/*
* Migrate a simple extent-based inode to use the i_blocks[] array
*/
int ext4_ind_migrate(struct inode *inode)
{
struct ext4_extent_header *eh;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC))
return -EOPNOTSUPP;
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
down_write(&EXT4_I(inode)->i_data_sem);
ret = ext4_ext_check_inode(inode);
if (ret)
goto errout;
eh = ext_inode_hdr(inode);
ex = EXT_FIRST_EXTENT(eh);
if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS ||
eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) {
ret = -EOPNOTSUPP;
goto errout;
}
if (eh->eh_entries == 0)
blk = len = 0;
else {
len = le16_to_cpu(ex->ee_len);
blk = ext4_ext_pblock(ex);
if (len > EXT4_NDIR_BLOCKS) {
ret = -EOPNOTSUPP;
goto errout;
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
memset(ei->i_data, 0, sizeof(ei->i_data));
for (i=0; i < len; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
errout:
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
return ret;
}
int ext4_delete_inline_entry(handle_t *handle,
struct inode *dir,
struct ext4_dir_entry_2 *de_del,
struct buffer_head *bh,
int *has_inline_data)
{
int err, inline_size;
struct ext4_iloc iloc;
void *inline_start;
err = ext4_get_inode_loc(dir, &iloc);
if (err)
return err;
down_write(&EXT4_I(dir)->xattr_sem);
if (!ext4_has_inline_data(dir)) {
*has_inline_data = 0;
goto out;
}
if ((void *)de_del - ((void *)ext4_raw_inode(&iloc)->i_block) <
EXT4_MIN_INLINE_DATA_SIZE) {
inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
EXT4_INLINE_DOTDOT_SIZE;
inline_size = EXT4_MIN_INLINE_DATA_SIZE -
EXT4_INLINE_DOTDOT_SIZE;
} else {
inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
inline_size = ext4_get_inline_size(dir) -
EXT4_MIN_INLINE_DATA_SIZE;
}
BUFFER_TRACE(bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bh);
if (err)
goto out;
err = ext4_generic_delete_entry(handle, dir, de_del, bh,
inline_start, inline_size, 0);
if (err)
goto out;
BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
err = ext4_mark_inode_dirty(handle, dir);
if (unlikely(err))
goto out;
ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size);
out:
up_write(&EXT4_I(dir)->xattr_sem);
brelse(iloc.bh);
if (err != -ENOENT)
ext4_std_error(dir->i_sb, err);
return err;
}
static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
struct inode *tmp_inode)
{
int retval;
__le32 i_data[3];
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
/*
* One credit accounted for writing the
* i_data field of the original inode
*/
retval = ext4_journal_extend(handle, 1);
if (retval != 0) {
retval = ext4_journal_restart(handle, 1);
if (retval)
goto err_out;
}
i_data[0] = ei->i_data[EXT4_IND_BLOCK];
i_data[1] = ei->i_data[EXT4_DIND_BLOCK];
i_data[2] = ei->i_data[EXT4_TIND_BLOCK];
down_write(&EXT4_I(inode)->i_data_sem);
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
*/
ei->i_flags |= EXT4_EXTENTS_FL;
memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
/*
* Update i_blocks with the new blocks that got
* allocated while adding extents for extent index
* blocks.
*
* While converting to extents we need not
* update the orignal inode i_blocks for extent blocks
* via quota APIs. The quota update happened via tmp_inode already.
*/
spin_lock(&inode->i_lock);
inode->i_blocks += tmp_inode->i_blocks;
spin_unlock(&inode->i_lock);
up_write(&EXT4_I(inode)->i_data_sem);
/*
* We mark the inode dirty after, because we decrement the
* i_blocks when freeing the indirect meta-data blocks
*/
retval = free_ind_block(handle, inode, i_data);
ext4_mark_inode_dirty(handle, inode);
err_out:
return retval;
}
/*
* Set the access or default ACL of an inode.
