/**
* ext4_get_crypto_ctx() - Gets an encryption context
* @inode: The inode for which we are doing the crypto
*
* Allocates and initializes an encryption context.
*
* Return: An allocated and initialized encryption context on success; error
* value or NULL otherwise.
*/
struct ext4_crypto_ctx *ext4_get_crypto_ctx(struct inode *inode)
{
struct ext4_crypto_ctx *ctx = NULL;
int res = 0;
unsigned long flags;
struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
if (ci == NULL)
return ERR_PTR(-ENOKEY);
/*
* We first try getting the ctx from a free list because in
* the common case the ctx will have an allocated and
* initialized crypto tfm, so it's probably a worthwhile
* optimization. For the bounce page, we first try getting it
* from the kernel allocator because that's just about as fast
* as getting it from a list and because a cache of free pages
* should generally be a "last resort" option for a filesystem
* to be able to do its job.
*/
spin_lock_irqsave(&ext4_crypto_ctx_lock, flags);
ctx = list_first_entry_or_null(&ext4_free_crypto_ctxs,
struct ext4_crypto_ctx, free_list);
if (ctx)
list_del(&ctx->free_list);
spin_unlock_irqrestore(&ext4_crypto_ctx_lock, flags);
if (!ctx) {
ctx = kmem_cache_zalloc(ext4_crypto_ctx_cachep, GFP_NOFS);
if (!ctx) {
res = -ENOMEM;
goto out;
}
ctx->flags |= EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
} else {
ctx->flags &= ~EXT4_CTX_REQUIRES_FREE_ENCRYPT_FL;
}
ctx->flags &= ~EXT4_WRITE_PATH_FL;
out:
if (res) {
if (!IS_ERR_OR_NULL(ctx))
ext4_release_crypto_ctx(ctx);
ctx = ERR_PTR(res);
}
return ctx;
}
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret;
tid_t commit_tid;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, dentry, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_aio_dio_completed_IO(inode);
if (ret < 0)
return ret;
if (!journal)
return simple_fsync(file, dentry, datasync);
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext4_force_commit will write the file data into the journal and
* will wait on that.
* filemap_fdatawait() will encounter a ton of newly-dirtied pages
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext4_should_journal_data(inode))
return ext4_force_commit(inode->i_sb);
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (jbd2_log_start_commit(journal, commit_tid))
jbd2_log_wait_commit(journal, commit_tid);
else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
void ext4_free_io_end(ext4_io_end_t *io)
{
int i;
wait_queue_head_t *wq;
BUG_ON(!io);
if (io->page)
put_page(io->page);
for (i = 0; i < io->num_io_pages; i++)
put_io_page(io->pages[i]);
io->num_io_pages = 0;
wq = to_ioend_wq(io->inode);
if (atomic_dec_and_test(&EXT4_I(io->inode)->i_ioend_count) &&
waitqueue_active(wq))
wake_up_all(wq);
kmem_cache_free(io_end_cachep, io);
}
static int ext4_finish_convert_inline_dir(handle_t *handle,
struct inode *inode,
struct buffer_head *dir_block,
void *buf,
int inline_size)
{
int err, csum_size = 0, header_size = 0;
struct ext4_dir_entry_2 *de;
struct ext4_dir_entry_tail *t;
void *target = dir_block->b_data;
/*
* First create "." and ".." and then copy the dir information
* back to the block.
