Merge branch 'nd/clone-connectivity-shortcut'

Special case "git clone" and use lighter-weight implementation to
check the completeness of the history behind refs.

* nd/clone-connectivity-shortcut:
  clone: open a shortcut for connectivity check
  index-pack: remove dead code (it should never happen)
  fetch-pack: prepare updated shallow file before fetching the pack
  clone: let the user know when check_everything_connected is run

Documentation/git-index-pack.txt

@@ -74,6 +74,9 @@ OPTIONS
 --strict::
 	Die, if the pack contains broken objects or links.
 
+--check-self-contained-and-connected::
+	Die if the pack contains broken links. For internal use only.
+
 --threads=<n>::
 	Specifies the number of threads to spawn when resolving
 	deltas. This requires that index-pack be compiled with

builtin/clone.c

@@ -541,12 +541,18 @@ static void update_remote_refs(const struct ref *refs,
 			       const struct ref *mapped_refs,
 			       const struct ref *remote_head_points_at,
 			       const char *branch_top,
-			       const char *msg)
+			       const char *msg,
+			       struct transport *transport)
 {
 	const struct ref *rm = mapped_refs;
 
-	if (check_everything_connected(iterate_ref_map, 0, &rm))
+	if (0 <= option_verbosity)
+		printf(_("Checking connectivity... "));
+	if (check_everything_connected_with_transport(iterate_ref_map,
+						      0, &rm, transport))
 		die(_("remote did not send all necessary objects"));
+	if (0 <= option_verbosity)
+		printf(_("done\n"));
 
 	if (refs) {
 		write_remote_refs(mapped_refs);
@@ -890,6 +896,9 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		if (option_upload_pack)
 			transport_set_option(transport, TRANS_OPT_UPLOADPACK,
 					     option_upload_pack);
+
+		if (transport->smart_options && !option_depth)
+			transport->smart_options->check_self_contained_and_connected = 1;
 	}
 
 	refs = transport_get_remote_refs(transport);
@@ -951,7 +960,7 @@ int cmd_clone(int argc, const char **argv, const char *prefix)
 		transport_fetch_refs(transport, mapped_refs);
 
 	update_remote_refs(refs, mapped_refs, remote_head_points_at,
-			   branch_top.buf, reflog_msg.buf);
+			   branch_top.buf, reflog_msg.buf, transport);
 
 	update_head(our_head_points_at, remote_head, reflog_msg.buf);
 

builtin/index-pack.c

@@ -77,8 +77,10 @@ static int nr_threads;
 
 static int from_stdin;
 static int strict;
+static int do_fsck_object;
 static int verbose;
 static int show_stat;
+static int check_self_contained_and_connected;
 
 static struct progress *progress;
 
@@ -187,13 +189,13 @@ static int mark_link(struct object *obj, int type, void *data)
 
 /* The content of each linked object must have been checked
    or it must be already present in the object database */
-static void check_object(struct object *obj)
+static unsigned check_object(struct object *obj)
 {
 	if (!obj)
-		return;
+		return 0;
 
 	if (!(obj->flags & FLAG_LINK))
-		return;
+		return 0;
 
 	if (!(obj->flags & FLAG_CHECKED)) {
 		unsigned long size;
@@ -201,17 +203,20 @@ static void check_object(struct object *obj)
 		if (type != obj->type || type <= 0)
 			die(_("object of unexpected type"));
 		obj->flags |= FLAG_CHECKED;
-		return;
+		return 1;
 	}
+
+	return 0;
 }
 
-static void check_objects(void)
+static unsigned check_objects(void)
 {
-	unsigned i, max;
+	unsigned i, max, foreign_nr = 0;
 
 	max = get_max_object_index();
 	for (i = 0; i < max; i++)
-		check_object(get_indexed_object(i));
+		foreign_nr += check_object(get_indexed_object(i));
+	return foreign_nr;
 }
 
 
@@ -747,8 +752,7 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 			int eaten;
 			void *buf = (void *) data;
 
-			if (!buf)
-				buf = new_data = get_data_from_pack(obj_entry);
+			assert(data && "data can only be NULL for large _blobs_");
 
