![Linus Torvalds](/assets/img/avatar_default.png)
* Fix performance problems found in dioread_nolock now that it is the default, caused by transaction leaks. * Clean up fiemap handling in ext4 * Clean up and refactor multiple block allocator (mballoc) code * Fix a problem with mballoc with a smaller file systems running out of blocks because they couldn't properly use blocks that had been reserved by inode preallocation. * Fixed a race in ext4_sync_parent() versus rename() * Simplify the error handling in the extent manipulation code * Make sure all metadata I/O errors are felected to ext4_ext_dirty()'s and ext4_make_inode_dirty()'s callers. * Avoid passing an error pointer to brelse in ext4_xattr_set() * Fix race which could result to freeing an inode on the dirty last in data=journal mode. * Fix refcount handling if ext4_iget() fails * Fix a crash in generic/019 caused by a corrupted extent node -----BEGIN PGP SIGNATURE----- iQEyBAABCAAdFiEEK2m5VNv+CHkogTfJ8vlZVpUNgaMFAl7Ze8kACgkQ8vlZVpUN gaNChAf4xn0ytFSrweI/S2Sp05G/2L/ocZ2TZZk2ZdGeN1E+ABdSIv/zIF9zuFgZ /pY/C+fyEZWt4E3FlNO8gJzoEedkzMCMnUhSIfI+wZbcclyTOSNMJtnrnJKAEtVH HOvGZJmg357jy407RCGhZpJ773nwU2xhBTr5OFxvSf9mt/vzebxIOnw5D7HPlC1V Fgm6Du8q+tRrPsyjv1Yu4pUEVXMJ7qUcvt326AXVM3kCZO1Aa5GrURX0w3J4mzW1 tc1tKmtbLcVVYTo9CwHXhk/edbxrhAydSP2iACand3tK6IJuI6j9x+bBJnxXitnr vsxsfTYMG18+2SxrJ9LwmagqmrRq =HMTs -----END PGP SIGNATURE----- Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 Pull ext4 updates from Ted Ts'o: "A lot of bug fixes and cleanups for ext4, including: - Fix performance problems found in dioread_nolock now that it is the default, caused by transaction leaks. - Clean up fiemap handling in ext4 - Clean up and refactor multiple block allocator (mballoc) code - Fix a problem with mballoc with a smaller file systems running out of blocks because they couldn't properly use blocks that had been reserved by inode preallocation. - Fixed a race in ext4_sync_parent() versus rename() - Simplify the error handling in the extent manipulation code - Make sure all metadata I/O errors are felected to ext4_ext_dirty()'s and ext4_make_inode_dirty()'s callers. - Avoid passing an error pointer to brelse in ext4_xattr_set() - Fix race which could result to freeing an inode on the dirty last in data=journal mode. - Fix refcount handling if ext4_iget() fails - Fix a crash in generic/019 caused by a corrupted extent node" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (58 commits) ext4: avoid unnecessary transaction starts during writeback ext4: don't block for O_DIRECT if IOCB_NOWAIT is set ext4: remove the access_ok() check in ext4_ioctl_get_es_cache fs: remove the access_ok() check in ioctl_fiemap fs: handle FIEMAP_FLAG_SYNC in fiemap_prep fs: move fiemap range validation into the file systems instances iomap: fix the iomap_fiemap prototype fs: move the fiemap definitions out of fs.h fs: mark __generic_block_fiemap static ext4: remove the call to fiemap_check_flags in ext4_fiemap ext4: split _ext4_fiemap ext4: fix fiemap size checks for bitmap files ext4: fix EXT4_MAX_LOGICAL_BLOCK macro add comment for ext4_dir_entry_2 file_type member jbd2: avoid leaking transaction credits when unreserving handle ext4: drop ext4_journal_free_reserved() ext4: mballoc: use lock for checking free blocks while retrying ext4: mballoc: refactor ext4_mb_good_group() ext4: mballoc: introduce pcpu seqcnt for freeing PA to improve ENOSPC handling ext4: mballoc: refactor ext4_mb_discard_preallocations() ...
