xfs_log_recover.c

linux 内核源代码

		error = -1;
		goto out;
	}

	/*
	 * We have the final block of the good log (the first block
	 * of the log record _before_ the head. So we check the uuid.
	 */
	if ((error = xlog_header_check_mount(log->l_mp, head)))
		goto out;

	/*
	 * We may have found a log record header before we expected one.
	 * last_blk will be the 1st block # with a given cycle #.  We may end
	 * up reading an entire log record.  In this case, we don't want to
	 * reset last_blk.  Only when last_blk points in the middle of a log
	 * record do we update last_blk.
	 */
	if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
		uint	h_size = INT_GET(head->h_size, ARCH_CONVERT);

		xhdrs = h_size / XLOG_HEADER_CYCLE_SIZE;
		if (h_size % XLOG_HEADER_CYCLE_SIZE)
			xhdrs++;
	} else {
		xhdrs = 1;
	}

	if (*last_blk - i + extra_bblks
			!= BTOBB(INT_GET(head->h_len, ARCH_CONVERT)) + xhdrs)
		*last_blk = i;

out:
	xlog_put_bp(bp);
	return error;
}

/*
 * Head is defined to be the point of the log where the next log write
 * write could go.  This means that incomplete LR writes at the end are
 * eliminated when calculating the head.  We aren't guaranteed that previous
 * LR have complete transactions.  We only know that a cycle number of
 * current cycle number -1 won't be present in the log if we start writing
 * from our current block number.
 *
 * last_blk contains the block number of the first block with a given
 * cycle number.
 *
 * Return: zero if normal, non-zero if error.
 */
STATIC int
xlog_find_head(
	xlog_t 		*log,
	xfs_daddr_t	*return_head_blk)
{
	xfs_buf_t	*bp;
	xfs_caddr_t	offset;
	xfs_daddr_t	new_blk, first_blk, start_blk, last_blk, head_blk;
	int		num_scan_bblks;
	uint		first_half_cycle, last_half_cycle;
	uint		stop_on_cycle;
	int		error, log_bbnum = log->l_logBBsize;

	/* Is the end of the log device zeroed? */
	if ((error = xlog_find_zeroed(log, &first_blk)) == -1) {
		*return_head_blk = first_blk;

		/* Is the whole lot zeroed? */
		if (!first_blk) {
			/* Linux XFS shouldn't generate totally zeroed logs -
			 * mkfs etc write a dummy unmount record to a fresh
			 * log so we can store the uuid in there
			 */
			xlog_warn("XFS: totally zeroed log");
		}

		return 0;
	} else if (error) {
		xlog_warn("XFS: empty log check failed");
		return error;
	}

	first_blk = 0;			/* get cycle # of 1st block */
	bp = xlog_get_bp(log, 1);
	if (!bp)
		return ENOMEM;
	if ((error = xlog_bread(log, 0, 1, bp)))
		goto bp_err;
	offset = xlog_align(log, 0, 1, bp);
	first_half_cycle = GET_CYCLE(offset, ARCH_CONVERT);

	last_blk = head_blk = log_bbnum - 1;	/* get cycle # of last block */
	if ((error = xlog_bread(log, last_blk, 1, bp)))
		goto bp_err;
	offset = xlog_align(log, last_blk, 1, bp);
	last_half_cycle = GET_CYCLE(offset, ARCH_CONVERT);
	ASSERT(last_half_cycle != 0);

