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_file_open(struct inode * inode, struct file * filp)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!(sb->s_flags & MS_RDONLY))) {
sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
memset(buf, 0, sizeof(buf));
path.mnt = mnt;
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
handle_t *handle;
int err;
handle = ext4_journal_start_sb(sb, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err) {
ext4_journal_stop(handle);
return err;
}
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
ext4_handle_dirty_super(handle, sb);
ext4_journal_stop(handle);
}
}
if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
spin_lock(&inode->i_lock);
if (!ei->jinode) {
if (!jinode) {
spin_unlock(&inode->i_lock);
return -ENOMEM;
}
ei->jinode = jinode;
jbd2_journal_init_jbd_inode(ei->jinode, inode);
jinode = NULL;
}
spin_unlock(&inode->i_lock);
if (unlikely(jinode != NULL))
jbd2_free_inode(jinode);
}
return dquot_file_open(inode, filp);
}
/*
* 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;
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT4_IOC_GETFLAGS:
ext4_get_inode_flags(ei);
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
handle_t *handle = NULL;
int err, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags, mask, i;
unsigned int jflag;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
err = mnt_want_write_file(filp);
if (err)
return err;
flags = ext4_mask_flags(inode->i_mode, flags);
err = -EPERM;
mutex_lock(&inode->i_mutex);
/* Is it quota file? Do not allow user to mess with it */
if (IS_NOQUOTA(inode))
goto flags_out;
oldflags = ei->i_flags;
/* The JOURNAL_DATA flag is modifiable only by root */
jflag = flags & EXT4_JOURNAL_DATA_FL;
/*
* The IMMUTABLE and APPEND_ONLY flags can only be changed by
* the relevant capability.
*
* This test looks nicer. Thanks to Pauline Middelink
*/
if ((flags ^ oldflags) & (EXT4_APPEND_FL | EXT4_IMMUTABLE_FL)) {
if (!capable(CAP_LINUX_IMMUTABLE))
goto flags_out;
}
/*
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
*/
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
migrate = 1;
if (flags & EXT4_EOFBLOCKS_FL) {
/* we don't support adding EOFBLOCKS flag */
if (!(oldflags & EXT4_EOFBLOCKS_FL)) {
err = -EOPNOTSUPP;
goto flags_out;
}
} else if (oldflags & EXT4_EOFBLOCKS_FL)
ext4_truncate(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
}
if (IS_SYNC(inode))
ext4_handle_sync(handle);
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
if (!(mask & EXT4_FL_USER_MODIFIABLE))
continue;
if (mask & flags)
ext4_set_inode_flag(inode, i);
else
ext4_clear_inode_flag(inode, i);
}
ext4_set_inode_flags(inode);
inode->i_ctime = ext4_current_time(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext4_journal_stop(handle);
if (err)
goto flags_out;
if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL))
err = ext4_change_inode_journal_flag(inode, jflag);
if (err)
goto flags_out;
if (migrate) {
if (flags & EXT4_EXTENTS_FL)
err = ext4_ext_migrate(inode);
else
err = ext4_ind_migrate(inode);
}
flags_out:
mutex_unlock(&inode->i_mutex);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (ext4_has_metadata_csum(inode->i_sb)) {
ext4_warning(sb, "Setting inode version is not "
"supported with metadata_csum enabled.");
return -ENOTTY;
}
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
mutex_lock(&inode->i_mutex);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = ext4_current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
mutex_unlock(&inode->i_mutex);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_extend_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_extend_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
me.moved_len = 0;
donor = fdget(me.donor_fd);
if (!donor.file)
return -EBADF;
if (!(donor.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
err = -EOPNOTSUPP;
goto mext_out;
}
err = mnt_want_write_file(filp);
if (err)
goto mext_out;
err = ext4_move_extents(filp, donor.file, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fdput(donor);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input))) {
err = -EFAULT;
goto group_add_out;
}
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_add_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_add_out;
