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 | 9 +- fs/ext4/ext4.h | 107 ++++++++++++++++-- fs/ext4/fast_commit.c | 2 +- fs/ext4/inline.c | 8 +- fs/ext4/namei.c | 251 ++++++++++++++++++++++++++++++++---------- fs/ext4/super.c | 12 +- 6 files changed, 314 insertions(+), 75 deletions(-) diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c index 3985f8c3..b8e4df14 100644 --- a/fs/ext4/dir.c +++ b/fs/ext4/dir.c @@ -465,12 +465,17 @@ 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; @@ -479,7 +484,7 @@ 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 a4af3ec8..930ca3a5 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1184,6 +1184,7 @@ struct ext4_inode_info { __u32 i_csum_seed; kprojid_t i_projid; + void *i_dirdata; }; /* @@ -1205,6 +1206,7 @@ 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 */ @@ -2174,6 +2176,7 @@ 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 | \ @@ -2385,6 +2388,42 @@ 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 @@ -2396,6 +2435,17 @@ struct ext4_dir_entry_tail { #define EXT4_DIR_PAD 4 #define EXT4_DIR_ROUND (EXT4_DIR_PAD - 1) #define EXT4_MAX_REC_LEN ((1<<16)-1) +#define EXT4_DIR_REC_LEN_(name_len, i_dir) \ + ext4_dir_rec_len((name_len), (i_dir)) +#define EXT4_DIR_ENTRY_LEN_(de, i_dir) \ + (EXT4_DIR_REC_LEN_((de)->name_len + ext4_get_dirent_data_len(de), \ + (i_dir))) +/* ldiskfs */ +#define EXT4_DIR_REC_LEN(name_len, i_dir) EXT4_DIR_REC_LEN_((name_len), (i_dir)) +#define EXT4_DIR_ENTRY_LEN(de, i_dir) EXT4_DIR_ENTRY_LEN_((de), (i_dir)) +/* lustre osd_handler compat -- ifdef LDISKFS_DIR_REC_LEN_WITH_DIR */ +#define EXT4_DIR_REC_LEN_WITH_DIR 1 +#define __EXT4_DIR_REC_LEN(name_len) EXT4_DIR_REC_LEN_((name_len), NULL) /* * The rec_len is dependent on the type of directory. Directories that are @@ -2403,10 +2453,10 @@ struct ext4_dir_entry_tail { * 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. */ -static inline unsigned int ext4_dir_rec_len(__u8 name_len, +static inline unsigned int ext4_dir_rec_len(__u32 name_len, const struct inode *dir) { - int rec_len = (name_len + 8 + EXT4_DIR_ROUND); + __u32 rec_len = (name_len + 8 + EXT4_DIR_ROUND); if (dir && ext4_hash_in_dirent(dir)) rec_len += sizeof(struct ext4_dir_entry_hash); @@ -2831,11 +2881,13 @@ 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 *dir, 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) && @@ -2851,10 +2903,17 @@ 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); @@ -3058,9 +3117,13 @@ 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_add_dot_dotdot(handle_t *handle, struct inode *dir, + struct inode *inode, + const void *data1, const void *data2); extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, __u32 start_minor_hash, __u32 *next_hash); extern struct inode *ext4_create_inode(handle_t *handle, @@ -3887,6 +3950,36 @@ 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 8de354dc..00c4769b 100644 --- a/fs/ext4/fast_commit.c +++ b/fs/ext4/fast_commit.c @@ -1674,7 +1674,7 @@ static int ext4_fc_replay_create(struct super_block *sb, ext4_debug("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 c4475a74..3fc75d80 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -1031,7 +1031,7 @@ 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, NULL); if (err) return err; @@ -1040,7 +1040,7 @@ 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(dir, 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, NULL), + EXT4_DIR_ENTRY_LEN(&fake, NULL), 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, NULL), + EXT4_DIR_ENTRY_LEN(&fake, NULL), 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 