*
* inode->i_mutex: down unless called from ext4_new_inode
*/
static int
ext4_set_acl(handle_t *handle, struct inode *inode, int type,
struct posix_acl *acl)
{
int name_index;
void *value = NULL;
size_t size = 0;
int error;
if (S_ISLNK(inode->i_mode))
return -EOPNOTSUPP;
switch (type) {
case ACL_TYPE_ACCESS:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl) {
mode_t mode = inode->i_mode;
error = posix_acl_equiv_mode(acl, &mode);
if (error < 0)
return error;
else {
inode->i_mode = mode;
ext4_mark_inode_dirty(handle, inode);
if (error == 0)
acl = NULL;
}
}
break;
case ACL_TYPE_DEFAULT:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
if (!S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
break;
default:
return -EINVAL;
}
if (acl) {
value = ext4_acl_to_disk(acl, &size);
if (IS_ERR(value))
return (int)PTR_ERR(value);
}
error = ext4_xattr_set_handle(handle, inode, name_index, "",
value, size, 0);
kfree(value);
if (!error)
set_cached_acl(inode, type, acl);
return error;
}
static int ext4_finish_convert_inline_dir(handle_t *handle,
struct inode *inode,
struct buffer_head *dir_block,
void *buf,
int inline_size)
{
int err, csum_size = 0, header_size = 0;
struct ext4_dir_entry_2 *de;
struct ext4_dir_entry_tail *t;
void *target = dir_block->b_data;
/*
* First create "." and ".." and then copy the dir information
* back to the block.
*/
de = (struct ext4_dir_entry_2 *)target;
de = ext4_init_dot_dotdot(inode, de,
inode->i_sb->s_blocksize, csum_size,
le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1);
header_size = (void *)de - target;
memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE,
inline_size - EXT4_INLINE_DOTDOT_SIZE);
if (ext4_has_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
inode->i_size = inode->i_sb->s_blocksize;
i_size_write(inode, inode->i_sb->s_blocksize);
EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
ext4_update_final_de(dir_block->b_data,
inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size,
inode->i_sb->s_blocksize - csum_size);
if (csum_size) {
t = EXT4_DIRENT_TAIL(dir_block->b_data,
inode->i_sb->s_blocksize);
initialize_dirent_tail(t, inode->i_sb->s_blocksize);
}
set_buffer_uptodate(dir_block);
err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
if (err)
return err;
set_buffer_verified(dir_block);
return ext4_mark_inode_dirty(handle, inode);
}
/*
* Set the access or default ACL of an inode.
*
* inode->i_mutex: down unless called from ext4_new_inode
*/
static int
__ext4_set_acl(handle_t *handle, struct inode *inode, int type,
struct posix_acl *acl)
{
int name_index;
void *value = NULL;
size_t size = 0;
int error;
switch (type) {
case ACL_TYPE_ACCESS:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_ACCESS;
if (acl) {
error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
if (error)
return error;
inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
}
break;
case ACL_TYPE_DEFAULT:
name_index = EXT4_XATTR_INDEX_POSIX_ACL_DEFAULT;
if (!S_ISDIR(inode->i_mode))
return acl ? -EACCES : 0;
break;
default:
return -EINVAL;
}
if (acl) {
value = ext4_acl_to_disk(acl, &size);
if (IS_ERR(value))
return (int)PTR_ERR(value);
}
error = ext4_xattr_set_handle(handle, inode, name_index, "",
value, size, 0);
kfree(value);
if (!error)
set_cached_acl(inode, type, acl);
return error;
}
/*
* Add a new entry into a inline dir.
* It will return -ENOSPC if no space is available, and -EIO
* and -EEXIST if directory entry already exists.
*/
static int ext4_add_dirent_to_inline(handle_t *handle,
struct dentry *dentry,
struct inode *inode,
struct ext4_iloc *iloc,
void *inline_start, int inline_size)
{
struct inode *dir = dentry->d_parent->d_inode;
const char *name = dentry->d_name.name;
int namelen = dentry->d_name.len;
unsigned short reclen;
int err;
struct ext4_dir_entry_2 *de;
reclen = EXT4_DIR_REC_LEN(namelen);
err = ext4_find_dest_de(dir, inode, iloc->bh,
inline_start, inline_size,
name, namelen, &de);
if (err)
return err;
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err)
return err;
ext4_insert_dentry(inode, de, inline_size, name, namelen);
ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
/*
* XXX shouldn't update any times until successful
* completion of syscall, but too many callers depend
* on this.
*
* XXX similarly, too many callers depend on
* ext4_new_inode() setting the times, but error
* recovery deletes the inode, so the worst that can
* happen is that the times are slightly out of date
* and/or different from the directory change time.
