From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: Amir Goldstein <amir73il@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>,
Christoph Hellwig <hch@lst.de>,
Olga Kornievskaia <olga.kornievskaia@gmail.com>,
Luis Henriques <lhenriques@suse.com>,
Al Viro <viro@zeniv.linux.org.uk>,
linux-fsdevel@vger.kernel.org, linux-xfs@vger.kernel.org,
linux-nfs@vger.kernel.org, linux-cifs@vger.kernel.org,
ceph-devel@vger.kernel.org, linux-api@vger.kernel.org,
Dave Chinner <dchinner@redhat.com>
Subject: Re: [PATCH v2 7/8] vfs: allow copy_file_range to copy across devices
Date: Tue, 28 May 2019 09:34:25 -0700 [thread overview]
Message-ID: <20190528163425.GH5221@magnolia> (raw)
In-Reply-To: <20190526061100.21761-8-amir73il@gmail.com>
On Sun, May 26, 2019 at 09:10:58AM +0300, Amir Goldstein wrote:
> We want to enable cross-filesystem copy_file_range functionality
> where possible, so push the "same superblock only" checks down to
> the individual filesystem callouts so they can make their own
> decisions about cross-superblock copy offload and fallack to
> generic_copy_file_range() for cross-superblock copy.
>
> [Amir] We do not call ->remap_file_range() in case the inodes are not
> on the same sb and do not call ->copy_file_range() in case the inodes
> are not on the same filesystem type.
>
> This changes behavior of the copy_file_range(2) syscall, which will
> now allow cross filesystem in-kernel copy. CIFS already supports
> cross-superblock copy, between two shares to the same server. This
> functionality will now be available via the copy_file_range(2) syscall.
>
> Cc: Steve French <stfrench@microsoft.com>
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> Signed-off-by: Amir Goldstein <amir73il@gmail.com>
> ---
> fs/ceph/file.c | 4 +++-
> fs/cifs/cifsfs.c | 2 +-
> fs/fuse/file.c | 5 ++++-
> fs/nfs/nfs4file.c | 5 ++++-
> fs/read_write.c | 20 ++++++++++++++------
> 5 files changed, 26 insertions(+), 10 deletions(-)
>
> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
> index 54cfc877a6ef..adf99557c46c 100644
> --- a/fs/ceph/file.c
> +++ b/fs/ceph/file.c
> @@ -1909,6 +1909,8 @@ static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
>
> if (src_inode == dst_inode)
> return -EINVAL;
> + if (src_inode->i_sb != dst_inode->i_sb)
> + return -EXDEV;
> if (ceph_snap(dst_inode) != CEPH_NOSNAP)
> return -EROFS;
>
> @@ -2118,7 +2120,7 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
> ret = __ceph_copy_file_range(src_file, src_off, dst_file, dst_off,
> len, flags);
>
> - if (ret == -EOPNOTSUPP)
> + if (ret == -EOPNOTSUPP || ret == -EXDEV)
> ret = generic_copy_file_range(src_file, src_off, dst_file,
> dst_off, len, flags);
> return ret;
> diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
> index e103b499aaa8..7bde046110ce 100644
> --- a/fs/cifs/cifsfs.c
> +++ b/fs/cifs/cifsfs.c
> @@ -1152,7 +1152,7 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
> len, flags);
> free_xid(xid);
>
> - if (rc == -EOPNOTSUPP)
> + if (rc == -EOPNOTSUPP || rc == -EXDEV)
> rc = generic_copy_file_range(src_file, off, dst_file,
> destoff, len, flags);
> return rc;
> diff --git a/fs/fuse/file.c b/fs/fuse/file.c
> index 3531d4a3d9ec..180161f6f0bd 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -3126,6 +3126,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
> if (fc->no_copy_file_range)
> return -EOPNOTSUPP;
>
> + if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
> + return -EXDEV;
> +
> inode_lock(inode_out);
>
> err = generic_copy_file_range_prep(file_in, file_out);
> @@ -3186,7 +3189,7 @@ static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off,
> ret = __fuse_copy_file_range(src_file, src_off, dst_file, dst_off,
> len, flags);
>
> - if (ret == -EOPNOTSUPP)
> + if (ret == -EOPNOTSUPP || ret == -EXDEV)
> ret = generic_copy_file_range(src_file, src_off, dst_file,
> dst_off, len, flags);
> return ret;
> diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
> index 4842f3ab3161..f4157eb1f69d 100644
> --- a/fs/nfs/nfs4file.c
> +++ b/fs/nfs/nfs4file.c
> @@ -133,6 +133,9 @@ static ssize_t __nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
> struct file *file_out, loff_t pos_out,
> size_t count, unsigned int flags)
> {
> + /* Only offload copy if superblock is the same */
> + if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
> + return -EXDEV;
> if (!nfs_server_capable(file_inode(file_out), NFS_CAP_COPY))
> return -EOPNOTSUPP;
> if (file_inode(file_in) == file_inode(file_out))
> @@ -148,7 +151,7 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
>
> ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count,
> flags);
> - if (ret == -EOPNOTSUPP)
> + if (ret == -EOPNOTSUPP || ret == -EXDEV)
> ret = generic_copy_file_range(file_in, pos_in, file_out,
> pos_out, count, flags);
> return ret;
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 4b23a86aacd9..283ec30d2136 100644
> --- a/fs/read_write.c
> +++ b/fs/read_write.c
> @@ -1640,7 +1640,18 @@ static ssize_t do_copy_file_range(struct file *file_in, loff_t pos_in,
> struct file *file_out, loff_t pos_out,
> size_t len, unsigned int flags)
> {
> - if (file_out->f_op->copy_file_range)
> + /*
> + * Although we now allow filesystems to handle cross sb copy, passing
> + * an inode of the wrong filesystem type to filesystem operation can
> + * often result in an attempt to dereference the wrong concrete inode
> + * struct, so avoid doing that until we really have a good reason.
