Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
IronPort-HdrOrdr: =?us-ascii?q?A9a23=3AqG8lp6w62WhFzzXJfKTUKrPwEL1zdoMgy1kn?=
 =?us-ascii?q?xilNoH1uA6ilfqWV8cjzuiWbtN9vYhsdcLy7WZVoIkmskKKdg7NhXotKNTOO0A?=
 =?us-ascii?q?SVxepZnOnfKlPbexHWx6p00KdMV+xEAsTsMF4St63HyTj9P9E+4NTvysyVuds?=
 =?us-ascii?q?=3D?=
From:   Shiyang Ruan <ruansy.fnst@fujitsu.com>
To:     <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
        <linux-nvdimm@lists.01.org>, <linux-fsdevel@vger.kernel.org>
CC:     <darrick.wong@oracle.com>, <dan.j.williams@intel.com>,
        <willy@infradead.org>, <viro@zeniv.linux.org.uk>,
        <david@fromorbit.com>, <hch@lst.de>, <rgoldwyn@suse.de>
Subject: [PATCH v6 6/7] fs/xfs: Handle CoW for fsdax write() path
Date:   Wed, 19 May 2021 14:00:44 +0800
Message-ID: <20210519060045.1051226-7-ruansy.fnst@fujitsu.com>
In-Reply-To: <20210519060045.1051226-1-ruansy.fnst@fujitsu.com>
References: <20210519060045.1051226-1-ruansy.fnst@fujitsu.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

In fsdax mode, WRITE and ZERO on a shared extent need CoW performed. After
CoW, new allocated extents needs to be remapped to the file.  So, add an
iomap_end for dax write ops to do the remapping work.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
---
 fs/xfs/xfs_bmap_util.c |  3 +--
 fs/xfs/xfs_file.c      |  9 +++------
 fs/xfs/xfs_iomap.c     | 38 +++++++++++++++++++++++++++++++++++++-
 fs/xfs/xfs_iomap.h     | 24 ++++++++++++++++++++++++
 fs/xfs/xfs_iops.c      |  7 +++----
 fs/xfs/xfs_reflink.c   |  3 +--
 6 files changed, 69 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index a5e9d7d34023..2a36dc93ff27 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -965,8 +965,7 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	error = iomap_zero_range(VFS_I(ip), offset, len, NULL,
-			&xfs_buffered_write_iomap_ops);
+	error = xfs_iomap_zero_range(ip, offset, len, NULL);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 396ef36dcd0a..38d8eca05aee 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -684,11 +684,8 @@ xfs_file_dax_write(
 	pos = iocb->ki_pos;
 
 	trace_xfs_file_dax_write(iocb, from);
-	ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops);
-	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
-		i_size_write(inode, iocb->ki_pos);
-		error = xfs_setfilesize(ip, pos, ret);
-	}
+	ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops);
+
 out:
 	if (iolock)
 		xfs_iunlock(ip, iolock);
@@ -1309,7 +1306,7 @@ __xfs_filemap_fault(
 
 		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
 				(write_fault && !vmf->cow_page) ?
-				 &xfs_direct_write_iomap_ops :
+				 &xfs_dax_write_iomap_ops :
 				 &xfs_read_iomap_ops);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d154f42e2dc6..938723aa137d 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -761,7 +761,8 @@ xfs_direct_write_iomap_begin(
 
 		/* may drop and re-acquire the ilock */
 		error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
-				&lockmode, flags & IOMAP_DIRECT);
+				&lockmode,
+				(flags & IOMAP_DIRECT) || IS_DAX(inode));
 		if (error)
 			goto out_unlock;
 		if (shared)
@@ -854,6 +855,41 @@ const struct iomap_ops xfs_direct_write_iomap_ops = {
 	.iomap_begin		= xfs_direct_write_iomap_begin,
 };
 
+static int
+xfs_dax_write_iomap_end(
+	struct inode		*inode,
+	loff_t			pos,
+	loff_t			length,
+	ssize_t			written,
+	unsigned int		flags,
+	struct iomap		*iomap)
+{
+	int			error = 0;
+	struct xfs_inode	*ip = XFS_I(inode);
+	bool			cow = xfs_is_cow_inode(ip);
+
+	if (!written)
+		return 0;
+
+	if (pos + written > i_size_read(inode) && !(flags & IOMAP_FAULT)) {
+		i_size_write(inode, pos + written);
+		error = xfs_setfilesize(ip, pos, written);
+		if (error && cow) {
+			xfs_reflink_cancel_cow_range(ip, pos, written, true);
+			return error;
+		}
+	}
+	if (cow)
+		error = xfs_reflink_end_cow(ip, pos, written);
+
+	return error;
+}
+
+const struct iomap_ops xfs_dax_write_iomap_ops = {
+	.iomap_begin		= xfs_direct_write_iomap_begin,
+	.iomap_end		= xfs_dax_write_iomap_end,
+};
+
 static int
 xfs_buffered_write_iomap_begin(
 	struct inode		*inode,
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 7d3703556d0e..fbacf638ab21 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -42,8 +42,32 @@ xfs_aligned_fsb_count(
 
 extern const struct iomap_ops xfs_buffered_write_iomap_ops;
 extern const struct iomap_ops xfs_direct_write_iomap_ops;
+extern const struct iomap_ops xfs_dax_write_iomap_ops;
 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;
 
+static inline int
+xfs_iomap_zero_range(
+	struct xfs_inode	*ip,
+	loff_t			offset,
+	loff_t			len,
+	bool			*did_zero)
+{
+	return iomap_zero_range(VFS_I(ip), offset, len, did_zero,
+			IS_DAX(VFS_I(ip)) ? &xfs_dax_write_iomap_ops
+					  : &xfs_buffered_write_iomap_ops);
+}
+
+static inline int
+xfs_iomap_truncate_page(
+	struct xfs_inode	*ip,
+	loff_t			pos,
+	bool			*did_zero)
+{
+	return iomap_truncate_page(VFS_I(ip), pos, did_zero,
+			IS_DAX(VFS_I(ip)) ? &xfs_dax_write_iomap_ops
+					  : &xfs_buffered_write_iomap_ops);
+}
+
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index dfe24b7f26e5..6d936c3e1a6e 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -911,8 +911,8 @@ xfs_setattr_size(
 	 */
 	if (newsize > oldsize) {
 		trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
-		error = iomap_zero_range(inode, oldsize, newsize - oldsize,
-				&did_zeroing, &xfs_buffered_write_iomap_ops);
+		error = xfs_iomap_zero_range(ip, oldsize, newsize - oldsize,
+				&did_zeroing);
 	} else {
 		/*
 		 * iomap won't detect a dirty page over an unwritten block (or a
@@ -924,8 +924,7 @@ xfs_setattr_size(
 						     newsize);
 		if (error)
 			return error;
-		error = iomap_truncate_page(inode, newsize, &did_zeroing,
-				&xfs_buffered_write_iomap_ops);
+		error = xfs_iomap_truncate_page(ip, newsize, &did_zeroing);
 	}
 
 	if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index d25434f93235..9a780948dbd0 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1266,8 +1266,7 @@ xfs_reflink_zero_posteof(
 		return 0;
 
 	trace_xfs_zero_eof(ip, isize, pos - isize);
-	return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
-			&xfs_buffered_write_iomap_ops);
+	return xfs_iomap_zero_range(ip, isize, pos - isize, NULL);
 }
 
 /*
-- 
2.31.1