Linux-NVDIMM Archive on lore.kernel.org
 help / color / Atom feed
From: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
To: linux-xfs@vger.kernel.org, linux-nvdimm@lists.01.org,
	darrick.wong@oracle.com
Cc: qi.fuli@fujitsu.com, gujx@cn.fujitsu.com, rgoldwyn@suse.de,
	david@fromorbit.com, linux-kernel@vger.kernel.org
Subject: [RFC PATCH 6/7] xfs: Add COW handle for fsdax.
Date: Wed, 31 Jul 2019 19:49:34 +0800
Message-ID: <20190731114935.11030-7-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20190731114935.11030-1-ruansy.fnst@cn.fujitsu.com>

WRITE and ZERO on a shared extent need to perform COW.  For direct io in
dax mode, it is handled like WRITE, but with block aligned.  So COW
seems a bit redundant for it.

Because of COW, new extent has been allocated.  The extent list needs to
be updated at the end.

Signed-off-by: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
---
 fs/xfs/xfs_iomap.c   | 42 +++++++++++++++++++++++++-----------------
 fs/xfs/xfs_reflink.c |  1 +
 2 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 6116a75f03da..ae3b9bf5d784 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -930,10 +930,10 @@ xfs_file_iomap_begin(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_bmbt_irec	imap;
+	struct xfs_bmbt_irec	imap = { 0 }, cmap = { 0 };
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			nimaps = 1, error = 0;
-	bool			shared = false;
+	bool			shared = false, need_cow = false;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -967,6 +967,8 @@ xfs_file_iomap_begin(
 	if (error)
 		goto out_unlock;
 
+	cmap = imap;
+
 	if (flags & IOMAP_REPORT) {
 		/* Trim the mapping to the nearest shared extent boundary. */
 		error = xfs_reflink_trim_around_shared(ip, &imap, &shared);
@@ -983,8 +985,7 @@ xfs_file_iomap_begin(
 	 * been done up front, so we don't need to do them here.
 	 */
 	if (xfs_is_cow_inode(ip)) {
-		struct xfs_bmbt_irec	cmap;
-		bool			directio = (flags & IOMAP_DIRECT);
+		bool directio = flags & IOMAP_DIRECT;
 
 		/* if zeroing doesn't need COW allocation, then we are done. */
 		if ((flags & IOMAP_ZERO) &&
@@ -992,23 +993,21 @@ xfs_file_iomap_begin(
 			goto out_found;
 
 		/* may drop and re-acquire the ilock */
-		cmap = imap;
 		error = xfs_reflink_allocate_cow(ip, &cmap, &shared, &lockmode,
-				directio);
+						 directio || IS_DAX(inode));
 		if (error)
 			goto out_unlock;
 
 		/*
-		 * For buffered writes we need to report the address of the
-		 * previous block (if there was any) so that the higher level
-		 * write code can perform read-modify-write operations; we
-		 * won't need the CoW fork mapping until writeback.  For direct
-		 * I/O, which must be block aligned, we need to report the
-		 * newly allocated address.  If the data fork has a hole, copy
-		 * the COW fork mapping to avoid allocating to the data fork.
+		 * WRITE and ZERO on a shared extent under dax mode need to
+		 * perform COW, source address will be reported in srcmap.
 		 */
-		if (directio || imap.br_startblock == HOLESTARTBLOCK)
+		if (imap.br_startblock != HOLESTARTBLOCK && IS_DAX(inode) &&
+		    shared) {
+			need_cow = true;
+		} else {
 			imap = cmap;
+		}
 
 		end_fsb = imap.br_startoff + imap.br_blockcount;
 		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
@@ -1044,8 +1043,7 @@ xfs_file_iomap_begin(
 	 */
 	if (lockmode == XFS_ILOCK_EXCL)
 		xfs_ilock_demote(ip, lockmode);
-	error = xfs_iomap_write_direct(ip, offset, length, &imap,
-			nimaps);
+	error = xfs_iomap_write_direct(ip, offset, length, &imap, nimaps);
 	if (error)
 		return error;
 
@@ -1053,7 +1051,15 @@ xfs_file_iomap_begin(
 	trace_xfs_iomap_alloc(ip, offset, length, XFS_DATA_FORK, &imap);
 
 out_finish:
-	return xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
+	if (need_cow) {
+		error = xfs_bmbt_to_iomap(ip, iomap, &cmap, shared);
+		if (error)
+			return error;
+		iomap->flags |= IOMAP_F_NEW;
+		iomap->type = IOMAP_COW;
+		return xfs_bmbt_to_iomap(ip, srcmap, &imap, shared);
+	} else
+		return xfs_bmbt_to_iomap(ip, iomap, &imap, shared);
 
 out_found:
 	ASSERT(nimaps);
@@ -1135,6 +1141,8 @@ xfs_file_iomap_end(
 	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
 		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
 				length, written, iomap);
+	else if (iomap->type == IOMAP_COW && written)
+		return xfs_reflink_end_cow(XFS_I(inode), offset, length);
 	return 0;
 }
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 68e4257cebb0..a1b000be3699 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -446,6 +446,7 @@ xfs_reflink_allocate_cow(
 	 */
 	if (!convert_now || imap->br_state == XFS_EXT_NORM)
 		return 0;
+	imap->br_state = XFS_EXT_NORM;
 	trace_xfs_reflink_convert_cow(ip, imap);
 	return xfs_reflink_convert_cow_locked(ip, offset_fsb, count_fsb);
 
-- 
2.17.0



_______________________________________________
Linux-nvdimm mailing list
Linux-nvdimm@lists.01.org
https://lists.01.org/mailman/listinfo/linux-nvdimm

  parent reply index

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-31 11:49 [RFC PATCH 0/7] xfs: add reflink & dedupe support " Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 1/7] dax: Introduce dax_copy_edges() for COW Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 2/7] dax: copy data before write Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 3/7] dax: replace mmap entry in case of CoW Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 4/7] fs: dedup file range to use a compare function Shiyang Ruan
2019-07-31 11:49 ` [RFC PATCH 5/7] dax: memcpy before zeroing range Shiyang Ruan
2019-07-31 11:49 ` Shiyang Ruan [this message]
2019-07-31 11:49 ` [RFC PATCH 7/7] xfs: Add dedupe support for fsdax Shiyang Ruan
2019-07-31 20:33 ` [RFC PATCH 0/7] xfs: add reflink & " Goldwyn Rodrigues
2019-08-01  1:37   ` Shiyang Ruan
2019-08-05  0:21     ` Dave Chinner
2019-10-09  6:31 ` Christoph Hellwig
2019-10-09 17:11   ` Darrick J. Wong
2019-10-10  7:30     ` Dave Chinner

Reply instructions:

You may reply publically 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=20190731114935.11030-7-ruansy.fnst@cn.fujitsu.com \
    --to=ruansy.fnst@cn.fujitsu.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=gujx@cn.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=qi.fuli@fujitsu.com \
    --cc=rgoldwyn@suse.de \
    /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

Linux-NVDIMM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvdimm/0 linux-nvdimm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvdimm linux-nvdimm/ https://lore.kernel.org/linux-nvdimm \
		linux-nvdimm@lists.01.org
	public-inbox-index linux-nvdimm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.01.lists.linux-nvdimm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git