err = ext4_group_add(sb, &input);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, input.group);
group_add_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
mutex_lock(&(inode->i_mutex));
err = ext4_ext_migrate(inode);
mutex_unlock(&(inode->i_mutex));
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_SWAP_BOOT:
{
int err;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
err = mnt_want_write_file(filp);
if (err)
return err;
err = swap_inode_boot_loader(sb, inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
int err = 0, err2 = 0;
ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
if (EXT4_HAS_RO_COMPAT_FEATURE(sb,
EXT4_FEATURE_RO_COMPAT_BIGALLOC)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not (yet) supported with bigalloc");
return -EOPNOTSUPP;
}
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
err = ext4_resize_begin(sb);
if (err)
return err;
err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
resizefs_out:
ext4_resize_end(sb);
return err;
}
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
case EXT4_IOC_PRECACHE_EXTENTS:
return ext4_ext_precache(inode);
case EXT4_IOC_SET_ENCRYPTION_POLICY: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
struct ext4_encryption_policy policy;
int err = 0;
if (copy_from_user(&policy,
(struct ext4_encryption_policy __user *)arg,
sizeof(policy))) {
err = -EFAULT;
goto encryption_policy_out;
}
err = ext4_process_policy(&policy, inode);
encryption_policy_out:
return err;
#else
return -EOPNOTSUPP;
#endif
}
case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
int err, err2;
struct ext4_sb_info *sbi = EXT4_SB(sb);
handle_t *handle;
if (!ext4_sb_has_crypto(sb))
return -EOPNOTSUPP;
if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
err = mnt_want_write_file(filp);
if (err)
return err;
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto pwsalt_err_exit;
}
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
err2 = ext4_journal_stop(handle);
if (err2 && !err)
err = err2;
pwsalt_err_exit:
mnt_drop_write_file(filp);
if (err)
return err;
}
if (copy_to_user((void *) arg, sbi->s_es->s_encrypt_pw_salt,
16))
return -EFAULT;
return 0;
}
case EXT4_IOC_GET_ENCRYPTION_POLICY: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
struct ext4_encryption_policy policy;
int err = 0;
if (!ext4_encrypted_inode(inode))
return -ENOENT;
err = ext4_get_policy(inode, &policy);
if (err)
return err;
if (copy_to_user((void *)arg, &policy, sizeof(policy)))
return -EFAULT;
return 0;
#else
return -EOPNOTSUPP;
#endif
}
default:
return -ENOTTY;
}
}
/**
* ext4_add_groupblocks() -- Add given blocks to an existing group
* @handle: handle to this transaction
* @sb: super block
* @block: start physcial block to add to the block group
* @count: number of blocks to free
*
* This marks the blocks as free in the bitmap. We ask the
* mballoc to reload the buddy after this by setting group
* EXT4_GROUP_INFO_NEED_INIT_BIT flag
*/
void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
ext4_fsblk_t block, unsigned long count)
{
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *gd_bh;
ext4_group_t block_group;
ext4_grpblk_t bit;
unsigned int i;
struct ext4_group_desc *desc;
struct ext4_sb_info *sbi = EXT4_SB(sb);
int err = 0, ret, blk_free_count;
ext4_grpblk_t blocks_freed;
struct ext4_group_info *grp;
ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
grp = ext4_get_group_info(sb, block_group);
/*
* Check to see if we are freeing blocks across a group
* boundary.
*/
if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
goto error_return;
}
bitmap_bh = ext4_read_block_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
desc = ext4_get_group_desc(sb, block_group, &gd_bh);
if (!desc)
goto error_return;
if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
in_range(ext4_inode_bitmap(sb, desc), block, count) ||
in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
in_range(block + count - 1, ext4_inode_table(sb, desc),
sbi->s_itb_per_group)) {
ext4_error(sb, __func__,
"Adding blocks in system zones - "
"Block = %llu, count = %lu",
block, count);
goto error_return;
}
/*
* We are about to add blocks to the bitmap,
* so we need undo access.
