int empty_inline_dir(struct inode *dir, int *has_inline_data)
{
int err, inline_size;
struct ext4_iloc iloc;
void *inline_pos;
unsigned int offset;
struct ext4_dir_entry_2 *de;
int ret = 1;
err = ext4_get_inode_loc(dir, &iloc);
if (err) {
EXT4_ERROR_INODE(dir, "error %d getting inode %lu block",
err, dir->i_ino);
return 1;
}
down_read(&EXT4_I(dir)->xattr_sem);
if (!ext4_has_inline_data(dir)) {
*has_inline_data = 0;
goto out;
}
de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block;
if (!le32_to_cpu(de->inode)) {
ext4_warning(dir->i_sb,
"bad inline directory (dir #%lu) - no `..'",
dir->i_ino);
ret = 1;
goto out;
}
offset = EXT4_INLINE_DOTDOT_SIZE;
while (offset < dir->i_size) {
de = ext4_get_inline_entry(dir, &iloc, offset,
&inline_pos, &inline_size);
if (ext4_check_dir_entry(dir, NULL, de,
iloc.bh, inline_pos,
inline_size, offset)) {
ext4_warning(dir->i_sb,
"bad inline directory (dir #%lu) - "
"inode %u, rec_len %u, name_len %d"
"inline size %d\n",
dir->i_ino, le32_to_cpu(de->inode),
le16_to_cpu(de->rec_len), de->name_len,
inline_size);
ret = 1;
goto out;
}
if (le32_to_cpu(de->inode)) {
ret = 0;
goto out;
}
offset += ext4_rec_len_from_disk(de->rec_len, inline_size);
}
out:
up_read(&EXT4_I(dir)->xattr_sem);
brelse(iloc.bh);
return ret;
}
/* Verify that we are loading a valid orphan from disk */
struct inode *ext4_orphan_get(struct super_block *sb, unsigned long ino)
{
unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
unsigned long block_group;
int bit;
struct buffer_head *bitmap_bh = NULL;
struct inode *inode = NULL;
/* Error cases - e2fsck has already cleaned up for us */
if (ino > max_ino) {
ext4_warning(sb, __FUNCTION__,
"bad orphan ino %lu! e2fsck was run?", ino);
goto out;
}
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) {
ext4_warning(sb, __FUNCTION__,
"inode bitmap error for orphan %lu", ino);
goto out;
}
/* Having the inode bit set should be a 100% indicator that this
* is a valid orphan (no e2fsck run on fs). Orphans also include
* inodes that were being truncated, so we can't check i_nlink==0.
*/
if (!ext4_test_bit(bit, bitmap_bh->b_data) ||
!(inode = iget(sb, ino)) || is_bad_inode(inode) ||
NEXT_ORPHAN(inode) > max_ino) {
ext4_warning(sb, __FUNCTION__,
"bad orphan inode %lu! e2fsck was run?", ino);
printk(KERN_NOTICE "ext4_test_bit(bit=%d, block=%llu) = %d\n",
bit, (unsigned long long)bitmap_bh->b_blocknr,
ext4_test_bit(bit, bitmap_bh->b_data));
printk(KERN_NOTICE "inode=%p\n", inode);
if (inode) {
printk(KERN_NOTICE "is_bad_inode(inode)=%d\n",
is_bad_inode(inode));
printk(KERN_NOTICE "NEXT_ORPHAN(inode)=%u\n",
NEXT_ORPHAN(inode));
printk(KERN_NOTICE "max_ino=%lu\n", max_ino);
}
/* Avoid freeing blocks if we got a bad deleted inode */
if (inode && inode->i_nlink == 0)
inode->i_blocks = 0;
iput(inode);
inode = NULL;
}
out:
brelse(bitmap_bh);
return inode;
}
static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
ext4_fsblk_t mmp_block)
{
struct mmp_struct *mmp;
if (*bh)
clear_buffer_uptodate(*bh);
if (!*bh)
*bh = sb_getblk(sb, mmp_block);
if (!*bh)
return -ENOMEM;
if (*bh) {
get_bh(*bh);
lock_buffer(*bh);
(*bh)->b_end_io = end_buffer_read_sync;
submit_bh(READ_SYNC, *bh);
wait_on_buffer(*bh);
if (!buffer_uptodate(*bh)) {
brelse(*bh);
*bh = NULL;
}
}
if (!*bh) {
ext4_warning(sb, "Error while reading MMP block %llu",
mmp_block);
return -EIO;
}
mmp = (struct mmp_struct *)((*bh)->b_data);
if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC)
return -EINVAL;
return 0;
}
/*
* Read the MMP block. It _must_ be read from disk and hence we clear the
* uptodate flag on the buffer.