 			/*
 			 * we do not need to free the memory here, as the
@@ -757,7 +761,8 @@ static void sha1_object(const void *data, struct object_entry *obj_entry,
 			obj = parse_object_buffer(sha1, type, size, buf, &eaten);
 			if (!obj)
 				die(_("invalid %s"), typename(type));
-			if (fsck_object(obj, 1, fsck_error_function))
+			if (do_fsck_object &&
+			    fsck_object(obj, 1, fsck_error_function))
 				die(_("Error in object"));
 			if (fsck_walk(obj, mark_link, NULL))
 				die(_("Not all child objects of %s are reachable"), sha1_to_hex(obj->sha1));
@@ -1491,6 +1496,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	struct pack_idx_entry **idx_objects;
 	struct pack_idx_option opts;
 	unsigned char pack_sha1[20];
+	unsigned foreign_nr = 1;	/* zero is a "good" value, assume bad */
 
 	if (argc == 2 && !strcmp(argv[1], "-h"))
 		usage(index_pack_usage);
@@ -1512,6 +1518,10 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 				fix_thin_pack = 1;
 			} else if (!strcmp(arg, "--strict")) {
 				strict = 1;
+				do_fsck_object = 1;
+			} else if (!strcmp(arg, "--check-self-contained-and-connected")) {
+				strict = 1;
+				check_self_contained_and_connected = 1;
 			} else if (!strcmp(arg, "--verify")) {
 				verify = 1;
 			} else if (!strcmp(arg, "--verify-stat")) {
@@ -1625,7 +1635,7 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	conclude_pack(fix_thin_pack, curr_pack, pack_sha1);
 	free(deltas);
 	if (strict)
-		check_objects();
+		foreign_nr = check_objects();
 
 	if (show_stat)
 		show_pack_info(stat_only);
@@ -1651,5 +1661,11 @@ int cmd_index_pack(int argc, const char **argv, const char *prefix)
 	if (index_name == NULL)
 		free((void *) curr_index);
 
+	/*
+	 * Let the caller know this pack is not self contained
+	 */
+	if (check_self_contained_and_connected && foreign_nr)
+		return 1;
+
 	return 0;
 }

commit.h

@@ -176,6 +176,8 @@ extern int for_each_commit_graft(each_commit_graft_fn, void *);
 extern int is_repository_shallow(void);
 extern struct commit_list *get_shallow_commits(struct object_array *heads,
 		int depth, int shallow_flag, int not_shallow_flag);
+extern void check_shallow_file_for_update(void);
+extern void set_alternate_shallow_file(const char *path);
 
 int is_descendant_of(struct commit *, struct commit_list *);
 int in_merge_bases(struct commit *, struct commit *);

connected.c

@@ -2,7 +2,12 @@
 #include "run-command.h"
 #include "sigchain.h"
 #include "connected.h"
+#include "transport.h"
 
+int check_everything_connected(sha1_iterate_fn fn, int quiet, void *cb_data)
+{
+	return check_everything_connected_with_transport(fn, quiet, cb_data, NULL);
+}
 /*
  * If we feed all the commits we want to verify to this command
  *
@@ -14,7 +19,10 @@
  *
  * Returns 0 if everything is connected, non-zero otherwise.
  */
-int check_everything_connected(sha1_iterate_fn fn, int quiet, void *cb_data)
+int check_everything_connected_with_transport(sha1_iterate_fn fn,
+					      int quiet,
+					      void *cb_data,
+					      struct transport *transport)
 {
 	struct child_process rev_list;
 	const char *argv[] = {"rev-list", "--objects",
@@ -22,10 +30,23 @@ int check_everything_connected(sha1_iterate_fn fn, int quiet, void *cb_data)
 	char commit[41];
 	unsigned char sha1[20];
 	int err = 0;
+	struct packed_git *new_pack = NULL;
 
 	if (fn(cb_data, sha1))
 		return err;
 
+	if (transport && transport->smart_options &&
+	    transport->smart_options->self_contained_and_connected &&
+	    transport->pack_lockfile &&
+	    !suffixcmp(transport->pack_lockfile, ".keep")) {
+		struct strbuf idx_file = STRBUF_INIT;
+		strbuf_addstr(&idx_file, transport->pack_lockfile);
+		strbuf_setlen(&idx_file, idx_file.len - 5); /* ".keep" */
+		strbuf_addstr(&idx_file, ".idx");
+		new_pack = add_packed_git(idx_file.buf, idx_file.len, 1);
+		strbuf_release(&idx_file);
+	}
+
 	if (quiet)
 		argv[5] = "--quiet";
 
