Re: [PATCH 2/4] vfs: pull btrfs clone API to vfs layer

["Darrick J. Wong" <darrick.wong@oracle.com>]

On Thu, Dec 03, 2015 at 12:59:50PM +0100, Christoph Hellwig wrote:
> The btrfs clone ioctls are now adopted by other file systems, with NFS
> and CIFS already having support for them, and XFS being under active
> development.  To avoid growth of various slightly incompatible
> implementations, add one to the VFS.  Note that clones are different from
> file copies in several ways:
> 
>  - they are atomic vs other writers
>  - they support whole file clones
>  - they support 64-bit legth clones
>  - they do not allow partial success (aka short writes)
>  - clones are expected to be a fast metadata operation
> 
> Because of that it would be rather cumbersome to try to piggyback them on
> top of the recent clone_file_range infrastructure.  The converse isn't
> true and the clone_file_range system call could try clone file range as
> a first attempt to copy, something that further patches will enable.
> 
> Based on earlier work from Peng Tao.
> 
> Signed-off-by: Christoph Hellwig <hch@lst.de>
> ---
>  fs/btrfs/ctree.h        |   3 +-
>  fs/btrfs/file.c         |   1 +
>  fs/btrfs/ioctl.c        |  49 ++-----------------
>  fs/cifs/cifsfs.c        |  63 ++++++++++++++++++++++++
>  fs/cifs/cifsfs.h        |   1 -
>  fs/cifs/ioctl.c         | 126 +++++++++++++++++++++++-------------------------
>  fs/ioctl.c              |  29 +++++++++++

I tried this patch series on ppc64 (w/ 32-bit powerpc userland) and I think
it needs to fix up the compat ioctl to make the vfs call...

diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index dcf2653..70d4b10 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1580,6 +1580,10 @@ COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd,
                goto out_fput;
 #endif
 
+       case FICLONE:
+       case FICLONERANGE:
+               goto do_ioctl;
+
        case FIBMAP:
        case FIGETBSZ:
        case FIONREAD:

--D

>  fs/nfs/nfs4file.c       |  87 ++++-----------------------------
>  fs/read_write.c         |  72 +++++++++++++++++++++++++++
>  include/linux/fs.h      |   7 ++-
>  include/uapi/linux/fs.h |   9 ++++
>  11 files changed, 254 insertions(+), 193 deletions(-)
> 
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index ede7277..dd4733f 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -4025,7 +4025,6 @@ void btrfs_get_block_group_info(struct list_head *groups_list,
>  void update_ioctl_balance_args(struct btrfs_fs_info *fs_info, int lock,
>  			       struct btrfs_ioctl_balance_args *bargs);
>  
> -
>  /* file.c */
>  int btrfs_auto_defrag_init(void);
>  void btrfs_auto_defrag_exit(void);
> @@ -4058,6 +4057,8 @@ int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
>  ssize_t btrfs_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);
> +int btrfs_clone_file_range(struct file *file_in, loff_t pos_in,
> +			   struct file *file_out, loff_t pos_out, u64 len);
>  
>  /* tree-defrag.c */
>  int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
> diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> index e67fe6a..232e300 100644
> --- a/fs/btrfs/file.c
> +++ b/fs/btrfs/file.c
> @@ -2925,6 +2925,7 @@ const struct file_operations btrfs_file_operations = {
>  	.compat_ioctl	= btrfs_ioctl,
>  #endif
>  	.copy_file_range = btrfs_copy_file_range,
> +	.clone_file_range = btrfs_clone_file_range,
>  };
>  
>  void btrfs_auto_defrag_exit(void)
> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
> index 0f92735..85b1cae 100644
> --- a/fs/btrfs/ioctl.c
> +++ b/fs/btrfs/ioctl.c
> @@ -3906,49 +3906,10 @@ ssize_t btrfs_copy_file_range(struct file *file_in, loff_t pos_in,
