Merge branch 'jk/submodule-name-verify-fix' into jk/submodule-name-verify-fsck

* jk/submodule-name-verify-fix:
  verify_path: disallow symlinks in .gitmodules, etc
  update-index: stat updated files earlier
  verify_path: drop clever fallthrough
  skip_prefix: add icase-insensitive variant
  is_{hfs,ntfs}_dotgitmodules: add tests
  path: match NTFS short names for more .git files
  is_hfs_dotgit: match other .git files
  is_ntfs_dotgit: use a size_t for traversing string
  submodule-config: verify submodule names as paths

Note that this includes two bits of evil-merge:

 - there's a new call to verify_path() that doesn't actually
   have a mode available. It should be OK to pass "0" here,
   since we're just manipulating the untracked cache, not an
   actual index entry.

 - the lstat() in builtin/update-index.c:update_one() needs
   to be updated to handle the fsmonitor case (without this
   it still behaves correctly, but does an unnecessary
   lstat).

Author: peff

apply.c

@@ -3860,9 +3860,9 @@ static int check_unsafe_path(struct patch *patch)
 	if (!patch->is_delete)
 		new_name = patch->new_name;
 
-	if (old_name && !verify_path(old_name))
+	if (old_name && !verify_path(old_name, patch->old_mode))
 		return error(_("invalid path '%s'"), old_name);
-	if (new_name && !verify_path(new_name))
+	if (new_name && !verify_path(new_name, patch->new_mode))
 		return error(_("invalid path '%s'"), new_name);
 	return 0;
 }

builtin/submodule--helper.c

@@ -1817,6 +1817,29 @@ static int is_active(int argc, const char **argv, const char *prefix)
 	return !is_submodule_active(the_repository, argv[1]);
 }
 
+/*
+ * Exit non-zero if any of the submodule names given on the command line is
+ * invalid. If no names are given, filter stdin to print only valid names
+ * (which is primarily intended for testing).
+ */
+static int check_name(int argc, const char **argv, const char *prefix)
+{
+	if (argc > 1) {
+		while (*++argv) {
+			if (check_submodule_name(*argv) < 0)
+				return 1;
+		}
+	} else {
+		struct strbuf buf = STRBUF_INIT;
+		while (strbuf_getline(&buf, stdin) != EOF) {
+			if (!check_submodule_name(buf.buf))
+				printf("%s\n", buf.buf);
+		}
+		strbuf_release(&buf);
+	}
+	return 0;
+}
+
 #define SUPPORT_SUPER_PREFIX (1<<0)
 
 struct cmd_struct {
@@ -1842,6 +1865,7 @@ static struct cmd_struct commands[] = {
 	{"push-check", push_check, 0},
 	{"absorb-git-dirs", absorb_git_dirs, SUPPORT_SUPER_PREFIX},
 	{"is-active", is_active, 0},
+	{"check-name", check_name, 0},
 };
 
 int cmd_submodule__helper(int argc, const char **argv, const char *prefix)

builtin/update-index.c

@@ -364,10 +364,9 @@ static int process_directory(const char *path, int len, struct stat *st)
 	return error("%s: is a directory - add files inside instead", path);
 }
 
-static int process_path(const char *path)
+static int process_path(const char *path, struct stat *st, int stat_errno)
 {
 	int pos, len;
-	struct stat st;
 	const struct cache_entry *ce;
 
 	len = strlen(path);
@@ -391,13 +390,13 @@ static int process_path(const char *path)
 	 * First things first: get the stat information, to decide
 	 * what to do about the pathname!
 	 */
-	if (lstat(path, &st) < 0)
-		return process_lstat_error(path, errno);
+	if (stat_errno)
+		return process_lstat_error(path, stat_errno);
 
-	if (S_ISDIR(st.st_mode))
-		return process_directory(path, len, &st);
+	if (S_ISDIR(st->st_mode))
+		return process_directory(path, len, st);
 
