xfs: add xfs_atomic_write_cow_iomap_begin()

For CoW-based atomic writes, reuse the infrastructure for reflink CoW fork
support.

Add ->iomap_begin() callback xfs_atomic_write_cow_iomap_begin() to create
staging mappings in the CoW fork for atomic write updates.

The general steps in the function are as follows:
- find extent mapping in the CoW fork for the FS block range being written
	- if part or full extent is found, proceed to process found extent
	- if no extent found, map in new blocks to the CoW fork
- convert unwritten blocks in extent if required
- update iomap extent mapping and return

The bulk of this function is quite similar to the processing in
xfs_reflink_allocate_cow(), where we try to find an extent mapping; if
none exists, then allocate a new extent in the CoW fork, convert unwritten
blocks, and return a mapping.

Performance testing has shown the XFS_ILOCK_EXCL locking to be quite
a bottleneck, so this is an area which could be optimised in future.

Christoph Hellwig contributed almost all of the code in
xfs_atomic_write_cow_iomap_begin().

Reviewed-by: Darrick J. Wong <djwong@kernel.org>
[djwong: add a new xfs_can_sw_atomic_write to convey intent better]
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: John Garry <john.g.garry@oracle.com>

6 files changed, 159 insertions, 1 deletions

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index cb23c8871f81..166fba2ff1ef 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1023,6 +1023,134 @@ const struct iomap_ops xfs_zoned_direct_write_iomap_ops = {
 #endif /* CONFIG_XFS_RT */
 
 static int
+xfs_atomic_write_cow_iomap_begin(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			length,
+	unsigned		flags,
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	const xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, length);
+	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
+	int			nmaps = 1;
+	xfs_filblks_t		resaligned;
+	struct xfs_bmbt_irec	cmap;
+	struct xfs_iext_cursor	icur;
+	struct xfs_trans	*tp;
+	unsigned int		dblocks = 0, rblocks = 0;
+	int			error;
+	u64			seq;
+
+	ASSERT(flags & IOMAP_WRITE);
+	ASSERT(flags & IOMAP_DIRECT);
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	if (!xfs_can_sw_atomic_write(mp)) {
+		ASSERT(xfs_can_sw_atomic_write(mp));
+		return -EINVAL;
+	}
+
+	/* blocks are always allocated in this path */
+	if (flags & IOMAP_NOWAIT)
+		return -EAGAIN;
+
+	trace_xfs_iomap_atomic_write_cow(ip, offset, length);
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+
+	if (!ip->i_cowfp) {
+		ASSERT(!xfs_is_reflink_inode(ip));
+		xfs_ifork_init_cow(ip);
+	}
+
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
+		cmap.br_startoff = end_fsb;
+	if (cmap.br_startoff <= offset_fsb) {
+		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+		goto found;
+	}
+
+	end_fsb = cmap.br_startoff;
+	count_fsb = end_fsb - offset_fsb;
+
+	resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb,
+			xfs_get_cowextsz_hint(ip));
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	if (XFS_IS_REALTIME_INODE(ip)) {
+		dblocks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+		rblocks = resaligned;
+	} else {
+		dblocks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
+		rblocks = 0;
+	}
+
+	error = xfs_trans_alloc_inode(ip, &M_RES(mp)->tr_write, dblocks,
+			rblocks, false, &tp);
+	if (error)
+		return error;
+
+	/* extent layout could have changed since the unlock, so check again */
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &cmap))
+		cmap.br_startoff = end_fsb;
+	if (cmap.br_startoff <= offset_fsb) {
+		xfs_trim_extent(&cmap, offset_fsb, count_fsb);
+		xfs_trans_cancel(tp);
+		goto found;
+	}
+
+	/*
+	 * Allocate the entire reservation as unwritten blocks.
+	 *
+	 * Use XFS_BMAPI_EXTSZALIGN to hint at aligning new extents according to
+	 * extszhint, such that there will be a greater chance that future
+	 * atomic writes to that same range will be aligned (and don't require
+	 * this COW-based method).
+	 */
+	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
+			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC |
+			XFS_BMAPI_EXTSZALIGN, 0, &cmap, &nmaps);
+	if (error) {
+		xfs_trans_cancel(tp);
+		goto out_unlock;
+	}
+
+	xfs_inode_set_cowblocks_tag(ip);
+	error = xfs_trans_commit(tp);
+	if (error)
+		goto out_unlock;
+
+found:
+	if (cmap.br_state != XFS_EXT_NORM) {
+		error = xfs_reflink_convert_cow_locked(ip, offset_fsb,
+				count_fsb);
+		if (error)
+			goto out_unlock;
+		cmap.br_state = XFS_EXT_NORM;
+	}
+
+	length = XFS_FSB_TO_B(mp, cmap.br_startoff + cmap.br_blockcount);
+	trace_xfs_iomap_found(ip, offset, length - offset, XFS_COW_FORK, &cmap);
+	seq = xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return xfs_bmbt_to_iomap(ip, iomap, &cmap, flags, IOMAP_F_SHARED, seq);
+
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	return error;
+}
+
+const struct iomap_ops xfs_atomic_write_cow_iomap_ops = {
+	.iomap_begin		= xfs_atomic_write_cow_iomap_begin,
+};
+
+static int
 xfs_dax_write_iomap_end(
 	struct inode		*inode,
 	loff_t			pos,
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index d330c4a581b1..674f8ac1b9bd 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -56,5 +56,6 @@ extern const struct iomap_ops xfs_read_iomap_ops;
 extern const struct iomap_ops xfs_seek_iomap_ops;
 extern const struct iomap_ops xfs_xattr_iomap_ops;
 extern const struct iomap_ops xfs_dax_write_iomap_ops;
+extern const struct iomap_ops xfs_atomic_write_cow_iomap_ops;
 
