Merge branch 'ds/commit-graph-fsck' into jt/commit-graph-per-object-store

* ds/commit-graph-fsck: (23 commits)
  coccinelle: update commit.cocci
  commit-graph: update design document
  gc: automatically write commit-graph files
  commit-graph: add '--reachable' option
  commit-graph: use string-list API for input
  fsck: verify commit-graph
  commit-graph: verify contents match checksum
  commit-graph: test for corrupted octopus edge
  commit-graph: verify commit date
  commit-graph: verify generation number
  commit-graph: verify parent list
  commit-graph: verify root tree OIDs
  commit-graph: verify objects exist
  commit-graph: verify corrupt OID fanout and lookup
  commit-graph: verify required chunks are present
  commit-graph: verify catches corrupt signature
  commit-graph: add 'verify' subcommand
  commit-graph: load a root tree from specific graph
  commit: force commit to parse from object database
  commit-graph: parse commit from chosen graph
  ...

3 files changed, 95 insertions, 31 deletions

diff --git a/builtin/commit-graph.c b/builtin/commit-graph.c
index 37420ae0fd..c7d0db5ab4 100644
--- a/builtin/commit-graph.c
+++ b/builtin/commit-graph.c
@@ -3,12 +3,19 @@
 #include "dir.h"
 #include "lockfile.h"
 #include "parse-options.h"
+#include "repository.h"
 #include "commit-graph.h"
 
 static char const * const builtin_commit_graph_usage[] = {
 	N_("git commit-graph [--object-dir <objdir>]"),
 	N_("git commit-graph read [--object-dir <objdir>]"),
-	N_("git commit-graph write [--object-dir <objdir>] [--append] [--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph verify [--object-dir <objdir>]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append] [--reachable|--stdin-packs|--stdin-commits]"),
+	NULL
+};
+
+static const char * const builtin_commit_graph_verify_usage[] = {
+	N_("git commit-graph verify [--object-dir <objdir>]"),
 	NULL
 };
 
@@ -18,17 +25,48 @@ static const char * const builtin_commit_graph_read_usage[] = {
 };
 
 static const char * const builtin_commit_graph_write_usage[] = {
-	N_("git commit-graph write [--object-dir <objdir>] [--append] [--stdin-packs|--stdin-commits]"),
+	N_("git commit-graph write [--object-dir <objdir>] [--append] [--reachable|--stdin-packs|--stdin-commits]"),
 	NULL
 };
 
 static struct opts_commit_graph {
 	const char *obj_dir;
+	int reachable;
 	int stdin_packs;
 	int stdin_commits;
 	int append;
 } opts;
 
+
+static int graph_verify(int argc, const char **argv)
+{
+	struct commit_graph *graph = NULL;
+	char *graph_name;
+
+	static struct option builtin_commit_graph_verify_options[] = {
+		OPT_STRING(0, "object-dir", &opts.obj_dir,
+			   N_("dir"),
+			   N_("The object directory to store the graph")),
+		OPT_END(),
+	};
+
+	argc = parse_options(argc, argv, NULL,
+			     builtin_commit_graph_verify_options,
+			     builtin_commit_graph_verify_usage, 0);
+
+	if (!opts.obj_dir)
+		opts.obj_dir = get_object_directory();
+
+	graph_name = get_commit_graph_filename(opts.obj_dir);
+	graph = load_commit_graph_one(graph_name);
+	FREE_AND_NULL(graph_name);
+
+	if (!graph)
+		return 0;
+
+	return verify_commit_graph(the_repository, graph);
+}
+
 static int graph_read(int argc, const char **argv)
 {
 	struct commit_graph *graph = NULL;
@@ -51,8 +89,11 @@ static int graph_read(int argc, const char **argv)
 	graph_name = get_commit_graph_filename(opts.obj_dir);
 	graph = load_commit_graph_one(graph_name);
 
-	if (!graph)
+	if (!graph) {
+		UNLEAK(graph_name);
 		die("graph file %s does not exist", graph_name);
+	}
+
 	FREE_AND_NULL(graph_name);
 
 	printf("header: %08x %d %d %d %d\n",
@@ -79,18 +120,16 @@ static int graph_read(int argc, const char **argv)
 
 static int graph_write(int argc, const char **argv)
 {
-	const char **pack_indexes = NULL;
-	int packs_nr = 0;
-	const char **commit_hex = NULL;
-	int commits_nr = 0;
-	const char **lines = NULL;
-	int lines_nr = 0;
-	int lines_alloc = 0;
+	struct string_list *pack_indexes = NULL;
+	struct string_list *commit_hex = NULL;
+	struct string_list lines;
 
 	static struct option builtin_commit_graph_write_options[] = {
 		OPT_STRING(0, "object-dir", &opts.obj_dir,
 			N_("dir"),
 			N_("The object directory to store the graph")),
+		OPT_BOOL(0, "reachable", &opts.reachable,
+			N_("start walk at all refs")),
 		OPT_BOOL(0, "stdin-packs", &opts.stdin_packs,
 			N_("scan pack-indexes listed by stdin for commits")),
 		OPT_BOOL(0, "stdin-commits", &opts.stdin_commits,
@@ -104,39 +143,35 @@ static int graph_write(int argc, const char **argv)
 			     builtin_commit_graph_write_options,
 			     builtin_commit_graph_write_usage, 0);
 
-	if (opts.stdin_packs && opts.stdin_commits)
-		die(_("cannot use both --stdin-commits and --stdin-packs"));
+	if (opts.reachable + opts.stdin_packs + opts.stdin_commits > 1)
+		die(_("use at most one of --reachable, --stdin-commits, or --stdin-packs"));
 	if (!opts.obj_dir)
 		opts.obj_dir = get_object_directory();
 
