Merge branch 'nd/fetch-into-shallow' into maint

When there is no sufficient overlap between old and new history
during a "git fetch" into a shallow repository, objects that the
sending side knows the receiving end has were unnecessarily sent.

* nd/fetch-into-shallow:
  Add testcase for needless objects during a shallow fetch
  list-objects: mark more commits as edges in mark_edges_uninteresting
  list-objects: reduce one argument in mark_edges_uninteresting
  upload-pack: delegate rev walking in shallow fetch to pack-objects
  shallow: add setup_temporary_shallow()
  shallow: only add shallow graft points to new shallow file
  move setup_alternate_shallow and write_shallow_commits to shallow.c

12 files changed, 152 insertions, 160 deletions

diff --git a/bisect.c b/bisect.c
index 71c19581da..1e46a4f50e 100644
--- a/bisect.c
+++ b/bisect.c
@@ -624,7 +624,7 @@ static void bisect_common(struct rev_info *revs)
 	if (prepare_revision_walk(revs))
 		die("revision walk setup failed");
 	if (revs->tree_objects)
-		mark_edges_uninteresting(revs->commits, revs, NULL);
+		mark_edges_uninteresting(revs, NULL);
 }
 
 static void exit_if_skipped_commits(struct commit_list *tried,
diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c
index f069462cb0..dd117b379a 100644
--- a/builtin/pack-objects.c
+++ b/builtin/pack-objects.c
@@ -2378,7 +2378,7 @@ static void get_object_list(int ac, const char **av)
 
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed");
-	mark_edges_uninteresting(revs.commits, &revs, show_edge);
+	mark_edges_uninteresting(&revs, show_edge);
 	traverse_commit_list(&revs, show_commit, show_object, NULL);
 
 	if (keep_unreachable)
diff --git a/builtin/rev-list.c b/builtin/rev-list.c
index a5ec30d74e..4fc1616637 100644
--- a/builtin/rev-list.c
+++ b/builtin/rev-list.c
@@ -336,7 +336,7 @@ int cmd_rev_list(int argc, const char **argv, const char *prefix)
 	if (prepare_revision_walk(&revs))
 		die("revision walk setup failed");
 	if (revs.tree_objects)
-		mark_edges_uninteresting(revs.commits, &revs, show_edge);
+		mark_edges_uninteresting(&revs, show_edge);
 
 	if (bisect_list) {
 		int reaches = reaches, all = all;
diff --git a/commit.h b/commit.h
index f9504f70cc..c308674120 100644
--- a/commit.h
+++ b/commit.h
@@ -201,6 +201,10 @@ 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);
+extern int write_shallow_commits(struct strbuf *out, int use_pack_protocol);
+extern void setup_alternate_shallow(struct lock_file *shallow_lock,
+				    const char **alternate_shallow_file);
+extern char *setup_temporary_shallow(void);
 
 int is_descendant_of(struct commit *, struct commit_list *);
 int in_merge_bases(struct commit *, struct commit *);
diff --git a/fetch-pack.c b/fetch-pack.c
index f5d99c1181..aff4f5abab 100644
--- a/fetch-pack.c
+++ b/fetch-pack.c
@@ -184,36 +184,6 @@ static void consume_shallow_list(struct fetch_pack_args *args, int fd)
 	}
 }
 
-struct write_shallow_data {
-	struct strbuf *out;
-	int use_pack_protocol;
-	int count;
-};
-
-static int write_one_shallow(const struct commit_graft *graft, void *cb_data)
-{
-	struct write_shallow_data *data = cb_data;
-	const char *hex = sha1_to_hex(graft->sha1);
-	data->count++;
-	if (data->use_pack_protocol)
-		packet_buf_write(data->out, "shallow %s", hex);
-	else {
-		strbuf_addstr(data->out, hex);
-		strbuf_addch(data->out, '\n');
-	}
-	return 0;
-}
-
-static int write_shallow_commits(struct strbuf *out, int use_pack_protocol)
-{
-	struct write_shallow_data data;
-	data.out = out;
-	data.use_pack_protocol = use_pack_protocol;
-	data.count = 0;
-	for_each_commit_graft(write_one_shallow, &data);
-	return data.count;
-}
-
 static enum ack_type get_ack(int fd, unsigned char *result_sha1)
 {
 	int len;
@@ -795,27 +765,6 @@ 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,
@@ -896,7 +845,7 @@ 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();
+		setup_alternate_shallow(&shallow_lock, &alternate_shallow_file);
 	else
 		alternate_shallow_file = NULL;
 	if (get_pack(args, fd, pack_lockfile))
diff --git a/http-push.c b/http-push.c
index 6dad188b5f..cde6416d37 100644
--- a/http-push.c
+++ b/http-push.c
@@ -1976,7 +1976,7 @@ int main(int argc, char **argv)
 		pushing = 0;
 		if (prepare_revision_walk(&revs))
 			die("revision walk setup failed");
-		mark_edges_uninteresting(revs.commits, &revs, NULL);
+		mark_edges_uninteresting(&revs, NULL);
 		objects_to_send = get_delta(&revs, ref_lock);
 		finish_all_active_slots();
 
