode *inode, const struct qstr *d_name, struct dentry *dentry); +extern unsigned char ext4_dirdata_get(struct ext4_dir_entry_2 *de, + struct inode *dir, + struct ext4_dirent_fid *lufid, + struct dx_hash_info *hinfo); #define S_SHIFT 12 static const unsigned char ext4_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = { diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 1fff4defd45b..32b4ff83d4df 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1350,10 +1350,8 @@ int ext4_inlinedir_to_tree(struct file *dir_file, } } - if (ext4_hash_in_dirent(dir)) { - hinfo->hash = EXT4_DIRENT_HASH(de); - hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); - } else { + if (!(ext4_dirdata_get(de, dir, NULL, hinfo) & + EXT4_DIRENT_CFHASH)) { err = ext4fs_dirhash(dir, de->name, de->name_len, hinfo); if (err) { ret = err; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 91def9e0f84d..6fba1a7c0876 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -1108,22 +1108,22 @@ static int htree_dirblock_to_tree(struct file *dir_file, /* silently ignore the rest of the block */ break; } - if (ext4_hash_in_dirent(dir)) { - if (de->name_len && de->inode) { - hinfo->hash = EXT4_DIRENT_HASH(de); - hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); - } else { - hinfo->hash = 0; - hinfo->minor_hash = 0; - } + if (de->name_len && de->inode) { + /* check for saved hash first, or generate it from name */ + if (!(ext4_dirdata_get(de, dir, NULL, hinfo) & + EXT4_DIRENT_CFHASH)) { + err = ext4fs_dirhash(dir, de->name, + de->name_len, hinfo); + if (err < 0) { + count = err; + goto errout; + } + } } else { - err = ext4fs_dirhash(dir, de->name, - de->name_len, hinfo); - if (err < 0) { - count = err; - goto errout; - } + hinfo->hash = 0; + hinfo->minor_hash = 0; } + if ((hinfo->hash < start_hash) || ((hinfo->hash == start_hash) && (hinfo->minor_hash < start_minor_hash))) @@ -1301,9 +1301,191 @@ static inline int search_dirblock(struct buffer_head *bh, */ /* - * Create map of hash values, offsets, and sizes, stored at end of block. - * Returns number of entries mapped. + * ext4_dirdata_get() - Read dirdata fields from a directory entry. + * @de: directory entry + * @dir: directory inode (used for fscrypt+casefold hash fallback) + * @dfid: if non-NULL and EXT4_DIRENT_LUFID is set, LUFID data is copied + * here + * @hinfo: if non-NULL, receives the casefold hash and minor hash + * + * Reads any dirdata stored in @de. If the dirdata feature is not enabled, + * falls back to reading the hash stored inline after the filename (for + * compatibility with the older casefold+fscrypt format). + * + * Returns a bitmask of EXT4_DIRENT_* flags indicating which fields were read. + */ +unsigned char ext4_dirdata_get(struct ext4_dir_entry_2 *de, struct inode *dir, + struct ext4_dirent_fid *dfid, + struct dx_hash_info *hinfo) +{ + unsigned char ret = 0; + unsigned int data_offset = de->name_len + 1; + unsigned int rec_len = ext4_rec_len_from_disk(de->rec_len, + dir->i_sb->s_blocksize); + + /* data_offset is relative to de->name, which itself starts + * EXT4_BASE_DIR_LEN bytes into the entry -- rec_len is relative to + * the start of the entry, so add the header size before comparing, + * or this lets reads run EXT4_BASE_DIR_LEN bytes past the entry. */ + if (EXT4_BASE_DIR_LEN + data_offset > rec_len) + return ret; + + /* compatibility: hash stored inline after filename (no dirdata) */ + if (hinfo && !ext4_has_feature_dirdata(dir->i_sb) && + ext4_hash_in_dirent(dir)) { + hinfo->hash = EXT4_DIRENT_HASH(de); + hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de); + ret |= EXT4_DIRENT_CFHASH; + + return ret; + } + + /* EXT4_DIRENT_* are not expected without flag in i_sb */ + if (de->file_type & EXT4_DIRENT_LUFID) { + struct ext4_dirent_fid *disk_fid = + (struct ext4_dirent_fid *)(de->name + data_offset); + unsigned int dlen; + + if (EXT4_BASE_DIR_LEN + data_offset + sizeof(disk_fid->df_header) > rec_len) + return ret; + + dlen = disk_fid->df_header.ddh_length; + if (dlen < sizeof(*disk_fid) || + EXT4_BASE_DIR_LEN + data_offset + dlen > rec_len) + return ret; + + if (dfid) { + /* copy the whole record (header + fid), not just the fid + * payload -- dlen already includes the header's length */ + memcpy(dfid, disk_fid, dlen); + ret |= EXT4_DIRENT_LUFID; + } + data_offset += dlen; + } + + /* Skip INO64 for now*/ + if (de->file_type & EXT4_DIRENT_INO64) { + struct ext4_dirent_data_header *ddh = + (struct ext4_dirent_data_header *)(de->name + data_offset); + unsigned int dlen; + + if (EXT4_BASE_DIR_LEN + data_offset + sizeof(*ddh) > rec_len) + return ret; + + dlen = ddh->ddh_length; + if (dlen < sizeof(*ddh) || + EXT4_BASE_DIR_LEN + data_offset + dlen > rec_len) + return ret; + + data_offset += dlen; + } + + if (!hinfo) + return ret; + + if (de->file_type & EXT4_DIRENT_CFHASH) { + struct ext4_dirent_hash *dh = + (struct ext4_dirent_hash *)(de->name + data_offset); + unsigned int dlen; + + dlen = dh->dh_header.ddh_length; + if (dlen < sizeof(*dh) || + EXT4_BASE_DIR_LEN + data_offset + dlen > rec_len) + return ret; + + hinfo->hash = le32_to_cpu(dh->dh_hash.hash); + hinfo->minor_hash = le32_to_cpu(dh->dh_hash.minor_hash); + ret |= EXT4_DIRENT_CFHASH; + } + + return ret; +} + +/* + * ext4_dirdata_set() - Write dirdata fields into a directory entry. + * @de: directory entry (name must already be set) + * @dir: directory inode + * @data: LUFID data to store (or NULL) + * @fname: filename info carrying the casefold hash + * + * Writes any required dirdata into @de after the filename. If the dirdata + * feature is not enabled, falls back to writing the hash inline after the + * filename (for compatibility with the older casefold+fscrypt format). */ +static void ext4_dirdata_set(struct ext4_dir_entry_2 *de, struct inode *dir, + struct ext4_dirent_fid *dfid, + struct ext4_filename *fname) +{ + struct dx_hash_info *hinfo = &fname->hinfo; + unsigned int data_offset = de->name_len + 1; + unsigned int rec_len = ext4_rec_len_from_disk(de->rec_len, + dir->i_sb->s_blocksize); + + /* de->name[] is declared with a fixed EXT4_NAME_LEN size, but the + * real backing storage is this entry's rec_len-sized space in the + * directory block; a max-length name (name_len == EXT4_NAME_LEN) + * leaves no declared array slot for the NUL terminator below, which + * FORTIFY_SOURCE treats as an out-of-bounds array write regardless + * of how much real space the entry has. */ + if (dfid && de->name_len >= EXT4_NAME_LEN) { + EXT4_ERROR_INODE(dir, "Can not insert FID: name_len too long"); + return; + } + + /* always clear the gap byte at de->name[de->name_len], even when no + * FID is being appended -- otherwise it's never initialized before + * dirdata is written right after it, leaking a byte of stale memory + * to disk. Skip it for a max-length name: there's no declared array + * slot for it, and no dirdata can be appended in that case anyway + * (rejected above for dfid; data_offset would already be >= rec_len + * for any other dirdata kind). */ + if (de->name_len < EXT4_NAME_LEN) + de->name[de->name_len] = 0; + + if (dfid) { + unsigned int dlen = dfid->df_header.ddh_length; + + if (EXT4_BASE_DIR_LEN + data_offset + dlen > rec_len) { + EXT4_ERROR_INODE(dir, "Can not insert FID"); + return; + } + + memcpy(&de->name[de->name_len + 1], dfid, + dlen); + de->file_type |= EXT4_DIRENT_LUFID; + data_offset += dlen; + } + + if (ext4_hash_in_dirent(dir)) { + if (ext4_has_feature_dirdata(dir->i_sb)) { + struct ext4_dirent_hash *dh = + (struct ext4_dirent_hash *)(de->name + data_offset); + + if (EXT4_BASE_DIR_LEN + data_offset + sizeof(*dh) > rec_len) { + EXT4_ERROR_INODE(dir, "Can not insert dhash dirdata"); + return; + } + + dh->dh_header.ddh_length = sizeof(*dh); + dh->dh_hash.hash = cpu_to_le32(hinfo->hash); + dh->dh_hash.minor_hash = cpu_to_le32(hinfo->minor_hash); + de->file_type |= EXT4_DIRENT_CFHASH; + } else { + /* Compatibility: store hash inline after filename */ + if (EXT4_BASE_DIR_LEN + data_offset + + sizeof(struct ext4_dir_entry_hash) > rec_len) { + EXT4_ERROR_INODE(dir, "Can not insert dhash"); + return; + } + + EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo->hash); + EXT4_DIRENT_HASHES(de)->minor_hash = + cpu_to_le32(hinfo->minor_hash); + } + } +} + + static int dx_make_map(struct inode *dir, struct buffer_head *bh, struct dx_hash_info *hinfo, struct dx_map_entry *map_tail) @@ -1323,9 +1505,8 @@ static int dx_make_map(struct inode *dir, struct buffer_head *bh, ((char *)de) - base)) return -EFSCORRUPTED; if (de->name_len && de->inode) { - if (ext4_hash_in_dirent(dir)) - h.hash = EXT4_DIRENT_HASH(de); - else { + if (!(ext4_dirdata_get(de, dir, NULL, &h) & + EXT4_DIRENT_CFHASH)) { int err = ext4fs_dirhash(dir, de->name, de->name_len, &h); if (err < 0) @@ -2113,13 +2294,7 @@ void ext4_insert_dentry_data(struct inode *dir, struct inode *inode, ext4_set_de_type(inode->i_sb, de, inode->i_mode); de->name_len = fname_len(fname); memcpy(de->name, fname_name(fname), fname_len(fname)); - if (ext4_hash_in_dirent(dir)) { - struct dx_hash_info *hinfo = &fname->hinfo; - - EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo->hash); - EXT4_DIRENT_HASHES(de)->minor_hash = - cpu_to_le32(hinfo->minor_hash); - } + ext4_dirdata_set(de, dir, data, fname); } /* -- 2.43.7 From: Artem Blagodarenko Add a new ioctl command that allows setting LUFID (Locally Unique File ID) data on existing directory entries. This includes: - ext4_ioctl_set_lufid(): ioctl handler that validates parameters and calls the underlying implementation - ext4_set_direntry_lufid(): Core function that performs the operation by: * Looking up the target directory entry * Retrieving the associated inode * Deleting the old entry and re-creating it with LUFID data attached This implementation requires the dirdata feature to be enabled on the filesystem and properly handles transactions and inode locking to ensure consistency. Signed-off-by: Artem Blagodarenko artem.blagodarenko@gmail.com Reviewed-by: Andreas Dilger --- fs/ext4/ext4.h | 15 ++++ fs/ext4/ioctl.c | 84 +++++++++++++++++++++ fs/ext4/namei.c | 155 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/ext4.h | 13 ++++ 4 files changed, 267 insertions(+) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5674a64f830f..252a5a529205 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1227,6 +1227,7 @@ struct ext4_inode_info { #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_inode_info *i_crypt_info; #endif + void *i_dirdata; }; /* @@ -2601,6 +2602,18 @@ struct ext4_dirent_hash { struct ext4_dir_entry_hash dh_hash; } __packed; +static inline +struct ext4_dirent_fid *ext4_dentry_get_fid(struct super_block *sb, + struct ext4_dentry_param *p) +{ + if (!ext4_has_feature_dirdata(sb)) + return NULL; + if (p && p->edp_magic == EXT4_LUFID_MAGIC) + return &p->edp_dfid; + + return NULL; +} + #define EXT4_FT_DIR_CSUM 0xDE /* @@ -3302,6 +3315,8 @@ static inline int ext4_init_new_dir(handle_t *handle, struct inode *dir, } extern int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh); +extern int ext4_dirdata_set_lufid(struct inode *dir, const char *filename, + int namelen, struct ext4_dentry_param *edp); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, __u32 start_minor_hash, __u32 *next_hash); extern int ext4_search_dir(struct buffer_head *bh, diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c index c8387e6a2c6e..725e46e1e46d 100644 --- a/fs/ext4/ioctl.c +++ b/fs/ext4/ioctl.c @@ -1535,6 +1535,87 @@ static int ext4_ioctl_set_tune_sb(struct file *filp, return ret; } +/* + * ext4_ioctl_set_lufid() - Set LUFID on a directory entry + * @filp: file pointer (parent directory) + * @arg: pointer to ext4_set_lufid structure with filename and LUFID data + * + * This ioctl allows setting LUFID data on an existing + * directory entry. It is called on the parent directory with a filename and + * LUFID data. + */ +static long ext4_ioctl_set_lufid(struct file *filp, unsigned long arg) +{ + struct inode *dir = file_inode(filp); + struct mnt_idmap *idmap = file_mnt_idmap(filp); + struct ext4_set_lufid lufid_args; + struct { + __u32 edp_magic; + struct ext4_dirent_data_header df_header; + char df_fid[255]; + } edp; + int err; + + /* Check if parent is a directory */ + if (!S_ISDIR(dir->i_mode)) + return -ENOTDIR; + + /* This ioctl mutates directory entries; merely having the directory + * open (which only ever requires read access) is not enough */ + err = inode_permission(idmap, dir, MAY_WRITE); + if (err) + return err; + + /* Copy arguments from user space */ + if (copy_from_user(&lufid_args, (struct ext4_set_lufid __user *)arg, + sizeof(lufid_args))) + return -EFAULT; + + /* Validate parameters */ + if (lufid_args.esl_name_len == 0 || lufid_args.esl_name_len > EXT4_NAME_LEN) + return -EINVAL; + + /* ddh_length (esl_data_len + the header byte below) must itself fit + * in the __u8 ddh_length field without wrapping */ + if (lufid_args.esl_data_len == 0 || + lufid_args.esl_data_len > 255 - sizeof(edp.df_header)) + return -EINVAL; + + /* Ensure filename is NUL-terminated and unmodified */ + if (lufid_args.esl_name[lufid_args.esl_name_len - 1] != '\0') + return -EINVAL; + + /* '.' and '..' are not ordinary entries -- they must stay the first + * two entries in the directory's first block, so they can't go + * through the general delete+re-add path this ioctl uses */ + if (!strcmp(lufid_args.esl_name, ".") || !strcmp(lufid_args.esl_name, "..")) + return -EINVAL; + + /* Prepare the dentry param struct with LUFID data. ddh_length is + * documented (see struct ext4_dirent_data_header) as the length of + * the header plus the whole data blob -- include the header here so + * every dirdata reader/writer that takes ddh_length at face value + * (e.g. ext4_dirdata_set()'s memcpy) copies the full LUFID payload + * instead of silently dropping its last byte. */ + edp.edp_magic = EXT4_LUFID_MAGIC; + edp.df_header.ddh_length = lufid_args.esl_data_len + + sizeof(edp.df_header); + memcpy(edp.df_fid, lufid_args.esl_data, lufid_args.esl_data_len); + + /* Want write access */ + err = mnt_want_write_file(filp); + if (err) + return err; + + /* Call the helper function