Merge tag 'copy-file-range-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull copy_file_range updates from Darrick Wong:
 "This fixes numerous parameter checking problems and inconsistent
  behaviors in the new(ish) copy_file_range system call.

  Now the system call will actually check its range parameters
  correctly; refuse to copy into files for which the caller does not
  have sufficient privileges; update mtime and strip setuid like file
  writes are supposed to do; and allows copying up to the EOF of the
  source file instead of failing the call like we used to.

  Summary:

   - Create a generic copy_file_range handler and make individual
     filesystems responsible for calling it (i.e. no more assuming that
     do_splice_direct will work or is appropriate)

   - Refactor copy_file_range and remap_range parameter checking where
     they are the same

   - Install missing copy_file_range parameter checking(!)

   - Remove suid/sgid and update mtime like any other file write

   - Change the behavior so that a copy range crossing the source file's
     eof will result in a short copy to the source file's eof instead of
     EINVAL

   - Permit filesystems to decide if they want to handle
     cross-superblock copy_file_range in their local handlers"

* tag 'copy-file-range-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  fuse: copy_file_range needs to strip setuid bits and update timestamps
  vfs: allow copy_file_range to copy across devices
  xfs: use file_modified() helper
  vfs: introduce file_modified() helper
  vfs: add missing checks to copy_file_range
  vfs: remove redundant checks from generic_remap_checks()
  vfs: introduce generic_file_rw_checks()
  vfs: no fallback for ->copy_file_range
  vfs: introduce generic_copy_file_range()

fs/ceph/file.c

@@ -1889,7 +1889,7 @@ static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode,
 	return 0;
 }
 
-static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
+static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
 				      struct file *dst_file, loff_t dst_off,
 				      size_t len, unsigned int flags)
 {
@@ -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;
 
@@ -2100,6 +2102,21 @@ static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
 	return ret;
 }
 
+static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
+				    struct file *dst_file, loff_t dst_off,
+				    size_t len, unsigned int flags)
+{
+	ssize_t ret;
+
+	ret = __ceph_copy_file_range(src_file, src_off, dst_file, dst_off,
+				     len, flags);
+
+	if (ret == -EOPNOTSUPP || ret == -EXDEV)
+		ret = generic_copy_file_range(src_file, src_off, dst_file,
+					      dst_off, len, flags);
+	return ret;
+}
+
 const struct file_operations ceph_file_fops = {
 	.open = ceph_open,
 	.release = ceph_release,

fs/cifs/cifsfs.c

@@ -1149,6 +1149,10 @@ static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
 	rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff,
 					len, flags);
 	free_xid(xid);
+
+	if (rc == -EOPNOTSUPP || rc == -EXDEV)
+		rc = generic_copy_file_range(src_file, off, dst_file,
+					     destoff, len, flags);
 	return rc;
 }
 

fs/fuse/file.c

@@ -3112,7 +3112,7 @@ static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
 	return err;
 }
 
-static ssize_t fuse_copy_file_range(struct file *file_in, loff_t pos_in,
+static ssize_t __fuse_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)
 {
@@ -3142,6 +3142,9 @@ 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;
+
 	if (fc->writeback_cache) {
 		inode_lock(inode_in);
 		err = fuse_writeback_range(inode_in, pos_in, pos_in + len);
@@ -3152,6 +3155,10 @@ static ssize_t fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 
 	inode_lock(inode_out);
 
+	err = file_modified(file_out);
+	if (err)
+		goto out;
+
 	if (fc->writeback_cache) {
 		err = fuse_writeback_range(inode_out, pos_out, pos_out + len);
 		if (err)
@@ -3190,10 +3197,26 @@ static ssize_t fuse_copy_file_range(struct file *file_in, loff_t pos_in,
 		clear_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state);
 
 	inode_unlock(inode_out);
+	file_accessed(file_in);
 
 	return err;
 }
 
+static ssize_t fuse_copy_file_range(struct file *src_file, loff_t src_off,
+				    struct file *dst_file, loff_t dst_off,
+				    size_t len, unsigned int flags)
+{
+	ssize_t ret;
+
+	ret = __fuse_copy_file_range(src_file, src_off, dst_file, dst_off,
+				     len, flags);
+
+	if (ret == -EOPNOTSUPP || ret == -EXDEV)
+		ret = generic_copy_file_range(src_file, src_off, dst_file,
+					      dst_off, len, flags);
+	return ret;
+}
+
 static const struct file_operations fuse_file_operations = {
 	.llseek		= fuse_file_llseek,
 	.read_iter	= fuse_file_read_iter,

fs/inode.c

@@ -1899,6 +1899,26 @@ int file_update_time(struct file *file)
 }
 EXPORT_SYMBOL(file_update_time);
 
