/*
* So this function is called when the volume is mkfsed with
* dir_index disabled. In order to keep f_pos persistent
* after we convert from an inlined dir to a blocked based,
* we just pretend that we are a normal dir and return the
* offset as if '.' and '..' really take place.
*
*/
int ext4_read_inline_dir(struct file *file,
struct dir_context *ctx,
int *has_inline_data)
{
unsigned int offset, parent_ino;
int i;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
struct inode *inode = file_inode(file);
int ret, inline_size = 0;
struct ext4_iloc iloc;
void *dir_buf = NULL;
int dotdot_offset, dotdot_size, extra_offset, extra_size;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
down_read(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
up_read(&EXT4_I(inode)->xattr_sem);
*has_inline_data = 0;
goto out;
}
inline_size = ext4_get_inline_size(inode);
dir_buf = kmalloc(inline_size, GFP_NOFS);
if (!dir_buf) {
ret = -ENOMEM;
up_read(&EXT4_I(inode)->xattr_sem);
goto out;
}
ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
up_read(&EXT4_I(inode)->xattr_sem);
if (ret < 0)
goto out;
ret = 0;
sb = inode->i_sb;
parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
offset = ctx->pos;
/*
* dotdot_offset and dotdot_size is the real offset and
* size for ".." and "." if the dir is block based while
* the real size for them are only EXT4_INLINE_DOTDOT_SIZE.
* So we will use extra_offset and extra_size to indicate them
* during the inline dir iteration.
*/
dotdot_offset = EXT4_DIR_REC_LEN(1);
dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2);
extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE;
extra_size = extra_offset + inline_size;
/*
* If the version has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the inline
* dir to make sure.
*/
if (file->f_version != inode->i_version) {
for (i = 0; i < extra_size && i < offset;) {
/*
* "." is with offset 0 and
* ".." is dotdot_offset.
*/
if (!i) {
i = dotdot_offset;
continue;
} else if (i == dotdot_offset) {
i = dotdot_size;
continue;
}
/* for other entry, the real offset in
* the buf has to be tuned accordingly.
*/
de = (struct ext4_dir_entry_2 *)
(dir_buf + i - extra_offset);
/* It's too expensive to do a full
* dirent test each time round this
* loop, but we do have to test at
* 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, extra_size)
< EXT4_DIR_REC_LEN(1))
break;
i += ext4_rec_len_from_disk(de->rec_len,
extra_size);
}
offset = i;
ctx->pos = offset;
file->f_version = inode->i_version;
}
while (ctx->pos < extra_size) {
if (ctx->pos == 0) {
if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR))
goto out;
ctx->pos = dotdot_offset;
continue;
}
if (ctx->pos == dotdot_offset) {
if (!dir_emit(ctx, "..", 2, parent_ino, DT_DIR))
goto out;
ctx->pos = dotdot_size;
continue;
}
de = (struct ext4_dir_entry_2 *)
(dir_buf + ctx->pos - extra_offset);
if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf,
extra_size, ctx->pos))
goto out;
if (le32_to_cpu(de->inode)) {
if (!dir_emit(ctx, de->name, de->name_len,
le32_to_cpu(de->inode),
get_dtype(sb, de->file_type)))
goto out;
}
ctx->pos += ext4_rec_len_from_disk(de->rec_len, extra_size);
}
out:
kfree(dir_buf);
brelse(iloc.bh);
return ret;
}
static int ext4_destroy_inline_data_nolock(handle_t *handle,
struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_xattr_ibody_find is = {
.s = { .not_found = 0, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
.value = NULL,
.value_len = 0,
};
int error;
if (!ei->i_inline_off)
return 0;
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
return error;
error = ext4_xattr_ibody_find(inode, &i, &is);
if (error)
goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error)
goto out;
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
if (ext4_has_feature_extents(inode->i_sb)) {
if (S_ISDIR(inode->i_mode) ||
S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) {
ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode);
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
get_bh(is.iloc.bh);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
EXT4_I(inode)->i_inline_off = 0;
EXT4_I(inode)->i_inline_size = 0;
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
out:
brelse(is.iloc.bh);
if (error == -ENODATA)
error = 0;
return error;
}
static int ext4_read_inline_page(struct inode *inode, struct page *page)
{
void *kaddr;
int ret = 0;
size_t len;
struct ext4_iloc iloc;
BUG_ON(!PageLocked(page));
BUG_ON(!ext4_has_inline_data(inode));
BUG_ON(page->index);
if (!EXT4_I(inode)->i_inline_off) {
ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.",
inode->i_ino);
goto out;
}
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
goto out;
len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
kaddr = kmap_atomic(page);
ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
flush_dcache_page(page);
kunmap_atomic(kaddr);
zero_user_segment(page, len, PAGE_CACHE_SIZE);
SetPageUptodate(page);
brelse(iloc.bh);
out:
return ret;
}
/*
* This function fills a red-black tree with information from an
* inlined dir. It returns the number directory entries loaded
* into the tree. If there is an error it is returned in err.