>  	return ret;
>  }
>  
> -static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd,
> -				       u64 off, u64 olen, u64 destoff)
> +int btrfs_clone_file_range(struct file *src_file, loff_t off,
> +		struct file *dst_file, loff_t destoff, u64 len)
>  {
> -	struct fd src_file;
> -	int ret;
> -
> -	/* the destination must be opened for writing */
> -	if (!(file->f_mode & FMODE_WRITE) || (file->f_flags & O_APPEND))
> -		return -EINVAL;
> -
> -	ret = mnt_want_write_file(file);
> -	if (ret)
> -		return ret;
> -
> -	src_file = fdget(srcfd);
> -	if (!src_file.file) {
> -		ret = -EBADF;
> -		goto out_drop_write;
> -	}
> -
> -	/* the src must be open for reading */
> -	if (!(src_file.file->f_mode & FMODE_READ)) {
> -		ret = -EINVAL;
> -		goto out_fput;
> -	}
> -
> -	ret = btrfs_clone_files(file, src_file.file, off, olen, destoff);
> -
> -out_fput:
> -	fdput(src_file);
> -out_drop_write:
> -	mnt_drop_write_file(file);
> -	return ret;
> -}
> -
> -static long btrfs_ioctl_clone_range(struct file *file, void __user *argp)
> -{
> -	struct btrfs_ioctl_clone_range_args args;
> -
> -	if (copy_from_user(&args, argp, sizeof(args)))
> -		return -EFAULT;
> -	return btrfs_ioctl_clone(file, args.src_fd, args.src_offset,
> -				 args.src_length, args.dest_offset);
> +	return btrfs_clone_files(dst_file, src_file, off, len, destoff);
>  }
>  
>  /*
> @@ -5498,10 +5459,6 @@ long btrfs_ioctl(struct file *file, unsigned int
>  		return btrfs_ioctl_dev_info(root, argp);
>  	case BTRFS_IOC_BALANCE:
>  		return btrfs_ioctl_balance(file, NULL);
> -	case BTRFS_IOC_CLONE:
> -		return btrfs_ioctl_clone(file, arg, 0, 0, 0);
> -	case BTRFS_IOC_CLONE_RANGE:
> -		return btrfs_ioctl_clone_range(file, argp);
>  	case BTRFS_IOC_TRANS_START:
>  		return btrfs_ioctl_trans_start(file);
>  	case BTRFS_IOC_TRANS_END:
> diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
> index cbc0f4b..e9b978f 100644
> --- a/fs/cifs/cifsfs.c
> +++ b/fs/cifs/cifsfs.c
> @@ -914,6 +914,61 @@ const struct inode_operations cifs_symlink_inode_ops = {
>  #endif
>  };
>  
> +static int cifs_clone_file_range(struct file *src_file, loff_t off,
> +		struct file *dst_file, loff_t destoff, u64 len)
> +{
> +	struct inode *src_inode = file_inode(src_file);
> +	struct inode *target_inode = file_inode(dst_file);
> +	struct cifsFileInfo *smb_file_src = src_file->private_data;
> +	struct cifsFileInfo *smb_file_target = dst_file->private_data;
> +	struct cifs_tcon *src_tcon = tlink_tcon(smb_file_src->tlink);
> +	struct cifs_tcon *target_tcon = tlink_tcon(smb_file_target->tlink);
> +	unsigned int xid;
> +	int rc;
> +
> +	cifs_dbg(FYI, "clone range\n");
> +
> +	xid = get_xid();
> +
> +	if (!src_file->private_data || !dst_file->private_data) {
> +		rc = -EBADF;
> +		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
> +		goto out;
> +	}
> +
> +	/*
> +	 * Note: cifs case is easier than btrfs since server responsible for
> +	 * checks for proper open modes and file type and if it wants
> +	 * server could even support copy of range where source = target
> +	 */
> +	lock_two_nondirectories(target_inode, src_inode);
> +
> +	if (len == 0)
> +		len = src_inode->i_size - off;
> +
> +	cifs_dbg(FYI, "about to flush pages\n");
> +	/* should we flush first and last page first */
> +	truncate_inode_pages_range(&target_inode->i_data, destoff,
> +				   PAGE_CACHE_ALIGN(destoff + len)-1);
> +
> +	if (target_tcon->ses->server->ops->duplicate_extents)
> +		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
> +			smb_file_src, smb_file_target, off, len, destoff);
> +	else
> +		rc = -EOPNOTSUPP;
> +
> +	/* force revalidate of size and timestamps of target file now
> +	   that target is updated on the server */
