commit 2db3b2b33ee796f4ea61316773452d936303ad27 Author: Pravin Shelar AuthorDate: Sun Oct 4 18:13:14 2009 +0000 Subject: ext4: add ext4-data-in-dirent patch Allows ext4 to store extra data records inside the ext4_dirent along with the regular directory entry (type, length, filename). Data is stored in ext4 dirent after filename, with a bit flag in de->file_type to indicate if any record after de->name is used. Each in-use record is variable length and must store a 1-byte length (including the length byte itself) at the start so that it can be skipped if the record type is unknown/uneeded. The record starts after a NUL byte terminator for the filename. This extra space is accounted in de->rec_len but not de->name_len. Flag EXT4_DIRENT_LUFID is used for a 128-bit file identifier. Make use of dentry->d_fsdata to pass LUFID to ext4, so no changes in ext4_add_entry() interface are required. Bugzilla-ID: b=17670 Signed-off-by: Pravin Shelar Reviewed-by: Huang Hua Signed-off-by: Andreas Dilger --- fs/ext4/dir.c | 13 ++- fs/ext4/ext4.h | 100 +++++++++++++++++++-- fs/ext4/fast_commit.c | 2 +- fs/ext4/inline.c | 8 +- fs/ext4/namei.c | 201 +++++++++++++++++++++++++++++++++--------- fs/ext4/super.c | 4 +- 6 files changed, 270 insertions(+), 58 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 70a0f5e..ff7d8c3 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -78,7 +78,7 @@ int __ext4_check_dir_entry(const char *function, unsigned int line, 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))) + else if (unlikely(rlen < EXT4_DIR_ENTRY_LEN(de))) error_msg = "rec_len is too small for name_len"; else if (unlikely(next_offset > size)) error_msg = "directory entry overrun"; @@ -226,7 +226,7 @@ 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_DIR_REC_LEN(1)) break; i += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize); @@ -449,12 +449,17 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, struct fname *fname, *new_fn; struct dir_private_info *info; int len; + int extra_data = 0; info = dir_file->private_data; p = &info->root.rb_node; /* Create and allocate the fname structure */ - len = sizeof(struct fname) + ent_name->len + 1; + if (dirent->file_type & EXT4_DIRENT_LUFID) + extra_data = ext4_get_dirent_data_len(dirent); + + len = sizeof(struct fname) + ent_name->len + extra_data + 1; + new_fn = kzalloc(len, GFP_KERNEL); if (!new_fn) return -ENOMEM; @@ -463,7 +468,7 @@ int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, new_fn->inode = le32_to_cpu(dirent->inode); new_fn->name_len = ent_name->len; new_fn->file_type = dirent->file_type; - memcpy(new_fn->name, ent_name->name, ent_name->len); + memcpy(new_fn->name, ent_name->name, ent_name->len + extra_data); while (*p) { parent = *p; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 143ce00..98786d8 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1167,6 +1167,7 @@ struct ext4_inode_info { __u32 i_csum_seed; kprojid_t i_projid; + void *i_dirdata; /* Protect concurrent add cluster delayed block and remove block */ struct mutex i_clu_lock; @@ -1191,6 +1192,7 @@ struct ext4_inode_info { * Mount flags set via mount options or defaults */ #define EXT4_MOUNT_NO_MBCACHE 0x00001 /* Do not use mbcache */ +#define EXT4_MOUNT_DIRDATA 0x00002 /* Data in directory entries */ #define EXT4_MOUNT_GRPID 0x00004 /* Create files with directory's group */ #define EXT4_MOUNT_DEBUG 0x00008 /* Some debugging messages */ #define EXT4_MOUNT_ERRORS_CONT 0x00010 /* Continue on errors */ @@ -2086,6 +2088,7 @@ 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 | \ @@ -2268,6 +2271,43 @@ 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 data. these different + * type of data (e.g. lustre data, high 32 bits of 64-bit inode number) can be + * stored, in flag order, after file-name in ext4 dirent. +*/ +/* + * this flag is 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 start after filename NUL byte. + * This is used by Lustre FS. + */ +#define EXT4_DIRENT_LUFID 0x10 + +#define EXT4_LUFID_MAGIC 0xAD200907UL +struct ext4_dentry_param { + __u32 edp_magic; /* EXT4_LUFID_MAGIC */ + char edp_len; /* size of edp_data in bytes */ + char edp_data[0]; /* packed array of data */ +} __packed; + +static inline unsigned char *ext4_dentry_get_data(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_len; + else + return NULL; +} #define EXT4_FT_DIR_CSUM 0xDE @@ -2278,8 +2318,16 @@ struct ext4_dir_entry_tail { */ #define EXT4_DIR_PAD 4 #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) -#define EXT4_DIR_REC_LEN(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ +#define EXT4_DIR_REC_LEN_(name_len) (((name_len) + 8 + EXT4_DIR_ROUND) & \ ~EXT4_DIR_ROUND) +#define EXT4_DIR_ENTRY_LEN_(de) (EXT4_DIR_REC_LEN_((de)->name_len +\ + ext4_get_dirent_data_len(de))) +/* ldiskfs */ +#define EXT4_DIR_REC_LEN(name_len) EXT4_DIR_REC_LEN_((name_len)) +#define EXT4_DIR_ENTRY_LEN(de) EXT4_DIR_ENTRY_LEN_((de)) +/* lustre osd_handler compat */ +#define __EXT4_DIR_REC_LEN(name_len) EXT4_DIR_REC_LEN_((name_len)) + #define EXT4_MAX_REC_LEN ((1<<16)-1) /* @@ -2746,11 +2794,11 @@ extern int ext4_find_dest_de(struct inode *dir, struct inode *inode, 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 *inode, struct ext4_dir_entry_2 *de, int buf_size, - struct ext4_filename *fname); + struct ext4_filename *fname, void *data); static inline void ext4_update_dx_flag(struct inode *inode) { if (!ext4_has_feature_dir_index(inode->i_sb) && @@ -2766,10 +2814,17 @@ static const unsigned char ext4_filetype_table[] = { static inline unsigned char get_dtype(struct super_block *sb, int filetype) { - if (!ext4_has_feature_filetype(sb) || filetype >= EXT4_FT_MAX) + int 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]; + if (!test_opt(sb, DIRDATA)) + return ext4_filetype_table[fl_index]; + + return (ext4_filetype_table[fl_index]) | + (filetype & EXT4_DIRENT_LUFID); + } extern int ext4_check_all_de(struct inode *dir, struct buffer_head *bh, void *buf, int buf_size); @@ -2965,7 +3020,8 @@ 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); + struct inode *inode, + const void *data1, const void *data2); extern int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh); extern int ext4_orphan_add(handle_t *, struct inode *); @@ -2976,6 +3032,8 @@ extern struct inode *ext4_create_inode(handle_t *handle, extern int ext4_delete_entry(handle_t *handle, struct inode * dir, struct ext4_dir_entry_2 *de_del, struct buffer_head *bh); +extern int ext4_add_dot_dotdot(handle_t *handle, struct inode *dir, + struct inode *inode, const void *, const void *); 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, @@ -3765,6 +3823,36 @@ static inline int ext4_buffer_uptodate(struct buffer_head *bh) return buffer_uptodate(bh); } +/* + * Compute the total directory entry data length. + * This includes the filename and an implicit NUL terminator (always present), + * and optional extensions. Each extension has a bit set in the high 4 bits of + * de->file_type, and the extension length is the first byte in each entry. + */ +static inline int ext4_get_dirent_data_len(struct ext4_dir_entry_2 *de) +{ + char *len = de->name + de->name_len + 1 /* NUL terminator */; + int dlen = 0; + __u8 extra_data_flags = (de->file_type & ~EXT4_FT_MASK) >> 4; + struct ext4_dir_entry_tail *t = (struct ext4_dir_entry_tail *)de; + + if (!t->det_reserved_zero1 && + le16_to_cpu(t->det_rec_len) == + sizeof(struct ext4_dir_entry_tail) && + !t->det_reserved_zero2 && + t->det_reserved_ft == EXT4_FT_DIR_CSUM) + return 0; + + while (extra_data_flags) { + if (extra_data_flags & 1) { + dlen += *len + (dlen == 0); + len += *len; + } + extra_data_flags >>= 1; + } + return dlen; +} + #endif /* __KERNEL__ */ #define EFSBADCRC EBADMSG /* Bad CRC detected */ diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c index 41dcf21..1023ace 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1547,7 +1547,7 @@ static int ext4_fc_replay_create(struct super_block *sb, struct ext4_fc_tl *tl, jbd_debug(1, "Dir %d not found.", darg.ino); goto out; } - ret = ext4_init_new_dir(NULL, dir, inode); + ret = ext4_init_new_dir(NULL, dir, inode, NULL, NULL); iput(dir); if (ret) { ret = 0; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index c2c688c..686d14a 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1033,7 +1033,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, struct ext4_dir_entry_2 *de; err = ext4_find_dest_de(dir, inode, iloc->bh, inline_start, - inline_size, fname, &de); + inline_size, fname, &de, 0); if (err) return err; @@ -1041,7 +1041,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle, err = ext4_journal_get_write_access(handle, iloc->bh); if (err) return err; - ext4_insert_dentry(inode, de, inline_size, fname); + ext4_insert_dentry(inode, de, inline_size, fname, NULL); ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size); @@ -1398,7 +1398,7 @@ int ext4_inlinedir_to_tree(struct file *dir_file, fake.name_len = 1; strcpy(fake.name, "."); fake.rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(fake.name_len), + EXT4_DIR_ENTRY_LEN(&fake), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; @@ -1408,7 +1408,7 @@ int ext4_inlinedir_to_tree(struct file *dir_file, fake.name_len = 2; strcpy(fake.name, ".."); fake.rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(fake.name_len), + EXT4_DIR_ENTRY_LEN(&fake), inline_size); ext4_set_de_type(inode->i_sb, &fake, S_IFDIR); de = &fake; diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c index 1537a76..24e1276 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -295,7 +295,8 @@ static unsigned dx_get_count(struct dx_entry *entries); static unsigned dx_get_limit(struct dx_entry *entries); static void dx_set_count(struct dx_entry *entries, unsigned value); static void dx_set_limit(struct dx_entry *entries, unsigned value); -static 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 infosize); static unsigned dx_node_limit(struct inode *dir); static struct dx_frame *dx_probe(struct ext4_filename *fname, struct inode *dir, @@ -439,22 +440,23 @@ static struct dx_countlimit *get_dx_countlimit(struct inode *inode, { struct ext4_dir_entry *dp; struct dx_root_info *root; - int count_offset; + int count_offset, dot_rec_len, dotdot_rec_len; if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb)) count_offset = 8; - else if (le16_to_cpu(dirent->rec_len) == 12) { - dp = (struct ext4_dir_entry *)(((void *)dirent) + 12); + else { + dot_rec_len = le16_to_cpu(dirent->rec_len); + dp = (struct ext4_dir_entry *)(((void *)dirent) + dot_rec_len); if (le16_to_cpu(dp->rec_len) != - EXT4_BLOCK_SIZE(inode->i_sb) - 12) + EXT4_BLOCK_SIZE(inode->i_sb) - dot_rec_len) return NULL; - root = (struct dx_root_info *)(((void *)dp + 12)); + dotdot_rec_len = EXT4_DIR_ENTRY_LEN((struct ext4_dir_entry_2 *)dp); + root = (struct dx_root_info *)(((void *)dp + 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 = 8 + dot_rec_len + dotdot_rec_len; + } if (offset) *offset = count_offset; @@ -559,11 +561,12 @@ ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize) */ struct dx_root_info *dx_get_dx_info(struct ext4_dir_entry_2 *de) { + BUG_ON(de->name_len != 1); /* get dotdot first */ - de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_REC_LEN(1)); + de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_ENTRY_LEN(de)); /* dx root info is after dotdot entry */ - de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_REC_LEN(2)); + de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_ENTRY_LEN(de)); return (struct dx_root_info *)de; } @@ -608,10 +611,16 @@ 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 infosize) { - unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(1) - - EXT4_DIR_REC_LEN(2) - infosize; + struct ext4_dir_entry_2 *dotdot_de; + unsigned entry_space; + + BUG_ON(dot_de->name_len != 1); + dotdot_de = ext4_next_entry(dot_de, dir->i_sb->s_blocksize); + entry_space = dir->i_sb->s_blocksize - EXT4_DIR_ENTRY_LEN(dot_de) - + EXT4_DIR_ENTRY_LEN(dotdot_de) - infosize; if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -731,7 +740,7 @@ static struct stats dx_show_leaf(struct inode *dir, (unsigned) ((char *) de - base)); #endif } - space += EXT4_DIR_REC_LEN(de->name_len); + space += EXT4_DIR_ENTRY_LEN(de); names++; } de = ext4_next_entry(de, size); @@ -840,11 +849,14 @@ 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, + info->info_length)) { 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, + info->info_length)); goto fail; } @@ -1851,7 +1863,7 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count, 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); + rec_len = EXT4_DIR_ENTRY_LEN(de); memcpy (to, de, rec_len); ((struct ext4_dir_entry_2 *) to)->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); @@ -1882,7 +1894,7 @@ static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize) 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); + rec_len = EXT4_DIR_ENTRY_LEN(de); if (de > to) memmove(to, de, rec_len); to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); @@ -2023,10 +2035,10 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, 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)); + unsigned short reclen = EXT4_DIR_REC_LEN(fname_len(fname) + dlen); int nlen, rlen; unsigned int offset = 0; char *top; @@ -2039,7 +2053,7 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, return -EFSCORRUPTED; if (ext4_match(dir, fname, de)) return -EEXIST; - nlen = EXT4_DIR_REC_LEN(de->name_len); + nlen = EXT4_DIR_ENTRY_LEN(de); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if ((de->inode ? rlen - nlen : rlen) >= reclen) break; @@ -2056,12 +2086,12 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode, void ext4_insert_dentry(struct inode *inode, struct ext4_dir_entry_2 *de, int buf_size, - struct ext4_filename *fname) + struct ext4_filename *fname, void *data) { int nlen, rlen; - nlen = EXT4_DIR_REC_LEN(de->name_len); + nlen = EXT4_DIR_ENTRY_LEN(de); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if (de->inode) { struct ext4_dir_entry_2 *de1 = @@ -2075,6 +2105,11 @@ void ext4_insert_dentry(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 (data) { + de->name[fname_len(fname)] = 0; + memcpy(&de->name[fname_len(fname) + 1], data, *(char *)data); + de->file_type |= EXT4_DIRENT_LUFID; + } } /* @@ -2092,14 +2127,19 @@ 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; + data = ext4_dentry_get_data(inode->i_sb, (struct ext4_dentry_param *) + EXT4_I(inode)->i_dirdata); if (ext4_has_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, inode, bh, bh->b_data, - blocksize - csum_size, fname, &de); + blocksize - csum_size, fname, &de, dlen); if (err) return err; } @@ -2111,7 +2151,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname, } /* By now the buffer is marked for journaling */ - ext4_insert_dentry(inode, de, blocksize, fname); + ext4_insert_dentry(inode, de, blocksize, fname, data); /* * XXX shouldn't update any times until successful @@ -2217,7 +2260,8 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, 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, sizeof(*dx_info))); /* Initialize as for dx_probe */ fname->hinfo.hash_version = dx_info->hash_version; @@ -2259,7 +2282,104 @@ out_frames: return retval; } -/* update ".." entry */ +static int ext4_expand_dotdot(struct inode *dir, + struct buffer_head *bh, + int dlen) +{ + struct ext4_dir_entry_2 *dot_de; + struct ext4_dir_entry_2 *dotdot_de; + int len; + unsigned blocksize = dir->i_sb->s_blocksize; + + dot_de = (struct ext4_dir_entry_2 *)bh->b_data; + dotdot_de = ext4_next_entry(dot_de, blocksize); + + if (is_dx(dir)) { + struct dx_entry *entries; + struct dx_root_info *dx_info; + int limit, count; + int entry_space; + + len = EXT4_DIR_REC_LEN(2 + dlen) - + EXT4_DIR_ENTRY_LEN(dotdot_de); + + dx_info = dx_get_dx_info(dot_de); + entries = (struct dx_entry *)((char *)dx_info + + sizeof(*dx_info)); + count = dx_get_count(entries); + + /* + * figure out new limit with dlen, + * check if we have enough space + */ + entry_space = blocksize; + entry_space -= (char *)dotdot_de - (char *)dot_de + + EXT4_DIR_REC_LEN(2 + dlen) + sizeof(*dx_info); + if (ext4_has_metadata_csum(dir->i_sb)) + entry_space -= sizeof(struct dx_tail); + limit = entry_space / sizeof(struct dx_entry); + if (count > limit) + return -ENOSPC; + + /* set the new limit, move dx_info and the entries */ + dx_set_limit(entries, limit); + memmove((char *)dx_info + len, dx_info, + sizeof(*dx_info) + count * sizeof(struct dx_entry)); + } else { + struct ext4_dir_entry_2 *next, *to, *prev, *de; + char *top = (char *)bh->b_data + blocksize; + int space = 0; + unsigned rec_len = 0; + + len = EXT4_DIR_REC_LEN(2 + dlen) - + ext4_rec_len_from_disk(dotdot_de->rec_len, blocksize); + + if (ext4_has_metadata_csum(dir->i_sb)) + top -= sizeof(struct ext4_dir_entry_tail); + + de = ext4_next_entry(dotdot_de, blocksize); + while ((char *)de < top) { + space += ext4_rec_len_from_disk(de->rec_len, blocksize) - + EXT4_DIR_ENTRY_LEN(de); + de = ext4_next_entry(de, blocksize); + } + + if (space < len) + return -ENOSPC; + + /* pack all the entries after dotdot */ + de = ext4_next_entry(dotdot_de, blocksize); + prev = to = de; + while ((char *)de < top) { + next = ext4_next_entry(de, blocksize); + if (de->inode && de->name_len) { + rec_len = EXT4_DIR_ENTRY_LEN(de); + if (de > to) + memmove(to, de, rec_len); + to->rec_len = ext4_rec_len_to_disk(rec_len, + blocksize); + prev = to; + to = (struct ext4_dir_entry_2 *) + (((char *)to) + rec_len); + } + de = next; + } + /* fix up rec_len for the last entry */ + prev->rec_len = ext4_rec_len_to_disk(top - (char *)prev - len, + blocksize); + /* move all the entries after dotdot to make space */ + de = ext4_next_entry(dotdot_de, blocksize); + memmove((char *)de + len, de, (char *)prev - (char *)de + + EXT4_DIR_ENTRY_LEN(prev)); + /* fix the rec_len for dotdot */ + dotdot_de->rec_len = ext4_rec_len_to_disk( + EXT4_DIR_REC_LEN(2 + dlen), blocksize); + } + + return 0; +} + +/* update ".." entry, try to expand the entry if necessary */ static int ext4_update_dotdot(handle_t *handle, struct dentry *dentry, struct inode *inode) { @@ -2268,6 +2388,8 @@ static int ext4_update_dotdot(handle_t * struct ext4_dir_entry_2 *dot_de, *dotdot_de; unsigned int offset; int retval = 0; + int dlen = 0; + char *data; if (IS_ERR(handle)) return PTR_ERR(handle); @@ -2307,6 +2429,30 @@ static int ext4_update_dotdot(handle_t * dotdot_de->inode = cpu_to_le32(inode->i_ino); + data = ext4_dentry_get_data(dir->i_sb, + (struct ext4_dentry_param *)dentry->d_fsdata); + if (data != NULL) { + dlen = *data + 1; + if (is_dx(dir)) { + if (ext4_get_dirent_data_len(dotdot_de) < dlen) { + if (ext4_expand_dotdot(dir, bh, dlen) < 0) + dlen = 0; + } + } else { + if (ext4_rec_len_from_disk(dotdot_de->rec_len, + dir->i_sb->s_blocksize) < + EXT4_DIR_REC_LEN(2 + dlen)) { + if (ext4_expand_dotdot(dir, bh, dlen) < 0) + dlen = 0; + } + } + } + if (dlen) { + dotdot_de->name[2] = 0; + memcpy(&dotdot_de->name[2 + 1], data, *data); + dotdot_de->file_type |= LDISKFS_DIRENT_LUFID; + } + ext4_mark_inode_dirty(handle, dir); BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata"); if (is_dx(dir)) { @@ -2351,6 +2407,7 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry, ext4_lblk_t block, blocks; int csum_size = 0; + EXT4_I(inode)->i_dirdata = dentry->d_fsdata; if (ext4_has_metadata_csum(inode->i_sb)) csum_size = sizeof(struct ext4_dir_entry_tail); @@ -2918,37 +2975,70 @@ err_unlock_inode: return err; } +struct tp_block { + struct inode *inode; + void *data1; + void *data2; +}; + struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode, struct ext4_dir_entry_2 *de, int blocksize, int csum_size, unsigned int parent_ino, int dotdot_real_len) { + void *data1 = NULL, *data2 = NULL; + int dot_reclen = 0; + + if (dotdot_real_len == 10) { + struct tp_block *tpb = (struct tp_block *)inode; + data1 = tpb->data1; + data2 = tpb->data2; + inode = tpb->inode; + dotdot_real_len = 0; + } 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), - blocksize); strcpy(de->name, "."); ext4_set_de_type(inode->i_sb, de, S_IFDIR); + /* get