*/
int htree_inlinedir_to_tree(struct file *dir_file,
struct inode *dir, ext4_lblk_t block,
struct dx_hash_info *hinfo,
__u32 start_hash, __u32 start_minor_hash,
int *has_inline_data)
{
int err = 0, count = 0;
unsigned int parent_ino;
int pos;
struct ext4_dir_entry_2 *de;
struct inode *inode = file_inode(dir_file);
int ret, inline_size = 0;
struct ext4_iloc iloc;
void *dir_buf = NULL;
struct ext4_dir_entry_2 fake;
struct ext4_str tmp_str;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
down_read(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
up_read(&EXT4_I(inode)->xattr_sem);
*has_inline_data = 0;
goto out;
}
inline_size = ext4_get_inline_size(inode);
dir_buf = kmalloc(inline_size, GFP_NOFS);
if (!dir_buf) {
ret = -ENOMEM;
up_read(&EXT4_I(inode)->xattr_sem);
goto out;
}
ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
up_read(&EXT4_I(inode)->xattr_sem);
if (ret < 0)
goto out;
pos = 0;
parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
while (pos < inline_size) {
/*
* As inlined dir doesn't store any information about '.' and
* only the inode number of '..' is stored, we have to handle
* them differently.
*/
if (pos == 0) {
fake.inode = cpu_to_le32(inode->i_ino);
fake.name_len = 1;
strcpy(fake.name, ".");
fake.rec_len = ext4_rec_len_to_disk(
EXT4_DIR_REC_LEN(fake.name_len),
inline_size);
ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
de = &fake;
pos = EXT4_INLINE_DOTDOT_OFFSET;
} else if (pos == EXT4_INLINE_DOTDOT_OFFSET) {
fake.inode = cpu_to_le32(parent_ino);
fake.name_len = 2;
strcpy(fake.name, "..");
fake.rec_len = ext4_rec_len_to_disk(
EXT4_DIR_REC_LEN(fake.name_len),
inline_size);
ext4_set_de_type(inode->i_sb, &fake, S_IFDIR);
de = &fake;
pos = EXT4_INLINE_DOTDOT_SIZE;
} else {
de = (struct ext4_dir_entry_2 *)(dir_buf + pos);
pos += ext4_rec_len_from_disk(de->rec_len, inline_size);
if (ext4_check_dir_entry(inode, dir_file, de,
iloc.bh, dir_buf,
inline_size, pos)) {
ret = count;
goto out;
}
}
ext4fs_dirhash(de->name, de->name_len, hinfo);
if ((hinfo->hash < start_hash) ||
((hinfo->hash == start_hash) &&
(hinfo->minor_hash < start_minor_hash)))
continue;
if (de->inode == 0)
continue;
tmp_str.name = de->name;
tmp_str.len = de->name_len;
err = ext4_htree_store_dirent(dir_file, hinfo->hash,
hinfo->minor_hash, de, &tmp_str);
if (err) {
count = err;
goto out;
}
count++;
}
ret = count;
out:
kfree(dir_buf);
brelse(iloc.bh);
return ret;
}
static int ext4_convert_inline_data_nolock(handle_t *handle,
struct inode *inode,
struct ext4_iloc *iloc)
{
int error;
void *buf = NULL;
struct buffer_head *data_bh = NULL;
struct ext4_map_blocks map;
int inline_size;
inline_size = ext4_get_inline_size(inode);
buf = kmalloc(inline_size, GFP_NOFS);
if (!buf) {
error = -ENOMEM;
goto out;
}
error = ext4_read_inline_data(inode, buf, inline_size, iloc);
if (error < 0)
goto out;
/*
* Make sure the inline directory entries pass checks before we try to
* convert them, so that we avoid touching stuff that needs fsck.