*/
de = (struct ext4_dir_entry_2 *)target;
de = ext4_init_dot_dotdot(inode, de,
inode->i_sb->s_blocksize, csum_size,
le32_to_cpu(((struct ext4_dir_entry_2 *)buf)->inode), 1);
header_size = (void *)de - target;
memcpy((void *)de, buf + EXT4_INLINE_DOTDOT_SIZE,
inline_size - EXT4_INLINE_DOTDOT_SIZE);
if (ext4_has_metadata_csum(inode->i_sb))
csum_size = sizeof(struct ext4_dir_entry_tail);
inode->i_size = inode->i_sb->s_blocksize;
i_size_write(inode, inode->i_sb->s_blocksize);
EXT4_I(inode)->i_disksize = inode->i_sb->s_blocksize;
ext4_update_final_de(dir_block->b_data,
inline_size - EXT4_INLINE_DOTDOT_SIZE + header_size,
inode->i_sb->s_blocksize - csum_size);
if (csum_size) {
t = EXT4_DIRENT_TAIL(dir_block->b_data,
inode->i_sb->s_blocksize);
initialize_dirent_tail(t, inode->i_sb->s_blocksize);
}
set_buffer_uptodate(dir_block);
err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
if (err)
return err;
set_buffer_verified(dir_block);
return ext4_mark_inode_dirty(handle, inode);
}
/*
* Validate dentries for encrypted directories to make sure we aren't
* potentially caching stale data after a key has been added or
* removed.
*/
static int ext4_d_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *dir = d_inode(dentry->d_parent);
struct ext4_crypt_info *ci = EXT4_I(dir)->i_crypt_info;
int dir_has_key, cached_with_key;
if (!ext4_encrypted_inode(dir))
return 0;
if (ci && ci->ci_keyring_key &&
(ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
(1 << KEY_FLAG_REVOKED) |
(1 << KEY_FLAG_DEAD))))
ci = NULL;
/* this should eventually be an flag in d_flags */
cached_with_key = dentry->d_fsdata != NULL;
dir_has_key = (ci != NULL);
/*
* If the dentry was cached without the key, and it is a
* negative dentry, it might be a valid name. We can't check
* if the key has since been made available due to locking
* reasons, so we fail the validation so ext4_lookup() can do
* this check.
*
* We also fail the validation if the dentry was created with
* the key present, but we no longer have the key, or vice versa.
*/
if ((!cached_with_key && d_is_negative(dentry)) ||
(!cached_with_key && dir_has_key) ||
(cached_with_key && !dir_has_key)) {
#if 0 /* Revalidation debug */
char buf[80];
char *cp = simple_dname(dentry, buf, sizeof(buf));
if (IS_ERR(cp))
cp = (char *) "???";
pr_err("revalidate: %s %p %d %d %d\n", cp, dentry->d_fsdata,
cached_with_key, d_is_negative(dentry),
dir_has_key);
#endif
return 0;
}
return 1;
}
static void ext4_release_io_end(ext4_io_end_t *io_end)
{
struct bio *bio, *next_bio;
BUG_ON(!list_empty(&io_end->list));
BUG_ON(io_end->flag & EXT4_IO_END_UNWRITTEN);
WARN_ON(io_end->handle);
if (atomic_dec_and_test(&EXT4_I(io_end->inode)->i_ioend_count))
wake_up_all(ext4_ioend_wq(io_end->inode));
for (bio = io_end->bio; bio; bio = next_bio) {
next_bio = bio->bi_private;
ext4_finish_bio(bio);
bio_put(bio);
}
kmem_cache_free(io_end_cachep, io_end);
}
static void ext4_es_print_tree(struct inode *inode)
{
struct ext4_es_tree *tree;
struct rb_node *node;
printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino);
tree = &EXT4_I(inode)->i_es_tree;
node = rb_first(&tree->root);
while (node) {
struct extent_status *es;
es = rb_entry(node, struct extent_status, rb_node);
