mirrors/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2024-11-01 08:58:07 +00:00
Code Issues Releases Wiki Activity
linux-stable/fs/xfs/xfs_trans_priv.h
Dave Chinner 0dcd5a10d9 xfs: l_last_sync_lsn is really AIL state 
The current implementation of xlog_assign_tail_lsn() assumes that
when the AIL is empty, the log tail matches the LSN of the last
written commit record. This is recorded in xlog_state_set_callback()
as log->l_last_sync_lsn when the iclog state changes to
XLOG_STATE_CALLBACK. This change is then immediately followed by
running the callbacks on the iclog which then insert the log items
into the AIL at the "commit lsn" of that checkpoint.

The AIL tracks log items via the start record LSN of the checkpoint,
not the commit record LSN. This is because we can pipeline multiple
checkpoints, and so the start record of checkpoint N+1 can be
written before the commit record of checkpoint N. i.e:

     start N			commit N
	+-------------+------------+----------------+
		  start N+1			commit N+1

The tail of the log cannot be moved to the LSN of commit N when all
the items of that checkpoint are written back, because then the
start record for N+1 is no longer in the active portion of the log
and recovery will fail/corrupt the filesystem.

Hence when all the log items in checkpoint N are written back, the
tail of the log most now only move as far forwards as the start LSN
of checkpoint N+1.

Hence we cannot use the maximum start record LSN the AIL sees as a
replacement the pointer to the current head of the on-disk log
records. However, we currently only use the l_last_sync_lsn when the
AIL is empty - when there is no start LSN remaining, the tail of the
log moves to the LSN of the last commit record as this is where
recovery needs to start searching for recoverable records. THe next
checkpoint will have a start record LSN that is higher than
l_last_sync_lsn, and so everything still works correctly when new
checkpoints are written to an otherwise empty log.

l_last_sync_lsn is an atomic variable because it is currently
updated when an iclog with callbacks attached moves to the CALLBACK
state. While we hold the icloglock at this point, we don't hold the
AIL lock. When we assign the log tail, we hold the AIL lock, not the
icloglock because we have to look up the AIL. Hence it is an atomic
variable so it's not bound to a specific lock context.

However, the iclog callbacks are only used for CIL checkpoints. We
don't use callbacks with unmount record writes, so the
l_last_sync_lsn variable only gets updated when we are processing
CIL checkpoint callbacks. And those callbacks run under AIL lock
contexts, not icloglock context. The CIL checkpoint already knows
what the LSN of the iclog the commit record was written to (obtained
when written into the iclog before submission) and so we can update
the l_last_sync_lsn under the AIL lock in this callback. No other
iclog callbacks will run until the currently executing one
completes, and hence we can update the l_last_sync_lsn under the AIL
lock safely.

This means l_last_sync_lsn can move to the AIL as the "ail_head_lsn"
and it can be used to replace the atomic l_last_sync_lsn in the
iclog code. This makes tracking the log tail belong entirely to the
AIL, rather than being smeared across log, iclog and AIL state and
locking.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Chandan Babu R <chandanbabu@kernel.org>
2024-07-04 12:46:46 +05:30