	/*
	 * If the 1st half cycle number is equal to the last half cycle number,
	 * then the entire log is stamped with the same cycle number.  In this
	 * case, head_blk can't be set to zero (which makes sense).  The below
	 * math doesn't work out properly with head_blk equal to zero.  Instead,
	 * we set it to log_bbnum which is an invalid block number, but this
	 * value makes the math correct.  If head_blk doesn't changed through
	 * all the tests below, *head_blk is set to zero at the very end rather
	 * than log_bbnum.  In a sense, log_bbnum and zero are the same block
	 * in a circular file.
	 */
	if (first_half_cycle == last_half_cycle) {
		/*
		 * In this case we believe that the entire log should have
		 * cycle number last_half_cycle.  We need to scan backwards
		 * from the end verifying that there are no holes still
		 * containing last_half_cycle - 1.  If we find such a hole,
		 * then the start of that hole will be the new head.  The
		 * simple case looks like
		 *        x | x ... | x - 1 | x
		 * Another case that fits this picture would be
		 *        x | x + 1 | x ... | x
		 * In this case the head really is somewhere at the end of the
		 * log, as one of the latest writes at the beginning was
		 * incomplete.
		 * One more case is
		 *        x | x + 1 | x ... | x - 1 | x
		 * This is really the combination of the above two cases, and
		 * the head has to end up at the start of the x-1 hole at the
		 * end of the log.
		 *
		 * In the 256k log case, we will read from the beginning to the
		 * end of the log and search for cycle numbers equal to x-1.
		 * We don't worry about the x+1 blocks that we encounter,
		 * because we know that they cannot be the head since the log
		 * started with x.
		 */
		head_blk = log_bbnum;
		stop_on_cycle = last_half_cycle - 1;
	} else {
		/*
		 * In this case we want to find the first block with cycle
		 * number matching last_half_cycle.  We expect the log to be
		 * some variation on
		 *        x + 1 ... | x ...
		 * The first block with cycle number x (last_half_cycle) will
		 * be where the new head belongs.  First we do a binary search
		 * for the first occurrence of last_half_cycle.  The binary
		 * search may not be totally accurate, so then we scan back
		 * from there looking for occurrences of last_half_cycle before
		 * us.  If that backwards scan wraps around the beginning of
		 * the log, then we look for occurrences of last_half_cycle - 1
		 * at the end of the log.  The cases we're looking for look
		 * like
		 *        x + 1 ... | x | x + 1 | x ...
		 *                               ^ binary search stopped here
		 * or
		 *        x + 1 ... | x ... | x - 1 | x
		 *        <---------> less than scan distance
		 */
		stop_on_cycle = last_half_cycle;
		if ((error = xlog_find_cycle_start(log, bp, first_blk,
						&head_blk, last_half_cycle)))
			goto bp_err;
	}

	/*
	 * Now validate the answer.  Scan back some number of maximum possible
	 * blocks and make sure each one has the expected cycle number.  The
	 * maximum is determined by the total possible amount of buffering
	 * in the in-core log.  The following number can be made tighter if
	 * we actually look at the block size of the filesystem.
	 */
	num_scan_bblks = XLOG_TOTAL_REC_SHIFT(log);
	if (head_blk >= num_scan_bblks) {
		/*
		 * We are guaranteed that the entire check can be performed
		 * in one buffer.
		 */
		start_blk = head_blk - num_scan_bblks;
		if ((error = xlog_find_verify_cycle(log,
						start_blk, num_scan_bblks,
						stop_on_cycle, &new_blk)))
			goto bp_err;
		if (new_blk != -1)
			head_blk = new_blk;
	} else {		/* need to read 2 parts of log */
		/*
		 * We are going to scan backwards in the log in two parts.
		 * First we scan the physical end of the log.  In this part
		 * of the log, we are looking for blocks with cycle number
		 * last_half_cycle - 1.
		 * If we find one, then we know that the log starts there, as
		 * we've found a hole that didn't get written in going around
		 * the end of the physical log.  The simple case for this is
		 *        x + 1 ... | x ... | x - 1 | x
		 *        <---------> less than scan distance
		 * If all of the blocks at the end of the log have cycle number
		 * last_half_cycle, then we check the blocks at the start of
		 * the log looking for occurrences of last_half_cycle.  If we
		 * find one, then our current estimate for the location of the
		 * first occurrence of last_half_cycle is wrong and we move
		 * back to the hole we've found.  This case looks like
		 *        x + 1 ... | x | x + 1 | x ...
		 *                               ^ binary search stopped here
		 * Another case we need to handle that only occurs in 256k
		 * logs is
		 *        x + 1 ... | x ... | x+1 | x ...
		 *                   ^ binary search stops here
		 * In a 256k log, the scan at the end of the log will see the
		 * x + 1 blocks.  We need to skip past those since that is
		 * certainly not the head of the log.  By searching for
		 * last_half_cycle-1 we accomplish that.
		 */
		start_blk = log_bbnum - num_scan_bblks + head_blk;
		ASSERT(head_blk <= INT_MAX &&
			(xfs_daddr_t) num_scan_bblks - head_blk >= 0);
		if ((error = xlog_find_verify_cycle(log, start_blk,
					num_scan_bblks - (int)head_blk,
					(stop_on_cycle - 1), &new_blk)))
			goto bp_err;
		if (new_blk != -1) {
			head_blk = new_blk;
			goto bad_blk;
		}

