ext4: New rec_len encoding for very large blocksizes
The rec_len field in the directory entry is 16 bits, so to encode
blocksizes larger than 64k becomes problematic. This patch allows us
to supprot block sizes up to 256k, by using the low 2 bits to extend
the range of rec_len to 2**18-1 (since valid rec_len sizes must be a
multiple of 4). We use the convention that a rec_len of 0 or 65535
means the filesystem block size, for compatibility with older kernels.
It's unlikely we'll see VM pages of up to 256k, but at some point we
might find that the Linux VM has been enhanced to support filesystem
block sizes > than the VM page size, at which point it might be useful
for some applications to allow very large filesystem block sizes.
Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 2df2e40..b647899 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -67,7 +67,8 @@
unsigned int offset)
{
const char *error_msg = NULL;
- const int rlen = ext4_rec_len_from_disk(de->rec_len);
+ const int rlen = ext4_rec_len_from_disk(de->rec_len,
+ dir->i_sb->s_blocksize);
if (rlen < EXT4_DIR_REC_LEN(1))
error_msg = "rec_len is smaller than minimal";
@@ -178,10 +179,11 @@
* least that it is non-zero. A
* failure will be detected in the
* dirent test below. */
- if (ext4_rec_len_from_disk(de->rec_len)
- < EXT4_DIR_REC_LEN(1))
+ if (ext4_rec_len_from_disk(de->rec_len,
+ sb->s_blocksize) < EXT4_DIR_REC_LEN(1))
break;
- i += ext4_rec_len_from_disk(de->rec_len);
+ i += ext4_rec_len_from_disk(de->rec_len,
+ sb->s_blocksize);
}
offset = i;
filp->f_pos = (filp->f_pos & ~(sb->s_blocksize - 1))
@@ -203,7 +205,8 @@
ret = stored;
goto out;
}
- offset += ext4_rec_len_from_disk(de->rec_len);
+ offset += ext4_rec_len_from_disk(de->rec_len,
+ sb->s_blocksize);
if (le32_to_cpu(de->inode)) {
/* We might block in the next section
* if the data destination is
@@ -225,7 +228,8 @@
goto revalidate;
stored++;
}
- filp->f_pos += ext4_rec_len_from_disk(de->rec_len);
+ filp->f_pos += ext4_rec_len_from_disk(de->rec_len,
+ sb->s_blocksize);
}
offset = 0;
brelse(bh);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0db0142..d5193b5 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -855,24 +855,6 @@
~EXT4_DIR_ROUND)
#define EXT4_MAX_REC_LEN ((1<<16)-1)
-static inline unsigned ext4_rec_len_from_disk(__le16 dlen)
-{
- unsigned len = le16_to_cpu(dlen);
-
- if (len == EXT4_MAX_REC_LEN || len == 0)
- return 1 << 16;
- return len;
-}
-
-static inline __le16 ext4_rec_len_to_disk(unsigned len)
-{
- if (len == (1 << 16))
- return cpu_to_le16(EXT4_MAX_REC_LEN);
- else if (len > (1 << 16))
- BUG();
- return cpu_to_le16(len);
-}
-
/*
* Hash Tree Directory indexing
* (c) Daniel Phillips, 2001
@@ -1097,7 +1079,10 @@
/* migrate.c */
extern int ext4_ext_migrate(struct inode *);
+
/* namei.c */
+extern unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize);
+extern __le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize);
extern int ext4_orphan_add(handle_t *, struct inode *);
extern int ext4_orphan_del(handle_t *, struct inode *);
