Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 2f43bbd9 authored by Dave Chinner's avatar Dave Chinner
Browse files

Merge branch 'xfs-trans-recover-cleanup' into for-next

parents 33044dc4 b818cca1
Loading
Loading
Loading
Loading
+308 −256
Original line number Diff line number Diff line
@@ -1445,160 +1445,6 @@ xlog_clear_stale_blocks(
 ******************************************************************************
 */

STATIC xlog_recover_t *
xlog_recover_find_tid(
	struct hlist_head	*head,
	xlog_tid_t		tid)
{
	xlog_recover_t		*trans;

	hlist_for_each_entry(trans, head, r_list) {
		if (trans->r_log_tid == tid)
			return trans;
	}
	return NULL;
}

STATIC void
xlog_recover_new_tid(
	struct hlist_head	*head,
	xlog_tid_t		tid,
	xfs_lsn_t		lsn)
{
	xlog_recover_t		*trans;

	trans = kmem_zalloc(sizeof(xlog_recover_t), KM_SLEEP);
	trans->r_log_tid   = tid;
	trans->r_lsn	   = lsn;
	INIT_LIST_HEAD(&trans->r_itemq);

	INIT_HLIST_NODE(&trans->r_list);
	hlist_add_head(&trans->r_list, head);
}

STATIC void
xlog_recover_add_item(
	struct list_head	*head)
{
	xlog_recover_item_t	*item;

	item = kmem_zalloc(sizeof(xlog_recover_item_t), KM_SLEEP);
	INIT_LIST_HEAD(&item->ri_list);
	list_add_tail(&item->ri_list, head);
}

STATIC int
xlog_recover_add_to_cont_trans(
	struct xlog		*log,
	struct xlog_recover	*trans,
	xfs_caddr_t		dp,
	int			len)
{
	xlog_recover_item_t	*item;
	xfs_caddr_t		ptr, old_ptr;
	int			old_len;

	if (list_empty(&trans->r_itemq)) {
		/* 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;
	}
	/* take the tail entry */
	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);

	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, KM_SLEEP);
	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;
	trace_xfs_log_recover_item_add_cont(log, trans, item, 0);
	return 0;
}

/*
 * The next region to add is the start of a new region.  It could be
 * a whole region or it could be the first part of a new region.  Because
 * of this, the assumption here is that the type and size fields of all
 * format structures fit into the first 32 bits of the structure.
 *
 * This works because all regions must be 32 bit aligned.  Therefore, we
 * either have both fields or we have neither field.  In the case we have
 * neither field, the data part of the region is zero length.  We only have
 * a log_op_header and can throw away the header since a new one will appear
 * later.  If we have at least 4 bytes, then we can determine how many regions
 * will appear in the current log item.
 */
STATIC int
xlog_recover_add_to_trans(
	struct xlog		*log,
	struct xlog_recover	*trans,
	xfs_caddr_t		dp,
	int			len)
{
	xfs_inode_log_format_t	*in_f;			/* any will do */
	xlog_recover_item_t	*item;
	xfs_caddr_t		ptr;

	if (!len)
		return 0;
	if (list_empty(&trans->r_itemq)) {
		/* we need to catch log corruptions here */
		if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) {
			xfs_warn(log->l_mp, "%s: bad header magic number",
				__func__);
			ASSERT(0);
			return -EIO;
		}
		if (len == sizeof(xfs_trans_header_t))
			xlog_recover_add_item(&trans->r_itemq);
		memcpy(&trans->r_theader, dp, len); /* d, s, l */
		return 0;
	}

	ptr = kmem_alloc(len, KM_SLEEP);
	memcpy(ptr, dp, len);
	in_f = (xfs_inode_log_format_t *)ptr;