*/
static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
ext4_fsblk_t mmp_block)
{
struct mmp_struct *mmp;
int ret;
if (*bh)
clear_buffer_uptodate(*bh);
/* This would be sb_bread(sb, mmp_block), except we need to be sure
* that the MD RAID device cache has been bypassed, and that the read
* is not blocked in the elevator. */
if (!*bh) {
*bh = sb_getblk(sb, mmp_block);
if (!*bh) {
ret = -ENOMEM;
goto warn_exit;
}
}
get_bh(*bh);
lock_buffer(*bh);
(*bh)->b_end_io = end_buffer_read_sync;
submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh);
wait_on_buffer(*bh);
if (!buffer_uptodate(*bh)) {
ret = -EIO;
goto warn_exit;
}
mmp = (struct mmp_struct *)((*bh)->b_data);
if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC) {
ret = -EFSCORRUPTED;
goto warn_exit;
}
if (!ext4_mmp_csum_verify(sb, mmp)) {
ret = -EFSBADCRC;
goto warn_exit;
}
return 0;
warn_exit:
brelse(*bh);
*bh = NULL;
ext4_warning(sb, "Error %d while reading MMP block %llu",
ret, mmp_block);
return ret;
}
/*
* Read the MMP block. It _must_ be read from disk and hence we clear the
* uptodate flag on the buffer.
*/
static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
ext4_fsblk_t mmp_block)
{
struct mmp_struct *mmp;
if (*bh)
clear_buffer_uptodate(*bh);
/* This would be sb_bread(sb, mmp_block), except we need to be sure
* that the MD RAID device cache has been bypassed, and that the read
* is not blocked in the elevator. */
if (!*bh)
*bh = sb_getblk(sb, mmp_block);
if (!*bh)
return -ENOMEM;
if (*bh) {
get_bh(*bh);
lock_buffer(*bh);
(*bh)->b_end_io = end_buffer_read_sync;
#ifdef FEATURE_STORAGE_META_LOG
if( (*bh) && (*bh)->b_bdev && (*bh)->b_bdev->bd_disk)
set_metadata_rw_status((*bh)->b_bdev->bd_disk->first_minor, WAIT_READ_CNT);
#endif
submit_bh(READ_SYNC | REQ_META | REQ_PRIO, *bh);
wait_on_buffer(*bh);
if (!buffer_uptodate(*bh)) {
brelse(*bh);
*bh = NULL;
}
}
if (unlikely(!*bh)) {
ext4_warning(sb, "Error while reading MMP block %llu",
mmp_block);
return -EIO;
}
mmp = (struct mmp_struct *)((*bh)->b_data);
if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC ||
!ext4_mmp_csum_verify(sb, mmp))
return -EINVAL;
return 0;
}
/*
* Read the MMP block. It _must_ be read from disk and hence we clear the
* uptodate flag on the buffer.
