Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
IronPort-Data: =?us-ascii?q?A9a23=3AVCeG0KroByT6upQOk0pb1Qj5K9deBmL0ZBIvgKr?=
 =?us-ascii?q?LsJaIsI5as4F+vmoWWDyOPq3YMGejedx1Oom2o0pVvMOHxtBrQFY4rCswQiMRo?=
 =?us-ascii?q?6IpJ/zDcB6oYHn6wu4v7a5fx5xHLIGGdajYd1eEzvuWGuWn/SkUOZ2gHOKmUra?=
 =?us-ascii?q?eYnkpHGeIdQ964f5ds79g6mJXqYjha++9kYuaT/z3YDdJ6RYtWo4nw/7rRCdUg?=
 =?us-ascii?q?RjHkGhwUmrSyhx8lAS2e3E9VPrzLEwqRpfyatE88uWSH44vwFwll1418SvBCvv?=
 =?us-ascii?q?9+lr6WkYMBLDPPwmSkWcQUK+n6vRAjnVqlP9la7xHMgEK49mKt4kZJNFlr4G5T?=
 =?us-ascii?q?xw4eKPKg/g1XQRaEj1lIOtN/7qvzX2X6JbPlxKbLCe9qxlpJARsVWECwc57CH9?=
 =?us-ascii?q?P+dQWMjcIaQqJhv7wy7W+IsFoh8ImLcDsPI43umxp0jzYS/0hRPjrQ67Kzd5e0?=
 =?us-ascii?q?i05is1HEbDZfcVxQSVuaBDRSxxJNE0eBJ83kKGvnHaXWzFRrhSX47U252zSxQl?=
 =?us-ascii?q?q+LnrLNfRPNeNQK19kkSHoWTJ12f0GBcXMJqY0zXt2natgPLf2Cb+cIEMHba7s?=
 =?us-ascii?q?PlwjzW7wHIfCRgTfV+6uuWizEq/Xc9PbUAZ5EIGraMy3EiwUp/xUnWQpneDrxd?=
 =?us-ascii?q?aW91KEuIn4wGM4qzZ6ECSAW1sZjxIbtFgv88rbTsw31SNkpXiAjkHmKeaTnaR6?=
 =?us-ascii?q?aaShSivIiVTIWJqTSsFSxYVptf4rIwtgxbnUNluCui2g8fzFDW2xCqFxAA6hrM?=
 =?us-ascii?q?OnYsI2r+98FTvnT2hvN7KQxQz6wGRWXiqhit9ZYi4d8m450Pz8/lNNsCaQ0OHs?=
 =?us-ascii?q?XxCnNKRhMgQDIuKvD6ARuQTWrWo4euVdjrGjhhyHPEcG56Fk5K4VdkIpmggewE?=
 =?us-ascii?q?yaYBZEQIFqXT74Wt5jKK/9lP2BUOvX7+MNg=3D=3D?=
IronPort-HdrOrdr: =?us-ascii?q?A9a23=3APwrT5a/T7DOupuOHy0Fuk+DkI+orL9Y04lQ7?=
 =?us-ascii?q?vn2ZKCYlFvBw8vrCoB1173HJYUkqMk3I9ergBEDiewK4yXcW2/hzAV7KZmCP11?=
 =?us-ascii?q?dAR7sSj7cKrQeBJwTOssZZ1YpFN5N1EcDMCzFB5vrS0U2VFMkBzbC8nJyVuQ?=
 =?us-ascii?q?=3D=3D?=
From:   Shiyang Ruan <ruansy.fnst@fujitsu.com>
To:     <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
        <nvdimm@lists.linux.dev>, <linux-mm@kvack.org>,
        <linux-fsdevel@vger.kernel.org>
CC:     <djwong@kernel.org>, <dan.j.williams@intel.com>,
        <david@fromorbit.com>, <hch@infradead.org>, <jane.chu@oracle.com>,
        <rgoldwyn@suse.de>, <viro@zeniv.linux.org.uk>,
        <willy@infradead.org>, <naoya.horiguchi@nec.com>,
        <linmiaohe@huawei.com>, Christoph Hellwig <hch@lst.de>
Subject: [PATCH v11 07/07] xfs: Add dax dedupe support
Date:   Sun, 8 May 2022 22:36:20 +0800
Message-ID: <20220508143620.1775214-15-ruansy.fnst@fujitsu.com>
In-Reply-To: <20220508143620.1775214-1-ruansy.fnst@fujitsu.com>
References: <20220508143620.1775214-1-ruansy.fnst@fujitsu.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