extern int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 0482495..a5ba1a8 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -165,7 +165,7 @@
struct dx_hash_info *hinfo, struct dx_map_entry map[]);
static void dx_sort_map(struct dx_map_entry *map, unsigned count);
static struct ext4_dir_entry_2 *dx_move_dirents(char *from, char *to,
- struct dx_map_entry *offsets, int count);
+ struct dx_map_entry *offsets, int count, unsigned blocksize);
static struct ext4_dir_entry_2* dx_pack_dirents(char *base, unsigned blocksize);
static void dx_insert_block(struct dx_frame *frame,
u32 hash, ext4_lblk_t block);
@@ -180,14 +180,38 @@
static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
struct inode *inode);
+unsigned int ext4_rec_len_from_disk(__le16 dlen, unsigned blocksize)
+{
+ unsigned len = le16_to_cpu(dlen);
+
+ if (len == EXT4_MAX_REC_LEN || len == 0)
+ return blocksize;
+ return (len & 65532) | ((len & 3) << 16);
+}
+
+__le16 ext4_rec_len_to_disk(unsigned len, unsigned blocksize)
+{
+ if ((len > blocksize) || (blocksize > (1 << 18)) || (len & 3))
+ BUG();
+ if (len < 65536)
+ return cpu_to_le16(len);
+ if (len == blocksize) {
+ if (blocksize == 65536)
+ return cpu_to_le16(EXT4_MAX_REC_LEN);
+ else
+ return cpu_to_le16(0);
+ }
+ return cpu_to_le16((len & 65532) | ((len >> 16) & 3));
+}
+
/*
* p is at least 6 bytes before the end of page
*/
static inline struct ext4_dir_entry_2 *
-ext4_next_entry(struct ext4_dir_entry_2 *p)
+ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize)
{
return (struct ext4_dir_entry_2 *)((char *)p +
- ext4_rec_len_from_disk(p->rec_len));
+ ext4_rec_len_from_disk(p->rec_len, blocksize));
}
/*
@@ -294,7 +318,7 @@
space += EXT4_DIR_REC_LEN(de->name_len);
names++;
}
- de = ext4_next_entry(de);
+ de = ext4_next_entry(de, size);
}
printk("(%i)\n", names);
return (struct stats) { names, space, 1 };
@@ -585,7 +609,7 @@
top = (struct ext4_dir_entry_2 *) ((char *) de +
dir->i_sb->s_blocksize -
EXT4_DIR_REC_LEN(0));
- for (; de < top; de = ext4_next_entry(de)) {
+ 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))
+((char *)de - bh->b_data))) {
@@ -663,7 +687,7 @@
}
if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) {
de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
- de = ext4_next_entry(de);
+ de = ext4_next_entry(de, dir->i_sb->s_blocksize);
if ((err = ext4_htree_store_dirent(dir_file, 2, 0, de)) != 0)
goto errout;
count++;
@@ -732,7 +756,7 @@
cond_resched();
}
/* XXX: do we need to check rec_len == 0 case? -Chris */
- de = ext4_next_entry(de);
+ de = ext4_next_entry(de, blocksize);
}
return count;
}
@@ -832,7 +856,8 @@
return 1;
}
/* prevent looping on a bad block */
- de_len = ext4_rec_len_from_disk(de->rec_len);
+ de_len = ext4_rec_len_from_disk(de->rec_len,
+ dir->i_sb->s_blocksize);
if (de_len <= 0)
return -1;
offset += de_len;
@@ -996,7 +1021,7 @@
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));
- for (; de < top; de = ext4_next_entry(de)) {
+ for (; de < top; de = ext4_next_entry(de, sb->s_blocksize)) {
int off = (block << EXT4_BLOCK_SIZE_BITS(sb))
+ ((char *) de - bh->b_data);
@@ -1109,7 +1134,8 @@
* Returns pointer to last entry moved.
