xfs_log_recover.c

linux 内核源代码

			ASSIGN_ANY_LSN_HOST(log->l_last_sync_lsn, log->l_curr_cycle,
					after_umount_blk);
			*tail_blk = after_umount_blk;

			/*
			 * Note that the unmount was clean. If the unmount
			 * was not clean, we need to know this to rebuild the
			 * superblock counters from the perag headers if we
			 * have a filesystem using non-persistent counters.
			 */
			log->l_mp->m_flags |= XFS_MOUNT_WAS_CLEAN;
		}
	}

	/*
	 * Make sure that there are no blocks in front of the head
	 * with the same cycle number as the head.  This can happen
	 * because we allow multiple outstanding log writes concurrently,
	 * and the later writes might make it out before earlier ones.
	 *
	 * We use the lsn from before modifying it so that we'll never
	 * overwrite the unmount record after a clean unmount.
	 *
	 * Do this only if we are going to recover the filesystem
	 *
	 * NOTE: This used to say "if (!readonly)"
	 * However on Linux, we can & do recover a read-only filesystem.
	 * We only skip recovery if NORECOVERY is specified on mount,
	 * in which case we would not be here.
	 *
	 * But... if the -device- itself is readonly, just skip this.
	 * We can't recover this device anyway, so it won't matter.
	 */
	if (!xfs_readonly_buftarg(log->l_mp->m_logdev_targp)) {
		error = xlog_clear_stale_blocks(log, tail_lsn);
	}

bread_err:
exit:
	xlog_put_bp(bp);

	if (error)
		xlog_warn("XFS: failed to locate log tail");
	return error;
}

/*
 * Is the log zeroed at all?
 *
 * The last binary search should be changed to perform an X block read
 * once X becomes small enough.  You can then search linearly through
 * the X blocks.  This will cut down on the number of reads we need to do.
 *
 * If the log is partially zeroed, this routine will pass back the blkno
 * of the first block with cycle number 0.  It won't have a complete LR
 * preceding it.
 *
 * Return:
 *	0  => the log is completely written to
 *	-1 => use *blk_no as the first block of the log
 *	>0 => error has occurred
 */
int
xlog_find_zeroed(
	xlog_t		*log,
	xfs_daddr_t	*blk_no)
{
	xfs_buf_t	*bp;
	xfs_caddr_t	offset;
	uint	        first_cycle, last_cycle;
	xfs_daddr_t	new_blk, last_blk, start_blk;
	xfs_daddr_t     num_scan_bblks;
	int	        error, log_bbnum = log->l_logBBsize;

	*blk_no = 0;

	/* check totally zeroed log */
	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_cycle = GET_CYCLE(offset, ARCH_CONVERT);
	if (first_cycle == 0) {		/* completely zeroed log */
		*blk_no = 0;
		xlog_put_bp(bp);
		return -1;
	}

	/* check partially zeroed log */
	if ((error = xlog_bread(log, log_bbnum-1, 1, bp)))
		goto bp_err;
	offset = xlog_align(log, log_bbnum-1, 1, bp);
	last_cycle = GET_CYCLE(offset, ARCH_CONVERT);
	if (last_cycle != 0) {		/* log completely written to */
		xlog_put_bp(bp);
		return 0;
	} else if (first_cycle != 1) {
		/*
		 * If the cycle of the last block is zero, the cycle of
		 * the first block must be 1. If it's not, maybe we're
		 * not looking at a log... Bail out.
		 */
		xlog_warn("XFS: Log inconsistent or not a log (last==0, first!=1)");
		return XFS_ERROR(EINVAL);
	}

	/* we have a partially zeroed log */
	last_blk = log_bbnum-1;
	if ((error = xlog_find_cycle_start(log, bp, 0, &last_blk, 0)))
		goto bp_err;

	/*
	 * Validate the answer.  Because there is no way to guarantee that
	 * the entire log is made up of log records which are the same size,
	 * we scan over the defined maximum blocks.  At this point, the maximum
	 * is not chosen to mean anything special.   XXXmiken
	 */
	num_scan_bblks = XLOG_TOTAL_REC_SHIFT(log);
	ASSERT(num_scan_bblks <= INT_MAX);

	if (last_blk < num_scan_bblks)
		num_scan_bblks = last_blk;
	start_blk = last_blk - num_scan_bblks;

	/*
	 * We search for any instances of cycle number 0 that occur before
	 * our current estimate of the head.  What we're trying to detect is
	 *        1 ... | 0 | 1 | 0...
	 *                       ^ binary search ends here
	 */
	if ((error = xlog_find_verify_cycle(log, start_blk,
					 (int)num_scan_bblks, 0, &new_blk)))
		goto bp_err;
	if (new_blk != -1)
		last_blk = new_blk;

	/*
	 * Potentially backup over partial log record write.  We don't need
	 * to search the end of the log because we know it is zero.
	 */
	if ((error = xlog_find_verify_log_record(log, start_blk,
				&last_blk, 0)) == -1) {
	    error = XFS_ERROR(EIO);
	    goto bp_err;
	} else if (error)
	    goto bp_err;