printk(KERN_DEBUG " [%u/%u) %llu %x",
es->es_lblk, es->es_len,
ext4_es_pblock(es), ext4_es_status(es));
node = rb_next(node);
}
printk(KERN_DEBUG "\n");
}
static unsigned long ext4_inode_by_name(struct inode *inode, struct qstr *unit)
{
struct super_block *sb = inode->i_sb;
struct ext4_sb_info *e4_sbi;
struct ext4_inode_info *e4_ini = EXT4_I(inode);
struct ext4_dir_entry_2 *e4_de;
struct ext4_inode *parent = e4_ini->i_e4in;
char buff[inode->i_sb->s_blocksize];
size_t len = 0;
int blocks, i;
size_t block_size;
e4_sbi = sb->s_fs_info;
block_size = 1024 << e4_sbi->e4_sb.s_log_block_size;
blocks = (parent->i_size_lo + block_size - 1) / block_size;
__le32 block_indexs[blocks];
ext4_get_blknums(inode, 0, block_indexs, blocks);
for (i = 0; i < blocks; i++) {
__ext4_read_block(sb, buff, block_indexs[i]);
e4_de = (struct ext4_dir_entry_2 *)buff;
while (e4_de->rec_len > 0 && len < parent->i_size_lo && len < (i + 1) * block_size) {
e4_de->name[e4_de->name_len] = '\0';
DPRINT("%s: inode = %d, e4_de size = %d, name size = %d, block = %d\n",
e4_de->name, e4_de->inode, e4_de->rec_len, e4_de->name_len, i);
if (unit->len == e4_de->name_len && \
!strncmp(e4_de->name, unit->name, e4_de->name_len))
return e4_de->inode;
e4_de = (struct ext4_dir_entry_2 *)((char *)e4_de + e4_de->rec_len);
len += e4_de->rec_len;
}
}
GEN_DBG("\"%s\" not found!\n", unit->name);
return 0;
}
/*
* Free the extent meta data blocks only
*/
static int free_ext_block(handle_t *handle, struct inode *inode)
{
int i, retval = 0;
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_extent_header *eh = (struct ext4_extent_header *)ei->i_data;
struct ext4_extent_idx *ix;
if (eh->eh_depth == 0)
/*
* No extra blocks allocated for extent meta data
*/
return 0;
ix = EXT_FIRST_INDEX(eh);
for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ix++) {
retval = free_ext_idx(handle, inode, ix);
if (retval)
return retval;
}
return retval;
}
/*
* work on completed aio dio IO, to convert unwritten extents to extents
*/
static void ext4_end_io_work(struct work_struct *work)
{
ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
struct inode *inode = io->inode;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned long flags;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (io->flag & EXT4_IO_END_IN_FSYNC)
goto requeue;
if (list_empty(&io->list)) {
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
goto free;
}
if (!mutex_trylock(&inode->i_mutex)) {
bool was_queued;
requeue:
was_queued = !!(io->flag & EXT4_IO_END_QUEUED);
io->flag |= EXT4_IO_END_QUEUED;
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/*
* Requeue the work instead of waiting so that the work
* items queued after this can be processed.
*/
queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
/*
* To prevent the ext4-dio-unwritten thread from keeping
* requeueing end_io requests and occupying cpu for too long,
* yield the cpu if it sees an end_io request that has already
* been requeued.
*/
if (was_queued)
yield();
return;
}
list_del_init(&io->list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
(void) ext4_end_io_nolock(io);
mutex_unlock(&inode->i_mutex);
free:
ext4_free_io_end(io);
}
/*
* check a range of space and convert unwritten extents to written.