*/
BUFFER_TRACE(bitmap_bh, "getting undo access");
err = ext4_journal_get_undo_access(handle, bitmap_bh);
if (err)
goto error_return;
/*
* We are about to modify some metadata. Call the journal APIs
* to unshare ->b_data if a currently-committing transaction is
* using it
*/
BUFFER_TRACE(gd_bh, "get_write_access");
err = ext4_journal_get_write_access(handle, gd_bh);
if (err)
goto error_return;
/*
* make sure we don't allow a parallel init on other groups in the
* same buddy cache
*/
down_write(&grp->alloc_sem);
for (i = 0, blocks_freed = 0; i < count; i++) {
BUFFER_TRACE(bitmap_bh, "clear bit");
if (!ext4_clear_bit_atomic(ext4_group_lock_ptr(sb, block_group),
bit + i, bitmap_bh->b_data)) {
ext4_error(sb, __func__,
"bit already cleared for block %llu",
(ext4_fsblk_t)(block + i));
BUFFER_TRACE(bitmap_bh, "bit already cleared");
} else {
blocks_freed++;
}
}
ext4_lock_group(sb, block_group);
blk_free_count = blocks_freed + ext4_free_blks_count(sb, desc);
ext4_free_blks_set(sb, desc, blk_free_count);
desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
ext4_unlock_group(sb, block_group);
percpu_counter_mod(&sbi->s_freeblocks_counter, blocks_freed);
if (sbi->s_log_groups_per_flex) {
ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
atomic_add(blocks_freed,
&sbi->s_flex_groups[flex_group].free_blocks);
}
/*
* request to reload the buddy with the
* new bitmap information
*/
set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
grp->bb_free += blocks_freed;
up_write(&grp->alloc_sem);
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
err = ext4_handle_dirty_metadata(handle, NULL, bitmap_bh);
/* And the group descriptor block */
BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
ret = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
if (!err)
err = ret;
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, err);
return;
}
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;
}
static int ext4_update_inline_data(handle_t *handle, struct inode *inode,
unsigned int len)
{
int error;
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,
};
/* If the old space is ok, write the data directly. */
if (len <= EXT4_I(inode)->i_inline_size)
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;
BUG_ON(is.s.not_found);
len -= EXT4_MIN_INLINE_DATA_SIZE;
value = kzalloc(len, GFP_NOFS);
if (!value)
goto out;
error = ext4_xattr_ibody_get(inode, i.name_index, i.name,
value, len);
if (error == -ENODATA)
goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
/* Update the xttr entry. */
i.value = value;
i.value_len = len;
error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error)
goto out;
EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
(void *)ext4_raw_inode(&is.iloc));
EXT4_I(inode)->i_inline_size = EXT4_MIN_INLINE_DATA_SIZE +
le32_to_cpu(is.s.here->e_value_size);
ext4_set_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
get_bh(is.iloc.bh);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
out:
kfree(value);
brelse(is.iloc.bh);
return error;
}
static int ext4_create_inline_data(handle_t *handle,
struct inode *inode, unsigned len)
{
int error;
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,
};
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
return error;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
if (len > EXT4_MIN_INLINE_DATA_SIZE) {
value = EXT4_ZERO_XATTR_VALUE;
len -= EXT4_MIN_INLINE_DATA_SIZE;
} else {
value = "";
len = 0;
}
/* Insert the the xttr entry. */
i.value = value;
i.value_len = len;
error = ext4_xattr_ibody_find(inode, &i, &is);
if (error)
goto out;
BUG_ON(!is.s.not_found);
error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error) {
if (error == -ENOSPC)
ext4_clear_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA);
goto out;
}
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
(void *)ext4_raw_inode(&is.iloc));
EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE;
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA);
get_bh(is.iloc.bh);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
out:
brelse(is.iloc.bh);
return error;
}
static int ext4_file_open(struct inode * inode, struct file * filp)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
struct ext4_inode_info *ei = EXT4_I(inode);
struct vfsmount *mnt = filp->f_path.mnt;
struct path path;
char buf[64], *cp;
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!(sb->s_flags & MS_RDONLY))) {
sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
/*
* Sample where the filesystem has been mounted and
* store it in the superblock for sysadmin convenience
* when trying to sort through large numbers of block
* devices or filesystem images.
