/*
* Try to make the page cache and handle ready for the inline data case.
* We can call this function in 2 cases:
* 1. The inode is created and the first write exceeds inline size. We can
* clear the inode state safely.
* 2. The inode has inline data, then we need to read the data, make it
* update and dirty so that ext4_da_writepages can handle it. We don't
* need to start the journal since the file's metatdata isn't changed now.
*/
static int ext4_da_convert_inline_data_to_extent(struct address_space *mapping,
struct inode *inode,
unsigned flags,
void **fsdata)
{
int ret = 0, inline_size;
struct page *page;
page = grab_cache_page_write_begin(mapping, 0, flags);
if (!page)
return -ENOMEM;
down_read(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
goto out;
}
inline_size = ext4_get_inline_size(inode);
if (!PageUptodate(page)) {
ret = ext4_read_inline_page(inode, page);
if (ret < 0)
goto out;
}
ret = __block_write_begin(page, 0, inline_size,
ext4_da_get_block_prep);
if (ret) {
up_read(&EXT4_I(inode)->xattr_sem);
unlock_page(page);
page_cache_release(page);
ext4_truncate_failed_write(inode);
return ret;
}
SetPageDirty(page);
SetPageUptodate(page);
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
*fsdata = (void *)CONVERT_INLINE_DATA;
out:
up_read(&EXT4_I(inode)->xattr_sem);
if (page) {
unlock_page(page);
page_cache_release(page);
}
return ret;
}
/*
* If we're not journaling and this is a just-created file, we have to
* sync our parent directory (if it was freshly created) since
* otherwise it will only be written by writeback, leaving a huge
* window during which a crash may lose the file. This may apply for
* the parent directory's parent as well, and so on recursively, if
* they are also freshly created.
*/
static int ext4_sync_parent(struct inode *inode)
{
struct dentry *dentry = NULL;
struct inode *next;
int ret = 0;
if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
return 0;
inode = igrab(inode);
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
dentry = d_find_any_alias(inode);
if (!dentry)
break;
next = igrab(dentry->d_parent->d_inode);
dput(dentry);
if (!next)
break;
iput(inode);
inode = next;
ret = sync_mapping_buffers(inode->i_mapping);
if (ret)
break;
ret = sync_inode_metadata(inode, 1);
if (ret)
break;
}
iput(inode);
return ret;
}
/*
* If we're not journaling and this is a just-created file, we have to
* sync our parent directory (if it was freshly created) since
* otherwise it will only be written by writeback, leaving a huge
* window during which a crash may lose the file. This may apply for
* the parent directory's parent as well, and so on recursively, if
* they are also freshly created.
*/
static int ext4_sync_parent(struct inode *inode)
{
struct writeback_control wbc;
struct dentry *dentry = NULL;
struct inode *next;
int ret = 0;
if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
return 0;
inode = igrab(inode);
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
dentry = d_find_any_alias(inode);
if (!dentry)
break;
next = igrab(dentry->d_parent->d_inode);
dput(dentry);
if (!next)
break;
iput(inode);
inode = next;
ret = sync_mapping_buffers(inode->i_mapping);
if (ret)
break;
memset(&wbc, 0, sizeof(wbc));
wbc.sync_mode = WB_SYNC_ALL;
wbc.nr_to_write = 0; /* only write out the inode */
ret = sync_inode(inode, &wbc);
if (ret)
break;
}
iput(inode);
return ret;
}
int ext4_convert_inline_data(struct inode *inode)
{
int error, needed_blocks, no_expand;
handle_t *handle;
struct ext4_iloc iloc;
if (!ext4_has_inline_data(inode)) {
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
return 0;
}
needed_blocks = ext4_writepage_trans_blocks(inode);
iloc.bh = NULL;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
handle = ext4_journal_start(inode, EXT4_HT_WRITE_PAGE, needed_blocks);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto out_free;
}
ext4_write_lock_xattr(inode, &no_expand);
if (ext4_has_inline_data(inode))
error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
ext4_write_unlock_xattr(inode, &no_expand);
ext4_journal_stop(handle);
out_free:
brelse(iloc.bh);
return error;
}
/*
* If we're not journaling and this is a just-created file, we have to
* sync our parent directory (if it was freshly created) since
* otherwise it will only be written by writeback, leaving a huge
* window during which a crash may lose the file. This may apply for
* the parent directory's parent as well, and so on recursively, if
* they are also freshly created.
