linux/fs/xfs/libxfs/xfs_defer.h
Darrick J. Wong 93293bcbde xfs: log new intent items created as part of finishing recovered intent items
During a code inspection, I found a serious bug in the log intent item
recovery code when an intent item cannot complete all the work and
decides to requeue itself to get that done.  When this happens, the
item recovery creates a new incore deferred op representing the
remaining work and attaches it to the transaction that it allocated.  At
the end of _item_recover, it moves the entire chain of deferred ops to
the dummy parent_tp that xlog_recover_process_intents passed to it, but
fail to log a new intent item for the remaining work before committing
the transaction for the single unit of work.

xlog_finish_defer_ops logs those new intent items once recovery has
finished dealing with the intent items that it recovered, but this isn't
sufficient.  If the log is forced to disk after a recovered log item
decides to requeue itself and the system goes down before we call
xlog_finish_defer_ops, the second log recovery will never see the new
intent item and therefore has no idea that there was more work to do.
It will finish recovery leaving the filesystem in a corrupted state.

The same logic applies to /any/ deferred ops added during intent item
recovery, not just the one handling the remaining work.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
2020-09-23 08:58:51 -07:00

72 lines
2.4 KiB
C

/* SPDX-License-Identifier: GPL-2.0+ */
/*
* Copyright (C) 2016 Oracle. All Rights Reserved.
* Author: Darrick J. Wong <darrick.wong@oracle.com>
*/
#ifndef __XFS_DEFER_H__
#define __XFS_DEFER_H__
struct xfs_btree_cur;
struct xfs_defer_op_type;
/*
* Header for deferred operation list.
*/
enum xfs_defer_ops_type {
XFS_DEFER_OPS_TYPE_BMAP,
XFS_DEFER_OPS_TYPE_REFCOUNT,
XFS_DEFER_OPS_TYPE_RMAP,
XFS_DEFER_OPS_TYPE_FREE,
XFS_DEFER_OPS_TYPE_AGFL_FREE,
XFS_DEFER_OPS_TYPE_MAX,
};
/*
* Save a log intent item and a list of extents, so that we can replay
* whatever action had to happen to the extent list and file the log done
* item.
*/
struct xfs_defer_pending {
struct list_head dfp_list; /* pending items */
struct list_head dfp_work; /* work items */
struct xfs_log_item *dfp_intent; /* log intent item */
struct xfs_log_item *dfp_done; /* log done item */
unsigned int dfp_count; /* # extent items */
enum xfs_defer_ops_type dfp_type;
};
void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
struct list_head *h);
int xfs_defer_finish_noroll(struct xfs_trans **tp);
int xfs_defer_finish(struct xfs_trans **tp);
void xfs_defer_cancel(struct xfs_trans *);
void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
/* Description of a deferred type. */
struct xfs_defer_op_type {
struct xfs_log_item *(*create_intent)(struct xfs_trans *tp,
struct list_head *items, unsigned int count, bool sort);
void (*abort_intent)(struct xfs_log_item *intent);
struct xfs_log_item *(*create_done)(struct xfs_trans *tp,
struct xfs_log_item *intent, unsigned int count);
int (*finish_item)(struct xfs_trans *tp, struct xfs_log_item *done,
struct list_head *item, struct xfs_btree_cur **state);
void (*finish_cleanup)(struct xfs_trans *tp,
struct xfs_btree_cur *state, int error);
void (*cancel_item)(struct list_head *item);
unsigned int max_items;
};
extern const struct xfs_defer_op_type xfs_bmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_refcount_update_defer_type;
extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
/*
* Functions to capture a chain of deferred operations and continue them later.
* This doesn't normally happen except log recovery.
*/
void xfs_defer_capture(struct xfs_trans *dtp, struct xfs_trans *stp);
#endif /* __XFS_DEFER_H__ */