*/
if (S_ISDIR(inode->i_mode)) {
error = ext4_check_all_de(inode, iloc->bh,
buf + EXT4_INLINE_DOTDOT_SIZE,
inline_size - EXT4_INLINE_DOTDOT_SIZE);
if (error)
goto out;
}
error = ext4_destroy_inline_data_nolock(handle, inode);
if (error)
goto out;
map.m_lblk = 0;
map.m_len = 1;
map.m_flags = 0;
error = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE);
if (error < 0)
goto out_restore;
if (!(map.m_flags & EXT4_MAP_MAPPED)) {
error = -EIO;
goto out_restore;
}
data_bh = sb_getblk(inode->i_sb, map.m_pblk);
if (!data_bh) {
error = -ENOMEM;
goto out_restore;
}
lock_buffer(data_bh);
error = ext4_journal_get_create_access(handle, data_bh);
if (error) {
unlock_buffer(data_bh);
error = -EIO;
goto out_restore;
}
memset(data_bh->b_data, 0, inode->i_sb->s_blocksize);
if (!S_ISDIR(inode->i_mode)) {
memcpy(data_bh->b_data, buf, inline_size);
set_buffer_uptodate(data_bh);
error = ext4_handle_dirty_metadata(handle,
inode, data_bh);
} else {
error = ext4_finish_convert_inline_dir(handle, inode, data_bh,
buf, inline_size);
}
unlock_buffer(data_bh);
out_restore:
if (error)
ext4_restore_inline_data(handle, inode, iloc, buf, inline_size);
out:
brelse(data_bh);
kfree(buf);
return error;
}
static int ext4_convert_inline_data_nolock(handle_t *handle,
struct inode *inode,
struct ext4_iloc *iloc)
{
int error;
void *buf = NULL;
struct buffer_head *data_bh = NULL;
struct ext4_map_blocks map;
int inline_size;
inline_size = ext4_get_inline_size(inode);
buf = kmalloc(inline_size, GFP_NOFS);
if (!buf) {
error = -ENOMEM;
goto out;
}
error = ext4_read_inline_data(inode, buf, inline_size, iloc);
if (error < 0)
goto out;
error = ext4_destroy_inline_data_nolock(handle, inode);
if (error)
goto out;
map.m_lblk = 0;
map.m_len = 1;
map.m_flags = 0;
error = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_CREATE);
if (error < 0)
goto out_restore;
if (!(map.m_flags & EXT4_MAP_MAPPED)) {
error = -EIO;
goto out_restore;
}
data_bh = sb_getblk(inode->i_sb, map.m_pblk);
if (!data_bh) {
error = -ENOMEM;
goto out_restore;
}
lock_buffer(data_bh);
error = ext4_journal_get_create_access(handle, data_bh);
if (error) {
unlock_buffer(data_bh);
error = -EIO;
goto out_restore;
}
memset(data_bh->b_data, 0, inode->i_sb->s_blocksize);
if (!S_ISDIR(inode->i_mode)) {
memcpy(data_bh->b_data, buf, inline_size);
set_buffer_uptodate(data_bh);
error = ext4_handle_dirty_metadata(handle,
inode, data_bh);
} else {
error = ext4_finish_convert_inline_dir(handle, inode, data_bh,
buf, inline_size);
}
unlock_buffer(data_bh);
out_restore:
if (error)
ext4_restore_inline_data(handle, inode, iloc, buf, inline_size);
out:
brelse(data_bh);
kfree(buf);
return error;
}
int ext4_read_inline_dir(struct file *filp,
void *dirent, filldir_t filldir,
int *has_inline_data)
{
int error = 0;
unsigned int offset, parent_ino;
int i, stored;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
struct inode *inode = filp->f_path.dentry->d_inode;
int ret, inline_size = 0;
struct ext4_iloc iloc;
void *dir_buf = NULL;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
down_read(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
up_read(&EXT4_I(inode)->xattr_sem);
*has_inline_data = 0;
goto out;
}
inline_size = ext4_get_inline_size(inode);
dir_buf = kmalloc(inline_size, GFP_NOFS);
if (!dir_buf) {
ret = -ENOMEM;
up_read(&EXT4_I(inode)->xattr_sem);
goto out;
}
ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
up_read(&EXT4_I(inode)->xattr_sem);
if (ret < 0)
goto out;
sb = inode->i_sb;
stored = 0;
parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
while (!error && !stored && filp->f_pos < inode->i_size) {
revalidate:
/*
* If the version has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the inline
* dir to make sure.
