diff mbox series

[v7,8/8] fs/xfs: Add dax dedupe support

Message ID 20210816060359.1442450-9-ruansy.fnst@fujitsu.com (mailing list archive)
State Superseded
Headers show
Series fsdax,xfs: Add reflink&dedupe support for fsdax | expand

Commit Message

Shiyang Ruan Aug. 16, 2021, 6:03 a.m. UTC
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>
---
 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(-)

Comments

Dan Williams Aug. 20, 2021, 3:08 a.m. UTC | #1
On Sun, Aug 15, 2021 at 11:05 PM Shiyang Ruan <ruansy.fnst@fujitsu.com> wrote:
>
> 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>
> ---
>  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_reflink.c b/fs/xfs/xfs_reflink.c
> index 13e461cf2055..86c737c2baeb 100644
> --- a/fs/xfs/xfs_reflink.c
> +++ b/fs/xfs/xfs_reflink.c
> @@ -1327,8 +1327,8 @@ 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;

What if you have 2 DAX inodes sharing data and one is flipped to
non-DAX? Does that operation need to first go undo all sharing?
Shiyang Ruan Aug. 27, 2021, 3:36 a.m. UTC | #2
On 2021/8/20 11:08, Dan Williams wrote:
> On Sun, Aug 15, 2021 at 11:05 PM Shiyang Ruan <ruansy.fnst@fujitsu.com> wrote:
>>
>> 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>
>> ---
>>   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_reflink.c b/fs/xfs/xfs_reflink.c
>> index 13e461cf2055..86c737c2baeb 100644
>> --- a/fs/xfs/xfs_reflink.c
>> +++ b/fs/xfs/xfs_reflink.c
>> @@ -1327,8 +1327,8 @@ 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;
> 
> What if you have 2 DAX inodes sharing data and one is flipped to
> non-DAX? Does that operation need to first go undo all sharing?
> 

Yes, I think it is needed to unshare the extents when the DAX flags of 
the file is changed.  I'll look into it.


--
Thanks,
Ruan.
diff mbox series

Patch

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 226e3fbaf405..4765abfe777e 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -846,7 +846,7 @@  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 990b72ae3635..4b44d9d1e42a 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3727,6 +3727,59 @@  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.
@@ -3741,6 +3794,10 @@  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 4b6703dbffb8..f1547330b087 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -456,6 +456,7 @@  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 13e461cf2055..86c737c2baeb 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1327,8 +1327,8 @@  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))