int ext3_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
struct ext3_inode_info *ei = EXT3_I(inode);
journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
int ret, needs_barrier = 0;
tid_t commit_tid;
trace_ext3_sync_file_enter(file, datasync);
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
if (ret)
goto out;
J_ASSERT(ext3_journal_current_handle() == NULL);
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for a proper transaction
* to commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext3_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 (ext3_should_journal_data(inode)) {
ret = ext3_force_commit(inode->i_sb);
goto out;
}
if (datasync)
commit_tid = atomic_read(&ei->i_datasync_tid);
else
commit_tid = atomic_read(&ei->i_sync_tid);
if (test_opt(inode->i_sb, BARRIER) &&
!journal_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = 1;
log_start_commit(journal, commit_tid);
ret = log_wait_commit(journal, commit_tid);
/*
* In case we didn't commit a transaction, we have to flush
* disk caches manually so that data really is on persistent
* storage
*/
if (needs_barrier)
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
out:
trace_ext3_sync_file_exit(inode, ret);
return ret;
}
static ssize_t
ext3_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_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 (!ext3_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 = ext3_force_commit(inode->i_sb);
if (err)
return err;
return ret;
}
int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
int ret = 0;
J_ASSERT(ext3_journal_current_handle() == 0);
/*
* 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).
* ext3_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 (ext3_should_journal_data(inode)) {
ret = ext3_force_commit(inode->i_sb);
goto out;
}
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
goto flush;
/*
* 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);
goto out;
}
flush:
/*
* In case we didn't commit a transaction, we have to flush
* disk caches manually so that data really is on persistent
* storage
*/
if (test_opt(inode->i_sb, BARRIER))
blkdev_issue_flush(inode->i_sb->s_bdev, NULL);
out:
return ret;
}
int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
struct ext3_inode_info *ei = EXT3_I(inode);
journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
int ret = 0;
tid_t commit_tid;
if (inode->i_sb->s_flags & MS_RDONLY)
return 0;
J_ASSERT(ext3_journal_current_handle() == NULL);
/*
* data=writeback,ordered:
* The caller's filemap_fdatawrite()/wait will sync the data.
* Metadata is in the journal, we wait for a proper transaction
* to commit here.
*
* data=journal:
* filemap_fdatawrite won't do anything (the buffers are clean).
* ext3_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 (ext3_should_journal_data(inode)) {
ret = ext3_force_commit(inode->i_sb);
goto out;
}
if (datasync)
commit_tid = atomic_read(&ei->i_datasync_tid);
else
commit_tid = atomic_read(&ei->i_sync_tid);
if (log_start_commit(journal, commit_tid)) {
log_wait_commit(journal, commit_tid);
goto out;
}
/*
* In case we didn't commit a transaction, we have to flush
* disk caches manually so that data really is on persistent
* storage
*/
if (test_opt(inode->i_sb, BARRIER))
blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL,
BLKDEV_IFL_WAIT);
out:
return ret;
}
int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync)
{
struct inode *inode = dentry->d_inode;
int ret = 0;
J_ASSERT(ext3_journal_current_handle() == NULL);
/*
* 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).
* ext3_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 (ext3_should_journal_data(inode)) {
ret = ext3_force_commit(inode->i_sb);
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);
}
out:
return ret;
}
/*
* The ext3 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.
