Merge branch 'sj/ref-consistency-checks-more'

"git fsck" becomes more careful when checking the refs.

* sj/ref-consistency-checks-more:
  builtin/fsck: add `git refs verify` child process
  packed-backend: check whether the "packed-refs" is sorted
  packed-backend: add "packed-refs" entry consistency check
  packed-backend: check whether the refname contains NUL characters
  packed-backend: add "packed-refs" header consistency check
  packed-backend: check if header starts with "# pack-refs with: "
  packed-backend: check whether the "packed-refs" is regular file
  builtin/refs: get worktrees without reading head information
  t0602: use subshell to ensure working directory unchanged

Author: gitster

Documentation/fsck-msgids.adoc

@@ -16,6 +16,13 @@
 `badObjectSha1`::
 	(ERROR) An object has a bad sha1.
 
+`badPackedRefEntry`::
+	(ERROR) The "packed-refs" file contains an invalid entry.
+
+`badPackedRefHeader`::
+	(ERROR) The "packed-refs" file contains an invalid
+	header.
+
 `badParentSha1`::
 	(ERROR) A commit object has a bad parent sha1.
 
@@ -176,6 +183,13 @@
 `nullSha1`::
 	(WARN) Tree contains entries pointing to a null sha1.
 
+`packedRefEntryNotTerminated`::
+	(ERROR) The "packed-refs" file contains an entry that is
+	not terminated by a newline.
+
+`packedRefUnsorted`::
+	(ERROR) The "packed-refs" file is not sorted.
+
 `refMissingNewline`::
 	(INFO) A loose ref that does not end with newline(LF). As
 	valid implementations of Git never created such a loose ref

Documentation/git-fsck.adoc

@@ -12,7 +12,7 @@ SYNOPSIS
 'git fsck' [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]
 	 [--[no-]full] [--strict] [--verbose] [--lost-found]
 	 [--[no-]dangling] [--[no-]progress] [--connectivity-only]
-	 [--[no-]name-objects] [<object>...]
+	 [--[no-]name-objects] [--[no-]references] [<object>...]
 
 DESCRIPTION
 -----------
@@ -104,6 +104,11 @@ care about this output and want to speed it up further.
 	progress status even if the standard error stream is not
 	directed to a terminal.
 
+--[no-]references::
+	Control whether to check the references database consistency
+	via 'git refs verify'. See linkgit:git-refs[1] for details.
+	The default is to check the references database.
+
 CONFIGURATION
 -------------
 

builtin/fsck.c

@@ -50,6 +50,7 @@ static int verbose;
 static int show_progress = -1;
 static int show_dangling = 1;
 static int name_objects;
+static int check_references = 1;
 #define ERROR_OBJECT 01
 #define ERROR_REACHABLE 02
 #define ERROR_PACK 04
@@ -905,11 +906,37 @@ static int check_pack_rev_indexes(struct repository *r, int show_progress)
 	return res;
 }
 
+static void fsck_refs(struct repository *r)
+{
+	struct child_process refs_verify = CHILD_PROCESS_INIT;
+	struct progress *progress = NULL;
+
+	if (show_progress)
+		progress = start_progress(r, _("Checking ref database"), 1);
+
+	if (verbose)
+		fprintf_ln(stderr, _("Checking ref database"));
+
+	child_process_init(&refs_verify);
+	refs_verify.git_cmd = 1;
+	strvec_pushl(&refs_verify.args, "refs", "verify", NULL);
+	if (verbose)
+		strvec_push(&refs_verify.args, "--verbose");
+	if (check_strict)
+		strvec_push(&refs_verify.args, "--strict");
+
+	if (run_command(&refs_verify))
+		errors_found |= ERROR_REFS;
+
+	display_progress(progress, 1);
+	stop_progress(&progress);
+}
+
 static char const * const fsck_usage[] = {
 	N_("git fsck [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]\n"
 	   "         [--[no-]full] [--strict] [--verbose] [--lost-found]\n"
 	   "         [--[no-]dangling] [--[no-]progress] [--connectivity-only]\n"
-	   "         [--[no-]name-objects] [<object>...]"),
+	   "         [--[no-]name-objects] [--[no-]references] [<object>...]"),
 	NULL
 };
 
@@ -928,6 +955,7 @@ static struct option fsck_opts[] = {
 				N_("write dangling objects in .git/lost-found")),
 	OPT_BOOL(0, "progress", &show_progress, N_("show progress")),
 	OPT_BOOL(0, "name-objects", &name_objects, N_("show verbose names for reachable objects")),
+	OPT_BOOL(0, "references", &check_references, N_("check reference database consistency")),
 	OPT_END(),
 };
 
@@ -970,6 +998,9 @@ int cmd_fsck(int argc,
 	git_config(git_fsck_config, &fsck_obj_options);
 	prepare_repo_settings(the_repository);
 
+	if (check_references)
+		fsck_refs(the_repository);
+
 	if (connectivity_only) {
 		for_each_loose_object(mark_loose_for_connectivity, NULL, 0);
 		for_each_packed_object(the_repository,

builtin/refs.c

@@ -91,7 +91,7 @@ static int cmd_refs_verify(int argc, const char **argv, const char *prefix,
 	git_config(git_fsck_config, &fsck_refs_options);
 	prepare_repo_settings(the_repository);
 
-	worktrees = get_worktrees();
+	worktrees = get_worktrees_without_reading_head();
 	for (size_t i = 0; worktrees[i]; i++)
 		ret |= refs_fsck(get_worktree_ref_store(worktrees[i]),
 				 &fsck_refs_options, worktrees[i]);

fsck.h

@@ -30,6 +30,8 @@ enum fsck_msg_type {
 	FUNC(BAD_EMAIL, ERROR) \
 	FUNC(BAD_NAME, ERROR) \
 	FUNC(BAD_OBJECT_SHA1, ERROR) \
+	FUNC(BAD_PACKED_REF_ENTRY, ERROR) \
+	FUNC(BAD_PACKED_REF_HEADER, ERROR) \
 	FUNC(BAD_PARENT_SHA1, ERROR) \
 	FUNC(BAD_REF_CONTENT, ERROR) \
 	FUNC(BAD_REF_FILETYPE, ERROR) \
@@ -53,6 +55,8 @@ enum fsck_msg_type {
 	FUNC(MISSING_TYPE, ERROR) \
 	FUNC(MISSING_TYPE_ENTRY, ERROR) \
 	FUNC(MULTIPLE_AUTHORS, ERROR) \
+	FUNC(PACKED_REF_ENTRY_NOT_TERMINATED, ERROR) \
+	FUNC(PACKED_REF_UNSORTED, ERROR) \
 	FUNC(TREE_NOT_SORTED, ERROR) \
 	FUNC(UNKNOWN_TYPE, ERROR) \
 	FUNC(ZERO_PADDED_DATE, ERROR) \