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()

1 files changed, 89 insertions, 21 deletions

diff --git a/mm/filemap.c b/mm/filemap.c
index 6dd9a2274c80..01e7e0869bba 100644
--- a/mm/filemap.c
+++ b/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,
-				       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)
 {
+	struct inode *inode = file->f_mapping->host;
+	loff_t max_size = inode->i_sb->s_maxbytes;
 	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)