Introduce xfs_mmaplock_two_inodes_and_break_dax_layout() for dax files
who are going to be deduped.  After that, call compare range function
only when files are both DAX or not.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/xfs_file.c    |  2 +-
 fs/xfs/xfs_inode.c   | 69 +++++++++++++++++++++++++++++++++++++++++---
 fs/xfs/xfs_inode.h   |  1 +
 fs/xfs/xfs_reflink.c |  4 +--
 4 files changed, 69 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5a4508b23b51..cf78eb393258 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -807,7 +807,7 @@ xfs_wait_dax_page(
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 }
 
-static int
+int
 xfs_break_dax_layouts(
 	struct inode		*inode,
 	bool			*retry)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b2879870a17e..96308065a2b3 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3767,6 +3767,50 @@ xfs_iolock_two_inodes_and_break_layout(
 	return 0;
 }
 
+static int
+xfs_mmaplock_two_inodes_and_break_dax_layout(
+	struct xfs_inode	*ip1,
+	struct xfs_inode	*ip2)
+{
+	int			error;
+	bool			retry;
+	struct page		*page;
+
+	if (ip1->i_ino > ip2->i_ino)
+		swap(ip1, ip2);
+
+again:
+	retry = false;
+	/* Lock the first inode */
+	xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
+	error = xfs_break_dax_layouts(VFS_I(ip1), &retry);
+	if (error || retry) {
+		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+		if (error == 0 && retry)
+			goto again;
+		return error;
+	}
+
+	if (ip1 == ip2)
+		return 0;
+
+	/* Nested lock the second inode */
+	xfs_ilock(ip2, xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1));
+	/*
+	 * We cannot use xfs_break_dax_layouts() directly here because it may
+	 * need to unlock & lock the XFS_MMAPLOCK_EXCL which is not suitable
+	 * for this nested lock case.
+	 */
+	page = dax_layout_busy_page(VFS_I(ip2)->i_mapping);
+	if (page && page_ref_count(page) != 1) {
+		xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
+		xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+		goto again;
+	}
+
+	return 0;
+}
+
 /*
  * Lock two inodes so that userspace cannot initiate I/O via file syscalls or
  * mmap activity.
@@ -3781,8 +3825,19 @@ xfs_ilock2_io_mmap(
 	ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
 	if (ret)
 		return ret;
-	filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping,
-				    VFS_I(ip2)->i_mapping);
+
+	if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) {
+		ret = xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2);
+		if (ret) {
+			inode_unlock(VFS_I(ip2));
+			if (ip1 != ip2)
+				inode_unlock(VFS_I(ip1));
+			return ret;
+		}
+	} else
+		filemap_invalidate_lock_two(VFS_I(ip1)->i_mapping,
+					    VFS_I(ip2)->i_mapping);
+
 	return 0;
 }
 
@@ -3792,8 +3847,14 @@ xfs_iunlock2_io_mmap(
 	struct xfs_inode	*ip1,
 	struct xfs_inode	*ip2)
 {
-	filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping,
-				      VFS_I(ip2)->i_mapping);
+	if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2))) {
+		xfs_iunlock(ip2, XFS_MMAPLOCK_EXCL);
+		if (ip1 != ip2)
+			xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+	} else
+		filemap_invalidate_unlock_two(VFS_I(ip1)->i_mapping,
+					      VFS_I(ip2)->i_mapping);
+
 	inode_unlock(VFS_I(ip2));
 	if (ip1 != ip2)
 		inode_unlock(VFS_I(ip1));
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 7be6f8e705ab..8313cc83b6ee 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -467,6 +467,7 @@ xfs_itruncate_extents(
 }
 
 /* from xfs_file.c */
+int	xfs_break_dax_layouts(struct inode *inode, bool *retry);
 int	xfs_break_layouts(struct inode *inode, uint *iolock,
 		enum layout_break_reason reason);
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 10a9947e35d9..7cceea510a01 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1338,8 +1338,8 @@ xfs_reflink_remap_prep(
 	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
 		goto out_unlock;
 
-	/* Don't share DAX file data for now. */
-	if (IS_DAX(inode_in) || IS_DAX(inode_out))
+	/* Don't share DAX file data with non-DAX file. */
+	if (IS_DAX(inode_in) != IS_DAX(inode_out))
 		goto out_unlock;
 
 	if (!IS_DAX(inode_in))
-- 
2.35.1