diff --git a/list-objects.c b/list-objects.c
index 3dd4a96019..05c8c5c616 100644
--- a/list-objects.c
+++ b/list-objects.c
@@ -145,19 +145,35 @@ static void mark_edge_parents_uninteresting(struct commit *commit,
 	}
 }
 
-void mark_edges_uninteresting(struct commit_list *list,
-			      struct rev_info *revs,
-			      show_edge_fn show_edge)
+void mark_edges_uninteresting(struct rev_info *revs, show_edge_fn show_edge)
 {
-	for ( ; list; list = list->next) {
+	struct commit_list *list;
+	int i;
+
+	for (list = revs->commits; list; list = list->next) {
 		struct commit *commit = list->item;
 
 		if (commit->object.flags & UNINTERESTING) {
 			mark_tree_uninteresting(commit->tree);
+			if (revs->edge_hint && !(commit->object.flags & SHOWN)) {
+				commit->object.flags |= SHOWN;
+				show_edge(commit);
+			}
 			continue;
 		}
 		mark_edge_parents_uninteresting(commit, revs, show_edge);
 	}
+	for (i = 0; i < revs->cmdline.nr; i++) {
+		struct object *obj = revs->cmdline.rev[i].item;
+		struct commit *commit = (struct commit *)obj;
+		if (obj->type != OBJ_COMMIT || !(obj->flags & UNINTERESTING))
+			continue;
+		mark_tree_uninteresting(commit->tree);
+		if (revs->edge_hint && !(obj->flags & SHOWN)) {
+			obj->flags |= SHOWN;
+			show_edge(commit);
+		}
+	}
 }
 
 static void add_pending_tree(struct rev_info *revs, struct tree *tree)
diff --git a/list-objects.h b/list-objects.h
index 3db7bb6fa3..136a1da5a6 100644
--- a/list-objects.h
+++ b/list-objects.h
@@ -6,6 +6,6 @@ typedef void (*show_object_fn)(struct object *, const struct name_path *, const
 void traverse_commit_list(struct rev_info *, show_commit_fn, show_object_fn, void *);
 
 typedef void (*show_edge_fn)(struct commit *);
-void mark_edges_uninteresting(struct commit_list *, struct rev_info *, show_edge_fn);
+void mark_edges_uninteresting(struct rev_info *, show_edge_fn);
 
 #endif
diff --git a/shallow.c b/shallow.c
index 8a9c96d019..cdf37d694d 100644
--- a/shallow.c
+++ b/shallow.c
@@ -1,6 +1,7 @@
 #include "cache.h"
 #include "commit.h"
 #include "tag.h"
+#include "pkt-line.h"
 
