ocfs2-devel.oss.oracle.com archive mirror
 help / color / mirror / Atom feed
From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
	<linux-nvdimm@lists.01.org>, <linux-fsdevel@vger.kernel.org>
Cc: jack@suse.cz, darrick.wong@oracle.com, david@fromorbit.com,
	ocfs2-devel@oss.oracle.com, viro@zeniv.linux.org.uk,
	dan.j.williams@intel.com, linux-btrfs@vger.kernel.org
Subject: [Ocfs2-devel] [PATCH v3 09/10] fs/xfs: Handle CoW for fsdax write() path
Date: Fri, 19 Mar 2021 09:52:36 +0800	[thread overview]
Message-ID: <20210319015237.993880-10-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20210319015237.993880-1-ruansy.fnst@fujitsu.com>

In fsdax mode, WRITE and ZERO on a shared extent need CoW performed. After
CoW, new allocated extents needs to be remapped to the file.  So, add an
iomap_end for dax write ops to do the remapping work.

Signed-off-by: Shiyang Ruan <ruansy.fnst@fujitsu.com>
---
 fs/xfs/xfs_bmap_util.c |  3 +--
 fs/xfs/xfs_file.c      |  9 +++----
 fs/xfs/xfs_iomap.c     | 58 +++++++++++++++++++++++++++++++++++++++++-
 fs/xfs/xfs_iomap.h     |  4 +++
 fs/xfs/xfs_iops.c      |  7 +++--
 fs/xfs/xfs_reflink.c   |  3 +--
 6 files changed, 69 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 7371a7f7c652..809013de9915 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -976,8 +976,7 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	error = iomap_zero_range(VFS_I(ip), offset, len, NULL,
-			&xfs_buffered_write_iomap_ops);
+	error = xfs_iomap_zero_range(VFS_I(ip), offset, len, NULL);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5b0f93f73837..1987d15eab61 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -623,11 +623,8 @@ xfs_file_dax_write(
 	count = iov_iter_count(from);
 
 	trace_xfs_file_dax_write(ip, count, pos);
-	ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops);
-	if (ret > 0 && iocb->ki_pos > i_size_read(inode)) {
-		i_size_write(inode, iocb->ki_pos);
-		error = xfs_setfilesize(ip, pos, ret);
-	}
+	ret = dax_iomap_rw(iocb, from, &xfs_dax_write_iomap_ops);
+
 out:
 	xfs_iunlock(ip, iolock);
 	if (error)
@@ -1250,7 +1247,7 @@ __xfs_filemap_fault(
 
 		ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
 				(write_fault && !vmf->cow_page) ?
-				 &xfs_direct_write_iomap_ops :
+				 &xfs_dax_write_iomap_ops :
 				 &xfs_read_iomap_ops);
 		if (ret & VM_FAULT_NEEDDSYNC)
 			ret = dax_finish_sync_fault(vmf, pe_size, pfn);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 7b9ff824e82d..0afae5dbbce1 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -771,7 +771,8 @@ xfs_direct_write_iomap_begin(
 
 		/* may drop and re-acquire the ilock */
 		error = xfs_reflink_allocate_cow(ip, &imap, &cmap, &shared,
-				&lockmode, flags & IOMAP_DIRECT);
+				&lockmode,
+				flags & IOMAP_DIRECT || IS_DAX(inode));
 		if (error)
 			goto out_unlock;
 		if (shared)
@@ -850,6 +851,38 @@ const struct iomap_ops xfs_direct_write_iomap_ops = {
 	.iomap_begin		= xfs_direct_write_iomap_begin,
 };
 
+static int
+xfs_dax_write_iomap_end(
+	struct inode		*inode,
+	loff_t			pos,
+	loff_t			length,
+	ssize_t			written,
+	unsigned int		flags,
+	struct iomap		*iomap)
+{
+	int			error = 0;
+	xfs_inode_t		*ip = XFS_I(inode);
+	bool			cow = xfs_is_cow_inode(ip);
+
+	if (pos + written > i_size_read(inode)) {
+		i_size_write(inode, pos + written);
+		error = xfs_setfilesize(ip, pos, written);
+		if (error && cow) {
+			xfs_reflink_cancel_cow_range(ip, pos, written, true);
+			return error;
+		}
+	}
+	if (cow)
+		error = xfs_reflink_end_cow(ip, pos, written);
+
+	return error;
+}
+
+const struct iomap_ops xfs_dax_write_iomap_ops = {
+	.iomap_begin		= xfs_direct_write_iomap_begin,
+	.iomap_end		= xfs_dax_write_iomap_end,
+};
+
 static int
 xfs_buffered_write_iomap_begin(
 	struct inode		*inode,
@@ -1308,3 +1341,26 @@ xfs_xattr_iomap_begin(
 const struct iomap_ops xfs_xattr_iomap_ops = {
 	.iomap_begin		= xfs_xattr_iomap_begin,
 };
+
+int
+xfs_iomap_zero_range(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			len,
+	bool			*did_zero)
+{
+	return iomap_zero_range(inode, offset, len, did_zero,
+			IS_DAX(inode) ? &xfs_dax_write_iomap_ops :
+					&xfs_buffered_write_iomap_ops);
+}
+
+int
+xfs_iomap_truncate_page(
+	struct inode		*inode,
+	loff_t			pos,
+	bool			*did_zero)
+{
+	return iomap_truncate_page(inode, pos, did_zero,
+			IS_DAX(inode) ? &xfs_dax_write_iomap_ops :
+					&xfs_buffered_write_iomap_ops);
+}
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 7d3703556d0e..8adb2bf78a5a 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -14,6 +14,9 @@ struct xfs_bmbt_irec;
 int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb,
 		xfs_fileoff_t count_fsb, struct xfs_bmbt_irec *imap);
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
+int xfs_iomap_zero_range(struct inode *inode, loff_t offset, loff_t len,
+		bool *did_zero);
+int xfs_iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero);
 xfs_fileoff_t xfs_iomap_eof_align_last_fsb(struct xfs_inode *ip,
 		xfs_fileoff_t end_fsb);
 
