attached RFC patches adds facility in ext4 to have user data in every ext4 dirent.
lustre assigns cluserwide unique id to every inode in system, so we have added
user data field in ext4 dirent to map filename to id efficiently.
i would like to get feedback on this as it might have some conflict with 64 bit
inode work (which is in discussion phase). also please comment on INCOMPAT flag
added.
patch[1] removes dx_root struct so that "." and ".." can have extra data.
patch[2] add user data field to ext4 dirent.
Thanks,
Pravin.
this is cleanup patch which removes dx_root structure; this is reuqired
for next patch.
Index: b/fs/ext4/namei.c
===================================================================
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -105,22 +105,13 @@ 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[0];
+ __le32 reserved_zero;
+ u8 hash_version;
+ u8 info_length; /* 8 */
+ u8 indirect_levels;
+ u8 unused_flags;
};
struct dx_node
@@ -217,6 +208,16 @@ ext4_next_entry(struct ext4_dir_entry_2
* 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)
+{
+ /* get dotdot first */
+ de = (struct ext4_dir_entry_2 *)((char *)de + EXT4_DIR_REC_LEN(1));
+
+ /* 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;
+}
static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
{
@@ -371,7 +372,7 @@ dx_probe(const struct qstr *d_name, stru
{
unsigned count, indirect;
struct dx_entry *at, *entries, *p, *q, *m;
- struct dx_root *root;
+ struct dx_root_info * info;
struct buffer_head *bh;
struct dx_frame *frame = frame_in;
u32 hash;
@@ -379,18 +380,18 @@ dx_probe(const struct qstr *d_name, stru
frame->bh = NULL;
if (!(bh = ext4_bread (NULL,dir, 0, 0, err)))
goto fail;
- root = (struct dx_root *) 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) {
+ info = dx_get_dx_info((struct ext4_dir_entry_2*)bh->b_data);
+ if (info->hash_version != DX_HASH_TEA &&
+ info->hash_version != DX_HASH_HALF_MD4 &&
+ info->hash_version != DX_HASH_LEGACY) {
ext4_warning(dir->i_sb, __func__,
"Unrecognised inode hash code %d",
- root->info.hash_version);
+ info->hash_version);
brelse(bh);
*err = ERR_BAD_DX_DIR;
goto fail;
}
- 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;
@@ -398,29 +399,28 @@ dx_probe(const struct qstr *d_name, stru
ext4fs_dirhash(d_name->name, d_name->len, hinfo);
hash = hinfo->hash;
- if (root->info.unused_flags & 1) {
+ if (info->unused_flags & 1) {
ext4_warning(dir->i_sb, __func__,
"Unimplemented inode hash flags: %#06x",
- root->info.unused_flags);
+ info->unused_flags);
brelse(bh);
*err = ERR_BAD_DX_DIR;
goto fail;
}
- if ((indirect = root->info.indirect_levels) > 1) {
+ if ((indirect = info->indirect_levels) > 1) {
ext4_warning(dir->i_sb, __func__,
"Unimplemented inode hash depth: %#06x",
- root->info.indirect_levels);
+ info->indirect_levels);
brelse(bh);
*err = ERR_BAD_DX_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)) {
+ info->info_length)) {
ext4_warning(dir->i_sb, __func__,
"dx entry: limit != root limit");
brelse(bh);
@@ -502,10 +502,12 @@ fail:
static void dx_release (struct dx_frame *frames)
{
+ struct dx_root_info *info;
if (frames[0].bh == NULL)
return;
- if (((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels)
+ info = dx_get_dx_info((struct ext4_dir_entry_2*)frames[0].bh->b_data);
+ if (info->indirect_levels)
brelse(frames[1].bh);
brelse(frames[0].bh);
}
@@ -1392,17 +1394,16 @@ static int make_indexed_dir(handle_t *ha
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
struct buffer_head *bh2;
- struct dx_root *root;
struct dx_frame frames[2], *frame;
struct dx_entry *entries;
- struct ext4_dir_entry_2 *de, *de2;
+ struct ext4_dir_entry_2 *de, *de2, *dot_de, *dotdot_de;
char *data1, *top;
unsigned len;
int retval;
unsigned blocksize;
struct dx_hash_info hinfo;
ext4_lblk_t block;
- struct fake_dirent *fde;
+ struct dx_root_info *dx_info;
blocksize = dir->i_sb->s_blocksize;
dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
@@ -1412,20 +1413,20 @@ static int make_indexed_dir(handle_t *ha
brelse(bh);
return retval;
}
- root = (struct dx_root *) bh->b_data;
+ dot_de = (struct ext4_dir_entry_2 *) bh->b_data;
/* 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));
- if ((char *) de >= (((char *) root) + blocksize)) {
+ dotdot_de = ext4_next_entry(dot_de, blocksize);
+ de = ext4_next_entry(dotdot_de, blocksize);
+ len = ((char *) dot_de) + blocksize - (char *) de;
+
+ if ((char *) de >= (((char *) dot_de) + blocksize)) {
ext4_error(dir->i_sb, __func__,
"invalid rec_len for '..' in inode %lu",
dir->i_ino);
brelse(bh);
return -EIO;
}
- len = ((char *) root) + blocksize - (char *) de;
/* Allocate new block for the 0th block's dirents */
bh2 = ext4_append(handle, dir, &block, &retval);
@@ -1444,19 +1445,23 @@ static int make_indexed_dir(handle_t *ha
de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de,
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),
- blocksize);
- memset (&root->info, 0, sizeof(root->info));
- root->info.info_length = sizeof(root->info);
- root->info.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
- entries = root->entries;
+ 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);
+ dx_info->hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+
+ 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 */
- hinfo.hash_version = root->info.hash_version;
+ hinfo.hash_version = dx_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;
@@ -1630,6 +1635,8 @@ static int ext4_dx_add_entry(handle_t *h
goto journal_error;
brelse (bh2);
} else {
+ struct dx_root_info *info;
+
dxtrace(printk(KERN_DEBUG
"Creating second level index...\n"));
memcpy((char *) entries2, (char *) entries,
@@ -1639,7 +1646,9 @@ static int ext4_dx_add_entry(handle_t *h
/* Set up root */
dx_set_count(entries, 1);
dx_set_block(entries + 0, newblock);
- ((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1;
+ info = dx_get_dx_info((struct ext4_dir_entry_2*)
+ frames[0].bh->b_data);
+ info->indirect_levels = 1;
/* Add new access path frame */
frame = frames + 1;
