Merge branch 'guilt/xlog-write-rework' into xfs-5.19-for-next

fs/xfs/libxfs/xfs_log_format.h

@@ -69,7 +69,6 @@ static inline uint xlog_get_cycle(char *ptr)
 
 /* Log Clients */
 #define XFS_TRANSACTION		0x69
-#define XFS_VOLUME		0x2
 #define XFS_LOG			0xaa
 
 #define XLOG_UNMOUNT_TYPE	0x556e	/* Un for Unmount */

fs/xfs/xfs_log.c

@@ -49,7 +49,6 @@ xlog_state_get_iclog_space(
 	int			len,
 	struct xlog_in_core	**iclog,
 	struct xlog_ticket	*ticket,
-	int			*continued_write,
 	int			*logoffsetp);
 STATIC void
 xlog_grant_push_ail(
@@ -61,10 +60,6 @@ xlog_sync(
 	struct xlog_in_core	*iclog);
 #if defined(DEBUG)
 STATIC void
-xlog_verify_dest_ptr(
-	struct xlog		*log,
-	void			*ptr);
-STATIC void
 xlog_verify_grant_tail(
 	struct xlog *log);
 STATIC void
@@ -77,7 +72,6 @@ xlog_verify_tail_lsn(
 	struct xlog		*log,
 	struct xlog_in_core	*iclog);
 #else
-#define xlog_verify_dest_ptr(a,b)
 #define xlog_verify_grant_tail(a)
 #define xlog_verify_iclog(a,b,c)
 #define xlog_verify_tail_lsn(a,b)
@@ -90,6 +84,62 @@ xlog_iclogs_empty(
 static int
 xfs_log_cover(struct xfs_mount *);
 
+/*
+ * We need to make sure the buffer pointer returned is naturally aligned for the
+ * biggest basic data type we put into it. We have already accounted for this
+ * padding when sizing the buffer.
+ *
+ * However, this padding does not get written into the log, and hence we have to
+ * track the space used by the log vectors separately to prevent log space hangs
+ * due to inaccurate accounting (i.e. a leak) of the used log space through the
+ * CIL context ticket.
+ *
+ * We also add space for the xlog_op_header that describes this region in the
+ * log. This prepends the data region we return to the caller to copy their data
+ * into, so do all the static initialisation of the ophdr now. Because the ophdr
+ * is not 8 byte aligned, we have to be careful to ensure that we align the
+ * start of the buffer such that the region we return to the call is 8 byte
+ * aligned and packed against the tail of the ophdr.
+ */
+void *
+xlog_prepare_iovec(
+	struct xfs_log_vec	*lv,
+	struct xfs_log_iovec	**vecp,
+	uint			type)
+{
+	struct xfs_log_iovec	*vec = *vecp;
+	struct xlog_op_header	*oph;
+	uint32_t		len;
+	void			*buf;
+
+	if (vec) {
+		ASSERT(vec - lv->lv_iovecp < lv->lv_niovecs);
+		vec++;
+	} else {
+		vec = &lv->lv_iovecp[0];
+	}
+
+	len = lv->lv_buf_len + sizeof(struct xlog_op_header);
+	if (!IS_ALIGNED(len, sizeof(uint64_t))) {
+		lv->lv_buf_len = round_up(len, sizeof(uint64_t)) -
+					sizeof(struct xlog_op_header);
+	}
+
+	vec->i_type = type;
+	vec->i_addr = lv->lv_buf + lv->lv_buf_len;
+
+	oph = vec->i_addr;
+	oph->oh_clientid = XFS_TRANSACTION;
+	oph->oh_res2 = 0;
+	oph->oh_flags = 0;
+
+	buf = vec->i_addr + sizeof(struct xlog_op_header);
+	ASSERT(IS_ALIGNED((unsigned long)buf, sizeof(uint64_t)));
+
+	*vecp = vec;
+	return buf;
+}
+
 static void
 xlog_grant_sub_space(
 	struct xlog		*log,
@@ -322,30 +372,6 @@ xlog_grant_head_check(
 	return error;
 }
 
-static void
-xlog_tic_reset_res(xlog_ticket_t *tic)
-{
-	tic->t_res_num = 0;
-	tic->t_res_arr_sum = 0;
-	tic->t_res_num_ophdrs = 0;
-}
-
-static void
-xlog_tic_add_region(xlog_ticket_t *tic, uint len, uint type)
-{
-	if (tic->t_res_num == XLOG_TIC_LEN_MAX) {
-		/* add to overflow and start again */
-		tic->t_res_o_flow += tic->t_res_arr_sum;
-		tic->t_res_num = 0;
-		tic->t_res_arr_sum = 0;
-	}
-
-	tic->t_res_arr[tic->t_res_num].r_len = len;
-	tic->t_res_arr[tic->t_res_num].r_type = type;
-	tic->t_res_arr_sum += len;
-	tic->t_res_num++;
-}
-
 bool
 xfs_log_writable(
 	struct xfs_mount	*mp)
@@ -395,8 +421,6 @@ xfs_log_regrant(
 	xlog_grant_push_ail(log, tic->t_unit_res);
 
 	tic->t_curr_res = tic->t_unit_res;
-	xlog_tic_reset_res(tic);
-
 	if (tic->t_cnt > 0)
 		return 0;
 
@@ -437,7 +461,6 @@ xfs_log_reserve(
 	int			unit_bytes,
 	int			cnt,
 	struct xlog_ticket	**ticp,
-	uint8_t		 	client,
 	bool			permanent)
 {
 	struct xlog		*log = mp->m_log;
@@ -445,15 +468,13 @@ xfs_log_reserve(
 	int			need_bytes;
 	int			error = 0;
 
-	ASSERT(client == XFS_TRANSACTION || client == XFS_LOG);
-
 	if (xlog_is_shutdown(log))
 		return -EIO;
 
 	XFS_STATS_INC(mp, xs_try_logspace);
 
 	ASSERT(*ticp == NULL);
-	tic = xlog_ticket_alloc(log, unit_bytes, cnt, client, permanent);
+	tic = xlog_ticket_alloc(log, unit_bytes, cnt, permanent);
 	*ticp = tic;
 
 	xlog_grant_push_ail(log, tic->t_cnt ? tic->t_unit_res * tic->t_cnt
@@ -901,12 +922,22 @@ xlog_write_unmount_record(
 	struct xlog		*log,
 	struct xlog_ticket	*ticket)
 {
-	struct xfs_unmount_log_format ulf = {
+	struct  {
+		struct xlog_op_header ophdr;
+		struct xfs_unmount_log_format ulf;
+	} unmount_rec = {
+		.ophdr = {
+			.oh_clientid = XFS_LOG,
+			.oh_tid = cpu_to_be32(ticket->t_tid),
+			.oh_flags = XLOG_UNMOUNT_TRANS,
+		},
+		.ulf = {
 			.magic = XLOG_UNMOUNT_TYPE,
+		},
 	};
 	struct xfs_log_iovec reg = {
-		.i_addr = &ulf,
-		.i_len = sizeof(ulf),
+		.i_addr = &unmount_rec,
+		.i_len = sizeof(unmount_rec),
 		.i_type = XLOG_REG_TYPE_UNMOUNT,
 	};
 	struct xfs_log_vec vec = {
@@ -914,10 +945,14 @@ xlog_write_unmount_record(
 		.lv_iovecp = &reg,
 	};
 
+	BUILD_BUG_ON((sizeof(struct xlog_op_header) +
+		      sizeof(struct xfs_unmount_log_format)) !=
+							sizeof(unmount_rec));
+
 	/* account for space used by record data */
-	ticket->t_curr_res -= sizeof(ulf);
+	ticket->t_curr_res -= sizeof(unmount_rec);
 