*/
static void ext4_sync_parent(struct inode *inode)
{
struct dentry *dentry = NULL;
while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
dentry = list_entry(inode->i_dentry.next,
struct dentry, d_alias);
if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
break;
inode = dentry->d_parent->d_inode;
sync_mapping_buffers(inode->i_mapping);
}
}
/*
* Called when an inode is released. Note that this is different
* from ext4_file_open: open gets called at every open, but release
* gets called only when /all/ the files are closed.
*/
static int ext4_release_file(struct inode *inode, struct file *filp)
{
if (ext4_test_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE)) {
ext4_alloc_da_blocks(inode);
ext4_clear_inode_state(inode, EXT4_STATE_DA_ALLOC_CLOSE);
}
/* if we are the last writer on the inode, drop the block reservation */
if ((filp->f_mode & FMODE_WRITE) &&
(atomic_read(&inode->i_writecount) == 1) &&
!EXT4_I(inode)->i_reserved_data_blocks)
{
down_write(&EXT4_I(inode)->i_data_sem);
ext4_discard_preallocations(inode);
up_write(&EXT4_I(inode)->i_data_sem);
}
if (is_dx(inode) && filp->private_data)
ext4_htree_free_dir_info(filp->private_data);
return 0;
}
int ext4_convert_inline_data(struct inode *inode)
{
int error, needed_blocks;
handle_t *handle;
struct ext4_iloc iloc;
if (!ext4_has_inline_data(inode)) {
ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA);
return 0;
}
needed_blocks = ext4_writepage_trans_blocks(inode);
iloc.bh = NULL;
error = ext4_get_inode_loc(inode, &iloc);
if (error)
return error;
handle = ext4_journal_start(inode, needed_blocks);
if (IS_ERR(handle)) {
error = PTR_ERR(handle);
goto out_free;
}
down_write(&EXT4_I(inode)->xattr_sem);
if (!ext4_has_inline_data(inode)) {
up_write(&EXT4_I(inode)->xattr_sem);
goto out;
}
error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
up_write(&EXT4_I(inode)->xattr_sem);
out:
ext4_journal_stop(handle);
out_free:
brelse(iloc.bh);
return error;
}
/*
* If we're not journaling and this is a just-created file, we have to
* sync our parent directory (if it was freshly created) since
* otherwise it will only be written by writeback, leaving a huge
* window during which a crash may lose the file. This may apply for
* the parent directory's parent as well, and so on recursively, if
* they are also freshly created.
*/
static int ext4_sync_parent(struct inode *inode)
{
struct dentry *dentry = NULL;
struct inode *next;
int ret = 0;
if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
return 0;
inode = igrab(inode);
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
dentry = d_find_any_alias(inode);
if (!dentry)
break;
next = igrab(d_inode(dentry->d_parent));
dput(dentry);
if (!next)
break;
iput(inode);
inode = next;
/*
* The directory inode may have gone through rmdir by now. But
* the inode itself and its blocks are still allocated (we hold
* a reference to the inode so it didn't go through
* ext4_evict_inode()) and so we are safe to flush metadata
* blocks and the inode.