+/* Caller must hold the file's inode lock */
+int file_modified(struct file *file)
+{
+	int err;
+
+	/*
+	 * Clear the security bits if the process is not being run by root.
+	 * This keeps people from modifying setuid and setgid binaries.
+	 */
+	err = file_remove_privs(file);
+	if (err)
+		return err;
+
+	if (unlikely(file->f_mode & FMODE_NOCMTIME))
+		return 0;
+
+	return file_update_time(file);
+}
+EXPORT_SYMBOL(file_modified);
+
 int inode_needs_sync(struct inode *inode)
 {
 	if (IS_SYNC(inode))

fs/nfs/nfs4file.c

@@ -129,10 +129,13 @@ nfs4_file_flush(struct file *file, fl_owner_t id)
 }
 
 #ifdef CONFIG_NFS_V4_2
-static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
+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))
@@ -140,6 +143,20 @@ static ssize_t nfs4_copy_file_range(struct file *file_in, loff_t pos_in,
 	return nfs42_proc_copy(file_in, pos_in, file_out, pos_out, count);
 }
 
+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;
+
+	ret = __nfs4_copy_file_range(file_in, pos_in, file_out, pos_out, count,
+				     flags);
+	if (ret == -EOPNOTSUPP || ret == -EXDEV)
+		ret = generic_copy_file_range(file_in, pos_in, file_out,
+					      pos_out, count, flags);
+	return ret;
+}
+
 static loff_t nfs4_file_llseek(struct file *filep, loff_t offset, int whence)
 {
 	loff_t ret;

fs/read_write.c

@@ -1565,6 +1565,58 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
 }
 #endif
 
+/**
+ * generic_copy_file_range - copy data between two files
+ * @file_in:	file structure to read from
+ * @pos_in:	file offset to read from
+ * @file_out:	file structure to write data to
+ * @pos_out:	file offset to write data to
+ * @len:	amount of data to copy
+ * @flags:	copy flags
+ *
+ * This is a generic filesystem helper to copy data from one file to another.
+ * It has no constraints on the source or destination file owners - the files
+ * can belong to different superblocks and different filesystem types. Short
+ * copies are allowed.
+ *
+ * This should be called from the @file_out filesystem, as per the
+ * ->copy_file_range() method.
+ *
+ * Returns the number of bytes copied or a negative error indicating the
+ * failure.
+ */
+
+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)
+{
+	return do_splice_direct(file_in, &pos_in, file_out, &pos_out,
+				len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
+}
+EXPORT_SYMBOL(generic_copy_file_range);
+
+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)
+{
+	/*
+	 * Although we now allow filesystems to handle cross sb copy, passing
+	 * a file of the wrong filesystem type to filesystem driver can result
+	 * in an attempt to dereference the wrong type of ->private_data, so
+	 * avoid doing that until we really have a good reason.  NFS defines
+	 * several different file_system_type structures, but they all end up
+	 * using the same ->copy_file_range() function pointer.
+	 */
+	if (file_out->f_op->copy_file_range &&
+	    file_out->f_op->copy_file_range == file_in->f_op->copy_file_range)
+		return file_out->f_op->copy_file_range(file_in, pos_in,
+						       file_out, pos_out,
+						       len, flags);
+
+	return generic_copy_file_range(file_in, pos_in, file_out, pos_out, len,
+				       flags);
+}
+
 /*
  * copy_file_range() differs from regular file read and write in that it
  * specifically allows return partial success.  When it does so is up to
@@ -1574,17 +1626,15 @@ 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;
 
-	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 -EINVAL;
+	ret = generic_copy_file_checks(file_in, pos_in, file_out, pos_out, &len,
+				       flags);
+	if (unlikely(ret))
+		return ret;
 
 	ret = rw_verify_area(READ, file_in, &pos_in, len);
 	if (unlikely(ret))
@@ -1594,15 +1644,6 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (unlikely(ret))
 		return ret;
 
-	if (!(file_in->f_mode & FMODE_READ) ||
-	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND))
-		return -EBADF;
-
-	/* this could be relaxed once a method supports cross-fs copies */
-	if (inode_in->i_sb != inode_out->i_sb)
-		return -EXDEV;
-
 	if (len == 0)
 		return 0;
 
