vfs: pull btrfs clone API to vfs layer

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>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 72 insertions, 0 deletions

diff --git a/fs/read_write.c b/fs/read_write.c
index 6cfad4761fd8..c75d02cb13ec 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(inode, 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);