-	return xlog_write(log, NULL, &vec, ticket, XLOG_UNMOUNT_TRANS);
+	return xlog_write(log, NULL, &vec, ticket, reg.i_len);
 }
 
 /*
@@ -933,7 +968,7 @@ xlog_unmount_write(
 	struct xlog_ticket	*tic = NULL;
 	int			error;
 
-	error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
+	error = xfs_log_reserve(mp, 600, 1, &tic, 0);
 	if (error)
 		goto out_err;
 
@@ -1584,9 +1619,6 @@ xlog_alloc_log(
 				GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 		if (!iclog->ic_data)
 			goto out_free_iclog;
-#ifdef DEBUG
-		log->l_iclog_bak[i] = &iclog->ic_header;
-#endif
 		head = &iclog->ic_header;
 		memset(head, 0, sizeof(xlog_rec_header_t));
 		head->h_magicno = cpu_to_be32(XLOG_HEADER_MAGIC_NUM);
@@ -1602,7 +1634,7 @@ xlog_alloc_log(
 		iclog->ic_log = log;
 		atomic_set(&iclog->ic_refcnt, 0);
 		INIT_LIST_HEAD(&iclog->ic_callbacks);
-		iclog->ic_datap = (char *)iclog->ic_data + log->l_iclog_hsize;
+		iclog->ic_datap = (void *)iclog->ic_data + log->l_iclog_hsize;
 
 		init_waitqueue_head(&iclog->ic_force_wait);
 		init_waitqueue_head(&iclog->ic_write_wait);
@@ -2111,63 +2143,11 @@ xlog_print_tic_res(
 	struct xfs_mount	*mp,
 	struct xlog_ticket	*ticket)
 {
-	uint i;
-	uint ophdr_spc = ticket->t_res_num_ophdrs * (uint)sizeof(xlog_op_header_t);
-
-	/* match with XLOG_REG_TYPE_* in xfs_log.h */
-#define REG_TYPE_STR(type, str)	[XLOG_REG_TYPE_##type] = str
-	static char *res_type_str[] = {
-	    REG_TYPE_STR(BFORMAT, "bformat"),
-	    REG_TYPE_STR(BCHUNK, "bchunk"),
-	    REG_TYPE_STR(EFI_FORMAT, "efi_format"),
-	    REG_TYPE_STR(EFD_FORMAT, "efd_format"),
-	    REG_TYPE_STR(IFORMAT, "iformat"),
-	    REG_TYPE_STR(ICORE, "icore"),
-	    REG_TYPE_STR(IEXT, "iext"),
-	    REG_TYPE_STR(IBROOT, "ibroot"),
-	    REG_TYPE_STR(ILOCAL, "ilocal"),
-	    REG_TYPE_STR(IATTR_EXT, "iattr_ext"),
-	    REG_TYPE_STR(IATTR_BROOT, "iattr_broot"),
-	    REG_TYPE_STR(IATTR_LOCAL, "iattr_local"),
-	    REG_TYPE_STR(QFORMAT, "qformat"),
-	    REG_TYPE_STR(DQUOT, "dquot"),
-	    REG_TYPE_STR(QUOTAOFF, "quotaoff"),
-	    REG_TYPE_STR(LRHEADER, "LR header"),
-	    REG_TYPE_STR(UNMOUNT, "unmount"),
-	    REG_TYPE_STR(COMMIT, "commit"),
-	    REG_TYPE_STR(TRANSHDR, "trans header"),
-	    REG_TYPE_STR(ICREATE, "inode create"),
-	    REG_TYPE_STR(RUI_FORMAT, "rui_format"),
-	    REG_TYPE_STR(RUD_FORMAT, "rud_format"),
-	    REG_TYPE_STR(CUI_FORMAT, "cui_format"),
-	    REG_TYPE_STR(CUD_FORMAT, "cud_format"),
-	    REG_TYPE_STR(BUI_FORMAT, "bui_format"),
-	    REG_TYPE_STR(BUD_FORMAT, "bud_format"),
-	};
-	BUILD_BUG_ON(ARRAY_SIZE(res_type_str) != XLOG_REG_TYPE_MAX + 1);
-#undef REG_TYPE_STR
-
 	xfs_warn(mp, "ticket reservation summary:");
-	xfs_warn(mp, "  unit res    = %d bytes",
-		 ticket->t_unit_res);
-	xfs_warn(mp, "  current res = %d bytes",
-		 ticket->t_curr_res);
-	xfs_warn(mp, "  total reg   = %u bytes (o/flow = %u bytes)",
-		 ticket->t_res_arr_sum, ticket->t_res_o_flow);
-	xfs_warn(mp, "  ophdrs      = %u (ophdr space = %u bytes)",
-		 ticket->t_res_num_ophdrs, ophdr_spc);
-	xfs_warn(mp, "  ophdr + reg = %u bytes",
-		 ticket->t_res_arr_sum + ticket->t_res_o_flow + ophdr_spc);
-	xfs_warn(mp, "  num regions = %u",
-		 ticket->t_res_num);
-
-	for (i = 0; i < ticket->t_res_num; i++) {
-		uint r_type = ticket->t_res_arr[i].r_type;
-		xfs_warn(mp, "region[%u]: %s - %u bytes", i,
-			    ((r_type <= 0 || r_type > XLOG_REG_TYPE_MAX) ?
-			    "bad-rtype" : res_type_str[r_type]),
-			    ticket->t_res_arr[i].r_len);
-	}
+	xfs_warn(mp, "  unit res    = %d bytes", ticket->t_unit_res);
+	xfs_warn(mp, "  current res = %d bytes", ticket->t_curr_res);
+	xfs_warn(mp, "  original count  = %d", ticket->t_ocnt);
+	xfs_warn(mp, "  remaining count = %d", ticket->t_cnt);
 }
 
 /*
@@ -2220,187 +2200,226 @@ xlog_print_trans(
 	}
 }
 
+static inline void
+xlog_write_iovec(
+	struct xlog_in_core	*iclog,
+	uint32_t		*log_offset,
+	void			*data,
+	uint32_t		write_len,
+	int			*bytes_left,
+	uint32_t		*record_cnt,
+	uint32_t		*data_cnt)
+{
+	ASSERT(*log_offset < iclog->ic_log->l_iclog_size);
+	ASSERT(*log_offset % sizeof(int32_t) == 0);
+	ASSERT(write_len % sizeof(int32_t) == 0);
+
+	memcpy(iclog->ic_datap + *log_offset, data, write_len);
+	*log_offset += write_len;
+	*bytes_left -= write_len;
+	(*record_cnt)++;
+	*data_cnt += write_len;
+}
+
 /*
- * Calculate the potential space needed by the log vector.  We may need a start
- * record, and each region gets its own struct xlog_op_header and may need to be
- * double word aligned.
+ * Write log vectors into a single iclog which is guaranteed by the caller
+ * to have enough space to write the entire log vector into.
  */
-static int
-xlog_write_calc_vec_length(
+static void
+xlog_write_full(
+	struct xfs_log_vec	*lv,
 	struct xlog_ticket	*ticket,
-	struct xfs_log_vec	*log_vector,
-	uint			optype)
+	struct xlog_in_core	*iclog,
+	uint32_t		*log_offset,
+	uint32_t		*len,
+	uint32_t		*record_cnt,
+	uint32_t		*data_cnt)
 {
-	struct xfs_log_vec	*lv;
-	int			headers = 0;
-	int			len = 0;
-	int			i;
+	int			index;
 
-	if (optype & XLOG_START_TRANS)
-		headers++;
+	ASSERT(*log_offset + *len <= iclog->ic_size ||
+		iclog->ic_state == XLOG_STATE_WANT_SYNC);
 
