forked from Minki/linux
a45086e27d
Since the onset of v5 superblocks, the LSN of the last modification has been included in a variety of on-disk data structures. This LSN is used to provide log recovery ordering guarantees (e.g., to ensure an older log recovery item is not replayed over a newer target data structure). While this works correctly from the point a filesystem is formatted and mounted, userspace tools have some problematic behaviors that defeat this mechanism. For example, xfs_repair historically zeroes out the log unconditionally (regardless of whether corruption is detected). If this occurs, the LSN of the filesystem is reset and the log is now in a problematic state with respect to on-disk metadata structures that might have a larger LSN. Until either the log catches up to the highest previously used metadata LSN or each affected data structure is modified and written out without incident (which resets the metadata LSN), log recovery is susceptible to filesystem corruption. This problem is ultimately addressed and repaired in the associated userspace tools. The kernel is still responsible to detect the problem and notify the user that something is wrong. Check the superblock LSN at mount time and fail the mount if it is invalid. From that point on, trigger verifier failure on any metadata I/O where an invalid LSN is detected. This results in a filesystem shutdown and guarantees that we do not log metadata changes with invalid LSNs on disk. Since this is a known issue with a known recovery path, present a warning to instruct the user how to recover. Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Dave Chinner <david@fromorbit.com>
187 lines
5.5 KiB
C
187 lines
5.5 KiB
C
/*
|
|
* Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
|
|
* All Rights Reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License as
|
|
* published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope that it would be useful,
|
|
* but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
|
* GNU General Public License for more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License
|
|
* along with this program; if not, write the Free Software Foundation,
|
|
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
|
|
*/
|
|
#ifndef __XFS_LOG_H__
|
|
#define __XFS_LOG_H__
|
|
|
|
struct xfs_log_vec {
|
|
struct xfs_log_vec *lv_next; /* next lv in build list */
|
|
int lv_niovecs; /* number of iovecs in lv */
|
|
struct xfs_log_iovec *lv_iovecp; /* iovec array */
|
|
struct xfs_log_item *lv_item; /* owner */
|
|
char *lv_buf; /* formatted buffer */
|
|
int lv_bytes; /* accounted space in buffer */
|
|
int lv_buf_len; /* aligned size of buffer */
|
|
int lv_size; /* size of allocated lv */
|
|
};
|
|
|
|
#define XFS_LOG_VEC_ORDERED (-1)
|
|
|
|
static inline void *
|
|
xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
|
|
uint type)
|
|
{
|
|
struct xfs_log_iovec *vec = *vecp;
|
|
|
|
if (vec) {
|
|
ASSERT(vec - lv->lv_iovecp < lv->lv_niovecs);
|
|
vec++;
|
|
} else {
|
|
vec = &lv->lv_iovecp[0];
|
|
}
|
|
|
|
vec->i_type = type;
|
|
vec->i_addr = lv->lv_buf + lv->lv_buf_len;
|
|
|
|
ASSERT(IS_ALIGNED((unsigned long)vec->i_addr, sizeof(uint64_t)));
|
|
|
|
*vecp = vec;
|
|
return vec->i_addr;
|
|
}
|
|
|
|
/*
|
|
* We need to make sure the next buffer is naturally aligned for the biggest
|
|
* basic data type we put into it. We already accounted for this padding when
|
|
* sizing the buffer.
|
|
*
|
|
* However, this padding does not get written into the log, and hence we have to
|
|
* track the space used by the log vectors separately to prevent log space hangs
|
|
* due to inaccurate accounting (i.e. a leak) of the used log space through the
|
|
* CIL context ticket.
|
|
*/
|
|
static inline void
|
|
xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len)
|
|
{
|
|
lv->lv_buf_len += round_up(len, sizeof(uint64_t));
|
|
lv->lv_bytes += len;
|
|
vec->i_len = len;
|
|
}
|
|
|
|
static inline void *
|
|
xlog_copy_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
|
|
uint type, void *data, int len)
|
|
{
|
|
void *buf;
|
|
|
|
buf = xlog_prepare_iovec(lv, vecp, type);
|
|
memcpy(buf, data, len);
|
|
xlog_finish_iovec(lv, *vecp, len);
|
|
return buf;
|
|
}
|
|
|
|
/*
|
|
* Structure used to pass callback function and the function's argument
|
|
* to the log manager.
