linux-nvdimm.lists.01.org archive mirror
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <djwong@kernel.org>
To: Shiyang Ruan <ruansy.fnst@fujitsu.com>
Cc: linux-kernel@vger.kernel.org, linux-xfs@vger.kernel.org,
	linux-nvdimm@lists.01.org, linux-fsdevel@vger.kernel.org,
	darrick.wong@oracle.com, willy@infradead.org,
	viro@zeniv.linux.org.uk, david@fromorbit.com, hch@lst.de,
	rgoldwyn@suse.de
Subject: Re: [PATCH v5 7/7] fs/xfs: Add dax dedupe support
Date: Tue, 11 May 2021 18:04:28 -0700	[thread overview]
Message-ID: <20210512010428.GQ8582@magnolia> (raw)
In-Reply-To: <20210511030933.3080921-8-ruansy.fnst@fujitsu.com>

On Tue, May 11, 2021 at 11:09:33AM +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>
> ---
>  fs/xfs/xfs_file.c    |  2 +-
>  fs/xfs/xfs_inode.c   | 66 +++++++++++++++++++++++++++++++++++++++++++-
>  fs/xfs/xfs_inode.h   |  1 +
>  fs/xfs/xfs_reflink.c |  4 +--
>  4 files changed, 69 insertions(+), 4 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..0774b6e2b940 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
> @@ -3711,6 +3711,64 @@ xfs_iolock_two_inodes_and_break_layout(
>  	return 0;
>  }
>  
> +static int
> +xfs_mmaplock_two_inodes_and_break_dax_layout(
> +	struct inode		*src,
> +	struct inode		*dest)

MMAPLOCK is an xfs_inode lock, so please pass those in here.

> +{
> +	int			error, attempts = 0;
> +	bool			retry;
> +	struct xfs_inode	*ip0, *ip1;
> +	struct page		*page;
> +	struct xfs_log_item	*lp;
> +
> +	if (src > dest)
> +		swap(src, dest);

The MMAPLOCK (and ILOCK) locking order is increasing inode number, not
the address of the incore object.  This is different (and not consistent
with) i_rwsem/XFS_IOLOCK, but those are the rules.

> +	ip0 = XFS_I(src);
> +	ip1 = XFS_I(dest);
> +
> +again:
> +	retry = false;
> +	/* Lock the first inode */
> +	xfs_ilock(ip0, XFS_MMAPLOCK_EXCL);
> +	error = xfs_break_dax_layouts(src, &retry);
> +	if (error || retry) {
> +		xfs_iunlock(ip0, XFS_MMAPLOCK_EXCL);
> +		goto again;
> +	}
> +
> +	if (src == dest)
> +		return 0;
> +
> +	/* Nested lock the second inode */
> +	lp = &ip0->i_itemp->ili_item;
> +	if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) {
> +		if (!xfs_ilock_nowait(ip1,
> +		    xfs_lock_inumorder(XFS_MMAPLOCK_EXCL, 1))) {
> +			xfs_iunlock(ip0, XFS_MMAPLOCK_EXCL);
> +			if ((++attempts % 5) == 0)
> +				delay(1); /* Don't just spin the CPU */
> +			goto again;
> +		}
> +	} else
> +		xfs_ilock(ip1, 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(dest->i_mapping);
> +	if (page) {
> +		if (page_ref_count(page) != 1) {

This could be flattened to:

	if (page && page_ref_count(page) != 1) {
		...
	}

--D

> +			xfs_iunlock(ip1, XFS_MMAPLOCK_EXCL);
> +			xfs_iunlock(ip0, XFS_MMAPLOCK_EXCL);
> +			goto again;
> +		}
> +	}
> +
> +	return 0;
> +}
> +
>  /*
>   * Lock two inodes so that userspace cannot initiate I/O via file syscalls or
>   * mmap activity.
> @@ -3721,10 +3779,16 @@ xfs_ilock2_io_mmap(
>  	struct xfs_inode	*ip2)
>  {
>  	int			ret;
> +	struct inode		*ino1 = VFS_I(ip1);
> +	struct inode		*ino2 = 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(ino1, ino2);
>  	if (ret)
>  		return ret;
> +
> +	if (IS_DAX(ino1) && IS_DAX(ino2))
> +		return xfs_mmaplock_two_inodes_and_break_dax_layout(ino1, ino2);
> +
>  	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
> 
> 
> 
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org

  reply	other threads:[~2021-05-12  1:04 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-05-11  3:09 [PATCH v5 0/7] fsdax,xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-05-11  3:09 ` [PATCH v5 1/7] fsdax: Introduce dax_iomap_cow_copy() Shiyang Ruan
2021-05-12  1:08   ` Darrick J. Wong
2021-05-13  7:57     ` ruansy.fnst
2021-05-13 15:02       ` Darrick J. Wong
2021-05-11  3:09 ` [PATCH v5 2/7] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-05-12  1:09   ` Darrick J. Wong
2021-05-11  3:09 ` [PATCH v5 3/7] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-05-12  1:17   ` Darrick J. Wong
2021-05-12  1:37     ` ruansy.fnst
2021-05-12  2:27   ` Mika Penttilä
2021-05-13  7:48     ` ruansy.fnst
2021-05-11  3:09 ` [PATCH v5 4/7] iomap: Introduce iomap_apply2() for operations on two files Shiyang Ruan
2021-05-11  3:09 ` [PATCH v5 5/7] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-05-12  1:23   ` Darrick J. Wong
2021-05-14  8:35     ` ruansy.fnst
2021-05-14 16:03       ` Darrick J. Wong
2021-05-11  3:09 ` [PATCH v5 6/7] fs/xfs: Handle CoW for fsdax write() path Shiyang Ruan
2021-05-12  1:30   ` Darrick J. Wong
2021-05-11  3:09 ` [PATCH v5 7/7] fs/xfs: Add dax dedupe support Shiyang Ruan
2021-05-12  1:04   ` Darrick J. Wong [this message]
2021-05-12  1:26     ` ruansy.fnst
2021-05-11  3:57 ` [PATCH v5 0/7] fsdax,xfs: Add reflink&dedupe support for fsdax Darrick J. Wong
2021-05-11  5:53   ` ruansy.fnst

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=20210512010428.GQ8582@magnolia \
    --to=djwong@kernel.org \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@lst.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=rgoldwyn@suse.de \
    --cc=ruansy.fnst@fujitsu.com \
    --cc=viro@zeniv.linux.org.uk \
    --cc=willy@infradead.org \
    --subject='Re: [PATCH v5 7/7] fs/xfs: Add dax dedupe support' \
    /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

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).