*/
dir->i_mtime = dir->i_ctime = ext4_current_time(dir);
ext4_update_dx_flag(dir);
dir->i_version++;
ext4_mark_inode_dirty(handle, dir);
return 1;
}
/*
* Add a new entry into a inline dir.
* It will return -ENOSPC if no space is available, and -EIO
* and -EEXIST if directory entry already exists.
*/
static int ext4_add_dirent_to_inline(handle_t *handle,
struct ext4_filename *fname,
struct inode *dir,
struct inode *inode,
struct ext4_iloc *iloc,
void *inline_start, int inline_size)
{
int err;
struct ext4_dir_entry_2 *de;
err = ext4_find_dest_de(dir, inode, iloc->bh, inline_start,
inline_size, fname, &de);
if (err)
return err;
BUFFER_TRACE(iloc->bh, "get_write_access");
err = ext4_journal_get_write_access(handle, iloc->bh);
if (err)
return err;
ext4_insert_dentry(dir, inode, de, inline_size, fname);
ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
/*
* XXX shouldn't update any times until successful
* completion of syscall, but too many callers depend
* on this.
*
* XXX similarly, too many callers depend on
* ext4_new_inode() setting the times, but error
* recovery deletes the inode, so the worst that can
* happen is that the times are slightly out of date
* and/or different from the directory change time.
*/
dir->i_mtime = dir->i_ctime = ext4_current_time(dir);
ext4_update_dx_flag(dir);
dir->i_version++;
ext4_mark_inode_dirty(handle, dir);
return 1;
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
struct ext4_sb_info *sbi = EXT4_SB(sb);
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode)) {
err = -EINVAL;
goto swap_boot_out;
}
if (!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto swap_boot_out;
}
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO);
if (IS_ERR(inode_bl)) {
err = PTR_ERR(inode_bl);
goto swap_boot_out;
}
ei_bl = EXT4_I(inode_bl);
filemap_flush(inode->i_mapping);
filemap_flush(inode_bl->i_mapping);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(inode);
ext4_inode_block_unlocked_dio(inode_bl);
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto journal_err_out;
}
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_bl->i_version = 1;
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (EXT4_HAS_INCOMPAT_FEATURE(sb,
EXT4_FEATURE_INCOMPAT_EXTENTS)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = ext4_current_time(inode);
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
inode_bl->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
} else {
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
}
}
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
journal_err_out:
ext4_inode_resume_unlocked_dio(inode);
ext4_inode_resume_unlocked_dio(inode_bl);
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
swap_boot_out:
return err;
}
void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
{
handle_t *handle;
int inline_size, value_len, needed_blocks;
size_t i_size;
void *value = NULL;
struct ext4_xattr_ibody_find is = {
.s = { .not_found = -ENODATA, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
};
needed_blocks = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
if (IS_ERR(handle))
return;
down_write(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
*has_inline = 0;
ext4_journal_stop(handle);
return;
}
if (ext4_orphan_add(handle, inode))
goto out;
if (ext4_get_inode_loc(inode, &is.iloc))
goto out;
down_write(&EXT4_I(inode)->i_data_sem);
i_size = inode->i_size;
inline_size = ext4_get_inline_size(inode);
EXT4_I(inode)->i_disksize = i_size;
if (i_size < inline_size) {
/* Clear the content in the xattr space. */
if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
if (ext4_xattr_ibody_find(inode, &i, &is))
goto out_error;
BUG_ON(is.s.not_found);
value_len = le32_to_cpu(is.s.here->e_value_size);
value = kmalloc(value_len, GFP_NOFS);
if (!value)
goto out_error;
if (ext4_xattr_ibody_get(inode, i.name_index, i.name,
value, value_len))
goto out_error;
i.value = value;
i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is))
goto out_error;
}
/* Clear the content within i_blocks. */
if (i_size < EXT4_MIN_INLINE_DATA_SIZE) {
void *p = (void *) ext4_raw_inode(&is.iloc)->i_block;
memset(p + i_size, 0,
EXT4_MIN_INLINE_DATA_SIZE - i_size);
}
EXT4_I(inode)->i_inline_size = i_size <
EXT4_MIN_INLINE_DATA_SIZE ?