@@ -1612,7 +1653,8 @@ 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) {
 		loff_t cloned;
 
 		cloned = file_in->f_op->remap_file_range(file_in, pos_in,
@@ -1625,16 +1667,9 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 		}
 	}
 
-	if (file_out->f_op->copy_file_range) {
-		ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
-						      pos_out, len, flags);
-		if (ret != -EOPNOTSUPP)
-			goto done;
-	}
-
-	ret = do_splice_direct(file_in, &pos_in, file_out, &pos_out,
-			len > MAX_RW_COUNT ? MAX_RW_COUNT : len, 0);
-
+	ret = do_copy_file_range(file_in, pos_in, file_out, pos_out, len,
+				flags);
+	WARN_ON_ONCE(ret == -EOPNOTSUPP);
 done:
 	if (ret > 0) {
 		fsnotify_access(file_in);
@@ -1951,25 +1986,10 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 		return ret;
 
 	/* If can't alter the file contents, we're done. */
-	if (!(remap_flags & REMAP_FILE_DEDUP)) {
-		/* Update the timestamps, since we can alter file contents. */
-		if (!(file_out->f_mode & FMODE_NOCMTIME)) {
-			ret = file_update_time(file_out);
-			if (ret)
-				return ret;
-		}
+	if (!(remap_flags & REMAP_FILE_DEDUP))
+		ret = file_modified(file_out);
 
-		/*
-		 * Clear the security bits if the process is not being run by
-		 * root.  This keeps people from modifying setuid and setgid
-		 * binaries.
-		 */
-		ret = file_remove_privs(file_out);
-		if (ret)
 	return ret;
-	}
-
-	return 0;
 }
 EXPORT_SYMBOL(generic_remap_file_range_prep);
 
@@ -1977,29 +1997,21 @@ loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
 			   struct file *file_out, loff_t pos_out,
 			   loff_t len, unsigned int remap_flags)
 {
-	struct inode *inode_in = file_inode(file_in);
-	struct inode *inode_out = file_inode(file_out);
 	loff_t ret;
 
 	WARN_ON_ONCE(remap_flags & REMAP_FILE_DEDUP);
 
-	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 -EINVAL;
-
 	/*
 	 * FICLONE/FICLONERANGE ioctls enforce that src and dest files are on
 	 * the same mount. Practically, they only need to be on the same file
 	 * system.
 	 */
-	if (inode_in->i_sb != inode_out->i_sb)
+	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
 		return -EXDEV;
 
-	if (!(file_in->f_mode & FMODE_READ) ||
-	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND))
-		return -EBADF;
+	ret = generic_file_rw_checks(file_in, file_out);
+	if (ret < 0)
+		return ret;
 
 	if (!file_in->f_op->remap_file_range)
 		return -EOPNOTSUPP;

fs/xfs/xfs_file.c

@@ -367,20 +367,7 @@ xfs_file_aio_write_checks(
 	 * lock above.  Eventually we should look into a way to avoid
 	 * the pointless lock roundtrip.
 	 */
-	if (likely(!(file->f_mode & FMODE_NOCMTIME))) {
-		error = file_update_time(file);
-		if (error)
-			return error;
-	}
-
-	/*
-	 * If we're writing the file then make sure to clear the setuid and
-	 * setgid bits if the process is not being run by root.  This keeps
-	 * people from modifying setuid and setgid binaries.
-	 */
-	if (!IS_NOSEC(inode))
-		return file_remove_privs(file);
-	return 0;
+	return file_modified(file);
 }
 
 static int

include/linux/fs.h

@@ -1889,6 +1889,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *,
 		unsigned long, loff_t *, rwf_t);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
+extern 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);
 extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 					 struct file *file_out, loff_t pos_out,
 					 loff_t *count,
@@ -2174,6 +2177,8 @@ static inline void file_accessed(struct file *file)
 		touch_atime(&file->f_path);
 }
 
+extern int file_modified(struct file *file);
+
 int sync_inode(struct inode *inode, struct writeback_control *wbc);
 int sync_inode_metadata(struct inode *inode, int wait);
 