*/
int ext4_end_io_nolock(ext4_io_end_t *io)
{
struct inode *inode = io->inode;
loff_t offset = io->offset;
ssize_t size = io->size;
wait_queue_head_t *wq;
int ret = 0;
ext4_debug("ext4_end_io_nolock: io 0x%p from inode %lu,list->next 0x%p,"
"list->prev 0x%p\n",
io, inode->i_ino, io->list.next, io->list.prev);
if (list_empty(&io->list))
return ret;
if (!(io->flag & EXT4_IO_END_UNWRITTEN))
return ret;
ret = ext4_convert_unwritten_extents(inode, offset, size);
if (ret < 0) {
printk(KERN_EMERG "%s: failed to convert unwritten "
"extents to written extents, error is %d "
"io is still on inode %lu aio dio list\n",
__func__, ret, inode->i_ino);
return ret;
}
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
/* clear the DIO AIO unwritten flag */
if (io->flag & EXT4_IO_END_UNWRITTEN) {
io->flag &= ~EXT4_IO_END_UNWRITTEN;
/* Wake up anyone waiting on unwritten extent conversion */
wq = ext4_ioend_wq(io->inode);
if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten) &&
waitqueue_active(wq)) {
wake_up_all(wq);
}
}
return ret;
}
long ext4_set_gps_location(struct inode *inode)
{
struct gps_location loc;
struct ext4_inode_info *iinfo = EXT4_I(inode);
long ts;
if (!test_opt(inode->i_sb, GPS_AWARE_INODE))
return -ENODEV;
kget_gps_location(&loc, &ts);
ts = CURRENT_TIME_SEC.tv_sec - ts;
write_lock(&iinfo->i_gps_lock);
memcpy(&iinfo->i_latitude, &loc.latitude, sizeof(long long));
memcpy(&iinfo->i_longitude, &loc.longitude, sizeof(long long));
memcpy(&iinfo->i_accuracy, &loc.accuracy, sizeof(long));
memcpy(&iinfo->i_coord_age, &ts, sizeof(long));
write_unlock(&iinfo->i_gps_lock);
return 0;
}
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)) {
strlcpy(sbi->s_es->s_last_mounted, cp,
sizeof(sbi->s_es->s_last_mounted));
ext4_mark_super_dirty(sb);
}
}
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);
}
/*
* work on completed aio dio IO, to convert unwritten extents to extents
*/
static void ext4_end_io_work(struct work_struct *work)
{
ext4_io_end_t *io = container_of(work, ext4_io_end_t, work);
struct inode *inode = io->inode;
struct ext4_inode_info *ei = EXT4_I(inode);
unsigned long flags;
int ret;
mutex_lock(&inode->i_mutex);
ret = ext4_end_io_nolock(io);
if (ret < 0) {
mutex_unlock(&inode->i_mutex);
return;
}
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
if (!list_empty(&io->list))
list_del_init(&io->list);
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
mutex_unlock(&inode->i_mutex);
ext4_free_io_end(io);
}
/*
* Try to create the inline data for the new dir.
* If it succeeds, return 0, otherwise return the error.
* In case of ENOSPC, the caller should create the normal disk layout dir.
*/
int ext4_try_create_inline_dir(handle_t *handle, struct inode *parent,
struct inode *inode)
{
int ret, inline_size = EXT4_MIN_INLINE_DATA_SIZE;
struct ext4_iloc iloc;
struct ext4_dir_entry_2 *de;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
ret = ext4_prepare_inline_data(handle, inode, inline_size);
if (ret)
goto out;
de = (struct ext4_dir_entry_2 *)ext4_raw_inode(&iloc)->i_block;
ext4_init_dot_dotdot(parent, inode, de, inline_size);
inode->i_size = EXT4_I(inode)->i_disksize = inline_size;
out:
brelse(iloc.bh);
return ret;
}
static int ext4_ioctl_check_project(struct inode *inode, struct fsxattr *fa)
{
/*
* Project Quota ID state is only allowed to change from within the init
* namespace. Enforce that restriction only if we are trying to change
* the quota ID state. Everything else is allowed in user namespaces.
*/
if (current_user_ns() == &init_user_ns)
return 0;
if (__kprojid_val(EXT4_I(inode)->i_projid) != fa->fsx_projid)
return -EINVAL;
if (ext4_test_inode_flag(inode, EXT4_INODE_PROJINHERIT)) {
if (!(fa->fsx_xflags & FS_XFLAG_PROJINHERIT))
return -EINVAL;
} else {
if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
return -EINVAL;
}
return 0;
}
static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
unsigned int len)
{
int ret, size, no_expand;
struct ext4_inode_info *ei = EXT4_I(inode);
if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
return -ENOSPC;
size = ext4_get_max_inline_size(inode);
if (size < len)
return -ENOSPC;
ext4_write_lock_xattr(inode, &no_expand);
if (ei->i_inline_off)
ret = ext4_update_inline_data(handle, inode, len);
else
ret = ext4_create_inline_data(handle, inode, len);
ext4_write_unlock_xattr(inode, &no_expand);
return ret;
}
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret;
tid_t commit_tid;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, dentry, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_completed_IO(inode);
if (ret < 0)
return ret;
if (!journal) {
ret = simple_fsync(file, dentry, datasync);
if (!ret && !list_empty(&inode->i_dentry))
ext4_sync_parent(inode);
return ret;
}
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for proper transaction to
* commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext4_force_commit will write the file data into the journal and
* will wait on that.
