xfs: only CIL pushes require a start record

So move the one-off start record writing in xlog_write() out into
the static header that the CIL push builds to write into the log
initially. This simplifes the xlog_write() logic a lot.

pahole on x86-64 confirms that the xlog_cil_trans_hdr is correctly
32 bit aligned and packed for copying the log op and transaction
headers directly into the log as a single log region copy.

struct xlog_cil_trans_hdr {
        struct xlog_op_header      oph[2];               /*     0    24 */
        struct xfs_trans_header    thdr;                 /*    24    16 */
        struct xfs_log_iovec       lhdr[2];              /*    40    32 */

        /* size: 72, cachelines: 2, members: 3 */
        /* last cacheline: 8 bytes */
};

A wart is needed to handle the fact that length of the region the
opheader points to doesn't include the opheader length. hence if
we embed the opheader, we have to substract the opheader length from
the length written into the opheader by the generic copying code.
This will eventually go away when everything is converted to
embedded opheaders.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chandan Babu R <chandan.babu@oracle.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>

1 files changed, 36 insertions, 7 deletions

diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index 93f966c191a3..5ff046e82912 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -869,14 +869,22 @@ xlog_cil_write_commit_record(
 }
 
 struct xlog_cil_trans_hdr {
+	struct xlog_op_header	oph[2];
 	struct xfs_trans_header	thdr;
-	struct xfs_log_iovec	lhdr;
+	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(
@@ -886,20 +894,41 @@ xlog_cil_build_trans_hdr(
 	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;
-	hdr->lhdr.i_addr = &hdr->thdr;
-	hdr->lhdr.i_len = sizeof(xfs_trans_header_t);
-	hdr->lhdr.i_type = XLOG_REG_TYPE_TRANSHDR;
-	tic->t_curr_res -= hdr->lhdr.i_len + sizeof(struct xlog_op_header);
 
-	lvhdr->lv_niovecs = 1;
-	lvhdr->lv_iovecp = &hdr->lhdr;
+	/* 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;
+
+	tic->t_curr_res -= hdr->lhdr[0].i_len + hdr->lhdr[1].i_len;
+
+	lvhdr->lv_niovecs = 2;
+	lvhdr->lv_iovecp = &hdr->lhdr[0];
 	lvhdr->lv_next = ctx->lv_chain;
 }