this patch implements feature which allows ext4 fs uses (e.g. Lustre)
store data in ext4 dirent.
data is stored in ext4 dirent after file-name, this space is accounted
in de->rec_len. flag EXT4_DIRENT_LUFID added to d_type if extra data
is present.
===================================================================
@@ -53,6 +53,8 @@ const struct file_operations ext4_dir_op
static unsigned char get_dtype(struct super_block *sb, int filetype)
{
+ filetype &= EXT4_FT_MASK;
+
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_FILETYPE) ||
(filetype >= EXT4_FT_MAX))
return DT_UNKNOWN;
@@ -70,11 +72,11 @@ int ext4_check_dir_entry(const char *fun
const int rlen = ext4_rec_len_from_disk(de->rec_len,
dir->i_sb->s_blocksize);
- if (rlen < EXT4_DIR_REC_LEN(1))
+ if (rlen < __EXT4_DIR_REC_LEN(1))
error_msg = "rec_len is smaller than minimal";
else if (rlen % 4 != 0)
error_msg = "rec_len % 4 != 0";
- else if (rlen < EXT4_DIR_REC_LEN(de->name_len))
+ else if (rlen < EXT4_DIR_REC_LEN(de))
error_msg = "rec_len is too small for name_len";
else if (((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize)
error_msg = "directory entry across blocks";
@@ -179,7 +181,7 @@ revalidate:
* 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);
@@ -215,12 +217,13 @@ revalidate:
* during the copy operation.
*/
u64 version = filp->f_version;
-
error = filldir(dirent, de->name,
de->name_len,
filp->f_pos,
le32_to_cpu(de->inode),
- get_dtype(sb, de->file_type));
+ get_dtype(sb, de->file_type)|
+ (de->file_type &
+ EXT4_DIRENT_LUFID));
if (error)
break;
if (version != filp->f_version)
@@ -342,12 +345,17 @@ int ext4_htree_store_dirent(struct file
struct fname *fname, *new_fn;
struct dir_private_info *info;
int len;
+ int extra_data = 1;
info = (struct dir_private_info *) dir_file->private_data;
p = &info->root.rb_node;
/* Create and allocate the fname structure */
- len = sizeof(struct fname) + dirent->name_len + 1;
+ if (dirent->file_type & EXT4_DIRENT_LUFID)
+ extra_data = ext4_get_dirent_data_len(dirent);
+
+ len = sizeof(struct fname) + dirent->name_len + extra_data;
+
new_fn = kzalloc(len, GFP_KERNEL);
if (!new_fn)
return -ENOMEM;
@@ -356,7 +364,7 @@ int ext4_htree_store_dirent(struct file
new_fn->inode = le32_to_cpu(dirent->inode);
new_fn->name_len = dirent->name_len;
new_fn->file_type = dirent->file_type;
- memcpy(new_fn->name, dirent->name, dirent->name_len);
+ memcpy(new_fn->name, dirent->name, dirent->name_len + extra_data);
new_fn->name[dirent->name_len] = 0;
while (*p) {
@@ -417,7 +425,9 @@ static int call_filldir(struct file *fil
error = filldir(dirent, fname->name,
fname->name_len, curr_pos,
fname->inode,
- get_dtype(sb, fname->file_type));
+ get_dtype(sb, fname->file_type)|
+ (fname->file_type &
+ EXT4_DIRENT_LUFID));
if (error) {
filp->f_pos = curr_pos;
info->extra_fname = fname;
===================================================================
@@ -1061,6 +1061,7 @@ static inline int ext4_valid_inum(struct
#define EXT4_FEATURE_INCOMPAT_64BIT 0x0080
#define EXT4_FEATURE_INCOMPAT_MMP 0x0100
#define EXT4_FEATURE_INCOMPAT_FLEX_BG 0x0200
+#define EXT4_FEATURE_INCOMPAT_DIRDATA 0x1000
#define EXT4_FEATURE_COMPAT_SUPP EXT2_FEATURE_COMPAT_EXT_ATTR
#define EXT4_FEATURE_INCOMPAT_SUPP (EXT4_FEATURE_INCOMPAT_FILETYPE| \
@@ -1068,7 +1069,8 @@ static inline int ext4_valid_inum(struct
EXT4_FEATURE_INCOMPAT_META_BG| \
EXT4_FEATURE_INCOMPAT_EXTENTS| \
EXT4_FEATURE_INCOMPAT_64BIT| \
- EXT4_FEATURE_INCOMPAT_FLEX_BG)
+ EXT4_FEATURE_INCOMPAT_FLEX_BG| \
+ EXT4_FEATURE_INCOMPAT_DIRDATA)