@@ -3047,6 +3052,10 @@ extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 extern int generic_remap_checks(struct file *file_in, loff_t pos_in,
 				struct file *file_out, loff_t pos_out,
 				loff_t *count, unsigned int remap_flags);
+extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
+extern int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
+				    struct file *file_out, loff_t pos_out,
+				    size_t *count, unsigned int flags);
 extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
 extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);

mm/filemap.c

@@ -2925,24 +2925,11 @@ EXPORT_SYMBOL(read_cache_page_gfp);
  * LFS limits.  If pos is under the limit it becomes a short access.  If it
  * exceeds the limit we return -EFBIG.
  */
-static int generic_access_check_limits(struct file *file, loff_t pos,
+static int generic_write_check_limits(struct file *file, loff_t pos,
 				      loff_t *count)
 {
 	struct inode *inode = file->f_mapping->host;
 	loff_t max_size = inode->i_sb->s_maxbytes;
-
-	if (!(file->f_flags & O_LARGEFILE))
-		max_size = MAX_NON_LFS;
-
-	if (unlikely(pos >= max_size))
-		return -EFBIG;
-	*count = min(*count, max_size - pos);
-	return 0;
-}
-
-static int generic_write_check_limits(struct file *file, loff_t pos,
-				      loff_t *count)
-{
 	loff_t limit = rlimit(RLIMIT_FSIZE);
 
 	if (limit != RLIM_INFINITY) {
@@ -2953,7 +2940,15 @@ static int generic_write_check_limits(struct file *file, loff_t pos,
 		*count = min(*count, limit - pos);
 	}
 
-	return generic_access_check_limits(file, pos, count);
+	if (!(file->f_flags & O_LARGEFILE))
+		max_size = MAX_NON_LFS;
+
+	if (unlikely(pos >= max_size))
+		return -EFBIG;
+
+	*count = min(*count, max_size - pos);
+
+	return 0;
 }
 
 /*
@@ -2993,7 +2988,7 @@ EXPORT_SYMBOL(generic_write_checks);
 /*
  * Performs necessary checks before doing a clone.
  *
- * Can adjust amount of bytes to clone.
+ * Can adjust amount of bytes to clone via @req_count argument.
  * Returns appropriate error code that caller should return or
  * zero in case the clone should be allowed.
  */
@@ -3031,10 +3026,6 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 		return -EINVAL;
 	count = min(count, size_in - (uint64_t)pos_in);
 
-	ret = generic_access_check_limits(file_in, pos_in, &count);
-	if (ret)
-		return ret;
-
 	ret = generic_write_check_limits(file_out, pos_out, &count);
 	if (ret)
 		return ret;
@@ -3071,6 +3062,83 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in,
 	return 0;
 }
 
+
+/*
+ * Performs common checks before doing a file copy/clone
+ * from @file_in to @file_out.
+ */
+int generic_file_rw_checks(struct file *file_in, struct file *file_out)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+
+	/* Don't copy dirs, pipes, sockets... */
+	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 -EINVAL;
+
+	if (!(file_in->f_mode & FMODE_READ) ||
+	    !(file_out->f_mode & FMODE_WRITE) ||
+	    (file_out->f_flags & O_APPEND))
+		return -EBADF;
+
+	return 0;
+}
+
+/*
+ * Performs necessary checks before doing a file copy
+ *
+ * Can adjust amount of bytes to copy via @req_count argument.
+ * Returns appropriate error code that caller should return or
+ * zero in case the copy should be allowed.
+ */
+int generic_copy_file_checks(struct file *file_in, loff_t pos_in,
+			     struct file *file_out, loff_t pos_out,
+			     size_t *req_count, unsigned int flags)
+{
+	struct inode *inode_in = file_inode(file_in);
+	struct inode *inode_out = file_inode(file_out);
+	uint64_t count = *req_count;
+	loff_t size_in;
+	int ret;
+
+	ret = generic_file_rw_checks(file_in, file_out);
+	if (ret)
+		return ret;
+
+	/* Don't touch certain kinds of inodes */
+	if (IS_IMMUTABLE(inode_out))
+		return -EPERM;
+
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		return -ETXTBSY;
+
+	/* Ensure offsets don't wrap. */
+	if (pos_in + count < pos_in || pos_out + count < pos_out)
+		return -EOVERFLOW;
+
+	/* Shorten the copy to EOF */
+	size_in = i_size_read(inode_in);
+	if (pos_in >= size_in)
+		count = 0;
+	else
+		count = min(count, size_in - (uint64_t)pos_in);
+
+	ret = generic_write_check_limits(file_out, pos_out, &count);
+	if (ret)
+		return ret;
+
+	/* Don't allow overlapped copying within the same file. */
+	if (inode_in == inode_out &&
+	    pos_out + count > pos_in &&
+	    pos_out < pos_in + count)
+		return -EINVAL;
+
+	*req_count = count;
+	return 0;
+}
+
 int pagecache_write_begin(struct file *file, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned flags,
 				struct page **pagep, void **fsdata)