> + * The incentive for passing inode from different sb to filesystem is
> + * NFS cross server copy and for that use case, enforcing same
> + * filesystem type is acceptable.
> + */
> + if (file_out->f_op->copy_file_range &&
> + file_inode(file_in)->i_sb->s_type ==
> + file_inode(file_out)->i_sb->s_type)
> return file_out->f_op->copy_file_range(file_in, pos_in,
> file_out, pos_out,
> len, flags);
> @@ -1663,10 +1674,6 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
> if (flags != 0)
> return -EINVAL;
>
> - /* this could be relaxed once a method supports cross-fs copies */
> - if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
> - return -EXDEV;
> -
> ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len,
> flags);
> if (unlikely(ret))
> @@ -1689,7 +1696,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
> * Try cloning first, this is supported by more file systems, and
> * more efficient if both clone and copy are supported (e.g. NFS).
> */
> - if (file_in->f_op->remap_file_range) {
> + if (file_in->f_op->remap_file_range &&
> + file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) {
For the fs/read_write.c bits,
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
(I'm not going to pass judgement on whether or not cifs/nfs should be
doing cross-sb copies, as I know nothing about how well that works in
practice.)
--D
> loff_t cloned;
>
> cloned = file_in->f_op->remap_file_range(file_in, pos_in,
> --
> 2.17.1
>
next prev parent reply other threads:[~2019-05-28 16:35 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-26 6:10 [PATCH v2 0/8] Fixes for major copy_file_range() issues Amir Goldstein
2019-05-26 6:10 ` [PATCH v2 1/8] vfs: introduce generic_copy_file_range() Amir Goldstein
2019-05-28 16:11 ` Darrick J. Wong
2019-05-26 6:10 ` [PATCH v2 2/8] vfs: no fallback for ->copy_file_range Amir Goldstein
2019-05-28 16:09 ` Darrick J. Wong
2019-05-26 6:10 ` [PATCH v2 3/8] vfs: introduce generic_file_rw_checks() Amir Goldstein
2019-05-28 16:14 ` Darrick J. Wong
2019-05-26 6:10 ` [PATCH v2 4/8] vfs: add missing checks to copy_file_range Amir Goldstein
2019-05-28 16:18 ` Darrick J. Wong
2019-05-28 16:26 ` Amir Goldstein
2019-05-28 16:31 ` Darrick J. Wong
2019-05-28 16:39 ` Amir Goldstein
2019-05-26 6:10 ` [PATCH v2 5/8] vfs: copy_file_range needs to strip setuid bits Amir Goldstein
2019-05-28 16:25 ` Darrick J. Wong
2019-05-31 19:34 ` J. Bruce Fields
2019-05-26 6:10 ` [PATCH v2 6/8] vfs: copy_file_range should update file timestamps Amir Goldstein
2019-05-27 14:35 ` Luis Henriques
2019-05-27 22:05 ` Dave Chinner
2019-05-28 8:53 ` Luis Henriques
2019-05-28 16:30 ` Darrick J. Wong
2019-05-28 16:36 ` Amir Goldstein
2019-05-26 6:10 ` [PATCH v2 7/8] vfs: allow copy_file_range to copy across devices Amir Goldstein
2019-05-28 16:34 ` Darrick J. Wong [this message]
2019-05-26 6:10 ` [PATCH v2 8/8] vfs: remove redundant checks from generic_remap_checks() Amir Goldstein
2019-05-28 16:37 ` Darrick J. Wong
2019-05-26 6:11 ` [PATCH v2 9/8] man-pages: copy_file_range updates Amir Goldstein
2019-05-28 16:48 ` Darrick J. Wong
2019-05-29 16:20 ` Amir Goldstein
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=20190528163425.GH5221@magnolia \
--to=darrick.wong@oracle.com \
--cc=amir73il@gmail.com \
--cc=ceph-devel@vger.kernel.org \
--cc=david@fromorbit.com \
--cc=dchinner@redhat.com \
--cc=hch@lst.de \
--cc=lhenriques@suse.com \
--cc=linux-api@vger.kernel.org \
--cc=linux-cifs@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-nfs@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=olga.kornievskaia@gmail.com \
--cc=viro@zeniv.linux.org.uk \
/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).