|
|
*/
|
|
typedef struct xfs_log_callback {
|
|
struct xfs_log_callback *cb_next;
|
|
void (*cb_func)(void *, int);
|
|
void *cb_arg;
|
|
} xfs_log_callback_t;
|
|
|
|
/*
|
|
* By comparing each component, we don't have to worry about extra
|
|
* endian issues in treating two 32 bit numbers as one 64 bit number
|
|
*/
|
|
static inline xfs_lsn_t _lsn_cmp(xfs_lsn_t lsn1, xfs_lsn_t lsn2)
|
|
{
|
|
if (CYCLE_LSN(lsn1) != CYCLE_LSN(lsn2))
|
|
return (CYCLE_LSN(lsn1)<CYCLE_LSN(lsn2))? -999 : 999;
|
|
|
|
if (BLOCK_LSN(lsn1) != BLOCK_LSN(lsn2))
|
|
return (BLOCK_LSN(lsn1)<BLOCK_LSN(lsn2))? -999 : 999;
|
|
|
|
return 0;
|
|
}
|
|
|
|
#define XFS_LSN_CMP(x,y) _lsn_cmp(x,y)
|
|
|
|
/*
|
|
* Flags to xfs_log_force()
|
|
*
|
|
* XFS_LOG_SYNC: Synchronous force in-core log to disk
|
|
*/
|
|
#define XFS_LOG_SYNC 0x1
|
|
|
|
/* Log manager interfaces */
|
|
struct xfs_mount;
|
|
struct xlog_in_core;
|
|
struct xlog_ticket;
|
|
struct xfs_log_item;
|
|
struct xfs_item_ops;
|
|
struct xfs_trans;
|
|
struct xfs_log_callback;
|
|
|
|
xfs_lsn_t xfs_log_done(struct xfs_mount *mp,
|
|
struct xlog_ticket *ticket,
|
|
struct xlog_in_core **iclog,
|
|
bool regrant);
|
|
int _xfs_log_force(struct xfs_mount *mp,
|
|
uint flags,
|
|
int *log_forced);
|
|
void xfs_log_force(struct xfs_mount *mp,
|
|
uint flags);
|
|
int _xfs_log_force_lsn(struct xfs_mount *mp,
|
|
xfs_lsn_t lsn,
|
|
uint flags,
|
|
int *log_forced);
|
|
void xfs_log_force_lsn(struct xfs_mount *mp,
|
|
xfs_lsn_t lsn,
|
|
uint flags);
|
|
int xfs_log_mount(struct xfs_mount *mp,
|
|
struct xfs_buftarg *log_target,
|
|
xfs_daddr_t start_block,
|
|
int num_bblocks);
|
|
int xfs_log_mount_finish(struct xfs_mount *mp);
|
|
int xfs_log_mount_cancel(struct xfs_mount *);
|
|
xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp);
|
|
xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp);
|
|
void xfs_log_space_wake(struct xfs_mount *mp);
|
|
int xfs_log_notify(struct xfs_mount *mp,
|
|
struct xlog_in_core *iclog,
|
|
struct xfs_log_callback *callback_entry);
|
|
int xfs_log_release_iclog(struct xfs_mount *mp,
|
|
struct xlog_in_core *iclog);
|
|
int xfs_log_reserve(struct xfs_mount *mp,
|
|
int length,
|
|
int count,
|
|
struct xlog_ticket **ticket,
|
|
__uint8_t clientid,
|
|
bool permanent,
|
|
uint t_type);
|
|
int xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic);
|
|
int xfs_log_unmount_write(struct xfs_mount *mp);
|
|
void xfs_log_unmount(struct xfs_mount *mp);
|
|
int xfs_log_force_umount(struct xfs_mount *mp, int logerror);
|
|
int xfs_log_need_covered(struct xfs_mount *mp);
|
|
|
|
void xlog_iodone(struct xfs_buf *);
|
|
|
|
struct xlog_ticket *xfs_log_ticket_get(struct xlog_ticket *ticket);
|
|
void xfs_log_ticket_put(struct xlog_ticket *ticket);
|
|
|
|
void xfs_log_commit_cil(struct xfs_mount *mp, struct xfs_trans *tp,
|
|
xfs_lsn_t *commit_lsn, bool regrant);
|
|
bool xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
|
|
|
|
void xfs_log_work_queue(struct xfs_mount *mp);
|
|
void xfs_log_worker(struct work_struct *work);
|
|
void xfs_log_quiesce(struct xfs_mount *mp);
|
|
bool xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
|
|
|
|
#endif /* __XFS_LOG_H__ */
|