> +	CIFS_I(target_inode)->time = 0;
> +out_unlock:
> +	/* although unlocking in the reverse order from locking is not
> +	   strictly necessary here it is a little cleaner to be consistent */
> +	unlock_two_nondirectories(src_inode, target_inode);
> +out:
> +	free_xid(xid);
> +	return rc;
> +}
> +
>  const struct file_operations cifs_file_ops = {
>  	.read_iter = cifs_loose_read_iter,
>  	.write_iter = cifs_file_write_iter,
> @@ -926,6 +981,7 @@ const struct file_operations cifs_file_ops = {
>  	.splice_read = generic_file_splice_read,
>  	.llseek = cifs_llseek,
>  	.unlocked_ioctl	= cifs_ioctl,
> +	.clone_file_range = cifs_clone_file_range,
>  	.setlease = cifs_setlease,
>  	.fallocate = cifs_fallocate,
>  };
> @@ -942,6 +998,8 @@ const struct file_operations cifs_file_strict_ops = {
>  	.splice_read = generic_file_splice_read,
>  	.llseek = cifs_llseek,
>  	.unlocked_ioctl	= cifs_ioctl,
> +	.clone_file_range = cifs_clone_file_range,
> +	.clone_file_range = cifs_clone_file_range,
>  	.setlease = cifs_setlease,
>  	.fallocate = cifs_fallocate,
>  };
> @@ -958,6 +1016,7 @@ const struct file_operations cifs_file_direct_ops = {
>  	.mmap = cifs_file_mmap,
>  	.splice_read = generic_file_splice_read,
>  	.unlocked_ioctl  = cifs_ioctl,
> +	.clone_file_range = cifs_clone_file_range,
>  	.llseek = cifs_llseek,
>  	.setlease = cifs_setlease,
>  	.fallocate = cifs_fallocate,
> @@ -974,6 +1033,7 @@ const struct file_operations cifs_file_nobrl_ops = {
>  	.splice_read = generic_file_splice_read,
>  	.llseek = cifs_llseek,
>  	.unlocked_ioctl	= cifs_ioctl,
> +	.clone_file_range = cifs_clone_file_range,
>  	.setlease = cifs_setlease,
>  	.fallocate = cifs_fallocate,
>  };
> @@ -989,6 +1049,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
>  	.splice_read = generic_file_splice_read,
>  	.llseek = cifs_llseek,
>  	.unlocked_ioctl	= cifs_ioctl,
> +	.clone_file_range = cifs_clone_file_range,
>  	.setlease = cifs_setlease,
>  	.fallocate = cifs_fallocate,
>  };
> @@ -1004,6 +1065,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
>  	.mmap = cifs_file_mmap,
>  	.splice_read = generic_file_splice_read,
>  	.unlocked_ioctl  = cifs_ioctl,
> +	.clone_file_range = cifs_clone_file_range,
>  	.llseek = cifs_llseek,
>  	.setlease = cifs_setlease,
>  	.fallocate = cifs_fallocate,
> @@ -1014,6 +1076,7 @@ const struct file_operations cifs_dir_ops = {
>  	.release = cifs_closedir,
>  	.read    = generic_read_dir,
>  	.unlocked_ioctl  = cifs_ioctl,
> +	.clone_file_range = cifs_clone_file_range,
>  	.llseek = generic_file_llseek,
>  };
>  
> diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
> index c3cc160..c399513 100644
> --- a/fs/cifs/cifsfs.h
> +++ b/fs/cifs/cifsfs.h
> @@ -131,7 +131,6 @@ extern int	cifs_setxattr(struct dentry *, const char *, const void *,
>  extern ssize_t	cifs_getxattr(struct dentry *, const char *, void *, size_t);
>  extern ssize_t	cifs_listxattr(struct dentry *, char *, size_t);
>  extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
> -
>  #ifdef CONFIG_CIFS_NFSD_EXPORT
>  extern const struct export_operations cifs_export_ops;
>  #endif /* CONFIG_CIFS_NFSD_EXPORT */
> diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
> index 35cf990..7a3b84e 100644
> --- a/fs/cifs/ioctl.c
> +++ b/fs/cifs/ioctl.c
> @@ -34,73 +34,36 @@
>  #include "cifs_ioctl.h"
>  #include <linux/btrfs.h>
>  
> -static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
> -			unsigned long srcfd, u64 off, u64 len, u64 destoff,
> -			bool dup_extents)
> +static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
> +			  struct file *dst_file)
>  {
> -	int rc;
> -	struct cifsFileInfo *smb_file_target = dst_file->private_data;
