mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 11:50:52 +07:00
d4682ba03e
When we add a new name for an inode which was logged in the current
transaction, we update the inode in the log so that its new name and
ancestors are added to the log. However when we do this we do not persist
the log, so the changes remain in memory only, and as a consequence, any
ancestors that were created in the current transaction are updated such
that future calls to btrfs_inode_in_log() return true. This leads to a
subsequent fsync against such new ancestor directories returning
immediately, without persisting the log, therefore after a power failure
the new ancestor directories do not exist, despite fsync being called
against them explicitly.
Example:
$ mkfs.btrfs -f /dev/sdb
$ mount /dev/sdb /mnt
$ mkdir /mnt/A
$ mkdir /mnt/B
$ mkdir /mnt/A/C
$ touch /mnt/B/foo
$ xfs_io -c "fsync" /mnt/B/foo
$ ln /mnt/B/foo /mnt/A/C/foo
$ xfs_io -c "fsync" /mnt/A
<power failure>
After the power failure, directory "A" does not exist, despite the explicit
fsync on it.
Instead of fixing this by changing the behaviour of the explicit fsync on
directory "A" to persist the log instead of doing nothing, make the logging
of the new file name (which happens when creating a hard link or renaming)
persist the log. This approach not only is simpler, not requiring addition
of new fields to the inode in memory structure, but also gives us the same
behaviour as ext4, xfs and f2fs (possibly other filesystems too).
A test case for fstests follows soon.
Fixes: 12fcfd22fe ("Btrfs: tree logging unlink/rename fixes")
Reported-by: Vijay Chidambaram <vvijay03@gmail.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
87 lines
2.6 KiB
C
87 lines
2.6 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Copyright (C) 2008 Oracle. All rights reserved.
|
|
*/
|
|
|
|
#ifndef BTRFS_TREE_LOG_H
|
|
#define BTRFS_TREE_LOG_H
|
|
|
|
#include "ctree.h"
|
|
#include "transaction.h"
|
|
|
|
/* return value for btrfs_log_dentry_safe that means we don't need to log it at all */
|
|
#define BTRFS_NO_LOG_SYNC 256
|
|
|
|
struct btrfs_log_ctx {
|
|
int log_ret;
|
|
int log_transid;
|
|
int io_err;
|
|
bool log_new_dentries;
|
|
struct inode *inode;
|
|
struct list_head list;
|
|
};
|
|
|
|
static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
|
|
struct inode *inode)
|
|
{
|
|
ctx->log_ret = 0;
|
|
ctx->log_transid = 0;
|
|
ctx->io_err = 0;
|
|
ctx->log_new_dentries = false;
|
|
ctx->inode = inode;
|
|
INIT_LIST_HEAD(&ctx->list);
|
|
}
|
|
|
|
static inline void btrfs_set_log_full_commit(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_trans_handle *trans)
|
|
{
|
|
WRITE_ONCE(fs_info->last_trans_log_full_commit, trans->transid);
|
|
}
|
|
|
|
static inline int btrfs_need_log_full_commit(struct btrfs_fs_info *fs_info,
|
|
struct btrfs_trans_handle *trans)
|
|
{
|
|
return READ_ONCE(fs_info->last_trans_log_full_commit) ==
|
|
trans->transid;
|
|
}
|
|
|
|
int btrfs_sync_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root, struct btrfs_log_ctx *ctx);
|
|
int btrfs_free_log(struct btrfs_trans_handle *trans, struct btrfs_root *root);
|
|
int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
|
|
struct btrfs_fs_info *fs_info);
|
|
int btrfs_recover_log_trees(struct btrfs_root *tree_root);
|
|
int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
|
|
struct dentry *dentry,
|
|
const loff_t start,
|
|
const loff_t end,
|
|
struct btrfs_log_ctx *ctx);
|
|
int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
const char *name, int name_len,
|
|
struct btrfs_inode *dir, u64 index);
|
|
int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
|
|
struct btrfs_root *root,
|
|
const char *name, int name_len,
|
|
struct btrfs_inode *inode, u64 dirid);
|
|
void btrfs_end_log_trans(struct btrfs_root *root);
|
|
int btrfs_pin_log_trans(struct btrfs_root *root);
|
|
void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *dir, struct btrfs_inode *inode,
|
|
int for_rename);
|
|
void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *dir);
|
|
/* Return values for btrfs_log_new_name() */
|
|
enum {
|
|
BTRFS_DONT_NEED_TRANS_COMMIT,
|
|
BTRFS_NEED_TRANS_COMMIT,
|
|
BTRFS_DONT_NEED_LOG_SYNC,
|
|
BTRFS_NEED_LOG_SYNC,
|
|
};
|
|
int btrfs_log_new_name(struct btrfs_trans_handle *trans,
|
|
struct btrfs_inode *inode, struct btrfs_inode *old_dir,
|
|
struct dentry *parent,
|
|
bool sync_log, struct btrfs_log_ctx *ctx);
|
|
|
|
#endif
|