d0afa8f2..839d51ba 100644 --- a/fs/ext4/namei.c +++ b/fs/ext4/namei.c @@ -291,13 +291,14 @@ 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, struct dx_hash_info *hinfo, struct dx_frame *frame); -static void dx_release(struct dx_frame *frames); +static void dx_release(struct dx_frame *frames, struct inode *dir); static int dx_make_map(struct inode *dir, struct buffer_head *bh, struct dx_hash_info *hinfo, struct dx_map_entry *map_tail); @@ -437,22 +438,23 @@ 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, NULL); + 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; @@ -555,13 +557,14 @@ 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. */ -struct dx_root_info *dx_get_dx_info(struct ext4_dir_entry_2 *de) +struct dx_root_info *dx_get_dx_info(struct ext4_dir_entry_2 *de, struct inode *i_dir) { + 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, i_dir)); /* 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, i_dir)); return (struct dx_root_info *)de; } @@ -606,11 +609,16 @@ 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 int entry_space = dir->i_sb->s_blocksize - - ext4_dir_rec_len(1, NULL) - - ext4_dir_rec_len(2, NULL) - 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, NULL) - + EXT4_DIR_ENTRY_LEN(dotdot_de, NULL) - infosize; if (ext4_has_metadata_csum(dir->i_sb)) entry_space -= sizeof(struct dx_tail); @@ -728,7 +736,7 @@ 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, dir); names++; } de = ext4_next_entry(de, size); @@ -822,7 +830,7 @@ 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((struct ext4_dir_entry_2 *)frame->bh->b_data, dir); if (info->hash_version != DX_HASH_TEA && info->hash_version != DX_HASH_HALF_MD4 && info->hash_version != DX_HASH_LEGACY && @@ -878,11 +886,14 @@ 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; } @@ -959,7 +970,7 @@ fail: return ret_err; } -static void dx_release(struct dx_frame *frames) +static void dx_release(struct dx_frame *frames, struct inode *dir) { struct dx_root_info *info; int i; @@ -968,7 +979,7 @@ 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((struct ext4_dir_entry_2 *)frames[0].bh->b_data, dir); /* save local copy, "info" may be freed after brelse() */ indirect_levels = info->indirect_levels; for (i = 0; i <= indirect_levels; i++) { @@ -1269,12 +1280,12 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash, (count && ((hashval & 1) == 0))) break; } - dx_release(frames); + dx_release(frames, dir); dxtrace(printk(KERN_DEBUG "Fill tree: returned %d entries, " "next hash: %x\n", count, *next_hash)); return count; errout: - dx_release(frames); + dx_release(frames, dir); return (err); } @@ -1806,7 +1817,7 @@ 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(frames, dir); return bh; } @@ -1930,7 +1941,7 @@ 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, dir); memcpy (to, de, rec_len); ((struct ext4_dir_entry_2 *) to)->rec_len = @@ -1963,7 +1974,7 @@ 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, dir); if (de > to) memmove(to, de, rec_len); to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize); @@ -2106,14 +2117,22 @@ 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), dir); + unsigned short reclen; int nlen, rlen; unsigned int offset = 0; char *top; + if (dlen) { + reclen = ext4_dir_rec_len(fname_len(fname) + *dlen, dir); + *dlen = 0; + } else { + reclen = ext4_dir_rec_len(fname_len(fname), dir); + } + de = buf; top = buf + buf_size - reclen; while ((char *) de <= top) { @@ -2122,10 +2141,31 @@ 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, dir); + nlen = EXT4_DIR_ENTRY_LEN(de, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if ((de->inode ? rlen - nlen : rlen) >= reclen) break; + + /* Then for dotdot entries, check for the smaller space + * required for just the entry, no FID + */ + if (fname_len(fname) == 2 && memcmp(fname_name(fname), "..", 2) == 0) { + if ((de->inode ? rlen - nlen : rlen) >= + ext4_dir_rec_len(fname_len(fname), dir)) { + /* set dlen = 1 to indicate not + * enough space store fid + */ + if (dlen) + *dlen = 1; + break; + } + /* The new ".." entry must be written over the + * previous ".." entry, which is the first + * entry traversed by this scan. If it doesn't + * fit, something is badly wrong, so -EIO. + */ + return -EIO; + } de = (struct ext4_dir_entry_2 *)((char *)de + rlen); offset += rlen; } @@ -2140,12 +2180,13 @@ void ext4_insert_dentry(struct inode *dir, 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, dir); + nlen = EXT4_DIR_ENTRY_LEN(de, dir); rlen = ext4_rec_len_from_disk(de->rec_len, buf_size); if (de->inode) { struct ext4_dir_entry_2 *de1 = @@ -2166,6 +2207,12 @@ void ext4_insert_dentry(struct inode *dir, EXT4_DIRENT_HASHES(de)->minor_hash = cpu_to_le32(hinfo->minor_hash); } + if (data) { + de->name[fname_len(fname)] = 0; + memcpy(&de->name[fname_len(fname) + 1], data, *(char *)data); + de->file_type |= EXT4_DIRENT_LUFID; + } + } /* @@ -2183,14 +2230,19 @@ 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; } @@ -2203,7 +2255,10 @@ 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); + /* If writing the short form of "dotdot", don't add the data section */ + if (dlen == 1) + data = NULL; + ext4_insert_dentry(dir, inode, de, blocksize, fname, data); /* * XXX shouldn't update any times until successful @@ -2309,7 +2364,7 @@ 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(dot_de, dir); memset(dx_info, 0, sizeof(*dx_info)); dx_info->info_length = sizeof(*dx_info); if (ext4_hash_in_dirent(dir)) @@ -2320,7 +2375,8 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname, 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(*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; @@ -2361,7 +2417,7 @@ out_frames: */ if (retval) ext4_mark_inode_dirty(handle, dir); - dx_release(frames); + dx_release(frames, dir); brelse(bh2); return retval; } @@ -2374,6 +2430,8 @@ static int ext4_update_dotdot(handle_t *handle, struct dentry *dentry, struct buffer_head *dir_block; struct ext4_dir_entry_2 *de; int len, journal = 0, err = 0; + int dlen = 0; + char *data; if (IS_ERR(handle)) return PTR_ERR(handle); @@ -2389,21 +2447,26 @@ static int ext4_update_dotdot(handle_t *handle, struct dentry *dentry, de = (struct ext4_dir_entry_2 *)dir_block->b_data; /* the first item must be "." */ - assert(de->name_len == 1 && de->name[0] == '.'); + ASSERT(de->name_len == 1 && de->name[0] == '.'); len = le16_to_cpu(de->rec_len); - assert(len >= EXT4_DIR_REC_LEN(1)); - if (len > EXT4_DIR_REC_LEN(1)) { + ASSERT(len >= EXT4_DIR_REC_LEN(1, dir)); + if (len > EXT4_DIR_REC_LEN(1, dir)) { BUFFER_TRACE(dir_block, "get_write_access"); err = ext4_journal_get_write_access(handle, dir->i_sb, dir_block, EXT4_JTR_NONE); if (err) goto out_journal; journal = 1; - de->rec_len = cpu_to_le16(EXT4_DIR_REC_LEN(1)); + de->rec_len = cpu_to_le16(EXT4_DIR_ENTRY_LEN(de, dir)); } - len -= EXT4_DIR_REC_LEN(1); - assert(len == 0 || len >= EXT4_DIR_REC_LEN(2)); + len -= EXT4_DIR_ENTRY_LEN(de, NULL); + data = ext4_dentry_get_data(dir->i_sb, + (struct ext4_dentry_param *)dentry->d_fsdata); + if (data) + dlen = *data + 1; + ASSERT(len == 0 || len >= EXT4_DIR_REC_LEN(2 + dlen, dir)); + de = (struct ext4_dir_entry_2 *) ((char *) de + le16_to_cpu(de->rec_len)); if (!journal) { @@ -2417,10 +2480,15 @@ static int ext4_update_dotdot(handle_t *handle, struct dentry *dentry, if (len > 0) de->rec_len = cpu_to_le16(len); else - assert(le16_to_cpu(de->rec_len) >= EXT4_DIR_REC_LEN(2)); + ASSERT(le16_to_cpu(de->rec_len) >= EXT4_DIR_REC_LEN(2, dir)); de->name_len = 2; strcpy(de->name, ".."); - ext4_set_de_type(dir->i_sb, de, S_IFDIR); + if (data != NULL && ext4_get_dirent_data_len(de) >= dlen) { + de->name[2] = 0; + memcpy(&de->name[2 + 1], data, *data); + ext4_set_de_type(dir->i_sb, de, S_IFDIR); + de->file_type |= EXT4_DIRENT_LUFID; + } out_journal: if (journal) { @@ -2458,6 +2526,7 @@ 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); @@ -2700,7 +2769,7 @@ again: dx_set_count(entries, 1); dx_set_block(entries + 0, newblock); info = dx_get_dx_info((struct ext4_dir_entry_2 *) - frames[0].bh->b_data); + frames[0].bh->b_data, dir); info->indirect_levels = 1; dxtrace(printk(KERN_DEBUG "Creating %d level index...\n", @@ -2726,7 +2795,7 @@ journal_error: ext4_std_error(dir->i_sb, err); /* this is a no-op if err == 0 */ cleanup: brelse(bh); - dx_release(frames); + dx_release(frames, dir); /* @restart is true means htree-path has been changed, we need to * repeat dx_probe() to find out valid htree-path */ @@ -3029,38 +3098,73 @@ 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, NULL), - 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, NULL)); + + 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, NULL)), - blocksize); + (csum_size + dot_reclen), blocksize); else de->rec_len = ext4_rec_len_to_disk( - ext4_dir_rec_len(de->name_len, NULL), + EXT4_DIR_ENTRY_LEN(de, NULL), blocksize); - strcpy(de->name, ".."); - ext4_set_de_type(inode->i_sb, de, S_IFDIR); 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; @@ -3084,7 +3188,11 @@ 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); @@ -3099,6 +3207,29 @@ 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 user_namespace *mnt_userns, struct inode *dir, struct dentry *dentry, umode_t mode) { @@ -3126,7 +3257,7 @@ 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 c013357d..1838ee86 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -1571,7 +1571,7 @@ enum { Opt_data_err_abort, Opt_data_err_ignore, Opt_test_dummy_encryption, Opt_inlinecrypt, Opt_usrjquota, Opt_grpjquota, 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_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never, Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error, @@ -1687,6 +1687,7 @@ static const struct fs_parameter_spec ext4_param_specs[] = { fsparam_u32 ("stripe", Opt_stripe), fsparam_flag ("delalloc", Opt_delalloc), fsparam_flag ("nodelalloc", Opt_nodelalloc), + fsparam_flag ("dirdata", Opt_dirdata), fsparam_flag ("warn_on_error", Opt_warn_on_error), fsparam_flag ("nowarn_on_error", Opt_nowarn_on_error), fsparam_u32 ("debug_want_extra_isize", @@ -1823,6 +1824,7 @@ static const struct mount_opts { MOPT_CLEAR | MOPT_Q}, {Opt_usrjquota, 0, MOPT_Q}, {Opt_grpjquota, 0, MOPT_Q}, + {Opt_dirdata, EXT4_MOUNT_DIRDATA, MOPT_SET}, {Opt_jqfmt, 0, MOPT_QFMT}, {Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET}, {Opt_no_prefetch_block_bitmaps, EXT4_MOUNT_NO_PREFETCH_BLOCK_BITMAPS, @@ -3563,6 +3565,14 @@ int ext4_feature_set_ok(struct super_block *sb, int readonly) } #endif + if ((ext4_has_feature_casefold(sb) || ext4_has_feature_encrypt(sb)) && + ext4_has_feature_dirdata(sb)) { + ext4_msg(sb, KERN_ERR, + "Filesystem with casefold and encrypt are incompatible " + "with dirdata"); + return 0; + } + if (readonly) return 1; -- 2.25.1