From: Shiyang Ruan <ruansy.fnst@fujitsu.com>
To: <djwong@kernel.org>, <hch@lst.de>, <linux-xfs@vger.kernel.org>
Cc: <ruansy.fnst@fujitsu.com>, <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: [PATCH v9 7/8] xfs: support CoW in fsdax mode
Date: Wed, 15 Sep 2021 18:45:00 +0800 [thread overview]
Message-ID: <20210915104501.4146910-8-ruansy.fnst@fujitsu.com> (raw)
In-Reply-To: <20210915104501.4146910-1-ruansy.fnst@fujitsu.com>
In fsdax mode, WRITE and ZERO on a shared extent need CoW performed.
After that, new allocated extents needs to be remapped to the file.
So, add a CoW identification in ->iomap_begin(), and implement
->iomap_end() 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 | 6 +++---
fs/xfs/xfs_iomap.c | 38 +++++++++++++++++++++++++++++++++++++-
fs/xfs/xfs_iomap.h | 30 ++++++++++++++++++++++++++++++
fs/xfs/xfs_iops.c | 7 +++----
fs/xfs/xfs_reflink.c | 3 +--
6 files changed, 75 insertions(+), 12 deletions(-)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 73a36b7be3bd..0681250e0a5d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1009,8 +1009,7 @@ 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(ip, offset, len, NULL);
if (error)
return error;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 7aa943edfc02..2ef1930374d2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -704,7 +704,7 @@ xfs_file_dax_write(
pos = iocb->ki_pos;
trace_xfs_file_dax_write(iocb, from);
- ret = dax_iomap_rw(iocb, from, &xfs_direct_write_iomap_ops);
+ ret = dax_iomap_rw(iocb, from, &xfs_dax_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);
@@ -1329,8 +1329,8 @@ __xfs_filemap_fault(
xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
ret = dax_iomap_fault(vmf, pe_size, &pfn, NULL,
(write_fault && !vmf->cow_page) ?
- &xfs_direct_write_iomap_ops :
- &xfs_read_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);
xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 093758440ad5..6fa3b377cb81 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -761,7 +761,8 @@ 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)
@@ -854,6 +855,41 @@ 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 flags,
+ struct iomap *iomap)
+{
+ struct xfs_inode *ip = XFS_I(inode);
+ /*
+ * Usually we use @written to indicate whether the operation was
+ * successful. But it is always positive or zero. The CoW needs the
+ * actual error code from actor(). So, get it from
+ * iomap_iter->processed.
+ */
+ const struct iomap_iter *iter =
+ container_of(iomap, typeof(*iter), iomap);
+
+ if (!xfs_is_cow_inode(ip))
+ return 0;
+
+ if (iter->processed <= 0) {
+ xfs_reflink_cancel_cow_range(ip, pos, length, true);
+ return 0;
+ }
+
+ return xfs_reflink_end_cow(ip, pos, iter->processed);
+}
+
+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,
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 7d3703556d0e..92679a0c3578 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -45,5 +45,35 @@ extern const struct iomap_ops xfs_direct_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;
+extern const struct iomap_ops xfs_dax_write_iomap_ops;
+
+static inline int
+xfs_iomap_zero_range(
+ struct xfs_inode *ip,
+ loff_t pos,
+ loff_t len,
+ bool *did_zero)
+{
+ struct inode *inode = VFS_I(ip);
+
+ return iomap_zero_range(inode, pos, len, did_zero,
+ IS_DAX(inode) ?
+ &xfs_dax_write_iomap_ops :
+ &xfs_buffered_write_iomap_ops);
+}
+
+static inline int
+xfs_iomap_truncate_page(
+ struct xfs_inode *ip,
+ loff_t pos,
+ bool *did_zero)
+{
+ struct inode *inode = VFS_I(ip);
+
+ return iomap_truncate_page(inode, pos, did_zero,
+ IS_DAX(inode)?
+ &xfs_dax_write_iomap_ops :
+ &xfs_buffered_write_iomap_ops);
+}
#endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index a607d6aca5c4..332e6208dffd 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -911,8 +911,8 @@ 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(ip, oldsize, newsize - oldsize,
+ &did_zeroing);
} else {
/*
* iomap won't detect a dirty page over an unwritten block (or a
@@ -924,8 +924,7 @@ 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(ip, newsize, &did_zeroing);
}
if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 7ecea0311e88..9d876e268734 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1269,8 +1269,7 @@ 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(ip, isize, pos - isize, NULL);
}
/*
--
2.33.0
next prev parent reply other threads:[~2021-09-15 10:46 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 ` Shiyang Ruan [this message]
2021-09-16 0:22 ` [PATCH v9 7/8] xfs: support CoW in fsdax mode 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
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=20210915104501.4146910-8-ruansy.fnst@fujitsu.com \
--to=ruansy.fnst@fujitsu.com \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=djwong@kernel.org \
--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=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).