	/* take the tail entry */
	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);
	if (item->ri_total != 0 &&
	     item->ri_total == item->ri_cnt) {
		/* tail item is in use, get a new one */
		xlog_recover_add_item(&trans->r_itemq);
		item = list_entry(trans->r_itemq.prev,
					xlog_recover_item_t, ri_list);
	}

	if (item->ri_total == 0) {		/* first region to be added */
		if (in_f->ilf_size == 0 ||
		    in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
			xfs_warn(log->l_mp,
		"bad number of regions (%d) in inode log format",
				  in_f->ilf_size);
			ASSERT(0);
			kmem_free(ptr);
			return -EIO;
		}

		item->ri_total = in_f->ilf_size;
		item->ri_buf =
			kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
				    KM_SLEEP);
	}
	ASSERT(item->ri_total > item->ri_cnt);
	/* Description region is ri_buf[0] */
	item->ri_buf[item->ri_cnt].i_addr = ptr;
	item->ri_buf[item->ri_cnt].i_len  = len;
	item->ri_cnt++;
	trace_xfs_log_recover_item_add(log, trans, item, 0);
	return 0;
}

/*
 * Sort the log items in the transaction.
 *
@@ -3254,31 +3100,6 @@ xlog_recover_do_icreate_pass2(
	return 0;
}

/*
 * Free up any resources allocated by the transaction
 *
 * Remember that EFIs, EFDs, and IUNLINKs are handled later.
 */
STATIC void
xlog_recover_free_trans(
	struct xlog_recover	*trans)
{
	xlog_recover_item_t	*item, *n;
	int			i;

	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
		/* Free the regions in the item. */
		list_del(&item->ri_list);
		for (i = 0; i < item->ri_cnt; i++)
			kmem_free(item->ri_buf[i].i_addr);
		/* Free the item itself */
		kmem_free(item->ri_buf);
		kmem_free(item);
	}
	/* Free the transaction recover structure */
	kmem_free(trans);
}

STATIC void
xlog_recover_buffer_ra_pass2(
	struct xlog                     *log,
@@ -3528,118 +3349,349 @@ out:
	if (!list_empty(&done_list))
		list_splice_init(&done_list, &trans->r_itemq);

	xlog_recover_free_trans(trans);

	error2 = xfs_buf_delwri_submit(&buffer_list);
	return error ? error : error2;
}

STATIC void
xlog_recover_add_item(
	struct list_head	*head)
{
	xlog_recover_item_t	*item;

	item = kmem_zalloc(sizeof(xlog_recover_item_t), KM_SLEEP);
	INIT_LIST_HEAD(&item->ri_list);
	list_add_tail(&item->ri_list, head);
}

STATIC int
xlog_recover_unmount_trans(
	struct xlog		*log)
xlog_recover_add_to_cont_trans(
	struct xlog		*log,
	struct xlog_recover	*trans,
	xfs_caddr_t		dp,
	int			len)
{
	/* Do nothing now */
	xfs_warn(log->l_mp, "%s: Unmount LR", __func__);
	xlog_recover_item_t	*item;
	xfs_caddr_t		ptr, old_ptr;
	int			old_len;

	if (list_empty(&trans->r_itemq)) {
		/* 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);
		return 0;
	}
	/* take the tail entry */
	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);

	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, KM_SLEEP);
	memcpy(&ptr[old_len], dp, len);
	item->ri_buf[item->ri_cnt-1].i_len += len;
	item->ri_buf[item->ri_cnt-1].i_addr = ptr;
	trace_xfs_log_recover_item_add_cont(log, trans, item, 0);
	return 0;
}

/*
 * There are two valid states of the r_state field.  0 indicates that the
 * transaction structure is in a normal state.  We have either seen the
 * start of the transaction or the last operation we added was not a partial
 * operation.  If the last operation we added to the transaction was a
 * partial operation, we need to mark r_state with XLOG_WAS_CONT_TRANS.
 * The next region to add is the start of a new region.  It could be
 * a whole region or it could be the first part of a new region.  Because
 * of this, the assumption here is that the type and size fields of all
 * format structures fit into the first 32 bits of the structure.
 *
 * NOTE: skip LRs with 0 data length.
 * This works because all regions must be 32 bit aligned.  Therefore, we
 * either have both fields or we have neither field.  In the case we have
 * neither field, the data part of the region is zero length.  We only have
 * a log_op_header and can throw away the header since a new one will appear
 * later.  If we have at least 4 bytes, then we can determine how many regions
 * will appear in the current log item.
 */
STATIC int
xlog_recover_process_data(
xlog_recover_add_to_trans(
	struct xlog		*log,
	struct hlist_head	rhash[],
	struct xlog_rec_header	*rhead,
	struct xlog_recover	*trans,
	xfs_caddr_t		dp,
	int			pass)
	int			len)
{
	xfs_caddr_t		lp;
	int			num_logops;
	xlog_op_header_t	*ohead;
	xlog_recover_t		*trans;
	xlog_tid_t		tid;
	int			error;
	unsigned long		hash;
	uint			flags;