-	for (lv = log_vector; lv; lv = lv->lv_next) {
-		/* we don't write ordered log vectors */
-		if (lv->lv_buf_len == XFS_LOG_VEC_ORDERED)
-			continue;
-
-		headers += lv->lv_niovecs;
-
-		for (i = 0; i < lv->lv_niovecs; i++) {
-			struct xfs_log_iovec	*vecp = &lv->lv_iovecp[i];
-
-			len += vecp->i_len;
-			xlog_tic_add_region(ticket, vecp->i_len, vecp->i_type);
-		}
-	}
-
-	ticket->t_res_num_ophdrs += headers;
-	len += headers * sizeof(struct xlog_op_header);
-
-	return len;
-}
+	/*
+	 * Ordered log vectors have no regions to write so this
+	 * loop will naturally skip them.
+	 */
+	for (index = 0; index < lv->lv_niovecs; index++) {
+		struct xfs_log_iovec	*reg = &lv->lv_iovecp[index];
+		struct xlog_op_header	*ophdr = reg->i_addr;
 
-static void
-xlog_write_start_rec(
-	struct xlog_op_header	*ophdr,
-	struct xlog_ticket	*ticket)
-{
 		ophdr->oh_tid = cpu_to_be32(ticket->t_tid);
-	ophdr->oh_clientid = ticket->t_clientid;
-	ophdr->oh_len = 0;
-	ophdr->oh_flags = XLOG_START_TRANS;
-	ophdr->oh_res2 = 0;
+		xlog_write_iovec(iclog, log_offset, reg->i_addr,
+				reg->i_len, len, record_cnt, data_cnt);
+	}
 }
 
-static xlog_op_header_t *
-xlog_write_setup_ophdr(
-	struct xlog		*log,
-	struct xlog_op_header	*ophdr,
+static int
+xlog_write_get_more_iclog_space(
 	struct xlog_ticket	*ticket,
-	uint			flags)
+	struct xlog_in_core	**iclogp,
+	uint32_t		*log_offset,
+	uint32_t		len,
+	uint32_t		*record_cnt,
+	uint32_t		*data_cnt)
 {
-	ophdr->oh_tid = cpu_to_be32(ticket->t_tid);
-	ophdr->oh_clientid = ticket->t_clientid;
-	ophdr->oh_res2 = 0;
-
-	/* are we copying a commit or unmount record? */
-	ophdr->oh_flags = flags;
+	struct xlog_in_core	*iclog = *iclogp;
+	struct xlog		*log = iclog->ic_log;
+	int			error;
 
-	/*
-	 * We've seen logs corrupted with bad transaction client ids.  This
-	 * makes sure that XFS doesn't generate them on.  Turn this into an EIO
-	 * and shut down the filesystem.
-	 */
-	switch (ophdr->oh_clientid)  {
-	case XFS_TRANSACTION:
-	case XFS_VOLUME:
-	case XFS_LOG:
-		break;
-	default:
-		xfs_warn(log->l_mp,
-			"Bad XFS transaction clientid 0x%x in ticket "PTR_FMT,
-			ophdr->oh_clientid, ticket);
-		return NULL;
-	}
+	spin_lock(&log->l_icloglock);
+	ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC);
+	xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt);
+	error = xlog_state_release_iclog(log, iclog);
+	spin_unlock(&log->l_icloglock);
+	if (error)
+		return error;
 
-	return ophdr;
+	error = xlog_state_get_iclog_space(log, len, &iclog, ticket,
+					log_offset);
+	if (error)
+		return error;
+	*record_cnt = 0;
+	*data_cnt = 0;
+	*iclogp = iclog;
+	return 0;
 }
 
 /*
- * Set up the parameters of the region copy into the log. This has
- * to handle region write split across multiple log buffers - this
- * state is kept external to this function so that this code can
- * be written in an obvious, self documenting manner.
+ * Write log vectors into a single iclog which is smaller than the current chain
+ * length. We write until we cannot fit a full record into the remaining space
+ * and then stop. We return the log vector that is to be written that cannot
+ * wholly fit in the iclog.
  */
 static int
-xlog_write_setup_copy(
+xlog_write_partial(
+	struct xfs_log_vec	*lv,
 	struct xlog_ticket	*ticket,
-	struct xlog_op_header	*ophdr,
-	int			space_available,
-	int			space_required,
-	int			*copy_off,
-	int			*copy_len,
-	int			*last_was_partial_copy,
-	int			*bytes_consumed)
-{
-	int			still_to_copy;
-
-	still_to_copy = space_required - *bytes_consumed;
-	*copy_off = *bytes_consumed;
-
-	if (still_to_copy <= space_available) {
-		/* write of region completes here */
-		*copy_len = still_to_copy;
-		ophdr->oh_len = cpu_to_be32(*copy_len);
-		if (*last_was_partial_copy)
-			ophdr->oh_flags |= (XLOG_END_TRANS|XLOG_WAS_CONT_TRANS);
-		*last_was_partial_copy = 0;
-		*bytes_consumed = 0;
-		return 0;
+	struct xlog_in_core	**iclogp,
+	uint32_t		*log_offset,
+	uint32_t		*len,
+	uint32_t		*record_cnt,
+	uint32_t		*data_cnt)
+{
+	struct xlog_in_core	*iclog = *iclogp;
+	struct xlog_op_header	*ophdr;
+	int			index = 0;
+	uint32_t		rlen;
+	int			error;
+
+	/* walk the logvec, copying until we run out of space in the iclog */
+	for (index = 0; index < lv->lv_niovecs; index++) {
+		struct xfs_log_iovec	*reg = &lv->lv_iovecp[index];
+		uint32_t		reg_offset = 0;
+
+		/*
+		 * The first region of a continuation must have a non-zero
+		 * length otherwise log recovery will just skip over it and
+		 * start recovering from the next opheader it finds. Because we
+		 * mark the next opheader as a continuation, recovery will then
+		 * incorrectly add the continuation to the previous region and
+		 * that breaks stuff.
+		 *
+		 * Hence if there isn't space for region data after the
+		 * opheader, then we need to start afresh with a new iclog.
+		 */
+		if (iclog->ic_size - *log_offset <=
+					sizeof(struct xlog_op_header)) {
+			error = xlog_write_get_more_iclog_space(ticket,
+					&iclog, log_offset, *len, record_cnt,
+					data_cnt);
+			if (error)
+				return error;
 		}
 
-	/* partial write of region, needs extra log op header reservation */
-	*copy_len = space_available;
-	ophdr->oh_len = cpu_to_be32(*copy_len);
+		ophdr = reg->i_addr;
+		rlen = min_t(uint32_t, reg->i_len, iclog->ic_size - *log_offset);
+
+		ophdr->oh_tid = cpu_to_be32(ticket->t_tid);
+		ophdr->oh_len = cpu_to_be32(rlen - sizeof(struct xlog_op_header));
+		if (rlen != reg->i_len)
 			ophdr->oh_flags |= XLOG_CONTINUE_TRANS;
-	if (*last_was_partial_copy)
-		ophdr->oh_flags |= XLOG_WAS_CONT_TRANS;
-	*bytes_consumed += *copy_len;
-	(*last_was_partial_copy)++;
 
-	/* account for new log op header */
-	ticket->t_curr_res -= sizeof(struct xlog_op_header);
-	ticket->t_res_num_ophdrs++;
+		xlog_write_iovec(iclog, log_offset, reg->i_addr,
+				rlen, len, record_cnt, data_cnt);
 
-	return sizeof(struct xlog_op_header);
-}
+		/* If we wrote the whole region, move to the next. */
+		if (rlen == reg->i_len)
+			continue;
 
