[RFC 5/7] erofs-utils: mkfs: support two-field manifest records

[Wenyuan Xu <sereno.xu@deepseek.com>]

Accept PATH PAYLOAD records alongside complete manifest records. Import
metadata and xattrs from the backing file using local import policies,
without recursively scanning directories. Read symbolic links without
following their targets.

Preserve source hard links unless hard dereferencing is requested, and
count only entries imported into the image. Allow explicit hard links
to refer to entries imported from backing files.

Assisted-by: LLM
Signed-off-by: Wenyuan Xu <sereno.xu@deepseek.com>
---
 lib/manifest.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 86 insertions(+), 2 deletions(-)

diff --git a/lib/manifest.c b/lib/manifest.c
index bf8eb8c..244c1a0 100644
--- a/lib/manifest.c
+++ b/lib/manifest.c
@@ -175,6 +175,75 @@ enum erofs_manifest_field {
 	EROFS_MANIFEST_FIELD_COUNT,
 };
 
+static struct erofs_inode *erofs_manifest_load_local(struct erofs_importer *im,
+		struct erofs_inode *parent, char *payload)
+{
+	struct erofs_inode *inode;
+	struct stat st;
+	char *path;
+	size_t len;
+	int ret;
+
+	/* PAYLOAD */
+	if (erofs_manifest_decode(payload, false, &len) || *payload != '/')
+		return ERR_PTR(-EINVAL);
+	if (asprintf(&path, "%s%s", im->params->source, payload) < 0)
+		return ERR_PTR(-ENOMEM);
+
+	ret = lstat(path, &st) ? -errno : 0;
+	if (ret)
+		goto out_path;
+	if (!S_ISDIR(st.st_mode) && !im->params->hard_dereference) {
+		inode = erofs_iget(st.st_dev, st.st_ino);
+		if (inode) {
+			free(path);
+			if (inode->i_nlink == UINT_MAX) {
+				erofs_iput(inode);
+				return ERR_PTR(-EOVERFLOW);
+			}
+			++inode->i_nlink;
+			return inode;
+		}
+	}
+
+	inode = erofs_new_inode(im->sbi);
+	if (IS_ERR(inode)) {
+		ret = PTR_ERR(inode);
+		goto out_path;
+	}
+	ret = erofs_fill_inode(im, inode, &st, path);
+	if (ret)
+		goto out_inode;
+	inode->i_parent = parent;
+	inode->datasource = EROFS_INODE_DATA_SOURCE_LOCALPATH;
+	if (S_ISLNK(inode->i_mode)) {
+		inode->i_link = malloc(st.st_size);
+		if (!inode->i_link) {
+			ret = -ENOMEM;
+			goto out_inode;
+		}
+		if (readlink(path, inode->i_link, st.st_size) < 0) {
+			ret = -errno;
+			goto out_inode;
+		}
+	}
+
+	if (!im->params->no_xattrs) {
+		/* XATTR */
+		ret = erofs_scan_file_xattrs(inode);
+		if (ret)
+			goto out_inode;
+	}
+
+	free(path);
+	return inode;
+out_inode:
+	erofs_iput(inode);
+out_path:
+	free(path);
+	return ERR_PTR(ret);
+}
+
 static int erofs_manifest_parse_record(struct erofs_importer *im,
 				 struct erofs_inode *sentinel, char *line)
 {
@@ -183,7 +252,7 @@ static int erofs_manifest_parse_record(struct erofs_importer *im,
 	struct erofs_dentry *d;
 	char *f[EROFS_MANIFEST_FIELD_COUNT], *token, *dot;
 	char name[EROFS_NAME_LEN + 1];
-	bool hardlink, is_root;
+	bool hardlink, is_root, short_record = false;
 	u64 mode, size = 0, uid, gid, rdev = 0, sec, nsec;
 	size_t len;
 	int i, ret = -EINVAL;
@@ -196,8 +265,13 @@ static int erofs_manifest_parse_record(struct erofs_importer *im,
 		do {
 			token = strsep(&line, " ");
 		} while (token && !*token);
-		if (!token)
+		if (!token) {
+			if (i == EROFS_MANIFEST_PAYLOAD + 1) {
+				short_record = true;
+				break;
+			}
 			return -EINVAL;
+		}
 		f[i] = token;
 	}
 
@@ -212,6 +286,16 @@ static int erofs_manifest_parse_record(struct erofs_importer *im,
 		return -EEXIST;
 	is_root = parent == sentinel;
 
+	if (short_record) {
+		inode = erofs_manifest_load_local(im, parent,
+				f[EROFS_MANIFEST_PAYLOAD]);
+		if (IS_ERR(inode))
+			return PTR_ERR(inode);
+		if (is_root && !S_ISDIR(inode->i_mode))
+			goto out;
+		goto link;
+	}
+
 	/* MODE */
 	hardlink = f[EROFS_MANIFEST_MODE][0] == '@';
 	if (hardlink) {
-- 
2.43.0