	lp = dp + be32_to_cpu(rhead->h_len);
	num_logops = be32_to_cpu(rhead->h_num_logops);
	xfs_inode_log_format_t	*in_f;			/* any will do */
	xlog_recover_item_t	*item;
	xfs_caddr_t		ptr;

	/* check the log format matches our own - else we can't recover */
	if (xlog_header_check_recover(log->l_mp, rhead))
	if (!len)
		return 0;
	if (list_empty(&trans->r_itemq)) {
		/* we need to catch log corruptions here */
		if (*(uint *)dp != XFS_TRANS_HEADER_MAGIC) {
			xfs_warn(log->l_mp, "%s: bad header magic number",
				__func__);
			ASSERT(0);
			return -EIO;
		}
		if (len == sizeof(xfs_trans_header_t))
			xlog_recover_add_item(&trans->r_itemq);
		memcpy(&trans->r_theader, dp, len);
		return 0;
	}

	while ((dp < lp) && num_logops) {
		ASSERT(dp + sizeof(xlog_op_header_t) <= lp);
		ohead = (xlog_op_header_t *)dp;
		dp += sizeof(xlog_op_header_t);
		if (ohead->oh_clientid != XFS_TRANSACTION &&
		    ohead->oh_clientid != XFS_LOG) {
			xfs_warn(log->l_mp, "%s: bad clientid 0x%x",
					__func__, ohead->oh_clientid);
	ptr = kmem_alloc(len, KM_SLEEP);
	memcpy(ptr, dp, len);
	in_f = (xfs_inode_log_format_t *)ptr;

	/* take the tail entry */
	item = list_entry(trans->r_itemq.prev, xlog_recover_item_t, ri_list);
	if (item->ri_total != 0 &&
	     item->ri_total == item->ri_cnt) {
		/* tail item is in use, get a new one */
		xlog_recover_add_item(&trans->r_itemq);
		item = list_entry(trans->r_itemq.prev,
					xlog_recover_item_t, ri_list);
	}

	if (item->ri_total == 0) {		/* first region to be added */
		if (in_f->ilf_size == 0 ||
		    in_f->ilf_size > XLOG_MAX_REGIONS_IN_ITEM) {
			xfs_warn(log->l_mp,
		"bad number of regions (%d) in inode log format",
				  in_f->ilf_size);
			ASSERT(0);
			kmem_free(ptr);
			return -EIO;
		}
		tid = be32_to_cpu(ohead->oh_tid);
		hash = XLOG_RHASH(tid);
		trans = xlog_recover_find_tid(&rhash[hash], tid);
		if (trans == NULL) {		   /* not found; add new tid */
			if (ohead->oh_flags & XLOG_START_TRANS)
				xlog_recover_new_tid(&rhash[hash], tid,
					be64_to_cpu(rhead->h_lsn));
		} else {
			if (dp + be32_to_cpu(ohead->oh_len) > lp) {
				xfs_warn(log->l_mp, "%s: bad length 0x%x",
					__func__, be32_to_cpu(ohead->oh_len));
				WARN_ON(1);
				return -EIO;

		item->ri_total = in_f->ilf_size;
		item->ri_buf =
			kmem_zalloc(item->ri_total * sizeof(xfs_log_iovec_t),
				    KM_SLEEP);
	}
	ASSERT(item->ri_total > item->ri_cnt);
	/* Description region is ri_buf[0] */
	item->ri_buf[item->ri_cnt].i_addr = ptr;
	item->ri_buf[item->ri_cnt].i_len  = len;
	item->ri_cnt++;
	trace_xfs_log_recover_item_add(log, trans, item, 0);
	return 0;
}