*/
memset(buf, 0, sizeof(buf));
path.mnt = mnt;
path.dentry = mnt->mnt_root;
cp = d_path(&path, buf, sizeof(buf));
if (!IS_ERR(cp)) {
handle_t *handle;
int err;
handle = ext4_journal_start_sb(sb, 1);
if (IS_ERR(handle))
return PTR_ERR(handle);
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err) {
ext4_journal_stop(handle);
return err;
}
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
ext4_handle_dirty_super(handle, sb);
ext4_journal_stop(handle);
}
}
/*
* Set up the jbd2_inode if we are opening the inode for
* writing and the journal is present
*/
if (sbi->s_journal && !ei->jinode && (filp->f_mode & FMODE_WRITE)) {
struct jbd2_inode *jinode = jbd2_alloc_inode(GFP_KERNEL);
spin_lock(&inode->i_lock);
if (!ei->jinode) {
if (!jinode) {
spin_unlock(&inode->i_lock);
return -ENOMEM;
}
ei->jinode = jinode;
jbd2_journal_init_jbd_inode(ei->jinode, inode);
jinode = NULL;
}
spin_unlock(&inode->i_lock);
if (unlikely(jinode != NULL))
jbd2_free_inode(jinode);
}
return dquot_file_open(inode, filp);
}
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
struct super_block *sb = inode->i_sb;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned int flags;
ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case FS_IOC_GETFSMAP:
return ext4_ioc_getfsmap(sb, (void __user *)arg);
case EXT4_IOC_GETFLAGS:
flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT4_IOC_SETFLAGS: {
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
if (get_user(flags, (int __user *) arg))
return -EFAULT;
if (flags & ~EXT4_FL_USER_VISIBLE)
return -EOPNOTSUPP;
/*
* chattr(1) grabs flags via GETFLAGS, modifies the result and
* passes that to SETFLAGS. So we cannot easily make SETFLAGS
* more restrictive than just silently masking off visible but
* not settable flags as we always did.
*/
flags &= EXT4_FL_USER_MODIFIABLE;
if (ext4_mask_flags(inode->i_mode, flags) != flags)
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
inode_lock(inode);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GETVERSION:
case EXT4_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT4_IOC_SETVERSION:
case EXT4_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext4_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
if (ext4_has_metadata_csum(inode->i_sb)) {
ext4_warning(sb, "Setting inode version is not "
"supported with metadata_csum enabled.");
return -ENOTTY;
}
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
inode_lock(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto unlock_out;
}
err = ext4_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = current_time(inode);
inode->i_generation = generation;
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
ext4_journal_stop(handle);
unlock_out:
inode_unlock(inode);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_GROUP_EXTEND: {
ext4_fsblk_t n_blocks_count;
int err, err2=0;
err = ext4_resize_begin(sb);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online resizing not supported with bigalloc");
err = -EOPNOTSUPP;
goto group_extend_out;
}
err = mnt_want_write_file(filp);
if (err)
goto group_extend_out;
err = ext4_group_extend(sb, EXT4_SB(sb)->s_es, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
group_extend_out:
ext4_resize_end(sb);
return err;
}
case EXT4_IOC_MOVE_EXT: {
struct move_extent me;
struct fd donor;
int err;
if (!(filp->f_mode & FMODE_READ) ||
!(filp->f_mode & FMODE_WRITE))
return -EBADF;
if (copy_from_user(&me,
(struct move_extent __user *)arg, sizeof(me)))
return -EFAULT;
me.moved_len = 0;
donor = fdget(me.donor_fd);
if (!donor.file)
return -EBADF;
if (!(donor.file->f_mode & FMODE_WRITE)) {
err = -EBADF;
goto mext_out;
}
if (ext4_has_feature_bigalloc(sb)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with bigalloc");
err = -EOPNOTSUPP;
goto mext_out;
} else if (IS_DAX(inode)) {
ext4_msg(sb, KERN_ERR,
"Online defrag not supported with DAX");
err = -EOPNOTSUPP;
goto mext_out;
}
err = mnt_want_write_file(filp);
if (err)
goto mext_out;
err = ext4_move_extents(filp, donor.file, me.orig_start,
me.donor_start, me.len, &me.moved_len);
mnt_drop_write_file(filp);
if (copy_to_user((struct move_extent __user *)arg,
&me, sizeof(me)))
err = -EFAULT;
mext_out:
fdput(donor);
return err;
}
case EXT4_IOC_GROUP_ADD: {
struct ext4_new_group_data input;
if (copy_from_user(&input, (struct ext4_new_group_input __user *)arg,
sizeof(input)))
return -EFAULT;
return ext4_ioctl_group_add(filp, &input);
}
case EXT4_IOC_MIGRATE:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
/*
* inode_mutex prevent write and truncate on the file.
* Read still goes through. We take i_data_sem in
* ext4_ext_swap_inode_data before we switch the
* inode format to prevent read.