@@ -42,6 +45,7 @@ xfs_aligned_fsb_count(
 
 extern const struct iomap_ops xfs_buffered_write_iomap_ops;
 extern const struct iomap_ops xfs_direct_write_iomap_ops;
+extern const struct iomap_ops xfs_dax_write_iomap_ops;
 extern const struct iomap_ops xfs_read_iomap_ops;
 extern const struct iomap_ops xfs_seek_iomap_ops;
 extern const struct iomap_ops xfs_xattr_iomap_ops;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 67c8dc9de8aa..2281161e05c8 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -889,8 +889,8 @@ xfs_setattr_size(
 	 */
 	if (newsize > oldsize) {
 		trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
-		error = iomap_zero_range(inode, oldsize, newsize - oldsize,
-				&did_zeroing, &xfs_buffered_write_iomap_ops);
+		error = xfs_iomap_zero_range(inode, oldsize, newsize - oldsize,
+				&did_zeroing);
 	} else {
 		/*
 		 * iomap won't detect a dirty page over an unwritten block (or a
@@ -902,8 +902,7 @@ xfs_setattr_size(
 						     newsize);
 		if (error)
 			return error;
-		error = iomap_truncate_page(inode, newsize, &did_zeroing,
-				&xfs_buffered_write_iomap_ops);
+		error = xfs_iomap_truncate_page(inode, newsize, &did_zeroing);
 	}
 
 	if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index f5b3a3da36b7..73c556c2ff76 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1245,8 +1245,7 @@ xfs_reflink_zero_posteof(
 		return 0;
 
 	trace_xfs_zero_eof(ip, isize, pos - isize);
-	return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
-			&xfs_buffered_write_iomap_ops);
+	return xfs_iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL);
 }
 
 /*
-- 
2.30.1




_______________________________________________
Ocfs2-devel mailing list
Ocfs2-devel@oss.oracle.com
https://oss.oracle.com/mailman/listinfo/ocfs2-devel

  parent reply	other threads:[~2021-03-19  1:53 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-03-19  1:52 [Ocfs2-devel] [PATCH v3 00/10] fsdax, xfs: Add reflink&dedupe support for fsdax Shiyang Ruan
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 01/10] fsdax: Factor helpers to simplify dax fault code Shiyang Ruan
2021-03-23 15:33   ` Ritesh Harjani
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 02/10] fsdax: Factor helper: dax_fault_actor() Shiyang Ruan
2021-03-23 15:48   ` Ritesh Harjani
2021-03-31  3:57     ` ruansy.fnst
2021-04-02  7:47   ` Christoph Hellwig
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 03/10] fsdax: Output address in dax_iomap_pfn() and rename it Shiyang Ruan
2021-03-23 15:54   ` Ritesh Harjani
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 04/10] fsdax: Introduce dax_iomap_cow_copy() Shiyang Ruan
2021-03-23 16:08   ` Ritesh Harjani
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 05/10] fsdax: Replace mmap entry in case of CoW Shiyang Ruan
2021-04-01  6:39   ` Ritesh Harjani
2021-04-01  7:03     ` ruansy.fnst
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 06/10] fsdax: Add dax_iomap_cow_copy() for dax_iomap_zero Shiyang Ruan
2021-04-01  6:45   ` Ritesh Harjani
2021-04-01  7:00     ` ruansy.fnst
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 07/10] iomap: Introduce iomap_apply2() for operations on two files Shiyang Ruan
2021-04-01  7:12   ` Ritesh Harjani
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 08/10] fsdax: Dedup file range to use a compare function Shiyang Ruan
2021-04-01 11:11   ` Ritesh Harjani
2021-04-08  3:21     ` ruansy.fnst
2021-03-19  1:52 ` Shiyang Ruan [this message]
2021-03-19  1:52 ` [Ocfs2-devel] [PATCH v3 10/10] fs/xfs: Add dedupe support for fsdax Shiyang Ruan
2021-03-23 15:27 ` [Ocfs2-devel] [PATCH v3 00/10] fsdax, xfs: Add reflink&dedupe " Ritesh Harjani
2021-04-02  7:49 ` Christoph Hellwig
2021-04-02  8:18   ` 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=20210319015237.993880-10-ruansy.fnst@fujitsu.com \
    --to=ruansy.fnst@fujitsu.com \
    --cc=dan.j.williams@intel.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=jack@suse.cz \
    --cc=linux-btrfs@vger.kernel.org \
    --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=ocfs2-devel@oss.oracle.com \
    --cc=viro@zeniv.linux.org.uk \
    --subject='Re: [Ocfs2-devel] [PATCH v3 09/10] fs/xfs: Handle CoW for fsdax write() path' \
    /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).