long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = filp->f_dentry->d_inode;
struct ext3_inode_info *ei = EXT3_I(inode);
unsigned int flags;
unsigned short rsv_window_size;
ext3_debug ("cmd = %u, arg = %lu\n", cmd, arg);
switch (cmd) {
case EXT3_IOC_GETFLAGS:
ext3_get_inode_flags(ei);
flags = ei->i_flags & EXT3_FL_USER_VISIBLE;
return put_user(flags, (int __user *) arg);
case EXT3_IOC_SETFLAGS: {
handle_t *handle = NULL;
int err;
struct ext3_iloc iloc;
unsigned int oldflags;
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 = ext3_mask_flags(inode->i_mode, flags);
mutex_lock(&inode->i_mutex);
/* Is it quota file? Do not allow user to mess with it */
err = -EPERM;
if (IS_NOQUOTA(inode))
goto flags_out;
oldflags = ei->i_flags;
/* The JOURNAL_DATA flag is modifiable only by root */
jflag = flags & EXT3_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) & (EXT3_APPEND_FL | EXT3_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) & (EXT3_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
handle = ext3_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto flags_out;
}
if (IS_SYNC(inode))
handle->h_sync = 1;
err = ext3_reserve_inode_write(handle, inode, &iloc);
if (err)
goto flags_err;
flags = flags & EXT3_FL_USER_MODIFIABLE;
flags |= oldflags & ~EXT3_FL_USER_MODIFIABLE;
ei->i_flags = flags;
ext3_set_inode_flags(inode);
inode->i_ctime = CURRENT_TIME_SEC;
err = ext3_mark_iloc_dirty(handle, inode, &iloc);
flags_err:
ext3_journal_stop(handle);
if (err)
goto flags_out;
if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL))
err = ext3_change_inode_journal_flag(inode, jflag);
flags_out:
mutex_unlock(&inode->i_mutex);
mnt_drop_write_file(filp);
return err;
}
case EXT3_IOC_GETVERSION:
case EXT3_IOC_GETVERSION_OLD:
return put_user(inode->i_generation, (int __user *) arg);
case EXT3_IOC_SETVERSION:
case EXT3_IOC_SETVERSION_OLD: {
handle_t *handle;
struct ext3_iloc iloc;
__u32 generation;
int err;
if (!inode_owner_or_capable(inode))
return -EPERM;
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(generation, (int __user *) arg)) {
err = -EFAULT;
goto setversion_out;
}
handle = ext3_journal_start(inode, 1);
if (IS_ERR(handle)) {
err = PTR_ERR(handle);
goto setversion_out;
}
err = ext3_reserve_inode_write(handle, inode, &iloc);
if (err == 0) {
inode->i_ctime = CURRENT_TIME_SEC;
inode->i_generation = generation;
err = ext3_mark_iloc_dirty(handle, inode, &iloc);
}
ext3_journal_stop(handle);
setversion_out:
mnt_drop_write_file(filp);
return err;
}
case EXT3_IOC_GETRSVSZ:
if (test_opt(inode->i_sb, RESERVATION)
&& S_ISREG(inode->i_mode)
&& ei->i_block_alloc_info) {
rsv_window_size = ei->i_block_alloc_info->rsv_window_node.rsv_goal_size;
return put_user(rsv_window_size, (int __user *)arg);
}
return -ENOTTY;
case EXT3_IOC_SETRSVSZ: {
int err;
if (!test_opt(inode->i_sb, RESERVATION) ||!S_ISREG(inode->i_mode))
return -ENOTTY;
err = mnt_want_write_file(filp);
if (err)
return err;
if (!inode_owner_or_capable(inode)) {
err = -EACCES;
goto setrsvsz_out;
}
if (get_user(rsv_window_size, (int __user *)arg)) {
err = -EFAULT;
goto setrsvsz_out;
}
if (rsv_window_size > EXT3_MAX_RESERVE_BLOCKS)
rsv_window_size = EXT3_MAX_RESERVE_BLOCKS;
/*
* need to allocate reservation structure for this inode
* before set the window size
*/
mutex_lock(&ei->truncate_mutex);
if (!ei->i_block_alloc_info)
ext3_init_block_alloc_info(inode);
if (ei->i_block_alloc_info){
struct ext3_reserve_window_node *rsv = &ei->i_block_alloc_info->rsv_window_node;
rsv->rsv_goal_size = rsv_window_size;
}
mutex_unlock(&ei->truncate_mutex);
setrsvsz_out:
mnt_drop_write_file(filp);
return err;
}
case EXT3_IOC_GROUP_EXTEND: {
ext3_fsblk_t n_blocks_count;
struct super_block *sb = inode->i_sb;
int err, err2;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
err = mnt_want_write_file(filp);
if (err)
return err;
if (get_user(n_blocks_count, (__u32 __user *)arg)) {
err = -EFAULT;
goto group_extend_out;
}
err = ext3_group_extend(sb, EXT3_SB(sb)->s_es, n_blocks_count);
journal_lock_updates(EXT3_SB(sb)->s_journal);
err2 = journal_flush(EXT3_SB(sb)->s_journal);
journal_unlock_updates(EXT3_SB(sb)->s_journal);
if (err == 0)
err = err2;
group_extend_out:
mnt_drop_write_file(filp);
return err;
}
case EXT3_IOC_GROUP_ADD: {
struct ext3_new_group_data input;