to do the actual work */ + err = ext4_dirdata_set_lufid(dir, lufid_args.esl_name, + lufid_args.esl_name_len - 1, + (struct ext4_dentry_param *)&edp); + + mnt_drop_write_file(filp); + return err; +} + static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); @@ -1921,6 +2002,8 @@ static long __ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) (void __user *)arg); case EXT4_IOC_SET_TUNE_SB_PARAM: return ext4_ioctl_set_tune_sb(filp, (void __user *)arg); + case EXT4_IOC_SET_LUFID: + return ext4_ioctl_set_lufid(filp, arg); default: return -ENOTTY; } @@ -2000,6 +2083,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) case FS_IOC_SETFSLABEL: case EXT4_IOC_GETFSUUID: case EXT4_IOC_SETFSUUID: + case EXT4_IOC_SET_LUFID: break; default: return -ENOIOCTLCMD; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 6fba1a7c0876..3aeea503f12d 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -2319,6 +2319,8 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, if (ext4_has_feature_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); + dfid = ext4_dentry_get_fid(inode->i_sb, + (struct ext4_dentry_param *)EXT4_I(inode)->i_dirdata); if (!de) { if (dfid) dlen = dfid->df_header.ddh_length; @@ -2665,6 +2667,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, { struct inode *dir = d_inode(dentry->d_parent); + EXT4_I(inode)->i_dirdata = dentry->d_fsdata; if (fscrypt_is_nokey_name(dentry)) return -ENOKEY; return __ext4_add_entry(handle, dir, &dentry->d_name, inode); @@ -4426,6 +4429,158 @@ static int ext4_rename2(struct mnt_idmap *idmap, return ext4_rename(idmap, old_dir, old_dentry, new_dir, new_dentry, flags); } +/* + * ext4_dirdata_set_lufid() - Set LUFID data on an existing directory entry + * @dir: parent directory inode + * @filename: name of the file in the directory + * @namelen: length of filename + * @edp: pointer to initialized dentry param with LUFID data + * + * This function finds an existing directory entry, deletes it, and re-creates it + * with LUFID data attached. Used by the EXT4_IOC_SET_LUFID ioctl. + * + * Returns 0 on success, negative error code on failure. + */ +int ext4_dirdata_set_lufid(struct inode *dir, const char *filename, + int namelen, struct ext4_dentry_param *edp) +{ + struct super_block *sb = dir->i_sb; + struct ext4_filename fname; + struct ext4_dir_entry_2 *de = NULL; + struct buffer_head *bh = NULL; + struct inode *inode = NULL; + handle_t *handle = NULL; + struct qstr d_name; + void *old_dirdata = NULL; + int err = 0; + + /* Check if dirdata feature is enabled */ + if (!ext4_has_feature_dirdata(sb)) + return -ENOTSUPP; + + if (namelen > EXT4_NAME_LEN) + return -ENAMETOOLONG; + if (namelen != strnlen(filename, namelen + 1)) + return -EINVAL; + + /* Setup the filename for lookup */ + d_name.name = filename; + d_name.len = namelen; + + /* Lookup the filename in the directory */ + err = ext4_fname_setup_filename(dir, &d_name, 0, &fname); + if (err) + goto out_free; + + bh = ext4_find_entry(dir, &d_name, &de, NULL); + if (!bh) { + err = -ENOENT; + goto out_free; + } + + /* Get the inode number from the directory entry */ + inode = ext4_iget(sb, le32_to_cpu(de->inode), EXT4_IGET_NORMAL); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + inode = NULL; + goto out_brelse; + } + + /* Start a transaction */ + handle = ext4_journal_start(dir, EXT4_HT_DIR, + 2 * EXT4_DATA_TRANS_BLOCKS(sb) + + EXT4_INDEX_EXTRA_TRANS_BLOCKS); + if (IS_ERR(handle)) { + err = PTR_ERR(handle); + handle = NULL; + goto out_iput; + } + + inode_lock(dir); + + /* EXT4_I(inode)->i_dirdata