Merge branch 'vd/fsck-submodule-url-test'

Tighten URL checks fsck makes in a URL recorded for submodules.

* vd/fsck-submodule-url-test:
  submodule-config.c: strengthen URL fsck check
  t7450: test submodule urls
  test-submodule: remove command line handling for check-name
  submodule-config.h: move check_submodule_url

submodule-config.c

@@ -14,6 +14,8 @@
 #include "parse-options.h"
 #include "thread-utils.h"
 #include "tree-walk.h"
+#include "url.h"
+#include "urlmatch.h"
 
 /*
  * submodule cache lookup structure
@@ -228,6 +230,144 @@ in_component:
 	return 0;
 }
 
+static int starts_with_dot_slash(const char *const path)
+{
+	return path_match_flags(path, PATH_MATCH_STARTS_WITH_DOT_SLASH |
+				PATH_MATCH_XPLATFORM);
+}
+
+static int starts_with_dot_dot_slash(const char *const path)
+{
+	return path_match_flags(path, PATH_MATCH_STARTS_WITH_DOT_DOT_SLASH |
+				PATH_MATCH_XPLATFORM);
+}
+
+static int submodule_url_is_relative(const char *url)
+{
+	return starts_with_dot_slash(url) || starts_with_dot_dot_slash(url);
+}
+
+/*
+ * Count directory components that a relative submodule URL should chop
+ * from the remote_url it is to be resolved against.
+ *
+ * In other words, this counts "../" components at the start of a
+ * submodule URL.
+ *
+ * Returns the number of directory components to chop and writes a
+ * pointer to the next character of url after all leading "./" and
+ * "../" components to out.
+ */
+static int count_leading_dotdots(const char *url, const char **out)
+{
+	int result = 0;
+	while (1) {
+		if (starts_with_dot_dot_slash(url)) {
+			result++;
+			url += strlen("../");
+			continue;
+		}
+		if (starts_with_dot_slash(url)) {
+			url += strlen("./");
+			continue;
+		}
+		*out = url;
+		return result;
+	}
+}
+/*
+ * Check whether a transport is implemented by git-remote-curl.
+ *
+ * If it is, returns 1 and writes the URL that would be passed to
+ * git-remote-curl to the "out" parameter.
+ *
+ * Otherwise, returns 0 and leaves "out" untouched.
+ *
+ * Examples:
+ *   http::https://example.com/repo.git -> 1, https://example.com/repo.git
+ *   https://example.com/repo.git -> 1, https://example.com/repo.git
+ *   git://example.com/repo.git -> 0
+ *
+ * This is for use in checking for previously exploitable bugs that
+ * required a submodule URL to be passed to git-remote-curl.
+ */
+static int url_to_curl_url(const char *url, const char **out)
+{
+	/*
+	 * We don't need to check for case-aliases, "http.exe", and so
+	 * on because in the default configuration, is_transport_allowed
+	 * prevents URLs with those schemes from being cloned
+	 * automatically.
+	 */
+	if (skip_prefix(url, "http::", out) ||
+	    skip_prefix(url, "https::", out) ||
+	    skip_prefix(url, "ftp::", out) ||
+	    skip_prefix(url, "ftps::", out))
+		return 1;
+	if (starts_with(url, "http://") ||
+	    starts_with(url, "https://") ||
+	    starts_with(url, "ftp://") ||
+	    starts_with(url, "ftps://")) {
+		*out = url;
+		return 1;
+	}
+	return 0;
+}
+
+int check_submodule_url(const char *url)
+{
+	const char *curl_url;
+
+	if (looks_like_command_line_option(url))
+		return -1;
+
+	if (submodule_url_is_relative(url) || starts_with(url, "git://")) {
+		char *decoded;
+		const char *next;
+		int has_nl;
+
+		/*
+		 * This could be appended to an http URL and url-decoded;
+		 * check for malicious characters.
+		 */
+		decoded = url_decode(url);
+		has_nl = !!strchr(decoded, '\n');
+
+		free(decoded);
+		if (has_nl)
+			return -1;
+
+		/*
+		 * URLs which escape their root via "../" can overwrite
+		 * the host field and previous components, resolving to
+		 * URLs like https::example.com/submodule.git and
+		 * https:///example.com/submodule.git that were
+		 * susceptible to CVE-2020-11008.
+		 */
+		if (count_leading_dotdots(url, &next) > 0 &&
+		    (*next == ':' || *next == '/'))
+			return -1;
+	}
+
+	else if (url_to_curl_url(url, &curl_url)) {
+		int ret = 0;
+		char *normalized = url_normalize(curl_url, NULL);
+		if (normalized) {
+			char *decoded = url_decode(normalized);
+			if (strchr(decoded, '\n'))
+				ret = -1;
+			free(normalized);
+			free(decoded);
+		} else {
+			ret = -1;
+		}
+
+		return ret;
+	}
+
+	return 0;
+}
+
 static int name_and_item_from_var(const char *var, struct strbuf *name,
 				  struct strbuf *item)
 {