-	return add_one_path(ce, path, len, &st);
+	return add_one_path(ce, path, len, st);
 }
 
 static int add_cacheinfo(unsigned int mode, const struct object_id *oid,
@@ -406,7 +405,7 @@ static int add_cacheinfo(unsigned int mode, const struct object_id *oid,
 	int size, len, option;
 	struct cache_entry *ce;
 
-	if (!verify_path(path))
+	if (!verify_path(path, mode))
 		return error("Invalid path '%s'", path);
 
 	len = strlen(path);
@@ -449,7 +448,18 @@ static void chmod_path(char flip, const char *path)
 
 static void update_one(const char *path)
 {
-	if (!verify_path(path)) {
+	int stat_errno = 0;
+	struct stat st;
+
+	if (mark_valid_only || mark_skip_worktree_only || force_remove ||
+	    mark_fsmonitor_only)
+		st.st_mode = 0;
+	else if (lstat(path, &st) < 0) {
+		st.st_mode = 0;
+		stat_errno = errno;
+	} /* else stat is valid */
+
+	if (!verify_path(path, st.st_mode)) {
 		fprintf(stderr, "Ignoring path %s\n", path);
 		return;
 	}
@@ -475,7 +485,7 @@ static void update_one(const char *path)
 		report("remove '%s'", path);
 		return;
 	}
-	if (process_path(path))
+	if (process_path(path, &st, stat_errno))
 		die("Unable to process path %s", path);
 	report("add '%s'", path);
 }
@@ -545,7 +555,7 @@ static void read_index_info(int nul_term_line)
 			path_name = uq.buf;
 		}
 
-		if (!verify_path(path_name)) {
+		if (!verify_path(path_name, mode)) {
 			fprintf(stderr, "Ignoring path %s\n", path_name);
 			continue;
 		}

cache.h

@@ -634,7 +634,7 @@ extern int unmerged_index(const struct index_state *);
  */
 extern int index_has_changes(struct strbuf *sb);
 
-extern int verify_path(const char *path);
+extern int verify_path(const char *path, unsigned mode);
 extern int strcmp_offset(const char *s1, const char *s2, size_t *first_change);
 extern int index_dir_exists(struct index_state *istate, const char *name, int namelen);
 extern void adjust_dirname_case(struct index_state *istate, char *name);
@@ -1165,7 +1165,15 @@ int normalize_path_copy(char *dst, const char *src);
 int longest_ancestor_length(const char *path, struct string_list *prefixes);
 char *strip_path_suffix(const char *path, const char *suffix);
 int daemon_avoid_alias(const char *path);
-extern int is_ntfs_dotgit(const char *name);
+
+/*
+ * These functions match their is_hfs_dotgit() counterparts; see utf8.h for
+ * details.
+ */
+int is_ntfs_dotgit(const char *name);
+int is_ntfs_dotgitmodules(const char *name);
+int is_ntfs_dotgitignore(const char *name);
+int is_ntfs_dotgitattributes(const char *name);
 
 /*
  * Returns true iff "str" could be confused as a command-line option when

dir.c

@@ -2992,7 +2992,7 @@ void untracked_cache_invalidate_path(struct index_state *istate,
 {
 	if (!istate->untracked || !istate->untracked->root)
 		return;
-	if (!safe_path && !verify_path(path))
+	if (!safe_path && !verify_path(path, 0))
 		return;
 	invalidate_one_component(istate->untracked, istate->untracked->root,
 				 path, strlen(path));

git-compat-util.h

@@ -1001,6 +1001,23 @@ static inline int sane_iscase(int x, int is_lower)
 		return (x & 0x20) == 0;
 }
 
+/*
+ * Like skip_prefix, but compare case-insensitively. Note that the comparison
+ * is done via tolower(), so it is strictly ASCII (no multi-byte characters or
+ * locale-specific conversions).
+ */
+static inline int skip_iprefix(const char *str, const char *prefix,
+			       const char **out)
+{
+	do {
+		if (!*prefix) {
+			*out = str;
+			return 1;
+		}
+	} while (tolower(*str++) == tolower(*prefix++));
+	return 0;
+}
+
 static inline int strtoul_ui(char const *s, int base, unsigned int *result)
 {
 	unsigned long ul;

git-submodule.sh

@@ -229,6 +229,11 @@ Use -f if you really want to add it." >&2
 		sm_name="$sm_path"
 	fi
 