-static int
-xlog_write_copy_finish(
-	struct xlog		*log,
-	struct xlog_in_core	*iclog,
-	uint			flags,
-	int			*record_cnt,
-	int			*data_cnt,
-	int			*partial_copy,
-	int			*partial_copy_len,
-	int			log_offset)
-{
-	int			error;
+		/*
+		 * We now have a partially written iovec, but it can span
+		 * multiple iclogs so we loop here. First we release the iclog
+		 * we currently have, then we get a new iclog and add a new
+		 * opheader. Then we continue copying from where we were until
+		 * we either complete the iovec or fill the iclog. If we
+		 * complete the iovec, then we increment the index and go right
+		 * back to the top of the outer loop. if we fill the iclog, we
+		 * run the inner loop again.
+		 *
+		 * This is complicated by the tail of a region using all the
+		 * space in an iclog and hence requiring us to release the iclog
+		 * and get a new one before returning to the outer loop. We must
+		 * always guarantee that we exit this inner loop with at least
+		 * space for log transaction opheaders left in the current
+		 * iclog, hence we cannot just terminate the loop at the end
+		 * of the of the continuation. So we loop while there is no
+		 * space left in the current iclog, and check for the end of the
+		 * continuation after getting a new iclog.
+		 */
+		do {
+			/*
+			 * Ensure we include the continuation opheader in the
+			 * space we need in the new iclog by adding that size
+			 * to the length we require. This continuation opheader
+			 * needs to be accounted to the ticket as the space it
+			 * consumes hasn't been accounted to the lv we are
+			 * writing.
+			 */
+			error = xlog_write_get_more_iclog_space(ticket,
+					&iclog, log_offset,
+					*len + sizeof(struct xlog_op_header),
+					record_cnt, data_cnt);
+			if (error)
+				return error;
+
+			ophdr = iclog->ic_datap + *log_offset;
+			ophdr->oh_tid = cpu_to_be32(ticket->t_tid);
+			ophdr->oh_clientid = XFS_TRANSACTION;
+			ophdr->oh_res2 = 0;
+			ophdr->oh_flags = XLOG_WAS_CONT_TRANS;
+
+			ticket->t_curr_res -= sizeof(struct xlog_op_header);
+			*log_offset += sizeof(struct xlog_op_header);
+			*data_cnt += sizeof(struct xlog_op_header);
 
-	if (*partial_copy) {
 			/*
-		 * This iclog has already been marked WANT_SYNC by
-		 * xlog_state_get_iclog_space.
+			 * If rlen fits in the iclog, then end the region
+			 * continuation. Otherwise we're going around again.
 			 */
-		spin_lock(&log->l_icloglock);
-		xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt);
-		*record_cnt = 0;
-		*data_cnt = 0;
-		goto release_iclog;
-	}
+			reg_offset += rlen;
+			rlen = reg->i_len - reg_offset;
+			if (rlen <= iclog->ic_size - *log_offset)
+				ophdr->oh_flags |= XLOG_END_TRANS;
+			else
+				ophdr->oh_flags |= XLOG_CONTINUE_TRANS;
 
-	*partial_copy = 0;
-	*partial_copy_len = 0;
+			rlen = min_t(uint32_t, rlen, iclog->ic_size - *log_offset);
+			ophdr->oh_len = cpu_to_be32(rlen);
 
-	if (iclog->ic_size - log_offset > sizeof(xlog_op_header_t))
-		return 0;
+			xlog_write_iovec(iclog, log_offset,
+					reg->i_addr + reg_offset,
+					rlen, len, record_cnt, data_cnt);
 
-	/* no more space in this iclog - push it. */
-	spin_lock(&log->l_icloglock);
-	xlog_state_finish_copy(log, iclog, *record_cnt, *data_cnt);
-	*record_cnt = 0;
-	*data_cnt = 0;
+		} while (ophdr->oh_flags & XLOG_CONTINUE_TRANS);
+	}
 
-	if (iclog->ic_state == XLOG_STATE_ACTIVE)
-		xlog_state_switch_iclogs(log, iclog, 0);
-	else
-		ASSERT(iclog->ic_state == XLOG_STATE_WANT_SYNC ||
-			xlog_is_shutdown(log));
-release_iclog:
-	error = xlog_state_release_iclog(log, iclog);
-	spin_unlock(&log->l_icloglock);
-	return error;
+	/*
+	 * No more iovecs remain in this logvec so return the next log vec to
+	 * the caller so it can go back to fast path copying.
+	 */
+	*iclogp = iclog;
+	return 0;
 }
 
 /*
@@ -2449,27 +2468,16 @@ xlog_write(
 	struct xfs_cil_ctx	*ctx,
 	struct xfs_log_vec	*log_vector,
 	struct xlog_ticket	*ticket,
-	uint			optype)
+	uint32_t		len)
+
 {
 	struct xlog_in_core	*iclog = NULL;
 	struct xfs_log_vec	*lv = log_vector;
-	struct xfs_log_iovec	*vecp = lv->lv_iovecp;
-	int			index = 0;
-	int			len;
-	int			partial_copy = 0;
-	int			partial_copy_len = 0;
-	int			contwr = 0;
-	int			record_cnt = 0;
-	int			data_cnt = 0;
+	uint32_t		record_cnt = 0;
+	uint32_t		data_cnt = 0;
 	int			error = 0;
+	int			log_offset;
 
-	/*
-	 * If this is a commit or unmount transaction, we don't need a start
-	 * record to be written.  We do, however, have to account for the
-	 * commit or unmount header that gets written. Hence we always have
-	 * to account for an extra xlog_op_header here.
-	 */
-	ticket->t_curr_res -= sizeof(struct xlog_op_header);
 	if (ticket->t_curr_res < 0) {
 		xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES,
 		     "ctx ticket reservation ran out. Need to up reservation");
@@ -2477,144 +2485,54 @@ xlog_write(
 		xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
 	}
 
-	len = xlog_write_calc_vec_length(ticket, log_vector, optype);
-	while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) {
-		void		*ptr;
-		int		log_offset;
-
 	error = xlog_state_get_iclog_space(log, len, &iclog, ticket,
-						   &contwr, &log_offset);
+					   &log_offset);
 	if (error)
 		return error;
 
 	ASSERT(log_offset <= iclog->ic_size - 1);
-		ptr = iclog->ic_datap + log_offset;
 
 	/*
 	 * If we have a context pointer, pass it the first iclog we are
 	 * writing to so it can record state needed for iclog write
 	 * ordering.
 	 */
-		if (ctx) {
+	if (ctx)
 		xlog_cil_set_ctx_write_state(ctx, iclog);
-			ctx = NULL;
-		}
 