#define EXT4_FEATURE_RO_COMPAT_SUPP (EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
@@ -1150,6 +1152,25 @@ struct ext4_dir_entry_2 {
#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
/*
* EXT4_DIR_PAD defines the directory entries boundaries
@@ -1158,8 +1179,11 @@ struct ext4_dir_entry_2 {
*/
#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_REC_LEN(de) (__EXT4_DIR_REC_LEN(de->name_len +\
+ ext4_get_dirent_data_len(de)))
+
#define EXT4_MAX_REC_LEN ((1<<16)-1)
/*
@@ -1678,6 +1702,17 @@ static inline void set_bitmap_uptodate(s
set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
}
+static inline int ext4_get_dirent_data_len(struct ext4_dir_entry_2 *de)
+{
+ int dlen = 0;
+ char *data;
+ if (de->file_type & EXT4_DIRENT_LUFID) {
+ data = de->name + de->name_len + 1;
+ dlen = *data + 1;
+ }
+ return dlen;
+}
+
#endif /* __KERNEL__ */
#endif /* _EXT4_H */
===================================================================
@@ -143,7 +143,8 @@ static unsigned dx_get_count(struct dx_e
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 *de, unsigned infosize);
static unsigned dx_node_limit(struct inode *dir);
static struct dx_frame *dx_probe(const struct qstr *d_name,
struct inode *dir,
@@ -210,13 +211,15 @@ ext4_next_entry(struct ext4_dir_entry_2
*/
struct dx_root_info * dx_get_dx_info(struct ext4_dir_entry_2 *de)
{
- /* get dotdot first */
- de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_REC_LEN(1));
+ BUG_ON(de->name_len != 1);
+ /* get dotdot first */
+ de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_REC_LEN(de));
+
+ /* dx root info is after dotdot entry */
+ de = (struct ext4_dir_entry_2 *)((char *)de +
+ __EXT4_DIR_REC_LEN(2 + ext4_get_dirent_data_len(de)));
- /* dx root info is after dotdot entry */
- de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_REC_LEN(2));
-
- return (struct dx_root_info *) de;
+ return (struct dx_root_info *) de;
}
static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
@@ -259,16 +262,20 @@ static inline void dx_set_limit(struct d
((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 = ext4_next_entry(dot_de,
+ dir->i_sb->s_blocksize);
+ unsigned entry_space = dir->i_sb->s_blocksize -
+ EXT4_DIR_REC_LEN(dot_de) - EXT4_DIR_REC_LEN(dotdot_de) - infosize;
+ BUG_ON(dot_de->name_len != 1);
return entry_space / sizeof(struct dx_entry);
}
static inline unsigned dx_node_limit(struct inode *dir)
{
- unsigned entry_space = dir->i_sb->s_blocksize - EXT4_DIR_REC_LEN(0);
+ unsigned entry_space = dir->i_sb->s_blocksize - __EXT4_DIR_REC_LEN(0);
return entry_space / sizeof(struct dx_entry);
}
@@ -315,7 +322,7 @@ static struct stats dx_show_leaf(struct
printk(":%x.%u ", h.hash,
((char *) de - base));
}
- space += EXT4_DIR_REC_LEN(de->name_len);
+ space += EXT4_DIR_REC_LEN(de);
names++;
}
de = ext4_next_entry(de, size);
@@ -420,6 +427,7 @@ dx_probe(const struct qstr *d_name, stru
entries = (struct dx_entry *) (((char *)info) + info->info_length);
if (dx_get_limit(entries) != dx_root_limit(dir,
+ (struct ext4_dir_entry_2*)bh->b_data,
info->info_length)) {
ext4_warning(dir->i_sb, __func__,
"dx entry: limit != root limit");
@@ -609,7 +617,7 @@ static int htree_dirblock_to_tree(struct
de = (struct ext4_dir_entry_2 *) bh->b_data;
top = (struct ext4_dir_entry_2 *) ((char *) de +
dir->i_sb->s_blocksize -
- EXT4_DIR_REC_LEN(0));
+ __EXT4_DIR_REC_LEN(0));
for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
if (!ext4_check_dir_entry("htree_dirblock_to_tree", dir, de, bh,
(block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
@@ -1021,7 +1029,7 @@ static struct buffer_head * ext4_dx_find
