DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org C1690208A3
Message-ID: <679f1cda1b43fc4cfcd6cdf6dbac223b42db24c2.camel@gmail.com>
Subject: Re: [PATCH 09/11] vfs: push copy_file_ranges -EXDEV checks down
From:   Anna Schumaker <schumaker.anna@gmail.com>
To:     Dave Chinner <david@fromorbit.com>, linux-fsdevel@vger.kernel.org,
        linux-xfs@vger.kernel.org
Cc:     olga.kornievskaia@gmail.com, linux-nfs@vger.kernel.org,
        linux-unionfs@vger.kernel.org, ceph-devel@vger.kernel.org,
        linux-cifs@vger.kernel.org
Date:   Mon, 03 Dec 2018 13:53:35 -0500
In-Reply-To: <20181203083416.28978-10-david@fromorbit.com>
References: <20181203083416.28978-1-david@fromorbit.com>
         <20181203083416.28978-10-david@fromorbit.com>
Content-Type: text/plain; charset="UTF-8"
User-Agent: Evolution 3.30.2 
Mime-Version: 1.0
Content-Transfer-Encoding: 7bit
Sender: linux-nfs-owner@vger.kernel.org
Precedence: bulk

On Mon, 2018-12-03 at 19:34 +1100, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> 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.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> ---
>  fs/ceph/file.c      |  4 +++-
>  fs/cifs/cifsfs.c    |  8 +++++++-
>  fs/fuse/file.c      |  5 ++++-
>  fs/nfs/nfs4file.c   | 16 ++++++++++------
>  fs/overlayfs/file.c | 10 +++++++++-
>  fs/read_write.c     | 10 ++++------
>  6 files changed, 37 insertions(+), 16 deletions(-)
> 
> diff --git a/fs/ceph/file.c b/fs/ceph/file.c
> index cf29f0410dcb..eb876e19c1dc 100644
> --- a/fs/ceph/file.c
> +++ b/fs/ceph/file.c
> @@ -1905,6 +1905,8 @@ 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;
>  
> @@ -2105,7 +2107,7 @@ 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 5ef4baec6234..03e4b9eacbd1 100644
> --- a/fs/cifs/cifsfs.c
> +++ b/fs/cifs/cifsfs.c
> @@ -1072,6 +1072,12 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
>  		goto out;
>  	}
>  
> +	if (src_inode->i_sb != target_inode->i_sb) {
> +		rc = -EXDEV;
> +		goto out;
> +	}
> +
> +
>  	if (!src_file->private_data || !dst_file->private_data) {
>  		rc = -EBADF;
>  		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
> @@ -1142,7 +1148,7 @@ 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 b86fb0298739..0758f831a4eb 100644
> --- a/fs/fuse/file.c
> +++ b/fs/fuse/file.c
> @@ -3053,6 +3053,9 @@ 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);
>  
>  	if (fc->writeback_cache) {
> @@ -3109,7 +3112,7 @@ 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 d7766a6eb0f4..4783c0c1c49e 100644
> --- a/fs/nfs/nfs4file.c
> +++ b/fs/nfs/nfs4file.c
> @@ -133,16 +133,20 @@ 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)
>  {
> -	ssize_t ret;
> +	ssize_t ret = -EXDEV;
>  
>  	if (file_inode(file_in) == file_inode(file_out))
>  		return -EINVAL;
> -retry:
> -	ret = nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
> -	if (ret == -EAGAIN)
> -		goto retry;
>  
> -	if (ret == -EOPNOTSUPP)
> +	/* only offload copy if superblock is the same */
> +	if (file_inode(file_in)->i_sb == file_inode(file_out)->i_sb) {
> +		do {
> +			ret = nfs42_proc_copy(file_in, pos_in, file_out,
> +					pos_out, count);
> +		} while (ret == -EAGAIN);

I'm not convinced we can actually return -EAGAIN from nfs42_proc_copy().  The
nfs_get_lock_context() function doesn't return it, and if _nfs42_proc_copy()
returns -EAGAIN it's immediately retried by nfs42_proc_copy() instead of
returning.

Olga, am I missing something here?
Anna

> +	}
> +
> +	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/overlayfs/file.c b/fs/overlayfs/file.c
> index 68736e5d6a56..34fb0398d016 100644
> --- a/fs/overlayfs/file.c
> +++ b/fs/overlayfs/file.c
> @@ -443,6 +443,14 @@ static loff_t ovl_copyfile(struct file *file_in, loff_t
> pos_in,
>  	const struct cred *old_cred;
>  	loff_t ret;
>  
> +	/*
> +	 * Temporary. Cross device copy checks should be left to the copy file
> +	 * call on the real inodes, but existing behaviour checks the upper
> +	 * files only.
> +	 */
> +	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
> +		return -EXDEV;
> +
>  	ret = ovl_real_fdget(file_out, &real_out);
>  	if (ret)
>  		return ret;
> @@ -491,7 +499,7 @@ static ssize_t ovl_copy_file_range(struct file *file_in,
> loff_t pos_in,
>  	ret =  ovl_copyfile(file_in, pos_in, file_out, pos_out, len, flags,
>  			    OVL_COPY);
>  
> -	if (ret == -EOPNOTSUPP)
> +	if (ret == -EOPNOTSUPP || ret == -EXDEV)
>  		ret = generic_copy_file_range(file_in, pos_in, file_out,
>  					pos_out, len, flags);
>  	return ret;
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 174cf92eea1d..4e0666de0d69 100644
> --- a/fs/read_write.c
> +++ b/fs/read_write.c
> @@ -1565,6 +1565,10 @@ ssize_t generic_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)
>  {
> +	/* Temporary, do_splice_direct supports cross-sb copies */
> +	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
> +		return -EXDEV;
> +
>  	return do_splice_direct(file_in, &pos_in, file_out, &pos_out,
>  			len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
>  }
> @@ -1611,17 +1615,11 @@ ssize_t vfs_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)
>  {
> -	struct inode *inode_in = file_inode(file_in);
> -	struct inode *inode_out = file_inode(file_out);
>  	ssize_t ret;
>  
>  	if (flags != 0)
>  		return -EINVAL;
>  
> -	/* this could be relaxed once a method supports cross-fs copies */
> -	if (inode_in->i_sb != inode_out->i_sb)
> -		return -EXDEV;
> -
>  	ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len,
>  					flags);
>  	if (ret < 0)