*/
static int read_mmp_block(struct super_block *sb, struct buffer_head **bh,
ext4_fsblk_t mmp_block)
{
struct mmp_struct *mmp;
if (*bh)
clear_buffer_uptodate(*bh);
/* This would be sb_bread(sb, mmp_block), except we need to be sure
* that the MD RAID device cache has been bypassed, and that the read
* is not blocked in the elevator. */
if (!*bh)
*bh = sb_getblk(sb, mmp_block);
if (!*bh)
return -ENOMEM;
if (*bh) {
get_bh(*bh);
lock_buffer(*bh);
(*bh)->b_end_io = end_buffer_read_sync;
submit_bh(READ_SYNC, *bh);
wait_on_buffer(*bh);
if (!buffer_uptodate(*bh)) {
brelse(*bh);
*bh = NULL;
}
}
if (unlikely(!*bh)) {
ext4_warning(sb, "Error while reading MMP block %llu",
mmp_block);
return -EIO;
}
mmp = (struct mmp_struct *)((*bh)->b_data);
if (le32_to_cpu(mmp->mmp_magic) != EXT4_MMP_MAGIC ||
!ext4_mmp_csum_verify(sb, mmp))
return -EINVAL;
return 0;
}
/**
* 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;
}
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 FIDTRIM:
case FITRIM:
{
struct request_queue *q = bdev_get_queue(sb->s_bdev);
struct fstrim_range range;
int ret = 0;
int flags = cmd == FIDTRIM ? BLKDEV_DISCARD_SECURE : 0;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (!blk_queue_discard(q))
return -EOPNOTSUPP;
if ((flags & BLKDEV_DISCARD_SECURE) && !blk_queue_secdiscard(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, flags);
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);
default:
return -ENOTTY;
}
}
/*
* Protect the filesystem from being mounted more than once.
*/
int ext4_multi_mount_protect(struct super_block *sb,
ext4_fsblk_t mmp_block)
{
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct buffer_head *bh = NULL;
struct mmp_struct *mmp = NULL;
struct mmpd_data *mmpd_data;
u32 seq;
unsigned int mmp_check_interval = le16_to_cpu(es->s_mmp_update_interval);
unsigned int wait_time = 0;
int retval;
if (mmp_block < le32_to_cpu(es->s_first_data_block) ||
mmp_block >= ext4_blocks_count(es)) {
ext4_warning(sb, "Invalid MMP block in superblock");
goto failed;
}
retval = read_mmp_block(sb, &bh, mmp_block);
if (retval)
goto failed;
mmp = (struct mmp_struct *)(bh->b_data);
if (mmp_check_interval < EXT4_MMP_MIN_CHECK_INTERVAL)
mmp_check_interval = EXT4_MMP_MIN_CHECK_INTERVAL;
/*
* If check_interval in MMP block is larger, use that instead of
* update_interval from the superblock.
*/
if (le16_to_cpu(mmp->mmp_check_interval) > mmp_check_interval)
mmp_check_interval = le16_to_cpu(mmp->mmp_check_interval);
seq = le32_to_cpu(mmp->mmp_seq);
if (seq == EXT4_MMP_SEQ_CLEAN)
goto skip;
if (seq == EXT4_MMP_SEQ_FSCK) {
dump_mmp_msg(sb, mmp, "fsck is running on the filesystem");
goto failed;
}
wait_time = min(mmp_check_interval * 2 + 1,
mmp_check_interval + 60);
/* Print MMP interval if more than 20 secs. */
if (wait_time > EXT4_MMP_MIN_CHECK_INTERVAL * 4)
ext4_warning(sb, "MMP interval %u higher than expected, please"
" wait.\n", wait_time * 2);
if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
ext4_warning(sb, "MMP startup interrupted, failing mount\n");
goto failed;
}
retval = read_mmp_block(sb, &bh, mmp_block);
if (retval)
goto failed;
mmp = (struct mmp_struct *)(bh->b_data);
if (seq != le32_to_cpu(mmp->mmp_seq)) {
dump_mmp_msg(sb, mmp,
"Device is already active on another node.");
goto failed;
}
skip:
/*
* write a new random sequence number.
*/
seq = mmp_new_seq();
mmp->mmp_seq = cpu_to_le32(seq);
retval = write_mmp_block(sb, bh);
if (retval)
goto failed;
/*
* wait for MMP interval and check mmp_seq.
*/
if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
ext4_warning(sb, "MMP startup interrupted, failing mount\n");
goto failed;
}
retval = read_mmp_block(sb, &bh, mmp_block);
if (retval)
goto failed;
mmp = (struct mmp_struct *)(bh->b_data);
if (seq != le32_to_cpu(mmp->mmp_seq)) {
dump_mmp_msg(sb, mmp,
"Device is already active on another node.");
goto failed;
}
mmpd_data = kmalloc(sizeof(struct mmpd_data), GFP_KERNEL);
if (!mmpd_data) {
ext4_warning(sb, "not enough memory for mmpd_data");
goto failed;
}
mmpd_data->sb = sb;
mmpd_data->bh = bh;
/*
* Start a kernel thread to update the MMP block periodically.