* filemap_fdatawait() will encounter a ton of newly-dirtied pages
* (they were dirtied by commit). But that's OK - the blocks are
* safe in-journal, which is all fsync() needs to ensure.
*/
if (ext4_should_journal_data(inode))
return ext4_force_commit(inode->i_sb);
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (jbd2_log_start_commit(journal, commit_tid)) {
/*
* When the journal is on a different device than the
* fs data disk, we need to issue the barrier in
* writeback mode. (In ordered mode, the jbd2 layer
* will take care of issuing the barrier. In
* data=journal, all of the data blocks are written to
* the journal device.)
*/
if (ext4_should_writeback_data(inode) &&
(journal->j_fs_dev != journal->j_dev) &&
(journal->j_flags & JBD2_BARRIER))
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
ret = jbd2_log_wait_commit(journal, commit_tid);
} else if (journal->j_flags & JBD2_BARRIER)
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
return ret;
}
void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
{
handle_t *handle;
int inline_size, value_len, needed_blocks;
size_t i_size;
void *value = NULL;
struct ext4_xattr_ibody_find is = {
.s = { .not_found = -ENODATA, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
};
needed_blocks = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
if (IS_ERR(handle))
return;
down_write(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
*has_inline = 0;
ext4_journal_stop(handle);
return;
}
if (ext4_orphan_add(handle, inode))
goto out;
if (ext4_get_inode_loc(inode, &is.iloc))
goto out;
down_write(&EXT4_I(inode)->i_data_sem);
i_size = inode->i_size;
inline_size = ext4_get_inline_size(inode);
EXT4_I(inode)->i_disksize = i_size;
if (i_size < inline_size) {
/* Clear the content in the xattr space. */
if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
if (ext4_xattr_ibody_find(inode, &i, &is))
goto out_error;
BUG_ON(is.s.not_found);
value_len = le32_to_cpu(is.s.here->e_value_size);
value = kmalloc(value_len, GFP_NOFS);
if (!value)
goto out_error;
if (ext4_xattr_ibody_get(inode, i.name_index, i.name,
value, value_len))
goto out_error;
i.value = value;
i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is))
goto out_error;
}
/* Clear the content within i_blocks. */
if (i_size < EXT4_MIN_INLINE_DATA_SIZE) {
void *p = (void *) ext4_raw_inode(&is.iloc)->i_block;
memset(p + i_size, 0,
EXT4_MIN_INLINE_DATA_SIZE - i_size);
}
EXT4_I(inode)->i_inline_size = i_size <
EXT4_MIN_INLINE_DATA_SIZE ?
EXT4_MIN_INLINE_DATA_SIZE : i_size;
}
out_error:
up_write(&EXT4_I(inode)->i_data_sem);
out:
brelse(is.iloc.bh);
up_write(&EXT4_I(inode)->xattr_sem);
kfree(value);
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
ext4_mark_inode_dirty(handle, inode);
if (IS_SYNC(inode))
ext4_handle_sync(handle);
ext4_journal_stop(handle);
return;
}
/*
* Try to 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;
}
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);
page_cache_release(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)
ext4_journal_stop(handle);
brelse(iloc.bh);
return ret;
convert:
return ext4_convert_inline_data_to_extent(mapping,
inode, flags);
}
/*
* 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) {
ret = ext4_da_convert_inline_data_to_extent(mapping,
inode,
flags,
fsdata);
ext4_journal_stop(handle);
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;
}
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);
page_cache_release(page);
out_journal:
ext4_journal_stop(handle);
out:
brelse(iloc.bh);
return ret;
}
static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
struct inode *inode,
unsigned flags)
{
int ret, needed_blocks;
handle_t *handle = NULL;
int retries = 0, sem_held = 0;
struct page *page = NULL;
unsigned from, to;
struct ext4_iloc iloc;
if (!ext4_has_inline_data(inode)) {
/*
* clear the flag so that no new write
* will trap here again.