@@ -42,6 +63,17 @@ int check_everything_connected(sha1_iterate_fn fn, int quiet, void *cb_data)
 
 	commit[40] = '\n';
 	do {
+		/*
+		 * If index-pack already checked that:
+		 * - there are no dangling pointers in the new pack
+		 * - the pack is self contained
+		 * Then if the updated ref is in the new pack, then we
+		 * are sure the ref is good and not sending it to
+		 * rev-list for verification.
+		 */
+		if (new_pack && find_pack_entry_one(sha1, new_pack))
+			continue;
+
 		memcpy(commit, sha1_to_hex(sha1), 40);
 		if (write_in_full(rev_list.in, commit, 41) < 0) {
 			if (errno != EPIPE && errno != EINVAL)

connected.h

@@ -1,6 +1,8 @@
 #ifndef CONNECTED_H
 #define CONNECTED_H
 
+struct transport;
+
 /*
  * Take callback data, and return next object name in the buffer.
  * When called after returning the name for the last object, return -1
@@ -16,5 +18,8 @@ typedef int (*sha1_iterate_fn)(void *, unsigned char [20]);
  * Return 0 if Ok, non zero otherwise (i.e. some missing objects)
  */
 extern int check_everything_connected(sha1_iterate_fn, int quiet, void *cb_data);
+extern int check_everything_connected_with_transport(sha1_iterate_fn, int quiet,
+						     void *cb_data,
+						     struct transport *transport);
 
 #endif /* CONNECTED_H */

fetch-pack.c

@@ -20,6 +20,8 @@ static int no_done;
 static int fetch_fsck_objects = -1;
 static int transfer_fsck_objects = -1;
 static int agent_supported;
+static struct lock_file shallow_lock;
+static const char *alternate_shallow_file;
 
 #define COMPLETE	(1U << 0)
 #define COMMON		(1U << 1)
@@ -683,12 +685,13 @@ static int get_pack(struct fetch_pack_args *args,
 		    int xd[2], char **pack_lockfile)
 {
 	struct async demux;
-	const char *argv[20];
+	const char *argv[22];
 	char keep_arg[256];
 	char hdr_arg[256];
 	const char **av;
 	int do_keep = args->keep_pack;
 	struct child_process cmd;
+	int ret;
 
 	memset(&demux, 0, sizeof(demux));
 	if (use_sideband) {
@@ -724,6 +727,11 @@ static int get_pack(struct fetch_pack_args *args,
 			do_keep = 1;
 	}
 
+	if (alternate_shallow_file) {
+		*av++ = "--shallow-file";
+		*av++ = alternate_shallow_file;
+	}
+
 	if (do_keep) {
 		if (pack_lockfile)
 			cmd.out = -1;
@@ -740,11 +748,14 @@ static int get_pack(struct fetch_pack_args *args,
 				strcpy(keep_arg + s, "localhost");
 			*av++ = keep_arg;
 		}
+		if (args->check_self_contained_and_connected)
+			*av++ = "--check-self-contained-and-connected";
 	}
 	else {
 		*av++ = "unpack-objects";
 		if (args->quiet || args->no_progress)
 			*av++ = "-q";
+		args->check_self_contained_and_connected = 0;
 	}
 	if (*hdr_arg)
 		*av++ = hdr_arg;
@@ -765,7 +776,12 @@ static int get_pack(struct fetch_pack_args *args,
 		close(cmd.out);
 	}
 
-	if (finish_command(&cmd))
+	ret = finish_command(&cmd);
+	if (!ret || (args->check_self_contained_and_connected && ret == 1))
+		args->self_contained_and_connected =
+			args->check_self_contained_and_connected &&
+			ret == 0;
+	else
 		die("%s failed", argv[0]);
 	if (use_sideband && finish_async(&demux))
 		die("error in sideband demultiplexer");
@@ -779,6 +795,27 @@ static int cmp_ref_by_name(const void *a_, const void *b_)
 	return strcmp(a->name, b->name);
 }
 
