static ssize_t
ext4_file_write(struct kiocb *iocb, const struct iovec *iov,
unsigned long nr_segs, loff_t pos)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_path.dentry->d_inode;
ssize_t ret;
int err;
ret = generic_file_aio_write(iocb, iov, nr_segs, pos);
/*
* Skip flushing if there was an error, or if nothing was written.
*/
if (ret <= 0)
return ret;
/*
* If the inode is IS_SYNC, or is O_SYNC and we are doing data
* journalling then we need to make sure that we force the transaction
* to disk to keep all metadata uptodate synchronously.
*/
if (file->f_flags & O_SYNC) {
/*
* If we are non-data-journaled, then the dirty data has
* already been flushed to backing store by generic_osync_inode,
* and the inode has been flushed too if there have been any
* modifications other than mere timestamp updates.
*
* Open question --- do we care about flushing timestamps too
* if the inode is IS_SYNC?
*/
if (!ext4_should_journal_data(inode))
return ret;
goto force_commit;
}
/*
* So we know that there has been no forced data flush. If the inode
* is marked IS_SYNC, we need to force one ourselves.
*/
if (!IS_SYNC(inode))
return ret;
/*
* Open question #2 --- should we force data to disk here too? If we
* don't, the only impact is that data=writeback filesystems won't
* flush data to disk automatically on IS_SYNC, only metadata (but
* historically, that is what ext2 has done.)
*/
force_commit:
err = ext4_force_commit(inode->i_sb);
if (err)
return err;
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_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)) {
/*
* 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;
}
int ext4_sync_file(struct file *file, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret;
tid_t commit_tid;
bool needs_barrier = false;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file(file, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = flush_completed_IO(inode);
if (ret < 0)
return ret;
if (!journal) {
ret = generic_file_fsync(file, 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 (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
jbd2_log_start_commit(journal, commit_tid);
ret = jbd2_log_wait_commit(journal, commit_tid);
if (needs_barrier)
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
BLKDEV_IFL_WAIT);
return ret;
}
/*
* The ext4 forget function must perform a revoke if we are freeing data
* which has been journaled. Metadata (eg. indirect blocks) must be
* revoked in all cases.
*
* "bh" may be NULL: a metadata block may have been freed from memory
* but there may still be a record of it in the journal, and that record
* still needs to be revoked.
*
* If the handle isn't valid we're not journaling, but we still need to
* call into ext4_journal_revoke() to put the buffer head.
*/
int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
int is_metadata, struct inode *inode,
struct buffer_head *bh, ext4_fsblk_t blocknr)
{
int err;
might_sleep();
trace_ext4_forget(inode, is_metadata, blocknr);
BUFFER_TRACE(bh, "enter");
jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
"data mode %x\n",
bh, is_metadata, inode->i_mode,
test_opt(inode->i_sb, DATA_FLAGS));
/* In the no journal case, we can just do a bforget and return */
if (!ext4_handle_valid(handle)) {
bforget(bh);
return 0;
}
/* Never use the revoke function if we are doing full data
* journaling: there is no need to, and a V1 superblock won't
* support it. Otherwise, only skip the revoke on un-journaled
* data blocks. */
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA ||
(!is_metadata && !ext4_should_journal_data(inode))) {
if (bh) {
BUFFER_TRACE(bh, "call jbd2_journal_forget");
err = jbd2_journal_forget(handle, bh);
if (err)
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
return err;
}
return 0;
}
/*
* data!=journal && (is_metadata || should_journal_data(inode))
*/
BUFFER_TRACE(bh, "call jbd2_journal_revoke");
err = jbd2_journal_revoke(handle, blocknr, bh);
if (err) {
ext4_journal_abort_handle(where, line, __func__,
bh, handle, err);
__ext4_abort(inode->i_sb, where, line,
"error %d when attempting revoke", err);
}
BUFFER_TRACE(bh, "exit");
return err;
}
int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret = 0;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_mark(ext4_sync_file, "dev %s datasync %d ino %ld parent %ld",
inode->i_sb->s_id, datasync, inode->i_ino,
dentry->d_parent->d_inode->i_ino);
/*
* data=writeback:
* The caller's filemap_fdatawrite()/wait will sync the data.
* sync_inode() will sync the metadata
*
* data=ordered:
* The caller's filemap_fdatawrite() will write the data and
* sync_inode() will write the inode if it is dirty. Then the caller's
* filemap_fdatawait() will wait on the pages.
*
* 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)) {
ret = ext4_force_commit(inode->i_sb);
goto out;
}
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
goto out;
/*
* The VFS has written the file data. If the inode is unaltered
* then we need not start a commit.
*/
if (inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC)) {
struct writeback_control wbc = {
.sync_mode = WB_SYNC_ALL,
.nr_to_write = 0, /* sys_fsync did this */
};
ret = sync_inode(inode, &wbc);
if (journal && (journal->j_flags & JBD2_BARRIER))
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
}
out:
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;
}
int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret = 0, err;
tid_t commit_tid;
bool needs_barrier = false;
if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
return -EIO;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file_enter(file, datasync);
if (inode->i_sb->s_flags & MS_RDONLY) {
/* Make sure that we read updated s_mount_flags value */
smp_rmb();
if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
ret = -EROFS;
goto out;
}
if (!journal) {
ret = __generic_file_fsync(file, start, end, datasync);
if (!ret)
ret = ext4_sync_parent(inode);
if (test_opt(inode->i_sb, BARRIER))
goto issue_flush;
goto out;
}
ret = file_write_and_wait_range(file, start, end);
if (ret)
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)) {
ret = ext4_force_commit(inode->i_sb);
goto out;
}
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
ret = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
issue_flush:
err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
if (!ret)
ret = err;
}
out:
trace_ext4_sync_file_exit(inode, ret);
return ret;
}
int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct ext4_inode_info *ei = EXT4_I(inode);
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
int ret, err;
tid_t commit_tid;
bool needs_barrier = false;
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file_enter(file, datasync);
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (ret)
return ret;
if (!mutex_trylock(&inode->i_mutex)) {
ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
trace_ext4_sync_file_exit(inode, ret);
return ret;
}
if (inode->i_sb->s_flags & MS_RDONLY)
goto out;
ret = ext4_flush_unwritten_io(inode);
if (ret < 0)
goto out;
if (!journal) {
ret = __sync_inode(inode, datasync);
if (!ret && !hlist_empty(&inode->i_dentry))
ret = ext4_sync_parent(inode);
goto out;
}
/*
* 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)) {
ret = ext4_force_commit(inode->i_sb);
goto out;
}
commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
ret = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
if (!ret)
ret = err;
}
out:
mutex_unlock(&inode->i_mutex);
trace_ext4_sync_file_exit(inode, ret);
return ret;
}