*/
inode_lock((inode));
err = ext4_ext_migrate(inode);
inode_unlock((inode));
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_ALLOC_DA_BLKS:
{
int err;
if (!inode_owner_or_capable(inode))
return -EACCES;
err = mnt_want_write_file(filp);
if (err)
return err;
err = ext4_alloc_da_blocks(inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_SWAP_BOOT:
{
int err;
if (!(filp->f_mode & FMODE_WRITE))
return -EBADF;
err = mnt_want_write_file(filp);
if (err)
return err;
err = swap_inode_boot_loader(sb, inode);
mnt_drop_write_file(filp);
return err;
}
case EXT4_IOC_RESIZE_FS: {
ext4_fsblk_t n_blocks_count;
int err = 0, err2 = 0;
ext4_group_t o_group = EXT4_SB(sb)->s_groups_count;
if (copy_from_user(&n_blocks_count, (__u64 __user *)arg,
sizeof(__u64))) {
return -EFAULT;
}
err = ext4_resize_begin(sb);
if (err)
return err;
err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
err = ext4_resize_fs(sb, n_blocks_count);
if (EXT4_SB(sb)->s_journal) {
jbd2_journal_lock_updates(EXT4_SB(sb)->s_journal);
err2 = jbd2_journal_flush(EXT4_SB(sb)->s_journal);
jbd2_journal_unlock_updates(EXT4_SB(sb)->s_journal);
}
if (err == 0)
err = err2;
mnt_drop_write_file(filp);
if (!err && (o_group > EXT4_SB(sb)->s_groups_count) &&
ext4_has_group_desc_csum(sb) &&
test_opt(sb, INIT_INODE_TABLE))
err = ext4_register_li_request(sb, o_group);
resizefs_out:
ext4_resize_end(sb);
return err;
}
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
range.minlen = max((unsigned int)range.minlen,
q->limits.discard_granularity);
ret = ext4_trim_fs(sb, &range);
if (ret < 0)
return ret;
if (copy_to_user((struct fstrim_range __user *)arg, &range,
sizeof(range)))
return -EFAULT;
return 0;
}
case EXT4_IOC_PRECACHE_EXTENTS:
return ext4_ext_precache(inode);
case EXT4_IOC_SET_ENCRYPTION_POLICY:
if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
return fscrypt_ioctl_set_policy(filp, (const void __user *)arg);
case EXT4_IOC_GET_ENCRYPTION_PWSALT: {
#ifdef CONFIG_EXT4_FS_ENCRYPTION
int err, err2;
struct ext4_sb_info *sbi = EXT4_SB(sb);
handle_t *handle;
if (!ext4_has_feature_encrypt(sb))
return -EOPNOTSUPP;
if (uuid_is_zero(sbi->s_es->s_encrypt_pw_salt)) {
err = mnt_want_write_file(filp);
if (err)
return err;
handle = ext4_journal_start_sb(sb, EXT4_HT_MISC, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto pwsalt_err_exit;
}
err = ext4_journal_get_write_access(handle, sbi->s_sbh);
if (err)
goto pwsalt_err_journal;
generate_random_uuid(sbi->s_es->s_encrypt_pw_salt);
err = ext4_handle_dirty_metadata(handle, NULL,
sbi->s_sbh);
pwsalt_err_journal:
err2 = ext4_journal_stop(handle);
if (err2 && !err)
err = err2;
pwsalt_err_exit:
mnt_drop_write_file(filp);
if (err)
return err;
}
if (copy_to_user((void __user *) arg,
sbi->s_es->s_encrypt_pw_salt, 16))
return -EFAULT;
return 0;
#else
return -EOPNOTSUPP;
#endif
}
case EXT4_IOC_GET_ENCRYPTION_POLICY:
return fscrypt_ioctl_get_policy(filp, (void __user *)arg);
case EXT4_IOC_FSGETXATTR:
{
struct fsxattr fa;
memset(&fa, 0, sizeof(struct fsxattr));
fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
if (ext4_has_feature_project(inode->i_sb)) {
fa.fsx_projid = (__u32)from_kprojid(&init_user_ns,
EXT4_I(inode)->i_projid);
}
if (copy_to_user((struct fsxattr __user *)arg,
&fa, sizeof(fa)))
return -EFAULT;
return 0;
}
case EXT4_IOC_FSSETXATTR:
{
struct fsxattr fa;
int err;
if (copy_from_user(&fa, (struct fsxattr __user *)arg,
sizeof(fa)))
return -EFAULT;
/* Make sure caller has proper permission */
if (!inode_owner_or_capable(inode))
return -EACCES;
if (fa.fsx_xflags & ~EXT4_SUPPORTED_FS_XFLAGS)
return -EOPNOTSUPP;
flags = ext4_xflags_to_iflags(fa.fsx_xflags);
if (ext4_mask_flags(inode->i_mode, flags) != flags)
return -EOPNOTSUPP;
err = mnt_want_write_file(filp);
if (err)
return err;
inode_lock(inode);
flags = (ei->i_flags & ~EXT4_FL_XFLAG_VISIBLE) |
(flags & EXT4_FL_XFLAG_VISIBLE);
err = ext4_ioctl_setflags(inode, flags);
inode_unlock(inode);
mnt_drop_write_file(filp);
if (err)
return err;
err = ext4_ioctl_setproject(filp, fa.fsx_projid);
if (err)
return err;
return 0;
}
case EXT4_IOC_SHUTDOWN:
return ext4_shutdown(sb, arg);
default:
return -ENOTTY;
}
}
/*
* NOTE! When we get the inode, we're the only people
* that have access to it, and as such there are no
* race conditions we have to worry about. The inode
* is not on the hash-lists, and it cannot be reached
* through the filesystem because the directory entry
* has been deleted earlier.
