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=3AX+uZmqyMOhl4y1NrYDX+KrPwEL1zdoMgy1kn?=
 =?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 7/7] fs/xfs: Add dax dedupe support
Date:   Wed, 19 May 2021 14:00:45 +0800
Message-ID: <20210519060045.1051226-8-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

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>
---
 fs/xfs/xfs_file.c    |  2 +-
 fs/xfs/xfs_inode.c   | 57 ++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_inode.h   |  1 +
 fs/xfs/xfs_reflink.c |  4 ++--
 4 files changed, 61 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 38d8eca05aee..bd5002d38df4 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -823,7 +823,7 @@ 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 0369eb22c1bb..d5e2791969ba 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3711,6 +3711,59 @@ 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, attempts = 0;
+	bool			retry;
+	struct page		*page;
+	struct xfs_log_item	*lp;
+
+	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);
+		goto again;
+	}
+
+	if (ip1 == ip2)
+		return 0;
+
+	/* Nested lock the second inode */
+	lp = &ip1->i_itemp->ili_item;
+	if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) {
+		if (!xfs_ilock_nowait(ip2,
+		    xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1))) {
+			xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
+			if ((++attempts % 5) == 0)
+				delay(1); /* Don't just spin the CPU */
+			goto again;
+		}
+	} else
+		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.
@@ -3725,6 +3778,10 @@ xfs_ilock2_io_mmap(
 	ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
 	if (ret)
 		return ret;
+
+	if (IS_DAX(VFS_I(ip1)) && IS_DAX(VFS_I(ip2)))
+		return xfs_mmaplock_two_inodes_and_break_dax_layout(ip1, ip2);
+
 	if (ip1 == ip2)
 		xfs_ilock(ip1, XFS_MMAPLOCK_EXCL);
 	else
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index ca826cfba91c..2d0b344fb100 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -457,6 +457,7 @@ enum xfs_prealloc_flags {
 
 int	xfs_update_prealloc_flags(struct xfs_inode *ip,
 				  enum xfs_prealloc_flags flags);
+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 9a780948dbd0..ff308304c5cd 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1324,8 +1324,8 @@ 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))
-- 
2.31.1