EXT4_MIN_INLINE_DATA_SIZE : i_size;
}
out_error:
up_write(&EXT4_I(inode)->i_data_sem);
out:
brelse(is.iloc.bh);
up_write(&EXT4_I(inode)->xattr_sem);
kfree(value);
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
ext4_journal_stop(handle);
return;
}
/*
* Try to add the new entry to the inline data.
* If succeeds, return 0. If not, extended the inline dir and copied data to
* the new created block.
*/
int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
struct inode *dir, struct inode *inode)
{
int ret, inline_size;
void *inline_start;
struct ext4_iloc iloc;
ret = ext4_get_inode_loc(dir, &iloc);
if (ret)
return ret;
down_write(&EXT4_I(dir)->xattr_sem);
if (!ext4_has_inline_data(dir))
goto out;
inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
EXT4_INLINE_DOTDOT_SIZE;
inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
ret = ext4_add_dirent_to_inline(handle, fname, dir, inode, &iloc,
inline_start, inline_size);
if (ret != -ENOSPC)
goto out;
/* check whether it can be inserted to inline xattr space. */
inline_size = EXT4_I(dir)->i_inline_size -
EXT4_MIN_INLINE_DATA_SIZE;
if (!inline_size) {
/* Try to use the xattr space.*/
ret = ext4_update_inline_dir(handle, dir, &iloc);
if (ret && ret != -ENOSPC)
goto out;
inline_size = EXT4_I(dir)->i_inline_size -
EXT4_MIN_INLINE_DATA_SIZE;
}
if (inline_size) {
inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
ret = ext4_add_dirent_to_inline(handle, fname, dir,
inode, &iloc, inline_start,
inline_size);
if (ret != -ENOSPC)
goto out;
}
/*
* The inline space is filled up, so create a new block for it.
* As the extent tree will be created, we have to save the inline
* dir first.
*/
ret = ext4_convert_inline_data_nolock(handle, dir, &iloc);
out:
ext4_mark_inode_dirty(handle, dir);
up_write(&EXT4_I(dir)->xattr_sem);
brelse(iloc.bh);
return ret;
}
/*
* Migrate a simple extent-based inode to use the i_blocks[] array
*/
int ext4_ind_migrate(struct inode *inode)
{
struct ext4_extent_header *eh;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent *ex;
unsigned int i, len;
ext4_lblk_t start, end;
ext4_fsblk_t blk;
handle_t *handle;
int ret;
if (!EXT4_HAS_INCOMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_INCOMPAT_EXTENTS) ||
(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)))
return -EINVAL;
if (EXT4_HAS_RO_COMPAT_FEATURE(inode->i_sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC))
return -EOPNOTSUPP;
/*
* In order to get correct extent info, force all delayed allocation
* blocks to be allocated, otherwise delayed allocation blocks may not
* be reflected and bypass the checks on extent header.
*/
if (test_opt(inode->i_sb, DELALLOC))
ext4_alloc_da_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
down_write(&EXT4_I(inode)->i_data_sem);
ret = ext4_ext_check_inode(inode);
if (ret)
goto errout;
eh = ext_inode_hdr(inode);
ex = EXT_FIRST_EXTENT(eh);
if (ext4_blocks_count(es) > EXT4_MAX_BLOCK_FILE_PHYS ||
eh->eh_depth != 0 || le16_to_cpu(eh->eh_entries) > 1) {
ret = -EOPNOTSUPP;
goto errout;
}
if (eh->eh_entries == 0)
blk = len = start = end = 0;
else {
len = le16_to_cpu(ex->ee_len);
blk = ext4_ext_pblock(ex);
start = le32_to_cpu(ex->ee_block);
end = start + len - 1;
if (end >= EXT4_NDIR_BLOCKS) {
ret = -EOPNOTSUPP;
goto errout;
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
memset(ei->i_data, 0, sizeof(ei->i_data));
for (i = start; i <= end; i++)
ei->i_data[i] = cpu_to_le32(blk++);
ext4_mark_inode_dirty(handle, inode);
errout:
ext4_journal_stop(handle);
up_write(&EXT4_I(inode)->i_data_sem);
return ret;
}
/*
* There are two policies for allocating an inode. If the new inode is
* a directory, then a forward search is made for a block group with both
* free space and a low directory-to-inode ratio; if that fails, then of
* the groups with above-average free space, that group with the fewest
* directories already is chosen.