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index e5192c12e7ac..e67bc3e91f98 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -464,6 +464,11 @@ static inline bool xfs_has_nonzoned(const struct xfs_mount *mp)
 	return !xfs_has_zoned(mp);
 }
 
+static inline bool xfs_can_sw_atomic_write(struct xfs_mount *mp)
+{
+	return xfs_has_reflink(mp);
+}
+
 /*
  * Some features are always on for v5 file systems, allow the compiler to
  * eliminiate dead code when building without v4 support.
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index bd711c5bb6bb..f5d338916098 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -293,7 +293,7 @@ xfs_bmap_trim_cow(
 	return xfs_reflink_trim_around_shared(ip, imap, shared);
 }
 
-static int
+int
 xfs_reflink_convert_cow_locked(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		offset_fsb,
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index cc4e92278279..379619f24247 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -35,6 +35,8 @@ int xfs_reflink_allocate_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
 		bool convert_now);
 extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
+int xfs_reflink_convert_cow_locked(struct xfs_inode *ip,
+		xfs_fileoff_t offset_fsb, xfs_filblks_t count_fsb);
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index e56ba1963160..9554578c6da4 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1657,6 +1657,28 @@ DEFINE_RW_EVENT(xfs_file_direct_write);
 DEFINE_RW_EVENT(xfs_file_dax_write);
 DEFINE_RW_EVENT(xfs_reflink_bounce_dio_write);
 
+TRACE_EVENT(xfs_iomap_atomic_write_cow,
+	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),
+	TP_ARGS(ip, offset, count),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(xfs_off_t, offset)
+		__field(ssize_t, count)
+	),
+	TP_fast_assign(
+		__entry->dev = VFS_I(ip)->i_sb->s_dev;
+		__entry->ino = ip->i_ino;
+		__entry->offset = offset;
+		__entry->count = count;
+	),
+	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx bytecount 0x%zx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->offset,
+		  __entry->count)
+)
+
 DECLARE_EVENT_CLASS(xfs_imap_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count,
 		 int whichfork, struct xfs_bmbt_irec *irec),