+static void setup_alternate_shallow(void)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int fd;
+
+	check_shallow_file_for_update();
+	fd = hold_lock_file_for_update(&shallow_lock, git_path("shallow"),
+				       LOCK_DIE_ON_ERROR);
+	if (write_shallow_commits(&sb, 0)) {
+		if (write_in_full(fd, sb.buf, sb.len) != sb.len)
+			die_errno("failed to write to %s", shallow_lock.filename);
+		alternate_shallow_file = shallow_lock.filename;
+	} else
+		/*
+		 * is_repository_shallow() sees empty string as "no
+		 * shallow file".
+		 */
+		alternate_shallow_file = "";
+	strbuf_release(&sb);
+}
+
 static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 				 int fd[2],
 				 const struct ref *orig_ref,
@@ -858,6 +895,8 @@ static struct ref *do_fetch_pack(struct fetch_pack_args *args,
 
 	if (args->stateless_rpc)
 		packet_flush(fd[1]);
+	if (args->depth > 0)
+		setup_alternate_shallow();
 	if (get_pack(args, fd, pack_lockfile))
 		die("git fetch-pack: fetch failed.");
 
@@ -936,15 +975,9 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 		       struct ref **sought, int nr_sought,
 		       char **pack_lockfile)
 {
-	struct stat st;
 	struct ref *ref_cpy;
 
 	fetch_pack_setup();
-	if (args->depth > 0) {
-		if (stat(git_path("shallow"), &st))
-			st.st_mtime = 0;
-	}
-
 	if (nr_sought)
 		nr_sought = remove_duplicates_in_refs(sought, nr_sought);
 
@@ -954,35 +987,12 @@ struct ref *fetch_pack(struct fetch_pack_args *args,
 	}
 	ref_cpy = do_fetch_pack(args, fd, ref, sought, nr_sought, pack_lockfile);
 
-	if (args->depth > 0) {
-		static struct lock_file lock;
-		struct cache_time mtime;
-		struct strbuf sb = STRBUF_INIT;
-		char *shallow = git_path("shallow");
-		int fd;
-
-		mtime.sec = st.st_mtime;
-		mtime.nsec = ST_MTIME_NSEC(st);
-		if (stat(shallow, &st)) {
-			if (mtime.sec)
-				die("shallow file was removed during fetch");
-		} else if (st.st_mtime != mtime.sec
-#ifdef USE_NSEC
-				|| ST_MTIME_NSEC(st) != mtime.nsec
-#endif
-			  )
-			die("shallow file was changed during fetch");
-
-		fd = hold_lock_file_for_update(&lock, shallow,
-					       LOCK_DIE_ON_ERROR);
-		if (!write_shallow_commits(&sb, 0)
-		 || write_in_full(fd, sb.buf, sb.len) != sb.len) {
-			unlink_or_warn(shallow);
-			rollback_lock_file(&lock);
-		} else {
-			commit_lock_file(&lock);
-		}
-		strbuf_release(&sb);
+	if (alternate_shallow_file) {
+		if (*alternate_shallow_file == '\0') { /* --unshallow */
+			unlink_or_warn(git_path("shallow"));
+			rollback_lock_file(&shallow_lock);
+		} else
+			commit_lock_file(&shallow_lock);
 	}
 
 	reprepare_packed_git();

fetch-pack.h

@@ -16,7 +16,9 @@ struct fetch_pack_args {
 		verbose:1,
 		no_progress:1,
 		include_tag:1,
-		stateless_rpc:1;
+		stateless_rpc:1,
+		check_self_contained_and_connected:1,
+		self_contained_and_connected:1;
 };
 