188 lines
5.2 KiB
C
188 lines
5.2 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* linux/fs/ext4/fsync.c
|
|
*
|
|
* Copyright (C) 1993 Stephen Tweedie (sct@redhat.com)
|
|
* from
|
|
* Copyright (C) 1992 Remy Card (card@masi.ibp.fr)
|
|
* Laboratoire MASI - Institut Blaise Pascal
|
|
* Universite Pierre et Marie Curie (Paris VI)
|
|
* from
|
|
* linux/fs/minix/truncate.c Copyright (C) 1991, 1992 Linus Torvalds
|
|
*
|
|
* ext4fs fsync primitive
|
|
*
|
|
* Big-endian to little-endian byte-swapping/bitmaps by
|
|
* David S. Miller (davem@caip.rutgers.edu), 1995
|
|
*
|
|
* Removed unnecessary code duplication for little endian machines
|
|
* and excessive __inline__s.
|
|
* Andi Kleen, 1997
|
|
*
|
|
* Major simplications and cleanup - we only need to do the metadata, because
|
|
* we can depend on generic_block_fdatasync() to sync the data blocks.
|
|
*/
|
|
|
|
#include <linux/time.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/sched.h>
|
|
#include <linux/writeback.h>
|
|
#include <linux/blkdev.h>
|
|
|
|
#include "ext4.h"
|
|
#include "ext4_jbd2.h"
|
|
|
|
#include <trace/events/ext4.h>
|
|
|
|
/*
|
|
* 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, *next;
|
|
int ret = 0;
|
|
|
|
if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
|
|
return 0;
|
|
dentry = d_find_any_alias(inode);
|
|
if (!dentry)
|
|
return 0;
|
|
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
|
|
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
|
|
|
|
next = dget_parent(dentry);
|
|
dput(dentry);
|
|
dentry = next;
|
|
inode = dentry->d_inode;
|
|
|
|
/*
|
|
* 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 via its dentry), 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;
|
|
}
|
|
dput(dentry);
|
|
return ret;
|
|
}
|
|
|
|
static int ext4_fsync_nojournal(struct inode *inode, bool datasync,
|
|
bool *needs_barrier)
|
|
{
|
|
int ret, err;
|
|
|
|
ret = sync_mapping_buffers(inode->i_mapping);
|
|
if (!(inode->i_state & I_DIRTY_ALL))
|
|
return ret;
|
|
if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
|
|
return ret;
|
|
|
|
err = sync_inode_metadata(inode, 1);
|
|
if (!ret)
|
|
ret = err;
|
|
|
|
if (!ret)
|
|
ret = ext4_sync_parent(inode);
|
|
if (test_opt(inode->i_sb, BARRIER))
|
|
*needs_barrier = true;
|
|
|
|
return ret;
|
|
}
|
|
|
|
static int ext4_fsync_journal(struct inode *inode, bool datasync,
|
|
bool *needs_barrier)
|
|
{
|
|
struct ext4_inode_info *ei = EXT4_I(inode);
|
|
journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
|
|
tid_t 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;
|
|
|
|
return jbd2_complete_transaction(journal, commit_tid);
|
|
}
|
|
|
|
/*
|
|
* akpm: A new design for ext4_sync_file().
|
|
*
|
|
* This is only called from sys_fsync(), sys_fdatasync() and sys_msync().
|
|
* There cannot be a transaction open by this task.
|
|
* Another task could have dirtied this inode. Its data can be in any
|
|
* state in the journalling system.
|
|
*
|
|
* What we do is just kick off a commit and wait on it. This will snapshot the
|
|
* inode to disk.
|
|
*/
|
|
int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
|
|
{
|
|
int ret = 0, err;
|
|
bool needs_barrier = false;
|
|
struct inode *inode = file->f_mapping->host;
|
|
struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
|
|
|
|
if (unlikely(ext4_forced_shutdown(sbi)))
|
|
return -EIO;
|
|
|
|
J_ASSERT(ext4_journal_current_handle() == NULL);
|
|
|
|
trace_ext4_sync_file_enter(file, datasync);
|
|
|
|
if (sb_rdonly(inode->i_sb)) {
|
|
/* Make sure that we read updated s_mount_flags value */
|
|
smp_rmb();
|
|
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
|
|
ret = -EROFS;
|
|
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 (!sbi->s_journal)
|
|
ret = ext4_fsync_nojournal(inode, datasync, &needs_barrier);
|
|
else if (ext4_should_journal_data(inode))
|
|
ret = ext4_force_commit(inode->i_sb);
|
|
else
|
|
ret = ext4_fsync_journal(inode, datasync, &needs_barrier);
|
|
|
|
if (needs_barrier) {
|
|
err = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL);
|
|
if (!ret)
|
|
ret = err;
|
|
}
|
|
out:
|
|
err = file_check_and_advance_wb_err(file);
|
|
if (ret == 0)
|
|
ret = err;
|
|
trace_ext4_sync_file_exit(inode, ret);
|
|
return ret;
|
|
}
|