		/*
		 * Scan beginning of log now.  The last part of the physical
		 * log is good.  This scan needs to verify that it doesn't find
		 * the last_half_cycle.
		 */
		start_blk = 0;
		ASSERT(head_blk <= INT_MAX);
		if ((error = xlog_find_verify_cycle(log,
					start_blk, (int)head_blk,
					stop_on_cycle, &new_blk)))
			goto bp_err;
		if (new_blk != -1)
			head_blk = new_blk;
	}

 bad_blk:
	/*
	 * Now we need to make sure head_blk is not pointing to a block in
	 * the middle of a log record.
	 */
	num_scan_bblks = XLOG_REC_SHIFT(log);
	if (head_blk >= num_scan_bblks) {
		start_blk = head_blk - num_scan_bblks; /* don't read head_blk */

		/* start ptr at last block ptr before head_blk */
		if ((error = xlog_find_verify_log_record(log, start_blk,
							&head_blk, 0)) == -1) {
			error = XFS_ERROR(EIO);
			goto bp_err;
		} else if (error)
			goto bp_err;
	} else {
		start_blk = 0;
		ASSERT(head_blk <= INT_MAX);
		if ((error = xlog_find_verify_log_record(log, start_blk,
							&head_blk, 0)) == -1) {
			/* We hit the beginning of the log during our search */
			start_blk = log_bbnum - num_scan_bblks + head_blk;
			new_blk = log_bbnum;
			ASSERT(start_blk <= INT_MAX &&
				(xfs_daddr_t) log_bbnum-start_blk >= 0);
			ASSERT(head_blk <= INT_MAX);
			if ((error = xlog_find_verify_log_record(log,
							start_blk, &new_blk,
							(int)head_blk)) == -1) {
				error = XFS_ERROR(EIO);
				goto bp_err;
			} else if (error)
				goto bp_err;
			if (new_blk != log_bbnum)
				head_blk = new_blk;
		} else if (error)
			goto bp_err;
	}

	xlog_put_bp(bp);
	if (head_blk == log_bbnum)
		*return_head_blk = 0;
	else
		*return_head_blk = head_blk;
	/*
	 * When returning here, we have a good block number.  Bad block
	 * means that during a previous crash, we didn't have a clean break
	 * from cycle number N to cycle number N-1.  In this case, we need
	 * to find the first block with cycle number N-1.
	 */
	return 0;

 bp_err:
	xlog_put_bp(bp);

	if (error)
	    xlog_warn("XFS: failed to find log head");
	return error;
}

/*
 * Find the sync block number or the tail of the log.
 *
 * This will be the block number of the last record to have its
 * associated buffers synced to disk.  Every log record header has
 * a sync lsn embedded in it.  LSNs hold block numbers, so it is easy
 * to get a sync block number.  The only concern is to figure out which
 * log record header to believe.
 *
 * The following algorithm uses the log record header with the largest
 * lsn.  The entire log record does not need to be valid.  We only care
 * that the header is valid.
 *
 * We could speed up search by using current head_blk buffer, but it is not
 * available.
 */
int
xlog_find_tail(
	xlog_t			*log,
	xfs_daddr_t		*head_blk,
	xfs_daddr_t		*tail_blk)
{
	xlog_rec_header_t	*rhead;
	xlog_op_header_t	*op_head;
	xfs_caddr_t		offset = NULL;
	xfs_buf_t		*bp;
	int			error, i, found;
	xfs_daddr_t		umount_data_blk;
	xfs_daddr_t		after_umount_blk;
	xfs_lsn_t		tail_lsn;
	int			hblks;

	found = 0;

	/*
	 * Find previous log record
	 */
	if ((error = xlog_find_head(log, head_blk)))
		return error;

	bp = xlog_get_bp(log, 1);
	if (!bp)
		return ENOMEM;
	if (*head_blk == 0) {				/* special case */
		if ((error = xlog_bread(log, 0, 1, bp)))
			goto bread_err;
		offset = xlog_align(log, 0, 1, bp);
		if (GET_CYCLE(offset, ARCH_CONVERT) == 0) {
			*tail_blk = 0;
			/* leave all other log inited values alone */
			goto exit;
		}
	}