 /*

git.c

@@ -4,6 +4,7 @@
 #include "help.h"
 #include "quote.h"
 #include "run-command.h"
+#include "commit.h"
 
 const char git_usage_string[] =
 	"git [--version] [--help] [-c name=value]\n"
@@ -146,6 +147,12 @@ static int handle_options(const char ***argv, int *argc, int *envchanged)
 			setenv(GIT_LITERAL_PATHSPECS_ENVIRONMENT, "0", 1);
 			if (envchanged)
 				*envchanged = 1;
+		} else if (!strcmp(cmd, "--shallow-file")) {
+			(*argv)++;
+			(*argc)--;
+			set_alternate_shallow_file((*argv)[0]);
+			if (envchanged)
+				*envchanged = 1;
 		} else {
 			fprintf(stderr, "Unknown option: %s\n", cmd);
 			usage(git_usage_string);

shallow.c

@@ -3,6 +3,16 @@
 #include "tag.h"
 
 static int is_shallow = -1;
+static struct stat shallow_stat;
+static char *alternate_shallow_file;
+
+void set_alternate_shallow_file(const char *path)
+{
+	if (is_shallow != -1)
+		die("BUG: is_repository_shallow must not be called before set_alternate_shallow_file");
+	free(alternate_shallow_file);
+	alternate_shallow_file = path ? xstrdup(path) : NULL;
+}
 
 int register_shallow(const unsigned char *sha1)
 {
@@ -21,12 +31,21 @@ int is_repository_shallow(void)
 {
 	FILE *fp;
 	char buf[1024];
+	const char *path = alternate_shallow_file;
 
 	if (is_shallow >= 0)
 		return is_shallow;
 
-	fp = fopen(git_path("shallow"), "r");
-	if (!fp) {
+	if (!path)
+		path = git_path("shallow");
+	/*
+	 * fetch-pack sets '--shallow-file ""' as an indicator that no
+	 * shallow file should be used. We could just open it and it
+	 * will likely fail. But let's do an explicit check instead.
+	 */
+	if (!*path ||
+	    stat(path, &shallow_stat) ||
+	    (fp = fopen(path, "r")) == NULL) {
 		is_shallow = 0;
 		return is_shallow;
 	}
@@ -108,3 +127,22 @@ struct commit_list *get_shallow_commits(struct object_array *heads, int depth,
 
 	return result;
 }
+
+void check_shallow_file_for_update(void)
+{
+	struct stat st;
+
+	if (!is_shallow)
+		return;
+	else if (is_shallow == -1)
+		die("BUG: shallow must be initialized by now");
+
+	if (stat(git_path("shallow"), &st))
+		die("shallow file was removed during fetch");
+	else if (st.st_mtime != shallow_stat.st_mtime
+#ifdef USE_NSEC
+		 || ST_MTIME_NSEC(st) != ST_MTIME_NSEC(shallow_stat)
+#endif
+		   )
+		die("shallow file was changed during fetch");
+}

t/t5500-fetch-pack.sh

@@ -135,6 +135,13 @@ test_expect_success 'clone shallow depth 1' '
 	test "`git --git-dir=shallow0/.git rev-list --count HEAD`" = 1
 '
 
+test_expect_success 'clone shallow depth 1 with fsck' '
+	git config --global fetch.fsckobjects true &&
+	git clone --no-single-branch --depth 1 "file://$(pwd)/." shallow0fsck &&
+	test "`git --git-dir=shallow0fsck/.git rev-list --count HEAD`" = 1 &&
+	git config --global --unset fetch.fsckobjects
+'
+
 test_expect_success 'clone shallow' '
 	git clone --no-single-branch --depth 2 "file://$(pwd)/." shallow
 '

transport.c

@@ -534,6 +534,8 @@ static int fetch_refs_via_pack(struct transport *transport,
 	args.quiet = (transport->verbose < 0);
 	args.no_progress = !transport->progress;
 	args.depth = data->options.depth;
+	args.check_self_contained_and_connected =
+		data->options.check_self_contained_and_connected;
 
 	if (!data->got_remote_heads) {
 		connect_setup(transport, 0, 0);
@@ -551,6 +553,8 @@ static int fetch_refs_via_pack(struct transport *transport,
 		refs = NULL;
 	data->conn = NULL;
 	data->got_remote_heads = 0;
+	data->options.self_contained_and_connected =
+		args.self_contained_and_connected;
 
 	free_refs(refs_tmp);
 

transport.h

@@ -8,6 +8,8 @@ struct git_transport_options {
 	unsigned thin : 1;
 	unsigned keep : 1;
 	unsigned followtags : 1;
+	unsigned check_self_contained_and_connected : 1;
+	unsigned self_contained_and_connected : 1;
 	int depth;
 	const char *uploadpack;
 	const char *receivepack;