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, 63 insertions, 0 deletions

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index cbc0f4bca0c0..e9b978f2e114 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,
 };