packed fid data*/ + data1 = ext4_dentry_get_data(inode->i_sb, + (struct ext4_dentry_param *) data1); + if (data1) { + de->name[1] = 0; + memcpy(&de->name[2], data1, *(char *) data1); + de->file_type |= EXT4_DIRENT_LUFID; + } + de->rec_len = cpu_to_le16(EXT4_DIR_ENTRY_LEN(de)); + dot_reclen = cpu_to_le16(de->rec_len); de = ext4_next_entry(de, blocksize); de->inode = cpu_to_le32(parent_ino); de->name_len = 2; + strcpy(de->name, ".."); + ext4_set_de_type(inode->i_sb, de, S_IFDIR); + data2 = ext4_dentry_get_data(inode->i_sb, + (struct ext4_dentry_param *) data2); + if (data2) { + de->name[2] = 0; + memcpy(&de->name[3], data2, *(char *) data2); + de->file_type |= EXT4_DIRENT_LUFID; + } if (!dotdot_real_len) de->rec_len = ext4_rec_len_to_disk(blocksize - - (csum_size + EXT4_DIR_REC_LEN(1)), + (csum_size + dot_reclen), blocksize); else de->rec_len = ext4_rec_len_to_disk( - EXT4_DIR_REC_LEN(de->name_len), blocksize); - strcpy(de->name, ".."); - ext4_set_de_type(inode->i_sb, de, S_IFDIR); + EXT4_DIR_ENTRY_LEN(de), blocksize); return ext4_next_entry(de, blocksize); } int ext4_init_new_dir(handle_t *handle, struct inode *dir, - struct inode *inode) + struct inode *inode, + const void *data1, const void *data2) { + struct tp_block param; struct buffer_head *dir_block = NULL; struct ext4_dir_entry_2 *de; ext4_lblk_t block = 0; @@ -2972,7 +3062,11 @@ int ext4_init_new_dir(handle_t *handle, struct inode *dir, if (IS_ERR(dir_block)) return PTR_ERR(dir_block); de = (struct ext4_dir_entry_2 *)dir_block->b_data; - ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0); + param.inode = inode; + param.data1 = (void *)data1; + param.data2 = (void *)data2; + ext4_init_dot_dotdot((struct inode *)(¶m), de, blocksize, + csum_size, dir->i_ino, 10); set_nlink(inode, 2); if (csum_size) ext4_initialize_dirent_tail(dir_block, blocksize); @@ -2987,6 +3081,29 @@ out: return err; } +/* Initialize @inode as a subdirectory of @dir, and add the + * "." and ".." entries into the first directory block. */ +int ext4_add_dot_dotdot(handle_t *handle, struct inode *dir, + struct inode *inode, + const void *data1, const void *data2) +{ + int rc; + + if (IS_ERR(handle)) + return PTR_ERR(handle); + + if (IS_DIRSYNC(dir)) + ext4_handle_sync(handle); + + inode->i_op = &ext4_dir_inode_operations; + inode->i_fop = &ext4_dir_operations; + rc = ext4_init_new_dir(handle, dir, inode, data1, data2); + if (!rc) + rc = ext4_mark_inode_dirty(handle, inode); + return rc; +} +EXPORT_SYMBOL(ext4_add_dot_dotdot); + static int ext4_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { handle_t *handle; @@ -3013,7 +3130,7 @@ retry: inode->i_op = &ext4_dir_inode_operations; inode->i_fop = &ext4_dir_operations; - err = ext4_init_new_dir(handle, dir, inode); + err = ext4_init_new_dir(handle, dir, inode, NULL, NULL); if (err) goto out_clear_inode; err = ext4_mark_inode_dirty(handle, inode); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 6c33a10..59b87b4 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1719,7 +1719,7 @@ enum { Opt_inlinecrypt, Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota, Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota, - Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, + Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err, Opt_dirdata, Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, @@ -1803,6 +1803,7 @@ static const match_table_t tokens = { {Opt_nolazytime, "nolazytime"}, {Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"}, {Opt_nodelalloc, "nodelalloc"}, + {Opt_dirdata, "dirdata"}, {Opt_removed, "mblk_io_submit"}, {Opt_removed, "nomblk_io_submit"}, {Opt_block_validity, "block_validity"}, @@ -2043,6 +2044,7 @@ static const struct mount_opts { {Opt_usrjquota, 0, MOPT_Q | MOPT_STRING}, {Opt_grpjquota, 0, MOPT_Q | MOPT_STRING}, {Opt_offusrjquota, 0, MOPT_Q}, + {Opt_dirdata, EXT4_MOUNT_DIRDATA, MOPT_SET}, {Opt_offgrpjquota, 0, MOPT_Q}, {Opt_jqfmt_vfsold, QFMT_VFS_OLD, MOPT_QFMT}, {Opt_jqfmt_vfsv0, QFMT_VFS_V0, MOPT_QFMT}, -- 2.33.0