*
* HOWEVER: we must make sure that we get no aliases,
* which means that we have to call "clear_inode()"
* _before_ we mark the inode not in use in the inode
* bitmaps. Otherwise a newly created file might use
* the same inode number (not actually the same pointer
* though), and then we'd have two inodes sharing the
* same inode number and space on the harddisk.
*/
void ext4_free_inode (handle_t *handle, struct inode * inode)
{
struct super_block * sb = inode->i_sb;
int is_directory;
unsigned long ino;
struct buffer_head *bitmap_bh = NULL;
struct buffer_head *bh2;
unsigned long block_group;
unsigned long bit;
struct ext4_group_desc * gdp;
struct ext4_super_block * es;
struct ext4_sb_info *sbi;
int fatal = 0, err;
if (atomic_read(&inode->i_count) > 1) {
printk ("ext4_free_inode: inode has count=%d\n",
atomic_read(&inode->i_count));
return;
}
if (inode->i_nlink) {
printk ("ext4_free_inode: inode has nlink=%d\n",
inode->i_nlink);
return;
}
if (!sb) {
printk("ext4_free_inode: inode on nonexistent device\n");
return;
}
sbi = EXT4_SB(sb);
ino = inode->i_ino;
ext4_debug ("freeing inode %lu\n", ino);
/*
* Note: we must free any quota before locking the superblock,
* as writing the quota to disk may need the lock as well.
*/
DQUOT_INIT(inode);
ext4_xattr_delete_inode(handle, inode);
DQUOT_FREE_INODE(inode);
DQUOT_DROP(inode);
is_directory = S_ISDIR(inode->i_mode);
/* Do this BEFORE marking the inode not in use or returning an error */
clear_inode (inode);
es = EXT4_SB(sb)->s_es;
if (ino < EXT4_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext4_error (sb, "ext4_free_inode",
"reserved or nonexistent inode %lu", ino);
goto error_return;
}
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = read_inode_bitmap(sb, block_group);
if (!bitmap_bh)
goto error_return;
BUFFER_TRACE(bitmap_bh, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bitmap_bh);
if (fatal)
goto error_return;
/* Ok, now we can actually update the inode bitmaps.. */
if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
bit, bitmap_bh->b_data))
ext4_error (sb, "ext4_free_inode",
"bit already cleared for inode %lu", ino);
else {
gdp = ext4_get_group_desc (sb, block_group, &bh2);
BUFFER_TRACE(bh2, "get_write_access");
fatal = ext4_journal_get_write_access(handle, bh2);
if (fatal) goto error_return;
if (gdp) {
spin_lock(sb_bgl_lock(sbi, block_group));
gdp->bg_free_inodes_count = cpu_to_le16(
le16_to_cpu(gdp->bg_free_inodes_count) + 1);
if (is_directory)
gdp->bg_used_dirs_count = cpu_to_le16(
le16_to_cpu(gdp->bg_used_dirs_count) - 1);
spin_unlock(sb_bgl_lock(sbi, block_group));
percpu_counter_inc(&sbi->s_freeinodes_counter);
if (is_directory)
percpu_counter_dec(&sbi->s_dirs_counter);
}
BUFFER_TRACE(bh2, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, bh2);
if (!fatal) fatal = err;
}
BUFFER_TRACE(bitmap_bh, "call ext4_journal_dirty_metadata");
err = ext4_journal_dirty_metadata(handle, bitmap_bh);
if (!fatal)
fatal = err;
sb->s_dirt = 1;
error_return:
brelse(bitmap_bh);
ext4_std_error(sb, fatal);
}
/*
* 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);
}
/*
* 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;
}
/*
* Prepare the write for the inline data.