> +	struct inode *src_inode = file_inode(src_file);
>  	struct inode *target_inode = file_inode(dst_file);
> -	struct cifs_tcon *target_tcon;
> -	struct fd src_file;
>  	struct cifsFileInfo *smb_file_src;
> -	struct inode *src_inode;
> +	struct cifsFileInfo *smb_file_target;
>  	struct cifs_tcon *src_tcon;
> +	struct cifs_tcon *target_tcon;
> +	int rc;
>  
>  	cifs_dbg(FYI, "ioctl clone range\n");
> -	/* the destination must be opened for writing */
> -	if (!(dst_file->f_mode & FMODE_WRITE)) {
> -		cifs_dbg(FYI, "file target not open for write\n");
> -		return -EINVAL;
> -	}
>  
> -	/* check if target volume is readonly and take reference */
> -	rc = mnt_want_write_file(dst_file);
> -	if (rc) {
> -		cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc);
> -		return rc;
> -	}
> -
> -	src_file = fdget(srcfd);
> -	if (!src_file.file) {
> -		rc = -EBADF;
> -		goto out_drop_write;
> -	}
> -
> -	if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) {
> -		rc = -EBADF;
> -		cifs_dbg(VFS, "src file seems to be from a different filesystem type\n");
> -		goto out_fput;
> -	}
> -
> -	if ((!src_file.file->private_data) || (!dst_file->private_data)) {
> +	if (!src_file->private_data || !dst_file->private_data) {
>  		rc = -EBADF;
>  		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
> -		goto out_fput;
> +		goto out;
>  	}
>  
>  	rc = -EXDEV;
>  	smb_file_target = dst_file->private_data;
> -	smb_file_src = src_file.file->private_data;
> +	smb_file_src = src_file->private_data;
>  	src_tcon = tlink_tcon(smb_file_src->tlink);
>  	target_tcon = tlink_tcon(smb_file_target->tlink);
>  
> -	/* check source and target on same server (or volume if dup_extents) */
> -	if (dup_extents && (src_tcon != target_tcon)) {
> -		cifs_dbg(VFS, "source and target of copy not on same share\n");
> -		goto out_fput;
> -	}
> -
> -	if (!dup_extents && (src_tcon->ses != target_tcon->ses)) {
> +	if (src_tcon->ses != target_tcon->ses) {
>  		cifs_dbg(VFS, "source and target of copy not on same server\n");
> -		goto out_fput;
> +		goto out;
>  	}
>  
> -	src_inode = file_inode(src_file.file);
> -	rc = -EINVAL;
> -	if (S_ISDIR(src_inode->i_mode))
> -		goto out_fput;
> -
>  	/*
>  	 * Note: cifs case is easier than btrfs since server responsible for
>  	 * checks for proper open modes and file type and if it wants
> @@ -108,34 +71,66 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
>  	 */
>  	lock_two_nondirectories(target_inode, src_inode);
>  
> -	/* determine range to clone */
> -	rc = -EINVAL;
> -	if (off + len > src_inode->i_size || off + len < off)
> -		goto out_unlock;
> -	if (len == 0)
> -		len = src_inode->i_size - off;
> -
>  	cifs_dbg(FYI, "about to flush pages\n");
>  	/* should we flush first and last page first */
> -	truncate_inode_pages_range(&target_inode->i_data, destoff,
> -				   PAGE_CACHE_ALIGN(destoff + len)-1);
> +	truncate_inode_pages(&target_inode->i_data, 0);
>  
> -	if (dup_extents && target_tcon->ses->server->ops->duplicate_extents)
> -		rc = target_tcon->ses->server->ops->duplicate_extents(xid,
> -			smb_file_src, smb_file_target, off, len, destoff);
> -	else if (!dup_extents && target_tcon->ses->server->ops->clone_range)
> +	if (target_tcon->ses->server->ops->clone_range)
>  		rc = target_tcon->ses->server->ops->clone_range(xid,
> -			smb_file_src, smb_file_target, off, len, destoff);
> +			smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
>  	else
>  		rc = -EOPNOTSUPP;
>  
>  	/* force revalidate of size and timestamps of target file now
>  	   that target is updated on the server */
>  	CIFS_I(target_inode)->time = 0;
> -out_unlock:
>  	/* although unlocking in the reverse order from locking is not
>  	   strictly necessary here it is a little cleaner to be consistent */