*
* For other inodes, search forward from the parent directory's block
* group to find a free inode.
*/
struct inode *ext4_new_inode(handle_t *handle, struct inode * dir, int mode)
{
struct super_block *sb;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
int group;
unsigned long ino = 0;
struct inode * inode;
struct ext4_group_desc * gdp = NULL;
struct ext4_super_block * es;
struct ext4_inode_info *ei;
struct ext4_sb_info *sbi;
int err = 0;
struct inode *ret;
int i;
/* Cannot create files in a deleted directory */
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
sb = dir->i_sb;
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT4_I(inode);
sbi = EXT4_SB(sb);
es = sbi->s_es;
if (S_ISDIR(mode)) {
if (test_opt (sb, OLDALLOC))
group = find_group_dir(sb, dir);
else
group = find_group_orlov(sb, dir);
} else
group = find_group_other(sb, dir);
err = -ENOSPC;
if (group == -1)
goto out;
for (i = 0; i < sbi->s_groups_count; i++) {
err = -EIO;
gdp = ext4_get_group_desc(sb, group, &bh2);
if (!gdp)
goto fail;
brelse(bitmap_bh);
bitmap_bh = read_inode_bitmap(sb, group);
if (!bitmap_bh)
goto fail;
ino = 0;
repeat_in_this_group:
ino = ext4_find_next_zero_bit((unsigned long *)
bitmap_bh->b_data, EXT4_INODES_PER_GROUP(sb), ino);
if (ino < EXT4_INODES_PER_GROUP(sb)) {
BUFFER_TRACE(bitmap_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, bitmap_bh);
if (err)
goto fail;
if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
"call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
jbd2_journal_release_buffer(handle, bitmap_bh);
if (++ino < EXT4_INODES_PER_GROUP(sb))
goto repeat_in_this_group;
}
/*
* This case is possible in concurrent environment. It is very
* rare. We cannot repeat the find_group_xxx() call because
* that will simply return the same blockgroup, because the
* group descriptor metadata has not yet been updated.
* So we just go onto the next blockgroup.
*/
if (++group == sbi->s_groups_count)
group = 0;
}
err = -ENOSPC;
goto out;
got:
ino += group * EXT4_INODES_PER_GROUP(sb) + 1;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext4_error (sb, "ext4_new_inode",
"reserved inode or inode > inodes count - "
"block_group = %d, inode=%lu", group, ino);
err = -EIO;
goto fail;
}
BUFFER_TRACE(bh2, "get_write_access");
err = ext4_journal_get_write_access(handle, bh2);
if (err) goto fail;
spin_lock(sb_bgl_lock(sbi, group));
gdp->bg_free_inodes_count =
cpu_to_le16(le16_to_cpu(gdp->bg_free_inodes_count) - 1);
if (S_ISDIR(mode)) {
gdp->bg_used_dirs_count =
cpu_to_le16(le16_to_cpu(gdp->bg_used_dirs_count) + 1);
}
spin_unlock(sb_bgl_lock(sbi, group));
BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, bh2);
if (err) goto fail;
percpu_counter_dec(&sbi->s_freeinodes_counter);
if (S_ISDIR(mode))
percpu_counter_inc(&sbi->s_dirs_counter);
sb->s_dirt = 1;
inode->i_uid = current->fsuid;
if (test_opt (sb, GRPID))
inode->i_gid = dir->i_gid;
else if (dir->i_mode & S_ISGID) {
inode->i_gid = dir->i_gid;
if (S_ISDIR(mode))
mode |= S_ISGID;
} else
inode->i_gid = current->fsgid;
inode->i_mode = mode;
inode->i_ino = ino;
/* This is the optimal IO size (for stat), not the fs block size */
inode->i_blocks = 0;
inode->i_mtime = inode->i_atime = inode->i_ctime = ei->i_crtime =
ext4_current_time(inode);
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
ei->i_flags = EXT4_I(dir)->i_flags & ~EXT4_INDEX_FL;
if (S_ISLNK(mode))