struct super_block *sb = inode->i_sb;
int err, err2;
if (!capable(CAP_SYS_RESOURCE))
return -EPERM;
err = mnt_want_write_file(filp);
if (err)
return err;
if (copy_from_user(&input, (struct ext3_new_group_input __user *)arg,
sizeof(input))) {
err = -EFAULT;
goto group_add_out;
}
err = ext3_group_add(sb, &input);
journal_lock_updates(EXT3_SB(sb)->s_journal);
err2 = journal_flush(EXT3_SB(sb)->s_journal);
journal_unlock_updates(EXT3_SB(sb)->s_journal);
if (err == 0)
err = err2;
group_add_out:
mnt_drop_write_file(filp);
return err;
}
case FITRIM: {
struct super_block *sb = inode->i_sb;
struct fstrim_range range;
int ret = 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (copy_from_user(&range, (struct fstrim_range __user *)arg,
sizeof(range)))
return -EFAULT;
ret = ext3_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;
}
default:
return -ENOTTY;
}
}
/*
* 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 *ext3_new_inode(handle_t *handle, struct inode * dir,
const struct qstr *qstr, 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 ext3_group_desc * gdp = NULL;
struct ext3_super_block * es;
struct ext3_inode_info *ei;
struct ext3_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;
trace_ext3_request_inode(dir, mode);
inode = new_inode(sb);
if (!inode)
return ERR_PTR(-ENOMEM);
ei = EXT3_I(inode);
sbi = EXT3_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 = ext3_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 = ext3_find_next_zero_bit((unsigned long *)
bitmap_bh->b_data, EXT3_INODES_PER_GROUP(sb), ino);
if (ino < EXT3_INODES_PER_GROUP(sb)) {
BUFFER_TRACE(bitmap_bh, "get_write_access");
err = ext3_journal_get_write_access(handle, bitmap_bh);
if (err)
goto fail;
if (!ext3_set_bit_atomic(sb_bgl_lock(sbi, group),
ino, bitmap_bh->b_data)) {
/* we won it */
BUFFER_TRACE(bitmap_bh,
"call ext3_journal_dirty_metadata");
err = ext3_journal_dirty_metadata(handle,
bitmap_bh);
if (err)
goto fail;
goto got;
}
/* we lost it */
journal_release_buffer(handle, bitmap_bh);
if (++ino < EXT3_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 * EXT3_INODES_PER_GROUP(sb) + 1;
if (ino < EXT3_FIRST_INO(sb) || ino > le32_to_cpu(es->s_inodes_count)) {
ext3_error (sb, "ext3_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 = ext3_journal_get_write_access(handle, bh2);
if (err) goto fail;
spin_lock(sb_bgl_lock(sbi, group));
le16_add_cpu(&gdp->bg_free_inodes_count, -1);
if (S_ISDIR(mode)) {
le16_add_cpu(&gdp->bg_used_dirs_count, 1);
}
spin_unlock(sb_bgl_lock(sbi, group));
BUFFER_TRACE(bh2, "call ext3_journal_dirty_metadata");
err = ext3_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);
if (test_opt(sb, GRPID)) {
inode->i_mode = mode;
inode->i_uid = current_fsuid();
inode->i_gid = dir->i_gid;
} else
inode_init_owner(inode, dir, 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 = CURRENT_TIME_SEC;
memset(ei->i_data, 0, sizeof(ei->i_data));
ei->i_dir_start_lookup = 0;
ei->i_disksize = 0;
ei->i_flags =
ext3_mask_flags(mode, EXT3_I(dir)->i_flags & EXT3_FL_INHERITED);
#ifdef EXT3_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;
ext3_set_inode_flags(inode);
if (IS_DIRSYNC(inode))
handle->h_sync = 1;
if (insert_inode_locked(inode) < 0) {
err = -EINVAL;
goto fail_drop;
}
spin_lock(&sbi->s_next_gen_lock);
inode->i_generation = sbi->s_next_generation++;
spin_unlock(&sbi->s_next_gen_lock);
ei->i_state_flags = 0;
ext3_set_inode_state(inode, EXT3_STATE_NEW);
/* See comment in ext3_iget for explanation */
if (ino >= EXT3_FIRST_INO(sb) + 1 &&
EXT3_INODE_SIZE(sb) > EXT3_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize =
sizeof(struct ext3_inode) - EXT3_GOOD_OLD_INODE_SIZE;
} else {
ei->i_extra_isize = 0;
}
ret = inode;
dquot_initialize(inode);
err = dquot_alloc_inode(inode);
if (err)
goto fail_drop;
err = ext3_init_acl(handle, inode, dir);
if (err)
goto fail_free_drop;
err = ext3_init_security(handle, inode, dir, qstr);
if (err)
goto fail_free_drop;
err = ext3_mark_inode_dirty(handle, inode);
if (err) {
ext3_std_error(sb, err);
goto fail_free_drop;
}
ext3_debug("allocating inode %lu\n", inode->i_ino);
trace_ext3_allocate_inode(inode, dir, mode);
goto really_out;
fail:
ext3_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;
unlock_new_inode(inode);
iput(inode);
brelse(bitmap_bh);
return ERR_PTR(err);
}