 static int is_shallow = -1;
 static struct stat shallow_stat;
@@ -141,3 +142,81 @@ void check_shallow_file_for_update(void)
 		   )
 		die("shallow file was changed during fetch");
 }
+
+struct write_shallow_data {
+	struct strbuf *out;
+	int use_pack_protocol;
+	int count;
+};
+
+static int write_one_shallow(const struct commit_graft *graft, void *cb_data)
+{
+	struct write_shallow_data *data = cb_data;
+	const char *hex = sha1_to_hex(graft->sha1);
+	if (graft->nr_parent != -1)
+		return 0;
+	data->count++;
+	if (data->use_pack_protocol)
+		packet_buf_write(data->out, "shallow %s", hex);
+	else {
+		strbuf_addstr(data->out, hex);
+		strbuf_addch(data->out, '\n');
+	}
+	return 0;
+}
+
+int write_shallow_commits(struct strbuf *out, int use_pack_protocol)
+{
+	struct write_shallow_data data;
+	data.out = out;
+	data.use_pack_protocol = use_pack_protocol;
+	data.count = 0;
+	for_each_commit_graft(write_one_shallow, &data);
+	return data.count;
+}
+
+char *setup_temporary_shallow(void)
+{
+	struct strbuf sb = STRBUF_INIT;
+	int fd;
+
+	if (write_shallow_commits(&sb, 0)) {
+		struct strbuf path = STRBUF_INIT;
+		strbuf_addstr(&path, git_path("shallow_XXXXXX"));
+		fd = xmkstemp(path.buf);
+		if (write_in_full(fd, sb.buf, sb.len) != sb.len)
+			die_errno("failed to write to %s",
+				  path.buf);
+		close(fd);
+		strbuf_release(&sb);
+		return strbuf_detach(&path, NULL);
+	}
+	/*
+	 * is_repository_shallow() sees empty string as "no shallow
+	 * file".
+	 */
+	return xstrdup("");
+}
+
+void setup_alternate_shallow(struct lock_file *shallow_lock,
+			     const char **alternate_shallow_file)
+{
+	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);
+}
diff --git a/t/t5500-fetch-pack.sh b/t/t5500-fetch-pack.sh
index a80584ea0e..d87ddf73b7 100755
--- a/t/t5500-fetch-pack.sh
+++ b/t/t5500-fetch-pack.sh
@@ -393,6 +393,17 @@ test_expect_success 'fetch in shallow repo unreachable shallow objects' '
 		git fsck --no-dangling
 	)
 '
+test_expect_success 'fetch creating new shallow root' '
+	(
+		git clone "file://$(pwd)/." shallow10 &&
+		git commit --allow-empty -m empty &&
+		cd shallow10 &&
+		git fetch --depth=1 --progress 2>actual &&
+		# This should fetch only the empty commit, no tree or
+		# blob objects
+		grep "remote: Total 1" actual
+	)
+'
 
 test_expect_success 'setup tests for the --stdin parameter' '
 	for head in C D E F
diff --git a/t/t5530-upload-pack-error.sh b/t/t5530-upload-pack-error.sh
index c983d3694c..3932e797f7 100755
--- a/t/t5530-upload-pack-error.sh
+++ b/t/t5530-upload-pack-error.sh
@@ -54,9 +54,6 @@ test_expect_success 'upload-pack fails due to error in rev-list' '
 	printf "0032want %s\n0034shallow %s00000009done\n0000" \
 		$(git rev-parse HEAD) $(git rev-parse HEAD^) >input &&
 	test_must_fail git upload-pack . <input >/dev/null 2>output.err &&
-	# pack-objects survived
-	grep "Total.*, reused" output.err &&
-	# but there was an error, which must have been in rev-list
 	grep "bad tree object" output.err
 '
 
diff --git a/upload-pack.c b/upload-pack.c
index 04a8707bb5..8327dc0b7c 100644
--- a/upload-pack.c
+++ b/upload-pack.c
@@ -69,87 +69,28 @@ static ssize_t send_client_data(int fd, const char *data, ssize_t sz)
 	return sz;
 }
 
-static FILE *pack_pipe = NULL;
-static void show_commit(struct commit *commit, void *data)
-{
-	if (commit->object.flags & BOUNDARY)
-		fputc('-', pack_pipe);
-	if (fputs(sha1_to_hex(commit->object.sha1), pack_pipe) < 0)
-		die("broken output pipe");
-	fputc('\n', pack_pipe);
-	fflush(pack_pipe);
-	free(commit->buffer);
-	commit->buffer = NULL;
-}
-
-static void show_object(struct object *obj,
-			const struct name_path *path, const char *component,
-			void *cb_data)
-{
-	show_object_with_name(pack_pipe, obj, path, component);
-}
-
-static void show_edge(struct commit *commit)
-{
-	fprintf(pack_pipe, "-%s\n", sha1_to_hex(commit->object.sha1));
-}
-
-static int do_rev_list(int in, int out, void *user_data)
-{
-	int i;
-	struct rev_info revs;
-
-	pack_pipe = xfdopen(out, "w");
-	init_revisions(&revs, NULL);
-	revs.tag_objects = 1;
-	revs.tree_objects = 1;
-	revs.blob_objects = 1;
-	if (use_thin_pack)
-		revs.edge_hint = 1;
-
-	for (i = 0; i < want_obj.nr; i++) {
-		struct object *o = want_obj.objects[i].item;
-		/* why??? */
-		o->flags &= ~UNINTERESTING;
-		add_pending_object(&revs, o, NULL);
-	}
-	for (i = 0; i < have_obj.nr; i++) {
-		struct object *o = have_obj.objects[i].item;
-		o->flags |= UNINTERESTING;
-		add_pending_object(&revs, o, NULL);
-	}
-	setup_revisions(0, NULL, &revs, NULL);
-	if (prepare_revision_walk(&revs))
-		die("revision walk setup failed");
-	mark_edges_uninteresting(revs.commits, &revs, show_edge);
-	if (use_thin_pack)
-		for (i = 0; i < extra_edge_obj.nr; i++)
-			fprintf(pack_pipe, "-%s\n", sha1_to_hex(
-					extra_edge_obj.objects[i].item->sha1));
-	traverse_commit_list(&revs, show_commit, show_object, NULL);
-	fflush(pack_pipe);
-	fclose(pack_pipe);
-	return 0;
-}
-
 static void create_pack_file(void)
 {
-	struct async rev_list;
 	struct child_process pack_objects;
 	char data[8193], progress[128];
 	char abort_msg[] = "aborting due to possible repository "
 		"corruption on the remote side.";
 	int buffered = -1;
 	ssize_t sz;
-	const char *argv[10];
-	int arg = 0;
+	const char *argv[12];
+	int i, arg = 0;
+	FILE *pipe_fd;
+	char *shallow_file = NULL;
 