	*blk_no = last_blk;
bp_err:
	xlog_put_bp(bp);
	if (error)
		return error;
	return -1;
}

/*
 * These are simple subroutines used by xlog_clear_stale_blocks() below
 * to initialize a buffer full of empty log record headers and write
 * them into the log.
 */
STATIC void
xlog_add_record(
	xlog_t			*log,
	xfs_caddr_t		buf,
	int			cycle,
	int			block,
	int			tail_cycle,
	int			tail_block)
{
	xlog_rec_header_t	*recp = (xlog_rec_header_t *)buf;

	memset(buf, 0, BBSIZE);
	INT_SET(recp->h_magicno, ARCH_CONVERT, XLOG_HEADER_MAGIC_NUM);
	INT_SET(recp->h_cycle, ARCH_CONVERT, cycle);
	INT_SET(recp->h_version, ARCH_CONVERT,
			XFS_SB_VERSION_HASLOGV2(&log->l_mp->m_sb) ? 2 : 1);
	ASSIGN_ANY_LSN_DISK(recp->h_lsn, cycle, block);
	ASSIGN_ANY_LSN_DISK(recp->h_tail_lsn, tail_cycle, tail_block);
	INT_SET(recp->h_fmt, ARCH_CONVERT, XLOG_FMT);
	memcpy(&recp->h_fs_uuid, &log->l_mp->m_sb.sb_uuid, sizeof(uuid_t));
}

STATIC int
xlog_write_log_records(
	xlog_t		*log,
	int		cycle,
	int		start_block,
	int		blocks,
	int		tail_cycle,
	int		tail_block)
{
	xfs_caddr_t	offset;
	xfs_buf_t	*bp;
	int		balign, ealign;
	int		sectbb = XLOG_SECTOR_ROUNDUP_BBCOUNT(log, 1);
	int		end_block = start_block + blocks;
	int		bufblks;
	int		error = 0;
	int		i, j = 0;

	bufblks = 1 << ffs(blocks);
	while (!(bp = xlog_get_bp(log, bufblks))) {
		bufblks >>= 1;
		if (bufblks <= log->l_sectbb_log)
			return ENOMEM;
	}

	/* We may need to do a read at the start to fill in part of
	 * the buffer in the starting sector not covered by the first
	 * write below.
	 */
	balign = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, start_block);
	if (balign != start_block) {
		if ((error = xlog_bread(log, start_block, 1, bp))) {
			xlog_put_bp(bp);
			return error;
		}
		j = start_block - balign;
	}

	for (i = start_block; i < end_block; i += bufblks) {
		int		bcount, endcount;

		bcount = min(bufblks, end_block - start_block);
		endcount = bcount - j;

		/* We may need to do a read at the end to fill in part of
		 * the buffer in the final sector not covered by the write.
		 * If this is the same sector as the above read, skip it.
		 */
		ealign = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, end_block);
		if (j == 0 && (start_block + endcount > ealign)) {
			offset = XFS_BUF_PTR(bp);
			balign = BBTOB(ealign - start_block);
			XFS_BUF_SET_PTR(bp, offset + balign, BBTOB(sectbb));
			if ((error = xlog_bread(log, ealign, sectbb, bp)))
				break;
			XFS_BUF_SET_PTR(bp, offset, bufblks);
		}

		offset = xlog_align(log, start_block, endcount, bp);
		for (; j < endcount; j++) {
			xlog_add_record(log, offset, cycle, i+j,
					tail_cycle, tail_block);
			offset += BBSIZE;
		}
		error = xlog_bwrite(log, start_block, endcount, bp);
		if (error)
			break;
		start_block += endcount;
		j = 0;
	}
	xlog_put_bp(bp);
	return error;
}

/*
 * This routine is called to blow away any incomplete log writes out
 * in front of the log head.  We do this so that we won't become confused
 * if we come up, write only a little bit more, and then crash again.
 * If we leave the partial log records out there, this situation could
 * cause us to think those partial writes are valid blocks since they
 * have the current cycle number.  We get rid of them by overwriting them
 * with empty log records with the old cycle number rather than the
 * current one.
 *
 * The tail lsn is passed in rather than taken from
 * the log so that we will not write over the unmount record after a
 * clean unmount in a 512 block log.  Doing so would leave the log without
 * any valid log records in it until a new one was written.  If we crashed
 * during that time we would not be able to recover.
 */
STATIC int
xlog_clear_stale_blocks(
	xlog_t		*log,
	xfs_lsn_t	tail_lsn)
{
	int		tail_cycle, head_cycle;
	int		tail_block, head_block;
	int		tail_distance, max_distance;
	int		distance;
	int		error;

	tail_cycle = CYCLE_LSN(tail_lsn);
	tail_block = BLOCK_LSN(tail_lsn);
	head_cycle = log->l_curr_cycle;
	head_block = log->l_curr_block;