*/
static struct ext4_dir_entry_2 *
-dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
+dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count,
+ unsigned blocksize)
{
unsigned rec_len = 0;
@@ -1118,7 +1144,7 @@
rec_len = EXT4_DIR_REC_LEN(de->name_len);
memcpy (to, de, rec_len);
((struct ext4_dir_entry_2 *) to)->rec_len =
- ext4_rec_len_to_disk(rec_len);
+ ext4_rec_len_to_disk(rec_len, blocksize);
de->inode = 0;
map++;
to += rec_len;
@@ -1137,12 +1163,12 @@
prev = to = de;
while ((char*)de < base + blocksize) {
- next = ext4_next_entry(de);
+ next = ext4_next_entry(de, blocksize);
if (de->inode && de->name_len) {
rec_len = EXT4_DIR_REC_LEN(de->name_len);
if (de > to)
memmove(to, de, rec_len);
- to->rec_len = ext4_rec_len_to_disk(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);
}
@@ -1215,10 +1241,12 @@
hash2, split, count-split));
/* Fancy dance to stay within two buffers */
- de2 = dx_move_dirents(data1, data2, map + split, count - split);
+ de2 = dx_move_dirents(data1, data2, map + split, count - split, blocksize);
de = dx_pack_dirents(data1, blocksize);
- de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
- de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2);
+ de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de,
+ blocksize);
+ de2->rec_len = ext4_rec_len_to_disk(data2 + blocksize - (char *) de2,
+ blocksize);
dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data1, blocksize, 1));
dxtrace(dx_show_leaf (hinfo, (struct ext4_dir_entry_2 *) data2, blocksize, 1));
@@ -1268,6 +1296,7 @@
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
unsigned int offset = 0;
+ unsigned int blocksize = dir->i_sb->s_blocksize;
unsigned short reclen;
int nlen, rlen, err;
char *top;
@@ -1275,7 +1304,7 @@
reclen = EXT4_DIR_REC_LEN(namelen);
if (!de) {
de = (struct ext4_dir_entry_2 *)bh->b_data;
- top = bh->b_data + dir->i_sb->s_blocksize - reclen;
+ top = bh->b_data + blocksize - reclen;
while ((char *) de <= top) {
if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
bh, offset)) {
@@ -1287,7 +1316,7 @@
return -EEXIST;
}
nlen = EXT4_DIR_REC_LEN(de->name_len);
- rlen = ext4_rec_len_from_disk(de->rec_len);
+ rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
if ((de->inode? rlen - nlen: rlen) >= reclen)
break;
de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
@@ -1306,11 +1335,11 @@
/* By now the buffer is marked for journaling */
nlen = EXT4_DIR_REC_LEN(de->name_len);
- rlen = ext4_rec_len_from_disk(de->rec_len);
+ 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);
- de1->rec_len = ext4_rec_len_to_disk(rlen - nlen);
- de->rec_len = ext4_rec_len_to_disk(nlen);
+ de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, blocksize);
+ de->rec_len = ext4_rec_len_to_disk(nlen, blocksize);
de = de1;
}
de->file_type = EXT4_FT_UNKNOWN;
@@ -1380,7 +1409,7 @@
/* 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));
+ ext4_rec_len_from_disk(fde->rec_len, blocksize));
if ((char *) de >= (((char *) root) + blocksize)) {
ext4_error(dir->i_sb, __func__,
"invalid rec_len for '..' in inode %lu",
@@ -1402,12 +1431,14 @@
memcpy (data1, de, len);
de = (struct ext4_dir_entry_2 *) data1;
top = data1 + len;
- while ((char *)(de2 = ext4_next_entry(de)) < top)
+ while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top)
de = de2;
- de->rec_len = ext4_rec_len_to_disk(data1 + blocksize - (char *) de);
+ 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));
+ 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;
@@ -1488,7 +1519,7 @@
return retval;
de = (struct ext4_dir_entry_2 *) bh->b_data;
de->inode = 0;
- de->rec_len = ext4_rec_len_to_disk(blocksize);
+ de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
return add_dirent_to_buf(handle, dentry, inode, de, bh);
}
@@ -1551,7 +1582,8 @@
goto cleanup;
node2 = (struct dx_node *)(bh2->b_data);