-	argv[arg++] = "pack-objects";
-	if (!shallow_nr) {
-		argv[arg++] = "--revs";
-		if (use_thin_pack)
-			argv[arg++] = "--thin";
+	if (shallow_nr) {
+		shallow_file = setup_temporary_shallow();
+		argv[arg++] = "--shallow-file";
+		argv[arg++] = shallow_file;
 	}
+	argv[arg++] = "pack-objects";
+	argv[arg++] = "--revs";
+	if (use_thin_pack)
+		argv[arg++] = "--thin";
 
 	argv[arg++] = "--stdout";
 	if (!no_progress)
@@ -170,29 +111,21 @@ static void create_pack_file(void)
 	if (start_command(&pack_objects))
 		die("git upload-pack: unable to fork git-pack-objects");
 
-	if (shallow_nr) {
-		memset(&rev_list, 0, sizeof(rev_list));
-		rev_list.proc = do_rev_list;
-		rev_list.out = pack_objects.in;
-		if (start_async(&rev_list))
-			die("git upload-pack: unable to fork git-rev-list");
-	}
-	else {
-		FILE *pipe_fd = xfdopen(pack_objects.in, "w");
-		int i;
-
-		for (i = 0; i < want_obj.nr; i++)
-			fprintf(pipe_fd, "%s\n",
-				sha1_to_hex(want_obj.objects[i].item->sha1));
-		fprintf(pipe_fd, "--not\n");
-		for (i = 0; i < have_obj.nr; i++)
-			fprintf(pipe_fd, "%s\n",
-				sha1_to_hex(have_obj.objects[i].item->sha1));
-		fprintf(pipe_fd, "\n");
-		fflush(pipe_fd);
-		fclose(pipe_fd);
-	}
-
+	pipe_fd = xfdopen(pack_objects.in, "w");
+
+	for (i = 0; i < want_obj.nr; i++)
+		fprintf(pipe_fd, "%s\n",
+			sha1_to_hex(want_obj.objects[i].item->sha1));
+	fprintf(pipe_fd, "--not\n");
+	for (i = 0; i < have_obj.nr; i++)
+		fprintf(pipe_fd, "%s\n",
+			sha1_to_hex(have_obj.objects[i].item->sha1));
+	for (i = 0; i < extra_edge_obj.nr; i++)
+		fprintf(pipe_fd, "%s\n",
+			sha1_to_hex(extra_edge_obj.objects[i].item->sha1));
+	fprintf(pipe_fd, "\n");
+	fflush(pipe_fd);
+	fclose(pipe_fd);
 
 	/* We read from pack_objects.err to capture stderr output for
 	 * progress bar, and pack_objects.out to capture the pack data.
@@ -308,8 +241,11 @@ static void create_pack_file(void)
 		error("git upload-pack: git-pack-objects died with error.");
 		goto fail;
 	}
-	if (shallow_nr && finish_async(&rev_list))
-		goto fail;	/* error was already reported */
+	if (shallow_file) {
+		if (*shallow_file)
+			unlink(shallow_file);
+		free(shallow_file);
+	}
 
 	/* flush the data */
 	if (0 <= buffered) {