/*
 * Free up any resources allocated by the transaction
 *
 * Remember that EFIs, EFDs, and IUNLINKs are handled later.
 */
STATIC void
xlog_recover_free_trans(
	struct xlog_recover	*trans)
{
	xlog_recover_item_t	*item, *n;
	int			i;

	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
		/* Free the regions in the item. */
		list_del(&item->ri_list);
		for (i = 0; i < item->ri_cnt; i++)
			kmem_free(item->ri_buf[i].i_addr);
		/* Free the item itself */
		kmem_free(item->ri_buf);
		kmem_free(item);
	}
	/* Free the transaction recover structure */
	kmem_free(trans);
}
			flags = ohead->oh_flags & ~XLOG_END_TRANS;

/*
 * On error or completion, trans is freed.
 */
STATIC int
xlog_recovery_process_trans(
	struct xlog		*log,
	struct xlog_recover	*trans,
	xfs_caddr_t		dp,
	unsigned int		len,
	unsigned int		flags,
	int			pass)
{
	int			error = 0;
	bool			freeit = false;

	/* mask off ophdr transaction container flags */
	flags &= ~XLOG_END_TRANS;
	if (flags & XLOG_WAS_CONT_TRANS)
		flags &= ~XLOG_CONTINUE_TRANS;

	/*
	 * Callees must not free the trans structure. We'll decide if we need to
	 * free it or not based on the operation being done and it's result.
	 */
	switch (flags) {
			case XLOG_COMMIT_TRANS:
				error = xlog_recover_commit_trans(log,
								trans, pass);
				break;
			case XLOG_UNMOUNT_TRANS:
				error = xlog_recover_unmount_trans(log);
	/* expected flag values */
	case 0:
	case XLOG_CONTINUE_TRANS:
		error = xlog_recover_add_to_trans(log, trans, dp, len);
		break;
	case XLOG_WAS_CONT_TRANS:
				error = xlog_recover_add_to_cont_trans(log,
						trans, dp,
						be32_to_cpu(ohead->oh_len));
		error = xlog_recover_add_to_cont_trans(log, trans, dp, len);
		break;
			case XLOG_START_TRANS:
				xfs_warn(log->l_mp, "%s: bad transaction",
					__func__);
				ASSERT(0);
				error = -EIO;
	case XLOG_COMMIT_TRANS:
		error = xlog_recover_commit_trans(log, trans, pass);
		/* success or fail, we are now done with this transaction. */
		freeit = true;
		break;
			case 0:
			case XLOG_CONTINUE_TRANS:
				error = xlog_recover_add_to_trans(log, trans,
						dp, be32_to_cpu(ohead->oh_len));

	/* unexpected flag values */
	case XLOG_UNMOUNT_TRANS:
		/* just skip trans */
		xfs_warn(log->l_mp, "%s: Unmount LR", __func__);
		freeit = true;
		break;
	case XLOG_START_TRANS:
	default:
				xfs_warn(log->l_mp, "%s: bad flag 0x%x",
					__func__, flags);
		xfs_warn(log->l_mp, "%s: bad flag 0x%x", __func__, flags);
		ASSERT(0);
		error = -EIO;
		break;
	}
			if (error) {
	if (error || freeit)
		xlog_recover_free_trans(trans);
	return error;
}

/*
 * Lookup the transaction recovery structure associated with the ID in the
 * current ophdr. If the transaction doesn't exist and the start flag is set in
 * the ophdr, then allocate a new transaction for future ID matches to find.
 * Either way, return what we found during the lookup - an existing transaction
 * or nothing.
 */
STATIC struct xlog_recover *
xlog_recover_ophdr_to_trans(
	struct hlist_head	rhash[],
	struct xlog_rec_header	*rhead,
	struct xlog_op_header	*ohead)
{
	struct xlog_recover	*trans;
	xlog_tid_t		tid;
	struct hlist_head	*rhp;

	tid = be32_to_cpu(ohead->oh_tid);
	rhp = &rhash[XLOG_RHASH(tid)];
	hlist_for_each_entry(trans, rhp, r_list) {
		if (trans->r_log_tid == tid)
			return trans;
	}