>  	unlock_two_nondirectories(src_inode, target_inode);
> +out:
> +	return rc;
> +}
> +
> +static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
> +			unsigned long srcfd)
> +{
> +	int rc;
> +	struct fd src_file;
> +	struct inode *src_inode;
> +
> +	cifs_dbg(FYI, "ioctl clone range\n");
> +	/* the destination must be opened for writing */
> +	if (!(dst_file->f_mode & FMODE_WRITE)) {
> +		cifs_dbg(FYI, "file target not open for write\n");
> +		return -EINVAL;
> +	}
> +
> +	/* check if target volume is readonly and take reference */
> +	rc = mnt_want_write_file(dst_file);
> +	if (rc) {
> +		cifs_dbg(FYI, "mnt_want_write failed with rc %d\n", rc);
> +		return rc;
> +	}
> +
> +	src_file = fdget(srcfd);
> +	if (!src_file.file) {
> +		rc = -EBADF;
> +		goto out_drop_write;
> +	}
> +
> +	if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) {
> +		rc = -EBADF;
> +		cifs_dbg(VFS, "src file seems to be from a different filesystem type\n");
> +		goto out_fput;
> +	}
> +
> +	src_inode = file_inode(src_file.file);
> +	rc = -EINVAL;
> +	if (S_ISDIR(src_inode->i_mode))
> +		goto out_fput;
> +
> +	rc = cifs_file_clone_range(xid, src_file.file, dst_file);
> +
>  out_fput:
>  	fdput(src_file);
>  out_drop_write:
> @@ -256,10 +251,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
>  			}
>  			break;
>  		case CIFS_IOC_COPYCHUNK_FILE:
> -			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, false);
> -			break;
> -		case BTRFS_IOC_CLONE:
> -			rc = cifs_ioctl_clone(xid, filep, arg, 0, 0, 0, true);
> +			rc = cifs_ioctl_clone(xid, filep, arg);
>  			break;
>  		case CIFS_IOC_SET_INTEGRITY:
>  			if (pSMBFile == NULL)
> diff --git a/fs/ioctl.c b/fs/ioctl.c
> index 5d01d26..84c6e79 100644
> --- a/fs/ioctl.c
> +++ b/fs/ioctl.c
> @@ -215,6 +215,29 @@ static int ioctl_fiemap(struct file *filp, unsigned long arg)
>  	return error;
>  }
>  
> +static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd,
> +			     u64 off, u64 olen, u64 destoff)
> +{
> +	struct fd src_file = fdget(srcfd);
> +	int ret;
> +
> +	if (!src_file.file)
> +		return -EBADF;
> +	ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen);
> +	fdput(src_file);
> +	return ret;
> +}
> +
> +static long ioctl_file_clone_range(struct file *file, void __user *argp)
> +{
> +	struct file_clone_range args;
> +
> +	if (copy_from_user(&args, argp, sizeof(args)))
> +		return -EFAULT;
> +	return ioctl_file_clone(file, args.src_fd, args.src_offset,
> +				args.src_length, args.dest_offset);
> +}
> +
>  #ifdef CONFIG_BLOCK
>  
>  static inline sector_t logical_to_blk(struct inode *inode, loff_t offset)
> @@ -600,6 +623,12 @@ int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd,
>  	case FIGETBSZ:
>  		return put_user(inode->i_sb->s_blocksize, argp);
>  
> +	case FICLONE:
> +		return ioctl_file_clone(filp, arg, 0, 0, 0);
> +
> +	case FICLONERANGE:
> +		return ioctl_file_clone_range(filp, argp);
> +
>  	default:
>  		if (S_ISREG(inode->i_mode))
>  			error = file_ioctl(filp, cmd, arg);
> diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
> index db9b5fe..26f9a23 100644
> --- a/fs/nfs/nfs4file.c
> +++ b/fs/nfs/nfs4file.c
> @@ -195,65 +195,27 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t
>  	return nfs42_proc_allocate(filep, offset, len);
>  }
>  
> -static noinline long
> -nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
> -		  u64 src_off, u64 dst_off, u64 count)
> +static int nfs42_clone_file_range(struct file *src_file, loff_t src_off,
> +		struct file *dst_file, loff_t dst_off, u64 count)
>  {
>  	struct inode *dst_inode = file_inode(dst_file);
>  	struct nfs_server *server = NFS_SERVER(dst_inode);
> -	struct fd src_file;
