From: "Darrick J. Wong" <djwong@kernel.org>
To: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Cc: hch@lst.de, linux-xfs@vger.kernel.org, dan.j.williams@intel.com,
david@fromorbit.com, linux-fsdevel@vger.kernel.org,
linux-kernel@vger.kernel.org, nvdimm@lists.linux.dev,
rgoldwyn@suse.de, viro@zeniv.linux.org.uk, willy@infradead.org
Subject: Re: [PATCH v9 8/8] xfs: Add dax dedupe support
Date: Wed, 15 Sep 2021 17:30:08 -0700 [thread overview]
Message-ID: <20210916003008.GE34830@magnolia> (raw)
In-Reply-To: <20210915104501.4146910-9-ruansy.fnst@fujitsu.com>
On Wed, Sep 15, 2021 at 06:45:01PM +0800, Shiyang Ruan 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>
> Reviewed-by: Christoph Hellwig <hch@lst.de>
> ---
> fs/xfs/xfs_file.c | 2 +-
> fs/xfs/xfs_inode.c | 80 +++++++++++++++++++++++++++++++++++++++++---
> fs/xfs/xfs_inode.h | 1 +
> fs/xfs/xfs_reflink.c | 4 +--
> 4 files changed, 80 insertions(+), 7 deletions(-)
>
> diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
> index 2ef1930374d2..c3061723613c 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 a4f6f034fb81..bdc084cdbf46 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
> @@ -3790,6 +3790,61 @@ 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);
> + if (error == 0 && retry)
> + goto again;
> + return error;
> + }
> +
> + 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;
> + }
I suspect we don't need this part for grabbing the MMAPLOCK^W pagecache
invalidatelock. The AIL only grabs the ILOCK, never the IOLOCK or the
MMAPLOCK.
> + } 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) {
Do you think the patch "ext4/xfs: add page refcount helper" would be a
good cleanup to head this series?
https://lore.kernel.org/linux-xfs/20210913161604.31981-1-alex.sierra@amd.com/T/#m59cf7cd5c0d521ad487fa3a15d31c3865db88bdf
The rest of the logic looks ok.
--D
> + 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.
> @@ -3804,8 +3859,19 @@ 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;
> }
>
> @@ -3815,8 +3881,14 @@ 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 b21b177832d1..f7e26fe31a26 100644
> --- a/fs/xfs/xfs_inode.h
> +++ b/fs/xfs/xfs_inode.h
> @@ -472,6 +472,7 @@ 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 9d876e268734..3b99c9dfcf0d 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))
> --
> 2.33.0
>
>
>
next prev parent reply other threads:[~2021-09-16 0:30 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-09-15 10:44 [PATCH v9 0/8] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-09-15 10:44 ` [PATCH v9 1/8] fsdax: Output address in dax_iomap_pfn() and rename it Shiyang Ruan
2021-09-16 0:09 ` Darrick J. Wong
2021-09-16 1:36 ` Shiyang Ruan
2021-09-15 10:44 ` [PATCH v9 2/8] fsdax: Introduce dax_iomap_cow_copy() Shiyang Ruan
2021-09-15 10:44 ` [PATCH v9 3/8] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-09-16 14:51 ` kernel test robot
2021-09-15 10:44 ` [PATCH v9 4/8] fsdax: Convert dax_iomap_zero to iter model Shiyang Ruan
2021-09-16 0:11 ` Darrick J. Wong
2021-09-16 6:15 ` Christoph Hellwig
2021-09-15 10:44 ` [PATCH v9 5/8] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-09-16 6:16 ` Christoph Hellwig
2021-09-16 8:49 ` Shiyang Ruan
2021-09-16 22:55 ` Darrick J. Wong
2021-09-15 10:44 ` [PATCH v9 6/8] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-09-16 6:17 ` Christoph Hellwig
2021-09-15 10:45 ` [PATCH v9 7/8] xfs: support CoW in fsdax mode Shiyang Ruan
2021-09-16 0:22 ` Darrick J. Wong
2021-09-16 6:32 ` Christoph Hellwig
2021-09-17 15:33 ` Darrick J. Wong
2021-09-21 8:14 ` Christoph Hellwig
2021-09-16 6:23 ` Christoph Hellwig
2021-09-16 8:51 ` Shiyang Ruan
2021-09-15 10:45 ` [PATCH v9 8/8] xfs: Add dax dedupe support Shiyang Ruan
2021-09-16 0:30 ` Darrick J. Wong [this message]
2021-09-16 4:01 ` Shiyang Ruan
2021-09-16 4:18 ` Darrick J. Wong
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20210916003008.GE34830@magnolia \
--to=djwong@kernel.org \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=hch@lst.de \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=nvdimm@lists.linux.dev \
--cc=rgoldwyn@suse.de \
--cc=ruansy.fnst@fujitsu.com \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).