+	while (lv) {
 		/*
-		 * This loop writes out as many regions as can fit in the amount
-		 * of space which was allocated by xlog_state_get_iclog_space().
+		 * If the entire log vec does not fit in the iclog, punt it to
+		 * the partial copy loop which can handle this case.
 		 */
-		while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) {
-			struct xfs_log_iovec	*reg;
-			struct xlog_op_header	*ophdr;
-			int			copy_len;
-			int			copy_off;
-			bool			ordered = false;
-			bool			wrote_start_rec = false;
-
-			/* ordered log vectors have no regions to write */
-			if (lv->lv_buf_len == XFS_LOG_VEC_ORDERED) {
-				ASSERT(lv->lv_niovecs == 0);
-				ordered = true;
-				goto next_lv;
-			}
-
-			reg = &vecp[index];
-			ASSERT(reg->i_len % sizeof(int32_t) == 0);
-			ASSERT((unsigned long)ptr % sizeof(int32_t) == 0);
-
+		if (lv->lv_niovecs &&
+		    lv->lv_bytes > iclog->ic_size - log_offset) {
+			error = xlog_write_partial(lv, ticket, &iclog,
+					&log_offset, &len, &record_cnt,
+					&data_cnt);
+			if (error) {
 				/*
-			 * Before we start formatting log vectors, we need to
-			 * write a start record. Only do this for the first
-			 * iclog we write to.
+				 * We have no iclog to release, so just return
+				 * the error immediately.
 				 */
-			if (optype & XLOG_START_TRANS) {
-				xlog_write_start_rec(ptr, ticket);
-				xlog_write_adv_cnt(&ptr, &len, &log_offset,
-						sizeof(struct xlog_op_header));
-				optype &= ~XLOG_START_TRANS;
-				wrote_start_rec = true;
-			}
-
-			ophdr = xlog_write_setup_ophdr(log, ptr, ticket, optype);
-			if (!ophdr)
-				return -EIO;
-
-			xlog_write_adv_cnt(&ptr, &len, &log_offset,
-					   sizeof(struct xlog_op_header));
-
-			len += xlog_write_setup_copy(ticket, ophdr,
-						     iclog->ic_size-log_offset,
-						     reg->i_len,
-						     &copy_off, &copy_len,
-						     &partial_copy,
-						     &partial_copy_len);
-			xlog_verify_dest_ptr(log, ptr);
-
-			/*
-			 * Copy region.
-			 *
-			 * Unmount records just log an opheader, so can have
-			 * empty payloads with no data region to copy. Hence we
-			 * only copy the payload if the vector says it has data
-			 * to copy.
-			 */
-			ASSERT(copy_len >= 0);
-			if (copy_len > 0) {
-				memcpy(ptr, reg->i_addr + copy_off, copy_len);
-				xlog_write_adv_cnt(&ptr, &len, &log_offset,
-						   copy_len);
-			}
-			copy_len += sizeof(struct xlog_op_header);
-			record_cnt++;
-			if (wrote_start_rec) {
-				copy_len += sizeof(struct xlog_op_header);
-				record_cnt++;
-			}
-			data_cnt += contwr ? copy_len : 0;
-
-			error = xlog_write_copy_finish(log, iclog, optype,
-						       &record_cnt, &data_cnt,
-						       &partial_copy,
-						       &partial_copy_len,
-						       log_offset);
-			if (error)
 				return error;
-
-			/*
-			 * if we had a partial copy, we need to get more iclog
-			 * space but we don't want to increment the region
-			 * index because there is still more is this region to
-			 * write.
-			 *
-			 * If we completed writing this region, and we flushed
-			 * the iclog (indicated by resetting of the record
-			 * count), then we also need to get more log space. If
-			 * this was the last record, though, we are done and
-			 * can just return.
-			 */
-			if (partial_copy)
-				break;
-
-			if (++index == lv->lv_niovecs) {
-next_lv:
-				lv = lv->lv_next;
-				index = 0;
-				if (lv)
-					vecp = lv->lv_iovecp;
-			}
-			if (record_cnt == 0 && !ordered) {
-				if (!lv)
-					return 0;
-				break;
 			}
+		} else {
+			xlog_write_full(lv, ticket, iclog, &log_offset,
+					 &len, &record_cnt, &data_cnt);
 		}
+		lv = lv->lv_next;
 	}
-
 	ASSERT(len == 0);
 
+	/*
+	 * We've already been guaranteed that the last writes will fit inside
+	 * the current iclog, and hence it will already have the space used by
+	 * those writes accounted to it. Hence we do not need to update the
+	 * iclog with the number of bytes written here.
+	 */
 	spin_lock(&log->l_icloglock);
-	xlog_state_finish_copy(log, iclog, record_cnt, data_cnt);
+	xlog_state_finish_copy(log, iclog, record_cnt, 0);
 	error = xlog_state_release_iclog(log, iclog);
 	spin_unlock(&log->l_icloglock);
 
@@ -2971,7 +2889,6 @@ xlog_state_get_iclog_space(
 	int			len,
 	struct xlog_in_core	**iclogp,
 	struct xlog_ticket	*ticket,
-	int			*continued_write,
 	int			*logoffsetp)
 {
 	int		  log_offset;
@@ -3008,9 +2925,6 @@ xlog_state_get_iclog_space(
 	 */
 	if (log_offset == 0) {
 		ticket->t_curr_res -= log->l_iclog_hsize;
-		xlog_tic_add_region(ticket,
-				    log->l_iclog_hsize,
-				    XLOG_REG_TYPE_LRHEADER);
 		head->h_cycle = cpu_to_be32(log->l_curr_cycle);
 		head->h_lsn = cpu_to_be64(
 			xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block));
@@ -3052,13 +2966,10 @@ xlog_state_get_iclog_space(
 	 * iclogs (to mark it taken), this particular iclog will release/sync
 	 * to disk in xlog_write().
 	 */
-	if (len <= iclog->ic_size - iclog->ic_offset) {
-		*continued_write = 0;
+	if (len <= iclog->ic_size - iclog->ic_offset)
 		iclog->ic_offset += len;
-	} else {
-		*continued_write = 1;
+	else
 		xlog_state_switch_iclogs(log, iclog, iclog->ic_size);
-	}
 	*iclogp = iclog;
 
 	ASSERT(iclog->ic_offset <= iclog->ic_size);
@@ -3090,7 +3001,6 @@ xfs_log_ticket_regrant(
 	xlog_grant_sub_space(log, &log->l_write_head.grant,
 					ticket->t_curr_res);
 	ticket->t_curr_res = ticket->t_unit_res;
-	xlog_tic_reset_res(ticket);
 
 	trace_xfs_log_ticket_regrant_sub(log, ticket);
 
@@ -3101,7 +3011,6 @@ xfs_log_ticket_regrant(
 		trace_xfs_log_ticket_regrant_exit(log, ticket);
 
 		ticket->t_curr_res = ticket->t_unit_res;
-		xlog_tic_reset_res(ticket);
 	}
 
 	xfs_log_ticket_put(ticket);
@@ -3591,7 +3500,6 @@ xlog_ticket_alloc(
 	struct xlog		*log,
 	int			unit_bytes,
 	int			cnt,
-	char			client,
 	bool			permanent)
 {
 	struct xlog_ticket	*tic;
@@ -3609,39 +3517,13 @@ xlog_ticket_alloc(
 	tic->t_cnt		= cnt;
 	tic->t_ocnt		= cnt;
 	tic->t_tid		= prandom_u32();
-	tic->t_clientid		= client;
 	if (permanent)
 		tic->t_flags |= XLOG_TIC_PERM_RESERV;
 
-	xlog_tic_reset_res(tic);
-
 	return tic;
 }
 
 #if defined(DEBUG)
-/*
- * Make sure that the destination ptr is within the valid data region of
- * one of the iclogs.  This uses backup pointers stored in a different
- * part of the log in case we trash the log structure.
- */
-STATIC void
-xlog_verify_dest_ptr(
-	struct xlog	*log,
-	void		*ptr)
-{
-	int i;
-	int good_ptr = 0;
-
-	for (i = 0; i < log->l_iclog_bufs; i++) {
-		if (ptr >= log->l_iclog_bak[i] &&
-		    ptr <= log->l_iclog_bak[i] + log->l_iclog_size)
-			good_ptr++;
-	}
-
-	if (!good_ptr)
-		xfs_emerg(log->l_mp, "%s: invalid ptr", __func__);
-}
-
 /*
  * Check to make sure the grant write head didn't just over lap the tail.  If
  * the cycles are the same, we can't be overlapping.  Otherwise, make sure that
@@ -3769,7 +3651,7 @@ xlog_verify_iclog(
 		if (field_offset & 0x1ff) {
 			clientid = ophead->oh_clientid;
 		} else {
-			idx = BTOBBT((char *)&ophead->oh_clientid - iclog->ic_datap);
+			idx = BTOBBT((void *)&ophead->oh_clientid - iclog->ic_datap);
 			if (idx >= (XLOG_HEADER_CYCLE_SIZE / BBSIZE)) {
 				j = idx / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
 				k = idx % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
@@ -3780,11 +3662,12 @@ xlog_verify_iclog(
 					iclog->ic_header.h_cycle_data[idx]);
 			}
 		}
-		if (clientid != XFS_TRANSACTION && clientid != XFS_LOG)
+		if (clientid != XFS_TRANSACTION && clientid != XFS_LOG) {
 			xfs_warn(log->l_mp,
-				"%s: invalid clientid %d op "PTR_FMT" offset 0x%lx",
-				__func__, clientid, ophead,
+				"%s: op %d invalid clientid %d op "PTR_FMT" offset 0x%lx",
+				__func__, i, clientid, ophead,
 				(unsigned long)field_offset);
+		}
 