	/*
	 * Search backwards looking for log record header block
	 */
	ASSERT(*head_blk < INT_MAX);
	for (i = (int)(*head_blk) - 1; i >= 0; i--) {
		if ((error = xlog_bread(log, i, 1, bp)))
			goto bread_err;
		offset = xlog_align(log, i, 1, bp);
		if (XLOG_HEADER_MAGIC_NUM ==
		    INT_GET(*(uint *)offset, ARCH_CONVERT)) {
			found = 1;
			break;
		}
	}
	/*
	 * If we haven't found the log record header block, start looking
	 * again from the end of the physical log.  XXXmiken: There should be
	 * a check here to make sure we didn't search more than N blocks in
	 * the previous code.
	 */
	if (!found) {
		for (i = log->l_logBBsize - 1; i >= (int)(*head_blk); i--) {
			if ((error = xlog_bread(log, i, 1, bp)))
				goto bread_err;
			offset = xlog_align(log, i, 1, bp);
			if (XLOG_HEADER_MAGIC_NUM ==
			    INT_GET(*(uint*)offset, ARCH_CONVERT)) {
				found = 2;
				break;
			}
		}
	}
	if (!found) {
		xlog_warn("XFS: xlog_find_tail: couldn't find sync record");
		ASSERT(0);
		return XFS_ERROR(EIO);
	}

	/* find blk_no of tail of log */
	rhead = (xlog_rec_header_t *)offset;
	*tail_blk = BLOCK_LSN(INT_GET(rhead->h_tail_lsn, ARCH_CONVERT));

	/*
	 * Reset log values according to the state of the log when we
	 * crashed.  In the case where head_blk == 0, we bump curr_cycle
	 * one because the next write starts a new cycle rather than
	 * continuing the cycle of the last good log record.  At this
	 * point we have guaranteed that all partial log records have been
	 * accounted for.  Therefore, we know that the last good log record
	 * written was complete and ended exactly on the end boundary
	 * of the physical log.
	 */
	log->l_prev_block = i;
	log->l_curr_block = (int)*head_blk;
	log->l_curr_cycle = INT_GET(rhead->h_cycle, ARCH_CONVERT);
	if (found == 2)
		log->l_curr_cycle++;
	log->l_tail_lsn = INT_GET(rhead->h_tail_lsn, ARCH_CONVERT);
	log->l_last_sync_lsn = INT_GET(rhead->h_lsn, ARCH_CONVERT);
	log->l_grant_reserve_cycle = log->l_curr_cycle;
	log->l_grant_reserve_bytes = BBTOB(log->l_curr_block);
	log->l_grant_write_cycle = log->l_curr_cycle;
	log->l_grant_write_bytes = BBTOB(log->l_curr_block);

	/*
	 * Look for unmount record.  If we find it, then we know there
	 * was a clean unmount.  Since 'i' could be the last block in
	 * the physical log, we convert to a log block before comparing
	 * to the head_blk.
	 *
	 * Save the current tail lsn to use to pass to
	 * xlog_clear_stale_blocks() below.  We won't want to clear the
	 * unmount record if there is one, so we pass the lsn of the
	 * unmount record rather than the block after it.
	 */
	if (XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb)) {
		int	h_size = INT_GET(rhead->h_size, ARCH_CONVERT);
		int	h_version = INT_GET(rhead->h_version, ARCH_CONVERT);

		if ((h_version & XLOG_VERSION_2) &&
		    (h_size > XLOG_HEADER_CYCLE_SIZE)) {
			hblks = h_size / XLOG_HEADER_CYCLE_SIZE;
			if (h_size % XLOG_HEADER_CYCLE_SIZE)
				hblks++;
		} else {
			hblks = 1;
		}
	} else {
		hblks = 1;
	}
	after_umount_blk = (i + hblks + (int)
		BTOBB(INT_GET(rhead->h_len, ARCH_CONVERT))) % log->l_logBBsize;
	tail_lsn = log->l_tail_lsn;
	if (*head_blk == after_umount_blk &&
	    INT_GET(rhead->h_num_logops, ARCH_CONVERT) == 1) {
		umount_data_blk = (i + hblks) % log->l_logBBsize;
		if ((error = xlog_bread(log, umount_data_blk, 1, bp))) {
			goto bread_err;
		}
		offset = xlog_align(log, umount_data_blk, 1, bp);
		op_head = (xlog_op_header_t *)offset;
		if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
			/*
			 * Set tail and last sync so that newly written
			 * log records will point recovery to after the
			 * current unmount record.
			 */
			ASSIGN_ANY_LSN_HOST(log->l_tail_lsn, log->l_curr_cycle,
					after_umount_blk);