* If the the data can be written into the inode, we just read
* the page and make it uptodate, and start the journal.
* Otherwise read the page, makes it dirty so that it can be
* handle in writepages(the i_disksize update is left to the
* normal ext4_da_write_end).
*/
int ext4_da_write_inline_data_begin(struct address_space *mapping,
struct inode *inode,
loff_t pos, unsigned len,
unsigned flags,
struct page **pagep,
void **fsdata)
{
int ret, inline_size;
handle_t *handle;
struct page *page;
struct ext4_iloc iloc;
int retries;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
retry_journal:
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
inline_size = ext4_get_max_inline_size(inode);
ret = -ENOSPC;
if (inline_size >= pos + len) {
ret = ext4_prepare_inline_data(handle, inode, pos + len);
if (ret && ret != -ENOSPC)
goto out_journal;
}
/*
* We cannot recurse into the filesystem as the transaction
* is already started.
*/
flags |= AOP_FLAG_NOFS;
if (ret == -ENOSPC) {
ext4_journal_stop(handle);
ret = ext4_da_convert_inline_data_to_extent(mapping,
inode,
flags,
fsdata);
if (ret == -ENOSPC &&
ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry_journal;
goto out;
}
page = grab_cache_page_write_begin(mapping, 0, flags);
if (!page) {
ret = -ENOMEM;
goto out_journal;
}
down_read(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
ret = 0;
goto out_release_page;
}
if (!PageUptodate(page)) {
ret = ext4_read_inline_page(inode, page);
if (ret < 0)
goto out_release_page;
}
ret = ext4_journal_get_write_access(handle, iloc.bh);
if (ret)
goto out_release_page;
up_read(&EXT4_I(inode)->xattr_sem);
*pagep = page;
brelse(iloc.bh);
return 1;
out_release_page:
up_read(&EXT4_I(inode)->xattr_sem);
unlock_page(page);
put_page(page);
out_journal:
ext4_journal_stop(handle);
out:
brelse(iloc.bh);
return ret;
}
/*
* Try to write data in the inode.
* If the inode has inline data, check whether the new write can be
* in the inode also. If not, create the page the handle, move the data
* to the page make it update and let the later codes create extent for it.
*/
int ext4_try_to_write_inline_data(struct address_space *mapping,
struct inode *inode,
loff_t pos, unsigned len,
unsigned flags,
struct page **pagep)
{
int ret;
handle_t *handle;
struct page *page;
struct ext4_iloc iloc;
if (pos + len > ext4_get_max_inline_size(inode))
goto convert;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
/*
* The possible write could happen in the inode,
* so try to reserve the space in inode first.
*/
handle = ext4_journal_start(inode, EXT4_HT_INODE, 1);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
goto out;
}
ret = ext4_prepare_inline_data(handle, inode, pos + len);
if (ret && ret != -ENOSPC)
goto out;
/* We don't have space in inline inode, so convert it to extent. */
if (ret == -ENOSPC) {
ext4_journal_stop(handle);
brelse(iloc.bh);
goto convert;
}
ret = ext4_journal_get_write_access(handle, iloc.bh);
if (ret)
goto out;
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, 0, flags);
if (!page) {
ret = -ENOMEM;
goto out;
}
*pagep = page;
down_read(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
ret = 0;
unlock_page(page);
put_page(page);
goto out_up_read;
}
if (!PageUptodate(page)) {
ret = ext4_read_inline_page(inode, page);
if (ret < 0)
goto out_up_read;
}
ret = 1;
handle = NULL;
out_up_read:
up_read(&EXT4_I(inode)->xattr_sem);
out:
if (handle && (ret != 1))
ext4_journal_stop(handle);
brelse(iloc.bh);
return ret;
convert:
return ext4_convert_inline_data_to_extent(mapping,
inode, flags);
}