198 lines
5 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000,2002,2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#ifndef __XFS_TRANS_PRIV_H__
#define __XFS_TRANS_PRIV_H__
struct xlog;
struct xfs_log_item;
struct xfs_mount;
struct xfs_trans;
struct xfs_ail;
struct xfs_log_vec;
void xfs_trans_init(struct xfs_mount *);
void xfs_trans_add_item(struct xfs_trans *, struct xfs_log_item *);
void xfs_trans_del_item(struct xfs_log_item *);
void xfs_trans_unreserve_and_mod_sb(struct xfs_trans *tp);
/*
* AIL traversal cursor.
*
* Rather than using a generation number for detecting changes in the ail, use
* a cursor that is protected by the ail lock. The aild cursor exists in the
* struct xfs_ail, but other traversals can declare it on the stack and link it
* to the ail list.
*
* When an object is deleted from or moved int the AIL, the cursor list is
* searched to see if the object is a designated cursor item. If it is, it is
* deleted from the cursor so that the next time the cursor is used traversal
* will return to the start.
*
* This means a traversal colliding with a removal will cause a restart of the
* list scan, rather than any insertion or deletion anywhere in the list. The
* low bit of the item pointer is set if the cursor has been invalidated so
* that we can tell the difference between invalidation and reaching the end
* of the list to trigger traversal restarts.
*/
struct xfs_ail_cursor {
struct list_head list;
struct xfs_log_item *item;
};
/*
* Private AIL structures.
*
* Eventually we need to drive the locking in here as well.
*/
struct xfs_ail {
struct xlog *ail_log;
struct task_struct *ail_task;
struct list_head ail_head;
struct list_head ail_cursors;
spinlock_t ail_lock;
xfs_lsn_t ail_last_pushed_lsn;
xfs_lsn_t ail_head_lsn;
int ail_log_flush;
unsigned long ail_opstate;
struct list_head ail_buf_list;
wait_queue_head_t ail_empty;
xfs_lsn_t ail_target;
};
/* Push all items out of the AIL immediately. */
#define XFS_AIL_OPSTATE_PUSH_ALL 0u
/*
* From xfs_trans_ail.c
*/
void xfs_trans_ail_update_bulk(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur,
struct xfs_log_item **log_items, int nr_items,
xfs_lsn_t lsn) __releases(ailp->ail_lock);
/*
* Return a pointer to the first item in the AIL. If the AIL is empty, then
* return NULL.
*/
static inline struct xfs_log_item *
xfs_ail_min(
struct xfs_ail *ailp)
{
return list_first_entry_or_null(&ailp->ail_head, struct xfs_log_item,
li_ail);
}
static inline void
xfs_trans_ail_update(
struct xfs_ail *ailp,
struct xfs_log_item *lip,
xfs_lsn_t lsn) __releases(ailp->ail_lock)
{
xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn);
}
void xfs_trans_ail_insert(struct xfs_ail *ailp, struct xfs_log_item *lip,
xfs_lsn_t lsn);
xfs_lsn_t xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip);
void xfs_ail_update_finish(struct xfs_ail *ailp, xfs_lsn_t old_lsn)
__releases(ailp->ail_lock);
void xfs_trans_ail_delete(struct xfs_log_item *lip, int shutdown_type);
static inline void xfs_ail_push(struct xfs_ail *ailp)
{
wake_up_process(ailp->ail_task);
}
static inline void xfs_ail_push_all(struct xfs_ail *ailp)
{
if (!test_and_set_bit(XFS_AIL_OPSTATE_PUSH_ALL, &ailp->ail_opstate))
xfs_ail_push(ailp);
}
static inline xfs_lsn_t xfs_ail_get_push_target(struct xfs_ail *ailp)
{
return READ_ONCE(ailp->ail_target);
}
void xfs_ail_push_all_sync(struct xfs_ail *ailp);
xfs_lsn_t xfs_ail_min_lsn(struct xfs_ail *ailp);
struct xfs_log_item * xfs_trans_ail_cursor_first(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur,
xfs_lsn_t lsn);
struct xfs_log_item * xfs_trans_ail_cursor_last(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur,
xfs_lsn_t lsn);
struct xfs_log_item * xfs_trans_ail_cursor_next(struct xfs_ail *ailp,
struct xfs_ail_cursor *cur);
void xfs_trans_ail_cursor_done(struct xfs_ail_cursor *cur);
void __xfs_ail_assign_tail_lsn(struct xfs_ail *ailp);
static inline void
xfs_ail_assign_tail_lsn(
struct xfs_ail *ailp)
{
spin_lock(&ailp->ail_lock);
__xfs_ail_assign_tail_lsn(ailp);
spin_unlock(&ailp->ail_lock);
}
#if BITS_PER_LONG != 64
static inline void
xfs_trans_ail_copy_lsn(
struct xfs_ail *ailp,
xfs_lsn_t *dst,
xfs_lsn_t *src)
{
ASSERT(sizeof(xfs_lsn_t) == 8); /* don't lock if it shrinks */
spin_lock(&ailp->ail_lock);
*dst = *src;
spin_unlock(&ailp->ail_lock);
}
#else
static inline void
xfs_trans_ail_copy_lsn(
struct xfs_ail *ailp,
xfs_lsn_t *dst,
xfs_lsn_t *src)
{
ASSERT(sizeof(xfs_lsn_t) == 8);
*dst = *src;
}
#endif
static inline void
xfs_clear_li_failed(
struct xfs_log_item *lip)
{
struct xfs_buf *bp = lip->li_buf;
ASSERT(test_bit(XFS_LI_IN_AIL, &lip->li_flags));
lockdep_assert_held(&lip->li_ailp->ail_lock);
if (test_and_clear_bit(XFS_LI_FAILED, &lip->li_flags)) {
lip->li_buf = NULL;
xfs_buf_rele(bp);
}
}
static inline void
xfs_set_li_failed(
struct xfs_log_item *lip,
struct xfs_buf *bp)
{
lockdep_assert_held(&lip->li_ailp->ail_lock);
if (!test_and_set_bit(XFS_LI_FAILED, &lip->li_flags)) {
xfs_buf_hold(bp);
lip->li_buf = bp;
}
}
#endif /* __XFS_TRANS_PRIV_H__ */
Reference in a new issue View git blame Copy permalink