> -	struct inode *src_inode;
> +	struct inode *src_inode = file_inode(src_file);
>  	unsigned int bs = server->clone_blksize;
>  	bool same_inode = false;
>  	int ret;
>  
> -	/* dst file must be opened for writing */
> -	if (!(dst_file->f_mode & FMODE_WRITE))
> -		return -EINVAL;
> -
> -	ret = mnt_want_write_file(dst_file);
> -	if (ret)
> -		return ret;
> -
> -	src_file = fdget(srcfd);
> -	if (!src_file.file) {
> -		ret = -EBADF;
> -		goto out_drop_write;
> -	}
> -
> -	src_inode = file_inode(src_file.file);
> -
> -	if (src_inode == dst_inode)
> -		same_inode = true;
> -
> -	/* src file must be opened for reading */
> -	if (!(src_file.file->f_mode & FMODE_READ))
> -		goto out_fput;
> -
> -	/* src and dst must be regular files */
> -	ret = -EISDIR;
> -	if (!S_ISREG(src_inode->i_mode) || !S_ISREG(dst_inode->i_mode))
> -		goto out_fput;
> -
> -	ret = -EXDEV;
> -	if (src_file.file->f_path.mnt != dst_file->f_path.mnt ||
> -	    src_inode->i_sb != dst_inode->i_sb)
> -		goto out_fput;
> -
>  	/* check alignment w.r.t. clone_blksize */
>  	ret = -EINVAL;
>  	if (bs) {
>  		if (!IS_ALIGNED(src_off, bs) || !IS_ALIGNED(dst_off, bs))
> -			goto out_fput;
> +			goto out;
>  		if (!IS_ALIGNED(count, bs) && i_size_read(src_inode) != (src_off + count))
> -			goto out_fput;
> +			goto out;
>  	}
>  
> -	/* verify if ranges are overlapped within the same file */
> -	if (same_inode) {
> -		if (dst_off + count > src_off && dst_off < src_off + count)
> -			goto out_fput;
> -	}
> +	if (src_inode == dst_inode)
> +		same_inode = true;
>  
>  	/* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */
>  	if (same_inode) {
> @@ -275,7 +237,7 @@ nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd,
>  	if (ret)
>  		goto out_unlock;
>  
> -	ret = nfs42_proc_clone(src_file.file, dst_file, src_off, dst_off, count);
> +	ret = nfs42_proc_clone(src_file, dst_file, src_off, dst_off, count);
>  
>  	/* truncate inode page cache of the dst range so that future reads can fetch
>  	 * new data from server */
> @@ -292,37 +254,9 @@ out_unlock:
>  		mutex_unlock(&dst_inode->i_mutex);
>  		mutex_unlock(&src_inode->i_mutex);
>  	}
> -out_fput:
> -	fdput(src_file);
> -out_drop_write:
> -	mnt_drop_write_file(dst_file);
> +out:
>  	return ret;
>  }
> -
> -static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp)
> -{
> -	struct btrfs_ioctl_clone_range_args args;
> -
> -	if (copy_from_user(&args, argp, sizeof(args)))
> -		return -EFAULT;
> -
> -	return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_offset,
> -				 args.dest_offset, args.src_length);
> -}
> -
> -long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
> -{
> -	void __user *argp = (void __user *)arg;
> -
> -	switch (cmd) {
> -	case BTRFS_IOC_CLONE:
> -		return nfs42_ioctl_clone(file, arg, 0, 0, 0);
> -	case BTRFS_IOC_CLONE_RANGE:
> -		return nfs42_ioctl_clone_range(file, argp);
> -	}
> -
> -	return -ENOTTY;
> -}
>  #endif /* CONFIG_NFS_V4_2 */
>  
>  const struct file_operations nfs4_file_operations = {
> @@ -342,8 +276,7 @@ const struct file_operations nfs4_file_operations = {
>  #ifdef CONFIG_NFS_V4_2
>  	.llseek		= nfs4_file_llseek,
>  	.fallocate	= nfs42_fallocate,
> -	.unlocked_ioctl = nfs4_ioctl,
> -	.compat_ioctl	= nfs4_ioctl,
> +	.clone_file_range = nfs42_clone_file_range,
>  #else
>  	.llseek		= nfs_file_llseek,
>  #endif
> diff --git a/fs/read_write.c b/fs/read_write.c
> index 6c1aa73..9e3dd8f 100644
> --- a/fs/read_write.c
> +++ b/fs/read_write.c
> @@ -1451,3 +1451,75 @@ out1:
>  out2:
>  	return ret;
>  }
> +
> +static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write)
> +{
> +	struct inode *inode = file_inode(file);
> +
> +	if (unlikely(pos < 0))
> +		return -EINVAL;
> +
