linux-kernel - [RFC PATCH v2 6/7] xfs: handle copy-on-write in fsdax write() path.

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20191030041358.14450-7-ruansy.fnst@cn.fujitsu.com>
Date:   Wed, 30 Oct 2019 12:13:57 +0800
From:   Shiyang Ruan <ruansy.fnst@...fujitsu.com>
To:     <linux-xfs@...r.kernel.org>, <linux-nvdimm@...ts.01.org>,
        <darrick.wong@...cle.com>, <rgoldwyn@...e.de>, <hch@...radead.org>,
        <david@...morbit.com>
CC:     <linux-kernel@...r.kernel.org>, <gujx@...fujitsu.com>,
        <qi.fuli@...itsu.com>, <caoj.fnst@...fujitsu.com>,
        <ruansy.fnst@...fujitsu.com>
Subject: [RFC PATCH v2 6/7] xfs: handle copy-on-write in fsdax write() path.

In fsdax mode, WRITE and ZERO on a shared extent need COW mechanism
performed.  After COW, new extents needs to be remapped to the file.

Signed-off-by: Shiyang Ruan <ruansy.fnst@...fujitsu.com>
---
 fs/xfs/xfs_bmap_util.c |  6 +++++-
 fs/xfs/xfs_file.c      | 10 +++++++---
 fs/xfs/xfs_iomap.c     |  3 ++-
 fs/xfs/xfs_iops.c      | 11 ++++++++---
 fs/xfs/xfs_reflink.c   |  2 ++
 5 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 99bf372ed551..1b7d0665d889 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1114,10 +1114,14 @@ xfs_free_file_space(
 	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);
+		  IS_DAX(VFS_I(ip)) ?
+		  &xfs_direct_write_iomap_ops : &xfs_buffered_write_iomap_ops);
 	if (error)
 		return error;
 
+	if (xfs_is_reflink_inode(ip))
+		xfs_reflink_end_cow(ip, offset, len);
+
 	/*
 	 * If we zeroed right up to EOF and EOF straddles a page boundary we
 	 * must make sure that the post-EOF area is also zeroed because the
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 24659667d5cb..48071f16a436 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -594,9 +594,13 @@ xfs_file_dax_write(
 
 	trace_xfs_file_dax_write(ip, count, pos);
 	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);
+	if (ret > 0) {
+		if (iocb->ki_pos > i_size_read(inode)) {
+			i_size_write(inode, iocb->ki_pos);
+			error = xfs_setfilesize(ip, pos, ret);
+		}
+		if (xfs_is_cow_inode(ip))
+			xfs_reflink_end_cow(ip, pos, ret);
 	}
 out:
 	xfs_iunlock(ip, iolock);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index e8fb500e1880..db8ee371252f 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -772,13 +772,14 @@ xfs_direct_write_iomap_begin(
 		goto out_unlock;
 
 	if (imap_needs_cow(ip, flags, &imap, nimaps)) {
+		bool need_convert = flags & IOMAP_DIRECT || IS_DAX(inode);
 		error = -EAGAIN;
 		if (flags & IOMAP_NOWAIT)
 			goto out_unlock;
 
 		/* may drop and re-acquire the ilock */
 		error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
-				&lockmode, flags & IOMAP_DIRECT);
+				&lockmode, need_convert);
 		if (error)
 			goto out_unlock;
 		if (shared)
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 329a34af8e79..0052a97ccebf 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -834,6 +834,7 @@ xfs_setattr_size(
 	int			error;
 	uint			lock_flags = 0;
 	bool			did_zeroing = false;
+	const struct iomap_ops	*ops;
 
 	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
 	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
@@ -880,13 +881,17 @@ xfs_setattr_size(
 	 * extension, or zeroing out the rest of the block on a downward
 	 * truncate.
 	 */
+	if (IS_DAX(inode))
+		ops = &xfs_direct_write_iomap_ops;
+	else
+		ops = &xfs_buffered_write_iomap_ops;
+
 	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);
+				&did_zeroing, ops);
 	} else {
-		error = iomap_truncate_page(inode, newsize, &did_zeroing,
-				&xfs_buffered_write_iomap_ops);
+		error = iomap_truncate_page(inode, newsize, &did_zeroing, ops);
 	}
 
 	if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 2c8ad581d4db..e3620bc794a2 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1270,6 +1270,8 @@ xfs_reflink_zero_posteof(
 
 	trace_xfs_zero_eof(ip, isize, pos - isize);
 	return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
+			IS_DAX(VFS_I(ip)) ?
+			&xfs_direct_write_iomap_ops :
 			&xfs_buffered_write_iomap_ops);
 }
 
-- 
2.23.0