[PATCH v2 14/14] xfs: Add dax dedupe support

From: Shiyang Ruan
Date: Fri Jun 03 2022 - 01:39:35 EST


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@xxxxxxxxxxx>
Reviewed-by: Darrick J. Wong <djwong@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
---
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 07ec4ada5163..9f433006edcd 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -808,7 +808,7 @@ 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 cbaf36d21020..d07f06ff0f13 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1363,8 +1363,8 @@ 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))
--
2.36.1