*/
int ext3_forget(handle_t *handle, int is_metadata, struct inode *inode,
struct buffer_head *bh, ext3_fsblk_t blocknr)
{
int err;
might_sleep();
trace_ext3_forget(inode, is_metadata, blocknr);
BUFFER_TRACE(bh, "enter");
jbd_debug(4, "forgetting bh %p: is_metadata = %d, mode %o, "
"data mode %lx\n",
bh, is_metadata, inode->i_mode,
test_opt(inode->i_sb, DATA_FLAGS));
/* 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) == EXT3_MOUNT_JOURNAL_DATA ||
(!is_metadata && !ext3_should_journal_data(inode))) {
if (bh) {
BUFFER_TRACE(bh, "call journal_forget");
return ext3_journal_forget(handle, bh);
}
return 0;
}
/*
* data!=journal && (is_metadata || should_journal_data(inode))
*/
BUFFER_TRACE(bh, "call ext3_journal_revoke");
err = ext3_journal_revoke(handle, blocknr, bh);
if (err)
ext3_abort(inode->i_sb, __func__,
"error %d when attempting revoke", err);
BUFFER_TRACE(bh, "exit");
return err;
}
/*
* Called at inode eviction from icache
*/
void ext3_evict_inode (struct inode *inode)
{
struct ext3_inode_info *ei = EXT3_I(inode);
struct ext3_block_alloc_info *rsv;
handle_t *handle;
int want_delete = 0;
trace_ext3_evict_inode(inode);
if (!inode->i_nlink && !is_bad_inode(inode)) {
dquot_initialize(inode);
want_delete = 1;
}
/*
* When journalling data dirty buffers are tracked only in the journal.
* So although mm thinks everything is clean and ready for reaping the
* inode might still have some pages to write in the running
* transaction or waiting to be checkpointed. Thus calling
* journal_invalidatepage() (via truncate_inode_pages()) to discard
* these buffers can cause data loss. Also even if we did not discard
* these buffers, we would have no way to find them after the inode
* is reaped and thus user could see stale data if he tries to read
* them before the transaction is checkpointed. So be careful and
* force everything to disk here... We use ei->i_datasync_tid to
* store the newest transaction containing inode's data.
*
* Note that directories do not have this problem because they don't
* use page cache.
*
* The s_journal check handles the case when ext3_get_journal() fails
* and puts the journal inode.
*/
if (inode->i_nlink && ext3_should_journal_data(inode) &&
EXT3_SB(inode->i_sb)->s_journal &&
(S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
inode->i_ino != EXT3_JOURNAL_INO) {
tid_t commit_tid = atomic_read(&ei->i_datasync_tid);
journal_t *journal = EXT3_SB(inode->i_sb)->s_journal;
log_start_commit(journal, commit_tid);
log_wait_commit(journal, commit_tid);
filemap_write_and_wait(&inode->i_data);
}
truncate_inode_pages(&inode->i_data, 0);
ext3_discard_reservation(inode);
rsv = ei->i_block_alloc_info;
ei->i_block_alloc_info = NULL;
if (unlikely(rsv))
kfree(rsv);
if (!want_delete)
goto no_delete;
handle = start_transaction(inode);
if (IS_ERR(handle)) {
/*
* If we're going to skip the normal cleanup, we still need to
* make sure that the in-core orphan linked list is properly
* cleaned up.
*/
ext3_orphan_del(NULL, inode);
goto no_delete;
}
if (IS_SYNC(inode))
handle->h_sync = 1;
inode->i_size = 0;
if (inode->i_blocks)
ext3_truncate(inode);
/*
* Kill off the orphan record created when the inode lost the last
* link. Note that ext3_orphan_del() has to be able to cope with the
* deletion of a non-existent orphan - ext3_truncate() could
* have removed the record.
*/
ext3_orphan_del(handle, inode);
ei->i_dtime = get_seconds();
/*
* One subtle ordering requirement: if anything has gone wrong
* (transaction abort, IO errors, whatever), then we can still
* do these next steps (the fs will already have been marked as
* having errors), but we can't free the inode if the mark_dirty
* fails.
*/
if (ext3_mark_inode_dirty(handle, inode)) {
/* If that failed, just dquot_drop() and be done with that */
dquot_drop(inode);
clear_inode(inode);
} else {
ext3_xattr_delete_inode(handle, inode);
dquot_free_inode(inode);
dquot_drop(inode);
clear_inode(inode);
ext3_free_inode(handle, inode);
}
ext3_journal_stop(handle);
return;
no_delete:
clear_inode(inode);
dquot_drop(inode);
}