below is a *shared* per-inode field used + * to smuggle the LUFID payload into ext4_add_entry(); locking only + * dir does not stop a concurrent EXT4_IOC_SET_LUFID call targeting a + * different hardlink of the same inode (different dir, same inode) + * from clobbering it mid-call with its own stack-local pointer. + * Lock the target inode too, consistently dir-then-inode, to + * serialize the i_dirdata set/use/restore window below. */ + if (inode != dir) + inode_lock_nested(inode, I_MUTEX_NONDIR2); + + /* Delete the old entry */ + err = ext4_delete_entry(handle, dir, de, bh); + if (err) + goto out_unlock; + + brelse(bh); + bh = NULL; + + /* Re-add the entry with LUFID data + * We set i_dirdata before adding so the entry can include it + */ + old_dirdata = EXT4_I(inode)->i_dirdata; + EXT4_I(inode)->i_dirdata = edp; + + /* Use ext4_add_entry() to properly handle hash table management + * and block splitting, just like rename does. This ensures the entry + * is placed in the correct hash block and avoids breaking dirhash. + */ + { + struct dentry parent_dentry = { .d_inode = dir }; + struct dentry new_dentry = { + .d_name = d_name, + .d_parent = &parent_dentry, + .d_inode = inode, /* Same inode (in-place update) */ + .d_fsdata = edp, /* required */ + }; + err = ext4_add_entry(handle, &new_dentry, inode); + } + EXT4_I(inode)->i_dirdata = old_dirdata; + + if (err) { + /* + * The original entry was already removed above and the + * re-add with the new LUFID failed; try to restore the + * original entry so the inode isn't left without any + * directory entry pointing at it. + */ + struct dentry parent_dentry = { .d_inode = dir }; + struct dentry orig_dentry = { + .d_name = d_name, + .d_parent = &parent_dentry, + .d_inode = inode, + }; + int rollback_err = ext4_add_entry(handle, &orig_dentry, inode); + + if (rollback_err) + EXT4_ERROR_INODE(dir, + "Failed to set LUFID on '%.*s' (err=%d) and failed to restore the original directory entry (err=%d); inode %llu may be orphaned", + namelen, filename, err, rollback_err, + inode->i_ino); + goto out_unlock; + } + + /* Update inode times */ + inode_set_ctime_current(dir); + inode_inc_iversion(dir); + ext4_mark_inode_dirty(handle, dir); + +out_unlock: + if (inode != dir) + inode_unlock(inode); + inode_unlock(dir); + ext4_journal_stop(handle); +out_iput: + iput(inode); +out_brelse: + brelse(bh); +out_free: + ext4_fname_free_filename(&fname); + + return err; +} + /* * directories can handle most operations... */ diff --git a/include/uapi/linux/ext4.h b/include/uapi/linux/ext4.h index 9c683991c32f..9fab8978843b 100644 --- a/include/uapi/linux/ext4.h +++ b/include/uapi/linux/ext4.h @@ -35,6 +35,7 @@ #define EXT4_IOC_SETFSUUID _IOW('f', 44, struct fsuuid) #define EXT4_IOC_GET_TUNE_SB_PARAM _IOR('f', 45, struct ext4_tune_sb_params) #define EXT4_IOC_SET_TUNE_SB_PARAM _IOW('f', 46, struct ext4_tune_sb_params) +#define EXT4_IOC_SET_LUFID _IOW('f', 47, struct ext4_set_lufid) #define EXT4_IOC_SHUTDOWN _IOR('X', 125, __u32) @@ -92,6 +93,18 @@ struct move_extent { __u64 moved_len; /* moved block length */ }; +/* + * Structure for EXT4_IOC_SET_LUFID + * Sets LUFID on a directory entry + * Called on parent directory with filename and LUFID data as arguments + */ +struct ext4_set_lufid { + __u8 esl_name_len; /* length of filename */ + char esl_name[255 + 1]; /* filename (NUL-terminated) */ + __u8 esl_data_len; /* length of LUFID data */ + char esl_data[255]; /* LUFID data (raw bytes) */ +}; + /* * Flags used by EXT4_IOC_SHUTDOWN */ -- 2.43.7