ei->i_flags &= ~(EXT4_IMMUTABLE_FL|EXT4_APPEND_FL);
/* dirsync only applies to directories */
if (!S_ISDIR(mode))
ei->i_flags &= ~EXT4_DIRSYNC_FL;
#ifdef EXT4_FRAGMENTS
ei->i_faddr = 0;
ei->i_frag_no = 0;
ei->i_frag_size = 0;
#endif
ei->i_file_acl = 0;
ei->i_dir_acl = 0;
ei->i_dtime = 0;
ei->i_block_alloc_info = NULL;
ei->i_block_group = group;
ext4_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
insert_inode_hash(inode);
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state = EXT4_STATE_NEW;
ei->i_extra_isize = EXT4_SB(sb)->s_want_extra_isize;
ret = inode;
if(DQUOT_ALLOC_INODE(inode)) {
err = -EDQUOT;
goto fail_drop;
}
err = ext4_init_acl(handle, inode, dir);
if (err)
goto fail_free_drop;
err = ext4_init_security(handle,inode, dir);
if (err)
goto fail_free_drop;
err = ext4_mark_inode_dirty(handle, inode);
if (err) {
ext4_std_error(sb, err);
goto fail_free_drop;
}
if (test_opt(sb, EXTENTS)) {
EXT4_I(inode)->i_flags |= EXT4_EXTENTS_FL;
ext4_ext_tree_init(handle, inode);
if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) {
err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
if (err) goto fail;
EXT4_SET_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS);
BUFFER_TRACE(EXT4_SB(sb)->s_sbh, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, EXT4_SB(sb)->s_sbh);
}
}
ext4_debug("allocating inode %lu\n", inode->i_ino);
goto really_out;
fail:
ext4_std_error(sb, err);
out:
iput(inode);
ret = ERR_PTR(err);
really_out:
brelse(bitmap_bh);
return ret;
fail_free_drop:
DQUOT_FREE_INODE(inode);
fail_drop:
DQUOT_DROP(inode);
inode->i_flags |= S_NOQUOTA;
inode->i_nlink = 0;
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}
void ext4_inline_data_truncate(struct inode *inode)
{
handle_t *handle;
int inline_size = ext4_get_inline_size(inode);
size_t isize = i_size_read(inode);
int needed_blocks, value_len;
void *value = NULL;
struct ext4_xattr_ibody_find is = {
.s = { .not_found = -ENODATA, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM_DATA,
.name = EXT4_XATTR_SYSTEM_DATA_NAME,
};
needed_blocks = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, needed_blocks);
if (IS_ERR(handle))
return;
if (ext4_orphan_add(handle, inode))
goto out;
EXT4_I(inode)->i_disksize = inode->i_size;
if (isize < ext4_get_max_inline_size(inode)) {
if (ext4_get_inode_loc(inode, &is.iloc))
goto out;
if (isize < EXT4_MIN_INLINE_DATA_SIZE)
memset(ext4_raw_inode(&is.iloc)->i_block + isize, 0,
EXT4_MIN_INLINE_DATA_SIZE - isize);
if (inline_size > EXT4_MIN_INLINE_DATA_SIZE &&
isize < inline_size) {
if (ext4_xattr_ibody_find(inode, &i, &is))
goto out_bh;
BUG_ON(is.s.not_found);
value_len = le32_to_cpu(is.s.here->e_value_size);
value = kmalloc(value_len, GFP_NOFS);
if (ext4_xattr_ibody_get(inode, i.name_index, i.name,
value, value_len))
goto out_bh;
i.value = value;
i.value_len = isize - EXT4_MIN_INLINE_DATA_SIZE;
if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is))
goto out_bh;
}
if (isize < inline_size)
EXT4_I(inode)->i_inline_size = isize <
EXT4_MIN_INLINE_DATA_SIZE ?
EXT4_MIN_INLINE_DATA_SIZE : isize;
out_bh:
if (value)
kfree(value);
brelse(is.iloc.bh);
} else
ext4_convert_inline_data_to_extent(inode->i_mapping, inode, 0);
out:
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
ext4_journal_stop(handle);
}
/*
* Try to add the new entry to the inline data.
* If succeeds, return 0. If not, extended the inline dir and copied data to
* the new created block.