*/
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
return 0;
}
needed_blocks = ext4_writepage_trans_blocks(inode);
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
retry:
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
handle = NULL;
goto out;
}
/* We cannot recurse into the filesystem as the transaction is already
* started */
flags |= AOP_FLAG_NOFS;
page = grab_cache_page_write_begin(mapping, 0, flags);
if (!page) {
ret = -ENOMEM;
goto out;
}
down_write(&EXT4_I(inode)->xattr_sem);
sem_held = 1;
/* If some one has already done this for us, just exit. */
if (!ext4_has_inline_data(inode)) {
ret = 0;
goto out;
}
from = 0;
to = ext4_get_inline_size(inode);
if (!PageUptodate(page)) {
ret = ext4_read_inline_page(inode, page);
if (ret < 0)
goto out;
}
ret = ext4_destroy_inline_data_nolock(handle, inode);
if (ret)
goto out;
if (ext4_should_dioread_nolock(inode)) {
ret = __block_write_begin(page, from, to,
ext4_get_block_unwritten);
} else
ret = __block_write_begin(page, from, to, ext4_get_block);
if (!ret && ext4_should_journal_data(inode)) {
ret = ext4_walk_page_buffers(handle, page_buffers(page),
from, to, NULL,
do_journal_get_write_access);
}
if (ret) {
unlock_page(page);
page_cache_release(page);
page = NULL;
ext4_orphan_add(handle, inode);
up_write(&EXT4_I(inode)->xattr_sem);
sem_held = 0;
ext4_journal_stop(handle);
handle = NULL;
ext4_truncate_failed_write(inode);
/*
* If truncate failed early the inode might
* still be on the orphan list; we need to
* make sure the inode is removed from the
* orphan list in that case.
*/
if (inode->i_nlink)
ext4_orphan_del(NULL, inode);
}
if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
goto retry;
if (page)
block_commit_write(page, from, to);
out:
if (page) {
unlock_page(page);
page_cache_release(page);
}
if (sem_held)
up_write(&EXT4_I(inode)->xattr_sem);
if (handle)
ext4_journal_stop(handle);
brelse(iloc.bh);
return ret;
}
static int ext4_destroy_inline_data_nolock(handle_t *handle,
struct inode *inode)
{
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_xattr_ibody_find is = {
.s = { .not_found = 0, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
.value = NULL,
.value_len = 0,
};
int error;
if (!ei->i_inline_off)
return 0;
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
return error;
error = ext4_xattr_ibody_find(inode, &i, &is);
if (error)
goto out;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error)
goto out;
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
if (ext4_has_feature_extents(inode->i_sb)) {
if (S_ISDIR(inode->i_mode) ||
S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) {
ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_ext_tree_init(handle, inode);
}
}
ext4_clear_inode_flag(inode, EXT4_INODE_INLINE_DATA);
get_bh(is.iloc.bh);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
EXT4_I(inode)->i_inline_off = 0;
EXT4_I(inode)->i_inline_size = 0;
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
out:
brelse(is.iloc.bh);
if (error == -ENODATA)
error = 0;
return error;
}
static int ext4_read_inline_page(struct inode *inode, struct page *page)
{
void *kaddr;
int ret = 0;
size_t len;
struct ext4_iloc iloc;
BUG_ON(!PageLocked(page));
BUG_ON(!ext4_has_inline_data(inode));
BUG_ON(page->index);
if (!EXT4_I(inode)->i_inline_off) {
ext4_warning(inode->i_sb, "inode %lu doesn't have inline data.",
inode->i_ino);
goto out;
}
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
goto out;
len = min_t(size_t, ext4_get_inline_size(inode), i_size_read(inode));
kaddr = kmap_atomic(page);
ret = ext4_read_inline_data(inode, kaddr, len, &iloc);
flush_dcache_page(page);
kunmap_atomic(kaddr);
zero_user_segment(page, len, PAGE_CACHE_SIZE);
SetPageUptodate(page);
brelse(iloc.bh);
out:
return ret;
}
/*
* So this function is called when the volume is mkfsed with
* dir_index disabled. In order to keep f_pos persistent
* after we convert from an inlined dir to a blocked based,
* we just pretend that we are a normal dir and return the
* offset as if '.' and '..' really take place.