	/*
	 * skip over non-start transaction headers - we could be
	 * processing slack space before the next transaction starts
	 */
	if (!(ohead->oh_flags & XLOG_START_TRANS))
		return NULL;

	ASSERT(be32_to_cpu(ohead->oh_len) == 0);

	/*
	 * This is a new transaction so allocate a new recovery container to
	 * hold the recovery ops that will follow.
	 */
	trans = kmem_zalloc(sizeof(struct xlog_recover), KM_SLEEP);
	trans->r_log_tid = tid;
	trans->r_lsn = be64_to_cpu(rhead->h_lsn);
	INIT_LIST_HEAD(&trans->r_itemq);
	INIT_HLIST_NODE(&trans->r_list);
	hlist_add_head(&trans->r_list, rhp);

	/*
	 * Nothing more to do for this ophdr. Items to be added to this new
	 * transaction will be in subsequent ophdr containers.
	 */
	return NULL;
}

STATIC int
xlog_recover_process_ophdr(
	struct xlog		*log,
	struct hlist_head	rhash[],
	struct xlog_rec_header	*rhead,
	struct xlog_op_header	*ohead,
	xfs_caddr_t		dp,
	xfs_caddr_t		end,
	int			pass)
{
	struct xlog_recover	*trans;
	unsigned int		len;

	/* Do we understand who wrote this op? */
	if (ohead->oh_clientid != XFS_TRANSACTION &&
	    ohead->oh_clientid != XFS_LOG) {
		xfs_warn(log->l_mp, "%s: bad clientid 0x%x",
			__func__, ohead->oh_clientid);
		ASSERT(0);
		return -EIO;
	}

	/*
	 * Check the ophdr contains all the data it is supposed to contain.
	 */
	len = be32_to_cpu(ohead->oh_len);
	if (dp + len > end) {
		xfs_warn(log->l_mp, "%s: bad length 0x%x", __func__, len);
		WARN_ON(1);
		return -EIO;
	}

	trans = xlog_recover_ophdr_to_trans(rhash, rhead, ohead);
	if (!trans) {
		/* nothing to do, so skip over this ophdr */
		return 0;
	}

	return xlog_recovery_process_trans(log, trans, dp, len,
					   ohead->oh_flags, pass);
}

/*
 * There are two valid states of the r_state field.  0 indicates that the
 * transaction structure is in a normal state.  We have either seen the
 * start of the transaction or the last operation we added was not a partial
 * operation.  If the last operation we added to the transaction was a
 * partial operation, we need to mark r_state with XLOG_WAS_CONT_TRANS.
 *
 * NOTE: skip LRs with 0 data length.
 */
STATIC int
xlog_recover_process_data(
	struct xlog		*log,
	struct hlist_head	rhash[],
	struct xlog_rec_header	*rhead,
	xfs_caddr_t		dp,
	int			pass)
{
	struct xlog_op_header	*ohead;
	xfs_caddr_t		end;
	int			num_logops;
	int			error;

	end = dp + be32_to_cpu(rhead->h_len);
	num_logops = be32_to_cpu(rhead->h_num_logops);

	/* check the log format matches our own - else we can't recover */
	if (xlog_header_check_recover(log->l_mp, rhead))
		return -EIO;

	while ((dp < end) && num_logops) {

		ohead = (struct xlog_op_header *)dp;
		dp += sizeof(*ohead);
		ASSERT(dp <= end);

		/* errors will abort recovery */
		error = xlog_recover_process_ophdr(log, rhash, rhead, ohead,
						    dp, end, pass);
		if (error)
			return error;

		dp += be32_to_cpu(ohead->oh_len);
		num_logops--;
	}