*/
int ext4_try_add_inline_entry(handle_t *handle, struct dentry *dentry,
struct inode *inode)
{
int ret, inline_size;
void *inline_start, *backup_buf = NULL;
struct buffer_head *dir_block = NULL;
struct ext4_iloc iloc;
int blocksize = inode->i_sb->s_blocksize;
struct inode *dir = dentry->d_parent->d_inode;
ret = ext4_get_inode_loc(dir, &iloc);
if (ret)
return ret;
down_write(&EXT4_I(dir)->xattr_sem);
if (!ext4_has_inline_data(dir))
goto out;
inline_start = ext4_raw_inode(&iloc)->i_block;
inline_size = EXT4_MIN_INLINE_DATA_SIZE;
ret = ext4_add_dirent_to_inline(handle, dentry, inode, &iloc,
inline_start, inline_size);
if (ret != -ENOSPC)
goto out;
/* check whether it can be inserted to inline xattr space. */
inline_size = EXT4_I(dir)->i_inline_size -
EXT4_MIN_INLINE_DATA_SIZE;
if (inline_size > 0) {
inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
ret = ext4_add_dirent_to_inline(handle, dentry, inode, &iloc,
inline_start, inline_size);
if (ret != -ENOSPC)
goto out;
}
/* Try to add more xattr space.*/
ret = ext4_update_inline_dir(handle, dentry, dir, &iloc);
if (ret && ret != -ENOSPC)
goto out;
else if (!ret) {
inline_size = EXT4_I(dir)->i_inline_size -
EXT4_MIN_INLINE_DATA_SIZE;
inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
ret = ext4_add_dirent_to_inline(handle, dentry, inode, &iloc,
inline_start, inline_size);
if (ret != -ENOSPC)
goto out;
}
/*
* The inline space is filled up, so create a new block for it.
* As the extent tree will be created, we have to save the inline
* dir first.
*/
inline_size = EXT4_I(dir)->i_inline_size;
backup_buf = kmalloc(inline_size, GFP_NOFS);
if (!backup_buf) {
ret = -ENOMEM;
goto out;
}
memcpy(backup_buf, (void *)ext4_raw_inode(&iloc)->i_block,
EXT4_MIN_INLINE_DATA_SIZE);
if (inline_size > EXT4_MIN_INLINE_DATA_SIZE)
memcpy(backup_buf + EXT4_MIN_INLINE_DATA_SIZE,
ext4_get_inline_xattr_pos(dir, &iloc),
inline_size - EXT4_MIN_INLINE_DATA_SIZE);
/* clear the entry and the flag in dir now. */
ret = ext4_destroy_inline_data_nolock(handle, dir);
if (ret)
goto out;
dir->i_size = EXT4_I(dir)->i_disksize = blocksize;
dir_block = ext4_bread(handle, dir, 0, 1, &ret);
if (!dir_block)
goto out;
BUFFER_TRACE(dir_block, "get_write_access");
ret = ext4_journal_get_write_access(handle, dir_block);
if (ret)
goto out;
memcpy(dir_block->b_data, backup_buf, inline_size);
/* Set the final de to cover the whole block. */
ext4_update_final_de(dir_block->b_data, inline_size,
blocksize);
BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
ret = ext4_handle_dirty_metadata(handle, dir, dir_block);
out:
kfree(backup_buf);
brelse(dir_block);
if (!ret || ret == 1)
ext4_mark_inode_dirty(handle, dir);
up_write(&EXT4_I(dir)->xattr_sem);
brelse(iloc.bh);
return ret;
}
/**
* Swap the information from the given @inode and the inode
* EXT4_BOOT_LOADER_INO. It will basically swap i_data and all other
* important fields of the inodes.