 		/* check length */
 		p = &ophead->oh_len;
@@ -3792,8 +3675,7 @@ xlog_verify_iclog(
 		if (field_offset & 0x1ff) {
 			op_len = be32_to_cpu(ophead->oh_len);
 		} else {
-			idx = BTOBBT((uintptr_t)&ophead->oh_len -
-				    (uintptr_t)iclog->ic_datap);
+			idx = BTOBBT((void *)&ophead->oh_len - iclog->ic_datap);
 			if (idx >= (XLOG_HEADER_CYCLE_SIZE / BBSIZE)) {
 				j = idx / (XLOG_HEADER_CYCLE_SIZE / BBSIZE);
 				k = idx % (XLOG_HEADER_CYCLE_SIZE / BBSIZE);

fs/xfs/xfs_log.h

@@ -21,42 +21,19 @@ struct xfs_log_vec {
 
 #define XFS_LOG_VEC_ORDERED	(-1)
 
-static inline void *
-xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
-		uint type)
-{
-	struct xfs_log_iovec *vec = *vecp;
-
-	if (vec) {
-		ASSERT(vec - lv->lv_iovecp < lv->lv_niovecs);
-		vec++;
-	} else {
-		vec = &lv->lv_iovecp[0];
-	}
-
-	vec->i_type = type;
-	vec->i_addr = lv->lv_buf + lv->lv_buf_len;
-
-	ASSERT(IS_ALIGNED((unsigned long)vec->i_addr, sizeof(uint64_t)));
-
-	*vecp = vec;
-	return vec->i_addr;
-}
+void *xlog_prepare_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec **vecp,
+		uint type);
 
-/*
- * We need to make sure the next buffer is naturally aligned for the biggest
- * basic data type we put into it.  We already accounted for this padding when
- * sizing the buffer.
- *
- * However, this padding does not get written into the log, and hence we have to
- * track the space used by the log vectors separately to prevent log space hangs
- * due to inaccurate accounting (i.e. a leak) of the used log space through the
- * CIL context ticket.
- */
 static inline void
 xlog_finish_iovec(struct xfs_log_vec *lv, struct xfs_log_iovec *vec, int len)
 {
-	lv->lv_buf_len += round_up(len, sizeof(uint64_t));
+	struct xlog_op_header	*oph = vec->i_addr;
+
+	/* opheader tracks payload length, logvec tracks region length */
+	oph->oh_len = cpu_to_be32(len);
+
+	len += sizeof(struct xlog_op_header);
+	lv->lv_buf_len += len;
 	lv->lv_bytes += len;
 	vec->i_len = len;
 }
@@ -118,12 +95,8 @@ void	xfs_log_mount_cancel(struct xfs_mount *);
 xfs_lsn_t xlog_assign_tail_lsn(struct xfs_mount *mp);
 xfs_lsn_t xlog_assign_tail_lsn_locked(struct xfs_mount *mp);
 void	xfs_log_space_wake(struct xfs_mount *mp);
-int	  xfs_log_reserve(struct xfs_mount *mp,
-			  int		   length,
-			  int		   count,
-			  struct xlog_ticket **ticket,
-			  uint8_t		   clientid,
-			  bool		   permanent);
+int	xfs_log_reserve(struct xfs_mount *mp, int length, int count,
+			struct xlog_ticket **ticket, bool permanent);
 int	xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic);
 void	xfs_log_unmount(struct xfs_mount *mp);
 bool	xfs_log_writable(struct xfs_mount *mp);

fs/xfs/xfs_log_cil.c

@@ -37,7 +37,7 @@ xlog_cil_ticket_alloc(
 {
 	struct xlog_ticket *tic;
 
-	tic = xlog_ticket_alloc(log, 0, 1, XFS_TRANSACTION, 0);
+	tic = xlog_ticket_alloc(log, 0, 1, 0);
 
 	/*
 	 * set the current reservation to zero so we know to steal the basic
@@ -214,13 +214,20 @@ xlog_cil_alloc_shadow_bufs(
 		}
 
 		/*
-		 * We 64-bit align the length of each iovec so that the start
-		 * of the next one is naturally aligned.  We'll need to
-		 * account for that slack space here. Then round nbytes up
-		 * to 64-bit alignment so that the initial buffer alignment is
-		 * easy to calculate and verify.
+		 * We 64-bit align the length of each iovec so that the start of
+		 * the next one is naturally aligned.  We'll need to account for
+		 * that slack space here.
+		 *
+		 * We also add the xlog_op_header to each region when
+		 * formatting, but that's not accounted to the size of the item
+		 * at this point. Hence we'll need an addition number of bytes
+		 * for each vector to hold an opheader.
+		 *
+		 * Then round nbytes up to 64-bit alignment so that the initial
+		 * buffer alignment is easy to calculate and verify.
 		 */
-		nbytes += niovecs * sizeof(uint64_t);
+		nbytes += niovecs *
+			(sizeof(uint64_t) + sizeof(struct xlog_op_header));
 		nbytes = round_up(nbytes, sizeof(uint64_t));
 
 		/*
@@ -277,22 +284,18 @@ xlog_cil_alloc_shadow_bufs(
 
 /*
  * Prepare the log item for insertion into the CIL. Calculate the difference in
- * log space and vectors it will consume, and if it is a new item pin it as
- * well.
+ * log space it will consume, and if it is a new item pin it as well.
  */
 STATIC void
 xfs_cil_prepare_item(
 	struct xlog		*log,
 	struct xfs_log_vec	*lv,
 	struct xfs_log_vec	*old_lv,
-	int			*diff_len,
-	int			*diff_iovecs)
+	int			*diff_len)
 {
 	/* Account for the new LV being passed in */
-	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED) {
+	if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED)
 		*diff_len += lv->lv_bytes;
-		*diff_iovecs += lv->lv_niovecs;
-	}
 
 	/*
 	 * If there is no old LV, this is the first time we've seen the item in
@@ -309,7 +312,6 @@ xfs_cil_prepare_item(
 		ASSERT(lv->lv_buf_len != XFS_LOG_VEC_ORDERED);
 
 		*diff_len -= old_lv->lv_bytes;
-		*diff_iovecs -= old_lv->lv_niovecs;
 		lv->lv_item->li_lv_shadow = old_lv;
 	}
 
@@ -358,12 +360,10 @@ static void
 xlog_cil_insert_format_items(
 	struct xlog		*log,
 	struct xfs_trans	*tp,
-	int			*diff_len,
-	int			*diff_iovecs)
+	int			*diff_len)
 {
 	struct xfs_log_item	*lip;
 
-
 	/* Bail out if we didn't find a log item.  */
 	if (list_empty(&tp->t_items)) {
 		ASSERT(0);
@@ -406,7 +406,6 @@ xlog_cil_insert_format_items(
 			 * set the item up as though it is a new insertion so
 			 * that the space reservation accounting is correct.
 			 */
-			*diff_iovecs -= lv->lv_niovecs;
 			*diff_len -= lv->lv_bytes;
 