	/*
	 * Figure out the distance between the new head of the log
	 * and the tail.  We want to write over any blocks beyond the
	 * head that we may have written just before the crash, but
	 * we don't want to overwrite the tail of the log.
	 */
	if (head_cycle == tail_cycle) {
		/*
		 * The tail is behind the head in the physical log,
		 * so the distance from the head to the tail is the
		 * distance from the head to the end of the log plus
		 * the distance from the beginning of the log to the
		 * tail.
		 */
		if (unlikely(head_block < tail_block || head_block >= log->l_logBBsize)) {
			XFS_ERROR_REPORT("xlog_clear_stale_blocks(1)",
					 XFS_ERRLEVEL_LOW, log->l_mp);
			return XFS_ERROR(EFSCORRUPTED);
		}
		tail_distance = tail_block + (log->l_logBBsize - head_block);
	} else {
		/*
		 * The head is behind the tail in the physical log,
		 * so the distance from the head to the tail is just
		 * the tail block minus the head block.
		 */
		if (unlikely(head_block >= tail_block || head_cycle != (tail_cycle + 1))){
			XFS_ERROR_REPORT("xlog_clear_stale_blocks(2)",
					 XFS_ERRLEVEL_LOW, log->l_mp);
			return XFS_ERROR(EFSCORRUPTED);
		}
		tail_distance = tail_block - head_block;
	}

	/*
	 * If the head is right up against the tail, we can't clear
	 * anything.
	 */
	if (tail_distance <= 0) {
		ASSERT(tail_distance == 0);
		return 0;
	}

	max_distance = XLOG_TOTAL_REC_SHIFT(log);
	/*
	 * Take the smaller of the maximum amount of outstanding I/O
	 * we could have and the distance to the tail to clear out.
	 * We take the smaller so that we don't overwrite the tail and
	 * we don't waste all day writing from the head to the tail
	 * for no reason.
	 */
	max_distance = MIN(max_distance, tail_distance);

	if ((head_block + max_distance) <= log->l_logBBsize) {
		/*
		 * We can stomp all the blocks we need to without
		 * wrapping around the end of the log.  Just do it
		 * in a single write.  Use the cycle number of the
		 * current cycle minus one so that the log will look like:
		 *     n ... | n - 1 ...
		 */
		error = xlog_write_log_records(log, (head_cycle - 1),
				head_block, max_distance, tail_cycle,
				tail_block);
		if (error)
			return error;
	} else {
		/*
		 * We need to wrap around the end of the physical log in
		 * order to clear all the blocks.  Do it in two separate
		 * I/Os.  The first write should be from the head to the
		 * end of the physical log, and it should use the current
		 * cycle number minus one just like above.
		 */
		distance = log->l_logBBsize - head_block;
		error = xlog_write_log_records(log, (head_cycle - 1),
				head_block, distance, tail_cycle,
				tail_block);

		if (error)
			return error;

		/*
		 * Now write the blocks at the start of the physical log.
		 * This writes the remainder of the blocks we want to clear.
		 * It uses the current cycle number since we're now on the
		 * same cycle as the head so that we get:
		 *    n ... n ... | n - 1 ...
		 *    ^^^^^ blocks we're writing
		 */
		distance = max_distance - (log->l_logBBsize - head_block);
		error = xlog_write_log_records(log, head_cycle, 0, distance,
				tail_cycle, tail_block);
		if (error)
			return error;
	}

	return 0;
}

/******************************************************************************
 *
 *		Log recover routines
 *
 ******************************************************************************
 */

STATIC xlog_recover_t *
xlog_recover_find_tid(
	xlog_recover_t		*q,
	xlog_tid_t		tid)
{
	xlog_recover_t		*p = q;

	while (p != NULL) {
		if (p->r_log_tid == tid)
		    break;
		p = p->r_next;
	}
	return p;
}

STATIC void
xlog_recover_put_hashq(
	xlog_recover_t		**q,
	xlog_recover_t		*trans)
{
	trans->r_next = *q;
	*q = trans;
}

STATIC void
xlog_recover_add_item(
	xlog_recover_item_t	**itemq)
{
	xlog_recover_item_t	*item;

	item = kmem_zalloc(sizeof(xlog_recover_item_t), KM_SLEEP);
	xlog_recover_insert_item_backq(itemq, item);
}

STATIC int
xlog_recover_add_to_cont_trans(
	xlog_recover_t		*trans,
	xfs_caddr_t		dp,
	int			len)
{
	xlog_recover_item_t	*item;
	xfs_caddr_t		ptr, old_ptr;
	int			old_len;

	item = trans->r_itemq;
	if (item == NULL) {
		/* finish copying rest of trans header */
		xlog_recover_add_item(&trans->r_itemq);
		ptr = (xfs_caddr_t) &trans->r_theader +
				sizeof(xfs_trans_header_t) - len;
		memcpy(ptr, dp, len); /* d, s, l */
		return 0;
	}
	item = item->ri_prev;

	old_ptr = item->ri_buf[item->ri_cnt-1].i_addr;
	old_len = item->ri_buf[item->ri_cnt-1].i_len;

	ptr = kmem_realloc(old_ptr, len+old_len, old_len, 0u);
	memcpy(&ptr[old_len], dp, len); /* d, s, l */
	item->ri_buf[item->ri_cnt-1].i_len += len;
	item->ri_buf[item->ri_cnt-1].i_addr = ptr;
	return 0;
}

/*