xfs: commit CoW-based atomic writes atomically

When completing a CoW-based write, each extent range mapping update is
covered by a separate transaction.

For a CoW-based atomic write, all mappings must be changed at once, so
change to use a single transaction.

Note that there is a limit on the amount of log intent items which can be
fit into a single transaction, but this is being ignored for now since
the count of items for a typical atomic write would be much less than is
typically supported. A typical atomic write would be expected to be 64KB
or less, which means only 16 possible extents unmaps, which is quite
small.

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
[djwong: add tr_atomic_ioend]
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: John Garry <john.g.garry@oracle.com>

Author: johnpgarry

fs/xfs/libxfs/xfs_log_rlimit.c

@@ -91,6 +91,7 @@ xfs_log_calc_trans_resv_for_minlogblocks(
 	 */
 	if (xfs_want_minlogsize_fixes(&mp->m_sb)) {
 		xfs_trans_resv_calc(mp, resv);
+		resv->tr_atomic_ioend = M_RES(mp)->tr_atomic_ioend;
 		return;
 	}
 
@@ -107,6 +108,9 @@ xfs_log_calc_trans_resv_for_minlogblocks(
 
 	xfs_trans_resv_calc(mp, resv);
 
+	/* Copy the dynamic transaction reservation types from the running fs */
+	resv->tr_atomic_ioend = M_RES(mp)->tr_atomic_ioend;
+
 	if (xfs_has_reflink(mp)) {
 		/*
 		 * In the early days of reflink, typical log operation counts

fs/xfs/libxfs/xfs_trans_resv.c

@@ -1284,6 +1284,15 @@ xfs_calc_namespace_reservations(
 	resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES;
 }
 
+STATIC void
+xfs_calc_default_atomic_ioend_reservation(
+	struct xfs_mount	*mp,
+	struct xfs_trans_resv	*resp)
+{
+	/* Pick a default that will scale reasonably for the log size. */
+	resp->tr_atomic_ioend = resp->tr_itruncate;
+}
+
 void
 xfs_trans_resv_calc(
 	struct xfs_mount	*mp,
@@ -1378,4 +1387,10 @@ xfs_trans_resv_calc(
 	resp->tr_itruncate.tr_logcount += logcount_adj;
 	resp->tr_write.tr_logcount += logcount_adj;
 	resp->tr_qm_dqalloc.tr_logcount += logcount_adj;
+
+	/*
+	 * Now that we've finished computing the static reservations, we can
+	 * compute the dynamic reservation for atomic writes.
+	 */
+	xfs_calc_default_atomic_ioend_reservation(mp, resp);
 }

fs/xfs/libxfs/xfs_trans_resv.h

@@ -48,6 +48,7 @@ struct xfs_trans_resv {
 	struct xfs_trans_res	tr_qm_dqalloc;	/* allocate quota on disk */
 	struct xfs_trans_res	tr_sb;		/* modify superblock */
 	struct xfs_trans_res	tr_fsyncts;	/* update timestamps on fsync */
+	struct xfs_trans_res	tr_atomic_ioend; /* untorn write completion */
 };
 
 /* shorthand way of accessing reservation structure */

fs/xfs/xfs_file.c

@@ -576,7 +576,10 @@ xfs_dio_write_end_io(
 	nofs_flag = memalloc_nofs_save();
 
 	if (flags & IOMAP_DIO_COW) {
-		error = xfs_reflink_end_cow(ip, offset, size);
+		if (iocb->ki_flags & IOCB_ATOMIC)
+			error = xfs_reflink_end_atomic_cow(ip, offset, size);
+		else
+			error = xfs_reflink_end_cow(ip, offset, size);
 		if (error)
 			goto out;
 	}

fs/xfs/xfs_reflink.c

@@ -984,6 +984,62 @@ xfs_reflink_end_cow(
 	return error;
 }
 
+/*
+ * Fully remap all of the file's data fork at once, which is the critical part
+ * in achieving atomic behaviour.
+ * The regular CoW end path does not use function as to keep the block
+ * reservation per transaction as low as possible.
+ */
+int
+xfs_reflink_end_atomic_cow(
+	struct xfs_inode		*ip,
+	xfs_off_t			offset,
+	xfs_off_t			count)
+{
+	xfs_fileoff_t			offset_fsb;
+	xfs_fileoff_t			end_fsb;
+	int				error = 0;
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_trans		*tp;
+	unsigned int			resblks;
+
+	trace_xfs_reflink_end_cow(ip, offset, count);
+
+	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	end_fsb = XFS_B_TO_FSB(mp, offset + count);
+
+	/*
+	 * Each remapping operation could cause a btree split, so in the worst
+	 * case that's one for each block.
+	 */
+	resblks = (end_fsb - offset_fsb) *
+			XFS_NEXTENTADD_SPACE_RES(mp, 1, XFS_DATA_FORK);
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_atomic_ioend, resblks, 0,
+			XFS_TRANS_RESERVE, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
+
+	while (end_fsb > offset_fsb && !error) {
+		error = xfs_reflink_end_cow_extent_locked(tp, ip, &offset_fsb,
+				end_fsb);
+	}
+	if (error) {
+		trace_xfs_reflink_end_cow_error(ip, error, _RET_IP_);
+		goto out_cancel;
+	}
+	error = xfs_trans_commit(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+out_cancel:
+	xfs_trans_cancel(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+}
+
 /*
  * Free all CoW staging blocks that are still referenced by the ondisk refcount
  * metadata.  The ondisk metadata does not track which inode created the

fs/xfs/xfs_reflink.h

@@ -45,6 +45,8 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count, bool cancel_real);
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
+int xfs_reflink_end_atomic_cow(struct xfs_inode *ip, xfs_off_t offset,
+		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
 extern loff_t xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
 		struct file *file_out, loff_t pos_out, loff_t len,