 			/* Ensure the lv is set up according to ->iop_size */
@@ -431,7 +430,7 @@ xlog_cil_insert_format_items(
 		ASSERT(IS_ALIGNED((unsigned long)lv->lv_buf, sizeof(uint64_t)));
 		lip->li_ops->iop_format(lip, lv);
 insert:
-		xfs_cil_prepare_item(log, lv, old_lv, diff_len, diff_iovecs);
+		xfs_cil_prepare_item(log, lv, old_lv, diff_len);
 	}
 }
 
@@ -451,7 +450,6 @@ xlog_cil_insert_items(
 	struct xfs_cil_ctx	*ctx = cil->xc_ctx;
 	struct xfs_log_item	*lip;
 	int			len = 0;
-	int			diff_iovecs = 0;
 	int			iclog_space;
 	int			iovhdr_res = 0, split_res = 0, ctx_res = 0;
 
@@ -461,15 +459,10 @@ xlog_cil_insert_items(
 	 * We can do this safely because the context can't checkpoint until we
 	 * are done so it doesn't matter exactly how we update the CIL.
 	 */
-	xlog_cil_insert_format_items(log, tp, &len, &diff_iovecs);
+	xlog_cil_insert_format_items(log, tp, &len);
 
 	spin_lock(&cil->xc_cil_lock);
 
-	/* account for space used by new iovec headers  */
-	iovhdr_res = diff_iovecs * sizeof(xlog_op_header_t);
-	len += iovhdr_res;
-	ctx->nvecs += diff_iovecs;
-
 	/* attach the transaction to the CIL if it has any busy extents */
 	if (!list_empty(&tp->t_busy))
 		list_splice_init(&tp->t_busy, &ctx->busy_extents);
@@ -822,7 +815,8 @@ xlog_cil_order_write(
 static int
 xlog_cil_write_chain(
 	struct xfs_cil_ctx	*ctx,
-	struct xfs_log_vec	*chain)
+	struct xfs_log_vec	*chain,
+	uint32_t		chain_len)
 {
 	struct xlog		*log = ctx->cil->xc_log;
 	int			error;
@@ -830,7 +824,7 @@ xlog_cil_write_chain(
 	error = xlog_cil_order_write(ctx->cil, ctx->sequence, _START_RECORD);
 	if (error)
 		return error;
-	return xlog_write(log, ctx, chain, ctx->ticket, XLOG_START_TRANS);
+	return xlog_write(log, ctx, chain, ctx->ticket, chain_len);
 }
 
 /*
@@ -844,9 +838,14 @@ xlog_cil_write_commit_record(
 	struct xfs_cil_ctx	*ctx)
 {
 	struct xlog		*log = ctx->cil->xc_log;
+	struct xlog_op_header	ophdr = {
+		.oh_clientid = XFS_TRANSACTION,
+		.oh_tid = cpu_to_be32(ctx->ticket->t_tid),
+		.oh_flags = XLOG_COMMIT_TRANS,
+	};
 	struct xfs_log_iovec	reg = {
-		.i_addr = NULL,
-		.i_len = 0,
+		.i_addr = &ophdr,
+		.i_len = sizeof(struct xlog_op_header),
 		.i_type = XLOG_REG_TYPE_COMMIT,
 	};
 	struct xfs_log_vec	vec = {
@@ -862,12 +861,79 @@ xlog_cil_write_commit_record(
 	if (error)
 		return error;
 
-	error = xlog_write(log, ctx, &vec, ctx->ticket, XLOG_COMMIT_TRANS);
+	/* account for space used by record data */
+	ctx->ticket->t_curr_res -= reg.i_len;
+	error = xlog_write(log, ctx, &vec, ctx->ticket, reg.i_len);
 	if (error)
 		xlog_force_shutdown(log, SHUTDOWN_LOG_IO_ERROR);
 	return error;
 }
 
+struct xlog_cil_trans_hdr {
+	struct xlog_op_header	oph[2];
+	struct xfs_trans_header	thdr;
+	struct xfs_log_iovec	lhdr[2];
+};
+
+/*
+ * Build a checkpoint transaction header to begin the journal transaction.  We
+ * need to account for the space used by the transaction header here as it is
+ * not accounted for in xlog_write().
+ *
+ * This is the only place we write a transaction header, so we also build the
+ * log opheaders that indicate the start of a log transaction and wrap the
+ * transaction header. We keep the start record in it's own log vector rather
+ * than compacting them into a single region as this ends up making the logic
+ * in xlog_write() for handling empty opheaders for start, commit and unmount
+ * records much simpler.
+ */
+static void
+xlog_cil_build_trans_hdr(
+	struct xfs_cil_ctx	*ctx,
+	struct xlog_cil_trans_hdr *hdr,
+	struct xfs_log_vec	*lvhdr,
+	int			num_iovecs)
+{
+	struct xlog_ticket	*tic = ctx->ticket;
+	__be32			tid = cpu_to_be32(tic->t_tid);
+
+	memset(hdr, 0, sizeof(*hdr));
+
+	/* Log start record */
+	hdr->oph[0].oh_tid = tid;
+	hdr->oph[0].oh_clientid = XFS_TRANSACTION;
+	hdr->oph[0].oh_flags = XLOG_START_TRANS;
+
+	/* log iovec region pointer */
+	hdr->lhdr[0].i_addr = &hdr->oph[0];
+	hdr->lhdr[0].i_len = sizeof(struct xlog_op_header);
+	hdr->lhdr[0].i_type = XLOG_REG_TYPE_LRHEADER;
+
+	/* log opheader */
+	hdr->oph[1].oh_tid = tid;
+	hdr->oph[1].oh_clientid = XFS_TRANSACTION;
+	hdr->oph[1].oh_len = cpu_to_be32(sizeof(struct xfs_trans_header));
+
+	/* transaction header in host byte order format */
+	hdr->thdr.th_magic = XFS_TRANS_HEADER_MAGIC;
+	hdr->thdr.th_type = XFS_TRANS_CHECKPOINT;
+	hdr->thdr.th_tid = tic->t_tid;
+	hdr->thdr.th_num_items = num_iovecs;
+
+	/* log iovec region pointer */
+	hdr->lhdr[1].i_addr = &hdr->oph[1];
+	hdr->lhdr[1].i_len = sizeof(struct xlog_op_header) +
+				sizeof(struct xfs_trans_header);
+	hdr->lhdr[1].i_type = XLOG_REG_TYPE_TRANSHDR;
+
+	lvhdr->lv_niovecs = 2;
+	lvhdr->lv_iovecp = &hdr->lhdr[0];
+	lvhdr->lv_bytes = hdr->lhdr[0].i_len + hdr->lhdr[1].i_len;
+	lvhdr->lv_next = ctx->lv_chain;
+
+	tic->t_curr_res -= lvhdr->lv_bytes;
+}
+
 /*
  * Push the Committed Item List to the log.
  *
@@ -892,11 +958,10 @@ xlog_cil_push_work(
 	struct xlog		*log = cil->xc_log;
 	struct xfs_log_vec	*lv;
 	struct xfs_cil_ctx	*new_ctx;
-	struct xlog_ticket	*tic;
-	int			num_iovecs;
+	int			num_iovecs = 0;
+	int			num_bytes = 0;
 	int			error = 0;
-	struct xfs_trans_header thdr;
-	struct xfs_log_iovec	lhdr;
+	struct xlog_cil_trans_hdr thdr;
 	struct xfs_log_vec	lvhdr = { NULL };
 	xfs_csn_t		push_seq;
 	bool			push_commit_stable;
@@ -975,7 +1040,6 @@ xlog_cil_push_work(
 	 * by the flush lock.
 	 */
 	lv = NULL;
-	num_iovecs = 0;
 	while (!list_empty(&cil->xc_cil)) {
 		struct xfs_log_item	*item;
 