+	if ! git submodule--helper check-name "$sm_name"
+	then
+		die "$(eval_gettext "'$sm_name' is not a valid submodule name")"
+	fi
+
 	# perhaps the path exists and is already a git repo, else clone it
 	if test -e "$sm_path"
 	then

path.c

@@ -1305,7 +1305,7 @@ static int only_spaces_and_periods(const char *path, size_t len, size_t skip)
 
 int is_ntfs_dotgit(const char *name)
 {
-	int len;
+	size_t len;
 
 	for (len = 0; ; len++)
 		if (!name[len] || name[len] == '\\' || is_dir_sep(name[len])) {
@@ -1322,6 +1322,90 @@ int is_ntfs_dotgit(const char *name)
 		}
 }
 
+static int is_ntfs_dot_generic(const char *name,
+			       const char *dotgit_name,
+			       size_t len,
+			       const char *dotgit_ntfs_shortname_prefix)
+{
+	int saw_tilde;
+	size_t i;
+
+	if ((name[0] == '.' && !strncasecmp(name + 1, dotgit_name, len))) {
+		i = len + 1;
+only_spaces_and_periods:
+		for (;;) {
+			char c = name[i++];
+			if (!c)
+				return 1;
+			if (c != ' ' && c != '.')
+				return 0;
+		}
+	}
+
+	/*
+	 * Is it a regular NTFS short name, i.e. shortened to 6 characters,
+	 * followed by ~1, ... ~4?
+	 */
+	if (!strncasecmp(name, dotgit_name, 6) && name[6] == '~' &&
+	    name[7] >= '1' && name[7] <= '4') {
+		i = 8;
+		goto only_spaces_and_periods;
+	}
+
+	/*
+	 * Is it a fall-back NTFS short name (for details, see
+	 * https://en.wikipedia.org/wiki/8.3_filename?
+	 */
+	for (i = 0, saw_tilde = 0; i < 8; i++)
+		if (name[i] == '\0')
+			return 0;
+		else if (saw_tilde) {
+			if (name[i] < '0' || name[i] > '9')
+				return 0;
+		} else if (name[i] == '~') {
+			if (name[++i] < '1' || name[i] > '9')
+				return 0;
+			saw_tilde = 1;
+		} else if (i >= 6)
+			return 0;
+		else if (name[i] < 0) {
+			/*
+			 * We know our needles contain only ASCII, so we clamp
+			 * here to make the results of tolower() sane.
+			 */
+			return 0;
+		} else if (tolower(name[i]) != dotgit_ntfs_shortname_prefix[i])
+			return 0;
+
+	goto only_spaces_and_periods;
+}
+
+/*
+ * Inline helper to make sure compiler resolves strlen() on literals at
+ * compile time.
+ */
+static inline int is_ntfs_dot_str(const char *name, const char *dotgit_name,
+				  const char *dotgit_ntfs_shortname_prefix)
+{
+	return is_ntfs_dot_generic(name, dotgit_name, strlen(dotgit_name),
+				   dotgit_ntfs_shortname_prefix);
+}
+
+int is_ntfs_dotgitmodules(const char *name)
+{
+	return is_ntfs_dot_str(name, "gitmodules", "gi7eba");
+}
+
+int is_ntfs_dotgitignore(const char *name)
+{
+	return is_ntfs_dot_str(name, "gitignore", "gi250a");
+}
+
+int is_ntfs_dotgitattributes(const char *name)
+{
+	return is_ntfs_dot_str(name, "gitattributes", "gi7d29");
+}
+
 int looks_like_command_line_option(const char *str)
 {
 	return str && str[0] == '-';