entries2 = node2->entries;
- node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize);
+ node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize,
+ sb->s_blocksize);
node2->fake.inode = 0;
BUFFER_TRACE(frame->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, frame->bh);
@@ -1639,6 +1671,7 @@
struct buffer_head *bh)
{
struct ext4_dir_entry_2 *de, *pde;
+ unsigned int blocksize = dir->i_sb->s_blocksize;
int i;
i = 0;
@@ -1652,8 +1685,11 @@
ext4_journal_get_write_access(handle, bh);
if (pde)
pde->rec_len = ext4_rec_len_to_disk(
- ext4_rec_len_from_disk(pde->rec_len) +
- ext4_rec_len_from_disk(de->rec_len));
+ ext4_rec_len_from_disk(pde->rec_len,
+ blocksize) +
+ ext4_rec_len_from_disk(de->rec_len,
+ blocksize),
+ blocksize);
else
de->inode = 0;
dir->i_version++;
@@ -1661,9 +1697,9 @@
ext4_handle_dirty_metadata(handle, dir, bh);
return 0;
}
- i += ext4_rec_len_from_disk(de->rec_len);
+ i += ext4_rec_len_from_disk(de->rec_len, blocksize);
pde = de;
- de = ext4_next_entry(de);
+ de = ext4_next_entry(de, blocksize);
}
return -ENOENT;
}
@@ -1793,6 +1829,7 @@
struct inode *inode;
struct buffer_head *dir_block;
struct ext4_dir_entry_2 *de;
+ unsigned int blocksize = dir->i_sb->s_blocksize;
int err, retries = 0;
if (EXT4_DIR_LINK_MAX(dir))
@@ -1824,13 +1861,14 @@
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->name_len),
+ blocksize);
strcpy(de->name, ".");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
- de = ext4_next_entry(de);
+ de = ext4_next_entry(de, blocksize);
de->inode = cpu_to_le32(dir->i_ino);
- de->rec_len = ext4_rec_len_to_disk(inode->i_sb->s_blocksize -
- EXT4_DIR_REC_LEN(1));
+ de->rec_len = ext4_rec_len_to_disk(blocksize - EXT4_DIR_REC_LEN(1),
+ blocksize);
de->name_len = 2;
strcpy(de->name, "..");
ext4_set_de_type(dir->i_sb, de, S_IFDIR);
@@ -1885,7 +1923,7 @@
return 1;
}
de = (struct ext4_dir_entry_2 *) bh->b_data;
- de1 = ext4_next_entry(de);
+ de1 = ext4_next_entry(de, sb->s_blocksize);
if (le32_to_cpu(de->inode) != inode->i_ino ||
!le32_to_cpu(de1->inode) ||
strcmp(".", de->name) ||
@@ -1896,9 +1934,9 @@
brelse(bh);
return 1;
}
- offset = ext4_rec_len_from_disk(de->rec_len) +
- ext4_rec_len_from_disk(de1->rec_len);
- de = ext4_next_entry(de1);
+ offset = ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) +
+ ext4_rec_len_from_disk(de1->rec_len, sb->s_blocksize);
+ de = ext4_next_entry(de1, sb->s_blocksize);
while (offset < inode->i_size) {
if (!bh ||
(void *) de >= (void *) (bh->b_data+sb->s_blocksize)) {
@@ -1927,8 +1965,8 @@
brelse(bh);
return 0;
}
- offset += ext4_rec_len_from_disk(de->rec_len);
- de = ext4_next_entry(de);
+ offset += ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize);
+ de = ext4_next_entry(de, sb->s_blocksize);
}
brelse(bh);
return 1;
@@ -2297,8 +2335,8 @@
return err;
}
-#define PARENT_INO(buffer) \
- (ext4_next_entry((struct ext4_dir_entry_2 *)(buffer))->inode)
+#define PARENT_INO(buffer, size) \
+ (ext4_next_entry((struct ext4_dir_entry_2 *)(buffer), size)->inode)
/*
* Anybody can rename anything with this: the permission checks are left to the
@@ -2358,7 +2396,8 @@
dir_bh = ext4_bread(handle, old_inode, 0, 0, &retval);
if (!dir_bh)
goto end_rename;
- if (le32_to_cpu(PARENT_INO(dir_bh->b_data)) != old_dir->i_ino)
+ if (le32_to_cpu(PARENT_INO(dir_bh->b_data,
+ old_dir->i_sb->s_blocksize)) != old_dir->i_ino)
goto end_rename;
retval = -EMLINK;
if (!new_inode && new_dir != old_dir &&
@@ -2430,7 +2469,8 @@
if (dir_bh) {
BUFFER_TRACE(dir_bh, "get_write_access");
ext4_journal_get_write_access(handle, dir_bh);
- PARENT_INO(dir_bh->b_data) = cpu_to_le32(new_dir->i_ino);
+ PARENT_INO(dir_bh->b_data, new_dir->i_sb->s_blocksize) =
+ cpu_to_le32(new_dir->i_ino);
BUFFER_TRACE(dir_bh, "call ext4_handle_dirty_metadata");
ext4_handle_dirty_metadata(handle, old_dir, dir_bh);
ext4_dec_count(handle, old_dir);