*/
EXT4_SB(sb)->s_mmp_tsk = kthread_run(kmmpd, mmpd_data, "kmmpd-%s",
bdevname(bh->b_bdev,
mmp->mmp_bdevname));
if (IS_ERR(EXT4_SB(sb)->s_mmp_tsk)) {
EXT4_SB(sb)->s_mmp_tsk = NULL;
kfree(mmpd_data);
ext4_warning(sb, "Unable to create kmmpd thread for %s.",
sb->s_id);
goto failed;
}
return 0;
failed:
brelse(bh);
return 1;
}
/*
* kmmpd will update the MMP sequence every s_mmp_update_interval seconds
*/
static int kmmpd(void *data)
{
struct super_block *sb = ((struct mmpd_data *) data)->sb;
struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct mmp_struct *mmp;
ext4_fsblk_t mmp_block;
u32 seq = 0;
unsigned long failed_writes = 0;
int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
unsigned mmp_check_interval;
unsigned long last_update_time;
unsigned long diff;
int retval;
mmp_block = le64_to_cpu(es->s_mmp_block);
mmp = (struct mmp_struct *)(bh->b_data);
mmp->mmp_time = cpu_to_le64(get_seconds());
/*
* Start with the higher mmp_check_interval and reduce it if
* the MMP block is being updated on time.
*/
mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
EXT4_MMP_MIN_CHECK_INTERVAL);
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
bdevname(bh->b_bdev, mmp->mmp_bdevname);
memcpy(mmp->mmp_nodename, init_utsname()->nodename,
sizeof(mmp->mmp_nodename));
while (!kthread_should_stop()) {
if (++seq > EXT4_MMP_SEQ_MAX)
seq = 1;
mmp->mmp_seq = cpu_to_le32(seq);
mmp->mmp_time = cpu_to_le64(get_seconds());
last_update_time = jiffies;
retval = write_mmp_block(sb, bh);
/*
* Don't spew too many error messages. Print one every
* (s_mmp_update_interval * 60) seconds.
*/
if (retval) {
if ((failed_writes % 60) == 0)
ext4_error(sb, "Error writing to MMP block");
failed_writes++;
}
if (!(le32_to_cpu(es->s_feature_incompat) &
EXT4_FEATURE_INCOMPAT_MMP)) {
ext4_warning(sb, "kmmpd being stopped since MMP feature"
" has been disabled.");
EXT4_SB(sb)->s_mmp_tsk = NULL;
goto failed;
}
if (sb->s_flags & MS_RDONLY) {
ext4_warning(sb, "kmmpd being stopped since filesystem "
"has been remounted as readonly.");
EXT4_SB(sb)->s_mmp_tsk = NULL;
goto failed;
}
diff = jiffies - last_update_time;
if (diff < mmp_update_interval * HZ)
schedule_timeout_interruptible(mmp_update_interval *
HZ - diff);
/*
* We need to make sure that more than mmp_check_interval
* seconds have not passed since writing. If that has happened
* we need to check if the MMP block is as we left it.
*/
diff = jiffies - last_update_time;
if (diff > mmp_check_interval * HZ) {
struct buffer_head *bh_check = NULL;
struct mmp_struct *mmp_check;
retval = read_mmp_block(sb, &bh_check, mmp_block);
if (retval) {
ext4_error(sb, "error reading MMP data: %d",
retval);
EXT4_SB(sb)->s_mmp_tsk = NULL;
goto failed;
}
mmp_check = (struct mmp_struct *)(bh_check->b_data);
if (mmp->mmp_seq != mmp_check->mmp_seq ||
memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
sizeof(mmp->mmp_nodename))) {
dump_mmp_msg(sb, mmp_check,
"Error while updating MMP info. "
"The filesystem seems to have been"
" multiply mounted.");
ext4_error(sb, "abort");
goto failed;
}
put_bh(bh_check);
}
/*
* Adjust the mmp_check_interval depending on how much time
* it took for the MMP block to be written.