*
* @sb: the super block of the filesystem
* @inode: the inode to swap with EXT4_BOOT_LOADER_INO
*
*/
static long swap_inode_boot_loader(struct super_block *sb,
struct inode *inode)
{
handle_t *handle;
int err;
struct inode *inode_bl;
struct ext4_inode_info *ei_bl;
qsize_t size, size_bl, diff;
blkcnt_t blocks;
unsigned short bytes;
inode_bl = ext4_iget(sb, EXT4_BOOT_LOADER_INO, EXT4_IGET_SPECIAL);
if (IS_ERR(inode_bl))
return PTR_ERR(inode_bl);
ei_bl = EXT4_I(inode_bl);
/* Protect orig inodes against a truncate and make sure,
* that only 1 swap_inode_boot_loader is running. */
lock_two_nondirectories(inode, inode_bl);
if (inode->i_nlink != 1 || !S_ISREG(inode->i_mode) ||
IS_SWAPFILE(inode) || IS_ENCRYPTED(inode) ||
(EXT4_I(inode)->i_flags & EXT4_JOURNAL_DATA_FL) ||
ext4_has_inline_data(inode)) {
err = -EINVAL;
goto journal_err_out;
}
if (IS_RDONLY(inode) || IS_APPEND(inode) || IS_IMMUTABLE(inode) ||
!inode_owner_or_capable(inode) || !capable(CAP_SYS_ADMIN)) {
err = -EPERM;
goto journal_err_out;
}
down_write(&EXT4_I(inode)->i_mmap_sem);
err = filemap_write_and_wait(inode->i_mapping);
if (err)
goto err_out;
err = filemap_write_and_wait(inode_bl->i_mapping);
if (err)
goto err_out;
/* Wait for all existing dio workers */
inode_dio_wait(inode);
inode_dio_wait(inode_bl);
truncate_inode_pages(&inode->i_data, 0);
truncate_inode_pages(&inode_bl->i_data, 0);
handle = ext4_journal_start(inode_bl, EXT4_HT_MOVE_EXTENTS, 2);
if (IS_ERR(handle)) {
err = -EINVAL;
goto err_out;
}
/* Protect extent tree against block allocations via delalloc */
ext4_double_down_write_data_sem(inode, inode_bl);
if (inode_bl->i_nlink == 0) {
/* this inode has never been used as a BOOT_LOADER */
set_nlink(inode_bl, 1);
i_uid_write(inode_bl, 0);
i_gid_write(inode_bl, 0);
inode_bl->i_flags = 0;
ei_bl->i_flags = 0;
inode_set_iversion(inode_bl, 1);
i_size_write(inode_bl, 0);
inode_bl->i_mode = S_IFREG;
if (ext4_has_feature_extents(sb)) {
ext4_set_inode_flag(inode_bl, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode_bl);
} else
memset(ei_bl->i_data, 0, sizeof(ei_bl->i_data));
}
err = dquot_initialize(inode);
if (err)
goto err_out1;
size = (qsize_t)(inode->i_blocks) * (1 << 9) + inode->i_bytes;
size_bl = (qsize_t)(inode_bl->i_blocks) * (1 << 9) + inode_bl->i_bytes;
diff = size - size_bl;
swap_inode_data(inode, inode_bl);
inode->i_ctime = inode_bl->i_ctime = current_time(inode);
inode->i_generation = prandom_u32();
inode_bl->i_generation = prandom_u32();
reset_inode_seed(inode);
reset_inode_seed(inode_bl);
ext4_discard_preallocations(inode);
err = ext4_mark_inode_dirty(handle, inode);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode->i_ino, err);
/* Revert all changes: */
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
goto err_out1;
}
blocks = inode_bl->i_blocks;
bytes = inode_bl->i_bytes;
inode_bl->i_blocks = inode->i_blocks;
inode_bl->i_bytes = inode->i_bytes;
err = ext4_mark_inode_dirty(handle, inode_bl);
if (err < 0) {
/* No need to update quota information. */
ext4_warning(inode_bl->i_sb,
"couldn't mark inode #%lu dirty (err %d)",
inode_bl->i_ino, err);
goto revert;
}
/* Bootloader inode should not be counted into quota information. */
if (diff > 0)
dquot_free_space(inode, diff);
else
err = dquot_alloc_space(inode, -1 * diff);
if (err < 0) {
revert:
/* Revert all changes: */
inode_bl->i_blocks = blocks;
inode_bl->i_bytes = bytes;
swap_inode_data(inode, inode_bl);
ext4_mark_inode_dirty(handle, inode);
ext4_mark_inode_dirty(handle, inode_bl);
}
err_out1:
ext4_journal_stop(handle);
ext4_double_up_write_data_sem(inode, inode_bl);
err_out:
up_write(&EXT4_I(inode)->i_mmap_sem);
journal_err_out:
unlock_two_nondirectories(inode, inode_bl);
iput(inode_bl);
return err;
}