*
*/
int ext4_read_inline_dir(struct file *file,
struct dir_context *ctx,
int *has_inline_data)
{
unsigned int offset, parent_ino;
int i;
struct ext4_dir_entry_2 *de;
struct super_block *sb;
struct inode *inode = file_inode(file);
int ret, inline_size = 0;
struct ext4_iloc iloc;
void *dir_buf = NULL;
int dotdot_offset, dotdot_size, extra_offset, extra_size;
ret = ext4_get_inode_loc(inode, &iloc);
if (ret)
return ret;
down_read(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
up_read(&EXT4_I(inode)->xattr_sem);
*has_inline_data = 0;
goto out;
}
inline_size = ext4_get_inline_size(inode);
dir_buf = kmalloc(inline_size, GFP_NOFS);
if (!dir_buf) {
ret = -ENOMEM;
up_read(&EXT4_I(inode)->xattr_sem);
goto out;
}
ret = ext4_read_inline_data(inode, dir_buf, inline_size, &iloc);
up_read(&EXT4_I(inode)->xattr_sem);
if (ret < 0)
goto out;
ret = 0;
sb = inode->i_sb;
parent_ino = le32_to_cpu(((struct ext4_dir_entry_2 *)dir_buf)->inode);
offset = ctx->pos;
/*
* dotdot_offset and dotdot_size is the real offset and
* size for ".." and "." if the dir is block based while
* the real size for them are only EXT4_INLINE_DOTDOT_SIZE.
* So we will use extra_offset and extra_size to indicate them
* during the inline dir iteration.
*/
dotdot_offset = EXT4_DIR_REC_LEN(1);
dotdot_size = dotdot_offset + EXT4_DIR_REC_LEN(2);
extra_offset = dotdot_size - EXT4_INLINE_DOTDOT_SIZE;
extra_size = extra_offset + inline_size;
/*
* If the version has changed since the last call to
* readdir(2), then we might be pointing to an invalid
* dirent right now. Scan from the start of the inline
* dir to make sure.
*/
if (file->f_version != inode->i_version) {
for (i = 0; i < extra_size && i < offset;) {
/*
* "." is with offset 0 and
* ".." is dotdot_offset.
*/
if (!i) {
i = dotdot_offset;
continue;
} else if (i == dotdot_offset) {
i = dotdot_size;
continue;
}
/* for other entry, the real offset in
* the buf has to be tuned accordingly.
*/
de = (struct ext4_dir_entry_2 *)
(dir_buf + i - extra_offset);
/* It's too expensive to do a full
* dirent test each time round this
* loop, but we do have to test at
* least that it is non-zero. A
* failure will be detected in the
* dirent test below. */
if (ext4_rec_len_from_disk(de->rec_len, extra_size)
< EXT4_DIR_REC_LEN(1))
break;
i += ext4_rec_len_from_disk(de->rec_len,
extra_size);
}
offset = i;
ctx->pos = offset;
file->f_version = inode->i_version;
}
while (ctx->pos < extra_size) {
if (ctx->pos == 0) {
if (!dir_emit(ctx, ".", 1, inode->i_ino, DT_DIR))
goto out;
ctx->pos = dotdot_offset;
continue;
}
if (ctx->pos == dotdot_offset) {
if (!dir_emit(ctx, "..", 2, parent_ino, DT_DIR))
goto out;
ctx->pos = dotdot_size;
continue;
}
de = (struct ext4_dir_entry_2 *)
(dir_buf + ctx->pos - extra_offset);
if (ext4_check_dir_entry(inode, file, de, iloc.bh, dir_buf,
extra_size, ctx->pos))
goto out;
if (le32_to_cpu(de->inode)) {
if (!dir_emit(ctx, de->name, de->name_len,
le32_to_cpu(de->inode),
get_dtype(sb, de->file_type)))
goto out;
}
ctx->pos += ext4_rec_len_from_disk(de->rec_len, extra_size);
}
out:
kfree(dir_buf);
brelse(iloc.bh);
return ret;
}
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;
}
}
/**
* ext4_fname_encrypt() -
*
* This function encrypts the input filename, and returns the length of the
* ciphertext. Errors are returned as negative numbers. We trust the caller to
* allocate sufficient memory to oname string.