*/
ret = sync_mapping_buffers(inode->i_mapping);
if (ret)
break;
ret = sync_inode_metadata(inode, 1);
if (ret)
break;
}
iput(inode);
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;
}
static int ext4_create_inline_data(handle_t *handle,
struct inode *inode, unsigned len)
{
int error;
void *value = NULL;
struct ext4_xattr_ibody_find is = {
.s = { .not_found = -ENODATA, },
};
struct ext4_xattr_info i = {
.name_index = EXT4_XATTR_INDEX_SYSTEM,
.name = EXT4_XATTR_SYSTEM_DATA,
};
error = ext4_get_inode_loc(inode, &is.iloc);
if (error)
return error;
BUFFER_TRACE(is.iloc.bh, "get_write_access");
error = ext4_journal_get_write_access(handle, is.iloc.bh);
if (error)
goto out;
if (len > EXT4_MIN_INLINE_DATA_SIZE) {
value = EXT4_ZERO_XATTR_VALUE;
len -= EXT4_MIN_INLINE_DATA_SIZE;
} else {
value = "";
len = 0;
}
/* Insert the the xttr entry. */
i.value = value;
i.value_len = len;
error = ext4_xattr_ibody_find(inode, &i, &is);
if (error)
goto out;
BUG_ON(!is.s.not_found);
error = ext4_xattr_ibody_inline_set(handle, inode, &i, &is);
if (error) {
if (error == -ENOSPC)
ext4_clear_inode_state(inode,
EXT4_STATE_MAY_INLINE_DATA);
goto out;
}
memset((void *)ext4_raw_inode(&is.iloc)->i_block,
0, EXT4_MIN_INLINE_DATA_SIZE);
EXT4_I(inode)->i_inline_off = (u16)((void *)is.s.here -
(void *)ext4_raw_inode(&is.iloc));
EXT4_I(inode)->i_inline_size = len + EXT4_MIN_INLINE_DATA_SIZE;
ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
ext4_set_inode_flag(inode, EXT4_INODE_INLINE_DATA);
get_bh(is.iloc.bh);
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
out:
brelse(is.iloc.bh);
return error;
}
static int ext4_ext_swap_inode_data(handle_t *handle, struct inode *inode,
struct inode *tmp_inode)
{
int retval;
__le32 i_data[3];
struct ext4_inode_info *ei = EXT4_I(inode);
struct ext4_inode_info *tmp_ei = EXT4_I(tmp_inode);
/*
* One credit accounted for writing the
* i_data field of the original inode
*/
retval = ext4_journal_extend(handle, 1);
if (retval) {
retval = ext4_journal_restart(handle, 1);
if (retval)
goto err_out;
}
i_data[0] = ei->i_data[EXT4_IND_BLOCK];
i_data[1] = ei->i_data[EXT4_DIND_BLOCK];
i_data[2] = ei->i_data[EXT4_TIND_BLOCK];
down_write(&EXT4_I(inode)->i_data_sem);
/*
* if EXT4_STATE_EXT_MIGRATE is cleared a block allocation
* happened after we started the migrate. We need to
* fail the migrate
*/
if (!ext4_test_inode_state(inode, EXT4_STATE_EXT_MIGRATE)) {
retval = -EAGAIN;
up_write(&EXT4_I(inode)->i_data_sem);
goto err_out;
} else
ext4_clear_inode_state(inode, EXT4_STATE_EXT_MIGRATE);
/*
* We have the extent map build with the tmp inode.
* Now copy the i_data across
*/
ext4_set_inode_flag(inode, EXT4_INODE_EXTENTS);
memcpy(ei->i_data, tmp_ei->i_data, sizeof(ei->i_data));
/*
* Update i_blocks with the new blocks that got
* allocated while adding extents for extent index
* blocks.
*
* While converting to extents we need not
* update the orignal inode i_blocks for extent blocks
* via quota APIs. The quota update happened via tmp_inode already.
*/
spin_lock(&inode->i_lock);
inode->i_blocks += tmp_inode->i_blocks;
spin_unlock(&inode->i_lock);
up_write(&EXT4_I(inode)->i_data_sem);
/*
* We mark the inode dirty after, because we decrement the
* i_blocks when freeing the indirect meta-data blocks
*/
retval = free_ind_block(handle, inode, i_data);
ext4_mark_inode_dirty(handle, inode);
err_out:
return retval;
}