@@ -989,6 +1053,10 @@ xlog_cil_push_work(
 		lv = item->li_lv;
 		item->li_lv = NULL;
 		num_iovecs += lv->lv_niovecs;
+
+		/* we don't write ordered log vectors */
+		if (lv->lv_buf_len != XFS_LOG_VEC_ORDERED)
+			num_bytes += lv->lv_bytes;
 	}
 
 	/*
@@ -1025,26 +1093,11 @@ xlog_cil_push_work(
 	 * Build a checkpoint transaction header and write it to the log to
 	 * begin the transaction. We need to account for the space used by the
 	 * transaction header here as it is not accounted for in xlog_write().
-	 *
-	 * The LSN we need to pass to the log items on transaction commit is
-	 * the LSN reported by the first log vector write. If we use the commit
-	 * record lsn then we can move the tail beyond the grant write head.
-	 */
-	tic = ctx->ticket;
-	thdr.th_magic = XFS_TRANS_HEADER_MAGIC;
-	thdr.th_type = XFS_TRANS_CHECKPOINT;
-	thdr.th_tid = tic->t_tid;
-	thdr.th_num_items = num_iovecs;
-	lhdr.i_addr = &thdr;
-	lhdr.i_len = sizeof(xfs_trans_header_t);
-	lhdr.i_type = XLOG_REG_TYPE_TRANSHDR;
-	tic->t_curr_res -= lhdr.i_len + sizeof(xlog_op_header_t);
-
-	lvhdr.lv_niovecs = 1;
-	lvhdr.lv_iovecp = &lhdr;
-	lvhdr.lv_next = ctx->lv_chain;
-
-	error = xlog_cil_write_chain(ctx, &lvhdr);
+	 */
+	xlog_cil_build_trans_hdr(ctx, &thdr, &lvhdr, num_iovecs);
+	num_bytes += lvhdr.lv_bytes;
+
+	error = xlog_cil_write_chain(ctx, &lvhdr, num_bytes);
 	if (error)
 		goto out_abort_free_ticket;
 
@@ -1052,7 +1105,7 @@ xlog_cil_push_work(
 	if (error)
 		goto out_abort_free_ticket;
 
-	xfs_log_ticket_ungrant(log, tic);
+	xfs_log_ticket_ungrant(log, ctx->ticket);
 
 	/*
 	 * If the checkpoint spans multiple iclogs, wait for all previous iclogs
@@ -1116,7 +1169,7 @@ xlog_cil_push_work(
 	return;
 
 out_abort_free_ticket:
-	xfs_log_ticket_ungrant(log, tic);
+	xfs_log_ticket_ungrant(log, ctx->ticket);
 	ASSERT(xlog_is_shutdown(log));
 	if (!ctx->commit_iclog) {
 		xlog_cil_committed(ctx);

fs/xfs/xfs_log_priv.h

@@ -142,19 +142,6 @@ enum xlog_iclog_state {
 
 #define XLOG_COVER_OPS		5
 
-/* Ticket reservation region accounting */ 
-#define XLOG_TIC_LEN_MAX	15
-
-/*
- * Reservation region
- * As would be stored in xfs_log_iovec but without the i_addr which
- * we don't care about.
- */
-typedef struct xlog_res {
-	uint	r_len;	/* region length		:4 */
-	uint	r_type;	/* region's transaction type	:4 */
-} xlog_res_t;
-
 typedef struct xlog_ticket {
 	struct list_head   t_queue;	 /* reserve/write queue */
 	struct task_struct *t_task;	 /* task that owns this ticket */
@@ -164,15 +151,7 @@ typedef struct xlog_ticket {
 	int		   t_unit_res;	 /* unit reservation in bytes    : 4  */
 	char		   t_ocnt;	 /* original count		 : 1  */
 	char		   t_cnt;	 /* current count		 : 1  */
-	char		   t_clientid;	 /* who does this belong to;	 : 1  */
 	uint8_t		   t_flags;	 /* properties of reservation	 : 1  */
-
-        /* reservation array fields */
-	uint		   t_res_num;                    /* num in array : 4 */
-	uint		   t_res_num_ophdrs;		 /* num op hdrs  : 4 */
-	uint		   t_res_arr_sum;		 /* array sum    : 4 */
-	uint		   t_res_o_flow;		 /* sum overflow : 4 */
-	xlog_res_t	   t_res_arr[XLOG_TIC_LEN_MAX];  /* array of res : 8 * 15 */ 
 } xlog_ticket_t;
 
 /*
@@ -211,7 +190,7 @@ typedef struct xlog_in_core {
 	u32			ic_offset;
 	enum xlog_iclog_state	ic_state;
 	unsigned int		ic_flags;
-	char			*ic_datap;	/* pointer to iclog data */
+	void			*ic_datap;	/* pointer to iclog data */
 	struct list_head	ic_callbacks;
 
 	/* reference counts need their own cacheline */
@@ -242,7 +221,6 @@ struct xfs_cil_ctx {
 	xfs_lsn_t		commit_lsn;	/* chkpt commit record lsn */
 	struct xlog_in_core	*commit_iclog;
 	struct xlog_ticket	*ticket;	/* chkpt ticket */
-	int			nvecs;		/* number of regions */
 	int			space_used;	/* aggregate size of regions */
 	struct list_head	busy_extents;	/* busy extents in chkpt */
 	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
@@ -441,10 +419,6 @@ struct xlog {
 
 	struct xfs_kobj		l_kobj;
 
-	/* The following field are used for debugging; need to hold icloglock */
-#ifdef DEBUG
-	void			*l_iclog_bak[XLOG_MAX_ICLOGS];
-#endif
 	/* log recovery lsn tracking (for buffer submission */
 	xfs_lsn_t		l_recovery_lsn;
 
@@ -509,27 +483,14 @@ extern __le32	 xlog_cksum(struct xlog *log, struct xlog_rec_header *rhead,
 			    char *dp, int size);
 
 extern struct kmem_cache *xfs_log_ticket_cache;
-struct xlog_ticket *
-xlog_ticket_alloc(
-	struct xlog	*log,
-	int		unit_bytes,
-	int		count,
-	char		client,
-	bool		permanent);
-
-static inline void
-xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes)
-{
-	*ptr += bytes;
-	*len -= bytes;
-	*off += bytes;
-}
+struct xlog_ticket *xlog_ticket_alloc(struct xlog *log, int unit_bytes,
+		int count, bool permanent);
 
 void	xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket);
 void	xlog_print_trans(struct xfs_trans *);
 int	xlog_write(struct xlog *log, struct xfs_cil_ctx *ctx,
 		struct xfs_log_vec *log_vector, struct xlog_ticket *tic,
-		uint optype);
+		uint32_t len);
 void	xfs_log_ticket_ungrant(struct xlog *log, struct xlog_ticket *ticket);
 void	xfs_log_ticket_regrant(struct xlog *log, struct xlog_ticket *ticket);
 

fs/xfs/xfs_trans.c

@@ -194,11 +194,9 @@ xfs_trans_reserve(
 			ASSERT(resp->tr_logflags & XFS_TRANS_PERM_LOG_RES);
 			error = xfs_log_regrant(mp, tp->t_ticket);
 		} else {
-			error = xfs_log_reserve(mp,
-						resp->tr_logres,
+			error = xfs_log_reserve(mp, resp->tr_logres,
 						resp->tr_logcount,
-						&tp->t_ticket, XFS_TRANSACTION,
-						permanent);
+						&tp->t_ticket, permanent);
 		}
 
 		if (error)