> +	 if (unlikely((loff_t) (pos + len) < 0))
> +		return -EINVAL;
> +
> +	if (unlikely(inode->i_flctx && mandatory_lock(inode))) {
> +		loff_t end = len ? pos + len - 1 : OFFSET_MAX;
> +		int retval;
> +
> +		retval = locks_mandatory_area(file, pos, end,
> +				write ? F_WRLCK : F_RDLCK);
> +		if (retval < 0)
> +			return retval;
> +	}
> +
> +	return security_file_permission(file, write ? MAY_WRITE : MAY_READ);
> +}
> +
> +int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
> +		struct file *file_out, loff_t pos_out, u64 len)
> +{
> +	struct inode *inode_in = file_inode(file_in);
> +	struct inode *inode_out = file_inode(file_out);
> +	int ret;
> +
> +	if (inode_in->i_sb != inode_out->i_sb ||
> +	    file_in->f_path.mnt != file_out->f_path.mnt)
> +		return -EXDEV;
> +
> +	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
> +		return -EISDIR;
> +	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
> +		return -EOPNOTSUPP;
> +
> +	if (!(file_in->f_mode & FMODE_READ) ||
> +	    !(file_out->f_mode & FMODE_WRITE) ||
> +	    (file_out->f_flags & O_APPEND) ||
> +	    !file_in->f_op->clone_file_range)
> +		return -EBADF;
> +
> +	ret = clone_verify_area(file_in, pos_in, len, false);
> +	if (ret)
> +		return ret;
> +
> +	ret = clone_verify_area(file_out, pos_out, len, true);
> +	if (ret)
> +		return ret;
> +
> +	if (pos_in + len > i_size_read(inode_in))
> +		return -EINVAL;
> +
> +	ret = mnt_want_write_file(file_out);
> +	if (ret)
> +		return ret;
> +
> +	ret = file_in->f_op->clone_file_range(file_in, pos_in,
> +			file_out, pos_out, len);
> +	if (!ret) {
> +		fsnotify_access(file_in);
> +		fsnotify_modify(file_out);
> +	}
> +
> +	mnt_drop_write_file(file_out);
> +	return ret;
> +}
> +EXPORT_SYMBOL(vfs_clone_file_range);
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index af559ac..59bf96d 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1629,7 +1629,10 @@ struct file_operations {
>  #ifndef CONFIG_MMU
>  	unsigned (*mmap_capabilities)(struct file *);
>  #endif
> -	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int);
> +	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
> +			loff_t, size_t, unsigned int);
> +	int (*clone_file_range)(struct file *, loff_t, struct file *, loff_t,
> +			u64);
>  };
>  
>  struct inode_operations {
> @@ -1683,6 +1686,8 @@ extern ssize_t vfs_writev(struct file *, const struct iovec __user *,
>  		unsigned long, loff_t *);
>  extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
>  				   loff_t, size_t, unsigned int);
> +extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
> +		struct file *file_out, loff_t pos_out, u64 len);
>  
>  struct super_operations {
>     	struct inode *(*alloc_inode)(struct super_block *sb);
> diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
> index f15d980..cd5db7f 100644
> --- a/include/uapi/linux/fs.h
> +++ b/include/uapi/linux/fs.h
> @@ -39,6 +39,13 @@
>  #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
>  #define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
>  
> +struct file_clone_range {
> +	__s64 src_fd;
> +	__u64 src_offset;
> +	__u64 src_length;
> +	__u64 dest_offset;
> +};
> +
>  struct fstrim_range {
>  	__u64 start;
>  	__u64 len;
> @@ -159,6 +166,8 @@ struct inodes_stat_t {
>  #define FIFREEZE	_IOWR('X', 119, int)	/* Freeze */
>  #define FITHAW		_IOWR('X', 120, int)	/* Thaw */
>  #define FITRIM		_IOWR('X', 121, struct fstrim_range)	/* Trim */
> +#define FICLONE		_IOW(0x94, 9, int)
> +#define FICLONERANGE	_IOW(0x94, 13, struct file_clone_range)
>  
>  #define	FS_IOC_GETFLAGS			_IOR('f', 1, long)
>  #define	FS_IOC_SETFLAGS			_IOW('f', 2, long)
> -- 
> 1.9.1
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html