goto errout;
de = (struct ext4_dir_entry_2 *) bh->b_data;
top = (struct ext4_dir_entry_2 *) ((char *) de + sb->s_blocksize -
- EXT4_DIR_REC_LEN(0));
+ __EXT4_DIR_REC_LEN(0));
for (; de < top; de = ext4_next_entry(de, sb->s_blocksize)) {
int off = (block << EXT4_BLOCK_SIZE_BITS(sb))
+ ((char *) de - bh->b_data);
@@ -1151,7 +1159,7 @@ dx_move_dirents(char *from, char *to, st
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_REC_LEN(de);
memcpy (to, de, rec_len);
((struct ext4_dir_entry_2 *) to)->rec_len =
ext4_rec_len_to_disk(rec_len, blocksize);
@@ -1175,7 +1183,7 @@ static struct ext4_dir_entry_2* dx_pack_
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_REC_LEN(de);
if (de > to)
memmove(to, de, rec_len);
to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize);
@@ -1308,10 +1316,13 @@ static int add_dirent_to_buf(handle_t *h
unsigned int offset = 0;
unsigned int blocksize = dir->i_sb->s_blocksize;
unsigned short reclen;
- int nlen, rlen, err;
+ int nlen, rlen, err, dlen = 0;
+ unsigned char *data = dentry->d_fsdata;
char *top;
- reclen = EXT4_DIR_REC_LEN(namelen);
+ if (data)
+ dlen = (*data) + 1;
+ reclen = __EXT4_DIR_REC_LEN(namelen + dlen);
if (!de) {
de = (struct ext4_dir_entry_2 *)bh->b_data;
top = bh->b_data + blocksize - reclen;
@@ -1325,7 +1336,7 @@ static int add_dirent_to_buf(handle_t *h
brelse(bh);
return -EEXIST;
}
- nlen = EXT4_DIR_REC_LEN(de->name_len);
+ nlen = EXT4_DIR_REC_LEN(de);
rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
if ((de->inode? rlen - nlen: rlen) >= reclen)
break;
@@ -1344,7 +1355,7 @@ static int add_dirent_to_buf(handle_t *h
}
/* By now the buffer is marked for journaling */
- nlen = EXT4_DIR_REC_LEN(de->name_len);
+ nlen = EXT4_DIR_REC_LEN(de);
rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
if (de->inode) {
struct ext4_dir_entry_2 *de1 = (struct ext4_dir_entry_2 *)((char *)de + nlen);
@@ -1360,6 +1371,11 @@ static int add_dirent_to_buf(handle_t *h
de->inode = 0;
de->name_len = namelen;
memcpy(de->name, name, namelen);
+ if (data) {
+ de->name[namelen] = 0;
+ memcpy(&de->name[namelen + 1], data, *(char*) data);
+ de->file_type |= EXT4_DIRENT_LUFID;
+ }
/*
* XXX shouldn't update any times until successful
* completion of syscall, but too many callers depend
@@ -1458,7 +1474,7 @@ static int make_indexed_dir(handle_t *ha
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 */
hinfo.hash_version = dx_info->hash_version;
@@ -1846,6 +1862,7 @@ static int ext4_mkdir(struct inode *dir,
struct inode *inode;
struct buffer_head *dir_block;
struct ext4_dir_entry_2 *de;
+ struct ext4_dir_entry_2 *dot_de;
unsigned int blocksize = dir->i_sb->s_blocksize;
int err, retries = 0;
@@ -1879,13 +1896,14 @@ retry:
de = (struct ext4_dir_entry_2 *) dir_block->b_data;
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),
+ de->rec_len = ext4_rec_len_to_disk(EXT4_DIR_REC_LEN(de),
blocksize);
strcpy(de->name, ".");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
+ dot_de = de;
de = ext4_next_entry(de, blocksize);
de->inode = cpu_to_le32(dir->i_ino);
- de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(1),
+ de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(dot_de),
blocksize);
de->name_len = 2;
strcpy(de->name, "..");
@@ -1928,7 +1946,7 @@ static int empty_dir(struct inode *inode
int err = 0;
sb = inode->i_sb;
- if (inode->i_size < EXT4_DIR_REC_LEN(1) + EXT4_DIR_REC_LEN(2) ||
+ if (inode->i_size < __EXT4_DIR_REC_LEN(1) + __EXT4_DIR_REC_LEN(2) ||
!(bh = ext4_bread(NULL, inode, 0, 0, &err))) {
if (err)
ext4_error(inode->i_sb, __func__,