*/
if (filp->f_version != inode->i_version) {
for (i = 0;
i < inode->i_size && i < offset;) {
if (!i) {
/* skip "." and ".." if needed. */
i += EXT4_INLINE_DOTDOT_SIZE;
continue;
}
de = (struct ext4_dir_entry_2 *)
(dir_buf + i);
/* It's too expensive to do a full
* dirent test each time round this
* loop, but we do have to test at
* 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,
inline_size) < EXT4_DIR_REC_LEN(1))
break;
i += ext4_rec_len_from_disk(de->rec_len,
inline_size);
}
offset = i;
filp->f_pos = offset;
filp->f_version = inode->i_version;
}
while (!error && filp->f_pos < inode->i_size) {
if (filp->f_pos == 0) {
error = filldir(dirent, ".", 1, 0, inode->i_ino,
DT_DIR);
if (error)
break;
stored++;
error = filldir(dirent, "..", 2, 0, parent_ino,
DT_DIR);
if (error)
break;
stored++;
filp->f_pos = offset = EXT4_INLINE_DOTDOT_SIZE;
continue;
}
de = (struct ext4_dir_entry_2 *)(dir_buf + offset);
if (ext4_check_dir_entry(inode, filp, de,
iloc.bh, dir_buf,
inline_size, offset)) {
ret = stored;
goto out;
}
offset += ext4_rec_len_from_disk(de->rec_len,
inline_size);
if (le32_to_cpu(de->inode)) {
/* We might block in the next section
* if the data destination is
* currently swapped out. So, use a
* version stamp to detect whether or
* not the directory has been modified
* 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));
if (error)
break;
if (version != filp->f_version)
goto revalidate;
stored++;
}
filp->f_pos += ext4_rec_len_from_disk(de->rec_len,
inline_size);
}
offset = 0;
}
out:
kfree(dir_buf);
brelse(iloc.bh);
return ret;
}
/*
* Called during xattr set, and if we can sparse space 'needed',
* just create the extent tree evict the data to the outer block.
*
* We use jbd2 instead of page cache to move data to the 1st block
* so that the whole transaction can be committed as a whole and
* the data isn't lost because of the delayed page cache write.
*/
int ext4_try_to_evict_inline_data(handle_t *handle,
struct inode *inode,
int needed)
{
int error;
struct ext4_xattr_entry *entry;
struct ext4_xattr_ibody_header *header;
struct ext4_inode *raw_inode;
struct ext4_iloc iloc;
void *buf = NULL;
struct buffer_head *data_bh = NULL, tmp_bh;
struct ext4_map_blocks map;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
raw_inode = ext4_raw_inode(&iloc);
header = IHDR(inode, raw_inode);
entry = (struct ext4_xattr_entry *)((void *)raw_inode +
EXT4_I(inode)->i_inline_off);
if (EXT4_XATTR_LEN(entry->e_name_len) +
EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size)) < needed) {
error = -ENOSPC;
goto out;
}
buf = kmalloc(ext4_get_inline_size(inode), GFP_NOFS);
if (!buf) {
error = -ENOMEM;
goto out;
}
error = ext4_read_inline_data(inode, buf,
ext4_get_inline_size(inode), &iloc);
if (error < 0)
goto out;
error = ext4_destroy_inline_data_nolock(handle, inode);
if (error)
goto out;
map.m_lblk = 0;
map.m_len = 1;
map.m_flags = 0;
error = ext4_get_blocks(handle, inode, &map, &tmp_bh, EXT4_GET_BLOCKS_CREATE);
if (error < 0)
goto out;
if (!(map.m_flags & EXT4_MAP_MAPPED)) {
error = -EIO;
goto out;
}
data_bh = sb_getblk(inode->i_sb, map.m_pblk);
if (!data_bh) {
error = -EIO;
goto out;
}
lock_buffer(data_bh);
error = ext4_journal_get_create_access(handle, data_bh);
if (error) {
unlock_buffer(data_bh);
error = -EIO;
goto out;
}
memcpy(data_bh->b_data, buf, data_bh->b_size);
set_buffer_uptodate(data_bh);
unlock_buffer(data_bh);
error = ext4_handle_dirty_metadata(handle,
inode, data_bh);
out:
brelse(data_bh);
kfree(buf);
brelse(iloc.bh);
return error;
}