+	if (opts.reachable) {
+		write_commit_graph_reachable(opts.obj_dir, opts.append);
+		return 0;
+	}
+
+	string_list_init(&lines, 0);
 	if (opts.stdin_packs || opts.stdin_commits) {
 		struct strbuf buf = STRBUF_INIT;
-		lines_nr = 0;
-		lines_alloc = 128;
-		ALLOC_ARRAY(lines, lines_alloc);
-
-		while (strbuf_getline(&buf, stdin) != EOF) {
-			ALLOC_GROW(lines, lines_nr + 1, lines_alloc);
-			lines[lines_nr++] = strbuf_detach(&buf, NULL);
-		}
-
-		if (opts.stdin_packs) {
-			pack_indexes = lines;
-			packs_nr = lines_nr;
-		}
-		if (opts.stdin_commits) {
-			commit_hex = lines;
-			commits_nr = lines_nr;
-		}
+
+		while (strbuf_getline(&buf, stdin) != EOF)
+			string_list_append(&lines, strbuf_detach(&buf, NULL));
+
+		if (opts.stdin_packs)
+			pack_indexes = &lines;
+		if (opts.stdin_commits)
+			commit_hex = &lines;
 	}
 
 	write_commit_graph(opts.obj_dir,
 			   pack_indexes,
-			   packs_nr,
 			   commit_hex,
-			   commits_nr,
 			   opts.append);
 
+	string_list_clear(&lines, 0);
 	return 0;
 }
 
@@ -162,6 +197,8 @@ int cmd_commit_graph(int argc, const char **argv, const char *prefix)
 	if (argc > 0) {
 		if (!strcmp(argv[0], "read"))
 			return graph_read(argc, argv);
+		if (!strcmp(argv[0], "verify"))
+			return graph_verify(argc, argv);
 		if (!strcmp(argv[0], "write"))
 			return graph_write(argc, argv);
 	}
diff --git a/builtin/fsck.c b/builtin/fsck.c
index 263191942d..ea5e2a03e6 100644
--- a/builtin/fsck.c
+++ b/builtin/fsck.c
@@ -18,6 +18,7 @@
 #include "decorate.h"
 #include "packfile.h"
 #include "object-store.h"
+#include "run-command.h"
 
 #define REACHABLE 0x0001
 #define SEEN      0x0002
@@ -47,6 +48,7 @@ static int name_objects;
 #define ERROR_REACHABLE 02
 #define ERROR_PACK 04
 #define ERROR_REFS 010
+#define ERROR_COMMIT_GRAPH 020
 
 static const char *describe_object(struct object *obj)
 {
@@ -827,5 +829,24 @@ int cmd_fsck(int argc, const char **argv, const char *prefix)
 	}
 
 	check_connectivity();
+
+	if (core_commit_graph) {
+		struct child_process commit_graph_verify = CHILD_PROCESS_INIT;
+		const char *verify_argv[] = { "commit-graph", "verify", NULL, NULL, NULL };
+
+		commit_graph_verify.argv = verify_argv;
+		commit_graph_verify.git_cmd = 1;
+		if (run_command(&commit_graph_verify))
+			errors_found |= ERROR_COMMIT_GRAPH;
+
+		prepare_alt_odb(the_repository);
+		for (alt =  the_repository->objects->alt_odb_list; alt; alt = alt->next) {
+			verify_argv[2] = "--object-dir";
+			verify_argv[3] = alt->path;
+			if (run_command(&commit_graph_verify))
+				errors_found |= ERROR_COMMIT_GRAPH;
+		}
+	}
+
 	return errors_found;
 }
diff --git a/builtin/gc.c b/builtin/gc.c
index ccfb1ceaeb..e103f0f85d 100644
--- a/builtin/gc.c
+++ b/builtin/gc.c
@@ -20,6 +20,7 @@
 #include "sigchain.h"
 #include "argv-array.h"
 #include "commit.h"
+#include "commit-graph.h"
 #include "packfile.h"
 #include "object-store.h"
 #include "pack.h"
@@ -40,6 +41,7 @@ static int aggressive_depth = 50;
 static int aggressive_window = 250;
 static int gc_auto_threshold = 6700;
 static int gc_auto_pack_limit = 50;
+static int gc_write_commit_graph;
 static int detach_auto = 1;
 static timestamp_t gc_log_expire_time;
 static const char *gc_log_expire = "1.day.ago";
@@ -129,6 +131,7 @@ static void gc_config(void)
 	git_config_get_int("gc.aggressivedepth", &aggressive_depth);
 	git_config_get_int("gc.auto", &gc_auto_threshold);
 	git_config_get_int("gc.autopacklimit", &gc_auto_pack_limit);
+	git_config_get_bool("gc.writecommitgraph", &gc_write_commit_graph);
 	git_config_get_bool("gc.autodetach", &detach_auto);
 	git_config_get_expiry("gc.pruneexpire", &prune_expire);
 	git_config_get_expiry("gc.worktreepruneexpire", &prune_worktrees_expire);
@@ -641,6 +644,9 @@ int cmd_gc(int argc, const char **argv, const char *prefix)
 	if (pack_garbage.nr > 0)
 		clean_pack_garbage();
 
+	if (gc_write_commit_graph)
+		write_commit_graph_reachable(get_object_directory(), 0);
+
 	if (auto_gc && too_many_loose_objects())
 		warning(_("There are too many unreachable loose objects; "
 			"run 'git prune' to remove them."));