*/
static int ext4_fname_encrypt(struct inode *inode,
const struct qstr *iname,
struct ext4_str *oname)
{
u32 ciphertext_len;
struct ablkcipher_request *req = NULL;
DECLARE_EXT4_COMPLETION_RESULT(ecr);
struct ext4_crypt_info *ci = EXT4_I(inode)->i_crypt_info;
struct crypto_ablkcipher *tfm = ci->ci_ctfm;
int res = 0;
char iv[EXT4_CRYPTO_BLOCK_SIZE];
struct scatterlist src_sg, dst_sg;
int padding = 4 << (ci->ci_flags & EXT4_POLICY_FLAGS_PAD_MASK);
char *workbuf, buf[32], *alloc_buf = NULL;
unsigned lim = max_name_len(inode);
if (iname->len <= 0 || iname->len > lim)
return -EIO;
ciphertext_len = (iname->len < EXT4_CRYPTO_BLOCK_SIZE) ?
EXT4_CRYPTO_BLOCK_SIZE : iname->len;
ciphertext_len = ext4_fname_crypto_round_up(ciphertext_len, padding);
ciphertext_len = (ciphertext_len > lim)
? lim : ciphertext_len;
if (ciphertext_len <= sizeof(buf)) {
workbuf = buf;
} else {
alloc_buf = kmalloc(ciphertext_len, GFP_NOFS);
if (!alloc_buf)
return -ENOMEM;
workbuf = alloc_buf;
}
/* Allocate request */
req = ablkcipher_request_alloc(tfm, GFP_NOFS);
if (!req) {
printk_ratelimited(
KERN_ERR "%s: crypto_request_alloc() failed\n", __func__);
kfree(alloc_buf);
return -ENOMEM;
}
ablkcipher_request_set_callback(req,
CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
ext4_dir_crypt_complete, &ecr);
/* Copy the input */
memcpy(workbuf, iname->name, iname->len);
if (iname->len < ciphertext_len)
memset(workbuf + iname->len, 0, ciphertext_len - iname->len);
/* Initialize IV */
memset(iv, 0, EXT4_CRYPTO_BLOCK_SIZE);
/* Create encryption request */
sg_init_one(&src_sg, workbuf, ciphertext_len);
sg_init_one(&dst_sg, oname->name, ciphertext_len);
ablkcipher_request_set_crypt(req, &src_sg, &dst_sg, ciphertext_len, iv);
res = crypto_ablkcipher_encrypt(req);
if (res == -EINPROGRESS || res == -EBUSY) {
BUG_ON(req->base.data != &ecr);
wait_for_completion(&ecr.completion);
res = ecr.res;
}
kfree(alloc_buf);
ablkcipher_request_free(req);
if (res < 0) {
printk_ratelimited(
KERN_ERR "%s: Error (error code %d)\n", __func__, res);
}
oname->len = ciphertext_len;
return res;
}
static void ext4_aiodio_wait(struct inode *inode)
{
wait_queue_head_t *wq = ext4_ioend_wq(inode);
wait_event(*wq, (atomic_read(&EXT4_I(inode)->i_aiodio_unwritten) == 0));
}
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;
}
/**
* 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;
}
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;
}