*/
mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ,
EXT4_MMP_MAX_CHECK_INTERVAL),
EXT4_MMP_MIN_CHECK_INTERVAL);
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
}
/*
* Unmount seems to be clean.
*/
mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
mmp->mmp_time = cpu_to_le64(get_seconds());
retval = write_mmp_block(sb, bh);
failed:
kfree(data);
brelse(bh);
return retval;
}
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;
}
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;
}
}
/**
* 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;
}
static int kmmpd(void *data)
{
struct super_block *sb = ((struct mmpd_data *) data)->sb;
struct buffer_head *bh = ((struct mmpd_data *) data)->bh;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
struct mmp_struct *mmp;
ext4_fsblk_t mmp_block;
u32 seq = 0;
unsigned long failed_writes = 0;
int mmp_update_interval = le16_to_cpu(es->s_mmp_update_interval);
unsigned mmp_check_interval;
unsigned long last_update_time;
unsigned long diff;
int retval;
mmp_block = le64_to_cpu(es->s_mmp_block);
mmp = (struct mmp_struct *)(bh->b_data);
mmp->mmp_time = cpu_to_le64(get_seconds());
mmp_check_interval = max(EXT4_MMP_CHECK_MULT * mmp_update_interval,
EXT4_MMP_MIN_CHECK_INTERVAL);
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
bdevname(bh->b_bdev, mmp->mmp_bdevname);
memcpy(mmp->mmp_nodename, init_utsname()->nodename,
sizeof(mmp->mmp_nodename));
while (!kthread_should_stop()) {
if (++seq > EXT4_MMP_SEQ_MAX)
seq = 1;
mmp->mmp_seq = cpu_to_le32(seq);
mmp->mmp_time = cpu_to_le64(get_seconds());
last_update_time = jiffies;
retval = write_mmp_block(bh);
if (retval) {
if ((failed_writes % 60) == 0)
ext4_error(sb, "Error writing to MMP block");
failed_writes++;
}
if (!(le32_to_cpu(es->s_feature_incompat) &
EXT4_FEATURE_INCOMPAT_MMP)) {
ext4_warning(sb, "kmmpd being stopped since MMP feature"
" has been disabled.");
EXT4_SB(sb)->s_mmp_tsk = NULL;
goto failed;
}
if (sb->s_flags & MS_RDONLY) {
ext4_warning(sb, "kmmpd being stopped since filesystem "
"has been remounted as readonly.");
EXT4_SB(sb)->s_mmp_tsk = NULL;
goto failed;
}
diff = jiffies - last_update_time;
if (diff < mmp_update_interval * HZ)
schedule_timeout_interruptible(mmp_update_interval *
HZ - diff);
diff = jiffies - last_update_time;
if (diff > mmp_check_interval * HZ) {
struct buffer_head *bh_check = NULL;
struct mmp_struct *mmp_check;
retval = read_mmp_block(sb, &bh_check, mmp_block);
if (retval) {
ext4_error(sb, "error reading MMP data: %d",
retval);
EXT4_SB(sb)->s_mmp_tsk = NULL;
goto failed;
}
mmp_check = (struct mmp_struct *)(bh_check->b_data);
if (mmp->mmp_seq != mmp_check->mmp_seq ||
memcmp(mmp->mmp_nodename, mmp_check->mmp_nodename,
sizeof(mmp->mmp_nodename))) {
dump_mmp_msg(sb, mmp_check,
"Error while updating MMP info. "
"The filesystem seems to have been"
" multiply mounted.");
ext4_error(sb, "abort");
goto failed;
}
put_bh(bh_check);
}
mmp_check_interval = max(min(EXT4_MMP_CHECK_MULT * diff / HZ,
EXT4_MMP_MAX_CHECK_INTERVAL),
EXT4_MMP_MIN_CHECK_INTERVAL);
mmp->mmp_check_interval = cpu_to_le16(mmp_check_interval);
}
mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
mmp->mmp_time = cpu_to_le64(get_seconds());
retval = write_mmp_block(bh);
failed:
kfree(data);
brelse(bh);
return retval;
}
