fsck: create scaffolding for rev-index checks

The 'fsck' builtin checks many of Git's on-disk data structures, but
does not currently validate the pack rev-index files (a .rev file to
pair with a .pack and .idx file).

Before doing a more-involved check process, create the scaffolding
within builtin/fsck.c to have a new error type and add that error type
when the API method verify_pack_revindex() returns an error. That method
does nothing currently, but we will add checks to it in later changes.

For now, check that 'git fsck' succeeds without any errors in the normal
case. Future checks will be paired with tests that corrupt the .rev file
appropriately.

Signed-off-by: Derrick Stolee <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: derrickstolee

builtin/fsck.c

@@ -24,6 +24,7 @@
 #include "resolve-undo.h"
 #include "run-command.h"
 #include "worktree.h"
+#include "pack-revindex.h"
 
 #define REACHABLE 0x0001
 #define SEEN      0x0002
@@ -53,6 +54,7 @@ static int name_objects;
 #define ERROR_REFS 010
 #define ERROR_COMMIT_GRAPH 020
 #define ERROR_MULTI_PACK_INDEX 040
+#define ERROR_PACK_REV_INDEX 0100
 
 static const char *describe_object(const struct object_id *oid)
 {
@@ -856,6 +858,32 @@ static int mark_packed_for_connectivity(const struct object_id *oid,
 	return 0;
 }
 
+static int check_pack_rev_indexes(struct repository *r, int show_progress)
+{
+	struct progress *progress = NULL;
+	uint32_t pack_count = 0;
+	int res = 0;
+
+	if (show_progress) {
+		for (struct packed_git *p = get_all_packs(the_repository); p; p = p->next)
+			pack_count++;
+		progress = start_delayed_progress("Verifying reverse pack-indexes", pack_count);
+		pack_count = 0;
+	}
+
+	for (struct packed_git *p = get_all_packs(the_repository); p; p = p->next) {
+		if (!load_pack_revindex(the_repository, p) &&
+		    verify_pack_revindex(p)) {
+			error(_("invalid rev-index for pack '%s'"), p->pack_name);
+			res = ERROR_PACK_REV_INDEX;
+		}
+		display_progress(progress, ++pack_count);
+	}
+	stop_progress(&progress);
+
+	return res;
+}
+
 static char const * const fsck_usage[] = {
 	N_("git fsck [--tags] [--root] [--unreachable] [--cache] [--no-reflogs]\n"
 	   "         [--[no-]full] [--strict] [--verbose] [--lost-found]\n"
@@ -1019,6 +1047,8 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 		free_worktrees(worktrees);
 	}
 
+	errors_found |= check_pack_rev_indexes(the_repository, show_progress);
+
 	check_connectivity();
 
 	if (the_repository->settings.core_commit_graph) {

pack-revindex.c

@@ -301,6 +301,17 @@ int load_pack_revindex(struct repository *r, struct packed_git *p)
 	return -1;
 }
 
+/*
+ * verify_pack_revindex verifies that the on-disk rev-index for the given
+ * pack-file is the same that would be created if written from scratch.
+ *
+ * A negative number is returned on error.
+ */
+int verify_pack_revindex(struct packed_git *p)
+{
+	return 0;
+}
+
 int load_midx_revindex(struct multi_pack_index *m)
 {
 	struct strbuf revindex_name = STRBUF_INIT;

pack-revindex.h

@@ -51,6 +51,14 @@ struct repository;
  */
 int load_pack_revindex(struct repository *r, struct packed_git *p);
 
+/*
+ * verify_pack_revindex verifies that the on-disk rev-index for the given
+ * pack-file is the same that would be created if written from scratch.
+ *
+ * A negative number is returned on error.
+ */
+int verify_pack_revindex(struct packed_git *p);
+
 /*
  * load_midx_revindex loads the '.rev' file corresponding to the given
  * multi-pack index by mmap-ing it and assigning pointers in the

t/t5325-reverse-index.sh

@@ -131,4 +131,18 @@ test_expect_success 'revindex in-memory vs on-disk' '
 		test_cmp on-disk in-core
 	)
 '
+
+test_expect_success 'fsck succeeds on good rev-index' '
+	test_when_finished rm -fr repo &&
+	git init repo &&
+	(
+		cd repo &&
+
+		test_commit commit &&
+		git -c pack.writeReverseIndex=true repack -ad &&
+		git fsck 2>err &&
+		test_must_be_empty err
+	)
+'
+
 test_done