linux-kernel - [PATCH 7/7] fs/xfs: Add dedupe support for fsdax

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: <20210207170924.2933035-8-ruansy.fnst@cn.fujitsu.com>
Date:   Mon, 8 Feb 2021 01:09:24 +0800
From:   Shiyang Ruan <ruansy.fnst@...fujitsu.com>
To:     <linux-kernel@...r.kernel.org>, <linux-xfs@...r.kernel.org>,
        <linux-nvdimm@...ts.01.org>, <linux-fsdevel@...r.kernel.org>
CC:     <darrick.wong@...cle.com>, <dan.j.williams@...el.com>,
        <willy@...radead.org>, <jack@...e.cz>, <viro@...iv.linux.org.uk>,
        <linux-btrfs@...r.kernel.org>, <ocfs2-devel@....oracle.com>,
        <david@...morbit.com>, <hch@....de>, <rgoldwyn@...e.de>
Subject: [PATCH 7/7] fs/xfs: Add dedupe support for fsdax

Add xfs_break_two_dax_layouts() to break layout for tow dax files.  Then
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    | 20 ++++++++++++++++++++
 fs/xfs/xfs_inode.c   |  8 +++++++-
 fs/xfs/xfs_inode.h   |  1 +
 fs/xfs/xfs_reflink.c | 21 ++++++++++++++++++---
 4 files changed, 46 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index ab738641a3f4..64ded96b43c8 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -791,6 +791,26 @@ xfs_break_dax_layouts(
 			0, 0, xfs_wait_dax_page(inode));
 }
 
+int
+xfs_break_two_dax_layouts(
+	struct inode		*src,
+	struct inode		*dest)
+{
+	int			error;
+	bool			retry = false;
+
+retry:
+	error = xfs_break_dax_layouts(src, &retry);
+	if (error || retry)
+		goto retry;
+
+	error = xfs_break_dax_layouts(dest, &retry);
+	if (error || retry)
+		goto retry;
+
+	return error;
+}
+
 int
 xfs_break_layouts(
 	struct inode		*inode,
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 2bfbcf28b1bd..6483dbaa4d57 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3786,8 +3786,10 @@ xfs_ilock2_io_mmap(
 	struct xfs_inode	*ip2)
 {
 	int			ret;
+	struct inode		*inode1 = VFS_I(ip1);
+	struct inode		*inode2 = VFS_I(ip2);
 
-	ret = xfs_iolock_two_inodes_and_break_layout(VFS_I(ip1), VFS_I(ip2));
+	ret = xfs_iolock_two_inodes_and_break_layout(inode1, inode2);
 	if (ret)
 		return ret;
 	if (ip1 == ip2)
@@ -3795,6 +3797,10 @@ xfs_ilock2_io_mmap(
 	else
 		xfs_lock_two_inodes(ip1, XFS_MMAPLOCK_EXCL,
 				    ip2, XFS_MMAPLOCK_EXCL);
+
+	if (IS_DAX(inode1) && IS_DAX(inode2))
+		ret = xfs_break_two_dax_layouts(inode1, inode2);
+
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 751a3d1d7d84..462b61bea691 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -431,6 +431,7 @@ enum xfs_prealloc_flags {
 
 int	xfs_update_prealloc_flags(struct xfs_inode *ip,
 				  enum xfs_prealloc_flags flags);
+int	xfs_break_two_dax_layouts(struct inode *inode1, struct inode *inode2);
 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 38bde16cdb39..bdb9a07e703f 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -29,6 +29,7 @@
 #include "xfs_iomap.h"
 #include "xfs_sb.h"
 #include "xfs_ag_resv.h"
+#include <linux/dax.h>
 
 /*
  * Copy on Write of Shared Blocks
@@ -1251,6 +1252,14 @@ xfs_reflink_zero_posteof(
 			&xfs_buffered_write_iomap_ops);
 }
 
+int xfs_reflink_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
+					  struct inode *dest, loff_t destoff,
+					  loff_t len, bool *is_same)
+{
+	return dax_file_range_compare(src, srcoff, dest, destoff, len, is_same,
+				      &xfs_read_iomap_ops);
+}
+
 /*
  * Prepare two files for range cloning.  Upon a successful return both inodes
  * will have the iolock and mmaplock held, the page cache of the out file will
@@ -1293,6 +1302,7 @@ xfs_reflink_remap_prep(
 	struct xfs_inode	*src = XFS_I(inode_in);
 	struct inode		*inode_out = file_inode(file_out);
 	struct xfs_inode	*dest = XFS_I(inode_out);
+	compare_range_t		compare_range_fn;
 	int			ret;
 
 	/* Lock both files against IO */
@@ -1306,12 +1316,17 @@ 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))
+		compare_range_fn = xfs_reflink_dedupe_file_range_compare;
+	else
+		compare_range_fn = vfs_dedupe_file_range_compare;
+
 	ret = generic_remap_file_range_prep(file_in, pos_in, file_out, pos_out,
-			len, remap_flags, vfs_dedupe_file_range_compare);
+			len, remap_flags, compare_range_fn);
 	if (ret || *len == 0)
 		goto out_unlock;
 
-- 
2.30.0